@@ -1494,24 +1494,9 @@ int cayman_vm_bind(struct radeon_device *rdev, struct radeon_vm *vm, int id)
WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR + (id << 2), 0);
WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR + (id << 2), vm->last_pfn);
WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (id << 2), vm->pt_gpu_addr >> 12);
- /* flush hdp cache */
- WREG32(HDP_MEM_COHERENCY_FLUSH_CNTL, 0x1);
- /* bits 0-7 are the VM contexts0-7 */
- WREG32(VM_INVALIDATE_REQUEST, 1 << id);
return 0;
}
-void cayman_vm_tlb_flush(struct radeon_device *rdev, struct radeon_vm *vm)
-{
- if (vm->id == -1)
- return;
-
- /* flush hdp cache */
- WREG32(HDP_MEM_COHERENCY_FLUSH_CNTL, 0x1);
- /* bits 0-7 are the VM contexts0-7 */
- WREG32(VM_INVALIDATE_REQUEST, 1 << vm->id);
-}
-
#define R600_PTE_VALID (1 << 0)
#define R600_PTE_SYSTEM (1 << 1)
#define R600_PTE_SNOOPED (1 << 2)
@@ -1543,3 +1528,19 @@ void cayman_vm_set_page(struct radeon_device *rdev, struct radeon_vm *vm,
addr |= flags;
writeq(addr, ptr + (pfn * 8));
}
+
+void cayman_vm_flush(struct radeon_device *rdev, struct radeon_ib *ib)
+{
+ struct radeon_ring *ring = &rdev->ring[ib->ring];
+
+ if (!ib->vm || ib->vm->id == -1)
+ return;
+
+ /* flush hdp cache */
+ radeon_ring_write(ring, PACKET0(HDP_MEM_COHERENCY_FLUSH_CNTL, 0));
+ radeon_ring_write(ring, 0x1);
+
+ /* bits 0-7 are the VM contexts0-7 */
+ radeon_ring_write(ring, PACKET0(VM_INVALIDATE_REQUEST, 0));
+ radeon_ring_write(ring, 1 << ib->vm->id);
+}
@@ -658,6 +658,8 @@ struct radeon_vm {
struct mutex mutex;
/* last fence for cs using this vm */
struct radeon_fence *fence;
+ /* last flush or NULL if we still need to flush */
+ struct radeon_fence *last_flush;
};
struct radeon_vm_manager {
@@ -1135,7 +1137,6 @@ struct radeon_asic {
int (*init)(struct radeon_device *rdev);
void (*fini)(struct radeon_device *rdev);
int (*bind)(struct radeon_device *rdev, struct radeon_vm *vm, int id);
- void (*tlb_flush)(struct radeon_device *rdev, struct radeon_vm *vm);
uint32_t (*page_flags)(struct radeon_device *rdev,
struct radeon_vm *vm,
uint32_t flags);
@@ -1154,6 +1155,7 @@ struct radeon_asic {
int (*ring_test)(struct radeon_device *rdev, struct radeon_ring *cp);
int (*ib_test)(struct radeon_device *rdev, struct radeon_ring *cp);
bool (*is_lockup)(struct radeon_device *rdev, struct radeon_ring *cp);
+ void (*vm_flush)(struct radeon_device *rdev, struct radeon_ib *ib);
} ring[RADEON_NUM_RINGS];
/* irqs */
struct {
@@ -1696,7 +1698,6 @@ void radeon_ring_write(struct radeon_ring *ring, uint32_t v);
#define radeon_asic_vm_init(rdev) (rdev)->asic->vm.init((rdev))
#define radeon_asic_vm_fini(rdev) (rdev)->asic->vm.fini((rdev))
#define radeon_asic_vm_bind(rdev, v, id) (rdev)->asic->vm.bind((rdev), (v), (id))
-#define radeon_asic_vm_tlb_flush(rdev, v) (rdev)->asic->vm.tlb_flush((rdev), (v))
#define radeon_asic_vm_page_flags(rdev, v, flags) (rdev)->asic->vm.page_flags((rdev), (v), (flags))
#define radeon_asic_vm_set_page(rdev, v, pfn, addr, flags) (rdev)->asic->vm.set_page((rdev), (v), (pfn), (addr), (flags))
#define radeon_ring_start(rdev, r, cp) (rdev)->asic->ring[(r)].ring_start((rdev), (cp))
@@ -1705,6 +1706,7 @@ void radeon_ring_write(struct radeon_ring *ring, uint32_t v);
#define radeon_ring_ib_execute(rdev, r, ib) (rdev)->asic->ring[(r)].ib_execute((rdev), (ib))
