cancel
Showing results for 
Search instead for 
Did you mean: 

Archives Discussions

yurtesen
Miniboss

OpenCL crash multiple devices after multiple kernel enqueues.

I am trying to run a multi-device program on HD 5870 and 7970 devices.

I tried it with single context multiple devices/queues, and multiple context a device/queue per context. Also both on Ubuntu 11 with kernel 3.0.x and Fedora 16 with kernel 3.3.x

The program divides the problem into small pieces, if global size was 1million, it divides it to 50k pieces and runs 0-50k, 50k-100k ... so instead of a single kernel enqueue between 1 and 1million, I do enqueue offset 0 size 50k, offset 50k, size 50k and so on... After several kernel enqueues, this error appears in dmesg and program freezes and I have to reboot the box...

The single context version works correctly on Nvidia with 2x Tesla cards.

Multiple context version does run on Nvidia platform but kernels just do not execute for some reason. (there might be a bug in my multi-context version, I am trying to debug it yet). But I guess I shouldnt have to make a multi-context program to use 2 GPGPUs...

Any ideas on how can I debug this further? (I use latest 12.4 catalyst and 2.6 app sdk)

[ 5545.593322] [fglrx] ASIC hang happened

[ 5545.593331] Pid: 5164, comm: reference Tainted: P           O 3.3.2-6.fc16.x86_64 #1

[ 5545.593337] Call Trace:

[ 5545.593420]  [<ffffffffa010bf9e>] KCL_DEBUG_OsDump+0xe/0x10 [fglrx]

[ 5545.593475]  [<ffffffffa01195cc>] firegl_hardwareHangRecovery+0x1c/0x50 [fglrx]

[ 5545.593584]  [<ffffffffa01b51d9>] ? _ZN4Asic9WaitUntil15ResetASICIfHungEv+0x9/0x10 [fglrx]

[ 5545.593691]  [<ffffffffa01b517c>] ? _ZN4Asic9WaitUntil15WaitForCompleteEv+0x9c/0xf0 [fglrx]

[ 5545.593798]  [<ffffffffa01aef41>] ? _ZN4Asic19PM4ElapsedTimeStampEj14_LARGE_INTEGER12_QS_CP_RING_+0x141/0x160 [fglrx]

[ 5545.593860]  [<ffffffffa01372a2>] ? firegl_trace+0x72/0x1e0 [fglrx]

[ 5545.593921]  [<ffffffffa01372a2>] ? firegl_trace+0x72/0x1e0 [fglrx]

[ 5545.593983]  [<ffffffffa01372a2>] ? firegl_trace+0x72/0x1e0 [fglrx]

[ 5545.594129]  [<ffffffffa01a5ce3>] ? _ZN15QS_PRIVATE_CORE27multiVpuPM4ElapsedTimeStampEj14_LARGE_INTEGER12_QS_CP_RING_+0x33/0x50 [fglrx]

[ 5545.594240]  [<ffffffffa019e4c4>] ? _Z19uQSTimeStampRetiredmjj14_LARGE_INTEGER+0x74/0x80 [fglrx]

[ 5545.594348]  [<ffffffffa019a34d>] ? _Z8uCWDDEQCmjjPvjS_+0x54d/0x10c0 [fglrx]

[ 5545.594367]  [<ffffffff8107fcee>] ? down+0x2e/0x50

[ 5545.594438]  [<ffffffffa0139baf>] ? firegl_cmmqs_CWDDE_32+0x36f/0x480 [fglrx]

[ 5545.594507]  [<ffffffffa013831e>] ? firegl_cmmqs_CWDDE32+0x6e/0x100 [fglrx]

[ 5545.594523]  [<ffffffff812692c8>] ? security_capable+0x18/0x20

[ 5545.594592]  [<ffffffffa01382b0>] ? firegl_cmmqs_createdriver+0x170/0x170 [fglrx]

[ 5545.594652]  [<ffffffffa01152ed>] ? firegl_ioctl+0x1ed/0x250 [fglrx]

[ 5545.594668]  [<ffffffff815f7c60>] ? do_page_fault+0x200/0x4f0

[ 5545.594720]  [<ffffffffa01059ae>] ? ip_firegl_unlocked_ioctl+0xe/0x20 [fglrx]

[ 5545.594735]  [<ffffffff81193228>] ? do_vfs_ioctl+0x98/0x550

[ 5545.594750]  [<ffffffff81193771>] ? sys_ioctl+0x91/0xa0

[ 5545.594764]  [<ffffffff815fc1e9>] ? system_call_fastpath+0x16/0x1b

[ 5545.594778] pubdev:0xffffffffa03b3320, num of device:2 , name:fglrx, major 8, minor 96.

[ 5545.594789] device 0 : 0xffff8804361ec000 .

[ 5545.594798] Asic ID:0x6898, revision:0x2, MMIOReg:0xffffc90012c00000.

[ 5545.594808] FB phys addr: 0xc0000000, MC :0xf00000000, Total FB size :0x80000000.

[ 5545.594819] gart table MC:0xf0f8fd000, Physical:0xcf8fd000, size:0x402000.

