aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd
AgeCommit message (Collapse)AuthorFilesLines
2017-04-28drm/amdgpu/uvd7: add uvd doorbell initialization for sriovFrank Min1-0/+14
Add UVD doorbell for SRIOV. Signed-off-by: Frank Min <[email protected]> Signed-off-by: Xiangliang Yu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu/uvd7: add sriov uvd initialization sequencesFrank Min1-0/+246
Add UVD initialization for SRIOV. Signed-off-by: Frank Min <[email protected]> Signed-off-by: Xiangliang Yu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu/vce4: replaced with virt_alloc_mm_tableXiangliang Yu1-17/+3
Used virt_alloc_mm_table function to allocate MM table memory. Signed-off-by: Xiangliang Yu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu/virt: add two functions for MM tableXiangliang Yu2-0/+48
Add two functions to allocate & free MM table memory. Signed-off-by: Xiangliang Yu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu/vce4: move mm table constructions functions into mmsch header fileFrank Min2-97/+103
Move mm table construction functions into mmsch header file so that UVD can reuse it. Signed-off-by: Frank Min <[email protected]> Signed-off-by: Xiangliang Yu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu/vce4: fix a PSP loading VCE issueDaniel Wang1-3/+15
Fixed PSP loading issue for sriov. Signed-off-by: Daniel Wang <[email protected]> Signed-off-by: Xiangliang Yu <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu/psp: skip loading SDMA/RLCG under SRIOV VFDaniel Wang1-0/+6
Now GPU hypervisor will load SDMA and RLCG ucode, so skip it in guest. Signed-off-by: Daniel Wang <[email protected]> Signed-off-by: Xiangliang Yu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu: fix gpu reset crashChunming Zhou1-3/+4
[ 413.687439] BUG: unable to handle kernel NULL pointer dereference at 0000000000000548 [ 413.687479] IP: [<ffffffff8109b175>] to_live_kthread+0x5/0x60 [ 413.687507] PGD 1efd12067 [ 413.687519] PUD 1efd11067 [ 413.687531] PMD 0 [ 413.687543] Oops: 0000 [#1] SMP [ 413.687557] Modules linked in: amdgpu(OE) ttm(OE) drm_kms_helper(E) drm(E) i2c_algo_bit(E) fb_sys_fops(E) syscopyarea(E) sysfillrect(E) sysimgblt(E) rpcsec_gss_krb5(E) nfsv4(E) nfs(E) fscache(E) snd_hda_codec_realtek(E) snd_hda_codec_generic(E) snd_hda_codec_hdmi(E) snd_hda_intel(E) eeepc_wmi(E) snd_hda_codec(E) asus_wmi(E) snd_hda_core(E) sparse_keymap(E) snd_hwdep(E) video(E) snd_pcm(E) snd_seq_midi(E) joydev(E) snd_seq_midi_event(E) snd_rawmidi(E) snd_seq(E) snd_seq_device(E) snd_timer(E) kvm(E) irqbypass(E) crct10dif_pclmul(E) snd(E) crc32_pclmul(E) ghash_clmulni_intel(E) soundcore(E) aesni_intel(E) aes_x86_64(E) lrw(E) gf128mul(E) glue_helper(E) ablk_helper(E) cryptd(E) shpchp(E) serio_raw(E) i2c_piix4(E) 8250_dw(E) i2c_designware_platform(E) i2c_designware_core(E) mac_hid(E) binfmt_misc(E) [ 413.687894] parport_pc(E) ppdev(E) lp(E) parport(E) nfsd(E) auth_rpcgss(E) nfs_acl(E) lockd(E) grace(E) sunrpc(E) autofs4(E) hid_generic(E) usbhid(E) hid(E) psmouse(E) ahci(E) r8169(E) mii(E) libahci(E) wmi(E) [ 413.687989] CPU: 13 PID: 1134 Comm: kworker/13:2 Tainted: G OE 4.9.0-custom #4 [ 413.688019] Hardware name: System manufacturer System Product Name/PRIME B350-PLUS, BIOS 0606 04/06/2017 [ 413.688089] Workqueue: events amd_sched_job_timedout [amdgpu] [ 413.688116] task: ffff88020f9657c0 task.stack: ffffc90001a88000 [ 413.688139] RIP: 0010:[<ffffffff8109b175>] [<ffffffff8109b175>] to_live_kthread+0x5/0x60 [ 413.688171] RSP: 0018:ffffc90001a8bd60 EFLAGS: 00010282 [ 413.688191] RAX: ffff88020f0073f8 RBX: ffff88020f000000 RCX: 0000000000000000 [ 