[TCWG CI] Regression caused by linux: net: mpls: Fix notifications when deleting a device: commit 7d4741eacdefa5f0475431645b56baf00784df1f Author: Benjamin Poirier bpoirier@nvidia.com
net: mpls: Fix notifications when deleting a device
Results regressed to # reset_artifacts: -10 # build_abe binutils: -9 # build_abe stage1: -5 # build_abe qemu: -2 # linux_n_obj: 19797 # First few build errors in logs: # 00:01:06 sound/core/oss/mixer_oss.c:1057:21: error: ‘slot’ is used uninitialized [-Werror=uninitialized] # 00:01:06 make[3]: *** [scripts/Makefile.build:287: sound/core/oss/mixer_oss.o] Error 1 # 00:01:06 sound/core/seq/oss/seq_oss_init.c:350:35: error: ‘qinfo’ is used uninitialized [-Werror=uninitialized] # 00:01:06 sound/core/seq/oss/seq_oss_init.c:370:35: error: ‘qinfo’ is used uninitialized [-Werror=uninitialized] # 00:01:06 make[4]: *** [scripts/Makefile.build:287: sound/core/seq/oss/seq_oss_init.o] Error 1 # 00:01:11 sound/core/oss/pcm_oss.c:108:29: error: ‘t’ is used uninitialized [-Werror=uninitialized] # 00:01:11 sound/core/oss/pcm_oss.c:2475:34: error: ‘setup’ is used uninitialized [-Werror=uninitialized] # 00:01:11 sound/core/oss/pcm_oss.c:2985:51: error: ‘template’ is used uninitialized [-Werror=uninitialized] # 00:01:11 make[3]: *** [scripts/Makefile.build:287: sound/core/oss/pcm_oss.o] Error 1 # 00:01:11 make[2]: *** [scripts/Makefile.build:549: sound/core/oss] Error 2
from # reset_artifacts: -10 # build_abe binutils: -9 # build_abe stage1: -5 # build_abe qemu: -2 # linux_n_obj: 19798
THIS IS THE END OF INTERESTING STUFF. BELOW ARE LINKS TO BUILDS, REPRODUCTION INSTRUCTIONS, AND THE RAW COMMIT.
This commit has regressed these CI configurations: - tcwg_kernel/gnu-master-aarch64-mainline-allyesconfig
First_bad build: https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-aarch64-mainline... Last_good build: https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-aarch64-mainline... Baseline build: https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-aarch64-mainline... Even more details: https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-aarch64-mainline...
Reproduce builds: <cut> mkdir investigate-linux-7d4741eacdefa5f0475431645b56baf00784df1f cd investigate-linux-7d4741eacdefa5f0475431645b56baf00784df1f
# Fetch scripts git clone https://git.linaro.org/toolchain/jenkins-scripts
# Fetch manifests and test.sh script mkdir -p artifacts/manifests curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-aarch64-mainline... --fail curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-aarch64-mainline... --fail curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-aarch64-mainline... --fail chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites) ./jenkins-scripts/tcwg_kernel-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh) mkdir -p ./bisect rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /linux/ ./ ./bisect/baseline/
cd linux
# Reproduce first_bad build git checkout --detach 7d4741eacdefa5f0475431645b56baf00784df1f ../artifacts/test.sh
# Reproduce last_good build git checkout --detach 817b653160db9852d5a0498a31f047e18ce27e5b ../artifacts/test.sh
cd .. </cut>
Full commit (up to 1000 lines): <cut> commit 7d4741eacdefa5f0475431645b56baf00784df1f Author: Benjamin Poirier bpoirier@nvidia.com Date: Mon Nov 29 15:15:05 2021 +0900
net: mpls: Fix notifications when deleting a device
There are various problems related to netlink notifications for mpls route changes in response to interfaces being deleted: * delete interface of only nexthop DELROUTE notification is missing RTA_OIF attribute * delete interface of non-last nexthop NEWROUTE notification is missing entirely * delete interface of last nexthop DELROUTE notification is missing nexthop
All of these problems stem from the fact that existing routes are modified in-place before sending a notification. Restructure mpls_ifdown() to avoid changing the route in the DELROUTE cases and to create a copy in the NEWROUTE case.
