unsigned int cr4_smap:1;
unsigned int cr4_smep:1;
unsigned int cr4_la57:1;
+ unsigned int efer_lma:1;
};
};
*
* Note that while the PKRU state lives inside the fpu registers,
* it is switched out separately at VMENTER and VMEXIT time. The
- * "guest_fpu" state here contains the guest FPU context, with the
+ * "guest_fpstate" state here contains the guest FPU context, with the
* host PRKU bits.
*/
- struct fpu *user_fpu;
- struct fpu *guest_fpu;
+ struct fpu_guest guest_fpu;
u64 xcr0;
u64 guest_supported_xcr0;
struct kvm_pio_request pio;
void *pio_data;
- void *guest_ins_data;
+ void *sev_pio_data;
+ unsigned sev_pio_count;
u8 event_exit_inst_len;
int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
int (*vm_copy_enc_context_from)(struct kvm *kvm, unsigned int source_fd);
+ int (*vm_move_enc_context_from)(struct kvm *kvm, unsigned int source_fd);
int (*get_msr_feature)(struct kvm_msr_entry *entry);
int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index,
int reason, bool has_error_code, u32 error_code);
-void kvm_free_guest_fpu(struct kvm_vcpu *vcpu);
-
void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned long cr0);
void kvm_post_set_cr4(struct kvm_vcpu *vcpu, unsigned long old_cr4, unsigned long cr4);
int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
unsigned bit;
bool wp;
- if (!is_cr4_pke(mmu)) {
- mmu->pkru_mask = 0;
+ mmu->pkru_mask = 0;
+
+ if (!is_cr4_pke(mmu))
return;
- }
wp = is_cr0_wp(mmu);
/* PKEY and LA57 are active iff long mode is active. */
ext.cr4_pke = ____is_efer_lma(regs) && ____is_cr4_pke(regs);
ext.cr4_la57 = ____is_efer_lma(regs) && ____is_cr4_la57(regs);
+ ext.efer_lma = ____is_efer_lma(regs);
}
ext.valid = 1;
#include <linux/misc_cgroup.h>
#include <linux/processor.h>
#include <linux/trace_events.h>
-#include <asm/fpu/internal.h>
#include <asm/pkru.h>
#include <asm/trapnr.h>
+#include <asm/fpu/xcr.h>
#include "x86.h"
#include "svm.h"
return true;
}
+static int sev_misc_cg_try_charge(struct kvm_sev_info *sev)
+{
+ enum misc_res_type type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV;
+ return misc_cg_try_charge(type, sev->misc_cg, 1);
+}
+
+static void sev_misc_cg_uncharge(struct kvm_sev_info *sev)
+{
+ enum misc_res_type type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV;
+ misc_cg_uncharge(type, sev->misc_cg, 1);
+}
+
static int sev_asid_new(struct kvm_sev_info *sev)
{
int asid, min_asid, max_asid, ret;
bool retry = true;
- enum misc_res_type type;
- type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV;
WARN_ON(sev->misc_cg);
sev->misc_cg = get_current_misc_cg();
- ret = misc_cg_try_charge(type, sev->misc_cg, 1);
+ ret = sev_misc_cg_try_charge(sev);
if (ret) {
put_misc_cg(sev->misc_cg);
sev->misc_cg = NULL;
return asid;
e_uncharge:
- misc_cg_uncharge(type, sev->misc_cg, 1);
+ sev_misc_cg_uncharge(sev);
put_misc_cg(sev->misc_cg);
sev->misc_cg = NULL;
return ret;
{
struct svm_cpu_data *sd;
int cpu;
- enum misc_res_type type;
mutex_lock(&sev_bitmap_lock);
mutex_unlock(&sev_bitmap_lock);
- type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV;
- misc_cg_uncharge(type, sev->misc_cg, 1);
+ sev_misc_cg_uncharge(sev);
put_misc_cg(sev->misc_cg);
sev->misc_cg = NULL;
}
static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
- bool es_active = argp->id == KVM_SEV_ES_INIT;
int asid, ret;
if (kvm->created_vcpus)
if (unlikely(sev->active))
return ret;
- sev->es_active = es_active;
+ sev->active = true;
+ sev->es_active = argp->id == KVM_SEV_ES_INIT;
asid = sev_asid_new(sev);
if (asid < 0)
goto e_no_asid;
if (ret)
goto e_free;
- sev->active = true;
- sev->asid = asid;
INIT_LIST_HEAD(&sev->regions_list);
return 0;
sev->asid = 0;
e_no_asid:
sev->es_active = false;
+ sev->active = false;
return ret;
}
* traditional VMSA as it has been built so far (in prep
* for LAUNCH_UPDATE_VMSA) to be the initial SEV-ES state.
*/
- memcpy(svm->vmsa, save, sizeof(*save));
+ memcpy(svm->sev_es.vmsa, save, sizeof(*save));
return 0;
}
* the VMSA memory content (i.e it will write the same memory region
* with the guest's key), so invalidate it first.
*/
- clflush_cache_range(svm->vmsa, PAGE_SIZE);
+ clflush_cache_range(svm->sev_es.vmsa, PAGE_SIZE);
vmsa.reserved = 0;
vmsa.handle = to_kvm_svm(kvm)->sev_info.handle;
- vmsa.address = __sme_pa(svm->vmsa);
+ vmsa.address = __sme_pa(svm->sev_es.vmsa);
vmsa.len = PAGE_SIZE;
- return sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error);
+ ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error);
+ if (ret)
+ return ret;
+
+ vcpu->arch.guest_state_protected = true;
+ return 0;
}
static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp)
goto e_free_trans;
}
+ /*
+ * Flush (on non-coherent CPUs) before RECEIVE_UPDATE_DATA, the PSP
+ * encrypts the written data with the guest's key, and the cache may
+ * contain dirty, unencrypted data.
+ */
+ sev_clflush_pages(guest_page, n);
+
/* The RECEIVE_UPDATE_DATA command requires C-bit to be always set. */
data.guest_address = (page_to_pfn(guest_page[0]) << PAGE_SHIFT) + offset;
data.guest_address |= sev_me_mask;
return sev_issue_cmd(kvm, SEV_CMD_RECEIVE_FINISH, &data, &argp->error);
}
- static bool cmd_allowed_from_miror(u32 cmd_id)
+ static bool is_cmd_allowed_from_mirror(u32 cmd_id)
{
/*
* Allow mirrors VM to call KVM_SEV_LAUNCH_UPDATE_VMSA to enable SEV-ES
return false;
}
+static int sev_lock_for_migration(struct kvm *kvm)
+{
+ struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+
+ /*
+ * Bail if this VM is already involved in a migration to avoid deadlock
+ * between two VMs trying to migrate to/from each other.
