xref: /kernel/linux/linux-5.10/drivers/iommu/amd/init.c (revision 8c2ecf20)
1// SPDX-License-Identifier: GPL-2.0-only
2/*
3 * Copyright (C) 2007-2010 Advanced Micro Devices, Inc.
4 * Author: Joerg Roedel <jroedel@suse.de>
5 *         Leo Duran <leo.duran@amd.com>
6 */
7
8#define pr_fmt(fmt)     "AMD-Vi: " fmt
9#define dev_fmt(fmt)    pr_fmt(fmt)
10
11#include <linux/pci.h>
12#include <linux/acpi.h>
13#include <linux/list.h>
14#include <linux/bitmap.h>
15#include <linux/slab.h>
16#include <linux/syscore_ops.h>
17#include <linux/interrupt.h>
18#include <linux/msi.h>
19#include <linux/amd-iommu.h>
20#include <linux/export.h>
21#include <linux/kmemleak.h>
22#include <linux/mem_encrypt.h>
23#include <linux/iopoll.h>
24#include <asm/pci-direct.h>
25#include <asm/iommu.h>
26#include <asm/apic.h>
27#include <asm/msidef.h>
28#include <asm/gart.h>
29#include <asm/x86_init.h>
30#include <asm/iommu_table.h>
31#include <asm/io_apic.h>
32#include <asm/irq_remapping.h>
33#include <asm/set_memory.h>
34
35#include <linux/crash_dump.h>
36
37#include "amd_iommu.h"
38#include "../irq_remapping.h"
39
40/*
41 * definitions for the ACPI scanning code
42 */
43#define IVRS_HEADER_LENGTH 48
44
45#define ACPI_IVHD_TYPE_MAX_SUPPORTED	0x40
46#define ACPI_IVMD_TYPE_ALL              0x20
47#define ACPI_IVMD_TYPE                  0x21
48#define ACPI_IVMD_TYPE_RANGE            0x22
49
50#define IVHD_DEV_ALL                    0x01
51#define IVHD_DEV_SELECT                 0x02
52#define IVHD_DEV_SELECT_RANGE_START     0x03
53#define IVHD_DEV_RANGE_END              0x04
54#define IVHD_DEV_ALIAS                  0x42
55#define IVHD_DEV_ALIAS_RANGE            0x43
56#define IVHD_DEV_EXT_SELECT             0x46
57#define IVHD_DEV_EXT_SELECT_RANGE       0x47
58#define IVHD_DEV_SPECIAL		0x48
59#define IVHD_DEV_ACPI_HID		0xf0
60
61#define UID_NOT_PRESENT                 0
62#define UID_IS_INTEGER                  1
63#define UID_IS_CHARACTER                2
64
65#define IVHD_SPECIAL_IOAPIC		1
66#define IVHD_SPECIAL_HPET		2
67
68#define IVHD_FLAG_HT_TUN_EN_MASK        0x01
69#define IVHD_FLAG_PASSPW_EN_MASK        0x02
70#define IVHD_FLAG_RESPASSPW_EN_MASK     0x04
71#define IVHD_FLAG_ISOC_EN_MASK          0x08
72
73#define IVMD_FLAG_EXCL_RANGE            0x08
74#define IVMD_FLAG_IW                    0x04
75#define IVMD_FLAG_IR                    0x02
76#define IVMD_FLAG_UNITY_MAP             0x01
77
78#define ACPI_DEVFLAG_INITPASS           0x01
79#define ACPI_DEVFLAG_EXTINT             0x02
80#define ACPI_DEVFLAG_NMI                0x04
81#define ACPI_DEVFLAG_SYSMGT1            0x10
82#define ACPI_DEVFLAG_SYSMGT2            0x20
83#define ACPI_DEVFLAG_LINT0              0x40
84#define ACPI_DEVFLAG_LINT1              0x80
85#define ACPI_DEVFLAG_ATSDIS             0x10000000
86
87#define LOOP_TIMEOUT	2000000
88
89#define IVRS_GET_SBDF_ID(seg, bus, dev, fd)	(((seg & 0xffff) << 16) | ((bus & 0xff) << 8) \
90						 | ((dev & 0x1f) << 3) | (fn & 0x7))
91
92/*
93 * ACPI table definitions
94 *
95 * These data structures are laid over the table to parse the important values
96 * out of it.
97 */
98
99extern const struct iommu_ops amd_iommu_ops;
100
101/*
102 * structure describing one IOMMU in the ACPI table. Typically followed by one
103 * or more ivhd_entrys.
104 */
105struct ivhd_header {
106	u8 type;
107	u8 flags;
108	u16 length;
109	u16 devid;
110	u16 cap_ptr;
111	u64 mmio_phys;
112	u16 pci_seg;
113	u16 info;
114	u32 efr_attr;
115
116	/* Following only valid on IVHD type 11h and 40h */
117	u64 efr_reg; /* Exact copy of MMIO_EXT_FEATURES */
118	u64 res;
119} __attribute__((packed));
120
121/*
122 * A device entry describing which devices a specific IOMMU translates and
123 * which requestor ids they use.
124 */
125struct ivhd_entry {
126	u8 type;
127	u16 devid;
128	u8 flags;
129	u32 ext;
130	u32 hidh;
131	u64 cid;
132	u8 uidf;
133	u8 uidl;
134	u8 uid;
135} __attribute__((packed));
136
137/*
138 * An AMD IOMMU memory definition structure. It defines things like exclusion
139 * ranges for devices and regions that should be unity mapped.
140 */
141struct ivmd_header {
142	u8 type;
143	u8 flags;
144	u16 length;
145	u16 devid;
146	u16 aux;
147	u64 resv;
148	u64 range_start;
149	u64 range_length;
150} __attribute__((packed));
151
152bool amd_iommu_dump;
153bool amd_iommu_irq_remap __read_mostly;
154
155int amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_VAPIC;
156static int amd_iommu_xt_mode = IRQ_REMAP_XAPIC_MODE;
157
158static bool amd_iommu_detected;
159static bool __initdata amd_iommu_disabled;
160static int amd_iommu_target_ivhd_type;
161
162u16 amd_iommu_last_bdf;			/* largest PCI device id we have
163					   to handle */
164LIST_HEAD(amd_iommu_unity_map);		/* a list of required unity mappings
165					   we find in ACPI */
166bool amd_iommu_unmap_flush;		/* if true, flush on every unmap */
167
168LIST_HEAD(amd_iommu_list);		/* list of all AMD IOMMUs in the
169					   system */
170
171/* Array to assign indices to IOMMUs*/
172struct amd_iommu *amd_iommus[MAX_IOMMUS];
173
174/* Number of IOMMUs present in the system */
175static int amd_iommus_present;
176
177/* IOMMUs have a non-present cache? */
178bool amd_iommu_np_cache __read_mostly;
179bool amd_iommu_iotlb_sup __read_mostly = true;
180
181u32 amd_iommu_max_pasid __read_mostly = ~0;
182
183bool amd_iommu_v2_present __read_mostly;
184static bool amd_iommu_pc_present __read_mostly;
185
186bool amd_iommu_force_isolation __read_mostly;
187
188/*
189 * Pointer to the device table which is shared by all AMD IOMMUs
190 * it is indexed by the PCI device id or the HT unit id and contains
191 * information about the domain the device belongs to as well as the
192 * page table root pointer.
193 */
194struct dev_table_entry *amd_iommu_dev_table;
195/*
196 * Pointer to a device table which the content of old device table
197 * will be copied to. It's only be used in kdump kernel.
198 */
199static struct dev_table_entry *old_dev_tbl_cpy;
200
201/*
202 * The alias table is a driver specific data structure which contains the
203 * mappings of the PCI device ids to the actual requestor ids on the IOMMU.
204 * More than one device can share the same requestor id.
205 */
206u16 *amd_iommu_alias_table;
207
208/*
209 * The rlookup table is used to find the IOMMU which is responsible
210 * for a specific device. It is also indexed by the PCI device id.
211 */
212struct amd_iommu **amd_iommu_rlookup_table;
213EXPORT_SYMBOL(amd_iommu_rlookup_table);
214
215/*
216 * This table is used to find the irq remapping table for a given device id
217 * quickly.
218 */
219struct irq_remap_table **irq_lookup_table;
220
221/*
222 * AMD IOMMU allows up to 2^16 different protection domains. This is a bitmap
223 * to know which ones are already in use.
224 */
225unsigned long *amd_iommu_pd_alloc_bitmap;
226
227static u32 dev_table_size;	/* size of the device table */
228static u32 alias_table_size;	/* size of the alias table */
229static u32 rlookup_table_size;	/* size if the rlookup table */
230
231enum iommu_init_state {
232	IOMMU_START_STATE,
233	IOMMU_IVRS_DETECTED,
234	IOMMU_ACPI_FINISHED,
235	IOMMU_ENABLED,
236	IOMMU_PCI_INIT,
237	IOMMU_INTERRUPTS_EN,
238	IOMMU_DMA_OPS,
239	IOMMU_INITIALIZED,
240	IOMMU_NOT_FOUND,
241	IOMMU_INIT_ERROR,
242	IOMMU_CMDLINE_DISABLED,
243};
244
245/* Early ioapic and hpet maps from kernel command line */
246#define EARLY_MAP_SIZE		4
247static struct devid_map __initdata early_ioapic_map[EARLY_MAP_SIZE];
248static struct devid_map __initdata early_hpet_map[EARLY_MAP_SIZE];
249static struct acpihid_map_entry __initdata early_acpihid_map[EARLY_MAP_SIZE];
250
251static int __initdata early_ioapic_map_size;
252static int __initdata early_hpet_map_size;
253static int __initdata early_acpihid_map_size;
254
255static bool __initdata cmdline_maps;
256
257static enum iommu_init_state init_state = IOMMU_START_STATE;
258
259static int amd_iommu_enable_interrupts(void);
260static int __init iommu_go_to_state(enum iommu_init_state state);
261static void init_device_table_dma(void);
262
263static bool amd_iommu_pre_enabled = true;
264
265static u32 amd_iommu_ivinfo __initdata;
266
267bool translation_pre_enabled(struct amd_iommu *iommu)
268{
269	return (iommu->flags & AMD_IOMMU_FLAG_TRANS_PRE_ENABLED);
270}
271EXPORT_SYMBOL(translation_pre_enabled);
272
273static void clear_translation_pre_enabled(struct amd_iommu *iommu)
274{
275	iommu->flags &= ~AMD_IOMMU_FLAG_TRANS_PRE_ENABLED;
276}
277
278static void init_translation_status(struct amd_iommu *iommu)
279{
280	u64 ctrl;
281
282	ctrl = readq(iommu->mmio_base + MMIO_CONTROL_OFFSET);
283	if (ctrl & (1<<CONTROL_IOMMU_EN))
284		iommu->flags |= AMD_IOMMU_FLAG_TRANS_PRE_ENABLED;
285}
286
287static inline void update_last_devid(u16 devid)
288{
289	if (devid > amd_iommu_last_bdf)
290		amd_iommu_last_bdf = devid;
291}
292
293static inline unsigned long tbl_size(int entry_size)
294{
295	unsigned shift = PAGE_SHIFT +
296			 get_order(((int)amd_iommu_last_bdf + 1) * entry_size);
297
298	return 1UL << shift;
299}
300
301int amd_iommu_get_num_iommus(void)
302{
303	return amd_iommus_present;
304}
305
306#ifdef CONFIG_IRQ_REMAP
307static bool check_feature_on_all_iommus(u64 mask)
308{
309	bool ret = false;
310	struct amd_iommu *iommu;
311
312	for_each_iommu(iommu) {
313		ret = iommu_feature(iommu, mask);
314		if (!ret)
315			return false;
316	}
317
318	return true;
319}
320#endif
321
322/*
323 * For IVHD type 0x11/0x40, EFR is also available via IVHD.
324 * Default to IVHD EFR since it is available sooner
325 * (i.e. before PCI init).
326 */
327static void __init early_iommu_features_init(struct amd_iommu *iommu,
328					     struct ivhd_header *h)
329{
330	if (amd_iommu_ivinfo & IOMMU_IVINFO_EFRSUP)
331		iommu->features = h->efr_reg;
332}
333
334/* Access to l1 and l2 indexed register spaces */
335
336static u32 iommu_read_l1(struct amd_iommu *iommu, u16 l1, u8 address)
337{
338	u32 val;
339
340	pci_write_config_dword(iommu->dev, 0xf8, (address | l1 << 16));
341	pci_read_config_dword(iommu->dev, 0xfc, &val);
342	return val;
343}
344
345static void iommu_write_l1(struct amd_iommu *iommu, u16 l1, u8 address, u32 val)
346{
347	pci_write_config_dword(iommu->dev, 0xf8, (address | l1 << 16 | 1 << 31));
348	pci_write_config_dword(iommu->dev, 0xfc, val);
349	pci_write_config_dword(iommu->dev, 0xf8, (address | l1 << 16));
350}
351
352static u32 iommu_read_l2(struct amd_iommu *iommu, u8 address)
353{
354	u32 val;
355
356	pci_write_config_dword(iommu->dev, 0xf0, address);
357	pci_read_config_dword(iommu->dev, 0xf4, &val);
358	return val;
359}
360
361static void iommu_write_l2(struct amd_iommu *iommu, u8 address, u32 val)
362{
363	pci_write_config_dword(iommu->dev, 0xf0, (address | 1 << 8));
364	pci_write_config_dword(iommu->dev, 0xf4, val);
365}
366
367/****************************************************************************
368 *
369 * AMD IOMMU MMIO register space handling functions
370 *
371 * These functions are used to program the IOMMU device registers in
372 * MMIO space required for that driver.
373 *
374 ****************************************************************************/
375
376/*
377 * This function set the exclusion range in the IOMMU. DMA accesses to the
378 * exclusion range are passed through untranslated
379 */
380static void iommu_set_exclusion_range(struct amd_iommu *iommu)
381{
382	u64 start = iommu->exclusion_start & PAGE_MASK;
383	u64 limit = (start + iommu->exclusion_length - 1) & PAGE_MASK;
384	u64 entry;
385
386	if (!iommu->exclusion_start)
387		return;
388
389	entry = start | MMIO_EXCL_ENABLE_MASK;
390	memcpy_toio(iommu->mmio_base + MMIO_EXCL_BASE_OFFSET,
391			&entry, sizeof(entry));
392
393	entry = limit;
394	memcpy_toio(iommu->mmio_base + MMIO_EXCL_LIMIT_OFFSET,
395			&entry, sizeof(entry));
396}
397
398static void iommu_set_cwwb_range(struct amd_iommu *iommu)
399{
400	u64 start = iommu_virt_to_phys((void *)iommu->cmd_sem);
401	u64 entry = start & PM_ADDR_MASK;
402
403	if (!iommu_feature(iommu, FEATURE_SNP))
404		return;
405
406	/* Note:
407	 * Re-purpose Exclusion base/limit registers for Completion wait
408	 * write-back base/limit.
409	 */
410	memcpy_toio(iommu->mmio_base + MMIO_EXCL_BASE_OFFSET,
411		    &entry, sizeof(entry));
412
413	/* Note:
414	 * Default to 4 Kbytes, which can be specified by setting base
415	 * address equal to the limit address.
