UPGRADE YOUR BROWSER

We have detected your current browser version is not the latest one. Xilinx.com uses the latest web technologies to bring you the best online experience possible. Please upgrade to a Xilinx.com supported browser:Chrome, Firefox, Internet Explorer 11, Safari. Thank you!

cancel
Showing results for 
Search instead for 
Did you mean: 
Adventurer
Adventurer
472 Views
Registered: ‎04-11-2018

Error of no DPU core found in current configuration of DPU IP!

Jump to solution

Hi,
I am following the DPU integration tutorial. I am getting this error when I boot on ZU4EV board. Although, I have checked for the previous answers on the Xilinx forum none of solutions did apply on solving this error. The error presented is shown below.

[ 4.121067] [DPU][2102]Found DPU signature addr = 0xbf000000 in device-tree
[ 4.128023] [DPU][2102]Checking DPU signature at addr = 0xbff00000,
[ 4.134387] [DPU][2102]DPU signature NOT found, fallback to device-tree.
[ 4.141082] [DPU][2102]Error of no DPU core found in current configuration of DPU IP!

In addition, when the DPU signature and signature VA is checked by printing the fields in dpucore.c file (line 1139)

if (signature_addr != SIG_BASE_NULL) {
dpr_init("Checking DPU signature at addr = 0x%lx, \n", signature_addr);
signature_va =
ioremap((phys_addr_t)signature_addr, 1 * sizeof(signature_field));
signature_field = ioread32(signature_va);

dpr_init("Checking DPU signature field is = 0x%lx, \n",signature_field);
dpr_init("Checking DPU signature VA field is = 0x%lx, \n",signature_va);

I get the following error on booting the board

root@FM191_kernel:~# lsmod
Tainted: G
dpu 49152 0 - Live 0xffffff8000b23000 (O)
mali 241664 0 - Live 0xffffff8000ad0000 (O)
uio_pdrv_genirq 16384 0 - Live 0xffffff8000ac0000

root@FM191_kernel:~# dmesg

[ 4.340785] [DPU][2105]Found DPU signature addr = 0xbf000000 in device-tree
[ 4.347747] [DPU][2105]Checking DPU signature at addr = 0xbff00000,
[ 4.354115] [DPU][2105]Checking DPU signature field is = 0x0,
[ 4.359941] [DPU][2105]Checking DPU signature VA field is = 0xffffff80093ad000,
[ 4.367327] [DPU][2105]DPU signature NOT found, fallback to device-tree.
[ 4.374025] [DPU][2105]Error of no DPU core found in current configuration of DPU IP!
[ 4.393505] EXT4-fs (mmcblk1p2): re-mounted. Opts: data=ordered
[ 4.694489] pps pps0: new PPS source ptp0
[ 4.698515] macb ff0e0000.ethernet: gem-ptp-timer ptp clock registered.
[ 4.705196] IPv6: ADDRCONF(NETDEV_UP): eth0: link is not ready
[ 4.940190] PLL: shutdown
[ 7.824223] macb ff0e0000.ethernet eth0: link up (1000/Full)
[ 7.829904] IPv6: ADDRCONF(NETDEV_CHANGE): eth0: link becomes ready

I attaching the system-user.dtsi.

The PL interface is PL_PS_IRQ1 the GIC RIQ number is 143:136. The interrupt number calculated is (136-32=104) which is 68 hex.

Can you please help me check what am I missing.

0 Kudos
1 Solution

Accepted Solutions
Contributor
Contributor
360 Views
Registered: ‎10-27-2008

回复: Error of no DPU core found in current configuration of DPU IP!

Jump to solution

Hello,

I ran into a similar situation, where I was reading 0x00000000 from the DPU's address space, as configured in the Address Editor.

To see if you are in the same situation, please execute the following command in the TCL Console (change "dpu_eu_0" to the instance name of your DPU core)::

   report_property [get_bd_cells dpu_eu_0]

Check what the value of the following is:

   CONFIG.S_AXI_SLAVES_BASE_ADDR

In your design, this should report as 0xBF000000.

 

If it does not match the value in the Address Editor, you are in the same situation that I ran into.

 

The fix consists of making these two values match.

Hope this helps !

 

Regards,

Mario.

0 Kudos
9 Replies
Xilinx Employee
Xilinx Employee
449 Views
Registered: ‎03-27-2013

回复: Error of no DPU core found in current configuration of DPU IP!

Jump to solution

Hi @pranju ,

 

From your log information it seems that you have maped the DPU to a base address of 0xbf000000.

But the driver can't get a signature at 0xbff00000.

Have you tried to read this physical address via devmem?

"devmem 0xbff00000"

Or you can print the value of signature_field in the driver.

