Merge branch kvm-arm64/stage2-vhe-load into kvmarm/next

* kvm-arm64/stage2-vhe-load:
  : Setup stage-2 MMU from vcpu_load() for VHE
  :
  : Unlike nVHE, there is no need to switch the stage-2 MMU around on guest
  : entry/exit in VHE mode as the host is running at EL2. Despite this KVM
  : reloads the stage-2 on every guest entry, which is needless.
  :
  : This series moves the setup of the stage-2 MMU context to vcpu_load()
  : when running in VHE mode. This is likely to be a win across the board,
  : but also allows us to remove an ISB on the guest entry path for systems
  : with one of the speculative AT errata.
  KVM: arm64: Move VTCR_EL2 into struct s2_mmu
  KVM: arm64: Load the stage-2 MMU context in kvm_vcpu_load_vhe()
  KVM: arm64: Rename helpers for VHE vCPU load/put
  KVM: arm64: Reload stage-2 for VMID change on VHE
  KVM: arm64: Restore the stage-2 context in VHE's __tlb_switch_to_host()
  KVM: arm64: Don't zero VTTBR in __tlb_switch_to_host()

Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
This commit is contained in:
Oliver Upton 2023-10-30 20:18:56 +00:00
commit df26b77915
15 changed files with 90 additions and 62 deletions

View file

@ -158,6 +158,16 @@ struct kvm_s2_mmu {
phys_addr_t pgd_phys;
struct kvm_pgtable *pgt;
/*
* VTCR value used on the host. For a non-NV guest (or a NV
* guest that runs in a context where its own S2 doesn't
* apply), its T0SZ value reflects that of the IPA size.
*
* For a shadow S2 MMU, T0SZ reflects the PARange exposed to
* the guest.
*/
u64 vtcr;
/* The last vcpu id that ran on each physical CPU */
int __percpu *last_vcpu_ran;
@ -205,9 +215,6 @@ struct kvm_protected_vm {
struct kvm_arch {
struct kvm_s2_mmu mmu;
/* VTCR_EL2 value for this VM */
u64 vtcr;
/* Interrupt controller */
struct vgic_dist vgic;
@ -1020,7 +1027,7 @@ int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu,
extern unsigned int __ro_after_init kvm_arm_vmid_bits;
int __init kvm_arm_vmid_alloc_init(void);
void __init kvm_arm_vmid_alloc_free(void);
void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid);
bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid);
void kvm_arm_vmid_clear_active(void);
static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch)
@ -1104,8 +1111,8 @@ static inline bool kvm_set_pmuserenr(u64 val)
}
#endif
void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu);
void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu);
void kvm_vcpu_load_vhe(struct kvm_vcpu *vcpu);
void kvm_vcpu_put_vhe(struct kvm_vcpu *vcpu);
int __init kvm_set_ipa_limit(void);

View file

@ -93,6 +93,8 @@ void __timer_disable_traps(struct kvm_vcpu *vcpu);
void __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt);
void __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt);
#else
void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu);
void __vcpu_put_switch_sysregs(struct kvm_vcpu *vcpu);
void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt);
void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt);
void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt);
@ -111,11 +113,6 @@ void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
void __sve_restore_state(void *sve_pffr, u32 *fpsr);
#ifndef __KVM_NVHE_HYPERVISOR__
void activate_traps_vhe_load(struct kvm_vcpu *vcpu);
void deactivate_traps_vhe_put(struct kvm_vcpu *vcpu);
#endif
u64 __guest_enter(struct kvm_vcpu *vcpu);
bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt, u32 func_id);