[ 5545.594829] mc_node :FB, total 1 zones

[ 5545.594837]     MC start:0xf00000000, Physical:0xc0000000, size:0xfd00000.

[ 5545.594848]     Mapped heap -- Offset:0x0, size:0xf8fd000, reference count:21, mapping count:0,

[ 5545.594859]     Mapped heap -- Offset:0x0, size:0x1000000, reference count:1, mapping count:0,

[ 5545.594869]     Mapped heap -- Offset:0xf8fd000, size:0x403000, reference count:1, mapping count:0,

[ 5545.594880] mc_node :INV_FB, total 1 zones

[ 5545.594891]     MC start:0xf0fd00000, Physical:0xcfd00000, size:0x70300000.

[ 5545.594901]     Mapped heap -- Offset:0x702f4000, size:0xc000, reference count:1, mapping count:0,

[ 5545.594912] mc_node :GART_USWC, total 3 zones

[ 5545.594920]     MC start:0x40100000, Physical:0x0, size:0x50000000.

[ 5545.594931]     Mapped heap -- Offset:0x0, size:0x2000000, reference count:17, mapping count:0,

[ 5545.594941] mc_node :GART_CACHEABLE, total 3 zones

[ 5545.594950]     MC start:0x10400000, Physical:0x0, size:0x2fd00000.

[ 5545.594960]     Mapped heap -- Offset:0x1400000, size:0x100000, reference count:2, mapping count:0,

[ 5545.594972]     Mapped heap -- Offset:0x2600000, size:0x900000, reference count:2, mapping count:0,

[ 5545.594982]     Mapped heap -- Offset:0xb00000, size:0x900000, reference count:2, mapping count:0,

[ 5545.594994]     Mapped heap -- Offset:0x200000, size:0x900000, reference count:3, mapping count:0,

[ 5545.595014]     Mapped heap -- Offset:0x0, size:0x200000, reference count:4, mapping count:0,

[ 5545.595026]     Mapped heap -- Offset:0xef000, size:0x11000, reference count:1, mapping count:0,

[ 5545.595038] GRBM : 0xa0635028, SRBM : 0x200000c0 .

[ 5545.595049] CP_RB_BASE : 0x401000, CP_RB_RPTR : 0x9a70 , CP_RB_WPTR :0x9a70.

[ 5545.595061] CP_IB1_BUFSZ:0x0, CP_IB1_BASE_HI:0x0, CP_IB1_BASE_LO:0x4023b000.

[ 5545.595071] last submit IB buffer -- MC :0x4023b000,phys:0x422fb3000.

[ 5545.595086] device 1 : 0xffff880436134000 .

[ 5545.595095] Asic ID:0x6798, revision:0x5, MMIOReg:0xffffc90012c80000.

[ 5545.595104] FB phys addr: 0xb0000000, MC :0xf400000000, Total FB size :0xc0000000.

[ 5545.595114] gart table MC:0xf40f8fd000, Physical:0xbf8fd000, size:0x402000.

[ 5545.595124] mc_node :FB, total 1 zones

[ 5545.595133]     MC start:0xf400000000, Physical:0xb0000000, size:0xfd00000.

[ 5545.595143]     Mapped heap -- Offset:0x0, size:0xf8fd000, reference count:21, mapping count:0,

[ 5545.595154]     Mapped heap -- Offset:0x0, size:0x1000000, reference count:1, mapping count:0,

[ 5545.595164]     Mapped heap -- Offset:0xf8fd000, size:0x403000, reference count:1, mapping count:0,

[ 5545.595174] mc_node :INV_FB, total 1 zones

[ 5545.595183]     MC start:0xf40fd00000, Physical:0xbfd00000, size:0xb0300000.

[ 5545.595193]     Mapped heap -- Offset:0xb02f4000, size:0xc000, reference count:1, mapping count:0,

[ 5545.595203] mc_node :GART_USWC, total 3 zones

[ 5545.595212]     MC start:0xffa0100000, Physical:0x0, size:0x50000000.

[ 5545.595222]     Mapped heap -- Offset:0x0, size:0x2000000, reference count:16, mapping count:0,

[ 5545.595232] mc_node :GART_CACHEABLE, total 3 zones

[ 5545.595241]     MC start:0xff70400000, Physical:0x0, size:0x2fd00000.

[ 5545.595251]     Mapped heap -- Offset:0x2600000, size:0x900000, reference count:2, mapping count:0,

[ 5545.595262]     Mapped heap -- Offset:0x1d00000, size:0x900000, reference count:3, mapping count:0,

[ 5545.595273]     Mapped heap -- Offset:0xb00000, size:0x900000, reference count:2, mapping count:0,

[ 5545.595284]     Mapped heap -- Offset:0x200000, size:0x900000, reference count:3, mapping count:0,

[ 5545.595294]     Mapped heap -- Offset:0x0, size:0x200000, reference count:4, mapping count:0,

[ 5545.595304]     Mapped heap -- Offset:0xef000, size:0x11000, reference count:1, mapping count:0,

[ 5545.595316] GRBM : 0xa04c7028, SRBM : 0x200000c0 .

