aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)AuthorFilesLines
2016-02-12drm/amdgpu: use SDMA round robin for VM updates v3Christian König6-11/+43
Distribute the load on both rings. v2: use a loop for the initialization v3: agd: rebase on upstream Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
2016-02-12drm/amdgpu: remove is_pte_ringChristian König4-4/+0
Not used for anything. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
2016-02-12drm/amdgpu: use per VM entity for page table updates (v2)Christian König6-22/+51
Updates from different VMs can be processed independently. v2: agd: rebase on upstream Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
2016-02-12drm/amdgpu: remove the userptr rmn->lockChristian König1-20/+12
Avoid a lock inversion problem by just using the mmap_sem to protect the entries of the intervall tree. Signed-off-by: Christian König <[email protected]> Reviewed-by: Felix Kuehling <[email protected]>
2016-02-12drm/amd/include: Update dce 8 headers for dalHarry Wentland2-0/+13
Signed-off-by: Harry Wentland <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
2016-02-12drm/amdgpu/gfx7: Fix whitespaceTom St Denis1-1/+1
Signed-off-by: Tom St Denis <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
2016-02-12drm/amdgpu/gfx7: Simplify wptr/rptr functionsTom St Denis1-19/+4
Signed-off-by: Tom St Denis <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
2016-02-12drm/amdgpu/gfx7: LOC reduction in gfx_v7_0_setup_rbTom St Denis1-7/+2
Reduce for loop with bitmask to simple complement and mask Signed-off-by: Tom St Denis <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
2016-02-12drm/amdgpu/gfx7: Simplify bitmask creationTom St Denis1-7/+1
Signed-off-by: Tom St Denis <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
2016-02-12drm/amdgpu/gfx7: Reduce linecount in table initTom St Denis1-820/+525
Replaces switch statements with direct assignments to reduce line count significantly. Signed-off-by: Tom St Denis <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
2016-02-12dma-buf: Add ioctls to allow userspace to flushDaniel Vetter3-1/+105
The userspace might need some sort of cache coherency management e.g. when CPU and GPU domains are being accessed through dma-buf at the same time. To circumvent this problem there are begin/end coherency markers, that forward directly to existing dma-buf device drivers vfunc hooks. Userspace can make use of those markers through the DMA_BUF_IOCTL_SYNC ioctl. The sequence would be used like following: - mmap dma-buf fd - for each drawing/upload cycle in CPU 1. SYNC_START ioctl, 2. read/write to mmap area 3. SYNC_END ioctl. This can be repeated as often as you want (with the new data being consumed by the GPU or say scanout device) - munmap once you don't need the buffer any more v2 (Tiago): Fix header file type names (u64 -> __u64) v3 (Tiago): Add documentation. Use enum dma_buf_sync_flags to the begin/end dma-buf functions. Check for overflows in start/length. v4 (Tiago): use 2d regions for sync. v5 (Tiago): forget about 2d regions (v4); use _IOW in DMA_BUF_IOCTL_SYNC and remove range information from struct dma_buf_sync. v6 (Tiago): use __u64 structured padded flags instead enum. Adjust documentation about the recommendation on using sync ioctls. v7 (Tiago): Alex' nit on flags definition and being even more wording in the doc about sync usage. v9 (Tiago): remove useless is_dma_buf_file check. Fix sync.flags conditionals and its mask order check. Add <linux/types.h> include in dma-buf.h. Cc: Ville Syrjälä <[email protected]> Cc: David Herrmann <[email protected]> Cc: Sumit Semwal <[email protected]> Reviewed-by: Stéphane Marchesin <[email protected]> Signed-off-by: Daniel Vetter <[email protected]> Signed-off-by: Tiago Vignatti <[email protected]> Reviewed-by: David Herrmann <[email protected]> Signed-off-by: Daniel Vetter <[email protected]> Link: http://patchwork.freedesktop.org/patch/msgid/[email protected]
2016-02-12drm/dp: Add a drm_aux-dev module for reading/writing dpcd registers.Rafael Antognolli6-2/+468
This module is heavily based on i2c-dev. Once loaded, it provides one dev node per DP AUX channel, named drm_dp_auxN, where N is an integer. It's possible to know which connector owns this aux channel by looking at the respective sysfs /sys/class/drm_aux_dev/drm_dp_auxN/connector, if the connector device pointer was correctly set in the aux helper struct. Two main operations are provided on the registers read and write. The address of the register to be read or written is given using lseek. The seek position is updated upon read or write. v2: - lseek is used to select the register to read/write - read/write are used instead of ioctl - no blocking_notifier is used, just a direct callback v3: - use drm_dp_aux_dev prefix for public functions - chardev is named drm_dp_auxN - read/write don't allocate a buffer anymore, and transfer up to 16 bytes a time - remove notifier list from the implementation - option on menuconfig is now a boolean - add inline stub functions to avoid breakage when this option is disabled v4: - fix build system changes - actually disable this module when not selected. v5: - Use kref to avoid device closing while still in use - Don't use list, use an idr for storing aux_dev - Remove "connector" attribute - set aux.dev to the connector drm_connector device, instead of drm_device v6: - Use atomic_t for usage count - Use a mutex instead of spinlock for idr lock - Destroy chardev immediately on unregister - other minor suggestions from Ville v7: - style fixes - error handling fixes v8: - more error handling fixes v9: - remove module_init and module_exit, and add drm_dp_aux_dev_init/exit to drm_kms_helper_init/exit. Signed-off-by: Rafael Antognolli <[email protected]> Reviewed-by: Ville Syrjälä <[email protected]> Signed-off-by: Daniel Vetter <[email protected]> Link: http://patchwork.freedesktop.org/patch/msgid/[email protected]
2016-02-12drm/kms_helper: Add a common place to call init and exit functions.Rafael Antognolli5-9/+60
The module_init and module_exit functions will start here, and call the subsequent init's and exit's. v10: - Keep __init on drm_fb_helper init function. - Move MODULE_* macros to the common file. Signed-off-by: Rafael Antognolli <[email protected]> Reviewed-by: Ville Syrjälä <[email protected]> Signed-off-by: Daniel Vetter <[email protected]> Link: http://patchwork.freedesktop.org/patch/msgid/[email protected]
2016-02-11drm/msm: remove unused variableArnd Bergmann1-1/+0
After the drm_device_is_unplugged() was removed, the 'dev' variable is now unused, and we get a warning for that: drivers/gpu/drm/msm/msm_fbdev.c: In function 'msm_fbdev_mmap': drivers/gpu/drm/msm/msm_fbdev.c:65:21: error: unused variable 'dev' [-Werror=unused-variable] This removes the variable as well. Signed-off-by: Arnd Bergmann <[email protected]> Fixes: e9f8250f2f92 ("drm/msm: remove the drm_device_is_unplugged check") Signed-off-by: Daniel Vetter <[email protected]> Link: http://patchwork.freedesktop.org/patch/msgid/[email protected]
2016-02-11drm/bridge: removed dummy mode_fixup function from dw-hdmi.Carlos Palminha1-8/+0
Other bridge drivers don't implement this optional function. Removed dummy code from dw-hdmi brigde driver. Signed-off-by: Carlos Palminha <[email protected]> Signed-off-by: Daniel Vetter <[email protected]> Link: http://patchwork.freedesktop.org/patch/msgid/[email protected]
2016-02-11drm/i2c/tda998x: removed unnecessary code, mode_fixup is now optional.Carlos Palminha1-9/+0
Removed dummy mode_fixup. Signed-off-by: Carlos Palminha <[email protected]> Signed-off-by: Daniel Vetter <[email protected]> Link: http://patchwork.freedesktop.org/patch/msgid/[email protected]
2016-02-11drm/i2c/sil164: removed unnecessary code, mode_fixup is now optional.Carlos Palminha1-9/+0
Removed dummy mode_fixup. Signed-off-by: Carlos Palminha <[email protected]> Signed-off-by: Daniel Vetter <[email protected]> Link: http://patchwork.freedesktop.org/patch/msgid/[email protected]
2016-02-11apple-gmux: Fix build breakage if !CONFIG_ACPILukas Wunner1-1/+12
The DRM drivers i915, nouveau and radeon may be compiled with CONFIG_ACPI not set, in which case acpi_dev_present() is undefined. Add a no-op stub for apple_gmux_present() which is used if CONFIG_APPLE_GMUX is not enabled to avoid build breakage. (CONFIG_APPLE_GMUX depends on CONFIG_ACPI.) Reported-by: Stephen Rothwell <[email protected]> Signed-off-by: Lukas Wunner <[email protected]> Signed-off-by: Daniel Vetter <[email protected]> Link: http://patchwork.freedesktop.org/patch/msgid/[email protected]
2016-02-11drm: fixes crct set_mode when encoder mode_fixup is null.Carlos Palminha2-5/+7
Avoids null crash when encoders don't implement mode_fixup. Signed-off-by: Carlos Palminha <[email protected]> [danvet: Also update kerneldoc.] Signed-off-by: Daniel Vetter <[email protected]> Link: http://patchwork.freedesktop.org/patch/msgid/[email protected]
2016-02-11drm: virtio-gpu: set atomic flagRob Herring1-1/+1
Advertise atomic mode setting capability to user space. Signed-off-by: Rob Herring <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
2016-02-11drm: virtio-gpu: transfer dumb buffers to host on plane updateRob Herring1-0/+7
For dumb buffers, we need to transfer them to the host when updating a plane. Signed-off-by: Rob Herring <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
2016-02-11drm: virtio-gpu: ensure plane is flushed to host on atomic updateRob Herring1-0/+5
This fixes drawing updates when updating planes with atomic API. Signed-off-by: Rob Herring <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
2016-02-11drm: virtio-gpu: get the fb from the plane state for atomic updatesRob Herring1-2/+2
When using the atomic API, plane->fb is not set when calling virtio_gpu_plane_atomic_update. Use plane->state->fb instead. Signed-off-by: Rob Herring <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
2016-02-11Merge git://linux-arm.org/linux-ld into drm-nextDave Airlie9-0/+1044
Pull upstream HDLCD driver. * git://linux-arm.org/linux-ld: MAINTAINERS: Add Liviu Dudau as maintainer for ARM HDLCD driver. drm: Add support for ARM's HDLCD controller.