View file

@ -150,9 +150,9 @@ static __always_inline unsigned long __kern_hyp_va(unsigned long v)
*/
#define KVM_PHYS_SHIFT (40)
#define kvm_phys_shift(kvm) VTCR_EL2_IPA(kvm->arch.vtcr)
#define kvm_phys_size(kvm) (_AC(1, ULL) << kvm_phys_shift(kvm))
#define kvm_phys_mask(kvm) (kvm_phys_size(kvm) - _AC(1, ULL))
#define kvm_phys_shift(mmu) VTCR_EL2_IPA((mmu)->vtcr)
#define kvm_phys_size(mmu) (_AC(1, ULL) << kvm_phys_shift(mmu))
#define kvm_phys_mask(mmu) (kvm_phys_size(mmu) - _AC(1, ULL))
#include <asm/kvm_pgtable.h>
#include <asm/stage2_pgtable.h>
@ -324,7 +324,7 @@ static __always_inline u64 kvm_get_vttbr(struct kvm_s2_mmu *mmu)
static __always_inline void __load_stage2(struct kvm_s2_mmu *mmu,
struct kvm_arch *arch)
{
write_sysreg(arch->vtcr, vtcr_el2);
write_sysreg(mmu->vtcr, vtcr_el2);
write_sysreg(kvm_get_vttbr(mmu), vttbr_el2);
/*

View file

@ -21,13 +21,13 @@
* (IPA_SHIFT - 4).
*/
#define stage2_pgtable_levels(ipa) ARM64_HW_PGTABLE_LEVELS((ipa) - 4)
#define kvm_stage2_levels(kvm) VTCR_EL2_LVLS(kvm->arch.vtcr)
#define kvm_stage2_levels(mmu) VTCR_EL2_LVLS((mmu)->vtcr)
/*
* kvm_mmmu_cache_min_pages() is the number of pages required to install
* a stage-2 translation. We pre-allocate the entry level page table at
* the VM creation.
*/
#define kvm_mmu_cache_min_pages(kvm) (kvm_stage2_levels(kvm) - 1)
#define kvm_mmu_cache_min_pages(mmu) (kvm_stage2_levels(mmu) - 1)
#endif /* __ARM64_S2_PGTABLE_H_ */

View file

@ -447,7 +447,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
kvm_vgic_load(vcpu);
kvm_timer_vcpu_load(vcpu);
if (has_vhe())
kvm_vcpu_load_sysregs_vhe(vcpu);
kvm_vcpu_load_vhe(vcpu);
kvm_arch_vcpu_load_fp(vcpu);
kvm_vcpu_pmu_restore_guest(vcpu);
if (kvm_arm_is_pvtime_enabled(&vcpu->arch))
@ -471,7 +471,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
kvm_arch_vcpu_put_debug_state_flags(vcpu);
kvm_arch_vcpu_put_fp(vcpu);
if (has_vhe())
kvm_vcpu_put_sysregs_vhe(vcpu);
kvm_vcpu_put_vhe(vcpu);
kvm_timer_vcpu_put(vcpu);
kvm_vgic_put(vcpu);
kvm_vcpu_pmu_restore_host(vcpu);
@ -949,7 +949,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
* making a thread's VMID inactive. So we need to call
* kvm_arm_vmid_update() in non-premptible context.
*/
kvm_arm_vmid_update(&vcpu->arch.hw_mmu->vmid);
if (kvm_arm_vmid_update(&vcpu->arch.hw_mmu->vmid) &&
has_vhe())
__load_stage2(vcpu->arch.hw_mmu,
vcpu->arch.hw_mmu->arch);
kvm_pmu_flush_hwstate(vcpu);

View file

@ -129,8 +129,8 @@ static void prepare_host_vtcr(void)
parange = kvm_get_parange(id_aa64mmfr0_el1_sys_val);
phys_shift = id_aa64mmfr0_parange_to_phys_shift(parange);
host_mmu.arch.vtcr = kvm_get_vtcr(id_aa64mmfr0_el1_sys_val,
id_aa64mmfr1_el1_sys_val, phys_shift);
host_mmu.arch.mmu.vtcr = kvm_get_vtcr(id_aa64mmfr0_el1_sys_val,
id_aa64mmfr1_el1_sys_val, phys_shift);
}
static bool host_stage2_force_pte_cb(u64 addr, u64 end, enum kvm_pgtable_prot prot);
@ -235,7 +235,7 @@ int kvm_guest_prepare_stage2(struct pkvm_hyp_vm *vm, void *pgd)
unsigned long nr_pages;
int ret;
nr_pages = kvm_pgtable_stage2_pgd_size(vm->kvm.arch.vtcr) >> PAGE_SHIFT;
nr_pages = kvm_pgtable_stage2_pgd_size(mmu->vtcr) >> PAGE_SHIFT;
ret = hyp_pool_init(&vm->pool, hyp_virt_to_pfn(pgd), nr_pages, 0);
if (ret)
return ret;
@ -295,7 +295,7 @@ int __pkvm_prot_finalize(void)
return -EPERM;
params->vttbr = kvm_get_vttbr(mmu);
params->vtcr = host_mmu.arch.vtcr;
params->vtcr = mmu->vtcr;
params->hcr_el2 |= HCR_VM;
/*

