This variable will be used to determine whether packet
manager is initialized or not, in a future patch.
Signed-off-by: Oak Zeng
Acked-by: Christian Konig
Reviewed-by: Felix Kuehling
---
drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c | 1 +
1 file changed, 1 insertion(+)
diff --git a
Oak Zeng (5):
drm/amdgpu: Fix a printing message
drm/amdgpu: Change a few function names
drm/amdkfd: Renaming dqm->packets to dqm->packet_mgr
drm/amdkfd: Set priv_queue to NULL after it is freed
drm/amdkfd: Fix a concurrency issue during kfd recovery
drivers/gpu/drm/amd/
ck
hw_init. Fix the printing message
Signed-off-by: Oak Zeng
Reviewed-by: Christian Konig
---
drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c | 2 +-
drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c | 2 +-
drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c | 2 +-
drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c | 2 +-
4 files changed, 4
Function name "psp_np_fw_load" is not proper as people don't
know _np_fw_ means "non psp firmware". Change the function
name to psp_load_non_psp_fw for better understanding. Same
thing for function psp_execute_np_fw_load.
Signed-off-by: Oak Zeng
Reviewed-by: Alex Deuche
patch moves pm_init/uninit inside the dpm lock and check
packet manager is initialized before using packet manager
function.
Signed-off-by: Oak Zeng
Acked-by: Christian Konig
---
drivers/gpu/drm/amd/amdkfd/kfd_device.c | 8 +---
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_mana
Renaming packets to packet_mgr to reflect the real meaning
of this variable.
Signed-off-by: Oak Zeng
Acked-by: Christian Konig
---
drivers/gpu/drm/amd/amdkfd/kfd_device.c| 2 +-
.../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 26 +++---
.../gpu/drm/amd/amdkfd
ck
hw_init. Fix the printing message
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c | 2 +-
drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c | 2 +-
drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c | 2 +-
drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c | 2 +-
4 files changed, 4 insertions(+), 4 deletions(-)
This variable will be used to determine whether packet
manager is initialized or not, in a future patch.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
b/drivers/gpu
Oak Zeng (5):
drm/amdgpu: Fix a printing message
drm/amdgpu: Change a few function names
drm/amdkfd: Renaming dqm->packets to dqm->dpm
drm/amdkfd: Set priv_queue to NULL after it is freed
drm/amdkfd: Fix a concurrency issue during kfd recovery
drivers/gpu/drm/amd/amdgpu/amdgpu
Renaming packets to dpm (device packet manager) to
reflect the real meaning of this variable.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdkfd/kfd_device.c| 2 +-
.../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 26 +++---
.../gpu/drm/amd/amdkfd
Function name "psp_np_fw_load" is not proper as people don't
know _np_fw_ means "non psp firmware". Change the function
name to psp_load_non_psp_fw for better understanding. Same
thing for function psp_execute_np_fw_load.
