cancel
Showing results for 
Search instead for 
Did you mean: 

Drivers & Software

globetrotter
Adept I

Has anyone succeeded in using HP Gen9 servers with FirePro S7150x2?

I have an ML350 Gen 9 (same server as DL380, just in tower configuration) with the latest BIOS.  I am using xcp-ng 8.1, but I have also tried Citrix Xenserver 8.2  I have installed the latest GIM supplement from the AMD website.  Running "modprobe gim" followed by "lspci | grep 7150" only shows the 7150 PFs, never the VFs.  System setup:

  • HP ML350 Gen9
  • 1 Xeon E2650v3
  • Latest HP firmware
  • SR-IOV enabled in BIOS
  • xcp-ng 8.1
  • Xenserver MxGPU host driver 2.0

dmesg indicates the host driver can see the VFs but cannot allocate them:

[16:30 xenserver ~]# dmesg | grep gim
[ 49.663165] gim: module license 'Proprietary' taints kernel.
[ 49.665881] gim info:(gim_init:197) *******AMD GIM init
[ 49.665883] gim info:(print_gim_version:62) GPU IOV MODULE (GIM) - version 2.00.0000
[ 49.665883] gim info:(gim_init:200) Copyright (c) 2014-2016 AMD Corporation.
[ 49.666057] gim info:(parse_config_file:295) AMD GIM fb_option = 0
[ 49.666058] gim info:(parse_config_file:295) AMD GIM sched_option = 0
[ 49.666059] gim info:(parse_config_file:295) AMD GIM vf_num = 0
[ 49.666060] gim info:(parse_config_file:295) AMD GIM pf_fb = 0
[ 49.666061] gim info:(parse_config_file:295) AMD GIM vf_fb = 0
[ 49.666062] gim info:(parse_config_file:295) AMD GIM sched_interval = 7
[ 49.666063] gim info:(parse_config_file:295) AMD GIM fb_clear = 1
[ 49.666064] gim info:(parse_config_file:295) AMD GIM hang_detect_timeout = 100
[ 49.666065] gim info:(parse_config_file:295) AMD GIM max_quanta = 1000
[ 49.666066] gim info:(parse_config_file:295) AMD GIM self_switch = 500
[ 49.666068] gim info:(parse_config_file:295) AMD GIM exclusive = 1600
[ 49.666069] gim info:(parse_config_file:295) AMD GIM fair_scheduling = 0
[ 49.666070] gim info:(parse_config_file:295) AMD GIM debug_level = 3
[ 49.666071] gim info:(parse_config_file:295) AMD GIM clear_fb_on_flr = 0
[ 49.666073] gim info:(parse_config_file:295) AMD GIM clear_fb_on_free_vf = 1
[ 49.666074] gim info:(init_config:445) INIT CONFIG
[ 49.674506] gim error:(gim_probe:123) gim_probe(06:00.0)
[ 49.674516] gim info:(alloc_adapter:454) allocate adapter for PF 0x0600
[ 49.674517] gim info:(alloc_adapter:457) Found free adapter at index 0
[ 49.674523] PF0 gim info:(SetNewAdapter:1096) curr allocated at 0000000010b15569
[ 49.674523] PF0 gim info:(SetNewAdapter:1102) Can't disable ATS --> Not enabled in the first place
[ 49.674524] PF0 gim info:(SetNewAdapter:1113) SRIOV is supported
[ 49.674525] PF0 gim info:(SetNewAdapter:1121) found PCI bridge device
[ 49.674526] PF0 gim info:(SetNewAdapter:1124) found: 05:8.0
[ 49.674635] PF0 gim info:(SetNewAdapter:1147) mmio_base = 00000000e8b48023
[ 49.675191] PF0 gim info:(SetNewAdapter:1149) doorbell = 000000008b7f5cae
[ 49.743564] PF0 gim info:(SetNewAdapter:1151) pf.fb_va = 0000000095b745af
[ 49.743584] gim info:(sriov_is_ari_enabled:180) PCI_SRIOV_CAP = 0x00000002
[ 49.743586] gim info:(sriov_is_ari_enabled:190) PCI_SRIOV_CTRL = 0x00000010
