#
c68cbbfd |
|
15-Aug-2023 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: cleanup conditional execution First of all calculating the number of dw to patch into a conditional execution is not something HW generation specific. This is just standard ring buffer calculations. While at it also reduce the BUG_ON() into WARN_ON(). Then instead of a random bit pattern use 0 as default value for the number of dw skipped, this way it's not mandatory any more to patch the conditional execution. And last make the address to check a parameter of the conditional execution instead of getting this from the ring. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
4acd31e6 |
|
18-Feb-2024 |
Ma Jun <Jun.Ma2@amd.com> |
drm/amdgpu: Drop redundant parameter in amdgpu_gfx_kiq_init_ring Drop redundant parameters in function amdgpu_gfx_kiq_init_ring to simplify the code Signed-off-by: Ma Jun <Jun.Ma2@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
b5387349 |
|
11-Jan-2024 |
YuanShang <YuanShang.Mao@amd.com> |
drm/amd/amdgpu: Update RLC_SPM_MC_CNT by ring wreg in guest Submit command of wreg in GFX and COMPUTE ring to update RLC_SPM_MC_CNT in guest machine during runtime. Signed-off-by: YuanShang <YuanShang.Mao@amd.com> Reviewed-by: Emily Deng <Emily.Deng@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
88f4b10a |
|
20-Nov-2023 |
Tim Huang <Tim.Huang@amd.com> |
drm/amdgpu: fix memory overflow in the IB test Fix a memory overflow issue in the gfx IB test for some ASICs. At least 20 bytes are needed for the IB test packet. v2: correct code indentation errors. (Christian) Signed-off-by: Tim Huang <Tim.Huang@amd.com> Reviewed-by: Yifan Zhang <yifan1.zhang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
6b0b7789 |
|
20-Nov-2023 |
Tim Huang <Tim.Huang@amd.com> |
drm/amdgpu: fix memory overflow in the IB test Fix a memory overflow issue in the gfx IB test for some ASICs. At least 20 bytes are needed for the IB test packet. v2: correct code indentation errors. (Christian) Signed-off-by: Tim Huang <Tim.Huang@amd.com> Reviewed-by: Yifan Zhang <yifan1.zhang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
|
#
f705a6f0 |
|
25-Aug-2023 |
Mukul Joshi <mukul.joshi@amd.com> |
drm/amdgpu: Store CU info from all XCCs for GFX v9.4.3 Currently, we store CU info only for a single XCC assuming that it is the same for all XCCs. However, that may not be true. As a result, store CU info for all XCCs. This info is later used for CU masking. Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
97e3c6a8 |
|
25-Aug-2023 |
Mukul Joshi <mukul.joshi@amd.com> |
drm/amdgpu: Store CU info from all XCCs for GFX v9.4.3 Currently, we store CU info only for a single XCC assuming that it is the same for all XCCs. However, that may not be true. As a result, store CU info for all XCCs. This info is later used for CU masking. Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c6a64ad9 |
|
30-May-2023 |
Lijo Lazar <lijo.lazar@amd.com> |
drm/amdgpu: Initialize xcc mask For ASICs which are not initialized through discovery, initialize GFX cluster as 1. Signed-off-by: Lijo Lazar <lijo.lazar@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
232f2431 |
|
12-May-2023 |
Guchun Chen <guchun.chen@amd.com> |
drm/amdgpu/gfx: set sched.ready status after ring/IB test in gfx sched.ready is nothing with ring initialization, it needs to set to be true after ring/IB test in amdgpu_ring_test_helper to tell the ring is ready for submission. Signed-off-by: Guchun Chen <guchun.chen@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
553f973a |
|
11-Oct-2022 |
Tom St Denis <tom.stdenis@amd.com> |
drm/amd/amdgpu: Update debugfs for XCC support (v3) This patch updates the 'regs2' interface for MMIO registers to add a new IOCTL command for a 'v2' state data that includes the XCC ID. This patch then updates amdgpu_gfx_select_se_sh() and amdgpu_gfx_select_me_pipe_q() (and the implementations in the gfx drivers) to support an additional parameter. This patch then creates a new debugfs interface "gprwave" which is a merge of shader GPR and wave status access. This new inteface uses an IOCTL to select banks as well as XCC identity. (v2) Fix missing xcc_id in wave_ind function (v3) Fix pm runtime calls and mutex locking (v4) Fix bad label Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
42cdf6f6 |
|
26-Apr-2023 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: always restore kcq MQDs Always restore the MQD not just when we do a reset. This allows us to move the MQD to VRAM if we want. v2: always reset ring pointer as well (Christian) Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
609d8300 |
|
23-Apr-2023 |
Sukrut Bellary <sukrut.bellary@linux.com> |
drm:amd:amdgpu: Fix missing bo unlock in failure path smatch warning - inconsistent handling of buffer object reserve and unreserve. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Sukrut Bellary <sukrut.bellary@linux.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
86b20703 |
|
27-Jul-2022 |
Le Ma <le.ma@amd.com> |
drm/amdgpu: add xcc index argument to rlc safe_mode func (v4) v1: To support multple XCD case (Le) v2: unify naming style (Le) v3: apply the changes to gc v11_0 (Hawking) v4: apply the changes to gc SOC21 (Morris) Signed-off-by: Le Ma <le.ma@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Morris Zhang <Shiwu.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
d51ac6d0 |
|
23-May-2022 |
Le Ma <le.ma@amd.com> |
drm/amdgpu: add xcc index argument to select_sh_se function v2 v1: To support multiple XCD case (Le) v2: introduce xcc index to gfx_v11_0_select_sh_se (Hawking) Signed-off-by: Le Ma <le.ma@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
def799c6 |
|
23-May-2022 |
Le Ma <le.ma@amd.com> |
drm/amdgpu: add multi-xcc support to amdgpu_gfx interfaces (v4) v1: Modify kiq_init/fini, mqd_sw_init/fini and enable/disable_kcq to adapt to multi-die case. Pass 0 as default to all asics with single xcc (Le) v2: squash commits to avoid breaking the build (Le) v3: unify naming style (Le) v4: apply the changes to gc v11_0 (Hawking) Signed-off-by: Le Ma <le.ma@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
be697aa3 |
|
27-Jul-2022 |
Le Ma <le.ma@amd.com> |
drm/amdgpu: move queue_bitmap to an independent structure (v3) To allocate independent queue_bitmap for each XCD, then the old bitmap policy can be continued to use with a clear logic. Use mec_bitmap[0] as default for all non-GC 9.4.3 IPs. v2: squash commits to avoid breaking the build v3: unify naming style Signed-off-by: Le Ma <le.ma@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
277bd337 |
|
23-May-2022 |
Le Ma <le.ma@amd.com> |
drm/amdgpu: convert gfx.kiq to array type (v3) v1: more kiq instances are a available in SOC (Le) v2: squash commits to avoid breaking the build (Le) v3: make the conversion for gfx/mec v11_0 (Hawking) Signed-off-by: Le Ma <le.ma@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
19d88e1d |
|
13-Jan-2023 |
Dan Carpenter <error27@gmail.com> |
drm/amdgpu: Add a missing tab This tab was deleted accidentally and triggers a Smatch warning: drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c:1006 gfx_v8_0_init_microcode() warn: inconsistent indenting Add it back. Fixes: 0aaafb7359d2 ("drm/amd: Use `amdgpu_ucode_*` helpers for GFX8") Signed-off-by: Dan Carpenter <error27@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
0aaafb73 |
|
04-Jan-2023 |
Mario Limonciello <mario.limonciello@amd.com> |
drm/amd: Use `amdgpu_ucode_*` helpers for GFX8 The `amdgpu_ucode_request` helper will ensure that the return code for missing firmware is -ENODEV so that early_init can fail. The `amdgpu_ucode_release` helper is for symmetry on unloading. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Lijo Lazar <lijo.lazar@amd.com> Signed-off-by: Mario Limonciello <mario.limonciello@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
58ab2c08 |
|
14-Jan-2022 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: use VRAM|GTT for a bunch of kernel allocations Technically all of those can use GTT as well, no need to force things into VRAM. Signed-off-by: Christian König <christian.koenig@amd.com> Signed-off-by: Luben Tuikov <luben.tuikov@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
ec4927d4 |
|
25-Oct-2022 |
Victor Zhao <Victor.Zhao@amd.com> |
drm/amdgpu: fix for suspend/resume sequence under sriov - clear kiq ring after suspend/resume under sriov to aviod kiq ring test failure - update irq after resume to fix kiq interrput loss Signed-off-by: Victor Zhao <Victor.Zhao@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
ab5a7fb6 |
|
21-May-2022 |
Julia Lawall <Julia.Lawall@inria.fr> |
drm/amdgpu/gfx: fix typos in comments Spelling mistakes (triple letters) in comments. Detected with the help of Coccinelle. Signed-off-by: Julia Lawall <Julia.Lawall@inria.fr> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
84203554 |
|
17-May-2022 |
Haohui Mai <ricetons@gmail.com> |
drm/amdgpu: Set CP_HQD_PQ_CONTROL.RPTR_BLOCK_SIZE correctly Remove the accidental shifts on the values of RPTR_BLOCK_SIZE in gfx_v8-v11. The bug essentially always programs the corresponding fields to zero instead of the correct value. The hardware clamps the min value to 5 so this resulted in a value of 5 being programmed. Signed-off-by: Haohui Mai <ricetons@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
d54762cc |
|
05-May-2022 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: nuke dynamic gfx scratch reg allocation It's over a decade ago that this was actually used for more than ring and IB tests. Just use the static register directly where needed and nuke the now useless infrastructure. Signed-off-by: Christian König <christian.koenig@amd.com> Acked-by: Lang Yu <Lang.Yu@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
3748424b |
|
19-Mar-2020 |
Jack Xiao <Jack.Xiao@amd.com> |
drm/amdgpu: use ring structure to access rptr/wptr v2 Use ring structure to access the cpu/gpu address of rptr/wptr. v2: merge gfx10/sdma5/sdma5.2 patches Signed-off-by: Jack Xiao <Jack.Xiao@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
6f90a49b |
|
08-Apr-2022 |
Grigory Vasilyev <h0tc0d3@gmail.com> |
drm/amdgpu: Fix incorrect enum type Instead of the 'amdgpu_ring_priority_level' type, the 'amdgpu_gfx_pipe_priority' type was used, which is an error when setting ring priority. This is a minor error, but may cause problems in the future. Instead of AMDGPU_RING_PRIO_2 = 2, we can use AMDGPU_RING_PRIO_MAX = 3, but AMDGPU_RING_PRIO_2 = 2 is used for compatibility with AMDGPU_GFX_PIPE_PRIO_HIGH = 2, and not change the behavior of the code. Signed-off-by: Grigory Vasilyev <h0tc0d3@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
25faeddc |
|
25-Mar-2022 |
Evan Quan <evan.quan@amd.com> |
drm/amdgpu: expand cg_flags from u32 to u64 With this, we can support more CG flags. Signed-off-by: Evan Quan <evan.quan@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
e6ef9b39 |
|
03-Nov-2021 |
Evan Quan <evan.quan@amd.com> |
drm/amdgpu: correctly toggle gfx on/off around RLC_SPM_* register access As part of the ib padding process, accessing the RLC_SPM_* register may trigger gfx hang. Since gfxoff may be already kicked during the whole period. To address that, we manually toggle gfx on/off around the RLC_SPM_* register access. This can resolve the gfx hang issue observed on running Talos with RDP launched in parallel. Signed-off-by: Evan Quan <evan.quan@amd.com> Acked-by: Guchun Chen <guchun.chen@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
685967b3 |
|
29-Jun-2021 |
Joseph Greathouse <Joseph.Greathouse@amd.com> |
drm/amdgpu: Put MODE register in wave debug info Add the MODE register into the per-wave debug information. This register holds state such as FP rounding and denorm modes, which exceptions are enabled, and active clamping modes. Signed-off-by: Joseph Greathouse <Joseph.Greathouse@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c107171b |
|
02-Feb-2021 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: add the sched_score to amdgpu_ring_init Allow separate ring to share the same scheduler score. No functional change. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-and-Tested-by: Leo Liu <leo.liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
8b75c9b4 |
|
09-Feb-2021 |
Sebastian Andrzej Siewior <bigeasy@linutronix.de> |
drm/amdgpu: Replace in_task() in gfx_v8_0_parse_sq_irq() gfx_v8_0_parse_sq_irq() is using in_task() to distinguish if it is invoked from a workqueue worker or directly from the interrupt handler. The usage of in_interrupt() in drivers is phased out and Linus clearly requested that code which changes behaviour depending on context should either be separated or the context be conveyed in an argument passed by the caller, which usually knows the context. gfx_v8_0_parse_sq_irq() is invoked directly either from a worker or from the interrupt service routine. The worker is only bypassed if the worker is already busy. Add an argument `from_wq' to gfx_v8_0_parse_sq_irq() which is true if invoked from the worker. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
f8bf6450 |
|
03-Feb-2021 |
Nirmoy Das <nirmoy.das@amd.com> |
drm/amdgpu: enable wave limit on non high prio cs pipes To achieve the best QoS for high priority compute jobs it is required to limit waves on other compute pipes as well. This patch will set min value in non high priority mmSPI_WCL_PIPE_PERCENT_CS[0-3] registers to minimize the impact of normal/low priority compute jobs over high priority compute jobs. Signed-off-by: Nirmoy Das <nirmoy.das@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
0a52a6ca |
|
27-Jan-2021 |
Nirmoy Das <nirmoy.das@amd.com> |
drm/amdgpu: add wave limit functionality for gfx8,9 Wave limiting can be use to load balance high priority compute jobs along with gfx jobs. When enabled, this will reserve ~75% of waves for compute jobs. We do not need this from gfx10 onwards because >=gfx10 has asynchronous compute tunneling to replace wave limit requirement. Signed-off-by: Nirmoy Das <nirmoy.das@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
8c0225d7 |
|
31-Jan-2021 |
Nirmoy Das <nirmoy.das@amd.com> |
drm/amdgpu: enable only one high prio compute queue For high priority compute to work properly we need to enable wave limiting on gfx pipe. Wave limiting is done through writing into mmSPI_WCL_PIPE_PERCENT_GFX register. Enable only one high priority compute queue to avoid race condition between multiple high priority compute queues writing that register simultaneously. Signed-off-by: Nirmoy Das <nirmoy.das@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
68fce5f0 |
|
08-Dec-2020 |
Nirmoy Das <nirmoy.das@amd.com> |
drm/amdgpu: use AMDGPU_NUM_VMID when possible Replace hardcoded vmid number with AMDGPU_NUM_VMID macro. Signed-off-by: Nirmoy Das <nirmoy.das@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c5ce5115 |
|
24-Nov-2020 |
Lee Jones <lee.jones@linaro.org> |
drm/amd/amdgpu/gfx_v8_0: Functions must follow directly after their headers Fixes the following W=1 kernel build warning(s): drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c:3698: warning: Excess function parameter 'adev' description in 'DEFAULT_SH_MEM_BASES' Cc: Alex Deucher <alexander.deucher@amd.com> Cc: "Christian König" <christian.koenig@amd.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Sumit Semwal <sumit.semwal@linaro.org> Cc: amd-gfx@lists.freedesktop.org Cc: dri-devel@lists.freedesktop.org Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Signed-off-by: Lee Jones <lee.jones@linaro.org> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
3f66bf40 |
|
09-Nov-2020 |
Nirmoy Das <nirmoy.das@amd.com> |
drm/amdgpu: fix compute queue priority if num_kcq is less than 4 Compute queues are configurable with module param, num_kcq. amdgpu_gfx_is_high_priority_compute_queue was setting 1st 4 queues to high priority queue leaving a null drm scheduler in adev->gpu_sched[hw_ip]["normal_prio"].sched if num_kcq < 5. This patch tries to fix it by alternating compute queue priority between normal and high priority. Fixes: 33abcb1f5a1719b1c (drm/amdgpu: set compute queue priority at mqd_init) Signed-off-by: Nirmoy Das <nirmoy.das@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
99dac206 |
|
02-Nov-2020 |
Deepak R Varma <mh12gx2825@gmail.com> |
drm/amdgpu/gfx: improve code indentation and alignment General code indentation and alignment changes such as replace spaces by tabs or align function arguments as per the coding style guidelines. Issue reported by checkpatch script. Signed-off-by: Deepak R Varma <mh12gx2825@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
92995254 |
|
18-Jun-2020 |
Evan Quan <evan.quan@amd.com> |
drm/amdgpu: correct CG_ACLK_CNTL setting Correct polaris CG_ACLK_CNTL setting. Signed-off-by: Evan Quan <evan.quan@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
a3bab325 |
|
16-Oct-2020 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: move amdgpu_num_kcq handling to a helper Add a helper so we can set per asic default values. Also, the module parameter is currently clamped to 8, but clamp it per asic just in case some asics have different limits in the future. Enable the option on gfx6,7 as well for consistency. Acked-by: Nirmoy Das <nirmoy.das@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
53b3f8f4 |
|
19-Aug-2020 |
Dennis Li <Dennis.Li@amd.com> |
drm/amdgpu: refine codes to avoid reentering GPU recovery if other threads have holden the reset lock, recovery will fail to try_lock. Therefore we introduce atomic hive->in_reset and adev->in_gpu_reset, to avoid reentering GPU recovery. v2: drop "? true : false" in the definition of amdgpu_in_reset Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Dennis Li <Dennis.Li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
df561f66 |
|
23-Aug-2020 |
Gustavo A. R. Silva <gustavoars@kernel.org> |
treewide: Use fallthrough pseudo-keyword Replace the existing /* fall through */ comments and its variants with the new pseudo-keyword macro fallthrough[1]. Also, remove unnecessary fall-through markings when it is the case. [1] https://www.kernel.org/doc/html/v5.7/process/deprecated.html?highlight=fallthrough#implicit-switch-case-fall-through Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
|
#
70bdb6ed |
|
11-Aug-2020 |
Evan Quan <evan.quan@amd.com> |
drm/amd/powerplay: drop unnecessary pp_funcs checker It's redundant. Also, the callers should not care about the implementation details. Signed-off-by: Evan Quan <evan.quan@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Nirmoy Das <nirmoy.das@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
b89e9eb6 |
|
11-Aug-2020 |
Evan Quan <evan.quan@amd.com> |
drm/amd/powerplay: optimize amdgpu_dpm_set_clockgating_by_smu() implementation Cover the implementation details from outside(of power part). Signed-off-by: Evan Quan <evan.quan@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Nirmoy Das <nirmoy.das@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
f1403342 |
|
12-Aug-2020 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: revert "fix system hang issue during GPU reset" The whole approach wasn't thought through till the end. We already had a reset lock like this in the past and it caused the same problems like this one. Completely revert the patch for now and add individual trylock protection to the hardware access functions as necessary. This reverts commit df9c8d1aa278c435c30a69b8f2418b4a52fcb929. Signed-off-by: Christian König <christian.koenig@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
a300de40 |
|
27-Jul-2020 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu: introduce a new parameter to configure how many KCQ we want(v5) what: the MQD's save and restore of KCQ (kernel compute queue) cost lots of clocks during world switch which impacts a lot to multi-VF performance how: introduce a paramter to control the number of KCQ to avoid performance drop if there is no kernel compute queue needed notes: this paramter only affects gfx 8/9/10 v2: refine namings v3: choose queues for each ring to that try best to cross pipes evenly. v4: fix indentation some cleanupsin the gfx_compute_queue_acquire() v5: further fix on indentations more cleanupsin gfx_compute_queue_acquire() TODO: in the future we will let hypervisor driver to set this paramter automatically thus no need for user to configure it through modprobe in virtual machine Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
df9c8d1a |
|
08-Jul-2020 |
Dennis Li <Dennis.Li@amd.com> |
