1// SPDX-License-Identifier: GPL-2.0
2/* Copyright(c) 1999 - 2018 Intel Corporation. */
3
4#include <linux/types.h>
5#include <linux/module.h>
6#include <linux/pci.h>
7#include <linux/netdevice.h>
8#include <linux/vmalloc.h>
9#include <linux/string.h>
10#include <linux/in.h>
11#include <linux/interrupt.h>
12#include <linux/ip.h>
13#include <linux/tcp.h>
14#include <linux/sctp.h>
15#include <linux/pkt_sched.h>
16#include <linux/ipv6.h>
17#include <linux/slab.h>
18#include <net/checksum.h>
19#include <net/ip6_checksum.h>
20#include <linux/etherdevice.h>
21#include <linux/ethtool.h>
22#include <linux/if.h>
23#include <linux/if_vlan.h>
24#include <linux/if_macvlan.h>
25#include <linux/if_bridge.h>
26#include <linux/prefetch.h>
27#include <linux/bpf.h>
28#include <linux/bpf_trace.h>
29#include <linux/atomic.h>
30#include <linux/numa.h>
31#include <generated/utsrelease.h>
32#include <scsi/fc/fc_fcoe.h>
33#include <net/udp_tunnel.h>
34#include <net/pkt_cls.h>
35#include <net/tc_act/tc_gact.h>
36#include <net/tc_act/tc_mirred.h>
37#include <net/vxlan.h>
38#include <net/mpls.h>
39#include <net/xdp_sock_drv.h>
40#include <net/xfrm.h>
41
42#include "ixgbe.h"
43#include "ixgbe_common.h"
44#include "ixgbe_dcb_82599.h"
45#include "ixgbe_phy.h"
46#include "ixgbe_sriov.h"
47#include "ixgbe_model.h"
48#include "ixgbe_txrx_common.h"
49
50char ixgbe_driver_name[] = "ixgbe";
51static const char ixgbe_driver_string[] =
52			      "Intel(R) 10 Gigabit PCI Express Network Driver";
53#ifdef IXGBE_FCOE
54char ixgbe_default_device_descr[] =
55			      "Intel(R) 10 Gigabit Network Connection";
56#else
57static char ixgbe_default_device_descr[] =
58			      "Intel(R) 10 Gigabit Network Connection";
59#endif
60static const char ixgbe_copyright[] =
61				"Copyright (c) 1999-2016 Intel Corporation.";
62
63static const char ixgbe_overheat_msg[] = "Network adapter has been stopped because it has over heated. Restart the computer. If the problem persists, power off the system and replace the adapter";
64
65static const struct ixgbe_info *ixgbe_info_tbl[] = {
66	[board_82598]		= &ixgbe_82598_info,
67	[board_82599]		= &ixgbe_82599_info,
68	[board_X540]		= &ixgbe_X540_info,
69	[board_X550]		= &ixgbe_X550_info,
70	[board_X550EM_x]	= &ixgbe_X550EM_x_info,
71	[board_x550em_x_fw]	= &ixgbe_x550em_x_fw_info,
72	[board_x550em_a]	= &ixgbe_x550em_a_info,
73	[board_x550em_a_fw]	= &ixgbe_x550em_a_fw_info,
74};
75
76/* ixgbe_pci_tbl - PCI Device ID Table
77 *
78 * Wildcard entries (PCI_ANY_ID) should come last
79 * Last entry must be all 0s
80 *
81 * { Vendor ID, Device ID, SubVendor ID, SubDevice ID,
82 *   Class, Class Mask, private data (not used) }
83 */
84static const struct pci_device_id ixgbe_pci_tbl[] = {
85	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598), board_82598 },
86	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AF_DUAL_PORT), board_82598 },
87	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AF_SINGLE_PORT), board_82598 },
88	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AT), board_82598 },
89	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AT2), board_82598 },
90	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598EB_CX4), board_82598 },
91	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_CX4_DUAL_PORT), board_82598 },
92	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_DA_DUAL_PORT), board_82598 },
93	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_SR_DUAL_PORT_EM), board_82598 },
94	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598EB_XF_LR), board_82598 },
95	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598EB_SFP_LOM), board_82598 },
96	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_BX), board_82598 },
97	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_KX4), board_82599 },
98	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_XAUI_LOM), board_82599 },
99	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_KR), board_82599 },
100	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP), board_82599 },
101	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_EM), board_82599 },
102	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_KX4_MEZZ), board_82599 },
103	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_CX4), board_82599 },
104	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_BACKPLANE_FCOE), board_82599 },
105	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_FCOE), board_82599 },
106	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_T3_LOM), board_82599 },
107	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_COMBO_BACKPLANE), board_82599 },
108	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X540T), board_X540 },
109	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_SF2), board_82599 },
110	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_LS), board_82599 },
111	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_QSFP_SF_QP), board_82599 },
112	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599EN_SFP), board_82599 },
113	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_SF_QP), board_82599 },
114	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X540T1), board_X540 },
115	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550T), board_X550},
116	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550T1), board_X550},
117	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_KX4), board_X550EM_x},
118	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_XFI), board_X550EM_x},
119	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_KR), board_X550EM_x},
120	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_10G_T), board_X550EM_x},
121	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_SFP), board_X550EM_x},
122	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_1G_T), board_x550em_x_fw},
123	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_KR), board_x550em_a },
124	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_KR_L), board_x550em_a },
125	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_SFP_N), board_x550em_a },
126	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_SGMII), board_x550em_a },
127	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_SGMII_L), board_x550em_a },
128	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_10G_T), board_x550em_a},
129	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_SFP), board_x550em_a },
130	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_1G_T), board_x550em_a_fw },
131	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_1G_T_L), board_x550em_a_fw },
132	/* required last entry */
133	{0, }
134};
135MODULE_DEVICE_TABLE(pci, ixgbe_pci_tbl);
136
137#ifdef CONFIG_IXGBE_DCA
138static int ixgbe_notify_dca(struct notifier_block *, unsigned long event,
139			    void *p);
140static struct notifier_block dca_notifier = {
141	.notifier_call = ixgbe_notify_dca,
142	.next          = NULL,
143	.priority      = 0
144};
145#endif
146
147#ifdef CONFIG_PCI_IOV
148static unsigned int max_vfs;
149module_param(max_vfs, uint, 0);
150MODULE_PARM_DESC(max_vfs,
151		 "Maximum number of virtual functions to allocate per physical function - default is zero and maximum value is 63. (Deprecated)");
152#endif /* CONFIG_PCI_IOV */
153
154static unsigned int allow_unsupported_sfp;
155module_param(allow_unsupported_sfp, uint, 0);
156MODULE_PARM_DESC(allow_unsupported_sfp,
157		 "Allow unsupported and untested SFP+ modules on 82599-based adapters");
158
159#define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK)
160static int debug = -1;
161module_param(debug, int, 0);
162MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
163
164MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
165MODULE_DESCRIPTION("Intel(R) 10 Gigabit PCI Express Network Driver");
166MODULE_LICENSE("GPL v2");
167
168static struct workqueue_struct *ixgbe_wq;
169
170static bool ixgbe_check_cfg_remove(struct ixgbe_hw *hw, struct pci_dev *pdev);
171static void ixgbe_watchdog_link_is_down(struct ixgbe_adapter *);
172
173static const struct net_device_ops ixgbe_netdev_ops;
174
175static bool netif_is_ixgbe(struct net_device *dev)
176{
177	return dev && (dev->netdev_ops == &ixgbe_netdev_ops);
178}
179
180static int ixgbe_read_pci_cfg_word_parent(struct ixgbe_adapter *adapter,
181					  u32 reg, u16 *value)
182{
183	struct pci_dev *parent_dev;
184	struct pci_bus *parent_bus;
185
186	parent_bus = adapter->pdev->bus->parent;
187	if (!parent_bus)
188		return -1;
189
190	parent_dev = parent_bus->self;
191	if (!parent_dev)
192		return -1;
193
194	if (!pci_is_pcie(parent_dev))
195		return -1;
196
197	pcie_capability_read_word(parent_dev, reg, value);
198	if (*value == IXGBE_FAILED_READ_CFG_WORD &&
199	    ixgbe_check_cfg_remove(&adapter->hw, parent_dev))
200		return -1;
201	return 0;
202}
203
204static s32 ixgbe_get_parent_bus_info(struct ixgbe_adapter *adapter)
205{
206	struct ixgbe_hw *hw = &adapter->hw;
207	u16 link_status = 0;
208	int err;
209
210	hw->bus.type = ixgbe_bus_type_pci_express;
211
212	/* Get the negotiated link width and speed from PCI config space of the
213	 * parent, as this device is behind a switch
214	 */
215	err = ixgbe_read_pci_cfg_word_parent(adapter, 18, &link_status);
216
217	/* assume caller will handle error case */
218	if (err)
219		return err;
220
221	hw->bus.width = ixgbe_convert_bus_width(link_status);
222	hw->bus.speed = ixgbe_convert_bus_speed(link_status);
223
224	return 0;
225}
226
227/**
228 * ixgbe_check_from_parent - Determine whether PCIe info should come from parent
229 * @hw: hw specific details
230 *
231 * This function is used by probe to determine whether a device's PCI-Express
232 * bandwidth details should be gathered from the parent bus instead of from the
233 * device. Used to ensure that various locations all have the correct device ID
234 * checks.
235 */
236static inline bool ixgbe_pcie_from_parent(struct ixgbe_hw *hw)
237{
238	switch (hw->device_id) {
239	case IXGBE_DEV_ID_82599_SFP_SF_QP:
240	case IXGBE_DEV_ID_82599_QSFP_SF_QP:
241		return true;
242	default:
243		return false;
244	}
245}
246
247static void ixgbe_check_minimum_link(struct ixgbe_adapter *adapter,
248				     int expected_gts)
249{
250	struct ixgbe_hw *hw = &adapter->hw;
251	struct pci_dev *pdev;
252
253	/* Some devices are not connected over PCIe and thus do not negotiate
254	 * speed. These devices do not have valid bus info, and thus any report
255	 * we generate may not be correct.
256	 */
257	if (hw->bus.type == ixgbe_bus_type_internal)
258		return;
259
260	/* determine whether to use the parent device */
261	if (ixgbe_pcie_from_parent(&adapter->hw))
262		pdev = adapter->pdev->bus->parent->self;
263	else
264		pdev = adapter->pdev;
265
266	pcie_print_link_status(pdev);
267}
268
269static void ixgbe_service_event_schedule(struct ixgbe_adapter *adapter)
270{
271	if (!test_bit(__IXGBE_DOWN, &adapter->state) &&
272	    !test_bit(__IXGBE_REMOVING, &adapter->state) &&
273	    !test_and_set_bit(__IXGBE_SERVICE_SCHED, &adapter->state))
274		queue_work(ixgbe_wq, &adapter->service_task);
275}
276
277static void ixgbe_remove_adapter(struct ixgbe_hw *hw)
278{
279	struct ixgbe_adapter *adapter = hw->back;
280
281	if (!hw->hw_addr)
282		return;
283	hw->hw_addr = NULL;
284	e_dev_err("Adapter removed\n");
285	if (test_bit(__IXGBE_SERVICE_INITED, &adapter->state))
286		ixgbe_service_event_schedule(adapter);
287}
288
289static u32 ixgbe_check_remove(struct ixgbe_hw *hw, u32 reg)
290{
291	u8 __iomem *reg_addr;
292	u32 value;
293	int i;
294
295	reg_addr = READ_ONCE(hw->hw_addr);
296	if (ixgbe_removed(reg_addr))
297		return IXGBE_FAILED_READ_REG;
298
299	/* Register read of 0xFFFFFFF can indicate the adapter has been removed,
300	 * so perform several status register reads to determine if the adapter
301	 * has been removed.
302	 */
303	for (i = 0; i < IXGBE_FAILED_READ_RETRIES; i++) {
304		value = readl(reg_addr + IXGBE_STATUS);
305		if (value != IXGBE_FAILED_READ_REG)
306			break;
307		mdelay(3);
308	}
309
310	if (value == IXGBE_FAILED_READ_REG)
311		ixgbe_remove_adapter(hw);
312	else
313		value = readl(reg_addr + reg);
314	return value;
315}
316
317/**
318 * ixgbe_read_reg - Read from device register
319 * @hw: hw specific details
320 * @reg: offset of register to read
321 *
322 * Returns : value read or IXGBE_FAILED_READ_REG if removed
323 *
324 * This function is used to read device registers. It checks for device
325 * removal by confirming any read that returns all ones by checking the
326 * status register value for all ones. This function avoids reading from
327 * the hardware if a removal was previously detected in which case it
328 * returns IXGBE_FAILED_READ_REG (all ones).
329 */
330u32 ixgbe_read_reg(struct ixgbe_hw *hw, u32 reg)
331{
332	u8 __iomem *reg_addr = READ_ONCE(hw->hw_addr);
333	u32 value;
334
335	if (ixgbe_removed(reg_addr))
336		return IXGBE_FAILED_READ_REG;
337	if (unlikely(hw->phy.nw_mng_if_sel &
338		     IXGBE_NW_MNG_IF_SEL_SGMII_ENABLE)) {
339		struct ixgbe_adapter *adapter;
340		int i;
341
342		for (i = 0; i < 200; ++i) {
343			value = readl(reg_addr + IXGBE_MAC_SGMII_BUSY);
344			if (likely(!value))
345				goto writes_completed;
346			if (value == IXGBE_FAILED_READ_REG) {
347				ixgbe_remove_adapter(hw);
348				return IXGBE_FAILED_READ_REG;
349			}
350			udelay(5);
351		}
352
353		adapter = hw->back;
354		e_warn(hw, "register writes incomplete %08x\n", value);
355	}
356
357writes_completed:
358	value = readl(reg_addr + reg);
359	if (unlikely(value == IXGBE_FAILED_READ_REG))
360		value = ixgbe_check_remove(hw, reg);
361	return value;
362}
363
364static bool ixgbe_check_cfg_remove(struct ixgbe_hw *hw, struct pci_dev *pdev)
365{
366	u16 value;
367
368	pci_read_config_word(pdev, PCI_VENDOR_ID, &value);
369	if (value == IXGBE_FAILED_READ_CFG_WORD) {
370		ixgbe_remove_adapter(hw);
371		return true;
372	}
373	return false;
374}
375
376u16 ixgbe_read_pci_cfg_word(struct ixgbe_hw *hw, u32 reg)
377{
378	struct ixgbe_adapter *adapter = hw->back;
379	u16 value;
380
381	if (ixgbe_removed(hw->hw_addr))
382		return IXGBE_FAILED_READ_CFG_WORD;
383	pci_read_config_word(adapter->pdev, reg, &value);
384	if (value == IXGBE_FAILED_READ_CFG_WORD &&
385	    ixgbe_check_cfg_remove(hw, adapter->pdev))
386		return IXGBE_FAILED_READ_CFG_WORD;
387	return value;
388}
389
390#ifdef CONFIG_PCI_IOV
391static u32 ixgbe_read_pci_cfg_dword(struct ixgbe_hw *hw, u32 reg)
392{
393	struct ixgbe_adapter *adapter = hw->back;
394	u32 value;
395
396	if (ixgbe_removed(hw->hw_addr))
397		return IXGBE_FAILED_READ_CFG_DWORD;
398	pci_read_config_dword(adapter->pdev, reg, &value);
399	if (value == IXGBE_FAILED_READ_CFG_DWORD &&
400	    ixgbe_check_cfg_remove(hw, adapter->pdev))
401		return IXGBE_FAILED_READ_CFG_DWORD;
402	return value;
403}
404#endif /* CONFIG_PCI_IOV */
405
406void ixgbe_write_pci_cfg_word(struct ixgbe_hw *hw, u32 reg, u16 value)
407{
408	struct ixgbe_adapter *adapter = hw->back;
409
410	if (ixgbe_removed(hw->hw_addr))
411		return;
412	pci_write_config_word(adapter->pdev, reg, value);
413}
414
415static void ixgbe_service_event_complete(struct ixgbe_adapter *adapter)
416{
417	BUG_ON(!test_bit(__IXGBE_SERVICE_SCHED, &adapter->state));
418
419	/* flush memory to make sure state is correct before next watchdog */
420	smp_mb__before_atomic();
421	clear_bit(__IXGBE_SERVICE_SCHED, &adapter->state);
422}
423
424struct ixgbe_reg_info {
425	u32 ofs;
426	char *name;
427};
428
429static const struct ixgbe_reg_info ixgbe_reg_info_tbl[] = {
430
431	/* General Registers */
432	{IXGBE_CTRL, "CTRL"},
433	{IXGBE_STATUS, "STATUS"},
434	{IXGBE_CTRL_EXT, "CTRL_EXT"},
435
436	/* Interrupt Registers */
437	{IXGBE_EICR, "EICR"},
438
439	/* RX Registers */
440	{IXGBE_SRRCTL(0), "SRRCTL"},
441	{IXGBE_DCA_RXCTRL(0), "DRXCTL"},
442	{IXGBE_RDLEN(0), "RDLEN"},
443	{IXGBE_RDH(0), "RDH"},
444	{IXGBE_RDT(0), "RDT"},
445	{IXGBE_RXDCTL(0), "RXDCTL"},
446	{IXGBE_RDBAL(0), "RDBAL"},
447	{IXGBE_RDBAH(0), "RDBAH"},
448
449	/* TX Registers */
450	{IXGBE_TDBAL(0), "TDBAL"},
451	{IXGBE_TDBAH(0), "TDBAH"},
452	{IXGBE_TDLEN(0), "TDLEN"},
453	{IXGBE_TDH(0), "TDH"},
454	{IXGBE_TDT(0), "TDT"},
455	{IXGBE_TXDCTL(0), "TXDCTL"},
456
457	/* List Terminator */
458	{ .name = NULL }
459};
460
461
462/*
463 * ixgbe_regdump - register printout routine
464 */
465static void ixgbe_regdump(struct ixgbe_hw *hw, struct ixgbe_reg_info *reginfo)
466{
467	int i;
468	char rname[16];
469	u32 regs[64];
470
471	switch (reginfo->ofs) {
472	case IXGBE_SRRCTL(0):
473		for (i = 0; i < 64; i++)
474			regs[i] = IXGBE_READ_REG(hw, IXGBE_SRRCTL(i));
475		break;
476	case IXGBE_DCA_RXCTRL(0):
477		for (i = 0; i < 64; i++)
478			regs[i] = IXGBE_READ_REG(hw, IXGBE_DCA_RXCTRL(i));
479		break;
480	case IXGBE_RDLEN(0):
481		for (i = 0; i < 64; i++)
482			regs[i] = IXGBE_READ_REG(hw, IXGBE_RDLEN(i));
483		break;
484	case IXGBE_RDH(0):
485		for (i = 0; i < 64; i++)
486			regs[i] = IXGBE_READ_REG(hw, IXGBE_RDH(i));
487		break;
488	case IXGBE_RDT(0):
489		for (i = 0; i < 64; i++)
490			regs[i] = IXGBE_READ_REG(hw, IXGBE_RDT(i));
491		break;
492	case IXGBE_RXDCTL(0):
493		for (i = 0; i < 64; i++)
494			regs[i] = IXGBE_READ_REG(hw, IXGBE_RXDCTL(i));
495		break;
496	case IXGBE_RDBAL(0):
497		for (i = 0; i < 64; i++)
498			regs[i] = IXGBE_READ_REG(hw, IXGBE_RDBAL(i));
499		break;
500	case IXGBE_RDBAH(0):
501		for (i = 0; i < 64; i++)
502			regs[i] = IXGBE_READ_REG(hw, IXGBE_RDBAH(i));
503		break;
504	case IXGBE_TDBAL(0):
505		for (i = 0; i < 64; i++)
506			regs[i] = IXGBE_READ_REG(hw, IXGBE_TDBAL(i));
507		break;
508	case IXGBE_TDBAH(0):
509		for (i = 0; i < 64; i++)
510			regs[i] = IXGBE_READ_REG(hw, IXGBE_TDBAH(i));
511		break;
512	case IXGBE_TDLEN(0):
513		for (i = 0; i < 64; i++)
514			regs[i] = IXGBE_READ_REG(hw, IXGBE_TDLEN(i));
515		break;
516	case IXGBE_TDH(0):
517		for (i = 0; i < 64; i++)
518			regs[i] = IXGBE_READ_REG(hw, IXGBE_TDH(i));
519		break;
520	case IXGBE_TDT(0):
521		for (i = 0; i < 64; i++)
522			regs[i] = IXGBE_READ_REG(hw, IXGBE_TDT(i));
523		break;
524	case IXGBE_TXDCTL(0):
525		for (i = 0; i < 64; i++)
526			regs[i] = IXGBE_READ_REG(hw, IXGBE_TXDCTL(i));
527		break;
528	default:
529		pr_info("%-15s %08x\n",
530			reginfo->name, IXGBE_READ_REG(hw, reginfo->ofs));
531		return;
532	}
533
534	i = 0;
535	while (i < 64) {
536		int j;
537		char buf[9 * 8 + 1];
538		char *p = buf;
539
540		snprintf(rname, 16, "%s[%d-%d]", reginfo->name, i, i + 7);
541		for (j = 0; j < 8; j++)
542			p += sprintf(p, " %08x", regs[i++]);
543		pr_err("%-15s%s\n", rname, buf);
544	}
545
546}
547
548static void ixgbe_print_buffer(struct ixgbe_ring *ring, int n)
549{
550	struct ixgbe_tx_buffer *tx_buffer;
551
552	tx_buffer = &ring->tx_buffer_info[ring->next_to_clean];
553	pr_info(" %5d %5X %5X %016llX %08X %p %016llX\n",
554		n, ring->next_to_use, ring->next_to_clean,
555		(u64)dma_unmap_addr(tx_buffer, dma),
556		dma_unmap_len(tx_buffer, len),
557		tx_buffer->next_to_watch,
558		(u64)tx_buffer->time_stamp);
559}
560
561/*
562 * ixgbe_dump - Print registers, tx-rings and rx-rings
563 */
564static void ixgbe_dump(struct ixgbe_adapter *adapter)
565{
566	struct net_device *netdev = adapter->netdev;
567	struct ixgbe_hw *hw = &adapter->hw;
568	struct ixgbe_reg_info *reginfo;
569	int n = 0;
570	struct ixgbe_ring *ring;
571	struct ixgbe_tx_buffer *tx_buffer;
572	union ixgbe_adv_tx_desc *tx_desc;
573	struct my_u0 { u64 a; u64 b; } *u0;
574	struct ixgbe_ring *rx_ring;
575	union ixgbe_adv_rx_desc *rx_desc;
576	struct ixgbe_rx_buffer *rx_buffer_info;
577	int i = 0;
578
579	if (!netif_msg_hw(adapter))
580		return;
581
582	/* Print netdevice Info */
583	if (netdev) {
584		dev_info(&adapter->pdev->dev, "Net device Info\n");
585		pr_info("Device Name     state            "
586			"trans_start\n");
587		pr_info("%-15s %016lX %016lX\n",
588			netdev->name,
589			netdev->state,
590			dev_trans_start(netdev));
591	}
592
593	/* Print Registers */
594	dev_info(&adapter->pdev->dev, "Register Dump\n");
595	pr_info(" Register Name   Value\n");
596	for (reginfo = (struct ixgbe_reg_info *)ixgbe_reg_info_tbl;
597	     reginfo->name; reginfo++) {
598		ixgbe_regdump(hw, reginfo);
599	}
600
601	/* Print TX Ring Summary */
602	if (!netdev || !netif_running(netdev))
603		return;
604
605	dev_info(&adapter->pdev->dev, "TX Rings Summary\n");
606	pr_info(" %s     %s              %s        %s\n",
607		"Queue [NTU] [NTC] [bi(ntc)->dma  ]",
608		"leng", "ntw", "timestamp");
609	for (n = 0; n < adapter->num_tx_queues; n++) {
610		ring = adapter->tx_ring[n];
611		ixgbe_print_buffer(ring, n);
612	}
613
614	for (n = 0; n < adapter->num_xdp_queues; n++) {
615		ring = adapter->xdp_ring[n];
616		ixgbe_print_buffer(ring, n);
617	}
618
619	/* Print TX Rings */
620	if (!netif_msg_tx_done(adapter))
621		goto rx_ring_summary;
622
623	dev_info(&adapter->pdev->dev, "TX Rings Dump\n");
624
625	/* Transmit Descriptor Formats
626	 *
627	 * 82598 Advanced Transmit Descriptor
628	 *   +--------------------------------------------------------------+
629	 * 0 |         Buffer Address [63:0]                                |
630	 *   +--------------------------------------------------------------+
631	 * 8 |  PAYLEN  | POPTS  | IDX | STA | DCMD  |DTYP |  RSV |  DTALEN |
632	 *   +--------------------------------------------------------------+
633	 *   63       46 45    40 39 36 35 32 31   24 23 20 19              0
634	 *
635	 * 82598 Advanced Transmit Descriptor (Write-Back Format)
636	 *   +--------------------------------------------------------------+
637	 * 0 |                          RSV [63:0]                          |
638	 *   +--------------------------------------------------------------+
639	 * 8 |            RSV           |  STA  |          NXTSEQ           |
640	 *   +--------------------------------------------------------------+
641	 *   63                       36 35   32 31                         0
642	 *
643	 * 82599+ Advanced Transmit Descriptor
644	 *   +--------------------------------------------------------------+
645	 * 0 |         Buffer Address [63:0]                                |
646	 *   +--------------------------------------------------------------+
647	 * 8 |PAYLEN  |POPTS|CC|IDX  |STA  |DCMD  |DTYP |MAC  |RSV  |DTALEN |
648	 *   +--------------------------------------------------------------+
649	 *   63     46 45 40 39 38 36 35 32 31  24 23 20 19 18 17 16 15     0
650	 *
651	 * 82599+ Advanced Transmit Descriptor (Write-Back Format)
652	 *   +--------------------------------------------------------------+
653	 * 0 |                          RSV [63:0]                          |
654	 *   +--------------------------------------------------------------+
655	 * 8 |            RSV           |  STA  |           RSV             |
656	 *   +--------------------------------------------------------------+
657	 *   63                       36 35   32 31                         0
658	 */
659
660	for (n = 0; n < adapter->num_tx_queues; n++) {
661		ring = adapter->tx_ring[n];
662		pr_info("------------------------------------\n");
663		pr_info("TX QUEUE INDEX = %d\n", ring->queue_index);
664		pr_info("------------------------------------\n");
665		pr_info("%s%s    %s              %s        %s          %s\n",
666			"T [desc]     [address 63:0  ] ",
667			"[PlPOIdStDDt Ln] [bi->dma       ] ",
668			"leng", "ntw", "timestamp", "bi->skb");
669
670		for (i = 0; ring->desc && (i < ring->count); i++) {
671			tx_desc = IXGBE_TX_DESC(ring, i);
672			tx_buffer = &ring->tx_buffer_info[i];
673			u0 = (struct my_u0 *)tx_desc;
674			if (dma_unmap_len(tx_buffer, len) > 0) {
675				const char *ring_desc;
676
677				if (i == ring->next_to_use &&
678				    i == ring->next_to_clean)
679					ring_desc = " NTC/U";
680				else if (i == ring->next_to_use)
681					ring_desc = " NTU";
682				else if (i == ring->next_to_clean)
683					ring_desc = " NTC";
684				else
685					ring_desc = "";
686				pr_info("T [0x%03X]    %016llX %016llX %016llX %08X %p %016llX %p%s",
687					i,
688					le64_to_cpu((__force __le64)u0->a),
689					le64_to_cpu((__force __le64)u0->b),
690					(u64)dma_unmap_addr(tx_buffer, dma),
691					dma_unmap_len(tx_buffer, len),
692					tx_buffer->next_to_watch,
693					(u64)tx_buffer->time_stamp,
694					tx_buffer->skb,
695					ring_desc);
696
697				if (netif_msg_pktdata(adapter) &&
698				    tx_buffer->skb)
699					print_hex_dump(KERN_INFO, "",
700						DUMP_PREFIX_ADDRESS, 16, 1,
701						tx_buffer->skb->data,
702						dma_unmap_len(tx_buffer, len),
703						true);
704			}
705		}
706	}
707
708	/* Print RX Rings Summary */
709rx_ring_summary:
710	dev_info(&adapter->pdev->dev, "RX Rings Summary\n");
711	pr_info("Queue [NTU] [NTC]\n");
712	for (n = 0; n < adapter->num_rx_queues; n++) {
713		rx_ring = adapter->rx_ring[n];
714		pr_info("%5d %5X %5X\n",
715			n, rx_ring->next_to_use, rx_ring->next_to_clean);
716	}
717
718	/* Print RX Rings */
719	if (!netif_msg_rx_status(adapter))
720		return;
721
722	dev_info(&adapter->pdev->dev, "RX Rings Dump\n");
723
724	/* Receive Descriptor Formats
725	 *
726	 * 82598 Advanced Receive Descriptor (Read) Format
727	 *    63                                           1        0
728	 *    +-----------------------------------------------------+
729	 *  0 |       Packet Buffer Address [63:1]           |A0/NSE|
730	 *    +----------------------------------------------+------+
731	 *  8 |       Header Buffer Address [63:1]           |  DD  |
732	 *    +-----------------------------------------------------+
733	 *
734	 *
735	 * 82598 Advanced Receive Descriptor (Write-Back) Format
736	 *
737	 *   63       48 47    32 31  30      21 20 16 15   4 3     0
738	 *   +------------------------------------------------------+
739	 * 0 |       RSS Hash /  |SPH| HDR_LEN  | RSV |Packet|  RSS |
740	 *   | Packet   | IP     |   |          |     | Type | Type |
741	 *   | Checksum | Ident  |   |          |     |      |      |
742	 *   +------------------------------------------------------+
743	 * 8 | VLAN Tag | Length | Extended Error | Extended Status |
744	 *   +------------------------------------------------------+
745	 *   63       48 47    32 31            20 19               0
746	 *
747	 * 82599+ Advanced Receive Descriptor (Read) Format
748	 *    63                                           1        0
749	 *    +-----------------------------------------------------+
750	 *  0 |       Packet Buffer Address [63:1]           |A0/NSE|
751	 *    +----------------------------------------------+------+
752	 *  8 |       Header Buffer Address [63:1]           |  DD  |
753	 *    +-----------------------------------------------------+
754	 *
755	 *
756	 * 82599+ Advanced Receive Descriptor (Write-Back) Format
757	 *
758	 *   63       48 47    32 31  30      21 20 17 16   4 3     0
759	 *   +------------------------------------------------------+
760	 * 0 |RSS / Frag Checksum|SPH| HDR_LEN  |RSC- |Packet|  RSS |
761	 *   |/ RTT / PCoE_PARAM |   |          | CNT | Type | Type |
762	 *   |/ Flow Dir Flt ID  |   |          |     |      |      |
763	 *   +------------------------------------------------------+
764	 * 8 | VLAN Tag | Length |Extended Error| Xtnd Status/NEXTP |
765	 *   +------------------------------------------------------+
766	 *   63       48 47    32 31          20 19                 0
767	 */
768
769	for (n = 0; n < adapter->num_rx_queues; n++) {
770		rx_ring = adapter->rx_ring[n];
771		pr_info("------------------------------------\n");
772		pr_info("RX QUEUE INDEX = %d\n", rx_ring->queue_index);
773		pr_info("------------------------------------\n");
774		pr_info("%s%s%s\n",
775			"R  [desc]      [ PktBuf     A0] ",
776			"[  HeadBuf   DD] [bi->dma       ] [bi->skb       ] ",
777			"<-- Adv Rx Read format");
778		pr_info("%s%s%s\n",
779			"RWB[desc]      [PcsmIpSHl PtRs] ",
780			"[vl er S cks ln] ---------------- [bi->skb       ] ",
781			"<-- Adv Rx Write-Back format");
782
783		for (i = 0; i < rx_ring->count; i++) {
784			const char *ring_desc;
785
786			if (i == rx_ring->next_to_use)
787				ring_desc = " NTU";
788			else if (i == rx_ring->next_to_clean)
789				ring_desc = " NTC";
790			else
791				ring_desc = "";
792
793			rx_buffer_info = &rx_ring->rx_buffer_info[i];
794			rx_desc = IXGBE_RX_DESC(rx_ring, i);
795			u0 = (struct my_u0 *)rx_desc;
796			if (rx_desc->wb.upper.length) {
797				/* Descriptor Done */
798				pr_info("RWB[0x%03X]     %016llX %016llX ---------------- %p%s\n",
799					i,
800					le64_to_cpu((__force __le64)u0->a),
801					le64_to_cpu((__force __le64)u0->b),
802					rx_buffer_info->skb,
803					ring_desc);
804			} else {
805				pr_info("R  [0x%03X]     %016llX %016llX %016llX %p%s\n",
806					i,
807					le64_to_cpu((__force __le64)u0->a),
808					le64_to_cpu((__force __le64)u0->b),
809					(u64)rx_buffer_info->dma,
810					rx_buffer_info->skb,
811					ring_desc);
812
813				if (netif_msg_pktdata(adapter) &&
814				    rx_buffer_info->dma) {
815					print_hex_dump(KERN_INFO, "",
816					   DUMP_PREFIX_ADDRESS, 16, 1,
817					   page_address(rx_buffer_info->page) +
818						    rx_buffer_info->page_offset,
819					   ixgbe_rx_bufsz(rx_ring), true);
820				}
821			}
822		}
823	}
824}
825
826static void ixgbe_release_hw_control(struct ixgbe_adapter *adapter)
827{
828	u32 ctrl_ext;
829
830	/* Let firmware take over control of h/w */
831	ctrl_ext = IXGBE_READ_REG(&adapter->hw, IXGBE_CTRL_EXT);
832	IXGBE_WRITE_REG(&adapter->hw, IXGBE_CTRL_EXT,
833			ctrl_ext & ~IXGBE_CTRL_EXT_DRV_LOAD);
834}
835
836static void ixgbe_get_hw_control(struct ixgbe_adapter *adapter)
837{
838	u32 ctrl_ext;
839
840	/* Let firmware know the driver has taken over */
841	ctrl_ext = IXGBE_READ_REG(&adapter->hw, IXGBE_CTRL_EXT);
842	IXGBE_WRITE_REG(&adapter->hw, IXGBE_CTRL_EXT,
843			ctrl_ext | IXGBE_CTRL_EXT_DRV_LOAD);
844}
845
846/**
847 * ixgbe_set_ivar - set the IVAR registers, mapping interrupt causes to vectors
848 * @adapter: pointer to adapter struct
849 * @direction: 0 for Rx, 1 for Tx, -1 for other causes
850 * @queue: queue to map the corresponding interrupt to
851 * @msix_vector: the vector to map to the corresponding queue
852 *
853 */
854static void ixgbe_set_ivar(struct ixgbe_adapter *adapter, s8 direction,
855			   u8 queue, u8 msix_vector)
856{
857	u32 ivar, index;
858	struct ixgbe_hw *hw = &adapter->hw;
859	switch (hw->mac.type) {
860	case ixgbe_mac_82598EB:
861		msix_vector |= IXGBE_IVAR_ALLOC_VAL;
862		if (direction == -1)
863			direction = 0;
864		index = (((direction * 64) + queue) >> 2) & 0x1F;
865		ivar = IXGBE_READ_REG(hw, IXGBE_IVAR(index));
866		ivar &= ~(0xFF << (8 * (queue & 0x3)));
867		ivar |= (msix_vector << (8 * (queue & 0x3)));
868		IXGBE_WRITE_REG(hw, IXGBE_IVAR(index), ivar);
869		break;
870	case ixgbe_mac_82599EB:
871	case ixgbe_mac_X540:
872	case ixgbe_mac_X550:
873	case ixgbe_mac_X550EM_x:
874	case ixgbe_mac_x550em_a:
875		if (direction == -1) {
876			/* other causes */
877			msix_vector |= IXGBE_IVAR_ALLOC_VAL;
878			index = ((queue & 1) * 8);
879			ivar = IXGBE_READ_REG(&adapter->hw, IXGBE_IVAR_MISC);
880			ivar &= ~(0xFF << index);
881			ivar |= (msix_vector << index);
882			IXGBE_WRITE_REG(&adapter->hw, IXGBE_IVAR_MISC, ivar);
883			break;
884		} else {
885			/* tx or rx causes */
886			msix_vector |= IXGBE_IVAR_ALLOC_VAL;
887			index = ((16 * (queue & 1)) + (8 * direction));
888			ivar = IXGBE_READ_REG(hw, IXGBE_IVAR(queue >> 1));
889			ivar &= ~(0xFF << index);
890			ivar |= (msix_vector << index);
891			IXGBE_WRITE_REG(hw, IXGBE_IVAR(queue >> 1), ivar);
892			break;
893		}
894	default:
895		break;
896	}
897}
898
899void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter,
900			    u64 qmask)
901{
902	u32 mask;
903
904	switch (adapter->hw.mac.type) {
905	case ixgbe_mac_82598EB:
906		mask = (IXGBE_EIMS_RTX_QUEUE & qmask);
907		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS, mask);
908		break;
909	case ixgbe_mac_82599EB:
910	case ixgbe_mac_X540:
911	case ixgbe_mac_X550:
912	case ixgbe_mac_X550EM_x:
913	case ixgbe_mac_x550em_a:
914		mask = (qmask & 0xFFFFFFFF);
915		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS_EX(0), mask);
916		mask = (qmask >> 32);
917		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS_EX(1), mask);
918		break;
919	default:
920		break;
921	}
922}
923
924static void ixgbe_update_xoff_rx_lfc(struct ixgbe_adapter *adapter)
925{
926	struct ixgbe_hw *hw = &adapter->hw;
927	struct ixgbe_hw_stats *hwstats = &adapter->stats;
928	int i;
929	u32 data;
930
931	if ((hw->fc.current_mode != ixgbe_fc_full) &&
932	    (hw->fc.current_mode != ixgbe_fc_rx_pause))
933		return;
934
935	switch (hw->mac.type) {
936	case ixgbe_mac_82598EB:
937		data = IXGBE_READ_REG(hw, IXGBE_LXOFFRXC);
938		break;
939	default:
940		data = IXGBE_READ_REG(hw, IXGBE_LXOFFRXCNT);
941	}
942	hwstats->lxoffrxc += data;
943
944	/* refill credits (no tx hang) if we received xoff */
945	if (!data)
946		return;
947
948	for (i = 0; i < adapter->num_tx_queues; i++)
949		clear_bit(__IXGBE_HANG_CHECK_ARMED,
950			  &adapter->tx_ring[i]->state);
951
952	for (i = 0; i < adapter->num_xdp_queues; i++)
953		clear_bit(__IXGBE_HANG_CHECK_ARMED,
954			  &adapter->xdp_ring[i]->state);
955}
956
957static void ixgbe_update_xoff_received(struct ixgbe_adapter *adapter)
958{
959	struct ixgbe_hw *hw = &adapter->hw;
960	struct ixgbe_hw_stats *hwstats = &adapter->stats;
961	u32 xoff[8] = {0};
962	u8 tc;
963	int i;
964	bool pfc_en = adapter->dcb_cfg.pfc_mode_enable;
965
966	if (adapter->ixgbe_ieee_pfc)
967		pfc_en |= !!(adapter->ixgbe_ieee_pfc->pfc_en);
968
969	if (!(adapter->flags & IXGBE_FLAG_DCB_ENABLED) || !pfc_en) {
970		ixgbe_update_xoff_rx_lfc(adapter);
971		return;
972	}
973
974	/* update stats for each tc, only valid with PFC enabled */
975	for (i = 0; i < MAX_TX_PACKET_BUFFERS; i++) {
976		u32 pxoffrxc;
977
978		switch (hw->mac.type) {
979		case ixgbe_mac_82598EB:
980			pxoffrxc = IXGBE_READ_REG(hw, IXGBE_PXOFFRXC(i));
981			break;
982		default:
983			pxoffrxc = IXGBE_READ_REG(hw, IXGBE_PXOFFRXCNT(i));
984		}
985		hwstats->pxoffrxc[i] += pxoffrxc;
986		/* Get the TC for given UP */
987		tc = netdev_get_prio_tc_map(adapter->netdev, i);
988		xoff[tc] += pxoffrxc;
989	}
990
991	/* disarm tx queues that have received xoff frames */
992	for (i = 0; i < adapter->num_tx_queues; i++) {
993		struct ixgbe_ring *tx_ring = adapter->tx_ring[i];
994
995		tc = tx_ring->dcb_tc;
996		if (xoff[tc])
997			clear_bit(__IXGBE_HANG_CHECK_ARMED, &tx_ring->state);
998	}
999
1000	for (i = 0; i < adapter->num_xdp_queues; i++) {
1001		struct ixgbe_ring *xdp_ring = adapter->xdp_ring[i];
1002
1003		tc = xdp_ring->dcb_tc;
1004		if (xoff[tc])
1005			clear_bit(__IXGBE_HANG_CHECK_ARMED, &xdp_ring->state);
1006	}
1007}
1008
1009static u64 ixgbe_get_tx_completed(struct ixgbe_ring *ring)
1010{
1011	return ring->stats.packets;
1012}
1013
1014static u64 ixgbe_get_tx_pending(struct ixgbe_ring *ring)
1015{
1016	unsigned int head, tail;
1017
1018	head = ring->next_to_clean;
1019	tail = ring->next_to_use;
1020
1021	return ((head <= tail) ? tail : tail + ring->count) - head;
1022}
1023
1024static inline bool ixgbe_check_tx_hang(struct ixgbe_ring *tx_ring)
1025{
1026	u32 tx_done = ixgbe_get_tx_completed(tx_ring);
1027	u32 tx_done_old = tx_ring->tx_stats.tx_done_old;
1028	u32 tx_pending = ixgbe_get_tx_pending(tx_ring);
1029
1030	clear_check_for_tx_hang(tx_ring);
1031
1032	/*
1033	 * Check for a hung queue, but be thorough. This verifies
1034	 * that a transmit has been completed since the previous
1035	 * check AND there is at least one packet pending. The
1036	 * ARMED bit is set to indicate a potential hang. The
1037	 * bit is cleared if a pause frame is received to remove
1038	 * false hang detection due to PFC or 802.3x frames. By
1039	 * requiring this to fail twice we avoid races with
1040	 * pfc clearing the ARMED bit and conditions where we
1041	 * run the check_tx_hang logic with a transmit completion
1042	 * pending but without time to complete it yet.
1043	 */
1044	if (tx_done_old == tx_done && tx_pending)
1045		/* make sure it is true for two checks in a row */
1046		return test_and_set_bit(__IXGBE_HANG_CHECK_ARMED,
1047					&tx_ring->state);
1048	/* update completed stats and continue */
1049	tx_ring->tx_stats.tx_done_old = tx_done;
1050	/* reset the countdown */
1051	clear_bit(__IXGBE_HANG_CHECK_ARMED, &tx_ring->state);
1052
1053	return false;
1054}
1055
1056/**
1057 * ixgbe_tx_timeout_reset - initiate reset due to Tx timeout
1058 * @adapter: driver private struct
1059 **/
1060static void ixgbe_tx_timeout_reset(struct ixgbe_adapter *adapter)
1061{
1062
1063	/* Do the reset outside of interrupt context */
1064	if (!test_bit(__IXGBE_DOWN, &adapter->state)) {
1065		set_bit(__IXGBE_RESET_REQUESTED, &adapter->state);
1066		e_warn(drv, "initiating reset due to tx timeout\n");
1067		ixgbe_service_event_schedule(adapter);
1068	}
1069}
1070
1071/**
1072 * ixgbe_tx_maxrate - callback to set the maximum per-queue bitrate
1073 * @netdev: network interface device structure
1074 * @queue_index: Tx queue to set
1075 * @maxrate: desired maximum transmit bitrate
1076 **/
1077static int ixgbe_tx_maxrate(struct net_device *netdev,
1078			    int queue_index, u32 maxrate)
1079{
1080	struct ixgbe_adapter *adapter = netdev_priv(netdev);
1081	struct ixgbe_hw *hw = &adapter->hw;
1082	u32 bcnrc_val = ixgbe_link_mbps(adapter);
1083
1084	if (!maxrate)
1085		return 0;
1086
1087	/* Calculate the rate factor values to set */
1088	bcnrc_val <<= IXGBE_RTTBCNRC_RF_INT_SHIFT;
1089	bcnrc_val /= maxrate;
1090
1091	/* clear everything but the rate factor */
1092	bcnrc_val &= IXGBE_RTTBCNRC_RF_INT_MASK |
1093	IXGBE_RTTBCNRC_RF_DEC_MASK;
1094
1095	/* enable the rate scheduler */
1096	bcnrc_val |= IXGBE_RTTBCNRC_RS_ENA;
1097
1098	IXGBE_WRITE_REG(hw, IXGBE_RTTDQSEL, queue_index);
1099	IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRC, bcnrc_val);
1100
1101	return 0;
1102}
1103
1104/**
1105 * ixgbe_clean_tx_irq - Reclaim resources after transmit completes
1106 * @q_vector: structure containing interrupt and ring information
1107 * @tx_ring: tx ring to clean
1108 * @napi_budget: Used to determine if we are in netpoll
1109 **/
1110static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
1111			       struct ixgbe_ring *tx_ring, int napi_budget)
1112{
1113	struct ixgbe_adapter *adapter = q_vector->adapter;
1114	struct ixgbe_tx_buffer *tx_buffer;
1115	union ixgbe_adv_tx_desc *tx_desc;
1116	unsigned int total_bytes = 0, total_packets = 0, total_ipsec = 0;
1117	unsigned int budget = q_vector->tx.work_limit;
1118	unsigned int i = tx_ring->next_to_clean;
1119
1120	if (test_bit(__IXGBE_DOWN, &adapter->state))
1121		return true;
1122
1123	tx_buffer = &tx_ring->tx_buffer_info[i];
1124	tx_desc = IXGBE_TX_DESC(tx_ring, i);
1125	i -= tx_ring->count;
1126
1127	do {
1128		union ixgbe_adv_tx_desc *eop_desc = tx_buffer->next_to_watch;
1129
1130		/* if next_to_watch is not set then there is no work pending */
1131		if (!eop_desc)
1132			break;
1133
1134		/* prevent any other reads prior to eop_desc */
1135		smp_rmb();
1136
1137		/* if DD is not set pending work has not been completed */
1138		if (!(eop_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD)))
1139			break;
1140
1141		/* clear next_to_watch to prevent false hangs */
1142		tx_buffer->next_to_watch = NULL;
1143
1144		/* update the statistics for this packet */
1145		total_bytes += tx_buffer->bytecount;
1146		total_packets += tx_buffer->gso_segs;
1147		if (tx_buffer->tx_flags & IXGBE_TX_FLAGS_IPSEC)
1148			total_ipsec++;
1149
1150		/* free the skb */
1151		if (ring_is_xdp(tx_ring))
1152			xdp_return_frame(tx_buffer->xdpf);
1153		else
1154			napi_consume_skb(tx_buffer->skb, napi_budget);
1155
1156		/* unmap skb header data */
1157		dma_unmap_single(tx_ring->dev,
1158				 dma_unmap_addr(tx_buffer, dma),
1159				 dma_unmap_len(tx_buffer, len),
1160				 DMA_TO_DEVICE);
1161
1162		/* clear tx_buffer data */
1163		dma_unmap_len_set(tx_buffer, len, 0);
1164
1165		/* unmap remaining buffers */
1166		while (tx_desc != eop_desc) {
1167			tx_buffer++;
1168			tx_desc++;
1169			i++;
1170			if (unlikely(!i)) {
1171				i -= tx_ring->count;
1172				tx_buffer = tx_ring->tx_buffer_info;
1173				tx_desc = IXGBE_TX_DESC(tx_ring, 0);
1174			}
1175
1176			/* unmap any remaining paged data */
1177			if (dma_unmap_len(tx_buffer, len)) {
1178				dma_unmap_page(tx_ring->dev,
1179					       dma_unmap_addr(tx_buffer, dma),
1180					       dma_unmap_len(tx_buffer, len),
1181					       DMA_TO_DEVICE);
1182				dma_unmap_len_set(tx_buffer, len, 0);
1183			}
1184		}
1185
1186		/* move us one more past the eop_desc for start of next pkt */
1187		tx_buffer++;
1188		tx_desc++;
1189		i++;
1190		if (unlikely(!i)) {
1191			i -= tx_ring->count;
1192			tx_buffer = tx_ring->tx_buffer_info;
1193			tx_desc = IXGBE_TX_DESC(tx_ring, 0);
1194		}
1195
1196		/* issue prefetch for next Tx descriptor */
1197		prefetch(tx_desc);
1198
1199		/* update budget accounting */
1200		budget--;
1201	} while (likely(budget));
1202
1203	i += tx_ring->count;
1204	tx_ring->next_to_clean = i;
1205	u64_stats_update_begin(&tx_ring->syncp);
1206	tx_ring->stats.bytes += total_bytes;
1207	tx_ring->stats.packets += total_packets;
1208	u64_stats_update_end(&tx_ring->syncp);
1209	q_vector->tx.total_bytes += total_bytes;
1210	q_vector->tx.total_packets += total_packets;
1211	adapter->tx_ipsec += total_ipsec;
1212
1213	if (check_for_tx_hang(tx_ring) && ixgbe_check_tx_hang(tx_ring)) {
1214		/* schedule immediate reset if we believe we hung */
1215		struct ixgbe_hw *hw = &adapter->hw;
1216		e_err(drv, "Detected Tx Unit Hang %s\n"
1217			"  Tx Queue             <%d>\n"
1218			"  TDH, TDT             <%x>, <%x>\n"
1219			"  next_to_use          <%x>\n"
1220			"  next_to_clean        <%x>\n"
1221			"tx_buffer_info[next_to_clean]\n"
1222			"  time_stamp           <%lx>\n"
1223			"  jiffies              <%lx>\n",
1224			ring_is_xdp(tx_ring) ? "(XDP)" : "",
1225			tx_ring->queue_index,
1226			IXGBE_READ_REG(hw, IXGBE_TDH(tx_ring->reg_idx)),
1227			IXGBE_READ_REG(hw, IXGBE_TDT(tx_ring->reg_idx)),
1228			tx_ring->next_to_use, i,
1229			tx_ring->tx_buffer_info[i].time_stamp, jiffies);
1230
1231		if (!ring_is_xdp(tx_ring))
1232			netif_stop_subqueue(tx_ring->netdev,
1233					    tx_ring->queue_index);
1234
1235		e_info(probe,
1236		       "tx hang %d detected on queue %d, resetting adapter\n",
1237			adapter->tx_timeout_count + 1, tx_ring->queue_index);
1238
1239		/* schedule immediate reset if we believe we hung */
1240		ixgbe_tx_timeout_reset(adapter);
1241
1242		/* the adapter is about to reset, no point in enabling stuff */
1243		return true;
1244	}
1245
1246	if (ring_is_xdp(tx_ring))
1247		return !!budget;
1248
1249	netdev_tx_completed_queue(txring_txq(tx_ring),
1250				  total_packets, total_bytes);
1251
1252#define TX_WAKE_THRESHOLD (DESC_NEEDED * 2)
1253	if (unlikely(total_packets && netif_carrier_ok(tx_ring->netdev) &&
1254		     (ixgbe_desc_unused(tx_ring) >= TX_WAKE_THRESHOLD))) {
1255		/* Make sure that anybody stopping the queue after this
1256		 * sees the new next_to_clean.
1257		 */
1258		smp_mb();
1259		if (__netif_subqueue_stopped(tx_ring->netdev,
1260					     tx_ring->queue_index)
1261		    && !test_bit(__IXGBE_DOWN, &adapter->state)) {
1262			netif_wake_subqueue(tx_ring->netdev,
1263					    tx_ring->queue_index);
1264			++tx_ring->tx_stats.restart_queue;
1265		}
1266	}
1267
1268	return !!budget;
1269}
1270
1271#ifdef CONFIG_IXGBE_DCA
1272static void ixgbe_update_tx_dca(struct ixgbe_adapter *adapter,
1273				struct ixgbe_ring *tx_ring,
1274				int cpu)
1275{
1276	struct ixgbe_hw *hw = &adapter->hw;
1277	u32 txctrl = 0;
1278	u16 reg_offset;
1279
1280	if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
1281		txctrl = dca3_get_tag(tx_ring->dev, cpu);
1282
1283	switch (hw->mac.type) {
1284	case ixgbe_mac_82598EB:
1285		reg_offset = IXGBE_DCA_TXCTRL(tx_ring->reg_idx);
1286		break;
1287	case ixgbe_mac_82599EB:
1288	case ixgbe_mac_X540:
1289		reg_offset = IXGBE_DCA_TXCTRL_82599(tx_ring->reg_idx);
1290		txctrl <<= IXGBE_DCA_TXCTRL_CPUID_SHIFT_82599;
1291		break;
1292	default:
1293		/* for unknown hardware do not write register */
1294		return;
1295	}
1296
1297	/*
1298	 * We can enable relaxed ordering for reads, but not writes when
1299	 * DCA is enabled.  This is due to a known issue in some chipsets
1300	 * which will cause the DCA tag to be cleared.
1301	 */
1302	txctrl |= IXGBE_DCA_TXCTRL_DESC_RRO_EN |
1303		  IXGBE_DCA_TXCTRL_DATA_RRO_EN |
1304		  IXGBE_DCA_TXCTRL_DESC_DCA_EN;
1305
1306	IXGBE_WRITE_REG(hw, reg_offset, txctrl);
1307}
1308
1309static void ixgbe_update_rx_dca(struct ixgbe_adapter *adapter,
1310				struct ixgbe_ring *rx_ring,
1311				int cpu)
1312{
1313	struct ixgbe_hw *hw = &adapter->hw;
1314	u32 rxctrl = 0;
1315	u8 reg_idx = rx_ring->reg_idx;
1316
1317	if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
1318		rxctrl = dca3_get_tag(rx_ring->dev, cpu);
1319
1320	switch (hw->mac.type) {
1321	case ixgbe_mac_82599EB:
1322	case ixgbe_mac_X540:
1323		rxctrl <<= IXGBE_DCA_RXCTRL_CPUID_SHIFT_82599;
1324		break;
1325	default:
1326		break;
1327	}
1328
1329	/*
1330	 * We can enable relaxed ordering for reads, but not writes when
1331	 * DCA is enabled.  This is due to a known issue in some chipsets
1332	 * which will cause the DCA tag to be cleared.
1333	 */
1334	rxctrl |= IXGBE_DCA_RXCTRL_DESC_RRO_EN |
1335		  IXGBE_DCA_RXCTRL_DATA_DCA_EN |
1336		  IXGBE_DCA_RXCTRL_DESC_DCA_EN;
1337
1338	IXGBE_WRITE_REG(hw, IXGBE_DCA_RXCTRL(reg_idx), rxctrl);
1339}
1340
1341static void ixgbe_update_dca(struct ixgbe_q_vector *q_vector)
1342{
1343	struct ixgbe_adapter *adapter = q_vector->adapter;
1344	struct ixgbe_ring *ring;
1345	int cpu = get_cpu();
1346
1347	if (q_vector->cpu == cpu)
1348		goto out_no_update;
1349
1350	ixgbe_for_each_ring(ring, q_vector->tx)
1351		ixgbe_update_tx_dca(adapter, ring, cpu);
1352
1353	ixgbe_for_each_ring(ring, q_vector->rx)
1354		ixgbe_update_rx_dca(adapter, ring, cpu);
1355
1356	q_vector->cpu = cpu;
1357out_no_update:
1358	put_cpu();
1359}
1360
1361static void ixgbe_setup_dca(struct ixgbe_adapter *adapter)
1362{
1363	int i;
1364
1365	/* always use CB2 mode, difference is masked in the CB driver */
1366	if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
1367		IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL,
1368				IXGBE_DCA_CTRL_DCA_MODE_CB2);
1369	else
1370		IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL,
1371				IXGBE_DCA_CTRL_DCA_DISABLE);
1372
1373	for (i = 0; i < adapter->num_q_vectors; i++) {
1374		adapter->q_vector[i]->cpu = -1;
1375		ixgbe_update_dca(adapter->q_vector[i]);
1376	}
1377}
1378
1379static int __ixgbe_notify_dca(struct device *dev, void *data)
1380{
1381	struct ixgbe_adapter *adapter = dev_get_drvdata(dev);
1382	unsigned long event = *(unsigned long *)data;
1383
1384	if (!(adapter->flags & IXGBE_FLAG_DCA_CAPABLE))
1385		return 0;
1386
1387	switch (event) {
1388	case DCA_PROVIDER_ADD:
1389		/* if we're already enabled, don't do it again */
1390		if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
1391			break;
1392		if (dca_add_requester(dev) == 0) {
1393			adapter->flags |= IXGBE_FLAG_DCA_ENABLED;
1394			IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL,
1395					IXGBE_DCA_CTRL_DCA_MODE_CB2);
1396			break;
1397		}
1398		fallthrough; /* DCA is disabled. */
1399	case DCA_PROVIDER_REMOVE:
1400		if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) {
1401			dca_remove_requester(dev);
1402			adapter->flags &= ~IXGBE_FLAG_DCA_ENABLED;
1403			IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL,
1404					IXGBE_DCA_CTRL_DCA_DISABLE);
1405		}
1406		break;
1407	}
1408
1409	return 0;
1410}
1411
1412#endif /* CONFIG_IXGBE_DCA */
1413
1414#define IXGBE_RSS_L4_TYPES_MASK \
1415	((1ul << IXGBE_RXDADV_RSSTYPE_IPV4_TCP) | \
1416	 (1ul << IXGBE_RXDADV_RSSTYPE_IPV4_UDP) | \
1417	 (1ul << IXGBE_RXDADV_RSSTYPE_IPV6_TCP) | \
1418	 (1ul << IXGBE_RXDADV_RSSTYPE_IPV6_UDP))
1419
1420static inline void ixgbe_rx_hash(struct ixgbe_ring *ring,
1421				 union ixgbe_adv_rx_desc *rx_desc,
1422				 struct sk_buff *skb)
1423{
1424	u16 rss_type;
1425
1426	if (!(ring->netdev->features & NETIF_F_RXHASH))
1427		return;
1428
1429	rss_type = le16_to_cpu(rx_desc->wb.lower.lo_dword.hs_rss.pkt_info) &
1430		   IXGBE_RXDADV_RSSTYPE_MASK;
1431
1432	if (!rss_type)
1433		return;
1434
1435	skb_set_hash(skb, le32_to_cpu(rx_desc->wb.lower.hi_dword.rss),
1436		     (IXGBE_RSS_L4_TYPES_MASK & (1ul << rss_type)) ?
