[PATCH] drm/amdgpu: enable 48-bit IH timestamp counter

[Sierra Guiza, Alejandro (Alex)]

[AMD Public Use]

I just added support for vega10_ih too.

Regards,
Alex

> -----Original Message-----
> From: Sierra Guiza, Alejandro (Alex) <Alex.Sierra at amd.com>
> Sent: Tuesday, November 10, 2020 11:55 AM
> To: amd-gfx at lists.freedesktop.org
> Cc: Koenig, Christian <Christian.Koenig at amd.com>; Kuehling, Felix
> <Felix.Kuehling at amd.com>; Sierra Guiza, Alejandro (Alex)
> <Alex.Sierra at amd.com>
> Subject: [PATCH] drm/amdgpu: enable 48-bit IH timestamp counter
> 
> By default this timestamp is based on a 32 bit counter.
> This is used by the amdgpu_gmc_filter_faults, to avoid process the same
> interrupt in retry configuration.
> Apparently there's a problem when the timestamp coming from IH overflows
> and compares against timestamp coming from the the hash table.
> This patch only extends the time overflow from 10 minutes to aprx 455 days.
> 
> Signed-off-by: Alex Sierra <alex.sierra at amd.com>
> ---
>  drivers/gpu/drm/amd/amdgpu/navi10_ih.c | 6 ++++++
> drivers/gpu/drm/amd/amdgpu/vega10_ih.c | 6 ++++++
>  2 files changed, 12 insertions(+)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
> b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
> index 837769fcb35b..bda916f33805 100644
> --- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
> +++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
> @@ -94,6 +94,8 @@ static void navi10_ih_enable_interrupts(struct
> amdgpu_device *adev)
> 
>  	ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, RB_ENABLE, 1);
>  	ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, ENABLE_INTR,
> 1);
> +	ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL,
> +				   RB_GPU_TS_ENABLE, 1);
>  	if (amdgpu_sriov_vf(adev) && adev->asic_type < CHIP_NAVI10) {
>  		if (psp_reg_program(&adev->psp, PSP_REG_IH_RB_CNTL,
> ih_rb_cntl)) {
>  			DRM_ERROR("PSP program IH_RB_CNTL failed!\n");
> @@ -109,6 +111,8 @@ static void navi10_ih_enable_interrupts(struct
> amdgpu_device *adev)
>  		ih_rb_cntl = RREG32_SOC15(OSSSYS, 0,
> mmIH_RB_CNTL_RING1);
>  		ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL_RING1,
>  					   RB_ENABLE, 1);
> +		ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL_RING1,
> +					   RB_GPU_TS_ENABLE, 1);
>  		if (amdgpu_sriov_vf(adev) && adev->asic_type <
> CHIP_NAVI10) {
>  			if (psp_reg_program(&adev->psp,
> PSP_REG_IH_RB_CNTL_RING1,
>  						ih_rb_cntl)) {
> @@ -125,6 +129,8 @@ static void navi10_ih_enable_interrupts(struct
> amdgpu_device *adev)
>  		ih_rb_cntl = RREG32_SOC15(OSSSYS, 0,
> mmIH_RB_CNTL_RING2);
>  		ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL_RING2,
>  					   RB_ENABLE, 1);
> +		ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL_RING2,
> +					   RB_GPU_TS_ENABLE, 1);
>  		if (amdgpu_sriov_vf(adev) && adev->asic_type <
> CHIP_NAVI10) {
>  			if (psp_reg_program(&adev->psp,
> PSP_REG_IH_RB_CNTL_RING2,
>  						ih_rb_cntl)) {
> diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
> b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
> index 407c6093c2ec..35d68bc5d95e 100644
> --- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
> +++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
> @@ -50,6 +50,8 @@ static void vega10_ih_enable_interrupts(struct
> amdgpu_device *adev)
> 
>  	ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, RB_ENABLE, 1);
>  	ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, ENABLE_INTR,
> 1);
> +	ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL,
> +				   RB_GPU_TS_ENABLE, 1);
>  	if (amdgpu_sriov_vf(adev)) {
>  		if (psp_reg_program(&adev->psp, PSP_REG_IH_RB_CNTL,
> ih_rb_cntl)) {
>  			DRM_ERROR("PSP program IH_RB_CNTL failed!\n");
> @@ -64,6 +66,8 @@ static void vega10_ih_enable_interrupts(struct
> amdgpu_device *adev)
>  		ih_rb_cntl = RREG32_SOC15(OSSSYS, 0,
> mmIH_RB_CNTL_RING1);
>  		ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL_RING1,
>  					   RB_ENABLE, 1);
> +		ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL_RING1,
> +					   RB_GPU_TS_ENABLE, 1);
>  		if (amdgpu_sriov_vf(adev)) {
>  			if (psp_reg_program(&adev->psp,
> PSP_REG_IH_RB_CNTL_RING1,
>  						ih_rb_cntl)) {
> @@ -80,6 +84,8 @@ static void vega10_ih_enable_interrupts(struct
> amdgpu_device *adev)
>  		ih_rb_cntl = RREG32_SOC15(OSSSYS, 0,
> mmIH_RB_CNTL_RING2);
>  		ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL_RING2,
>  					   RB_ENABLE, 1);
> +		ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL_RING2,
> +					   RB_GPU_TS_ENABLE, 1);
>  		if (amdgpu_sriov_vf(adev)) {
>  			if (psp_reg_program(&adev->psp,
> PSP_REG_IH_RB_CNTL_RING2,
>  						ih_rb_cntl)) {
> --
> 2.17.1