Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755503Ab3HLWDP (ORCPT ); Mon, 12 Aug 2013 18:03:15 -0400 Received: from g1t0028.austin.hp.com ([15.216.28.35]:6885 "EHLO g1t0028.austin.hp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751797Ab3HLWDO (ORCPT ); Mon, 12 Aug 2013 18:03:14 -0400 Message-ID: <1376344985.13247.16.camel@buesod1.americas.hpqcorp.net> Subject: Re: [PATCH v2 09/20] mm, hugetlb: protect region tracking via newly introduced resv_map lock From: Davidlohr Bueso To: Joonsoo Kim Cc: Andrew Morton , Rik van Riel , Mel Gorman , Michal Hocko , "Aneesh Kumar K.V" , KAMEZAWA Hiroyuki , Hugh Dickins , Davidlohr Bueso , David Gibson , linux-mm@kvack.org, linux-kernel@vger.kernel.org, Joonsoo Kim , Wanpeng Li , Naoya Horiguchi , Hillf Danton Date: Mon, 12 Aug 2013 15:03:05 -0700 In-Reply-To: <1376040398-11212-10-git-send-email-iamjoonsoo.kim@lge.com> References: <1376040398-11212-1-git-send-email-iamjoonsoo.kim@lge.com> <1376040398-11212-10-git-send-email-iamjoonsoo.kim@lge.com> Content-Type: text/plain; charset="UTF-8" X-Mailer: Evolution 3.4.4 (3.4.4-2.fc17) Mime-Version: 1.0 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 6091 Lines: 196 On Fri, 2013-08-09 at 18:26 +0900, Joonsoo Kim wrote: > There is a race condition if we map a same file on different processes. > Region tracking is protected by mmap_sem and hugetlb_instantiation_mutex. > When we do mmap, we don't grab a hugetlb_instantiation_mutex, but, > grab a mmap_sem. This doesn't prevent other process to modify region > structure, so it can be modified by two processes concurrently. > > To solve this, I introduce a lock to resv_map and make region manipulation > function grab a lock before they do actual work. This makes region > tracking safe. > > Signed-off-by: Joonsoo Kim > > diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h > index 2677c07..e29e28f 100644 > --- a/include/linux/hugetlb.h > +++ b/include/linux/hugetlb.h > @@ -26,6 +26,7 @@ struct hugepage_subpool { > > struct resv_map { > struct kref refs; > + spinlock_t lock; > struct list_head regions; > }; > extern struct resv_map *resv_map_alloc(void); > diff --git a/mm/hugetlb.c b/mm/hugetlb.c > index d9cabf6..73034dd 100644 > --- a/mm/hugetlb.c > +++ b/mm/hugetlb.c > @@ -134,15 +134,8 @@ static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma) > * Region tracking -- allows tracking of reservations and instantiated pages > * across the pages in a mapping. > * > - * The region data structures are protected by a combination of the mmap_sem > - * and the hugetlb_instantiation_mutex. To access or modify a region the caller > - * must either hold the mmap_sem for write, or the mmap_sem for read and > - * the hugetlb_instantiation_mutex: > - * > - * down_write(&mm->mmap_sem); > - * or > - * down_read(&mm->mmap_sem); > - * mutex_lock(&hugetlb_instantiation_mutex); > + * The region data structures are embedded into a resv_map and > + * protected by a resv_map's lock > */ > struct file_region { > struct list_head link; > @@ -155,6 +148,7 @@ static long region_add(struct resv_map *resv, long f, long t) > struct list_head *head = &resv->regions; > struct file_region *rg, *nrg, *trg; > > + spin_lock(&resv->lock); > /* Locate the region we are either in or before. */ > list_for_each_entry(rg, head, link) > if (f <= rg->to) > @@ -184,15 +178,18 @@ static long region_add(struct resv_map *resv, long f, long t) > } > nrg->from = f; > nrg->to = t; > + spin_unlock(&resv->lock); > return 0; > } > > static long region_chg(struct resv_map *resv, long f, long t) > { > struct list_head *head = &resv->regions; > - struct file_region *rg, *nrg; > + struct file_region *rg, *nrg = NULL; > long chg = 0; > > +retry: > + spin_lock(&resv->lock); > /* Locate the region we are before or in. */ > list_for_each_entry(rg, head, link) > if (f <= rg->to) > @@ -202,15 +199,27 @@ static long region_chg(struct resv_map *resv, long f, long t) > * Subtle, allocate a new region at the position but make it zero > * size such that we can guarantee to record the reservation. */ > if (&rg->link == head || t < rg->from) { > - nrg = kmalloc(sizeof(*nrg), GFP_KERNEL); > - if (!nrg) > - return -ENOMEM; > + if (!nrg) { > + nrg = kmalloc(sizeof(*nrg), GFP_NOWAIT); > + if (!nrg) { > + spin_unlock(&resv->lock); > + nrg = kmalloc(sizeof(*nrg), GFP_KERNEL); > + if (!nrg) { > + chg = -ENOMEM; > + goto out; Just return -ENOMEM here. > + } > + goto retry; > + } > + } > + You seem to be right, at least in my workloads, the hold times for the region lock is quite small, so a spinlock is better than a sleeping lock. That said, this code is quite messy, but I cannot think of a better/cleaner approach right now. > nrg->from = f; > nrg->to = f; > INIT_LIST_HEAD(&nrg->link); > list_add(&nrg->link, rg->link.prev); > + nrg = NULL; > > - return t - f; > + chg = t - f; > + goto out_locked; > } > > /* Round our left edge to the current segment if it encloses us. */ > @@ -223,7 +232,7 @@ static long region_chg(struct resv_map *resv, long f, long t) > if (&rg->link == head) > break; > if (rg->from > t) > - return chg; > + goto out_locked; > > /* We overlap with this area, if it extends further than > * us then we must extend ourselves. Account for its > @@ -234,6 +243,11 @@ static long region_chg(struct resv_map *resv, long f, long t) > } > chg -= rg->to - rg->from; > } > + > +out_locked: > + spin_unlock(&resv->lock); > +out: > + kfree(nrg); > return chg; > } > > @@ -243,12 +257,13 @@ static long region_truncate(struct resv_map *resv, long end) > struct file_region *rg, *trg; > long chg = 0; > > + spin_lock(&resv->lock); > /* Locate the region we are either in or before. */ > list_for_each_entry(rg, head, link) > if (end <= rg->to) > break; > if (&rg->link == head) > - return 0; > + goto out; > > /* If we are in the middle of a region then adjust it. */ > if (end > rg->from) { > @@ -265,6 +280,9 @@ static long region_truncate(struct resv_map *resv, long end) > list_del(&rg->link); > kfree(rg); > } > + > +out: > + spin_unlock(&resv->lock); > return chg; > } > > @@ -274,6 +292,7 @@ static long region_count(struct resv_map *resv, long f, long t) > struct file_region *rg; > long chg = 0; > > + spin_lock(&resv->lock); > /* Locate each segment we overlap with, and count that overlap. */ > list_for_each_entry(rg, head, link) { > long seg_from; > @@ -289,6 +308,7 @@ static long region_count(struct resv_map *resv, long f, long t) > > chg += seg_to - seg_from; > } > + spin_unlock(&resv->lock); > > return chg; > } > @@ -386,6 +406,7 @@ struct resv_map *resv_map_alloc(void) > return NULL; > > kref_init(&resv_map->refs); > + spin_lock_init(&resv_map->lock); > INIT_LIST_HEAD(&resv_map->regions); > > return resv_map; -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/