416	 */
417	memcpy_toio(iommu->mmio_base + MMIO_EXCL_LIMIT_OFFSET,
418		    &entry, sizeof(entry));
419}
420
421/* Programs the physical address of the device table into the IOMMU hardware */
422static void iommu_set_device_table(struct amd_iommu *iommu)
423{
424	u64 entry;
425
426	BUG_ON(iommu->mmio_base == NULL);
427
428	entry = iommu_virt_to_phys(amd_iommu_dev_table);
429	entry |= (dev_table_size >> 12) - 1;
430	memcpy_toio(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET,
431			&entry, sizeof(entry));
432}
433
434/* Generic functions to enable/disable certain features of the IOMMU. */
435static void iommu_feature_enable(struct amd_iommu *iommu, u8 bit)
436{
437	u64 ctrl;
438
439	ctrl = readq(iommu->mmio_base +  MMIO_CONTROL_OFFSET);
440	ctrl |= (1ULL << bit);
441	writeq(ctrl, iommu->mmio_base +  MMIO_CONTROL_OFFSET);
442}
443
444static void iommu_feature_disable(struct amd_iommu *iommu, u8 bit)
445{
446	u64 ctrl;
447
448	ctrl = readq(iommu->mmio_base + MMIO_CONTROL_OFFSET);
449	ctrl &= ~(1ULL << bit);
450	writeq(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET);
451}
452
453static void iommu_set_inv_tlb_timeout(struct amd_iommu *iommu, int timeout)
454{
455	u64 ctrl;
456
457	ctrl = readq(iommu->mmio_base + MMIO_CONTROL_OFFSET);
458	ctrl &= ~CTRL_INV_TO_MASK;
459	ctrl |= (timeout << CONTROL_INV_TIMEOUT) & CTRL_INV_TO_MASK;
460	writeq(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET);
461}
462
463/* Function to enable the hardware */
464static void iommu_enable(struct amd_iommu *iommu)
465{
466	iommu_feature_enable(iommu, CONTROL_IOMMU_EN);
467}
468
469static void iommu_disable(struct amd_iommu *iommu)
470{
471	if (!iommu->mmio_base)
472		return;
473
474	/* Disable command buffer */
475	iommu_feature_disable(iommu, CONTROL_CMDBUF_EN);
476
477	/* Disable event logging and event interrupts */
478	iommu_feature_disable(iommu, CONTROL_EVT_INT_EN);
479	iommu_feature_disable(iommu, CONTROL_EVT_LOG_EN);
480
481	/* Disable IOMMU GA_LOG */
482	iommu_feature_disable(iommu, CONTROL_GALOG_EN);
483	iommu_feature_disable(iommu, CONTROL_GAINT_EN);
484
485	/* Disable IOMMU hardware itself */
486	iommu_feature_disable(iommu, CONTROL_IOMMU_EN);
487}
488
489/*
490 * mapping and unmapping functions for the IOMMU MMIO space. Each AMD IOMMU in
491 * the system has one.
492 */
493static u8 __iomem * __init iommu_map_mmio_space(u64 address, u64 end)
494{
495	if (!request_mem_region(address, end, "amd_iommu")) {
496		pr_err("Can not reserve memory region %llx-%llx for mmio\n",
497			address, end);
498		pr_err("This is a BIOS bug. Please contact your hardware vendor\n");
499		return NULL;
500	}
501
502	return (u8 __iomem *)ioremap(address, end);
503}
504
505static void __init iommu_unmap_mmio_space(struct amd_iommu *iommu)
506{
507	if (iommu->mmio_base)
508		iounmap(iommu->mmio_base);
509	release_mem_region(iommu->mmio_phys, iommu->mmio_phys_end);
510}
511
512static inline u32 get_ivhd_header_size(struct ivhd_header *h)
513{
514	u32 size = 0;
515
516	switch (h->type) {
517	case 0x10:
518		size = 24;
519		break;
520	case 0x11:
521	case 0x40:
522		size = 40;
523		break;
524	}
525	return size;
526}
527
528/****************************************************************************
529 *
530 * The functions below belong to the first pass of AMD IOMMU ACPI table
531 * parsing. In this pass we try to find out the highest device id this
532 * code has to handle. Upon this information the size of the shared data
533 * structures is determined later.
534 *
535 ****************************************************************************/
536
537/*
538 * This function calculates the length of a given IVHD entry
539 */
540static inline int ivhd_entry_length(u8 *ivhd)
541{
542	u32 type = ((struct ivhd_entry *)ivhd)->type;
543
544	if (type < 0x80) {
545		return 0x04 << (*ivhd >> 6);
546	} else if (type == IVHD_DEV_ACPI_HID) {
547		/* For ACPI_HID, offset 21 is uid len */
548		return *((u8 *)ivhd + 21) + 22;
549	}
550	return 0;
551}
552
553/*
554 * After reading the highest device id from the IOMMU PCI capability header
555 * this function looks if there is a higher device id defined in the ACPI table
556 */
557static int __init find_last_devid_from_ivhd(struct ivhd_header *h)
558{
559	u8 *p = (void *)h, *end = (void *)h;
560	struct ivhd_entry *dev;
561
562	u32 ivhd_size = get_ivhd_header_size(h);
563
564	if (!ivhd_size) {
565		pr_err("Unsupported IVHD type %#x\n", h->type);
566		return -EINVAL;
567	}
568
569	p += ivhd_size;
570	end += h->length;
571
572	while (p < end) {
573		dev = (struct ivhd_entry *)p;
574		switch (dev->type) {
575		case IVHD_DEV_ALL:
576			/* Use maximum BDF value for DEV_ALL */
577			update_last_devid(0xffff);
578			break;
579		case IVHD_DEV_SELECT:
580		case IVHD_DEV_RANGE_END:
581		case IVHD_DEV_ALIAS:
582		case IVHD_DEV_EXT_SELECT:
583			/* all the above subfield types refer to device ids */
584			update_last_devid(dev->devid);
585			break;
586		default:
587			break;
588		}
589		p += ivhd_entry_length(p);
590	}
591
592	WARN_ON(p != end);
593
594	return 0;
595}
596
597static int __init check_ivrs_checksum(struct acpi_table_header *table)
598{
599	int i;
600	u8 checksum = 0, *p = (u8 *)table;
601
602	for (i = 0; i < table->length; ++i)
603		checksum += p[i];
604	if (checksum != 0) {
605		/* ACPI table corrupt */
606		pr_err(FW_BUG "IVRS invalid checksum\n");
607		return -ENODEV;
608	}
609
610	return 0;
611}
612
613/*
614 * Iterate over all IVHD entries in the ACPI table and find the highest device
615 * id which we need to handle. This is the first of three functions which parse
616 * the ACPI table. So we check the checksum here.
617 */
618static int __init find_last_devid_acpi(struct acpi_table_header *table)
619{
620	u8 *p = (u8 *)table, *end = (u8 *)table;
621	struct ivhd_header *h;
622
623	p += IVRS_HEADER_LENGTH;
624
625	end += table->length;
626	while (p < end) {
627		h = (struct ivhd_header *)p;
628		if (h->type == amd_iommu_target_ivhd_type) {
629			int ret = find_last_devid_from_ivhd(h);
630
631			if (ret)
632				return ret;
633		}
634		p += h->length;
635	}
636	WARN_ON(p != end);
637
638	return 0;
639}
640
641/****************************************************************************
642 *
643 * The following functions belong to the code path which parses the ACPI table
644 * the second time. In this ACPI parsing iteration we allocate IOMMU specific
645 * data structures, initialize the device/alias/rlookup table and also
646 * basically initialize the hardware.
647 *
648 ****************************************************************************/
649
650/*
651 * Allocates the command buffer. This buffer is per AMD IOMMU. We can
652 * write commands to that buffer later and the IOMMU will execute them
653 * asynchronously
654 */
655static int __init alloc_command_buffer(struct amd_iommu *iommu)
656{
657	iommu->cmd_buf = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
658						  get_order(CMD_BUFFER_SIZE));
659
660	return iommu->cmd_buf ? 0 : -ENOMEM;
661}
662
663/*
664 * This function restarts event logging in case the IOMMU experienced
665 * an event log buffer overflow.
666 */
667void amd_iommu_restart_event_logging(struct amd_iommu *iommu)
668{
669	iommu_feature_disable(iommu, CONTROL_EVT_LOG_EN);
670	iommu_feature_enable(iommu, CONTROL_EVT_LOG_EN);
671}
672
673/*
674 * This function resets the command buffer if the IOMMU stopped fetching
675 * commands from it.
676 */
677void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu)
678{
679	iommu_feature_disable(iommu, CONTROL_CMDBUF_EN);
680
681	writel(0x00, iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
682	writel(0x00, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
683	iommu->cmd_buf_head = 0;
684	iommu->cmd_buf_tail = 0;
685
686	iommu_feature_enable(iommu, CONTROL_CMDBUF_EN);
687}
688
689/*
690 * This function writes the command buffer address to the hardware and
691 * enables it.
692 */
693static void iommu_enable_command_buffer(struct amd_iommu *iommu)
694{
695	u64 entry;
696
697	BUG_ON(iommu->cmd_buf == NULL);
698
699	entry = iommu_virt_to_phys(iommu->cmd_buf);
700	entry |= MMIO_CMD_SIZE_512;
701
702	memcpy_toio(iommu->mmio_base + MMIO_CMD_BUF_OFFSET,
703		    &entry, sizeof(entry));
704
705	amd_iommu_reset_cmd_buffer(iommu);
706}
707
708/*
709 * This function disables the command buffer
710 */
711static void iommu_disable_command_buffer(struct amd_iommu *iommu)
712{
713	iommu_feature_disable(iommu, CONTROL_CMDBUF_EN);
714}
715
716static void __init free_command_buffer(struct amd_iommu *iommu)
717{
718	free_pages((unsigned long)iommu->cmd_buf, get_order(CMD_BUFFER_SIZE));
719}
720
721static void *__init iommu_alloc_4k_pages(struct amd_iommu *iommu,
722					 gfp_t gfp, size_t size)
723{
724	int order = get_order(size);
725	void *buf = (void *)__get_free_pages(gfp, order);
726
727	if (buf &&
728	    iommu_feature(iommu, FEATURE_SNP) &&
729	    set_memory_4k((unsigned long)buf, (1 << order))) {
730		free_pages((unsigned long)buf, order);
731		buf = NULL;
732	}
733
734	return buf;
735}
736
737/* allocates the memory where the IOMMU will log its events to */
738static int __init alloc_event_buffer(struct amd_iommu *iommu)
739{
740	iommu->evt_buf = iommu_alloc_4k_pages(iommu, GFP_KERNEL | __GFP_ZERO,
741					      EVT_BUFFER_SIZE);
742
743	return iommu->evt_buf ? 0 : -ENOMEM;
744}
745
746static void iommu_enable_event_buffer(struct amd_iommu *iommu)
747{
748	u64 entry;
749
750	BUG_ON(iommu->evt_buf == NULL);
751
752	entry = iommu_virt_to_phys(iommu->evt_buf) | EVT_LEN_MASK;
753
754	memcpy_toio(iommu->mmio_base + MMIO_EVT_BUF_OFFSET,
755		    &entry, sizeof(entry));
756
757	/* set head and tail to zero manually */
758	writel(0x00, iommu->mmio_base + MMIO_EVT_HEAD_OFFSET);
759	writel(0x00, iommu->mmio_base + MMIO_EVT_TAIL_OFFSET);
760
761	iommu_feature_enable(iommu, CONTROL_EVT_LOG_EN);
762}
763
764/*
765 * This function disables the event log buffer
766 */
767static void iommu_disable_event_buffer(struct amd_iommu *iommu)
768{
769	iommu_feature_disable(iommu, CONTROL_EVT_LOG_EN);
770}
771
772static void __init free_event_buffer(struct amd_iommu *iommu)
773{
774	free_pages((unsigned long)iommu->evt_buf, get_order(EVT_BUFFER_SIZE));
775}
776
777/* allocates the memory where the IOMMU will log its events to */
778static int __init alloc_ppr_log(struct amd_iommu *iommu)
779{
780	iommu->ppr_log = iommu_alloc_4k_pages(iommu, GFP_KERNEL | __GFP_ZERO,
781					      PPR_LOG_SIZE);
782
783	return iommu->ppr_log ? 0 : -ENOMEM;
784}
785
786static void iommu_enable_ppr_log(struct amd_iommu *iommu)
787{
788	u64 entry;
789
790	if (iommu->ppr_log == NULL)
791		return;
792
793	entry = iommu_virt_to_phys(iommu->ppr_log) | PPR_LOG_SIZE_512;
794
795	memcpy_toio(iommu->mmio_base + MMIO_PPR_LOG_OFFSET,
796		    &entry, sizeof(entry));
797
798	/* set head and tail to zero manually */
799	writel(0x00, iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
800	writel(0x00, iommu->mmio_base + MMIO_PPR_TAIL_OFFSET);
801
802	iommu_feature_enable(iommu, CONTROL_PPRLOG_EN);
803	iommu_feature_enable(iommu, CONTROL_PPR_EN);
804}
805
806static void __init free_ppr_log(struct amd_iommu *iommu)
807{
808	free_pages((unsigned long)iommu->ppr_log, get_order(PPR_LOG_SIZE));
809}
810
811static void free_ga_log(struct amd_iommu *iommu)
812{
813#ifdef CONFIG_IRQ_REMAP
814	free_pages((unsigned long)iommu->ga_log, get_order(GA_LOG_SIZE));
815	free_pages((unsigned long)iommu->ga_log_tail, get_order(8));
816#endif
817}
818
819static int iommu_ga_log_enable(struct amd_iommu *iommu)
820{
821#ifdef CONFIG_IRQ_REMAP
822	u32 status, i;
823	u64 entry;
824
825	if (!iommu->ga_log)
826		return -EINVAL;
827
828	/* Check if already running */
829	status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
830	if (WARN_ON(status & (MMIO_STATUS_GALOG_RUN_MASK)))
831		return 0;
832
833	entry = iommu_virt_to_phys(iommu->ga_log) | GA_LOG_SIZE_512;
834	memcpy_toio(iommu->mmio_base + MMIO_GA_LOG_BASE_OFFSET,
835		    &entry, sizeof(entry));
836	entry = (iommu_virt_to_phys(iommu->ga_log_tail) &
837		 (BIT_ULL(52)-1)) & ~7ULL;
838	memcpy_toio(iommu->mmio_base + MMIO_GA_LOG_TAIL_OFFSET,
839		    &entry, sizeof(entry));
840	writel(0x00, iommu->mmio_base + MMIO_GA_HEAD_OFFSET);
841	writel(0x00, iommu->mmio_base + MMIO_GA_TAIL_OFFSET);
842
843
844	iommu_feature_enable(iommu, CONTROL_GAINT_EN);
845	iommu_feature_enable(iommu, CONTROL_GALOG_EN);
846
847	for (i = 0; i < LOOP_TIMEOUT; ++i) {
848		status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
849		if (status & (MMIO_STATUS_GALOG_RUN_MASK))
850			break;
851		udelay(10);
852	}
853
854	if (WARN_ON(i >= LOOP_TIMEOUT))
855		return -EINVAL;
856#endif /* CONFIG_IRQ_REMAP */
857	return 0;
858}
859
860static int iommu_init_ga_log(struct amd_iommu *iommu)
861{
862#ifdef CONFIG_IRQ_REMAP
863	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir))
864		return 0;
865
866	iommu->ga_log = (u8 *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
867					get_order(GA_LOG_SIZE));
868	if (!iommu->ga_log)
869		goto err_out;
870
871	iommu->ga_log_tail = (u8 *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
872					get_order(8));
873	if (!iommu->ga_log_tail)
874		goto err_out;
875
876	return 0;
877err_out:
878	free_ga_log(iommu);
879	return -EINVAL;
880#else
881	return 0;
882#endif /* CONFIG_IRQ_REMAP */
883}
884
885static int __init alloc_cwwb_sem(struct amd_iommu *iommu)
886{
887	iommu->cmd_sem = iommu_alloc_4k_pages(iommu, GFP_KERNEL | __GFP_ZERO, 1);
888
889	return iommu->cmd_sem ? 0 : -ENOMEM;
890}
891
892static void __init free_cwwb_sem(struct amd_iommu *iommu)
893{
894	if (iommu->cmd_sem)
895		free_page((unsigned long)iommu->cmd_sem);
896}
897
898static void iommu_enable_xt(struct amd_iommu *iommu)
899{
900#ifdef CONFIG_IRQ_REMAP
901	/*
902	 * XT mode (32-bit APIC destination ID) requires
903	 * GA mode (128-bit IRTE support) as a prerequisite.
