From: Ken Wang <Qingqing.Wang@xxxxxxx>
Newer asics use 64 bit wptrs
Signed-off-by: Ken Wang <Qingqing.Wang 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.h | 5 ++++-
drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c | 10 +++++++---
drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h | 12 +++++++-----
drivers/gpu/drm/amd/amdgpu/cik_sdma.c | 12 +++++++-----
drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c | 10 +++++-----
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 18 ++++++++++--------
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 22 ++++++++++++----------
drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c | 11 ++++++-----
drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c | 15 ++++++++-------
drivers/gpu/drm/amd/amdgpu/si_dma.c | 12 +++++++-----
drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c | 9 +++++----
drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c | 9 +++++----
drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c | 9 +++++----
drivers/gpu/drm/amd/amdgpu/vce_v2_0.c | 17 +++++++++--------
drivers/gpu/drm/amd/amdgpu/vce_v3_0.c | 23 ++++++++++++-----------
15 files changed, 109 insertions(+), 85 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index f0e8b2a..a23842d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1594,9 +1594,12 @@ void amdgpu_mm_wdoorbell(struct amdgpu_device *adev, u32 index, u32 v);
*/
static inline void amdgpu_ring_write(struct amdgpu_ring *ring, uint32_t v)
{
+ u32 tmp;
if (ring->count_dw <= 0)
DRM_ERROR("amdgpu: writing more dwords to the ring than expected!\n");
- ring->ring[ring->wptr++] = v;
+ tmp = lower_32_bits(ring->wptr++);
+ tmp &= ring->buf_mask;
+ ring->ring[tmp] = v;
ring->wptr &= ring->ptr_mask;
ring->count_dw--;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index cead88a..f0515b8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -126,7 +126,7 @@ void amdgpu_ring_commit(struct amdgpu_ring *ring)
/* We pad to match fetch size */
count = ring->funcs->align_mask + 1 -
- (ring->wptr & ring->funcs->align_mask);
+ (lower_32_bits(ring->wptr) & ring->funcs->align_mask);
count %= ring->funcs->align_mask + 1;
ring->funcs->insert_nop(ring, count);
@@ -232,7 +232,10 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
}
amdgpu_ring_clear_ring(ring);
}
- ring->ptr_mask = (ring->ring_size / 4) - 1;
+ ring->buf_mask = (ring->ring_size / 4) - 1;
+ ring->ptr_mask = ring->support_64bit_ptrs ?
+ 0xffffffffffffffff : ring->buf_mask;
+
ring->max_dw = max_dw;
if (amdgpu_debugfs_ring_init(adev, ring)) {
@@ -284,7 +287,8 @@ static ssize_t amdgpu_debugfs_ring_read(struct file *f, char __user *buf,
{
struct amdgpu_ring *ring = file_inode(f)->i_private;
int r, i;
- uint32_t value, result, early[3];
+ uint32_t value, result;
+ uint64_t early[3];
if (*pos & 3 || size & 3)
return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index da702dc..9f2d605 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -98,8 +98,8 @@ struct amdgpu_ring_funcs {
u32 nop;
/* ring read/write ptr handling */
- u32 (*get_rptr)(struct amdgpu_ring *ring);
- u32 (*get_wptr)(struct amdgpu_ring *ring);
+ u64 (*get_rptr)(struct amdgpu_ring *ring);
+ u64 (*get_wptr)(struct amdgpu_ring *ring);
void (*set_wptr)(struct amdgpu_ring *ring);
/* validating and patching of IBs */
int (*parse_cs)(struct amdgpu_cs_parser *p, uint32_t ib_idx);
@@ -148,13 +148,15 @@ struct amdgpu_ring {
struct amdgpu_bo *ring_obj;
volatile uint32_t *ring;
unsigned rptr_offs;
- unsigned wptr;
- unsigned wptr_old;
+ u64 wptr;
+ u64 wptr_old;
+ bool support_64bit_ptrs;
unsigned ring_size;
unsigned max_dw;
int count_dw;
uint64_t gpu_addr;
- uint32_t ptr_mask;
+ uint64_t ptr_mask;
+ uint32_t buf_mask;
bool ready;
u32 idx;
u32 me;
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index c33bc1b..b35ec4a 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -158,7 +158,7 @@ static int cik_sdma_init_microcode(struct amdgpu_device *adev)
*
* Get the current rptr from the hardware (CIK+).
*/
-static uint32_t cik_sdma_ring_get_rptr(struct amdgpu_ring *ring)
+static uint64_t cik_sdma_ring_get_rptr(struct amdgpu_ring *ring)
{
u32 rptr;
@@ -174,7 +174,7 @@ static uint32_t cik_sdma_ring_get_rptr(struct amdgpu_ring *ring)
*
* Get the current wptr from the hardware (CIK+).