drm/amdgpu: fix system hang issue during GPU reset when GPU hang, driver has multi-paths to enter amdgpu_device_gpu_recover, the atomic adev->in_gpu_reset and hive->in_reset are used to avoid re-entering GPU recovery. During GPU reset and resume, it is unsafe that other threads access GPU, which maybe cause GPU reset failed. Therefore the new rw_semaphore adev->reset_sem is introduced, which protect GPU from being accessed by external threads during recovery. v2: 1. add rwlock for some ioctls, debugfs and file-close function. 2. change to use dqm->is_resetting and dqm_lock for protection in kfd driver. 3. remove try_lock and change adev->in_gpu_reset as atomic, to avoid re-enter GPU recovery for the same GPU hang. v3: 1. change back to use adev->reset_sem to protect kfd callback functions, because dqm_lock couldn't protect all codes, for example: free_mqd must be called outside of dqm_lock; [ 1230.176199] Hardware name: Supermicro SYS-7049GP-TRT/X11DPG-QT, BIOS 3.1 05/23/2019 [ 1230.177221] Call Trace: [ 1230.178249] dump_stack+0x98/0xd5 [ 1230.179443] amdgpu_virt_kiq_reg_write_reg_wait+0x181/0x190 [amdgpu] [ 1230.180673] gmc_v9_0_flush_gpu_tlb+0xcc/0x310 [amdgpu] [ 1230.181882] amdgpu_gart_unbind+0xa9/0xe0 [amdgpu] [ 1230.183098] amdgpu_ttm_backend_unbind+0x46/0x180 [amdgpu] [ 1230.184239] ? ttm_bo_put+0x171/0x5f0 [ttm] [ 1230.185394] ttm_tt_unbind+0x21/0x40 [ttm] [ 1230.186558] ttm_tt_destroy.part.12+0x12/0x60 [ttm] [ 1230.187707] ttm_tt_destroy+0x13/0x20 [ttm] [ 1230.188832] ttm_bo_cleanup_memtype_use+0x36/0x80 [ttm] [ 1230.189979] ttm_bo_put+0x1be/0x5f0 [ttm] [ 1230.191230] amdgpu_bo_unref+0x1e/0x30 [amdgpu] [ 1230.192522] amdgpu_amdkfd_free_gtt_mem+0xaf/0x140 [amdgpu] [ 1230.193833] free_mqd+0x25/0x40 [amdgpu] [ 1230.195143] destroy_queue_cpsch+0x1a7/0x270 [amdgpu] [ 1230.196475] pqm_destroy_queue+0x105/0x260 [amdgpu] [ 1230.197819] kfd_ioctl_destroy_queue+0x37/0x70 [amdgpu] [ 1230.199154] kfd_ioctl+0x277/0x500 [amdgpu] [ 1230.200458] ? kfd_ioctl_get_clock_counters+0x60/0x60 [amdgpu] [ 1230.201656] ? tomoyo_file_ioctl+0x19/0x20 [ 1230.202831] ksys_ioctl+0x98/0xb0 [ 1230.204004] __x64_sys_ioctl+0x1a/0x20 [ 1230.205174] do_syscall_64+0x5f/0x250 [ 1230.206339] entry_SYSCALL_64_after_hwframe+0x49/0xbe 2. remove try_lock and introduce atomic hive->in_reset, to avoid re-enter GPU recovery. v4: 1. remove an unnecessary whitespace change in kfd_chardev.c 2. remove comment codes in amdgpu_device.c 3. add more detailed comment in commit message 4. define a wrap function amdgpu_in_reset v5: 1. Fix some style issues. Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Suggested-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Suggested-by: Christian König <christian.koenig@amd.com> Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com> Suggested-by: Lijo Lazar <Lijo.Lazar@amd.com> Suggested-by: Luben Tukov <luben.tuikov@amd.com> Signed-off-by: Dennis Li <Dennis.Li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
40111ec2 |
|
24-Jun-2020 |
Felix Kuehling <Felix.Kuehling@amd.com> |
drm/amdgpu: Clean up KFD VMID assignment The KFD VMID assignment was hard-coded in a few places. Consolidate that in a single variable adev->vm_manager.first_kfd_vmid. The value is still assigned in gmc-ip-version-specific code. Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
f3167919 |
|
18-Jun-2020 |
Nirmoy Das <nirmoy.das@amd.com> |
drm/amdgpu: label internally used symbols as static Used sparse(make C=1) to find these loose ends. v2: removed unwanted extra line Signed-off-by: Nirmoy Das <nirmoy.das@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
d35745bb |
|
27-Apr-2020 |
Marek Olšák <marek.olsak@amd.com> |
drm/amdgpu: apply AMDGPU_IB_FLAG_EMIT_MEM_SYNC to compute IBs too (v3) Compute IBs need this too. v2: split out version bump v3: squash in emit frame count fixes Signed-off-by: Marek Olšák <marek.olsak@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
2f9ce2a3 |
|
08-May-2020 |
Andrey Grodzovsky <andrey.grodzovsky@amd.com> |
drm/amdgpu: Add mem_sync implementation for all the ASICs. Implement the .mem_sync hook defined earlier. v2: Rename functions Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Reviewed-by: Luben Tuikov <luben.tuikov@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
0bb5d5b0 |
|
22-Apr-2020 |
Luben Tuikov <luben.tuikov@amd.com> |
drm/amdgpu: Move to a per-IB secure flag (TMZ) Move from a per-CS secure flag (TMZ) to a per-IB secure flag. Signed-off-by: Luben Tuikov <luben.tuikov@amd.com> Reviewed-by: Huang Rui <ray.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
8350361d |
|
22-Apr-2020 |
Huang Rui <ray.huang@amd.com> |
drm/amdgpu: expand the context control interface with trust flag This patch expands the context control function to support trusted flag while we want to set command buffer in trusted mode. Signed-off-by: Huang Rui <ray.huang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
54208194 |
|
22-Apr-2020 |
Yintian Tao <yttao@amd.com> |
drm/amdgpu: request reg_val_offs each kiq read reg According to the current kiq read register method, there will be race condition when using KIQ to read register if multiple clients want to read at same time just like the expample below: 1. client-A start to read REG-0 throguh KIQ 2. client-A poll the seqno-0 3. client-B start to read REG-1 through KIQ 4. client-B poll the seqno-1 5. the kiq complete these two read operation 6. client-A to read the register at the wb buffer and get REG-1 value Therefore, use amdgpu_device_wb_get() to request reg_val_offs for each kiq read register. v2: fix the error remove v3: fix the print typo v4: remove unused variables Signed-off-by: Yintian Tao <yttao@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
e09d40bd |
|
21-Apr-2020 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: change how we update mmRLC_SPM_MC_CNTL In pp_one_vf mode avoid the extra overhead and read/write the registers without the KIQ. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Monk Liu <monk.liu@amd.com> Acked-by: Yintian Tao <yintian.tao@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
1c6d567b |
|
01-Apr-2020 |
Nirmoy Das <nirmoy.das@amd.com> |
drm/amdgpu: rework sched_list generation Generate HW IP's sched_list in amdgpu_ring_init() instead of amdgpu_ctx.c. This makes amdgpu_ctx_init_compute_sched(), ring.has_high_prio and amdgpu_ctx_init_sched() unnecessary. This patch also stores sched_list for all HW IPs in one big array in struct amdgpu_device which makes amdgpu_ctx_init_entity() much more leaner. v2: fix a coding style issue do not use drm hw_ip const to populate amdgpu_ring_type enum v3: remove ctx reference and move sched array and num_sched to a struct use num_scheds to detect uninitialized scheduler list v4: use array_index_nospec for user space controlled variables fix possible checkpatch.pl warnings Signed-off-by: Nirmoy Das <nirmoy.das@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
1675c3a2 |
|
21-Feb-2020 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: stop disable the scheduler during HW fini When we stop the HW for example for GPU reset we should not stop the front-end scheduler. Otherwise we run into intermediate failures during command submission. The scheduler should only be stopped in very few cases: 1. We can't get the hardware working in ring or IB test after a GPU reset. 2. The KIQ scheduler is not used in the front-end and should be disabled during GPU reset. 3. In amdgpu_ring_fini() when the driver unloads. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Nirmoy Das <nirmoy.das@amd.com> Test-by: Dennis Li <dennis.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c8e42d57 |
|
25-Mar-2020 |
xinhui pan <xinhui.pan@amd.com> |
drm/amdgpu: implement more ib pools (v2) We have three ib pools, they are normal, VM, direct pools. Any jobs which schedule IBs without dependence on gpu scheduler should use DIRECT pool. Any jobs schedule direct VM update IBs should use VM pool. Any other jobs use NORMAL pool. v2: squash in coding style fix Signed-off-by: xinhui pan <xinhui.pan@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
552b80d7 |
|
27-Feb-2020 |
Nirmoy Das <nirmoy.das@amd.com> |
drm/amdgpu: remove unused functions AMDGPU statically sets priority for compute queues at initialization so remove all the functions responsible for changing compute queue priority dynamically. Signed-off-by: Nirmoy Das <nirmoy.das@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
33abcb1f |
|
27-Feb-2020 |
Nirmoy Das <nirmoy.das@amd.com> |
drm/amdgpu: set compute queue priority at mqd_init We were changing compute ring priority while rings were being used before every job submission which is not recommended. This patch sets compute queue priority at mqd initialization for gfx8, gfx9 and gfx10. Policy: make queue 0 of each pipe as high priority compute queue High/normal priority compute sched lists are generated from set of high/normal priority compute queues. At context creation, entity of compute queue get a sched list from high or normal priority depending on ctx->priority Signed-off-by: Nirmoy Das <nirmoy.das@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
752c683d |
|
19-Feb-2020 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu: fix IB test MCBP bug 1)for gfx IB test we shouldn't insert DE meta data 2)we should make sure IB test finished before we send event 3 to hypervisor otherwise the IDLE from event 3 will preempt IB test, which is not designed as a compatible structure for MCBP Signed-off-by: Monk Liu <Monk.Liu@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
460c484f |
|
27-Feb-2020 |
Jacob He <jacob.he@amd.com> |
drm/amdgpu: Initialize SPM_VMID with 0xf (v2) SPM_VMID is a global resource, SPM access the video memory according to SPM_VMID. The initial valude of SPM_VMID is 0 which is used by kernel. That means UMD can overwrite the memory of VMID0 by enabling SPM, that is really dangerous. Initialize SPM_VMID with 0xf, it messes up other user mode process at most. v2: squash in indentation fix Signed-off-by: Jacob He <jacob.he@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
94b5c215 |
|
25-Feb-2020 |
Yong Zhao <Yong.Zhao@amd.com> |
drm/amdgpu: Add num_banks and num_ranks to gfx config structure The two members will be used by KFD later. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
d33a99c4 |
|
14-Jan-2020 |
chen gong <curry.gong@amd.com> |
drm/amdgpu: provide a generic function interface for reading/writing register by KIQ Move amdgpu_virt_kiq_rreg/amdgpu_virt_kiq_wreg function to amdgpu_gfx.c, and rename them to amdgpu_kiq_rreg/amdgpu_kiq_wreg.Make it generic and flexible. Signed-off-by: chen gong <curry.gong@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Huang Rui <ray.huang@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
0e5b7a95 |
|
09-Jan-2020 |
Huang Rui <ray.huang@amd.com> |
drm/amdgpu: only set cp active field for kiq queue The mec ucode will set the CP_HQD_ACTIVE bit while the queue is mapped by MAP_QUEUES packet. So we only need set cp active field for kiq queue. Signed-off-by: Huang Rui <ray.huang@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
bf26da92 |
|
27-Nov-2019 |
Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com> |
drm/amdgpu: add cache flush workaround to gfx8 emit_fence The same workaround is used for gfx7. Both PAL and Mesa use it for gfx8 too, so port this commit to gfx_v8_0_ring_emit_fence_gfx. Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
b456c932 |
|
27-Nov-2019 |
Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com> |
drm/amdgpu: add cache flush workaround to gfx8 emit_fence The same workaround is used for gfx7. Both PAL and Mesa use it for gfx8 too, so port this commit to gfx_v8_0_ring_emit_fence_gfx. Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
747d4f71 |
|
26-Nov-2019 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu: fix calltrace during kmd unload(v3) issue: kernel would report a warning from a double unpin during the driver unloading on the CSB bo why: we unpin it during hw_fini, and there will be another unpin in sw_fini on CSB bo. fix: actually we don't need to pin/unpin it during hw_init/fini since it is created with kernel pinned, we only need to fullfill the CSB again during hw_init to prevent CSB/VRAM lost after S3 v2: get_csb in init_rlc so hw_init() will make CSIB content back even after reset or s3 v3: use bo_create_kernel instead of bo_create_reserved for CSB otherwise the bo_free_kernel() on CSB is not aligned and would lead to its internal reserve pending there forever take care of gfx7/8 as well Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: Xiaojie Yuan <xiaojie.yuan@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
82a829dc |
|
26-Nov-2019 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu: fix calltrace during kmd unload(v3) issue: kernel would report a warning from a double unpin during the driver unloading on the CSB bo why: we unpin it during hw_fini, and there will be another unpin in sw_fini on CSB bo. fix: actually we don't need to pin/unpin it during hw_init/fini since it is created with kernel pinned, we only need to fullfill the CSB again during hw_init to prevent CSB/VRAM lost after S3 v2: get_csb in init_rlc so hw_init() will make CSIB content back even after reset or s3 v3: use bo_create_kernel instead of bo_create_reserved for CSB otherwise the bo_free_kernel() on CSB is not aligned and would lead to its internal reserve pending there forever take care of gfx7/8 as well Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: Xiaojie Yuan <xiaojie.yuan@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
e98042db |
|
04-Nov-2019 |
yu kuai <yukuai3@huawei.com> |
drm/amdgpu: remove set but not used variable 'mc_shared_chmap' Fixes gcc '-Wunused-but-set-variable' warning: drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c: In function ‘gfx_v8_0_gpu_early_init’: drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c:1713:6: warning: variable ‘mc_shared_chmap’ set but not used [-Wunused-but-set-variable] Fixes: 0bde3a95eaa9 ("drm/amdgpu: split gfx8 gpu init into sw and hw parts") Signed-off-by: yu kuai <yukuai3@huawei.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
9f0256da |
|
23-Oct-2019 |
Nirmoy Das <nirmoy.das@amd.com> |
drm/amdgpu: remove unused parameter in amdgpu_gfx_kiq_free_ring Signed-off-by: Nirmoy Das <nirmoy.das@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
72cda9bb |
|
02-Aug-2019 |
Likun Gao <Likun.Gao@amd.com> |
drm/amdgpu: pin the csb buffer on hw init for gfx v8 Without this pin, the csb buffer will be filled with inconsistent data after S3 resume. And that will causes gfx hang on gfxoff exit since this csb will be executed then. Signed-off-by: Likun Gao <Likun.Gao@amd.com> Tested-by: Paul Gover <pmw.gover@yahoo.co.uk> Reviewed-by: Feifei Xu <Feifei.Xu@amd.com> Reviewed-by: Xiaojie Yuan <xiaojie.yuan@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
1f288afc |
|
02-Aug-2019 |
Likun Gao <Likun.Gao@amd.com> |
drm/amdgpu: pin the csb buffer on hw init for gfx v8 Without this pin, the csb buffer will be filled with inconsistent data after S3 resume. And that will causes gfx hang on gfxoff exit since this csb will be executed then. Signed-off-by: Likun Gao <Likun.Gao@amd.com> Tested-by: Paul Gover <pmw.gover@yahoo.co.uk> Reviewed-by: Feifei Xu <Feifei.Xu@amd.com> Reviewed-by: Xiaojie Yuan <xiaojie.yuan@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
2c897318 |
|
26-Jul-2019 |
Joseph Greathouse <Joseph.Greathouse@amd.com> |
drm/amdgpu: Default disable GDS for compute+gfx Units in the GDS block default to allowing all VMIDs access to all entries. Disable shader access to the GDS, GWS, and OA blocks from all compute and gfx VMIDs by default. For compute, HWS firmware will set up the access bits for the appropriate VMID when a compute queue requires access to these blocks. The driver will handle enabling access on-demand for graphics VMIDs. Leaving VMID0 with full access because otherwise HWS cannot save or restore values during task switch. v2: Fixed code and comment styling. Signed-off-by: Joseph Greathouse <Joseph.Greathouse@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
fbdc5d8d |
|
17-Jul-2019 |
Joseph Greathouse <Joseph.Greathouse@amd.com> |
drm/amdgpu: Default disable GDS for compute VMIDs The GDS and GWS blocks default to allowing all VMIDs to access all entries. Graphics VMIDs can handle setting these limits when the driver launches work. However, compute workloads under HWS control don't go through the kernel driver. Instead, HWS firmware should set these limits when a process is put into a VMID slot. Disable access to these devices by default by turning off all mask bits (for OA) and setting BASE=SIZE=0 (for GDS and GWS) for all compute VMIDs. If a process wants to use these resources, they can request this from the HWS firmware (when such capabilities are enabled). HWS will then handle setting the base and limit for the process when it is assigned to a VMID. This will also prevent user kernels from getting 'stuck' in GWS by accident if they write GWS-using code but HWS firmware is not set up to handle GWS reset. Until HWS is enabled to handle GWS properly, all GWS accesses will MEM_VIOL fault the kernel. v2: Move initialization outside of SRBM mutex Signed-off-by: Joseph Greathouse <Joseph.Greathouse@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
ad28e024 |
|
17-Jul-2019 |
Joseph Greathouse <Joseph.Greathouse@amd.com> |
drm/amdgpu: Default disable GDS for compute VMIDs The GDS and GWS blocks default to allowing all VMIDs to access all entries. Graphics VMIDs can handle setting these limits when the driver launches work. However, compute workloads under HWS control don't go through the kernel driver. Instead, HWS firmware should set these limits when a process is put into a VMID slot. Disable access to these devices by default by turning off all mask bits (for OA) and setting BASE=SIZE=0 (for GDS and GWS) for all compute VMIDs. If a process wants to use these resources, they can request this from the HWS firmware (when such capabilities are enabled). HWS will then handle setting the base and limit for the process when it is assigned to a VMID. This will also prevent user kernels from getting 'stuck' in GWS by accident if they write GWS-using code but HWS firmware is not set up to handle GWS reset. Until HWS is enabled to handle GWS properly, all GWS accesses will MEM_VIOL fault the kernel. v2: Move initialization outside of SRBM mutex Signed-off-by: Joseph Greathouse <Joseph.Greathouse@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
0fa4246e |
|
12-Jul-2019 |
Tom St Denis <tom.stdenis@amd.com> |
drm/amd/amdgpu: Add VMID to SRBM debugfs bank selection Add 5 bits to the offset for SRBM selection to handle VMIDs. Also update the select_me_pipe_q() callback to also select VMID. Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
d12c2022 |
|
03-Jul-2019 |
Fuqian Huang <huangfq.daxian@gmail.com> |
drm/amdgpu: Use kmemdup rather than duplicating its implementation kmemdup is introduced to duplicate a region of memory in a neat way. Rather than kmalloc/kzalloc + memcpy, which the programmer needs to write the size twice (sometimes lead to mistakes), kmemdup improves readability, leads to smaller code and also reduce the chances of mistakes. Suggestion to use kmemdup rather than using kmalloc/kzalloc + memcpy. Reviewed-by: Christian König <Christian.Koenig@amd.com> Reviewed-by: Emil Velikov <emil.velikov@collabora.com> Signed-off-by: Fuqian Huang <huangfq.daxian@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
53b2fe41 |
|
11-Mar-2019 |
Hawking Zhang <Hawking.Zhang@amd.com> |
drm/amdgpu: enable gfx eop interrupt per gfx pipe Navi10 has 2 gfx pipe and need to enable gfx eop interrupt per pipe, instead of enable eop int for all gfx pipes at one time. Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
4fc6a88f |
|
31-Jul-2018 |
Hawking Zhang <Hawking.Zhang@amd.com> |
drm/amdgpu: rename amdgpu_gfx_compute_mqd_sw_init The function now will create mqd bos for both gfx queue and compute queue Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: Jack Xiao <jack.xiao@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
7470bfcf |
|
31-Jul-2018 |
Hawking Zhang <Hawking.Zhang@amd.com> |
drm/amdgpu: add helper function for gfx queue/bitmap transition Similar to what we do for compute already. Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: Jack Xiao <jack.xiao@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
47b757fb |
|
09-Jun-2019 |
Sam Ravnborg <sam@ravnborg.org> |
drm/amd: drop use of drmP.h in remaining files With this commit drm/amd/ has no longer any uses of the deprecated drmP.h header file. Signed-off-by: Sam Ravnborg <sam@ravnborg.org> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Cc: "Christian König" <christian.koenig@amd.com> Cc: "David (ChunMing) Zhou" <David1.Zhou@amd.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20190609220757.10862-11-sam@ravnborg.org
|
#
c366be54 |
|
09-Jun-2019 |
Sam Ravnborg <sam@ravnborg.org> |
drm/amd: drop dependencies on drm_os_linux.h Fix so no files in drm/amd/ depends on the deprecated drm_os_linux.h header file. It was done manually: - remove drm_os_linux.h from drmP.h - fix all build errros Signed-off-by: Sam Ravnborg <sam@ravnborg.org> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Cc: "Christian König" <christian.koenig@amd.com> Cc: "David (ChunMing) Zhou" <David1.Zhou@amd.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20190609220757.10862-3-sam@ravnborg.org
|
#
dca29491 |
|
10-May-2019 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: remove static GDS, GWS and OA allocation As far as we know this was never used by userspace and so should be removed. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Marek Olšák <marek.olsak@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
a7dc289b |
|
01-Mar-2019 |
Gustavo A. R. Silva <gustavo@embeddedor.com> |
drm/amdgpu/gfx_v8_0: Mark expected switch fall-through In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. This patch fixes the following warning: drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c: In function ‘gfx_v8_0_tiling_mode_table_init’: ./include/linux/device.h:1487:2: warning: this statement may fall through [-Wimplicit-fallthrough=] _dev_warn(dev, dev_fmt(fmt), ##__VA_ARGS__) ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c:3236:3: note: in expansion of macro ‘dev_warn’ dev_warn(adev->dev, ^~~~~~~~ drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c:3240:2: note: here case CHIP_CARRIZO: ^~~~ Warning level 3 was used: -Wimplicit-fallthrough=3 This patch is part of the ongoing efforts to enable -Wimplicit-fallthrough. Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
a4a3ad35 |
|
19-Feb-2019 |
Yong Zhao <Yong.Zhao@amd.com> |
