From c350c4761e7f4767dea59aef036ce13276466fd0 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 21 Oct 2024 11:32:35 -0700 Subject: [PATCH 01/16] ipv4: Convert check_lifetime() to per-netns RTNL. Since commit 1675f385213e ("ipv4: Namespacify IPv4 address GC."), check_lifetime() works on a per-netns basis. Let's use rtnl_net_lock() and rtnl_net_dereference(). Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Signed-off-by: Paolo Abeni --- net/ipv4/devinet.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 6b7780e12f34..5eaef3bbb987 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -771,7 +771,8 @@ static void check_lifetime(struct work_struct *work) rcu_read_unlock(); if (!change_needed) continue; - rtnl_lock(); + + rtnl_net_lock(net); hlist_for_each_entry_safe(ifa, n, head, addr_lst) { unsigned long age; @@ -788,7 +789,7 @@ static void check_lifetime(struct work_struct *work) struct in_ifaddr *tmp; ifap = &ifa->ifa_dev->ifa_list; - tmp = rtnl_dereference(*ifap); + tmp = rtnl_net_dereference(net, *ifap); while (tmp) { if (tmp == ifa) { inet_del_ifa(ifa->ifa_dev, @@ -796,7 +797,7 @@ static void check_lifetime(struct work_struct *work) break; } ifap = &tmp->ifa_next; - tmp = rtnl_dereference(*ifap); + tmp = rtnl_net_dereference(net, *ifap); } } else if (ifa->ifa_preferred_lft != INFINITY_LIFE_TIME && @@ -806,7 +807,7 @@ static void check_lifetime(struct work_struct *work) rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0); } } - rtnl_unlock(); + rtnl_net_unlock(net); } next_sec = round_jiffies_up(next); -- 2.50.1 From d1c81818aa227b37d65b40f9883109c5256b9bfb Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 21 Oct 2024 11:32:36 -0700 Subject: [PATCH 02/16] rtnetlink: Define rtnl_net_trylock(). We will need the per-netns version of rtnl_trylock(). rtnl_net_trylock() calls __rtnl_net_lock() only when rtnl_trylock() successfully holds RTNL. When RTNL is removed, we will use mutex_trylock() for per-netns RTNL. Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Signed-off-by: Paolo Abeni --- include/linux/rtnetlink.h | 6 ++++++ net/core/rtnetlink.c | 11 +++++++++++ 2 files changed, 17 insertions(+) diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 0e62918de63b..14b88f551920 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -101,6 +101,7 @@ void __rtnl_net_lock(struct net *net); void __rtnl_net_unlock(struct net *net); void rtnl_net_lock(struct net *net); void rtnl_net_unlock(struct net *net); +int rtnl_net_trylock(struct net *net); int rtnl_net_lock_cmp_fn(const struct lockdep_map *a, const struct lockdep_map *b); bool rtnl_net_is_locked(struct net *net); @@ -132,6 +133,11 @@ static inline void rtnl_net_unlock(struct net *net) rtnl_unlock(); } +static inline int rtnl_net_trylock(struct net *net) +{ + return rtnl_trylock(); +} + static inline void ASSERT_RTNL_NET(struct net *net) { ASSERT_RTNL(); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 194a81e5f608..dda8230fdfd4 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -210,6 +210,17 @@ void rtnl_net_unlock(struct net *net) } EXPORT_SYMBOL(rtnl_net_unlock); +int rtnl_net_trylock(struct net *net) +{ + int ret = rtnl_trylock(); + + if (ret) + __rtnl_net_lock(net); + + return ret; +} +EXPORT_SYMBOL(rtnl_net_trylock); + static int rtnl_net_cmp_locks(const struct net *net_a, const struct net *net_b) { if (net_eq(net_a, net_b)) -- 2.50.1 From 77453d428d4c9c613341de7f9b943f0c83f37a27 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 21 Oct 2024 11:32:37 -0700 Subject: [PATCH 03/16] ipv4: Convert devinet_sysctl_forward() to per-netns RTNL. devinet_sysctl_forward() touches only a single netns. Let's use rtnl_trylock() and __in_dev_get_rtnl_net(). Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Signed-off-by: Paolo Abeni --- net/ipv4/devinet.