]> git.proxmox.com Git - mirror_ubuntu-jammy-kernel.git/commit
thunderx: Remove rcu_read_lock() around XDP program invocation
authorToke Høiland-Jørgensen <toke@redhat.com>
Thu, 24 Jun 2021 16:05:59 +0000 (18:05 +0200)
committerDaniel Borkmann <daniel@iogearbox.net>
Thu, 24 Jun 2021 17:44:02 +0000 (19:44 +0200)
commit36baafe347a85a9d85f61aac0a9b53c53635829e
treeedcad54526c97cfef56d152c7512ddf4bebfa822
parent158c1399fc45c5178a3f2b8b68ff2faa2e36a52d
thunderx: Remove rcu_read_lock() around XDP program invocation

The thunderx driver has rcu_read_lock()/rcu_read_unlock() pairs around XDP
program invocations. However, the actual lifetime of the objects referred
by the XDP program invocation is longer, all the way through to the call to
xdp_do_flush(), making the scope of the rcu_read_lock() too small. This
turns out to be harmless because it all happens in a single NAPI poll
cycle (and thus under local_bh_disable()), but it makes the rcu_read_lock()
misleading.

Rather than extend the scope of the rcu_read_lock(), just get rid of it
entirely. With the addition of RCU annotations to the XDP_REDIRECT map
types that take bh execution into account, lockdep even understands this to
be safe, so there's really no reason to keep it around.

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Sunil Goutham <sgoutham@marvell.com>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/bpf/20210624160609.292325-10-toke@redhat.com
drivers/net/ethernet/cavium/thunder/nicvf_main.c