are system memory.
v2: Report local_mem_size_private as 0. (Felix)
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c| 5 +
.../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 20 ++-
drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 2 +-
drivers/gpu/drm/
we can change BIOS settings to enlarge carveout size,
which is inflexible and may bring complaint. On the other hand,
the memory resource can't be effectively used between host and device.
The solution is MI300A approach, i.e., let VRAM allocations go to GTT.
Signed-off-by: Lang Yu
---
drivers
The default ttm_tt_pages_limit is 1/2 of system memory.
It is prone to out of memory with such a configuration.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 2 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h | 4 ++--
drivers/gpu/drm/amd/amdgpu
] ret_from_fork_asm+0x1b/0x30
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 101a2836480d
umsch test needs full GPU functionality(e.g., VM update, TLB flush,
possibly buffer moving under memory pressure) which may be not ready
under these states. Just skip it to avoid potential issues.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c | 3 +++
1 file changed, 3
in amdgpu_amdkfd_restore_process_bos. (Felix)
1.Validate BOs
2.Validate VM (and DMABuf attachments)
3.Update page tables for the BOs validated above
Fixes: 2fdba514ad5a ("drm/amdgpu: Auto-validate DMABuf imports in compute VMs")
Signed-off-by: Lang Yu
---
.../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpu
When VM is in evicting state, amdgpu_vm_update_range would return -EBUSY.
Then restore_process_worker runs into a dead loop.
Fixes: 2fdba514ad5a ("drm/amdgpu: Auto-validate DMABuf imports in compute VMs")
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 6
after GPU reset succeeds.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 24 ++
drivers/gpu/drm/amd/include/amd_shared.h | 3 +++
2 files changed, 27 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
b/drivers/gpu/drm/amd/amdgpu
Otherwise the old one will be used during GPU reset.
That's not expected.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c
b/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c
index
drm sched is stopped and SDMA mode is not available,
while CPU mode worked well in such a case.
Use case,
amdgpu_do_asic_reset
amdgpu_device_ip_late_init
umsch_mm_late_init
umsch_mm_test
amdgpu_vm_init
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 4 ++--
1 file changed
Share same codes with 4.0.5 and enable collaborate mode for VPE.
Signed-off-by: Lang Yu
Reviewed-by: Veerabadhran Gopalakrishnan
---
drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c | 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c | 12 ++--
drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c
Align with FW changes.
Signed-off-by: Lang Yu
Reviewed-by: Veerabadhran Gopalakrishnan
---
drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.h | 20 +--
.../drm/amd/include/umsch_mm_4_0_api_def.h| 13 ++--
2 files changed, 21 insertions(+), 12 deletions(-)
diff --git
Ready now. Remove this workaround.
This reverts commit 1a2bb3bb2a84f8364f0a8b338afa9b9025e1bcc0.
Signed-off-by: Lang Yu
Tested-by: Alan Liu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
b/drivers/gpu
Fixes: aba2be41470a ("drm/amdgpu: add mmhub 3.3.0 support")
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/mmhub_v3_3.c | 7 +++
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_3.c
b/drivers/gpu/drm/amd/amdgpu/mmhub_v3
This is useful to prevent copy-on-write semantics
from changing the physical location of a page if
the parent writes to it after a fork().
