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:   Mon, 13 Jan 2020 16:48:35 -0800 (PST)
From:   David Rientjes <rientjes@google.com>
To:     Mina Almasry <almasrymina@google.com>
cc:     mike.kravetz@oracle.com, shuah@kernel.org, shakeelb@google.com,
        gthelen@google.com, akpm@linux-foundation.org,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        linux-kselftest@vger.kernel.org, cgroups@vger.kernel.org,
        aneesh.kumar@linux.vnet.ibm.com, mkoutny@suse.com
Subject: Re: [PATCH v9 6/8] hugetlb_cgroup: support noreserve mappings
In-Reply-To: <20191217231615.164161-6-almasrymina@google.com>
Message-ID: <alpine.DEB.2.21.2001131646490.164268@chino.kir.corp.google.com>
References: <20191217231615.164161-1-almasrymina@google.com> <20191217231615.164161-6-almasrymina@google.com>
User-Agent: Alpine 2.21 (DEB 202 2017-01-01)
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Tue, 17 Dec 2019, Mina Almasry wrote:

> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index 39eb2fa53a420..3e94f5c2d7cd4 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -1367,6 +1367,9 @@ void free_huge_page(struct page *page)
>  	clear_page_huge_active(page);
>  	hugetlb_cgroup_uncharge_page(hstate_index(h), pages_per_huge_page(h),
>  				     page, false);
> +	hugetlb_cgroup_uncharge_page(hstate_index(h), pages_per_huge_page(h),
> +				     page, true);
> +
>  	if (restore_reserve)
>  		h->resv_huge_pages++;
> 
> @@ -2189,10 +2192,19 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
>  			gbl_chg = 1;
>  	}
> 
> +	/* If this allocation is not consuming a reservation, charge it now.
> +	 */
> +	if (map_chg || avoid_reserve || !vma_resv_map(vma)) {

These conditions are checked three times in this function, maybe better 
set a bool on the stack and use it throughout the function to guarantee it 
remains consistent?

bool deferred_reserve = !vma_resv_map(vma) || map_chg || avoid_reserve;

> +		ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h),
> +						   &h_cg, true);
> +		if (ret)
> +			goto out_subpool_put;
> +	}
> +
>  	ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg,
>  					   false);
>  	if (ret)
> -		goto out_subpool_put;
> +		goto out_uncharge_cgroup_reservation;
> 
>  	spin_lock(&hugetlb_lock);
>  	/*
> @@ -2216,6 +2228,14 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
>  	}
>  	hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, page,
>  				     false);
> +	/* If allocation is not consuming a reservation, also store the
> +	 * hugetlb_cgroup pointer on the page.
> +	 */
> +	if (!vma_resv_map(vma) || map_chg || avoid_reserve) {
> +		hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg,
> +					     page, true);
> +	}
> +
>  	spin_unlock(&hugetlb_lock);
> 
>  	set_page_private(page, (unsigned long)spool);
> @@ -2241,6 +2261,10 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
>  out_uncharge_cgroup:
>  	hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg,
>  				       false);
> +out_uncharge_cgroup_reservation:
> +	if (map_chg || avoid_reserve || !vma_resv_map(vma))
> +		hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h),
> +					       h_cg, true);
>  out_subpool_put:
>  	if (map_chg || avoid_reserve)
>  		hugepage_subpool_put_pages(spool, 1);
> --
> 2.24.1.735.g03f4e72817-goog
>