Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR.

No conflicts.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>

11 files changed, 184 insertions, 36 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index f93e835d90af..69101200c124 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -8519,7 +8519,7 @@ bool btf_nested_type_is_trusted(struct bpf_verifier_log *log,
 	tname = btf_name_by_offset(btf, walk_type->name_off);
 
 	ret = snprintf(safe_tname, sizeof(safe_tname), "%s%s", tname, suffix);
-	if (ret < 0)
+	if (ret >= sizeof(safe_tname))
 		return false;
 
 	safe_id = btf_find_by_name_kind(btf, safe_tname, BTF_INFO_KIND(walk_type->info));
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 5b2741aa0d9b..03b3d4492980 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -785,7 +785,8 @@ found:
  *                          to descendants
  * @cgrp: The cgroup which descendants to traverse
  * @link: A link for which to replace BPF program
- * @type: Type of attach operation
+ * @new_prog: &struct bpf_prog for the target BPF program with its refcnt
+ *            incremented
  *
  * Must be called with cgroup_mutex held.
  */
@@ -1334,7 +1335,7 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr,
  * __cgroup_bpf_run_filter_skb() - Run a program for packet filtering
  * @sk: The socket sending or receiving traffic
  * @skb: The skb that is being sent or received
- * @type: The type of program to be executed
+ * @atype: The type of program to be executed
  *
  * If no socket is passed, or the socket is not of type INET or INET6,
  * this function does nothing and returns 0.
@@ -1424,7 +1425,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb);
 /**
  * __cgroup_bpf_run_filter_sk() - Run a program on a sock
  * @sk: sock structure to manipulate
- * @type: The type of program to be executed
+ * @atype: The type of program to be executed
  *
  * socket is passed is expected to be of type INET or INET6.
  *
@@ -1449,7 +1450,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);
  *                                       provided by user sockaddr
  * @sk: sock struct that will use sockaddr
  * @uaddr: sockaddr struct provided by user
- * @type: The type of program to be executed
+ * @atype: The type of program to be executed
  * @t_ctx: Pointer to attach type specific context
  * @flags: Pointer to u32 which contains higher bits of BPF program
  *         return value (OR'ed together).
@@ -1496,7 +1497,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr);
  * @sock_ops: bpf_sock_ops_kern struct to pass to program. Contains
  * sk with connection information (IP addresses, etc.) May not contain
  * cgroup info if it is a req sock.
- * @type: The type of program to be executed
+ * @atype: The type of program to be executed
  *
  * socket passed is expected to be of type INET or INET6.
  *
@@ -1670,7 +1671,7 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = {
  * @ppos: value-result argument: value is position at which read from or write
  *	to sysctl is happening, result is new position if program overrode it,
  *	initial value otherwise
- * @type: type of program to be executed
+ * @atype: type of program to be executed
  *
  * Program is run when sysctl is being accessed, either read or written, and
  * can allow or deny such access.
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 961df89d45f1..0ad175277f89 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -459,8 +459,7 @@ static void notrace irq_work_raise(struct bpf_mem_cache *c)
  * Typical case will be between 11K and 116K closer to 11K.
  * bpf progs can and should share bpf_mem_cache when possible.
  */
-
-static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
+static void init_refill_work(struct bpf_mem_cache *c)
 {
 	init_irq_work(&c->refill_work, bpf_mem_refill);
 	if (c->unit_size <= 256) {
@@ -476,7 +475,10 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
 		c->high_watermark = max(96 * 256 / c->unit_size, 3);
 	}
 	c->batch = max((c->high_watermark - c->low_watermark) / 4 * 3, 1);
+}
 
+static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
+{
 	/* To avoid consuming memory assume that 1st run of bpf
 	 * prog won't be doing more than 4 map_update_elem from
 	 * irq disabled region
@@ -484,6 +486,31 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
 	alloc_bulk(c, c->unit_size <= 256 ? 4 : 1, cpu_to_node(cpu), false);
 }
 
