#include <linux/hugetlb.h>
#include <linux/hugetlb_cgroup.h>
-enum hugetlb_memory_event {
- HUGETLB_MAX,
- HUGETLB_NR_MEMORY_EVENTS,
-};
-
-struct hugetlb_cgroup {
- struct cgroup_subsys_state css;
-
- /*
- * the counter to account for hugepages from hugetlb.
- */
- struct page_counter hugepage[HUGE_MAX_HSTATE];
-
- atomic_long_t events[HUGE_MAX_HSTATE][HUGETLB_NR_MEMORY_EVENTS];
- atomic_long_t events_local[HUGE_MAX_HSTATE][HUGETLB_NR_MEMORY_EVENTS];
-
- /* Handle for "hugetlb.events" */
- struct cgroup_file events_file[HUGE_MAX_HSTATE];
-
- /* Handle for "hugetlb.events.local" */
- struct cgroup_file events_local_file[HUGE_MAX_HSTATE];
-};
-
#define MEMFILE_PRIVATE(x, val) (((x) << 16) | (val))
#define MEMFILE_IDX(val) (((val) >> 16) & 0xffff)
#define MEMFILE_ATTR(val) ((val) & 0xffff)
static struct hugetlb_cgroup *root_h_cgroup __read_mostly;
+static inline struct page_counter *
+__hugetlb_cgroup_counter_from_cgroup(struct hugetlb_cgroup *h_cg, int idx,
+ bool rsvd)
+{
+ if (rsvd)
+ return &h_cg->rsvd_hugepage[idx];
+ return &h_cg->hugepage[idx];
+}
+
+static inline struct page_counter *
+hugetlb_cgroup_counter_from_cgroup(struct hugetlb_cgroup *h_cg, int idx)
+{
+ return __hugetlb_cgroup_counter_from_cgroup(h_cg, idx, false);
+}
+
+static inline struct page_counter *
+hugetlb_cgroup_counter_from_cgroup_rsvd(struct hugetlb_cgroup *h_cg, int idx)
+{
+ return __hugetlb_cgroup_counter_from_cgroup(h_cg, idx, true);
+}
+
static inline
struct hugetlb_cgroup *hugetlb_cgroup_from_css(struct cgroup_subsys_state *s)
{
int idx;
for (idx = 0; idx < hugetlb_max_hstate; idx++) {
- if (page_counter_read(&h_cg->hugepage[idx]))
+ if (page_counter_read(
+ hugetlb_cgroup_counter_from_cgroup(h_cg, idx)) ||
+ page_counter_read(hugetlb_cgroup_counter_from_cgroup_rsvd(
+ h_cg, idx))) {
return true;
+ }
}
return false;
}
int idx;
for (idx = 0; idx < HUGE_MAX_HSTATE; idx++) {
- struct page_counter *counter = &h_cgroup->hugepage[idx];
- struct page_counter *parent = NULL;
+ struct page_counter *fault_parent = NULL;
+ struct page_counter *rsvd_parent = NULL;
unsigned long limit;
int ret;
- if (parent_h_cgroup)
- parent = &parent_h_cgroup->hugepage[idx];
- page_counter_init(counter, parent);
+ if (parent_h_cgroup) {
+ fault_parent = hugetlb_cgroup_counter_from_cgroup(
+ parent_h_cgroup, idx);
+ rsvd_parent = hugetlb_cgroup_counter_from_cgroup_rsvd(
+ parent_h_cgroup, idx);
+ }
+ page_counter_init(hugetlb_cgroup_counter_from_cgroup(h_cgroup,
+ idx),
+ fault_parent);
+ page_counter_init(
+ hugetlb_cgroup_counter_from_cgroup_rsvd(h_cgroup, idx),
+ rsvd_parent);
limit = round_down(PAGE_COUNTER_MAX,
1 << huge_page_order(&hstates[idx]));
- ret = page_counter_set_max(counter, limit);
+
+ ret = page_counter_set_max(
+ hugetlb_cgroup_counter_from_cgroup(h_cgroup, idx),
+ limit);
+ VM_BUG_ON(ret);
+ ret = page_counter_set_max(
+ hugetlb_cgroup_counter_from_cgroup_rsvd(h_cgroup, idx),
+ limit);
VM_BUG_ON(ret);
}
}
kfree(h_cgroup);
}
-
/*
* Should be called with hugetlb_lock held.
