1// SPDX-License-Identifier: GPL-2.0
2
3#define pr_fmt(fmt)     "DMAR-IR: " fmt
4
5#include <linux/interrupt.h>
6#include <linux/dmar.h>
7#include <linux/spinlock.h>
8#include <linux/slab.h>
9#include <linux/jiffies.h>
10#include <linux/hpet.h>
11#include <linux/pci.h>
12#include <linux/irq.h>
13#include <linux/intel-iommu.h>
14#include <linux/acpi.h>
15#include <linux/irqdomain.h>
16#include <linux/crash_dump.h>
17#include <asm/io_apic.h>
18#include <asm/apic.h>
19#include <asm/smp.h>
20#include <asm/cpu.h>
21#include <asm/irq_remapping.h>
22#include <asm/pci-direct.h>
23#include <asm/msidef.h>
24
25#include "../irq_remapping.h"
26
27enum irq_mode {
28	IRQ_REMAPPING,
29	IRQ_POSTING,
30};
31
32struct ioapic_scope {
33	struct intel_iommu *iommu;
34	unsigned int id;
35	unsigned int bus;	/* PCI bus number */
36	unsigned int devfn;	/* PCI devfn number */
37};
38
39struct hpet_scope {
40	struct intel_iommu *iommu;
41	u8 id;
42	unsigned int bus;
43	unsigned int devfn;
44};
45
46struct irq_2_iommu {
47	struct intel_iommu *iommu;
48	u16 irte_index;
49	u16 sub_handle;
50	u8  irte_mask;
51	enum irq_mode mode;
52};
53
54struct intel_ir_data {
55	struct irq_2_iommu			irq_2_iommu;
56	struct irte				irte_entry;
57	union {
58		struct msi_msg			msi_entry;
59	};
60};
61
62#define IR_X2APIC_MODE(mode) (mode ? (1 << 11) : 0)
63#define IRTE_DEST(dest) ((eim_mode) ? dest : dest << 8)
64
65static int __read_mostly eim_mode;
66static struct ioapic_scope ir_ioapic[MAX_IO_APICS];
67static struct hpet_scope ir_hpet[MAX_HPET_TBS];
68
69/*
70 * Lock ordering:
71 * ->dmar_global_lock
72 *	->irq_2_ir_lock
73 *		->qi->q_lock
74 *	->iommu->register_lock
75 * Note:
76 * intel_irq_remap_ops.{supported,prepare,enable,disable,reenable} are called
77 * in single-threaded environment with interrupt disabled, so no need to tabke
78 * the dmar_global_lock.
79 */
80DEFINE_RAW_SPINLOCK(irq_2_ir_lock);
81static const struct irq_domain_ops intel_ir_domain_ops;
82
83static void iommu_disable_irq_remapping(struct intel_iommu *iommu);
84static int __init parse_ioapics_under_ir(void);
85
86static bool ir_pre_enabled(struct intel_iommu *iommu)
87{
88	return (iommu->flags & VTD_FLAG_IRQ_REMAP_PRE_ENABLED);
89}
90
91static void clear_ir_pre_enabled(struct intel_iommu *iommu)
92{
93	iommu->flags &= ~VTD_FLAG_IRQ_REMAP_PRE_ENABLED;
94}
95
96static void init_ir_status(struct intel_iommu *iommu)
97{
98	u32 gsts;
99
100	gsts = readl(iommu->reg + DMAR_GSTS_REG);
101	if (gsts & DMA_GSTS_IRES)
102		iommu->flags |= VTD_FLAG_IRQ_REMAP_PRE_ENABLED;
103}
104
105static int alloc_irte(struct intel_iommu *iommu,
106		      struct irq_2_iommu *irq_iommu, u16 count)
107{
108	struct ir_table *table = iommu->ir_table;
109	unsigned int mask = 0;
110	unsigned long flags;
111	int index;
112
113	if (!count || !irq_iommu)
114		return -1;
115
116	if (count > 1) {
117		count = __roundup_pow_of_two(count);
118		mask = ilog2(count);
119	}
120
121	if (mask > ecap_max_handle_mask(iommu->ecap)) {
122		pr_err("Requested mask %x exceeds the max invalidation handle"
123		       " mask value %Lx\n", mask,
124		       ecap_max_handle_mask(iommu->ecap));
125		return -1;
126	}
127
128	raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
129	index = bitmap_find_free_region(table->bitmap,
130					INTR_REMAP_TABLE_ENTRIES, mask);
131	if (index < 0) {
132		pr_warn("IR%d: can't allocate an IRTE\n", iommu->seq_id);
133	} else {
134		irq_iommu->iommu = iommu;
135		irq_iommu->irte_index =  index;
136		irq_iommu->sub_handle = 0;
137		irq_iommu->irte_mask = mask;
138		irq_iommu->mode = IRQ_REMAPPING;
139	}
140	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
141
142	return index;
143}
144
145static int qi_flush_iec(struct intel_iommu *iommu, int index, int mask)
146{
147	struct qi_desc desc;
148
149	desc.qw0 = QI_IEC_IIDEX(index) | QI_IEC_TYPE | QI_IEC_IM(mask)
150		   | QI_IEC_SELECTIVE;
151	desc.qw1 = 0;
152	desc.qw2 = 0;
153	desc.qw3 = 0;
154
155	return qi_submit_sync(iommu, &desc, 1, 0);
156}
157
158static int modify_irte(struct irq_2_iommu *irq_iommu,
159		       struct irte *irte_modified)
160{
161	struct intel_iommu *iommu;
162	unsigned long flags;
163	struct irte *irte;
164	int rc, index;
165
166	if (!irq_iommu)
167		return -1;
168
169	raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
170
171	iommu = irq_iommu->iommu;
172
173	index = irq_iommu->irte_index + irq_iommu->sub_handle;
174	irte = &iommu->ir_table->base[index];
175
176#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE)
177	if ((irte->pst == 1) || (irte_modified->pst == 1)) {
178		bool ret;
179
180		ret = cmpxchg_double(&irte->low, &irte->high,
181				     irte->low, irte->high,
182				     irte_modified->low, irte_modified->high);
183		/*
184		 * We use cmpxchg16 to atomically update the 128-bit IRTE,
185		 * and it cannot be updated by the hardware or other processors
186		 * behind us, so the return value of cmpxchg16 should be the
187		 * same as the old value.