Signed-off-by: Oak Zeng
Reviewed-by: Alex Deuc
patch moves pm_init/uninit inside the dpm lock and check
packet manager is initialized before using packet manager
function.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdkfd/kfd_device.c | 8 +---
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 10 --
dr
This variable will be used to determine whether packet
manager is initialized or not, in a future patch.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
b/drivers/gpu
Function name "psp_np_fw_load" is not proper as people don't
know _np_fw_ means "non psp firmware". Change the function
name to psp_load_non_psp_fw for better understanding. Same
thing for function psp_execute_np_fw_load.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd
Renaming packets to dpm (device packet manager) to
reflect the real meaning of this variable.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdkfd/kfd_device.c| 2 +-
.../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 26 +++---
.../gpu/drm/amd/amdkfd
patch moves pm_init/uninit inside the dpm lock and check
packet manager is initialized before using packet manager
function.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdkfd/kfd_device.c | 8 +---
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 10 --
dr
ck
hw_init. Fix the printing message
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c | 2 +-
drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c | 2 +-
drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c | 2 +-
drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c | 2 +-
4 files changed, 4 insertions(+), 4 deletions(-)
Oak Zeng (5):
drm/amdgpu: Fix a printing message
drm/amdgpu: Change a few function names
drm/amdkfd: Renaming dqm->packets to dqm->dpm
drm/amdkfd: Set priv_queue to NULL after it is freed
drm/amdkfd: Fix a concurrency issue during kfd recovery
drivers/gpu/drm/amd/amdgpu/amdgpu
ck
hw_init. Fix the printing message
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c | 2 +-
drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c | 2 +-
drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c | 2 +-
drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c | 2 +-
4 files changed, 4 insertions(+), 4 deletions(-)
234508] __x64_sys_write+0x1a/0x20
[12808.234511] do_syscall_64+0x57/0x190
[12808.234514] entry_SYSCALL_64_after_hwframe+0x44/0xa9
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdkfd/kfd_device.c | 5 +
1 file changed, 5 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
b/d
Function name "psp_np_fw_load" is not proper as people don't
know _np_fw_ means "non psp firmware". Change the function
name to psp_load_non_psp_fw for better understanding. Same
thing for function psp_execute_np_fw_load.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd
Oak Zeng (3):
drm/amdkfd: Disallow debugfs to hang hws when GPU is resetting
drm/amdgpu: Fix a printing message
drm/amdgpu: Change a few function names
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 16
drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c | 2 +-
drivers/gpu/drm/amd/amdgpu
If GPU is during a resetting cycle, writing to GPU can cause
unpredictable protection fault. Disallow using kfd debugfs
hang_hws to hang hws if GPU is resetting.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdkfd/kfd_device.c | 5 +
1 file changed, 5 insertions(+)
diff --git a/drivers
This patch moves the ttm caching flags setting to function
amdgpu_vram_mgr_new - this function is called during the
first step of a buffer object create (eg, DRM_AMDGPU_GEM_CREATE)
so the later both CPU and GPU mapping function calls will
pick up this flag for CPU/GPU page table set up.
Signed-off-by
In some configuration, there is CPU-only (no memory) numa node. Don't
create crat memory sub-table for such node.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdkfd/kfd_crat.c | 21 +++--
1 file changed, 15 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/dr
There can be more than one CPU nodes. Patch memory width
and clock info for all CPU nodes, instead of only the first
one.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdkfd/kfd_topology.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd
Previously we used cpu_cores_count==0 to determine whether a node
is a GPU node. This is not correct any more since we introduced
memory only numa node. For memory only numa node, cpu_cores_count
is also 0 but it is not a GPU node.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdkfd
Previously kfd driver assumes all CPU numa nodes are associated
with system memory and there is no memory only numa node. This
is not true anymore for ALDEBARAN A+A set up. This patch creates
memory only node in kfd sysfs.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdkfd/kfd_crat.c | 73
In some configuration, there is CPU-only (no memory) numa node. Don't
create crat memory sub-table for such node.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdkfd/kfd_crat.c | 17 +++--
1 file changed, 11 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/amd/a
If RAS is disabled through amdgpu_ras_enable kernel parameter,
we should quit the RAS initialization eariler to avoid initialization
of some RAS data structure such as sysfs etc.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 2 +-
1 file changed, 1 insertion(+), 1
This reverts commit 34a33d4683cba7ba63c894132efb1998c0217631.
34a33d4683cba7ba63c894132efb1998c0217631 was a driver workaround
when PSP firmware was not ready. Now the PSP fw is ready so we
revert this driver workaround.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h | 9
Use amdgpu_gmc_vram_pa and amdgpu_gmc_vram_cpu_pa
to simplify codes. No logic change.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c | 4 +---
drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c | 3 +--
drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c | 3 +--
drivers/gpu/drm/amd/amdgpu
Add one function to calculate BO's GPU physical address.