* Since we are holding hugetlb_lock, pages cannot get moved from
!hugetlb_cgroup_is_root(hugetlb));
}
-int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
- struct hugetlb_cgroup **ptr)
+static int __hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
+ struct hugetlb_cgroup **ptr,
+ bool rsvd)
{
int ret = 0;
struct page_counter *counter;
}
rcu_read_unlock();
- if (!page_counter_try_charge(&h_cg->hugepage[idx], nr_pages,
- &counter)) {
+ if (!page_counter_try_charge(
+ __hugetlb_cgroup_counter_from_cgroup(h_cg, idx, rsvd),
+ nr_pages, &counter)) {
ret = -ENOMEM;
hugetlb_event(h_cg, idx, HUGETLB_MAX);
+ css_put(&h_cg->css);
+ goto done;
}
- css_put(&h_cg->css);
+ /* Reservations take a reference to the css because they do not get
+ * reparented.
+ */
+ if (!rsvd)
+ css_put(&h_cg->css);
done:
*ptr = h_cg;
return ret;
}
+int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
+ struct hugetlb_cgroup **ptr)
+{
+ return __hugetlb_cgroup_charge_cgroup(idx, nr_pages, ptr, false);
+}
+
+int hugetlb_cgroup_charge_cgroup_rsvd(int idx, unsigned long nr_pages,
+ struct hugetlb_cgroup **ptr)
+{
+ return __hugetlb_cgroup_charge_cgroup(idx, nr_pages, ptr, true);
+}
+
/* Should be called with hugetlb_lock held */
-void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages,
- struct hugetlb_cgroup *h_cg,
- struct page *page)
+static void __hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages,
+ struct hugetlb_cgroup *h_cg,
+ struct page *page, bool rsvd)
{
if (hugetlb_cgroup_disabled() || !h_cg)
return;
- set_hugetlb_cgroup(page, h_cg);
+ __set_hugetlb_cgroup(page, h_cg, rsvd);
return;
}
+void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages,
+ struct hugetlb_cgroup *h_cg,
+ struct page *page)
+{
+ __hugetlb_cgroup_commit_charge(idx, nr_pages, h_cg, page, false);
+}
+
+void hugetlb_cgroup_commit_charge_rsvd(int idx, unsigned long nr_pages,
+ struct hugetlb_cgroup *h_cg,
+ struct page *page)
+{
+ __hugetlb_cgroup_commit_charge(idx, nr_pages, h_cg, page, true);
+}
+
/*
* Should be called with hugetlb_lock held
*/
-void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages,
- struct page *page)
+static void __hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages,
+ struct page *page, bool rsvd)
{
struct hugetlb_cgroup *h_cg;
if (hugetlb_cgroup_disabled())
return;
lockdep_assert_held(&hugetlb_lock);
- h_cg = hugetlb_cgroup_from_page(page);
+ h_cg = __hugetlb_cgroup_from_page(page, rsvd);
if (unlikely(!h_cg))
return;
- set_hugetlb_cgroup(page, NULL);
- page_counter_uncharge(&h_cg->hugepage[idx], nr_pages);
+ __set_hugetlb_cgroup(page, NULL, rsvd);
+
+ page_counter_uncharge(__hugetlb_cgroup_counter_from_cgroup(h_cg, idx,
+ rsvd),
+ nr_pages);
+
+ if (rsvd)
+ css_put(&h_cg->css);
+
return;
}
-void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages,
- struct hugetlb_cgroup *h_cg)
+void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages,
+ struct page *page)
+{
+ __hugetlb_cgroup_uncharge_page(idx, nr_pages, page, false);
+}
+
+void hugetlb_cgroup_uncharge_page_rsvd(int idx, unsigned long nr_pages,
