linux-kernel - Re: [PATCH 23/31] huge tmpfs recovery: framework for reconstituting huge pages

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Wed, 6 Apr 2016 13:28:34 +0300
From:	Mika Penttilä <mika.penttila@...tfour.com>
To:	Hugh Dickins <hughd@...gle.com>,
	Andrew Morton <akpm@...ux-foundation.org>
CC:	"Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>,
	Andrea Arcangeli <aarcange@...hat.com>,
	Andres Lagar-Cavilla <andreslc@...gle.com>,
	Yang Shi <yang.shi@...aro.org>, Ning Qu <quning@...il.com>,
	<linux-kernel@...r.kernel.org>, <linux-mm@...ck.org>
Subject: Re: [PATCH 23/31] huge tmpfs recovery: framework for reconstituting
 huge pages

On 04/06/2016 12:53 AM, Hugh Dickins wrote:



> +static void shmem_recovery_work(struct work_struct *work)
> +{
> +	struct recovery *recovery;
> +	struct shmem_inode_info *info;
> +	struct address_space *mapping;
> +	struct page *page;
> +	struct page *head = NULL;
> +	int error = -ENOENT;
> +
> +	recovery = container_of(work, struct recovery, work);
> +	info = SHMEM_I(recovery->inode);
> +	if (!shmem_work_still_useful(recovery)) {
> +		shr_stats(work_too_late);
> +		goto out;
> +	}
> +
> +	/* Are we resuming from an earlier partially successful attempt? */
> +	mapping = recovery->inode->i_mapping;
> +	spin_lock_irq(&mapping->tree_lock);
> +	page = shmem_clear_tag_hugehole(mapping, recovery->head_index);
> +	if (page)
> +		head = team_head(page);
> +	spin_unlock_irq(&mapping->tree_lock);
> +	if (head) {
> +		/* Serialize with shrinker so it won't mess with our range */
> +		spin_lock(&shmem_shrinklist_lock);
> +		spin_unlock(&shmem_shrinklist_lock);
> +	}
> +
> +	/* If team is now complete, no tag and head would be found above */
> +	page = recovery->page;
> +	if (PageTeam(page))
> +		head = team_head(page);
> +
> +	/* Get a reference to the head of the team already being assembled */
> +	if (head) {
> +		if (!get_page_unless_zero(head))
> +			head = NULL;
> +		else if (!PageTeam(head) || head->mapping != mapping ||
> +				head->index != recovery->head_index) {
> +			put_page(head);
> +			head = NULL;
> +		}
> +	}
> +
> +	if (head) {
> +		/* We are resuming work from a previous partial recovery */
> +		if (PageTeam(page))
> +			shr_stats(resume_teamed);
> +		else
> +			shr_stats(resume_tagged);
> +	} else {
> +		gfp_t gfp = mapping_gfp_mask(mapping);
> +		/*
> +		 * XXX: Note that with swapin readahead, page_to_nid(page) will
> +		 * often choose an unsuitable NUMA node: something to fix soon,
> +		 * but not an immediate blocker.
> +		 */
> +		head = __alloc_pages_node(page_to_nid(page),
> +			gfp | __GFP_NOWARN | __GFP_THISNODE, HPAGE_PMD_ORDER);   
> +		if (!head) {
> +			shr_stats(huge_failed);
> +			error = -ENOMEM;
> +			goto out;
> +		}

Should this head marked PageTeam? Because in patch 27/31 when given as a hint to shmem_getpage_gfp() :

 		hugehint = NULL;
+		if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
+		    sgp == SGP_TEAM && *pagep) {
+			struct page *head;
+
+			if (!get_page_unless_zero(*pagep)) {
+				error = -ENOENT;
+				goto decused;
+			}
+			page = *pagep;
+			lock_page(page);
+			head = page - (index & (HPAGE_PMD_NR-1));     

we fail always because :
+			if (!PageTeam(head)) {
+				error = -ENOENT;
+				goto decused;
+			}


> +		if (!shmem_work_still_useful(recovery)) {
> +			__free_pages(head, HPAGE_PMD_ORDER);
> +			shr_stats(huge_too_late);
> +			goto out;
> +		}
> +		split_page(head, HPAGE_PMD_ORDER);
> +		get_page(head);
> +		shr_stats(huge_alloced);
> +	}


Thanks,
Mika