From 30bfce109420912f201d4f295f9130ff44f04b41 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 6 Jan 2021 13:06:36 -0800 Subject: net: remove ndo_udp_tunnel_* callbacks All UDP tunnel port management is now routed via udp_tunnel_nic infra directly. Remove the old callbacks. Reviewed-by: Alexander Duyck Reviewed-by: Jacob Keller Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 259be67644e3..1ec3ac5d5bbf 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1213,19 +1213,6 @@ struct netdev_net_notifier { * struct netdev_phys_item_id *ppid) * Called to get the parent ID of the physical port of this device. * - * void (*ndo_udp_tunnel_add)(struct net_device *dev, - * struct udp_tunnel_info *ti); - * Called by UDP tunnel to notify a driver about the UDP port and socket - * address family that a UDP tunnel is listnening to. It is called only - * when a new port starts listening. The operation is protected by the - * RTNL. - * - * void (*ndo_udp_tunnel_del)(struct net_device *dev, - * struct udp_tunnel_info *ti); - * Called by UDP tunnel to notify the driver about a UDP port and socket - * address family that the UDP tunnel is not listening to anymore. The - * operation is protected by the RTNL. - * * void* (*ndo_dfwd_add_station)(struct net_device *pdev, * struct net_device *dev) * Called by upper layer devices to accelerate switching or other @@ -1464,10 +1451,6 @@ struct net_device_ops { struct netdev_phys_item_id *ppid); int (*ndo_get_phys_port_name)(struct net_device *dev, char *name, size_t len); - void (*ndo_udp_tunnel_add)(struct net_device *dev, - struct udp_tunnel_info *ti); - void (*ndo_udp_tunnel_del)(struct net_device *dev, - struct udp_tunnel_info *ti); void* (*ndo_dfwd_add_station)(struct net_device *pdev, struct net_device *dev); void (*ndo_dfwd_del_station)(struct net_device *pdev, -- cgit v1.2.3 From b9ef3fecd1403fc1c2dd146e67b366691394b80f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 6 Jan 2021 13:06:37 -0800 Subject: udp_tunnel: reshuffle NETIF_F_RX_UDP_TUNNEL_PORT checks Move the NETIF_F_RX_UDP_TUNNEL_PORT feature check into udp_tunnel_nic_*_port() helpers, since they're always done right before the call. Add similar checks before calling the notifier. udp_tunnel_nic invokes the notifier without checking features which could result in some wasted cycles. Reviewed-by: Alexander Duyck Reviewed-by: Jacob Keller Signed-off-by: Jakub Kicinski --- include/net/udp_tunnel.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index 2ea453dac876..282d10ee60e1 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -129,12 +129,16 @@ void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type); static inline void udp_tunnel_get_rx_info(struct net_device *dev) { ASSERT_RTNL(); + if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) + return; call_netdevice_notifiers(NETDEV_UDP_TUNNEL_PUSH_INFO, dev); } static inline void udp_tunnel_drop_rx_info(struct net_device *dev) { ASSERT_RTNL(); + if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) + return; call_netdevice_notifiers(NETDEV_UDP_TUNNEL_DROP_INFO, dev); } @@ -323,6 +327,8 @@ udp_tunnel_nic_set_port_priv(struct net_device *dev, unsigned int table, static inline void udp_tunnel_nic_add_port(struct net_device *dev, struct udp_tunnel_info *ti) { + if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) + return; if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->add_port(dev, ti); } @@ -330,6 +336,8 @@ udp_tunnel_nic_add_port(struct net_device *dev, struct udp_tunnel_info *ti) static inline void udp_tunnel_nic_del_port(struct net_device *dev, struct udp_tunnel_info *ti) { + if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) + return; if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->del_port(dev, ti); } -- cgit v1.2.3 From 8b86850bf9ef259e194ce49c776aded3b8c281fb Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 6 Jan 2021 09:09:44 -0800 Subject: net: phy: bcm7xxx: Add an entry for BCM72116 BCM72116 features a 28nm integrated EPHY, add an entry to match this PHY OUI. Signed-off-by: Florian Fainelli Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20210106170944.1253046-1-f.fainelli@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/brcmphy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index d0bd226d6bd9..de9430d55c90 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -31,6 +31,7 @@ #define PHY_ID_BCM89610 0x03625cd0 #define PHY_ID_BCM72113 0x35905310 +#define PHY_ID_BCM72116 0x35905350 #define PHY_ID_BCM7250 0xae025280 #define PHY_ID_BCM7255 0xae025120 #define PHY_ID_BCM7260 0xae025190 -- cgit v1.2.3 From d5f19486cee79d04c054427577ac96ed123706db Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 6 Jan 2021 11:51:35 +0200 Subject: net: dsa: listen for SWITCHDEV_{FDB,DEL}_ADD_TO_DEVICE on foreign bridge neighbors Some DSA switches (and not only) cannot learn source MAC addresses from packets injected from the CPU. They only perform hardware address learning from inbound traffic. This can be problematic when we have a bridge spanning some DSA switch ports and some non-DSA ports (which we'll call "foreign interfaces" from DSA's perspective). There are 2 classes of problems created by the lack of learning on CPU-injected traffic: - excessive flooding, due to the fact that DSA treats those addresses as unknown - the risk of stale routes, which can lead to temporary packet loss To illustrate the second class, consider the following situation, which is common in production equipment (wireless access points, where there is a WLAN interface and an Ethernet switch, and these form a single bridging domain). AP 1: +------------------------------------------------------------------------+ | br0 | +------------------------------------------------------------------------+ +------------+ +------------+ +------------+ +------------+ +------------+ | swp0 | | swp1 | | swp2 | | swp3 | | wlan0 | +------------+ +------------+ +------------+ +------------+ +------------+ | ^ ^ | | | | | | | Client A Client B | | | +------------+ +------------+ +------------+ +------------+ +------------+ | swp0 | | swp1 | | swp2 | | swp3 | | wlan0 | +------------+ +------------+ +------------+ +------------+ +------------+ +------------------------------------------------------------------------+ | br0 | +------------------------------------------------------------------------+ AP 2 - br0 of AP 1 will know that Clients A and B are reachable via wlan0 - the hardware fdb of a DSA switch driver today is not kept in sync with the software entries on other bridge ports, so it will not know that clients A and B are reachable via the CPU port UNLESS the hardware switch itself performs SA learning from traffic injected from the CPU. Nonetheless, a substantial number of switches don't. - the hardware fdb of the DSA switch on AP 2 may autonomously learn that Client A and B are reachable through swp0. Therefore, the software br0 of AP 2 also may or may not learn this. In the example we're illustrating, some Ethernet traffic has been going on, and br0 from AP 2 has indeed learnt that it can reach Client B through swp0. One of the wireless clients, say Client B, disconnects from AP 1 and roams to AP 2. The topology now looks like this: AP 1: +------------------------------------------------------------------------+ | br0 | +------------------------------------------------------------------------+ +------------+ +------------+ +------------+ +------------+ +------------+ | swp0 | | swp1 | | swp2 | | swp3 | | wlan0 | +------------+ +------------+ +------------+ +------------+ +------------+ | ^ | | | Client A | | | Client B | | | v +------------+ +------------+ +------------+ +------------+ +------------+ | swp0 | | swp1 | | swp2 | | swp3 | | wlan0 | +------------+ +------------+ +------------+ +------------+ +------------+ +------------------------------------------------------------------------+ | br0 | +------------------------------------------------------------------------+ AP 2 - br0 of AP 1 still knows that Client A is reachable via wlan0 (no change) - br0 of AP 1 will (possibly) know that Client B has left wlan0. There are cases where it might never find out though. Either way, DSA today does not process that notification in any way. - the hardware FDB of the DSA switch on AP 1 may learn autonomously that Client B can be reached via swp0, if it receives any packet with Client 1's source MAC address over Ethernet. - the hardware FDB of the DSA switch on AP 2 still thinks that Client B can be reached via swp0. It does not know that it has roamed to wlan0, because it doesn't perform SA learning from the CPU port. Now Client A contacts Client B. AP 1 routes the packet fine towards swp0 and delivers it on the Ethernet segment. AP 2 sees a frame on swp0 and its fdb says that the destination is swp0. Hairpinning is disabled => drop. This problem comes from the fact that these switches have a 'blind spot' for addresses coming from software bridging. The generic solution is not to assume that hardware learning can be enabled somehow, but to listen to more bridge learning events. It turns out that the bridge driver does learn in software from all inbound frames, in __br_handle_local_finish. A proper SWITCHDEV_FDB_ADD_TO_DEVICE notification is emitted for the addresses serviced by the bridge on 'foreign' interfaces. The software bridge also does the right thing on migration, by notifying that the old entry is deleted, so that does not need to be special-cased in DSA. When it is deleted, we just need to delete our static FDB entry towards the CPU too, and wait. The problem is that DSA currently only cares about SWITCHDEV_FDB_ADD_TO_DEVICE events received on its own interfaces, such as static FDB entries. Luckily we can change that, and DSA can listen to all switchdev FDB add/del events in the system and figure out if those events were emitted by a bridge that spans at least one of DSA's own ports. In case that is true, DSA will also offload that address towards its own CPU port, in the eventuality that there might be bridge clients attached to the DSA switch who want to talk to the station connected to the foreign interface. In terms of implementation, we need to keep the fdb_info->added_by_user check for the case where the switchdev event was targeted directly at a DSA switch port. But we don't need to look at that flag for snooped events. So the check is currently too late, we need to move it earlier. This also simplifies the code a bit, since we avoid uselessly allocating and freeing switchdev_work. We could probably do some improvements in the future. For example, multi-bridge support is rudimentary at the moment. If there are two bridges spanning a DSA switch's ports, and both of them need to service the same MAC address, then what will happen is that the migration of one of those stations will trigger the deletion of the FDB entry from the CPU port while it is still used by other bridge. That could be improved with reference counting but is left for another time. This behavior needs to be enabled at driver level by setting ds->assisted_learning_on_cpu_port = true. This is because we don't want to inflict a potential performance penalty (accesses through MDIO/I2C/SPI are expensive) to hardware that really doesn't need it because address learning on the CPU port works there. Reported-by: DENG Qingfang Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Reviewed-by: Andrew Lunn Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 4e60d2610f20..6b74690bd8d4 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -319,6 +319,11 @@ struct dsa_switch { */ bool untag_bridge_pvid; + /* Let DSA manage the FDB entries towards the CPU, based on the + * software bridge database. + */ + bool assisted_learning_on_cpu_port; + /* In case vlan_filtering_is_global is set, the VLAN awareness state * should be retrieved from here and not from the per-port settings. */ -- cgit v1.2.3 From f46b9b8ee89b52f6ee1f4da49d392e609746ab10 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 7 Jan 2021 03:24:00 +0200 Subject: net: dsa: move the Broadcom tag information in a separate header file It is a bit strange to see something as specific as Broadcom SYSTEMPORT bits in the main DSA include file. Move these away into a separate header, and have the tagger and the SYSTEMPORT driver include them. Signed-off-by: Vladimir Oltean Acked-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/linux/dsa/brcm.h | 16 ++++++++++++++++ include/net/dsa.h | 6 ------ 2 files changed, 16 insertions(+), 6 deletions(-) create mode 100644 include/linux/dsa/brcm.h (limited to 'include') diff --git a/include/linux/dsa/brcm.h b/include/linux/dsa/brcm.h new file mode 100644 index 000000000000..47545a948784 --- /dev/null +++ b/include/linux/dsa/brcm.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * Copyright (C) 2014 Broadcom Corporation + */ + +/* Included by drivers/net/ethernet/broadcom/bcmsysport.c and + * net/dsa/tag_brcm.c + */ +#ifndef _NET_DSA_BRCM_H +#define _NET_DSA_BRCM_H + +/* Broadcom tag specific helpers to insert and extract queue/port number */ +#define BRCM_TAG_SET_PORT_QUEUE(p, q) ((p) << 8 | q) +#define BRCM_TAG_GET_PORT(v) ((v) >> 8) +#define BRCM_TAG_GET_QUEUE(v) ((v) & 0xff) + +#endif diff --git a/include/net/dsa.h b/include/net/dsa.h index 6b74690bd8d4..e92a09c77f96 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -878,12 +878,6 @@ static inline int call_dsa_notifiers(unsigned long val, struct net_device *dev, } #endif -/* Broadcom tag specific helpers to insert and extract queue/port number */ -#define BRCM_TAG_SET_PORT_QUEUE(p, q) ((p) << 8 | q) -#define BRCM_TAG_GET_PORT(v) ((v) >> 8) -#define BRCM_TAG_GET_QUEUE(v) ((v) & 0xff) - - netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev); int dsa_port_get_phy_strings(struct dsa_port *dp, uint8_t *data); int dsa_port_get_ethtool_phy_stats(struct dsa_port *dp, uint64_t *data); -- cgit v1.2.3 From a5e3c9ba9258dbe55cba0cc3804675c9f1eaa169 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 7 Jan 2021 03:24:01 +0200 Subject: net: dsa: export dsa_slave_dev_check Using the NETDEV_CHANGEUPPER notifications, drivers can be aware when they are enslaved to e.g. a bridge by calling netif_is_bridge_master(). Export this helper from DSA to get the equivalent functionality of determining whether the upper interface of a CHANGEUPPER notifier is a DSA switch interface or not. Signed-off-by: Vladimir Oltean Acked-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index e92a09c77f96..e218eca128d1 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -860,6 +860,7 @@ int register_dsa_notifier(struct notifier_block *nb); int unregister_dsa_notifier(struct notifier_block *nb); int call_dsa_notifiers(unsigned long val, struct net_device *dev, struct dsa_notifier_info *info); +bool dsa_slave_dev_check(const struct net_device *dev); #else static inline int register_dsa_notifier(struct notifier_block *nb) { @@ -876,6 +877,11 @@ static inline int call_dsa_notifiers(unsigned long val, struct net_device *dev, { return NOTIFY_DONE; } + +static inline bool dsa_slave_dev_check(const struct net_device *dev) +{ + return false; +} #endif netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev); -- cgit v1.2.3 From 1dbb130281c447fdd061475931e1eb7baf475f53 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 7 Jan 2021 03:24:03 +0200 Subject: net: dsa: remove the DSA specific notifiers This effectively reverts commit 60724d4bae14 ("net: dsa: Add support for DSA specific notifiers"). The reason is that since commit 2f1e8ea726e9 ("net: dsa: link interfaces with the DSA master to get rid of lockdep warnings"), it appears that there is a generic way to achieve the same purpose. The only user thus far, the Broadcom SYSTEMPORT driver, was converted to use the generic notifiers. Signed-off-by: Vladimir Oltean Acked-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 42 ------------------------------------------ 1 file changed, 42 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index e218eca128d1..9a0cab5fb7c4 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -833,51 +833,9 @@ static inline int dsa_switch_resume(struct dsa_switch *ds) } #endif /* CONFIG_PM_SLEEP */ -enum dsa_notifier_type { - DSA_PORT_REGISTER, - DSA_PORT_UNREGISTER, -}; - -struct dsa_notifier_info { - struct net_device *dev; -}; - -struct dsa_notifier_register_info { - struct dsa_notifier_info info; /* must be first */ - struct net_device *master; - unsigned int port_number; - unsigned int switch_number; -}; - -static inline struct net_device * -dsa_notifier_info_to_dev(const struct dsa_notifier_info *info) -{ - return info->dev; -} - #if IS_ENABLED(CONFIG_NET_DSA) -int register_dsa_notifier(struct notifier_block *nb); -int unregister_dsa_notifier(struct notifier_block *nb); -int call_dsa_notifiers(unsigned long val, struct net_device *dev, - struct dsa_notifier_info *info); bool dsa_slave_dev_check(const struct net_device *dev); #else -static inline int register_dsa_notifier(struct notifier_block *nb) -{ - return 0; -} - -static inline int unregister_dsa_notifier(struct notifier_block *nb) -{ - return 0; -} - -static inline int call_dsa_notifiers(unsigned long val, struct net_device *dev, - struct dsa_notifier_info *info) -{ - return NOTIFY_DONE; -} - static inline bool dsa_slave_dev_check(const struct net_device *dev) { return false; -- cgit v1.2.3 From 424f481f06dc7f1528447cc3224f5fd3c5e11f65 Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Wed, 6 Jan 2021 14:18:29 -0800 Subject: skbuff: remove unused skb_zcopy_abort function skb_zcopy_abort() has no in-tree consumers, remove it. Signed-off-by: Jonathan Lemon Acked-by: Willem de Bruijn Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 333bcdc39635..3ca8d7c7b30c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1490,17 +1490,6 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy) } } -/* Abort a zerocopy operation and revert zckey on error in send syscall */ -static inline void skb_zcopy_abort(struct sk_buff *skb) -{ - struct ubuf_info *uarg = skb_zcopy(skb); - - if (uarg) { - sock_zerocopy_put_abort(uarg, false); - skb_shinfo(skb)->tx_flags &= ~SKBTX_ZEROCOPY_FRAG; - } -} - static inline void skb_mark_not_on_list(struct sk_buff *skb) { skb->next = NULL; -- cgit v1.2.3 From 75518851a2a0c047def521aaf87db401de098352 Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Wed, 6 Jan 2021 14:18:31 -0800 Subject: skbuff: Push status and refcounts into sock_zerocopy_callback Before this change, the caller of sock_zerocopy_callback would need to save the zerocopy status, decrement and check the refcount, and then call the callback function - the callback was only invoked when the refcount reached zero. Now, the caller just passes the status into the callback function, which saves the status and handles its own refcounts. This makes the behavior of the sock_zerocopy_callback identical to the tpacket and vhost callbacks. Signed-off-by: Jonathan Lemon Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3ca8d7c7b30c..52e96c35f5af 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1479,9 +1479,6 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy) if (uarg) { if (skb_zcopy_is_nouarg(skb)) { /* no notification callback */ - } else if (uarg->callback == sock_zerocopy_callback) { - uarg->zerocopy = uarg->zerocopy && zerocopy; - sock_zerocopy_put(uarg); } else { uarg->callback(uarg, zerocopy); } -- cgit v1.2.3 From 59776362b14b81dc45c6bbd4e7cb3871f390fc1b Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Wed, 6 Jan 2021 14:18:32 -0800 Subject: skbuff: replace sock_zerocopy_put() with skb_zcopy_put() Replace sock_zerocopy_put with the generic skb_zcopy_put() function. Pass 'true' as the success argument, as this is identical to no change. Signed-off-by: Jonathan Lemon Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 52e96c35f5af..a6c86839035b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -496,7 +496,6 @@ static inline void sock_zerocopy_get(struct ubuf_info *uarg) refcount_inc(&uarg->refcnt); } -void sock_zerocopy_put(struct ubuf_info *uarg); void sock_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); void sock_zerocopy_callback(struct ubuf_info *uarg, bool success); @@ -1471,6 +1470,12 @@ static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb) return (void *)((uintptr_t) skb_shinfo(skb)->destructor_arg & ~0x1UL); } +static inline void skb_zcopy_put(struct ubuf_info *uarg) +{ + if (uarg) + uarg->callback(uarg, true); +} + /* Release a reference on a zerocopy structure */ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy) { -- cgit v1.2.3 From e76d46cfff8d2335f363f58bd7387de4059d871d Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Wed, 6 Jan 2021 14:18:33 -0800 Subject: skbuff: replace sock_zerocopy_get with skb_zcopy_get Rename the get routines for consistency. Signed-off-by: Jonathan Lemon Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a6c86839035b..5b8a53ab51fd 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -491,11 +491,6 @@ struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size); struct ubuf_info *sock_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg); -static inline void sock_zerocopy_get(struct ubuf_info *uarg) -{ - refcount_inc(&uarg->refcnt); -} - void sock_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); void sock_zerocopy_callback(struct ubuf_info *uarg, bool success); @@ -1441,6 +1436,11 @@ static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) return is_zcopy ? skb_uarg(skb) : NULL; } +static inline void skb_zcopy_get(struct ubuf_info *uarg) +{ + refcount_inc(&uarg->refcnt); +} + static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg, bool *have_ref) { @@ -1448,7 +1448,7 @@ static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg, if (unlikely(have_ref && *have_ref)) *have_ref = false; else - sock_zerocopy_get(uarg); + skb_zcopy_get(uarg); skb_shinfo(skb)->destructor_arg = uarg; skb_shinfo(skb)->tx_flags |= SKBTX_ZEROCOPY_FRAG; } -- cgit v1.2.3 From 36177832f42d9c7b222ab039678398a9d4070fff Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Wed, 6 Jan 2021 14:18:34 -0800 Subject: skbuff: Add skb parameter to the ubuf zerocopy callback Add an optional skb parameter to the zerocopy callback parameter, which is passed down from skb_zcopy_clear(). This gives access to the original skb, which is needed for upcoming RX zero-copy error handling. Signed-off-by: Jonathan Lemon Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5b8a53ab51fd..b23c3b4b3209 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -461,7 +461,8 @@ enum { * The desc field is used to track userspace buffer index. */ struct ubuf_info { - void (*callback)(struct ubuf_info *, bool zerocopy_success); + void (*callback)(struct sk_buff *, struct ubuf_info *, + bool zerocopy_success); union { struct { unsigned long desc; @@ -493,7 +494,8 @@ struct ubuf_info *sock_zerocopy_realloc(struct sock *sk, size_t size, void sock_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); -void sock_zerocopy_callback(struct ubuf_info *uarg, bool success); +void sock_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, + bool success); int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len); int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, @@ -1473,20 +1475,17 @@ static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb) static inline void skb_zcopy_put(struct ubuf_info *uarg) { if (uarg) - uarg->callback(uarg, true); + uarg->callback(NULL, uarg, true); } /* Release a reference on a zerocopy structure */ -static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy) +static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) { struct ubuf_info *uarg = skb_zcopy(skb); if (uarg) { - if (skb_zcopy_is_nouarg(skb)) { - /* no notification callback */ - } else { - uarg->callback(uarg, zerocopy); - } + if (!skb_zcopy_is_nouarg(skb)) + uarg->callback(skb, uarg, zerocopy_success); skb_shinfo(skb)->tx_flags &= ~SKBTX_ZEROCOPY_FRAG; } -- cgit v1.2.3 From 236a6b1cd585a408139550201343f3f16f9324b9 Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Wed, 6 Jan 2021 14:18:35 -0800 Subject: skbuff: Call sock_zerocopy_put_abort from skb_zcopy_put_abort The sock_zerocopy_put_abort function contains logic which is specific to the current zerocopy implementation. Add a wrapper which checks the callback and dispatches apppropriately. Signed-off-by: Jonathan Lemon Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b23c3b4b3209..9f7393167f0a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1478,6 +1478,16 @@ static inline void skb_zcopy_put(struct ubuf_info *uarg) uarg->callback(NULL, uarg, true); } +static inline void skb_zcopy_put_abort(struct ubuf_info *uarg, bool have_uref) +{ + if (uarg) { + if (uarg->callback == sock_zerocopy_callback) + sock_zerocopy_put_abort(uarg, have_uref); + else if (have_uref) + skb_zcopy_put(uarg); + } +} + /* Release a reference on a zerocopy structure */ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) { -- cgit v1.2.3 From 8c793822c5803e01d03f71c431f59316f0b278b7 Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Wed, 6 Jan 2021 14:18:37 -0800 Subject: skbuff: rename sock_zerocopy_* to msg_zerocopy_* At Willem's suggestion, rename the sock_zerocopy_* functions so that they match the MSG_ZEROCOPY flag, which makes it clear they are specific to this zerocopy implementation. Signed-off-by: Jonathan Lemon Acked-by: Willem de Bruijn Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9f7393167f0a..f6a3cee5c967 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -488,14 +488,14 @@ struct ubuf_info { int mm_account_pinned_pages(struct mmpin *mmp, size_t size); void mm_unaccount_pinned_pages(struct mmpin *mmp); -struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size); -struct ubuf_info *sock_zerocopy_realloc(struct sock *sk, size_t size, - struct ubuf_info *uarg); +struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size); +struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, + struct ubuf_info *uarg); -void sock_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); +void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); -void sock_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, - bool success); +void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, + bool success); int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len); int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, @@ -1481,8 +1481,8 @@ static inline void skb_zcopy_put(struct ubuf_info *uarg) static inline void skb_zcopy_put_abort(struct ubuf_info *uarg, bool have_uref) { if (uarg) { - if (uarg->callback == sock_zerocopy_callback) - sock_zerocopy_put_abort(uarg, have_uref); + if (uarg->callback == msg_zerocopy_callback) + msg_zerocopy_put_abort(uarg, have_uref); else if (have_uref) skb_zcopy_put(uarg); } @@ -2776,7 +2776,7 @@ static inline int skb_orphan_frags(struct sk_buff *skb, gfp_t gfp_mask) if (likely(!skb_zcopy(skb))) return 0; if (!skb_zcopy_is_nouarg(skb) && - skb_uarg(skb)->callback == sock_zerocopy_callback) + skb_uarg(skb)->callback == msg_zerocopy_callback) return 0; return skb_copy_ubufs(skb, gfp_mask); } -- cgit v1.2.3 From 06b4feb37e64e543714c971a4162a75e2e4024d4 Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Wed, 6 Jan 2021 14:18:38 -0800 Subject: net: group skb_shinfo zerocopy related bits together. In preparation for expanded zerocopy (TX and RX), move the zerocopy related bits out of tx_flags into their own flag word. Signed-off-by: Jonathan Lemon Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 38 +++++++++++++++++++++----------------- 1 file changed, 21 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f6a3cee5c967..7b5adc511ac6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -430,28 +430,32 @@ enum { /* device driver is going to provide hardware time stamp */ SKBTX_IN_PROGRESS = 1 << 2, - /* device driver supports TX zero-copy buffers */ - SKBTX_DEV_ZEROCOPY = 1 << 3, - /* generate wifi status information (where possible) */ SKBTX_WIFI_STATUS = 1 << 4, - /* This indicates at least one fragment might be overwritten - * (as in vmsplice(), sendfile() ...) - * If we need to compute a TX checksum, we'll need to copy - * all frags to avoid possible bad checksum - */ - SKBTX_SHARED_FRAG = 1 << 5, - /* generate software time stamp when entering packet scheduling */ SKBTX_SCHED_TSTAMP = 1 << 6, }; -#define SKBTX_ZEROCOPY_FRAG (SKBTX_DEV_ZEROCOPY | SKBTX_SHARED_FRAG) #define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \ SKBTX_SCHED_TSTAMP) #define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | SKBTX_ANY_SW_TSTAMP) +/* Definitions for flags in struct skb_shared_info */ +enum { + /* use zcopy routines */ + SKBFL_ZEROCOPY_ENABLE = BIT(0), + + /* This indicates at least one fragment might be overwritten + * (as in vmsplice(), sendfile() ...) + * If we need to compute a TX checksum, we'll need to copy + * all frags to avoid possible bad checksum + */ + SKBFL_SHARED_FRAG = BIT(1), +}; + +#define SKBFL_ZEROCOPY_FRAG (SKBFL_ZEROCOPY_ENABLE | SKBFL_SHARED_FRAG) + /* * The callback notifies userspace to release buffers when skb DMA is done in * lower device, the skb last reference should be 0 when calling this. @@ -506,7 +510,7 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, * the end of the header data, ie. at skb->end. */ struct skb_shared_info { - __u8 __unused; + __u8 flags; __u8 meta_len; __u8 nr_frags; __u8 tx_flags; @@ -1433,7 +1437,7 @@ static inline struct skb_shared_hwtstamps *skb_hwtstamps(struct sk_buff *skb) static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) { - bool is_zcopy = skb && skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY; + bool is_zcopy = skb && skb_shinfo(skb)->flags & SKBFL_ZEROCOPY_ENABLE; return is_zcopy ? skb_uarg(skb) : NULL; } @@ -1452,14 +1456,14 @@ static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg, else skb_zcopy_get(uarg); skb_shinfo(skb)->destructor_arg = uarg; - skb_shinfo(skb)->tx_flags |= SKBTX_ZEROCOPY_FRAG; + skb_shinfo(skb)->flags |= SKBFL_ZEROCOPY_FRAG; } } static inline void skb_zcopy_set_nouarg(struct sk_buff *skb, void *val) { skb_shinfo(skb)->destructor_arg = (void *)((uintptr_t) val | 0x1UL); - skb_shinfo(skb)->tx_flags |= SKBTX_ZEROCOPY_FRAG; + skb_shinfo(skb)->flags |= SKBFL_ZEROCOPY_FRAG; } static inline bool skb_zcopy_is_nouarg(struct sk_buff *skb) @@ -1497,7 +1501,7 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) if (!skb_zcopy_is_nouarg(skb)) uarg->callback(skb, uarg, zerocopy_success); - skb_shinfo(skb)->tx_flags &= ~SKBTX_ZEROCOPY_FRAG; + skb_shinfo(skb)->flags &= ~SKBFL_ZEROCOPY_FRAG; } } @@ -3323,7 +3327,7 @@ static inline int skb_linearize(struct sk_buff *skb) static inline bool skb_has_shared_frag(const struct sk_buff *skb) { return skb_is_nonlinear(skb) && - skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG; + skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; } /** -- cgit v1.2.3 From 04c2d33eabdc76df730e1e356f6b2c656381d7d5 Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Wed, 6 Jan 2021 14:18:39 -0800 Subject: skbuff: add flags to ubuf_info for ubuf setup Currently, when an ubuf is attached to a new skb, the shared flags word is initialized to a fixed value. Instead of doing this, set the default flags in the ubuf, and have new skbs inherit from this default. This is needed when setting up different zerocopy types. Signed-off-by: Jonathan Lemon Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7b5adc511ac6..a7bc71d2debb 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -480,6 +480,7 @@ struct ubuf_info { }; }; refcount_t refcnt; + u8 flags; struct mmpin { struct user_struct *user; @@ -1456,7 +1457,7 @@ static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg, else skb_zcopy_get(uarg); skb_shinfo(skb)->destructor_arg = uarg; - skb_shinfo(skb)->flags |= SKBFL_ZEROCOPY_FRAG; + skb_shinfo(skb)->flags |= uarg->flags; } } -- cgit v1.2.3 From 9ee5e5ade033875191a2d2e470033e9cdde44a6a Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Wed, 6 Jan 2021 14:18:40 -0800 Subject: tap/tun: add skb_zcopy_init() helper for initialization. Replace direct assignments with skb_zcopy_init() for zerocopy cases where a new skb is initialized, without changing the reference counts. Signed-off-by: Jonathan Lemon Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a7bc71d2debb..68ad45a98810 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1448,6 +1448,12 @@ static inline void skb_zcopy_get(struct ubuf_info *uarg) refcount_inc(&uarg->refcnt); } +static inline void skb_zcopy_init(struct sk_buff *skb, struct ubuf_info *uarg) +{ + skb_shinfo(skb)->destructor_arg = uarg; + skb_shinfo(skb)->flags |= uarg->flags; +} + static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg, bool *have_ref) { @@ -1456,8 +1462,7 @@ static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg, *have_ref = false; else skb_zcopy_get(uarg); - skb_shinfo(skb)->destructor_arg = uarg; - skb_shinfo(skb)->flags |= uarg->flags; + skb_zcopy_init(skb, uarg); } } -- cgit v1.2.3 From 8e0449172497a915e79da66b222255dc9b4a5f31 Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Wed, 6 Jan 2021 14:18:41 -0800 Subject: skbuff: Rename skb_zcopy_{get|put} to net_zcopy_{get|put} Unlike the rest of the skb_zcopy_ functions, these routines operate on a 'struct ubuf', not a skb. Remove the 'skb_' prefix from the naming to make things clearer. Suggested-by: Willem de Bruijn Signed-off-by: Jonathan Lemon Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 68ad45a98810..7a057b1f1eb8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1443,7 +1443,7 @@ static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) return is_zcopy ? skb_uarg(skb) : NULL; } -static inline void skb_zcopy_get(struct ubuf_info *uarg) +static inline void net_zcopy_get(struct ubuf_info *uarg) { refcount_inc(&uarg->refcnt); } @@ -1461,7 +1461,7 @@ static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg, if (unlikely(have_ref && *have_ref)) *have_ref = false; else - skb_zcopy_get(uarg); + net_zcopy_get(uarg); skb_zcopy_init(skb, uarg); } } @@ -1482,19 +1482,19 @@ static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb) return (void *)((uintptr_t) skb_shinfo(skb)->destructor_arg & ~0x1UL); } -static inline void skb_zcopy_put(struct ubuf_info *uarg) +static inline void net_zcopy_put(struct ubuf_info *uarg) { if (uarg) uarg->callback(NULL, uarg, true); } -static inline void skb_zcopy_put_abort(struct ubuf_info *uarg, bool have_uref) +static inline void net_zcopy_put_abort(struct ubuf_info *uarg, bool have_uref) { if (uarg) { if (uarg->callback == msg_zerocopy_callback) msg_zerocopy_put_abort(uarg, have_uref); else if (have_uref) - skb_zcopy_put(uarg); + net_zcopy_put(uarg); } } -- cgit v1.2.3 From 43b5169d8355ccf26d726fbc75f083b2429113e4 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 22 Dec 2020 22:09:28 +0100 Subject: net, xdp: Introduce xdp_init_buff utility routine Introduce xdp_init_buff utility routine to initialize xdp_buff fields const over NAPI iterations (e.g. frame_sz or rxq pointer). Rely on xdp_init_buff in all XDP capable drivers. Signed-off-by: Lorenzo Bianconi Signed-off-by: Daniel Borkmann Reviewed-by: Alexander Duyck Acked-by: Jesper Dangaard Brouer Acked-by: John Fastabend Acked-by: Shay Agroskin Acked-by: Martin Habets Acked-by: Camelia Groza Acked-by: Marcin Wojtas Link: https://lore.kernel.org/bpf/7f8329b6da1434dc2b05a77f2e800b29628a8913.1608670965.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/net/xdp.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/xdp.h b/include/net/xdp.h index 600acb307db6..8a589f7e08e0 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -76,6 +76,13 @@ struct xdp_buff { u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/ }; +static __always_inline void +xdp_init_buff(struct xdp_buff *xdp, u32 frame_sz, struct xdp_rxq_info *rxq) +{ + xdp->frame_sz = frame_sz; + xdp->rxq = rxq; +} + /* Reserve memory area at end-of data area. * * This macro reserves tailroom in the XDP buffer by limiting the -- cgit v1.2.3 From be9df4aff65f18caa79b35f88f42c3d5a43af14f Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 22 Dec 2020 22:09:29 +0100 Subject: net, xdp: Introduce xdp_prepare_buff utility routine Introduce xdp_prepare_buff utility routine to initialize per-descriptor xdp_buff fields (e.g. xdp_buff pointers). Rely on xdp_prepare_buff() in all XDP capable drivers. Signed-off-by: Lorenzo Bianconi Signed-off-by: Daniel Borkmann Reviewed-by: Alexander Duyck Acked-by: Jesper Dangaard Brouer Acked-by: John Fastabend Acked-by: Shay Agroskin Acked-by: Martin Habets Acked-by: Camelia Groza Acked-by: Marcin Wojtas Link: https://lore.kernel.org/bpf/45f46f12295972a97da8ca01990b3e71501e9d89.1608670965.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/net/xdp.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/net/xdp.h b/include/net/xdp.h index 8a589f7e08e0..0cf3976ce77c 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -83,6 +83,18 @@ xdp_init_buff(struct xdp_buff *xdp, u32 frame_sz, struct xdp_rxq_info *rxq) xdp->rxq = rxq; } +static __always_inline void +xdp_prepare_buff(struct xdp_buff *xdp, unsigned char *hard_start, + int headroom, int data_len, const bool meta_valid) +{ + unsigned char *data = hard_start + headroom; + + xdp->data_hard_start = hard_start; + xdp->data = data; + xdp->data_end = data + data_len; + xdp->data_meta = meta_valid ? data : data + 1; +} + /* Reserve memory area at end-of data area. * * This macro reserves tailroom in the XDP buffer by limiting the -- cgit v1.2.3 From 994122211665301080cd232c06ae219b681dcb57 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 7 Jan 2021 17:34:01 -0600 Subject: remoteproc: qcom: expose types for COMPILE_TEST Stub functions are defined for SSR notifier registration in case QCOM_RPROC_COMMON is not configured. As a result, code that uses these functions can link successfully even if the common remoteproc code is not built. Code that registers an SSR notifier function likely needs the types defined in "qcom_rproc.h", but those are only exposed if QCOM_RPROC_COMMON is enabled. Rearrange the conditional definition so the qcom_ssr_notify_data structure and qcom_ssr_notify_type enumerated type are defined whether or not QCOM_RPROC_COMMON is enabled. Reviewed-by: Bjorn Andersson Signed-off-by: Alex Elder Signed-off-by: Jakub Kicinski --- include/linux/remoteproc/qcom_rproc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/remoteproc/qcom_rproc.h b/include/linux/remoteproc/qcom_rproc.h index 647051662174..82b211518136 100644 --- a/include/linux/remoteproc/qcom_rproc.h +++ b/include/linux/remoteproc/qcom_rproc.h @@ -3,8 +3,6 @@ struct notifier_block; -#if IS_ENABLED(CONFIG_QCOM_RPROC_COMMON) - /** * enum qcom_ssr_notify_type - Startup/Shutdown events related to a remoteproc * processor. @@ -26,6 +24,8 @@ struct qcom_ssr_notify_data { bool crashed; }; +#if IS_ENABLED(CONFIG_QCOM_RPROC_COMMON) + void *qcom_register_ssr_notifier(const char *name, struct notifier_block *nb); int qcom_unregister_ssr_notifier(void *notify, struct notifier_block *nb); -- cgit v1.2.3 From ce2ceb9b1cff777c7d8beb368eddc3b8e45381f6 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 7 Jan 2021 17:34:02 -0600 Subject: soc: qcom: mdt_loader: define stubs for COMPILE_TEST Define stub functions for the exposed MDT functions in case QCOM_MDT_LOADER is not configured. This allows users of these functions to link correctly for COMPILE_TEST builds without QCOM_SCM enabled. Reviewed-by: Bjorn Andersson Signed-off-by: Alex Elder Signed-off-by: Jakub Kicinski --- include/linux/soc/qcom/mdt_loader.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'include') diff --git a/include/linux/soc/qcom/mdt_loader.h b/include/linux/soc/qcom/mdt_loader.h index e600baec6825..afd47217996b 100644 --- a/include/linux/soc/qcom/mdt_loader.h +++ b/include/linux/soc/qcom/mdt_loader.h @@ -11,6 +11,8 @@ struct device; struct firmware; +#if IS_ENABLED(CONFIG_QCOM_MDT_LOADER) + ssize_t qcom_mdt_get_size(const struct firmware *fw); int qcom_mdt_load(struct device *dev, const struct firmware *fw, const char *fw_name, int pas_id, void *mem_region, @@ -23,4 +25,37 @@ int qcom_mdt_load_no_init(struct device *dev, const struct firmware *fw, phys_addr_t *reloc_base); void *qcom_mdt_read_metadata(const struct firmware *fw, size_t *data_len); +#else /* !IS_ENABLED(CONFIG_QCOM_MDT_LOADER) */ + +static inline ssize_t qcom_mdt_get_size(const struct firmware *fw) +{ + return -ENODEV; +} + +static inline int qcom_mdt_load(struct device *dev, const struct firmware *fw, + const char *fw_name, int pas_id, + void *mem_region, phys_addr_t mem_phys, + size_t mem_size, phys_addr_t *reloc_base) +{ + return -ENODEV; +} + +static inline int qcom_mdt_load_no_init(struct device *dev, + const struct firmware *fw, + const char *fw_name, int pas_id, + void *mem_region, phys_addr_t mem_phys, + size_t mem_size, + phys_addr_t *reloc_base) +{ + return -ENODEV; +} + +static inline void *qcom_mdt_read_metadata(const struct firmware *fw, + size_t *data_len) +{ + return ERR_PTR(-ENODEV); +} + +#endif /* !IS_ENABLED(CONFIG_QCOM_MDT_LOADER) */ + #endif -- cgit v1.2.3 From 1d11fa696733ffb9ac24771716b1b1b9953e5a48 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 8 Jan 2021 03:39:03 -0800 Subject: net-gro: remove GRO_DROP GRO_DROP can only be returned from napi_gro_frags() if the skb has not been allocated by a prior napi_get_frags() Since drivers must use napi_get_frags() and test its result before populating the skb with metadata, we can safely remove GRO_DROP since it offers no practical use. Signed-off-by: Eric Dumazet Cc: Jesse Brandeburg Acked-by: Edward Cree Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1ec3ac5d5bbf..5b949076ed23 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -376,7 +376,6 @@ enum gro_result { GRO_MERGED_FREE, GRO_HELD, GRO_NORMAL, - GRO_DROP, GRO_CONSUMED, }; typedef enum gro_result gro_result_t; -- cgit v1.2.3 From 0f9f696a502e1b01fbb137a08f56f157da9d95eb Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Fri, 8 Jan 2021 16:47:59 -0800 Subject: mptcp: add set_flags command in PM netlink This patch added a new command MPTCP_PM_CMD_SET_FLAGS in PM netlink: In mptcp_nl_cmd_set_flags, parse the input address, get the backup value according to whether the address's FLAG_BACKUP flag is set from the user-space. Then check whether this address had been added in the local address list. If it had been, then call mptcp_nl_addr_backup to deal with this address. In mptcp_nl_addr_backup, traverse all the existing msk sockets to find the relevant sockets, and call mptcp_pm_nl_mp_prio_send_ack to send out a MP_PRIO ACK packet. Finally in mptcp_nl_cmd_set_flags, set or clear the address's FLAG_BACKUP flag. Signed-off-by: Geliang Tang Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- include/uapi/linux/mptcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 9762660df741..3674a451a18c 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -82,6 +82,7 @@ enum { MPTCP_PM_CMD_FLUSH_ADDRS, MPTCP_PM_CMD_SET_LIMITS, MPTCP_PM_CMD_GET_LIMITS, + MPTCP_PM_CMD_SET_FLAGS, __MPTCP_PM_CMD_AFTER_LAST }; -- cgit v1.2.3 From b7a9e0da2d1c954b7c38217a29e002528b90d174 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 9 Jan 2021 02:01:46 +0200 Subject: net: switchdev: remove vid_begin -> vid_end range from VLAN objects The call path of a switchdev VLAN addition to the bridge looks something like this today: nbp_vlan_init | __br_vlan_set_default_pvid | | | | | br_afspec | | | | | | | v | | | br_process_vlan_info | | | | | | | v | | | br_vlan_info | | | / \ / | | / \ / | | / \ / | | / \ / v v v v v nbp_vlan_add br_vlan_add ------+ | ^ ^ | | | / | | | | / / / | \ br_vlan_get_master/ / v \ ^ / / br_vlan_add_existing \ | / / | \ | / / / \ | / / / \ | / / / \ | / / / v | | v / __vlan_add / / | / / | / v | / __vlan_vid_add | / \ | / v v v br_switchdev_port_vlan_add The ranges UAPI was introduced to the bridge in commit bdced7ef7838 ("bridge: support for multiple vlans and vlan ranges in setlink and dellink requests") (Jan 10 2015). But the VLAN ranges (parsed in br_afspec) have always been passed one by one, through struct bridge_vlan_info tmp_vinfo, to br_vlan_info. So the range never went too far in depth. Then Scott Feldman introduced the switchdev_port_bridge_setlink function in commit 47f8328bb1a4 ("switchdev: add new switchdev bridge setlink"). That marked the introduction of the SWITCHDEV_OBJ_PORT_VLAN, which made full use of the range. But switchdev_port_bridge_setlink was called like this: br_setlink -> br_afspec -> switchdev_port_bridge_setlink Basically, the switchdev and the bridge code were not tightly integrated. Then commit 41c498b9359e ("bridge: restore br_setlink back to original") came, and switchdev drivers were required to implement .ndo_bridge_setlink = switchdev_port_bridge_setlink for a while. In the meantime, commits such as 0944d6b5a2fa ("bridge: try switchdev op first in __vlan_vid_add/del") finally made switchdev penetrate the br_vlan_info() barrier and start to develop the call path we have today. But remember, br_vlan_info() still receives VLANs one by one. Then Arkadi Sharshevsky refactored the switchdev API in 2017 in commit 29ab586c3d83 ("net: switchdev: Remove bridge bypass support from switchdev") so that drivers would not implement .ndo_bridge_setlink any longer. The switchdev_port_bridge_setlink also got deleted. This refactoring removed the parallel bridge_setlink implementation from switchdev, and left the only switchdev VLAN objects to be the ones offloaded from __vlan_vid_add (basically RX filtering) and __vlan_add (the latter coming from commit 9c86ce2c1ae3 ("net: bridge: Notify about bridge VLANs")). That is to say, today the switchdev VLAN object ranges are not used in the kernel. Refactoring the above call path is a bit complicated, when the bridge VLAN call path is already a bit complicated. Let's go off and finish the job of commit 29ab586c3d83 by deleting the bogus iteration through the VLAN ranges from the drivers. Some aspects of this feature never made too much sense in the first place. For example, what is a range of VLANs all having the BRIDGE_VLAN_INFO_PVID flag supposed to mean, when a port can obviously have a single pvid? This particular configuration _is_ denied as of commit 6623c60dc28e ("bridge: vlan: enforce no pvid flag in vlan ranges"), but from an API perspective, the driver still has to play pretend, and only offload the vlan->vid_end as pvid. And the addition of a switchdev VLAN object can modify the flags of another, completely unrelated, switchdev VLAN object! (a VLAN that is PVID will invalidate the PVID flag from whatever other VLAN had previously been offloaded with switchdev and had that flag. Yet switchdev never notifies about that change, drivers are supposed to guess). Nonetheless, having a VLAN range in the API makes error handling look scarier than it really is - unwinding on errors and all of that. When in reality, no one really calls this API with more than one VLAN. It is all unnecessary complexity. And despite appearing pretentious (two-phase transactional model and all), the switchdev API is really sloppy because the VLAN addition and removal operations are not paired with one another (you can add a VLAN 100 times and delete it just once). The bridge notifies through switchdev of a VLAN addition not only when the flags of an existing VLAN change, but also when nothing changes. There are switchdev drivers out there who don't like adding a VLAN that has already been added, and those checks don't really belong at driver level. But the fact that the API contains ranges is yet another factor that prevents this from being addressed in the future. Of the existing switchdev pieces of hardware, it appears that only Mellanox Spectrum supports offloading more than one VLAN at a time, through mlxsw_sp_port_vlan_set. I have kept that code internal to the driver, because there is some more bookkeeping that makes use of it, but I deleted it from the switchdev API. But since the switchdev support for ranges has already been de facto deleted by a Mellanox employee and nobody noticed for 4 years, I'm going to assume it's not a biggie. Signed-off-by: Vladimir Oltean Reviewed-by: Ido Schimmel # switchdev and mlxsw Reviewed-by: Florian Fainelli Reviewed-by: Kurt Kanzenbach # hellcreek Signed-off-by: Jakub Kicinski --- include/net/switchdev.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 99cd538d6519..bac7d3ba574f 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -97,8 +97,7 @@ struct switchdev_obj { struct switchdev_obj_port_vlan { struct switchdev_obj obj; u16 flags; - u16 vid_begin; - u16 vid_end; + u16 vid; }; #define SWITCHDEV_OBJ_PORT_VLAN(OBJ) \ -- cgit v1.2.3 From ffb68fc58e9640762be891f9aebe4f5aac615ab3 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 9 Jan 2021 02:01:48 +0200 Subject: net: switchdev: remove the transaction structure from port object notifiers Since the introduction of the switchdev API, port objects were transmitted to drivers for offloading using a two-step transactional model, with a prepare phase that was supposed to catch all errors, and a commit phase that was supposed to never fail. Some classes of failures can never be avoided, like hardware access, or memory allocation. In the latter case, merely attempting to move the memory allocation to the preparation phase makes it impossible to avoid memory leaks, since commit 91cf8eceffc1 ("switchdev: Remove unused transaction item queue") which has removed the unused mechanism of passing on the allocated memory between one phase and another. It is time we admit that separating the preparation from the commit phase is something that is best left for the driver to decide, and not something that should be baked into the API, especially since there are no switchdev callers that depend on this. This patch removes the struct switchdev_trans member from switchdev port object notifier structures, and converts drivers to not look at this member. Where driver conversion is trivial (like in the case of the Marvell Prestera driver, NXP DPAA2 switch, TI CPSW, and Rocker drivers), it is done in this patch. Where driver conversion needs more attention (DSA, Mellanox Spectrum), the conversion is left for subsequent patches and here we only fake the prepare/commit phases at a lower level, just not in the switchdev notifier itself. Where the code has a natural structure that is best left alone as a preparation and a commit phase (as in the case of the Ocelot switch), that structure is left in place, just made to not depend upon the switchdev transactional model. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Acked-by: Linus Walleij Acked-by: Jiri Pirko Reviewed-by: Ido Schimmel Signed-off-by: Jakub Kicinski --- include/net/switchdev.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index bac7d3ba574f..cbe6e35d51f5 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -233,7 +233,6 @@ struct switchdev_notifier_fdb_info { struct switchdev_notifier_port_obj_info { struct switchdev_notifier_info info; /* must be first */ const struct switchdev_obj *obj; - struct switchdev_trans *trans; bool handled; }; @@ -288,7 +287,6 @@ int switchdev_handle_port_obj_add(struct net_device *dev, bool (*check_cb)(const struct net_device *dev), int (*add_cb)(struct net_device *dev, const struct switchdev_obj *obj, - struct switchdev_trans *trans, struct netlink_ext_ack *extack)); int switchdev_handle_port_obj_del(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, @@ -372,7 +370,6 @@ switchdev_handle_port_obj_add(struct net_device *dev, bool (*check_cb)(const struct net_device *dev), int (*add_cb)(struct net_device *dev, const struct switchdev_obj *obj, - struct switchdev_trans *trans, struct netlink_ext_ack *extack)) { return 0; -- cgit v1.2.3 From bae33f2b5afea932176c1b9096851c81dc0983de Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 9 Jan 2021 02:01:50 +0200 Subject: net: switchdev: remove the transaction structure from port attributes Since the introduction of the switchdev API, port attributes were transmitted to drivers for offloading using a two-step transactional model, with a prepare phase that was supposed to catch all errors, and a commit phase that was supposed to never fail. Some classes of failures can never be avoided, like hardware access, or memory allocation. In the latter case, merely attempting to move the memory allocation to the preparation phase makes it impossible to avoid memory leaks, since commit 91cf8eceffc1 ("switchdev: Remove unused transaction item queue") which has removed the unused mechanism of passing on the allocated memory between one phase and another. It is time we admit that separating the preparation from the commit phase is something that is best left for the driver to decide, and not something that should be baked into the API, especially since there are no switchdev callers that depend on this. This patch removes the struct switchdev_trans member from switchdev port attribute notifier structures, and converts drivers to not look at this member. In part, this patch contains a revert of my previous commit 2e554a7a5d8a ("net: dsa: propagate switchdev vlan_filtering prepare phase to drivers"). For the most part, the conversion was trivial except for: - Rocker's world implementation based on Broadcom OF-DPA had an odd implementation of ofdpa_port_attr_bridge_flags_set. The conversion was done mechanically, by pasting the implementation twice, then only keeping the code that would get executed during prepare phase on top, then only keeping the code that gets executed during the commit phase on bottom, then simplifying the resulting code until this was obtained. - DSA's offloading of STP state, bridge flags, VLAN filtering and multicast router could be converted right away. But the ageing time could not, so a shim was introduced and this was left for a further commit. Signed-off-by: Vladimir Oltean Acked-by: Linus Walleij Acked-by: Jiri Pirko Reviewed-by: Kurt Kanzenbach # hellcreek Reviewed-by: Linus Walleij # RTL8366RB Reviewed-by: Ido Schimmel Reviewed-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 3 +-- include/net/switchdev.h | 7 ++----- include/soc/mscc/ocelot.h | 3 +-- 3 files changed, 4 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 9a0cab5fb7c4..d0f043091969 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -565,8 +565,7 @@ struct dsa_switch_ops { * VLAN support */ int (*port_vlan_filtering)(struct dsa_switch *ds, int port, - bool vlan_filtering, - struct switchdev_trans *trans); + bool vlan_filtering); int (*port_vlan_prepare)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); void (*port_vlan_add)(struct dsa_switch *ds, int port, diff --git a/include/net/switchdev.h b/include/net/switchdev.h index cbe6e35d51f5..f873e2c5e125 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -239,7 +239,6 @@ struct switchdev_notifier_port_obj_info { struct switchdev_notifier_port_attr_info { struct switchdev_notifier_info info; /* must be first */ const struct switchdev_attr *attr; - struct switchdev_trans *trans; bool handled; }; @@ -298,8 +297,7 @@ int switchdev_handle_port_attr_set(struct net_device *dev, struct switchdev_notifier_port_attr_info *port_attr_info, bool (*check_cb)(const struct net_device *dev), int (*set_cb)(struct net_device *dev, - const struct switchdev_attr *attr, - struct switchdev_trans *trans)); + const struct switchdev_attr *attr)); #else static inline void switchdev_deferred_process(void) @@ -390,8 +388,7 @@ switchdev_handle_port_attr_set(struct net_device *dev, struct switchdev_notifier_port_attr_info *port_attr_info, bool (*check_cb)(const struct net_device *dev), int (*set_cb)(struct net_device *dev, - const struct switchdev_attr *attr, - struct switchdev_trans *trans)) + const struct switchdev_attr *attr)) { return 0; } diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 2f4cd3288bcc..f3db75c0172b 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -739,8 +739,7 @@ int ocelot_get_ts_info(struct ocelot *ocelot, int port, void ocelot_set_ageing_time(struct ocelot *ocelot, unsigned int msecs); void ocelot_adjust_link(struct ocelot *ocelot, int port, struct phy_device *phydev); -int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, bool enabled, - struct switchdev_trans *trans); +int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, bool enabled); void ocelot_bridge_stp_state_set(struct ocelot *ocelot, int port, u8 state); int ocelot_port_bridge_join(struct ocelot *ocelot, int port, struct net_device *bridge); -- cgit v1.2.3 From a52b2da778fc93e01c4e5a744953f2ba1ec01c00 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 9 Jan 2021 02:01:52 +0200 Subject: net: dsa: remove the transactional logic from MDB entries For many drivers, the .port_mdb_prepare callback was not a good opportunity to avoid any error condition, and they would suppress errors found during the actual commit phase. Where a logical separation between the prepare and the commit phase existed, the function that used to implement the .port_mdb_prepare callback still exists, but now it is called directly from .port_mdb_add, which was modified to return an int code. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Acked-by: Linus Walleij Acked-by: Jiri Pirko Reviewed-by: Kurt Kanzenbach # hellcreek Reviewed-by: Linus Wallei # RTL8366 Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index d0f043091969..b8c0550dfa74 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -585,10 +585,8 @@ struct dsa_switch_ops { /* * Multicast database */ - int (*port_mdb_prepare)(struct dsa_switch *ds, int port, + int (*port_mdb_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb); - void (*port_mdb_add)(struct dsa_switch *ds, int port, - const struct switchdev_obj_port_mdb *mdb); int (*port_mdb_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb); /* -- cgit v1.2.3 From 1958d5815c91353960df2198a74f5ca15785ed28 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 9 Jan 2021 02:01:53 +0200 Subject: net: dsa: remove the transactional logic from VLAN objects It should be the driver's business to logically separate its VLAN offloading into a preparation and a commit phase, and some drivers don't need / can't do this. So remove the transactional shim from DSA and let drivers propagate errors directly from the .port_vlan_add callback. It would appear that the code has worse error handling now than it had before. DSA is the only in-kernel user of switchdev that offloads one switchdev object to more than one port: for every VLAN object offloaded to a user port, that VLAN is also offloaded to the CPU port. So the "prepare for user port -> check for errors -> prepare for CPU port -> check for errors -> commit for user port -> commit for CPU port" sequence appears to make more sense than the one we are using now: "offload to user port -> check for errors -> offload to CPU port -> check for errors", but it is really a compromise. In the new way, we can catch errors from the commit phase that we previously had to ignore. But we have our hands tied and cannot do any rollback now: if we add a VLAN on the CPU port and it fails, we can't do the rollback by simply deleting it from the user port, because the switchdev API is not so nice with us: it could have simply been there already, even with the same flags. So we don't even attempt to rollback anything on addition error, just leave whatever VLANs managed to get offloaded right where they are. This should not be a problem at all in practice. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Acked-by: Linus Walleij Acked-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index b8c0550dfa74..c9a3dd7588df 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -566,10 +566,8 @@ struct dsa_switch_ops { */ int (*port_vlan_filtering)(struct dsa_switch *ds, int port, bool vlan_filtering); - int (*port_vlan_prepare)(struct dsa_switch *ds, int port, + int (*port_vlan_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); - void (*port_vlan_add)(struct dsa_switch *ds, int port, - const struct switchdev_obj_port_vlan *vlan); int (*port_vlan_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); /* -- cgit v1.2.3 From 8f73cc50ba2dd5a5749d3670e453c3864258b892 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 9 Jan 2021 02:01:56 +0200 Subject: net: switchdev: delete the transaction object Now that all users of struct switchdev_trans have been modified to do without it, we can remove this structure and the two helpers to determine the phase. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Reviewed-by: Ido Schimmel Acked-by: Linus Walleij Acked-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- include/net/switchdev.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index f873e2c5e125..88fcac140966 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -16,20 +16,6 @@ #define SWITCHDEV_F_SKIP_EOPNOTSUPP BIT(1) #define SWITCHDEV_F_DEFER BIT(2) -struct switchdev_trans { - bool ph_prepare; -}; - -static inline bool switchdev_trans_ph_prepare(struct switchdev_trans *trans) -{ - return trans && trans->ph_prepare; -} - -static inline bool switchdev_trans_ph_commit(struct switchdev_trans *trans) -{ - return trans && !trans->ph_prepare; -} - enum switchdev_attr_id { SWITCHDEV_ATTR_ID_UNDEFINED, SWITCHDEV_ATTR_ID_PORT_STP_STATE, -- cgit v1.2.3 From ad0bfc233ae2e7ee3bcb9a6089e4aa54e2b44fa1 Mon Sep 17 00:00:00 2001 From: Danilo Carvalho Date: Fri, 8 Jan 2021 22:21:04 +0000 Subject: Fix whitespace in uapi/linux/tcp.h. List of things fixed: - Two of the socket options were idented with spaces instead of tabs. - Trailing whitespace in some lines. - Improper spacing around parenthesis caught by checkpatch.pl. - Mix of space and tabs in tcp_word_hdr union. Signed-off-by: Danilo Carvalho Link: https://lore.kernel.org/r/20210108222104.2079472-1-doak@google.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/tcp.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 13ceeb395eb8..768e93bd5b51 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -51,7 +51,7 @@ struct tcphdr { fin:1; #else #error "Adjust your defines" -#endif +#endif __be16 window; __sum16 check; __be16 urg_ptr; @@ -62,14 +62,14 @@ struct tcphdr { * (union is compatible to any of its members) * This means this part of the code is -fstrict-aliasing safe now. */ -union tcp_word_hdr { +union tcp_word_hdr { struct tcphdr hdr; - __be32 words[5]; -}; + __be32 words[5]; +}; -#define tcp_flag_word(tp) ( ((union tcp_word_hdr *)(tp))->words [3]) +#define tcp_flag_word(tp) (((union tcp_word_hdr *)(tp))->words[3]) -enum { +enum { TCP_FLAG_CWR = __constant_cpu_to_be32(0x00800000), TCP_FLAG_ECE = __constant_cpu_to_be32(0x00400000), TCP_FLAG_URG = __constant_cpu_to_be32(0x00200000), @@ -80,7 +80,7 @@ enum { TCP_FLAG_FIN = __constant_cpu_to_be32(0x00010000), TCP_RESERVED_BITS = __constant_cpu_to_be32(0x0F000000), TCP_DATA_OFFSET = __constant_cpu_to_be32(0xF0000000) -}; +}; /* * TCP general constants @@ -103,8 +103,8 @@ enum { #define TCP_QUICKACK 12 /* Block/reenable quick acks */ #define TCP_CONGESTION 13 /* Congestion control algorithm */ #define TCP_MD5SIG 14 /* TCP MD5 Signature (RFC2385) */ -#define TCP_THIN_LINEAR_TIMEOUTS 16 /* Use linear timeouts for thin streams*/ -#define TCP_THIN_DUPACK 17 /* Fast retrans. after 1 dupack */ +#define TCP_THIN_LINEAR_TIMEOUTS 16 /* Use linear timeouts for thin streams*/ +#define TCP_THIN_DUPACK 17 /* Fast retrans. after 1 dupack */ #define TCP_USER_TIMEOUT 18 /* How long for loss retry before timeout */ #define TCP_REPAIR 19 /* TCP sock is under repair right now */ #define TCP_REPAIR_QUEUE 20 -- cgit v1.2.3 From c6458e72f6fd6ac7e390da0d9abe8446084886e5 Mon Sep 17 00:00:00 2001 From: Brendan Jackman Date: Tue, 12 Jan 2021 12:34:22 +0000 Subject: bpf: Clarify return value of probe str helpers When the buffer is too small to contain the input string, these helpers return the length of the buffer, not the length of the original string. This tries to make the docs totally clear about that, since "the length of the [copied ]string" could also refer to the length of the input. Signed-off-by: Brendan Jackman Signed-off-by: Daniel Borkmann Acked-by: KP Singh Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210112123422.2011234-1-jackmanb@google.com --- include/uapi/linux/bpf.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 77d7c1bb2923..a1ad32456f89 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2993,10 +2993,10 @@ union bpf_attr { * string length is larger than *size*, just *size*-1 bytes are * copied and the last byte is set to NUL. * - * On success, the length of the copied string is returned. This - * makes this helper useful in tracing programs for reading - * strings, and more importantly to get its length at runtime. See - * the following snippet: + * On success, returns the number of bytes that were written, + * including the terminal NUL. This makes this helper useful in + * tracing programs for reading strings, and more importantly to + * get its length at runtime. See the following snippet: * * :: * @@ -3024,7 +3024,7 @@ union bpf_attr { * **->mm->env_start**: using this helper and the return value, * one can quickly iterate at the right offset of the memory area. * Return - * On success, the strictly positive length of the string, + * On success, the strictly positive length of the output string, * including the trailing NUL character. On error, a negative * value. * -- cgit v1.2.3 From a643bff752dcf72a07e1b2ab2f8587e4f51118be Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 11 Jan 2021 23:55:14 -0800 Subject: bpf: Add bpf_patch_call_args prototype to include/linux/bpf.h Add bpf_patch_call_args() prototype. This function is called from BPF verifier and only if CONFIG_BPF_JIT_ALWAYS_ON is not defined. This fixes compiler warning about missing prototype in some kernel configurations. Fixes: 1ea47e01ad6e ("bpf: add support for bpf_call to interpreter") Reported-by: kernel test robot Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210112075520.4103414-2-andrii@kernel.org --- include/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 07cb5d15e743..ef9309604b3e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1403,7 +1403,10 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, union bpf_attr __user *uattr); + +#ifndef CONFIG_BPF_JIT_ALWAYS_ON void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); +#endif struct btf *bpf_get_btf_vmlinux(void); -- cgit v1.2.3 From 6943c2b05bf09fd5c5729f7d7d803bf3f126cb9a Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 11 Jan 2021 23:55:15 -0800 Subject: bpf: Avoid warning when re-casting __bpf_call_base into __bpf_call_base_args BPF interpreter uses extra input argument, so re-casts __bpf_call_base into __bpf_call_base_args. Avoid compiler warning about incompatible function prototypes by casting to void * first. Fixes: 1ea47e01ad6e ("bpf: add support for bpf_call to interpreter") Reported-by: kernel test robot Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210112075520.4103414-3-andrii@kernel.org --- include/linux/filter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 29c27656165b..5edf2b660881 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -886,7 +886,7 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp); u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); #define __bpf_call_base_args \ ((u64 (*)(u64, u64, u64, u64, u64, const struct bpf_insn *)) \ - __bpf_call_base) + (void *)__bpf_call_base) struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog); void bpf_jit_compile(struct bpf_prog *prog); -- cgit v1.2.3 From 936f8946bdb48239f4292812d4d2e26c6d328c95 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 11 Jan 2021 23:55:16 -0800 Subject: bpf: Declare __bpf_free_used_maps() unconditionally __bpf_free_used_maps() is always defined in kernel/bpf/core.c, while include/linux/bpf.h is guarding it behind CONFIG_BPF_SYSCALL. Move it out of that guard region and fix compiler warning. Fixes: a2ea07465c8d ("bpf: Fix missing prog untrack in release_maps") Reported-by: kernel test robot Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210112075520.4103414-4-andrii@kernel.org --- include/linux/bpf.