From 6510ea973d8d9d4a0cb2fb557b36bd1ab3eb49f6 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 25 Apr 2022 18:39:46 +0200 Subject: net: Use this_cpu_inc() to increment net->core_stats The macro dev_core_stats_##FIELD##_inc() disables preemption and invokes netdev_core_stats_alloc() to return a per-CPU pointer. netdev_core_stats_alloc() will allocate memory on its first invocation which breaks on PREEMPT_RT because it requires non-atomic context for memory allocation. This can be avoided by enabling preemption in netdev_core_stats_alloc() assuming the caller always disables preemption. It might be better to replace local_inc() with this_cpu_inc() now that dev_core_stats_##FIELD##_inc() gained a preempt-disable section and does not rely on already disabled preemption. This results in less instructions on x86-64: local_inc: | incl %gs:__preempt_count(%rip) # __preempt_count | movq 488(%rdi), %rax # _1->core_stats, _22 | testq %rax, %rax # _22 | je .L585 #, | add %gs:this_cpu_off(%rip), %rax # this_cpu_off, tcp_ptr__ | .L586: | testq %rax, %rax # _27 | je .L587 #, | incq (%rax) # _6->a.counter | .L587: | decl %gs:__preempt_count(%rip) # __preempt_count this_cpu_inc(), this patch: | movq 488(%rdi), %rax # _1->core_stats, _5 | testq %rax, %rax # _5 | je .L591 #, | .L585: | incq %gs:(%rax) # _18->rx_dropped Use unsigned long as type for the counter. Use this_cpu_inc() to increment the counter. Use a plain read of the counter. Signed-off-by: Sebastian Andrzej Siewior Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/YmbO0pxgtKpCw4SY@linutronix.de Signed-off-by: Jakub Kicinski --- net/core/dev.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) (limited to 'net') diff --git a/net/core/dev.c b/net/core/dev.c index 8c6c08446556..1461c2d9dec8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10304,7 +10304,7 @@ void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, } EXPORT_SYMBOL(netdev_stats_to_stats64); -struct net_device_core_stats *netdev_core_stats_alloc(struct net_device *dev) +struct net_device_core_stats __percpu *netdev_core_stats_alloc(struct net_device *dev) { struct net_device_core_stats __percpu *p; @@ -10315,11 +10315,7 @@ struct net_device_core_stats *netdev_core_stats_alloc(struct net_device *dev) free_percpu(p); /* This READ_ONCE() pairs with the cmpxchg() above */ - p = READ_ONCE(dev->core_stats); - if (!p) - return NULL; - - return this_cpu_ptr(p); + return READ_ONCE(dev->core_stats); } EXPORT_SYMBOL(netdev_core_stats_alloc); @@ -10356,9 +10352,9 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, for_each_possible_cpu(i) { core_stats = per_cpu_ptr(p, i); - storage->rx_dropped += local_read(&core_stats->rx_dropped); - storage->tx_dropped += local_read(&core_stats->tx_dropped); - storage->rx_nohandler += local_read(&core_stats->rx_nohandler); + storage->rx_dropped += READ_ONCE(core_stats->rx_dropped); + storage->tx_dropped += READ_ONCE(core_stats->tx_dropped); + storage->rx_nohandler += READ_ONCE(core_stats->rx_nohandler); } } return storage; -- cgit v1.2.3