[dpdk-dev] [PATCH v3] vmxnet3: fix Rx deadlock

[Yong Wang]

> -----Original Message-----
> From: Stefan Puiu [mailto:stefan.puiu at gmail.com]
> Sent: Friday, December 16, 2016 7:37 AM
> To: dev at dpdk.org
> Cc: Yong Wang <yongwang at vmware.com>; mac_leehk at yahoo.com.hk;
> Stefan Puiu <stefan.puiu at gmail.com>
> Subject: [PATCH v3] vmxnet3: fix Rx deadlock
> 
> Our use case is that we have an app that needs to keep mbufs around
> for a while. We've seen cases when calling vmxnet3_post_rx_bufs() from
> vmxet3_recv_pkts(), it might not succeed to add any mbufs to any RX
> descriptors (where it returns -err). Since there are no mbufs that the
> virtual hardware can use, no packets will be received after this; the
> driver won't refill the mbuf after this so it gets stuck in this
> state. I call this a deadlock for lack of a better term - the virtual
> HW waits for free mbufs, while the app waits for the hardware to
> notify it for data (by flipping the generation bit on the used Rx
> descriptors). Note that after this, the app can't recover.
> 
> This fix is a rework of this patch by Marco Lee:
> https://urldefense.proofpoint.com/v2/url?u=http-
> 3A__dpdk.org_dev_patchwork_patch_6575_&d=DgIBAg&c=uilaK90D4TOVo
> H58JNXRgQ&r=v4BBYIqiDq552fkYnKKFBFyqvMXOR3UXSdFO2plFD1s&m=zvM
> IQvFmKNiehiMa4e9UerIU-
> XZTcnlOqJZ0FXx0lsM&s=nZk5Zsz_6yrZOCrteBQ4RJbgLMhsPxW8DQkZmzGSo
> yU&e= . I had to forward port
> it, address review comments and also reverted the allocation
> failure handling to the first version of the patch
> (https://urldefense.proofpoint.com/v2/url?u=http-
> 3A__dpdk.org_ml_archives_dev_2015-
> 2DJuly_022079.html&d=DgIBAg&c=uilaK90D4TOVoH58JNXRgQ&r=v4BBYIqiD
> q552fkYnKKFBFyqvMXOR3UXSdFO2plFD1s&m=zvMIQvFmKNiehiMa4e9UerI
> U-XZTcnlOqJZ0FXx0lsM&s=dU2FsdH7OPHIUXeXIrv0yubdCb-
> 4_koMclojVj_5ULo&e= ), since
> that's the only approach that seems to work, and seems to be what
> other drivers are doing (I checked ixgbe and em). Reusing the mbuf
> that's getting passed to the application doesn't seem to make
> sense, and it was causing weird issues in our app. Also, reusing
> rxm without checking if it's NULL could cause the code to crash.
> ---

Signoff info is missing from the commit description.  Otherwise, looks good.

Acked-by: Yong Wang <yongwang at vmware.com>