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

Cross-merge networking fixes after downstream PR.

Conflicts:

drivers/net/ethernet/broadcom/bnxt/bnxt.c
  e009b2efb7a8 ("bnxt_en: Remove mis-applied code from bnxt_cfg_ntp_filters()")
  0f2b21477988 ("bnxt_en: Fix compile error without CONFIG_RFS_ACCEL")
https://lore.kernel.org/all/20240105115509.225aa8a2@canb.auug.org.au/

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

7 files changed, 108 insertions, 78 deletions

diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec
index 2fd510256604..946dffa048b7 100644
--- a/kernel/Kconfig.kexec
+++ b/kernel/Kconfig.kexec
@@ -36,6 +36,8 @@ config KEXEC
 config KEXEC_FILE
 	bool "Enable kexec file based system call"
 	depends on ARCH_SUPPORTS_KEXEC_FILE
+	select CRYPTO
+	select CRYPTO_SHA256
 	select KEXEC_CORE
 	help
 	  This is new version of kexec system call. This system call is
diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c
index d5610ad52b92..75a6f6133866 100644
--- a/kernel/locking/osq_lock.c
+++ b/kernel/locking/osq_lock.c
@@ -11,6 +11,13 @@
  * called from interrupt context and we have preemption disabled while
  * spinning.
  */
+
+struct optimistic_spin_node {
+	struct optimistic_spin_node *next, *prev;
+	int locked; /* 1 if lock acquired */
+	int cpu; /* encoded CPU # + 1 value */
+};
+
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_node, osq_node);
 
 /*
@@ -37,32 +44,28 @@ static inline struct optimistic_spin_node *decode_cpu(int encoded_cpu_val)
 /*
  * Get a stable @node->next pointer, either for unlock() or unqueue() purposes.
  * Can return NULL in case we were the last queued and we updated @lock instead.
+ *
+ * If osq_lock() is being cancelled there must be a previous node
+ * and 'old_cpu' is its CPU #.
+ * For osq_unlock() there is never a previous node and old_cpu is
+ * set to OSQ_UNLOCKED_VAL.
  */
 static inline struct optimistic_spin_node *
 osq_wait_next(struct optimistic_spin_queue *lock,
 	      struct optimistic_spin_node *node,
-	      struct optimistic_spin_node *prev)
+	      int old_cpu)
 {
-	struct optimistic_spin_node *next = NULL;
 	int curr = encode_cpu(smp_processor_id());
-	int old;
-
-	/*
-	 * If there is a prev node in queue, then the 'old' value will be
-	 * the prev node's CPU #, else it's set to OSQ_UNLOCKED_VAL since if
-	 * we're currently last in queue, then the queue will then become empty.
-	 */
-	old = prev ? prev->cpu : OSQ_UNLOCKED_VAL;
 
 	for (;;) {
 		if (atomic_read(&lock->tail) == curr &&
-		    atomic_cmpxchg_acquire(&lock->tail, curr, old) == curr) {
+		    atomic_cmpxchg_acquire(&lock->tail, curr, old_cpu) == curr) {
 			/*
 			 * We were the last queued, we moved @lock back. @prev
 			 * will now observe @lock and will complete its
 			 * unlock()/unqueue().
 			 */
-			break;
+			return NULL;
 		}
 
 		/*
@@ -76,15 +79,15 @@ osq_wait_next(struct optimistic_spin_queue *lock,
 		 * wait for a new @node->next from its Step-C.
 		 */
 		if (node->next) {
+			struct optimistic_spin_node *next;
+
 			next = xchg(&node->next, NULL);
 			if (next)
-				break;
+				return next;
 		}
 
 		cpu_relax();
 	}
-
-	return next;
 }
 
 bool osq_lock(struct optimistic_spin_queue *lock)
@@ -186,7 +189,7 @@ bool osq_lock(struct optimistic_spin_queue *lock)
 	 * back to @prev.
 	 */
 