[ 5545.595327] CP_RB_BASE : 0xffa01000, CP_RB_RPTR : 0x5180 , CP_RB_WPTR :0x5180.

[ 5545.595338] CP_IB1_BUFSZ:0x0, CP_IB1_BASE_HI:0xff, CP_IB1_BASE_LO:0xa054e000.

[ 5545.595348] last submit IB buffer -- MC :0xffa054e000,phys:0x420590000.

[ 5545.595363] Dump the trace queue.

[ 5545.595371] End of dump

[ 5579.462541] [fglrx] ASIC hang happened

[ 5579.462550] Pid: 5163, comm: reference Tainted: P           O 3.3.2-6.fc16.x86_64 #1

[ 5579.462556] Call Trace:

[ 5579.462639]  [<ffffffffa010bf9e>] KCL_DEBUG_OsDump+0xe/0x10 [fglrx]

[ 5579.462694]  [<ffffffffa01195cc>] firegl_hardwareHangRecovery+0x1c/0x50 [fglrx]

[ 5579.462803]  [<ffffffffa01b51d9>] ? _ZN4Asic9WaitUntil15ResetASICIfHungEv+0x9/0x10 [fglrx]

[ 5579.462910]  [<ffffffffa01b517c>] ? _ZN4Asic9WaitUntil15WaitForCompleteEv+0x9c/0xf0 [fglrx]

[ 5579.463016]  [<ffffffffa01aef41>] ? _ZN4Asic19PM4ElapsedTimeStampEj14_LARGE_INTEGER12_QS_CP_RING_+0x141/0x160 [fglrx]

[ 5579.463131]  [<ffffffffa01372a2>] ? firegl_trace+0x72/0x1e0 [fglrx]

[ 5579.463200]  [<ffffffffa01372a2>] ? firegl_trace+0x72/0x1e0 [fglrx]

[ 5579.463271]  [<ffffffffa01372a2>] ? firegl_trace+0x72/0x1e0 [fglrx]

[ 5579.463391]  [<ffffffffa01a5ce3>] ? _ZN15QS_PRIVATE_CORE27multiVpuPM4ElapsedTimeStampEj14_LARGE_INTEGER12_QS_CP_RING_+0x33/0x50 [fglrx]

[ 5579.463501]  [<ffffffffa019e4c4>] ? _Z19uQSTimeStampRetiredmjj14_LARGE_INTEGER+0x74/0x80 [fglrx]

[ 5579.463609]  [<ffffffffa019a34d>] ? _Z8uCWDDEQCmjjPvjS_+0x54d/0x10c0 [fglrx]

[ 5579.463627]  [<ffffffff8107fcee>] ? down+0x2e/0x50

[ 5579.463696]  [<ffffffffa0139baf>] ? firegl_cmmqs_CWDDE_32+0x36f/0x480 [fglrx]

[ 5579.463766]  [<ffffffffa013831e>] ? firegl_cmmqs_CWDDE32+0x6e/0x100 [fglrx]

[ 5579.463782]  [<ffffffff812692c8>] ? security_capable+0x18/0x20

[ 5579.463850]  [<ffffffffa01382b0>] ? firegl_cmmqs_createdriver+0x170/0x170 [fglrx]

[ 5579.463910]  [<ffffffffa01152ed>] ? firegl_ioctl+0x1ed/0x250 [fglrx]

[ 5579.463925]  [<ffffffff815f7c60>] ? do_page_fault+0x200/0x4f0

[ 5579.463976]  [<ffffffffa01059ae>] ? ip_firegl_unlocked_ioctl+0xe/0x20 [fglrx]

[ 5579.463992]  [<ffffffff81193228>] ? do_vfs_ioctl+0x98/0x550

[ 5579.464012]  [<ffffffff81193771>] ? sys_ioctl+0x91/0xa0

[ 5579.464020]  [<ffffffff815fc1e9>] ? system_call_fastpath+0x16/0x1b

[ 5579.464032] pubdev:0xffffffffa03b3320, num of device:2 , name:fglrx, major 8, minor 96.

[ 5579.464043] device 0 : 0xffff8804361ec000 .

[ 5579.464052] Asic ID:0x6898, revision:0x2, MMIOReg:0xffffc90012c00000.

[ 5579.464061] FB phys addr: 0xc0000000, MC :0xf00000000, Total FB size :0x80000000.

[ 5579.464072] gart table MC:0xf0f8fd000, Physical:0xcf8fd000, size:0x402000.

[ 5579.464083] mc_node :FB, total 1 zones

[ 5579.464092]     MC start:0xf00000000, Physical:0xc0000000, size:0xfd00000.

[ 5579.464102]     Mapped heap -- Offset:0x0, size:0xf8fd000, reference count:21, mapping count:0,

[ 5579.464112]     Mapped heap -- Offset:0x0, size:0x1000000, reference count:1, mapping count:0,

[ 5579.464123]     Mapped heap -- Offset:0xf8fd000, size:0x403000, reference count:1, mapping count:0,

[ 5579.464134] mc_node :INV_FB, total 1 zones

[ 5579.464143]     MC start:0xf0fd00000, Physical:0xcfd00000, size:0x70300000.

