NV10 mask used for gfx12. Fix it.
Fixes: b8c76c59987a ("drm/amdgpu: rework how PTE flags are generated
v3")
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu
for cik and vi
family. So this commit only focuses on these two. A separate commit will
address other asics.
Signed-off-by: Harish Kasiviswanathan
---
.../drm/amd/amdkfd/kfd_device_queue_manager.c | 39 +-
.../amd/amdkfd/kfd_device_queue_manager_cik.c | 69 --
.../amd
for cik and vi
family. So this commit only focuses on these two. A separate commit will
address other asics.
Signed-off-by: Harish Kasiviswanathan
---
.../drm/amd/amdkfd/kfd_device_queue_manager.c | 39 +-
.../amd/amdkfd/kfd_device_queue_manager_cik.c | 69 --
.../amd
gt; ("drm/amdkfd: Add pm_config_dequeue_wait_counts API")
Signed-off-by: Harish Kasiviswanathan
---
.../gpu/drm/amd/amdkfd/kfd_packet_manager.c | 16 ++
.../drm/amd/amdkfd/kfd_packet_manager_v9.c| 30 +++
2 files changed, 27 insertions(+), 19 deletions(-)
diff --g
I")
Signed-off-by: Harish Kasiviswanathan
---
.../gpu/drm/amd/amdkfd/kfd_packet_manager.c | 14
.../drm/amd/amdkfd/kfd_packet_manager_v9.c| 36 +++
2 files changed, 29 insertions(+), 21 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
b
.config_dequeue_wait_counts returns a nop case. Modify return parameter
to reflect that since the caller also needs to ignore this condition.
Fixes: <98a5af8103f> ("drm/amdkfd: Add pm_config_dequeue_wait_counts API")
Signed-off-by: Harish Kasiviswanathan
---
drivers/gp
Expose unique_id for gfx12
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/pm/amdgpu_pm.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index 1d04f1b79ded..2179344e78d9 100644
--- a/drivers/gpu/drm
Add support for more per-process flags starting with option to configure
MFMA precision for gfx 9.5
v2: Change flag name to KFD_PROC_FLAG_MFMA_HIGH_PRECISION
Remove unused else condition
v3: Bump the KFD API version
Signed-off-by: Harish Kasiviswanathan
Reviewed-by: Felix Kuehling
Define set_cache_memory_policy() for these asics and move all static
changes from update_qpd() which is called each time a queue is created
to set_cache_memory_policy() which is called once during process
initialization
Signed-off-by: Harish Kasiviswanathan
---
.../amd/amdkfd
-by: Harish Kasiviswanathan
Reviewed-by: Felix Kuehling
---
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 3 ++-
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 6 --
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h | 6 --
.../gpu/drm/amd/amdkfd
Define set_cache_memory_policy() for these asics and move all static
changes from update_qpd() which is called each time a queue is created
to set_cache_memory_policy() which is called once during process
initialization
Signed-off-by: Harish Kasiviswanathan
---
.../amd/amdkfd
Dequeue retry timeout controls the interval between checks for unmet
conditions. On MI series, reduce this from 0x40 to 0x1 (~ 1 uS). The
cost of additional bandwidth consumed by CP when polling memory
shouldn't be substantial.
Signed-off-by: Harish Kasiviswanathan
Reviewed-by: : Jonatha
flexibility to update different dequeue wait times.
Signed-off-by: Harish Kasiviswanathan
---
.../drm/amd/amdkfd/kfd_device_queue_manager.c | 45 ++
.../drm/amd/amdkfd/kfd_device_queue_manager.h | 11 +++-
.../gpu/drm/amd/amdkfd/kfd_packet_manager.c | 26 +++-
.../drm/amd/amdkfd
flexibility to update different dequeue wait times.
Signed-off-by: Harish Kasiviswanathan
---
.../drm/amd/amdkfd/kfd_device_queue_manager.c | 45 +++
.../drm/amd/amdkfd/kfd_device_queue_manager.h | 11 +++-
.../gpu/drm/amd/amdkfd/kfd_packet_manager.c | 26 -
.../drm/amd
Dequeue retry timeout controls the interval between checks for unmet
conditions. On MI series, reduce this from 0x40 to 0x1 (~ 1 uS). The
cost of additional bandwidth consumed by CP when polling memory
shouldn't be substantial.