*/
-static uint32_t cik_sdma_ring_get_wptr(struct amdgpu_ring *ring)
+static uint64_t cik_sdma_ring_get_wptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
u32 me = (ring == &adev->sdma.instance[0].ring) ? 0 : 1;
@@ -194,7 +194,8 @@ static void cik_sdma_ring_set_wptr(struct amdgpu_ring *ring)
struct amdgpu_device *adev = ring->adev;
u32 me = (ring == &adev->sdma.instance[0].ring) ? 0 : 1;
- WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me], (ring->wptr << 2) & 0x3fffc);
+ WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me],
+ (lower_32_bits(ring->wptr) << 2) & 0x3fffc);
}
static void cik_sdma_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
@@ -225,7 +226,7 @@ static void cik_sdma_ring_emit_ib(struct amdgpu_ring *ring,
u32 extra_bits = vm_id & 0xf;
/* IB packet must end on a 8 DW boundary */
- cik_sdma_ring_insert_nop(ring, (12 - (ring->wptr & 7)) % 8);
+ cik_sdma_ring_insert_nop(ring, (12 - (lower_32_bits(ring->wptr) & 7)) % 8);
amdgpu_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_INDIRECT_BUFFER, 0, extra_bits));
amdgpu_ring_write(ring, ib->gpu_addr & 0xffffffe0); /* base must be 32 byte aligned */
@@ -432,7 +433,7 @@ static int cik_sdma_gfx_resume(struct amdgpu_device *adev)
WREG32(mmSDMA0_GFX_RB_BASE_HI + sdma_offsets[i], ring->gpu_addr >> 40);
ring->wptr = 0;
- WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[i], ring->wptr << 2);
+ WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[i], lower_32_bits(ring->wptr) << 2);
/* enable DMA RB */
WREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i],
@@ -940,6 +941,7 @@ static int cik_sdma_sw_init(void *handle)
ring = &adev->sdma.instance[i].ring;
ring->ring_obj = NULL;
sprintf(ring->name, "sdma%d", i);
+ ring->support_64bit_ptrs = false;
r = amdgpu_ring_init(adev, ring, 1024,
&adev->sdma.trap_irq,
(i == 0) ?
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
index 02ca232..cb3d2816 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
@@ -2192,12 +2192,12 @@ static int gfx_v6_0_cp_gfx_resume(struct amdgpu_device *adev)
return 0;
}
-static u32 gfx_v6_0_ring_get_rptr(struct amdgpu_ring *ring)
+static u64 gfx_v6_0_ring_get_rptr(struct amdgpu_ring *ring)
{
return ring->adev->wb.wb[ring->rptr_offs];
}
-static u32 gfx_v6_0_ring_get_wptr(struct amdgpu_ring *ring)
+static u64 gfx_v6_0_ring_get_wptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
@@ -2215,7 +2215,7 @@ static void gfx_v6_0_ring_set_wptr_gfx(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
- WREG32(mmCP_RB0_WPTR, ring->wptr);
+ WREG32(mmCP_RB0_WPTR, lower_32_bits(ring->wptr));
(void)RREG32(mmCP_RB0_WPTR);
}
@@ -2224,10 +2224,10 @@ static void gfx_v6_0_ring_set_wptr_compute(struct amdgpu_ring *ring)
struct amdgpu_device *adev = ring->adev;
if (ring == &adev->gfx.compute_ring[0]) {
- WREG32(mmCP_RB1_WPTR, ring->wptr);
+ WREG32(mmCP_RB1_WPTR, lower_32_bits(ring->wptr));
(void)RREG32(mmCP_RB1_WPTR);
} else if (ring == &adev->gfx.compute_ring[1]) {
- WREG32(mmCP_RB2_WPTR, ring->wptr);
+ WREG32(mmCP_RB2_WPTR, lower_32_bits(ring->wptr));
(void)RREG32(mmCP_RB2_WPTR);
} else {
BUG();
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index cd6a6ec..e6a25ee 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -2629,7 +2629,7 @@ static int gfx_v7_0_cp_gfx_resume(struct amdgpu_device *adev)
/* Initialize the ring buffer's read and write pointers */
WREG32(mmCP_RB0_CNTL, tmp | CP_RB0_CNTL__RB_RPTR_WR_ENA_MASK);
ring->wptr = 0;
- WREG32(mmCP_RB0_WPTR, ring->wptr);
+ WREG32(mmCP_RB0_WPTR, lower_32_bits(ring->wptr));
/* set the wb address wether it's enabled or not */
rptr_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4);
@@ -2658,12 +2658,12 @@ static int gfx_v7_0_cp_gfx_resume(struct amdgpu_device *adev)
return 0;
}
-static u32 gfx_v7_0_ring_get_rptr(struct amdgpu_ring *ring)