188		 */
189		WARN_ON(!ret);
190	} else
191#endif
192	{
193		set_64bit(&irte->low, irte_modified->low);
194		set_64bit(&irte->high, irte_modified->high);
195	}
196	__iommu_flush_cache(iommu, irte, sizeof(*irte));
197
198	rc = qi_flush_iec(iommu, index, 0);
199
200	/* Update iommu mode according to the IRTE mode */
201	irq_iommu->mode = irte->pst ? IRQ_POSTING : IRQ_REMAPPING;
202	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
203
204	return rc;
205}
206
207static struct irq_domain *map_hpet_to_ir(u8 hpet_id)
208{
209	int i;
210
211	for (i = 0; i < MAX_HPET_TBS; i++) {
212		if (ir_hpet[i].id == hpet_id && ir_hpet[i].iommu)
213			return ir_hpet[i].iommu->ir_domain;
214	}
215	return NULL;
216}
217
218static struct intel_iommu *map_ioapic_to_iommu(int apic)
219{
220	int i;
221
222	for (i = 0; i < MAX_IO_APICS; i++) {
223		if (ir_ioapic[i].id == apic && ir_ioapic[i].iommu)
224			return ir_ioapic[i].iommu;
225	}
226	return NULL;
227}
228
229static struct irq_domain *map_ioapic_to_ir(int apic)
230{
231	struct intel_iommu *iommu = map_ioapic_to_iommu(apic);
232
233	return iommu ? iommu->ir_domain : NULL;
234}
235
236static struct irq_domain *map_dev_to_ir(struct pci_dev *dev)
237{
238	struct dmar_drhd_unit *drhd = dmar_find_matched_drhd_unit(dev);
239
240	return drhd ? drhd->iommu->ir_msi_domain : NULL;
241}
242
243static int clear_entries(struct irq_2_iommu *irq_iommu)
244{
245	struct irte *start, *entry, *end;
246	struct intel_iommu *iommu;
247	int index;
248
249	if (irq_iommu->sub_handle)
250		return 0;
251
252	iommu = irq_iommu->iommu;
253	index = irq_iommu->irte_index;
254
255	start = iommu->ir_table->base + index;
256	end = start + (1 << irq_iommu->irte_mask);
257
258	for (entry = start; entry < end; entry++) {
259		set_64bit(&entry->low, 0);
260		set_64bit(&entry->high, 0);
261	}
262	bitmap_release_region(iommu->ir_table->bitmap, index,
263			      irq_iommu->irte_mask);
264
265	return qi_flush_iec(iommu, index, irq_iommu->irte_mask);
266}
267
268/*
269 * source validation type
270 */
271#define SVT_NO_VERIFY		0x0  /* no verification is required */
272#define SVT_VERIFY_SID_SQ	0x1  /* verify using SID and SQ fields */
273#define SVT_VERIFY_BUS		0x2  /* verify bus of request-id */
274
275/*
276 * source-id qualifier
277 */
278#define SQ_ALL_16	0x0  /* verify all 16 bits of request-id */
279#define SQ_13_IGNORE_1	0x1  /* verify most significant 13 bits, ignore
280			      * the third least significant bit
281			      */
282#define SQ_13_IGNORE_2	0x2  /* verify most significant 13 bits, ignore
283			      * the second and third least significant bits
284			      */
285#define SQ_13_IGNORE_3	0x3  /* verify most significant 13 bits, ignore
286			      * the least three significant bits
287			      */
288
289/*
290 * set SVT, SQ and SID fields of irte to verify
291 * source ids of interrupt requests
292 */
293static void set_irte_sid(struct irte *irte, unsigned int svt,
294			 unsigned int sq, unsigned int sid)
295{
296	if (disable_sourceid_checking)
297		svt = SVT_NO_VERIFY;
298	irte->svt = svt;
299	irte->sq = sq;
300	irte->sid = sid;
301}
302
303/*
304 * Set an IRTE to match only the bus number. Interrupt requests that reference
305 * this IRTE must have a requester-id whose bus number is between or equal
306 * to the start_bus and end_bus arguments.
307 */
308static void set_irte_verify_bus(struct irte *irte, unsigned int start_bus,
309				unsigned int end_bus)
310{
311	set_irte_sid(irte, SVT_VERIFY_BUS, SQ_ALL_16,
312		     (start_bus << 8) | end_bus);
313}
314
315static int set_ioapic_sid(struct irte *irte, int apic)
316{
317	int i;
318	u16 sid = 0;
319
320	if (!irte)
321		return -1;
322
323	down_read(&dmar_global_lock);
324	for (i = 0; i < MAX_IO_APICS; i++) {
325		if (ir_ioapic[i].iommu && ir_ioapic[i].id == apic) {
326			sid = (ir_ioapic[i].bus << 8) | ir_ioapic[i].devfn;
327			break;
328		}
329	}
330	up_read(&dmar_global_lock);
331
332	if (sid == 0) {
333		pr_warn("Failed to set source-id of IOAPIC (%d)\n", apic);
334		return -1;
335	}
336
337	set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_ALL_16, sid);
338
339	return 0;
340}
341
342static int set_hpet_sid(struct irte *irte, u8 id)
343{
344	int i;
345	u16 sid = 0;
346
347	if (!irte)
348		return -1;
349
350	down_read(&dmar_global_lock);
351	for (i = 0; i < MAX_HPET_TBS; i++) {
352		if (ir_hpet[i].iommu && ir_hpet[i].id == id) {
353			sid = (ir_hpet[i].bus << 8) | ir_hpet[i].devfn;
354			break;
355		}
356	}
357	up_read(&dmar_global_lock);
358
359	if (sid == 0) {
360		pr_warn("Failed to set source-id of HPET block (%d)\n", id);
361		return -1;
362	}
363
364	/*
365	 * Should really use SQ_ALL_16. Some platforms are broken.
366	 * While we figure out the right quirks for these broken platforms, use
367	 * SQ_13_IGNORE_3 for now.
368	 */
369	set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_13_IGNORE_3, sid);
370
371	return 0;
372}
373
374struct set_msi_sid_data {
375	struct pci_dev *pdev;
376	u16 alias;
377	int count;
378	int busmatch_count;
379};
380
381static int set_msi_sid_cb(struct pci_dev *pdev, u16 alias, void *opaque)
382{
383	struct set_msi_sid_data *data = opaque;
384
385	if (data->count == 0 || PCI_BUS_NUM(alias) == PCI_BUS_NUM(data->alias))
386		data->busmatch_count++;
387
388	data->pdev = pdev;
389	data->alias = alias;
390	data->count++;
391
392	return 0;
393}
394
395static int set_msi_sid(struct irte *irte, struct pci_dev *dev)
396{
397	struct set_msi_sid_data data;
398
399	if (!irte || !dev)
400		return -1;
401
402	data.count = 0;
403	data.busmatch_count = 0;
404	pci_for_each_dma_alias(dev, set_msi_sid_cb, &data);
405
406	/*
407	 * DMA alias provides us with a PCI device and alias.  The only case
408	 * where the it will return an alias on a different bus than the
409	 * device is the case of a PCIe-to-PCI bridge, where the alias is for
410	 * the subordinate bus.  In this case we can only verify the bus.
411	 *
412	 * If there are multiple aliases, all with the same bus number,
413	 * then all we can do is verify the bus. This is typical in NTB
414	 * hardware which use proxy IDs where the device will generate traffic
415	 * from multiple devfn numbers on the same bus.
