summaryrefslogtreecommitdiff
path: root/arch/loongarch/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/loongarch/kvm')
-rw-r--r--arch/loongarch/kvm/Kconfig1
-rw-r--r--arch/loongarch/kvm/exit.c38
-rw-r--r--arch/loongarch/kvm/main.c1
-rw-r--r--arch/loongarch/kvm/mmu.c72
-rw-r--r--arch/loongarch/kvm/tlb.c5
-rw-r--r--arch/loongarch/kvm/vcpu.c156
6 files changed, 243 insertions, 30 deletions
diff --git a/arch/loongarch/kvm/Kconfig b/arch/loongarch/kvm/Kconfig
index c4ef2b4d9797..248744b4d086 100644
--- a/arch/loongarch/kvm/Kconfig
+++ b/arch/loongarch/kvm/Kconfig
@@ -29,6 +29,7 @@ config KVM
select KVM_MMIO
select HAVE_KVM_READONLY_MEM
select KVM_XFER_TO_GUEST_WORK
+ select SCHED_INFO
help
Support hosting virtualized guest machines using
hardware virtualization extensions. You will need
diff --git a/arch/loongarch/kvm/exit.c b/arch/loongarch/kvm/exit.c
index a68573e091c0..ea73f9dc2cc6 100644
--- a/arch/loongarch/kvm/exit.c
+++ b/arch/loongarch/kvm/exit.c
@@ -24,7 +24,7 @@
static int kvm_emu_cpucfg(struct kvm_vcpu *vcpu, larch_inst inst)
{
int rd, rj;
- unsigned int index;
+ unsigned int index, ret;
if (inst.reg2_format.opcode != cpucfg_op)
return EMULATE_FAIL;
@@ -50,7 +50,10 @@ static int kvm_emu_cpucfg(struct kvm_vcpu *vcpu, larch_inst inst)
vcpu->arch.gprs[rd] = *(unsigned int *)KVM_SIGNATURE;
break;
case CPUCFG_KVM_FEATURE:
- vcpu->arch.gprs[rd] = KVM_FEATURE_IPI;
+ ret = KVM_FEATURE_IPI;
+ if (kvm_pvtime_supported())
+ ret |= KVM_FEATURE_STEAL_TIME;
+ vcpu->arch.gprs[rd] = ret;
break;
default:
vcpu->arch.gprs[rd] = 0;
@@ -687,6 +690,34 @@ static int kvm_handle_fpu_disabled(struct kvm_vcpu *vcpu)
return RESUME_GUEST;
}
+static long kvm_save_notify(struct kvm_vcpu *vcpu)
+{
+ unsigned long id, data;
+
+ id = kvm_read_reg(vcpu, LOONGARCH_GPR_A1);
+ data = kvm_read_reg(vcpu, LOONGARCH_GPR_A2);
+ switch (id) {
+ case KVM_FEATURE_STEAL_TIME:
+ if (!kvm_pvtime_supported())
+ return KVM_HCALL_INVALID_CODE;
+
+ if (data & ~(KVM_STEAL_PHYS_MASK | KVM_STEAL_PHYS_VALID))
+ return KVM_HCALL_INVALID_PARAMETER;
+
+ vcpu->arch.st.guest_addr = data;
+ if (!(data & KVM_STEAL_PHYS_VALID))
+ break;
+
+ vcpu->arch.st.last_steal = current->sched_info.run_delay;
+ kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
+ break;
+ default:
+ break;
+ };
+
+ return 0;
+};
+
/*
* kvm_handle_lsx_disabled() - Guest used LSX while disabled in root.
* @vcpu: Virtual CPU context.
