summaryrefslogtreecommitdiff
path: root/arch/powerpc/kvm/book3s_xive.h
blob: afe9eeac6d56e3ba622362ed8bd8ab362a610add (plain)
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
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
/* SPDX-License-Identifier: GPL-2.0-only */
/*
 * Copyright 2017 Benjamin Herrenschmidt, IBM Corporation
 */

#ifndef _KVM_PPC_BOOK3S_XIVE_H
#define _KVM_PPC_BOOK3S_XIVE_H

#ifdef CONFIG_KVM_XICS
#include "book3s_xics.h"

/*
 * The XIVE Interrupt source numbers are within the range 0 to
 * KVMPPC_XICS_NR_IRQS.
 */
#define KVMPPC_XIVE_FIRST_IRQ	0
#define KVMPPC_XIVE_NR_IRQS	KVMPPC_XICS_NR_IRQS

/*
 * State for one guest irq source.
 *
 * For each guest source we allocate a HW interrupt in the XIVE
 * which we use for all SW triggers. It will be unused for
 * pass-through but it's easier to keep around as the same
 * guest interrupt can alternatively be emulated or pass-through
 * if a physical device is hot unplugged and replaced with an
 * emulated one.
 *
 * This state structure is very similar to the XICS one with
 * additional XIVE specific tracking.
 */
struct kvmppc_xive_irq_state {
	bool valid;			/* Interrupt entry is valid */

	u32 number;			/* Guest IRQ number */
	u32 ipi_number;			/* XIVE IPI HW number */
	struct xive_irq_data ipi_data;	/* XIVE IPI associated data */
	u32 pt_number;			/* XIVE Pass-through number if any */
	struct xive_irq_data *pt_data;	/* XIVE Pass-through associated data */

	/* Targetting as set by guest */
	u8 guest_priority;		/* Guest set priority */
	u8 saved_priority;		/* Saved priority when masking */

	/* Actual targetting */
	u32 act_server;			/* Actual server */
	u8 act_priority;		/* Actual priority */

	/* Various state bits */
	bool in_eoi;			/* Synchronize with H_EOI */
	bool old_p;			/* P bit state when masking */
	bool old_q;			/* Q bit state when masking */
	bool lsi;			/* level-sensitive interrupt */
	bool asserted;			/* Only for emulated LSI: current state */

	/* Saved for migration state */
	bool in_queue;
	bool saved_p;
	bool saved_q;
	u8 saved_scan_prio;

	/* Xive native */
	u32 eisn;			/* Guest Effective IRQ number */
};

/* Select the "right" interrupt (IPI vs. passthrough) */
static inline void kvmppc_xive_select_irq(struct kvmppc_xive_irq_state *state,
					  u32 *out_hw_irq,
					  struct xive_irq_data **out_xd)
{
	if (state->pt_number) {
		if (out_hw_irq)
			*out_hw_irq = state->pt_number;
		if (out_xd)
			*out_xd = state->pt_data;
	} else {
		if (out_hw_irq)
			*out_hw_irq = state->ipi_number;
		if (out_xd)
			*out_xd = &state->ipi_data;
	}
}

/*
 * This corresponds to an "ICS" in XICS terminology, we use it
 * as a mean to break up source information into multiple structures.
 */
struct kvmppc_xive_src_block {
	arch_spinlock_t lock;
	u16 id;
	struct kvmppc_xive_irq_state irq_state[KVMPPC_XICS_IRQ_PER_ICS];
};

struct kvmppc_xive;

struct kvmppc_xive_ops {
	int (*reset_mapped)(struct kvm *kvm, unsigned long guest_irq);
};

struct kvmppc_xive {
	struct kvm *kvm;
	struct kvm_device *dev;
	struct dentry *dentry;

	/* VP block associated with the VM */
	u32	vp_base;

	/* Blocks of sources */
	struct kvmppc_xive_src_block *src_blocks[KVMPPC_XICS_MAX_ICS_ID + 1];
	u32	max_sbid;

	/*
	 * For state save, we lazily scan the queues on the first interrupt
	 * being migrated. We don't have a clean way to reset that flags
	 * so we keep track of the number of valid sources and how many of
	 * them were migrated so we can reset when all of them have been
	 * processed.
	 */
	u32	src_count;
	u32	saved_src_count;

	/*
	 * Some irqs are delayed on restore until the source is created,
	 * keep track here of how many of them
	 */
	u32	delayed_irqs;

	/* Which queues (priorities) are in use by the guest */
	u8	qmap;

	/* Queue orders */
	u32	q_order;
	u32	q_page_order;

	/* Flags */
	u8	single_escalation;

	/* Number of entries in the VP block */
	u32	nr_servers;

	struct kvmppc_xive_ops *ops;
	struct address_space   *mapping;
	struct mutex mapping_lock;
	struct mutex lock;
};

#define KVMPPC_XIVE_Q_COUNT	8

struct kvmppc_xive_vcpu {
	struct kvmppc_xive	*xive;
	struct kvm_vcpu		*vcpu;
	bool			valid;

	/* Server number. This is the HW CPU ID from a guest perspective */
	u32			server_num;

	/*
	 * HW VP corresponding to this VCPU. This is the base of the VP
	 * block plus the server number.
	 */
	u32			vp_id;
	u32			vp_chip_id;
	u32			vp_cam;

	/* IPI used for sending ... IPIs */
	u32			vp_ipi;
	struct xive_irq_data	vp_ipi_data;

