summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--arch/powerpc/kvm/Kconfig2
-rw-r--r--arch/powerpc/kvm/Makefile4
-rw-r--r--arch/powerpc/kvm/book3s_64_vio_hv.c13
-rw-r--r--arch/powerpc/kvm/book3s_hv_builtin.c9
-rw-r--r--arch/powerpc/kvm/book3s_pr_papr.c70
-rw-r--r--arch/powerpc/kvm/powerpc.c4
-rw-r--r--arch/x86/include/asm/kvm_host.h2
-rw-r--r--arch/x86/kernel/fpu/init.c1
-rw-r--r--arch/x86/kvm/paging_tmpl.h35
-rw-r--r--arch/x86/kvm/vmx.c4
-rw-r--r--arch/x86/kvm/x86.c9
11 files changed, 112 insertions, 41 deletions
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 24de532c1736..0c52cb5d43f5 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -67,7 +67,7 @@ config KVM_BOOK3S_64
select KVM_BOOK3S_64_HANDLER
select KVM
select KVM_BOOK3S_PR_POSSIBLE if !KVM_BOOK3S_HV_POSSIBLE
- select SPAPR_TCE_IOMMU if IOMMU_SUPPORT
+ select SPAPR_TCE_IOMMU if IOMMU_SUPPORT && (PPC_SERIES || PPC_POWERNV)
---help---
Support running unmodified book3s_64 and book3s_32 guest kernels
in virtual machines on book3s_64 host processors.
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index d91a2604c496..381a6ec0ff3b 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -46,7 +46,7 @@ kvm-e500mc-objs := \
e500_emulate.o
kvm-objs-$(CONFIG_KVM_E500MC) := $(kvm-e500mc-objs)
-kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) := \
+kvm-book3s_64-builtin-objs-$(CONFIG_SPAPR_TCE_IOMMU) := \
book3s_64_vio_hv.o
kvm-pr-y := \
@@ -90,11 +90,11 @@ kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \
book3s_xics.o
kvm-book3s_64-objs-$(CONFIG_KVM_XIVE) += book3s_xive.o
+kvm-book3s_64-objs-$(CONFIG_SPAPR_TCE_IOMMU) += book3s_64_vio.o
kvm-book3s_64-module-objs := \
$(common-objs-y) \
book3s.o \
- book3s_64_vio.o \
book3s_rtas.o \
$(kvm-book3s_64-objs-y)
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index eda0a8f6fae8..3adfd2f5301c 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -301,6 +301,10 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
/* liobn, ioba, tce); */
+ /* For radix, we might be in virtual mode, so punt */
+ if (kvm_is_radix(vcpu->kvm))
+ return H_TOO_HARD;
+
stt = kvmppc_find_table(vcpu->kvm, liobn);
if (!stt)
return H_TOO_HARD;
@@ -381,6 +385,10 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
bool prereg = false;
struct kvmppc_spapr_tce_iommu_table *stit;
+ /* For radix, we might be in virtual mode, so punt */
+ if (kvm_is_radix(vcpu->kvm))
+ return H_TOO_HARD;
+
stt = kvmppc_find_table(vcpu->kvm, liobn);
if (!stt)
return H_TOO_HARD;
@@ -491,6 +499,10 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
long i, ret;
struct kvmppc_spapr_tce_iommu_table *stit;
+ /* For radix, we might be in virtual mode, so punt */
+ if (kvm_is_radix(vcpu->kvm))
+ return H_TOO_HARD;
+
stt = kvmppc_find_table(vcpu->kvm, liobn);
if (!stt)
return H_TOO_HARD;
@@ -527,6 +539,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
return H_SUCCESS;
}
+/* This can be called in either virtual mode or real mode */
long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
