@@ -993,9 +993,7 @@ static int __sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_inde
}
/*
- * When called from ksgxd, returns the mem_cgroup of a struct mm stored
- * in the enclave's mm_list. When not called from ksgxd, just returns
- * the mem_cgroup of the current task.
+ * Returns the mem_cgroup of a struct mm stored in the enclave's mm_list.
*/
static struct mem_cgroup *sgx_encl_get_mem_cgroup(struct sgx_encl *encl)
{
@@ -1003,14 +1001,6 @@ static struct mem_cgroup *sgx_encl_get_mem_cgroup(struct sgx_encl *encl)
struct sgx_encl_mm *encl_mm;
int idx;
- /*
- * If called from normal task context, return the mem_cgroup
- * of the current task's mm. The remainder of the handling is for
- * ksgxd.
- */
- if (!current_is_ksgxd())
- return get_mem_cgroup_from_mm(current->mm);
-
/*
* Search the enclave's mm_list to find an mm associated with
* this enclave to charge the allocation to.
@@ -1047,29 +1037,38 @@ static struct mem_cgroup *sgx_encl_get_mem_cgroup(struct sgx_encl *encl)
* @encl: an enclave pointer
* @page_index: enclave page index
* @backing: data for accessing backing storage for the page
+ * @indirect: in ksgxd or EPC cgroup work queue context
+ *
+ * Create a backing page for loading data back into an EPC page with ELDU. This function takes
+ * a reference on a new backing page which must be dropped with a corresponding call to
+ * sgx_encl_put_backing().
*
- * When called from ksgxd, sets the active memcg from one of the
- * mms in the enclave's mm_list prior to any backing page allocation,
- * in order to ensure that shmem page allocations are charged to the
- * enclave. Create a backing page for loading data back into an EPC page with
- * ELDU. This function takes a reference on a new backing page which
- * must be dropped with a corresponding call to sgx_encl_put_backing().
+ * When @indirect is true, sets the active memcg from one of the mms in the enclave's mm_list
+ * prior to any backing page allocation, in order to ensure that shmem page allocations are
+ * charged to the enclave.
*
* Return:
* 0 on success,
* -errno otherwise.
*/
int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index,
- struct sgx_backing *backing)
+ struct sgx_backing *backing, bool indirect)
{
- struct mem_cgroup *encl_memcg = sgx_encl_get_mem_cgroup(encl);
- struct mem_cgroup *memcg = set_active_memcg(encl_memcg);
+ struct mem_cgroup *encl_memcg;
+ struct mem_cgroup *memcg;
int ret;
+ if (indirect) {
+ encl_memcg = sgx_encl_get_mem_cgroup(encl);
+ memcg = set_active_memcg(encl_memcg);
+ }
+
ret = __sgx_encl_get_backing(encl, page_index, backing);
- set_active_memcg(memcg);
- mem_cgroup_put(encl_memcg);
+ if (indirect) {
+ set_active_memcg(memcg);
+ mem_cgroup_put(encl_memcg);
+ }
return ret;
}
@@ -103,12 +103,11 @@ static inline int sgx_encl_find(struct mm_struct *mm, unsigned long addr,
int sgx_encl_may_map(struct sgx_encl *encl, unsigned long start,
unsigned long end, unsigned long vm_flags);
-bool current_is_ksgxd(void);
void sgx_encl_release(struct kref *ref);
int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm);
const cpumask_t *sgx_encl_cpumask(struct sgx_encl *encl);
int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index,
- struct sgx_backing *backing);
+ struct sgx_backing *backing, bool indirect);
void sgx_encl_put_backing(struct sgx_backing *backing);
int sgx_encl_test_and_clear_young(struct mm_struct *mm,
struct sgx_encl_page *page);