904	 */
905	if (AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir) &&
906	    amd_iommu_xt_mode == IRQ_REMAP_X2APIC_MODE)
907		iommu_feature_enable(iommu, CONTROL_XT_EN);
908#endif /* CONFIG_IRQ_REMAP */
909}
910
911static void iommu_enable_gt(struct amd_iommu *iommu)
912{
913	if (!iommu_feature(iommu, FEATURE_GT))
914		return;
915
916	iommu_feature_enable(iommu, CONTROL_GT_EN);
917}
918
919/* sets a specific bit in the device table entry. */
920static void set_dev_entry_bit(u16 devid, u8 bit)
921{
922	int i = (bit >> 6) & 0x03;
923	int _bit = bit & 0x3f;
924
925	amd_iommu_dev_table[devid].data[i] |= (1UL << _bit);
926}
927
928static int get_dev_entry_bit(u16 devid, u8 bit)
929{
930	int i = (bit >> 6) & 0x03;
931	int _bit = bit & 0x3f;
932
933	return (amd_iommu_dev_table[devid].data[i] & (1UL << _bit)) >> _bit;
934}
935
936
937static bool copy_device_table(void)
938{
939	u64 int_ctl, int_tab_len, entry = 0, last_entry = 0;
940	struct dev_table_entry *old_devtb = NULL;
941	u32 lo, hi, devid, old_devtb_size;
942	phys_addr_t old_devtb_phys;
943	struct amd_iommu *iommu;
944	u16 dom_id, dte_v, irq_v;
945	gfp_t gfp_flag;
946	u64 tmp;
947
948	if (!amd_iommu_pre_enabled)
949		return false;
950
951	pr_warn("Translation is already enabled - trying to copy translation structures\n");
952	for_each_iommu(iommu) {
953		/* All IOMMUs should use the same device table with the same size */
954		lo = readl(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET);
955		hi = readl(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET + 4);
956		entry = (((u64) hi) << 32) + lo;
957		if (last_entry && last_entry != entry) {
958			pr_err("IOMMU:%d should use the same dev table as others!\n",
959				iommu->index);
960			return false;
961		}
962		last_entry = entry;
963
964		old_devtb_size = ((entry & ~PAGE_MASK) + 1) << 12;
965		if (old_devtb_size != dev_table_size) {
966			pr_err("The device table size of IOMMU:%d is not expected!\n",
967				iommu->index);
968			return false;
969		}
970	}
971
972	/*
973	 * When SME is enabled in the first kernel, the entry includes the
974	 * memory encryption mask(sme_me_mask), we must remove the memory
975	 * encryption mask to obtain the true physical address in kdump kernel.
976	 */
977	old_devtb_phys = __sme_clr(entry) & PAGE_MASK;
978
979	if (old_devtb_phys >= 0x100000000ULL) {
980		pr_err("The address of old device table is above 4G, not trustworthy!\n");
981		return false;
982	}
983	old_devtb = (sme_active() && is_kdump_kernel())
984		    ? (__force void *)ioremap_encrypted(old_devtb_phys,
985							dev_table_size)
986		    : memremap(old_devtb_phys, dev_table_size, MEMREMAP_WB);
987
988	if (!old_devtb)
989		return false;
990
991	gfp_flag = GFP_KERNEL | __GFP_ZERO | GFP_DMA32;
992	old_dev_tbl_cpy = (void *)__get_free_pages(gfp_flag,
993				get_order(dev_table_size));
994	if (old_dev_tbl_cpy == NULL) {
995		pr_err("Failed to allocate memory for copying old device table!\n");
996		return false;
997	}
998
999	for (devid = 0; devid <= amd_iommu_last_bdf; ++devid) {
1000		old_dev_tbl_cpy[devid] = old_devtb[devid];
1001		dom_id = old_devtb[devid].data[1] & DEV_DOMID_MASK;
1002		dte_v = old_devtb[devid].data[0] & DTE_FLAG_V;
1003
1004		if (dte_v && dom_id) {
1005			old_dev_tbl_cpy[devid].data[0] = old_devtb[devid].data[0];
1006			old_dev_tbl_cpy[devid].data[1] = old_devtb[devid].data[1];
1007			__set_bit(dom_id, amd_iommu_pd_alloc_bitmap);
1008			/* If gcr3 table existed, mask it out */
1009			if (old_devtb[devid].data[0] & DTE_FLAG_GV) {
1010				tmp = DTE_GCR3_VAL_B(~0ULL) << DTE_GCR3_SHIFT_B;
1011				tmp |= DTE_GCR3_VAL_C(~0ULL) << DTE_GCR3_SHIFT_C;
1012				old_dev_tbl_cpy[devid].data[1] &= ~tmp;
1013				tmp = DTE_GCR3_VAL_A(~0ULL) << DTE_GCR3_SHIFT_A;
1014				tmp |= DTE_FLAG_GV;
1015				old_dev_tbl_cpy[devid].data[0] &= ~tmp;
1016			}
1017		}
1018
1019		irq_v = old_devtb[devid].data[2] & DTE_IRQ_REMAP_ENABLE;
1020		int_ctl = old_devtb[devid].data[2] & DTE_IRQ_REMAP_INTCTL_MASK;
1021		int_tab_len = old_devtb[devid].data[2] & DTE_IRQ_TABLE_LEN_MASK;
1022		if (irq_v && (int_ctl || int_tab_len)) {
1023			if ((int_ctl != DTE_IRQ_REMAP_INTCTL) ||
1024			    (int_tab_len != DTE_IRQ_TABLE_LEN)) {
1025				pr_err("Wrong old irq remapping flag: %#x\n", devid);
1026				return false;
1027			}
1028
1029		        old_dev_tbl_cpy[devid].data[2] = old_devtb[devid].data[2];
1030		}
1031	}
1032	memunmap(old_devtb);
1033
1034	return true;
1035}
1036
1037void amd_iommu_apply_erratum_63(u16 devid)
1038{
1039	int sysmgt;
1040
1041	sysmgt = get_dev_entry_bit(devid, DEV_ENTRY_SYSMGT1) |
1042		 (get_dev_entry_bit(devid, DEV_ENTRY_SYSMGT2) << 1);
1043
1044	if (sysmgt == 0x01)
1045		set_dev_entry_bit(devid, DEV_ENTRY_IW);
1046}
1047
1048/* Writes the specific IOMMU for a device into the rlookup table */
1049static void __init set_iommu_for_device(struct amd_iommu *iommu, u16 devid)
1050{
1051	amd_iommu_rlookup_table[devid] = iommu;
1052}
1053
1054/*
1055 * This function takes the device specific flags read from the ACPI
1056 * table and sets up the device table entry with that information
1057 */
1058static void __init set_dev_entry_from_acpi(struct amd_iommu *iommu,
1059					   u16 devid, u32 flags, u32 ext_flags)
1060{
1061	if (flags & ACPI_DEVFLAG_INITPASS)
1062		set_dev_entry_bit(devid, DEV_ENTRY_INIT_PASS);
1063	if (flags & ACPI_DEVFLAG_EXTINT)
1064		set_dev_entry_bit(devid, DEV_ENTRY_EINT_PASS);
1065	if (flags & ACPI_DEVFLAG_NMI)
1066		set_dev_entry_bit(devid, DEV_ENTRY_NMI_PASS);
1067	if (flags & ACPI_DEVFLAG_SYSMGT1)
1068		set_dev_entry_bit(devid, DEV_ENTRY_SYSMGT1);
1069	if (flags & ACPI_DEVFLAG_SYSMGT2)
1070		set_dev_entry_bit(devid, DEV_ENTRY_SYSMGT2);
1071	if (flags & ACPI_DEVFLAG_LINT0)
1072		set_dev_entry_bit(devid, DEV_ENTRY_LINT0_PASS);
1073	if (flags & ACPI_DEVFLAG_LINT1)
1074		set_dev_entry_bit(devid, DEV_ENTRY_LINT1_PASS);
1075
1076	amd_iommu_apply_erratum_63(devid);
1077
1078	set_iommu_for_device(iommu, devid);
1079}
1080
1081int __init add_special_device(u8 type, u8 id, u16 *devid, bool cmd_line)
1082{
1083	struct devid_map *entry;
1084	struct list_head *list;
1085
1086	if (type == IVHD_SPECIAL_IOAPIC)
1087		list = &ioapic_map;
1088	else if (type == IVHD_SPECIAL_HPET)
1089		list = &hpet_map;
1090	else
1091		return -EINVAL;
1092
1093	list_for_each_entry(entry, list, list) {
1094		if (!(entry->id == id && entry->cmd_line))
1095			continue;
1096
1097		pr_info("Command-line override present for %s id %d - ignoring\n",
1098			type == IVHD_SPECIAL_IOAPIC ? "IOAPIC" : "HPET", id);
1099
1100		*devid = entry->devid;
1101
1102		return 0;
1103	}
1104
1105	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
1106	if (!entry)
1107		return -ENOMEM;
1108
1109	entry->id	= id;
1110	entry->devid	= *devid;
1111	entry->cmd_line	= cmd_line;
1112
1113	list_add_tail(&entry->list, list);
1114
1115	return 0;
1116}
1117
1118static int __init add_acpi_hid_device(u8 *hid, u8 *uid, u16 *devid,
1119				      bool cmd_line)
1120{
1121	struct acpihid_map_entry *entry;
1122	struct list_head *list = &acpihid_map;
1123
1124	list_for_each_entry(entry, list, list) {
1125		if (strcmp(entry->hid, hid) ||
1126		    (*uid && *entry->uid && strcmp(entry->uid, uid)) ||
1127		    !entry->cmd_line)
1128			continue;
1129
1130		pr_info("Command-line override for hid:%s uid:%s\n",
1131			hid, uid);
1132		*devid = entry->devid;
1133		return 0;
1134	}
1135
1136	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
1137	if (!entry)
1138		return -ENOMEM;
1139
1140	memcpy(entry->uid, uid, strlen(uid));
1141	memcpy(entry->hid, hid, strlen(hid));
1142	entry->devid = *devid;
1143	entry->cmd_line	= cmd_line;
1144	entry->root_devid = (entry->devid & (~0x7));
1145
1146	pr_info("%s, add hid:%s, uid:%s, rdevid:%d\n",
1147		entry->cmd_line ? "cmd" : "ivrs",
1148		entry->hid, entry->uid, entry->root_devid);
1149
1150	list_add_tail(&entry->list, list);
1151	return 0;
1152}
1153
1154static int __init add_early_maps(void)
1155{
1156	int i, ret;
1157
1158	for (i = 0; i < early_ioapic_map_size; ++i) {
1159		ret = add_special_device(IVHD_SPECIAL_IOAPIC,
1160					 early_ioapic_map[i].id,
1161					 &early_ioapic_map[i].devid,
1162					 early_ioapic_map[i].cmd_line);
1163		if (ret)
1164			return ret;
1165	}
1166
1167	for (i = 0; i < early_hpet_map_size; ++i) {
1168		ret = add_special_device(IVHD_SPECIAL_HPET,
1169					 early_hpet_map[i].id,
1170					 &early_hpet_map[i].devid,
1171					 early_hpet_map[i].cmd_line);
1172		if (ret)
1173			return ret;
1174	}
1175
1176	for (i = 0; i < early_acpihid_map_size; ++i) {
1177		ret = add_acpi_hid_device(early_acpihid_map[i].hid,
1178					  early_acpihid_map[i].uid,
1179					  &early_acpihid_map[i].devid,
1180					  early_acpihid_map[i].cmd_line);
1181		if (ret)
1182			return ret;
1183	}
1184
1185	return 0;
1186}
1187
1188/*
1189 * Takes a pointer to an AMD IOMMU entry in the ACPI table and
1190 * initializes the hardware and our data structures with it.