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 1 +
drivers/gpu/drm/amd/amdkfd/kfd_svm.c| 1 +
2 files changed, 2 insertions
after_hwframe+0x6e/0xd8
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h| 2 +-
.../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 20 ---
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 4 +++-
3 files changed, 21 insertions(+), 5 deletions(-)
diff --git
10 [amdgpu]
[ 41.709945] ? srso_alias_return_thunk+0x5/0x7f
[ 41.709949] ? tomoyo_file_ioctl+0x20/0x30
[ 41.709959] __x64_sys_ioctl+0x9c/0xd0
[ 41.709967] do_syscall_64+0x3f/0x90
[ 41.709973] entry_SYSCALL_64_after_hwframe+0x6e/0xd8
Signed-off-by: Lang Yu
---
drivers/gpu/drm/
k+0x5/0x7f
[ 41.709949] ? tomoyo_file_ioctl+0x20/0x30
[ 41.709959] __x64_sys_ioctl+0x9c/0xd0
[ 41.709967] do_syscall_64+0x3f/0x90
[ 41.709973] entry_SYSCALL_64_after_hwframe+0x6e/0xd8
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 7 ++-
1 file changed, 6
On 10/31/ , Christian König wrote:
> Am 31.10.23 um 14:59 schrieb Bas Nieuwenhuizen:
> >
> >
> > On Tue, Oct 31, 2023 at 2:57 PM Christian König
> > wrote:
> >
> > Am 31.10.23 um 14:40 schrieb Tatsuyuki Ishi:
> > > The current amdgpu_gem_va_update_vm only tries to perform
> >
IB test would fail if not stop queue correctly.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/vpe_v6_1.c | 18 ++
1 file changed, 10 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/vpe_v6_1.c
b/drivers/gpu/drm/amd/amdgpu/vpe_v6_1.c
index
Add missing IP callbacks.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c | 16
1 file changed, 16 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
index 4bd076e9e367..f5fdde5181f7
These are missed during rebase.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index 771ef8017a98..3713d0749813 100644
FW uses IP_VERSION_MAJ_MIN_REV format.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c | 11 +++
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c
b/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c
index
Use v7.7 before, switch to v7.11 now.
Fix incorrect programing.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c | 56 +--
.../asic_reg/nbio/nbio_7_11_0_offset.h| 9 ++-
2 files changed, 33 insertions(+), 32 deletions(-)
diff --git a/drivers/gpu
Legacy invalidation is not supported.
This is missed during rebase.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/mmhub_v3_3.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_3.c
b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_3.c
index
On 10/10/ , Alex Deucher wrote:
> On Tue, Oct 10, 2023 at 9:42 AM Lang Yu wrote:
> >
> > On 10/10/ , Deucher, Alexander wrote:
> > > [Public]
> > >
> > > > -Original Message-
> > > > From: Yu, Lang
> > > > Sent: Saturd
adhran (Veera)
> > ; Yu, Lang
> > Subject: [PATCH 2/3] drm/amdgpu/umsch: power on/off UMSCH by DLDO
> >
> > VCN 4.0.5 uses DLDO.
> >
> > Signed-off-by: Lang Yu
> > ---
> > drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c | 26
> >
adhran (Veera)
> > ; Yu, Lang
> > Subject: [PATCH 2/3] drm/amdgpu/umsch: power on/off UMSCH by DLDO
> >
> > VCN 4.0.5 uses DLDO.
> >
> > Signed-off-by: Lang Yu
> > ---
> > drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c | 26
> >
VCN 4.0.5 uses DLDO.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c | 26 ++
1 file changed, 26 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c
b/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c
index a60178156c77..7e79954c833b 100644
Program vcn_doorbell_range with vcn_ring0_1.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c | 2 +-
drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c | 3 ++-
2 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
b
These changes are missed in rebase.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c | 35 +++---
drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.h | 18 +++-
drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c | 107 ---
3 files changed, 72 insertions(+), 88
On 10/06/ , Yifan Zhang wrote:
> add hub->ctx_distance when read CONTEXT1_CNTL, align w/
> write back operation.
>
> v2: fix coding style errors reported by checkpatch.pl (Christian)
>
> Signed-off-by: Yifan Zhang
> Acked-by: Christian König
Reviewed-by: Lang Yu
>
Avoid infinite loop when count is 0.
This is missed in rebase.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c | 9 +
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
index
Remove IB end boundary requirement,
VPE has no such limitions, use existing
amdgpu_ring_generic_pad_ib() instead.
This is missed in rebase.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c | 20 +---
1 file changed, 1 insertion(+), 19 deletions(-)
diff --git
MCBP is decided by adev->gfx.mcbp now.
This is missed in rebase.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
in
; Signed-off-by: Juntong Deng
Thanks!
Reviewed-by: Lang Yu
> ---
> drivers/gpu/drm/amd/include/amd_shared.h | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/drivers/gpu/drm/amd/include/amd_shared.h
> b/drivers/gpu/drm/amd/include/amd_shared.h
> index 63e2153c00c4
Fixes: ab041551f4a7 ("drm/amdgpu: add VPE 6.1.0 support")
Signed-off-by: Lang Yu
Reported-by: kernel test robot
Link: https://lore.kernel.org/oe-kbuild-all/202309200028.auvum8os-...@intel.com
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c | 5 +
1 file changed, 1 insertion(+), 4
O 09/21/ , Lang Yu wrote:
Sorry for sending this patch twice. Please ignore this one.
