[PATCH v12 1/5] drm/xe/guc: Prepare GuC register list and update ADS size for error capture
Zhanjun Dong
zhanjun.dong at intel.com
Fri Jul 12 16:47:20 UTC 2024
Add referenced registers defines and list of registers.
Update GuC ADS size allocation to include space for
the lists of error state capture register descriptors.
Then, populate GuC ADS with the lists of registers we want
GuC to report back to host on engine reset events. This list
should include global, engine-class and engine-instance
registers for every engine-class type on the current hardware.
Ensure we allocate a persistent store for the register lists
that are populated into ADS so that we don't need to allocate
memory during GT resets when GuC is reloaded and ADS population
happens again.
Signed-off-by: Zhanjun Dong <zhanjun.dong at intel.com>
---
drivers/gpu/drm/xe/Makefile | 1 +
drivers/gpu/drm/xe/abi/guc_capture_abi.h | 144 ++++++
.../drm/xe/abi/guc_communication_mmio_abi.h | 23 +
drivers/gpu/drm/xe/xe_guc.c | 5 +
drivers/gpu/drm/xe/xe_guc.h | 29 ++
drivers/gpu/drm/xe/xe_guc_ads.c | 151 +++++-
drivers/gpu/drm/xe/xe_guc_ads_types.h | 2 +
drivers/gpu/drm/xe/xe_guc_capture.c | 454 ++++++++++++++++++
drivers/gpu/drm/xe/xe_guc_capture.h | 22 +
drivers/gpu/drm/xe/xe_guc_capture_types.h | 55 +++
drivers/gpu/drm/xe/xe_guc_fwif.h | 26 +-
drivers/gpu/drm/xe/xe_guc_types.h | 2 +
12 files changed, 877 insertions(+), 37 deletions(-)
create mode 100644 drivers/gpu/drm/xe/abi/guc_capture_abi.h
create mode 100644 drivers/gpu/drm/xe/xe_guc_capture.c
create mode 100644 drivers/gpu/drm/xe/xe_guc_capture.h
create mode 100644 drivers/gpu/drm/xe/xe_guc_capture_types.h
diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
index 1ff9602a52f6..2d8f8acaf846 100644
--- a/drivers/gpu/drm/xe/Makefile
+++ b/drivers/gpu/drm/xe/Makefile
@@ -57,6 +57,7 @@ xe-y += xe_bb.o \
xe_gt_topology.o \
xe_guc.o \
xe_guc_ads.o \
+ xe_guc_capture.o \
xe_guc_ct.o \
xe_guc_db_mgr.o \
xe_guc_debugfs.o \
diff --git a/drivers/gpu/drm/xe/abi/guc_capture_abi.h b/drivers/gpu/drm/xe/abi/guc_capture_abi.h
new file mode 100644
index 000000000000..c71630aed49b
--- /dev/null
+++ b/drivers/gpu/drm/xe/abi/guc_capture_abi.h
@@ -0,0 +1,144 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2024 Intel Corporation
+ */
+
+#ifndef _ABI_GUC_CAPTURE_ABI_H
+#define _ABI_GUC_CAPTURE_ABI_H
+
+#include <linux/types.h>
+
+#include "abi/guc_communication_mmio_abi.h"
+
+/* Capture List Index */
+enum guc_capture_list_index_type {
+ GUC_CAPTURE_LIST_INDEX_PF = 0,
+ GUC_CAPTURE_LIST_INDEX_VF = 1,
+ GUC_CAPTURE_LIST_INDEX_MAX = 2
+};
+
+/* Register-types of GuC capture register lists */
+enum guc_state_capture_type {
+ GUC_STATE_CAPTURE_TYPE_GLOBAL = 0,
+ GUC_STATE_CAPTURE_TYPE_ENGINE_CLASS,
+ GUC_STATE_CAPTURE_TYPE_ENGINE_INSTANCE
+};
+
+#define GUC_STATE_CAPTURE_TYPE_MAX (GUC_STATE_CAPTURE_TYPE_ENGINE_INSTANCE + 1)
+
+/* Class indecies for capture_class and capture_instance arrays */
+enum guc_capture_list_class_type {
+ GUC_CAPTURE_LIST_CLASS_RENDER_COMPUTE = 0,
+ GUC_CAPTURE_LIST_CLASS_VIDEO = 1,
+ GUC_CAPTURE_LIST_CLASS_VIDEOENHANCE = 2,
+ GUC_CAPTURE_LIST_CLASS_BLITTER = 3,
+ GUC_CAPTURE_LIST_CLASS_GSC_OTHER = 4,
+ GUC_CAPTURE_LIST_CLASS_MAX = 5
+};
+
+/**
+ * struct guc_debug_capture_list_header - Debug capture list header.
+ *
+ * Debug capture list header.
+ */
+struct guc_debug_capture_list_header {
+ /** @info: contains number of MMIO descriptors in the capture list. */
+ u32 info;
+#define GUC_CAPTURELISTHDR_NUMDESCR GENMASK(15, 0)
+} __packed;
+
+/**
+ * struct guc_debug_capture_list - Debug capture list
+ *
+ * As part of ADS registration, these header structures (followed by
+ * an array of 'struct guc_mmio_reg' entries) are used to register with
+ * GuC microkernel the list of registers we want it to dump out prior
+ * to a engine reset.
+ */
+struct guc_debug_capture_list {
+ /** @header: Debug capture list header. */
+ struct guc_debug_capture_list_header header;
+ /** @regs: MMIO descriptors in the capture list. */
+ struct guc_mmio_reg regs[];
+} __packed;
+
+/**
+ * struct guc_state_capture_header_t - State capture header.
+ *
+ * Prior to resetting engines that have hung or faulted, GuC microkernel
+ * reports the engine error-state (register values that was read) by
+ * logging them into the shared GuC log buffer using these hierarchy
+ * of structures.
+ */
+struct guc_state_capture_header_t {
+ /**
+ * @owner: VFID
+ * BR[ 7: 0] MBZ when SRIOV is disabled. When SRIOV is enabled
+ * VFID is an integer in range [0, 63] where 0 means the state capture
+ * is corresponding to the PF and an integer N in range [1, 63] means
+ * the state capture is for VF N.