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ef9309604b3e..6e585dbc10df 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1206,8 +1206,6 @@ void bpf_prog_sub(struct bpf_prog *prog, int i); void bpf_prog_inc(struct bpf_prog *prog); struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); -void __bpf_free_used_maps(struct bpf_prog_aux *aux, - struct bpf_map **used_maps, u32 len); void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock); void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock); @@ -1676,6 +1674,9 @@ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, return bpf_prog_get_type_dev(ufd, type, false); } +void __bpf_free_used_maps(struct bpf_prog_aux *aux, + struct bpf_map **used_maps, u32 len); + bool bpf_prog_get_ok(struct bpf_prog *, enum bpf_prog_type *, bool); int bpf_prog_offload_compile(struct bpf_prog *prog); -- cgit v1.2.3 From 541c3bad8dc51b253ba8686d0cd7628e6b9b5f4c Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 11 Jan 2021 23:55:18 -0800 Subject: bpf: Support BPF ksym variables in kernel modules Add support for directly accessing kernel module variables from BPF programs using special ldimm64 instructions. This functionality builds upon vmlinux ksym support, but extends ldimm64 with src_reg=BPF_PSEUDO_BTF_ID to allow specifying kernel module BTF's FD in insn[1].imm field. During BPF program load time, verifier will resolve FD to BTF object and will take reference on BTF object itself and, for module BTFs, corresponding module as well, to make sure it won't be unloaded from under running BPF program. The mechanism used is similar to how bpf_prog keeps track of used bpf_maps. One interesting change is also in how per-CPU variable is determined. The logic is to find .data..percpu data section in provided BTF, but both vmlinux and module each have their own .data..percpu entries in BTF. So for module's case, the search for DATASEC record needs to look at only module's added BTF types. This is implemented with custom search function. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Acked-by: Hao Luo Link: https://lore.kernel.org/bpf/20210112075520.4103414-6-andrii@kernel.org --- include/linux/bpf.h | 10 ++++++++++ include/linux/bpf_verifier.h | 3 +++ include/linux/btf.h | 3 +++ 3 files changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6e585dbc10df..1aac2af12fed 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -761,9 +761,15 @@ struct bpf_ctx_arg_aux { u32 btf_id; }; +struct btf_mod_pair { + struct btf *btf; + struct module *module; +}; + struct bpf_prog_aux { atomic64_t refcnt; u32 used_map_cnt; + u32 used_btf_cnt; u32 max_ctx_offset; u32 max_pkt_offset; u32 max_tp_access; @@ -802,6 +808,7 @@ struct bpf_prog_aux { const struct bpf_prog_ops *ops; struct bpf_map **used_maps; struct mutex used_maps_mutex; /* mutex for used_maps and used_map_cnt */ + struct btf_mod_pair *used_btfs; struct bpf_prog *prog; struct user_struct *user; u64 load_time; /* ns since boottime */ @@ -1668,6 +1675,9 @@ bpf_base_func_proto(enum bpf_func_id func_id) } #endif /* CONFIG_BPF_SYSCALL */ +void __bpf_free_used_btfs(struct bpf_prog_aux *aux, + struct btf_mod_pair *used_btfs, u32 len); + static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) { diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index e941fe1484e5..dfe6f85d97dd 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -340,6 +340,7 @@ struct bpf_insn_aux_data { }; #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ +#define MAX_USED_BTFS 64 /* max number of BTFs accessed by one BPF program */ #define BPF_VERIFIER_TMP_LOG_SIZE 1024 @@ -398,7 +399,9 @@ struct bpf_verifier_env { struct bpf_verifier_state_list **explored_states; /* search pruning optimization */ struct bpf_verifier_state_list *free_list; struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */ + struct btf_mod_pair used_btfs[MAX_USED_BTFS]; /* array of BTF's used by BPF program */ u32 used_map_cnt; /* number of used maps */ + u32 used_btf_cnt; /* number of used BTF objects */ u32 id_gen; /* used to generate unique reg IDs */ bool allow_ptr_leaks; bool allow_ptr_to_map_access; diff --git a/include/linux/btf.h b/include/linux/btf.h index 4c200f5d242b..7fabf1428093 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -91,6 +91,9 @@ int btf_type_snprintf_show(const struct btf *btf, u32 type_id, void *obj, int btf_get_fd_by_id(u32 id); u32 btf_obj_id(const struct btf *btf); bool btf_is_kernel(const struct btf *btf); +bool btf_is_module(const struct btf *btf); +struct module *btf_try_get_module(const struct btf *btf); +u32 btf_nr_types(const struct btf *btf); bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, const struct btf_member *m, u32 expected_offset, u32 expected_size); -- cgit v1.2.3 From c2ec5f2ecf6aeef60c63d1af9ddcacdcbf829d68 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Mon, 11 Jan 2021 11:46:57 +0100 Subject: net: dsa: add optional stats64 support Allow DSA drivers to export stats64 Signed-off-by: Oleksij Rempel Reviewed-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index c9a3dd7588df..c3485ba6c312 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -482,7 +482,7 @@ struct dsa_switch_ops { void (*phylink_fixed_state)(struct dsa_switch *ds, int port, struct phylink_link_state *state); /* - * ethtool hardware statistics. + * Port statistics counters. */ void (*get_strings)(struct dsa_switch *ds, int port, u32 stringset, uint8_t *data); @@ -491,6 +491,8 @@ struct dsa_switch_ops { int (*get_sset_count)(struct dsa_switch *ds, int port, int sset); void (*get_ethtool_phy_stats)(struct dsa_switch *ds, int port, uint64_t *data); + void (*get_stats64)(struct dsa_switch *ds, int port, + struct rtnl_link_stats64 *s); /* * ethtool Wake-on-LAN -- cgit v1.2.3 From 5a9d5ecd69ed65fc2d49cdecfc1c1ab1e4d7af34 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 11 Jan 2021 15:19:18 +0100 Subject: can: dev: move bittiming related code into seperate file This patch moves the bittiming related code of the CAN device infrastructure into a separate file. Reviewed-by: Vincent Mailhol Link: https://lore.kernel.org/r/20210111141930.693847-4-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/linux/can/bittiming.h | 44 +++++++++++++++++++++++++++++++++++++++++++ include/linux/can/dev.h | 16 +--------------- 2 files changed, 45 insertions(+), 15 deletions(-) create mode 100644 include/linux/can/bittiming.h (limited to 'include') diff --git a/include/linux/can/bittiming.h b/include/linux/can/bittiming.h new file mode 100644 index 000000000000..707575c668f4 --- /dev/null +++ b/include/linux/can/bittiming.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2020 Pengutronix, Marc Kleine-Budde + */ + +#ifndef _CAN_BITTIMING_H +#define _CAN_BITTIMING_H + +#include +#include + +#define CAN_SYNC_SEG 1 + +#ifdef CONFIG_CAN_CALC_BITTIMING +int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt, + const struct can_bittiming_const *btc); +#else /* !CONFIG_CAN_CALC_BITTIMING */ +static inline int +can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt, + const struct can_bittiming_const *btc) +{ + netdev_err(dev, "bit-timing calculation not available\n"); + return -EINVAL; +} +#endif /* CONFIG_CAN_CALC_BITTIMING */ + +int can_get_bittiming(struct net_device *dev, struct can_bittiming *bt, + const struct can_bittiming_const *btc, + const u32 *bitrate_const, + const unsigned int bitrate_const_cnt); + +/* + * can_bit_time() - Duration of one bit + * + * Please refer to ISO 11898-1:2015, section 11.3.1.1 "Bit time" for + * additional information. + * + * Return: the number of time quanta in one bit. + */ +static inline unsigned int can_bit_time(const struct can_bittiming *bt) +{ + return CAN_SYNC_SEG + bt->prop_seg + bt->phase_seg1 + bt->phase_seg2; +} + +#endif /* !_CAN_BITTIMING_H */ diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 197a79535cc2..054c3bed190b 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -15,6 +15,7 @@ #define _CAN_DEV_H #include +#include #include #include #include @@ -82,21 +83,6 @@ struct can_priv { #endif }; -#define CAN_SYNC_SEG 1 - -/* - * can_bit_time() - Duration of one bit - * - * Please refer to ISO 11898-1:2015, section 11.3.1.1 "Bit time" for - * additional information. - * - * Return: the number of time quanta in one bit. - */ -static inline unsigned int can_bit_time(const struct can_bittiming *bt) -{ - return CAN_SYNC_SEG + bt->prop_seg + bt->phase_seg1 + bt->phase_seg2; -} - /* * can_cc_dlc2len(value) - convert a given data length code (dlc) of a * Classical CAN frame into a valid data length of max. 8 bytes. -- cgit v1.2.3 From bdd2e413192dd5f2153d166cd907b048cce872e8 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 11 Jan 2021 15:19:19 +0100 Subject: can: dev: move length related code into seperate file This patch moves all CAN frame length related code of the CAN device infrastructure into a separate file. Reviewed-by: Vincent Mailhol Link: https://lore.kernel.org/r/20210111141930.693847-5-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 41 +-------------------------------------- include/linux/can/length.h | 48 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 49 insertions(+), 40 deletions(-) create mode 100644 include/linux/can/length.h (limited to 'include') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 054c3bed190b..d75fba1d030a 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -83,15 +84,6 @@ struct can_priv { #endif }; -/* - * can_cc_dlc2len(value) - convert a given data length code (dlc) of a - * Classical CAN frame into a valid data length of max. 8 bytes. - * - * To be used in the CAN netdriver receive path to ensure conformance with - * ISO 11898-1 Chapter 8.4.2.3 (DLC field) - */ -#define can_cc_dlc2len(dlc) (min_t(u8, (dlc), CAN_MAX_DLEN)) - /* Check for outgoing skbs that have not been created by the CAN subsystem */ static inline bool can_skb_headroom_valid(struct net_device *dev, struct sk_buff *skb) @@ -156,31 +148,6 @@ static inline bool can_is_canfd_skb(const struct sk_buff *skb) return skb->len == CANFD_MTU; } -/* helper to get the data length code (DLC) for Classical CAN raw DLC access */ -static inline u8 can_get_cc_dlc(const struct can_frame *cf, const u32 ctrlmode) -{ - /* return len8_dlc as dlc value only if all conditions apply */ - if ((ctrlmode & CAN_CTRLMODE_CC_LEN8_DLC) && - (cf->len == CAN_MAX_DLEN) && - (cf->len8_dlc > CAN_MAX_DLEN && cf->len8_dlc <= CAN_MAX_RAW_DLC)) - return cf->len8_dlc; - - /* return the payload length as dlc value */ - return cf->len; -} - -/* helper to set len and len8_dlc value for Classical CAN raw DLC access */ -static inline void can_frame_set_cc_len(struct can_frame *cf, const u8 dlc, - const u32 ctrlmode) -{ - /* the caller already ensured that dlc is a value from 0 .. 15 */ - if (ctrlmode & CAN_CTRLMODE_CC_LEN8_DLC && dlc > CAN_MAX_DLEN) - cf->len8_dlc = dlc; - - /* limit the payload length 'len' to CAN_MAX_DLEN */ - cf->len = can_cc_dlc2len(dlc); -} - /* helper to define static CAN controller features at device creation time */ static inline void can_set_static_ctrlmode(struct net_device *dev, u32 static_mode) @@ -196,12 +163,6 @@ static inline void can_set_static_ctrlmode(struct net_device *dev, dev->mtu = CANFD_MTU; } -/* get data length from raw data length code (DLC) */ -u8 can_fd_dlc2len(u8 dlc); - -/* map the sanitized data length to an appropriate data length code */ -u8 can_fd_len2dlc(u8 len); - struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, unsigned int txqs, unsigned int rxqs); #define alloc_candev(sizeof_priv, echo_skb_max) \ diff --git a/include/linux/can/length.h b/include/linux/can/length.h new file mode 100644 index 000000000000..156b9d17969a --- /dev/null +++ b/include/linux/can/length.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2020 Oliver Hartkopp + */ + +#ifndef _CAN_LENGTH_H +#define _CAN_LENGTH_H + +/* + * can_cc_dlc2len(value) - convert a given data length code (dlc) of a + * Classical CAN frame into a valid data length of max. 8 bytes. + * + * To be used in the CAN netdriver receive path to ensure conformance with + * ISO 11898-1 Chapter 8.4.2.3 (DLC field) + */ +#define can_cc_dlc2len(dlc) (min_t(u8, (dlc), CAN_MAX_DLEN)) + +/* helper to get the data length code (DLC) for Classical CAN raw DLC access */ +static inline u8 can_get_cc_dlc(const struct can_frame *cf, const u32 ctrlmode) +{ + /* return len8_dlc as dlc value only if all conditions apply */ + if ((ctrlmode & CAN_CTRLMODE_CC_LEN8_DLC) && + (cf->len == CAN_MAX_DLEN) && + (cf->len8_dlc > CAN_MAX_DLEN && cf->len8_dlc <= CAN_MAX_RAW_DLC)) + return cf->len8_dlc; + + /* return the payload length as dlc value */ + return cf->len; +} + +/* helper to set len and len8_dlc value for Classical CAN raw DLC access */ +static inline void can_frame_set_cc_len(struct can_frame *cf, const u8 dlc, + const u32 ctrlmode) +{ + /* the caller already ensured that dlc is a value from 0 .. 15 */ + if (ctrlmode & CAN_CTRLMODE_CC_LEN8_DLC && dlc > CAN_MAX_DLEN) + cf->len8_dlc = dlc; + + /* limit the payload length 'len' to CAN_MAX_DLEN */ + cf->len = can_cc_dlc2len(dlc); +} + +/* get data length from raw data length code (DLC) */ +u8 can_fd_dlc2len(u8 dlc); + +/* map the sanitized data length to an appropriate data length code */ +u8 can_fd_len2dlc(u8 len); + +#endif /* !_CAN_LENGTH_H */ -- cgit v1.2.3 From 18f2dbfd2232212f53af9d249682f13a8335d54f Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 11 Jan 2021 15:19:20 +0100 Subject: can: dev: move skb related into seperate file This patch moves the skb related code of the CAN device infrastructure into a separate file. Reviewed-by: Vincent Mailhol Link: https://lore.kernel.org/r/20210111141930.693847-6-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 76 ------------------------------------------------ include/linux/can/skb.h | 77 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 77 insertions(+), 76 deletions(-) (limited to 'include') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index d75fba1d030a..4a26e128af7f 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -84,69 +84,6 @@ struct can_priv { #endif }; -/* Check for outgoing skbs that have not been created by the CAN subsystem */ -static inline bool can_skb_headroom_valid(struct net_device *dev, - struct sk_buff *skb) -{ - /* af_packet creates a headroom of HH_DATA_MOD bytes which is fine */ - if (WARN_ON_ONCE(skb_headroom(skb) < sizeof(struct can_skb_priv))) - return false; - - /* af_packet does not apply CAN skb specific settings */ - if (skb->ip_summed == CHECKSUM_NONE) { - /* init headroom */ - can_skb_prv(skb)->ifindex = dev->ifindex; - can_skb_prv(skb)->skbcnt = 0; - - skb->ip_summed = CHECKSUM_UNNECESSARY; - - /* perform proper loopback on capable devices */ - if (dev->flags & IFF_ECHO) - skb->pkt_type = PACKET_LOOPBACK; - else - skb->pkt_type = PACKET_HOST; - - skb_reset_mac_header(skb); - skb_reset_network_header(skb); - skb_reset_transport_header(skb); - } - - return true; -} - -/* Drop a given socketbuffer if it does not contain a valid CAN frame. */ -static inline bool can_dropped_invalid_skb(struct net_device *dev, - struct sk_buff *skb) -{ - const struct canfd_frame *cfd = (struct canfd_frame *)skb->data; - - if (skb->protocol == htons(ETH_P_CAN)) { - if (unlikely(skb->len != CAN_MTU || - cfd->len > CAN_MAX_DLEN)) - goto inval_skb; - } else if (skb->protocol == htons(ETH_P_CANFD)) { - if (unlikely(skb->len != CANFD_MTU || - cfd->len > CANFD_MAX_DLEN)) - goto inval_skb; - } else - goto inval_skb; - - if (!can_skb_headroom_valid(dev, skb)) - goto inval_skb; - - return false; - -inval_skb: - kfree_skb(skb); - dev->stats.tx_dropped++; - return true; -} - -static inline bool can_is_canfd_skb(const struct sk_buff *skb) -{ - /* the CAN specific type of skb is identified by its data length */ - return skb->len == CANFD_MTU; -} /* helper to define static CAN controller features at device creation time */ static inline void can_set_static_ctrlmode(struct net_device *dev, @@ -187,23 +124,10 @@ void can_bus_off(struct net_device *dev); void can_change_state(struct net_device *dev, struct can_frame *cf, enum can_state tx_state, enum can_state rx_state); -int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, - unsigned int idx); -struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, - u8 *len_ptr); -unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx); -void can_free_echo_skb(struct net_device *dev, unsigned int idx); - #ifdef CONFIG_OF void of_can_transceiver(struct net_device *dev); #else static inline void of_can_transceiver(struct net_device *dev) { } #endif -struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf); -struct sk_buff *alloc_canfd_skb(struct net_device *dev, - struct canfd_frame **cfd); -struct sk_buff *alloc_can_err_skb(struct net_device *dev, - struct can_frame **cf); - #endif /* !_CAN_DEV_H */ diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index fc61cf4eff1c..c90ebbd3008c 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -16,6 +16,19 @@ #include #include +void can_flush_echo_skb(struct net_device *dev); +int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, + unsigned int idx); +struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, + u8 *len_ptr); +unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx); +void can_free_echo_skb(struct net_device *dev, unsigned int idx); +struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf); +struct sk_buff *alloc_canfd_skb(struct net_device *dev, + struct canfd_frame **cfd); +struct sk_buff *alloc_can_err_skb(struct net_device *dev, + struct can_frame **cf); + /* * The struct can_skb_priv is used to transport additional information along * with the stored struct can(fd)_frame that can not be contained in existing @@ -74,4 +87,68 @@ static inline struct sk_buff *can_create_echo_skb(struct sk_buff *skb) return nskb; } +/* Check for outgoing skbs that have not been created by the CAN subsystem */ +static inline bool can_skb_headroom_valid(struct net_device *dev, + struct sk_buff *skb) +{ + /* af_packet creates a headroom of HH_DATA_MOD bytes which is fine */ + if (WARN_ON_ONCE(skb_headroom(skb) < sizeof(struct can_skb_priv))) + return false; + + /* af_packet does not apply CAN skb specific settings */ + if (skb->ip_summed == CHECKSUM_NONE) { + /* init headroom */ + can_skb_prv(skb)->ifindex = dev->ifindex; + can_skb_prv(skb)->skbcnt = 0; + + skb->ip_summed = CHECKSUM_UNNECESSARY; + + /* perform proper loopback on capable devices */ + if (dev->flags & IFF_ECHO) + skb->pkt_type = PACKET_LOOPBACK; + else + skb->pkt_type = PACKET_HOST; + + skb_reset_mac_header(skb); + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + } + + return true; +} + +/* Drop a given socketbuffer if it does not contain a valid CAN frame. */ +static inline bool can_dropped_invalid_skb(struct net_device *dev, + struct sk_buff *skb) +{ + const struct canfd_frame *cfd = (struct canfd_frame *)skb->data; + + if (skb->protocol == htons(ETH_P_CAN)) { + if (unlikely(skb->len != CAN_MTU || + cfd->len > CAN_MAX_DLEN)) + goto inval_skb; + } else if (skb->protocol == htons(ETH_P_CANFD)) { + if (unlikely(skb->len != CANFD_MTU || + cfd->len > CANFD_MAX_DLEN)) + goto inval_skb; + } else + goto inval_skb; + + if (!can_skb_headroom_valid(dev, skb)) + goto inval_skb; + + return false; + +inval_skb: + kfree_skb(skb); + dev->stats.tx_dropped++; + return true; +} + +static inline bool can_is_canfd_skb(const struct sk_buff *skb) +{ + /* the CAN specific type of skb is identified by its data length */ + return skb->len == CANFD_MTU; +} + #endif /* !_CAN_SKB_H */ -- cgit v1.2.3 From 0a042c6ec991e4d33062ee52e9e23f615bc659f9 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 11 Jan 2021 15:19:21 +0100 Subject: can: dev: move netlink related code into seperate file This patch moves the netlink related code of the CAN device infrastructure into a separate file. Reviewed-by: Vincent Mailhol Link: https://lore.kernel.org/r/20210111141930.693847-7-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 4a26e128af7f..7faf6a37d5b2 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -100,6 +100,8 @@ static inline void can_set_static_ctrlmode(struct net_device *dev, dev->mtu = CANFD_MTU; } +void can_setup(struct net_device *dev); + struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, unsigned int txqs, unsigned int rxqs); #define alloc_candev(sizeof_priv, echo_skb_max) \ @@ -130,4 +132,8 @@ void of_can_transceiver(struct net_device *dev); static inline void of_can_transceiver(struct net_device *dev) { } #endif +extern struct rtnl_link_ops can_link_ops; +int can_netlink_register(void); +void can_netlink_unregister(void); + #endif /* !_CAN_DEV_H */ -- cgit v1.2.3 From 838b00a2260ab6ec104a2a5696e619c19e8cd9be Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Mon, 11 Jan 2021 23:05:24 -0800 Subject: net/mlx5: Add HW definition of reg_c_preserve Add capability bit to test whether reg_c value is preserved on recirculation. Signed-off-by: Paul Blakey Signed-off-by: Maor Dickman Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- include/linux/mlx5/mlx5_ifc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 442c0160caab..823411e288c0 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1278,7 +1278,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_a0[0x3]; u8 ece_support[0x1]; - u8 reserved_at_a4[0x7]; + u8 reserved_at_a4[0x5]; + u8 reg_c_preserve[0x1]; + u8 reserved_at_aa[0x1]; u8 log_max_srq[0x5]; u8 reserved_at_b0[0x1]; u8 uplink_follow[0x1]; -- cgit v1.2.3 From 99b7beb0431a4b9728023e9169ed15af678d2c7f Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 11 Jan 2021 15:19:24 +0100 Subject: can: length: canfd_sanitize_len(): add function to sanitize CAN-FD data length The data field in CAN-FD frames have specifig frame length (0, 1, 2, 3, 4, 5, 6, 7, 8, 12, 16, 20, 24, 32, 48, 64). This function "rounds" up a given length to the next valid CAN-FD frame length. Reviewed-by: Vincent Mailhol Link: https://lore.kernel.org/r/20210111141930.693847-10-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/linux/can/length.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/can/length.h b/include/linux/can/length.h index 156b9d17969a..b2313b2a0b02 100644 --- a/include/linux/can/length.h +++ b/include/linux/can/length.h @@ -45,4 +45,10 @@ u8 can_fd_dlc2len(u8 dlc); /* map the sanitized data length to an appropriate data length code */ u8 can_fd_len2dlc(u8 len); +/* map the data length to an appropriate data link layer length */ +static inline u8 canfd_sanitize_len(u8 len) +{ + return can_fd_dlc2len(can_fd_len2dlc(len)); +} + #endif /* !_CAN_LENGTH_H */ -- cgit v1.2.3 From 85d99c3e2a13d542445342a1383a686dadeaac3d Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Mon, 11 Jan 2021 15:19:25 +0100 Subject: can: length: can_skb_get_frame_len(): introduce function to get data length of frame in data link layer This patch adds the function can_skb_get_frame_len() which returns the length of a CAN frame on the data link layer, including Start-of-frame, Identifier, various other bits, the actual data, the CRC, the End-of-frame, the Inter frame spacing. Co-developed-by: Arunachalam Santhanam Signed-off-by: Arunachalam Santhanam Co-developed-by: Vincent Mailhol Signed-off-by: Vincent Mailhol Acked-by: Vincent Mailhol Reviewed-by: Vincent Mailhol Co-developed-by: Marc Kleine-Budde Link: https://lore.kernel.org/r/20210111141930.693847-11-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/linux/can/length.h | 120 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 120 insertions(+) (limited to 'include') diff --git a/include/linux/can/length.h b/include/linux/can/length.h index b2313b2a0b02..6995092b774e 100644 --- a/include/linux/can/length.h +++ b/include/linux/can/length.h @@ -1,10 +1,127 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (C) 2020 Oliver Hartkopp + * Copyright (C) 2020 Marc Kleine-Budde */ #ifndef _CAN_LENGTH_H #define _CAN_LENGTH_H +/* + * Size of a Classical CAN Standard Frame + * + * Name of Field Bits + * --------------------------------------------------------- + * Start-of-frame 1 + * Identifier 11 + * Remote transmission request (RTR) 1 + * Identifier extension bit (IDE) 1 + * Reserved bit (r0) 1 + * Data length code (DLC) 4 + * Data field 0...64 + * CRC 15 + * CRC delimiter 1 + * ACK slot 1 + * ACK delimiter 1 + * End-of-frame (EOF) 7 + * Inter frame spacing 3 + * + * rounded up and ignoring bitstuffing + */ +#define CAN_FRAME_OVERHEAD_SFF DIV_ROUND_UP(47, 8) + +/* + * Size of a Classical CAN Extended Frame + * + * Name of Field Bits + * --------------------------------------------------------- + * Start-of-frame 1 + * Identifier A 11 + * Substitute remote request (SRR) 1 + * Identifier extension bit (IDE) 1 + * Identifier B 18 + * Remote transmission request (RTR) 1 + * Reserved bits (r1, r0) 2 + * Data length code (DLC) 4 + * Data field 0...64 + * CRC 15 + * CRC delimiter 1 + * ACK slot 1 + * ACK delimiter 1 + * End-of-frame (EOF) 7 + * Inter frame spacing 3 + * + * rounded up and ignoring bitstuffing + */ +#define CAN_FRAME_OVERHEAD_EFF DIV_ROUND_UP(67, 8) + +/* + * Size of a CAN-FD Standard Frame + * + * Name of Field Bits + * --------------------------------------------------------- + * Start-of-frame 1 + * Identifier 11 + * Reserved bit (r1) 1 + * Identifier extension bit (IDE) 1 + * Flexible data rate format (FDF) 1 + * Reserved bit (r0) 1 + * Bit Rate Switch (BRS) 1 + * Error Status Indicator (ESI) 1 + * Data length code (DLC) 4 + * Data field 0...512 + * Stuff Bit Count (SBC) 0...16: 4 20...64:5 + * CRC 0...16: 17 20...64:21 + * CRC delimiter (CD) 1 + * ACK slot (AS) 1 + * ACK delimiter (AD) 1 + * End-of-frame (EOF) 7 + * Inter frame spacing 3 + * + * assuming CRC21, rounded up and ignoring bitstuffing + */ +#define CANFD_FRAME_OVERHEAD_SFF DIV_ROUND_UP(61, 8) + +/* + * Size of a CAN-FD Extended Frame + * + * Name of Field Bits + * --------------------------------------------------------- + * Start-of-frame 1 + * Identifier A 11 + * Substitute remote request (SRR) 1 + * Identifier extension bit (IDE) 1 + * Identifier B 18 + * Reserved bit (r1) 1 + * Flexible data rate format (FDF) 1 + * Reserved bit (r0) 1 + * Bit Rate Switch (BRS) 1 + * Error Status Indicator (ESI) 1 + * Data length code (DLC) 4 + * Data field 0...512 + * Stuff Bit Count (SBC) 0...16: 4 20...64:5 + * CRC 0...16: 17 20...64:21 + * CRC delimiter (CD) 1 + * ACK slot (AS) 1 + * ACK delimiter (AD) 1 + * End-of-frame (EOF) 7 + * Inter frame spacing 3 + * + * assuming CRC21, rounded up and ignoring bitstuffing + */ +#define CANFD_FRAME_OVERHEAD_EFF DIV_ROUND_UP(80, 8) + +/* + * Maximum size of a Classical CAN frame + * (rounded up and ignoring bitstuffing) + */ +#define CAN_FRAME_LEN_MAX (CAN_FRAME_OVERHEAD_EFF + CAN_MAX_DLEN) + +/* + * Maximum size of a CAN-FD frame + * (rounded up and ignoring bitstuffing) + */ +#define CANFD_FRAME_LEN_MAX (CANFD_FRAME_OVERHEAD_EFF + CANFD_MAX_DLEN) + /* * can_cc_dlc2len(value) - convert a given data length code (dlc) of a * Classical CAN frame into a valid data length of max. 8 bytes. @@ -45,6 +162,9 @@ u8 can_fd_dlc2len(u8 dlc); /* map the sanitized data length to an appropriate data length code */ u8 can_fd_len2dlc(u8 len); +/* calculate the CAN Frame length in bytes of a given skb */ +unsigned int can_skb_get_frame_len(const struct sk_buff *skb); + /* map the data length to an appropriate data link layer length */ static inline u8 canfd_sanitize_len(u8 len) { -- cgit v1.2.3 From f0ef72febc9a6a569d92cdf6c7996015dfa8e8bb Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 11 Jan 2021 15:19:26 +0100 Subject: can: dev: extend struct can_skb_priv to hold CAN frame length In order to implement byte queue limits (bql) in CAN drivers, the length of the CAN frame needs to be passed into the networking stack after queueing and after transmission completion. To avoid to calculate this length twice, extend the struct can_skb_priv to hold the length of the CAN frame and extend __can_get_echo_skb() to return that value. Reviewed-by: Vincent Mailhol Link: https://lore.kernel.org/r/20210111141930.693847-12-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/linux/can/skb.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index c90ebbd3008c..5db9da30843c 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -20,7 +20,7 @@ void can_flush_echo_skb(struct net_device *dev); int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, unsigned int idx); struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, - u8 *len_ptr); + u8 *len_ptr, unsigned int *frame_len_ptr); unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx); void can_free_echo_skb(struct net_device *dev, unsigned int idx); struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf); @@ -42,11 +42,13 @@ struct sk_buff *alloc_can_err_skb(struct net_device *dev, * struct can_skb_priv - private additional data inside CAN sk_buffs * @ifindex: ifindex of the first interface the CAN frame appeared on * @skbcnt: atomic counter to have an unique id together with skb pointer + * @frame_len: length of CAN frame in data link layer * @cf: align to the following CAN frame at skb->data */ struct can_skb_priv { int ifindex; int skbcnt; + unsigned int frame_len; struct can_frame cf[]; }; -- cgit v1.2.3 From 1dcb6e57db833419483d0df2d956b1cc2a802683 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Mon, 11 Jan 2021 15:19:27 +0100 Subject: can: dev: can_put_echo_skb(): extend to handle frame_len Add a frame_len argument to can_put_echo_skb() which is used to save length of the CAN frame into field frame_len of struct can_skb_priv so that it can be later used after transmission completion. Convert all users of this function, too. Drivers which implement BQL call can_put_echo_skb() with the output of can_skb_get_frame_len(skb) and drivers which do not simply pass zero as an input (in the same way that NULL would be given to can_get_echo_skb()). This way, we have a nice symmetry between the two echo functions. Link: https://lore.kernel.org/r/20210111061335.39983-1-mailhol.vincent@wanadoo.fr Signed-off-by: Marc Kleine-Budde Reviewed-by: Vincent Mailhol Link: https://lore.kernel.org/r/20210111141930.693847-13-mkl@pengutronix.de Signed-off-by: Vincent Mailhol --- include/linux/can/skb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index 5db9da30843c..eaac4a637ae0 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -18,7 +18,7 @@ void can_flush_echo_skb(struct net_device *dev); int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, - unsigned int idx); + unsigned int idx, unsigned int frame_len); struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, u8 *len_ptr, unsigned int *frame_len_ptr); unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx); -- cgit v1.2.3 From 9420e1d495e2a3b5f673148b7e3ebc861b1441f7 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 11 Jan 2021 15:19:28 +0100 Subject: can: dev: can_get_echo_skb(): extend to return can frame length In order to implement byte queue limits (bql) in CAN drivers, the length of the CAN frame needs to be passed into the networking stack after queueing and after transmission completion. To avoid to calculate this length twice, extend can_get_echo_skb() to return that value. Convert all users of this function, too. Reviewed-by: Vincent Mailhol Link: https://lore.kernel.org/r/20210111141930.693847-14-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/linux/can/skb.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index eaac4a637ae0..685f34cfba20 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -21,7 +21,8 @@ int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, unsigned int idx, unsigned int frame_len); struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, u8 *len_ptr, unsigned int *frame_len_ptr); -unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx); +unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx, + unsigned int *frame_len_ptr); void can_free_echo_skb(struct net_device *dev, unsigned int idx); struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf); struct sk_buff *alloc_canfd_skb(struct net_device *dev, -- cgit v1.2.3 From 99842c9685ab00fa8689e8bd12bde62b706b6198 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 11 Jan 2021 15:19:29 +0100 Subject: can: dev: can_rx_offload_get_echo_skb(): extend to return can frame length In order to implement byte queue limits (bql) in CAN drivers, the length of the CAN frame needs to be passed into the networking stack after queueing and after transmission completion. To avoid to calculate this length twice, extend can_rx_offload_get_echo_skb() to return that value. Convert all users of this function, too. Reviewed-by: Vincent Mailhol Link: https://lore.kernel.org/r/20210111141930.693847-15-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/linux/can/rx-offload.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h index f1b38088b765..40882df7105e 100644 --- a/include/linux/can/rx-offload.h +++ b/include/linux/can/rx-offload.h @@ -44,7 +44,8 @@ int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload); int can_rx_offload_queue_sorted(struct can_rx_offload *offload, struct sk_buff *skb, u32 timestamp); unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload, - unsigned int idx, u32 timestamp); + unsigned int idx, u32 timestamp, + unsigned int *frame_len_ptr); int can_rx_offload_queue_tail(struct can_rx_offload *offload, struct sk_buff *skb); void can_rx_offload_del(struct can_rx_offload *offload); -- cgit v1.2.3 From b1ae3587d16a8c8fc9453e147c8708d6f006ffbb Mon Sep 17 00:00:00 2001 From: Bjarni Jonasson Date: Wed, 13 Jan 2021 12:56:25 +0100 Subject: net: phy: Add 100 base-x mode Sparx-5 supports this mode and it is missing in the PHY core. Signed-off-by: Bjarni Jonasson Reviewed-by: Russell King Signed-off-by: Jakub Kicinski --- include/linux/phy.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index 9effb511acde..24fcc6456a9e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -104,6 +104,7 @@ extern const int phy_10gbit_features_array[1]; * @PHY_INTERFACE_MODE_MOCA: Multimedia over Coax * @PHY_INTERFACE_MODE_QSGMII: Quad SGMII * @PHY_INTERFACE_MODE_TRGMII: Turbo RGMII + * @PHY_INTERFACE_MODE_100BASEX: 100 BaseX * @PHY_INTERFACE_MODE_1000BASEX: 1000 BaseX * @PHY_INTERFACE_MODE_2500BASEX: 2500 BaseX * @PHY_INTERFACE_MODE_RXAUI: Reduced XAUI @@ -135,6 +136,7 @@ typedef enum { PHY_INTERFACE_MODE_MOCA, PHY_INTERFACE_MODE_QSGMII, PHY_INTERFACE_MODE_TRGMII, + PHY_INTERFACE_MODE_100BASEX, PHY_INTERFACE_MODE_1000BASEX, PHY_INTERFACE_MODE_2500BASEX, PHY_INTERFACE_MODE_RXAUI, @@ -217,6 +219,8 @@ static inline const char *phy_modes(phy_interface_t interface) return "usxgmii"; case PHY_INTERFACE_MODE_10GKR: return "10gbase-kr"; + case PHY_INTERFACE_MODE_100BASEX: + return "100base-x"; default: return "unknown"; } -- cgit v1.2.3 From 058102a6e9eb1905a7da41b7a5a7a1f278a3828a Mon Sep 17 00:00:00 2001 From: Tobias Waldekranz Date: Wed, 13 Jan 2021 09:42:53 +0100 Subject: net: dsa: Link aggregation support Monitor the following events and notify the driver when: - A DSA port joins/leaves a LAG. - A LAG, made up of DSA ports, joins/leaves a bridge. - A DSA port in a LAG is enabled/disabled (enabled meaning "distributing" in 802.3ad LACP terms). When a LAG joins a bridge, the DSA subsystem will treat that as each individual port joining the bridge. The driver may look at the port's LAG device pointer to see if it is associated with any LAG, if that is required. This is analogue to how switchdev events are replicated out to all lower devices when reaching e.g. a LAG. Drivers can optionally request that DSA maintain a linear mapping from a LAG ID to the corresponding netdev by setting ds->num_lag_ids to the desired size. In the event that the hardware is not capable of offloading a particular LAG for any reason (the typical case being use of exotic modes like broadcast), DSA will take a hands-off approach, allowing the LAG to be formed as a pure software construct. This is reported back through the extended ACK, but is otherwise transparent to the user. Signed-off-by: Tobias Waldekranz Reviewed-by: Vladimir Oltean Tested-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 60 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 60 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index c3485ba6c312..06e3784ec55c 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -149,8 +149,41 @@ struct dsa_switch_tree { /* List of DSA links composing the routing table */ struct list_head rtable; + + /* Maps offloaded LAG netdevs to a zero-based linear ID for + * drivers that need it. + */ + struct net_device **lags; + unsigned int lags_len; }; +#define dsa_lags_foreach_id(_id, _dst) \ + for ((_id) = 0; (_id) < (_dst)->lags_len; (_id)++) \ + if ((_dst)->lags[(_id)]) + +#define dsa_lag_foreach_port(_dp, _dst, _lag) \ + list_for_each_entry((_dp), &(_dst)->ports, list) \ + if ((_dp)->lag_dev == (_lag)) + +static inline struct net_device *dsa_lag_dev(struct dsa_switch_tree *dst, + unsigned int id) +{ + return dst->lags[id]; +} + +static inline int dsa_lag_id(struct dsa_switch_tree *dst, + struct net_device *lag) +{ + unsigned int id; + + dsa_lags_foreach_id(id, dst) { + if (dsa_lag_dev(dst, id) == lag) + return id; + } + + return -ENODEV; +} + /* TC matchall action types */ enum dsa_port_mall_action_type { DSA_PORT_MALL_MIRROR, @@ -220,6 +253,8 @@ struct dsa_port { bool devlink_port_setup; struct phylink *pl; struct phylink_config pl_config; + struct net_device *lag_dev; + bool lag_tx_enabled; struct list_head list; @@ -340,6 +375,14 @@ struct dsa_switch { */ bool mtu_enforcement_ingress; + /* Drivers that benefit from having an ID associated with each + * offloaded LAG should set this to the maximum number of + * supported IDs. DSA will then maintain a mapping of _at + * least_ these many IDs, accessible to drivers via + * dsa_lag_id(). + */ + unsigned int num_lag_ids; + size_t num_ports; }; @@ -626,6 +669,13 @@ struct dsa_switch_ops { void (*crosschip_bridge_leave)(struct dsa_switch *ds, int tree_index, int sw_index, int port, struct net_device *br); + int (*crosschip_lag_change)(struct dsa_switch *ds, int sw_index, + int port); + int (*crosschip_lag_join)(struct dsa_switch *ds, int sw_index, + int port, struct net_device *lag, + struct netdev_lag_upper_info *info); + int (*crosschip_lag_leave)(struct dsa_switch *ds, int sw_index, + int port, struct net_device *lag); /* * PTP functionality @@ -657,6 +707,16 @@ struct dsa_switch_ops { int (*port_change_mtu)(struct dsa_switch *ds, int port, int new_mtu); int (*port_max_mtu)(struct dsa_switch *ds, int port); + + /* + * LAG integration + */ + int (*port_lag_change)(struct dsa_switch *ds, int port); + int (*port_lag_join)(struct dsa_switch *ds, int port, + struct net_device *lag, + struct netdev_lag_upper_info *info); + int (*port_lag_leave)(struct dsa_switch *ds, int port, + struct net_device *lag); }; #define DSA_DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes) \ -- cgit v1.2.3 From 91c960b0056672e74627776655c926388350fa30 Mon Sep 17 00:00:00 2001 From: Brendan Jackman Date: Thu, 14 Jan 2021 18:17:44 +0000 Subject: bpf: Rename BPF_XADD and prepare to encode other atomics in .imm MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A subsequent patch will add additional atomic operations. These new operations will use the same opcode field as the existing XADD, with the immediate discriminating different operations. In preparation, rename the instruction mode BPF_ATOMIC and start calling the zero immediate BPF_ADD. This is possible (doesn't break existing valid BPF progs) because the immediate field is currently reserved MBZ and BPF_ADD is zero. All uses are removed from the tree but the BPF_XADD definition is kept around to avoid breaking builds for people including kernel headers. Signed-off-by: Brendan Jackman Signed-off-by: Alexei Starovoitov Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/20210114181751.768687-5-jackmanb@google.com --- include/linux/filter.h | 16 ++++++++++++---- include/uapi/linux/bpf.h | 5 +++-- 2 files changed, 15 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 5edf2b660881..392e94b79668 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -259,15 +259,23 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) .off = OFF, \ .imm = 0 }) -/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */ -#define BPF_STX_XADD(SIZE, DST, SRC, OFF) \ +/* + * Atomic operations: + * + * BPF_ADD *(uint *) (dst_reg + off16) += src_reg + */ + +#define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ - .code = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD, \ + .code = BPF_STX | BPF_SIZE(SIZE) | BPF_ATOMIC, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ - .imm = 0 }) + .imm = OP }) + +/* Legacy alias */ +#define BPF_STX_XADD(SIZE, DST, SRC, OFF) BPF_ATOMIC_OP(SIZE, BPF_ADD, DST, SRC, OFF) /* Memory store, *(uint *) (dst_reg + off16) = imm32 */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a1ad32456f89..6b3996343e63 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -19,7 +19,8 @@ /* ld/ldx fields */ #define BPF_DW 0x18 /* double word (64-bit) */ -#define BPF_XADD 0xc0 /* exclusive add */ +#define BPF_ATOMIC 0xc0 /* atomic memory ops - op type in immediate */ +#define BPF_XADD 0xc0 /* exclusive add - legacy name */ /* alu/jmp fields */ #define BPF_MOV 0xb0 /* mov reg to reg */ @@ -2448,7 +2449,7 @@ union bpf_attr { * running simultaneously. * * A user should care about the synchronization by himself. - * For example, by using the **BPF_STX_XADD** instruction to alter + * For example, by using the **BPF_ATOMIC** instructions to alter * the shared data. * Return * A pointer to the local storage area. -- cgit v1.2.3 From 5ca419f2864a2c60940dcf4bbaeb69546200e36f Mon Sep 17 00:00:00 2001 From: Brendan Jackman Date: Thu, 14 Jan 2021 18:17:46 +0000 Subject: bpf: Add BPF_FETCH field / create atomic_fetch_add instruction The BPF_FETCH field can be set in bpf_insn.imm, for BPF_ATOMIC instructions, in order to have the previous value of the atomically-modified memory location loaded into the src register after an atomic op is carried out. Suggested-by: Yonghong Song Signed-off-by: Brendan Jackman Signed-off-by: Alexei Starovoitov Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20210114181751.768687-7-jackmanb@google.com --- include/linux/filter.h | 1 + include/uapi/linux/bpf.h | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 392e94b79668..23fca41b8540 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -264,6 +264,7 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) * Atomic operations: * * BPF_ADD *(uint *) (dst_reg + off16) += src_reg + * BPF_ADD | BPF_FETCH src_reg = atomic_fetch_add(dst_reg + off16, src_reg); */ #define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF) \ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6b3996343e63..ea262b009049 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -44,6 +44,9 @@ #define BPF_CALL 0x80 /* function call */ #define BPF_EXIT 0x90 /* function return */ +/* atomic op type fields (stored in immediate) */ +#define BPF_FETCH 0x01 /* fetch previous value into src reg */ + /* Register numbers */ enum { BPF_REG_0 = 0, -- cgit v1.2.3 From 5ffa25502b5ab3d639829a2d1e316cff7f59a41e Mon Sep 17 00:00:00 2001 From: Brendan Jackman Date: Thu, 14 Jan 2021 18:17:47 +0000 Subject: bpf: Add instructions for atomic_[cmp]xchg This adds two atomic opcodes, both of which include the BPF_FETCH flag. XCHG without the BPF_FETCH flag would naturally encode atomic_set. This is not supported because it would be of limited value to userspace (it doesn't imply any barriers). CMPXCHG without BPF_FETCH woulud be an atomic compare-and-write. We don't have such an operation in the kernel so it isn't provided to BPF either. There are two significant design decisions made for the CMPXCHG instruction: - To solve the issue that this operation fundamentally has 3 operands, but we only have two register fields. Therefore the operand we compare against (the kernel's API calls it 'old') is hard-coded to be R0. x86 has similar design (and A64 doesn't have this problem). A potential alternative might be to encode the other operand's register number in the immediate field. - The kernel's atomic_cmpxchg returns the old value, while the C11 userspace APIs return a boolean indicating the comparison result. Which should BPF do? A64 returns the old value. x86 returns the old value in the hard-coded register (and also sets a flag). That means return-old-value is easier to JIT, so that's what we use. Signed-off-by: Brendan Jackman Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210114181751.768687-8-jackmanb@google.com --- include/linux/filter.h | 2 ++ include/uapi/linux/bpf.h | 4 +++- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 23fca41b8540..d563820f197d 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -265,6 +265,8 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) * * BPF_ADD *(uint *) (dst_reg + off16) += src_reg * BPF_ADD | BPF_FETCH src_reg = atomic_fetch_add(dst_reg + off16, src_reg); + * BPF_XCHG src_reg = atomic_xchg(dst_reg + off16, src_reg) + * BPF_CMPXCHG r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg) */ #define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF) \ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index ea262b009049..c001766adcbc 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -45,7 +45,9 @@ #define BPF_EXIT 0x90 /* function return */ /* atomic op type fields (stored in immediate) */ -#define BPF_FETCH 0x01 /* fetch previous value into src reg */ +#define BPF_FETCH 0x01 /* not an opcode on its own, used to build others */ +#define BPF_XCHG (0xe0 | BPF_FETCH) /* atomic exchange */ +#define BPF_CMPXCHG (0xf0 | BPF_FETCH) /* atomic compare-and-write */ /* Register numbers */ enum { -- cgit v1.2.3 From 981f94c3e92146705baf97fb417a5ed1ab1a79a5 Mon Sep 17 00:00:00 2001 From: Brendan Jackman Date: Thu, 14 Jan 2021 18:17:49 +0000 Subject: bpf: Add bitwise atomic instructions This adds instructions for atomic[64]_[fetch_]and atomic[64]_[fetch_]or atomic[64]_[fetch_]xor All these operations are isomorphic enough to implement with the same verifier, interpreter, and x86 JIT code, hence being a single commit. The main interesting thing here is that x86 doesn't directly support the fetch_ version these operations, so we need to generate a CMPXCHG loop in the JIT. This requires the use of two temporary registers, IIUC it's safe to use BPF_REG_AX and x86's AUX_REG for this purpose. Signed-off-by: Brendan Jackman Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210114181751.768687-10-jackmanb@google.com --- include/linux/filter.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index d563820f197d..7fdce5407214 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -264,7 +264,13 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) * Atomic operations: * * BPF_ADD *(uint *) (dst_reg + off16) += src_reg + * BPF_AND *(uint *) (dst_reg + off16) &= src_reg + * BPF_OR *(uint *) (dst_reg + off16) |= src_reg + * BPF_XOR *(uint *) (dst_reg + off16) ^= src_reg * BPF_ADD | BPF_FETCH src_reg = atomic_fetch_add(dst_reg + off16, src_reg); + * BPF_AND | BPF_FETCH src_reg = atomic_fetch_and(dst_reg + off16, src_reg); + * BPF_OR | BPF_FETCH src_reg = atomic_fetch_or(dst_reg + off16, src_reg); + * BPF_XOR | BPF_FETCH src_reg = atomic_fetch_xor(dst_reg + off16, src_reg); * BPF_XCHG src_reg = atomic_xchg(dst_reg + off16, src_reg) * BPF_CMPXCHG r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg) */ -- cgit v1.2.3 From bd7525dacd7e204f8cae061941fb9001c89d6988 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 14 Jan 2021 14:40:42 +0100 Subject: bpf: Move stack_map_get_build_id into lib Moving stack_map_get_build_id into lib with declaration in linux/buildid.h header: int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id); This function returns build id for given struct vm_area_struct. There is no functional change to stack_map_get_build_id function. Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20210114134044.1418404-2-jolsa@kernel.org --- include/linux/buildid.h | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100644 include/linux/buildid.h (limited to 'include') diff --git a/include/linux/buildid.h b/include/linux/buildid.h new file mode 100644 index 000000000000..08028a212589 --- /dev/null +++ b/include/linux/buildid.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_BUILDID_H +#define _LINUX_BUILDID_H + +#include + +#define BUILD_ID_SIZE_MAX 20 + +int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id); + +#endif -- cgit v1.2.3 From 921f88fc891922b325b3668cd026a386571ed602 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 14 Jan 2021 14:40:43 +0100 Subject: bpf: Add size arg to build_id_parse function It's possible to have other build id types (other than default SHA1). Currently there's also ld support for MD5 build id. Adding size argument to build_id_parse function, that returns (if defined) size of the parsed build id, so we can recognize the build id type. Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210114134044.1418404-3-jolsa@kernel.org --- include/linux/buildid.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/buildid.h b/include/linux/buildid.h index 08028a212589..40232f90db6e 100644 --- a/include/linux/buildid.h +++ b/include/linux/buildid.h @@ -6,6 +6,7 @@ #define BUILD_ID_SIZE_MAX 20 -int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id); +int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, + __u32 *size); #endif -- cgit v1.2.3 From 88a16a1309333e43d328621ece3e9fa37027e8eb Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 14 Jan 2021 14:40:44 +0100 Subject: perf: Add build id data in mmap2 event Adding support to carry build id data in mmap2 event. The build id data replaces maj/min/ino/ino_generation fields, which are also used to identify map's binary, so it's ok to replace them with build id data: union { struct { u32 maj; u32 min; u64 ino; u64 ino_generation; }; struct { u8 build_id_size; u8 __reserved_1; u16 __reserved_2; u8 build_id[20]; }; }; Replaced maj/min/ino/ino_generation fields give us size of 24 bytes. We use 20 bytes for build id data, 1 byte for size and rest is unused. There's new misc bit for mmap2 to signal there's build id data in it: #define PERF_RECORD_MISC_MMAP_BUILD_ID (1 << 14) Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/bpf/20210114134044.1418404-4-jolsa@kernel.org --- include/uapi/linux/perf_event.h | 42 ++++++++++++++++++++++++++++++++++++----- 1 file changed, 37 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index b15e3447cd9f..cb6f84103560 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -386,7 +386,8 @@ struct perf_event_attr { aux_output : 1, /* generate AUX records instead of events */ cgroup : 1, /* include cgroup events */ text_poke : 1, /* include text poke events */ - __reserved_1 : 30; + build_id : 1, /* use build id in mmap2 events */ + __reserved_1 : 29; union { __u32 wakeup_events; /* wakeup every n events */ @@ -659,6 +660,22 @@ struct perf_event_mmap_page { __u64 aux_size; }; +/* + * The current state of perf_event_header::misc bits usage: + * ('|' used bit, '-' unused bit) + * + * 012 CDEF + * |||---------|||| + * + * Where: + * 0-2 CPUMODE_MASK + * + * C PROC_MAP_PARSE_TIMEOUT + * D MMAP_DATA / COMM_EXEC / FORK_EXEC / SWITCH_OUT + * E MMAP_BUILD_ID / EXACT_IP / SCHED_OUT_PREEMPT + * F (reserved) + */ + #define PERF_RECORD_MISC_CPUMODE_MASK (7 << 0) #define PERF_RECORD_MISC_CPUMODE_UNKNOWN (0 << 0) #define PERF_RECORD_MISC_KERNEL (1 << 0) @@ -690,6 +707,7 @@ struct perf_event_mmap_page { * * PERF_RECORD_MISC_EXACT_IP - PERF_RECORD_SAMPLE of precise events * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT - PERF_RECORD_SWITCH* events + * PERF_RECORD_MISC_MMAP_BUILD_ID - PERF_RECORD_MMAP2 event * * * PERF_RECORD_MISC_EXACT_IP: @@ -699,9 +717,13 @@ struct perf_event_mmap_page { * * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT: * Indicates that thread was preempted in TASK_RUNNING state. + * + * PERF_RECORD_MISC_MMAP_BUILD_ID: + * Indicates that mmap2 event carries build id data. */ #define PERF_RECORD_MISC_EXACT_IP (1 << 14) #define PERF_RECORD_MISC_SWITCH_OUT_PREEMPT (1 << 14) +#define PERF_RECORD_MISC_MMAP_BUILD_ID (1 << 14) /* * Reserve the last bit to indicate some extended misc field */ @@ -915,10 +937,20 @@ enum perf_event_type { * u64 addr; * u64 len; * u64 pgoff; - * u32 maj; - * u32 min; - * u64 ino; - * u64 ino_generation; + * union { + * struct { + * u32 maj; + * u32 min; + * u64 ino; + * u64 ino_generation; + * }; + * struct { + * u8 build_id_size; + * u8 __reserved_1; + * u16 __reserved_2; + * u8 build_id[20]; + * }; + * }; * u32 prot, flags; * char filename[]; * struct sample_id sample_id; -- cgit v1.2.3 From 54a52823a2d606871c33ef9e2793299768d5d896 Mon Sep 17 00:00:00 2001 From: George McCollister Date: Thu, 14 Jan 2021 13:57:32 -0600 Subject: dsa: add support for Arrow XRS700x tag trailer Add support for Arrow SpeedChips XRS700x single byte tag trailer. This is modeled on tag_trailer.c which works in a similar way. Signed-off-by: George McCollister Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Reviewed-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 06e3784ec55c..fa537afcab53 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -46,6 +46,7 @@ struct phylink_link_state; #define DSA_TAG_PROTO_AR9331_VALUE 16 #define DSA_TAG_PROTO_RTL4_A_VALUE 17 #define DSA_TAG_PROTO_HELLCREEK_VALUE 18 +#define DSA_TAG_PROTO_XRS700X_VALUE 19 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -67,6 +68,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_AR9331 = DSA_TAG_PROTO_AR9331_VALUE, DSA_TAG_PROTO_RTL4_A = DSA_TAG_PROTO_RTL4_A_VALUE, DSA_TAG_PROTO_HELLCREEK = DSA_TAG_PROTO_HELLCREEK_VALUE, + DSA_TAG_PROTO_XRS700X = DSA_TAG_PROTO_XRS700X_VALUE, }; struct packet_type; -- cgit v1.2.3 From f6fe01d6fa24dd3c89996ad82780872441e86bfa Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 15 Jan 2021 04:11:11 +0200 Subject: net: mscc: ocelot: auto-detect packet buffer size and number of frame references Instead of reading these values from the reference manual and writing them down into the driver, it appears that the hardware gives us the option of detecting them dynamically. The number of frame references corresponds to what the reference manual notes, however it seems that the frame buffers are reported as slightly less than the books would indicate. On VSC9959 (Felix), the books say it should have 128KB of packet buffer, but the registers indicate only 129840 bytes (126.79 KB). Also, the unit of measurement for FREECNT from the documentation of all these devices is incorrect (taken from an older generation). This was confirmed by Younes Leroul from Microchip support. Not having anything better to do with these values at the moment* (this will change soon), let's just print them. *The frame buffer size is, in fact, used to calculate the tail dropping watermarks. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot.h | 3 ++- include/soc/mscc/ocelot_qsys.h | 3 +++ 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index f3db75c0172b..c17a372335cd 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -607,7 +607,8 @@ struct ocelot { const struct ocelot_stat_layout *stats_layout; unsigned int num_stats; - int shared_queue_sz; + int packet_buffer_size; + int num_frame_refs; int num_mact_rows; struct net_device *hw_bridge_dev; diff --git a/include/soc/mscc/ocelot_qsys.h b/include/soc/mscc/ocelot_qsys.h index a814bc2017d8..b7b263a19068 100644 --- a/include/soc/mscc/ocelot_qsys.h +++ b/include/soc/mscc/ocelot_qsys.h @@ -77,6 +77,9 @@ #define QSYS_RES_STAT_MAXUSE(x) ((x) & GENMASK(11, 0)) #define QSYS_RES_STAT_MAXUSE_M GENMASK(11, 0) +#define QSYS_MMGT_EQ_CTRL_FP_FREE_CNT(x) ((x) & GENMASK(15, 0)) +#define QSYS_MMGT_EQ_CTRL_FP_FREE_CNT_M GENMASK(15, 0) + #define QSYS_EVENTS_CORE_EV_FDC(x) (((x) << 2) & GENMASK(4, 2)) #define QSYS_EVENTS_CORE_EV_FDC_M GENMASK(4, 2) #define QSYS_EVENTS_CORE_EV_FDC_X(x) (((x) & GENMASK(4, 2)) >> 2) -- cgit v1.2.3 From 703b762190e643bf46a048ebe99504b14d71449c Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 15 Jan 2021 04:11:12 +0200 Subject: net: mscc: ocelot: add ops for decoding watermark threshold and occupancy We'll need to read back the watermark thresholds and occupancy from hardware (for devlink-sb integration), not only to write them as we did so far in ocelot_port_set_maxlen. So introduce 2 new functions in struct ocelot_ops, similar to wm_enc, and implement them for the 3 supported mscc_ocelot switches. Remove the INUSE and MAXUSE unpacking helpers for the QSYS_RES_STAT register, because that doesn't scale with the number of switches that mscc_ocelot supports now. They have different bit widths for the watermarks, and we need function pointers to abstract that difference away. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot.h | 2 ++ include/soc/mscc/ocelot_qsys.h | 6 ------ 2 files changed, 2 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index c17a372335cd..e548b0f51d0c 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -563,6 +563,8 @@ struct ocelot_ops { int (*netdev_to_port)(struct net_device *dev); int (*reset)(struct ocelot *ocelot); u16 (*wm_enc)(u16 value); + u16 (*wm_dec)(u16 value); + void (*wm_stat)(u32 val, u32 *inuse, u32 *maxuse); }; struct ocelot_vcap_block { diff --git a/include/soc/mscc/ocelot_qsys.h b/include/soc/mscc/ocelot_qsys.h index b7b263a19068..9731895be643 100644 --- a/include/soc/mscc/ocelot_qsys.h +++ b/include/soc/mscc/ocelot_qsys.h @@ -71,12 +71,6 @@ #define QSYS_RES_STAT_GSZ 0x8 -#define QSYS_RES_STAT_INUSE(x) (((x) << 12) & GENMASK(23, 12)) -#define QSYS_RES_STAT_INUSE_M GENMASK(23, 12) -#define QSYS_RES_STAT_INUSE_X(x) (((x) & GENMASK(23, 12)) >> 12) -#define QSYS_RES_STAT_MAXUSE(x) ((x) & GENMASK(11, 0)) -#define QSYS_RES_STAT_MAXUSE_M GENMASK(11, 0) - #define QSYS_MMGT_EQ_CTRL_FP_FREE_CNT(x) ((x) & GENMASK(15, 0)) #define QSYS_MMGT_EQ_CTRL_FP_FREE_CNT_M GENMASK(15, 0) -- cgit v1.2.3 From 2a6ef763037238a5aa6a6505fc6693ee77c1a59b Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 15 Jan 2021 04:11:13 +0200 Subject: net: dsa: add ops for devlink-sb Switches that care about QoS might have hardware support for reserving buffer pools for individual ports or traffic classes, and configuring their sizes and thresholds. Through devlink-sb (shared buffers), this is all configurable, as well as their occupancy being viewable. Add the plumbing in DSA for these operations. Individual drivers still need to call devlink_sb_register() with the shared buffers they want to expose. A helper was not created in DSA for this purpose (unlike, say, dsa_devlink_params_register), since in my opinion it does not bring any benefit over plainly calling devlink_sb_register() directly. Signed-off-by: Vladimir Oltean Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index fa537afcab53..2f5435d3d1db 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -699,6 +699,40 @@ struct dsa_switch_ops { int (*devlink_info_get)(struct dsa_switch *ds, struct devlink_info_req *req, struct netlink_ext_ack *extack); + int (*devlink_sb_pool_get)(struct dsa_switch *ds, + unsigned int sb_index, u16 pool_index, + struct devlink_sb_pool_info *pool_info); + int (*devlink_sb_pool_set)(struct dsa_switch *ds, unsigned int sb_index, + u16 pool_index, u32 size, + enum devlink_sb_threshold_type threshold_type, + struct netlink_ext_ack *extack); + int (*devlink_sb_port_pool_get)(struct dsa_switch *ds, int port, + unsigned int sb_index, u16 pool_index, + u32 *p_threshold); + int (*devlink_sb_port_pool_set)(struct dsa_switch *ds, int port, + unsigned int sb_index, u16 pool_index, + u32 threshold, + struct netlink_ext_ack *extack); + int (*devlink_sb_tc_pool_bind_get)(struct dsa_switch *ds, int port, + unsigned int sb_index, u16 tc_index, + enum devlink_sb_pool_type pool_type, + u16 *p_pool_index, u32 *p_threshold); + int (*devlink_sb_tc_pool_bind_set)(struct dsa_switch *ds, int port, + unsigned int sb_index, u16 tc_index, + enum devlink_sb_pool_type pool_type, + u16 pool_index, u32 threshold, + struct netlink_ext_ack *extack); + int (*devlink_sb_occ_snapshot)(struct dsa_switch *ds, + unsigned int sb_index); + int (*devlink_sb_occ_max_clear)(struct dsa_switch *ds, + unsigned int sb_index); + int (*devlink_sb_occ_port_pool_get)(struct dsa_switch *ds, int port, + unsigned int sb_index, u16 pool_index, + u32 *p_cur, u32 *p_max); + int (*devlink_sb_occ_tc_port_bind_get)(struct dsa_switch *ds, int port, + unsigned int sb_index, u16 tc_index, + enum devlink_sb_pool_type pool_type, + u32 *p_cur, u32 *p_max); /* * MTU change functionality. Switches can also adjust their MRU through -- cgit v1.2.3 From 70d39a6e62d31a4a7372a712ccc6f8063bbb1550 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 15 Jan 2021 04:11:16 +0200 Subject: net: mscc: ocelot: export NUM_TC constant from felix to common switch lib We should be moving anything that isn't DSA-specific or SoC-specific out of the felix DSA driver, and into the common mscc_ocelot switch library. The number of traffic classes is one of the aspects that is common between all ocelot switches, so it belongs in the library. This patch also makes seville use 8 TX queues, and therefore enables prioritization via the QOS_CLASS field in the NPI injection header. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index e548b0f51d0c..1dc0c6d0671a 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -98,6 +98,7 @@ #define IFH_REW_OP_TWO_STEP_PTP 0x3 #define IFH_REW_OP_ORIGIN_PTP 0x5 +#define OCELOT_NUM_TC 8 #define OCELOT_TAG_LEN 16 #define OCELOT_SHORT_PREFIX_LEN 4 #define OCELOT_LONG_PREFIX_LEN 16 -- cgit v1.2.3 From 6c30384eb1dec96b678ff9c01c15134b1a0e81f4 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 15 Jan 2021 04:11:18 +0200 Subject: net: mscc: ocelot: register devlink ports Add devlink integration into the mscc_ocelot switchdev driver. All physical ports (i.e. the unused ones as well) except the CPU port module at ocelot->num_phys_ports are registered with devlink, and that requires keeping the devlink_port structure outside struct ocelot_port_private, since the latter has a 1:1 mapping with a struct net_device (which does not exist for unused ports). Since we use devlink_port_type_eth_set to link the devlink port to the net_device, we can as well remove the .ndo_get_phys_port_name and .ndo_get_port_parent_id implementations, since devlink takes care of retrieving the port name and number automatically, once .ndo_get_devlink_port is implemented. Note that the felix DSA driver is already integrated with devlink by default, since that is a thing that the DSA core takes care of. This is the reason why these devlink stubs were put in ocelot_net.c and not in the common library. It is also the reason why ocelot::devlink is a pointer and not a full structure embedded inside struct ocelot: because the mscc_ocelot driver allocates that by itself (as the container of struct ocelot, in fact), but in the case of felix, it is DSA who allocates the devlink, and felix just propagates the pointer towards struct ocelot. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 1dc0c6d0671a..fc7dc6679739 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -602,6 +602,8 @@ struct ocelot_port { struct ocelot { struct device *dev; + struct devlink *devlink; + struct devlink_port *devlink_ports; const struct ocelot_ops *ops; struct regmap *targets[TARGET_MAX]; -- cgit v1.2.3 From f59fd9cab7305266f4148776c3b66329551a2a3a Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 15 Jan 2021 04:11:20 +0200 Subject: net: mscc: ocelot: configure watermarks using devlink-sb Using devlink-sb, we can configure 12/16 (the important 75%) of the switch's controlling watermarks for congestion drops, and we can monitor 50% of the watermark occupancies (we can monitor the reservation watermarks, but not the sharing watermarks, which are exposed as pool sizes). The following definitions can be made: SB_BUF=0 # The devlink-sb for frame buffers SB_REF=1 # The devlink-sb for frame references POOL_ING=0 # The pool for ingress traffic. Both devlink-sb instances # have one of these. POOL_EGR=1 # The pool for egress traffic. Both devlink-sb instances # have one of these. Editing the hardware watermarks is done in the following way: BUF_xxxx_I is accessed when sb=$SB_BUF and pool=$POOL_ING REF_xxxx_I is accessed when sb=$SB_REF and pool=$POOL_ING BUF_xxxx_E is accessed when sb=$SB_BUF and pool=$POOL_EGR REF_xxxx_E is accessed when sb=$SB_REF and pool=$POOL_EGR Configuring the sharing watermarks for COL_SHR(dp=0) is done implicitly by modifying the corresponding pool size. By default, the pool size has maximum size, so this can be skipped. devlink sb pool set pci/0000:00:00.5 sb $SB_BUF pool $POOL_ING \ size 129840 thtype static Since by default there is no buffer reservation, the above command has maxed out BUF_COL_SHR_I(dp=0). Configuring the per-port reservation watermark (P_RSRV) is done in the following way: devlink sb port pool set pci/0000:00:00.5/0 sb $SB_BUF \ pool $POOL_ING th 1000 The above command sets BUF_P_RSRV_I(port 0) to 1000 bytes. After this command, the sharing watermarks are internally reconfigured with 1000 bytes less, i.e. from 129840 bytes to 128840 bytes. Configuring the per-port-tc reservation watermarks (Q_RSRV) is done in the following way: for tc in {0..7}; do devlink sb tc bind set pci/0000:00:00.5/0 sb 0 tc $tc \ type ingress pool $POOL_ING \ th 3000 done The above command sets BUF_Q_RSRV_I(port 0, tc 0..7) to 3000 bytes. The sharing watermarks are again reconfigured with 24000 bytes less. Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot.h | 47 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index fc7dc6679739..cdc33fa05660 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -579,6 +579,18 @@ struct ocelot_vlan { u16 vid; }; +enum ocelot_sb { + OCELOT_SB_BUF, + OCELOT_SB_REF, + OCELOT_SB_NUM, +}; + +enum ocelot_sb_pool { + OCELOT_SB_POOL_ING, + OCELOT_SB_POOL_EGR, + OCELOT_SB_POOL_NUM, +}; + struct ocelot_port { struct ocelot *ocelot; @@ -612,6 +624,7 @@ struct ocelot { const struct ocelot_stat_layout *stats_layout; unsigned int num_stats; + u32 pool_size[OCELOT_SB_NUM][OCELOT_SB_POOL_NUM]; int packet_buffer_size; int num_frame_refs; int num_mact_rows; @@ -783,4 +796,38 @@ int ocelot_port_mdb_add(struct ocelot *ocelot, int port, int ocelot_port_mdb_del(struct ocelot *ocelot, int port, const struct switchdev_obj_port_mdb *mdb); +int ocelot_devlink_sb_register(struct ocelot *ocelot); +void ocelot_devlink_sb_unregister(struct ocelot *ocelot); +int ocelot_sb_pool_get(struct ocelot *ocelot, unsigned int sb_index, + u16 pool_index, + struct devlink_sb_pool_info *pool_info); +int ocelot_sb_pool_set(struct ocelot *ocelot, unsigned int sb_index, + u16 pool_index, u32 size, + enum devlink_sb_threshold_type threshold_type, + struct netlink_ext_ack *extack); +int ocelot_sb_port_pool_get(struct ocelot *ocelot, int port, + unsigned int sb_index, u16 pool_index, + u32 *p_threshold); +int ocelot_sb_port_pool_set(struct ocelot *ocelot, int port, + unsigned int sb_index, u16 pool_index, + u32 threshold, struct netlink_ext_ack *extack); +int ocelot_sb_tc_pool_bind_get(struct ocelot *ocelot, int port, + unsigned int sb_index, u16 tc_index, + enum devlink_sb_pool_type pool_type, + u16 *p_pool_index, u32 *p_threshold); +int ocelot_sb_tc_pool_bind_set(struct ocelot *ocelot, int port, + unsigned int sb_index, u16 tc_index, + enum devlink_sb_pool_type pool_type, + u16 pool_index, u32 threshold, + struct netlink_ext_ack *extack); +int ocelot_sb_occ_snapshot(struct ocelot *ocelot, unsigned int sb_index); +int ocelot_sb_occ_max_clear(struct ocelot *ocelot, unsigned int sb_index); +int ocelot_sb_occ_port_pool_get(struct ocelot *ocelot, int port, + unsigned int sb_index, u16 pool_index, + u32 *p_cur, u32 *p_max); +int ocelot_sb_occ_tc_port_bind_get(struct ocelot *ocelot, int port, + unsigned int sb_index, u16 tc_index, + enum devlink_sb_pool_type pool_type, + u32 *p_cur, u32 *p_max); + #endif -- cgit v1.2.3 From 9ab7e76aefc97a9aa664accb59d6e8dc5e52514a Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Sat, 9 Jan 2021 23:00:21 -0800 Subject: GTP: add support for flow based tunneling API Following patch add support for flow based tunneling API to send and recv GTP tunnel packet over tunnel metadata API. This would allow this device integration with OVS or eBPF using flow based tunneling APIs. Signed-off-by: Pravin B Shelar Link: https://lore.kernel.org/r/20210110070021.26822-1-pbshelar@fb.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/gtp.h | 12 ++++++++++++ include/uapi/linux/if_link.h | 1 + include/uapi/linux/if_tunnel.h | 1 + 3 files changed, 14 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h index 79f9191bbb24..62aff78b7c56 100644 --- a/include/uapi/linux/gtp.h +++ b/include/uapi/linux/gtp.h @@ -2,6 +2,8 @@ #ifndef _UAPI_LINUX_GTP_H_ #define _UAPI_LINUX_GTP_H_ +#include + #define GTP_GENL_MCGRP_NAME "gtp" enum gtp_genl_cmds { @@ -34,4 +36,14 @@ enum gtp_attrs { }; #define GTPA_MAX (__GTPA_MAX + 1) +enum { + GTP_METADATA_V1 +}; + +struct gtpu_metadata { + __u8 ver; + __u8 flags; + __u8 type; +}; + #endif /* _UAPI_LINUX_GTP_H_ */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 82708c6db432..2bd0d8bbcdb2 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -809,6 +809,7 @@ enum { IFLA_GTP_FD1, IFLA_GTP_PDP_HASHSIZE, IFLA_GTP_ROLE, + IFLA_GTP_COLLECT_METADATA, __IFLA_GTP_MAX, }; #define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1) diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index 7d9105533c7b..802da679fab1 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -176,6 +176,7 @@ enum { #define TUNNEL_VXLAN_OPT __cpu_to_be16(0x1000) #define TUNNEL_NOCACHE __cpu_to_be16(0x2000) #define TUNNEL_ERSPAN_OPT __cpu_to_be16(0x4000) +#define TUNNEL_GTPU_OPT __cpu_to_be16(0x8000) #define TUNNEL_OPTIONS_PRESENT \ (TUNNEL_GENEVE_OPT | TUNNEL_VXLAN_OPT | TUNNEL_ERSPAN_OPT) -- cgit v1.2.3 From d349f997686887906b1183b5be96933c5452362a Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sat, 16 Jan 2021 16:56:57 -0800 Subject: net_sched: fix RTNL deadlock again caused by request_module() tcf_action_init_1() loads tc action modules automatically with request_module() after parsing the tc action names, and it drops RTNL lock and re-holds it before and after request_module(). This causes a lot of troubles, as discovered by syzbot, because we can be in the middle of batch initializations when we create an array of tc actions. One of the problem is deadlock: CPU 0 CPU 1 rtnl_lock(); for (...) { tcf_action_init_1(); -> rtnl_unlock(); -> request_module(); rtnl_lock(); for (...) { tcf_action_init_1(); -> tcf_idr_check_alloc(); // Insert one action into idr, // but it is not committed until // tcf_idr_insert_many(), then drop // the RTNL lock in the _next_ // iteration -> rtnl_unlock(); -> rtnl_lock(); -> a_o->init(); -> tcf_idr_check_alloc(); // Now waiting for the same index // to be committed -> request_module(); -> rtnl_lock() // Now waiting for RTNL lock } rtnl_unlock(); } rtnl_unlock(); This is not easy to solve, we can move the request_module() before this loop and pre-load all the modules we need for this netlink message and then do the rest initializations. So the loop breaks down to two now: for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { struct tc_action_ops *a_o; a_o = tc_action_load_ops(name, tb[i]...); ops[i - 1] = a_o; } for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { act = tcf_action_init_1(ops[i - 1]...); } Although this looks serious, it only has been reported by syzbot, so it seems hard to trigger this by humans. And given the size of this patch, I'd suggest to make it to net-next and not to backport to stable. This patch has been tested by syzbot and tested with tdc.py by me. Fixes: 0fedc63fadf0 ("net_sched: commit action insertions together") Reported-and-tested-by: syzbot+82752bc5331601cf4899@syzkaller.appspotmail.com Reported-and-tested-by: syzbot+b3b63b6bff456bd95294@syzkaller.appspotmail.com Reported-by: syzbot+ba67b12b1ca729912834@syzkaller.appspotmail.com Cc: Jiri Pirko Signed-off-by: Cong Wang Tested-by: Jamal Hadi Salim Acked-by: Jamal Hadi Salim Link: https://lore.kernel.org/r/20210117005657.14810-1-xiyou.wangcong@gmail.com Signed-off-by: Jakub Kicinski --- include/net/act_api.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/act_api.h b/include/net/act_api.h index 55dab604861f..761c0e331915 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -186,10 +186,13 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind, struct tc_action *actions[], size_t *attr_size, bool rtnl_held, struct netlink_ext_ack *extack); +struct tc_action_ops *tc_action_load_ops(char *name, struct nlattr *nla, + bool rtnl_held, + struct netlink_ext_ack *extack); struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind, - bool rtnl_held, + struct tc_action_ops *ops, bool rtnl_held, struct netlink_ext_ack *extack); int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], int bind, int ref, bool terse); -- cgit v1.2.3 From 719a402cf60311b1cdff3f6320abaecdcc5e46b7 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Sun, 17 Jan 2021 16:59:42 +0200 Subject: net: netdevice: Add operation ndo_sk_get_lower_dev ndo_sk_get_lower_dev returns the lower netdev that corresponds to a given socket. Additionally, we implement a helper netdev_sk_get_lowest_dev() to get the lowest one in chain. Signed-off-by: Tariq Toukan Reviewed-by: Boris Pismenny Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5b949076ed23..02dcef4d66e2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1398,6 +1398,8 @@ struct net_device_ops { struct net_device* (*ndo_get_xmit_slave)(struct net_device *dev, struct sk_buff *skb, bool all_slaves); + struct net_device* (*ndo_sk_get_lower_dev)(struct net_device *dev, + struct sock *sk); netdev_features_t (*ndo_fix_features)(struct net_device *dev, netdev_features_t features); int (*ndo_set_features)(struct net_device *dev, @@ -2858,6 +2860,8 @@ int init_dummy_netdev(struct net_device *dev); struct net_device *netdev_get_xmit_slave(struct net_device *dev, struct sk_buff *skb, bool all_slaves); +struct net_device *netdev_sk_get_lowest_dev(struct net_device *dev, + struct sock *sk); struct net_device *dev_get_by_index(struct net *net, int ifindex); struct net_device *__dev_get_by_index(struct net *net, int ifindex); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); -- cgit v1.2.3 From 007feb87fb15933b5de7135e6bdf57c219b3fbec Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Sun, 17 Jan 2021 16:59:44 +0200 Subject: net/bonding: Implement ndo_sk_get_lower_dev Add ndo_sk_get_lower_dev() implementation for bond interfaces. Support only for the cases where the socket's and SKBs' hash yields identical value for the whole connection lifetime. Here we restrict it to L3+4 sockets only, with xmit_hash_policy==LAYER34 and bond modes xor/802.3ad. Signed-off-by: Tariq Toukan Reviewed-by: Boris Pismenny Signed-off-by: Jakub Kicinski --- include/net/bonding.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/bonding.h b/include/net/bonding.h index adc3da776970..21497193c4a4 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -265,6 +265,8 @@ struct bond_vlan_tag { unsigned short vlan_id; }; +bool bond_sk_check(struct bonding *bond); + /** * Returns NULL if the net_device does not belong to any of the bond's slaves * -- cgit v1.2.3 From 89df6a8104706f94800ed527ad73d07465ea4d12 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Sun, 17 Jan 2021 16:59:46 +0200 Subject: net/bonding: Implement TLS TX device offload Implement TLS TX device offload for bonding interfaces. This allows kTLS sockets running on a bond to benefit from the device offload on capable lower devices. To allow a simple and fast maintenance of the TLS context in SW and lower devices, we bind the TLS socket to a specific lower dev. To achieve a behavior similar to SW kTLS, we support only balance-xor and 802.3ad modes, with xmit_hash_policy=layer3+4. This is enforced in bond_sk_check(), done in a previous patch. For the above configuration, the SW implementation keeps picking the same exact lower dev for all the socket's SKBs. The device offload behaves similarly, making the decision once at the connection creation. Per socket, the TLS module should work directly with the lowest netdev in chain, to call the tls_dev_ops operations. As the bond interface is being bypassed by the TLS module, interacting directly against the lower devs, there is no way for the bond interface to disable its device offload capabilities, as long as the mode/policy config allows it. Hence, the feature flag is not directly controllable, but just reflects the current offload status based on the logic under bond_sk_check(). Signed-off-by: Tariq Toukan Reviewed-by: Boris Pismenny Signed-off-by: Jakub Kicinski --- include/net/bonding.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/bonding.h b/include/net/bonding.h index 21497193c4a4..97fbec02df2d 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -89,6 +89,8 @@ #define BOND_XFRM_FEATURES (NETIF_F_HW_ESP | NETIF_F_HW_ESP_TX_CSUM | \ NETIF_F_GSO_ESP) +#define BOND_TLS_FEATURES (NETIF_F_HW_TLS_TX) + #ifdef CONFIG_NET_POLL_CONTROLLER extern atomic_t netpoll_block_tx; -- cgit v1.2.3 From dc5809f9e2b674a489723bd8d0131c97e565ca8d Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Sun, 17 Jan 2021 16:59:47 +0200 Subject: net/bonding: Declare TLS RX device offload support Following the description in previous patch (for TX): As the bond interface is being bypassed by the TLS module, interacting directly against the lower devs, there is no way for the bond interface to disable its device offload capabilities, as long as the mode/policy config allows it. Hence, the feature flag is not directly controllable, but just reflects the offload status based on the logic under bond_sk_check(). Here we just declare RX device offload support, and expose it via the NETIF_F_HW_TLS_RX flag. Signed-off-by: Tariq Toukan Reviewed-by: Boris Pismenny Signed-off-by: Jakub Kicinski --- include/net/bonding.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bonding.h b/include/net/bonding.h index 97fbec02df2d..019e998d944a 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -89,7 +89,7 @@ #define BOND_XFRM_FEATURES (NETIF_F_HW_ESP | NETIF_F_HW_ESP_TX_CSUM | \ NETIF_F_GSO_ESP) -#define BOND_TLS_FEATURES (NETIF_F_HW_TLS_TX) +#define BOND_TLS_FEATURES (NETIF_F_HW_TLS_TX | NETIF_F_HW_TLS_RX) #ifdef CONFIG_NET_POLL_CONTROLLER extern atomic_t netpoll_block_tx; -- cgit v1.2.3 From ab0da5a57188b80d16d3222236c4e184953a5bb4 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Wed, 30 Dec 2020 15:01:20 +0200 Subject: net/mlx5: Expose ifc bits for query modify header Expose ifc bits for query_modify_header_context_in to be used by DEVX. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 442c0160caab..cf692fc17f41 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5904,6 +5904,18 @@ struct mlx5_ifc_dealloc_modify_header_context_in_bits { u8 reserved_at_60[0x20]; }; +struct mlx5_ifc_query_modify_header_context_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 modify_header_id[0x20]; + + u8 reserved_at_60[0xa0]; +}; + struct mlx5_ifc_query_dct_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; -- cgit v1.2.3 From 7eab14de73a8028f770e703962c5437a2b0dda82 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Sat, 16 Jan 2021 16:13:22 +0000 Subject: mdio, phy: fix -Wshadow warnings triggered by nested container_of() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit container_of() macro hides a local variable '__mptr' inside. This becomes a problem when several container_of() are nested in each other within single line or plain macros. As C preprocessor doesn't support generating random variable names, the sole solution is to avoid defining macros that consist only of container_of() calls, or they will self-shadow '__mptr' each time: In file included from ./include/linux/bitmap.h:10, from drivers/net/phy/phy_device.c:12: drivers/net/phy/phy_device.c: In function ‘phy_device_release’: ./include/linux/kernel.h:693:8: warning: declaration of ‘__mptr’ shadows a previous local [-Wshadow] 693 | void *__mptr = (void *)(ptr); \ | ^~~~~~ ./include/linux/phy.h:647:26: note: in expansion of macro ‘container_of’ 647 | #define to_phy_device(d) container_of(to_mdio_device(d), \ | ^~~~~~~~~~~~ ./include/linux/mdio.h:52:27: note: in expansion of macro ‘container_of’ 52 | #define to_mdio_device(d) container_of(d, struct mdio_device, dev) | ^~~~~~~~~~~~ ./include/linux/phy.h:647:39: note: in expansion of macro ‘to_mdio_device’ 647 | #define to_phy_device(d) container_of(to_mdio_device(d), \ | ^~~~~~~~~~~~~~ drivers/net/phy/phy_device.c:217:8: note: in expansion of macro ‘to_phy_device’ 217 | kfree(to_phy_device(dev)); | ^~~~~~~~~~~~~ ./include/linux/kernel.h:693:8: note: shadowed declaration is here 693 | void *__mptr = (void *)(ptr); \ | ^~~~~~ ./include/linux/phy.h:647:26: note: in expansion of macro ‘container_of’ 647 | #define to_phy_device(d) container_of(to_mdio_device(d), \ | ^~~~~~~~~~~~ drivers/net/phy/phy_device.c:217:8: note: in expansion of macro ‘to_phy_device’ 217 | kfree(to_phy_device(dev)); | ^~~~~~~~~~~~~ As they are declared in header files, these warnings are highly repetitive and very annoying (along with the one from linux/pci.h). Convert the related macros from linux/{mdio,phy}.h to static inlines to avoid self-shadowing and potentially improve bug-catching. No functional changes implied. Signed-off-by: Alexander Lobakin Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20210116161246.67075-1-alobakin@pm.me Signed-off-by: Jakub Kicinski --- include/linux/mdio.h | 23 ++++++++++++++++++----- include/linux/phy.h | 7 +++++-- 2 files changed, 23 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index dbd69b3d170b..ffb787d5ebde 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -49,7 +49,11 @@ struct mdio_device { unsigned int reset_assert_delay; unsigned int reset_deassert_delay; }; -#define to_mdio_device(d) container_of(d, struct mdio_device, dev) + +static inline struct mdio_device *to_mdio_device(const struct device *dev) +{ + return container_of(dev, struct mdio_device, dev); +} /* struct mdio_driver_common: Common to all MDIO drivers */ struct mdio_driver_common { @@ -57,8 +61,12 @@ struct mdio_driver_common { int flags; }; #define MDIO_DEVICE_FLAG_PHY 1 -#define to_mdio_common_driver(d) \ - container_of(d, struct mdio_driver_common, driver) + +static inline struct mdio_driver_common * +to_mdio_common_driver(const struct device_driver *driver) +{ + return container_of(driver, struct mdio_driver_common, driver); +} /* struct mdio_driver: Generic MDIO driver */ struct mdio_driver { @@ -73,8 +81,13 @@ struct mdio_driver { /* Clears up any memory if needed */ void (*remove)(struct mdio_device *mdiodev); }; -#define to_mdio_driver(d) \ - container_of(to_mdio_common_driver(d), struct mdio_driver, mdiodrv) + +static inline struct mdio_driver * +to_mdio_driver(const struct device_driver *driver) +{ + return container_of(to_mdio_common_driver(driver), struct mdio_driver, + mdiodrv); +} /* device driver data */ static inline void mdiodev_set_drvdata(struct mdio_device *mdio, void *data) diff --git a/include/linux/phy.h b/include/linux/phy.h index 24fcc6456a9e..bc323fbdd21e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -648,8 +648,11 @@ struct phy_device { const struct macsec_ops *macsec_ops; #endif }; -#define to_phy_device(d) container_of(to_mdio_device(d), \ - struct phy_device, mdio) + +static inline struct phy_device *to_phy_device(const struct device *dev) +{ + return container_of(to_mdio_device(dev), struct phy_device, mdio); +} /** * struct phy_tdr_config - Configuration of a TDR raw test -- cgit v1.2.3 From fa82117010430aff2ce86400f7328f55a31b48a6 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 16 Jan 2021 14:13:37 +0800 Subject: net: add inline function skb_csum_is_sctp This patch is to define a inline function skb_csum_is_sctp(), and also replace all places where it checks if it's a SCTP CSUM skb. This function would be used later in many networking drivers in the following patches. Suggested-by: Alexander Duyck Signed-off-by: Xin Long Reviewed-by: Alexander Duyck Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c9568cf60c2a..46f901adf1a8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4621,6 +4621,11 @@ static inline void skb_reset_redirect(struct sk_buff *skb) #endif } +static inline bool skb_csum_is_sctp(struct sk_buff *skb) +{ + return skb->csum_not_inet; +} + static inline void skb_set_kcov_handle(struct sk_buff *skb, const u64 kcov_handle) { -- cgit v1.2.3 From 7b8fc0103bb51d1d3e1fb5fd67958612e709f883 Mon Sep 17 00:00:00 2001 From: Jarod Wilson Date: Mon, 18 Jan 2021 20:09:27 -0500 Subject: bonding: add a vlan+srcmac tx hashing option This comes from an end-user request, where they're running multiple VMs on hosts with bonded interfaces connected to some interest switch topologies, where 802.3ad isn't an option. They're currently running a proprietary solution that effectively achieves load-balancing of VMs and bandwidth utilization improvements with a similar form of transmission algorithm. Basically, each VM has it's own vlan, so it always sends its traffic out the same interface, unless that interface fails. Traffic gets split between the interfaces, maintaining a consistent path, with failover still available if an interface goes down. Unlike bond_eth_hash(), this hash function is using the full source MAC address instead of just the last byte, as there are so few components to the hash, and in the no-vlan case, we would be returning just the last byte of the source MAC as the hash value. It's entirely possible to have two NICs in a bond with the same last byte of their MAC, but not the same MAC, so this adjustment should guarantee distinct hashes in all cases. This has been rudimetarily tested to provide similar results to the proprietary solution it is aiming to replace. A patch for iproute2 is also posted, to properly support the new mode there as well. Cc: Jay Vosburgh Cc: Veaceslav Falico Cc: Andy Gospodarek Cc: Thomas Davis Signed-off-by: Jarod Wilson Link: https://lore.kernel.org/r/20210119010927.1191922-1-jarod@redhat.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 1 + include/uapi/linux/if_bonding.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 02dcef4d66e2..ef517254367d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2617,6 +2617,7 @@ enum netdev_lag_hash { NETDEV_LAG_HASH_L23, NETDEV_LAG_HASH_E23, NETDEV_LAG_HASH_E34, + NETDEV_LAG_HASH_VLAN_SRCMAC, NETDEV_LAG_HASH_UNKNOWN, }; diff --git a/include/uapi/linux/if_bonding.h b/include/uapi/linux/if_bonding.h index 45f3750aa861..e8eb4ad03cf1 100644 --- a/include/uapi/linux/if_bonding.h +++ b/include/uapi/linux/if_bonding.h @@ -94,6 +94,7 @@ #define BOND_XMIT_POLICY_LAYER23 2 /* layer 2+3 (IP ^ MAC) */ #define BOND_XMIT_POLICY_ENCAP23 3 /* encapsulated layer 2+3 */ #define BOND_XMIT_POLICY_ENCAP34 4 /* encapsulated layer 3+4 */ +#define BOND_XMIT_POLICY_VLAN_SRCMAC 5 /* vlan + source MAC */ /* 802.3ad port state definitions (43.4.2.2 in the 802.3ad standard) */ #define LACP_STATE_LACP_ACTIVITY 0x1 -- cgit v1.2.3 From 97a0e1ea7b41c2db762c1258632f6ccc22719510 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 12 Jan 2021 19:26:12 +0100 Subject: net, xdp: Introduce __xdp_build_skb_from_frame utility routine Introduce __xdp_build_skb_from_frame utility routine to build the skb from xdp_frame. Rely on __xdp_build_skb_from_frame in cpumap code. Signed-off-by: Lorenzo Bianconi Signed-off-by: Daniel Borkmann Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/bpf/4f9f4c6b3dd3933770c617eb6689dbc0c6e25863.1610475660.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/net/xdp.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/xdp.h b/include/net/xdp.h index 0cf3976ce77c..689206dee6de 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -164,6 +164,9 @@ void xdp_warn(const char *msg, const char *func, const int line); #define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__) struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp); +struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, + struct sk_buff *skb, + struct net_device *dev); static inline void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp) -- cgit v1.2.3 From 89f479f0eccfc879e7bc0a69f44ed4a4639dfc32 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 12 Jan 2021 19:26:13 +0100 Subject: net, xdp: Introduce xdp_build_skb_from_frame utility routine Introduce xdp_build_skb_from_frame utility routine to build the skb from xdp_frame. Respect to __xdp_build_skb_from_frame, xdp_build_skb_from_frame will allocate the skb object. Rely on xdp_build_skb_from_frame in veth driver. Introduce missing xdp metadata support in veth_xdp_rcv_one routine. Add missing metadata support in veth_xdp_rcv_one(). Signed-off-by: Lorenzo Bianconi Signed-off-by: Daniel Borkmann Reviewed-by: Toshiaki Makita Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/bpf/94ade9e853162ae1947941965193190da97457bc.1610475660.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/net/xdp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/xdp.h b/include/net/xdp.h index 689206dee6de..c4bfdc9a8b79 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -167,6 +167,8 @@ struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp); struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct sk_buff *skb, struct net_device *dev); +struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, + struct net_device *dev); static inline void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp) -- cgit v1.2.3 From 6939f4ef16d48f2093f337162cfc041d0e30ed25 Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Tue, 19 Jan 2021 12:22:36 +0000 Subject: trace: bpf: Allow bpf to attach to bare tracepoints Some subsystems only have bare tracepoints (a tracepoint with no associated trace event) to avoid the problem of trace events being an ABI that can't be changed. >From bpf presepective, bare tracepoints are what it calls RAW_TRACEPOINT(). Since bpf assumed there's 1:1 mapping, it relied on hooking to DEFINE_EVENT() macro to create bpf mapping of the tracepoints. Since bare tracepoints use DECLARE_TRACE() to create the tracepoint, bpf had no knowledge about their existence. By teaching bpf_probe.h to parse DECLARE_TRACE() in a similar fashion to DEFINE_EVENT(), bpf can find and attach to the new raw tracepoints. Enabling that comes with the contract that changes to raw tracepoints don't constitute a regression if they break existing bpf programs. We need the ability to continue to morph and modify these raw tracepoints without worrying about any ABI. Update Documentation/bpf/bpf_design_QA.rst to document this contract. Signed-off-by: Qais Yousef Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210119122237.2426878-2-qais.yousef@arm.com --- include/trace/bpf_probe.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/bpf_probe.h b/include/trace/bpf_probe.h index cd74bffed5c6..a23be89119aa 100644 --- a/include/trace/bpf_probe.h +++ b/include/trace/bpf_probe.h @@ -55,8 +55,7 @@ /* tracepoints with more than 12 arguments will hit build error */ #define CAST_TO_U64(...) CONCATENATE(__CAST, COUNT_ARGS(__VA_ARGS__))(__VA_ARGS__) -#undef DECLARE_EVENT_CLASS -#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ +#define __BPF_DECLARE_TRACE(call, proto, args) \ static notrace void \ __bpf_trace_##call(void *__data, proto) \ { \ @@ -64,6 +63,10 @@ __bpf_trace_##call(void *__data, proto) \ CONCATENATE(bpf_trace_run, COUNT_ARGS(args))(prog, CAST_TO_U64(args)); \ } +#undef DECLARE_EVENT_CLASS +#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ + __BPF_DECLARE_TRACE(call, PARAMS(proto), PARAMS(args)) + /* * This part is compiled out, it is only here as a build time check * to make sure that if the tracepoint handling changes, the @@ -111,6 +114,11 @@ __DEFINE_EVENT(template, call, PARAMS(proto), PARAMS(args), size) #define DEFINE_EVENT_PRINT(template, name, proto, args, print) \ DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args)) +#undef DECLARE_TRACE +#define DECLARE_TRACE(call, proto, args) \ + __BPF_DECLARE_TRACE(call, PARAMS(proto), PARAMS(args)) \ + __DEFINE_EVENT(call, call, PARAMS(proto), PARAMS(args), 0) + #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) #undef DEFINE_EVENT_WRITABLE -- cgit v1.2.3 From 9cacf81f8161111db25f98e78a7a0e32ae142b3f Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Fri, 15 Jan 2021 08:34:59 -0800 Subject: bpf: Remove extra lock_sock for TCP_ZEROCOPY_RECEIVE Add custom implementation of getsockopt hook for TCP_ZEROCOPY_RECEIVE. We skip generic hooks for TCP_ZEROCOPY_RECEIVE and have a custom call in do_tcp_getsockopt using the on-stack data. This removes 3% overhead for locking/unlocking the socket. Without this patch: 3.38% 0.07% tcp_mmap [kernel.kallsyms] [k] __cgroup_bpf_run_filter_getsockopt | --3.30%--__cgroup_bpf_run_filter_getsockopt | --0.81%--__kmalloc With the patch applied: 0.52% 0.12% tcp_mmap [kernel.kallsyms] [k] __cgroup_bpf_run_filter_getsockopt_kern Note, exporting uapi/tcp.h requires removing netinet/tcp.h from test_progs.h because those headers have confliciting definitions. Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20210115163501.805133-2-sdf@google.com --- include/linux/bpf-cgroup.h | 27 +++++++++++++++++++++++---- include/linux/indirect_call_wrapper.h | 6 ++++++ include/net/sock.h | 2 ++ include/net/tcp.h | 1 + 4 files changed, 32 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 72e69a0e1e8c..bcb2915e6124 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -147,6 +147,10 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, int __user *optlen, int max_optlen, int retval); +int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level, + int optname, void *optval, + int *optlen, int retval); + static inline enum bpf_cgroup_storage_type cgroup_storage_type( struct bpf_map *map) { @@ -364,10 +368,23 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, ({ \ int __ret = retval; \ if (cgroup_bpf_enabled) \ - __ret = __cgroup_bpf_run_filter_getsockopt(sock, level, \ - optname, optval, \ - optlen, max_optlen, \ - retval); \ + if (!(sock)->sk_prot->bpf_bypass_getsockopt || \ + !INDIRECT_CALL_INET_1((sock)->sk_prot->bpf_bypass_getsockopt, \ + tcp_bpf_bypass_getsockopt, \ + level, optname)) \ + __ret = __cgroup_bpf_run_filter_getsockopt( \ + sock, level, optname, optval, optlen, \ + max_optlen, retval); \ + __ret; \ +}) + +#define BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sock, level, optname, optval, \ + optlen, retval) \ +({ \ + int __ret = retval; \ + if (cgroup_bpf_enabled) \ + __ret = __cgroup_bpf_run_filter_getsockopt_kern( \ + sock, level, optname, optval, optlen, retval); \ __ret; \ }) @@ -452,6 +469,8 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \ optlen, max_optlen, retval) ({ retval; }) +#define BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sock, level, optname, optval, \ + optlen, retval) ({ retval; }) #define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen, \ kernel_optval) ({ 0; }) diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h index 54c02c84906a..cfcfef37b2f1 100644 --- a/include/linux/indirect_call_wrapper.h +++ b/include/linux/indirect_call_wrapper.h @@ -60,4 +60,10 @@ #define INDIRECT_CALL_INET(f, f2, f1, ...) f(__VA_ARGS__) #endif +#if IS_ENABLED(CONFIG_INET) +#define INDIRECT_CALL_INET_1(f, f1, ...) INDIRECT_CALL_1(f, f1, __VA_ARGS__) +#else +#define INDIRECT_CALL_INET_1(f, f1, ...) f(__VA_ARGS__) +#endif + #endif diff --git a/include/net/sock.h b/include/net/sock.h index 129d200bccb4..7644ea64a376 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1174,6 +1174,8 @@ struct proto { int (*backlog_rcv) (struct sock *sk, struct sk_buff *skb); + bool (*bpf_bypass_getsockopt)(int level, + int optname); void (*release_cb)(struct sock *sk); diff --git a/include/net/tcp.h b/include/net/tcp.h index 78d13c88720f..4bb42fb19711 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -403,6 +403,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); +bool tcp_bpf_bypass_getsockopt(int level, int optname); int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); void tcp_set_keepalive(struct sock *sk, int val); -- cgit v1.2.3 From 20f2505fb436cfa674cf1f46aaa624f44d3d1d03 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Fri, 15 Jan 2021 08:35:00 -0800 Subject: bpf: Try to avoid kzalloc in cgroup/{s,g}etsockopt When we attach a bpf program to cgroup/getsockopt any other getsockopt() syscall starts incurring kzalloc/kfree cost. Let add a small buffer on the stack and use it for small (majority) {s,g}etsockopt values. The buffer is small enough to fit into the cache line and cover the majority of simple options (most of them are 4 byte ints). It seems natural to do the same for setsockopt, but it's a bit more involved when the BPF program modifies the data (where we have to kmalloc). The assumption is that for the majority of setsockopt calls (which are doing pure BPF options or apply policy) this will bring some benefit as well. Without this patch (we remove about 1% __kmalloc): 3.38% 0.07% tcp_mmap [kernel.kallsyms] [k] __cgroup_bpf_run_filter_getsockopt | --3.30%--__cgroup_bpf_run_filter_getsockopt | --0.81%--__kmalloc Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20210115163501.805133-3-sdf@google.com --- include/linux/filter.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 7fdce5407214..5b3137d7b690 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1298,6 +1298,11 @@ struct bpf_sysctl_kern { u64 tmp_reg; }; +#define BPF_SOCKOPT_KERN_BUF_SIZE 32 +struct bpf_sockopt_buf { + u8 data[BPF_SOCKOPT_KERN_BUF_SIZE]; +}; + struct bpf_sockopt_kern { struct sock *sk; u8 *optval; -- cgit v1.2.3 From a9ed15dae0755a0368735e0556a462d8519bdb05 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Fri, 15 Jan 2021 08:35:01 -0800 Subject: bpf: Split cgroup_bpf_enabled per attach type When we attach any cgroup hook, the rest (even if unused/unattached) start to contribute small overhead. In particular, the one we want to avoid is __cgroup_bpf_run_filter_skb which does two redirections to get to the cgroup and pushes/pulls skb. Let's split cgroup_bpf_enabled to be per-attach to make sure only used attach types trigger. I've dropped some existing high-level cgroup_bpf_enabled in some places because BPF_PROG_CGROUP_XXX_RUN macros usually have another cgroup_bpf_enabled check. I also had to copy-paste BPF_CGROUP_RUN_SA_PROG_LOCK for GETPEERNAME/GETSOCKNAME because type for cgroup_bpf_enabled[type] has to be constant and known at compile time. Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20210115163501.805133-4-sdf@google.com --- include/linux/bpf-cgroup.h | 38 ++++++++++++++++++++------------------ 1 file changed, 20 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index bcb2915e6124..0748fd87969e 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -23,8 +23,8 @@ struct ctl_table_header; #ifdef CONFIG_CGROUP_BPF -extern struct static_key_false cgroup_bpf_enabled_key; -#define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key) +extern struct static_key_false cgroup_bpf_enabled_key[MAX_BPF_ATTACH_TYPE]; +#define cgroup_bpf_enabled(type) static_branch_unlikely(&cgroup_bpf_enabled_key[type]) DECLARE_PER_CPU(struct bpf_cgroup_storage*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); @@ -189,7 +189,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(BPF_CGROUP_INET_INGRESS)) \ __ret = __cgroup_bpf_run_filter_skb(sk, skb, \ BPF_CGROUP_INET_INGRESS); \ \ @@ -199,7 +199,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled && sk && sk == skb->sk) { \ + if (cgroup_bpf_enabled(BPF_CGROUP_INET_EGRESS) && sk && sk == skb->sk) { \ typeof(sk) __sk = sk_to_full_sk(sk); \ if (sk_fullsock(__sk)) \ __ret = __cgroup_bpf_run_filter_skb(__sk, skb, \ @@ -211,7 +211,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_SK_PROG(sk, type) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) { \ + if (cgroup_bpf_enabled(type)) { \ __ret = __cgroup_bpf_run_filter_sk(sk, type); \ } \ __ret; \ @@ -232,7 +232,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, type) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(type)) \ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ NULL); \ __ret; \ @@ -241,7 +241,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) { \ + if (cgroup_bpf_enabled(type)) { \ lock_sock(sk); \ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ t_ctx); \ @@ -256,8 +256,10 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_BIND, NULL) -#define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (cgroup_bpf_enabled && \ - sk->sk_prot->pre_connect) +#define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) \ + ((cgroup_bpf_enabled(BPF_CGROUP_INET4_CONNECT) || \ + cgroup_bpf_enabled(BPF_CGROUP_INET6_CONNECT)) && \ + (sk)->sk_prot->pre_connect) #define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) \ BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET4_CONNECT) @@ -301,7 +303,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(sock_ops, sk) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(BPF_CGROUP_SOCK_OPS)) \ __ret = __cgroup_bpf_run_filter_sock_ops(sk, \ sock_ops, \ BPF_CGROUP_SOCK_OPS); \ @@ -311,7 +313,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled && (sock_ops)->sk) { \ + if (cgroup_bpf_enabled(BPF_CGROUP_SOCK_OPS) && (sock_ops)->sk) { \ typeof(sk) __sk = sk_to_full_sk((sock_ops)->sk); \ if (__sk && sk_fullsock(__sk)) \ __ret = __cgroup_bpf_run_filter_sock_ops(__sk, \ @@ -324,7 +326,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(BPF_CGROUP_DEVICE)) \ __ret = __cgroup_bpf_check_dev_permission(type, major, minor, \ access, \ BPF_CGROUP_DEVICE); \ @@ -336,7 +338,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, count, pos) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(BPF_CGROUP_SYSCTL)) \ __ret = __cgroup_bpf_run_filter_sysctl(head, table, write, \ buf, count, pos, \ BPF_CGROUP_SYSCTL); \ @@ -347,7 +349,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, kernel_optval) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(BPF_CGROUP_SETSOCKOPT)) \ __ret = __cgroup_bpf_run_filter_setsockopt(sock, level, \ optname, optval, \ optlen, \ @@ -358,7 +360,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(BPF_CGROUP_GETSOCKOPT)) \ get_user(__ret, optlen); \ __ret; \ }) @@ -367,7 +369,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, max_optlen, retval) \ ({ \ int __ret = retval; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(BPF_CGROUP_GETSOCKOPT)) \ if (!(sock)->sk_prot->bpf_bypass_getsockopt || \ !INDIRECT_CALL_INET_1((sock)->sk_prot->bpf_bypass_getsockopt, \ tcp_bpf_bypass_getsockopt, \ @@ -382,7 +384,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, optlen, retval) \ ({ \ int __ret = retval; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(BPF_CGROUP_GETSOCKOPT)) \ __ret = __cgroup_bpf_run_filter_getsockopt_kern( \ sock, level, optname, optval, optlen, retval); \ __ret; \ @@ -444,7 +446,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, return 0; } -#define cgroup_bpf_enabled (0) +#define cgroup_bpf_enabled(type) (0) #define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx) ({ 0; }) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0) #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) -- cgit v1.2.3 From 7baf2429a1a965369b0ce44efb6315cdd515aa9c Mon Sep 17 00:00:00 2001 From: wenxu Date: Tue, 19 Jan 2021 16:31:50 +0800 Subject: net/sched: cls_flower add CT_FLAGS_INVALID flag support This patch add the TCA_FLOWER_KEY_CT_FLAGS_INVALID flag to match the ct_state with invalid for conntrack. Signed-off-by: wenxu Acked-by: Marcelo Ricardo Leitner Link: https://lore.kernel.org/r/1611045110-682-1-git-send-email-wenxu@ucloud.cn Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 4 ++-- include/net/sch_generic.h | 1 + include/uapi/linux/pkt_cls.h | 1 + 3 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 46f901adf1a8..186dad231e30 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1353,8 +1353,8 @@ void skb_flow_dissect_ct(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, - u16 *ctinfo_map, - size_t mapsize); + u16 *ctinfo_map, size_t mapsize, + bool post_ct); void skb_flow_dissect_tunnel_info(const struct sk_buff *skb, struct flow_dissector *flow_dissector, diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 639e465a108f..e7bee99aebce 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -388,6 +388,7 @@ struct qdisc_skb_cb { #define QDISC_CB_PRIV_LEN 20 unsigned char data[QDISC_CB_PRIV_LEN]; u16 mru; + bool post_ct; }; typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv); diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index ee95f42fb0ec..709668e264b0 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -591,6 +591,7 @@ enum { TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED = 1 << 1, /* Part of an existing connection. */ TCA_FLOWER_KEY_CT_FLAGS_RELATED = 1 << 2, /* Related to an established connection. */ TCA_FLOWER_KEY_CT_FLAGS_TRACKED = 1 << 3, /* Conntrack has occurred. */ + TCA_FLOWER_KEY_CT_FLAGS_INVALID = 1 << 4, /* Conntrack is invalid. */ }; enum { -- cgit v1.2.3 From 07be2fed5ee7b3a01e0b21c15814b590af9c1527 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Fri, 18 Dec 2020 19:47:13 +0100 Subject: net/fq_impl: bulk-free packets from a flow on overmemory This is similar to what sch_fq_codel does. It also amortizes the worst case cost of a follow-up patch that changes the selection of the biggest flow for dropping packets Signed-off-by: Felix Fietkau Link: https://lore.kernel.org/r/20201218184718.93650-1-nbd@nbd.name Signed-off-by: Johannes Berg --- include/net/fq_impl.h | 55 ++++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 44 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/fq_impl.h b/include/net/fq_impl.h index e73d74d2fabf..06d2a79233c9 100644 --- a/include/net/fq_impl.h +++ b/include/net/fq_impl.h @@ -11,17 +11,25 @@ /* functions that are embedded into includer */ + +static void +__fq_adjust_removal(struct fq *fq, struct fq_flow *flow, unsigned int packets, + unsigned int bytes, unsigned int truesize) +{ + struct fq_tin *tin = flow->tin; + + tin->backlog_bytes -= bytes; + tin->backlog_packets -= packets; + flow->backlog -= bytes; + fq->backlog -= packets; + fq->memory_usage -= truesize; +} + static void fq_adjust_removal(struct fq *fq, struct fq_flow *flow, struct sk_buff *skb) { - struct fq_tin *tin = flow->tin; - - tin->backlog_bytes -= skb->len; - tin->backlog_packets--; - flow->backlog -= skb->len; - fq->backlog--; - fq->memory_usage -= skb->truesize; + __fq_adjust_removal(fq, flow, 1, skb->len, skb->truesize); } static void fq_rejigger_backlog(struct fq *fq, struct fq_flow *flow) @@ -59,6 +67,34 @@ static struct sk_buff *fq_flow_dequeue(struct fq *fq, return skb; } +static int fq_flow_drop(struct fq *fq, struct fq_flow *flow, + fq_skb_free_t free_func) +{ + unsigned int packets = 0, bytes = 0, truesize = 0; + struct fq_tin *tin = flow->tin; + struct sk_buff *skb; + int pending; + + lockdep_assert_held(&fq->lock); + + pending = min_t(int, 32, skb_queue_len(&flow->queue) / 2); + do { + skb = __skb_dequeue(&flow->queue); + if (!skb) + break; + + packets++; + bytes += skb->len; + truesize += skb->truesize; + free_func(fq, tin, flow, skb); + } while (packets < pending); + + __fq_adjust_removal(fq, flow, packets, bytes, truesize); + fq_rejigger_backlog(fq, flow); + + return packets; +} + static struct sk_buff *fq_tin_dequeue(struct fq *fq, struct fq_tin *tin, fq_tin_dequeue_t dequeue_func) @@ -190,12 +226,9 @@ static void fq_tin_enqueue(struct fq *fq, if (!flow) return; - skb = fq_flow_dequeue(fq, flow); - if (!skb) + if (!fq_flow_drop(fq, flow, free_func)) return; - free_func(fq, flow->tin, flow, skb); - flow->tin->overlimit++; fq->overlimit++; if (oom) { -- cgit v1.2.3 From bf9009bf21b53501f2abb2f59f9314d85bde5fc9 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Fri, 18 Dec 2020 19:47:14 +0100 Subject: net/fq_impl: drop get_default_func, move default flow to fq_tin Simplifies the code and prepares for a rework of scanning for flows on overmemory drop. Signed-off-by: Felix Fietkau Link: https://lore.kernel.org/r/20201218184718.93650-2-nbd@nbd.name Signed-off-by: Johannes Berg --- include/net/fq.h | 1 + include/net/fq_impl.h | 11 +++++------ 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/fq.h b/include/net/fq.h index e39f3f8d5f8a..5df100b77099 100644 --- a/include/net/fq.h +++ b/include/net/fq.h @@ -47,6 +47,7 @@ struct fq_flow { struct fq_tin { struct list_head new_flows; struct list_head old_flows; + struct fq_flow default_flow; u32 backlog_bytes; u32 backlog_packets; u32 overlimit; diff --git a/include/net/fq_impl.h b/include/net/fq_impl.h index 06d2a79233c9..dd374c7f0fe5 100644 --- a/include/net/fq_impl.h +++ b/include/net/fq_impl.h @@ -151,8 +151,7 @@ static u32 fq_flow_idx(struct fq *fq, struct sk_buff *skb) static struct fq_flow *fq_flow_classify(struct fq *fq, struct fq_tin *tin, u32 idx, - struct sk_buff *skb, - fq_flow_get_default_t get_default_func) + struct sk_buff *skb) { struct fq_flow *flow; @@ -160,7 +159,7 @@ static struct fq_flow *fq_flow_classify(struct fq *fq, flow = &fq->flows[idx]; if (flow->tin && flow->tin != tin) { - flow = get_default_func(fq, tin, idx, skb); + flow = &tin->default_flow; tin->collisions++; fq->collisions++; } @@ -192,15 +191,14 @@ static void fq_recalc_backlog(struct fq *fq, static void fq_tin_enqueue(struct fq *fq, struct fq_tin *tin, u32 idx, struct sk_buff *skb, - fq_skb_free_t free_func, - fq_flow_get_default_t get_default_func) + fq_skb_free_t free_func) { struct fq_flow *flow; bool oom; lockdep_assert_held(&fq->lock); - flow = fq_flow_classify(fq, tin, idx, skb, get_default_func); + flow = fq_flow_classify(fq, tin, idx, skb); flow->tin = tin; flow->backlog += skb->len; @@ -331,6 +329,7 @@ static void fq_tin_init(struct fq_tin *tin) { INIT_LIST_HEAD(&tin->new_flows); INIT_LIST_HEAD(&tin->old_flows); + fq_flow_init(&tin->default_flow); } static int fq_init(struct fq *fq, int flows_cnt) -- cgit v1.2.3 From d7b649291782430904e17cde2ebfc90f76021ca5 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Fri, 18 Dec 2020 19:47:15 +0100 Subject: net/fq_impl: do not maintain a backlog-sorted list of flows A sorted flow list is only needed to drop packets in the biggest flow when hitting the overmemory condition. By scanning flows only when needed, we can avoid paying the cost of maintaining the list under normal conditions In order to avoid scanning lots of empty flows and touching too many cold cache lines, a bitmap of flows with backlog is maintained Signed-off-by: Felix Fietkau Link: https://lore.kernel.org/r/20201218184718.93650-3-nbd@nbd.name Signed-off-by: Johannes Berg --- include/net/fq.h | 10 ++--- include/net/fq_impl.h | 113 ++++++++++++++++++++++++++++++-------------------- 2 files changed, 71 insertions(+), 52 deletions(-) (limited to 'include') diff --git a/include/net/fq.h b/include/net/fq.h index 5df100b77099..2eccbbd2b559 100644 --- a/include/net/fq.h +++ b/include/net/fq.h @@ -19,8 +19,6 @@ struct fq_tin; * @flowchain: can be linked to fq_tin's new_flows or old_flows. Used for DRR++ * (deficit round robin) based round robin queuing similar to the one * found in net/sched/sch_fq_codel.c - * @backlogchain: can be linked to other fq_flow and fq. Used to keep track of - * fat flows and efficient head-dropping if packet limit is reached * @queue: sk_buff queue to hold packets * @backlog: number of bytes pending in the queue. The number of packets can be * found in @queue.qlen @@ -29,7 +27,6 @@ struct fq_tin; struct fq_flow { struct fq_tin *tin; struct list_head flowchain; - struct list_head backlogchain; struct sk_buff_head queue; u32 backlog; int deficit; @@ -47,6 +44,7 @@ struct fq_flow { struct fq_tin { struct list_head new_flows; struct list_head old_flows; + struct list_head tin_list; struct fq_flow default_flow; u32 backlog_bytes; u32 backlog_packets; @@ -60,14 +58,14 @@ struct fq_tin { /** * struct fq - main container for fair queuing purposes * - * @backlogs: linked to fq_flows. Used to maintain fat flows for efficient - * head-dropping when @backlog reaches @limit * @limit: max number of packets that can be queued across all flows * @backlog: number of packets queued across all flows */ struct fq { struct fq_flow *flows; - struct list_head backlogs; + unsigned long *flows_bitmap; + + struct list_head tin_backlog; spinlock_t lock; u32 flows_cnt; u32 limit; diff --git a/include/net/fq_impl.h b/include/net/fq_impl.h index dd374c7f0fe5..a5f67a2c0c73 100644 --- a/include/net/fq_impl.h +++ b/include/net/fq_impl.h @@ -17,12 +17,24 @@ __fq_adjust_removal(struct fq *fq, struct fq_flow *flow, unsigned int packets, unsigned int bytes, unsigned int truesize) { struct fq_tin *tin = flow->tin; + int idx; tin->backlog_bytes -= bytes; tin->backlog_packets -= packets; flow->backlog -= bytes; fq->backlog -= packets; fq->memory_usage -= truesize; + + if (flow->backlog) + return; + + if (flow == &tin->default_flow) { + list_del_init(&tin->tin_list); + return; + } + + idx = flow - fq->flows; + __clear_bit(idx, fq->flows_bitmap); } static void fq_adjust_removal(struct fq *fq, @@ -32,24 +44,6 @@ static void fq_adjust_removal(struct fq *fq, __fq_adjust_removal(fq, flow, 1, skb->len, skb->truesize); } -static void fq_rejigger_backlog(struct fq *fq, struct fq_flow *flow) -{ - struct fq_flow *i; - - if (flow->backlog == 0) { - list_del_init(&flow->backlogchain); - } else { - i = flow; - - list_for_each_entry_continue(i, &fq->backlogs, backlogchain) - if (i->backlog < flow->backlog) - break; - - list_move_tail(&flow->backlogchain, - &i->backlogchain); - } -} - static struct sk_buff *fq_flow_dequeue(struct fq *fq, struct fq_flow *flow) { @@ -62,7 +56,6 @@ static struct sk_buff *fq_flow_dequeue(struct fq *fq, return NULL; fq_adjust_removal(fq, flow, skb); - fq_rejigger_backlog(fq, flow); return skb; } @@ -90,7 +83,6 @@ static int fq_flow_drop(struct fq *fq, struct fq_flow *flow, } while (packets < pending); __fq_adjust_removal(fq, flow, packets, bytes, truesize); - fq_rejigger_backlog(fq, flow); return packets; } @@ -170,22 +162,36 @@ static struct fq_flow *fq_flow_classify(struct fq *fq, return flow; } -static void fq_recalc_backlog(struct fq *fq, - struct fq_tin *tin, - struct fq_flow *flow) +static struct fq_flow *fq_find_fattest_flow(struct fq *fq) { - struct fq_flow *i; + struct fq_tin *tin; + struct fq_flow *flow = NULL; + u32 len = 0; + int i; - if (list_empty(&flow->backlogchain)) - list_add_tail(&flow->backlogchain, &fq->backlogs); + for_each_set_bit(i, fq->flows_bitmap, fq->flows_cnt) { + struct fq_flow *cur = &fq->flows[i]; + unsigned int cur_len; - i = flow; - list_for_each_entry_continue_reverse(i, &fq->backlogs, - backlogchain) - if (i->backlog > flow->backlog) - break; + cur_len = cur->backlog; + if (cur_len <= len) + continue; + + flow = cur; + len = cur_len; + } + + list_for_each_entry(tin, &fq->tin_backlog, tin_list) { + unsigned int cur_len = tin->default_flow.backlog; - list_move(&flow->backlogchain, &i->backlogchain); + if (cur_len <= len) + continue; + + flow = &tin->default_flow; + len = cur_len; + } + + return flow; } static void fq_tin_enqueue(struct fq *fq, @@ -200,6 +206,13 @@ static void fq_tin_enqueue(struct fq *fq, flow = fq_flow_classify(fq, tin, idx, skb); + if (!flow->backlog) { + if (flow != &tin->default_flow) + __set_bit(idx, fq->flows_bitmap); + else if (list_empty(&tin->tin_list)) + list_add(&tin->tin_list, &fq->tin_backlog); + } + flow->tin = tin; flow->backlog += skb->len; tin->backlog_bytes += skb->len; @@ -207,8 +220,6 @@ static void fq_tin_enqueue(struct fq *fq, fq->memory_usage += skb->truesize; fq->backlog++; - fq_recalc_backlog(fq, tin, flow); - if (list_empty(&flow->flowchain)) { flow->deficit = fq->quantum; list_add_tail(&flow->flowchain, @@ -218,9 +229,7 @@ static void fq_tin_enqueue(struct fq *fq, __skb_queue_tail(&flow->queue, skb); oom = (fq->memory_usage > fq->memory_limit); while (fq->backlog > fq->limit || oom) { - flow = list_first_entry_or_null(&fq->backlogs, - struct fq_flow, - backlogchain); + flow = fq_find_fattest_flow(fq); if (!flow) return; @@ -255,8 +264,6 @@ static void fq_flow_filter(struct fq *fq, fq_adjust_removal(fq, flow, skb); free_func(fq, tin, flow, skb); } - - fq_rejigger_backlog(fq, flow); } static void fq_tin_filter(struct fq *fq, @@ -279,16 +286,18 @@ static void fq_flow_reset(struct fq *fq, struct fq_flow *flow, fq_skb_free_t free_func) { + struct fq_tin *tin = flow->tin; struct sk_buff *skb; while ((skb = fq_flow_dequeue(fq, flow))) - free_func(fq, flow->tin, flow, skb); + free_func(fq, tin, flow, skb); - if (!list_empty(&flow->flowchain)) + if (!list_empty(&flow->flowchain)) { list_del_init(&flow->flowchain); - - if (!list_empty(&flow->backlogchain)) - list_del_init(&flow->backlogchain); + if (list_empty(&tin->new_flows) && + list_empty(&tin->old_flows)) + list_del_init(&tin->tin_list); + } flow->tin = NULL; @@ -314,6 +323,7 @@ static void fq_tin_reset(struct fq *fq, fq_flow_reset(fq, flow, free_func); } + WARN_ON_ONCE(!list_empty(&tin->tin_list)); WARN_ON_ONCE(tin->backlog_bytes); WARN_ON_ONCE(tin->backlog_packets); } @@ -321,7 +331,6 @@ static void fq_tin_reset(struct fq *fq, static void fq_flow_init(struct fq_flow *flow) { INIT_LIST_HEAD(&flow->flowchain); - INIT_LIST_HEAD(&flow->backlogchain); __skb_queue_head_init(&flow->queue); } @@ -329,6 +338,7 @@ static void fq_tin_init(struct fq_tin *tin) { INIT_LIST_HEAD(&tin->new_flows); INIT_LIST_HEAD(&tin->old_flows); + INIT_LIST_HEAD(&tin->tin_list); fq_flow_init(&tin->default_flow); } @@ -337,8 +347,8 @@ static int fq_init(struct fq *fq, int flows_cnt) int i; memset(fq, 0, sizeof(fq[0])); - INIT_LIST_HEAD(&fq->backlogs); spin_lock_init(&fq->lock); + INIT_LIST_HEAD(&fq->tin_backlog); fq->flows_cnt = max_t(u32, flows_cnt, 1); fq->quantum = 300; fq->limit = 8192; @@ -348,6 +358,14 @@ static int fq_init(struct fq *fq, int flows_cnt) if (!fq->flows) return -ENOMEM; + fq->flows_bitmap = kcalloc(BITS_TO_LONGS(fq->flows_cnt), sizeof(long), + GFP_KERNEL); + if (!fq->flows_bitmap) { + kvfree(fq->flows); + fq->flows = NULL; + return -ENOMEM; + } + for (i = 0; i < fq->flows_cnt; i++) fq_flow_init(&fq->flows[i]); @@ -364,6 +382,9 @@ static void fq_reset(struct fq *fq, kvfree(fq->flows); fq->flows = NULL; + + kfree(fq->flows_bitmap); + fq->flows_bitmap = NULL; } #endif -- cgit v1.2.3 From 80a915ec4427f0083829f7e6518ee9f21521ee1e Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Fri, 18 Dec 2020 19:47:18 +0100 Subject: mac80211: add rx decapsulation offload support This allows drivers to pass 802.3 frames to mac80211, with some restrictions: - the skb must be passed with a valid sta - fast-rx needs to be active for the sta - monitor mode needs to be disabled mac80211 will tell the driver when it is safe to enable rx decap offload for a particular station. In order to implement support, a driver must: - call ieee80211_hw_set(hw, SUPPORTS_RX_DECAP_OFFLOAD) - implement ops->sta_set_decap_offload - mark 802.3 frames with RX_FLAG_8023 If it doesn't want to enable offload for some vif types, it can mask out IEEE80211_OFFLOAD_DECAP_ENABLED in vif->offload_flags from within the .add_interface or .update_vif_offload driver ops Signed-off-by: Felix Fietkau Link: https://lore.kernel.org/r/20201218184718.93650-6-nbd@nbd.name Signed-off-by: Johannes Berg --- include/net/mac80211.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 2bdbf62f4ecd..176fe0d9f67f 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1296,6 +1296,8 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * the "0-length PSDU" field included there. The value for it is * in &struct ieee80211_rx_status. Note that if this value isn't * known the frame shouldn't be reported. + * @RX_FLAG_8023: the frame has an 802.3 header (decap offload performed by + * hardware or driver) */ enum mac80211_rx_flags { RX_FLAG_MMIC_ERROR = BIT(0), @@ -1328,6 +1330,7 @@ enum mac80211_rx_flags { RX_FLAG_RADIOTAP_HE_MU = BIT(27), RX_FLAG_RADIOTAP_LSIG = BIT(28), RX_FLAG_NO_PSDU = BIT(29), + RX_FLAG_8023 = BIT(30), }; /** @@ -1649,11 +1652,15 @@ enum ieee80211_vif_flags { * The driver supports sending frames passed as 802.3 frames by mac80211. * It must also support sending 802.11 packets for the same interface. * @IEEE80211_OFFLOAD_ENCAP_4ADDR: support 4-address mode encapsulation offload + * @IEEE80211_OFFLOAD_DECAP_ENABLED: rx encapsulation offload is enabled + * The driver supports passing received 802.11 frames as 802.3 frames to + * mac80211. */ enum ieee80211_offload_flags { IEEE80211_OFFLOAD_ENCAP_ENABLED = BIT(0), IEEE80211_OFFLOAD_ENCAP_4ADDR = BIT(1), + IEEE80211_OFFLOAD_DECAP_ENABLED = BIT(2), }; /** @@ -2389,6 +2396,9 @@ struct ieee80211_txq { * @IEEE80211_HW_SUPPORTS_TX_ENCAP_OFFLOAD: Hardware supports tx encapsulation * offload * + * @IEEE80211_HW_SUPPORTS_RX_DECAP_OFFLOAD: Hardware supports rx decapsulation + * offload + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -2442,6 +2452,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_SUPPORTS_ONLY_HE_MULTI_BSSID, IEEE80211_HW_AMPDU_KEYBORDER_SUPPORT, IEEE80211_HW_SUPPORTS_TX_ENCAP_OFFLOAD, + IEEE80211_HW_SUPPORTS_RX_DECAP_OFFLOAD, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS @@ -3881,6 +3892,8 @@ enum ieee80211_reconfig_type { * @sta_set_4addr: Called to notify the driver when a station starts/stops using * 4-address mode * @set_sar_specs: Update the SAR (TX power) settings. + * @sta_set_decap_offload: Called to notify the driver when a station is allowed + * to use rx decapsulation offload */ struct ieee80211_ops { void (*tx)(struct ieee80211_hw *hw, @@ -4198,6 +4211,9 @@ struct ieee80211_ops { struct ieee80211_sta *sta, bool enabled); int (*set_sar_specs)(struct ieee80211_hw *hw, const struct cfg80211_sar_specs *sar); + void (*sta_set_decap_offload)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, bool enabled); }; /** -- cgit v1.2.3 From e8e507a8ac90d48053dfdea9d4855495b0204956 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Tue, 19 Jan 2021 16:07:47 +0100 Subject: soc: fsl: qe: make cpm_muram_offset take a const void* argument Allow passing const-qualified pointers without requiring a cast in the caller. Signed-off-by: Rasmus Villemoes Acked-by: Li Yang Signed-off-by: Jakub Kicinski --- include/soc/fsl/qe/qe.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/soc/fsl/qe/qe.h b/include/soc/fsl/qe/qe.h index 3feddfec9f87..8ee3747433c0 100644 --- a/include/soc/fsl/qe/qe.h +++ b/include/soc/fsl/qe/qe.h @@ -102,7 +102,7 @@ s32 cpm_muram_alloc(unsigned long size, unsigned long align); void cpm_muram_free(s32 offset); s32 cpm_muram_alloc_fixed(unsigned long offset, unsigned long size); void __iomem *cpm_muram_addr(unsigned long offset); -unsigned long cpm_muram_offset(void __iomem *addr); +unsigned long cpm_muram_offset(const void __iomem *addr); dma_addr_t cpm_muram_dma(void __iomem *addr); #else static inline s32 cpm_muram_alloc(unsigned long size, @@ -126,7 +126,7 @@ static inline void __iomem *cpm_muram_addr(unsigned long offset) return NULL; } -static inline unsigned long cpm_muram_offset(void __iomem *addr) +static inline unsigned long cpm_muram_offset(const void __iomem *addr) { return -ENOSYS; } -- cgit v1.2.3 From 186b8daffb4ec2dabb8a3d93b329b16152a5a100 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Tue, 19 Jan 2021 16:07:49 +0100 Subject: soc: fsl: qe: add cpm_muram_free_addr() helper Add a helper that takes a virtual address rather than the muram offset. This will be used in a couple of places to avoid having to store both the offset and the virtual address, as well as removing NULL checks from the callers. Signed-off-by: Rasmus Villemoes Acked-by: Li Yang Signed-off-by: Jakub Kicinski --- include/soc/fsl/qe/qe.