The patch titled
Subject: mm/hugetlb: compute/return the number of regions added by region_add()
has been added to the -mm tree. Its filename is
mm-hugetlb-compute-return-the-number-of-regions-added-by-region_add-v2.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-hugetlb-compute-return-the-number-of-regions-added-by-region_add-v2.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-hugetlb-compute-return-the-number-of-regions-added-by-region_add-v2.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Subject: mm/hugetlb: compute/return the number of regions added by region_add()
Signed-off-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Cc: Davidlohr Bueso <dave@xxxxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Luiz Capitulino <lcapitulino@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/hugetlb.c | 129 +++++++++++++++++++++++++++++++++++--------------
1 file changed, 93 insertions(+), 36 deletions(-)
diff -puN mm/hugetlb.c~mm-hugetlb-compute-return-the-number-of-regions-added-by-region_add-v2 mm/hugetlb.c
--- a/mm/hugetlb.c~mm-hugetlb-compute-return-the-number-of-regions-added-by-region_add-v2
+++ a/mm/hugetlb.c
@@ -217,8 +217,16 @@ static inline struct hugepage_subpool *s
* Region tracking -- allows tracking of reservations and instantiated pages
* across the pages in a mapping.
*
- * The region data structures are embedded into a resv_map and
- * protected by a resv_map's lock
+ * The region data structures are embedded into a resv_map and protected
+ * by a resv_map's lock. The set of regions within the resv_map represent
+ * reservations for huge pages, or huge pages that have already been
+ * instantiated within the map. The from and to elements are huge page
+ * indicies into the associated mapping. from indicates the starting index
+ * of the region. to represents the first index past the end of the region.
+ * For example, a file region structure with from == 0 and to == 4 represents
+ * four huge pages in a mapping. It is important to note that the to element
+ * represents the first element past the end of the region. This is used in
+ * arithmetic as 4(to) - 0(from) = 4 huge pages in the region.
*/
struct file_region {
struct list_head link;
@@ -226,11 +234,23 @@ struct file_region {
long to;
};
+/*
+ * Add the huge page range represented by indicies f (from)
+ * and t (to) to the reserve map. Existing regions will be
+ * expanded to accommodate the specified range. We know only
+ * existing regions need to be expanded, because region_add
+ * is only called after region_chg(with the same range). If
+ * a new file_region structure must be allocated, it is done
+ * in region_chg.
+ *
+ * Return the number of new huge pages added to the map. This
+ * number is greater than or equal to zero.
+ */
static long region_add(struct resv_map *resv, long f, long t)
{
struct list_head *head = &resv->regions;
struct file_region *rg, *nrg, *trg;
- long chg = 0;
+ long add = 0;
spin_lock(&resv->lock);
/* Locate the region we are either in or before. */
@@ -256,19 +276,44 @@ static long region_add(struct resv_map *
if (rg->to > t)
t = rg->to;
if (rg != nrg) {
- chg -= (rg->to - rg->from);
+ /* Decrement return value by the deleted range.
+ * Another range will span this area so that by
+ * end of routine add will be >= zero
+ */
+ add -= (rg->to - rg->from);
list_del(&rg->link);
kfree(rg);
}
}
- chg += (nrg->from - f);
+
+ add += (nrg->from - f); /* Added to beginning of region */
nrg->from = f;
- chg += t - nrg->to;
+ add += t - nrg->to; /* Added to end of region */
nrg->to = t;
+
spin_unlock(&resv->lock);
- return chg;
+ return add;
}
+/*
+ * Examine the existing reserve map and determine how many
+ * huge pages in the specified range (f, t) are NOT currently
+ * represented. This routine is called before a subsequent
+ * call to region_add that will actually modify the reserve
+ * map to add the specified range (f, t). region_chg does
+ * not change the number of huge pages represented by the
+ * map. However, if the existing regions in the map can not
+ * be expanded to represent the new range, a new file_region
+ * structure is added to the map as a placeholder. This is
+ * so that the subsequent region_add call will have all
+ * regions it needs and will not fail.
+ *
+ * Returns the number of huge pages that need to be added
+ * to the existing reservation map for the range (f, t).
+ * This number is greater or equal to zero. -ENOMEM is
+ * returned if a new file_region structure can not be
+ * allocated.
