drm/amdgpu/gfx8: add ring reset callback for gfx

Add ring reset callback for gfx.

v2: fix operator precedence (kernel test robot)
Acked-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c

@@ -6149,6 +6149,7 @@ static void gfx_v8_0_ring_emit_fence_gfx(struct amdgpu_ring *ring, u64 addr,
 {
 	bool write64bit = flags & AMDGPU_FENCE_FLAG_64BIT;
 	bool int_sel = flags & AMDGPU_FENCE_FLAG_INT;
+	bool exec = flags & AMDGPU_FENCE_FLAG_EXEC;
 
 	/* Workaround for cache flush problems. First send a dummy EOP
 	 * event down the pipe with seq one below.
@@ -6172,7 +6173,8 @@ static void gfx_v8_0_ring_emit_fence_gfx(struct amdgpu_ring *ring, u64 addr,
 				 EOP_TC_ACTION_EN |
 				 EOP_TC_WB_ACTION_EN |
 				 EVENT_TYPE(CACHE_FLUSH_AND_INV_TS_EVENT) |
-				 EVENT_INDEX(5)));
+				 EVENT_INDEX(5) |
+				 (exec ? EOP_EXEC : 0)));
 	amdgpu_ring_write(ring, addr & 0xfffffffc);
 	amdgpu_ring_write(ring, (upper_32_bits(addr) & 0xffff) |
 			  DATA_SEL(write64bit ? 2 : 1) | INT_SEL(int_sel ? 2 : 0));
@@ -6380,6 +6382,34 @@ static void gfx_v8_0_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg,
 	amdgpu_ring_write(ring, val);
 }
 
+static void gfx_v8_0_wait_reg_mem(struct amdgpu_ring *ring, int eng_sel,
+				  int mem_space, int opt, uint32_t addr0,
+				  uint32_t addr1, uint32_t ref, uint32_t mask,
+				  uint32_t inv)
+{
+	amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5));
+	amdgpu_ring_write(ring,
+			  /* memory (1) or register (0) */
+			  (WAIT_REG_MEM_MEM_SPACE(mem_space) |
+			   WAIT_REG_MEM_OPERATION(opt) | /* wait */
+			   WAIT_REG_MEM_FUNCTION(3) |  /* equal */
+			   WAIT_REG_MEM_ENGINE(eng_sel)));
+
+	if (mem_space)
+		BUG_ON(addr0 & 0x3); /* Dword align */
+	amdgpu_ring_write(ring, addr0);
+	amdgpu_ring_write(ring, addr1);
+	amdgpu_ring_write(ring, ref);
+	amdgpu_ring_write(ring, mask);
+	amdgpu_ring_write(ring, inv); /* poll interval */
+}
+
+static void gfx_v8_0_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
+					uint32_t val, uint32_t mask)
+{
+	gfx_v8_0_wait_reg_mem(ring, 0, 0, 0, reg, 0, val, mask, 0x20);
+}
+
 static void gfx_v8_0_ring_soft_recovery(struct amdgpu_ring *ring, unsigned vmid)
 {
 	struct amdgpu_device *adev = ring->adev;
@@ -6856,6 +6886,48 @@ static void gfx_v8_0_emit_wave_limit(struct amdgpu_ring *ring, bool enable)
 
 }
 
+static int gfx_v8_0_reset_kgq(struct amdgpu_ring *ring, unsigned int vmid)
+{
+	struct amdgpu_device *adev = ring->adev;
+	struct amdgpu_kiq *kiq = &adev->gfx.kiq[0];
+	struct amdgpu_ring *kiq_ring = &kiq->ring;
+	unsigned long flags;
+	u32 tmp;
+	int r;
+
+	if (amdgpu_sriov_vf(adev))
+		return -EINVAL;
+
+	if (!kiq->pmf || !kiq->pmf->kiq_unmap_queues)
+		return -EINVAL;
+
+	spin_lock_irqsave(&kiq->ring_lock, flags);
+
+	if (amdgpu_ring_alloc(kiq_ring, 5)) {
+		spin_unlock_irqrestore(&kiq->ring_lock, flags);
+		return -ENOMEM;
+	}
+
+	tmp = REG_SET_FIELD(0, CP_VMID_RESET, RESET_REQUEST, 1 << vmid);
+	gfx_v8_0_ring_emit_wreg(kiq_ring, mmCP_VMID_RESET, tmp);
+	amdgpu_ring_commit(kiq_ring);
+
+	spin_unlock_irqrestore(&kiq->ring_lock, flags);
+
+	r = amdgpu_ring_test_ring(kiq_ring);
+	if (r)
+		return r;
+
+	if (amdgpu_ring_alloc(ring, 7 + 12 + 5))
+		return -ENOMEM;
+	gfx_v8_0_ring_emit_fence_gfx(ring, ring->fence_drv.gpu_addr,
+				     ring->fence_drv.sync_seq, AMDGPU_FENCE_FLAG_EXEC);
+	gfx_v8_0_ring_emit_reg_wait(ring, mmCP_VMID_RESET, 0, 0xffff);
+	gfx_v8_0_ring_emit_wreg(ring, mmCP_VMID_RESET, 0);
+
+	return amdgpu_ring_test_ring(ring);
+}
+
 static const struct amd_ip_funcs gfx_v8_0_ip_funcs = {
 	.name = "gfx_v8_0",
 	.early_init = gfx_v8_0_early_init,
@@ -6923,6 +6995,7 @@ static const struct amdgpu_ring_funcs gfx_v8_0_ring_funcs_gfx = {
 	.emit_wreg = gfx_v8_0_ring_emit_wreg,
 	.soft_recovery = gfx_v8_0_ring_soft_recovery,
 	.emit_mem_sync = gfx_v8_0_emit_mem_sync,
+	.reset = gfx_v8_0_reset_kgq,
 };
 
 static const struct amdgpu_ring_funcs gfx_v8_0_ring_funcs_compute = {

drivers/gpu/drm/amd/amdgpu/vid.h

@@ -246,6 +246,7 @@
 		 * 1 - Stream
 		 * 2 - Bypass
 		 */
+#define		EOP_EXEC				(1 << 28) /* For Trailing Fence */
 #define		DATA_SEL(x)                             ((x) << 29)
 		/* 0 - discard
 		 * 1 - send low 32bit data