Revert "drm/amdgpu: Fix bugs in setting CP RB/MEC DOORBELL_RANGE registers" The original change caused a regression, so revert it until the new fix is ready. BUG: https://bugs.freedesktop.org/show_bug.cgi?id=109650 This reverts commit 764c85fef41722db0f21558c6c2fb38bee172d19. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
74b9b3ea |
|
05-Feb-2019 |
Yong Zhao <Yong.Zhao@amd.com> |
drm/amdgpu: Fix bugs in setting CP RB/MEC DOORBELL_RANGE registers CP_RB_DOORBELL_RANGE_LOWER/UPPER and CP_MEC_DOORBELL_RANGE_LOWER/UPPER are used for waking up an idle scheduler and for power gating support. Usually the first few doorbells in pci doorbell bar are used for RB and all leftover for MEC. This patch fixes the incorrect settings. Theoretically, gfx ring doorbells should come before all MEC doorbells to be consistent with the design. However, since the doorbell allocations are agreed by all and we are not free to change them, also considering the kernel MEC ring doorbells which are before gfx ring doorbells are not used often, we compromise by leaving the doorbell allocations unchanged. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
41cca166 |
|
21-Jan-2019 |
Marek Olšák <marek.olsak@amd.com> |
drm/amdgpu: add a workaround for GDS ordered append hangs with compute queues I'm not increasing the DRM version because GDS isn't totally without bugs yet. v2: update emit_ib_size Signed-off-by: Marek Olšák <marek.olsak@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c4c905ec |
|
18-Jan-2019 |
Jack Xiao <Jack.Xiao@amd.com> |
drm/amdgpu: add flags to emit_ib interface v2 Replace the last bool type parameter with a general flags parameter, to make the last parameter be able to contain more information. v2: drop setting need_ctx_switch = false Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Jack Xiao <Jack.Xiao@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c4312c27 |
|
03-Jan-2019 |
Kent Russell <kent.russell@amd.com> |
drm/amdgpu: Cleanup 2 compiler warnings These 2 variables are unused now, so remove their references. Fixes: e4ae0fc drm/amdgpu: implement gfx8 post_soft_reset Fixes: 5e01c09 drm/amdgpu/gfx_v8_0: Reorder the gfx, kiq and kcq rings test sequence Signed-off-by: Kent Russell <kent.russell@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c6064de4 |
|
23-Dec-2018 |
Tiecheng Zhou <Tiecheng.Zhou@amd.com> |
drm/amdgpu/gfx_v8_0: Reorder the gfx, kiq and kcq rings test sequence The kiq ring and the very first compute ring may fail occasionally if they are tested directly following kiq_kcq_enable. Insert the gfx ring test before kiq ring test to delay the kiq and kcq ring tests will fix the issue. Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Tiecheng Zhou <Tiecheng.Zhou@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
96d8f63c |
|
03-Jan-2019 |
Kent Russell <kent.russell@amd.com> |
drm/amdgpu: Cleanup 2 compiler warnings These 2 variables are unused now, so remove their references. Fixes: e4ae0fc drm/amdgpu: implement gfx8 post_soft_reset Fixes: 5e01c09 drm/amdgpu/gfx_v8_0: Reorder the gfx, kiq and kcq rings test sequence Signed-off-by: Kent Russell <kent.russell@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
e49cddcd |
|
23-Dec-2018 |
Tiecheng Zhou <Tiecheng.Zhou@amd.com> |
drm/amdgpu/gfx_v8_0: Reorder the gfx, kiq and kcq rings test sequence The kiq ring and the very first compute ring may fail occasionally if they are tested directly following kiq_kcq_enable. Insert the gfx ring test before kiq ring test to delay the kiq and kcq ring tests will fix the issue. Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Tiecheng Zhou <Tiecheng.Zhou@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
2e431a17 |
|
08-Dec-2018 |
YueHaibing <yuehaibing@huawei.com> |
drm/amdgpu: remove set but not used variable 'grbm_soft_reset' Fixes gcc '-Wunused-but-set-variable' warning: drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c: In function 'gfx_v8_0_pre_soft_reset': drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c:4950:27: warning: variable 'srbm_soft_reset' set but not used [-Wunused-but-set-variable] drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c: In function 'gfx_v8_0_post_soft_reset': drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c:5054:27: warning: variable 'srbm_soft_reset' set but not used [-Wunused-but-set-variable] It never used since introduction in commit d31a501ead7f ("drm/amdgpu: add pre_soft_reset ip func") and e4ae0fc33631 ("drm/amdgpu: implement gfx8 post_soft_reset") Reviewed-by: Chunming Zhou <david1.zhou@amd.com> Signed-off-by: YueHaibing <yuehaibing@huawei.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
31edd7c0 |
|
06-Dec-2018 |
Tiecheng Zhou <Tiecheng.Zhou@amd.com> |
drm/amdgpu: bypass RLC init under sriov for Tonga (v2) RLC will go wrong in soft_reset under sriov Workaroound: only need to init RLC csb, and skip RLC stop, reset, start this is because host-driver has already done full initialization on RLC v2: squash in build fix Signed-off-by: Tiecehng Zhou <Tiecheng.Zhou@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
9564f192 |
|
19-Nov-2018 |
Oak Zeng <ozeng@amd.com> |
drm/amdgpu: Use asic specific doorbell index instead of macro definition ASIC specific doorbell layout is used instead of enum definition Signed-off-by: Oak Zeng <ozeng@amd.com> Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com> Suggested-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
39e94569 |
|
19-Nov-2018 |
Brajeswar Ghosh <brajeswar.linux@gmail.com> |
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c: Remove duplicate header Remove gca/gfx_8_0_enum.h which is included more than once Signed-off-by: Brajeswar Ghosh <brajeswar.linux@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
106c7d61 |
|
08-Nov-2018 |
Likun Gao <Likun.Gao@amd.com> |
drm/amdgpu: abstract the function of enter/exit safe mode for RLC Abstract the function of amdgpu_gfx_rlc_enter/exit_safe_mode and some part of rlc_init to improve the reusability of RLC. Signed-off-by: Likun Gao <Likun.Gao@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
88dfc9a3 |
|
07-Nov-2018 |
Likun Gao <Likun.Gao@amd.com> |
drm/amdgpu: separate amdgpu_rlc into a single file Separate the function and struct of RLC from the file of GFX. Abstract the function of amdgpu_gfx_rlc_fini. Signed-off-by: Likun Gao <Likun.Gao@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
fdb81fd7 |
|
28-Sep-2018 |
Likun Gao <Likun.Gao@amd.com> |
drm/amdgpu: unify rlc function into structure Put function rlc_init,rlc_fini,rlc_resume,rlc_stop,rlc_start into structure amdgpu_rlc_funcs and change the method to call rlc function for each verssion of GFX. Signed-off-by: Likun Gao <Likun.Gao@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
34955e03 |
|
23-Oct-2018 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: Modify the argument of emit_ib interface use the point of struct amdgpu_job as the function argument instand of vmid, so the other members of struct amdgpu_job can be visit in emit_ib function. v2: add a wrapper for getting the VMID add the job before the ib on the parameter list. v3: refine the wrapper name Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
98079389 |
|
29-Oct-2018 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: remove messages from IB tests We already print an error message that an IB test failed in the common code. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
315fed03 |
|
29-Oct-2018 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: cleanup skipping IB test on KIQ Instead of hard coding the ring type in the function just never provide a test_ib callback. Additional to that remove the emit_ib callback to make sure the nobody ever tries to execute an IB on the KIQ. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
dc9eeff8 |
|
29-Oct-2018 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: further ring test cleanups Move all error messages from IP specific code into the common helper. This way we now uses the ring name in the messages instead of the index and note which device is affected as well. Also cleanup error handling in the IP specific code and consequently use ETIMEDOUT when the ring test timed out. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c66ed765 |
|
19-Oct-2018 |
Andrey Grodzovsky <andrey.grodzovsky@amd.com> |
drm/amdgpu: Retire amdgpu_ring.ready flag v4 Start using drm_gpu_scheduler.ready isntead. v3: Add helper function to run ring test and set sched.ready flag status accordingly, clean explicit sched.ready sets from the IP specific files. v4: Add kerneldoc and rebase. Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
17e4bd6c |
|
05-Oct-2018 |
Marek Olšák <marek.olsak@amd.com> |
drm/amdgpu: increase the size of HQD EOP buffers Signed-off-by: Marek Olšák <marek.olsak@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
b44da694 |
|
05-Oct-2018 |
Marek Olšák <marek.olsak@amd.com> |
drm/amdgpu: put HQD EOP buffers into VRAM This increases performance of compute queues. EOP events (PKT3_RELEASE_MEM) are stored into these buffers. Signed-off-by: Marek Olšák <marek.olsak@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
898c2cb5 |
|
16-Oct-2018 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: use scheduler fault instead of reset work Signal a fault to the scheduler on an illegal instruction or register access violation instead of kicking of the reset handler directly. Signed-off-by: Christian König <christian.koenig@amd.com> Acked-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
31e3aad6 |
|
25-Oct-2018 |
Andrey Grodzovsky <andrey.grodzovsky@amd.com> |
drm/amdgpu: Fix compute ring 1.0.0 failure after reset Problem: After GPU reset on dGPUs with gfx8 compute ring 1.0.0 fails to pass the ring test. Ring registers inspection shows that it's active and no hang is observed (rptr == wptr) No significant diffs were observed between CP_HQD* registers for the ring in good and bad shape. Fix: No clear reason why but reversing the order of ring tests fixes the problem. Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
7a3e0bb2 |
|
10-Oct-2018 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: Load fw between hw_init/resume_phase1 and phase2 Extract the function of fw loading out of powerplay. Do fw loading between hw_init/resuem_phase1 and phase2 Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
9d5aa2ef |
|
29-Sep-2018 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: Add fw load in gfx_v8 and sdma_v3 gfx and sdma can be initialized before smu. Reviewed-by: Evan Quan <evan.quan@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
9b008fb7 |
|
29-Sep-2018 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: Remove FW_LOAD_DIRECT type support on VI AMDGPU_FW_LOAD_DIRECT is used for bring up. Now it don't work any more. so remove the support. v2: Add warning message if user select AMDGPU_FW_LOAD_DIRECT/AMDGPU_FW_LOAD_PSP on VI. Reviewed-by: Evan Quan <evan.quan@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
bdbb4d6e |
|
04-Oct-2018 |
Shirish S <shirish.s@amd.com> |
drm/amdgpu: remove the intterupt handling for the KIQ events [Why] 1. we never submit IBs to the KIQ 2. there seems to be ~500ms delay during amdgpu resume spent in KIQ, hence pointing toward interrupts are not working correctly. [How] remove interrupt handling for KIQ. Signed-off-by: Shirish S <shirish.s@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com>i Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
44779b43 |
|
29-Sep-2018 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: Move gfx flag in_suspend to adev Move in_suspend flag to adev from gfx, so can be used in other ip blocks, also keep consistent with gpu_in_reset flag. Reviewed-by: Evan Quan <evan.quan@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
1ffdeca6 |
|
17-Sep-2018 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: move more defines into amdgpu_irq.h Everything that isn't related to the IH ring. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Huang Rui <ray.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
722ca51d |
|
20-Sep-2018 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: Remove redundant code in gfx_v8_0.c the CG related registers have been programed in golden setting PG register default value is 0. Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Hang Zhou <hang.zhou@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
5d944aaa |
|
10-Sep-2018 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: Halt rlc/cp in rlc_safe_mode before halt rlc/cp, need to 1. enter rlc safe mode 2. wait rlc/cp idle Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Hang Zhou <hang.zhou@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
434e6df2 |
|
28-Aug-2018 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: Refine function name change function name gfx_v6/7/8/9_0_gpu_init to gfx_v6/7/8/9_0_constants_init. this function is just for init gfx constants such as max pipes, render backends... Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
fd395547 |
|
14-Sep-2018 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: move reserving GDS/GWS/OA into common code We don't need that in the per ASIC code. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
77a2faa5 |
|
14-Sep-2018 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: fix up GDS/GWS/OA shifting That only worked by pure coincident. Completely remove the shifting and always apply correct PAGE_SHIFT. Signed-off-by: Christian König <christian.koenig@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
06668916 |
|
01-Jul-2018 |
A. Wilcox <AWilcox@Wilcox-Tech.com> |
drm/amdgpu: use processed values for counting adev->gfx.rlc has the values from rlc_hdr already processed by le32_to_cpu. Using the rlc_hdr values on big-endian machines causes a kernel Oops due to writing well outside of the array (0x24000000 instead of 0x24). Signed-off-by: A. Wilcox <AWilcox@Wilcox-Tech.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
36859cd5 |
|
22-Aug-2018 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: Change kiq initialize/reset sequence on gfx8 1. initialize kiq before initialize gfx ring. 2. set kiq ring ready immediately when kiq initialize successfully. 3. split function gfx_v8_0_kiq_resume into two functions. gfx_v8_0_kiq_resume is for kiq initialize. gfx_v8_0_kcq_resume is for kcq initialize. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
a62a49e5 |
|
17-Aug-2018 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: Refine gfx_v8_0_kcq_disable function Send all kcq unmap_queue packets and then wait for complete. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
6c10b5cc |
|
16-Aug-2018 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: Remove duplicate code in gfx_v8_0.c There are no any logical changes here. 1. if kcq can be enabled via kiq, we don't need to do kiq ring test. 2. amdgpu_ring_test_ring function can be used to sync the ring complete, remove the duplicate code. v2: alloc 6 (not 7) dws for unmap_queues Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
1f06dee8 |
|
24-Aug-2018 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: Enable/disable gfx PG feature in rlc safe mode This is required by gfx hw and can fix the rlc hang when do s3 stree test on Cz/St. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Hang Zhou <hang.zhou@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
f5d85033 |
|
20-Aug-2018 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: implement soft_recovery for GFX8 v2 Try to kill waves on the SQ. v2: only for the GFX ring for now. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Huang Rui <ray.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
8ef23364 |
|
24-Aug-2018 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: Enable/disable gfx PG feature in rlc safe mode This is required by gfx hw and can fix the rlc hang when do s3 stree test on Cz/St. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Hang Zhou <hang.zhou@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
05df1f01 |
|
14-Aug-2018 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: Set power ungate state when suspend/fini Unify to set power ungate state at the begin of suspend/fini. Remove the workaround code for gfx off feature in amdgpu_device.c. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
091aec0b |
|
25-May-2018 |
Andrey Grodzovsky <andrey.grodzovsky@amd.com> |
drm/amd: Use newly added interrupt source defs for VI v3. v2: Rebase v3: Use defines for CP_SQ and CP_ECC_ERROR interrupts. Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c9f96fd5 |
|
13-Jun-2018 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: Split set_pg_state into separate function 1. add amdgpu_device_ip_late_set_pg_state function for set pg state. 2. delete duplicate pg state setting on gfx_v8_0's late_init. Reviewed-by: Evan Quan <evan.quan@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
85f80cb3 |
|
13-Jun-2018 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amd/pp: Add gfx pg support in smu through set_powergating_by_smu gfx ip block can call set_powergating_by_smu to set gfx pg state if necessary. Reviewed-by: Evan Quan <evan.quan@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
9bdc2092 |
|
19-Jun-2018 |
Andrey Grodzovsky <andrey.grodzovsky@amd.com> |
drm/amdgpu: Add parsing SQ_EDC_INFO to SQ IH v3. Access to SQ_EDC_INFO requires selecting register instance and hence mutex lock when accessing GRBM_GFX_INDEX for which a work is schedueled from IH. But SQ interrupt can be raised on many instances at once which means queuing work will usually succeed for the first one but fail for the rest since the work takes time to process. To avoid losing info about other interrupt instances call the parsing function directly from high IRQ when current work hasn't finished and avoid accessing SQ_EDC_INFO in that case. v2: Simplify high IRQ and BH handlers synchronization using work_pending. Remove {READ,WRITE}_ONCE notations since smp_{r,w}mb are implicit compiler barriers. v3: Remove exlicit memory barriers as scedule_work has r/w barriers. Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
d9e222b4 |
|
18-Jun-2018 |
Andrey Grodzovsky <andrey.grodzovsky@amd.com> |
drm/amdgpu: Polish SQ IH. Switch to using reg fields defines istead of magic values. Add SH_ID and PRIV fields reading for instr. and err cases. Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
04ad26bb |
|
22-May-2018 |
David Panariti <David.Panariti@amd.com> |
drm/amdgpu: Add plumbing for handling SQ EDC/ECC interrupts v2. SQ can generate interrupts and installs the ISR to handle the SQ interrupts. Add parsing SQ data in interrupt handler. v2: Remove CZ only limitation. Rebase. Signed-off-by: David Panariti <David.Panariti@amd.com> Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
5a2f2913 |
|
15-May-2018 |
David Panariti <David.Panariti@amd.com> |
drm/amdgpu: Added ISR for CP ECC/EDC interrupt v2. ISR will DRM_ERROR ECC error message. v2: Remove CZ only limitation. Rebase. Signed-off-by: David Panariti <David.Panariti@amd.com> Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
8f4039fe |
|
07-Jun-2018 |
Shirish S <shirish.s@amd.com> |
drm/amdgpu: change gfx8 ib test to use WB This patch is extends the usage of WB in gfx8's ib test which was originally implemented in the below upstream patch "ed9324a drm/amdgpu: change gfx9 ib test to use WB" For reference below are the reasons for switching to WB: 1)Because when doing IB test we don't want to involve KIQ health status affect, and since SCRATCH register access is go through KIQ that way GFX IB test would failed due to KIQ fail. 2)acccessing SCRATCH register cost much more time than WB method because SCRATCH register access runs through KIQ which at least could begin after GPU world switch back to current Guest VF Signed-off-by: Shirish S <shirish.s@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
71765469 |
|
16-Nov-2017 |
Leo Liu <leo.liu@amd.com> |
drm/amdgpu: initialize VEGAM GFX Signed-off-by: Leo Liu <leo.liu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
aefbbd6c |
|
16-Nov-2017 |
Leo Liu <leo.liu@amd.com> |
drm/amdgpu: add VEGAM GFX golden settings Signed-off-by: Leo Liu <leo.liu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
62aac201 |
|
10-Nov-2017 |
Leo Liu <leo.liu@amd.com> |
drm/amdgpu: add VEGAM GFX firmware support Signed-off-by: Leo Liu <leo.liu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
38610f15 |
|
12-Apr-2018 |
Nicolai Hähnle <nicolai.haehnle@amd.com> |
drm/amdgpu: set COMPUTE_PGM_RSRC1 for SGPR/VGPR clearing shaders Otherwise, the SQ may skip some of the register writes, or shader waves may be allocated where we don't expect them, so that as a result we don't actually reset all of the register SRAMs. This can lead to spurious ECC errors later on if a shader uses an uninitialized register. Signed-off-by: Nicolai Hähnle <nicolai.haehnle@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
|
#
75569c18 |
|
12-Apr-2018 |
Nicolai Hähnle <nicolai.haehnle@amd.com> |
drm/amdgpu: set COMPUTE_PGM_RSRC1 for SGPR/VGPR clearing shaders Otherwise, the SQ may skip some of the register writes, or shader waves may be allocated where we don't expect them, so that as a result we don't actually reset all of the register SRAMs. This can lead to spurious ECC errors later on if a shader uses an uninitialized register. Signed-off-by: Nicolai Hähnle <nicolai.haehnle@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
|
#
f7a9ee81 |
|
29-Mar-2018 |
Andrey Grodzovsky <andrey.grodzovsky@amd.com> |
drm/amdgpu: Add support for SRBM selection v3 Also remove code duplication in write and read regs functions. This also fixes potential missing unlock in amdgpu_debugfs_regs_write in case get_user would fail. v2: Add SRBM mutex locking. v3: Fix TO counter and fix comment location. Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c633c00b |