+static int check_obj_size(struct bpf_mem_cache *c, unsigned int idx)
+{
+	struct llist_node *first;
+	unsigned int obj_size;
+
+	/* For per-cpu allocator, the size of free objects in free list doesn't
+	 * match with unit_size and now there is no way to get the size of
+	 * per-cpu pointer saved in free object, so just skip the checking.
+	 */
+	if (c->percpu_size)
+		return 0;
+
+	first = c->free_llist.first;
+	if (!first)
+		return 0;
+
+	obj_size = ksize(first);
+	if (obj_size != c->unit_size) {
+		WARN_ONCE(1, "bpf_mem_cache[%u]: unexpected object size %u, expect %u\n",
+			  idx, obj_size, c->unit_size);
+		return -EINVAL;
+	}
+	return 0;
+}
+
 /* When size != 0 bpf_mem_cache for each cpu.
  * This is typical bpf hash map use case when all elements have equal size.
  *
@@ -494,10 +521,10 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
 int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 {
 	static u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096};
+	int cpu, i, err, unit_size, percpu_size = 0;
 	struct bpf_mem_caches *cc, __percpu *pcc;
 	struct bpf_mem_cache *c, __percpu *pc;
 	struct obj_cgroup *objcg = NULL;
-	int cpu, i, unit_size, percpu_size = 0;
 
 	/* room for llist_node and per-cpu pointer */
 	if (percpu)
@@ -522,6 +549,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 			c->objcg = objcg;
 			c->percpu_size = percpu_size;
 			c->tgt = c;
+			init_refill_work(c);
 			prefill_mem_cache(c, cpu);
 		}
 		ma->cache = pc;
@@ -531,6 +559,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 	pcc = __alloc_percpu_gfp(sizeof(*cc), 8, GFP_KERNEL);
 	if (!pcc)
 		return -ENOMEM;
+	err = 0;
 #ifdef CONFIG_MEMCG_KMEM
 	objcg = get_obj_cgroup_from_current();
 #endif
@@ -542,11 +571,30 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 			c->objcg = objcg;
 			c->percpu_size = percpu_size;
 			c->tgt = c;
+
+			init_refill_work(c);
+			/* Another bpf_mem_cache will be used when allocating
+			 * c->unit_size in bpf_mem_alloc(), so doesn't prefill
+			 * for the bpf_mem_cache because these free objects will
+			 * never be used.
+			 */
+			if (i != bpf_mem_cache_idx(c->unit_size))
+				continue;
 			prefill_mem_cache(c, cpu);
+			err = check_obj_size(c, i);
+			if (err)
+				goto out;
 		}
 	}
+
+out:
 	ma->caches = pcc;
-	return 0;
+	/* refill_work is either zeroed or initialized, so it is safe to
+	 * call irq_work_sync().
+	 */
+	if (err)
+		bpf_mem_alloc_destroy(ma);
+	return err;
 }
 
 static void drain_mem_cache(struct bpf_mem_cache *c)
@@ -924,3 +972,41 @@ void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags)
 
 	return !ret ? NULL : ret + LLIST_NODE_SZ;
 }
+
+/* Most of the logic is taken from setup_kmalloc_cache_index_table() */
+static __init int bpf_mem_cache_adjust_size(void)
+{
+	unsigned int size, index;
+
+	/* Normally KMALLOC_MIN_SIZE is 8-bytes, but it can be
+	 * up-to 256-bytes.
+	 */
+	size = KMALLOC_MIN_SIZE;
+	if (size <= 192)
+		index = size_index[(size - 1) / 8];
+	else
+		index = fls(size - 1) - 1;
+	for (size = 8; size < KMALLOC_MIN_SIZE && size <= 192; size += 8)
+		size_index[(size - 1) / 8] = index;
+
+	/* The minimal alignment is 64-bytes, so disable 96-bytes cache and
+	 * use 128-bytes cache instead.
+	 */
+	if (KMALLOC_MIN_SIZE >= 64) {
+		index = size_index[(128 - 1) / 8];
+		for (size = 64 + 8; size <= 96; size += 8)
+			size_index[(size - 1) / 8] = index;
+	}
+
+	/* The minimal alignment is 128-bytes, so disable 192-bytes cache and
+	 * use 256-bytes cache instead.
+	 */
+	if (KMALLOC_MIN_SIZE >= 128) {
+		index = fls(256 - 1) - 1;
+		for (size = 128 + 8; size <= 192; size += 8)
+			size_index[(size - 1) / 8] = index;
+	}
+
+	return 0;
+}
+subsys_initcall(bpf_mem_cache_adjust_size);
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 92c9df46134a..1a4fec330eaa 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -199,12 +199,14 @@ static int __bpf_prog_dev_bound_init(struct bpf_prog *prog, struct net_device *n
 	offload->netdev = netdev;
 
