devres teardown is LIFO. The aperture devres node was registered after
the DRM device node, so devres_release_all() unmaps the aperture before
the DRM device release callback fires amdgpu_device_fini_sw(). IP
sw_fini callbacks (e.g. vcn_v4_0_sw_fini) write to fw_shared through a
pointer derived from aper_base_kaddr, causing a kernel page fault on
probe failure / rollback:
BUG: unable to handle page fault ... PMD 0
RIP: vcn_v4_0_sw_fini+0x7b/0x170 [amdgpu]
Call Trace:
amdgpu_device_fini_sw
amdgpu_driver_release_kms
devm_drm_dev_init_release
devres_release_all
This reverts commit 3763eacdfba23f3d642dda8d23f0e261653fe7fe.
Fixes: 3763eacdfba2 ("drm/amdgpu: fix aperture mapping leak")
Reported-by: Yuansheng Mao <[email protected]>
Closes: https://gitlab.freedesktop.org/drm/amd/issues/SWDEV-599369
Signed-off-by: Asad Kamal <[email protected]>
Reviewed-by: Lijo Lazar <[email protected]>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 ++
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 34 ++++++++++++----------
2 files changed, 20 insertions(+), 16 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 638dfaf127fd..964efec0d335 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4185,6 +4185,8 @@ 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 */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index c4094edbdff1..0b00625603c0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -2139,23 +2139,17 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
/* Change the size here instead of the init above so only lpfn is
affected */
amdgpu_ttm_disable_buffer_funcs(adev);
#ifdef CONFIG_64BIT
- 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) {
+#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)
DRM_DEBUG_DRIVER(
"No need to ioremap when real vram size is 0\n");
- } 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;
- }
+ else
+#endif
+ adev->mman.aper_base_kaddr = ioremap_wc(adev->gmc.aper_base,
+ adev->gmc.visible_vram_size);
#endif
amdgpu_ttm_init_vram_resv_regions(adev);
@@ -2284,6 +2278,7 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
*/
void amdgpu_ttm_fini(struct amdgpu_device *adev)
{
+ int idx;
if (!adev->mman.initialized)
return;
@@ -2306,7 +2301,14 @@ void amdgpu_ttm_fini(struct amdgpu_device *adev)
amdgpu_ttm_unmark_vram_reserved(adev, AMDGPU_RESV_FW_VRAM_USAGE);
amdgpu_ttm_unmark_vram_reserved(adev, AMDGPU_RESV_DRV_VRAM_USAGE);
- adev->mman.aper_base_kaddr = NULL;
+ 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);
+ }
if (!adev->gmc.is_app_apu)
amdgpu_vram_mgr_fini(adev);
--
2.46.0