Signed-off-by: Harish Kasiviswanathan
---
.../drm/amd/a
On 2025-02-18 15:27, Kim, Jonathan wrote:
> [Public]
>
>> -Original Message-
>> From: amd-gfx On Behalf Of Harish
>> Kasiviswanathan
>> Sent: Wednesday, February 12, 2025 5:04 PM
>> To: amd-gfx@lists.freedesktop.org
>> Cc: Kasiviswanathan,
Currently, grace period (SCH_WAVE) is set only for gfx943 APU. This
could change as other wait times also needs to be set. Move ASIC
specific settings to ASIC specific function.
Signed-off-by: Harish Kasiviswanathan
---
.../drm/amd/amdkfd/kfd_device_queue_manager.c | 28
change intended.
Signed-off-by: Harish Kasiviswanathan
---
.../drm/amd/amdkfd/kfd_device_queue_manager.c | 46 +--
.../drm/amd/amdkfd/kfd_device_queue_manager.h | 2 +-
.../gpu/drm/amd/amdkfd/kfd_packet_manager.c | 18 ++--
.../drm/amd/amdkfd/kfd_packet_manager_v9.c
Set more optimized queue retry timeout for gfx9 family starting with
arcturus.
Signed-off-by: Harish Kasiviswanathan
---
.../drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c| 7 ++
.../drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.h| 1 +
.../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c | 8
build_grace_period_packet_info is asic helper function that fetches the
correct format. It is the responsibility of the caller to validate the
value.
Signed-off-by: Harish Kasiviswanathan
---
.../drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c| 18 +--
.../gpu/drm/amd/amdgpu
SDMA writes has to probe invalidate RW lines. Set snoop bit in mmhub for
this to happen.
v2: Missed a few mmhub_v9_4. Added now.
v3: Calculate hub offset once since it doesn't change inside the loop
Modified function names based on review comments.
Signed-off-by: Harish Kasiviswan
SDMA writes has to probe invalidate RW lines. Set snoop bit in mmhub for
this to happen.
v2: Missed a few mmhub_v9_4. Added now.
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c | 25 ++
drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c | 27
SDMA writes has to probe invalidate RW lines. Set snoop bit in mmhub for
this to happen.
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c | 25 ++
drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c | 27 +++
drivers/gpu/drm/amd/amdgpu/mmhub_v9_4
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdkfd/kfd_crat.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
index 3ca95f54601e..e0faec4682f3 100644
--- a/drivers/gpu/drm/amd
This information is not available in ip discovery table.
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdkfd/kfd_crat.c | 22 --
1 file changed, 20 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
b/drivers/gpu/drm/amd
Reviewed-by: Harish Kasiviswanathan
On 2024-10-22 13:36, Jonathan Kim wrote:
> Flag KFD support for per-queue reset on GFX9 devices.
>
> Signed-off-by: Jonathan Kim
> ---
> drivers/gpu/drm/amd/amdkfd/kfd_topology.c | 2 ++
> include/uapi/linux/kfd_sysfs.h
Reviewed-by: Harish Kasiviswanathan
On 2024-10-16 15:08, Kim, Jonathan wrote:
> [Public]
>
> Messed up James' email in Tested-by tag. CC'ing James.
>
>> -Original Message-
>> From: Kim, Jonathan
>> Sent: Wednesday, October 16, 2024 11:59 AM
&g
To achieve full occupancy CP hardware needs to know if CUs in SE are
symmetrically or asymmetrically harvested
v2: Reset is_symmetric_cus for each loop
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c | 15 +--
1 file changed, 13 insertions(+), 2
To achieve full occupancy CP hardware needs to know if CUs in SE are
symmetrically or asymmetrically harvested
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c | 14 --
1 file changed, 12 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm
crc16 as suggested-by: Lijo Lazar
Ensure that gpu_id != 0
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdkfd/kfd_topology.c | 40 +++
1 file changed, 34 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
b/drivers/gpu
On 2024-05-06 16:30, Felix Kuehling wrote:
>
> On 2024-05-03 18:06, Harish Kasiviswanathan wrote:
>> gpu_id needs to be unique for user space to identify GPUs via KFD
>> interface. In the current implementation there is a very small
>> probability of having non uniqu
-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdkfd/kfd_topology.c | 26 ++-
1 file changed, 25 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index b93913934b03..01d4c2e10c6d 100644
gpu_id needs to be unique for user space to identify GPUs via KFD
interface. Do a single pass search to detect collision. If
detected, increment gpu_id by one.