+ */
static long region_chg(struct resv_map *resv, long f, long t)
{
struct list_head *head = &resv->regions;
@@ -335,6 +380,11 @@ out_nrg:
return chg;
}
+/*
+ * Truncate the reserve map at index 'end'. Modify/truncate any
+ * region which contains end. Delete any regions past end.
+ * Return the number of huge pages removed from the map.
+ */
static long region_truncate(struct resv_map *resv, long end)
{
struct list_head *head = &resv->regions;
@@ -370,6 +420,10 @@ out:
return chg;
}
+/*
+ * Count and return the number of huge pages in the reserve map
+ * that intersect with the range (f, t).
+ */
static long region_count(struct resv_map *resv, long f, long t)
{
struct list_head *head = &resv->regions;
@@ -1426,53 +1480,56 @@ static void return_unused_surplus_pages(
}
/*
- * Determine if the huge page at addr within the vma has an associated
- * reservation. Where it does not we will need to logically increase
- * reservation and actually increase subpool usage before an allocation
- * can occur. Where any new reservation would be required the
- * reservation change is prepared, but not committed. Once the page
- * has been allocated from the subpool and instantiated the change should
- * be committed via vma_commit_reservation. No action is required on
- * failure.
+ * vma_needs_reservation and vma_commit_reservation are used by the huge
+ * page allocation routines to manage reservations.
+ *
+ * vma_needs_reservation is called to determine if the huge page at addr
+ * within the vma has an associated reservation. If a reservation is
+ * needed, the value 1 is returned. The caller is then responsible for
+ * managing the global reservation and subpool usage counts. After
+ * the huge page has been allocated, vma_commit_reservation is called
+ * to add the page to the reservation map.
+ *
+ * In the normal case, vma_commit_reservation should return the same value
+ * as the preceding vma_needs_reservation call. The only time this is
+ * not the case is if a reserve map was changed between calls. It is the
+ * responsibility of the caller to notice the difference and take appropriate
+ * action.
*/
-static long vma_needs_reservation(struct hstate *h,
- struct vm_area_struct *vma, unsigned long addr)
+static long __vma_reservation_common(struct hstate *h,
+ struct vm_area_struct *vma, unsigned long addr,
+ bool needs)
{
struct resv_map *resv;
pgoff_t idx;
- long chg;
+ long ret;
resv = vma_resv_map(vma);
if (!resv)
return 1;
idx = vma_hugecache_offset(h, vma, addr);
- chg = region_chg(resv, idx, idx + 1);
+ if (needs)
+ ret = region_chg(resv, idx, idx + 1);
+ else
+ ret = region_add(resv, idx, idx + 1);
if (vma->vm_flags & VM_MAYSHARE)
- return chg;
+ return ret;
else
- return chg < 0 ? chg : 0;
+ return ret < 0 ? ret : 0;
}
-static long vma_commit_reservation(struct hstate *h,
+static long vma_needs_reservation(struct hstate *h,
struct vm_area_struct *vma, unsigned long addr)
{
- struct resv_map *resv;
- pgoff_t idx;
- long add;
-
- resv = vma_resv_map(vma);
- if (!resv)
- return 1;
-
- idx = vma_hugecache_offset(h, vma, addr);
- add = region_add(resv, idx, idx + 1);
+ return __vma_reservation_common(h, vma, addr, (bool)1);
+}
- if (vma->vm_flags & VM_MAYSHARE)
- return add;
- else
- return 0;
+static long vma_commit_reservation(struct hstate *h,
+ struct vm_area_struct *vma, unsigned long addr)
+{
+ return __vma_reservation_common(h, vma, addr, (bool)0);
}
static struct page *alloc_huge_page(struct vm_area_struct *vma,
_
Patches currently in -mm which might be from mike.kravetz@xxxxxxxxxx are
hugetlb-do-not-account-hugetlb-pages-as-nr_file_pages.patch
mm-hugetlb-compute-return-the-number-of-regions-added-by-region_add.patch
mm-hugetlb-compute-return-the-number-of-regions-added-by-region_add-v2.patch
mm-hugetlb-handle-races-in-alloc_huge_page-and-hugetlb_reserve_pages.patch
mm-hugetlb-handle-races-in-alloc_huge_page-and-hugetlb_reserve_pages-v2.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