1191 */
1192static int __init init_iommu_from_acpi(struct amd_iommu *iommu,
1193					struct ivhd_header *h)
1194{
1195	u8 *p = (u8 *)h;
1196	u8 *end = p, flags = 0;
1197	u16 devid = 0, devid_start = 0, devid_to = 0;
1198	u32 dev_i, ext_flags = 0;
1199	bool alias = false;
1200	struct ivhd_entry *e;
1201	u32 ivhd_size;
1202	int ret;
1203
1204
1205	ret = add_early_maps();
1206	if (ret)
1207		return ret;
1208
1209	amd_iommu_apply_ivrs_quirks();
1210
1211	/*
1212	 * First save the recommended feature enable bits from ACPI
1213	 */
1214	iommu->acpi_flags = h->flags;
1215
1216	/*
1217	 * Done. Now parse the device entries
1218	 */
1219	ivhd_size = get_ivhd_header_size(h);
1220	if (!ivhd_size) {
1221		pr_err("Unsupported IVHD type %#x\n", h->type);
1222		return -EINVAL;
1223	}
1224
1225	p += ivhd_size;
1226
1227	end += h->length;
1228
1229
1230	while (p < end) {
1231		e = (struct ivhd_entry *)p;
1232		switch (e->type) {
1233		case IVHD_DEV_ALL:
1234
1235			DUMP_printk("  DEV_ALL\t\t\tflags: %02x\n", e->flags);
1236
1237			for (dev_i = 0; dev_i <= amd_iommu_last_bdf; ++dev_i)
1238				set_dev_entry_from_acpi(iommu, dev_i, e->flags, 0);
1239			break;
1240		case IVHD_DEV_SELECT:
1241
1242			DUMP_printk("  DEV_SELECT\t\t\t devid: %02x:%02x.%x "
1243				    "flags: %02x\n",
1244				    PCI_BUS_NUM(e->devid),
1245				    PCI_SLOT(e->devid),
1246				    PCI_FUNC(e->devid),
1247				    e->flags);
1248
1249			devid = e->devid;
1250			set_dev_entry_from_acpi(iommu, devid, e->flags, 0);
1251			break;
1252		case IVHD_DEV_SELECT_RANGE_START:
1253
1254			DUMP_printk("  DEV_SELECT_RANGE_START\t "
1255				    "devid: %02x:%02x.%x flags: %02x\n",
1256				    PCI_BUS_NUM(e->devid),
1257				    PCI_SLOT(e->devid),
1258				    PCI_FUNC(e->devid),
1259				    e->flags);
1260
1261			devid_start = e->devid;
1262			flags = e->flags;
1263			ext_flags = 0;
1264			alias = false;
1265			break;
1266		case IVHD_DEV_ALIAS:
1267
1268			DUMP_printk("  DEV_ALIAS\t\t\t devid: %02x:%02x.%x "
1269				    "flags: %02x devid_to: %02x:%02x.%x\n",
1270				    PCI_BUS_NUM(e->devid),
1271				    PCI_SLOT(e->devid),
1272				    PCI_FUNC(e->devid),
1273				    e->flags,
1274				    PCI_BUS_NUM(e->ext >> 8),
1275				    PCI_SLOT(e->ext >> 8),
1276				    PCI_FUNC(e->ext >> 8));
1277
1278			devid = e->devid;
1279			devid_to = e->ext >> 8;
1280			set_dev_entry_from_acpi(iommu, devid   , e->flags, 0);
1281			set_dev_entry_from_acpi(iommu, devid_to, e->flags, 0);
1282			amd_iommu_alias_table[devid] = devid_to;
1283			break;
1284		case IVHD_DEV_ALIAS_RANGE:
1285
1286			DUMP_printk("  DEV_ALIAS_RANGE\t\t "
1287				    "devid: %02x:%02x.%x flags: %02x "
1288				    "devid_to: %02x:%02x.%x\n",
1289				    PCI_BUS_NUM(e->devid),
1290				    PCI_SLOT(e->devid),
1291				    PCI_FUNC(e->devid),
1292				    e->flags,
1293				    PCI_BUS_NUM(e->ext >> 8),
1294				    PCI_SLOT(e->ext >> 8),
1295				    PCI_FUNC(e->ext >> 8));
1296
1297			devid_start = e->devid;
1298			flags = e->flags;
1299			devid_to = e->ext >> 8;
1300			ext_flags = 0;
1301			alias = true;
1302			break;
1303		case IVHD_DEV_EXT_SELECT:
1304
1305			DUMP_printk("  DEV_EXT_SELECT\t\t devid: %02x:%02x.%x "
1306				    "flags: %02x ext: %08x\n",
1307				    PCI_BUS_NUM(e->devid),
1308				    PCI_SLOT(e->devid),
1309				    PCI_FUNC(e->devid),
1310				    e->flags, e->ext);
1311
1312			devid = e->devid;
1313			set_dev_entry_from_acpi(iommu, devid, e->flags,
1314						e->ext);
1315			break;
1316		case IVHD_DEV_EXT_SELECT_RANGE:
1317
1318			DUMP_printk("  DEV_EXT_SELECT_RANGE\t devid: "
1319				    "%02x:%02x.%x flags: %02x ext: %08x\n",
1320				    PCI_BUS_NUM(e->devid),
1321				    PCI_SLOT(e->devid),
1322				    PCI_FUNC(e->devid),
1323				    e->flags, e->ext);
1324
1325			devid_start = e->devid;
1326			flags = e->flags;
1327			ext_flags = e->ext;
1328			alias = false;
1329			break;
1330		case IVHD_DEV_RANGE_END:
1331
1332			DUMP_printk("  DEV_RANGE_END\t\t devid: %02x:%02x.%x\n",
1333				    PCI_BUS_NUM(e->devid),
1334				    PCI_SLOT(e->devid),
1335				    PCI_FUNC(e->devid));
1336
1337			devid = e->devid;
1338			for (dev_i = devid_start; dev_i <= devid; ++dev_i) {
1339				if (alias) {
1340					amd_iommu_alias_table[dev_i] = devid_to;
1341					set_dev_entry_from_acpi(iommu,
1342						devid_to, flags, ext_flags);
1343				}
1344				set_dev_entry_from_acpi(iommu, dev_i,
1345							flags, ext_flags);
1346			}
1347			break;
1348		case IVHD_DEV_SPECIAL: {
1349			u8 handle, type;
1350			const char *var;
1351			u16 devid;
1352			int ret;
1353
1354			handle = e->ext & 0xff;
1355			devid  = (e->ext >>  8) & 0xffff;
1356			type   = (e->ext >> 24) & 0xff;
1357
1358			if (type == IVHD_SPECIAL_IOAPIC)
1359				var = "IOAPIC";
1360			else if (type == IVHD_SPECIAL_HPET)
1361				var = "HPET";
1362			else
1363				var = "UNKNOWN";
1364
1365			DUMP_printk("  DEV_SPECIAL(%s[%d])\t\tdevid: %02x:%02x.%x\n",
1366				    var, (int)handle,
1367				    PCI_BUS_NUM(devid),
1368				    PCI_SLOT(devid),
1369				    PCI_FUNC(devid));
1370
1371			ret = add_special_device(type, handle, &devid, false);
1372			if (ret)
1373				return ret;
1374
1375			/*
1376			 * add_special_device might update the devid in case a
1377			 * command-line override is present. So call
1378			 * set_dev_entry_from_acpi after add_special_device.
1379			 */
1380			set_dev_entry_from_acpi(iommu, devid, e->flags, 0);
1381
1382			break;
1383		}
1384		case IVHD_DEV_ACPI_HID: {
1385			u16 devid;
1386			u8 hid[ACPIHID_HID_LEN];
1387			u8 uid[ACPIHID_UID_LEN];
1388			int ret;
1389
1390			if (h->type != 0x40) {
1391				pr_err(FW_BUG "Invalid IVHD device type %#x\n",
1392				       e->type);
1393				break;
1394			}
1395
1396			memcpy(hid, (u8 *)(&e->ext), ACPIHID_HID_LEN - 1);
1397			hid[ACPIHID_HID_LEN - 1] = '\0';
1398
1399			if (!(*hid)) {
1400				pr_err(FW_BUG "Invalid HID.\n");
1401				break;
1402			}
1403
1404			uid[0] = '\0';
1405			switch (e->uidf) {
1406			case UID_NOT_PRESENT:
1407
1408				if (e->uidl != 0)
1409					pr_warn(FW_BUG "Invalid UID length.\n");
1410
1411				break;
1412			case UID_IS_INTEGER:
1413
1414				sprintf(uid, "%d", e->uid);
1415
1416				break;
1417			case UID_IS_CHARACTER:
1418
1419				memcpy(uid, &e->uid, e->uidl);
1420				uid[e->uidl] = '\0';
1421
1422				break;
1423			default:
1424				break;
1425			}
1426
1427			devid = e->devid;
1428			DUMP_printk("  DEV_ACPI_HID(%s[%s])\t\tdevid: %02x:%02x.%x\n",
1429				    hid, uid,
1430				    PCI_BUS_NUM(devid),
1431				    PCI_SLOT(devid),
1432				    PCI_FUNC(devid));
1433
1434			flags = e->flags;
1435
1436			ret = add_acpi_hid_device(hid, uid, &devid, false);
1437			if (ret)
1438				return ret;
1439
1440			/*
1441			 * add_special_device might update the devid in case a
1442			 * command-line override is present. So call
1443			 * set_dev_entry_from_acpi after add_special_device.
1444			 */
1445			set_dev_entry_from_acpi(iommu, devid, e->flags, 0);
1446
1447			break;
1448		}
1449		default:
1450			break;
1451		}
1452
1453		p += ivhd_entry_length(p);
1454	}
1455
1456	return 0;
1457}
1458
1459static void __init free_iommu_one(struct amd_iommu *iommu)
1460{
1461	free_cwwb_sem(iommu);
1462	free_command_buffer(iommu);
1463	free_event_buffer(iommu);
1464	free_ppr_log(iommu);
1465	free_ga_log(iommu);
1466	iommu_unmap_mmio_space(iommu);
1467}
1468
1469static void __init free_iommu_all(void)
1470{
1471	struct amd_iommu *iommu, *next;
1472
1473	for_each_iommu_safe(iommu, next) {
1474		list_del(&iommu->list);
1475		free_iommu_one(iommu);
1476		kfree(iommu);
1477	}
1478}
1479
1480/*
1481 * Family15h Model 10h-1fh erratum 746 (IOMMU Logging May Stall Translations)
1482 * Workaround:
1483 *     BIOS should disable L2B micellaneous clock gating by setting
1484 *     L2_L2B_CK_GATE_CONTROL[CKGateL2BMiscDisable](D0F2xF4_x90[2]) = 1b
1485 */
1486static void amd_iommu_erratum_746_workaround(struct amd_iommu *iommu)
1487{
1488	u32 value;
1489
1490	if ((boot_cpu_data.x86 != 0x15) ||
1491	    (boot_cpu_data.x86_model < 0x10) ||
1492	    (boot_cpu_data.x86_model > 0x1f))
1493		return;
1494
1495	pci_write_config_dword(iommu->dev, 0xf0, 0x90);
1496	pci_read_config_dword(iommu->dev, 0xf4, &value);
1497
1498	if (value & BIT(2))
1499		return;
1500
1501	/* Select NB indirect register 0x90 and enable writing */
1502	pci_write_config_dword(iommu->dev, 0xf0, 0x90 | (1 << 8));
1503
1504	pci_write_config_dword(iommu->dev, 0xf4, value | 0x4);
1505	pci_info(iommu->dev, "Applying erratum 746 workaround\n");
1506
1507	/* Clear the enable writing bit */
1508	pci_write_config_dword(iommu->dev, 0xf0, 0x90);
1509}
1510
1511/*
1512 * Family15h Model 30h-3fh (IOMMU Mishandles ATS Write Permission)
1513 * Workaround:
1514 *     BIOS should enable ATS write permission check by setting
1515 *     L2_DEBUG_3[AtsIgnoreIWDis](D0F2xF4_x47[0]) = 1b
1516 */
1517static void amd_iommu_ats_write_check_workaround(struct amd_iommu *iommu)
1518{
1519	u32 value;
1520
1521	if ((boot_cpu_data.x86 != 0x15) ||
1522	    (boot_cpu_data.x86_model < 0x30) ||
1523	    (boot_cpu_data.x86_model > 0x3f))
1524		return;
1525
1526	/* Test L2_DEBUG_3[AtsIgnoreIWDis] == 1 */
1527	value = iommu_read_l2(iommu, 0x47);
1528
1529	if (value & BIT(0))
1530		return;
1531
1532	/* Set L2_DEBUG_3[AtsIgnoreIWDis] = 1 */
1533	iommu_write_l2(iommu, 0x47, value | BIT(0));
1534
1535	pci_info(iommu->dev, "Applying ATS write check workaround\n");
1536}
1537
1538/*
1539 * This function clues the initialization function for one IOMMU
1540 * together and also allocates the command buffer and programs the
1541 * hardware. It does NOT enable the IOMMU. This is done afterwards.
1542 */
1543static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
1544{
1545	int ret;
1546
1547	raw_spin_lock_init(&iommu->lock);
1548	iommu->cmd_sem_val = 0;
1549
1550	/* Add IOMMU to internal data structures */
1551	list_add_tail(&iommu->list, &amd_iommu_list);
1552	iommu->index = amd_iommus_present++;
1553
1554	if (unlikely(iommu->index >= MAX_IOMMUS)) {
1555		WARN(1, "System has more IOMMUs than supported by this driver\n");
1556		return -ENOSYS;
1557	}
1558
1559	/* Index is fine - add IOMMU to the array */
1560	amd_iommus[iommu->index] = iommu;
1561
1562	/*
1563	 * Copy data from ACPI table entry to the iommu struct
1564	 */
1565	iommu->devid   = h->devid;
1566	iommu->cap_ptr = h->cap_ptr;
1567	iommu->pci_seg = h->pci_seg;
1568	iommu->mmio_phys = h->mmio_phys;
1569
1570	switch (h->type) {
1571	case 0x10:
1572		/* Check if IVHD EFR contains proper max banks/counters */
1573		if ((h->efr_attr != 0) &&
1574		    ((h->efr_attr & (0xF << 13)) != 0) &&
1575		    ((h->efr_attr & (0x3F << 17)) != 0))
1576			iommu->mmio_phys_end = MMIO_REG_END_OFFSET;
1577		else
1578			iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET;
1579
1580		/*
1581		 * Note: GA (128-bit IRTE) mode requires cmpxchg16b supports.
1582		 * GAM also requires GA mode. Therefore, we need to
1583		 * check cmpxchg16b support before enabling it.
1584		 */
1585		if (!boot_cpu_has(X86_FEATURE_CX16) ||
1586		    ((h->efr_attr & (0x1 << IOMMU_FEAT_GASUP_SHIFT)) == 0))
1587			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY;
1588		break;
1589	case 0x11:
1590	case 0x40:
1591		if (h->efr_reg & (1 << 9))
1592			iommu->mmio_phys_end = MMIO_REG_END_OFFSET;
1593		else
1594			iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET;
1595
1596		/*
1597		 * Note: GA (128-bit IRTE) mode requires cmpxchg16b supports.
1598		 * XT, GAM also requires GA mode. Therefore, we need to
1599		 * check cmpxchg16b support before enabling them.
1600		 */
1601		if (!boot_cpu_has(X86_FEATURE_CX16) ||
1602		    ((h->efr_reg & (0x1 << IOMMU_EFR_GASUP_SHIFT)) == 0)) {
1603			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY;
1604			break;
1605		}
1606
1607		/*
1608		 * Note: Since iommu_update_intcapxt() leverages
1609		 * the IOMMU MMIO access to MSI capability block registers
1610		 * for MSI address lo/hi/data, we need to check both
1611		 * EFR[XtSup] and EFR[MsiCapMmioSup] for x2APIC support.
1612		 */
1613		if ((h->efr_reg & BIT(IOMMU_EFR_XTSUP_SHIFT)) &&
1614		    (h->efr_reg & BIT(IOMMU_EFR_MSICAPMMIOSUP_SHIFT)))
1615			amd_iommu_xt_mode = IRQ_REMAP_X2APIC_MODE;
1616
1617		early_iommu_features_init(iommu, h);
1618
1619		break;
1620	default:
1621		return -EINVAL;
1622	}
1623
1624	iommu->mmio_base = iommu_map_mmio_space(iommu->mmio_phys,
1625						iommu->mmio_phys_end);
1626	if (!iommu->mmio_base)
1627		return -ENOMEM;
1628
1629	if (alloc_cwwb_sem(iommu))
1630		return -ENOMEM;
1631
1632	if (alloc_command_buffer(iommu))
1633		return -ENOMEM;
1634
1635	if (alloc_event_buffer(iommu))
1636		return -ENOMEM;
1637
1638	iommu->int_enabled = false;
1639
1640	init_translation_status(iommu);
1641	if (translation_pre_enabled(iommu) && !is_kdump_kernel()) {
1642		iommu_disable(iommu);
1643		clear_translation_pre_enabled(iommu);
1644		pr_warn("Translation was enabled for IOMMU:%d but we are not in kdump mode\n",
1645			iommu->index);
1646	}
1647	if (amd_iommu_pre_enabled)
1648		amd_iommu_pre_enabled = translation_pre_enabled(iommu);
1649
1650	ret = init_iommu_from_acpi(iommu, h);
1651	if (ret)
1652		return ret;
1653
1654	ret = amd_iommu_create_irq_domain(iommu);
1655	if (ret)
1656		return ret;
1657
1658	/*
1659	 * Make sure IOMMU is not considered to translate itself. The IVRS
1660	 * table tells us so, but this is a lie!