And another function to calculate BO's CPU physical address.
v2: Use functions vs macros (Christian)
Use more proper function names (Christian)
Signed-off-by: Oak Zeng
Suggested-by: Lijo Lazar
---
drivers/gpu/drm/
This reverts commit 34a33d4683cba7ba63c894132efb1998c0217631.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h | 9 -
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 10 --
drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c | 21 ++---
drivers/gpu/drm/amd
This new interface passes both virtual and physical address
to PSP. It is backword compatible with old interface.
v2: use a function to simply tmr physical address calc (Lijo)
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 12 +---
drivers/gpu/drm/amd/amdgpu
This reverts commit 34a33d4683cba7ba63c894132efb1998c0217631.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h | 9 -
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 10 --
drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c | 21 ++---
drivers/gpu/drm/amd
Use amdgpu_gmc_gpu_pa and amdgpu_gmc_cpu_pa
to simplify codes. No logic change.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c | 4 +---
drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c | 3 +--
drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c | 3 +--
drivers/gpu/drm/amd/amdgpu
This new interface passes both virtual and physical address
to PSP. It is backword compatible with old interface.
v2: use a macro to simply tmr physical address calc (Lijo)
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 12 +---
drivers/gpu/drm/amd/amdgpu
Add one macro to calculate BO's GPU physical address.
And another one to calculate BO's CPU physical address.
Signed-off-by: Oak Zeng
Suggested-by: Lijo Lazar
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/
This new interface passes both virtual and physical address
to PSP. It is backword compatible with old interface.
v2: use a macro to simply tmr physical address calc (Lijo)
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 12 +---
drivers/gpu/drm/amd/amdgpu
This reverts commit 34a33d4683cba7ba63c894132efb1998c0217631.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h | 9 -
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 10 --
drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c | 21 ++---
drivers/gpu/drm/amd
Add one macro to calculate BO's GPU physical address.
And another one to calculate BO's CPU physical address.
Signed-off-by: Oak Zeng
Suggested-by: Lijo Lazar
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/
Use amdgpu_gmc_gpu_pa and amdgpu_gmc_cpu_pa
to simplify codes. No logic change.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 3 +--
drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c | 4 +---
drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 4 +---
drivers/gpu
This reverts commit 34a33d4683cba7ba63c894132efb1998c0217631.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h | 9 -
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 10 --
drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c | 21 ++---
drivers/gpu/drm/amd
This new interface passes both virtual and physical address
to PSP. It is backword compatible with old interface.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 13 ++---
drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h | 11 ++-
2 files changed, 20 insertions
1. make function mmhub_v1_7_setup_vm_pt_regs static
2. indent a if statement
Signed-off-by: Oak Zeng
Reported-by: kernel test robot
Reported-by: Dan Carpenter
---
drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c | 4 ++--
drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c | 2 +-
2 files changed, 3 insertions
ioremap_cache is not supported on some architecture
such as s390. Put the codes into a #ifdef to fix
some compile error reported by test robot.
Signed-off-by: Oak Zeng
Reported-by: Kernel test robot
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion
ff-by: Oak Zeng
Reviewed-by: Christian Konig
---
drivers/gpu/drm/ttm/ttm_bo_util.c | 14 ++
1 file changed, 14 insertions(+)
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c
b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 031e581..7429464 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/dr
ff-by: Oak Zeng
Reviewed-by: Christian Konig
---
drivers/gpu/drm/ttm/ttm_bo_util.c | 14 ++
1 file changed, 14 insertions(+)
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c
b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 031e581..7c848e2 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/dr
ff-by: Oak Zeng
Reviewed-by: Christian Konig
---
drivers/gpu/drm/ttm/ttm_bo_util.c | 8
1 file changed, 8 insertions(+)
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c
b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 031e581..8c65a13 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gp
applications only 1GB
of system memory. In many cases, this leads to OOM killer.
This patch changed the KFD system memory accounting scheme.
15/16 of free system memory when kfd driver load. This deduct
the system memory that OS already use.