@@ -131,7 +131,7 @@ void sgx_epc_cgroup_isolate_pages(struct misc_cg *root,
}
static unsigned int sgx_epc_cgroup_reclaim_pages(unsigned int nr_pages,
- struct misc_cg *root)
+ struct misc_cg *root, bool indirect)
{
LIST_HEAD(iso);
/*
@@ -143,7 +143,7 @@ static unsigned int sgx_epc_cgroup_reclaim_pages(unsigned int nr_pages,
nr_pages = min(nr_pages, SGX_NR_TO_SCAN_MAX);
sgx_epc_cgroup_isolate_pages(root, nr_pages, &iso);
- return sgx_do_epc_reclamation(&iso);
+ return sgx_do_epc_reclamation(&iso, indirect);
}
/*
@@ -191,7 +191,7 @@ static void sgx_epc_cgroup_reclaim_work_func(struct work_struct *work)
break;
/* Keep reclaiming until above condition is met. */
- sgx_epc_cgroup_reclaim_pages((unsigned int)(cur - max), epc_cg->cg);
+ sgx_epc_cgroup_reclaim_pages((unsigned int)(cur - max), epc_cg->cg, true);
}
}
@@ -214,7 +214,7 @@ static int __sgx_epc_cgroup_try_charge(struct sgx_epc_cgroup *epc_cg,
return -EBUSY;
}
- if (!sgx_epc_cgroup_reclaim_pages(1, epc_cg->cg))
+ if (!sgx_epc_cgroup_reclaim_pages(1, epc_cg->cg, false))
/* All pages were too young to reclaim, try again */
schedule();
}
@@ -274,7 +274,7 @@ static void sgx_encl_ewb(struct sgx_epc_page *epc_page,
}
static void sgx_reclaimer_write(struct sgx_epc_page *epc_page,
- struct sgx_backing *backing)
+ struct sgx_backing *backing, bool indirect)
{
struct sgx_encl_page *encl_page = epc_page->owner;
struct sgx_encl *encl = encl_page->encl;
@@ -290,7 +290,7 @@ static void sgx_reclaimer_write(struct sgx_epc_page *epc_page,
if (!encl->secs_child_cnt && test_bit(SGX_ENCL_INITIALIZED, &encl->flags)) {
ret = sgx_encl_alloc_backing(encl, PFN_DOWN(encl->size),
- &secs_backing);
+ &secs_backing, indirect);
if (ret)
goto out;
@@ -346,6 +346,7 @@ unsigned int sgx_isolate_epc_pages(struct sgx_epc_lru_list *lru, unsigned int n
/**
* sgx_do_epc_reclamation() - Perform reclamation for isolated EPC pages.
* @iso: List of isolated pages for reclamation
+ * @indirect: In ksgxd or EPC cgroup workqueue threads
*
* Take a list of EPC pages and reclaim them to the enclave's private shmem files. Do not
* reclaim the pages that have been accessed since the last scan, and move each of those pages
@@ -362,7 +363,7 @@ unsigned int sgx_isolate_epc_pages(struct sgx_epc_lru_list *lru, unsigned int n
*
* Return: number of pages successfully reclaimed.
*/
-unsigned int sgx_do_epc_reclamation(struct list_head *iso)
+unsigned int sgx_do_epc_reclamation(struct list_head *iso, bool indirect)
{
struct sgx_backing backing[SGX_NR_TO_SCAN_MAX];
struct sgx_epc_page *epc_page, *tmp;
@@ -384,7 +385,7 @@ unsigned int sgx_do_epc_reclamation(struct list_head *iso)
page_index = PFN_DOWN(encl_page->desc - encl_page->encl->base);
mutex_lock(&encl_page->encl->lock);
- ret = sgx_encl_alloc_backing(encl_page->encl, page_index, &backing[i]);
+ ret = sgx_encl_alloc_backing(encl_page->encl, page_index, &backing[i], indirect);
if (ret) {
mutex_unlock(&encl_page->encl->lock);
goto skip;
@@ -411,7 +412,7 @@ unsigned int sgx_do_epc_reclamation(struct list_head *iso)
i = 0;
list_for_each_entry_safe(epc_page, tmp, iso, list) {
encl_page = epc_page->owner;
- sgx_reclaimer_write(epc_page, &backing[i++]);
+ sgx_reclaimer_write(epc_page, &backing[i++], indirect);
kref_put(&encl_page->encl->refcount, sgx_encl_release);
sgx_epc_page_reset_state(epc_page);
@@ -422,7 +423,7 @@ unsigned int sgx_do_epc_reclamation(struct list_head *iso)
return i;
}
-static void sgx_reclaim_epc_pages_global(void)
+static void sgx_reclaim_epc_pages_global(bool indirect)