Regards,
Lang
> Cayn skilfish uses SMUIO v11.0.8 offset.
>
> Signed-off-by: Lang Yu
> Cc: # v5.15+
> ---
> drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 21 +
> 1 file c
Cayn skilfish uses SMUIO v11.0.8 offset.
Signed-off-by: Lang Yu
Cc: # v5.15+
---
drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 21 +
1 file changed, 21 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 1d671c330475
Cayn skilfish uses SMUIO v11.0.8 offset.
Signed-off-by: Lang Yu
Cc: # v5.15+
---
drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 21 +
1 file changed, 21 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 1d671c330475
t is longer than the FIFOs in
>the HW
> * Execute an atomic operation to memory on some GPU engine that could
>act as a fence, maybe just a RELEASE_MEM on the CP to some writeback
>location would do the job
> * If needed, RELEASE_MEM could also perform a cache flush
>
> R
cyan_skilfish has problems with other flush types.
v2: fix incorrect ternary conditional operator usage.(Yifan)
Signed-off-by: Lang Yu
Cc: # v5.15+
---
drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c | 7 ++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu
On 09/14/ , Zhang, Yifan wrote:
> [Public]
>
> -Original Message-
> From: amd-gfx On Behalf Of Lang Yu
> Sent: Thursday, September 14, 2023 3:00 PM
> To: amd-gfx@lists.freedesktop.org
> Cc: Deucher, Alexander ; Yu, Lang
> ; Koenig, Christian ;
> sta...@vger.k
cyan_skilfish has problems with other flush types.
Signed-off-by: Lang Yu
Cc: # v5.15+
---
drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c | 7 ++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index
On 09/13/ , Felix Kuehling wrote:
> On 2023-09-13 6:23, Lang Yu wrote:
> > On 09/12/ , Felix Kuehling wrote:
> > > On 2023-09-11 22:52, Lang Yu wrote:
> > > > On 09/11/ , Harish Kasiviswanathan wrote:
> > > > > Heavy-weight TLB flush is required afte
On 09/12/ , Felix Kuehling wrote:
> On 2023-09-11 22:52, Lang Yu wrote:
> > On 09/11/ , Harish Kasiviswanathan wrote:
> > > Heavy-weight TLB flush is required after unmap on all GPUs for
> > > correctness and security.
> > >
> > > Signed-off-by: Har
On 09/12/ , Alex Deucher wrote:
> Add missing IP discovery info.
>
> Signed-off-by: Alex Deucher
Reviewed-by: Lang Yu
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 3 +++
> 1 file changed, 3 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
On 09/11/ , Alex Deucher wrote:
> Implement support for remapping the HDP aperture registers for
> NBIO 7.11.
>
> Signed-off-by: Alex Deucher
The series is.
Reviewed-by: Lang Yu
> ---
> drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c | 9 +
> 1 file changed, 9 insertio
On 09/11/ , Harish Kasiviswanathan wrote:
> 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
OCm if
we don't use SVM for ASICs except MI series.
Regards,
Lang
> Regards,
> Felix
>
>
> On 2023-09-07 08:08, Lang Yu wrote:
> > GC 10.1.3/4 have problems with TLB_FLUSH_HEAVYWEIGHT
> > which is used by SVM in svm_range_unmap_from_gpus().
> > This causes pro
GC 10.1.3/4 have problems with TLB_FLUSH_HEAVYWEIGHT
which is used by SVM in svm_range_unmap_from_gpus().
This causes problems on GC 10.1.3/4.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 22 +-
1 file changed, 17 insertions(+), 5 deletions(-)
diff
Fixes: 77b13b916728 ("drm/amdgpu: add selftest framework for UMSCH")
Signed-off-by: Lang Yu
Reported-by: Dan Carpenter
Link: https://lore.kernel.org/all/ZPhddADtKmOuVyDq@lang-desktop
---
drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c | 7 +++
1 file changed, 3 insertions(+), 4
On 09/06/ , Dan Carpenter wrote:
Thanks for reporting this bug. Can you give a link to this bug report? Commit
message requests it.
