summaryrefslogtreecommitdiffstats
path: root/drivers/irqchip/irq-gic-v4.c
blob: dba9d67cb9c138856aec6d5b6917408bf7e87355 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
/*
 * Copyright (C) 2016,2017 ARM Limited, All Rights Reserved.
 * Author: Marc Zyngier <marc.zyngier@arm.com>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */

#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/irqdomain.h>
#include <linux/msi.h>
#include <linux/sched.h>

#include <linux/irqchip/arm-gic-v4.h>

/*
 * WARNING: The blurb below assumes that you understand the
 * intricacies of GICv3, GICv4, and how a guest's view of a GICv3 gets
 * translated into GICv4 commands. So it effectively targets at most
 * two individuals. You know who you are.
 *
 * The core GICv4 code is designed to *avoid* exposing too much of the
 * core GIC code (that would in turn leak into the hypervisor code),
 * and instead provide a hypervisor agnostic interface to the HW (of
 * course, the astute reader will quickly realize that hypervisor
 * agnostic actually means KVM-specific - what were you thinking?).
 *
 * In order to achieve a modicum of isolation, we try to hide most of
 * the GICv4 "stuff" behind normal irqchip operations:
 *
 * - Any guest-visible VLPI is backed by a Linux interrupt (and a
 *   physical LPI which gets unmapped when the guest maps the
 *   VLPI). This allows the same DevID/EventID pair to be either
 *   mapped to the LPI (host) or the VLPI (guest). Note that this is
 *   exclusive, and you cannot have both.
 *
 * - Enabling/disabling a VLPI is done by issuing mask/unmask calls.
 *
 * - Guest INT/CLEAR commands are implemented through
 *   irq_set_irqchip_state().
 *
 * - The *bizarre* stuff (mapping/unmapping an interrupt to a VLPI, or
 *   issuing an INV after changing a priority) gets shoved into the
 *   irq_set_vcpu_affinity() method. While this is quite horrible
 *   (let's face it, this is the irqchip version of an ioctl), it
 *   confines the crap to a single location. And map/unmap really is
 *   about setting the affinity of a VLPI to a vcpu, so only INV is
 *   majorly out of place. So there.
 *
 * A number of commands are simply not provided by this interface, as
 * they do not make direct sense. For example, MAPD is purely local to
 * the virtual ITS (because it references a virtual device, and the
 * physical ITS is still very much in charge of the physical
 * device). Same goes for things like MAPC (the physical ITS deals
 * with the actual vPE affinity, and not the braindead concept of
 * collection). SYNC is not provided either, as each and every command
 * is followed by a VSYNC. This could be relaxed in the future, should
 * this be seen as a bottleneck (yes, this means *never*).
 *
 * But handling VLPIs is only one side of the job of the GICv4
 * code. The other (darker) side is to take care of the doorbell
 * interrupts which are delivered when a VLPI targeting a non-running
 * vcpu is being made pending.
 *
 * The choice made here is that each vcpu (VPE in old northern GICv4
 * dialect) gets a single doorbell LPI, no matter how many interrupts
 * are targeting it. This has a nice property, which is that the
 * interrupt becomes a handle for the VPE, and that the hypervisor
 * code can manipulate it through the normal interrupt API:
 *
 * - VMs (or rather the VM abstraction that matters to the GIC)
 *   contain an irq domain where each interrupt maps to a VPE. In
 *   turn, this domain sits on top of the normal LPI allocator, and a
 *   specially crafted irq_chip implementation.
 *
 * - mask/unmask do what is expected on the doorbell interrupt.
 *
 * - irq_set_affinity is used to move a VPE from one redistributor to
 *   another.
 *
 * - irq_set_vcpu_affinity once again gets hijacked for the purpose of
 *   creating a new sub-API, namely scheduling/descheduling a VPE
 *   (which involves programming GICR_V{PROP,PEND}BASER) and
 *   performing INVALL operations.
 */

static struct irq_domain *gic_domain;
static const struct irq_domain_ops *vpe_domain_ops;

