- 18 Jan, 2015 1 commit
-
-
Ben Goz authored
Signed-off-by:
Ben Goz <ben.goz@amd.com> Signed-off-by:
Oded Gabbay <oded.gabbay@amd.com> Reviewed-by:
Alex Deucher <alexander.deucher@amd.com>
-
- 15 Jan, 2015 3 commits
-
-
Oded Gabbay authored
This patch completely removes the sync_with_hw() because it was broken and actually there is no point of using it. This function was used to: - Make sure that the submitted packet to the HIQ (which is a kernel queue) was read by the CP. However, it was discovered that the method this function used to do that (checking wptr == rptr) is not consistent with how the actual CP firmware works in all cases. - Make sure that the queue is empty before issuing the next packet. To achieve that, the function blocked amdkfd from continuing until the recently submitted packet was consumed. However, the acquire_packet_buffer() already checks if there is enough room for a new packet so calling sync_with_hw() is redundant. Signed-off-by:
-
Oded Gabbay authored
Signed-off-by:
-
Oded Gabbay authored
In order not to occupy the current core and thus prevent the core from servicing IOMMU PPR requests, this patch replaces the call in DQM to cpu_relax() with a call to schedule(). Signed-off-by:
-
- 13 Jan, 2015 1 commit
-
-
Ben Goz authored
This patch fixes a minor bug in allocate_hqd(), where the loop run from the next-to-allocate pipe until the number of pipes. This is wrong because we need to consider the possibility where next-to-allocate pipe is not 0, and thus, the for-loop only checks part of the pipes and doesn't wrap-around, as it supposed to do. Therefore, we add another counting variable to make sure we go over all the pipes, regardless of where we start to look at the first iteration of the loop. This bug only affected non-HWS mode. In HWS mode, the CP fw is responsible for allocating the HQD. Signed-off-by:
-
- 02 Dec, 2014 1 commit
-
-
Ben Goz authored
This patch starts to add support for the VI APU in the KQ (kernel queue) module. Because most (more than 90%) of the KQ code is shared among AMD's APUs, we chose a design that performs most/all the code in the shared KQ file (kfd_kernel_queue.c). If there is H/W specific code to be executed, than it is written in an asic-specific extension function for that H/W. That asic-specific extension function is called from the shared function at the appropriate time. This requires that for every asic-specific extension function that is implemented in a specific ASIC, there will be an equivalent implementation in ALL ASICs, even if those implementations are just stubs. That way we achieve: - Maintainability: by having one copy of most of the code, we only need to fix bugs at one locations - Readability: very clear what is the shared code and what is done per ASIC - Extensibility: very easy to add new H/W specific files/functions Signed-off-by:
-
- 12 Jan, 2015 4 commits
-
-
Oded Gabbay authored
This patch does some re-org on the kernel_queue structure. It takes out all the function pointers from the structure and puts them in a new structure, called kernel_queue_ops. Then, it puts an instance of that structure inside kernel_queue. This re-org is done to prepare the KQ module to support more than one AMD APU (Kaveri). Signed-off-by:
-
Ben Goz authored
This patch starts to add support for the VI APU in the DQM module. Because most (more than 90%) of the DQM code is shared among AMD's APUs, we chose a design that performs most/all the code in the shared DQM file (kfd_device_queue_manager.c). If there is H/W specific code to be executed, than it is written in an asic-specific extension function for that H/W. That asic-specific extension function is called from the shared function at the appropriate time. This requires that for every asic-specific extension function that is implemented in a specific ASIC, there will be an equivalent implementation in ALL ASICs, even if those implementations are just stubs. That way we achieve: - Maintainability: by having one copy of most of the code, we only need to fix bugs at one locations - Readability: very clear what is the shared code and what is done per ASIC - Extensibility: very easy to add new H/W specific files/functions Signed-off-by:
-
Oded Gabbay authored
This patch does some re-org on the device_queue_manager structure. It takes out all the function pointers from the structure and puts them in a new structure, called device_queue_manager_ops. Then, it puts an instance of that structure inside device_queue_manager. This re-org is done to prepare the DQM module to support more than one AMD APU (Kaveri). Signed-off-by:
-
Oded Gabbay authored
Instead of creating a BUG if trying to free a NULL GART sub-allocation object, just return 0 (success). This is done to mirror behavior of kfree. Signed-off-by:
-
- 18 Aug, 2014 1 commit
-
-
Ben Goz authored
This patch rewrites destroy_queue_nocpsch() as the current logic that is implemented in the function is completely flawed. This function is used only in non-HWS mode. Signed-off-by:
-
- 05 Jan, 2015 1 commit
-
-
Oded Gabbay authored