Signed-off-by: Oak Zeng
Suggested-by: Philip Yang
gfxhub functions are now called from function pointers,
instead of from asic-specific functions.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h| 4 ++
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c | 3 +-
.../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c
Add more accurate description of the pe parameter of function
amdgpu_vm_sdma_udpate and amdgpu_vm_cpu_update
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c | 2 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c | 4 ++--
2 files changed, 3 insertions(+), 3 deletions
Add comments to refect what function does
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 7 ++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 63e5414..8b70445
: I65ba660c69b74c7e779190c4f92e9d7138f7c7d4
Signed-off-by: Oak Zeng
---
.../gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c| 21 ++
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c | 4 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h | 3 ++
drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h | 13 ++
drivers
UTCL2 client ID is useful information to get which
UTCL2 client caused the gpuvm fault. Print it out
for debug purpose
Change-Id: I733d0127b0ee53aa788f194cefa53cbb55b49c11
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c | 3 +++
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 3
Config the translation retry behavior according to noretry
kernel parameter
Change-Id: I5b91ea77715137cf8cb84e258ccdfbb19c7a4ed1
Signed-off-by: Oak Zeng
Suggested-by: Jay Cornwall
---
drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git
Config the translation retry behavior according to noretry
kernel parameter
Change-Id: I5b91ea77715137cf8cb84e258ccdfbb19c7a4ed1
Signed-off-by: Oak Zeng
Suggested-by: Jay Cornwall
---
drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 4 +++-
drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c | 5 +++--
2 files
), not *2.
Change-Id: I62023bb91da33ca5532b22b263771b587b796d59
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 7 +--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
v2: Use enum definition instead of hardcoded value
v3: Remove unused enum definition
Change-Id: Ib72058337f0aa53adfc6c6aae5341a7cd665111a
Signed-off-by: Oak Zeng
Suggested-by: Felix Kuehling
Suggested-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 14
Change-Id: I84475efcfb482c474fccb133010abb5df5f4
Signed-off-by: Oak Zeng
Suggested-by: Felix Kuehling
Suggested-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 27 ---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 +-
drivers/gpu/drm/amd/amdgpu
v2: Use enum definition instead of hardcoded value
Change-Id: Ib72058337f0aa53adfc6c6aae5341a7cd665111a
Signed-off-by: Oak Zeng
Suggested-by: Felix Kuehling
Suggested-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/soc15.c | 1 +
drivers/gpu/drm/amd/amdgpu/soc15.h | 1
This is a preparation work to make reserved doorbell index per device,
instead of using a global macro definition. By doing this, we can easily
change doorbell layout for future ASICs while not affecting ASICs in
production.
Change-Id: If08e2bc9d0749748ed4083ba4eb32a4698763085
Signed-off-by: Oak
v2: Use enum definition instead of hardcoded value
Change-Id: I04d22fb717ac50483c0835f160a2e860e344f358
Signed-off-by: Oak Zeng
Suggested-by: Felix Kuehling
Suggested-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 50
drivers/gpu/drm/amd
v2: Use enum definition instead of hardcoded number
Change-Id: Id64eb98f5b1c24b51eb2fd5a083086fc3515813d
Signed-off-by: Oak Zeng
Suggested-by: Felix Kuehling
Suggested-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/cik.c | 1 +
drivers/gpu/drm/amd/amdgpu/cik.h | 1 +
drivers/gpu/drm/amd
Move doorbell structures, enum definitions and helper functions
from amdgpu.h to amdgpu_doorbell.h. No functional change
Change-Id: I09f7b84869b6d3c688b7a2506ff78d62b3de23f5
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 227 +---
drivers/gpu/drm
Also call functioin amdgpu_device_doorbell_init after
amdgpu_device_ip_early_init because the former depends
on the later to set up asic-specific init_doorbell_index