View file

@ -303,7 +303,7 @@ static void init_pkvm_hyp_vm(struct kvm *host_kvm, struct pkvm_hyp_vm *hyp_vm,
{
hyp_vm->host_kvm = host_kvm;
hyp_vm->kvm.created_vcpus = nr_vcpus;
hyp_vm->kvm.arch.vtcr = host_mmu.arch.vtcr;
hyp_vm->kvm.arch.mmu.vtcr = host_mmu.arch.mmu.vtcr;
}
static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu,
@ -483,7 +483,7 @@ int __pkvm_init_vm(struct kvm *host_kvm, unsigned long vm_hva,
}
vm_size = pkvm_get_hyp_vm_size(nr_vcpus);
pgd_size = kvm_pgtable_stage2_pgd_size(host_mmu.arch.vtcr);
pgd_size = kvm_pgtable_stage2_pgd_size(host_mmu.arch.mmu.vtcr);
ret = -ENOMEM;

View file

@ -1511,7 +1511,7 @@ int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
kvm_pgtable_force_pte_cb_t force_pte_cb)
{
size_t pgd_sz;
u64 vtcr = mmu->arch->vtcr;
u64 vtcr = mmu->vtcr;
u32 ia_bits = VTCR_EL2_IPA(vtcr);
u32 sl0 = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr);
u32 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0;

View file

@ -93,12 +93,12 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
NOKPROBE_SYMBOL(__deactivate_traps);
/*
* Disable IRQs in {activate,deactivate}_traps_vhe_{load,put}() to
* Disable IRQs in __vcpu_{load,put}_{activate,deactivate}_traps() to
* prevent a race condition between context switching of PMUSERENR_EL0
* in __{activate,deactivate}_traps_common() and IPIs that attempts to
* update PMUSERENR_EL0. See also kvm_set_pmuserenr().
*/
void activate_traps_vhe_load(struct kvm_vcpu *vcpu)
static void __vcpu_load_activate_traps(struct kvm_vcpu *vcpu)
{
unsigned long flags;
@ -107,7 +107,7 @@ void activate_traps_vhe_load(struct kvm_vcpu *vcpu)
local_irq_restore(flags);
}
void deactivate_traps_vhe_put(struct kvm_vcpu *vcpu)
static void __vcpu_put_deactivate_traps(struct kvm_vcpu *vcpu)
{
unsigned long flags;
@ -116,6 +116,19 @@ void deactivate_traps_vhe_put(struct kvm_vcpu *vcpu)
local_irq_restore(flags);
}
void kvm_vcpu_load_vhe(struct kvm_vcpu *vcpu)
{
__vcpu_load_switch_sysregs(vcpu);
__vcpu_load_activate_traps(vcpu);
__load_stage2(vcpu->arch.hw_mmu, vcpu->arch.hw_mmu->arch);
}
void kvm_vcpu_put_vhe(struct kvm_vcpu *vcpu)
{
__vcpu_put_deactivate_traps(vcpu);
__vcpu_put_switch_sysregs(vcpu);
}
static const exit_handler_fn hyp_exit_handlers[] = {
[0 ... ESR_ELx_EC_MAX] = NULL,
[ESR_ELx_EC_CP15_32] = kvm_hyp_handle_cp15_32,
@ -170,17 +183,11 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
sysreg_save_host_state_vhe(host_ctxt);
/*
* ARM erratum 1165522 requires us to configure both stage 1 and
* stage 2 translation for the guest context before we clear
* HCR_EL2.TGE.
*
* We have already configured the guest's stage 1 translation in
* kvm_vcpu_load_sysregs_vhe above. We must now call
* __load_stage2 before __activate_traps, because
* __load_stage2 configures stage 2 translation, and
* __activate_traps clear HCR_EL2.TGE (among other things).
* Note that ARM erratum 1165522 requires us to configure both stage 1
* and stage 2 translation for the guest context before we clear
* HCR_EL2.TGE. The stage 1 and stage 2 guest context has already been
* loaded on the CPU in kvm_vcpu_load_vhe().
*/
__load_stage2(vcpu->arch.hw_mmu, vcpu->arch.hw_mmu->arch);
__activate_traps(vcpu);
__kvm_adjust_pc(vcpu);