+ */
+ if (atomic_cmpxchg_acquire(&sev->migration_in_progress, 0, 1))
+ return -EBUSY;
+
+ mutex_lock(&kvm->lock);
+
+ return 0;
+}
+
+static void sev_unlock_after_migration(struct kvm *kvm)
+{
+ struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+
+ mutex_unlock(&kvm->lock);
+ atomic_set_release(&sev->migration_in_progress, 0);
+}
+
+
+static int sev_lock_vcpus_for_migration(struct kvm *kvm)
+{
+ struct kvm_vcpu *vcpu;
+ int i, j;
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (mutex_lock_killable(&vcpu->mutex))
+ goto out_unlock;
+ }
+
+ return 0;
+
+out_unlock:
+ kvm_for_each_vcpu(j, vcpu, kvm) {
+ if (i == j)
+ break;
+
+ mutex_unlock(&vcpu->mutex);
+ }
+ return -EINTR;
+}
+
+static void sev_unlock_vcpus_for_migration(struct kvm *kvm)
+{
+ struct kvm_vcpu *vcpu;
+ int i;
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ mutex_unlock(&vcpu->mutex);
+ }
+}
+
+static void sev_migrate_from(struct kvm_sev_info *dst,
+ struct kvm_sev_info *src)
+{
+ dst->active = true;
+ dst->asid = src->asid;
+ dst->handle = src->handle;
+ dst->pages_locked = src->pages_locked;
+
+ src->asid = 0;
+ src->active = false;
+ src->handle = 0;
+ src->pages_locked = 0;
+
+ INIT_LIST_HEAD(&dst->regions_list);
+ list_replace_init(&src->regions_list, &dst->regions_list);
+}
+
+static int sev_es_migrate_from(struct kvm *dst, struct kvm *src)
+{
+ int i;
+ struct kvm_vcpu *dst_vcpu, *src_vcpu;
+ struct vcpu_svm *dst_svm, *src_svm;
+
+ if (atomic_read(&src->online_vcpus) != atomic_read(&dst->online_vcpus))
+ return -EINVAL;
+
+ kvm_for_each_vcpu(i, src_vcpu, src) {
+ if (!src_vcpu->arch.guest_state_protected)
+ return -EINVAL;
+ }
+
+ kvm_for_each_vcpu(i, src_vcpu, src) {
+ src_svm = to_svm(src_vcpu);
+ dst_vcpu = kvm_get_vcpu(dst, i);
+ dst_svm = to_svm(dst_vcpu);
+
+ /*
+ * Transfer VMSA and GHCB state to the destination. Nullify and
+ * clear source fields as appropriate, the state now belongs to
+ * the destination.
+ */
+ memcpy(&dst_svm->sev_es, &src_svm->sev_es, sizeof(src_svm->sev_es));
+ dst_svm->vmcb->control.ghcb_gpa = src_svm->vmcb->control.ghcb_gpa;
+ dst_svm->vmcb->control.vmsa_pa = src_svm->vmcb->control.vmsa_pa;
+ dst_vcpu->arch.guest_state_protected = true;
+
+ memset(&src_svm->sev_es, 0, sizeof(src_svm->sev_es));
+ src_svm->vmcb->control.ghcb_gpa = INVALID_PAGE;
+ src_svm->vmcb->control.vmsa_pa = INVALID_PAGE;
+ src_vcpu->arch.guest_state_protected = false;
+ }
+ to_kvm_svm(src)->sev_info.es_active = false;
+ to_kvm_svm(dst)->sev_info.es_active = true;
+
+ return 0;
+}
+
+int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd)
+{
+ struct kvm_sev_info *dst_sev = &to_kvm_svm(kvm)->sev_info;
+ struct kvm_sev_info *src_sev, *cg_cleanup_sev;
+ struct file *source_kvm_file;
+ struct kvm *source_kvm;
+ bool charged = false;
+ int ret;
+
+ ret = sev_lock_for_migration(kvm);
+ if (ret)
+ return ret;
+
+ if (sev_guest(kvm)) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
+
+ source_kvm_file = fget(source_fd);
+ if (!file_is_kvm(source_kvm_file)) {
+ ret = -EBADF;
+ goto out_fput;
+ }
+
+ source_kvm = source_kvm_file->private_data;
+ ret = sev_lock_for_migration(source_kvm);
+ if (ret)
+ goto out_fput;
+
+ if (!sev_guest(source_kvm)) {
+ ret = -EINVAL;
+ goto out_source;
+ }
+
+ src_sev = &to_kvm_svm(source_kvm)->sev_info;
+ dst_sev->misc_cg = get_current_misc_cg();
+ cg_cleanup_sev = dst_sev;
+ if (dst_sev->misc_cg != src_sev->misc_cg) {
+ ret = sev_misc_cg_try_charge(dst_sev);
+ if (ret)
+ goto out_dst_cgroup;
+ charged = true;
+ }
+
+ ret = sev_lock_vcpus_for_migration(kvm);
+ if (ret)
+ goto out_dst_cgroup;
+ ret = sev_lock_vcpus_for_migration(source_kvm);
+ if (ret)
+ goto out_dst_vcpu;
+
+ if (sev_es_guest(source_kvm)) {
+ ret = sev_es_migrate_from(kvm, source_kvm);
+ if (ret)
+ goto out_source_vcpu;
+ }
+ sev_migrate_from(dst_sev, src_sev);
+ kvm_vm_dead(source_kvm);
+ cg_cleanup_sev = src_sev;
+ ret = 0;
+
+out_source_vcpu:
+ sev_unlock_vcpus_for_migration(source_kvm);
+out_dst_vcpu:
+ sev_unlock_vcpus_for_migration(kvm);
+out_dst_cgroup:
+ /* Operates on the source on success, on the destination on failure. */
+ if (charged)
+ sev_misc_cg_uncharge(cg_cleanup_sev);
+ put_misc_cg(cg_cleanup_sev->misc_cg);
+ cg_cleanup_sev->misc_cg = NULL;
+out_source:
+ sev_unlock_after_migration(source_kvm);
+out_fput:
+ if (source_kvm_file)
+ fput(source_kvm_file);
+out_unlock:
+ sev_unlock_after_migration(kvm);
+ return ret;
+}
+
int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
{
struct kvm_sev_cmd sev_cmd;
/* Only the enc_context_owner handles some memory enc operations. */
if (is_mirroring_enc_context(kvm) &&
- !cmd_allowed_from_miror(sev_cmd.id)) {
+ !is_cmd_allowed_from_mirror(sev_cmd.id)) {
r = -EINVAL;
goto out;
}
mutex_unlock(&source_kvm->lock);
mutex_lock(&kvm->lock);
- if (sev_guest(kvm)) {
+ /*
+ * Disallow out-of-band SEV/SEV-ES init if the target is already an
+ * SEV guest, or if vCPUs have been created. KVM relies on vCPUs being
+ * created after SEV/SEV-ES initialization, e.g. to init intercepts.
+ */
+ if (sev_guest(kvm) || kvm->created_vcpus) {
ret = -EINVAL;
goto e_mirror_unlock;
}
svm = to_svm(vcpu);
if (vcpu->arch.guest_state_protected)
- sev_flush_guest_memory(svm, svm->vmsa, PAGE_SIZE);
- __free_page(virt_to_page(svm->vmsa));
+ sev_flush_guest_memory(svm, svm->sev_es.vmsa, PAGE_SIZE);
+ __free_page(virt_to_page(svm->sev_es.vmsa));
- if (svm->ghcb_sa_free)
- kfree(svm->ghcb_sa);
+ if (svm->sev_es.ghcb_sa_free)
+ kfree(svm->sev_es.ghcb_sa);
}
static void dump_ghcb(struct vcpu_svm *svm)
{
- struct ghcb *ghcb = svm->ghcb;
+ struct ghcb *ghcb = svm->sev_es.ghcb;
unsigned int nbits;
/* Re-use the dump_invalid_vmcb module parameter */
static void sev_es_sync_to_ghcb(struct vcpu_svm *svm)
{
struct kvm_vcpu *vcpu = &svm->vcpu;
- struct ghcb *ghcb = svm->ghcb;
+ struct ghcb *ghcb = svm->sev_es.ghcb;
/*
* The GHCB protocol so far allows for the following data
{
struct vmcb_control_area *control = &svm->vmcb->control;
struct kvm_vcpu *vcpu = &svm->vcpu;
- struct ghcb *ghcb = svm->ghcb;
+ struct ghcb *ghcb = svm->sev_es.ghcb;
u64 exit_code;
/*
struct ghcb *ghcb;
u64 exit_code = 0;
- ghcb = svm->ghcb;
+ ghcb = svm->sev_es.ghcb;
/* Only GHCB Usage code 0 is supported */
if (ghcb->ghcb_usage)
void sev_es_unmap_ghcb(struct vcpu_svm *svm)
{
- if (!svm->ghcb)
+ if (!svm->sev_es.ghcb)
return;
- if (svm->ghcb_sa_free) {
+ if (svm->sev_es.ghcb_sa_free) {
/*
* The scratch area lives outside the GHCB, so there is a
* buffer that, depending on the operation performed, may
* need to be synced, then freed.