function
Change-Id: I2f004bbbe2565035460686f4fc16e86b77a2a9b5
Signed-off-by: Oak Zeng
Suggested-by: Felix Kuehling
Suggested-by
Change-Id: I7e8a9c9dfd4f3bd0902679a1771c1a043ece2674
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index b7ee4ef..719da32 100644
--- a/drivers/gpu
Move doorbell structures, enum definitions and helper functions
from amdgpu.h to amdgpu_doorbell.h. No functional change
Change-Id: I09f7b84869b6d3c688b7a2506ff78d62b3de23f5
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 227 +---
drivers/gpu/drm
v2: Use enum definition instead of hardcoded value
Change-Id: I04d22fb717ac50483c0835f160a2e860e344f358
Signed-off-by: Oak Zeng
Suggested-by: Felix Kuehling
Suggested-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 50
drivers/gpu/drm/amd
Change-Id: I84475efcfb482c474fccb133010abb5df5f4
Signed-off-by: Oak Zeng
Suggested-by: Felix Kuehling
Suggested-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 27 ---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 +-
drivers/gpu/drm/amd/amdgpu
Change-Id: I2f004bbbe2565035460686f4fc16e86b77a2a9b5
Signed-off-by: Oak Zeng
Suggested-by: Felix Kuehling
Suggested-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 7 +++
1 file changed, 7 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
b/drivers
v2: Use enum definition instead of hardcoded value
Change-Id: Ib72058337f0aa53adfc6c6aae5341a7cd665111a
Signed-off-by: Oak Zeng
Suggested-by: Felix Kuehling
Suggested-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/soc15.h | 1 +
drivers/gpu/drm/amd/amdgpu/vega10_reg_init.c | 28
v2: Use enum definition instead of hardcoded number
Change-Id: Id64eb98f5b1c24b51eb2fd5a083086fc3515813d
Signed-off-by: Oak Zeng
Suggested-by: Felix Kuehling
Suggested-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/Makefile | 2 +-
drivers/gpu/drm/amd/amdgpu/vi.h | 2
This is a preparation work to make reserved doorbell index per device,
instead of using a global macro definition. By doing this, we can easily
change doorbell layout for future ASICs while not affecting ASICs in
production.
Change-Id: If08e2bc9d0749748ed4083ba4eb32a4698763085
Signed-off-by: Oak
v2: Changed file name for consistency
Change-Id: Ib2c570224321bb7002d2ed01f43ac70203e86f88
Signed-off-by: Oak Zeng
Suggested-by: Felix Kuehling
Suggested-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/Makefile | 2 +-
drivers/gpu/drm/amd/amdgpu/soc15.h | 1 +
drivers/gpu
Change-Id: Id64eb98f5b1c24b51eb2fd5a083086fc3515813d
Signed-off-by: Oak Zeng
Suggested-by: Felix Kuehling
Suggested-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/Makefile| 3 +-
drivers/gpu/drm/amd/amdgpu/vi.h| 2 +-
.../gpu/drm/amd/amdgpu
Change-Id: I04d22fb717ac50483c0835f160a2e860e344f358
Signed-off-by: Oak Zeng
Suggested-by: Felix Kuehling
Suggested-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/Makefile| 4 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 +-
drivers/gpu/drm/amd/amdgpu/soc15.h
Also deleted doorbell index macro definition
Change-Id: I84475efcfb482c474fccb133010abb5df5f4
Signed-off-by: Oak Zeng
Suggested-by: Felix Kuehling
Suggested-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h| 106 -
drivers/gpu/drm/amd/amdgpu
Change-Id: Ib72058337f0aa53adfc6c6aae5341a7cd665111a
Signed-off-by: Oak Zeng
Suggested-by: Felix Kuehling
Suggested-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/Makefile| 2 +-
drivers/gpu/drm/amd/amdgpu/soc15.h | 1 +
.../drm/amd/amdgpu
Change-Id: I2f004bbbe2565035460686f4fc16e86b77a2a9b5
Signed-off-by: Oak Zeng
Suggested-by: Felix Kuehling
Suggested-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 7 +++
1 file changed, 7 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
b/drivers
Change-Id: Ib2c570224321bb7002d2ed01f43ac70203e86f88
Signed-off-by: Oak Zeng
Suggested-by: Felix Kuehling
Suggested-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/Makefile| 2 +-
drivers/gpu/drm/amd/amdgpu/soc15.h | 1 +
.../drm/amd/amdgpu
This is a preparation work to make reserved doorbell index per device,
instead of using a global macro definition. By doing this, we can easily
change doorbell layout for future ASICs while not affecting ASICs in
production.
