The patch titled
Subject: hugetlb_cgroup: add accounting for shared mappings
has been added to the -mm tree. Its filename is
hugetlb_cgroup-add-accounting-for-shared-mappings.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/hugetlb_cgroup-add-accounting-for-shared-mappings.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/hugetlb_cgroup-add-accounting-for-shared-mappings.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/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Mina Almasry <almasrymina@xxxxxxxxxx>
Subject: hugetlb_cgroup: add accounting for shared mappings
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.
Link: http://lkml.kernel.org/r/20200211213128.73302-5-almasrymina@xxxxxxxxxx
Signed-off-by: Mina Almasry <almasrymina@xxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Greg Thelen <gthelen@xxxxxxxxxx>
Cc: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: Sandipan Das <sandipan@xxxxxxxxxxxxx>
Cc: Shakeel Butt <shakeelb@xxxxxxxxxx>
Cc: Shuah Khan <shuah@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/hugetlb.h | 35 +++++++
include/linux/hugetlb_cgroup.h | 10 ++
mm/hugetlb.c | 148 +++++++++++++++++++------------
mm/hugetlb_cgroup.c | 15 +++
4 files changed, 154 insertions(+), 54 deletions(-)
--- a/include/linux/hugetlb_cgroup.h~hugetlb_cgroup-add-accounting-for-shared-mappings
+++ a/include/linux/hugetlb_cgroup.h
@@ -133,11 +133,21 @@ extern void hugetlb_cgroup_uncharge_coun
unsigned long start,
unsigned long end);
+extern void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv,
+ struct file_region *rg,
+ unsigned long nr_pages);
+
extern void hugetlb_cgroup_file_init(void) __init;
extern void hugetlb_cgroup_migrate(struct page *oldhpage,
struct page *newhpage);
#else
+static inline void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv,
+ struct file_region *rg,
+ unsigned long nr_pages)
+{
+}
+
static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page)
{
return NULL;
--- a/include/linux/hugetlb.h~hugetlb_cgroup-add-accounting-for-shared-mappings
+++ a/include/linux/hugetlb.h
@@ -57,6 +57,41 @@ struct resv_map {
struct cgroup_subsys_state *css;
#endif
};
+
+/*
+ * 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 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.
+ *
+ * Interval notation of the form [from, to) will be used to indicate that
+ * the endpoint from is inclusive and to is exclusive.
+ */
+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;
+ struct cgroup_subsys_state *css;
+#endif
+};
+
extern struct resv_map *resv_map_alloc(void);
void resv_map_release(struct kref *ref);
--- a/mm/hugetlb.c~hugetlb_cgroup-add-accounting-for-shared-mappings
+++ a/mm/hugetlb.c
@@ -220,31 +220,6 @@ static inline struct hugepage_subpool *s
return subpool_inode(file_inode(vma->vm_file));
}
-/*
- * 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 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.
- *
- * Interval notation of the form [from, to) will be used to indicate that
- * the endpoint from is inclusive and to is exclusive.
- */
-struct file_region {
- struct list_head link;
- long from;
- long to;
-};
-
/* Helper that removes a struct file_region from the resv_map cache and returns
* it for use.
*/
@@ -266,6 +241,41 @@ get_file_region_entry_from_cache(struct
return nrg;
}
+static void copy_hugetlb_cgroup_uncharge_info(struct file_region *nrg,
+ struct file_region *rg)
+{
+#ifdef CONFIG_CGROUP_HUGETLB
+ nrg->reservation_counter = rg->reservation_counter;
+ nrg->css = rg->css;
+ if (rg->css)
+ css_get(rg->css);
+#endif
+}
+
+/* Helper that records hugetlb_cgroup uncharge info. */
+static void record_hugetlb_cgroup_uncharge_info(struct hugetlb_cgroup *h_cg,
+ struct hstate *h,
+ struct resv_map *resv,
+ struct file_region *nrg)
+{
+#ifdef CONFIG_CGROUP_HUGETLB
+ if (h_cg) {
+ nrg->reservation_counter =
+ &h_cg->rsvd_hugepage[hstate_index(h)];
+ nrg->css = &h_cg->css;
+ if (!resv->pages_per_hpage)
+ resv->pages_per_hpage = pages_per_huge_page(h);
+ /* pages_per_hpage should be the same for all entries in
+ * a resv_map.