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 5eaef3bbb987..bd65e0ef774e 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -2395,7 +2395,7 @@ static void inet_forward_change(struct net *net) if (on) dev_disable_lro(dev); - in_dev = __in_dev_get_rtnl(dev); + in_dev = __in_dev_get_rtnl_net(dev); if (in_dev) { IN_DEV_CONF_SET(in_dev, FORWARDING, on); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, @@ -2486,7 +2486,7 @@ static int devinet_sysctl_forward(const struct ctl_table *ctl, int write, if (write && *valp != val) { if (valp != &IPV4_DEVCONF_DFLT(net, FORWARDING)) { - if (!rtnl_trylock()) { + if (!rtnl_net_trylock(net)) { /* Restore the original values before restarting */ *valp = val; *ppos = pos; @@ -2505,7 +2505,7 @@ static int devinet_sysctl_forward(const struct ctl_table *ctl, int write, idev->dev->ifindex, cnf); } - rtnl_unlock(); + rtnl_net_unlock(net); rt_cache_flush(net); } else inet_netconf_notify_devconf(net, RTM_NEWNETCONF, -- 2.50.1 From 88d1f8770690791cbe5d8f60b17137df05476299 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 21 Oct 2024 11:32:38 -0700 Subject: [PATCH 04/16] ipv4: Convert devinet_ioctl() to per-netns RTNL except for SIOCSIFFLAGS. Basically, devinet_ioctl() operates on a single netns. However, ioctl(SIOCSIFFLAGS) will trigger the netdev notifier that could touch another netdev in different netns. Let's use per-netns RTNL helper in devinet_ioctl() and place ASSERT_RTNL() for SIOCSIFFLAGS. We will remove ASSERT_RTNL() once RTM_SETLINK and RTM_DELLINK are converted. Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Signed-off-by: Paolo Abeni --- net/ipv4/devinet.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index bd65e0ef774e..fb4bc63b8fa2 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -589,9 +589,7 @@ static int inet_insert_ifa(struct in_ifaddr *ifa) static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa) { - struct in_device *in_dev = __in_dev_get_rtnl(dev); - - ASSERT_RTNL(); + struct in_device *in_dev = __in_dev_get_rtnl_net(dev); ipv4_devconf_setall(in_dev); neigh_parms_data_state_setall(in_dev->arp_parms); @@ -1129,7 +1127,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr) goto out; } - rtnl_lock(); + rtnl_net_lock(net); ret = -ENODEV; dev = __dev_get_by_name(net, ifr->ifr_name); @@ -1139,7 +1137,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr) if (colon) *colon = ':'; - in_dev = __in_dev_get_rtnl(dev); + in_dev = __in_dev_get_rtnl_net(dev); if (in_dev) { if (tryaddrmatch) { /* Matthias Andree */ @@ -1149,7 +1147,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr) This is checked above. */ for (ifap = &in_dev->ifa_list; - (ifa = rtnl_dereference(*ifap)) != NULL; + (ifa = rtnl_net_dereference(net, *ifap)) != NULL; ifap = &ifa->ifa_next) { if (!strcmp(ifr->ifr_name, ifa->ifa_label) && sin_orig.sin_addr.s_addr == @@ -1163,7 +1161,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr) comparing just the label */ if (!ifa) { for (ifap = &in_dev->ifa_list; - (ifa = rtnl_dereference(*ifap)) != NULL; + (ifa = rtnl_net_dereference(net, *ifap)) != NULL; ifap = &ifa->ifa_next) if (!strcmp(ifr->ifr_name, ifa->ifa_label)) break; @@ -1205,6 +1203,9 @@ int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr) inet_del_ifa(in_dev, ifap, 1); break; } + + /* NETDEV_UP/DOWN/CHANGE could touch a peer dev */ + ASSERT_RTNL(); ret = dev_change_flags(dev, ifr->ifr_flags, NULL); break; @@ -1306,7 +1307,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr) break; } done: - rtnl_unlock(); + rtnl_net_unlock(net); out: return ret; } -- 2.50.1 From 7ed8da17bfb2b033e42afa842ca22641821e231c Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 21 Oct 2024 11:32:39 -0700 Subject: [PATCH 05/16] ipv4: Convert devinet_ioctl to per-netns RTNL. ioctl(SIOCGIFCONF) calls dev_ifconf() that operates on the current netns. Let's use per-netns RTNL helpers in dev_ifconf() and inet_gifconf(). Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Signed-off-by: Paolo Abeni --- net/core/dev_ioctl.c | 6 +++--- net/ipv4/devinet.c | 4 ++-- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 473c437b6b53..46d43b950471 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -64,7 +64,7 @@ int dev_ifconf(struct net *net, struct ifconf __user *uifc) } /* Loop over the interfaces, and write an info block for each. */ - rtnl_lock(); + rtnl_net_lock(net); for_each_netdev(net, dev) { if (!pos) done = inet_gifconf(dev, NULL, 0, size); @@ -72,12 +72,12 @@ int dev_ifconf(struct net *net, struct ifconf __user *uifc) done = inet_gifconf(dev, pos + total, len - total, size); if (done < 0) { - rtnl_unlock(); + rtnl_net_unlock(net); return -EFAULT; } total += done; } - rtnl_unlock(); + rtnl_net_unlock(net); return put_user(total, &uifc->ifc_len); } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index fb4bc63b8fa2..f58f39a9ee87 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1314,7 +1314,7 @@ out: int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size) { - struct in_device *in_dev = __in_dev_get_rtnl(dev); + struct in_device *in_dev = __in_dev_get_rtnl_net(dev); const struct in_ifaddr *ifa; struct ifreq ifr; int done = 0; @@ -1325,7 +1325,7 @@ int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size) if (!in_dev) goto out; - in_dev_for_each_ifa_rtnl(ifa, in_dev) { + in_dev_for_each_ifa_rtnl_net(dev_net(dev), ifa, in_dev) { if (!buf) { done += size; continue; -- 2.50.1 From 0a24488d93e8039d046518990291aae827c0eab9 Mon Sep 17 00:00:00 2001 From: Rosen Penev Date: Mon, 21 Oct 2024 17:22:41 -0700 Subject: [PATCH 06/16] net: ibm: emac: use netif_receive_skb_list Small rx improvement. Would use napi_gro_receive instead but that's a lot more involved than netif_receive_skb_list because of how the function is implemented. Before: > iperf -c 192.168.1.1 ------------------------------------------------------------ Client connecting to 192.168.1.1, TCP port 5001 TCP window size: 16.0 KByte (default) ------------------------------------------------------------ [ 1] local 192.168.1.101 port 51556 connected with 192.168.1.1 port 5001 [ ID] Interval Transfer Bandwidth [ 1] 0.00-10.04 sec 559 MBytes 467 Mbits/sec > iperf -c 192.168.1.1 ------------------------------------------------------------ Client connecting to 192.168.1.1, TCP port 5001 TCP window size: 16.0 KByte (default) ------------------------------------------------------------ [ 1] local 192.168.1.101 port 48228 connected with 192.168.1.1 port 5001 [ ID] Interval Transfer Bandwidth [ 1] 0.00-10.03 sec 558 MBytes 467 Mbits/sec > iperf -c 192.168.1.1 ------------------------------------------------------------ Client connecting to 192.168.1.1, TCP port 5001 TCP window size: 16.0 KByte (default) ------------------------------------------------------------ [ 1] local 192.168.1.101 port 47600 connected with 192.168.1.1 port 5001 [ ID] Interval Transfer Bandwidth [ 1] 0.00-10.04 sec 557 MBytes 466 Mbits/sec > iperf -c 192.168.1.1 ------------------------------------------------------------ Client connecting to 192.168.1.1, TCP port 5001 TCP window size: 16.0 KByte (default) ------------------------------------------------------------ [ 1] local 192.168.1.101 port 37252 connected with 192.168.1.1 port 5001 [ ID] Interval Transfer Bandwidth [ 1] 0.00-10.05 sec 559 MBytes 467 Mbits/sec After: > iperf -c 192.168.1.1 ------------------------------------------------------------ Client connecting to 192.168.1.1, TCP port 5001 TCP window size: 16.0 KByte (default) ------------------------------------------------------------ [ 1] local 192.168.1.101 port 40786 connected with 192.168.1.1 port 5001 [ ID] Interval Transfer Bandwidth [ 1] 0.00-10.05 sec 572 MBytes 478 Mbits/sec > iperf -c 192.168.1.1 ------------------------------------------------------------ Client connecting to 192.168.1.1, TCP port 5001 TCP window size: 16.0 KByte (default) ------------------------------------------------------------ [ 1] local 192.168.1.101 port 52482 connected with 192.168.1.1 port 5001 [ ID] Interval Transfer Bandwidth [ 1] 0.00-10.04 sec 571 MBytes 477 Mbits/sec > iperf -c 192.168.1.1 ------------------------------------------------------------ Client connecting to 192.168.1.1, TCP port 5001 TCP window size: 16.0 KByte (default) ------------------------------------------------------------ [ 1] local 192.168.1.101 port 48370 connected with 192.168.1.1 port 5001 [ ID] Interval Transfer Bandwidth [ 1] 0.00-10.04 sec 572 MBytes 478 Mbits/sec > iperf -c 192.168.1.1 ------------------------------------------------------------ Client connecting to 192.168.1.1, TCP port 5001 TCP window size: 16.0 KByte (default) ------------------------------------------------------------ [ 1] local 192.168.1.101 port 46086 connected with 192.168.1.1 port 5001 [ ID] Interval Transfer Bandwidth [ 1] 0.00-10.05 sec 571 MBytes 476 Mbits/sec > iperf -c 192.168.1.1 ------------------------------------------------------------ Client connecting to 192.168.1.1, TCP port 5001 TCP window size: 16.0 KByte (default) ------------------------------------------------------------ [ 1] local 192.168.1.101 port 46062 connected with 192.168.1.1 port 5001 [ ID] Interval Transfer Bandwidth [ 1] 0.00-10.04 sec 572 MBytes 478 Mbits/sec Signed-off-by: Rosen Penev Reviewed-by: Simon Horman Reviewed-by: Shannon Nelson Signed-off-by: Paolo Abeni --- drivers/net/ethernet/ibm/emac/core.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index dadd987efb6b..0edcb435e62f 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -1727,6 +1727,7 @@ static inline int emac_rx_sg_append(struct emac_instance *dev, int slot) /* NAPI poll context */ static int emac_poll_rx(void *param, int budget) { + LIST_HEAD(rx_list); struct emac_instance *dev = param; int slot = dev->rx_slot, received = 0; @@ -1783,8 +1784,7 @@ static int emac_poll_rx(void *param, int budget) skb->protocol = eth_type_trans(skb, dev->ndev); emac_rx_csum(dev, skb, ctrl); - if (unlikely(netif_receive_skb(skb) == NET_RX_DROP)) - ++dev->estats.rx_dropped_stack; + list_add_tail(&skb->list, &rx_list); next: ++dev->stats.rx_packets; skip: @@ -1828,6 +1828,8 @@ static int emac_poll_rx(void *param, int budget) goto next; } + netif_receive_skb_list(&rx_list); + if (received) { DBG2(dev, "rx %d BDs" NL, received); dev->rx_slot = slot; -- 2.50.1 From c9bf90863df5fc8bae9513ce9bfcc260fad2ea0e Mon Sep 17 00:00:00 2001 From: Rosen Penev Date: Mon, 21 Oct 2024 17:22:42 -0700 Subject: [PATCH 07/16] net: ibm: emac: use devm_platform_ioremap_resource No need to have a struct resource. Gets rid of the TODO. Signed-off-by: Rosen Penev Reviewed-by: Simon Horman Reviewed-by: Shannon Nelson Signed-off-by: Paolo Abeni --- drivers/net/ethernet/ibm/emac/core.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index 0edcb435e62f..f387c4635cc6 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -3050,12 +3050,10 @@ static int emac_probe(struct platform_device *ofdev) ndev->irq = dev->emac_irq; - /* Map EMAC regs */ - // TODO : platform_get_resource() and devm_ioremap_resource() - dev->emacp = devm_of_iomap(&ofdev->dev, np, 0, NULL); - if (!dev->emacp) { + dev->emacp = devm_platform_ioremap_resource(ofdev, 0); + if (IS_ERR(dev->emacp)) { dev_err(&ofdev->dev, "can't map device registers"); - err = -ENOMEM; + err = PTR_ERR(dev->emacp); goto err_gone; } -- 2.50.1 From a598f66d9169312e7eaab8cc7b8f175866e68997 Mon Sep 17 00:00:00 2001 From: Rosen Penev Date: Mon, 21 Oct 2024 17:22:43 -0700 Subject: [PATCH 08/16] net: ibm: emac: use platform_get_irq No need for irq_of_parse_and_map since we have platform_device. Signed-off-by: Rosen Penev Reviewed-by: Simon Horman Reviewed-by: Shannon Nelson Signed-off-by: Paolo Abeni --- drivers/net/ethernet/ibm/emac/core.