[ 5579.464154]     Mapped heap -- Offset:0x702f4000, size:0xc000, reference count:1, mapping count:0,

[ 5579.464164] mc_node :GART_USWC, total 3 zones

[ 5579.464173]     MC start:0x40100000, Physical:0x0, size:0x50000000.

[ 5579.464183]     Mapped heap -- Offset:0x0, size:0x2000000, reference count:17, mapping count:0,

[ 5579.464194] mc_node :GART_CACHEABLE, total 3 zones

[ 5579.464202]     MC start:0x10400000, Physical:0x0, size:0x2fd00000.

[ 5579.464212]     Mapped heap -- Offset:0x1400000, size:0x100000, reference count:2, mapping count:0,

[ 5579.464224]     Mapped heap -- Offset:0x2600000, size:0x900000, reference count:2, mapping count:0,

[ 5579.464234]     Mapped heap -- Offset:0xb00000, size:0x900000, reference count:2, mapping count:0,

[ 5579.464247]     Mapped heap -- Offset:0x200000, size:0x900000, reference count:3, mapping count:0,

[ 5579.464258]     Mapped heap -- Offset:0x0, size:0x200000, reference count:4, mapping count:0,

[ 5579.464269]     Mapped heap -- Offset:0xef000, size:0x11000, reference count:1, mapping count:0,

[ 5579.464281] GRBM : 0xe0735828, SRBM : 0x200000c0 .

[ 5579.464291] CP_RB_BASE : 0x401000, CP_RB_RPTR : 0x9ab0 , CP_RB_WPTR :0x9ab0.

[ 5579.464302] CP_IB1_BUFSZ:0x0, CP_IB1_BASE_HI:0x0, CP_IB1_BASE_LO:0x4023d000.

[ 5579.464313] last submit IB buffer -- MC :0x4023d000,phys:0x422fb5000.

[ 5579.464329] device 1 : 0xffff880436134000 .

[ 5579.464339] Asic ID:0x6798, revision:0x5, MMIOReg:0xffffc90012c80000.

[ 5579.464348] FB phys addr: 0xb0000000, MC :0xf400000000, Total FB size :0xc0000000.

[ 5579.464359] gart table MC:0xf40f8fd000, Physical:0xbf8fd000, size:0x402000.

[ 5579.464369] mc_node :FB, total 1 zones

[ 5579.464377]     MC start:0xf400000000, Physical:0xb0000000, size:0xfd00000.

[ 5579.464388]     Mapped heap -- Offset:0x0, size:0xf8fd000, reference count:21, mapping count:0,

[ 5579.464399]     Mapped heap -- Offset:0x0, size:0x1000000, reference count:1, mapping count:0,

[ 5579.464410]     Mapped heap -- Offset:0xf8fd000, size:0x403000, reference count:1, mapping count:0,

[ 5579.464421] mc_node :INV_FB, total 1 zones

[ 5579.464430]     MC start:0xf40fd00000, Physical:0xbfd00000, size:0xb0300000.

[ 5579.464441]     Mapped heap -- Offset:0xb02f4000, size:0xc000, reference count:1, mapping count:0,

[ 5579.464452] mc_node :GART_USWC, total 3 zones

[ 5579.464460]     MC start:0xffa0100000, Physical:0x0, size:0x50000000.

[ 5579.464470]     Mapped heap -- Offset:0x0, size:0x2000000, reference count:16, mapping count:0,

[ 5579.464480] mc_node :GART_CACHEABLE, total 3 zones

[ 5579.464489]     MC start:0xff70400000, Physical:0x0, size:0x2fd00000.

[ 5579.464499]     Mapped heap -- Offset:0x2600000, size:0x900000, reference count:2, mapping count:0,

[ 5579.464510]     Mapped heap -- Offset:0x1d00000, size:0x900000, reference count:3, mapping count:0,

[ 5579.464521]     Mapped heap -- Offset:0xb00000, size:0x900000, reference count:2, mapping count:0,

[ 5579.464532]     Mapped heap -- Offset:0x200000, size:0x900000, reference count:3, mapping count:0,

[ 5579.464543]     Mapped heap -- Offset:0x0, size:0x200000, reference count:4, mapping count:0,

[ 5579.464554]     Mapped heap -- Offset:0xef000, size:0x11000, reference count:1, mapping count:0,

[ 5579.464565] GRBM : 0xa0407028, SRBM : 0x200000c0 .

[ 5579.464576] CP_RB_BASE : 0xffa01000, CP_RB_RPTR : 0x5180 , CP_RB_WPTR :0x5180.

[ 5579.464587] CP_IB1_BUFSZ:0x0, CP_IB1_BASE_HI:0xff, CP_IB1_BASE_LO:0xa054e000.

[ 5579.464597] last submit IB buffer -- MC :0xffa054e000,phys:0x420590000.

[ 5579.464611] Dump the trace queue.

[ 5579.464619] End of dump

0 Likes
4 Replies
yurtesen
Miniboss

I made changes in my code so I can now select Cypress or Tahiti when running the program. It functions fine on Cypress with several kernel enqueues. On Tahiti it does crash after few enqueues... so what can you suggest? this looks like a bug?