View file

@ -52,7 +52,7 @@ void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt)
NOKPROBE_SYMBOL(sysreg_restore_guest_state_vhe);
/**
* kvm_vcpu_load_sysregs_vhe - Load guest system registers to the physical CPU
* __vcpu_load_switch_sysregs - Load guest system registers to the physical CPU
*
* @vcpu: The VCPU pointer
*
@ -62,7 +62,7 @@ NOKPROBE_SYMBOL(sysreg_restore_guest_state_vhe);
* and loading system register state early avoids having to load them on
* every entry to the VM.
*/
void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu)
void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu)
{
struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
struct kvm_cpu_context *host_ctxt;
@ -92,12 +92,10 @@ void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu)
__sysreg_restore_el1_state(guest_ctxt);
vcpu_set_flag(vcpu, SYSREGS_ON_CPU);
activate_traps_vhe_load(vcpu);
}
/**
* kvm_vcpu_put_sysregs_vhe - Restore host system registers to the physical CPU
* __vcpu_put_switch_syregs - Restore host system registers to the physical CPU
*
* @vcpu: The VCPU pointer
*
@ -107,13 +105,12 @@ void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu)
* and deferring saving system register state until we're no longer running the
* VCPU avoids having to save them on every exit from the VM.
*/
void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu)
void __vcpu_put_switch_sysregs(struct kvm_vcpu *vcpu)
{
struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
struct kvm_cpu_context *host_ctxt;
host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
deactivate_traps_vhe_put(vcpu);
__sysreg_save_el1_state(guest_ctxt);
__sysreg_save_user_state(guest_ctxt);

View file

@ -11,18 +11,25 @@
#include <asm/tlbflush.h>
struct tlb_inv_context {
unsigned long flags;
u64 tcr;
u64 sctlr;
struct kvm_s2_mmu *mmu;
unsigned long flags;
u64 tcr;
u64 sctlr;
};
static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu,
struct tlb_inv_context *cxt)
{
struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
u64 val;
local_irq_save(cxt->flags);
if (vcpu && mmu != vcpu->arch.hw_mmu)
cxt->mmu = vcpu->arch.hw_mmu;
else
cxt->mmu = NULL;
if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
/*
* For CPUs that are affected by ARM errata 1165522 or 1530923,
@ -66,10 +73,13 @@ static void __tlb_switch_to_host(struct tlb_inv_context *cxt)
* We're done with the TLB operation, let's restore the host's
* view of HCR_EL2.
*/
write_sysreg(0, vttbr_el2);
write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
isb();
/* ... and the stage-2 MMU context that we switched away from */
if (cxt->mmu)
__load_stage2(cxt->mmu, cxt->mmu->arch);
if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
/* Restore the registers to what they were */
write_sysreg_el1(cxt->tcr, SYS_TCR);