+ */
+ u32 owner;
+#define GUC_STATE_CAPTURE_HEADER_VFID GENMASK(7, 0)
+ /** @info: Engine class/instance and capture type info */
+ u32 info;
+#define GUC_STATE_CAPTURE_HEADER_CAPTURE_TYPE GENMASK(3, 0) /* see guc_state_capture_type */
+#define GUC_STATE_CAPTURE_HEADER_ENGINE_CLASS GENMASK(7, 4) /* see guc_capture_list_class_type */
+#define GUC_STATE_CAPTURE_HEADER_ENGINE_INSTANCE GENMASK(11, 8)
+ /** @lrca: logical ring context address. */
+ u32 lrca; /* if type-instance, LRCA (address) that hung, else set to ~0 */
+ /** @guc_id: context_index. */
+ u32 guc_id; /* if type-instance, context index of hung context, else set to ~0 */
+ /** @num_mmio_entries: Number of captured MMIO entries. */
+ u32 num_mmio_entries;
+#define GUC_STATE_CAPTURE_HEADER_NUM_MMIO_ENTRIES GENMASK(9, 0)
+} __packed;
+
+/**
+ * struct guc_state_capture_t - State capture.
+ *
+ * State capture
+ */
+struct guc_state_capture_t {
+ /** @header: State capture header. */
+ struct guc_state_capture_header_t header;
+ /** @mmio_entries: Array of captured guc_mmio_reg entries. */
+ struct guc_mmio_reg mmio_entries[];
+} __packed;
+
+/* State Capture Group Type */
+enum guc_state_capture_group_type {
+ GUC_STATE_CAPTURE_GROUP_TYPE_FULL = 0,
+ GUC_STATE_CAPTURE_GROUP_TYPE_PARTIAL
+};
+
+#define GUC_STATE_CAPTURE_GROUP_TYPE_MAX (GUC_STATE_CAPTURE_GROUP_TYPE_PARTIAL + 1)
+
+/**
+ * struct guc_state_capture_group_header_t - State capture group header
+ *
+ * State capture group header.
+ */
+struct guc_state_capture_group_header_t {
+ /** @owner: VFID */
+ u32 owner;
+#define GUC_STATE_CAPTURE_GROUP_HEADER_VFID GENMASK(7, 0)
+ /** @info: Engine class/instance and capture type info */
+ u32 info;
+#define GUC_STATE_CAPTURE_GROUP_HEADER_NUM_CAPTURES GENMASK(7, 0)
+#define GUC_STATE_CAPTURE_GROUP_HEADER_CAPTURE_GROUP_TYPE GENMASK(15, 8)
+} __packed;
+
+/**
+ * struct guc_state_capture_group_t - State capture group.
+ *
+ * this is the top level structure where an error-capture dump starts
+ */
+struct guc_state_capture_group_t {
+ /** @grp_header: State capture group header. */
+ struct guc_state_capture_group_header_t grp_header;
+ /** @capture_entries: Array of state captures */
+ struct guc_state_capture_t capture_entries[];
+} __packed;
+
+#endif
diff --git a/drivers/gpu/drm/xe/abi/guc_communication_mmio_abi.h b/drivers/gpu/drm/xe/abi/guc_communication_mmio_abi.h
index ef538e34f894..219b40063f43 100644
--- a/drivers/gpu/drm/xe/abi/guc_communication_mmio_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_communication_mmio_abi.h
@@ -6,6 +6,29 @@
#ifndef _ABI_GUC_COMMUNICATION_MMIO_ABI_H
#define _ABI_GUC_COMMUNICATION_MMIO_ABI_H
+#include <linux/types.h>
+
+/* GuC MMIO reg state struct */
+struct guc_mmio_reg {
+ u32 offset;
+ u32 value;
+ u32 flags;
+ u32 mask;
+#define GUC_REGSET_MASKED BIT(0)
+#define GUC_REGSET_STEERING_NEEDED BIT(1)
+#define GUC_REGSET_MASKED_WITH_VALUE BIT(2)
+#define GUC_REGSET_RESTORE_ONLY BIT(3)
+#define GUC_REGSET_STEERING_GROUP GENMASK(16, 12)
+#define GUC_REGSET_STEERING_INSTANCE GENMASK(23, 20)
+} __packed;
+
+/* GuC register sets */
+struct guc_mmio_reg_set {
+ u32 address;
+ u16 count;
+ u16 reserved;
+} __packed;
+
/**
* DOC: GuC MMIO based communication
*
diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c
index eb655cee19f7..5e108cedbdc5 100644
--- a/drivers/gpu/drm/xe/xe_guc.c
+++ b/drivers/gpu/drm/xe/xe_guc.c
@@ -22,6 +22,7 @@
#include "xe_gt_sriov_vf.h"
#include "xe_gt_throttle.h"
#include "xe_guc_ads.h"
+#include "xe_guc_capture.h"
#include "xe_guc_ct.h"
#include "xe_guc_db_mgr.h"
#include "xe_guc_hwconfig.h"
@@ -338,6 +339,10 @@ int xe_guc_init(struct xe_guc *guc)
if (ret)
goto out;
+ ret = xe_guc_capture_init(guc);
+ if (ret)
+ goto out;
+
ret = xe_guc_ads_init(&guc->ads);
if (ret)
goto out;
diff --git a/drivers/gpu/drm/xe/xe_guc.h b/drivers/gpu/drm/xe/xe_guc.h
index af59c9545753..a823c5b8ab22 100644
--- a/drivers/gpu/drm/xe/xe_guc.h
+++ b/drivers/gpu/drm/xe/xe_guc.h
@@ -59,6 +59,30 @@ static inline u16 xe_engine_class_to_guc_class(enum xe_engine_class class)
}
}
+static inline enum guc_capture_list_class_type xe_guc_class_to_capture_class(uint class)
+{
+ switch (class) {
+ case GUC_RENDER_CLASS:
+ case GUC_COMPUTE_CLASS:
+ return GUC_CAPTURE_LIST_CLASS_RENDER_COMPUTE;
