[PATCH] drm/syncobj: add sync obj wait interface. (v5)

From: Dave Airlie This interface will allow sync object to be used to back Vulkan fences. This API is pretty much the vulkan fence waiting API, and I've ported the code from amdgpu. v2: accept relative timeout, pass remaining time back to userspace. v3: return to absolute

syncobj wait patch

I'm going to push the syncobj and sync_file interaction patches into drm-next, but I think this patch still needs a few more trips on the merry go round. I've decided to read Daniel's ioctl guide, use sec/nsec, and convert to timespec internally then use timespec as much as possible. Dave.

Re: [PATCH 2/4] drm/amdgpu: Optimization of critical section

On 13 June 2017 at 16:54, axie wrote: > > On 2017-06-12 06:47 PM, Christian König wrote: >> >> Am 12.06.2017 um 22:31 schrieb Alex Xie: >>> >>> Make the critical section smaller. There is no >>> need to protect the bo_list, because there is >>> no other task can access the newly

Re: [PATCH] drm/amd/sched: print sched job id in amd_sched_job trace

On 2017-06-13 04:14 PM, Nicolai Hähnle wrote: From: Nicolai Hähnle This makes it easier to correlate amd_sched_job with with other trace points that don't log the job pointer. Signed-off-by: Nicolai Hähnle ---

[PATCH] drm/amd/sched: print sched job id in amd_sched_job trace

From: Nicolai Hähnle This makes it easier to correlate amd_sched_job with with other trace points that don't log the job pointer. Signed-off-by: Nicolai Hähnle --- drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h | 7 +-- 1 file changed, 5

[PATCH] drm/amdgpu/gfx9: support the amdgpu.disable_cu option

From: Nicolai Hähnle This is ported from gfx8. Signed-off-by: Nicolai Hähnle --- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 20 1 file changed, 20 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c

Re: [PATCH 1/2] drm/amdgpu: vm_update_ptes remove code duplication

Am 13.06.2017 um 19:07 schrieb Alex Deucher: On Fri, Jun 9, 2017 at 5:47 PM, Harish Kasiviswanathan wrote: Signed-off-by: Harish Kasiviswanathan Series is: Acked-by: Alex Deucher Acked-by: Christian

Re: Various SOC15 macro cleanups

On Mon, Jun 12, 2017 at 1:54 PM, Tom St Denis wrote: > These replace some of the more verbose patterns with new SOC15 macros. Should > be no functional change to anything. Series is: Reviewed-by: Alex Deucher > >

[PATCH umr] Add ability to add pci/smc registers to database and fix minor related bugs

With this change we can do things like this update file: add reg carrizo.smu80.ixSMUSVI_NB_CURRENTVID smc 0xD8230044 add bit carrizo.smu80.ixSMUSVI_NB_CURRENTVID.CURRENT_NB_VID 24 31 add reg carrizo.smu80.ixSMUSVI_GFX_CURRENTVID smc 0xD8230048 add bit

Re: [PATCH] drm/amdgpu: add virtual display support for raven

Am 13.06.2017 um 19:08 schrieb Alex Deucher: On Wed, Jun 7, 2017 at 5:53 PM, Alex Deucher wrote: Same as other asics. If enabled, exposes a user selectable number of virtual displays. Signed-off-by: Alex Deucher Ping? Reviewed-by:

Re: [PATCH 1/4] drm/amdgpu: Optimization of critical section

On 2017-06-13 06:23 AM, Christian König wrote: Am 13.06.2017 um 08:29 schrieb axie: On 2017-06-12 07:00 PM, Christian König wrote: Am 12.06.2017 um 22:31 schrieb Alex Xie: This patch is to move a loop of unref BOs and several memory free function calls out of critical sections.

Re: [PATCH] drm/amdgpu: add virtual display support for raven

On Wed, Jun 7, 2017 at 5:53 PM, Alex Deucher wrote: > Same as other asics. If enabled, exposes a user selectable > number of virtual displays. > > Signed-off-by: Alex Deucher Ping? > --- > drivers/gpu/drm/amd/amdgpu/soc15.c | 2 ++ > 1 file

Re: [PATCH 1/2] drm/amdgpu: vm_update_ptes remove code duplication

On Fri, Jun 9, 2017 at 5:47 PM, Harish Kasiviswanathan wrote: > Signed-off-by: Harish Kasiviswanathan Series is: Acked-by: Alex Deucher > --- > drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 73 >

Re: [PATCH libdrm v8] amdgpu: move asic id table to a separate file

On Tue, Jun 13, 2017 at 5:45 AM, Michel Dänzer wrote: > From: Xiaojie Yuan > > v2: fix an off by one error and leading white spaces > v3: use thread safe strtok_r(); initialize len before calling getline(); > change printf() to drmMsg(); add initial