[ 49.743586] gim info:(sriov_is_ari_enabled:194) PCI_SRIOV_CTRL_ARI is set --> ARI is supported
[ 49.743588] PF0 gim info:(program_ari_mode:957) Read bif_strap8 = 0x00200004
[ 49.743589] PF0 gim info:(program_ari_mode:963) program_ari_mode - Set ARI_Mode = PF_BUS
[ 49.743589] PF0 gim info:(program_ari_mode:978) Write bif_strap8 = 0x00000004
[ 49.743590] PF0 gim info:(gim_read_rom_from_reg:634) Reading VBios from ROM
[ 49.743742] PF0 gim info:(gim_read_VBIOS:695) VBIOS starts: 0x55, 0xaa
[ 49.743743] PF0 gim info:(gim_read_VBIOS:698) VBios size is 0x10000
[ 49.743747] PF0 gim info:(gim_read_VBIOS:708) pVBIOS allocated at 00000000de62d681 for size of 0x80000
[ 49.743747] PF0 gim info:(gim_read_rom_from_reg:634) Reading VBios from ROM
[ 51.195035] PF0 gim info:(gim_read_VBIOS:718) BIOS Version Major 0xF Minor 0x31
[ 51.195133] PF0 gim info:(gim_read_VBIOS:729) VBios Checksum = 0x548300
[ 51.195134] PF0 gim info:(gim_read_VBIOS:738) Valid video BIOS image, size = 0x10000, check sum is 0x548300
[ 51.195135] PF0 gim info:(gim_read_VBIOS:739) Read in full Vbios image of size = 0x80000
[ 51.195139] PF0 gim info:(SetNewAdapter:1248) Scheduler Time interval set to 7 msec
[ 51.195141] gim info:(EnableSriov:398) Enable SRIOV
[ 51.195141] gim info:(EnableSriov:399) Enable SRIOV vfs count = 16
[ 51.306998] gim info:(EnumerateVFs:128) vf found: 06:2.0
[ 51.306999] gim info:(EnumerateVFs:128) vf found: 06:2.1
[ 51.307000] gim info:(EnumerateVFs:128) vf found: 06:2.2
[ 51.307001] gim info:(EnumerateVFs:128) vf found: 06:2.3
[ 51.307002] gim info:(EnumerateVFs:128) vf found: 06:2.4
[ 51.307003] gim info:(EnumerateVFs:128) vf found: 06:2.5
[ 51.307004] gim info:(EnumerateVFs:128) vf found: 06:2.6
[ 51.307005] gim info:(EnumerateVFs:128) vf found: 06:2.7
[ 51.307006] gim info:(EnumerateVFs:128) vf found: 06:3.0
[ 51.307006] gim info:(EnumerateVFs:128) vf found: 06:3.1
[ 51.307007] gim info:(EnumerateVFs:128) vf found: 06:3.2
[ 51.307008] gim info:(EnumerateVFs:128) vf found: 06:3.3
[ 51.307009] gim info:(EnumerateVFs:128) vf found: 06:3.4
[ 51.307010] gim info:(EnumerateVFs:128) vf found: 06:3.5
[ 51.307011] gim info:(EnumerateVFs:128) vf found: 06:3.6
[ 51.307012] gim info:(EnumerateVFs:128) vf found: 06:3.7
[ 51.308275] gim info:(pci_disable_error_reporting:830) Disable error reporting for device: 06:2.0
[ 51.308277] gim info:(pci_disable_error_reporting:834) Mask before -> corr = 0x00000000, uncorr = 0x00000000
[ 51.308288] gim info:(pci_disable_error_reporting:844) Mask after -> corr = 0x00000000, uncorr = 0x00000000
[ 51.309635] gim info:(pci_disable_error_reporting:830) Disable error reporting for device: 06:2.1
[ 51.309638] gim info:(pci_disable_error_reporting:834) Mask before -> corr = 0x00000000, uncorr = 0x00000000
[ 51.309649] gim info:(pci_disable_error_reporting:844) Mask after -> corr = 0x00000000, uncorr = 0x00000000
[ 51.310957] gim info:(pci_disable_error_reporting:830) Disable error reporting for device: 06:2.2
[ 51.310959] gim info:(pci_disable_error_reporting:834) Mask before -> corr = 0x00000000, uncorr = 0x00000000
[ 51.310970] gim info:(pci_disable_error_reporting:844) Mask after -> corr = 0x00000000, uncorr = 0x00000000