|
04-Feb-2018 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: separate PASID mapping from VM flush v2 Stuffing the PASID mapping into the VM flush isn't flexible enough since the PASID mapping changes not as often as we need a VM flush. v2: add missing use of gmc_v7_0_emit_pasid_mapping Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
062d2e6a |
|
24-Jan-2018 |
Andrey Grodzovsky <andrey.grodzovsky@amd.com> |
Revert "drm/amdgpu/gfx8: Fix compute ring failure after resetting" This reverts commit 75737cb4eb78c7f185e4700b4aa20cf7a3381aca. Fixes compute rings test failure on bare metal during full GPU reset. RCA: the ring buffer has to be filled with valid packets (such as NOPs) first before submitting MAP_QUEUEs packet into KIQ. Once a compute engine is mapped, it will immediately execute the ring buffer if the RTPR is not equal to the WTPR from the MQD. It could lead to engine hang if the ring buffer filled with random data. Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
6f05c4e9 |
|
22-Jan-2018 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: move static CSA address to top of address space v2 Move the CSA area to the top of the VA space to avoid clashing with HMM/ATC in the lower range on GFX9. v2: wrong sign noticed by Roger, rebase on CSA_VADDR cleanup, handle VA hole on GFX9 as well. Signed-off-by: Christian König <christian.koenig@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Monk Liu <monk.liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
97745f68 |
|
23-Jan-2018 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: consistently use AMDGPU_CSA_VADDR Instead of repeating this multiple times. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Monk Liu <monk.liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
2ee150cd |
|
19-Jan-2018 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: remove now superflous *_hdp operation All HDP invalidation and most flush can now be replaced by the generic ASIC function. Signed-off-by: Christian König <christian.koenig@amd.com> Acked-by: Chunming Zhou <david1.zhou@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
5518625d |
|
12-Jan-2018 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: implement gmc_v8_0_emit_flush_gpu_tlb Unify tlb flushing for gmc v8. v2: handle UVD v6 as well Signed-off-by: Christian König <christian.koenig@amd.com> Acked-by: Chunming Zhou <david1.zhou@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
9ed88047 |
|
12-Jan-2018 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: wire up emit_wreg for gfx v8 Needed for vm_flush unification. v2: handle compute rings as well Signed-off-by: Christian König <christian.koenig@amd.com> Acked-by: Chunming Zhou <david1.zhou@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
5a4633c4 |
|
08-Jan-2018 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: forward pasid to backend flush implementations rd the pasid from the VM code to the emit_vm_flush function and update all implementations with the new parameter. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
770d13b1 |
|
12-Jan-2018 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: move struct amdgpu_mc into amdgpu_gmc.h And rename it to amdgpu_gmc as well. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Samuel Li <Samuel.Li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c4f46f22 |
|
18-Dec-2017 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: rename vm_id to vmid sed -i "s/vm_id/vmid/g" drivers/gpu/drm/amd/amdgpu/*.c sed -i "s/vm_id/vmid/g" drivers/gpu/drm/amd/amdgpu/*.h Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
2990a1fc |
|
15-Dec-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: rename ip block helper functions add device to the name for consistency. Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
9c3f2b54 |
|
14-Dec-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: rename amdgpu_program_register_sequence add device for consistency with other functions in this file. Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
ebdebf42 |
|
08-Dec-2017 |
Flora Cui <flora.cui@amd.com> |
drm/amdgpu: add amdgpu interface to query cu info Signed-off-by: Flora Cui <flora.cui@amd.com> Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
|
#
1b1f42d8 |
|
06-Dec-2017 |
Lucas Stach <l.stach@pengutronix.de> |
drm: move amd_gpu_scheduler into common location This moves and renames the AMDGPU scheduler to a common location in DRM in order to facilitate re-use by other drivers. This is mostly a straight forward rename with no code changes. One notable exception is the function to_drm_sched_fence(), which is no longer a inline header function to avoid the need to export the drm_sched_fence_ops_scheduled and drm_sched_fence_ops_finished structures. Reviewed-by: Chunming Zhou <david1.zhou@amd.com> Tested-by: Dieter Nützel <Dieter@nuetzel-hh.de> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
84e5b516 |
|
14-Nov-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:free CSA in unified place instead of doing it in each GFX ip's sw_fini Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
93442184 |
|
13-Nov-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: use cached values for raster config in clear state Use the cached values rather than hardcoding it. Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c47b41a7 |
|
03-Nov-2017 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: remove nonsense const u32 cast on ARRAY_SIZE result Not sure what that should originally been good for, but it doesn't seem to make any sense any more. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
75737cb4 |
|
09-Nov-2017 |
Xiangliang.Yu <Xiangliang.Yu@amd.com> |
drm/amdgpu/gfx8: Fix compute ring failure after resetting Do ring clear before ring test, otherwise compute ring test will fail after gpu resetting. Still can't find the root cause, just workaround it. Signed-off-by: Xiangliang.Yu <Xiangliang.Yu@amd.com> Acked-by: Monk Liu <Monk.Liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
13a752e3 |
|
17-Oct-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:cleanup in_sriov_reset and lock_reset since now gpu reset is unified with gpu_recover for both bare-metal and SR-IOV: 1)rename in_sriov_reset to in_gpu_reset 2)move lock_reset from adev->virt to adev Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
1366b2d0 |
|
23-Oct-2017 |
pding <Pixel.Ding@amd.com> |
drm/amdgpu: avoid soft lockup when waiting for RLC serdes (v2) Normally all waiting get timeout if there's one. Release the lock and return immediately when timeout happens. v2: - set the se_sh to broadcase before return Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: pding <Pixel.Ding@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
9953b72f |
|
25-Oct-2017 |
pding <Pixel.Ding@amd.com> |
drm/amdgpu: change redundant init logs to debug level When this VF stays in exclusive mode for long, other VFs will be impacted. The redundant messages causes exclusive mode timeout when they're redirected. That is a normal use case for cloud service to redirect guest log to virtual serial port. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: pding <Pixel.Ding@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
9862def9 |
|
14-Nov-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:fix memleak those RLC used buffers are not cleared in GFX's sw_fini Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c1b24a14 |
|
15-Oct-2017 |
Jérémy Lefaure <jeremy.lefaure@lse.epita.fr> |
drm/amdgpu: use ARRAY_SIZE Using the ARRAY_SIZE macro improves the readability of the code. Found with Coccinelle with the following semantic patch: @r depends on (org || report)@ type T; T[] E; position p; @@ ( (sizeof(E)@p /sizeof(*E)) | (sizeof(E)@p /sizeof(E[...])) | (sizeof(E)@p /sizeof(T)) ) Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Thierry Reding <treding@nvidia.com> Signed-off-by: Jérémy Lefaure <jeremy.lefaure@lse.epita.fr> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
b8866c26 |
|
28-Apr-2017 |
Andres Rodriguez <andresx7@gmail.com> |
drm/amdgpu: implement ring set_priority for gfx_v8 compute v9 Programming CP_HQD_QUEUE_PRIORITY enables a queue to take priority over other queues on the same pipe. Multiple queues on a pipe are timesliced so this gives us full precedence over other queues. Programming CP_HQD_PIPE_PRIORITY changes the SPI_ARB_PRIORITY of the wave as follows: 0x2: CS_H 0x1: CS_M 0x0: CS_L The SPI block will then dispatch work according to the policy set by SPI_ARB_PRIORITY. In the current policy CS_H is higher priority than gfx. In order to prevent getting stuck in loops of resources bouncing between GFX and high priority compute and introducing further latency, we statically reserve a portion of the pipe. v2: fix srbm_select to ring->queue and use ring->funcs->type v3: use AMD_SCHED_PRIORITY_* instead of AMDGPU_CTX_PRIORITY_* v4: switch int to enum amd_sched_priority v5: corresponding changes for srbm_lock v6: change CU reservation to PIPE_PERCENT allocation v7: use kiq instead of MMIO v8: back to MMIO, and make the implementation sleep safe. v9: corresponding changes for splitting HIGH into _HW/_SW Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Andres Rodriguez <andresx7@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
3811f8f0 |
|
25-Sep-2017 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amd/powerplay: move set_clockgating_by_smu to pp func table Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
d81a2209 |
|
28-Sep-2017 |
Dave Airlie <airlied@redhat.com> |
amdgfx/gfx: don't use static objects for ce/de meta. (v2) This isn't safe if we have multiple GPUs plugged in, since there is only one copy of this struct in the bss, just allocate on stack, it's 40/108 bytes which should be safe. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Dave Airlie <airlied@redhat.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
790d84fd |
|
25-Sep-2017 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: delete dead code about fw load check Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
85f95ad6 |
|
21-Sep-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:unmap KCQ in gfx hw_fini(v2) v2: move kcq_disable out of SRIOV, make it genearal Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
030308fc |
|
15-Sep-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu/sriov:fix page fault issue of driver unload bo_free on csa is too late to put in amdgpu_fini because that time ttm is already finished, Move it earlier to avoid the page fault. Signed-off-by: Monk Liu <Monk.Liu@amd.com> Signed-off-by: Horace Chen <horace.chen@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
3224a12b |
|
15-Sep-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu/sriov:move in_reset to adev and rename currently in_reset is only used in sriov gpu reset, and it will be used for other non-gfx hw component later, like PSP, so move it from gfx to adev and rename to in_sriov_reset make more sense. Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
f5830465 |
|
01-Sep-2017 |
Evan Quan <evan.quan@amd.com> |
drm/amdgpu: declare the new firmware files needed by polaris asics Signed-off-by: Evan Quan <evan.quan@amd.com> Reviewed-by: Flora Cui <Flora.Cui@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
925d5d79 |
|
24-Aug-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: apply dynamic cu mask to APUs as well Confirmed with the hw team. It's the same for all asics. Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
727030b0 |
|
18-Aug-2017 |
Evan Quan <evan.quan@amd.com> |
drm/amdgpu: support polaris10/11/12 new cp firmwares Newer versions of the CP firmware require changes in how the driver initializes the hw block. Change the firmware name for new firmware to maintain compatibility with older kernels. Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Evan Quan <evan.quan@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
2d6fb105 |
|
18-Aug-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: fix spelling typo in mqd allocation Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
871594e7 |
|
18-Aug-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: fix spelling typo in mqd allocation Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
111159b5 |
|
15-Aug-2017 |
Felix Kuehling <Felix.Kuehling@amd.com> |
drm/amdgpu: Program SH_STATIC_MEM_CONFIG globally, not per-VMID This register only has a single instance in the hardware. Its value applies to all VMIDS. Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
|
#
078af1a3 |
|
27-Jul-2017 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: use amdgpu_bo_free_kernel more often Saves us even more loc. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
a4a02777 |
|
27-Jul-2017 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: use amdgpu_bo_create_kernel more often Saves us quite a bunch of loc. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
6a41f981 |
|
20-Jul-2017 |
Huang Rui <ray.huang@amd.com> |
drm/amdgpu: fix the incorrect scratch reg number on gfx v8 Signed-off-by: Huang Rui <ray.huang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
1d11ee89 |
|
11-Jul-2017 |
Dan Carpenter <dan.carpenter@oracle.com> |
drm/amdgpu: Off by one sanity checks This is just future proofing code, not something that can be triggered in real life. We're testing to make sure we don't shift wrap when we do "1ull << i" so "i" has to be in the 0-63 range. If it's 64 then we have gone too far. Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
98b09f52 |
|
27-Jun-2017 |
ozeng <oak.zeng@amd.com> |
drm/amdgpu: Changed CU reservation golden settings With previous golden settings, compute task can't use reserved LDS (32K) on CU0 and CU1. On 64K LDS system, if compute work group allocate more than 32K LDS, then it can't be dispatched to CU0 and CU1 because of the reservation. This enables compute task to use reserved LDS on CU0 and CU1. Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
dcf75843 |
|
03-Jul-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: fix driver reload with KIQ Drop the deactivation in KIQ init and drop the KCQ disabling via KIQ. We disable the MEC shortly after anyway, so there is no need to wait for all of this. Doing so seems to leave the MEC in a bad way. Tested-by: Michel Dänzer <michel.daenzer@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
dbfe85ea |
|
19-Jun-2017 |
Flora Cui <Flora.Cui@amd.com> |
drm/amdgpu: Fix the exported always on CU bitmap Newer asics with 4 SEs are not able to fit the entire bitmask in the original field, use an array instead. v2: keep cu_ao_mask for backward compatibility. Signed-off-by: Flora Cui <Flora.Cui@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
6b0fa871 |
|
26-Jun-2017 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: fix vulkan test performance drop and hang on VI caused by not program dynamic_cu_mask_addr in the KIQ MQD. v2: create struct vi_mqd_allocation in FB which will contain 1. PM4 MQD structure. 2. Write Pointer Poll Memory. 3. Read Pointer Report Memory 4. Dynamic CU Mask. 5. Dynamic RB Mask. Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
d0c55cdf |
|
09-Jun-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx: fix MEC interrupt enablement for pipes != 0 The interrupt registers are not indexed. Fixes: 763a47b8e (drm/amdgpu: teach amdgpu how to enable interrupts for any pipe v3) Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
b9683c21 |
|
07-Jun-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx: consolidate mqd buffer setup code It was duplicated across multiple generations. Reviewed-by: Alex Xie <AlexBin.Xie@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
4853bbb6 |
|
07-Jun-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx: move mec parameter setup into sw_init This will allow us to share more mec code. Reviewed-by: Alex Xie <AlexBin.Xie@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
71c37505 |
|
07-Jun-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx: move more common KIQ code to amdgpu_gfx.c Lots more common stuff. Reviewed-by: Alex Xie <AlexBin.Xie@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
2db0cdbe |
|
06-Jun-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: move mec queue helpers to amdgpu_gfx.h They are gfx related, not general helpers. Reviewed-by: Alex Xie <AlexBin.Xie@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
d6b20c87 |
|
07-Jun-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: whitespace change Make it consistent. Reviewed-by: Alex Xie <AlexBin.Xie@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
41f6a99a |
|
07-Jun-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: move gfx_v*_0_compute_queue_acquire to common code Same function was duplicated in all gfx IP files. Reviewed-by: Alex Xie <AlexBin.Xie@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
cf8b611f |
|
07-Jun-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: fix mec queue policy on single MEC asics Fixes hangs on single MEC asics. Fixes: 2ed286fb434 (drm/amdgpu: new queue policy, take first 2 queues of each pipe v2) Reviewed-by: Alex Xie <AlexBin.Xie@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
378506a7 |
|
06-Jun-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx: create a common bitmask function (v2) The same function was duplicated in all the gfx IPs. Use a single implementation for all. v2: use static inline (Alex Xie) Reviewed-by: Alex Xie <AlexBin.Xie@amd.com> Suggested-by: Andres Rodriguez <andresx7@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
943c05bd |
|
31-May-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: drop per-APU CU limits Always use the max for the family rather than the per sku limits. This makes sure the mask is always the max size to avoid reporting the wrong number of CUs. Reviewed-by: Alex Xie <AlexBin.Xie@amd.com> Reviewed-by: Andres Rodriguez <andresx7@gmail.com> Cc: stable@vger.kernel.org Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
ecd910eb |
|
24-Feb-2017 |
Andres Rodriguez <andresx7@gmail.com> |
drm/amdgpu: workaround tonga HW bug in HQD programming sequence Tonga based asics may experience hangs when an HQD's EOP parameters are modified. Workaround this HW issue by avoiding writes to these registers for tonga asics. Based on the following ROCm commit: 2a0fb8 - drm/amdgpu: Synchronize KFD HQD load protocol with CP scheduler From the ROCm git repository: https://github.com/RadeonOpenCompute/ROCK-Kernel-Driver.git CC: Jay Cornwall <Jay.Cornwall@amd.com> Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Andres Rodriguez <andresx7@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
894700f3 |
|
24-Feb-2017 |
Andres Rodriguez <andresx7@gmail.com> |
drm/amdgpu: condense mqd programming sequence The MQD structure matches the reg layout. Take advantage of this to simplify HQD programming. Note that the ACTIVE field still needs to be programmed last. Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Andres Rodriguez <andresx7@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
0a281f5a |
|
03-Feb-2017 |
Andres Rodriguez <andresx7@gmail.com> |
drm/amdgpu: new queue policy, take first 2 queues of each pipe v2 Instead of taking the first pipe and giving the rest to kfd, take the first 2 queues of each pipe. Effectively, amdgpu and amdkfd own the same number of queues. But because the queues are spread over multiple pipes the hardware will be able to better handle concurrent compute workloads. amdgpu goes from 1 pipe to 4 pipes, i.e. from 1 compute threads to 4 amdkfd goes from 3 pipe to 4 pipes, i.e. from 3 compute threads to 4 v2: fix policy comment Reviewed-by: Edward O'Callaghan <funfunctor@folklore1984.net> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Andres Rodriguez <andresx7@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
7b2124a5 |
|
05-Apr-2017 |
Andres Rodriguez <andresx7@gmail.com> |
drm/amdgpu: avoid KIQ clashing with compute or KFD queues v2 Instead of picking an arbitrary queue for KIQ, search for one according to policy. The queue must be unused. Also report the KIQ as an unavailable resource to KFD. In testing I ran into KCQ initialization issues when using pipes 2/3 of MEC2 for the KIQ. Therefore the policy disallows grabbing one of these. v2: fix (ring.me + 1) to (ring.me -1) in amdgpu_amdkfd_device_init Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Andres Rodriguez <andresx7@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
de65513a |
|
04-Apr-2017 |
Andres Rodriguez <andresx7@gmail.com> |
drm/amdgpu: remove hardcoded queue_mask in PACKET3_SET_RESOURCES The assumption that we are only using the first pipe no longer holds. Instead, calculate the queue_mask from the queue_bitmap. Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Andres Rodriguez <andresx7@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
e33fec48 |
|
03-Feb-2017 |
Andres Rodriguez <andresx7@gmail.com> |
drm/amdgpu: allocate queues horizontally across pipes Pipes provide better concurrency than queues, therefore we want to make sure that apps use queues from different pipes whenever possible. Optimize for the trivial case where an app will consume rings in order, therefore we don't want adjacent rings to belong to the same pipe. Reviewed-by: Edward O'Callaghan <funfunctor@folklore1984.net> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Andres Rodriguez <andresx7@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
763a47b8 |
|
09-Feb-2017 |
Andres Rodriguez <andresx7@gmail.com> |
