Re: [PATCH v9 6/8] KVM: Update lpage info when private/shared memory are mixed

From: Isaku Yamahata <isaku.yamahata@gmail.com>
To: Chao Peng <chao.p.peng@linux.intel.com>
Cc: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-mm@kvack.org, linux-fsdevel@vger.kernel.org,
	linux-arch@vger.kernel.org, linux-api@vger.kernel.org,
	linux-doc@vger.kernel.org, qemu-devel@nongnu.org,
	Paolo Bonzini <pbonzini@redhat.com>,
	Jonathan Corbet <corbet@lwn.net>,
	Sean Christopherson <seanjc@google.com>,
	Vitaly Kuznetsov <vkuznets@redhat.com>,
	Wanpeng Li <wanpengli@tencent.com>,
	Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
	x86@kernel.org, "H . Peter Anvin" <hpa@zytor.com>,
	Hugh Dickins <hughd@google.com>, Jeff Layton <jlayton@kernel.org>,
	"J . Bruce Fields" <bfields@fieldses.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Shuah Khan <shuah@kernel.org>, Mike Rapoport <rppt@kernel.org>,
	Steven Price <steven.price@arm.com>,
	"Maciej S . Szmigiero" <mail@maciej.szmigiero.name>,
	Vlastimil Babka <vbabka@suse.cz>,
	Vishal Annapurve <vannapurve@google.com>,
	Yu Zhang <yu.c.zhang@linux.intel.com>,
	"Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
	luto@kernel.org, jun.nakajima@intel.com, dave.hansen@intel.com,
	ak@linux.intel.com, david@redhat.com, aarcange@redhat.com,
	ddutile@redhat.com, dhildenb@redhat.com,
	Quentin Perret <qperret@google.com>,
	tabba@google.com, Michael Roth <michael.roth@amd.com>,
	mhocko@suse.com, Muchun Song <songmuchun@bytedance.com>,
	wei.w.wang@intel.com, isaku.yamahata@gmail.com
Subject: Re: [PATCH v9 6/8] KVM: Update lpage info when private/shared memory are mixed
Date: Wed, 26 Oct 2022 13:46:20 -0700	[thread overview]
Message-ID: <20221026204620.GB3819453@ls.amr.corp.intel.com> (raw)
In-Reply-To: <20221025151344.3784230-7-chao.p.peng@linux.intel.com>

On Tue, Oct 25, 2022 at 11:13:42PM +0800,
Chao Peng <chao.p.peng@linux.intel.com> 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@linux.intel.com>
> ---
>  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@gmail.com>