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/soc/fsl/qe/qe.h b/include/soc/fsl/qe/qe.h index 8ee3747433c0..66f1afc393d1 100644 --- a/include/soc/fsl/qe/qe.h +++ b/include/soc/fsl/qe/qe.h @@ -104,6 +104,7 @@ s32 cpm_muram_alloc_fixed(unsigned long offset, unsigned long size); void __iomem *cpm_muram_addr(unsigned long offset); unsigned long cpm_muram_offset(const void __iomem *addr); dma_addr_t cpm_muram_dma(void __iomem *addr); +void cpm_muram_free_addr(const void __iomem *addr); #else static inline s32 cpm_muram_alloc(unsigned long size, unsigned long align) @@ -135,6 +136,9 @@ static inline dma_addr_t cpm_muram_dma(void __iomem *addr) { return 0; } +static inline void cpm_muram_free_addr(const void __iomem *addr) +{ +} #endif /* defined(CONFIG_CPM) || defined(CONFIG_QUICC_ENGINE) */ /* QE PIO */ @@ -239,6 +243,7 @@ static inline int qe_alive_during_sleep(void) #define qe_muram_addr cpm_muram_addr #define qe_muram_offset cpm_muram_offset #define qe_muram_dma cpm_muram_dma +#define qe_muram_free_addr cpm_muram_free_addr #ifdef CONFIG_PPC32 #define qe_iowrite8(val, addr) out_8(addr, val) -- cgit v1.2.3 From 64a99fe596f9cb2af2c23c64352817ff8cf662bb Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Tue, 19 Jan 2021 16:07:58 +0100 Subject: ethernet: ucc_geth: remove bd_mem_part and all associated code The bd_mem_part member of ucc_geth_info always has the value MEM_PART_SYSTEM, and AFAICT, there has never been any code setting it to any other value. Moreover, muram is a somewhat precious resource, so there's no point using that when normal memory serves just as well. Apart from removing a lot of dead code, this is also motivated by wanting to clean up the "store result from kmalloc() in a u32" mess. Signed-off-by: Rasmus Villemoes Signed-off-by: Jakub Kicinski --- include/soc/fsl/qe/qe.h | 6 ------ include/soc/fsl/qe/ucc_fast.h | 1 - 2 files changed, 7 deletions(-) (limited to 'include') diff --git a/include/soc/fsl/qe/qe.h b/include/soc/fsl/qe/qe.h index 66f1afc393d1..4925a1b59dc9 100644 --- a/include/soc/fsl/qe/qe.h +++ b/include/soc/fsl/qe/qe.h @@ -27,12 +27,6 @@ #define QE_NUM_OF_BRGS 16 #define QE_NUM_OF_PORTS 1024 -/* Memory partitions -*/ -#define MEM_PART_SYSTEM 0 -#define MEM_PART_SECONDARY 1 -#define MEM_PART_MURAM 2 - /* Clocks and BRGs */ enum qe_clock { QE_CLK_NONE = 0, diff --git a/include/soc/fsl/qe/ucc_fast.h b/include/soc/fsl/qe/ucc_fast.h index dc4e79468094..9696a5b9b5d1 100644 --- a/include/soc/fsl/qe/ucc_fast.h +++ b/include/soc/fsl/qe/ucc_fast.h @@ -146,7 +146,6 @@ struct ucc_fast_info { resource_size_t regs; int irq; u32 uccm_mask; - int bd_mem_part; int brkpt_support; int grant_support; int tsa; -- cgit v1.2.3 From d9c85e24726587277ce0dcf33b5695acfcc72234 Mon Sep 17 00:00:00 2001 From: Max Chen Date: Wed, 6 Jan 2021 15:50:49 -0800 Subject: cfg80211: Add phyrate conversion support for extended MCS in 60GHz band The current phyrate conversion does not include extended MCS and provides incorrect rates. Add a flag for extended MCS in DMG and add corresponding phyrate table for the correct conversions using base MCS in DMG specs. Signed-off-by: Max Chen Link: https://lore.kernel.org/r/1609977050-7089-2-git-send-email-mxchen@codeaurora.org [reduce data size, make a single WARN] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 0d6f7ec86061..798f8eb15e00 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1460,6 +1460,7 @@ int cfg80211_check_station_change(struct wiphy *wiphy, * @RATE_INFO_FLAGS_DMG: 60GHz MCS * @RATE_INFO_FLAGS_HE_MCS: HE MCS information * @RATE_INFO_FLAGS_EDMG: 60GHz MCS in EDMG mode + * @RATE_INFO_FLAGS_EXTENDED_SC_DMG: 60GHz extended SC MCS */ enum rate_info_flags { RATE_INFO_FLAGS_MCS = BIT(0), @@ -1468,6 +1469,7 @@ enum rate_info_flags { RATE_INFO_FLAGS_DMG = BIT(3), RATE_INFO_FLAGS_HE_MCS = BIT(4), RATE_INFO_FLAGS_EDMG = BIT(5), + RATE_INFO_FLAGS_EXTENDED_SC_DMG = BIT(6), }; /** -- cgit v1.2.3 From 2fe8ef106238b274c505c480ecf00d8765abf0d8 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 22 Jan 2021 16:19:42 +0100 Subject: cfg80211: change netdev registration/unregistration semantics We used to not require anything in terms of registering netdevs with cfg80211, using a netdev notifier instead. However, in the next patch reducing RTNL locking, this causes big problems, and the simplest way is to just require drivers to do things better. Change the registration/unregistration semantics to require the drivers to call cfg80211_(un)register_netdevice() when this is happening due to a cfg80211 request, i.e. add_virtual_intf() or del_virtual_intf() (or if it somehow has to happen in any other cfg80211 callback). Otherwise, in other contexts, drivers may continue to use the normal netdev (un)registration functions as usual. Internally, we still use the netdev notifier and track (by the new wdev->registered bool) if the wdev had already been added to cfg80211 or not. Link: https://lore.kernel.org/r/20210122161942.cf2f4b65e4e9.Ida8234e50da13eb675b557bac52a713ad4eddf71@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 40 ++++++++++++++++++++++++++++++++-------- 1 file changed, 32 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 798f8eb15e00..e7703fdbac8d 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5228,6 +5228,7 @@ struct cfg80211_cqm_config; * * @wiphy: pointer to hardware description * @iftype: interface type + * @registered: is this wdev already registered with cfg80211 * @list: (private) Used to collect the interfaces * @netdev: (private) Used to reference back to the netdev, may be %NULL * @identifier: (private) Identifier used in nl80211 to identify this @@ -5311,7 +5312,7 @@ struct wireless_dev { struct mutex mtx; - bool use_4addr, is_running; + bool use_4addr, is_running, registered; u8 address[ETH_ALEN] __aligned(sizeof(u16)); @@ -7654,18 +7655,41 @@ u32 cfg80211_calculate_bitrate(struct rate_info *rate); * cfg80211_unregister_wdev - remove the given wdev * @wdev: struct wireless_dev to remove * - * Call this function only for wdevs that have no netdev assigned, - * e.g. P2P Devices. It removes the device from the list so that - * it can no longer be used. It is necessary to call this function - * even when cfg80211 requests the removal of the interface by - * calling the del_virtual_intf() callback. The function must also - * be called when the driver wishes to unregister the wdev, e.g. - * when the device is unbound from the driver. + * This function removes the device so it can no longer be used. It is necessary + * to call this function even when cfg80211 requests the removal of the device + * by calling the del_virtual_intf() callback. The function must also be called + * when the driver wishes to unregister the wdev, e.g. when the hardware device + * is unbound from the driver. * * Requires the RTNL to be held. */ void cfg80211_unregister_wdev(struct wireless_dev *wdev); +/** + * cfg80211_register_netdevice - register the given netdev + * @dev: the netdev to register + * + * Note: In contexts coming from cfg80211 callbacks, you must call this rather + * than register_netdevice(), unregister_netdev() is impossible as the RTNL is + * held. Otherwise, both register_netdevice() and register_netdev() are usable + * instead as well. + */ +int cfg80211_register_netdevice(struct net_device *dev); + +/** + * cfg80211_unregister_netdevice - unregister the given netdev + * @dev: the netdev to register + * + * Note: In contexts coming from cfg80211 callbacks, you must call this rather + * than unregister_netdevice(), unregister_netdev() is impossible as the RTNL + * is held. Otherwise, both unregister_netdevice() and unregister_netdev() are + * usable instead as well. + */ +static inline void cfg80211_unregister_netdevice(struct net_device *dev) +{ + cfg80211_unregister_wdev(dev->ieee80211_ptr); +} + /** * struct cfg80211_ft_event_params - FT Information Elements * @ies: FT IEs -- cgit v1.2.3 From b8288837ef6bdaac331752b401f5ca3b59b37430 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 11 Dec 2020 22:12:13 -0800 Subject: devlink: Introduce PCI SF port flavour and port attribute A PCI sub-function (SF) represents a portion of the device similar to PCI VF. In an eswitch, PCI SF may have port which is normally represented using a representor netdevice. To have better visibility of eswitch port, its association with SF, and its representor netdevice, introduce a PCI SF port flavour. When devlink port flavour is PCI SF, fill up PCI SF attributes of the port. Extend port name creation using PCI PF and SF number scheme on best effort basis, so that vendor drivers can skip defining their own scheme. This is done as cApfNSfM, where A, N and M are controller, PCI PF and PCI SF number respectively. This is similar to existing naming for PCI PF and PCI VF ports. An example view of a PCI SF port: $ devlink port show pci/0000:06:00.0/32768 pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false function: hw_addr 00:00:00:00:88:88 state active opstate attached $ devlink port show pci/0000:06:00.0/32768 -jp { "port": { "pci/0000:06:00.0/32768": { "type": "eth", "netdev": "ens2f0npf0sf88", "flavour": "pcisf", "controller": 0, "pfnum": 0, "sfnum": 88, "splittable": false, "function": { "hw_addr": "00:00:00:00:88:88", "state": "active", "opstate": "attached" } } } } Signed-off-by: Parav Pandit Reviewed-by: Jiri Pirko Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- include/net/devlink.h | 16 ++++++++++++++++ include/uapi/linux/devlink.h | 5 +++++ 2 files changed, 21 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index f466819cc477..dc3bf8000082 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -93,6 +93,18 @@ struct devlink_port_pci_vf_attrs { u8 external:1; }; +/** + * struct devlink_port_pci_sf_attrs - devlink port's PCI SF attributes + * @controller: Associated controller number + * @sf: Associated PCI SF for of the PCI PF for this port. + * @pf: Associated PCI PF number for this port. + */ +struct devlink_port_pci_sf_attrs { + u32 controller; + u32 sf; + u16 pf; +}; + /** * struct devlink_port_attrs - devlink port object * @flavour: flavour of the port @@ -103,6 +115,7 @@ struct devlink_port_pci_vf_attrs { * @phys: physical port attributes * @pci_pf: PCI PF port attributes * @pci_vf: PCI VF port attributes + * @pci_sf: PCI SF port attributes */ struct devlink_port_attrs { u8 split:1, @@ -114,6 +127,7 @@ struct devlink_port_attrs { struct devlink_port_phys_attrs phys; struct devlink_port_pci_pf_attrs pci_pf; struct devlink_port_pci_vf_attrs pci_vf; + struct devlink_port_pci_sf_attrs pci_sf; }; }; @@ -1404,6 +1418,8 @@ void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 contro u16 pf, bool external); void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 controller, u16 pf, u16 vf, bool external); +void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, + u32 controller, u16 pf, u32 sf); int devlink_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, u16 egress_pools_count, u16 ingress_tc_count, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index cf89c318f2ac..1a241b09a7f8 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -200,6 +200,10 @@ enum devlink_port_flavour { DEVLINK_PORT_FLAVOUR_UNUSED, /* Port which exists in the switch, but * is not used in any way. */ + DEVLINK_PORT_FLAVOUR_PCI_SF, /* Represents eswitch port + * for the PCI SF. It is an internal + * port that faces the PCI SF. + */ }; enum devlink_param_cmode { @@ -529,6 +533,7 @@ enum devlink_attr { DEVLINK_ATTR_RELOAD_ACTION_INFO, /* nested */ DEVLINK_ATTR_RELOAD_ACTION_STATS, /* nested */ + DEVLINK_ATTR_PORT_PCI_SF_NUMBER, /* u32 */ /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, -- cgit v1.2.3 From cd76dcd68d96aa5bbc63b7ef25a87a1dbea3d73c Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 11 Dec 2020 22:12:14 -0800 Subject: devlink: Support add and delete devlink port Extended devlink interface for the user to add and delete a port. Extend devlink to connect user requests to driver to add/delete a port in the device. Driver routines are invoked without holding devlink instance lock. This enables driver to perform several devlink objects registration, unregistration such as (port, health reporter, resource etc) by using existing devlink APIs. This also helps to uniformly use the code for port unregistration during driver unload and during port deletion initiated by user. Examples of add, show and delete commands: $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev $ devlink port show pci/0000:06:00.0/65535: type eth netdev ens2f0np0 flavour physical port 0 splittable false $ devlink port add pci/0000:06:00.0 flavour pcisf pfnum 0 sfnum 88 pci/0000:06:00.0/32768: type eth netdev eth6 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false function: hw_addr 00:00:00:00:00:00 state inactive opstate detached $ devlink port show pci/0000:06:00.0/32768 pci/0000:06:00.0/32768: type eth netdev eth6 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false function: hw_addr 00:00:00:00:00:00 state inactive opstate detached $ udevadm test-builtin net_id /sys/class/net/eth6 Load module index Parsed configuration file /usr/lib/systemd/network/99-default.link Created link configuration context. Using default interface naming scheme 'v245'. ID_NET_NAMING_SCHEME=v245 ID_NET_NAME_PATH=enp6s0f0npf0sf88 ID_NET_NAME_SLOT=ens2f0npf0sf88 Unload module index Unloaded link configuration context. Signed-off-by: Parav Pandit Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- include/net/devlink.h | 52 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index dc3bf8000082..d8edd9a10907 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -152,6 +152,17 @@ struct devlink_port { struct mutex reporters_lock; /* Protects reporter_list */ }; +struct devlink_port_new_attrs { + enum devlink_port_flavour flavour; + unsigned int port_index; + u32 controller; + u32 sfnum; + u16 pfnum; + u8 port_index_valid:1, + controller_valid:1, + sfnum_valid:1; +}; + struct devlink_sb_pool_info { enum devlink_sb_pool_type pool_type; u32 size; @@ -1362,6 +1373,47 @@ struct devlink_ops { int (*port_function_hw_addr_set)(struct devlink *devlink, struct devlink_port *port, const u8 *hw_addr, int hw_addr_len, struct netlink_ext_ack *extack); + /** + * port_new() - Add a new port function of a specified flavor + * @devlink: Devlink instance + * @attrs: attributes of the new port + * @extack: extack for reporting error messages + * @new_port_index: index of the new port + * + * Devlink core will call this device driver function upon user request + * to create a new port function of a specified flavor and optional + * attributes + * + * Notes: + * - Called without devlink instance lock being held. Drivers must + * implement own means of synchronization + * - On success, drivers must register a port with devlink core + * + * Return: 0 on success, negative value otherwise. + */ + int (*port_new)(struct devlink *devlink, + const struct devlink_port_new_attrs *attrs, + struct netlink_ext_ack *extack, + unsigned int *new_port_index); + /** + * port_del() - Delete a port function + * @devlink: Devlink instance + * @port_index: port function index to delete + * @extack: extack for reporting error messages + * + * Devlink core will call this device driver function upon user request + * to delete a previously created port function + * + * Notes: + * - Called without devlink instance lock being held. Drivers must + * implement own means of synchronization + * - On success, drivers must unregister the corresponding devlink + * port + * + * Return: 0 on success, negative value otherwise. + */ + int (*port_del)(struct devlink *devlink, unsigned int port_index, + struct netlink_ext_ack *extack); }; static inline void *devlink_priv(struct devlink *devlink) -- cgit v1.2.3 From a556dded9c23c51c82654f1ebe389cbc0bc22057 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 11 Dec 2020 22:12:15 -0800 Subject: devlink: Support get and set state of port function devlink port function can be in active or inactive state. Allow users to get and set port function's state. When the port function it activated, its operational state may change after a while when the device is created and driver binds to it. Similarly on deactivation flow. To clearly describe the state of the port function and its device's operational state in the host system, define state and opstate attributes. Example of a PCI SF port which supports a port function: $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev $ devlink port show pci/0000:06:00.0/65535: type eth netdev ens2f0np0 flavour physical port 0 splittable false $ devlink port add pci/0000:06:00.0 flavour pcisf pfnum 0 sfnum 88 pci/0000:08:00.0/32768: type eth netdev eth6 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false function: hw_addr 00:00:00:00:00:00 state inactive opstate detached $ devlink port show pci/0000:06:00.0/32768 pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false function: hw_addr 00:00:00:00:88:88 state inactive opstate detached $ devlink port function set pci/0000:06:00.0/32768 hw_addr 00:00:00:00:88:88 state active $ devlink port show pci/0000:06:00.0/32768 -jp { "port": { "pci/0000:06:00.0/32768": { "type": "eth", "netdev": "ens2f0npf0sf88", "flavour": "pcisf", "controller": 0, "pfnum": 0, "sfnum": 88, "external": false, "splittable": false, "function": { "hw_addr": "00:00:00:00:88:88", "state": "active", "opstate": "attached" } } } } Signed-off-by: Parav Pandit Reviewed-by: Jiri Pirko Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- include/net/devlink.h | 32 ++++++++++++++++++++++++++++++++ include/uapi/linux/devlink.h | 20 ++++++++++++++++++++ 2 files changed, 52 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index d8edd9a10907..691ee76ca548 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1414,6 +1414,38 @@ struct devlink_ops { */ int (*port_del)(struct devlink *devlink, unsigned int port_index, struct netlink_ext_ack *extack); + /** + * port_fn_state_get() - Get the state of a port function + * @devlink: Devlink instance + * @port: The devlink port + * @state: Admin configured state + * @opstate: Current operational state + * @extack: extack for reporting error messages + * + * Reports the admin and operational state of a devlink port function + * + * Return: 0 on success, negative value otherwise. + */ + int (*port_fn_state_get)(struct devlink *devlink, + struct devlink_port *port, + enum devlink_port_fn_state *state, + enum devlink_port_fn_opstate *opstate, + struct netlink_ext_ack *extack); + /** + * port_fn_state_set() - Set the admin state of a port function + * @devlink: Devlink instance + * @port: The devlink port + * @state: Admin state + * @extack: extack for reporting error messages + * + * Set the admin state of a devlink port function + * + * Return: 0 on success, negative value otherwise. + */ + int (*port_fn_state_set)(struct devlink *devlink, + struct devlink_port *port, + enum devlink_port_fn_state state, + struct netlink_ext_ack *extack); }; static inline void *devlink_priv(struct devlink *devlink) diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 1a241b09a7f8..f6008b2fa60f 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -583,9 +583,29 @@ enum devlink_resource_unit { enum devlink_port_function_attr { DEVLINK_PORT_FUNCTION_ATTR_UNSPEC, DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, /* binary */ + DEVLINK_PORT_FN_ATTR_STATE, /* u8 */ + DEVLINK_PORT_FN_ATTR_OPSTATE, /* u8 */ __DEVLINK_PORT_FUNCTION_ATTR_MAX, DEVLINK_PORT_FUNCTION_ATTR_MAX = __DEVLINK_PORT_FUNCTION_ATTR_MAX - 1 }; +enum devlink_port_fn_state { + DEVLINK_PORT_FN_STATE_INACTIVE, + DEVLINK_PORT_FN_STATE_ACTIVE, +}; + +/** + * enum devlink_port_fn_opstate - indicates operational state of the function + * @DEVLINK_PORT_FN_OPSTATE_ATTACHED: Driver is attached to the function. + * For graceful tear down of the function, after inactivation of the + * function, user should wait for operational state to turn DETACHED. + * @DEVLINK_PORT_FN_OPSTATE_DETACHED: Driver is detached from the function. + * It is safe to delete the port. + */ +enum devlink_port_fn_opstate { + DEVLINK_PORT_FN_OPSTATE_DETACHED, + DEVLINK_PORT_FN_OPSTATE_ATTACHED, +}; + #endif /* _UAPI_LINUX_DEVLINK_H_ */ -- cgit v1.2.3 From f3196bb0f14c0ffb5089c15668bda196c98d3900 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 11 Dec 2020 22:12:16 -0800 Subject: net/mlx5: Introduce vhca state event notifier vhca state events indicates change in the state of the vhca that may occur due to a SF allocation, deallocation or enabling/disabling the SF HCA. Introduce vhca state event handler which will be used by SF devlink port manager and SF hardware id allocator in subsequent patches to act on the event. This enables single entity to subscribe, query and rearm the event for a function. Signed-off-by: Parav Pandit Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f93bfe7473aa..ffba0786051e 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -507,6 +507,7 @@ struct mlx5_devcom; struct mlx5_fw_reset; struct mlx5_eq_table; struct mlx5_irq_table; +struct mlx5_vhca_state_notifier; struct mlx5_rate_limit { u32 rate; @@ -603,6 +604,9 @@ struct mlx5_priv { struct mlx5_bfreg_data bfregs; struct mlx5_uars_page *uar; +#ifdef CONFIG_MLX5_SF + struct mlx5_vhca_state_notifier *vhca_state_notifier; +#endif }; enum mlx5_device_state { -- cgit v1.2.3 From 90d010b8634b89a97ca3b7aa6a88fd566fc77717 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 11 Dec 2020 22:12:17 -0800 Subject: net/mlx5: SF, Add auxiliary device support Introduce API to add and delete an auxiliary device for an SF. Each SF has its own dedicated window in the PCI BAR 2. SF device is similar to PCI PF and VF that supports multiple class of devices such as net, rdma and vdpa. SF device will be added or removed in subsequent patch during SF devlink port function state change command. A subfunction device exposes user supplied subfunction number which will be further used by systemd/udev to have deterministic name for its netdevice and rdma device. An mlx5 subfunction auxiliary device example: $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev $ devlink port show pci/0000:06:00.0/65535: type eth netdev ens2f0np0 flavour physical port 0 splittable false $ devlink port add pci/0000:06:00.0 flavour pcisf pfnum 0 sfnum 88 pci/0000:08:00.0/32768: type eth netdev eth6 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false function: hw_addr 00:00:00:00:00:00 state inactive opstate detached $ devlink port show ens2f0npf0sf88 pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false function: hw_addr 00:00:00:00:88:88 state inactive opstate detached $ devlink port function set ens2f0npf0sf88 hw_addr 00:00:00:00:88:88 state active On activation, $ ls -l /sys/bus/auxiliary/devices/ mlx5_core.sf.4 -> ../../../devices/pci0000:00/0000:00:03.0/0000:06:00.0/mlx5_core.sf.4 $ cat /sys/bus/auxiliary/devices/mlx5_core.sf.4/sfnum 88 Signed-off-by: Parav Pandit Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index ffba0786051e..08e5fbe97df0 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -508,6 +508,7 @@ struct mlx5_fw_reset; struct mlx5_eq_table; struct mlx5_irq_table; struct mlx5_vhca_state_notifier; +struct mlx5_sf_dev_table; struct mlx5_rate_limit { u32 rate; @@ -606,6 +607,7 @@ struct mlx5_priv { struct mlx5_uars_page *uar; #ifdef CONFIG_MLX5_SF struct mlx5_vhca_state_notifier *vhca_state_notifier; + struct mlx5_sf_dev_table *sf_dev_table; #endif }; -- cgit v1.2.3 From 1958fc2f0712ae771bfd2351b55e5a5b6b0bcfa4 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 11 Dec 2020 22:12:18 -0800 Subject: net/mlx5: SF, Add auxiliary device driver Add auxiliary device driver for mlx5 subfunction auxiliary device. A mlx5 subfunction is similar to PCI PF and VF. For a subfunction an auxiliary device is created. As a result, when mlx5 SF auxiliary device binds to the driver, its netdev and rdma device are created, they appear as $ ls -l /sys/bus/auxiliary/devices/ mlx5_core.sf.4 -> ../../../devices/pci0000:00/0000:00:03.0/0000:06:00.0/mlx5_core.sf.4 $ ls -l /sys/class/net/eth1/device /sys/class/net/eth1/device -> ../../../mlx5_core.sf.4 $ cat /sys/bus/auxiliary/devices/mlx5_core.sf.4/sfnum 88 $ devlink dev show pci/0000:06:00.0 auxiliary/mlx5_core.sf.4 $ devlink port show auxiliary/mlx5_core.sf.4/1 auxiliary/mlx5_core.sf.4/1: type eth netdev p0sf88 flavour virtual port 0 splittable false $ rdma link show mlx5_0/1 link mlx5_0/1 state ACTIVE physical_state LINK_UP netdev p0sf88 $ rdma dev show 8: rocep6s0f1: node_type ca fw 16.29.0550 node_guid 248a:0703:00b3:d113 sys_image_guid 248a:0703:00b3:d112 13: mlx5_0: node_type ca fw 16.29.0550 node_guid 0000:00ff:fe00:8888 sys_image_guid 248a:0703:00b3:d112 In future, devlink device instance name will adapt to have sfnum annotation using either an alias or as devlink instance name described in RFC [1]. [1] https://lore.kernel.org/netdev/20200519092258.GF4655@nanopsycho/ Signed-off-by: Parav Pandit Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 08e5fbe97df0..48e3638b1185 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -193,7 +193,8 @@ enum port_state_policy { enum mlx5_coredev_type { MLX5_COREDEV_PF, - MLX5_COREDEV_VF + MLX5_COREDEV_VF, + MLX5_COREDEV_SF, }; struct mlx5_field_desc { @@ -608,6 +609,7 @@ struct mlx5_priv { #ifdef CONFIG_MLX5_SF struct mlx5_vhca_state_notifier *vhca_state_notifier; struct mlx5_sf_dev_table *sf_dev_table; + struct mlx5_core_dev *parent_mdev; #endif }; -- cgit v1.2.3 From 8f01054186683fe0986d54d584aa13723d51edce Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 11 Dec 2020 22:12:21 -0800 Subject: net/mlx5: SF, Add port add delete functionality To handle SF port management outside of the eswitch as independent software layer, introduce eswitch notifier APIs so that mlx5 upper layer who wish to support sf port management in switchdev mode can perform its task whenever eswitch mode is set to switchdev or before eswitch is disabled. Initialize sf port table on such eswitch event. Add SF port add and delete functionality in switchdev mode. Destroy all SF ports when eswitch is disabled. Expose SF port add and delete to user via devlink commands. $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev $ devlink port show pci/0000:06:00.0/65535: type eth netdev ens2f0np0 flavour physical port 0 splittable false $ devlink port add pci/0000:06:00.0 flavour pcisf pfnum 0 sfnum 88 pci/0000:06:00.0/32768: type eth netdev eth6 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false function: hw_addr 00:00:00:00:00:00 state inactive opstate detached $ devlink port show ens2f0npf0sf88 pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false function: hw_addr 00:00:00:00:00:00 state inactive opstate detached or by its unique port index: $ devlink port show pci/0000:06:00.0/32768 pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false function: hw_addr 00:00:00:00:00:00 state inactive opstate detached $ devlink port show ens2f0npf0sf88 -jp { "port": { "pci/0000:06:00.0/32768": { "type": "eth", "netdev": "ens2f0npf0sf88", "flavour": "pcisf", "controller": 0, "pfnum": 0, "sfnum": 88, "external": false, "splittable": false, "function": { "hw_addr": "00:00:00:00:00:00", "state": "inactive", "opstate": "detached" } } } } Signed-off-by: Parav Pandit Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 48e3638b1185..7e357c7f0d5e 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -510,6 +510,8 @@ struct mlx5_eq_table; struct mlx5_irq_table; struct mlx5_vhca_state_notifier; struct mlx5_sf_dev_table; +struct mlx5_sf_hw_table; +struct mlx5_sf_table; struct mlx5_rate_limit { u32 rate; @@ -611,6 +613,10 @@ struct mlx5_priv { struct mlx5_sf_dev_table *sf_dev_table; struct mlx5_core_dev *parent_mdev; #endif +#ifdef CONFIG_MLX5_SF_MANAGER + struct mlx5_sf_hw_table *sf_hw_table; + struct mlx5_sf_table *sf_table; +#endif }; enum mlx5_device_state { -- cgit v1.2.3 From a05a7280f5453ed24c2001eb66b359776ab18cb5 Mon Sep 17 00:00:00 2001 From: Pengcheng Yang Date: Thu, 21 Jan 2021 22:31:13 +0800 Subject: tcp: remove unused ICSK_TIME_EARLY_RETRANS Since the early retransmit has been removed by commit bec41a11dd3d ("tcp: remove early retransmit"), we also remove the unused ICSK_TIME_EARLY_RETRANS macro. Signed-off-by: Pengcheng Yang Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/1611239473-27304-1-git-send-email-yangpc@wangsu.com Signed-off-by: Jakub Kicinski --- include/net/inet_connection_sock.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 111d7771b208..c11f80f328f1 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -141,7 +141,6 @@ struct inet_connection_sock { #define ICSK_TIME_RETRANS 1 /* Retransmit timer */ #define ICSK_TIME_DACK 2 /* Delayed ack timer */ #define ICSK_TIME_PROBE0 3 /* Zero window probe timer */ -#define ICSK_TIME_EARLY_RETRANS 4 /* Early retransmit timer */ #define ICSK_TIME_LOSS_PROBE 5 /* Tail loss probe timer */ #define ICSK_TIME_REO_TIMEOUT 6 /* Reordering timer */ @@ -227,8 +226,7 @@ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what, } if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0 || - what == ICSK_TIME_EARLY_RETRANS || what == ICSK_TIME_LOSS_PROBE || - what == ICSK_TIME_REO_TIMEOUT) { + what == ICSK_TIME_LOSS_PROBE || what == ICSK_TIME_REO_TIMEOUT) { icsk->icsk_pending = what; icsk->icsk_timeout = jiffies + when; sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout); -- cgit v1.2.3 From e7ed11ee945438b737e2ae2370e35591e16ec371 Mon Sep 17 00:00:00 2001 From: Yousuk Seung Date: Wed, 20 Jan 2021 12:41:55 -0800 Subject: tcp: add TTL to SCM_TIMESTAMPING_OPT_STATS This patch adds TCP_NLA_TTL to SCM_TIMESTAMPING_OPT_STATS that exports the time-to-live or hop limit of the latest incoming packet with SCM_TSTAMP_ACK. The value exported may not be from the packet that acks the sequence when incoming packets are aggregated. Exporting the time-to-live or hop limit value of incoming packets helps to estimate the hop count of the path of the flow that may change over time. Signed-off-by: Yousuk Seung Signed-off-by: Eric Dumazet Signed-off-by: Neal Cardwell Link: https://lore.kernel.org/r/20210120204155.552275-1-ysseung@google.com Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 2 +- include/linux/tcp.h | 3 ++- include/uapi/linux/tcp.h | 1 + 3 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 186dad231e30..9313b5aaf45b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3859,7 +3859,7 @@ static inline bool skb_defer_rx_timestamp(struct sk_buff *skb) void skb_complete_tx_timestamp(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps); -void __skb_tstamp_tx(struct sk_buff *orig_skb, +void __skb_tstamp_tx(struct sk_buff *orig_skb, const struct sk_buff *ack_skb, struct skb_shared_hwtstamps *hwtstamps, struct sock *sk, int tstype); diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 2f87377e9af7..48d8a363319e 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -496,7 +496,8 @@ static inline u32 tcp_saved_syn_len(const struct saved_syn *saved_syn) } struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, - const struct sk_buff *orig_skb); + const struct sk_buff *orig_skb, + const struct sk_buff *ack_skb); static inline u16 tcp_mss_clamp(const struct tcp_sock *tp, u16 mss) { diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 768e93bd5b51..16dfa40bdac3 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -314,6 +314,7 @@ enum { TCP_NLA_TIMEOUT_REHASH, /* Timeout-triggered rehash attempts */ TCP_NLA_BYTES_NOTSENT, /* Bytes in write queue not yet sent */ TCP_NLA_EDT, /* Earliest departure time (CLOCK_MONOTONIC) */ + TCP_NLA_TTL, /* TTL or hop limit of a packet received */ }; /* for TCP_MD5SIG socket option */ -- cgit v1.2.3 From 7eeba1706eba6def15f6cb2fc7b3c3b9a2651edc Mon Sep 17 00:00:00 2001 From: Arjun Roy Date: Wed, 20 Jan 2021 16:41:48 -0800 Subject: tcp: Add receive timestamp support for receive zerocopy. tcp_recvmsg() uses the CMSG mechanism to receive control information like packet receive timestamps. This patch adds CMSG fields to struct tcp_zerocopy_receive, and provides receive timestamps if available to the user. Signed-off-by: Arjun Roy Signed-off-by: Jakub Kicinski --- include/uapi/linux/tcp.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 16dfa40bdac3..42fc5a640df4 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -354,5 +354,9 @@ struct tcp_zerocopy_receive { __u64 copybuf_address; /* in: copybuf address (small reads) */ __s32 copybuf_len; /* in/out: copybuf bytes avail/used or error */ __u32 flags; /* in: flags */ + __u64 msg_control; /* ancillary data */ + __u64 msg_controllen; + __u32 msg_flags; + /* __u32 hole; Next we must add >1 u32 otherwise length checks fail. */ }; #endif /* _UAPI_LINUX_TCP_H */ -- cgit v1.2.3 From ca1e4ab199933e1af3f9a86d31060b7f9181c3fc Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Tue, 19 Jan 2021 14:08:11 +0200 Subject: net: sched: Add multi-queue support to sch_tree_lock The existing qdiscs that set TCQ_F_MQROOT don't use sch_tree_lock. However, hardware-offloaded HTB will start setting this flag while also using sch_tree_lock. The current implementation of sch_tree_lock basically locks on qdisc->dev_queue->qdisc, and it works fine when the tree is attached to some queue. However, it's not the case for MQROOT qdiscs: such a qdisc is the root itself, and its dev_queue just points to queue 0, while not actually being used, because there are real per-queue qdiscs. This patch changes the logic of sch_tree_lock and sch_tree_unlock to lock the qdisc itself if it's the MQROOT. Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Signed-off-by: Jakub Kicinski --- include/net/sch_generic.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index e7bee99aebce..296919010552 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -552,14 +552,20 @@ static inline struct net_device *qdisc_dev(const struct Qdisc *qdisc) return qdisc->dev_queue->dev; } -static inline void sch_tree_lock(const struct Qdisc *q) +static inline void sch_tree_lock(struct Qdisc *q) { - spin_lock_bh(qdisc_root_sleeping_lock(q)); + if (q->flags & TCQ_F_MQROOT) + spin_lock_bh(qdisc_lock(q)); + else + spin_lock_bh(qdisc_root_sleeping_lock(q)); } -static inline void sch_tree_unlock(const struct Qdisc *q) +static inline void sch_tree_unlock(struct Qdisc *q) { - spin_unlock_bh(qdisc_root_sleeping_lock(q)); + if (q->flags & TCQ_F_MQROOT) + spin_unlock_bh(qdisc_lock(q)); + else + spin_unlock_bh(qdisc_root_sleeping_lock(q)); } extern struct Qdisc noop_qdisc; -- cgit v1.2.3 From 4dd78a73738afa92d33a226ec477b42938b31c83 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Tue, 19 Jan 2021 14:08:12 +0200 Subject: net: sched: Add extack to Qdisc_class_ops.delete In a following commit, sch_htb will start using extack in the delete class operation to pass hardware errors in offload mode. This commit prepares for that by adding the extack parameter to this callback and converting usage of the existing qdiscs. Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Signed-off-by: Jakub Kicinski --- include/net/sch_generic.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 296919010552..070f01bf17eb 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -210,7 +210,8 @@ struct Qdisc_class_ops { int (*change)(struct Qdisc *, u32, u32, struct nlattr **, unsigned long *, struct netlink_ext_ack *); - int (*delete)(struct Qdisc *, unsigned long); + int (*delete)(struct Qdisc *, unsigned long, + struct netlink_ext_ack *); void (*walk)(struct Qdisc *, struct qdisc_walker * arg); /* Filter manipulation */ -- cgit v1.2.3 From d03b195b5aa015f6c11988b86a3625f8d5dbac52 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Tue, 19 Jan 2021 14:08:13 +0200 Subject: sch_htb: Hierarchical QoS hardware offload HTB doesn't scale well because of contention on a single lock, and it also consumes CPU. This patch adds support for offloading HTB to hardware that supports hierarchical rate limiting. In the offload mode, HTB passes control commands to the driver using ndo_setup_tc. The driver has to replicate the whole hierarchy of classes and their settings (rate, ceil) in the NIC. Every modification of the HTB tree caused by the admin results in ndo_setup_tc being called. After this setup, the HTB algorithm is done completely in the NIC. An SQ (send queue) is created for every leaf class and attached to the hierarchy, so that the NIC can calculate and obey aggregated rate limits, too. In the future, it can be changed, so that multiple SQs will back a single leaf class. ndo_select_queue is responsible for selecting the right queue that serves the traffic class of each packet. The data path works as follows: a packet is classified by clsact, the driver selects a hardware queue according to its class, and the packet is enqueued into this queue's qdisc. This solution addresses two main problems of scaling HTB: 1. Contention by flow classification. Currently the filters are attached to the HTB instance as follows: # tc filter add dev eth0 parent 1:0 protocol ip flower dst_port 80 classid 1:10 It's possible to move classification to clsact egress hook, which is thread-safe and lock-free: # tc filter add dev eth0 egress protocol ip flower dst_port 80 action skbedit priority 1:10 This way classification still happens in software, but the lock contention is eliminated, and it happens before selecting the TX queue, allowing the driver to translate the class to the corresponding hardware queue in ndo_select_queue. Note that this is already compatible with non-offloaded HTB and doesn't require changes to the kernel nor iproute2. 2. Contention by handling packets. HTB is not multi-queue, it attaches to a whole net device, and handling of all packets takes the same lock. When HTB is offloaded, it registers itself as a multi-queue qdisc, similarly to mq: HTB is attached to the netdev, and each queue has its own qdisc. Some features of HTB may be not supported by some particular hardware, for example, the maximum number of classes may be limited, the granularity of rate and ceil parameters may be different, etc. - so, the offload is not enabled by default, a new parameter is used to enable it: # tc qdisc replace dev eth0 root handle 1: htb offload Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 1 + include/net/pkt_cls.h | 36 ++++++++++++++++++++++++++++++++++++ include/uapi/linux/pkt_sched.h | 1 + 3 files changed, 38 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ef517254367d..9e8572533d8e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -858,6 +858,7 @@ enum tc_setup_type { TC_SETUP_QDISC_ETS, TC_SETUP_QDISC_TBF, TC_SETUP_QDISC_FIFO, + TC_SETUP_QDISC_HTB, }; /* These structures hold the attributes of bpf state that are being passed diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 0f2a9c44171c..255e4f4b521f 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -783,6 +783,42 @@ struct tc_mq_qopt_offload { }; }; +enum tc_htb_command { + /* Root */ + TC_HTB_CREATE, /* Initialize HTB offload. */ + TC_HTB_DESTROY, /* Destroy HTB offload. */ + + /* Classes */ + /* Allocate qid and create leaf. */ + TC_HTB_LEAF_ALLOC_QUEUE, + /* Convert leaf to inner, preserve and return qid, create new leaf. */ + TC_HTB_LEAF_TO_INNER, + /* Delete leaf, while siblings remain. */ + TC_HTB_LEAF_DEL, + /* Delete leaf, convert parent to leaf, preserving qid. */ + TC_HTB_LEAF_DEL_LAST, + /* TC_HTB_LEAF_DEL_LAST, but delete driver data on hardware errors. */ + TC_HTB_LEAF_DEL_LAST_FORCE, + /* Modify parameters of a node. */ + TC_HTB_NODE_MODIFY, + + /* Class qdisc */ + TC_HTB_LEAF_QUERY_QUEUE, /* Query qid by classid. */ +}; + +struct tc_htb_qopt_offload { + struct netlink_ext_ack *extack; + enum tc_htb_command command; + u16 classid; + u32 parent_classid; + u16 qid; + u16 moved_qid; + u64 rate; + u64 ceil; +}; + +#define TC_HTB_CLASSID_ROOT U32_MAX + enum tc_red_command { TC_RED_REPLACE, TC_RED_DESTROY, diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 9e7c2c607845..79a699f106b1 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -434,6 +434,7 @@ enum { TCA_HTB_RATE64, TCA_HTB_CEIL64, TCA_HTB_PAD, + TCA_HTB_OFFLOAD, __TCA_HTB_MAX, }; -- cgit v1.2.3 From 214baf22870cfa437522f3bd4fbae56338674b04 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Tue, 19 Jan 2021 14:08:15 +0200 Subject: net/mlx5e: Support HTB offload This commit adds support for HTB offload in the mlx5e driver. Performance: NIC: Mellanox ConnectX-6 Dx CPU: Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz (24 cores with HT) 100 Gbit/s line rate, 500 UDP streams @ ~200 Mbit/s each 48 traffic classes, flower used for steering No shaping (rate limits set to 4 Gbit/s per TC) - checking for max throughput. Baseline: 98.7 Gbps, 8.25 Mpps HTB: 6.7 Gbps, 0.56 Mpps HTB offload: 95.6 Gbps, 8.00 Mpps Limitations: 1. 256 leaf nodes, 3 levels of depth. 2. Granularity for ceil is 1 Mbit/s. Rates are converted to weights, and the bandwidth is split among the siblings according to these weights. Other parameters for classes are not supported. Ethtool statistics support for QoS SQs are also added. The counters are called qos_txN_*, where N is the QoS queue number (starting from 0, the numeration is separate from the normal SQs), and * is the counter name (the counters are the same as for the normal SQs). Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Signed-off-by: Jakub Kicinski --- include/linux/mlx5/mlx5_ifc.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 823411e288c0..71ae6aac3410 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -842,11 +842,16 @@ struct mlx5_ifc_qos_cap_bits { u8 reserved_at_4[0x1]; u8 packet_pacing_burst_bound[0x1]; u8 packet_pacing_typical_size[0x1]; - u8 reserved_at_7[0x4]; + u8 reserved_at_7[0x1]; + u8 nic_sq_scheduling[0x1]; + u8 nic_bw_share[0x1]; + u8 nic_rate_limit[0x1]; u8 packet_pacing_uid[0x1]; u8 reserved_at_c[0x14]; - u8 reserved_at_20[0x20]; + u8 reserved_at_20[0xb]; + u8 log_max_qos_nic_queue_group[0x5]; + u8 reserved_at_30[0x10]; u8 packet_pacing_max_rate[0x20]; @@ -3347,7 +3352,7 @@ struct mlx5_ifc_sqc_bits { u8 reserved_at_e0[0x10]; u8 packet_pacing_rate_limit_index[0x10]; u8 tis_lst_sz[0x10]; - u8 reserved_at_110[0x10]; + u8 qos_queue_group_id[0x10]; u8 reserved_at_120[0x40]; @@ -3362,6 +3367,7 @@ enum { SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT = 0x1, SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC = 0x2, SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC = 0x3, + SCHEDULING_CONTEXT_ELEMENT_TYPE_QUEUE_GROUP = 0x4, }; enum { @@ -4805,6 +4811,7 @@ struct mlx5_ifc_query_scheduling_element_out_bits { enum { SCHEDULING_HIERARCHY_E_SWITCH = 0x2, + SCHEDULING_HIERARCHY_NIC = 0x3, }; struct mlx5_ifc_query_scheduling_element_in_bits { -- cgit v1.2.3 From 321f7ab0d45899fe0313139822d69c2d5adbb760 Mon Sep 17 00:00:00 2001 From: Danielle Ratson Date: Thu, 21 Jan 2021 15:10:23 +0200 Subject: mlxsw: Register physical ports as a devlink resource The switch ASIC has a limited capacity of physical ('flavour physical' in devlink terminology) ports that it can support. While each system is brought up with a different number of ports, this number can be increased via splitting up to the ASIC's limit. Expose physical ports as a devlink resource so that user space will have visibility to the maximum number of ports that can be supported and the current occupancy. In addition, add a "Generic Resources" section in devlink-resource documentation so the different drivers will be aligned by the same resource name when exposing to user space. Signed-off-by: Danielle Ratson Reviewed-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index f466819cc477..d12ed2854c34 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -380,6 +380,8 @@ struct devlink_resource { #define DEVLINK_RESOURCE_ID_PARENT_TOP 0 +#define DEVLINK_RESOURCE_GENERIC_NAME_PORTS "physical_ports" + #define __DEVLINK_PARAM_MAX_STRING_VALUE 32 enum devlink_param_type { DEVLINK_PARAM_TYPE_U8, -- cgit v1.2.3 From 6f1c0ea133a6e4a193a7b285efe209664caeea43 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Fri, 22 Jan 2021 18:19:48 +0000 Subject: net: introduce a netdev feature for UDP GRO forwarding Introduce a new netdev feature, NETIF_F_GRO_UDP_FWD, to allow user to turn UDP GRO on and off for forwarding. Defaults to off to not change current datapath. Suggested-by: Paolo Abeni Signed-off-by: Alexander Lobakin Signed-off-by: Jakub Kicinski --- include/linux/netdev_features.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 934de56644e7..c06d6aaba9df 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -84,6 +84,7 @@ enum { NETIF_F_GRO_FRAGLIST_BIT, /* Fraglist GRO */ NETIF_F_HW_MACSEC_BIT, /* Offload MACsec operations */ + NETIF_F_GRO_UDP_FWD_BIT, /* Allow UDP GRO for forwarding */ /* * Add your fresh new feature above and remember to update @@ -157,6 +158,7 @@ enum { #define NETIF_F_GRO_FRAGLIST __NETIF_F(GRO_FRAGLIST) #define NETIF_F_GSO_FRAGLIST __NETIF_F(GSO_FRAGLIST) #define NETIF_F_HW_MACSEC __NETIF_F(HW_MACSEC) +#define NETIF_F_GRO_UDP_FWD __NETIF_F(GRO_UDP_FWD) /* Finds the next feature with the highest number of the range of start till 0. */ @@ -234,7 +236,7 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) #define NETIF_F_SOFT_FEATURES (NETIF_F_GSO | NETIF_F_GRO) /* Changeable features with no special hardware requirements that defaults to off. */ -#define NETIF_F_SOFT_FEATURES_OFF NETIF_F_GRO_FRAGLIST +#define NETIF_F_SOFT_FEATURES_OFF (NETIF_F_GRO_FRAGLIST | NETIF_F_GRO_UDP_FWD) #define NETIF_F_VLAN_FEATURES (NETIF_F_HW_VLAN_CTAG_FILTER | \ NETIF_F_HW_VLAN_CTAG_RX | \ -- cgit v1.2.3 From b4a221ea8a1f890b50838ef389d016c7ff280abc Mon Sep 17 00:00:00 2001 From: Archie Pusaka Date: Fri, 22 Jan 2021 16:36:11 +0800 Subject: Bluetooth: advmon offload MSFT add rssi support MSFT needs rssi parameter for monitoring advertisement packet, therefore we should supply them from mgmt. This adds a new opcode to add advertisement monitor with rssi parameters. Signed-off-by: Archie Pusaka Reviewed-by: Manish Mandlik Reviewed-by: Miao-chen Chou Reviewed-by: Yun-Hao Chung Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 9 +++++++++ include/net/bluetooth/mgmt.h | 16 ++++++++++++++++ 2 files changed, 25 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 677a8c50b2ad..8b7cf3620938 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -250,8 +250,17 @@ struct adv_pattern { __u8 value[HCI_MAX_AD_LENGTH]; }; +struct adv_rssi_thresholds { + __s8 low_threshold; + __s8 high_threshold; + __u16 low_threshold_timeout; + __u16 high_threshold_timeout; + __u8 sampling_period; +}; + struct adv_monitor { struct list_head patterns; + struct adv_rssi_thresholds rssi; bool active; __u16 handle; }; diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index f9a6638e20b3..839a2028009e 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -821,6 +821,22 @@ struct mgmt_rp_add_ext_adv_data { __u8 instance; } __packed; +struct mgmt_adv_rssi_thresholds { + __s8 high_threshold; + __le16 high_threshold_timeout; + __s8 low_threshold; + __le16 low_threshold_timeout; + __u8 sampling_period; +} __packed; + +#define MGMT_OP_ADD_ADV_PATTERNS_MONITOR_RSSI 0x0056 +struct mgmt_cp_add_adv_patterns_monitor_rssi { + struct mgmt_adv_rssi_thresholds rssi; + __u8 pattern_count; + struct mgmt_adv_pattern patterns[]; +} __packed; +#define MGMT_ADD_ADV_PATTERNS_MONITOR_RSSI_SIZE 8 + #define MGMT_EV_CMD_COMPLETE 0x0001 struct mgmt_ev_cmd_complete { __le16 opcode; -- cgit v1.2.3 From a2a4dedf88ab2f807a7ca90947d686816b430f97 Mon Sep 17 00:00:00 2001 From: Archie Pusaka Date: Fri, 22 Jan 2021 16:36:12 +0800 Subject: Bluetooth: advmon offload MSFT add monitor Enables advertising monitor offloading to the controller, if MSFT extension is supported. The kernel won't adjust the monitor parameters to match what the controller supports - that is the user space's responsibility. This patch only manages the addition of monitors. Monitor removal is going to be handled by another patch. Signed-off-by: Archie Pusaka Reviewed-by: Manish Mandlik Reviewed-by: Miao-chen Chou Reviewed-by: Yun-Hao Chung Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 8b7cf3620938..879d1e38ce96 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -261,13 +261,20 @@ struct adv_rssi_thresholds { struct adv_monitor { struct list_head patterns; struct adv_rssi_thresholds rssi; - bool active; __u16 handle; + + enum { + ADV_MONITOR_STATE_NOT_REGISTERED, + ADV_MONITOR_STATE_REGISTERED, + ADV_MONITOR_STATE_OFFLOADED + } state; }; #define HCI_MIN_ADV_MONITOR_HANDLE 1 -#define HCI_MAX_ADV_MONITOR_NUM_HANDLES 32 +#define HCI_MAX_ADV_MONITOR_NUM_HANDLES 32 #define HCI_MAX_ADV_MONITOR_NUM_PATTERNS 16 +#define HCI_ADV_MONITOR_EXT_NONE 1 +#define HCI_ADV_MONITOR_EXT_MSFT 2 #define HCI_MAX_SHORT_NAME_LENGTH 10 @@ -1326,9 +1333,12 @@ void hci_adv_instances_set_rpa_expired(struct hci_dev *hdev, bool rpa_expired); void hci_adv_monitors_clear(struct hci_dev *hdev); void hci_free_adv_monitor(struct adv_monitor *monitor); -int hci_add_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor); +int hci_add_adv_patterns_monitor_complete(struct hci_dev *hdev, u8 status); +bool hci_add_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor, + int *err); int hci_remove_adv_monitor(struct hci_dev *hdev, u16 handle); bool hci_is_adv_monitoring(struct hci_dev *hdev); +int hci_get_adv_monitor_offload_ext(struct hci_dev *hdev); void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb); @@ -1804,6 +1814,7 @@ void mgmt_advertising_added(struct sock *sk, struct hci_dev *hdev, void mgmt_advertising_removed(struct sock *sk, struct hci_dev *hdev, u8 instance); int mgmt_phy_configuration_changed(struct hci_dev *hdev, struct sock *skip); +int mgmt_add_adv_patterns_monitor_complete(struct hci_dev *hdev, u8 status); u8 hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, u16 to_multiplier); -- cgit v1.2.3 From 66bd095ab5d408af106808cce302406542f70f65 Mon Sep 17 00:00:00 2001 From: Archie Pusaka Date: Fri, 22 Jan 2021 16:36:13 +0800 Subject: Bluetooth: advmon offload MSFT remove monitor Implements the monitor removal functionality for advertising monitor offloading to MSFT controllers. Supply handle = 0 to remove all monitors. Signed-off-by: Archie Pusaka Reviewed-by: Miao-chen Chou Reviewed-by: Yun-Hao Chung Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 879d1e38ce96..29cfc6a2d689 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1332,11 +1332,13 @@ int hci_remove_adv_instance(struct hci_dev *hdev, u8 instance); void hci_adv_instances_set_rpa_expired(struct hci_dev *hdev, bool rpa_expired); void hci_adv_monitors_clear(struct hci_dev *hdev); -void hci_free_adv_monitor(struct adv_monitor *monitor); +void hci_free_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor); int hci_add_adv_patterns_monitor_complete(struct hci_dev *hdev, u8 status); +int hci_remove_adv_monitor_complete(struct hci_dev *hdev, u8 status); bool hci_add_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor, int *err); -int hci_remove_adv_monitor(struct hci_dev *hdev, u16 handle); +bool hci_remove_single_adv_monitor(struct hci_dev *hdev, u16 handle, int *err); +bool hci_remove_all_adv_monitor(struct hci_dev *hdev, int *err); bool hci_is_adv_monitoring(struct hci_dev *hdev); int hci_get_adv_monitor_offload_ext(struct hci_dev *hdev); @@ -1813,8 +1815,10 @@ void mgmt_advertising_added(struct sock *sk, struct hci_dev *hdev, u8 instance); void mgmt_advertising_removed(struct sock *sk, struct hci_dev *hdev, u8 instance); +void mgmt_adv_monitor_removed(struct hci_dev *hdev, u16 handle); int mgmt_phy_configuration_changed(struct hci_dev *hdev, struct sock *skip); int mgmt_add_adv_patterns_monitor_complete(struct hci_dev *hdev, u8 status); +int mgmt_remove_adv_monitor_complete(struct hci_dev *hdev, u8 status); u8 hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, u16 to_multiplier); -- cgit v1.2.3 From bf6a4e30ffbd9e9ef8934582feb937f6532f8b68 Mon Sep 17 00:00:00 2001 From: Howard Chung Date: Fri, 22 Jan 2021 16:36:17 +0800 Subject: Bluetooth: disable advertisement filters during suspend This adds logic to disable and reenable advertisement filters during suspend and resume. After this patch, we would only receive packets from devices in allow list during suspend. Signed-off-by: Howard Chung Reviewed-by: Abhishek Pandit-Subedi Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 29cfc6a2d689..fd1d10fe2f11 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -105,6 +105,8 @@ enum suspend_tasks { SUSPEND_POWERING_DOWN, SUSPEND_PREPARE_NOTIFIER, + + SUSPEND_SET_ADV_FILTER, __SUSPEND_NUM_TASKS }; -- cgit v1.2.3 From 4d7ea8ee90e42fc75995f6fb24032d3233314528 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Wed, 13 Jan 2021 15:28:58 -0800 Subject: Bluetooth: L2CAP: Fix handling fragmented length Bluetooth Core Specification v5.2, Vol. 3, Part A, section 1.4, table 1.1: 'Start Fragments always either begin with the first octet of the Basic L2CAP header of a PDU or they have a length of zero (see [Vol 2] Part B, Section 6.6.2).' Apparently this was changed by the following errata: https://www.bluetooth.org/tse/errata_view.cfm?errata_id=10216 Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Marcel Holtmann --- include/net/bluetooth/l2cap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 1d1232917de7..61800a7b6192 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -207,6 +207,7 @@ struct l2cap_hdr { __le16 len; __le16 cid; } __packed; +#define L2CAP_LEN_SIZE 2 #define L2CAP_HDR_SIZE 4 #define L2CAP_ENH_HDR_SIZE 6 #define L2CAP_EXT_HDR_SIZE 8 -- cgit v1.2.3 From 83ace77f51175023c3757e2d08a92565f9b1c7f3 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 20 Jan 2021 16:30:03 +0100 Subject: netfilter: ctnetlink: remove get_ct indirection Use nf_ct_get() directly, its a small inline helper without dependencies. Add CONFIG_NF_CONNTRACK guards to elide the relevant part when conntrack isn't available at all. v2: add ifdef guard around nf_ct_get call (kernel test robot) Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 0101747de549..f0f3a8354c3c 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -463,8 +463,6 @@ extern struct nf_ct_hook __rcu *nf_ct_hook; struct nlattr; struct nfnl_ct_hook { - struct nf_conn *(*get_ct)(const struct sk_buff *skb, - enum ip_conntrack_info *ctinfo); size_t (*build_size)(const struct nf_conn *ct); int (*build)(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, -- cgit v1.2.3 From dbc859d96f1a90bafe9c3ba2e437aae5d5677318 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 25 Jan 2021 18:56:01 +0100 Subject: netfilter: flowtable: add hash offset field to tuple Add a placeholder field to calculate hash tuple offset. Similar to 2c407aca6497 ("netfilter: conntrack: avoid gcc-10 zero-length-bounds warning"). Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_flow_table.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 16e8b2f8d006..54c4d5c908a5 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -107,6 +107,10 @@ struct flow_offload_tuple { u8 l3proto; u8 l4proto; + + /* All members above are keys for lookups, see flow_offload_hash(). */ + struct { } __hash; + u8 dir; u16 mtu; -- cgit v1.2.3 From a05829a7222e9d10c416dd2dbbf3929fe6646b89 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 22 Jan 2021 16:19:43 +0100 Subject: cfg80211: avoid holding the RTNL when calling the driver Currently, _everything_ in cfg80211 holds the RTNL, and if you have a slow USB device (or a few) you can get some bad lock contention on that. Fix that by re-adding a mutex to each wiphy/rdev as we had at some point, so we have locking for the wireless_dev lists and all the other things in there, and also so that drivers still don't have to worry too much about it (they still won't get parallel calls for a single device). Then, we can restrict the RTNL to a few cases where we add or remove interfaces and really need the added protection. Some of the global list management still also uses the RTNL, since we need to have it anyway for netdev management, but we only hold the RTNL for very short periods of time here. Link: https://lore.kernel.org/r/20210122161942.81df9f5e047a.I4a8e1a60b18863ea8c5e6d3a0faeafb2d45b2f40@changeid Tested-by: Marek Szyprowski [marvell driver issues] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 104 ++++++++++++++++++++++++++++++++++++++++++------- include/net/mac80211.h | 10 ++--- 2 files changed, 94 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index e7703fdbac8d..4741d71ead21 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -3632,9 +3632,10 @@ struct mgmt_frame_regs { * All callbacks except where otherwise noted should return 0 * on success or a negative error code. * - * All operations are currently invoked under rtnl for consistency with the - * wireless extensions but this is subject to reevaluation as soon as this - * code is used more widely and we have a first user without wext. + * All operations are invoked with the wiphy mutex held. The RTNL may be + * held in addition (due to wireless extensions) but this cannot be relied + * upon except in cases where documented below. Note that due to ordering, + * the RTNL also cannot be acquired in any handlers. * * @suspend: wiphy device needs to be suspended. The variable @wow will * be %NULL or contain the enabled Wake-on-Wireless triggers that are @@ -3649,11 +3650,14 @@ struct mgmt_frame_regs { * the new netdev in the wiphy's network namespace! Returns the struct * wireless_dev, or an ERR_PTR. For P2P device wdevs, the driver must * also set the address member in the wdev. + * This additionally holds the RTNL to be able to do netdev changes. * * @del_virtual_intf: remove the virtual interface + * This additionally holds the RTNL to be able to do netdev changes. * * @change_virtual_intf: change type/configuration of virtual interface, * keep the struct wireless_dev's iftype updated. + * This additionally holds the RTNL to be able to do netdev changes. * * @add_key: add a key with the given parameters. @mac_addr will be %NULL * when adding a group key. @@ -4743,6 +4747,7 @@ struct wiphy_iftype_akm_suites { /** * struct wiphy - wireless hardware description + * @mtx: mutex for the data (structures) of this device * @reg_notifier: the driver's regulatory notification callback, * note that if your driver uses wiphy_apply_custom_regulatory() * the reg_notifier's request can be passed as NULL @@ -4936,6 +4941,8 @@ struct wiphy_iftype_akm_suites { * @sar_capa: SAR control capabilities */ struct wiphy { + struct mutex mtx; + /* assign these fields before you register the wiphy */ u8 perm_addr[ETH_ALEN]; @@ -5188,6 +5195,37 @@ static inline struct wiphy *wiphy_new(const struct cfg80211_ops *ops, */ int wiphy_register(struct wiphy *wiphy); +/* this is a define for better error reporting (file/line) */ +#define lockdep_assert_wiphy(wiphy) lockdep_assert_held(&(wiphy)->mtx) + +/** + * rcu_dereference_wiphy - rcu_dereference with debug checking + * @wiphy: the wiphy to check the locking on + * @p: The pointer to read, prior to dereferencing + * + * Do an rcu_dereference(p), but check caller either holds rcu_read_lock() + * or RTNL. Note: Please prefer wiphy_dereference() or rcu_dereference(). + */ +#define rcu_dereference_wiphy(wiphy, p) \ + rcu_dereference_check(p, lockdep_is_held(&wiphy->mtx)) + +/** + * wiphy_dereference - fetch RCU pointer when updates are prevented by wiphy mtx + * @wiphy: the wiphy to check the locking on + * @p: The pointer to read, prior to dereferencing + * + * Return the value of the specified RCU-protected pointer, but omit the + * READ_ONCE(), because caller holds the wiphy mutex used for updates. + */ +#define wiphy_dereference(wiphy, p) \ + rcu_dereference_protected(p, lockdep_is_held(&wiphy->mtx)) + +/** + * get_wiphy_regdom - get custom regdomain for the given wiphy + * @wiphy: the wiphy to get the regdomain from + */ +const struct ieee80211_regdomain *get_wiphy_regdom(struct wiphy *wiphy); + /** * wiphy_unregister - deregister a wiphy from cfg80211 * @@ -5212,6 +5250,35 @@ struct cfg80211_internal_bss; struct cfg80211_cached_keys; struct cfg80211_cqm_config; +/** + * wiphy_lock - lock the wiphy + * @wiphy: the wiphy to lock + * + * This is mostly exposed so it can be done around registering and + * unregistering netdevs that aren't created through cfg80211 calls, + * since that requires locking in cfg80211 when the notifiers is + * called, but that cannot differentiate which way it's called. + * + * When cfg80211 ops are called, the wiphy is already locked. + */ +static inline void wiphy_lock(struct wiphy *wiphy) + __acquires(&wiphy->mtx) +{ + mutex_lock(&wiphy->mtx); + __acquire(&wiphy->mtx); +} + +/** + * wiphy_unlock - unlock the wiphy again + * @wiphy: the wiphy to unlock + */ +static inline void wiphy_unlock(struct wiphy *wiphy) + __releases(&wiphy->mtx) +{ + __release(&wiphy->mtx); + mutex_unlock(&wiphy->mtx); +} + /** * struct wireless_dev - wireless device state * @@ -5219,7 +5286,10 @@ struct cfg80211_cqm_config; * that uses the ieee80211_ptr field in struct net_device (this * is intentional so it can be allocated along with the netdev.) * It need not be registered then as netdev registration will - * be intercepted by cfg80211 to see the new wireless device. + * be intercepted by cfg80211 to see the new wireless device, + * however, drivers must lock the wiphy before registering or + * unregistering netdevs if they pre-create any netdevs (in ops + * called from cfg80211, the wiphy is already locked.) * * For non-netdev uses, it must also be allocated by the driver * in response to the cfg80211 callbacks that require it, as @@ -5981,18 +6051,18 @@ int regulatory_set_wiphy_regd(struct wiphy *wiphy, struct ieee80211_regdomain *rd); /** - * regulatory_set_wiphy_regd_sync_rtnl - set regdom for self-managed drivers + * regulatory_set_wiphy_regd_sync - set regdom for self-managed drivers * @wiphy: the wireless device we want to process the regulatory domain on * @rd: the regulatory domain information to use for this wiphy * - * This functions requires the RTNL to be held and applies the new regdomain - * synchronously to this wiphy. For more details see - * regulatory_set_wiphy_regd(). + * This functions requires the RTNL and the wiphy mutex to be held and + * applies the new regdomain synchronously to this wiphy. For more details + * see regulatory_set_wiphy_regd(). * * Return: 0 on success. -EINVAL, -EPERM */ -int regulatory_set_wiphy_regd_sync_rtnl(struct wiphy *wiphy, - struct ieee80211_regdomain *rd); +int regulatory_set_wiphy_regd_sync(struct wiphy *wiphy, + struct ieee80211_regdomain *rd); /** * wiphy_apply_custom_regulatory - apply a custom driver regulatory domain @@ -6110,7 +6180,7 @@ void cfg80211_sched_scan_results(struct wiphy *wiphy, u64 reqid); void cfg80211_sched_scan_stopped(struct wiphy *wiphy, u64 reqid); /** - * cfg80211_sched_scan_stopped_rtnl - notify that the scheduled scan has stopped + * cfg80211_sched_scan_stopped_locked - notify that the scheduled scan has stopped * * @wiphy: the wiphy on which the scheduled scan stopped * @reqid: identifier for the related scheduled scan request @@ -6118,9 +6188,9 @@ void cfg80211_sched_scan_stopped(struct wiphy *wiphy, u64 reqid); * The driver can call this function to inform cfg80211 that the * scheduled scan had to be stopped, for whatever reason. The driver * is then called back via the sched_scan_stop operation when done. - * This function should be called with rtnl locked. + * This function should be called with the wiphy mutex held. */ -void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy, u64 reqid); +void cfg80211_sched_scan_stopped_locked(struct wiphy *wiphy, u64 reqid); /** * cfg80211_inform_bss_frame_data - inform cfg80211 of a received BSS frame @@ -7557,7 +7627,7 @@ bool cfg80211_reg_can_beacon(struct wiphy *wiphy, * also checks if IR-relaxation conditions apply, to allow beaconing under * more permissive conditions. * - * Requires the RTNL to be held. + * Requires the wiphy mutex to be held. */ bool cfg80211_reg_can_beacon_relax(struct wiphy *wiphy, struct cfg80211_chan_def *chandef, @@ -7661,7 +7731,7 @@ u32 cfg80211_calculate_bitrate(struct rate_info *rate); * when the driver wishes to unregister the wdev, e.g. when the hardware device * is unbound from the driver. * - * Requires the RTNL to be held. + * Requires the RTNL and wiphy mutex to be held. */ void cfg80211_unregister_wdev(struct wireless_dev *wdev); @@ -7673,6 +7743,8 @@ void cfg80211_unregister_wdev(struct wireless_dev *wdev); * than register_netdevice(), unregister_netdev() is impossible as the RTNL is * held. Otherwise, both register_netdevice() and register_netdev() are usable * instead as well. + * + * Requires the RTNL and wiphy mutex to be held. */ int cfg80211_register_netdevice(struct net_device *dev); @@ -7684,6 +7756,8 @@ int cfg80211_register_netdevice(struct net_device *dev); * than unregister_netdevice(), unregister_netdev() is impossible as the RTNL * is held. Otherwise, both unregister_netdevice() and unregister_netdev() are * usable instead as well. + * + * Requires the RTNL and wiphy mutex to be held. */ static inline void cfg80211_unregister_netdevice(struct net_device *dev) { diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 176fe0d9f67f..2d1d629e5d14 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -5529,7 +5529,7 @@ void ieee80211_iterate_active_interfaces_atomic(struct ieee80211_hw *hw, void *data); /** - * ieee80211_iterate_active_interfaces_rtnl - iterate active interfaces + * ieee80211_iterate_active_interfaces_mtx - iterate active interfaces * * This function iterates over the interfaces associated with a given * hardware that are currently active and calls the callback for them. @@ -5540,12 +5540,12 @@ void ieee80211_iterate_active_interfaces_atomic(struct ieee80211_hw *hw, * @iterator: the iterator function to call, cannot sleep * @data: first argument of the iterator function */ -void ieee80211_iterate_active_interfaces_rtnl(struct ieee80211_hw *hw, - u32 iter_flags, - void (*iterator)(void *data, +void ieee80211_iterate_active_interfaces_mtx(struct ieee80211_hw *hw, + u32 iter_flags, + void (*iterator)(void *data, u8 *mac, struct ieee80211_vif *vif), - void *data); + void *data); /** * ieee80211_iterate_stations_atomic - iterate stations -- cgit v1.2.3 From 6b2e04bc240fe9be9e690059f710e9f95346d34d Mon Sep 17 00:00:00 2001 From: Praveen Chaudhary Date: Mon, 25 Jan 2021 13:44:30 -0800 Subject: net: allow user to set metric on default route learned via Router Advertisement For IPv4, default route is learned via DHCPv4 and user is allowed to change metric using config etc/network/interfaces. But for IPv6, default route can be learned via RA, for which, currently a fixed metric value 1024 is used. Ideally, user should be able to configure metric on default route for IPv6 similar to IPv4. This patch adds sysctl for the same. Logs: For IPv4: Config in etc/network/interfaces: auto eth0 iface eth0 inet dhcp metric 4261413864 IPv4 Kernel Route Table: $ ip route list default via 172.21.47.1 dev eth0 metric 4261413864 FRR Table, if a static route is configured: [In real scenario, it is useful to prefer BGP learned default route over DHCPv4 default route.] Codes: K - kernel route, C - connected, S - static, R - RIP, O - OSPF, I - IS-IS, B - BGP, P - PIM, E - EIGRP, N - NHRP, T - Table, v - VNC, V - VNC-Direct, A - Babel, D - SHARP, > - selected route, * - FIB route S>* 0.0.0.0/0 [20/0] is directly connected, eth0, 00:00:03 K 0.0.0.0/0 [254/1000] via 172.21.47.1, eth0, 6d08h51m i.e. User can prefer Default Router learned via Routing Protocol in IPv4. Similar behavior is not possible for IPv6, without this fix. After fix [for IPv6]: sudo sysctl -w net.ipv6.conf.eth0.net.ipv6.conf.eth0.ra_defrtr_metric=1996489705 IP monitor: [When IPv6 RA is received] default via fe80::xx16:xxxx:feb3:ce8e dev eth0 proto ra metric 1996489705 pref high Kernel IPv6 routing table $ ip -6 route list default via fe80::be16:65ff:feb3:ce8e dev eth0 proto ra metric 1996489705 expires 21sec hoplimit 64 pref high FRR Table, if a static route is configured: [In real scenario, it is useful to prefer BGP learned default route over IPv6 RA default route.] Codes: K - kernel route, C - connected, S - static, R - RIPng, O - OSPFv3, I - IS-IS, B - BGP, N - NHRP, T - Table, v - VNC, V - VNC-Direct, A - Babel, D - SHARP, > - selected route, * - FIB route S>* ::/0 [20/0] is directly connected, eth0, 00:00:06 K ::/0 [119/1001] via fe80::xx16:xxxx:feb3:ce8e, eth0, 6d07h43m If the metric is changed later, the effect will be seen only when next IPv6 RA is received, because the default route must be fully controlled by RA msg. Below metric is changed from 1996489705 to 1996489704. $ sudo sysctl -w net.ipv6.conf.eth0.ra_defrtr_metric=1996489704 net.ipv6.conf.eth0.ra_defrtr_metric = 1996489704 IP monitor: [On next IPv6 RA msg, Kernel deletes prev route and installs new route with updated metric] Deleted default via fe80::xx16:xxxx:feb3:ce8e dev eth0 proto ra metric 1996489705 expires 3sec hoplimit 64 pref high default via fe80::xx16:xxxx:feb3:ce8e dev eth0 proto ra metric 1996489704 pref high Signed-off-by: Praveen Chaudhary Signed-off-by: Zhenggen Xu Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20210125214430.24079-1-pchaudhary@linkedin.com Signed-off-by: Jakub Kicinski --- include/linux/ipv6.h | 1 + include/net/ip6_route.h | 3 ++- include/uapi/linux/ipv6.h | 1 + include/uapi/linux/sysctl.h | 1 + 4 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index dda61d150a13..9d1f29f0c512 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -31,6 +31,7 @@ struct ipv6_devconf { __s32 max_desync_factor; __s32 max_addresses; __s32 accept_ra_defrtr; + __u32 ra_defrtr_metric; __s32 accept_ra_min_hop_limit; __s32 accept_ra_pinfo; __s32 ignore_routes_with_linkdown; diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 2a5277758379..f51a118bfce8 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -174,7 +174,8 @@ struct fib6_info *rt6_get_dflt_router(struct net *net, struct net_device *dev); struct fib6_info *rt6_add_dflt_router(struct net *net, const struct in6_addr *gwaddr, - struct net_device *dev, unsigned int pref); + struct net_device *dev, unsigned int pref, + u32 defrtr_usr_metric); void rt6_purge_dflt_routers(struct net *net); diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 13e8751bf24a..70603775fe91 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -189,6 +189,7 @@ enum { DEVCONF_ACCEPT_RA_RT_INFO_MIN_PLEN, DEVCONF_NDISC_TCLASS, DEVCONF_RPL_SEG_ENABLED, + DEVCONF_RA_DEFRTR_METRIC, DEVCONF_MAX }; diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h index 458179df9b27..1e05d3caa712 100644 --- a/include/uapi/linux/sysctl.h +++ b/include/uapi/linux/sysctl.h @@ -571,6 +571,7 @@ enum { NET_IPV6_ACCEPT_SOURCE_ROUTE=25, NET_IPV6_ACCEPT_RA_FROM_LOCAL=26, NET_IPV6_ACCEPT_RA_RT_INFO_MIN_PLEN=27, + NET_IPV6_RA_DEFRTR_METRIC=28, __NET_IPV6_MAX }; -- cgit v1.2.3 From 6fe27d68b45666381691b6a841a2adbda8c8d153 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Wed, 20 Jan 2021 02:03:55 +0900 Subject: can: dev: export can_get_state_str() function The can_get_state_str() function is also relevant to the drivers. Export the symbol and make it visible in the can/dev.h header. Link: https://lore.kernel.org/r/20210119170355.12040-1-mailhol.vincent@wanadoo.fr Signed-off-by: Vincent Mailhol Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 7faf6a37d5b2..ac4d83a1ab81 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -123,6 +123,7 @@ void unregister_candev(struct net_device *dev); int can_restart_now(struct net_device *dev); void can_bus_off(struct net_device *dev); +const char *can_get_state_str(const enum can_state state); void can_change_state(struct net_device *dev, struct can_frame *cf, enum can_state tx_state, enum can_state rx_state); -- cgit v1.2.3 From 87baa23e0236bc1c41ce744f524bf12dbe7fde66 Mon Sep 17 00:00:00 2001 From: Hemant Kumar Date: Mon, 11 Jan 2021 19:07:40 +0100 Subject: bus: mhi: core: Add helper API to return number of free TREs Introduce mhi_get_free_desc_count() API to return number of TREs available to queue buffer. MHI clients can use this API to know before hand if ring is full without calling queue API. Signed-off-by: Hemant Kumar Reviewed-by: Jeffrey Hugo Reviewed-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/1610388462-16322-1-git-send-email-loic.poulain@linaro.org Signed-off-by: Manivannan Sadhasivam --- include/linux/mhi.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 562862ff819c..ece53a252217 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -598,6 +598,15 @@ void mhi_set_mhi_state(struct mhi_controller *mhi_cntrl, */ void mhi_notify(struct mhi_device *mhi_dev, enum mhi_callback cb_reason); +/** + * mhi_get_free_desc_count - Get transfer ring length + * Get # of TD available to queue buffers + * @mhi_dev: Device associated with the channels + * @dir: Direction of the channel + */ +int mhi_get_free_desc_count(struct mhi_device *mhi_dev, + enum dma_data_direction dir); + /** * mhi_prepare_for_power_up - Do pre-initialization before power up. * This is optional, call this before power up if -- cgit v1.2.3 From 4f16d25c68ec844299a4df6ecbb0234eaf88a935 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 25 Jan 2021 17:28:18 +0100 Subject: netfilter: nftables: add nft_parse_register_load() and use it MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This new function combines the netlink register attribute parser and the load validation function. This update requires to replace: enum nft_registers sreg:8; in many of the expression private areas otherwise compiler complains with: error: cannot take address of bit-field ‘sreg’ when passing the register field as reference. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 2 +- include/net/netfilter/nf_tables_core.h | 6 +++--- include/net/netfilter/nft_meta.h | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index f4af8362d234..033b31aa38cc 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -203,7 +203,7 @@ int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest); unsigned int nft_parse_register(const struct nlattr *attr); int nft_dump_register(struct sk_buff *skb, unsigned int attr, unsigned int reg); -int nft_validate_register_load(enum nft_registers reg, unsigned int len); +int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len); int nft_validate_register_store(const struct nft_ctx *ctx, enum nft_registers reg, const struct nft_data *data, diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index 8657e6815b07..b7aff03a3f0f 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -26,14 +26,14 @@ void nf_tables_core_module_exit(void); struct nft_bitwise_fast_expr { u32 mask; u32 xor; - enum nft_registers sreg:8; + u8 sreg; enum nft_registers dreg:8; }; struct nft_cmp_fast_expr { u32 data; u32 mask; - enum nft_registers sreg:8; + u8 sreg; u8 len; bool inv; }; @@ -67,7 +67,7 @@ struct nft_payload_set { enum nft_payload_bases base:8; u8 offset; u8 len; - enum nft_registers sreg:8; + u8 sreg; u8 csum_type; u8 csum_offset; u8 csum_flags; diff --git a/include/net/netfilter/nft_meta.h b/include/net/netfilter/nft_meta.h index 07e2fd507963..946fa8c83798 100644 --- a/include/net/netfilter/nft_meta.h +++ b/include/net/netfilter/nft_meta.h @@ -8,7 +8,7 @@ struct nft_meta { enum nft_meta_keys key:8; union { enum nft_registers dreg:8; - enum nft_registers sreg:8; + u8 sreg; }; }; -- cgit v1.2.3 From 345023b0db315648ccc3c1a36aee88304a8b4d91 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 25 Jan 2021 18:27:22 +0100 Subject: netfilter: nftables: add nft_parse_register_store() and use it MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This new function combines the netlink register attribute parser and the store validation function. This update requires to replace: enum nft_registers dreg:8; in many of the expression private areas otherwise compiler complains with: error: cannot take address of bit-field ‘dreg’ when passing the register field as reference. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 8 ++++---- include/net/netfilter/nf_tables_core.h | 6 +++--- include/net/netfilter/nft_fib.h | 2 +- include/net/netfilter/nft_meta.h | 2 +- 4 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 033b31aa38cc..78d174517749 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -204,10 +204,10 @@ unsigned int nft_parse_register(const struct nlattr *attr); int nft_dump_register(struct sk_buff *skb, unsigned int attr, unsigned int reg); int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len); -int nft_validate_register_store(const struct nft_ctx *ctx, - enum nft_registers reg, - const struct nft_data *data, - enum nft_data_types type, unsigned int len); +int nft_parse_register_store(const struct nft_ctx *ctx, + const struct nlattr *attr, u8 *dreg, + const struct nft_data *data, + enum nft_data_types type, unsigned int len); /** * struct nft_userdata - user defined data associated with an object diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index b7aff03a3f0f..fd10a7862fdc 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -27,7 +27,7 @@ struct nft_bitwise_fast_expr { u32 mask; u32 xor; u8 sreg; - enum nft_registers dreg:8; + u8 dreg; }; struct nft_cmp_fast_expr { @@ -40,7 +40,7 @@ struct nft_cmp_fast_expr { struct nft_immediate_expr { struct nft_data data; - enum nft_registers dreg:8; + u8 dreg; u8 dlen; }; @@ -60,7 +60,7 @@ struct nft_payload { enum nft_payload_bases base:8; u8 offset; u8 len; - enum nft_registers dreg:8; + u8 dreg; }; struct nft_payload_set { diff --git a/include/net/netfilter/nft_fib.h b/include/net/netfilter/nft_fib.h index 628b6fa579cd..237f3757637e 100644 --- a/include/net/netfilter/nft_fib.h +++ b/include/net/netfilter/nft_fib.h @@ -5,7 +5,7 @@ #include struct nft_fib { - enum nft_registers dreg:8; + u8 dreg; u8 result; u32 flags; }; diff --git a/include/net/netfilter/nft_meta.h b/include/net/netfilter/nft_meta.h index 946fa8c83798..2dce55c736f4 100644 --- a/include/net/netfilter/nft_meta.h +++ b/include/net/netfilter/nft_meta.h @@ -7,7 +7,7 @@ struct nft_meta { enum nft_meta_keys key:8; union { - enum nft_registers dreg:8; + u8 dreg; u8 sreg; }; }; -- cgit v1.2.3 From 08a01c11a5bb3de9b0a9c9b2685867e50eda9910 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 25 Jan 2021 23:19:17 +0100 Subject: netfilter: nftables: statify nft_parse_register() This function is not used anymore by any extension, statify it. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 78d174517749..99d4571fef46 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -200,7 +200,6 @@ static inline enum nft_registers nft_type_to_reg(enum nft_data_types type) } int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest); -unsigned int nft_parse_register(const struct nlattr *attr); int nft_dump_register(struct sk_buff *skb, unsigned int attr, unsigned int reg); int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len); -- cgit v1.2.3 From 8063e184e49011f6f3f34f6c358dc8a83890bb5b Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Wed, 27 Jan 2021 14:15:01 -0800 Subject: skmsg: Make sk_psock_destroy() static sk_psock_destroy() is a RCU callback, I can't see any reason why it could be used outside. Signed-off-by: Cong Wang Signed-off-by: Daniel Borkmann Cc: John Fastabend Cc: Jakub Sitnicki Cc: Lorenz Bauer Link: https://lore.kernel.org/bpf/20210127221501.46866-1-xiyou.wangcong@gmail.com --- include/linux/skmsg.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index fec0c5ac1c4f..8edbbf5f2f93 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -390,7 +390,6 @@ static inline struct sk_psock *sk_psock_get(struct sock *sk) } void sk_psock_stop(struct sock *sk, struct sk_psock *psock); -void sk_psock_destroy(struct rcu_head *rcu); void sk_psock_drop(struct sock *sk, struct sk_psock *psock); static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock) -- cgit v1.2.3 From 2dba407f994e5b0eb3b70a8cb280e014ec4a7ff3 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 26 Jan 2021 11:35:33 +0200 Subject: net: bridge: multicast: make tracked EHT hosts limit configurable Add two new port attributes which make EHT hosts limit configurable and export the current number of tracked EHT hosts: - IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT: configure/retrieve current limit - IFLA_BRPORT_MCAST_EHT_HOSTS_CNT: current number of tracked hosts Setting IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT to 0 is currently not allowed. Note that we have to increase RTNL_SLAVE_MAX_TYPE to 38 minimum, I've increased it to 40 to have space for two more future entries. v2: move br_multicast_eht_set_hosts_limit() to br_multicast_eht.c, no functional change Signed-off-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_link.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 2bd0d8bbcdb2..eb8018c3a737 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -525,6 +525,8 @@ enum { IFLA_BRPORT_BACKUP_PORT, IFLA_BRPORT_MRP_RING_OPEN, IFLA_BRPORT_MRP_IN_OPEN, + IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, + IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) -- cgit v1.2.3 From 772412176fb98493158929b220fe250127f611af Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Wed, 27 Jan 2021 11:31:39 -0800 Subject: bpf: Allow rewriting to ports under ip_unprivileged_port_start At the moment, BPF_CGROUP_INET{4,6}_BIND hooks can rewrite user_port to the privileged ones (< ip_unprivileged_port_start), but it will be rejected later on in the __inet_bind or __inet6_bind. Let's add another return value to indicate that CAP_NET_BIND_SERVICE check should be ignored. Use the same idea as we currently use in cgroup/egress where bit #1 indicates CN. Instead, for cgroup/bind{4,6}, bit #1 indicates that CAP_NET_BIND_SERVICE should be bypassed. v5: - rename flags to be less confusing (Andrey Ignatov) - rework BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY to work on flags and accept BPF_RET_SET_CN (no behavioral changes) v4: - Add missing IPv6 support (Martin KaFai Lau) v3: - Update description (Martin KaFai Lau) - Fix capability restore in selftest (Martin KaFai Lau) v2: - Switch to explicit return code (Martin KaFai Lau) Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Reviewed-by: Martin KaFai Lau Acked-by: Andrey Ignatov Link: https://lore.kernel.org/bpf/20210127193140.3170382-1-sdf@google.com --- include/linux/bpf-cgroup.h | 38 ++++++++++++++++++++++++--------- include/linux/bpf.h | 52 +++++++++++++++++++++++++++++----------------- include/net/inet_common.h | 2 ++ 3 files changed, 63 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 0748fd87969e..c42e02b4d84b 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -125,7 +125,8 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, struct sockaddr *uaddr, enum bpf_attach_type type, - void *t_ctx); + void *t_ctx, + u32 *flags); int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, struct bpf_sock_ops_kern *sock_ops, @@ -231,30 +232,48 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, type) \ ({ \ + u32 __unused_flags; \ int __ret = 0; \ if (cgroup_bpf_enabled(type)) \ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ - NULL); \ + NULL, \ + &__unused_flags); \ __ret; \ }) #define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx) \ ({ \ + u32 __unused_flags; \ int __ret = 0; \ if (cgroup_bpf_enabled(type)) { \ lock_sock(sk); \ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ - t_ctx); \ + t_ctx, \ + &__unused_flags); \ release_sock(sk); \ } \ __ret; \ }) -#define BPF_CGROUP_RUN_PROG_INET4_BIND_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET4_BIND, NULL) - -#define BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_BIND, NULL) +/* BPF_CGROUP_INET4_BIND and BPF_CGROUP_INET6_BIND can return extra flags + * via upper bits of return code. The only flag that is supported + * (at bit position 0) is to indicate CAP_NET_BIND_SERVICE capability check + * should be bypassed (BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE). + */ +#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, type, bind_flags) \ +({ \ + u32 __flags = 0; \ + int __ret = 0; \ + if (cgroup_bpf_enabled(type)) { \ + lock_sock(sk); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ + NULL, &__flags); \ + release_sock(sk); \ + if (__flags & BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE) \ + *bind_flags |= BIND_NO_CAP_NET_BIND_SERVICE; \ + } \ + __ret; \ +}) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) \ ((cgroup_bpf_enabled(BPF_CGROUP_INET4_CONNECT) || \ @@ -453,8 +472,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_INET4_BIND_LOCK(sk, uaddr) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, type, flags) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) ({ 0; }) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1aac2af12fed..321966fc35db 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1073,6 +1073,34 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *include_prog, struct bpf_prog_array **new_array); +/* BPF program asks to bypass CAP_NET_BIND_SERVICE in bind. */ +#define BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE (1 << 0) +/* BPF program asks to set CN on the packet. */ +#define BPF_RET_SET_CN (1 << 0) + +#define BPF_PROG_RUN_ARRAY_FLAGS(array, ctx, func, ret_flags) \ + ({ \ + struct bpf_prog_array_item *_item; \ + struct bpf_prog *_prog; \ + struct bpf_prog_array *_array; \ + u32 _ret = 1; \ + u32 func_ret; \ + migrate_disable(); \ + rcu_read_lock(); \ + _array = rcu_dereference(array); \ + _item = &_array->items[0]; \ + while ((_prog = READ_ONCE(_item->prog))) { \ + bpf_cgroup_storage_set(_item->cgroup_storage); \ + func_ret = func(_prog, ctx); \ + _ret &= (func_ret & 1); \ + *(ret_flags) |= (func_ret >> 1); \ + _item++; \ + } \ + rcu_read_unlock(); \ + migrate_enable(); \ + _ret; \ + }) + #define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null) \ ({ \ struct bpf_prog_array_item *_item; \ @@ -1120,25 +1148,11 @@ _out: \ */ #define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func) \ ({ \ - struct bpf_prog_array_item *_item; \ - struct bpf_prog *_prog; \ - struct bpf_prog_array *_array; \ - u32 ret; \ - u32 _ret = 1; \ - u32 _cn = 0; \ - migrate_disable(); \ - rcu_read_lock(); \ - _array = rcu_dereference(array); \ - _item = &_array->items[0]; \ - while ((_prog = READ_ONCE(_item->prog))) { \ - bpf_cgroup_storage_set(_item->cgroup_storage); \ - ret = func(_prog, ctx); \ - _ret &= (ret & 1); \ - _cn |= (ret & 2); \ - _item++; \ - } \ - rcu_read_unlock(); \ - migrate_enable(); \ + u32 _flags = 0; \ + bool _cn; \ + u32 _ret; \ + _ret = BPF_PROG_RUN_ARRAY_FLAGS(array, ctx, func, &_flags); \ + _cn = _flags & BPF_RET_SET_CN; \ if (_ret) \ _ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \ else \ diff --git a/include/net/inet_common.h b/include/net/inet_common.h index cb2818862919..cad2a611efde 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -41,6 +41,8 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); #define BIND_WITH_LOCK (1 << 1) /* Called from BPF program. */ #define BIND_FROM_BPF (1 << 2) +/* Skip CAP_NET_BIND_SERVICE check. */ +#define BIND_NO_CAP_NET_BIND_SERVICE (1 << 3) int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, u32 flags); int inet_getname(struct socket *sock, struct sockaddr *uaddr, -- cgit v1.2.3 From e78ab164591ffd55d2771401ed0d9b083dad55fa Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Tue, 26 Jan 2021 15:24:06 -0800 Subject: devlink: Add DMAC filter generic packet trap Add packet trap that can report packets that were dropped due to destination MAC filtering. Signed-off-by: Aya Levin Reviewed-by: Ido Schimmel Reviewed-by: Moshe Shemesh Reviewed-by: Tariq Toukan Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index d12ed2854c34..426b98e74b6e 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -838,6 +838,7 @@ enum devlink_trap_generic_id { DEVLINK_TRAP_GENERIC_ID_GTP_PARSING, DEVLINK_TRAP_GENERIC_ID_ESP_PARSING, DEVLINK_TRAP_GENERIC_ID_BLACKHOLE_NEXTHOP, + DEVLINK_TRAP_GENERIC_ID_DMAC_FILTER, /* Add new generic trap IDs above */ __DEVLINK_TRAP_GENERIC_ID_MAX, @@ -1063,6 +1064,8 @@ enum devlink_trap_group_generic_id { "esp_parsing" #define DEVLINK_TRAP_GENERIC_NAME_BLACKHOLE_NEXTHOP \ "blackhole_nexthop" +#define DEVLINK_TRAP_GENERIC_NAME_DMAC_FILTER \ + "dest_mac_filter" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_L2_DROPS \ "l2_drops" -- cgit v1.2.3 From 3d347b1b19da20f973d1d3c6bb60c11185606afd Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Tue, 26 Jan 2021 15:24:07 -0800 Subject: net/mlx5: Add support for devlink traps in mlx5 core driver Add devlink traps infra-structure to mlx5 core driver. Add traps list to mlx5_priv and corresponding API: - mlx5_devlink_trap_report() to wrap trap reports to devlink - mlx5_devlink_trap_get_num_active() to decide whether to open/close trap resources. Signed-off-by: Aya Levin Reviewed-by: Tariq Toukan Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- include/linux/mlx5/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f93bfe7473aa..c4615dc51b6f 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -564,6 +564,7 @@ struct mlx5_priv { int host_pf_pages; struct mlx5_core_health health; + struct list_head traps; /* start: qp staff */ struct dentry *qp_debugfs; -- cgit v1.2.3 From 241dc159391fb9d351362d911a39dff84074cc92 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Tue, 26 Jan 2021 15:24:11 -0800 Subject: net/mlx5: Notify on trap action by blocking event In order to allow mlx5 core driver to trigger synchronous operations to its consumers, add a blocking events handler. Add wrappers to blocking_notifier_[call_chain/chain_register/chain_unregister]. Add trap callback for action set and notify about this change. Following patches in the set add a listener for this event. Signed-off-by: Aya Levin Reviewed-by: Tariq Toukan Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- include/linux/mlx5/device.h | 4 ++++ include/linux/mlx5/driver.h | 15 +++++++++++++++ 2 files changed, 19 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index f1de49d64a98..77ba54d38772 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -359,6 +359,10 @@ enum mlx5_event { MLX5_EVENT_TYPE_MAX = 0x100, }; +enum mlx5_driver_event { + MLX5_DRIVER_EVENT_TYPE_TRAP = 0, +}; + enum { MLX5_TRACER_SUBTYPE_OWNERSHIP_CHANGE = 0x0, MLX5_TRACER_SUBTYPE_TRACES_AVAILABLE = 0x1, diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index c4615dc51b6f..45df5b465ba8 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1073,11 +1073,26 @@ enum { MAX_MR_CACHE_ENTRIES }; +/* Async-atomic event notifier used by mlx5 core to forward FW + * evetns recived from event queue to mlx5 consumers. + * Optimise event queue dipatching. + */ int mlx5_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb); int mlx5_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb); + +/* Async-atomic event notifier used for forwarding + * evetns from the event queue into the to mlx5 events dispatcher, + * eswitch, clock and others. + */ int mlx5_eq_notifier_register(struct mlx5_core_dev *dev, struct mlx5_nb *nb); int mlx5_eq_notifier_unregister(struct mlx5_core_dev *dev, struct mlx5_nb *nb); +/* Blocking event notifier used to forward SW events, used for slow path */ +int mlx5_blocking_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb); +int mlx5_blocking_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb); +int mlx5_blocking_notifier_call_chain(struct mlx5_core_dev *dev, unsigned int event, + void *data); + int mlx5_core_query_vendor_id(struct mlx5_core_dev *mdev, u32 *vendor_id); int mlx5_cmd_create_vport_lag(struct mlx5_core_dev *dev); -- cgit v1.2.3 From 5543e989fe5e2fe6a5829ee42c00152cac2bb8a0 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Tue, 26 Jan 2021 15:24:16 -0800 Subject: net/mlx5e: Add trap entity to ETH driver Introduce mlx5e_trap which includes a dedicated RQ and NAPI for trapped packets. Trap-RQ processes packets that were destined to be dropped, but for debug and visibility sake these packets are trapped and reported to devlink. Trap-RQ connects between the HW and the driver and is not a part of a channel. Open mlx5e_create_rq() and mlx5_core_destroy_rq() as API and add dedicate RQ handlers which report to devlink of trapped packets. Signed-off-by: Aya Levin Reviewed-by: Tariq Toukan Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- include/linux/mlx5/device.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 77ba54d38772..00057eae89ab 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -903,6 +903,11 @@ static inline u64 get_cqe_ts(struct mlx5_cqe64 *cqe) return (u64)lo | ((u64)hi << 32); } +static inline u16 get_cqe_flow_tag(struct mlx5_cqe64 *cqe) +{ + return be32_to_cpu(cqe->sop_drop_qpn) & 0xFFF; +} + #define MLX5_MPWQE_LOG_NUM_STRIDES_BASE (9) #define MLX5_MPWQE_LOG_STRIDE_SZ_BASE (6) -- cgit v1.2.3 From 28af22c6c8dff6a16163e5b6a56211d5b535c97b Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 26 Jan 2021 18:39:39 +0100 Subject: net: adjust net_device layout for cacheline usage The current layout of net_device is not optimal for cacheline usage. The member adj_list.lower linked list is split between cacheline 2 and 3. The ifindex is placed together with stats (struct net_device_stats), although most modern drivers don't update this stats member. The members netdev_ops, mtu and hard_header_len are placed on three different cachelines. These members are accessed for XDP redirect into devmap, which were noticeably with perf tool. When not using the map redirect variant (like TC-BPF does), then ifindex is also used, which is placed on a separate fourth cacheline. These members are also accessed during forwarding with regular network stack. The members priv_flags and flags are on fast-path for network stack transmit path in __dev_queue_xmit (currently located together with mtu cacheline). This patch creates a read mostly cacheline, with the purpose of keeping the above mentioned members on the same cacheline. Some netdev_features_t members also becomes part of this cacheline, which is on purpose, as function netif_skb_features() is on fast-path via validate_xmit_skb(). Signed-off-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/r/161168277983.410784.12401225493601624417.stgit@firesoul Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 53 ++++++++++++++++++++++++----------------------- 1 file changed, 27 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9e8572533d8e..e9e7ada07ea1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1858,7 +1858,6 @@ struct net_device { unsigned long mem_end; unsigned long mem_start; unsigned long base_addr; - int irq; /* * Some hardware also needs these fields (state,dev_list, @@ -1880,6 +1879,23 @@ struct net_device { struct list_head lower; } adj_list; + /* Read-mostly cache-line for fast-path access */ + unsigned int flags; + unsigned int priv_flags; + const struct net_device_ops *netdev_ops; + int ifindex; + unsigned short gflags; + unsigned short hard_header_len; + + /* Note : dev->mtu is often read without holding a lock. + * Writers usually hold RTNL. + * It is recommended to use READ_ONCE() to annotate the reads, + * and to use WRITE_ONCE() to annotate the writes. + */ + unsigned int mtu; + unsigned short needed_headroom; + unsigned short needed_tailroom; + netdev_features_t features; netdev_features_t hw_features; netdev_features_t wanted_features; @@ -1888,10 +1904,15 @@ struct net_device { netdev_features_t mpls_features; netdev_features_t gso_partial_features; - int ifindex; + unsigned int min_mtu; + unsigned int max_mtu; + unsigned short type; + unsigned char min_header_len; + unsigned char name_assign_type; + int group; - struct net_device_stats stats; + struct net_device_stats stats; /* not used by modern drivers */ atomic_long_t rx_dropped; atomic_long_t tx_dropped; @@ -1905,7 +1926,6 @@ struct net_device { const struct iw_handler_def *wireless_handlers; struct iw_public_data *wireless_data; #endif - const struct net_device_ops *netdev_ops; const struct ethtool_ops *ethtool_ops; #ifdef CONFIG_NET_L3_MASTER_DEV const struct l3mdev_ops *l3mdev_ops; @@ -1924,34 +1944,12 @@ struct net_device { const struct header_ops *header_ops; - unsigned int flags; - unsigned int priv_flags; - - unsigned short gflags; - unsigned short padded; - unsigned char operstate; unsigned char link_mode; unsigned char if_port; unsigned char dma; - /* Note : dev->mtu is often read without holding a lock. - * Writers usually hold RTNL. - * It is recommended to use READ_ONCE() to annotate the reads, - * and to use WRITE_ONCE() to annotate the writes. - */ - unsigned int mtu; - unsigned int min_mtu; - unsigned int max_mtu; - unsigned short type; - unsigned short hard_header_len; - unsigned char min_header_len; - unsigned char name_assign_type; - - unsigned short needed_headroom; - unsigned short needed_tailroom; - /* Interface address info. */ unsigned char perm_addr[MAX_ADDR_LEN]; unsigned char addr_assign_type; @@ -1962,7 +1960,10 @@ struct net_device { unsigned short neigh_priv_len; unsigned short dev_id; unsigned short dev_port; + unsigned short padded; + spinlock_t addr_list_lock; + int irq; struct netdev_hw_addr_list uc; struct netdev_hw_addr_list mc; -- cgit v1.2.3 From ef6af7bdb9e6c14eae8dc5fe852aefe1e089c85c Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Thu, 28 Jan 2021 12:41:06 +0100 Subject: net/af_iucv: count packets in the xmit path The TX code keeps track of all skbs that are in-flight but haven't actually been sent out yet. For native IUCV sockets that's not a huge deal, but with TRANS_HIPER sockets it would be much better if we didn't need to maintain a list of skb clones. Note that we actually only care about the _count_ of skbs in this stage of the TX pipeline. So as prep work for removing the skb tracking on TRANS_HIPER sockets, keep track of the skb count in a separate variable and pair any list {enqueue, unlink} with a count {increment, decrement}. Then replace all occurences where we currently look at the skb list's fill level. Signed-off-by: Julian Wiedmann Acked-by: Willem de Bruijn Signed-off-by: Jakub Kicinski --- include/net/iucv/af_iucv.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/iucv/af_iucv.h b/include/net/iucv/af_iucv.h index 9259ce2b22f3..0816bcd44dd1 100644 --- a/include/net/iucv/af_iucv.h +++ b/include/net/iucv/af_iucv.h @@ -128,6 +128,7 @@ struct iucv_sock { u8 flags; u16 msglimit; u16 msglimit_peer; + atomic_t skbs_in_xmit; atomic_t msg_sent; atomic_t msg_recv; atomic_t pendings; -- cgit v1.2.3 From 80bc97aa0aaab974bbbfb99a78d7515414004616 Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Thu, 28 Jan 2021 12:41:07 +0100 Subject: net/af_iucv: don't track individual TX skbs for TRANS_HIPER sockets Stop maintaining the skb_send_q list for TRANS_HIPER sockets. Not only is it extra overhead, but keeping around a list of skb clones means that we later also have to match the ->sk_txnotify() calls against these clones and free them accordingly. The current matching logic (comparing the skbs' shinfo location) is frustratingly fragile, and breaks if the skb's head is mangled in any sort of way while passing from dev_queue_xmit() to the device's HW queue. Also adjust the interface for ->sk_txnotify(), to make clear that we don't actually care about any skb internals. Signed-off-by: Julian Wiedmann Acked-by: Willem de Bruijn Signed-off-by: Jakub Kicinski --- include/net/iucv/af_iucv.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/iucv/af_iucv.h b/include/net/iucv/af_iucv.h index 0816bcd44dd1..ff06246dbbb9 100644 --- a/include/net/iucv/af_iucv.h +++ b/include/net/iucv/af_iucv.h @@ -133,7 +133,7 @@ struct iucv_sock { atomic_t msg_recv; atomic_t pendings; int transport; - void (*sk_txnotify)(struct sk_buff *skb, + void (*sk_txnotify)(struct sock *sk, enum iucv_tx_notify n); }; -- cgit v1.2.3 From b9bae61be46645aa3b8b5d79d5cdfabe55ae1507 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Thu, 28 Jan 2021 13:49:15 +0100 Subject: nexthop: Introduce to struct nh_grp_entry a per-type union The values that a next-hop group needs to keep track of depend on the group type. Introduce a union to separate fields specific to the mpath groups from fields specific to other group types. Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- include/net/nexthop.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 226930d66b63..d0e245b0635d 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -66,7 +66,12 @@ struct nh_info { struct nh_grp_entry { struct nexthop *nh; u8 weight; - atomic_t upper_bound; + + union { + struct { + atomic_t upper_bound; + } mpath; + }; struct list_head nh_list; struct nexthop *nh_parent; /* nexthop of group with this entry */ -- cgit v1.2.3 From 09ad6becf5355fe0645f500f518fbbd531715722 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 28 Jan 2021 13:49:17 +0100 Subject: nexthop: Use enum to encode notification type Currently there are only two types of in-kernel nexthop notification. The two are distinguished by the 'is_grp' boolean field in 'struct nh_notifier_info'. As more notification types are introduced for more next-hop group types, a boolean is not an easily extensible interface. Instead, convert it to an enum. Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Signed-off-by: Petr Machata Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- include/net/nexthop.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/nexthop.h b/include/net/nexthop.h index d0e245b0635d..7bc057aee40b 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -114,6 +114,11 @@ enum nexthop_event_type { NEXTHOP_EVENT_REPLACE, }; +enum nh_notifier_info_type { + NH_NOTIFIER_INFO_TYPE_SINGLE, + NH_NOTIFIER_INFO_TYPE_GRP, +}; + struct nh_notifier_single_info { struct net_device *dev; u8 gw_family; @@ -142,7 +147,7 @@ struct nh_notifier_info { struct net *net; struct netlink_ext_ack *extack; u32 id; - bool is_grp; + enum nh_notifier_info_type type; union { struct nh_notifier_single_info *nh; struct nh_notifier_grp_info *nh_grp; -- cgit v1.2.3 From 1d3f9bb1be8556bce237934ae82b3cdeda3242fd Mon Sep 17 00:00:00 2001 From: dingsenjie Date: Wed, 27 Jan 2021 10:28:01 +0800 Subject: linux/qed: fix spelling typo in qed_chain.h allocted -> allocated Signed-off-by: dingsenjie Link: https://lore.kernel.org/r/20210127022801.8028-1-dingsenjie@163.com Signed-off-by: Jakub Kicinski --- include/linux/qed/qed_chain.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 4d58dc8943f0..e339b48de32d 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -470,7 +470,7 @@ static inline void *qed_chain_consume(struct qed_chain *p_chain) /** * @brief qed_chain_reset - Resets the chain to its start state * - * @param p_chain pointer to a previously allocted chain + * @param p_chain pointer to a previously allocated chain */ static inline void qed_chain_reset(struct qed_chain *p_chain) { -- cgit v1.2.3 From 219991e6be7f4a31d471611e265b72f75b2d0538 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 28 Jan 2021 17:33:12 +0100 Subject: Bluetooth: Add new HCI_QUIRK_NO_SUSPEND_NOTIFIER quirk Some devices, e.g. the RTL8723BS bluetooth part, some USB attached devices, completely drop from the bus on a system-suspend. These devices will have their driver unbound and rebound on resume (when the dropping of the bus gets detected) and will show up as a new HCI after resume. These devices do not benefit from the suspend / resume handling work done by the hci_suspend_notifier. At best this unnecessarily adds some time to the suspend/resume time. But this may also actually cause problems, if the code doing the driver unbinding runs after the pm-notifier then the hci_suspend_notifier code will try to talk to a device which is now in an uninitialized state. This commit adds a new HCI_QUIRK_NO_SUSPEND_NOTIFIER quirk which allows drivers to opt-out of the hci_suspend_notifier when they know beforehand that their device will be fully re-initialized / reprobed on resume. Signed-off-by: Hans de Goede Reviewed-by: Abhishek Pandit-Subedi Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index c1504aa3d9cf..ba2f439bc04d 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -238,6 +238,14 @@ enum { * during the hdev->setup vendor callback. */ HCI_QUIRK_BROKEN_ERR_DATA_REPORTING, + + /* + * When this quirk is set, then the hci_suspend_notifier is not + * registered. This is intended for devices which drop completely + * from the bus on system-suspend and which will show up as a new + * HCI after resume. + */ + HCI_QUIRK_NO_SUSPEND_NOTIFIER, }; /* HCI device flags */ -- cgit v1.2.3 From 8c85d18ce647ac2517a1a1bb01b02648e23700e6 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Wed, 27 Jan 2021 16:32:45 +0200 Subject: net/sched: cls_flower: Add match on the ct_state reply flag Add match on the ct_state reply flag. Example: $ tc filter add dev ens1f0_0 ingress prio 1 chain 1 proto ip flower \ ct_state +trk+est+rpl \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress prio 1 chain 1 proto ip flower \ ct_state +trk+est-rpl \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- include/uapi/linux/pkt_cls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 709668e264b0..afe6836e44b1 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -592,6 +592,7 @@ enum { TCA_FLOWER_KEY_CT_FLAGS_RELATED = 1 << 2, /* Related to an established connection. */ TCA_FLOWER_KEY_CT_FLAGS_TRACKED = 1 << 3, /* Conntrack has occurred. */ TCA_FLOWER_KEY_CT_FLAGS_INVALID = 1 << 4, /* Conntrack is invalid. */ + TCA_FLOWER_KEY_CT_FLAGS_REPLY = 1 << 5, /* Packet is in the reply direction. */ }; enum { -- cgit v1.2.3 From 941eff5aea5d4371fb8a496a66e29aa8fc7a0c23 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Wed, 27 Jan 2021 16:32:46 +0200 Subject: net: flow_offload: Add original direction flag to ct_metadata Give offloading drivers the direction of the offloaded ct flow, this will be used for matches on direction (ct_state +/-rpl). Signed-off-by: Paul Blakey Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- include/net/flow_offload.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 123b1e9ea304..e6bd8ebf9ac3 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -245,6 +245,7 @@ struct flow_action_entry { unsigned long cookie; u32 mark; u32 labels[4]; + bool orig_dir; } ct_metadata; struct { /* FLOW_ACTION_MPLS_PUSH */ u32 label; -- cgit v1.2.3 From efa1a65c7e1946ff174c56d36bf015ff9e11c4a1 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 28 Jan 2021 17:18:32 +0800 Subject: ip_gre: add csum offload support for gre header This patch is to add csum offload support for gre header: On the TX path in gre_build_header(), when CHECKSUM_PARTIAL's set for inner proto, it will calculate the csum for outer proto, and inner csum will be offloaded later. Otherwise, CHECKSUM_PARTIAL and csum_start/offset will be set for outer proto, and the outer csum will be offloaded later. On the GSO path in gre_gso_segment(), when CHECKSUM_PARTIAL is not set for inner proto and the hardware supports csum offload, CHECKSUM_PARTIAL and csum_start/offset will be set for outer proto, and outer csum will be offloaded later. Otherwise, it will do csum for outer proto by calling gso_make_checksum(). Note that SCTP has to do the csum by itself for non GSO path in sctp_packet_pack(), as gre_build_header() can't handle the csum with CHECKSUM_PARTIAL set for SCTP CRC csum offload. v1->v2: - remove the SCTP part, as GRE dev doesn't support SCTP CRC CSUM and it will always do checksum for SCTP in sctp_packet_pack() when it's not a GSO packet. Signed-off-by: Xin Long Signed-off-by: Jakub Kicinski --- include/net/gre.h | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/net/gre.h b/include/net/gre.h index b60f212c16c6..4e209708b754 100644 --- a/include/net/gre.h +++ b/include/net/gre.h @@ -106,17 +106,6 @@ static inline __be16 gre_tnl_flags_to_gre_flags(__be16 tflags) return flags; } -static inline __sum16 gre_checksum(struct sk_buff *skb) -{ - __wsum csum; - - if (skb->ip_summed == CHECKSUM_PARTIAL) - csum = lco_csum(skb); - else - csum = skb_checksum(skb, 0, skb->len, 0); - return csum_fold(csum); -} - static inline void gre_build_header(struct sk_buff *skb, int hdr_len, __be16 flags, __be16 proto, __be32 key, __be32 seq) @@ -146,7 +135,13 @@ static inline void gre_build_header(struct sk_buff *skb, int hdr_len, !(skb_shinfo(skb)->gso_type & (SKB_GSO_GRE | SKB_GSO_GRE_CSUM))) { *ptr = 0; - *(__sum16 *)ptr = gre_checksum(skb); + if (skb->ip_summed == CHECKSUM_PARTIAL) { + *(__sum16 *)ptr = csum_fold(lco_csum(skb)); + } else { + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = sizeof(*greh); + } } } } -- cgit v1.2.3 From 9c7caf28068421c9e0d1faea437e35e6b8983ac6 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 29 Jan 2021 02:59:59 +0200 Subject: net: dsa: tag_8021q: add helpers to deduce whether a VLAN ID is RX or TX VLAN The sja1105 implementation can be blind about this, but the felix driver doesn't do exactly what it's being told, so it needs to know whether it is a TX or an RX VLAN, so it can install the appropriate type of TCAM rule. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/linux/dsa/8021q.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 88cd72dfa4e0..b12b05f1c8b4 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -64,6 +64,10 @@ int dsa_8021q_rx_source_port(u16 vid); u16 dsa_8021q_rx_subvlan(u16 vid); +bool vid_is_dsa_8021q_rxvlan(u16 vid); + +bool vid_is_dsa_8021q_txvlan(u16 vid); + bool vid_is_dsa_8021q(u16 vid); #else @@ -123,6 +127,16 @@ u16 dsa_8021q_rx_subvlan(u16 vid) return 0; } +bool vid_is_dsa_8021q_rxvlan(u16 vid) +{ + return false; +} + +bool vid_is_dsa_8021q_txvlan(u16 vid) +{ + return false; +} + bool vid_is_dsa_8021q(u16 vid) { return false; -- cgit v1.2.3 From 0e9bb4e9d93f2711897b8e2a613899f7b8a15a3b Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 29 Jan 2021 03:00:00 +0200 Subject: net: mscc: ocelot: export VCAP structures to include/soc/mscc The Felix driver will need to preinstall some VCAP filters for its tag_8021q implementation (outside of the tc-flower offload logic), so these need to be exported to the common includes. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot_vcap.h | 289 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 289 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index 96300adf3648..7f1b82fba63c 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -400,4 +400,293 @@ enum vcap_es0_action_field { VCAP_ES0_ACT_HIT_STICKY, }; +struct ocelot_ipv4 { + u8 addr[4]; +}; + +enum ocelot_vcap_bit { + OCELOT_VCAP_BIT_ANY, + OCELOT_VCAP_BIT_0, + OCELOT_VCAP_BIT_1 +}; + +struct ocelot_vcap_u8 { + u8 value[1]; + u8 mask[1]; +}; + +struct ocelot_vcap_u16 { + u8 value[2]; + u8 mask[2]; +}; + +struct ocelot_vcap_u24 { + u8 value[3]; + u8 mask[3]; +}; + +struct ocelot_vcap_u32 { + u8 value[4]; + u8 mask[4]; +}; + +struct ocelot_vcap_u40 { + u8 value[5]; + u8 mask[5]; +}; + +struct ocelot_vcap_u48 { + u8 value[6]; + u8 mask[6]; +}; + +struct ocelot_vcap_u64 { + u8 value[8]; + u8 mask[8]; +}; + +struct ocelot_vcap_u128 { + u8 value[16]; + u8 mask[16]; +}; + +struct ocelot_vcap_vid { + u16 value; + u16 mask; +}; + +struct ocelot_vcap_ipv4 { + struct ocelot_ipv4 value; + struct ocelot_ipv4 mask; +}; + +struct ocelot_vcap_udp_tcp { + u16 value; + u16 mask; +}; + +struct ocelot_vcap_port { + u8 value; + u8 mask; +}; + +enum ocelot_vcap_key_type { + OCELOT_VCAP_KEY_ANY, + OCELOT_VCAP_KEY_ETYPE, + OCELOT_VCAP_KEY_LLC, + OCELOT_VCAP_KEY_SNAP, + OCELOT_VCAP_KEY_ARP, + OCELOT_VCAP_KEY_IPV4, + OCELOT_VCAP_KEY_IPV6 +}; + +struct ocelot_vcap_key_vlan { + struct ocelot_vcap_vid vid; /* VLAN ID (12 bit) */ + struct ocelot_vcap_u8 pcp; /* PCP (3 bit) */ + enum ocelot_vcap_bit dei; /* DEI */ + enum ocelot_vcap_bit tagged; /* Tagged/untagged frame */ +}; + +struct ocelot_vcap_key_etype { + struct ocelot_vcap_u48 dmac; + struct ocelot_vcap_u48 smac; + struct ocelot_vcap_u16 etype; + struct ocelot_vcap_u16 data; /* MAC data */ +}; + +struct ocelot_vcap_key_llc { + struct ocelot_vcap_u48 dmac; + struct ocelot_vcap_u48 smac; + + /* LLC header: DSAP at byte 0, SSAP at byte 1, Control at byte 2 */ + struct ocelot_vcap_u32 llc; +}; + +struct ocelot_vcap_key_snap { + struct ocelot_vcap_u48 dmac; + struct ocelot_vcap_u48 smac; + + /* SNAP header: Organization Code at byte 0, Type at byte 3 */ + struct ocelot_vcap_u40 snap; +}; + +struct ocelot_vcap_key_arp { + struct ocelot_vcap_u48 smac; + enum ocelot_vcap_bit arp; /* Opcode ARP/RARP */ + enum ocelot_vcap_bit req; /* Opcode request/reply */ + enum ocelot_vcap_bit unknown; /* Opcode unknown */ + enum ocelot_vcap_bit smac_match; /* Sender MAC matches SMAC */ + enum ocelot_vcap_bit dmac_match; /* Target MAC matches DMAC */ + + /**< Protocol addr. length 4, hardware length 6 */ + enum ocelot_vcap_bit length; + + enum ocelot_vcap_bit ip; /* Protocol address type IP */ + enum ocelot_vcap_bit ethernet; /* Hardware address type Ethernet */ + struct ocelot_vcap_ipv4 sip; /* Sender IP address */ + struct ocelot_vcap_ipv4 dip; /* Target IP address */ +}; + +struct ocelot_vcap_key_ipv4 { + enum ocelot_vcap_bit ttl; /* TTL zero */ + enum ocelot_vcap_bit fragment; /* Fragment */ + enum ocelot_vcap_bit options; /* Header options */ + struct ocelot_vcap_u8 ds; + struct ocelot_vcap_u8 proto; /* Protocol */ + struct ocelot_vcap_ipv4 sip; /* Source IP address */ + struct ocelot_vcap_ipv4 dip; /* Destination IP address */ + struct ocelot_vcap_u48 data; /* Not UDP/TCP: IP data */ + struct ocelot_vcap_udp_tcp sport; /* UDP/TCP: Source port */ + struct ocelot_vcap_udp_tcp dport; /* UDP/TCP: Destination port */ + enum ocelot_vcap_bit tcp_fin; + enum ocelot_vcap_bit tcp_syn; + enum ocelot_vcap_bit tcp_rst; + enum ocelot_vcap_bit tcp_psh; + enum ocelot_vcap_bit tcp_ack; + enum ocelot_vcap_bit tcp_urg; + enum ocelot_vcap_bit sip_eq_dip; /* SIP equals DIP */ + enum ocelot_vcap_bit sport_eq_dport; /* SPORT equals DPORT */ + enum ocelot_vcap_bit seq_zero; /* TCP sequence number is zero */ +}; + +struct ocelot_vcap_key_ipv6 { + struct ocelot_vcap_u8 proto; /* IPv6 protocol */ + struct ocelot_vcap_u128 sip; /* IPv6 source (byte 0-7 ignored) */ + struct ocelot_vcap_u128 dip; /* IPv6 destination (byte 0-7 ignored) */ + enum ocelot_vcap_bit ttl; /* TTL zero */ + struct ocelot_vcap_u8 ds; + struct ocelot_vcap_u48 data; /* Not UDP/TCP: IP data */ + struct ocelot_vcap_udp_tcp sport; + struct ocelot_vcap_udp_tcp dport; + enum ocelot_vcap_bit tcp_fin; + enum ocelot_vcap_bit tcp_syn; + enum ocelot_vcap_bit tcp_rst; + enum ocelot_vcap_bit tcp_psh; + enum ocelot_vcap_bit tcp_ack; + enum ocelot_vcap_bit tcp_urg; + enum ocelot_vcap_bit sip_eq_dip; /* SIP equals DIP */ + enum ocelot_vcap_bit sport_eq_dport; /* SPORT equals DPORT */ + enum ocelot_vcap_bit seq_zero; /* TCP sequence number is zero */ +}; + +enum ocelot_mask_mode { + OCELOT_MASK_MODE_NONE, + OCELOT_MASK_MODE_PERMIT_DENY, + OCELOT_MASK_MODE_POLICY, + OCELOT_MASK_MODE_REDIRECT, +}; + +enum ocelot_es0_tag { + OCELOT_NO_ES0_TAG, + OCELOT_ES0_TAG, + OCELOT_FORCE_PORT_TAG, + OCELOT_FORCE_UNTAG, +}; + +enum ocelot_tag_tpid_sel { + OCELOT_TAG_TPID_SEL_8021Q, + OCELOT_TAG_TPID_SEL_8021AD, +}; + +struct ocelot_vcap_action { + union { + /* VCAP ES0 */ + struct { + enum ocelot_es0_tag push_outer_tag; + enum ocelot_es0_tag push_inner_tag; + enum ocelot_tag_tpid_sel tag_a_tpid_sel; + int tag_a_vid_sel; + int tag_a_pcp_sel; + u16 vid_a_val; + u8 pcp_a_val; + u8 dei_a_val; + enum ocelot_tag_tpid_sel tag_b_tpid_sel; + int tag_b_vid_sel; + int tag_b_pcp_sel; + u16 vid_b_val; + u8 pcp_b_val; + u8 dei_b_val; + }; + + /* VCAP IS1 */ + struct { + bool vid_replace_ena; + u16 vid; + bool vlan_pop_cnt_ena; + int vlan_pop_cnt; + bool pcp_dei_ena; + u8 pcp; + u8 dei; + bool qos_ena; + u8 qos_val; + u8 pag_override_mask; + u8 pag_val; + }; + + /* VCAP IS2 */ + struct { + bool cpu_copy_ena; + u8 cpu_qu_num; + enum ocelot_mask_mode mask_mode; + unsigned long port_mask; + bool police_ena; + struct ocelot_policer pol; + u32 pol_ix; + }; + }; +}; + +struct ocelot_vcap_stats { + u64 bytes; + u64 pkts; + u64 used; +}; + +enum ocelot_vcap_filter_type { + OCELOT_VCAP_FILTER_DUMMY, + OCELOT_VCAP_FILTER_PAG, + OCELOT_VCAP_FILTER_OFFLOAD, +}; + +struct ocelot_vcap_filter { + struct list_head list; + + enum ocelot_vcap_filter_type type; + int block_id; + int goto_target; + int lookup; + u8 pag; + u16 prio; + u32 id; + + struct ocelot_vcap_action action; + struct ocelot_vcap_stats stats; + /* For VCAP IS1 and IS2 */ + unsigned long ingress_port_mask; + /* For VCAP ES0 */ + struct ocelot_vcap_port ingress_port; + struct ocelot_vcap_port egress_port; + + enum ocelot_vcap_bit dmac_mc; + enum ocelot_vcap_bit dmac_bc; + struct ocelot_vcap_key_vlan vlan; + + enum ocelot_vcap_key_type key_type; + union { + /* OCELOT_VCAP_KEY_ANY: No specific fields */ + struct ocelot_vcap_key_etype etype; + struct ocelot_vcap_key_llc llc; + struct ocelot_vcap_key_snap snap; + struct ocelot_vcap_key_arp arp; + struct ocelot_vcap_key_ipv4 ipv4; + struct ocelot_vcap_key_ipv6 ipv6; + } key; +}; + +int ocelot_vcap_filter_add(struct ocelot *ocelot, + struct ocelot_vcap_filter *rule, + struct netlink_ext_ack *extack); +int ocelot_vcap_filter_del(struct ocelot *ocelot, + struct ocelot_vcap_filter *rule); + #endif /* _OCELOT_VCAP_H_ */ -- cgit v1.2.3 From 50c6cc5b9283efdbf72162dee467bd68c7167807 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 29 Jan 2021 03:00:01 +0200 Subject: net: mscc: ocelot: store a namespaced VCAP filter ID We will be adding some private VCAP filters that should not interfere in any way with the filters added using tc-flower. So we need to allocate some IDs which will not be used by tc. Currently ocelot uses an u32 id derived from the flow cookie, which in itself is an unsigned long. This is a problem in itself, since on 64 bit systems, sizeof(unsigned long)=8, so the driver is already truncating these. Create a struct ocelot_vcap_id which contains the full unsigned long cookie from tc, as well as a boolean that is supposed to namespace the filters added by tc with the ones that aren't. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot_vcap.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index 7f1b82fba63c..76e01c927e17 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -648,6 +648,11 @@ enum ocelot_vcap_filter_type { OCELOT_VCAP_FILTER_OFFLOAD, }; +struct ocelot_vcap_id { + unsigned long cookie; + bool tc_offload; +}; + struct ocelot_vcap_filter { struct list_head list; @@ -657,7 +662,7 @@ struct ocelot_vcap_filter { int lookup; u8 pag; u16 prio; - u32 id; + struct ocelot_vcap_id id; struct ocelot_vcap_action action; struct ocelot_vcap_stats stats; -- cgit v1.2.3 From cacea62fcdda5656cb5b8104e73a00e043b61730 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 29 Jan 2021 03:00:03 +0200 Subject: net: mscc: ocelot: don't use NPI tag prefix for the CPU port module Context: Ocelot switches put the injection/extraction frame header in front of the Ethernet header. When used in NPI mode, a DSA master would see junk instead of the destination MAC address, and it would most likely drop the packets. So the Ocelot frame header can have an optional prefix, which is just "ff:ff:ff:ff:ff:fe > ff:ff:ff:ff:ff:ff" padding put before the actual tag (still before the real Ethernet header) such that the DSA master thinks it's looking at a broadcast frame with a strange EtherType. Unfortunately, a lesson learned in commit 69df578c5f4b ("net: mscc: ocelot: eliminate confusion between CPU and NPI port") seems to have been forgotten in the meanwhile. The CPU port module and the NPI port have independent settings for the length of the tag prefix. However, the driver is using the same variable to program both of them. There is no reason really to use any tag prefix with the CPU port module, since that is not connected to any Ethernet port. So this patch makes the inj_prefix and xtr_prefix variables apply only to the NPI port (which the switchdev ocelot_vsc7514 driver does not use). Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index cdc33fa05660..93c22627dedd 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -651,8 +651,8 @@ struct ocelot { int npi; - enum ocelot_tag_prefix inj_prefix; - enum ocelot_tag_prefix xtr_prefix; + enum ocelot_tag_prefix npi_inj_prefix; + enum ocelot_tag_prefix npi_xtr_prefix; u32 *lags; -- cgit v1.2.3 From 357f203bb3b529fa7471494c7ad6a7a54d070353 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 29 Jan 2021 03:00:05 +0200 Subject: net: dsa: keep a copy of the tagging protocol in the DSA switch tree Cascading DSA switches can be done multiple ways. There is the brute force approach / tag stacking, where one upstream switch, located between leaf switches and the host Ethernet controller, will just happily transport the DSA header of those leaf switches as payload. For this kind of setups, DSA works without any special kind of treatment compared to a single switch - they just aren't aware of each other. Then there's the approach where the upstream switch understands the tags it transports from its leaves below, as it doesn't push a tag of its own, but it routes based on the source port & switch id information present in that tag (as opposed to DMAC & VID) and it strips the tag when egressing a front-facing port. Currently only Marvell implements the latter, and Marvell DSA trees contain only Marvell switches. So it is safe to say that DSA trees already have a single tag protocol shared by all switches, and in fact this is what makes the switches able to understand each other. This fact is also implied by the fact that currently, the tagging protocol is reported as part of a sysfs installed on the DSA master and not per port, so it must be the same for all the ports connected to that DSA master regardless of the switch that they belong to. It's time to make this official and enforce it (yes, this also means we won't have any "switch understands tag to some extent but is not able to speak it" hardware oddities that we'll support in the future). This is needed due to the imminent introduction of the dsa_switch_ops:: change_tag_protocol driver API. When that is introduced, we'll have to notify switches of the tagging protocol that they're configured to use. Currently the tag_ops structure pointer is held only for CPU ports. But there are switches which don't have CPU ports and nonetheless still need to be configured. These would be Marvell leaf switches whose upstream port is just a DSA link. How do we inform these of their tagging protocol setup/deletion? One answer to the above would be: iterate through the DSA switch tree's ports once, list the CPU ports, get their tag_ops, then iterate again now that we have it, and notify everybody of that tag_ops. But what to do if conflicts appear between one cpu_dp->tag_ops and another? There's no escaping the fact that conflict resolution needs to be done, so we can be upfront about it. Ease our work and just keep the master copy of the tag_ops inside the struct dsa_switch_tree. Reference counting is now moved to be per-tree too, instead of per-CPU port. There are many places in the data path that access master->dsa_ptr->tag_ops and we would introduce unnecessary performance penalty going through yet another indirection, so keep those right where they are. Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 2f5435d3d1db..b8af1d6c879a 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -140,6 +140,9 @@ struct dsa_switch_tree { /* Has this tree been applied to the hardware? */ bool setup; + /* Tagging protocol operations */ + const struct dsa_device_ops *tag_ops; + /* * Configuration data for the platform device that owns * this dsa switch tree instance. @@ -225,7 +228,9 @@ struct dsa_port { struct net_device *slave; }; - /* CPU port tagging operations used by master or slave devices */ + /* Copy of the tagging protocol operations, for quicker access + * in the data path. Valid only for the CPU ports. + */ const struct dsa_device_ops *tag_ops; /* Copies for faster access in master receive hot path */ -- cgit v1.2.3 From 53da0ebaad102626f56495e0967a614f89a2acc8 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 29 Jan 2021 03:00:06 +0200 Subject: net: dsa: allow changing the tag protocol via the "tagging" device attribute Currently DSA exposes the following sysfs: $ cat /sys/class/net/eno2/dsa/tagging ocelot which is a read-only device attribute, introduced in the kernel as commit 98cdb4807123 ("net: dsa: Expose tagging protocol to user-space"), and used by libpcap since its commit 993db3800d7d ("Add support for DSA link-layer types"). It would be nice if we could extend this device attribute by making it writable: $ echo ocelot-8021q > /sys/class/net/eno2/dsa/tagging This is useful with DSA switches that can make use of more than one tagging protocol. It may be useful in dsa_loop in the future too, to perform offline testing of various taggers, or for changing between dsa and edsa on Marvell switches, if that is desirable. In terms of implementation, drivers can support this feature by implementing .change_tag_protocol, which should always leave the switch in a consistent state: either with the new protocol if things went well, or with the old one if something failed. Teardown of the old protocol, if necessary, must be handled by the driver. Some things remain as before: - The .get_tag_protocol is currently only called at probe time, to load the initial tagging protocol driver. Nonetheless, new drivers should report the tagging protocol in current use now. - The driver should manage by itself the initial setup of tagging protocol, no later than the .setup() method, as well as destroying resources used by the last tagger in use, no earlier than the .teardown() method. For multi-switch DSA trees, error handling is a bit more complicated, since e.g. the 5th out of 7 switches may fail to change the tag protocol. When that happens, a revert to the original tag protocol is attempted, but that may fail too, leaving the tree in an inconsistent state despite each individual switch implementing .change_tag_protocol transactionally. Since the intersection between drivers that implement .change_tag_protocol and drivers that support D in DSA is currently the empty set, the possibility for this error to happen is ignored for now. Testing: $ insmod mscc_felix.ko [ 79.549784] mscc_felix 0000:00:00.5: Adding to iommu group 14 [ 79.565712] mscc_felix 0000:00:00.5: Failed to register DSA switch: -517 $ insmod tag_ocelot.ko $ rmmod mscc_felix.ko $ insmod mscc_felix.ko [ 97.261724] libphy: VSC9959 internal MDIO bus: probed [ 97.267363] mscc_felix 0000:00:00.5: Found PCS at internal MDIO address 0 [ 97.274998] mscc_felix 0000:00:00.5: Found PCS at internal MDIO address 1 [ 97.282561] mscc_felix 0000:00:00.5: Found PCS at internal MDIO address 2 [ 97.289700] mscc_felix 0000:00:00.5: Found PCS at internal MDIO address 3 [ 97.599163] mscc_felix 0000:00:00.5 swp0 (uninitialized): PHY [0000:00:00.3:10] driver [Microsemi GE VSC8514 SyncE] (irq=POLL) [ 97.862034] mscc_felix 0000:00:00.5 swp1 (uninitialized): PHY [0000:00:00.3:11] driver [Microsemi GE VSC8514 SyncE] (irq=POLL) [ 97.950731] mscc_felix 0000:00:00.5 swp0: configuring for inband/qsgmii link mode [ 97.964278] 8021q: adding VLAN 0 to HW filter on device swp0 [ 98.146161] mscc_felix 0000:00:00.5 swp2 (uninitialized): PHY [0000:00:00.3:12] driver [Microsemi GE VSC8514 SyncE] (irq=POLL) [ 98.238649] mscc_felix 0000:00:00.5 swp1: configuring for inband/qsgmii link mode [ 98.251845] 8021q: adding VLAN 0 to HW filter on device swp1 [ 98.433916] mscc_felix 0000:00:00.5 swp3 (uninitialized): PHY [0000:00:00.3:13] driver [Microsemi GE VSC8514 SyncE] (irq=POLL) [ 98.485542] mscc_felix 0000:00:00.5: configuring for fixed/internal link mode [ 98.503584] mscc_felix 0000:00:00.5: Link is Up - 2.5Gbps/Full - flow control rx/tx [ 98.527948] device eno2 entered promiscuous mode [ 98.544755] DSA: tree 0 setup $ ping 10.0.0.1 PING 10.0.0.1 (10.0.0.1): 56 data bytes 64 bytes from 10.0.0.1: seq=0 ttl=64 time=2.337 ms 64 bytes from 10.0.0.1: seq=1 ttl=64 time=0.754 ms ^C - 10.0.0.1 ping statistics - 2 packets transmitted, 2 packets received, 0% packet loss round-trip min/avg/max = 0.754/1.545/2.337 ms $ cat /sys/class/net/eno2/dsa/tagging ocelot $ cat ./test_ocelot_8021q.sh #!/bin/bash ip link set swp0 down ip link set swp1 down ip link set swp2 down ip link set swp3 down ip link set swp5 down ip link set eno2 down echo ocelot-8021q > /sys/class/net/eno2/dsa/tagging ip link set eno2 up ip link set swp0 up ip link set swp1 up ip link set swp2 up ip link set swp3 up ip link set swp5 up $ ./test_ocelot_8021q.sh ./test_ocelot_8021q.sh: line 9: echo: write error: Protocol not available $ rmmod tag_ocelot.ko rmmod: can't unload module 'tag_ocelot': Resource temporarily unavailable $ insmod tag_ocelot_8021q.ko $ ./test_ocelot_8021q.sh $ cat /sys/class/net/eno2/dsa/tagging ocelot-8021q $ rmmod tag_ocelot.ko $ rmmod tag_ocelot_8021q.ko rmmod: can't unload module 'tag_ocelot_8021q': Resource temporarily unavailable $ ping 10.0.0.1 PING 10.0.0.1 (10.0.0.1): 56 data bytes 64 bytes from 10.0.0.1: seq=0 ttl=64 time=0.953 ms 64 bytes from 10.0.0.1: seq=1 ttl=64 time=0.787 ms 64 bytes from 10.0.0.1: seq=2 ttl=64 time=0.771 ms $ rmmod mscc_felix.ko [ 645.544426] mscc_felix 0000:00:00.5: Link is Down [ 645.838608] DSA: tree 0 torn down $ rmmod tag_ocelot_8021q.ko Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index b8af1d6c879a..7ea3918b2e61 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -485,9 +485,18 @@ static inline bool dsa_port_is_vlan_filtering(const struct dsa_port *dp) typedef int dsa_fdb_dump_cb_t(const unsigned char *addr, u16 vid, bool is_static, void *data); struct dsa_switch_ops { + /* + * Tagging protocol helpers called for the CPU ports and DSA links. + * @get_tag_protocol retrieves the initial tagging protocol and is + * mandatory. Switches which can operate using multiple tagging + * protocols should implement @change_tag_protocol and report in + * @get_tag_protocol the tagger in current use. + */ enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds, int port, enum dsa_tag_protocol mprot); + int (*change_tag_protocol)(struct dsa_switch *ds, int port, + enum dsa_tag_protocol proto); int (*setup)(struct dsa_switch *ds); void (*teardown)(struct dsa_switch *ds); -- cgit v1.2.3 From 7c83a7c539abe9f980996063ac20532a7a7f6eb1 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 29 Jan 2021 03:00:08 +0200 Subject: net: dsa: add a second tagger for Ocelot switches based on tag_8021q There are use cases for which the existing tagger, based on the NPI (Node Processor Interface) functionality, is insufficient. Namely: - Frames injected through the NPI port bypass the frame analyzer, so no source address learning is performed, no TSN stream classification, etc. - Flow control is not functional over an NPI port (PAUSE frames are encapsulated in the same Extraction Frame Header as all other frames) - There can be at most one NPI port configured for an Ocelot switch. But in NXP LS1028A and T1040 there are two Ethernet CPU ports. The non-NPI port is currently either disabled, or operated as a plain user port (albeit an internally-facing one). Having the ability to configure the two CPU ports symmetrically could pave the way for e.g. creating a LAG between them, to increase bandwidth seamlessly for the system. So there is a desire to have an alternative to the NPI mode. This change keeps the default tagger for the Seville and Felix switches as "ocelot", but it can be changed via the following device attribute: echo ocelot-8021q > /sys/class//dsa/tagging Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 7ea3918b2e61..60acb9fca124 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -47,6 +47,7 @@ struct phylink_link_state; #define DSA_TAG_PROTO_RTL4_A_VALUE 17 #define DSA_TAG_PROTO_HELLCREEK_VALUE 18 #define DSA_TAG_PROTO_XRS700X_VALUE 19 +#define DSA_TAG_PROTO_OCELOT_8021Q_VALUE 20 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -69,6 +70,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_RTL4_A = DSA_TAG_PROTO_RTL4_A_VALUE, DSA_TAG_PROTO_HELLCREEK = DSA_TAG_PROTO_HELLCREEK_VALUE, DSA_TAG_PROTO_XRS700X = DSA_TAG_PROTO_XRS700X_VALUE, + DSA_TAG_PROTO_OCELOT_8021Q = DSA_TAG_PROTO_OCELOT_8021Q_VALUE, }; struct packet_type; -- cgit v1.2.3 From e21268efbe26d9ab3f7468577d691b992d76e06a Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 29 Jan 2021 03:00:09 +0200 Subject: net: dsa: felix: perform switch setup for tag_8021q Unlike sja1105, the only other user of the software-defined tag_8021q.c tagger format, the implementation we choose for the Felix DSA switch driver preserves full functionality under a vlan_filtering bridge (i.e. IP termination works through the DSA user ports under all circumstances). The tag_8021q protocol just wants: - Identifying the ingress switch port based on the RX VLAN ID, as seen by the CPU. We achieve this by using the TCAM engines (which are also used for tc-flower offload) to push the RX VLAN as a second, outer tag, on egress towards the CPU port. - Steering traffic injected into the switch from the network stack towards the correct front port based on the TX VLAN, and consuming (popping) that header on the switch's egress. A tc-flower pseudocode of the static configuration done by the driver would look like this: $ tc qdisc add dev clsact $ for eth in swp0 swp1 swp2 swp3; do \ tc filter add dev egress flower indev ${eth} \ action vlan push id protocol 802.1ad; \ tc filter add dev ingress protocol 802.1Q flower vlan_id action vlan pop \ action mirred egress redirect dev ${eth}; \ done but of course since DSA does not register network interfaces for the CPU port, this configuration would be impossible for the user to do. Also, due to the same reason, it is impossible for the user to inadvertently delete these rules using tc. These rules do not collide in any way with tc-flower, they just consume some TCAM space, which is something we can live with. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot.h | 2 ++ include/soc/mscc/ocelot_vcap.h | 3 +++ 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 93c22627dedd..6a61c499a30d 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -610,6 +610,7 @@ struct ocelot_port { phy_interface_t phy_mode; u8 *xmit_template; + bool is_dsa_8021q_cpu; }; struct ocelot { @@ -760,6 +761,7 @@ void ocelot_adjust_link(struct ocelot *ocelot, int port, struct phy_device *phydev); int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, bool enabled); void ocelot_bridge_stp_state_set(struct ocelot *ocelot, int port, u8 state); +void ocelot_apply_bridge_fwd_mask(struct ocelot *ocelot); int ocelot_port_bridge_join(struct ocelot *ocelot, int port, struct net_device *bridge); int ocelot_port_bridge_leave(struct ocelot *ocelot, int port, diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index 76e01c927e17..25fd525aaf92 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -693,5 +693,8 @@ int ocelot_vcap_filter_add(struct ocelot *ocelot, struct netlink_ext_ack *extack); int ocelot_vcap_filter_del(struct ocelot *ocelot, struct ocelot_vcap_filter *rule); +struct ocelot_vcap_filter * +ocelot_vcap_block_find_filter_by_id(struct ocelot_vcap_block *block, int id, + bool tc_offload); #endif /* _OCELOT_VCAP_H_ */ -- cgit v1.2.3 From 14e8e0f6008865d823a8184a276702a6c3cbef3d Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Fri, 29 Jan 2021 13:54:38 -0500 Subject: tcp: shrink inet_connection_sock icsk_mtup enabled and probe_size This commit shrinks inet_connection_sock by 4 bytes, by shrinking icsk_mtup.enabled from 32 bits to 1 bit, and shrinking icsk_mtup.probe_size from s32 to an unsuigned 31 bit field. This is to save space to compensate for the recent introduction of a new u32 in inet_connection_sock, icsk_probes_tstamp, in the recent bug fix commit 9d9b1ee0b2d1 ("tcp: fix TCP_USER_TIMEOUT with zero window"). This should not change functionality, since icsk_mtup.enabled is only ever set to 0 or 1, and icsk_mtup.probe_size can only be either 0 or a positive MTU value returned by tcp_mss_to_mtu() Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20210129185438.1813237-1-ncardwell.kernel@gmail.com Signed-off-by: Jakub Kicinski --- include/net/inet_connection_sock.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index c11f80f328f1..10a625760de9 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -120,14 +120,14 @@ struct inet_connection_sock { __u16 rcv_mss; /* MSS used for delayed ACK decisions */ } icsk_ack; struct { - int enabled; - /* Range of MTUs to search */ int search_high; int search_low; /* Information on the current probe. */ - int probe_size; + u32 probe_size:31, + /* Is the MTUP feature enabled for this connection? */ + enabled:1; u32 probe_timestamp; } icsk_mtup; -- cgit v1.2.3 From 8b1c324c9faeb3e159256df0b84f9251a7941a33 Mon Sep 17 00:00:00 2001 From: Yu Liu Date: Fri, 29 Jan 2021 13:53:48 -0800 Subject: Bluetooth: Skip eSCO 2M params when not supported If a peer device doesn't support eSCO 2M we should skip the params that use it when setting up sync connection since they will always fail. Signed-off-by: Yu Liu Reviewed-by: Abhishek Pandit-Subedi Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index fd1d10fe2f11..ebdd4afe30d2 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1365,6 +1365,7 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define lmp_le_capable(dev) ((dev)->features[0][4] & LMP_LE) #define lmp_sniffsubr_capable(dev) ((dev)->features[0][5] & LMP_SNIFF_SUBR) #define lmp_pause_enc_capable(dev) ((dev)->features[0][5] & LMP_PAUSE_ENC) +#define lmp_esco_2m_capable(dev) ((dev)->features[0][5] & LMP_EDR_ESCO_2M) #define lmp_ext_inq_capable(dev) ((dev)->features[0][6] & LMP_EXT_INQ) #define lmp_le_br_capable(dev) (!!((dev)->features[0][6] & LMP_SIMUL_LE_BR)) #define lmp_ssp_capable(dev) ((dev)->features[0][6] & LMP_SIMPLE_PAIR) -- cgit v1.2.3 From 40c575d1ec71f7a61c73ba1603a69650c130559c Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 1 Feb 2021 19:20:50 +0100 Subject: cfg80211: fix netdev registration deadlock If register_netdevice() fails after having called cfg80211's netdev notifier (cfg80211_netdev_notifier_call) it will call the notifier again with UNREGISTER. This would then lock the wiphy mutex because we're marked as registered, which causes a deadlock. Fix this by separately keeping track of whether or not we're in the middle of registering to also skip the notifier call on this unregister. Reported-by: syzbot+2ae0ca9d7737ad1a62b7@syzkaller.appspotmail.com Fixes: a05829a7222e ("cfg80211: avoid holding the RTNL when calling the driver") Link: https://lore.kernel.org/r/20210201192048.ed8bad436737.I7cae042c44b15f80919a285799a15df467e9d42d@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 4741d71ead21..4cdd75449d73 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5299,6 +5299,8 @@ static inline void wiphy_unlock(struct wiphy *wiphy) * @wiphy: pointer to hardware description * @iftype: interface type * @registered: is this wdev already registered with cfg80211 + * @registering: indicates we're doing registration under wiphy lock + * for the notifier * @list: (private) Used to collect the interfaces * @netdev: (private) Used to reference back to the netdev, may be %NULL * @identifier: (private) Identifier used in nl80211 to identify this @@ -5382,7 +5384,7 @@ struct wireless_dev { struct mutex mtx; - bool use_4addr, is_running, registered; + bool use_4addr, is_running, registered, registering; u8 address[ETH_ALEN] __aligned(sizeof(u16)); -- cgit v1.2.3 From 680aea08e78c003292415518ad270bc20f9c80b1 Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Mon, 1 Feb 2021 21:47:52 +0200 Subject: net: ipv4: Emit notification when fib hardware flags are changed After installing a route to the kernel, user space receives an acknowledgment, which means the route was installed in the kernel, but not necessarily in hardware. The asynchronous nature of route installation in hardware can lead to a routing daemon advertising a route before it was actually installed in hardware. This can result in packet loss or mis-routed packets until the route is installed in hardware. It is also possible for a route already installed in hardware to change its action and therefore its flags. For example, a host route that is trapping packets can be "promoted" to perform decapsulation following the installation of an IPinIP/VXLAN tunnel. Emit RTM_NEWROUTE notifications whenever RTM_F_OFFLOAD/RTM_F_TRAP flags are changed. The aim is to provide an indication to user-space (e.g., routing daemons) about the state of the route in hardware. Introduce a sysctl that controls this behavior. Keep the default value at 0 (i.e., do not emit notifications) for several reasons: - Multiple RTM_NEWROUTE notification per-route might confuse existing routing daemons. - Convergence reasons in routing daemons. - The extra notifications will negatively impact the insertion rate. - Not all users are interested in these notifications. Signed-off-by: Amit Cohen Acked-by: Roopa Prabhu Signed-off-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- include/net/netns/ipv4.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 8e4fcac4df72..70a2a085dd1a 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -188,6 +188,8 @@ struct netns_ipv4 { int sysctl_udp_wmem_min; int sysctl_udp_rmem_min; + int sysctl_fib_notify_on_flag_change; + #ifdef CONFIG_NET_L3_MASTER_DEV int sysctl_udp_l3mdev_accept; #endif -- cgit v1.2.3 From fbaca8f895a6855b0b442227bc21da2d4cf77a01 Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Mon, 1 Feb 2021 21:47:53 +0200 Subject: net: Pass 'net' struct as first argument to fib6_info_hw_flags_set() The next patch will emit notification when hardware flags are changed, in case that fib_notify_on_flag_change sysctl is set to 1. To know sysctl values, net struct is needed. This change is consistent with the IPv4 version, which gets 'net' struct as its first argument. Currently, the only callers of this function are mlxsw and netdevsim. Patch the callers to pass net. Signed-off-by: Amit Cohen Signed-off-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- include/net/ip6_fib.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index ac5ff3c3afb1..cc189e668adf 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -336,8 +336,9 @@ static inline void fib6_info_release(struct fib6_info *f6i) call_rcu(&f6i->rcu, fib6_info_destroy_rcu); } -static inline void fib6_info_hw_flags_set(struct fib6_info *f6i, bool offload, - bool trap) +static inline void +fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i, bool offload, + bool trap) { f6i->offload = offload; f6i->trap = trap; -- cgit v1.2.3 From 907eea486888cfe118c19759bbc4b8fca2e004df Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Mon, 1 Feb 2021 21:47:55 +0200 Subject: net: ipv6: Emit notification when fib hardware flags are changed After installing a route to the kernel, user space receives an acknowledgment, which means the route was installed in the kernel, but not necessarily in hardware. The asynchronous nature of route installation in hardware can lead to a routing daemon advertising a route before it was actually installed in hardware. This can result in packet loss or mis-routed packets until the route is installed in hardware. It is also possible for a route already installed in hardware to change its action and therefore its flags. For example, a host route that is trapping packets can be "promoted" to perform decapsulation following the installation of an IPinIP/VXLAN tunnel. Emit RTM_NEWROUTE notifications whenever RTM_F_OFFLOAD/RTM_F_TRAP flags are changed. The aim is to provide an indication to user-space (e.g., routing daemons) about the state of the route in hardware. Introduce a sysctl that controls this behavior. Keep the default value at 0 (i.e., do not emit notifications) for several reasons: - Multiple RTM_NEWROUTE notification per-route might confuse existing routing daemons. - Convergence reasons in routing daemons. - The extra notifications will negatively impact the insertion rate. - Not all users are interested in these notifications. Move fib6_info_hw_flags_set() to C file because it is no longer a short function. Signed-off-by: Amit Cohen Signed-off-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- include/net/ip6_fib.h | 10 ++-------- include/net/netns/ipv6.h | 1 + 2 files changed, 3 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index cc189e668adf..1e262b23c68b 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -336,14 +336,6 @@ static inline void fib6_info_release(struct fib6_info *f6i) call_rcu(&f6i->rcu, fib6_info_destroy_rcu); } -static inline void -fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i, bool offload, - bool trap) -{ - f6i->offload = offload; - f6i->trap = trap; -} - enum fib6_walk_state { #ifdef CONFIG_IPV6_SUBTREES FWS_S, @@ -546,6 +538,8 @@ static inline bool fib6_metric_locked(struct fib6_info *f6i, int metric) { return !!