[PATCH 01/11] drm/radeon: rework vm_flush parameters
Christian König
deathsimple at vodafone.de
Mon Oct 13 03:41:37 PDT 2014
From: Christian König <christian.koenig at amd.com>
Use ring structure instead of index and provide vm_id and pd_addr separately.
Signed-off-by: Christian König <christian.koenig at amd.com>
---
drivers/gpu/drm/radeon/cik.c | 23 ++++++++++-------------
drivers/gpu/drm/radeon/cik_sdma.c | 22 +++++++++-------------
drivers/gpu/drm/radeon/ni.c | 14 +++++---------
drivers/gpu/drm/radeon/ni_dma.c | 14 +++++---------
drivers/gpu/drm/radeon/radeon.h | 5 +++--
drivers/gpu/drm/radeon/radeon_asic.h | 18 ++++++++++++------
drivers/gpu/drm/radeon/radeon_vm.c | 3 ++-
drivers/gpu/drm/radeon/si.c | 18 +++++++-----------
drivers/gpu/drm/radeon/si_dma.c | 19 ++++++++-----------
9 files changed, 61 insertions(+), 75 deletions(-)
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index d48a539..5e58504 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -5958,26 +5958,23 @@ static void cik_vm_decode_fault(struct radeon_device *rdev,
* Update the page table base and flush the VM TLB
* using the CP (CIK).
*/
-void cik_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
+void cik_vm_flush(struct radeon_device *rdev, struct radeon_ring *ring,
+ unsigned vm_id, uint64_t pd_addr)
{
- struct radeon_ring *ring = &rdev->ring[ridx];
- int usepfp = (ridx == RADEON_RING_TYPE_GFX_INDEX);
-
- if (vm == NULL)
- return;
+ int usepfp = (ring->idx == RADEON_RING_TYPE_GFX_INDEX);
radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(usepfp) |
WRITE_DATA_DST_SEL(0)));
- if (vm->id < 8) {
+ if (vm_id < 8) {
radeon_ring_write(ring,
- (VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm->id << 2)) >> 2);
+ (VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm_id << 2)) >> 2);
} else {
radeon_ring_write(ring,
- (VM_CONTEXT8_PAGE_TABLE_BASE_ADDR + ((vm->id - 8) << 2)) >> 2);
+ (VM_CONTEXT8_PAGE_TABLE_BASE_ADDR + ((vm_id - 8) << 2)) >> 2);
}
radeon_ring_write(ring, 0);
- radeon_ring_write(ring, vm->pd_gpu_addr >> 12);
+ radeon_ring_write(ring, pd_addr >> 12);
/* update SH_MEM_* regs */
radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
@@ -5985,7 +5982,7 @@ void cik_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
WRITE_DATA_DST_SEL(0)));
radeon_ring_write(ring, SRBM_GFX_CNTL >> 2);
radeon_ring_write(ring, 0);
- radeon_ring_write(ring, VMID(vm->id));
+ radeon_ring_write(ring, VMID(vm_id));
radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 6));
radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(usepfp) |
@@ -6006,7 +6003,7 @@ void cik_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
radeon_ring_write(ring, VMID(0));
/* HDP flush */
- cik_hdp_flush_cp_ring_emit(rdev, ridx);
+ cik_hdp_flush_cp_ring_emit(rdev, ring->idx);
/* bits 0-15 are the VM contexts0-15 */
radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
@@ -6014,7 +6011,7 @@ void cik_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
WRITE_DATA_DST_SEL(0)));
radeon_ring_write(ring, VM_INVALIDATE_REQUEST >> 2);
radeon_ring_write(ring, 0);
- radeon_ring_write(ring, 1 << vm->id);
+ radeon_ring_write(ring, 1 << vm_id);
/* compute doesn't have PFP */
if (usepfp) {
diff --git a/drivers/gpu/drm/radeon/cik_sdma.c b/drivers/gpu/drm/radeon/cik_sdma.c
index c473c91..2bc8a2f 100644
--- a/drivers/gpu/drm/radeon/cik_sdma.c
+++ b/drivers/gpu/drm/radeon/cik_sdma.c
@@ -905,25 +905,21 @@ void cik_sdma_vm_pad_ib(struct radeon_ib *ib)
* Update the page table base and flush the VM TLB
* using sDMA (CIK).