Change-Id: If08e2bc9d0749748ed4083ba4eb32a4698763085
Signed-off-by: Oak
From: Oak Zeng
Change-Id: I32e0304cdf6ceeed12ea8d0af62f44e1ab20bffb
Signed-off-by: Oak Zeng
Reviewd-by: Felix Kuehling
---
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 26 +--
.../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 30 +++---
2 files
From: Oak Zeng
Change-Id: I47ec79eceac810f7031eaf88d267fc8370501c27
Signed-off-by: Oak Zeng
Reviewd-by: Felix Kuehling
---
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
b
From: Oak Zeng
Maximumly support 64 sdma queues
Change-Id: Ia34b81fe606f730cb0cddb5dfc833cfe8abcf776
Signed-off-by: Oak Zeng
Reviewed-by: Felix Kuehling
Reviewed-by: Alex Deucher
---
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 10 +-
drivers/gpu/drm/amd/amdkfd
From: Oak Zeng
The new types are used to allocate SDMA queue on specific
SDMA engine
Change-Id: Ica4cd7013eb86103a92cec2f74d96ac037b5ecbd
Signed-off-by: Oak Zeng
Reviewd-by: Felix Kuehling
---
include/uapi/linux/kfd_ioctl.h | 10 +++---
1 file changed, 7 insertions(+), 3 deletions
Expose get_reg_offset function of sdma_v4_0 for kfd to use
Change-Id: Ib687b390d6d3f8c8a35651e064e35aacf6722f98
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 7 +++
drivers/gpu/drm/amd/include/amd_shared.h | 3 +++
2 files changed, 10 insertions(+)
diff --git a
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c | 2 ++
drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h | 1 +
2 files changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index 9a212aa..6d11e17 100644
--- a
In stead of share one fault hash table per device, make it
per vm. This can avoid inter-process lock issue when fault
hash table is full.
Change-Id: I5d1281b7c41eddc8e26113e010516557588d3708
Signed-off-by: Oak Zeng
Suggested-by: Christian Konig
Suggested-by: Felix Kuehling
---
drivers/gpu/drm
With the change of making fault hash per vm, this is not needed
anymore.
Change-Id: I9427ff1786deaf1f5b7d121a6f7f75f00acfc9b7
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 5 -
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 3 ---
drivers/gpu/drm/amd/amdgpu/vega10_ih.c | 9
For compute vm acquired from amdgpu, vm.pasid is managed
by kfd. Decouple pasid from such vm on process destroy
to avoid duplicate pasid release.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h| 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c | 1
To make a amdgpu vm to a compute vm, the old pasid will be freed and
replaced with a pasid managed by kfd. Kfd can't reuse original pasid
allocated by amdgpu because kfd uses different pasid policy with amdgpu.
For example, all graphic devices share one same pasid in a process.
Signed-off-by
To make a amdgpu vm to a compute vm, the old pasid will be freed and
replaced with a pasid managed by kfd. Kfd can't reuse original pasid
allocated by amdgpu because kfd uses different pasid policy with amdgpu.
For example, all graphic devices share one same pasid in a process.
Signed-off-by
For compute vm acquired from amdgpu, vm.pasid is managed
by kfd. Decouple pasid from such vm on process destroy
to avoid duplicate pasid release.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h| 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c | 1
To make a amdgpu vm to a compute vm, the old pasid will be freed and
replaced with a pasid managed by kfd. Kfd can't reuse original pasid
allocated by amdgpu because kfd uses different pasid policy with amdgpu.
For example, all graphic devices share one same pasid in a process.
Signed-off-by
For compute vm acquired from amdgpu, vm.pasid is managed
by kfd. Decouple pasid from such vm on process destroy
to avoid duplicate pasid release.
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h| 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c | 1
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h | 4 ++--
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 8
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 20 +---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 2 +-
drivers
This is preparation for sharing client ID definitions
between amdgpu and amdkfd
Change-Id: Ie0b7b14c9c2366fd896745a51b74a9ba97ee3224
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h | 43 +
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 8
This is preparation for sharing client ID definitions
between amdgpu and amdkfd
Change-Id: Ie0b7b14c9c2366fd896745a51b74a9ba97ee3224
Signed-off-by: Oak Zeng
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h | 44 +--
drivers/gpu/drm/amd/include/soc15_ih_clientid.h | 72
1 - 100 of 102 matches
Mail list logo