0 Likes

Hi yurtesen,

There may be something wrong in the code.

I think you can comment some code of your kernel and test it reppetitively untill you find the reason caused the crash.


Thanks

0 Likes

Doing that wouldnt necessarily mean that there is something wrong in the code. I have a completely different algorithm which runs on the same data and it also crashes.

The code works fine on cypress, on both intel and amd SDKs on CPUs and on nvidia cards and gives consistently same results. It only fails on tahiti...

I will try to debug the issue further... It is not very easy to debug unfortunately...

0 Likes
yurtesen
Miniboss

APP SDK 2.7 still crashes...

[ 3180.358015] [fglrx] ASIC hang happened

[ 3180.358024] Pid: 6388, comm: reference Tainted: P           O 3.3.5-2.fc16.x86_64 #1

[ 3180.358035] Call Trace:

[ 3180.358119]  [<ffffffffa023ff9e>] KCL_DEBUG_OsDump+0xe/0x10 [fglrx]

[ 3180.358174]  [<ffffffffa024d5cc>] firegl_hardwareHangRecovery+0x1c/0x50 [fglrx]

[ 3180.358284]  [<ffffffffa02e91d9>] ? _ZN4Asic9WaitUntil15ResetASICIfHungEv+0x9/0x10 [fglrx]

[ 3180.358392]  [<ffffffffa02e917c>] ? _ZN4Asic9WaitUntil15WaitForCompleteEv+0x9c/0xf0 [fglrx]

[ 3180.358499]  [<ffffffffa02e2f41>] ? _ZN4Asic19PM4ElapsedTimeStampEj14_LARGE_INTEGER12_QS_CP_RING_+0x141/0x160 [fglrx]

[ 3180.358563]  [<ffffffffa026b2a2>] ? firegl_trace+0x72/0x1e0 [fglrx]

[ 3180.358624]  [<ffffffffa026b2a2>] ? firegl_trace+0x72/0x1e0 [fglrx]

[ 3180.358687]  [<ffffffffa026b2a2>] ? firegl_trace+0x72/0x1e0 [fglrx]

[ 3180.358805]  [<ffffffffa02d9ce3>] ? _ZN15QS_PRIVATE_CORE27multiVpuPM4ElapsedTimeStampEj14_LARGE_INTEGER12_QS_CP_RING_+0x33/0x50 [fglrx]

[ 3180.358909]  [<ffffffffa02d24c4>] ? _Z19uQSTimeStampRetiredmjj14_LARGE_INTEGER+0x74/0x80 [fglrx]

[ 3180.359002]  [<ffffffffa02ce34d>] ? _Z8uCWDDEQCmjjPvjS_+0x54d/0x10c0 [fglrx]

[ 3180.359045]  [<ffffffff8107fcce>] ? down+0x2e/0x50

[ 3180.359108]  [<ffffffffa026dbaf>] ? firegl_cmmqs_CWDDE_32+0x36f/0x480 [fglrx]

[ 3180.359178]  [<ffffffffa026c31e>] ? firegl_cmmqs_CWDDE32+0x6e/0x100 [fglrx]

[ 3180.359195]  [<ffffffff81268f88>] ? security_capable+0x18/0x20

[ 3180.359265]  [<ffffffffa026c2b0>] ? firegl_cmmqs_createdriver+0x170/0x170 [fglrx]

[ 3180.359324]  [<ffffffffa02492ed>] ? firegl_ioctl+0x1ed/0x250 [fglrx]

[ 3180.359341]  [<ffffffff815f7d60>] ? do_page_fault+0x200/0x4f0

[ 3180.359394]  [<ffffffffa02399ae>] ? ip_firegl_unlocked_ioctl+0xe/0x20 [fglrx]

[ 3180.359409]  [<ffffffff81192fb8>] ? do_vfs_ioctl+0x98/0x550

[ 3180.359423]  [<ffffffff81193501>] ? sys_ioctl+0x91/0xa0

[ 3180.359437]  [<ffffffff815fc2e9>] ? system_call_fastpath+0x16/0x1b

[ 3180.359450] pubdev:0xffffffffa04e7320, num of device:2 , name:fglrx, major 8, minor 96.

[ 3180.359461] device 0 : 0xffff880436b20000 .

[ 3180.359471] Asic ID:0x6898, revision:0x2, MMIOReg:0xffffc90012c00000.

[ 3180.359482] FB phys addr: 0xc0000000, MC :0xf00000000, Total FB size :0x80000000.

[ 3180.359492] gart table MC:0xf0f8fd000, Physical:0xcf8fd000, size:0x402000.

[ 3180.359503] mc_node :FB, total 1 zones

[ 3180.359511]     MC start:0xf00000000, Physical:0xc0000000, size:0xfd00000.

[ 3180.359522]     Mapped heap -- Offset:0x0, size:0xf8fd000, reference count:22, mapping count:0,

[ 3180.359533]     Mapped heap -- Offset:0x0, size:0x1000000, reference count:1, mapping count:0,

[ 3180.359544]     Mapped heap -- Offset:0xf8fd000, size:0x403000, reference count:1, mapping count:0,

[ 3180.359553] mc_node :INV_FB, total 1 zones

[ 3180.359562]     MC start:0xf0fd00000, Physical:0xcfd00000, size:0x70300000.