+ case GUC_GSC_OTHER_CLASS:
+ return GUC_CAPTURE_LIST_CLASS_GSC_OTHER;
+ case GUC_VIDEO_CLASS:
+ case GUC_VIDEOENHANCE_CLASS:
+ case GUC_BLITTER_CLASS:
+ return class;
+ default:
+ XE_WARN_ON(class);
+ return -1;
+ }
+}
+
+static inline enum guc_capture_list_class_type
+xe_engine_class_to_guc_capture_class(enum xe_engine_class class)
+{
+ return xe_guc_class_to_capture_class(xe_engine_class_to_guc_class(class));
+}
+
static inline struct xe_gt *guc_to_gt(struct xe_guc *guc)
{
return container_of(guc, struct xe_gt, uc.guc);
@@ -69,4 +93,9 @@ static inline struct xe_device *guc_to_xe(struct xe_guc *guc)
return gt_to_xe(guc_to_gt(guc));
}
+static inline struct drm_device *guc_to_drm(struct xe_guc *guc)
+{
+ return &guc_to_xe(guc)->drm;
+}
+
#endif
diff --git a/drivers/gpu/drm/xe/xe_guc_ads.c b/drivers/gpu/drm/xe/xe_guc_ads.c
index 1c60b685dbc6..533eb5285942 100644
--- a/drivers/gpu/drm/xe/xe_guc_ads.c
+++ b/drivers/gpu/drm/xe/xe_guc_ads.c
@@ -18,6 +18,7 @@
#include "xe_gt_ccs_mode.h"
#include "xe_gt_printk.h"
#include "xe_guc.h"
+#include "xe_guc_capture.h"
#include "xe_guc_ct.h"
#include "xe_hw_engine.h"
#include "xe_lrc.h"
@@ -148,8 +149,7 @@ static u32 guc_ads_waklv_size(struct xe_guc_ads *ads)
static size_t guc_ads_capture_size(struct xe_guc_ads *ads)
{
- /* FIXME: Allocate a proper capture list */
- return PAGE_ALIGN(PAGE_SIZE);
+ return PAGE_ALIGN(ads->capture_size);
}
static size_t guc_ads_um_queues_size(struct xe_guc_ads *ads)
@@ -398,6 +398,7 @@ int xe_guc_ads_init(struct xe_guc_ads *ads)
struct xe_bo *bo;
ads->golden_lrc_size = calculate_golden_lrc_size(ads);
+ ads->capture_size = xe_guc_capture_ads_input_worst_size(ads_to_guc(ads));
ads->regset_size = calculate_regset_size(gt);
ads->ads_waklv_size = calculate_waklv_size(ads);
@@ -417,9 +418,9 @@ int xe_guc_ads_init(struct xe_guc_ads *ads)
* xe_guc_ads_init_post_hwconfig - initialize ADS post hwconfig load
* @ads: Additional data structures object
*
- * Recalcuate golden_lrc_size & regset_size as the number hardware engines may
- * have changed after the hwconfig was loaded. Also verify the new sizes fit in
- * the already allocated ADS buffer object.
+ * Recalculate golden_lrc_size, capture_size and regset_size as the number
+ * hardware engines may have changed after the hwconfig was loaded. Also verify
+ * the new sizes fit in the already allocated ADS buffer object.
*
* Return: 0 on success, negative error code on error.
*/
@@ -431,6 +432,8 @@ int xe_guc_ads_init_post_hwconfig(struct xe_guc_ads *ads)
xe_gt_assert(gt, ads->bo);
ads->golden_lrc_size = calculate_golden_lrc_size(ads);
+ /* Calculate Capture size with worst size */
+ ads->capture_size = xe_guc_capture_ads_input_worst_size(ads_to_guc(ads));
ads->regset_size = calculate_regset_size(gt);
xe_gt_assert(gt, ads->golden_lrc_size +
@@ -530,20 +533,142 @@ static void guc_mapping_table_init(struct xe_gt *gt,
}
}
-static void guc_capture_list_init(struct xe_guc_ads *ads)
+static u32 guc_get_capture_engine_mask(struct xe_gt *gt, struct iosys_map *info_map,
+ enum guc_capture_list_class_type capture_class)
{
+ struct xe_device *xe = gt_to_xe(gt);
+ u32 mask;
+
+ switch (capture_class) {
+ case GUC_CAPTURE_LIST_CLASS_RENDER_COMPUTE:
+ mask = info_map_read(xe, info_map, engine_enabled_masks[GUC_RENDER_CLASS]);
+ mask |= info_map_read(xe, info_map, engine_enabled_masks[GUC_COMPUTE_CLASS]);
+ break;
+ case GUC_CAPTURE_LIST_CLASS_VIDEO:
+ mask = info_map_read(xe, info_map, engine_enabled_masks[GUC_VIDEO_CLASS]);
+ break;
+ case GUC_CAPTURE_LIST_CLASS_VIDEOENHANCE:
+ mask = info_map_read(xe, info_map, engine_enabled_masks[GUC_VIDEOENHANCE_CLASS]);
+ break;
+ case GUC_CAPTURE_LIST_CLASS_BLITTER:
+ mask = info_map_read(xe, info_map, engine_enabled_masks[GUC_BLITTER_CLASS]);
+ break;
+ case GUC_CAPTURE_LIST_CLASS_GSC_OTHER:
+ mask = info_map_read(xe, info_map, engine_enabled_masks[GUC_GSC_OTHER_CLASS]);
+ break;
+ default:
+ mask = 0;
+ }
+
+ return mask;
+}
+
+static inline bool get_capture_list(struct xe_guc_ads *ads, struct xe_guc *guc, struct xe_gt *gt,
+ int owner, int type, int class, u32 *total_size, size_t *size,
+ void **pptr)
+{
+ *size = 0;
+
+ if (!xe_guc_capture_getlistsize(guc, owner, type, class, size)) {
+ if (*total_size + *size > ads->capture_size)
