[PATCH 04/11] drm/radeon: split semaphore and sync object handling v2

2014-11-19 Thread Christian König 
From: Christian König 

Previously we just allocated space for four hardware semaphores
in each software semaphore object. Make software semaphore objects
represent only one hardware semaphore address again by splitting
the sync code into it's own object.

v2: fix typo in comment

Signed-off-by: Christian König 
---
 drivers/gpu/drm/radeon/Makefile   |   3 +-
 drivers/gpu/drm/radeon/cik.c  |  18 +--
 drivers/gpu/drm/radeon/cik_sdma.c |  18 +--
 drivers/gpu/drm/radeon/evergreen_dma.c|  18 +--
 drivers/gpu/drm/radeon/r600.c |  18 +--
 drivers/gpu/drm/radeon/r600_dma.c |  18 +--
 drivers/gpu/drm/radeon/radeon.h   |  42 +++---
 drivers/gpu/drm/radeon/radeon_cs.c|   8 +-
 drivers/gpu/drm/radeon/radeon_ib.c|  13 +-
 drivers/gpu/drm/radeon/radeon_semaphore.c | 154 +
 drivers/gpu/drm/radeon/radeon_sync.c  | 213 ++
 drivers/gpu/drm/radeon/radeon_vm.c|   4 +-
 drivers/gpu/drm/radeon/rv770_dma.c|  18 +--
 drivers/gpu/drm/radeon/si_dma.c   |  18 +--
 14 files changed, 303 insertions(+), 260 deletions(-)
 create mode 100644 drivers/gpu/drm/radeon/radeon_sync.c

diff --git a/drivers/gpu/drm/radeon/Makefile b/drivers/gpu/drm/radeon/Makefile
index d01b879..a02434a 100644
--- a/drivers/gpu/drm/radeon/Makefile
+++ b/drivers/gpu/drm/radeon/Makefile
@@ -80,7 +80,8 @@ radeon-y += radeon_device.o radeon_asic.o radeon_kms.o \
r600_dpm.o rs780_dpm.o rv6xx_dpm.o rv770_dpm.o rv730_dpm.o rv740_dpm.o \
rv770_smc.o cypress_dpm.o btc_dpm.o sumo_dpm.o sumo_smc.o trinity_dpm.o 
\
trinity_smc.o ni_dpm.o si_smc.o si_dpm.o kv_smc.o kv_dpm.o ci_smc.o \
-   ci_dpm.o dce6_afmt.o radeon_vm.o radeon_ucode.o radeon_ib.o radeon_mn.o
+   ci_dpm.o dce6_afmt.o radeon_vm.o radeon_ucode.o radeon_ib.o radeon_mn.o 
\
+   radeon_sync.o

 # add async DMA block
 radeon-y += \
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index d52ead9..6bb8b84 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -3979,31 +3979,27 @@ struct radeon_fence *cik_copy_cpdma(struct 
radeon_device *rdev,
unsigned num_gpu_pages,
struct reservation_object *resv)
 {
-   struct radeon_semaphore *sem = NULL;
struct radeon_fence *fence;
+   struct radeon_sync sync;
int ring_index = rdev->asic->copy.blit_ring_index;
struct radeon_ring *ring = &rdev->ring[ring_index];
u32 size_in_bytes, cur_size_in_bytes, control;
int i, num_loops;
int r = 0;

-   r = radeon_semaphore_create(rdev, &sem);
-   if (r) {
-   DRM_ERROR("radeon: moving bo (%d).\n", r);
-   return ERR_PTR(r);
-   }
+   radeon_sync_create(&sync);

size_in_bytes = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT);
num_loops = DIV_ROUND_UP(size_in_bytes, 0x1f);
r = radeon_ring_lock(rdev, ring, num_loops * 7 + 18);
if (r) {
DRM_ERROR("radeon: moving bo (%d).\n", r);
-   radeon_semaphore_free(rdev, &sem, NULL);
+   radeon_sync_free(rdev, &sync, NULL);
return ERR_PTR(r);
}