413.688217] RDX: 0000000000000001 RSI: ffff88020f9670c0 RDI: 0000000000000000 [ 413.688243] RBP: ffffc90001a8bd78 R08: 0000000000000000 R09: 0000000000001000 [ 413.688269] R10: 0000006051b11a82 R11: 0000000000000001 R12: 0000000000000000 [ 413.688295] R13: ffff88020f002770 R14: ffff88020f004838 R15: ffff8801b23c2c60 [ 413.688321] FS: 0000000000000000(0000) GS:ffff88021ef40000(0000) knlGS:0000000000000000 [ 413.688352] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 413.688373] CR2: 0000000000000548 CR3: 00000001efd0f000 CR4: 00000000003406e0 [ 413.688399] Stack: [ 413.688407] ffffffff8109b304 ffff88020f000000 0000000000000070 ffffc90001a8bdf0 [ 413.688439] ffffffffa05ce29d ffffffffa052feb7 ffffffffa07b5820 ffffc90001a8bda0 [ 413.688470] ffffffff00000018 ffff8801bb88f060 0000000001a8bdb8 ffff88021ef59280 [ 413.688502] Call Trace: [ 413.688514] [<ffffffff8109b304>] ? kthread_park+0x14/0x60 [ 413.688555] [<ffffffffa05ce29d>] amdgpu_gpu_reset+0x7d/0x670 [amdgpu] [ 413.688589] [<ffffffffa052feb7>] ? drm_printk+0x97/0xa0 [drm] [ 413.688643] [<ffffffffa0698136>] amdgpu_job_timedout+0x46/0x50 [amdgpu] [ 413.688700] [<ffffffffa06969e7>] amd_sched_job_timedout+0x17/0x20 [amdgpu] [ 413.688727] [<ffffffff81095493>] process_one_work+0x153/0x3f0 [ 413.688751] [<ffffffff81095c5b>] worker_thread+0x12b/0x4b0 [ 413.688773] [<ffffffff8100392e>] ? do_syscall_64+0x6e/0x180 [ 413.688795] [<ffffffff81095b30>] ? rescuer_thread+0x350/0x350 [ 413.688818] [<ffffffff8100392e>] ? do_syscall_64+0x6e/0x180 [ 413.688839] [<ffffffff8109b423>] kthread+0xd3/0xf0 [ 413.688858] [<ffffffff8109b350>] ? kthread_park+0x60/0x60 [ 413.688881] [<ffffffff817e1ee5>] ret_from_fork+0x25/0x30 [ 413.688901] Code: 25 40 d3 00 00 48 8b 80 48 05 00 00 48 89 e5 5d 48 8b 40 c8 48 c1 e8 02 83 e0 01 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 <48> 8b b7 48 05 00 00 55 48 89 e5 48 85 f6 74 31 8b 97 f8 18 00 [ 413.689045] RIP [<ffffffff8109b175>] to_live_kthread+0x5/0x60 [ 413.689064] RSP <ffffc90001a8bd60> [ 413.689076] CR2: 0000000000000548 [ 413.697985] ---[ end trace 0a314a64821f84e9 ]--- The root cause is some ring doesn't have scheduler, like KIQ ring Reviewed-by: Christian König <[email protected]> Signed-off-by: Chunming Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu: fix no-vmid jobChunming Zhou1-1/+1
[ 132.036658] amdgpu 0000:22:00.0: VM IB without ID [ 132.036709] [drm:amdgpu_job_run [amdgpu]] *ERROR* Error scheduling IBs (-22) [ 132.036755] [drm:amd_sched_main [amdgpu]] *ERROR* Failed to run job! root cause is fence is signaled during sync transfer. Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu: fix indentRoger.He1-17/+17
Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Roger.He <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu: increase gtt size to 3GB by default v2Chunming Zhou5-4/+9
v2: address Alex's comment, add AMDGPU_DEFAULT_GTT_SIZE_MB. Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu: fix VM clearing in amdgpu_gem_object_closeChristian König1-31/+37
We need to check if the VM is swapped out before trying to update it. Fixes: 23e0563e48f7 ("drm/amdgpu: clear freed mappings immediately when BO may be freed") Signed-off-by: Christian König <[email protected]> Reviewed-by: Nicolai Hähnle <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu: add gtt print like vram when dump mm table V2Chunming Zhou2-1/+18
Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu: fix amdgpu_ttm_bo_eviction_valuableChristian König1-5/+13
BOs not mapped into the GART are always valuable for an eviction. Otherwise we don't correctly swap them out on VRAM evictions during memory pressure. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amd/powerplay: Fix AVFS param.Rex Zhu1-4/+4
