summaryrefslogtreecommitdiff
path: root/virt
diff options
context:
space:
mode:
Diffstat (limited to 'virt')
-rw-r--r--virt/kvm/arm/arm.c37
-rw-r--r--virt/kvm/arm/mmu.c12
-rw-r--r--virt/kvm/arm/psci.c143
-rw-r--r--virt/kvm/eventfd.c4
-rw-r--r--virt/kvm/kvm_main.c52
5 files changed, 165 insertions, 83 deletions
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index 94a36f6bd0ef..86941f6181bb 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -31,6 +31,7 @@
#include <linux/irqbypass.h>
#include <trace/events/kvm.h>
#include <kvm/arm_pmu.h>
+#include <kvm/arm_psci.h>
#define CREATE_TRACE_POINTS
#include "trace.h"
@@ -46,15 +47,14 @@
#include <asm/kvm_mmu.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_coproc.h>
-#include <asm/kvm_psci.h>
#include <asm/sections.h>
#ifdef REQUIRES_VIRT
__asm__(".arch_extension virt");
#endif
+DEFINE_PER_CPU(kvm_cpu_context_t, kvm_host_cpu_state);
static DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page);
-static kvm_cpu_context_t __percpu *kvm_host_cpu_state;
/* Per-CPU variable containing the currently running vcpu. */
static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_arm_running_vcpu);
@@ -357,7 +357,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
}
vcpu->cpu = cpu;
- vcpu->arch.host_cpu_context = this_cpu_ptr(kvm_host_cpu_state);
+ vcpu->arch.host_cpu_context = this_cpu_ptr(&kvm_host_cpu_state);
kvm_arm_set_running_vcpu(vcpu);
kvm_vgic_load(vcpu);
@@ -520,7 +520,7 @@ static void update_vttbr(struct kvm *kvm)
pgd_phys = virt_to_phys(kvm->arch.pgd);
BUG_ON(pgd_phys & ~VTTBR_BADDR_MASK);
vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK(kvm_vmid_bits);
- kvm->arch.vttbr = pgd_phys | vmid;
+ kvm->arch.vttbr = kvm_phys_to_vttbr(pgd_phys) | vmid;
spin_unlock(&kvm_vmid_lock);
}
@@ -741,9 +741,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
*/
trace_kvm_entry(*vcpu_pc(vcpu));
guest_enter_irqoff();
+ if (has_vhe())
+ kvm_arm_vhe_guest_enter();
ret = kvm_call_hyp(__kvm_vcpu_run, vcpu);
+ if (has_vhe())
+ kvm_arm_vhe_guest_exit();
vcpu->mode = OUTSIDE_GUEST_MODE;
vcpu->stat.exits++;
/*
@@ -797,6 +801,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
guest_exit();
trace_kvm_exit(ret, kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
+ /* Exit types that need handling before we can be preempted */
+ handle_exit_early(vcpu, run, ret);
+
preempt_enable();
ret = handle_exit(vcpu, run, ret);
@@ -1220,7 +1227,7 @@ static void cpu_init_hyp_mode(void *dummy)
pgd_ptr = kvm_mmu_get_httbr();
stack_page = __this_cpu_read(kvm_arm_hyp_stack_page);
hyp_stack_ptr = stack_page + PAGE_SIZE;
- vector_ptr = (unsigned long)kvm_ksym_ref(__kvm_hyp_vector);
+ vector_ptr = (unsigned long)kvm_get_hyp_vector();
__cpu_init_hyp_mode(pgd_ptr, hyp_stack_ptr, vector_ptr);
__cpu_init_stage2();
@@ -1335,19 +1342,8 @@ static inline void hyp_cpu_pm_exit(void)
}
#endif
-static void teardown_common_resources(void)
-{
- free_percpu(kvm_host_cpu_state);
-}
-
static int init_common_resources(void)
{
- kvm_host_cpu_state = alloc_percpu(kvm_cpu_context_t);
- if (!kvm_host_cpu_state) {