+ struct page *page)
+{
+ __hugetlb_cgroup_uncharge_page(idx, nr_pages, page, true);
+}
+
+static void __hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages,
+ struct hugetlb_cgroup *h_cg,
+ bool rsvd)
{
if (hugetlb_cgroup_disabled() || !h_cg)
return;
if (huge_page_order(&hstates[idx]) < HUGETLB_CGROUP_MIN_ORDER)
return;
- page_counter_uncharge(&h_cg->hugepage[idx], nr_pages);
- return;
+ page_counter_uncharge(__hugetlb_cgroup_counter_from_cgroup(h_cg, idx,
+ rsvd),
+ nr_pages);
+
+ if (rsvd)
+ css_put(&h_cg->css);
+}
+
+void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages,
+ struct hugetlb_cgroup *h_cg)
+{
+ __hugetlb_cgroup_uncharge_cgroup(idx, nr_pages, h_cg, false);
+}
+
+void hugetlb_cgroup_uncharge_cgroup_rsvd(int idx, unsigned long nr_pages,
+ struct hugetlb_cgroup *h_cg)
+{
+ __hugetlb_cgroup_uncharge_cgroup(idx, nr_pages, h_cg, true);
+}
+
+void hugetlb_cgroup_uncharge_counter(struct resv_map *resv, unsigned long start,
+ unsigned long end)
+{
+ if (hugetlb_cgroup_disabled() || !resv || !resv->reservation_counter ||
+ !resv->css)
+ return;
+
+ page_counter_uncharge(resv->reservation_counter,
+ (end - start) * resv->pages_per_hpage);
+ 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,
RES_LIMIT,
+ RES_RSVD_LIMIT,
RES_MAX_USAGE,
+ RES_RSVD_MAX_USAGE,
RES_FAILCNT,
+ RES_RSVD_FAILCNT,
};
static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css,
struct cftype *cft)
{
struct page_counter *counter;
+ struct page_counter *rsvd_counter;
struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css);
counter = &h_cg->hugepage[MEMFILE_IDX(cft->private)];
+ rsvd_counter = &h_cg->rsvd_hugepage[MEMFILE_IDX(cft->private)];
switch (MEMFILE_ATTR(cft->private)) {
case RES_USAGE:
return (u64)page_counter_read(counter) * PAGE_SIZE;
+ case RES_RSVD_USAGE:
+ return (u64)page_counter_read(rsvd_counter) * PAGE_SIZE;
case RES_LIMIT:
return (u64)counter->max * PAGE_SIZE;
+ case RES_RSVD_LIMIT:
+ return (u64)rsvd_counter->max * PAGE_SIZE;
case RES_MAX_USAGE:
return (u64)counter->watermark * PAGE_SIZE;
+ case RES_RSVD_MAX_USAGE:
+ return (u64)rsvd_counter->watermark * PAGE_SIZE;
case RES_FAILCNT:
return counter->failcnt;
+ case RES_RSVD_FAILCNT:
+ return rsvd_counter->failcnt;
default:
BUG();
}
1 << huge_page_order(&hstates[idx]));
switch (MEMFILE_ATTR(cft->private)) {
+ case RES_RSVD_USAGE:
+ counter = &h_cg->rsvd_hugepage[idx];
+ fallthrough;
case RES_USAGE:
val = (u64)page_counter_read(counter);
seq_printf(seq, "%llu\n", val * PAGE_SIZE);
break;
+ case RES_RSVD_LIMIT:
+ counter = &h_cg->rsvd_hugepage[idx];
+ fallthrough;
case RES_LIMIT:
val = (u64)counter->max;
if (val == limit)
int ret, idx;
unsigned long nr_pages;
struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of));
+ bool rsvd = false;
if (hugetlb_cgroup_is_root(h_cg)) /* Can't set limit on root */
return -EINVAL;
nr_pages = round_down(nr_pages, 1 << huge_page_order(&hstates[idx]));
switch (MEMFILE_ATTR(of_cft(of)->private)) {
+ case RES_RSVD_LIMIT:
+ rsvd = true;
+ fallthrough;
case RES_LIMIT:
mutex_lock(&hugetlb_limit_mutex);