-   radeon_semaphore_sync_resv(rdev, sem, resv, false);
-   radeon_semaphore_sync_rings(rdev, sem, ring->idx);
+   radeon_sync_resv(rdev, &sync, resv, false);
+   radeon_sync_rings(rdev, &sync, ring->idx);

for (i = 0; i < num_loops; i++) {
cur_size_in_bytes = size_in_bytes;
@@ -4027,12 +4023,12 @@ struct radeon_fence *cik_copy_cpdma(struct 
radeon_device *rdev,
r = radeon_fence_emit(rdev, &fence, ring->idx);
if (r) {
radeon_ring_unlock_undo(rdev, ring);
-   radeon_semaphore_free(rdev, &sem, NULL);
+   radeon_sync_free(rdev, &sync, NULL);
return ERR_PTR(r);
}

radeon_ring_unlock_commit(rdev, ring, false);
-   radeon_semaphore_free(rdev, &sem, fence);
+   radeon_sync_free(rdev, &sync, fence);

return fence;
 }
diff --git a/drivers/gpu/drm/radeon/cik_sdma.c 
b/drivers/gpu/drm/radeon/cik_sdma.c
index 7470a2e..604e2e7 100644
--- a/drivers/gpu/drm/radeon/cik_sdma.c
+++ b/drivers/gpu/drm/radeon/cik_sdma.c
@@ -541,31 +541,27 @@ struct radeon_fence *cik_copy_dma(struct radeon_device 
*rdev,
  unsigned num_gpu_pages,
  struct reservation_object *resv)
 {
-   struct radeon_semaphore *sem = NULL;
struct radeon_fence *fence;
+   struct radeon_sync sync;
int ring_index = rdev->asic->copy.dma_ring_index;
struct radeon_ring *ring = &rdev->ring[ring_index];
u32 size_in_bytes, cur_size_in_bytes;
int i, num_loops;
int r = 0;

-   r = radeon_semaphore_create(rdev, &sem);
-   if (r) {
-   DRM_ERROR("radeon: moving

[PATCH 04/11] drm/radeon: split semaphore and sync object handling v2

2014-10-13 Thread Christian König 
From: Christian K?nig 

Previously we just allocated space for four hardware semaphores
in each software semaphore object. Make software semaphore objects
represent only one hardware semaphore address again by splitting
the sync code into it's own object.

v2: fix typo in comment

Signed-off-by: Christian K?nig 
---
 drivers/gpu/drm/radeon/Makefile   |   3 +-
 drivers/gpu/drm/radeon/cik.c  |  18 +--
 drivers/gpu/drm/radeon/cik_sdma.c |  18 +--
 drivers/gpu/drm/radeon/evergreen_dma.c|  18 +--
 drivers/gpu/drm/radeon/r600.c |  18 +--
 drivers/gpu/drm/radeon/r600_dma.c |  18 +--
 drivers/gpu/drm/radeon/radeon.h   |  42 +++---
 drivers/gpu/drm/radeon/radeon_cs.c|   8 +-
 drivers/gpu/drm/radeon/radeon_ib.c|  13 +-
 drivers/gpu/drm/radeon/radeon_semaphore.c | 154 +
 drivers/gpu/drm/radeon/radeon_sync.c  | 213 ++
 drivers/gpu/drm/radeon/radeon_vm.c|   4 +-
 drivers/gpu/drm/radeon/rv770_dma.c|  18 +--
 drivers/gpu/drm/radeon/si_dma.c   |  18 +--
 14 files changed, 303 insertions(+), 260 deletions(-)
 create mode 100644 drivers/gpu/drm/radeon/radeon_sync.c

diff --git a/drivers/gpu/drm/radeon/Makefile b/drivers/gpu/drm/radeon/Makefile
index d01b879..a02434a 100644
--- a/drivers/gpu/drm/radeon/Makefile
+++ b/drivers/gpu/drm/radeon/Makefile
@@ -80,7 +80,8 @@ radeon-y += radeon_device.o radeon_asic.o radeon_kms.o \
r600_dpm.o rs780_dpm.o rv6xx_dpm.o rv770_dpm.o rv730_dpm.o rv740_dpm.o \
rv770_smc.o cypress_dpm.o btc_dpm.o sumo_dpm.o sumo_smc.o trinity_dpm.o 
\
trinity_smc.o ni_dpm.o si_smc.o si_dpm.o kv_smc.o kv_dpm.o ci_smc.o \
-   ci_dpm.o dce6_afmt.o radeon_vm.o radeon_ucode.o radeon_ib.o radeon_mn.o
+   ci_dpm.o dce6_afmt.o radeon_vm.o radeon_ucode.o radeon_ib.o radeon_mn.o 
\
+   radeon_sync.o