unsigned long ioba)
{
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 88a65923c649..ee4c2558c305 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -207,7 +207,14 @@ EXPORT_SYMBOL_GPL(kvmppc_hwrng_present);
long kvmppc_h_random(struct kvm_vcpu *vcpu)
{
- if (powernv_get_random_real_mode(&vcpu->arch.gpr[4]))
+ int r;
+
+ /* Only need to do the expensive mfmsr() on radix */
+ if (kvm_is_radix(vcpu->kvm) && (mfmsr() & MSR_IR))
+ r = powernv_get_random_long(&vcpu->arch.gpr[4]);
+ else
+ r = powernv_get_random_real_mode(&vcpu->arch.gpr[4]);
+ if (r)
return H_SUCCESS;
return H_HARDWARE;
diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c
index bcbeeb62dd13..8a4205fa774f 100644
--- a/arch/powerpc/kvm/book3s_pr_papr.c
+++ b/arch/powerpc/kvm/book3s_pr_papr.c
@@ -50,7 +50,9 @@ static int kvmppc_h_pr_enter(struct kvm_vcpu *vcpu)
pteg_addr = get_pteg_addr(vcpu, pte_index);
mutex_lock(&vcpu->kvm->arch.hpt_mutex);
- copy_from_user(pteg, (void __user *)pteg_addr, sizeof(pteg));
+ ret = H_FUNCTION;
+ if (copy_from_user(pteg, (void __user *)pteg_addr, sizeof(pteg)))
+ goto done;
hpte = pteg;
ret = H_PTEG_FULL;
@@ -71,7 +73,9 @@ static int kvmppc_h_pr_enter(struct kvm_vcpu *vcpu)
hpte[0] = cpu_to_be64(kvmppc_get_gpr(vcpu, 6));
hpte[1] = cpu_to_be64(kvmppc_get_gpr(vcpu, 7));
pteg_addr += i * HPTE_SIZE;
- copy_to_user((void __user *)pteg_addr, hpte, HPTE_SIZE);
+ ret = H_FUNCTION;
+ if (copy_to_user((void __user *)pteg_addr, hpte, HPTE_SIZE))
+ goto done;
kvmppc_set_gpr(vcpu, 4, pte_index | i);
ret = H_SUCCESS;
@@ -93,7 +97,9 @@ static int kvmppc_h_pr_remove(struct kvm_vcpu *vcpu)
pteg = get_pteg_addr(vcpu, pte_index);
mutex_lock(&vcpu->kvm->arch.hpt_mutex);
- copy_from_user(pte, (void __user *)pteg, sizeof(pte));
+ ret = H_FUNCTION;
+ if (copy_from_user(pte, (void __user *)pteg, sizeof(pte)))
+ goto done;
pte[0] = be64_to_cpu((__force __be64)pte[0]);
pte[1] = be64_to_cpu((__force __be64)pte[1]);
@@ -103,7 +109,9 @@ static int kvmppc_h_pr_remove(struct kvm_vcpu *vcpu)
((flags & H_ANDCOND) && (pte[0] & avpn) != 0))
goto done;
- copy_to_user((void __user *)pteg, &v, sizeof(v));
+ ret = H_FUNCTION;
+ if (copy_to_user((void __user *)pteg, &v, sizeof(v)))
+ goto done;
rb = compute_tlbie_rb(pte[0], pte[1], pte_index);
vcpu->arch.mmu.tlbie(vcpu, rb, rb & 1 ? true : false);
@@ -171,7 +179,10 @@ static int kvmppc_h_pr_bulk_remove(struct kvm_vcpu *vcpu)
}
pteg = get_pteg_addr(vcpu, tsh & H_BULK_REMOVE_PTEX);
- copy_from_user(pte, (void __user *)pteg, sizeof(pte));
+ if (copy_from_user(pte, (void __user *)pteg, sizeof(pte))) {
+ ret = H_FUNCTION;
+ break;
+ }
pte[0] = be64_to_cpu((__force __be64)pte[0]);
pte[1] = be64_to_cpu((__force __be64)pte[1]);
@@ -184,7 +195,10 @@ static int kvmppc_h_pr_bulk_remove(struct kvm_vcpu *vcpu)
tsh |= H_BULK_REMOVE_NOT_FOUND;
} else {
/* Splat the pteg in (userland) hpt */
- copy_to_user((void __user *)pteg, &v, sizeof(v));
+ if (copy_to_user((void __user *)pteg, &v, sizeof(v))) {
+ ret = H_FUNCTION;