1661	 */
1662	amd_iommu_rlookup_table[iommu->devid] = NULL;
1663
1664	return 0;
1665}
1666
1667/**
1668 * get_highest_supported_ivhd_type - Look up the appropriate IVHD type
1669 * @ivrs: Pointer to the IVRS header
1670 *
1671 * This function search through all IVDB of the maximum supported IVHD
1672 */
1673static u8 get_highest_supported_ivhd_type(struct acpi_table_header *ivrs)
1674{
1675	u8 *base = (u8 *)ivrs;
1676	struct ivhd_header *ivhd = (struct ivhd_header *)
1677					(base + IVRS_HEADER_LENGTH);
1678	u8 last_type = ivhd->type;
1679	u16 devid = ivhd->devid;
1680
1681	while (((u8 *)ivhd - base < ivrs->length) &&
1682	       (ivhd->type <= ACPI_IVHD_TYPE_MAX_SUPPORTED)) {
1683		u8 *p = (u8 *) ivhd;
1684
1685		if (ivhd->devid == devid)
1686			last_type = ivhd->type;
1687		ivhd = (struct ivhd_header *)(p + ivhd->length);
1688	}
1689
1690	return last_type;
1691}
1692
1693/*
1694 * Iterates over all IOMMU entries in the ACPI table, allocates the
1695 * IOMMU structure and initializes it with init_iommu_one()
1696 */
1697static int __init init_iommu_all(struct acpi_table_header *table)
1698{
1699	u8 *p = (u8 *)table, *end = (u8 *)table;
1700	struct ivhd_header *h;
1701	struct amd_iommu *iommu;
1702	int ret;
1703
1704	end += table->length;
1705	p += IVRS_HEADER_LENGTH;
1706
1707	while (p < end) {
1708		h = (struct ivhd_header *)p;
1709		if (*p == amd_iommu_target_ivhd_type) {
1710
1711			DUMP_printk("device: %02x:%02x.%01x cap: %04x "
1712				    "seg: %d flags: %01x info %04x\n",
1713				    PCI_BUS_NUM(h->devid), PCI_SLOT(h->devid),
1714				    PCI_FUNC(h->devid), h->cap_ptr,
1715				    h->pci_seg, h->flags, h->info);
1716			DUMP_printk("       mmio-addr: %016llx\n",
1717				    h->mmio_phys);
1718
1719			iommu = kzalloc(sizeof(struct amd_iommu), GFP_KERNEL);
1720			if (iommu == NULL)
1721				return -ENOMEM;
1722
1723			ret = init_iommu_one(iommu, h);
1724			if (ret)
1725				return ret;
1726		}
1727		p += h->length;
1728
1729	}
1730	WARN_ON(p != end);
1731
1732	return 0;
1733}
1734
1735static void init_iommu_perf_ctr(struct amd_iommu *iommu)
1736{
1737	u64 val;
1738	struct pci_dev *pdev = iommu->dev;
1739
1740	if (!iommu_feature(iommu, FEATURE_PC))
1741		return;
1742
1743	amd_iommu_pc_present = true;
1744
1745	pci_info(pdev, "IOMMU performance counters supported\n");
1746
1747	val = readl(iommu->mmio_base + MMIO_CNTR_CONF_OFFSET);
1748	iommu->max_banks = (u8) ((val >> 12) & 0x3f);
1749	iommu->max_counters = (u8) ((val >> 7) & 0xf);
1750
1751	return;
1752}
1753
1754static ssize_t amd_iommu_show_cap(struct device *dev,
1755				  struct device_attribute *attr,
1756				  char *buf)
1757{
1758	struct amd_iommu *iommu = dev_to_amd_iommu(dev);
1759	return sprintf(buf, "%x\n", iommu->cap);
1760}
1761static DEVICE_ATTR(cap, S_IRUGO, amd_iommu_show_cap, NULL);
1762
1763static ssize_t amd_iommu_show_features(struct device *dev,
1764				       struct device_attribute *attr,
1765				       char *buf)
1766{
1767	struct amd_iommu *iommu = dev_to_amd_iommu(dev);
1768	return sprintf(buf, "%llx\n", iommu->features);
1769}
1770static DEVICE_ATTR(features, S_IRUGO, amd_iommu_show_features, NULL);
1771
1772static struct attribute *amd_iommu_attrs[] = {
1773	&dev_attr_cap.attr,
1774	&dev_attr_features.attr,
1775	NULL,
1776};
1777
1778static struct attribute_group amd_iommu_group = {
1779	.name = "amd-iommu",
1780	.attrs = amd_iommu_attrs,
1781};
1782
1783static const struct attribute_group *amd_iommu_groups[] = {
1784	&amd_iommu_group,
1785	NULL,
1786};
1787
1788/*
1789 * Note: IVHD 0x11 and 0x40 also contains exact copy
1790 * of the IOMMU Extended Feature Register [MMIO Offset 0030h].
1791 * Default to EFR in IVHD since it is available sooner (i.e. before PCI init).
1792 */
1793static void __init late_iommu_features_init(struct amd_iommu *iommu)
1794{
1795	u64 features;
1796
1797	if (!(iommu->cap & (1 << IOMMU_CAP_EFR)))
1798		return;
1799
1800	/* read extended feature bits */
1801	features = readq(iommu->mmio_base + MMIO_EXT_FEATURES);
1802
1803	if (!iommu->features) {
1804		iommu->features = features;
1805		return;
1806	}
1807
1808	/*
1809	 * Sanity check and warn if EFR values from
1810	 * IVHD and MMIO conflict.
1811	 */
1812	if (features != iommu->features)
1813		pr_warn(FW_WARN "EFR mismatch. Use IVHD EFR (%#llx : %#llx).\n",
1814			features, iommu->features);
1815}
1816
1817static int __init iommu_init_pci(struct amd_iommu *iommu)
1818{
1819	int cap_ptr = iommu->cap_ptr;
1820	int ret;
1821
1822	iommu->dev = pci_get_domain_bus_and_slot(0, PCI_BUS_NUM(iommu->devid),
1823						 iommu->devid & 0xff);
1824	if (!iommu->dev)
1825		return -ENODEV;
1826
1827	/* Prevent binding other PCI device drivers to IOMMU devices */
1828	iommu->dev->match_driver = false;
1829
1830	pci_read_config_dword(iommu->dev, cap_ptr + MMIO_CAP_HDR_OFFSET,
1831			      &iommu->cap);
1832
1833	if (!(iommu->cap & (1 << IOMMU_CAP_IOTLB)))
1834		amd_iommu_iotlb_sup = false;
1835
1836	late_iommu_features_init(iommu);
1837
1838	if (iommu_feature(iommu, FEATURE_GT)) {
1839		int glxval;
1840		u32 max_pasid;
1841		u64 pasmax;
1842
1843		pasmax = iommu->features & FEATURE_PASID_MASK;
1844		pasmax >>= FEATURE_PASID_SHIFT;
1845		max_pasid  = (1 << (pasmax + 1)) - 1;
1846
1847		amd_iommu_max_pasid = min(amd_iommu_max_pasid, max_pasid);
1848
1849		BUG_ON(amd_iommu_max_pasid & ~PASID_MASK);
1850
1851		glxval   = iommu->features & FEATURE_GLXVAL_MASK;
1852		glxval >>= FEATURE_GLXVAL_SHIFT;
1853
1854		if (amd_iommu_max_glx_val == -1)
1855			amd_iommu_max_glx_val = glxval;
1856		else
1857			amd_iommu_max_glx_val = min(amd_iommu_max_glx_val, glxval);
1858	}
1859
1860	if (iommu_feature(iommu, FEATURE_GT) &&
1861	    iommu_feature(iommu, FEATURE_PPR)) {
1862		iommu->is_iommu_v2   = true;
1863		amd_iommu_v2_present = true;
1864	}
1865
1866	if (iommu_feature(iommu, FEATURE_PPR) && alloc_ppr_log(iommu))
1867		return -ENOMEM;
1868
1869	ret = iommu_init_ga_log(iommu);
1870	if (ret)
1871		return ret;
1872
1873	if (iommu->cap & (1UL << IOMMU_CAP_NPCACHE))
1874		amd_iommu_np_cache = true;
1875
1876	init_iommu_perf_ctr(iommu);
1877
1878	if (is_rd890_iommu(iommu->dev)) {
1879		int i, j;
1880
1881		iommu->root_pdev =
1882			pci_get_domain_bus_and_slot(0, iommu->dev->bus->number,
1883						    PCI_DEVFN(0, 0));
1884
1885		/*
1886		 * Some rd890 systems may not be fully reconfigured by the
1887		 * BIOS, so it's necessary for us to store this information so
1888		 * it can be reprogrammed on resume
1889		 */
1890		pci_read_config_dword(iommu->dev, iommu->cap_ptr + 4,
1891				&iommu->stored_addr_lo);
1892		pci_read_config_dword(iommu->dev, iommu->cap_ptr + 8,
1893				&iommu->stored_addr_hi);
1894
1895		/* Low bit locks writes to configuration space */
1896		iommu->stored_addr_lo &= ~1;
1897
1898		for (i = 0; i < 6; i++)
1899			for (j = 0; j < 0x12; j++)
1900				iommu->stored_l1[i][j] = iommu_read_l1(iommu, i, j);
1901
1902		for (i = 0; i < 0x83; i++)
1903			iommu->stored_l2[i] = iommu_read_l2(iommu, i);
1904	}
1905
1906	amd_iommu_erratum_746_workaround(iommu);
1907	amd_iommu_ats_write_check_workaround(iommu);
1908
1909	iommu_device_sysfs_add(&iommu->iommu, &iommu->dev->dev,
1910			       amd_iommu_groups, "ivhd%d", iommu->index);
1911	iommu_device_set_ops(&iommu->iommu, &amd_iommu_ops);
1912	iommu_device_register(&iommu->iommu);
1913
1914	return pci_enable_device(iommu->dev);
1915}
1916
1917static void print_iommu_info(void)
1918{
1919	static const char * const feat_str[] = {
1920		"PreF", "PPR", "X2APIC", "NX", "GT", "[5]",
1921		"IA", "GA", "HE", "PC"
1922	};
1923	struct amd_iommu *iommu;
1924
1925	for_each_iommu(iommu) {
1926		struct pci_dev *pdev = iommu->dev;
1927		int i;
1928
1929		pci_info(pdev, "Found IOMMU cap 0x%hx\n", iommu->cap_ptr);
1930
1931		if (iommu->cap & (1 << IOMMU_CAP_EFR)) {
1932			pr_info("Extended features (%#llx):", iommu->features);
1933
1934			for (i = 0; i < ARRAY_SIZE(feat_str); ++i) {
1935				if (iommu_feature(iommu, (1ULL << i)))
1936					pr_cont(" %s", feat_str[i]);
1937			}
1938
1939			if (iommu->features & FEATURE_GAM_VAPIC)
1940				pr_cont(" GA_vAPIC");
1941
1942			pr_cont("\n");
1943		}
1944	}
1945	if (irq_remapping_enabled) {
1946		pr_info("Interrupt remapping enabled\n");
1947		if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir))
1948			pr_info("Virtual APIC enabled\n");
1949		if (amd_iommu_xt_mode == IRQ_REMAP_X2APIC_MODE)
1950			pr_info("X2APIC enabled\n");
1951	}
1952}
1953
1954static int __init amd_iommu_init_pci(void)
1955{
1956	struct amd_iommu *iommu;
1957	int ret = 0;
1958
1959	for_each_iommu(iommu) {
1960		ret = iommu_init_pci(iommu);
1961		if (ret)
1962			break;
1963
1964		/* Need to setup range after PCI init */
1965		iommu_set_cwwb_range(iommu);
1966	}
1967
1968	/*
1969	 * Order is important here to make sure any unity map requirements are
1970	 * fulfilled. The unity mappings are created and written to the device
1971	 * table during the amd_iommu_init_api() call.
1972	 *
1973	 * After that we call init_device_table_dma() to make sure any
1974	 * uninitialized DTE will block DMA, and in the end we flush the caches
1975	 * of all IOMMUs to make sure the changes to the device table are
1976	 * active.
1977	 */
1978	ret = amd_iommu_init_api();
1979
1980	init_device_table_dma();
1981
1982	for_each_iommu(iommu)
1983		iommu_flush_all_caches(iommu);
1984
1985	if (!ret)
1986		print_iommu_info();
1987
1988	return ret;
1989}
1990
1991/****************************************************************************
1992 *
1993 * The following functions initialize the MSI interrupts for all IOMMUs
1994 * in the system. It's a bit challenging because there could be multiple
1995 * IOMMUs per PCI BDF but we can call pci_enable_msi(x) only once per
1996 * pci_dev.
1997 *
1998 ****************************************************************************/
1999
2000static int iommu_setup_msi(struct amd_iommu *iommu)
2001{
2002	int r;
2003
2004	r = pci_enable_msi(iommu->dev);
2005	if (r)
2006		return r;
2007
2008	r = request_threaded_irq(iommu->dev->irq,
2009				 amd_iommu_int_handler,
2010				 amd_iommu_int_thread,
2011				 0, "AMD-Vi",
2012				 iommu);
2013
2014	if (r) {
2015		pci_disable_msi(iommu->dev);
2016		return r;
2017	}
2018
2019	iommu->int_enabled = true;
2020
2021	return 0;
2022}
2023
2024#define XT_INT_DEST_MODE(x)	(((x) & 0x1ULL) << 2)
2025#define XT_INT_DEST_LO(x)	(((x) & 0xFFFFFFULL) << 8)
2026#define XT_INT_VEC(x)		(((x) & 0xFFULL) << 32)
2027#define XT_INT_DEST_HI(x)	((((x) >> 24) & 0xFFULL) << 56)
2028
2029/*
2030 * Setup the IntCapXT registers with interrupt routing information
2031 * based on the PCI MSI capability block registers, accessed via
2032 * MMIO MSI address low/hi and MSI data registers.
2033 */
2034static void iommu_update_intcapxt(struct amd_iommu *iommu)
2035{
2036	u64 val;
2037	u32 addr_lo = readl(iommu->mmio_base + MMIO_MSI_ADDR_LO_OFFSET);
2038	u32 addr_hi = readl(iommu->mmio_base + MMIO_MSI_ADDR_HI_OFFSET);
2039	u32 data    = readl(iommu->mmio_base + MMIO_MSI_DATA_OFFSET);
2040	bool dm     = (addr_lo >> MSI_ADDR_DEST_MODE_SHIFT) & 0x1;
2041	u32 dest    = ((addr_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xFF);
2042
2043	if (x2apic_enabled())
2044		dest |= MSI_ADDR_EXT_DEST_ID(addr_hi);
2045
2046	val = XT_INT_VEC(data & 0xFF) |
2047	      XT_INT_DEST_MODE(dm) |
2048	      XT_INT_DEST_LO(dest) |
2049	      XT_INT_DEST_HI(dest);
2050
2051	/**
2052	 * Current IOMMU implemtation uses the same IRQ for all
2053	 * 3 IOMMU interrupts.