@@ -758,6 +789,9 @@ static void kvm_handle_service(struct kvm_vcpu *vcpu)
kvm_send_pv_ipi(vcpu);
ret = KVM_HCALL_SUCCESS;
break;
+ case KVM_HCALL_FUNC_NOTIFY:
+ ret = kvm_save_notify(vcpu);
+ break;
default:
ret = KVM_HCALL_INVALID_CODE;
break;
diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c
index 86a2f2d0cb27..844736b99d38 100644
--- a/arch/loongarch/kvm/main.c
+++ b/arch/loongarch/kvm/main.c
@@ -242,6 +242,7 @@ void kvm_check_vpid(struct kvm_vcpu *vcpu)
kvm_update_vpid(vcpu, cpu);
trace_kvm_vpid_change(vcpu, vcpu->arch.vpid);
vcpu->cpu = cpu;
+ kvm_clear_request(KVM_REQ_TLB_FLUSH_GPA, vcpu);
}
/* Restore GSTAT(0x50).vpid */
diff --git a/arch/loongarch/kvm/mmu.c b/arch/loongarch/kvm/mmu.c
index 98883aa23ab8..2634a9e8d82c 100644
--- a/arch/loongarch/kvm/mmu.c
+++ b/arch/loongarch/kvm/mmu.c
@@ -163,6 +163,7 @@ static kvm_pte_t *kvm_populate_gpa(struct kvm *kvm,
child = kvm_mmu_memory_cache_alloc(cache);
_kvm_pte_init(child, ctx.invalid_ptes[ctx.level - 1]);
+ smp_wmb(); /* Make pte visible before pmd */
kvm_set_pte(entry, __pa(child));
} else if (kvm_pte_huge(*entry)) {
return entry;
@@ -444,6 +445,17 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
enum kvm_mr_change change)
{
int needs_flush;
+ u32 old_flags = old ? old->flags : 0;
+ u32 new_flags = new ? new->flags : 0;
+ bool log_dirty_pages = new_flags & KVM_MEM_LOG_DIRTY_PAGES;
+
+ /* Only track memslot flags changed */
+ if (change != KVM_MR_FLAGS_ONLY)
+ return;
+
+ /* Discard dirty page tracking on readonly memslot */
+ if ((old_flags & new_flags) & KVM_MEM_READONLY)
+ return;
/*
* If dirty page logging is enabled, write protect all pages in the slot
@@ -454,9 +466,14 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
* MOVE/DELETE: The old mappings will already have been cleaned up by
* kvm_arch_flush_shadow_memslot()
*/
- if (change == KVM_MR_FLAGS_ONLY &&
- (!(old->flags & KVM_MEM_LOG_DIRTY_PAGES) &&
- new->flags & KVM_MEM_LOG_DIRTY_PAGES)) {
+ if (!(old_flags & KVM_MEM_LOG_DIRTY_PAGES) && log_dirty_pages) {
+ /*
+ * Initially-all-set does not require write protecting any page
+ * because they're all assumed to be dirty.
+ */
+ if (kvm_dirty_log_manual_protect_and_init_set(kvm))
+ return;
+
spin_lock(&kvm->mmu_lock);
/* Write protect GPA page table entries */
needs_flush = kvm_mkclean_gpa_pt(kvm, new->base_gfn,
@@ -540,6 +557,7 @@ static int kvm_map_page_fast(struct kvm_vcpu *vcpu, unsigned long gpa, bool writ
gfn_t gfn = gpa >> PAGE_SHIFT;
struct kvm *kvm = vcpu->kvm;
struct kvm_memory_slot *slot;
+ struct page *page;
spin_lock(&kvm->mmu_lock);
@@ -551,10 +569,8 @@ static int kvm_map_page_fast(struct kvm_vcpu *vcpu, unsigned long gpa, bool writ
}
/* Track access to pages marked old */
- new = *ptep;
- if (!kvm_pte_young(new))
- new = kvm_pte_mkyoung(new);
- /* call kvm_set_pfn_accessed() after unlock */
+ new = kvm_pte_mkyoung(*ptep);
+ /* call kvm_set_pfn_accessed() after unlock */
if (write && !kvm_pte_dirty(new)) {
if (!kvm_pte_write(new)) {
@@ -582,19 +598,22 @@ static int kvm_map_page_fast(struct kvm_vcpu *vcpu, unsigned long gpa, bool writ
if (changed) {
kvm_set_pte(ptep, new);
pfn = kvm_pte_pfn(new);
+ page = kvm_pfn_to_refcounted_page(pfn);
+ if (page)
+ get_page(page);
}
spin_unlock(&kvm->mmu_lock);
- /*
- * Fixme: pfn may be freed after mmu_lock
- * kvm_try_get_pfn(pfn)/kvm_release_pfn pair to prevent this?