+static u64 gfx_v7_0_ring_get_rptr(struct amdgpu_ring *ring)
{
return ring->adev->wb.wb[ring->rptr_offs];
}
-static u32 gfx_v7_0_ring_get_wptr_gfx(struct amdgpu_ring *ring)
+static u64 gfx_v7_0_ring_get_wptr_gfx(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
@@ -2674,11 +2674,11 @@ static void gfx_v7_0_ring_set_wptr_gfx(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
- WREG32(mmCP_RB0_WPTR, ring->wptr);
+ WREG32(mmCP_RB0_WPTR, lower_32_bits(ring->wptr));
(void)RREG32(mmCP_RB0_WPTR);
}
-static u32 gfx_v7_0_ring_get_wptr_compute(struct amdgpu_ring *ring)
+static u64 gfx_v7_0_ring_get_wptr_compute(struct amdgpu_ring *ring)
{
/* XXX check if swapping is necessary on BE */
return ring->adev->wb.wb[ring->wptr_offs];
@@ -2689,8 +2689,8 @@ static void gfx_v7_0_ring_set_wptr_compute(struct amdgpu_ring *ring)
struct amdgpu_device *adev = ring->adev;
/* XXX check if swapping is necessary on BE */
- adev->wb.wb[ring->wptr_offs] = ring->wptr;
- WDOORBELL32(ring->doorbell_index, ring->wptr);
+ adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
+ WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
}
/**
@@ -3160,7 +3160,7 @@ static int gfx_v7_0_cp_compute_resume(struct amdgpu_device *adev)
/* read and write pointers, similar to CP_RB0_WPTR/_RPTR */
ring->wptr = 0;
- mqd->queue_state.cp_hqd_pq_wptr = ring->wptr;
+ mqd->queue_state.cp_hqd_pq_wptr = lower_32_bits(ring->wptr);
WREG32(mmCP_HQD_PQ_WPTR, mqd->queue_state.cp_hqd_pq_wptr);
mqd->queue_state.cp_hqd_pq_rptr = RREG32(mmCP_HQD_PQ_RPTR);
@@ -4708,6 +4708,7 @@ static int gfx_v7_0_sw_init(void *handle)
ring = &adev->gfx.gfx_ring[i];
ring->ring_obj = NULL;
sprintf(ring->name, "gfx");
+ ring->support_64bit_ptrs = false;
r = amdgpu_ring_init(adev, ring, 1024,
&adev->gfx.eop_irq, AMDGPU_CP_IRQ_GFX_EOP);
if (r)
@@ -4732,6 +4733,7 @@ static int gfx_v7_0_sw_init(void *handle)
ring->queue = i % 8;
sprintf(ring->name, "comp_%d.%d.%d", ring->me, ring->pipe, ring->queue);
irq_type = AMDGPU_CP_IRQ_COMPUTE_MEC1_PIPE0_EOP + ring->pipe;
+ ring->support_64bit_ptrs = false;
/* type-2 packets are deprecated on MEC, use type-3 instead */
r = amdgpu_ring_init(adev, ring, 1024,
&adev->gfx.eop_irq, irq_type);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index af6294f..304f28c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -2125,6 +2125,7 @@ static int gfx_v8_0_sw_init(void *handle)
ring->doorbell_index = AMDGPU_DOORBELL_GFX_RING0;
}
+ ring->support_64bit_ptrs = false;
r = amdgpu_ring_init(adev, ring, 1024, &adev->gfx.eop_irq,
AMDGPU_CP_IRQ_GFX_EOP);
if (r)
@@ -2149,6 +2150,7 @@ static int gfx_v8_0_sw_init(void *handle)
ring->queue = i % 8;
sprintf(ring->name, "comp_%d.%d.%d", ring->me, ring->pipe, ring->queue);
irq_type = AMDGPU_CP_IRQ_COMPUTE_MEC1_PIPE0_EOP + ring->pipe;
+ ring->support_64bit_ptrs = false;
/* type-2 packets are deprecated on MEC, use type-3 instead */
r = amdgpu_ring_init(adev, ring, 1024, &adev->gfx.eop_irq,
irq_type);
@@ -4490,7 +4492,7 @@ static int gfx_v8_0_cp_gfx_resume(struct amdgpu_device *adev)
/* Initialize the ring buffer's read and write pointers */
WREG32(mmCP_RB0_CNTL, tmp | CP_RB0_CNTL__RB_RPTR_WR_ENA_MASK);
ring->wptr = 0;
- WREG32(mmCP_RB0_WPTR, ring->wptr);
+ WREG32(mmCP_RB0_WPTR, lower_32_bits(ring->wptr));
/* set the wb address wether it's enabled or not */
rptr_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4);
@@ -5204,7 +5206,7 @@ static int gfx_v8_0_cp_compute_resume(struct amdgpu_device *adev)
/* reset read and write pointers, similar to CP_RB0_WPTR/_RPTR */
ring->wptr = 0;
- mqd->cp_hqd_pq_wptr = ring->wptr;
+ mqd->cp_hqd_pq_wptr = lower_32_bits(ring->wptr);
WREG32(mmCP_HQD_PQ_WPTR, mqd->cp_hqd_pq_wptr);
mqd->cp_hqd_pq_rptr = RREG32(mmCP_HQD_PQ_RPTR);
@@ -6458,12 +6460,12 @@ static int gfx_v8_0_set_clockgating_state(void *handle,