2054	 */
2055	writeq(val, iommu->mmio_base + MMIO_INTCAPXT_EVT_OFFSET);
2056	writeq(val, iommu->mmio_base + MMIO_INTCAPXT_PPR_OFFSET);
2057	writeq(val, iommu->mmio_base + MMIO_INTCAPXT_GALOG_OFFSET);
2058}
2059
2060static void _irq_notifier_notify(struct irq_affinity_notify *notify,
2061				 const cpumask_t *mask)
2062{
2063	struct amd_iommu *iommu;
2064
2065	for_each_iommu(iommu) {
2066		if (iommu->dev->irq == notify->irq) {
2067			iommu_update_intcapxt(iommu);
2068			break;
2069		}
2070	}
2071}
2072
2073static void _irq_notifier_release(struct kref *ref)
2074{
2075}
2076
2077static int iommu_init_intcapxt(struct amd_iommu *iommu)
2078{
2079	int ret;
2080	struct irq_affinity_notify *notify = &iommu->intcapxt_notify;
2081
2082	/**
2083	 * IntCapXT requires XTSup=1 and MsiCapMmioSup=1,
2084	 * which can be inferred from amd_iommu_xt_mode.
2085	 */
2086	if (amd_iommu_xt_mode != IRQ_REMAP_X2APIC_MODE)
2087		return 0;
2088
2089	/**
2090	 * Also, we need to setup notifier to update the IntCapXT registers
2091	 * whenever the irq affinity is changed from user-space.
2092	 */
2093	notify->irq = iommu->dev->irq;
2094	notify->notify = _irq_notifier_notify,
2095	notify->release = _irq_notifier_release,
2096	ret = irq_set_affinity_notifier(iommu->dev->irq, notify);
2097	if (ret) {
2098		pr_err("Failed to register irq affinity notifier (devid=%#x, irq %d)\n",
2099		       iommu->devid, iommu->dev->irq);
2100		return ret;
2101	}
2102
2103	iommu_update_intcapxt(iommu);
2104	iommu_feature_enable(iommu, CONTROL_INTCAPXT_EN);
2105	return ret;
2106}
2107
2108static int iommu_init_msi(struct amd_iommu *iommu)
2109{
2110	int ret;
2111
2112	if (iommu->int_enabled)
2113		goto enable_faults;
2114
2115	if (iommu->dev->msi_cap)
2116		ret = iommu_setup_msi(iommu);
2117	else
2118		ret = -ENODEV;
2119
2120	if (ret)
2121		return ret;
2122
2123enable_faults:
2124	ret = iommu_init_intcapxt(iommu);
2125	if (ret)
2126		return ret;
2127
2128	iommu_feature_enable(iommu, CONTROL_EVT_INT_EN);
2129
2130	if (iommu->ppr_log != NULL)
2131		iommu_feature_enable(iommu, CONTROL_PPRINT_EN);
2132
2133	iommu_ga_log_enable(iommu);
2134
2135	return 0;
2136}
2137
2138/****************************************************************************
2139 *
2140 * The next functions belong to the third pass of parsing the ACPI
2141 * table. In this last pass the memory mapping requirements are
2142 * gathered (like exclusion and unity mapping ranges).
2143 *
2144 ****************************************************************************/
2145
2146static void __init free_unity_maps(void)
2147{
2148	struct unity_map_entry *entry, *next;
2149
2150	list_for_each_entry_safe(entry, next, &amd_iommu_unity_map, list) {
2151		list_del(&entry->list);
2152		kfree(entry);
2153	}
2154}
2155
2156/* called for unity map ACPI definition */
2157static int __init init_unity_map_range(struct ivmd_header *m)
2158{
2159	struct unity_map_entry *e = NULL;
2160	char *s;
2161
2162	e = kzalloc(sizeof(*e), GFP_KERNEL);
2163	if (e == NULL)
2164		return -ENOMEM;
2165
2166	switch (m->type) {
2167	default:
2168		kfree(e);
2169		return 0;
2170	case ACPI_IVMD_TYPE:
2171		s = "IVMD_TYPEi\t\t\t";
2172		e->devid_start = e->devid_end = m->devid;
2173		break;
2174	case ACPI_IVMD_TYPE_ALL:
2175		s = "IVMD_TYPE_ALL\t\t";
2176		e->devid_start = 0;
2177		e->devid_end = amd_iommu_last_bdf;
2178		break;
2179	case ACPI_IVMD_TYPE_RANGE:
2180		s = "IVMD_TYPE_RANGE\t\t";
2181		e->devid_start = m->devid;
2182		e->devid_end = m->aux;
2183		break;
2184	}
2185	e->address_start = PAGE_ALIGN(m->range_start);
2186	e->address_end = e->address_start + PAGE_ALIGN(m->range_length);
2187	e->prot = m->flags >> 1;
2188
2189	/*
2190	 * Treat per-device exclusion ranges as r/w unity-mapped regions
2191	 * since some buggy BIOSes might lead to the overwritten exclusion
2192	 * range (exclusion_start and exclusion_length members). This
2193	 * happens when there are multiple exclusion ranges (IVMD entries)
2194	 * defined in ACPI table.
2195	 */
2196	if (m->flags & IVMD_FLAG_EXCL_RANGE)
2197		e->prot = (IVMD_FLAG_IW | IVMD_FLAG_IR) >> 1;
2198
2199	DUMP_printk("%s devid_start: %02x:%02x.%x devid_end: %02x:%02x.%x"
2200		    " range_start: %016llx range_end: %016llx flags: %x\n", s,
2201		    PCI_BUS_NUM(e->devid_start), PCI_SLOT(e->devid_start),
2202		    PCI_FUNC(e->devid_start), PCI_BUS_NUM(e->devid_end),
2203		    PCI_SLOT(e->devid_end), PCI_FUNC(e->devid_end),
2204		    e->address_start, e->address_end, m->flags);
2205
2206	list_add_tail(&e->list, &amd_iommu_unity_map);
2207
2208	return 0;
2209}
2210
2211/* iterates over all memory definitions we find in the ACPI table */
2212static int __init init_memory_definitions(struct acpi_table_header *table)
2213{
2214	u8 *p = (u8 *)table, *end = (u8 *)table;
2215	struct ivmd_header *m;
2216
2217	end += table->length;
2218	p += IVRS_HEADER_LENGTH;
2219
2220	while (p < end) {
2221		m = (struct ivmd_header *)p;
2222		if (m->flags & (IVMD_FLAG_UNITY_MAP | IVMD_FLAG_EXCL_RANGE))
2223			init_unity_map_range(m);
2224
2225		p += m->length;
2226	}
2227
2228	return 0;
2229}
2230
2231/*
2232 * Init the device table to not allow DMA access for devices
2233 */
2234static void init_device_table_dma(void)
2235{
2236	u32 devid;
2237
2238	for (devid = 0; devid <= amd_iommu_last_bdf; ++devid) {
2239		set_dev_entry_bit(devid, DEV_ENTRY_VALID);
2240		set_dev_entry_bit(devid, DEV_ENTRY_TRANSLATION);
2241	}
2242}
2243
2244static void __init uninit_device_table_dma(void)
2245{
2246	u32 devid;
2247
2248	for (devid = 0; devid <= amd_iommu_last_bdf; ++devid) {
2249		amd_iommu_dev_table[devid].data[0] = 0ULL;
2250		amd_iommu_dev_table[devid].data[1] = 0ULL;
2251	}
2252}
2253
2254static void init_device_table(void)
2255{
2256	u32 devid;
2257
2258	if (!amd_iommu_irq_remap)
2259		return;
2260
2261	for (devid = 0; devid <= amd_iommu_last_bdf; ++devid)
2262		set_dev_entry_bit(devid, DEV_ENTRY_IRQ_TBL_EN);
2263}
2264
2265static void iommu_init_flags(struct amd_iommu *iommu)
2266{
2267	iommu->acpi_flags & IVHD_FLAG_HT_TUN_EN_MASK ?
2268		iommu_feature_enable(iommu, CONTROL_HT_TUN_EN) :
2269		iommu_feature_disable(iommu, CONTROL_HT_TUN_EN);
2270
2271	iommu->acpi_flags & IVHD_FLAG_PASSPW_EN_MASK ?
2272		iommu_feature_enable(iommu, CONTROL_PASSPW_EN) :
2273		iommu_feature_disable(iommu, CONTROL_PASSPW_EN);
2274
2275	iommu->acpi_flags & IVHD_FLAG_RESPASSPW_EN_MASK ?
2276		iommu_feature_enable(iommu, CONTROL_RESPASSPW_EN) :
2277		iommu_feature_disable(iommu, CONTROL_RESPASSPW_EN);
2278
2279	iommu->acpi_flags & IVHD_FLAG_ISOC_EN_MASK ?
2280		iommu_feature_enable(iommu, CONTROL_ISOC_EN) :
2281		iommu_feature_disable(iommu, CONTROL_ISOC_EN);
2282
2283	/*
2284	 * make IOMMU memory accesses cache coherent
2285	 */
2286	iommu_feature_enable(iommu, CONTROL_COHERENT_EN);
2287
2288	/* Set IOTLB invalidation timeout to 1s */
2289	iommu_set_inv_tlb_timeout(iommu, CTRL_INV_TO_1S);
2290}
2291
2292static void iommu_apply_resume_quirks(struct amd_iommu *iommu)
2293{
2294	int i, j;
2295	u32 ioc_feature_control;
2296	struct pci_dev *pdev = iommu->root_pdev;
2297
2298	/* RD890 BIOSes may not have completely reconfigured the iommu */
2299	if (!is_rd890_iommu(iommu->dev) || !pdev)
2300		return;
2301
2302	/*
2303	 * First, we need to ensure that the iommu is enabled. This is
2304	 * controlled by a register in the northbridge
2305	 */
2306
2307	/* Select Northbridge indirect register 0x75 and enable writing */
2308	pci_write_config_dword(pdev, 0x60, 0x75 | (1 << 7));
2309	pci_read_config_dword(pdev, 0x64, &ioc_feature_control);
2310
2311	/* Enable the iommu */
2312	if (!(ioc_feature_control & 0x1))
2313		pci_write_config_dword(pdev, 0x64, ioc_feature_control | 1);
2314
2315	/* Restore the iommu BAR */
2316	pci_write_config_dword(iommu->dev, iommu->cap_ptr + 4,
2317			       iommu->stored_addr_lo);
2318	pci_write_config_dword(iommu->dev, iommu->cap_ptr + 8,
2319			       iommu->stored_addr_hi);
2320
2321	/* Restore the l1 indirect regs for each of the 6 l1s */
2322	for (i = 0; i < 6; i++)
2323		for (j = 0; j < 0x12; j++)
2324			iommu_write_l1(iommu, i, j, iommu->stored_l1[i][j]);
2325
2326	/* Restore the l2 indirect regs */
2327	for (i = 0; i < 0x83; i++)
2328		iommu_write_l2(iommu, i, iommu->stored_l2[i]);
2329
2330	/* Lock PCI setup registers */
2331	pci_write_config_dword(iommu->dev, iommu->cap_ptr + 4,
2332			       iommu->stored_addr_lo | 1);
2333}
2334
2335static void iommu_enable_ga(struct amd_iommu *iommu)
2336{
2337#ifdef CONFIG_IRQ_REMAP
2338	switch (amd_iommu_guest_ir) {
2339	case AMD_IOMMU_GUEST_IR_VAPIC:
2340		iommu_feature_enable(iommu, CONTROL_GAM_EN);
2341		fallthrough;
2342	case AMD_IOMMU_GUEST_IR_LEGACY_GA:
2343		iommu_feature_enable(iommu, CONTROL_GA_EN);
2344		iommu->irte_ops = &irte_128_ops;
2345		break;
2346	default:
2347		iommu->irte_ops = &irte_32_ops;
2348		break;
2349	}
2350#endif
2351}
2352
2353static void early_enable_iommu(struct amd_iommu *iommu)
2354{
2355	iommu_disable(iommu);
2356	iommu_init_flags(iommu);
2357	iommu_set_device_table(iommu);
2358	iommu_enable_command_buffer(iommu);
2359	iommu_enable_event_buffer(iommu);
2360	iommu_set_exclusion_range(iommu);
2361	iommu_enable_ga(iommu);
2362	iommu_enable_xt(iommu);
2363	iommu_enable(iommu);
2364	iommu_flush_all_caches(iommu);
2365}
2366
2367/*
2368 * This function finally enables all IOMMUs found in the system after
2369 * they have been initialized.
2370 *
2371 * Or if in kdump kernel and IOMMUs are all pre-enabled, try to copy
2372 * the old content of device table entries. Not this case or copy failed,
2373 * just continue as normal kernel does.
2374 */
2375static void early_enable_iommus(void)
2376{
2377	struct amd_iommu *iommu;
2378
2379
2380	if (!copy_device_table()) {
2381		/*
2382		 * If come here because of failure in copying device table from old
2383		 * kernel with all IOMMUs enabled, print error message and try to
2384		 * free allocated old_dev_tbl_cpy.
2385		 */
2386		if (amd_iommu_pre_enabled)
2387			pr_err("Failed to copy DEV table from previous kernel.\n");
2388		if (old_dev_tbl_cpy != NULL)
2389			free_pages((unsigned long)old_dev_tbl_cpy,
2390					get_order(dev_table_size));
2391
2392		for_each_iommu(iommu) {
2393			clear_translation_pre_enabled(iommu);
2394			early_enable_iommu(iommu);
2395		}
2396	} else {
2397		pr_info("Copied DEV table from previous kernel.\n");
2398		free_pages((unsigned long)amd_iommu_dev_table,
2399				get_order(dev_table_size));
2400		amd_iommu_dev_table = old_dev_tbl_cpy;
2401		for_each_iommu(iommu) {
2402			iommu_disable_command_buffer(iommu);
2403			iommu_disable_event_buffer(iommu);
2404			iommu_enable_command_buffer(iommu);
2405			iommu_enable_event_buffer(iommu);
2406			iommu_enable_ga(iommu);
2407			iommu_enable_xt(iommu);
2408			iommu_set_device_table(iommu);
2409			iommu_flush_all_caches(iommu);
2410		}
2411	}
2412
2413#ifdef CONFIG_IRQ_REMAP
2414	/*
2415	 * Note: We have already checked GASup from IVRS table.
2416	 *       Now, we need to make sure that GAMSup is set.
