On a few of our systems, I found frequent 'unshare(CLONE_NEWNET)' calls
make the number of active slab objects including 'sock_inode_cache' type
rapidly and continuously increase.  As a result, memory pressure occurs.

In more detail, I made an artificial reproducer that resembles the
workload that we found the problem and reproduce the problem faster.  It
merely repeats 'unshare(CLONE_NEWNET)' 50,000 times in a loop.  It takes
about 2 minutes.  On 40 CPU cores / 70GB DRAM machine, the available
memory continuously reduced in a fast speed (about 120MB per second,
15GB in total within the 2 minutes).  Note that the issue don't
reproduce on every machine.  On my 6 CPU cores machine, the problem
didn't reproduce.

'cleanup_net()' and 'fqdir_work_fn()' are functions that deallocate the
relevant memory objects.  They are asynchronously invoked by the work
queues and internally use 'rcu_barrier()' to ensure safe destructions.
'cleanup_net()' works in a batched maneer in a single thread worker,
while 'fqdir_work_fn()' works for each 'fqdir_exit()' call in the
'system_wq'.  Therefore, 'fqdir_work_fn()' called frequently under the
workload and made the contention for 'rcu_barrier()' high.  In more
detail, the global mutex, 'rcu_state.barrier_mutex' became the
bottleneck.

This commit avoids such contention by doing the 'rcu_barrier()' and
subsequent lightweight works in a batched manner, as similar to that of
'cleanup_net()'.  The fqdir hashtable destruction, which is done before
the 'rcu_barrier()', is still allowed to run in parallel for fast
processing, but this commit makes it to use a dedicated work queue
instead of the 'system_wq', to make sure that the number of threads is
bounded.
Signed-off-by: SeongJae Park <sjpark@amazon.de>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20201211112405.31158-1-sjpark@amazon.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>