drm/amdgpu: fix modprobe failure of the secondary GPU when GDDR6 training enabled(V5)

[why]
In dual GPUs scenario, stolen_size is assigned to zero on the secondary GPU,
since there is no pre-OS console using that memory. Then the bottom region of
VRAM was allocated as GTT, unfortunately a small region of bottom VRAM was
encroached by UMC firmware during GDDR6 BIST training, this cause page fault.

[how]
Forcing stolen_size to 3MB, then the bottom region of VRAM was
allocated as stolen memory, GTT corruption avoid.

Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Tianci.Yin <tianci.yin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
index d3c27a3c43f68ad5ed11ff5b0379d8d06c648d13..86267baca07ccda96234ce9304cfa46a841e43ff 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
@@ -60,6 +60,11 @@
  */
 #define AMDGPU_GMC_FAULT_TIMEOUT       5000ULL
 
+/*
+ * Default stolen memory size, 1024 * 768 * 4
+ */
+#define AMDGPU_STOLEN_BIST_TRAINING_DEFAULT_SIZE       0x300000ULL
+
 struct firmware;
 
 /*

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 8afd058347142afe90a9212a6b9d116d83e63b0b..bbede09983e1d2edfc0d1803ed8f6e6fb0019161 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -640,7 +640,12 @@ static int gmc_v10_0_late_init(void *handle)
        struct amdgpu_device *adev = (struct amdgpu_device *)handle;
        int r;
 
-       amdgpu_bo_late_init(adev);
+       /*
+        * Can't free the stolen VGA memory when it might be used for memory
+        * training again.
+        */
+       if (!adev->fw_vram_usage.mem_train_support)
+               amdgpu_bo_late_init(adev);
 
        r = amdgpu_gmc_allocate_vm_inv_eng(adev);
        if (r)
@@ -824,6 +829,19 @@ static int gmc_v10_0_sw_init(void *handle)
 
        adev->gmc.stolen_size = gmc_v10_0_get_vbios_fb_size(adev);
 
+       /*
+        * In dual GPUs scenario, stolen_size is assigned to zero on the
+        * secondary GPU, since there is no pre-OS console using that memory.
+        * Then the bottom region of VRAM was allocated as GTT, unfortunately a
+        * small region of bottom VRAM was encroached by UMC firmware during
+        * GDDR6 BIST training, this cause page fault.
+        * The page fault can be fixed by forcing stolen_size to 3MB, then the
+        * bottom region of VRAM was allocated as stolen memory, GTT corruption
+        * avoid.
+        */
+       adev->gmc.stolen_size = max(adev->gmc.stolen_size,
+                                   AMDGPU_STOLEN_BIST_TRAINING_DEFAULT_SIZE);
+
        /* Memory manager */
        r = amdgpu_bo_init(adev);
        if (r)
@@ -863,6 +881,13 @@ static void gmc_v10_0_gart_fini(struct amdgpu_device *adev)
 static int gmc_v10_0_sw_fini(void *handle)
 {
        struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+       void *stolen_vga_buf;
+
+       /*
+        * Free the stolen memory if it wasn't already freed in late_init
+        * because of memory training.
+        */
+       amdgpu_bo_free_kernel(&adev->stolen_vga_memory, NULL, &stolen_vga_buf);
 
        amdgpu_vm_manager_fini(adev);
        gmc_v10_0_gart_fini(adev);