Merge branch 'for-4.16/nfit' into libnvdimm-for-next

kernel/acct.c

@@ -102,7 +102,7 @@ static int check_free_space(struct bsd_acct_struct *acct)
 {
 	struct kstatfs sbuf;
 
-	if (time_is_before_jiffies(acct->needcheck))
+	if (time_is_after_jiffies(acct->needcheck))
 		goto out;
 
 	/* May block */

kernel/bpf/arraymap.c

@@ -53,9 +53,10 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 {
 	bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
 	int numa_node = bpf_map_attr_numa_node(attr);
+	u32 elem_size, index_mask, max_entries;
+	bool unpriv = !capable(CAP_SYS_ADMIN);
 	struct bpf_array *array;
 	u64 array_size;
-	u32 elem_size;
 
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
@@ -72,11 +73,20 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 
 	elem_size = round_up(attr->value_size, 8);
 
+	max_entries = attr->max_entries;
+	index_mask = roundup_pow_of_two(max_entries) - 1;
+
+	if (unpriv)
+		/* round up array size to nearest power of 2,
+		 * since cpu will speculate within index_mask limits
+		 */
+		max_entries = index_mask + 1;
+
 	array_size = sizeof(*array);
 	if (percpu)
-		array_size += (u64) attr->max_entries * sizeof(void *);
+		array_size += (u64) max_entries * sizeof(void *);
 	else
-		array_size += (u64) attr->max_entries * elem_size;
+		array_size += (u64) max_entries * elem_size;
 
 	/* make sure there is no u32 overflow later in round_up() */
 	if (array_size >= U32_MAX - PAGE_SIZE)
@@ -86,6 +96,8 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 	array = bpf_map_area_alloc(array_size, numa_node);
 	if (!array)
 		return ERR_PTR(-ENOMEM);
+	array->index_mask = index_mask;
+	array->map.unpriv_array = unpriv;
 
 	/* copy mandatory map attributes */
 	array->map.map_type = attr->map_type;
@@ -121,12 +133,13 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key)
 	if (unlikely(index >= array->map.max_entries))
 		return NULL;
 
-	return array->value + array->elem_size * index;
+	return array->value + array->elem_size * (index & array->index_mask);
 }
 
 /* emit BPF instructions equivalent to C code of array_map_lookup_elem() */
 static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 {
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	struct bpf_insn *insn = insn_buf;
 	u32 elem_size = round_up(map->value_size, 8);
 	const int ret = BPF_REG_0;
@@ -135,7 +148,12 @@ static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 
 	*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value));
 	*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
-	*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 3);
+	if (map->unpriv_array) {
+		*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 4);
+		*insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask);
+	} else {
+		*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 3);
+	}
 
 	if (is_power_of_2(elem_size)) {
 		*insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size));
@@ -157,7 +175,7 @@ static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key)
 	if (unlikely(index >= array->map.max_entries))
 		return NULL;
 
-	return this_cpu_ptr(array->pptrs[index]);
+	return this_cpu_ptr(array->pptrs[index & array->index_mask]);
 }
 
 int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value)
@@ -177,7 +195,7 @@ int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value)
 	 */
 	size = round_up(map->value_size, 8);
 	rcu_read_lock();
-	pptr = array->pptrs[index];
+	pptr = array->pptrs[index & array->index_mask];
 	for_each_possible_cpu(cpu) {
 		bpf_long_memcpy(value + off, per_cpu_ptr(pptr, cpu), size);
 		off += size;
@@ -225,10 +243,11 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
 		return -EEXIST;
 
