Hello,


I use x86 device with FPGA device.

The FPGA device acts strangely with Linux, while with other OS on same HW there is no issues at all.
Other PCIe device on Linux acts fine without any issues. Doing lspci after reset, sometimes the device appear and other times not enumerated at all.

After reset it is almost always missing.

Then I force rescan several times, until it appears in lspci:

03:00.0 RAM memory: Xilinx Corporation Default PCIe endpoint ID (rev ff)

After it appears there is still inconsistency when reading configuration BAR with lspci -vv:

03:00.0 RAM memory: Xilinx Corporation Default PCIe endpoint ID
Subsystem: Xilinx Corporation Default PCIe endpoint ID
Control: I/O- Mem- BusMaster- SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B- DisINTx-
Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR- INTx-
Interrupt: pin A routed to IRQ 255
Region 0: [virtual] Memory at 91500000 (32-bit, non-prefetchable) [size=1M]
Capabilities: [40] Power Management version 3
Flags: PMEClk- DSI+ D1- D2- AuxCurrent=0mA PME(D0-,D1-,D2-,D3hot-,D3cold-)
Status: D0 NoSoftRst+ PME-Enable- DSel=0 DScale=0 PME-
Capabilities: [48] MSI: Enable- Count=1/1 Maskable- 64bit+
Address: 0000000000000000 Data: 0000
Capabilities: [58] Express (v1) Endpoint, MSI 00
DevCap: MaxPayload 256 bytes, PhantFunc 1, Latency L0s <64ns, L1 <1us
ExtTag+ AttnBtn- AttnInd- PwrInd- RBE+ FLReset- SlotPowerLimit 10.000W
DevCtl: Report errors: Correctable- Non-Fatal- Fatal- Unsupported-
RlxdOrd+ ExtTag- PhantFunc- AuxPwr- NoSnoop+
MaxPayload 128 bytes, MaxReadReq 512 bytes
DevSta: CorrErr+ UncorrErr- FatalErr- UnsuppReq- AuxPwr- TransPend-
LnkCap: Port #0, Speed 2.5GT/s, Width x1, ASPM L0s, Exit Latency L0s unlimited
ClockPM- Surprise- LLActRep- BwNot- ASPMOptComp-
LnkCtl: ASPM Disabled; RCB 64 bytes Disabled- CommClk-
ExtSynch- ClockPM- AutWidDis- BWInt- AutBWInt-
LnkSta: Speed 2.5GT/s, Width x1, TrErr- Train- SlotClk+ DLActive- BWMgmt- ABWMgmt-
Capabilities: [100 v1] Device Serial Number 00-00-00-00-00-00-00-00
[root@localhost ~]# lspci -xx -s 03:00.00

03:00.0 RAM memory: Xilinx Corporation Default PCIe endpoint ID
00: ee 10 07 00 00 00 10 00 00 00 00 05 00 00 00 00
10: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
20: 00 00 00 00 00 00 00 00 00 00 00 00 ee 10 07 00
30: 00 00 00 00 40 00 00 00 00 00 00 00 ff 01 00 00

Other tries of reading (without reseting in between):

03:00.0 RAM memory: Xilinx Corporation Default PCIe endpoint ID (rev ff) (prog-if ff)
!!! Unknown header type 7f

root@localhost ~]# lspci -xx -s 03:00.00

03:00.0 RAM memory: Xilinx Corporation Default PCIe endpoint ID (rev ff)
00: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
10: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
20: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
30: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff

[root@localhost pcimem]# ./pcimem /sys/bus/pci/devices/0000:03:00.0/resource0 0 w*100

/sys/bus/pci/devices/0000:03:00.0/resource0 opened.
Target offset is 0x0, page size is 4096
mmap(0, 4096, 0x3, 0x1, 3, 0x0)
PCI Memory mapped to address 0x7faf91256000.
0x0000: 0xFFFFFFFF
...
The BIOS is also different between Linux and the other OS on same HW.

Any idea what might cause this behavior ?

Thanks

My first instinct is that you mentioned your problem without one detail we need to work on or solve. Everything you mention answer 'exactly what' or 'exactly which?'

Generalities: Xilinx support Linux, and I believe kernel drivers. But their physical hardware might be more out of date. You're saying "PCI" but it's all PCIE now, and old standards will fall away. Give us some specs on your PC, versions, device, perhaps a log snippet of it booting, because honestly, what you wrote in the post was like something you'd say to your kid.