 	ondev = bpf_offload_find_netdev(offload->netdev);
+	/* When program is offloaded require presence of "true"
+	 * bpf_offload_netdev, avoid the one created for !ondev case below.
+	 */
+	if (bpf_prog_is_offloaded(prog->aux) && (!ondev || !ondev->offdev)) {
+		err = -EINVAL;
+		goto err_free;
+	}
 	if (!ondev) {
-		if (bpf_prog_is_offloaded(prog->aux)) {
-			err = -EINVAL;
-			goto err_free;
-		}
-
 		/* When only binding to the device, explicitly
 		 * create an entry in the hashtable.
 		 */
diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c
index 8d2ddcb7566b..d869f51ea93a 100644
--- a/kernel/bpf/queue_stack_maps.c
+++ b/kernel/bpf/queue_stack_maps.c
@@ -98,7 +98,12 @@ static long __queue_map_get(struct bpf_map *map, void *value, bool delete)
 	int err = 0;
 	void *ptr;
 
-	raw_spin_lock_irqsave(&qs->lock, flags);
+	if (in_nmi()) {
+		if (!raw_spin_trylock_irqsave(&qs->lock, flags))
+			return -EBUSY;
+	} else {
+		raw_spin_lock_irqsave(&qs->lock, flags);
+	}
 
 	if (queue_stack_map_is_empty(qs)) {
 		memset(value, 0, qs->map.value_size);
@@ -128,7 +133,12 @@ static long __stack_map_get(struct bpf_map *map, void *value, bool delete)
 	void *ptr;
 	u32 index;
 
-	raw_spin_lock_irqsave(&qs->lock, flags);
+	if (in_nmi()) {
+		if (!raw_spin_trylock_irqsave(&qs->lock, flags))
+			return -EBUSY;
+	} else {
+		raw_spin_lock_irqsave(&qs->lock, flags);
+	}
 
 	if (queue_stack_map_is_empty(qs)) {
 		memset(value, 0, qs->map.value_size);
@@ -193,7 +203,12 @@ static long queue_stack_map_push_elem(struct bpf_map *map, void *value,
 	if (flags & BPF_NOEXIST || flags > BPF_EXIST)
 		return -EINVAL;
 
-	raw_spin_lock_irqsave(&qs->lock, irq_flags);
+	if (in_nmi()) {
+		if (!raw_spin_trylock_irqsave(&qs->lock, irq_flags))
+			return -EBUSY;
+	} else {
+		raw_spin_lock_irqsave(&qs->lock, irq_flags);
+	}
 
 	if (queue_stack_map_is_full(qs)) {
 		if (!replace) {
diff --git a/kernel/panic.c b/kernel/panic.c
index 07239d4ad81e..ffa037fa777d 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -697,6 +697,7 @@ void warn_slowpath_fmt(const char *file, int line, unsigned taint,
 	if (!fmt) {
 		__warn(file, line, __builtin_return_address(0), taint,
 		       NULL, NULL);
+		warn_rcu_exit(rcu);
 		return;
 	}
 
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 2b4a946a6ff5..8d35b9f9aaa3 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -786,9 +786,9 @@ int hibernate(void)
 	unlock_device_hotplug();
 	if (snapshot_test) {
 		pm_pr_dbg("Checking hibernation image\n");
-		error = swsusp_check(snapshot_test);
+		error = swsusp_check(false);
 		if (!error)
-			error = load_image_and_restore(snapshot_test);
+			error = load_image_and_restore(false);
 	}
 	thaw_processes();
 