1437		     PKT_HASH_TYPE_L4 : PKT_HASH_TYPE_L3);
1438}
1439
1440#ifdef IXGBE_FCOE
1441/**
1442 * ixgbe_rx_is_fcoe - check the rx desc for incoming pkt type
1443 * @ring: structure containing ring specific data
1444 * @rx_desc: advanced rx descriptor
1445 *
1446 * Returns : true if it is FCoE pkt
1447 */
1448static inline bool ixgbe_rx_is_fcoe(struct ixgbe_ring *ring,
1449				    union ixgbe_adv_rx_desc *rx_desc)
1450{
1451	__le16 pkt_info = rx_desc->wb.lower.lo_dword.hs_rss.pkt_info;
1452
1453	return test_bit(__IXGBE_RX_FCOE, &ring->state) &&
1454	       ((pkt_info & cpu_to_le16(IXGBE_RXDADV_PKTTYPE_ETQF_MASK)) ==
1455		(cpu_to_le16(IXGBE_ETQF_FILTER_FCOE <<
1456			     IXGBE_RXDADV_PKTTYPE_ETQF_SHIFT)));
1457}
1458
1459#endif /* IXGBE_FCOE */
1460/**
1461 * ixgbe_rx_checksum - indicate in skb if hw indicated a good cksum
1462 * @ring: structure containing ring specific data
1463 * @rx_desc: current Rx descriptor being processed
1464 * @skb: skb currently being received and modified
1465 **/
1466static inline void ixgbe_rx_checksum(struct ixgbe_ring *ring,
1467				     union ixgbe_adv_rx_desc *rx_desc,
1468				     struct sk_buff *skb)
1469{
1470	__le16 pkt_info = rx_desc->wb.lower.lo_dword.hs_rss.pkt_info;
1471	bool encap_pkt = false;
1472
1473	skb_checksum_none_assert(skb);
1474
1475	/* Rx csum disabled */
1476	if (!(ring->netdev->features & NETIF_F_RXCSUM))
1477		return;
1478
1479	/* check for VXLAN and Geneve packets */
1480	if (pkt_info & cpu_to_le16(IXGBE_RXDADV_PKTTYPE_VXLAN)) {
1481		encap_pkt = true;
1482		skb->encapsulation = 1;
1483	}
1484
1485	/* if IP and error */
1486	if (ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_IPCS) &&
1487	    ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_ERR_IPE)) {
1488		ring->rx_stats.csum_err++;
1489		return;
1490	}
1491
1492	if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_L4CS))
1493		return;
1494
1495	if (ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_ERR_TCPE)) {
1496		/*
1497		 * 82599 errata, UDP frames with a 0 checksum can be marked as
1498		 * checksum errors.
1499		 */
1500		if ((pkt_info & cpu_to_le16(IXGBE_RXDADV_PKTTYPE_UDP)) &&
1501		    test_bit(__IXGBE_RX_CSUM_UDP_ZERO_ERR, &ring->state))
1502			return;
1503
1504		ring->rx_stats.csum_err++;
1505		return;
1506	}
1507
1508	/* It must be a TCP or UDP packet with a valid checksum */
1509	skb->ip_summed = CHECKSUM_UNNECESSARY;
1510	if (encap_pkt) {
1511		if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_OUTERIPCS))
1512			return;
1513
1514		if (ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_ERR_OUTERIPER)) {
1515			skb->ip_summed = CHECKSUM_NONE;
1516			return;
1517		}
1518		/* If we checked the outer header let the stack know */
1519		skb->csum_level = 1;
1520	}
1521}
1522
1523static inline unsigned int ixgbe_rx_offset(struct ixgbe_ring *rx_ring)
1524{
1525	return ring_uses_build_skb(rx_ring) ? IXGBE_SKB_PAD : 0;
1526}
1527
1528static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring,
1529				    struct ixgbe_rx_buffer *bi)
1530{
1531	struct page *page = bi->page;
1532	dma_addr_t dma;
1533
1534	/* since we are recycling buffers we should seldom need to alloc */
1535	if (likely(page))
1536		return true;
1537
1538	/* alloc new page for storage */
1539	page = dev_alloc_pages(ixgbe_rx_pg_order(rx_ring));
1540	if (unlikely(!page)) {
1541		rx_ring->rx_stats.alloc_rx_page_failed++;
1542		return false;
1543	}
1544
1545	/* map page for use */
1546	dma = dma_map_page_attrs(rx_ring->dev, page, 0,
1547				 ixgbe_rx_pg_size(rx_ring),
1548				 DMA_FROM_DEVICE,
1549				 IXGBE_RX_DMA_ATTR);
1550
1551	/*
1552	 * if mapping failed free memory back to system since
1553	 * there isn't much point in holding memory we can't use
1554	 */
1555	if (dma_mapping_error(rx_ring->dev, dma)) {
1556		__free_pages(page, ixgbe_rx_pg_order(rx_ring));
1557
1558		rx_ring->rx_stats.alloc_rx_page_failed++;
1559		return false;
1560	}
1561
1562	bi->dma = dma;
1563	bi->page = page;
1564	bi->page_offset = ixgbe_rx_offset(rx_ring);
1565	page_ref_add(page, USHRT_MAX - 1);
1566	bi->pagecnt_bias = USHRT_MAX;
1567	rx_ring->rx_stats.alloc_rx_page++;
1568
1569	return true;
1570}
1571
1572/**
1573 * ixgbe_alloc_rx_buffers - Replace used receive buffers
1574 * @rx_ring: ring to place buffers on
1575 * @cleaned_count: number of buffers to replace
1576 **/
1577void ixgbe_alloc_rx_buffers(struct ixgbe_ring *rx_ring, u16 cleaned_count)
1578{
1579	union ixgbe_adv_rx_desc *rx_desc;
1580	struct ixgbe_rx_buffer *bi;
1581	u16 i = rx_ring->next_to_use;
1582	u16 bufsz;
1583
1584	/* nothing to do */
1585	if (!cleaned_count)
1586		return;
1587
1588	rx_desc = IXGBE_RX_DESC(rx_ring, i);
1589	bi = &rx_ring->rx_buffer_info[i];
1590	i -= rx_ring->count;
1591
1592	bufsz = ixgbe_rx_bufsz(rx_ring);
1593
1594	do {
1595		if (!ixgbe_alloc_mapped_page(rx_ring, bi))
1596			break;
1597
1598		/* sync the buffer for use by the device */
1599		dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
1600						 bi->page_offset, bufsz,
1601						 DMA_FROM_DEVICE);
1602
1603		/*
1604		 * Refresh the desc even if buffer_addrs didn't change
1605		 * because each write-back erases this info.
1606		 */
1607		rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset);
1608
1609		rx_desc++;
1610		bi++;
1611		i++;
1612		if (unlikely(!i)) {
1613			rx_desc = IXGBE_RX_DESC(rx_ring, 0);
1614			bi = rx_ring->rx_buffer_info;
1615			i -= rx_ring->count;
1616		}
1617
1618		/* clear the length for the next_to_use descriptor */
1619		rx_desc->wb.upper.length = 0;
1620
1621		cleaned_count--;
1622	} while (cleaned_count);
1623
1624	i += rx_ring->count;
1625
1626	if (rx_ring->next_to_use != i) {
1627		rx_ring->next_to_use = i;
1628
1629		/* update next to alloc since we have filled the ring */
1630		rx_ring->next_to_alloc = i;
1631
1632		/* Force memory writes to complete before letting h/w
1633		 * know there are new descriptors to fetch.  (Only
1634		 * applicable for weak-ordered memory model archs,
1635		 * such as IA-64).
1636		 */
1637		wmb();
1638		writel(i, rx_ring->tail);
1639	}
1640}
1641
1642static void ixgbe_set_rsc_gso_size(struct ixgbe_ring *ring,
1643				   struct sk_buff *skb)
1644{
1645	u16 hdr_len = skb_headlen(skb);
1646
1647	/* set gso_size to avoid messing up TCP MSS */
1648	skb_shinfo(skb)->gso_size = DIV_ROUND_UP((skb->len - hdr_len),
1649						 IXGBE_CB(skb)->append_cnt);
1650	skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
1651}
1652
1653static void ixgbe_update_rsc_stats(struct ixgbe_ring *rx_ring,
1654				   struct sk_buff *skb)
1655{
1656	/* if append_cnt is 0 then frame is not RSC */
1657	if (!IXGBE_CB(skb)->append_cnt)
1658		return;
1659
1660	rx_ring->rx_stats.rsc_count += IXGBE_CB(skb)->append_cnt;
1661	rx_ring->rx_stats.rsc_flush++;
1662
1663	ixgbe_set_rsc_gso_size(rx_ring, skb);
1664
1665	/* gso_size is computed using append_cnt so always clear it last */
1666	IXGBE_CB(skb)->append_cnt = 0;
1667}
1668
1669/**
1670 * ixgbe_process_skb_fields - Populate skb header fields from Rx descriptor
1671 * @rx_ring: rx descriptor ring packet is being transacted on
1672 * @rx_desc: pointer to the EOP Rx descriptor
1673 * @skb: pointer to current skb being populated
1674 *
1675 * This function checks the ring, descriptor, and packet information in
1676 * order to populate the hash, checksum, VLAN, timestamp, protocol, and
1677 * other fields within the skb.
1678 **/
1679void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring,
1680			      union ixgbe_adv_rx_desc *rx_desc,
1681			      struct sk_buff *skb)
1682{
1683	struct net_device *dev = rx_ring->netdev;
1684	u32 flags = rx_ring->q_vector->adapter->flags;
1685
1686	ixgbe_update_rsc_stats(rx_ring, skb);
1687
1688	ixgbe_rx_hash(rx_ring, rx_desc, skb);
1689
1690	ixgbe_rx_checksum(rx_ring, rx_desc, skb);
1691
1692	if (unlikely(flags & IXGBE_FLAG_RX_HWTSTAMP_ENABLED))
1693		ixgbe_ptp_rx_hwtstamp(rx_ring, rx_desc, skb);
1694
1695	if ((dev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
1696	    ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_VP)) {
1697		u16 vid = le16_to_cpu(rx_desc->wb.upper.vlan);
1698		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid);
1699	}
1700
1701	if (ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_STAT_SECP))
1702		ixgbe_ipsec_rx(rx_ring, rx_desc, skb);
1703
1704	/* record Rx queue, or update MACVLAN statistics */
1705	if (netif_is_ixgbe(dev))
1706		skb_record_rx_queue(skb, rx_ring->queue_index);
1707	else
1708		macvlan_count_rx(netdev_priv(dev), skb->len + ETH_HLEN, true,
1709				 false);
1710
1711	skb->protocol = eth_type_trans(skb, dev);
1712}
1713
1714void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector,
1715		  struct sk_buff *skb)
1716{
1717	napi_gro_receive(&q_vector->napi, skb);
1718}
1719
1720/**
1721 * ixgbe_is_non_eop - process handling of non-EOP buffers
1722 * @rx_ring: Rx ring being processed
1723 * @rx_desc: Rx descriptor for current buffer
1724 * @skb: Current socket buffer containing buffer in progress
1725 *
1726 * This function updates next to clean.  If the buffer is an EOP buffer
1727 * this function exits returning false, otherwise it will place the
1728 * sk_buff in the next buffer to be chained and return true indicating
1729 * that this is in fact a non-EOP buffer.
1730 **/
1731static bool ixgbe_is_non_eop(struct ixgbe_ring *rx_ring,
1732			     union ixgbe_adv_rx_desc *rx_desc,
1733			     struct sk_buff *skb)
1734{
1735	u32 ntc = rx_ring->next_to_clean + 1;
1736
1737	/* fetch, update, and store next to clean */
1738	ntc = (ntc < rx_ring->count) ? ntc : 0;
1739	rx_ring->next_to_clean = ntc;
1740
1741	prefetch(IXGBE_RX_DESC(rx_ring, ntc));
1742
1743	/* update RSC append count if present */
1744	if (ring_is_rsc_enabled(rx_ring)) {
1745		__le32 rsc_enabled = rx_desc->wb.lower.lo_dword.data &
1746				     cpu_to_le32(IXGBE_RXDADV_RSCCNT_MASK);
1747
1748		if (unlikely(rsc_enabled)) {
1749			u32 rsc_cnt = le32_to_cpu(rsc_enabled);
1750
1751			rsc_cnt >>= IXGBE_RXDADV_RSCCNT_SHIFT;
1752			IXGBE_CB(skb)->append_cnt += rsc_cnt - 1;
1753
1754			/* update ntc based on RSC value */
1755			ntc = le32_to_cpu(rx_desc->wb.upper.status_error);
1756			ntc &= IXGBE_RXDADV_NEXTP_MASK;
1757			ntc >>= IXGBE_RXDADV_NEXTP_SHIFT;
1758		}
1759	}
1760
1761	/* if we are the last buffer then there is nothing else to do */
1762	if (likely(ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)))
1763		return false;
1764
1765	/* place skb in next buffer to be received */
1766	rx_ring->rx_buffer_info[ntc].skb = skb;
1767	rx_ring->rx_stats.non_eop_descs++;
1768
1769	return true;
1770}
1771
1772/**
1773 * ixgbe_pull_tail - ixgbe specific version of skb_pull_tail
1774 * @rx_ring: rx descriptor ring packet is being transacted on
1775 * @skb: pointer to current skb being adjusted
1776 *
1777 * This function is an ixgbe specific version of __pskb_pull_tail.  The
1778 * main difference between this version and the original function is that
1779 * this function can make several assumptions about the state of things
1780 * that allow for significant optimizations versus the standard function.
1781 * As a result we can do things like drop a frag and maintain an accurate
1782 * truesize for the skb.
1783 */
1784static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring,
1785			    struct sk_buff *skb)
1786{
1787	skb_frag_t *frag = &skb_shinfo(skb)->frags[0];
1788	unsigned char *va;
1789	unsigned int pull_len;
1790
1791	/*
1792	 * it is valid to use page_address instead of kmap since we are
1793	 * working with pages allocated out of the lomem pool per
1794	 * alloc_page(GFP_ATOMIC)
1795	 */
1796	va = skb_frag_address(frag);
1797
1798	/*
1799	 * we need the header to contain the greater of either ETH_HLEN or
1800	 * 60 bytes if the skb->len is less than 60 for skb_pad.
1801	 */
1802	pull_len = eth_get_headlen(skb->dev, va, IXGBE_RX_HDR_SIZE);
1803
1804	/* align pull length to size of long to optimize memcpy performance */
1805	skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long)));
1806
1807	/* update all of the pointers */
1808	skb_frag_size_sub(frag, pull_len);
1809	skb_frag_off_add(frag, pull_len);
1810	skb->data_len -= pull_len;
1811	skb->tail += pull_len;
1812}
1813
1814/**
1815 * ixgbe_dma_sync_frag - perform DMA sync for first frag of SKB
1816 * @rx_ring: rx descriptor ring packet is being transacted on
1817 * @skb: pointer to current skb being updated
1818 *
1819 * This function provides a basic DMA sync up for the first fragment of an
1820 * skb.  The reason for doing this is that the first fragment cannot be
1821 * unmapped until we have reached the end of packet descriptor for a buffer
1822 * chain.
1823 */
1824static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring,
1825				struct sk_buff *skb)
1826{
1827	if (ring_uses_build_skb(rx_ring)) {
1828		unsigned long mask = (unsigned long)ixgbe_rx_pg_size(rx_ring) - 1;
1829		unsigned long offset = (unsigned long)(skb->data) & mask;
1830
1831		dma_sync_single_range_for_cpu(rx_ring->dev,
1832					      IXGBE_CB(skb)->dma,
1833					      offset,
1834					      skb_headlen(skb),
1835					      DMA_FROM_DEVICE);
1836	} else {
1837		skb_frag_t *frag = &skb_shinfo(skb)->frags[0];
1838
1839		dma_sync_single_range_for_cpu(rx_ring->dev,
1840					      IXGBE_CB(skb)->dma,
1841					      skb_frag_off(frag),
1842					      skb_frag_size(frag),
1843					      DMA_FROM_DEVICE);
1844	}
1845
1846	/* If the page was released, just unmap it. */
1847	if (unlikely(IXGBE_CB(skb)->page_released)) {
1848		dma_unmap_page_attrs(rx_ring->dev, IXGBE_CB(skb)->dma,
1849				     ixgbe_rx_pg_size(rx_ring),
1850				     DMA_FROM_DEVICE,
1851				     IXGBE_RX_DMA_ATTR);
1852	}
1853}
1854
1855/**
1856 * ixgbe_cleanup_headers - Correct corrupted or empty headers
1857 * @rx_ring: rx descriptor ring packet is being transacted on
1858 * @rx_desc: pointer to the EOP Rx descriptor
1859 * @skb: pointer to current skb being fixed
1860 *
1861 * Check if the skb is valid in the XDP case it will be an error pointer.
1862 * Return true in this case to abort processing and advance to next
1863 * descriptor.
1864 *
1865 * Check for corrupted packet headers caused by senders on the local L2
1866 * embedded NIC switch not setting up their Tx Descriptors right.  These
1867 * should be very rare.
1868 *
1869 * Also address the case where we are pulling data in on pages only
1870 * and as such no data is present in the skb header.
1871 *
1872 * In addition if skb is not at least 60 bytes we need to pad it so that
1873 * it is large enough to qualify as a valid Ethernet frame.
1874 *
1875 * Returns true if an error was encountered and skb was freed.
1876 **/
1877bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring,
1878			   union ixgbe_adv_rx_desc *rx_desc,
1879			   struct sk_buff *skb)
1880{
1881	struct net_device *netdev = rx_ring->netdev;
1882
1883	/* XDP packets use error pointer so abort at this point */
1884	if (IS_ERR(skb))
1885		return true;
1886
1887	/* Verify netdev is present, and that packet does not have any
1888	 * errors that would be unacceptable to the netdev.
1889	 */
1890	if (!netdev ||
1891	    (unlikely(ixgbe_test_staterr(rx_desc,
1892					 IXGBE_RXDADV_ERR_FRAME_ERR_MASK) &&
1893	     !(netdev->features & NETIF_F_RXALL)))) {
1894		dev_kfree_skb_any(skb);
1895		return true;
1896	}
1897
1898	/* place header in linear portion of buffer */
1899	if (!skb_headlen(skb))
1900		ixgbe_pull_tail(rx_ring, skb);
1901
1902#ifdef IXGBE_FCOE
1903	/* do not attempt to pad FCoE Frames as this will disrupt DDP */
1904	if (ixgbe_rx_is_fcoe(rx_ring, rx_desc))
1905		return false;
1906
1907#endif
1908	/* if eth_skb_pad returns an error the skb was freed */
1909	if (eth_skb_pad(skb))
1910		return true;
1911
1912	return false;
1913}
1914
1915/**
1916 * ixgbe_reuse_rx_page - page flip buffer and store it back on the ring
1917 * @rx_ring: rx descriptor ring to store buffers on
1918 * @old_buff: donor buffer to have page reused
1919 *
1920 * Synchronizes page for reuse by the adapter
1921 **/
1922static void ixgbe_reuse_rx_page(struct ixgbe_ring *rx_ring,
1923				struct ixgbe_rx_buffer *old_buff)
1924{
1925	struct ixgbe_rx_buffer *new_buff;
1926	u16 nta = rx_ring->next_to_alloc;
1927
1928	new_buff = &rx_ring->rx_buffer_info[nta];
1929
1930	/* update, and store next to alloc */
1931	nta++;
1932	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
1933
1934	/* Transfer page from old buffer to new buffer.
1935	 * Move each member individually to avoid possible store
1936	 * forwarding stalls and unnecessary copy of skb.
1937	 */
1938	new_buff->dma		= old_buff->dma;
1939	new_buff->page		= old_buff->page;
1940	new_buff->page_offset	= old_buff->page_offset;
1941	new_buff->pagecnt_bias	= old_buff->pagecnt_bias;
1942}
1943
1944static inline bool ixgbe_page_is_reserved(struct page *page)
1945{
1946	return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page);
1947}
1948
1949static bool ixgbe_can_reuse_rx_page(struct ixgbe_rx_buffer *rx_buffer,
1950				    int rx_buffer_pgcnt)
1951{
1952	unsigned int pagecnt_bias = rx_buffer->pagecnt_bias;
1953	struct page *page = rx_buffer->page;
1954
1955	/* avoid re-using remote pages */
1956	if (unlikely(ixgbe_page_is_reserved(page)))
1957		return false;
1958
1959#if (PAGE_SIZE < 8192)
1960	/* if we are only owner of page we can reuse it */
1961	if (unlikely((rx_buffer_pgcnt - pagecnt_bias) > 1))
1962		return false;
1963#else
1964	/* The last offset is a bit aggressive in that we assume the
1965	 * worst case of FCoE being enabled and using a 3K buffer.
1966	 * However this should have minimal impact as the 1K extra is
1967	 * still less than one buffer in size.
1968	 */
1969#define IXGBE_LAST_OFFSET \
1970	(SKB_WITH_OVERHEAD(PAGE_SIZE) - IXGBE_RXBUFFER_3K)
1971	if (rx_buffer->page_offset > IXGBE_LAST_OFFSET)
1972		return false;
1973#endif
1974
1975	/* If we have drained the page fragment pool we need to update
1976	 * the pagecnt_bias and page count so that we fully restock the
1977	 * number of references the driver holds.
1978	 */
1979	if (unlikely(pagecnt_bias == 1)) {
1980		page_ref_add(page, USHRT_MAX - 1);
1981		rx_buffer->pagecnt_bias = USHRT_MAX;
1982	}
1983
1984	return true;
1985}
1986
1987/**
1988 * ixgbe_add_rx_frag - Add contents of Rx buffer to sk_buff
1989 * @rx_ring: rx descriptor ring to transact packets on
1990 * @rx_buffer: buffer containing page to add
1991 * @skb: sk_buff to place the data into
1992 * @size: size of data in rx_buffer
1993 *
1994 * This function will add the data contained in rx_buffer->page to the skb.
1995 * This is done either through a direct copy if the data in the buffer is
1996 * less than the skb header size, otherwise it will just attach the page as
1997 * a frag to the skb.
1998 *
1999 * The function will then update the page offset if necessary and return
2000 * true if the buffer can be reused by the adapter.
2001 **/
2002static void ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring,
2003			      struct ixgbe_rx_buffer *rx_buffer,
2004			      struct sk_buff *skb,
2005			      unsigned int size)
2006{
2007#if (PAGE_SIZE < 8192)
2008	unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2;
2009#else
2010	unsigned int truesize = ring_uses_build_skb(rx_ring) ?
2011				SKB_DATA_ALIGN(IXGBE_SKB_PAD + size) :
2012				SKB_DATA_ALIGN(size);
2013#endif
2014	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page,
2015			rx_buffer->page_offset, size, truesize);
2016#if (PAGE_SIZE < 8192)
2017	rx_buffer->page_offset ^= truesize;
2018#else
2019	rx_buffer->page_offset += truesize;
2020#endif
2021}
2022
2023static struct ixgbe_rx_buffer *ixgbe_get_rx_buffer(struct ixgbe_ring *rx_ring,
2024						   union ixgbe_adv_rx_desc *rx_desc,
2025						   struct sk_buff **skb,
2026						   const unsigned int size,
2027						   int *rx_buffer_pgcnt)
2028{
2029	struct ixgbe_rx_buffer *rx_buffer;
2030
2031	rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
2032	*rx_buffer_pgcnt =
2033#if (PAGE_SIZE < 8192)
2034		page_count(rx_buffer->page);
2035#else
2036		0;
2037#endif
2038	prefetchw(rx_buffer->page);
2039	*skb = rx_buffer->skb;
2040
2041	/* Delay unmapping of the first packet. It carries the header
2042	 * information, HW may still access the header after the writeback.
2043	 * Only unmap it when EOP is reached
2044	 */
2045	if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)) {
2046		if (!*skb)
2047			goto skip_sync;
2048	} else {
2049		if (*skb)
2050			ixgbe_dma_sync_frag(rx_ring, *skb);
2051	}
2052
2053	/* we are reusing so sync this buffer for CPU use */
2054	dma_sync_single_range_for_cpu(rx_ring->dev,
2055				      rx_buffer->dma,
2056				      rx_buffer->page_offset,
2057				      size,
2058				      DMA_FROM_DEVICE);
2059skip_sync:
2060	rx_buffer->pagecnt_bias--;
2061
2062	return rx_buffer;
2063}
2064
2065static void ixgbe_put_rx_buffer(struct ixgbe_ring *rx_ring,
2066				struct ixgbe_rx_buffer *rx_buffer,
2067				struct sk_buff *skb,
2068				int rx_buffer_pgcnt)
2069{
2070	if (ixgbe_can_reuse_rx_page(rx_buffer, rx_buffer_pgcnt)) {
2071		/* hand second half of page back to the ring */
2072		ixgbe_reuse_rx_page(rx_ring, rx_buffer);
2073	} else {
2074		if (!IS_ERR(skb) && IXGBE_CB(skb)->dma == rx_buffer->dma) {
2075			/* the page has been released from the ring */
2076			IXGBE_CB(skb)->page_released = true;
2077		} else {
2078			/* we are not reusing the buffer so unmap it */
2079			dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma,
2080					     ixgbe_rx_pg_size(rx_ring),
2081					     DMA_FROM_DEVICE,
2082					     IXGBE_RX_DMA_ATTR);
2083		}
2084		__page_frag_cache_drain(rx_buffer->page,
2085					rx_buffer->pagecnt_bias);
2086	}
2087
2088	/* clear contents of rx_buffer */
2089	rx_buffer->page = NULL;
2090	rx_buffer->skb = NULL;
2091}
2092
2093static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring,
2094					   struct ixgbe_rx_buffer *rx_buffer,
2095					   struct xdp_buff *xdp,
2096					   union ixgbe_adv_rx_desc *rx_desc)
2097{
2098	unsigned int size = xdp->data_end - xdp->data;
2099#if (PAGE_SIZE < 8192)
2100	unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2;
2101#else
2102	unsigned int truesize = SKB_DATA_ALIGN(xdp->data_end -
2103					       xdp->data_hard_start);
2104#endif
2105	struct sk_buff *skb;
2106
2107	/* prefetch first cache line of first page */
2108	net_prefetch(xdp->data);
2109
2110	/* Note, we get here by enabling legacy-rx via:
2111	 *
2112	 *    ethtool --set-priv-flags <dev> legacy-rx on
2113	 *
2114	 * In this mode, we currently get 0 extra XDP headroom as
2115	 * opposed to having legacy-rx off, where we process XDP
2116	 * packets going to stack via ixgbe_build_skb(). The latter
2117	 * provides us currently with 192 bytes of headroom.
2118	 *
2119	 * For ixgbe_construct_skb() mode it means that the
2120	 * xdp->data_meta will always point to xdp->data, since
2121	 * the helper cannot expand the head. Should this ever
2122	 * change in future for legacy-rx mode on, then lets also
2123	 * add xdp->data_meta handling here.
2124	 */
2125
2126	/* allocate a skb to store the frags */
2127	skb = napi_alloc_skb(&rx_ring->q_vector->napi, IXGBE_RX_HDR_SIZE);
2128	if (unlikely(!skb))
2129		return NULL;
2130
2131	if (size > IXGBE_RX_HDR_SIZE) {
2132		if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP))
2133			IXGBE_CB(skb)->dma = rx_buffer->dma;
2134
2135		skb_add_rx_frag(skb, 0, rx_buffer->page,
2136				xdp->data - page_address(rx_buffer->page),
2137				size, truesize);
2138#if (PAGE_SIZE < 8192)
2139		rx_buffer->page_offset ^= truesize;
2140#else
2141		rx_buffer->page_offset += truesize;
2142#endif
2143	} else {
2144		memcpy(__skb_put(skb, size),
2145		       xdp->data, ALIGN(size, sizeof(long)));
2146		rx_buffer->pagecnt_bias++;
2147	}
2148
2149	return skb;
2150}
2151
2152static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
2153				       struct ixgbe_rx_buffer *rx_buffer,
2154				       struct xdp_buff *xdp,
2155				       union ixgbe_adv_rx_desc *rx_desc)
2156{
2157	unsigned int metasize = xdp->data - xdp->data_meta;
2158#if (PAGE_SIZE < 8192)
2159	unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2;
2160#else
2161	unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
2162				SKB_DATA_ALIGN(xdp->data_end -
2163					       xdp->data_hard_start);
2164#endif
2165	struct sk_buff *skb;
2166
2167	/* Prefetch first cache line of first page. If xdp->data_meta
2168	 * is unused, this points extactly as xdp->data, otherwise we
2169	 * likely have a consumer accessing first few bytes of meta
2170	 * data, and then actual data.
2171	 */
2172	net_prefetch(xdp->data_meta);
2173
2174	/* build an skb to around the page buffer */
2175	skb = build_skb(xdp->data_hard_start, truesize);
2176	if (unlikely(!skb))
2177		return NULL;
2178
2179	/* update pointers within the skb to store the data */
2180	skb_reserve(skb, xdp->data - xdp->data_hard_start);
2181	__skb_put(skb, xdp->data_end - xdp->data);
2182	if (metasize)
2183		skb_metadata_set(skb, metasize);
2184
2185	/* record DMA address if this is the start of a chain of buffers */
2186	if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP))
2187		IXGBE_CB(skb)->dma = rx_buffer->dma;
2188
2189	/* update buffer offset */
2190#if (PAGE_SIZE < 8192)
2191	rx_buffer->page_offset ^= truesize;
2192#else
2193	rx_buffer->page_offset += truesize;
2194#endif
2195
2196	return skb;
2197}
2198
2199static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
2200				     struct ixgbe_ring *rx_ring,
2201				     struct xdp_buff *xdp)
2202{
2203	int err, result = IXGBE_XDP_PASS;
2204	struct bpf_prog *xdp_prog;
2205	struct xdp_frame *xdpf;
2206	u32 act;
2207
2208	rcu_read_lock();
2209	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
2210
2211	if (!xdp_prog)
2212		goto xdp_out;
2213
2214	prefetchw(xdp->data_hard_start); /* xdp_frame write */
2215
2216	act = bpf_prog_run_xdp(xdp_prog, xdp);
2217	switch (act) {
2218	case XDP_PASS:
2219		break;
2220	case XDP_TX:
2221		xdpf = xdp_convert_buff_to_frame(xdp);
2222		if (unlikely(!xdpf))
2223			goto out_failure;
2224		result = ixgbe_xmit_xdp_ring(adapter, xdpf);
2225		if (result == IXGBE_XDP_CONSUMED)
2226			goto out_failure;
2227		break;
2228	case XDP_REDIRECT:
2229		err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog);
2230		if (err)
2231			goto out_failure;
2232		result = IXGBE_XDP_REDIR;
2233		break;
2234	default:
2235		bpf_warn_invalid_xdp_action(act);
2236		fallthrough;
2237	case XDP_ABORTED:
2238out_failure:
2239		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
2240		fallthrough; /* handle aborts by dropping packet */
2241	case XDP_DROP:
2242		result = IXGBE_XDP_CONSUMED;
2243		break;
2244	}
2245xdp_out:
2246	rcu_read_unlock();
2247	return ERR_PTR(-result);
2248}
2249
2250static unsigned int ixgbe_rx_frame_truesize(struct ixgbe_ring *rx_ring,
2251					    unsigned int size)
2252{
2253	unsigned int truesize;
2254
2255#if (PAGE_SIZE < 8192)
2256	truesize = ixgbe_rx_pg_size(rx_ring) / 2; /* Must be power-of-2 */
2257#else
2258	truesize = ring_uses_build_skb(rx_ring) ?
2259		SKB_DATA_ALIGN(IXGBE_SKB_PAD + size) +
2260		SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) :
2261		SKB_DATA_ALIGN(size);
2262#endif
2263	return truesize;
2264}
2265
2266static void ixgbe_rx_buffer_flip(struct ixgbe_ring *rx_ring,
2267				 struct ixgbe_rx_buffer *rx_buffer,
2268				 unsigned int size)
2269{
2270	unsigned int truesize = ixgbe_rx_frame_truesize(rx_ring, size);
2271#if (PAGE_SIZE < 8192)
2272	rx_buffer->page_offset ^= truesize;
2273#else
2274	rx_buffer->page_offset += truesize;
2275#endif
2276}
2277
2278/**
2279 * ixgbe_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
2280 * @q_vector: structure containing interrupt and ring information
2281 * @rx_ring: rx descriptor ring to transact packets on
2282 * @budget: Total limit on number of packets to process
2283 *
2284 * This function provides a "bounce buffer" approach to Rx interrupt
2285 * processing.  The advantage to this is that on systems that have
2286 * expensive overhead for IOMMU access this provides a means of avoiding
2287 * it by maintaining the mapping of the page to the syste.
2288 *
2289 * Returns amount of work completed
2290 **/
2291static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
2292			       struct ixgbe_ring *rx_ring,
2293			       const int budget)
2294{
2295	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
2296	struct ixgbe_adapter *adapter = q_vector->adapter;
2297#ifdef IXGBE_FCOE
2298	int ddp_bytes;
2299	unsigned int mss = 0;
2300#endif /* IXGBE_FCOE */
2301	u16 cleaned_count = ixgbe_desc_unused(rx_ring);
2302	unsigned int xdp_xmit = 0;
2303	struct xdp_buff xdp;
2304
2305	xdp.rxq = &rx_ring->xdp_rxq;
2306
2307	/* Frame size depend on rx_ring setup when PAGE_SIZE=4K */
2308#if (PAGE_SIZE < 8192)
2309	xdp.frame_sz = ixgbe_rx_frame_truesize(rx_ring, 0);
2310#endif
2311
2312	while (likely(total_rx_packets < budget)) {
2313		union ixgbe_adv_rx_desc *rx_desc;
2314		struct ixgbe_rx_buffer *rx_buffer;
2315		struct sk_buff *skb;
2316		int rx_buffer_pgcnt;
2317		unsigned int size;
2318
2319		/* return some buffers to hardware, one at a time is too slow */
2320		if (cleaned_count >= IXGBE_RX_BUFFER_WRITE) {
2321			ixgbe_alloc_rx_buffers(rx_ring, cleaned_count);
2322			cleaned_count = 0;
2323		}
2324
2325		rx_desc = IXGBE_RX_DESC(rx_ring, rx_ring->next_to_clean);
2326		size = le16_to_cpu(rx_desc->wb.upper.length);
2327		if (!size)
2328			break;
2329
2330		/* This memory barrier is needed to keep us from reading
2331		 * any other fields out of the rx_desc until we know the
2332		 * descriptor has been written back
2333		 */
2334		dma_rmb();
2335
2336		rx_buffer = ixgbe_get_rx_buffer(rx_ring, rx_desc, &skb, size, &rx_buffer_pgcnt);
2337
2338		/* retrieve a buffer from the ring */
2339		if (!skb) {
2340			xdp.data = page_address(rx_buffer->page) +
2341				   rx_buffer->page_offset;
2342			xdp.data_meta = xdp.data;
2343			xdp.data_hard_start = xdp.data -
2344					      ixgbe_rx_offset(rx_ring);
2345			xdp.data_end = xdp.data + size;
2346#if (PAGE_SIZE > 4096)
2347			/* At larger PAGE_SIZE, frame_sz depend on len size */
2348			xdp.frame_sz = ixgbe_rx_frame_truesize(rx_ring, size);
2349#endif
2350			skb = ixgbe_run_xdp(adapter, rx_ring, &xdp);
2351		}
2352
2353		if (IS_ERR(skb)) {
2354			unsigned int xdp_res = -PTR_ERR(skb);
2355
2356			if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) {
2357				xdp_xmit |= xdp_res;
2358				ixgbe_rx_buffer_flip(rx_ring, rx_buffer, size);
2359			} else {
2360				rx_buffer->pagecnt_bias++;
2361			}
2362			total_rx_packets++;
2363			total_rx_bytes += size;
2364		} else if (skb) {
2365			ixgbe_add_rx_frag(rx_ring, rx_buffer, skb, size);
2366		} else if (ring_uses_build_skb(rx_ring)) {
2367			skb = ixgbe_build_skb(rx_ring, rx_buffer,
2368					      &xdp, rx_desc);
2369		} else {
2370			skb = ixgbe_construct_skb(rx_ring, rx_buffer,
2371						  &xdp, rx_desc);
2372		}
2373
2374		/* exit if we failed to retrieve a buffer */
2375		if (!skb) {
2376			rx_ring->rx_stats.alloc_rx_buff_failed++;
2377			rx_buffer->pagecnt_bias++;
2378			break;
2379		}
2380
2381		ixgbe_put_rx_buffer(rx_ring, rx_buffer, skb, rx_buffer_pgcnt);
2382		cleaned_count++;
2383
2384		/* place incomplete frames back on ring for completion */
2385		if (ixgbe_is_non_eop(rx_ring, rx_desc, skb))
2386			continue;
2387
2388		/* verify the packet layout is correct */
2389		if (ixgbe_cleanup_headers(rx_ring, rx_desc, skb))
2390			continue;
2391
2392		/* probably a little skewed due to removing CRC */
2393		total_rx_bytes += skb->len;
2394
2395		/* populate checksum, timestamp, VLAN, and protocol */
2396		ixgbe_process_skb_fields(rx_ring, rx_desc, skb);
2397
2398#ifdef IXGBE_FCOE
2399		/* if ddp, not passing to ULD unless for FCP_RSP or error */
2400		if (ixgbe_rx_is_fcoe(rx_ring, rx_desc)) {
2401			ddp_bytes = ixgbe_fcoe_ddp(adapter, rx_desc, skb);
2402			/* include DDPed FCoE data */
2403			if (ddp_bytes > 0) {
2404				if (!mss) {
2405					mss = rx_ring->netdev->mtu -
2406						sizeof(struct fcoe_hdr) -
2407						sizeof(struct fc_frame_header) -
2408						sizeof(struct fcoe_crc_eof);
2409					if (mss > 512)
2410						mss &= ~511;
2411				}
2412				total_rx_bytes += ddp_bytes;
2413				total_rx_packets += DIV_ROUND_UP(ddp_bytes,
2414								 mss);
2415			}
2416			if (!ddp_bytes) {
2417				dev_kfree_skb_any(skb);
2418				continue;
2419			}
2420		}
2421
2422#endif /* IXGBE_FCOE */
2423		ixgbe_rx_skb(q_vector, skb);
2424
2425		/* update budget accounting */
2426		total_rx_packets++;
2427	}
2428
2429	if (xdp_xmit & IXGBE_XDP_REDIR)
2430		xdp_do_flush_map();
2431
2432	if (xdp_xmit & IXGBE_XDP_TX) {
2433		struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()];
2434
2435		/* Force memory writes to complete before letting h/w
2436		 * know there are new descriptors to fetch.
2437		 */
2438		wmb();
2439		writel(ring->next_to_use, ring->tail);
2440	}
2441
2442	u64_stats_update_begin(&rx_ring->syncp);
2443	rx_ring->stats.packets += total_rx_packets;
2444	rx_ring->stats.bytes += total_rx_bytes;
2445	u64_stats_update_end(&rx_ring->syncp);
2446	q_vector->rx.total_packets += total_rx_packets;
2447	q_vector->rx.total_bytes += total_rx_bytes;
2448
2449	return total_rx_packets;
2450}
2451
2452/**
2453 * ixgbe_configure_msix - Configure MSI-X hardware
2454 * @adapter: board private structure
2455 *
2456 * ixgbe_configure_msix sets up the hardware to properly generate MSI-X
2457 * interrupts.
2458 **/
2459static void ixgbe_configure_msix(struct ixgbe_adapter *adapter)
2460{
2461	struct ixgbe_q_vector *q_vector;
2462	int v_idx;
2463	u32 mask;
2464
2465	/* Populate MSIX to EITR Select */
2466	if (adapter->num_vfs > 32) {
2467		u32 eitrsel = BIT(adapter->num_vfs - 32) - 1;
2468		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EITRSEL, eitrsel);
2469	}
2470
2471	/*
2472	 * Populate the IVAR table and set the ITR values to the
2473	 * corresponding register.
2474	 */
2475	for (v_idx = 0; v_idx < adapter->num_q_vectors; v_idx++) {
2476		struct ixgbe_ring *ring;
2477		q_vector = adapter->q_vector[v_idx];
2478
2479		ixgbe_for_each_ring(ring, q_vector->rx)
2480			ixgbe_set_ivar(adapter, 0, ring->reg_idx, v_idx);
2481
2482		ixgbe_for_each_ring(ring, q_vector->tx)
2483			ixgbe_set_ivar(adapter, 1, ring->reg_idx, v_idx);
2484
2485		ixgbe_write_eitr(q_vector);
2486	}
2487
2488	switch (adapter->hw.mac.type) {
2489	case ixgbe_mac_82598EB:
2490		ixgbe_set_ivar(adapter, -1, IXGBE_IVAR_OTHER_CAUSES_INDEX,
2491			       v_idx);
2492		break;
2493	case ixgbe_mac_82599EB:
2494	case ixgbe_mac_X540:
2495	case ixgbe_mac_X550:
2496	case ixgbe_mac_X550EM_x:
2497	case ixgbe_mac_x550em_a:
2498		ixgbe_set_ivar(adapter, -1, 1, v_idx);
2499		break;
2500	default:
2501		break;
2502	}
2503	IXGBE_WRITE_REG(&adapter->hw, IXGBE_EITR(v_idx), 1950);
2504
2505	/* set up to autoclear timer, and the vectors */
2506	mask = IXGBE_EIMS_ENABLE_MASK;
2507	mask &= ~(IXGBE_EIMS_OTHER |
2508		  IXGBE_EIMS_MAILBOX |
2509		  IXGBE_EIMS_LSC);
2510
2511	IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIAC, mask);
2512}
2513
2514/**
2515 * ixgbe_update_itr - update the dynamic ITR value based on statistics
2516 * @q_vector: structure containing interrupt and ring information
2517 * @ring_container: structure containing ring performance data
2518 *
2519 *      Stores a new ITR value based on packets and byte
2520 *      counts during the last interrupt.  The advantage of per interrupt
2521 *      computation is faster updates and more accurate ITR for the current
2522 *      traffic pattern.  Constants in this function were computed
2523 *      based on theoretical maximum wire speed and thresholds were set based
2524 *      on testing data as well as attempting to minimize response time
2525 *      while increasing bulk throughput.
2526 **/
2527static void ixgbe_update_itr(struct ixgbe_q_vector *q_vector,
2528			     struct ixgbe_ring_container *ring_container)
2529{
2530	unsigned int itr = IXGBE_ITR_ADAPTIVE_MIN_USECS |
2531			   IXGBE_ITR_ADAPTIVE_LATENCY;
2532	unsigned int avg_wire_size, packets, bytes;
2533	unsigned long next_update = jiffies;
2534
2535	/* If we don't have any rings just leave ourselves set for maximum
2536	 * possible latency so we take ourselves out of the equation.
2537	 */
2538	if (!ring_container->ring)
2539		return;
2540
2541	/* If we didn't update within up to 1 - 2 jiffies we can assume
2542	 * that either packets are coming in so slow there hasn't been
2543	 * any work, or that there is so much work that NAPI is dealing
2544	 * with interrupt moderation and we don't need to do anything.
2545	 */
2546	if (time_after(next_update, ring_container->next_update))
2547		goto clear_counts;
2548
2549	packets = ring_container->total_packets;
2550
2551	/* We have no packets to actually measure against. This means
2552	 * either one of the other queues on this vector is active or
2553	 * we are a Tx queue doing TSO with too high of an interrupt rate.
2554	 *
2555	 * When this occurs just tick up our delay by the minimum value
2556	 * and hope that this extra delay will prevent us from being called
2557	 * without any work on our queue.
2558	 */
2559	if (!packets) {
2560		itr = (q_vector->itr >> 2) + IXGBE_ITR_ADAPTIVE_MIN_INC;
2561		if (itr > IXGBE_ITR_ADAPTIVE_MAX_USECS)
2562			itr = IXGBE_ITR_ADAPTIVE_MAX_USECS;
2563		itr += ring_container->itr & IXGBE_ITR_ADAPTIVE_LATENCY;
2564		goto clear_counts;
2565	}
2566
2567	bytes = ring_container->total_bytes;
2568
2569	/* If packets are less than 4 or bytes are less than 9000 assume
2570	 * insufficient data to use bulk rate limiting approach. We are
2571	 * likely latency driven.
2572	 */
2573	if (packets < 4 && bytes < 9000) {
2574		itr = IXGBE_ITR_ADAPTIVE_LATENCY;
2575		goto adjust_by_size;
2576	}
2577
2578	/* Between 4 and 48 we can assume that our current interrupt delay
2579	 * is only slightly too low. As such we should increase it by a small
2580	 * fixed amount.
2581	 */
2582	if (packets < 48) {
2583		itr = (q_vector->itr >> 2) + IXGBE_ITR_ADAPTIVE_MIN_INC;
2584		if (itr > IXGBE_ITR_ADAPTIVE_MAX_USECS)
2585			itr = IXGBE_ITR_ADAPTIVE_MAX_USECS;
2586		goto clear_counts;
2587	}
2588
2589	/* Between 48 and 96 is our "goldilocks" zone where we are working
2590	 * out "just right". Just report that our current ITR is good for us.
2591	 */
2592	if (packets < 96) {
2593		itr = q_vector->itr >> 2;
2594		goto clear_counts;
2595	}
2596
2597	/* If packet count is 96 or greater we are likely looking at a slight
2598	 * overrun of the delay we want. Try halving our delay to see if that
2599	 * will cut the number of packets in half per interrupt.
2600	 */
2601	if (packets < 256) {
2602		itr = q_vector->itr >> 3;
2603		if (itr < IXGBE_ITR_ADAPTIVE_MIN_USECS)
2604			itr = IXGBE_ITR_ADAPTIVE_MIN_USECS;
2605		goto clear_counts;
2606	}
2607
2608	/* The paths below assume we are dealing with a bulk ITR since number
2609	 * of packets is 256 or greater. We are just going to have to compute
2610	 * a value and try to bring the count under control, though for smaller
2611	 * packet sizes there isn't much we can do as NAPI polling will likely
2612	 * be kicking in sooner rather than later.
2613	 */
2614	itr = IXGBE_ITR_ADAPTIVE_BULK;
2615
2616adjust_by_size:
2617	/* If packet counts are 256 or greater we can assume we have a gross
2618	 * overestimation of what the rate should be. Instead of trying to fine
2619	 * tune it just use the formula below to try and dial in an exact value
2620	 * give the current packet size of the frame.
2621	 */
2622	avg_wire_size = bytes / packets;
2623
2624	/* The following is a crude approximation of:
2625	 *  wmem_default / (size + overhead) = desired_pkts_per_int
2626	 *  rate / bits_per_byte / (size + ethernet overhead) = pkt_rate
2627	 *  (desired_pkt_rate / pkt_rate) * usecs_per_sec = ITR value
2628	 *
2629	 * Assuming wmem_default is 212992 and overhead is 640 bytes per
2630	 * packet, (256 skb, 64 headroom, 320 shared info), we can reduce the
2631	 * formula down to
2632	 *
2633	 *  (170 * (size + 24)) / (size + 640) = ITR
2634	 *
2635	 * We first do some math on the packet size and then finally bitshift
2636	 * by 8 after rounding up. We also have to account for PCIe link speed
2637	 * difference as ITR scales based on this.
2638	 */
2639	if (avg_wire_size <= 60) {
2640		/* Start at 50k ints/sec */
2641		avg_wire_size = 5120;
2642	} else if (avg_wire_size <= 316) {
2643		/* 50K ints/sec to 16K ints/sec */
2644		avg_wire_size *= 40;
2645		avg_wire_size += 2720;
2646	} else if (avg_wire_size <= 1084) {
2647		/* 16K ints/sec to 9.2K ints/sec */
2648		avg_wire_size *= 15;
2649		avg_wire_size += 11452;
2650	} else if (avg_wire_size < 1968) {
2651		/* 9.2K ints/sec to 8K ints/sec */
2652		avg_wire_size *= 5;
2653		avg_wire_size += 22420;
2654	} else {
2655		/* plateau at a limit of 8K ints/sec */
2656		avg_wire_size = 32256;
2657	}
2658
2659	/* If we are in low latency mode half our delay which doubles the rate
2660	 * to somewhere between 100K to 16K ints/sec
2661	 */
2662	if (itr & IXGBE_ITR_ADAPTIVE_LATENCY)
2663		avg_wire_size >>= 1;
2664
2665	/* Resultant value is 256 times larger than it needs to be. This
2666	 * gives us room to adjust the value as needed to either increase
2667	 * or decrease the value based on link speeds of 10G, 2.5G, 1G, etc.
2668	 *
2669	 * Use addition as we have already recorded the new latency flag
2670	 * for the ITR value.
2671	 */
2672	switch (q_vector->adapter->link_speed) {
2673	case IXGBE_LINK_SPEED_10GB_FULL:
2674	case IXGBE_LINK_SPEED_100_FULL:
2675	default:
2676		itr += DIV_ROUND_UP(avg_wire_size,
2677				    IXGBE_ITR_ADAPTIVE_MIN_INC * 256) *
2678		       IXGBE_ITR_ADAPTIVE_MIN_INC;
2679		break;
2680	case IXGBE_LINK_SPEED_2_5GB_FULL:
2681	case IXGBE_LINK_SPEED_1GB_FULL:
2682	case IXGBE_LINK_SPEED_10_FULL:
2683		if (avg_wire_size > 8064)
2684			avg_wire_size = 8064;
2685		itr += DIV_ROUND_UP(avg_wire_size,
2686				    IXGBE_ITR_ADAPTIVE_MIN_INC * 64) *
2687		       IXGBE_ITR_ADAPTIVE_MIN_INC;
2688		break;
2689	}
2690
2691clear_counts:
2692	/* write back value */
2693	ring_container->itr = itr;
2694
2695	/* next update should occur within next jiffy */
2696	ring_container->next_update = next_update + 1;
2697
2698	ring_container->total_bytes = 0;
2699	ring_container->total_packets = 0;
2700}
2701
2702/**
2703 * ixgbe_write_eitr - write EITR register in hardware specific way
2704 * @q_vector: structure containing interrupt and ring information
2705 *
2706 * This function is made to be called by ethtool and by the driver
2707 * when it needs to update EITR registers at runtime.  Hardware
2708 * specific quirks/differences are taken care of here.
2709 */
2710void ixgbe_write_eitr(struct ixgbe_q_vector *q_vector)
2711{
2712	struct ixgbe_adapter *adapter = q_vector->adapter;
2713	struct ixgbe_hw *hw = &adapter->hw;
2714	int v_idx = q_vector->v_idx;
2715	u32 itr_reg = q_vector->itr & IXGBE_MAX_EITR;
2716
2717	switch (adapter->hw.mac.type) {
2718	case ixgbe_mac_82598EB:
2719		/* must write high and low 16 bits to reset counter */
2720		itr_reg |= (itr_reg << 16);
2721		break;
2722	case ixgbe_mac_82599EB:
2723	case ixgbe_mac_X540:
2724	case ixgbe_mac_X550:
2725	case ixgbe_mac_X550EM_x:
2726	case ixgbe_mac_x550em_a:
2727		/*
2728		 * set the WDIS bit to not clear the timer bits and cause an
2729		 * immediate assertion of the interrupt
2730		 */
2731		itr_reg |= IXGBE_EITR_CNT_WDIS;
2732		break;
2733	default:
2734		break;
2735	}
2736	IXGBE_WRITE_REG(hw, IXGBE_EITR(v_idx), itr_reg);
2737}
2738
2739static void ixgbe_set_itr(struct ixgbe_q_vector *q_vector)
2740{
2741	u32 new_itr;
2742
2743	ixgbe_update_itr(q_vector, &q_vector->tx);
2744	ixgbe_update_itr(q_vector, &q_vector->rx);
2745
2746	/* use the smallest value of new ITR delay calculations */
2747	new_itr = min(q_vector->rx.itr, q_vector->tx.itr);
2748
2749	/* Clear latency flag if set, shift into correct position */
2750	new_itr &= ~IXGBE_ITR_ADAPTIVE_LATENCY;
2751	new_itr <<= 2;
2752
2753	if (new_itr != q_vector->itr) {
2754		/* save the algorithm value here */
2755		q_vector->itr = new_itr;
2756
2757		ixgbe_write_eitr(q_vector);
2758	}
2759}
2760
2761/**
2762 * ixgbe_check_overtemp_subtask - check for over temperature
2763 * @adapter: pointer to adapter
2764 **/
2765static void ixgbe_check_overtemp_subtask(struct ixgbe_adapter *adapter)
2766{
2767	struct ixgbe_hw *hw = &adapter->hw;
2768	u32 eicr = adapter->interrupt_event;
2769
2770	if (test_bit(__IXGBE_DOWN, &adapter->state))
2771		return;
2772
2773	if (!(adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_EVENT))
2774		return;
2775
2776	adapter->flags2 &= ~IXGBE_FLAG2_TEMP_SENSOR_EVENT;
2777
2778	switch (hw->device_id) {
2779	case IXGBE_DEV_ID_82599_T3_LOM:
2780		/*
2781		 * Since the warning interrupt is for both ports
2782		 * we don't have to check if:
2783		 *  - This interrupt wasn't for our port.
2784		 *  - We may have missed the interrupt so always have to
2785		 *    check if we  got a LSC
2786		 */
2787		if (!(eicr & IXGBE_EICR_GPI_SDP0_8259X) &&
2788		    !(eicr & IXGBE_EICR_LSC))
2789			return;
2790
2791		if (!(eicr & IXGBE_EICR_LSC) && hw->mac.ops.check_link) {
2792			u32 speed;
2793			bool link_up = false;
2794
2795			hw->mac.ops.check_link(hw, &speed, &link_up, false);
2796
2797			if (link_up)
2798				return;
2799		}
2800
2801		/* Check if this is not due to overtemp */
2802		if (!hw->phy.ops.check_overtemp(hw))
2803			return;
2804
2805		break;
2806	case IXGBE_DEV_ID_X550EM_A_1G_T:
2807	case IXGBE_DEV_ID_X550EM_A_1G_T_L:
2808		if (!hw->phy.ops.check_overtemp(hw))
2809			return;
2810		break;
2811	default:
2812		if (adapter->hw.mac.type >= ixgbe_mac_X540)
2813			return;
2814		if (!(eicr & IXGBE_EICR_GPI_SDP0(hw)))
2815			return;
2816		break;
2817	}
2818	e_crit(drv, "%s\n", ixgbe_overheat_msg);
2819
2820	adapter->interrupt_event = 0;
2821}
2822
2823static void ixgbe_check_fan_failure(struct ixgbe_adapter *adapter, u32 eicr)
2824{
2825	struct ixgbe_hw *hw = &adapter->hw;
2826
2827	if ((adapter->flags & IXGBE_FLAG_FAN_FAIL_CAPABLE) &&
2828	    (eicr & IXGBE_EICR_GPI_SDP1(hw))) {
2829		e_crit(probe, "Fan has stopped, replace the adapter\n");
2830		/* write to clear the interrupt */
2831		IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP1(hw));
2832	}
2833}
2834
2835static void ixgbe_check_overtemp_event(struct ixgbe_adapter *adapter, u32 eicr)
2836{
2837	struct ixgbe_hw *hw = &adapter->hw;
2838
2839	if (!(adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE))
2840		return;
2841
2842	switch (adapter->hw.mac.type) {
2843	case ixgbe_mac_82599EB:
2844		/*
2845		 * Need to check link state so complete overtemp check
2846		 * on service task
2847		 */
2848		if (((eicr & IXGBE_EICR_GPI_SDP0(hw)) ||
2849		     (eicr & IXGBE_EICR_LSC)) &&
2850		    (!test_bit(__IXGBE_DOWN, &adapter->state))) {
2851			adapter->interrupt_event = eicr;
2852			adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_EVENT;
2853			ixgbe_service_event_schedule(adapter);
2854			return;
2855		}
2856		return;
2857	case ixgbe_mac_x550em_a:
2858		if (eicr & IXGBE_EICR_GPI_SDP0_X550EM_a) {
2859			adapter->interrupt_event = eicr;
2860			adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_EVENT;
2861			ixgbe_service_event_schedule(adapter);
2862			IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC,
2863					IXGBE_EICR_GPI_SDP0_X550EM_a);
2864			IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICR,
2865					IXGBE_EICR_GPI_SDP0_X550EM_a);
2866		}
2867		return;
2868	case ixgbe_mac_X550:
2869	case ixgbe_mac_X540:
2870		if (!(eicr & IXGBE_EICR_TS))
2871			return;
2872		break;
2873	default:
2874		return;
2875	}
2876
2877	e_crit(drv, "%s\n", ixgbe_overheat_msg);
2878}
2879
2880static inline bool ixgbe_is_sfp(struct ixgbe_hw *hw)
2881{
2882	switch (hw->mac.type) {
2883	case ixgbe_mac_82598EB:
2884		if (hw->phy.type == ixgbe_phy_nl)
2885			return true;
2886		return false;
2887	case ixgbe_mac_82599EB:
2888	case ixgbe_mac_X550EM_x:
2889	case ixgbe_mac_x550em_a:
2890		switch (hw->mac.ops.get_media_type(hw)) {
2891		case ixgbe_media_type_fiber:
2892		case ixgbe_media_type_fiber_qsfp:
2893			return true;
2894		default:
2895			return false;
2896		}
2897	default:
2898		return false;
2899	}
2900}
2901
2902static void ixgbe_check_sfp_event(struct ixgbe_adapter *adapter, u32 eicr)
2903{
2904	struct ixgbe_hw *hw = &adapter->hw;
2905	u32 eicr_mask = IXGBE_EICR_GPI_SDP2(hw);
2906
2907	if (!ixgbe_is_sfp(hw))
2908		return;
2909
2910	/* Later MAC's use different SDP */
2911	if (hw->mac.type >= ixgbe_mac_X540)
2912		eicr_mask = IXGBE_EICR_GPI_SDP0_X540;
2913
2914	if (eicr & eicr_mask) {
2915		/* Clear the interrupt */
2916		IXGBE_WRITE_REG(hw, IXGBE_EICR, eicr_mask);
2917		if (!test_bit(__IXGBE_DOWN, &adapter->state)) {
2918			adapter->flags2 |= IXGBE_FLAG2_SFP_NEEDS_RESET;
2919			adapter->sfp_poll_time = 0;
2920			ixgbe_service_event_schedule(adapter);
2921		}
2922	}
2923
2924	if (adapter->hw.mac.type == ixgbe_mac_82599EB &&
2925	    (eicr & IXGBE_EICR_GPI_SDP1(hw))) {
2926		/* Clear the interrupt */
2927		IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP1(hw));
2928		if (!test_bit(__IXGBE_DOWN, &adapter->state)) {
2929			adapter->flags |= IXGBE_FLAG_NEED_LINK_CONFIG;
2930			ixgbe_service_event_schedule(adapter);
2931		}
2932	}
2933}
2934
2935static void ixgbe_check_lsc(struct ixgbe_adapter *adapter)
2936{
2937	struct ixgbe_hw *hw = &adapter->hw;
2938
2939	adapter->lsc_int++;
2940	adapter->flags |= IXGBE_FLAG_NEED_LINK_UPDATE;
2941	adapter->link_check_timeout = jiffies;
2942	if (!test_bit(__IXGBE_DOWN, &adapter->state)) {
2943		IXGBE_WRITE_REG(hw, IXGBE_EIMC, IXGBE_EIMC_LSC);
2944		IXGBE_WRITE_FLUSH(hw);
2945		ixgbe_service_event_schedule(adapter);
2946	}
2947}
2948
2949static inline void ixgbe_irq_enable_queues(struct ixgbe_adapter *adapter,
2950					   u64 qmask)
2951{
2952	u32 mask;
2953	struct ixgbe_hw *hw = &adapter->hw;
2954
2955	switch (hw->mac.type) {
2956	case ixgbe_mac_82598EB:
2957		mask = (IXGBE_EIMS_RTX_QUEUE & qmask);
2958		IXGBE_WRITE_REG(hw, IXGBE_EIMS, mask);
2959		break;
2960	case ixgbe_mac_82599EB:
2961	case ixgbe_mac_X540:
2962	case ixgbe_mac_X550:
2963	case ixgbe_mac_X550EM_x:
2964	case ixgbe_mac_x550em_a:
2965		mask = (qmask & 0xFFFFFFFF);
2966		if (mask)
2967			IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(0), mask);
2968		mask = (qmask >> 32);
2969		if (mask)
2970			IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(1), mask);
2971		break;
2972	default:
2973		break;
2974	}
2975	/* skip the flush */
2976}
2977
2978/**
2979 * ixgbe_irq_enable - Enable default interrupt generation settings
2980 * @adapter: board private structure
2981 * @queues: enable irqs for queues
2982 * @flush: flush register write
2983 **/
2984static inline void ixgbe_irq_enable(struct ixgbe_adapter *adapter, bool queues,
2985				    bool flush)
2986{
2987	struct ixgbe_hw *hw = &adapter->hw;
2988	u32 mask = (IXGBE_EIMS_ENABLE_MASK & ~IXGBE_EIMS_RTX_QUEUE);
2989
2990	/* don't reenable LSC while waiting for link */
2991	if (adapter->flags & IXGBE_FLAG_NEED_LINK_UPDATE)
2992		mask &= ~IXGBE_EIMS_LSC;
2993
2994	if (adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE)
2995		switch (adapter->hw.mac.type) {
2996		case ixgbe_mac_82599EB:
2997			mask |= IXGBE_EIMS_GPI_SDP0(hw);
2998			break;
2999		case ixgbe_mac_X540:
3000		case ixgbe_mac_X550:
3001		case ixgbe_mac_X550EM_x:
3002		case ixgbe_mac_x550em_a:
3003			mask |= IXGBE_EIMS_TS;
3004			break;
3005		default:
3006			break;
3007		}
3008	if (adapter->flags & IXGBE_FLAG_FAN_FAIL_CAPABLE)
3009		mask |= IXGBE_EIMS_GPI_SDP1(hw);
3010	switch (adapter->hw.mac.type) {
3011	case ixgbe_mac_82599EB:
3012		mask |= IXGBE_EIMS_GPI_SDP1(hw);
3013		mask |= IXGBE_EIMS_GPI_SDP2(hw);
3014		fallthrough;
3015	case ixgbe_mac_X540:
3016	case ixgbe_mac_X550:
3017	case ixgbe_mac_X550EM_x:
3018	case ixgbe_mac_x550em_a:
3019		if (adapter->hw.device_id == IXGBE_DEV_ID_X550EM_X_SFP ||
3020		    adapter->hw.device_id == IXGBE_DEV_ID_X550EM_A_SFP ||
3021		    adapter->hw.device_id == IXGBE_DEV_ID_X550EM_A_SFP_N)
3022			mask |= IXGBE_EIMS_GPI_SDP0(&adapter->hw);
3023		if (adapter->hw.phy.type == ixgbe_phy_x550em_ext_t)
3024			mask |= IXGBE_EICR_GPI_SDP0_X540;
3025		mask |= IXGBE_EIMS_ECC;
3026		mask |= IXGBE_EIMS_MAILBOX;
3027		break;
3028	default:
3029		break;
3030	}
3031
3032	if ((adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) &&
3033	    !(adapter->flags2 & IXGBE_FLAG2_FDIR_REQUIRES_REINIT))
3034		mask |= IXGBE_EIMS_FLOW_DIR;
3035
3036	IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMS, mask);
3037	if (queues)
3038		ixgbe_irq_enable_queues(adapter, ~0);
3039	if (flush)
3040		IXGBE_WRITE_FLUSH(&adapter->hw);
3041}
3042
3043static irqreturn_t ixgbe_msix_other(int irq, void *data)
3044{
3045	struct ixgbe_adapter *adapter = data;
3046	struct ixgbe_hw *hw = &adapter->hw;
3047	u32 eicr;
3048
3049	/*
3050	 * Workaround for Silicon errata.  Use clear-by-write instead
3051	 * of clear-by-read.  Reading with EICS will return the
3052	 * interrupt causes without clearing, which later be done
3053	 * with the write to EICR.
