1 files changed, 158 insertions, 43 deletions

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index a09d507c5b03..07cb99b114bd 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -24,6 +24,7 @@
 #include <linux/of_net.h>
 #include <linux/cpu.h>
 #include <net/netdev_rx_queue.h>
+#include <net/rps.h>
 
 #include "dev.h"
 #include "net-sysfs.h"
@@ -31,13 +32,14 @@
 #ifdef CONFIG_SYSFS
 static const char fmt_hex[] = "%#x\n";
 static const char fmt_dec[] = "%d\n";
+static const char fmt_uint[] = "%u\n";
 static const char fmt_ulong[] = "%lu\n";
 static const char fmt_u64[] = "%llu\n";
 
-/* Caller holds RTNL or dev_base_lock */
+/* Caller holds RTNL, netdev->lock or RCU */
 static inline int dev_isalive(const struct net_device *dev)
 {
-	return dev->reg_state <= NETREG_REGISTERED;
+	return READ_ONCE(dev->reg_state) <= NETREG_REGISTERED;
 }
 
 /* use same locking rules as GIF* ioctl's */
@@ -48,10 +50,10 @@ static ssize_t netdev_show(const struct device *dev,
 	struct net_device *ndev = to_net_dev(dev);
 	ssize_t ret = -EINVAL;
 
-	read_lock(&dev_base_lock);
+	rcu_read_lock();
 	if (dev_isalive(ndev))
 		ret = (*format)(ndev, buf);
-	read_unlock(&dev_base_lock);
+	rcu_read_unlock();
 
 	return ret;
 }
@@ -60,7 +62,7 @@ static ssize_t netdev_show(const struct device *dev,
 #define NETDEVICE_SHOW(field, format_string)				\
 static ssize_t format_##field(const struct net_device *dev, char *buf)	\
 {									\
-	return sysfs_emit(buf, format_string, dev->field);		\
+	return sysfs_emit(buf, format_string, READ_ONCE(dev->field));		\
 }									\
 static ssize_t field##_show(struct device *dev,				\
 			    struct device_attribute *attr, char *buf)	\
@@ -106,6 +108,36 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr,
 	return ret;
 }
 
+/* Same as netdev_store() but takes netdev_lock() instead of rtnl_lock() */
+static ssize_t
+netdev_lock_store(struct device *dev, struct device_attribute *attr,
+		  const char *buf, size_t len,
+		  int (*set)(struct net_device *, unsigned long))
+{
+	struct net_device *netdev = to_net_dev(dev);
+	struct net *net = dev_net(netdev);
+	unsigned long new;
+	int ret;
+
+	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+		return -EPERM;
+
+	ret = kstrtoul(buf, 0, &new);
+	if (ret)
+		return ret;
+
+	netdev_lock(netdev);
+
+	if (dev_isalive(netdev)) {
+		ret = (*set)(netdev, new);
+		if (ret == 0)
+			ret = len;
+	}
+	netdev_unlock(netdev);
+
+	return ret;
+}
+
 NETDEVICE_SHOW_RO(dev_id, fmt_hex);
 NETDEVICE_SHOW_RO(dev_port, fmt_dec);
 NETDEVICE_SHOW_RO(addr_assign_type, fmt_dec);
@@ -125,7 +157,7 @@ static DEVICE_ATTR_RO(iflink);
 
 static ssize_t format_name_assign_type(const struct net_device *dev, char *buf)
 {
-	return sysfs_emit(buf, fmt_dec, dev->name_assign_type);
+	return sysfs_emit(buf, fmt_dec, READ_ONCE(dev->name_assign_type));
 }
 
 static ssize_t name_assign_type_show(struct device *dev,
@@ -135,24 +167,28 @@ static ssize_t name_assign_type_show(struct device *dev,
 	struct net_device *ndev = to_net_dev(dev);
 	ssize_t ret = -EINVAL;
 
-	if (ndev->name_assign_type != NET_NAME_UNKNOWN)
+	if (READ_ONCE(ndev->name_assign_type) != NET_NAME_UNKNOWN)
 		ret = netdev_show(dev, attr, buf, format_name_assign_type);
 
 	return ret;
 }
 static DEVICE_ATTR_RO(name_assign_type);
 