 	if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
-		memcpy(this_cpu_ptr(array->pptrs[index]),
+		memcpy(this_cpu_ptr(array->pptrs[index & array->index_mask]),
 		       value, map->value_size);
 	else
-		memcpy(array->value + array->elem_size * index,
+		memcpy(array->value +
+		       array->elem_size * (index & array->index_mask),
 		       value, map->value_size);
 	return 0;
 }
@@ -262,7 +281,7 @@ int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
 	 */
 	size = round_up(map->value_size, 8);
 	rcu_read_lock();
-	pptr = array->pptrs[index];
+	pptr = array->pptrs[index & array->index_mask];
 	for_each_possible_cpu(cpu) {
 		bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value + off, size);
 		off += size;
@@ -613,6 +632,7 @@ static void *array_of_map_lookup_elem(struct bpf_map *map, void *key)
 static u32 array_of_map_gen_lookup(struct bpf_map *map,
 				   struct bpf_insn *insn_buf)
 {
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	u32 elem_size = round_up(map->value_size, 8);
 	struct bpf_insn *insn = insn_buf;
 	const int ret = BPF_REG_0;
@@ -621,7 +641,12 @@ static u32 array_of_map_gen_lookup(struct bpf_map *map,
 
 	*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value));
 	*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
-	*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 5);
+	if (map->unpriv_array) {
+		*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 6);
+		*insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask);
+	} else {
+		*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 5);
+	}
 	if (is_power_of_2(elem_size))
 		*insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size));
 	else

kernel/bpf/core.c

@@ -767,6 +767,7 @@ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 }
 EXPORT_SYMBOL_GPL(__bpf_call_base);
 
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
 /**
  *	__bpf_prog_run - run eBPF program on a given context
  *	@ctx: is the data we are operating on
@@ -1317,6 +1318,14 @@ EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384)
 EVAL4(PROG_NAME_LIST, 416, 448, 480, 512)
 };
 
+#else
+static unsigned int __bpf_prog_ret0(const void *ctx,
+				    const struct bpf_insn *insn)
+{
+	return 0;
+}
+#endif
+
 bool bpf_prog_array_compatible(struct bpf_array *array,
 			       const struct bpf_prog *fp)
 {
@@ -1364,9 +1373,13 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
  */
 struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 {
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
 	u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1);
 
 	fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1];
+#else
+	fp->bpf_func = __bpf_prog_ret0;
+#endif
 
 	/* eBPF JITs can rewrite the program in case constant
 	 * blinding is active. However, in case of error during
@@ -1376,6 +1389,12 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 	 */
 	if (!bpf_prog_is_dev_bound(fp->aux)) {
 		fp = bpf_int_jit_compile(fp);
+#ifdef CONFIG_BPF_JIT_ALWAYS_ON
+		if (!fp->jited) {
+			*err = -ENOTSUPP;
+			return fp;
+		}
+#endif
 	} else {
 		*err = bpf_prog_offload_compile(fp);
 		if (*err)

kernel/bpf/inode.c

@@ -368,7 +368,45 @@ out:
 	putname(pname);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(bpf_obj_get_user);
+
+static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type type)
+{
+	struct bpf_prog *prog;
+	int ret = inode_permission(inode, MAY_READ | MAY_WRITE);
+	if (ret)
+		return ERR_PTR(ret);
+
+	if (inode->i_op == &bpf_map_iops)
+		return ERR_PTR(-EINVAL);
+	if (inode->i_op != &bpf_prog_iops)
+		return ERR_PTR(-EACCES);
+
+	prog = inode->i_private;
+
+	ret = security_bpf_prog(prog);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	if (!bpf_prog_get_ok(prog, &type, false))
+		return ERR_PTR(-EINVAL);
+
+	return bpf_prog_inc(prog);
+}
+
+struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type)
+{
+	struct bpf_prog *prog;
+	struct path path;
+	int ret = kern_path(name, LOOKUP_FOLLOW, &path);
+	if (ret)
+		return ERR_PTR(ret);
+	prog = __get_prog_inode(d_backing_inode(path.dentry), type);
+	if (!IS_ERR(prog))
+		touch_atime(&path);
+	path_put(&path);
+	return prog;
+}
+EXPORT_SYMBOL(bpf_prog_get_type_path);
 
 static void bpf_evict_inode(struct inode *inode)
 {

kernel/bpf/sockmap.c

@@ -591,8 +591,15 @@ static void sock_map_free(struct bpf_map *map)
 