*/
-void cik_dma_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
+void cik_dma_vm_flush(struct radeon_device *rdev, struct radeon_ring *ring,
+ unsigned vm_id, uint64_t pd_addr)
{
- struct radeon_ring *ring = &rdev->ring[ridx];
-
- if (vm == NULL)
- return;
-
radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SRBM_WRITE, 0, 0xf000));
- if (vm->id < 8) {
- radeon_ring_write(ring, (VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm->id << 2)) >> 2);
+ if (vm_id < 8) {
+ radeon_ring_write(ring, (VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm_id << 2)) >> 2);
} else {
- radeon_ring_write(ring, (VM_CONTEXT8_PAGE_TABLE_BASE_ADDR + ((vm->id - 8) << 2)) >> 2);
+ radeon_ring_write(ring, (VM_CONTEXT8_PAGE_TABLE_BASE_ADDR + ((vm_id - 8) << 2)) >> 2);
}
- radeon_ring_write(ring, vm->pd_gpu_addr >> 12);
+ radeon_ring_write(ring, pd_addr >> 12);
/* update SH_MEM_* regs */
radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SRBM_WRITE, 0, 0xf000));
radeon_ring_write(ring, SRBM_GFX_CNTL >> 2);
- radeon_ring_write(ring, VMID(vm->id));
+ radeon_ring_write(ring, VMID(vm_id));
radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SRBM_WRITE, 0, 0xf000));
radeon_ring_write(ring, SH_MEM_BASES >> 2);
@@ -946,11 +942,11 @@ void cik_dma_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm
radeon_ring_write(ring, VMID(0));
/* flush HDP */
- cik_sdma_hdp_flush_ring_emit(rdev, ridx);
+ cik_sdma_hdp_flush_ring_emit(rdev, ring->idx);
/* flush TLB */
radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SRBM_WRITE, 0, 0xf000));
radeon_ring_write(ring, VM_INVALIDATE_REQUEST >> 2);
- radeon_ring_write(ring, 1 << vm->id);
+ radeon_ring_write(ring, 1 << vm_id);
}
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 3faee58..bee432d 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -2502,15 +2502,11 @@ void cayman_vm_decode_fault(struct radeon_device *rdev,
* Update the page table base and flush the VM TLB
* using the CP (cayman-si).
*/
-void cayman_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
+void cayman_vm_flush(struct radeon_device *rdev, struct radeon_ring *ring,
+ unsigned vm_id, uint64_t pd_addr)
{
- struct radeon_ring *ring = &rdev->ring[ridx];
-
- if (vm == NULL)
- return;
-
- radeon_ring_write(ring, PACKET0(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm->id << 2), 0));
- radeon_ring_write(ring, vm->pd_gpu_addr >> 12);
+ radeon_ring_write(ring, PACKET0(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm_id << 2), 0));
+ radeon_ring_write(ring, pd_addr >> 12);
/* flush hdp cache */
radeon_ring_write(ring, PACKET0(HDP_MEM_COHERENCY_FLUSH_CNTL, 0));
@@ -2518,7 +2514,7 @@ void cayman_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
/* bits 0-7 are the VM contexts0-7 */
radeon_ring_write(ring, PACKET0(VM_INVALIDATE_REQUEST, 0));
- radeon_ring_write(ring, 1 << vm->id);
+ radeon_ring_write(ring, 1 << vm_id);
/* sync PFP to ME, otherwise we might get invalid PFP reads */
radeon_ring_write(ring, PACKET3(PACKET3_PFP_SYNC_ME, 0));
diff --git a/drivers/gpu/drm/radeon/ni_dma.c b/drivers/gpu/drm/radeon/ni_dma.c
index 8a3e622..1d15f6b 100644
--- a/drivers/gpu/drm/radeon/ni_dma.c
+++ b/drivers/gpu/drm/radeon/ni_dma.c
@@ -452,16 +452,12 @@ void cayman_dma_vm_pad_ib(struct radeon_ib *ib)
ib->ptr[ib->length_dw++] = DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0);
}
-void cayman_dma_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
+void cayman_dma_vm_flush(struct radeon_device *rdev, struct radeon_ring *ring,
+ unsigned vm_id, uint64_t pd_addr)
{
- struct radeon_ring *ring = &rdev->ring[ridx];
-
- if (vm == NULL)
- return;
-
radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0));
- radeon_ring_write(ring, (0xf << 16) | ((VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm->id << 2)) >> 2));
- radeon_ring_write(ring, vm->pd_gpu_addr >> 12);
+ radeon_ring_write(ring, (0xf << 16) | ((VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm_id << 2)) >> 2));
+ radeon_ring_write(ring, pd_addr >> 12);
/* flush hdp cache */
radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0));
@@ -471,6 +467,6 @@ void cayman_dma_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm
/* bits 0-7 are the VM contexts0-7 */
radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0));
radeon_ring_write(ring, (0xf << 16) | (VM_INVALIDATE_REQUEST >> 2));
- radeon_ring_write(ring, 1 << vm->id);
+ radeon_ring_write(ring, 1 << vm_id);
}
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index e01424f..273c5e8 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1782,7 +1782,8 @@ struct radeon_asic_ring {
void (*hdp_flush)(struct radeon_device *rdev, struct radeon_ring *ring);
bool (*emit_semaphore)(struct radeon_device *rdev, struct radeon_ring *cp,
struct radeon_semaphore *semaphore, bool emit_wait);
- void (*vm_flush)(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
+ void (*vm_flush)(struct radeon_device *rdev, struct radeon_ring *ring,
+ unsigned vm_id, uint64_t pd_addr);
/* testing functions */
int (*ring_test)(struct radeon_device *rdev, struct radeon_ring *cp);
@@ -2828,7 +2829,7 @@ static inline 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, vm) (rdev)->asic->ring[(r)]->vm_flush((rdev), (r), (vm))
+#define radeon_ring_vm_flush(rdev, r, vm_id, pd_addr) (rdev)->asic->ring[(r)->idx]->vm_flush((rdev), (r), (vm_id), (pd_addr))
#define radeon_ring_get_rptr(rdev, r) (rdev)->asic->ring[(r)->idx]->get_rptr((rdev), (r))
#define radeon_ring_get_wptr(rdev, r) (rdev)->asic->ring[(r)->idx]->get_wptr((rdev), (r))
#define radeon_ring_set_wptr(rdev, r) (rdev)->asic->ring[(r)->idx]->set_wptr((rdev), (r))
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index c41363f..e0362a2 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -600,7 +600,8 @@ int cayman_asic_reset(struct radeon_device *rdev);
void cayman_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib);
int cayman_vm_init(struct radeon_device *rdev);
void cayman_vm_fini(struct radeon_device *rdev);
-void cayman_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
+void cayman_vm_flush(struct radeon_device *rdev, struct radeon_ring *ring,
+ unsigned vm_id, uint64_t pd_addr);
uint32_t cayman_vm_page_flags(struct radeon_device *rdev, uint32_t flags);
int evergreen_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib);
int evergreen_dma_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib);
@@ -625,7 +626,8 @@ void cayman_dma_vm_set_pages(struct radeon_device *rdev,
uint32_t incr, uint32_t flags);
void cayman_dma_vm_pad_ib(struct radeon_ib *ib);
-void cayman_dma_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
+void cayman_dma_vm_flush(struct radeon_device *rdev, struct radeon_ring *ring,
+ unsigned vm_id, uint64_t pd_addr);
u32 cayman_gfx_get_rptr(struct radeon_device *rdev,
struct radeon_ring *ring);
@@ -700,7 +702,8 @@ int si_irq_set(struct radeon_device *rdev);
int si_irq_process(struct radeon_device *rdev);
int si_vm_init(struct radeon_device *rdev);
void si_vm_fini(struct radeon_device *rdev);
-void si_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
+void si_vm_flush(struct radeon_device *rdev, struct radeon_ring *ring,
+ unsigned vm_id, uint64_t pd_addr);
int si_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib);
struct radeon_fence *si_copy_dma(struct radeon_device *rdev,
uint64_t src_offset, uint64_t dst_offset,
@@ -722,7 +725,8 @@ void si_dma_vm_set_pages(struct radeon_device *rdev,
uint64_t addr, unsigned count,
uint32_t incr, uint32_t flags);
-void si_dma_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
+void si_dma_vm_flush(struct radeon_device *rdev, struct radeon_ring *ring,
+ unsigned vm_id, uint64_t pd_addr);
u32 si_get_xclk(struct radeon_device *rdev);
uint64_t si_get_gpu_clock_counter(struct radeon_device *rdev);
int si_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk);
@@ -794,7 +798,8 @@ int cik_irq_set(struct radeon_device *rdev);
int cik_irq_process(struct radeon_device *rdev);
int cik_vm_init(struct radeon_device *rdev);
void cik_vm_fini(struct radeon_device *rdev);
-void cik_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
+void cik_vm_flush(struct radeon_device *rdev, struct radeon_ring *ring,
+ unsigned vm_id, uint64_t pd_addr);
void cik_sdma_vm_copy_pages(struct radeon_device *rdev,
struct radeon_ib *ib,