2417	 */
2418	if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) &&
2419	    !check_feature_on_all_iommus(FEATURE_GAM_VAPIC))
2420		amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY_GA;
2421
2422	if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir))
2423		amd_iommu_irq_ops.capability |= (1 << IRQ_POSTING_CAP);
2424#endif
2425}
2426
2427static void enable_iommus_v2(void)
2428{
2429	struct amd_iommu *iommu;
2430
2431	for_each_iommu(iommu) {
2432		iommu_enable_ppr_log(iommu);
2433		iommu_enable_gt(iommu);
2434	}
2435}
2436
2437static void enable_iommus(void)
2438{
2439	early_enable_iommus();
2440
2441	enable_iommus_v2();
2442}
2443
2444static void disable_iommus(void)
2445{
2446	struct amd_iommu *iommu;
2447
2448	for_each_iommu(iommu)
2449		iommu_disable(iommu);
2450
2451#ifdef CONFIG_IRQ_REMAP
2452	if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir))
2453		amd_iommu_irq_ops.capability &= ~(1 << IRQ_POSTING_CAP);
2454#endif
2455}
2456
2457/*
2458 * Suspend/Resume support
2459 * disable suspend until real resume implemented
2460 */
2461
2462static void amd_iommu_resume(void)
2463{
2464	struct amd_iommu *iommu;
2465
2466	for_each_iommu(iommu)
2467		iommu_apply_resume_quirks(iommu);
2468
2469	/* re-load the hardware */
2470	enable_iommus();
2471
2472	amd_iommu_enable_interrupts();
2473}
2474
2475static int amd_iommu_suspend(void)
2476{
2477	/* disable IOMMUs to go out of the way for BIOS */
2478	disable_iommus();
2479
2480	return 0;
2481}
2482
2483static struct syscore_ops amd_iommu_syscore_ops = {
2484	.suspend = amd_iommu_suspend,
2485	.resume = amd_iommu_resume,
2486};
2487
2488static void __init free_iommu_resources(void)
2489{
2490	kmemleak_free(irq_lookup_table);
2491	free_pages((unsigned long)irq_lookup_table,
2492		   get_order(rlookup_table_size));
2493	irq_lookup_table = NULL;
2494
2495	kmem_cache_destroy(amd_iommu_irq_cache);
2496	amd_iommu_irq_cache = NULL;
2497
2498	free_pages((unsigned long)amd_iommu_rlookup_table,
2499		   get_order(rlookup_table_size));
2500	amd_iommu_rlookup_table = NULL;
2501
2502	free_pages((unsigned long)amd_iommu_alias_table,
2503		   get_order(alias_table_size));
2504	amd_iommu_alias_table = NULL;
2505
2506	free_pages((unsigned long)amd_iommu_dev_table,
2507		   get_order(dev_table_size));
2508	amd_iommu_dev_table = NULL;
2509
2510	free_iommu_all();
2511}
2512
2513/* SB IOAPIC is always on this device in AMD systems */
2514#define IOAPIC_SB_DEVID		((0x00 << 8) | PCI_DEVFN(0x14, 0))
2515
2516static bool __init check_ioapic_information(void)
2517{
2518	const char *fw_bug = FW_BUG;
2519	bool ret, has_sb_ioapic;
2520	int idx;
2521
2522	has_sb_ioapic = false;
2523	ret           = false;
2524
2525	/*
2526	 * If we have map overrides on the kernel command line the
2527	 * messages in this function might not describe firmware bugs
2528	 * anymore - so be careful
2529	 */
2530	if (cmdline_maps)
2531		fw_bug = "";
2532
2533	for (idx = 0; idx < nr_ioapics; idx++) {
2534		int devid, id = mpc_ioapic_id(idx);
2535
2536		devid = get_ioapic_devid(id);
2537		if (devid < 0) {
2538			pr_err("%s: IOAPIC[%d] not in IVRS table\n",
2539				fw_bug, id);
2540			ret = false;
2541		} else if (devid == IOAPIC_SB_DEVID) {
2542			has_sb_ioapic = true;
2543			ret           = true;
2544		}
2545	}
2546
2547	if (!has_sb_ioapic) {
2548		/*
2549		 * We expect the SB IOAPIC to be listed in the IVRS
2550		 * table. The system timer is connected to the SB IOAPIC
2551		 * and if we don't have it in the list the system will
2552		 * panic at boot time.  This situation usually happens
2553		 * when the BIOS is buggy and provides us the wrong
2554		 * device id for the IOAPIC in the system.
2555		 */
2556		pr_err("%s: No southbridge IOAPIC found\n", fw_bug);
2557	}
2558
2559	if (!ret)
2560		pr_err("Disabling interrupt remapping\n");
2561
2562	return ret;
2563}
2564
2565static void __init free_dma_resources(void)
2566{
2567	free_pages((unsigned long)amd_iommu_pd_alloc_bitmap,
2568		   get_order(MAX_DOMAIN_ID/8));
2569	amd_iommu_pd_alloc_bitmap = NULL;
2570
2571	free_unity_maps();
2572}
2573
2574static void __init ivinfo_init(void *ivrs)
2575{
2576	amd_iommu_ivinfo = *((u32 *)(ivrs + IOMMU_IVINFO_OFFSET));
2577}
2578
2579/*
2580 * This is the hardware init function for AMD IOMMU in the system.
2581 * This function is called either from amd_iommu_init or from the interrupt
2582 * remapping setup code.
2583 *
2584 * This function basically parses the ACPI table for AMD IOMMU (IVRS)
2585 * four times:
2586 *
2587 *	1 pass) Discover the most comprehensive IVHD type to use.
2588 *
2589 *	2 pass) Find the highest PCI device id the driver has to handle.
2590 *		Upon this information the size of the data structures is
2591 *		determined that needs to be allocated.
2592 *
2593 *	3 pass) Initialize the data structures just allocated with the
2594 *		information in the ACPI table about available AMD IOMMUs
2595 *		in the system. It also maps the PCI devices in the
2596 *		system to specific IOMMUs
2597 *
2598 *	4 pass) After the basic data structures are allocated and
2599 *		initialized we update them with information about memory
2600 *		remapping requirements parsed out of the ACPI table in
2601 *		this last pass.
2602 *
2603 * After everything is set up the IOMMUs are enabled and the necessary
2604 * hotplug and suspend notifiers are registered.
2605 */
2606static int __init early_amd_iommu_init(void)
2607{
2608	struct acpi_table_header *ivrs_base;
2609	acpi_status status;
2610	int i, remap_cache_sz, ret = 0;
2611	u32 pci_id;
2612
2613	if (!amd_iommu_detected)
2614		return -ENODEV;
2615
2616	status = acpi_get_table("IVRS", 0, &ivrs_base);
2617	if (status == AE_NOT_FOUND)
2618		return -ENODEV;
2619	else if (ACPI_FAILURE(status)) {
2620		const char *err = acpi_format_exception(status);
2621		pr_err("IVRS table error: %s\n", err);
2622		return -EINVAL;
2623	}
2624
2625	/*
2626	 * Validate checksum here so we don't need to do it when
2627	 * we actually parse the table
2628	 */
2629	ret = check_ivrs_checksum(ivrs_base);
2630	if (ret)
2631		goto out;
2632
2633	ivinfo_init(ivrs_base);
2634
2635	amd_iommu_target_ivhd_type = get_highest_supported_ivhd_type(ivrs_base);
2636	DUMP_printk("Using IVHD type %#x\n", amd_iommu_target_ivhd_type);
2637
2638	/*
2639	 * First parse ACPI tables to find the largest Bus/Dev/Func
2640	 * we need to handle. Upon this information the shared data
2641	 * structures for the IOMMUs in the system will be allocated
2642	 */
2643	ret = find_last_devid_acpi(ivrs_base);
2644	if (ret)
2645		goto out;
2646
2647	dev_table_size     = tbl_size(DEV_TABLE_ENTRY_SIZE);
2648	alias_table_size   = tbl_size(ALIAS_TABLE_ENTRY_SIZE);
2649	rlookup_table_size = tbl_size(RLOOKUP_TABLE_ENTRY_SIZE);
2650
2651	/* Device table - directly used by all IOMMUs */
2652	ret = -ENOMEM;
2653	amd_iommu_dev_table = (void *)__get_free_pages(
2654				      GFP_KERNEL | __GFP_ZERO | GFP_DMA32,
2655				      get_order(dev_table_size));
2656	if (amd_iommu_dev_table == NULL)
2657		goto out;
2658
2659	/*
2660	 * Alias table - map PCI Bus/Dev/Func to Bus/Dev/Func the
2661	 * IOMMU see for that device
2662	 */
2663	amd_iommu_alias_table = (void *)__get_free_pages(GFP_KERNEL,
2664			get_order(alias_table_size));
2665	if (amd_iommu_alias_table == NULL)
2666		goto out;
2667
2668	/* IOMMU rlookup table - find the IOMMU for a specific device */
2669	amd_iommu_rlookup_table = (void *)__get_free_pages(
2670			GFP_KERNEL | __GFP_ZERO,
2671			get_order(rlookup_table_size));
2672	if (amd_iommu_rlookup_table == NULL)
2673		goto out;
2674
2675	amd_iommu_pd_alloc_bitmap = (void *)__get_free_pages(
2676					    GFP_KERNEL | __GFP_ZERO,
2677					    get_order(MAX_DOMAIN_ID/8));
2678	if (amd_iommu_pd_alloc_bitmap == NULL)
2679		goto out;
2680
2681	/*
2682	 * let all alias entries point to itself
2683	 */
2684	for (i = 0; i <= amd_iommu_last_bdf; ++i)
2685		amd_iommu_alias_table[i] = i;
2686
2687	/*
2688	 * never allocate domain 0 because its used as the non-allocated and
2689	 * error value placeholder
2690	 */
2691	__set_bit(0, amd_iommu_pd_alloc_bitmap);
2692
2693	/*
2694	 * now the data structures are allocated and basically initialized
2695	 * start the real acpi table scan
2696	 */
2697	ret = init_iommu_all(ivrs_base);
2698	if (ret)
2699		goto out;
2700
2701	/* Disable IOMMU if there's Stoney Ridge graphics */
2702	for (i = 0; i < 32; i++) {
2703		pci_id = read_pci_config(0, i, 0, 0);
2704		if ((pci_id & 0xffff) == 0x1002 && (pci_id >> 16) == 0x98e4) {
2705			pr_info("Disable IOMMU on Stoney Ridge\n");
2706			amd_iommu_disabled = true;
2707			break;
2708		}
2709	}
2710
2711	/* Disable any previously enabled IOMMUs */
2712	if (!is_kdump_kernel() || amd_iommu_disabled)
2713		disable_iommus();
2714
2715	if (amd_iommu_irq_remap)
2716		amd_iommu_irq_remap = check_ioapic_information();
2717
2718	if (amd_iommu_irq_remap) {
2719		/*
2720		 * Interrupt remapping enabled, create kmem_cache for the
2721		 * remapping tables.
2722		 */
2723		ret = -ENOMEM;
2724		if (!AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir))
2725			remap_cache_sz = MAX_IRQS_PER_TABLE * sizeof(u32);
2726		else
2727			remap_cache_sz = MAX_IRQS_PER_TABLE * (sizeof(u64) * 2);
2728		amd_iommu_irq_cache = kmem_cache_create("irq_remap_cache",
2729							remap_cache_sz,
2730							IRQ_TABLE_ALIGNMENT,
2731							0, NULL);
2732		if (!amd_iommu_irq_cache)
2733			goto out;
2734
2735		irq_lookup_table = (void *)__get_free_pages(
2736				GFP_KERNEL | __GFP_ZERO,
2737				get_order(rlookup_table_size));
2738		kmemleak_alloc(irq_lookup_table, rlookup_table_size,
2739			       1, GFP_KERNEL);
2740		if (!irq_lookup_table)
2741			goto out;
2742	}
2743
2744	ret = init_memory_definitions(ivrs_base);
2745	if (ret)
2746		goto out;
2747
2748	/* init the device table */
2749	init_device_table();
2750
2751out:
2752	/* Don't leak any ACPI memory */
2753	acpi_put_table(ivrs_base);
2754	ivrs_base = NULL;
2755
2756	return ret;
2757}
2758
2759static int amd_iommu_enable_interrupts(void)
2760{
2761	struct amd_iommu *iommu;
2762	int ret = 0;
2763
2764	for_each_iommu(iommu) {
2765		ret = iommu_init_msi(iommu);
2766		if (ret)
2767			goto out;
2768	}
2769
2770out:
2771	return ret;
2772}
2773
2774static bool detect_ivrs(void)
2775{
2776	struct acpi_table_header *ivrs_base;
2777	acpi_status status;
2778
2779	status = acpi_get_table("IVRS", 0, &ivrs_base);
2780	if (status == AE_NOT_FOUND)
2781		return false;
2782	else if (ACPI_FAILURE(status)) {
2783		const char *err = acpi_format_exception(status);
2784		pr_err("IVRS table error: %s\n", err);
2785		return false;
2786	}
2787
2788	acpi_put_table(ivrs_base);
2789
2790	/* Make sure ACS will be enabled during PCI probe */
2791	pci_request_acs();
2792
2793	return true;
2794}
2795
2796/****************************************************************************
2797 *
2798 * AMD IOMMU Initialization State Machine
2799 *
2800 ****************************************************************************/
2801
2802static int __init state_next(void)
2803{
2804	int ret = 0;
2805
2806	switch (init_state) {
2807	case IOMMU_START_STATE:
2808		if (!detect_ivrs()) {
2809			init_state	= IOMMU_NOT_FOUND;
2810			ret		= -ENODEV;
2811		} else {
2812			init_state	= IOMMU_IVRS_DETECTED;
2813		}
2814		break;
2815	case IOMMU_IVRS_DETECTED:
2816		ret = early_amd_iommu_init();
2817		init_state = ret ? IOMMU_INIT_ERROR : IOMMU_ACPI_FINISHED;
2818		if (init_state == IOMMU_ACPI_FINISHED && amd_iommu_disabled) {
2819			pr_info("AMD IOMMU disabled\n");
2820			init_state = IOMMU_CMDLINE_DISABLED;
2821			ret = -EINVAL;
2822		}
2823		break;
2824	case IOMMU_ACPI_FINISHED:
2825		early_enable_iommus();
2826		x86_platform.iommu_shutdown = disable_iommus;
2827		init_state = IOMMU_ENABLED;
2828		break;
2829	case IOMMU_ENABLED:
2830		register_syscore_ops(&amd_iommu_syscore_ops);
2831		ret = amd_iommu_init_pci();
2832		init_state = ret ? IOMMU_INIT_ERROR : IOMMU_PCI_INIT;
2833		enable_iommus_v2();
2834		break;
2835	case IOMMU_PCI_INIT:
2836		ret = amd_iommu_enable_interrupts();
2837		init_state = ret ? IOMMU_INIT_ERROR : IOMMU_INTERRUPTS_EN;
2838		break;
2839	case IOMMU_INTERRUPTS_EN:
2840		ret = amd_iommu_init_dma_ops();
2841		init_state = ret ? IOMMU_INIT_ERROR : IOMMU_DMA_OPS;
2842		break;
2843	case IOMMU_DMA_OPS:
2844		init_state = IOMMU_INITIALIZED;
2845		break;
2846	case IOMMU_INITIALIZED:
2847		/* Nothing to do */
2848		break;
2849	case IOMMU_NOT_FOUND:
2850	case IOMMU_INIT_ERROR:
2851	case IOMMU_CMDLINE_DISABLED:
2852		/* Error states => do nothing */
2853		ret = -EINVAL;
2854		break;
2855	default:
2856		/* Unknown state */
2857		BUG();
2858	}
2859
2860	if (ret) {
2861		free_dma_resources();
2862		if (!irq_remapping_enabled) {
2863			disable_iommus();
2864			free_iommu_resources();
2865		} else {
2866			struct amd_iommu *iommu;
2867
2868			uninit_device_table_dma();
2869			for_each_iommu(iommu)
2870				iommu_flush_all_caches(iommu);
2871		}
2872	}
2873	return ret;
2874}
2875
2876static int __init iommu_go_to_state(enum iommu_init_state state)
2877{
2878	int ret = -EINVAL;
2879
2880	while (init_state != state) {
2881		if (init_state == IOMMU_NOT_FOUND         ||
2882		    init_state == IOMMU_INIT_ERROR        ||
2883		    init_state == IOMMU_CMDLINE_DISABLED)
2884			break;
2885		ret = state_next();
2886	}
2887
2888	return ret;
2889}
2890
2891#ifdef CONFIG_IRQ_REMAP
2892int __init amd_iommu_prepare(void)
2893{
2894	int ret;
2895
2896	amd_iommu_irq_remap = true;
2897
2898	ret = iommu_go_to_state(IOMMU_ACPI_FINISHED);
2899	if (ret)
2900		return ret;
2901	return amd_iommu_irq_remap ? 0 : -ENODEV;
2902}
2903
2904int __init amd_iommu_enable(void)
2905{
2906	int ret;
2907
2908	ret = iommu_go_to_state(IOMMU_ENABLED);
2909	if (ret)
2910		return ret;
2911
2912	irq_remapping_enabled = 1;
2913	return amd_iommu_xt_mode;
2914}
2915
2916void amd_iommu_disable(void)
2917{
2918	amd_iommu_suspend();
2919}
2920
2921int amd_iommu_reenable(int mode)
2922{
2923	amd_iommu_resume();
2924
2925	return 0;
2926}
2927
2928int __init amd_iommu_enable_faulting(void)
2929{
2930	/* We enable MSI later when PCI is initialized */
2931	return 0;
2932}
2933#endif
2934
2935/*
2936 * This is the core init function for AMD IOMMU hardware in the system.