(f6i->fib6_metrics->metrics[RTAX_LOCK - 1] & (1 << metric)); } +void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i, + bool offload, bool trap); #if IS_BUILTIN(CONFIG_IPV6) && defined(CONFIG_BPF_SYSCALL) struct bpf_iter__ipv6_route { diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 5ec054473d81..21c0debbd39e 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -51,6 +51,7 @@ struct netns_sysctl_ipv6 { int max_hbh_opts_len; int seg6_flowlabel; bool skip_notify_on_dev_down; + int fib_notify_on_flag_change; }; struct netns_ipv6 { -- cgit v1.2.3 From 4f4e54366eae20d5867864001db57c5d90693d8c Mon Sep 17 00:00:00 2001 From: Emil Renner Berthing Date: Sun, 31 Jan 2021 00:46:37 +0100 Subject: net: usb: cdc_ncm: use new API for bh tasklet This converts the driver to use the new tasklet API introduced in commit 12cc923f1ccc ("tasklet: Introduce new initialization API") It is unfortunate that we need to add a pointer to the driver context to get back to the usbnet device, but the space will be reclaimed once there are no more users of the old API left and we can remove the data value and flag from the tasklet struct. Signed-off-by: Emil Renner Berthing Link: https://lore.kernel.org/r/20210130234637.26505-1-kernel@esmil.dk Signed-off-by: Jakub Kicinski --- include/linux/usb/cdc_ncm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index 0ce4377545f8..f7cb3ddce7fb 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -98,6 +98,8 @@ struct cdc_ncm_ctx { struct hrtimer tx_timer; struct tasklet_struct bh; + struct usbnet *dev; + const struct usb_cdc_ncm_desc *func_desc; const struct usb_cdc_mbim_desc *mbim_desc; const struct usb_cdc_mbim_extended_desc *mbim_extended_desc; -- cgit v1.2.3 From e43b21906439ed14dda84f9784d38c03d0464607 Mon Sep 17 00:00:00 2001 From: Brian Vazquez Date: Mon, 1 Feb 2021 17:41:29 +0000 Subject: net: use indirect call helpers for dst_input This patch avoids the indirect call for the common case: ip_local_deliver and ip6_input Signed-off-by: Brian Vazquez Signed-off-by: Jakub Kicinski --- include/net/dst.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/dst.h b/include/net/dst.h index 10f0a8399867..98cf6e8c06c4 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -18,6 +18,7 @@ #include #include #include +#include struct sk_buff; @@ -441,10 +442,13 @@ static inline int dst_output(struct net *net, struct sock *sk, struct sk_buff *s return skb_dst(skb)->output(net, sk, skb); } +INDIRECT_CALLABLE_DECLARE(int ip6_input(struct sk_buff *)); +INDIRECT_CALLABLE_DECLARE(int ip_local_deliver(struct sk_buff *)); /* Input packet from network to transport. */ static inline int dst_input(struct sk_buff *skb) { - return skb_dst(skb)->input(skb); + return INDIRECT_CALL_INET(skb_dst(skb)->input, + ip6_input, ip_local_deliver, skb); } static inline struct dst_entry *dst_check(struct dst_entry *dst, u32 cookie) -- cgit v1.2.3 From 6585d7dc491d9d5e323ed52ee32ad071e04c9dfa Mon Sep 17 00:00:00 2001 From: Brian Vazquez Date: Mon, 1 Feb 2021 17:41:30 +0000 Subject: net: use indirect call helpers for dst_output This patch avoids the indirect call for the common case: ip6_output and ip_output Signed-off-by: Brian Vazquez Signed-off-by: Jakub Kicinski --- include/net/dst.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/dst.h b/include/net/dst.h index 98cf6e8c06c4..3932e9931f08 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -436,10 +436,16 @@ static inline void dst_set_expires(struct dst_entry *dst, int timeout) dst->expires = expires; } +INDIRECT_CALLABLE_DECLARE(int ip6_output(struct net *, struct sock *, + struct sk_buff *)); +INDIRECT_CALLABLE_DECLARE(int ip_output(struct net *, struct sock *, + struct sk_buff *)); /* Output packet to network from transport. */ static inline int dst_output(struct net *net, struct sock *sk, struct sk_buff *skb) { - return skb_dst(skb)->output(net, sk, skb); + return INDIRECT_CALL_INET(skb_dst(skb)->output, + ip6_output, ip_output, + net, sk, skb); } INDIRECT_CALLABLE_DECLARE(int ip6_input(struct sk_buff *)); -- cgit v1.2.3 From f67fbeaebdc0356e0cbc94f4b099f45ebe174b02 Mon Sep 17 00:00:00 2001 From: Brian Vazquez Date: Mon, 1 Feb 2021 17:41:31 +0000 Subject: net: use indirect call helpers for dst_mtu This patch avoids the indirect call for the common case: ip6_mtu and ipv4_mtu Signed-off-by: Brian Vazquez Signed-off-by: Jakub Kicinski --- include/net/dst.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/dst.h b/include/net/dst.h index 3932e9931f08..9f474a79ed7d 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -194,9 +194,11 @@ dst_feature(const struct dst_entry *dst, u32 feature) return dst_metric(dst, RTAX_FEATURES) & feature; } +INDIRECT_CALLABLE_DECLARE(unsigned int ip6_mtu(const struct dst_entry *)); +INDIRECT_CALLABLE_DECLARE(unsigned int ipv4_mtu(const struct dst_entry *)); static inline u32 dst_mtu(const struct dst_entry *dst) { - return dst->ops->mtu(dst); + return INDIRECT_CALL_INET(dst->ops->mtu, ip6_mtu, ipv4_mtu, dst); } /* RTT metrics are stored in milliseconds for user ABI, but used as jiffies */ -- cgit v1.2.3 From bbd807dfbf20506f5548b0297c430a09326e7c4b Mon Sep 17 00:00:00 2001 From: Brian Vazquez Date: Mon, 1 Feb 2021 17:41:32 +0000 Subject: net: indirect call helpers for ipv4/ipv6 dst_check functions This patch avoids the indirect call for the common case: ip6_dst_check and ipv4_dst_check Signed-off-by: Brian Vazquez Signed-off-by: Jakub Kicinski --- include/net/dst.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/dst.h b/include/net/dst.h index 9f474a79ed7d..26f134ad3a25 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -459,10 +459,15 @@ static inline int dst_input(struct sk_buff *skb) ip6_input, ip_local_deliver, skb); } +INDIRECT_CALLABLE_DECLARE(struct dst_entry *ip6_dst_check(struct dst_entry *, + u32)); +INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *, + u32)); static inline struct dst_entry *dst_check(struct dst_entry *dst, u32 cookie) { if (dst->obsolete) - dst = dst->ops->check(dst, cookie); + dst = INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, + ipv4_dst_check, dst, cookie); return dst; } -- cgit v1.2.3 From 65e6dcf73398ddb64bb782ff2acd918d3a37a53a Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 29 Jan 2021 23:04:08 +0100 Subject: net, veth: Alloc skb in bulk for ndo_xdp_xmit Split ndo_xdp_xmit and ndo_start_xmit use cases in veth_xdp_rcv routine in order to alloc skbs in bulk for XDP_PASS verdict. Introduce xdp_alloc_skb_bulk utility routine to alloc skb bulk list. The proposed approach has been tested in the following scenario: eth (ixgbe) --> XDP_REDIRECT --> veth0 --> (remote-ns) veth1 --> XDP_PASS XDP_REDIRECT: xdp_redirect_map bpf sample XDP_PASS: xdp_rxq_info bpf sample traffic generator: pkt_gen sending udp traffic on a remote device bpf-next master: ~3.64Mpps bpf-next + skb bulking allocation: ~3.79Mpps Signed-off-by: Lorenzo Bianconi Signed-off-by: Daniel Borkmann Reviewed-by: Toshiaki Makita Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/bpf/a14a30d3c06fff24e13f836c733d80efc0bd6eb5.1611957532.git.lorenzo@kernel.org --- include/net/xdp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/xdp.h b/include/net/xdp.h index c4bfdc9a8b79..a5bc214a49d9 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -169,6 +169,7 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct net_device *dev); struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct net_device *dev); +int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp); static inline void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp) -- cgit v1.2.3 From 012ce4dd3102a0f4d80167de343e9d44b257c1b8 Mon Sep 17 00:00:00 2001 From: Danielle Ratson Date: Tue, 2 Feb 2021 20:06:06 +0200 Subject: ethtool: Extend link modes settings uAPI with lanes Currently, when auto negotiation is on, the user can advertise all the linkmodes which correspond to a specific speed, but does not have a similar selector for the number of lanes. This is significant when a specific speed can be achieved using different number of lanes. For example, 2x50 or 4x25. Add 'ETHTOOL_A_LINKMODES_LANES' attribute and expand 'struct ethtool_link_settings' with lanes field in order to implement a new lanes-selector that will enable the user to advertise a specific number of lanes as well. When auto negotiation is off, lanes parameter can be forced only if the driver supports it. Add a capability bit in 'struct ethtool_ops' that allows ethtool know if the driver can handle the lanes parameter when auto negotiation is off, so if it does not, an error message will be returned when trying to set lanes. Example: $ ethtool -s swp1 lanes 4 $ ethtool swp1 Settings for swp1: Supported ports: [ FIBRE ] Supported link modes: 1000baseKX/Full 10000baseKR/Full 40000baseCR4/Full 40000baseSR4/Full 40000baseLR4/Full 25000baseCR/Full 25000baseSR/Full 50000baseCR2/Full 100000baseSR4/Full 100000baseCR4/Full Supported pause frame use: Symmetric Receive-only Supports auto-negotiation: Yes Supported FEC modes: Not reported Advertised link modes: 40000baseCR4/Full 40000baseSR4/Full 40000baseLR4/Full 100000baseSR4/Full 100000baseCR4/Full Advertised pause frame use: No Advertised auto-negotiation: Yes Advertised FEC modes: Not reported Speed: Unknown! Duplex: Unknown! (255) Auto-negotiation: on Port: Direct Attach Copper PHYAD: 0 Transceiver: internal Link detected: no Signed-off-by: Danielle Ratson Signed-off-by: Jakub Kicinski --- include/linux/ethtool.h | 4 ++++ include/uapi/linux/ethtool_netlink.h | 1 + 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index e3da25b51ae4..1ab13c5dfb2f 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -128,6 +128,7 @@ struct ethtool_link_ksettings { __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); } link_modes; + u32 lanes; }; /** @@ -265,6 +266,8 @@ struct ethtool_pause_stats { /** * struct ethtool_ops - optional netdev operations + * @cap_link_lanes_supported: indicates if the driver supports lanes + * parameter. * @supported_coalesce_params: supported types of interrupt coalescing. * @get_drvinfo: Report driver/device information. Should only set the * @driver, @version, @fw_version and @bus_info fields. If not @@ -420,6 +423,7 @@ struct ethtool_pause_stats { * of the generic netdev features interface. */ struct ethtool_ops { + u32 cap_link_lanes_supported:1; u32 supported_coalesce_params; void (*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *); int (*get_regs_len)(struct net_device *); diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index e2bf36e6964b..a286635ac9b8 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -227,6 +227,7 @@ enum { ETHTOOL_A_LINKMODES_DUPLEX, /* u8 */ ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG, /* u8 */ ETHTOOL_A_LINKMODES_MASTER_SLAVE_STATE, /* u8 */ + ETHTOOL_A_LINKMODES_LANES, /* u32 */ /* add new constants above here */ __ETHTOOL_A_LINKMODES_CNT, -- cgit v1.2.3 From c8907043c6ac9ed58e6c1a76f2824be714b42228 Mon Sep 17 00:00:00 2001 From: Danielle Ratson Date: Tue, 2 Feb 2021 20:06:07 +0200 Subject: ethtool: Get link mode in use instead of speed and duplex parameters Currently, when user space queries the link's parameters, as speed and duplex, each parameter is passed from the driver to ethtool. Instead, get the link mode bit in use, and derive each of the parameters from it in ethtool. Signed-off-by: Danielle Ratson Signed-off-by: Jakub Kicinski --- include/linux/ethtool.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 1ab13c5dfb2f..ec4cd3921c67 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -129,6 +129,7 @@ struct ethtool_link_ksettings { __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); } link_modes; u32 lanes; + enum ethtool_link_mode_bit_indices link_mode; }; /** -- cgit v1.2.3 From f5a5589c72509abaeb705123b64e7f5a078becf0 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Tue, 2 Feb 2021 11:34:08 -0800 Subject: tcp: use a smaller percpu_counter batch size for sk_alloc Currently, a percpu_counter with the default batch size (2*nr_cpus) is used to record the total # of active sockets per protocol. This means sk_sockets_allocated_read_positive() could be off by +/-2*(nr_cpus^2). This under/over-estimation could lead to wrong memory suppression conditions in __sk_raise_mem_allocated(). Fix this by using a more reasonable fixed batch size of 16. See related commit cf86a086a180 ("net/dst: use a smaller percpu_counter batch for dst entries accounting") that addresses a similar issue. Signed-off-by: Wei Wang Signed-off-by: Eric Dumazet Reviewed-by: Soheil Hassas Yeganeh Link: https://lore.kernel.org/r/20210202193408.1171634-1-weiwan@google.com Signed-off-by: Jakub Kicinski --- include/net/sock.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 129d200bccb4..690e496a0e79 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1350,14 +1350,18 @@ sk_memory_allocated_sub(struct sock *sk, int amt) atomic_long_sub(amt, sk->sk_prot->memory_allocated); } +#define SK_ALLOC_PERCPU_COUNTER_BATCH 16 + static inline void sk_sockets_allocated_dec(struct sock *sk) { - percpu_counter_dec(sk->sk_prot->sockets_allocated); + percpu_counter_add_batch(sk->sk_prot->sockets_allocated, -1, + SK_ALLOC_PERCPU_COUNTER_BATCH); } static inline void sk_sockets_allocated_inc(struct sock *sk) { - percpu_counter_inc(sk->sk_prot->sockets_allocated); + percpu_counter_add_batch(sk->sk_prot->sockets_allocated, 1, + SK_ALLOC_PERCPU_COUNTER_BATCH); } static inline u64 -- cgit v1.2.3 From 3dd344ea84e122f791ab55498aab985535f32cba Mon Sep 17 00:00:00 2001 From: Hariharan Ananthakrishnan Date: Fri, 29 Jan 2021 00:12:10 +0000 Subject: net: tracepoint: exposing sk_family in all tcp:tracepoints Similar to sock:inet_sock_set_state tracepoint, expose sk_family to distinguish AF_INET and AF_INET6 families. The following tcp tracepoints are updated: tcp:tcp_destroy_sock tcp:tcp_rcv_space_adjust tcp:tcp_retransmit_skb tcp:tcp_send_reset tcp:tcp_receive_reset tcp:tcp_retransmit_synack tcp:tcp_probe Signed-off-by: Hariharan Ananthakrishnan Signed-off-by: Brendan Gregg Link: https://lore.kernel.org/r/20210129001210.344438-1-hari@netflix.com Signed-off-by: Jakub Kicinski --- include/trace/events/tcp.h | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index cf97f6339acb..ba94857eea11 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -59,6 +59,7 @@ DECLARE_EVENT_CLASS(tcp_event_sk_skb, __field(int, state) __field(__u16, sport) __field(__u16, dport) + __field(__u16, family) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) @@ -75,6 +76,7 @@ DECLARE_EVENT_CLASS(tcp_event_sk_skb, __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); + __entry->family = sk->sk_family; p32 = (__be32 *) __entry->saddr; *p32 = inet->inet_saddr; @@ -86,7 +88,8 @@ DECLARE_EVENT_CLASS(tcp_event_sk_skb, sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); ), - TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c state=%s", + TP_printk("family=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c state=%s", + show_family_name(__entry->family), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, show_tcp_state_name(__entry->state)) @@ -125,6 +128,7 @@ DECLARE_EVENT_CLASS(tcp_event_sk, __field(const void *, skaddr) __field(__u16, sport) __field(__u16, dport) + __field(__u16, family) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) @@ -140,6 +144,7 @@ DECLARE_EVENT_CLASS(tcp_event_sk, __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); + __entry->family = sk->sk_family; p32 = (__be32 *) __entry->saddr; *p32 = inet->inet_saddr; @@ -153,7 +158,8 @@ DECLARE_EVENT_CLASS(tcp_event_sk, __entry->sock_cookie = sock_gen_cookie(sk); ), - TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c sock_cookie=%llx", + TP_printk("family=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c sock_cookie=%llx", + show_family_name(__entry->family), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, @@ -192,6 +198,7 @@ TRACE_EVENT(tcp_retransmit_synack, __field(const void *, req) __field(__u16, sport) __field(__u16, dport) + __field(__u16, family) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) @@ -207,6 +214,7 @@ TRACE_EVENT(tcp_retransmit_synack, __entry->sport = ireq->ir_num; __entry->dport = ntohs(ireq->ir_rmt_port); + __entry->family = sk->sk_family; p32 = (__be32 *) __entry->saddr; *p32 = ireq->ir_loc_addr; @@ -218,7 +226,8 @@ TRACE_EVENT(tcp_retransmit_synack, ireq->ir_v6_loc_addr, ireq->ir_v6_rmt_addr); ), - TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c", + TP_printk("family=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c", + show_family_name(__entry->family), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6) @@ -238,6 +247,7 @@ TRACE_EVENT(tcp_probe, __array(__u8, daddr, sizeof(struct sockaddr_in6)) __field(__u16, sport) __field(__u16, dport) + __field(__u16, family) __field(__u32, mark) __field(__u16, data_len) __field(__u32, snd_nxt) @@ -264,6 +274,7 @@ TRACE_EVENT(tcp_probe, __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); __entry->mark = skb->mark; + __entry->family = sk->sk_family; __entry->data_len = skb->len - __tcp_hdrlen(th); __entry->snd_nxt = tp->snd_nxt; @@ -276,7 +287,8 @@ TRACE_EVENT(tcp_probe, __entry->sock_cookie = sock_gen_cookie(sk); ), - TP_printk("src=%pISpc dest=%pISpc mark=%#x data_len=%d snd_nxt=%#x snd_una=%#x snd_cwnd=%u ssthresh=%u snd_wnd=%u srtt=%u rcv_wnd=%u sock_cookie=%llx", + TP_printk("family=%s src=%pISpc dest=%pISpc mark=%#x data_len=%d snd_nxt=%#x snd_una=%#x snd_cwnd=%u ssthresh=%u snd_wnd=%u srtt=%u rcv_wnd=%u sock_cookie=%llx", + show_family_name(__entry->family), __entry->saddr, __entry->daddr, __entry->mark, __entry->data_len, __entry->snd_nxt, __entry->snd_una, __entry->snd_cwnd, __entry->ssthresh, __entry->snd_wnd, -- cgit v1.2.3 From 49ecc587dca2754571791bebd36e9e36e2a0d973 Mon Sep 17 00:00:00 2001 From: Jonas Bonn Date: Wed, 3 Feb 2021 08:07:59 +0100 Subject: Revert "GTP: add support for flow based tunneling API" This reverts commit 9ab7e76aefc97a9aa664accb59d6e8dc5e52514a. This patch was committed without maintainer approval and despite a number of unaddressed concerns from review. There are several issues that impede the acceptance of this patch and that make a reversion of this particular instance of these changes the best way forward: i) the patch contains several logically separate changes that would be better served as smaller patches (for review purposes) ii) functionality like the handling of end markers has been introduced without further explanation iii) symmetry between the handling of GTPv0 and GTPv1 has been unnecessarily broken iv) the patchset produces 'broken' packets when extension headers are included v) there are no available userspace tools to allow for testing this functionality vi) there is an unaddressed Coverity report against the patch concering memory leakage vii) most importantly, the patch contains a large amount of superfluous churn that impedes other ongoing work with this driver This patch will be reworked into a series that aligns with other ongoing work and facilitates review. Signed-off-by: Jonas Bonn Acked-by: Harald Welte Acked-by: Pravin B Shelar Signed-off-by: Jakub Kicinski --- include/uapi/linux/gtp.h | 12 ------------ include/uapi/linux/if_link.h | 1 - include/uapi/linux/if_tunnel.h | 1 - 3 files changed, 14 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h index 62aff78b7c56..79f9191bbb24 100644 --- a/include/uapi/linux/gtp.h +++ b/include/uapi/linux/gtp.h @@ -2,8 +2,6 @@ #ifndef _UAPI_LINUX_GTP_H_ #define _UAPI_LINUX_GTP_H_ -#include - #define GTP_GENL_MCGRP_NAME "gtp" enum gtp_genl_cmds { @@ -36,14 +34,4 @@ enum gtp_attrs { }; #define GTPA_MAX (__GTPA_MAX + 1) -enum { - GTP_METADATA_V1 -}; - -struct gtpu_metadata { - __u8 ver; - __u8 flags; - __u8 type; -}; - #endif /* _UAPI_LINUX_GTP_H_ */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index eb8018c3a737..91c8dda6d95d 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -811,7 +811,6 @@ enum { IFLA_GTP_FD1, IFLA_GTP_PDP_HASHSIZE, IFLA_GTP_ROLE, - IFLA_GTP_COLLECT_METADATA, __IFLA_GTP_MAX, }; #define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1) diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index 802da679fab1..7d9105533c7b 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -176,7 +176,6 @@ enum { #define TUNNEL_VXLAN_OPT __cpu_to_be16(0x1000) #define TUNNEL_NOCACHE __cpu_to_be16(0x2000) #define TUNNEL_ERSPAN_OPT __cpu_to_be16(0x4000) -#define TUNNEL_GTPU_OPT __cpu_to_be16(0x8000) #define TUNNEL_OPTIONS_PRESENT \ (TUNNEL_GENEVE_OPT | TUNNEL_VXLAN_OPT | TUNNEL_ERSPAN_OPT) -- cgit v1.2.3 From 7e3ce05e7f650371061d0b9eec1e1cf74ed6fca0 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Wed, 3 Feb 2021 22:48:16 -0300 Subject: netlink: add tracepoint at NL_SET_ERR_MSG Often userspace won't request the extack information, or they don't log it because of log level or so, and even when they do, sometimes it's not enough to know exactly what caused the error. Netlink extack is the standard way of reporting erros with descriptive error messages. With a trace point on it, we then can know exactly where the error happened, regardless of userspace app. Also, we can even see if the err msg was overwritten. The wrapper do_trace_netlink_extack() is because trace points shouldn't be called from .h files, as trace points are not that small, and the function call to do_trace_netlink_extack() on the macros is not protected by tracepoint_enabled() because the macros are called from modules, and this would require exporting some trace structs. As this is error path, it's better to export just the wrapper instead. v2: removed leftover tracepoint declaration Signed-off-by: Marcelo Ricardo Leitner Reviewed-by: David Ahern Link: https://lore.kernel.org/r/4546b63e67b2989789d146498b13cc09e1fdc543.1612403190.git.marcelo.leitner@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/netlink.h | 6 ++++++ include/trace/events/netlink.h | 29 +++++++++++++++++++++++++++++ 2 files changed, 35 insertions(+) create mode 100644 include/trace/events/netlink.h (limited to 'include') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 9f118771e248..0bcf98098c5a 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -11,6 +11,8 @@ struct net; +void do_trace_netlink_extack(const char *msg); + static inline struct nlmsghdr *nlmsg_hdr(const struct sk_buff *skb) { return (struct nlmsghdr *)skb->data; @@ -90,6 +92,8 @@ struct netlink_ext_ack { static const char __msg[] = msg; \ struct netlink_ext_ack *__extack = (extack); \ \ + do_trace_netlink_extack(__msg); \ + \ if (__extack) \ __extack->_msg = __msg; \ } while (0) @@ -110,6 +114,8 @@ struct netlink_ext_ack { static const char __msg[] = msg; \ struct netlink_ext_ack *__extack = (extack); \ \ + do_trace_netlink_extack(__msg); \ + \ if (__extack) { \ __extack->_msg = __msg; \ __extack->bad_attr = (attr); \ diff --git a/include/trace/events/netlink.h b/include/trace/events/netlink.h new file mode 100644 index 000000000000..3b7be3b386a4 --- /dev/null +++ b/include/trace/events/netlink.h @@ -0,0 +1,29 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM netlink + +#if !defined(_TRACE_NETLINK_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_NETLINK_H + +#include + +TRACE_EVENT(netlink_extack, + + TP_PROTO(const char *msg), + + TP_ARGS(msg), + + TP_STRUCT__entry( + __string( msg, msg ) + ), + + TP_fast_assign( + __assign_str(msg, msg); + ), + + TP_printk("msg=%s", __get_str(msg)) +); + +#endif /* _TRACE_NETLINK_H */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3 From 0053859496baa17c7675526936677c9213bf5a0d Mon Sep 17 00:00:00 2001 From: Brian Vazquez Date: Thu, 4 Feb 2021 18:18:38 +0000 Subject: net: add EXPORT_INDIRECT_CALLABLE wrapper When a static function is annotated with INDIRECT_CALLABLE_SCOPE and CONFIG_RETPOLINE is set, the static keyword is removed. Sometimes the function needs to be exported but EXPORT_SYMBOL can't be used because if CONFIG_RETPOLINE is not set, we will attempt to export a static symbol. This patch introduces a new indirect call wrapper: EXPORT_INDIRECT_CALLABLE. This basically does EXPORT_SYMBOL when CONFIG_RETPOLINE is set, but does nothing when it's not. Reported-by: Stephen Rothwell Signed-off-by: Brian Vazquez Link: https://lore.kernel.org/r/20210204181839.558951-1-brianvv@google.com Signed-off-by: Jakub Kicinski --- include/linux/indirect_call_wrapper.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h index 54c02c84906a..a8345c8a613d 100644 --- a/include/linux/indirect_call_wrapper.h +++ b/include/linux/indirect_call_wrapper.h @@ -36,6 +36,7 @@ #define INDIRECT_CALLABLE_DECLARE(f) f #define INDIRECT_CALLABLE_SCOPE +#define EXPORT_INDIRECT_CALLABLE(f) EXPORT_SYMBOL(f) #else #define INDIRECT_CALL_1(f, f1, ...) f(__VA_ARGS__) @@ -44,6 +45,7 @@ #define INDIRECT_CALL_4(f, f4, f3, f2, f1, ...) f(__VA_ARGS__) #define INDIRECT_CALLABLE_DECLARE(f) #define INDIRECT_CALLABLE_SCOPE static +#define EXPORT_INDIRECT_CALLABLE(f) #endif /* -- cgit v1.2.3 From 1d7bab6a94458e959f3f55788fd50ddc7d97403b Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Tue, 2 Feb 2021 13:30:54 +0000 Subject: mm: constify page_is_pfmemalloc() argument The function only tests for page->index, so its argument should be const. Signed-off-by: Alexander Lobakin Reviewed-by: Jesse Brandeburg Acked-by: David Rientjes Signed-off-by: Jakub Kicinski --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index ecdf8a8cd6ae..078633d43af9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1584,7 +1584,7 @@ struct address_space *page_mapping_file(struct page *page); * ALLOC_NO_WATERMARKS and the low watermark was not * met implying that the system is under some pressure. */ -static inline bool page_is_pfmemalloc(struct page *page) +static inline bool page_is_pfmemalloc(const struct page *page) { /* * Page index cannot be this large so this must be -- cgit v1.2.3 From 48f971c9c80a728646fc03367a28df747f20d0f4 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Tue, 2 Feb 2021 13:31:05 +0000 Subject: skbuff: constify skb_propagate_pfmemalloc() "page" argument The function doesn't write anything to the page struct itself, so this argument can be const. Misc: align second argument to the brace while at it. Signed-off-by: Alexander Lobakin Reviewed-by: Jesse Brandeburg Acked-by: David Rientjes Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9313b5aaf45b..b027526da4f9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2943,8 +2943,8 @@ static inline struct page *dev_alloc_page(void) * @page: The page that was allocated from skb_alloc_page * @skb: The skb that may need pfmemalloc set */ -static inline void skb_propagate_pfmemalloc(struct page *page, - struct sk_buff *skb) +static inline void skb_propagate_pfmemalloc(const struct page *page, + struct sk_buff *skb) { if (page_is_pfmemalloc(page)) skb->pfmemalloc = true; -- cgit v1.2.3 From bc38f30f8dbce0afb8af05d917bee084b1329418 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Tue, 2 Feb 2021 13:31:21 +0000 Subject: net: introduce common dev_page_is_reusable() A bunch of drivers test the page before reusing/recycling for two common conditions: - if a page was allocated under memory pressure (pfmemalloc page); - if a page was allocated at a distant memory node (to exclude slowdowns). Introduce a new common inline for doing this, with likely() already folded inside to make driver code a bit simpler. Suggested-by: David Rientjes Suggested-by: Jakub Kicinski Cc: John Hubbard Signed-off-by: Alexander Lobakin Reviewed-by: Jesse Brandeburg Acked-by: David Rientjes Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b027526da4f9..0e42c53b8ca9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2938,6 +2938,22 @@ static inline struct page *dev_alloc_page(void) return dev_alloc_pages(0); } +/** + * dev_page_is_reusable - check whether a page can be reused for network Rx + * @page: the page to test + * + * A page shouldn't be considered for reusing/recycling if it was allocated + * under memory pressure or at a distant memory node. + * + * Returns false if this page should be returned to page allocator, true + * otherwise. + */ +static inline bool dev_page_is_reusable(const struct page *page) +{ + return likely(page_to_nid(page) == numa_mem_id() && + !page_is_pfmemalloc(page)); +} + /** * skb_propagate_pfmemalloc - Propagate pfmemalloc if skb is allocated after RX page * @page: The page that was allocated from skb_alloc_page -- cgit v1.2.3 From a4a600dd301ccde6ea239804ec1f19364a39d643 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 3 Feb 2021 16:54:22 +0800 Subject: udp: call udp_encap_enable for v6 sockets when enabling encap When enabling encap for a ipv6 socket without udp_encap_needed_key increased, UDP GRO won't work for v4 mapped v6 address packets as sk will be NULL in udp4_gro_receive(). This patch is to enable it by increasing udp_encap_needed_key for v6 sockets in udp_tunnel_encap_enable(), and correspondingly decrease udp_encap_needed_key in udpv6_destroy_sock(). v1->v2: - add udp_encap_disable() and export it. v2->v3: - add the change for rxrpc and bareudp into one patch, as Alex suggested. v3->v4: - move rxrpc part to another patch. Acked-by: Willem de Bruijn Signed-off-by: Xin Long Signed-off-by: Jakub Kicinski --- include/net/udp.h | 1 + include/net/udp_tunnel.h | 3 +-- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/udp.h b/include/net/udp.h index 01351ba25b87..5ddbb42fdb36 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -467,6 +467,7 @@ void udp_init(void); DECLARE_STATIC_KEY_FALSE(udp_encap_needed_key); void udp_encap_enable(void); +void udp_encap_disable(void); #if IS_ENABLED(CONFIG_IPV6) DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); void udpv6_encap_enable(void); diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index 282d10ee60e1..afc7ce713657 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -181,9 +181,8 @@ static inline void udp_tunnel_encap_enable(struct socket *sock) #if IS_ENABLED(CONFIG_IPV6) if (sock->sk->sk_family == PF_INET6) ipv6_stub->udpv6_encap_enable(); - else #endif - udp_encap_enable(); + udp_encap_enable(); } #define UDP_TUNNEL_NIC_MAX_TABLES 4 -- cgit v1.2.3 From 1faba27f11c8da244e793546a1b35a9b1da8208e Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 3 Feb 2021 15:51:09 +0200 Subject: ipv6: silence compilation warning for non-IPV6 builds The W=1 compilation of allmodconfig generates the following warning: net/ipv6/icmp.c:448:6: warning: no previous prototype for 'icmp6_send' [-Wmissing-prototypes] 448 | void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, | ^~~~~~~~~~ Fix it by providing function declaration for builds with ipv6 as a module. Signed-off-by: Leon Romanovsky Signed-off-by: Jakub Kicinski --- include/linux/icmpv6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index 1b3371ae8193..452d8978ffc7 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -16,9 +16,9 @@ static inline struct icmp6hdr *icmp6_hdr(const struct sk_buff *skb) typedef void ip6_icmp_send_t(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct in6_addr *force_saddr); -#if IS_BUILTIN(CONFIG_IPV6) void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct in6_addr *force_saddr); +#if IS_BUILTIN(CONFIG_IPV6) static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) { icmp6_send(skb, type, code, info, NULL); -- cgit v1.2.3 From f9a4719cc16fcf4f8816521e0c903a218fa072b6 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 3 Feb 2021 15:51:10 +0200 Subject: ipv6: move udp declarations to net/udp.h Fix the following compilation warning: net/ipv6/udp.c:1031:30: warning: no previous prototype for 'udp_v6_early_demux' [-Wmissing-prototypes] 1031 | INDIRECT_CALLABLE_SCOPE void udp_v6_early_demux(struct sk_buff *skb) | ^~~~~~~~~~~~~~~~~~ net/ipv6/udp.c:1072:29: warning: no previous prototype for 'udpv6_rcv' [-Wmissing-prototypes] 1072 | INDIRECT_CALLABLE_SCOPE int udpv6_rcv(struct sk_buff *skb) | ^~~~~~~~~ Signed-off-by: Leon Romanovsky Signed-off-by: Jakub Kicinski --- include/net/udp.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/udp.h b/include/net/udp.h index 5ddbb42fdb36..a132a02b2f2c 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -173,6 +173,9 @@ INDIRECT_CALLABLE_DECLARE(int udp4_gro_complete(struct sk_buff *, int)); INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp6_gro_receive(struct list_head *, struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int udp6_gro_complete(struct sk_buff *, int)); +INDIRECT_CALLABLE_DECLARE(void udp_v6_early_demux(struct sk_buff *)); +INDIRECT_CALLABLE_DECLARE(int udpv6_rcv(struct sk_buff *)); + struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, struct udphdr *uh, struct sock *sk); int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup); -- cgit v1.2.3 From 04f00ab2275f60658b5e4996e28f52ab1bc51d75 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 3 Feb 2021 15:51:11 +0200 Subject: net/core: move gro function declarations to separate header MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fir the following compilation warnings: 1031 | INDIRECT_CALLABLE_SCOPE void udp_v6_early_demux(struct sk_buff *skb) net/ipv6/ip6_offload.c:182:41: warning: no previous prototype for ‘ipv6_gro_receive’ [-Wmissing-prototypes] 182 | INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head, | ^~~~~~~~~~~~~~~~ net/ipv6/ip6_offload.c:320:29: warning: no previous prototype for ‘ipv6_gro_complete’ [-Wmissing-prototypes] 320 | INDIRECT_CALLABLE_SCOPE int ipv6_gro_complete(struct sk_buff *skb, int nhoff) | ^~~~~~~~~~~~~~~~~ net/ipv6/ip6_offload.c:182:41: warning: no previous prototype for ‘ipv6_gro_receive’ [-Wmissing-prototypes] 182 | INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head, | ^~~~~~~~~~~~~~~~ net/ipv6/ip6_offload.c:320:29: warning: no previous prototype for ‘ipv6_gro_complete’ [-Wmissing-prototypes] 320 | INDIRECT_CALLABLE_SCOPE int ipv6_gro_complete(struct sk_buff *skb, int nhoff) Signed-off-by: Leon Romanovsky Signed-off-by: Jakub Kicinski --- include/net/gro.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) create mode 100644 include/net/gro.h (limited to 'include') diff --git a/include/net/gro.h b/include/net/gro.h new file mode 100644 index 000000000000..8a6eb5303cc4 --- /dev/null +++ b/include/net/gro.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef _NET_IPV6_GRO_H +#define _NET_IPV6_GRO_H + +INDIRECT_CALLABLE_DECLARE(struct sk_buff *ipv6_gro_receive(struct list_head *, + struct sk_buff *)); +INDIRECT_CALLABLE_DECLARE(int ipv6_gro_complete(struct sk_buff *, int)); +INDIRECT_CALLABLE_DECLARE(struct sk_buff *inet_gro_receive(struct list_head *, + struct sk_buff *)); +INDIRECT_CALLABLE_DECLARE(int inet_gro_complete(struct sk_buff *, int)); +#endif /* _NET_IPV6_GRO_H */ -- cgit v1.2.3 From edf597da02a01edb26bddf06890fb81eee3d82cf Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 3 Feb 2021 15:51:12 +0200 Subject: netfilter: move handlers to net/ip_vs.h Fix the following compilation warnings: net/netfilter/ipvs/ip_vs_proto_tcp.c:147:1: warning: no previous prototype for 'tcp_snat_handler' [-Wmissing-prototypes] 147 | tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, | ^~~~~~~~~~~~~~~~ net/netfilter/ipvs/ip_vs_proto_udp.c:136:1: warning: no previous prototype for 'udp_snat_handler' [-Wmissing-prototypes] 136 | udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, | ^~~~~~~~~~~~~~~~ Signed-off-by: Leon Romanovsky Signed-off-by: Jakub Kicinski --- include/net/ip_vs.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index d609e957a3ec..7cb5a1aace40 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1712,4 +1712,15 @@ ip_vs_dest_conn_overhead(struct ip_vs_dest *dest) atomic_read(&dest->inactconns); } +#ifdef CONFIG_IP_VS_PROTO_TCP +INDIRECT_CALLABLE_DECLARE(int + tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, + struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)); +#endif + +#ifdef CONFIG_IP_VS_PROTO_UDP +INDIRECT_CALLABLE_DECLARE(int + udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, + struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)); +#endif #endif /* _NET_IP_VS_H */ -- cgit v1.2.3 From 10742efc20a429b2040658af685d6bb2aa674a73 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Thu, 21 Jan 2021 19:41:52 +0200 Subject: net/mlx5e: VF tunnel TX traffic offloading When tunnel endpoint is on VF, driver still assumes that endpoint is on uplink and incorrectly configures encap rule offload according to that assumption. As a result, traffic is sent directly to the uplink and rules installed on representor of tunnel endpoint VF are ignored. Implement following changes to allow offloading tx traffic with tunnel endpoint on VF: - For tunneling flows perform route lookup on route and out devices pair. If out device is uplink and route device is VF of same physical port, then modify packet reg_c_0 metadata register (source port) with the value of VF vport. Use eswitch vhca_id->vport mapping introduced in one of previous patches in the series to obtain vport from route netdevice. - Recirculate encapsulated packets to VF vport in order to apply any flow rules installed on VF representor that match on encapsulated traffic. Only enable support for this functionality when all following conditions are true: - Hardware advertises capability to preserve reg_c_0 value on packet recirculation. - Vport metadata matching is enabled. - Termination tables are to be used by the flow. Example TC rules for VF tunnel traffic: 1. Rule that redirects packets from UL to VF rep that has the tunnel endpoint IP address: $ tc -s filter show dev enp8s0f0 ingress filter protocol ip pref 4 flower chain 0 filter protocol ip pref 4 flower chain 0 handle 0x1 dst_mac 16:c9:a0:2d:69:2c src_mac 0c:42:a1:58:ab:e4 eth_type ipv4 ip_flags nofrag in_hw in_hw_count 1 action order 1: mirred (Egress Redirect to device enp8s0f0_0) stolen index 3 ref 1 bind 1 installed 377 sec used 0 sec Action statistics: Sent 114096 bytes 952 pkt (dropped 0, overlimits 0 requeues 0) Sent software 0 bytes 0 pkt Sent hardware 114096 bytes 952 pkt backlog 0b 0p requeues 0 cookie 878fa48d8c423fc08c3b6ca599b50a97 no_percpu used_hw_stats delayed 2. Rule that decapsulates the tunneled flow and redirects to destination VF representor: $ tc -s filter show dev vxlan_sys_4789 ingress filter protocol ip pref 4 flower chain 0 filter protocol ip pref 4 flower chain 0 handle 0x1 dst_mac ca:2e:a7:3f:f5:0f src_mac 0a:40:bd:30:89:99 eth_type ipv4 enc_dst_ip 7.7.7.5 enc_src_ip 7.7.7.1 enc_key_id 98 enc_dst_port 4789 enc_tos 0 ip_flags nofrag in_hw in_hw_count 1 action order 1: tunnel_key unset pipe index 2 ref 1 bind 1 installed 434 sec used 434 sec Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 used_hw_stats delayed action order 2: mirred (Egress Redirect to device enp8s0f0_1) stolen index 4 ref 1 bind 1 installed 434 sec used 0 sec Action statistics: Sent 129936 bytes 1082 pkt (dropped 0, overlimits 0 requeues 0) Sent software 0 bytes 0 pkt Sent hardware 129936 bytes 1082 pkt backlog 0b 0p requeues 0 cookie ac17cf398c4c69e4a5b2f7aabd1b88ff no_percpu used_hw_stats delayed Co-developed-by: Dmytro Linkin Signed-off-by: Dmytro Linkin Signed-off-by: Vlad Buslov Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/eswitch.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 29fd832950e0..67e341274a22 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -96,6 +96,8 @@ static inline u32 mlx5_eswitch_get_vport_metadata_mask(void) u32 mlx5_eswitch_get_vport_metadata_for_match(struct mlx5_eswitch *esw, u16 vport_num); +u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw, + u16 vport_num); u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev); #else /* CONFIG_MLX5_ESWITCH */ -- cgit v1.2.3 From 48d216e5596a58e3cfa6d4548343f982c5921b79 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Mon, 31 Aug 2020 16:18:19 +0300 Subject: net/mlx5e: Refactor reg_c1 usage Following patch in series uses reg_c1 in eswitch code. To use reg_c1 helpers in both TC and eswitch code, refactor existing helpers according to similar use case of reg_c0 and move the functionality into eswitch.h. Calculate reg mappings length from new defines to ensure that they are always in sync and only need to be changed in single place. Signed-off-by: Vlad Buslov Signed-off-by: Dmytro Linkin Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/eswitch.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 67e341274a22..3b20e84049c1 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -98,6 +98,25 @@ u32 mlx5_eswitch_get_vport_metadata_for_match(struct mlx5_eswitch *esw, u16 vport_num); u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw, u16 vport_num); + +/* Reg C1 usage: + * Reg C1 = < ESW_TUN_ID(12) | ESW_TUN_OPTS(12) | ESW_ZONE_ID(8) > + * + * Highest 12 bits of reg c1 is the encapsulation tunnel id, next 12 bits is + * encapsulation tunnel options, and the lowest 8 bits are used for zone id. + * + * Zone id is used to restore CT flow when packet misses on chain. + * + * Tunnel id and options are used together to restore the tunnel info metadata + * on miss and to support inner header rewrite by means of implicit chain 0 + * flows. + */ +#define ESW_ZONE_ID_BITS 8 +#define ESW_TUN_OPTS_BITS 12 +#define ESW_TUN_ID_BITS 12 +#define ESW_TUN_OFFSET ESW_ZONE_ID_BITS +#define ESW_ZONE_ID_MASK GENMASK(ESW_ZONE_ID_BITS - 1, 0) + u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev); #else /* CONFIG_MLX5_ESWITCH */ -- cgit v1.2.3 From 8e404fefa58b6138531e3d4b5647ee79f75ae9a8 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Mon, 31 Aug 2020 16:18:57 +0300 Subject: net/mlx5e: Match recirculated packet miss in slow table using reg_c1 Previous patch in series that implements stack devices RX path implements indirect table rules that match on tunnel VNI. After such rule is created all tunnel traffic is recirculated to root table. However, recirculated packet might not match on any rules installed in the table (for example, when IP traffic follows ARP traffic). In that case packets appear on representor of tunnel endpoint VF instead being redirected to the VF itself. Extend slow table with additional flow group that matches on reg_c0 (source port value set by indirect tables implemented by previous patch in series) and reg_c1 (special 0xFFF mark). When creating offloads fdb tables, install one rule per VF vport to match on recirculated miss packets and redirect them to appropriate VF vport. Modify indirect tables code to also rewrite reg_c1 with special 0xFFF mark. Implementation reuses reg_c1 tunnel id bits. This is safe to do because recirculated packets are always matched before decapsulation. Signed-off-by: Vlad Buslov Signed-off-by: Dmytro Linkin Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/eswitch.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 3b20e84049c1..994c2c8cb4fd 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -114,8 +114,16 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw, #define ESW_ZONE_ID_BITS 8 #define ESW_TUN_OPTS_BITS 12 #define ESW_TUN_ID_BITS 12 -#define ESW_TUN_OFFSET ESW_ZONE_ID_BITS +#define ESW_TUN_OPTS_OFFSET ESW_ZONE_ID_BITS +#define ESW_TUN_OFFSET ESW_TUN_OPTS_OFFSET #define ESW_ZONE_ID_MASK GENMASK(ESW_ZONE_ID_BITS - 1, 0) +#define ESW_TUN_OPTS_MASK GENMASK(32 - ESW_TUN_ID_BITS - 1, ESW_TUN_OPTS_OFFSET) +#define ESW_TUN_MASK GENMASK(31, ESW_TUN_OFFSET) +#define ESW_TUN_ID_SLOW_TABLE_GOTO_VPORT 0 /* 0 is not a valid tunnel id */ +#define ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT 0xFFF /* 0xFFF is a reserved mapping */ +#define ESW_TUN_SLOW_TABLE_GOTO_VPORT ((ESW_TUN_ID_SLOW_TABLE_GOTO_VPORT << ESW_TUN_OPTS_BITS) | \ + ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT) +#define ESW_TUN_SLOW_TABLE_GOTO_VPORT_MARK ESW_TUN_OPTS_MASK u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev); #else /* CONFIG_MLX5_ESWITCH */ -- cgit v1.2.3 From cfa55c6d47b1e75ccc4b950616e881f3fd07712e Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Fri, 1 Jan 2021 00:00:01 +0100 Subject: batman-adv: Drop publication years from copyright info The batman-adv source code was using the year of publication (to net-next) as "last" year for the copyright statement. The whole source code mentioned in the MAINTAINERS "BATMAN ADVANCED" section was handled as a single entity regarding the publishing year. This avoided having outdated (in sense of year information - not copyright holder) publishing information inside several files. But since the simple "update copyright year" commit (without other changes) in the file was not well received in the upstream kernel, the option to not have a copyright year (for initial and last publication) in the files are chosen instead. More detailed information about the years can still be retrieved from the SCM system. Signed-off-by: Sven Eckelmann Acked-by: Marek Lindner Signed-off-by: Simon Wunderlich --- include/uapi/linux/batadv_packet.h | 2 +- include/uapi/linux/batman_adv.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/batadv_packet.h b/include/uapi/linux/batadv_packet.h index 9c8604c5b5f6..ea4692c339ce 100644 --- a/include/uapi/linux/batadv_packet.h +++ b/include/uapi/linux/batadv_packet.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) */ -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h index bdb317faa1dc..35dc016c9bb4 100644 --- a/include/uapi/linux/batman_adv.h +++ b/include/uapi/linux/batman_adv.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: MIT */ -/* Copyright (C) 2016-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Matthias Schiffer */ -- cgit v1.2.3 From b358e2122b9d7aa99f681d4edfafd999845d16ff Mon Sep 17 00:00:00 2001 From: Kevin Hao Date: Thu, 4 Feb 2021 18:56:35 +0800 Subject: mm: page_frag: Introduce page_frag_alloc_align() In the current implementation of page_frag_alloc(), it doesn't have any align guarantee for the returned buffer address. But for some hardwares they do require the DMA buffer to be aligned correctly, so we would have to use some workarounds like below if the buffers allocated by the page_frag_alloc() are used by these hardwares for DMA. buf = page_frag_alloc(really_needed_size + align); buf = PTR_ALIGN(buf, align); These codes seems ugly and would waste a lot of memories if the buffers are used in a network driver for the TX/RX. So introduce page_frag_alloc_align() to make sure that an aligned buffer address is returned. Signed-off-by: Kevin Hao Acked-by: Vlastimil Babka Reviewed-by: Alexander Duyck Signed-off-by: Jakub Kicinski --- include/linux/gfp.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 6e479e9c48ce..80544d5c08e7 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -583,8 +583,16 @@ extern void free_pages(unsigned long addr, unsigned int order); struct page_frag_cache; extern void __page_frag_cache_drain(struct page *page, unsigned int count); -extern void *page_frag_alloc(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask); +extern void *page_frag_alloc_align(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask, + unsigned int align_mask); + +static inline void *page_frag_alloc(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask) +{ + return page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u); +} + extern void page_frag_free(void *addr); #define __free_page(page) __free_pages((page), 0) -- cgit v1.2.3 From 3f6e687dff395da43b056c18150a423bc7bf5d14 Mon Sep 17 00:00:00 2001 From: Kevin Hao Date: Thu, 4 Feb 2021 18:56:36 +0800 Subject: net: Introduce {netdev,napi}_alloc_frag_align() In the current implementation of {netdev,napi}_alloc_frag(), it doesn't have any align guarantee for the returned buffer address, But for some hardwares they do require the DMA buffer to be aligned correctly, so we would have to use some workarounds like below if the buffers allocated by the {netdev,napi}_alloc_frag() are used by these hardwares for DMA. buf = napi_alloc_frag(really_needed_size + align); buf = PTR_ALIGN(buf, align); These codes seems ugly and would waste a lot of memories if the buffers are used in a network driver for the TX/RX. We have added the align support for the page_frag functions, so add the corresponding {netdev,napi}_frag functions. Signed-off-by: Kevin Hao Reviewed-by: Alexander Duyck Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 36 ++++++++++++++++++++++++++++++++++-- 1 file changed, 34 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0e42c53b8ca9..0a4e91a2f873 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2818,7 +2818,26 @@ void skb_queue_purge(struct sk_buff_head *list); unsigned int skb_rbtree_purge(struct rb_root *root); -void *netdev_alloc_frag(unsigned int fragsz); +void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask); + +/** + * netdev_alloc_frag - allocate a page fragment + * @fragsz: fragment size + * + * Allocates a frag from a page for receive buffer. + * Uses GFP_ATOMIC allocations. + */ +static inline void *netdev_alloc_frag(unsigned int fragsz) +{ + return __netdev_alloc_frag_align(fragsz, ~0u); +} + +static inline void *netdev_alloc_frag_align(unsigned int fragsz, + unsigned int align) +{ + WARN_ON_ONCE(!is_power_of_2(align)); + return __netdev_alloc_frag_align(fragsz, -align); +} struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int length, gfp_t gfp_mask); @@ -2877,7 +2896,20 @@ static inline void skb_free_frag(void *addr) page_frag_free(addr); } -void *napi_alloc_frag(unsigned int fragsz); +void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask); + +static inline void *napi_alloc_frag(unsigned int fragsz) +{ + return __napi_alloc_frag_align(fragsz, ~0u); +} + +static inline void *napi_alloc_frag_align(unsigned int fragsz, + unsigned int align) +{ + WARN_ON_ONCE(!is_power_of_2(align)); + return __napi_alloc_frag_align(fragsz, -align); +} + struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int length, gfp_t gfp_mask); static inline struct sk_buff *napi_alloc_skb(struct napi_struct *napi, -- cgit v1.2.3 From b80af659699d212cf8cec6593f6551905c4ae86f Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 6 Feb 2021 00:02:14 +0200 Subject: net: mscc: ocelot: set up the bonding mask in a way that avoids a net_device Since this code should be called from pure switchdev as well as from DSA, we must find a way to determine the bonding mask not by looking directly at the net_device lowers of the bonding interface, since those could have different private structures. We keep a pointer to the bonding upper interface, if present, in struct ocelot_port. Then the bonding mask becomes the bitwise OR of all ports that have the same bonding upper interface. This adds a duplication of functionality with the current "lags" array, but the duplication will be short-lived, since further patches will remove the latter completely. Signed-off-by: Vladimir Oltean Reviewed-by: Alexandre Belloni Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 6a61c499a30d..e36a1ed29c01 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -611,6 +611,8 @@ struct ocelot_port { u8 *xmit_template; bool is_dsa_8021q_cpu; + + struct net_device *bond; }; struct ocelot { -- cgit v1.2.3 From 528d3f190c98c8f7d9581f68db4af021696727b2 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 6 Feb 2021 00:02:17 +0200 Subject: net: mscc: ocelot: drop the use of the "lags" array We can now simplify the implementation by always using ocelot_get_bond_mask to look up the other ports that are offloading the same bonding interface as us. In ocelot_set_aggr_pgids, the code had a way to uniquely iterate through LAGs. We need to achieve the same behavior by marking each LAG as visited, which we do now by using a temporary 32-bit "visited" bitmask. This is ok and we do not need dynamic memory allocation, because we know that this switch architecture will not have more than 32 ports (the PGID port masks are 32-bit anyway). Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index e36a1ed29c01..089e552719e0 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -657,8 +657,6 @@ struct ocelot { enum ocelot_tag_prefix npi_inj_prefix; enum ocelot_tag_prefix npi_xtr_prefix; - u32 *lags; - struct list_head multicast; struct list_head pgids; -- cgit v1.2.3 From 23ca3b727ee6b432166391607b614d3a6beb6784 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 6 Feb 2021 00:02:19 +0200 Subject: net: mscc: ocelot: rebalance LAGs on link up/down events At present there is an issue when ocelot is offloading a bonding interface, but one of the links of the physical ports goes down. Traffic keeps being hashed towards that destination, and of course gets dropped on egress. Monitor the netdev notifier events emitted by the bonding driver for changes in the physical state of lower interfaces, to determine which ports are active and which ones are no longer. Then extend ocelot_get_bond_mask to return either the configured bonding interfaces, or the active ones, depending on a boolean argument. The code that does rebalancing only needs to do so among the active ports, whereas the bridge forwarding mask and the logical port IDs still need to look at the permanently bonded ports. Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 089e552719e0..6e806872cd24 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -613,6 +613,7 @@ struct ocelot_port { bool is_dsa_8021q_cpu; struct net_device *bond; + bool lag_tx_active; }; struct ocelot { -- cgit v1.2.3 From 8fe6832e96acbf9d5777fc0b13e3e680ff46ba11 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 6 Feb 2021 00:02:21 +0200 Subject: net: dsa: felix: propagate the LAG offload ops towards the ocelot lib The ocelot switch has been supporting LAG offload since its initial commit, however felix could not make use of that, due to lack of a LAG abstraction in DSA. Now that we have that, let's forward DSA's calls towards the ocelot library, who will deal with setting up the bonding. Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 6e806872cd24..d0d48e9620fb 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -798,6 +798,12 @@ int ocelot_port_mdb_add(struct ocelot *ocelot, int port, const struct switchdev_obj_port_mdb *mdb); int ocelot_port_mdb_del(struct ocelot *ocelot, int port, const struct switchdev_obj_port_mdb *mdb); +int ocelot_port_lag_join(struct ocelot *ocelot, int port, + struct net_device *bond, + struct netdev_lag_upper_info *info); +void ocelot_port_lag_leave(struct ocelot *ocelot, int port, + struct net_device *bond); +void ocelot_port_lag_change(struct ocelot *ocelot, int port, bool lag_tx_active); int ocelot_devlink_sb_register(struct ocelot *ocelot); void ocelot_devlink_sb_unregister(struct ocelot *ocelot); -- cgit v1.2.3 From 4331667fa14e6643859d0498b34281185eb8018b Mon Sep 17 00:00:00 2001 From: Jiapeng Chong Date: Fri, 5 Feb 2021 14:56:39 +0800 Subject: ssb: Use true and false for bool variable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix the following coccicheck warnings: ./include/linux/ssb/ssb_driver_gige.h:89:8-9: WARNING: return of 0/1 in function 'ssb_gige_one_dma_at_once' with return type bool. ./include/linux/ssb/ssb_driver_gige.h:79:8-9: WARNING: return of 0/1 in function 'ssb_gige_have_roboswitch' with return type bool. ./include/linux/ssb/ssb_driver_gige.h:182:8-9: WARNING: return of 0/1 in function 'ssb_gige_must_flush_posted_writes' with return type bool. ./include/linux/ssb/ssb_driver_gige.h:178:8-9: WARNING: return of 0/1 in function 'ssb_gige_one_dma_at_once' with return type bool. ./include/linux/ssb/ssb_driver_gige.h:174:8-9: WARNING: return of 0/1 in function 'ssb_gige_have_roboswitch' with return type bool. ./include/linux/ssb/ssb_driver_gige.h:170:8-9: WARNING: return of 0/1 in function 'ssb_gige_is_rgmii' with return type bool. ./include/linux/ssb/ssb_driver_gige.h:162:8-9: WARNING: return of 0/1 in function 'pdev_is_ssb_gige_core' with return type bool. Reported-by: Abaci Robot Signed-off-by: Jiapeng Chong Acked-by: Michael Büsch Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/1612508199-92282-1-git-send-email-jiapeng.chong@linux.alibaba.com --- include/linux/ssb/ssb_driver_gige.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/ssb/ssb_driver_gige.h b/include/linux/ssb/ssb_driver_gige.h index 31593b34608e..15ba0df1ee0d 100644 --- a/include/linux/ssb/ssb_driver_gige.h +++ b/include/linux/ssb/ssb_driver_gige.h @@ -76,7 +76,7 @@ static inline bool ssb_gige_have_roboswitch(struct pci_dev *pdev) if (dev) return !!(dev->dev->bus->sprom.boardflags_lo & SSB_GIGE_BFL_ROBOSWITCH); - return 0; + return false; } /* Returns whether we can only do one DMA at once. */ @@ -86,7 +86,7 @@ static inline bool ssb_gige_one_dma_at_once(struct pci_dev *pdev) if (dev) return ((dev->dev->bus->chip_id == 0x4785) && (dev->dev->bus->chip_rev < 2)); - return 0; + return false; } /* Returns whether we must flush posted writes. */ @@ -159,7 +159,7 @@ static inline void ssb_gige_exit(void) static inline bool pdev_is_ssb_gige_core(struct pci_dev *pdev) { - return 0; + return false; } static inline struct ssb_gige * pdev_to_ssb_gige(struct pci_dev *pdev) { @@ -167,19 +167,19 @@ static inline struct ssb_gige * pdev_to_ssb_gige(struct pci_dev *pdev) } static inline bool ssb_gige_is_rgmii(struct pci_dev *pdev) { - return 0; + return false; } static inline bool ssb_gige_have_roboswitch(struct pci_dev *pdev) { - return 0; + return false; } static inline bool ssb_gige_one_dma_at_once(struct pci_dev *pdev) { - return 0; + return false; } static inline bool ssb_gige_must_flush_posted_writes(struct pci_dev *pdev) { - return 0; + return false; } static inline int ssb_gige_get_macaddr(struct pci_dev *pdev, u8 *macaddr) { -- cgit v1.2.3 From 49fc251360a10e6bff0d886c9e3c62008a1c4caf Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Sun, 7 Feb 2021 10:22:49 +0200 Subject: rtnetlink: Add RTM_F_OFFLOAD_FAILED flag The flag indicates to user space that route offload failed. Previous patch set added the ability to emit RTM_NEWROUTE notifications whenever RTM_F_OFFLOAD/RTM_F_TRAP flags are changed, but if the offload fails there is no indication to user-space. The flag will be used in subsequent patches by netdevsim and mlxsw to indicate to user space that route offload failed, so that users will have better visibility into the offload process. Signed-off-by: Amit Cohen Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/uapi/linux/rtnetlink.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index b841caa4657e..91e4ca064d61 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -319,6 +319,11 @@ enum rt_scope_t { #define RTM_F_FIB_MATCH 0x2000 /* return full fib lookup match */ #define RTM_F_OFFLOAD 0x4000 /* route is offloaded */ #define RTM_F_TRAP 0x8000 /* route is trapping packets */ +#define RTM_F_OFFLOAD_FAILED 0x20000000 /* route offload failed, this value + * is chosen to avoid conflicts with + * other flags defined in + * include/uapi/linux/ipv6_route.h + */ /* Reserved table identifiers */ -- cgit v1.2.3 From 36c5100e859d93b3436ae24810612b05addb1e89 Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Sun, 7 Feb 2021 10:22:50 +0200 Subject: IPv4: Add "offload failed" indication to routes After installing a route to the kernel, user space receives an acknowledgment, which means the route was installed in the kernel, but not necessarily in hardware. The asynchronous nature of route installation in hardware can lead to a routing daemon advertising a route before it was actually installed in hardware. This can result in packet loss or mis-routed packets until the route is installed in hardware. To avoid such cases, previous patch set added the ability to emit RTM_NEWROUTE notifications whenever RTM_F_OFFLOAD/RTM_F_TRAP flags are changed, this behavior is controlled by sysctl. With the above mentioned behavior, it is possible to know from user-space if the route was offloaded, but if the offload fails there is no indication to user-space. Following a failure, a routing daemon will wait indefinitely for a notification that will never come. This patch adds an "offload_failed" indication to IPv4 routes, so that users will have better visibility into the offload process. 'struct fib_alias', and 'struct fib_rt_info' are extended with new field that indicates if route offload failed. Note that the new field is added using unused bit and therefore there is no need to increase structs size. Signed-off-by: Amit Cohen Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/net/ip_fib.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 2ec062aaa978..a914f33f3ed5 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -213,7 +213,8 @@ struct fib_rt_info { u8 type; u8 offload:1, trap:1, - unused:6; + offload_failed:1, + unused:5; }; struct fib_entry_notifier_info { -- cgit v1.2.3 From 0c5fcf9e249ee1d94cf872c99baf9cba7ff9ce27 Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Sun, 7 Feb 2021 10:22:52 +0200 Subject: IPv6: Add "offload failed" indication to routes After installing a route to the kernel, user space receives an acknowledgment, which means the route was installed in the kernel, but not necessarily in hardware. The asynchronous nature of route installation in hardware can lead to a routing daemon advertising a route before it was actually installed in hardware. This can result in packet loss or mis-routed packets until the route is installed in hardware. To avoid such cases, previous patch set added the ability to emit RTM_NEWROUTE notifications whenever RTM_F_OFFLOAD/RTM_F_TRAP flags are changed, this behavior is controlled by sysctl. With the above mentioned behavior, it is possible to know from user-space if the route was offloaded, but if the offload fails there is no indication to user-space. Following a failure, a routing daemon will wait indefinitely for a notification that will never come. This patch adds an "offload_failed" indication to IPv6 routes, so that users will have better visibility into the offload process. 'struct fib6_info' is extended with new field that indicates if route offload failed. Note that the new field is added using unused bit and therefore there is no need to increase struct size. Signed-off-by: Amit Cohen Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 1e262b23c68b..15b7fbe6b15c 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -195,7 +195,8 @@ struct fib6_info { fib6_destroying:1, offload:1, trap:1, - unused:2; + offload_failed:1, + unused:1; struct rcu_head rcu; struct nexthop *nh; @@ -539,7 +540,7 @@ static inline bool fib6_metric_locked(struct fib6_info *f6i, int metric) return !!