/* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive * for more details. * * KVM/MIPS MMU handling in the KVM module. * * Copyright (C) 2012 MIPS Technologies, Inc. All rights reserved. * Authors: Sanjay Lal <sanjayl@kymasys.com>
*/
/* * KVM_MMU_CACHE_MIN_PAGES is the number of GPA page table translation levels * for which pages need to be cached.
*/ #ifdefined(__PAGETABLE_PMD_FOLDED) #define KVM_MMU_CACHE_MIN_PAGES 1 #else #define KVM_MMU_CACHE_MIN_PAGES 2 #endif
/** * kvm_pgd_init() - Initialise KVM GPA page directory. * @page: Pointer to page directory (PGD) for KVM GPA. * * Initialise a KVM GPA page directory with pointers to the invalid table, i.e. * representing no mappings. This is similar to pgd_init(), however it * initialises all the page directory pointers, not just the ones corresponding * to the userland address space (since it is for the guest physical address * space rather than a virtual address space).
*/ staticvoid kvm_pgd_init(void *page)
{ unsignedlong *p, *end; unsignedlong entry;
/** * kvm_pgd_alloc() - Allocate and initialise a KVM GPA page directory. * * Allocate a blank KVM GPA page directory (PGD) for representing guest physical * to host physical page mappings. * * Returns: Pointer to new KVM GPA page directory. * NULL on allocation failure.
*/
pgd_t *kvm_pgd_alloc(void)
{
pgd_t *ret;
ret = (pgd_t *)__get_free_pages(GFP_KERNEL, PGD_TABLE_ORDER); if (ret)
kvm_pgd_init(ret);
return ret;
}
/** * kvm_mips_walk_pgd() - Walk page table with optional allocation. * @pgd: Page directory pointer. * @addr: Address to index page table using. * @cache: MMU page cache to allocate new page tables from, or NULL. * * Walk the page tables pointed to by @pgd to find the PTE corresponding to the * address @addr. If page tables don't exist for @addr, they will be created * from the MMU cache if @cache is not NULL. * * Returns: Pointer to pte_t corresponding to @addr. * NULL if a page table doesn't exist for @addr and !@cache. * NULL if a page table allocation failed.
*/ static pte_t *kvm_mips_walk_pgd(pgd_t *pgd, struct kvm_mmu_memory_cache *cache, unsignedlong addr)
{
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pgd += pgd_index(addr); if (pgd_none(*pgd)) { /* Not used on MIPS yet */
BUG(); return NULL;
}
p4d = p4d_offset(pgd, addr);
pud = pud_offset(p4d, addr); if (pud_none(*pud)) {
pmd_t *new_pmd;
/** * kvm_mips_flush_gpa_pt() - Flush a range of guest physical addresses. * @kvm: KVM pointer. * @start_gfn: Guest frame number of first page in GPA range to flush. * @end_gfn: Guest frame number of last page in GPA range to flush. * * Flushes a range of GPA mappings from the GPA page tables. * * The caller must hold the @kvm->mmu_lock spinlock. * * Returns: Whether its safe to remove the top level page directory because * all lower levels have been removed.
