@@ -243,6 +243,16 @@ struct file_region {
struct list_head link;
long from;
long to;
+#ifdef CONFIG_CGROUP_HUGETLB
+ /*
+ * On shared mappings, each reserved region appears as a struct
+ * file_region in resv_map. These fields hold the info needed to
+ * uncharge each reservation.
+ */
+ struct page_counter *reservation_counter;
+ unsigned long pages_per_hpage;
+ struct cgroup_subsys_state *css;
+#endif
};
/* Helper that removes a struct file_region from the resv_map cache and returns
@@ -266,6 +276,25 @@ get_file_region_entry_from_cache(struct resv_map *resv, long from, long to)
return nrg;
}
+/* Helper that records hugetlb_cgroup uncharge info. */
+static void record_hugetlb_cgroup_uncharge_info(struct hugetlb_cgroup *h_cg,
+ struct file_region *nrg,
+ struct hstate *h)
+{
+#ifdef CONFIG_CGROUP_HUGETLB
+ if (h_cg) {
+ nrg->reservation_counter =
+ &h_cg->reserved_hugepage[hstate_index(h)];
+ nrg->pages_per_hpage = pages_per_huge_page(h);
+ nrg->css = &h_cg->css;
+ } else {
+ nrg->reservation_counter = NULL;
+ nrg->pages_per_hpage = 0;
+ nrg->css = NULL;
+ }
+#endif
+}
+
/* Must be called with resv->lock held. Calling this with count_only == true
* will count the number of pages to be added but will not modify the linked
* list. If regions_needed != NULL and count_only == true, then regions_needed
@@ -273,7 +302,9 @@ get_file_region_entry_from_cache(struct resv_map *resv, long from, long to)
* add the regions for this range.
*/
static long add_reservation_in_range(struct resv_map *resv, long f, long t,
- long *regions_needed, bool count_only)
+ struct hugetlb_cgroup *h_cg,
+ struct hstate *h, long *regions_needed,
+ bool count_only)
{
long add = 0;
struct list_head *head = &resv->regions;
@@ -312,6 +343,8 @@ static long add_reservation_in_range(struct resv_map *resv, long f, long t,
if (!count_only) {
nrg = get_file_region_entry_from_cache(
resv, last_accounted_offset, rg->from);
+ record_hugetlb_cgroup_uncharge_info(h_cg, nrg,
+ h);
list_add(&nrg->link, rg->link.prev);
} else if (regions_needed)
*regions_needed += 1;
@@ -328,11 +361,13 @@ static long add_reservation_in_range(struct resv_map *resv, long f, long t,
if (!count_only) {
nrg = get_file_region_entry_from_cache(
resv, last_accounted_offset, t);
+ record_hugetlb_cgroup_uncharge_info(h_cg, nrg, h);
list_add(&nrg->link, rg->link.prev);
} else if (regions_needed)
*regions_needed += 1;
}
+ VM_BUG_ON(add < 0);
return add;
}
@@ -353,7 +388,8 @@ static long add_reservation_in_range(struct resv_map *resv, long f, long t,
* fail; region_chg will always allocate at least 1 entry and a region_add for
* 1 page will only require at most 1 entry.
*/
-static long region_add(struct resv_map *resv, long f, long t,
+static long region_add(struct hstate *h, struct hugetlb_cgroup *h_cg,
+ struct resv_map *resv, long f, long t,
long in_regions_needed)
{
long add = 0, actual_regions_needed = 0, i = 0;
@@ -366,7 +402,8 @@ static long region_add(struct resv_map *resv, long f, long t,
retry:
/* Count how many regions are actually needed to execute this add. */
- add_reservation_in_range(resv, f, t, &actual_regions_needed, true);
+ add_reservation_in_range(resv, f, t, NULL, NULL, &actual_regions_needed,
+ true);
/*
* Check for sufficient descriptors in the cache to accommodate
@@ -404,7 +441,7 @@ static long region_add(struct resv_map *resv, long f, long t,
goto retry;
}
- add = add_reservation_in_range(resv, f, t, NULL, false);
+ add = add_reservation_in_range(resv, f, t, h_cg, h, NULL, false);
resv->adds_in_progress -= in_regions_needed;
@@ -452,7 +489,8 @@ static long region_chg(struct resv_map *resv, long f, long t,
spin_lock(&resv->lock);
/* Count how many hugepages in this range are NOT respresented. */
- chg = add_reservation_in_range(resv, f, t, out_regions_needed, true);
+ chg = add_reservation_in_range(resv, f, t, NULL, NULL,
+ out_regions_needed, true);
if (*out_regions_needed == 0)
*out_regions_needed = 1;
@@ -524,6 +562,29 @@ static void region_abort(struct resv_map *resv, long f, long t,
spin_unlock(&resv->lock);
}
+static void uncharge_cgroup_if_shared_mapping(struct resv_map *resv,
+ struct file_region *rg,
+ unsigned long nr_pages)
+{
+#ifdef CONFIG_CGROUP_HUGETLB
+ /*
+ * If resv->reservation_counter is NULL, then this is either a shared
+ * reservation, or cgroup charging is disabled on this resv_map.
