Merge tag 'amd-drm-next-6.10-2024-04-26' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.10-2024-04-26:

amdgpu:
- Misc code cleanups and refactors
- Support setting reset method at runtime
- Report OD status
- SMU 14.0.1 fixes
- SDMA 4.4.2 fixes
- VPE fixes
- MES fixes
- Update BO eviction priorities
- UMSCH fixes
- Reset fixes
- Freesync fixes
- GFXIP 9.4.3 fixes
- SDMA 5.2 fixes
- MES UAF fix
- RAS updates
- Devcoredump updates for dumping IP state
- DSC fixes
- JPEG fix
- Fix VRAM memory accounting
- VCN 5.0 fixes
- MES fixes
- UMC 12.0 updates
- Modify contiguous flags handling
- Initial support for mapping kernel queues via MES

amdkfd:
- Fix rescheduling of restore worker
- VRAM accounting for SVM migrations
- mGPU fix
- Enable SQ watchpoint for gfx10

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240426221245.1613332-1-alexander.deucher@amd.com

1 files changed, 47 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index 8d26989c75c8..c8980d5f6540 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -26,6 +26,9 @@
 
 #include <linux/debugfs.h>
 #include <linux/list.h>
+#include <linux/kfifo.h>
+#include <linux/radix-tree.h>
+#include <linux/siphash.h>
 #include "ta_ras_if.h"
 #include "amdgpu_ras_eeprom.h"
 #include "amdgpu_smuio.h"
@@ -442,6 +445,37 @@ struct ras_query_context {
 	u64 event_id;
 };
 
+typedef int (*pasid_notify)(struct amdgpu_device *adev,
+		uint16_t pasid, void *data);
+
+struct ras_poison_msg {
+	enum amdgpu_ras_block block;
+	uint16_t pasid;
+	uint32_t reset;
+	pasid_notify pasid_fn;
+	void *data;
+};
+
+struct ras_err_pages {
+	uint32_t count;
+	uint64_t *pfn;
+};
+
+struct ras_ecc_err {
+	u64 hash_index;
+	uint64_t status;
+	uint64_t ipid;
+	uint64_t addr;
+	struct ras_err_pages err_pages;
+};
+
+struct ras_ecc_log_info {
+	struct mutex lock;
+	siphash_key_t ecc_key;
+	struct radix_tree_root de_page_tree;
+	bool	de_updated;
+};
+
 struct amdgpu_ras {
 	/* ras infrastructure */
 	/* for ras itself. */
@@ -500,6 +534,11 @@ struct amdgpu_ras {
 	wait_queue_head_t page_retirement_wq;
 	struct mutex page_retirement_lock;
 	atomic_t page_retirement_req_cnt;
+	struct mutex page_rsv_lock;
+	DECLARE_KFIFO(poison_fifo, struct ras_poison_msg, 128);
+	struct ras_ecc_log_info  umc_ecc_log;
+	struct delayed_work page_retirement_dwork;
+
 	/* Fatal error detected flag */
 	atomic_t fed;
 
@@ -540,6 +579,7 @@ struct ras_err_data {
 	unsigned long de_count;
 	unsigned long err_addr_cnt;
 	struct eeprom_table_record *err_addr;
+	unsigned long err_addr_len;
 	u32 err_list_count;
 	struct list_head err_node_list;
 };
@@ -909,4 +949,11 @@ bool amdgpu_ras_get_fed_status(struct amdgpu_device *adev);
 
 bool amdgpu_ras_event_id_is_valid(struct amdgpu_device *adev, u64 id);
 u64 amdgpu_ras_acquire_event_id(struct amdgpu_device *adev, enum ras_event_type type);
+
+int amdgpu_ras_reserve_page(struct amdgpu_device *adev, uint64_t pfn);
+
+int amdgpu_ras_put_poison_req(struct amdgpu_device *adev,
+		enum amdgpu_ras_block block, uint16_t pasid,
+		pasid_notify pasid_fn, void *data, uint32_t reset);
+
 #endif