- */
- if (kvm_pte_young(changed))
- kvm_set_pfn_accessed(pfn);
+ if (changed) {
+ if (kvm_pte_young(changed))
+ kvm_set_pfn_accessed(pfn);
- if (kvm_pte_dirty(changed)) {
- mark_page_dirty(kvm, gfn);
- kvm_set_pfn_dirty(pfn);
+ if (kvm_pte_dirty(changed)) {
+ mark_page_dirty(kvm, gfn);
+ kvm_set_pfn_dirty(pfn);
+ }
+ if (page)
+ put_page(page);
}
return ret;
out:
@@ -737,6 +756,7 @@ static kvm_pte_t *kvm_split_huge(struct kvm_vcpu *vcpu, kvm_pte_t *ptep, gfn_t g
val += PAGE_SIZE;
}
+ smp_wmb(); /* Make pte visible before pmd */
/* The later kvm_flush_tlb_gpa() will flush hugepage tlb */
kvm_set_pte(ptep, __pa(child));
@@ -858,11 +878,21 @@ retry:
/* Disable dirty logging on HugePages */
level = 0;
- if (!fault_supports_huge_mapping(memslot, hva, write)) {
- level = 0;
- } else {
+ if (fault_supports_huge_mapping(memslot, hva, write)) {
+ /* Check page level about host mmu*/
level = host_pfn_mapping_level(kvm, gfn, memslot);
if (level == 1) {
+ /*
+ * Check page level about secondary mmu
+ * Disable hugepage if it is normal page on
+ * secondary mmu already
+ */
+ ptep = kvm_populate_gpa(kvm, NULL, gpa, 0);
+ if (ptep && !kvm_pte_huge(*ptep))
+ level = 0;
+ }
+
+ if (level == 1) {
gfn = gfn & ~(PTRS_PER_PTE - 1);
pfn = pfn & ~(PTRS_PER_PTE - 1);
}
@@ -892,7 +922,6 @@ retry:
kvm_set_pfn_dirty(pfn);
}
- kvm_set_pfn_accessed(pfn);
kvm_release_pfn_clean(pfn);
out:
srcu_read_unlock(&kvm->srcu, srcu_idx);
@@ -908,7 +937,8 @@ int kvm_handle_mm_fault(struct kvm_vcpu *vcpu, unsigned long gpa, bool write)
return ret;
/* Invalidate this entry in the TLB */
- kvm_flush_tlb_gpa(vcpu, gpa);
+ vcpu->arch.flush_gpa = gpa;
+ kvm_make_request(KVM_REQ_TLB_FLUSH_GPA, vcpu);
return 0;
}
diff --git a/arch/loongarch/kvm/tlb.c b/arch/loongarch/kvm/tlb.c
index 02535df6b51f..ebdbe9264e9c 100644
--- a/arch/loongarch/kvm/tlb.c
+++ b/arch/loongarch/kvm/tlb.c
@@ -23,10 +23,7 @@ void kvm_flush_tlb_all(void)
void kvm_flush_tlb_gpa(struct kvm_vcpu *vcpu, unsigned long gpa)
{
- unsigned long flags;
-
- local_irq_save(flags);
+ lockdep_assert_irqs_disabled();
gpa &= (PAGE_MASK << 1);
invtlb(INVTLB_GID_ADDR, read_csr_gstat() & CSR_GSTAT_GID, gpa);
- local_irq_restore(flags);
}
diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index 9e8030d45129..16756ffb55e8 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -31,6 +31,50 @@ const struct kvm_stats_header kvm_vcpu_stats_header = {
sizeof(kvm_vcpu_stats_desc),
};
+static void kvm_update_stolen_time(struct kvm_vcpu *vcpu)
+{
+ u32 version;
+ u64 steal;
+ gpa_t gpa;
+ struct kvm_memslots *slots;
+ struct kvm_steal_time __user *st;
+ struct gfn_to_hva_cache *ghc;
+
+ ghc = &vcpu->arch.st.cache;
+ gpa = vcpu->arch.st.guest_addr;
+ if (!(gpa & KVM_STEAL_PHYS_VALID))
+ return;
+
+ gpa &= KVM_STEAL_PHYS_MASK;
+ slots = kvm_memslots(vcpu->kvm);
+ if (slots->generation != ghc->generation || gpa != ghc->gpa) {
+ if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, gpa, sizeof(*st))) {
+ ghc->gpa = INVALID_GPA;
+ return;
+ }
+ }
+
+ st = (struct kvm_steal_time __user *)ghc->hva;
+ unsafe_get_user(version, &st->version, out);
+ if (version & 1)
+ version += 1; /* first time write, random junk */
+
+ version += 1;
+ unsafe_put_user(version, &st->version, out);