+ *
+ * If the cgroup charging is disabled, then rg->reservation_counter is
+ * NULL and the uncharge counter call is a no-op. If the mapping is
+ * shared then the reserved memory is tracked in the file_struct
+ * entries inside of resv_map. So we need to uncharge the memory here.
+ */
+ if (rg->reservation_counter && rg->pages_per_hpage && nr_pages > 0 &&
+ !resv->reservation_counter) {
+ hugetlb_cgroup_uncharge_counter(rg->reservation_counter,
+ nr_pages * rg->pages_per_hpage,
+ rg->css);
+ }
+#endif
+}
+
/*
* Delete the specified range [f, t) from the reserve map. If the
* t parameter is LONG_MAX, this indicates that ALL regions after f
@@ -588,11 +649,22 @@ static long region_del(struct resv_map *resv, long f, long t)
/* New entry for end of split region */
nrg->from = t;
nrg->to = rg->to;
+
+#ifdef CONFIG_CGROUP_HUGETLB
+ nrg->reservation_counter = rg->reservation_counter;
+ nrg->pages_per_hpage = rg->pages_per_hpage;
+ nrg->css = rg->css;
+ css_get(rg->css);
+#endif
+
INIT_LIST_HEAD(&nrg->link);
/* Original entry is trimmed */
rg->to = f;
+ uncharge_cgroup_if_shared_mapping(resv, rg,
+ nrg->to - nrg->from);
+
list_add(&nrg->link, &rg->link);
nrg = NULL;
break;
@@ -600,6 +672,8 @@ static long region_del(struct resv_map *resv, long f, long t)
if (f <= rg->from && t >= rg->to) { /* Remove entire region */
del += rg->to - rg->from;
+ uncharge_cgroup_if_shared_mapping(resv, rg,
+ rg->to - rg->from);
list_del(&rg->link);
kfree(rg);
continue;
@@ -608,14 +682,20 @@ static long region_del(struct resv_map *resv, long f, long t)
if (f <= rg->from) { /* Trim beginning of region */
del += t - rg->from;
rg->from = t;
+
+ uncharge_cgroup_if_shared_mapping(resv, rg,
+ t - rg->from);
} else { /* Trim end of region */
del += rg->to - f;
rg->to = f;
+
+ uncharge_cgroup_if_shared_mapping(resv, rg, rg->to - f);
}
}
spin_unlock(&resv->lock);
kfree(nrg);
+
return del;
}
@@ -2002,7 +2082,7 @@ static long __vma_reservation_common(struct hstate *h,
VM_BUG_ON(dummy_out_regions_needed != 1);
break;
case VMA_COMMIT_RESV:
- ret = region_add(resv, idx, idx + 1, 1);
+ ret = region_add(NULL, NULL, resv, idx, idx + 1, 1);
/* region_add calls of range 1 should never fail. */
VM_BUG_ON(ret < 0);
break;
@@ -2012,7 +2092,7 @@ static long __vma_reservation_common(struct hstate *h,
break;
case VMA_ADD_RESV:
if (vma->vm_flags & VM_MAYSHARE) {
- ret = region_add(resv, idx, idx + 1, 1);
+ ret = region_add(NULL, NULL, resv, idx, idx + 1, 1);
/* region_add calls of range 1 should never fail. */
VM_BUG_ON(ret < 0);
} else {
@@ -4679,7 +4759,7 @@ int hugetlb_reserve_pages(struct inode *inode,
struct hstate *h = hstate_inode(inode);
struct hugepage_subpool *spool = subpool_inode(inode);
struct resv_map *resv_map;
- struct hugetlb_cgroup *h_cg;
+ struct hugetlb_cgroup *h_cg = NULL;
long gbl_reserve, regions_needed = 0;
/* This should never happen */
@@ -4720,23 +4800,6 @@ int hugetlb_reserve_pages(struct inode *inode,
chg = to - from;
- if (hugetlb_cgroup_charge_cgroup(hstate_index(h),
- chg * pages_per_huge_page(h),
- &h_cg, true)) {
- kref_put(&resv_map->refs, resv_map_release);
- return -ENOMEM;
- }
-
-#ifdef CONFIG_CGROUP_HUGETLB
- /*
- * Since this branch handles private mappings, we attach the
- * counter to uncharge for this reservation off resv_map.