- kvm_err("Cannot allocate host CPU state\n");
- return -ENOMEM;
- }
-
/* set size of VMID supported by CPU */
kvm_vmid_bits = kvm_get_vmid_bits();
kvm_info("%d-bit VMID\n", kvm_vmid_bits);
@@ -1466,6 +1462,12 @@ static int init_hyp_mode(void)
goto out_err;
}
+ err = kvm_map_vectors();
+ if (err) {
+ kvm_err("Cannot map vectors\n");
+ goto out_err;
+ }
+
/*
* Map the Hyp stack pages
*/
@@ -1483,7 +1485,7 @@ static int init_hyp_mode(void)
for_each_possible_cpu(cpu) {
kvm_cpu_context_t *cpu_ctxt;
- cpu_ctxt = per_cpu_ptr(kvm_host_cpu_state, cpu);
+ cpu_ctxt = per_cpu_ptr(&kvm_host_cpu_state, cpu);
err = create_hyp_mappings(cpu_ctxt, cpu_ctxt + 1, PAGE_HYP);
if (err) {
@@ -1607,7 +1609,6 @@ out_hyp:
if (!in_hyp_mode)
teardown_hyp_mode();
out_err:
- teardown_common_resources();
return err;
}
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index 71dc178ac3bd..ec62d1cccab7 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -621,7 +621,7 @@ static int create_hyp_pud_mappings(pgd_t *pgd, unsigned long start,
return 0;
}
-static int __create_hyp_mappings(pgd_t *pgdp,
+static int __create_hyp_mappings(pgd_t *pgdp, unsigned long ptrs_per_pgd,
unsigned long start, unsigned long end,
unsigned long pfn, pgprot_t prot)
{
@@ -634,7 +634,7 @@ static int __create_hyp_mappings(pgd_t *pgdp,
addr = start & PAGE_MASK;
end = PAGE_ALIGN(end);
do {
- pgd = pgdp + pgd_index(addr);
+ pgd = pgdp + ((addr >> PGDIR_SHIFT) & (ptrs_per_pgd - 1));
if (pgd_none(*pgd)) {
pud = pud_alloc_one(NULL, addr);
@@ -697,8 +697,8 @@ int create_hyp_mappings(void *from, void *to, pgprot_t prot)
int err;
phys_addr = kvm_kaddr_to_phys(from + virt_addr - start);
- err = __create_hyp_mappings(hyp_pgd, virt_addr,
- virt_addr + PAGE_SIZE,
+ err = __create_hyp_mappings(hyp_pgd, PTRS_PER_PGD,
+ virt_addr, virt_addr + PAGE_SIZE,
__phys_to_pfn(phys_addr),
prot);
if (err)
@@ -729,7 +729,7 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr)
if (!is_vmalloc_addr(from) || !is_vmalloc_addr(to - 1))
return -EINVAL;
- return __create_hyp_mappings(hyp_pgd, start, end,
+ return __create_hyp_mappings(hyp_pgd, PTRS_PER_PGD, start, end,
__phys_to_pfn(phys_addr), PAGE_HYP_DEVICE);
}
@@ -1785,7 +1785,7 @@ static int kvm_map_idmap_text(pgd_t *pgd)
int err;
/* Create the idmap in the boot page tables */
- err = __create_hyp_mappings(pgd,
+ err = __create_hyp_mappings(pgd, __kvm_idmap_ptrs_per_pgd(),
hyp_idmap_start, hyp_idmap_end,
__phys_to_pfn(hyp_idmap_start),
PAGE_HYP_EXEC);
diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c
index f1e363bab5e8..6919352cbf15 100644
--- a/virt/kvm/arm/psci.c
+++ b/virt/kvm/arm/psci.c
@@ -15,16 +15,16 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/arm-smccc.h>
#include <linux/preempt.h>
#include <linux/kvm_host.h>
#include <linux/wait.h>
#include <asm/cputype.h>
#include <asm/kvm_emulate.h>
-#include <asm/kvm_psci.h>
#include <asm/kvm_host.h>
-#include <uapi/linux/psci.h>
+#include <kvm/arm_psci.h>
/*
* This is an implementation of the Power State Coordination Interface
@@ -33,6 +33,38 @@
#define AFFINITY_MASK(level) ~((0x1UL << ((level) * MPIDR_LEVEL_BITS)) - 1)