[ 3180.359572]     Mapped heap -- Offset:0x702f4000, size:0xc000, reference count:1, mapping count:0,

[ 3180.359583] mc_node :GART_USWC, total 3 zones

[ 3180.359592]     MC start:0x40100000, Physical:0x0, size:0x50000000.

[ 3180.359602]     Mapped heap -- Offset:0x0, size:0x2000000, reference count:17, mapping count:0,

[ 3180.359613] mc_node :GART_CACHEABLE, total 3 zones

[ 3180.359622]     MC start:0x10400000, Physical:0x0, size:0x2fd00000.

[ 3180.359632]     Mapped heap -- Offset:0x2f00000, size:0x1100000, reference count:1, mapping count:0,

[ 3180.359643]     Mapped heap -- Offset:0x1500000, size:0x100000, reference count:2, mapping count:0,

[ 3180.359654]     Mapped heap -- Offset:0x1400000, size:0x100000, reference count:1, mapping count:0,

[ 3180.359666]     Mapped heap -- Offset:0x2600000, size:0x900000, reference count:2, mapping count:0,

[ 3180.359678]     Mapped heap -- Offset:0xb00000, size:0x900000, reference count:3, mapping count:0,

[ 3180.359689]     Mapped heap -- Offset:0x200000, size:0x900000, reference count:2, mapping count:0,

[ 3180.359700]     Mapped heap -- Offset:0x0, size:0x200000, reference count:6, mapping count:0,

[ 3180.359711]     Mapped heap -- Offset:0xef000, size:0x11000, reference count:1, mapping count:0,

[ 3180.359723] GRBM : 0xa0635028, SRBM : 0x200000c0 .

[ 3180.359734] CP_RB_BASE : 0x401000, CP_RB_RPTR : 0xdfa0 , CP_RB_WPTR :0xdfa0.

[ 3180.359746] CP_IB1_BUFSZ:0x0, CP_IB1_BASE_HI:0x0, CP_IB1_BASE_LO:0x4034a000.

[ 3180.359756] last submit IB buffer -- MC :0x4034a000,phys:0x4220b6000.

[ 3180.359771] device 1 : 0xffff880436cd0000 .

[ 3180.359780] Asic ID:0x6798, revision:0x5, MMIOReg:0xffffc90012c80000.

[ 3180.359790] FB phys addr: 0xb0000000, MC :0xf400000000, Total FB size :0xc0000000.

[ 3180.359801] gart table MC:0xf40f8fd000, Physical:0xbf8fd000, size:0x402000.

[ 3180.359810] mc_node :FB, total 1 zones

[ 3180.359819]     MC start:0xf400000000, Physical:0xb0000000, size:0xfd00000.

[ 3180.359829]     Mapped heap -- Offset:0x0, size:0xf8fd000, reference count:21, mapping count:0,

[ 3180.359840]     Mapped heap -- Offset:0x0, size:0x1000000, reference count:1, mapping count:0,

[ 3180.359851]     Mapped heap -- Offset:0xf8fd000, size:0x403000, reference count:1, mapping count:0,

[ 3180.359862] mc_node :INV_FB, total 1 zones

[ 3180.359871]     MC start:0xf40fd00000, Physical:0xbfd00000, size:0xb0300000.

[ 3180.359881]     Mapped heap -- Offset:0xb02f4000, size:0xc000, reference count:1, mapping count:0,

[ 3180.359891] mc_node :GART_USWC, total 3 zones

[ 3180.359900]     MC start:0xffa0100000, Physical:0x0, size:0x50000000.

[ 3180.359910]     Mapped heap -- Offset:0x0, size:0x2000000, reference count:16, mapping count:0,

[ 3180.359920] mc_node :GART_CACHEABLE, total 3 zones

[ 3180.359929]     MC start:0xff70400000, Physical:0x0, size:0x2fd00000.

[ 3180.359939]     Mapped heap -- Offset:0x2f00000, size:0x1100000, reference count:1, mapping count:0,

[ 3180.359949]     Mapped heap -- Offset:0x2600000, size:0x900000, reference count:2, mapping count:0,

[ 3180.359961]     Mapped heap -- Offset:0x1d00000, size:0x900000, reference count:3, mapping count:0,

[ 3180.359972]     Mapped heap -- Offset:0xb00000, size:0x900000, reference count:2, mapping count:0,

[ 3180.359983]     Mapped heap -- Offset:0x200000, size:0x900000, reference count:3, mapping count:0,

[ 3180.359995]     Mapped heap -- Offset:0x0, size:0x200000, reference count:4, mapping count:0,

[ 3180.360010]     Mapped heap -- Offset:0xef000, size:0x11000, reference count:1, mapping count:0,

[ 3180.360017] GRBM : 0xa04c7028, SRBM : 0x20000fc0 .

[ 3180.360023] CP_RB_BASE : 0xffa01000, CP_RB_RPTR : 0xedd0 , CP_RB_WPTR :0xedd0.