drm/amdgpu: teach amdgpu how to enable interrupts for any pipe v3 The current implementation is hardcoded to enable ME1/PIPE0 interrupts only. This patch allows amdgpu to enable interrupts for any pipe of ME1. v2: added gfx9 support v3: use soc15_grbm_select for gfx9 Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Andres Rodriguez <andresx7@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
78c16834 |
|
01-Feb-2017 |
Andres Rodriguez <andresx7@gmail.com> |
drm/amdgpu: allow split of queues with kfd at queue granularity v4 Previously the queue/pipe split with kfd operated with pipe granularity. This patch allows amdgpu to take ownership of an arbitrary set of queues. It also consolidates the last few magic numbers in the compute initialization process into mec_init. v2: support for gfx9 v3: renamed AMDGPU_MAX_QUEUES to AMDGPU_MAX_COMPUTE_QUEUES v4: fix off-by-one in num_mec checks in *_compute_queue_acquire Reviewed-by: Edward O'Callaghan <funfunctor@folklore1984.net> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Andres Rodriguez <andresx7@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
42794b27 |
|
01-Feb-2017 |
Andres Rodriguez <andresx7@gmail.com> |
drm/amdgpu: take ownership of per-pipe configuration v3 Make amdgpu the owner of all per-pipe state of the HQDs. This change will allow us to split the queues between kfd and amdgpu with a queue granularity instead of pipe granularity. This patch fixes kfd allocating an HDP_EOP region for its 3 pipes which goes unused. v2: support for gfx9 v3: fix gfx7 HPD intitialization Reviewed-by: Edward O'Callaghan <funfunctor@folklore1984.net> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Andres Rodriguez <andresx7@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
dc102c43 |
|
01-Feb-2017 |
Andres Rodriguez <andresx7@gmail.com> |
drm/amdgpu: rename rdev to adev Rename straggler instances of r(adeon)dev to a(mdgpu)dev Reviewed-by: Edward O'Callaghan <funfunctor@folklore1984.net> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Andres Rodriguez <andresx7@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
97bf47b2 |
|
01-Feb-2017 |
Andres Rodriguez <andresx7@gmail.com> |
drm/amdgpu: unify MQD programming sequence for kfd and amdgpu v2 Use the same gfx_*_mqd_commit function for kfd and amdgpu codepaths. This removes the last duplicates of this programming sequence. v2: fix cp_hqd_pq_wptr value Reviewed-by: Edward O'Callaghan <funfunctor@folklore1984.net> Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Andres Rodriguez <andresx7@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
bf13ed6b |
|
31-Jan-2017 |
Andres Rodriguez <andresx7@gmail.com> |
drm/amdgpu: detect timeout error when deactivating hqd Handle HQD deactivation timeouts instead of ignoring them. Reviewed-by: Edward O'Callaghan <funfunctor@folklore1984.net> Acked-by: Christian König <christian.koenig@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Andres Rodriguez <andresx7@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
34130fb1 |
|
12-Apr-2017 |
Andres Rodriguez <andresx7@gmail.com> |
drm/amdgpu: refactor MQD/HQD initialization v3 The MQD programming sequence currently exists in 3 different places. Refactor it to absorb all the duplicates. The success path remains mostly identical except for a slightly different order in the non-kiq case. This shouldn't matter if the HQD is disabled. The error handling paths have been updated to deal with the new code structure. v2: the non-kiq path for gfxv8 was dropped in the rebase v3: split MEC_HPD_SIZE rename, dropped doorbell changes Reviewed-by: Edward O'Callaghan <funfunctor@folklore1984.net> Acked-by: Christian König <christian.koenig@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Andres Rodriguez <andresx7@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
268cb4c7 |
|
12-Apr-2017 |
Andres Rodriguez <andresx7@gmail.com> |
drm/amdgpu: clarify MEC_HPD_SIZE is specific to a gfx generation Rename MEC_HPD_SIZE to GFXN_MEC_HPD_SIZE to clarify it is specific to a gfx generation. Signed-off-by: Andres Rodriguez <andresx7@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
3b4d68e9 |
|
01-May-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:use FRAME_CNTL for new GFX ucode (v2) AI affected: CP/HW team requires KMD insert FRAME_CONTROL(end) after the last IB and before the fence of this DMAframe. this is to make sure the cache are flushed, and it's a must change no matter MCBP/SR-IOV or bare-metal case because new CP hw won't do the cache flush for each IB anymore, it just leaves it to KMD now. with this patch, certain MCBP hang issue when rendering vulkan/chained-ib are resolved. v2: drop gfx8 changes. gfx8 is not affected (Alex) Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
635e7132 |
|
01-May-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:change SR-IOV DMAframe scheme According to CP/hw team requirment, to support PAL/CHAINED-IB MCBP, kernel driver must guarantee DE_META must be inserted right prior to the work_load DE IB (with PREEMPT flag), there cannot be any non-work_load DE IB between-in DE_META and work_load DE IB. Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
95243543 |
|
01-May-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:unify gfx8/9 ce/de meta_data Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
cdf6adb2 |
|
28-Apr-2017 |
Shaoyun Liu <Shaoyun.Liu@amd.com> |
drm/amdgpu: Move kiq ring lock out of virt structure The usage of kiq should not depend on the virtualization. Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com> Reviewed-by:Andres Rodriquez <andresx7@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
63a7c748 |
|
27-Apr-2017 |
Trigger Huang <trigger.huang@amd.com> |
drm/amdgpu: Enable chained IB MCBP support Support for MCBP/Virtualization in combination with chained IBs is formal released on firmware feature version #46. So enable it according to firmware feature version, otherwise, world switch will hang. Signed-off-by: Trigger Huang <trigger.huang@amd.com> Reviewed-by: Monk Liu <monk.liu@amd.com> Reviewed-by: Xiangliang Yu <Xiangliang.Yu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
fe723cd3 |
|
26-Apr-2017 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu:fix get wrong gfx always on cu masks. Bug: SWDEV-117987: Always on CU mask broken for gfx7+ Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
94c9cead |
|
24-Apr-2017 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: fix s3 ring test failed on Vi caused by KIQ enabled. Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
ca541f33 |
|
17-Apr-2017 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: delete redundant kiq irq funcs type check in gfx8. Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
2d0806ca |
|
17-Apr-2017 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: fix typo in dmesg in gfx_v8_0_kiq_kcq_disable. Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
6a124e67 |
|
13-Apr-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: move CP_PQ_STATUS after doorbell range setting (v2) I'm not sure if the order matters, but it seems like it makes more sense to set this after the range is programmed. v2: rebase (Alex) Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
4f339b29 |
|
11-Apr-2017 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: set cpg doorbell for fiji and polaris. add set_doorbell functions for mec and cpg. Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
a99f249d |
|
11-Apr-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: unify the HQD deactivation code This could be used in Andres' priority scheduling patch as well. Reviewed-by: Andres Rodriguez <andresx7@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
d5dc36a4 |
|
14-Mar-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: enable cp/rlc ints after we disable clockgating Even if we disable clockgating, we still need to make sure the cp/rlc interrupts are enabled for powergating which might still be enabled. Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
d17c0faf |
|
10-Apr-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: move MEC doorbell range setting It's global, not queue specific, so move it out of the kiq register init function. Tested-and-Reviewed-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
a545e491 |
|
30-Mar-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: fix resume of KIQ and KCQs No need to reset the wptr and clear the rings. The UNMAP_QUEUES packet writes the current MQD state back the MQD on suspend, so there is no need to reset it as well. Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
9d11ca9c |
|
30-Mar-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: properly disable the KCQs in hw_fini Use the UNMAP_QUEUES packet to have the KIQ properly disable them. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
3d7e30b3 |
|
29-Mar-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: use new KIQ packet defines Rather than open coding them. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
346586d5 |
|
29-Mar-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: move SET_RESOURCES into the same command stream As the KCQ setup. This way we only have to wait once for the entire MEC. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c3a49ab5 |
|
29-Mar-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: wait once for all KCQs to be created Rather than waiting for each queue. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
39300115 |
|
29-Mar-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: split gfx_v8_0_kiq_init_queue into two One for KIQ and one for the KCQ. This simplifies the logic and allows for future optimizations. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
f776952b |
|
29-Mar-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: wait for completion in KIQ init We need to make sure the various init sequences submitted to KIQ complete before testing the rings. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
b4e40676 |
|
27-Mar-2017 |
David Panariti <David.Panariti@amd.com> |
drm/amdgpu: Switch baremetal to use KIQ for compute ring management. (v3) KIQ is the Kernel Interface Queue for managing the MEC. Rather than setting up rings via direct MMIO of ring registers, the rings are configured via special packets sent to the KIQ. The allows the MEC to better manage shared resources and certain power events. v2: squash in s3/s4 fix from Rex v3: further fixes from Rex Signed-off-by: David Panariti <David.Panariti@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Tom St Denis <tom.stdenis@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
a576fe51 |
|
09-Apr-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: set doorbell range for polaris as well Add missing chips to the doorbell range setup. These were missed in the KIQ code. Fixes power and performance regressions with KIQ. Spotted by Rex. Tested-and-Reviewed-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
ed6f55d1 |
|
07-Apr-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: add additional MQD initialization Need to properly set the MTYPE and ROQ space setting. This should fix performance regressions with KIQ enabled. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
248a1d6f |
|
23-Apr-2017 |
Masahiro Yamada <yamada.masahiro@socionext.com> |
drm/amd: fix include notation and remove -Iinclude/drm flag Include <drm/*.h> instead of relative path from include/drm, then remove the -Iinclude/drm compiler flag. Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com> Reviewed-by: Michel Dänzer <michel.daenzer@amd.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: http://patchwork.freedesktop.org/patch/msgid/1493009447-31524-4-git-send-email-yamada.masahiro@socionext.com
|
#
80112bff |
|
18-Apr-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: update revision id settings for BR/ST Add new RIDs. Acked-by: Christian König <christian.koenig@amd.com> Acked-by: Alex Xie <AlexBin.Xie@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c81a1a74 |
|
28-Apr-2017 |
Michel Dänzer <michel.daenzer@amd.com> |
drm/amdgpu: Make amdgpu_bo_reserve use uninterruptible waits for cleanup Some of these paths probably cannot be interrupted by a signal anyway. Those that can would fail to clean up things if they actually got interrupted. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Michel Dänzer <michel.daenzer@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
7645670d |
|
06-Apr-2017 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: split VMID management by VMHUB 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 <christian.koenig@amd.com> Reviewed-by: Andres Rodriguez <andresx7@gmail.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
377e2759 |
|
05-Apr-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:no need to involv HDP in KIQ 1,KIQ won't touch VRAM so no need to involv HDP flush/invalidate at all. 2,According to CP hw designer KIQ better not use any PM4 package lead to wait behave. Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
d1a5b250 |
|
04-Apr-2017 |
Tom St Denis <tom.stdenis@amd.com> |
drm/amd/amdgpu: Fix srbm_indexing in init/inactive hqd code Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
bb215962 |
|
04-Apr-2017 |
Tom St Denis <tom.stdenis@amd.com> |
drm/amd/amdgpu: Clean up gfx_v8_0_mqd_init() Clean up a toggle with ?:. Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
699d12b7 |
|
04-Apr-2017 |
Tom St Denis <tom.stdenis@amd.com> |
drm/amd/amdgpu: de-numberify HQD_ACTIVE check. Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
0ac642c5 |
|
04-Apr-2017 |
Tom St Denis <tom.stdenis@amd.com> |
drm/amd/amdgpu: clean up gfx_v8_0_kiq_init_register() Swap read/write pattern for WREG32_FIELD() Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
35e259d5 |
|
04-Apr-2017 |
Tom St Denis <tom.stdenis@amd.com> |
drm/amd/amdgpu: Clean up gfx_v8_0_inactive_hqd() Swap read/write pattern for WREG32_FIELD() Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
ccaf3574 |
|
04-Apr-2017 |
Tom St Denis <tom.stdenis@amd.com> |
drm/amd/amdgpu: Clean up gfx_v8_0_kiq_set_interrupt_state() Use new WREG32_FIELD_OFFSET() to clean up code. Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
fcf17a43 |
|
30-Mar-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: KIQ is also disabled when MEC is disabled Set the ready flag to reflect this. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
e9d672b2 |
|
14-Mar-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:changes in gfx DMAframe scheme (v2) 1) Adapt to vulkan: Now use double SWITCH BUFFER to replace the 128 nops w/a, because when vulkan introduced, umd can insert 7 ~ 16 IBs per submit which makes 256 DW size cannot hold the whole DMAframe (if we still insert those 128 nops), CP team suggests use double SWITCH_BUFFERs, instead of tricky 128 NOPs w/a. 2) To fix the CE VM fault issue when MCBP introduced: Need one more COND_EXEC wrapping IB part (original one us for VM switch part). this change can fix vm fault issue caused by below scenario without this change: >CE passed original COND_EXEC (no MCBP issued this moment), proceed as normal. >DE catch up to this COND_EXEC, but this time MCBP issued, thus DE treats all following packages as NOP. The following VM switch packages now looks just as NOP to DE, so DE dosen't do VM flush at all. >Now CE proceeds to the first IBc, and triggers VM fault, because DE didn't do VM flush for this DMAframe. 3) change estimated alloc size for gfx9. with new DMAframe scheme, we need modify emit_frame_size for gfx9 4) No need to insert 128 nops after gfx8 vm flush anymore because there was double SWITCH_BUFFER append to vm flush, and for gfx7 we already use double SWITCH_BUFFER following after vm_flush so no change needed for it. 5) Change emit_frame_size for gfx8 v2: squash in BUG removal from Monk Signed-off-by: Monk Liu <Monk.Liu@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
2e2e3c7f |
|
08-Mar-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:enable MCBP for SR-IOV (v2) Apply the new IB during IB emit for SRIOV with MCBP v2: agd: use define instead of magic number Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
806ba2d4 |
|
23-Mar-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:implement cond_exec for gfx8 when MCBP enabled for gfx8, the cond_exec must also be implemented, otherwise there will be odds to meet cross engine (ce and me) deadlock when world switch happens. Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
e635ee07 |
|
01-Nov-2016 |
Huang Rui <ray.huang@amd.com> |
drm/amdgpu: use new flag to handle different firmware loading method This patch introduces a new flag named "amdgpu_firmware_load_type" to handle different firmware loading method. Since Vega10, there are three ways to load firmware. It would be better to use a flag and a fw_load_type kernel parameter to configure it. Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Huang Rui <ray.huang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
a2140e00 |
|
23-Mar-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: further KIQ parameter cleanup The ring structure already has what we need. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
34534610 |
|
23-Mar-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: store the eop gpu addr in the ring structure Avoids passing around additional parameters during setup. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
015c2360 |
|
23-Mar-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: reduce the functon params for mpq setup Everything we need is in the ring structure. No need to pass all the bits explicitly. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
f2effd49 |
|
22-Mar-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: reserve kiq eop object before unmapping it It's required. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
0104cf25 |
|
22-Mar-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: fold loops in kiq_resume() No need to loop through the compute queues twice. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
2e263c82 |
|
22-Mar-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: test KIQ before compute rings If KIQ isn't working, the compute rings won't work either. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
6a6f380f |
|
22-Mar-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: reserve mqd objects before mapping them It's required. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
0875a242 |
|
27-Mar-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: rename some functions To better match where they are used. Called from sw_init and sw_fini. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
b0ac2a32 |
|
22-Mar-2017 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: whitespace cleanup Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
739e9fff |
|
17-Mar-2017 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: enable gfx/system/vce clockgating on Polars12. Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
7e913664 |
|
15-Mar-2017 |
Andrew F. Davis <afd@ti.com> |
drm/amdgpu: remove unneeded conversions to bool Found with scripts/coccinelle/misc/boolconv.cocci. Signed-off-by: Andrew F. Davis <afd@ti.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
d766e6a3 |
|
29-Mar-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: switch ih handling to two levels (v3) Newer asics have a two levels of irq ids now: client id - the IP src id - the interrupt src within the IP v2: integrated Christian's comments. v3: fix rebase fail in SI and CIK Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Ken Wang <Qingqing.Wang@amd.com> Reviewed-by: Ken Wang <Qingqing.Wang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
536fbf94 |
|
11-Mar-2016 |
Ken Wang <Qingqing.Wang@amd.com> |
drm/amdgpu: change wptr to 64 bits (v2) Newer asics need 64 bit wptrs. If the wptr is now smaller than the rptr that doesn't indicate a wrap-around anymore. v2: integrate Christian's comments. Signed-off-by: Ken Wang <Qingqing.Wang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
8fe73328 |
|
09-Mar-2016 |
Junwei Zhang <Jerry.Zhang@amd.com> |
drm/amdgpu: init aperture definitions (v2) v2: agd: move apertures to mc structure Signed-off-by: Flora Cui <Flora.Cui@amd.com> Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
49abb980 |
|
06-Mar-2017 |
Xiangliang Yu <Xiangliang.Yu@amd.com> |
drm/amdgpu/gfx8: move CE&DE meta data structure to vi_structs.h Because different HWs have different definition for CE & DE meta data, follow mqd design to move the structures to vi_structs.h. And change the prefix from amdgpu to vi as the structures is only for VI family. Signed-off-by: Xiangliang Yu <Xiangliang.Yu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
07c397f9 |
|
19-Feb-2017 |
Trigger Huang <trigger.huang@amd.com> |
drm/amdgpu: Fix module unload hang by KIQ IRQ set In some cases, manually insmod/rmmod amdgpu is necessary. When unloading amdgpu, the KIQ IRQ enable/disable function will case system hang. The root cause is, in the sequence of function amdgpu_fini, the sw_fini of IP block AMD_IP_BLOCK_TYPE_GFX will be invoked earlier than that of AMD_IP_BLOCK_TYPE_IH. So continue to use the variable freed by AMD_IP_BLOCK_TYPE_GFX will cause system hang. Signed-off-by: Trigger Huang <trigger.huang@amd.com> Reviewed-by: Xiangliang Yu < Xiangliang.Yu@amd.com> Reviewed-by: Monk Liu <monk.liu@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
df6e2c4a |
|
16-Feb-2017 |
Junwei Zhang <Jerry.Zhang@amd.com> |
drm/amdgpu: export gfx config double offchip LDS buffers (v3) v2: move the config struct to drm_amdgpu_info_device v3: move the config feature to amdgpu_gca_config Signed-off-by: Junwei Zhang <Jerry.Zhang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
24de7515 |
|
16-Feb-2017 |
Xiangliang Yu <Xiangliang.Yu@amd.com> |