Probability of collisons are very rare. Hence, no more complexity is
added to ensure uniqueness.
Signed-off-by: Harish Kasiviswanathan
No functional change. This will help in moving gpu_id creation to next
step while still being able to identify the correct GPU
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdkfd/kfd_topology.c | 19 ---
1 file changed, 8 insertions(+), 11 deletions(-)
diff
Queue buffer, though it is in system memory, has to be created using the
correct amdgpu device. Enforce this as the BO needs to mapped to the
GART for MES Hardware scheduler to access it.
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 5 +
1 file
ff-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 151fabf84040..c08b6ee25289 100644
--- a/dr
Also passing adev is misleading if BO is associated with different adev.
In this case BO is mapped to a different device
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h | 2 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 4 ++--
drivers/gpu/drm
Heavy-weight TLB flush is required after unmap on all GPUs for
correctness and security.
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
b/drivers/gpu/drm
From: Jay Cornwall
mqd_stride function was introduced in commit 129c7b6a0217
("drm/amdkfd: Update MQD management on multi XCC setup")
but not assigned for gfx11. Fixes a NULL dereference in debugfs.
Signed-off-by: Jay Cornwall
Signed-off-by: Harish Kasiviswanathan
---
drivers/g
No functional change. Use ratelimited version of pr_ to avoid
overflowing of dmesg buffer
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c | 6 +++---
drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c | 6 +++---
drivers/gpu/drm/amd/amdkfd
Signed-off-by: Harish Kasiviswanathan
Reviewed-by: Hawking Zhang
---
drivers/gpu/drm/amd/amdgpu/ih_v6_0.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
index 92dc60a9d209..085e613f3646 100644
--- a/drivers/gpu
Aldebaran has 48-bit physical address support
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 9 +++--
1 file changed, 7 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index
Print alloc node, peer node and memory domain when peer map fails. This
is more useful
v2: use dev_err instead of pr_err
use bdf for identify peer gpu
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 11 +--
1 file changed, 9 insertions(+), 2
Print alloc node, peer node and memory domain when peer map fails. This
is more useful
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
b/drivers
v2: updated MEC FW version after validating gws with debugger
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdkfd/kfd_device.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
b/drivers/gpu/drm/amd/amdkfd
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
index 1f02e4ee2909
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
index dcbe3a72da09
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdkfd/kfd_device.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index b31bae91fbd0..bc57b07523e0 100644
--- a/drivers/gpu
From: Oak Zeng
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 ++---
drive
From: Oak Zeng
This new interface passes both virtual and physical address
to PSP. It is backward compatible with old interface.
v2: use a function to simplify tmr physical address calc (Lijo)
Signed-off-by: Oak Zeng
Reviewed-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdgpu
From: Oak Zeng
Use amdgpu_gmc_vram_pa and amdgpu_gmc_vram_cpu_pa
to simplify codes. No logic change.
Signed-off-by: Oak Zeng
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c | 4 +---
drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c | 3 +--
drivers/gpu/drm/amd
From: Oak Zeng
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
Reviewed-by: Christian K
This reverts commit 73bf5cad2696fe3a21f70101821405db839ea18e.