 		write_lock_bh(&sock->sk_callback_lock);
 		psock = smap_psock_sk(sock);
-		smap_list_remove(psock, &stab->sock_map[i]);
-		smap_release_sock(psock, sock);
+		/* This check handles a racing sock event that can get the
+		 * sk_callback_lock before this case but after xchg happens
+		 * causing the refcnt to hit zero and sock user data (psock)
+		 * to be null and queued for garbage collection.
+		 */
+		if (likely(psock)) {
+			smap_list_remove(psock, &stab->sock_map[i]);
+			smap_release_sock(psock, sock);
+		}
 		write_unlock_bh(&sock->sk_callback_lock);
 	}
 	rcu_read_unlock();

kernel/bpf/syscall.c

@@ -1057,7 +1057,7 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog)
 }
 EXPORT_SYMBOL_GPL(bpf_prog_inc_not_zero);
 
-static bool bpf_prog_get_ok(struct bpf_prog *prog,
+bool bpf_prog_get_ok(struct bpf_prog *prog,
 			    enum bpf_prog_type *attach_type, bool attach_drv)
 {
 	/* not an attachment, just a refcount inc, always allow */

kernel/bpf/verifier.c

@@ -1729,6 +1729,13 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
 	err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &meta);
 	if (err)
 		return err;
+	if (func_id == BPF_FUNC_tail_call) {
+		if (meta.map_ptr == NULL) {
+			verbose(env, "verifier bug\n");
+			return -EINVAL;
+		}
+		env->insn_aux_data[insn_idx].map_ptr = meta.map_ptr;
+	}
 	err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &meta);
 	if (err)
 		return err;
@@ -4456,6 +4463,35 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 			 */
 			insn->imm = 0;
 			insn->code = BPF_JMP | BPF_TAIL_CALL;
+
+			/* instead of changing every JIT dealing with tail_call
+			 * emit two extra insns:
+			 * if (index >= max_entries) goto out;
+			 * index &= array->index_mask;
+			 * to avoid out-of-bounds cpu speculation
+			 */
+			map_ptr = env->insn_aux_data[i + delta].map_ptr;
+			if (map_ptr == BPF_MAP_PTR_POISON) {
+				verbose(env, "tail_call obusing map_ptr\n");
+				return -EINVAL;
+			}
+			if (!map_ptr->unpriv_array)
+				continue;
+			insn_buf[0] = BPF_JMP_IMM(BPF_JGE, BPF_REG_3,
+						  map_ptr->max_entries, 2);
+			insn_buf[1] = BPF_ALU32_IMM(BPF_AND, BPF_REG_3,
+						    container_of(map_ptr,
+								 struct bpf_array,
+								 map)->index_mask);
+			insn_buf[2] = *insn;
+			cnt = 3;
+			new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+			if (!new_prog)
+				return -ENOMEM;
+
+			delta    += cnt - 1;
+			env->prog = prog = new_prog;
+			insn      = new_prog->insnsi + i + delta;
 			continue;
 		}
 

kernel/cgroup/cgroup-v1.c

@@ -123,7 +123,11 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
 	 */
 	do {
 		css_task_iter_start(&from->self, 0, &it);
-		task = css_task_iter_next(&it);
+
+		do {
+			task = css_task_iter_next(&it);
+		} while (task && (task->flags & PF_EXITING));
+
 		if (task)
 			get_task_struct(task);
 		css_task_iter_end(&it);

kernel/cgroup/cgroup.c

@@ -1397,7 +1397,7 @@ static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft,
 			 cgroup_on_dfl(cgrp) ? ss->name : ss->legacy_name,
 			 cft->name);
 	else
-		strncpy(buf, cft->name, CGROUP_FILE_NAME_MAX);
+		strlcpy(buf, cft->name, CGROUP_FILE_NAME_MAX);
 	return buf;
 }
 