-	next = osq_wait_next(lock, node, prev);
+	next = osq_wait_next(lock, node, prev->cpu);
 	if (!next)
 		return false;
 
@@ -226,7 +229,7 @@ void osq_unlock(struct optimistic_spin_queue *lock)
 		return;
 	}
 
-	next = osq_wait_next(lock, node, NULL);
+	next = osq_wait_next(lock, node, OSQ_UNLOCKED_VAL);
 	if (next)
 		WRITE_ONCE(next->locked, 1);
 }
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 8de8bec5f366..b01ae7d36021 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1183,18 +1183,19 @@ static void __add_hash_entry(struct ftrace_hash *hash,
 	hash->count++;
 }
 
-static int add_hash_entry(struct ftrace_hash *hash, unsigned long ip)
+static struct ftrace_func_entry *
+add_hash_entry(struct ftrace_hash *hash, unsigned long ip)
 {
 	struct ftrace_func_entry *entry;
 
 	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry)
-		return -ENOMEM;
+		return NULL;
 
 	entry->ip = ip;
 	__add_hash_entry(hash, entry);
 
-	return 0;
+	return entry;
 }
 
 static void
@@ -1349,7 +1350,6 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash)
 	struct ftrace_func_entry *entry;
 	struct ftrace_hash *new_hash;
 	int size;
-	int ret;
 	int i;
 
 	new_hash = alloc_ftrace_hash(size_bits);
@@ -1366,8 +1366,7 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash)
 	size = 1 << hash->size_bits;
 	for (i = 0; i < size; i++) {
 		hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
-			ret = add_hash_entry(new_hash, entry->ip);
-			if (ret < 0)
+			if (add_hash_entry(new_hash, entry->ip) == NULL)
 				goto free_hash;
 		}
 	}
@@ -2536,7 +2535,7 @@ ftrace_find_unique_ops(struct dyn_ftrace *rec)
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 /* Protected by rcu_tasks for reading, and direct_mutex for writing */
-static struct ftrace_hash *direct_functions = EMPTY_HASH;
+static struct ftrace_hash __rcu *direct_functions = EMPTY_HASH;
 static DEFINE_MUTEX(direct_mutex);
 int ftrace_direct_func_count;
 
@@ -2555,39 +2554,6 @@ unsigned long ftrace_find_rec_direct(unsigned long ip)
 	return entry->direct;
 }
 
-static struct ftrace_func_entry*
-ftrace_add_rec_direct(unsigned long ip, unsigned long addr,
-		      struct ftrace_hash **free_hash)
-{
-	struct ftrace_func_entry *entry;
-
-	if (ftrace_hash_empty(direct_functions) ||
-	    direct_functions->count > 2 * (1 << direct_functions->size_bits)) {
-		struct ftrace_hash *new_hash;
-		int size = ftrace_hash_empty(direct_functions) ? 0 :
-			direct_functions->count + 1;
-
-		if (size < 32)
-			size = 32;
-
-		new_hash = dup_hash(direct_functions, size);
-		if (!new_hash)
-			return NULL;
-
-		*free_hash = direct_functions;
-		direct_functions = new_hash;
-	}
-
-	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
-	if (!entry)
-		return NULL;
-
-	entry->ip = ip;
-	entry->direct = addr;
-	__add_hash_entry(direct_functions, entry);
-	return entry;
-}
-
 static void call_direct_funcs(unsigned long ip, unsigned long pip,
 			      struct ftrace_ops *ops, struct ftrace_regs *fregs)
 {
@@ -4223,8 +4189,8 @@ enter_record(struct ftrace_hash *hash, struct dyn_ftrace *rec, int clear_filter)
 		/* Do nothing if it exists */
 		if (entry)
 			return 0;
-
-		ret = add_hash_entry(hash, rec->ip);
+		if (add_hash_entry(hash, rec->ip) == NULL)
+			ret = -ENOMEM;
 	}
 	return ret;
 }
@@ -5266,7 +5232,8 @@ __ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove)
 		return 0;
 	}
 