3054	 */
3055	eicr = IXGBE_READ_REG(hw, IXGBE_EICS);
3056
3057	/* The lower 16bits of the EICR register are for the queue interrupts
3058	 * which should be masked here in order to not accidentally clear them if
3059	 * the bits are high when ixgbe_msix_other is called. There is a race
3060	 * condition otherwise which results in possible performance loss
3061	 * especially if the ixgbe_msix_other interrupt is triggering
3062	 * consistently (as it would when PPS is turned on for the X540 device)
3063	 */
3064	eicr &= 0xFFFF0000;
3065
3066	IXGBE_WRITE_REG(hw, IXGBE_EICR, eicr);
3067
3068	if (eicr & IXGBE_EICR_LSC)
3069		ixgbe_check_lsc(adapter);
3070
3071	if (eicr & IXGBE_EICR_MAILBOX)
3072		ixgbe_msg_task(adapter);
3073
3074	switch (hw->mac.type) {
3075	case ixgbe_mac_82599EB:
3076	case ixgbe_mac_X540:
3077	case ixgbe_mac_X550:
3078	case ixgbe_mac_X550EM_x:
3079	case ixgbe_mac_x550em_a:
3080		if (hw->phy.type == ixgbe_phy_x550em_ext_t &&
3081		    (eicr & IXGBE_EICR_GPI_SDP0_X540)) {
3082			adapter->flags2 |= IXGBE_FLAG2_PHY_INTERRUPT;
3083			ixgbe_service_event_schedule(adapter);
3084			IXGBE_WRITE_REG(hw, IXGBE_EICR,
3085					IXGBE_EICR_GPI_SDP0_X540);
3086		}
3087		if (eicr & IXGBE_EICR_ECC) {
3088			e_info(link, "Received ECC Err, initiating reset\n");
3089			set_bit(__IXGBE_RESET_REQUESTED, &adapter->state);
3090			ixgbe_service_event_schedule(adapter);
3091			IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_ECC);
3092		}
3093		/* Handle Flow Director Full threshold interrupt */
3094		if (eicr & IXGBE_EICR_FLOW_DIR) {
3095			int reinit_count = 0;
3096			int i;
3097			for (i = 0; i < adapter->num_tx_queues; i++) {
3098				struct ixgbe_ring *ring = adapter->tx_ring[i];
3099				if (test_and_clear_bit(__IXGBE_TX_FDIR_INIT_DONE,
3100						       &ring->state))
3101					reinit_count++;
3102			}
3103			if (reinit_count) {
3104				/* no more flow director interrupts until after init */
3105				IXGBE_WRITE_REG(hw, IXGBE_EIMC, IXGBE_EIMC_FLOW_DIR);
3106				adapter->flags2 |= IXGBE_FLAG2_FDIR_REQUIRES_REINIT;
3107				ixgbe_service_event_schedule(adapter);
3108			}
3109		}
3110		ixgbe_check_sfp_event(adapter, eicr);
3111		ixgbe_check_overtemp_event(adapter, eicr);
3112		break;
3113	default:
3114		break;
3115	}
3116
3117	ixgbe_check_fan_failure(adapter, eicr);
3118
3119	if (unlikely(eicr & IXGBE_EICR_TIMESYNC))
3120		ixgbe_ptp_check_pps_event(adapter);
3121
3122	/* re-enable the original interrupt state, no lsc, no queues */
3123	if (!test_bit(__IXGBE_DOWN, &adapter->state))
3124		ixgbe_irq_enable(adapter, false, false);
3125
3126	return IRQ_HANDLED;
3127}
3128
3129static irqreturn_t ixgbe_msix_clean_rings(int irq, void *data)
3130{
3131	struct ixgbe_q_vector *q_vector = data;
3132
3133	/* EIAM disabled interrupts (on this vector) for us */
3134
3135	if (q_vector->rx.ring || q_vector->tx.ring)
3136		napi_schedule_irqoff(&q_vector->napi);
3137
3138	return IRQ_HANDLED;
3139}
3140
3141/**
3142 * ixgbe_poll - NAPI Rx polling callback
3143 * @napi: structure for representing this polling device
3144 * @budget: how many packets driver is allowed to clean
3145 *
3146 * This function is used for legacy and MSI, NAPI mode
3147 **/
3148int ixgbe_poll(struct napi_struct *napi, int budget)
3149{
3150	struct ixgbe_q_vector *q_vector =
3151				container_of(napi, struct ixgbe_q_vector, napi);
3152	struct ixgbe_adapter *adapter = q_vector->adapter;
3153	struct ixgbe_ring *ring;
3154	int per_ring_budget, work_done = 0;
3155	bool clean_complete = true;
3156
3157#ifdef CONFIG_IXGBE_DCA
3158	if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
3159		ixgbe_update_dca(q_vector);
3160#endif
3161
3162	ixgbe_for_each_ring(ring, q_vector->tx) {
3163		bool wd = ring->xsk_pool ?
3164			  ixgbe_clean_xdp_tx_irq(q_vector, ring, budget) :
3165			  ixgbe_clean_tx_irq(q_vector, ring, budget);
3166
3167		if (!wd)
3168			clean_complete = false;
3169	}
3170
3171	/* Exit if we are called by netpoll */
3172	if (budget <= 0)
3173		return budget;
3174
3175	/* attempt to distribute budget to each queue fairly, but don't allow
3176	 * the budget to go below 1 because we'll exit polling */
3177	if (q_vector->rx.count > 1)
3178		per_ring_budget = max(budget/q_vector->rx.count, 1);
3179	else
3180		per_ring_budget = budget;
3181
3182	ixgbe_for_each_ring(ring, q_vector->rx) {
3183		int cleaned = ring->xsk_pool ?
3184			      ixgbe_clean_rx_irq_zc(q_vector, ring,
3185						    per_ring_budget) :
3186			      ixgbe_clean_rx_irq(q_vector, ring,
3187						 per_ring_budget);
3188
3189		work_done += cleaned;
3190		if (cleaned >= per_ring_budget)
3191			clean_complete = false;
3192	}
3193
3194	/* If all work not completed, return budget and keep polling */
3195	if (!clean_complete)
3196		return budget;
3197
3198	/* all work done, exit the polling mode */
3199	if (likely(napi_complete_done(napi, work_done))) {
3200		if (adapter->rx_itr_setting & 1)
3201			ixgbe_set_itr(q_vector);
3202		if (!test_bit(__IXGBE_DOWN, &adapter->state))
3203			ixgbe_irq_enable_queues(adapter,
3204						BIT_ULL(q_vector->v_idx));
3205	}
3206
3207	return min(work_done, budget - 1);
3208}
3209
3210/**
3211 * ixgbe_request_msix_irqs - Initialize MSI-X interrupts
3212 * @adapter: board private structure
3213 *
3214 * ixgbe_request_msix_irqs allocates MSI-X vectors and requests
3215 * interrupts from the kernel.
3216 **/
3217static int ixgbe_request_msix_irqs(struct ixgbe_adapter *adapter)
3218{
3219	struct net_device *netdev = adapter->netdev;
3220	unsigned int ri = 0, ti = 0;
3221	int vector, err;
3222
3223	for (vector = 0; vector < adapter->num_q_vectors; vector++) {
3224		struct ixgbe_q_vector *q_vector = adapter->q_vector[vector];
3225		struct msix_entry *entry = &adapter->msix_entries[vector];
3226
3227		if (q_vector->tx.ring && q_vector->rx.ring) {
3228			snprintf(q_vector->name, sizeof(q_vector->name),
3229				 "%s-TxRx-%u", netdev->name, ri++);
3230			ti++;
3231		} else if (q_vector->rx.ring) {
3232			snprintf(q_vector->name, sizeof(q_vector->name),
3233				 "%s-rx-%u", netdev->name, ri++);
3234		} else if (q_vector->tx.ring) {
3235			snprintf(q_vector->name, sizeof(q_vector->name),
3236				 "%s-tx-%u", netdev->name, ti++);
3237		} else {
3238			/* skip this unused q_vector */
3239			continue;
3240		}
3241		err = request_irq(entry->vector, &ixgbe_msix_clean_rings, 0,
3242				  q_vector->name, q_vector);
3243		if (err) {
3244			e_err(probe, "request_irq failed for MSIX interrupt "
3245			      "Error: %d\n", err);
3246			goto free_queue_irqs;
3247		}
3248		/* If Flow Director is enabled, set interrupt affinity */
3249		if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) {
3250			/* assign the mask for this irq */
3251			irq_set_affinity_hint(entry->vector,
3252					      &q_vector->affinity_mask);
3253		}
3254	}
3255
3256	err = request_irq(adapter->msix_entries[vector].vector,
3257			  ixgbe_msix_other, 0, netdev->name, adapter);
3258	if (err) {
3259		e_err(probe, "request_irq for msix_other failed: %d\n", err);
3260		goto free_queue_irqs;
3261	}
3262
3263	return 0;
3264
3265free_queue_irqs:
3266	while (vector) {
3267		vector--;
3268		irq_set_affinity_hint(adapter->msix_entries[vector].vector,
3269				      NULL);
3270		free_irq(adapter->msix_entries[vector].vector,
3271			 adapter->q_vector[vector]);
3272	}
3273	adapter->flags &= ~IXGBE_FLAG_MSIX_ENABLED;
3274	pci_disable_msix(adapter->pdev);
3275	kfree(adapter->msix_entries);
3276	adapter->msix_entries = NULL;
3277	return err;
3278}
3279
3280/**
3281 * ixgbe_intr - legacy mode Interrupt Handler
3282 * @irq: interrupt number
3283 * @data: pointer to a network interface device structure
3284 **/
3285static irqreturn_t ixgbe_intr(int irq, void *data)
3286{
3287	struct ixgbe_adapter *adapter = data;
3288	struct ixgbe_hw *hw = &adapter->hw;
3289	struct ixgbe_q_vector *q_vector = adapter->q_vector[0];
3290	u32 eicr;
3291
3292	/*
3293	 * Workaround for silicon errata #26 on 82598.  Mask the interrupt
3294	 * before the read of EICR.
3295	 */
3296	IXGBE_WRITE_REG(hw, IXGBE_EIMC, IXGBE_IRQ_CLEAR_MASK);
3297
3298	/* for NAPI, using EIAM to auto-mask tx/rx interrupt bits on read
3299	 * therefore no explicit interrupt disable is necessary */
3300	eicr = IXGBE_READ_REG(hw, IXGBE_EICR);
3301	if (!eicr) {
3302		/*
3303		 * shared interrupt alert!
3304		 * make sure interrupts are enabled because the read will
3305		 * have disabled interrupts due to EIAM
3306		 * finish the workaround of silicon errata on 82598.  Unmask
3307		 * the interrupt that we masked before the EICR read.
3308		 */
3309		if (!test_bit(__IXGBE_DOWN, &adapter->state))
3310			ixgbe_irq_enable(adapter, true, true);
3311		return IRQ_NONE;	/* Not our interrupt */
3312	}
3313
3314	if (eicr & IXGBE_EICR_LSC)
3315		ixgbe_check_lsc(adapter);
3316
3317	switch (hw->mac.type) {
3318	case ixgbe_mac_82599EB:
3319		ixgbe_check_sfp_event(adapter, eicr);
3320		fallthrough;
3321	case ixgbe_mac_X540:
3322	case ixgbe_mac_X550:
3323	case ixgbe_mac_X550EM_x:
3324	case ixgbe_mac_x550em_a:
3325		if (eicr & IXGBE_EICR_ECC) {
3326			e_info(link, "Received ECC Err, initiating reset\n");
3327			set_bit(__IXGBE_RESET_REQUESTED, &adapter->state);
3328			ixgbe_service_event_schedule(adapter);
3329			IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_ECC);
3330		}
3331		ixgbe_check_overtemp_event(adapter, eicr);
3332		break;
3333	default:
3334		break;
3335	}
3336
3337	ixgbe_check_fan_failure(adapter, eicr);
3338	if (unlikely(eicr & IXGBE_EICR_TIMESYNC))
3339		ixgbe_ptp_check_pps_event(adapter);
3340
3341	/* would disable interrupts here but EIAM disabled it */
3342	napi_schedule_irqoff(&q_vector->napi);
3343
3344	/*
3345	 * re-enable link(maybe) and non-queue interrupts, no flush.
3346	 * ixgbe_poll will re-enable the queue interrupts
3347	 */
3348	if (!test_bit(__IXGBE_DOWN, &adapter->state))
3349		ixgbe_irq_enable(adapter, false, false);
3350
3351	return IRQ_HANDLED;
3352}
3353
3354/**
3355 * ixgbe_request_irq - initialize interrupts
3356 * @adapter: board private structure
3357 *
3358 * Attempts to configure interrupts using the best available
3359 * capabilities of the hardware and kernel.
3360 **/
3361static int ixgbe_request_irq(struct ixgbe_adapter *adapter)
3362{
3363	struct net_device *netdev = adapter->netdev;
3364	int err;
3365
3366	if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED)
3367		err = ixgbe_request_msix_irqs(adapter);
3368	else if (adapter->flags & IXGBE_FLAG_MSI_ENABLED)
3369		err = request_irq(adapter->pdev->irq, ixgbe_intr, 0,
3370				  netdev->name, adapter);
3371	else
3372		err = request_irq(adapter->pdev->irq, ixgbe_intr, IRQF_SHARED,
3373				  netdev->name, adapter);
3374
3375	if (err)
3376		e_err(probe, "request_irq failed, Error %d\n", err);
3377
3378	return err;
3379}
3380
3381static void ixgbe_free_irq(struct ixgbe_adapter *adapter)
3382{
3383	int vector;
3384
3385	if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) {
3386		free_irq(adapter->pdev->irq, adapter);
3387		return;
3388	}
3389
3390	if (!adapter->msix_entries)
3391		return;
3392
3393	for (vector = 0; vector < adapter->num_q_vectors; vector++) {
3394		struct ixgbe_q_vector *q_vector = adapter->q_vector[vector];
3395		struct msix_entry *entry = &adapter->msix_entries[vector];
3396
3397		/* free only the irqs that were actually requested */
3398		if (!q_vector->rx.ring && !q_vector->tx.ring)
3399			continue;
3400
3401		/* clear the affinity_mask in the IRQ descriptor */
3402		irq_set_affinity_hint(entry->vector, NULL);
3403
3404		free_irq(entry->vector, q_vector);
3405	}
3406
3407	free_irq(adapter->msix_entries[vector].vector, adapter);
3408}
3409
3410/**
3411 * ixgbe_irq_disable - Mask off interrupt generation on the NIC
3412 * @adapter: board private structure
3413 **/
3414static inline void ixgbe_irq_disable(struct ixgbe_adapter *adapter)
3415{
3416	switch (adapter->hw.mac.type) {
3417	case ixgbe_mac_82598EB:
3418		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, ~0);
3419		break;
3420	case ixgbe_mac_82599EB:
3421	case ixgbe_mac_X540:
3422	case ixgbe_mac_X550:
3423	case ixgbe_mac_X550EM_x:
3424	case ixgbe_mac_x550em_a:
3425		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, 0xFFFF0000);
3426		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC_EX(0), ~0);
3427		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC_EX(1), ~0);
3428		break;
3429	default:
3430		break;
3431	}
3432	IXGBE_WRITE_FLUSH(&adapter->hw);
3433	if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) {
3434		int vector;
3435
3436		for (vector = 0; vector < adapter->num_q_vectors; vector++)
3437			synchronize_irq(adapter->msix_entries[vector].vector);
3438
3439		synchronize_irq(adapter->msix_entries[vector++].vector);
3440	} else {
3441		synchronize_irq(adapter->pdev->irq);
3442	}
3443}
3444
3445/**
3446 * ixgbe_configure_msi_and_legacy - Initialize PIN (INTA...) and MSI interrupts
3447 * @adapter: board private structure
3448 *
3449 **/
3450static void ixgbe_configure_msi_and_legacy(struct ixgbe_adapter *adapter)
3451{
3452	struct ixgbe_q_vector *q_vector = adapter->q_vector[0];
3453
3454	ixgbe_write_eitr(q_vector);
3455
3456	ixgbe_set_ivar(adapter, 0, 0, 0);
3457	ixgbe_set_ivar(adapter, 1, 0, 0);
3458
3459	e_info(hw, "Legacy interrupt IVAR setup done\n");
3460}
3461
3462/**
3463 * ixgbe_configure_tx_ring - Configure 8259x Tx ring after Reset
3464 * @adapter: board private structure
3465 * @ring: structure containing ring specific data
3466 *
3467 * Configure the Tx descriptor ring after a reset.
3468 **/
3469void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter,
3470			     struct ixgbe_ring *ring)
3471{
3472	struct ixgbe_hw *hw = &adapter->hw;
3473	u64 tdba = ring->dma;
3474	int wait_loop = 10;
3475	u32 txdctl = IXGBE_TXDCTL_ENABLE;
3476	u8 reg_idx = ring->reg_idx;
3477
3478	ring->xsk_pool = NULL;
3479	if (ring_is_xdp(ring))
3480		ring->xsk_pool = ixgbe_xsk_pool(adapter, ring);
3481
3482	/* disable queue to avoid issues while updating state */
3483	IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), 0);
3484	IXGBE_WRITE_FLUSH(hw);
3485
3486	IXGBE_WRITE_REG(hw, IXGBE_TDBAL(reg_idx),
3487			(tdba & DMA_BIT_MASK(32)));
3488	IXGBE_WRITE_REG(hw, IXGBE_TDBAH(reg_idx), (tdba >> 32));
3489	IXGBE_WRITE_REG(hw, IXGBE_TDLEN(reg_idx),
3490			ring->count * sizeof(union ixgbe_adv_tx_desc));
3491	IXGBE_WRITE_REG(hw, IXGBE_TDH(reg_idx), 0);
3492	IXGBE_WRITE_REG(hw, IXGBE_TDT(reg_idx), 0);
3493	ring->tail = adapter->io_addr + IXGBE_TDT(reg_idx);
3494
3495	/*
3496	 * set WTHRESH to encourage burst writeback, it should not be set
3497	 * higher than 1 when:
3498	 * - ITR is 0 as it could cause false TX hangs
3499	 * - ITR is set to > 100k int/sec and BQL is enabled
3500	 *
3501	 * In order to avoid issues WTHRESH + PTHRESH should always be equal
3502	 * to or less than the number of on chip descriptors, which is
3503	 * currently 40.
3504	 */
3505	if (!ring->q_vector || (ring->q_vector->itr < IXGBE_100K_ITR))
3506		txdctl |= 1u << 16;	/* WTHRESH = 1 */
3507	else
3508		txdctl |= 8u << 16;	/* WTHRESH = 8 */
3509
3510	/*
3511	 * Setting PTHRESH to 32 both improves performance
3512	 * and avoids a TX hang with DFP enabled
3513	 */
3514	txdctl |= (1u << 8) |	/* HTHRESH = 1 */
3515		   32;		/* PTHRESH = 32 */
3516
3517	/* reinitialize flowdirector state */
3518	if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) {
3519		ring->atr_sample_rate = adapter->atr_sample_rate;
3520		ring->atr_count = 0;
3521		set_bit(__IXGBE_TX_FDIR_INIT_DONE, &ring->state);
3522	} else {
3523		ring->atr_sample_rate = 0;
3524	}
3525
3526	/* initialize XPS */
3527	if (!test_and_set_bit(__IXGBE_TX_XPS_INIT_DONE, &ring->state)) {
3528		struct ixgbe_q_vector *q_vector = ring->q_vector;
3529
3530		if (q_vector)
3531			netif_set_xps_queue(ring->netdev,
3532					    &q_vector->affinity_mask,
3533					    ring->queue_index);
3534	}
3535
3536	clear_bit(__IXGBE_HANG_CHECK_ARMED, &ring->state);
3537
3538	/* reinitialize tx_buffer_info */
3539	memset(ring->tx_buffer_info, 0,
3540	       sizeof(struct ixgbe_tx_buffer) * ring->count);
3541
3542	/* enable queue */
3543	IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), txdctl);
3544
3545	/* TXDCTL.EN will return 0 on 82598 if link is down, so skip it */
3546	if (hw->mac.type == ixgbe_mac_82598EB &&
3547	    !(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP))
3548		return;
3549
3550	/* poll to verify queue is enabled */
3551	do {
3552		usleep_range(1000, 2000);
3553		txdctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(reg_idx));
3554	} while (--wait_loop && !(txdctl & IXGBE_TXDCTL_ENABLE));
3555	if (!wait_loop)
3556		hw_dbg(hw, "Could not enable Tx Queue %d\n", reg_idx);
3557}
3558
3559static void ixgbe_setup_mtqc(struct ixgbe_adapter *adapter)
3560{
3561	struct ixgbe_hw *hw = &adapter->hw;
3562	u32 rttdcs, mtqc;
3563	u8 tcs = adapter->hw_tcs;
3564
3565	if (hw->mac.type == ixgbe_mac_82598EB)
3566		return;
3567
3568	/* disable the arbiter while setting MTQC */
3569	rttdcs = IXGBE_READ_REG(hw, IXGBE_RTTDCS);
3570	rttdcs |= IXGBE_RTTDCS_ARBDIS;
3571	IXGBE_WRITE_REG(hw, IXGBE_RTTDCS, rttdcs);
3572
3573	/* set transmit pool layout */
3574	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) {
3575		mtqc = IXGBE_MTQC_VT_ENA;
3576		if (tcs > 4)
3577			mtqc |= IXGBE_MTQC_RT_ENA | IXGBE_MTQC_8TC_8TQ;
3578		else if (tcs > 1)
3579			mtqc |= IXGBE_MTQC_RT_ENA | IXGBE_MTQC_4TC_4TQ;
3580		else if (adapter->ring_feature[RING_F_VMDQ].mask ==
3581			 IXGBE_82599_VMDQ_4Q_MASK)
3582			mtqc |= IXGBE_MTQC_32VF;
3583		else
3584			mtqc |= IXGBE_MTQC_64VF;
3585	} else {
3586		if (tcs > 4) {
3587			mtqc = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_8TC_8TQ;
3588		} else if (tcs > 1) {
3589			mtqc = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_4TC_4TQ;
3590		} else {
3591			u8 max_txq = adapter->num_tx_queues +
3592				adapter->num_xdp_queues;
3593			if (max_txq > 63)
3594				mtqc = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_4TC_4TQ;
3595			else
3596				mtqc = IXGBE_MTQC_64Q_1PB;
3597		}
3598	}
3599
3600	IXGBE_WRITE_REG(hw, IXGBE_MTQC, mtqc);
3601
3602	/* Enable Security TX Buffer IFG for multiple pb */
3603	if (tcs) {
3604		u32 sectx = IXGBE_READ_REG(hw, IXGBE_SECTXMINIFG);
3605		sectx |= IXGBE_SECTX_DCB;
3606		IXGBE_WRITE_REG(hw, IXGBE_SECTXMINIFG, sectx);
3607	}
3608
3609	/* re-enable the arbiter */
3610	rttdcs &= ~IXGBE_RTTDCS_ARBDIS;
3611	IXGBE_WRITE_REG(hw, IXGBE_RTTDCS, rttdcs);
3612}
3613
3614/**
3615 * ixgbe_configure_tx - Configure 8259x Transmit Unit after Reset
3616 * @adapter: board private structure
3617 *
3618 * Configure the Tx unit of the MAC after a reset.
3619 **/
3620static void ixgbe_configure_tx(struct ixgbe_adapter *adapter)
3621{
3622	struct ixgbe_hw *hw = &adapter->hw;
3623	u32 dmatxctl;
3624	u32 i;
3625
3626	ixgbe_setup_mtqc(adapter);
3627
3628	if (hw->mac.type != ixgbe_mac_82598EB) {
3629		/* DMATXCTL.EN must be before Tx queues are enabled */
3630		dmatxctl = IXGBE_READ_REG(hw, IXGBE_DMATXCTL);
3631		dmatxctl |= IXGBE_DMATXCTL_TE;
3632		IXGBE_WRITE_REG(hw, IXGBE_DMATXCTL, dmatxctl);
3633	}
3634
3635	/* Setup the HW Tx Head and Tail descriptor pointers */
3636	for (i = 0; i < adapter->num_tx_queues; i++)
3637		ixgbe_configure_tx_ring(adapter, adapter->tx_ring[i]);
3638	for (i = 0; i < adapter->num_xdp_queues; i++)
3639		ixgbe_configure_tx_ring(adapter, adapter->xdp_ring[i]);
3640}
3641
3642static void ixgbe_enable_rx_drop(struct ixgbe_adapter *adapter,
3643				 struct ixgbe_ring *ring)
3644{
3645	struct ixgbe_hw *hw = &adapter->hw;
3646	u8 reg_idx = ring->reg_idx;
3647	u32 srrctl = IXGBE_READ_REG(hw, IXGBE_SRRCTL(reg_idx));
3648
3649	srrctl |= IXGBE_SRRCTL_DROP_EN;
3650
3651	IXGBE_WRITE_REG(hw, IXGBE_SRRCTL(reg_idx), srrctl);
3652}
3653
3654static void ixgbe_disable_rx_drop(struct ixgbe_adapter *adapter,
3655				  struct ixgbe_ring *ring)
3656{
3657	struct ixgbe_hw *hw = &adapter->hw;
3658	u8 reg_idx = ring->reg_idx;
3659	u32 srrctl = IXGBE_READ_REG(hw, IXGBE_SRRCTL(reg_idx));
3660
3661	srrctl &= ~IXGBE_SRRCTL_DROP_EN;
3662
3663	IXGBE_WRITE_REG(hw, IXGBE_SRRCTL(reg_idx), srrctl);
3664}
3665
3666#ifdef CONFIG_IXGBE_DCB
3667void ixgbe_set_rx_drop_en(struct ixgbe_adapter *adapter)
3668#else
3669static void ixgbe_set_rx_drop_en(struct ixgbe_adapter *adapter)
3670#endif
3671{
3672	int i;
3673	bool pfc_en = adapter->dcb_cfg.pfc_mode_enable;
3674
3675	if (adapter->ixgbe_ieee_pfc)
3676		pfc_en |= !!(adapter->ixgbe_ieee_pfc->pfc_en);
3677
3678	/*
3679	 * We should set the drop enable bit if:
3680	 *  SR-IOV is enabled
3681	 *   or
3682	 *  Number of Rx queues > 1 and flow control is disabled
3683	 *
3684	 *  This allows us to avoid head of line blocking for security
3685	 *  and performance reasons.
3686	 */
3687	if (adapter->num_vfs || (adapter->num_rx_queues > 1 &&
3688	    !(adapter->hw.fc.current_mode & ixgbe_fc_tx_pause) && !pfc_en)) {
3689		for (i = 0; i < adapter->num_rx_queues; i++)
3690			ixgbe_enable_rx_drop(adapter, adapter->rx_ring[i]);
3691	} else {
3692		for (i = 0; i < adapter->num_rx_queues; i++)
3693			ixgbe_disable_rx_drop(adapter, adapter->rx_ring[i]);
3694	}
3695}
3696
3697#define IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT 2
3698
3699static void ixgbe_configure_srrctl(struct ixgbe_adapter *adapter,
3700				   struct ixgbe_ring *rx_ring)
3701{
3702	struct ixgbe_hw *hw = &adapter->hw;
3703	u32 srrctl;
3704	u8 reg_idx = rx_ring->reg_idx;
3705
3706	if (hw->mac.type == ixgbe_mac_82598EB) {
3707		u16 mask = adapter->ring_feature[RING_F_RSS].mask;
3708
3709		/*
3710		 * if VMDq is not active we must program one srrctl register
3711		 * per RSS queue since we have enabled RDRXCTL.MVMEN
3712		 */
3713		reg_idx &= mask;
3714	}
3715
3716	/* configure header buffer length, needed for RSC */
3717	srrctl = IXGBE_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT;
3718
3719	/* configure the packet buffer length */
3720	if (rx_ring->xsk_pool) {
3721		u32 xsk_buf_len = xsk_pool_get_rx_frame_size(rx_ring->xsk_pool);
3722
3723		/* If the MAC support setting RXDCTL.RLPML, the
3724		 * SRRCTL[n].BSIZEPKT is set to PAGE_SIZE and
3725		 * RXDCTL.RLPML is set to the actual UMEM buffer
3726		 * size. If not, then we are stuck with a 1k buffer
3727		 * size resolution. In this case frames larger than
3728		 * the UMEM buffer size viewed in a 1k resolution will
3729		 * be dropped.
3730		 */
3731		if (hw->mac.type != ixgbe_mac_82599EB)
3732			srrctl |= PAGE_SIZE >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
3733		else
3734			srrctl |= xsk_buf_len >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
3735	} else if (test_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state)) {
3736		srrctl |= IXGBE_RXBUFFER_3K >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
3737	} else {
3738		srrctl |= IXGBE_RXBUFFER_2K >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
3739	}
3740
3741	/* configure descriptor type */
3742	srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF;
3743
3744	IXGBE_WRITE_REG(hw, IXGBE_SRRCTL(reg_idx), srrctl);
3745}
3746
3747/**
3748 * ixgbe_rss_indir_tbl_entries - Return RSS indirection table entries
3749 * @adapter: device handle
3750 *
3751 *  - 82598/82599/X540:     128
3752 *  - X550(non-SRIOV mode): 512
3753 *  - X550(SRIOV mode):     64
3754 */
3755u32 ixgbe_rss_indir_tbl_entries(struct ixgbe_adapter *adapter)
3756{
3757	if (adapter->hw.mac.type < ixgbe_mac_X550)
3758		return 128;
3759	else if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
3760		return 64;
3761	else
3762		return 512;
3763}
3764
3765/**
3766 * ixgbe_store_key - Write the RSS key to HW
3767 * @adapter: device handle
3768 *
3769 * Write the RSS key stored in adapter.rss_key to HW.
3770 */
3771void ixgbe_store_key(struct ixgbe_adapter *adapter)
3772{
3773	struct ixgbe_hw *hw = &adapter->hw;
3774	int i;
3775
3776	for (i = 0; i < 10; i++)
3777		IXGBE_WRITE_REG(hw, IXGBE_RSSRK(i), adapter->rss_key[i]);
3778}
3779
3780/**
3781 * ixgbe_init_rss_key - Initialize adapter RSS key
3782 * @adapter: device handle
3783 *
3784 * Allocates and initializes the RSS key if it is not allocated.
3785 **/
3786static inline int ixgbe_init_rss_key(struct ixgbe_adapter *adapter)
3787{
3788	u32 *rss_key;
3789
3790	if (!adapter->rss_key) {
3791		rss_key = kzalloc(IXGBE_RSS_KEY_SIZE, GFP_KERNEL);
3792		if (unlikely(!rss_key))
3793			return -ENOMEM;
3794
3795		netdev_rss_key_fill(rss_key, IXGBE_RSS_KEY_SIZE);
3796		adapter->rss_key = rss_key;
3797	}
3798
3799	return 0;
3800}
3801
3802/**
3803 * ixgbe_store_reta - Write the RETA table to HW
3804 * @adapter: device handle
3805 *
3806 * Write the RSS redirection table stored in adapter.rss_indir_tbl[] to HW.
3807 */
3808void ixgbe_store_reta(struct ixgbe_adapter *adapter)
3809{
3810	u32 i, reta_entries = ixgbe_rss_indir_tbl_entries(adapter);
3811	struct ixgbe_hw *hw = &adapter->hw;
3812	u32 reta = 0;
3813	u32 indices_multi;
3814	u8 *indir_tbl = adapter->rss_indir_tbl;
3815
3816	/* Fill out the redirection table as follows:
3817	 *  - 82598:      8 bit wide entries containing pair of 4 bit RSS
3818	 *    indices.
3819	 *  - 82599/X540: 8 bit wide entries containing 4 bit RSS index
3820	 *  - X550:       8 bit wide entries containing 6 bit RSS index
3821	 */
3822	if (adapter->hw.mac.type == ixgbe_mac_82598EB)
3823		indices_multi = 0x11;
3824	else
3825		indices_multi = 0x1;
3826
3827	/* Write redirection table to HW */
3828	for (i = 0; i < reta_entries; i++) {
3829		reta |= indices_multi * indir_tbl[i] << (i & 0x3) * 8;
3830		if ((i & 3) == 3) {
3831			if (i < 128)
3832				IXGBE_WRITE_REG(hw, IXGBE_RETA(i >> 2), reta);
3833			else
3834				IXGBE_WRITE_REG(hw, IXGBE_ERETA((i >> 2) - 32),
3835						reta);
3836			reta = 0;
3837		}
3838	}
3839}
3840
3841/**
3842 * ixgbe_store_vfreta - Write the RETA table to HW (x550 devices in SRIOV mode)
3843 * @adapter: device handle
3844 *
3845 * Write the RSS redirection table stored in adapter.rss_indir_tbl[] to HW.
3846 */
3847static void ixgbe_store_vfreta(struct ixgbe_adapter *adapter)
3848{
3849	u32 i, reta_entries = ixgbe_rss_indir_tbl_entries(adapter);
3850	struct ixgbe_hw *hw = &adapter->hw;
3851	u32 vfreta = 0;
3852
3853	/* Write redirection table to HW */
3854	for (i = 0; i < reta_entries; i++) {
3855		u16 pool = adapter->num_rx_pools;
3856
3857		vfreta |= (u32)adapter->rss_indir_tbl[i] << (i & 0x3) * 8;
3858		if ((i & 3) != 3)
3859			continue;
3860
3861		while (pool--)
3862			IXGBE_WRITE_REG(hw,
3863					IXGBE_PFVFRETA(i >> 2, VMDQ_P(pool)),
3864					vfreta);
3865		vfreta = 0;
3866	}
3867}
3868
3869static void ixgbe_setup_reta(struct ixgbe_adapter *adapter)
3870{
3871	u32 i, j;
3872	u32 reta_entries = ixgbe_rss_indir_tbl_entries(adapter);
3873	u16 rss_i = adapter->ring_feature[RING_F_RSS].indices;
3874
3875	/* Program table for at least 4 queues w/ SR-IOV so that VFs can
3876	 * make full use of any rings they may have.  We will use the
3877	 * PSRTYPE register to control how many rings we use within the PF.
3878	 */
3879	if ((adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) && (rss_i < 4))
3880		rss_i = 4;
3881
3882	/* Fill out hash function seeds */
3883	ixgbe_store_key(adapter);
3884
3885	/* Fill out redirection table */
3886	memset(adapter->rss_indir_tbl, 0, sizeof(adapter->rss_indir_tbl));
3887
3888	for (i = 0, j = 0; i < reta_entries; i++, j++) {
3889		if (j == rss_i)
3890			j = 0;
3891
3892		adapter->rss_indir_tbl[i] = j;
3893	}
3894
3895	ixgbe_store_reta(adapter);
3896}
3897
3898static void ixgbe_setup_vfreta(struct ixgbe_adapter *adapter)
3899{
3900	struct ixgbe_hw *hw = &adapter->hw;
3901	u16 rss_i = adapter->ring_feature[RING_F_RSS].indices;
3902	int i, j;
3903
3904	/* Fill out hash function seeds */
3905	for (i = 0; i < 10; i++) {
3906		u16 pool = adapter->num_rx_pools;
3907
3908		while (pool--)
3909			IXGBE_WRITE_REG(hw,
3910					IXGBE_PFVFRSSRK(i, VMDQ_P(pool)),
3911					*(adapter->rss_key + i));
3912	}
3913
3914	/* Fill out the redirection table */
3915	for (i = 0, j = 0; i < 64; i++, j++) {
3916		if (j == rss_i)
3917			j = 0;
3918
3919		adapter->rss_indir_tbl[i] = j;
3920	}
3921
3922	ixgbe_store_vfreta(adapter);
3923}
3924
3925static void ixgbe_setup_mrqc(struct ixgbe_adapter *adapter)
3926{
3927	struct ixgbe_hw *hw = &adapter->hw;
3928	u32 mrqc = 0, rss_field = 0, vfmrqc = 0;
3929	u32 rxcsum;
3930
3931	/* Disable indicating checksum in descriptor, enables RSS hash */
3932	rxcsum = IXGBE_READ_REG(hw, IXGBE_RXCSUM);
3933	rxcsum |= IXGBE_RXCSUM_PCSD;
3934	IXGBE_WRITE_REG(hw, IXGBE_RXCSUM, rxcsum);
3935
3936	if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
3937		if (adapter->ring_feature[RING_F_RSS].mask)
3938			mrqc = IXGBE_MRQC_RSSEN;
3939	} else {
3940		u8 tcs = adapter->hw_tcs;
3941
3942		if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) {
3943			if (tcs > 4)
3944				mrqc = IXGBE_MRQC_VMDQRT8TCEN;	/* 8 TCs */
3945			else if (tcs > 1)
3946				mrqc = IXGBE_MRQC_VMDQRT4TCEN;	/* 4 TCs */
3947			else if (adapter->ring_feature[RING_F_VMDQ].mask ==
3948				 IXGBE_82599_VMDQ_4Q_MASK)
3949				mrqc = IXGBE_MRQC_VMDQRSS32EN;
3950			else
3951				mrqc = IXGBE_MRQC_VMDQRSS64EN;
3952
3953			/* Enable L3/L4 for Tx Switched packets only for X550,
3954			 * older devices do not support this feature
3955			 */
3956			if (hw->mac.type >= ixgbe_mac_X550)
3957				mrqc |= IXGBE_MRQC_L3L4TXSWEN;
3958		} else {
3959			if (tcs > 4)
3960				mrqc = IXGBE_MRQC_RTRSS8TCEN;
3961			else if (tcs > 1)
3962				mrqc = IXGBE_MRQC_RTRSS4TCEN;
3963			else
3964				mrqc = IXGBE_MRQC_RSSEN;
3965		}
3966	}
3967
3968	/* Perform hash on these packet types */
3969	rss_field |= IXGBE_MRQC_RSS_FIELD_IPV4 |
3970		     IXGBE_MRQC_RSS_FIELD_IPV4_TCP |
3971		     IXGBE_MRQC_RSS_FIELD_IPV6 |
3972		     IXGBE_MRQC_RSS_FIELD_IPV6_TCP;
3973
3974	if (adapter->flags2 & IXGBE_FLAG2_RSS_FIELD_IPV4_UDP)
3975		rss_field |= IXGBE_MRQC_RSS_FIELD_IPV4_UDP;
3976	if (adapter->flags2 & IXGBE_FLAG2_RSS_FIELD_IPV6_UDP)
3977		rss_field |= IXGBE_MRQC_RSS_FIELD_IPV6_UDP;
3978
3979	if ((hw->mac.type >= ixgbe_mac_X550) &&
3980	    (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) {
3981		u16 pool = adapter->num_rx_pools;
3982
3983		/* Enable VF RSS mode */
3984		mrqc |= IXGBE_MRQC_MULTIPLE_RSS;
3985		IXGBE_WRITE_REG(hw, IXGBE_MRQC, mrqc);
3986
3987		/* Setup RSS through the VF registers */
3988		ixgbe_setup_vfreta(adapter);
3989		vfmrqc = IXGBE_MRQC_RSSEN;
3990		vfmrqc |= rss_field;
3991
3992		while (pool--)
3993			IXGBE_WRITE_REG(hw,
3994					IXGBE_PFVFMRQC(VMDQ_P(pool)),
3995					vfmrqc);
3996	} else {
3997		ixgbe_setup_reta(adapter);
3998		mrqc |= rss_field;
3999		IXGBE_WRITE_REG(hw, IXGBE_MRQC, mrqc);
4000	}
4001}
4002
4003/**
4004 * ixgbe_configure_rscctl - enable RSC for the indicated ring
4005 * @adapter: address of board private structure
4006 * @ring: structure containing ring specific data
4007 **/
4008static void ixgbe_configure_rscctl(struct ixgbe_adapter *adapter,
4009				   struct ixgbe_ring *ring)
4010{
4011	struct ixgbe_hw *hw = &adapter->hw;
4012	u32 rscctrl;
4013	u8 reg_idx = ring->reg_idx;
4014
4015	if (!ring_is_rsc_enabled(ring))
4016		return;
4017
4018	rscctrl = IXGBE_READ_REG(hw, IXGBE_RSCCTL(reg_idx));
4019	rscctrl |= IXGBE_RSCCTL_RSCEN;
4020	/*
4021	 * we must limit the number of descriptors so that the
4022	 * total size of max desc * buf_len is not greater
4023	 * than 65536
4024	 */
4025	rscctrl |= IXGBE_RSCCTL_MAXDESC_16;
4026	IXGBE_WRITE_REG(hw, IXGBE_RSCCTL(reg_idx), rscctrl);
4027}
4028
4029#define IXGBE_MAX_RX_DESC_POLL 10
4030static void ixgbe_rx_desc_queue_enable(struct ixgbe_adapter *adapter,
4031				       struct ixgbe_ring *ring)
4032{
4033	struct ixgbe_hw *hw = &adapter->hw;
4034	int wait_loop = IXGBE_MAX_RX_DESC_POLL;
4035	u32 rxdctl;
4036	u8 reg_idx = ring->reg_idx;
4037
4038	if (ixgbe_removed(hw->hw_addr))
4039		return;
4040	/* RXDCTL.EN will return 0 on 82598 if link is down, so skip it */
4041	if (hw->mac.type == ixgbe_mac_82598EB &&
4042	    !(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP))
4043		return;
4044
4045	do {
4046		usleep_range(1000, 2000);
4047		rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
4048	} while (--wait_loop && !(rxdctl & IXGBE_RXDCTL_ENABLE));
4049
4050	if (!wait_loop) {
4051		e_err(drv, "RXDCTL.ENABLE on Rx queue %d not set within "
4052		      "the polling period\n", reg_idx);
4053	}
4054}
4055
4056void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
4057			     struct ixgbe_ring *ring)
4058{
4059	struct ixgbe_hw *hw = &adapter->hw;
4060	union ixgbe_adv_rx_desc *rx_desc;
4061	u64 rdba = ring->dma;
4062	u32 rxdctl;
4063	u8 reg_idx = ring->reg_idx;
4064
4065	xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
4066	ring->xsk_pool = ixgbe_xsk_pool(adapter, ring);
4067	if (ring->xsk_pool) {
4068		WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
4069						   MEM_TYPE_XSK_BUFF_POOL,
4070						   NULL));
4071		xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq);
4072	} else {
4073		WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
4074						   MEM_TYPE_PAGE_SHARED, NULL));
4075	}
4076
4077	/* disable queue to avoid use of these values while updating state */
4078	rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
4079	rxdctl &= ~IXGBE_RXDCTL_ENABLE;
4080
4081	/* write value back with RXDCTL.ENABLE bit cleared */
4082	IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl);
4083	IXGBE_WRITE_FLUSH(hw);
4084
4085	IXGBE_WRITE_REG(hw, IXGBE_RDBAL(reg_idx), (rdba & DMA_BIT_MASK(32)));
4086	IXGBE_WRITE_REG(hw, IXGBE_RDBAH(reg_idx), (rdba >> 32));
4087	IXGBE_WRITE_REG(hw, IXGBE_RDLEN(reg_idx),
4088			ring->count * sizeof(union ixgbe_adv_rx_desc));
4089	/* Force flushing of IXGBE_RDLEN to prevent MDD */
4090	IXGBE_WRITE_FLUSH(hw);
4091
4092	IXGBE_WRITE_REG(hw, IXGBE_RDH(reg_idx), 0);
4093	IXGBE_WRITE_REG(hw, IXGBE_RDT(reg_idx), 0);
4094	ring->tail = adapter->io_addr + IXGBE_RDT(reg_idx);
4095
4096	ixgbe_configure_srrctl(adapter, ring);
4097	ixgbe_configure_rscctl(adapter, ring);
4098
4099	if (hw->mac.type == ixgbe_mac_82598EB) {
4100		/*
4101		 * enable cache line friendly hardware writes:
4102		 * PTHRESH=32 descriptors (half the internal cache),
4103		 * this also removes ugly rx_no_buffer_count increment
4104		 * HTHRESH=4 descriptors (to minimize latency on fetch)
4105		 * WTHRESH=8 burst writeback up to two cache lines
4106		 */
4107		rxdctl &= ~0x3FFFFF;
4108		rxdctl |=  0x080420;
4109#if (PAGE_SIZE < 8192)
4110	/* RXDCTL.RLPML does not work on 82599 */
4111	} else if (hw->mac.type != ixgbe_mac_82599EB) {
4112		rxdctl &= ~(IXGBE_RXDCTL_RLPMLMASK |
4113			    IXGBE_RXDCTL_RLPML_EN);
4114
4115		/* Limit the maximum frame size so we don't overrun the skb.
4116		 * This can happen in SRIOV mode when the MTU of the VF is
4117		 * higher than the MTU of the PF.
4118		 */
4119		if (ring_uses_build_skb(ring) &&
4120		    !test_bit(__IXGBE_RX_3K_BUFFER, &ring->state))
4121			rxdctl |= IXGBE_MAX_2K_FRAME_BUILD_SKB |
4122				  IXGBE_RXDCTL_RLPML_EN;
4123#endif
4124	}
4125
4126	if (ring->xsk_pool && hw->mac.type != ixgbe_mac_82599EB) {
4127		u32 xsk_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool);
4128
4129		rxdctl &= ~(IXGBE_RXDCTL_RLPMLMASK |
4130			    IXGBE_RXDCTL_RLPML_EN);
4131		rxdctl |= xsk_buf_len | IXGBE_RXDCTL_RLPML_EN;
4132
4133		ring->rx_buf_len = xsk_buf_len;
4134	}
4135
4136	/* initialize rx_buffer_info */
4137	memset(ring->rx_buffer_info, 0,
4138	       sizeof(struct ixgbe_rx_buffer) * ring->count);
4139
4140	/* initialize Rx descriptor 0 */
4141	rx_desc = IXGBE_RX_DESC(ring, 0);
4142	rx_desc->wb.upper.length = 0;
4143
4144	/* enable receive descriptor ring */
4145	rxdctl |= IXGBE_RXDCTL_ENABLE;
4146	IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl);
4147
4148	ixgbe_rx_desc_queue_enable(adapter, ring);
4149	if (ring->xsk_pool)
4150		ixgbe_alloc_rx_buffers_zc(ring, ixgbe_desc_unused(ring));
4151	else
4152		ixgbe_alloc_rx_buffers(ring, ixgbe_desc_unused(ring));
4153}
4154
4155static void ixgbe_setup_psrtype(struct ixgbe_adapter *adapter)
4156{
4157	struct ixgbe_hw *hw = &adapter->hw;
4158	int rss_i = adapter->ring_feature[RING_F_RSS].indices;
4159	u16 pool = adapter->num_rx_pools;
4160
4161	/* PSRTYPE must be initialized in non 82598 adapters */
4162	u32 psrtype = IXGBE_PSRTYPE_TCPHDR |
4163		      IXGBE_PSRTYPE_UDPHDR |
4164		      IXGBE_PSRTYPE_IPV4HDR |
4165		      IXGBE_PSRTYPE_L2HDR |
4166		      IXGBE_PSRTYPE_IPV6HDR;
4167
4168	if (hw->mac.type == ixgbe_mac_82598EB)
4169		return;
4170
4171	if (rss_i > 3)
4172		psrtype |= 2u << 29;
4173	else if (rss_i > 1)
4174		psrtype |= 1u << 29;
4175
4176	while (pool--)
4177		IXGBE_WRITE_REG(hw, IXGBE_PSRTYPE(VMDQ_P(pool)), psrtype);
4178}
4179
4180static void ixgbe_configure_virtualization(struct ixgbe_adapter *adapter)
4181{
4182	struct ixgbe_hw *hw = &adapter->hw;
4183	u16 pool = adapter->num_rx_pools;
4184	u32 reg_offset, vf_shift, vmolr;
4185	u32 gcr_ext, vmdctl;
4186	int i;
4187
4188	if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED))
4189		return;
4190
4191	vmdctl = IXGBE_READ_REG(hw, IXGBE_VT_CTL);
4192	vmdctl |= IXGBE_VMD_CTL_VMDQ_EN;
4193	vmdctl &= ~IXGBE_VT_CTL_POOL_MASK;
4194	vmdctl |= VMDQ_P(0) << IXGBE_VT_CTL_POOL_SHIFT;
4195	vmdctl |= IXGBE_VT_CTL_REPLEN;
4196	IXGBE_WRITE_REG(hw, IXGBE_VT_CTL, vmdctl);
4197
4198	/* accept untagged packets until a vlan tag is
4199	 * specifically set for the VMDQ queue/pool
4200	 */
4201	vmolr = IXGBE_VMOLR_AUPE;
4202	while (pool--)
4203		IXGBE_WRITE_REG(hw, IXGBE_VMOLR(VMDQ_P(pool)), vmolr);
4204
4205	vf_shift = VMDQ_P(0) % 32;
4206	reg_offset = (VMDQ_P(0) >= 32) ? 1 : 0;
4207
4208	/* Enable only the PF's pool for Tx/Rx */
4209	IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset), GENMASK(31, vf_shift));
4210	IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset ^ 1), reg_offset - 1);
4211	IXGBE_WRITE_REG(hw, IXGBE_VFTE(reg_offset), GENMASK(31, vf_shift));
4212	IXGBE_WRITE_REG(hw, IXGBE_VFTE(reg_offset ^ 1), reg_offset - 1);
4213	if (adapter->bridge_mode == BRIDGE_MODE_VEB)
4214		IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, IXGBE_PFDTXGSWC_VT_LBEN);
4215
4216	/* Map PF MAC address in RAR Entry 0 to first pool following VFs */
4217	hw->mac.ops.set_vmdq(hw, 0, VMDQ_P(0));
4218
4219	/* clear VLAN promisc flag so VFTA will be updated if necessary */
4220	adapter->flags2 &= ~IXGBE_FLAG2_VLAN_PROMISC;
4221
4222	/*
4223	 * Set up VF register offsets for selected VT Mode,
4224	 * i.e. 32 or 64 VFs for SR-IOV
4225	 */
4226	switch (adapter->ring_feature[RING_F_VMDQ].mask) {
4227	case IXGBE_82599_VMDQ_8Q_MASK:
4228		gcr_ext = IXGBE_GCR_EXT_VT_MODE_16;
4229		break;
4230	case IXGBE_82599_VMDQ_4Q_MASK:
4231		gcr_ext = IXGBE_GCR_EXT_VT_MODE_32;
4232		break;
4233	default:
4234		gcr_ext = IXGBE_GCR_EXT_VT_MODE_64;
4235		break;
4236	}
4237
4238	IXGBE_WRITE_REG(hw, IXGBE_GCR_EXT, gcr_ext);
4239
4240	for (i = 0; i < adapter->num_vfs; i++) {
4241		/* configure spoof checking */
4242		ixgbe_ndo_set_vf_spoofchk(adapter->netdev, i,
4243					  adapter->vfinfo[i].spoofchk_enabled);
4244
4245		/* Enable/Disable RSS query feature  */
4246		ixgbe_ndo_set_vf_rss_query_en(adapter->netdev, i,
4247					  adapter->vfinfo[i].rss_query_enabled);
4248	}
4249}
4250
4251static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter)
4252{
4253	struct ixgbe_hw *hw = &adapter->hw;
4254	struct net_device *netdev = adapter->netdev;
4255	int max_frame = netdev->mtu + ETH_HLEN + ETH_FCS_LEN;
4256	struct ixgbe_ring *rx_ring;
4257	int i;
4258	u32 mhadd, hlreg0;
4259
4260#ifdef IXGBE_FCOE
4261	/* adjust max frame to be able to do baby jumbo for FCoE */
4262	if ((adapter->flags & IXGBE_FLAG_FCOE_ENABLED) &&
4263	    (max_frame < IXGBE_FCOE_JUMBO_FRAME_SIZE))
4264		max_frame = IXGBE_FCOE_JUMBO_FRAME_SIZE;
4265
4266#endif /* IXGBE_FCOE */
4267
4268	/* adjust max frame to be at least the size of a standard frame */
4269	if (max_frame < (ETH_FRAME_LEN + ETH_FCS_LEN))
4270		max_frame = (ETH_FRAME_LEN + ETH_FCS_LEN);
4271
4272	mhadd = IXGBE_READ_REG(hw, IXGBE_MHADD);
4273	if (max_frame != (mhadd >> IXGBE_MHADD_MFS_SHIFT)) {
4274		mhadd &= ~IXGBE_MHADD_MFS_MASK;
4275		mhadd |= max_frame << IXGBE_MHADD_MFS_SHIFT;
4276
4277		IXGBE_WRITE_REG(hw, IXGBE_MHADD, mhadd);
4278	}
4279
4280	hlreg0 = IXGBE_READ_REG(hw, IXGBE_HLREG0);
4281	/* set jumbo enable since MHADD.MFS is keeping size locked at max_frame */
4282	hlreg0 |= IXGBE_HLREG0_JUMBOEN;
4283	IXGBE_WRITE_REG(hw, IXGBE_HLREG0, hlreg0);
4284
4285	/*
4286	 * Setup the HW Rx Head and Tail Descriptor Pointers and
4287	 * the Base and Length of the Rx Descriptor Ring
4288	 */
4289	for (i = 0; i < adapter->num_rx_queues; i++) {
4290		rx_ring = adapter->rx_ring[i];
4291
4292		clear_ring_rsc_enabled(rx_ring);
4293		clear_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
4294		clear_bit(__IXGBE_RX_BUILD_SKB_ENABLED, &rx_ring->state);
4295
4296		if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)
4297			set_ring_rsc_enabled(rx_ring);
4298
4299		if (test_bit(__IXGBE_RX_FCOE, &rx_ring->state))
4300			set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
4301
4302		if (adapter->flags2 & IXGBE_FLAG2_RX_LEGACY)
4303			continue;
4304
4305		set_bit(__IXGBE_RX_BUILD_SKB_ENABLED, &rx_ring->state);
4306
4307#if (PAGE_SIZE < 8192)
4308		if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)
4309			set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
4310
4311		if (IXGBE_2K_TOO_SMALL_WITH_PADDING ||
4312		    (max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN)))
4313			set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
4314#endif
4315	}
4316}
4317
4318static void ixgbe_setup_rdrxctl(struct ixgbe_adapter *adapter)
4319{
4320	struct ixgbe_hw *hw = &adapter->hw;
4321	u32 rdrxctl = IXGBE_READ_REG(hw, IXGBE_RDRXCTL);
4322
4323	switch (hw->mac.type) {
4324	case ixgbe_mac_82598EB:
4325		/*
4326		 * For VMDq support of different descriptor types or
4327		 * buffer sizes through the use of multiple SRRCTL
4328		 * registers, RDRXCTL.MVMEN must be set to 1
4329		 *
4330		 * also, the manual doesn't mention it clearly but DCA hints
4331		 * will only use queue 0's tags unless this bit is set.  Side
4332		 * effects of setting this bit are only that SRRCTL must be
4333		 * fully programmed [0..15]
4334		 */
4335		rdrxctl |= IXGBE_RDRXCTL_MVMEN;
4336		break;
4337	case ixgbe_mac_X550:
4338	case ixgbe_mac_X550EM_x:
4339	case ixgbe_mac_x550em_a:
4340		if (adapter->num_vfs)
4341			rdrxctl |= IXGBE_RDRXCTL_PSP;
4342		fallthrough;
4343	case ixgbe_mac_82599EB:
4344	case ixgbe_mac_X540:
4345		/* Disable RSC for ACK packets */
4346		IXGBE_WRITE_REG(hw, IXGBE_RSCDBU,
4347		   (IXGBE_RSCDBU_RSCACKDIS | IXGBE_READ_REG(hw, IXGBE_RSCDBU)));
4348		rdrxctl &= ~IXGBE_RDRXCTL_RSCFRSTSIZE;
4349		/* hardware requires some bits to be set by default */
4350		rdrxctl |= (IXGBE_RDRXCTL_RSCACKC | IXGBE_RDRXCTL_FCOE_WRFIX);
4351		rdrxctl |= IXGBE_RDRXCTL_CRCSTRIP;
4352		break;
4353	default:
4354		/* We should do nothing since we don't know this hardware */
4355		return;
4356	}
4357
4358	IXGBE_WRITE_REG(hw, IXGBE_RDRXCTL, rdrxctl);
4359}
4360
4361/**
4362 * ixgbe_configure_rx - Configure 8259x Receive Unit after Reset
4363 * @adapter: board private structure
4364 *
4365 * Configure the Rx unit of the MAC after a reset.