*/ bool kvm_mips_flush_gpa_pt(struct kvm *kvm, gfn_t start_gfn, gfn_t end_gfn)
{ return kvm_mips_flush_gpa_pgd(kvm->arch.gpa_mm.pgd,
start_gfn << PAGE_SHIFT,
end_gfn << PAGE_SHIFT);
}
#define BUILD_PTE_RANGE_OP(name, op) \ staticint kvm_mips_##name##_pte(pte_t *pte, unsignedlong start, \ unsignedlong end) \
{ \ int ret = 0; \ int i_min = pte_index(start); \ int i_max = pte_index(end); \ int i; \
pte_t old, new; \
\ for (i = i_min; i <= i_max; ++i) { \ if (!pte_present(pte[i])) \ continue; \
\
old = pte[i]; \ new = op(old); \ if (pte_val(new) == pte_val(old)) \ continue; \
set_pte(pte + i, new); \
ret = 1; \
} \ return ret; \
} \
\ /* returns true if anything was done */ \ staticint kvm_mips_##name##_pmd(pmd_t *pmd, unsignedlong start, \ unsignedlong end) \
{ \ int ret = 0; \
pte_t *pte; \ unsignedlong cur_end = ~0ul; \ int i_min = pmd_index(start); \ int i_max = pmd_index(end); \ int i; \
\ for (i = i_min; i <= i_max; ++i, start = 0) { \ if (!pmd_present(pmd[i])) \ continue; \
\
pte = pte_offset_kernel(pmd + i, 0); \ if (i == i_max) \
cur_end = end; \
\
ret |= kvm_mips_##name##_pte(pte, start, cur_end); \
} \ return ret; \
} \
\ staticint kvm_mips_##name##_pud(pud_t *pud, unsignedlong start, \ unsignedlong end) \
{ \ int ret = 0; \
pmd_t *pmd; \ unsignedlong cur_end = ~0ul; \ int i_min = pud_index(start); \ int i_max = pud_index(end); \ int i; \
\ for (i = i_min; i <= i_max; ++i, start = 0) { \ if (!pud_present(pud[i])) \ continue; \
\
pmd = pmd_offset(pud + i, 0); \ if (i == i_max) \
cur_end = end; \
\
ret |= kvm_mips_##name##_pmd(pmd, start, cur_end); \
} \ return ret; \
} \
\ staticint kvm_mips_##name##_pgd(pgd_t *pgd, unsignedlong start, \ unsignedlong end) \
{ \ int ret = 0; \
p4d_t *p4d; \
pud_t *pud; \ unsignedlong cur_end = ~0ul; \ int i_min = pgd_index(start); \ int i_max = pgd_index(end); \ int i; \
\ for (i = i_min; i <= i_max; ++i, start = 0) { \ if (!pgd_present(pgd[i])) \ continue; \
\
p4d = p4d_offset(pgd, 0); \
pud = pud_offset(p4d + i, 0); \ if (i == i_max) \
cur_end = end; \
\
ret |= kvm_mips_##name##_pud(pud, start, cur_end); \
} \ return ret; \
}
/* * kvm_mips_mkclean_gpa_pt. * Mark a range of guest physical address space clean (writes fault) in the VM's * GPA page table to allow dirty page tracking.
*/
BUILD_PTE_RANGE_OP(mkclean, pte_mkclean)
/** * kvm_mips_mkclean_gpa_pt() - Make a range of guest physical addresses clean. * @kvm: KVM pointer. * @start_gfn: Guest frame number of first page in GPA range to flush. * @end_gfn: Guest frame number of last page in GPA range to flush. * * Make a range of GPA mappings clean so that guest writes will fault and * trigger dirty page logging. * * The caller must hold the @kvm->mmu_lock spinlock. * * Returns: Whether any GPA mappings were modified, which would require * derived mappings (GVA page tables & TLB enties) to be * invalidated.
*/ int kvm_mips_mkclean_gpa_pt(struct kvm *kvm, gfn_t start_gfn, gfn_t end_gfn)
{ return kvm_mips_mkclean_pgd(kvm->arch.gpa_mm.pgd,
start_gfn << PAGE_SHIFT,
end_gfn << PAGE_SHIFT);
}
/** * kvm_arch_mmu_enable_log_dirty_pt_masked() - write protect dirty pages * @kvm: The KVM pointer * @slot: The memory slot associated with mask * @gfn_offset: The gfn offset in memory slot * @mask: The mask of dirty pages at offset 'gfn_offset' in this memory * slot to be write protected * * Walks bits set in mask write protects the associated pte's. Caller must * acquire @kvm->mmu_lock.