-/* use same locking rules as GIFHWADDR ioctl's */
+/* use same locking rules as GIFHWADDR ioctl's (dev_get_mac_address()) */
 static ssize_t address_show(struct device *dev, struct device_attribute *attr,
 			    char *buf)
 {
 	struct net_device *ndev = to_net_dev(dev);
 	ssize_t ret = -EINVAL;
 
-	read_lock(&dev_base_lock);
+	down_read(&dev_addr_sem);
+
+	rcu_read_lock();
 	if (dev_isalive(ndev))
 		ret = sysfs_format_mac(buf, ndev->dev_addr, ndev->addr_len);
-	read_unlock(&dev_base_lock);
+	rcu_read_unlock();
+
+	up_read(&dev_addr_sem);
 	return ret;
 }
 static DEVICE_ATTR_RO(address);
@@ -161,10 +197,13 @@ static ssize_t broadcast_show(struct device *dev,
 			      struct device_attribute *attr, char *buf)
 {
 	struct net_device *ndev = to_net_dev(dev);
+	int ret = -EINVAL;
 
+	rcu_read_lock();
 	if (dev_isalive(ndev))
-		return sysfs_format_mac(buf, ndev->broadcast, ndev->addr_len);
-	return -EINVAL;
+		ret = sysfs_format_mac(buf, ndev->broadcast, ndev->addr_len);
+	rcu_read_unlock();
+	return ret;
 }
 static DEVICE_ATTR_RO(broadcast);
 
@@ -227,7 +266,7 @@ static ssize_t speed_show(struct device *dev,
 	if (!rtnl_trylock())
 		return restart_syscall();
 
-	if (netif_running(netdev) && netif_device_present(netdev)) {
+	if (netif_running(netdev)) {
 		struct ethtool_link_ksettings cmd;
 
 		if (!__ethtool_get_link_ksettings(netdev, &cmd))
@@ -318,11 +357,9 @@ static ssize_t operstate_show(struct device *dev,
 	const struct net_device *netdev = to_net_dev(dev);
 	unsigned char operstate;
 
-	read_lock(&dev_base_lock);
-	operstate = netdev->operstate;
+	operstate = READ_ONCE(netdev->operstate);
 	if (!netif_running(netdev))
 		operstate = IF_OPER_DOWN;
-	read_unlock(&dev_base_lock);
 
 	if (operstate >= ARRAY_SIZE(operstates))
 		return -EINVAL; /* should not happen */
@@ -402,7 +439,7 @@ NETDEVICE_SHOW_RW(tx_queue_len, fmt_dec);
 
 static int change_gro_flush_timeout(struct net_device *dev, unsigned long val)
 {
-	WRITE_ONCE(dev->gro_flush_timeout, val);
+	netdev_set_gro_flush_timeout(dev, val);
 	return 0;
 }
 
@@ -413,13 +450,16 @@ static ssize_t gro_flush_timeout_store(struct device *dev,
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
 
-	return netdev_store(dev, attr, buf, len, change_gro_flush_timeout);
+	return netdev_lock_store(dev, attr, buf, len, change_gro_flush_timeout);
 }
 NETDEVICE_SHOW_RW(gro_flush_timeout, fmt_ulong);
 
 static int change_napi_defer_hard_irqs(struct net_device *dev, unsigned long val)
 {
-	WRITE_ONCE(dev->napi_defer_hard_irqs, val);
+	if (val > S32_MAX)
+		return -ERANGE;
+
+	netdev_set_defer_hard_irqs(dev, (u32)val);
 	return 0;
 }
 
@@ -430,9 +470,10 @@ static ssize_t napi_defer_hard_irqs_store(struct device *dev,
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
 
-	return netdev_store(dev, attr, buf, len, change_napi_defer_hard_irqs);
+	return netdev_lock_store(dev, attr, buf, len,
+				 change_napi_defer_hard_irqs);
 }
-NETDEVICE_SHOW_RW(napi_defer_hard_irqs, fmt_dec);
+NETDEVICE_SHOW_RW(napi_defer_hard_irqs, fmt_uint);
 
 static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr,
 			     const char *buf, size_t len)
@@ -599,13 +640,13 @@ static ssize_t threaded_show(struct device *dev,
 	struct net_device *netdev = to_net_dev(dev);
 	ssize_t ret = -EINVAL;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
+	rcu_read_lock();
 
 	if (dev_isalive(netdev))
-		ret = sysfs_emit(buf, fmt_dec, netdev->threaded);
+		ret = sysfs_emit(buf, fmt_dec, READ_ONCE(netdev->threaded));
+
+	rcu_read_unlock();
 
