* [PATCH] drm/amdgpu: Fix SDMA UTC_L1 handling during start/stop sequences
@ 2025-06-16 11:43 Jesse Zhang
2025-06-16 13:51 ` Philip Yang
0 siblings, 1 reply; 2+ messages in thread
From: Jesse Zhang @ 2025-06-16 11:43 UTC (permalink / raw)
To: amd-gfx
Cc: Alexander.Deucher, Christian Koenig, Jesse Zhang, Jonathan Kim,
Jesse Zhang
This commit makes two key fixes to SDMA v4.4.2 handling:
1. disable UTC_L1 in sdma_cntl register when stopping SDMA engines
by reading the current value before modifying UTC_L1_ENABLE bit.
2. Ensure UTC_L1_ENABLE is consistently managed by:
- Adding the missing register write when enabling UTC_L1 during start
- Keeping UTC_L1 enabled by default as per hardware requirements
Fixes the commit 7f03b1d14d51 ("drm/amdgpu:
Remove sdma halt/unhalt during frontdoor load") by maintaining proper
SDMA controller state during initialization sequences.
Suggested-by: Jonathan Kim <jonathan.kim@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
---
drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
index e6af50c947a1..1f6a8944b1ea 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
@@ -492,7 +492,7 @@ static void sdma_v4_4_2_inst_gfx_stop(struct amdgpu_device *adev,
{
struct amdgpu_ring *sdma[AMDGPU_MAX_SDMA_INSTANCES];
u32 doorbell_offset, doorbell;
- u32 rb_cntl, ib_cntl;
+ u32 rb_cntl, ib_cntl, sdma_cntl;
int i;
for_each_inst(i, inst_mask) {
@@ -504,6 +504,8 @@ static void sdma_v4_4_2_inst_gfx_stop(struct amdgpu_device *adev,
ib_cntl = RREG32_SDMA(i, regSDMA_GFX_IB_CNTL);
ib_cntl = REG_SET_FIELD(ib_cntl, SDMA_GFX_IB_CNTL, IB_ENABLE, 0);
WREG32_SDMA(i, regSDMA_GFX_IB_CNTL, ib_cntl);
+ sdma_cntl = REG_SET_FIELD(sdma_cntl, SDMA_CNTL, UTC_L1_ENABLE, 0);
+ WREG32_SDMA(i, regSDMA_CNTL, sdma_cntl);
if (sdma[i]->use_doorbell) {
doorbell = RREG32_SDMA(i, regSDMA_GFX_DOORBELL);
@@ -997,6 +999,7 @@ static int sdma_v4_4_2_inst_start(struct amdgpu_device *adev,
/* set utc l1 enable flag always to 1 */
temp = RREG32_SDMA(i, regSDMA_CNTL);
temp = REG_SET_FIELD(temp, SDMA_CNTL, UTC_L1_ENABLE, 1);
+ WREG32_SDMA(i, regSDMA_CNTL, temp);
if (amdgpu_ip_version(adev, SDMA0_HWIP, 0) < IP_VERSION(4, 4, 5)) {
/* enable context empty interrupt during initialization */
--
2.34.1
^ permalink raw reply related [flat|nested] 2+ messages in thread
* Re: [PATCH] drm/amdgpu: Fix SDMA UTC_L1 handling during start/stop sequences
2025-06-16 11:43 [PATCH] drm/amdgpu: Fix SDMA UTC_L1 handling during start/stop sequences Jesse Zhang
@ 2025-06-16 13:51 ` Philip Yang
0 siblings, 0 replies; 2+ messages in thread
From: Philip Yang @ 2025-06-16 13:51 UTC (permalink / raw)
To: Jesse Zhang, amd-gfx; +Cc: Alexander.Deucher, Christian Koenig, Jonathan Kim
On 2025-06-16 07:43, Jesse Zhang wrote:
> This commit makes two key fixes to SDMA v4.4.2 handling:
>
> 1. disable UTC_L1 in sdma_cntl register when stopping SDMA engines
> by reading the current value before modifying UTC_L1_ENABLE bit.
>
> 2. Ensure UTC_L1_ENABLE is consistently managed by:
> - Adding the missing register write when enabling UTC_L1 during start
> - Keeping UTC_L1 enabled by default as per hardware requirements
>
> Fixes the commit 7f03b1d14d51 ("drm/amdgpu:
> Remove sdma halt/unhalt during frontdoor load") by maintaining proper
> SDMA controller state during initialization sequences.
>
> Suggested-by: Jonathan Kim <jonathan.kim@amd.com>
> Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
> ---
> drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c | 5 ++++-
> 1 file changed, 4 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
> index e6af50c947a1..1f6a8944b1ea 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
> @@ -492,7 +492,7 @@ static void sdma_v4_4_2_inst_gfx_stop(struct amdgpu_device *adev,
> {
> struct amdgpu_ring *sdma[AMDGPU_MAX_SDMA_INSTANCES];
> u32 doorbell_offset, doorbell;
> - u32 rb_cntl, ib_cntl;
> + u32 rb_cntl, ib_cntl, sdma_cntl;
> int i;
>
> for_each_inst(i, inst_mask) {
> @@ -504,6 +504,8 @@ static void sdma_v4_4_2_inst_gfx_stop(struct amdgpu_device *adev,
> ib_cntl = RREG32_SDMA(i, regSDMA_GFX_IB_CNTL);
> ib_cntl = REG_SET_FIELD(ib_cntl, SDMA_GFX_IB_CNTL, IB_ENABLE, 0);
> WREG32_SDMA(i, regSDMA_GFX_IB_CNTL, ib_cntl);
seems using random value sdma_cntl to init, probably you need add this?
sdma_cntl = RREG32_SDMA(i, SDMA_CNTL);
Regards,
Philip
> + sdma_cntl = REG_SET_FIELD(sdma_cntl, SDMA_CNTL, UTC_L1_ENABLE, 0);
> + WREG32_SDMA(i, regSDMA_CNTL, sdma_cntl);
>
> if (sdma[i]->use_doorbell) {
> doorbell = RREG32_SDMA(i, regSDMA_GFX_DOORBELL);
> @@ -997,6 +999,7 @@ static int sdma_v4_4_2_inst_start(struct amdgpu_device *adev,
> /* set utc l1 enable flag always to 1 */
> temp = RREG32_SDMA(i, regSDMA_CNTL);
> temp = REG_SET_FIELD(temp, SDMA_CNTL, UTC_L1_ENABLE, 1);
> + WREG32_SDMA(i, regSDMA_CNTL, temp);
>
> if (amdgpu_ip_version(adev, SDMA0_HWIP, 0) < IP_VERSION(4, 4, 5)) {
> /* enable context empty interrupt during initialization */
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2025-06-16 13:51 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2025-06-16 11:43 [PATCH] drm/amdgpu: Fix SDMA UTC_L1 handling during start/stop sequences Jesse Zhang
2025-06-16 13:51 ` Philip Yang
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).