4366 **/
4367static void ixgbe_configure_rx(struct ixgbe_adapter *adapter)
4368{
4369	struct ixgbe_hw *hw = &adapter->hw;
4370	int i;
4371	u32 rxctrl, rfctl;
4372
4373	/* disable receives while setting up the descriptors */
4374	hw->mac.ops.disable_rx(hw);
4375
4376	ixgbe_setup_psrtype(adapter);
4377	ixgbe_setup_rdrxctl(adapter);
4378
4379	/* RSC Setup */
4380	rfctl = IXGBE_READ_REG(hw, IXGBE_RFCTL);
4381	rfctl &= ~IXGBE_RFCTL_RSC_DIS;
4382	if (!(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED))
4383		rfctl |= IXGBE_RFCTL_RSC_DIS;
4384
4385	/* disable NFS filtering */
4386	rfctl |= (IXGBE_RFCTL_NFSW_DIS | IXGBE_RFCTL_NFSR_DIS);
4387	IXGBE_WRITE_REG(hw, IXGBE_RFCTL, rfctl);
4388
4389	/* Program registers for the distribution of queues */
4390	ixgbe_setup_mrqc(adapter);
4391
4392	/* set_rx_buffer_len must be called before ring initialization */
4393	ixgbe_set_rx_buffer_len(adapter);
4394
4395	/*
4396	 * Setup the HW Rx Head and Tail Descriptor Pointers and
4397	 * the Base and Length of the Rx Descriptor Ring
4398	 */
4399	for (i = 0; i < adapter->num_rx_queues; i++)
4400		ixgbe_configure_rx_ring(adapter, adapter->rx_ring[i]);
4401
4402	rxctrl = IXGBE_READ_REG(hw, IXGBE_RXCTRL);
4403	/* disable drop enable for 82598 parts */
4404	if (hw->mac.type == ixgbe_mac_82598EB)
4405		rxctrl |= IXGBE_RXCTRL_DMBYPS;
4406
4407	/* enable all receives */
4408	rxctrl |= IXGBE_RXCTRL_RXEN;
4409	hw->mac.ops.enable_rx_dma(hw, rxctrl);
4410}
4411
4412static int ixgbe_vlan_rx_add_vid(struct net_device *netdev,
4413				 __be16 proto, u16 vid)
4414{
4415	struct ixgbe_adapter *adapter = netdev_priv(netdev);
4416	struct ixgbe_hw *hw = &adapter->hw;
4417
4418	/* add VID to filter table */
4419	if (!vid || !(adapter->flags2 & IXGBE_FLAG2_VLAN_PROMISC))
4420		hw->mac.ops.set_vfta(&adapter->hw, vid, VMDQ_P(0), true, !!vid);
4421
4422	set_bit(vid, adapter->active_vlans);
4423
4424	return 0;
4425}
4426
4427static int ixgbe_find_vlvf_entry(struct ixgbe_hw *hw, u32 vlan)
4428{
4429	u32 vlvf;
4430	int idx;
4431
4432	/* short cut the special case */
4433	if (vlan == 0)
4434		return 0;
4435
4436	/* Search for the vlan id in the VLVF entries */
4437	for (idx = IXGBE_VLVF_ENTRIES; --idx;) {
4438		vlvf = IXGBE_READ_REG(hw, IXGBE_VLVF(idx));
4439		if ((vlvf & VLAN_VID_MASK) == vlan)
4440			break;
4441	}
4442
4443	return idx;
4444}
4445
4446void ixgbe_update_pf_promisc_vlvf(struct ixgbe_adapter *adapter, u32 vid)
4447{
4448	struct ixgbe_hw *hw = &adapter->hw;
4449	u32 bits, word;
4450	int idx;
4451
4452	idx = ixgbe_find_vlvf_entry(hw, vid);
4453	if (!idx)
4454		return;
4455
4456	/* See if any other pools are set for this VLAN filter
4457	 * entry other than the PF.
4458	 */
4459	word = idx * 2 + (VMDQ_P(0) / 32);
4460	bits = ~BIT(VMDQ_P(0) % 32);
4461	bits &= IXGBE_READ_REG(hw, IXGBE_VLVFB(word));
4462
4463	/* Disable the filter so this falls into the default pool. */
4464	if (!bits && !IXGBE_READ_REG(hw, IXGBE_VLVFB(word ^ 1))) {
4465		if (!(adapter->flags2 & IXGBE_FLAG2_VLAN_PROMISC))
4466			IXGBE_WRITE_REG(hw, IXGBE_VLVFB(word), 0);
4467		IXGBE_WRITE_REG(hw, IXGBE_VLVF(idx), 0);
4468	}
4469}
4470
4471static int ixgbe_vlan_rx_kill_vid(struct net_device *netdev,
4472				  __be16 proto, u16 vid)
4473{
4474	struct ixgbe_adapter *adapter = netdev_priv(netdev);
4475	struct ixgbe_hw *hw = &adapter->hw;
4476
4477	/* remove VID from filter table */
4478	if (vid && !(adapter->flags2 & IXGBE_FLAG2_VLAN_PROMISC))
4479		hw->mac.ops.set_vfta(hw, vid, VMDQ_P(0), false, true);
4480
4481	clear_bit(vid, adapter->active_vlans);
4482
4483	return 0;
4484}
4485
4486/**
4487 * ixgbe_vlan_strip_disable - helper to disable hw vlan stripping
4488 * @adapter: driver data
4489 */
4490static void ixgbe_vlan_strip_disable(struct ixgbe_adapter *adapter)
4491{
4492	struct ixgbe_hw *hw = &adapter->hw;
4493	u32 vlnctrl;
4494	int i, j;
4495
4496	switch (hw->mac.type) {
4497	case ixgbe_mac_82598EB:
4498		vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL);
4499		vlnctrl &= ~IXGBE_VLNCTRL_VME;
4500		IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl);
4501		break;
4502	case ixgbe_mac_82599EB:
4503	case ixgbe_mac_X540:
4504	case ixgbe_mac_X550:
4505	case ixgbe_mac_X550EM_x:
4506	case ixgbe_mac_x550em_a:
4507		for (i = 0; i < adapter->num_rx_queues; i++) {
4508			struct ixgbe_ring *ring = adapter->rx_ring[i];
4509
4510			if (!netif_is_ixgbe(ring->netdev))
4511				continue;
4512
4513			j = ring->reg_idx;
4514			vlnctrl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(j));
4515			vlnctrl &= ~IXGBE_RXDCTL_VME;
4516			IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(j), vlnctrl);
4517		}
4518		break;
4519	default:
4520		break;
4521	}
4522}
4523
4524/**
4525 * ixgbe_vlan_strip_enable - helper to enable hw vlan stripping
4526 * @adapter: driver data
4527 */
4528static void ixgbe_vlan_strip_enable(struct ixgbe_adapter *adapter)
4529{
4530	struct ixgbe_hw *hw = &adapter->hw;
4531	u32 vlnctrl;
4532	int i, j;
4533
4534	switch (hw->mac.type) {
4535	case ixgbe_mac_82598EB:
4536		vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL);
4537		vlnctrl |= IXGBE_VLNCTRL_VME;
4538		IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl);
4539		break;
4540	case ixgbe_mac_82599EB:
4541	case ixgbe_mac_X540:
4542	case ixgbe_mac_X550:
4543	case ixgbe_mac_X550EM_x:
4544	case ixgbe_mac_x550em_a:
4545		for (i = 0; i < adapter->num_rx_queues; i++) {
4546			struct ixgbe_ring *ring = adapter->rx_ring[i];
4547
4548			if (!netif_is_ixgbe(ring->netdev))
4549				continue;
4550
4551			j = ring->reg_idx;
4552			vlnctrl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(j));
4553			vlnctrl |= IXGBE_RXDCTL_VME;
4554			IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(j), vlnctrl);
4555		}
4556		break;
4557	default:
4558		break;
4559	}
4560}
4561
4562static void ixgbe_vlan_promisc_enable(struct ixgbe_adapter *adapter)
4563{
4564	struct ixgbe_hw *hw = &adapter->hw;
4565	u32 vlnctrl, i;
4566
4567	vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL);
4568
4569	if (adapter->flags & IXGBE_FLAG_VMDQ_ENABLED) {
4570	/* For VMDq and SR-IOV we must leave VLAN filtering enabled */
4571		vlnctrl |= IXGBE_VLNCTRL_VFE;
4572		IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl);
4573	} else {
4574		vlnctrl &= ~IXGBE_VLNCTRL_VFE;
4575		IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl);
4576		return;
4577	}
4578
4579	/* Nothing to do for 82598 */
4580	if (hw->mac.type == ixgbe_mac_82598EB)
4581		return;
4582
4583	/* We are already in VLAN promisc, nothing to do */
4584	if (adapter->flags2 & IXGBE_FLAG2_VLAN_PROMISC)
4585		return;
4586
4587	/* Set flag so we don't redo unnecessary work */
4588	adapter->flags2 |= IXGBE_FLAG2_VLAN_PROMISC;
4589
4590	/* Add PF to all active pools */
4591	for (i = IXGBE_VLVF_ENTRIES; --i;) {
4592		u32 reg_offset = IXGBE_VLVFB(i * 2 + VMDQ_P(0) / 32);
4593		u32 vlvfb = IXGBE_READ_REG(hw, reg_offset);
4594
4595		vlvfb |= BIT(VMDQ_P(0) % 32);
4596		IXGBE_WRITE_REG(hw, reg_offset, vlvfb);
4597	}
4598
4599	/* Set all bits in the VLAN filter table array */
4600	for (i = hw->mac.vft_size; i--;)
4601		IXGBE_WRITE_REG(hw, IXGBE_VFTA(i), ~0U);
4602}
4603
4604#define VFTA_BLOCK_SIZE 8
4605static void ixgbe_scrub_vfta(struct ixgbe_adapter *adapter, u32 vfta_offset)
4606{
4607	struct ixgbe_hw *hw = &adapter->hw;
4608	u32 vfta[VFTA_BLOCK_SIZE] = { 0 };
4609	u32 vid_start = vfta_offset * 32;
4610	u32 vid_end = vid_start + (VFTA_BLOCK_SIZE * 32);
4611	u32 i, vid, word, bits;
4612
4613	for (i = IXGBE_VLVF_ENTRIES; --i;) {
4614		u32 vlvf = IXGBE_READ_REG(hw, IXGBE_VLVF(i));
4615
4616		/* pull VLAN ID from VLVF */
4617		vid = vlvf & VLAN_VID_MASK;
4618
4619		/* only concern outselves with a certain range */
4620		if (vid < vid_start || vid >= vid_end)
4621			continue;
4622
4623		if (vlvf) {
4624			/* record VLAN ID in VFTA */
4625			vfta[(vid - vid_start) / 32] |= BIT(vid % 32);
4626
4627			/* if PF is part of this then continue */
4628			if (test_bit(vid, adapter->active_vlans))
4629				continue;
4630		}
4631
4632		/* remove PF from the pool */
4633		word = i * 2 + VMDQ_P(0) / 32;
4634		bits = ~BIT(VMDQ_P(0) % 32);
4635		bits &= IXGBE_READ_REG(hw, IXGBE_VLVFB(word));
4636		IXGBE_WRITE_REG(hw, IXGBE_VLVFB(word), bits);
4637	}
4638
4639	/* extract values from active_vlans and write back to VFTA */
4640	for (i = VFTA_BLOCK_SIZE; i--;) {
4641		vid = (vfta_offset + i) * 32;
4642		word = vid / BITS_PER_LONG;
4643		bits = vid % BITS_PER_LONG;
4644
4645		vfta[i] |= adapter->active_vlans[word] >> bits;
4646
4647		IXGBE_WRITE_REG(hw, IXGBE_VFTA(vfta_offset + i), vfta[i]);
4648	}
4649}
4650
4651static void ixgbe_vlan_promisc_disable(struct ixgbe_adapter *adapter)
4652{
4653	struct ixgbe_hw *hw = &adapter->hw;
4654	u32 vlnctrl, i;
4655
4656	/* Set VLAN filtering to enabled */
4657	vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL);
4658	vlnctrl |= IXGBE_VLNCTRL_VFE;
4659	IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl);
4660
4661	if (!(adapter->flags & IXGBE_FLAG_VMDQ_ENABLED) ||
4662	    hw->mac.type == ixgbe_mac_82598EB)
4663		return;
4664
4665	/* We are not in VLAN promisc, nothing to do */
4666	if (!(adapter->flags2 & IXGBE_FLAG2_VLAN_PROMISC))
4667		return;
4668
4669	/* Set flag so we don't redo unnecessary work */
4670	adapter->flags2 &= ~IXGBE_FLAG2_VLAN_PROMISC;
4671
4672	for (i = 0; i < hw->mac.vft_size; i += VFTA_BLOCK_SIZE)
4673		ixgbe_scrub_vfta(adapter, i);
4674}
4675
4676static void ixgbe_restore_vlan(struct ixgbe_adapter *adapter)
4677{
4678	u16 vid = 1;
4679
4680	ixgbe_vlan_rx_add_vid(adapter->netdev, htons(ETH_P_8021Q), 0);
4681
4682	for_each_set_bit_from(vid, adapter->active_vlans, VLAN_N_VID)
4683		ixgbe_vlan_rx_add_vid(adapter->netdev, htons(ETH_P_8021Q), vid);
4684}
4685
4686/**
4687 * ixgbe_write_mc_addr_list - write multicast addresses to MTA
4688 * @netdev: network interface device structure
4689 *
4690 * Writes multicast address list to the MTA hash table.
4691 * Returns: -ENOMEM on failure
4692 *                0 on no addresses written
4693 *                X on writing X addresses to MTA
4694 **/
4695static int ixgbe_write_mc_addr_list(struct net_device *netdev)
4696{
4697	struct ixgbe_adapter *adapter = netdev_priv(netdev);
4698	struct ixgbe_hw *hw = &adapter->hw;
4699
4700	if (!netif_running(netdev))
4701		return 0;
4702
4703	if (hw->mac.ops.update_mc_addr_list)
4704		hw->mac.ops.update_mc_addr_list(hw, netdev);
4705	else
4706		return -ENOMEM;
4707
4708#ifdef CONFIG_PCI_IOV
4709	ixgbe_restore_vf_multicasts(adapter);
4710#endif
4711
4712	return netdev_mc_count(netdev);
4713}
4714
4715#ifdef CONFIG_PCI_IOV
4716void ixgbe_full_sync_mac_table(struct ixgbe_adapter *adapter)
4717{
4718	struct ixgbe_mac_addr *mac_table = &adapter->mac_table[0];
4719	struct ixgbe_hw *hw = &adapter->hw;
4720	int i;
4721
4722	for (i = 0; i < hw->mac.num_rar_entries; i++, mac_table++) {
4723		mac_table->state &= ~IXGBE_MAC_STATE_MODIFIED;
4724
4725		if (mac_table->state & IXGBE_MAC_STATE_IN_USE)
4726			hw->mac.ops.set_rar(hw, i,
4727					    mac_table->addr,
4728					    mac_table->pool,
4729					    IXGBE_RAH_AV);
4730		else
4731			hw->mac.ops.clear_rar(hw, i);
4732	}
4733}
4734
4735#endif
4736static void ixgbe_sync_mac_table(struct ixgbe_adapter *adapter)
4737{
4738	struct ixgbe_mac_addr *mac_table = &adapter->mac_table[0];
4739	struct ixgbe_hw *hw = &adapter->hw;
4740	int i;
4741
4742	for (i = 0; i < hw->mac.num_rar_entries; i++, mac_table++) {
4743		if (!(mac_table->state & IXGBE_MAC_STATE_MODIFIED))
4744			continue;
4745
4746		mac_table->state &= ~IXGBE_MAC_STATE_MODIFIED;
4747
4748		if (mac_table->state & IXGBE_MAC_STATE_IN_USE)
4749			hw->mac.ops.set_rar(hw, i,
4750					    mac_table->addr,
4751					    mac_table->pool,
4752					    IXGBE_RAH_AV);
4753		else
4754			hw->mac.ops.clear_rar(hw, i);
4755	}
4756}
4757
4758static void ixgbe_flush_sw_mac_table(struct ixgbe_adapter *adapter)
4759{
4760	struct ixgbe_mac_addr *mac_table = &adapter->mac_table[0];
4761	struct ixgbe_hw *hw = &adapter->hw;
4762	int i;
4763
4764	for (i = 0; i < hw->mac.num_rar_entries; i++, mac_table++) {
4765		mac_table->state |= IXGBE_MAC_STATE_MODIFIED;
4766		mac_table->state &= ~IXGBE_MAC_STATE_IN_USE;
4767	}
4768
4769	ixgbe_sync_mac_table(adapter);
4770}
4771
4772static int ixgbe_available_rars(struct ixgbe_adapter *adapter, u16 pool)
4773{
4774	struct ixgbe_mac_addr *mac_table = &adapter->mac_table[0];
4775	struct ixgbe_hw *hw = &adapter->hw;
4776	int i, count = 0;
4777
4778	for (i = 0; i < hw->mac.num_rar_entries; i++, mac_table++) {
4779		/* do not count default RAR as available */
4780		if (mac_table->state & IXGBE_MAC_STATE_DEFAULT)
4781			continue;
4782
4783		/* only count unused and addresses that belong to us */
4784		if (mac_table->state & IXGBE_MAC_STATE_IN_USE) {
4785			if (mac_table->pool != pool)
4786				continue;
4787		}
4788
4789		count++;
4790	}
4791
4792	return count;
4793}
4794
4795/* this function destroys the first RAR entry */
4796static void ixgbe_mac_set_default_filter(struct ixgbe_adapter *adapter)
4797{
4798	struct ixgbe_mac_addr *mac_table = &adapter->mac_table[0];
4799	struct ixgbe_hw *hw = &adapter->hw;
4800
4801	memcpy(&mac_table->addr, hw->mac.addr, ETH_ALEN);
4802	mac_table->pool = VMDQ_P(0);
4803
4804	mac_table->state = IXGBE_MAC_STATE_DEFAULT | IXGBE_MAC_STATE_IN_USE;
4805
4806	hw->mac.ops.set_rar(hw, 0, mac_table->addr, mac_table->pool,
4807			    IXGBE_RAH_AV);
4808}
4809
4810int ixgbe_add_mac_filter(struct ixgbe_adapter *adapter,
4811			 const u8 *addr, u16 pool)
4812{
4813	struct ixgbe_mac_addr *mac_table = &adapter->mac_table[0];
4814	struct ixgbe_hw *hw = &adapter->hw;
4815	int i;
4816
4817	if (is_zero_ether_addr(addr))
4818		return -EINVAL;
4819
4820	for (i = 0; i < hw->mac.num_rar_entries; i++, mac_table++) {
4821		if (mac_table->state & IXGBE_MAC_STATE_IN_USE)
4822			continue;
4823
4824		ether_addr_copy(mac_table->addr, addr);
4825		mac_table->pool = pool;
4826
4827		mac_table->state |= IXGBE_MAC_STATE_MODIFIED |
4828				    IXGBE_MAC_STATE_IN_USE;
4829
4830		ixgbe_sync_mac_table(adapter);
4831
4832		return i;
4833	}
4834
4835	return -ENOMEM;
4836}
4837
4838int ixgbe_del_mac_filter(struct ixgbe_adapter *adapter,
4839			 const u8 *addr, u16 pool)
4840{
4841	struct ixgbe_mac_addr *mac_table = &adapter->mac_table[0];
4842	struct ixgbe_hw *hw = &adapter->hw;
4843	int i;
4844
4845	if (is_zero_ether_addr(addr))
4846		return -EINVAL;
4847
4848	/* search table for addr, if found clear IN_USE flag and sync */
4849	for (i = 0; i < hw->mac.num_rar_entries; i++, mac_table++) {
4850		/* we can only delete an entry if it is in use */
4851		if (!(mac_table->state & IXGBE_MAC_STATE_IN_USE))
4852			continue;
4853		/* we only care about entries that belong to the given pool */
4854		if (mac_table->pool != pool)
4855			continue;
4856		/* we only care about a specific MAC address */
4857		if (!ether_addr_equal(addr, mac_table->addr))
4858			continue;
4859
4860		mac_table->state |= IXGBE_MAC_STATE_MODIFIED;
4861		mac_table->state &= ~IXGBE_MAC_STATE_IN_USE;
4862
4863		ixgbe_sync_mac_table(adapter);
4864
4865		return 0;
4866	}
4867
4868	return -ENOMEM;
4869}
4870
4871static int ixgbe_uc_sync(struct net_device *netdev, const unsigned char *addr)
4872{
4873	struct ixgbe_adapter *adapter = netdev_priv(netdev);
4874	int ret;
4875
4876	ret = ixgbe_add_mac_filter(adapter, addr, VMDQ_P(0));
4877
4878	return min_t(int, ret, 0);
4879}
4880
4881static int ixgbe_uc_unsync(struct net_device *netdev, const unsigned char *addr)
4882{
4883	struct ixgbe_adapter *adapter = netdev_priv(netdev);
4884
4885	ixgbe_del_mac_filter(adapter, addr, VMDQ_P(0));
4886
4887	return 0;
4888}
4889
4890/**
4891 * ixgbe_set_rx_mode - Unicast, Multicast and Promiscuous mode set
4892 * @netdev: network interface device structure
4893 *
4894 * The set_rx_method entry point is called whenever the unicast/multicast
4895 * address list or the network interface flags are updated.  This routine is
4896 * responsible for configuring the hardware for proper unicast, multicast and
4897 * promiscuous mode.
4898 **/
4899void ixgbe_set_rx_mode(struct net_device *netdev)
4900{
4901	struct ixgbe_adapter *adapter = netdev_priv(netdev);
4902	struct ixgbe_hw *hw = &adapter->hw;
4903	u32 fctrl, vmolr = IXGBE_VMOLR_BAM | IXGBE_VMOLR_AUPE;
4904	netdev_features_t features = netdev->features;
4905	int count;
4906
4907	/* Check for Promiscuous and All Multicast modes */
4908	fctrl = IXGBE_READ_REG(hw, IXGBE_FCTRL);
4909
4910	/* set all bits that we expect to always be set */
4911	fctrl &= ~IXGBE_FCTRL_SBP; /* disable store-bad-packets */
4912	fctrl |= IXGBE_FCTRL_BAM;
4913	fctrl |= IXGBE_FCTRL_DPF; /* discard pause frames when FC enabled */
4914	fctrl |= IXGBE_FCTRL_PMCF;
4915
4916	/* clear the bits we are changing the status of */
4917	fctrl &= ~(IXGBE_FCTRL_UPE | IXGBE_FCTRL_MPE);
4918	if (netdev->flags & IFF_PROMISC) {
4919		hw->addr_ctrl.user_set_promisc = true;
4920		fctrl |= (IXGBE_FCTRL_UPE | IXGBE_FCTRL_MPE);
4921		vmolr |= IXGBE_VMOLR_MPE;
4922		features &= ~NETIF_F_HW_VLAN_CTAG_FILTER;
4923	} else {
4924		if (netdev->flags & IFF_ALLMULTI) {
4925			fctrl |= IXGBE_FCTRL_MPE;
4926			vmolr |= IXGBE_VMOLR_MPE;
4927		}
4928		hw->addr_ctrl.user_set_promisc = false;
4929	}
4930
4931	/*
4932	 * Write addresses to available RAR registers, if there is not
4933	 * sufficient space to store all the addresses then enable
4934	 * unicast promiscuous mode
4935	 */
4936	if (__dev_uc_sync(netdev, ixgbe_uc_sync, ixgbe_uc_unsync)) {
4937		fctrl |= IXGBE_FCTRL_UPE;
4938		vmolr |= IXGBE_VMOLR_ROPE;
4939	}
4940
4941	/* Write addresses to the MTA, if the attempt fails
4942	 * then we should just turn on promiscuous mode so
4943	 * that we can at least receive multicast traffic
4944	 */
4945	count = ixgbe_write_mc_addr_list(netdev);
4946	if (count < 0) {
4947		fctrl |= IXGBE_FCTRL_MPE;
4948		vmolr |= IXGBE_VMOLR_MPE;
4949	} else if (count) {
4950		vmolr |= IXGBE_VMOLR_ROMPE;
4951	}
4952
4953	if (hw->mac.type != ixgbe_mac_82598EB) {
4954		vmolr |= IXGBE_READ_REG(hw, IXGBE_VMOLR(VMDQ_P(0))) &
4955			 ~(IXGBE_VMOLR_MPE | IXGBE_VMOLR_ROMPE |
4956			   IXGBE_VMOLR_ROPE);
4957		IXGBE_WRITE_REG(hw, IXGBE_VMOLR(VMDQ_P(0)), vmolr);
4958	}
4959
4960	/* This is useful for sniffing bad packets. */
4961	if (features & NETIF_F_RXALL) {
4962		/* UPE and MPE will be handled by normal PROMISC logic
4963		 * in e1000e_set_rx_mode */
4964		fctrl |= (IXGBE_FCTRL_SBP | /* Receive bad packets */
4965			  IXGBE_FCTRL_BAM | /* RX All Bcast Pkts */
4966			  IXGBE_FCTRL_PMCF); /* RX All MAC Ctrl Pkts */
4967
4968		fctrl &= ~(IXGBE_FCTRL_DPF);
4969		/* NOTE:  VLAN filtering is disabled by setting PROMISC */
4970	}
4971
4972	IXGBE_WRITE_REG(hw, IXGBE_FCTRL, fctrl);
4973
4974	if (features & NETIF_F_HW_VLAN_CTAG_RX)
4975		ixgbe_vlan_strip_enable(adapter);
4976	else
4977		ixgbe_vlan_strip_disable(adapter);
4978
4979	if (features & NETIF_F_HW_VLAN_CTAG_FILTER)
4980		ixgbe_vlan_promisc_disable(adapter);
4981	else
4982		ixgbe_vlan_promisc_enable(adapter);
4983}
4984
4985static void ixgbe_napi_enable_all(struct ixgbe_adapter *adapter)
4986{
4987	int q_idx;
4988
4989	for (q_idx = 0; q_idx < adapter->num_q_vectors; q_idx++)
4990		napi_enable(&adapter->q_vector[q_idx]->napi);
4991}
4992
4993static void ixgbe_napi_disable_all(struct ixgbe_adapter *adapter)
4994{
4995	int q_idx;
4996
4997	for (q_idx = 0; q_idx < adapter->num_q_vectors; q_idx++)
4998		napi_disable(&adapter->q_vector[q_idx]->napi);
4999}
5000
5001static int ixgbe_udp_tunnel_sync(struct net_device *dev, unsigned int table)
5002{
5003	struct ixgbe_adapter *adapter = netdev_priv(dev);
5004	struct ixgbe_hw *hw = &adapter->hw;
5005	struct udp_tunnel_info ti;
5006
5007	udp_tunnel_nic_get_port(dev, table, 0, &ti);
5008	if (ti.type == UDP_TUNNEL_TYPE_VXLAN)
5009		adapter->vxlan_port = ti.port;
5010	else
5011		adapter->geneve_port = ti.port;
5012
5013	IXGBE_WRITE_REG(hw, IXGBE_VXLANCTRL,
5014			ntohs(adapter->vxlan_port) |
5015			ntohs(adapter->geneve_port) <<
5016				IXGBE_VXLANCTRL_GENEVE_UDPPORT_SHIFT);
5017	return 0;
5018}
5019
5020static const struct udp_tunnel_nic_info ixgbe_udp_tunnels_x550 = {
5021	.sync_table	= ixgbe_udp_tunnel_sync,
5022	.flags		= UDP_TUNNEL_NIC_INFO_IPV4_ONLY,
5023	.tables		= {
5024		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN,  },
5025	},
5026};
5027
5028static const struct udp_tunnel_nic_info ixgbe_udp_tunnels_x550em_a = {
5029	.sync_table	= ixgbe_udp_tunnel_sync,
5030	.flags		= UDP_TUNNEL_NIC_INFO_IPV4_ONLY,
5031	.tables		= {
5032		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN,  },
5033		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, },
5034	},
5035};
5036
5037#ifdef CONFIG_IXGBE_DCB
5038/**
5039 * ixgbe_configure_dcb - Configure DCB hardware
5040 * @adapter: ixgbe adapter struct
5041 *
5042 * This is called by the driver on open to configure the DCB hardware.
5043 * This is also called by the gennetlink interface when reconfiguring
5044 * the DCB state.
5045 */
5046static void ixgbe_configure_dcb(struct ixgbe_adapter *adapter)
5047{
5048	struct ixgbe_hw *hw = &adapter->hw;
5049	int max_frame = adapter->netdev->mtu + ETH_HLEN + ETH_FCS_LEN;
5050
5051	if (!(adapter->flags & IXGBE_FLAG_DCB_ENABLED)) {
5052		if (hw->mac.type == ixgbe_mac_82598EB)
5053			netif_set_gso_max_size(adapter->netdev, 65536);
5054		return;
5055	}
5056
5057	if (hw->mac.type == ixgbe_mac_82598EB)
5058		netif_set_gso_max_size(adapter->netdev, 32768);
5059
5060#ifdef IXGBE_FCOE
5061	if (adapter->netdev->features & NETIF_F_FCOE_MTU)
5062		max_frame = max(max_frame, IXGBE_FCOE_JUMBO_FRAME_SIZE);
5063#endif
5064
5065	/* reconfigure the hardware */
5066	if (adapter->dcbx_cap & DCB_CAP_DCBX_VER_CEE) {
5067		ixgbe_dcb_calculate_tc_credits(hw, &adapter->dcb_cfg, max_frame,
5068						DCB_TX_CONFIG);
5069		ixgbe_dcb_calculate_tc_credits(hw, &adapter->dcb_cfg, max_frame,
5070						DCB_RX_CONFIG);
5071		ixgbe_dcb_hw_config(hw, &adapter->dcb_cfg);
5072	} else if (adapter->ixgbe_ieee_ets && adapter->ixgbe_ieee_pfc) {
5073		ixgbe_dcb_hw_ets(&adapter->hw,
5074				 adapter->ixgbe_ieee_ets,
5075				 max_frame);
5076		ixgbe_dcb_hw_pfc_config(&adapter->hw,
5077					adapter->ixgbe_ieee_pfc->pfc_en,
5078					adapter->ixgbe_ieee_ets->prio_tc);
5079	}
5080
5081	/* Enable RSS Hash per TC */
5082	if (hw->mac.type != ixgbe_mac_82598EB) {
5083		u32 msb = 0;
5084		u16 rss_i = adapter->ring_feature[RING_F_RSS].indices - 1;
5085
5086		while (rss_i) {
5087			msb++;
5088			rss_i >>= 1;
5089		}
5090
5091		/* write msb to all 8 TCs in one write */
5092		IXGBE_WRITE_REG(hw, IXGBE_RQTC, msb * 0x11111111);
5093	}
5094}
5095#endif
5096
5097/* Additional bittime to account for IXGBE framing */
5098#define IXGBE_ETH_FRAMING 20
5099
5100/**
5101 * ixgbe_hpbthresh - calculate high water mark for flow control
5102 *
5103 * @adapter: board private structure to calculate for
5104 * @pb: packet buffer to calculate
5105 */
5106static int ixgbe_hpbthresh(struct ixgbe_adapter *adapter, int pb)
5107{
5108	struct ixgbe_hw *hw = &adapter->hw;
5109	struct net_device *dev = adapter->netdev;
5110	int link, tc, kb, marker;
5111	u32 dv_id, rx_pba;
5112
5113	/* Calculate max LAN frame size */
5114	tc = link = dev->mtu + ETH_HLEN + ETH_FCS_LEN + IXGBE_ETH_FRAMING;
5115
5116#ifdef IXGBE_FCOE
5117	/* FCoE traffic class uses FCOE jumbo frames */
5118	if ((dev->features & NETIF_F_FCOE_MTU) &&
5119	    (tc < IXGBE_FCOE_JUMBO_FRAME_SIZE) &&
5120	    (pb == ixgbe_fcoe_get_tc(adapter)))
5121		tc = IXGBE_FCOE_JUMBO_FRAME_SIZE;
5122#endif
5123
5124	/* Calculate delay value for device */
5125	switch (hw->mac.type) {
5126	case ixgbe_mac_X540:
5127	case ixgbe_mac_X550:
5128	case ixgbe_mac_X550EM_x:
5129	case ixgbe_mac_x550em_a:
5130		dv_id = IXGBE_DV_X540(link, tc);
5131		break;
5132	default:
5133		dv_id = IXGBE_DV(link, tc);
5134		break;
5135	}
5136
5137	/* Loopback switch introduces additional latency */
5138	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
5139		dv_id += IXGBE_B2BT(tc);
5140
5141	/* Delay value is calculated in bit times convert to KB */
5142	kb = IXGBE_BT2KB(dv_id);
5143	rx_pba = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(pb)) >> 10;
5144
5145	marker = rx_pba - kb;
5146
5147	/* It is possible that the packet buffer is not large enough
5148	 * to provide required headroom. In this case throw an error
5149	 * to user and a do the best we can.
5150	 */
5151	if (marker < 0) {
5152		e_warn(drv, "Packet Buffer(%i) can not provide enough"
5153			    "headroom to support flow control."
5154			    "Decrease MTU or number of traffic classes\n", pb);
5155		marker = tc + 1;
5156	}
5157
5158	return marker;
5159}
5160
5161/**
5162 * ixgbe_lpbthresh - calculate low water mark for for flow control
5163 *
5164 * @adapter: board private structure to calculate for
5165 * @pb: packet buffer to calculate
5166 */
5167static int ixgbe_lpbthresh(struct ixgbe_adapter *adapter, int pb)
5168{
5169	struct ixgbe_hw *hw = &adapter->hw;
5170	struct net_device *dev = adapter->netdev;
5171	int tc;
5172	u32 dv_id;
5173
5174	/* Calculate max LAN frame size */
5175	tc = dev->mtu + ETH_HLEN + ETH_FCS_LEN;
5176
5177#ifdef IXGBE_FCOE
5178	/* FCoE traffic class uses FCOE jumbo frames */
5179	if ((dev->features & NETIF_F_FCOE_MTU) &&
5180	    (tc < IXGBE_FCOE_JUMBO_FRAME_SIZE) &&
5181	    (pb == netdev_get_prio_tc_map(dev, adapter->fcoe.up)))
5182		tc = IXGBE_FCOE_JUMBO_FRAME_SIZE;
5183#endif
5184
5185	/* Calculate delay value for device */
5186	switch (hw->mac.type) {
5187	case ixgbe_mac_X540:
5188	case ixgbe_mac_X550:
5189	case ixgbe_mac_X550EM_x:
5190	case ixgbe_mac_x550em_a:
5191		dv_id = IXGBE_LOW_DV_X540(tc);
5192		break;
5193	default:
5194		dv_id = IXGBE_LOW_DV(tc);
5195		break;
5196	}
5197
5198	/* Delay value is calculated in bit times convert to KB */
5199	return IXGBE_BT2KB(dv_id);
5200}
5201
5202/*
5203 * ixgbe_pbthresh_setup - calculate and setup high low water marks
5204 */
5205static void ixgbe_pbthresh_setup(struct ixgbe_adapter *adapter)
5206{
5207	struct ixgbe_hw *hw = &adapter->hw;
5208	int num_tc = adapter->hw_tcs;
5209	int i;
5210
5211	if (!num_tc)
5212		num_tc = 1;
5213
5214	for (i = 0; i < num_tc; i++) {
5215		hw->fc.high_water[i] = ixgbe_hpbthresh(adapter, i);
5216		hw->fc.low_water[i] = ixgbe_lpbthresh(adapter, i);
5217
5218		/* Low water marks must not be larger than high water marks */
5219		if (hw->fc.low_water[i] > hw->fc.high_water[i])
5220			hw->fc.low_water[i] = 0;
5221	}
5222
5223	for (; i < MAX_TRAFFIC_CLASS; i++)
5224		hw->fc.high_water[i] = 0;
5225}
5226
5227static void ixgbe_configure_pb(struct ixgbe_adapter *adapter)
5228{
5229	struct ixgbe_hw *hw = &adapter->hw;
5230	int hdrm;
5231	u8 tc = adapter->hw_tcs;
5232
5233	if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE ||
5234	    adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE)
5235		hdrm = 32 << adapter->fdir_pballoc;
5236	else
5237		hdrm = 0;
5238
5239	hw->mac.ops.set_rxpba(hw, tc, hdrm, PBA_STRATEGY_EQUAL);
5240	ixgbe_pbthresh_setup(adapter);
5241}
5242
5243static void ixgbe_fdir_filter_restore(struct ixgbe_adapter *adapter)
5244{
5245	struct ixgbe_hw *hw = &adapter->hw;
5246	struct hlist_node *node2;
5247	struct ixgbe_fdir_filter *filter;
5248	u8 queue;
5249
5250	spin_lock(&adapter->fdir_perfect_lock);
5251
5252	if (!hlist_empty(&adapter->fdir_filter_list))
5253		ixgbe_fdir_set_input_mask_82599(hw, &adapter->fdir_mask);
5254
5255	hlist_for_each_entry_safe(filter, node2,
5256				  &adapter->fdir_filter_list, fdir_node) {
5257		if (filter->action == IXGBE_FDIR_DROP_QUEUE) {
5258			queue = IXGBE_FDIR_DROP_QUEUE;
5259		} else {
5260			u32 ring = ethtool_get_flow_spec_ring(filter->action);
5261			u8 vf = ethtool_get_flow_spec_ring_vf(filter->action);
5262
5263			if (!vf && (ring >= adapter->num_rx_queues)) {
5264				e_err(drv, "FDIR restore failed without VF, ring: %u\n",
5265				      ring);
5266				continue;
5267			} else if (vf &&
5268				   ((vf > adapter->num_vfs) ||
5269				     ring >= adapter->num_rx_queues_per_pool)) {
5270				e_err(drv, "FDIR restore failed with VF, vf: %hhu, ring: %u\n",
5271				      vf, ring);
5272				continue;
5273			}
5274
5275			/* Map the ring onto the absolute queue index */
5276			if (!vf)
5277				queue = adapter->rx_ring[ring]->reg_idx;
5278			else
5279				queue = ((vf - 1) *
5280					adapter->num_rx_queues_per_pool) + ring;
5281		}
5282
5283		ixgbe_fdir_write_perfect_filter_82599(hw,
5284				&filter->filter, filter->sw_idx, queue);
5285	}
5286
5287	spin_unlock(&adapter->fdir_perfect_lock);
5288}
5289
5290/**
5291 * ixgbe_clean_rx_ring - Free Rx Buffers per Queue
5292 * @rx_ring: ring to free buffers from
5293 **/
5294static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring)
5295{
5296	u16 i = rx_ring->next_to_clean;
5297	struct ixgbe_rx_buffer *rx_buffer = &rx_ring->rx_buffer_info[i];
5298
5299	if (rx_ring->xsk_pool) {
5300		ixgbe_xsk_clean_rx_ring(rx_ring);
5301		goto skip_free;
5302	}
5303
5304	/* Free all the Rx ring sk_buffs */
5305	while (i != rx_ring->next_to_alloc) {
5306		if (rx_buffer->skb) {
5307			struct sk_buff *skb = rx_buffer->skb;
5308			if (IXGBE_CB(skb)->page_released)
5309				dma_unmap_page_attrs(rx_ring->dev,
5310						     IXGBE_CB(skb)->dma,
5311						     ixgbe_rx_pg_size(rx_ring),
5312						     DMA_FROM_DEVICE,
5313						     IXGBE_RX_DMA_ATTR);
5314			dev_kfree_skb(skb);
5315		}
5316
5317		/* Invalidate cache lines that may have been written to by
5318		 * device so that we avoid corrupting memory.
5319		 */
5320		dma_sync_single_range_for_cpu(rx_ring->dev,
5321					      rx_buffer->dma,
5322					      rx_buffer->page_offset,
5323					      ixgbe_rx_bufsz(rx_ring),
5324					      DMA_FROM_DEVICE);
5325
5326		/* free resources associated with mapping */
5327		dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma,
5328				     ixgbe_rx_pg_size(rx_ring),
5329				     DMA_FROM_DEVICE,
5330				     IXGBE_RX_DMA_ATTR);
5331		__page_frag_cache_drain(rx_buffer->page,
5332					rx_buffer->pagecnt_bias);
5333
5334		i++;
5335		rx_buffer++;
5336		if (i == rx_ring->count) {
5337			i = 0;
5338			rx_buffer = rx_ring->rx_buffer_info;
5339		}
5340	}
5341
5342skip_free:
5343	rx_ring->next_to_alloc = 0;
5344	rx_ring->next_to_clean = 0;
5345	rx_ring->next_to_use = 0;
5346}
5347
5348static int ixgbe_fwd_ring_up(struct ixgbe_adapter *adapter,
5349			     struct ixgbe_fwd_adapter *accel)
5350{
5351	u16 rss_i = adapter->ring_feature[RING_F_RSS].indices;
5352	int num_tc = netdev_get_num_tc(adapter->netdev);
5353	struct net_device *vdev = accel->netdev;
5354	int i, baseq, err;
5355
5356	baseq = accel->pool * adapter->num_rx_queues_per_pool;
5357	netdev_dbg(vdev, "pool %i:%i queues %i:%i\n",
5358		   accel->pool, adapter->num_rx_pools,
5359		   baseq, baseq + adapter->num_rx_queues_per_pool);
5360
5361	accel->rx_base_queue = baseq;
5362	accel->tx_base_queue = baseq;
5363
5364	/* record configuration for macvlan interface in vdev */
5365	for (i = 0; i < num_tc; i++)
5366		netdev_bind_sb_channel_queue(adapter->netdev, vdev,
5367					     i, rss_i, baseq + (rss_i * i));
5368
5369	for (i = 0; i < adapter->num_rx_queues_per_pool; i++)
5370		adapter->rx_ring[baseq + i]->netdev = vdev;
5371
5372	/* Guarantee all rings are updated before we update the
5373	 * MAC address filter.
5374	 */
5375	wmb();
5376
5377	/* ixgbe_add_mac_filter will return an index if it succeeds, so we
5378	 * need to only treat it as an error value if it is negative.
5379	 */
5380	err = ixgbe_add_mac_filter(adapter, vdev->dev_addr,
5381				   VMDQ_P(accel->pool));
5382	if (err >= 0)
5383		return 0;
5384
5385	/* if we cannot add the MAC rule then disable the offload */
5386	macvlan_release_l2fw_offload(vdev);
5387
5388	for (i = 0; i < adapter->num_rx_queues_per_pool; i++)
5389		adapter->rx_ring[baseq + i]->netdev = NULL;
5390
5391	netdev_err(vdev, "L2FW offload disabled due to L2 filter error\n");
5392
5393	/* unbind the queues and drop the subordinate channel config */
5394	netdev_unbind_sb_channel(adapter->netdev, vdev);
5395	netdev_set_sb_channel(vdev, 0);
5396
5397	clear_bit(accel->pool, adapter->fwd_bitmask);
5398	kfree(accel);
5399
5400	return err;
5401}
5402
5403static int ixgbe_macvlan_up(struct net_device *vdev,
5404			    struct netdev_nested_priv *priv)
5405{
5406	struct ixgbe_adapter *adapter = (struct ixgbe_adapter *)priv->data;
5407	struct ixgbe_fwd_adapter *accel;
5408
5409	if (!netif_is_macvlan(vdev))
5410		return 0;
5411
5412	accel = macvlan_accel_priv(vdev);
5413	if (!accel)
5414		return 0;
5415
5416	ixgbe_fwd_ring_up(adapter, accel);
5417
5418	return 0;
5419}
5420
5421static void ixgbe_configure_dfwd(struct ixgbe_adapter *adapter)
5422{
5423	struct netdev_nested_priv priv = {
5424		.data = (void *)adapter,
5425	};
5426
5427	netdev_walk_all_upper_dev_rcu(adapter->netdev,
5428				      ixgbe_macvlan_up, &priv);
5429}
5430
5431static void ixgbe_configure(struct ixgbe_adapter *adapter)
5432{
5433	struct ixgbe_hw *hw = &adapter->hw;
5434
5435	ixgbe_configure_pb(adapter);
5436#ifdef CONFIG_IXGBE_DCB
5437	ixgbe_configure_dcb(adapter);
5438#endif
5439	/*
5440	 * We must restore virtualization before VLANs or else
5441	 * the VLVF registers will not be populated
5442	 */
5443	ixgbe_configure_virtualization(adapter);
5444
5445	ixgbe_set_rx_mode(adapter->netdev);
5446	ixgbe_restore_vlan(adapter);
5447	ixgbe_ipsec_restore(adapter);
5448
5449	switch (hw->mac.type) {
5450	case ixgbe_mac_82599EB:
5451	case ixgbe_mac_X540:
5452		hw->mac.ops.disable_rx_buff(hw);
5453		break;
5454	default:
5455		break;
5456	}
5457
5458	if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) {
5459		ixgbe_init_fdir_signature_82599(&adapter->hw,
5460						adapter->fdir_pballoc);
5461	} else if (adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE) {
5462		ixgbe_init_fdir_perfect_82599(&adapter->hw,
5463					      adapter->fdir_pballoc);
5464		ixgbe_fdir_filter_restore(adapter);
5465	}
5466
5467	switch (hw->mac.type) {
5468	case ixgbe_mac_82599EB:
5469	case ixgbe_mac_X540:
5470		hw->mac.ops.enable_rx_buff(hw);
5471		break;
5472	default:
5473		break;
5474	}
5475
5476#ifdef CONFIG_IXGBE_DCA
5477	/* configure DCA */
5478	if (adapter->flags & IXGBE_FLAG_DCA_CAPABLE)
5479		ixgbe_setup_dca(adapter);
5480#endif /* CONFIG_IXGBE_DCA */
5481
5482#ifdef IXGBE_FCOE
5483	/* configure FCoE L2 filters, redirection table, and Rx control */
5484	ixgbe_configure_fcoe(adapter);
5485
5486#endif /* IXGBE_FCOE */
5487	ixgbe_configure_tx(adapter);
5488	ixgbe_configure_rx(adapter);
5489	ixgbe_configure_dfwd(adapter);
5490}
5491
5492/**
5493 * ixgbe_sfp_link_config - set up SFP+ link
5494 * @adapter: pointer to private adapter struct
5495 **/
5496static void ixgbe_sfp_link_config(struct ixgbe_adapter *adapter)
5497{
5498	/*
5499	 * We are assuming the worst case scenario here, and that
5500	 * is that an SFP was inserted/removed after the reset
5501	 * but before SFP detection was enabled.  As such the best
5502	 * solution is to just start searching as soon as we start
5503	 */
5504	if (adapter->hw.mac.type == ixgbe_mac_82598EB)
5505		adapter->flags2 |= IXGBE_FLAG2_SEARCH_FOR_SFP;
5506
5507	adapter->flags2 |= IXGBE_FLAG2_SFP_NEEDS_RESET;
5508	adapter->sfp_poll_time = 0;
5509}
5510
5511/**
5512 * ixgbe_non_sfp_link_config - set up non-SFP+ link
5513 * @hw: pointer to private hardware struct
5514 *
5515 * Returns 0 on success, negative on failure
5516 **/
5517static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw)
5518{
5519	u32 speed;
5520	bool autoneg, link_up = false;
5521	int ret = -EIO;
5522
5523	if (hw->mac.ops.check_link)
5524		ret = hw->mac.ops.check_link(hw, &speed, &link_up, false);
5525
5526	if (ret)
5527		return ret;
5528
5529	speed = hw->phy.autoneg_advertised;
5530	if (!speed && hw->mac.ops.get_link_capabilities) {
5531		ret = hw->mac.ops.get_link_capabilities(hw, &speed,
5532							&autoneg);
5533		/* remove NBASE-T speeds from default autonegotiation
5534		 * to accommodate broken network switches in the field
5535		 * which cannot cope with advertised NBASE-T speeds
5536		 */
5537		speed &= ~(IXGBE_LINK_SPEED_5GB_FULL |
5538			   IXGBE_LINK_SPEED_2_5GB_FULL);
5539	}
5540
5541	if (ret)
5542		return ret;
5543
5544	if (hw->mac.ops.setup_link)
5545		ret = hw->mac.ops.setup_link(hw, speed, link_up);
5546
5547	return ret;
5548}
5549
5550static void ixgbe_setup_gpie(struct ixgbe_adapter *adapter)
5551{
5552	struct ixgbe_hw *hw = &adapter->hw;
5553	u32 gpie = 0;
5554
5555	if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) {
5556		gpie = IXGBE_GPIE_MSIX_MODE | IXGBE_GPIE_PBA_SUPPORT |
5557		       IXGBE_GPIE_OCD;
5558		gpie |= IXGBE_GPIE_EIAME;
5559		/*
5560		 * use EIAM to auto-mask when MSI-X interrupt is asserted
5561		 * this saves a register write for every interrupt
5562		 */
5563		switch (hw->mac.type) {
5564		case ixgbe_mac_82598EB:
5565			IXGBE_WRITE_REG(hw, IXGBE_EIAM, IXGBE_EICS_RTX_QUEUE);
5566			break;
5567		case ixgbe_mac_82599EB:
5568		case ixgbe_mac_X540:
5569		case ixgbe_mac_X550:
5570		case ixgbe_mac_X550EM_x:
5571		case ixgbe_mac_x550em_a:
5572		default:
5573			IXGBE_WRITE_REG(hw, IXGBE_EIAM_EX(0), 0xFFFFFFFF);
5574			IXGBE_WRITE_REG(hw, IXGBE_EIAM_EX(1), 0xFFFFFFFF);
5575			break;
5576		}
5577	} else {
5578		/* legacy interrupts, use EIAM to auto-mask when reading EICR,
5579		 * specifically only auto mask tx and rx interrupts */
5580		IXGBE_WRITE_REG(hw, IXGBE_EIAM, IXGBE_EICS_RTX_QUEUE);
5581	}
5582
5583	/* XXX: to interrupt immediately for EICS writes, enable this */
5584	/* gpie |= IXGBE_GPIE_EIMEN; */
5585
5586	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) {
5587		gpie &= ~IXGBE_GPIE_VTMODE_MASK;
5588
5589		switch (adapter->ring_feature[RING_F_VMDQ].mask) {
5590		case IXGBE_82599_VMDQ_8Q_MASK:
5591			gpie |= IXGBE_GPIE_VTMODE_16;
5592			break;
5593		case IXGBE_82599_VMDQ_4Q_MASK:
5594			gpie |= IXGBE_GPIE_VTMODE_32;
5595			break;
5596		default:
5597			gpie |= IXGBE_GPIE_VTMODE_64;
5598			break;
5599		}
5600	}
5601
5602	/* Enable Thermal over heat sensor interrupt */
5603	if (adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE) {
5604		switch (adapter->hw.mac.type) {
5605		case ixgbe_mac_82599EB:
5606			gpie |= IXGBE_SDP0_GPIEN_8259X;
5607			break;
5608		default:
5609			break;
5610		}
5611	}
5612
5613	/* Enable fan failure interrupt */
5614	if (adapter->flags & IXGBE_FLAG_FAN_FAIL_CAPABLE)
5615		gpie |= IXGBE_SDP1_GPIEN(hw);
5616
5617	switch (hw->mac.type) {
5618	case ixgbe_mac_82599EB:
5619		gpie |= IXGBE_SDP1_GPIEN_8259X | IXGBE_SDP2_GPIEN_8259X;
5620		break;
5621	case ixgbe_mac_X550EM_x:
5622	case ixgbe_mac_x550em_a:
5623		gpie |= IXGBE_SDP0_GPIEN_X540;
5624		break;
5625	default:
5626		break;
5627	}
5628
5629	IXGBE_WRITE_REG(hw, IXGBE_GPIE, gpie);
5630}
5631
5632static void ixgbe_up_complete(struct ixgbe_adapter *adapter)
5633{
5634	struct ixgbe_hw *hw = &adapter->hw;
5635	int err;
5636	u32 ctrl_ext;
5637
5638	ixgbe_get_hw_control(adapter);
5639	ixgbe_setup_gpie(adapter);
5640
5641	if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED)
5642		ixgbe_configure_msix(adapter);
5643	else
5644		ixgbe_configure_msi_and_legacy(adapter);
5645
5646	/* enable the optics for 82599 SFP+ fiber */
5647	if (hw->mac.ops.enable_tx_laser)
5648		hw->mac.ops.enable_tx_laser(hw);
5649
5650	if (hw->phy.ops.set_phy_power)
5651		hw->phy.ops.set_phy_power(hw, true);
5652
5653	smp_mb__before_atomic();
5654	clear_bit(__IXGBE_DOWN, &adapter->state);
5655	ixgbe_napi_enable_all(adapter);
5656
5657	if (ixgbe_is_sfp(hw)) {
5658		ixgbe_sfp_link_config(adapter);
5659	} else {
5660		err = ixgbe_non_sfp_link_config(hw);
5661		if (err)
5662			e_err(probe, "link_config FAILED %d\n", err);
5663	}
5664
5665	/* clear any pending interrupts, may auto mask */
5666	IXGBE_READ_REG(hw, IXGBE_EICR);
5667	ixgbe_irq_enable(adapter, true, true);
5668
5669	/*
5670	 * If this adapter has a fan, check to see if we had a failure
5671	 * before we enabled the interrupt.
5672	 */
5673	if (adapter->flags & IXGBE_FLAG_FAN_FAIL_CAPABLE) {
5674		u32 esdp = IXGBE_READ_REG(hw, IXGBE_ESDP);
5675		if (esdp & IXGBE_ESDP_SDP1)
5676			e_crit(drv, "Fan has stopped, replace the adapter\n");
5677	}
5678
5679	/* bring the link up in the watchdog, this could race with our first
5680	 * link up interrupt but shouldn't be a problem */
5681	adapter->flags |= IXGBE_FLAG_NEED_LINK_UPDATE;
5682	adapter->link_check_timeout = jiffies;
5683	mod_timer(&adapter->service_timer, jiffies);
5684
5685	/* Set PF Reset Done bit so PF/VF Mail Ops can work */
5686	ctrl_ext = IXGBE_READ_REG(hw, IXGBE_CTRL_EXT);
5687	ctrl_ext |= IXGBE_CTRL_EXT_PFRSTD;
5688	IXGBE_WRITE_REG(hw, IXGBE_CTRL_EXT, ctrl_ext);
5689
5690	/* update setting rx tx for all active vfs */
5691	ixgbe_set_all_vfs(adapter);
5692}
5693
5694void ixgbe_reinit_locked(struct ixgbe_adapter *adapter)
5695{
5696	/* put off any impending NetWatchDogTimeout */
5697	netif_trans_update(adapter->netdev);
5698
5699	while (test_and_set_bit(__IXGBE_RESETTING, &adapter->state))
5700		usleep_range(1000, 2000);
5701	if (adapter->hw.phy.type == ixgbe_phy_fw)
5702		ixgbe_watchdog_link_is_down(adapter);
5703	ixgbe_down(adapter);
5704	/*
5705	 * If SR-IOV enabled then wait a bit before bringing the adapter
5706	 * back up to give the VFs time to respond to the reset.  The
5707	 * two second wait is based upon the watchdog timer cycle in
5708	 * the VF driver.
5709	 */
5710	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
5711		msleep(2000);
5712	ixgbe_up(adapter);
5713	clear_bit(__IXGBE_RESETTING, &adapter->state);
5714}
5715
5716void ixgbe_up(struct ixgbe_adapter *adapter)
5717{
5718	/* hardware has been reset, we need to reload some things */
5719	ixgbe_configure(adapter);
5720
5721	ixgbe_up_complete(adapter);
5722}
5723
5724static unsigned long ixgbe_get_completion_timeout(struct ixgbe_adapter *adapter)
5725{
5726	u16 devctl2;
5727
5728	pcie_capability_read_word(adapter->pdev, PCI_EXP_DEVCTL2, &devctl2);
5729
5730	switch (devctl2 & IXGBE_PCIDEVCTRL2_TIMEO_MASK) {
5731	case IXGBE_PCIDEVCTRL2_17_34s:
5732	case IXGBE_PCIDEVCTRL2_4_8s:
5733		/* For now we cap the upper limit on delay to 2 seconds
5734		 * as we end up going up to 34 seconds of delay in worst
5735		 * case timeout value.
5736		 */
5737	case IXGBE_PCIDEVCTRL2_1_2s:
5738		return 2000000ul;	/* 2.0 s */
5739	case IXGBE_PCIDEVCTRL2_260_520ms:
5740		return 520000ul;	/* 520 ms */
5741	case IXGBE_PCIDEVCTRL2_65_130ms:
5742		return 130000ul;	/* 130 ms */
5743	case IXGBE_PCIDEVCTRL2_16_32ms:
5744		return 32000ul;		/* 32 ms */
5745	case IXGBE_PCIDEVCTRL2_1_2ms:
5746		return 2000ul;		/* 2 ms */
5747	case IXGBE_PCIDEVCTRL2_50_100us:
5748		return 100ul;		/* 100 us */
5749	case IXGBE_PCIDEVCTRL2_16_32ms_def:
5750		return 32000ul;		/* 32 ms */
5751	default:
5752		break;
5753	}
5754
5755	/* We shouldn't need to hit this path, but just in case default as
5756	 * though completion timeout is not supported and support 32ms.
