Merge tag 'drm-fixes-2024-02-09' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Regular weekly fixes, xe, amdgpu and msm are most of them, with some
  misc in i915, ivpu and nouveau, scattered but nothing too intense at
  this point.

  i915:
   - gvt: docs fix, uninit var, MAINTAINERS

  ivpu:
   - add aborted job status
   - disable d3 hot delay
   - mmu fixes

  nouveau:
   - fix gsp rpc size request
   - fix dma buffer leaks
   - use common code for gsp mem ctor

  xe:
   - Fix a loop in an error path
   - Fix a missing dma-fence reference
   - Fix a retry path on userptr REMAP
   - Workaround for a false gcc warning
   - Fix missing map of the usm batch buffer in the migrate vm.
   - Fix a memory leak.
   - Fix a bad assumption of used page size
   - Fix hitting a BUG() due to zero pages to map.
   - Remove some leftover async bind queue relics

  amdgpu:
   - Misc NULL/bounds check fixes
   - ODM pipe policy fix
   - Aborted suspend fixes
   - JPEG 4.0.5 fix
   - DCN 3.5 fixes
   - PSP fix
   - DP MST fix
   - Phantom pipe fix
   - VRAM vendor fix
   - Clang fix
   - SR-IOV fix

  msm:
   - DPU:
      - fix for kernel doc warnings and smatch warnings in dpu_encoder
      - fix for smatch warning in dpu_encoder
      - fix the bus bandwidth value for SDM670
   - DP:
      - fixes to handle unknown bpc case correctly for DP
      - fix for MISC0 programming
   - GPU:
      - dmabuf vmap fix
      - a610 UBWC corruption fix (incorrect hbb)
      - revert a commit that was making GPU recovery unreliable"

* tag 'drm-fixes-2024-02-09' of git://anongit.freedesktop.org/drm/drm: (43 commits)
  drm/xe: Remove TEST_VM_ASYNC_OPS_ERROR
  drm/xe/vm: don't ignore error when in_kthread
  drm/xe: Assume large page size if VMA not yet bound
  drm/xe/display: Fix memleak in display initialization
  drm/xe: Map both mem.kernel_bb_pool and usm.bb_pool
  drm/xe: circumvent bogus stringop-overflow warning
  drm/xe: Pick correct userptr VMA to repin on REMAP op failure
  drm/xe: Take a reference in xe_exec_queue_last_fence_get()
  drm/xe: Fix loop in vm_bind_ioctl_ops_unwind
  drm/amdgpu: Fix HDP flush for VFs on nbio v7.9
  drm/amd/display: Implement bounds check for stream encoder creation in DCN301
  drm/amd/display: Increase frame-larger-than for all display_mode_vba files
  drm/amd/display: Clear phantom stream count and plane count
  drm/amdgpu: Avoid fetching VRAM vendor info
  drm/amd/display: Disable ODM by default for DCN35
  drm/amd/display: Update phantom pipe enable / disable sequence
  drm/amd/display: Fix MST Null Ptr for RV
  drm/amdgpu: Fix shared buff copy to user
  drm/amd/display: Increase eval/entry delay for DCN35
  drm/amdgpu: remove asymmetrical irq disabling in jpeg 4.0.5 suspend
  ...

2 files changed, 48 insertions, 31 deletions

diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
index d1437c08645f..6f5d376d8fcc 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
@@ -9,7 +9,7 @@
 #define GSP_PAGE_SIZE  BIT(GSP_PAGE_SHIFT)
 
 struct nvkm_gsp_mem {
-	u32 size;
+	size_t size;
 	void *data;
 	dma_addr_t addr;
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
index 5e1fa176aac4..a41735ab6068 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
@@ -997,6 +997,32 @@ r535_gsp_rpc_get_gsp_static_info(struct nvkm_gsp *gsp)
 	return 0;
 }
 
+static void
+nvkm_gsp_mem_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_mem *mem)
+{
+	if (mem->data) {
+		/*
+		 * Poison the buffer to catch any unexpected access from
+		 * GSP-RM if the buffer was prematurely freed.
+		 */
+		memset(mem->data, 0xFF, mem->size);
+
+		dma_free_coherent(gsp->subdev.device->dev, mem->size, mem->data, mem->addr);
+		memset(mem, 0, sizeof(*mem));
+	}
+}
+
+static int
+nvkm_gsp_mem_ctor(struct nvkm_gsp *gsp, size_t size, struct nvkm_gsp_mem *mem)
+{
+	mem->size = size;
+	mem->data = dma_alloc_coherent(gsp->subdev.device->dev, size, &mem->addr, GFP_KERNEL);
+	if (WARN_ON(!mem->data))
+		return -ENOMEM;
+
+	return 0;
+}
+
 static int
 r535_gsp_postinit(struct nvkm_gsp *gsp)
 {
@@ -1024,6 +1050,13 @@ r535_gsp_postinit(struct nvkm_gsp *gsp)
 
 	nvkm_inth_allow(&gsp->subdev.inth);
 	nvkm_wr32(device, 0x110004, 0x00000040);
+
+	/* Release the DMA buffers that were needed only for boot and init */
+	nvkm_gsp_mem_dtor(gsp, &gsp->boot.fw);
+	nvkm_gsp_mem_dtor(gsp, &gsp->libos);
+	nvkm_gsp_mem_dtor(gsp, &gsp->rmargs);
+	nvkm_gsp_mem_dtor(gsp, &gsp->wpr_meta);
+
 	return ret;
 }
 