2016-02-10drm/amd/powerplay: add powerplay valid check to avoid null point.Rex Zhu1-3/+9
In case CONFIG_DRM_AMD_POWERPLAY is defined and amdgpu.powerplay=0. some functions in powrplay can also be called by DAL. and the input parameter is *adev. if just check point not NULL was not enough and will lead to NULL point error. Signed-off-by: Rex Zhu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amd/powerplay: Enable low mem pstate when cancel_highEric Yang1-1/+1
Signed-off-by: Eric Yang <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amd/powerplay: Use correct clock in cz_apply_state_adjust_rulesEric Yang1-2/+2
Signed-off-by: Eric Yang <[email protected]> Reviewed-by: Eagle Yeh <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amd/powerplay: get real display device num by cgs interfaceRex Zhu1-9/+16
Signed-off-by: Rex Zhu <[email protected]> Reviewed-by: Jammy Zhou <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amd/powerplay: Use engine clock limit calculated by dalVitaly Prosyak1-3/+3
Use min required system clock calculated by dal Signed-off-by: Harry Wentland <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amd/powerplay: Make declarations of functions exposed to DAL type-safe.David Rokhvarg2-14/+16
Signed-off-by: David Rokhvarg <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amd/powerplay: implement functions in carrizo for DAL.Rex Zhu1-11/+115
Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Rex Zhu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amd/powerplay: export interface to DAL.Rex Zhu5-21/+251
Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Rex Zhu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amd/powerplay: change struct name.Rex Zhu6-8/+8
amd_pp_dal_clock_info to amd_pp_simple_clock_info. Signed-off-by: Rex Zhu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amd: Adding IVSRC register headersHarry Wentland1-0/+102
Signed-off-by: Harry Wentland <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amdgpu: Move MMIO flip out of spinlocked regionVitaly Prosyak1-3/+3
Prior actual MMIO flip we need to acquire DAL mutex to guard our target state which get modified on reset mode. Assign page flip status before actual flip to handle the possible race condition with interrupt. Signed-off-by: Vitaly Prosyak <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amdgpu: Don't crash system if we can't get crtcHarry Wentland1-0/+6
Signed-off-by: Harry Wentland <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-11drm/msm: add max-freq gpu param to uapiRob Clark2-0/+4
We need this in userspace for interpreting some of the perf ctrs. Note possibly not quite sufficient if we had some frequency mgmt approach other than race-to-idle. Not really sure what the best thing to do if we did. Although displaying results as a percentage of max frequence seems sensible(ish) if we did. Signed-off-by: Rob Clark <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
2016-02-10drm/amdgpu: move sync into job objectChristian König13-38/+46
No need to keep that for every IB. Signed-off-by: Christian König <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amdgpu: send VCE IB tests directly to the ring againChristian König2-8/+22
We need the IB test for GPU resets as well and the scheduler should be stoped then. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amdgpu: send UVD IB tests directly to the ring againChristian König5-15/+25
We need the IB test for GPU resets as well and the scheduler should be stoped then. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amdgpu: rename amdgpu_sched.c to amdgpu_job.cChristian König2-5/+5
That's probably a better matching name. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amdgpu: cleanup in kernel job submissionChristian König7-204/+111
Add a job_alloc_with_ib helper and proper job submission. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amdgpu: send SDMA/GFX IB tests directly to the ring againChristian König5-18/+6
There is no point in sending them through the scheduler. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amdgpu: directly return fence from ib_scheduleChristian König3-8/+12
Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amdgpu: move ring from IBs into jobChristian König14-44/+45
We can't submit to multiple rings at the same time anyway. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amdgpu: make pad_ib a ring function v3Christian König14-18/+41
The padding depends on the firmware version and we need that for BO moves as well, not only for VM updates. v2: new approach of making pad_ib a ring function v3: fix typo in macro name Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amdgpu: cleanup user fence handling in the CSChristian König2-17/+13
Don't keep that around twice. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amdgpu: add proper job alloc/free functionsChristian König6-55/+69
And use them in the CS instead of allocating IBs and jobs separately. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amdgpu: fix num_ibs checkChristian König1-11/+5
Specifying no IBs on command submission is invalid, stop crashing badly when somebody tries it. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Cc: [email protected] Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amdgpu: remove AMDGPU_NUM_SYNCSChristian König2-4/+1
Just a leftover from semaphores. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.