*/
- if (svm->ghcb_sa_sync) {
+ if (svm->sev_es.ghcb_sa_sync) {
kvm_write_guest(svm->vcpu.kvm,
- ghcb_get_sw_scratch(svm->ghcb),
- svm->ghcb_sa, svm->ghcb_sa_len);
- svm->ghcb_sa_sync = false;
+ ghcb_get_sw_scratch(svm->sev_es.ghcb),
+ svm->sev_es.ghcb_sa,
+ svm->sev_es.ghcb_sa_len);
+ svm->sev_es.ghcb_sa_sync = false;
}
- kfree(svm->ghcb_sa);
- svm->ghcb_sa = NULL;
- svm->ghcb_sa_free = false;
+ kfree(svm->sev_es.ghcb_sa);
+ svm->sev_es.ghcb_sa = NULL;
+ svm->sev_es.ghcb_sa_free = false;
}
- trace_kvm_vmgexit_exit(svm->vcpu.vcpu_id, svm->ghcb);
+ trace_kvm_vmgexit_exit(svm->vcpu.vcpu_id, svm->sev_es.ghcb);
sev_es_sync_to_ghcb(svm);
- kvm_vcpu_unmap(&svm->vcpu, &svm->ghcb_map, true);
- svm->ghcb = NULL;
+ kvm_vcpu_unmap(&svm->vcpu, &svm->sev_es.ghcb_map, true);
+ svm->sev_es.ghcb = NULL;
}
void pre_sev_run(struct vcpu_svm *svm, int cpu)
static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
{
struct vmcb_control_area *control = &svm->vmcb->control;
- struct ghcb *ghcb = svm->ghcb;
+ struct ghcb *ghcb = svm->sev_es.ghcb;
u64 ghcb_scratch_beg, ghcb_scratch_end;
u64 scratch_gpa_beg, scratch_gpa_end;
void *scratch_va;
return false;
}
- scratch_va = (void *)svm->ghcb;
+ scratch_va = (void *)svm->sev_es.ghcb;
scratch_va += (scratch_gpa_beg - control->ghcb_gpa);
} else {
/*
* the vCPU next time (i.e. a read was requested so the data
* must be written back to the guest memory).
*/
- svm->ghcb_sa_sync = sync;
- svm->ghcb_sa_free = true;
+ svm->sev_es.ghcb_sa_sync = sync;
+ svm->sev_es.ghcb_sa_free = true;
}
- svm->ghcb_sa = scratch_va;
- svm->ghcb_sa_len = len;
+ svm->sev_es.ghcb_sa = scratch_va;
+ svm->sev_es.ghcb_sa_len = len;
return true;
}
return -EINVAL;
}
- if (kvm_vcpu_map(vcpu, ghcb_gpa >> PAGE_SHIFT, &svm->ghcb_map)) {
+ if (kvm_vcpu_map(vcpu, ghcb_gpa >> PAGE_SHIFT, &svm->sev_es.ghcb_map)) {
/* Unable to map GHCB from guest */
vcpu_unimpl(vcpu, "vmgexit: error mapping GHCB [%#llx] from guest\n",
ghcb_gpa);
return -EINVAL;
}
- svm->ghcb = svm->ghcb_map.hva;
- ghcb = svm->ghcb_map.hva;
+ svm->sev_es.ghcb = svm->sev_es.ghcb_map.hva;
+ ghcb = svm->sev_es.ghcb_map.hva;
trace_kvm_vmgexit_enter(vcpu->vcpu_id, ghcb);
ret = kvm_sev_es_mmio_read(vcpu,
control->exit_info_1,
control->exit_info_2,
- svm->ghcb_sa);
+ svm->sev_es.ghcb_sa);
break;
case SVM_VMGEXIT_MMIO_WRITE:
if (!setup_vmgexit_scratch(svm, false, control->exit_info_2))
ret = kvm_sev_es_mmio_write(vcpu,
control->exit_info_1,
control->exit_info_2,
- svm->ghcb_sa);
+ svm->sev_es.ghcb_sa);
break;
case SVM_VMGEXIT_NMI_COMPLETE:
ret = svm_invoke_exit_handler(vcpu, SVM_EXIT_IRET);
int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in)
{
- if (!setup_vmgexit_scratch(svm, in, svm->vmcb->control.exit_info_2))
+ int count;
+ int bytes;
+
+ if (svm->vmcb->control.exit_info_2 > INT_MAX)
+ return -EINVAL;
+
+ count = svm->vmcb->control.exit_info_2;
+ if (unlikely(check_mul_overflow(count, size, &bytes)))
+ return -EINVAL;
+
+ if (!setup_vmgexit_scratch(svm, in, bytes))
return -EINVAL;
- return kvm_sev_es_string_io(&svm->vcpu, size, port,
- svm->ghcb_sa, svm->ghcb_sa_len / size, in);
+ return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->sev_es.ghcb_sa,
+ count, in);
}
void sev_es_init_vmcb(struct vcpu_svm *svm)
* VMCB page. Do not include the encryption mask on the VMSA physical
* address since hardware will access it using the guest key.
*/
- svm->vmcb->control.vmsa_pa = __pa(svm->vmsa);
+ svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
/* Can't intercept CR register access, HV can't modify CR registers */
svm_clr_intercept(svm, INTERCEPT_CR0_READ);
struct vcpu_svm *svm = to_svm(vcpu);
/* First SIPI: Use the values as initially set by the VMM */
- if (!svm->received_first_sipi) {
- svm->received_first_sipi = true;
+ if (!svm->sev_es.received_first_sipi) {
+ svm->sev_es.received_first_sipi = true;
return;
}
* the guest will set the CS and RIP. Set SW_EXIT_INFO_2 to a
* non-zero value.