+ xe_gt_dbg(gt, "Capture size overflow :%zu vs %d\n",
+ *total_size + *size, ads->capture_size);
+ else if (!xe_guc_capture_getlist(guc, owner, type, class, pptr))
+ return false;
+ }
+
+ return true;
+}
+
+static int guc_capture_prep_lists(struct xe_guc_ads *ads)
+{
+ struct xe_guc *guc = ads_to_guc(ads);
+ struct xe_gt *gt = ads_to_gt(ads);
+ u32 ads_ggtt, capture_offset, null_ggtt, total_size = 0;
+ struct iosys_map info_map;
+ size_t size = 0;
+ void *ptr;
int i, j;
- u32 addr = xe_bo_ggtt_addr(ads->bo) + guc_ads_capture_offset(ads);
- /* FIXME: Populate a proper capture list */
+ capture_offset = guc_ads_capture_offset(ads);
+ ads_ggtt = xe_bo_ggtt_addr(ads->bo);
+ info_map = IOSYS_MAP_INIT_OFFSET(ads_to_map(ads),
+ offsetof(struct __guc_ads_blob, system_info));
+
+ /* first, set aside the first page for a capture_list with zero descriptors */
+ total_size = PAGE_SIZE;
+ if (!xe_guc_capture_getnullheader(guc, &ptr, &size))
+ xe_map_memcpy_to(ads_to_xe(ads), ads_to_map(ads), capture_offset, ptr, size);
+
+ null_ggtt = ads_ggtt + capture_offset;
+ capture_offset += PAGE_SIZE;
+
+ /*
+ * Populate capture list : at this point adps is already allocated and
+ * mapped to worst case size
+ */
for (i = 0; i < GUC_CAPTURE_LIST_INDEX_MAX; i++) {
- for (j = 0; j < GUC_MAX_ENGINE_CLASSES; j++) {
- ads_blob_write(ads, ads.capture_instance[i][j], addr);
- ads_blob_write(ads, ads.capture_class[i][j], addr);
+ bool write_empty_list;
+
+ for (j = 0; j < GUC_CAPTURE_LIST_CLASS_MAX; j++) {
+ u32 engine_mask = guc_get_capture_engine_mask(gt, &info_map, j);
+ /* null list if we dont have said engine or list */
+ if (!engine_mask) {
+ ads_blob_write(ads, ads.capture_class[i][j], null_ggtt);
+ ads_blob_write(ads, ads.capture_instance[i][j], null_ggtt);
+ continue;
+ }
+
+ /* engine exists: start with engine-class registers */
+ write_empty_list = get_capture_list(ads, guc, gt, i,
+ GUC_STATE_CAPTURE_TYPE_ENGINE_CLASS,
+ j, &total_size, &size, &ptr);
+ if (!write_empty_list) {
+ ads_blob_write(ads, ads.capture_class[i][j],
+ ads_ggtt + capture_offset);
+ xe_map_memcpy_to(ads_to_xe(ads), ads_to_map(ads), capture_offset,
+ ptr, size);
+ total_size += size;
+ capture_offset += size;
+ } else {
+ ads_blob_write(ads, ads.capture_class[i][j], null_ggtt);
+ }
+
+ /* engine exists: next, engine-instance registers */
+ write_empty_list = get_capture_list(ads, guc, gt, i,
+ GUC_STATE_CAPTURE_TYPE_ENGINE_INSTANCE,
+ j, &total_size, &size, &ptr);
+ if (!write_empty_list) {
+ ads_blob_write(ads, ads.capture_instance[i][j],
+ ads_ggtt + capture_offset);
+ xe_map_memcpy_to(ads_to_xe(ads), ads_to_map(ads), capture_offset,
+ ptr, size);
+ total_size += size;
+ capture_offset += size;
+ } else {
+ ads_blob_write(ads, ads.capture_instance[i][j], null_ggtt);
+ }
}
- ads_blob_write(ads, ads.capture_global[i], addr);
+ /* global registers is last in our PF/VF loops */
+ write_empty_list = get_capture_list(ads, guc, gt, i,
+ GUC_STATE_CAPTURE_TYPE_GLOBAL,
+ 0, &total_size, &size, &ptr);
+ if (!write_empty_list) {
+ ads_blob_write(ads, ads.capture_global[i], ads_ggtt + capture_offset);
+ xe_map_memcpy_to(ads_to_xe(ads), ads_to_map(ads), capture_offset, ptr,
+ size);
+ total_size += size;
+ capture_offset += size;
+ } else {
+ ads_blob_write(ads, ads.capture_global[i], null_ggtt);
+ }
}
+
+ if (ads->capture_size != PAGE_ALIGN(total_size))
+ xe_gt_dbg(gt, "ADS capture alloc size changed from %d to %d\n",
+ ads->capture_size, PAGE_ALIGN(total_size));
+ return PAGE_ALIGN(total_size);
}
static void guc_mmio_regset_write_one(struct xe_guc_ads *ads,
@@ -732,7 +857,7 @@ void xe_guc_ads_populate(struct xe_guc_ads *ads)
guc_mmio_reg_state_init(ads);
guc_prep_golden_lrc_null(ads);
guc_mapping_table_init(gt, &info_map);
- guc_capture_list_init(ads);
+ guc_capture_prep_lists(ads);
guc_doorbell_init(ads);
guc_waklv_init(ads);
diff --git a/drivers/gpu/drm/xe/xe_guc_ads_types.h b/drivers/gpu/drm/xe/xe_guc_ads_types.h
index 2de5decfe0fd..70c132458ac3 100644
--- a/drivers/gpu/drm/xe/xe_guc_ads_types.h
+++ b/drivers/gpu/drm/xe/xe_guc_ads_types.h
@@ -22,6 +22,8 @@ struct xe_guc_ads {
u32 regset_size;
/** @ads_waklv_size: total waklv size supported by platform */
u32 ads_waklv_size;
+ /** @capture_size: size of register set passed to GuC for capture */
