From: Junwei Zhang <Jerry.Zhang@xxxxxxx>
Signed-off-by: Flora Cui <Flora.Cui at amd.com>
Reviewed-by: Jammy Zhou <Jammy.Zhou at amd.com>
Reviewed-by: Alex Deucher <alexander.deucher at amd.com>
Signed-off-by: Alex Deucher <alexander.deucher at amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 6 ++++++
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 24 +++++++++++++++++++++---
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 17 +++++++++++++----
drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c | 7 +++++++
drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c | 7 +++++++
5 files changed, 54 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 57eaf71..b2ff9e1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -165,6 +165,12 @@ struct amdgpu_vm_manager {
/* partial resident texture handling */
spinlock_t prt_lock;
atomic_t num_prt_users;
+
+ /* vm aperture */
+ u64 shared_aperture_start;
+ u64 shared_aperture_end;
+ u64 private_aperture_start;
+ u64 private_aperture_end;
};
void amdgpu_vm_manager_init(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index e471c08..cd6a6ec 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -1889,7 +1889,8 @@ static void gfx_v7_0_config_init(struct amdgpu_device *adev)
*/
static void gfx_v7_0_gpu_init(struct amdgpu_device *adev)
{
- u32 tmp, sh_mem_cfg;
+ u32 sh_mem_cfg, sh_static_mem_cfg, sh_mem_base;
+ u32 tmp;
int i;
WREG32(mmGRBM_CNTL, (0xff << GRBM_CNTL__READ_TIMEOUT__SHIFT));
@@ -1920,15 +1921,32 @@ static void gfx_v7_0_gpu_init(struct amdgpu_device *adev)
/* where to put LDS, scratch, GPUVM in FSA64 space */
sh_mem_cfg = REG_SET_FIELD(0, SH_MEM_CONFIG, ALIGNMENT_MODE,
SH_MEM_ALIGNMENT_MODE_UNALIGNED);
+ sh_mem_cfg = REG_SET_FIELD(sh_mem_cfg, SH_MEM_CONFIG, DEFAULT_MTYPE,
+ MTYPE_NC);
+ sh_mem_cfg = REG_SET_FIELD(sh_mem_cfg, SH_MEM_CONFIG, APE1_MTYPE,
+ MTYPE_UC);
+ sh_mem_cfg = REG_SET_FIELD(sh_mem_cfg, SH_MEM_CONFIG, PRIVATE_ATC, 0);
+
+ sh_static_mem_cfg = REG_SET_FIELD(0, SH_STATIC_MEM_CONFIG,
+ SWIZZLE_ENABLE, 1);
+ sh_static_mem_cfg = REG_SET_FIELD(sh_static_mem_cfg, SH_STATIC_MEM_CONFIG,
+ ELEMENT_SIZE, 1);
+ sh_static_mem_cfg = REG_SET_FIELD(sh_static_mem_cfg, SH_STATIC_MEM_CONFIG,
+ INDEX_STRIDE, 3);
mutex_lock(&adev->srbm_mutex);
- for (i = 0; i < 16; i++) {
+ for (i = 0; i < adev->vm_manager.num_ids; i++) {
+ if (i == 0)
+ sh_mem_base = 0;
+ else
+ sh_mem_base = adev->vm_manager.shared_aperture_start >> 48;
cik_srbm_select(adev, 0, 0, 0, i);
/* CP and shaders */
WREG32(mmSH_MEM_CONFIG, sh_mem_cfg);
WREG32(mmSH_MEM_APE1_BASE, 1);
WREG32(mmSH_MEM_APE1_LIMIT, 0);
- WREG32(mmSH_MEM_BASES, 0);
+ WREG32(mmSH_MEM_BASES, sh_mem_base);
+ WREG32(mmSH_STATIC_MEM_CONFIG, sh_static_mem_cfg);
}
cik_srbm_select(adev, 0, 0, 0, 0);
mutex_unlock(&adev->srbm_mutex);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 5dcf8db..af6294f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -3859,7 +3859,7 @@ static void gfx_v8_0_config_init(struct amdgpu_device *adev)
static void gfx_v8_0_gpu_init(struct amdgpu_device *adev)
{