+ */
+ VM_BUG_ON(resv->pages_per_hpage != pages_per_huge_page(h));
+ } else {
+ nrg->reservation_counter = NULL;
+ 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 +283,9 @@ get_file_region_entry_from_cache(struct
* 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 +324,8 @@ static long add_reservation_in_range(str
if (!count_only) {
nrg = get_file_region_entry_from_cache(
resv, last_accounted_offset, rg->from);
+ record_hugetlb_cgroup_uncharge_info(h_cg, h,
+ resv, nrg);
list_add(&nrg->link, rg->link.prev);
} else if (regions_needed)
*regions_needed += 1;
@@ -328,6 +342,7 @@ static long add_reservation_in_range(str
if (!count_only) {
nrg = get_file_region_entry_from_cache(
resv, last_accounted_offset, t);
+ record_hugetlb_cgroup_uncharge_info(h_cg, h, resv, nrg);
list_add(&nrg->link, rg->link.prev);
} else if (regions_needed)
*regions_needed += 1;
@@ -355,7 +370,8 @@ static long add_reservation_in_range(str
* 1 page will only require at most 1 entry.
*/
static long region_add(struct resv_map *resv, long f, long t,
- long in_regions_needed)
+ long in_regions_needed, struct hstate *h,
+ struct hugetlb_cgroup *h_cg)
{
long add = 0, actual_regions_needed = 0, i = 0;
struct file_region *trg = NULL, *rg = NULL;
@@ -367,7 +383,8 @@ static long region_add(struct resv_map *
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
@@ -405,7 +422,7 @@ retry:
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;
@@ -453,7 +470,8 @@ static long region_chg(struct resv_map *
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;
@@ -589,11 +607,17 @@ retry:
/* New entry for end of split region */
nrg->from = t;
nrg->to = rg->to;
+
+ copy_hugetlb_cgroup_uncharge_info(nrg, rg);
+
INIT_LIST_HEAD(&nrg->link);
/* Original entry is trimmed */
rg->to = f;
+ hugetlb_cgroup_uncharge_file_region(
+ resv, rg, nrg->to - nrg->from);
+
list_add(&nrg->link, &rg->link);
nrg = NULL;
break;
@@ -601,6 +625,8 @@ retry:
if (f <= rg->from && t >= rg->to) { /* Remove entire region */
del += rg->to - rg->from;
+ hugetlb_cgroup_uncharge_file_region(resv, rg,
+ rg->to - rg->from);
list_del(&rg->link);
kfree(rg);
continue;
@@ -609,9 +635,15 @@ retry:
if (f <= rg->from) { /* Trim beginning of region */
del += t - rg->from;
rg->from = t;
+
+ hugetlb_cgroup_uncharge_file_region(resv, rg,
+ t - rg->from);
} else { /* Trim end of region */
del += rg->to - f;
rg->to = f;
+
+ hugetlb_cgroup_uncharge_file_region(resv, rg,
+ rg->to - f);
}
}
@@ -2024,7 +2056,7 @@ static long __vma_reservation_common(str
VM_BUG_ON(dummy_out_regions_needed != 1);
break;
case VMA_COMMIT_RESV:
- ret = region_add(resv, idx, idx + 1, 1);
+ ret = region_add(resv, idx, idx + 1, 1, NULL, NULL);
/* region_add calls of range 1 should never fail. */
VM_BUG_ON(ret < 0);
break;
@@ -2034,7 +2066,7 @@ static long __vma_reservation_common(str
break;
case VMA_ADD_RESV:
if (vma->vm_flags & VM_MAYSHARE) {
- ret = region_add(resv, idx, idx + 1, 1);
+ ret = region_add(resv, idx, idx + 1, 1, NULL, NULL);
/* region_add calls of range 1 should never fail. */
VM_BUG_ON(ret < 0);
} else {
@@ -4694,7 +4726,7 @@ int hugetlb_reserve_pages(struct 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 */
@@ -4735,19 +4767,6 @@ int hugetlb_reserve_pages(struct inode *
chg = to - from;
- if (hugetlb_cgroup_charge_cgroup_rsvd(
- hstate_index(h), chg * pages_per_huge_page(h),
- &h_cg)) {
- kref_put(&resv_map->refs, resv_map_release);
- return -ENOMEM;
- }
-
- /*
- * Since this branch handles private mappings, we attach the
- * counter to uncharge for this reservation off resv_map.