+static u32 smccc_get_function(struct kvm_vcpu *vcpu)
+{
+ return vcpu_get_reg(vcpu, 0);
+}
+
+static unsigned long smccc_get_arg1(struct kvm_vcpu *vcpu)
+{
+ return vcpu_get_reg(vcpu, 1);
+}
+
+static unsigned long smccc_get_arg2(struct kvm_vcpu *vcpu)
+{
+ return vcpu_get_reg(vcpu, 2);
+}
+
+static unsigned long smccc_get_arg3(struct kvm_vcpu *vcpu)
+{
+ return vcpu_get_reg(vcpu, 3);
+}
+
+static void smccc_set_retval(struct kvm_vcpu *vcpu,
+ unsigned long a0,
+ unsigned long a1,
+ unsigned long a2,
+ unsigned long a3)
+{
+ vcpu_set_reg(vcpu, 0, a0);
+ vcpu_set_reg(vcpu, 1, a1);
+ vcpu_set_reg(vcpu, 2, a2);
+ vcpu_set_reg(vcpu, 3, a3);
+}
+
static unsigned long psci_affinity_mask(unsigned long affinity_level)
{
if (affinity_level <= 3)
@@ -78,7 +110,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
unsigned long context_id;
phys_addr_t target_pc;
- cpu_id = vcpu_get_reg(source_vcpu, 1) & MPIDR_HWID_BITMASK;
+ cpu_id = smccc_get_arg1(source_vcpu) & MPIDR_HWID_BITMASK;
if (vcpu_mode_is_32bit(source_vcpu))
cpu_id &= ~((u32) 0);
@@ -91,14 +123,14 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
if (!vcpu)
return PSCI_RET_INVALID_PARAMS;
if (!vcpu->arch.power_off) {
- if (kvm_psci_version(source_vcpu) != KVM_ARM_PSCI_0_1)
+ if (kvm_psci_version(source_vcpu, kvm) != KVM_ARM_PSCI_0_1)
return PSCI_RET_ALREADY_ON;
else
return PSCI_RET_INVALID_PARAMS;
}
- target_pc = vcpu_get_reg(source_vcpu, 2);
- context_id = vcpu_get_reg(source_vcpu, 3);
+ target_pc = smccc_get_arg2(source_vcpu);
+ context_id = smccc_get_arg3(source_vcpu);
kvm_reset_vcpu(vcpu);
@@ -117,7 +149,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
* NOTE: We always update r0 (or x0) because for PSCI v0.1
* the general puspose registers are undefined upon CPU_ON.
*/
- vcpu_set_reg(vcpu, 0, context_id);
+ smccc_set_retval(vcpu, context_id, 0, 0, 0);
vcpu->arch.power_off = false;
smp_mb(); /* Make sure the above is visible */
@@ -137,8 +169,8 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu)
struct kvm *kvm = vcpu->kvm;
struct kvm_vcpu *tmp;
- target_affinity = vcpu_get_reg(vcpu, 1);
- lowest_affinity_level = vcpu_get_reg(vcpu, 2);
+ target_affinity = smccc_get_arg1(vcpu);
+ lowest_affinity_level = smccc_get_arg2(vcpu);
/* Determine target affinity mask */
target_affinity_mask = psci_affinity_mask(lowest_affinity_level);
@@ -200,18 +232,10 @@ static void kvm_psci_system_reset(struct kvm_vcpu *vcpu)
kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET);
}
-int kvm_psci_version(struct kvm_vcpu *vcpu)
-{
- if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features))
- return KVM_ARM_PSCI_0_2;
-
- return KVM_ARM_PSCI_0_1;
-}
-
static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
{
struct kvm *kvm = vcpu->kvm;
- unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0);
+ u32 psci_fn = smccc_get_function(vcpu);
unsigned long val;
int ret = 1;
@@ -221,7 +245,7 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
* Bits[31:16] = Major Version = 0
* Bits[15:0] = Minor Version = 2
*/
- val = 2;
+ val = KVM_ARM_PSCI_0_2;
break;
case PSCI_0_2_FN_CPU_SUSPEND:
case PSCI_0_2_FN64_CPU_SUSPEND:
@@ -278,14 +302,56 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
break;
}
- vcpu_set_reg(vcpu, 0, val);
+ smccc_set_retval(vcpu, val, 0, 0, 0);
+ return ret;
+}
+
+static int kvm_psci_1_0_call(struct kvm_vcpu *vcpu)
+{
+ u32 psci_fn = smccc_get_function(vcpu);
+ u32 feature;
+ unsigned long val;
+ int ret = 1;
+
+ switch(psci_fn) {
+ case PSCI_0_2_FN_PSCI_VERSION:
+ val = KVM_ARM_PSCI_1_0;
+ break;
+ case PSCI_1_0_FN_PSCI_FEATURES:
+ feature = smccc_get_arg1(vcpu);
+ switch(feature) {
+ case PSCI_0_2_FN_PSCI_VERSION:
+ case PSCI_0_2_FN_CPU_SUSPEND:
+ case PSCI_0_2_FN64_CPU_SUSPEND:
+ case PSCI_0_2_FN_CPU_OFF:
+ case PSCI_0_2_FN_CPU_ON:
+ case PSCI_0_2_FN64_CPU_ON:
+ case PSCI_0_2_FN_AFFINITY_INFO:
+ case PSCI_0_2_FN64_AFFINITY_INFO:
+ case PSCI_0_2_FN_MIGRATE_INFO_TYPE:
+ case PSCI_0_2_FN_SYSTEM_OFF:
+ case PSCI_0_2_FN_SYSTEM_RESET:
+ case PSCI_1_0_FN_PSCI_FEATURES:
+ case ARM_SMCCC_VERSION_FUNC_ID:
+ val = 0;
+ break;
+ default:
+ val = PSCI_RET_NOT_SUPPORTED;
+ break;
+ }
+ break;
+ default:
+ return kvm_psci_0_2_call(vcpu);
+ }
+
+ smccc_set_retval(vcpu, val, 0, 0, 0);
return ret;
}
static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
{
struct kvm *kvm = vcpu->kvm;
- unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0);
+ u32 psci_fn = smccc_get_function(vcpu);
unsigned long val;
switch (psci_fn) {
@@ -303,7 +369,7 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
break;
}
- vcpu_set_reg(vcpu, 0, val);
+ smccc_set_retval(vcpu, val, 0, 0, 0);
return 1;
}
@@ -321,9 +387,11 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
* Errors:
* -EINVAL: Unrecognized PSCI function
*/
-int kvm_psci_call(struct kvm_vcpu *vcpu)
+static int kvm_psci_call(struct kvm_vcpu *vcpu)
{
- switch (kvm_psci_version(vcpu)) {
+ switch (kvm_psci_version(vcpu, vcpu->kvm)) {
+ case KVM_ARM_PSCI_1_0:
+ return kvm_psci_1_0_call(vcpu);
case KVM_ARM_PSCI_0_2:
return kvm_psci_0_2_call(vcpu);
case KVM_ARM_PSCI_0_1:
@@ -332,3 +400,30 @@ int kvm_psci_call(struct kvm_vcpu *vcpu)
return -EINVAL;
};
}
+
+int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
+{
+ u32 func_id = smccc_get_function(vcpu);
+ u32 val = PSCI_RET_NOT_SUPPORTED;
+ u32 feature;
+
+ switch (func_id) {
+ case ARM_SMCCC_VERSION_FUNC_ID:
+ val = ARM_SMCCC_VERSION_1_1;
+ break;
+ case ARM_SMCCC_ARCH_FEATURES_FUNC_ID:
+ feature = smccc_get_arg1(vcpu);
+ switch(feature) {
+ case ARM_SMCCC_ARCH_WORKAROUND_1:
+ if (kvm_arm_harden_branch_predictor())
+ val = 0;
+ break;
+ }
+ break;
+ default:
+ return kvm_psci_call(vcpu);
+ }
+
+ smccc_set_retval(vcpu, val, 0, 0, 0);
+ return 1;
+}
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index f2ac53ab8243..a334399fafec 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -188,7 +188,7 @@ irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
{
struct kvm_kernel_irqfd *irqfd =
container_of(wait, struct kvm_kernel_irqfd, wait);
- unsigned long flags = (unsigned long)key;
+ __poll_t flags = key_to_poll(key);
struct kvm_kernel_irq_routing_entry irq;
struct kvm *kvm = irqfd->kvm;
unsigned seq;
