[RFC PATCH 19/20] x86/sgx: Add stats and events interfaces to EPC cgroup controller
From: Kristen Carlson Accardi
Date: Thu Sep 22 2022 - 13:14:17 EST
From: Sean Christopherson <sean.j.christopherson@xxxxxxxxx>
Enable the cgroup sgx_epc.stats and sgx_epc.events files and
associated counters.
Signed-off-by: Sean Christopherson <sean.j.christopherson@xxxxxxxxx>
Signed-off-by: Kristen Carlson Accardi <kristen@xxxxxxxxxxxxxxx>
Cc: Sean Christopherson <seanjc@xxxxxxxxxx>
---
arch/x86/kernel/cpu/sgx/epc_cgroup.c | 134 +++++++++++++++++++++++++--
arch/x86/kernel/cpu/sgx/epc_cgroup.h | 16 +++-
arch/x86/kernel/cpu/sgx/main.c | 6 +-
3 files changed, 145 insertions(+), 11 deletions(-)
diff --git a/arch/x86/kernel/cpu/sgx/epc_cgroup.c b/arch/x86/kernel/cpu/sgx/epc_cgroup.c
index 71da3b499950..8541029b86be 100644
--- a/arch/x86/kernel/cpu/sgx/epc_cgroup.c
+++ b/arch/x86/kernel/cpu/sgx/epc_cgroup.c
@@ -77,6 +77,43 @@ static struct sgx_epc_cgroup *parent_epc_cgroup(struct sgx_epc_cgroup *epc_cg)
return sgx_epc_cgroup_from_css(epc_cg->css.parent);
}
+static inline unsigned long sgx_epc_cgroup_cnt_read(struct sgx_epc_cgroup *epc_cg,
+ enum sgx_epc_cgroup_counter i)
+{
+ return atomic_long_read(&epc_cg->cnt[i]);
+}
+
+static inline void sgx_epc_cgroup_cnt_reset(struct sgx_epc_cgroup *epc_cg,
+ enum sgx_epc_cgroup_counter i)
+{
+ atomic_long_set(&epc_cg->cnt[i], 0);
+}
+
+static inline void sgx_epc_cgroup_cnt_add(struct sgx_epc_cgroup *epc_cg,
+ enum sgx_epc_cgroup_counter i,
+ unsigned long cnt)
+{
+ atomic_long_add(cnt, &epc_cg->cnt[i]);
+}
+
+static inline void sgx_epc_cgroup_event(struct sgx_epc_cgroup *epc_cg,
+ enum sgx_epc_cgroup_counter i,
+ unsigned long cnt)
+{
+ sgx_epc_cgroup_cnt_add(epc_cg, i, cnt);
+
+ if (i == SGX_EPC_CGROUP_LOW || i == SGX_EPC_CGROUP_HIGH ||
+ i == SGX_EPC_CGROUP_MAX)
+ cgroup_file_notify(&epc_cg->events_file);
+}
+
+static inline void sgx_epc_cgroup_cnt_sub(struct sgx_epc_cgroup *epc_cg,
+ enum sgx_epc_cgroup_counter i,
+ unsigned long cnt)
+{
+ atomic_long_sub(cnt, &epc_cg->cnt[i]);
+}
+
/**
* sgx_epc_cgroup_iter - iterate over the EPC cgroup hierarchy
* @root: hierarchy root
@@ -368,7 +405,9 @@ void sgx_epc_cgroup_isolate_pages(struct sgx_epc_cgroup *root,
*/
if (!sgx_epc_cgroup_all_in_use_are_low(root))
continue;
+ sgx_epc_cgroup_event(epc_cg, SGX_EPC_CGROUP_LOW, 1);
}
+ sgx_epc_cgroup_event(epc_cg, SGX_EPC_CGROUP_RECLAMATIONS, 1);
sgx_isolate_epc_pages(&epc_cg->lru, nr_to_scan, dst);
if (!*nr_to_scan) {
@@ -383,8 +422,11 @@ void sgx_epc_cgroup_isolate_pages(struct sgx_epc_cgroup *root,
}