- */
- resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, h_cg, h);
-
set_vma_resv_map(vma, resv_map);
set_vma_resv_flags(vma, HPAGE_RESV_OWNER);
}
@@ -4757,6 +4776,21 @@ int hugetlb_reserve_pages(struct inode *
goto out_err;
}
+ ret = hugetlb_cgroup_charge_cgroup_rsvd(
+ hstate_index(h), chg * pages_per_huge_page(h), &h_cg);
+
+ if (ret < 0) {
+ ret = -ENOMEM;
+ goto out_err;
+ }
+
+ if (vma && !(vma->vm_flags & VM_MAYSHARE) && h_cg) {
+ /* For private mappings, the hugetlb_cgroup uncharge info hangs
+ * of the resv_map.
+ */
+ resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, h_cg, h);
+ }
+
/*
* There must be enough pages in the subpool for the mapping. If
* the subpool has a minimum size, there may be some global
@@ -4765,7 +4799,7 @@ int hugetlb_reserve_pages(struct inode *
gbl_reserve = hugepage_subpool_get_pages(spool, chg);
if (gbl_reserve < 0) {
ret = -ENOSPC;
- goto out_err;
+ goto out_uncharge_cgroup;
}
/*
@@ -4774,9 +4808,7 @@ int hugetlb_reserve_pages(struct 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;
}
/*
@@ -4791,13 +4823,11 @@ int hugetlb_reserve_pages(struct 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(resv_map, from, to, regions_needed, h, h_cg);
if (unlikely(add < 0)) {
hugetlb_acct_memory(h, -gbl_reserve);
- /* put back original number of pages, chg */
- (void)hugepage_subpool_put_pages(spool, chg);
- goto out_err;
+ goto out_put_pages;
} else if (unlikely(chg > add)) {
/*
* pages in this range were added to the reserve
@@ -4808,12 +4838,22 @@ int hugetlb_reserve_pages(struct inode *
*/
long rsv_adjust;
+ hugetlb_cgroup_uncharge_cgroup_rsvd(
+ hstate_index(h),
+ (chg - add) * pages_per_huge_page(h), h_cg);
+
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_rsvd(hstate_index(h),
+ chg * pages_per_huge_page(h), h_cg);
out_err:
if (!vma || vma->vm_flags & VM_MAYSHARE)
/* Only call region_abort if the region_chg succeeded but the
--- a/mm/hugetlb_cgroup.c~hugetlb_cgroup-add-accounting-for-shared-mappings
+++ a/mm/hugetlb_cgroup.c
@@ -392,6 +392,21 @@ void hugetlb_cgroup_uncharge_counter(str
css_put(resv->css);
}
+void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv,
+ struct file_region *rg,
+ unsigned long nr_pages)
+{
+ if (hugetlb_cgroup_disabled() || !resv || !rg || !nr_pages)
+ return;
+
+ if (rg->reservation_counter && resv->pages_per_hpage && nr_pages > 0 &&
+ !resv->reservation_counter) {
+ page_counter_uncharge(rg->reservation_counter,
+ nr_pages * resv->pages_per_hpage);
+ css_put(rg->css);
+ }
+}
+
enum {
RES_USAGE,
RES_RSVD_USAGE,
_
Patches currently in -mm which might be from almasrymina@xxxxxxxxxx are
hugetlb_cgroup-add-hugetlb_cgroup-reservation-counter.patch
hugetlb_cgroup-add-interface-for-charge-uncharge-hugetlb-reservations.patch
hugetlb_cgroup-add-reservation-accounting-for-private-mappings.patch
hugetlb-disable-region_add-file_region-coalescing.patch
hugetlb_cgroup-add-accounting-for-shared-mappings.patch
hugetlb_cgroup-support-noreserve-mappings.patch
hugetlb-support-file_region-coalescing-again.patch
hugetlb_cgroup-add-hugetlb_cgroup-reservation-tests.patch
hugetlb_cgroup-add-hugetlb_cgroup-reservation-docs.patch