416	 *
417	 * If the alias device is on a different bus than our source device
418	 * then we have a topology based alias, use it.
419	 *
420	 * Otherwise, the alias is for a device DMA quirk and we cannot
421	 * assume that MSI uses the same requester ID.  Therefore use the
422	 * original device.
423	 */
424	if (PCI_BUS_NUM(data.alias) != data.pdev->bus->number)
425		set_irte_verify_bus(irte, PCI_BUS_NUM(data.alias),
426				    dev->bus->number);
427	else if (data.count >= 2 && data.busmatch_count == data.count)
428		set_irte_verify_bus(irte, dev->bus->number, dev->bus->number);
429	else if (data.pdev->bus->number != dev->bus->number)
430		set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_ALL_16, data.alias);
431	else
432		set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_ALL_16,
433			     pci_dev_id(dev));
434
435	return 0;
436}
437
438static int iommu_load_old_irte(struct intel_iommu *iommu)
439{
440	struct irte *old_ir_table;
441	phys_addr_t irt_phys;
442	unsigned int i;
443	size_t size;
444	u64 irta;
445
446	/* Check whether the old ir-table has the same size as ours */
447	irta = dmar_readq(iommu->reg + DMAR_IRTA_REG);
448	if ((irta & INTR_REMAP_TABLE_REG_SIZE_MASK)
449	     != INTR_REMAP_TABLE_REG_SIZE)
450		return -EINVAL;
451
452	irt_phys = irta & VTD_PAGE_MASK;
453	size     = INTR_REMAP_TABLE_ENTRIES*sizeof(struct irte);
454
455	/* Map the old IR table */
456	old_ir_table = memremap(irt_phys, size, MEMREMAP_WB);
457	if (!old_ir_table)
458		return -ENOMEM;
459
460	/* Copy data over */
461	memcpy(iommu->ir_table->base, old_ir_table, size);
462
463	__iommu_flush_cache(iommu, iommu->ir_table->base, size);
464
465	/*
466	 * Now check the table for used entries and mark those as
467	 * allocated in the bitmap
468	 */
469	for (i = 0; i < INTR_REMAP_TABLE_ENTRIES; i++) {
470		if (iommu->ir_table->base[i].present)
471			bitmap_set(iommu->ir_table->bitmap, i, 1);
472	}
473
474	memunmap(old_ir_table);
475
476	return 0;
477}
478
479
480static void iommu_set_irq_remapping(struct intel_iommu *iommu, int mode)
481{
482	unsigned long flags;
483	u64 addr;
484	u32 sts;
485
486	addr = virt_to_phys((void *)iommu->ir_table->base);
487
488	raw_spin_lock_irqsave(&iommu->register_lock, flags);
489
490	dmar_writeq(iommu->reg + DMAR_IRTA_REG,
491		    (addr) | IR_X2APIC_MODE(mode) | INTR_REMAP_TABLE_REG_SIZE);
492
493	/* Set interrupt-remapping table pointer */
494	writel(iommu->gcmd | DMA_GCMD_SIRTP, iommu->reg + DMAR_GCMD_REG);
495
496	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
497		      readl, (sts & DMA_GSTS_IRTPS), sts);
498	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
499
500	/*
501	 * Global invalidation of interrupt entry cache to make sure the
502	 * hardware uses the new irq remapping table.
503	 */
504	qi_global_iec(iommu);
505}
506
507static void iommu_enable_irq_remapping(struct intel_iommu *iommu)
508{
509	unsigned long flags;
510	u32 sts;
511
512	raw_spin_lock_irqsave(&iommu->register_lock, flags);
513
514	/* Enable interrupt-remapping */
515	iommu->gcmd |= DMA_GCMD_IRE;
516	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
517	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
518		      readl, (sts & DMA_GSTS_IRES), sts);
519
520	/* Block compatibility-format MSIs */
521	if (sts & DMA_GSTS_CFIS) {
522		iommu->gcmd &= ~DMA_GCMD_CFI;
523		writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
524		IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
525			      readl, !(sts & DMA_GSTS_CFIS), sts);
526	}
527
528	/*
529	 * With CFI clear in the Global Command register, we should be
530	 * protected from dangerous (i.e. compatibility) interrupts
531	 * regardless of x2apic status.  Check just to be sure.
532	 */
533	if (sts & DMA_GSTS_CFIS)
534		WARN(1, KERN_WARNING
535			"Compatibility-format IRQs enabled despite intr remapping;\n"
536			"you are vulnerable to IRQ injection.\n");
537
538	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
539}
540
541static int intel_setup_irq_remapping(struct intel_iommu *iommu)
542{
543	struct ir_table *ir_table;
544	struct fwnode_handle *fn;
545	unsigned long *bitmap;
546	struct page *pages;
547
548	if (iommu->ir_table)
549		return 0;
550
551	ir_table = kzalloc(sizeof(struct ir_table), GFP_KERNEL);
552	if (!ir_table)
553		return -ENOMEM;
554
555	pages = alloc_pages_node(iommu->node, GFP_KERNEL | __GFP_ZERO,
556				 INTR_REMAP_PAGE_ORDER);
557	if (!pages) {
558		pr_err("IR%d: failed to allocate pages of order %d\n",
559		       iommu->seq_id, INTR_REMAP_PAGE_ORDER);
560		goto out_free_table;
561	}
562
563	bitmap = bitmap_zalloc(INTR_REMAP_TABLE_ENTRIES, GFP_ATOMIC);
564	if (bitmap == NULL) {
565		pr_err("IR%d: failed to allocate bitmap\n", iommu->seq_id);
566		goto out_free_pages;
567	}
568
569	fn = irq_domain_alloc_named_id_fwnode("INTEL-IR", iommu->seq_id);
570	if (!fn)
571		goto out_free_bitmap;
572
573	iommu->ir_domain =
574		irq_domain_create_hierarchy(arch_get_ir_parent_domain(),
575					    0, INTR_REMAP_TABLE_ENTRIES,
576					    fn, &intel_ir_domain_ops,
577					    iommu);
578	if (!iommu->ir_domain) {
579		pr_err("IR%d: failed to allocate irqdomain\n", iommu->seq_id);
580		goto out_free_fwnode;
581	}
582	iommu->ir_msi_domain =
583		arch_create_remap_msi_irq_domain(iommu->ir_domain,
584						 "INTEL-IR-MSI",
585						 iommu->seq_id);
586
587	ir_table->base = page_address(pages);
588	ir_table->bitmap = bitmap;
589	iommu->ir_table = ir_table;
590
591	/*
592	 * If the queued invalidation is already initialized,
593	 * shouldn't disable it.
594	 */
595	if (!iommu->qi) {
596		/*
597		 * Clear previous faults.