(f6i->fib6_metrics->metrics[RTAX_LOCK - 1] & (1 << metric)); } void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i, - bool offload, bool trap); + bool offload, bool trap, bool offload_failed); #if IS_BUILTIN(CONFIG_IPV6) && defined(CONFIG_BPF_SYSCALL) struct bpf_iter__ipv6_route { -- cgit v1.2.3 From 29863d41bb6e1d969c62fdb15b0961806942960e Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Mon, 8 Feb 2021 11:34:09 -0800 Subject: net: implement threaded-able napi poll loop support This patch allows running each napi poll loop inside its own kernel thread. The kthread is created during netif_napi_add() if dev->threaded is set. And threaded mode is enabled in napi_enable(). We will provide a way to set dev->threaded and enable threaded mode without a device up/down in the following patch. Once that threaded mode is enabled and the kthread is started, napi_schedule() will wake-up such thread instead of scheduling the softirq. The threaded poll loop behaves quite likely the net_rx_action, but it does not have to manipulate local irqs and uses an explicit scheduling point based on netdev_budget. Co-developed-by: Paolo Abeni Signed-off-by: Paolo Abeni Co-developed-by: Hannes Frederic Sowa Signed-off-by: Hannes Frederic Sowa Co-developed-by: Jakub Kicinski Signed-off-by: Jakub Kicinski Signed-off-by: Wei Wang Reviewed-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/netdevice.h | 21 +++++++-------------- 1 file changed, 7 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e9e7ada07ea1..99fb4ec9573e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -347,6 +347,7 @@ struct napi_struct { struct list_head dev_list; struct hlist_node napi_hash_node; unsigned int napi_id; + struct task_struct *thread; }; enum { @@ -358,6 +359,7 @@ enum { NAPI_STATE_NO_BUSY_POLL, /* Do not add in napi_hash, no busy polling */ NAPI_STATE_IN_BUSY_POLL, /* sk_busy_loop() owns this NAPI */ NAPI_STATE_PREFER_BUSY_POLL, /* prefer busy-polling over softirq processing*/ + NAPI_STATE_THREADED, /* The poll is performed inside its own thread*/ }; enum { @@ -369,6 +371,7 @@ enum { NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL), NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL), NAPIF_STATE_PREFER_BUSY_POLL = BIT(NAPI_STATE_PREFER_BUSY_POLL), + NAPIF_STATE_THREADED = BIT(NAPI_STATE_THREADED), }; enum gro_result { @@ -503,20 +506,7 @@ static inline bool napi_complete(struct napi_struct *n) */ void napi_disable(struct napi_struct *n); -/** - * napi_enable - enable NAPI scheduling - * @n: NAPI context - * - * Resume NAPI from being scheduled on this context. - * Must be paired with napi_disable. - */ -static inline void napi_enable(struct napi_struct *n) -{ - BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state)); - smp_mb__before_atomic(); - clear_bit(NAPI_STATE_SCHED, &n->state); - clear_bit(NAPI_STATE_NPSVC, &n->state); -} +void napi_enable(struct napi_struct *n); /** * napi_synchronize - wait until NAPI is not running @@ -1827,6 +1817,8 @@ enum netdev_priv_flags { * * @wol_enabled: Wake-on-LAN is enabled * + * @threaded: napi threaded mode is enabled + * * @net_notifier_list: List of per-net netdev notifier block * that follow this device when it is moved * to another network namespace. @@ -2145,6 +2137,7 @@ struct net_device { struct lock_class_key *qdisc_running_key; bool proto_down; unsigned wol_enabled:1; + unsigned threaded:1; struct list_head net_notifier_list; -- cgit v1.2.3 From 5fdd2f0e5c64846bf3066689b73fc3b8dddd1c74 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Mon, 8 Feb 2021 11:34:10 -0800 Subject: net: add sysfs attribute to control napi threaded mode This patch adds a new sysfs attribute to the network device class. Said attribute provides a per-device control to enable/disable the threaded mode for all the napi instances of the given network device, without the need for a device up/down. User sets it to 1 or 0 to enable or disable threaded mode. Note: when switching between threaded and the current softirq based mode for a napi instance, it will not immediately take effect if the napi is currently being polled. The mode switch will happen for the next time napi_schedule() is called. Co-developed-by: Paolo Abeni Signed-off-by: Paolo Abeni Co-developed-by: Hannes Frederic Sowa Signed-off-by: Hannes Frederic Sowa Co-developed-by: Felix Fietkau Signed-off-by: Felix Fietkau Signed-off-by: Wei Wang Reviewed-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 99fb4ec9573e..1340327f7abf 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -497,6 +497,8 @@ static inline bool napi_complete(struct napi_struct *n) return napi_complete_done(n, 0); } +int dev_set_threaded(struct net_device *dev, bool threaded); + /** * napi_disable - prevent NAPI from scheduling * @n: NAPI context -- cgit v1.2.3 From 01f810ace9ed37255f27608a0864abebccf0aab3 Mon Sep 17 00:00:00 2001 From: Andrei Matei Date: Sat, 6 Feb 2021 20:10:24 -0500 Subject: bpf: Allow variable-offset stack access Before this patch, variable offset access to the stack was dissalowed for regular instructions, but was allowed for "indirect" accesses (i.e. helpers). This patch removes the restriction, allowing reading and writing to the stack through stack pointers with variable offsets. This makes stack-allocated buffers more usable in programs, and brings stack pointers closer to other types of pointers. The motivation is being able to use stack-allocated buffers for data manipulation. When the stack size limit is sufficient, allocating buffers on the stack is simpler than per-cpu arrays, or other alternatives. In unpriviledged programs, variable-offset reads and writes are disallowed (they were already disallowed for the indirect access case) because the speculative execution checking code doesn't support them. Additionally, when writing through a variable-offset stack pointer, if any pointers are in the accessible range, there's possilibities of later leaking pointers because the write cannot be tracked precisely. Writes with variable offset mark the whole range as initialized, even though we don't know which stack slots are actually written. This is in order to not reject future reads to these slots. Note that this doesn't affect writes done through helpers; like before, helpers need the whole stack range to be initialized to begin with. All the stack slots are in range are considered scalars after the write; variable-offset register spills are not tracked. For reads, all the stack slots in the variable range needs to be initialized (but see above about what writes do), otherwise the read is rejected. All register spilled in stack slots that might be read are marked as having been read, however reads through such pointers don't do register filling; the target register will always be either a scalar or a constant zero. Signed-off-by: Andrei Matei Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210207011027.676572-2-andreimatei1@gmail.com --- include/linux/bpf.h | 5 +++++ include/linux/bpf_verifier.h | 3 ++- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 321966fc35db..079162bbd387 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1290,6 +1290,11 @@ static inline bool bpf_allow_ptr_leaks(void) return perfmon_capable(); } +static inline bool bpf_allow_uninit_stack(void) +{ + return perfmon_capable(); +} + static inline bool bpf_allow_ptr_to_map_access(void) { return perfmon_capable(); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index dfe6f85d97dd..532c97836d0d 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -195,7 +195,7 @@ struct bpf_func_state { * 0 = main function, 1 = first callee. */ u32 frameno; - /* subprog number == index within subprog_stack_depth + /* subprog number == index within subprog_info * zero == main subprog */ u32 subprogno; @@ -404,6 +404,7 @@ struct bpf_verifier_env { u32 used_btf_cnt; /* number of used BTF objects */ u32 id_gen; /* used to generate unique reg IDs */ bool allow_ptr_leaks; + bool allow_uninit_stack; bool allow_ptr_to_map_access; bool bpf_capable; bool bypass_spec_v1; -- cgit v1.2.3 From 1bcc51ac0731aab1b109b2cd5c3d495f1884e5ca Mon Sep 17 00:00:00 2001 From: wenxu Date: Tue, 9 Feb 2021 14:37:49 +0800 Subject: net/sched: cls_flower: Reject invalid ct_state flags rules Reject the unsupported and invalid ct_state flags of cls flower rules. Fixes: e0ace68af2ac ("net/sched: cls_flower: Add matching on conntrack info") Signed-off-by: wenxu Reviewed-by: Marcelo Ricardo Leitner Reviewed-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index ee95f42fb0ec..88f4bf0047e7 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -591,6 +591,8 @@ enum { TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED = 1 << 1, /* Part of an existing connection. */ TCA_FLOWER_KEY_CT_FLAGS_RELATED = 1 << 2, /* Related to an established connection. */ TCA_FLOWER_KEY_CT_FLAGS_TRACKED = 1 << 3, /* Conntrack has occurred. */ + + __TCA_FLOWER_KEY_CT_FLAGS_MAX, }; enum { -- cgit v1.2.3 From 5b74df80f301e872143fa716f3f4361b2e293e19 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 4 Jan 2021 09:38:57 +0200 Subject: net/mlx5: Delete device list leftover Device list is not stored in mlx5_priv anymore, so delete it as it's not used. Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 88197b87bd81..936302b2c141 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -588,7 +588,6 @@ struct mlx5_priv { /* end: alloc staff */ struct dentry *dbg_root; - struct list_head dev_list; struct list_head ctx_list; spinlock_t ctx_lock; struct mlx5_adev **adev; -- cgit v1.2.3 From 700d4796ef59f5faf240d307839bd419e2b6bdff Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 9 Feb 2021 19:36:26 -0800 Subject: bpf: Optimize program stats Move bpf_prog_stats from prog->aux into prog to avoid one extra load in critical path of program execution. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210210033634.62081-2-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 8 -------- include/linux/filter.h | 14 +++++++++++--- 2 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 079162bbd387..5a388955e6b6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include @@ -507,12 +506,6 @@ enum bpf_cgroup_storage_type { */ #define MAX_BPF_FUNC_ARGS 12 -struct bpf_prog_stats { - u64 cnt; - u64 nsecs; - struct u64_stats_sync syncp; -} __aligned(2 * sizeof(u64)); - struct btf_func_model { u8 ret_size; u8 nr_args; @@ -845,7 +838,6 @@ struct bpf_prog_aux { u32 linfo_idx; u32 num_exentries; struct exception_table_entry *extable; - struct bpf_prog_stats __percpu *stats; union { struct work_struct work; struct rcu_head rcu; diff --git a/include/linux/filter.h b/include/linux/filter.h index 5b3137d7b690..cecb03c9d251 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -22,6 +22,7 @@ #include #include #include +#include #include @@ -539,6 +540,12 @@ struct bpf_binary_header { u8 image[] __aligned(BPF_IMAGE_ALIGNMENT); }; +struct bpf_prog_stats { + u64 cnt; + u64 nsecs; + struct u64_stats_sync syncp; +} __aligned(2 * sizeof(u64)); + struct bpf_prog { u16 pages; /* Number of allocated pages */ u16 jited:1, /* Is our filter JIT'ed? */ @@ -557,10 +564,11 @@ struct bpf_prog { u32 len; /* Number of filter blocks */ u32 jited_len; /* Size of jited insns in bytes */ u8 tag[BPF_TAG_SIZE]; - struct bpf_prog_aux *aux; /* Auxiliary fields */ - struct sock_fprog_kern *orig_prog; /* Original BPF program */ + struct bpf_prog_stats __percpu *stats; unsigned int (*bpf_func)(const void *ctx, const struct bpf_insn *insn); + struct bpf_prog_aux *aux; /* Auxiliary fields */ + struct sock_fprog_kern *orig_prog; /* Original BPF program */ /* Instructions for interpreter */ struct sock_filter insns[0]; struct bpf_insn insnsi[]; @@ -581,7 +589,7 @@ DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key); struct bpf_prog_stats *__stats; \ u64 __start = sched_clock(); \ __ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ - __stats = this_cpu_ptr(prog->aux->stats); \ + __stats = this_cpu_ptr(prog->stats); \ u64_stats_update_begin(&__stats->syncp); \ __stats->cnt++; \ __stats->nsecs += sched_clock() - __start; \ -- cgit v1.2.3 From f2dd3b39467411c53703125a111f45b3672c1771 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 9 Feb 2021 19:36:28 -0800 Subject: bpf: Compute program stats for sleepable programs Since sleepable programs don't migrate from the cpu the excution stats can be computed for them as well. Reuse the same infrastructure for both sleepable and non-sleepable programs. run_cnt -> the number of times the program was executed. run_time_ns -> the program execution time in nanoseconds including the off-cpu time when the program was sleeping. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: KP Singh Link: https://lore.kernel.org/bpf/20210210033634.62081-4-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 5a388955e6b6..e1840ceaf55f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -563,8 +563,8 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end, /* these two functions are called from generated trampoline */ u64 notrace __bpf_prog_enter(void); void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start); -void notrace __bpf_prog_enter_sleepable(void); -void notrace __bpf_prog_exit_sleepable(void); +u64 notrace __bpf_prog_enter_sleepable(void); +void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start); struct bpf_ksym { unsigned long start; -- cgit v1.2.3 From ca06f55b90020cd97f4cc6d52db95436162e7dcf Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 9 Feb 2021 19:36:29 -0800 Subject: bpf: Add per-program recursion prevention mechanism Since both sleepable and non-sleepable programs execute under migrate_disable add recursion prevention mechanism to both types of programs when they're executed via bpf trampoline. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210210033634.62081-5-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 6 +++--- include/linux/filter.h | 1 + 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e1840ceaf55f..1c8ea682c007 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -529,7 +529,7 @@ struct btf_func_model { /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. Pick a number to fit into BPF_IMAGE_SIZE / 2 */ -#define BPF_MAX_TRAMP_PROGS 40 +#define BPF_MAX_TRAMP_PROGS 38 struct bpf_tramp_progs { struct bpf_prog *progs[BPF_MAX_TRAMP_PROGS]; @@ -561,9 +561,9 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end, struct bpf_tramp_progs *tprogs, void *orig_call); /* these two functions are called from generated trampoline */ -u64 notrace __bpf_prog_enter(void); +u64 notrace __bpf_prog_enter(struct bpf_prog *prog); void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start); -u64 notrace __bpf_prog_enter_sleepable(void); +u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog); void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start); struct bpf_ksym { diff --git a/include/linux/filter.h b/include/linux/filter.h index cecb03c9d251..6a06f3c69f4e 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -565,6 +565,7 @@ struct bpf_prog { u32 jited_len; /* Size of jited insns in bytes */ u8 tag[BPF_TAG_SIZE]; struct bpf_prog_stats __percpu *stats; + int __percpu *active; unsigned int (*bpf_func)(const void *ctx, const struct bpf_insn *insn); struct bpf_prog_aux *aux; /* Auxiliary fields */ -- cgit v1.2.3 From 9ed9e9ba2337205311398a312796c213737bac35 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 9 Feb 2021 19:36:31 -0800 Subject: bpf: Count the number of times recursion was prevented Add per-program counter for number of times recursion prevention mechanism was triggered and expose it via show_fdinfo and bpf_prog_info. Teach bpftool to print it. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210210033634.62081-7-alexei.starovoitov@gmail.com --- include/linux/filter.h | 1 + include/uapi/linux/bpf.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 6a06f3c69f4e..3b00fc906ccd 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -543,6 +543,7 @@ struct bpf_binary_header { struct bpf_prog_stats { u64 cnt; u64 nsecs; + u64 misses; struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c001766adcbc..c547ad1ffe43 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4501,6 +4501,7 @@ struct bpf_prog_info { __aligned_u64 prog_tags; __u64 run_time_ns; __u64 run_cnt; + __u64 recursion_misses; } __attribute__((aligned(8))); struct bpf_map_info { -- cgit v1.2.3 From e13e4536f0922a5bf8df92bb64964c9279fb4cdc Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Tue, 9 Feb 2021 12:59:55 +0200 Subject: devlink: Fix dmac_filter trap name, align to its documentation %s/dest_mac_filter/dmac_filter/g Fixes: e78ab164591f ("devlink: Add DMAC filter generic packet trap") Signed-off-by: Aya Levin Reported-by: Ido Schimmel Reviewed-by: Tariq Toukan Reviewed-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/devlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 47b4b063401b..853420db5d32 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1090,7 +1090,7 @@ enum devlink_trap_group_generic_id { #define DEVLINK_TRAP_GENERIC_NAME_BLACKHOLE_NEXTHOP \ "blackhole_nexthop" #define DEVLINK_TRAP_GENERIC_NAME_DMAC_FILTER \ - "dest_mac_filter" + "dmac_filter" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_L2_DROPS \ "l2_drops" -- cgit v1.2.3 From 4217a64e18a1647a0dbc68cb3169a5a06f054ec8 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Tue, 9 Feb 2021 17:38:52 +0100 Subject: net: phy: introduce phydev->port At the moment, PORT_MII is reported in the ethtool ops. This is odd because it is an interface between the MAC and the PHY and no external port. Some network card drivers will overwrite the port to twisted pair or fiber, though. Even worse, the MDI/MDIX setting is only used by ethtool if the port is twisted pair. Set the port to PORT_TP by default because most PHY drivers are copper ones. If there is fibre support and it is enabled, the PHY driver will set it to PORT_FIBRE. This will change reporting PORT_MII to either PORT_TP or PORT_FIBRE; except for the genphy fallback driver. Suggested-by: Andrew Lunn Signed-off-by: Michael Walle Reviewed-by: Florian Fainelli Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index bc323fbdd21e..c130788306c8 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -503,6 +503,7 @@ struct macsec_ops; * * @speed: Current link speed * @duplex: Current duplex + * @port: Current port * @pause: Current pause * @asym_pause: Current asymmetric pause * @supported: Combined MAC/PHY supported linkmodes @@ -581,6 +582,7 @@ struct phy_device { */ int speed; int duplex; + int port; int pause; int asym_pause; u8 master_slave_get; -- cgit v1.2.3 From dcf0cd1cc58b8e88793ad6531db9b3a47324ca09 Mon Sep 17 00:00:00 2001 From: George McCollister Date: Tue, 9 Feb 2021 19:02:11 -0600 Subject: net: hsr: add offloading support Add support for offloading of HSR/PRP (IEC 62439-3) tag insertion tag removal, duplicate generation and forwarding. For HSR, insertion involves the switch adding a 6 byte HSR header after the 14 byte Ethernet header. For PRP it adds a 6 byte trailer. Tag removal involves automatically stripping the HSR/PRP header/trailer in the switch. This is possible when the switch also performs auto deduplication using the HSR/PRP header/trailer (making it no longer required). Forwarding involves automatically forwarding between redundant ports in an HSR. This is crucial because delay is accumulated as a frame passes through each node in the ring. Duplication involves the switch automatically sending a single frame from the CPU port to both redundant ports. This is required because the inserted HSR/PRP header/trailer must contain the same sequence number on the frames sent out both redundant ports. Export is_hsr_master so DSA can tell them apart from other devices in dsa_slave_changeupper. Signed-off-by: George McCollister Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/if_hsr.h | 27 +++++++++++++++++++++++++++ include/linux/netdev_features.h | 9 +++++++++ 2 files changed, 36 insertions(+) create mode 100644 include/linux/if_hsr.h (limited to 'include') diff --git a/include/linux/if_hsr.h b/include/linux/if_hsr.h new file mode 100644 index 000000000000..38bbc537d4e4 --- /dev/null +++ b/include/linux/if_hsr.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_IF_HSR_H_ +#define _LINUX_IF_HSR_H_ + +/* used to differentiate various protocols */ +enum hsr_version { + HSR_V0 = 0, + HSR_V1, + PRP_V1, +}; + +#if IS_ENABLED(CONFIG_HSR) +extern bool is_hsr_master(struct net_device *dev); +extern int hsr_get_version(struct net_device *dev, enum hsr_version *ver); +#else +static inline bool is_hsr_master(struct net_device *dev) +{ + return false; +} +static inline int hsr_get_version(struct net_device *dev, + enum hsr_version *ver) +{ + return -EINVAL; +} +#endif /* CONFIG_HSR */ + +#endif /*_LINUX_IF_HSR_H_*/ diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index c06d6aaba9df..3de38d6a0aea 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -86,6 +86,11 @@ enum { NETIF_F_HW_MACSEC_BIT, /* Offload MACsec operations */ NETIF_F_GRO_UDP_FWD_BIT, /* Allow UDP GRO for forwarding */ + NETIF_F_HW_HSR_TAG_INS_BIT, /* Offload HSR tag insertion */ + NETIF_F_HW_HSR_TAG_RM_BIT, /* Offload HSR tag removal */ + NETIF_F_HW_HSR_FWD_BIT, /* Offload HSR forwarding */ + NETIF_F_HW_HSR_DUP_BIT, /* Offload HSR duplication */ + /* * Add your fresh new feature above and remember to update * netdev_features_strings[] in net/core/ethtool.c and maybe @@ -159,6 +164,10 @@ enum { #define NETIF_F_GSO_FRAGLIST __NETIF_F(GSO_FRAGLIST) #define NETIF_F_HW_MACSEC __NETIF_F(HW_MACSEC) #define NETIF_F_GRO_UDP_FWD __NETIF_F(GRO_UDP_FWD) +#define NETIF_F_HW_HSR_TAG_INS __NETIF_F(HW_HSR_TAG_INS) +#define NETIF_F_HW_HSR_TAG_RM __NETIF_F(HW_HSR_TAG_RM) +#define NETIF_F_HW_HSR_FWD __NETIF_F(HW_HSR_FWD) +#define NETIF_F_HW_HSR_DUP __NETIF_F(HW_HSR_DUP) /* Finds the next feature with the highest number of the range of start till 0. */ -- cgit v1.2.3 From 18596f504a3e56c4f8e132b2a437cbe23a3f4635 Mon Sep 17 00:00:00 2001 From: George McCollister Date: Tue, 9 Feb 2021 19:02:12 -0600 Subject: net: dsa: add support for offloading HSR Add support for offloading of HSR/PRP (IEC 62439-3) tag insertion tag removal, duplicate generation and forwarding on DSA switches. Add DSA_NOTIFIER_HSR_JOIN and DSA_NOTIFIER_HSR_LEAVE which trigger calls to .port_hsr_join and .port_hsr_leave in the DSA driver for the switch. The DSA switch driver should then set netdev feature flags for the HSR/PRP operation that it offloads. NETIF_F_HW_HSR_TAG_INS NETIF_F_HW_HSR_TAG_RM NETIF_F_HW_HSR_FWD NETIF_F_HW_HSR_DUP Signed-off-by: George McCollister Reviewed-by: Florian Fainelli Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/net/dsa.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 60acb9fca124..d8de23ce7221 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -172,6 +172,10 @@ struct dsa_switch_tree { list_for_each_entry((_dp), &(_dst)->ports, list) \ if ((_dp)->lag_dev == (_lag)) +#define dsa_hsr_foreach_port(_dp, _ds, _hsr) \ + list_for_each_entry((_dp), &(_ds)->dst->ports, list) \ + if ((_dp)->ds == (_ds) && (_dp)->hsr_dev == (_hsr)) + static inline struct net_device *dsa_lag_dev(struct dsa_switch_tree *dst, unsigned int id) { @@ -264,6 +268,7 @@ struct dsa_port { struct phylink_config pl_config; struct net_device *lag_dev; bool lag_tx_enabled; + struct net_device *hsr_dev; struct list_head list; @@ -769,6 +774,14 @@ struct dsa_switch_ops { struct netdev_lag_upper_info *info); int (*port_lag_leave)(struct dsa_switch *ds, int port, struct net_device *lag); + + /* + * HSR integration + */ + int (*port_hsr_join)(struct dsa_switch *ds, int port, + struct net_device *hsr); + int (*port_hsr_leave)(struct dsa_switch *ds, int port, + struct net_device *hsr); }; #define DSA_DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes) \ -- cgit v1.2.3 From 3d368ab87cf6681f928de1ddf804d69600671bb2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 10 Feb 2021 06:41:44 -0800 Subject: net: initialize net->net_cookie at netns setup It is simpler to make net->net_cookie a plain u64 written once in setup_net() instead of looping and using atomic64 helpers. Lorenz Bauer wants to add SO_NETNS_COOKIE socket option and this patch would makes his patch series simpler. Signed-off-by: Eric Dumazet Cc: Daniel Borkmann Cc: Lorenz Bauer Acked-by: Daniel Borkmann Tested-by: Lorenz Bauer Signed-off-by: David S. Miller --- include/net/net_namespace.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 29567875f428..dcaee24a4d87 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -165,7 +165,7 @@ struct net { struct netns_xfrm xfrm; #endif - atomic64_t net_cookie; /* written once */ + u64 net_cookie; /* written once */ #if IS_ENABLED(CONFIG_IP_VS) struct netns_ipvs *ipvs; @@ -224,8 +224,6 @@ extern struct list_head net_namespace_list; struct net *get_net_ns_by_pid(pid_t pid); struct net *get_net_ns_by_fd(int fd); -u64 __net_gen_cookie(struct net *net); - #ifdef CONFIG_SYSCTL void ipx_register_sysctl(void); void ipx_unregister_sysctl(void); -- cgit v1.2.3 From f2fa0e5e9f31dd90741f1151043ca1eaa4086690 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 11 Feb 2021 11:16:13 +0100 Subject: xen/events: link interdomain events to associated xenbus device In order to support the possibility of per-device event channel settings (e.g. lateeoi spurious event thresholds) add a xenbus device pointer to struct irq_info() and modify the related event channel binding interfaces to take the pointer to the xenbus device as a parameter instead of the domain id of the other side. While at it remove the stale prototype of bind_evtchn_to_irq_lateeoi(). Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Reviewed-by: Wei Liu Reviewed-by: Paul Durrant Signed-off-by: David S. Miller --- include/xen/events.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/xen/events.h b/include/xen/events.h index 8ec418e30c7f..c204262d9fc2 100644 --- a/include/xen/events.h +++ b/include/xen/events.h @@ -12,10 +12,11 @@ #include #include +struct xenbus_device; + unsigned xen_evtchn_nr_channels(void); int bind_evtchn_to_irq(evtchn_port_t evtchn); -int bind_evtchn_to_irq_lateeoi(evtchn_port_t evtchn); int bind_evtchn_to_irqhandler(evtchn_port_t evtchn, irq_handler_t handler, unsigned long irqflags, const char *devname, @@ -35,9 +36,9 @@ int bind_ipi_to_irqhandler(enum ipi_vector ipi, unsigned long irqflags, const char *devname, void *dev_id); -int bind_interdomain_evtchn_to_irq_lateeoi(unsigned int remote_domain, +int bind_interdomain_evtchn_to_irq_lateeoi(struct xenbus_device *dev, evtchn_port_t remote_port); -int bind_interdomain_evtchn_to_irqhandler_lateeoi(unsigned int remote_domain, +int bind_interdomain_evtchn_to_irqhandler_lateeoi(struct xenbus_device *dev, evtchn_port_t remote_port, irq_handler_t handler, unsigned long irqflags, -- cgit v1.2.3 From 4c236d5dc8b86222dc155cd68e7934624264150f Mon Sep 17 00:00:00 2001 From: Geetha sowjanya Date: Thu, 11 Feb 2021 21:28:27 +0530 Subject: octeontx2-pf: cn10k: Use LMTST lines for NPA/NIX operations This patch adds support to use new LMTST lines for NPA batch free and burst SQE flush. Adds new dev_hw_ops structure to hold platform specific functions and create new files cn10k.c and cn10k.h. Signed-off-by: Geetha sowjanya Signed-off-by: Sunil Goutham Signed-off-by: David S. Miller --- include/linux/soc/marvell/octeontx2/asm.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/soc/marvell/octeontx2/asm.h b/include/linux/soc/marvell/octeontx2/asm.h index ae2279fe830a..28c04d918f0f 100644 --- a/include/linux/soc/marvell/octeontx2/asm.h +++ b/include/linux/soc/marvell/octeontx2/asm.h @@ -22,8 +22,16 @@ : [rs]"r" (ioaddr)); \ (result); \ }) +#define cn10k_lmt_flush(val, addr) \ +({ \ + __asm__ volatile(".cpu generic+lse\n" \ + "steor %x[rf],[%[rs]]" \ + : [rf]"+r"(val) \ + : [rs]"r"(addr)); \ +}) #else #define otx2_lmt_flush(ioaddr) ({ 0; }) +#define cn10k_lmt_flush(val, addr) ({ addr = val; }) #endif #endif /* __SOC_OTX2_ASM_H */ -- cgit v1.2.3 From 07881ccbf40cc7893869f3f170301889ddca54ac Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Wed, 10 Feb 2021 12:14:02 +0100 Subject: bpf: Be less specific about socket cookies guarantees Since "92acdc58ab11 bpf, net: Rework cookie generator as per-cpu one" socket cookies are not guaranteed to be non-decreasing. The bpf_get_socket_cookie helper descriptions are currently specifying that cookies are non-decreasing but we don't want users to rely on that. Reported-by: Daniel Borkmann Signed-off-by: Florent Revest Signed-off-by: Alexei Starovoitov Acked-by: KP Singh Link: https://lore.kernel.org/bpf/20210210111406.785541-1-revest@chromium.org --- include/uapi/linux/bpf.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c547ad1ffe43..dbf10bf08582 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1656,22 +1656,22 @@ union bpf_attr { * networking traffic statistics as it provides a global socket * identifier that can be assumed unique. * Return - * A 8-byte long non-decreasing number on success, or 0 if the - * socket field is missing inside *skb*. + * A 8-byte long unique number on success, or 0 if the socket + * field is missing inside *skb*. * * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx) * Description * Equivalent to bpf_get_socket_cookie() helper that accepts * *skb*, but gets socket from **struct bpf_sock_addr** context. * Return - * A 8-byte long non-decreasing number. + * A 8-byte long unique number. * * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx) * Description * Equivalent to **bpf_get_socket_cookie**\ () helper that accepts * *skb*, but gets socket from **struct bpf_sock_ops** context. * Return - * A 8-byte long non-decreasing number. + * A 8-byte long unique number. * * u32 bpf_get_socket_uid(struct sk_buff *skb) * Return -- cgit v1.2.3 From c5dbb89fc2ac013afe67b9e4fcb3743c02b567cd Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Wed, 10 Feb 2021 12:14:03 +0100 Subject: bpf: Expose bpf_get_socket_cookie to tracing programs This needs a new helper that: - can work in a sleepable context (using sock_gen_cookie) - takes a struct sock pointer and checks that it's not NULL Signed-off-by: Florent Revest Signed-off-by: Alexei Starovoitov Acked-by: KP Singh Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210210111406.785541-2-revest@chromium.org --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 8 ++++++++ 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1c8ea682c007..cccaef1088ea 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1885,6 +1885,7 @@ extern const struct bpf_func_proto bpf_per_cpu_ptr_proto; extern const struct bpf_func_proto bpf_this_cpu_ptr_proto; extern const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto; extern const struct bpf_func_proto bpf_sock_from_file_proto; +extern const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index dbf10bf08582..07cc2e404291 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1673,6 +1673,14 @@ union bpf_attr { * Return * A 8-byte long unique number. * + * u64 bpf_get_socket_cookie(struct sock *sk) + * Description + * Equivalent to **bpf_get_socket_cookie**\ () helper that accepts + * *sk*, but gets socket from a BTF **struct sock**. This helper + * also works for sleepable programs. + * Return + * A 8-byte long unique number or 0 if *sk* is NULL. + * * u32 bpf_get_socket_uid(struct sk_buff *skb) * Return * The owner UID of the socket associated to *skb*. If the socket -- cgit v1.2.3 From 3b23a32a63219f51a5298bc55a65ecee866e79d0 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 11 Feb 2021 11:34:10 -0800 Subject: net: fix dev_ifsioc_locked() race condition dev_ifsioc_locked() is called with only RCU read lock, so when there is a parallel writer changing the mac address, it could get a partially updated mac address, as shown below: Thread 1 Thread 2 // eth_commit_mac_addr_change() memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); // dev_ifsioc_locked() memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr,...); Close this race condition by guarding them with a RW semaphore, like netdev_get_name(). We can not use seqlock here as it does not allow blocking. The writers already take RTNL anyway, so this does not affect the slow path. To avoid bothering existing dev_set_mac_address() callers in drivers, introduce a new wrapper just for user-facing callers on ioctl and rtnetlink paths. Note, bonding also changes slave mac addresses but that requires a separate patch due to the complexity of bonding code. Fixes: 3710becf8a58 ("net: RCU locking for simple ioctl()") Reported-by: "Gong, Sishuai" Cc: Eric Dumazet Cc: Jakub Kicinski Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a20310ff5083..bfadf3b82f9c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3902,6 +3902,9 @@ int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr, struct netlink_ext_ack *extack); int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa, struct netlink_ext_ack *extack); +int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa, + struct netlink_ext_ack *extack); +int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name); int dev_change_carrier(struct net_device *, bool new_carrier); int dev_get_phys_port_id(struct net_device *dev, struct netdev_phys_item_id *ppid); -- cgit v1.2.3 From 3c5a2fd042d0bfac71a2dfb99515723d318df47b Mon Sep 17 00:00:00 2001 From: Arjun Roy Date: Thu, 11 Feb 2021 13:21:07 -0800 Subject: tcp: Sanitize CMSG flags and reserved args in tcp_zerocopy_receive. Explicitly define reserved field and require it and any subsequent fields to be zero-valued for now. Additionally, limit the valid CMSG flags that tcp_zerocopy_receive accepts. Fixes: 7eeba1706eba ("tcp: Add receive timestamp support for receive zerocopy.") Signed-off-by: Arjun Roy Signed-off-by: Eric Dumazet Signed-off-by: Soheil Hassas Yeganeh Suggested-by: David Ahern Suggested-by: Leon Romanovsky Suggested-by: Jakub Kicinski Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/uapi/linux/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 42fc5a640df4..8fc09e8638b3 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -357,6 +357,6 @@ struct tcp_zerocopy_receive { __u64 msg_control; /* ancillary data */ __u64 msg_controllen; __u32 msg_flags; - /* __u32 hole; Next we must add >1 u32 otherwise length checks fail. */ + __u32 reserved; /* set to 0 for now */ }; #endif /* _UAPI_LINUX_TCP_H */ -- cgit v1.2.3 From 4e1beecc3b586e5d05401c0a9e456f96aab0e5a4 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Thu, 11 Feb 2021 13:35:51 +0200 Subject: net/sock: Add kernel config SOCK_RX_QUEUE_MAPPING Use a new config SOCK_RX_QUEUE_MAPPING to compile-in the socket RX queue field and logic, instead of the XPS config. This breaks dependency in XPS, and allows selecting it from non-XPS use cases, as we do in the next patch. In addition, use the new flag to wrap the logic in sk_rx_queue_get() and protect access to the sk_rx_queue_mapping field, while keeping the function exposed unconditionally, just like sk_rx_queue_set() and sk_rx_queue_clear(). Signed-off-by: Tariq Toukan Reviewed-by: Maxim Mikityanskiy Signed-off-by: David S. Miller --- include/net/sock.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 690e496a0e79..855c068c6c86 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -226,7 +226,7 @@ struct sock_common { struct hlist_nulls_node skc_nulls_node; }; unsigned short skc_tx_queue_mapping; -#ifdef CONFIG_XPS +#ifdef CONFIG_SOCK_RX_QUEUE_MAPPING unsigned short skc_rx_queue_mapping; #endif union { @@ -356,7 +356,7 @@ struct sock { #define sk_nulls_node __sk_common.skc_nulls_node #define sk_refcnt __sk_common.skc_refcnt #define sk_tx_queue_mapping __sk_common.skc_tx_queue_mapping -#ifdef CONFIG_XPS +#ifdef CONFIG_SOCK_RX_QUEUE_MAPPING #define sk_rx_queue_mapping __sk_common.skc_rx_queue_mapping #endif @@ -1838,7 +1838,7 @@ static inline int sk_tx_queue_get(const struct sock *sk) static inline void sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb) { -#ifdef CONFIG_XPS +#ifdef CONFIG_SOCK_RX_QUEUE_MAPPING if (skb_rx_queue_recorded(skb)) { u16 rx_queue = skb_get_rx_queue(skb); @@ -1852,20 +1852,20 @@ static inline void sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb) static inline void sk_rx_queue_clear(struct sock *sk) { -#ifdef CONFIG_XPS +#ifdef CONFIG_SOCK_RX_QUEUE_MAPPING sk->sk_rx_queue_mapping = NO_QUEUE_MAPPING; #endif } -#ifdef CONFIG_XPS static inline int sk_rx_queue_get(const struct sock *sk) { +#ifdef CONFIG_SOCK_RX_QUEUE_MAPPING if (sk && sk->sk_rx_queue_mapping != NO_QUEUE_MAPPING) return sk->sk_rx_queue_mapping; +#endif return -1; } -#endif static inline void sk_set_socket(struct sock *sk, struct socket *sock) { -- cgit v1.2.3 From b6db0f899a16a23f5a9ea6c8b0fafc7bbd38e03d Mon Sep 17 00:00:00 2001 From: Ben Greear Date: Thu, 4 Feb 2021 06:46:10 -0800 Subject: cfg80211/mac80211: Support disabling HE mode Allow user to disable HE mode, similar to how VHT and HT can be disabled. Useful for testing. Signed-off-by: Ben Greear Link: https://lore.kernel.org/r/20210204144610.25971-1-greearb@candelatech.com Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 ++ include/uapi/linux/nl80211.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 4cdd75449d73..911fae42b0c0 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2583,12 +2583,14 @@ struct cfg80211_auth_request { * authentication capability. Drivers can offload authentication to * userspace if this flag is set. Only applicable for cfg80211_connect() * request (connect callback). + * @ASSOC_REQ_DISABLE_HE: Disable HE */ enum cfg80211_assoc_req_flags { ASSOC_REQ_DISABLE_HT = BIT(0), ASSOC_REQ_DISABLE_VHT = BIT(1), ASSOC_REQ_USE_RRM = BIT(2), CONNECT_REQ_EXTERNAL_AUTH_SUPPORT = BIT(3), + ASSOC_REQ_DISABLE_HE = BIT(4), }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 40832d13c2f1..5188fe581efc 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3045,6 +3045,8 @@ enum nl80211_attrs { NL80211_ATTR_SAR_SPEC, + NL80211_ATTR_DISABLE_HE, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, -- cgit v1.2.3 From 735a48481cca453525d9199772f9c3733a47cff4 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 12 Feb 2021 10:50:23 +0100 Subject: nl80211: add documentation for HT/VHT/HE disable attributes These were missed earlier, add the necessary documentation and, while at it, clarify it. Signed-off-by: Johannes Berg Link: https://lore.kernel.org/r/20210212105023.895c3389f063.I46dea3bfc64385bc6f600c50d294007510994f8f@changeid Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 5188fe581efc..ac78da99fccd 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1963,8 +1963,15 @@ enum nl80211_commands { * @NL80211_ATTR_PROBE_RESP: Probe Response template data. Contains the entire * probe-response frame. The DA field in the 802.11 header is zero-ed out, * to be filled by the FW. - * @NL80211_ATTR_DISABLE_HT: Force HT capable interfaces to disable - * this feature. Currently, only supported in mac80211 drivers. + * @NL80211_ATTR_DISABLE_HT: Force HT capable interfaces to disable + * this feature during association. This is a flag attribute. + * Currently only supported in mac80211 drivers. + * @NL80211_ATTR_DISABLE_VHT: Force VHT capable interfaces to disable + * this feature during association. This is a flag attribute. + * Currently only supported in mac80211 drivers. + * @NL80211_ATTR_DISABLE_HE: Force HE capable interfaces to disable + * this feature during association. This is a flag attribute. + * Currently only supported in mac80211 drivers. * @NL80211_ATTR_HT_CAPABILITY_MASK: Specify which bits of the * ATTR_HT_CAPABILITY to which attention should be paid. * Currently, only mac80211 NICs support this feature. -- cgit v1.2.3 From e1850ea9bd9eca3656820b4875967d6f9c11c237 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 9 Feb 2021 14:38:19 +0100 Subject: bpf: bpf_fib_lookup return MTU value as output when looked up The BPF-helpers for FIB lookup (bpf_xdp_fib_lookup and bpf_skb_fib_lookup) can perform MTU check and return BPF_FIB_LKUP_RET_FRAG_NEEDED. The BPF-prog don't know the MTU value that caused this rejection. If the BPF-prog wants to implement PMTU (Path MTU Discovery) (rfc1191) it need to know this MTU value for the ICMP packet. Patch change lookup and result struct bpf_fib_lookup, to contain this MTU value as output via a union with 'tot_len' as this is the value used for the MTU lookup. V5: - Fixed uninit value spotted by Dan Carpenter. - Name struct output member mtu_result Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/161287789952.790810.13134700381067698781.stgit@firesoul --- include/uapi/linux/bpf.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 07cc2e404291..6b1f6058cccf 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2239,6 +2239,9 @@ union bpf_attr { * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the * packet is not forwarded or needs assist from full stack * + * If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU + * was exceeded and output params->mtu_result contains the MTU. + * * long bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) * Description * Add an entry to, or update a sockhash *map* referencing sockets. @@ -4990,9 +4993,13 @@ struct bpf_fib_lookup { __be16 sport; __be16 dport; - /* total length of packet from network header - used for MTU check */ - __u16 tot_len; + union { /* used for MTU check */ + /* input to lookup */ + __u16 tot_len; /* L3 length from network hdr (iph->tot_len) */ + /* output: MTU value */ + __u16 mtu_result; + }; /* input: L3 device index for lookup * output: device index from FIB lookup */ -- cgit v1.2.3 From 34b2021cc61642d61c3cf943d9e71925b827941b Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 9 Feb 2021 14:38:24 +0100 Subject: bpf: Add BPF-helper for MTU checking This BPF-helper bpf_check_mtu() works for both XDP and TC-BPF programs. The SKB object is complex and the skb->len value (accessible from BPF-prog) also include the length of any extra GRO/GSO segments, but without taking into account that these GRO/GSO segments get added transport (L4) and network (L3) headers before being transmitted. Thus, this BPF-helper is created such that the BPF-programmer don't need to handle these details in the BPF-prog. The API is designed to help the BPF-programmer, that want to do packet context size changes, which involves other helpers. These other helpers usually does a delta size adjustment. This helper also support a delta size (len_diff), which allow BPF-programmer to reuse arguments needed by these other helpers, and perform the MTU check prior to doing any actual size adjustment of the packet context. It is on purpose, that we allow the len adjustment to become a negative result, that will pass the MTU check. This might seem weird, but it's not this helpers responsibility to "catch" wrong len_diff adjustments. Other helpers will take care of these checks, if BPF-programmer chooses to do actual size adjustment. V14: - Improve man-page desc of len_diff. V13: - Enforce flag BPF_MTU_CHK_SEGS cannot use len_diff. V12: - Simplify segment check that calls skb_gso_validate_network_len. - Helpers should return long V9: - Use dev->hard_header_len (instead of ETH_HLEN) - Annotate with unlikely req from Daniel - Fix logic error using skb_gso_validate_network_len from Daniel V6: - Took John's advice and dropped BPF_MTU_CHK_RELAX - Returned MTU is kept at L3-level (like fib_lookup) V4: Lot of changes - ifindex 0 now use current netdev for MTU lookup - rename helper from bpf_mtu_check to bpf_check_mtu - fix bug for GSO pkt length (as skb->len is total len) - remove __bpf_len_adj_positive, simply allow negative len adj Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/161287790461.790810.3429728639563297353.stgit@firesoul --- include/uapi/linux/bpf.h | 75 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 75 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6b1f6058cccf..4c24daa43bac 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3847,6 +3847,69 @@ union bpf_attr { * Return * A pointer to a struct socket on success or NULL if the file is * not a socket. + * + * long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags) + * Description + + * Check ctx packet size against exceeding MTU of net device (based + * on *ifindex*). This helper will likely be used in combination + * with helpers that adjust/change the packet size. + * + * The argument *len_diff* can be used for querying with a planned + * size change. This allows to check MTU prior to changing packet + * ctx. Providing an *len_diff* adjustment that is larger than the + * actual packet size (resulting in negative packet size) will in + * principle not exceed the MTU, why it is not considered a + * failure. Other BPF-helpers are needed for performing the + * planned size change, why the responsability for catch a negative + * packet size belong in those helpers. + * + * Specifying *ifindex* zero means the MTU check is performed + * against the current net device. This is practical if this isn't + * used prior to redirect. + * + * The Linux kernel route table can configure MTUs on a more + * specific per route level, which is not provided by this helper. + * For route level MTU checks use the **bpf_fib_lookup**\ () + * helper. + * + * *ctx* is either **struct xdp_md** for XDP programs or + * **struct sk_buff** for tc cls_act programs. + * + * The *flags* argument can be a combination of one or more of the + * following values: + * + * **BPF_MTU_CHK_SEGS** + * This flag will only works for *ctx* **struct sk_buff**. + * If packet context contains extra packet segment buffers + * (often knows as GSO skb), then MTU check is harder to + * check at this point, because in transmit path it is + * possible for the skb packet to get re-segmented + * (depending on net device features). This could still be + * a MTU violation, so this flag enables performing MTU + * check against segments, with a different violation + * return code to tell it apart. Check cannot use len_diff. + * + * On return *mtu_len* pointer contains the MTU value of the net + * device. Remember the net device configured MTU is the L3 size, + * which is returned here and XDP and TX length operate at L2. + * Helper take this into account for you, but remember when using + * MTU value in your BPF-code. On input *mtu_len* must be a valid + * pointer and be initialized (to zero), else verifier will reject + * BPF program. + * + * Return + * * 0 on success, and populate MTU value in *mtu_len* pointer. + * + * * < 0 if any input argument is invalid (*mtu_len* not updated) + * + * MTU violations return positive values, but also populate MTU + * value in *mtu_len* pointer, as this can be needed for + * implementing PMTU handing: + * + * * **BPF_MTU_CHK_RET_FRAG_NEEDED** + * * **BPF_MTU_CHK_RET_SEGS_TOOBIG** + * */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -4012,6 +4075,7 @@ union bpf_attr { FN(ktime_get_coarse_ns), \ FN(ima_inode_hash), \ FN(sock_from_file), \ + FN(check_mtu), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -5045,6 +5109,17 @@ struct bpf_redir_neigh { }; }; +/* bpf_check_mtu flags*/ +enum bpf_check_mtu_flags { + BPF_MTU_CHK_SEGS = (1U << 0), +}; + +enum bpf_check_mtu_ret { + BPF_MTU_CHK_RET_SUCCESS, /* check and lookup successful */ + BPF_MTU_CHK_RET_FRAG_NEEDED, /* fragmentation required to fwd */ + BPF_MTU_CHK_RET_SEGS_TOOBIG, /* GSO re-segmentation needed to fwd */ +}; + enum bpf_task_fd_type { BPF_FD_TYPE_RAW_TRACEPOINT, /* tp name */ BPF_FD_TYPE_TRACEPOINT, /* tp name */ -- cgit v1.2.3 From 5f7d57280c1982d993d5f4ff0edac310f820f607 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 9 Feb 2021 14:38:29 +0100 Subject: bpf: Drop MTU check when doing TC-BPF redirect to ingress The use-case for dropping the MTU check when TC-BPF does redirect to ingress, is described by Eyal Birger in email[0]. The summary is the ability to increase packet size (e.g. with IPv6 headers for NAT64) and ingress redirect packet and let normal netstack fragment packet as needed. [0] https://lore.kernel.org/netdev/CAHsH6Gug-hsLGHQ6N0wtixdOa85LDZ3HNRHVd0opR=19Qo4W4Q@mail.gmail.com/ V15: - missing static for function declaration V9: - Make net_device "up" (IFF_UP) check explicit in skb_do_redirect V4: - Keep net_device "up" (IFF_UP) check. - Adjustment to handle bpf_redirect_peer() helper Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/161287790971.790810.11785274340154740591.stgit@firesoul --- include/linux/netdevice.h | 32 ++++++++++++++++++++++++++++++-- 1 file changed, 30 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ef517254367d..b9bcbfde7849 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3931,14 +3931,42 @@ int xdp_umem_query(struct net_device *dev, u16 queue_id); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); +int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb); bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb); +static __always_inline bool __is_skb_forwardable(const struct net_device *dev, + const struct sk_buff *skb, + const bool check_mtu) +{ + const u32 vlan_hdr_len = 4; /* VLAN_HLEN */ + unsigned int len; + + if (!(dev->flags & IFF_UP)) + return false; + + if (!check_mtu) + return true; + + len = dev->mtu + dev->hard_header_len + vlan_hdr_len; + if (skb->len <= len) + return true; + + /* if TSO is enabled, we don't care about the length as the packet + * could be forwarded without being segmented before + */ + if (skb_is_gso(skb)) + return true; + + return false; +} + static __always_inline int ____dev_forward_skb(struct net_device *dev, - struct sk_buff *skb) + struct sk_buff *skb, + const bool check_mtu) { if (skb_orphan_frags(skb, GFP_ATOMIC) || - unlikely(!is_skb_forwardable(dev, skb))) { + unlikely(!__is_skb_forwardable(dev, skb, check_mtu))) { atomic_long_inc(&dev->rx_dropped); kfree_skb(skb); return NET_RX_DROP; -- cgit v1.2.3 From 4d54cc32112d8d8b0667559c9309f1a6f764f70b Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 12 Feb 2021 15:59:59 -0800 Subject: mptcp: avoid lock_fast usage in accept path Once event support is added this may need to allocate memory while msk lock is held with softirqs disabled. Not using lock_fast also allows to do the allocation with GFP_KERNEL. Signed-off-by: Florian Westphal Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/net/genetlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index e55ec1597ce7..7cb3fa8310ed 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -14,6 +14,7 @@ */ struct genl_multicast_group { char name[GENL_NAMSIZ]; + u8 flags; }; struct genl_ops; -- cgit v1.2.3 From b911c97c7dc771633c68ea9b8f15070f8af3d323 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 12 Feb 2021 16:00:01 -0800 Subject: mptcp: add netlink event support Allow userspace (mptcpd) to subscribe to mptcp genl multicast events. This implementation reuses the same event API as the mptcp kernel fork to ease integration of existing tools, e.g. mptcpd. Supported events include: 1. start and close of an mptcp connection 2. start and close of subflows (joins) 3. announce and withdrawals of addresses 4. subflow priority (backup/non-backup) change. Reviewed-by: Matthieu Baerts Signed-off-by: Florian Westphal Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/uapi/linux/mptcp.h | 74 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 74 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 3674a451a18c..c91578aaab32 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -36,6 +36,7 @@ enum { /* netlink interface */ #define MPTCP_PM_NAME "mptcp_pm" #define MPTCP_PM_CMD_GRP_NAME "mptcp_pm_cmds" +#define MPTCP_PM_EV_GRP_NAME "mptcp_pm_events" #define MPTCP_PM_VER 0x1 /* @@ -104,4 +105,77 @@ struct mptcp_info { __u64 mptcpi_rcv_nxt; }; +/* + * MPTCP_EVENT_CREATED: token, family, saddr4 | saddr6, daddr4 | daddr6, + * sport, dport + * A new MPTCP connection has been created. It is the good time to allocate + * memory and send ADD_ADDR if needed. Depending on the traffic-patterns + * it can take a long time until the MPTCP_EVENT_ESTABLISHED is sent. + * + * MPTCP_EVENT_ESTABLISHED: token, family, saddr4 | saddr6, daddr4 | daddr6, + * sport, dport + * A MPTCP connection is established (can start new subflows). + * + * MPTCP_EVENT_CLOSED: token + * A MPTCP connection has stopped. + * + * MPTCP_EVENT_ANNOUNCED: token, rem_id, family, daddr4 | daddr6 [, dport] + * A new address has been announced by the peer. + * + * MPTCP_EVENT_REMOVED: token, rem_id + * An address has been lost by the peer. + * + * MPTCP_EVENT_SUB_ESTABLISHED: token, family, saddr4 | saddr6, + * daddr4 | daddr6, sport, dport, backup, + * if_idx [, error] + * A new subflow has been established. 'error' should not be set. + * + * MPTCP_EVENT_SUB_CLOSED: token, family, saddr4 | saddr6, daddr4 | daddr6, + * sport, dport, backup, if_idx [, error] + * A subflow has been closed. An error (copy of sk_err) could be set if an + * error has been detected for this subflow. + * + * MPTCP_EVENT_SUB_PRIORITY: token, family, saddr4 | saddr6, daddr4 | daddr6, + * sport, dport, backup, if_idx [, error] + * The priority of a subflow has changed. 'error' should not be set. + */ +enum mptcp_event_type { + MPTCP_EVENT_UNSPEC = 0, + MPTCP_EVENT_CREATED = 1, + MPTCP_EVENT_ESTABLISHED = 2, + MPTCP_EVENT_CLOSED = 3, + + MPTCP_EVENT_ANNOUNCED = 6, + MPTCP_EVENT_REMOVED = 7, + + MPTCP_EVENT_SUB_ESTABLISHED = 10, + MPTCP_EVENT_SUB_CLOSED = 11, + + MPTCP_EVENT_SUB_PRIORITY = 13, +}; + +enum mptcp_event_attr { + MPTCP_ATTR_UNSPEC = 0, + + MPTCP_ATTR_TOKEN, /* u32 */ + MPTCP_ATTR_FAMILY, /* u16 */ + MPTCP_ATTR_LOC_ID, /* u8 */ + MPTCP_ATTR_REM_ID, /* u8 */ + MPTCP_ATTR_SADDR4, /* be32 */ + MPTCP_ATTR_SADDR6, /* struct in6_addr */ + MPTCP_ATTR_DADDR4, /* be32 */ + MPTCP_ATTR_DADDR6, /* struct in6_addr */ + MPTCP_ATTR_SPORT, /* be16 */ + MPTCP_ATTR_DPORT, /* be16 */ + MPTCP_ATTR_BACKUP, /* u8 */ + MPTCP_ATTR_ERROR, /* u8 */ + MPTCP_ATTR_FLAGS, /* u16 */ + MPTCP_ATTR_TIMEOUT, /* u32 */ + MPTCP_ATTR_IF_IDX, /* s32 */ + + __MPTCP_ATTR_AFTER_LAST +}; + +#define MPTCP_ATTR_MAX (__MPTCP_ATTR_AFTER_LAST - 1) + #endif /* _UAPI_MPTCP_H */ -- cgit v1.2.3 From 4c08c586ff29bda47e3db14da096331d84933f48 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 12 Feb 2021 17:15:51 +0200 Subject: net: switchdev: propagate extack to port attributes When a struct switchdev_attr is notified through switchdev, there is no way to report informational messages, unlike for struct switchdev_obj. Signed-off-by: Vladimir Oltean Reviewed-by: Ido Schimmel Reviewed-by: Florian Fainelli Reviewed-by: Nikolay Aleksandrov Reviewed-by: Grygorii Strashko Signed-off-by: David S. Miller --- include/net/switchdev.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 6dcfc4c51a6e..9279d4245bab 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -281,7 +281,8 @@ int switchdev_handle_port_attr_set(struct net_device *dev, struct switchdev_notifier_port_attr_info *port_attr_info, bool (*check_cb)(const struct net_device *dev), int (*set_cb)(struct net_device *dev, - const struct switchdev_attr *attr)); + const struct switchdev_attr *attr, + struct netlink_ext_ack *extack)); #else static inline void switchdev_deferred_process(void) @@ -372,7 +373,8 @@ switchdev_handle_port_attr_set(struct net_device *dev, struct switchdev_notifier_port_attr_info *port_attr_info, bool (*check_cb)(const struct net_device *dev), int (*set_cb)(struct net_device *dev, - const struct switchdev_attr *attr)) + const struct switchdev_attr *attr, + struct netlink_ext_ack *extack)) { return 0; } -- cgit v1.2.3 From e18f4c18ab5b0dd47caaf8377c2e36d66f632a8c Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 12 Feb 2021 17:15:55 +0200 Subject: net: switchdev: pass flags and mask to both {PRE_,}BRIDGE_FLAGS attributes This switchdev attribute offers a counterproductive API for a driver writer, because although br_switchdev_set_port_flag gets passed a "flags" and a "mask", those are passed piecemeal to the driver, so while the PRE_BRIDGE_FLAGS listener knows what changed because it has the "mask", the BRIDGE_FLAGS listener doesn't, because it only has the final value. But certain drivers can offload only certain combinations of settings, like for example they cannot change unicast flooding independently of multicast flooding - they must be both on or both off. The way the information is passed to switchdev makes drivers not expressive enough, and unable to reject this request ahead of time, in the PRE_BRIDGE_FLAGS notifier, so they are forced to reject it during the deferred BRIDGE_FLAGS attribute, where the rejection is currently ignored. This patch also changes drivers to make use of the "mask" field for edge detection when possible. Signed-off-by: Vladimir Oltean Reviewed-by: Grygorii Strashko Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/net/switchdev.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 9279d4245bab..25d9e4570934 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -32,6 +32,11 @@ enum switchdev_attr_id { #endif }; +struct switchdev_brport_flags { + unsigned long val; + unsigned long mask; +}; + struct switchdev_attr { struct net_device *orig_dev; enum switchdev_attr_id id; @@ -40,7 +45,7 @@ struct switchdev_attr { void (*complete)(struct net_device *dev, int err, void *priv); union { u8 stp_state; /* PORT_STP_STATE */ - unsigned long brport_flags; /* PORT_{PRE}_BRIDGE_FLAGS */ + struct switchdev_brport_flags brport_flags; /* PORT_BRIDGE_FLAGS */ bool mrouter; /* PORT_MROUTER */ clock_t ageing_time; /* BRIDGE_AGEING_TIME */ bool vlan_filtering; /* BRIDGE_VLAN_FILTERING */ -- cgit v1.2.3 From a8b659e7ff75a6e766bc5691df57ceb26018db9f Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 12 Feb 2021 17:15:56 +0200 Subject: net: dsa: act as passthrough for bridge port flags There are multiple ways in which a PORT_BRIDGE_FLAGS attribute can be expressed by the bridge through switchdev, and not all of them can be emulated by DSA mid-layer API at the same time. One possible configuration is when the bridge offloads the port flags using a mask that has a single bit set - therefore only one feature should change. However, DSA currently groups together unicast and multicast flooding in the .port_egress_floods method, which limits our options when we try to add support for turning off broadcast flooding: do we extend .port_egress_floods with a third parameter which b53 and mv88e6xxx will ignore? But that means that the DSA layer, which currently implements the PRE_BRIDGE_FLAGS attribute all by itself, will see that .port_egress_floods is implemented, and will report that all 3 types of flooding are supported - not necessarily true. Another configuration is when the user specifies more than one flag at the same time, in the same netlink message. If we were to create one individual function per offloadable bridge port flag, we would limit the expressiveness of the switch driver of refusing certain combinations of flag values. For example, a switch may not have an explicit knob for flooding of unknown multicast, just for flooding in general. In that case, the only correct thing to do is to allow changes to BR_FLOOD and BR_MCAST_FLOOD in tandem, and never allow mismatched values. But having a separate .port_set_unicast_flood and .port_set_multicast_flood would not allow the driver to possibly reject that. Also, DSA doesn't consider it necessary to inform the driver that a SWITCHDEV_ATTR_ID_BRIDGE_MROUTER attribute was offloaded, because it just calls .port_egress_floods for the CPU port. When we'll add support for the plain SWITCHDEV_ATTR_ID_PORT_MROUTER, that will become a real problem because the flood settings will need to be held statefully in the DSA middle layer, otherwise changing the mrouter port attribute will impact the flooding attribute. And that's _assuming_ that the underlying hardware doesn't have anything else to do when a multicast router attaches to a port than flood unknown traffic to it. If it does, there will need to be a dedicated .port_set_mrouter anyway. So we need to let the DSA drivers see the exact form that the bridge passes this switchdev attribute in, otherwise we are standing in the way. Therefore we also need to use this form of language when communicating to the driver that it needs to configure its initial (before bridge join) and final (after bridge leave) port flags. The b53 and mv88e6xxx drivers are converted to the passthrough API and their implementation of .port_egress_floods is split into two: a function that configures unicast flooding and another for multicast. The mv88e6xxx implementation is quite hairy, and it turns out that the implementations of unknown unicast flooding are actually the same for 6185 and for 6352: behind the confusing names actually lie two individual bits: NO_UNKNOWN_MC -> FLOOD_UC = 0x4 = BIT(2) NO_UNKNOWN_UC -> FLOOD_MC = 0x8 = BIT(3) so there was no reason to entangle them in the first place. Whereas the 6185 writes to MV88E6185_PORT_CTL0_FORWARD_UNKNOWN of PORT_CTL0, which has the exact same bit index. I have left the implementations separate though, for the only reason that the names are different enough to confuse me, since I am not able to double-check with a user manual. The multicast flooding setting for 6185 is in a different register than for 6352 though. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/net/dsa.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index d8de23ce7221..74457aaffec7 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -626,8 +626,14 @@ struct dsa_switch_ops { void (*port_stp_state_set)(struct dsa_switch *ds, int port, u8 state); void (*port_fast_age)(struct dsa_switch *ds, int port); - int (*port_egress_floods)(struct dsa_switch *ds, int port, - bool unicast, bool multicast); + int (*port_pre_bridge_flags)(struct dsa_switch *ds, int port, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack); + int (*port_bridge_flags)(struct dsa_switch *ds, int port, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack); + int (*port_set_mrouter)(struct dsa_switch *ds, int port, bool mrouter, + struct netlink_ext_ack *extack); /* * VLAN support -- cgit v1.2.3 From b360d94f1b8647bc164e7519ec900471836be14a Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 12 Feb 2021 17:15:58 +0200 Subject: net: mscc: ocelot: use separate flooding PGID for broadcast In preparation of offloading the bridge port flags which have independent settings for unknown multicast and for broadcast, we should also start reserving one destination Port Group ID for the flooding of broadcast packets, to allow configuring it individually. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index bfce3df61bfd..9acbef1416f1 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -54,16 +54,17 @@ * PGID_CPU: used for whitelisting certain MAC addresses, such as the addresses * of the switch port net devices, towards the CPU port module. * PGID_UC: the flooding destinations for unknown unicast traffic. - * PGID_MC: the flooding destinations for broadcast and non-IP multicast - * traffic. + * PGID_MC: the flooding destinations for non-IP multicast traffic. * PGID_MCIPV4: the flooding destinations for IPv4 multicast traffic. * PGID_MCIPV6: the flooding destinations for IPv6 multicast traffic. + * PGID_BC: the flooding destinations for broadcast traffic. */ -#define PGID_CPU 59 -#define PGID_UC 60 -#define PGID_MC 61 -#define PGID_MCIPV4 62 -#define PGID_MCIPV6 63 +#define PGID_CPU 58 +#define PGID_UC 59 +#define PGID_MC 60 +#define PGID_MCIPV4 61 +#define PGID_MCIPV6 62 +#define PGID_BC 63 #define for_each_unicast_dest_pgid(ocelot, pgid) \ for ((pgid) = 0; \ -- cgit v1.2.3 From 421741ea5672cf16fa551bcde23e327075ed419e Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 12 Feb 2021 17:15:59 +0200 Subject: net: mscc: ocelot: offload bridge port flags to device We should not be unconditionally enabling address learning, since doing that is actively detrimential when a port is standalone and not offloading a bridge. Namely, if a port in the switch is standalone and others are offloading the bridge, then we could enter a situation where we learn an address towards the standalone port, but the bridged ports could not forward the packet there, because the CPU is the only path between the standalone and the bridged ports. The solution of course is to not enable address learning unless the bridge asks for it. We need to set up the initial port flags for no learning and flooding everything, and also when the port joins and leaves the bridge. The flood configuration was already configured ok for standalone mode in ocelot_init, we just need to disable learning in ocelot_init_port. Signed-off-by: Vladimir Oltean Reviewed-by: Alexandre Belloni Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 9acbef1416f1..40792b37bb9f 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -612,6 +612,7 @@ struct ocelot_port { u8 *xmit_template; bool is_dsa_8021q_cpu; + bool learn_ena; struct net_device *bond; bool lag_tx_active; @@ -766,6 +767,10 @@ void ocelot_adjust_link(struct ocelot *ocelot, int port, int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, bool enabled); void ocelot_bridge_stp_state_set(struct ocelot *ocelot, int port, u8 state); void ocelot_apply_bridge_fwd_mask(struct ocelot *ocelot); +int ocelot_port_pre_bridge_flags(struct ocelot *ocelot, int port, + struct switchdev_brport_flags val); +void ocelot_port_bridge_flags(struct ocelot *ocelot, int port, + struct switchdev_brport_flags val); int ocelot_port_bridge_join(struct ocelot *ocelot, int port, struct net_device *bridge); int ocelot_port_bridge_leave(struct ocelot *ocelot, int port, -- cgit v1.2.3 From f969dc5a885736842c3511ecdea240fbb02d25d9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 12 Feb 2021 15:22:13 -0800 Subject: tcp: fix SO_RCVLOWAT related hangs under mem pressure While commit 24adbc1676af ("tcp: fix SO_RCVLOWAT hangs with fat skbs") fixed an issue vs too small sk_rcvbuf for given sk_rcvlowat constraint, it missed to address issue caused by memory pressure. 1) If we are under memory pressure and socket receive queue is empty. First incoming packet is allowed to be queued, after commit 76dfa6082032 ("tcp: allow one skb to be received per socket under memory pressure") But we do not send EPOLLIN yet, in case tcp_data_ready() sees sk_rcvlowat is bigger than skb length. 2) Then, when next packet comes, it is dropped, and we directly call sk->sk_data_ready(). 3) If application is using poll(), tcp_poll() will then use tcp_stream_is_readable() and decide the socket receive queue is not yet filled, so nothing will happen. Even when sender retransmits packets, phases 2) & 3) repeat and flow is effectively frozen, until memory pressure is off. Fix is to consider tcp_under_memory_pressure() to take care of global memory pressure or memcg pressure. Fixes: 24adbc1676af ("tcp: fix SO_RCVLOWAT hangs with fat skbs") Signed-off-by: Eric Dumazet Reported-by: Arjun Roy Suggested-by: Wei Wang Reviewed-by: Wei Wang Signed-off-by: David S. Miller --- include/net/tcp.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 25bbada379c4..244208f6f6c2 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1431,8 +1431,13 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied); */ static inline bool tcp_rmem_pressure(const struct sock *sk) { - int rcvbuf = READ_ONCE(sk->sk_rcvbuf); - int threshold = rcvbuf - (rcvbuf >> 3); + int rcvbuf, threshold; + + if (tcp_under_memory_pressure(sk)) + return true; + + rcvbuf = READ_ONCE(sk->sk_rcvbuf); + threshold = rcvbuf - (rcvbuf >> 3); return atomic_read(&sk->sk_rmem_alloc) > threshold; } -- cgit v1.2.3 From 05dc72aba364d374a27de567fac58c199ff5ee97 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 12 Feb 2021 15:22:14 -0800 Subject: tcp: factorize logic into tcp_epollin_ready() Both tcp_data_ready() and tcp_stream_is_readable() share the same logic. Add tcp_epollin_ready() helper to avoid duplication. Signed-off-by: Eric Dumazet Cc: Arjun Roy Cc: Wei Wang Signed-off-by: David S. Miller --- include/net/tcp.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 244208f6f6c2..484eb2362645 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1442,6 +1442,18 @@ static inline bool tcp_rmem_pressure(const struct sock *sk) return atomic_read(&sk->sk_rmem_alloc) > threshold; } +static inline bool tcp_epollin_ready(const struct sock *sk, int target) +{ + const struct tcp_sock *tp = tcp_sk(sk); + int avail = READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq); + + if (avail <= 0) + return false; + + return (avail >= target) || tcp_rmem_pressure(sk) || + (tcp_receive_window(tp) <= inet_csk(sk)->icsk_ack.rcv_mss); +} + extern void tcp_openreq_init_rwin(struct request_sock *req, const struct sock *sk_listener, const struct dst_entry *dst); -- cgit v1.2.3 From e5069b9c23b3857db986c58801bebe450cff3392 Mon Sep 17 00:00:00 2001 From: Dmitrii Banshchikov Date: Sat, 13 Feb 2021 00:56:41 +0400 Subject: bpf: Support pointers in global func args Add an ability to pass a pointer to a type with known size in arguments of a global function. Such pointers may be used to overcome the limit on the maximum number of arguments, avoid expensive and tricky workarounds and to have multiple output arguments. A referenced type may contain pointers but indirect access through them isn't supported. The implementation consists of two parts. If a global function has an argument that is a pointer to a type with known size then: 1) In btf_check_func_arg_match(): check that the corresponding register points to NULL or to a valid memory region that is large enough to contain the expected argument's type. 2) In btf_prepare_func_args(): set the corresponding register type to PTR_TO_MEM_OR_NULL and its size to the size of the expected type. Only global functions are supported because allowance of pointers for static functions might break validation. Consider the following scenario. A static function has a pointer argument. A caller passes pointer to its stack memory. Because the callee can change referenced memory verifier cannot longer assume any particular slot type of the caller's stack memory hence the slot type is changed to SLOT_MISC. If there is an operation that relies on slot type other than SLOT_MISC then verifier won't be able to infer safety of the operation. When verifier sees a static function that has a pointer argument different from PTR_TO_CTX then it skips arguments check and continues with "inline" validation with more information available. The operation that relies on the particular slot type now succeeds. Because global functions were not allowed to have pointer arguments different from PTR_TO_CTX it's not possible to break existing and valid code. Signed-off-by: Dmitrii Banshchikov Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210212205642.620788-4-me@ubique.spb.ru --- include/linux/bpf_verifier.