summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c75
1 files changed, 46 insertions, 29 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index f7e66bf0f647..ec90c62078d9 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -49,8 +49,6 @@
#include "mmhub_v2_0.h"
#include "athub_v2_0.h"
#include "athub_v2_1.h"
-/* XXX Move this macro to navi10 header file, which is like vid.h for VI.*/
-#define AMDGPU_NUM_OF_VMIDS 8
#if 0
static const struct soc15_reg_golden golden_settings_navi10_hdp[] =
@@ -88,7 +86,7 @@ gmc_v10_0_vm_fault_interrupt_state(struct amdgpu_device *adev,
/* MM HUB */
hub = &adev->vmhub[AMDGPU_MMHUB_0];
for (i = 0; i < 16; i++) {
- reg = hub->vm_context0_cntl + i;
+ reg = hub->vm_context0_cntl + hub->ctx_distance * i;
tmp = RREG32(reg);
tmp &= ~bits[AMDGPU_MMHUB_0];
WREG32(reg, tmp);
@@ -97,7 +95,7 @@ gmc_v10_0_vm_fault_interrupt_state(struct amdgpu_device *adev,
/* GFX HUB */
hub = &adev->vmhub[AMDGPU_GFXHUB_0];
for (i = 0; i < 16; i++) {
- reg = hub->vm_context0_cntl + i;
+ reg = hub->vm_context0_cntl + hub->ctx_distance * i;
tmp = RREG32(reg);
tmp &= ~bits[AMDGPU_GFXHUB_0];
WREG32(reg, tmp);
@@ -107,7 +105,7 @@ gmc_v10_0_vm_fault_interrupt_state(struct amdgpu_device *adev,
/* MM HUB */
hub = &adev->vmhub[AMDGPU_MMHUB_0];
for (i = 0; i < 16; i++) {
- reg = hub->vm_context0_cntl + i;
+ reg = hub->vm_context0_cntl + hub->ctx_distance * i;
tmp = RREG32(reg);
tmp |= bits[AMDGPU_MMHUB_0];
WREG32(reg, tmp);
@@ -116,7 +114,7 @@ gmc_v10_0_vm_fault_interrupt_state(struct amdgpu_device *adev,
/* GFX HUB */
hub = &adev->vmhub[AMDGPU_GFXHUB_0];
for (i = 0; i < 16; i++) {
- reg = hub->vm_context0_cntl + i;
+ reg = hub->vm_context0_cntl + hub->ctx_distance * i;
tmp = RREG32(reg);
tmp |= bits[AMDGPU_GFXHUB_0];
WREG32(reg, tmp);
@@ -285,7 +283,8 @@ static void gmc_v10_0_flush_vm_hub(struct amdgpu_device *adev, uint32_t vmid,
if (use_semaphore) {
for (i = 0; i < adev->usec_timeout; i++) {
/* a read return value of 1 means semaphore acuqire */
- tmp = RREG32_NO_KIQ(hub->vm_inv_eng0_sem + eng);
+ tmp = RREG32_NO_KIQ(hub->vm_inv_eng0_sem +
+ hub->eng_distance * eng);
if (tmp & 0x1)
break;
udelay(1);
@@ -295,18 +294,19 @@ static void gmc_v10_0_flush_vm_hub(struct amdgpu_device *adev, uint32_t vmid,
DRM_ERROR("Timeout waiting for sem acquire in VM flush!\n");
}
- WREG32_NO_KIQ(hub->vm_inv_eng0_req + eng, inv_req);
+ WREG32_NO_KIQ(hub->vm_inv_eng0_req + hub->eng_distance * eng, inv_req);
/*
* Issue a dummy read to wait for the ACK register to be cleared
* to avoid a false ACK due to the new fast GRBM interface.