-	return add_hash_entry(hash, ip);
+	entry = add_hash_entry(hash, ip);
+	return entry ? 0 :  -ENOMEM;
 }
 
 static int
@@ -5410,7 +5377,7 @@ static void remove_direct_functions_hash(struct ftrace_hash *hash, unsigned long
  */
 int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
 {
-	struct ftrace_hash *hash, *free_hash = NULL;
+	struct ftrace_hash *hash, *new_hash = NULL, *free_hash = NULL;
 	struct ftrace_func_entry *entry, *new;
 	int err = -EBUSY, size, i;
 
@@ -5436,17 +5403,44 @@ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
 		}
 	}
 
-	/* ... and insert them to direct_functions hash. */
 	err = -ENOMEM;
+
+	/* Make a copy hash to place the new and the old entries in */
+	size = hash->count + direct_functions->count;
+	if (size > 32)
+		size = 32;
+	new_hash = alloc_ftrace_hash(fls(size));
+	if (!new_hash)
+		goto out_unlock;
+
+	/* Now copy over the existing direct entries */
+	size = 1 << direct_functions->size_bits;
+	for (i = 0; i < size; i++) {
+		hlist_for_each_entry(entry, &direct_functions->buckets[i], hlist) {
+			new = add_hash_entry(new_hash, entry->ip);
+			if (!new)
+				goto out_unlock;
+			new->direct = entry->direct;
+		}
+	}
+
+	/* ... and add the new entries */
+	size = 1 << hash->size_bits;
 	for (i = 0; i < size; i++) {
 		hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
-			new = ftrace_add_rec_direct(entry->ip, addr, &free_hash);
+			new = add_hash_entry(new_hash, entry->ip);
 			if (!new)
-				goto out_remove;
+				goto out_unlock;
+			/* Update both the copy and the hash entry */
+			new->direct = addr;
 			entry->direct = addr;
 		}
 	}
 
+	free_hash = direct_functions;
+	rcu_assign_pointer(direct_functions, new_hash);
+	new_hash = NULL;
+
 	ops->func = call_direct_funcs;
 	ops->flags = MULTI_FLAGS;
 	ops->trampoline = FTRACE_REGS_ADDR;
@@ -5454,17 +5448,17 @@ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
 
 	err = register_ftrace_function_nolock(ops);
 
- out_remove:
-	if (err)
-		remove_direct_functions_hash(hash, addr);
-
  out_unlock:
 	mutex_unlock(&direct_mutex);
 
-	if (free_hash) {
+	if (free_hash && free_hash != EMPTY_HASH) {
 		synchronize_rcu_tasks();
 		free_ftrace_hash(free_hash);
 	}
+
+	if (new_hash)
+		free_ftrace_hash(new_hash);
+
 	return err;
 }
 EXPORT_SYMBOL_GPL(register_ftrace_direct);
@@ -6309,7 +6303,7 @@ ftrace_graph_set_hash(struct ftrace_hash *hash, char *buffer)
 
 				if (entry)
 					continue;
-				if (add_hash_entry(hash, rec->ip) < 0)
+				if (add_hash_entry(hash, rec->ip) == NULL)
 					goto out;
 			} else {
 				if (entry) {
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 83eab547f1d1..9286f88fcd32 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -881,9 +881,14 @@ static __always_inline bool full_hit(struct trace_buffer *buffer, int cpu, int f
 	if (!nr_pages || !full)
 		return true;
 
-	dirty = ring_buffer_nr_dirty_pages(buffer, cpu);
+	/*
+	 * Add one as dirty will never equal nr_pages, as the sub-buffer
+	 * that the writer is on is not counted as dirty.
+	 * This is needed if "buffer_percent" is set to 100.
+	 */
+	dirty = ring_buffer_nr_dirty_pages(buffer, cpu) + 1;
 