("Reported-by: should be immediately followed by Link: with a URL to the
report")
Regards,
Lang
> Hello Lang Yu,
>
> The patch 5d5eac7e830
Fixes: ab041551f4a7 ("drm/amdgpu: add VPE 6.1.0 support")
Signed-off-by: Lang Yu
Reported-by: kernel test robot
Link: https://lore.kernel.org/oe-kbuild-all/202309020608.fwp8qmht-...@intel.com
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.h | 2 +-
drivers/gpu/drm/amd/amdgpu/vpe_v6
ep 1MB in the VRAM range.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 38 +++--
1 file changed, 35 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 15217e33b51d..3fadfaa63b2e
CPU domain first, it will always succeed.
v2: Don't overwrite the contents at specific offset.
v3: Don't return GPU addr.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 19 ++-
1 file changed, 14 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/
On 07/28/ , Christian König wrote:
> Am 28.07.23 um 09:00 schrieb Lazar, Lijo:
> >
> >
> > On 7/28/2023 11:34 AM, Lang Yu wrote:
> > > Use amdgpu_bo_create_reserved() to create a BO in VRAM
> > > domain would fail if requested VRAM size is large(>128MB
CPU domain first, it will always succeed.
v2: Don't overwrite the contents at specific offset.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 24 --
drivers/gpu/drm/amd/amdgpu/amdgpu_object.h | 3 ++-
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c|
On 07/27/ , Christian König wrote:
> Am 27.07.23 um 10:15 schrieb Lang Yu:
> > On 07/27/ , Christian König wrote:
> > > Am 27.07.23 um 09:56 schrieb Lang Yu:
> > > > amdgpu_bo_create_kernel_at() is used to create a physical
> > > > contiguou
On 07/27/ , Christian König wrote:
> Am 27.07.23 um 09:56 schrieb Lang Yu:
> > TMR requires physical contiguous memory, amdgpu_bo_create_kernel()
> > can't satisfy large(>128MB) physical contiguous memory allocation
> > request with default 512MB VRAM on APU.
> >
On 07/27/ , Christian König wrote:
> Am 27.07.23 um 09:56 schrieb Lang Yu:
> > amdgpu_bo_create_kernel_at() is used to create a physical
> > contiguous VRAM BO at the specific offset. It calls
> > amdgpu_bo_create_reserved() to create a VRAM BO first,
> > then frees i
TMR requires physical contiguous memory, amdgpu_bo_create_kernel()
can't satisfy large(>128MB) physical contiguous memory allocation
request with default 512MB VRAM on APU.
When requested TMR size > 128MB, use amdgpu_bo_create_kernel_at()
to create the TMR BO at offset 64MB.
Signed-off-by
rst, it will always succeed.
Then use amdgpu_bo_pin_restricted() to move the BO to
requested domain and location.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 30 --
drivers/gpu/drm/amd/amdgpu/amdgpu_object.h | 3 ++-
drivers/gpu/drm/amd/amdgpu/amdgpu_tt
Align with new vmhub definition.
v2: use client_id == VMC to decide vmhub(Hawking)
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c | 4 +++-
drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c | 4 +++-
2 files changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd
t; -Original Message-
> From: Yu, Lang
> Sent: Wednesday, July 26, 2023 19:25
> To: amd-gfx@lists.freedesktop.org
> Cc: Deucher, Alexander ; Zhang, Hawking
> ; Zhang, Yifan ; Yu, Lang
>
> Subject: [PATCH] drm/amdgpu: correct vmid_src -> vmhub_index mapping
>
>
Align with new vmhub definition.
vmid_src 0 -> AMDGPU_GFXHUB(0).
vmid_src 1 -> AMDGPU_MMHUB0(0).
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c | 3 ++-
drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c | 3 ++-
2 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/drive
Replace the old ones with psp_execute_load_ip_fw.
Suggested-by: Lijo Lazar
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 13 -
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h | 2 --
drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 15 +++
drivers/gpu/drm/amd
This will make this function more general, and then serve other IPs.
Suggested-by: Lijo Lazar
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 12 ++--
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h | 3 +++
2 files changed, 9 insertions(+), 6 deletions(-)
diff --git
On 07/07/ , Lazar, Lijo wrote:
>
>
> On 7/7/2023 5:01 PM, Lang Yu wrote:
> > It uses the same UCODE ID(VCN0_RAM) but differnet cmd buffers
> > for all instances.