2937 * This function is called from the generic x86 DMA layer initialization
2938 * code.
2939 */
2940static int __init amd_iommu_init(void)
2941{
2942	struct amd_iommu *iommu;
2943	int ret;
2944
2945	ret = iommu_go_to_state(IOMMU_INITIALIZED);
2946#ifdef CONFIG_GART_IOMMU
2947	if (ret && list_empty(&amd_iommu_list)) {
2948		/*
2949		 * We failed to initialize the AMD IOMMU - try fallback
2950		 * to GART if possible.
2951		 */
2952		gart_iommu_init();
2953	}
2954#endif
2955
2956	for_each_iommu(iommu)
2957		amd_iommu_debugfs_setup(iommu);
2958
2959	return ret;
2960}
2961
2962static bool amd_iommu_sme_check(void)
2963{
2964	if (!sme_active() || (boot_cpu_data.x86 != 0x17))
2965		return true;
2966
2967	/* For Fam17h, a specific level of support is required */
2968	if (boot_cpu_data.microcode >= 0x08001205)
2969		return true;
2970
2971	if ((boot_cpu_data.microcode >= 0x08001126) &&
2972	    (boot_cpu_data.microcode <= 0x080011ff))
2973		return true;
2974
2975	pr_notice("IOMMU not currently supported when SME is active\n");
2976
2977	return false;
2978}
2979
2980/****************************************************************************
2981 *
2982 * Early detect code. This code runs at IOMMU detection time in the DMA
2983 * layer. It just looks if there is an IVRS ACPI table to detect AMD
2984 * IOMMUs
2985 *
2986 ****************************************************************************/
2987int __init amd_iommu_detect(void)
2988{
2989	int ret;
2990
2991	if (no_iommu || (iommu_detected && !gart_iommu_aperture))
2992		return -ENODEV;
2993
2994	if (!amd_iommu_sme_check())
2995		return -ENODEV;
2996
2997	ret = iommu_go_to_state(IOMMU_IVRS_DETECTED);
2998	if (ret)
2999		return ret;
3000
3001	amd_iommu_detected = true;
3002	iommu_detected = 1;
3003	x86_init.iommu.iommu_init = amd_iommu_init;
3004
3005	return 1;
3006}
3007
3008/****************************************************************************
3009 *
3010 * Parsing functions for the AMD IOMMU specific kernel command line
3011 * options.
3012 *
3013 ****************************************************************************/
3014
3015static int __init parse_amd_iommu_dump(char *str)
3016{
3017	amd_iommu_dump = true;
3018
3019	return 1;
3020}
3021
3022static int __init parse_amd_iommu_intr(char *str)
3023{
3024	for (; *str; ++str) {
3025		if (strncmp(str, "legacy", 6) == 0) {
3026			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY_GA;
3027			break;
3028		}
3029		if (strncmp(str, "vapic", 5) == 0) {
3030			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_VAPIC;
3031			break;
3032		}
3033	}
3034	return 1;
3035}
3036
3037static int __init parse_amd_iommu_options(char *str)
3038{
3039	for (; *str; ++str) {
3040		if (strncmp(str, "fullflush", 9) == 0)
3041			amd_iommu_unmap_flush = true;
3042		if (strncmp(str, "off", 3) == 0)
3043			amd_iommu_disabled = true;
3044		if (strncmp(str, "force_isolation", 15) == 0)
3045			amd_iommu_force_isolation = true;
3046	}
3047
3048	return 1;
3049}
3050
3051static int __init parse_ivrs_ioapic(char *str)
3052{
3053	u32 seg = 0, bus, dev, fn;
3054	int id, i;
3055	u32 devid;
3056
3057	if (sscanf(str, "=%d@%x:%x.%x", &id, &bus, &dev, &fn) == 4 ||
3058	    sscanf(str, "=%d@%x:%x:%x.%x", &id, &seg, &bus, &dev, &fn) == 5)
3059		goto found;
3060
3061	if (sscanf(str, "[%d]=%x:%x.%x", &id, &bus, &dev, &fn) == 4 ||
3062	    sscanf(str, "[%d]=%x:%x:%x.%x", &id, &seg, &bus, &dev, &fn) == 5) {
3063		pr_warn("ivrs_ioapic%s option format deprecated; use ivrs_ioapic=%d@%04x:%02x:%02x.%d instead\n",
3064			str, id, seg, bus, dev, fn);
3065		goto found;
3066	}
3067
3068	pr_err("Invalid command line: ivrs_ioapic%s\n", str);
3069	return 1;
3070
3071found:
3072	if (early_ioapic_map_size == EARLY_MAP_SIZE) {
3073		pr_err("Early IOAPIC map overflow - ignoring ivrs_ioapic%s\n",
3074			str);
3075		return 1;
3076	}
3077
3078	devid = IVRS_GET_SBDF_ID(seg, bus, dev, fn);
3079
3080	cmdline_maps			= true;
3081	i				= early_ioapic_map_size++;
3082	early_ioapic_map[i].id		= id;
3083	early_ioapic_map[i].devid	= devid;
3084	early_ioapic_map[i].cmd_line	= true;
3085
3086	return 1;
3087}
3088
3089static int __init parse_ivrs_hpet(char *str)
3090{
3091	u32 seg = 0, bus, dev, fn;
3092	int id, i;
3093	u32 devid;
3094
3095	if (sscanf(str, "=%d@%x:%x.%x", &id, &bus, &dev, &fn) == 4 ||
3096	    sscanf(str, "=%d@%x:%x:%x.%x", &id, &seg, &bus, &dev, &fn) == 5)
3097		goto found;
3098
3099	if (sscanf(str, "[%d]=%x:%x.%x", &id, &bus, &dev, &fn) == 4 ||
3100	    sscanf(str, "[%d]=%x:%x:%x.%x", &id, &seg, &bus, &dev, &fn) == 5) {
3101		pr_warn("ivrs_hpet%s option format deprecated; use ivrs_hpet=%d@%04x:%02x:%02x.%d instead\n",
3102			str, id, seg, bus, dev, fn);
3103		goto found;
3104	}
3105
3106	pr_err("Invalid command line: ivrs_hpet%s\n", str);
3107	return 1;
3108
3109found:
3110	if (early_hpet_map_size == EARLY_MAP_SIZE) {
3111		pr_err("Early HPET map overflow - ignoring ivrs_hpet%s\n",
3112			str);
3113		return 1;
3114	}
3115
3116	devid = IVRS_GET_SBDF_ID(seg, bus, dev, fn);
3117
3118	cmdline_maps			= true;
3119	i				= early_hpet_map_size++;
3120	early_hpet_map[i].id		= id;
3121	early_hpet_map[i].devid		= devid;
3122	early_hpet_map[i].cmd_line	= true;
3123
3124	return 1;
3125}
3126
3127#define ACPIID_LEN (ACPIHID_UID_LEN + ACPIHID_HID_LEN)
3128
3129static int __init parse_ivrs_acpihid(char *str)
3130{
3131	u32 seg = 0, bus, dev, fn;
3132	char *hid, *uid, *p, *addr;
3133	char acpiid[ACPIID_LEN] = {0};
3134	int i;
3135
3136	addr = strchr(str, '@');
3137	if (!addr) {
3138		addr = strchr(str, '=');
3139		if (!addr)
3140			goto not_found;
3141
3142		++addr;
3143
3144		if (strlen(addr) > ACPIID_LEN)
3145			goto not_found;
3146
3147		if (sscanf(str, "[%x:%x.%x]=%s", &bus, &dev, &fn, acpiid) == 4 ||
3148		    sscanf(str, "[%x:%x:%x.%x]=%s", &seg, &bus, &dev, &fn, acpiid) == 5) {
3149			pr_warn("ivrs_acpihid%s option format deprecated; use ivrs_acpihid=%s@%04x:%02x:%02x.%d instead\n",
3150				str, acpiid, seg, bus, dev, fn);
3151			goto found;
3152		}
3153		goto not_found;
3154	}
3155
3156	/* We have the '@', make it the terminator to get just the acpiid */
3157	*addr++ = 0;
3158
3159	if (strlen(str) > ACPIID_LEN + 1)
3160		goto not_found;
3161
3162	if (sscanf(str, "=%s", acpiid) != 1)
3163		goto not_found;
3164
3165	if (sscanf(addr, "%x:%x.%x", &bus, &dev, &fn) == 3 ||
3166	    sscanf(addr, "%x:%x:%x.%x", &seg, &bus, &dev, &fn) == 4)
3167		goto found;
3168
3169not_found:
3170	pr_err("Invalid command line: ivrs_acpihid%s\n", str);
3171	return 1;
3172
3173found:
3174	p = acpiid;
3175	hid = strsep(&p, ":");
3176	uid = p;
3177
3178	if (!hid || !(*hid) || !uid) {
3179		pr_err("Invalid command line: hid or uid\n");
3180		return 1;
3181	}
3182
3183	/*
3184	 * Ignore leading zeroes after ':', so e.g., AMDI0095:00
3185	 * will match AMDI0095:0 in the second strcmp in acpi_dev_hid_uid_match
3186	 */
3187	while (*uid == '0' && *(uid + 1))
3188		uid++;
3189
3190	i = early_acpihid_map_size++;
3191	memcpy(early_acpihid_map[i].hid, hid, strlen(hid));
3192	memcpy(early_acpihid_map[i].uid, uid, strlen(uid));
3193	early_acpihid_map[i].devid = IVRS_GET_SBDF_ID(seg, bus, dev, fn);
3194	early_acpihid_map[i].cmd_line	= true;
3195
3196	return 1;
3197}
3198
3199__setup("amd_iommu_dump",	parse_amd_iommu_dump);
3200__setup("amd_iommu=",		parse_amd_iommu_options);
3201__setup("amd_iommu_intr=",	parse_amd_iommu_intr);
3202__setup("ivrs_ioapic",		parse_ivrs_ioapic);
3203__setup("ivrs_hpet",		parse_ivrs_hpet);
3204__setup("ivrs_acpihid",		parse_ivrs_acpihid);
3205
3206IOMMU_INIT_FINISH(amd_iommu_detect,
3207		  gart_iommu_hole_init,
3208		  NULL,
3209		  NULL);
3210
3211bool amd_iommu_v2_supported(void)
3212{
3213	return amd_iommu_v2_present;
3214}
3215EXPORT_SYMBOL(amd_iommu_v2_supported);
3216
3217struct amd_iommu *get_amd_iommu(unsigned int idx)
3218{
3219	unsigned int i = 0;
3220	struct amd_iommu *iommu;
3221
3222	for_each_iommu(iommu)
3223		if (i++ == idx)
3224			return iommu;
3225	return NULL;
3226}
3227EXPORT_SYMBOL(get_amd_iommu);
3228
3229/****************************************************************************
3230 *
3231 * IOMMU EFR Performance Counter support functionality. This code allows
3232 * access to the IOMMU PC functionality.
3233 *
3234 ****************************************************************************/
3235
3236u8 amd_iommu_pc_get_max_banks(unsigned int idx)
3237{
3238	struct amd_iommu *iommu = get_amd_iommu(idx);
3239
3240	if (iommu)
3241		return iommu->max_banks;
3242
3243	return 0;
3244}
3245EXPORT_SYMBOL(amd_iommu_pc_get_max_banks);
3246
3247bool amd_iommu_pc_supported(void)
3248{
3249	return amd_iommu_pc_present;
3250}
3251EXPORT_SYMBOL(amd_iommu_pc_supported);
3252
3253u8 amd_iommu_pc_get_max_counters(unsigned int idx)
3254{
3255	struct amd_iommu *iommu = get_amd_iommu(idx);
3256
3257	if (iommu)
3258		return iommu->max_counters;
3259
3260	return 0;
3261}
3262EXPORT_SYMBOL(amd_iommu_pc_get_max_counters);
3263
3264static int iommu_pc_get_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
3265				u8 fxn, u64 *value, bool is_write)
3266{
3267	u32 offset;
3268	u32 max_offset_lim;
3269
3270	/* Make sure the IOMMU PC resource is available */
3271	if (!amd_iommu_pc_present)
3272		return -ENODEV;
3273
3274	/* Check for valid iommu and pc register indexing */
3275	if (WARN_ON(!iommu || (fxn > 0x28) || (fxn & 7)))
3276		return -ENODEV;
3277
3278	offset = (u32)(((0x40 | bank) << 12) | (cntr << 8) | fxn);
3279
3280	/* Limit the offset to the hw defined mmio region aperture */
3281	max_offset_lim = (u32)(((0x40 | iommu->max_banks) << 12) |
3282				(iommu->max_counters << 8) | 0x28);
3283	if ((offset < MMIO_CNTR_REG_OFFSET) ||
3284	    (offset > max_offset_lim))
3285		return -EINVAL;
3286
3287	if (is_write) {
3288		u64 val = *value & GENMASK_ULL(47, 0);
3289
3290		writel((u32)val, iommu->mmio_base + offset);
3291		writel((val >> 32), iommu->mmio_base + offset + 4);
3292	} else {
3293		*value = readl(iommu->mmio_base + offset + 4);
3294		*value <<= 32;
3295		*value |= readl(iommu->mmio_base + offset);
3296		*value &= GENMASK_ULL(47, 0);
3297	}
3298
3299	return 0;
3300}
3301
3302int amd_iommu_pc_get_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn, u64 *value)
3303{
3304	if (!iommu)
3305		return -EINVAL;
3306
3307	return iommu_pc_get_set_reg(iommu, bank, cntr, fxn, value, false);
3308}
3309EXPORT_SYMBOL(amd_iommu_pc_get_reg);
3310
3311int amd_iommu_pc_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn, u64 *value)
3312{
3313	if (!iommu)
3314		return -EINVAL;
3315
3316	return iommu_pc_get_set_reg(iommu, bank, cntr, fxn, value, true);
3317}
3318EXPORT_SYMBOL(amd_iommu_pc_set_reg);
3319