#define radeon_ring_ib_parse(rdev, r, ib) (rdev)->asic->ring[(r)].ib_parse((rdev), (ib))
#define radeon_ring_is_lockup(rdev, r, cp) (rdev)->asic->ring[(r)].is_lockup((rdev), (cp))
+#define radeon_ring_vm_flush(rdev, r, ib) (rdev)->asic->ring[(r)].vm_flush((rdev), (ib))
#define radeon_irq_set(rdev) (rdev)->asic->irq.set((rdev))
#define radeon_irq_process(rdev) (rdev)->asic->irq.process((rdev))
#define radeon_get_vblank_counter(rdev, crtc) (rdev)->asic->display.get_vblank_counter((rdev), (crtc))
@@ -1360,7 +1360,6 @@ static struct radeon_asic cayman_asic = {
.init = &cayman_vm_init,
.fini = &cayman_vm_fini,
.bind = &cayman_vm_bind,
- .tlb_flush = &cayman_vm_tlb_flush,
.page_flags = &cayman_vm_page_flags,
.set_page = &cayman_vm_set_page,
},
@@ -1374,6 +1373,7 @@ static struct radeon_asic cayman_asic = {
.ring_test = &r600_ring_test,
.ib_test = &r600_ib_test,
.is_lockup = &evergreen_gpu_is_lockup,
+ .vm_flush = &cayman_vm_flush,
},
[CAYMAN_RING_TYPE_CP1_INDEX] = {
.ib_execute = &cayman_ring_ib_execute,
@@ -1384,6 +1384,7 @@ static struct radeon_asic cayman_asic = {
.ring_test = &r600_ring_test,
.ib_test = &r600_ib_test,
.is_lockup = &evergreen_gpu_is_lockup,
+ .vm_flush = &cayman_vm_flush,
},
[CAYMAN_RING_TYPE_CP2_INDEX] = {
.ib_execute = &cayman_ring_ib_execute,
@@ -1394,6 +1395,7 @@ static struct radeon_asic cayman_asic = {
.ring_test = &r600_ring_test,
.ib_test = &r600_ib_test,
.is_lockup = &evergreen_gpu_is_lockup,
+ .vm_flush = &cayman_vm_flush,
}
},
.irq = {
@@ -1462,7 +1464,6 @@ static struct radeon_asic trinity_asic = {
.init = &cayman_vm_init,
.fini = &cayman_vm_fini,
.bind = &cayman_vm_bind,
- .tlb_flush = &cayman_vm_tlb_flush,
.page_flags = &cayman_vm_page_flags,
.set_page = &cayman_vm_set_page,
},
@@ -1476,6 +1477,7 @@ static struct radeon_asic trinity_asic = {
.ring_test = &r600_ring_test,
.ib_test = &r600_ib_test,
.is_lockup = &evergreen_gpu_is_lockup,
+ .vm_flush = &cayman_vm_flush,
},
[CAYMAN_RING_TYPE_CP1_INDEX] = {
.ib_execute = &cayman_ring_ib_execute,
@@ -1486,6 +1488,7 @@ static struct radeon_asic trinity_asic = {
.ring_test = &r600_ring_test,
.ib_test = &r600_ib_test,
.is_lockup = &evergreen_gpu_is_lockup,
+ .vm_flush = &cayman_vm_flush,
},
[CAYMAN_RING_TYPE_CP2_INDEX] = {
.ib_execute = &cayman_ring_ib_execute,
@@ -1496,6 +1499,7 @@ static struct radeon_asic trinity_asic = {
.ring_test = &r600_ring_test,
.ib_test = &r600_ib_test,
.is_lockup = &evergreen_gpu_is_lockup,
+ .vm_flush = &cayman_vm_flush,
}
},
.irq = {
@@ -1564,7 +1568,6 @@ static struct radeon_asic si_asic = {
.init = &si_vm_init,
.fini = &si_vm_fini,
.bind = &si_vm_bind,
- .tlb_flush = &si_vm_tlb_flush,
.page_flags = &cayman_vm_page_flags,
.set_page = &cayman_vm_set_page,
},
@@ -1578,6 +1581,7 @@ static struct radeon_asic si_asic = {
.ring_test = &r600_ring_test,
.ib_test = &r600_ib_test,
.is_lockup = &si_gpu_is_lockup,
+ .vm_flush = &cayman_vm_flush,
},
[CAYMAN_RING_TYPE_CP1_INDEX] = {
.ib_execute = &si_ring_ib_execute,
@@ -1588,6 +1592,7 @@ static struct radeon_asic si_asic = {
.ring_test = &r600_ring_test,
.ib_test = &r600_ib_test,
.is_lockup = &si_gpu_is_lockup,
+ .vm_flush = &cayman_vm_flush,
},
[CAYMAN_RING_TYPE_CP2_INDEX] = {
.ib_execute = &si_ring_ib_execute,
@@ -1598,6 +1603,7 @@ static struct radeon_asic si_asic = {
.ring_test = &r600_ring_test,
