static void lazy_hcall1(unsigned long call, unsigned long arg1)
{
if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE)
hcall(call, arg1, 0, 0, 0);
else
async_hcall(call, arg1, 0, 0, 0);
}
int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
struct gnttab_map_grant_ref *kmap_ops,
struct page **pages, unsigned int count)
{
int i, ret;
bool lazy = false;
ret = HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, unmap_ops, count);
if (ret)
return ret;
if (xen_feature(XENFEAT_auto_translated_physmap))
return ret;
if (!in_interrupt() && paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
arch_enter_lazy_mmu_mode();
lazy = true;
}
for (i = 0; i < count; i++) {
ret = m2p_remove_override(pages[i], kmap_ops ?
&kmap_ops[i] : NULL);
if (ret)
return ret;
}
if (lazy)
arch_leave_lazy_mmu_mode();
return ret;
}
void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pteval)
{
ADD_STATS(set_pte_at, 1);
// ADD_STATS(set_pte_at_pinned, xen_page_pinned(ptep));
ADD_STATS(set_pte_at_current, mm == current->mm);
ADD_STATS(set_pte_at_kernel, mm == &init_mm);
if (mm == current->mm || mm == &init_mm) {
if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
struct multicall_space mcs;
mcs = xen_mc_entry(0);
MULTI_update_va_mapping(mcs.mc, addr, pteval, 0);
ADD_STATS(set_pte_at_batched, 1);
xen_mc_issue(PARAVIRT_LAZY_MMU);
goto out;
} else
if (HYPERVISOR_update_va_mapping(addr, pteval, 0) == 0)
goto out;
}
xen_set_pte(ptep, pteval);
out: return;
}
/* You can imagine what lazy_hcall2, 3 and 4 look like. :*/
static void lazy_hcall2(unsigned long call,
unsigned long arg1,
unsigned long arg2)
{
if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE)
kvm_hypercall2(call, arg1, arg2);
else
async_hcall(call, arg1, arg2, 0, 0);
}
int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
struct gnttab_map_grant_ref *kmap_ops,
struct page **pages, unsigned int count)
{
int i, ret = 0;
bool lazy = false;
pte_t *pte;
if (xen_feature(XENFEAT_auto_translated_physmap))
return 0;
if (kmap_ops &&
!in_interrupt() &&
paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
arch_enter_lazy_mmu_mode();
lazy = true;
}
for (i = 0; i < count; i++) {
unsigned long mfn, pfn;
/* Do not add to override if the map failed. */
if (map_ops[i].status)
continue;
if (map_ops[i].flags & GNTMAP_contains_pte) {
pte = (pte_t *)(mfn_to_virt(PFN_DOWN(map_ops[i].host_addr)) +
(map_ops[i].host_addr & ~PAGE_MASK));
mfn = pte_mfn(*pte);
} else {
mfn = PFN_DOWN(map_ops[i].dev_bus_addr);
}
pfn = page_to_pfn(pages[i]);
WARN_ON(PagePrivate(pages[i]));
SetPagePrivate(pages[i]);
set_page_private(pages[i], mfn);
pages[i]->index = pfn_to_mfn(pfn);
if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) {
ret = -ENOMEM;
goto out;
}
if (kmap_ops) {
ret = m2p_add_override(mfn, pages[i], &kmap_ops[i]);
if (ret)
goto out;
}
}
out:
if (lazy)
arch_leave_lazy_mmu_mode();
return ret;
}
void paravirt_flush_lazy_mmu(void)
{
preempt_disable();
if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
arch_leave_lazy_mmu_mode();
arch_enter_lazy_mmu_mode();
}
preempt_enable();
}
static void lazy_hcall4(unsigned long call,
unsigned long arg1,
unsigned long arg2,
unsigned long arg3,
unsigned long arg4)
{
if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE)
hcall(call, arg1, arg2, arg3, arg4);
else
async_hcall(call, arg1, arg2, arg3, arg4);
}
void arch_flush_lazy_cpu_mode(void)
{
preempt_disable();
if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) {
WARN_ON(preempt_count() == 1);
arch_leave_lazy_cpu_mode();
arch_enter_lazy_cpu_mode();
}
preempt_enable();
}
static void kvm_deferred_mmu_op(void *buffer, int len)
{
struct kvm_para_state *state = kvm_para_state();
if (paravirt_get_lazy_mode() != PARAVIRT_LAZY_MMU) {
kvm_mmu_op(buffer, len);
return;
}
if (state->mmu_queue_len + len > sizeof state->mmu_queue)
mmu_queue_flush(state);
memcpy(state->mmu_queue + state->mmu_queue_len, buffer, len);
state->mmu_queue_len += len;
}
int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
struct gnttab_map_grant_ref *kmap_ops,
struct page **pages, unsigned int count)
{
int i, ret;
bool lazy = false;
pte_t *pte;
unsigned long mfn;
ret = HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, map_ops, count);
if (ret)
return ret;
/* Retry eagain maps */
for (i = 0; i < count; i++)
if (map_ops[i].status == GNTST_eagain)
gnttab_retry_eagain_gop(GNTTABOP_map_grant_ref, map_ops + i,
&map_ops[i].status, __func__);
if (xen_feature(XENFEAT_auto_translated_physmap))
return ret;
if (!in_interrupt() && paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
arch_enter_lazy_mmu_mode();
lazy = true;
}
for (i = 0; i < count; i++) {
/* Do not add to override if the map failed. */
if (map_ops[i].status)
continue;
if (map_ops[i].flags & GNTMAP_contains_pte) {
pte = (pte_t *) (mfn_to_virt(PFN_DOWN(map_ops[i].host_addr)) +
(map_ops[i].host_addr & ~PAGE_MASK));
mfn = pte_mfn(*pte);
} else {
mfn = PFN_DOWN(map_ops[i].dev_bus_addr);
}
ret = m2p_add_override(mfn, pages[i], kmap_ops ?
