summaryrefslogtreecommitdiffstats
path: root/arch/arm64/kvm/hyp/nvhe/switch.c
blob: 341be2f2f31261c36563b67d818d7f52b0c2ec05 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2015 - ARM Ltd
 * Author: Marc Zyngier <marc.zyngier@arm.com>
 */

#include <hyp/switch.h>
#include <hyp/sysreg-sr.h>

#include <linux/arm-smccc.h>
#include <linux/kvm_host.h>
#include <linux/types.h>
#include <linux/jump_label.h>
#include <uapi/linux/psci.h>

#include <kvm/arm_psci.h>

#include <asm/barrier.h>
#include <asm/cpufeature.h>
#include <asm/kprobes.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_hyp.h>
#include <asm/kvm_mmu.h>
#include <asm/fpsimd.h>
#include <asm/debug-monitors.h>
#include <asm/processor.h>
#include <asm/thread_info.h>

static void __activate_traps(struct kvm_vcpu *vcpu)
{
	u64 val;

	___activate_traps(vcpu);
	__activate_traps_common(vcpu);

	val = CPTR_EL2_DEFAULT;
	val |= CPTR_EL2_TTA | CPTR_EL2_TZ | CPTR_EL2_TAM;
	if (!update_fp_enabled(vcpu)) {
		val |= CPTR_EL2_TFP;
		__activate_traps_fpsimd32(vcpu);
	}

	write_sysreg(val, cptr_el2);

	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
		struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;

		isb();
		/*
		 * At this stage, and thanks to the above isb(), S2 is
		 * configured and enabled. We can now restore the guest's S1
		 * configuration: SCTLR, and only then TCR.
		 */
		write_sysreg_el1(ctxt_sys_reg(ctxt, SCTLR_EL1),	SYS_SCTLR);
		isb();
		write_sysreg_el1(ctxt_sys_reg(ctxt, TCR_EL1),	SYS_TCR);
	}
}

static void __deactivate_traps(struct kvm_vcpu *vcpu)
{
	u64 mdcr_el2;

	___deactivate_traps(vcpu);

	mdcr_el2 = read_sysreg(mdcr_el2);

	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
		u64 val;

		/*
		 * Set the TCR and SCTLR registers in the exact opposite
		 * sequence as __activate_traps (first prevent walks,
		 * then force the MMU on). A generous sprinkling of isb()
		 * ensure that things happen in this exact order.
		 */
		val = read_sysreg_el1(SYS_TCR);
		write_sysreg_el1(val | TCR_EPD1_MASK | TCR_EPD0_MASK, SYS_TCR);
		isb();
		val = read_sysreg_el1(SYS_SCTLR);
		write_sysreg_el1(val | SCTLR_ELx_M, SYS_SCTLR);
		isb();
	}

	__deactivate_traps_common();

	mdcr_el2 &= MDCR_EL2_HPMN_MASK;
	mdcr_el2 |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT;

	write_sysreg(mdcr_el2, mdcr_el2);
	write_sysreg(HCR_HOST_NVHE_FLAGS, hcr_el2);
	write_sysreg(CPTR_EL2_DEFAULT, cptr_el2);
}

static void __deactivate_vm(struct kvm_vcpu *vcpu)
{
	write_sysreg(0, vttbr_el2);
}

/* Save VGICv3 state on non-VHE systems */
static void __hyp_vgic_save_state(struct kvm_vcpu *vcpu)
{
	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
		__vgic_v3_save_state(&vcpu->arch.vgic_cpu.vgic_v3);
		__vgic_v3_deactivate_traps(&vcpu->arch.vgic_cpu.vgic_v3);
	}
}

/* Restore VGICv3 state on non_VEH systems */
static void __hyp_vgic_restore_state(struct kvm_vcpu *vcpu)
{
	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
		__vgic_v3_activate_traps(&vcpu->arch.vgic_cpu.vgic_v3);
		__vgic_v3_restore_state(&vcpu->arch.vgic_cpu.vgic_v3);
	}
}

/**
 * Disable host events, enable guest events
 */
static bool __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt)
{
	struct kvm_host_data *host;
	struct kvm_pmu_events *pmu;

