Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Sat, 9 Feb 2019 19:57:31 -0500
From:   "Michael S. Tsirkin" <mst@redhat.com>
To:     Alexander Duyck <alexander.duyck@gmail.com>
Cc:     linux-mm@kvack.org, linux-kernel@vger.kernel.org,
        kvm@vger.kernel.org, rkrcmar@redhat.com,
        alexander.h.duyck@linux.intel.com, x86@kernel.org,
        mingo@redhat.com, bp@alien8.de, hpa@zytor.com, pbonzini@redhat.com,
        tglx@linutronix.de, akpm@linux-foundation.org
Subject: Re: [RFC PATCH 4/4] mm: Add merge page notifier
Message-ID: <20190209195325-mutt-send-email-mst@kernel.org>
References: <20190204181118.12095.38300.stgit@localhost.localdomain>
 <20190204181558.12095.83484.stgit@localhost.localdomain>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20190204181558.12095.83484.stgit@localhost.localdomain>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Mon, Feb 04, 2019 at 10:15:58AM -0800, Alexander Duyck wrote:
> From: Alexander Duyck <alexander.h.duyck@linux.intel.com>
> 
> Because the implementation was limiting itself to only providing hints on
> pages huge TLB order sized or larger we introduced the possibility for free
> pages to slip past us because they are freed as something less then
> huge TLB in size and aggregated with buddies later.
> 
> To address that I am adding a new call arch_merge_page which is called
> after __free_one_page has merged a pair of pages to create a higher order
> page. By doing this I am able to fill the gap and provide full coverage for
> all of the pages huge TLB order or larger.
> 
> Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>

Looks like this will be helpful whenever active free page
hints are added. So I think it's a good idea to
add a hook.

However, could you split adding the hook to a separate
patch from the KVM hypercall based implementation?

Then e.g. Nilal's patches could reuse it too.


> ---
>  arch/x86/include/asm/page.h |   12 ++++++++++++
>  arch/x86/kernel/kvm.c       |   28 ++++++++++++++++++++++++++++
>  include/linux/gfp.h         |    4 ++++
>  mm/page_alloc.c             |    2 ++
>  4 files changed, 46 insertions(+)
> 
> diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h
> index 4487ad7a3385..9540a97c9997 100644
> --- a/arch/x86/include/asm/page.h
> +++ b/arch/x86/include/asm/page.h
> @@ -29,6 +29,18 @@ static inline void arch_free_page(struct page *page, unsigned int order)
>  	if (static_branch_unlikely(&pv_free_page_hint_enabled))
>  		__arch_free_page(page, order);
>  }
> +
> +struct zone;
> +
> +#define HAVE_ARCH_MERGE_PAGE
> +void __arch_merge_page(struct zone *zone, struct page *page,
> +		       unsigned int order);
> +static inline void arch_merge_page(struct zone *zone, struct page *page,
> +				   unsigned int order)
> +{
> +	if (static_branch_unlikely(&pv_free_page_hint_enabled))
> +		__arch_merge_page(zone, page, order);
> +}
>  #endif
>  
>  #include <linux/range.h>
> diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
> index 09c91641c36c..957bb4f427bb 100644
> --- a/arch/x86/kernel/kvm.c
> +++ b/arch/x86/kernel/kvm.c
> @@ -785,6 +785,34 @@ void __arch_free_page(struct page *page, unsigned int order)
>  		       PAGE_SIZE << order);
>  }
>  
> +void __arch_merge_page(struct zone *zone, struct page *page,
> +		       unsigned int order)
> +{
> +	/*
> +	 * The merging logic has merged a set of buddies up to the
> +	 * KVM_PV_UNUSED_PAGE_HINT_MIN_ORDER. Since that is the case, take
> +	 * advantage of this moment to notify the hypervisor of the free
> +	 * memory.
> +	 */
> +	if (order != KVM_PV_UNUSED_PAGE_HINT_MIN_ORDER)
> +		return;
> +
> +	/*
> +	 * Drop zone lock while processing the hypercall. This
> +	 * should be safe as the page has not yet been added
> +	 * to the buddy list as of yet and all the pages that
> +	 * were merged have had their buddy/guard flags cleared
> +	 * and their order reset to 0.
> +	 */
> +	spin_unlock(&zone->lock);
> +
> +	kvm_hypercall2(KVM_HC_UNUSED_PAGE_HINT, page_to_phys(page),
> +		       PAGE_SIZE << order);
> +
> +	/* reacquire lock and resume freeing memory */
> +	spin_lock(&zone->lock);
> +}
> +
>  #ifdef CONFIG_PARAVIRT_SPINLOCKS
>  
>  /* Kick a cpu by its apicid. Used to wake up a halted vcpu */
> diff --git a/include/linux/gfp.h b/include/linux/gfp.h
> index fdab7de7490d..4746d5560193 100644
> --- a/include/linux/gfp.h
> +++ b/include/linux/gfp.h
> @@ -459,6 +459,10 @@ static inline struct zonelist *node_zonelist(int nid, gfp_t flags)
>  #ifndef HAVE_ARCH_FREE_PAGE
>  static inline void arch_free_page(struct page *page, int order) { }
>  #endif
> +#ifndef HAVE_ARCH_MERGE_PAGE
> +static inline void
> +arch_merge_page(struct zone *zone, struct page *page, int order) { }
> +#endif
>  #ifndef HAVE_ARCH_ALLOC_PAGE
>  static inline void arch_alloc_page(struct page *page, int order) { }
>  #endif
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index c954f8c1fbc4..7a1309b0b7c5 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -913,6 +913,8 @@ static inline void __free_one_page(struct page *page,
>  		page = page + (combined_pfn - pfn);
>  		pfn = combined_pfn;
>  		order++;
> +
> +		arch_merge_page(zone, page, order);
>  	}
>  	if (max_order < MAX_ORDER) {
>  		/* If we are here, it means order is >= pageblock_order.