[ 51.312276] gim info:(pci_disable_error_reporting:830) Disable error reporting for device: 06:2.3
[ 51.312278] gim info:(pci_disable_error_reporting:834) Mask before -> corr = 0x00000000, uncorr = 0x00000000
[ 51.312288] gim info:(pci_disable_error_reporting:844) Mask after -> corr = 0x00000000, uncorr = 0x00000000
[ 51.313610] gim info:(pci_disable_error_reporting:830) Disable error reporting for device: 06:2.4
[ 51.313613] gim info:(pci_disable_error_reporting:834) Mask before -> corr = 0x00000000, uncorr = 0x00000000
[ 51.313623] gim info:(pci_disable_error_reporting:844) Mask after -> corr = 0x00000000, uncorr = 0x00000000
[ 51.314931] gim info:(pci_disable_error_reporting:830) Disable error reporting for device: 06:2.5
[ 51.314933] gim info:(pci_disable_error_reporting:834) Mask before -> corr = 0x00000000, uncorr = 0x00000000
[ 51.314944] gim info:(pci_disable_error_reporting:844) Mask after -> corr = 0x00000000, uncorr = 0x00000000
[ 51.316248] gim info:(pci_disable_error_reporting:830) Disable error reporting for device: 06:2.6
[ 51.316250] gim info:(pci_disable_error_reporting:834) Mask before -> corr = 0x00000000, uncorr = 0x00000000
[ 51.316261] gim info:(pci_disable_error_reporting:844) Mask after -> corr = 0x00000000, uncorr = 0x00000000
[ 51.317585] gim info:(pci_disable_error_reporting:830) Disable error reporting for device: 06:2.7
[ 51.317587] gim info:(pci_disable_error_reporting:834) Mask before -> corr = 0x00000000, uncorr = 0x00000000
[ 51.317597] gim info:(pci_disable_error_reporting:844) Mask after -> corr = 0x00000000, uncorr = 0x00000000
[ 51.318947] gim info:(pci_disable_error_reporting:830) Disable error reporting for device: 06:3.0
[ 51.318949] gim info:(pci_disable_error_reporting:834) Mask before -> corr = 0x00000000, uncorr = 0x00000000
[ 51.318960] gim info:(pci_disable_error_reporting:844) Mask after -> corr = 0x00000000, uncorr = 0x00000000
[ 51.320313] gim info:(pci_disable_error_reporting:830) Disable error reporting for device: 06:3.1
[ 51.320315] gim info:(pci_disable_error_reporting:834) Mask before -> corr = 0x00000000, uncorr = 0x00000000
[ 51.320326] gim info:(pci_disable_error_reporting:844) Mask after -> corr = 0x00000000, uncorr = 0x00000000
[ 51.321699] gim info:(pci_disable_error_reporting:830) Disable error reporting for device: 06:3.2
[ 51.321701] gim info:(pci_disable_error_reporting:834) Mask before -> corr = 0x00000000, uncorr = 0x00000000
[ 51.321711] gim info:(pci_disable_error_reporting:844) Mask after -> corr = 0x00000000, uncorr = 0x00000000
[ 51.323120] gim info:(pci_disable_error_reporting:830) Disable error reporting for device: 06:3.3
[ 51.323122] gim info:(pci_disable_error_reporting:834) Mask before -> corr = 0x00000000, uncorr = 0x00000000
[ 51.323133] gim info:(pci_disable_error_reporting:844) Mask after -> corr = 0x00000000, uncorr = 0x00000000
[ 51.324576] gim info:(pci_disable_error_reporting:830) Disable error reporting for device: 06:3.4
[ 51.324578] gim info:(pci_disable_error_reporting:834) Mask before -> corr = 0x00000000, uncorr = 0x00000000
[ 51.324588] gim info:(pci_disable_error_reporting:844) Mask after -> corr = 0x00000000, uncorr = 0x00000000