@@ -1532,27 +1565,6 @@ r535_gsp_msg_run_cpu_sequencer(void *priv, u32 fn, void *repv, u32 repc)
 	return 0;
 }
 
-static void
-nvkm_gsp_mem_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_mem *mem)
-{
-	if (mem->data) {
-		dma_free_coherent(gsp->subdev.device->dev, mem->size, mem->data, mem->addr);
-		mem->data = NULL;
-	}
-}
-
-static int
-nvkm_gsp_mem_ctor(struct nvkm_gsp *gsp, u32 size, struct nvkm_gsp_mem *mem)
-{
-	mem->size = size;
-	mem->data = dma_alloc_coherent(gsp->subdev.device->dev, size, &mem->addr, GFP_KERNEL);
-	if (WARN_ON(!mem->data))
-		return -ENOMEM;
-
-	return 0;
-}
-
-
 static int
 r535_gsp_booter_unload(struct nvkm_gsp *gsp, u32 mbox0, u32 mbox1)
 {
@@ -1938,20 +1950,20 @@ nvkm_gsp_radix3_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_radix3 *rx3)
  * See kgspCreateRadix3_IMPL
  */
 static int
-nvkm_gsp_radix3_sg(struct nvkm_device *device, struct sg_table *sgt, u64 size,
+nvkm_gsp_radix3_sg(struct nvkm_gsp *gsp, struct sg_table *sgt, u64 size,
 		   struct nvkm_gsp_radix3 *rx3)
 {
 	u64 addr;
 
 	for (int i = ARRAY_SIZE(rx3->mem) - 1; i >= 0; i--) {
 		u64 *ptes;
-		int idx;
+		size_t bufsize;
+		int ret, idx;
 
-		rx3->mem[i].size = ALIGN((size / GSP_PAGE_SIZE) * sizeof(u64), GSP_PAGE_SIZE);
-		rx3->mem[i].data = dma_alloc_coherent(device->dev, rx3->mem[i].size,
-						      &rx3->mem[i].addr, GFP_KERNEL);
-		if (WARN_ON(!rx3->mem[i].data))
-			return -ENOMEM;
+		bufsize = ALIGN((size / GSP_PAGE_SIZE) * sizeof(u64), GSP_PAGE_SIZE);
+		ret = nvkm_gsp_mem_ctor(gsp, bufsize, &rx3->mem[i]);
+		if (ret)
+			return ret;
 
 		ptes = rx3->mem[i].data;
 		if (i == 2) {
@@ -1991,7 +2003,7 @@ r535_gsp_fini(struct nvkm_gsp *gsp, bool suspend)
 		if (ret)
 			return ret;
 
-		ret = nvkm_gsp_radix3_sg(gsp->subdev.device, &gsp->sr.sgt, len, &gsp->sr.radix3);
+		ret = nvkm_gsp_radix3_sg(gsp, &gsp->sr.sgt, len, &gsp->sr.radix3);
 		if (ret)
 			return ret;
 
@@ -2150,6 +2162,11 @@ r535_gsp_dtor(struct nvkm_gsp *gsp)
 	mutex_destroy(&gsp->cmdq.mutex);
 
 	r535_gsp_dtor_fws(gsp);
+
+	nvkm_gsp_mem_dtor(gsp, &gsp->shm.mem);
+	nvkm_gsp_mem_dtor(gsp, &gsp->loginit);
+	nvkm_gsp_mem_dtor(gsp, &gsp->logintr);
+	nvkm_gsp_mem_dtor(gsp, &gsp->logrm);
 }
 
 int
@@ -2194,7 +2211,7 @@ r535_gsp_oneinit(struct nvkm_gsp *gsp)
 	memcpy(gsp->sig.data, data, size);
 
 	/* Build radix3 page table for ELF image. */
-	ret = nvkm_gsp_radix3_sg(device, &gsp->fw.mem.sgt, gsp->fw.len, &gsp->radix3);
+	ret = nvkm_gsp_radix3_sg(gsp, &gsp->fw.mem.sgt, gsp->fw.len, &gsp->radix3);
 	if (ret)
 		return ret;