- u32 tmp;
+ u32 tmp, sh_static_mem_cfg;
int i;
WREG32_FIELD(GRBM_CNTL, READ_TIMEOUT, 0xFF);
@@ -3874,8 +3874,14 @@ static void gfx_v8_0_gpu_init(struct amdgpu_device *adev)
/* XXX SH_MEM regs */
/* where to put LDS, scratch, GPUVM in FSA64 space */
+ sh_static_mem_cfg = REG_SET_FIELD(0, SH_STATIC_MEM_CONFIG,
+ SWIZZLE_ENABLE, 1);
+ sh_static_mem_cfg = REG_SET_FIELD(sh_static_mem_cfg, SH_STATIC_MEM_CONFIG,
+ ELEMENT_SIZE, 1);
+ sh_static_mem_cfg = REG_SET_FIELD(sh_static_mem_cfg, SH_STATIC_MEM_CONFIG,
+ INDEX_STRIDE, 3);
mutex_lock(&adev->srbm_mutex);
- for (i = 0; i < 16; i++) {
+ for (i = 0; i < adev->vm_manager.num_ids; i++) {
vi_srbm_select(adev, 0, 0, 0, i);
/* CP and shaders */
if (i == 0) {
@@ -3884,17 +3890,20 @@ static void gfx_v8_0_gpu_init(struct amdgpu_device *adev)
tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, ALIGNMENT_MODE,
SH_MEM_ALIGNMENT_MODE_UNALIGNED);
WREG32(mmSH_MEM_CONFIG, tmp);
+ WREG32(mmSH_MEM_BASES, 0);
} else {
tmp = REG_SET_FIELD(0, SH_MEM_CONFIG, DEFAULT_MTYPE, MTYPE_NC);
- tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, APE1_MTYPE, MTYPE_NC);
+ tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, APE1_MTYPE, MTYPE_UC);
tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, ALIGNMENT_MODE,
SH_MEM_ALIGNMENT_MODE_UNALIGNED);
WREG32(mmSH_MEM_CONFIG, tmp);
+ tmp = adev->vm_manager.shared_aperture_start >> 48;
+ WREG32(mmSH_MEM_BASES, tmp);
}
WREG32(mmSH_MEM_APE1_BASE, 1);
WREG32(mmSH_MEM_APE1_LIMIT, 0);
- WREG32(mmSH_MEM_BASES, 0);
+ WREG32(mmSH_STATIC_MEM_CONFIG, sh_static_mem_cfg);
}
vi_srbm_select(adev, 0, 0, 0, 0);
mutex_unlock(&adev->srbm_mutex);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 552bf6b..dc2b4c7 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -726,6 +726,13 @@ static int gmc_v7_0_vm_init(struct amdgpu_device *adev)
* amdkfd will use VMIDs 8-15
*/
adev->vm_manager.num_ids = AMDGPU_NUM_OF_VMIDS;
+ adev->vm_manager.shared_aperture_start = 0x2000000000000000ULL;
+ adev->vm_manager.shared_aperture_end =
+ adev->vm_manager.shared_aperture_start + (4ULL << 30) - 1;
+ adev->vm_manager.private_aperture_start =
+ adev->vm_manager.shared_aperture_end + 1;
+ adev->vm_manager.private_aperture_end =
+ adev->vm_manager.private_aperture_start + (4ULL << 30) - 1;
amdgpu_vm_manager_init(adev);
/* base offset of vram pages */
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index f2bd016..81b1a49 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -857,6 +857,13 @@ static int gmc_v8_0_vm_init(struct amdgpu_device *adev)
* amdkfd will use VMIDs 8-15
*/
adev->vm_manager.num_ids = AMDGPU_NUM_OF_VMIDS;
+ adev->vm_manager.shared_aperture_start = 0x2000000000000000ULL;
+ adev->vm_manager.shared_aperture_end =
+ adev->vm_manager.shared_aperture_start + (4ULL << 30) - 1;
+ adev->vm_manager.private_aperture_start =
+ adev->vm_manager.shared_aperture_end + 1;
+ adev->vm_manager.private_aperture_end =
+ adev->vm_manager.private_aperture_start + (4ULL << 30) - 1;
amdgpu_vm_manager_init(adev);
/* base offset of vram pages */
--
2.5.5