@@ -287,7 +287,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
struct fd f;
struct eventfd_ctx *eventfd = NULL, *resamplefd = NULL;
int ret;
- unsigned int events;
+ __poll_t events;
int idx;
if (!kvm_arch_intc_initialized(kvm))
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 8a937b7cde35..4501e658e8d6 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -470,6 +470,7 @@ static void kvm_mmu_notifier_release(struct mmu_notifier *mn,
}
static const struct mmu_notifier_ops kvm_mmu_notifier_ops = {
+ .flags = MMU_INVALIDATE_DOES_NOT_BLOCK,
.invalidate_range_start = kvm_mmu_notifier_invalidate_range_start,
.invalidate_range_end = kvm_mmu_notifier_invalidate_range_end,
.clear_flush_young = kvm_mmu_notifier_clear_flush_young,
@@ -1316,17 +1317,6 @@ unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *w
return gfn_to_hva_memslot_prot(slot, gfn, writable);
}
-static int get_user_page_nowait(unsigned long start, int write,
- struct page **page)
-{
- int flags = FOLL_NOWAIT | FOLL_HWPOISON;
-
- if (write)
- flags |= FOLL_WRITE;
-
- return get_user_pages(start, 1, flags, page, NULL);
-}
-
static inline int check_user_page_hwpoison(unsigned long addr)
{
int rc, flags = FOLL_HWPOISON | FOLL_WRITE;
@@ -1375,7 +1365,8 @@ static bool hva_to_pfn_fast(unsigned long addr, bool atomic, bool *async,
static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,
bool *writable, kvm_pfn_t *pfn)
{
- struct page *page[1];
+ unsigned int flags = FOLL_HWPOISON;
+ struct page *page;
int npages = 0;
might_sleep();
@@ -1383,35 +1374,26 @@ static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,
if (writable)
*writable = write_fault;
- if (async) {
- down_read(&current->mm->mmap_sem);
- npages = get_user_page_nowait(addr, write_fault, page);
- up_read(&current->mm->mmap_sem);
- } else {
- unsigned int flags = FOLL_HWPOISON;
-
- if (write_fault)
- flags |= FOLL_WRITE;
+ if (write_fault)
+ flags |= FOLL_WRITE;
+ if (async)
+ flags |= FOLL_NOWAIT;
- npages = get_user_pages_unlocked(addr, 1, page, flags);
- }
+ npages = get_user_pages_unlocked(addr, 1, &page, flags);
if (npages != 1)
return npages;
/* map read fault as writable if possible */
if (unlikely(!write_fault) && writable) {
- struct page *wpage[1];
+ struct page *wpage;
- npages = __get_user_pages_fast(addr, 1, 1, wpage);
- if (npages == 1) {
+ if (__get_user_pages_fast(addr, 1, 1, &wpage) == 1) {
*writable = true;
- put_page(page[0]);
- page[0] = wpage[0];
+ put_page(page);
+ page = wpage;
}
-
- npages = 1;
}
- *pfn = page_to_pfn(page[0]);
+ *pfn = page_to_pfn(page);
return npages;
}
@@ -4035,8 +4017,12 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
/* A kmem cache lets us meet the alignment requirements of fx_save. */
if (!vcpu_align)
vcpu_align = __alignof__(struct kvm_vcpu);
- kvm_vcpu_cache = kmem_cache_create("kvm_vcpu", vcpu_size, vcpu_align,
- SLAB_ACCOUNT, NULL);
+ kvm_vcpu_cache =
+ kmem_cache_create_usercopy("kvm_vcpu", vcpu_size, vcpu_align,
+ SLAB_ACCOUNT,
+ offsetof(struct kvm_vcpu, arch),
+ sizeof_field(struct kvm_vcpu, arch),
+ NULL);
if (!kvm_vcpu_cache) {
r = -ENOMEM;
goto out_free_3;