.ib_test = &r600_ib_test,
.is_lockup = &si_gpu_is_lockup,
+ .vm_flush = &cayman_vm_flush,
}
},
.irq = {
@@ -440,7 +440,7 @@ int cayman_vm_init(struct radeon_device *rdev);
void cayman_vm_fini(struct radeon_device *rdev);
int cayman_vm_bind(struct radeon_device *rdev, struct radeon_vm *vm, int id);
void cayman_vm_unbind(struct radeon_device *rdev, struct radeon_vm *vm);
-void cayman_vm_tlb_flush(struct radeon_device *rdev, struct radeon_vm *vm);
+void cayman_vm_flush(struct radeon_device *rdev, struct radeon_ib *ib);
uint32_t cayman_vm_page_flags(struct radeon_device *rdev,
struct radeon_vm *vm,
uint32_t flags);
@@ -470,7 +470,6 @@ int si_vm_init(struct radeon_device *rdev);
void si_vm_fini(struct radeon_device *rdev);
int si_vm_bind(struct radeon_device *rdev, struct radeon_vm *vm, int id);
void si_vm_unbind(struct radeon_device *rdev, struct radeon_vm *vm);
-void si_vm_tlb_flush(struct radeon_device *rdev, struct radeon_vm *vm);
int si_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib);
#endif
@@ -484,6 +484,7 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev,
goto out;
}
radeon_cs_sync_rings(parser);
+ radeon_cs_sync_to(parser, vm->last_flush);
if ((rdev->family >= CHIP_TAHITI) &&
(parser->chunk_const_ib_idx != -1)) {
@@ -520,6 +520,7 @@ static void radeon_vm_unbind_locked(struct radeon_device *rdev,
break;
}
radeon_fence_unref(&vm->fence);
+ radeon_fence_unref(&vm->last_flush);
/* hw unbind */
rdev->vm_manager.use_bitmap &= ~(1 << vm->id);
@@ -639,6 +640,7 @@ retry_id:
/* do hw bind */
r = radeon_asic_vm_bind(rdev, vm, id);
+ radeon_fence_unref(&vm->last_flush);
if (r) {
radeon_sa_bo_free(rdev, &vm->sa_bo, NULL);
return r;
@@ -836,7 +838,7 @@ int radeon_vm_bo_update_pte(struct radeon_device *rdev,
}
radeon_asic_vm_set_page(rdev, bo_va->vm, i + pfn, addr, flags);
}
- radeon_asic_vm_tlb_flush(rdev, bo_va->vm);
+ radeon_fence_unref(&vm->last_flush);
return 0;
}
@@ -160,6 +160,10 @@ int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib,
if (!need_sync) {
radeon_semaphore_free(rdev, &ib->semaphore, NULL);
}
+ /* if we can't remember our last VM flush then flush now! */
+ if (ib->vm && !ib->vm->last_flush) {
+ radeon_ring_vm_flush(rdev, ib->ring, ib);
+ }
if (const_ib) {
radeon_ring_ib_execute(rdev, const_ib->ring, const_ib);
radeon_semaphore_free(rdev, &const_ib->semaphore, NULL);
@@ -174,6 +178,10 @@ int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib,
if (const_ib) {
const_ib->fence = radeon_fence_ref(ib->fence);
}
+ /* we just flushed the VM, remember that */
+ if (ib->vm && !ib->vm->last_flush) {
+ ib->vm->last_flush = radeon_fence_ref(ib->fence);
+ }
radeon_ring_unlock_commit(rdev, ring);
return 0;
}
@@ -2788,24 +2788,9 @@ int si_vm_bind(struct radeon_device *rdev, struct radeon_vm *vm, int id)
else
WREG32(VM_CONTEXT8_PAGE_TABLE_BASE_ADDR + ((id - 8) << 2),
vm->pt_gpu_addr >> 12);
- /* flush hdp cache */
- WREG32(HDP_MEM_COHERENCY_FLUSH_CNTL, 0x1);
- /* bits 0-15 are the VM contexts0-15 */
- WREG32(VM_INVALIDATE_REQUEST, 1 << id);
return 0;
}
-void si_vm_tlb_flush(struct radeon_device *rdev, struct radeon_vm *vm)
-{
- if (vm->id == -1)
- return;
-
- /* flush hdp cache */
- WREG32(HDP_MEM_COHERENCY_FLUSH_CNTL, 0x1);
- /* bits 0-15 are the VM contexts0-15 */
- WREG32(VM_INVALIDATE_REQUEST, 1 << vm->id);
-}
-
/*
* RLC
*/