X-Git-Url: https://repo.jachan.dev/J-linux.git/blobdiff_plain/466b179346094e01deccd051a215fe782b59ca68..f5500f385ba344d24468c086eb9c50f5ef4f1419:/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 49c71cfc7fc6..4d387557cc37 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -24,6 +24,8 @@
 #include <linux/debugfs.h>
 #include <linux/list.h>
 #include <linux/module.h>
+#include <linux/uaccess.h>
+
 #include "amdgpu.h"
 #include "amdgpu_ras.h"
 #include "amdgpu_atomfirmware.h"
@@ -128,6 +130,12 @@ const char *ras_block_string[] = {
 #define AMDGPU_RAS_FLAG_INIT_NEED_RESET		2
 #define RAS_DEFAULT_FLAGS (AMDGPU_RAS_FLAG_INIT_BY_VBIOS)
 
+static int amdgpu_ras_reserve_vram(struct amdgpu_device *adev,
+		uint64_t offset, uint64_t size,
+		struct amdgpu_bo **bo_ptr);
+static int amdgpu_ras_release_vram(struct amdgpu_device *adev,
+		struct amdgpu_bo **bo_ptr);
+
 static void amdgpu_ras_self_test(struct amdgpu_device *adev)
 {
 	/* TODO */
@@ -244,8 +252,8 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f,
 
 	return 0;
 }
-/*
- * DOC: ras debugfs control interface
+/**
+ * DOC: AMDGPU RAS debugfs control interface
  *
  * It accepts struct ras_debug_if who has two members.
  *
@@ -307,6 +315,7 @@ static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f, const char __user *
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)file_inode(f)->i_private;
 	struct ras_debug_if data;
+	struct amdgpu_bo *bo;
 	int ret = 0;
 
 	ret = amdgpu_ras_debugfs_ctrl_parse_data(f, buf, size, pos, &data);
@@ -324,7 +333,16 @@ static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f, const char __user *
 		ret = amdgpu_ras_feature_enable(adev, &data.head, 1);
 		break;
 	case 2:
+		ret = amdgpu_ras_reserve_vram(adev,
+				data.inject.address, PAGE_SIZE, &bo);
+		/* This address might be used already on failure. In fact we can
+		 * perform an injection in such case.
+		 */
+		if (ret)
+			break;
+		data.inject.address = amdgpu_bo_gpu_offset(bo);
 		ret = amdgpu_ras_error_inject(adev, &data.inject);
+		amdgpu_ras_release_vram(adev, &bo);
 		break;
 	default:
 		ret = -EINVAL;
@@ -764,8 +782,8 @@ static ssize_t amdgpu_ras_sysfs_badpages_read(struct file *f,
 	struct amdgpu_device *adev = con->adev;
 	const unsigned int element_size =
 		sizeof("0xabcdabcd : 0x12345678 : R\n") - 1;
-	unsigned int start = (ppos + element_size - 1) / element_size;
-	unsigned int end = (ppos + count - 1) / element_size;
+	unsigned int start = div64_ul(ppos + element_size - 1, element_size);
+	unsigned int end = div64_ul(ppos + count - 1, element_size);
 	ssize_t s = 0;
 	struct ras_badpage *bps = NULL;
 	unsigned int bps_count = 0;
@@ -1594,12 +1612,9 @@ recovery_out:
 }
 
 /* do some init work after IP late init as dependence.
- * TODO
- * gpu reset will re-enable ras, need fint out one way to run it again.
- * for now, if a gpu reset happened, unless IP enable its ras, the ras state
- * will be showed as disabled.
+ * and it runs in resume/gpu reset/booting up cases.
  */
-void amdgpu_ras_post_init(struct amdgpu_device *adev)
+void amdgpu_ras_resume(struct amdgpu_device *adev)
 {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 	struct ras_manager *obj, *tmp;
@@ -1642,6 +1657,19 @@ void amdgpu_ras_post_init(struct amdgpu_device *adev)
 	}
 }
 
+void amdgpu_ras_suspend(struct amdgpu_device *adev)
+{
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+
+	if (!con)
+		return;
+
+	amdgpu_ras_disable_all_features(adev, 0);
+	/* Make sure all ras objects are disabled. */
+	if (con->features)
+		amdgpu_ras_disable_all_features(adev, 1);
+}
+
 /* do some fini work before IP fini as dependence */
 int amdgpu_ras_pre_fini(struct amdgpu_device *adev)
 {