@@ -945,14 +945,14 @@ static int software_resume(void)
 	pm_pr_dbg("Looking for hibernation image.\n");
 
 	mutex_lock(&system_transition_mutex);
-	error = swsusp_check(false);
+	error = swsusp_check(true);
 	if (error)
 		goto Unlock;
 
 	/* The snapshot device should not be opened while we're running */
 	if (!hibernate_acquire()) {
 		error = -EBUSY;
-		swsusp_close(false);
+		swsusp_close(true);
 		goto Unlock;
 	}
 
@@ -973,7 +973,7 @@ static int software_resume(void)
 		goto Close_Finish;
 	}
 
-	error = load_image_and_restore(false);
+	error = load_image_and_restore(true);
 	thaw_processes();
  Finish:
 	pm_notifier_call_chain(PM_POST_RESTORE);
@@ -987,7 +987,7 @@ static int software_resume(void)
 	pm_pr_dbg("Hibernation image not present or could not be loaded.\n");
 	return error;
  Close_Finish:
-	swsusp_close(false);
+	swsusp_close(true);
 	goto Finish;
 }
 
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 46eb14dc50c3..a98f95e309a3 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -168,11 +168,11 @@ extern int swsusp_swap_in_use(void);
 #define SF_HW_SIG		8
 
 /* kernel/power/hibernate.c */
-int swsusp_check(bool snapshot_test);
+int swsusp_check(bool exclusive);
 extern void swsusp_free(void);
 extern int swsusp_read(unsigned int *flags_p);
 extern int swsusp_write(unsigned int flags);
-void swsusp_close(bool snapshot_test);
+void swsusp_close(bool exclusive);
 #ifdef CONFIG_SUSPEND
 extern int swsusp_unmark(void);
 #endif
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index f6ebcd00c410..74edbce2320b 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -1513,12 +1513,13 @@ end:
 static void *swsusp_holder;
 
 /**
- *      swsusp_check - Check for swsusp signature in the resume device
+ * swsusp_check - Check for swsusp signature in the resume device
+ * @exclusive: Open the resume device exclusively.
  */
 
-int swsusp_check(bool snapshot_test)
+int swsusp_check(bool exclusive)
 {
-	void *holder = snapshot_test ? &swsusp_holder : NULL;
+	void *holder = exclusive ? &swsusp_holder : NULL;
 	int error;
 
 	hib_resume_bdev = blkdev_get_by_dev(swsusp_resume_device, BLK_OPEN_READ,
@@ -1563,17 +1564,18 @@ put:
 }
 
 /**
- *	swsusp_close - close swap device.
+ * swsusp_close - close swap device.
+ * @exclusive: Close the resume device which is exclusively opened.
  */
 
-void swsusp_close(bool snapshot_test)
+void swsusp_close(bool exclusive)
 {
 	if (IS_ERR(hib_resume_bdev)) {
 		pr_debug("Image device not initialised\n");
 		return;
 	}
 
-	blkdev_put(hib_resume_bdev, snapshot_test ? &swsusp_holder : NULL);
+	blkdev_put(hib_resume_bdev, exclusive ? &swsusp_holder : NULL);
 }
 
 /**
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8dbff6e7ad4f..cb225921bbca 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6619,6 +6619,7 @@ dequeue_throttle:
 /* Working cpumask for: load_balance, load_balance_newidle. */
 static DEFINE_PER_CPU(cpumask_var_t, load_balance_mask);
 static DEFINE_PER_CPU(cpumask_var_t, select_rq_mask);
+static DEFINE_PER_CPU(cpumask_var_t, should_we_balance_tmpmask);
 
 #ifdef CONFIG_NO_HZ_COMMON
 
@@ -9579,7 +9580,7 @@ static inline long sibling_imbalance(struct lb_env *env,
 	imbalance /= ncores_local + ncores_busiest;
 
 	/* Take advantage of resource in an empty sched group */
-	if (imbalance == 0 && local->sum_nr_running == 0 &&
+	if (imbalance <= 1 && local->sum_nr_running == 0 &&
 	    busiest->sum_nr_running > 1)
 		imbalance = 2;
 