598		 */
599		dmar_fault(-1, iommu);
600		dmar_disable_qi(iommu);
601
602		if (dmar_enable_qi(iommu)) {
603			pr_err("Failed to enable queued invalidation\n");
604			goto out_free_ir_domain;
605		}
606	}
607
608	init_ir_status(iommu);
609
610	if (ir_pre_enabled(iommu)) {
611		if (!is_kdump_kernel()) {
612			pr_warn("IRQ remapping was enabled on %s but we are not in kdump mode\n",
613				iommu->name);
614			clear_ir_pre_enabled(iommu);
615			iommu_disable_irq_remapping(iommu);
616		} else if (iommu_load_old_irte(iommu))
617			pr_err("Failed to copy IR table for %s from previous kernel\n",
618			       iommu->name);
619		else
620			pr_info("Copied IR table for %s from previous kernel\n",
621				iommu->name);
622	}
623
624	iommu_set_irq_remapping(iommu, eim_mode);
625
626	return 0;
627
628out_free_ir_domain:
629	if (iommu->ir_msi_domain)
630		irq_domain_remove(iommu->ir_msi_domain);
631	iommu->ir_msi_domain = NULL;
632	irq_domain_remove(iommu->ir_domain);
633	iommu->ir_domain = NULL;
634out_free_fwnode:
635	irq_domain_free_fwnode(fn);
636out_free_bitmap:
637	bitmap_free(bitmap);
638out_free_pages:
639	__free_pages(pages, INTR_REMAP_PAGE_ORDER);
640out_free_table:
641	kfree(ir_table);
642
643	iommu->ir_table  = NULL;
644
645	return -ENOMEM;
646}
647
648static void intel_teardown_irq_remapping(struct intel_iommu *iommu)
649{
650	struct fwnode_handle *fn;
651
652	if (iommu && iommu->ir_table) {
653		if (iommu->ir_msi_domain) {
654			fn = iommu->ir_msi_domain->fwnode;
655
656			irq_domain_remove(iommu->ir_msi_domain);
657			irq_domain_free_fwnode(fn);
658			iommu->ir_msi_domain = NULL;
659		}
660		if (iommu->ir_domain) {
661			fn = iommu->ir_domain->fwnode;
662
663			irq_domain_remove(iommu->ir_domain);
664			irq_domain_free_fwnode(fn);
665			iommu->ir_domain = NULL;
666		}
667		free_pages((unsigned long)iommu->ir_table->base,
668			   INTR_REMAP_PAGE_ORDER);
669		bitmap_free(iommu->ir_table->bitmap);
670		kfree(iommu->ir_table);
671		iommu->ir_table = NULL;
672	}
673}
674
675/*
676 * Disable Interrupt Remapping.
677 */
678static void iommu_disable_irq_remapping(struct intel_iommu *iommu)
679{
680	unsigned long flags;
681	u32 sts;
682
683	if (!ecap_ir_support(iommu->ecap))
684		return;
685
686	/*
687	 * global invalidation of interrupt entry cache before disabling
688	 * interrupt-remapping.
689	 */
690	qi_global_iec(iommu);
691
692	raw_spin_lock_irqsave(&iommu->register_lock, flags);
693
694	sts = readl(iommu->reg + DMAR_GSTS_REG);
695	if (!(sts & DMA_GSTS_IRES))
696		goto end;
697
698	iommu->gcmd &= ~DMA_GCMD_IRE;
699	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
700
701	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
702		      readl, !(sts & DMA_GSTS_IRES), sts);
703
704end:
705	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
706}
707
708static int __init dmar_x2apic_optout(void)
709{
710	struct acpi_table_dmar *dmar;
711	dmar = (struct acpi_table_dmar *)dmar_tbl;
712	if (!dmar || no_x2apic_optout)
713		return 0;
714	return dmar->flags & DMAR_X2APIC_OPT_OUT;
715}
716
717static void __init intel_cleanup_irq_remapping(void)
718{
719	struct dmar_drhd_unit *drhd;
720	struct intel_iommu *iommu;
721
722	for_each_iommu(iommu, drhd) {
723		if (ecap_ir_support(iommu->ecap)) {
724			iommu_disable_irq_remapping(iommu);
725			intel_teardown_irq_remapping(iommu);
726		}
727	}
728
729	if (x2apic_supported())
730		pr_warn("Failed to enable irq remapping. You are vulnerable to irq-injection attacks.\n");
731}
732
733static int __init intel_prepare_irq_remapping(void)
734{
735	struct dmar_drhd_unit *drhd;
736	struct intel_iommu *iommu;
737	int eim = 0;
738
739	if (irq_remap_broken) {
740		pr_warn("This system BIOS has enabled interrupt remapping\n"
741			"on a chipset that contains an erratum making that\n"
742			"feature unstable.  To maintain system stability\n"
743			"interrupt remapping is being disabled.  Please\n"
744			"contact your BIOS vendor for an update\n");
745		add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
746		return -ENODEV;
747	}
748
749	if (dmar_table_init() < 0)
750		return -ENODEV;
751
752	if (!dmar_ir_support())
753		return -ENODEV;
754
755	if (parse_ioapics_under_ir()) {
756		pr_info("Not enabling interrupt remapping\n");
757		goto error;
758	}
759
760	/* First make sure all IOMMUs support IRQ remapping */
761	for_each_iommu(iommu, drhd)
762		if (!ecap_ir_support(iommu->ecap))
763			goto error;
764
765	/* Detect remapping mode: lapic or x2apic */
766	if (x2apic_supported()) {
767		eim = !dmar_x2apic_optout();
768		if (!eim) {
769			pr_info("x2apic is disabled because BIOS sets x2apic opt out bit.");
770			pr_info("Use 'intremap=no_x2apic_optout' to override the BIOS setting.\n");
771		}
772	}
773
774	for_each_iommu(iommu, drhd) {
775		if (eim && !ecap_eim_support(iommu->ecap)) {
776			pr_info("%s does not support EIM\n", iommu->name);
777			eim = 0;
778		}
779	}
780
781	eim_mode = eim;
782	if (eim)
783		pr_info("Queued invalidation will be enabled to support x2apic and Intr-remapping.\n");
784
785	/* Do the initializations early */
786	for_each_iommu(iommu, drhd) {
787		if (intel_setup_irq_remapping(iommu)) {
788			pr_err("Failed to setup irq remapping for %s\n",
789			       iommu->name);
790			goto error;
791		}
792	}
793
794	return 0;
795
796error:
797	intel_cleanup_irq_remapping();
798	return -ENODEV;
799}
800
801/*
802 * Set Posted-Interrupts capability.
803 */
804static inline void set_irq_posting_cap(void)
805{
806	struct dmar_drhd_unit *drhd;
807	struct intel_iommu *iommu;
808
809	if (!disable_irq_post) {
810		/*
811		 * If IRTE is in posted format, the 'pda' field goes across the
812		 * 64-bit boundary, we need use cmpxchg16b to atomically update
813		 * it. We only expose posted-interrupt when X86_FEATURE_CX16
814		 * is supported. Actually, hardware platforms supporting PI
815		 * should have X86_FEATURE_CX16 support, this has been confirmed
816		 * with Intel hardware guys.