[ 3180.360030] CP_IB1_BUFSZ:0x0, CP_IB1_BASE_HI:0xff, CP_IB1_BASE_LO:0xa083b000.

[ 3180.360035] last submit IB buffer -- MC :0xffa083b000,phys:0x41e0f8000.

[ 3180.360051] Dump the trace queue.

[ 3180.360058] End of dump

[ 3197.866847] [fglrx] ASIC hang happened

[ 3197.866852] Pid: 6387, comm: reference Tainted: P           O 3.3.5-2.fc16.x86_64 #1

[ 3197.866854] Call Trace:

[ 3197.866905]  [<ffffffffa023ff9e>] KCL_DEBUG_OsDump+0xe/0x10 [fglrx]

[ 3197.866931]  [<ffffffffa024d5cc>] firegl_hardwareHangRecovery+0x1c/0x50 [fglrx]

[ 3197.866979]  [<ffffffffa02e91d9>] ? _ZN4Asic9WaitUntil15ResetASICIfHungEv+0x9/0x10 [fglrx]

[ 3197.867027]  [<ffffffffa02e917c>] ? _ZN4Asic9WaitUntil15WaitForCompleteEv+0x9c/0xf0 [fglrx]

[ 3197.867086]  [<ffffffffa02e2f41>] ? _ZN4Asic19PM4ElapsedTimeStampEj14_LARGE_INTEGER12_QS_CP_RING_+0x141/0x160 [fglrx]

[ 3197.867118]  [<ffffffffa026b2a2>] ? firegl_trace+0x72/0x1e0 [fglrx]

[ 3197.867148]  [<ffffffffa026b2a2>] ? firegl_trace+0x72/0x1e0 [fglrx]

[ 3197.867180]  [<ffffffffa026b2a2>] ? firegl_trace+0x72/0x1e0 [fglrx]

[ 3197.867237]  [<ffffffffa02d9ce3>] ? _ZN15QS_PRIVATE_CORE27multiVpuPM4ElapsedTimeStampEj14_LARGE_INTEGER12_QS_CP_RING_+0x33/0x50 [fglrx]

[ 3197.867286]  [<ffffffffa02d24c4>] ? _Z19uQSTimeStampRetiredmjj14_LARGE_INTEGER+0x74/0x80 [fglrx]

[ 3197.867333]  [<ffffffffa02ce34d>] ? _Z8uCWDDEQCmjjPvjS_+0x54d/0x10c0 [fglrx]

[ 3197.867342]  [<ffffffff8107fcce>] ? down+0x2e/0x50

[ 3197.867373]  [<ffffffffa026dbaf>] ? firegl_cmmqs_CWDDE_32+0x36f/0x480 [fglrx]

[ 3197.867404]  [<ffffffffa026c31e>] ? firegl_cmmqs_CWDDE32+0x6e/0x100 [fglrx]

[ 3197.867412]  [<ffffffff81268f88>] ? security_capable+0x18/0x20

[ 3197.867443]  [<ffffffffa026c2b0>] ? firegl_cmmqs_createdriver+0x170/0x170 [fglrx]

[ 3197.867470]  [<ffffffffa02492ed>] ? firegl_ioctl+0x1ed/0x250 [fglrx]

[ 3197.867477]  [<ffffffff815f7d60>] ? do_page_fault+0x200/0x4f0

[ 3197.867501]  [<ffffffffa02399ae>] ? ip_firegl_unlocked_ioctl+0xe/0x20 [fglrx]

[ 3197.867508]  [<ffffffff81192fb8>] ? do_vfs_ioctl+0x98/0x550

[ 3197.867515]  [<ffffffff81193501>] ? sys_ioctl+0x91/0xa0

[ 3197.867522]  [<ffffffff815fc2e9>] ? system_call_fastpath+0x16/0x1b

[ 3197.867527] pubdev:0xffffffffa04e7320, num of device:2 , name:fglrx, major 8, minor 96.

[ 3197.867533] device 0 : 0xffff880436b20000 .

[ 3197.867537] Asic ID:0x6898, revision:0x2, MMIOReg:0xffffc90012c00000.

[ 3197.867541] FB phys addr: 0xc0000000, MC :0xf00000000, Total FB size :0x80000000.

[ 3197.867546] gart table MC:0xf0f8fd000, Physical:0xcf8fd000, size:0x402000.

[ 3197.867551] mc_node :FB, total 1 zones

[ 3197.867556]     MC start:0xf00000000, Physical:0xc0000000, size:0xfd00000.

[ 3197.867561]     Mapped heap -- Offset:0x0, size:0xf8fd000, reference count:22, mapping count:0,

[ 3197.867566]     Mapped heap -- Offset:0x0, size:0x1000000, reference count:1, mapping count:0,

[ 3197.867571]     Mapped heap -- Offset:0xf8fd000, size:0x403000, reference count:1, mapping count:0,

[ 3197.867575] mc_node :INV_FB, total 1 zones

[ 3197.867579]     MC start:0xf0fd00000, Physical:0xcfd00000, size:0x70300000.

[ 3197.867583]     Mapped heap -- Offset:0x702f4000, size:0xc000, reference count:1, mapping count:0,

[ 3197.867588] mc_node :GART_USWC, total 3 zones

[ 3197.867592]     MC start:0x40100000, Physical:0x0, size:0x50000000.