View file

@ -892,7 +892,7 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
kvm->arch.vtcr = kvm_get_vtcr(mmfr0, mmfr1, phys_shift);
mmu->vtcr = kvm_get_vtcr(mmfr0, mmfr1, phys_shift);
if (mmu->pgt != NULL) {
kvm_err("kvm_arch already initialized?\n");
@ -1067,7 +1067,8 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
phys_addr_t addr;
int ret = 0;
struct kvm_mmu_memory_cache cache = { .gfp_zero = __GFP_ZERO };
struct kvm_pgtable *pgt = kvm->arch.mmu.pgt;
struct kvm_s2_mmu *mmu = &kvm->arch.mmu;
struct kvm_pgtable *pgt = mmu->pgt;
enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_DEVICE |
KVM_PGTABLE_PROT_R |
(writable ? KVM_PGTABLE_PROT_W : 0);
@ -1080,7 +1081,7 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
for (addr = guest_ipa; addr < guest_ipa + size; addr += PAGE_SIZE) {
ret = kvm_mmu_topup_memory_cache(&cache,
kvm_mmu_cache_min_pages(kvm));
kvm_mmu_cache_min_pages(mmu));
if (ret)
break;
@ -1411,7 +1412,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
if (fault_status != ESR_ELx_FSC_PERM ||
(logging_active && write_fault)) {
ret = kvm_mmu_topup_memory_cache(memcache,
kvm_mmu_cache_min_pages(kvm));
kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu));
if (ret)
return ret;
}
@ -1727,7 +1728,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
}
/* Userspace should not be able to register out-of-bounds IPAs */
VM_BUG_ON(fault_ipa >= kvm_phys_size(vcpu->kvm));
VM_BUG_ON(fault_ipa >= kvm_phys_size(vcpu->arch.hw_mmu));
if (fault_status == ESR_ELx_FSC_ACCESS) {
handle_access_fault(vcpu, fault_ipa);
@ -2001,7 +2002,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
* Prevent userspace from creating a memory region outside of the IPA
* space addressable by the KVM guest IPA space.
*/
if ((new->base_gfn + new->npages) > (kvm_phys_size(kvm) >> PAGE_SHIFT))
if ((new->base_gfn + new->npages) > (kvm_phys_size(&kvm->arch.mmu) >> PAGE_SHIFT))
return -EFAULT;
hva = new->userspace_addr;

View file

@ -123,7 +123,7 @@ static int __pkvm_create_hyp_vm(struct kvm *host_kvm)
if (host_kvm->created_vcpus < 1)
return -EINVAL;
pgd_sz = kvm_pgtable_stage2_pgd_size(host_kvm->arch.vtcr);
pgd_sz = kvm_pgtable_stage2_pgd_size(host_kvm->arch.mmu.vtcr);
/*
* The PGD pages will be reclaimed using a hyp_memcache which implies

View file

@ -27,7 +27,8 @@ int vgic_check_iorange(struct kvm *kvm, phys_addr_t ioaddr,
if (addr + size < addr)
return -EINVAL;
if (addr & ~kvm_phys_mask(kvm) || addr + size > kvm_phys_size(kvm))
if (addr & ~kvm_phys_mask(&kvm->arch.mmu) ||
(addr + size) > kvm_phys_size(&kvm->arch.mmu))
return -E2BIG;
return 0;

View file

@ -135,10 +135,11 @@ void kvm_arm_vmid_clear_active(void)
atomic64_set(this_cpu_ptr(&active_vmids), VMID_ACTIVE_INVALID);
}
void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid)
bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid)
{
unsigned long flags;
u64 vmid, old_active_vmid;
bool updated = false;
vmid = atomic64_read(&kvm_vmid->id);
@ -156,17 +157,21 @@ void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid)
if (old_active_vmid != 0 && vmid_gen_match(vmid) &&
0 != atomic64_cmpxchg_relaxed(this_cpu_ptr(&active_vmids),
old_active_vmid, vmid))
return;
return false;
raw_spin_lock_irqsave(&cpu_vmid_lock, flags);
/* Check that our VMID belongs to the current generation. */
vmid = atomic64_read(&kvm_vmid->id);
if (!vmid_gen_match(vmid))
if (!vmid_gen_match(vmid)) {
vmid = new_vmid(kvm_vmid);
updated = true;
}
atomic64_set(this_cpu_ptr(&active_vmids), vmid);
raw_spin_unlock_irqrestore(&cpu_vmid_lock, flags);
return updated;
}
/*