> >
> > Fixes: e928b52c58dd ("drm/amdgpu: use psp_execute_load_ip_fw_cmd_buf
> &g
It uses the same UCODE ID(VCN0_RAM) but differnet cmd buffers
for all instances.
Fixes: e928b52c58dd ("drm/amdgpu: use psp_execute_load_ip_fw_cmd_buf instead")
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
On 07/07/ , Lazar, Lijo wrote:
>
>
> On 6/29/2023 1:44 PM, Lang Yu wrote:
> > Ping.
> >
> > On 06/27/ , Lang Yu wrote:
> > > Replace the old ones with psp_execute_load_ip_fw_cmd_buf.
> > >
> > > Signed-off-by: Lang Yu
> >
On 07/05/ , Matthew Auld wrote:
> On Wed, 5 Jul 2023 at 11:08, Lang Yu wrote:
> >
> > bo->kref is increased once(kref_init()) in ttm_bo_release,
> > but decreased twice(ttm_bo_put()) respectively in
> > ttm_bo_delayed_delete and ttm_bo_cleanup_refs,
> > which
[ 67.403579] ? tomoyo_file_ioctl+0x19/0x20
[ 67.403590] __x64_sys_ioctl+0x95/0xd0
[ 67.403601] do_syscall_64+0x3b/0x90
[ 67.403609] entry_SYSCALL_64_after_hwframe+0x72/0xdc
Signed-off-by: Lang Yu
---
drivers/gpu/drm/ttm/ttm_bo.c | 89
1 file changed, 10 inse
Please ignore this patch, it will cause another issue.
Will send a new one.
Regards,
Lang
On 07/05/ , Lang Yu wrote:
> [ 67.399887] refcount_t: underflow; use-after-free.
> [ 67.399901] WARNING: CPU: 0 PID: 3172 at lib/refcount.c:28
> refcount_warn_saturate+0xc2/0x110
> [ 67
+0x19/0x20
[ 67.403590] __x64_sys_ioctl+0x95/0xd0
[ 67.403601] do_syscall_64+0x3b/0x90
[ 67.403609] entry_SYSCALL_64_after_hwframe+0x72/0xdc
Fixes: 9bff18d13473 ("drm/ttm: use per BO cleanup workers")
Signed-off-by: Lang Yu
---
drivers/gpu/drm/ttm/ttm_bo.c | 3 +++
1 file
Ping.
On 06/27/ , Lang Yu wrote:
> Replace the old ones with psp_execute_load_ip_fw_cmd_buf.
>
> Signed-off-by: Lang Yu
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 31 -
> drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h | 2 --
> drivers/gpu/drm/am
Ping.
On 06/27/ , Lang Yu wrote:
> This function is more general and easy to use by more clients.
>
> Signed-off-by: Lang Yu
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 29 +
> drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h | 6 +
> 2 files c
This function is more general and easy to use by more clients.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 29 +
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h | 6 +
2 files changed, 35 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu
Replace the old ones with psp_execute_load_ip_fw_cmd_buf.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 31 -
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h | 2 --
drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 9 +++
drivers/gpu/drm/amd/amdgpu
Please ignore this patch, will send a new one.
Regards,
Lang
On 06/27/ , Lang Yu wrote:
> Rename psp_update_vcn_sram to psp_execute_ucode_loading
> so that other clients can feel free to use it.
>
> Signed-off-by: Lang Yu
> ---
> drivers/gpu/drm/amd/amdgpu
Rename psp_update_vcn_sram to psp_execute_ucode_loading
so that other clients can feel free to use it.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 19 ++-
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h | 7 +--
drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c | 7
Try to disable CONFIG_HSA_AMD_SVM in your kernel config.
Regards,
Lang
On 06/09/ , 彭逸豪 wrote:
> I have a Radeon RX 6800 and want to use it on my ARM server (Hardware name:
> Think-Force Technology Universal Server/7140 Advanced, BIOS 1.1.7 20230216).