+ smp_wmb();
+
+ unsafe_get_user(steal, &st->steal, out);
+ steal += current->sched_info.run_delay - vcpu->arch.st.last_steal;
+ vcpu->arch.st.last_steal = current->sched_info.run_delay;
+ unsafe_put_user(steal, &st->steal, out);
+
+ smp_wmb();
+ version += 1;
+ unsafe_put_user(version, &st->version, out);
+out:
+ mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa));
+}
+
/*
* kvm_check_requests - check and handle pending vCPU requests
*
@@ -48,9 +92,22 @@ static int kvm_check_requests(struct kvm_vcpu *vcpu)
if (kvm_dirty_ring_check_request(vcpu))
return RESUME_HOST;
+ if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu))
+ kvm_update_stolen_time(vcpu);
+
return RESUME_GUEST;
}
+static void kvm_late_check_requests(struct kvm_vcpu *vcpu)
+{
+ lockdep_assert_irqs_disabled();
+ if (kvm_check_request(KVM_REQ_TLB_FLUSH_GPA, vcpu))
+ if (vcpu->arch.flush_gpa != INVALID_GPA) {
+ kvm_flush_tlb_gpa(vcpu, vcpu->arch.flush_gpa);
+ vcpu->arch.flush_gpa = INVALID_GPA;
+ }
+}
+
/*
* Check and handle pending signal and vCPU requests etc
* Run with irq enabled and preempt enabled
@@ -101,6 +158,13 @@ static int kvm_pre_enter_guest(struct kvm_vcpu *vcpu)
/* Make sure the vcpu mode has been written */
smp_store_mb(vcpu->mode, IN_GUEST_MODE);
kvm_check_vpid(vcpu);
+
+ /*
+ * Called after function kvm_check_vpid()
+ * Since it updates CSR.GSTAT used by kvm_flush_tlb_gpa(),
+ * and it may also clear KVM_REQ_TLB_FLUSH_GPA pending bit
+ */
+ kvm_late_check_requests(vcpu);
vcpu->arch.host_eentry = csr_read64(LOONGARCH_CSR_EENTRY);
/* Clear KVM_LARCH_SWCSR_LATEST as CSR will change when enter guest */
vcpu->arch.aux_inuse &= ~KVM_LARCH_SWCSR_LATEST;
@@ -354,6 +418,17 @@ static int _kvm_getcsr(struct kvm_vcpu *vcpu, unsigned int id, u64 *val)
return -EINVAL;
if (id == LOONGARCH_CSR_ESTAT) {
+ preempt_disable();
+ vcpu_load(vcpu);
+ /*
+ * Sync pending interrupts into ESTAT so that interrupt
+ * remains during VM migration stage
+ */
+ kvm_deliver_intr(vcpu);
+ vcpu->arch.aux_inuse &= ~KVM_LARCH_SWCSR_LATEST;
+ vcpu_put(vcpu);
+ preempt_enable();
+
/* ESTAT IP0~IP7 get from GINTC */
gintc = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_GINTC) & 0xff;
*val = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_ESTAT) | (gintc << 2);
@@ -662,6 +737,16 @@ static int kvm_loongarch_cpucfg_has_attr(struct kvm_vcpu *vcpu,
return -ENXIO;
}
+static int kvm_loongarch_pvtime_has_attr(struct kvm_vcpu *vcpu,
+ struct kvm_device_attr *attr)
+{
+ if (!kvm_pvtime_supported() ||
+ attr->attr != KVM_LOONGARCH_VCPU_PVTIME_GPA)
+ return -ENXIO;
+
+ return 0;
+}
+
static int kvm_loongarch_vcpu_has_attr(struct kvm_vcpu *vcpu,
struct kvm_device_attr *attr)
{
@@ -671,6 +756,9 @@ static int kvm_loongarch_vcpu_has_attr(struct kvm_vcpu *vcpu,
case KVM_LOONGARCH_VCPU_CPUCFG:
ret = kvm_loongarch_cpucfg_has_attr(vcpu, attr);
break;
+ case KVM_LOONGARCH_VCPU_PVTIME_CTRL:
+ ret = kvm_loongarch_pvtime_has_attr(vcpu, attr);
+ break;
default:
break;
}
@@ -678,7 +766,7 @@ static int kvm_loongarch_vcpu_has_attr(struct kvm_vcpu *vcpu,
return ret;
}
-static int kvm_loongarch_get_cpucfg_attr(struct kvm_vcpu *vcpu,
+static int kvm_loongarch_cpucfg_get_attr(struct kvm_vcpu *vcpu,
struct kvm_device_attr *attr)
{
int ret = 0;