5757	 */
5758	return 32000ul;
5759}
5760
5761void ixgbe_disable_rx(struct ixgbe_adapter *adapter)
5762{
5763	unsigned long wait_delay, delay_interval;
5764	struct ixgbe_hw *hw = &adapter->hw;
5765	int i, wait_loop;
5766	u32 rxdctl;
5767
5768	/* disable receives */
5769	hw->mac.ops.disable_rx(hw);
5770
5771	if (ixgbe_removed(hw->hw_addr))
5772		return;
5773
5774	/* disable all enabled Rx queues */
5775	for (i = 0; i < adapter->num_rx_queues; i++) {
5776		struct ixgbe_ring *ring = adapter->rx_ring[i];
5777		u8 reg_idx = ring->reg_idx;
5778
5779		rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
5780		rxdctl &= ~IXGBE_RXDCTL_ENABLE;
5781		rxdctl |= IXGBE_RXDCTL_SWFLSH;
5782
5783		/* write value back with RXDCTL.ENABLE bit cleared */
5784		IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl);
5785	}
5786
5787	/* RXDCTL.EN may not change on 82598 if link is down, so skip it */
5788	if (hw->mac.type == ixgbe_mac_82598EB &&
5789	    !(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP))
5790		return;
5791
5792	/* Determine our minimum delay interval. We will increase this value
5793	 * with each subsequent test. This way if the device returns quickly
5794	 * we should spend as little time as possible waiting, however as
5795	 * the time increases we will wait for larger periods of time.
5796	 *
5797	 * The trick here is that we increase the interval using the
5798	 * following pattern: 1x 3x 5x 7x 9x 11x 13x 15x 17x 19x. The result
5799	 * of that wait is that it totals up to 100x whatever interval we
5800	 * choose. Since our minimum wait is 100us we can just divide the
5801	 * total timeout by 100 to get our minimum delay interval.
5802	 */
5803	delay_interval = ixgbe_get_completion_timeout(adapter) / 100;
5804
5805	wait_loop = IXGBE_MAX_RX_DESC_POLL;
5806	wait_delay = delay_interval;
5807
5808	while (wait_loop--) {
5809		usleep_range(wait_delay, wait_delay + 10);
5810		wait_delay += delay_interval * 2;
5811		rxdctl = 0;
5812
5813		/* OR together the reading of all the active RXDCTL registers,
5814		 * and then test the result. We need the disable to complete
5815		 * before we start freeing the memory and invalidating the
5816		 * DMA mappings.
5817		 */
5818		for (i = 0; i < adapter->num_rx_queues; i++) {
5819			struct ixgbe_ring *ring = adapter->rx_ring[i];
5820			u8 reg_idx = ring->reg_idx;
5821
5822			rxdctl |= IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
5823		}
5824
5825		if (!(rxdctl & IXGBE_RXDCTL_ENABLE))
5826			return;
5827	}
5828
5829	e_err(drv,
5830	      "RXDCTL.ENABLE for one or more queues not cleared within the polling period\n");
5831}
5832
5833void ixgbe_disable_tx(struct ixgbe_adapter *adapter)
5834{
5835	unsigned long wait_delay, delay_interval;
5836	struct ixgbe_hw *hw = &adapter->hw;
5837	int i, wait_loop;
5838	u32 txdctl;
5839
5840	if (ixgbe_removed(hw->hw_addr))
5841		return;
5842
5843	/* disable all enabled Tx queues */
5844	for (i = 0; i < adapter->num_tx_queues; i++) {
5845		struct ixgbe_ring *ring = adapter->tx_ring[i];
5846		u8 reg_idx = ring->reg_idx;
5847
5848		IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH);
5849	}
5850
5851	/* disable all enabled XDP Tx queues */
5852	for (i = 0; i < adapter->num_xdp_queues; i++) {
5853		struct ixgbe_ring *ring = adapter->xdp_ring[i];
5854		u8 reg_idx = ring->reg_idx;
5855
5856		IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH);
5857	}
5858
5859	/* If the link is not up there shouldn't be much in the way of
5860	 * pending transactions. Those that are left will be flushed out
5861	 * when the reset logic goes through the flush sequence to clean out
5862	 * the pending Tx transactions.
5863	 */
5864	if (!(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP))
5865		goto dma_engine_disable;
5866
5867	/* Determine our minimum delay interval. We will increase this value
5868	 * with each subsequent test. This way if the device returns quickly
5869	 * we should spend as little time as possible waiting, however as
5870	 * the time increases we will wait for larger periods of time.
5871	 *
5872	 * The trick here is that we increase the interval using the
5873	 * following pattern: 1x 3x 5x 7x 9x 11x 13x 15x 17x 19x. The result
5874	 * of that wait is that it totals up to 100x whatever interval we
5875	 * choose. Since our minimum wait is 100us we can just divide the
5876	 * total timeout by 100 to get our minimum delay interval.
5877	 */
5878	delay_interval = ixgbe_get_completion_timeout(adapter) / 100;
5879
5880	wait_loop = IXGBE_MAX_RX_DESC_POLL;
5881	wait_delay = delay_interval;
5882
5883	while (wait_loop--) {
5884		usleep_range(wait_delay, wait_delay + 10);
5885		wait_delay += delay_interval * 2;
5886		txdctl = 0;
5887
5888		/* OR together the reading of all the active TXDCTL registers,
5889		 * and then test the result. We need the disable to complete
5890		 * before we start freeing the memory and invalidating the
5891		 * DMA mappings.
5892		 */
5893		for (i = 0; i < adapter->num_tx_queues; i++) {
5894			struct ixgbe_ring *ring = adapter->tx_ring[i];
5895			u8 reg_idx = ring->reg_idx;
5896
5897			txdctl |= IXGBE_READ_REG(hw, IXGBE_TXDCTL(reg_idx));
5898		}
5899		for (i = 0; i < adapter->num_xdp_queues; i++) {
5900			struct ixgbe_ring *ring = adapter->xdp_ring[i];
5901			u8 reg_idx = ring->reg_idx;
5902
5903			txdctl |= IXGBE_READ_REG(hw, IXGBE_TXDCTL(reg_idx));
5904		}
5905
5906		if (!(txdctl & IXGBE_TXDCTL_ENABLE))
5907			goto dma_engine_disable;
5908	}
5909
5910	e_err(drv,
5911	      "TXDCTL.ENABLE for one or more queues not cleared within the polling period\n");
5912
5913dma_engine_disable:
5914	/* Disable the Tx DMA engine on 82599 and later MAC */
5915	switch (hw->mac.type) {
5916	case ixgbe_mac_82599EB:
5917	case ixgbe_mac_X540:
5918	case ixgbe_mac_X550:
5919	case ixgbe_mac_X550EM_x:
5920	case ixgbe_mac_x550em_a:
5921		IXGBE_WRITE_REG(hw, IXGBE_DMATXCTL,
5922				(IXGBE_READ_REG(hw, IXGBE_DMATXCTL) &
5923				 ~IXGBE_DMATXCTL_TE));
5924		fallthrough;
5925	default:
5926		break;
5927	}
5928}
5929
5930void ixgbe_reset(struct ixgbe_adapter *adapter)
5931{
5932	struct ixgbe_hw *hw = &adapter->hw;
5933	struct net_device *netdev = adapter->netdev;
5934	int err;
5935
5936	if (ixgbe_removed(hw->hw_addr))
5937		return;
5938	/* lock SFP init bit to prevent race conditions with the watchdog */
5939	while (test_and_set_bit(__IXGBE_IN_SFP_INIT, &adapter->state))
5940		usleep_range(1000, 2000);
5941
5942	/* clear all SFP and link config related flags while holding SFP_INIT */
5943	adapter->flags2 &= ~(IXGBE_FLAG2_SEARCH_FOR_SFP |
5944			     IXGBE_FLAG2_SFP_NEEDS_RESET);
5945	adapter->flags &= ~IXGBE_FLAG_NEED_LINK_CONFIG;
5946
5947	err = hw->mac.ops.init_hw(hw);
5948	switch (err) {
5949	case 0:
5950	case -ENOENT:
5951	case -EOPNOTSUPP:
5952		break;
5953	case -EALREADY:
5954		e_dev_err("primary disable timed out\n");
5955		break;
5956	case -EACCES:
5957		/* We are running on a pre-production device, log a warning */
5958		e_dev_warn("This device is a pre-production adapter/LOM. "
5959			   "Please be aware there may be issues associated with "
5960			   "your hardware.  If you are experiencing problems "
5961			   "please contact your Intel or hardware "
5962			   "representative who provided you with this "
5963			   "hardware.\n");
5964		break;
5965	default:
5966		e_dev_err("Hardware Error: %d\n", err);
5967	}
5968
5969	clear_bit(__IXGBE_IN_SFP_INIT, &adapter->state);
5970
5971	/* flush entries out of MAC table */
5972	ixgbe_flush_sw_mac_table(adapter);
5973	__dev_uc_unsync(netdev, NULL);
5974
5975	/* do not flush user set addresses */
5976	ixgbe_mac_set_default_filter(adapter);
5977
5978	/* update SAN MAC vmdq pool selection */
5979	if (hw->mac.san_mac_rar_index)
5980		hw->mac.ops.set_vmdq_san_mac(hw, VMDQ_P(0));
5981
5982	if (test_bit(__IXGBE_PTP_RUNNING, &adapter->state))
5983		ixgbe_ptp_reset(adapter);
5984
5985	if (hw->phy.ops.set_phy_power) {
5986		if (!netif_running(adapter->netdev) && !adapter->wol)
5987			hw->phy.ops.set_phy_power(hw, false);
5988		else
5989			hw->phy.ops.set_phy_power(hw, true);
5990	}
5991}
5992
5993/**
5994 * ixgbe_clean_tx_ring - Free Tx Buffers
5995 * @tx_ring: ring to be cleaned
5996 **/
5997static void ixgbe_clean_tx_ring(struct ixgbe_ring *tx_ring)
5998{
5999	u16 i = tx_ring->next_to_clean;
6000	struct ixgbe_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i];
6001
6002	if (tx_ring->xsk_pool) {
6003		ixgbe_xsk_clean_tx_ring(tx_ring);
6004		goto out;
6005	}
6006
6007	while (i != tx_ring->next_to_use) {
6008		union ixgbe_adv_tx_desc *eop_desc, *tx_desc;
6009
6010		/* Free all the Tx ring sk_buffs */
6011		if (ring_is_xdp(tx_ring))
6012			xdp_return_frame(tx_buffer->xdpf);
6013		else
6014			dev_kfree_skb_any(tx_buffer->skb);
6015
6016		/* unmap skb header data */
6017		dma_unmap_single(tx_ring->dev,
6018				 dma_unmap_addr(tx_buffer, dma),
6019				 dma_unmap_len(tx_buffer, len),
6020				 DMA_TO_DEVICE);
6021
6022		/* check for eop_desc to determine the end of the packet */
6023		eop_desc = tx_buffer->next_to_watch;
6024		tx_desc = IXGBE_TX_DESC(tx_ring, i);
6025
6026		/* unmap remaining buffers */
6027		while (tx_desc != eop_desc) {
6028			tx_buffer++;
6029			tx_desc++;
6030			i++;
6031			if (unlikely(i == tx_ring->count)) {
6032				i = 0;
6033				tx_buffer = tx_ring->tx_buffer_info;
6034				tx_desc = IXGBE_TX_DESC(tx_ring, 0);
6035			}
6036
6037			/* unmap any remaining paged data */
6038			if (dma_unmap_len(tx_buffer, len))
6039				dma_unmap_page(tx_ring->dev,
6040					       dma_unmap_addr(tx_buffer, dma),
6041					       dma_unmap_len(tx_buffer, len),
6042					       DMA_TO_DEVICE);
6043		}
6044
6045		/* move us one more past the eop_desc for start of next pkt */
6046		tx_buffer++;
6047		i++;
6048		if (unlikely(i == tx_ring->count)) {
6049			i = 0;
6050			tx_buffer = tx_ring->tx_buffer_info;
6051		}
6052	}
6053
6054	/* reset BQL for queue */
6055	if (!ring_is_xdp(tx_ring))
6056		netdev_tx_reset_queue(txring_txq(tx_ring));
6057
6058out:
6059	/* reset next_to_use and next_to_clean */
6060	tx_ring->next_to_use = 0;
6061	tx_ring->next_to_clean = 0;
6062}
6063
6064/**
6065 * ixgbe_clean_all_rx_rings - Free Rx Buffers for all queues
6066 * @adapter: board private structure
6067 **/
6068static void ixgbe_clean_all_rx_rings(struct ixgbe_adapter *adapter)
6069{
6070	int i;
6071
6072	for (i = 0; i < adapter->num_rx_queues; i++)
6073		ixgbe_clean_rx_ring(adapter->rx_ring[i]);
6074}
6075
6076/**
6077 * ixgbe_clean_all_tx_rings - Free Tx Buffers for all queues
6078 * @adapter: board private structure
6079 **/
6080static void ixgbe_clean_all_tx_rings(struct ixgbe_adapter *adapter)
6081{
6082	int i;
6083
6084	for (i = 0; i < adapter->num_tx_queues; i++)
6085		ixgbe_clean_tx_ring(adapter->tx_ring[i]);
6086	for (i = 0; i < adapter->num_xdp_queues; i++)
6087		ixgbe_clean_tx_ring(adapter->xdp_ring[i]);
6088}
6089
6090static void ixgbe_fdir_filter_exit(struct ixgbe_adapter *adapter)
6091{
6092	struct hlist_node *node2;
6093	struct ixgbe_fdir_filter *filter;
6094
6095	spin_lock(&adapter->fdir_perfect_lock);
6096
6097	hlist_for_each_entry_safe(filter, node2,
6098				  &adapter->fdir_filter_list, fdir_node) {
6099		hlist_del(&filter->fdir_node);
6100		kfree(filter);
6101	}
6102	adapter->fdir_filter_count = 0;
6103
6104	spin_unlock(&adapter->fdir_perfect_lock);
6105}
6106
6107void ixgbe_down(struct ixgbe_adapter *adapter)
6108{
6109	struct net_device *netdev = adapter->netdev;
6110	struct ixgbe_hw *hw = &adapter->hw;
6111	int i;
6112
6113	/* signal that we are down to the interrupt handler */
6114	if (test_and_set_bit(__IXGBE_DOWN, &adapter->state))
6115		return; /* do nothing if already down */
6116
6117	/* Shut off incoming Tx traffic */
6118	netif_tx_stop_all_queues(netdev);
6119
6120	/* call carrier off first to avoid false dev_watchdog timeouts */
6121	netif_carrier_off(netdev);
6122	netif_tx_disable(netdev);
6123
6124	/* Disable Rx */
6125	ixgbe_disable_rx(adapter);
6126
6127	/* synchronize_rcu() needed for pending XDP buffers to drain */
6128	if (adapter->xdp_ring[0])
6129		synchronize_rcu();
6130
6131	ixgbe_irq_disable(adapter);
6132
6133	ixgbe_napi_disable_all(adapter);
6134
6135	clear_bit(__IXGBE_RESET_REQUESTED, &adapter->state);
6136	adapter->flags2 &= ~IXGBE_FLAG2_FDIR_REQUIRES_REINIT;
6137	adapter->flags &= ~IXGBE_FLAG_NEED_LINK_UPDATE;
6138
6139	del_timer_sync(&adapter->service_timer);
6140
6141	if (adapter->num_vfs) {
6142		/* Clear EITR Select mapping */
6143		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EITRSEL, 0);
6144
6145		/* Mark all the VFs as inactive */
6146		for (i = 0 ; i < adapter->num_vfs; i++)
6147			adapter->vfinfo[i].clear_to_send = false;
6148
6149		/* update setting rx tx for all active vfs */
6150		ixgbe_set_all_vfs(adapter);
6151	}
6152
6153	/* disable transmits in the hardware now that interrupts are off */
6154	ixgbe_disable_tx(adapter);
6155
6156	if (!pci_channel_offline(adapter->pdev))
6157		ixgbe_reset(adapter);
6158
6159	/* power down the optics for 82599 SFP+ fiber */
6160	if (hw->mac.ops.disable_tx_laser)
6161		hw->mac.ops.disable_tx_laser(hw);
6162
6163	ixgbe_clean_all_tx_rings(adapter);
6164	ixgbe_clean_all_rx_rings(adapter);
6165}
6166
6167/**
6168 * ixgbe_eee_capable - helper function to determine EEE support on X550
6169 * @adapter: board private structure
6170 */
6171static void ixgbe_set_eee_capable(struct ixgbe_adapter *adapter)
6172{
6173	struct ixgbe_hw *hw = &adapter->hw;
6174
6175	switch (hw->device_id) {
6176	case IXGBE_DEV_ID_X550EM_A_1G_T:
6177	case IXGBE_DEV_ID_X550EM_A_1G_T_L:
6178		if (!hw->phy.eee_speeds_supported)
6179			break;
6180		adapter->flags2 |= IXGBE_FLAG2_EEE_CAPABLE;
6181		if (!hw->phy.eee_speeds_advertised)
6182			break;
6183		adapter->flags2 |= IXGBE_FLAG2_EEE_ENABLED;
6184		break;
6185	default:
6186		adapter->flags2 &= ~IXGBE_FLAG2_EEE_CAPABLE;
6187		adapter->flags2 &= ~IXGBE_FLAG2_EEE_ENABLED;
6188		break;
6189	}
6190}
6191
6192/**
6193 * ixgbe_tx_timeout - Respond to a Tx Hang
6194 * @netdev: network interface device structure
6195 * @txqueue: queue number that timed out
6196 **/
6197static void ixgbe_tx_timeout(struct net_device *netdev, unsigned int __always_unused txqueue)
6198{
6199	struct ixgbe_adapter *adapter = netdev_priv(netdev);
6200
6201	/* Do the reset outside of interrupt context */
6202	ixgbe_tx_timeout_reset(adapter);
6203}
6204
6205#ifdef CONFIG_IXGBE_DCB
6206static void ixgbe_init_dcb(struct ixgbe_adapter *adapter)
6207{
6208	struct ixgbe_hw *hw = &adapter->hw;
6209	struct tc_configuration *tc;
6210	int j;
6211
6212	switch (hw->mac.type) {
6213	case ixgbe_mac_82598EB:
6214	case ixgbe_mac_82599EB:
6215		adapter->dcb_cfg.num_tcs.pg_tcs = MAX_TRAFFIC_CLASS;
6216		adapter->dcb_cfg.num_tcs.pfc_tcs = MAX_TRAFFIC_CLASS;
6217		break;
6218	case ixgbe_mac_X540:
6219	case ixgbe_mac_X550:
6220		adapter->dcb_cfg.num_tcs.pg_tcs = X540_TRAFFIC_CLASS;
6221		adapter->dcb_cfg.num_tcs.pfc_tcs = X540_TRAFFIC_CLASS;
6222		break;
6223	case ixgbe_mac_X550EM_x:
6224	case ixgbe_mac_x550em_a:
6225	default:
6226		adapter->dcb_cfg.num_tcs.pg_tcs = DEF_TRAFFIC_CLASS;
6227		adapter->dcb_cfg.num_tcs.pfc_tcs = DEF_TRAFFIC_CLASS;
6228		break;
6229	}
6230
6231	/* Configure DCB traffic classes */
6232	for (j = 0; j < MAX_TRAFFIC_CLASS; j++) {
6233		tc = &adapter->dcb_cfg.tc_config[j];
6234		tc->path[DCB_TX_CONFIG].bwg_id = 0;
6235		tc->path[DCB_TX_CONFIG].bwg_percent = 12 + (j & 1);
6236		tc->path[DCB_RX_CONFIG].bwg_id = 0;
6237		tc->path[DCB_RX_CONFIG].bwg_percent = 12 + (j & 1);
6238		tc->dcb_pfc = pfc_disabled;
6239	}
6240
6241	/* Initialize default user to priority mapping, UPx->TC0 */
6242	tc = &adapter->dcb_cfg.tc_config[0];
6243	tc->path[DCB_TX_CONFIG].up_to_tc_bitmap = 0xFF;
6244	tc->path[DCB_RX_CONFIG].up_to_tc_bitmap = 0xFF;
6245
6246	adapter->dcb_cfg.bw_percentage[DCB_TX_CONFIG][0] = 100;
6247	adapter->dcb_cfg.bw_percentage[DCB_RX_CONFIG][0] = 100;
6248	adapter->dcb_cfg.pfc_mode_enable = false;
6249	adapter->dcb_set_bitmap = 0x00;
6250	if (adapter->flags & IXGBE_FLAG_DCB_CAPABLE)
6251		adapter->dcbx_cap = DCB_CAP_DCBX_HOST | DCB_CAP_DCBX_VER_CEE;
6252	memcpy(&adapter->temp_dcb_cfg, &adapter->dcb_cfg,
6253	       sizeof(adapter->temp_dcb_cfg));
6254}
6255#endif
6256
6257/**
6258 * ixgbe_sw_init - Initialize general software structures (struct ixgbe_adapter)
6259 * @adapter: board private structure to initialize
6260 * @ii: pointer to ixgbe_info for device
6261 *
6262 * ixgbe_sw_init initializes the Adapter private data structure.
6263 * Fields are initialized based on PCI device information and
6264 * OS network device settings (MTU size).
6265 **/
6266static int ixgbe_sw_init(struct ixgbe_adapter *adapter,
6267			 const struct ixgbe_info *ii)
6268{
6269	struct ixgbe_hw *hw = &adapter->hw;
6270	struct pci_dev *pdev = adapter->pdev;
6271	unsigned int rss, fdir;
6272	u32 fwsm;
6273	int i;
6274
6275	/* PCI config space info */
6276
6277	hw->vendor_id = pdev->vendor;
6278	hw->device_id = pdev->device;
6279	hw->revision_id = pdev->revision;
6280	hw->subsystem_vendor_id = pdev->subsystem_vendor;
6281	hw->subsystem_device_id = pdev->subsystem_device;
6282
6283	/* get_invariants needs the device IDs */
6284	ii->get_invariants(hw);
6285
6286	/* Set common capability flags and settings */
6287	rss = min_t(int, ixgbe_max_rss_indices(adapter), num_online_cpus());
6288	adapter->ring_feature[RING_F_RSS].limit = rss;
6289	adapter->flags2 |= IXGBE_FLAG2_RSC_CAPABLE;
6290	adapter->max_q_vectors = MAX_Q_VECTORS_82599;
6291	adapter->atr_sample_rate = 20;
6292	fdir = min_t(int, IXGBE_MAX_FDIR_INDICES, num_online_cpus());
6293	adapter->ring_feature[RING_F_FDIR].limit = fdir;
6294	adapter->fdir_pballoc = IXGBE_FDIR_PBALLOC_64K;
6295	adapter->ring_feature[RING_F_VMDQ].limit = 1;
6296#ifdef CONFIG_IXGBE_DCA
6297	adapter->flags |= IXGBE_FLAG_DCA_CAPABLE;
6298#endif
6299#ifdef CONFIG_IXGBE_DCB
6300	adapter->flags |= IXGBE_FLAG_DCB_CAPABLE;
6301	adapter->flags &= ~IXGBE_FLAG_DCB_ENABLED;
6302#endif
6303#ifdef IXGBE_FCOE
6304	adapter->flags |= IXGBE_FLAG_FCOE_CAPABLE;
6305	adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED;
6306#ifdef CONFIG_IXGBE_DCB
6307	/* Default traffic class to use for FCoE */
6308	adapter->fcoe.up = IXGBE_FCOE_DEFTC;
6309#endif /* CONFIG_IXGBE_DCB */
6310#endif /* IXGBE_FCOE */
6311
6312	/* initialize static ixgbe jump table entries */
6313	adapter->jump_tables[0] = kzalloc(sizeof(*adapter->jump_tables[0]),
6314					  GFP_KERNEL);
6315	if (!adapter->jump_tables[0])
6316		return -ENOMEM;
6317	adapter->jump_tables[0]->mat = ixgbe_ipv4_fields;
6318
6319	for (i = 1; i < IXGBE_MAX_LINK_HANDLE; i++)
6320		adapter->jump_tables[i] = NULL;
6321
6322	adapter->mac_table = kcalloc(hw->mac.num_rar_entries,
6323				     sizeof(struct ixgbe_mac_addr),
6324				     GFP_KERNEL);
6325	if (!adapter->mac_table)
6326		return -ENOMEM;
6327
6328	if (ixgbe_init_rss_key(adapter))
6329		return -ENOMEM;
6330
6331	adapter->af_xdp_zc_qps = bitmap_zalloc(MAX_XDP_QUEUES, GFP_KERNEL);
6332	if (!adapter->af_xdp_zc_qps)
6333		return -ENOMEM;
6334
6335	/* Set MAC specific capability flags and exceptions */
6336	switch (hw->mac.type) {
6337	case ixgbe_mac_82598EB:
6338		adapter->flags2 &= ~IXGBE_FLAG2_RSC_CAPABLE;
6339
6340		if (hw->device_id == IXGBE_DEV_ID_82598AT)
6341			adapter->flags |= IXGBE_FLAG_FAN_FAIL_CAPABLE;
6342
6343		adapter->max_q_vectors = MAX_Q_VECTORS_82598;
6344		adapter->ring_feature[RING_F_FDIR].limit = 0;
6345		adapter->atr_sample_rate = 0;
6346		adapter->fdir_pballoc = 0;
6347#ifdef IXGBE_FCOE
6348		adapter->flags &= ~IXGBE_FLAG_FCOE_CAPABLE;
6349		adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED;
6350#ifdef CONFIG_IXGBE_DCB
6351		adapter->fcoe.up = 0;
6352#endif /* IXGBE_DCB */
6353#endif /* IXGBE_FCOE */
6354		break;
6355	case ixgbe_mac_82599EB:
6356		if (hw->device_id == IXGBE_DEV_ID_82599_T3_LOM)
6357			adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE;
6358		break;
6359	case ixgbe_mac_X540:
6360		fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw));
6361		if (fwsm & IXGBE_FWSM_TS_ENABLED)
6362			adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE;
6363		break;
6364	case ixgbe_mac_x550em_a:
6365		switch (hw->device_id) {
6366		case IXGBE_DEV_ID_X550EM_A_1G_T:
6367		case IXGBE_DEV_ID_X550EM_A_1G_T_L:
6368			adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE;
6369			break;
6370		default:
6371			break;
6372		}
6373		fallthrough;
6374	case ixgbe_mac_X550EM_x:
6375#ifdef CONFIG_IXGBE_DCB
6376		adapter->flags &= ~IXGBE_FLAG_DCB_CAPABLE;
6377#endif
6378#ifdef IXGBE_FCOE
6379		adapter->flags &= ~IXGBE_FLAG_FCOE_CAPABLE;
6380#ifdef CONFIG_IXGBE_DCB
6381		adapter->fcoe.up = 0;
6382#endif /* IXGBE_DCB */
6383#endif /* IXGBE_FCOE */
6384		fallthrough;
6385	case ixgbe_mac_X550:
6386		if (hw->mac.type == ixgbe_mac_X550)
6387			adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE;
6388#ifdef CONFIG_IXGBE_DCA
6389		adapter->flags &= ~IXGBE_FLAG_DCA_CAPABLE;
6390#endif
6391		break;
6392	default:
6393		break;
6394	}
6395
6396#ifdef IXGBE_FCOE
6397	/* FCoE support exists, always init the FCoE lock */
6398	spin_lock_init(&adapter->fcoe.lock);
6399
6400#endif
6401	/* n-tuple support exists, always init our spinlock */
6402	spin_lock_init(&adapter->fdir_perfect_lock);
6403
6404	/* init spinlock to avoid concurrency of VF resources */
6405	spin_lock_init(&adapter->vfs_lock);
6406
6407#ifdef CONFIG_IXGBE_DCB
6408	ixgbe_init_dcb(adapter);
6409#endif
6410	ixgbe_init_ipsec_offload(adapter);
6411
6412	/* default flow control settings */
6413	hw->fc.requested_mode = ixgbe_fc_full;
6414	hw->fc.current_mode = ixgbe_fc_full;	/* init for ethtool output */
6415	ixgbe_pbthresh_setup(adapter);
6416	hw->fc.pause_time = IXGBE_DEFAULT_FCPAUSE;
6417	hw->fc.send_xon = true;
6418	hw->fc.disable_fc_autoneg = ixgbe_device_supports_autoneg_fc(hw);
6419
6420#ifdef CONFIG_PCI_IOV
6421	if (max_vfs > 0)
6422		e_dev_warn("Enabling SR-IOV VFs using the max_vfs module parameter is deprecated - please use the pci sysfs interface instead.\n");
6423
6424	/* assign number of SR-IOV VFs */
6425	if (hw->mac.type != ixgbe_mac_82598EB) {
6426		if (max_vfs > IXGBE_MAX_VFS_DRV_LIMIT) {
6427			max_vfs = 0;
6428			e_dev_warn("max_vfs parameter out of range. Not assigning any SR-IOV VFs\n");
6429		}
6430	}
6431#endif /* CONFIG_PCI_IOV */
6432
6433	/* enable itr by default in dynamic mode */
6434	adapter->rx_itr_setting = 1;
6435	adapter->tx_itr_setting = 1;
6436
6437	/* set default ring sizes */
6438	adapter->tx_ring_count = IXGBE_DEFAULT_TXD;
6439	adapter->rx_ring_count = IXGBE_DEFAULT_RXD;
6440
6441	/* set default work limits */
6442	adapter->tx_work_limit = IXGBE_DEFAULT_TX_WORK;
6443
6444	/* initialize eeprom parameters */
6445	if (ixgbe_init_eeprom_params_generic(hw)) {
6446		e_dev_err("EEPROM initialization failed\n");
6447		return -EIO;
6448	}
6449
6450	/* PF holds first pool slot */
6451	set_bit(0, adapter->fwd_bitmask);
6452	set_bit(__IXGBE_DOWN, &adapter->state);
6453
6454	return 0;
6455}
6456
6457/**
6458 * ixgbe_setup_tx_resources - allocate Tx resources (Descriptors)
6459 * @tx_ring:    tx descriptor ring (for a specific queue) to setup
6460 *
6461 * Return 0 on success, negative on failure
6462 **/
6463int ixgbe_setup_tx_resources(struct ixgbe_ring *tx_ring)
6464{
6465	struct device *dev = tx_ring->dev;
6466	int orig_node = dev_to_node(dev);
6467	int ring_node = NUMA_NO_NODE;
6468	int size;
6469
6470	size = sizeof(struct ixgbe_tx_buffer) * tx_ring->count;
6471
6472	if (tx_ring->q_vector)
6473		ring_node = tx_ring->q_vector->numa_node;
6474
6475	tx_ring->tx_buffer_info = vmalloc_node(size, ring_node);
6476	if (!tx_ring->tx_buffer_info)
6477		tx_ring->tx_buffer_info = vmalloc(size);
6478	if (!tx_ring->tx_buffer_info)
6479		goto err;
6480
6481	/* round up to nearest 4K */
6482	tx_ring->size = tx_ring->count * sizeof(union ixgbe_adv_tx_desc);
6483	tx_ring->size = ALIGN(tx_ring->size, 4096);
6484
6485	set_dev_node(dev, ring_node);
6486	tx_ring->desc = dma_alloc_coherent(dev,
6487					   tx_ring->size,
6488					   &tx_ring->dma,
6489					   GFP_KERNEL);
6490	set_dev_node(dev, orig_node);
6491	if (!tx_ring->desc)
6492		tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size,
6493						   &tx_ring->dma, GFP_KERNEL);
6494	if (!tx_ring->desc)
6495		goto err;
6496
6497	tx_ring->next_to_use = 0;
6498	tx_ring->next_to_clean = 0;
6499	return 0;
6500
6501err:
6502	vfree(tx_ring->tx_buffer_info);
6503	tx_ring->tx_buffer_info = NULL;
6504	dev_err(dev, "Unable to allocate memory for the Tx descriptor ring\n");
6505	return -ENOMEM;
6506}
6507
6508/**
6509 * ixgbe_setup_all_tx_resources - allocate all queues Tx resources
6510 * @adapter: board private structure
6511 *
6512 * If this function returns with an error, then it's possible one or
6513 * more of the rings is populated (while the rest are not).  It is the
6514 * callers duty to clean those orphaned rings.
6515 *
6516 * Return 0 on success, negative on failure
6517 **/
6518static int ixgbe_setup_all_tx_resources(struct ixgbe_adapter *adapter)
6519{
6520	int i, j = 0, err = 0;
6521
6522	for (i = 0; i < adapter->num_tx_queues; i++) {
6523		err = ixgbe_setup_tx_resources(adapter->tx_ring[i]);
6524		if (!err)
6525			continue;
6526
6527		e_err(probe, "Allocation for Tx Queue %u failed\n", i);
6528		goto err_setup_tx;
6529	}
6530	for (j = 0; j < adapter->num_xdp_queues; j++) {
6531		err = ixgbe_setup_tx_resources(adapter->xdp_ring[j]);
6532		if (!err)
6533			continue;
6534
6535		e_err(probe, "Allocation for Tx Queue %u failed\n", j);
6536		goto err_setup_tx;
6537	}
6538
6539	return 0;
6540err_setup_tx:
6541	/* rewind the index freeing the rings as we go */
6542	while (j--)
6543		ixgbe_free_tx_resources(adapter->xdp_ring[j]);
6544	while (i--)
6545		ixgbe_free_tx_resources(adapter->tx_ring[i]);
6546	return err;
6547}
6548
6549/**
6550 * ixgbe_setup_rx_resources - allocate Rx resources (Descriptors)
6551 * @adapter: pointer to ixgbe_adapter
6552 * @rx_ring:    rx descriptor ring (for a specific queue) to setup
6553 *
6554 * Returns 0 on success, negative on failure
6555 **/
6556int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter,
6557			     struct ixgbe_ring *rx_ring)
6558{
6559	struct device *dev = rx_ring->dev;
6560	int orig_node = dev_to_node(dev);
6561	int ring_node = NUMA_NO_NODE;
6562	int size;
6563
6564	size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count;
6565
6566	if (rx_ring->q_vector)
6567		ring_node = rx_ring->q_vector->numa_node;
6568
6569	rx_ring->rx_buffer_info = vmalloc_node(size, ring_node);
6570	if (!rx_ring->rx_buffer_info)
6571		rx_ring->rx_buffer_info = vmalloc(size);
6572	if (!rx_ring->rx_buffer_info)
6573		goto err;
6574
6575	/* Round up to nearest 4K */
6576	rx_ring->size = rx_ring->count * sizeof(union ixgbe_adv_rx_desc);
6577	rx_ring->size = ALIGN(rx_ring->size, 4096);
6578
6579	set_dev_node(dev, ring_node);
6580	rx_ring->desc = dma_alloc_coherent(dev,
6581					   rx_ring->size,
6582					   &rx_ring->dma,
6583					   GFP_KERNEL);
6584	set_dev_node(dev, orig_node);
6585	if (!rx_ring->desc)
6586		rx_ring->desc = dma_alloc_coherent(dev, rx_ring->size,
6587						   &rx_ring->dma, GFP_KERNEL);
6588	if (!rx_ring->desc)
6589		goto err;
6590
6591	rx_ring->next_to_clean = 0;
6592	rx_ring->next_to_use = 0;
6593
6594	/* XDP RX-queue info */
6595	if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, adapter->netdev,
6596			     rx_ring->queue_index) < 0)
6597		goto err;
6598
6599	rx_ring->xdp_prog = adapter->xdp_prog;
6600
6601	return 0;
6602err:
6603	vfree(rx_ring->rx_buffer_info);
6604	rx_ring->rx_buffer_info = NULL;
6605	dev_err(dev, "Unable to allocate memory for the Rx descriptor ring\n");
6606	return -ENOMEM;
6607}
6608
6609/**
6610 * ixgbe_setup_all_rx_resources - allocate all queues Rx resources
6611 * @adapter: board private structure
6612 *
6613 * If this function returns with an error, then it's possible one or
6614 * more of the rings is populated (while the rest are not).  It is the
6615 * callers duty to clean those orphaned rings.
6616 *
6617 * Return 0 on success, negative on failure
6618 **/
6619static int ixgbe_setup_all_rx_resources(struct ixgbe_adapter *adapter)
6620{
6621	int i, err = 0;
6622
6623	for (i = 0; i < adapter->num_rx_queues; i++) {
6624		err = ixgbe_setup_rx_resources(adapter, adapter->rx_ring[i]);
6625		if (!err)
6626			continue;
6627
6628		e_err(probe, "Allocation for Rx Queue %u failed\n", i);
6629		goto err_setup_rx;
6630	}
6631
6632#ifdef IXGBE_FCOE
6633	err = ixgbe_setup_fcoe_ddp_resources(adapter);
6634	if (!err)
6635#endif
6636		return 0;
6637err_setup_rx:
6638	/* rewind the index freeing the rings as we go */
6639	while (i--)
6640		ixgbe_free_rx_resources(adapter->rx_ring[i]);
6641	return err;
6642}
6643
6644/**
6645 * ixgbe_free_tx_resources - Free Tx Resources per Queue
6646 * @tx_ring: Tx descriptor ring for a specific queue
6647 *
6648 * Free all transmit software resources
6649 **/
6650void ixgbe_free_tx_resources(struct ixgbe_ring *tx_ring)
6651{
6652	ixgbe_clean_tx_ring(tx_ring);
6653
6654	vfree(tx_ring->tx_buffer_info);
6655	tx_ring->tx_buffer_info = NULL;
6656
6657	/* if not set, then don't free */
6658	if (!tx_ring->desc)
6659		return;
6660
6661	dma_free_coherent(tx_ring->dev, tx_ring->size,
6662			  tx_ring->desc, tx_ring->dma);
6663
6664	tx_ring->desc = NULL;
6665}
6666
6667/**
6668 * ixgbe_free_all_tx_resources - Free Tx Resources for All Queues
6669 * @adapter: board private structure
6670 *
6671 * Free all transmit software resources
6672 **/
6673static void ixgbe_free_all_tx_resources(struct ixgbe_adapter *adapter)
6674{
6675	int i;
6676
6677	for (i = 0; i < adapter->num_tx_queues; i++)
6678		if (adapter->tx_ring[i]->desc)
6679			ixgbe_free_tx_resources(adapter->tx_ring[i]);
6680	for (i = 0; i < adapter->num_xdp_queues; i++)
6681		if (adapter->xdp_ring[i]->desc)
6682			ixgbe_free_tx_resources(adapter->xdp_ring[i]);
6683}
6684
6685/**
6686 * ixgbe_free_rx_resources - Free Rx Resources
6687 * @rx_ring: ring to clean the resources from
6688 *
6689 * Free all receive software resources
6690 **/
6691void ixgbe_free_rx_resources(struct ixgbe_ring *rx_ring)
6692{
6693	ixgbe_clean_rx_ring(rx_ring);
6694
6695	rx_ring->xdp_prog = NULL;
6696	xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
6697	vfree(rx_ring->rx_buffer_info);
6698	rx_ring->rx_buffer_info = NULL;
6699
6700	/* if not set, then don't free */
6701	if (!rx_ring->desc)
6702		return;
6703
6704	dma_free_coherent(rx_ring->dev, rx_ring->size,
6705			  rx_ring->desc, rx_ring->dma);
6706
6707	rx_ring->desc = NULL;
6708}
6709
6710/**
6711 * ixgbe_free_all_rx_resources - Free Rx Resources for All Queues
6712 * @adapter: board private structure
6713 *
6714 * Free all receive software resources
6715 **/
6716static void ixgbe_free_all_rx_resources(struct ixgbe_adapter *adapter)
6717{
6718	int i;
6719
6720#ifdef IXGBE_FCOE
6721	ixgbe_free_fcoe_ddp_resources(adapter);
6722
6723#endif
6724	for (i = 0; i < adapter->num_rx_queues; i++)
6725		if (adapter->rx_ring[i]->desc)
6726			ixgbe_free_rx_resources(adapter->rx_ring[i]);
6727}
6728
6729/**
6730 * ixgbe_max_xdp_frame_size - returns the maximum allowed frame size for XDP
6731 * @adapter: device handle, pointer to adapter
6732 */
6733static int ixgbe_max_xdp_frame_size(struct ixgbe_adapter *adapter)
6734{
6735	if (PAGE_SIZE >= 8192 || adapter->flags2 & IXGBE_FLAG2_RX_LEGACY)
6736		return IXGBE_RXBUFFER_2K;
6737	else
6738		return IXGBE_RXBUFFER_3K;
6739}
6740
6741/**
6742 * ixgbe_change_mtu - Change the Maximum Transfer Unit
6743 * @netdev: network interface device structure
6744 * @new_mtu: new value for maximum frame size
6745 *
6746 * Returns 0 on success, negative on failure
6747 **/
6748static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu)
6749{
6750	struct ixgbe_adapter *adapter = netdev_priv(netdev);
6751
6752	if (ixgbe_enabled_xdp_adapter(adapter)) {
6753		int new_frame_size = new_mtu + IXGBE_PKT_HDR_PAD;
6754
6755		if (new_frame_size > ixgbe_max_xdp_frame_size(adapter)) {
6756			e_warn(probe, "Requested MTU size is not supported with XDP\n");
6757			return -EINVAL;
6758		}
6759	}
6760
6761	/*
6762	 * For 82599EB we cannot allow legacy VFs to enable their receive
6763	 * paths when MTU greater than 1500 is configured.  So display a
6764	 * warning that legacy VFs will be disabled.
6765	 */
6766	if ((adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) &&
6767	    (adapter->hw.mac.type == ixgbe_mac_82599EB) &&
6768	    (new_mtu > ETH_DATA_LEN))
6769		e_warn(probe, "Setting MTU > 1500 will disable legacy VFs\n");
6770
6771	netdev_dbg(netdev, "changing MTU from %d to %d\n",
6772		   netdev->mtu, new_mtu);
6773
6774	/* must set new MTU before calling down or up */
6775	netdev->mtu = new_mtu;
6776
6777	if (netif_running(netdev))
6778		ixgbe_reinit_locked(adapter);
6779
6780	return 0;
6781}
6782
6783/**
6784 * ixgbe_open - Called when a network interface is made active
6785 * @netdev: network interface device structure
6786 *
6787 * Returns 0 on success, negative value on failure
6788 *
6789 * The open entry point is called when a network interface is made
6790 * active by the system (IFF_UP).  At this point all resources needed
6791 * for transmit and receive operations are allocated, the interrupt
6792 * handler is registered with the OS, the watchdog timer is started,
6793 * and the stack is notified that the interface is ready.
6794 **/
6795int ixgbe_open(struct net_device *netdev)
6796{
6797	struct ixgbe_adapter *adapter = netdev_priv(netdev);
6798	struct ixgbe_hw *hw = &adapter->hw;
6799	int err, queues;
6800
6801	/* disallow open during test */
6802	if (test_bit(__IXGBE_TESTING, &adapter->state))
6803		return -EBUSY;
6804
6805	netif_carrier_off(netdev);
6806
6807	/* allocate transmit descriptors */
6808	err = ixgbe_setup_all_tx_resources(adapter);
6809	if (err)
6810		goto err_setup_tx;
6811
6812	/* allocate receive descriptors */
6813	err = ixgbe_setup_all_rx_resources(adapter);
6814	if (err)
6815		goto err_setup_rx;
6816
6817	ixgbe_configure(adapter);
6818
6819	err = ixgbe_request_irq(adapter);
6820	if (err)
6821		goto err_req_irq;
6822
6823	/* Notify the stack of the actual queue counts. */
6824	queues = adapter->num_tx_queues;
6825	err = netif_set_real_num_tx_queues(netdev, queues);
6826	if (err)
6827		goto err_set_queues;
6828
6829	queues = adapter->num_rx_queues;
6830	err = netif_set_real_num_rx_queues(netdev, queues);
6831	if (err)
6832		goto err_set_queues;
6833
6834	ixgbe_ptp_init(adapter);
6835
6836	ixgbe_up_complete(adapter);
6837
6838	udp_tunnel_nic_reset_ntf(netdev);
6839
6840	return 0;
6841
6842err_set_queues:
6843	ixgbe_free_irq(adapter);
6844err_req_irq:
6845	ixgbe_free_all_rx_resources(adapter);
6846	if (hw->phy.ops.set_phy_power && !adapter->wol)
6847		hw->phy.ops.set_phy_power(&adapter->hw, false);
6848err_setup_rx:
6849	ixgbe_free_all_tx_resources(adapter);
6850err_setup_tx:
6851	ixgbe_reset(adapter);
6852
6853	return err;
6854}
6855
6856static void ixgbe_close_suspend(struct ixgbe_adapter *adapter)
6857{
6858	ixgbe_ptp_suspend(adapter);
6859
6860	if (adapter->hw.phy.ops.enter_lplu) {
6861		adapter->hw.phy.reset_disable = true;
6862		ixgbe_down(adapter);
6863		adapter->hw.phy.ops.enter_lplu(&adapter->hw);
6864		adapter->hw.phy.reset_disable = false;
6865	} else {
6866		ixgbe_down(adapter);
6867	}
6868
6869	ixgbe_free_irq(adapter);
6870
6871	ixgbe_free_all_tx_resources(adapter);
6872	ixgbe_free_all_rx_resources(adapter);
6873}
6874
6875/**
6876 * ixgbe_close - Disables a network interface
6877 * @netdev: network interface device structure
6878 *
6879 * Returns 0, this is not allowed to fail
6880 *
6881 * The close entry point is called when an interface is de-activated
6882 * by the OS.  The hardware is still under the drivers control, but
6883 * needs to be disabled.  A global MAC reset is issued to stop the
6884 * hardware, and all transmit and receive resources are freed.
6885 **/
6886int ixgbe_close(struct net_device *netdev)
6887{
6888	struct ixgbe_adapter *adapter = netdev_priv(netdev);
6889
6890	ixgbe_ptp_stop(adapter);
6891
6892	if (netif_device_present(netdev))
6893		ixgbe_close_suspend(adapter);
6894
6895	ixgbe_fdir_filter_exit(adapter);
6896
6897	ixgbe_release_hw_control(adapter);
6898
6899	return 0;
6900}
6901
6902static int __maybe_unused ixgbe_resume(struct device *dev_d)
6903{
6904	struct pci_dev *pdev = to_pci_dev(dev_d);
6905	struct ixgbe_adapter *adapter = pci_get_drvdata(pdev);
6906	struct net_device *netdev = adapter->netdev;
6907	u32 err;
6908
6909	adapter->hw.hw_addr = adapter->io_addr;
6910
6911	err = pci_enable_device_mem(pdev);
6912	if (err) {
6913		e_dev_err("Cannot enable PCI device from suspend\n");
6914		return err;
6915	}
6916	smp_mb__before_atomic();
6917	clear_bit(__IXGBE_DISABLED, &adapter->state);
6918	pci_set_master(pdev);
6919
6920	device_wakeup_disable(dev_d);
6921
6922	ixgbe_reset(adapter);
6923
6924	IXGBE_WRITE_REG(&adapter->hw, IXGBE_WUS, ~0);
6925
6926	rtnl_lock();
6927	err = ixgbe_init_interrupt_scheme(adapter);
6928	if (!err && netif_running(netdev))
6929		err = ixgbe_open(netdev);
6930
6931
6932	if (!err)
6933		netif_device_attach(netdev);
6934	rtnl_unlock();
6935
6936	return err;
6937}
6938
6939static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake)
6940{
6941	struct ixgbe_adapter *adapter = pci_get_drvdata(pdev);
6942	struct net_device *netdev = adapter->netdev;
6943	struct ixgbe_hw *hw = &adapter->hw;
6944	u32 ctrl;
6945	u32 wufc = adapter->wol;
6946
6947	rtnl_lock();
6948	netif_device_detach(netdev);
6949
6950	if (netif_running(netdev))
6951		ixgbe_close_suspend(adapter);
6952
6953	ixgbe_clear_interrupt_scheme(adapter);
6954	rtnl_unlock();
6955
6956	if (hw->mac.ops.stop_link_on_d3)
6957		hw->mac.ops.stop_link_on_d3(hw);
6958
6959	if (wufc) {
6960		u32 fctrl;
6961
6962		ixgbe_set_rx_mode(netdev);
6963
6964		/* enable the optics for 82599 SFP+ fiber as we can WoL */
6965		if (hw->mac.ops.enable_tx_laser)
6966			hw->mac.ops.enable_tx_laser(hw);
6967
6968		/* enable the reception of multicast packets */
6969		fctrl = IXGBE_READ_REG(hw, IXGBE_FCTRL);
6970		fctrl |= IXGBE_FCTRL_MPE;
6971		IXGBE_WRITE_REG(hw, IXGBE_FCTRL, fctrl);
6972
6973		ctrl = IXGBE_READ_REG(hw, IXGBE_CTRL);
6974		ctrl |= IXGBE_CTRL_GIO_DIS;
6975		IXGBE_WRITE_REG(hw, IXGBE_CTRL, ctrl);
6976
6977		IXGBE_WRITE_REG(hw, IXGBE_WUFC, wufc);
6978	} else {
6979		IXGBE_WRITE_REG(hw, IXGBE_WUC, 0);
6980		IXGBE_WRITE_REG(hw, IXGBE_WUFC, 0);
6981	}
6982
6983	switch (hw->mac.type) {
6984	case ixgbe_mac_82598EB:
6985		pci_wake_from_d3(pdev, false);
6986		break;
6987	case ixgbe_mac_82599EB:
6988	case ixgbe_mac_X540:
6989	case ixgbe_mac_X550:
6990	case ixgbe_mac_X550EM_x:
6991	case ixgbe_mac_x550em_a:
6992		pci_wake_from_d3(pdev, !!wufc);
6993		break;
6994	default:
6995		break;
6996	}
6997
6998	*enable_wake = !!wufc;
6999	if (hw->phy.ops.set_phy_power && !*enable_wake)
7000		hw->phy.ops.set_phy_power(hw, false);
7001
7002	ixgbe_release_hw_control(adapter);
7003
7004	if (!test_and_set_bit(__IXGBE_DISABLED, &adapter->state))
7005		pci_disable_device(pdev);
7006
7007	return 0;
7008}
7009
7010static int __maybe_unused ixgbe_suspend(struct device *dev_d)
7011{
7012	struct pci_dev *pdev = to_pci_dev(dev_d);
7013	int retval;
7014	bool wake;
7015
7016	retval = __ixgbe_shutdown(pdev, &wake);
7017
7018	device_set_wakeup_enable(dev_d, wake);
7019
7020	return retval;
7021}
7022
7023static void ixgbe_shutdown(struct pci_dev *pdev)
7024{
7025	bool wake;
7026
7027	__ixgbe_shutdown(pdev, &wake);
7028
7029	if (system_state == SYSTEM_POWER_OFF) {
7030		pci_wake_from_d3(pdev, wake);
7031		pci_set_power_state(pdev, PCI_D3hot);
7032	}
7033}
7034
7035/**
7036 * ixgbe_update_stats - Update the board statistics counters.
7037 * @adapter: board private structure
7038 **/
7039void ixgbe_update_stats(struct ixgbe_adapter *adapter)
7040{
7041	struct net_device *netdev = adapter->netdev;
7042	struct ixgbe_hw *hw = &adapter->hw;
7043	struct ixgbe_hw_stats *hwstats = &adapter->stats;
7044	u64 total_mpc = 0;
7045	u32 i, missed_rx = 0, mpc, bprc, lxon, lxoff, xon_off_tot;
7046	u64 non_eop_descs = 0, restart_queue = 0, tx_busy = 0;
7047	u64 alloc_rx_page_failed = 0, alloc_rx_buff_failed = 0;
7048	u64 alloc_rx_page = 0;
7049	u64 bytes = 0, packets = 0, hw_csum_rx_error = 0;
7050
7051	if (test_bit(__IXGBE_DOWN, &adapter->state) ||
7052	    test_bit(__IXGBE_RESETTING, &adapter->state))
7053		return;
7054
7055	if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) {
7056		u64 rsc_count = 0;
7057		u64 rsc_flush = 0;
7058		for (i = 0; i < adapter->num_rx_queues; i++) {
7059			rsc_count += adapter->rx_ring[i]->rx_stats.rsc_count;
7060			rsc_flush += adapter->rx_ring[i]->rx_stats.rsc_flush;
7061		}
7062		adapter->rsc_total_count = rsc_count;
7063		adapter->rsc_total_flush = rsc_flush;
7064	}
7065
7066	for (i = 0; i < adapter->num_rx_queues; i++) {
7067		struct ixgbe_ring *rx_ring = READ_ONCE(adapter->rx_ring[i]);
7068
7069		if (!rx_ring)
7070			continue;
7071		non_eop_descs += rx_ring->rx_stats.non_eop_descs;
7072		alloc_rx_page += rx_ring->rx_stats.alloc_rx_page;
7073		alloc_rx_page_failed += rx_ring->rx_stats.alloc_rx_page_failed;
7074		alloc_rx_buff_failed += rx_ring->rx_stats.alloc_rx_buff_failed;
7075		hw_csum_rx_error += rx_ring->rx_stats.csum_err;
7076		bytes += rx_ring->stats.bytes;
7077		packets += rx_ring->stats.packets;
7078	}
7079	adapter->non_eop_descs = non_eop_descs;
7080	adapter->alloc_rx_page = alloc_rx_page;
7081	adapter->alloc_rx_page_failed = alloc_rx_page_failed;
7082	adapter->alloc_rx_buff_failed = alloc_rx_buff_failed;
7083	adapter->hw_csum_rx_error = hw_csum_rx_error;
7084	netdev->stats.rx_bytes = bytes;
7085	netdev->stats.rx_packets = packets;
7086
7087	bytes = 0;
7088	packets = 0;
7089	/* gather some stats to the adapter struct that are per queue */
7090	for (i = 0; i < adapter->num_tx_queues; i++) {
7091		struct ixgbe_ring *tx_ring = READ_ONCE(adapter->tx_ring[i]);
7092
7093		if (!tx_ring)
7094			continue;
7095		restart_queue += tx_ring->tx_stats.restart_queue;
7096		tx_busy += tx_ring->tx_stats.tx_busy;
7097		bytes += tx_ring->stats.bytes;
7098		packets += tx_ring->stats.packets;
7099	}
7100	for (i = 0; i < adapter->num_xdp_queues; i++) {
7101		struct ixgbe_ring *xdp_ring = READ_ONCE(adapter->xdp_ring[i]);
7102
7103		if (!xdp_ring)
7104			continue;
7105		restart_queue += xdp_ring->tx_stats.restart_queue;
7106		tx_busy += xdp_ring->tx_stats.tx_busy;
7107		bytes += xdp_ring->stats.bytes;
7108		packets += xdp_ring->stats.packets;
7109	}
7110	adapter->restart_queue = restart_queue;
7111	adapter->tx_busy = tx_busy;
7112	netdev->stats.tx_bytes = bytes;
7113	netdev->stats.tx_packets = packets;
7114
7115	hwstats->crcerrs += IXGBE_READ_REG(hw, IXGBE_CRCERRS);
7116
7117	/* 8 register reads */
7118	for (i = 0; i < 8; i++) {
7119		/* for packet buffers not used, the register should read 0 */
7120		mpc = IXGBE_READ_REG(hw, IXGBE_MPC(i));
7121		missed_rx += mpc;
7122		hwstats->mpc[i] += mpc;
7123		total_mpc += hwstats->mpc[i];
7124		hwstats->pxontxc[i] += IXGBE_READ_REG(hw, IXGBE_PXONTXC(i));
7125		hwstats->pxofftxc[i] += IXGBE_READ_REG(hw, IXGBE_PXOFFTXC(i));
7126		switch (hw->mac.type) {
7127		case ixgbe_mac_82598EB:
7128			hwstats->rnbc[i] += IXGBE_READ_REG(hw, IXGBE_RNBC(i));
7129			hwstats->qbtc[i] += IXGBE_READ_REG(hw, IXGBE_QBTC(i));
7130			hwstats->qbrc[i] += IXGBE_READ_REG(hw, IXGBE_QBRC(i));
7131			hwstats->pxonrxc[i] +=
7132				IXGBE_READ_REG(hw, IXGBE_PXONRXC(i));
7133			break;
7134		case ixgbe_mac_82599EB:
7135		case ixgbe_mac_X540:
7136		case ixgbe_mac_X550:
7137		case ixgbe_mac_X550EM_x:
7138		case ixgbe_mac_x550em_a:
7139			hwstats->pxonrxc[i] +=
7140				IXGBE_READ_REG(hw, IXGBE_PXONRXCNT(i));
7141			break;
7142		default:
7143			break;
7144		}
7145	}
7146
7147	/*16 register reads */
7148	for (i = 0; i < 16; i++) {
7149		hwstats->qptc[i] += IXGBE_READ_REG(hw, IXGBE_QPTC(i));
7150		hwstats->qprc[i] += IXGBE_READ_REG(hw, IXGBE_QPRC(i));
7151		if ((hw->mac.type == ixgbe_mac_82599EB) ||
7152		    (hw->mac.type == ixgbe_mac_X540) ||
7153		    (hw->mac.type == ixgbe_mac_X550) ||
7154		    (hw->mac.type == ixgbe_mac_X550EM_x) ||
7155		    (hw->mac.type == ixgbe_mac_x550em_a)) {
7156			hwstats->qbtc[i] += IXGBE_READ_REG(hw, IXGBE_QBTC_L(i));
7157			IXGBE_READ_REG(hw, IXGBE_QBTC_H(i)); /* to clear */
7158			hwstats->qbrc[i] += IXGBE_READ_REG(hw, IXGBE_QBRC_L(i));
7159			IXGBE_READ_REG(hw, IXGBE_QBRC_H(i)); /* to clear */
7160		}
7161	}
7162
7163	hwstats->gprc += IXGBE_READ_REG(hw, IXGBE_GPRC);
7164	/* work around hardware counting issue */
7165	hwstats->gprc -= missed_rx;
7166
7167	ixgbe_update_xoff_received(adapter);
7168
7169	/* 82598 hardware only has a 32 bit counter in the high register */
7170	switch (hw->mac.type) {
7171	case ixgbe_mac_82598EB:
7172		hwstats->lxonrxc += IXGBE_READ_REG(hw, IXGBE_LXONRXC);
7173		hwstats->gorc += IXGBE_READ_REG(hw, IXGBE_GORCH);
7174		hwstats->gotc += IXGBE_READ_REG(hw, IXGBE_GOTCH);
7175		hwstats->tor += IXGBE_READ_REG(hw, IXGBE_TORH);
7176		break;
7177	case ixgbe_mac_X540:
7178	case ixgbe_mac_X550:
7179	case ixgbe_mac_X550EM_x:
7180	case ixgbe_mac_x550em_a:
7181		/* OS2BMC stats are X540 and later */
7182		hwstats->o2bgptc += IXGBE_READ_REG(hw, IXGBE_O2BGPTC);
7183		hwstats->o2bspc += IXGBE_READ_REG(hw, IXGBE_O2BSPC);
7184		hwstats->b2ospc += IXGBE_READ_REG(hw, IXGBE_B2OSPC);
7185		hwstats->b2ogprc += IXGBE_READ_REG(hw, IXGBE_B2OGPRC);
7186		fallthrough;
7187	case ixgbe_mac_82599EB:
7188		for (i = 0; i < 16; i++)
7189			adapter->hw_rx_no_dma_resources +=
7190					     IXGBE_READ_REG(hw, IXGBE_QPRDC(i));
7191		hwstats->gorc += IXGBE_READ_REG(hw, IXGBE_GORCL);
7192		IXGBE_READ_REG(hw, IXGBE_GORCH); /* to clear */
7193		hwstats->gotc += IXGBE_READ_REG(hw, IXGBE_GOTCL);
7194		IXGBE_READ_REG(hw, IXGBE_GOTCH); /* to clear */
7195		hwstats->tor += IXGBE_READ_REG(hw, IXGBE_TORL);
7196		IXGBE_READ_REG(hw, IXGBE_TORH); /* to clear */
7197		hwstats->lxonrxc += IXGBE_READ_REG(hw, IXGBE_LXONRXCNT);
7198		hwstats->fdirmatch += IXGBE_READ_REG(hw, IXGBE_FDIRMATCH);
7199		hwstats->fdirmiss += IXGBE_READ_REG(hw, IXGBE_FDIRMISS);
7200#ifdef IXGBE_FCOE
7201		hwstats->fccrc += IXGBE_READ_REG(hw, IXGBE_FCCRC);
7202		hwstats->fcoerpdc += IXGBE_READ_REG(hw, IXGBE_FCOERPDC);
7203		hwstats->fcoeprc += IXGBE_READ_REG(hw, IXGBE_FCOEPRC);
7204		hwstats->fcoeptc += IXGBE_READ_REG(hw, IXGBE_FCOEPTC);
7205		hwstats->fcoedwrc += IXGBE_READ_REG(hw, IXGBE_FCOEDWRC);
7206		hwstats->fcoedwtc += IXGBE_READ_REG(hw, IXGBE_FCOEDWTC);
7207		/* Add up per cpu counters for total ddp aloc fail */
7208		if (adapter->fcoe.ddp_pool) {
7209			struct ixgbe_fcoe *fcoe = &adapter->fcoe;
7210			struct ixgbe_fcoe_ddp_pool *ddp_pool;
7211			unsigned int cpu;
7212			u64 noddp = 0, noddp_ext_buff = 0;
7213			for_each_possible_cpu(cpu) {
7214				ddp_pool = per_cpu_ptr(fcoe->ddp_pool, cpu);
7215				noddp += ddp_pool->noddp;
7216				noddp_ext_buff += ddp_pool->noddp_ext_buff;
7217			}
7218			hwstats->fcoe_noddp = noddp;
7219			hwstats->fcoe_noddp_ext_buff = noddp_ext_buff;
7220		}
7221#endif /* IXGBE_FCOE */
7222		break;
7223	default:
7224		break;
7225	}
7226	bprc = IXGBE_READ_REG(hw, IXGBE_BPRC);
7227	hwstats->bprc += bprc;
7228	hwstats->mprc += IXGBE_READ_REG(hw, IXGBE_MPRC);
7229	if (hw->mac.type == ixgbe_mac_82598EB)
7230		hwstats->mprc -= bprc;
7231	hwstats->roc += IXGBE_READ_REG(hw, IXGBE_ROC);
7232	hwstats->prc64 += IXGBE_READ_REG(hw, IXGBE_PRC64);
7233	hwstats->prc127 += IXGBE_READ_REG(hw, IXGBE_PRC127);
7234	hwstats->prc255 += IXGBE_READ_REG(hw, IXGBE_PRC255);
7235	hwstats->prc511 += IXGBE_READ_REG(hw, IXGBE_PRC511);
7236	hwstats->prc1023 += IXGBE_READ_REG(hw, IXGBE_PRC1023);
7237	hwstats->prc1522 += IXGBE_READ_REG(hw, IXGBE_PRC1522);
7238	hwstats->rlec += IXGBE_READ_REG(hw, IXGBE_RLEC);
7239	lxon = IXGBE_READ_REG(hw, IXGBE_LXONTXC);
7240	hwstats->lxontxc += lxon;
7241	lxoff = IXGBE_READ_REG(hw, IXGBE_LXOFFTXC);
7242	hwstats->lxofftxc += lxoff;
7243	hwstats->gptc += IXGBE_READ_REG(hw, IXGBE_GPTC);
7244	hwstats->mptc += IXGBE_READ_REG(hw, IXGBE_MPTC);
7245	/*
7246	 * 82598 errata - tx of flow control packets is included in tx counters
7247	 */
7248	xon_off_tot = lxon + lxoff;
7249	hwstats->gptc -= xon_off_tot;
7250	hwstats->mptc -= xon_off_tot;
7251	hwstats->gotc -= (xon_off_tot * (ETH_ZLEN + ETH_FCS_LEN));
7252	hwstats->ruc += IXGBE_READ_REG(hw, IXGBE_RUC);
7253	hwstats->rfc += IXGBE_READ_REG(hw, IXGBE_RFC);
7254	hwstats->rjc += IXGBE_READ_REG(hw, IXGBE_RJC);
7255	hwstats->tpr += IXGBE_READ_REG(hw, IXGBE_TPR);
7256	hwstats->ptc64 += IXGBE_READ_REG(hw, IXGBE_PTC64);
7257	hwstats->ptc64 -= xon_off_tot;
7258	hwstats->ptc127 += IXGBE_READ_REG(hw, IXGBE_PTC127);
7259	hwstats->ptc255 += IXGBE_READ_REG(hw, IXGBE_PTC255);
7260	hwstats->ptc511 += IXGBE_READ_REG(hw, IXGBE_PTC511);
7261	hwstats->ptc1023 += IXGBE_READ_REG(hw, IXGBE_PTC1023);
7262	hwstats->ptc1522 += IXGBE_READ_REG(hw, IXGBE_PTC1522);
7263	hwstats->bptc += IXGBE_READ_REG(hw, IXGBE_BPTC);
7264
7265	/* Fill out the OS statistics structure */
7266	netdev->stats.multicast = hwstats->mprc;
7267
7268	/* Rx Errors */
7269	netdev->stats.rx_errors = hwstats->crcerrs + hwstats->rlec;
7270	netdev->stats.rx_dropped = 0;
7271	netdev->stats.rx_length_errors = hwstats->rlec;
7272	netdev->stats.rx_crc_errors = hwstats->crcerrs;
7273	netdev->stats.rx_missed_errors = total_mpc;
7274}
7275
7276/**
7277 * ixgbe_fdir_reinit_subtask - worker thread to reinit FDIR filter table
7278 * @adapter: pointer to the device adapter structure
7279 **/
7280static void ixgbe_fdir_reinit_subtask(struct ixgbe_adapter *adapter)
7281{
7282	struct ixgbe_hw *hw = &adapter->hw;
7283	int i;
7284
7285	if (!(adapter->flags2 & IXGBE_FLAG2_FDIR_REQUIRES_REINIT))
7286		return;
7287
7288	adapter->flags2 &= ~IXGBE_FLAG2_FDIR_REQUIRES_REINIT;
7289
7290	/* if interface is down do nothing */
7291	if (test_bit(__IXGBE_DOWN, &adapter->state))
7292		return;
7293
7294	/* do nothing if we are not using signature filters */
7295	if (!(adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE))
7296		return;
7297
7298	adapter->fdir_overflow++;
7299
7300	if (ixgbe_reinit_fdir_tables_82599(hw) == 0) {
7301		for (i = 0; i < adapter->num_tx_queues; i++)
7302			set_bit(__IXGBE_TX_FDIR_INIT_DONE,
7303				&(adapter->tx_ring[i]->state));
7304		for (i = 0; i < adapter->num_xdp_queues; i++)
7305			set_bit(__IXGBE_TX_FDIR_INIT_DONE,
7306				&adapter->xdp_ring[i]->state);
7307		/* re-enable flow director interrupts */
7308		IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMS_FLOW_DIR);
7309	} else {
7310		e_err(probe, "failed to finish FDIR re-initialization, "
7311		      "ignored adding FDIR ATR filters\n");
7312	}
7313}
7314
7315/**
7316 * ixgbe_check_hang_subtask - check for hung queues and dropped interrupts
7317 * @adapter: pointer to the device adapter structure
7318 *
7319 * This function serves two purposes.  First it strobes the interrupt lines
7320 * in order to make certain interrupts are occurring.  Secondly it sets the
7321 * bits needed to check for TX hangs.  As a result we should immediately
7322 * determine if a hang has occurred.