817		 */
818		if (boot_cpu_has(X86_FEATURE_CX16))
819			intel_irq_remap_ops.capability |= 1 << IRQ_POSTING_CAP;
820
821		for_each_iommu(iommu, drhd)
822			if (!cap_pi_support(iommu->cap)) {
823				intel_irq_remap_ops.capability &=
824						~(1 << IRQ_POSTING_CAP);
825				break;
826			}
827	}
828}
829
830static int __init intel_enable_irq_remapping(void)
831{
832	struct dmar_drhd_unit *drhd;
833	struct intel_iommu *iommu;
834	bool setup = false;
835
836	/*
837	 * Setup Interrupt-remapping for all the DRHD's now.
838	 */
839	for_each_iommu(iommu, drhd) {
840		if (!ir_pre_enabled(iommu))
841			iommu_enable_irq_remapping(iommu);
842		setup = true;
843	}
844
845	if (!setup)
846		goto error;
847
848	irq_remapping_enabled = 1;
849
850	set_irq_posting_cap();
851
852	pr_info("Enabled IRQ remapping in %s mode\n", eim_mode ? "x2apic" : "xapic");
853
854	return eim_mode ? IRQ_REMAP_X2APIC_MODE : IRQ_REMAP_XAPIC_MODE;
855
856error:
857	intel_cleanup_irq_remapping();
858	return -1;
859}
860
861static int ir_parse_one_hpet_scope(struct acpi_dmar_device_scope *scope,
862				   struct intel_iommu *iommu,
863				   struct acpi_dmar_hardware_unit *drhd)
864{
865	struct acpi_dmar_pci_path *path;
866	u8 bus;
867	int count, free = -1;
868
869	bus = scope->bus;
870	path = (struct acpi_dmar_pci_path *)(scope + 1);
871	count = (scope->length - sizeof(struct acpi_dmar_device_scope))
872		/ sizeof(struct acpi_dmar_pci_path);
873
874	while (--count > 0) {
875		/*
876		 * Access PCI directly due to the PCI
877		 * subsystem isn't initialized yet.
878		 */
879		bus = read_pci_config_byte(bus, path->device, path->function,
880					   PCI_SECONDARY_BUS);
881		path++;
882	}
883
884	for (count = 0; count < MAX_HPET_TBS; count++) {
885		if (ir_hpet[count].iommu == iommu &&
886		    ir_hpet[count].id == scope->enumeration_id)
887			return 0;
888		else if (ir_hpet[count].iommu == NULL && free == -1)
889			free = count;
890	}
891	if (free == -1) {
892		pr_warn("Exceeded Max HPET blocks\n");
893		return -ENOSPC;
894	}
895
896	ir_hpet[free].iommu = iommu;
897	ir_hpet[free].id    = scope->enumeration_id;
898	ir_hpet[free].bus   = bus;
899	ir_hpet[free].devfn = PCI_DEVFN(path->device, path->function);
900	pr_info("HPET id %d under DRHD base 0x%Lx\n",
901		scope->enumeration_id, drhd->address);
902
903	return 0;
904}
905
906static int ir_parse_one_ioapic_scope(struct acpi_dmar_device_scope *scope,
907				     struct intel_iommu *iommu,
908				     struct acpi_dmar_hardware_unit *drhd)
909{
910	struct acpi_dmar_pci_path *path;
911	u8 bus;
912	int count, free = -1;
913
914	bus = scope->bus;
915	path = (struct acpi_dmar_pci_path *)(scope + 1);
916	count = (scope->length - sizeof(struct acpi_dmar_device_scope))
917		/ sizeof(struct acpi_dmar_pci_path);
918
919	while (--count > 0) {
920		/*
921		 * Access PCI directly due to the PCI
922		 * subsystem isn't initialized yet.
923		 */
924		bus = read_pci_config_byte(bus, path->device, path->function,
925					   PCI_SECONDARY_BUS);
926		path++;
927	}
928
929	for (count = 0; count < MAX_IO_APICS; count++) {
930		if (ir_ioapic[count].iommu == iommu &&
931		    ir_ioapic[count].id == scope->enumeration_id)
932			return 0;
933		else if (ir_ioapic[count].iommu == NULL && free == -1)
934			free = count;
935	}
936	if (free == -1) {
937		pr_warn("Exceeded Max IO APICS\n");
938		return -ENOSPC;
939	}
940
941	ir_ioapic[free].bus   = bus;
942	ir_ioapic[free].devfn = PCI_DEVFN(path->device, path->function);
943	ir_ioapic[free].iommu = iommu;
944	ir_ioapic[free].id    = scope->enumeration_id;
945	pr_info("IOAPIC id %d under DRHD base  0x%Lx IOMMU %d\n",
946		scope->enumeration_id, drhd->address, iommu->seq_id);
947
948	return 0;
949}
950
951static int ir_parse_ioapic_hpet_scope(struct acpi_dmar_header *header,
952				      struct intel_iommu *iommu)
953{
954	int ret = 0;
955	struct acpi_dmar_hardware_unit *drhd;
956	struct acpi_dmar_device_scope *scope;
957	void *start, *end;
958
959	drhd = (struct acpi_dmar_hardware_unit *)header;
960	start = (void *)(drhd + 1);
961	end = ((void *)drhd) + header->length;
962
963	while (start < end && ret == 0) {
964		scope = start;
965		if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_IOAPIC)
966			ret = ir_parse_one_ioapic_scope(scope, iommu, drhd);
967		else if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_HPET)
968			ret = ir_parse_one_hpet_scope(scope, iommu, drhd);
969		start += scope->length;
970	}
971
972	return ret;
973}
974
975static void ir_remove_ioapic_hpet_scope(struct intel_iommu *iommu)
976{
977	int i;
978
979	for (i = 0; i < MAX_HPET_TBS; i++)
980		if (ir_hpet[i].iommu == iommu)
981			ir_hpet[i].iommu = NULL;
982
983	for (i = 0; i < MAX_IO_APICS; i++)
984		if (ir_ioapic[i].iommu == iommu)
985			ir_ioapic[i].iommu = NULL;
986}
987
988/*
989 * Finds the assocaition between IOAPIC's and its Interrupt-remapping
990 * hardware unit.