Re: [PATCH] drm/amd/display: Guard some DCN-only code in dc_debug

On 12/06/17 03:09 PM, Tom St Denis wrote: Acked-By: Tom St Denis It fixes the compile error but since I'm out of time today to actually test that's about all I can say. :-) Seems to work fine and the delta is obviously correct so please add my RB if you want. Tom

Re: [PATCH 1/4] drm/amdgpu: Optimization of critical section

Am 13.06.2017 um 08:29 schrieb axie: On 2017-06-12 07:00 PM, Christian König wrote: Am 12.06.2017 um 22:31 schrieb Alex Xie: This patch is to move a loop of unref BOs and several memory free function calls out of critical sections. Signed-off-by: Alex Xie ---

Re: [PATCH 2/4] drm/amdgpu: Optimization of critical section

Am 13.06.2017 um 08:54 schrieb axie: On 2017-06-12 06:47 PM, Christian König wrote: Am 12.06.2017 um 22:31 schrieb Alex Xie: Make the critical section smaller. There is no need to protect the bo_list, because there is no other task can access the newly created BO list yet. NAK, a task can

Re: [PATCH 4/4] drm/amdgpu: Optimize mutex usage

Am 13.06.2017 um 08:03 schrieb axie: Hi Christian, Regarding comment 1. Please read the file idr.c line 24 to line 29. Let me quote here. Isn't it surprise you? idr_alloc only need read lock. ... * Simultaneous modifications to the @idr are not allowed and should be * prevented by the

[PATCH libdrm v8] amdgpu: move asic id table to a separate file

From: Xiaojie Yuan v2: fix an off by one error and leading white spaces v3: use thread safe strtok_r(); initialize len before calling getline(); change printf() to drmMsg(); add initial amdgpu.ids v4: integrate some recent internal changes, including format changes v5:

Re: [PATCH 01/10] drm/amd/amdgpu: Add offset variant to SOC15 macros

Am 12.06.2017 um 19:54 schrieb Tom St Denis: Allows reading/writing via SOC15 macros with offset for various register banks. Signed-off-by: Tom St Denis Acked-by: Christian König --- drivers/gpu/drm/amd/amdgpu/soc15_common.h | 14

Re: [PATCH 1/4] drm/amdgpu: Optimization of critical section

Am 13.06.2017 um 04:25 schrieb Dave Airlie: On 13 June 2017 at 09:00, Christian König wrote: Am 12.06.2017 um 22:31 schrieb Alex Xie: This patch is to move a loop of unref BOs and several memory free function calls out of critical sections. Signed-off-by: Alex Xie

Re: [PATCH 2/2] drm/amd/amdgpu: Rename KIQ ring to avoid spaces

Am 12.06.2017 um 17:54 schrieb Deucher, Alexander: -Original Message- From: amd-gfx [mailto:amd-gfx-boun...@lists.freedesktop.org] On Behalf Of Tom St Denis Sent: Monday, June 12, 2017 9:06 AM To: amd-gfx@lists.freedesktop.org Cc: StDenis, Tom Subject: [PATCH 2/2] drm/amd/amdgpu: Rename

Re: [Intel-gfx] [PATCH i-g-t] tests: Rename I915_MAX_PIPES to IGT_MAX_PIPES

On Mon, 12 Jun 2017, Harry Wentland wrote: > The email was sent but might be stuck in the moderation queue since Leo > (Sun peng) is fairly new on the FDO mailing lists. > > Jani, Daniel, can you check if Leo's IGT emails are stuck in the > moderation queue? Done. I've

Re: [PATCH 2/4] drm/amdgpu: Optimization of critical section

On 2017-06-12 06:47 PM, Christian König wrote: Am 12.06.2017 um 22:31 schrieb Alex Xie: Make the critical section smaller. There is no need to protect the bo_list, because there is no other task can access the newly created BO list yet. NAK, a task can guess the next id number so could get

Re: [PATCH 1/4] drm/amdgpu: Optimization of critical section

On 2017-06-12 07:00 PM, Christian König wrote: Am 12.06.2017 um 22:31 schrieb Alex Xie: This patch is to move a loop of unref BOs and several memory free function calls out of critical sections. Signed-off-by: Alex Xie --- drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c | 5

Re: [PATCH 4/4] drm/amdgpu: Optimize mutex usage

Hi Christian, Regarding comment 1. Please read the file idr.c line 24 to line 29. Let me quote here. Isn't it surprise you? idr_alloc only need read lock. ... * Simultaneous modifications to the @idr are not allowed and should be * prevented by the user, usually with a lock. idr_alloc()