*/
- if (!svm->ghcb)
+ if (!svm->sev_es.ghcb)
return;
- ghcb_set_sw_exit_info_2(svm->ghcb, 1);
+ ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 1);
}
u64 ap_jump_table; /* SEV-ES AP Jump Table address */
struct kvm *enc_context_owner; /* Owner of copied encryption context */
struct misc_cg *misc_cg; /* For misc cgroup accounting */
+ atomic_t migration_in_progress;
};
struct kvm_svm {
bool initialized;
};
+struct vcpu_sev_es_state {
+ /* SEV-ES support */
+ struct vmcb_save_area *vmsa;
+ struct ghcb *ghcb;
+ struct kvm_host_map ghcb_map;
+ bool received_first_sipi;
+
+ /* SEV-ES scratch area support */
+ void *ghcb_sa;
+ u32 ghcb_sa_len;
+ bool ghcb_sa_sync;
+ bool ghcb_sa_free;
+};
+
struct vcpu_svm {
struct kvm_vcpu vcpu;
/* vmcb always points at current_vmcb->ptr, it's purely a shorthand. */
DECLARE_BITMAP(write, MAX_DIRECT_ACCESS_MSRS);
} shadow_msr_intercept;
- /* SEV-ES support */
- struct vmcb_save_area *vmsa;
- struct ghcb *ghcb;
- struct kvm_host_map ghcb_map;
- bool received_first_sipi;
-
- /* SEV-ES scratch area support */
- void *ghcb_sa;
- u64 ghcb_sa_len;
- bool ghcb_sa_sync;
- bool ghcb_sa_free;
+ struct vcpu_sev_es_state sev_es;
bool guest_state_loaded;
};
void recalc_intercepts(struct vcpu_svm *svm);
-static inline struct kvm_svm *to_kvm_svm(struct kvm *kvm)
+static __always_inline struct kvm_svm *to_kvm_svm(struct kvm *kvm)
{
return container_of(kvm, struct kvm_svm, kvm);
}
-static inline bool sev_guest(struct kvm *kvm)
+static __always_inline bool sev_guest(struct kvm *kvm)
{
#ifdef CONFIG_KVM_AMD_SEV
struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
#endif
}
-static inline bool sev_es_guest(struct kvm *kvm)
+static __always_inline bool sev_es_guest(struct kvm *kvm)
{
#ifdef CONFIG_KVM_AMD_SEV
struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
- return sev_guest(kvm) && sev->es_active;
+ return sev->es_active && !WARN_ON_ONCE(!sev->active);
#else
return false;
#endif
return !test_bit(bit, (unsigned long *)&vmcb->control.clean);
}
-static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu)
+static __always_inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu)
{
return container_of(vcpu, struct vcpu_svm, vcpu);
}
int svm_unregister_enc_region(struct kvm *kvm,
struct kvm_enc_region *range);
int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd);
+int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd);
void pre_sev_run(struct vcpu_svm *svm, int cpu);
void __init sev_set_cpu_caps(void);
void __init sev_hardware_setup(void);
#include <asm/mce.h>
#include <asm/pkru.h>
#include <linux/kernel_stat.h>
-#include <asm/fpu/internal.h> /* Ugh! */
+#include <asm/fpu/api.h>
+#include <asm/fpu/xcr.h>
+#include <asm/fpu/xstate.h>
#include <asm/pvclock.h>
#include <asm/div64.h>
#include <asm/irq_remapping.h>
u64 __read_mostly supported_xcr0;
EXPORT_SYMBOL_GPL(supported_xcr0);
-static struct kmem_cache *x86_fpu_cache;
-
static struct kmem_cache *x86_emulator_cache;
/*
}
st = (struct kvm_steal_time __user *)ghc->hva;
- if (!user_access_begin(st, sizeof(*st)))
- return;
-
/*
* Doing a TLB flush here, on the guest's behalf, can avoid
* expensive IPIs.
u8 st_preempted = 0;
int err = -EFAULT;
+ if (!user_access_begin(st, sizeof(*st)))
+ return;
+
asm volatile("1: xchgb %0, %2\n"
"xor %1, %1\n"
"2:\n"
_ASM_EXTABLE_UA(1b, 2b)
- : "+r" (st_preempted),
- "+&r" (err)
- : "m" (st->preempted));
+ : "+q" (st_preempted),
+ "+&r" (err),
+ "+m" (st->preempted));
if (err)
goto out;
if (!user_access_begin(st, sizeof(*st)))
goto dirty;
} else {
+ if (!user_access_begin(st, sizeof(*st)))
+ return;
+
unsafe_put_user(0, &st->preempted, out);
vcpu->arch.st.preempted = 0;
}
return 0;
}
-#define XSTATE_COMPACTION_ENABLED (1ULL << 63)
-
-static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
-{
- struct xregs_state *xsave = &vcpu->arch.guest_fpu->state.xsave;
- u64 xstate_bv = xsave->header.xfeatures;
- u64 valid;
-
- /*
- * Copy legacy XSAVE area, to avoid complications with CPUID
- * leaves 0 and 1 in the loop below.
- */
- memcpy(dest, xsave, XSAVE_HDR_OFFSET);
-
- /* Set XSTATE_BV */
- xstate_bv &= vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE;
- *(u64 *)(dest + XSAVE_HDR_OFFSET) = xstate_bv;
-
- /*
- * Copy each region from the possibly compacted offset to the
- * non-compacted offset.
- */
- valid = xstate_bv & ~XFEATURE_MASK_FPSSE;
- while (valid) {
- u32 size, offset, ecx, edx;
- u64 xfeature_mask = valid & -valid;
- int xfeature_nr = fls64(xfeature_mask) - 1;
- void *src;
-
- cpuid_count(XSTATE_CPUID, xfeature_nr,
- &size, &offset, &ecx, &edx);
-
- if (xfeature_nr == XFEATURE_PKRU) {
- memcpy(dest + offset, &vcpu->arch.pkru,
- sizeof(vcpu->arch.pkru));
- } else {
- src = get_xsave_addr(xsave, xfeature_nr);
- if (src)
- memcpy(dest + offset, src, size);
- }
-
- valid -= xfeature_mask;
- }
-}
-
-static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
-{
- struct xregs_state *xsave = &vcpu->arch.guest_fpu->state.xsave;
- u64 xstate_bv = *(u64 *)(src + XSAVE_HDR_OFFSET);
- u64 valid;
-
- /*
- * Copy legacy XSAVE area, to avoid complications with CPUID
- * leaves 0 and 1 in the loop below.
- */
- memcpy(xsave, src, XSAVE_HDR_OFFSET);
-
- /* Set XSTATE_BV and possibly XCOMP_BV. */
- xsave->header.xfeatures = xstate_bv;
- if (boot_cpu_has(X86_FEATURE_XSAVES))
- xsave->header.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED;
-
- /*
- * Copy each region from the non-compacted offset to the
- * possibly compacted offset.
- */
- valid = xstate_bv & ~XFEATURE_MASK_FPSSE;
- while (valid) {
- u32 size, offset, ecx, edx;
- u64 xfeature_mask = valid & -valid;
- int xfeature_nr = fls64(xfeature_mask) - 1;
-
- cpuid_count(XSTATE_CPUID, xfeature_nr,
- &size, &offset, &ecx, &edx);
-
- if (xfeature_nr == XFEATURE_PKRU) {
- memcpy(&vcpu->arch.pkru, src + offset,
- sizeof(vcpu->arch.pkru));
- } else {
- void *dest = get_xsave_addr(xsave, xfeature_nr);
-
- if (dest)
- memcpy(dest, src + offset, size);
- }
-
- valid -= xfeature_mask;
- }
-}
-
static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
struct kvm_xsave *guest_xsave)
{
- if (!vcpu->arch.guest_fpu)
+ if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
return;
- if (boot_cpu_has(X86_FEATURE_XSAVE)) {
- memset(guest_xsave, 0, sizeof(struct kvm_xsave));
- fill_xsave((u8 *) guest_xsave->region, vcpu);
- } else {
- memcpy(guest_xsave->region,
- &vcpu->arch.guest_fpu->state.fxsave,
- sizeof(struct fxregs_state));
- *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] =
- XFEATURE_MASK_FPSSE;
- }
+ fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu,
+ guest_xsave->region,
+ sizeof(guest_xsave->region),
+ vcpu->arch.pkru);
}
-#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;
- u32 mxcsr;
-
- if (!vcpu->arch.guest_fpu)
+ if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
return 0;
- xstate_bv = *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)];
- mxcsr = *(u32 *)&guest_xsave->region[XSAVE_MXCSR_OFFSET / sizeof(u32)];
-
- if (boot_cpu_has(X86_FEATURE_XSAVE)) {
- /*
- * Here we allow setting states that are not present in
- * CPUID leaf 0xD, index 0, EDX:EAX. This is for compatibility
- * with old userspace.