 # add async DMA block
 radeon-y += \
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 5e58504..203e895 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -3970,31 +3970,27 @@ struct radeon_fence *cik_copy_cpdma(struct 
radeon_device *rdev,
unsigned num_gpu_pages,
struct reservation_object *resv)
 {
-   struct radeon_semaphore *sem = NULL;
struct radeon_fence *fence;
+   struct radeon_sync sync;
int ring_index = rdev->asic->copy.blit_ring_index;
struct radeon_ring *ring = &rdev->ring[ring_index];
u32 size_in_bytes, cur_size_in_bytes, control;
int i, num_loops;
int r = 0;

-   r = radeon_semaphore_create(rdev, &sem);
-   if (r) {
-   DRM_ERROR("radeon: moving bo (%d).\n", r);
-   return ERR_PTR(r);
-   }
+   radeon_sync_create(&sync);

size_in_bytes = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT);
num_loops = DIV_ROUND_UP(size_in_bytes, 0x1f);
r = radeon_ring_lock(rdev, ring, num_loops * 7 + 18);
if (r) {
DRM_ERROR("radeon: moving bo (%d).\n", r);
-   radeon_semaphore_free(rdev, &sem, NULL);
+   radeon_sync_free(rdev, &sync, NULL);
return ERR_PTR(r);
}

-   radeon_semaphore_sync_resv(rdev, sem, resv, false);
-   radeon_semaphore_sync_rings(rdev, sem, ring->idx);
+   radeon_sync_resv(rdev, &sync, resv, false);
+   radeon_sync_rings(rdev, &sync, ring->idx);

for (i = 0; i < num_loops; i++) {
cur_size_in_bytes = size_in_bytes;
@@ -4018,12 +4014,12 @@ struct radeon_fence *cik_copy_cpdma(struct 
radeon_device *rdev,
r = radeon_fence_emit(rdev, &fence, ring->idx);
if (r) {
radeon_ring_unlock_undo(rdev, ring);
-   radeon_semaphore_free(rdev, &sem, NULL);
+   radeon_sync_free(rdev, &sync, NULL);
return ERR_PTR(r);
}

radeon_ring_unlock_commit(rdev, ring, false);
-   radeon_semaphore_free(rdev, &sem, fence);
+   radeon_sync_free(rdev, &sync, fence);

return fence;
 }
diff --git a/drivers/gpu/drm/radeon/cik_sdma.c 
b/drivers/gpu/drm/radeon/cik_sdma.c
index 2bc8a2f..1216a3c 100644
--- a/drivers/gpu/drm/radeon/cik_sdma.c
+++ b/drivers/gpu/drm/radeon/cik_sdma.c
@@ -548,31 +548,27 @@ struct radeon_fence *cik_copy_dma(struct radeon_device 
*rdev,
  unsigned num_gpu_pages,
  struct reservation_object *resv)
 {
-   struct radeon_semaphore *sem = NULL;
struct radeon_fence *fence;
+   struct radeon_sync sync;
int ring_index = rdev->asic->copy.dma_ring_index;
struct radeon_ring *ring = &rdev->ring[ring_index];
u32 size_in_bytes, cur_size_in_bytes;
int i, num_loops;
int r = 0;

-   r = radeon_semaphore_create(rdev, &sem);
-   if (r) {
-   DRM_ERROR("radeon: moving b

[PATCH 04/11] drm/radeon: split semaphore and sync object handling

2014-09-17 Thread Alex Deucher 
On Fri, Sep 12, 2014 at 7:52 AM, Christian K?nig
 wrote:
> From: Christian K?nig 
>
> Previously we just allocated space for four hardware semaphores
> in each software semaphore object. Make software semaphore objects
> represent only one hardware semaphore address again by splitting
> the sync code into it's own object.
>
> Signed-off-by: Christian K?nig 

Minor typo noted below.

