aboutsummaryrefslogtreecommitdiffstats
path: root/include/linux/hugetlb.h
diff options
context:
space:
mode:
authorDavid Gibson <david@gibson.dropbear.id.au>2012-03-21 19:34:12 -0400
committerLinus Torvalds <torvalds@linux-foundation.org>2012-03-21 20:54:59 -0400
commit90481622d75715bfcb68501280a917dbfe516029 (patch)
tree63f7d9e4455366ab326ee74e6b39acf76b618fcf /include/linux/hugetlb.h
parenta1d776ee3147cec2a54a645e92eb2e3e2f65a137 (diff)
hugepages: fix use after free bug in "quota" handling
hugetlbfs_{get,put}_quota() are badly named. They don't interact with the general quota handling code, and they don't much resemble its behaviour. Rather than being about maintaining limits on on-disk block usage by particular users, they are instead about maintaining limits on in-memory page usage (including anonymous MAP_PRIVATE copied-on-write pages) associated with a particular hugetlbfs filesystem instance. Worse, they work by having callbacks to the hugetlbfs filesystem code from the low-level page handling code, in particular from free_huge_page(). This is a layering violation of itself, but more importantly, if the kernel does a get_user_pages() on hugepages (which can happen from KVM amongst others), then the free_huge_page() can be delayed until after the associated inode has already been freed. If an unmount occurs at the wrong time, even the hugetlbfs superblock where the "quota" limits are stored may have been freed. Andrew Barry proposed a patch to fix this by having hugepages, instead of storing a pointer to their address_space and reaching the superblock from there, had the hugepages store pointers directly to the superblock, bumping the reference count as appropriate to avoid it being freed. Andrew Morton rejected that version, however, on the grounds that it made the existing layering violation worse. This is a reworked version of Andrew's patch, which removes the extra, and some of the existing, layering violation. It works by introducing the concept of a hugepage "subpool" at the lower hugepage mm layer - that is a finite logical pool of hugepages to allocate from. hugetlbfs now creates a subpool for each filesystem instance with a page limit set, and a pointer to the subpool gets added to each allocated hugepage, instead of the address_space pointer used now. The subpool has its own lifetime and is only freed once all pages in it _and_ all other references to it (i.e. superblocks) are gone. subpools are optional - a NULL subpool pointer is taken by the code to mean that no subpool limits are in effect. Previous discussion of this bug found in: "Fix refcounting in hugetlbfs quota handling.". See: https://lkml.org/lkml/2011/8/11/28 or http://marc.info/?l=linux-mm&m=126928970510627&w=1 v2: Fixed a bug spotted by Hillf Danton, and removed the extra parameter to alloc_huge_page() - since it already takes the vma, it is not necessary. Signed-off-by: Andrew Barry <abarry@cray.com> Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Hillf Danton <dhillf@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'include/linux/hugetlb.h')
-rw-r--r--include/linux/hugetlb.h14
1 files changed, 10 insertions, 4 deletions
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 7adc4923e7ac..cf0181738c9e 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -14,6 +14,15 @@ struct user_struct;
14#include <linux/shm.h> 14#include <linux/shm.h>
15#include <asm/tlbflush.h> 15#include <asm/tlbflush.h>
16 16
17struct hugepage_subpool {
18 spinlock_t lock;
19 long count;
20 long max_hpages, used_hpages;
21};
22
23struct hugepage_subpool *hugepage_new_subpool(long nr_blocks);
24void hugepage_put_subpool(struct hugepage_subpool *spool);
25
17int PageHuge(struct page *page); 26int PageHuge(struct page *page);
18 27
19void reset_vma_resv_huge_pages(struct vm_area_struct *vma); 28void reset_vma_resv_huge_pages(struct vm_area_struct *vma);
@@ -129,12 +138,11 @@ enum {
129 138
130#ifdef CONFIG_HUGETLBFS 139#ifdef CONFIG_HUGETLBFS
131struct hugetlbfs_sb_info { 140struct hugetlbfs_sb_info {
132 long max_blocks; /* blocks allowed */
133 long free_blocks; /* blocks free */
134 long max_inodes; /* inodes allowed */ 141 long max_inodes; /* inodes allowed */
135 long free_inodes; /* inodes free */ 142 long free_inodes; /* inodes free */
136 spinlock_t stat_lock; 143 spinlock_t stat_lock;
137 struct hstate *hstate; 144 struct hstate *hstate;
145 struct hugepage_subpool *spool;
138}; 146};
139 147
140static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb) 148static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb)
@@ -146,8 +154,6 @@ extern const struct file_operations hugetlbfs_file_operations;
146extern const struct vm_operations_struct hugetlb_vm_ops; 154extern const struct vm_operations_struct hugetlb_vm_ops;
147struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct, 155struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct,
148 struct user_struct **user, int creat_flags); 156 struct user_struct **user, int creat_flags);
149int hugetlb_get_quota(struct address_space *mapping, long delta);
150void hugetlb_put_quota(struct address_space *mapping, long delta);
151 157
152static inline int is_file_hugepages(struct file *file) 158static inline int is_file_hugepages(struct file *file)
153{ 159{