+ break;
+ }
rb = compute_tlbie_rb(pte[0], pte[1],
tsh & H_BULK_REMOVE_PTEX);
@@ -211,7 +225,9 @@ static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu)
pteg = get_pteg_addr(vcpu, pte_index);
mutex_lock(&vcpu->kvm->arch.hpt_mutex);
- copy_from_user(pte, (void __user *)pteg, sizeof(pte));
+ ret = H_FUNCTION;
+ if (copy_from_user(pte, (void __user *)pteg, sizeof(pte)))
+ goto done;
pte[0] = be64_to_cpu((__force __be64)pte[0]);
pte[1] = be64_to_cpu((__force __be64)pte[1]);
@@ -234,7 +250,9 @@ static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu)
vcpu->arch.mmu.tlbie(vcpu, rb, rb & 1 ? true : false);
pte[0] = (__force u64)cpu_to_be64(pte[0]);
pte[1] = (__force u64)cpu_to_be64(pte[1]);
- copy_to_user((void __user *)pteg, pte, sizeof(pte));
+ ret = H_FUNCTION;
+ if (copy_to_user((void __user *)pteg, pte, sizeof(pte)))
+ goto done;
ret = H_SUCCESS;
done:
@@ -244,36 +262,37 @@ static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu)
return EMULATE_DONE;
}
-static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu)
+static int kvmppc_h_pr_logical_ci_load(struct kvm_vcpu *vcpu)
{
- unsigned long liobn = kvmppc_get_gpr(vcpu, 4);
- unsigned long ioba = kvmppc_get_gpr(vcpu, 5);
- unsigned long tce = kvmppc_get_gpr(vcpu, 6);
long rc;
- rc = kvmppc_h_put_tce(vcpu, liobn, ioba, tce);
+ rc = kvmppc_h_logical_ci_load(vcpu);
if (rc == H_TOO_HARD)
return EMULATE_FAIL;
kvmppc_set_gpr(vcpu, 3, rc);
return EMULATE_DONE;
}
-static int kvmppc_h_pr_logical_ci_load(struct kvm_vcpu *vcpu)
+static int kvmppc_h_pr_logical_ci_store(struct kvm_vcpu *vcpu)
{
long rc;
- rc = kvmppc_h_logical_ci_load(vcpu);
+ rc = kvmppc_h_logical_ci_store(vcpu);
if (rc == H_TOO_HARD)
return EMULATE_FAIL;
kvmppc_set_gpr(vcpu, 3, rc);
return EMULATE_DONE;
}
-static int kvmppc_h_pr_logical_ci_store(struct kvm_vcpu *vcpu)
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu)
{
+ unsigned long liobn = kvmppc_get_gpr(vcpu, 4);
+ unsigned long ioba = kvmppc_get_gpr(vcpu, 5);
+ unsigned long tce = kvmppc_get_gpr(vcpu, 6);
long rc;
- rc = kvmppc_h_logical_ci_store(vcpu);
+ rc = kvmppc_h_put_tce(vcpu, liobn, ioba, tce);
if (rc == H_TOO_HARD)
return EMULATE_FAIL;
kvmppc_set_gpr(vcpu, 3, rc);
@@ -311,6 +330,23 @@ static int kvmppc_h_pr_stuff_tce(struct kvm_vcpu *vcpu)
return EMULATE_DONE;
}
+#else /* CONFIG_SPAPR_TCE_IOMMU */
+static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu)
+{
+ return EMULATE_FAIL;
+}
+
+static int kvmppc_h_pr_put_tce_indirect(struct kvm_vcpu *vcpu)
+{
+ return EMULATE_FAIL;
+}
+
+static int kvmppc_h_pr_stuff_tce(struct kvm_vcpu *vcpu)
+{
+ return EMULATE_FAIL;
+}
+#endif /* CONFIG_SPAPR_TCE_IOMMU */
+
static int kvmppc_h_pr_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd)
{
long rc = kvmppc_xics_hcall(vcpu, cmd);
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index f7cf2cd564ef..7f71ab5fcad1 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -1749,7 +1749,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
