drm/amdgpu: simplify padding calculations (v2)

Simplify padding calculations.

v2: Comment update and spacing.
Signed-off-by: Luben Tuikov <luben.tuikov@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/cik_sdma.c

@@ -228,7 +228,7 @@ static void cik_sdma_ring_emit_ib(struct amdgpu_ring *ring,
 	u32 extra_bits = vmid & 0xf;
 
 	/* IB packet must end on a 8 DW boundary */
-	cik_sdma_ring_insert_nop(ring, (12 - (lower_32_bits(ring->wptr) & 7)) % 8);
+	cik_sdma_ring_insert_nop(ring, (4 - lower_32_bits(ring->wptr)) & 7);
 
 	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 */
@@ -811,7 +811,7 @@ static void cik_sdma_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib)
 	u32 pad_count;
 	int i;
 
-	pad_count = (8 - (ib->length_dw & 0x7)) % 8;
+	pad_count = (-ib->length_dw) & 7;
 	for (i = 0; i < pad_count; i++)
 		if (sdma && sdma->burst_nop && (i == 0))
 			ib->ptr[ib->length_dw++] =

drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c

@@ -255,7 +255,7 @@ static void sdma_v2_4_ring_emit_ib(struct amdgpu_ring *ring,
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 
 	/* IB packet must end on a 8 DW boundary */
-	sdma_v2_4_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
+	sdma_v2_4_ring_insert_nop(ring, (2 - lower_32_bits(ring->wptr)) & 7);
 
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
 			  SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
@@ -750,7 +750,7 @@ static void sdma_v2_4_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib
 	u32 pad_count;
 	int i;
 
-	pad_count = (8 - (ib->length_dw & 0x7)) % 8;
+	pad_count = (-ib->length_dw) & 7;
 	for (i = 0; i < pad_count; i++)
 		if (sdma && sdma->burst_nop && (i == 0))
 			ib->ptr[ib->length_dw++] =

drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c

@@ -429,7 +429,7 @@ static void sdma_v3_0_ring_emit_ib(struct amdgpu_ring *ring,
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 
 	/* IB packet must end on a 8 DW boundary */
-	sdma_v3_0_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
+	sdma_v3_0_ring_insert_nop(ring, (2 - lower_32_bits(ring->wptr)) & 7);
 
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
 			  SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
@@ -1021,7 +1021,7 @@ static void sdma_v3_0_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib
 	u32 pad_count;
 	int i;
 
-	pad_count = (8 - (ib->length_dw & 0x7)) % 8;
+	pad_count = (-ib->length_dw) & 7;
 	for (i = 0; i < pad_count; i++)
 		if (sdma && sdma->burst_nop && (i == 0))
 			ib->ptr[ib->length_dw++] =

drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c

@@ -698,7 +698,7 @@ static void sdma_v4_0_ring_emit_ib(struct amdgpu_ring *ring,
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 
 	/* IB packet must end on a 8 DW boundary */
-	sdma_v4_0_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
+	sdma_v4_0_ring_insert_nop(ring, (2 - lower_32_bits(ring->wptr)) & 7);
 
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
 			  SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
@@ -1579,7 +1579,7 @@ static void sdma_v4_0_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib
 	u32 pad_count;
 	int i;
 
-	pad_count = (8 - (ib->length_dw & 0x7)) % 8;
+	pad_count = (-ib->length_dw) & 7;
 	for (i = 0; i < pad_count; i++)
 		if (sdma && sdma->burst_nop && (i == 0))
 			ib->ptr[ib->length_dw++] =

drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c

@@ -382,8 +382,15 @@ static void sdma_v5_0_ring_emit_ib(struct amdgpu_ring *ring,
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 	uint64_t csa_mc_addr = amdgpu_sdma_get_csa_mc_addr(ring, vmid);
 
-	/* IB packet must end on a 8 DW boundary */
-	sdma_v5_0_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
+	/* An IB packet must end on a 8 DW boundary--the next dword
+	 * must be on a 8-dword boundary. Our IB packet below is 6
+	 * dwords long, thus add x number of NOPs, such that, in
+	 * modular arithmetic,
+	 * wptr + 6 + x = 8k, k >= 0, which in C is,
+	 * (wptr + 6 + x) % 8 = 0.
+	 * The expression below, is a solution of x.
+	 */
+	sdma_v5_0_ring_insert_nop(ring, (2 - lower_32_bits(ring->wptr)) & 7);
 
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
 			  SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
@@ -1076,10 +1083,10 @@ static void sdma_v5_0_vm_set_pte_pde(struct amdgpu_ib *ib,
 }
 
 /**
- * sdma_v5_0_ring_pad_ib - pad the IB to the required number of dw
- *
+ * sdma_v5_0_ring_pad_ib - pad the IB
  * @ib: indirect buffer to fill with padding
  *
+ * Pad the IB with NOPs to a boundary multiple of 8.
  */
 static void sdma_v5_0_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib)
 {
@@ -1087,7 +1094,7 @@ static void sdma_v5_0_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib
 	u32 pad_count;
 	int i;
 
-	pad_count = (8 - (ib->length_dw & 0x7)) % 8;
+	pad_count = (-ib->length_dw) & 0x7;
 	for (i = 0; i < pad_count; i++)
 		if (sdma && sdma->burst_nop && (i == 0))
 			ib->ptr[ib->length_dw++] =