- */
- if (xstate_bv & ~supported_xcr0 || mxcsr & ~mxcsr_feature_mask)
- return -EINVAL;
- load_xsave(vcpu, (u8 *)guest_xsave->region);
- } else {
- 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));
- }
- return 0;
+ return fpu_copy_uabi_to_guest_fpstate(&vcpu->arch.guest_fpu,
+ guest_xsave->region,
+ supported_xcr0, &vcpu->arch.pkru);
}
static void kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu,
if (kvm_x86_ops.vm_copy_enc_context_from)
r = kvm_x86_ops.vm_copy_enc_context_from(kvm, cap->args[0]);
return r;
+ case KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM:
+ r = -EINVAL;
+ if (kvm_x86_ops.vm_move_enc_context_from)
+ r = kvm_x86_ops.vm_move_enc_context_from(
+ kvm, cap->args[0]);
+ return r;
case KVM_CAP_EXIT_HYPERCALL:
if (cap->args[0] & ~KVM_EXIT_HYPERCALL_VALID_MASK) {
r = -EINVAL;
}
static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size,
- unsigned short port, void *val,
+ unsigned short port,
unsigned int count, bool in)
{
vcpu->arch.pio.port = port;
vcpu->arch.pio.count = count;
vcpu->arch.pio.size = size;
- if (!kernel_pio(vcpu, vcpu->arch.pio_data)) {
- vcpu->arch.pio.count = 0;
+ if (!kernel_pio(vcpu, vcpu->arch.pio_data))
return 1;
- }
vcpu->run->exit_reason = KVM_EXIT_IO;
vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT;
return 0;
}
-static int emulator_pio_in(struct kvm_vcpu *vcpu, int size,
- unsigned short port, void *val, unsigned int count)
+static int __emulator_pio_in(struct kvm_vcpu *vcpu, int size,
+ unsigned short port, unsigned int count)
{
- int ret;
+ WARN_ON(vcpu->arch.pio.count);
+ memset(vcpu->arch.pio_data, 0, size * count);
+ return emulator_pio_in_out(vcpu, size, port, count, true);
+}
- if (vcpu->arch.pio.count)
- goto data_avail;
+static void complete_emulator_pio_in(struct kvm_vcpu *vcpu, void *val)
+{
+ int size = vcpu->arch.pio.size;
+ unsigned count = vcpu->arch.pio.count;
+ memcpy(val, vcpu->arch.pio_data, size * count);
+ trace_kvm_pio(KVM_PIO_IN, vcpu->arch.pio.port, size, count, vcpu->arch.pio_data);
+ vcpu->arch.pio.count = 0;
+}
- memset(vcpu->arch.pio_data, 0, size * count);
+static int emulator_pio_in(struct kvm_vcpu *vcpu, int size,
+ unsigned short port, void *val, unsigned int count)
+{
+ if (vcpu->arch.pio.count) {
+ /* Complete previous iteration. */
+ } else {
+ int r = __emulator_pio_in(vcpu, size, port, count);
+ if (!r)
+ return r;
- ret = emulator_pio_in_out(vcpu, size, port, val, count, true);
- if (ret) {
-data_avail:
- memcpy(val, vcpu->arch.pio_data, size * count);
- trace_kvm_pio(KVM_PIO_IN, port, size, count, vcpu->arch.pio_data);
- vcpu->arch.pio.count = 0;
- return 1;
+ /* Results already available, fall through. */
}
- return 0;
+ WARN_ON(count != vcpu->arch.pio.count);
+ complete_emulator_pio_in(vcpu, val);
+ return 1;
}
static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt,
unsigned short port, const void *val,
unsigned int count)
{
+ int ret;
+
memcpy(vcpu->arch.pio_data, val, size * count);
trace_kvm_pio(KVM_PIO_OUT, port, size, count, vcpu->arch.pio_data);
- return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false);
+ ret = emulator_pio_in_out(vcpu, size, port, count, false);
+ if (ret)
+ vcpu->arch.pio.count = 0;
+
+ return ret;
}
static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt,
}
r = -ENOMEM;
- x86_fpu_cache = kmem_cache_create("x86_fpu", sizeof(struct fpu),
- __alignof__(struct fpu), SLAB_ACCOUNT,
- NULL);
- if (!x86_fpu_cache) {
- printk(KERN_ERR "kvm: failed to allocate cache for x86 fpu\n");
- goto out;
- }
x86_emulator_cache = kvm_alloc_emulator_cache();
if (!x86_emulator_cache) {
pr_err("kvm: failed to allocate cache for x86 emulator\n");
- goto out_free_x86_fpu_cache;
+ goto out;
}
user_return_msrs = alloc_percpu(struct kvm_user_return_msrs);
free_percpu(user_return_msrs);
out_free_x86_emulator_cache:
kmem_cache_destroy(x86_emulator_cache);
-out_free_x86_fpu_cache:
- kmem_cache_destroy(x86_fpu_cache);
out:
return r;
}
kvm_mmu_module_exit();
free_percpu(user_return_msrs);
kmem_cache_destroy(x86_emulator_cache);
- kmem_cache_destroy(x86_fpu_cache);
#ifdef CONFIG_KVM_XEN
static_key_deferred_flush(&kvm_xen_enabled);
WARN_ON(static_branch_unlikely(&kvm_xen_enabled.key));
kvm_run->cr8 = kvm_get_cr8(vcpu);
kvm_run->apic_base = kvm_get_apic_base(vcpu);
+
+ /*
+ * The call to kvm_ready_for_interrupt_injection() may end up in
+ * kvm_xen_has_interrupt() which may require the srcu lock to be
+ * held, to protect against changes in the vcpu_info address.