r = kvm_vm_ioctl_enable_cap(kvm, &cap);
break;
}
-#ifdef CONFIG_PPC_BOOK3S_64
+#ifdef CONFIG_SPAPR_TCE_IOMMU
case KVM_CREATE_SPAPR_TCE_64: {
struct kvm_create_spapr_tce_64 create_tce_64;
@@ -1780,6 +1780,8 @@ long kvm_arch_vm_ioctl(struct file *filp,
r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce_64);
goto out;
}
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
case KVM_PPC_GET_SMMU_INFO: {
struct kvm_ppc_smmu_info info;
struct kvm *kvm = filp->private_data;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 9c761fea0c98..695605eb1dfb 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -43,7 +43,7 @@
#define KVM_PRIVATE_MEM_SLOTS 3
#define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS)
-#define KVM_HALT_POLL_NS_DEFAULT 400000
+#define KVM_HALT_POLL_NS_DEFAULT 200000
#define KVM_IRQCHIP_NUM_PINS KVM_IOAPIC_NUM_PINS
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index c2f8dde3255c..d5d44c452624 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -90,6 +90,7 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
* Boot time FPU feature detection code:
*/
unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
+EXPORT_SYMBOL_GPL(mxcsr_feature_mask);
static void __init fpu__init_system_mxcsr(void)
{
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 56241746abbd..b0454c7e4cff 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -283,11 +283,13 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
pt_element_t pte;
pt_element_t __user *uninitialized_var(ptep_user);
gfn_t table_gfn;
- unsigned index, pt_access, pte_access, accessed_dirty, pte_pkey;
+ u64 pt_access, pte_access;
+ unsigned index, accessed_dirty, pte_pkey;
unsigned nested_access;
gpa_t pte_gpa;
bool have_ad;
int offset;
+ u64 walk_nx_mask = 0;
const int write_fault = access & PFERR_WRITE_MASK;
const int user_fault = access & PFERR_USER_MASK;
const int fetch_fault = access & PFERR_FETCH_MASK;
@@ -302,6 +304,7 @@ retry_walk:
have_ad = PT_HAVE_ACCESSED_DIRTY(mmu);
#if PTTYPE == 64
+ walk_nx_mask = 1ULL << PT64_NX_SHIFT;
if (walker->level == PT32E_ROOT_LEVEL) {
pte = mmu->get_pdptr(vcpu, (addr >> 30) & 3);
trace_kvm_mmu_paging_element(pte, walker->level);
@@ -313,8 +316,6 @@ retry_walk:
walker->max_level = walker->level;
ASSERT(!(is_long_mode(vcpu) && !is_pae(vcpu)));
- accessed_dirty = have_ad ? PT_GUEST_ACCESSED_MASK : 0;
-
/*
* FIXME: on Intel processors, loads of the PDPTE registers for PAE paging
* by the MOV to CR instruction are treated as reads and do not cause the
@@ -322,14 +323,14 @@ retry_walk:
*/
nested_access = (have_ad ? PFERR_WRITE_MASK : 0) | PFERR_USER_MASK;
- pt_access = pte_access = ACC_ALL;
+ pte_access = ~0;
++walker->level;
do {
gfn_t real_gfn;
unsigned long host_addr;
- pt_access &= pte_access;
+ pt_access = pte_access;
--walker->level;
index = PT_INDEX(addr, walker->level);
@@ -371,6 +372,12 @@ retry_walk:
trace_kvm_mmu_paging_element(pte, walker->level);
+ /*
+ * Inverting the NX it lets us AND it like other
+ * permission bits.