static int sgx_epc_cgroup_reclaim_pages(unsigned long nr_pages,
- struct sgx_epc_reclaim_control *rc)
+ struct sgx_epc_reclaim_control *rc,
+ enum sgx_epc_cgroup_counter c)
{
+ sgx_epc_cgroup_event(rc->epc_cg, c, 1);
+
/*
* Ensure sgx_reclaim_pages is called with a minimum and maximum
* number of pages. Attempting to reclaim only a few pages will
@@ -434,7 +476,8 @@ static inline void __sgx_epc_cgroup_reclaim_high(struct sgx_epc_cgroup *epc_cg)
if (cur <= high)
break;
- if (!sgx_epc_cgroup_reclaim_pages(cur - high, &rc)) {
+ if (!sgx_epc_cgroup_reclaim_pages(cur - high, &rc,
+ SGX_EPC_CGROUP_HIGH)) {
if (sgx_epc_cgroup_reclaim_failed(&rc))
break;
}
@@ -494,7 +537,8 @@ static void sgx_epc_cgroup_reclaim_work_func(struct work_struct *work)
if (cur <= max)
break;
- if (!sgx_epc_cgroup_reclaim_pages(cur - max, &rc)) {
+ if (!sgx_epc_cgroup_reclaim_pages(cur - max, &rc,
+ SGX_EPC_CGROUP_MAX)) {
if (sgx_epc_cgroup_reclaim_failed(&rc))
break;
}
@@ -539,7 +583,8 @@ static int __sgx_epc_cgroup_try_charge(struct sgx_epc_cgroup *epc_cg,
over = ((cur + nr_pages) > max) ?
(cur + nr_pages) - max : SGX_EPC_RECLAIM_MIN_PAGES;
- if (!sgx_epc_cgroup_reclaim_pages(over, &rc)) {
+ if (!sgx_epc_cgroup_reclaim_pages(over, &rc,
+ SGX_EPC_CGROUP_MAX)) {
if (sgx_epc_cgroup_reclaim_failed(&rc)) {
if (++nr_empty > SGX_EPC_RECLAIM_OOM_THRESHOLD)
return -ENOMEM;
@@ -586,6 +631,8 @@ struct sgx_epc_cgroup *sgx_epc_cgroup_try_charge(struct mm_struct *mm,
if (ret)
return ERR_PTR(ret);
+
+ sgx_epc_cgroup_cnt_add(epc_cg, SGX_EPC_CGROUP_PAGES, 1);
return epc_cg;
}
@@ -593,13 +640,17 @@ struct sgx_epc_cgroup *sgx_epc_cgroup_try_charge(struct mm_struct *mm,
* sgx_epc_cgroup_uncharge - hierarchically uncharge EPC pages
* @epc_cg: the charged epc cgroup
* @nr_pages: the number of pages to uncharge
+ * @reclaimed: whether the pages were reclaimed (vs. freed)
*/
-void sgx_epc_cgroup_uncharge(struct sgx_epc_cgroup *epc_cg)
+void sgx_epc_cgroup_uncharge(struct sgx_epc_cgroup *epc_cg, bool reclaimed)
{
if (sgx_epc_cgroup_disabled())
return;
page_counter_uncharge(&epc_cg->pc, 1);
+ sgx_epc_cgroup_cnt_sub(epc_cg, SGX_EPC_CGROUP_PAGES, 1);
+ if (reclaimed)
+ sgx_epc_cgroup_event(epc_cg, SGX_EPC_CGROUP_RECLAIMED, 1);
if (epc_cg != root_epc_cgroup)
css_put_many(&epc_cg->css, 1);
@@ -665,6 +716,61 @@ static u64 sgx_epc_current_read(struct cgroup_subsys_state *css,
return (u64)page_counter_read(&epc_cg->pc) * PAGE_SIZE;
}
+static int sgx_epc_stats_show(struct seq_file *m, void *v)
+{
+ struct sgx_epc_cgroup *epc_cg = sgx_epc_cgroup_from_css(seq_css(m));
+