991 */
992static int __init parse_ioapics_under_ir(void)
993{
994	struct dmar_drhd_unit *drhd;
995	struct intel_iommu *iommu;
996	bool ir_supported = false;
997	int ioapic_idx;
998
999	for_each_iommu(iommu, drhd) {
1000		int ret;
1001
1002		if (!ecap_ir_support(iommu->ecap))
1003			continue;
1004
1005		ret = ir_parse_ioapic_hpet_scope(drhd->hdr, iommu);
1006		if (ret)
1007			return ret;
1008
1009		ir_supported = true;
1010	}
1011
1012	if (!ir_supported)
1013		return -ENODEV;
1014
1015	for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++) {
1016		int ioapic_id = mpc_ioapic_id(ioapic_idx);
1017		if (!map_ioapic_to_iommu(ioapic_id)) {
1018			pr_err(FW_BUG "ioapic %d has no mapping iommu, "
1019			       "interrupt remapping will be disabled\n",
1020			       ioapic_id);
1021			return -1;
1022		}
1023	}
1024
1025	return 0;
1026}
1027
1028static int __init ir_dev_scope_init(void)
1029{
1030	int ret;
1031
1032	if (!irq_remapping_enabled)
1033		return 0;
1034
1035	down_write(&dmar_global_lock);
1036	ret = dmar_dev_scope_init();
1037	up_write(&dmar_global_lock);
1038
1039	return ret;
1040}
1041rootfs_initcall(ir_dev_scope_init);
1042
1043static void disable_irq_remapping(void)
1044{
1045	struct dmar_drhd_unit *drhd;
1046	struct intel_iommu *iommu = NULL;
1047
1048	/*
1049	 * Disable Interrupt-remapping for all the DRHD's now.
1050	 */
1051	for_each_iommu(iommu, drhd) {
1052		if (!ecap_ir_support(iommu->ecap))
1053			continue;
1054
1055		iommu_disable_irq_remapping(iommu);
1056	}
1057
1058	/*
1059	 * Clear Posted-Interrupts capability.
1060	 */
1061	if (!disable_irq_post)
1062		intel_irq_remap_ops.capability &= ~(1 << IRQ_POSTING_CAP);
1063}
1064
1065static int reenable_irq_remapping(int eim)
1066{
1067	struct dmar_drhd_unit *drhd;
1068	bool setup = false;
1069	struct intel_iommu *iommu = NULL;
1070
1071	for_each_iommu(iommu, drhd)
1072		if (iommu->qi)
1073			dmar_reenable_qi(iommu);
1074
1075	/*
1076	 * Setup Interrupt-remapping for all the DRHD's now.
1077	 */
1078	for_each_iommu(iommu, drhd) {
1079		if (!ecap_ir_support(iommu->ecap))
1080			continue;
1081
1082		/* Set up interrupt remapping for iommu.*/
1083		iommu_set_irq_remapping(iommu, eim);
1084		iommu_enable_irq_remapping(iommu);
1085		setup = true;
1086	}
1087
1088	if (!setup)
1089		goto error;
1090
1091	set_irq_posting_cap();
1092
1093	return 0;
1094
1095error:
1096	/*
1097	 * handle error condition gracefully here!
1098	 */
1099	return -1;
1100}
1101
1102/*
1103 * Store the MSI remapping domain pointer in the device if enabled.
1104 *
1105 * This is called from dmar_pci_bus_add_dev() so it works even when DMA
1106 * remapping is disabled. Only update the pointer if the device is not
1107 * already handled by a non default PCI/MSI interrupt domain. This protects
1108 * e.g. VMD devices.
1109 */
1110void intel_irq_remap_add_device(struct dmar_pci_notify_info *info)
1111{
1112	if (!irq_remapping_enabled || pci_dev_has_special_msi_domain(info->dev))
1113		return;
1114
1115	dev_set_msi_domain(&info->dev->dev, map_dev_to_ir(info->dev));
1116}
1117
1118static void prepare_irte(struct irte *irte, int vector, unsigned int dest)
1119{
1120	memset(irte, 0, sizeof(*irte));
1121
1122	irte->present = 1;
1123	irte->dst_mode = apic->irq_dest_mode;
1124	/*
1125	 * Trigger mode in the IRTE will always be edge, and for IO-APIC, the
1126	 * actual level or edge trigger will be setup in the IO-APIC
1127	 * RTE. This will help simplify level triggered irq migration.
1128	 * For more details, see the comments (in io_apic.c) explainig IO-APIC
1129	 * irq migration in the presence of interrupt-remapping.
1130	*/
1131	irte->trigger_mode = 0;
1132	irte->dlvry_mode = apic->irq_delivery_mode;
1133	irte->vector = vector;
1134	irte->dest_id = IRTE_DEST(dest);
1135	irte->redir_hint = 1;
1136}
1137
1138static struct irq_domain *intel_get_irq_domain(struct irq_alloc_info *info)
1139{
1140	if (!info)
1141		return NULL;
1142
1143	switch (info->type) {
1144	case X86_IRQ_ALLOC_TYPE_IOAPIC_GET_PARENT:
1145		return map_ioapic_to_ir(info->devid);
1146	case X86_IRQ_ALLOC_TYPE_HPET_GET_PARENT:
1147		return map_hpet_to_ir(info->devid);
1148	default:
1149		WARN_ON_ONCE(1);
1150		return NULL;
1151	}
1152}
1153
1154struct irq_remap_ops intel_irq_remap_ops = {
1155	.prepare		= intel_prepare_irq_remapping,
1156	.enable			= intel_enable_irq_remapping,
1157	.disable		= disable_irq_remapping,
1158	.reenable		= reenable_irq_remapping,
1159	.enable_faulting	= enable_drhd_fault_handling,
1160	.get_irq_domain		= intel_get_irq_domain,
1161};
1162
1163static void intel_ir_reconfigure_irte(struct irq_data *irqd, bool force)
1164{
1165	struct intel_ir_data *ir_data = irqd->chip_data;
1166	struct irte *irte = &ir_data->irte_entry;
1167	struct irq_cfg *cfg = irqd_cfg(irqd);
1168
1169	/*
1170	 * Atomically updates the IRTE with the new destination, vector
1171	 * and flushes the interrupt entry cache.
1172	 */
1173	irte->vector = cfg->vector;
1174	irte->dest_id = IRTE_DEST(cfg->dest_apicid);
1175
1176	/* Update the hardware only if the interrupt is in remapped mode. */
1177	if (force || ir_data->irq_2_iommu.mode == IRQ_REMAPPING)
1178		modify_irte(&ir_data->irq_2_iommu, irte);
1179}
1180
1181/*
1182 * Migrate the IO-APIC irq in the presence of intr-remapping.
1183 *
1184 * For both level and edge triggered, irq migration is a simple atomic
1185 * update(of vector and cpu destination) of IRTE and flush the hardware cache.
1186 *
1187 * For level triggered, we eliminate the io-apic RTE modification (with the
1188 * updated vector information), by using a virtual vector (io-apic pin number).
1189 * Real vector that is used for interrupting cpu will be coming from
1190 * the interrupt-remapping table entry.
1191 *
1192 * As the migration is a simple atomic update of IRTE, the same mechanism
1193 * is used to migrate MSI irq's in the presence of interrupt-remapping.