drm/amdgpu/gfx: free memory of mqd backup Need to free mqd backup when destroying ring. Signed-off-by: Xiangliang Yu <Xiangliang.Yu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Monk Liu <Monk.Liu@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
59a82d7d |
|
17-Feb-2017 |
Xiangliang Yu <Xiangliang.Yu@amd.com> |
drm/amdgpu: change pointer of mqd_ptr & mqd_backup to void vi_mqd is only used by VI family but mqd_ptr and mqd_backup is common for all ASIC, so change the pointer to void. Signed-off-by: Xiangliang Yu <Xiangliang.Yu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Monk Liu <Monk.Liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
1fb37a3d |
|
26-Jan-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:fix kiq_resume routine (V2) v2: use in_rest to fix compute ring test failure issue which occured after FLR/gpu_reset. we need backup a clean status of MQD which was created in drv load stage, and use it in resume stage, otherwise KCQ and KIQ all may faild in ring/ib test. Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Xiangliang Yu <Xiangliang.Yu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
f6bd7942 |
|
08-Feb-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:use clear_ring to clr RB In resume routine, we need clr RB prior to the ring test of engine, otherwise some engine hang duplicated during GPU reset. Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
9b49c3ab |
|
26-Jan-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:alloc mqd backup this is required for restoring the mqds after GPU reset. Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Xiangliang Yu <Xiangliang.Yu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
b85c9d2a |
|
08-Feb-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:use MACRO like other places Change-Id: Ica8f86577a50d817119de4b4fb95068dc72652a9 Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
596c67d0 |
|
06-Feb-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:divide KCQ mqd init to sw and hw sw part only invoked once during sw_init. hw part invoked during first drv load and resume later. that way we cannot alloc mqd in hw/resume, we only keep mqd allocted in sw_init routine. and hw_init routine only kmap and set it. Signed-off-by: Monk Liu <Monk.Liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
2da4da3c |
|
06-Feb-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:minor cleanup Signed-off-by: Monk Liu <Monk.Liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
bffa2280 |
|
06-Feb-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:no need use sriov vf checks We ultimately want to re-use this for bare metal, so no need to have vf checks in the KIQ code itself since kiq itself is currently only used in VF cases. Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
283caf78 |
|
06-Feb-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:bo_free_kernel will set ptr to NULL if freed Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
5ff98043 |
|
06-Feb-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:imple mqd soft ini/fini this is for SRIOV fix: mqd soft init/fini will be invoked by sw_init to allocate BO for compute MQD resource, instead of original scheme that hw_init allocates MQD. because if hw_init allocates MQD, then resume will allocate MQD, and that lead to memory leak after driver recovered from hang. Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
f3972b53 |
|
24-Jan-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/damdgpu:add new mqd member in ring introduce a new mqd member in ring is for later usage. we need keep a clean version of MQD for the purpose of recovering compute rings from hang. Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
ce137c04 |
|
22-Jan-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:cg & pg shouldn't active on VF device CG & PG function changes engine clock/gating, which is not appropriate for VF device, because one vf doesn't know the whole picture of engine's overall workload. Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
e8411302 |
|
03-Feb-2017 |
Arnd Bergmann <arnd@arndb.de> |
drm/amdgpu: fix warning on older gcc releases gcc-4.8 warns about '{0}' being used an an initializer for nested structures: drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c: In function ‘gfx_v8_0_ring_emit_ce_meta_init’: drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c:7263:2: warning: missing braces around initializer [-Wmissing-braces] } ce_payload = {0}; drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c: In function ‘gfx_v8_0_ring_emit_de_meta_init’: drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c:7290:2: warning: missing braces around initializer [-Wmissing-braces] } de_payload = {0}; Using an empty {} initializer however has the same effect and works on all versions. Fixes: acad2b2a7b70 ("drm/amdgpu:implement CE/DE meta-init routines") Signed-off-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
d2383267 |
|
10-Feb-2017 |
ozeng <oak.zeng@amd.com> |
drm/amdgpu: Initialize pipe priority order on graphic initialization Initialized PIPE_ORDER_TS0/1/2/3 field of SPI_ARB_PRIORITY register to 2. This set the pipe priority order to: 02 - HP3D, CS_H, GFX, CS_M, CS_L Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
50ddc75e |
|
23-Jan-2017 |
Junwei Zhang <Jerry.Zhang@amd.com> |
drm/amd/amdgpu: remove the uncessary parameter for ib scheduler Signed-off-by: Junwei Zhang <Jerry.Zhang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c2ce92fc |
|
16-Jan-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:in cntx_ctrl we need insert meta-init for CE/DE(V2) to support SRIOV preemption. v2: fix emit_frame_size Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
acad2b2a |
|
16-Jan-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:implement CE/DE meta-init routines those package need to insert into ring buffer for SRIOV case. they are used to let CP do preemption. Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
ae65a26d |
|
12-Jan-2017 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:add META_DATA struct for CSA/SRIOV v2 META-DATA is used in GFX cmd submit, we have two format suit for META-DATA-init, one is legacy and another is for chained-ib preempt, which is used in vulkan UMD. v2: drop use CP version number to judge if chain-ib supports or not, we wait for it mature Signed-off-by: Monk Liu <Monk.Liu@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
50261151 |
|
16-Jan-2017 |
Nils Wallménius <nils.wallmenius@gmail.com> |
drm/amdgpu: simplify allocation of scratch regs The scratch regs are sequential so there's no need to keep them in an array, we can just return the index of the first free register + the base register. Also change the array of bools for keeping track of the free regs to a bitfield. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Nils Wallménius <nils.wallmenius@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
f10b478d |
|
09-Jan-2017 |
Julia Lawall <julia.lawall@lip6.fr> |
drm/amdgpu/gfx8: fix bugon.cocci warnings Use BUG_ON instead of a if condition followed by BUG. Generated by: scripts/coccinelle/misc/bugon.cocci Reviewed-by: Christian König <christian.koenig@amd.com> Reviewd-by: Xiangliang.Yu <Xiangliang.Yu@amd.com> CC: Xiangliang Yu <Xiangliang.Yu@amd.com> Signed-off-by: Julia Lawall <julia.lawall@lip6.fr> Signed-off-by: Fengguang Wu <fengguang.wu@intel.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
880e87e3 |
|
11-Jan-2017 |
Xiangliang Yu <Xiangliang.Yu@amd.com> |
drm/amdgpu/gfx8: implement emit_rreg/wreg function Implement emit_rreg/wreg function for kiq ring. Signed-off-by: Xiangliang Yu <Xiangliang.Yu@amd.com> Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
ebd843d6 |
|
05-Jan-2017 |
Huang Rui <ray.huang@amd.com> |
drm/amdgpu: add get clockgating_state method for gfx v8 Signed-off-by: Huang Rui <ray.huang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
4e638ae9 |
|
23-Dec-2016 |
Xiangliang Yu <Xiangliang.Yu@amd.com> |
drm/amdgpu/gfx8: add support kernel interface queue(KIQ) KIQ is queue-memory based initialization method: setup KIQ queue firstly, then send command to KIQ to setup other queues, without accessing registers. For virtualization, need KIQ to access virtual function registers when running on guest mode. V2: use amdgpu_bo_create/free_kernel to allocate BO. Signed-off-by: Monk Liu <Monk.Liu@amd.com> Signed-off-by: Xiangliang Yu <Xiangliang.Yu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
ae6a58e4 |
|
21-Dec-2016 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: use same enter/exit safe mode for gfx_8. Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
5c964221 |
|
14-Dec-2016 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: refine gfx_v8 pg code. move en/disable GFX CP/SMU_HS PG to function gfx_v8_0_set_powergating_state Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c4642a47 |
|
14-Dec-2016 |
Junwei Zhang <Jerry.Zhang@amd.com> |
drm/amd/amdgpu: add Polaris12 support (v3) v2: agd: squash in various fixes v3: agd: squash in: drm/amdgpu: remove unnecessary smc sk firmware for polaris12 Signed-off-by: Junwei Zhang <Jerry.Zhang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Ken Wang <Qingqing.Wang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
8a19e7fa |
|
07-Dec-2016 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: refine set clock gating for tonga/polaris Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
ad1830d5 |
|
07-Dec-2016 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: fix pg can't be disabled by PG mask. Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c4d17b81 |
|
07-Dec-2016 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: always initialize gfx pg for gfx_v8.0. v2: always init gfx pg for asics that can support. Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
202e0b22 |
|
07-Dec-2016 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: fix init save/restore list in gfx_v8.0 set valid data to mmRLC_SRM_INDEX_CNTL_ADDRx/DATAx. Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
|
#
eb584241 |
|
07-Dec-2016 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: fix enable_cp_power_gating in gfx_v8.0. the CP_PG_DISABLE bit was reversed. Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
|
#
c5a60ce8 |
|
05-Dec-2016 |
Tom St Denis <tom.stdenis@amd.com> |
drm/amd/amdgpu: Add debugfs support for reading GPRs (v2) Implemented for SGPRs for GFX v8 initially. (v2) cleanup minor whitespace and remove sanity check and addressing is in dwords not bytes Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Acked-by: Edward O'Callaghan <funfunctor@folklore1984.net> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
ff9d6460 |
|
01-Aug-2016 |
Huang Rui <ray.huang@amd.com> |
drm/amdgpu: update golden setting of tonga Signed-off-by: Huang Rui <ray.huang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Ken Wang <Qingqing.Wang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
84f3f05b |
|
29-Nov-2016 |
Xiangliang Yu <Xiangliang.Yu@amd.com> |
drm/amdgpu: Don't touch GFX hw during HW fini For SR-IOV client, driver shouldn't touch the GFX hw during HW fini, otherwise, gfx will fail to start after rebooting guest os. Signed-off-by: shaoyunl <Shaoyun.Liu@amd.com> Signed-off-by: Xiangliang Yu <Xiangliang.Yu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Monk Liu <Monk.Liu@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
aeab2032 |
|
29-Nov-2016 |
Xiangliang Yu <Xiangliang.Yu@amd.com> |
drm/amdgpu: drop redundant vi_mqd define Vi_structs.h has defined vi_mqd, drop redundant vi_mqd define. Signed-off-by: Monk Liu <Monk.Liu@amd.com> Signed-off-by: Xiangliang Yu <Xiangliang.Yu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
dd31ae9a |
|
25-Nov-2016 |
Arindam Nath <arindam.nath@amd.com> |
drm/amd/amdgpu: enable GUI idle INT after enabling CGCG GUI idle interrupts should be enabled only after we have enabled coarse grain clock gating (CGCG). This prevents GFX engine generating idle interrupt even though CGCG is not completely enabled. Most of the time this goes un-noticed, but on some Stoney ASICs this results in GFX engine hang after system resumes from suspend. The issue is not particular to Stoney though and could have occured on any ASIC. The patch fixes this issue. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reported-by: Sunil Uttarwar <Sunil.Uttarwar1@amd.com> Signed-off-by: Arindam Nath <arindam.nath@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
|
#
ad3b9614 |
|
15-Nov-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: move eop programming per queue It's per queue not per pipe. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
45682886 |
|
11-Nov-2016 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:impl vgt_flush for VI(V5) when shadowing enabled, tesselation app will trigger vm fault because below three tesselation registers: VGT_TF_RING_SIZE__CI__VI, VGT_HS_OFFCHIP_PARAM__CI__VI, VGT_TF_MEMORY_BASE__CI__VI, need to be programed after vgt-flush. Tesselation picture vm fault disappeared after vgt-flush introduced. v2:implement vgt-flush for CI & SI. v3:move vgt flush inside of cntx_cntrl v4:count vgt flush in frame_size v5:squash in typo fix Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
3f12325a |
|
07-Nov-2016 |
Ravikant B Sharma <ravikant.s2@samsung.com> |
drm/amd/amdgpu : Fix NULL pointer comparison Replace direct comparisons to NULL i.e. 'x == NULL' with '!x'. As per coding standard. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Ravikant B Sharma <ravikant.s2@samsung.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
bc24fbe9 |
|
07-Nov-2016 |
Tom St Denis <tom.stdenis@amd.com> |
drm/amd/amdgpu: Clean up wave gfx8 helper De-numberify indirect register access for gfx v8. Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
74f3ce31 |
|
14-Oct-2016 |
Tom St Denis <tom.stdenis@amd.com> |
drm/amd/amdgpu: Put in rest of wave fields Add the rest of the basic SQ WAVE fields to finish off the implementation. Eventually, a separate interface will be needed for GPRs. Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
472259f0 |
|
14-Oct-2016 |
Tom St Denis <tom.stdenis@amd.com> |
drm/amd/amdgpu: re-factor debugfs wave reader Move IP version specific code into a callback. Also add support for gfx7 devices. Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
a1255107 |
|
13-Oct-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: rework IP block registration (v2) This makes it easier to replace specific IP blocks on asics for handling virtual_dce, DAL, etc. and for building IP lists for hw or tables. This also stored the status information in the same structure. v2: split out spelling fix into a separate patch add a function to add IPs to the list Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
79887142 |
|
05-Oct-2016 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: move align_mask and nop into ring funcs as well (v2) They are constant as well. v2: update uvd and vce phys ring structures as well Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
21cd942e |
|
05-Oct-2016 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: move the ring type into the funcs structure (v2) It's constant, so it doesn't make to much sense to keep it with the variable data. v2: update vce and uvd phys mode ring structures as well Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
e12f3d7a |
|
05-Oct-2016 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: move IB and frame size directly into the engine description I should have suggested that on the initial patchset. This saves us a few CPU cycles during CS and a bunch of loc. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
7bc6be82 |
|
05-Oct-2016 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: remove explicit NULL init for parse_cs sed -i "/\.parse_cs = NULL,/d" drivers/gpu/drm/amd/amdgpu/*.c That's just a leftover from radeon. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
e08c90a7 |
|
04-Oct-2016 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: remove 128 NOP hack from vm_flush v2 With the padding raised to 256 DW that shouldn't be needed any more. v2: reduce estimation as well Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
66f3b2d5 |
|
04-Oct-2016 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: pad gfx and compute rings to 256 dw The same as on windows to avoid further problems with CE/DE command submission overlaps. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
34817db6 |
|
10-Oct-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: use cached raster config values in csb setup Simplify the code and properly set the csb for harvest values. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
392f0c77 |
|
10-Oct-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: cache rb config values Needed when for SR-IOV and when PG is enabled. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
42e8cb50 |
|
27-Apr-2016 |
Frank Min <Frank.Min@amd.com> |
drm/amdgpu:wptr poll address of gfx8 is needed for GFX8, gfx ring's wptr_addr is needed by SRIOV & CP for polling. Signed-off-by: Frank Min <Frank.Min@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
4c2b2453 |
|
27-Sep-2016 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:properly fix some JumpTable issues we found some MEC ucode leads to IB test fail or even ring test fail if Jump Table of it is not start in FW bo with page aligned address, fixed by always make JT address page aligned. we don't need to patch JT2 for MEC2, because for VI, MEC2 is a copy of MEC1, thus when converting fw_type for MEC_JT2 we just return MEC1,hw can use the same JT for both MEC1 & MEC2. above two change fixed some ring/ib test failure issue for some version of MEC ucode. Signed-off-by: Frank Min <Frank.Min@amd.com> Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
bed5712e |
|
26-Sep-2016 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:add MEC_STORAGE ucode id for sriov for sriov, SMC need MEC_STORAGE reserved in fw bo. Signed-off-by: Monk Liu <Monk.Liu@amd.com> Signed-off-by: Frank Min <frank.min@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
03f48dd5 |
|
15-Aug-2016 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: add AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS flag v3 Add a flag noting that a BO must be created using linear VRAM and set this flag on all in kernel users where appropriate. Hopefully I haven't missed anything. v2: add it in a few more places, fix CPU mapping. v3: rename to VRAM_CONTIGUOUS, fix typo in CS code. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Edward O'Callaghan <funfunctor@folklore1984.net> Tested-by: Mike Lothian <mike@fireburn.co.uk> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
f54d1867 |
|
25-Oct-2016 |
Chris Wilson <chris@chris-wilson.co.uk> |
dma-buf: Rename struct fence to dma_fence I plan to usurp the short name of struct fence for a core kernel struct, and so I need to rename the specialised fence/timeline for DMA operations to make room. A consensus was reached in https://lists.freedesktop.org/archives/dri-devel/2016-July/113083.html that making clear this fence applies to DMA operations was a good thing. Since then the patch has grown a bit as usage increases, so hopefully it remains a good thing! (v2...: rebase, rerun spatch) v3: Compile on msm, spotted a manual fixup that I broke. v4: Try again for msm, sorry Daniel coccinelle script: @@ @@ - struct fence + struct dma_fence @@ @@ - struct fence_ops + struct dma_fence_ops @@ @@ - struct fence_cb + struct dma_fence_cb @@ @@ - struct fence_array + struct dma_fence_array @@ @@ - enum fence_flag_bits + enum dma_fence_flag_bits @@ @@ ( - fence_init + dma_fence_init | - fence_release + dma_fence_release | - fence_free + dma_fence_free | - fence_get + dma_fence_get | - fence_get_rcu + dma_fence_get_rcu | - fence_put + dma_fence_put | - fence_signal + dma_fence_signal | - fence_signal_locked + dma_fence_signal_locked | - fence_default_wait + dma_fence_default_wait | - fence_add_callback + dma_fence_add_callback | - fence_remove_callback + dma_fence_remove_callback | - fence_enable_sw_signaling + dma_fence_enable_sw_signaling | - fence_is_signaled_locked + dma_fence_is_signaled_locked | - fence_is_signaled + dma_fence_is_signaled | - fence_is_later + dma_fence_is_later | - fence_later + dma_fence_later | - fence_wait_timeout + dma_fence_wait_timeout | - fence_wait_any_timeout + dma_fence_wait_any_timeout | - fence_wait + dma_fence_wait | - fence_context_alloc + dma_fence_context_alloc | - fence_array_create + dma_fence_array_create | - to_fence_array + to_dma_fence_array | - fence_is_array + dma_fence_is_array | - trace_fence_emit + trace_dma_fence_emit | - FENCE_TRACE + DMA_FENCE_TRACE | - FENCE_WARN + DMA_FENCE_WARN | - FENCE_ERR + DMA_FENCE_ERR ) ( ... ) Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk> Acked-by: Sumit Semwal <sumit.semwal@linaro.org> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: http://patchwork.freedesktop.org/patch/msgid/20161025120045.28839-1-chris@chris-wilson.co.uk
|
#
0711257e |
|
17-Oct-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/st: move ATC CG golden init from gfx to mc It's technically an MC register so make sure we initialize it in the MC module rather than the gfx module. Since other bits in the same register are used to enable ATC CG features make sure we apply the golden setting first. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
da146d3b |
|
13-Oct-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: fix amdgpu_need_full_reset (v2) IP types are not an index. Each asic may have number and type of IPs. Properly check the the type rather than using the type id as an index. v2: fix all the IPs to not use IP type as an idx as well. Reviewed-by: Chunming Zhou <david1.zhou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