&kmap_ops[i] : NULL);
if (ret)
goto out;
}
out:
if (lazy)
arch_leave_lazy_mmu_mode();
return ret;
}
void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte)
{
struct mmu_update u;
xen_mc_batch();
u.ptr = arbitrary_virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD;
u.val = pte_val_ma(pte);
xen_extend_mmu_update(&u);
ADD_STATS(prot_commit, 1);
ADD_STATS(prot_commit_batched, paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU);
xen_mc_issue(PARAVIRT_LAZY_MMU);
}
static bool xen_batched_set_pte(pte_t *ptep, pte_t pteval)
{
struct mmu_update u;
if (paravirt_get_lazy_mode() != PARAVIRT_LAZY_MMU)
return false;
xen_mc_batch();
u.ptr = virt_to_machine(ptep).maddr | MMU_NORMAL_PT_UPDATE;
u.val = pte_val_ma(pteval);
xen_extend_mmu_update(&u);
xen_mc_issue(PARAVIRT_LAZY_MMU);
return true;
}
static void xen_load_tls(struct thread_struct *t, unsigned int cpu)
{
if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) {
#ifdef CONFIG_X86_32
lazy_load_gs(0);
#else
loadsegment(fs, 0);
#endif
}
xen_mc_batch();
load_TLS_descriptor(t, cpu, 0);
load_TLS_descriptor(t, cpu, 1);
load_TLS_descriptor(t, cpu, 2);
xen_mc_issue(PARAVIRT_LAZY_CPU);
}
void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val)
{
struct mmu_update u;
preempt_disable();
xen_mc_batch();
/* ptr may be ioremapped for 64-bit pagetable setup */
u.ptr = arbitrary_virt_to_machine(ptr).maddr;
u.val = pmd_val_ma(val);
xen_extend_mmu_update(&u);
ADD_STATS(pmd_update_batched, paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU);
xen_mc_issue(PARAVIRT_LAZY_MMU);
preempt_enable();
}
int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
struct gnttab_map_grant_ref *kmap_ops,
struct page **pages, unsigned int count)
{
int i, ret = 0;
bool lazy = false;
if (xen_feature(XENFEAT_auto_translated_physmap))
return 0;
if (kmap_ops &&
!in_interrupt() &&
paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
arch_enter_lazy_mmu_mode();
lazy = true;
}
for (i = 0; i < count; i++) {
unsigned long mfn = __pfn_to_mfn(page_to_pfn(pages[i]));
unsigned long pfn = page_to_pfn(pages[i]);
if (mfn == INVALID_P2M_ENTRY || !(mfn & FOREIGN_FRAME_BIT)) {
ret = -EINVAL;
goto out;
}
set_page_private(pages[i], INVALID_P2M_ENTRY);
WARN_ON(!PagePrivate(pages[i]));
ClearPagePrivate(pages[i]);
set_phys_to_machine(pfn, pages[i]->index);
if (kmap_ops)
ret = m2p_remove_override(pages[i], &kmap_ops[i], mfn);
if (ret)
goto out;
}
out:
if (lazy)
arch_leave_lazy_mmu_mode();
return ret;
}
static void xen_load_tls(struct thread_struct *t, unsigned int cpu)
{
/*
* XXX sleazy hack: If we're being called in a lazy-cpu zone
* and lazy gs handling is enabled, it means we're in a
* context switch, and %gs has just been saved. This means we
* can zero it out to prevent faults on exit from the
* hypervisor if the next process has no %gs. Either way, it
* has been saved, and the new value will get loaded properly.