	/* Local emulation state */
	uint8_t			cppr;	/* guest CPPR */
	uint8_t			hw_cppr;/* Hardware CPPR */
	uint8_t			mfrr;
	uint8_t			pending;

	/* Each VP has 8 queues though we only provision some */
	struct xive_q		queues[KVMPPC_XIVE_Q_COUNT];
	u32			esc_virq[KVMPPC_XIVE_Q_COUNT];
	char			*esc_virq_names[KVMPPC_XIVE_Q_COUNT];

	/* Stash a delayed irq on restore from migration (see set_icp) */
	u32			delayed_irq;

	/* Stats */
	u64			stat_rm_h_xirr;
	u64			stat_rm_h_ipoll;
	u64			stat_rm_h_cppr;
	u64			stat_rm_h_eoi;
	u64			stat_rm_h_ipi;
	u64			stat_vm_h_xirr;
	u64			stat_vm_h_ipoll;
	u64			stat_vm_h_cppr;
	u64			stat_vm_h_eoi;
	u64			stat_vm_h_ipi;
};

static inline struct kvm_vcpu *kvmppc_xive_find_server(struct kvm *kvm, u32 nr)
{
	struct kvm_vcpu *vcpu = NULL;
	int i;

	kvm_for_each_vcpu(i, vcpu, kvm) {
		if (vcpu->arch.xive_vcpu && nr == vcpu->arch.xive_vcpu->server_num)
			return vcpu;
	}
	return NULL;
}

static inline struct kvmppc_xive_src_block *kvmppc_xive_find_source(struct kvmppc_xive *xive,
		u32 irq, u16 *source)
{
	u32 bid = irq >> KVMPPC_XICS_ICS_SHIFT;
	u16 src = irq & KVMPPC_XICS_SRC_MASK;

	if (source)
		*source = src;
	if (bid > KVMPPC_XICS_MAX_ICS_ID)
		return NULL;
	return xive->src_blocks[bid];
}

/*
 * When the XIVE resources are allocated at the HW level, the VP
 * structures describing the vCPUs of a guest are distributed among
 * the chips to optimize the PowerBUS usage. For best performance, the
 * guest vCPUs can be pinned to match the VP structure distribution.
 *
 * Currently, the VP identifiers are deduced from the vCPU id using
 * the kvmppc_pack_vcpu_id() routine which is not incorrect but not
 * optimal either. It VSMT is used, the result is not continuous and
 * the constraints on HW resources described above can not be met.
 */
static inline u32 kvmppc_xive_vp(struct kvmppc_xive *xive, u32 server)
{
	return xive->vp_base + kvmppc_pack_vcpu_id(xive->kvm, server);
}

static inline bool kvmppc_xive_vp_in_use(struct kvm *kvm, u32 vp_id)
{
	struct kvm_vcpu *vcpu = NULL;
	int i;

	kvm_for_each_vcpu(i, vcpu, kvm) {
		if (vcpu->arch.xive_vcpu && vp_id == vcpu->arch.xive_vcpu->vp_id)
			return true;
	}
	return false;
}

/*
 * Mapping between guest priorities and host priorities
 * is as follow.
 *
 * Guest request for 0...6 are honored. Guest request for anything
 * higher results in a priority of 6 being applied.
 *
 * Similar mapping is done for CPPR values
 */
static inline u8 xive_prio_from_guest(u8 prio)
{
	if (prio == 0xff || prio < 6)
		return prio;
	return 6;
}

static inline u8 xive_prio_to_guest(u8 prio)
{
	return prio;
}

static inline u32 __xive_read_eq(__be32 *qpage, u32 msk, u32 *idx, u32 *toggle)
{
	u32 cur;

	if (!qpage)
		return 0;
	cur = be32_to_cpup(qpage + *idx);
	if ((cur >> 31) == *toggle)
		return 0;
	*idx = (*idx + 1) & msk;
	if (*idx == 0)
		(*toggle) ^= 1;
	return cur & 0x7fffffff;
}

extern unsigned long xive_rm_h_xirr(struct kvm_vcpu *vcpu);
extern unsigned long xive_rm_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server);
extern int xive_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
			 unsigned long mfrr);
extern int xive_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr);
extern int xive_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr);

/*
 * Common Xive routines for XICS-over-XIVE and XIVE native
 */
void kvmppc_xive_disable_vcpu_interrupts(struct kvm_vcpu *vcpu);
int kvmppc_xive_debug_show_queues(struct seq_file *m, struct kvm_vcpu *vcpu);
void kvmppc_xive_debug_show_sources(struct seq_file *m,
				    struct kvmppc_xive_src_block *sb);
struct kvmppc_xive_src_block *kvmppc_xive_create_src_block(
	struct kvmppc_xive *xive, int irq);
void kvmppc_xive_free_sources(struct kvmppc_xive_src_block *sb);
int kvmppc_xive_select_target(struct kvm *kvm, u32 *server, u8 prio);
int kvmppc_xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio,
				  bool single_escalation);
struct kvmppc_xive *kvmppc_xive_get_device(struct kvm *kvm, u32 type);
void xive_cleanup_single_escalation(struct kvm_vcpu *vcpu,
				    struct kvmppc_xive_vcpu *xc, int irq);
int kvmppc_xive_compute_vp_id(struct kvmppc_xive *xive, u32 cpu, u32 *vp);
int kvmppc_xive_set_nr_servers(struct kvmppc_xive *xive, u64 addr);

#endif /* CONFIG_KVM_XICS */
#endif /* _KVM_PPC_BOOK3S_XICS_H */