Merge branch 'linus' into locking/core, to pick up fixes and dependencies

Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/bpf/arraymap.c

@@ -26,8 +26,10 @@ static void bpf_array_free_percpu(struct bpf_array *array)
 {
 	int i;
 
-	for (i = 0; i < array->map.max_entries; i++)
+	for (i = 0; i < array->map.max_entries; i++) {
 		free_percpu(array->pptrs[i]);
+		cond_resched();
+	}
 }
 
 static int bpf_array_alloc_percpu(struct bpf_array *array)
@@ -43,6 +45,7 @@ static int bpf_array_alloc_percpu(struct bpf_array *array)
 			return -ENOMEM;
 		}
 		array->pptrs[i] = ptr;
+		cond_resched();
 	}
 
 	return 0;
@@ -73,11 +76,11 @@ static int array_map_alloc_check(union bpf_attr *attr)
 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);
+	int ret, numa_node = bpf_map_attr_numa_node(attr);
 	u32 elem_size, index_mask, max_entries;
 	bool unpriv = !capable(CAP_SYS_ADMIN);
+	u64 cost, array_size, mask64;
 	struct bpf_array *array;
-	u64 array_size, mask64;
 
 	elem_size = round_up(attr->value_size, 8);
 
@@ -109,8 +112,19 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 		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)
+	cost = array_size;
+	if (cost >= U32_MAX - PAGE_SIZE)
 		return ERR_PTR(-ENOMEM);
+	if (percpu) {
+		cost += (u64)attr->max_entries * elem_size * num_possible_cpus();
+		if (cost >= U32_MAX - PAGE_SIZE)
+			return ERR_PTR(-ENOMEM);
+	}
+	cost = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+	ret = bpf_map_precharge_memlock(cost);
+	if (ret < 0)
+		return ERR_PTR(ret);
 
 	/* allocate all map elements and zero-initialize them */
 	array = bpf_map_area_alloc(array_size, numa_node);
@@ -121,20 +135,13 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 
 	/* copy mandatory map attributes */
 	bpf_map_init_from_attr(&array->map, attr);
+	array->map.pages = cost;
 	array->elem_size = elem_size;
 
-	if (!percpu)
-		goto out;
-
-	array_size += (u64) attr->max_entries * elem_size * num_possible_cpus();
-
-	if (array_size >= U32_MAX - PAGE_SIZE ||
-	    bpf_array_alloc_percpu(array)) {
+	if (percpu && bpf_array_alloc_percpu(array)) {
 		bpf_map_area_free(array);
 		return ERR_PTR(-ENOMEM);
 	}
-out:
-	array->map.pages = round_up(array_size, PAGE_SIZE) >> PAGE_SHIFT;
 
 	return &array->map;
 }

kernel/bpf/core.c

@@ -1590,7 +1590,7 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
 	 * so always copy 'cnt' prog_ids to the user.
 	 * In a rare race the user will see zero prog_ids
 	 */
-	ids = kcalloc(cnt, sizeof(u32), GFP_USER);
+	ids = kcalloc(cnt, sizeof(u32), GFP_USER | __GFP_NOWARN);
 	if (!ids)
 		return -ENOMEM;
 	rcu_read_lock();

kernel/bpf/cpumap.c

@@ -334,7 +334,7 @@ static int cpu_map_kthread_run(void *data)
 static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu,
 						       int map_id)
 {
-	gfp_t gfp = GFP_ATOMIC|__GFP_NOWARN;
+	gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
 	struct bpf_cpu_map_entry *rcpu;
 	int numa, err;
 

kernel/bpf/lpm_trie.c

@@ -555,7 +555,10 @@ static void trie_free(struct bpf_map *map)
 	struct lpm_trie_node __rcu **slot;
 	struct lpm_trie_node *node;
 
-	raw_spin_lock(&trie->lock);
+	/* Wait for outstanding programs to complete
+	 * update/lookup/delete/get_next_key and free the trie.
+	 */
+	synchronize_rcu();
 
 	/* Always start at the root and walk down to a node that has no
 	 * children. Then free that node, nullify its reference in the parent
@@ -566,10 +569,9 @@ static void trie_free(struct bpf_map *map)
 		slot = &trie->root;
 
 		for (;;) {
-			node = rcu_dereference_protected(*slot,
-					lockdep_is_held(&trie->lock));
+			node = rcu_dereference_protected(*slot, 1);
 			if (!node)
-				goto unlock;
+				goto out;
 
 			if (rcu_access_pointer(node->child[0])) {
 				slot = &node->child[0];
@@ -587,8 +589,8 @@ static void trie_free(struct bpf_map *map)
 		}
 	}
 