+ unsigned long cur, dir, rec, recs;
+ cur = page_counter_read(&epc_cg->pc);
+ dir = sgx_epc_cgroup_cnt_read(epc_cg, SGX_EPC_CGROUP_PAGES);
+ rec = sgx_epc_cgroup_cnt_read(epc_cg, SGX_EPC_CGROUP_RECLAIMED);
+ recs= sgx_epc_cgroup_cnt_read(epc_cg, SGX_EPC_CGROUP_RECLAMATIONS);
+
+ seq_printf(m, "pages %lu\n", cur);
+ seq_printf(m, "direct %lu\n", dir);
+ seq_printf(m, "indirect %lu\n", (cur - dir));
+ seq_printf(m, "reclaimed %lu\n", rec);
+ seq_printf(m, "reclamations %lu\n", recs);
+
+ return 0;
+}
+
+static ssize_t sgx_epc_stats_reset(struct kernfs_open_file *of,
+ char *buf, size_t nbytes, loff_t off)
+{
+ struct sgx_epc_cgroup *epc_cg = sgx_epc_cgroup_from_css(of_css(of));
+ sgx_epc_cgroup_cnt_reset(epc_cg, SGX_EPC_CGROUP_RECLAIMED);
+ sgx_epc_cgroup_cnt_reset(epc_cg, SGX_EPC_CGROUP_RECLAMATIONS);
+ return nbytes;
+}
+
+
+static int sgx_epc_events_show(struct seq_file *m, void *v)
+{
+ struct sgx_epc_cgroup *epc_cg = sgx_epc_cgroup_from_css(seq_css(m));
+
+ unsigned long low, high, max;
+ low = sgx_epc_cgroup_cnt_read(epc_cg, SGX_EPC_CGROUP_LOW);
+ high = sgx_epc_cgroup_cnt_read(epc_cg, SGX_EPC_CGROUP_HIGH);
+ max = sgx_epc_cgroup_cnt_read(epc_cg, SGX_EPC_CGROUP_MAX);
+
+ seq_printf(m, "low %lu\n", low);
+ seq_printf(m, "high %lu\n", high);
+ seq_printf(m, "max %lu\n", max);
+
+ return 0;
+}
+
+static ssize_t sgx_epc_events_reset(struct kernfs_open_file *of,
+ char *buf, size_t nbytes, loff_t off)
+{
+ struct sgx_epc_cgroup *epc_cg = sgx_epc_cgroup_from_css(of_css(of));
+ sgx_epc_cgroup_cnt_reset(epc_cg, SGX_EPC_CGROUP_LOW);
+ sgx_epc_cgroup_cnt_reset(epc_cg, SGX_EPC_CGROUP_HIGH);
+ sgx_epc_cgroup_cnt_reset(epc_cg, SGX_EPC_CGROUP_MAX);
+ return nbytes;
+}
+
static int sgx_epc_low_show(struct seq_file *m, void *v)
{
struct sgx_epc_cgroup *epc_cg = sgx_epc_cgroup_from_css(seq_css(m));
@@ -733,7 +839,8 @@ static ssize_t sgx_epc_high_write(struct kernfs_open_file *of,
if (signal_pending(current))
break;
- if (!sgx_epc_cgroup_reclaim_pages(cur - high, &rc)) {
+ if (!sgx_epc_cgroup_reclaim_pages(cur - high, &rc,
+ SGX_EPC_CGROUP_HIGH)) {
if (sgx_epc_cgroup_reclaim_failed(&rc))
break;
}
@@ -782,7 +889,8 @@ static ssize_t sgx_epc_max_write(struct kernfs_open_file *of, char *buf,
if (signal_pending(current))
break;
- if (!sgx_epc_cgroup_reclaim_pages(cur - max, &rc)) {
+ if (!sgx_epc_cgroup_reclaim_pages(cur - max, &rc,
+ SGX_EPC_CGROUP_MAX)) {
if (sgx_epc_cgroup_reclaim_failed(&rc)) {
if (++nr_empty > SGX_EPC_RECLAIM_OOM_THRESHOLD)
sgx_epc_cgroup_oom(epc_cg);
@@ -799,6 +907,18 @@ static struct cftype sgx_epc_cgroup_files[] = {
