Re: [PATCH net] mlx4: reduce OOM risk on arches with large pages
From: David Miller <davem@davemloft.net>
Date: 2017-02-20 15:32:10
From: Eric Dumazet <redacted> Date: Sat, 18 Feb 2017 10:34:18 -0800
From: Eric Dumazet <edumazet@google.com>
Since mlx4 NIC are used on PowerPC with 64K pages, we need to adapt
MLX4_EN_ALLOC_PREFER_ORDER definition.
Otherwise, a fragment sitting in an out of order TCP queue can hold
0.5 Mbytes and it is a serious OOM risk.
Fixes: 51151a16a60f ("mlx4: allow order-0 memory allocations in RX path")
Signed-off-by: Eric Dumazet <edumazet@google.com>Applied.