*/
if (vmhub == AMDGPU_GFXHUB_0)
- RREG32_NO_KIQ(hub->vm_inv_eng0_req + eng);
+ RREG32_NO_KIQ(hub->vm_inv_eng0_req + hub->eng_distance * eng);
/* Wait for ACK with a delay.*/
for (i = 0; i < adev->usec_timeout; i++) {
- tmp = RREG32_NO_KIQ(hub->vm_inv_eng0_ack + eng);
+ tmp = RREG32_NO_KIQ(hub->vm_inv_eng0_ack +
+ hub->eng_distance * eng);
tmp &= 1 << vmid;
if (tmp)
break;
@@ -320,7 +320,8 @@ static void gmc_v10_0_flush_vm_hub(struct amdgpu_device *adev, uint32_t vmid,
* add semaphore release after invalidation,
* write with 0 means semaphore release
*/
- WREG32_NO_KIQ(hub->vm_inv_eng0_sem + eng, 0);
+ WREG32_NO_KIQ(hub->vm_inv_eng0_sem +
+ hub->eng_distance * eng, 0);
spin_unlock(&adev->gmc.invalidate_lock);
@@ -360,8 +361,8 @@ static void gmc_v10_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
struct amdgpu_vmhub *hub = &adev->vmhub[vmhub];
const unsigned eng = 17;
u32 inv_req = gmc_v10_0_get_invalidate_req(vmid, flush_type);
- u32 req = hub->vm_inv_eng0_req + eng;
- u32 ack = hub->vm_inv_eng0_ack + eng;
+ u32 req = hub->vm_inv_eng0_req + hub->eng_distance * eng;
+ u32 ack = hub->vm_inv_eng0_ack + hub->eng_distance * eng;
amdgpu_virt_kiq_reg_write_reg_wait(adev, req, ack, inv_req,
1 << vmid);
@@ -504,16 +505,21 @@ static uint64_t gmc_v10_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
if (use_semaphore)
/* a read return value of 1 means semaphore acuqire */
amdgpu_ring_emit_reg_wait(ring,
- hub->vm_inv_eng0_sem + eng, 0x1, 0x1);
+ hub->vm_inv_eng0_sem +
+ hub->eng_distance * eng, 0x1, 0x1);
- amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_lo32 + (2 * vmid),
+ amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_lo32 +
+ (hub->ctx_addr_distance * vmid),
lower_32_bits(pd_addr));
- amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_hi32 + (2 * vmid),
+ amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_hi32 +
+ (hub->ctx_addr_distance * vmid),
upper_32_bits(pd_addr));
- amdgpu_ring_emit_reg_write_reg_wait(ring, hub->vm_inv_eng0_req + eng,
- hub->vm_inv_eng0_ack + eng,
+ amdgpu_ring_emit_reg_write_reg_wait(ring, hub->vm_inv_eng0_req +
+ hub->eng_distance * eng,
+ hub->vm_inv_eng0_ack +
+ hub->eng_distance * eng,
req, 1 << vmid);
/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
@@ -522,7 +528,8 @@ static uint64_t gmc_v10_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
* add semaphore release after invalidation,
* write with 0 means semaphore release
*/
- amdgpu_ring_emit_wreg(ring, hub->vm_inv_eng0_sem + eng, 0);
+ amdgpu_ring_emit_wreg(ring, hub->vm_inv_eng0_sem +
+ hub->eng_distance * eng, 0);
return pd_addr;
}
@@ -686,7 +693,8 @@ static void gmc_v10_0_vram_gtt_location(struct amdgpu_device *adev,
{
u64 base = 0;
- if (adev->asic_type == CHIP_SIENNA_CICHLID)
+ if (adev->asic_type == CHIP_SIENNA_CICHLID ||
+ adev->asic_type == CHIP_NAVY_FLOUNDER)
base = gfxhub_v2_1_get_fb_location(adev);
else
base = gfxhub_v2_0_get_fb_location(adev);
@@ -698,7 +706,8 @@ static void gmc_v10_0_vram_gtt_location(struct amdgpu_device *adev,
amdgpu_gmc_gart_location(adev, mc);
/* base offset of vram pages */
- if (adev->asic_type == CHIP_SIENNA_CICHLID)
+ if (adev->asic_type == CHIP_SIENNA_CICHLID ||
+ adev->asic_type == CHIP_NAVY_FLOUNDER)
adev->vm_manager.vram_base_offset = gfxhub_v2_1_get_mc_fb_offset(adev);