Alex

> ---
>  drivers/gpu/drm/radeon/Makefile   |   3 +-
>  drivers/gpu/drm/radeon/cik.c  |  18 ++-
>  drivers/gpu/drm/radeon/cik_sdma.c |  18 ++-
>  drivers/gpu/drm/radeon/evergreen_dma.c|  18 ++-
>  drivers/gpu/drm/radeon/r600.c |  18 ++-
>  drivers/gpu/drm/radeon/r600_dma.c |  18 ++-
>  drivers/gpu/drm/radeon/radeon.h   |  40 +++---
>  drivers/gpu/drm/radeon/radeon_cs.c|   7 +-
>  drivers/gpu/drm/radeon/radeon_ib.c|  13 +-
>  drivers/gpu/drm/radeon/radeon_semaphore.c | 139 +
>  drivers/gpu/drm/radeon/radeon_sync.c  | 198 
> ++
>  drivers/gpu/drm/radeon/radeon_vm.c|   4 +-
>  drivers/gpu/drm/radeon/rv770_dma.c|  18 ++-
>  drivers/gpu/drm/radeon/si_dma.c   |  18 ++-
>  14 files changed, 286 insertions(+), 244 deletions(-)
>  create mode 100644 drivers/gpu/drm/radeon/radeon_sync.c
>
> diff --git a/drivers/gpu/drm/radeon/Makefile b/drivers/gpu/drm/radeon/Makefile
> index 7d7aed5..8cc9f68 100644
> --- a/drivers/gpu/drm/radeon/Makefile
> +++ b/drivers/gpu/drm/radeon/Makefile
> @@ -80,7 +80,8 @@ radeon-y += radeon_device.o radeon_asic.o radeon_kms.o \
> r600_dpm.o rs780_dpm.o rv6xx_dpm.o rv770_dpm.o rv730_dpm.o 
> rv740_dpm.o \
> rv770_smc.o cypress_dpm.o btc_dpm.o sumo_dpm.o sumo_smc.o 
> trinity_dpm.o \
> trinity_smc.o ni_dpm.o si_smc.o si_dpm.o kv_smc.o kv_dpm.o ci_smc.o \
> -   ci_dpm.o dce6_afmt.o radeon_vm.o radeon_ucode.o radeon_ib.o 
> radeon_mn.o
> +   ci_dpm.o dce6_afmt.o radeon_vm.o radeon_ucode.o radeon_ib.o 
> radeon_mn.o \
> +   radeon_sync.o
>
>  # add async DMA block
>  radeon-y += \
> diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
> index 16a861d..6dd55ea 100644
> --- a/drivers/gpu/drm/radeon/cik.c
> +++ b/drivers/gpu/drm/radeon/cik.c
> @@ -3970,31 +3970,27 @@ struct radeon_fence *cik_copy_cpdma(struct 
> radeon_device *rdev,
> unsigned num_gpu_pages,
> struct reservation_object *resv)
>  {
> -   struct radeon_semaphore *sem = NULL;
> struct radeon_fence *fence;
> +   struct radeon_sync sync;
> int ring_index = rdev->asic->copy.blit_ring_index;
> struct radeon_ring *ring = &rdev->ring[ring_index];
> u32 size_in_bytes, cur_size_in_bytes, control;
> int i, num_loops;
> int r = 0;
>
> -   r = radeon_semaphore_create(rdev, &sem);
> -   if (r) {
> -   DRM_ERROR("radeon: moving bo (%d).\n", r);
> -   return ERR_PTR(r);
> -   }
> +   radeon_sync_create(&sync);
>
> size_in_bytes = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT);
> num_loops = DIV_ROUND_UP(size_in_bytes, 0x1f);
> r = radeon_ring_lock(rdev, ring, num_loops * 7 + 18);
> if (r) {
> DRM_ERROR("radeon: moving bo (%d).\n", r);
> -   radeon_semaphore_free(rdev, &sem, NULL);
> +   radeon_sync_free(rdev, &sync, NULL);
> return ERR_PTR(r);
> }
>
> -   radeon_semaphore_sync_resv(sem, resv, false);
> -   radeon_semaphore_sync_rings(rdev, sem, ring->idx);
> +   radeon_sync_resv(&sync, resv, false);
> +   radeon_sync_rings(rdev, &sync, ring->idx);
>
> for (i = 0; i < num_loops; i++) {
> cur_size_in_bytes = size_in_bytes;
> @@ -4018,12 +4014,12 @@ struct radeon_fence *cik_copy_cpdma(struct 
> radeon_device *rdev,
> r = radeon_fence_emit(rdev, &fence, ring->idx);
> if (r) {
> radeon_ring_unlock_undo(rdev, ring);
> -   radeon_semaphore_free(rdev, &sem, NULL);
> +   radeon_sync_free(rdev, &sync, NULL);
> return ERR_PTR(r);
> }
>
> radeon_ring_unlock_commit(rdev, ring, false);
> -   radeon_semaphore_free(rdev, &sem, fence);
> +   radeon_sync_free(rdev, &sync, fence);
>
> return fence;
>  }
> diff --git a/drivers/gpu/drm/radeon/cik_sdma.c 
> b/drivers/gpu/drm/radeon/cik_sdma.c
> index dd73246..06602e4 100644
> --- a/drivers/gpu/drm/radeon/cik_sdma.c
> +++ b/drivers/gpu/drm/radeon/cik_sdma.c
> @@ -548,31 +548,27 @@ struct radeon_fence *cik_copy_dma(struct radeon_device 
> *rdev,
>   unsigned num_gpu_pages,
>   struct reservation_object *resv)
>  {
> -   struct radeon_semaphore *sem = NULL;
> struct radeon_fence *fence;
> +   struct radeon_sync sync;
> int ring_index = rdev->asic->cop