7323 */
7324static void ixgbe_check_hang_subtask(struct ixgbe_adapter *adapter)
7325{
7326	struct ixgbe_hw *hw = &adapter->hw;
7327	u64 eics = 0;
7328	int i;
7329
7330	/* If we're down, removing or resetting, just bail */
7331	if (test_bit(__IXGBE_DOWN, &adapter->state) ||
7332	    test_bit(__IXGBE_REMOVING, &adapter->state) ||
7333	    test_bit(__IXGBE_RESETTING, &adapter->state))
7334		return;
7335
7336	/* Force detection of hung controller */
7337	if (netif_carrier_ok(adapter->netdev)) {
7338		for (i = 0; i < adapter->num_tx_queues; i++)
7339			set_check_for_tx_hang(adapter->tx_ring[i]);
7340		for (i = 0; i < adapter->num_xdp_queues; i++)
7341			set_check_for_tx_hang(adapter->xdp_ring[i]);
7342	}
7343
7344	if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) {
7345		/*
7346		 * for legacy and MSI interrupts don't set any bits
7347		 * that are enabled for EIAM, because this operation
7348		 * would set *both* EIMS and EICS for any bit in EIAM
7349		 */
7350		IXGBE_WRITE_REG(hw, IXGBE_EICS,
7351			(IXGBE_EICS_TCP_TIMER | IXGBE_EICS_OTHER));
7352	} else {
7353		/* get one bit for every active tx/rx interrupt vector */
7354		for (i = 0; i < adapter->num_q_vectors; i++) {
7355			struct ixgbe_q_vector *qv = adapter->q_vector[i];
7356			if (qv->rx.ring || qv->tx.ring)
7357				eics |= BIT_ULL(i);
7358		}
7359	}
7360
7361	/* Cause software interrupt to ensure rings are cleaned */
7362	ixgbe_irq_rearm_queues(adapter, eics);
7363}
7364
7365/**
7366 * ixgbe_watchdog_update_link - update the link status
7367 * @adapter: pointer to the device adapter structure
7368 **/
7369static void ixgbe_watchdog_update_link(struct ixgbe_adapter *adapter)
7370{
7371	struct ixgbe_hw *hw = &adapter->hw;
7372	u32 link_speed = adapter->link_speed;
7373	bool link_up = adapter->link_up;
7374	bool pfc_en = adapter->dcb_cfg.pfc_mode_enable;
7375
7376	if (!(adapter->flags & IXGBE_FLAG_NEED_LINK_UPDATE))
7377		return;
7378
7379	if (hw->mac.ops.check_link) {
7380		hw->mac.ops.check_link(hw, &link_speed, &link_up, false);
7381	} else {
7382		/* always assume link is up, if no check link function */
7383		link_speed = IXGBE_LINK_SPEED_10GB_FULL;
7384		link_up = true;
7385	}
7386
7387	if (adapter->ixgbe_ieee_pfc)
7388		pfc_en |= !!(adapter->ixgbe_ieee_pfc->pfc_en);
7389
7390	if (link_up && !((adapter->flags & IXGBE_FLAG_DCB_ENABLED) && pfc_en)) {
7391		hw->mac.ops.fc_enable(hw);
7392		ixgbe_set_rx_drop_en(adapter);
7393	}
7394
7395	if (link_up ||
7396	    time_after(jiffies, (adapter->link_check_timeout +
7397				 IXGBE_TRY_LINK_TIMEOUT))) {
7398		adapter->flags &= ~IXGBE_FLAG_NEED_LINK_UPDATE;
7399		IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMC_LSC);
7400		IXGBE_WRITE_FLUSH(hw);
7401	}
7402
7403	adapter->link_up = link_up;
7404	adapter->link_speed = link_speed;
7405}
7406
7407static void ixgbe_update_default_up(struct ixgbe_adapter *adapter)
7408{
7409#ifdef CONFIG_IXGBE_DCB
7410	struct net_device *netdev = adapter->netdev;
7411	struct dcb_app app = {
7412			      .selector = IEEE_8021QAZ_APP_SEL_ETHERTYPE,
7413			      .protocol = 0,
7414			     };
7415	u8 up = 0;
7416
7417	if (adapter->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)
7418		up = dcb_ieee_getapp_mask(netdev, &app);
7419
7420	adapter->default_up = (up > 1) ? (ffs(up) - 1) : 0;
7421#endif
7422}
7423
7424/**
7425 * ixgbe_watchdog_link_is_up - update netif_carrier status and
7426 *                             print link up message
7427 * @adapter: pointer to the device adapter structure
7428 **/
7429static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter)
7430{
7431	struct net_device *netdev = adapter->netdev;
7432	struct ixgbe_hw *hw = &adapter->hw;
7433	u32 link_speed = adapter->link_speed;
7434	const char *speed_str;
7435	bool flow_rx, flow_tx;
7436
7437	/* only continue if link was previously down */
7438	if (netif_carrier_ok(netdev))
7439		return;
7440
7441	adapter->flags2 &= ~IXGBE_FLAG2_SEARCH_FOR_SFP;
7442
7443	switch (hw->mac.type) {
7444	case ixgbe_mac_82598EB: {
7445		u32 frctl = IXGBE_READ_REG(hw, IXGBE_FCTRL);
7446		u32 rmcs = IXGBE_READ_REG(hw, IXGBE_RMCS);
7447		flow_rx = !!(frctl & IXGBE_FCTRL_RFCE);
7448		flow_tx = !!(rmcs & IXGBE_RMCS_TFCE_802_3X);
7449	}
7450		break;
7451	case ixgbe_mac_X540:
7452	case ixgbe_mac_X550:
7453	case ixgbe_mac_X550EM_x:
7454	case ixgbe_mac_x550em_a:
7455	case ixgbe_mac_82599EB: {
7456		u32 mflcn = IXGBE_READ_REG(hw, IXGBE_MFLCN);
7457		u32 fccfg = IXGBE_READ_REG(hw, IXGBE_FCCFG);
7458		flow_rx = !!(mflcn & IXGBE_MFLCN_RFCE);
7459		flow_tx = !!(fccfg & IXGBE_FCCFG_TFCE_802_3X);
7460	}
7461		break;
7462	default:
7463		flow_tx = false;
7464		flow_rx = false;
7465		break;
7466	}
7467
7468	adapter->last_rx_ptp_check = jiffies;
7469
7470	if (test_bit(__IXGBE_PTP_RUNNING, &adapter->state))
7471		ixgbe_ptp_start_cyclecounter(adapter);
7472
7473	switch (link_speed) {
7474	case IXGBE_LINK_SPEED_10GB_FULL:
7475		speed_str = "10 Gbps";
7476		break;
7477	case IXGBE_LINK_SPEED_5GB_FULL:
7478		speed_str = "5 Gbps";
7479		break;
7480	case IXGBE_LINK_SPEED_2_5GB_FULL:
7481		speed_str = "2.5 Gbps";
7482		break;
7483	case IXGBE_LINK_SPEED_1GB_FULL:
7484		speed_str = "1 Gbps";
7485		break;
7486	case IXGBE_LINK_SPEED_100_FULL:
7487		speed_str = "100 Mbps";
7488		break;
7489	case IXGBE_LINK_SPEED_10_FULL:
7490		speed_str = "10 Mbps";
7491		break;
7492	default:
7493		speed_str = "unknown speed";
7494		break;
7495	}
7496	e_info(drv, "NIC Link is Up %s, Flow Control: %s\n", speed_str,
7497	       ((flow_rx && flow_tx) ? "RX/TX" :
7498	       (flow_rx ? "RX" :
7499	       (flow_tx ? "TX" : "None"))));
7500
7501	netif_carrier_on(netdev);
7502	ixgbe_check_vf_rate_limit(adapter);
7503
7504	/* enable transmits */
7505	netif_tx_wake_all_queues(adapter->netdev);
7506
7507	/* update the default user priority for VFs */
7508	ixgbe_update_default_up(adapter);
7509
7510	/* ping all the active vfs to let them know link has changed */
7511	ixgbe_ping_all_vfs(adapter);
7512}
7513
7514/**
7515 * ixgbe_watchdog_link_is_down - update netif_carrier status and
7516 *                               print link down message
7517 * @adapter: pointer to the adapter structure
7518 **/
7519static void ixgbe_watchdog_link_is_down(struct ixgbe_adapter *adapter)
7520{
7521	struct net_device *netdev = adapter->netdev;
7522	struct ixgbe_hw *hw = &adapter->hw;
7523
7524	adapter->link_up = false;
7525	adapter->link_speed = 0;
7526
7527	/* only continue if link was up previously */
7528	if (!netif_carrier_ok(netdev))
7529		return;
7530
7531	/* poll for SFP+ cable when link is down */
7532	if (ixgbe_is_sfp(hw) && hw->mac.type == ixgbe_mac_82598EB)
7533		adapter->flags2 |= IXGBE_FLAG2_SEARCH_FOR_SFP;
7534
7535	if (test_bit(__IXGBE_PTP_RUNNING, &adapter->state))
7536		ixgbe_ptp_start_cyclecounter(adapter);
7537
7538	e_info(drv, "NIC Link is Down\n");
7539	netif_carrier_off(netdev);
7540
7541	/* ping all the active vfs to let them know link has changed */
7542	ixgbe_ping_all_vfs(adapter);
7543}
7544
7545static bool ixgbe_ring_tx_pending(struct ixgbe_adapter *adapter)
7546{
7547	int i;
7548
7549	for (i = 0; i < adapter->num_tx_queues; i++) {
7550		struct ixgbe_ring *tx_ring = adapter->tx_ring[i];
7551
7552		if (tx_ring->next_to_use != tx_ring->next_to_clean)
7553			return true;
7554	}
7555
7556	for (i = 0; i < adapter->num_xdp_queues; i++) {
7557		struct ixgbe_ring *ring = adapter->xdp_ring[i];
7558
7559		if (ring->next_to_use != ring->next_to_clean)
7560			return true;
7561	}
7562
7563	return false;
7564}
7565
7566static bool ixgbe_vf_tx_pending(struct ixgbe_adapter *adapter)
7567{
7568	struct ixgbe_hw *hw = &adapter->hw;
7569	struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ];
7570	u32 q_per_pool = __ALIGN_MASK(1, ~vmdq->mask);
7571
7572	int i, j;
7573
7574	if (!adapter->num_vfs)
7575		return false;
7576
7577	/* resetting the PF is only needed for MAC before X550 */
7578	if (hw->mac.type >= ixgbe_mac_X550)
7579		return false;
7580
7581	for (i = 0; i < adapter->num_vfs; i++) {
7582		for (j = 0; j < q_per_pool; j++) {
7583			u32 h, t;
7584
7585			h = IXGBE_READ_REG(hw, IXGBE_PVFTDHN(q_per_pool, i, j));
7586			t = IXGBE_READ_REG(hw, IXGBE_PVFTDTN(q_per_pool, i, j));
7587
7588			if (h != t)
7589				return true;
7590		}
7591	}
7592
7593	return false;
7594}
7595
7596/**
7597 * ixgbe_watchdog_flush_tx - flush queues on link down
7598 * @adapter: pointer to the device adapter structure
7599 **/
7600static void ixgbe_watchdog_flush_tx(struct ixgbe_adapter *adapter)
7601{
7602	if (!netif_carrier_ok(adapter->netdev)) {
7603		if (ixgbe_ring_tx_pending(adapter) ||
7604		    ixgbe_vf_tx_pending(adapter)) {
7605			/* We've lost link, so the controller stops DMA,
7606			 * but we've got queued Tx work that's never going
7607			 * to get done, so reset controller to flush Tx.
7608			 * (Do the reset outside of interrupt context).
7609			 */
7610			e_warn(drv, "initiating reset to clear Tx work after link loss\n");
7611			set_bit(__IXGBE_RESET_REQUESTED, &adapter->state);
7612		}
7613	}
7614}
7615
7616#ifdef CONFIG_PCI_IOV
7617static void ixgbe_bad_vf_abort(struct ixgbe_adapter *adapter, u32 vf)
7618{
7619	struct ixgbe_hw *hw = &adapter->hw;
7620
7621	if (adapter->hw.mac.type == ixgbe_mac_82599EB &&
7622	    adapter->flags2 & IXGBE_FLAG2_AUTO_DISABLE_VF) {
7623		adapter->vfinfo[vf].primary_abort_count++;
7624		if (adapter->vfinfo[vf].primary_abort_count ==
7625		    IXGBE_PRIMARY_ABORT_LIMIT) {
7626			ixgbe_set_vf_link_state(adapter, vf,
7627						IFLA_VF_LINK_STATE_DISABLE);
7628			adapter->vfinfo[vf].primary_abort_count = 0;
7629
7630			e_info(drv,
7631			       "Malicious Driver Detection event detected on PF %d VF %d MAC: %pM mdd-disable-vf=on",
7632			       hw->bus.func, vf,
7633			       adapter->vfinfo[vf].vf_mac_addresses);
7634		}
7635	}
7636}
7637
7638static void ixgbe_check_for_bad_vf(struct ixgbe_adapter *adapter)
7639{
7640	struct ixgbe_hw *hw = &adapter->hw;
7641	struct pci_dev *pdev = adapter->pdev;
7642	unsigned int vf;
7643	u32 gpc;
7644
7645	if (!(netif_carrier_ok(adapter->netdev)))
7646		return;
7647
7648	gpc = IXGBE_READ_REG(hw, IXGBE_TXDGPC);
7649	if (gpc) /* If incrementing then no need for the check below */
7650		return;
7651	/* Check to see if a bad DMA write target from an errant or
7652	 * malicious VF has caused a PCIe error.  If so then we can
7653	 * issue a VFLR to the offending VF(s) and then resume without
7654	 * requesting a full slot reset.
7655	 */
7656
7657	if (!pdev)
7658		return;
7659
7660	/* check status reg for all VFs owned by this PF */
7661	for (vf = 0; vf < adapter->num_vfs; ++vf) {
7662		struct pci_dev *vfdev = adapter->vfinfo[vf].vfdev;
7663		u16 status_reg;
7664
7665		if (!vfdev)
7666			continue;
7667		pci_read_config_word(vfdev, PCI_STATUS, &status_reg);
7668		if (status_reg != IXGBE_FAILED_READ_CFG_WORD &&
7669		    status_reg & PCI_STATUS_REC_MASTER_ABORT) {
7670			ixgbe_bad_vf_abort(adapter, vf);
7671			pcie_flr(vfdev);
7672		}
7673	}
7674}
7675
7676static void ixgbe_spoof_check(struct ixgbe_adapter *adapter)
7677{
7678	u32 ssvpc;
7679
7680	/* Do not perform spoof check for 82598 or if not in IOV mode */
7681	if (adapter->hw.mac.type == ixgbe_mac_82598EB ||
7682	    adapter->num_vfs == 0)
7683		return;
7684
7685	ssvpc = IXGBE_READ_REG(&adapter->hw, IXGBE_SSVPC);
7686
7687	/*
7688	 * ssvpc register is cleared on read, if zero then no
7689	 * spoofed packets in the last interval.
7690	 */
7691	if (!ssvpc)
7692		return;
7693
7694	e_warn(drv, "%u Spoofed packets detected\n", ssvpc);
7695}
7696#else
7697static void ixgbe_spoof_check(struct ixgbe_adapter __always_unused *adapter)
7698{
7699}
7700
7701static void
7702ixgbe_check_for_bad_vf(struct ixgbe_adapter __always_unused *adapter)
7703{
7704}
7705#endif /* CONFIG_PCI_IOV */
7706
7707
7708/**
7709 * ixgbe_watchdog_subtask - check and bring link up
7710 * @adapter: pointer to the device adapter structure
7711 **/
7712static void ixgbe_watchdog_subtask(struct ixgbe_adapter *adapter)
7713{
7714	/* if interface is down, removing or resetting, do nothing */
7715	if (test_bit(__IXGBE_DOWN, &adapter->state) ||
7716	    test_bit(__IXGBE_REMOVING, &adapter->state) ||
7717	    test_bit(__IXGBE_RESETTING, &adapter->state))
7718		return;
7719
7720	ixgbe_watchdog_update_link(adapter);
7721
7722	if (adapter->link_up)
7723		ixgbe_watchdog_link_is_up(adapter);
7724	else
7725		ixgbe_watchdog_link_is_down(adapter);
7726
7727	ixgbe_check_for_bad_vf(adapter);
7728	ixgbe_spoof_check(adapter);
7729	ixgbe_update_stats(adapter);
7730
7731	ixgbe_watchdog_flush_tx(adapter);
7732}
7733
7734/**
7735 * ixgbe_sfp_detection_subtask - poll for SFP+ cable
7736 * @adapter: the ixgbe adapter structure
7737 **/
7738static void ixgbe_sfp_detection_subtask(struct ixgbe_adapter *adapter)
7739{
7740	struct ixgbe_hw *hw = &adapter->hw;
7741	s32 err;
7742
7743	/* not searching for SFP so there is nothing to do here */
7744	if (!(adapter->flags2 & IXGBE_FLAG2_SEARCH_FOR_SFP) &&
7745	    !(adapter->flags2 & IXGBE_FLAG2_SFP_NEEDS_RESET))
7746		return;
7747
7748	if (adapter->sfp_poll_time &&
7749	    time_after(adapter->sfp_poll_time, jiffies))
7750		return; /* If not yet time to poll for SFP */
7751
7752	/* someone else is in init, wait until next service event */
7753	if (test_and_set_bit(__IXGBE_IN_SFP_INIT, &adapter->state))
7754		return;
7755
7756	adapter->sfp_poll_time = jiffies + IXGBE_SFP_POLL_JIFFIES - 1;
7757
7758	err = hw->phy.ops.identify_sfp(hw);
7759	if (err == -EOPNOTSUPP)
7760		goto sfp_out;
7761
7762	if (err == -ENOENT) {
7763		/* If no cable is present, then we need to reset
7764		 * the next time we find a good cable. */
7765		adapter->flags2 |= IXGBE_FLAG2_SFP_NEEDS_RESET;
7766	}
7767
7768	/* exit on error */
7769	if (err)
7770		goto sfp_out;
7771
7772	/* exit if reset not needed */
7773	if (!(adapter->flags2 & IXGBE_FLAG2_SFP_NEEDS_RESET))
7774		goto sfp_out;
7775
7776	adapter->flags2 &= ~IXGBE_FLAG2_SFP_NEEDS_RESET;
7777
7778	/*
7779	 * A module may be identified correctly, but the EEPROM may not have
7780	 * support for that module.  setup_sfp() will fail in that case, so
7781	 * we should not allow that module to load.
7782	 */
7783	if (hw->mac.type == ixgbe_mac_82598EB)
7784		err = hw->phy.ops.reset(hw);
7785	else
7786		err = hw->mac.ops.setup_sfp(hw);
7787
7788	if (err == -EOPNOTSUPP)
7789		goto sfp_out;
7790
7791	adapter->flags |= IXGBE_FLAG_NEED_LINK_CONFIG;
7792	e_info(probe, "detected SFP+: %d\n", hw->phy.sfp_type);
7793
7794sfp_out:
7795	clear_bit(__IXGBE_IN_SFP_INIT, &adapter->state);
7796
7797	if (err == -EOPNOTSUPP &&
7798	    adapter->netdev->reg_state == NETREG_REGISTERED) {
7799		e_dev_err("failed to initialize because an unsupported "
7800			  "SFP+ module type was detected.\n");
7801		e_dev_err("Reload the driver after installing a "
7802			  "supported module.\n");
7803		unregister_netdev(adapter->netdev);
7804	}
7805}
7806
7807/**
7808 * ixgbe_sfp_link_config_subtask - set up link SFP after module install
7809 * @adapter: the ixgbe adapter structure
7810 **/
7811static void ixgbe_sfp_link_config_subtask(struct ixgbe_adapter *adapter)
7812{
7813	struct ixgbe_hw *hw = &adapter->hw;
7814	u32 cap_speed;
7815	u32 speed;
7816	bool autoneg = false;
7817
7818	if (!(adapter->flags & IXGBE_FLAG_NEED_LINK_CONFIG))
7819		return;
7820
7821	/* someone else is in init, wait until next service event */
7822	if (test_and_set_bit(__IXGBE_IN_SFP_INIT, &adapter->state))
7823		return;
7824
7825	adapter->flags &= ~IXGBE_FLAG_NEED_LINK_CONFIG;
7826
7827	hw->mac.ops.get_link_capabilities(hw, &cap_speed, &autoneg);
7828
7829	/* advertise highest capable link speed */
7830	if (!autoneg && (cap_speed & IXGBE_LINK_SPEED_10GB_FULL))
7831		speed = IXGBE_LINK_SPEED_10GB_FULL;
7832	else
7833		speed = cap_speed & (IXGBE_LINK_SPEED_10GB_FULL |
7834				     IXGBE_LINK_SPEED_1GB_FULL);
7835
7836	if (hw->mac.ops.setup_link)
7837		hw->mac.ops.setup_link(hw, speed, true);
7838
7839	adapter->flags |= IXGBE_FLAG_NEED_LINK_UPDATE;
7840	adapter->link_check_timeout = jiffies;
7841	clear_bit(__IXGBE_IN_SFP_INIT, &adapter->state);
7842}
7843
7844/**
7845 * ixgbe_service_timer - Timer Call-back
7846 * @t: pointer to timer_list structure
7847 **/
7848static void ixgbe_service_timer(struct timer_list *t)
7849{
7850	struct ixgbe_adapter *adapter = from_timer(adapter, t, service_timer);
7851	unsigned long next_event_offset;
7852
7853	/* poll faster when waiting for link */
7854	if (adapter->flags & IXGBE_FLAG_NEED_LINK_UPDATE)
7855		next_event_offset = HZ / 10;
7856	else
7857		next_event_offset = HZ * 2;
7858
7859	/* Reset the timer */
7860	mod_timer(&adapter->service_timer, next_event_offset + jiffies);
7861
7862	ixgbe_service_event_schedule(adapter);
7863}
7864
7865static void ixgbe_phy_interrupt_subtask(struct ixgbe_adapter *adapter)
7866{
7867	struct ixgbe_hw *hw = &adapter->hw;
7868	bool overtemp;
7869
7870	if (!(adapter->flags2 & IXGBE_FLAG2_PHY_INTERRUPT))
7871		return;
7872
7873	adapter->flags2 &= ~IXGBE_FLAG2_PHY_INTERRUPT;
7874
7875	if (!hw->phy.ops.handle_lasi)
7876		return;
7877
7878	hw->phy.ops.handle_lasi(&adapter->hw, &overtemp);
7879	if (overtemp)
7880		e_crit(drv, "%s\n", ixgbe_overheat_msg);
7881}
7882
7883static void ixgbe_reset_subtask(struct ixgbe_adapter *adapter)
7884{
7885	if (!test_and_clear_bit(__IXGBE_RESET_REQUESTED, &adapter->state))
7886		return;
7887
7888	rtnl_lock();
7889	/* If we're already down, removing or resetting, just bail */
7890	if (test_bit(__IXGBE_DOWN, &adapter->state) ||
7891	    test_bit(__IXGBE_REMOVING, &adapter->state) ||
7892	    test_bit(__IXGBE_RESETTING, &adapter->state)) {
7893		rtnl_unlock();
7894		return;
7895	}
7896
7897	ixgbe_dump(adapter);
7898	netdev_err(adapter->netdev, "Reset adapter\n");
7899	adapter->tx_timeout_count++;
7900
7901	ixgbe_reinit_locked(adapter);
7902	rtnl_unlock();
7903}
7904
7905/**
7906 * ixgbe_check_fw_error - Check firmware for errors
7907 * @adapter: the adapter private structure
7908 *
7909 * Check firmware errors in register FWSM
7910 */
7911static bool ixgbe_check_fw_error(struct ixgbe_adapter *adapter)
7912{
7913	struct ixgbe_hw *hw = &adapter->hw;
7914	u32 fwsm;
7915
7916	/* read fwsm.ext_err_ind register and log errors */
7917	fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw));
7918
7919	if (fwsm & IXGBE_FWSM_EXT_ERR_IND_MASK ||
7920	    !(fwsm & IXGBE_FWSM_FW_VAL_BIT))
7921		e_dev_warn("Warning firmware error detected FWSM: 0x%08X\n",
7922			   fwsm);
7923
7924	if (hw->mac.ops.fw_recovery_mode && hw->mac.ops.fw_recovery_mode(hw)) {
7925		e_dev_err("Firmware recovery mode detected. Limiting functionality. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode.\n");
7926		return true;
7927	}
7928
7929	return false;
7930}
7931
7932/**
7933 * ixgbe_service_task - manages and runs subtasks
7934 * @work: pointer to work_struct containing our data
7935 **/
7936static void ixgbe_service_task(struct work_struct *work)
7937{
7938	struct ixgbe_adapter *adapter = container_of(work,
7939						     struct ixgbe_adapter,
7940						     service_task);
7941	if (ixgbe_removed(adapter->hw.hw_addr)) {
7942		if (!test_bit(__IXGBE_DOWN, &adapter->state)) {
7943			rtnl_lock();
7944			ixgbe_down(adapter);
7945			rtnl_unlock();
7946		}
7947		ixgbe_service_event_complete(adapter);
7948		return;
7949	}
7950	if (ixgbe_check_fw_error(adapter)) {
7951		if (!test_bit(__IXGBE_DOWN, &adapter->state))
7952			unregister_netdev(adapter->netdev);
7953		ixgbe_service_event_complete(adapter);
7954		return;
7955	}
7956	ixgbe_reset_subtask(adapter);
7957	ixgbe_phy_interrupt_subtask(adapter);
7958	ixgbe_sfp_detection_subtask(adapter);
7959	ixgbe_sfp_link_config_subtask(adapter);
7960	ixgbe_check_overtemp_subtask(adapter);
7961	ixgbe_watchdog_subtask(adapter);
7962	ixgbe_fdir_reinit_subtask(adapter);
7963	ixgbe_check_hang_subtask(adapter);
7964
7965	if (test_bit(__IXGBE_PTP_RUNNING, &adapter->state)) {
7966		ixgbe_ptp_overflow_check(adapter);
7967		if (adapter->flags & IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER)
7968			ixgbe_ptp_rx_hang(adapter);
7969		ixgbe_ptp_tx_hang(adapter);
7970	}
7971
7972	ixgbe_service_event_complete(adapter);
7973}
7974
7975static int ixgbe_tso(struct ixgbe_ring *tx_ring,
7976		     struct ixgbe_tx_buffer *first,
7977		     u8 *hdr_len,
7978		     struct ixgbe_ipsec_tx_data *itd)
7979{
7980	u32 vlan_macip_lens, type_tucmd, mss_l4len_idx;
7981	struct sk_buff *skb = first->skb;
7982	union {
7983		struct iphdr *v4;
7984		struct ipv6hdr *v6;
7985		unsigned char *hdr;
7986	} ip;
7987	union {
7988		struct tcphdr *tcp;
7989		struct udphdr *udp;
7990		unsigned char *hdr;
7991	} l4;
7992	u32 paylen, l4_offset;
7993	u32 fceof_saidx = 0;
7994	int err;
7995
7996	if (skb->ip_summed != CHECKSUM_PARTIAL)
7997		return 0;
7998
7999	if (!skb_is_gso(skb))
8000		return 0;
8001
8002	err = skb_cow_head(skb, 0);
8003	if (err < 0)
8004		return err;
8005
8006	if (eth_p_mpls(first->protocol))
8007		ip.hdr = skb_inner_network_header(skb);
8008	else
8009		ip.hdr = skb_network_header(skb);
8010	l4.hdr = skb_checksum_start(skb);
8011
8012	/* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */
8013	type_tucmd = (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) ?
8014		      IXGBE_ADVTXD_TUCMD_L4T_UDP : IXGBE_ADVTXD_TUCMD_L4T_TCP;
8015
8016	/* initialize outer IP header fields */
8017	if (ip.v4->version == 4) {
8018		unsigned char *csum_start = skb_checksum_start(skb);
8019		unsigned char *trans_start = ip.hdr + (ip.v4->ihl * 4);
8020		int len = csum_start - trans_start;
8021
8022		/* IP header will have to cancel out any data that
8023		 * is not a part of the outer IP header, so set to
8024		 * a reverse csum if needed, else init check to 0.
8025		 */
8026		ip.v4->check = (skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) ?
8027					   csum_fold(csum_partial(trans_start,
8028								  len, 0)) : 0;
8029		type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4;
8030
8031		ip.v4->tot_len = 0;
8032		first->tx_flags |= IXGBE_TX_FLAGS_TSO |
8033				   IXGBE_TX_FLAGS_CSUM |
8034				   IXGBE_TX_FLAGS_IPV4;
8035	} else {
8036		ip.v6->payload_len = 0;
8037		first->tx_flags |= IXGBE_TX_FLAGS_TSO |
8038				   IXGBE_TX_FLAGS_CSUM;
8039	}
8040
8041	/* determine offset of inner transport header */
8042	l4_offset = l4.hdr - skb->data;
8043
8044	/* remove payload length from inner checksum */
8045	paylen = skb->len - l4_offset;
8046
8047	if (type_tucmd & IXGBE_ADVTXD_TUCMD_L4T_TCP) {
8048		/* compute length of segmentation header */
8049		*hdr_len = (l4.tcp->doff * 4) + l4_offset;
8050		csum_replace_by_diff(&l4.tcp->check,
8051				     (__force __wsum)htonl(paylen));
8052	} else {
8053		/* compute length of segmentation header */
8054		*hdr_len = sizeof(*l4.udp) + l4_offset;
8055		csum_replace_by_diff(&l4.udp->check,
8056				     (__force __wsum)htonl(paylen));
8057	}
8058
8059	/* update gso size and bytecount with header size */
8060	first->gso_segs = skb_shinfo(skb)->gso_segs;
8061	first->bytecount += (first->gso_segs - 1) * *hdr_len;
8062
8063	/* mss_l4len_id: use 0 as index for TSO */
8064	mss_l4len_idx = (*hdr_len - l4_offset) << IXGBE_ADVTXD_L4LEN_SHIFT;
8065	mss_l4len_idx |= skb_shinfo(skb)->gso_size << IXGBE_ADVTXD_MSS_SHIFT;
8066
8067	fceof_saidx |= itd->sa_idx;
8068	type_tucmd |= itd->flags | itd->trailer_len;
8069
8070	/* vlan_macip_lens: HEADLEN, MACLEN, VLAN tag */
8071	vlan_macip_lens = l4.hdr - ip.hdr;
8072	vlan_macip_lens |= (ip.hdr - skb->data) << IXGBE_ADVTXD_MACLEN_SHIFT;
8073	vlan_macip_lens |= first->tx_flags & IXGBE_TX_FLAGS_VLAN_MASK;
8074
8075	ixgbe_tx_ctxtdesc(tx_ring, vlan_macip_lens, fceof_saidx, type_tucmd,
8076			  mss_l4len_idx);
8077
8078	return 1;
8079}
8080
8081static inline bool ixgbe_ipv6_csum_is_sctp(struct sk_buff *skb)
8082{
8083	unsigned int offset = 0;
8084
8085	ipv6_find_hdr(skb, &offset, IPPROTO_SCTP, NULL, NULL);
8086
8087	return offset == skb_checksum_start_offset(skb);
8088}
8089
8090static void ixgbe_tx_csum(struct ixgbe_ring *tx_ring,
8091			  struct ixgbe_tx_buffer *first,
8092			  struct ixgbe_ipsec_tx_data *itd)
8093{
8094	struct sk_buff *skb = first->skb;
8095	u32 vlan_macip_lens = 0;
8096	u32 fceof_saidx = 0;
8097	u32 type_tucmd = 0;
8098
8099	if (skb->ip_summed != CHECKSUM_PARTIAL) {
8100csum_failed:
8101		if (!(first->tx_flags & (IXGBE_TX_FLAGS_HW_VLAN |
8102					 IXGBE_TX_FLAGS_CC)))
8103			return;
8104		goto no_csum;
8105	}
8106
8107	switch (skb->csum_offset) {
8108	case offsetof(struct tcphdr, check):
8109		type_tucmd = IXGBE_ADVTXD_TUCMD_L4T_TCP;
8110		fallthrough;
8111	case offsetof(struct udphdr, check):
8112		break;
8113	case offsetof(struct sctphdr, checksum):
8114		/* validate that this is actually an SCTP request */
8115		if (((first->protocol == htons(ETH_P_IP)) &&
8116		     (ip_hdr(skb)->protocol == IPPROTO_SCTP)) ||
8117		    ((first->protocol == htons(ETH_P_IPV6)) &&
8118		     ixgbe_ipv6_csum_is_sctp(skb))) {
8119			type_tucmd = IXGBE_ADVTXD_TUCMD_L4T_SCTP;
8120			break;
8121		}
8122		fallthrough;
8123	default:
8124		skb_checksum_help(skb);
8125		goto csum_failed;
8126	}
8127
8128	/* update TX checksum flag */
8129	first->tx_flags |= IXGBE_TX_FLAGS_CSUM;
8130	vlan_macip_lens = skb_checksum_start_offset(skb) -
8131			  skb_network_offset(skb);
8132no_csum:
8133	/* vlan_macip_lens: MACLEN, VLAN tag */
8134	vlan_macip_lens |= skb_network_offset(skb) << IXGBE_ADVTXD_MACLEN_SHIFT;
8135	vlan_macip_lens |= first->tx_flags & IXGBE_TX_FLAGS_VLAN_MASK;
8136
8137	fceof_saidx |= itd->sa_idx;
8138	type_tucmd |= itd->flags | itd->trailer_len;
8139
8140	ixgbe_tx_ctxtdesc(tx_ring, vlan_macip_lens, fceof_saidx, type_tucmd, 0);
8141}
8142
8143#define IXGBE_SET_FLAG(_input, _flag, _result) \
8144	((_flag <= _result) ? \
8145	 ((u32)(_input & _flag) * (_result / _flag)) : \
8146	 ((u32)(_input & _flag) / (_flag / _result)))
8147
8148static u32 ixgbe_tx_cmd_type(struct sk_buff *skb, u32 tx_flags)
8149{
8150	/* set type for advanced descriptor with frame checksum insertion */
8151	u32 cmd_type = IXGBE_ADVTXD_DTYP_DATA |
8152		       IXGBE_ADVTXD_DCMD_DEXT |
8153		       IXGBE_ADVTXD_DCMD_IFCS;
8154
8155	/* set HW vlan bit if vlan is present */
8156	cmd_type |= IXGBE_SET_FLAG(tx_flags, IXGBE_TX_FLAGS_HW_VLAN,
8157				   IXGBE_ADVTXD_DCMD_VLE);
8158
8159	/* set segmentation enable bits for TSO/FSO */
8160	cmd_type |= IXGBE_SET_FLAG(tx_flags, IXGBE_TX_FLAGS_TSO,
8161				   IXGBE_ADVTXD_DCMD_TSE);
8162
8163	/* set timestamp bit if present */
8164	cmd_type |= IXGBE_SET_FLAG(tx_flags, IXGBE_TX_FLAGS_TSTAMP,
8165				   IXGBE_ADVTXD_MAC_TSTAMP);
8166
8167	/* insert frame checksum */
8168	cmd_type ^= IXGBE_SET_FLAG(skb->no_fcs, 1, IXGBE_ADVTXD_DCMD_IFCS);
8169
8170	return cmd_type;
8171}
8172
8173static void ixgbe_tx_olinfo_status(union ixgbe_adv_tx_desc *tx_desc,
8174				   u32 tx_flags, unsigned int paylen)
8175{
8176	u32 olinfo_status = paylen << IXGBE_ADVTXD_PAYLEN_SHIFT;
8177
8178	/* enable L4 checksum for TSO and TX checksum offload */
8179	olinfo_status |= IXGBE_SET_FLAG(tx_flags,
8180					IXGBE_TX_FLAGS_CSUM,
8181					IXGBE_ADVTXD_POPTS_TXSM);
8182
8183	/* enable IPv4 checksum for TSO */
8184	olinfo_status |= IXGBE_SET_FLAG(tx_flags,
8185					IXGBE_TX_FLAGS_IPV4,
8186					IXGBE_ADVTXD_POPTS_IXSM);
8187
8188	/* enable IPsec */
8189	olinfo_status |= IXGBE_SET_FLAG(tx_flags,
8190					IXGBE_TX_FLAGS_IPSEC,
8191					IXGBE_ADVTXD_POPTS_IPSEC);
8192
8193	/*
8194	 * Check Context must be set if Tx switch is enabled, which it
8195	 * always is for case where virtual functions are running
8196	 */
8197	olinfo_status |= IXGBE_SET_FLAG(tx_flags,
8198					IXGBE_TX_FLAGS_CC,
8199					IXGBE_ADVTXD_CC);
8200
8201	tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status);
8202}
8203
8204static int __ixgbe_maybe_stop_tx(struct ixgbe_ring *tx_ring, u16 size)
8205{
8206	netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
8207
8208	/* Herbert's original patch had:
8209	 *  smp_mb__after_netif_stop_queue();
8210	 * but since that doesn't exist yet, just open code it.
8211	 */
8212	smp_mb();
8213
8214	/* We need to check again in a case another CPU has just
8215	 * made room available.
8216	 */
8217	if (likely(ixgbe_desc_unused(tx_ring) < size))
8218		return -EBUSY;
8219
8220	/* A reprieve! - use start_queue because it doesn't call schedule */
8221	netif_start_subqueue(tx_ring->netdev, tx_ring->queue_index);
8222	++tx_ring->tx_stats.restart_queue;
8223	return 0;
8224}
8225
8226static inline int ixgbe_maybe_stop_tx(struct ixgbe_ring *tx_ring, u16 size)
8227{
8228	if (likely(ixgbe_desc_unused(tx_ring) >= size))
8229		return 0;
8230
8231	return __ixgbe_maybe_stop_tx(tx_ring, size);
8232}
8233
8234static int ixgbe_tx_map(struct ixgbe_ring *tx_ring,
8235			struct ixgbe_tx_buffer *first,
8236			const u8 hdr_len)
8237{
8238	struct sk_buff *skb = first->skb;
8239	struct ixgbe_tx_buffer *tx_buffer;
8240	union ixgbe_adv_tx_desc *tx_desc;
8241	skb_frag_t *frag;
8242	dma_addr_t dma;
8243	unsigned int data_len, size;
8244	u32 tx_flags = first->tx_flags;
8245	u32 cmd_type = ixgbe_tx_cmd_type(skb, tx_flags);
8246	u16 i = tx_ring->next_to_use;
8247
8248	tx_desc = IXGBE_TX_DESC(tx_ring, i);
8249
8250	ixgbe_tx_olinfo_status(tx_desc, tx_flags, skb->len - hdr_len);
8251
8252	size = skb_headlen(skb);
8253	data_len = skb->data_len;
8254
8255#ifdef IXGBE_FCOE
8256	if (tx_flags & IXGBE_TX_FLAGS_FCOE) {
8257		if (data_len < sizeof(struct fcoe_crc_eof)) {
8258			size -= sizeof(struct fcoe_crc_eof) - data_len;
8259			data_len = 0;
8260		} else {
8261			data_len -= sizeof(struct fcoe_crc_eof);
8262		}
8263	}
8264
8265#endif
8266	dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE);
8267
8268	tx_buffer = first;
8269
8270	for (frag = &skb_shinfo(skb)->frags[0];; frag++) {
8271		if (dma_mapping_error(tx_ring->dev, dma))
8272			goto dma_error;
8273
8274		/* record length, and DMA address */
8275		dma_unmap_len_set(tx_buffer, len, size);
8276		dma_unmap_addr_set(tx_buffer, dma, dma);
8277
8278		tx_desc->read.buffer_addr = cpu_to_le64(dma);
8279
8280		while (unlikely(size > IXGBE_MAX_DATA_PER_TXD)) {
8281			tx_desc->read.cmd_type_len =
8282				cpu_to_le32(cmd_type ^ IXGBE_MAX_DATA_PER_TXD);
8283
8284			i++;
8285			tx_desc++;
8286			if (i == tx_ring->count) {
8287				tx_desc = IXGBE_TX_DESC(tx_ring, 0);
8288				i = 0;
8289			}
8290			tx_desc->read.olinfo_status = 0;
8291
8292			dma += IXGBE_MAX_DATA_PER_TXD;
8293			size -= IXGBE_MAX_DATA_PER_TXD;
8294
8295			tx_desc->read.buffer_addr = cpu_to_le64(dma);
8296		}
8297
8298		if (likely(!data_len))
8299			break;
8300
8301		tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type ^ size);
8302
8303		i++;
8304		tx_desc++;
8305		if (i == tx_ring->count) {
8306			tx_desc = IXGBE_TX_DESC(tx_ring, 0);
8307			i = 0;
8308		}
8309		tx_desc->read.olinfo_status = 0;
8310
8311#ifdef IXGBE_FCOE
8312		size = min_t(unsigned int, data_len, skb_frag_size(frag));
8313#else
8314		size = skb_frag_size(frag);
8315#endif
8316		data_len -= size;
8317
8318		dma = skb_frag_dma_map(tx_ring->dev, frag, 0, size,
8319				       DMA_TO_DEVICE);
8320
8321		tx_buffer = &tx_ring->tx_buffer_info[i];
8322	}
8323
8324	/* write last descriptor with RS and EOP bits */
8325	cmd_type |= size | IXGBE_TXD_CMD;
8326	tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type);
8327
8328	netdev_tx_sent_queue(txring_txq(tx_ring), first->bytecount);
8329
8330	/* set the timestamp */
8331	first->time_stamp = jiffies;
8332
8333	skb_tx_timestamp(skb);
8334
8335	/*
8336	 * Force memory writes to complete before letting h/w know there
8337	 * are new descriptors to fetch.  (Only applicable for weak-ordered
8338	 * memory model archs, such as IA-64).
8339	 *
8340	 * We also need this memory barrier to make certain all of the
8341	 * status bits have been updated before next_to_watch is written.
8342	 */
8343	wmb();
8344
8345	/* set next_to_watch value indicating a packet is present */
8346	first->next_to_watch = tx_desc;
8347
8348	i++;
8349	if (i == tx_ring->count)
8350		i = 0;
8351
8352	tx_ring->next_to_use = i;
8353
8354	ixgbe_maybe_stop_tx(tx_ring, DESC_NEEDED);
8355
8356	if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
8357		writel(i, tx_ring->tail);
8358	}
8359
8360	return 0;
8361dma_error:
8362	dev_err(tx_ring->dev, "TX DMA map failed\n");
8363
8364	/* clear dma mappings for failed tx_buffer_info map */
8365	for (;;) {
8366		tx_buffer = &tx_ring->tx_buffer_info[i];
8367		if (dma_unmap_len(tx_buffer, len))
8368			dma_unmap_page(tx_ring->dev,
8369				       dma_unmap_addr(tx_buffer, dma),
8370				       dma_unmap_len(tx_buffer, len),
8371				       DMA_TO_DEVICE);
8372		dma_unmap_len_set(tx_buffer, len, 0);
8373		if (tx_buffer == first)
8374			break;
8375		if (i == 0)
8376			i += tx_ring->count;
8377		i--;
8378	}
8379
8380	dev_kfree_skb_any(first->skb);
8381	first->skb = NULL;
8382
8383	tx_ring->next_to_use = i;
8384
8385	return -1;
8386}
8387
8388static void ixgbe_atr(struct ixgbe_ring *ring,
8389		      struct ixgbe_tx_buffer *first)
8390{
8391	struct ixgbe_q_vector *q_vector = ring->q_vector;
8392	union ixgbe_atr_hash_dword input = { .dword = 0 };
8393	union ixgbe_atr_hash_dword common = { .dword = 0 };
8394	union {
8395		unsigned char *network;
8396		struct iphdr *ipv4;
8397		struct ipv6hdr *ipv6;
8398	} hdr;
8399	struct tcphdr *th;
8400	unsigned int hlen;
8401	struct sk_buff *skb;
8402	__be16 vlan_id;
8403	int l4_proto;
8404
8405	/* if ring doesn't have a interrupt vector, cannot perform ATR */
8406	if (!q_vector)
8407		return;
8408
8409	/* do nothing if sampling is disabled */
8410	if (!ring->atr_sample_rate)
8411		return;
8412
8413	ring->atr_count++;
8414
8415	/* currently only IPv4/IPv6 with TCP is supported */
8416	if ((first->protocol != htons(ETH_P_IP)) &&
8417	    (first->protocol != htons(ETH_P_IPV6)))
8418		return;
8419
8420	/* snag network header to get L4 type and address */
8421	skb = first->skb;
8422	hdr.network = skb_network_header(skb);
8423	if (unlikely(hdr.network <= skb->data))
8424		return;
8425	if (skb->encapsulation &&
8426	    first->protocol == htons(ETH_P_IP) &&
8427	    hdr.ipv4->protocol == IPPROTO_UDP) {
8428		struct ixgbe_adapter *adapter = q_vector->adapter;
8429
8430		if (unlikely(skb_tail_pointer(skb) < hdr.network +
8431			     vxlan_headroom(0)))
8432			return;
8433
8434		/* verify the port is recognized as VXLAN */
8435		if (adapter->vxlan_port &&
8436		    udp_hdr(skb)->dest == adapter->vxlan_port)
8437			hdr.network = skb_inner_network_header(skb);
8438
8439		if (adapter->geneve_port &&
8440		    udp_hdr(skb)->dest == adapter->geneve_port)
8441			hdr.network = skb_inner_network_header(skb);
8442	}
8443
8444	/* Make sure we have at least [minimum IPv4 header + TCP]
8445	 * or [IPv6 header] bytes
8446	 */
8447	if (unlikely(skb_tail_pointer(skb) < hdr.network + 40))
8448		return;
8449
8450	/* Currently only IPv4/IPv6 with TCP is supported */
8451	switch (hdr.ipv4->version) {
8452	case IPVERSION:
8453		/* access ihl as u8 to avoid unaligned access on ia64 */
8454		hlen = (hdr.network[0] & 0x0F) << 2;
8455		l4_proto = hdr.ipv4->protocol;
8456		break;
8457	case 6:
8458		hlen = hdr.network - skb->data;
8459		l4_proto = ipv6_find_hdr(skb, &hlen, IPPROTO_TCP, NULL, NULL);
8460		hlen -= hdr.network - skb->data;
8461		break;
8462	default:
8463		return;
8464	}
8465
8466	if (l4_proto != IPPROTO_TCP)
8467		return;
8468
8469	if (unlikely(skb_tail_pointer(skb) < hdr.network +
8470		     hlen + sizeof(struct tcphdr)))
8471		return;
8472
8473	th = (struct tcphdr *)(hdr.network + hlen);
8474
8475	/* skip this packet since the socket is closing */
8476	if (th->fin)
8477		return;
8478
8479	/* sample on all syn packets or once every atr sample count */
8480	if (!th->syn && (ring->atr_count < ring->atr_sample_rate))
8481		return;
8482
8483	/* reset sample count */
8484	ring->atr_count = 0;
8485
8486	vlan_id = htons(first->tx_flags >> IXGBE_TX_FLAGS_VLAN_SHIFT);
8487
8488	/*
8489	 * src and dst are inverted, think how the receiver sees them
8490	 *
8491	 * The input is broken into two sections, a non-compressed section
8492	 * containing vm_pool, vlan_id, and flow_type.  The rest of the data
8493	 * is XORed together and stored in the compressed dword.