Signed-off-by: Rex Zhu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amd/powerplay: enable clock stretch feature on Vega10.Rex Zhu1-5/+7
Correctly calculate CKSVidOffset Signed-off-by: Rex Zhu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amd/powerplay: enable pcie dpm on Vega10.Rex Zhu1-1/+2
Signed-off-by: Rex Zhu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amd/powerplay: allocate fb for avfs fuse table on vega10.Rex Zhu2-0/+37
Signed-off-by: Rex Zhu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amd/powerplay: enable AGM logging while dpm disabled.Rex Zhu2-3/+2
Signed-off-by: Rex Zhu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amd/powerplay: add error message to remind user updating firmwareHuang Rui1-2/+5
Signed-off-by: Huang Rui <[email protected]> Reviewed-by: Evan Quan <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28Revert "drm/amd/amdgpu: Set VCE/UVD off during late init"Alex Deucher1-4/+0
This leads to hangs on init. This reverts commit d1aff8ec49c3ece05cee9b6e63d44e96a420b068.
2017-04-28drm/amdgpu: PRT support for gfx9 (v3)Zhang, Jerry2-1/+8
Fix PRT handling on gfx9 v2: unify PRT bit for all ASICs v3: move PRT flag checking in amdgpu_vm_bo_split_mapping() Signed-off-by: Junwei Zhang <[email protected]> Acked-by: David Zhou <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu: fix amdgpu_vm_clear_freed v2Christian König1-2/+3
Use amdgpu_vm_bo_update_mapping() instead of amdgpu_vm_bo_split_mapping() here. We don't want any flags set in the cleared areas and splitting shouldn't be necessary. v2: fix typo in commit message Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Junwei Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Cc: [email protected]
2017-04-28drm/amdgpu: Destroy psp ring in hw_finiTrigger Huang4-2/+39
Fix issue that PSP initialization will fail if reload amdgpu module. That's because the PSP ring must be destroyed to be ready for the next time PSP initialization. Changes in v2: - Move psp_ring_destroy before all BOs free (suggested by Ray Huang). Changes in v3: - Check firmware load type, if it is not PSP, we should do nothing in fw_fini(), and of course will not destroy PSP ring too (suggested by Ray Huang). Signed-off-by: Trigger Huang <[email protected]> Reviewed-by: Xiangliang Yu <[email protected]> Reviewed-by: Huang Rui <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu: update smu9 driver interfaceEvan Quan1-2/+16
Updated interface between the driver and the SMU controller. Signed-off-by: Evan Quan <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amd/amdgpu: Print out ring name in dev_infoTom St Denis1-2/+3
So it's more obvious which rings are using which INV engines. Signed-off-by: Tom St Denis <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amd/amdgpu: Change comp GFXv9 ring name to remove spaceTom St Denis1-1/+1
umr expects the ring name to be a complete word. This also makes it consistent with GFXv7/8. Signed-off-by: Tom St Denis <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amd/amdgpu: Change comp GFXv6 ring name to remove spaceTom St Denis1-1/+1
umr expects the ring name to be a complete word. This also makes it consistent with GFXv7/8. Signed-off-by: Tom St Denis <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu: Fix module unload hang by KIQ on Vega10Trigger Huang1-8/+2
Apply commit 4e683cb2644f ("drm/amdgpu: Fix module unload hang by KIQ IRQ set")to vega10 V2: delete reduant kiq irq funcs type check (suggested by Rex.Zhu) Signed-off-by: Trigger Huang <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu: fix memory clock can't switch on CI.Rex Zhu1-2/+1