[PATCH 04/11] drm/radeon: split semaphore and sync object handling

2014-09-12 Thread Christian König 
From: Christian K?nig 

Previously we just allocated space for four hardware semaphores
in each software semaphore object. Make software semaphore objects
represent only one hardware semaphore address again by splitting
the sync code into it's own object.

Signed-off-by: Christian K?nig 
---
 drivers/gpu/drm/radeon/Makefile   |   3 +-
 drivers/gpu/drm/radeon/cik.c  |  18 ++-
 drivers/gpu/drm/radeon/cik_sdma.c |  18 ++-
 drivers/gpu/drm/radeon/evergreen_dma.c|  18 ++-
 drivers/gpu/drm/radeon/r600.c |  18 ++-
 drivers/gpu/drm/radeon/r600_dma.c |  18 ++-
 drivers/gpu/drm/radeon/radeon.h   |  40 +++---
 drivers/gpu/drm/radeon/radeon_cs.c|   7 +-
 drivers/gpu/drm/radeon/radeon_ib.c|  13 +-
 drivers/gpu/drm/radeon/radeon_semaphore.c | 139 +
 drivers/gpu/drm/radeon/radeon_sync.c  | 198 ++
 drivers/gpu/drm/radeon/radeon_vm.c|   4 +-
 drivers/gpu/drm/radeon/rv770_dma.c|  18 ++-
 drivers/gpu/drm/radeon/si_dma.c   |  18 ++-
 14 files changed, 286 insertions(+), 244 deletions(-)
 create mode 100644 drivers/gpu/drm/radeon/radeon_sync.c