|
#
6ae81452 |
|
07-Oct-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: fix CGCG_CGLS handling When setting up the RLC, only disable the CGCG and CGLS bits rather than clearing the entire register to avoid losing the golden settings. Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
|
#
a8ca3413 |
|
18-Sep-2016 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: set gfx clock gating for tonga/polaris. Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
167ac573 |
|
14-Sep-2016 |
Huang Rui <ray.huang@amd.com> |
drm/amdgpu: implement raster configuration for gfx v8 This patch is to implement the raster configuration and harvested configuration of gfx v8. Signed-off-by: Huang Rui <ray.huang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Edward O'Callaghan <funfunctor@folklore1984.net> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
7512ad16 |
|
16-Sep-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: add ring callbacks for ib and dma frame size Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
761c2e82 |
|
02-Sep-2016 |
Baoyou Xie <baoyou.xie@linaro.org> |
drm/amdgpu: mark symbols static where possible We get a few warnings when building kernel with W=1: drivers/gpu/drm/amd/amdgpu/cz_smc.c:51:5: warning: no previous prototype for 'cz_send_msg_to_smc_async' [-Wmissing-prototypes] drivers/gpu/drm/amd/amdgpu/cz_smc.c:143:5: warning: no previous prototype for 'cz_write_smc_sram_dword' [-Wmissing-prototypes] drivers/gpu/drm/amd/amdgpu/iceland_smc.c:124:6: warning: no previous prototype for 'iceland_start_smc' [-Wmissing-prototypes] drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c:3926:6: warning: no previous prototype for 'gfx_v8_0_rlc_stop' [-Wmissing-prototypes] drivers/gpu/drm/amd/amdgpu/amdgpu_job.c:94:6: warning: no previous prototype for 'amdgpu_job_free_cb' [-Wmissing-prototypes] .... In fact, these functions are only used in the file in which they are declared and don't need a declaration, but can be made static. So this patch marks these functions with 'static'. Reviewed-by: Christian König <christian.koenig@amd.com> Acked-by: Huang Rui <ray.huang@amd.com> Reviewed-by: Edward O'Callaghan <funfunctor@folklore1984.net> Signed-off-by: Baoyou Xie <baoyou.xie@linaro.org> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
753ad49c |
|
25-Aug-2016 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:implement CONTEXT_CONTROL (v5) v1: for gfx8, use CONTEXT_CONTROL package to dynamically skip preamble CEIB and other load_xxx command in sequence. v2: support GFX7 as well. remove cntxcntl in compute ring funcs because CPC doesn't support this packet. v3: fix reduntant judgement in cntxcntl. v4: some cleanups, don't change cs_submit() v5: keep old MESA supported & bump up KMS version. Signed-off-by: Monk Liu <Monk.Liu@amd.com> Ack-by: Chunming Zhou <David1.Zhou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
8640faed |
|
07-Sep-2016 |
Junwei Zhang <Jerry.Zhang@amd.com> |
drm/amdgpu: free the BO in kernel by helper amdgpu_bo_free_kernel() Signed-off-by: Junwei Zhang <Jerry.Zhang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
d4946ccf |
|
26-Aug-2016 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu: new method to sync ce&de sync switch buffer scheme with windows kmd for gfx v8, step2: Insert 128NOP after&before VM flush to prevent CE vm fault. Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
e7706b42 |
|
02-Sep-2016 |
Tom St Denis <tom.stdenis@amd.com> |
drm/amd/amdgpu: Merge get_rptr functions in gfx8 Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c2167a65 |
|
26-Aug-2016 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu:add switch buffer to end of CS (v2) sync switch buffer scheme with windows kmd for gfx v8, step1: append a switch_buffer to the end of CS v2:rebase on latest staging Signed-off-by: Monk Liu <Monk.Liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
61cb8cef |
|
09-Aug-2016 |
Tom St Denis <tom.stdenis@amd.com> |
drm/amd/amdgpu: Simplify bitfield operations in gfx v8 This patch introduces a new macro WREG32_FIELD which is used to write to a register with a new value in a field. It's designed to replace the pattern: tmp = RREG32(mmFoo); tmp &= ~REG__FIELD_MASK; tmp |= new_value << REG__FIELD__SHIFT; WREG32(mmFoo, tmp) with: WREG32_FIELD(Foo, FIELD, new_value); Unlike WREG32_P() it understands offsets/masks and doesn't require the caller to shift the value (or mask properly). It's applied where suitable in the gfx_v8_0.c driver to start with. Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
5003f278 |
|
09-Aug-2016 |
Tom St Denis <tom.stdenis@amd.com> |
drm/amd/amdgpu: Simplify various gfx v8 functions Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
62d2ce4b |
|
09-Aug-2016 |
Tom St Denis <tom.stdenis@amd.com> |
drm/amd/amdgpu: Correct whitespace in GFX v8 Fix various whitespace issues in gfx v8 driver. Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
5765a36d |
|
29-Jul-2016 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: AMD SW workaround for certain partner boards Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
78bbbd9c |
|
14-Dec-2015 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: pin shared GWS, GDS and OA resources They can't move anyway, but just to be clean here. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
e4ae0fc3 |
|
15-Jul-2016 |
Chunming Zhou <David1.Zhou@amd.com> |
drm/amdgpu: implement gfx8 post_soft_reset Signed-off-by: Chunming Zhou <David1.Zhou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
1057f20c |
|
15-Jul-2016 |
Chunming Zhou <David1.Zhou@amd.com> |
drm/amdgpu: add gfx8 pre soft reset Signed-off-by: Chunming Zhou <David1.Zhou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
3d7c6384 |
|
14-Jul-2016 |
Chunming Zhou <David1.Zhou@amd.com> |
drm/amdgpu: implement gfx8 check_soft_reset Signed-off-by: Chunming Zhou <David1.Zhou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
a5a5e308 |
|
01-Aug-2016 |
Huang Rui <ray.huang@amd.com> |
drm/amdgpu: update golden setting of polaris10 Signed-off-by: Huang Rui <ray.huang@amd.com> Reviewed-by: Ken Wang <Qingqing.Wang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
9761bc53 |
|
01-Aug-2016 |
Huang Rui <ray.huang@amd.com> |
drm/amdgpu: update golden setting of polaris11 Signed-off-by: Huang Rui <ray.huang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Ken Wang <Qingqing.Wang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
3a494b58 |
|
01-Aug-2016 |
Huang Rui <ray.huang@amd.com> |
drm/amdgpu: update golden setting of carrizo Signed-off-by: Huang Rui <ray.huang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
fe85f07f |
|
01-Aug-2016 |
Huang Rui <ray.huang@amd.com> |
drm/amdgpu: update golden setting of iceland Signed-off-by: Huang Rui <ray.huang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
bbec97aa |
|
05-Jul-2016 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: add a fence timeout for the IB tests v2 10ms should be enough for now. v2: fix some typos in CIK code Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com> Reviewed-by: Edward O'Callaghan <funfunctor@folklore1984.net> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
6d44565d |
|
05-Jul-2016 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: remove usec timeout loop from IB tests We already waited for the fence, so waiting for the registers is completely pointless and just copy & pasted from the ring test. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
22a77cf6 |
|
05-Jul-2016 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: cleanup hw reference handling in the IB tests Reference should be taken when we make the assignment, not anywhere else. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
eeade25a |
|
10-Jul-2016 |
Ken Wang <Qingqing.Wang@amd.com> |
drm/amdgpu: fix power distribution issue for Polaris10 XT Signed-off-by: Ken Wang <Qingqing.Wang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
795c2109 |
|
06-Jul-2016 |
Ken Wang <Qingqing.Wang@amd.com> |
drm/amdgpu: Add a missing register to Polaris golden setting Signed-off-by: Ken Wang <Qingqing.Wang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
33b7ed01 |
|
05-Jul-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: remove more of the ring backup code Not used anymore. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
9559ef5b |
|
28-Jun-2016 |
Tom St Denis <tom.stdenis@amd.com> |
drm/amd/gfx: add instance field to select_se_sh (v3) Add ability to specify instance in select_se_sh callback. Defaults to 0xffffffff all over the driver. (v2) Don't enable INSTANCE_BROADCAST by default (v3) Style changes Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
05fb7291 |
|
20-Jun-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: move select_se_sh into the gfx struct It's gfx IP specific, not asic specific, so move to a gfx callback. Reviewed-by: Chunming Zhou <david1.zhou@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
b95e31fd |
|
07-Jul-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: move get_gpu_clock_counter into the gfx struct It's gfx IP specific, not asic specific, so move to a gfx callback. Reviewed-by: Chunming Zhou <david1.zhou@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
9de06de8 |
|
17-Jun-2016 |
Nicolai Hähnle <nicolai.haehnle@amd.com> |
drm/amdgpu/gfx8: set USER_SHADER_ARRAY_CONFIG based on disable_cu parameter v2: do not overwrite register when bitmap is zero Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Nicolai Hähnle <nicolai.haehnle@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
07cf1a0b |
|
09-Jun-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: fix CP jump table size Align to the jump table offset. Fixes hangs on some systems with GFX PG enabled. Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com> Tested-by: Nicolai Hähnle <nicolai.haehnle@amd.com> Reviewed-by: Tom St Denis <tom.stdenis@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
78f73bf0 |
|
03-Jun-2016 |
Tom St Denis <tom.stdenis@amd.com> |
drm/amdgpu/gfx80: Add QUICK_PG bit to GFX header and use it. Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
dad4acc8 |
|
02-Jun-2016 |
Tom St Denis <tom.stdenis@amd.com> |
drm/amdgpu/gfx8: Tidy up various PG helpers Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
6ab3886c |
|
02-Jun-2016 |
Tom St Denis <tom.stdenis@amd.com> |
drm/amdgpu/gfx8: Switch Stoney to share CZ's RLC functions According to the bringup code ST/CZ share the RLC ENTER/EXIT logic. Tested on my ST board. Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
7894745a |
|
26-May-2016 |
Tom St Denis <tom.stdenis@amd.com> |
drm/amdgpu/gfx8: Add serdes wait for idle in CGCG en/disable Must wait for SERDES idle before exiting RLC SAFEMODE Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
7ba0eb6d |
|
04-May-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: clean up polaris11 PG enable Fix the logic for enabling/disabling. Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
2c547165 |
|
04-May-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: add powergating support for CZ/ST This implements powergating support for CZ/ST asics. Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c2546f55 |
|
03-May-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: rename some pg functions So they can be shared with other asics. Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
fb16007b |
|
03-May-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: add state setup for CZ/ST GFX power gating This sets up the CP jump table and GDS buffer and sets the PG state registers. Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
d9d533c1 |
|
27-Jun-2016 |
Ken Wang <Qingqing.Wang@amd.com> |
drm/amdgpu: add ACLK_CNTL setting for polaris10 This is a temporary workaround for early boards. Signed-off-by: Ken Wang <Qingqing.Wang@amd.com> Reviewed-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
92d15768 |
|
07-Jun-2016 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu/gfx8: update golden setting for polaris10 Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
13331ac3 |
|
30-May-2016 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu: fix gfx8 ucode mem leak Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
d1a7f7aa |
|
23-May-2016 |
Ken Wang <Qingqing.Wang@amd.com> |
drm/amdgpu/iceland: Set SC_PA_RASTER_CONFIG according to different RB enabled fix the raster config setting for different iceland configs. Signed-off-by: Ken Wang <Qingqing.Wang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
b9934878 |
|
16-May-2016 |
Flora Cui <Flora.Cui@amd.com> |
drm/amdgpu: update Polaris11 golden setting Signed-off-by: Flora Cui <Flora.Cui@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
d4ab989f |
|
16-May-2016 |
Flora Cui <Flora.Cui@amd.com> |
drm/amdgpu: update Polaris10 golden setting Signed-off-by: Flora Cui <Flora.Cui@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
f84e63f2 |
|
28-Apr-2016 |
Marek Olšák <marek.olsak@amd.com> |
drm/amdgpu: fix TC cache flushing TC_WB_ACTION must be set according to the docs Signed-off-by: Marek Olšák <marek.olsak@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
d88bf583 |
|
06-May-2016 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: move VM fields into job They are the same for all IBs. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
f153d286 |
|
06-May-2016 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: move context switch handling into common code v2 It was a source of bugs to repeat that in each IP version. v2: rename parameter Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
9f8fb5a2 |
|
06-May-2016 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: move preamble IB handling into common code This fixes the handling which was completely broken when you ad more than one preamble IB. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
88a907d6 |
|
04-May-2016 |
Tom St Denis <tom.stdenis@amd.com> |
drm/amd/amdgpu: Add name field to amd_ip_funcs (v2) Add name that we can print out in kernel messages to aid in debugging. v2: drop DAL changes for upstream Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
7dae69a2 |
|
03-May-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: fetch cu_info once at init Fetch this info once at init and just store the results for future requests. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
edf600da |
|
03-May-2016 |
Christian König <christian.koenig@amd.com> |
drm/amd: cleanup remaining spaces and tabs v2 This is the result of running the following commands: find drivers/gpu/drm/amd/ -name "*.h" -exec sed -i 's/[ \t]\+$//' {} \; find drivers/gpu/drm/amd/ -name "*.c" -exec sed -i 's/[ \t]\+$//' {} \; find drivers/gpu/drm/amd/ -name "*.h" -exec sed -i 's/ \+\t/\t/' {} \; find drivers/gpu/drm/amd/ -name "*.c" -exec sed -i 's/ \+\t/\t/' {} \; v2: drop changes to DAL and internal headers Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c5637837 |
|
19-Apr-2016 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu: keep vm in job instead of ib (v2) ib.vm is a legacy way to get vm, after scheduler implemented vm should be get from job, and all ibs from one job share the same vm, no need to keep ib.vm just move vm field to job. this patch as well add job as paramter to ib_schedule so it can get vm from job->vm. v2: agd: sqaush in: drm/amdgpu: check if ring emit_vm_flush exists in vm flush No vm flush on engines that don't support VM. bug: https://bugs.freedesktop.org/show_bug.cgi?id=95195 Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
16a7989a |
|
28-Mar-2016 |
Tom St Denis <tom.stdenis@amd.com> |
drm/amd/amdgpu: Drop print_status callbacks. First patch in series to move to user mode debug tools we're removing the print_status callbacks. These functions were unused at the moment anyway. Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
ae17c999 |
|
22-Mar-2016 |
Slava Grigorev <slava.grigorev@amd.com> |
drm/amd/amdgpu: fix 64-bit division Signed-off-by: Slava Grigorev <slava.grigorev@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
2cc0c0b5 |
|
14-Mar-2016 |
Flora Cui <Flora.Cui@amd.com> |
drm/amdgpu: change ELM/BAF to Polaris10/Polaris11 Adjust to preferred code names. Signed-off-by: Flora Cui <Flora.Cui@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
f4bfffdd |
|
16-Feb-2016 |
Eric Huang <JinHuiEric.Huang@amd.com> |
drm/amd/amdgpu: add power gating init for Baffin Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Eric Huang <JinHuiEric.Huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
2b6cd977 |
|
14-Apr-2016 |
Eric Huang <JinHuiEric.Huang@amd.com> |
drm/amd/amdgpu: add power gating initialization support for GFX8.0 Signed-off-by: Eric Huang <JinHuiEric.Huang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
62a86fc2 |
|
12-Feb-2016 |
Eric Huang <JinHuiEric.Huang@amd.com> |
drm/amd/amdgpu: add medium grain powergating support for Baffin Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Eric Huang <JinHuiEric.Huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
68182d90 |
|
29-Oct-2015 |
Flora Cui <Flora.Cui@amd.com> |
drm/amdgpu: add GFX support for ELM/BAF V2: use gfx_8_0_*.h instead of gfx_8_1_*.h v3: agd: integrate support for gfx info table Signed-off-by: Flora Cui <Flora.Cui@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
dbff57bc |
|
07-Apr-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx: rework fiji cg functions so they can be shared They can be shared with other asics with minor modifications. Acked-by: Tom St Denis <tom.stdenis@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
146f256f |
|
07-Apr-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx: adjust gfx_v8_0_send_serdes_cmd for ST Acked-by: Tom St Denis <tom.stdenis@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
79deaaf4 |
|
07-Apr-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: rename send_serdes_cmd So it can be shared with CZ/ST. Acked-by: Tom St Denis <tom.stdenis@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
14698b6c |
|
07-Apr-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx: add proper CG flags for fiji We were already enabling these CG features, this uses the standard interface for doing so. Acked-by: Tom St Denis <tom.stdenis@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
771c8ec17 |
|
13-Apr-2016 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: use the ring name for debugfs (v2) Instead of hard coding just another name in the ring code. v2: squash in Tom's rebase fix Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
2800de2e |
|
13-Apr-2016 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: reduce the ring size for GFX Those are way too large. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
a3f1cf35 |
|
12-Apr-2016 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: use max_dw in ring_init Instead of specifying the total ring size calculate that from the maximum number of dw a submission can have and the number of concurrent submissions. This fixes UVD with 8 concurrent submissions or more. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
73cfa5f5 |
|
16-Mar-2016 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu: move ib.fence to job.fence Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
cc55c45d |
|
16-Mar-2016 |
Monk Liu <Monk.Liu@amd.com> |
drm/amdgpu: give a fence param to ib_free thus amdgpu_ib_free() can hook sched fence to SA manager in later patches. BTW: for amdgpu_free_job(), it should only fence_put() the fence of the last ib once, so fix it as well in this patch. Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
b8c7b39e |
|
01-Mar-2016 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: split pipeline sync and vm flush This allows us to use the pipeline sync for other tasks as well. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
|
#
336d1f5e |
|
16-Feb-2016 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: remove HW fence owner Not used any more since we now always use the sheduler. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
|
#
d35db561 |
|
02-Mar-2016 |
Chunming Zhou <David1.Zhou@amd.com> |
drm/amdgpu: add hdp invalidation for gfx8 Signed-off-by: Chunming Zhou <David1.Zhou@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
6157bd7a |
|
02-Mar-2016 |
Flora Cui <Flora.Cui@amd.com> |
drm/amdgpu: fix rb bitmap & cu bitmap calculation Fix some copy paste typos. Signed-off-by: Flora Cui <Flora.Cui@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
9cac5373 |
|
28-Feb-2016 |
Chunming Zhou <David1.Zhou@amd.com> |
drm/amdgpu/gfx8: specify which engine to wait before vm flush Select between me and pfp properly. Signed-off-by: Chunming Zhou <David1.Zhou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Cc: stable@vger.kernel.org Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
4ff37a83 |
|
26-Feb-2016 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: fix VM faults caused by vm_grab_id() v4 The owner must be per ring as long as we don't support sharing VMIDs per process. Also move the assigned VMID and page directory address into the IB structure. v3: assign the VMID to all IBs, not just the first one. v4: use correct pointer for owner Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
aac1e3ca |
|
24-Feb-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx: fix off by one in rb rework (v2) When I reworked this code, I messed up num rb count. v2: use hweight32 Reviewed-by: Ken Wang <Qingquing.Wang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
04ab3b76 |
|