+ u32 capture_size;
};
#endif
diff --git a/drivers/gpu/drm/xe/xe_guc_capture.c b/drivers/gpu/drm/xe/xe_guc_capture.c
new file mode 100644
index 000000000000..f520c5fe0363
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_guc_capture.c
@@ -0,0 +1,454 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2021-2024 Intel Corporation
+ */
+
+#include <linux/types.h>
+
+#include <drm/drm_managed.h>
+#include <drm/drm_print.h>
+
+#include "abi/guc_actions_abi.h"
+#include "abi/guc_capture_abi.h"
+#include "regs/xe_engine_regs.h"
+#include "regs/xe_gt_regs.h"
+#include "regs/xe_guc_regs.h"
+#include "regs/xe_regs.h"
+
+#include "xe_bo.h"
+#include "xe_device.h"
+#include "xe_exec_queue_types.h"
+#include "xe_gt.h"
+#include "xe_gt_mcr.h"
+#include "xe_gt_printk.h"
+#include "xe_guc.h"
+#include "xe_guc_capture.h"
+#include "xe_guc_capture_types.h"
+#include "xe_guc_ct.h"
+#include "xe_guc_log.h"
+#include "xe_guc_submit.h"
+#include "xe_hw_engine_types.h"
+#include "xe_macros.h"
+#include "xe_map.h"
+
+/*
+ * Define all device tables of GuC error capture register lists
+ * NOTE: For engine-registers, GuC only needs the register offsets
+ * from the engine-mmio-base
+ */
+#define COMMON_XELP_BASE_GLOBAL \
+ { FORCEWAKE_GT, 0, 0}
+
+#define COMMON_BASE_ENGINE_INSTANCE \
+ { RING_ESR(0), 0, 0}, \
+ { RING_EMR(0), 0, 0}, \
+ { RING_EIR(0), 0, 0}, \
+ { RING_EXECLIST_STATUS_HI(0), 0, 0}, \
+ { RING_EXECLIST_STATUS_LO(0), 0, 0}, \
+ { RING_DMA_FADD(0), 0, 0}, \
+ { RING_DMA_FADD_UDW(0), 0, 0}, \
+ { RING_IPEHR(0), 0, 0}, \
+ { RING_BBADDR(0), 0, 0}, \
+ { RING_BBADDR_UDW(0), 0, 0}, \
+ { RING_ACTHD(0), 0, 0}, \
+ { RING_ACTHD_UDW(0), 0, 0}, \
+ { RING_START(0), 0, 0}, \
+ { RING_HEAD(0), 0, 0}, \
+ { RING_TAIL(0), 0, 0}, \
+ { RING_CTL(0), 0, 0}, \
+ { RING_MI_MODE(0), 0, 0}, \
+ { RING_HWS_PGA(0), 0, 0}, \
+ { RING_MODE(0), 0, 0}
+
+/* XE_LP Global */
+static const struct __guc_mmio_reg_descr xe_lp_global_regs[] = {
+ COMMON_XELP_BASE_GLOBAL,
+};
+
+/* Render / Compute Per-Engine-Instance */
+static const struct __guc_mmio_reg_descr xe_rc_inst_regs[] = {
+ COMMON_BASE_ENGINE_INSTANCE,
+};
+
+/* Media Decode/Encode Per-Engine-Instance */
+static const struct __guc_mmio_reg_descr xe_vd_inst_regs[] = {
+ COMMON_BASE_ENGINE_INSTANCE,
+};
+
+/* Video Enhancement Per-Engine-Instance */
+static const struct __guc_mmio_reg_descr xe_vec_inst_regs[] = {
+ COMMON_BASE_ENGINE_INSTANCE,
+};
+
+/* Blitter Per-Engine-Instance */
+static const struct __guc_mmio_reg_descr xe_blt_inst_regs[] = {
+ COMMON_BASE_ENGINE_INSTANCE,
+};
+
+/* XE_LP - GSC Per-Engine-Instance */
+static const struct __guc_mmio_reg_descr xe_lp_gsc_inst_regs[] = {
+ COMMON_BASE_ENGINE_INSTANCE,
+};
+
+/*
+ * Empty list to prevent warnings about unknown class/instance types
+ * as not all class/instance types have entries on all platforms.
+ */
+static const struct __guc_mmio_reg_descr empty_regs_list[] = {
+};
+
+#define TO_GCAP_DEF_OWNER(x) (GUC_CAPTURE_LIST_INDEX_##x)
+#define TO_GCAP_DEF_TYPE(x) (GUC_STATE_CAPTURE_TYPE_##x)
+#define MAKE_REGLIST(regslist, regsowner, regstype, class) \
+ { \
+ regslist, \
+ ARRAY_SIZE(regslist), \
+ TO_GCAP_DEF_OWNER(regsowner), \
+ TO_GCAP_DEF_TYPE(regstype), \
+ class, \
+ }
+
+/* List of lists */
+static const struct __guc_mmio_reg_descr_group xe_lp_lists[] = {
+ MAKE_REGLIST(xe_lp_global_regs, PF, GLOBAL, 0),
+ MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_CAPTURE_LIST_CLASS_RENDER_COMPUTE),
+ MAKE_REGLIST(xe_rc_inst_regs, PF, ENGINE_INSTANCE, GUC_CAPTURE_LIST_CLASS_RENDER_COMPUTE),
+ MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_CAPTURE_LIST_CLASS_VIDEO),
+ MAKE_REGLIST(xe_vd_inst_regs, PF, ENGINE_INSTANCE, GUC_CAPTURE_LIST_CLASS_VIDEO),
+ MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_CAPTURE_LIST_CLASS_VIDEOENHANCE),
+ MAKE_REGLIST(xe_vec_inst_regs, PF, ENGINE_INSTANCE, GUC_CAPTURE_LIST_CLASS_VIDEOENHANCE),
+ MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_CAPTURE_LIST_CLASS_BLITTER),
+ MAKE_REGLIST(xe_blt_inst_regs, PF, ENGINE_INSTANCE, GUC_CAPTURE_LIST_CLASS_BLITTER),
+ MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_CAPTURE_LIST_CLASS_GSC_OTHER),
+ MAKE_REGLIST(xe_lp_gsc_inst_regs, PF, ENGINE_INSTANCE, GUC_CAPTURE_LIST_CLASS_GSC_OTHER),
