Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

3 files changed, 320 insertions, 0 deletions

diff --git a/net/l3mdev/Kconfig b/net/l3mdev/Kconfig
new file mode 100644
index 000000000..2b2861e1f
--- /dev/null
+++ b/net/l3mdev/Kconfig
@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Configuration for L3 master device support
+#
+
+config NET_L3_MASTER_DEV
+	bool "L3 Master device support"
+	depends on INET || IPV6
+	help
+	  This module provides glue between core networking code and device
+	  drivers to support L3 master devices like VRF.
diff --git a/net/l3mdev/Makefile b/net/l3mdev/Makefile
new file mode 100644
index 000000000..9e7da0acc
--- /dev/null
+++ b/net/l3mdev/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Makefile for the L3 device API
+#
+
+obj-y += l3mdev.o
diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c
new file mode 100644
index 000000000..5432a5f2d
--- /dev/null
+++ b/net/l3mdev/l3mdev.c
@@ -0,0 +1,303 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * net/l3mdev/l3mdev.c - L3 master device implementation
+ * Copyright (c) 2015 Cumulus Networks
+ * Copyright (c) 2015 David Ahern <dsa@cumulusnetworks.com>
+ */
+
+#include <linux/netdevice.h>
+#include <net/fib_rules.h>
+#include <net/l3mdev.h>
+
+static DEFINE_SPINLOCK(l3mdev_lock);
+
+struct l3mdev_handler {
+	lookup_by_table_id_t dev_lookup;
+};
+
+static struct l3mdev_handler l3mdev_handlers[L3MDEV_TYPE_MAX + 1];
+
+static int l3mdev_check_type(enum l3mdev_type l3type)
+{
+	if (l3type <= L3MDEV_TYPE_UNSPEC || l3type > L3MDEV_TYPE_MAX)
+		return -EINVAL;
+
+	return 0;
+}
+
+int l3mdev_table_lookup_register(enum l3mdev_type l3type,
+				 lookup_by_table_id_t fn)
+{
+	struct l3mdev_handler *hdlr;
+	int res;
+
+	res = l3mdev_check_type(l3type);
+	if (res)
+		return res;
+
+	hdlr = &l3mdev_handlers[l3type];
+
+	spin_lock(&l3mdev_lock);
+
+	if (hdlr->dev_lookup) {
+		res = -EBUSY;
+		goto unlock;
+	}
+
+	hdlr->dev_lookup = fn;
+	res = 0;
+
+unlock:
+	spin_unlock(&l3mdev_lock);
+
+	return res;
+}
+EXPORT_SYMBOL_GPL(l3mdev_table_lookup_register);
+
+void l3mdev_table_lookup_unregister(enum l3mdev_type l3type,
+				    lookup_by_table_id_t fn)
+{
+	struct l3mdev_handler *hdlr;
+
+	if (l3mdev_check_type(l3type))
+		return;
+
+	hdlr = &l3mdev_handlers[l3type];
+
+	spin_lock(&l3mdev_lock);
+
+	if (hdlr->dev_lookup == fn)
+		hdlr->dev_lookup = NULL;
+
+	spin_unlock(&l3mdev_lock);
+}
+EXPORT_SYMBOL_GPL(l3mdev_table_lookup_unregister);
+
+int l3mdev_ifindex_lookup_by_table_id(enum l3mdev_type l3type,
+				      struct net *net, u32 table_id)
+{
+	lookup_by_table_id_t lookup;
+	struct l3mdev_handler *hdlr;
+	int ifindex = -EINVAL;
+	int res;
+
+	res = l3mdev_check_type(l3type);
+	if (res)
+		return res;
+
+	hdlr = &l3mdev_handlers[l3type];
+
+	spin_lock(&l3mdev_lock);
+
+	lookup = hdlr->dev_lookup;
+	if (!lookup)
+		goto unlock;
+
+	ifindex = lookup(net, table_id);
+
+unlock:
+	spin_unlock(&l3mdev_lock);
+
+	return ifindex;
+}
+EXPORT_SYMBOL_GPL(l3mdev_ifindex_lookup_by_table_id);
+
+/**
+ *	l3mdev_master_ifindex_rcu - get index of L3 master device
+ *	@dev: targeted interface
+ */
+
+int l3mdev_master_ifindex_rcu(const struct net_device *dev)
+{
+	int ifindex = 0;
+
+	if (!dev)
+		return 0;
+
+	if (netif_is_l3_master(dev)) {
+		ifindex = dev->ifindex;
+	} else if (netif_is_l3_slave(dev)) {
+		struct net_device *master;
+		struct net_device *_dev = (struct net_device *)dev;
+
+		/* netdev_master_upper_dev_get_rcu calls
+		 * list_first_or_null_rcu to walk the upper dev list.
