On 09/10/2014 08:12 PM, Christoffer Dall wrote:
> On Tue, Aug 26, 2014 at 05:04:06PM -0700, Mario Smarduch wrote:
>> Patch adds support for initial write protection of VM memlsot. This patch series
>> assumes that huge PUDs will not be used in 2nd stage tables, which is awlays
>> valid on ARMv7.
>>
>> Signed-off-by: Mario Smarduch <m.smarduch@xxxxxxxxxxx>
>> ---
>> arch/arm/include/asm/kvm_host.h | 1 +
>> arch/arm/include/asm/kvm_mmu.h | 20 ++++++
>> arch/arm/include/asm/pgtable-3level.h | 1 +
>> arch/arm/kvm/arm.c | 9 +++
>> arch/arm/kvm/mmu.c | 128 ++++++++++++++++++++++++++++++++++
>> 5 files changed, 159 insertions(+)
>>
[...]
>> +
>> +/**
>> + * stage2_wp_pmd_range - write protect PMD range
>> + * @pud: pointer to pud entry
>> + * @addr: range start address
>> + * @end: range end address
>> + */
>> +static void stage2_wp_pmd_range(pud_t *pud, phys_addr_t addr, phys_addr_t end)
>> +{
>> + pmd_t *pmd;
>> + phys_addr_t next;
>> +
>> + pmd = pmd_offset(pud, addr);
>> +
>> + do {
>> + next = kvm_pmd_addr_end(addr, end);
>> + if (!pmd_none(*pmd)) {
>> + if (kvm_pmd_huge(*pmd)) {
>> + if (!kvm_s2pmd_readonly(pmd))
>> + kvm_set_s2pmd_readonly(pmd);
>> + } else {
>> + stage2_wp_pte_range(pmd, addr, next);
>> + }
>> + }
>> + } while (pmd++, addr = next, addr != end);
>> +}
>> +
>> +/**
>> + * stage2_wp_pud_range - write protect PUD range
>> + * @kvm: pointer to kvm structure
>> + * @pud: pointer to pgd entry
> pgd
>
>> + * @addr: range start address
>> + * @end: range end address
>> + *
>> + * While walking the PUD range huge PUD pages are ignored.
>> + */
>> +static void stage2_wp_pud_range(struct kvm *kvm, pgd_t *pgd,
>
> the naming of this function feels weird. You're write-protecting
> the puds covered by the range of a single PGD, so I would say,
> stage2_wp_puds(), or stage2_wp_pgd_range().
>
> [apologies if I suggested this specific naming]
>
> applies consecutively to the functions above.
Ok will update.
>
>> + phys_addr_t addr, phys_addr_t end)
>> +{
>> + pud_t *pud;
>> + phys_addr_t next;
>> +
>> + pud = pud_offset(pgd, addr);
>> + do {
>> + next = kvm_pud_addr_end(addr, end);
>> + /* TODO: PUD not supported, revisit later if implemented */
>> + BUG_ON(kvm_pud_huge(*pud));
>> + if (!pud_none(*pud))
>> + stage2_wp_pmd_range(pud, addr, next);
>> + } while (pud++, addr = next, addr != end);
>> +}
>> +
>> +/**
>> + * stage2_wp_range() - write protect stage2 memory region range
>> + * @kvm: The KVM pointer
>> + * @start: Start address of range
>
> the parameter is called addr
>
>> + * &end: End address of range
>> + */
>> +static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
>> +{
>> + pgd_t *pgd;
>> + phys_addr_t next;
>> +
>> + pgd = kvm->arch.pgd + pgd_index(addr);
>> + do {
>> + /*
>> + * Release kvm_mmu_lock periodically if the memory region is
>> + * large. Otherwise, we may see kernel panics with
>> + * CONFIG_DETECT_HUNG_TASK, CONFIG_LOCK_DETECTOR,
>> + * CONFIG_LOCK_DEP. Additionally, holding the lock too long
>> + * will also starve other vCPUs.
>> + */
>> + if (need_resched() || spin_needbreak(&kvm->mmu_lock))
>> + cond_resched_lock(&kvm->mmu_lock);
>> +
>> + next = kvm_pgd_addr_end(addr, end);
>> + if (pgd_present(*pgd))
>> + stage2_wp_pud_range(kvm, pgd, addr, next);
>> + } while (pgd++, addr = next, addr != end);
>> +}
>> +
>> +/**
>> + * kvm_mmu_wp_memory_region() - write protect stage 2 entries for memory slot
>> + * @kvm: The KVM pointer
>> + * @slot: The memory slot to write protect
>> + *
>> + * Called to start logging dirty pages after memory region
>> + * KVM_MEM_LOG_DIRTY_PAGES operation is called. After this function returns
>> + * all present PMD and PTEs are write protected in the memory region.
>> + * Afterwards read of dirty page log can be called.
>> + *
>> + * Acquires kvm_mmu_lock. Called with kvm->slots_lock mutex acquired,
>> + * serializing operations for VM memory regions.
>> + */
>> +
>> +void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot)
>> +{
>> + struct kvm_memory_slot *memslot = id_to_memslot(kvm->memslots, slot);
>> + phys_addr_t start = memslot->base_gfn << PAGE_SHIFT;
>> + phys_addr_t end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
>> +
>> + spin_lock(&kvm->mmu_lock);
>> + stage2_wp_range(kvm, start, end);
>> + kvm_flush_remote_tlbs(kvm);
>
> do you need to hold the lock while flushing the TLBs?
>
>> + spin_unlock(&kvm->mmu_lock);
>> +}
>> +#endif
>> +
>> static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
>> struct kvm_memory_slot *memslot,
>> unsigned long fault_status)
>> --
>> 1.8.3.2
>>
> Thanks,
> -Christoffer
>
_______________________________________________
kvmarm mailing list
kvmarm@xxxxxxxxxxxxxxxxxxxxx
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