int its_alloc_vcpu_irqs(struct its_vm *vm)
{
	int vpe_base_irq, i;

	vm->fwnode = irq_domain_alloc_named_id_fwnode("GICv4-vpe",
						      task_pid_nr(current));
	if (!vm->fwnode)
		goto err;

	vm->domain = irq_domain_create_hierarchy(gic_domain, 0, vm->nr_vpes,
						 vm->fwnode, vpe_domain_ops,
						 vm);
	if (!vm->domain)
		goto err;

	for (i = 0; i < vm->nr_vpes; i++) {
		vm->vpes[i]->its_vm = vm;
		vm->vpes[i]->idai = true;
	}

	vpe_base_irq = __irq_domain_alloc_irqs(vm->domain, -1, vm->nr_vpes,
					       NUMA_NO_NODE, vm,
					       false, NULL);
	if (vpe_base_irq <= 0)
		goto err;

	for (i = 0; i < vm->nr_vpes; i++)
		vm->vpes[i]->irq = vpe_base_irq + i;

	return 0;

err:
	if (vm->domain)
		irq_domain_remove(vm->domain);
	if (vm->fwnode)
		irq_domain_free_fwnode(vm->fwnode);

	return -ENOMEM;
}

void its_free_vcpu_irqs(struct its_vm *vm)
{
	irq_domain_free_irqs(vm->vpes[0]->irq, vm->nr_vpes);
	irq_domain_remove(vm->domain);
	irq_domain_free_fwnode(vm->fwnode);
}

static int its_send_vpe_cmd(struct its_vpe *vpe, struct its_cmd_info *info)
{
	return irq_set_vcpu_affinity(vpe->irq, info);
}

int its_schedule_vpe(struct its_vpe *vpe, bool on)
{
	struct its_cmd_info info;

	WARN_ON(preemptible());

	info.cmd_type = on ? SCHEDULE_VPE : DESCHEDULE_VPE;

	return its_send_vpe_cmd(vpe, &info);
}

int its_invall_vpe(struct its_vpe *vpe)
{
	struct its_cmd_info info = {
		.cmd_type = INVALL_VPE,
	};

	return its_send_vpe_cmd(vpe, &info);
}

int its_map_vlpi(int irq, struct its_vlpi_map *map)
{
	struct its_cmd_info info = {
		.cmd_type = MAP_VLPI,
		{
			.map      = map,
		},
	};
	int ret;

	/*
	 * The host will never see that interrupt firing again, so it
	 * is vital that we don't do any lazy masking.
	 */
	irq_set_status_flags(irq, IRQ_DISABLE_UNLAZY);

	ret = irq_set_vcpu_affinity(irq, &info);
	if (ret)
		irq_clear_status_flags(irq, IRQ_DISABLE_UNLAZY);

	return ret;
}

int its_get_vlpi(int irq, struct its_vlpi_map *map)
{
	struct its_cmd_info info = {
		.cmd_type = GET_VLPI,
		{
			.map      = map,
		},
	};

	return irq_set_vcpu_affinity(irq, &info);
}

int its_unmap_vlpi(int irq)
{
	irq_clear_status_flags(irq, IRQ_DISABLE_UNLAZY);
	return irq_set_vcpu_affinity(irq, NULL);
}

int its_prop_update_vlpi(int irq, u8 config, bool inv)
{
	struct its_cmd_info info = {
		.cmd_type = inv ? PROP_UPDATE_AND_INV_VLPI : PROP_UPDATE_VLPI,
		{
			.config   = config,
		},
	};

	return irq_set_vcpu_affinity(irq, &info);
}

int its_init_v4(struct irq_domain *domain, const struct irq_domain_ops *ops)
{
	if (domain) {
		pr_info("ITS: Enabling GICv4 support\n");
		gic_domain = domain;
		vpe_domain_ops = ops;
		return 0;
	}

	pr_err("ITS: No GICv4 VPE domain allocated\n");
	return -ENODEV;
}