On Tue, Oct 25, 2022 at 11:13:42PM +0800,
Chao Peng <chao.p.peng@xxxxxxxxxxxxxxx> wrote:
> When private/shared memory are mixed in a large page, the lpage_info may
> not be accurate and should be updated with this mixed info. A large page
> has mixed pages can't be really mapped as large page since its
> private/shared pages are from different physical memory.
>
> Update lpage_info when private/shared memory attribute is changed. If
> both private and shared pages are within a large page region, it can't
> be mapped as large page. It's a bit challenge to track the mixed
> info in a 'count' like variable, this patch instead reserves a bit in
> 'disallow_lpage' to indicate a large page has mixed private/share pages.
>
> Signed-off-by: Chao Peng <chao.p.peng@xxxxxxxxxxxxxxx>
> ---
> arch/x86/include/asm/kvm_host.h | 8 +++
> arch/x86/kvm/mmu/mmu.c | 112 +++++++++++++++++++++++++++++++-
> arch/x86/kvm/x86.c | 2 +
> include/linux/kvm_host.h | 19 ++++++
> virt/kvm/kvm_main.c | 16 +++--
> 5 files changed, 152 insertions(+), 5 deletions(-)
>
...
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index 33b1aec44fb8..67a9823a8c35 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
...
> @@ -6910,3 +6915,108 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
> if (kvm->arch.nx_lpage_recovery_thread)
> kthread_stop(kvm->arch.nx_lpage_recovery_thread);
> }
> +
> +static inline bool linfo_is_mixed(struct kvm_lpage_info *linfo)
> +{
> + return linfo->disallow_lpage & KVM_LPAGE_PRIVATE_SHARED_MIXED;
> +}
> +
> +static inline void linfo_update_mixed(struct kvm_lpage_info *linfo, bool mixed)
> +{
> + if (mixed)
> + linfo->disallow_lpage |= KVM_LPAGE_PRIVATE_SHARED_MIXED;
> + else
> + linfo->disallow_lpage &= ~KVM_LPAGE_PRIVATE_SHARED_MIXED;
> +}
> +
> +static bool mem_attr_is_mixed_2m(struct kvm *kvm, unsigned int attr,
> + gfn_t start, gfn_t end)
> +{
> + XA_STATE(xas, &kvm->mem_attr_array, start);
> + gfn_t gfn = start;
> + void *entry;
> + bool shared = attr == KVM_MEM_ATTR_SHARED;
> + bool mixed = false;
> +
> + rcu_read_lock();
> + entry = xas_load(&xas);
> + while (gfn < end) {
> + if (xas_retry(&xas, entry))
> + continue;
> +
> + KVM_BUG_ON(gfn != xas.xa_index, kvm);
> +
> + if ((entry && !shared) || (!entry && shared)) {
> + mixed = true;
> + goto out;
nitpick: goto isn't needed. break should work.
> + }
> +
> + entry = xas_next(&xas);
> + gfn++;
> + }
> +out:
> + rcu_read_unlock();
> + return mixed;
> +}
> +
> +static bool mem_attr_is_mixed(struct kvm *kvm, struct kvm_memory_slot *slot,
> + int level, unsigned int attr,
> + gfn_t start, gfn_t end)
> +{
> + unsigned long gfn;
> + void *entry;
> +
> + if (level == PG_LEVEL_2M)
> + return mem_attr_is_mixed_2m(kvm, attr, start, end);
> +
> + entry = xa_load(&kvm->mem_attr_array, start);
> + for (gfn = start; gfn < end; gfn += KVM_PAGES_PER_HPAGE(level - 1)) {
> + if (linfo_is_mixed(lpage_info_slot(gfn, slot, level - 1)))
> + return true;
> + if (xa_load(&kvm->mem_attr_array, gfn) != entry)
> + return true;
> + }
> + return false;
> +}
> +
> +void kvm_arch_update_mem_attr(struct kvm *kvm, struct kvm_memory_slot *slot,
> + unsigned int attr, gfn_t start, gfn_t end)
> +{
> +
> + unsigned long lpage_start, lpage_end;
> + unsigned long gfn, pages, mask;
> + int level;
> +
> + WARN_ONCE(!(attr & (KVM_MEM_ATTR_PRIVATE | KVM_MEM_ATTR_SHARED)),
> + "Unsupported mem attribute.\n");
> +
> + /*
> + * The sequence matters here: we update the higher level basing on the
> + * lower level's scanning result.
> + */
> + for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) {
> + pages = KVM_PAGES_PER_HPAGE(level);
> + mask = ~(pages - 1);
nitpick: KVM_HPAGE_MASK(level). Maybe matter of preference.
> + lpage_start = max(start & mask, slot->base_gfn);
> + lpage_end = (end - 1) & mask;
> +
> + /*
> + * We only need to scan the head and tail page, for middle pages
> + * we know they are not mixed.
> + */
> + linfo_update_mixed(lpage_info_slot(lpage_start, slot, level),
> + mem_attr_is_mixed(kvm, slot, level, attr,
> + lpage_start, start));
> +
> + if (lpage_start == lpage_end)
> + return;
> +
> + for (gfn = lpage_start + pages; gfn < lpage_end; gfn += pages)
> + linfo_update_mixed(lpage_info_slot(gfn, slot, level),
> + false);
> +
> + linfo_update_mixed(lpage_info_slot(lpage_end, slot, level),
> + mem_attr_is_mixed(kvm, slot, level, attr,
> + end, lpage_end + pages));
> + }
> +}
--
Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