-	return (dirty * 100) > (full * nr_pages);
+	return (dirty * 100) >= (full * nr_pages);
 }
 
 /*
@@ -944,7 +949,8 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu)
 	/* make sure the waiters see the new index */
 	smp_wmb();
 
-	rb_wake_up_waiters(&rbwork->work);
+	/* This can be called in any context */
+	irq_work_queue(&rbwork->work);
 }
 
 /**
diff --git a/kernel/trace/synth_event_gen_test.c b/kernel/trace/synth_event_gen_test.c
index 8dfe85499d4a..354c2117be43 100644
--- a/kernel/trace/synth_event_gen_test.c
+++ b/kernel/trace/synth_event_gen_test.c
@@ -477,6 +477,17 @@ static int __init synth_event_gen_test_init(void)
 
 	ret = test_trace_synth_event();
 	WARN_ON(ret);
+
+	/* Disable when done */
+	trace_array_set_clr_event(gen_synth_test->tr,
+				  "synthetic",
+				  "gen_synth_test", false);
+	trace_array_set_clr_event(empty_synth_test->tr,
+				  "synthetic",
+				  "empty_synth_test", false);
+	trace_array_set_clr_event(create_synth_test->tr,
+				  "synthetic",
+				  "create_synth_test", false);
  out:
 	return ret;
 }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 199df497db07..a0defe156b57 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1894,6 +1894,9 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu,
 	__update_max_tr(tr, tsk, cpu);
 
 	arch_spin_unlock(&tr->max_lock);
+
+	/* Any waiters on the old snapshot buffer need to wake up */
+	ring_buffer_wake_waiters(tr->array_buffer.buffer, RING_BUFFER_ALL_CPUS);
 }
 
 /**
@@ -1945,12 +1948,23 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 
 static int wait_on_pipe(struct trace_iterator *iter, int full)
 {
+	int ret;
+
 	/* Iterators are static, they should be filled or empty */
 	if (trace_buffer_iter(iter, iter->cpu_file))
 		return 0;
 
-	return ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file,
-				full);
+	ret = ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, full);
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+	/*
+	 * Make sure this is still the snapshot buffer, as if a snapshot were
+	 * to happen, this would now be the main buffer.
+	 */
+	if (iter->snapshot)
+		iter->array_buffer = &iter->tr->max_buffer;
+#endif
+	return ret;
 }
 
 #ifdef CONFIG_FTRACE_STARTUP_TEST
@@ -8517,7 +8531,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 
 		wait_index = READ_ONCE(iter->wait_index);
 
-		ret = wait_on_pipe(iter, iter->tr->buffer_percent);
+		ret = wait_on_pipe(iter, iter->snapshot ? 0 : iter->tr->buffer_percent);
 		if (ret)
 			goto out;
 
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 846e02c0fb59..e7af286af4f1 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -1137,7 +1137,7 @@ EXPORT_SYMBOL_GPL(synth_event_add_fields);
  * @cmd: A pointer to the dynevent_cmd struct representing the new event
  * @name: The name of the synthetic event
  * @mod: The module creating the event, NULL if not created from a module
- * @args: Variable number of arg (pairs), one pair for each field
+ * @...: Variable number of arg (pairs), one pair for each field
  *
  * NOTE: Users normally won't want to call this function directly, but
  * rather use the synth_event_gen_cmd_start() wrapper, which
@@ -1695,7 +1695,7 @@ __synth_event_trace_end(struct synth_event_trace_state *trace_state)
  * synth_event_trace - Trace a synthetic event
  * @file: The trace_event_file representing the synthetic event
  * @n_vals: The number of values in vals
- * @args: Variable number of args containing the event values
+ * @...: Variable number of args containing the event values
  *
  * Trace a synthetic event using the values passed in the variable
  * argument list.