Add two files under amdkfd section. Signed-off-by:
-
- 04 Jan, 2015 1 commit
-
-
Ben Goz authored
The MQDs for CI and VI are different. Therefore, the MQD manager module need to be H/W specific. This patch splits the current MQD manager into three files: - kfd_mqd_manager.c, which contains common functions and initializes the specific mqd manager module according to the H/W - kfd_mqd_manager_cik.c, which contains Kaveri specific functions. This is basically the old kfd_mqd_manager.c - kfd_mqd_manager_vi.c, which will contain VI specific functions. Currently it is not implemented except for returning NULL on initialization. Signed-off-by:
-
- 01 Jan, 2015 1 commit
-
-
Ben Goz authored
This patch adds a new property to kfd_device_info structure. That structure holds information that is H/W specific. The new property is called asic_family and its purpose is to distinguish between different asic families in amdkfd operations, mainly in QCM (queue control & management) This patch also adds a new enum, to select different ASICs. We set the current kfd_device_info instance as Kaveri and create a new instance which describes the new AMD APU, codenamed 'Carrizo'. Signed-off-by:
-
- 04 Jan, 2015 2 commits
-
-
Ben Goz authored
As the MQD types are common across all AMD GPUs/APUs, let's remove the CIK part from the name. Signed-off-by:
-
Ben Goz authored
This patch adds new fields to the queue_properties structure. The new fields are relevant only for queues running on AMD GPU VI architecture. The eop_ring_buffer_address and eop_ring_buffer_size describe an end-of-pipe queue which is assigned to the MQD. In CI, the EOP queue was per pipeline and in VI it is per queue. The ctx_save_restore_area_address and ctx_save_restore_area_size describe a memory area that is designated to allow the CP to do context save/restore in mid-wave state. This patch also modifies the set_queue_properties_from_user() (called from kfd_ioctl_create_queue()) to check and copy those new parameters. Signed-off-by:
-
- 02 Jan, 2015 4 commits
-
-
Oded Gabbay authored
Signed-off-by:
-
Oded Gabbay authored
Because amdkfd will need to work both with radeon and amdgpu, don't include header files that are in radeon's folder. Instead, use the common amd include folder and move amdkfd specific defines to amdkfd header files. Signed-off-by:
-
Ben Goz authored
This patch creates a new file, cik_structs.h, and puts the cik_mqd and cik_sdma_rlc_registers structures in that file. The new file is placed in a common include folder under the drm/amd folder, so it will be shared among all amd drm drivers. Signed-off-by:
-
Oded Gabbay authored
Signed-off-by:
-
- 26 Oct, 2014 1 commit
-
-
Ben Goz authored
This patch removes a call to kfd-->kgd interface function that is doing H/W initialization. That function is moved into radeon to be part of the common H/W initialization sequence. The interface function will be deleted. Signed-off-by:
-
- 02 Jan, 2015 1 commit
-
-
Ben Goz authored
This patch moves to radeon the initialization of compute vmid. That initializations was done in kfd-->kgd interface, but doing it in radeon as part of radeon's H/W initialization routines is more appropriate. In addition, this simplifies the kfd-->kgd interface. The patch removes the function from the interface file and from the interface declaration file. The function initializes memory apertures to fixed base/limit address and non cached memory types. Signed-off-by:
-
- 21 Jan, 2015 3 commits
-
-
git://git.pengutronix.de/git/pza/linuxDave Airlie authored
imx-drm mode fixup support, imx-hdmi bridge conversion and imx-drm cleanup - Implement mode_fixup for a DI vertical timing limitation - Use generic DRM OF helpers in DRM core - Convert imx-hdmi to dw_hdmi drm_bridge and add rockchip driver - Add DC use counter to fix multi-display support - Simplify handling of DI clock flags - A few small fixes and cleanup * tag 'imx-drm-next-2015-01-09' of git://git.pengutronix.de/git/pza/linux: (26 commits) imx-drm: core: handling of DI clock flags to ipu_crtc_mode_set() gpu: ipu-di: Switch to DIV_ROUND_CLOSEST for DI clock divider calc gpu: ipu-v3: Use videomode in struct ipu_di_signal_cfg imx-drm: encoder prepare/mode_set must use adjusted mode imx-drm: ipuv3-crtc: Implement mode_fixup drm_modes: add drm_display_mode_to_videomode gpu: ipu-di: remove some non-functional code gpu: ipu-di: Add ipu_di_adjust_videomode() drm: rockchip: export functions needed by rockchip dw_hdmi bridge driver drm: bridge/dw_hdmi: request interrupt only after initializing the mutes drm: bridge/dw_hdmi: add rockchip rk3288 support dt-bindings: Add documentation for rockchip dw hdmi drm: bridge/dw_hdmi: add function dw_hdmi_phy_enable_spare drm: bridge/dw_hdmi: clear i2cmphy_stat0 reg in hdmi_phy_wait_i2c_done drm: bridge/dw_hdmi: add mode_valid support drm: bridge/dw_hdmi: add support for multi-byte register width access dt-bindings: add document for dw_hdmi drm: imx: imx-hdmi: move imx-hdmi to bridge/dw_hdmi drm: imx: imx-hdmi: split phy configuration to platform driver drm: imx: imx-hdmi: convert imx-hdmi to drm_bridge mode ...