if we set only lowest mclk level enabled, when we enable uvd dpm during boot time, mclk will be fixed in the lowest level. the mclk switch will fail if try to enable other level of mclk at this time. so set all mclk levels enabled. Signed-off-by: Rex Zhu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu/gfx9: bypass clockgating settingXiangliang Yu1-0/+3
For SRIOV doesn't need clockgating, bypass it. Signed-off-by: Xiangliang Yu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu/mmhub_v1: bypass clockgating settingXiangliang Yu1-0/+3
For SRIOV doesn't need CG, so bypass it. Signed-off-by: Xiangliang Yu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu: fix coding style and printing in amdgpu_doorbell_initChristian König1-5/+4
Based on commit "drm/radeon: remove useless and potentially wrong message". The size of the info printing is incorrect and the PCI subsystems prints the same info on boot anyway. Signed-off-by: Christian König <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu/virt: don't check VALID bit for FLR completion messagePixel Ding1-3/+6
The interrupt after FLR is missed sometimes due to hardware reason, so guest driver get the notification of FLR completion via polling message. Then host doesn't write VALID bit to avoid sending interrupt, otherwise the completion will be handled twice. So there's a valid message without VALID bit for FLR completion, driver should handle it without checking. Signed-off-by: Pixel Ding <[email protected]> Reviewed-by: Xiangliang Yu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu: fix double_offchip_lds_buf for gfx v6Junwei Zhang1-1/+1
Was incorrect for SI. Signed-off-by: Junwei Zhang <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Cc: [email protected]
2017-04-28drm/amd/powerplay: delete dead functions in vega10.Rex Zhu3-38/+2
Vega10 does not support AVFS BTC, remove function. Signed-off-by: Rex Zhu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amd/amdgpu: coding style refine in sdma_v4_0.cRex Zhu1-76/+75
Replace 8 spaces with tabs. correct {} braces, etc. Signed-off-by: Rex Zhu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu: Remove redundant itermediate return val in sdma_v4_0.cRex Zhu1-5/+1
Signed-off-by: Rex Zhu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu: fix to print incorrect wptr addressHuang Rui1-1/+1
Signed-off-by: Huang Rui <[email protected]> Reviewed-by: Michel Dänzer <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu: fix dead lock if any ip block resume failed in s3Huang Rui1-15/+11
Driver must free the console lock whether driver resuming successful or not. Otherwise, fb_console will be always waiting for the lock and then cause system stuck. [ 244.405541] INFO: task kworker/0:0:4 blocked for more than 120 seconds. [ 244.405543] Tainted: G OE 4.9.0-custom #1 [ 244.405544] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 244.405541] INFO: task kworker/0:0:4 blocked for more than 120 seconds. [ 244.405543] Tainted: G OE 4.9.0-custom #1 [ 244.405544] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 244.405550] kworker/0:0 D 0 4 2 0x00080000 [ 244.405559] Workqueue: events console_callback [ 244.405564] ffff88045a2cfc00 0000000000000000 ffff880462b75940 ffffffff81c0e500 [ 244.405568] ffff880476419280 ffffc900018f7c90 ffffffff817dcf62 000000000000003c [ 244.405572] 0000000100000000 0000000000000002 ffff880462b75940 ffff880462b75940 [ 244.405573] Call Trace: [ 244.405580] [<ffffffff817dcf62>] ? __schedule+0x222/0x6a0 [ 