-unlock:
-	raw_spin_unlock(&trie->lock);
+out:
+	kfree(trie);
 }
 
 static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key)

kernel/bpf/sockmap.c

@@ -521,8 +521,8 @@ static struct smap_psock *smap_init_psock(struct sock *sock,
 static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
 {
 	struct bpf_stab *stab;
-	int err = -EINVAL;
 	u64 cost;
+	int err;
 
 	if (!capable(CAP_NET_ADMIN))
 		return ERR_PTR(-EPERM);
@@ -547,6 +547,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
 
 	/* make sure page count doesn't overflow */
 	cost = (u64) stab->map.max_entries * sizeof(struct sock *);
+	err = -EINVAL;
 	if (cost >= U32_MAX - PAGE_SIZE)
 		goto free_stab;
 

kernel/bpf/verifier.c

@@ -1356,6 +1356,13 @@ static bool is_ctx_reg(struct bpf_verifier_env *env, int regno)
 	return reg->type == PTR_TO_CTX;
 }
 
+static bool is_pkt_reg(struct bpf_verifier_env *env, int regno)
+{
+	const struct bpf_reg_state *reg = cur_regs(env) + regno;
+
+	return type_is_pkt_pointer(reg->type);
+}
+
 static int check_pkt_ptr_alignment(struct bpf_verifier_env *env,
 				   const struct bpf_reg_state *reg,
 				   int off, int size, bool strict)
@@ -1416,10 +1423,10 @@ static int check_generic_ptr_alignment(struct bpf_verifier_env *env,
 }
 
 static int check_ptr_alignment(struct bpf_verifier_env *env,
-			       const struct bpf_reg_state *reg,
-			       int off, int size)
+			       const struct bpf_reg_state *reg, int off,
+			       int size, bool strict_alignment_once)
 {
-	bool strict = env->strict_alignment;
+	bool strict = env->strict_alignment || strict_alignment_once;
 	const char *pointer_desc = "";
 
 	switch (reg->type) {
@@ -1576,9 +1583,9 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size)
  * if t==write && value_regno==-1, some unknown value is stored into memory
  * if t==read && value_regno==-1, don't care what we read from memory
  */
-static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno, int off,
-			    int bpf_size, enum bpf_access_type t,
-			    int value_regno)
+static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno,
+			    int off, int bpf_size, enum bpf_access_type t,
+			    int value_regno, bool strict_alignment_once)
 {
 	struct bpf_reg_state *regs = cur_regs(env);
 	struct bpf_reg_state *reg = regs + regno;
@@ -1590,7 +1597,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		return size;
 
 	/* alignment checks will add in reg->off themselves */
-	err = check_ptr_alignment(env, reg, off, size);
+	err = check_ptr_alignment(env, reg, off, size, strict_alignment_once);
 	if (err)
 		return err;
 
@@ -1735,21 +1742,23 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins
 		return -EACCES;
 	}
 
-	if (is_ctx_reg(env, insn->dst_reg)) {
-		verbose(env, "BPF_XADD stores into R%d context is not allowed\n",
-			insn->dst_reg);
+	if (is_ctx_reg(env, insn->dst_reg) ||
+	    is_pkt_reg(env, insn->dst_reg)) {
+		verbose(env, "BPF_XADD stores into R%d %s is not allowed\n",
+			insn->dst_reg, is_ctx_reg(env, insn->dst_reg) ?
+			"context" : "packet");
 		return -EACCES;
 	}
 
 	/* check whether atomic_add can read the memory */
 	err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
-			       BPF_SIZE(insn->code), BPF_READ, -1);
+			       BPF_SIZE(insn->code), BPF_READ, -1, true);
 	if (err)
 		return err;
 
 	/* check whether atomic_add can write into the same memory */
 	return check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
-				BPF_SIZE(insn->code), BPF_WRITE, -1);
+				BPF_SIZE(insn->code), BPF_WRITE, -1, true);
 }
 
 /* when register 'regno' is passed into function that will read 'access_size'
@@ -2388,7 +2397,8 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 	 * is inferred from register state.
 	 */
 	for (i = 0; i < meta.access_size; i++) {
-		err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B, BPF_WRITE, -1);
+		err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B,
+				       BPF_WRITE, -1, false);
 		if (err)
 			return err;
 	}
@@ -4632,7 +4642,7 @@ static int do_check(struct bpf_verifier_env *env)
 			 */
 			err = check_mem_access(env, insn_idx, insn->src_reg, insn->off,
 					       BPF_SIZE(insn->code), BPF_READ,
-					       insn->dst_reg);
+					       insn->dst_reg, false);
 			if (err)
 				return err;
 