+ {}
+};
+
+static const char * const capture_list_type_names[] = {
+ "Global",
+ "Class",
+ "Instance",
+};
+
+static const char * const capture_engine_class_names[] = {
+ "Render/Compute",
+ "Video",
+ "VideoEnhance",
+ "Blitter",
+ "GSC-Other",
+};
+
+struct __guc_capture_ads_cache {
+ bool is_valid;
+ void *ptr;
+ size_t size;
+ int status;
+};
+
+struct xe_guc_state_capture {
+ const struct __guc_mmio_reg_descr_group *reglists;
+ struct __guc_capture_ads_cache ads_cache[GUC_CAPTURE_LIST_INDEX_MAX]
+ [GUC_STATE_CAPTURE_TYPE_MAX]
+ [GUC_CAPTURE_LIST_CLASS_MAX];
+ void *ads_null_cache;
+};
+
+static const struct __guc_mmio_reg_descr_group *
+guc_capture_get_one_list(const struct __guc_mmio_reg_descr_group *reglists,
+ u32 owner, u32 type, enum guc_capture_list_class_type capture_class)
+{
+ int i;
+
+ if (!reglists)
+ return NULL;
+
+ for (i = 0; reglists[i].list; ++i) {
+ if (reglists[i].owner == owner && reglists[i].type == type &&
+ (reglists[i].engine == capture_class ||
+ reglists[i].type == GUC_STATE_CAPTURE_TYPE_GLOBAL))
+ return ®lists[i];
+ }
+
+ return NULL;
+}
+
+static const struct __guc_mmio_reg_descr_group *
+guc_capture_get_device_reglist(struct xe_guc *guc)
+{
+ return xe_lp_lists;
+}
+
+static int
+guc_capture_list_init(struct xe_guc *guc, u32 owner, u32 type,
+ enum guc_capture_list_class_type capture_class, struct guc_mmio_reg *ptr,
+ u16 num_entries)
+{
+ u32 i = 0;
+ const struct __guc_mmio_reg_descr_group *reglists = guc->capture->reglists;
+ const struct __guc_mmio_reg_descr_group *match;
+
+ if (!reglists)
+ return -ENODEV;
+
+ match = guc_capture_get_one_list(reglists, owner, type, capture_class);
+ if (!match)
+ return -ENODATA;
+
+ for (i = 0; i < num_entries && i < match->num_regs; ++i) {
+ ptr[i].offset = match->list[i].reg.addr;
+ ptr[i].value = 0xDEADF00D;
+ ptr[i].flags = match->list[i].flags;
+ ptr[i].mask = match->list[i].mask;
+ }
+
+ if (i < num_entries)
+ xe_gt_dbg(guc_to_gt(guc), "Got short capture reglist init: %d out %d.\n", i,
+ num_entries);
+
+ return 0;
+}
+
+static int
+guc_cap_list_num_regs(struct xe_guc_state_capture *gc, u32 owner, u32 type,
+ enum guc_capture_list_class_type capture_class)
+{
+ const struct __guc_mmio_reg_descr_group *match;
+
+ match = guc_capture_get_one_list(gc->reglists, owner, type, capture_class);
+ if (!match)
+ return 0;
+
+ return match->num_regs;
+}
+
+static int
+guc_capture_getlistsize(struct xe_guc *guc, u32 owner, u32 type,
+ enum guc_capture_list_class_type capture_class,
+ size_t *size, bool is_purpose_est)
+{
+ struct xe_guc_state_capture *gc = guc->capture;
+ struct xe_gt *gt = guc_to_gt(guc);
+ struct __guc_capture_ads_cache *cache;
+ int num_regs;
+
+ xe_gt_assert(gt, type < GUC_STATE_CAPTURE_TYPE_MAX);
+ xe_gt_assert(gt, capture_class < GUC_CAPTURE_LIST_CLASS_MAX);
+
+ cache = &gc->ads_cache[owner][type][capture_class];
+ if (!gc->reglists) {
+ xe_gt_warn(gt, "No capture reglist for this device\n");
+ return -ENODEV;
+ }
+
+ if (cache->is_valid) {
+ *size = cache->size;
+ return cache->status;
+ }
+
+ if (!is_purpose_est && owner == GUC_CAPTURE_LIST_INDEX_PF &&
+ !guc_capture_get_one_list(gc->reglists, owner, type, capture_class)) {
+ if (type == GUC_STATE_CAPTURE_TYPE_GLOBAL)
+ xe_gt_warn(gt, "Missing capture reglist: global!\n");
+ else
+ xe_gt_warn(gt, "Missing capture reglist: %s(%u):%s(%u)!\n",
+ capture_list_type_names[type], type,
+ capture_engine_class_names[capture_class], capture_class);
+ return -ENODEV;
+ }
+
+ num_regs = guc_cap_list_num_regs(gc, owner, type, capture_class);
+ /* intentional empty lists can exist depending on hw config */
+ if (!num_regs)
+ return -ENODATA;
+
+ if (size)
+ *size = PAGE_ALIGN((sizeof(struct guc_debug_capture_list)) +
+ (num_regs * sizeof(struct guc_mmio_reg)));
+
+ return 0;
+}
+
+/**
+ * xe_guc_capture_getlistsize - Get list size for owner/type/class combination
+ * @guc: The GuC object
+ * @owner: PF/VF owner
+ * @type: GuC capture register type
+ * @capture_class: GuC capture engine class id
+ * @size: Point to the size
+ *
+ * This function will get the list for the owner/type/class combination, and
+ * return the page aligned list size.
+ *
+ * Returns: 0 on success or a negative error code on failure.