Fixed in newer firmware
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 7 ---
1 file changed, 7 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
b/drivers/gpu/drm/amd
Signed-off-by: Harish Kasiviswanathan
Change-Id: Ic139a8b9c8bef1df183804e543103be206405dca
---
drivers/gpu/drm/amd/amdkfd/kfd_device.c | 14 +++---
1 file changed, 7 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
b/drivers/gpu/drm/amd/amdkfd
Signed-off-by: Harish Kasiviswanathan
Change-Id: Ia9f8872b7654b99864bbef1afb9998d0cf39b7e5
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 7 +++
1 file changed, 7 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index
jobs are identified by the fence owner
AMDGPU_FENCE_OWNER_UNDEFINED
v2: Always sync to exclusive fence
v3: avoid unncessary diverge from amd-staging-drm-next
Change-Id: I8752d1cf6b2a1c4f2a57292b7c2cd308d5b6f9b7
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdgpu/amdgpu_sync.
jobs are identified by the fence owner
AMDGPU_FENCE_OWNER_UNDEFINED
v2: Always sync to exclusive fence
Change-Id: I8752d1cf6b2a1c4f2a57292b7c2cd308d5b6f9b7
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c | 8
1 file changed, 4 insertions(+), 4 dele
jobs are identified by the fence owner
AMDGPU_FENCE_OWNER_UNDEFINED
Change-Id: I8752d1cf6b2a1c4f2a57292b7c2cd308d5b6f9b7
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c | 8 +---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/dr
timeout the reverse is done to make the process queues active again.
What is the current issue?
Interop BOs. KFD fence is attached to shared BO. So when graphics
tries do a CS using this BO, KFD driver mistakes this to be an
eviction. This patch is to solve this issue.
Harish
v2: Use amdgpu_find_mm_node() in amdgpu_ttm_io_mem_pfn()
Change-Id: I12231e18bb60152843cd0e0213ddd0d0e04e7497
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 49 ++---
1 file changed, 27 insertions(+), 22 deletions(-)
diff --git a
nged amdgpu_copy_ttm_mem_to_mem()
function parameters to use the struct
v3: Minor function name change
Change-Id: I848d541a84a1c2d12827d9dcf6d9054d854b4159
Signed-off-by: Harish Kasiviswanathan
Reviewed-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c |
Change-Id: I12231e18bb60152843cd0e0213ddd0d0e04e7497
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 36 +++--
1 file changed, 21 insertions(+), 15 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
b/drivers/gpu
nged amdgpu_copy_ttm_mem_to_mem()
function parameters to use the struct
Change-Id: I848d541a84a1c2d12827d9dcf6d9054d854b4159
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 169 +++-
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h | 12 +++
2 f
4159
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 159
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h | 7 ++
2 files changed, 107 insertions(+), 59 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
b/drivers/gpu
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 73 --
1 file changed, 16 insertions(+), 57 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index c4f1a30..c308047 100644
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index c308047..9743db5 100644
--- a/drivers/gpu/drm/amd
Helper function useful for CPU update of VM page tables. Also useful if
kernel have to synchronously wait till VM page tables are updated.
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c | 19 +++
drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h | 1
If amdgpu.vm_update_context param is set to use CPU, then Page
Directories will be updated by CPU instead of SDMA
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 151 -
1 file changed, 109 insertions(+), 42 deletions(-)
diff
This change is also useful for the upcoming changes where page tables
can be updated by CPU.
Change-Id: I07510ed60c94cf1944ee96bb4b16c40ec88ea17c
Signed-off-by: Harish Kasiviswanathan
Reviewed-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 48
large BAR system vm_update_mode = 2, indicating
that Graphics VMs will be updated via SDMA and Compute VMs will be
updated via CPU. And for all all other systems (by default)
vm_update_mode = 0
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 +
drivers/gpu
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 86 +-
1 file changed, 85 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index d72a624..e98d558 100644
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 82 +-
1 file changed, 81 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 63f0572..63b4696 100644
This change is also useful for the upcoming changes where page tables
can be updated by CPU.
Change-Id: I07510ed60c94cf1944ee96bb4b16c40ec88ea17c
Signed-off-by: Harish Kasiviswanathan
Reviewed-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 48
If amdgpu.vm_update_context param is set to use CPU, then Page
Directories will be updated by CPU instead of SDMA
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 141 +++--
1 file changed, 99 insertions(+), 42 deletions(-)
diff
for large BAR system vm_update_context = 2, indicating
that Graphics VMs will be updated via SDMA and Compute VMs will be
updated via CPU. And for all all other systems (by default)
vm_update_context = 0
Signed-off-by: Harish Kasiviswanathan
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1
75 matches
Mail list logo