+ */
+ vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
kvm_run->ready_for_interrupt_injection =
pic_in_kernel(vcpu->kvm) ||
kvm_vcpu_ready_for_interrupt_injection(vcpu);
+ srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
if (is_smm(vcpu))
kvm_run->flags |= KVM_RUN_X86_SMM;
if (!kvm_apic_hw_enabled(vcpu->arch.apic))
return;
- if (to_hv_vcpu(vcpu))
+ if (to_hv_vcpu(vcpu)) {
bitmap_or((ulong *)eoi_exit_bitmap,
vcpu->arch.ioapic_handled_vectors,
to_hv_synic(vcpu)->vec_bitmap, 256);
+ static_call(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap);
+ return;
+ }
- static_call(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap);
+ static_call(kvm_x86_load_eoi_exitmap)(
+ vcpu, (u64 *)vcpu->arch.ioapic_handled_vectors);
}
void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
}
if (kvm_request_pending(vcpu)) {
- if (kvm_check_request(KVM_REQ_VM_BUGGED, vcpu)) {
+ if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu)) {
r = -EIO;
goto out;
}
if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST))
break;
- if (unlikely(kvm_vcpu_exit_request(vcpu))) {
+ if (vcpu->arch.apicv_active)
+ static_call(kvm_x86_sync_pir_to_irr)(vcpu);
+
+ if (unlikely(kvm_vcpu_exit_request(vcpu))) {
exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED;
break;
}
-
- if (vcpu->arch.apicv_active)
- static_call(kvm_x86_sync_pir_to_irr)(vcpu);
- }
+ }
/*
* Do this here before restoring debug registers on the host. And
return 0;
}
-static void kvm_save_current_fpu(struct fpu *fpu)
-{
- /*
- * If the target FPU state is not resident in the CPU registers, just
- * memcpy() from current, else save CPU state directly to the target.
- */
- if (test_thread_flag(TIF_NEED_FPU_LOAD))
- memcpy(&fpu->state, ¤t->thread.fpu.state,
- fpu_kernel_xstate_size);
- else
- save_fpregs_to_fpstate(fpu);
-}
-
/* Swap (qemu) user FPU context for the guest FPU context. */
static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
{
- fpregs_lock();
-
- kvm_save_current_fpu(vcpu->arch.user_fpu);
-
/*
- * Guests with protected state can't have it set by the hypervisor,
- * so skip trying to set it.
+ * Exclude PKRU from restore as restored separately in
+ * kvm_x86_ops.run().
*/
- if (vcpu->arch.guest_fpu)
- /* PKRU is separately restored in kvm_x86_ops.run. */
- __restore_fpregs_from_fpstate(&vcpu->arch.guest_fpu->state,
- ~XFEATURE_MASK_PKRU);
-
- fpregs_mark_activate();
- fpregs_unlock();
-
+ fpu_swap_kvm_fpstate(&vcpu->arch.guest_fpu, true);
trace_kvm_fpu(1);
}
/* When vcpu_run ends, restore user space FPU context. */
static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
{
- fpregs_lock();
-
- /*
- * Guests with protected state can't have it read by the hypervisor,
- * so skip trying to save it.
- */
- if (vcpu->arch.guest_fpu)
- kvm_save_current_fpu(vcpu->arch.guest_fpu);
-
- restore_fpregs_from_fpstate(&vcpu->arch.user_fpu->state);
-
- fpregs_mark_activate();
- fpregs_unlock();
-
+ fpu_swap_kvm_fpstate(&vcpu->arch.guest_fpu, false);
++vcpu->stat.fpu_reload;
trace_kvm_fpu(0);
}
{
struct fxregs_state *fxsave;
- if (!vcpu->arch.guest_fpu)
+ if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
return 0;
vcpu_load(vcpu);
- fxsave = &vcpu->arch.guest_fpu->state.fxsave;
+ fxsave = &vcpu->arch.guest_fpu.fpstate->regs.fxsave;
memcpy(fpu->fpr, fxsave->st_space, 128);
fpu->fcw = fxsave->cwd;
fpu->fsw = fxsave->swd;
{
struct fxregs_state *fxsave;
- if (!vcpu->arch.guest_fpu)
+ if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
return 0;
vcpu_load(vcpu);
- fxsave = &vcpu->arch.guest_fpu->state.fxsave;
+ fxsave = &vcpu->arch.guest_fpu.fpstate->regs.fxsave;
memcpy(fxsave->st_space, fpu->fpr, 128);
fxsave->cwd = fpu->fcw;
return 0;
}
-void kvm_free_guest_fpu(struct kvm_vcpu *vcpu)
-{
- if (vcpu->arch.guest_fpu) {
- kmem_cache_free(x86_fpu_cache, vcpu->arch.guest_fpu);
- vcpu->arch.guest_fpu = NULL;
- }
-}
-EXPORT_SYMBOL_GPL(kvm_free_guest_fpu);
-
int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
{
if (kvm_check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0)
if (!alloc_emulate_ctxt(vcpu))
goto free_wbinvd_dirty_mask;
- vcpu->arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache,
- GFP_KERNEL_ACCOUNT);
- if (!vcpu->arch.user_fpu) {
- pr_err("kvm: failed to allocate userspace's fpu\n");
- goto free_emulate_ctxt;
- }
-
- vcpu->arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache,
- GFP_KERNEL_ACCOUNT);
- if (!vcpu->arch.guest_fpu) {
+ if (!fpu_alloc_guest_fpstate(&vcpu->arch.guest_fpu)) {
pr_err("kvm: failed to allocate vcpu's fpu\n");
- goto free_user_fpu;
+ goto free_emulate_ctxt;
}
- fpstate_init(&vcpu->arch.guest_fpu->state);
- if (boot_cpu_has(X86_FEATURE_XSAVES))
- vcpu->arch.guest_fpu->state.xsave.header.xcomp_bv =
- host_xcr0 | XSTATE_COMPACTION_ENABLED;
vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
vcpu->arch.reserved_gpa_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu);
return 0;
free_guest_fpu:
- kvm_free_guest_fpu(vcpu);
-free_user_fpu:
- kmem_cache_free(x86_fpu_cache, vcpu->arch.user_fpu);
+ fpu_free_guest_fpstate(&vcpu->arch.guest_fpu);
free_emulate_ctxt:
kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt);
free_wbinvd_dirty_mask:
kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt);
free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
- kmem_cache_free(x86_fpu_cache, vcpu->arch.user_fpu);
- kvm_free_guest_fpu(vcpu);
+ fpu_free_guest_fpstate(&vcpu->arch.guest_fpu);
kvm_hv_vcpu_uninit(vcpu);
kvm_pmu_destroy(vcpu);
kvm_async_pf_hash_reset(vcpu);
vcpu->arch.apf.halted = false;
- if (vcpu->arch.guest_fpu && kvm_mpx_supported()) {
- void *mpx_state_buffer;
+ if (vcpu->arch.guest_fpu.fpstate && kvm_mpx_supported()) {
+ struct fpstate *fpstate = vcpu->arch.guest_fpu.fpstate;
/*
* To avoid have the INIT path from kvm_apic_has_events() that be
*/
if (init_event)
kvm_put_guest_fpu(vcpu);
- mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu->state.xsave,
- XFEATURE_BNDREGS);
- if (mpx_state_buffer)
- memset(mpx_state_buffer, 0, sizeof(struct mpx_bndreg_state));
- mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu->state.xsave,
- XFEATURE_BNDCSR);
- if (mpx_state_buffer)
- memset(mpx_state_buffer, 0, sizeof(struct mpx_bndcsr));
+
+ fpstate_clear_xstate_component(fpstate, XFEATURE_BNDREGS);
+ fpstate_clear_xstate_component(fpstate, XFEATURE_BNDCSR);