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index f387c4635cc6..8c6f69f90af9 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -3031,15 +3031,8 @@ static int emac_probe(struct platform_device *ofdev) if (err) goto err_gone; - /* Get interrupts. EMAC irq is mandatory */ - dev->emac_irq = irq_of_parse_and_map(np, 0); - if (!dev->emac_irq) { - printk(KERN_ERR "%pOF: Can't map main interrupt\n", np); - err = -ENODEV; - goto err_gone; - } - /* Setup error IRQ handler */ + dev->emac_irq = platform_get_irq(ofdev, 0); err = devm_request_irq(&ofdev->dev, dev->emac_irq, emac_irq, 0, "EMAC", dev); if (err) { -- 2.50.1 From af4698be49e856589f559fee2054de5bc7d5b72f Mon Sep 17 00:00:00 2001 From: Rosen Penev Date: Mon, 21 Oct 2024 17:22:44 -0700 Subject: [PATCH 09/16] net: ibm: emac: use devm for mutex_init It seems since inception that mutex_destroy was never called for these in _remove. Instead of handling this manually, just use devm for simplicity. Signed-off-by: Rosen Penev Reviewed-by: Shannon Nelson Signed-off-by: Paolo Abeni --- drivers/net/ethernet/ibm/emac/core.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index 8c6f69f90af9..1f45f2a78829 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -3021,8 +3021,14 @@ static int emac_probe(struct platform_device *ofdev) SET_NETDEV_DEV(ndev, &ofdev->dev); /* Initialize some embedded data structures */ - mutex_init(&dev->mdio_lock); - mutex_init(&dev->link_lock); + err = devm_mutex_init(&ofdev->dev, &dev->mdio_lock); + if (err) + goto err_gone; + + err = devm_mutex_init(&ofdev->dev, &dev->link_lock); + if (err) + goto err_gone; + spin_lock_init(&dev->lock); INIT_WORK(&dev->reset_work, emac_reset_work); -- 2.50.1 From 707f1c4b6a2cf0bd290a63b6f3701878bb15e05f Mon Sep 17 00:00:00 2001 From: Rosen Penev Date: Mon, 21 Oct 2024 17:22:45 -0700 Subject: [PATCH 10/16] net: ibm: emac: generate random MAC if not found On this Cisco MX60W, u-boot sets the local-mac-address property. Unfortunately by default, the MAC is wrong and is actually located on a UBI partition. Which means nvmem needs to be used to grab it. In the case where that fails, EMAC fails to initialize instead of generating a random MAC as many other drivers do. Match behavior with other drivers to have a working ethernet interface. Signed-off-by: Rosen Penev Reviewed-by: Shannon Nelson Signed-off-by: Paolo Abeni --- drivers/net/ethernet/ibm/emac/core.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index 1f45f2a78829..25b8a3556004 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -2937,9 +2937,12 @@ static int emac_init_config(struct emac_instance *dev) /* Read MAC-address */ err = of_get_ethdev_address(np, dev->ndev); - if (err) - return dev_err_probe(&dev->ofdev->dev, err, - "Can't get valid [local-]mac-address from OF !\n"); + if (err == -EPROBE_DEFER) + return err; + if (err) { + dev_warn(&dev->ofdev->dev, "Can't get valid mac-address. Generating random."); + eth_hw_addr_random(dev->ndev); + } /* IAHT and GAHT filter parameterization */ if (emac_has_feature(dev, EMAC_FTR_EMAC4SYNC)) { -- 2.50.1 From b76ebf22c578375e69b35061b5d47149efd957f9 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Tue, 22 Oct 2024 11:48:00 +0200 Subject: [PATCH 11/16] ipv4: Prepare fib_compute_spec_dst() to future .flowi4_tos conversion. Use ip4h_dscp() to get the DSCP from the IPv4 header, then convert the dscp_t value to __u8 with inet_dscp_to_dsfield(). Then, when we'll convert .flowi4_tos to dscp_t, we'll just have to drop the inet_dscp_to_dsfield() call. Signed-off-by: Guillaume Nault Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/a0eba69cce94f747e4c7516184a85ffd0abbe3f0.1729530028.git.gnault@redhat.com Signed-off-by: Jakub Kicinski --- net/ipv4/fib_frontend.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 53bd26315df5..0c9ce934b490 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -293,7 +293,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb) .flowi4_iif = LOOPBACK_IFINDEX, .flowi4_l3mdev = l3mdev_master_ifindex_rcu(dev), .daddr = ip_hdr(skb)->saddr, - .flowi4_tos = ip_hdr(skb)->tos & INET_DSCP_MASK, + .flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(ip_hdr(skb))), .flowi4_scope = scope, .flowi4_mark = vmark ? skb->mark : 0, }; -- 2.50.1 From 0ed373390c5c180d19a40f258c2e72754f641eb9 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Tue, 22 Oct 2024 11:48:08 +0200 