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

Conflicts:

MAINTAINERS
 - keep Chandrasekar
drivers/net/ethernet/mellanox/mlx5/core/en_main.c
 - simple fix + trust the code re-added to param.c in -next is fine
include/linux/bpf.h
 - trivial
include/linux/ethtool.h
 - trivial, fix kdoc while at it
include/linux/skmsg.h
 - move to relevant place in tcp.c, comment re-wrapped
net/core/skmsg.c
 - add the sk = sk // sk = NULL around calls
net/tipc/crypto.c
 - trivial

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

14 files changed, 89 insertions, 42 deletions

diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c
index dad821c8ecd0..bbfc6bb79240 100644
--- a/kernel/bpf/disasm.c
+++ b/kernel/bpf/disasm.c
@@ -91,7 +91,7 @@ static const char *const bpf_atomic_alu_string[16] = {
 	[BPF_ADD >> 4]  = "add",
 	[BPF_AND >> 4]  = "and",
 	[BPF_OR >> 4]  = "or",
-	[BPF_XOR >> 4]  = "or",
+	[BPF_XOR >> 4]  = "xor",
 };
 
 static const char *const bpf_ldst_string[] = {
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 1576ff331ee4..d2de2abec35b 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -543,11 +543,11 @@ int bpf_obj_get_user(const char __user *pathname, int flags)
 		return PTR_ERR(raw);
 
 	if (type == BPF_TYPE_PROG)
-		ret = bpf_prog_new_fd(raw);
+		ret = (f_flags != O_RDWR) ? -EINVAL : bpf_prog_new_fd(raw);
 	else if (type == BPF_TYPE_MAP)
 		ret = bpf_map_new_fd(raw, f_flags);
 	else if (type == BPF_TYPE_LINK)
-		ret = bpf_link_new_fd(raw);
+		ret = (f_flags != O_RDWR) ? -EINVAL : bpf_link_new_fd(raw);
 	else
 		return -ENOENT;
 
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index be35bfb7fb13..6fbc2abe9c91 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -517,9 +517,17 @@ const struct bpf_func_proto bpf_get_stack_proto = {
 BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf,
 	   u32, size, u64, flags)
 {
-	struct pt_regs *regs = task_pt_regs(task);
+	struct pt_regs *regs;
+	long res;
 
-	return __bpf_get_stack(regs, task, NULL, buf, size, flags);
+	if (!try_get_task_stack(task))
+		return -EFAULT;
+
+	regs = task_pt_regs(task);
+	res = __bpf_get_stack(regs, task, NULL, buf, size, flags);
+	put_task_stack(task);
+
+	return res;
 }
 
 BTF_ID_LIST_SINGLE(bpf_get_task_stack_btf_ids, struct, task_struct)
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 1f3a4be4b175..4aa8b52adf25 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -9,6 +9,7 @@
 #include <linux/btf.h>
 #include <linux/rcupdate_trace.h>
 #include <linux/rcupdate_wait.h>
+#include <linux/module.h>
 
 /* dummy _ops. The verifier will operate on target program's ops. */
 const struct bpf_verifier_ops bpf_extension_verifier_ops = {
@@ -87,6 +88,26 @@ out:
 	return tr;
 }
 
+static int bpf_trampoline_module_get(struct bpf_trampoline *tr)
+{
+	struct module *mod;
+	int err = 0;
+
+	preempt_disable();
+	mod = __module_text_address((unsigned long) tr->func.addr);
+	if (mod && !try_module_get(mod))
+		err = -ENOENT;
+	preempt_enable();
+	tr->mod = mod;
+	return err;
+}
+
+static void bpf_trampoline_module_put(struct bpf_trampoline *tr)
+{
+	module_put(tr->mod);
+	tr->mod = NULL;
+}
+
 static int is_ftrace_location(void *ip)
 {
 	long addr;
@@ -108,6 +129,9 @@ static int unregister_fentry(struct bpf_trampoline *tr, void *old_addr)
 		ret = unregister_ftrace_direct((long)ip, (long)old_addr);
 	else
 		ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, NULL);
+
+	if (!ret)
+		bpf_trampoline_module_put(tr);
 	return ret;
 }
 
@@ -134,10 +158,16 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr)
 		return ret;
 	tr->func.ftrace_managed = ret;
 
+	if (bpf_trampoline_module_get(tr))
+		return -ENOENT;
+
 	if (tr->func.ftrace_managed)
 		ret = register_ftrace_direct((long)ip, (long)new_addr);
 	else
 		ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, NULL, new_addr);
+
+	if (ret)
+		bpf_trampoline_module_put(tr);
 	return ret;
 }
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 852541a435ef..f63b27574b3a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -12724,6 +12724,11 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env)
 	u32 btf_id, member_idx;
 	const char *mname;
 
+	if (!prog->gpl_compatible) {
+		verbose(env, "struct ops programs must have a GPL compatible license\n");
+		return -EINVAL;
+	}
+
 	btf_id = prog->aux->attach_btf_id;
 	st_ops = bpf_struct_ops_find(btf_id);
 	if (!st_ops) {
diff --git a/kernel/fork.c b/kernel/fork.c
index 50209691f21a..85ca68f4b01e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1950,8 +1950,14 @@ static __latent_entropy struct task_struct *copy_process(
 	p = dup_task_struct(current, node);
 	if (!p)
 		goto fork_out;
-	if (args->io_thread)
+	if (args->io_thread) {
+		/*
+		 * Mark us an IO worker, and block any signal that isn't
+		 * fatal or STOP
+		 */
 		p->flags |= PF_IO_WORKER;
+		siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP));
+	}
 
 	/*
 	 * This _must_ happen before we call free_task(), i.e. before we jump
@@ -2443,14 +2449,8 @@ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node)
 		.stack_size	= (unsigned long)arg,
 		.io_thread	= 1,
 	};
-	struct task_struct *tsk;
 
-	tsk = copy_process(NULL, 0, node, &args);
-	if (!IS_ERR(tsk)) {
-		sigfillset(&tsk->blocked);
-		sigdelsetmask(&tsk->blocked, sigmask(SIGKILL));
-	}
-	return tsk;
+	return copy_process(NULL, 0, node, &args);
 }
 
 /*
diff --git a/kernel/freezer.c b/kernel/freezer.c
index 1a2d57d1327c..dc520f01f99d 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -134,7 +134,7 @@ bool freeze_task(struct task_struct *p)
 		return false;
 	}
 
-	if (!(p->flags & (PF_KTHREAD | PF_IO_WORKER)))
+	if (!(p->flags & PF_KTHREAD))
 		fake_signal_wake_up(p);
 	else
 		wake_up_state(p, TASK_INTERRUPTIBLE);
diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
index 1358fa4abfa8..0f4530b3a8cd 100644
--- a/kernel/power/energy_model.c
+++ b/kernel/power/energy_model.c
@@ -98,7 +98,7 @@ static int __init em_debug_init(void)
 
 	return 0;
 }
-core_initcall(em_debug_init);
+fs_initcall(em_debug_init);
 #else /* CONFIG_DEBUG_FS */
 static void em_debug_create_pd(struct device *dev) {}
 static void em_debug_remove_pd(struct device *dev) {}
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 821cf1723814..61db50f7ca86 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -375,7 +375,7 @@ static int ptrace_attach(struct task_struct *task, long request,
 	audit_ptrace(task);
 
 	retval = -EPERM;
-	if (unlikely(task->flags & (PF_KTHREAD | PF_IO_WORKER)))
+	if (unlikely(task->flags & PF_KTHREAD))
 		goto out;
 	if (same_thread_group(task, current))
 		goto out;
diff --git a/kernel/signal.c b/kernel/signal.c
index f2a1b898da29..f2718350bf4b 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -91,7 +91,7 @@ static bool sig_task_ignored(struct task_struct *t, int sig, bool force)
 		return true;
 
 	/* Only allow kernel generated signals to this kthread */
-	if (unlikely((t->flags & (PF_KTHREAD | PF_IO_WORKER)) &&
+	if (unlikely((t->flags & PF_KTHREAD) &&
 		     (handler == SIG_KTHREAD_KERNEL) && !force))
 		return true;
 
@@ -288,8 +288,7 @@ bool task_set_jobctl_pending(struct task_struct *task, unsigned long mask)
 			JOBCTL_STOP_SIGMASK | JOBCTL_TRAPPING));
 	BUG_ON((mask & JOBCTL_TRAPPING) && !(mask & JOBCTL_PENDING_MASK));
 
-	if (unlikely(fatal_signal_pending(task) ||
-		     (task->flags & (PF_EXITING | PF_IO_WORKER))))
+	if (unlikely(fatal_signal_pending(task) || (task->flags & PF_EXITING)))
 		return false;
 
 	if (mask & JOBCTL_STOP_SIGMASK)
@@ -834,9 +833,6 @@ static int check_kill_permission(int sig, struct kernel_siginfo *info,
 
 	if (!valid_signal(sig))
 		return -EINVAL;
-	/* PF_IO_WORKER threads don't take any signals */
-	if (t->flags & PF_IO_WORKER)
-		return -ESRCH;
 
 	if (!si_fromuser(info))
 		return 0;
@@ -1100,7 +1096,7 @@ static int __send_signal(int sig, struct kernel_siginfo *info, struct task_struc
 	/*
 	 * Skip useless siginfo allocation for SIGKILL and kernel threads.
 	 */
-	if ((sig == SIGKILL) || (t->flags & (PF_KTHREAD | PF_IO_WORKER)))
+	if ((sig == SIGKILL) || (t->flags & PF_KTHREAD))
 		goto out_set;
 
 	/*
@@ -2772,13 +2768,21 @@ relock:
 		}
 
 		/*
+		 * PF_IO_WORKER threads will catch and exit on fatal signals
+		 * themselves. They have cleanup that must be performed, so
+		 * we cannot call do_exit() on their behalf.
+		 */
+		if (current->flags & PF_IO_WORKER)
+			goto out;
+
+		/*
 		 * Death signals, no core dump.
 		 */
 		do_group_exit(ksig->info.si_signo);
 		/* NOTREACHED */
 	}
 	spin_unlock_irq(&sighand->siglock);
-
+out:
 	ksig->sig = signr;
 
 	if (!(ksig->ka.sa.sa_flags & SA_EXPOSE_TAGBITS))
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index b7e29db127fa..3ba52d4e1314 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3231,7 +3231,8 @@ ftrace_allocate_pages(unsigned long num_to_init)
 	pg = start_pg;
 	while (pg) {
 		order = get_count_order(pg->size / ENTRIES_PER_PAGE);
-		free_pages((unsigned long)pg->records, order);
+		if (order >= 0)
+			free_pages((unsigned long)pg->records, order);
 		start_pg = pg->next;
 		kfree(pg);
 		pg = start_pg;
@@ -6451,7 +6452,8 @@ void ftrace_release_mod(struct module *mod)
 		clear_mod_from_hashes(pg);
 
 		order = get_count_order(pg->size / ENTRIES_PER_PAGE);
-		free_pages((unsigned long)pg->records, order);
+		if (order >= 0)
+			free_pages((unsigned long)pg->records, order);
 		tmp_page = pg->next;
 		kfree(pg);
 		ftrace_number_of_pages -= 1 << order;
@@ -6811,7 +6813,8 @@ void ftrace_free_mem(struct module *mod, void *start_ptr, void *end_ptr)
 		if (!pg->index) {
 			*last_pg = pg->next;
 			order = get_count_order(pg->size / ENTRIES_PER_PAGE);
-			free_pages((unsigned long)pg->records, order);
+			if (order >= 0)
+				free_pages((unsigned long)pg->records, order);
 			ftrace_number_of_pages -= 1 << order;
 			ftrace_number_of_groups--;
 			kfree(pg);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index eccb4e1187cc..5c777627212f 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2984,7 +2984,8 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer,
 
 	size = nr_entries * sizeof(unsigned long);
 	event = __trace_buffer_lock_reserve(buffer, TRACE_STACK,
-					    sizeof(*entry) + size, trace_ctx);
+				    (sizeof(*entry) - sizeof(entry->caller)) + size,
+				    trace_ctx);
 	if (!event)
 		goto out;
 	entry = ring_buffer_event_data(event);
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 71109065bd8e..107bc38b1945 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -278,9 +278,10 @@ void touch_all_softlockup_watchdogs(void)
 	 * update as well, the only side effect might be a cycle delay for
 	 * the softlockup check.
 	 */
-	for_each_cpu(cpu, &watchdog_allowed_mask)
+	for_each_cpu(cpu, &watchdog_allowed_mask) {
 		per_cpu(watchdog_touch_ts, cpu) = SOFTLOCKUP_RESET;
-	wq_watchdog_touch(-1);
+		wq_watchdog_touch(cpu);
+	}
 }
 
 void touch_softlockup_watchdog_sync(void)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 0d150da252e8..79f2319543ce 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1412,7 +1412,6 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 	 */
 	lockdep_assert_irqs_disabled();
 
-	debug_work_activate(work);
 
 	/* if draining, only works from the same workqueue are allowed */
 	if (unlikely(wq->flags & __WQ_DRAINING) &&
@@ -1494,6 +1493,7 @@ retry:
 		worklist = &pwq->delayed_works;
 	}
 
+	debug_work_activate(work);
 	insert_work(pwq, work, worklist, work_flags);
 
 out:
@@ -5787,22 +5787,17 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
 			continue;
 
 		/* get the latest of pool and touched timestamps */
+		if (pool->cpu >= 0)
+			touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu));
+		else
+			touched = READ_ONCE(wq_watchdog_touched);
 		pool_ts = READ_ONCE(pool->watchdog_ts);
-		touched = READ_ONCE(wq_watchdog_touched);
 
 		if (time_after(pool_ts, touched))
 			ts = pool_ts;
 		else
 			ts = touched;
 
-		if (pool->cpu >= 0) {
-			unsigned long cpu_touched =
-				READ_ONCE(per_cpu(wq_watchdog_touched_cpu,
-						  pool->cpu));
-			if (time_after(cpu_touched, ts))
-				ts = cpu_touched;
-		}
-
 		/* did we stall? */
 		if (time_after(jiffies, ts + thresh)) {
 			lockup_detected = true;
@@ -5826,8 +5821,8 @@ notrace void wq_watchdog_touch(int cpu)
 {
 	if (cpu >= 0)
 		per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies;
-	else
-		wq_watchdog_touched = jiffies;
+
+	wq_watchdog_touched = jiffies;
 }
 
 static void wq_watchdog_set_thresh(unsigned long thresh)