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 532c97836d0d..971b33aca13d 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -471,6 +471,8 @@ bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt); int check_ctx_reg(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno); +int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + u32 regno, u32 mem_size); /* this lives here instead of in bpf.h because it needs to dereference tgt_prog */ static inline u64 bpf_trampoline_compute_key(const struct bpf_prog *tgt_prog, -- cgit v1.2.3 From fec6e49b63989657bc4076dad99fa51d5ece34da Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Sat, 13 Feb 2021 14:12:02 +0000 Subject: skbuff: remove __kfree_skb_flush() This function isn't much needed as NAPI skb queue gets bulk-freed anyway when there's no more room, and even may reduce the efficiency of bulk operations. It will be even less needed after reusing skb cache on allocation path, so remove it and this way lighten network softirqs a bit. Suggested-by: Eric Dumazet Signed-off-by: Alexander Lobakin Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0a4e91a2f873..0e0707296098 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2919,7 +2919,6 @@ static inline struct sk_buff *napi_alloc_skb(struct napi_struct *napi, } void napi_consume_skb(struct sk_buff *skb, int budget); -void __kfree_skb_flush(void); void __kfree_skb_defer(struct sk_buff *skb); /** -- cgit v1.2.3 From f450d539c05a14c103dd174718f81bb2fe65cb4b Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Sat, 13 Feb 2021 14:12:25 +0000 Subject: skbuff: introduce {,__}napi_build_skb() which reuses NAPI cache heads Instead of just bulk-flushing skbuff_heads queued up through napi_consume_skb() or __kfree_skb_defer(), try to reuse them on allocation path. If the cache is empty on allocation, bulk-allocate the first 16 elements, which is more efficient than per-skb allocation. If the cache is full on freeing, bulk-wipe the second half of the cache (32 elements). This also includes custom KASAN poisoning/unpoisoning to be double sure there are no use-after-free cases. To not change current behaviour, introduce a new function, napi_build_skb(), to optionally use a new approach later in drivers. Note on selected bulk size, 16: - this equals to XDP_BULK_QUEUE_SIZE, DEV_MAP_BULK_SIZE and especially VETH_XDP_BATCH, which is also used to bulk-allocate skbuff_heads and was tested on powerful setups; - this also showed the best performance in the actual test series (from the array of {8, 16, 32}). Suggested-by: Edward Cree # Divide on two halves Suggested-by: Eric Dumazet # KASAN poisoning Cc: Dmitry Vyukov # Help with KASAN Cc: Paolo Abeni # Reduced batch size Signed-off-by: Alexander Lobakin Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0e0707296098..906122eac82a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1087,6 +1087,8 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size); +struct sk_buff *napi_build_skb(void *data, unsigned int frag_size); + /** * alloc_skb - allocate a network buffer * @size: size to allocate -- cgit v1.2.3 From 9243adfc311a20371c3f4d8eaf0af4b135e6fac3 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Sat, 13 Feb 2021 14:13:09 +0000 Subject: skbuff: queue NAPI_MERGED_FREE skbs into NAPI cache instead of freeing napi_frags_finish() and napi_skb_finish() can only be called inside NAPI Rx context, so we can feed NAPI cache with skbuff_heads that got NAPI_MERGED_FREE verdict instead of immediate freeing. Replace __kfree_skb() with __kfree_skb_defer() in napi_skb_finish() and move napi_skb_free_stolen_head() to skbuff.c, so it can drop skbs to NAPI cache. As many drivers call napi_alloc_skb()/napi_get_frags() on their receive path, this becomes especially useful. Signed-off-by: Alexander Lobakin Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 906122eac82a..6d0a33d1c0db 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2921,6 +2921,7 @@ static inline struct sk_buff *napi_alloc_skb(struct napi_struct *napi, } void napi_consume_skb(struct sk_buff *skb, int budget); +void napi_skb_free_stolen_head(struct sk_buff *skb); void __kfree_skb_defer(struct sk_buff *skb); /** -- cgit v1.2.3 From 137ffbc4bb86a12d7979e6f839d4babc8aef7669 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 14 Feb 2021 00:37:54 +0200 Subject: net: mscc: ocelot: refactor ocelot_port_inject_frame out of ocelot_port_xmit The felix DSA driver will inject some frames through register MMIO, same as ocelot switchdev currently does. So we need to be able to reuse the common code. Also create some shim definitions, since the DSA tagger can be compiled without support for the switch driver. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 40792b37bb9f..a22aa944e921 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -742,6 +742,28 @@ u32 __ocelot_target_read_ix(struct ocelot *ocelot, enum ocelot_target target, void __ocelot_target_write_ix(struct ocelot *ocelot, enum ocelot_target target, u32 val, u32 reg, u32 offset); +/* Packet I/O */ +#if IS_ENABLED(CONFIG_MSCC_OCELOT_SWITCH_LIB) + +bool ocelot_can_inject(struct ocelot *ocelot, int grp); +void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, + u32 rew_op, struct sk_buff *skb); + +#else + +static inline bool ocelot_can_inject(struct ocelot *ocelot, int grp) +{ + return false; +} + +static inline void ocelot_port_inject_frame(struct ocelot *ocelot, int port, + int grp, u32 rew_op, + struct sk_buff *skb) +{ +} + +#endif + /* Hardware initialization */ int ocelot_regfields_init(struct ocelot *ocelot, const struct reg_field *const regfields); -- cgit v1.2.3 From 40d3f295b5feda409784e569550057b5fbc2a295 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 14 Feb 2021 00:37:56 +0200 Subject: net: mscc: ocelot: use common tag parsing code with DSA The Injection Frame Header and Extraction Frame Header that the switch prepends to frames over the NPI port is also prepended to frames delivered over the CPU port module's queues. Let's unify the handling of the frame headers by making the ocelot driver call some helpers exported by the DSA tagger. Among other things, this allows us to get rid of the strange cpu_to_be32 when transmitting the Injection Frame Header on ocelot, since the packing API uses network byte order natively (when "quirks" is 0). The comments above ocelot_gen_ifh talk about setting pop_cnt to 3, and the cpu extraction queue mask to something, but the code doesn't do it, so we don't do it either. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/dsa/ocelot.h | 208 +++++++++++++++++++++++++++++++++++++++++++++ include/soc/mscc/ocelot.h | 7 -- 2 files changed, 208 insertions(+), 7 deletions(-) create mode 100644 include/linux/dsa/ocelot.h (limited to 'include') diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h new file mode 100644 index 000000000000..763dbbfaff7a --- /dev/null +++ b/include/linux/dsa/ocelot.h @@ -0,0 +1,208 @@ +/* SPDX-License-Identifier: GPL-2.0 + * Copyright 2019-2021 NXP Semiconductors + */ + +#ifndef _NET_DSA_TAG_OCELOT_H +#define _NET_DSA_TAG_OCELOT_H + +#include + +#define OCELOT_TAG_LEN 16 +#define OCELOT_SHORT_PREFIX_LEN 4 +#define OCELOT_LONG_PREFIX_LEN 16 +#define OCELOT_TOTAL_TAG_LEN (OCELOT_SHORT_PREFIX_LEN + OCELOT_TAG_LEN) + +/* The CPU injection header and the CPU extraction header can have 3 types of + * prefixes: long, short and no prefix. The format of the header itself is the + * same in all 3 cases. + * + * Extraction with long prefix: + * + * +-------------------+-------------------+------+------+------------+-------+ + * | ff:ff:ff:ff:ff:ff | fe:ff:ff:ff:ff:ff | 8880 | 000a | extraction | frame | + * | | | | | header | | + * +-------------------+-------------------+------+------+------------+-------+ + * 48 bits 48 bits 16 bits 16 bits 128 bits + * + * Extraction with short prefix: + * + * +------+------+------------+-------+ + * | 8880 | 000a | extraction | frame | + * | | | header | | + * +------+------+------------+-------+ + * 16 bits 16 bits 128 bits + * + * Extraction with no prefix: + * + * +------------+-------+ + * | extraction | frame | + * | header | | + * +------------+-------+ + * 128 bits + * + * + * Injection with long prefix: + * + * +-------------------+-------------------+------+------+------------+-------+ + * | any dmac | any smac | 8880 | 000a | injection | frame | + * | | | | | header | | + * +-------------------+-------------------+------+------+------------+-------+ + * 48 bits 48 bits 16 bits 16 bits 128 bits + * + * Injection with short prefix: + * + * +------+------+------------+-------+ + * | 8880 | 000a | injection | frame | + * | | | header | | + * +------+------+------------+-------+ + * 16 bits 16 bits 128 bits + * + * Injection with no prefix: + * + * +------------+-------+ + * | injection | frame | + * | header | | + * +------------+-------+ + * 128 bits + * + * The injection header looks like this (network byte order, bit 127 + * is part of lowest address byte in memory, bit 0 is part of highest + * address byte): + * + * +------+------+------+------+------+------+------+------+ + * 127:120 |BYPASS| MASQ | MASQ_PORT |REW_OP|REW_OP| + * +------+------+------+------+------+------+------+------+ + * 119:112 | REW_OP | + * +------+------+------+------+------+------+------+------+ + * 111:104 | REW_VAL | + * +------+------+------+------+------+------+------+------+ + * 103: 96 | REW_VAL | + * +------+------+------+------+------+------+------+------+ + * 95: 88 | REW_VAL | + * +------+------+------+------+------+------+------+------+ + * 87: 80 | REW_VAL | + * +------+------+------+------+------+------+------+------+ + * 79: 72 | RSV | + * +------+------+------+------+------+------+------+------+ + * 71: 64 | RSV | DEST | + * +------+------+------+------+------+------+------+------+ + * 63: 56 | DEST | + * +------+------+------+------+------+------+------+------+ + * 55: 48 | RSV | + * +------+------+------+------+------+------+------+------+ + * 47: 40 | RSV | SRC_PORT | RSV |TFRM_TIMER| + * +------+------+------+------+------+------+------+------+ + * 39: 32 | TFRM_TIMER | RSV | + * +------+------+------+------+------+------+------+------+ + * 31: 24 | RSV | DP | POP_CNT | CPUQ | + * +------+------+------+------+------+------+------+------+ + * 23: 16 | CPUQ | QOS_CLASS |TAG_TYPE| + * +------+------+------+------+------+------+------+------+ + * 15: 8 | PCP | DEI | VID | + * +------+------+------+------+------+------+------+------+ + * 7: 0 | VID | + * +------+------+------+------+------+------+------+------+ + * + * And the extraction header looks like this: + * + * +------+------+------+------+------+------+------+------+ + * 127:120 | RSV | REW_OP | + * +------+------+------+------+------+------+------+------+ + * 119:112 | REW_OP | REW_VAL | + * +------+------+------+------+------+------+------+------+ + * 111:104 | REW_VAL | + * +------+------+------+------+------+------+------+------+ + * 103: 96 | REW_VAL | + * +------+------+------+------+------+------+------+------+ + * 95: 88 | REW_VAL | + * +------+------+------+------+------+------+------+------+ + * 87: 80 | REW_VAL | LLEN | + * +------+------+------+------+------+------+------+------+ + * 79: 72 | LLEN | WLEN | + * +------+------+------+------+------+------+------+------+ + * 71: 64 | WLEN | RSV | + * +------+------+------+------+------+------+------+------+ + * 63: 56 | RSV | + * +------+------+------+------+------+------+------+------+ + * 55: 48 | RSV | + * +------+------+------+------+------+------+------+------+ + * 47: 40 | RSV | SRC_PORT | ACL_ID | + * +------+------+------+------+------+------+------+------+ + * 39: 32 | ACL_ID | RSV | SFLOW_ID | + * +------+------+------+------+------+------+------+------+ + * 31: 24 |ACL_HIT| DP | LRN_FLAGS | CPUQ | + * +------+------+------+------+------+------+------+------+ + * 23: 16 | CPUQ | QOS_CLASS |TAG_TYPE| + * +------+------+------+------+------+------+------+------+ + * 15: 8 | PCP | DEI | VID | + * +------+------+------+------+------+------+------+------+ + * 7: 0 | VID | + * +------+------+------+------+------+------+------+------+ + */ + +static inline void ocelot_xfh_get_rew_val(void *extraction, u64 *rew_val) +{ + packing(extraction, rew_val, 116, 85, OCELOT_TAG_LEN, UNPACK, 0); +} + +static inline void ocelot_xfh_get_len(void *extraction, u64 *len) +{ + u64 llen, wlen; + + packing(extraction, &llen, 84, 79, OCELOT_TAG_LEN, UNPACK, 0); + packing(extraction, &wlen, 78, 71, OCELOT_TAG_LEN, UNPACK, 0); + + *len = 60 * wlen + llen - 80; +} + +static inline void ocelot_xfh_get_src_port(void *extraction, u64 *src_port) +{ + packing(extraction, src_port, 46, 43, OCELOT_TAG_LEN, UNPACK, 0); +} + +static inline void ocelot_xfh_get_qos_class(void *extraction, u64 *qos_class) +{ + packing(extraction, qos_class, 19, 17, OCELOT_TAG_LEN, UNPACK, 0); +} + +static inline void ocelot_xfh_get_tag_type(void *extraction, u64 *tag_type) +{ + packing(extraction, tag_type, 16, 16, OCELOT_TAG_LEN, UNPACK, 0); +} + +static inline void ocelot_xfh_get_vlan_tci(void *extraction, u64 *vlan_tci) +{ + packing(extraction, vlan_tci, 15, 0, OCELOT_TAG_LEN, UNPACK, 0); +} + +static inline void ocelot_ifh_set_bypass(void *injection, u64 bypass) +{ + packing(injection, &bypass, 127, 127, OCELOT_TAG_LEN, PACK, 0); +} + +static inline void ocelot_ifh_set_rew_op(void *injection, u64 rew_op) +{ + packing(injection, &rew_op, 125, 117, OCELOT_TAG_LEN, PACK, 0); +} + +static inline void ocelot_ifh_set_dest(void *injection, u64 dest) +{ + packing(injection, &dest, 67, 56, OCELOT_TAG_LEN, PACK, 0); +} + +static inline void ocelot_ifh_set_qos_class(void *injection, u64 qos_class) +{ + packing(injection, &qos_class, 19, 17, OCELOT_TAG_LEN, PACK, 0); +} + +static inline void ocelot_ifh_set_tag_type(void *injection, u64 tag_type) +{ + packing(injection, &tag_type, 16, 16, OCELOT_TAG_LEN, PACK, 0); +} + +static inline void ocelot_ifh_set_vid(void *injection, u64 vid) +{ + packing(injection, &vid, 11, 0, OCELOT_TAG_LEN, PACK, 0); +} + +#endif diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index a22aa944e921..11cae2e968b5 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -87,9 +87,6 @@ /* Source PGIDs, one per physical port */ #define PGID_SRC 80 -#define IFH_INJ_BYPASS BIT(31) -#define IFH_INJ_POP_CNT_DISABLE (3 << 28) - #define IFH_TAG_TYPE_C 0 #define IFH_TAG_TYPE_S 1 @@ -100,10 +97,6 @@ #define IFH_REW_OP_ORIGIN_PTP 0x5 #define OCELOT_NUM_TC 8 -#define OCELOT_TAG_LEN 16 -#define OCELOT_SHORT_PREFIX_LEN 4 -#define OCELOT_LONG_PREFIX_LEN 16 -#define OCELOT_TOTAL_TAG_LEN (OCELOT_SHORT_PREFIX_LEN + OCELOT_TAG_LEN) #define OCELOT_SPEED_2500 0 #define OCELOT_SPEED_1000 1 -- cgit v1.2.3 From 7c4bb540e9173c914c2091fdd9b6aee3c2a3e1e5 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 14 Feb 2021 00:37:58 +0200 Subject: net: dsa: tag_ocelot: create separate tagger for Seville The ocelot tagger is a hot mess currently, it relies on memory initialized by the attached driver for basic frame transmission. This is against all that DSA tagging protocols stand for, which is that the transmission and reception of a DSA-tagged frame, the data path, should be independent from the switch control path, because the tag protocol is in principle hot-pluggable and reusable across switches (even if in practice it wasn't until very recently). But if another driver like dsa_loop wants to make use of tag_ocelot, it couldn't. This was done to have common code between Felix and Ocelot, which have one bit difference in the frame header format. Quoting from commit 67c2404922c2 ("net: dsa: felix: create a template for the DSA tags on xmit"): Other alternatives have been analyzed, such as: - Create a separate tag_seville.c: too much code duplication for just 1 bit field difference. - Create a separate DSA_TAG_PROTO_SEVILLE under tag_ocelot.c, just like tag_brcm.c, which would have a separate .xmit function. Again, too much code duplication for just 1 bit field difference. - Allocate the template from the init function of the tag_ocelot.c module, instead of from the driver: couldn't figure out a method of accessing the correct port template corresponding to the correct tagger in the .xmit function. The really interesting part is that Seville should have had its own tagging protocol defined - it is not compatible on the wire with Ocelot, even for that single bit. In principle, a packet generated by DSA_TAG_PROTO_OCELOT when booted on NXP LS1028A would look in a certain way, but when booted on NXP T1040 it would look differently. The reverse is also true: a packet generated by a Seville switch would be interpreted incorrectly by Wireshark if it was told it was generated by an Ocelot switch. Actually things are a bit more nuanced. If we concentrate only on the DSA tag, what I said above is true, but Ocelot/Seville also support an optional DSA tag prefix, which can be short or long, and it is possible to distinguish the two taggers based on an integer constant put in that prefix. Nonetheless, creating a separate tagger is still justified, since the tag prefix is optional, and without it, there is again no way to distinguish. Claiming backwards binary compatibility is a bit more tough, since I've already changed the format of tag_ocelot once, in commit 5124197ce58b ("net: dsa: tag_ocelot: use a short prefix on both ingress and egress"). Therefore I am not very concerned with treating this as a bugfix and backporting it to stable kernels (which would be another mess due to the fact that there would be lots of conflicts with the other DSA_TAG_PROTO* definitions). It's just simpler to say that the string values of the taggers have ABI value starting with kernel 5.12, which will be when the changing of tag protocol via /sys/class/net//dsa/tagging goes live. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/dsa/ocelot.h | 10 ++++++++++ include/net/dsa.h | 2 ++ 2 files changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h index 763dbbfaff7a..c6bc45ae5e03 100644 --- a/include/linux/dsa/ocelot.h +++ b/include/linux/dsa/ocelot.h @@ -195,6 +195,16 @@ static inline void ocelot_ifh_set_qos_class(void *injection, u64 qos_class) packing(injection, &qos_class, 19, 17, OCELOT_TAG_LEN, PACK, 0); } +static inline void seville_ifh_set_dest(void *injection, u64 dest) +{ + packing(injection, &dest, 67, 57, OCELOT_TAG_LEN, PACK, 0); +} + +static inline void ocelot_ifh_set_src(void *injection, u64 src) +{ + packing(injection, &src, 46, 43, OCELOT_TAG_LEN, PACK, 0); +} + static inline void ocelot_ifh_set_tag_type(void *injection, u64 tag_type) { packing(injection, &tag_type, 16, 16, OCELOT_TAG_LEN, PACK, 0); diff --git a/include/net/dsa.h b/include/net/dsa.h index 74457aaffec7..b095ef114fe8 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -48,6 +48,7 @@ struct phylink_link_state; #define DSA_TAG_PROTO_HELLCREEK_VALUE 18 #define DSA_TAG_PROTO_XRS700X_VALUE 19 #define DSA_TAG_PROTO_OCELOT_8021Q_VALUE 20 +#define DSA_TAG_PROTO_SEVILLE_VALUE 21 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -71,6 +72,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_HELLCREEK = DSA_TAG_PROTO_HELLCREEK_VALUE, DSA_TAG_PROTO_XRS700X = DSA_TAG_PROTO_XRS700X_VALUE, DSA_TAG_PROTO_OCELOT_8021Q = DSA_TAG_PROTO_OCELOT_8021Q_VALUE, + DSA_TAG_PROTO_SEVILLE = DSA_TAG_PROTO_SEVILLE_VALUE, }; struct packet_type; -- cgit v1.2.3 From 924ee317f72459a49ac4130272c7d33063e60339 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 14 Feb 2021 00:37:59 +0200 Subject: net: mscc: ocelot: refactor ocelot_xtr_irq_handler into ocelot_xtr_poll Since the felix DSA driver will need to poll the CPU port module for extracted frames as well, let's create some common functions that read an Extraction Frame Header, and then an skb, from a CPU extraction group. We abuse the struct ocelot_ops :: port_to_netdev function a little bit, in order to retrieve the DSA port net_device or the ocelot switchdev net_device based on the source port information from the Extraction Frame Header, but it's all in the benefit of code simplification - netdev_alloc_skb needs it. Originally, the port_to_netdev method was intended for parsing act->dev from tc flower offload code. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 11cae2e968b5..ded9ae1149bc 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -741,6 +741,7 @@ void __ocelot_target_write_ix(struct ocelot *ocelot, enum ocelot_target target, bool ocelot_can_inject(struct ocelot *ocelot, int grp); void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 rew_op, struct sk_buff *skb); +int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **skb); #else @@ -755,6 +756,12 @@ static inline void ocelot_port_inject_frame(struct ocelot *ocelot, int port, { } +static inline int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, + struct sk_buff **skb) +{ + return -EIO; +} + #endif /* Hardware initialization */ -- cgit v1.2.3 From 0a6f17c6ae2116809a7b7eb6dd3eab59ef5460ef Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 14 Feb 2021 00:38:01 +0200 Subject: net: dsa: tag_ocelot_8021q: add support for PTP timestamping For TX timestamping, we use the felix_txtstamp method which is common with the regular (non-8021q) ocelot tagger. This method says that skb deferral is needed, prepares a timestamp request ID, and puts a clone of the skb in a queue waiting for the timestamp IRQ. felix_txtstamp is called by dsa_skb_tx_timestamp() just before the tagger's xmit method. In the tagger xmit, we divert the packets classified by dsa_skb_tx_timestamp() as PTP towards the MMIO-based injection registers, and we declare them as dead towards dsa_slave_xmit. If not PTP, we proceed with normal tag_8021q stuff. Then the timestamp IRQ fires, the clone queued up from felix_txtstamp is matched to the TX timestamp retrieved from the switch's FIFO based on the timestamp request ID, and the clone is delivered to the stack. On RX, thanks to the VCAP IS2 rule that redirects the frames with an EtherType for 1588 towards two destinations: - the CPU port module (for MMIO based extraction) and - if the "no XTR IRQ" workaround is in place, the dsa_8021q CPU port the relevant data path processing starts in the ptp_classify_raw BPF classifier installed by DSA in the RX data path (post tagger, which is completely unaware that it saw a PTP packet). This time we can't reuse the same implementation of .port_rxtstamp that also works with the default ocelot tagger. That is because felix_rxtstamp is given an skb with a freshly stripped DSA header, and it says "I don't need deferral for its RX timestamp, it's right in it, let me show you"; and it just points to the header right behind skb->data, from where it unpacks the timestamp and annotates the skb with it. The same thing cannot happen with tag_ocelot_8021q, because for one thing, the skb did not have an extraction frame header in the first place, but a VLAN tag with no timestamp information. So the code paths in felix_rxtstamp for the regular and 8021q tagger are completely independent. With tag_8021q, the timestamp must come from the packet's duplicate delivered to the CPU port module, but there is potentially complex logic to be handled [ and prone to reordering ] if we were to just start reading packets from the CPU port module, and try to match them to the one we received over Ethernet and which needs an RX timestamp. So we do something simple: we tell DSA "give me some time to think" (we request skb deferral by returning false from .port_rxtstamp) and we just drop the frame we got over Ethernet with no attempt to match it to anything - we just treat it as a notification that there's data to be processed from the CPU port module's queues. Then we proceed to read the packets from those, one by one, which we deliver up the stack, timestamped, using netif_rx - the same function that any driver would use anyway if it needed RX timestamp deferral. So the assumption is that we'll come across the PTP packet that triggered the CPU extraction notification eventually, but we don't know when exactly. Thanks to the VCAP IS2 trap/redirect rule and the exclusion of the CPU port module from the flooding replicators, only PTP frames should be present in the CPU port module's RX queues anyway. There is just one conflict between the VCAP IS2 trapping rule and the semantics of the BPF classifier. Namely, ptp_classify_raw() deems general messages as non-timestampable, but still, those are trapped to the CPU port module since they have an EtherType of ETH_P_1588. So, if the "no XTR IRQ" workaround is in place, we need to run another BPF classifier on the frames extracted over MMIO, to avoid duplicates being sent to the stack (once over Ethernet, once over MMIO). It doesn't look like it's possible to install VCAP IS2 rules based on keys extracted from the 1588 frame headers. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index ded9ae1149bc..1f2d90976564 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -742,6 +742,7 @@ bool ocelot_can_inject(struct ocelot *ocelot, int grp); void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 rew_op, struct sk_buff *skb); int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **skb); +void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp); #else @@ -762,6 +763,10 @@ static inline int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, return -EIO; } +static inline void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp) +{ +} + #endif /* Hardware initialization */ -- cgit v1.2.3 From dcbdf1350e3312c199dbc6a76f41cf8f67e8c09c Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 13 Feb 2021 22:43:17 +0200 Subject: net: bridge: propagate extack through switchdev_port_attr_set The benefit is the ability to propagate errors from switchdev drivers for the SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING and SWITCHDEV_ATTR_ID_BRIDGE_VLAN_PROTOCOL attributes. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/net/switchdev.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 25d9e4570934..195f62672cc4 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -247,7 +247,8 @@ switchdev_notifier_info_to_extack(const struct switchdev_notifier_info *info) void switchdev_deferred_process(void); int switchdev_port_attr_set(struct net_device *dev, - const struct switchdev_attr *attr); + const struct switchdev_attr *attr, + struct netlink_ext_ack *extack); int switchdev_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj, struct netlink_ext_ack *extack); -- cgit v1.2.3 From 31046a5fd92c57d99e8861f3dc56a2584787b473 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 13 Feb 2021 22:43:18 +0200 Subject: net: dsa: propagate extack to .port_vlan_add Allow drivers to communicate their restrictions to user space directly, instead of printing to the kernel log. Where the conversion would have been lossy and things like VLAN ID could no longer be conveyed (due to the lack of support for printf format specifier in netlink extack), I chose to keep the messages in full form to the kernel log only, and leave it up to individual driver maintainers to move more messages to extack. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/net/dsa.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index b095ef114fe8..01bd154798c5 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -643,7 +643,8 @@ struct dsa_switch_ops { int (*port_vlan_filtering)(struct dsa_switch *ds, int port, bool vlan_filtering); int (*port_vlan_add)(struct dsa_switch *ds, int port, - const struct switchdev_obj_port_vlan *vlan); + const struct switchdev_obj_port_vlan *vlan, + struct netlink_ext_ack *extack); int (*port_vlan_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); /* -- cgit v1.2.3 From 89153ed6ebc14879b04686f0e3f3066b1b6bef05 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 13 Feb 2021 22:43:19 +0200 Subject: net: dsa: propagate extack to .port_vlan_filtering Some drivers can't dynamically change the VLAN filtering option, or impose some restrictions, it would be nice to propagate this info through netlink instead of printing it to a kernel log that might never be read. Also netlink extack includes the module that emitted the message, which means that it's easier to figure out which ones are driver-generated errors as opposed to command misuse. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/net/dsa.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 01bd154798c5..68f8159564a3 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -641,7 +641,8 @@ struct dsa_switch_ops { * VLAN support */ int (*port_vlan_filtering)(struct dsa_switch *ds, int port, - bool vlan_filtering); + bool vlan_filtering, + struct netlink_ext_ack *extack); int (*port_vlan_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, struct netlink_ext_ack *extack); -- cgit v1.2.3 From 6001a930ce0378b62210d4f83583fc88a903d89d Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 15 Feb 2021 12:28:07 +0100 Subject: netfilter: nftables: introduce table ownership A userspace daemon like firewalld might need to monitor for netlink updates to detect its ruleset removal by the (global) flush ruleset command to ensure ruleset persistency. This adds extra complexity from userspace and, for some little time, the firewall policy is not in place. This patch adds the NFT_TABLE_F_OWNER flag which allows a userspace program to own the table that creates in exclusivity. Tables that are owned... - can only be updated and removed by the owner, non-owners hit EPERM if they try to update it or remove it. - are destroyed when the owner closes the netlink socket or the process is gone (implicit netlink socket closure). - are skipped by the global flush ruleset command. - are listed in the global ruleset. The userspace process that sets on the NFT_TABLE_F_OWNER flag need to leave open the netlink socket. A new NFTA_TABLE_OWNER netlink attribute specifies the netlink port ID to identify the owner from userspace. This patch also updates error reporting when an unknown table flag is specified to change it from EINVAL to EOPNOTSUPP given that EINVAL is usually reserved to report for malformed netlink messages to userspace. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 6 ++++++ include/uapi/linux/netfilter/nf_tables.h | 5 +++++ 2 files changed, 11 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 80bc2e8282ae..fdec57d862b7 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1106,11 +1106,17 @@ struct nft_table { u16 family:6, flags:8, genmask:2; + u32 nlpid; char *name; u16 udlen; u8 *udata; }; +static inline bool nft_table_has_owner(const struct nft_table *table) +{ + return table->flags & NFT_TABLE_F_OWNER; +} + static inline bool nft_base_chain_netdev(int family, u32 hooknum) { return family == NFPROTO_NETDEV || diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index b1633e7ba529..79bab7a36b30 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -164,7 +164,10 @@ enum nft_hook_attributes { */ enum nft_table_flags { NFT_TABLE_F_DORMANT = 0x1, + NFT_TABLE_F_OWNER = 0x2, }; +#define NFT_TABLE_F_MASK (NFT_TABLE_F_DORMANT | \ + NFT_TABLE_F_OWNER) /** * enum nft_table_attributes - nf_tables table netlink attributes @@ -173,6 +176,7 @@ enum nft_table_flags { * @NFTA_TABLE_FLAGS: bitmask of enum nft_table_flags (NLA_U32) * @NFTA_TABLE_USE: number of chains in this table (NLA_U32) * @NFTA_TABLE_USERDATA: user data (NLA_BINARY) + * @NFTA_TABLE_OWNER: owner of this table through netlink portID (NLA_U32) */ enum nft_table_attributes { NFTA_TABLE_UNSPEC, @@ -182,6 +186,7 @@ enum nft_table_attributes { NFTA_TABLE_HANDLE, NFTA_TABLE_PAD, NFTA_TABLE_USERDATA, + NFTA_TABLE_OWNER, __NFTA_TABLE_MAX }; #define NFTA_TABLE_MAX (__NFTA_TABLE_MAX - 1) -- cgit v1.2.3 From d0a0bbe7b0a181c58bd22d6942146cfa3ab9e49a Mon Sep 17 00:00:00 2001 From: Tong Zhang Date: Sun, 14 Feb 2021 18:43:08 -0500 Subject: atm: idt77252: fix build broken on amd64 idt77252 is broken and wont load on amd64 systems modprobe idt77252 shows the following idt77252_init: skb->cb is too small (48 < 56) Add packed attribute to struct idt77252_skb_prv and struct atm_skb_data so that the total size can be <= sizeof(skb->cb) Also convert runtime size check to buildtime size check in idt77252_init() Signed-off-by: Tong Zhang Signed-off-by: David S. Miller --- include/linux/atmdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h index d7493016cd46..60cd25c0461b 100644 --- a/include/linux/atmdev.h +++ b/include/linux/atmdev.h @@ -207,7 +207,7 @@ struct atm_skb_data { struct atm_vcc *vcc; /* ATM VCC */ unsigned long atm_options; /* ATM layer options */ unsigned int acct_truesize; /* truesize accounted to vcc */ -}; +} __packed; #define VCC_HTABLE_SIZE 32 -- cgit v1.2.3 From 419dfaed7ccc9533b3f4d88eb6f4997b41f8a4fc Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 15 Feb 2021 23:09:11 +0200 Subject: net: bridge: fix switchdev_port_attr_set stub when CONFIG_SWITCHDEV=n The switchdev_port_attr_set function prototype was updated only for the case where CONFIG_SWITCHDEV=y|m, leaving a prototype mismatch with the stub definition for the disabled case. This results in a build error, so update that function too. Fixes: dcbdf1350e33 ("net: bridge: propagate extack through switchdev_port_attr_set") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/net/switchdev.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 195f62672cc4..9a5426b61ca5 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -296,7 +296,8 @@ static inline void switchdev_deferred_process(void) } static inline int switchdev_port_attr_set(struct net_device *dev, - const struct switchdev_attr *attr) + const struct switchdev_attr *attr, + struct netlink_ext_ack *extack) { return -EOPNOTSUPP; } -- cgit v1.2.3 From 0caf3ada24e4623d4b2c938a5b6d2d09e4ccee18 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Fri, 12 Feb 2021 16:52:02 -0800 Subject: mptcp: add local addr info in mptcp_info Add mptcpi_local_addr_used and mptcpi_local_addr_max in struct mptcp_info. Signed-off-by: Geliang Tang Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/uapi/linux/mptcp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index c91578aaab32..e1172c1ffdfd 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -103,6 +103,8 @@ struct mptcp_info { __u64 mptcpi_write_seq; __u64 mptcpi_snd_una; __u64 mptcpi_rcv_nxt; + __u8 mptcpi_local_addr_used; + __u8 mptcpi_local_addr_max; }; /* -- cgit v1.2.3 From 17d3a83afbbff34209d6c3636718fc1abe305ef8 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 12 Feb 2021 19:46:31 -0800 Subject: net: phy: broadcom: Remove unused flags We have a number of unused flags defined today and since we are scarce on space and may need to introduce new flags in the future remove and shift every existing flag down into a contiguous assignment. PHY_BCM_FLAGS_MODE_1000BX was only used internally for the BCM54616S PHY, so we allocate a driver private structure instead to store that flag instead of canibalizing one from phydev->dev_flags for that purpose. Signed-off-by: Florian Fainelli Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 21 ++++++++------------- 1 file changed, 8 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index de9430d55c90..844dcfe789a2 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -61,19 +61,14 @@ #define PHY_BCM_OUI_5 0x03625e00 #define PHY_BCM_OUI_6 0xae025000 -#define PHY_BCM_FLAGS_MODE_COPPER 0x00000001 -#define PHY_BCM_FLAGS_MODE_1000BX 0x00000002 -#define PHY_BCM_FLAGS_INTF_SGMII 0x00000010 -#define PHY_BCM_FLAGS_INTF_XAUI 0x00000020 -#define PHY_BRCM_WIRESPEED_ENABLE 0x00000100 -#define PHY_BRCM_AUTO_PWRDWN_ENABLE 0x00000200 -#define PHY_BRCM_RX_REFCLK_UNUSED 0x00000400 -#define PHY_BRCM_STD_IBND_DISABLE 0x00000800 -#define PHY_BRCM_EXT_IBND_RX_ENABLE 0x00001000 -#define PHY_BRCM_EXT_IBND_TX_ENABLE 0x00002000 -#define PHY_BRCM_CLEAR_RGMII_MODE 0x00004000 -#define PHY_BRCM_DIS_TXCRXC_NOENRGY 0x00008000 -#define PHY_BRCM_EN_MASTER_MODE 0x00010000 +#define PHY_BRCM_AUTO_PWRDWN_ENABLE 0x00000001 +#define PHY_BRCM_RX_REFCLK_UNUSED 0x00000002 +#define PHY_BRCM_STD_IBND_DISABLE 0x00000004 +#define PHY_BRCM_EXT_IBND_RX_ENABLE 0x00000008 +#define PHY_BRCM_EXT_IBND_TX_ENABLE 0x00000010 +#define PHY_BRCM_CLEAR_RGMII_MODE 0x00000020 +#define PHY_BRCM_DIS_TXCRXC_NOENRGY 0x00000040 +#define PHY_BRCM_EN_MASTER_MODE 0x00000080 /* Broadcom BCM7xxx specific workarounds */ #define PHY_BRCM_7XXX_REV(x) (((x) >> 8) & 0xff) -- cgit v1.2.3 From 5d4358ede8ebe2e4ae03a633082f3ce21ec2df3e Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 12 Feb 2021 19:46:32 -0800 Subject: net: phy: broadcom: Allow BCM54210E to configure APD BCM54210E/BCM50212E has been verified to work correctly with the auto-power down configuration done by bcm54xx_adjust_rxrefclk(), add it to the list of PHYs working. While we are at it, provide an appropriate name for the bit we are changing which disables the RXC and TXC during auto-power down when there is no energy on the cable. Signed-off-by: Florian Fainelli Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 844dcfe789a2..16597d3fa011 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -193,6 +193,7 @@ #define BCM54XX_SHD_SCR3_DEF_CLK125 0x0001 #define BCM54XX_SHD_SCR3_DLLAPD_DIS 0x0002 #define BCM54XX_SHD_SCR3_TRDDAPD 0x0004 +#define BCM54XX_SHD_SCR3_RXCTXC_DIS 0x0100 /* 01010: Auto Power-Down */ #define BCM54XX_SHD_APD 0x0a @@ -253,7 +254,6 @@ #define BCM54810_EXP_BROADREACH_LRE_MISC_CTL_EN (1 << 0) #define BCM54810_SHD_CLK_CTL 0x3 #define BCM54810_SHD_CLK_CTL_GTXCLK_EN (1 << 9) -#define BCM54810_SHD_SCR3_TRDDAPD 0x0100 /* BCM54612E Registers */ #define BCM54612E_EXP_SPARE0 (MII_BCM54XX_EXP_SEL_ETC + 0x34) -- cgit v1.2.3 From 93e8990c24bee30696c02e8f6aed043333491a25 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sun, 14 Feb 2021 15:16:23 +0100 Subject: net: phy: rename PHY_IGNORE_INTERRUPT to PHY_MAC_INTERRUPT Some internal PHY's have their events like link change reported by the MAC interrupt. We have PHY_IGNORE_INTERRUPT to deal with this scenario. I'm not too happy with this name. We don't ignore interrupts, typically there is no interrupt exposed at a PHY level. So let's rename it to PHY_MAC_INTERRUPT. This is in line with phy_mac_interrupt(), which is called from the MAC interrupt handler to handle PHY events. Signed-off-by: Heiner Kallweit Reviewed-by: Andrew Lunn Acked-by: Florian Fainelli Reviewed-by: Russell King Signed-off-by: David S. Miller --- include/linux/phy.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index c130788306c8..5d7c4084ade9 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -71,11 +71,11 @@ extern const int phy_10gbit_features_array[1]; /* * Set phydev->irq to PHY_POLL if interrupts are not supported, - * or not desired for this PHY. Set to PHY_IGNORE_INTERRUPT if - * the attached driver handles the interrupt + * or not desired for this PHY. Set to PHY_MAC_INTERRUPT if + * the attached MAC driver handles the interrupt */ #define PHY_POLL -1 -#define PHY_IGNORE_INTERRUPT -2 +#define PHY_MAC_INTERRUPT -2 #define PHY_IS_INTERNAL 0x00000001 #define PHY_RST_AFTER_CLK_EN 0x00000002 @@ -1202,11 +1202,11 @@ static inline int phy_clear_bits_mmd(struct phy_device *phydev, int devad, * @phydev: the phy_device struct * * NOTE: must be kept in sync with addition/removal of PHY_POLL and - * PHY_IGNORE_INTERRUPT + * PHY_MAC_INTERRUPT */ static inline bool phy_interrupt_is_valid(struct phy_device *phydev) { - return phydev->irq != PHY_POLL && phydev->irq != PHY_IGNORE_INTERRUPT; + return phydev->irq != PHY_POLL && phydev->irq != PHY_MAC_INTERRUPT; } /** -- cgit v1.2.3 From a6a217dddcd544f6b75f0e2a60b6e84c1d494b7e Mon Sep 17 00:00:00 2001 From: Aharon Landau Date: Tue, 9 Feb 2021 15:11:06 +0200 Subject: net/mlx5: Add new timestamp mode bits These fields declare which timestamp mode is supported by the device per RQ/SQ/QP. In addition add the ts_format field to the select the mode for RQ/SQ/QP. Link: https://lore.kernel.org/r/20210209131107.698833-2-leon@kernel.org Signed-off-by: Aharon Landau Signed-off-by: Maor Gottlieb Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 54 +++++++++++++++++++++++++++++++++++++++---- 1 file changed, 49 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index cf692fc17f41..436d6f421dfd 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -932,11 +932,18 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 reserved_at_200[0x600]; }; +enum { + MLX5_QP_TIMESTAMP_FORMAT_CAP_FREE_RUNNING = 0x0, + MLX5_QP_TIMESTAMP_FORMAT_CAP_REAL_TIME = 0x1, + MLX5_QP_TIMESTAMP_FORMAT_CAP_FREE_RUNNING_AND_REAL_TIME = 0x2, +}; + struct mlx5_ifc_roce_cap_bits { u8 roce_apm[0x1]; u8 reserved_at_1[0x3]; u8 sw_r_roce_src_udp_port[0x1]; - u8 reserved_at_5[0x1b]; + u8 reserved_at_5[0x19]; + u8 qp_ts_format[0x2]; u8 reserved_at_20[0x60]; @@ -1253,6 +1260,18 @@ enum { MLX5_STEERING_FORMAT_CONNECTX_6DX = 1, }; +enum { + MLX5_SQ_TIMESTAMP_FORMAT_CAP_FREE_RUNNING = 0x0, + MLX5_SQ_TIMESTAMP_FORMAT_CAP_REAL_TIME = 0x1, + MLX5_SQ_TIMESTAMP_FORMAT_CAP_FREE_RUNNING_AND_REAL_TIME = 0x2, +}; + +enum { + MLX5_RQ_TIMESTAMP_FORMAT_CAP_FREE_RUNNING = 0x0, + MLX5_RQ_TIMESTAMP_FORMAT_CAP_REAL_TIME = 0x1, + MLX5_RQ_TIMESTAMP_FORMAT_CAP_FREE_RUNNING_AND_REAL_TIME = 0x2, +}; + struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_0[0x1f]; u8 vhca_resource_manager[0x1]; @@ -1564,7 +1583,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 general_obj_types[0x40]; - u8 reserved_at_440[0x4]; + u8 sq_ts_format[0x2]; + u8 rq_ts_format[0x2]; u8 steering_format_version[0x4]; u8 create_qp_start_hint[0x18]; @@ -2868,6 +2888,12 @@ enum { MLX5_QPC_CS_RES_UP_TO_64B = 0x2, }; +enum { + MLX5_QPC_TIMESTAMP_FORMAT_FREE_RUNNING = 0x0, + MLX5_QPC_TIMESTAMP_FORMAT_DEFAULT = 0x1, + MLX5_QPC_TIMESTAMP_FORMAT_REAL_TIME = 0x2, +}; + struct mlx5_ifc_qpc_bits { u8 state[0x4]; u8 lag_tx_port_affinity[0x4]; @@ -2896,7 +2922,9 @@ struct mlx5_ifc_qpc_bits { u8 log_rq_stride[0x3]; u8 no_sq[0x1]; u8 log_sq_size[0x4]; - u8 reserved_at_55[0x6]; + u8 reserved_at_55[0x3]; + u8 ts_format[0x2]; + u8 reserved_at_5a[0x1]; u8 rlky[0x1]; u8 ulp_stateless_offload_mode[0x4]; @@ -3312,6 +3340,12 @@ enum { MLX5_SQC_STATE_ERR = 0x3, }; +enum { + MLX5_SQC_TIMESTAMP_FORMAT_FREE_RUNNING = 0x0, + MLX5_SQC_TIMESTAMP_FORMAT_DEFAULT = 0x1, + MLX5_SQC_TIMESTAMP_FORMAT_REAL_TIME = 0x2, +}; + struct mlx5_ifc_sqc_bits { u8 rlky[0x1]; u8 cd_master[0x1]; @@ -3323,7 +3357,9 @@ struct mlx5_ifc_sqc_bits { u8 reg_umr[0x1]; u8 allow_swp[0x1]; u8 hairpin[0x1]; - u8 reserved_at_f[0x11]; + u8 reserved_at_f[0xb]; + u8 ts_format[0x2]; + u8 reserved_at_1c[0x4]; u8 reserved_at_20[0x8]; u8 user_index[0x18]; @@ -3414,6 +3450,12 @@ enum { MLX5_RQC_STATE_ERR = 0x3, }; +enum { + MLX5_RQC_TIMESTAMP_FORMAT_FREE_RUNNING = 0x0, + MLX5_RQC_TIMESTAMP_FORMAT_DEFAULT = 0x1, + MLX5_RQC_TIMESTAMP_FORMAT_REAL_TIME = 0x2, +}; + struct mlx5_ifc_rqc_bits { u8 rlky[0x1]; u8 delay_drop_en[0x1]; @@ -3424,7 +3466,9 @@ struct mlx5_ifc_rqc_bits { u8 reserved_at_c[0x1]; u8 flush_in_error_en[0x1]; u8 hairpin[0x1]; - u8 reserved_at_f[0x11]; + u8 reserved_at_f[0xb]; + u8 ts_format[0x2]; + u8 reserved_at_1c[0x4]; u8 reserved_at_20[0x8]; u8 user_index[0x18]; -- cgit v1.2.3 From ae02d41551d6f2a035d3e63ce4415e1b2ba3a7e6 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Fri, 12 Feb 2021 14:30:38 -0800 Subject: net/mlx5: Add register layout to support real-time time-stamp Add needed structure layouts and defines for MTUTC (Management UTC) register. MTUTC will be used for cyc2time HW translation. In addition, add cyc2time modify capability bit and init segment HCA real time address. Finally, add capability bits indicating which time-stamping format is supported per SQ and RQ. Add ts_format in the queue's context layout to allow configuration. Signed-off-by: Eran Ben Elisha Signed-off-by: Aya Levin Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 5 ++++- include/linux/mlx5/driver.h | 1 + include/linux/mlx5/mlx5_ifc.h | 30 ++++++++++++++++++++++++++++-- 3 files changed, 33 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index f1de49d64a98..fd694add6ff0 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -578,7 +578,10 @@ struct mlx5_init_seg { __be32 internal_timer_l; __be32 rsvd3[2]; __be32 health_counter; - __be32 rsvd4[1019]; + __be32 rsvd4[11]; + __be32 real_time_h; + __be32 real_time_l; + __be32 rsvd5[1006]; __be64 ieee1588_clk; __be32 ieee1588_clk_type; __be32 clr_intx; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f93bfe7473aa..2eb7755143d7 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -143,6 +143,7 @@ enum { MLX5_REG_MPCNT = 0x9051, MLX5_REG_MTPPS = 0x9053, MLX5_REG_MTPPSE = 0x9054, + MLX5_REG_MTUTC = 0x9055, MLX5_REG_MPEGC = 0x9056, MLX5_REG_MCQS = 0x9060, MLX5_REG_MCQI = 0x9061, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 436d6f421dfd..7059fcdf54a3 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -9150,6 +9150,28 @@ struct mlx5_ifc_mpegc_reg_bits { u8 reserved_at_60[0x100]; }; +enum { + MLX5_MTUTC_OPERATION_SET_TIME_IMMEDIATE = 0x1, + MLX5_MTUTC_OPERATION_ADJUST_TIME = 0x2, + MLX5_MTUTC_OPERATION_ADJUST_FREQ_UTC = 0x3, +}; + +struct mlx5_ifc_mtutc_reg_bits { + u8 reserved_at_0[0x1c]; + u8 operation[0x4]; + + u8 freq_adjustment[0x20]; + + u8 reserved_at_40[0x40]; + + u8 utc_sec[0x20]; + + u8 reserved_at_a0[0x2]; + u8 utc_nsec[0x1e]; + + u8 time_adjustment[0x20]; +}; + struct mlx5_ifc_pcam_enhanced_features_bits { u8 reserved_at_0[0x68]; u8 fec_50G_per_lane_in_pplm[0x1]; @@ -9208,7 +9230,9 @@ struct mlx5_ifc_pcam_reg_bits { }; struct mlx5_ifc_mcam_enhanced_features_bits { - u8 reserved_at_0[0x6e]; + u8 reserved_at_0[0x6b]; + u8 ptpcyc2realtime_modify[0x1]; + u8 reserved_at_6c[0x2]; u8 pci_status_and_power[0x1]; u8 reserved_at_6f[0x5]; u8 mark_tx_action_cnp[0x1]; @@ -9231,7 +9255,8 @@ struct mlx5_ifc_mcam_access_reg_bits { u8 regs_95_to_87[0x9]; u8 mpegc[0x1]; - u8 regs_85_to_68[0x12]; + u8 mtutc[0x1]; + u8 regs_84_to_68[0x11]; u8 tracer_registers[0x4]; u8 regs_63_to_32[0x20]; @@ -9964,6 +9989,7 @@ union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_mcda_reg_bits mcda_reg; struct mlx5_ifc_mirc_reg_bits mirc_reg; struct mlx5_ifc_mfrl_reg_bits mfrl_reg; + struct mlx5_ifc_mtutc_reg_bits mtutc_reg; u8 reserved_at_0[0x60e0]; }; -- cgit v1.2.3 From d6f3dc8f509ce6288e2537eb4b0614ef444fd84a Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Fri, 12 Feb 2021 14:30:40 -0800 Subject: net/mlx5: Move all internal timer metadata into a dedicated struct Internal timer mode (SW clock) requires some PTP clock related metadata structs. Real time mode (HW clock) will not need these metadata structs. This separation emphasize the different interfaces for HW clock and SW clock. Signed-off-by: Eran Ben Elisha Signed-off-by: Aya Levin Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 2eb7755143d7..2f4d6182df1b 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -662,18 +662,22 @@ struct mlx5_pps { u8 enabled; }; -struct mlx5_clock { - struct mlx5_nb pps_nb; - seqlock_t lock; +struct mlx5_timer { struct cyclecounter cycles; struct timecounter tc; - struct hwtstamp_config hwtstamp_config; u32 nominal_c_mult; unsigned long overflow_period; struct delayed_work overflow_work; +}; + +struct mlx5_clock { + struct mlx5_nb pps_nb; + seqlock_t lock; + struct hwtstamp_config hwtstamp_config; struct ptp_clock *ptp; struct ptp_clock_info ptp_info; struct mlx5_pps pps_info; + struct mlx5_timer timer; }; struct mlx5_dm; -- cgit v1.2.3 From 32aeba1f7a98b0c69d4a5704a7d9cea42ba856ba Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 16 Feb 2021 11:08:37 -0800 Subject: tg3: Remove unused PHY_BRCM flags The tg3 driver tried to communicate towards the PHY driver whether it wanted RGMII in-band signaling enabled or disabled however there is nothing that looks at those flags in drivers/net/phy/broadcom.c so this does do not anything. Suggested-by: Vladimir Oltean Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 16597d3fa011..8fe1d55371ac 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -63,12 +63,9 @@ #define PHY_BRCM_AUTO_PWRDWN_ENABLE 0x00000001 #define PHY_BRCM_RX_REFCLK_UNUSED 0x00000002 -#define PHY_BRCM_STD_IBND_DISABLE 0x00000004 -#define PHY_BRCM_EXT_IBND_RX_ENABLE 0x00000008 -#define PHY_BRCM_EXT_IBND_TX_ENABLE 0x00000010 -#define PHY_BRCM_CLEAR_RGMII_MODE 0x00000020 -#define PHY_BRCM_DIS_TXCRXC_NOENRGY 0x00000040 -#define PHY_BRCM_EN_MASTER_MODE 0x00000080 +#define PHY_BRCM_CLEAR_RGMII_MODE 0x00000004 +#define PHY_BRCM_DIS_TXCRXC_NOENRGY 0x00000008 +#define PHY_BRCM_EN_MASTER_MODE 0x00000010 /* Broadcom BCM7xxx specific workarounds */ #define PHY_BRCM_7XXX_REV(x) (((x) >> 8) & 0xff) -- cgit v1.2.3 From 7331d1d4622ba7e668ec19cfba2ed7feb4a3084e Mon Sep 17 00:00:00 2001 From: Pavana Sharma Date: Tue, 16 Feb 2021 20:20:53 +0100 Subject: net: phy: Add 5GBASER interface mode MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add 5GBASE-R phy interface mode Signed-off-by: Pavana Sharma Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: Marek Behún Signed-off-by: David S. Miller --- include/linux/phy.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index 5d7c4084ade9..0d537f59b77f 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -107,6 +107,7 @@ extern const int phy_10gbit_features_array[1]; * @PHY_INTERFACE_MODE_100BASEX: 100 BaseX * @PHY_INTERFACE_MODE_1000BASEX: 1000 BaseX * @PHY_INTERFACE_MODE_2500BASEX: 2500 BaseX + * @PHY_INTERFACE_MODE_5GBASER: 5G BaseR * @PHY_INTERFACE_MODE_RXAUI: Reduced XAUI * @PHY_INTERFACE_MODE_XAUI: 10 Gigabit Attachment Unit Interface * @PHY_INTERFACE_MODE_10GBASER: 10G BaseR @@ -139,6 +140,7 @@ typedef enum { PHY_INTERFACE_MODE_100BASEX, PHY_INTERFACE_MODE_1000BASEX, PHY_INTERFACE_MODE_2500BASEX, + PHY_INTERFACE_MODE_5GBASER, PHY_INTERFACE_MODE_RXAUI, PHY_INTERFACE_MODE_XAUI, /* 10GBASE-R, XFI, SFI - single lane 10G Serdes */ @@ -209,6 +211,8 @@ static inline const char *phy_modes(phy_interface_t interface) return "1000base-x"; case PHY_INTERFACE_MODE_2500BASEX: return "2500base-x"; + case PHY_INTERFACE_MODE_5GBASER: + return "5gbase-r"; case PHY_INTERFACE_MODE_RXAUI: return "rxaui"; case PHY_INTERFACE_MODE_XAUI: -- cgit v1.2.3 From 405be6b46b707590f8014d468f4b42f25c6064cb Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Tue, 16 Feb 2021 22:41:58 +0100 Subject: switchdev: mrp: Remove CONFIG_BRIDGE_MRP Remove #IS_ENABLED(CONFIG_BRIDGE_MRP) from switchdev.h. This will simplify the code implements MRP callbacks and will be similar with the vlan filtering. Signed-off-by: Horatiu Vultur Signed-off-by: David S. Miller --- include/net/switchdev.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 9a5426b61ca5..465362d9d063 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -27,9 +27,7 @@ enum switchdev_attr_id { SWITCHDEV_ATTR_ID_BRIDGE_VLAN_PROTOCOL, SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED, SWITCHDEV_ATTR_ID_BRIDGE_MROUTER, -#if IS_ENABLED(CONFIG_BRIDGE_MRP) SWITCHDEV_ATTR_ID_MRP_PORT_ROLE, -#endif }; struct switchdev_brport_flags { @@ -51,9 +49,7 @@ struct switchdev_attr { bool vlan_filtering; /* BRIDGE_VLAN_FILTERING */ u16 vlan_protocol; /* BRIDGE_VLAN_PROTOCOL */ bool mc_disabled; /* MC_DISABLED */ -#if IS_ENABLED(CONFIG_BRIDGE_MRP) u8 mrp_port_role; /* MRP_PORT_ROLE */ -#endif } u; }; @@ -62,7 +58,6 @@ enum switchdev_obj_id { SWITCHDEV_OBJ_ID_PORT_VLAN, SWITCHDEV_OBJ_ID_PORT_MDB, SWITCHDEV_OBJ_ID_HOST_MDB, -#if IS_ENABLED(CONFIG_BRIDGE_MRP) SWITCHDEV_OBJ_ID_MRP, SWITCHDEV_OBJ_ID_RING_TEST_MRP, SWITCHDEV_OBJ_ID_RING_ROLE_MRP, @@ -70,8 +65,6 @@ enum switchdev_obj_id { SWITCHDEV_OBJ_ID_IN_TEST_MRP, SWITCHDEV_OBJ_ID_IN_ROLE_MRP, SWITCHDEV_OBJ_ID_IN_STATE_MRP, - -#endif }; struct switchdev_obj { @@ -103,7 +96,6 @@ struct switchdev_obj_port_mdb { container_of((OBJ), struct switchdev_obj_port_mdb, obj) -#if IS_ENABLED(CONFIG_BRIDGE_MRP) /* SWITCHDEV_OBJ_ID_MRP */ struct switchdev_obj_mrp { struct switchdev_obj obj; @@ -183,8 +175,6 @@ struct switchdev_obj_in_state_mrp { #define SWITCHDEV_OBJ_IN_STATE_MRP(OBJ) \ container_of((OBJ), struct switchdev_obj_in_state_mrp, obj) -#endif - typedef int switchdev_obj_dump_cb_t(struct switchdev_obj *obj); enum switchdev_notifier_type { -- cgit v1.2.3 From c513efa20c5254ef74c4157a03d515abdc46c503 Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Tue, 16 Feb 2021 22:41:59 +0100 Subject: switchdev: mrp: Extend ring_role_mrp and in_role_mrp Add the member sw_backup to the structures switchdev_obj_ring_role_mrp and switchdev_obj_in_role_mrp. In this way the SW can call the driver in 2 ways, once when sw_backup is set to false, meaning that the driver should implement this completely in HW. And if that is not supported the SW will call again but with sw_backup set to true, meaning that the HW should help or allow the SW to run the protocol. For example when role is MRM, if the HW can't detect when it stops receiving MRP Test frames but it can trap these frames to CPU, then it needs to return -EOPNOTSUPP when sw_backup is false and return 0 when sw_backup is true. Signed-off-by: Horatiu Vultur Signed-off-by: David S. Miller --- include/net/switchdev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 465362d9d063..b7fc7d0f54e2 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -127,6 +127,7 @@ struct switchdev_obj_ring_role_mrp { struct switchdev_obj obj; u8 ring_role; u32 ring_id; + u8 sw_backup; }; #define SWITCHDEV_OBJ_RING_ROLE_MRP(OBJ) \ @@ -161,6 +162,7 @@ struct switchdev_obj_in_role_mrp { u32 ring_id; u16 in_id; u8 in_role; + u8 sw_backup; }; #define SWITCHDEV_OBJ_IN_ROLE_MRP(OBJ) \ -- cgit v1.2.3 From d8ea7ff3995ead5193313c72c0d97c9c16c83be9 Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Tue, 16 Feb 2021 22:42:03 +0100 Subject: net: mscc: ocelot: Add support for MRP Add basic support for MRP. The HW will just trap all MRP frames on the ring ports to CPU and allow the SW to process them. In this way it is possible to for this node to behave both as MRM and MRC. Current limitations are: - it doesn't support Interconnect roles. - it supports only a single ring. - the HW should be able to do forwarding of MRP Test frames so the SW will not need to do this. So it would be able to have the role MRC without SW support. Signed-off-by: Horatiu Vultur Signed-off-by: David S. Miller --- include/linux/dsa/ocelot.h | 5 +++++ include/soc/mscc/ocelot.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 50 insertions(+) (limited to 'include') diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h index c6bc45ae5e03..4265f328681a 100644 --- a/include/linux/dsa/ocelot.h +++ b/include/linux/dsa/ocelot.h @@ -160,6 +160,11 @@ static inline void ocelot_xfh_get_src_port(void *extraction, u64 *src_port) packing(extraction, src_port, 46, 43, OCELOT_TAG_LEN, UNPACK, 0); } +static inline void ocelot_xfh_get_cpuq(void *extraction, u64 *cpuq) +{ + packing(extraction, cpuq, 28, 20, OCELOT_TAG_LEN, UNPACK, 0); +} + static inline void ocelot_xfh_get_qos_class(void *extraction, u64 *qos_class) { packing(extraction, qos_class, 19, 17, OCELOT_TAG_LEN, UNPACK, 0); diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 1f2d90976564..425ff29d9389 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -112,6 +112,8 @@ #define REG_RESERVED_ADDR 0xffffffff #define REG_RESERVED(reg) REG(reg, REG_RESERVED_ADDR) +#define OCELOT_MRP_CPUQ 7 + enum ocelot_target { ANA = 1, QS, @@ -677,6 +679,12 @@ struct ocelot { /* Protects the PTP clock */ spinlock_t ptp_clock_lock; struct ptp_pin_desc ptp_pins[OCELOT_PTP_PINS_NUM]; + +#if IS_ENABLED(CONFIG_BRIDGE_MRP) + u16 mrp_ring_id; + struct net_device *mrp_p_port; + struct net_device *mrp_s_port; +#endif }; struct ocelot_policer { @@ -874,4 +882,41 @@ int ocelot_sb_occ_tc_port_bind_get(struct ocelot *ocelot, int port, enum devlink_sb_pool_type pool_type, u32 *p_cur, u32 *p_max); +#if IS_ENABLED(CONFIG_BRIDGE_MRP) +int ocelot_mrp_add(struct ocelot *ocelot, int port, + const struct switchdev_obj_mrp *mrp); +int ocelot_mrp_del(struct ocelot *ocelot, int port, + const struct switchdev_obj_mrp *mrp); +int ocelot_mrp_add_ring_role(struct ocelot *ocelot, int port, + const struct switchdev_obj_ring_role_mrp *mrp); +int ocelot_mrp_del_ring_role(struct ocelot *ocelot, int port, + const struct switchdev_obj_ring_role_mrp *mrp); +#else +static inline int ocelot_mrp_add(struct ocelot *ocelot, int port, + const struct switchdev_obj_mrp *mrp) +{ + return -EOPNOTSUPP; +} + +static inline int ocelot_mrp_del(struct ocelot *ocelot, int port, + const struct switchdev_obj_mrp *mrp) +{ + return -EOPNOTSUPP; +} + +static inline int +ocelot_mrp_add_ring_role(struct ocelot *ocelot, int port, + const struct switchdev_obj_ring_role_mrp *mrp) +{ + return -EOPNOTSUPP; +} + +static inline int +ocelot_mrp_del_ring_role(struct ocelot *ocelot, int port, + const struct switchdev_obj_ring_role_mrp *mrp) +{ + return -EOPNOTSUPP; +} +#endif + #endif -- cgit v1.2.3 From c595c4330da06fff716337239a8d5e528341a502 Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Tue, 16 Feb 2021 22:42:04 +0100 Subject: net: dsa: add MRP support Add support for offloading MRP in HW. Currently implement the switchdev calls 'SWITCHDEV_OBJ_ID_MRP', 'SWITCHDEV_OBJ_ID_RING_ROLE_MRP', to allow to create MRP instances and to set the role of these instances. Add DSA_NOTIFIER_MRP_ADD/DEL and DSA_NOTIFIER_MRP_ADD/DEL_RING_ROLE which calls to .port_mrp_add/del and .port_mrp_add/del_ring_role in the DSA driver for the switch. Signed-off-by: Horatiu Vultur Signed-off-by: David S. Miller --- include/net/dsa.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 68f8159564a3..83a933e563fe 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -792,6 +792,18 @@ struct dsa_switch_ops { struct net_device *hsr); int (*port_hsr_leave)(struct dsa_switch *ds, int port, struct net_device *hsr); + + /* + * MRP integration + */ + int (*port_mrp_add)(struct dsa_switch *ds, int port, + const struct switchdev_obj_mrp *mrp); + int (*port_mrp_del)(struct dsa_switch *ds, int port, + const struct switchdev_obj_mrp *mrp); + int (*port_mrp_add_ring_role)(struct dsa_switch *ds, int port, + const struct switchdev_obj_ring_role_mrp *mrp); + int (*port_mrp_del_ring_role)(struct dsa_switch *ds, int port, + const struct switchdev_obj_ring_role_mrp *mrp); }; #define DSA_DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes) \ -- cgit v1.2.3 From 396d7f23adf9e8c436dd81a69488b5b6a865acf8 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Tue, 16 Feb 2021 18:22:00 +0200 Subject: net: sched: fix police ext initialization When police action is created by cls API tcf_exts_validate() first conditional that calls tcf_action_init_1() directly, the action idr is not updated according to latest changes in action API that require caller to commit newly created action to idr with tcf_idr_insert_many(). This results such action not being accessible through act API and causes crash reported by syzbot: ================================================================== BUG: KASAN: null-ptr-deref in instrument_atomic_read include/linux/instrumented.h:71 [inline] BUG: KASAN: null-ptr-deref in atomic_read include/asm-generic/atomic-instrumented.h:27 [inline] BUG: KASAN: null-ptr-deref in __tcf_idr_release net/sched/act_api.c:178 [inline] BUG: KASAN: null-ptr-deref in tcf_idrinfo_destroy+0x129/0x1d0 net/sched/act_api.c:598 Read of size 4 at addr 0000000000000010 by task kworker/u4:5/204 CPU: 0 PID: 204 Comm: kworker/u4:5 Not tainted 5.11.0-rc7-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: netns cleanup_net Call Trace: __dump_stack lib/dump_stack.c:79 [inline] dump_stack+0x107/0x163 lib/dump_stack.c:120 __kasan_report mm/kasan/report.c:400 [inline] kasan_report.cold+0x5f/0xd5 mm/kasan/report.c:413 check_memory_region_inline mm/kasan/generic.c:179 [inline] check_memory_region+0x13d/0x180 mm/kasan/generic.c:185 instrument_atomic_read include/linux/instrumented.h:71 [inline] atomic_read include/asm-generic/atomic-instrumented.h:27 [inline] __tcf_idr_release net/sched/act_api.c:178 [inline] tcf_idrinfo_destroy+0x129/0x1d0 net/sched/act_api.c:598 tc_action_net_exit include/net/act_api.h:151 [inline] police_exit_net+0x168/0x360 net/sched/act_police.c:390 ops_exit_list+0x10d/0x160 net/core/net_namespace.c:190 cleanup_net+0x4ea/0xb10 net/core/net_namespace.c:604 process_one_work+0x98d/0x15f0 kernel/workqueue.c:2275 worker_thread+0x64c/0x1120 kernel/workqueue.c:2421 kthread+0x3b1/0x4a0 kernel/kthread.c:292 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:296 ================================================================== Kernel panic - not syncing: panic_on_warn set ... CPU: 0 PID: 204 Comm: kworker/u4:5 Tainted: G B 5.11.0-rc7-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: netns cleanup_net Call Trace: __dump_stack lib/dump_stack.c:79 [inline] dump_stack+0x107/0x163 lib/dump_stack.c:120 panic+0x306/0x73d kernel/panic.c:231 end_report+0x58/0x5e mm/kasan/report.c:100 __kasan_report mm/kasan/report.c:403 [inline] kasan_report.cold+0x67/0xd5 mm/kasan/report.c:413 check_memory_region_inline mm/kasan/generic.c:179 [inline] check_memory_region+0x13d/0x180 mm/kasan/generic.c:185 instrument_atomic_read include/linux/instrumented.h:71 [inline] atomic_read include/asm-generic/atomic-instrumented.h:27 [inline] __tcf_idr_release net/sched/act_api.c:178 [inline] tcf_idrinfo_destroy+0x129/0x1d0 net/sched/act_api.c:598 tc_action_net_exit include/net/act_api.h:151 [inline] police_exit_net+0x168/0x360 net/sched/act_police.c:390 ops_exit_list+0x10d/0x160 net/core/net_namespace.c:190 cleanup_net+0x4ea/0xb10 net/core/net_namespace.c:604 process_one_work+0x98d/0x15f0 kernel/workqueue.c:2275 worker_thread+0x64c/0x1120 kernel/workqueue.c:2421 kthread+0x3b1/0x4a0 kernel/kthread.c:292 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:296 Kernel Offset: disabled Fix the issue by calling tcf_idr_insert_many() after successful action initialization. Fixes: 0fedc63fadf0 ("net_sched: commit action insertions together") Reported-by: syzbot+151e3e714d34ae4ce7e8@syzkaller.appspotmail.com Signed-off-by: Vlad Buslov Reviewed-by: Cong Wang Signed-off-by: David S. Miller --- include/net/act_api.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/act_api.h b/include/net/act_api.h index 55dab604861f..57be7c5d273b 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -166,6 +166,7 @@ int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index, struct nlattr *est, struct tc_action **a, const struct tc_action_ops *ops, int bind, u32 flags); +void tcf_idr_insert_many(struct tc_action *actions[]); void tcf_idr_cleanup(struct tc_action_net *tn, u32 index); int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index, struct tc_action **a, int bind); -- cgit v1.2.3 From 3afd0218992a8d1398e9791d6c2edd4c948ae7ee Mon Sep 17 00:00:00 2001 From: Robert Hancock Date: Tue, 16 Feb 2021 16:54:52 -0600 Subject: net: phy: broadcom: Set proper 1000BaseX/SGMII interface mode for BCM54616S The default configuration for the BCM54616S PHY may not match the desired mode when using 1000BaseX or SGMII interface modes, such as when it is on an SFP module. Add code to explicitly set the correct mode using programming sequences provided by Bel-Fuse: https://www.belfuse.com/resources/datasheets/powersolutions/ds-bps-sfp-1gbt-05-series.pdf https://www.belfuse.com/resources/datasheets/powersolutions/ds-bps-sfp-1gbt-06-series.pdf Signed-off-by: Robert Hancock Acked-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 8fe1d55371ac..c2c2147dfeb8 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -129,6 +129,7 @@ #define MII_BCM54XX_AUXCTL_SHDWSEL_MISC 0x07 #define MII_BCM54XX_AUXCTL_SHDWSEL_MISC_WIRESPEED_EN 0x0010 +#define MII_BCM54XX_AUXCTL_SHDWSEL_MISC_RGMII_EN 0x0080 #define MII_BCM54XX_AUXCTL_SHDWSEL_MISC_RGMII_SKEW_EN 0x0100 #define MII_BCM54XX_AUXCTL_MISC_FORCE_AMDIX 0x0200 #define MII_BCM54XX_AUXCTL_MISC_WREN 0x8000 @@ -216,6 +217,9 @@ /* 11111: Mode Control Register */ #define BCM54XX_SHD_MODE 0x1f #define BCM54XX_SHD_INTF_SEL_MASK GENMASK(2, 1) /* INTERF_SEL[1:0] */ +#define BCM54XX_SHD_INTF_SEL_RGMII 0x02 +#define BCM54XX_SHD_INTF_SEL_SGMII 0x04 +#define BCM54XX_SHD_INTF_SEL_GBIC 0x06 #define BCM54XX_SHD_MODE_1000BX BIT(0) /* Enable 1000-X registers */ /* -- cgit v1.2.3 From b834489bceccc64641684eee5e93275cdf5f465b Mon Sep 17 00:00:00 2001 From: Robert Hancock Date: Tue, 16 Feb 2021 16:54:53 -0600 Subject: net: phy: Add is_on_sfp_module flag and phy_on_sfp helper Add a flag and helper function to indicate that a PHY device is part of an SFP module, which is set on attach. This can be used by PHY drivers to handle SFP-specific quirks or behavior. Signed-off-by: Robert Hancock Signed-off-by: David S. Miller --- include/linux/phy.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index 0d537f59b77f..1a12e4436b5b 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -492,6 +492,7 @@ struct macsec_ops; * @sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal. * @loopback_enabled: Set true if this PHY has been loopbacked successfully. * @downshifted_rate: Set true if link speed has been downshifted. + * @is_on_sfp_module: Set true if PHY is located on an SFP module. * @state: State of the PHY for management purposes * @dev_flags: Device-specific flags used by the PHY driver. * @irq: IRQ number of the PHY's interrupt (-1 if none) @@ -565,6 +566,7 @@ struct phy_device { unsigned sysfs_links:1; unsigned loopback_enabled:1; unsigned downshifted_rate:1; + unsigned is_on_sfp_module:1; unsigned autoneg:1; /* The most recently read link state */ @@ -1296,6 +1298,15 @@ static inline bool phy_is_internal(struct phy_device *phydev) return phydev->is_internal; } +/** + * phy_on_sfp - Convenience function for testing if a PHY is on an SFP module + * @phydev: the phy_device struct + */ +static inline bool phy_on_sfp(struct phy_device *phydev) +{ + return phydev->is_on_sfp_module; +} + /** * phy_interface_mode_is_rgmii - Convenience function for testing if a * PHY interface mode is RGMII (all variants) -- cgit v1.2.3 From 96313e1db8e5629cc2217616dca78f03e6463008 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 17 Feb 2021 12:25:57 -0800 Subject: net: mdio: Remove of_phy_attach() We have no in-tree users, also update the sfp-phylink.rst documentation to indicate that phy_attach_direct() is used instead of of_phy_attach(). Signed-off-by: Florian Fainelli Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/of_mdio.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include') diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index cfe8c607a628..2b05e7f7c238 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -26,9 +26,6 @@ of_phy_connect(struct net_device *dev, struct device_node *phy_np, struct phy_device * of_phy_get_and_connect(struct net_device *dev, struct device_node *np, void (*hndlr)(struct net_device *)); -struct phy_device * -of_phy_attach(struct net_device *dev, struct device_node *phy_np, - u32 flags, phy_interface_t iface); struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np); int of_phy_register_fixed_link(struct device_node *np); @@ -100,13 +97,6 @@ of_phy_get_and_connect(struct net_device *dev, struct device_node *np, return NULL; } -static inline struct phy_device *of_phy_attach(struct net_device *dev, - struct device_node *phy_np, - u32 flags, phy_interface_t iface) -{ - return NULL; -} - static inline struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np) { return NULL; -- cgit v1.2.3 From 20e07e2c3cf310578ef19fb4f1e64dc9832abd9d Mon Sep 17 00:00:00 2001 From: Wong Vee Khee Date: Wed, 17 Feb 2021 17:57:05 +0800 Subject: net: stmmac: Add PCI bus info to ethtool driver query output This patch populates the PCI bus info in the ethtool driver query data. Users will be able to view PCI bus info using 'ethtool -i '. Signed-off-by: Wong Vee Khee Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 15ca6b4167cc..a302982de2d7 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -202,5 +202,6 @@ struct plat_stmmacenet_data { bool vlan_fail_q_en; u8 vlan_fail_q; unsigned int eee_usecs_rate; + struct pci_dev *pdev; }; #endif -- cgit v1.2.3