return 0;
}
-static u32 gfx_v8_0_ring_get_rptr(struct amdgpu_ring *ring)
+static u64 gfx_v8_0_ring_get_rptr(struct amdgpu_ring *ring)
{
return ring->adev->wb.wb[ring->rptr_offs];
}
-static u32 gfx_v8_0_ring_get_wptr_gfx(struct amdgpu_ring *ring)
+static u64 gfx_v8_0_ring_get_wptr_gfx(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
@@ -6480,10 +6482,10 @@ static void gfx_v8_0_ring_set_wptr_gfx(struct amdgpu_ring *ring)
if (ring->use_doorbell) {
/* XXX check if swapping is necessary on BE */
- adev->wb.wb[ring->wptr_offs] = ring->wptr;
- WDOORBELL32(ring->doorbell_index, ring->wptr);
+ adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
+ WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
} else {
- WREG32(mmCP_RB0_WPTR, ring->wptr);
+ WREG32(mmCP_RB0_WPTR, lower_32_bits(ring->wptr));
(void)RREG32(mmCP_RB0_WPTR);
}
}
@@ -6671,7 +6673,7 @@ static void gfx_v8_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
}
}
-static u32 gfx_v8_0_ring_get_wptr_compute(struct amdgpu_ring *ring)
+static u64 gfx_v8_0_ring_get_wptr_compute(struct amdgpu_ring *ring)
{
return ring->adev->wb.wb[ring->wptr_offs];
}
@@ -6681,8 +6683,8 @@ static void gfx_v8_0_ring_set_wptr_compute(struct amdgpu_ring *ring)
struct amdgpu_device *adev = ring->adev;
/* XXX check if swapping is necessary on BE */
- adev->wb.wb[ring->wptr_offs] = ring->wptr;
- WDOORBELL32(ring->doorbell_index, ring->wptr);
+ adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
+ WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
}
static void gfx_v8_0_ring_emit_fence_compute(struct amdgpu_ring *ring,
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index a881cf4..f5ee5f3 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -186,7 +186,7 @@ static int sdma_v2_4_init_microcode(struct amdgpu_device *adev)
*
* Get the current rptr from the hardware (VI+).
*/
-static uint32_t sdma_v2_4_ring_get_rptr(struct amdgpu_ring *ring)
+static uint64_t sdma_v2_4_ring_get_rptr(struct amdgpu_ring *ring)
{
/* XXX check if swapping is necessary on BE */
return ring->adev->wb.wb[ring->rptr_offs] >> 2;
@@ -199,7 +199,7 @@ static uint32_t sdma_v2_4_ring_get_rptr(struct amdgpu_ring *ring)
*
* Get the current wptr from the hardware (VI+).
*/
-static uint32_t sdma_v2_4_ring_get_wptr(struct amdgpu_ring *ring)
+static uint64_t sdma_v2_4_ring_get_wptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
@@ -220,7 +220,7 @@ static void sdma_v2_4_ring_set_wptr(struct amdgpu_ring *ring)
struct amdgpu_device *adev = ring->adev;
int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
- WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me], ring->wptr << 2);
+ WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me], lower_32_bits(ring->wptr) << 2);
}
static void sdma_v2_4_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
@@ -251,7 +251,7 @@ static void sdma_v2_4_ring_emit_ib(struct amdgpu_ring *ring,
u32 vmid = vm_id & 0xf;
/* IB packet must end on a 8 DW boundary */
- sdma_v2_4_ring_insert_nop(ring, (10 - (ring->wptr & 7)) % 8);
+ sdma_v2_4_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
SDMA_PKT_INDIRECT_HEADER_VMID(vmid));
@@ -466,7 +466,7 @@ static int sdma_v2_4_gfx_resume(struct amdgpu_device *adev)
WREG32(mmSDMA0_GFX_RB_BASE_HI + sdma_offsets[i], ring->gpu_addr >> 40);
ring->wptr = 0;
- WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[i], ring->wptr << 2);
+ WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[i], lower_32_bits(ring->wptr) << 2);
/* enable DMA RB */
rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, 1);
@@ -946,6 +946,7 @@ static int sdma_v2_4_sw_init(void *handle)
ring->ring_obj = NULL;
ring->use_doorbell = false;
sprintf(ring->name, "sdma%d", i);
+ ring->support_64bit_ptrs = false;
r = amdgpu_ring_init(adev, ring, 1024,
&adev->sdma.trap_irq,
(i == 0) ?