@@ -4684,7 +4694,7 @@ static int do_check(struct bpf_verifier_env *env)
 			/* check that memory (dst_reg + off) is writeable */
 			err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
 					       BPF_SIZE(insn->code), BPF_WRITE,
-					       insn->src_reg);
+					       insn->src_reg, false);
 			if (err)
 				return err;
 
@@ -4719,7 +4729,7 @@ static int do_check(struct bpf_verifier_env *env)
 			/* check that memory (dst_reg + off) is writeable */
 			err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
 					       BPF_SIZE(insn->code), BPF_WRITE,
-					       -1);
+					       -1, false);
 			if (err)
 				return err;
 

kernel/compat.c

@@ -488,25 +488,6 @@ get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat)
 }
 EXPORT_SYMBOL_GPL(get_compat_sigset);
 
-int
-put_compat_sigset(compat_sigset_t __user *compat, const sigset_t *set,
-		  unsigned int size)
-{
-	/* size <= sizeof(compat_sigset_t) <= sizeof(sigset_t) */
-#ifdef __BIG_ENDIAN
-	compat_sigset_t v;
-	switch (_NSIG_WORDS) {
-	case 4: v.sig[7] = (set->sig[3] >> 32); v.sig[6] = set->sig[3];
-	case 3: v.sig[5] = (set->sig[2] >> 32); v.sig[4] = set->sig[2];
-	case 2: v.sig[3] = (set->sig[1] >> 32); v.sig[2] = set->sig[1];
-	case 1: v.sig[1] = (set->sig[0] >> 32); v.sig[0] = set->sig[0];
-	}
-	return copy_to_user(compat, &v, size) ? -EFAULT : 0;
-#else
-	return copy_to_user(compat, set, size) ? -EFAULT : 0;
-#endif
-}
-
 #ifdef CONFIG_NUMA
 COMPAT_SYSCALL_DEFINE6(move_pages, pid_t, pid, compat_ulong_t, nr_pages,
 		       compat_uptr_t __user *, pages32,

kernel/extable.c

@@ -64,7 +64,7 @@ const struct exception_table_entry *search_exception_tables(unsigned long addr)
 	return e;
 }
 
-static inline int init_kernel_text(unsigned long addr)
+int init_kernel_text(unsigned long addr)
 {
 	if (addr >= (unsigned long)_sinittext &&
 	    addr < (unsigned long)_einittext)

kernel/fork.c

@@ -592,7 +592,7 @@ static void check_mm(struct mm_struct *mm)
  * is dropped: either by a lazy thread or by
  * mmput. Free the page directory and the mm.
  */
-static void __mmdrop(struct mm_struct *mm)
+void __mmdrop(struct mm_struct *mm)
 {
 	BUG_ON(mm == &init_mm);
 	mm_free_pgd(mm);
@@ -603,18 +603,7 @@ static void __mmdrop(struct mm_struct *mm)
 	put_user_ns(mm->user_ns);
 	free_mm(mm);
 }
-
-void mmdrop(struct mm_struct *mm)
-{
-	/*
-	 * The implicit full barrier implied by atomic_dec_and_test() is
-	 * required by the membarrier system call before returning to
-	 * user-space, after storing to rq->curr.
-	 */
-	if (unlikely(atomic_dec_and_test(&mm->mm_count)))
-		__mmdrop(mm);
-}
-EXPORT_SYMBOL_GPL(mmdrop);
+EXPORT_SYMBOL_GPL(__mmdrop);
 
 static void mmdrop_async_fn(struct work_struct *work)
 {

kernel/irq/matrix.c

@@ -16,6 +16,7 @@ struct cpumap {
 	unsigned int		available;
 	unsigned int		allocated;
 	unsigned int		managed;
+	bool			initialized;
 	bool			online;
 	unsigned long		alloc_map[IRQ_MATRIX_SIZE];
 	unsigned long		managed_map[IRQ_MATRIX_SIZE];
@@ -81,9 +82,11 @@ void irq_matrix_online(struct irq_matrix *m)
 
 	BUG_ON(cm->online);
 