1194 */
1195static int
1196intel_ir_set_affinity(struct irq_data *data, const struct cpumask *mask,
1197		      bool force)
1198{
1199	struct irq_data *parent = data->parent_data;
1200	struct irq_cfg *cfg = irqd_cfg(data);
1201	int ret;
1202
1203	ret = parent->chip->irq_set_affinity(parent, mask, force);
1204	if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
1205		return ret;
1206
1207	intel_ir_reconfigure_irte(data, false);
1208	/*
1209	 * After this point, all the interrupts will start arriving
1210	 * at the new destination. So, time to cleanup the previous
1211	 * vector allocation.
1212	 */
1213	send_cleanup_vector(cfg);
1214
1215	return IRQ_SET_MASK_OK_DONE;
1216}
1217
1218static void intel_ir_compose_msi_msg(struct irq_data *irq_data,
1219				     struct msi_msg *msg)
1220{
1221	struct intel_ir_data *ir_data = irq_data->chip_data;
1222
1223	*msg = ir_data->msi_entry;
1224}
1225
1226static int intel_ir_set_vcpu_affinity(struct irq_data *data, void *info)
1227{
1228	struct intel_ir_data *ir_data = data->chip_data;
1229	struct vcpu_data *vcpu_pi_info = info;
1230
1231	/* stop posting interrupts, back to remapping mode */
1232	if (!vcpu_pi_info) {
1233		modify_irte(&ir_data->irq_2_iommu, &ir_data->irte_entry);
1234	} else {
1235		struct irte irte_pi;
1236
1237		/*
1238		 * We are not caching the posted interrupt entry. We
1239		 * copy the data from the remapped entry and modify
1240		 * the fields which are relevant for posted mode. The
1241		 * cached remapped entry is used for switching back to
1242		 * remapped mode.
1243		 */
1244		memset(&irte_pi, 0, sizeof(irte_pi));
1245		dmar_copy_shared_irte(&irte_pi, &ir_data->irte_entry);
1246
1247		/* Update the posted mode fields */
1248		irte_pi.p_pst = 1;
1249		irte_pi.p_urgent = 0;
1250		irte_pi.p_vector = vcpu_pi_info->vector;
1251		irte_pi.pda_l = (vcpu_pi_info->pi_desc_addr >>
1252				(32 - PDA_LOW_BIT)) & ~(-1UL << PDA_LOW_BIT);
1253		irte_pi.pda_h = (vcpu_pi_info->pi_desc_addr >> 32) &
1254				~(-1UL << PDA_HIGH_BIT);
1255
1256		modify_irte(&ir_data->irq_2_iommu, &irte_pi);
1257	}
1258
1259	return 0;
1260}
1261
1262static struct irq_chip intel_ir_chip = {
1263	.name			= "INTEL-IR",
1264	.irq_ack		= apic_ack_irq,
1265	.irq_set_affinity	= intel_ir_set_affinity,
1266	.irq_compose_msi_msg	= intel_ir_compose_msi_msg,
1267	.irq_set_vcpu_affinity	= intel_ir_set_vcpu_affinity,
1268};
1269
1270static void intel_irq_remapping_prepare_irte(struct intel_ir_data *data,
1271					     struct irq_cfg *irq_cfg,
1272					     struct irq_alloc_info *info,
1273					     int index, int sub_handle)
1274{
1275	struct IR_IO_APIC_route_entry *entry;
1276	struct irte *irte = &data->irte_entry;
1277	struct msi_msg *msg = &data->msi_entry;
1278
1279	prepare_irte(irte, irq_cfg->vector, irq_cfg->dest_apicid);
1280	switch (info->type) {
1281	case X86_IRQ_ALLOC_TYPE_IOAPIC:
1282		/* Set source-id of interrupt request */
1283		set_ioapic_sid(irte, info->devid);
1284		apic_printk(APIC_VERBOSE, KERN_DEBUG "IOAPIC[%d]: Set IRTE entry (P:%d FPD:%d Dst_Mode:%d Redir_hint:%d Trig_Mode:%d Dlvry_Mode:%X Avail:%X Vector:%02X Dest:%08X SID:%04X SQ:%X SVT:%X)\n",
1285			info->devid, irte->present, irte->fpd,
1286			irte->dst_mode, irte->redir_hint,
1287			irte->trigger_mode, irte->dlvry_mode,
1288			irte->avail, irte->vector, irte->dest_id,
1289			irte->sid, irte->sq, irte->svt);
1290
1291		entry = (struct IR_IO_APIC_route_entry *)info->ioapic.entry;
1292		info->ioapic.entry = NULL;
1293		memset(entry, 0, sizeof(*entry));
1294		entry->index2	= (index >> 15) & 0x1;
1295		entry->zero	= 0;
1296		entry->format	= 1;
1297		entry->index	= (index & 0x7fff);
1298		/*
1299		 * IO-APIC RTE will be configured with virtual vector.
1300		 * irq handler will do the explicit EOI to the io-apic.
1301		 */
1302		entry->vector	= info->ioapic.pin;
1303		entry->mask	= 0;			/* enable IRQ */
1304		entry->trigger	= info->ioapic.trigger;
1305		entry->polarity	= info->ioapic.polarity;
1306		if (info->ioapic.trigger)
1307			entry->mask = 1; /* Mask level triggered irqs. */
1308		break;
1309
1310	case X86_IRQ_ALLOC_TYPE_HPET:
1311	case X86_IRQ_ALLOC_TYPE_PCI_MSI:
1312	case X86_IRQ_ALLOC_TYPE_PCI_MSIX:
1313		if (info->type == X86_IRQ_ALLOC_TYPE_HPET)
1314			set_hpet_sid(irte, info->devid);
1315		else
1316			set_msi_sid(irte, msi_desc_to_pci_dev(info->desc));
1317
1318		msg->address_hi = MSI_ADDR_BASE_HI;
1319		msg->data = sub_handle;
1320		msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_IR_EXT_INT |
1321				  MSI_ADDR_IR_SHV |
1322				  MSI_ADDR_IR_INDEX1(index) |
1323				  MSI_ADDR_IR_INDEX2(index);
1324		break;
1325
1326	default:
1327		BUG_ON(1);
1328		break;
1329	}
1330}
1331
1332static void intel_free_irq_resources(struct irq_domain *domain,
1333				     unsigned int virq, unsigned int nr_irqs)
1334{
1335	struct irq_data *irq_data;
1336	struct intel_ir_data *data;
1337	struct irq_2_iommu *irq_iommu;
1338	unsigned long flags;
1339	int i;
1340	for (i = 0; i < nr_irqs; i++) {
1341		irq_data = irq_domain_get_irq_data(domain, virq  + i);
1342		if (irq_data && irq_data->chip_data) {
1343			data = irq_data->chip_data;
1344			irq_iommu = &data->irq_2_iommu;
1345			raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
1346			clear_entries(irq_iommu);
1347			raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
1348			irq_domain_reset_irq_data(irq_data);
1349			kfree(data);
1350		}
1351	}
1352}
1353
1354static int intel_irq_remapping_alloc(struct irq_domain *domain,
1355				     unsigned int virq, unsigned int nr_irqs,
1356				     void *arg)
1357{
1358	struct intel_iommu *iommu = domain->host_data;
1359	struct irq_alloc_info *info = arg;
1360	struct intel_ir_data *data, *ird;
1361	struct irq_data *irq_data;
1362	struct irq_cfg *irq_cfg;
1363	int i, ret, index;
1364
1365	if (!info || !iommu)
1366		return -EINVAL;
1367	if (nr_irqs > 1 && info->type != X86_IRQ_ALLOC_TYPE_PCI_MSI &&
1368	    info->type != X86_IRQ_ALLOC_TYPE_PCI_MSIX)
1369		return -EINVAL;
1370
1371	/*
1372	 * With IRQ remapping enabled, don't need contiguous CPU vectors
1373	 * to support multiple MSI interrupts.