*/ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot,
gfn_t gfn_offset, unsignedlong mask)
{
gfn_t base_gfn = slot->base_gfn + gfn_offset;
gfn_t start = base_gfn + __ffs(mask);
gfn_t end = base_gfn + __fls(mask);
kvm_mips_mkclean_gpa_pt(kvm, start, end);
}
/* * kvm_mips_mkold_gpa_pt. * Mark a range of guest physical address space old (all accesses fault) in the * VM's GPA page table to allow detection of commonly used pages.
*/
if (!gpa_pte) returnfalse; return pte_young(*gpa_pte);
}
/** * _kvm_mips_map_page_fast() - Fast path GPA fault handler. * @vcpu: VCPU pointer. * @gpa: Guest physical address of fault. * @write_fault: Whether the fault was due to a write. * @out_entry: New PTE for @gpa (written on success unless NULL). * @out_buddy: New PTE for @gpa's buddy (written on success unless * NULL). * * Perform fast path GPA fault handling, doing all that can be done without * calling into KVM. This handles marking old pages young (for idle page * tracking), and dirtying of clean pages (for dirty page logging). * * Returns: 0 on success, in which case we can update derived mappings and * resume guest execution. * -EFAULT on failure due to absent GPA mapping or write to * read-only page, in which case KVM must be consulted.
*/ staticint _kvm_mips_map_page_fast(struct kvm_vcpu *vcpu, unsignedlong gpa, bool write_fault,
pte_t *out_entry, pte_t *out_buddy)
{ struct kvm *kvm = vcpu->kvm;
gfn_t gfn = gpa >> PAGE_SHIFT;
pte_t *ptep; int ret = 0;
spin_lock(&kvm->mmu_lock);
/* Fast path - just check GPA page table for an existing entry */
ptep = kvm_mips_pte_for_gpa(kvm, NULL, gpa); if (!ptep || !pte_present(*ptep)) {
ret = -EFAULT; goto out;
}
/* Track access to pages marked old */ if (!pte_young(*ptep))
set_pte(ptep, pte_mkyoung(*ptep));
if (write_fault && !pte_dirty(*ptep)) { if (!pte_write(*ptep)) {
ret = -EFAULT; goto out;
}
if (out_entry)
*out_entry = *ptep; if (out_buddy)
*out_buddy = *ptep_buddy(ptep);
out:
spin_unlock(&kvm->mmu_lock); return ret;
}
/** * kvm_mips_map_page() - Map a guest physical page. * @vcpu: VCPU pointer. * @gpa: Guest physical address of fault. * @write_fault: Whether the fault was due to a write. * @out_entry: New PTE for @gpa (written on success unless NULL). * @out_buddy: New PTE for @gpa's buddy (written on success unless * NULL). * * Handle GPA faults by creating a new GPA mapping (or updating an existing * one). * * This takes care of marking pages young or dirty (idle/dirty page tracking), * asking KVM for the corresponding PFN, and creating a mapping in the GPA page * tables. Derived mappings (GVA page tables and TLBs) must be handled by the * caller. * * Returns: 0 on success, in which case the caller may use the @out_entry * and @out_buddy PTEs to update derived mappings and resume guest * execution. * -EFAULT if there is no memory region at @gpa or a write was * attempted to a read-only memory region. This is usually handled * as an MMIO access.
*/ staticint kvm_mips_map_page(struct kvm_vcpu *vcpu, unsignedlong gpa, bool write_fault,
pte_t *out_entry, pte_t *out_buddy)
{ struct kvm *kvm = vcpu->kvm; struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
gfn_t gfn = gpa >> PAGE_SHIFT; int srcu_idx, err;
kvm_pfn_t pfn;
pte_t *ptep, entry; bool writeable; unsignedlong prot_bits; unsignedlong mmu_seq; struct page *page;
/* Try the fast path to handle old / clean pages */
srcu_idx = srcu_read_lock(&kvm->srcu);
err = _kvm_mips_map_page_fast(vcpu, gpa, write_fault, out_entry,
out_buddy); if (!err) goto out;
/* We need a minimum of cached pages ready for page table creation */
err = kvm_mmu_topup_memory_cache(memcache, KVM_MMU_CACHE_MIN_PAGES); if (err) goto out;
retry: /* * Used to check for invalidations in progress, of the pfn that is * returned by pfn_to_pfn_prot below.
