| 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
| ||
|
Date: Thu, 23 Apr 2015 15:13:13 -0700
From: Mike Kravetz <mike.kravetz@...cle.com>
To: linux-mm@...ck.org, linux-kernel@...r.kernel.org
Cc: Dave Hansen <dave.hansen@...ux.intel.com>,
Naoya Horiguchi <n-horiguchi@...jp.nec.com>,
David Rientjes <rientjes@...gle.com>,
Hugh Dickins <hughd@...gle.com>,
Davidlohr Bueso <dave@...olabs.net>,
Aneesh Kumar <aneesh.kumar@...ux.vnet.ibm.com>,
Hillf Danton <hillf.zj@...baba-inc.com>,
Christoph Hellwig <hch@...radead.org>,
Mike Kravetz <mike.kravetz@...cle.com>
Subject: [RFC v2 PATCH 1/5] hugetlbfs: truncate_hugepages() takes a range of pages
Modify truncate_hugepages() to take a range of pages (start, end)
instead of simply start. If the value of end is -1, this indicates
the end of the range is the end of the file. This functionality
will be used for fallocate hole punching.
Downstream of truncate_hugepages, the routines hugetlb_unreserve_pages
must also be modified to accept a range of pages.
A new region tracking/resv_map routine region_del() is added to delete
a range of regions within the reserve maps. As in truncate_hugepages,
a range end value of -1 indicates all regions after the starting value
should be deleted.
Based-on code-by: Dave Hansen <dave.hansen@...ux.intel.com>
Signed-off-by: Mike Kravetz <mike.kravetz@...cle.com>
---
fs/hugetlbfs/inode.c | 31 +++++++++++++++-----
include/linux/hugetlb.h | 3 +-
mm/hugetlb.c | 76 +++++++++++++++++++++++++++++++++++++++++++++++--
3 files changed, 100 insertions(+), 10 deletions(-)
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index c274aca..2faf2c4 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -324,19 +324,32 @@ static void truncate_huge_page(struct page *page)
delete_from_page_cache(page);
}
-static void truncate_hugepages(struct inode *inode, loff_t lstart)
+static void truncate_hugepages(struct inode *inode, loff_t lstart, loff_t lend)
{
struct hstate *h = hstate_inode(inode);
struct address_space *mapping = &inode->i_data;
const pgoff_t start = lstart >> huge_page_shift(h);
+ const pgoff_t end = lend >> huge_page_shift(h);
struct pagevec pvec;
pgoff_t next;
int i, freed = 0;
+ long lookup_nr = PAGEVEC_SIZE;
pagevec_init(&pvec, 0);
next = start;
- while (1) {
- if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
+ while (next < end) {
+ /*
+ * Make sure to never grab more pages that we
+ * might possibly need.
+ */
+ if (end - next < lookup_nr)
+ lookup_nr = end - next;
+
+ /*
+ * This pagevec_lookup() may return pages past 'end',
+ * so we must check for page->index > end.