+		 * list_first_or_null_rcu does not handle a const arg. We aren't
+		 * making changes, just want the master device from that list so
+		 * typecast to remove the const
+		 */
+		master = netdev_master_upper_dev_get_rcu(_dev);
+		if (master)
+			ifindex = master->ifindex;
+	}
+
+	return ifindex;
+}
+EXPORT_SYMBOL_GPL(l3mdev_master_ifindex_rcu);
+
+/**
+ *	l3mdev_master_upper_ifindex_by_index_rcu - get index of upper l3 master
+ *					       device
+ *	@net: network namespace for device index lookup
+ *	@ifindex: targeted interface
+ */
+int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex)
+{
+	struct net_device *dev;
+
+	dev = dev_get_by_index_rcu(net, ifindex);
+	while (dev && !netif_is_l3_master(dev))
+		dev = netdev_master_upper_dev_get_rcu(dev);
+
+	return dev ? dev->ifindex : 0;
+}
+EXPORT_SYMBOL_GPL(l3mdev_master_upper_ifindex_by_index_rcu);
+
+/**
+ *	l3mdev_fib_table_rcu - get FIB table id associated with an L3
+ *                             master interface
+ *	@dev: targeted interface
+ */
+
+u32 l3mdev_fib_table_rcu(const struct net_device *dev)
+{
+	u32 tb_id = 0;
+
+	if (!dev)
+		return 0;
+
+	if (netif_is_l3_master(dev)) {
+		if (dev->l3mdev_ops->l3mdev_fib_table)
+			tb_id = dev->l3mdev_ops->l3mdev_fib_table(dev);
+	} else if (netif_is_l3_slave(dev)) {
+		/* Users of netdev_master_upper_dev_get_rcu need non-const,
+		 * but current inet_*type functions take a const
+		 */
+		struct net_device *_dev = (struct net_device *) dev;
+		const struct net_device *master;
+
+		master = netdev_master_upper_dev_get_rcu(_dev);
+		if (master &&
+		    master->l3mdev_ops->l3mdev_fib_table)
+			tb_id = master->l3mdev_ops->l3mdev_fib_table(master);
+	}
+
+	return tb_id;
+}
+EXPORT_SYMBOL_GPL(l3mdev_fib_table_rcu);
+
+u32 l3mdev_fib_table_by_index(struct net *net, int ifindex)
+{
+	struct net_device *dev;
+	u32 tb_id = 0;
+
+	if (!ifindex)
+		return 0;
+
+	rcu_read_lock();
+
+	dev = dev_get_by_index_rcu(net, ifindex);
+	if (dev)
+		tb_id = l3mdev_fib_table_rcu(dev);
+
+	rcu_read_unlock();
+
+	return tb_id;
+}
+EXPORT_SYMBOL_GPL(l3mdev_fib_table_by_index);
+
+/**
+ *	l3mdev_link_scope_lookup - IPv6 route lookup based on flow for link
+ *			     local and multicast addresses
+ *	@net: network namespace for device index lookup
+ *	@fl6: IPv6 flow struct for lookup
+ *	This function does not hold refcnt on the returned dst.
+ *	Caller must hold rcu_read_lock().
+ */
+
+struct dst_entry *l3mdev_link_scope_lookup(struct net *net,
+					   struct flowi6 *fl6)
+{
+	struct dst_entry *dst = NULL;
+	struct net_device *dev;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	if (fl6->flowi6_oif) {
+		dev = dev_get_by_index_rcu(net, fl6->flowi6_oif);
+		if (dev && netif_is_l3_slave(dev))
+			dev = netdev_master_upper_dev_get_rcu(dev);
+
+		if (dev && netif_is_l3_master(dev) &&
+		    dev->l3mdev_ops->l3mdev_link_scope_lookup)
+			dst = dev->l3mdev_ops->l3mdev_link_scope_lookup(dev, fl6);
+	}
+
+	return dst;
+}
+EXPORT_SYMBOL_GPL(l3mdev_link_scope_lookup);
+
+/**
+ *	l3mdev_fib_rule_match - Determine if flowi references an
+ *				L3 master device
+ *	@net: network namespace for device index lookup
+ *	@fl:  flow struct
+ *	@arg: store the table the rule matched with here
+ */
+
+int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
+			  struct fib_lookup_arg *arg)
+{
+	struct net_device *dev;
+	int rc = 0;
+
+	/* update flow ensures flowi_l3mdev is set when relevant */
+	if (!fl->flowi_l3mdev)
+		return 0;
+
+	rcu_read_lock();
+
+	dev = dev_get_by_index_rcu(net, fl->flowi_l3mdev);
+	if (dev && netif_is_l3_master(dev) &&
+	    dev->l3mdev_ops->l3mdev_fib_table) {
+		arg->table = dev->l3mdev_ops->l3mdev_fib_table(dev);
+		rc = 1;
+	}
+
+	rcu_read_unlock();
+
+	return rc;
+}
+
+void l3mdev_update_flow(struct net *net, struct flowi *fl)
+{
+	struct net_device *dev;
+
+	rcu_read_lock();
+
+	if (fl->flowi_oif) {
+		dev = dev_get_by_index_rcu(net, fl->flowi_oif);
+		if (dev) {
+			if (!fl->flowi_l3mdev) {
+				fl->flowi_l3mdev = l3mdev_master_ifindex_rcu(dev);
+				fl->flowi_flags |= FLOWI_FLAG_L3MDEV_OIF;
+			}
+
+			/* oif set to L3mdev directs lookup to its table;
+			 * reset to avoid oif match in fib_lookup
+			 */
+			if (netif_is_l3_master(dev))
+				fl->flowi_oif = 0;
+			goto out;
+		}
+	}
+
+	if (fl->flowi_iif > LOOPBACK_IFINDEX && !fl->flowi_l3mdev) {
+		dev = dev_get_by_index_rcu(net, fl->flowi_iif);
+		if (dev)
+			fl->flowi_l3mdev = l3mdev_master_ifindex_rcu(dev);
+	}
+
+out:
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(l3mdev_update_flow);