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 1df5b34..e715385 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -337,7 +337,7 @@ static int sdma_v3_0_init_microcode(struct amdgpu_device *adev)
*
* Get the current rptr from the hardware (VI+).
*/
-static uint32_t sdma_v3_0_ring_get_rptr(struct amdgpu_ring *ring)
+static uint64_t sdma_v3_0_ring_get_rptr(struct amdgpu_ring *ring)
{
/* XXX check if swapping is necessary on BE */
return ring->adev->wb.wb[ring->rptr_offs] >> 2;
@@ -350,7 +350,7 @@ static uint32_t sdma_v3_0_ring_get_rptr(struct amdgpu_ring *ring)
*
* Get the current wptr from the hardware (VI+).
*/
-static uint32_t sdma_v3_0_ring_get_wptr(struct amdgpu_ring *ring)
+static uint64_t sdma_v3_0_ring_get_wptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
u32 wptr;
@@ -380,12 +380,12 @@ static void sdma_v3_0_ring_set_wptr(struct amdgpu_ring *ring)
if (ring->use_doorbell) {
/* XXX check if swapping is necessary on BE */
- adev->wb.wb[ring->wptr_offs] = ring->wptr << 2;
- WDOORBELL32(ring->doorbell_index, ring->wptr << 2);
+ adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr) << 2;
+ WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr) << 2);
} else {
int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
- WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me], ring->wptr << 2);
+ WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me], lower_32_bits(ring->wptr) << 2);
}
}
@@ -417,7 +417,7 @@ static void sdma_v3_0_ring_emit_ib(struct amdgpu_ring *ring,
u32 vmid = vm_id & 0xf;
/* IB packet must end on a 8 DW boundary */
- sdma_v3_0_ring_insert_nop(ring, (10 - (ring->wptr & 7)) % 8);
+ sdma_v3_0_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
SDMA_PKT_INDIRECT_HEADER_VMID(vmid));
@@ -660,7 +660,7 @@ static int sdma_v3_0_gfx_resume(struct amdgpu_device *adev)
WREG32(mmSDMA0_GFX_RB_BASE_HI + sdma_offsets[i], ring->gpu_addr >> 40);
ring->wptr = 0;
- WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[i], ring->wptr << 2);
+ WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[i], lower_32_bits(ring->wptr) << 2);
doorbell = RREG32(mmSDMA0_GFX_DOORBELL + sdma_offsets[i]);
@@ -1165,6 +1165,7 @@ static int sdma_v3_0_sw_init(void *handle)
AMDGPU_DOORBELL_sDMA_ENGINE0 : AMDGPU_DOORBELL_sDMA_ENGINE1;
sprintf(ring->name, "sdma%d", i);
+ ring->support_64bit_ptrs = false;
r = amdgpu_ring_init(adev, ring, 1024,
&adev->sdma.trap_irq,
(i == 0) ?
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dma.c b/drivers/gpu/drm/amd/amdgpu/si_dma.c
index 3372a07..256a77b 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dma.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dma.c
@@ -37,12 +37,12 @@ static void si_dma_set_buffer_funcs(struct amdgpu_device *adev);
static void si_dma_set_vm_pte_funcs(struct amdgpu_device *adev);
static void si_dma_set_irq_funcs(struct amdgpu_device *adev);
-static uint32_t si_dma_ring_get_rptr(struct amdgpu_ring *ring)
+static uint64_t si_dma_ring_get_rptr(struct amdgpu_ring *ring)
{
return ring->adev->wb.wb[ring->rptr_offs>>2];
}
-static uint32_t si_dma_ring_get_wptr(struct amdgpu_ring *ring)
+static uint64_t si_dma_ring_get_wptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
u32 me = (ring == &adev->sdma.instance[0].ring) ? 0 : 1;
@@ -55,7 +55,8 @@ static void si_dma_ring_set_wptr(struct amdgpu_ring *ring)
struct amdgpu_device *adev = ring->adev;
u32 me = (ring == &adev->sdma.instance[0].ring) ? 0 : 1;
- WREG32(DMA_RB_WPTR + sdma_offsets[me], (ring->wptr << 2) & 0x3fffc);
+ WREG32(DMA_RB_WPTR + sdma_offsets[me],
+ (lower_32_bits(ring->wptr) << 2) & 0x3fffc);
}
static void si_dma_ring_emit_ib(struct amdgpu_ring *ring,
@@ -65,7 +66,7 @@ static void si_dma_ring_emit_ib(struct amdgpu_ring *ring,
/* The indirect buffer packet must end on an 8 DW boundary in the DMA ring.