- */
- resv_map->reservation_counter =
- &h_cg->reserved_hugepage[hstate_index(h)];
- resv_map->pages_per_hpage = pages_per_huge_page(h);
-#endif
-
set_vma_resv_map(vma, resv_map);
set_vma_resv_flags(vma, HPAGE_RESV_OWNER);
}
@@ -4746,6 +4809,26 @@ int hugetlb_reserve_pages(struct inode *inode,
goto out_err;
}
+ ret = hugetlb_cgroup_charge_cgroup(
+ hstate_index(h), chg * pages_per_huge_page(h), &h_cg, true);
+
+ if (ret < 0) {
+ ret = -ENOMEM;
+ goto out_err;
+ }
+
+#ifdef CONFIG_CGROUP_HUGETLB
+ if (vma && !(vma->vm_flags & VM_MAYSHARE) && h_cg) {
+ /* For private mappings, the hugetlb_cgroup uncharge info hangs
+ * of the resv_map.
+ */
+ resv_map->reservation_counter =
+ &h_cg->reserved_hugepage[hstate_index(h)];
+ resv_map->pages_per_hpage = pages_per_huge_page(h);
+ resv_map->css = &h_cg->css;
+ }
+#endif
+
/*
* There must be enough pages in the subpool for the mapping. If
* the subpool has a minimum size, there may be some global
@@ -4754,7 +4837,7 @@ int hugetlb_reserve_pages(struct inode *inode,
gbl_reserve = hugepage_subpool_get_pages(spool, chg);
if (gbl_reserve < 0) {
ret = -ENOSPC;
- goto out_err;
+ goto out_uncharge_cgroup;
}
/*
@@ -4763,9 +4846,7 @@ int hugetlb_reserve_pages(struct inode *inode,
*/
ret = hugetlb_acct_memory(h, gbl_reserve);
if (ret < 0) {
- /* put back original number of pages, chg */
- (void)hugepage_subpool_put_pages(spool, chg);
- goto out_err;
+ goto out_put_pages;
}
/*
@@ -4780,7 +4861,7 @@ int hugetlb_reserve_pages(struct inode *inode,
* else has to be done for private mappings here
*/
if (!vma || vma->vm_flags & VM_MAYSHARE) {
- add = region_add(resv_map, from, to, regions_needed);
+ add = region_add(h, h_cg, resv_map, from, to, regions_needed);
if (unlikely(add < 0)) {
hugetlb_acct_memory(h, -gbl_reserve);
@@ -4797,12 +4878,23 @@ int hugetlb_reserve_pages(struct inode *inode,
*/
long rsv_adjust;
- rsv_adjust = hugepage_subpool_put_pages(spool,
- chg - add);
+ hugetlb_cgroup_uncharge_cgroup(
+ hstate_index(h),
+ (chg - add) * pages_per_huge_page(h), h_cg,
+ true);
+
+ rsv_adjust =
+ hugepage_subpool_put_pages(spool, chg - add);
hugetlb_acct_memory(h, -rsv_adjust);
}
}
return 0;
+out_put_pages:
+ /* put back original number of pages, chg */
+ (void)hugepage_subpool_put_pages(spool, chg);
+out_uncharge_cgroup:
+ hugetlb_cgroup_uncharge_cgroup(
+ hstate_index(h), chg * pages_per_huge_page(h), h_cg, true);
out_err:
if (!vma || vma->vm_flags & VM_MAYSHARE)
/* Only call region_abort if the region_chg succeeded but the
For shared mappings, the pointer to the hugetlb_cgroup to uncharge lives in the resv_map entries, in file_region->reservation_counter. After a call to region_chg, we charge the approprate hugetlb_cgroup, and if successful, we pass on the hugetlb_cgroup info to a follow up region_add call. When a file_region entry is added to the resv_map via region_add, we put the pointer to that cgroup in file_region->reservation_counter. If charging doesn't succeed, we report the error to the caller, so that the kernel fails the reservation. On region_del, which is when the hugetlb memory is unreserved, we also uncharge the file_region->reservation_counter. Signed-off-by: Mina Almasry <almasrymina@google.com> --- Changes in v10: - Deleted duplicated code snippet. Changes in V9: - Updated for hugetlb reservation repareting. --- mm/hugetlb.c | 156 ++++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 124 insertions(+), 32 deletions(-) -- 2.25.0.rc1.283.g88dfdc4193-goog