-	bitmap_zero(cm->alloc_map, m->matrix_bits);
-	cm->available = m->alloc_size - (cm->managed + m->systembits_inalloc);
-	cm->allocated = 0;
+	if (!cm->initialized) {
+		cm->available = m->alloc_size;
+		cm->available -= cm->managed + m->systembits_inalloc;
+		cm->initialized = true;
+	}
 	m->global_available += cm->available;
 	cm->online = true;
 	m->online_maps++;
@@ -370,14 +373,16 @@ void irq_matrix_free(struct irq_matrix *m, unsigned int cpu,
 	if (WARN_ON_ONCE(bit < m->alloc_start || bit >= m->alloc_end))
 		return;
 
-	if (cm->online) {
-		clear_bit(bit, cm->alloc_map);
-		cm->allocated--;
+	clear_bit(bit, cm->alloc_map);
+	cm->allocated--;
+
+	if (cm->online)
 		m->total_allocated--;
-		if (!managed) {
-			cm->available++;
+
+	if (!managed) {
+		cm->available++;
+		if (cm->online)
 			m->global_available++;
-		}
 	}
 	trace_irq_matrix_free(bit, cpu, m, cm);
 }

kernel/jump_label.c

@@ -366,12 +366,15 @@ static void __jump_label_update(struct static_key *key,
 {
 	for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) {
 		/*
-		 * entry->code set to 0 invalidates module init text sections
-		 * kernel_text_address() verifies we are not in core kernel
-		 * init code, see jump_label_invalidate_module_init().
+		 * An entry->code of 0 indicates an entry which has been
+		 * disabled because it was in an init text area.
 		 */
-		if (entry->code && kernel_text_address(entry->code))
-			arch_jump_label_transform(entry, jump_label_type(entry));
+		if (entry->code) {
+			if (kernel_text_address(entry->code))
+				arch_jump_label_transform(entry, jump_label_type(entry));
+			else
+				WARN_ONCE(1, "can't patch jump_label at %pS", (void *)entry->code);
+		}
 	}
 }
 
@@ -417,6 +420,19 @@ void __init jump_label_init(void)
 	cpus_read_unlock();
 }
 
+/* Disable any jump label entries in __init code */
+void __init jump_label_invalidate_init(void)
+{
+	struct jump_entry *iter_start = __start___jump_table;
+	struct jump_entry *iter_stop = __stop___jump_table;
+	struct jump_entry *iter;
+
+	for (iter = iter_start; iter < iter_stop; iter++) {
+		if (init_kernel_text(iter->code))
+			iter->code = 0;
+	}
+}
+
 #ifdef CONFIG_MODULES
 
 static enum jump_label_type jump_label_init_type(struct jump_entry *entry)
@@ -633,6 +649,7 @@ static void jump_label_del_module(struct module *mod)
 	}
 }
 
+/* Disable any jump label entries in module init code */
 static void jump_label_invalidate_module_init(struct module *mod)
 {
 	struct jump_entry *iter_start = mod->jump_entries;

kernel/memremap.c

@@ -275,8 +275,15 @@ static unsigned long pfn_end(struct dev_pagemap *pgmap)
 	return (res->start + resource_size(res)) >> PAGE_SHIFT;
 }
 
+static unsigned long pfn_next(unsigned long pfn)
+{
+	if (pfn % 1024 == 0)
+		cond_resched();
+	return pfn + 1;
+}
+
 #define for_each_device_pfn(pfn, map) \
-	for (pfn = pfn_first(map); pfn < pfn_end(map); pfn++)
+	for (pfn = pfn_first(map); pfn < pfn_end(map); pfn = pfn_next(pfn))
 
 static void devm_memremap_pages_release(void *data)
 {
@@ -337,10 +344,10 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 	resource_size_t align_start, align_size, align_end;
 	struct vmem_altmap *altmap = pgmap->altmap_valid ?
 			&pgmap->altmap : NULL;
+	struct resource *res = &pgmap->res;
 	unsigned long pfn, pgoff, order;
 	pgprot_t pgprot = PAGE_KERNEL;
-	int error, nid, is_ram, i = 0;
-	struct resource *res = &pgmap->res;
+	int error, nid, is_ram;
 
 	align_start = res->start & ~(SECTION_SIZE - 1);
 	align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
@@ -409,8 +416,6 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 		list_del(&page->lru);
 		page->pgmap = pgmap;
 		percpu_ref_get(pgmap->ref);
-		if (!(++i % 1024))
-			cond_resched();
 	}
 
 	devm_add_action(dev, devm_memremap_pages_release, pgmap);