*/
mmu_seq = kvm->mmu_invalidate_seq; /* * Ensure the read of mmu_invalidate_seq isn't reordered with PTE reads * in kvm_faultin_pfn() (which calls get_user_pages()), so that we don't * risk the page we get a reference to getting unmapped before we have a * chance to grab the mmu_lock without mmu_invalidate_retry() noticing. * * This smp_rmb() pairs with the effective smp_wmb() of the combination * of the pte_unmap_unlock() after the PTE is zapped, and the * spin_lock() in kvm_mmu_notifier_invalidate_<page|range_end>() before * mmu_invalidate_seq is incremented.
*/
smp_rmb();
/* Slow path - ask KVM core whether we can access this GPA */
pfn = kvm_faultin_pfn(vcpu, gfn, write_fault, &writeable, &page); if (is_error_noslot_pfn(pfn)) {
err = -EFAULT; goto out;
}
spin_lock(&kvm->mmu_lock); /* Check if an invalidation has taken place since we got pfn */ if (mmu_invalidate_retry(kvm, mmu_seq)) { /* * This can happen when mappings are changed asynchronously, but * also synchronously if a COW is triggered by * kvm_faultin_pfn().
*/
spin_unlock(&kvm->mmu_lock);
kvm_release_page_unused(page); goto retry;
}
int kvm_mips_handle_vz_root_tlb_fault(unsignedlong badvaddr, struct kvm_vcpu *vcpu, bool write_fault)
{ int ret;
ret = kvm_mips_map_page(vcpu, badvaddr, write_fault, NULL, NULL); if (ret) return ret;
/* Invalidate this entry in the TLB */ return kvm_vz_host_tlb_inv(vcpu, badvaddr);
}
/** * kvm_mips_migrate_count() - Migrate timer. * @vcpu: Virtual CPU. * * Migrate CP0_Count hrtimer to the current CPU by cancelling and restarting it * if it was running prior to being cancelled. * * Must be called when the VCPU is migrated to a different CPU to ensure that * timer expiry during guest execution interrupts the guest and causes the * interrupt to be delivered in a timely manner.
*/ staticvoid kvm_mips_migrate_count(struct kvm_vcpu *vcpu)
{ if (hrtimer_cancel(&vcpu->arch.comparecount_timer))
hrtimer_restart(&vcpu->arch.comparecount_timer);
}
/* Restore ASID once we are scheduled back after preemption */ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{ unsignedlong flags;
vcpu->cpu = cpu; if (vcpu->arch.last_sched_cpu != cpu) {
kvm_debug("[%d->%d]KVM VCPU[%d] switch\n",
vcpu->arch.last_sched_cpu, cpu, vcpu->vcpu_id); /* * Migrate the timer interrupt to the current CPU so that it * always interrupts the guest and synchronously triggers a * guest timer interrupt.
*/
kvm_mips_migrate_count(vcpu);
}
/* restore guest state to registers */
kvm_mips_callbacks->vcpu_load(vcpu, cpu);
local_irq_restore(flags);
}
/* ASID can change if another task is scheduled during preemption */ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{ unsignedlong flags; int cpu;
local_irq_save(flags);
cpu = smp_processor_id();
vcpu->arch.last_sched_cpu = cpu;
vcpu->cpu = -1;
/* save guest state in registers */
kvm_mips_callbacks->vcpu_put(vcpu, cpu);
local_irq_restore(flags);
}
Messung V0.5
¤ Dauer der Verarbeitung: 0.2 Sekunden
(vorverarbeitet)
¤
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.