-	rtnl_unlock();
 	return ret;
 }
 
@@ -628,7 +669,7 @@ static ssize_t threaded_store(struct device *dev,
 			      struct device_attribute *attr,
 			      const char *buf, size_t len)
 {
-	return netdev_store(dev, attr, buf, len, modify_napi_threaded);
+	return netdev_lock_store(dev, attr, buf, len, modify_napi_threaded);
 }
 static DEVICE_ATTR_RW(threaded);
 
@@ -680,14 +721,14 @@ static ssize_t netstat_show(const struct device *d,
 	WARN_ON(offset > sizeof(struct rtnl_link_stats64) ||
 		offset % sizeof(u64) != 0);
 
-	read_lock(&dev_base_lock);
+	rcu_read_lock();
 	if (dev_isalive(dev)) {
 		struct rtnl_link_stats64 temp;
 		const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp);
 
 		ret = sysfs_emit(buf, fmt_u64, *(u64 *)(((u8 *)stats) + offset));
 	}
-	read_unlock(&dev_base_lock);
+	rcu_read_unlock();
 	return ret;
 }
 
@@ -1050,7 +1091,7 @@ static const void *rx_queue_namespace(const struct kobject *kobj)
 	struct device *dev = &queue->dev->dev;
 	const void *ns = NULL;
 
-	if (dev->class && dev->class->ns_type)
+	if (dev->class && dev->class->namespace)
 		ns = dev->class->namespace(dev);
 
 	return ns;
@@ -1409,6 +1450,65 @@ static struct netdev_queue_attribute bql_hold_time_attribute __ro_after_init
 	= __ATTR(hold_time, 0644,
 		 bql_show_hold_time, bql_set_hold_time);
 
+static ssize_t bql_show_stall_thrs(struct netdev_queue *queue, char *buf)
+{
+	struct dql *dql = &queue->dql;
+
+	return sysfs_emit(buf, "%u\n", jiffies_to_msecs(dql->stall_thrs));
+}
+
+static ssize_t bql_set_stall_thrs(struct netdev_queue *queue,
+				  const char *buf, size_t len)
+{
+	struct dql *dql = &queue->dql;
+	unsigned int value;
+	int err;
+
+	err = kstrtouint(buf, 10, &value);
+	if (err < 0)
+		return err;
+
+	value = msecs_to_jiffies(value);
+	if (value && (value < 4 || value > 4 / 2 * BITS_PER_LONG))
+		return -ERANGE;
+
+	if (!dql->stall_thrs && value)
+		dql->last_reap = jiffies;
+	/* Force last_reap to be live */
+	smp_wmb();
+	dql->stall_thrs = value;
+
+	return len;
+}
+
+static struct netdev_queue_attribute bql_stall_thrs_attribute __ro_after_init =
+	__ATTR(stall_thrs, 0644, bql_show_stall_thrs, bql_set_stall_thrs);
+
+static ssize_t bql_show_stall_max(struct netdev_queue *queue, char *buf)
+{
+	return sysfs_emit(buf, "%u\n", READ_ONCE(queue->dql.stall_max));
+}
+
+static ssize_t bql_set_stall_max(struct netdev_queue *queue,
+				 const char *buf, size_t len)
+{
+	WRITE_ONCE(queue->dql.stall_max, 0);
+	return len;
+}
+
+static struct netdev_queue_attribute bql_stall_max_attribute __ro_after_init =
+	__ATTR(stall_max, 0644, bql_show_stall_max, bql_set_stall_max);
+
+static ssize_t bql_show_stall_cnt(struct netdev_queue *queue, char *buf)
+{
+	struct dql *dql = &queue->dql;
+
+	return sysfs_emit(buf, "%lu\n", dql->stall_cnt);
+}
+
+static struct netdev_queue_attribute bql_stall_cnt_attribute __ro_after_init =
+	__ATTR(stall_cnt, 0444, bql_show_stall_cnt, NULL);
+
 static ssize_t bql_show_inflight(struct netdev_queue *queue,
 				 char *buf)
 {
@@ -1447,6 +1547,9 @@ static struct attribute *dql_attrs[] __ro_after_init = {
 	&bql_limit_min_attribute.attr,
 	&bql_hold_time_attribute.attr,
 	&bql_inflight_attribute.attr,
+	&bql_stall_thrs_attribute.attr,
+	&bql_stall_cnt_attribute.attr,
+	&bql_stall_max_attribute.attr,
 	NULL
 };
 
