Re: [PATCH] net/mlx4: Fix EEH recovery failure

[Gavin Shan <gwshan@linux.vnet.ibm.com>]

On Sun, Nov 23, 2014 at 06:21:47PM +0200, Amir Vadai wrote:
>On 11/22/2014 12:56 PM, Gavin Shan wrote:
>> The patch fixes couple of EEH recovery failures on PPC PowerNV
>> platform:
>> 
>>    * Release reserved memory regions in mlx4_pci_err_detected().
>>      Otherwise, __mlx4_init_one() fails because of reserving
>>      same memory regions recursively.
>>    * Disable PCI device in mlx4_pci_err_detected(). Otherwise,
>>      pci_enable_device() in __mlx4_init_one() doesn't enable
>>      the PCI device because it's already in enabled state indicated
>>      by struct pci_dev::enable_cnt.
>>    * Don't clear struct mlx4_priv instance in mlx4_pci_err_detected().
>>      Otherwise, __mlx4_init_one() runs into kernel crash because
>>      of dereferencing to NULL pointer.
>> 
>> With the patch applied, EEH recovery for mlx4 adapter succeeds on PPC
>> PowerNV platform.
>> 
>>    # lspci
>>    0003:0f:00.0 Network controller: Mellanox Technologies \
>>    MT27500 Family [ConnectX-3]
>> 
>> Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
>
>Hi Gavin,
>
>Yishai (added to the CC) is few days before sending a patchset to fix
>the reset flow and inside it there is a fix to EEH recovery.
>I would be happy if you could wait for the whole reset flow fix by Yishai.
>

Yes, It's not urgent and I can wait. Thanks for the info.

>If you'd like, I can send you the patchset to try. Currently it is under
>review inside Mellanox before being sent to the mailing list.
>

It would be nice to send me the patchset for me to have a try.

Thanks,
Gavin

>Thanks,
>Amir
>
>
>
>