On 8/21/2017 2:00 PM, Bjorn Helgaas wrote:

On Mon, Aug 21, 2017 at 09:44:09AM -0400, Sinan Kaya wrote:

quoted

Hi Bjorn,

On 8/18/2017 5:01 PM, Bjorn Helgaas wrote:

It would still be interesting to see the lspci output.  Likely <MAbort
in the upstream bridge will be set even before the FLR because of
aborts during enumeration.  The PCI core should probably clear that
after enumeration.  I expect that if you manually clear it with
setpci, do the lspci, do the FLR, do another lspci, you will probably
see <MAbort being set by this pci_flr_wait() loop.  We might want to
consider clearing it here as well.

     Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR- INTx-
        Latency: 0
        Interrupt: pin A routed to IRQ 345
        Bus: primary=00, secondary=01, subordinate=01, sec-latency=0
        I/O behind bridge: 00002000-00002fff
        Memory behind bridge: 00100000-002fffff
        Prefetchable memory behind bridge: 0000090400000000-00000904001fffff
        Secondary status: 66MHz- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- <SERR- <PERR-

FLR reset here with CRS to the NVMe drive.
	
     Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR- INTx-
        Latency: 0
        Interrupt: pin A routed to IRQ 345
        Bus: primary=00, secondary=01, subordinate=01, sec-latency=0
        I/O behind bridge: 00002000-00002fff
        Memory behind bridge: 00100000-002fffff
        Prefetchable memory behind bridge: 0000090400000000-00000904001fffff
        Secondary status: 66MHz- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- <SERR- <PERR-
	
I don't see <MAbort getting set. 




-- 
Sinan Kaya
Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum, a Linux Foundation Collaborative Project.