* Pad as necessary with NOPs.
*/
- while ((ring->wptr & 7) != 5)
+ while ((lower_32_bits(ring->wptr) & 7) != 5)
amdgpu_ring_write(ring, DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0, 0));
amdgpu_ring_write(ring, DMA_IB_PACKET(DMA_PACKET_INDIRECT_BUFFER, vm_id, 0));
amdgpu_ring_write(ring, (ib->gpu_addr & 0xFFFFFFE0));
@@ -184,7 +185,7 @@ static int si_dma_start(struct amdgpu_device *adev)
WREG32(DMA_CNTL + sdma_offsets[i], dma_cntl);
ring->wptr = 0;
- WREG32(DMA_RB_WPTR + sdma_offsets[i], ring->wptr << 2);
+ WREG32(DMA_RB_WPTR + sdma_offsets[i], lower_32_bits(ring->wptr) << 2);
WREG32(DMA_RB_CNTL + sdma_offsets[i], rb_cntl | DMA_RB_ENABLE);
ring->ready = true;
@@ -530,6 +531,7 @@ static int si_dma_sw_init(void *handle)
ring->ring_obj = NULL;
ring->use_doorbell = false;
sprintf(ring->name, "sdma%d", i);
+ ring->support_64bit_ptrs = false;
r = amdgpu_ring_init(adev, ring, 1024,
&adev->sdma.trap_irq,
(i == 0) ?
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
index b34cefc..580c658 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
@@ -55,7 +55,7 @@ static void uvd_v4_2_set_dcm(struct amdgpu_device *adev,
*
* Returns the current hardware read pointer
*/
-static uint32_t uvd_v4_2_ring_get_rptr(struct amdgpu_ring *ring)
+static uint64_t uvd_v4_2_ring_get_rptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
@@ -69,7 +69,7 @@ static uint32_t uvd_v4_2_ring_get_rptr(struct amdgpu_ring *ring)
*
* Returns the current hardware write pointer
*/
-static uint32_t uvd_v4_2_ring_get_wptr(struct amdgpu_ring *ring)
+static uint64_t uvd_v4_2_ring_get_wptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
@@ -87,7 +87,7 @@ static void uvd_v4_2_ring_set_wptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
- WREG32(mmUVD_RBC_RB_WPTR, ring->wptr);
+ WREG32(mmUVD_RBC_RB_WPTR, lower_32_bits(ring->wptr));
}
static int uvd_v4_2_early_init(void *handle)
@@ -121,6 +121,7 @@ static int uvd_v4_2_sw_init(void *handle)
ring = &adev->uvd.ring;
sprintf(ring->name, "uvd");
+ ring->support_64bit_ptrs = false;
r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.irq, 0);
return r;
@@ -367,7 +368,7 @@ static int uvd_v4_2_start(struct amdgpu_device *adev)
WREG32(mmUVD_RBC_RB_RPTR, 0x0);
ring->wptr = RREG32(mmUVD_RBC_RB_RPTR);
- WREG32(mmUVD_RBC_RB_WPTR, ring->wptr);
+ WREG32(mmUVD_RBC_RB_WPTR, lower_32_bits(ring->wptr));
/* set the ring address */
WREG32(mmUVD_RBC_RB_BASE, ring->gpu_addr);
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
index ad8c02e..7a4fca0 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
@@ -51,7 +51,7 @@ static void uvd_v5_0_enable_mgcg(struct amdgpu_device *adev,
*
* Returns the current hardware read pointer
*/
-static uint32_t uvd_v5_0_ring_get_rptr(struct amdgpu_ring *ring)
+static uint64_t uvd_v5_0_ring_get_rptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
@@ -65,7 +65,7 @@ static uint32_t uvd_v5_0_ring_get_rptr(struct amdgpu_ring *ring)
*
* Returns the current hardware write pointer
*/
-static uint32_t uvd_v5_0_ring_get_wptr(struct amdgpu_ring *ring)
+static uint64_t uvd_v5_0_ring_get_wptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
@@ -83,7 +83,7 @@ static void uvd_v5_0_ring_set_wptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
- WREG32(mmUVD_RBC_RB_WPTR, ring->wptr);
+ WREG32(mmUVD_RBC_RB_WPTR, lower_32_bits(ring->wptr));
}
static int uvd_v5_0_early_init(void *handle)
@@ -117,6 +117,7 @@ static int uvd_v5_0_sw_init(void *handle)