+ */
+ if (!pagevec_lookup(&pvec, mapping, next, lookup_nr)) {
if (next == start)
break;
next = start;
@@ -347,6 +360,11 @@ static void truncate_hugepages(struct inode *inode, loff_t lstart)
struct page *page = pvec.pages[i];
lock_page(page);
+ if (page->index >= end) {
+ unlock_page(page);
+ next = end; /* we are done */
+ break;
+ }
if (page->index > next)
next = page->index;
++next;
@@ -356,15 +374,14 @@ static void truncate_hugepages(struct inode *inode, loff_t lstart)
}
huge_pagevec_release(&pvec);
}
- BUG_ON(!lstart && mapping->nrpages);
- hugetlb_unreserve_pages(inode, start, freed);
+ hugetlb_unreserve_pages(inode, start, end, freed);
}
static void hugetlbfs_evict_inode(struct inode *inode)
{
struct resv_map *resv_map;
- truncate_hugepages(inode, 0);
+ truncate_hugepages(inode, 0, -1);
resv_map = (struct resv_map *)inode->i_mapping->private_data;
/* root inode doesn't have the resv_map, so we should check it */
if (resv_map)
@@ -410,7 +427,7 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset)
if (!RB_EMPTY_ROOT(&mapping->i_mmap))
hugetlb_vmtruncate_list(&mapping->i_mmap, pgoff);
i_mmap_unlock_write(mapping);
- truncate_hugepages(inode, offset);
+ truncate_hugepages(inode, offset, -1);
return 0;
}
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 7b57850..de39705 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -75,7 +75,8 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
int hugetlb_reserve_pages(struct inode *inode, long from, long to,
struct vm_area_struct *vma,
vm_flags_t vm_flags);
-void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed);
+void hugetlb_unreserve_pages(struct inode *inode, long start, long end,
+ long freed);
int dequeue_hwpoisoned_huge_page(struct page *page);
bool isolate_huge_page(struct page *page, struct list_head *list);
void putback_active_hugepage(struct page *page);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index c41b2a0..31e36cd 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -257,6 +257,77 @@ out_nrg:
return chg;
}
+static long region_del(struct resv_map *resv, long f, long t)
+{
+ struct list_head *head = &resv->regions;
+ struct file_region *rg, *trg;
+ struct file_region *nrg = NULL;
+ long chg = 0;
+
+ /*
+ * Locate segments we overlap and etiher split, remove or
+ * trim the existing regions. The end of region (t) == -1
+ * indicates all remaining regions. Special case t == -1 as
+ * all comparisons are signed.
+ */
+ if (t == -1)
+ t = LONG_MAX;
+retry:
+ spin_lock(&resv->lock);
+ list_for_each_entry_safe(rg, trg, head, link) {
+ if (rg->to <= f)
+ continue;
+ if (rg->from >= t)
+ break;
+
+ if (f > rg->from && t < rg->to) { /* must split region */
+ if (!nrg) {
+ spin_unlock(&resv->lock);
+ nrg = kmalloc(sizeof(*nrg),
+ GFP_KERNEL | __GFP_REPEAT);
+ if (!nrg) {
+ /* FIXME FIXME FIXME FIXME */
+ return -ENOMEM;
+ }
+ goto retry;
+ }
+
+ chg += t - f;
+
+ /* new entry for end of split region */
+ nrg->from = t;
+ nrg->to = rg->to;
+ INIT_LIST_HEAD(&nrg->link);
+
+ /* original entry is trimmed */
+ rg->to = f;
+
+ list_add(&nrg->link, &rg->link);
+ nrg = NULL;
+ break;
+ }
+
+ if (f <= rg->from && t >= rg->to) { /* remove entire region */
+ chg += rg->to - rg->from;
+ list_del(&rg->link);
+ kfree(rg);
+ continue;
+ }
+
+ if (f <= rg->from) { /* trim beginning of region */
+ chg += t - rg->from;
+ rg->from = t;
+ } else { /* trim end of region */
+ chg += rg->to - f;
+ rg->to = f;
+ }
+ }
+
+ spin_unlock(&resv->lock);
+ kfree(nrg);
+ return chg;
+}
+
static long region_truncate(struct resv_map *resv, long end)
{
struct list_head *head = &resv->regions;
@@ -3510,7 +3581,8 @@ out_err:
return ret;
}
-void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
+void hugetlb_unreserve_pages(struct inode *inode, long start, long end,
+ long freed)
{
struct hstate *h = hstate_inode(inode);
struct resv_map *resv_map = inode_resv_map(inode);
@@ -3518,7 +3590,7 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
struct hugepage_subpool *spool = subpool_inode(inode);
if (resv_map)
- chg = region_truncate(resv_map, offset);
+ chg = region_del(resv_map, start, end);
spin_lock(&inode->i_lock);
inode->i_blocks -= (blocks_per_huge_page(h) * freed);
spin_unlock(&inode->i_lock);
--
2.1.0
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists