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

Cross-merge networking fixes after downstream PR (net-6.13-rc6).

No conflicts.

Adjacent changes:

include/linux/if_vlan.h
  f91a5b808938 ("af_packet: fix vlan_get_protocol_dgram() vs MSG_PEEK")
  3f330db30638 ("net: reformat kdoc return statements")

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

10 files changed, 61 insertions, 20 deletions

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index f7f892a52a37..77f56674aaa9 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -21281,11 +21281,15 @@ patch_map_ops_generic:
 			 * changed in some incompatible and hard to support
 			 * way, it's fine to back out this inlining logic
 			 */
+#ifdef CONFIG_SMP
 			insn_buf[0] = BPF_MOV32_IMM(BPF_REG_0, (u32)(unsigned long)&pcpu_hot.cpu_number);
 			insn_buf[1] = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0);
 			insn_buf[2] = BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0);
 			cnt = 3;
-
+#else
+			insn_buf[0] = BPF_ALU32_REG(BPF_XOR, BPF_REG_0, BPF_REG_0);
+			cnt = 1;
+#endif
 			new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
 			if (!new_prog)
 				return -ENOMEM;
diff --git a/kernel/fork.c b/kernel/fork.c
index 1450b461d196..9b301180fd41 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -639,11 +639,8 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 	LIST_HEAD(uf);
 	VMA_ITERATOR(vmi, mm, 0);
 
-	uprobe_start_dup_mmap();
-	if (mmap_write_lock_killable(oldmm)) {
-		retval = -EINTR;
-		goto fail_uprobe_end;
-	}
+	if (mmap_write_lock_killable(oldmm))
+		return -EINTR;
 	flush_cache_dup_mm(oldmm);
 	uprobe_dup_mmap(oldmm, mm);
 	/*
@@ -782,8 +779,6 @@ out:
 		dup_userfaultfd_complete(&uf);
 	else
 		dup_userfaultfd_fail(&uf);
-fail_uprobe_end:
-	uprobe_end_dup_mmap();
 	return retval;
 
 fail_nomem_anon_vma_fork:
@@ -1692,9 +1687,11 @@ static struct mm_struct *dup_mm(struct task_struct *tsk,
 	if (!mm_init(mm, tsk, mm->user_ns))
 		goto fail_nomem;
 
+	uprobe_start_dup_mmap();
 	err = dup_mmap(mm, oldmm);
 	if (err)
 		goto free_pt;
+	uprobe_end_dup_mmap();
 
 	mm->hiwater_rss = get_mm_rss(mm);
 	mm->hiwater_vm = mm->total_vm;
@@ -1709,6 +1706,8 @@ free_pt:
 	mm->binfmt = NULL;
 	mm_init_owner(mm, NULL);
 	mmput(mm);
+	if (err)
+		uprobe_end_dup_mmap();
 
 fail_nomem:
 	return NULL;
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index e858de203eb6..697a56d3d949 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1292,7 +1292,13 @@ static int __sched task_blocks_on_rt_mutex(struct rt_mutex_base *lock,
 	 */
 	get_task_struct(owner);
 
+	preempt_disable();
 	raw_spin_unlock_irq(&lock->wait_lock);
+	/* wake up any tasks on the wake_q before calling rt_mutex_adjust_prio_chain */
+	wake_up_q(wake_q);
+	wake_q_init(wake_q);
+	preempt_enable();
+
 
 	res = rt_mutex_adjust_prio_chain(owner, chwalk, lock,
 					 next_lock, waiter, task);
@@ -1596,6 +1602,7 @@ static void __sched remove_waiter(struct rt_mutex_base *lock,
  *			 or TASK_UNINTERRUPTIBLE)
  * @timeout:		 the pre-initialized and started timer, or NULL for none
  * @waiter:		 the pre-initialized rt_mutex_waiter
+ * @wake_q:		 wake_q of tasks to wake when we drop the lock->wait_lock
  *
  * Must be called with lock->wait_lock held and interrupts disabled
  */
@@ -1603,7 +1610,8 @@ static int __sched rt_mutex_slowlock_block(struct rt_mutex_base *lock,
 					   struct ww_acquire_ctx *ww_ctx,
 					   unsigned int state,
 					   struct hrtimer_sleeper *timeout,
-					   struct rt_mutex_waiter *waiter)
+					   struct rt_mutex_waiter *waiter,
+					   struct wake_q_head *wake_q)
 	__releases(&lock->wait_lock) __acquires(&lock->wait_lock)
 {
 	struct rt_mutex *rtm = container_of(lock, struct rt_mutex, rtmutex);
@@ -1634,7 +1642,13 @@ static int __sched rt_mutex_slowlock_block(struct rt_mutex_base *lock,
 			owner = rt_mutex_owner(lock);
 		else
 			owner = NULL;
+		preempt_disable();
 		raw_spin_unlock_irq(&lock->wait_lock);
+		if (wake_q) {
+			wake_up_q(wake_q);
+			wake_q_init(wake_q);
+		}
+		preempt_enable();
 
 		if (!owner || !rtmutex_spin_on_owner(lock, waiter, owner))
 			rt_mutex_schedule();
@@ -1708,7 +1722,7 @@ static int __sched __rt_mutex_slowlock(struct rt_mutex_base *lock,
 
 	ret = task_blocks_on_rt_mutex(lock, waiter, current, ww_ctx, chwalk, wake_q);
 	if (likely(!ret))
-		ret = rt_mutex_slowlock_block(lock, ww_ctx, state, NULL, waiter);
+		ret = rt_mutex_slowlock_block(lock, ww_ctx, state, NULL, waiter, wake_q);
 
 	if (likely(!ret)) {
 		/* acquired the lock */
diff --git a/kernel/locking/rtmutex_api.c b/kernel/locking/rtmutex_api.c
index 33ea31d6a7b3..191e4720e546 100644
--- a/kernel/locking/rtmutex_api.c
+++ b/kernel/locking/rtmutex_api.c
@@ -383,7 +383,7 @@ int __sched rt_mutex_wait_proxy_lock(struct rt_mutex_base *lock,
 	raw_spin_lock_irq(&lock->wait_lock);
 	/* sleep on the mutex */
 	set_current_state(TASK_INTERRUPTIBLE);
-	ret = rt_mutex_slowlock_block(lock, NULL, TASK_INTERRUPTIBLE, to, waiter);
+	ret = rt_mutex_slowlock_block(lock, NULL, TASK_INTERRUPTIBLE, to, waiter, NULL);
 	/*
 	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
 	 * have to fix that up.
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index ddedcb50917f..30e3ddc8a8a8 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -833,7 +833,7 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs
 #endif
 	{
 		for_each_set_bit(i, &bitmap, sizeof(bitmap) * BITS_PER_BYTE) {
-			struct fgraph_ops *gops = fgraph_array[i];
+			struct fgraph_ops *gops = READ_ONCE(fgraph_array[i]);
 
 			if (gops == &fgraph_stub)
 				continue;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 9b17efb1a87d..2e113f8b13a2 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -902,16 +902,13 @@ static void profile_graph_return(struct ftrace_graph_ret *trace,
 }
 
 static struct fgraph_ops fprofiler_ops = {
-	.ops = {
-		.flags = FTRACE_OPS_FL_INITIALIZED,
-		INIT_OPS_HASH(fprofiler_ops.ops)
-	},
 	.entryfunc = &profile_graph_entry,
 	.retfunc = &profile_graph_return,
 };
 
 static int register_ftrace_profiler(void)
 {
+	ftrace_ops_set_global_filter(&fprofiler_ops.ops);
 	return register_ftrace_graph(&fprofiler_ops);
 }
 
@@ -922,12 +919,11 @@ static void unregister_ftrace_profiler(void)
 #else
 static struct ftrace_ops ftrace_profile_ops __read_mostly = {
 	.func		= function_profile_call,
-	.flags		= FTRACE_OPS_FL_INITIALIZED,
-	INIT_OPS_HASH(ftrace_profile_ops)
 };
 
 static int register_ftrace_profiler(void)
 {
+	ftrace_ops_set_global_filter(&ftrace_profile_ops);
 	return register_ftrace_function(&ftrace_profile_ops);
 }
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 7e257e855dd1..60210fb5b211 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -7019,7 +7019,11 @@ static int __rb_map_vma(struct ring_buffer_per_cpu *cpu_buffer,
 	lockdep_assert_held(&cpu_buffer->mapping_lock);
 
 	nr_subbufs = cpu_buffer->nr_pages + 1; /* + reader-subbuf */
-	nr_pages = ((nr_subbufs + 1) << subbuf_order) - pgoff; /* + meta-page */
+	nr_pages = ((nr_subbufs + 1) << subbuf_order); /* + meta-page */
+	if (nr_pages <= pgoff)
+		return -EINVAL;
+
+	nr_pages -= pgoff;
 
 	nr_vma_pages = vma_pages(vma);
 	if (!nr_vma_pages || nr_vma_pages > nr_pages)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 7cc18b9bce27..f8aebcb01e62 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4206,6 +4206,15 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
 	if (event) {
 		if (tr->trace_flags & TRACE_ITER_FIELDS)
 			return print_event_fields(iter, event);
+		/*
+		 * For TRACE_EVENT() events, the print_fmt is not
+		 * safe to use if the array has delta offsets
+		 * Force printing via the fields.
+		 */
+		if ((tr->text_delta || tr->data_delta) &&
+		    event->type > __TRACE_LAST_TYPE)
+			return print_event_fields(iter, event);
+
 		return event->funcs->trace(iter, sym_flags, event);
 	}
 
@@ -5078,6 +5087,9 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 	cpumask_var_t tracing_cpumask_new;
 	int err;
 
+	if (count == 0 || count > KMALLOC_MAX_SIZE)
+		return -EINVAL;
+
 	if (!zalloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL))
 		return -ENOMEM;
 
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 1545cc8b49d0..770e7ed91716 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -365,6 +365,18 @@ static bool process_string(const char *fmt, int len, struct trace_event_call *ca
 	} while (s < e);
 
 	/*
+	 * Check for arrays. If the argument has: foo[REC->val]
+	 * then it is very likely that foo is an array of strings
+	 * that are safe to use.
+	 */
+	r = strstr(s, "[");
+	if (r && r < e) {
+		r = strstr(r, "REC->");
+		if (r && r < e)
+			return true;
+	}
+
+	/*
 	 * If there's any strings in the argument consider this arg OK as it
 	 * could be: REC->field ? "foo" : "bar" and we don't want to get into
 	 * verifying that logic here.
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 263fac44d3ca..935a886af40c 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -725,7 +725,7 @@ static int trace_kprobe_module_callback(struct notifier_block *nb,
 
 static struct notifier_block trace_kprobe_module_nb = {
 	.notifier_call = trace_kprobe_module_callback,
-	.priority = 1	/* Invoked after kprobe module callback */
+	.priority = 2	/* Invoked after kprobe and jump_label module callback */
 };
 static int trace_kprobe_register_module_notifier(void)
 {