+ */
+ pte_access = pt_access & (pte ^ walk_nx_mask);
+
if (unlikely(!FNAME(is_present_gpte)(pte)))
goto error;
@@ -379,14 +386,16 @@ retry_walk:
goto error;
}
- accessed_dirty &= pte;
- pte_access = pt_access & FNAME(gpte_access)(vcpu, pte);
-
walker->ptes[walker->level - 1] = pte;
} while (!is_last_gpte(mmu, walker->level, pte));
pte_pkey = FNAME(gpte_pkeys)(vcpu, pte);
- errcode = permission_fault(vcpu, mmu, pte_access, pte_pkey, access);
+ accessed_dirty = have_ad ? pte_access & PT_GUEST_ACCESSED_MASK : 0;
+
+ /* Convert to ACC_*_MASK flags for struct guest_walker. */
+ walker->pt_access = FNAME(gpte_access)(vcpu, pt_access ^ walk_nx_mask);
+ walker->pte_access = FNAME(gpte_access)(vcpu, pte_access ^ walk_nx_mask);
+ errcode = permission_fault(vcpu, mmu, walker->pte_access, pte_pkey, access);
if (unlikely(errcode))
goto error;
@@ -403,7 +412,7 @@ retry_walk:
walker->gfn = real_gpa >> PAGE_SHIFT;
if (!write_fault)
- FNAME(protect_clean_gpte)(mmu, &pte_access, pte);
+ FNAME(protect_clean_gpte)(mmu, &walker->pte_access, pte);
else
/*
* On a write fault, fold the dirty bit into accessed_dirty.
@@ -421,10 +430,8 @@ retry_walk:
goto retry_walk;
}
- walker->pt_access = pt_access;
- walker->pte_access = pte_access;
pgprintk("%s: pte %llx pte_access %x pt_access %x\n",
- __func__, (u64)pte, pte_access, pt_access);
+ __func__, (u64)pte, walker->pte_access, walker->pt_access);
return 1;
error:
@@ -452,7 +459,7 @@ error:
*/
if (!(errcode & PFERR_RSVD_MASK)) {
vcpu->arch.exit_qualification &= 0x187;
- vcpu->arch.exit_qualification |= ((pt_access & pte) & 0x7) << 3;
+ vcpu->arch.exit_qualification |= (pte_access & 0x7) << 3;
}
#endif
walker->fault.address = addr;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c6f4ad44aa95..72f78396bc09 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6504,7 +6504,7 @@ static __init int hardware_setup(void)
enable_ept_ad_bits = 0;
}
- if (!cpu_has_vmx_ept_ad_bits())
+ if (!cpu_has_vmx_ept_ad_bits() || !enable_ept)
enable_ept_ad_bits = 0;
if (!cpu_has_vmx_unrestricted_guest())
@@ -11213,7 +11213,7 @@ static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu)
if (!nested_cpu_has_pml(vmcs12))
return 0;
- if (vmcs12->guest_pml_index > PML_ENTITY_NUM) {
+ if (vmcs12->guest_pml_index >= PML_ENTITY_NUM) {
vmx->nested.pml_full = true;
return 1;
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 464da936c53d..b54125b590e8 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3288,11 +3288,14 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
}
}
+#define XSAVE_MXCSR_OFFSET 24
+
static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
struct kvm_xsave *guest_xsave)
{
u64 xstate_bv =
*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)];
+ u32 mxcsr = *(u32 *)&guest_xsave->region[XSAVE_MXCSR_OFFSET / sizeof(u32)];
if (boot_cpu_has(X86_FEATURE_XSAVE)) {
/*
@@ -3300,11 +3303,13 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
* CPUID leaf 0xD, index 0, EDX:EAX. This is for compatibility
* with old userspace.
*/
- if (xstate_bv & ~kvm_supported_xcr0())
+ if (xstate_bv & ~kvm_supported_xcr0() ||
+ mxcsr & ~mxcsr_feature_mask)
return -EINVAL;
load_xsave(vcpu, (u8 *)guest_xsave->region);
} else {
- if (xstate_bv & ~XFEATURE_MASK_FPSSE)
+ if (xstate_bv & ~XFEATURE_MASK_FPSSE ||
+ mxcsr & ~mxcsr_feature_mask)
return -EINVAL;
memcpy(&vcpu->arch.guest_fpu.state.fxsave,
guest_xsave->region, sizeof(struct fxregs_state));
generated by cgit (git 2.34.1) at 2025-05-28 06:12:34 +0000