ring = &adev->uvd.ring;
sprintf(ring->name, "uvd");
+ ring->support_64bit_ptrs = false;
r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.irq, 0);
return r;
@@ -424,7 +425,7 @@ static int uvd_v5_0_start(struct amdgpu_device *adev)
WREG32(mmUVD_RBC_RB_RPTR, 0);
ring->wptr = RREG32(mmUVD_RBC_RB_RPTR);
- WREG32(mmUVD_RBC_RB_WPTR, ring->wptr);
+ WREG32(mmUVD_RBC_RB_WPTR, lower_32_bits(ring->wptr));
WREG32_P(mmUVD_RBC_RB_CNTL, 0, ~UVD_RBC_RB_CNTL__RB_NO_FETCH_MASK);
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index 18a6de4..2c5482e 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -54,7 +54,7 @@ static void uvd_v6_0_enable_mgcg(struct amdgpu_device *adev,
*
* Returns the current hardware read pointer
*/
-static uint32_t uvd_v6_0_ring_get_rptr(struct amdgpu_ring *ring)
+static uint64_t uvd_v6_0_ring_get_rptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
@@ -68,7 +68,7 @@ static uint32_t uvd_v6_0_ring_get_rptr(struct amdgpu_ring *ring)
*
* Returns the current hardware write pointer
*/
-static uint32_t uvd_v6_0_ring_get_wptr(struct amdgpu_ring *ring)
+static uint64_t uvd_v6_0_ring_get_wptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
@@ -86,7 +86,7 @@ static void uvd_v6_0_ring_set_wptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
- WREG32(mmUVD_RBC_RB_WPTR, ring->wptr);
+ WREG32(mmUVD_RBC_RB_WPTR, lower_32_bits(ring->wptr));
}
static int uvd_v6_0_early_init(void *handle)
@@ -120,6 +120,7 @@ static int uvd_v6_0_sw_init(void *handle)
ring = &adev->uvd.ring;
sprintf(ring->name, "uvd");
+ ring->support_64bit_ptrs = false;
r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.irq, 0);
return r;
@@ -521,7 +522,7 @@ static int uvd_v6_0_start(struct amdgpu_device *adev)
WREG32(mmUVD_RBC_RB_RPTR, 0);
ring->wptr = RREG32(mmUVD_RBC_RB_RPTR);
- WREG32(mmUVD_RBC_RB_WPTR, ring->wptr);
+ WREG32(mmUVD_RBC_RB_WPTR, lower_32_bits(ring->wptr));
WREG32_FIELD(UVD_RBC_RB_CNTL, RB_NO_FETCH, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
index cb0b730f..9a4aa5e 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
@@ -52,7 +52,7 @@ static void vce_v2_0_set_irq_funcs(struct amdgpu_device *adev);
*
* Returns the current hardware read pointer
*/
-static uint32_t vce_v2_0_ring_get_rptr(struct amdgpu_ring *ring)
+static uint64_t vce_v2_0_ring_get_rptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
@@ -69,7 +69,7 @@ static uint32_t vce_v2_0_ring_get_rptr(struct amdgpu_ring *ring)
*
* Returns the current hardware write pointer
*/
-static uint32_t vce_v2_0_ring_get_wptr(struct amdgpu_ring *ring)
+static uint64_t vce_v2_0_ring_get_wptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
@@ -91,9 +91,9 @@ static void vce_v2_0_ring_set_wptr(struct amdgpu_ring *ring)
struct amdgpu_device *adev = ring->adev;
if (ring == &adev->vce.ring[0])
- WREG32(mmVCE_RB_WPTR, ring->wptr);
+ WREG32(mmVCE_RB_WPTR, lower_32_bits(ring->wptr));
else
- WREG32(mmVCE_RB_WPTR2, ring->wptr);
+ WREG32(mmVCE_RB_WPTR2, lower_32_bits(ring->wptr));
}
static int vce_v2_0_lmi_clean(struct amdgpu_device *adev)
@@ -241,15 +241,15 @@ static int vce_v2_0_start(struct amdgpu_device *adev)
vce_v2_0_mc_resume(adev);
ring = &adev->vce.ring[0];
- WREG32(mmVCE_RB_RPTR, ring->wptr);
- WREG32(mmVCE_RB_WPTR, ring->wptr);
+ WREG32(mmVCE_RB_RPTR, lower_32_bits(ring->wptr));
+ WREG32(mmVCE_RB_WPTR, lower_32_bits(ring->wptr));
WREG32(mmVCE_RB_BASE_LO, ring->gpu_addr);