244.405584] [<ffffffff817dd416>] schedule+0x36/0x80 [ 244.405588] [<ffffffff817e041c>] schedule_timeout+0x1fc/0x390 [ 244.405592] [<ffffffff817df1b4>] __down_common+0xa5/0xf8 [ 244.405598] [<ffffffff810b2ca8>] ? put_prev_entity+0x48/0x710 [ 244.405601] [<ffffffff817df224>] __down+0x1d/0x1f [ 244.405606] [<ffffffff810c71a1>] down+0x41/0x50 [ 244.405611] [<ffffffff810d380a>] console_lock+0x1a/0x40 [ 244.405614] [<ffffffff814e3c03>] console_callback+0x13/0x160 [ 244.405617] [<ffffffff817dcf6a>] ? __schedule+0x22a/0x6a0 [ 244.405623] [<ffffffff810954e3>] process_one_work+0x153/0x3f0 [ 244.405628] [<ffffffff81095cab>] worker_thread+0x12b/0x4b0 [ 244.405633] [<ffffffff81095b80>] ? rescuer_thread+0x350/0x350 [ 244.405637] [<ffffffff8109b473>] kthread+0xd3/0xf0 [ 244.405641] [<ffffffff8109b3a0>] ? kthread_park+0x60/0x60 [ 244.405645] [<ffffffff8109b3a0>] ? kthread_park+0x60/0x60 [ 244.405649] [<ffffffff817e1ee5>] ret_from_fork+0x25/0x30 Signed-off-by: Huang Rui <[email protected]> Reviewed-by: Michel Dänzer <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu: bump version number to note race fix and new fence functionalityAlex Deucher1-1/+2
fixed in: "drm/amdgpu:fix race condition" Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu: trace vm hub during flush as well v2Christian König2-9/+13
Trace on which hub we are doing the flush. v2: fix typo in commit message Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Andres Rodriguez <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu: trace the vmhub in grab_id as wellChristian König2-8/+11
Trace on which VMHUB we assigned an VMID. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu: allow concurrent VM flushesChristian König1-22/+28
Enable concurrent VM flushes for Vega10. Signed-off-by: Christian König <[email protected]> Acked-by: Alex Deucher <[email protected]> Reviewed-by: Andres Rodriguez <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu: assign VM invalidation engine manually v2Christian König6-5/+22
For Vega10 we have 18 VM invalidation engines for each VMHUB. Start to assign them manually to the rings. v2: add a BUG_ON if we use to many engines Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Andres Rodriguez <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu: invalidate only the currently needed VMHUB v2Christian König5-148/+119
Drop invalidating both hubs from each engine. v2: don't use hardcoded values Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Andres Rodriguez <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu: split VMID management by VMHUBChristian König10-45/+69
This way GFX and MM won't fight for VMIDs any more. Initially disabled since we need to stop flushing all HUBS at the same time as well. Signed-off-by: Christian König <[email protected]> Reviewed-by: Andres Rodriguez <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu: drop VMID per ring trackingChristian König2-17/+3
David suggested this a long time ago, instead of checking each ring just walk over all the VMIDs in reverse LRU order. Signed-off-by: Christian König <[email protected]> Reviewed-by: Andres Rodriguez <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu: add VMHUB to ring associationChristian König5-0/+8
Add the info which ring belonging to which VMHUB. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Andres Rodriguez <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-04-28drm/amdgpu/vce4: enable ring & ib test for sriovFrank Min1-8/+0
Now VCE block can work for SRIOV, enable ring & ib test. Signed-off-by: Frank Min <[email protected]> Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.