.name = "current",
.read_u64 = sgx_epc_current_read,
},
+ {
+ .name = "stats",
+ .seq_show = sgx_epc_stats_show,
+ .write = sgx_epc_stats_reset,
+ },
+ {
+ .name = "events",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .file_offset = offsetof(struct sgx_epc_cgroup, events_file),
+ .seq_show = sgx_epc_events_show,
+ .write = sgx_epc_events_reset,
+ },
{
.name = "low",
.flags = CFTYPE_NOT_ON_ROOT,
diff --git a/arch/x86/kernel/cpu/sgx/epc_cgroup.h b/arch/x86/kernel/cpu/sgx/epc_cgroup.h
index 226304a3d523..656c9f386b48 100644
--- a/arch/x86/kernel/cpu/sgx/epc_cgroup.h
+++ b/arch/x86/kernel/cpu/sgx/epc_cgroup.h
@@ -14,6 +14,16 @@
#ifndef CONFIG_CGROUP_SGX_EPC
struct sgx_epc_cgroup;
#else
+enum sgx_epc_cgroup_counter {
+ SGX_EPC_CGROUP_PAGES,
+ SGX_EPC_CGROUP_RECLAIMED,
+ SGX_EPC_CGROUP_RECLAMATIONS,
+ SGX_EPC_CGROUP_LOW,
+ SGX_EPC_CGROUP_HIGH,
+ SGX_EPC_CGROUP_MAX,
+ SGX_EPC_CGROUP_NR_COUNTERS,
+};
+
struct sgx_epc_cgroup {
struct cgroup_subsys_state css;
@@ -24,11 +34,15 @@ struct sgx_epc_cgroup {
struct sgx_epc_cgroup *reclaim_iter;
struct work_struct reclaim_work;
unsigned int epoch;
+
+ atomic_long_t cnt[SGX_EPC_CGROUP_NR_COUNTERS];
+
+ struct cgroup_file events_file;
};
struct sgx_epc_cgroup *sgx_epc_cgroup_try_charge(struct mm_struct *mm,
bool reclaim);
-void sgx_epc_cgroup_uncharge(struct sgx_epc_cgroup *epc_cg);
+void sgx_epc_cgroup_uncharge(struct sgx_epc_cgroup *epc_cg, bool reclaimed);
bool sgx_epc_cgroup_lru_empty(struct sgx_epc_cgroup *root);
void sgx_epc_cgroup_isolate_pages(struct sgx_epc_cgroup *root,
int *nr_to_scan, struct list_head *dst);
diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
index 29653a0d4670..3330ed4d0d43 100644
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -412,7 +412,7 @@ int sgx_reclaim_epc_pages(int nr_to_scan, bool ignore_age,
#ifdef CONFIG_CGROUP_SGX_EPC
if (epc_page->epc_cg) {
- sgx_epc_cgroup_uncharge(epc_page->epc_cg);
+ sgx_epc_cgroup_uncharge(epc_page->epc_cg, true);
epc_page->epc_cg = NULL;
}
#endif
@@ -663,7 +663,7 @@ struct sgx_epc_page *sgx_alloc_epc_page(void *owner, bool reclaim)
WARN_ON(page->epc_cg);
page->epc_cg = epc_cg;
} else {
- sgx_epc_cgroup_uncharge(epc_cg);
+ sgx_epc_cgroup_uncharge(epc_cg, false);
}
#endif
if (sgx_should_reclaim(SGX_NR_LOW_PAGES))
@@ -698,7 +698,7 @@ void sgx_free_epc_page(struct sgx_epc_page *page)
spin_unlock(&node->lock);
#ifdef CONFIG_CGROUP_SGX_EPC
if (page->epc_cg) {
- sgx_epc_cgroup_uncharge(page->epc_cg);
+ sgx_epc_cgroup_uncharge(page->epc_cg, false);
page->epc_cg = NULL;
}
#endif
--
2.37.3