-
git://linuxtv.org/pinchartl/fbdevDave Airlie authored
* 'drm/next/du' of git://linuxtv.org/pinchartl/fbdev: drm: rcar-du: Implement support for interlaced modes drm: rcar-du: Clamp DPMS states to on and off drm: rcar-du: Enable hotplug detection on HDMI connector drm: rcar-du: Output HSYNC instead of CSYNC drm: rcar-du: Add support for external pixel clock drm: rcar-du: Refactor DEFR8 feature drm: rcar-du: Remove LVDS and HDMI encoders chaining restriction drm: rcar-du: Configure pitch for chroma plane of multiplanar formats drm: rcar-du: Don't fail probe in case of partial encoder init error drm: adv7511: Remove interlaced mode check
-
git://people.freedesktop.org/~gabbayo/linuxDave Airlie authored
- Add support for SDMA usermode queues - Replace logic of sub-allocating from GART buffer in amdkfd. Instead of using radeon_sa module, use a new module that is more suited for this purpose - Add the number of watch points to amdkfd topology - Split a function that did two things into two seperate functions. * tag 'drm-amdkfd-next-2015-01-09' of git://people.freedesktop.org/~gabbayo/linux: drm/amd: Remove old radeon_sa funcs from kfd-->kgd interface drm/radeon: Remove old radeon_sa usage from kfd-->kgd interface drm/amdkfd: Using new gtt sa in amdkfd drm/amdkfd: Allocate gart memory using new interface drm/amdkfd: Fixed calculation of gart buffer size drm/amdkfd: Add kfd gtt sub-allocator functions drm/amdkfd: Add gtt sa related data to kfd_dev struct drm/radeon: Impl. new gtt allocate/free functions drm/amd: Add new kfd-->kgd interface for gart usage drm/radeon: Enable sdma preemption drm/amdkfd: Pass queue type to pqm_create_queue() drm/amdkfd: Identify SDMA queue in create queue ioctl drm/amdkfd: Add SDMA user-mode queues support to QCM drm/amdkfd: Add SDMA mqd support drm/radeon: Implement SDMA interface functions drm/amd: Add SDMA functions to kfd-->kgd interface drm/amdkfd: Process-device data creation and lookup split drm/amdkfd: Add number of watch points to topology
-
- 12 Jan, 2015 1 commit
-
-
Dave Airlie authored
Daniel merged two things in 72a36970, but he merged this code twice, Dan's static checker spotted it. Reported-by:
Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by:
Dave Airlie <airlied@redhat.com>
-
- 09 Jan, 2015 14 commits
-
-
git://anongit.freedesktop.org/drm-intelDave Airlie authored
- plane handling refactoring from Matt Roper and Gustavo Padovan in prep for atomic updates - fixes and more patches for the seqno to request transformation from John - docbook for fbc from Rodrigo - prep work for dual-link dsi from Gaurav Signh - crc fixes from Ville - special ggtt views infrastructure from Tvrtko Ursulin - shadow patch copying for the cmd parser from Brad Volkin - execlist and full ppgtt by default on gen8, for testing for now * tag 'drm-intel-next-2014-12-19' of git://anongit.freedesktop.org/drm-intel: (131 commits) drm/i915: Update DRIVER_DATE to 20141219 drm/i915: Hold runtime PM during plane commit drm/i915: Organize bind_vma funcs drm/i915: Organize INSTDONE report for future. drm/i915: Organize PDP regs report for future. drm/i915: Organize PPGTT init drm/i915: Organize Fence registers for future enablement. drm/i915: tame the chattermouth (v2) drm/i915: Warn about missing context state workarounds only once drm/i915: Use true PPGTT in Gen8+ when execlists are enabled drm/i915: Skip gunit save/restore for cherryview drm/i915/chv: Use timeout mode for RC6 on chv drm/i915: Add GPGPU_THREADS_DISPATCHED to the register whitelist drm/i915: Tidy up execbuffer command parsing code drm/i915: Mark shadow batch buffers as purgeable drm/i915: Use batch length instead of object size in command parser drm/i915: Use batch pools with the command parser drm/i915: Implement a framework for batch buffer pools drm/i915: fix use after free during eDP encoder destroying drm/i915/skl: Skylake also supports DP MST ...