@@ -694,6 +782,23 @@ static int kvm_loongarch_get_cpucfg_attr(struct kvm_vcpu *vcpu,
return ret;
}
+static int kvm_loongarch_pvtime_get_attr(struct kvm_vcpu *vcpu,
+ struct kvm_device_attr *attr)
+{
+ u64 gpa;
+ u64 __user *user = (u64 __user *)attr->addr;
+
+ if (!kvm_pvtime_supported() ||
+ attr->attr != KVM_LOONGARCH_VCPU_PVTIME_GPA)
+ return -ENXIO;
+
+ gpa = vcpu->arch.st.guest_addr;
+ if (put_user(gpa, user))
+ return -EFAULT;
+
+ return 0;
+}
+
static int kvm_loongarch_vcpu_get_attr(struct kvm_vcpu *vcpu,
struct kvm_device_attr *attr)
{
@@ -701,7 +806,10 @@ static int kvm_loongarch_vcpu_get_attr(struct kvm_vcpu *vcpu,
switch (attr->group) {
case KVM_LOONGARCH_VCPU_CPUCFG:
- ret = kvm_loongarch_get_cpucfg_attr(vcpu, attr);
+ ret = kvm_loongarch_cpucfg_get_attr(vcpu, attr);
+ break;
+ case KVM_LOONGARCH_VCPU_PVTIME_CTRL:
+ ret = kvm_loongarch_pvtime_get_attr(vcpu, attr);
break;
default:
break;
@@ -716,6 +824,43 @@ static int kvm_loongarch_cpucfg_set_attr(struct kvm_vcpu *vcpu,
return -ENXIO;
}
+static int kvm_loongarch_pvtime_set_attr(struct kvm_vcpu *vcpu,
+ struct kvm_device_attr *attr)
+{
+ int idx, ret = 0;
+ u64 gpa, __user *user = (u64 __user *)attr->addr;
+ struct kvm *kvm = vcpu->kvm;
+
+ if (!kvm_pvtime_supported() ||
+ attr->attr != KVM_LOONGARCH_VCPU_PVTIME_GPA)
+ return -ENXIO;
+
+ if (get_user(gpa, user))
+ return -EFAULT;
+
+ if (gpa & ~(KVM_STEAL_PHYS_MASK | KVM_STEAL_PHYS_VALID))
+ return -EINVAL;
+
+ if (!(gpa & KVM_STEAL_PHYS_VALID)) {
+ vcpu->arch.st.guest_addr = gpa;
+ return 0;
+ }
+
+ /* Check the address is in a valid memslot */
+ idx = srcu_read_lock(&kvm->srcu);
+ if (kvm_is_error_hva(gfn_to_hva(kvm, gpa >> PAGE_SHIFT)))
+ ret = -EINVAL;
+ srcu_read_unlock(&kvm->srcu, idx);
+
+ if (!ret) {
+ vcpu->arch.st.guest_addr = gpa;
+ vcpu->arch.st.last_steal = current->sched_info.run_delay;
+ kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
+ }
+
+ return ret;
+}
+
static int kvm_loongarch_vcpu_set_attr(struct kvm_vcpu *vcpu,
struct kvm_device_attr *attr)
{
@@ -725,6 +870,9 @@ static int kvm_loongarch_vcpu_set_attr(struct kvm_vcpu *vcpu,
case KVM_LOONGARCH_VCPU_CPUCFG:
ret = kvm_loongarch_cpucfg_set_attr(vcpu, attr);
break;
+ case KVM_LOONGARCH_VCPU_PVTIME_CTRL:
+ ret = kvm_loongarch_pvtime_set_attr(vcpu, attr);
+ break;
default:
break;
}
@@ -994,6 +1142,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
struct loongarch_csrs *csr;
vcpu->arch.vpid = 0;
+ vcpu->arch.flush_gpa = INVALID_GPA;
hrtimer_init(&vcpu->arch.swtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
vcpu->arch.swtimer.function = kvm_swtimer_wakeup;
@@ -1084,6 +1233,7 @@ static int _kvm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
/* Control guest page CCA attribute */
change_csr_gcfg(CSR_GCFG_MATC_MASK, CSR_GCFG_MATC_ROOT);
+ kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
/* Don't bother restoring registers multiple times unless necessary */
if (vcpu->arch.aux_inuse & KVM_LARCH_HWCSR_USABLE)
@@ -1266,7 +1416,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
kvm_complete_iocsr_read(vcpu, run);
}
- if (run->immediate_exit)
+ if (!vcpu->wants_to_run)
return r;
/* Clear exit_reason */
generated by cgit v1.2.3 (git 2.39.0) at 2025-03-11 12:08:07 +0300