[ 51.326066] gim info:(pci_disable_error_reporting:830) Disable error reporting for device: 06:3.5
[ 51.326069] gim info:(pci_disable_error_reporting:834) Mask before -> corr = 0x00000000, uncorr = 0x00000000
[ 51.326079] gim info:(pci_disable_error_reporting:844) Mask after -> corr = 0x00000000, uncorr = 0x00000000
[ 51.327631] gim info:(pci_disable_error_reporting:830) Disable error reporting for device: 06:3.6
[ 51.327633] gim info:(pci_disable_error_reporting:834) Mask before -> corr = 0x00000000, uncorr = 0x00000000
[ 51.327643] gim info:(pci_disable_error_reporting:844) Mask after -> corr = 0x00000000, uncorr = 0x00000000
[ 51.329223] gim info:(pci_disable_error_reporting:830) Disable error reporting for device: 06:3.7
[ 51.329225] gim info:(pci_disable_error_reporting:834) Mask before -> corr = 0x00000000, uncorr = 0x00000000
[ 51.329235] gim info:(pci_disable_error_reporting:844) Mask after -> corr = 0x00000000, uncorr = 0x00000000
[ 51.329249] gim info:(pci_gpu_iov_init:117) totalFBAvailable = 8190
[ 51.329250] gim info:(pci_gpu_iov_init:118) AMD GIM pci_gpu_iov_init pos = 400
[ 51.329250] gim info:(pci_gpu_iov_init:119) AMD GIM pci_gpu_iov_init totalFBAvailable = 1ffe
[ 51.329251] gim info:(init_frame_buffer_partition:232) PCI defined PF FB size = 256 MB
[ 51.329252] gim info:(init_frame_buffer_partition:236) PCI defined VF FB size = 256 MB
[ 51.329253] gim info:(init_frame_buffer_partition:239) Total FB Available = 8190 MB, CSA = 8 MB, Max remaining FB size = 8160 MB
[ 51.329254] gim info:(init_frame_buffer_partition:240) max_fb_size = 8160
[ 51.329254] gim info:(init_frame_buffer_partition:253) PF FB size after checking limits from config file = 256 MB
[ 51.329255] gim info:(init_frame_buffer_partition:255) PF rounded down to nearest 16MB boundary = 256
[ 51.329256] gim info:(init_pf_fb:99) total framebuffer available = 1ffe
[ 51.329257] gim info:(init_pf_fb:100) pf framebuffer = 100
[ 51.329257] gim info:(init_pf_fb:101) total framebuffer consumed = 1efe
[ 51.329260] gim info:(init_frame_buffer_partition:262) CSA starts at offset 256MB
[ 51.329261] gim info:(init_context_save_area:84) AMD GIM init_context_save_area: base =100 size=1.
[ 51.329264] gim info:(init_frame_buffer_partition:267) VF FB base = 272MB (256 + 8)
[ 51.329265] gim info:(init_frame_buffer_partition:270) VF FB Size = 7904MB (8160 - 256)
[ 51.329266] gim info:(init_fb_static:160) AMD GIM init_fb_static: num_vf = 10, base= 110, total_size=1ee0, mini_size=100
[ 51.329267] gim info:(init_fb_static:189) AMD GIM init_fb_static: vf_fb_size = 1e0, base= 110
[ 51.329267] gim info:(init_fb_static:194) num_vf = 16
[ 51.329268] gim info:(init_fb_static:200) AMD GIM init_fb_static: partition 0 base = 110, size= 1e0
[ 51.329271] gim info:(init_fb_static:200) AMD GIM init_fb_static: partition 1 base = 2f0, size= 1e0
[ 51.329274] gim info:(init_fb_static:200) AMD GIM init_fb_static: partition 2 base = 4d0, size= 1e0
[ 51.329277] gim info:(init_fb_static:200) AMD GIM init_fb_static: partition 3 base = 6b0, size= 1e0
[ 51.329280] gim info:(init_fb_static:200) AMD GIM init_fb_static: partition 4 base = 890, size= 1e0