+ */
+int
+xe_guc_capture_getlistsize(struct xe_guc *guc, u32 owner, u32 type,
+ enum guc_capture_list_class_type capture_class, size_t *size)
+{
+ return guc_capture_getlistsize(guc, owner, type, capture_class, size, false);
+}
+
+/**
+ * xe_guc_capture_getlist - Get register capture list for owner/type/class
+ * combination
+ * @guc: The GuC object
+ * @owner: PF/VF owner
+ * @type: GuC capture register type
+ * @capture_class: GuC capture engine class id
+ * @outptr: Point to cached register capture list
+ *
+ * This function will get the register capture list for the owner/type/class
+ * combination.
+ *
+ * Returns: 0 on success or a negative error code on failure.
+ */
+int
+xe_guc_capture_getlist(struct xe_guc *guc, u32 owner, u32 type,
+ enum guc_capture_list_class_type capture_class, void **outptr)
+{
+ struct xe_guc_state_capture *gc = guc->capture;
+ struct __guc_capture_ads_cache *cache = &gc->ads_cache[owner][type][capture_class];
+ struct guc_debug_capture_list *listnode;
+ int ret, num_regs;
+ u8 *caplist, *tmp;
+ size_t size = 0;
+
+ if (!gc->reglists)
+ return -ENODEV;
+
+ if (cache->is_valid) {
+ *outptr = cache->ptr;
+ return cache->status;
+ }
+
+ ret = xe_guc_capture_getlistsize(guc, owner, type, capture_class, &size);
+ if (ret) {
+ cache->is_valid = true;
+ cache->ptr = NULL;
+ cache->size = 0;
+ cache->status = ret;
+ return ret;
+ }
+
+ caplist = drmm_kzalloc(guc_to_drm(guc), size, GFP_KERNEL);
+ if (!caplist)
+ return -ENOMEM;
+
+ /* populate capture list header */
+ tmp = caplist;
+ num_regs = guc_cap_list_num_regs(guc->capture, owner, type, capture_class);
+ listnode = (struct guc_debug_capture_list *)tmp;
+ listnode->header.info = FIELD_PREP(GUC_CAPTURELISTHDR_NUMDESCR, (u32)num_regs);
+
+ /* populate list of register descriptor */
+ tmp += sizeof(struct guc_debug_capture_list);
+ guc_capture_list_init(guc, owner, type, capture_class,
+ (struct guc_mmio_reg *)tmp, num_regs);
+
+ /* cache this list */
+ cache->is_valid = true;
+ cache->ptr = caplist;
+ cache->size = size;
+ cache->status = 0;
+
+ *outptr = caplist;
+
+ return 0;
+}
+
+/**
+ * xe_guc_capture_getnullheader - Get a null list for register capture
+ * @guc: The GuC object
+ * @outptr: Point to cached register capture list
+ * @size: Point to the size
+ *
+ * This function will alloc for a null list for register capture.
+ *
+ * Returns: 0 on success or a negative error code on failure.
+ */
+int
+xe_guc_capture_getnullheader(struct xe_guc *guc, void **outptr, size_t *size)
+{
+ struct xe_guc_state_capture *gc = guc->capture;
+ int tmp = sizeof(u32) * 4;
+ void *null_header;
+
+ if (gc->ads_null_cache) {
+ *outptr = gc->ads_null_cache;
+ *size = tmp;
+ return 0;
+ }
+
+ null_header = drmm_kzalloc(guc_to_drm(guc), tmp, GFP_KERNEL);
+ if (!null_header)
+ return -ENOMEM;
+
+ gc->ads_null_cache = null_header;
+ *outptr = null_header;
+ *size = tmp;
+
+ return 0;
+}
+
+/**
+ * xe_guc_capture_ads_input_worst_size - Calculate the worst size for GuC register capture
+ * @guc: point to xe_guc structure
+ *
+ * Calculate the worst size for GuC register capture by including all possible engines classes.
+ *
+ * Returns: Calculated size
+ */
+size_t xe_guc_capture_ads_input_worst_size(struct xe_guc *guc)
+{
+ size_t total_size, class_size, instance_size, global_size;
+ int i, j;
+
+ /*
+ * This function calculates the worst case register lists size by
+ * including all possible engines classes. It is called during the
+ * first of a two-phase GuC (and ADS-population) initialization
+ * sequence, that is, during the pre-hwconfig phase before we have
+ * the exact engine fusing info.
+ */
+ total_size = PAGE_SIZE; /* Pad a page in front for empty lists */
+ for (i = 0; i < GUC_CAPTURE_LIST_INDEX_MAX; i++) {
+ for (j = 0; j < GUC_CAPTURE_LIST_CLASS_MAX; j++) {
+ if (xe_guc_capture_getlistsize(guc, i,
+ GUC_STATE_CAPTURE_TYPE_ENGINE_CLASS,
+ j, &class_size) < 0)
+ class_size = 0;
+ if (xe_guc_capture_getlistsize(guc, i,
+ GUC_STATE_CAPTURE_TYPE_ENGINE_INSTANCE,
+ j, &instance_size) < 0)
+ instance_size = 0;
+ total_size += class_size + instance_size;
+ }
+ if (xe_guc_capture_getlistsize(guc, i,
+ GUC_STATE_CAPTURE_TYPE_GLOBAL,
+ 0, &global_size) < 0)
+ global_size = 0;
+ total_size += global_size;
+ }
+
+ return PAGE_ALIGN(total_size);
+}
+
+/**
+ * xe_guc_capture_init - Init for GuC register capture
+ * @guc: The GuC object
+ *
+ * Init for GuC register capture, alloc memory for capture data structure.
+ *
+ * Returns: 0 if success.