diff --git a/drivers/gpu/drm/radeon/Makefile b/drivers/gpu/drm/radeon/Makefile
index 7d7aed5..8cc9f68 100644
--- a/drivers/gpu/drm/radeon/Makefile
+++ b/drivers/gpu/drm/radeon/Makefile
@@ -80,7 +80,8 @@ radeon-y += radeon_device.o radeon_asic.o radeon_kms.o \
r600_dpm.o rs780_dpm.o rv6xx_dpm.o rv770_dpm.o rv730_dpm.o rv740_dpm.o \
rv770_smc.o cypress_dpm.o btc_dpm.o sumo_dpm.o sumo_smc.o trinity_dpm.o 
\
trinity_smc.o ni_dpm.o si_smc.o si_dpm.o kv_smc.o kv_dpm.o ci_smc.o \
-   ci_dpm.o dce6_afmt.o radeon_vm.o radeon_ucode.o radeon_ib.o radeon_mn.o
+   ci_dpm.o dce6_afmt.o radeon_vm.o radeon_ucode.o radeon_ib.o radeon_mn.o 
\
+   radeon_sync.o

 # add async DMA block
 radeon-y += \
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 16a861d..6dd55ea 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -3970,31 +3970,27 @@ struct radeon_fence *cik_copy_cpdma(struct 
radeon_device *rdev,
unsigned num_gpu_pages,
struct reservation_object *resv)
 {
-   struct radeon_semaphore *sem = NULL;
struct radeon_fence *fence;
+   struct radeon_sync sync;
int ring_index = rdev->asic->copy.blit_ring_index;
struct radeon_ring *ring = &rdev->ring[ring_index];
u32 size_in_bytes, cur_size_in_bytes, control;
int i, num_loops;
int r = 0;

-   r = radeon_semaphore_create(rdev, &sem);
-   if (r) {
-   DRM_ERROR("radeon: moving bo (%d).\n", r);
-   return ERR_PTR(r);
-   }
+   radeon_sync_create(&sync);

size_in_bytes = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT);
num_loops = DIV_ROUND_UP(size_in_bytes, 0x1f);
r = radeon_ring_lock(rdev, ring, num_loops * 7 + 18);
if (r) {
DRM_ERROR("radeon: moving bo (%d).\n", r);
-   radeon_semaphore_free(rdev, &sem, NULL);
+   radeon_sync_free(rdev, &sync, NULL);
return ERR_PTR(r);
}

-   radeon_semaphore_sync_resv(sem, resv, false);
-   radeon_semaphore_sync_rings(rdev, sem, ring->idx);
+   radeon_sync_resv(&sync, resv, false);
+   radeon_sync_rings(rdev, &sync, ring->idx);

for (i = 0; i < num_loops; i++) {
cur_size_in_bytes = size_in_bytes;
@@ -4018,12 +4014,12 @@ struct radeon_fence *cik_copy_cpdma(struct 
radeon_device *rdev,
r = radeon_fence_emit(rdev, &fence, ring->idx);
if (r) {
radeon_ring_unlock_undo(rdev, ring);
-   radeon_semaphore_free(rdev, &sem, NULL);
+   radeon_sync_free(rdev, &sync, NULL);
return ERR_PTR(r);
}

radeon_ring_unlock_commit(rdev, ring, false);
-   radeon_semaphore_free(rdev, &sem, fence);
+   radeon_sync_free(rdev, &sync, fence);

return fence;
 }
diff --git a/drivers/gpu/drm/radeon/cik_sdma.c 
b/drivers/gpu/drm/radeon/cik_sdma.c
index dd73246..06602e4 100644
--- a/drivers/gpu/drm/radeon/cik_sdma.c
+++ b/drivers/gpu/drm/radeon/cik_sdma.c
@@ -548,31 +548,27 @@ struct radeon_fence *cik_copy_dma(struct radeon_device 
*rdev,
  unsigned num_gpu_pages,
  struct reservation_object *resv)
 {
-   struct radeon_semaphore *sem = NULL;
struct radeon_fence *fence;
+   struct radeon_sync sync;
int ring_index = rdev->asic->copy.dma_ring_index;
struct radeon_ring *ring = &rdev->ring[ring_index];
u32 size_in_bytes, cur_size_in_bytes;
int i, num_loops;
int r = 0;

-   r = radeon_semaphore_create(rdev, &sem);
-   if (r) {
-   DRM_ERROR("radeon: moving bo (%d).\n", r);
-   retur