- ret = page_counter_set_max(&h_cg->hugepage[idx], nr_pages);
+ ret = page_counter_set_max(
+ __hugetlb_cgroup_counter_from_cgroup(h_cg, idx, rsvd),
+ nr_pages);
mutex_unlock(&hugetlb_limit_mutex);
break;
default:
char *buf, size_t nbytes, loff_t off)
{
int ret = 0;
- struct page_counter *counter;
+ struct page_counter *counter, *rsvd_counter;
struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of));
counter = &h_cg->hugepage[MEMFILE_IDX(of_cft(of)->private)];
+ rsvd_counter = &h_cg->rsvd_hugepage[MEMFILE_IDX(of_cft(of)->private)];
switch (MEMFILE_ATTR(of_cft(of)->private)) {
case RES_MAX_USAGE:
page_counter_reset_watermark(counter);
break;
+ case RES_RSVD_MAX_USAGE:
+ page_counter_reset_watermark(rsvd_counter);
+ break;
case RES_FAILCNT:
counter->failcnt = 0;
break;
+ case RES_RSVD_FAILCNT:
+ rsvd_counter->failcnt = 0;
+ break;
default:
ret = -EINVAL;
break;
struct hstate *h = &hstates[idx];
/* format the size */
- mem_fmt(buf, 32, huge_page_size(h));
+ mem_fmt(buf, sizeof(buf), huge_page_size(h));
/* Add the limit file */
cft = &h->cgroup_files_dfl[0];
cft->write = hugetlb_cgroup_write_dfl;
cft->flags = CFTYPE_NOT_ON_ROOT;
- /* Add the current usage file */
+ /* Add the reservation limit file */
cft = &h->cgroup_files_dfl[1];
+ snprintf(cft->name, MAX_CFTYPE_NAME, "%s.rsvd.max", buf);
+ cft->private = MEMFILE_PRIVATE(idx, RES_RSVD_LIMIT);
+ cft->seq_show = hugetlb_cgroup_read_u64_max;
+ cft->write = hugetlb_cgroup_write_dfl;
+ cft->flags = CFTYPE_NOT_ON_ROOT;
+
+ /* Add the current usage file */
+ cft = &h->cgroup_files_dfl[2];
snprintf(cft->name, MAX_CFTYPE_NAME, "%s.current", buf);
cft->private = MEMFILE_PRIVATE(idx, RES_USAGE);
cft->seq_show = hugetlb_cgroup_read_u64_max;
cft->flags = CFTYPE_NOT_ON_ROOT;
+ /* Add the current reservation usage file */
+ cft = &h->cgroup_files_dfl[3];
+ snprintf(cft->name, MAX_CFTYPE_NAME, "%s.rsvd.current", buf);
+ cft->private = MEMFILE_PRIVATE(idx, RES_RSVD_USAGE);
+ cft->seq_show = hugetlb_cgroup_read_u64_max;
+ cft->flags = CFTYPE_NOT_ON_ROOT;
+
/* Add the events file */
- cft = &h->cgroup_files_dfl[2];
+ cft = &h->cgroup_files_dfl[4];
snprintf(cft->name, MAX_CFTYPE_NAME, "%s.events", buf);
cft->private = MEMFILE_PRIVATE(idx, 0);
cft->seq_show = hugetlb_events_show;
- cft->file_offset = offsetof(struct hugetlb_cgroup, events_file[idx]),
+ cft->file_offset = offsetof(struct hugetlb_cgroup, events_file[idx]);
cft->flags = CFTYPE_NOT_ON_ROOT;
/* Add the events.local file */
- cft = &h->cgroup_files_dfl[3];
+ cft = &h->cgroup_files_dfl[5];
snprintf(cft->name, MAX_CFTYPE_NAME, "%s.events.local", buf);
cft->private = MEMFILE_PRIVATE(idx, 0);
cft->seq_show = hugetlb_events_local_show;
cft->file_offset = offsetof(struct hugetlb_cgroup,
- events_local_file[idx]),
+ events_local_file[idx]);
cft->flags = CFTYPE_NOT_ON_ROOT;
/* NULL terminate the last cft */
- cft = &h->cgroup_files_dfl[4];
+ cft = &h->cgroup_files_dfl[6];
memset(cft, 0, sizeof(*cft));
WARN_ON(cgroup_add_dfl_cftypes(&hugetlb_cgrp_subsys,
struct hstate *h = &hstates[idx];
/* format the size */
- mem_fmt(buf, 32, huge_page_size(h));