* This will go away as soon as Xen has been modified to not
* save/restore %gs for normal hypercalls.
*
* On x86_64, this hack is not used for %gs, because gs points
* to KERNEL_GS_BASE (and uses it for PDA references), so we
* must not zero %gs on x86_64
*
* For x86_64, we need to zero %fs, otherwise we may get an
* exception between the new %fs descriptor being loaded and
* %fs being effectively cleared at __switch_to().
*/
if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) {
#ifdef CONFIG_X86_32
lazy_load_gs(0);
#else
loadsegment(fs, 0);
#endif
}
xen_mc_batch();
load_TLS_descriptor(t, cpu, 0);
load_TLS_descriptor(t, cpu, 1);
load_TLS_descriptor(t, cpu, 2);
xen_mc_issue(PARAVIRT_LAZY_CPU);
}
/* When lazy mode is turned off reset the per-cpu lazy mode variable and then
* issue the do-nothing hypercall to flush any stored calls. */
static void lguest_leave_lazy_mode(void)
{
paravirt_leave_lazy(paravirt_get_lazy_mode());
hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0);
}
void xen_leave_lazy(void)
{
paravirt_leave_lazy(paravirt_get_lazy_mode());
xen_mc_flush();
}
static void kvm_flush_tlb(void)
{
struct kvm_mmu_op_flush_tlb ftlb = {
.header.op = KVM_MMU_OP_FLUSH_TLB,
};
kvm_deferred_mmu_op(&ftlb, sizeof ftlb);
}
static void kvm_release_pt(unsigned long pfn)
{
struct kvm_mmu_op_release_pt rpt = {
.header.op = KVM_MMU_OP_RELEASE_PT,
.pt_phys = (u64)pfn << PAGE_SHIFT,
};
kvm_mmu_op(&rpt, sizeof rpt);
}
static void kvm_enter_lazy_mmu(void)
{
struct kvm_para_state *state = kvm_para_state();
paravirt_enter_lazy_mmu();
state->mode = paravirt_get_lazy_mode();
}
static void kvm_leave_lazy_mmu(void)
{
struct kvm_para_state *state = kvm_para_state();
mmu_queue_flush(state);
paravirt_leave_lazy_mmu();
state->mode = paravirt_get_lazy_mode();
}
static void __init paravirt_ops_setup(void)
{
pv_info.name = "KVM";
pv_info.paravirt_enabled = 1;
if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY))
pv_cpu_ops.io_delay = kvm_io_delay;
if (kvm_para_has_feature(KVM_FEATURE_MMU_OP)) {
pv_mmu_ops.set_pte = kvm_set_pte;
pv_mmu_ops.set_pte_at = kvm_set_pte_at;
pv_mmu_ops.set_pmd = kvm_set_pmd;
#if PAGETABLE_LEVELS >= 3
#ifdef CONFIG_X86_PAE
pv_mmu_ops.set_pte_atomic = kvm_set_pte_atomic;
pv_mmu_ops.pte_clear = kvm_pte_clear;
pv_mmu_ops.pmd_clear = kvm_pmd_clear;
#endif
pv_mmu_ops.set_pud = kvm_set_pud;
#if PAGETABLE_LEVELS == 4
pv_mmu_ops.set_pgd = kvm_set_pgd;
#endif
#endif
pv_mmu_ops.flush_tlb_user = kvm_flush_tlb;
pv_mmu_ops.release_pte = kvm_release_pt;
pv_mmu_ops.release_pmd = kvm_release_pt;
pv_mmu_ops.release_pud = kvm_release_pt;
pv_mmu_ops.lazy_mode.enter = kvm_enter_lazy_mmu;
pv_mmu_ops.lazy_mode.leave = kvm_leave_lazy_mmu;
}
#ifdef CONFIG_X86_IO_APIC
no_timer_check = 1;
#endif
}
void __init kvm_guest_init(void)
{
if (!kvm_para_available())
return;
paravirt_ops_setup();
}
/* When lazy mode is turned off reset the per-cpu lazy mode variable and then
* issue the do-nothing hypercall to flush any stored calls. */
static void lguest_leave_lazy_mode(void)
{
paravirt_leave_lazy(paravirt_get_lazy_mode());
kvm_hypercall0(LHCALL_FLUSH_ASYNC);
}