{
unsigned int nr_to_scan = SGX_NR_TO_SCAN;
LIST_HEAD(iso);
@@ -432,7 +433,7 @@ static void sgx_reclaim_epc_pages_global(void)
else
sgx_isolate_epc_pages(&sgx_global_lru, nr_to_scan, &iso);
- sgx_do_epc_reclamation(&iso);
+ sgx_do_epc_reclamation(&iso, indirect);
}
static bool sgx_should_reclaim(unsigned long watermark)
@@ -449,7 +450,7 @@ static bool sgx_should_reclaim(unsigned long watermark)
void sgx_reclaim_direct(void)
{
if (sgx_should_reclaim(SGX_NR_LOW_PAGES))
- sgx_reclaim_epc_pages_global();
+ sgx_reclaim_epc_pages_global(false);
}
static int ksgxd(void *p)
@@ -472,7 +473,7 @@ static int ksgxd(void *p)
sgx_should_reclaim(SGX_NR_HIGH_PAGES));
if (sgx_should_reclaim(SGX_NR_HIGH_PAGES))
- sgx_reclaim_epc_pages_global();
+ sgx_reclaim_epc_pages_global(true);
cond_resched();
}
@@ -495,11 +496,6 @@ static bool __init sgx_page_reclaimer_init(void)
return true;
}
-bool current_is_ksgxd(void)
-{
- return current == ksgxd_tsk;
-}
-
static struct sgx_epc_page *__sgx_alloc_epc_page_from_node(int nid)
{
struct sgx_numa_node *node = &sgx_numa_nodes[nid];
@@ -653,7 +649,7 @@ struct sgx_epc_page *sgx_alloc_epc_page(void *owner, bool reclaim)
* Need to do a global reclamation if cgroup was not full but free
* physical pages run out, causing __sgx_alloc_epc_page() to fail.
*/
- sgx_reclaim_epc_pages_global();
+ sgx_reclaim_epc_pages_global(false);
cond_resched();
}
@@ -167,7 +167,7 @@ void sgx_reclaim_direct(void);
void sgx_mark_page_reclaimable(struct sgx_epc_page *page);
int sgx_unmark_page_reclaimable(struct sgx_epc_page *page);
struct sgx_epc_page *sgx_alloc_epc_page(void *owner, bool reclaim);
-unsigned int sgx_do_epc_reclamation(struct list_head *iso);
+unsigned int sgx_do_epc_reclamation(struct list_head *iso, bool indirect);
unsigned int sgx_isolate_epc_pages(struct sgx_epc_lru_list *lru, unsigned int nr_to_scan,
struct list_head *dst);
Enclave Page Cache(EPC) memory can be swapped out to regular system memory, and the consumed memory should be charged to a proper mem_cgroup. Currently the selection of mem_cgroup to charge is done in sgx_encl_get_mem_cgroup(). But it only considers two contexts in which the swapping can be done: normal task and the ksgxd kthread. With the new EPC cgroup implementation, the swapping can also happen in EPC cgroup work-queue threads. In those cases, it improperly selects the root mem_cgroup to charge for the RAM usage. Change sgx_encl_get_mem_cgroup() to handle non-task contexts only and return the mem_cgroup of an mm_struct associated with the enclave. The return is used to charge for EPC backing pages in all kthread cases. Pass a flag into the top level reclamation function, sgx_do_epc_reclamation(), to explicitly indicate whether it is called from a background kthread. Internally, if the flag is true, switch the active mem_cgroup to the one returned from sgx_encl_get_mem_cgroup(), prior to any backing page allocation, in order to ensure that shmem page allocations are charged to the enclave's cgroup. Removed current_is_ksgxd() as it is no longer needed. Signed-off-by: Haitao Huang <haitao.huang@linux.intel.com> Reported-by: Mikko Ylinen <mikko.ylinen@linux.intel.com> --- arch/x86/kernel/cpu/sgx/encl.c | 43 ++++++++++++++-------------- arch/x86/kernel/cpu/sgx/encl.h | 3 +- arch/x86/kernel/cpu/sgx/epc_cgroup.c | 8 +++--- arch/x86/kernel/cpu/sgx/main.c | 26 +++++++---------- arch/x86/kernel/cpu/sgx/sgx.h | 2 +- 5 files changed, 38 insertions(+), 44 deletions(-)