8494	 */
8495	input.formatted.vlan_id = vlan_id;
8496
8497	/*
8498	 * since src port and flex bytes occupy the same word XOR them together
8499	 * and write the value to source port portion of compressed dword
8500	 */
8501	if (first->tx_flags & (IXGBE_TX_FLAGS_SW_VLAN | IXGBE_TX_FLAGS_HW_VLAN))
8502		common.port.src ^= th->dest ^ htons(ETH_P_8021Q);
8503	else
8504		common.port.src ^= th->dest ^ first->protocol;
8505	common.port.dst ^= th->source;
8506
8507	switch (hdr.ipv4->version) {
8508	case IPVERSION:
8509		input.formatted.flow_type = IXGBE_ATR_FLOW_TYPE_TCPV4;
8510		common.ip ^= hdr.ipv4->saddr ^ hdr.ipv4->daddr;
8511		break;
8512	case 6:
8513		input.formatted.flow_type = IXGBE_ATR_FLOW_TYPE_TCPV6;
8514		common.ip ^= hdr.ipv6->saddr.s6_addr32[0] ^
8515			     hdr.ipv6->saddr.s6_addr32[1] ^
8516			     hdr.ipv6->saddr.s6_addr32[2] ^
8517			     hdr.ipv6->saddr.s6_addr32[3] ^
8518			     hdr.ipv6->daddr.s6_addr32[0] ^
8519			     hdr.ipv6->daddr.s6_addr32[1] ^
8520			     hdr.ipv6->daddr.s6_addr32[2] ^
8521			     hdr.ipv6->daddr.s6_addr32[3];
8522		break;
8523	default:
8524		break;
8525	}
8526
8527	if (hdr.network != skb_network_header(skb))
8528		input.formatted.flow_type |= IXGBE_ATR_L4TYPE_TUNNEL_MASK;
8529
8530	/* This assumes the Rx queue and Tx queue are bound to the same CPU */
8531	ixgbe_fdir_add_signature_filter_82599(&q_vector->adapter->hw,
8532					      input, common, ring->queue_index);
8533}
8534
8535#ifdef IXGBE_FCOE
8536static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
8537			      struct net_device *sb_dev)
8538{
8539	struct ixgbe_adapter *adapter;
8540	struct ixgbe_ring_feature *f;
8541	int txq;
8542
8543	if (sb_dev) {
8544		u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
8545		struct net_device *vdev = sb_dev;
8546
8547		txq = vdev->tc_to_txq[tc].offset;
8548		txq += reciprocal_scale(skb_get_hash(skb),
8549					vdev->tc_to_txq[tc].count);
8550
8551		return txq;
8552	}
8553
8554	/*
8555	 * only execute the code below if protocol is FCoE
8556	 * or FIP and we have FCoE enabled on the adapter
8557	 */
8558	switch (vlan_get_protocol(skb)) {
8559	case htons(ETH_P_FCOE):
8560	case htons(ETH_P_FIP):
8561		adapter = netdev_priv(dev);
8562
8563		if (!sb_dev && (adapter->flags & IXGBE_FLAG_FCOE_ENABLED))
8564			break;
8565		fallthrough;
8566	default:
8567		return netdev_pick_tx(dev, skb, sb_dev);
8568	}
8569
8570	f = &adapter->ring_feature[RING_F_FCOE];
8571
8572	txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) :
8573					   smp_processor_id();
8574
8575	while (txq >= f->indices)
8576		txq -= f->indices;
8577
8578	return txq + f->offset;
8579}
8580
8581#endif
8582int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
8583			struct xdp_frame *xdpf)
8584{
8585	struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()];
8586	struct ixgbe_tx_buffer *tx_buffer;
8587	union ixgbe_adv_tx_desc *tx_desc;
8588	u32 len, cmd_type;
8589	dma_addr_t dma;
8590	u16 i;
8591
8592	len = xdpf->len;
8593
8594	if (unlikely(!ixgbe_desc_unused(ring)))
8595		return IXGBE_XDP_CONSUMED;
8596
8597	dma = dma_map_single(ring->dev, xdpf->data, len, DMA_TO_DEVICE);
8598	if (dma_mapping_error(ring->dev, dma))
8599		return IXGBE_XDP_CONSUMED;
8600
8601	/* record the location of the first descriptor for this packet */
8602	tx_buffer = &ring->tx_buffer_info[ring->next_to_use];
8603	tx_buffer->bytecount = len;
8604	tx_buffer->gso_segs = 1;
8605	tx_buffer->protocol = 0;
8606
8607	i = ring->next_to_use;
8608	tx_desc = IXGBE_TX_DESC(ring, i);
8609
8610	dma_unmap_len_set(tx_buffer, len, len);
8611	dma_unmap_addr_set(tx_buffer, dma, dma);
8612	tx_buffer->xdpf = xdpf;
8613
8614	tx_desc->read.buffer_addr = cpu_to_le64(dma);
8615
8616	/* put descriptor type bits */
8617	cmd_type = IXGBE_ADVTXD_DTYP_DATA |
8618		   IXGBE_ADVTXD_DCMD_DEXT |
8619		   IXGBE_ADVTXD_DCMD_IFCS;
8620	cmd_type |= len | IXGBE_TXD_CMD;
8621	tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type);
8622	tx_desc->read.olinfo_status =
8623		cpu_to_le32(len << IXGBE_ADVTXD_PAYLEN_SHIFT);
8624
8625	/* Avoid any potential race with xdp_xmit and cleanup */
8626	smp_wmb();
8627
8628	/* set next_to_watch value indicating a packet is present */
8629	i++;
8630	if (i == ring->count)
8631		i = 0;
8632
8633	tx_buffer->next_to_watch = tx_desc;
8634	ring->next_to_use = i;
8635
8636	return IXGBE_XDP_TX;
8637}
8638
8639netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb,
8640			  struct ixgbe_adapter *adapter,
8641			  struct ixgbe_ring *tx_ring)
8642{
8643	struct ixgbe_tx_buffer *first;
8644	int tso;
8645	u32 tx_flags = 0;
8646	unsigned short f;
8647	u16 count = TXD_USE_COUNT(skb_headlen(skb));
8648	struct ixgbe_ipsec_tx_data ipsec_tx = { 0 };
8649	__be16 protocol = skb->protocol;
8650	u8 hdr_len = 0;
8651
8652	/*
8653	 * need: 1 descriptor per page * PAGE_SIZE/IXGBE_MAX_DATA_PER_TXD,
8654	 *       + 1 desc for skb_headlen/IXGBE_MAX_DATA_PER_TXD,
8655	 *       + 2 desc gap to keep tail from touching head,
8656	 *       + 1 desc for context descriptor,
8657	 * otherwise try next time
8658	 */
8659	for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
8660		count += TXD_USE_COUNT(skb_frag_size(
8661						&skb_shinfo(skb)->frags[f]));
8662
8663	if (ixgbe_maybe_stop_tx(tx_ring, count + 3)) {
8664		tx_ring->tx_stats.tx_busy++;
8665		return NETDEV_TX_BUSY;
8666	}
8667
8668	/* record the location of the first descriptor for this packet */
8669	first = &tx_ring->tx_buffer_info[tx_ring->next_to_use];
8670	first->skb = skb;
8671	first->bytecount = skb->len;
8672	first->gso_segs = 1;
8673
8674	/* if we have a HW VLAN tag being added default to the HW one */
8675	if (skb_vlan_tag_present(skb)) {
8676		tx_flags |= skb_vlan_tag_get(skb) << IXGBE_TX_FLAGS_VLAN_SHIFT;
8677		tx_flags |= IXGBE_TX_FLAGS_HW_VLAN;
8678	/* else if it is a SW VLAN check the next protocol and store the tag */
8679	} else if (protocol == htons(ETH_P_8021Q)) {
8680		struct vlan_hdr *vhdr, _vhdr;
8681		vhdr = skb_header_pointer(skb, ETH_HLEN, sizeof(_vhdr), &_vhdr);
8682		if (!vhdr)
8683			goto out_drop;
8684
8685		tx_flags |= ntohs(vhdr->h_vlan_TCI) <<
8686				  IXGBE_TX_FLAGS_VLAN_SHIFT;
8687		tx_flags |= IXGBE_TX_FLAGS_SW_VLAN;
8688	}
8689	protocol = vlan_get_protocol(skb);
8690
8691	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
8692	    adapter->ptp_clock) {
8693		if (adapter->tstamp_config.tx_type == HWTSTAMP_TX_ON &&
8694		    !test_and_set_bit_lock(__IXGBE_PTP_TX_IN_PROGRESS,
8695					   &adapter->state)) {
8696			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
8697			tx_flags |= IXGBE_TX_FLAGS_TSTAMP;
8698
8699			/* schedule check for Tx timestamp */
8700			adapter->ptp_tx_skb = skb_get(skb);
8701			adapter->ptp_tx_start = jiffies;
8702			schedule_work(&adapter->ptp_tx_work);
8703		} else {
8704			adapter->tx_hwtstamp_skipped++;
8705		}
8706	}
8707
8708#ifdef CONFIG_PCI_IOV
8709	/*
8710	 * Use the l2switch_enable flag - would be false if the DMA
8711	 * Tx switch had been disabled.
8712	 */
8713	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
8714		tx_flags |= IXGBE_TX_FLAGS_CC;
8715
8716#endif
8717	/* DCB maps skb priorities 0-7 onto 3 bit PCP of VLAN tag. */
8718	if ((adapter->flags & IXGBE_FLAG_DCB_ENABLED) &&
8719	    ((tx_flags & (IXGBE_TX_FLAGS_HW_VLAN | IXGBE_TX_FLAGS_SW_VLAN)) ||
8720	     (skb->priority != TC_PRIO_CONTROL))) {
8721		tx_flags &= ~IXGBE_TX_FLAGS_VLAN_PRIO_MASK;
8722		tx_flags |= (skb->priority & 0x7) <<
8723					IXGBE_TX_FLAGS_VLAN_PRIO_SHIFT;
8724		if (tx_flags & IXGBE_TX_FLAGS_SW_VLAN) {
8725			struct vlan_ethhdr *vhdr;
8726
8727			if (skb_cow_head(skb, 0))
8728				goto out_drop;
8729			vhdr = skb_vlan_eth_hdr(skb);
8730			vhdr->h_vlan_TCI = htons(tx_flags >>
8731						 IXGBE_TX_FLAGS_VLAN_SHIFT);
8732		} else {
8733			tx_flags |= IXGBE_TX_FLAGS_HW_VLAN;
8734		}
8735	}
8736
8737	/* record initial flags and protocol */
8738	first->tx_flags = tx_flags;
8739	first->protocol = protocol;
8740
8741#ifdef IXGBE_FCOE
8742	/* setup tx offload for FCoE */
8743	if ((protocol == htons(ETH_P_FCOE)) &&
8744	    (tx_ring->netdev->features & (NETIF_F_FSO | NETIF_F_FCOE_CRC))) {
8745		tso = ixgbe_fso(tx_ring, first, &hdr_len);
8746		if (tso < 0)
8747			goto out_drop;
8748
8749		goto xmit_fcoe;
8750	}
8751
8752#endif /* IXGBE_FCOE */
8753
8754#ifdef CONFIG_IXGBE_IPSEC
8755	if (xfrm_offload(skb) &&
8756	    !ixgbe_ipsec_tx(tx_ring, first, &ipsec_tx))
8757		goto out_drop;
8758#endif
8759	tso = ixgbe_tso(tx_ring, first, &hdr_len, &ipsec_tx);
8760	if (tso < 0)
8761		goto out_drop;
8762	else if (!tso)
8763		ixgbe_tx_csum(tx_ring, first, &ipsec_tx);
8764
8765	/* add the ATR filter if ATR is on */
8766	if (test_bit(__IXGBE_TX_FDIR_INIT_DONE, &tx_ring->state))
8767		ixgbe_atr(tx_ring, first);
8768
8769#ifdef IXGBE_FCOE
8770xmit_fcoe:
8771#endif /* IXGBE_FCOE */
8772	if (ixgbe_tx_map(tx_ring, first, hdr_len))
8773		goto cleanup_tx_timestamp;
8774
8775	return NETDEV_TX_OK;
8776
8777out_drop:
8778	dev_kfree_skb_any(first->skb);
8779	first->skb = NULL;
8780cleanup_tx_timestamp:
8781	if (unlikely(tx_flags & IXGBE_TX_FLAGS_TSTAMP)) {
8782		dev_kfree_skb_any(adapter->ptp_tx_skb);
8783		adapter->ptp_tx_skb = NULL;
8784		cancel_work_sync(&adapter->ptp_tx_work);
8785		clear_bit_unlock(__IXGBE_PTP_TX_IN_PROGRESS, &adapter->state);
8786	}
8787
8788	return NETDEV_TX_OK;
8789}
8790
8791static netdev_tx_t __ixgbe_xmit_frame(struct sk_buff *skb,
8792				      struct net_device *netdev,
8793				      struct ixgbe_ring *ring)
8794{
8795	struct ixgbe_adapter *adapter = netdev_priv(netdev);
8796	struct ixgbe_ring *tx_ring;
8797
8798	/*
8799	 * The minimum packet size for olinfo paylen is 17 so pad the skb
8800	 * in order to meet this minimum size requirement.
8801	 */
8802	if (skb_put_padto(skb, 17))
8803		return NETDEV_TX_OK;
8804
8805	tx_ring = ring ? ring : adapter->tx_ring[skb_get_queue_mapping(skb)];
8806	if (unlikely(test_bit(__IXGBE_TX_DISABLED, &tx_ring->state)))
8807		return NETDEV_TX_BUSY;
8808
8809	return ixgbe_xmit_frame_ring(skb, adapter, tx_ring);
8810}
8811
8812static netdev_tx_t ixgbe_xmit_frame(struct sk_buff *skb,
8813				    struct net_device *netdev)
8814{
8815	return __ixgbe_xmit_frame(skb, netdev, NULL);
8816}
8817
8818/**
8819 * ixgbe_set_mac - Change the Ethernet Address of the NIC
8820 * @netdev: network interface device structure
8821 * @p: pointer to an address structure
8822 *
8823 * Returns 0 on success, negative on failure
8824 **/
8825static int ixgbe_set_mac(struct net_device *netdev, void *p)
8826{
8827	struct ixgbe_adapter *adapter = netdev_priv(netdev);
8828	struct ixgbe_hw *hw = &adapter->hw;
8829	struct sockaddr *addr = p;
8830
8831	if (!is_valid_ether_addr(addr->sa_data))
8832		return -EADDRNOTAVAIL;
8833
8834	memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
8835	memcpy(hw->mac.addr, addr->sa_data, netdev->addr_len);
8836
8837	ixgbe_mac_set_default_filter(adapter);
8838
8839	return 0;
8840}
8841
8842static int
8843ixgbe_mdio_read(struct net_device *netdev, int prtad, int devad, u16 addr)
8844{
8845	struct ixgbe_adapter *adapter = netdev_priv(netdev);
8846	struct ixgbe_hw *hw = &adapter->hw;
8847	u16 value;
8848	int rc;
8849
8850	if (adapter->mii_bus) {
8851		int regnum = addr;
8852
8853		if (devad != MDIO_DEVAD_NONE)
8854			regnum |= (devad << 16) | MII_ADDR_C45;
8855
8856		return mdiobus_read(adapter->mii_bus, prtad, regnum);
8857	}
8858
8859	if (prtad != hw->phy.mdio.prtad)
8860		return -EINVAL;
8861	rc = hw->phy.ops.read_reg(hw, addr, devad, &value);
8862	if (!rc)
8863		rc = value;
8864	return rc;
8865}
8866
8867static int ixgbe_mdio_write(struct net_device *netdev, int prtad, int devad,
8868			    u16 addr, u16 value)
8869{
8870	struct ixgbe_adapter *adapter = netdev_priv(netdev);
8871	struct ixgbe_hw *hw = &adapter->hw;
8872
8873	if (adapter->mii_bus) {
8874		int regnum = addr;
8875
8876		if (devad != MDIO_DEVAD_NONE)
8877			regnum |= (devad << 16) | MII_ADDR_C45;
8878
8879		return mdiobus_write(adapter->mii_bus, prtad, regnum, value);
8880	}
8881
8882	if (prtad != hw->phy.mdio.prtad)
8883		return -EINVAL;
8884	return hw->phy.ops.write_reg(hw, addr, devad, value);
8885}
8886
8887static int ixgbe_ioctl(struct net_device *netdev, struct ifreq *req, int cmd)
8888{
8889	struct ixgbe_adapter *adapter = netdev_priv(netdev);
8890
8891	switch (cmd) {
8892	case SIOCSHWTSTAMP:
8893		return ixgbe_ptp_set_ts_config(adapter, req);
8894	case SIOCGHWTSTAMP:
8895		return ixgbe_ptp_get_ts_config(adapter, req);
8896	case SIOCGMIIPHY:
8897		if (!adapter->hw.phy.ops.read_reg)
8898			return -EOPNOTSUPP;
8899		fallthrough;
8900	default:
8901		return mdio_mii_ioctl(&adapter->hw.phy.mdio, if_mii(req), cmd);
8902	}
8903}
8904
8905/**
8906 * ixgbe_add_sanmac_netdev - Add the SAN MAC address to the corresponding
8907 * netdev->dev_addrs
8908 * @dev: network interface device structure
8909 *
8910 * Returns non-zero on failure
8911 **/
8912static int ixgbe_add_sanmac_netdev(struct net_device *dev)
8913{
8914	int err = 0;
8915	struct ixgbe_adapter *adapter = netdev_priv(dev);
8916	struct ixgbe_hw *hw = &adapter->hw;
8917
8918	if (is_valid_ether_addr(hw->mac.san_addr)) {
8919		rtnl_lock();
8920		err = dev_addr_add(dev, hw->mac.san_addr, NETDEV_HW_ADDR_T_SAN);
8921		rtnl_unlock();
8922
8923		/* update SAN MAC vmdq pool selection */
8924		hw->mac.ops.set_vmdq_san_mac(hw, VMDQ_P(0));
8925	}
8926	return err;
8927}
8928
8929/**
8930 * ixgbe_del_sanmac_netdev - Removes the SAN MAC address to the corresponding
8931 * netdev->dev_addrs
8932 * @dev: network interface device structure
8933 *
8934 * Returns non-zero on failure
8935 **/
8936static int ixgbe_del_sanmac_netdev(struct net_device *dev)
8937{
8938	int err = 0;
8939	struct ixgbe_adapter *adapter = netdev_priv(dev);
8940	struct ixgbe_mac_info *mac = &adapter->hw.mac;
8941
8942	if (is_valid_ether_addr(mac->san_addr)) {
8943		rtnl_lock();
8944		err = dev_addr_del(dev, mac->san_addr, NETDEV_HW_ADDR_T_SAN);
8945		rtnl_unlock();
8946	}
8947	return err;
8948}
8949
8950static void ixgbe_get_ring_stats64(struct rtnl_link_stats64 *stats,
8951				   struct ixgbe_ring *ring)
8952{
8953	u64 bytes, packets;
8954	unsigned int start;
8955
8956	if (ring) {
8957		do {
8958			start = u64_stats_fetch_begin_irq(&ring->syncp);
8959			packets = ring->stats.packets;
8960			bytes   = ring->stats.bytes;
8961		} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
8962		stats->tx_packets += packets;
8963		stats->tx_bytes   += bytes;
8964	}
8965}
8966
8967static void ixgbe_get_stats64(struct net_device *netdev,
8968			      struct rtnl_link_stats64 *stats)
8969{
8970	struct ixgbe_adapter *adapter = netdev_priv(netdev);
8971	int i;
8972
8973	rcu_read_lock();
8974	for (i = 0; i < adapter->num_rx_queues; i++) {
8975		struct ixgbe_ring *ring = READ_ONCE(adapter->rx_ring[i]);
8976		u64 bytes, packets;
8977		unsigned int start;
8978
8979		if (ring) {
8980			do {
8981				start = u64_stats_fetch_begin_irq(&ring->syncp);
8982				packets = ring->stats.packets;
8983				bytes   = ring->stats.bytes;
8984			} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
8985			stats->rx_packets += packets;
8986			stats->rx_bytes   += bytes;
8987		}
8988	}
8989
8990	for (i = 0; i < adapter->num_tx_queues; i++) {
8991		struct ixgbe_ring *ring = READ_ONCE(adapter->tx_ring[i]);
8992
8993		ixgbe_get_ring_stats64(stats, ring);
8994	}
8995	for (i = 0; i < adapter->num_xdp_queues; i++) {
8996		struct ixgbe_ring *ring = READ_ONCE(adapter->xdp_ring[i]);
8997
8998		ixgbe_get_ring_stats64(stats, ring);
8999	}
9000	rcu_read_unlock();
9001
9002	/* following stats updated by ixgbe_watchdog_task() */
9003	stats->multicast	= netdev->stats.multicast;
9004	stats->rx_errors	= netdev->stats.rx_errors;
9005	stats->rx_length_errors	= netdev->stats.rx_length_errors;
9006	stats->rx_crc_errors	= netdev->stats.rx_crc_errors;
9007	stats->rx_missed_errors	= netdev->stats.rx_missed_errors;
9008}
9009
9010#ifdef CONFIG_IXGBE_DCB
9011/**
9012 * ixgbe_validate_rtr - verify 802.1Qp to Rx packet buffer mapping is valid.
9013 * @adapter: pointer to ixgbe_adapter
9014 * @tc: number of traffic classes currently enabled
9015 *
9016 * Configure a valid 802.1Qp to Rx packet buffer mapping ie confirm
9017 * 802.1Q priority maps to a packet buffer that exists.
9018 */
9019static void ixgbe_validate_rtr(struct ixgbe_adapter *adapter, u8 tc)
9020{
9021	struct ixgbe_hw *hw = &adapter->hw;
9022	u32 reg, rsave;
9023	int i;
9024
9025	/* 82598 have a static priority to TC mapping that can not
9026	 * be changed so no validation is needed.
9027	 */
9028	if (hw->mac.type == ixgbe_mac_82598EB)
9029		return;
9030
9031	reg = IXGBE_READ_REG(hw, IXGBE_RTRUP2TC);
9032	rsave = reg;
9033
9034	for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
9035		u8 up2tc = reg >> (i * IXGBE_RTRUP2TC_UP_SHIFT);
9036
9037		/* If up2tc is out of bounds default to zero */
9038		if (up2tc > tc)
9039			reg &= ~(0x7 << IXGBE_RTRUP2TC_UP_SHIFT);
9040	}
9041
9042	if (reg != rsave)
9043		IXGBE_WRITE_REG(hw, IXGBE_RTRUP2TC, reg);
9044
9045	return;
9046}
9047
9048/**
9049 * ixgbe_set_prio_tc_map - Configure netdev prio tc map
9050 * @adapter: Pointer to adapter struct
9051 *
9052 * Populate the netdev user priority to tc map
9053 */
9054static void ixgbe_set_prio_tc_map(struct ixgbe_adapter *adapter)
9055{
9056	struct net_device *dev = adapter->netdev;
9057	struct ixgbe_dcb_config *dcb_cfg = &adapter->dcb_cfg;
9058	struct ieee_ets *ets = adapter->ixgbe_ieee_ets;
9059	u8 prio;
9060
9061	for (prio = 0; prio < MAX_USER_PRIORITY; prio++) {
9062		u8 tc = 0;
9063
9064		if (adapter->dcbx_cap & DCB_CAP_DCBX_VER_CEE)
9065			tc = ixgbe_dcb_get_tc_from_up(dcb_cfg, 0, prio);
9066		else if (ets)
9067			tc = ets->prio_tc[prio];
9068
9069		netdev_set_prio_tc_map(dev, prio, tc);
9070	}
9071}
9072
9073#endif /* CONFIG_IXGBE_DCB */
9074static int ixgbe_reassign_macvlan_pool(struct net_device *vdev,
9075				       struct netdev_nested_priv *priv)
9076{
9077	struct ixgbe_adapter *adapter = (struct ixgbe_adapter *)priv->data;
9078	struct ixgbe_fwd_adapter *accel;
9079	int pool;
9080
9081	/* we only care about macvlans... */
9082	if (!netif_is_macvlan(vdev))
9083		return 0;
9084
9085	/* that have hardware offload enabled... */
9086	accel = macvlan_accel_priv(vdev);
9087	if (!accel)
9088		return 0;
9089
9090	/* If we can relocate to a different bit do so */
9091	pool = find_first_zero_bit(adapter->fwd_bitmask, adapter->num_rx_pools);
9092	if (pool < adapter->num_rx_pools) {
9093		set_bit(pool, adapter->fwd_bitmask);
9094		accel->pool = pool;
9095		return 0;
9096	}
9097
9098	/* if we cannot find a free pool then disable the offload */
9099	netdev_err(vdev, "L2FW offload disabled due to lack of queue resources\n");
9100	macvlan_release_l2fw_offload(vdev);
9101
9102	/* unbind the queues and drop the subordinate channel config */
9103	netdev_unbind_sb_channel(adapter->netdev, vdev);
9104	netdev_set_sb_channel(vdev, 0);
9105
9106	kfree(accel);
9107
9108	return 0;
9109}
9110
9111static void ixgbe_defrag_macvlan_pools(struct net_device *dev)
9112{
9113	struct ixgbe_adapter *adapter = netdev_priv(dev);
9114	struct netdev_nested_priv priv = {
9115		.data = (void *)adapter,
9116	};
9117
9118	/* flush any stale bits out of the fwd bitmask */
9119	bitmap_clear(adapter->fwd_bitmask, 1, 63);
9120
9121	/* walk through upper devices reassigning pools */
9122	netdev_walk_all_upper_dev_rcu(dev, ixgbe_reassign_macvlan_pool,
9123				      &priv);
9124}
9125
9126/**
9127 * ixgbe_setup_tc - configure net_device for multiple traffic classes
9128 *
9129 * @dev: net device to configure
9130 * @tc: number of traffic classes to enable
9131 */
9132int ixgbe_setup_tc(struct net_device *dev, u8 tc)
9133{
9134	struct ixgbe_adapter *adapter = netdev_priv(dev);
9135	struct ixgbe_hw *hw = &adapter->hw;
9136
9137	/* Hardware supports up to 8 traffic classes */
9138	if (tc > adapter->dcb_cfg.num_tcs.pg_tcs)
9139		return -EINVAL;
9140
9141	if (hw->mac.type == ixgbe_mac_82598EB && tc && tc < MAX_TRAFFIC_CLASS)
9142		return -EINVAL;
9143
9144	/* Hardware has to reinitialize queues and interrupts to
9145	 * match packet buffer alignment. Unfortunately, the
9146	 * hardware is not flexible enough to do this dynamically.
9147	 */
9148	if (netif_running(dev))
9149		ixgbe_close(dev);
9150	else
9151		ixgbe_reset(adapter);
9152
9153	ixgbe_clear_interrupt_scheme(adapter);
9154
9155#ifdef CONFIG_IXGBE_DCB
9156	if (tc) {
9157		if (adapter->xdp_prog) {
9158			e_warn(probe, "DCB is not supported with XDP\n");
9159
9160			ixgbe_init_interrupt_scheme(adapter);
9161			if (netif_running(dev))
9162				ixgbe_open(dev);
9163			return -EINVAL;
9164		}
9165
9166		netdev_set_num_tc(dev, tc);
9167		ixgbe_set_prio_tc_map(adapter);
9168
9169		adapter->hw_tcs = tc;
9170		adapter->flags |= IXGBE_FLAG_DCB_ENABLED;
9171
9172		if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
9173			adapter->last_lfc_mode = adapter->hw.fc.requested_mode;
9174			adapter->hw.fc.requested_mode = ixgbe_fc_none;
9175		}
9176	} else {
9177		netdev_reset_tc(dev);
9178
9179		if (adapter->hw.mac.type == ixgbe_mac_82598EB)
9180			adapter->hw.fc.requested_mode = adapter->last_lfc_mode;
9181
9182		adapter->flags &= ~IXGBE_FLAG_DCB_ENABLED;
9183		adapter->hw_tcs = tc;
9184
9185		adapter->temp_dcb_cfg.pfc_mode_enable = false;
9186		adapter->dcb_cfg.pfc_mode_enable = false;
9187	}
9188
9189	ixgbe_validate_rtr(adapter, tc);
9190
9191#endif /* CONFIG_IXGBE_DCB */
9192	ixgbe_init_interrupt_scheme(adapter);
9193
9194	ixgbe_defrag_macvlan_pools(dev);
9195
9196	if (netif_running(dev))
9197		return ixgbe_open(dev);
9198
9199	return 0;
9200}
9201
9202static int ixgbe_delete_clsu32(struct ixgbe_adapter *adapter,
9203			       struct tc_cls_u32_offload *cls)
9204{
9205	u32 hdl = cls->knode.handle;
9206	u32 uhtid = TC_U32_USERHTID(cls->knode.handle);
9207	u32 loc = cls->knode.handle & 0xfffff;
9208	int err = 0, i, j;
9209	struct ixgbe_jump_table *jump = NULL;
9210
9211	if (loc > IXGBE_MAX_HW_ENTRIES)
9212		return -EINVAL;
9213
9214	if ((uhtid != 0x800) && (uhtid >= IXGBE_MAX_LINK_HANDLE))
9215		return -EINVAL;
9216
9217	/* Clear this filter in the link data it is associated with */
9218	if (uhtid != 0x800) {
9219		jump = adapter->jump_tables[uhtid];
9220		if (!jump)
9221			return -EINVAL;
9222		if (!test_bit(loc - 1, jump->child_loc_map))
9223			return -EINVAL;
9224		clear_bit(loc - 1, jump->child_loc_map);
9225	}
9226
9227	/* Check if the filter being deleted is a link */
9228	for (i = 1; i < IXGBE_MAX_LINK_HANDLE; i++) {
9229		jump = adapter->jump_tables[i];
9230		if (jump && jump->link_hdl == hdl) {
9231			/* Delete filters in the hardware in the child hash
9232			 * table associated with this link
9233			 */
9234			for (j = 0; j < IXGBE_MAX_HW_ENTRIES; j++) {
9235				if (!test_bit(j, jump->child_loc_map))
9236					continue;
9237				spin_lock(&adapter->fdir_perfect_lock);
9238				err = ixgbe_update_ethtool_fdir_entry(adapter,
9239								      NULL,
9240								      j + 1);
9241				spin_unlock(&adapter->fdir_perfect_lock);
9242				clear_bit(j, jump->child_loc_map);
9243			}
9244			/* Remove resources for this link */
9245			kfree(jump->input);
9246			kfree(jump->mask);
9247			kfree(jump);
9248			adapter->jump_tables[i] = NULL;
9249			return err;
9250		}
9251	}
9252
9253	spin_lock(&adapter->fdir_perfect_lock);
9254	err = ixgbe_update_ethtool_fdir_entry(adapter, NULL, loc);
9255	spin_unlock(&adapter->fdir_perfect_lock);
9256	return err;
9257}
9258
9259static int ixgbe_configure_clsu32_add_hnode(struct ixgbe_adapter *adapter,
9260					    struct tc_cls_u32_offload *cls)
9261{
9262	u32 uhtid = TC_U32_USERHTID(cls->hnode.handle);
9263
9264	if (uhtid >= IXGBE_MAX_LINK_HANDLE)
9265		return -EINVAL;
9266
9267	/* This ixgbe devices do not support hash tables at the moment
9268	 * so abort when given hash tables.
9269	 */
9270	if (cls->hnode.divisor > 0)
9271		return -EINVAL;
9272
9273	set_bit(uhtid - 1, &adapter->tables);
9274	return 0;
9275}
9276
9277static int ixgbe_configure_clsu32_del_hnode(struct ixgbe_adapter *adapter,
9278					    struct tc_cls_u32_offload *cls)
9279{
9280	u32 uhtid = TC_U32_USERHTID(cls->hnode.handle);
9281
9282	if (uhtid >= IXGBE_MAX_LINK_HANDLE)
9283		return -EINVAL;
9284
9285	clear_bit(uhtid - 1, &adapter->tables);
9286	return 0;
9287}
9288
9289#ifdef CONFIG_NET_CLS_ACT
9290struct upper_walk_data {
9291	struct ixgbe_adapter *adapter;
9292	u64 action;
9293	int ifindex;
9294	u8 queue;
9295};
9296
9297static int get_macvlan_queue(struct net_device *upper,
9298			     struct netdev_nested_priv *priv)
9299{
9300	if (netif_is_macvlan(upper)) {
9301		struct ixgbe_fwd_adapter *vadapter = macvlan_accel_priv(upper);
9302		struct ixgbe_adapter *adapter;
9303		struct upper_walk_data *data;
9304		int ifindex;
9305
9306		data = (struct upper_walk_data *)priv->data;
9307		ifindex = data->ifindex;
9308		adapter = data->adapter;
9309		if (vadapter && upper->ifindex == ifindex) {
9310			data->queue = adapter->rx_ring[vadapter->rx_base_queue]->reg_idx;
9311			data->action = data->queue;
9312			return 1;
9313		}
9314	}
9315
9316	return 0;
9317}
9318
9319static int handle_redirect_action(struct ixgbe_adapter *adapter, int ifindex,
9320				  u8 *queue, u64 *action)
9321{
9322	struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ];
9323	unsigned int num_vfs = adapter->num_vfs, vf;
9324	struct netdev_nested_priv priv;
9325	struct upper_walk_data data;
9326	struct net_device *upper;
9327
9328	/* redirect to a SRIOV VF */
9329	for (vf = 0; vf < num_vfs; ++vf) {
9330		upper = pci_get_drvdata(adapter->vfinfo[vf].vfdev);
9331		if (upper->ifindex == ifindex) {
9332			*queue = vf * __ALIGN_MASK(1, ~vmdq->mask);
9333			*action = vf + 1;
9334			*action <<= ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF;
9335			return 0;
9336		}
9337	}
9338
9339	/* redirect to a offloaded macvlan netdev */
9340	data.adapter = adapter;
9341	data.ifindex = ifindex;
9342	data.action = 0;
9343	data.queue = 0;
9344	priv.data = (void *)&data;
9345	if (netdev_walk_all_upper_dev_rcu(adapter->netdev,
9346					  get_macvlan_queue, &priv)) {
9347		*action = data.action;
9348		*queue = data.queue;
9349
9350		return 0;
9351	}
9352
9353	return -EINVAL;
9354}
9355
9356static int parse_tc_actions(struct ixgbe_adapter *adapter,
9357			    struct tcf_exts *exts, u64 *action, u8 *queue)
9358{
9359	const struct tc_action *a;
9360	int i;
9361
9362	if (!tcf_exts_has_actions(exts))
9363		return -EINVAL;
9364
9365	tcf_exts_for_each_action(i, a, exts) {
9366		/* Drop action */
9367		if (is_tcf_gact_shot(a)) {
9368			*action = IXGBE_FDIR_DROP_QUEUE;
9369			*queue = IXGBE_FDIR_DROP_QUEUE;
9370			return 0;
9371		}
9372
9373		/* Redirect to a VF or a offloaded macvlan */
9374		if (is_tcf_mirred_egress_redirect(a)) {
9375			struct net_device *dev = tcf_mirred_dev(a);
9376
9377			if (!dev)
9378				return -EINVAL;
9379			return handle_redirect_action(adapter, dev->ifindex,
9380						      queue, action);
9381		}
9382
9383		return -EINVAL;
9384	}
9385
9386	return -EINVAL;
9387}
9388#else
9389static int parse_tc_actions(struct ixgbe_adapter *adapter,
9390			    struct tcf_exts *exts, u64 *action, u8 *queue)
9391{
9392	return -EINVAL;
9393}
9394#endif /* CONFIG_NET_CLS_ACT */
9395
9396static int ixgbe_clsu32_build_input(struct ixgbe_fdir_filter *input,
9397				    union ixgbe_atr_input *mask,
9398				    struct tc_cls_u32_offload *cls,
9399				    struct ixgbe_mat_field *field_ptr,
9400				    struct ixgbe_nexthdr *nexthdr)
9401{
9402	int i, j, off;
9403	__be32 val, m;
9404	bool found_entry = false, found_jump_field = false;
9405
9406	for (i = 0; i < cls->knode.sel->nkeys; i++) {
9407		off = cls->knode.sel->keys[i].off;
9408		val = cls->knode.sel->keys[i].val;
9409		m = cls->knode.sel->keys[i].mask;
9410
9411		for (j = 0; field_ptr[j].val; j++) {
9412			if (field_ptr[j].off == off) {
9413				field_ptr[j].val(input, mask, (__force u32)val,
9414						 (__force u32)m);
9415				input->filter.formatted.flow_type |=
9416					field_ptr[j].type;
9417				found_entry = true;
9418				break;
9419			}
9420		}
9421		if (nexthdr) {
9422			if (nexthdr->off == cls->knode.sel->keys[i].off &&
9423			    nexthdr->val ==
9424			    (__force u32)cls->knode.sel->keys[i].val &&
9425			    nexthdr->mask ==
9426			    (__force u32)cls->knode.sel->keys[i].mask)
9427				found_jump_field = true;
9428			else
9429				continue;
9430		}
9431	}
9432
9433	if (nexthdr && !found_jump_field)
9434		return -EINVAL;
9435
9436	if (!found_entry)
9437		return 0;
9438
9439	mask->formatted.flow_type = IXGBE_ATR_L4TYPE_IPV6_MASK |
9440				    IXGBE_ATR_L4TYPE_MASK;
9441
9442	if (input->filter.formatted.flow_type == IXGBE_ATR_FLOW_TYPE_IPV4)
9443		mask->formatted.flow_type &= IXGBE_ATR_L4TYPE_IPV6_MASK;
9444
9445	return 0;
9446}
9447
9448static int ixgbe_configure_clsu32(struct ixgbe_adapter *adapter,
9449				  struct tc_cls_u32_offload *cls)
9450{
9451	__be16 protocol = cls->common.protocol;
9452	u32 loc = cls->knode.handle & 0xfffff;
9453	struct ixgbe_hw *hw = &adapter->hw;
9454	struct ixgbe_mat_field *field_ptr;
9455	struct ixgbe_fdir_filter *input = NULL;
9456	union ixgbe_atr_input *mask = NULL;
9457	struct ixgbe_jump_table *jump = NULL;
9458	int i, err = -EINVAL;
9459	u8 queue;
9460	u32 uhtid, link_uhtid;
9461
9462	uhtid = TC_U32_USERHTID(cls->knode.handle);
9463	link_uhtid = TC_U32_USERHTID(cls->knode.link_handle);
9464
9465	/* At the moment cls_u32 jumps to network layer and skips past
9466	 * L2 headers. The canonical method to match L2 frames is to use
9467	 * negative values. However this is error prone at best but really
9468	 * just broken because there is no way to "know" what sort of hdr
9469	 * is in front of the network layer. Fix cls_u32 to support L2
9470	 * headers when needed.
9471	 */
9472	if (protocol != htons(ETH_P_IP))
9473		return err;
9474
9475	if (loc >= ((1024 << adapter->fdir_pballoc) - 2)) {
9476		e_err(drv, "Location out of range\n");
9477		return err;
9478	}
9479
9480	/* cls u32 is a graph starting at root node 0x800. The driver tracks
9481	 * links and also the fields used to advance the parser across each
9482	 * link (e.g. nexthdr/eat parameters from 'tc'). This way we can map
9483	 * the u32 graph onto the hardware parse graph denoted in ixgbe_model.h
9484	 * To add support for new nodes update ixgbe_model.h parse structures
9485	 * this function _should_ be generic try not to hardcode values here.
9486	 */
9487	if (uhtid == 0x800) {
9488		field_ptr = (adapter->jump_tables[0])->mat;
9489	} else {
9490		if (uhtid >= IXGBE_MAX_LINK_HANDLE)
9491			return err;
9492		if (!adapter->jump_tables[uhtid])
9493			return err;
9494		field_ptr = (adapter->jump_tables[uhtid])->mat;
9495	}
9496
9497	if (!field_ptr)
9498		return err;
9499
9500	/* At this point we know the field_ptr is valid and need to either
9501	 * build cls_u32 link or attach filter. Because adding a link to
9502	 * a handle that does not exist is invalid and the same for adding
9503	 * rules to handles that don't exist.
9504	 */
9505
9506	if (link_uhtid) {
9507		struct ixgbe_nexthdr *nexthdr = ixgbe_ipv4_jumps;
9508
9509		if (link_uhtid >= IXGBE_MAX_LINK_HANDLE)
9510			return err;
9511
9512		if (!test_bit(link_uhtid - 1, &adapter->tables))
9513			return err;
9514
9515		/* Multiple filters as links to the same hash table are not
9516		 * supported. To add a new filter with the same next header
9517		 * but different match/jump conditions, create a new hash table
9518		 * and link to it.
9519		 */
9520		if (adapter->jump_tables[link_uhtid] &&
9521		    (adapter->jump_tables[link_uhtid])->link_hdl) {
9522			e_err(drv, "Link filter exists for link: %x\n",
9523			      link_uhtid);
9524			return err;
9525		}
9526
9527		for (i = 0; nexthdr[i].jump; i++) {
9528			if (nexthdr[i].o != cls->knode.sel->offoff ||
9529			    nexthdr[i].s != cls->knode.sel->offshift ||
9530			    nexthdr[i].m !=
9531			    (__force u32)cls->knode.sel->offmask)
9532				return err;
9533
9534			jump = kzalloc(sizeof(*jump), GFP_KERNEL);
9535			if (!jump)
9536				return -ENOMEM;
9537			input = kzalloc(sizeof(*input), GFP_KERNEL);
9538			if (!input) {
9539				err = -ENOMEM;
9540				goto free_jump;
9541			}
9542			mask = kzalloc(sizeof(*mask), GFP_KERNEL);
9543			if (!mask) {
9544				err = -ENOMEM;
9545				goto free_input;
9546			}
9547			jump->input = input;
9548			jump->mask = mask;
9549			jump->link_hdl = cls->knode.handle;
9550
9551			err = ixgbe_clsu32_build_input(input, mask, cls,
9552						       field_ptr, &nexthdr[i]);
9553			if (!err) {
9554				jump->mat = nexthdr[i].jump;
9555				adapter->jump_tables[link_uhtid] = jump;
9556				break;
9557			} else {
9558				kfree(mask);
9559				kfree(input);
9560				kfree(jump);
9561			}
9562		}
9563		return 0;
9564	}
9565
9566	input = kzalloc(sizeof(*input), GFP_KERNEL);
9567	if (!input)
9568		return -ENOMEM;
9569	mask = kzalloc(sizeof(*mask), GFP_KERNEL);
9570	if (!mask) {
9571		err = -ENOMEM;
9572		goto free_input;
9573	}
9574
9575	if ((uhtid != 0x800) && (adapter->jump_tables[uhtid])) {
9576		if ((adapter->jump_tables[uhtid])->input)
9577			memcpy(input, (adapter->jump_tables[uhtid])->input,
9578			       sizeof(*input));
9579		if ((adapter->jump_tables[uhtid])->mask)
9580			memcpy(mask, (adapter->jump_tables[uhtid])->mask,
9581			       sizeof(*mask));
9582
9583		/* Lookup in all child hash tables if this location is already
9584		 * filled with a filter
9585		 */
9586		for (i = 1; i < IXGBE_MAX_LINK_HANDLE; i++) {
9587			struct ixgbe_jump_table *link = adapter->jump_tables[i];
9588
9589			if (link && (test_bit(loc - 1, link->child_loc_map))) {
9590				e_err(drv, "Filter exists in location: %x\n",
9591				      loc);
9592				err = -EINVAL;
9593				goto err_out;
9594			}
9595		}
9596	}
9597	err = ixgbe_clsu32_build_input(input, mask, cls, field_ptr, NULL);
9598	if (err)
9599		goto err_out;
9600
9601	err = parse_tc_actions(adapter, cls->knode.exts, &input->action,
9602			       &queue);
9603	if (err < 0)
9604		goto err_out;
9605
9606	input->sw_idx = loc;
9607
9608	spin_lock(&adapter->fdir_perfect_lock);
9609
9610	if (hlist_empty(&adapter->fdir_filter_list)) {
9611		memcpy(&adapter->fdir_mask, mask, sizeof(*mask));
9612		err = ixgbe_fdir_set_input_mask_82599(hw, mask);
9613		if (err)
9614			goto err_out_w_lock;
9615	} else if (memcmp(&adapter->fdir_mask, mask, sizeof(*mask))) {
9616		err = -EINVAL;
9617		goto err_out_w_lock;
9618	}
9619
9620	ixgbe_atr_compute_perfect_hash_82599(&input->filter, mask);
9621	err = ixgbe_fdir_write_perfect_filter_82599(hw, &input->filter,
9622						    input->sw_idx, queue);
9623	if (err)
9624		goto err_out_w_lock;
9625
9626	ixgbe_update_ethtool_fdir_entry(adapter, input, input->sw_idx);
9627	spin_unlock(&adapter->fdir_perfect_lock);
9628
9629	if ((uhtid != 0x800) && (adapter->jump_tables[uhtid]))
9630		set_bit(loc - 1, (adapter->jump_tables[uhtid])->child_loc_map);
9631
9632	kfree(mask);
9633	return err;
9634err_out_w_lock:
9635	spin_unlock(&adapter->fdir_perfect_lock);
9636err_out:
9637	kfree(mask);
9638free_input:
9639	kfree(input);
9640free_jump:
9641	kfree(jump);
9642	return err;
9643}
9644
9645static int ixgbe_setup_tc_cls_u32(struct ixgbe_adapter *adapter,
9646				  struct tc_cls_u32_offload *cls_u32)
9647{
9648	switch (cls_u32->command) {
9649	case TC_CLSU32_NEW_KNODE:
9650	case TC_CLSU32_REPLACE_KNODE:
9651		return ixgbe_configure_clsu32(adapter, cls_u32);
9652	case TC_CLSU32_DELETE_KNODE:
9653		return ixgbe_delete_clsu32(adapter, cls_u32);
9654	case TC_CLSU32_NEW_HNODE:
9655	case TC_CLSU32_REPLACE_HNODE:
9656		return ixgbe_configure_clsu32_add_hnode(adapter, cls_u32);
9657	case TC_CLSU32_DELETE_HNODE:
9658		return ixgbe_configure_clsu32_del_hnode(adapter, cls_u32);
9659	default:
9660		return -EOPNOTSUPP;
9661	}
9662}
9663
9664static int ixgbe_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
9665				   void *cb_priv)
9666{
9667	struct ixgbe_adapter *adapter = cb_priv;
9668
9669	if (!tc_cls_can_offload_and_chain0(adapter->netdev, type_data))
9670		return -EOPNOTSUPP;
9671
9672	switch (type) {
9673	case TC_SETUP_CLSU32:
9674		return ixgbe_setup_tc_cls_u32(adapter, type_data);
9675	default:
9676		return -EOPNOTSUPP;
9677	}
9678}
9679
9680static int ixgbe_setup_tc_mqprio(struct net_device *dev,
9681				 struct tc_mqprio_qopt *mqprio)
9682{
9683	mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
9684	return ixgbe_setup_tc(dev, mqprio->num_tc);
9685}
9686
9687static LIST_HEAD(ixgbe_block_cb_list);
9688
9689static int __ixgbe_setup_tc(struct net_device *dev, enum tc_setup_type type,
9690			    void *type_data)
9691{
9692	struct ixgbe_adapter *adapter = netdev_priv(dev);
9693
9694	switch (type) {
9695	case TC_SETUP_BLOCK:
9696		return flow_block_cb_setup_simple(type_data,
9697						  &ixgbe_block_cb_list,
9698						  ixgbe_setup_tc_block_cb,
9699						  adapter, adapter, true);
9700	case TC_SETUP_QDISC_MQPRIO:
9701		return ixgbe_setup_tc_mqprio(dev, type_data);
9702	default:
9703		return -EOPNOTSUPP;
9704	}
9705}
9706
9707#ifdef CONFIG_PCI_IOV
9708void ixgbe_sriov_reinit(struct ixgbe_adapter *adapter)
9709{
9710	struct net_device *netdev = adapter->netdev;
9711
9712	rtnl_lock();
9713	ixgbe_setup_tc(netdev, adapter->hw_tcs);
9714	rtnl_unlock();
9715}
9716
9717#endif
9718void ixgbe_do_reset(struct net_device *netdev)
9719{
9720	struct ixgbe_adapter *adapter = netdev_priv(netdev);
9721
9722	if (netif_running(netdev))
9723		ixgbe_reinit_locked(adapter);
9724	else
9725		ixgbe_reset(adapter);
9726}
9727
9728static netdev_features_t ixgbe_fix_features(struct net_device *netdev,
9729					    netdev_features_t features)
9730{
9731	struct ixgbe_adapter *adapter = netdev_priv(netdev);
9732
9733	/* If Rx checksum is disabled, then RSC/LRO should also be disabled */
9734	if (!(features & NETIF_F_RXCSUM))
9735		features &= ~NETIF_F_LRO;
9736
9737	/* Turn off LRO if not RSC capable */
9738	if (!(adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE))
9739		features &= ~NETIF_F_LRO;
9740
9741	if (adapter->xdp_prog && (features & NETIF_F_LRO)) {
9742		e_dev_err("LRO is not supported with XDP\n");
9743		features &= ~NETIF_F_LRO;
9744	}
9745
9746	return features;
9747}
9748
9749static void ixgbe_reset_l2fw_offload(struct ixgbe_adapter *adapter)
9750{
9751	int rss = min_t(int, ixgbe_max_rss_indices(adapter),
9752			num_online_cpus());
9753
9754	/* go back to full RSS if we're not running SR-IOV */
9755	if (!adapter->ring_feature[RING_F_VMDQ].offset)
9756		adapter->flags &= ~(IXGBE_FLAG_VMDQ_ENABLED |
9757				    IXGBE_FLAG_SRIOV_ENABLED);
9758
9759	adapter->ring_feature[RING_F_RSS].limit = rss;
9760	adapter->ring_feature[RING_F_VMDQ].limit = 1;
9761
9762	ixgbe_setup_tc(adapter->netdev, adapter->hw_tcs);
9763}
9764
9765static int ixgbe_set_features(struct net_device *netdev,
9766			      netdev_features_t features)
9767{
9768	struct ixgbe_adapter *adapter = netdev_priv(netdev);
9769	netdev_features_t changed = netdev->features ^ features;
9770	bool need_reset = false;
9771
9772	/* Make sure RSC matches LRO, reset if change */
9773	if (!(features & NETIF_F_LRO)) {
9774		if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)
9775			need_reset = true;
9776		adapter->flags2 &= ~IXGBE_FLAG2_RSC_ENABLED;
9777	} else if ((adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE) &&
9778		   !(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)) {
9779		if (adapter->rx_itr_setting == 1 ||
9780		    adapter->rx_itr_setting > IXGBE_MIN_RSC_ITR) {
9781			adapter->flags2 |= IXGBE_FLAG2_RSC_ENABLED;
9782			need_reset = true;
9783		} else if ((changed ^ features) & NETIF_F_LRO) {
9784			e_info(probe, "rx-usecs set too low, "
9785			       "disabling RSC\n");
9786		}
9787	}
9788
9789	/*
9790	 * Check if Flow Director n-tuple support or hw_tc support was
9791	 * enabled or disabled.  If the state changed, we need to reset.
9792	 */
9793	if ((features & NETIF_F_NTUPLE) || (features & NETIF_F_HW_TC)) {
9794		/* turn off ATR, enable perfect filters and reset */
9795		if (!(adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE))
9796			need_reset = true;
9797
9798		adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE;
9799		adapter->flags |= IXGBE_FLAG_FDIR_PERFECT_CAPABLE;
9800	} else {
9801		/* turn off perfect filters, enable ATR and reset */
9802		if (adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE)
9803			need_reset = true;
9804
9805		adapter->flags &= ~IXGBE_FLAG_FDIR_PERFECT_CAPABLE;
9806
9807		/* We cannot enable ATR if SR-IOV is enabled */
9808		if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED ||
9809		    /* We cannot enable ATR if we have 2 or more tcs */
9810		    (adapter->hw_tcs > 1) ||
9811		    /* We cannot enable ATR if RSS is disabled */
9812		    (adapter->ring_feature[RING_F_RSS].limit <= 1) ||
9813		    /* A sample rate of 0 indicates ATR disabled */
9814		    (!adapter->atr_sample_rate))
9815			; /* do nothing not supported */
9816		else /* otherwise supported and set the flag */
9817			adapter->flags |= IXGBE_FLAG_FDIR_HASH_CAPABLE;
9818	}
9819
9820	if (changed & NETIF_F_RXALL)
9821		need_reset = true;
9822
9823	netdev->features = features;
9824
9825	if ((changed & NETIF_F_HW_L2FW_DOFFLOAD) && adapter->num_rx_pools > 1)
9826		ixgbe_reset_l2fw_offload(adapter);
9827	else if (need_reset)
9828		ixgbe_do_reset(netdev);
9829	else if (changed & (NETIF_F_HW_VLAN_CTAG_RX |
9830			    NETIF_F_HW_VLAN_CTAG_FILTER))
9831		ixgbe_set_rx_mode(netdev);
9832
9833	return 1;
9834}
9835
9836static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
9837			     struct net_device *dev,
9838			     const unsigned char *addr, u16 vid,
9839			     u16 flags,
9840			     struct netlink_ext_ack *extack)
9841{
9842	/* guarantee we can provide a unique filter for the unicast address */
9843	if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) {
9844		struct ixgbe_adapter *adapter = netdev_priv(dev);
9845		u16 pool = VMDQ_P(0);
9846
9847		if (netdev_uc_count(dev) >= ixgbe_available_rars(adapter, pool))
9848			return -ENOMEM;
9849	}
9850
9851	return ndo_dflt_fdb_add(ndm, tb, dev, addr, vid, flags);
9852}
9853
9854/**
9855 * ixgbe_configure_bridge_mode - set various bridge modes
9856 * @adapter: the private structure
9857 * @mode: requested bridge mode
9858 *
9859 * Configure some settings require for various bridge modes.
9860 **/
9861static int ixgbe_configure_bridge_mode(struct ixgbe_adapter *adapter,
9862				       __u16 mode)
9863{
9864	struct ixgbe_hw *hw = &adapter->hw;
9865	unsigned int p, num_pools;
9866	u32 vmdctl;
9867
9868	switch (mode) {
9869	case BRIDGE_MODE_VEPA:
9870		/* disable Tx loopback, rely on switch hairpin mode */
9871		IXGBE_WRITE_REG(&adapter->hw, IXGBE_PFDTXGSWC, 0);
9872
9873		/* must enable Rx switching replication to allow multicast
9874		 * packet reception on all VFs, and to enable source address
9875		 * pruning.
9876		 */
9877		vmdctl = IXGBE_READ_REG(hw, IXGBE_VMD_CTL);
9878		vmdctl |= IXGBE_VT_CTL_REPLEN;
9879		IXGBE_WRITE_REG(hw, IXGBE_VMD_CTL, vmdctl);
9880
9881		/* enable Rx source address pruning. Note, this requires
9882		 * replication to be enabled or else it does nothing.
9883		 */
9884		num_pools = adapter->num_vfs + adapter->num_rx_pools;
9885		for (p = 0; p < num_pools; p++) {
9886			if (hw->mac.ops.set_source_address_pruning)
9887				hw->mac.ops.set_source_address_pruning(hw,
9888								       true,
9889								       p);
9890		}
9891		break;
9892	case BRIDGE_MODE_VEB:
9893		/* enable Tx loopback for internal VF/PF communication */
9894		IXGBE_WRITE_REG(&adapter->hw, IXGBE_PFDTXGSWC,
9895				IXGBE_PFDTXGSWC_VT_LBEN);
9896
9897		/* disable Rx switching replication unless we have SR-IOV
9898		 * virtual functions
9899		 */
9900		vmdctl = IXGBE_READ_REG(hw, IXGBE_VMD_CTL);
9901		if (!adapter->num_vfs)
9902			vmdctl &= ~IXGBE_VT_CTL_REPLEN;
9903		IXGBE_WRITE_REG(hw, IXGBE_VMD_CTL, vmdctl);
9904
9905		/* disable Rx source address pruning, since we don't expect to
9906		 * be receiving external loopback of our transmitted frames.
9907		 */
9908		num_pools = adapter->num_vfs + adapter->num_rx_pools;
9909		for (p = 0; p < num_pools; p++) {
9910			if (hw->mac.ops.set_source_address_pruning)
9911				hw->mac.ops.set_source_address_pruning(hw,
9912								       false,
9913								       p);
9914		}
9915		break;
9916	default:
9917		return -EINVAL;
9918	}
9919
9920	adapter->bridge_mode = mode;
9921
9922	e_info(drv, "enabling bridge mode: %s\n",
9923	       mode == BRIDGE_MODE_VEPA ? "VEPA" : "VEB");
9924
9925	return 0;
9926}
9927
9928static int ixgbe_ndo_bridge_setlink(struct net_device *dev,
9929				    struct nlmsghdr *nlh, u16 flags,
9930				    struct netlink_ext_ack *extack)
9931{
9932	struct ixgbe_adapter *adapter = netdev_priv(dev);
9933	struct nlattr *attr, *br_spec;
9934	int rem;
9935
9936	if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED))
9937		return -EOPNOTSUPP;
9938
9939	br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
9940	if (!br_spec)
9941		return -EINVAL;
9942
9943	nla_for_each_nested(attr, br_spec, rem) {
9944		int status;
9945		__u16 mode;
9946
9947		if (nla_type(attr) != IFLA_BRIDGE_MODE)
9948			continue;
9949
9950		if (nla_len(attr) < sizeof(mode))
9951			return -EINVAL;
9952
9953		mode = nla_get_u16(attr);
9954		status = ixgbe_configure_bridge_mode(adapter, mode);
9955		if (status)
9956			return status;
9957
9958		break;
9959	}
9960
9961	return 0;
9962}
9963
9964static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
9965				    struct net_device *dev,
9966				    u32 filter_mask, int nlflags)
9967{
9968	struct ixgbe_adapter *adapter = netdev_priv(dev);
9969
9970	if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED))
9971		return 0;
9972
9973	return ndo_dflt_bridge_getlink(skb, pid, seq, dev,
9974				       adapter->bridge_mode, 0, 0, nlflags,
9975				       filter_mask, NULL);
9976}
9977
9978static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev)
9979{
9980	struct ixgbe_adapter *adapter = netdev_priv(pdev);
9981	struct ixgbe_fwd_adapter *accel;
9982	int tcs = adapter->hw_tcs ? : 1;
9983	int pool, err;
9984
9985	if (adapter->xdp_prog) {
9986		e_warn(probe, "L2FW offload is not supported with XDP\n");
9987		return ERR_PTR(-EINVAL);
9988	}
9989
9990	/* The hardware supported by ixgbe only filters on the destination MAC
9991	 * address. In order to avoid issues we only support offloading modes
9992	 * where the hardware can actually provide the functionality.
9993	 */
9994	if (!macvlan_supports_dest_filter(vdev))
9995		return ERR_PTR(-EMEDIUMTYPE);
9996
9997	/* We need to lock down the macvlan to be a single queue device so that
9998	 * we can reuse the tc_to_txq field in the macvlan netdev to represent
9999	 * the queue mapping to our netdev.
10000	 */
10001	if (netif_is_multiqueue(vdev))
10002		return ERR_PTR(-ERANGE);
10003
10004	pool = find_first_zero_bit(adapter->fwd_bitmask, adapter->num_rx_pools);
10005	if (pool == adapter->num_rx_pools) {
10006		u16 used_pools = adapter->num_vfs + adapter->num_rx_pools;
10007		u16 reserved_pools;
10008
10009		if (((adapter->flags & IXGBE_FLAG_DCB_ENABLED) &&
10010		     adapter->num_rx_pools >= (MAX_TX_QUEUES / tcs)) ||
10011		    adapter->num_rx_pools > IXGBE_MAX_MACVLANS)
10012			return ERR_PTR(-EBUSY);
10013
10014		/* Hardware has a limited number of available pools. Each VF,
10015		 * and the PF require a pool. Check to ensure we don't
10016		 * attempt to use more then the available number of pools.
10017		 */
10018		if (used_pools >= IXGBE_MAX_VF_FUNCTIONS)
10019			return ERR_PTR(-EBUSY);
10020
10021		/* Enable VMDq flag so device will be set in VM mode */
10022		adapter->flags |= IXGBE_FLAG_VMDQ_ENABLED |
10023				  IXGBE_FLAG_SRIOV_ENABLED;
10024
10025		/* Try to reserve as many queues per pool as possible,
10026		 * we start with the configurations that support 4 queues
10027		 * per pools, followed by 2, and then by just 1 per pool.
10028		 */
10029		if (used_pools < 32 && adapter->num_rx_pools < 16)
10030			reserved_pools = min_t(u16,
10031					       32 - used_pools,
10032					       16 - adapter->num_rx_pools);
10033		else if (adapter->num_rx_pools < 32)
10034			reserved_pools = min_t(u16,
10035					       64 - used_pools,
10036					       32 - adapter->num_rx_pools);
10037		else
10038			reserved_pools = 64 - used_pools;
10039
10040
10041		if (!reserved_pools)
10042			return ERR_PTR(-EBUSY);
10043
10044		adapter->ring_feature[RING_F_VMDQ].limit += reserved_pools;
10045
10046		/* Force reinit of ring allocation with VMDQ enabled */
10047		err = ixgbe_setup_tc(pdev, adapter->hw_tcs);
10048		if (err)
10049			return ERR_PTR(err);
10050
10051		if (pool >= adapter->num_rx_pools)
10052			return ERR_PTR(-ENOMEM);
10053	}
10054
10055	accel = kzalloc(sizeof(*accel), GFP_KERNEL);
10056	if (!accel)
10057		return ERR_PTR(-ENOMEM);
10058
10059	set_bit(pool, adapter->fwd_bitmask);
10060	netdev_set_sb_channel(vdev, pool);
10061	accel->pool = pool;
10062	accel->netdev = vdev;
10063
10064	if (!netif_running(pdev))
10065		return accel;
10066
10067	err = ixgbe_fwd_ring_up(adapter, accel);
10068	if (err)
10069		return ERR_PTR(err);
10070
10071	return accel;
10072}
10073
10074static void ixgbe_fwd_del(struct net_device *pdev, void *priv)
10075{
10076	struct ixgbe_fwd_adapter *accel = priv;
10077	struct ixgbe_adapter *adapter = netdev_priv(pdev);
10078	unsigned int rxbase = accel->rx_base_queue;
10079	unsigned int i;
10080
10081	/* delete unicast filter associated with offloaded interface */
10082	ixgbe_del_mac_filter(adapter, accel->netdev->dev_addr,
10083			     VMDQ_P(accel->pool));
10084
10085	/* Allow remaining Rx packets to get flushed out of the
10086	 * Rx FIFO before we drop the netdev for the ring.