+ -ENOMEM if out of memory
+ */
+int xe_guc_capture_init(struct xe_guc *guc)
+{
+ guc->capture = drmm_kzalloc(guc_to_drm(guc), sizeof(*guc->capture), GFP_KERNEL);
+ if (!guc->capture)
+ return -ENOMEM;
+
+ guc->capture->reglists = guc_capture_get_device_reglist(guc);
+
+ return 0;
+}
diff --git a/drivers/gpu/drm/xe/xe_guc_capture.h b/drivers/gpu/drm/xe/xe_guc_capture.h
new file mode 100644
index 000000000000..0a6335b48c50
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_guc_capture.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021-2024 Intel Corporation
+ */
+
+#ifndef _XE_GUC_CAPTURE_H
+#define _XE_GUC_CAPTURE_H
+
+#include <linux/types.h>
+#include "abi/guc_capture_abi.h"
+
+struct xe_guc;
+
+int xe_guc_capture_getlist(struct xe_guc *guc, u32 owner, u32 type,
+ enum guc_capture_list_class_type capture_class, void **outptr);
+int xe_guc_capture_getlistsize(struct xe_guc *guc, u32 owner, u32 type,
+ enum guc_capture_list_class_type capture_class, size_t *size);
+int xe_guc_capture_getnullheader(struct xe_guc *guc, void **outptr, size_t *size);
+size_t xe_guc_capture_ads_input_worst_size(struct xe_guc *guc);
+int xe_guc_capture_init(struct xe_guc *guc);
+
+#endif
diff --git a/drivers/gpu/drm/xe/xe_guc_capture_types.h b/drivers/gpu/drm/xe/xe_guc_capture_types.h
new file mode 100644
index 000000000000..839148c9fa0f
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_guc_capture_types.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021-2024 Intel Corporation
+ */
+
+#ifndef _XE_GUC_CAPTURE_TYPES_H
+#define _XE_GUC_CAPTURE_TYPES_H
+
+#include <linux/types.h>
+#include "regs/xe_reg_defs.h"
+
+struct xe_guc;
+
+/**
+ * struct __guc_mmio_reg_descr - GuC mmio register descriptor
+ *
+ * xe_guc_capture module uses these structures to define a register
+ * (offsets, names, flags,...) that are used at the ADS regisration
+ * time as well as during runtime processing and reporting of error-
+ * capture states generated by GuC just prior to engine reset events.
+ */
+struct __guc_mmio_reg_descr {
+ /** @reg: the register */
+ struct xe_reg reg;
+ /** @flags: Flags for the register */
+ u32 flags;
+ /** @mask: The mask to apply */
+ u32 mask;
+ /** @regname: Name of the register */
+ const char *regname;
+};
+
+/**
+ * struct __guc_mmio_reg_descr_group - The group of register descriptor
+ *
+ * xe_guc_capture module uses these structures to maintain static
+ * tables (per unique platform) that consists of lists of registers
+ * (offsets, names, flags,...) that are used at the ADS regisration
+ * time as well as during runtime processing and reporting of error-
+ * capture states generated by GuC just prior to engine reset events.
+ */
+struct __guc_mmio_reg_descr_group {
+ /** @list: The register list */
+ const struct __guc_mmio_reg_descr *list;
+ /** @num_regs: Count of registers in the list */
+ u32 num_regs;
+ /** @owner: PF/VF owner */
+ u32 owner; /* see enum guc_capture_list_index_type */
+ /** @type: GuC capture register type */
+ u32 type; /* see enum guc_state_capture_type */
+ /** @engine: The engine class */
+ u32 engine; /* see enum guc_capture_list_class_type */
+};
+
+#endif
diff --git a/drivers/gpu/drm/xe/xe_guc_fwif.h b/drivers/gpu/drm/xe/xe_guc_fwif.h
index 19ee71aeaf17..01e3ab590c3a 100644
--- a/drivers/gpu/drm/xe/xe_guc_fwif.h
+++ b/drivers/gpu/drm/xe/xe_guc_fwif.h
@@ -8,7 +8,9 @@
#include <linux/bits.h>
+#include "abi/guc_capture_abi.h"
#include "abi/guc_klvs_abi.h"
+#include "xe_hw_engine_types.h"
#define G2H_LEN_DW_SCHED_CONTEXT_MODE_SET 4
#define G2H_LEN_DW_DEREGISTER_CONTEXT 3
@@ -157,24 +159,6 @@ struct guc_policies {
u32 reserved[4];
} __packed;
-/* GuC MMIO reg state struct */
-struct guc_mmio_reg {
- u32 offset;
- u32 value;
- u32 flags;
- u32 mask;
-#define GUC_REGSET_MASKED BIT(0)
-#define GUC_REGSET_MASKED_WITH_VALUE BIT(2)
-#define GUC_REGSET_RESTORE_ONLY BIT(3)
-} __packed;
-
-/* GuC register sets */
-struct guc_mmio_reg_set {
- u32 address;
- u16 count;
- u16 reserved;
-} __packed;
-
/* Generic GT SysInfo data types */
#define GUC_GENERIC_GT_SYSINFO_SLICE_ENABLED 0
#define GUC_GENERIC_GT_SYSINFO_VDBOX_SFC_SUPPORT_MASK 1
@@ -188,12 +172,6 @@ struct guc_gt_system_info {
u32 generic_gt_sysinfo[GUC_GENERIC_GT_SYSINFO_MAX];
} __packed;
-enum {
- GUC_CAPTURE_LIST_INDEX_PF = 0,
- GUC_CAPTURE_LIST_INDEX_VF = 1,
- GUC_CAPTURE_LIST_INDEX_MAX = 2,
-};
-
/* GuC Additional Data Struct */
struct guc_ads {
struct guc_mmio_reg_set reg_state_list[GUC_MAX_ENGINE_CLASSES][GUC_MAX_INSTANCES_PER_CLASS];
diff --git a/drivers/gpu/drm/xe/xe_guc_types.h b/drivers/gpu/drm/xe/xe_guc_types.h
index 546ac6350a31..6d7d0976b7af 100644
--- a/drivers/gpu/drm/xe/xe_guc_types.h
+++ b/drivers/gpu/drm/xe/xe_guc_types.h
@@ -58,6 +58,8 @@ struct xe_guc {
struct xe_guc_ads ads;
/** @ct: GuC ct */
struct xe_guc_ct ct;
+ /** @capture: the error-state-capture module's data and objects */
+ struct xe_guc_state_capture *capture;
/** @pc: GuC Power Conservation */
struct xe_guc_pc pc;
/** @dbm: GuC Doorbell Manager */
--
2.34.1
More information about the Intel-xe
mailing list