	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
	pmu = &host->pmu_events;

	if (pmu->events_host)
		write_sysreg(pmu->events_host, pmcntenclr_el0);

	if (pmu->events_guest)
		write_sysreg(pmu->events_guest, pmcntenset_el0);

	return (pmu->events_host || pmu->events_guest);
}

/**
 * Disable guest events, enable host events
 */
static void __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt)
{
	struct kvm_host_data *host;
	struct kvm_pmu_events *pmu;

	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
	pmu = &host->pmu_events;

	if (pmu->events_guest)
		write_sysreg(pmu->events_guest, pmcntenclr_el0);

	if (pmu->events_host)
		write_sysreg(pmu->events_host, pmcntenset_el0);
}

/* Switch to the guest for legacy non-VHE systems */
int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
{
	struct kvm_cpu_context *host_ctxt;
	struct kvm_cpu_context *guest_ctxt;
	bool pmu_switch_needed;
	u64 exit_code;

	/*
	 * Having IRQs masked via PMR when entering the guest means the GIC
	 * will not signal the CPU of interrupts of lower priority, and the
	 * only way to get out will be via guest exceptions.
	 * Naturally, we want to avoid this.
	 */
	if (system_uses_irq_prio_masking()) {
		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
		pmr_sync();
	}

	vcpu = kern_hyp_va(vcpu);

	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
	host_ctxt->__hyp_running_vcpu = vcpu;
	guest_ctxt = &vcpu->arch.ctxt;

	pmu_switch_needed = __pmu_switch_to_guest(host_ctxt);

	__sysreg_save_state_nvhe(host_ctxt);

	/*
	 * We must restore the 32-bit state before the sysregs, thanks
	 * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
	 *
	 * Also, and in order to be able to deal with erratum #1319537 (A57)
	 * and #1319367 (A72), we must ensure that all VM-related sysreg are
	 * restored before we enable S2 translation.
	 */
	__sysreg32_restore_state(vcpu);
	__sysreg_restore_state_nvhe(guest_ctxt);

	__activate_vm(kern_hyp_va(vcpu->arch.hw_mmu));
	__activate_traps(vcpu);

	__hyp_vgic_restore_state(vcpu);
	__timer_enable_traps(vcpu);

	__debug_switch_to_guest(vcpu);

	__set_guest_arch_workaround_state(vcpu);

	do {
		/* Jump in the fire! */
		exit_code = __guest_enter(vcpu, host_ctxt);

		/* And we're baaack! */
	} while (fixup_guest_exit(vcpu, &exit_code));

	__set_host_arch_workaround_state(vcpu);

	__sysreg_save_state_nvhe(guest_ctxt);
	__sysreg32_save_state(vcpu);
	__timer_disable_traps(vcpu);
	__hyp_vgic_save_state(vcpu);

	__deactivate_traps(vcpu);
	__deactivate_vm(vcpu);

	__sysreg_restore_state_nvhe(host_ctxt);

	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)
		__fpsimd_save_fpexc32(vcpu);

	/*
	 * This must come after restoring the host sysregs, since a non-VHE
	 * system may enable SPE here and make use of the TTBRs.
	 */
	__debug_switch_to_host(vcpu);

	if (pmu_switch_needed)
		__pmu_switch_to_host(host_ctxt);

	/* Returning to host will clear PSR.I, remask PMR if needed */
	if (system_uses_irq_prio_masking())
		gic_write_pmr(GIC_PRIO_IRQOFF);

	return exit_code;
}

void __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt)
{
	u64 spsr = read_sysreg_el2(SYS_SPSR);
	u64 elr = read_sysreg_el2(SYS_ELR);
	u64 par = read_sysreg(par_el1);
	struct kvm_vcpu *vcpu = host_ctxt->__hyp_running_vcpu;
	unsigned long str_va;

	if (read_sysreg(vttbr_el2)) {
		__timer_disable_traps(vcpu);
		__deactivate_traps(vcpu);
		__deactivate_vm(vcpu);
		__sysreg_restore_state_nvhe(host_ctxt);
	}

	/*
	 * Force the panic string to be loaded from the literal pool,
	 * making sure it is a kernel address and not a PC-relative
	 * reference.
	 */
	asm volatile("ldr %0, =%1" : "=r" (str_va) : "S" (__hyp_panic_string));

	__hyp_do_panic(str_va,
		       spsr, elr,
		       read_sysreg(esr_el2), read_sysreg_el2(SYS_FAR),
		       read_sysreg(hpfar_el2), par, vcpu);
	unreachable();
}