A single fix for x86/SGX to prevent that memory which is allocated for an

SGX enclave is accounted to the wrong memory control group.
 -----BEGIN PGP SIGNATURE-----
 
 iQJHBAABCgAxFiEEQp8+kY+LLUocC4bMphj1TA10mKEFAmKcd1MTHHRnbHhAbGlu
 dXRyb25peC5kZQAKCRCmGPVMDXSYoaalD/0TdNTH+LiM0BpEZ4VHIAFhE9mgfaU/
 1HIZcXEvAzPqS+iLMYAPo2dS7hNKv1GCCD8HcuOdEwC/CyTdrcpvhCNeQXCagF38
 BHtzVCMFd/Y6U7ERNVsaHiuHFSkF+3QHef4Gzljzblgj1FK7s55z9tlQmE3pElOg
 UGfRoD32ODUtQPmOCjlOhFjsUUtFpdpXFCbjPPFdOqJ80LbdKR2s/0IBpHMk1xoz
 ESmS10tVC3a5np1/4Ge8vRCZnewOpulL/Is84Q8MbCvxI8NQh9pD7Imom/wRjSAS
 19N+sWh7ywuUtAOVqJ23dDc6SOL3yjM4HbmsEYRGPsgzuJ5crezLcrKgCFeGmz/4
 4zbU3R9hzzXQy8ZqNjbj71FKswfUDcMLb26GA/62d2N6zR7O0TSzfIrpIYp+GwJ3
 5KaM0LiKoW/LXGfwEdEBWpCkK1OKgMXmZ5IQlr5bRz3Qihqzkk65Dgfo66XRt+jb
 DhMHW+cMfLwSX72QER6LyP2jPfUSCZgy5Pn8LfXUH30fc084gyrAPq2eqtVnf0lf
 Hq5/r1nMosPE0CtxHM1vNRj5M052nQxXhDhdsTcoO6PVBrvEjJbkanj3XbNRk66T
 FDWGWmdtDC2su6p0ezwbARMxYnsSS40GVsp/DoOu+SHxlAm9VkomY+QDJ2FuoJnb
 K0XfW5vV9MEsvw==
 =cuLD
 -----END PGP SIGNATURE-----

Merge tag 'x86-urgent-2022-06-05' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 SGX fix from Thomas Gleixner:
 "A single fix for x86/SGX to prevent that memory which is allocated for
  an SGX enclave is accounted to the wrong memory control group"

* tag 'x86-urgent-2022-06-05' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/sgx: Set active memcg prior to shmem allocation

arch/x86/kernel/cpu/sgx/encl.c

@@ -152,7 +152,7 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page,
 
 	page_pcmd_off = sgx_encl_get_backing_page_pcmd_offset(encl, page_index);
 
-	ret = sgx_encl_get_backing(encl, page_index, &b);
+	ret = sgx_encl_lookup_backing(encl, page_index, &b);
 	if (ret)
 		return ret;
 
@@ -718,7 +718,7 @@ static struct page *sgx_encl_get_backing_page(struct sgx_encl *encl,
  *   0 on success,
  *   -errno otherwise.
  */
-int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
+static int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
 			 struct sgx_backing *backing)
 {
 	pgoff_t page_pcmd_off = sgx_encl_get_backing_page_pcmd_offset(encl, page_index);
@@ -743,6 +743,107 @@ int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
 	return 0;
 }
 
+/*
+ * 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.
+ */
+static struct mem_cgroup *sgx_encl_get_mem_cgroup(struct sgx_encl *encl)
+{
+	struct mem_cgroup *memcg = NULL;
+	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.
+	 */
+	idx = srcu_read_lock(&encl->srcu);
+
+	list_for_each_entry_rcu(encl_mm, &encl->mm_list, list) {
+		if (!mmget_not_zero(encl_mm->mm))
+			continue;
+
+		memcg = get_mem_cgroup_from_mm(encl_mm->mm);
+
+		mmput_async(encl_mm->mm);
+
+		break;
+	}
+
+	srcu_read_unlock(&encl->srcu, idx);
+
+	/*
+	 * In the rare case that there isn't an mm associated with
+	 * the enclave, set memcg to the current active mem_cgroup.
+	 * This will be the root mem_cgroup if there is no active
+	 * mem_cgroup.
+	 */
+	if (!memcg)
+		return get_mem_cgroup_from_mm(NULL);
+
+	return memcg;
+}
+
+/**
+ * sgx_encl_alloc_backing() - allocate a new backing storage page
+ * @encl:	an enclave pointer
+ * @page_index:	enclave page index
+ * @backing:	data for accessing backing storage for the page
+ *
+ * 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.
+ *
+ * Return:
+ *   0 on success,
+ *   -errno otherwise.
+ */
+int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index,
+			   struct sgx_backing *backing)
+{
+	struct mem_cgroup *encl_memcg = sgx_encl_get_mem_cgroup(encl);
+	struct mem_cgroup *memcg = set_active_memcg(encl_memcg);
+	int ret;
+
+	ret = sgx_encl_get_backing(encl, page_index, backing);
+
+	set_active_memcg(memcg);
+	mem_cgroup_put(encl_memcg);
+
+	return ret;
+}
+
+/**
+ * sgx_encl_lookup_backing() - retrieve an existing backing storage page
+ * @encl:	an enclave pointer
+ * @page_index:	enclave page index
+ * @backing:	data for accessing backing storage for the page
+ *
+ * Retrieve a backing page for loading data back into an EPC page with ELDU.
+ * It is the caller's responsibility to ensure that it is appropriate to use
+ * sgx_encl_lookup_backing() rather than sgx_encl_alloc_backing(). If lookup is
+ * not used correctly, this will cause an allocation which is not accounted for.
+ *
+ * Return:
+ *   0 on success,
+ *   -errno otherwise.
+ */
+int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index,
+			   struct sgx_backing *backing)
+{
+	return sgx_encl_get_backing(encl, page_index, backing);
+}
+
 /**
  * sgx_encl_put_backing() - Unpin the backing storage
  * @backing:	data for accessing backing storage for the page

arch/x86/kernel/cpu/sgx/encl.h

@@ -103,10 +103,13 @@ 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);
-int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
-			 struct sgx_backing *backing);
+int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index,
+			    struct sgx_backing *backing);
+int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index,
+			   struct sgx_backing *backing);
 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);

arch/x86/kernel/cpu/sgx/main.c

@@ -313,7 +313,7 @@ static void sgx_reclaimer_write(struct sgx_epc_page *epc_page,
 	sgx_encl_put_backing(backing);
 
 	if (!encl->secs_child_cnt && test_bit(SGX_ENCL_INITIALIZED, &encl->flags)) {
-		ret = sgx_encl_get_backing(encl, PFN_DOWN(encl->size),
+		ret = sgx_encl_alloc_backing(encl, PFN_DOWN(encl->size),
 					   &secs_backing);
 		if (ret)
 			goto out;
@@ -384,7 +384,7 @@ static void sgx_reclaim_pages(void)
 		page_index = PFN_DOWN(encl_page->desc - encl_page->encl->base);
 
 		mutex_lock(&encl_page->encl->lock);
-		ret = sgx_encl_get_backing(encl_page->encl, page_index, &backing[i]);
+		ret = sgx_encl_alloc_backing(encl_page->encl, page_index, &backing[i]);
 		if (ret) {
 			mutex_unlock(&encl_page->encl->lock);
 			goto skip;
@@ -475,6 +475,11 @@ 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];