[AMD Official Use Only]
Hey Alex,
This change was based on the fact that amd-mainline-dkms-5.13 calls get_xgmi_info() in gmc_v9_0_early_init(). But I can see that drm-next it's instead called in gmc_v9_0_sw_init(). So, I'm not sure whats the correct behavior. But I do agree that the change is kind of ugly. I don't know where else to put it if we do need to call get_xgmi_info() in early_init.
Thanks,
Victor
-----Original Message-----
From: Alex Deucher <alexdeucher@xxxxxxxxx>
Sent: Wednesday, December 15, 2021 4:38 PM
To: Skvortsov, Victor <Victor.Skvortsov@xxxxxxx>
Cc: amd-gfx list <amd-gfx@xxxxxxxxxxxxxxxxxxxxx>; Deng, Emily <Emily.Deng@xxxxxxx>; Liu, Monk <Monk.Liu@xxxxxxx>; Ming, Davis <Davis.Ming@xxxxxxx>; Liu, Shaoyun <Shaoyun.Liu@xxxxxxx>; Zhou, Peng Ju <PengJu.Zhou@xxxxxxx>; Chen, JingWen <JingWen.Chen2@xxxxxxx>; Chen, Horace <Horace.Chen@xxxxxxx>; Nieto, David M <David.Nieto@xxxxxxx>
Subject: Re: [PATCH 4/5] drm/amdgpu: Initialize Aldebaran RLC function pointers
[CAUTION: External Email]
On Wed, Dec 15, 2021 at 1:56 PM Victor Skvortsov <victor.skvortsov@xxxxxxx> wrote:
>
> In SRIOV, RLC function pointers must be initialized early as we rely
> on the RLCG interface for all GC register access.
>
> Signed-off-by: Victor Skvortsov <victor.skvortsov@xxxxxxx>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c | 2 ++
> drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 3 +--
> drivers/gpu/drm/amd/amdgpu/gfx_v9_0.h | 2 ++
> 3 files changed, 5 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
> index 65e1f6cc59dd..1bc92a38d124 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
> @@ -844,6 +844,8 @@ static int amdgpu_discovery_set_gc_ip_blocks(struct amdgpu_device *adev)
> case IP_VERSION(9, 4, 1):
> case IP_VERSION(9, 4, 2):
> amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block);
> + if (amdgpu_sriov_vf(adev) && adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 4, 2))
> + gfx_v9_0_set_rlc_funcs(adev);
amdgpu_discovery.c is IP independent. I'd rather not add random IP specific function calls. gfx_v9_0_set_rlc_funcs() already gets called in gfx_v9_0_early_init(). Is that not early enough? In general we shouldn't be touching the hardware much if at all in early_init.
Alex
> break;
> case IP_VERSION(10, 1, 10):
> case IP_VERSION(10, 1, 2):
> diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
> b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
> index edb3e3b08eed..d252b06efa43 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
> @@ -816,7 +816,6 @@ static void gfx_v9_0_sriov_wreg(struct
> amdgpu_device *adev, u32 offset, static void
> gfx_v9_0_set_ring_funcs(struct amdgpu_device *adev); static void
> gfx_v9_0_set_irq_funcs(struct amdgpu_device *adev); static void
> gfx_v9_0_set_gds_init(struct amdgpu_device *adev); -static void
> gfx_v9_0_set_rlc_funcs(struct amdgpu_device *adev); static int gfx_v9_0_get_cu_info(struct amdgpu_device *adev,
> struct amdgpu_cu_info *cu_info);
> static uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device
> *adev); @@ -7066,7 +7065,7 @@ static void gfx_v9_0_set_irq_funcs(struct amdgpu_device *adev)
> adev->gfx.cp_ecc_error_irq.funcs =
> &gfx_v9_0_cp_ecc_error_irq_funcs; }
>
> -static void gfx_v9_0_set_rlc_funcs(struct amdgpu_device *adev)
> +void gfx_v9_0_set_rlc_funcs(struct amdgpu_device *adev)
> {
> switch (adev->ip_versions[GC_HWIP][0]) {
> case IP_VERSION(9, 0, 1):
> diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.h
> b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.h
> index dfe8d4841f58..1817e252354f 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.h
> +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.h
> @@ -29,4 +29,6 @@ extern const struct amdgpu_ip_block_version
> gfx_v9_0_ip_block; void gfx_v9_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num,
> u32 instance);
>
> +void gfx_v9_0_set_rlc_funcs(struct amdgpu_device *adev);
> +
> #endif
> --
> 2.25.1
>