18-Feb-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: fix priv reg interrupt enable Looks like a copy/paste typo. Reviewed-by: Christian König <christian.koenig@amd.com> Noticed-by: David Panariti <David.Panariti@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
549300ce |
|
12-Feb-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/vi: move uvd tiling config setup into uvd code Split uvd and gfx programming. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c458fe94 |
|
12-Feb-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/vi: move sdma tiling config setup into sdma code Split sdma and gfx programming. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
8f8e00c1 |
|
11-Feb-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx: clean up harvest configuration (v2) Read back harvest configuration from registers and simplify calculations. No need to program the raster config registers. These are programmed as golden registers and the user mode drivers program them as well. v2: rebase on Tom's patches Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
e86f9cee |
|
07-Feb-2016 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: move sync into job object No need to keep that for every IB. Signed-off-by: Christian König <christian.koenig@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
a0332b56 |
|
31-Jan-2016 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: send SDMA/GFX IB tests directly to the ring again There is no point in sending them through the scheduler. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucer@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
b07c60c0 |
|
30-Jan-2016 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: move ring from IBs into job We can't submit to multiple rings at the same time anyway. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucer@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
9e5d5309 |
|
30-Jan-2016 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: make pad_ib a ring function v3 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 <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucer@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
6e9821b2 |
|
04-Feb-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx: minor code cleanup Drop needless function wrapper. Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
a27de35c |
|
21-Jan-2016 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: remove the ring lock v2 It's not needed any more because all access goes through the scheduler now. v2: Update commit message. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
5907a0d8 |
|
18-Jan-2016 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: cleanup sync_seq handling Not used any more without semaphores Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
ea5e4c87 |
|
15-Jan-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: remove some more semaphore leftovers No longer needed since semaphores were removed. Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Chunming Zhou <David1.Zhou@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
2f4b9400 |
|
14-Jan-2016 |
Chunming Zhou <David1.Zhou@amd.com> |
drm/amdgpu: clean up hw semaphore support in driver No longer used. Signed-off-by: Chunming Zhou <David1.Zhou@amd.com> Reviewed-by: Ken Wang <Qingqing.Wang@amd.com> Reviewed-by: Monk Liu <monk.liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
951e0962 |
|
02-Feb-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: load MEC ucode manually on iceland The smc doesn't handle it. Reviewed-by: Ken Wang <Qingqing.Wang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
|
#
97dde76a |
|
02-Feb-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: don't load MEC2 on topaz Not validated. Reviewed-by: Ken Wang <Qingqing.Wang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
|
#
1d22a454 |
|
02-Feb-2016 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: enable cp inst/reg error interrupts Enable CP register/instruction error interrupts. Useful for debugging command stream problems. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
7776a693 |
|
15-Oct-2015 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: Add some tweaks to gfx 8 soft reset Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Ken Wang <Qingqing.Wang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
6e378858 |
|
10-Nov-2015 |
Eric Huang <JinHuiEric.Huang@amd.com> |
drm/amd/amdgpu: add gfx clock gating support for Fiji. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com> Signed-off-by: Eric Huang <JinHuiEric.Huang@amd.com>
|
#
e61710c5 |
|
10-Nov-2015 |
Jammy Zhou <Jammy.Zhou@amd.com> |
drm/amdgpu: support per device powerplay enablement (v2) The amdgu_powerplay variable is global for multiple GPU instances. v2: fold in Flora's module option change, protect adev reference in macros Signed-off-by: Jammy Zhou <Jammy.Zhou@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com>
|
#
ba5c2a87 |
|
06-Nov-2015 |
Rex Zhu <Rex.Zhu@amd.com> |
drm/amdgpu: disable legacy path of firmware check if powerplay is enabled Powerplay will use a different interface once it's integrated. These legacy pathes will be removed once powerplay is enabled by default. Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Jammy Zhou <Jammy.Zhou@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c27816a8 |
|
07-Dec-2015 |
Flora Cui <Flora.Cui@amd.com> |
drm/amdgpu/gfx8: update PA_SC_RASTER_CONFIG:PKR_MAP only Use default value as a base. Signed-off-by: Flora Cui <Flora.Cui@amd.com> Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com>
|
#
3b55ddad |
|
01-Dec-2015 |
Flora Cui <Flora.Cui@amd.com> |
drm/amdgpu/gfx8: Enable interrupt on ME1_PIPE3 Otherwise FW cannot see the RLC ACK for the memory clean request It's for Stoney. Signed-off-by: Flora Cui <Flora.Cui@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com>
|
#
eb64526f |
|
02-Dec-2015 |
Tom St Denis <tom.stdenis@amd.com> |
amdgpu/gfxv8: Remove magic numbers from function gfx_v8_0_tiling_mode_table_init() Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
|
#
0d07db7e |
|
01-Dec-2015 |
Tom St Denis <tom.stdenis@amd.com> |
amdgpu/gfxv8: Simplification in gfx_v8_0_enable_gui_idle_interrupt() Simplified the function by folding the two paths into one. Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
|
#
544b8a74 |
|
01-Dec-2015 |
Tom St Denis <tom.stdenis@amd.com> |
amdgpu/gfxv8: Simplification of gfx_v8_0_create_bitmask() Simplification of the function gfx_v8_0_create_bitmask(). Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
|
#
90bea0ab |
|
01-Dec-2015 |
Tom St Denis <tom.stdenis@amd.com> |
amdgpu/gfxv8: Cleanup of gfx_v8_0_tiling_mode_table_init() (v2) Simplification and LOC reduction of function gfx_v8_0_tiling_mode_table_init() v2: remove spurious break bug: https://bugs.freedesktop.org/show_bug.cgi?id=93236 Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
|
#
8cdacf44 |
|
30-Nov-2015 |
Tom St Denis <tom.stdenis@amd.com> |
amdgpu/gfxv8: Add missing break to switch statement from states init code Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com>
|
#
ccba7691 |
|
24-Nov-2015 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: add EDC support for CZ (v3) This adds EDC support for CZ. EDC = Error Correction and Detection This code properly initializes the EDC hardware and resets the error counts. This is done in late_init since it requires the IB pool which is not initialized during hw_init. v2: fix the IB size as noted by Felix, fix shader pgm register programming v3: use the IB for the shaders as suggested by Christian Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
5f2e816b |
|
04-Nov-2015 |
Flora Cui <Flora.Cui@amd.com> |
drm/amdgpu: update Fiji's tiling mode table Change-Id: I925c15015390113f7e27746ec5751eaa6a92c2a7 Signed-off-by: Flora Cui <Flora.Cui@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
|
#
451f698b |
|
05-Nov-2015 |
Flora Cui <Flora.Cui@amd.com> |
drm/amdgpu: update fiji_mgcg_cgcg_init table Change-Id: If44b8057741c78208f1976f60f31b535c944d0bd Signed-off-by: Flora Cui <Flora.Cui@amd.com> Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com>
|
#
fa676048 |
|
30-Oct-2015 |
Flora Cui <Flora.Cui@amd.com> |
drm/amdgpu: update Fiji's mmPA_SC_RASTER_CONFIG value Change-Id: I6d138306a878450e5bf8a77a2f1aacc380a39fe5 Signed-off-by: Flora Cui <Flora.Cui@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
|
#
a7ca8ef9 |
|
01-Nov-2015 |
Flora Cui <Flora.Cui@amd.com> |
drm/amdgpu: update Fiji's Golden setting Change-Id: Ic3f3bfce4767cc05d04f6eb24e22a0f3e7ceacaa Signed-off-by: Flora Cui <Flora.Cui@amd.com> Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com>
|
#
b8b339ea |
|
27-Oct-2015 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: add some additional CZ revisions Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
|
#
e3c7656c |
|
08-Oct-2015 |
Samuel Li <samuel.li@amd.com> |
drm/amdgpu: add GFX support for Stoney (v2) Stoney is GFX 8.1. v2: update to latest golden settings Signed-off-by: Samuel Li <samuel.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
b7e4dad3 |
|
01-Sep-2015 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: remove old lockup detection infrastructure It didn't worked to well anyway. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com> Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
|
#
a3d5aaa8 |
|
15-Oct-2015 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu/gfx8: set TC_WB_ACTION_EN in RELEASE_MEM packet This is the recommended setting from the hw team for newer versions of the firmware. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
|
#
0bde3a95 |
|
03-Sep-2015 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: split gfx8 gpu init into sw and hw parts Calculate the driver state in sw_init and program the registers in hw init. Acked-by: Leo Liu <leo.liu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
5c3422b0 |
|
22-Sep-2015 |
monk.liu <monk.liu@amd.com> |
drm/amdgpu: sync ce and me with SWITCH_BUFFER(2) we used to adopt wait_reg_mem to let CE wait before DE finish page updating, but from Tonga+, CE doesn't support wait_reg_mem package so this logic no longer works. so here is another approach to do same thing: Insert two of SWITCH_BUFFER at both front and end of vm_flush can guarantee that CE not go further to process IB_const before vm_flush done. Insert two of SWITCH_BUFFER also works on CI, so remove legency method to sync CE and ME v2: Insert double SWITCH_BUFFER at front of vm flush as well. Signed-off-by: monk.liu <monk.liu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com>
|
#
72d7668b |
|
03-Sep-2015 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: export reservation_object from dmabuf to ttm (v2) Adds an extra argument to amdgpu_bo_create, which is only used in amdgpu_prime.c. Port of radeon commit 831b6966a60fe72d85ae3576056b4e4e0775b112. v2: fix up kfd. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
|
#
20a85ff8 |
|
05-Sep-2015 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: use write confirm for vm_flush() Make sure the CP waits for the write to be confirmed before invalidating. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
|
#
22c01cc4 |
|
03-Sep-2015 |
Anatoli Antonovitch <anatoli.antonovitch@amd.com> |
drm/amdgpu: execution barrier after fence v2 Insert wait for reg mem after EOP to fix potential issue with vm context switch v2: move wait to vm_flush() use equal instead of greater than. Signed-off-by: Anatoli Antonovitch <anatoli.antonovitch@amd.com> Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
|
#
35c7a952 |
|
03-Sep-2015 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: rename gmc_v8_0_init_compute_vmid It should be gfx_v8_0_init_compute_vmid since it's part of the gfx block. Acked-by: Leo Liu <leo.liu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
bddf8026 |
|
01-Sep-2015 |
Jammy Zhou <Jammy.Zhou@amd.com> |
drm/amdgpu: set MEC doorbell range for Fiji Signed-off-by: Jammy Zhou <Jammy.Zhou@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
|
#
edff0e28 |
|
31-Aug-2015 |
Jammy Zhou <Jammy.Zhou@amd.com> |
drm/amdgpu: add insert_nop ring func and default implementation The insert_nop function is added to amdgpu_ring_funcs structure as well as the default implementation Signed-off-by: Jammy Zhou <Jammy.Zhou@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
|
#
b203dd95 |
|
18-Aug-2015 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: fix zeroing all IB fields manually v2 The problem now is that we don't necessarily call amdgpu_ib_get() in some error paths and so work with uninitialized data. Better require that the memory is already zeroed. v2: better commit message Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com> (v1) Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
|
#
281b4223 |
|
11-Aug-2015 |
Chunming Zhou <david1.zhou@amd.com> |
drm/amdgpu: add reference for **fence fix fence is released when pass to **fence sometimes. add reference for it. Signed-off-by: Chunming Zhou <david1.zhou@amd.com> Reviewed-by: Christian K?nig <christian.koenig@amd.com>
|
#
1763552e |
|
02-Aug-2015 |
Chunming Zhou <david1.zhou@amd.com> |
drm/amdgpu: add kernel fence in ib_submit_kernel_helper every sbumission should be able to get a fence. Signed-off-by: Chunming Zhou <david1.zhou@amd.com> Reviewed-by: Christian K?nig <christian.koenig@amd.com> Reviewed-by: Jammy Zhou <jammy.zhou@amd.com>
|
#
ab3cb0ce |
|
02-Aug-2015 |
Chunming Zhou <david1.zhou@amd.com> |
drm/amdgpu: use kernel fence for gfx ib test Signed-off-by: Chunming Zhou <david1.zhou@amd.com> Reviewed-by: Christian K?nig <christian.koenig@amd.com> Reviewed-by: Jammy Zhou <jammy.zhou@amd.com>
|
#
42d13693 |
|
01-Jun-2015 |
Chunming Zhou <david1.zhou@amd.com> |
drm/amdgpu: Use gpu scheduler for gfx ring ib test Signed-off-by: Chunming Zhou <david1.zhou@amd.com> Reviewed-by: Christian K?nig <christian.koenig@amd.com>
|
#
af15a2d5 |
|
30-Jul-2015 |
David Zhang <david1.zhang@amd.com> |
drm/amdgpu: Add Fiji support to the GFX 8.0 IP module (v2) v2: agd5f: fix the rb setup. Signed-off-by: David Zhang <david1.zhang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com>
|
#
2f7d10b3 |
|
21-Jul-2015 |
Jammy Zhou <Jammy.Zhou@amd.com> |
drm/amdgpu: merge amdgpu_family.h into amd_shared.h (v2) Make the definitions common for all driver components v2: fix kfd Signed-off-by: Jammy Zhou <Jammy.Zhou@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
|
#
b8826b0c |
|
10-Aug-2015 |
Alex Deucher <alexander.deucher@amd.com> |
Revert "drm/amdgpu: Configure doorbell to maximum slots" This reverts commit 78ad5cdd21f0d614983fc397338944e797ec70b9. This commit breaks dpm and suspend/resume on CZ.
|
#
595fd013 |
|
03-Aug-2015 |
Jammy Zhou <Jammy.Zhou@amd.com> |
drm/amdgpu: set fw_version and feature_version for smu fw loading The fw_version and feature_verion should be set correctly when the firmwares are loaded by SMU on Tonga/Carrzio/Iceland Signed-off-by: Jammy Zhou <Jammy.Zhou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com>
|
#
351643d7 |
|
03-Aug-2015 |
Jammy Zhou <Jammy.Zhou@amd.com> |
drm/amdgpu: add feature version for RLC and MEC v2 Expose feature version to user space for RLC/MEC/MEC2 ucode as well v2: fix coding style Signed-off-by: Jammy Zhou <Jammy.Zhou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com>
|
#
a0e2f50b |
|
08-Jul-2015 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: fix rb setting for CZ Always set num_rbs to 2 for CZ. The 1 RB parts are often harvest configs. The will get sorted out in mesa when we program PA_SC_RASTER_CONFIG[_1]. Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
93323131 |
|
15-Jul-2015 |
monk.liu <monk.liu@amd.com> |
drm/amdgpu: different emit_ib for gfx and compute compute ring didn't use const engine byfar, so ignore CE things in compute routine Signed-off-by: monk.liu <monk.liu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com>
|
#
4f2d3ad6 |
|
10-Jul-2015 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: remove bogus check in gfx8 rb setup Always respect the harvest configuration as is. Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
845253e7 |
|
23-Jun-2015 |
Sonny Jiang <sonny.jiang@amd.com> |
drm/amdgpu: reset wptr at cp compute resume (v2) This patch is to resolve compute hang at resume time. v2: (agd5f) squash in second fix Signed-off-by: Sonny Jiang <sonny.jiang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com>
|
#
78ad5cdd |
|
12-Jun-2015 |
Ben Goz <ben.goz@amd.com> |
drm/amdgpu: Configure doorbell to maximum slots Signed-off-by: Ben Goz <ben.goz@amd.com> Acked-by: Oded Gabbay <oded.gabbay@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
cd06bf68 |
|
24-Jun-2015 |
Ben Goz <ben.goz@amd.com> |
drm/amdgpu: Initialize compute sdma and memory from kgd v2: add missing MTYPE_NONCACHED enum Signed-off-by: Ben Goz <ben.goz@amd.com> Acked-by: Oded Gabbay <oded.gabbay@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
6a00a09e |
|
09-Jun-2015 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: update to latest gfx8 golden register settings Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
147dbfbc |
|
10-Jun-2015 |
David Zhang <david1.zhang@amd.com> |
drm/amdgpu: remove the VI hardware semaphore in ring sync Signed-off-by: David Zhang <david1.zhang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com>
|
#
bd5c97bc |
|
05-Jun-2015 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: set the gfx config properly for all CZ variants (v2) Need to adjust the number of CUs and RBs. v2: get proper values Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Samuel Li <samuel.li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
890ee23f |
|
01-Jun-2015 |
Chunming Zhou <david1.zhou@amd.com> |
drm/amdgpu: disable user fence interrupt (v2) amdgpu submits both kernel and user fences, but just need one interrupt, disable user fence interrupt and don't effect user fence. v2: fix merge error Signed-off-by: Chunming Zhou <david1.zhou@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
|
#
02558a00 |
|
03-Jun-2015 |
Ken Wang <Qingqing.Wang@amd.com> |
drm/amdgpu: add me/ce/pfp_feature_version interface query Provide this information to usermode drivers. We were previously missing this info. Signed-off-by: Ken Wang <Qingqing.Wang@amd.com> Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com>
|
#
a101a899 |
|
03-Jun-2015 |
Ken Wang <Qingqing.Wang@amd.com> |
drm/amdgpu add ce_ram_size for interface query Add a query for the CE ram size. User mode drivers will want to use this to determine how much size of the cache on the CE. Signed-off-by: Ken Wang <Qingqing.Wang@amd.com> Reviewd-by: Jammy Zhou <Jammy.Zhou@amd.com>
|
#
35074d2d |
|
03-Jun-2015 |
monk.liu <monk.liu@amd.com> |
drm/amdgpu: add hdp flush for gfx8 compute ring We had forgotten to register the callback. Signed-off-by: monk.liu <monk.liu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: jammy zhou <jammy.zhou@amd.com>
|
#
b9a7faae |
|
27-May-2015 |
monk.liu <monk.liu@amd.com> |
drm/amdgpu: remove all sh mem register modification in vm flush Leave that at the values set during init. No need to update them repeatedly. Signed-off-by: monk.liu <monk.liu@amd.com> Signed-off-by: David Zhang <david1.zhang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Jammy Zhou <jammy.zhou@amd.com>
|
#
5fc3aeeb |
|
22-May-2015 |
yanyang1 <young.yang@amd.com> |
drm/amdgpu: rename amdgpu_ip_funcs to amd_ip_funcs (v2) The structure is renamed and moved to amd_shared.h to make the component independent. This makes it easier to add new components in the future. v2: fix include path Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com> Signed-off-by: yanyang1 <young.yang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
#
c65444fe |
|
13-May-2015 |
Jammy Zhou <Jammy.Zhou@amd.com> |
drm/amdgpu: switch to amdgpu folder for firmware files v2 v2: keep using radeon folder for CIK Signed-off-by: Jammy Zhou <Jammy.Zhou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com>
|
#
3cb485f3 |
|
11-May-2015 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: fix context switch Properly protect the state and also handle submission failures. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com> Reviewed-by: Monk Liu <monk.liu@amd.com>
|
#
d2edb07b |
|
11-May-2015 |
Christian König <christian.koenig@amd.com> |
drm/amdgpu: cleanup HDP flush handling Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com> Reviewed-by: Monk Liu <monk.liu@amd.com>
|
#
aa2bdb24 |
|
11-May-2015 |
Jammy Zhou <Jammy.Zhou@amd.com> |
drm/amdgpu: add CE preamble flag v3 The CE preamble IB can be dropped for the same context v2: use the flags directly v3: remove 'CE' for potential preamble usage by other rings Signed-off-by: Jammy Zhou <Jammy.Zhou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com>
|
#
de807f81 |
|
11-May-2015 |
Jammy Zhou <Jammy.Zhou@amd.com> |
drm/amdgpu: add flags for amdgpu_ib structure Signed-off-by: Jammy Zhou <Jammy.Zhou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com>
|
#
74a5d165 |
|
08-May-2015 |
Jack Xiao <Jack.Xiao@amd.com> |
drm/amdgpu: allow unaligned memory access (v2) Set up the CP and SDMA for proper unaligned memory access. Required for OpenCL 2.x v2: udpate commit message Signed-off-by: Jack Xiao <Jack.Xiao@amd.com> Reviewed-by: Monk Liu <monk.liu@amd.com> Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com>
|
#
aaa36a97 |
|
20-Apr-2015 |
Alex Deucher <alexander.deucher@amd.com> |
drm/amdgpu: Add initial VI support This adds initial support for VI asics. This includes Iceland, Tonga, and Carrizo. Our inital focus as been Carrizo, so there are still gaps in support for Tonga and Iceland, notably power management. Acked-by: Christian König <christian.koenig@amd.com> Acked-by: Jammy Zhou <Jammy.Zhou@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|