-
Oded Gabbay authored
Signed-off-by:
Alexey Skidanov <Alexey.skidanov@amd.com> Reviewed-by:
-
Oded Gabbay authored
Signed-off-by:
-
Oded Gabbay authored
This patch change the calls throughout the amdkfd driver from the old kfd-->kgd interface to the new kfd gtt sa inside amdkfd v2: change the new call in sdma code that appeared because of the sdma feature Signed-off-by:
-
Oded Gabbay authored
This patch changes the calls to allocate the gart memory for amdkfd from the old interface (radeon_sa) to the new one (kfd_gtt_sa) The new gart sub-allocator is initialized with chunk size equal to 512 bytes. This is because the KV MQD is 512 Bytes and most of the sub-allocations are MQDs. Signed-off-by:
-
Oded Gabbay authored
This patch makes the gart's buffer size calculation more accurate. This buffer is needed per GPU. It takes into account maximum number of MQDs, runlist packets, kernel queues and reserves 512KB for other misc allocations. The total size is just shy of 4MB, for 32 processes and 128 queues per process, which are the defaults for amdkfd kernel module parameters. Signed-off-by:
-
Oded Gabbay authored
This patch adds new kfd gtt sub-allocator functions that service the amdkfd driver when it wants to use gtt memory. The sub-allocator uses a bitmap to handle the memory area that was transferred to it during init. It divides the memory area into chunks, according to chunk size parameter. The allocation function will allocate contiguous chunks from that memory area, according to the requested size. If the requested size is smaller than the chunk size, a single chunk will be allocated. v2: Do some more verifications on parameters that are passed into kfd_gtt_sa_init() Signed-off-by:
-
Oded Gabbay authored
This patch adds new fields to kfd_dev struct that are necessary for the new kfd gtt sa module Signed-off-by:
-
Oded Gabbay authored
This patch adds the implementation of the gtt interface functions. The allocate function will allocate a single bo, pin and map it to kernel memory. It will return the gpu address and cpu ptr as arguments. v2: The bulk of the allocations in the GART is for MQDs. MQDs represent active user-mode queues, which are on the current runlist. It is important to remember that active queues doesn't necessarily mean scheduled/running queues, especially if there is over-subscription of queues or more than a single HSA process. Because the scheduling of the user-mode queues is done by the CP firmware, amdkfd doesn't have any indication if the queue is scheduled or not. If the CP will try to schedule a queue, and its MQD is not present, this will probably stuck the CP permanently, as it will load garbage from the GART (the address of the MQD is given to the CP inside the runlist packet). In addition, there are a couple of small allocations which also should always be pinned - runlist packets (2 packets) and HPDs. runlist packets can be quite large, depending on number of processes and queues. This new allocate function represents the short/mid-term solution of limiting the total memory consumption to around 4MB by default. The long-term solution is to create a mechanism through which radeon/ttm can ask amdkfd to clear GART/VRAM memory due to memory pressure. Then, amdkfd will preempt the running queues and wait until the memory pressure is over. After that, amdkfd will reschedule the queues. Signed-off-by:
-
Oded Gabbay authored
This patch adds two new functions to the kfd-->kgd interface: init_gtt_mem_allocation, which allocate a large enough buffer on the amdkfd needs, such as mqds, hpds, kernel queue, fence and runlists. This function is only called once per GPU device. The size of the allocated buffer is based on the maximum number of HSA processes and maximum number of queues per HSA process (two amdkfd kernel module parameters). free_gtt_mem, which frees a buffer that was allocated on the gart aperture. Signed-off-by:
-
Ben Goz authored
This patch adds to radeon the enablement of sdma preemption. This is needed to support HWS of SDMA user-mode queues. Signed-off-by:
-
Ben Goz authored
This patch passes the correct queue type to pqm_create_queue() instead of a fixed KFD_QUEUE_TYPE_COMPUTE type. Signed-off-by:
-
Ben Goz authored
This patch adds a check to the create queue ioctl path, which identifies SDMA queue type that is sent by userspace. Signed-off-by:
-
Ben Goz authored
This patch adds support for SDMA user-mode queues to the QCM - the Queue management system that manages queues-per-device and queues-per-process. v2: Remove calls to interface function that initializes sdma engines. v3: Use the new names of some of the defines. Signed-off-by:
-