Fixes: f8efb73c97e2 ("mpls: multipath route support") Signed-off-by: Benjamin Poirier bpoirier@nvidia.com Signed-off-by: David S. Miller davem@davemloft.net --- net/mpls/af_mpls.c | 68 +++++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 52 insertions(+), 16 deletions(-)
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index ffeb2df8be7a..6e587feb705c 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1491,22 +1491,52 @@ static void mpls_dev_destroy_rcu(struct rcu_head *head) kfree(mdev); }
-static void mpls_ifdown(struct net_device *dev, int event) +static int mpls_ifdown(struct net_device *dev, int event) { struct mpls_route __rcu **platform_label; struct net *net = dev_net(dev); - u8 alive, deleted; unsigned index;
platform_label = rtnl_dereference(net->mpls.platform_label); for (index = 0; index < net->mpls.platform_labels; index++) { struct mpls_route *rt = rtnl_dereference(platform_label[index]); + bool nh_del = false; + u8 alive = 0;
if (!rt) continue;
- alive = 0; - deleted = 0; + if (event == NETDEV_UNREGISTER) { + u8 deleted = 0; + + for_nexthops(rt) { + struct net_device *nh_dev = + rtnl_dereference(nh->nh_dev); + + if (!nh_dev || nh_dev == dev) + deleted++; + if (nh_dev == dev) + nh_del = true; + } endfor_nexthops(rt); + + /* if there are no more nexthops, delete the route */ + if (deleted == rt->rt_nhn) { + mpls_route_update(net, index, NULL, NULL); + continue; + } + + if (nh_del) { + size_t size = sizeof(*rt) + rt->rt_nhn * + rt->rt_nh_size; + struct mpls_route *orig = rt; + + rt = kmalloc(size, GFP_KERNEL); + if (!rt) + return -ENOMEM; + memcpy(rt, orig, size); + } + } + change_nexthops(rt) { unsigned int nh_flags = nh->nh_flags;
@@ -1530,16 +1560,15 @@ static void mpls_ifdown(struct net_device *dev, int event) next: if (!(nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))) alive++; - if (!rtnl_dereference(nh->nh_dev)) - deleted++; } endfor_nexthops(rt);
WRITE_ONCE(rt->rt_nhn_alive, alive);
- /* if there are no more nexthops, delete the route */ - if (event == NETDEV_UNREGISTER && deleted == rt->rt_nhn) - mpls_route_update(net, index, NULL, NULL); + if (nh_del) + mpls_route_update(net, index, rt, NULL); } + + return 0; }
static void mpls_ifup(struct net_device *dev, unsigned int flags) @@ -1597,8 +1626,12 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event, return NOTIFY_OK;
switch (event) { + int err; + case NETDEV_DOWN: - mpls_ifdown(dev, event); + err = mpls_ifdown(dev, event); + if (err) + return notifier_from_errno(err); break; case NETDEV_UP: flags = dev_get_flags(dev); @@ -1609,13 +1642,18 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event, break; case NETDEV_CHANGE: flags = dev_get_flags(dev); - if (flags & (IFF_RUNNING | IFF_LOWER_UP)) + if (flags & (IFF_RUNNING | IFF_LOWER_UP)) { mpls_ifup(dev, RTNH_F_DEAD | RTNH_F_LINKDOWN); - else - mpls_ifdown(dev, event); + } else { + err = mpls_ifdown(dev, event); + if (err) + return notifier_from_errno(err); + } break; case NETDEV_UNREGISTER: - mpls_ifdown(dev, event); + err = mpls_ifdown(dev, event); + if (err) + return notifier_from_errno(err); mdev = mpls_dev_get(dev); if (mdev) { mpls_dev_sysctl_unregister(dev, mdev); @@ -1626,8 +1664,6 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event, case NETDEV_CHANGENAME: mdev = mpls_dev_get(dev); if (mdev) { - int err; - mpls_dev_sysctl_unregister(dev, mdev); err = mpls_dev_sysctl_register(dev, mdev); if (err) </cut>