[RFC PATCH 02/13] drm/admgpu: add helper functions to track status for ras manager
Jiang Liu
gerry at linux.alibaba.com
Wed Jan 8 13:59:54 UTC 2025
Add helper functions to track status for ras manager and ip blocks.
Signed-off-by: Jiang Liu <gerry at linux.alibaba.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 38 +++++++++++++++++++++++++
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 38 +++++++++++++++++++++++++
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h | 10 +++++++
3 files changed, 86 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index e4b13e729770..32941f29507c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -367,12 +367,29 @@ bool amdgpu_device_ip_is_valid(struct amdgpu_device *adev,
#define AMDGPU_MAX_IP_NUM 16
+enum amdgpu_marker {
+ // shared by ip blocks and ras blocks
+ AMDGPU_MARKER_IRQ0 = 0,
+ AMDGPU_MARKER_IRQ1 = 1,
+ AMDGPU_MARKER_IRQ2 = 2,
+ AMDGPU_MARKER_IRQ3 = 3,
+ AMDGPU_MARKER_IRQ4 = 4,
+ AMDGPU_MARKER_IRQ5 = 5,
+ AMDGPU_MARKER_IRQ6 = 6,
+ AMDGPU_MARKER_IRQ7 = 7,
+ AMDGPU_MARKER_IRQ_MAX = 47,
+ AMDGPU_MARKER_DEBUGFS = 63,
+};
+
+#define AMDGPU_MARKER_INDEX_IRQ(idx) (AMDGPU_MARKER_INDEX_IRQ0 + (idx))
+
struct amdgpu_ip_block_status {
bool valid;
bool sw;
bool hw;
bool late_initialized;
bool hang;
+ uint64_t markers;
};
struct amdgpu_ip_block_version {
@@ -400,6 +417,27 @@ amdgpu_device_ip_get_ip_block(struct amdgpu_device *adev,
int amdgpu_device_ip_block_add(struct amdgpu_device *adev,
const struct amdgpu_ip_block_version *ip_block_version);
+static inline void amdgpu_ip_block_set_marker(struct amdgpu_ip_block *ip_block,
+ enum amdgpu_marker marker)
+{
+ WARN_ON(ip_block->status.markers & (0x1ull << marker));
+ ip_block->status.markers |= 0x1ull << (int)marker;
+}
+
+static inline bool amdgpu_ip_block_test_and_clear_marker(struct amdgpu_ip_block *ip_block,
+ enum amdgpu_marker marker)
+{
+ bool set = false;
+ uint64_t value = 0x1ull << (int)marker;
+
+ if ((ip_block->status.markers & value) != 0 ) {
+ ip_block->status.markers &= ~value;
+ set = true;
+ }
+
+ return set;
+}
+
/*
* BIOS.
*/
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 71e8eafbbfbc..6d52e22691f7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -5007,3 +5007,41 @@ bool amdgpu_ras_is_rma(struct amdgpu_device *adev)
return con->is_rma;
}
+
+bool amdgpu_ras_test_marker(struct amdgpu_device *adev,
+ struct ras_common_if *head, int marker)
+{
+ struct ras_manager *obj = amdgpu_ras_find_obj(adev, head);
+
+ if (obj && obj->markers & (0x1ull << marker)) {
+ return true;
+ }
+
+ return false;
+}
+
+void amdgpu_ras_set_marker(struct amdgpu_device *adev,
+ struct ras_common_if *head, int marker)
+{
+ struct ras_manager *obj = amdgpu_ras_find_obj(adev, head);
+
+ WARN_ON(obj->markers & (0x1ull << marker));
+ if (obj) {
+ obj->markers |= 0x1ull << marker;
+ }
+}
+
+bool amdgpu_ras_test_and_clear_marker(struct amdgpu_device *adev,
+ struct ras_common_if *head, int marker)
+{
+ bool set = false;
+ uint64_t value = 0x1ull << marker;
+ struct ras_manager *obj = amdgpu_ras_find_obj(adev, head);
+
+ if (obj && (obj->markers & value) != 0 ) {
+ obj->markers &= ~value;
+ set = true;
+ }
+
+ return set;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index b13debcf48ee..bc7377eaf819 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -632,6 +632,8 @@ struct ras_manager {
struct ras_common_if head;
/* reference count */
int use;
+ /* Flags for status tracking */
+ uint64_t markers;
/* ras block link */
struct list_head node;
/* the device */
@@ -975,4 +977,12 @@ void amdgpu_ras_event_log_print(struct amdgpu_device *adev, u64 event_id,
const char *fmt, ...);
bool amdgpu_ras_is_rma(struct amdgpu_device *adev);
+
+bool amdgpu_ras_test_marker(struct amdgpu_device *adev,
+ struct ras_common_if *head, int marker);
+void amdgpu_ras_set_marker(struct amdgpu_device *adev,
+ struct ras_common_if *head, int marker);
+bool amdgpu_ras_test_and_clear_marker(struct amdgpu_device *adev,
+ struct ras_common_if *head,
+ int marker);
#endif
--
2.43.5
More information about the amd-gfx
mailing list