+ mem_fmt(buf, sizeof(buf), huge_page_size(h));
/* Add the limit file */
cft = &h->cgroup_files_legacy[0];
cft->read_u64 = hugetlb_cgroup_read_u64;
cft->write = hugetlb_cgroup_write_legacy;
- /* Add the usage file */
+ /* Add the reservation limit file */
cft = &h->cgroup_files_legacy[1];
+ snprintf(cft->name, MAX_CFTYPE_NAME, "%s.rsvd.limit_in_bytes", buf);
+ cft->private = MEMFILE_PRIVATE(idx, RES_RSVD_LIMIT);
+ cft->read_u64 = hugetlb_cgroup_read_u64;
+ cft->write = hugetlb_cgroup_write_legacy;
+
+ /* Add the usage file */
+ cft = &h->cgroup_files_legacy[2];
snprintf(cft->name, MAX_CFTYPE_NAME, "%s.usage_in_bytes", buf);
cft->private = MEMFILE_PRIVATE(idx, RES_USAGE);
cft->read_u64 = hugetlb_cgroup_read_u64;
+ /* Add the reservation usage file */
+ cft = &h->cgroup_files_legacy[3];
+ snprintf(cft->name, MAX_CFTYPE_NAME, "%s.rsvd.usage_in_bytes", buf);
+ cft->private = MEMFILE_PRIVATE(idx, RES_RSVD_USAGE);
+ cft->read_u64 = hugetlb_cgroup_read_u64;
+
/* Add the MAX usage file */
- cft = &h->cgroup_files_legacy[2];
+ cft = &h->cgroup_files_legacy[4];
snprintf(cft->name, MAX_CFTYPE_NAME, "%s.max_usage_in_bytes", buf);
cft->private = MEMFILE_PRIVATE(idx, RES_MAX_USAGE);
cft->write = hugetlb_cgroup_reset;
cft->read_u64 = hugetlb_cgroup_read_u64;
+ /* Add the MAX reservation usage file */
+ cft = &h->cgroup_files_legacy[5];
+ snprintf(cft->name, MAX_CFTYPE_NAME, "%s.rsvd.max_usage_in_bytes", buf);
+ cft->private = MEMFILE_PRIVATE(idx, RES_RSVD_MAX_USAGE);
+ cft->write = hugetlb_cgroup_reset;
+ cft->read_u64 = hugetlb_cgroup_read_u64;
+
/* Add the failcntfile */
- cft = &h->cgroup_files_legacy[3];
+ cft = &h->cgroup_files_legacy[6];
snprintf(cft->name, MAX_CFTYPE_NAME, "%s.failcnt", buf);
- cft->private = MEMFILE_PRIVATE(idx, RES_FAILCNT);
+ cft->private = MEMFILE_PRIVATE(idx, RES_FAILCNT);
+ cft->write = hugetlb_cgroup_reset;
+ cft->read_u64 = hugetlb_cgroup_read_u64;
+
+ /* Add the reservation failcntfile */
+ cft = &h->cgroup_files_legacy[7];
+ snprintf(cft->name, MAX_CFTYPE_NAME, "%s.rsvd.failcnt", buf);
+ cft->private = MEMFILE_PRIVATE(idx, RES_RSVD_FAILCNT);
cft->write = hugetlb_cgroup_reset;
cft->read_u64 = hugetlb_cgroup_read_u64;
/* NULL terminate the last cft */
- cft = &h->cgroup_files_legacy[4];
+ cft = &h->cgroup_files_legacy[8];
memset(cft, 0, sizeof(*cft));
WARN_ON(cgroup_add_legacy_cftypes(&hugetlb_cgrp_subsys,
void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage)
{
struct hugetlb_cgroup *h_cg;
+ struct hugetlb_cgroup *h_cg_rsvd;
struct hstate *h = page_hstate(oldhpage);
if (hugetlb_cgroup_disabled())
VM_BUG_ON_PAGE(!PageHuge(oldhpage), oldhpage);
spin_lock(&hugetlb_lock);
h_cg = hugetlb_cgroup_from_page(oldhpage);
+ h_cg_rsvd = hugetlb_cgroup_from_page_rsvd(oldhpage);
set_hugetlb_cgroup(oldhpage, NULL);
+ set_hugetlb_cgroup_rsvd(oldhpage, NULL);
/* move the h_cg details to new cgroup */
set_hugetlb_cgroup(newhpage, h_cg);
+ set_hugetlb_cgroup_rsvd(newhpage, h_cg_rsvd);
list_move(&newhpage->lru, &h->hugepage_activelist);
spin_unlock(&hugetlb_lock);
return;
projects / linux-2.6-microblaze.git / blobdiff