10087	 */
10088	usleep_range(10000, 20000);
10089
10090	for (i = 0; i < adapter->num_rx_queues_per_pool; i++) {
10091		struct ixgbe_ring *ring = adapter->rx_ring[rxbase + i];
10092		struct ixgbe_q_vector *qv = ring->q_vector;
10093
10094		/* Make sure we aren't processing any packets and clear
10095		 * netdev to shut down the ring.
10096		 */
10097		if (netif_running(adapter->netdev))
10098			napi_synchronize(&qv->napi);
10099		ring->netdev = NULL;
10100	}
10101
10102	/* unbind the queues and drop the subordinate channel config */
10103	netdev_unbind_sb_channel(pdev, accel->netdev);
10104	netdev_set_sb_channel(accel->netdev, 0);
10105
10106	clear_bit(accel->pool, adapter->fwd_bitmask);
10107	kfree(accel);
10108}
10109
10110#define IXGBE_MAX_MAC_HDR_LEN		127
10111#define IXGBE_MAX_NETWORK_HDR_LEN	511
10112
10113static netdev_features_t
10114ixgbe_features_check(struct sk_buff *skb, struct net_device *dev,
10115		     netdev_features_t features)
10116{
10117	unsigned int network_hdr_len, mac_hdr_len;
10118
10119	/* Make certain the headers can be described by a context descriptor */
10120	mac_hdr_len = skb_network_header(skb) - skb->data;
10121	if (unlikely(mac_hdr_len > IXGBE_MAX_MAC_HDR_LEN))
10122		return features & ~(NETIF_F_HW_CSUM |
10123				    NETIF_F_SCTP_CRC |
10124				    NETIF_F_GSO_UDP_L4 |
10125				    NETIF_F_HW_VLAN_CTAG_TX |
10126				    NETIF_F_TSO |
10127				    NETIF_F_TSO6);
10128
10129	network_hdr_len = skb_checksum_start(skb) - skb_network_header(skb);
10130	if (unlikely(network_hdr_len >  IXGBE_MAX_NETWORK_HDR_LEN))
10131		return features & ~(NETIF_F_HW_CSUM |
10132				    NETIF_F_SCTP_CRC |
10133				    NETIF_F_GSO_UDP_L4 |
10134				    NETIF_F_TSO |
10135				    NETIF_F_TSO6);
10136
10137	/* We can only support IPV4 TSO in tunnels if we can mangle the
10138	 * inner IP ID field, so strip TSO if MANGLEID is not supported.
10139	 * IPsec offoad sets skb->encapsulation but still can handle
10140	 * the TSO, so it's the exception.
10141	 */
10142	if (skb->encapsulation && !(features & NETIF_F_TSO_MANGLEID)) {
10143#ifdef CONFIG_IXGBE_IPSEC
10144		if (!secpath_exists(skb))
10145#endif
10146			features &= ~NETIF_F_TSO;
10147	}
10148
10149	return features;
10150}
10151
10152static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
10153{
10154	int i, frame_size = dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
10155	struct ixgbe_adapter *adapter = netdev_priv(dev);
10156	struct bpf_prog *old_prog;
10157	bool need_reset;
10158	int num_queues;
10159
10160	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
10161		return -EINVAL;
10162
10163	if (adapter->flags & IXGBE_FLAG_DCB_ENABLED)
10164		return -EINVAL;
10165
10166	/* verify ixgbe ring attributes are sufficient for XDP */
10167	for (i = 0; i < adapter->num_rx_queues; i++) {
10168		struct ixgbe_ring *ring = adapter->rx_ring[i];
10169
10170		if (ring_is_rsc_enabled(ring))
10171			return -EINVAL;
10172
10173		if (frame_size > ixgbe_rx_bufsz(ring))
10174			return -EINVAL;
10175	}
10176
10177	if (nr_cpu_ids > MAX_XDP_QUEUES)
10178		return -ENOMEM;
10179
10180	old_prog = xchg(&adapter->xdp_prog, prog);
10181	need_reset = (!!prog != !!old_prog);
10182
10183	/* If transitioning XDP modes reconfigure rings */
10184	if (need_reset) {
10185		int err;
10186
10187		if (!prog)
10188			/* Wait until ndo_xsk_wakeup completes. */
10189			synchronize_rcu();
10190		err = ixgbe_setup_tc(dev, adapter->hw_tcs);
10191
10192		if (err) {
10193			rcu_assign_pointer(adapter->xdp_prog, old_prog);
10194			return -EINVAL;
10195		}
10196	} else {
10197		for (i = 0; i < adapter->num_rx_queues; i++)
10198			(void)xchg(&adapter->rx_ring[i]->xdp_prog,
10199			    adapter->xdp_prog);
10200	}
10201
10202	if (old_prog)
10203		bpf_prog_put(old_prog);
10204
10205	/* Kick start the NAPI context if there is an AF_XDP socket open
10206	 * on that queue id. This so that receiving will start.
10207	 */
10208	if (need_reset && prog) {
10209		num_queues = min_t(int, adapter->num_rx_queues,
10210				   adapter->num_xdp_queues);
10211		for (i = 0; i < num_queues; i++)
10212			if (adapter->xdp_ring[i]->xsk_pool)
10213				(void)ixgbe_xsk_wakeup(adapter->netdev, i,
10214						       XDP_WAKEUP_RX);
10215	}
10216
10217	return 0;
10218}
10219
10220static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp)
10221{
10222	struct ixgbe_adapter *adapter = netdev_priv(dev);
10223
10224	switch (xdp->command) {
10225	case XDP_SETUP_PROG:
10226		return ixgbe_xdp_setup(dev, xdp->prog);
10227	case XDP_SETUP_XSK_POOL:
10228		return ixgbe_xsk_pool_setup(adapter, xdp->xsk.pool,
10229					    xdp->xsk.queue_id);
10230
10231	default:
10232		return -EINVAL;
10233	}
10234}
10235
10236void ixgbe_xdp_ring_update_tail(struct ixgbe_ring *ring)
10237{
10238	/* Force memory writes to complete before letting h/w know there
10239	 * are new descriptors to fetch.
10240	 */
10241	wmb();
10242	writel(ring->next_to_use, ring->tail);
10243}
10244
10245static int ixgbe_xdp_xmit(struct net_device *dev, int n,
10246			  struct xdp_frame **frames, u32 flags)
10247{
10248	struct ixgbe_adapter *adapter = netdev_priv(dev);
10249	struct ixgbe_ring *ring;
10250	int drops = 0;
10251	int i;
10252
10253	if (unlikely(test_bit(__IXGBE_DOWN, &adapter->state)))
10254		return -ENETDOWN;
10255
10256	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
10257		return -EINVAL;
10258
10259	/* During program transitions its possible adapter->xdp_prog is assigned
10260	 * but ring has not been configured yet. In this case simply abort xmit.
10261	 */
10262	ring = adapter->xdp_prog ? adapter->xdp_ring[smp_processor_id()] : NULL;
10263	if (unlikely(!ring))
10264		return -ENXIO;
10265
10266	if (unlikely(test_bit(__IXGBE_TX_DISABLED, &ring->state)))
10267		return -ENXIO;
10268
10269	for (i = 0; i < n; i++) {
10270		struct xdp_frame *xdpf = frames[i];
10271		int err;
10272
10273		err = ixgbe_xmit_xdp_ring(adapter, xdpf);
10274		if (err != IXGBE_XDP_TX) {
10275			xdp_return_frame_rx_napi(xdpf);
10276			drops++;
10277		}
10278	}
10279
10280	if (unlikely(flags & XDP_XMIT_FLUSH))
10281		ixgbe_xdp_ring_update_tail(ring);
10282
10283	return n - drops;
10284}
10285
10286static const struct net_device_ops ixgbe_netdev_ops = {
10287	.ndo_open		= ixgbe_open,
10288	.ndo_stop		= ixgbe_close,
10289	.ndo_start_xmit		= ixgbe_xmit_frame,
10290	.ndo_set_rx_mode	= ixgbe_set_rx_mode,
10291	.ndo_validate_addr	= eth_validate_addr,
10292	.ndo_set_mac_address	= ixgbe_set_mac,
10293	.ndo_change_mtu		= ixgbe_change_mtu,
10294	.ndo_tx_timeout		= ixgbe_tx_timeout,
10295	.ndo_set_tx_maxrate	= ixgbe_tx_maxrate,
10296	.ndo_vlan_rx_add_vid	= ixgbe_vlan_rx_add_vid,
10297	.ndo_vlan_rx_kill_vid	= ixgbe_vlan_rx_kill_vid,
10298	.ndo_do_ioctl		= ixgbe_ioctl,
10299	.ndo_set_vf_mac		= ixgbe_ndo_set_vf_mac,
10300	.ndo_set_vf_vlan	= ixgbe_ndo_set_vf_vlan,
10301	.ndo_set_vf_rate	= ixgbe_ndo_set_vf_bw,
10302	.ndo_set_vf_spoofchk	= ixgbe_ndo_set_vf_spoofchk,
10303	.ndo_set_vf_link_state	= ixgbe_ndo_set_vf_link_state,
10304	.ndo_set_vf_rss_query_en = ixgbe_ndo_set_vf_rss_query_en,
10305	.ndo_set_vf_trust	= ixgbe_ndo_set_vf_trust,
10306	.ndo_get_vf_config	= ixgbe_ndo_get_vf_config,
10307	.ndo_get_stats64	= ixgbe_get_stats64,
10308	.ndo_setup_tc		= __ixgbe_setup_tc,
10309#ifdef IXGBE_FCOE
10310	.ndo_select_queue	= ixgbe_select_queue,
10311	.ndo_fcoe_ddp_setup = ixgbe_fcoe_ddp_get,
10312	.ndo_fcoe_ddp_target = ixgbe_fcoe_ddp_target,
10313	.ndo_fcoe_ddp_done = ixgbe_fcoe_ddp_put,
10314	.ndo_fcoe_enable = ixgbe_fcoe_enable,
10315	.ndo_fcoe_disable = ixgbe_fcoe_disable,
10316	.ndo_fcoe_get_wwn = ixgbe_fcoe_get_wwn,
10317	.ndo_fcoe_get_hbainfo = ixgbe_fcoe_get_hbainfo,
10318#endif /* IXGBE_FCOE */
10319	.ndo_set_features = ixgbe_set_features,
10320	.ndo_fix_features = ixgbe_fix_features,
10321	.ndo_fdb_add		= ixgbe_ndo_fdb_add,
10322	.ndo_bridge_setlink	= ixgbe_ndo_bridge_setlink,
10323	.ndo_bridge_getlink	= ixgbe_ndo_bridge_getlink,
10324	.ndo_dfwd_add_station	= ixgbe_fwd_add,
10325	.ndo_dfwd_del_station	= ixgbe_fwd_del,
10326	.ndo_udp_tunnel_add	= udp_tunnel_nic_add_port,
10327	.ndo_udp_tunnel_del	= udp_tunnel_nic_del_port,
10328	.ndo_features_check	= ixgbe_features_check,
10329	.ndo_bpf		= ixgbe_xdp,
10330	.ndo_xdp_xmit		= ixgbe_xdp_xmit,
10331	.ndo_xsk_wakeup         = ixgbe_xsk_wakeup,
10332};
10333
10334static void ixgbe_disable_txr_hw(struct ixgbe_adapter *adapter,
10335				 struct ixgbe_ring *tx_ring)
10336{
10337	unsigned long wait_delay, delay_interval;
10338	struct ixgbe_hw *hw = &adapter->hw;
10339	u8 reg_idx = tx_ring->reg_idx;
10340	int wait_loop;
10341	u32 txdctl;
10342
10343	IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH);
10344
10345	/* delay mechanism from ixgbe_disable_tx */
10346	delay_interval = ixgbe_get_completion_timeout(adapter) / 100;
10347
10348	wait_loop = IXGBE_MAX_RX_DESC_POLL;
10349	wait_delay = delay_interval;
10350
10351	while (wait_loop--) {
10352		usleep_range(wait_delay, wait_delay + 10);
10353		wait_delay += delay_interval * 2;
10354		txdctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(reg_idx));
10355
10356		if (!(txdctl & IXGBE_TXDCTL_ENABLE))
10357			return;
10358	}
10359
10360	e_err(drv, "TXDCTL.ENABLE not cleared within the polling period\n");
10361}
10362
10363static void ixgbe_disable_txr(struct ixgbe_adapter *adapter,
10364			      struct ixgbe_ring *tx_ring)
10365{
10366	set_bit(__IXGBE_TX_DISABLED, &tx_ring->state);
10367	ixgbe_disable_txr_hw(adapter, tx_ring);
10368}
10369
10370static void ixgbe_disable_rxr_hw(struct ixgbe_adapter *adapter,
10371				 struct ixgbe_ring *rx_ring)
10372{
10373	unsigned long wait_delay, delay_interval;
10374	struct ixgbe_hw *hw = &adapter->hw;
10375	u8 reg_idx = rx_ring->reg_idx;
10376	int wait_loop;
10377	u32 rxdctl;
10378
10379	rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
10380	rxdctl &= ~IXGBE_RXDCTL_ENABLE;
10381	rxdctl |= IXGBE_RXDCTL_SWFLSH;
10382
10383	/* write value back with RXDCTL.ENABLE bit cleared */
10384	IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl);
10385
10386	/* RXDCTL.EN may not change on 82598 if link is down, so skip it */
10387	if (hw->mac.type == ixgbe_mac_82598EB &&
10388	    !(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP))
10389		return;
10390
10391	/* delay mechanism from ixgbe_disable_rx */
10392	delay_interval = ixgbe_get_completion_timeout(adapter) / 100;
10393
10394	wait_loop = IXGBE_MAX_RX_DESC_POLL;
10395	wait_delay = delay_interval;
10396
10397	while (wait_loop--) {
10398		usleep_range(wait_delay, wait_delay + 10);
10399		wait_delay += delay_interval * 2;
10400		rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
10401
10402		if (!(rxdctl & IXGBE_RXDCTL_ENABLE))
10403			return;
10404	}
10405
10406	e_err(drv, "RXDCTL.ENABLE not cleared within the polling period\n");
10407}
10408
10409static void ixgbe_reset_txr_stats(struct ixgbe_ring *tx_ring)
10410{
10411	memset(&tx_ring->stats, 0, sizeof(tx_ring->stats));
10412	memset(&tx_ring->tx_stats, 0, sizeof(tx_ring->tx_stats));
10413}
10414
10415static void ixgbe_reset_rxr_stats(struct ixgbe_ring *rx_ring)
10416{
10417	memset(&rx_ring->stats, 0, sizeof(rx_ring->stats));
10418	memset(&rx_ring->rx_stats, 0, sizeof(rx_ring->rx_stats));
10419}
10420
10421/**
10422 * ixgbe_txrx_ring_disable - Disable Rx/Tx/XDP Tx rings
10423 * @adapter: adapter structure
10424 * @ring: ring index
10425 *
10426 * This function disables a certain Rx/Tx/XDP Tx ring. The function
10427 * assumes that the netdev is running.
10428 **/
10429void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring)
10430{
10431	struct ixgbe_ring *rx_ring, *tx_ring, *xdp_ring;
10432
10433	rx_ring = adapter->rx_ring[ring];
10434	tx_ring = adapter->tx_ring[ring];
10435	xdp_ring = adapter->xdp_ring[ring];
10436
10437	ixgbe_disable_txr(adapter, tx_ring);
10438	if (xdp_ring)
10439		ixgbe_disable_txr(adapter, xdp_ring);
10440	ixgbe_disable_rxr_hw(adapter, rx_ring);
10441
10442	if (xdp_ring)
10443		synchronize_rcu();
10444
10445	/* Rx/Tx/XDP Tx share the same napi context. */
10446	napi_disable(&rx_ring->q_vector->napi);
10447
10448	ixgbe_clean_tx_ring(tx_ring);
10449	if (xdp_ring)
10450		ixgbe_clean_tx_ring(xdp_ring);
10451	ixgbe_clean_rx_ring(rx_ring);
10452
10453	ixgbe_reset_txr_stats(tx_ring);
10454	if (xdp_ring)
10455		ixgbe_reset_txr_stats(xdp_ring);
10456	ixgbe_reset_rxr_stats(rx_ring);
10457}
10458
10459/**
10460 * ixgbe_txrx_ring_enable - Enable Rx/Tx/XDP Tx rings
10461 * @adapter: adapter structure
10462 * @ring: ring index
10463 *
10464 * This function enables a certain Rx/Tx/XDP Tx ring. The function
10465 * assumes that the netdev is running.
10466 **/
10467void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring)
10468{
10469	struct ixgbe_ring *rx_ring, *tx_ring, *xdp_ring;
10470
10471	rx_ring = adapter->rx_ring[ring];
10472	tx_ring = adapter->tx_ring[ring];
10473	xdp_ring = adapter->xdp_ring[ring];
10474
10475	/* Rx/Tx/XDP Tx share the same napi context. */
10476	napi_enable(&rx_ring->q_vector->napi);
10477
10478	ixgbe_configure_tx_ring(adapter, tx_ring);
10479	if (xdp_ring)
10480		ixgbe_configure_tx_ring(adapter, xdp_ring);
10481	ixgbe_configure_rx_ring(adapter, rx_ring);
10482
10483	clear_bit(__IXGBE_TX_DISABLED, &tx_ring->state);
10484	if (xdp_ring)
10485		clear_bit(__IXGBE_TX_DISABLED, &xdp_ring->state);
10486}
10487
10488/**
10489 * ixgbe_enumerate_functions - Get the number of ports this device has
10490 * @adapter: adapter structure
10491 *
10492 * This function enumerates the phsyical functions co-located on a single slot,
10493 * in order to determine how many ports a device has. This is most useful in
10494 * determining the required GT/s of PCIe bandwidth necessary for optimal
10495 * performance.
10496 **/
10497static inline int ixgbe_enumerate_functions(struct ixgbe_adapter *adapter)
10498{
10499	struct pci_dev *entry, *pdev = adapter->pdev;
10500	int physfns = 0;
10501
10502	/* Some cards can not use the generic count PCIe functions method,
10503	 * because they are behind a parent switch, so we hardcode these with
10504	 * the correct number of functions.
10505	 */
10506	if (ixgbe_pcie_from_parent(&adapter->hw))
10507		physfns = 4;
10508
10509	list_for_each_entry(entry, &adapter->pdev->bus->devices, bus_list) {
10510		/* don't count virtual functions */
10511		if (entry->is_virtfn)
10512			continue;
10513
10514		/* When the devices on the bus don't all match our device ID,
10515		 * we can't reliably determine the correct number of
10516		 * functions. This can occur if a function has been direct
10517		 * attached to a virtual machine using VT-d, for example. In
10518		 * this case, simply return -1 to indicate this.
10519		 */
10520		if ((entry->vendor != pdev->vendor) ||
10521		    (entry->device != pdev->device))
10522			return -1;
10523
10524		physfns++;
10525	}
10526
10527	return physfns;
10528}
10529
10530/**
10531 * ixgbe_wol_supported - Check whether device supports WoL
10532 * @adapter: the adapter private structure
10533 * @device_id: the device ID
10534 * @subdevice_id: the subsystem device ID
10535 *
10536 * This function is used by probe and ethtool to determine
10537 * which devices have WoL support
10538 *
10539 **/
10540bool ixgbe_wol_supported(struct ixgbe_adapter *adapter, u16 device_id,
10541			 u16 subdevice_id)
10542{
10543	struct ixgbe_hw *hw = &adapter->hw;
10544	u16 wol_cap = adapter->eeprom_cap & IXGBE_DEVICE_CAPS_WOL_MASK;
10545
10546	/* WOL not supported on 82598 */
10547	if (hw->mac.type == ixgbe_mac_82598EB)
10548		return false;
10549
10550	/* check eeprom to see if WOL is enabled for X540 and newer */
10551	if (hw->mac.type >= ixgbe_mac_X540) {
10552		if ((wol_cap == IXGBE_DEVICE_CAPS_WOL_PORT0_1) ||
10553		    ((wol_cap == IXGBE_DEVICE_CAPS_WOL_PORT0) &&
10554		     (hw->bus.func == 0)))
10555			return true;
10556	}
10557
10558	/* WOL is determined based on device IDs for 82599 MACs */
10559	switch (device_id) {
10560	case IXGBE_DEV_ID_82599_SFP:
10561		/* Only these subdevices could supports WOL */
10562		switch (subdevice_id) {
10563		case IXGBE_SUBDEV_ID_82599_560FLR:
10564		case IXGBE_SUBDEV_ID_82599_LOM_SNAP6:
10565		case IXGBE_SUBDEV_ID_82599_SFP_WOL0:
10566		case IXGBE_SUBDEV_ID_82599_SFP_2OCP:
10567			/* only support first port */
10568			if (hw->bus.func != 0)
10569				break;
10570			fallthrough;
10571		case IXGBE_SUBDEV_ID_82599_SP_560FLR:
10572		case IXGBE_SUBDEV_ID_82599_SFP:
10573		case IXGBE_SUBDEV_ID_82599_RNDC:
10574		case IXGBE_SUBDEV_ID_82599_ECNA_DP:
10575		case IXGBE_SUBDEV_ID_82599_SFP_1OCP:
10576		case IXGBE_SUBDEV_ID_82599_SFP_LOM_OEM1:
10577		case IXGBE_SUBDEV_ID_82599_SFP_LOM_OEM2:
10578			return true;
10579		}
10580		break;
10581	case IXGBE_DEV_ID_82599EN_SFP:
10582		/* Only these subdevices support WOL */
10583		switch (subdevice_id) {
10584		case IXGBE_SUBDEV_ID_82599EN_SFP_OCP1:
10585			return true;
10586		}
10587		break;
10588	case IXGBE_DEV_ID_82599_COMBO_BACKPLANE:
10589		/* All except this subdevice support WOL */
10590		if (subdevice_id != IXGBE_SUBDEV_ID_82599_KX4_KR_MEZZ)
10591			return true;
10592		break;
10593	case IXGBE_DEV_ID_82599_KX4:
10594		return  true;
10595	default:
10596		break;
10597	}
10598
10599	return false;
10600}
10601
10602/**
10603 * ixgbe_set_fw_version - Set FW version
10604 * @adapter: the adapter private structure
10605 *
10606 * This function is used by probe and ethtool to determine the FW version to
10607 * format to display. The FW version is taken from the EEPROM/NVM.
10608 */
10609static void ixgbe_set_fw_version(struct ixgbe_adapter *adapter)
10610{
10611	struct ixgbe_hw *hw = &adapter->hw;
10612	struct ixgbe_nvm_version nvm_ver;
10613
10614	ixgbe_get_oem_prod_version(hw, &nvm_ver);
10615	if (nvm_ver.oem_valid) {
10616		snprintf(adapter->eeprom_id, sizeof(adapter->eeprom_id),
10617			 "%x.%x.%x", nvm_ver.oem_major, nvm_ver.oem_minor,
10618			 nvm_ver.oem_release);
10619		return;
10620	}
10621
10622	ixgbe_get_etk_id(hw, &nvm_ver);
10623	ixgbe_get_orom_version(hw, &nvm_ver);
10624
10625	if (nvm_ver.or_valid) {
10626		snprintf(adapter->eeprom_id, sizeof(adapter->eeprom_id),
10627			 "0x%08x, %d.%d.%d", nvm_ver.etk_id, nvm_ver.or_major,
10628			 nvm_ver.or_build, nvm_ver.or_patch);
10629		return;
10630	}
10631
10632	/* Set ETrack ID format */
10633	snprintf(adapter->eeprom_id, sizeof(adapter->eeprom_id),
10634		 "0x%08x", nvm_ver.etk_id);
10635}
10636
10637/**
10638 * ixgbe_probe - Device Initialization Routine
10639 * @pdev: PCI device information struct
10640 * @ent: entry in ixgbe_pci_tbl
10641 *
10642 * Returns 0 on success, negative on failure
10643 *
10644 * ixgbe_probe initializes an adapter identified by a pci_dev structure.
10645 * The OS initialization, configuring of the adapter private structure,
10646 * and a hardware reset occur.
10647 **/
10648static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
10649{
10650	struct net_device *netdev;
10651	struct ixgbe_adapter *adapter = NULL;
10652	struct ixgbe_hw *hw;
10653	const struct ixgbe_info *ii = ixgbe_info_tbl[ent->driver_data];
10654	int i, err, pci_using_dac, expected_gts;
10655	unsigned int indices = MAX_TX_QUEUES;
10656	u8 part_str[IXGBE_PBANUM_LENGTH];
10657	bool disable_dev = false;
10658#ifdef IXGBE_FCOE
10659	u16 device_caps;
10660#endif
10661	u32 eec;
10662
10663	/* Catch broken hardware that put the wrong VF device ID in
10664	 * the PCIe SR-IOV capability.
10665	 */
10666	if (pdev->is_virtfn) {
10667		WARN(1, KERN_ERR "%s (%hx:%hx) should not be a VF!\n",
10668		     pci_name(pdev), pdev->vendor, pdev->device);
10669		return -EINVAL;
10670	}
10671
10672	err = pci_enable_device_mem(pdev);
10673	if (err)
10674		return err;
10675
10676	if (!dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) {
10677		pci_using_dac = 1;
10678	} else {
10679		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
10680		if (err) {
10681			dev_err(&pdev->dev,
10682				"No usable DMA configuration, aborting\n");
10683			goto err_dma;
10684		}
10685		pci_using_dac = 0;
10686	}
10687
10688	err = pci_request_mem_regions(pdev, ixgbe_driver_name);
10689	if (err) {
10690		dev_err(&pdev->dev,
10691			"pci_request_selected_regions failed 0x%x\n", err);
10692		goto err_pci_reg;
10693	}
10694
10695	pci_enable_pcie_error_reporting(pdev);
10696
10697	pci_set_master(pdev);
10698	pci_save_state(pdev);
10699
10700	if (ii->mac == ixgbe_mac_82598EB) {
10701#ifdef CONFIG_IXGBE_DCB
10702		/* 8 TC w/ 4 queues per TC */
10703		indices = 4 * MAX_TRAFFIC_CLASS;
10704#else
10705		indices = IXGBE_MAX_RSS_INDICES;
10706#endif
10707	}
10708
10709	netdev = alloc_etherdev_mq(sizeof(struct ixgbe_adapter), indices);
10710	if (!netdev) {
10711		err = -ENOMEM;
10712		goto err_alloc_etherdev;
10713	}
10714
10715	SET_NETDEV_DEV(netdev, &pdev->dev);
10716
10717	adapter = netdev_priv(netdev);
10718
10719	adapter->netdev = netdev;
10720	adapter->pdev = pdev;
10721	hw = &adapter->hw;
10722	hw->back = adapter;
10723	adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE);
10724
10725	hw->hw_addr = ioremap(pci_resource_start(pdev, 0),
10726			      pci_resource_len(pdev, 0));
10727	adapter->io_addr = hw->hw_addr;
10728	if (!hw->hw_addr) {
10729		err = -EIO;
10730		goto err_ioremap;
10731	}
10732
10733	netdev->netdev_ops = &ixgbe_netdev_ops;
10734	ixgbe_set_ethtool_ops(netdev);
10735	netdev->watchdog_timeo = 5 * HZ;
10736	strlcpy(netdev->name, pci_name(pdev), sizeof(netdev->name));
10737
10738	/* Setup hw api */
10739	hw->mac.ops   = *ii->mac_ops;
10740	hw->mac.type  = ii->mac;
10741	hw->mvals     = ii->mvals;
10742	if (ii->link_ops)
10743		hw->link.ops  = *ii->link_ops;
10744
10745	/* EEPROM */
10746	hw->eeprom.ops = *ii->eeprom_ops;
10747	eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw));
10748	if (ixgbe_removed(hw->hw_addr)) {
10749		err = -EIO;
10750		goto err_ioremap;
10751	}
10752	/* If EEPROM is valid (bit 8 = 1), use default otherwise use bit bang */
10753	if (!(eec & BIT(8)))
10754		hw->eeprom.ops.read = &ixgbe_read_eeprom_bit_bang_generic;
10755
10756	/* PHY */
10757	hw->phy.ops = *ii->phy_ops;
10758	hw->phy.sfp_type = ixgbe_sfp_type_unknown;
10759	/* ixgbe_identify_phy_generic will set prtad and mmds properly */
10760	hw->phy.mdio.prtad = MDIO_PRTAD_NONE;
10761	hw->phy.mdio.mmds = 0;
10762	hw->phy.mdio.mode_support = MDIO_SUPPORTS_C45 | MDIO_EMULATE_C22;
10763	hw->phy.mdio.dev = netdev;
10764	hw->phy.mdio.mdio_read = ixgbe_mdio_read;
10765	hw->phy.mdio.mdio_write = ixgbe_mdio_write;
10766
10767	/* setup the private structure */
10768	err = ixgbe_sw_init(adapter, ii);
10769	if (err)
10770		goto err_sw_init;
10771
10772	if (adapter->hw.mac.type == ixgbe_mac_82599EB)
10773		adapter->flags2 |= IXGBE_FLAG2_AUTO_DISABLE_VF;
10774
10775	switch (adapter->hw.mac.type) {
10776	case ixgbe_mac_X550:
10777	case ixgbe_mac_X550EM_x:
10778		netdev->udp_tunnel_nic_info = &ixgbe_udp_tunnels_x550;
10779		break;
10780	case ixgbe_mac_x550em_a:
10781		netdev->udp_tunnel_nic_info = &ixgbe_udp_tunnels_x550em_a;
10782		break;
10783	default:
10784		break;
10785	}
10786
10787	/* Make sure the SWFW semaphore is in a valid state */
10788	if (hw->mac.ops.init_swfw_sync)
10789		hw->mac.ops.init_swfw_sync(hw);
10790
10791	/* Make it possible the adapter to be woken up via WOL */
10792	switch (adapter->hw.mac.type) {
10793	case ixgbe_mac_82599EB:
10794	case ixgbe_mac_X540:
10795	case ixgbe_mac_X550:
10796	case ixgbe_mac_X550EM_x:
10797	case ixgbe_mac_x550em_a:
10798		IXGBE_WRITE_REG(&adapter->hw, IXGBE_WUS, ~0);
10799		break;
10800	default:
10801		break;
10802	}
10803
10804	/*
10805	 * If there is a fan on this device and it has failed log the
10806	 * failure.
10807	 */
10808	if (adapter->flags & IXGBE_FLAG_FAN_FAIL_CAPABLE) {
10809		u32 esdp = IXGBE_READ_REG(hw, IXGBE_ESDP);
10810		if (esdp & IXGBE_ESDP_SDP1)
10811			e_crit(probe, "Fan has stopped, replace the adapter\n");
10812	}
10813
10814	if (allow_unsupported_sfp)
10815		hw->allow_unsupported_sfp = allow_unsupported_sfp;
10816
10817	/* reset_hw fills in the perm_addr as well */
10818	hw->phy.reset_if_overtemp = true;
10819	err = hw->mac.ops.reset_hw(hw);
10820	hw->phy.reset_if_overtemp = false;
10821	ixgbe_set_eee_capable(adapter);
10822	if (err == -ENOENT) {
10823		err = 0;
10824	} else if (err == -EOPNOTSUPP) {
10825		e_dev_err("failed to load because an unsupported SFP+ or QSFP module type was detected.\n");
10826		e_dev_err("Reload the driver after installing a supported module.\n");
10827		goto err_sw_init;
10828	} else if (err) {
10829		e_dev_err("HW Init failed: %d\n", err);
10830		goto err_sw_init;
10831	}
10832
10833#ifdef CONFIG_PCI_IOV
10834	/* SR-IOV not supported on the 82598 */
10835	if (adapter->hw.mac.type == ixgbe_mac_82598EB)
10836		goto skip_sriov;
10837	/* Mailbox */
10838	ixgbe_init_mbx_params_pf(hw);
10839	hw->mbx.ops = ii->mbx_ops;
10840	pci_sriov_set_totalvfs(pdev, IXGBE_MAX_VFS_DRV_LIMIT);
10841	ixgbe_enable_sriov(adapter, max_vfs);
10842skip_sriov:
10843
10844#endif
10845	netdev->features = NETIF_F_SG |
10846			   NETIF_F_TSO |
10847			   NETIF_F_TSO6 |
10848			   NETIF_F_RXHASH |
10849			   NETIF_F_RXCSUM |
10850			   NETIF_F_HW_CSUM;
10851
10852#define IXGBE_GSO_PARTIAL_FEATURES (NETIF_F_GSO_GRE | \
10853				    NETIF_F_GSO_GRE_CSUM | \
10854				    NETIF_F_GSO_IPXIP4 | \
10855				    NETIF_F_GSO_IPXIP6 | \
10856				    NETIF_F_GSO_UDP_TUNNEL | \
10857				    NETIF_F_GSO_UDP_TUNNEL_CSUM)
10858
10859	netdev->gso_partial_features = IXGBE_GSO_PARTIAL_FEATURES;
10860	netdev->features |= NETIF_F_GSO_PARTIAL |
10861			    IXGBE_GSO_PARTIAL_FEATURES;
10862
10863	if (hw->mac.type >= ixgbe_mac_82599EB)
10864		netdev->features |= NETIF_F_SCTP_CRC | NETIF_F_GSO_UDP_L4;
10865
10866#ifdef CONFIG_IXGBE_IPSEC
10867#define IXGBE_ESP_FEATURES	(NETIF_F_HW_ESP | \
10868				 NETIF_F_HW_ESP_TX_CSUM | \
10869				 NETIF_F_GSO_ESP)
10870
10871	if (adapter->ipsec)
10872		netdev->features |= IXGBE_ESP_FEATURES;
10873#endif
10874	/* copy netdev features into list of user selectable features */
10875	netdev->hw_features |= netdev->features |
10876			       NETIF_F_HW_VLAN_CTAG_FILTER |
10877			       NETIF_F_HW_VLAN_CTAG_RX |
10878			       NETIF_F_HW_VLAN_CTAG_TX |
10879			       NETIF_F_RXALL |
10880			       NETIF_F_HW_L2FW_DOFFLOAD;
10881
10882	if (hw->mac.type >= ixgbe_mac_82599EB)
10883		netdev->hw_features |= NETIF_F_NTUPLE |
10884				       NETIF_F_HW_TC;
10885
10886	if (pci_using_dac)
10887		netdev->features |= NETIF_F_HIGHDMA;
10888
10889	netdev->vlan_features |= netdev->features | NETIF_F_TSO_MANGLEID;
10890	netdev->hw_enc_features |= netdev->vlan_features;
10891	netdev->mpls_features |= NETIF_F_SG |
10892				 NETIF_F_TSO |
10893				 NETIF_F_TSO6 |
10894				 NETIF_F_HW_CSUM;
10895	netdev->mpls_features |= IXGBE_GSO_PARTIAL_FEATURES;
10896
10897	/* set this bit last since it cannot be part of vlan_features */
10898	netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER |
10899			    NETIF_F_HW_VLAN_CTAG_RX |
10900			    NETIF_F_HW_VLAN_CTAG_TX;
10901
10902	netdev->priv_flags |= IFF_UNICAST_FLT;
10903	netdev->priv_flags |= IFF_SUPP_NOFCS;
10904
10905	/* MTU range: 68 - 9710 */
10906	netdev->min_mtu = ETH_MIN_MTU;
10907	netdev->max_mtu = IXGBE_MAX_JUMBO_FRAME_SIZE - (ETH_HLEN + ETH_FCS_LEN);
10908
10909#ifdef CONFIG_IXGBE_DCB
10910	if (adapter->flags & IXGBE_FLAG_DCB_CAPABLE)
10911		netdev->dcbnl_ops = &ixgbe_dcbnl_ops;
10912#endif
10913
10914#ifdef IXGBE_FCOE
10915	if (adapter->flags & IXGBE_FLAG_FCOE_CAPABLE) {
10916		unsigned int fcoe_l;
10917
10918		if (hw->mac.ops.get_device_caps) {
10919			hw->mac.ops.get_device_caps(hw, &device_caps);
10920			if (device_caps & IXGBE_DEVICE_CAPS_FCOE_OFFLOADS)
10921				adapter->flags &= ~IXGBE_FLAG_FCOE_CAPABLE;
10922		}
10923
10924
10925		fcoe_l = min_t(int, IXGBE_FCRETA_SIZE, num_online_cpus());
10926		adapter->ring_feature[RING_F_FCOE].limit = fcoe_l;
10927
10928		netdev->features |= NETIF_F_FSO |
10929				    NETIF_F_FCOE_CRC;
10930
10931		netdev->vlan_features |= NETIF_F_FSO |
10932					 NETIF_F_FCOE_CRC |
10933					 NETIF_F_FCOE_MTU;
10934	}
10935#endif /* IXGBE_FCOE */
10936	if (adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE)
10937		netdev->hw_features |= NETIF_F_LRO;
10938	if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)
10939		netdev->features |= NETIF_F_LRO;
10940
10941	if (ixgbe_check_fw_error(adapter)) {
10942		err = -EIO;
10943		goto err_sw_init;
10944	}
10945
10946	/* make sure the EEPROM is good */
10947	if (hw->eeprom.ops.validate_checksum(hw, NULL) < 0) {
10948		e_dev_err("The EEPROM Checksum Is Not Valid\n");
10949		err = -EIO;
10950		goto err_sw_init;
10951	}
10952
10953	eth_platform_get_mac_address(&adapter->pdev->dev,
10954				     adapter->hw.mac.perm_addr);
10955
10956	memcpy(netdev->dev_addr, hw->mac.perm_addr, netdev->addr_len);
10957
10958	if (!is_valid_ether_addr(netdev->dev_addr)) {
10959		e_dev_err("invalid MAC address\n");
10960		err = -EIO;
10961		goto err_sw_init;
10962	}
10963
10964	/* Set hw->mac.addr to permanent MAC address */
10965	ether_addr_copy(hw->mac.addr, hw->mac.perm_addr);
10966	ixgbe_mac_set_default_filter(adapter);
10967
10968	timer_setup(&adapter->service_timer, ixgbe_service_timer, 0);
10969
10970	if (ixgbe_removed(hw->hw_addr)) {
10971		err = -EIO;
10972		goto err_sw_init;
10973	}
10974	INIT_WORK(&adapter->service_task, ixgbe_service_task);
10975	set_bit(__IXGBE_SERVICE_INITED, &adapter->state);
10976	clear_bit(__IXGBE_SERVICE_SCHED, &adapter->state);
10977
10978	err = ixgbe_init_interrupt_scheme(adapter);
10979	if (err)
10980		goto err_sw_init;
10981
10982	for (i = 0; i < adapter->num_rx_queues; i++)
10983		u64_stats_init(&adapter->rx_ring[i]->syncp);
10984	for (i = 0; i < adapter->num_tx_queues; i++)
10985		u64_stats_init(&adapter->tx_ring[i]->syncp);
10986	for (i = 0; i < adapter->num_xdp_queues; i++)
10987		u64_stats_init(&adapter->xdp_ring[i]->syncp);
10988
10989	/* WOL not supported for all devices */
10990	adapter->wol = 0;
10991	hw->eeprom.ops.read(hw, 0x2c, &adapter->eeprom_cap);
10992	hw->wol_enabled = ixgbe_wol_supported(adapter, pdev->device,
10993						pdev->subsystem_device);
10994	if (hw->wol_enabled)
10995		adapter->wol = IXGBE_WUFC_MAG;
10996
10997	device_set_wakeup_enable(&adapter->pdev->dev, adapter->wol);
10998
10999	/* save off EEPROM version number */
11000	ixgbe_set_fw_version(adapter);
11001
11002	/* pick up the PCI bus settings for reporting later */
11003	if (ixgbe_pcie_from_parent(hw))
11004		ixgbe_get_parent_bus_info(adapter);
11005	else
11006		 hw->mac.ops.get_bus_info(hw);
11007
11008	/* calculate the expected PCIe bandwidth required for optimal
11009	 * performance. Note that some older parts will never have enough
11010	 * bandwidth due to being older generation PCIe parts. We clamp these
11011	 * parts to ensure no warning is displayed if it can't be fixed.
11012	 */
11013	switch (hw->mac.type) {
11014	case ixgbe_mac_82598EB:
11015		expected_gts = min(ixgbe_enumerate_functions(adapter) * 10, 16);
11016		break;
11017	default:
11018		expected_gts = ixgbe_enumerate_functions(adapter) * 10;
11019		break;
11020	}
11021
11022	/* don't check link if we failed to enumerate functions */
11023	if (expected_gts > 0)
11024		ixgbe_check_minimum_link(adapter, expected_gts);
11025
11026	err = ixgbe_read_pba_string_generic(hw, part_str, sizeof(part_str));
11027	if (err)
11028		strlcpy(part_str, "Unknown", sizeof(part_str));
11029	if (ixgbe_is_sfp(hw) && hw->phy.sfp_type != ixgbe_sfp_type_not_present)
11030		e_dev_info("MAC: %d, PHY: %d, SFP+: %d, PBA No: %s\n",
11031			   hw->mac.type, hw->phy.type, hw->phy.sfp_type,
11032			   part_str);
11033	else
11034		e_dev_info("MAC: %d, PHY: %d, PBA No: %s\n",
11035			   hw->mac.type, hw->phy.type, part_str);
11036
11037	e_dev_info("%pM\n", netdev->dev_addr);
11038
11039	/* reset the hardware with the new settings */
11040	err = hw->mac.ops.start_hw(hw);
11041	if (err == -EACCES) {
11042		/* We are running on a pre-production device, log a warning */
11043		e_dev_warn("This device is a pre-production adapter/LOM. "
11044			   "Please be aware there may be issues associated "
11045			   "with your hardware.  If you are experiencing "
11046			   "problems please contact your Intel or hardware "
11047			   "representative who provided you with this "
11048			   "hardware.\n");
11049	}
11050	strcpy(netdev->name, "eth%d");
11051	pci_set_drvdata(pdev, adapter);
11052	err = register_netdev(netdev);
11053	if (err)
11054		goto err_register;
11055
11056
11057	/* power down the optics for 82599 SFP+ fiber */
11058	if (hw->mac.ops.disable_tx_laser)
11059		hw->mac.ops.disable_tx_laser(hw);
11060
11061	/* carrier off reporting is important to ethtool even BEFORE open */
11062	netif_carrier_off(netdev);
11063
11064#ifdef CONFIG_IXGBE_DCA
11065	if (dca_add_requester(&pdev->dev) == 0) {
11066		adapter->flags |= IXGBE_FLAG_DCA_ENABLED;
11067		ixgbe_setup_dca(adapter);
11068	}
11069#endif
11070	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) {
11071		e_info(probe, "IOV is enabled with %d VFs\n", adapter->num_vfs);
11072		for (i = 0; i < adapter->num_vfs; i++)
11073			ixgbe_vf_configuration(pdev, (i | 0x10000000));
11074	}
11075
11076	/* firmware requires driver version to be 0xFFFFFFFF
11077	 * since os does not support feature
11078	 */
11079	if (hw->mac.ops.set_fw_drv_ver)
11080		hw->mac.ops.set_fw_drv_ver(hw, 0xFF, 0xFF, 0xFF, 0xFF,
11081					   sizeof(UTS_RELEASE) - 1,
11082					   UTS_RELEASE);
11083
11084	/* add san mac addr to netdev */
11085	ixgbe_add_sanmac_netdev(netdev);
11086
11087	e_dev_info("%s\n", ixgbe_default_device_descr);
11088
11089#ifdef CONFIG_IXGBE_HWMON
11090	if (ixgbe_sysfs_init(adapter))
11091		e_err(probe, "failed to allocate sysfs resources\n");
11092#endif /* CONFIG_IXGBE_HWMON */
11093
11094	ixgbe_dbg_adapter_init(adapter);
11095
11096	/* setup link for SFP devices with MNG FW, else wait for IXGBE_UP */
11097	if (ixgbe_mng_enabled(hw) && ixgbe_is_sfp(hw) && hw->mac.ops.setup_link)
11098		hw->mac.ops.setup_link(hw,
11099			IXGBE_LINK_SPEED_10GB_FULL | IXGBE_LINK_SPEED_1GB_FULL,
11100			true);
11101
11102	err = ixgbe_mii_bus_init(hw);
11103	if (err)
11104		goto err_netdev;
11105
11106	return 0;
11107
11108err_netdev:
11109	unregister_netdev(netdev);
11110err_register:
11111	ixgbe_release_hw_control(adapter);
11112	ixgbe_clear_interrupt_scheme(adapter);
11113err_sw_init:
11114	ixgbe_disable_sriov(adapter);
11115	adapter->flags2 &= ~IXGBE_FLAG2_SEARCH_FOR_SFP;
11116	iounmap(adapter->io_addr);
11117	kfree(adapter->jump_tables[0]);
11118	kfree(adapter->mac_table);
11119	kfree(adapter->rss_key);
11120	bitmap_free(adapter->af_xdp_zc_qps);
11121err_ioremap:
11122	disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state);
11123	free_netdev(netdev);
11124err_alloc_etherdev:
11125	pci_disable_pcie_error_reporting(pdev);
11126	pci_release_mem_regions(pdev);
11127err_pci_reg:
11128err_dma:
11129	if (!adapter || disable_dev)
11130		pci_disable_device(pdev);
11131	return err;
11132}
11133
11134/**
11135 * ixgbe_remove - Device Removal Routine
11136 * @pdev: PCI device information struct
11137 *
11138 * ixgbe_remove is called by the PCI subsystem to alert the driver
11139 * that it should release a PCI device.  The could be caused by a
11140 * Hot-Plug event, or because the driver is going to be removed from
11141 * memory.
11142 **/
11143static void ixgbe_remove(struct pci_dev *pdev)
11144{
11145	struct ixgbe_adapter *adapter = pci_get_drvdata(pdev);
11146	struct net_device *netdev;
11147	bool disable_dev;
11148	int i;
11149
11150	/* if !adapter then we already cleaned up in probe */
11151	if (!adapter)
11152		return;
11153
11154	netdev  = adapter->netdev;
11155	ixgbe_dbg_adapter_exit(adapter);
11156
11157	set_bit(__IXGBE_REMOVING, &adapter->state);
11158	cancel_work_sync(&adapter->service_task);
11159
11160	if (adapter->mii_bus)
11161		mdiobus_unregister(adapter->mii_bus);
11162
11163#ifdef CONFIG_IXGBE_DCA
11164	if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) {
11165		adapter->flags &= ~IXGBE_FLAG_DCA_ENABLED;
11166		dca_remove_requester(&pdev->dev);
11167		IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL,
11168				IXGBE_DCA_CTRL_DCA_DISABLE);
11169	}
11170
11171#endif
11172#ifdef CONFIG_IXGBE_HWMON
11173	ixgbe_sysfs_exit(adapter);
11174#endif /* CONFIG_IXGBE_HWMON */
11175
11176	/* remove the added san mac */
11177	ixgbe_del_sanmac_netdev(netdev);
11178
11179#ifdef CONFIG_PCI_IOV
11180	ixgbe_disable_sriov(adapter);
11181#endif
11182	if (netdev->reg_state == NETREG_REGISTERED)
11183		unregister_netdev(netdev);
11184
11185	ixgbe_stop_ipsec_offload(adapter);
11186	ixgbe_clear_interrupt_scheme(adapter);
11187
11188	ixgbe_release_hw_control(adapter);
11189
11190#ifdef CONFIG_DCB
11191	kfree(adapter->ixgbe_ieee_pfc);
11192	kfree(adapter->ixgbe_ieee_ets);
11193
11194#endif
11195	iounmap(adapter->io_addr);
11196	pci_release_mem_regions(pdev);
11197
11198	e_dev_info("complete\n");
11199
11200	for (i = 0; i < IXGBE_MAX_LINK_HANDLE; i++) {
11201		if (adapter->jump_tables[i]) {
11202			kfree(adapter->jump_tables[i]->input);
11203			kfree(adapter->jump_tables[i]->mask);
11204		}
11205		kfree(adapter->jump_tables[i]);
11206	}
11207
11208	kfree(adapter->mac_table);
11209	kfree(adapter->rss_key);
11210	bitmap_free(adapter->af_xdp_zc_qps);
11211	disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state);
11212	free_netdev(netdev);
11213
11214	pci_disable_pcie_error_reporting(pdev);
11215
11216	if (disable_dev)
11217		pci_disable_device(pdev);
11218}
11219
11220/**
11221 * ixgbe_io_error_detected - called when PCI error is detected
11222 * @pdev: Pointer to PCI device
11223 * @state: The current pci connection state
11224 *
11225 * This function is called after a PCI bus error affecting
11226 * this device has been detected.
11227 */
11228static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev,
11229						pci_channel_state_t state)
11230{
11231	struct ixgbe_adapter *adapter = pci_get_drvdata(pdev);
11232	struct net_device *netdev = adapter->netdev;
11233
11234#ifdef CONFIG_PCI_IOV
11235	struct ixgbe_hw *hw = &adapter->hw;
11236	struct pci_dev *bdev, *vfdev;
11237	u32 dw0, dw1, dw2, dw3;
11238	int vf, pos;
11239	u16 req_id, pf_func;
11240
11241	if (adapter->hw.mac.type == ixgbe_mac_82598EB ||
11242	    adapter->num_vfs == 0)
11243		goto skip_bad_vf_detection;
11244
11245	bdev = pdev->bus->self;
11246	while (bdev && (pci_pcie_type(bdev) != PCI_EXP_TYPE_ROOT_PORT))
11247		bdev = bdev->bus->self;
11248
11249	if (!bdev)
11250		goto skip_bad_vf_detection;
11251
11252	pos = pci_find_ext_capability(bdev, PCI_EXT_CAP_ID_ERR);
11253	if (!pos)
11254		goto skip_bad_vf_detection;
11255
11256	dw0 = ixgbe_read_pci_cfg_dword(hw, pos + PCI_ERR_HEADER_LOG);
11257	dw1 = ixgbe_read_pci_cfg_dword(hw, pos + PCI_ERR_HEADER_LOG + 4);
11258	dw2 = ixgbe_read_pci_cfg_dword(hw, pos + PCI_ERR_HEADER_LOG + 8);
11259	dw3 = ixgbe_read_pci_cfg_dword(hw, pos + PCI_ERR_HEADER_LOG + 12);
11260	if (ixgbe_removed(hw->hw_addr))
11261		goto skip_bad_vf_detection;
11262
11263	req_id = dw1 >> 16;
11264	/* On the 82599 if bit 7 of the requestor ID is set then it's a VF */
11265	if (!(req_id & 0x0080))
11266		goto skip_bad_vf_detection;
11267
11268	pf_func = req_id & 0x01;
11269	if ((pf_func & 1) == (pdev->devfn & 1)) {
11270		unsigned int device_id;
11271
11272		vf = (req_id & 0x7F) >> 1;
11273		e_dev_err("VF %d has caused a PCIe error\n", vf);
11274		e_dev_err("TLP: dw0: %8.8x\tdw1: %8.8x\tdw2: "
11275				"%8.8x\tdw3: %8.8x\n",
11276		dw0, dw1, dw2, dw3);
11277		switch (adapter->hw.mac.type) {
11278		case ixgbe_mac_82599EB:
11279			device_id = IXGBE_82599_VF_DEVICE_ID;
11280			break;
11281		case ixgbe_mac_X540:
11282			device_id = IXGBE_X540_VF_DEVICE_ID;
11283			break;
11284		case ixgbe_mac_X550:
11285			device_id = IXGBE_DEV_ID_X550_VF;
11286			break;
11287		case ixgbe_mac_X550EM_x:
11288			device_id = IXGBE_DEV_ID_X550EM_X_VF;
11289			break;
11290		case ixgbe_mac_x550em_a:
11291			device_id = IXGBE_DEV_ID_X550EM_A_VF;
11292			break;
11293		default:
11294			device_id = 0;
11295			break;
11296		}
11297
11298		/* Find the pci device of the offending VF */
11299		vfdev = pci_get_device(PCI_VENDOR_ID_INTEL, device_id, NULL);
11300		while (vfdev) {
11301			if (vfdev->devfn == (req_id & 0xFF))
11302				break;
11303			vfdev = pci_get_device(PCI_VENDOR_ID_INTEL,
11304					       device_id, vfdev);
11305		}
11306		/*
11307		 * There's a slim chance the VF could have been hot plugged,
11308		 * so if it is no longer present we don't need to issue the
11309		 * VFLR.  Just clean up the AER in that case.
11310		 */
11311		if (vfdev) {
11312			pcie_flr(vfdev);
11313			/* Free device reference count */
11314			pci_dev_put(vfdev);
11315		}
11316	}
11317
11318	/*
11319	 * Even though the error may have occurred on the other port
11320	 * we still need to increment the vf error reference count for
11321	 * both ports because the I/O resume function will be called
11322	 * for both of them.
11323	 */
11324	adapter->vferr_refcount++;
11325
11326	return PCI_ERS_RESULT_RECOVERED;
11327
11328skip_bad_vf_detection:
11329#endif /* CONFIG_PCI_IOV */
11330	if (!test_bit(__IXGBE_SERVICE_INITED, &adapter->state))
11331		return PCI_ERS_RESULT_DISCONNECT;
11332
11333	if (!netif_device_present(netdev))
11334		return PCI_ERS_RESULT_DISCONNECT;
11335
11336	rtnl_lock();
11337	netif_device_detach(netdev);
11338
11339	if (netif_running(netdev))
11340		ixgbe_close_suspend(adapter);
11341
11342	if (state == pci_channel_io_perm_failure) {
11343		rtnl_unlock();
11344		return PCI_ERS_RESULT_DISCONNECT;
11345	}
11346
11347	if (!test_and_set_bit(__IXGBE_DISABLED, &adapter->state))
11348		pci_disable_device(pdev);
11349	rtnl_unlock();
11350
11351	/* Request a slot reset. */
11352	return PCI_ERS_RESULT_NEED_RESET;
11353}
11354
11355/**
11356 * ixgbe_io_slot_reset - called after the pci bus has been reset.
11357 * @pdev: Pointer to PCI device
11358 *
11359 * Restart the card from scratch, as if from a cold-boot.
11360 */
11361static pci_ers_result_t ixgbe_io_slot_reset(struct pci_dev *pdev)
11362{
11363	struct ixgbe_adapter *adapter = pci_get_drvdata(pdev);
11364	pci_ers_result_t result;
11365
11366	if (pci_enable_device_mem(pdev)) {
11367		e_err(probe, "Cannot re-enable PCI device after reset.\n");
11368		result = PCI_ERS_RESULT_DISCONNECT;
11369	} else {
11370		smp_mb__before_atomic();
11371		clear_bit(__IXGBE_DISABLED, &adapter->state);
11372		adapter->hw.hw_addr = adapter->io_addr;
11373		pci_set_master(pdev);
11374		pci_restore_state(pdev);
11375		pci_save_state(pdev);
11376
11377		pci_wake_from_d3(pdev, false);
11378
11379		ixgbe_reset(adapter);
11380		IXGBE_WRITE_REG(&adapter->hw, IXGBE_WUS, ~0);
11381		result = PCI_ERS_RESULT_RECOVERED;
11382	}
11383
11384	return result;
11385}
11386
11387/**
11388 * ixgbe_io_resume - called when traffic can start flowing again.
11389 * @pdev: Pointer to PCI device
11390 *
11391 * This callback is called when the error recovery driver tells us that
11392 * its OK to resume normal operation.
11393 */
11394static void ixgbe_io_resume(struct pci_dev *pdev)
11395{
11396	struct ixgbe_adapter *adapter = pci_get_drvdata(pdev);
11397	struct net_device *netdev = adapter->netdev;
11398
11399#ifdef CONFIG_PCI_IOV
11400	if (adapter->vferr_refcount) {
11401		e_info(drv, "Resuming after VF err\n");
11402		adapter->vferr_refcount--;
11403		return;
11404	}
11405
11406#endif
11407	rtnl_lock();
11408	if (netif_running(netdev))
11409		ixgbe_open(netdev);
11410
11411	netif_device_attach(netdev);
11412	rtnl_unlock();
11413}
11414
11415static const struct pci_error_handlers ixgbe_err_handler = {
11416	.error_detected = ixgbe_io_error_detected,
11417	.slot_reset = ixgbe_io_slot_reset,
11418	.resume = ixgbe_io_resume,
11419};
11420
11421static SIMPLE_DEV_PM_OPS(ixgbe_pm_ops, ixgbe_suspend, ixgbe_resume);
11422
11423static struct pci_driver ixgbe_driver = {
11424	.name      = ixgbe_driver_name,
11425	.id_table  = ixgbe_pci_tbl,
11426	.probe     = ixgbe_probe,
11427	.remove    = ixgbe_remove,
11428	.driver.pm = &ixgbe_pm_ops,
11429	.shutdown  = ixgbe_shutdown,
11430	.sriov_configure = ixgbe_pci_sriov_configure,
11431	.err_handler = &ixgbe_err_handler
11432};
11433
11434/**
11435 * ixgbe_init_module - Driver Registration Routine
11436 *
11437 * ixgbe_init_module is the first routine called when the driver is
11438 * loaded. All it does is register with the PCI subsystem.
11439 **/
11440static int __init ixgbe_init_module(void)
11441{
11442	int ret;
11443	pr_info("%s\n", ixgbe_driver_string);
11444	pr_info("%s\n", ixgbe_copyright);
11445
11446	ixgbe_wq = create_singlethread_workqueue(ixgbe_driver_name);
11447	if (!ixgbe_wq) {
11448		pr_err("%s: Failed to create workqueue\n", ixgbe_driver_name);
11449		return -ENOMEM;
11450	}
11451
11452	ixgbe_dbg_init();
11453
11454	ret = pci_register_driver(&ixgbe_driver);
11455	if (ret) {
11456		destroy_workqueue(ixgbe_wq);
11457		ixgbe_dbg_exit();
11458		return ret;
11459	}
11460
11461#ifdef CONFIG_IXGBE_DCA
11462	dca_register_notify(&dca_notifier);
11463#endif
11464
11465	return 0;
11466}
11467
11468module_init(ixgbe_init_module);
11469
11470/**
11471 * ixgbe_exit_module - Driver Exit Cleanup Routine
11472 *
11473 * ixgbe_exit_module is called just before the driver is removed
11474 * from memory.
11475 **/
11476static void __exit ixgbe_exit_module(void)
11477{
11478#ifdef CONFIG_IXGBE_DCA
11479	dca_unregister_notify(&dca_notifier);
11480#endif
11481	pci_unregister_driver(&ixgbe_driver);
11482
11483	ixgbe_dbg_exit();
11484	if (ixgbe_wq) {
11485		destroy_workqueue(ixgbe_wq);
11486		ixgbe_wq = NULL;
11487	}
11488}
11489
11490#ifdef CONFIG_IXGBE_DCA
11491static int ixgbe_notify_dca(struct notifier_block *nb, unsigned long event,
11492			    void *p)
11493{
11494	int ret_val;
11495
11496	ret_val = driver_for_each_device(&ixgbe_driver.driver, NULL, &event,
11497					 __ixgbe_notify_dca);
11498
11499	return ret_val ? NOTIFY_BAD : NOTIFY_DONE;
11500}
11501
11502#endif /* CONFIG_IXGBE_DCA */
11503
11504module_exit(ixgbe_exit_module);
11505
11506/* ixgbe_main.c */
11507