[ 3197.867596]     Mapped heap -- Offset:0x0, size:0x2000000, reference count:17, mapping count:0,

[ 3197.867601] mc_node :GART_CACHEABLE, total 3 zones

[ 3197.867605]     MC start:0x10400000, Physical:0x0, size:0x2fd00000.

[ 3197.867609]     Mapped heap -- Offset:0x2f00000, size:0x1100000, reference count:1, mapping count:0,

[ 3197.867614]     Mapped heap -- Offset:0x1500000, size:0x100000, reference count:2, mapping count:0,

[ 3197.867618]     Mapped heap -- Offset:0x1400000, size:0x100000, reference count:1, mapping count:0,

[ 3197.867624]     Mapped heap -- Offset:0x2600000, size:0x900000, reference count:2, mapping count:0,

[ 3197.867628]     Mapped heap -- Offset:0xb00000, size:0x900000, reference count:3, mapping count:0,

[ 3197.867633]     Mapped heap -- Offset:0x200000, size:0x900000, reference count:2, mapping count:0,

[ 3197.867638]     Mapped heap -- Offset:0x0, size:0x200000, reference count:6, mapping count:0,

[ 3197.867643]     Mapped heap -- Offset:0xef000, size:0x11000, reference count:1, mapping count:0,

[ 3197.867649] GRBM : 0xa0637828, SRBM : 0x20000cc0 .

[ 3197.867654] CP_RB_BASE : 0x401000, CP_RB_RPTR : 0xdfe0 , CP_RB_WPTR :0xdfe0.

[ 3197.867660] CP_IB1_BUFSZ:0x0, CP_IB1_BASE_HI:0x0, CP_IB1_BASE_LO:0x4034c000.

[ 3197.867664] last submit IB buffer -- MC :0x4034c000,phys:0x4220b8000.

[ 3197.867671] device 1 : 0xffff880436cd0000 .

[ 3197.867675] Asic ID:0x6798, revision:0x5, MMIOReg:0xffffc90012c80000.

[ 3197.867680] FB phys addr: 0xb0000000, MC :0xf400000000, Total FB size :0xc0000000.

[ 3197.867684] gart table MC:0xf40f8fd000, Physical:0xbf8fd000, size:0x402000.

[ 3197.867689] mc_node :FB, total 1 zones

[ 3197.867692]     MC start:0xf400000000, Physical:0xb0000000, size:0xfd00000.

[ 3197.867697]     Mapped heap -- Offset:0x0, size:0xf8fd000, reference count:21, mapping count:0,

[ 3197.867702]     Mapped heap -- Offset:0x0, size:0x1000000, reference count:1, mapping count:0,

[ 3197.867707]     Mapped heap -- Offset:0xf8fd000, size:0x403000, reference count:1, mapping count:0,

[ 3197.867712] mc_node :INV_FB, total 1 zones

[ 3197.867715]     MC start:0xf40fd00000, Physical:0xbfd00000, size:0xb0300000.

[ 3197.867720]     Mapped heap -- Offset:0xb02f4000, size:0xc000, reference count:1, mapping count:0,

[ 3197.867724] mc_node :GART_USWC, total 3 zones

[ 3197.867728]     MC start:0xffa0100000, Physical:0x0, size:0x50000000.

[ 3197.867732]     Mapped heap -- Offset:0x0, size:0x2000000, reference count:16, mapping count:0,

[ 3197.867737] mc_node :GART_CACHEABLE, total 3 zones

[ 3197.867740]     MC start:0xff70400000, Physical:0x0, size:0x2fd00000.

[ 3197.867745]     Mapped heap -- Offset:0x2f00000, size:0x1100000, reference count:1, mapping count:0,

[ 3197.867750]     Mapped heap -- Offset:0x2600000, size:0x900000, reference count:2, mapping count:0,

[ 3197.867755]     Mapped heap -- Offset:0x1d00000, size:0x900000, reference count:3, mapping count:0,

[ 3197.867760]     Mapped heap -- Offset:0xb00000, size:0x900000, reference count:2, mapping count:0,

[ 3197.867764]     Mapped heap -- Offset:0x200000, size:0x900000, reference count:3, mapping count:0,

[ 3197.867769]     Mapped heap -- Offset:0x0, size:0x200000, reference count:4, mapping count:0,

[ 3197.867774]     Mapped heap -- Offset:0xef000, size:0x11000, reference count:1, mapping count:0,

[ 3197.867780] GRBM : 0xa0407028, SRBM : 0x200000c0 .

[ 3197.867786] CP_RB_BASE : 0xffa01000, CP_RB_RPTR : 0xedd0 , CP_RB_WPTR :0xedd0.

[ 3197.867792] CP_IB1_BUFSZ:0x0, CP_IB1_BASE_HI:0xff, CP_IB1_BASE_LO:0xa083b000.

[ 3197.867796] last submit IB buffer -- MC :0xffa083b000,phys:0x41e0f8000.

[ 3197.867803] Dump the trace queue.

[ 3197.867806] End of dump

0 Likes