From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-ob0-f181.google.com (mail-ob0-f181.google.com [209.85.214.181]) by kanga.kvack.org (Postfix) with ESMTP id 2DC016B0038 for ; Fri, 31 Jan 2014 12:37:04 -0500 (EST) Received: by mail-ob0-f181.google.com with SMTP id va2so5204811obc.26 for ; Fri, 31 Jan 2014 09:37:03 -0800 (PST) Received: from g1t0029.austin.hp.com (g1t0029.austin.hp.com. [15.216.28.36]) by mx.google.com with ESMTPS id tb9si5184276obc.147.2014.01.31.09.37.03 for (version=TLSv1 cipher=RC4-SHA bits=128/128); Fri, 31 Jan 2014 09:37:03 -0800 (PST) From: Davidlohr Bueso Subject: [PATCH v2 3/6] mm, hugetlb: fix race in region tracking Date: Fri, 31 Jan 2014 09:36:43 -0800 Message-Id: <1391189806-13319-4-git-send-email-davidlohr@hp.com> In-Reply-To: <1391189806-13319-1-git-send-email-davidlohr@hp.com> References: <1391189806-13319-1-git-send-email-davidlohr@hp.com> Sender: owner-linux-mm@kvack.org List-ID: To: akpm@linux-foundation.org, iamjoonsoo.kim@lge.com Cc: riel@redhat.com, mgorman@suse.de, mhocko@suse.cz, aneesh.kumar@linux.vnet.ibm.com, kamezawa.hiroyu@jp.fujitsu.com, hughd@google.com, david@gibson.dropbear.id.au, js1304@gmail.com, liwanp@linux.vnet.ibm.com, n-horiguchi@ah.jp.nec.com, dhillf@gmail.com, rientjes@google.com, davidlohr@hp.com, aswin@hp.com, scott.norton@hp.com, linux-mm@kvack.org, linux-kernel@vger.kernel.org From: Davidlohr Bueso 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 only the, mmap_sem (exclusively). This doesn't prevent other tasks from modifying the region structure, so it can be modified by two processes concurrently. To solve this, introduce a spinlock to resv_map and make region manipulation function grab it before they do actual work. Acked-by: David Gibson Suggested-by: Joonsoo Kim Signed-off-by: Davidlohr Bueso Signed-off-by: Joonsoo Kim --- include/linux/hugetlb.h | 1 + mm/hugetlb.c | 58 ++++++++++++++++++++++++++++++++----------------- 2 files changed, 39 insertions(+), 20 deletions(-) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index f62c2f6..5b337cf 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -27,6 +27,7 @@ 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 dca03a6..3c03c7f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -135,15 +135,8 @@ 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; @@ -156,6 +149,7 @@ 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) @@ -185,15 +179,18 @@ 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) @@ -203,15 +200,21 @@ 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; - nrg->from = f; - nrg->to = f; - INIT_LIST_HEAD(&nrg->link); - list_add(&nrg->link, rg->link.prev); + if (!nrg) { + spin_unlock(&resv->lock); + nrg = kmalloc(sizeof(*nrg), GFP_KERNEL); + if (!nrg) + return -ENOMEM; + + nrg->from = f; + nrg->to = f; + INIT_LIST_HEAD(&nrg->link); + goto retry; + } - return t - f; + list_add(&nrg->link, rg->link.prev); + chg = t - f; + goto out_nrg; } /* Round our left edge to the current segment if it encloses us. */ @@ -224,7 +227,7 @@ 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; /* We overlap with this area, if it extends further than * us then we must extend ourselves. Account for its @@ -235,6 +238,14 @@ static long region_chg(struct resv_map *resv, long f, long t) } chg -= rg->to - rg->from; } + +out: + spin_unlock(&resv->lock); + /* We already know we raced and no longer need the new region */ + kfree(nrg); + return chg; +out_nrg: + spin_unlock(&resv->lock); return chg; } @@ -244,12 +255,13 @@ 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) { @@ -266,6 +278,9 @@ static long region_truncate(struct resv_map *resv, long end) list_del(&rg->link); kfree(rg); } + +out: + spin_unlock(&resv->lock); return chg; } @@ -275,6 +290,7 @@ 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; @@ -290,6 +306,7 @@ static long region_count(struct resv_map *resv, long f, long t) chg += seg_to - seg_from; } + spin_unlock(&resv->lock); return chg; } @@ -387,6 +404,7 @@ 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; -- 1.8.1.4 -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org