[ 51.329282] gim info:(init_fb_static:200) AMD GIM init_fb_static: partition 5 base = a70, size= 1e0
[ 51.329285] gim info:(init_fb_static:200) AMD GIM init_fb_static: partition 6 base = c50, size= 1e0
[ 51.329290] gim info:(init_fb_static:200) AMD GIM init_fb_static: partition 7 base = e30, size= 1e0
[ 51.329293] gim info:(init_fb_static:200) AMD GIM init_fb_static: partition 8 base = 1010, size= 1e0
[ 51.329295] gim info:(init_fb_static:200) AMD GIM init_fb_static: partition 9 base = 11f0, size= 1e0
[ 51.329298] gim info:(init_fb_static:200) AMD GIM init_fb_static: partition 10 base = 13d0, size= 1e0
[ 51.329301] gim info:(init_fb_static:200) AMD GIM init_fb_static: partition 11 base = 15b0, size= 1e0
[ 51.329304] gim info:(init_fb_static:200) AMD GIM init_fb_static: partition 12 base = 1790, size= 1e0
[ 51.329307] gim info:(init_fb_static:200) AMD GIM init_fb_static: partition 13 base = 1970, size= 1e0
[ 51.329309] gim info:(init_fb_static:200) AMD GIM init_fb_static: partition 14 base = 1b50, size= 1e0
[ 51.329312] gim info:(init_fb_static:200) AMD GIM init_fb_static: partition 15 base = 1d30, size= 1e0
[ 51.329315] PF0 gim info:(init_scheduler_cycle:303) Setting cycle time = 112msec
[ 51.329331] PF0 gim info:(SetNewAdapter:1304) enable MSI
[ 51.329425] PF0 gim info:(ih_iv_ring_disable:446) disable iv ring successfully
[ 51.329426] PF0 gim info:(alloc_iv_ring:144) ih->ivRingNumEntries = 256
[ 51.329427] PF0 gim info:(alloc_iv_ring:147) ih->ivRingSizeInBytes = 4096
[ 51.329427] PF0 gim info:(alloc_iv_ring:151) ih->ivRingAllocSizeInBytes = 4100
[ 51.329428] PF0 gim info:(alloc_iv_ring:153) iv ring page_cnt = 2
[ 51.329445] PF0 gim info:(alloc_iv_ring:183) ih->ivRing_VA = 00000000cd43de79
[ 51.329446] PF0 gim info:(alloc_iv_ring:186) ih->ivRing_MA.QuadPart = 0x1140ef000
[ 51.329447] PF0 gim info:(alloc_iv_ring:189) ih->ivRingWptrWB = 000000003c898296
[ 51.329447] PF0 gim info:(alloc_iv_ring:192) ih->ivRingWptrWB_MA.QuadPart = 0x1140e6000
[ 51.329448] PF0 gim info:(alloc_iv_ring:236) update rptr via doorbell
[ 51.329449] PF0 gim info:(ih_iv_ring_init:354) ih->rptrDoorbell = 0000000012db6e14
[ 51.329450] PF0 gim info:(ih_iv_ring_init:355) ih->rptrDoorbellOffset = 0x1e8
[ 51.329452] PF0 gim info:(ih_iv_ring_hw_init:255) the physical address of ring buffer: 0x1140ef0
[ 51.329460] PF0 gim info:(ih_iv_ring_setupRPTR:507) write mmBIF_DOORBELL_APER_EN: 0x1
[ 51.329460] PF0 gim info:(ih_iv_ring_enable:413) ih->ivRingWptr_Reg = 0x0
[ 51.329461] PF0 gim info:(ih_iv_ring_enable:415) ih->ivRingWptr = 0
[ 51.329462] PF0 gim info:(ih_iv_ring_enable:417) ih->ivRingRptr_Reg = 0x0
[ 51.329463] PF0 gim info:(ih_iv_ring_enable:419) ih->ivRingRptr = 0
[ 51.329464] PF0 gim info:(ih_iv_ring_enable:421) *(ih->rptrDoorbell) = 0x0
[ 51.329465] PF0 gim info:(ih_iv_ring_init:362) init iv ring successfully
[ 51.329551] PF0 gim info:(SetNewAdapter:1326) init work
[ 51.329552] PF0 gim info:(SetNewAdapter:1334) register interrupt
[ 51.329584] PF0 gim info:(ih_irq_source_enable:653) IH: read 0x00000000 from maskReg 0x14d1
[ 51.329585] PF0 gim info:(ih_irq_source_enable:658) IH: write 0x00000001 to maskReg 0x14d1