1374	 */
1375	if (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI)
1376		info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
1377
1378	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
1379	if (ret < 0)
1380		return ret;
1381
1382	ret = -ENOMEM;
1383	data = kzalloc(sizeof(*data), GFP_KERNEL);
1384	if (!data)
1385		goto out_free_parent;
1386
1387	down_read(&dmar_global_lock);
1388	index = alloc_irte(iommu, &data->irq_2_iommu, nr_irqs);
1389	up_read(&dmar_global_lock);
1390	if (index < 0) {
1391		pr_warn("Failed to allocate IRTE\n");
1392		kfree(data);
1393		goto out_free_parent;
1394	}
1395
1396	for (i = 0; i < nr_irqs; i++) {
1397		irq_data = irq_domain_get_irq_data(domain, virq + i);
1398		irq_cfg = irqd_cfg(irq_data);
1399		if (!irq_data || !irq_cfg) {
1400			if (!i)
1401				kfree(data);
1402			ret = -EINVAL;
1403			goto out_free_data;
1404		}
1405
1406		if (i > 0) {
1407			ird = kzalloc(sizeof(*ird), GFP_KERNEL);
1408			if (!ird)
1409				goto out_free_data;
1410			/* Initialize the common data */
1411			ird->irq_2_iommu = data->irq_2_iommu;
1412			ird->irq_2_iommu.sub_handle = i;
1413		} else {
1414			ird = data;
1415		}
1416
1417		irq_data->hwirq = (index << 16) + i;
1418		irq_data->chip_data = ird;
1419		irq_data->chip = &intel_ir_chip;
1420		intel_irq_remapping_prepare_irte(ird, irq_cfg, info, index, i);
1421		irq_set_status_flags(virq + i, IRQ_MOVE_PCNTXT);
1422	}
1423	return 0;
1424
1425out_free_data:
1426	intel_free_irq_resources(domain, virq, i);
1427out_free_parent:
1428	irq_domain_free_irqs_common(domain, virq, nr_irqs);
1429	return ret;
1430}
1431
1432static void intel_irq_remapping_free(struct irq_domain *domain,
1433				     unsigned int virq, unsigned int nr_irqs)
1434{
1435	intel_free_irq_resources(domain, virq, nr_irqs);
1436	irq_domain_free_irqs_common(domain, virq, nr_irqs);
1437}
1438
1439static int intel_irq_remapping_activate(struct irq_domain *domain,
1440					struct irq_data *irq_data, bool reserve)
1441{
1442	intel_ir_reconfigure_irte(irq_data, true);
1443	return 0;
1444}
1445
1446static void intel_irq_remapping_deactivate(struct irq_domain *domain,
1447					   struct irq_data *irq_data)
1448{
1449	struct intel_ir_data *data = irq_data->chip_data;
1450	struct irte entry;
1451
1452	memset(&entry, 0, sizeof(entry));
1453	modify_irte(&data->irq_2_iommu, &entry);
1454}
1455
1456static const struct irq_domain_ops intel_ir_domain_ops = {
1457	.alloc = intel_irq_remapping_alloc,
1458	.free = intel_irq_remapping_free,
1459	.activate = intel_irq_remapping_activate,
1460	.deactivate = intel_irq_remapping_deactivate,
1461};
1462
1463/*
1464 * Support of Interrupt Remapping Unit Hotplug
1465 */
1466static int dmar_ir_add(struct dmar_drhd_unit *dmaru, struct intel_iommu *iommu)
1467{
1468	int ret;
1469	int eim = x2apic_enabled();
1470
1471	if (eim && !ecap_eim_support(iommu->ecap)) {
1472		pr_info("DRHD %Lx: EIM not supported by DRHD, ecap %Lx\n",
1473			iommu->reg_phys, iommu->ecap);
1474		return -ENODEV;
1475	}
1476
1477	if (ir_parse_ioapic_hpet_scope(dmaru->hdr, iommu)) {
1478		pr_warn("DRHD %Lx: failed to parse managed IOAPIC/HPET\n",
1479			iommu->reg_phys);
1480		return -ENODEV;
1481	}
1482
1483	/* TODO: check all IOAPICs are covered by IOMMU */
1484
1485	/* Setup Interrupt-remapping now. */
1486	ret = intel_setup_irq_remapping(iommu);
1487	if (ret) {
1488		pr_err("Failed to setup irq remapping for %s\n",
1489		       iommu->name);
1490		intel_teardown_irq_remapping(iommu);
1491		ir_remove_ioapic_hpet_scope(iommu);
1492	} else {
1493		iommu_enable_irq_remapping(iommu);
1494	}
1495
1496	return ret;
1497}
1498
1499int dmar_ir_hotplug(struct dmar_drhd_unit *dmaru, bool insert)
1500{
1501	int ret = 0;
1502	struct intel_iommu *iommu = dmaru->iommu;
1503
1504	if (!irq_remapping_enabled)
1505		return 0;
1506	if (iommu == NULL)
1507		return -EINVAL;
1508	if (!ecap_ir_support(iommu->ecap))
1509		return 0;
1510	if (irq_remapping_cap(IRQ_POSTING_CAP) &&
1511	    !cap_pi_support(iommu->cap))
1512		return -EBUSY;
1513
1514	if (insert) {
1515		if (!iommu->ir_table)
1516			ret = dmar_ir_add(dmaru, iommu);
1517	} else {
1518		if (iommu->ir_table) {
1519			if (!bitmap_empty(iommu->ir_table->bitmap,
1520					  INTR_REMAP_TABLE_ENTRIES)) {
1521				ret = -EBUSY;
1522			} else {
1523				iommu_disable_irq_remapping(iommu);
1524				intel_teardown_irq_remapping(iommu);
1525				ir_remove_ioapic_hpet_scope(iommu);
1526			}
1527		}
1528	}
1529
1530	return ret;
1531}
1532