drm/amdgpu: fix aperture mapping leak

commit ea772a440d upstream.

amdgpu_pci_remove() calls drm_dev_unplug() before invoking the driver
fini routines. This causes drm_dev_enter() in amdgpu_ttm_fini() to
always return false, so iounmap(aper_base_kaddr) never runs on normal
driver unload, leaving an orphaned entry in the x86 PAT interval tree.

On connected_to_cpu hardware, the aperture is mapped write-back (WB) via
ioremap_cache(). On reload, IP discovery calls memremap(..., MEMREMAP_WC)
over the same range. The WC vs WB conflict causes:

  ioremap error for 0x..., requested 0x1, got 0x0
  amdgpu: discovery failed: -2

Fix by switching to devres-managed mappings so cleanup is guaranteed
regardless of drm_dev_enter() state:

- connected_to_cpu path: devm_memremap(MEMREMAP_WB). For
  IORESOURCE_SYSTEM_RAM ranges this takes the try_ram_remap() shortcut,
  returning __va(offset) from the existing kernel direct map. No new
  ioremap VA or PAT entry is created, so there is nothing to orphan.

- dGPU path: devm_ioremap_wc() registers iounmap() as a devres action,
  guaranteeing cleanup at device_del() time.

Also remove iounmap(aper_base_kaddr) from amdgpu_device_unmap_mmio()
since the mapping is now devres-owned.

v2: Remove redundant x86_64 guard (Lijo)

Fixes: 9d0af8b4de ("drm/amdgpu: pre-map device buffer as cached for A+A config")
Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit d871e99879)
Cc: stable@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

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

@@ -3977,8 +3977,6 @@ static void amdgpu_device_unmap_mmio(struct amdgpu_device *adev)
 
 	iounmap(adev->rmmio);
 	adev->rmmio = NULL;
-	if (adev->mman.aper_base_kaddr)
-		iounmap(adev->mman.aper_base_kaddr);
 	adev->mman.aper_base_kaddr = NULL;
 
 	/* Memory manager related */

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

@@ -1887,18 +1887,23 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 	/* Change the size here instead of the init above so only lpfn is affected */
 	amdgpu_ttm_set_buffer_funcs_status(adev, false);
 #ifdef CONFIG_64BIT
-#ifdef CONFIG_X86
-	if (adev->gmc.xgmi.connected_to_cpu)
-		adev->mman.aper_base_kaddr = ioremap_cache(adev->gmc.aper_base,
-				adev->gmc.visible_vram_size);
-
-	else if (adev->gmc.is_app_apu)
+	if (adev->gmc.xgmi.connected_to_cpu) {
+		void *kaddr = devm_memremap(adev->dev, adev->gmc.aper_base,
+					    adev->gmc.visible_vram_size,
+					    MEMREMAP_WB);
+		if (IS_ERR(kaddr))
+			return PTR_ERR(kaddr);
+		adev->mman.aper_base_kaddr = (__force void __iomem *)kaddr;
+	} else if (adev->gmc.is_app_apu) {
 		DRM_DEBUG_DRIVER(
 			"No need to ioremap when real vram size is 0\n");
-	else
-#endif
-		adev->mman.aper_base_kaddr = ioremap_wc(adev->gmc.aper_base,
-				adev->gmc.visible_vram_size);
+	} else {
+		adev->mman.aper_base_kaddr = devm_ioremap_wc(adev->dev,
+							     adev->gmc.aper_base,
+							     adev->gmc.visible_vram_size);
+		if (!adev->mman.aper_base_kaddr)
+			return -ENOMEM;
+	}
 #endif
 
 	/*
@@ -2033,8 +2038,6 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
  */
 void amdgpu_ttm_fini(struct amdgpu_device *adev)
 {
-	int idx;
-
 	if (!adev->mman.initialized)
 		return;
 
@@ -2057,14 +2060,7 @@ void amdgpu_ttm_fini(struct amdgpu_device *adev)
 	amdgpu_ttm_fw_reserve_vram_fini(adev);
 	amdgpu_ttm_drv_reserve_vram_fini(adev);
 
-	if (drm_dev_enter(adev_to_drm(adev), &idx)) {
-
-		if (adev->mman.aper_base_kaddr)
-			iounmap(adev->mman.aper_base_kaddr);
-		adev->mman.aper_base_kaddr = NULL;
-
-		drm_dev_exit(idx);
-	}
+	adev->mman.aper_base_kaddr = NULL;
 
 	amdgpu_vram_mgr_fini(adev);
 	amdgpu_gtt_mgr_fini(adev);