@@ -812,7 +817,8 @@ void cik_sdma_vm_set_pages(struct radeon_device *rdev,
uint32_t incr, uint32_t flags);
void cik_sdma_vm_pad_ib(struct radeon_ib *ib);
-void cik_dma_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
+void cik_dma_vm_flush(struct radeon_device *rdev, struct radeon_ring *ring,
+ unsigned vm_id, uint64_t pd_addr);
int cik_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib);
u32 cik_gfx_get_rptr(struct radeon_device *rdev,
struct radeon_ring *ring);
diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c
index 4532cc7..45987a4 100644
--- a/drivers/gpu/drm/radeon/radeon_vm.c
+++ b/drivers/gpu/drm/radeon/radeon_vm.c
@@ -243,7 +243,8 @@ void radeon_vm_flush(struct radeon_device *rdev,
if (!vm->last_flush || pd_addr != vm->pd_gpu_addr) {
trace_radeon_vm_flush(pd_addr, ring, vm->id);
vm->pd_gpu_addr = pd_addr;
- radeon_ring_vm_flush(rdev, ring, vm);
+ radeon_ring_vm_flush(rdev, &rdev->ring[ring],
+ vm->id, vm->pd_gpu_addr);
}
}
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 423a8cd..ceef52b 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -5020,27 +5020,23 @@ static void si_vm_decode_fault(struct radeon_device *rdev,
block, mc_id);
}
-void si_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
+void si_vm_flush(struct radeon_device *rdev, struct radeon_ring *ring,
+ unsigned vm_id, uint64_t pd_addr)
{
- struct radeon_ring *ring = &rdev->ring[ridx];
-
- if (vm == NULL)
- return;
-
/* write new base address */
radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(1) |
WRITE_DATA_DST_SEL(0)));
- if (vm->id < 8) {
+ if (vm_id < 8) {
radeon_ring_write(ring,
- (VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm->id << 2)) >> 2);
+ (VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm_id << 2)) >> 2);
} else {
radeon_ring_write(ring,
- (VM_CONTEXT8_PAGE_TABLE_BASE_ADDR + ((vm->id - 8) << 2)) >> 2);
+ (VM_CONTEXT8_PAGE_TABLE_BASE_ADDR + ((vm_id - 8) << 2)) >> 2);
}
radeon_ring_write(ring, 0);
- radeon_ring_write(ring, vm->pd_gpu_addr >> 12);
+ radeon_ring_write(ring, pd_addr >> 12);
/* flush hdp cache */
radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
@@ -5056,7 +5052,7 @@ void si_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
WRITE_DATA_DST_SEL(0)));
radeon_ring_write(ring, VM_INVALIDATE_REQUEST >> 2);
radeon_ring_write(ring, 0);
- radeon_ring_write(ring, 1 << vm->id);
+ radeon_ring_write(ring, 1 << vm_id);
/* sync PFP to ME, otherwise we might get invalid PFP reads */
radeon_ring_write(ring, PACKET3(PACKET3_PFP_SYNC_ME, 0));
diff --git a/drivers/gpu/drm/radeon/si_dma.c b/drivers/gpu/drm/radeon/si_dma.c
index b58f12b..e8bc0a5 100644
--- a/drivers/gpu/drm/radeon/si_dma.c
+++ b/drivers/gpu/drm/radeon/si_dma.c
@@ -185,20 +185,17 @@ void si_dma_vm_set_pages(struct radeon_device *rdev,
}
}
-void si_dma_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
-{
- struct radeon_ring *ring = &rdev->ring[ridx];
-
- if (vm == NULL)
- return;
+void si_dma_vm_flush(struct radeon_device *rdev, struct radeon_ring *ring,
+ unsigned vm_id, uint64_t pd_addr)
+{
radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0, 0));
- if (vm->id < 8) {
- radeon_ring_write(ring, (0xf << 16) | ((VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm->id << 2)) >> 2));
+ if (vm_id < 8) {
+ radeon_ring_write(ring, (0xf << 16) | ((VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm_id << 2)) >> 2));
} else {
- radeon_ring_write(ring, (0xf << 16) | ((VM_CONTEXT8_PAGE_TABLE_BASE_ADDR + ((vm->id - 8) << 2)) >> 2));
+ radeon_ring_write(ring, (0xf << 16) | ((VM_CONTEXT8_PAGE_TABLE_BASE_ADDR + ((vm_id - 8) << 2)) >> 2));
}
- radeon_ring_write(ring, vm->pd_gpu_addr >> 12);
+ radeon_ring_write(ring, pd_addr >> 12);
/* flush hdp cache */
radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0, 0));
@@ -208,7 +205,7 @@ void si_dma_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
/* bits 0-7 are the VM contexts0-7 */
radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0, 0));
radeon_ring_write(ring, (0xf << 16) | (VM_INVALIDATE_REQUEST >> 2));
- radeon_ring_write(ring, 1 << vm->id);
+ radeon_ring_write(ring, 1 << vm_id);
}
/**
--
1.9.1
More information about the dri-devel
mailing list