[ 51.329585] PF0 gim info:(ih_irq_source_enable:660) irq sourceID 0x89 get enabled
[ 51.329587] PF0 gim info:(ih_irq_source_enable:653) IH: read 0x00000001 from maskReg 0x14d1
[ 51.329588] PF0 gim info:(ih_irq_source_enable:658) IH: write 0x00000003 to maskReg 0x14d1
[ 51.329589] PF0 gim info:(ih_irq_source_enable:660) irq sourceID 0x88 get enabled
[ 51.329590] PF0 gim info:(init_vf:2428) Operation on PF!
[ 51.332621] gim error:(wait_cmd_complete:2387) wait_cmd_complete -- time out after 0.003003262 sec
[ 51.332644] gim error:(wait_cmd_complete:2390) Cmd = 0x17, Status = 0x0, cmd_Complete=0
[ 51.332653] PF0 gim warning:(dump_function_state:252) NULL
[ 51.332654] PF0 gim warning:(dump_function_state:254) Last known states:
[ 51.332654] PF0 gim warning:(dump_function_state:255) PF = Undefined
[ 51.332655] VF0-0 gim warning:(dump_function_state:259) Undefined, Marked as Not Runable
[ 51.332656] VF0-1 gim warning:(dump_function_state:259) Undefined, Marked as Not Runable
[ 51.332657] VF0-2 gim warning:(dump_function_state:259) Undefined, Marked as Not Runable
[ 51.332658] VF0-3 gim warning:(dump_function_state:259) Undefined, Marked as Not Runable
[ 51.332659] VF0-4 gim warning:(dump_function_state:259) Undefined, Marked as Not Runable
[ 51.332659] VF0-5 gim warning:(dump_function_state:259) Undefined, Marked as Not Runable
[ 51.332660] VF0-6 gim warning:(dump_function_state:259) Undefined, Marked as Not Runable
[ 51.332661] VF0-7 gim warning:(dump_function_state:259) Undefined, Marked as Not Runable
[ 51.332662] VF0-8 gim warning:(dump_function_state:259) Undefined, Marked as Not Runable
[ 51.332663] VF0-9 gim warning:(dump_function_state:259) Undefined, Marked as Not Runable
[ 51.332663] VF0-10 gim warning:(dump_function_state:259) Undefined, Marked as Not Runable
[ 51.332664] VF0-11 gim warning:(dump_function_state:259) Undefined, Marked as Not Runable
[ 51.332665] VF0-12 gim warning:(dump_function_state:259) Undefined, Marked as Not Runable
[ 51.332666] VF0-13 gim warning:(dump_function_state:259) Undefined, Marked as Not Runable
[ 51.332666] VF0-14 gim warning:(dump_function_state:259) Undefined, Marked as Not Runable
[ 51.332667] VF0-15 gim warning:(dump_function_state:259) Undefined, Marked as Not Runable
[ 51.332668] gim warning:(dump_gpu_status:1987) **** dump gpu status begin for Adapter 6:00.00
[ 51.332672] PF0 gim info:(check_base_addrs:1974) CP_MQD_BASE_ADDR = 0x0:00000000
[ 51.332700] gim warning:(dump_gpu_status:2029) mmGRBM_STATUS = 0x3028
[ 51.332701] gim warning:(dump_gpu_status:2032) mmGRBM_STATUS2 = 0x8
[ 51.332702] gim warning:(dump_gpu_status:2035) mmSRBM_STATUS = 0x20000040
[ 51.332704] gim warning:(dump_gpu_status:2038) mmSRBM_STATUS2 = 0x0
[ 51.332705] gim warning:(dump_gpu_status:2041) mmSDMA0_STATUS_REG = 0x46dee557
[ 51.332707] gim warning:(dump_gpu_status:2044) mmSDMA1_STATUS_REG = 0x46dee557
[ 51.332714] PF0 gim info:(check_ME_CNTL:1945) CP_ME_CNTL = 0x15000000 GPU dump
[ 51.332714] gim error:(check_ME_CNTL:1948) ME HALTED!
[ 51.332720] gim error:(check_ME_CNTL:1952) PFP HALTED!
[ 51.332726] gim error:(check_ME_CNTL:1956) CE HALTED!
[ 51.332735] gim warning:(dump_gpu_status:2209) **** dump gpu status end