Subject: [PATCH 12/16] ipv4: Prepare icmp_reply() to future .flowi4_tos conversion. Use ip4h_dscp() to get the DSCP from the IPv4 header, then convert the dscp_t value to __u8 with inet_dscp_to_dsfield(). Then, when we'll convert .flowi4_tos to dscp_t, we'll just have to drop the inet_dscp_to_dsfield() call. Signed-off-by: Guillaume Nault Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/61b7563563f8b0a562b5b62032fe5260034d0aac.1729530028.git.gnault@redhat.com Signed-off-by: Jakub Kicinski --- net/ipv4/icmp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 23664434922e..33eec844a5a0 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -445,7 +445,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) fl4.saddr = saddr; fl4.flowi4_mark = mark; fl4.flowi4_uid = sock_net_uid(net, NULL); - fl4.flowi4_tos = ip_hdr(skb)->tos & INET_DSCP_MASK; + fl4.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(ip_hdr(skb))); fl4.flowi4_proto = IPPROTO_ICMP; fl4.flowi4_oif = l3mdev_master_ifindex(skb->dev); security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4)); -- 2.50.1 From 6ab04392dd087d896910dc618b4a14e54c58a499 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Tue, 22 Oct 2024 11:48:15 +0200 Subject: [PATCH 13/16] ipv4: Prepare ipmr_rt_fib_lookup() to future .flowi4_tos conversion. Use ip4h_dscp() to get the DSCP from the IPv4 header, then convert the dscp_t value to __u8 with inet_dscp_to_dsfield(). Then, when we'll convert .flowi4_tos to dscp_t, we'll just have to drop the inet_dscp_to_dsfield() call. Signed-off-by: Guillaume Nault Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/462402a097260357a7aba80228612305f230b6a9.1729530028.git.gnault@redhat.com Signed-off-by: Jakub Kicinski --- net/ipv4/ipmr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index b4fc443481ce..99e7cd0531d9 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2081,7 +2081,7 @@ static struct mr_table *ipmr_rt_fib_lookup(struct net *net, struct sk_buff *skb) struct flowi4 fl4 = { .daddr = iph->daddr, .saddr = iph->saddr, - .flowi4_tos = iph->tos & INET_DSCP_MASK, + .flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(iph)), .flowi4_oif = (rt_is_output_route(rt) ? skb->dev->ifindex : 0), .flowi4_iif = (rt_is_output_route(rt) ? -- 2.50.1 From 85ef52e8693c4d3d23f33dc8007ebf11d5d4d4ce Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Tue, 22 Oct 2024 11:48:23 +0200 Subject: [PATCH 14/16] ipv4: Prepare ip_rt_get_source() to future .flowi4_tos conversion. Use ip4h_dscp() to get the DSCP from the IPv4 header, then convert the dscp_t value to __u8 with inet_dscp_to_dsfield(). Then, when we'll convert .flowi4_tos to dscp_t, we'll just have to drop the inet_dscp_to_dsfield() call. Signed-off-by: Guillaume Nault Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/0a13a200f31809841975e38633914af1061e0c04.1729530028.git.gnault@redhat.com Signed-off-by: Jakub Kicinski --- net/ipv4/route.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 18a08b4f4a5a..763398e08b7d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1263,7 +1263,7 @@ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt) struct flowi4 fl4 = { .daddr = iph->daddr, .saddr = iph->saddr, - .flowi4_tos = iph->tos & INET_DSCP_MASK, + .flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(iph)), .flowi4_oif = rt->dst.dev->ifindex, .flowi4_iif = skb->dev->ifindex, .flowi4_mark = skb->mark, -- 2.50.1 From bdd85ddce5a9fb786daecbc7ed73bf8cdee06856 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Tue, 22 Oct 2024 14:03:20 -0700 Subject: [PATCH 15/16] rtnetlink: Fix kdoc of rtnl_af_register(). Commit 26eebdc4b005 ("rtnetlink: Return int from rtnl_af_register().") made rtnl_af_register() return int again, and kdoc needs to be fixed up. Signed-off-by: Kuniyuki Iwashima Reviewed-by: Simon Horman Link: https://patch.msgid.link/20241022210320.86111-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- net/core/rtnetlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index