> However the presence of this GPU can
280
[14616.937239] fput+0xe/0x20
[14616.937241] task_work_run+0x61/0x90
[14616.937246] exit_to_user_mode_prepare+0x215/0x220
[14616.937251] syscall_exit_to_user_mode+0x2a/0x60
[14616.937254] do_syscall_64+0x48/0x90
[14616.937257] entry_SYSCALL_64_after_hwframe+0x63/0xcd
Signed-off-by: Lang
[14616.937246] exit_to_user_mode_prepare+0x215/0x220
[14616.937251] syscall_exit_to_user_mode+0x2a/0x60
[14616.937254] do_syscall_64+0x48/0x90
[14616.937257] entry_SYSCALL_64_after_hwframe+0x63/0xcd
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c | 38
When using cpu to update page tables, vm update fences are unused.
Install stub fence into these fence pointers instead of NULL
to avoid NULL dereference when calling dma_fence_wait() on them.
Suggested-by: Christian König
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 6
On 05/05/ , Christian König wrote:
> Am 05.05.23 um 11:10 schrieb Lang Yu:
> > Using cpu to update page tables is sychronous, no need to wait fence
> > and it is NULL in such a case.
>
> Good catch, be we usually install the stub into fence pointers when they are
> unused
Using cpu to update page tables is sychronous, no need to wait fence
and it is NULL in such a case.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c | 7 +--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
b/drivers
On 04/30/ , Yifan Zhang wrote:
> APUs w/ gfx9 onwards doesn't reply on PCIe atomics, rather
> it is internal path w/ native atomic support. Set have_atomics_support
> to true.
>
> Signed-off-by: Yifan Zhang
Reviewed-by: Lang Yu
> ---
> drivers/gpu/drm/amd/amdgp
There is only one MEC on these APUs.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 11 +--
1 file changed, 9 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 985fe704203e
Always enable multipipe policy on ASICs with GC VERSION > 9.0.0
instead of MEC number > 1.
This will allow multipipe policy on ASICs with one MEC,
e.g., gfx11 APUs.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/d
Then we can remove the burden of maintaining codes to
parse family_id from gfx version in rocr,
i.e., remove DevIDToAddrLibFamily().
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdkfd/kfd_topology.c | 3 +++
drivers/gpu/drm/amd/amdkfd/kfd_topology.h | 1 +
2 files changed, 4 insertions
The kgd_mem memory allocated in amdgpu_amdkfd_gpuvm_import_dmabuf()
is not freed properly.
Explicitly free it in amdgpu_amdkfd_gpuvm_free_memory_of_gpu()
under condition "mem->bo->kfd_bo != mem".
Suggested-by: Felix Kuehling
Signed-off-by: Lang Yu
---
drivers/gp
No need to reference the BO here, dmabuf framework will handle that.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
b/drivers/gpu/drm/amd/amdgpu
We have memory leak issue in current implenmention, i.e.,
the allocated struct kgd_mem memory is not handled properly.
The idea is always creating a buffer object when importing
a gfx BO based dmabuf.
Signed-off-by: Lang Yu
---
.../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 99
For clients(e.g., kfd) who want to determine whether to
create a buffer object by themselves especially when
importing a gfx BO based dmabuf.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 38 +
drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.h | 2 ++
2
ping.
On 07/14/ , Lang Yu wrote:
> The driver can only support AMDGPU_MAX_GFX_RINGS gfx queues
> at the moment. Once enabled gfx queues exceed the limit,
> we will run into problems when setting up gfx rings in
> gfx_xxx_sw_init().
>
> Signed-off-by: Lang Yu
> ---
> dr
The driver can only support AMDGPU_MAX_GFX_RINGS gfx queues
at the moment. Once enabled gfx queues exceed the limit,
we will run into problems when setting up gfx rings in
gfx_xxx_sw_init().
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 5 +++--
1 file changed, 3
On 06/29/ , Jack Xiao wrote:
> Use read/write register to test mes ring.
>
> Signed-off-by: Jack Xiao
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c | 36 +
> drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h | 1 +
> drivers/gpu/drm/amd/amdgpu/mes_v11_0.c | 6 +
> 3 files
updating vm->update_funcs
in amdgpu_vm_make_compute whether the vm_update_mode changed
or not.
v3:
- Add some comments suggested by Christian.
v2:
- Don't rename vm_validate_pt_pd_bos and make it public.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c |
to amdgpu_vm_make_compute.
v2:
- Don't rename vm_validate_pt_pd_bos and make it public.
Signed-off-by: Lang Yu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 14 --
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 5 +
2 files changed, 5 insertions(+), 14 deletions(-)
diff
1 - 100 of 201 matches
Mail list logo