@@ -9767,6 +9768,15 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 		break;
 
 	case group_smt_balance:
+		/*
+		 * Check if we have spare CPUs on either SMT group to
+		 * choose has spare or fully busy handling.
+		 */
+		if (sgs->idle_cpus != 0 || busiest->idle_cpus != 0)
+			goto has_spare;
+
+		fallthrough;
+
 	case group_fully_busy:
 		/*
 		 * Select the fully busy group with highest avg_load. In
@@ -9806,6 +9816,7 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 			else
 				return true;
 		}
+has_spare:
 
 		/*
 		 * Select not overloaded group with lowest number of idle cpus
@@ -10917,6 +10928,7 @@ static int active_load_balance_cpu_stop(void *data);
 
 static int should_we_balance(struct lb_env *env)
 {
+	struct cpumask *swb_cpus = this_cpu_cpumask_var_ptr(should_we_balance_tmpmask);
 	struct sched_group *sg = env->sd->groups;
 	int cpu, idle_smt = -1;
 
@@ -10940,8 +10952,9 @@ static int should_we_balance(struct lb_env *env)
 		return 1;
 	}
 
+	cpumask_copy(swb_cpus, group_balance_mask(sg));
 	/* Try to find first idle CPU */
-	for_each_cpu_and(cpu, group_balance_mask(sg), env->cpus) {
+	for_each_cpu_and(cpu, swb_cpus, env->cpus) {
 		if (!idle_cpu(cpu))
 			continue;
 
@@ -10953,6 +10966,14 @@ static int should_we_balance(struct lb_env *env)
 		if (!(env->sd->flags & SD_SHARE_CPUCAPACITY) && !is_core_idle(cpu)) {
 			if (idle_smt == -1)
 				idle_smt = cpu;
+			/*
+			 * If the core is not idle, and first SMT sibling which is
+			 * idle has been found, then its not needed to check other
+			 * SMT siblings for idleness:
+			 */
+#ifdef CONFIG_SCHED_SMT
+			cpumask_andnot(swb_cpus, swb_cpus, cpu_smt_mask(cpu));
+#endif
 			continue;
 		}
 
@@ -12918,6 +12939,8 @@ __init void init_sched_fair_class(void)
 	for_each_possible_cpu(i) {
 		zalloc_cpumask_var_node(&per_cpu(load_balance_mask, i), GFP_KERNEL, cpu_to_node(i));
 		zalloc_cpumask_var_node(&per_cpu(select_rq_mask,    i), GFP_KERNEL, cpu_to_node(i));
+		zalloc_cpumask_var_node(&per_cpu(should_we_balance_tmpmask, i),
+					GFP_KERNEL, cpu_to_node(i));
 
 #ifdef CONFIG_CFS_BANDWIDTH
 		INIT_CSD(&cpu_rq(i)->cfsb_csd, __cfsb_csd_unthrottle, cpu_rq(i));
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index a7264b2c17ad..868008f56fec 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2853,6 +2853,17 @@ static int get_modules_for_addrs(struct module ***mods, unsigned long *addrs, u3
 	return arr.mods_cnt;
 }
 
+static int addrs_check_error_injection_list(unsigned long *addrs, u32 cnt)
+{
+	u32 i;
+
+	for (i = 0; i < cnt; i++) {
+		if (!within_error_injection_list(addrs[i]))
+			return -EINVAL;
+	}
+	return 0;
+}
+
 int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 {
 	struct bpf_kprobe_multi_link *link = NULL;
@@ -2930,6 +2941,11 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 			goto error;
 	}
 
+	if (prog->kprobe_override && addrs_check_error_injection_list(addrs, cnt)) {
+		err = -EINVAL;
+		goto error;
+	}
+
 	link = kzalloc(sizeof(*link), GFP_KERNEL);
 	if (!link) {
 		err = -ENOMEM;
@@ -3207,8 +3223,10 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 		rcu_read_lock();
 		task = get_pid_task(find_vpid(pid), PIDTYPE_PID);
 		rcu_read_unlock();
-		if (!task)
+		if (!task) {
+			err = -ESRCH;
 			goto error_path_put;
+		}
 	}
 
 	err = -ENOMEM;