dda8230fdfd4..b70f90b98714 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -708,7 +708,7 @@ static void rtnl_af_put(struct rtnl_af_ops *ops, int srcu_index) * rtnl_af_register - Register rtnl_af_ops with rtnetlink. * @ops: struct rtnl_af_ops * to register * - * Returns 0 on success or a negative error code. + * Return: 0 on success or a negative error code. */ int rtnl_af_register(struct rtnl_af_ops *ops) { -- 2.50.1 From 9a1036389fa25cf90d58e3ae1bb0b1ad877ef1c8 Mon Sep 17 00:00:00 2001 From: Karan Sanghavi Date: Tue, 22 Oct 2024 18:30:52 +0000 Subject: [PATCH 16/16] selftests: tc-testing: Fix typo error Correct the typo errors in json files - "diffferent" is corrected to "different". - "muliple" and "miltiple" is corrected to "multiple". Reviewed-by: Simon Horman Reviewed-by: Shuah Khan Signed-off-by: Karan Sanghavi Link: https://patch.msgid.link/20241022-multiple_spell_error-v2-1-7e5036506fe5@gmail.com Signed-off-by: Jakub Kicinski --- .../selftests/tc-testing/tc-tests/filters/basic.json | 6 +++--- .../selftests/tc-testing/tc-tests/filters/cgroup.json | 6 +++--- .../testing/selftests/tc-testing/tc-tests/filters/flow.json | 2 +- .../selftests/tc-testing/tc-tests/filters/route.json | 2 +- 4 files changed, 8 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json b/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json index d1278de8ebc3..c9309a44a87e 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json @@ -67,7 +67,7 @@ }, { "id": "4943", - "name": "Add basic filter with cmp ematch u32/link layer and miltiple actions", + "name": "Add basic filter with cmp ematch u32/link layer and multiple actions", "category": [ "filter", "basic" @@ -155,7 +155,7 @@ }, { "id": "32d8", - "name": "Add basic filter with cmp ematch u32/network layer and miltiple actions", + "name": "Add basic filter with cmp ematch u32/network layer and multiple actions", "category": [ "filter", "basic" @@ -243,7 +243,7 @@ }, { "id": "62d7", - "name": "Add basic filter with cmp ematch u32/transport layer and miltiple actions", + "name": "Add basic filter with cmp ematch u32/transport layer and multiple actions", "category": [ "filter", "basic" diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/cgroup.json b/tools/testing/selftests/tc-testing/tc-tests/filters/cgroup.json index 03723cf84379..35c9a7dbe1c4 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/cgroup.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/cgroup.json @@ -67,7 +67,7 @@ }, { "id": "0234", - "name": "Add cgroup filter with cmp ematch u32/link layer and miltiple actions", + "name": "Add cgroup filter with cmp ematch u32/link layer and multiple actions", "category": [ "filter", "cgroup" @@ -155,7 +155,7 @@ }, { "id": "2733", - "name": "Add cgroup filter with cmp ematch u32/network layer and miltiple actions", + "name": "Add cgroup filter with cmp ematch u32/network layer and multiple actions", "category": [ "filter", "cgroup" @@ -1189,7 +1189,7 @@ }, { "id": "4319", - "name": "Replace cgroup filter with diffferent match", + "name": "Replace cgroup filter with different match", "category": [ "filter", "cgroup" diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json b/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json index 58189327f644..996448afe31b 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json @@ -507,7 +507,7 @@ }, { "id": "4341", - "name": "Add flow filter with muliple ops", + "name": "Add flow filter with multiple ops", "category": [ "filter", "flow" diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/route.json b/tools/testing/selftests/tc-testing/tc-tests/filters/route.json index 8d8de8f65aef..05cedca67cca 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/route.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/route.json @@ -111,7 +111,7 @@ }, { "id": "7994", - "name": "Add route filter with miltiple actions", + "name": "Add route filter with multiple actions", "category": [ "filter", "route" -- 2.50.1