@@ -1864,9 +1864,9 @@ void init_cgroup_root(struct cgroup_root *root, struct cgroup_sb_opts *opts)
 
 	root->flags = opts->flags;
 	if (opts->release_agent)
-		strcpy(root->release_agent_path, opts->release_agent);
+		strlcpy(root->release_agent_path, opts->release_agent, PATH_MAX);
 	if (opts->name)
-		strcpy(root->name, opts->name);
+		strlcpy(root->name, opts->name, MAX_CGROUP_ROOT_NAMELEN);
 	if (opts->cpuset_clone_children)
 		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags);
 }
@@ -4125,26 +4125,24 @@ static void css_task_iter_advance_css_set(struct css_task_iter *it)
 
 static void css_task_iter_advance(struct css_task_iter *it)
 {
-	struct list_head *l = it->task_pos;
+	struct list_head *next;
 
 	lockdep_assert_held(&css_set_lock);
-	WARN_ON_ONCE(!l);
-
 repeat:
 	/*
 	 * Advance iterator to find next entry.  cset->tasks is consumed
 	 * first and then ->mg_tasks.  After ->mg_tasks, we move onto the
 	 * next cset.
 	 */
-	l = l->next;
+	next = it->task_pos->next;
 
-	if (l == it->tasks_head)
-		l = it->mg_tasks_head->next;
+	if (next == it->tasks_head)
+		next = it->mg_tasks_head->next;
 
-	if (l == it->mg_tasks_head)
+	if (next == it->mg_tasks_head)
 		css_task_iter_advance_css_set(it);
 	else
-		it->task_pos = l;
+		it->task_pos = next;
 
 	/* if PROCS, skip over tasks which aren't group leaders */
 	if ((it->flags & CSS_TASK_ITER_PROCS) && it->task_pos &&

kernel/crash_core.c

@@ -410,7 +410,7 @@ static int __init crash_save_vmcoreinfo_init(void)
 	VMCOREINFO_SYMBOL(contig_page_data);
 #endif
 #ifdef CONFIG_SPARSEMEM
-	VMCOREINFO_SYMBOL(mem_section);
+	VMCOREINFO_SYMBOL_ARRAY(mem_section);
 	VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS);
 	VMCOREINFO_STRUCT_SIZE(mem_section);
 	VMCOREINFO_OFFSET(mem_section, section_mem_map);

kernel/exit.c

@@ -1763,3 +1763,4 @@ __weak void abort(void)
 	/* if that doesn't kill us, halt */
 	panic("Oops failed to kill thread");
 }
+EXPORT_SYMBOL(abort);

kernel/pid.c

@@ -193,10 +193,8 @@ struct pid *alloc_pid(struct pid_namespace *ns)
 	}
 
 	if (unlikely(is_child_reaper(pid))) {
-		if (pid_ns_prepare_proc(ns)) {
-			disable_pid_allocation(ns);
+		if (pid_ns_prepare_proc(ns))
 			goto out_free;
-		}
 	}
 
 	get_pid_ns(ns);
@@ -226,6 +224,10 @@ out_free:
 	while (++i <= ns->level)
 		idr_remove(&ns->idr, (pid->numbers + i)->nr);
 
+	/* On failure to allocate the first pid, reset the state */
+	if (ns->pid_allocated == PIDNS_ADDING)
+		idr_set_cursor(&ns->idr, 0);
+
 	spin_unlock_irq(&pidmap_lock);
 
 	kmem_cache_free(ns->pid_cachep, pid);

kernel/sched/completion.c

@@ -34,11 +34,6 @@ void complete(struct completion *x)
 
 	spin_lock_irqsave(&x->wait.lock, flags);
 
-	/*
-	 * Perform commit of crossrelease here.
-	 */
-	complete_release_commit(x);
-
 	if (x->done != UINT_MAX)
 		x->done++;
 	__wake_up_locked(&x->wait, TASK_NORMAL, 1);

kernel/sched/membarrier.c

@@ -89,7 +89,9 @@ static int membarrier_private_expedited(void)
 		rcu_read_unlock();
 	}
 	if (!fallback) {
+		preempt_disable();
 		smp_call_function_many(tmpmask, ipi_mb, NULL, 1);
+		preempt_enable();
 		free_cpumask_var(tmpmask);
 	}
 	cpus_read_unlock();