[ 51.332736] gim error:(init_register_init_state:4643) Failed to INIT PF for initial register 'init-state'
[ 51.332737] PF0 gim info:(dump_pf_vm_regs:207) 0xf4000000 - HDP_NONSURFACE_BASE
[ 51.332748] PF0 gim info:(dump_pf_vm_regs:207) 0xf5fff400 - MC_VM_FB_LOCATION
[ 51.332749] PF0 gim info:(dump_pf_vm_regs:207) 0x00000000 - MC_VM_FB_OFFSET
[ 51.332751] PF0 gim info:(dump_pf_vm_regs:207) 0x0f5fffff - MC_VM_SYSTEM_APERTURE_HI
[ 51.332753] PF0 gim info:(dump_pf_vm_regs:207) 0x0f400000 - MC_VM_SYSTEM_APERTURE_LO
[ 51.332754] PF0 gim info:(dump_pf_vm_regs:207) 0x00000000 - MC_VM_SYSTEM_APERTURE_DEF
[ 51.332756] PF0 gim info:(dump_pf_vm_regs:207) 0x00000503 - MC_VM_MX_L1_TLB_CNTL
[ 51.332758] PF0 gim info:(dump_pf_vm_regs:207) 0x00000000 - RLC_GPU_IOV_ACTIVE_FCN_ID
[ 51.332759] PF0 gim info:(dump_pf_vm_regs:207) 0x00000000 - SMU_ACTIVE_FCN_ID
[ 51.332761] PF0 gim info:(dump_pf_vm_regs:207) 0x00000000 - IH_ACTIVE_FCN_ID
[ 51.332763] PF0 gim info:(dump_pf_vm_regs:207) 0x00000000 - MC_SHARED_ACTIVE_FCN_ID
[ 51.332764] PF0 gim info:(dump_pf_vm_regs:207) 0x00000000 - SDMA0_ACTIVE_FCN_ID
[ 51.332766] PF0 gim info:(dump_pf_vm_regs:207) 0x00000000 - SDMA1_ACTIVE_FCN_ID
[ 51.332768] PF0 gim info:(dump_pf_vm_regs:207) 0x00000000 - SEM_ACTIVE_FCN_ID
[ 51.332769] PF0 gim info:(dump_pf_vm_regs:207) 0x00000000 - VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDRESS
[ 51.332770] gim error:(SetNewAdapter:1359) Failed to init register state(ih) !!!!
[ 51.332778] PF0 gim info:(dump_pf_vm_regs:207) 0xf4000000 - HDP_NONSURFACE_BASE
[ 51.332780] PF0 gim info:(dump_pf_vm_regs:207) 0xf5fff400 - MC_VM_FB_LOCATION
[ 51.332782] PF0 gim info:(dump_pf_vm_regs:207) 0x00000000 - MC_VM_FB_OFFSET
[ 51.332783] PF0 gim info:(dump_pf_vm_regs:207) 0x0f5fffff - MC_VM_SYSTEM_APERTURE_HI
[ 51.332785] PF0 gim info:(dump_pf_vm_regs:207) 0x0f400000 - MC_VM_SYSTEM_APERTURE_LO
[ 51.332787] PF0 gim info:(dump_pf_vm_regs:207) 0x00000000 - MC_VM_SYSTEM_APERTURE_DEF
[ 51.332788] PF0 gim info:(dump_pf_vm_regs:207) 0x00000503 - MC_VM_MX_L1_TLB_CNTL
[ 51.332790] PF0 gim info:(dump_pf_vm_regs:207) 0x00000000 - RLC_GPU_IOV_ACTIVE_FCN_ID
[ 51.332791] PF0 gim info:(dump_pf_vm_regs:207) 0x00000000 - SMU_ACTIVE_FCN_ID
[ 51.332793] PF0 gim info:(dump_pf_vm_regs:207) 0x00000000 - IH_ACTIVE_FCN_ID
[ 51.332795] PF0 gim info:(dump_pf_vm_regs:207) 0x00000000 - MC_SHARED_ACTIVE_FCN_ID
[ 51.332796] PF0 gim info:(dump_pf_vm_regs:207) 0x00000000 - SDMA0_ACTIVE_FCN_ID
[ 51.332798] PF0 gim info:(dump_pf_vm_regs:207) 0x00000000 - SDMA1_ACTIVE_FCN_ID
[ 51.332800] PF0 gim info:(dump_pf_vm_regs:207) 0x00000000 - SEM_ACTIVE_FCN_ID
[ 51.332801] PF0 gim info:(dump_pf_vm_regs:207) 0x00000000 - VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDRESS
[ 51.332803] PF0 gim info:(ih_irq_source_disable:698) disabled irq sourceID 0x89
[ 51.332805] PF0 gim info:(ih_irq_source_disable:698) disabled irq sourceID 0x88
[ 51.332844] PF0 gim info:(free_iv_ring:307) unmap the iv ring
[ 51.332898] gim info:(DisableSriov:424) Disable SRIOV
[ 52.464755] gim error:(gim_probe:126) Failed to create new adapter
[ 52.464773] gim: probe of 0000:06:00.0 failed with error -1