+
if (init_event)
kvm_load_guest_fpu(vcpu);
}
}
EXPORT_SYMBOL_GPL(kvm_sev_es_mmio_read);
-static int complete_sev_es_emulated_ins(struct kvm_vcpu *vcpu)
+static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size,
+ unsigned int port);
+
+static int complete_sev_es_emulated_outs(struct kvm_vcpu *vcpu)
{
- memcpy(vcpu->arch.guest_ins_data, vcpu->arch.pio_data,
- vcpu->arch.pio.count * vcpu->arch.pio.size);
- vcpu->arch.pio.count = 0;
+ int size = vcpu->arch.pio.size;
+ int port = vcpu->arch.pio.port;
+ vcpu->arch.pio.count = 0;
+ if (vcpu->arch.sev_pio_count)
+ return kvm_sev_es_outs(vcpu, size, port);
return 1;
}
static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size,
- unsigned int port, void *data, unsigned int count)
+ unsigned int port)
{
- int ret;
-
- ret = emulator_pio_out_emulated(vcpu->arch.emulate_ctxt, size, port,
- data, count);
- if (ret)
- return ret;
+ for (;;) {
+ unsigned int count =
+ min_t(unsigned int, PAGE_SIZE / size, vcpu->arch.sev_pio_count);
+ int ret = emulator_pio_out(vcpu, size, port, vcpu->arch.sev_pio_data, count);
+
+ /* memcpy done already by emulator_pio_out. */
+ vcpu->arch.sev_pio_count -= count;
+ vcpu->arch.sev_pio_data += count * vcpu->arch.pio.size;
+ if (!ret)
+ break;
- vcpu->arch.pio.count = 0;
+ /* Emulation done by the kernel. */
+ if (!vcpu->arch.sev_pio_count)
+ return 1;
+ }
+ vcpu->arch.complete_userspace_io = complete_sev_es_emulated_outs;
return 0;
}
static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size,
- unsigned int port, void *data, unsigned int count)
+ unsigned int port);
+
+static void advance_sev_es_emulated_ins(struct kvm_vcpu *vcpu)
{
- int ret;
+ unsigned count = vcpu->arch.pio.count;
+ complete_emulator_pio_in(vcpu, vcpu->arch.sev_pio_data);
+ vcpu->arch.sev_pio_count -= count;
+ vcpu->arch.sev_pio_data += count * vcpu->arch.pio.size;
+}
- ret = emulator_pio_in_emulated(vcpu->arch.emulate_ctxt, size, port,
- data, count);
- if (ret) {
- vcpu->arch.pio.count = 0;
- } else {
- vcpu->arch.guest_ins_data = data;
- vcpu->arch.complete_userspace_io = complete_sev_es_emulated_ins;
+static int complete_sev_es_emulated_ins(struct kvm_vcpu *vcpu)
+{
+ int size = vcpu->arch.pio.size;
+ int port = vcpu->arch.pio.port;
+
+ advance_sev_es_emulated_ins(vcpu);
+ if (vcpu->arch.sev_pio_count)
+ return kvm_sev_es_ins(vcpu, size, port);
+ return 1;
+}
+
+static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size,
+ unsigned int port)
+{
+ for (;;) {
+ unsigned int count =
+ min_t(unsigned int, PAGE_SIZE / size, vcpu->arch.sev_pio_count);
+ if (!__emulator_pio_in(vcpu, size, port, count))
+ break;
+
+ /* Emulation done by the kernel. */
+ advance_sev_es_emulated_ins(vcpu);
+ if (!vcpu->arch.sev_pio_count)
+ return 1;
}
+ vcpu->arch.complete_userspace_io = complete_sev_es_emulated_ins;
return 0;
}
unsigned int port, void *data, unsigned int count,
int in)
{
- return in ? kvm_sev_es_ins(vcpu, size, port, data, count)
- : kvm_sev_es_outs(vcpu, size, port, data, count);
+ vcpu->arch.sev_pio_data = data;
+ vcpu->arch.sev_pio_count = count;
+ return in ? kvm_sev_es_ins(vcpu, size, port)
+ : kvm_sev_es_outs(vcpu, size, port);
}
EXPORT_SYMBOL_GPL(kvm_sev_es_string_io);
state_entry_time = vx->runstate_entry_time;
state_entry_time |= XEN_RUNSTATE_UPDATE;
- BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->state_entry_time) !=
+ BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, state_entry_time) !=
sizeof(state_entry_time));
- BUILD_BUG_ON(sizeof(((struct compat_vcpu_runstate_info *)0)->state_entry_time) !=
+ BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state_entry_time) !=
sizeof(state_entry_time));
if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache,
*/
BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state) !=
offsetof(struct compat_vcpu_runstate_info, state));
- BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->state) !=
+ BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, state) !=
sizeof(vx->current_runstate));
- BUILD_BUG_ON(sizeof(((struct compat_vcpu_runstate_info *)0)->state) !=
+ BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state) !=
sizeof(vx->current_runstate));
if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache,
offsetof(struct vcpu_runstate_info, time) - sizeof(u64));
BUILD_BUG_ON(offsetof(struct compat_vcpu_runstate_info, state_entry_time) !=
offsetof(struct compat_vcpu_runstate_info, time) - sizeof(u64));
- BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->time) !=
- sizeof(((struct compat_vcpu_runstate_info *)0)->time));
- BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->time) !=
+ BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, time) !=
+ sizeof_field(struct compat_vcpu_runstate_info, time));
+ BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, time) !=
sizeof(vx->runstate_times));
if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache,
int __kvm_xen_has_interrupt(struct kvm_vcpu *v)
{
+ int err;
u8 rc = 0;
/*
BUILD_BUG_ON(offsetof(struct vcpu_info, evtchn_upcall_pending) !=
offsetof(struct compat_vcpu_info, evtchn_upcall_pending));
BUILD_BUG_ON(sizeof(rc) !=
- sizeof(((struct vcpu_info *)0)->evtchn_upcall_pending));
+ sizeof_field(struct vcpu_info, evtchn_upcall_pending));
BUILD_BUG_ON(sizeof(rc) !=
- sizeof(((struct compat_vcpu_info *)0)->evtchn_upcall_pending));
+ sizeof_field(struct compat_vcpu_info, evtchn_upcall_pending));
/*
* For efficiency, this mirrors the checks for using the valid
if (likely(slots->generation == ghc->generation &&
!kvm_is_error_hva(ghc->hva) && ghc->memslot)) {
/* Fast path */
- __get_user(rc, (u8 __user *)ghc->hva + offset);
- } else {
- /* Slow path */
- kvm_read_guest_offset_cached(v->kvm, ghc, &rc, offset,
- sizeof(rc));
+ pagefault_disable();
+ err = __get_user(rc, (u8 __user *)ghc->hva + offset);
+ pagefault_enable();
+ if (!err)
+ return rc;
}
+ /* Slow path */
+
+ /*
+ * This function gets called from kvm_vcpu_block() after setting the
+ * task to TASK_INTERRUPTIBLE, to see if it needs to wake immediately
+ * from a HLT. So we really mustn't sleep. If the page ended up absent
+ * at that point, just return 1 in order to trigger an immediate wake,
+ * and we'll end up getting called again from a context where we *can*
+ * fault in the page and wait for it.