else
adev->vm_manager.vram_base_offset = gfxhub_v2_0_get_mc_fb_offset(adev);
@@ -746,6 +755,7 @@ static int gmc_v10_0_mc_init(struct amdgpu_device *adev)
case CHIP_NAVI14:
case CHIP_NAVI12:
case CHIP_SIENNA_CICHLID:
+ case CHIP_NAVY_FLOUNDER:
default:
adev->gmc.gart_size = 512ULL << 20;
break;
@@ -814,7 +824,8 @@ static int gmc_v10_0_sw_init(void *handle)
int r, vram_width = 0, vram_type = 0, vram_vendor = 0;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- if (adev->asic_type == CHIP_SIENNA_CICHLID)
+ if (adev->asic_type == CHIP_SIENNA_CICHLID ||
+ adev->asic_type == CHIP_NAVY_FLOUNDER)
gfxhub_v2_1_init(adev);
else
gfxhub_v2_0_init(adev);
@@ -840,6 +851,7 @@ static int gmc_v10_0_sw_init(void *handle)
case CHIP_NAVI14:
case CHIP_NAVI12:
case CHIP_SIENNA_CICHLID:
+ case CHIP_NAVY_FLOUNDER:
adev->num_vmhubs = 2;
/*
* To fulfill 4-level page support,
@@ -905,8 +917,7 @@ static int gmc_v10_0_sw_init(void *handle)
* amdgpu graphics/compute will use VMIDs 1-7
* amdkfd will use VMIDs 8-15
*/
- adev->vm_manager.id_mgr[AMDGPU_GFXHUB_0].num_ids = AMDGPU_NUM_OF_VMIDS;
- adev->vm_manager.id_mgr[AMDGPU_MMHUB_0].num_ids = AMDGPU_NUM_OF_VMIDS;
+ adev->vm_manager.first_kfd_vmid = 8;
amdgpu_vm_manager_init(adev);
@@ -945,6 +956,7 @@ static void gmc_v10_0_init_golden_registers(struct amdgpu_device *adev)
case CHIP_NAVI14:
case CHIP_NAVI12:
case CHIP_SIENNA_CICHLID:
+ case CHIP_NAVY_FLOUNDER:
break;
default:
break;
@@ -971,7 +983,8 @@ static int gmc_v10_0_gart_enable(struct amdgpu_device *adev)
if (r)
return r;
- if (adev->asic_type == CHIP_SIENNA_CICHLID)
+ if (adev->asic_type == CHIP_SIENNA_CICHLID ||
+ adev->asic_type == CHIP_NAVY_FLOUNDER)
r = gfxhub_v2_1_gart_enable(adev);
else
r = gfxhub_v2_0_gart_enable(adev);
@@ -995,7 +1008,8 @@ static int gmc_v10_0_gart_enable(struct amdgpu_device *adev)
value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ?
false : true;
- if (adev->asic_type == CHIP_SIENNA_CICHLID)
+ if (adev->asic_type == CHIP_SIENNA_CICHLID ||
+ adev->asic_type == CHIP_NAVY_FLOUNDER)
gfxhub_v2_1_set_fault_enable_default(adev, value);
else
gfxhub_v2_0_set_fault_enable_default(adev, value);
@@ -1036,7 +1050,8 @@ static int gmc_v10_0_hw_init(void *handle)
*/
static void gmc_v10_0_gart_disable(struct amdgpu_device *adev)
{
- if (adev->asic_type == CHIP_SIENNA_CICHLID)
+ if (adev->asic_type == CHIP_SIENNA_CICHLID ||
+ adev->asic_type == CHIP_NAVY_FLOUNDER)
gfxhub_v2_1_gart_disable(adev);
else
gfxhub_v2_0_gart_disable(adev);
@@ -1110,7 +1125,8 @@ static int gmc_v10_0_set_clockgating_state(void *handle,
if (r)
return r;
- if (adev->asic_type == CHIP_SIENNA_CICHLID)
+ if (adev->asic_type == CHIP_SIENNA_CICHLID ||
+ adev->asic_type == CHIP_NAVY_FLOUNDER)
return athub_v2_1_set_clockgating(adev, state);
else
return athub_v2_0_set_clockgating(adev, state);
@@ -1122,7 +1138,8 @@ static void gmc_v10_0_get_clockgating_state(void *handle, u32 *flags)
mmhub_v2_0_get_clockgating(adev, flags);
- if (adev->asic_type == CHIP_SIENNA_CICHLID)
+ if (adev->asic_type == CHIP_SIENNA_CICHLID ||
+ adev->asic_type == CHIP_NAVY_FLOUNDER)
athub_v2_1_get_clockgating(adev, flags);
else
athub_v2_0_get_clockgating(adev, flags);
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-07 09:40:25 +0000