[PATCH V4 3/3] drm/amdgpu/sdma_v4_4_2: update VM flush implementation for SDMA

[Jesse.zhang@amd.com]

From: "Jesse.zhang at amd.com" <Jesse.zhang at amd.com>

This commit updates the VM flush implementation for the SDMA engine.

- Added a new function `sdma_v4_4_2_get_invalidate_req` to construct the VM_INVALIDATE_ENG0_REQ
  register value for the specified VMID and flush type. This function ensures that all relevant
  page table cache levels (L1 PTEs, L2 PTEs, and L2 PDEs) are invalidated.

- Modified the `sdma_v4_4_2_ring_emit_vm_flush` function to use the new `sdma_v4_4_2_get_invalidate_req`
  function. The updated function emits the necessary register writes and waits to perform a VM flush
  for the specified VMID. It updates the PTB address registers and issues a VM invalidation request
  using the specified VM invalidation engine.

- Included the necessary header file `gc/gc_9_0_sh_mask.h` to provide access to the required register
  definitions.

Suggested-by: Lijo Lazar <lijo.lazar at amd.com>
Signed-off-by: Jesse Zhang <jesse.zhang at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c | 66 ++++++++++++++++++++----
 1 file changed, 57 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
index ba43c8f46f45..f9cec50ce54e 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
@@ -31,6 +31,7 @@
 #include "amdgpu_ucode.h"
 #include "amdgpu_trace.h"
 #include "amdgpu_reset.h"
+#include "gc/gc_9_0_sh_mask.h"
 
 #include "sdma/sdma_4_4_2_offset.h"
 #include "sdma/sdma_4_4_2_sh_mask.h"
@@ -1292,21 +1293,68 @@ static void sdma_v4_4_2_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
 			       seq, 0xffffffff, 4);
 }
 
-
-/**
- * sdma_v4_4_2_ring_emit_vm_flush - vm flush using sDMA
+/*
+ * sdma_v4_4_2_get_invalidate_req - Construct the VM_INVALIDATE_ENG0_REQ register value
+ * @vmid: The VMID to invalidate
+ * @flush_type: The type of flush (0 = legacy, 1 = lightweight, 2 = heavyweight)
  *
- * @ring: amdgpu_ring pointer
- * @vmid: vmid number to use
- * @pd_addr: address
+ * This function constructs the VM_INVALIDATE_ENG0_REQ register value for the specified VMID
+ * and flush type. It ensures that all relevant page table cache levels (L1 PTEs, L2 PTEs, and
+ * L2 PDEs) are invalidated.
+ */
+static uint32_t sdma_v4_4_2_get_invalidate_req(unsigned int vmid,
+					uint32_t flush_type)
+{
+	u32 req = 0;
+
+	req = REG_SET_FIELD(req, VM_INVALIDATE_ENG0_REQ,
+			    PER_VMID_INVALIDATE_REQ, 1 << vmid);
+	req = REG_SET_FIELD(req, VM_INVALIDATE_ENG0_REQ, FLUSH_TYPE, flush_type);
+	req = REG_SET_FIELD(req, VM_INVALIDATE_ENG0_REQ, INVALIDATE_L2_PTES, 1);
+	req = REG_SET_FIELD(req, VM_INVALIDATE_ENG0_REQ, INVALIDATE_L2_PDE0, 1);
+	req = REG_SET_FIELD(req, VM_INVALIDATE_ENG0_REQ, INVALIDATE_L2_PDE1, 1);
+	req = REG_SET_FIELD(req, VM_INVALIDATE_ENG0_REQ, INVALIDATE_L2_PDE2, 1);
+	req = REG_SET_FIELD(req, VM_INVALIDATE_ENG0_REQ, INVALIDATE_L1_PTES, 1);
+	req = REG_SET_FIELD(req, VM_INVALIDATE_ENG0_REQ,
+			    CLEAR_PROTECTION_FAULT_STATUS_ADDR,	0);
+
+	return req;
+}
+
+/*
+ * sdma_v4_4_2_ring_emit_vm_flush - Emit VM flush commands for SDMA
+ * @ring: The SDMA ring
+ * @vmid: The VMID to flush
+ * @pd_addr: The page directory address
  *
- * Update the page table base and flush the VM TLB
- * using sDMA.
+ * This function emits the necessary register writes and waits to perform a VM flush for the
+ * specified VMID. It updates the PTB address registers and issues a VM invalidation request
+ * using the specified VM invalidation engine.
  */
 static void sdma_v4_4_2_ring_emit_vm_flush(struct amdgpu_ring *ring,
 					 unsigned vmid, uint64_t pd_addr)
 {
-	amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
+	struct amdgpu_device *adev = ring->adev;
+	struct amdgpu_vmhub *hub = &adev->vmhub[ring->vm_hub];
+	uint32_t req = sdma_v4_4_2_get_invalidate_req(vmid, 0);
+	unsigned int eng = ring->vm_inv_eng;
+
+	/* Update the PTB address for the specified VMID */
+	amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_lo32 +
+			      (hub->ctx_addr_distance * vmid),
+			      lower_32_bits(pd_addr));
+
+	amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_hi32 +
+			      (hub->ctx_addr_distance * vmid),
+			      upper_32_bits(pd_addr));
+
+	/* Issue the VM invalidation request and wait for acknowledgment */
+	amdgpu_ring_emit_reg_write_reg_wait(ring, hub->vm_inv_eng0_req +
+					    hub->eng_distance * eng,
+					    hub->vm_inv_eng0_ack +
+					    hub->eng_distance * eng,
+					    req, 1 << vmid);
+
 }
 
 static void sdma_v4_4_2_ring_emit_wreg(struct amdgpu_ring *ring,
-- 
2.25.1