@@ -1454,6 +1557,9 @@ static const struct attribute_group dql_group = {
 	.name  = "byte_queue_limits",
 	.attrs  = dql_attrs,
 };
+#else
+/* Fake declaration, all the code using it should be dead */
+static const struct attribute_group dql_group = {};
 #endif /* CONFIG_BQL */
 
 #ifdef CONFIG_XPS
@@ -1669,7 +1775,7 @@ static const void *netdev_queue_namespace(const struct kobject *kobj)
 	struct device *dev = &queue->dev->dev;
 	const void *ns = NULL;
 
-	if (dev->class && dev->class->ns_type)
+	if (dev->class && dev->class->namespace)
 		ns = dev->class->namespace(dev);
 
 	return ns;
@@ -1691,6 +1797,14 @@ static const struct kobj_type netdev_queue_ktype = {
 	.get_ownership = netdev_queue_get_ownership,
 };
 
+static bool netdev_uses_bql(const struct net_device *dev)
+{
+	if (dev->lltx || (dev->priv_flags & IFF_NO_QUEUE))
+		return false;
+
+	return IS_ENABLED(CONFIG_BQL);
+}
+
 static int netdev_queue_add_kobject(struct net_device *dev, int index)
 {
 	struct netdev_queue *queue = dev->_tx + index;
@@ -1708,11 +1822,11 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index)
 	if (error)
 		goto err;
 
-#ifdef CONFIG_BQL
-	error = sysfs_create_group(kobj, &dql_group);
-	if (error)
-		goto err;
-#endif
+	if (netdev_uses_bql(dev)) {
+		error = sysfs_create_group(kobj, &dql_group);
+		if (error)
+			goto err;
+	}
 
 	kobject_uevent(kobj, KOBJ_ADD);
 	return 0;
@@ -1733,9 +1847,9 @@ static int tx_queue_change_owner(struct net_device *ndev, int index,
 	if (error)
 		return error;
 
-#ifdef CONFIG_BQL
-	error = sysfs_group_change_owner(kobj, &dql_group, kuid, kgid);
-#endif
+	if (netdev_uses_bql(ndev))
+		error = sysfs_group_change_owner(kobj, &dql_group, kuid, kgid);
+
 	return error;
 }
 #endif /* CONFIG_SYSFS */
@@ -1767,9 +1881,10 @@ netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num)
 
 		if (!refcount_read(&dev_net(dev)->ns.count))
 			queue->kobj.uevent_suppress = 1;
-#ifdef CONFIG_BQL
-		sysfs_remove_group(&queue->kobj, &dql_group);
-#endif
+
+		if (netdev_uses_bql(dev))
+			sysfs_remove_group(&queue->kobj, &dql_group);
+
 		kobject_put(&queue->kobj);
 	}
 
@@ -1947,7 +2062,7 @@ static void netdev_release(struct device *d)
 	 * device is dead and about to be freed.
 	 */
 	kfree(rcu_access_pointer(dev->ifalias));
-	netdev_freemem(dev);
+	kvfree(dev);
 }
 
 static const void *net_namespace(const struct device *d)
@@ -1965,7 +2080,7 @@ static void net_get_ownership(const struct device *d, kuid_t *uid, kgid_t *gid)
 	net_ns_get_ownership(net, uid, gid);
 }
 
-static struct class net_class __ro_after_init = {
+static const struct class net_class = {
 	.name = "net",
 	.dev_release = netdev_release,
 	.dev_groups = net_class_groups,