+ */
+ if (in_atomic() || !task_is_running(current))
+ return 1;
+
+ kvm_read_guest_offset_cached(v->kvm, ghc, &rc, offset,
+ sizeof(rc));
+
return rc;
}
break;
case KVM_XEN_ATTR_TYPE_SHARED_INFO:
- data->u.shared_info.gfn = gpa_to_gfn(kvm->arch.xen.shinfo_gfn);
+ data->u.shared_info.gfn = kvm->arch.xen.shinfo_gfn;
r = 0;
break;
#define KVM_REQ_MMU_RELOAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_UNBLOCK 2
#define KVM_REQ_UNHALT 3
-#define KVM_REQ_VM_BUGGED (4 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_VM_DEAD (4 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQUEST_ARCH_BASE 8
#define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \
unsigned int max_halt_poll_ns;
u32 dirty_ring_size;
bool vm_bugged;
+ bool vm_dead;
#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
struct notifier_block pm_notifier;
#define vcpu_err(vcpu, fmt, ...) \
kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__)
+static inline void kvm_vm_dead(struct kvm *kvm)
+{
+ kvm->vm_dead = true;
+ kvm_make_all_cpus_request(kvm, KVM_REQ_VM_DEAD);
+}
+
static inline void kvm_vm_bugged(struct kvm *kvm)
{
kvm->vm_bugged = true;
- kvm_make_all_cpus_request(kvm, KVM_REQ_VM_BUGGED);
+ kvm_vm_dead(kvm);
}
+
#define KVM_BUG(cond, kvm, fmt...) \
({ \
int __ret = (cond); \
void kvm_set_pfn_dirty(kvm_pfn_t pfn);
void kvm_set_pfn_accessed(kvm_pfn_t pfn);
- void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache);
+ void kvm_release_pfn(kvm_pfn_t pfn, bool dirty);
int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
int len);
int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len);
kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn);
kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn);
int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map);
- int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map,
- struct gfn_to_pfn_cache *cache, bool atomic);
struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn);
void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty);
- int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map,
- struct gfn_to_pfn_cache *cache, bool dirty, bool atomic);
unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn);
unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable);
int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset,
}
EXPORT_SYMBOL_GPL(gfn_to_page);
- void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache)
+ void kvm_release_pfn(kvm_pfn_t pfn, bool dirty)
{
if (pfn == 0)
return;
- if (cache)
- cache->pfn = cache->gfn = 0;
-
if (dirty)
kvm_release_pfn_dirty(pfn);
else
kvm_release_pfn_clean(pfn);
}
- static void kvm_cache_gfn_to_pfn(struct kvm_memory_slot *slot, gfn_t gfn,
- struct gfn_to_pfn_cache *cache, u64 gen)
- {
- kvm_release_pfn(cache->pfn, cache->dirty, cache);
-
- cache->pfn = gfn_to_pfn_memslot(slot, gfn);
- cache->gfn = gfn;
- cache->dirty = false;
- cache->generation = gen;
- }
-
- static int __kvm_map_gfn(struct kvm_memslots *slots, gfn_t gfn,
- struct kvm_host_map *map,
- struct gfn_to_pfn_cache *cache,
- bool atomic)
+ int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map)
{
kvm_pfn_t pfn;
void *hva = NULL;
struct page *page = KVM_UNMAPPED_PAGE;
- struct kvm_memory_slot *slot = __gfn_to_memslot(slots, gfn);
- u64 gen = slots->generation;
if (!map)
return -EINVAL;
- if (cache) {
- if (!cache->pfn || cache->gfn != gfn ||
- cache->generation != gen) {
- if (atomic)
- return -EAGAIN;
- kvm_cache_gfn_to_pfn(slot, gfn, cache, gen);
- }
- pfn = cache->pfn;
- } else {
- if (atomic)
- return -EAGAIN;
- pfn = gfn_to_pfn_memslot(slot, gfn);
- }
+ pfn = gfn_to_pfn(vcpu->kvm, gfn);
if (is_error_noslot_pfn(pfn))
return -EINVAL;
if (pfn_valid(pfn)) {
page = pfn_to_page(pfn);
- if (atomic)
- hva = kmap_atomic(page);
- else
- hva = kmap(page);
+ hva = kmap(page);
#ifdef CONFIG_HAS_IOMEM
- } else if (!atomic) {
- hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB);
} else {
- return -EINVAL;
+ hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB);
#endif
}
return 0;
}
-
- int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map,
- struct gfn_to_pfn_cache *cache, bool atomic)
- {
- return __kvm_map_gfn(kvm_memslots(vcpu->kvm), gfn, map,
- cache, atomic);
- }
- EXPORT_SYMBOL_GPL(kvm_map_gfn);
-
- int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map)
- {
- return __kvm_map_gfn(kvm_vcpu_memslots(vcpu), gfn, map,
- NULL, false);
- }
EXPORT_SYMBOL_GPL(kvm_vcpu_map);
- static void __kvm_unmap_gfn(struct kvm *kvm,
- struct kvm_memory_slot *memslot,
- struct kvm_host_map *map,
- struct gfn_to_pfn_cache *cache,
- bool dirty, bool atomic)
+ void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty)
{
if (!map)
return;
if (!map->hva)
return;
- if (map->page != KVM_UNMAPPED_PAGE) {
- if (atomic)
- kunmap_atomic(map->hva);
- else
- kunmap(map->page);
- }
+ if (map->page != KVM_UNMAPPED_PAGE)
+ kunmap(map->page);
#ifdef CONFIG_HAS_IOMEM
- else if (!atomic)
- memunmap(map->hva);
else
- WARN_ONCE(1, "Unexpected unmapping in atomic context");
+ memunmap(map->hva);
#endif
if (dirty)
- mark_page_dirty_in_slot(kvm, memslot, map->gfn);
+ kvm_vcpu_mark_page_dirty(vcpu, map->gfn);
- if (cache)
- cache->dirty |= dirty;
- else
- kvm_release_pfn(map->pfn, dirty, NULL);
+ kvm_release_pfn(map->pfn, dirty);
map->hva = NULL;
map->page = NULL;
}
-
- int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map,
- struct gfn_to_pfn_cache *cache, bool dirty, bool atomic)
- {
- __kvm_unmap_gfn(vcpu->kvm, gfn_to_memslot(vcpu->kvm, map->gfn), map,
- cache, dirty, atomic);
- return 0;
- }
- EXPORT_SYMBOL_GPL(kvm_unmap_gfn);
-
- void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty)
- {
- __kvm_unmap_gfn(vcpu->kvm, kvm_vcpu_gfn_to_memslot(vcpu, map->gfn),
- map, NULL, dirty, false);
- }
EXPORT_SYMBOL_GPL(kvm_vcpu_unmap);
struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn)
struct kvm_fpu *fpu = NULL;
struct kvm_sregs *kvm_sregs = NULL;
- if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_bugged)
+ if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_dead)
return -EIO;
if (unlikely(_IOC_TYPE(ioctl) != KVMIO))
void __user *argp = compat_ptr(arg);
int r;
- if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_bugged)
+ if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_dead)
return -EIO;
switch (ioctl) {
{
struct kvm_device *dev = filp->private_data;
- if (dev->kvm->mm != current->mm || dev->kvm->vm_bugged)
+ if (dev->kvm->mm != current->mm || dev->kvm->vm_dead)
return -EIO;
switch (ioctl) {
void __user *argp = (void __user *)arg;
int r;
- if (kvm->mm != current->mm || kvm->vm_bugged)
+ if (kvm->mm != current->mm || kvm->vm_dead)
return -EIO;
switch (ioctl) {
case KVM_CREATE_VCPU:
struct kvm *kvm = filp->private_data;
int r;
- if (kvm->mm != current->mm || kvm->vm_bugged)
+ if (kvm->mm != current->mm || kvm->vm_dead)
return -EIO;
switch (ioctl) {
#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
projects / J-linux.git / commitdiff