WREG32(mmVCE_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
WREG32(mmVCE_RB_SIZE, ring->ring_size / 4);
ring = &adev->vce.ring[1];
- WREG32(mmVCE_RB_RPTR2, ring->wptr);
- WREG32(mmVCE_RB_WPTR2, ring->wptr);
+ WREG32(mmVCE_RB_RPTR2, lower_32_bits(ring->wptr));
+ WREG32(mmVCE_RB_WPTR2, lower_32_bits(ring->wptr));
WREG32(mmVCE_RB_BASE_LO2, ring->gpu_addr);
WREG32(mmVCE_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
WREG32(mmVCE_RB_SIZE2, ring->ring_size / 4);
@@ -446,6 +446,7 @@ static int vce_v2_0_sw_init(void *handle)
for (i = 0; i < adev->vce.num_rings; i++) {
ring = &adev->vce.ring[i];
sprintf(ring->name, "vce%d", i);
+ ring->support_64bit_ptrs = false;
r = amdgpu_ring_init(adev, ring, 512,
&adev->vce.irq, 0);
if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index 93ec881..7877a51 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -73,7 +73,7 @@ static int vce_v3_0_wait_for_idle(void *handle);
*
* Returns the current hardware read pointer
*/
-static uint32_t vce_v3_0_ring_get_rptr(struct amdgpu_ring *ring)
+static uint64_t vce_v3_0_ring_get_rptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
@@ -92,7 +92,7 @@ static uint32_t vce_v3_0_ring_get_rptr(struct amdgpu_ring *ring)
*
* Returns the current hardware write pointer
*/
-static uint32_t vce_v3_0_ring_get_wptr(struct amdgpu_ring *ring)
+static uint64_t vce_v3_0_ring_get_wptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
@@ -116,11 +116,11 @@ static void vce_v3_0_ring_set_wptr(struct amdgpu_ring *ring)
struct amdgpu_device *adev = ring->adev;
if (ring == &adev->vce.ring[0])
- WREG32(mmVCE_RB_WPTR, ring->wptr);
+ WREG32(mmVCE_RB_WPTR, lower_32_bits(ring->wptr));
else if (ring == &adev->vce.ring[1])
- WREG32(mmVCE_RB_WPTR2, ring->wptr);
+ WREG32(mmVCE_RB_WPTR2, lower_32_bits(ring->wptr));
else
- WREG32(mmVCE_RB_WPTR3, ring->wptr);
+ WREG32(mmVCE_RB_WPTR3, lower_32_bits(ring->wptr));
}
static void vce_v3_0_override_vce_clock_gating(struct amdgpu_device *adev, bool override)
@@ -231,22 +231,22 @@ static int vce_v3_0_start(struct amdgpu_device *adev)
int idx, r;
ring = &adev->vce.ring[0];
- WREG32(mmVCE_RB_RPTR, ring->wptr);
- WREG32(mmVCE_RB_WPTR, ring->wptr);
+ WREG32(mmVCE_RB_RPTR, lower_32_bits(ring->wptr));
+ WREG32(mmVCE_RB_WPTR, lower_32_bits(ring->wptr));
WREG32(mmVCE_RB_BASE_LO, ring->gpu_addr);
WREG32(mmVCE_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
WREG32(mmVCE_RB_SIZE, ring->ring_size / 4);
ring = &adev->vce.ring[1];
- WREG32(mmVCE_RB_RPTR2, ring->wptr);
- WREG32(mmVCE_RB_WPTR2, ring->wptr);
+ WREG32(mmVCE_RB_RPTR2, lower_32_bits(ring->wptr));
+ WREG32(mmVCE_RB_WPTR2, lower_32_bits(ring->wptr));
WREG32(mmVCE_RB_BASE_LO2, ring->gpu_addr);
WREG32(mmVCE_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
WREG32(mmVCE_RB_SIZE2, ring->ring_size / 4);
ring = &adev->vce.ring[2];
- WREG32(mmVCE_RB_RPTR3, ring->wptr);
- WREG32(mmVCE_RB_WPTR3, ring->wptr);
+ WREG32(mmVCE_RB_RPTR3, lower_32_bits(ring->wptr));
+ WREG32(mmVCE_RB_WPTR3, lower_32_bits(ring->wptr));
WREG32(mmVCE_RB_BASE_LO3, ring->gpu_addr);
WREG32(mmVCE_RB_BASE_HI3, upper_32_bits(ring->gpu_addr));
WREG32(mmVCE_RB_SIZE3, ring->ring_size / 4);
@@ -403,6 +403,7 @@ static int vce_v3_0_sw_init(void *handle)
for (i = 0; i < adev->vce.num_rings; i++) {
ring = &adev->vce.ring[i];
sprintf(ring->name, "vce%d", i);
+ ring->support_64bit_ptrs = false;
r = amdgpu_ring_init(adev, ring, 512, &adev->vce.irq, 0);
if (r)
return r;
--
2.5.5