0 Likes
6 Replies

AMD Forum's expert on Professional GPU cards, fsadough, might be able to assist you but you need to post your entire Computer information including all versions of Software and Windows being used for him to help.

0 Likes

elstacifsadough

  • HP ML350 G9
  • Gen10 Service Pack for ProLiant (SPP) Version 2020.03.2
  • Xenserver 8.2
  • Xencenter 8.2.0.7149
  • AMD FirePro S7150x2
  • AMD GIM v2.0 (dated 06/2020)

I cannot install any VMs, the hypervisor does not detect any VFs.

I can provide any other software versions you need, just tell me what you want

0 Likes

Thanks hopefully FSADOUGH, when he has the time, will reply and offer his assistance with your issue.

0 Likes

Have you contacted HPE? FirePro W7100 is the only certified card in your system.

pastedImage_1.png

Does this HPE Support page apply to his issue by any chance? Document Display | HPE Support Center 

AMD FirePro Accelerators for HPE ProLiant Servers - Overview

Product description

AMD server graphics and accelerators offer exceptional compute performance handling of a variety of workloads. Radeon instinctand AMD FirePro provide the general purpose compute needs in academic, government, energy, life science, and financialindustries. Radeon Pro WX graphics accelerators delivers advanced visualization and workstation workflows. Radeon instinctaccelerators provides the performance to support high performance compute workloads and industry leading frameworks likeTensorFlow, Caffe, PyTorch and others for machine

I got rid of Xen/Xenserver/xcp-ng since I could never get them to load the GIM 2.0 driver or see the VFs.  I installed VMware ESXi 7.0, installed the AMD VIB and everything worked right away...sort of.

Now, when I have SR-IOV enabled within vCenter and assign a MxGPU VF to a virtual machine, the mouse doesn't work, or the virtual machine won't accept mouse input.  It's strange behavior, and I cannot find any logs detailing why this might be happening.

fsadough‌ I know ESXi 7.0 is not officially supported, and I am happy to rollback to a supported version, but...have you ever seen the mouse issues?  If I could get this working in a stable manner I think I could convince several of my customers to adopt AMD GPUs.  The lack of required licenses (as opposed to NVIDIA GRID) is a killer advantage: some of these customers have hundreds of GPU-enabled servers.