kernel/panic.c

@@ -640,7 +640,7 @@ device_initcall(register_warn_debugfs);
  */
 __visible void __stack_chk_fail(void)
 {
-	panic("stack-protector: Kernel stack is corrupted in: %p\n",
+	panic("stack-protector: Kernel stack is corrupted in: %pB\n",
 		__builtin_return_address(0));
 }
 EXPORT_SYMBOL(__stack_chk_fail);

kernel/printk/printk.c

@@ -2397,7 +2397,7 @@ skip:
 
 		if (console_lock_spinning_disable_and_check()) {
 			printk_safe_exit_irqrestore(flags);
-			return;
+			goto out;
 		}
 
 		printk_safe_exit_irqrestore(flags);
@@ -2430,6 +2430,7 @@ skip:
 	if (retry && console_trylock())
 		goto again;
 
+out:
 	if (wake_klogd)
 		wake_up_klogd();
 }

kernel/relay.c

@@ -163,7 +163,7 @@ static struct rchan_buf *relay_create_buf(struct rchan *chan)
 {
 	struct rchan_buf *buf;
 
-	if (chan->n_subbufs > UINT_MAX / sizeof(size_t *))
+	if (chan->n_subbufs > KMALLOC_MAX_SIZE / sizeof(size_t *))
 		return NULL;
 
 	buf = kzalloc(sizeof(struct rchan_buf), GFP_KERNEL);

kernel/seccomp.c

@@ -1076,14 +1076,16 @@ long seccomp_get_metadata(struct task_struct *task,
 
 	size = min_t(unsigned long, size, sizeof(kmd));
 
-	if (copy_from_user(&kmd, data, size))
+	if (size < sizeof(kmd.filter_off))
+		return -EINVAL;
+
+	if (copy_from_user(&kmd.filter_off, data, sizeof(kmd.filter_off)))
 		return -EFAULT;
 
 	filter = get_nth_filter(task, kmd.filter_off);
 	if (IS_ERR(filter))
 		return PTR_ERR(filter);
 
-	memset(&kmd, 0, sizeof(kmd));
 	if (filter->log)
 		kmd.flags |= SECCOMP_FILTER_FLAG_LOG;
 

kernel/time/timer.c

@@ -1894,6 +1894,12 @@ int timers_dead_cpu(unsigned int cpu)
 		raw_spin_lock_irq(&new_base->lock);
 		raw_spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
 
+		/*
+		 * The current CPUs base clock might be stale. Update it
+		 * before moving the timers over.
+		 */
+		forward_timer_base(new_base);
+
 		BUG_ON(old_base->running_timer);
 
 		for (i = 0; i < WHEEL_SIZE; i++)

kernel/trace/bpf_trace.c

@@ -872,6 +872,8 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info)
 		return -EINVAL;
 	if (copy_from_user(&query, uquery, sizeof(query)))
 		return -EFAULT;
+	if (query.ids_len > BPF_TRACE_MAX_PROGS)
+		return -E2BIG;
 
 	mutex_lock(&bpf_event_mutex);
 	ret = bpf_prog_array_copy_info(event->tp_event->prog_array,

kernel/user.c

@@ -101,6 +101,7 @@ struct user_struct root_user = {
 	.sigpending	= ATOMIC_INIT(0),
 	.locked_shm     = 0,
 	.uid		= GLOBAL_ROOT_UID,
+	.ratelimit	= RATELIMIT_STATE_INIT(root_user.ratelimit, 0, 0),
 };
 
 /*
@@ -191,6 +192,8 @@ struct user_struct *alloc_uid(kuid_t uid)
 
 		new->uid = uid;
 		atomic_set(&new->__count, 1);
+		ratelimit_state_init(&new->ratelimit, HZ, 100);
+		ratelimit_set_flags(&new->ratelimit, RATELIMIT_MSG_ON_RELEASE);
 
 		/*
 		 * Before adding this, check whether we raced

kernel/workqueue.c

@@ -4179,6 +4179,22 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active)
 }
 EXPORT_SYMBOL_GPL(workqueue_set_max_active);
 
+/**
+ * current_work - retrieve %current task's work struct
+ *
+ * Determine if %current task is a workqueue worker and what it's working on.
+ * Useful to find out the context that the %current task is running in.
+ *
+ * Return: work struct if %current task is a workqueue worker, %NULL otherwise.
+ */
+struct work_struct *current_work(void)
+{
+	struct worker *worker = current_wq_worker();
+
+	return worker ? worker->current_work : NULL;
+}
+EXPORT_SYMBOL(current_work);
+
 /**
  * current_is_workqueue_rescuer - is %current workqueue rescuer?
  *