It should return a value with last 16-bit to 0x4450.

Best Regards,
Jason
-----------------------------------------------------------------------------------------------
Please mark the Answer as "Accept as solution" if the information provided is helpful.

Give Kudos to a post which you think is helpful and reply oriented.
-----------------------------------------------------------------------------------------------
Adventurer
Adventurer
441 Views
Registered: ‎04-11-2018

回复: Error of no DPU core found in current configuration of DPU IP!

Jump to solution

Hi @jasonwu ,

Thank you so much for the reply.

Yes, the DPU is at the base address of 0xbf000000.I tried to read the physical address and below is the result.

root@FM191_kernel:~# devmem 0xbff00000
0x00000000

Anyway, the result obtained is 0x00000000

How should I do this: you can print the value of signature_field in the driver? Are you saying in the dpucore.h?

Can you tell what should I do next, please?

 

 

0 Kudos
Xilinx Employee
Xilinx Employee
424 Views
Registered: ‎01-21-2014

回复: Error of no DPU core found in current configuration of DPU IP!

Jump to solution

You mostly like have a hardware issue in the PL if you're reading all zeros from that register. Check clocks and resets, double check your address tab to make sure you have the DPU AXI slave port where you think it is. 

 

Regards, 

Terry

 

Xilinx Employee
Xilinx Employee
416 Views
Registered: ‎03-27-2013

回复: Error of no DPU core found in current configuration of DPU IP!

Jump to solution

Yes, I agree with Terry.

Best Regards,
Jason
-----------------------------------------------------------------------------------------------
Please mark the Answer as "Accept as solution" if the information provided is helpful.

Give Kudos to a post which you think is helpful and reply oriented.
-----------------------------------------------------------------------------------------------
0 Kudos
Highlighted
Adventurer
Adventurer
399 Views
Registered: ‎04-11-2018

回复: Error of no DPU core found in current configuration of DPU IP!

Jump to solution

Hi @terryo ,

Okay. I have checked the address. I do have the DPU AXI slave port. Can you please check the attachment with the address editor and the block design.

Can you please tell me how should I proceed?

vivado_address_editor.png
vivado_bd.png
0 Kudos
Xilinx Employee
Xilinx Employee
372 Views
Registered: ‎01-21-2014

回复: Error of no DPU core found in current configuration of DPU IP!

Jump to solution

It's really hard to say without seeing the whole design.  I would first try accessing the DPU IP from bare-metal or the debugger to see if Linux is the problem - you could also dump the registers from u-boot.   You could put another slave IP out there on the same interconnect to see if you can access that - maybe axi bram.  At the same time throw in an ILA in there so you can see what's going on in hardware at boot. 

 

Terry

 

0 Kudos
Contributor
Contributor
361 Views
Registered: ‎10-27-2008

回复: Error of no DPU core found in current configuration of DPU IP!

Jump to solution

Hello,

I ran into a similar situation, where I was reading 0x00000000 from the DPU's address space, as configured in the Address Editor.

To see if you are in the same situation, please execute the following command in the TCL Console (change "dpu_eu_0" to the instance name of your DPU core)::

   report_property [get_bd_cells dpu_eu_0]

Check what the value of the following is:

   CONFIG.S_AXI_SLAVES_BASE_ADDR

In your design, this should report as 0xBF000000.

 

If it does not match the value in the Address Editor, you are in the same situation that I ran into.

 

The fix consists of making these two values match.

Hope this helps !

 

Regards,

Mario.

0 Kudos
Adventurer
Adventurer
333 Views
Registered: ‎04-11-2018

回复: Error of no DPU core found in current configuration of DPU IP!

Jump to solution

Hi @marron ,

Thank you so much. Yes, it was helpful. I checked the address of the DPU using the tcl command and the result is

CONFIG.S.AXI_SLAVES_BASE_ADDR 0X80000000

Whereas, the address in the address editor is 0xBF000000

Thus, the address does not match.

I tried changing the address in the address editor whereas I am getting an error as

The proposed address exceeds the base address limitations <0xB0000000 [ 256M ], 0x500000000 [ 4G ], 0x4800000000 [ 224G ]> of the interface(s) </zynq_ultra_ps_e_0/M_AXI_HPM1_FPD> through which this peripheral is accessed by this address space

In the TCL script the address mentioned is 0xBF000000. How do you recommend to map the address? Do I need to change the tcl script and rebuild the project?

Thanks!

0 Kudos
Contributor
Contributor
175 Views
Registered: ‎10-27-2008

回复: Error of no DPU core found in current configuration of DPU IP!

Jump to solution

Hi @pranju 

Were you able to resolve your second issue (related to address space) ?

Regards,

Mario.

0 Kudos