1 files changed, 446 insertions, 70 deletions

diff --git a/drivers/gpu/drm/panthor/panthor_sched.c b/drivers/gpu/drm/panthor/panthor_sched.c
index aee362abb710..43ee57728de5 100644
--- a/drivers/gpu/drm/panthor/panthor_sched.c
+++ b/drivers/gpu/drm/panthor/panthor_sched.c
@@ -9,6 +9,7 @@
 #include <drm/panthor_drm.h>
 
 #include <linux/build_bug.h>
+#include <linux/cleanup.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
@@ -88,11 +89,11 @@
 
 #define JOB_TIMEOUT_MS				5000
 
-#define MIN_CS_PER_CSG				8
-
-#define MIN_CSGS				3
 #define MAX_CSG_PRIO				0xf
 
+#define NUM_INSTRS_PER_CACHE_LINE		(64 / sizeof(u64))
+#define MAX_INSTRS_PER_JOB			24
+
 struct panthor_group;
 
 /**
@@ -137,8 +138,6 @@ enum panthor_csg_priority {
 	 * non-real-time groups. When such a group becomes executable,
 	 * it will evict the group with the lowest non-rt priority if
 	 * there's no free group slot available.
-	 *
-	 * Currently not exposed to userspace.
 	 */
 	PANTHOR_CSG_PRIORITY_RT,
 
@@ -476,6 +475,18 @@ struct panthor_queue {
 		 */
 		struct list_head in_flight_jobs;
 	} fence_ctx;
+
+	/** @profiling: Job profiling data slots and access information. */
+	struct {
+		/** @slots: Kernel BO holding the slots. */
+		struct panthor_kernel_bo *slots;
+
+		/** @slot_count: Number of jobs ringbuffer can hold at once. */
+		u32 slot_count;
+
+		/** @seqno: Index of the next available profiling information slot. */
+		u32 seqno;
+	} profiling;
 };
 
 /**
@@ -589,14 +600,25 @@ struct panthor_group {
 	 * @timedout: True when a timeout occurred on any of the queues owned by
 	 * this group.
 	 *
-	 * Timeouts can be reported by drm_sched or by the FW. In any case, any
-	 * timeout situation is unrecoverable, and the group becomes useless.
-	 * We simply wait for all references to be dropped so we can release the
-	 * group object.
+	 * Timeouts can be reported by drm_sched or by the FW. If a reset is required,
+	 * and the group can't be suspended, this also leads to a timeout. In any case,
+	 * any timeout situation is unrecoverable, and the group becomes useless. We
+	 * simply wait for all references to be dropped so we can release the group
+	 * object.
 	 */
 	bool timedout;
 
 	/**
+	 * @innocent: True when the group becomes unusable because the group suspension
+	 * failed during a reset.
+	 *
+	 * Sometimes the FW was put in a bad state by other groups, causing the group
+	 * suspension happening in the reset path to fail. In that case, we consider the
+	 * group innocent.
+	 */
+	bool innocent;
+
+	/**
 	 * @syncobjs: Pool of per-queue synchronization objects.
 	 *
 	 * One sync object per queue. The position of the sync object is
@@ -604,6 +626,21 @@ struct panthor_group {
 	 */
 	struct panthor_kernel_bo *syncobjs;
 
+	/** @fdinfo: Per-file info exposed through /proc/<process>/fdinfo */
+	struct {
+		/** @data: Total sampled values for jobs in queues from this group. */
+		struct panthor_gpu_usage data;
+
+		/**
+		 * @fdinfo.lock: Spinlock to govern concurrent access from drm file's fdinfo
+		 * callback and job post-completion processing function
+		 */
+		spinlock_t lock;
+
+		/** @fdinfo.kbo_sizes: Aggregate size of private kernel BO's held by the group. */
+		size_t kbo_sizes;
+	} fdinfo;
+
 	/** @state: Group state. */
 	enum panthor_group_state state;
 
@@ -661,6 +698,18 @@ struct panthor_group {
 	struct list_head wait_node;
 };
 
+struct panthor_job_profiling_data {
+	struct {
+		u64 before;
+		u64 after;
+	} cycles;
+
+	struct {
+		u64 before;
+		u64 after;
+	} time;
+};
+
 /**
  * group_queue_work() - Queue a group work
  * @group: Group to queue the work for.
@@ -774,6 +823,15 @@ struct panthor_job {
 
 	/** @done_fence: Fence signaled when the job is finished or cancelled. */
 	struct dma_fence *done_fence;
+
+	/** @profiling: Job profiling information. */
+	struct {
+		/** @mask: Current device job profiling enablement bitmask. */
+		u32 mask;
+
+		/** @slot: Job index in the profiling slots BO. */
+		u32 slot;
+	} profiling;
 };
 
 static void
@@ -782,7 +840,7 @@ panthor_queue_put_syncwait_obj(struct panthor_queue *queue)
 	if (queue->syncwait.kmap) {
 		struct iosys_map map = IOSYS_MAP_INIT_VADDR(queue->syncwait.kmap);
 
-		drm_gem_vunmap_unlocked(queue->syncwait.obj, &map);
+		drm_gem_vunmap(queue->syncwait.obj, &map);
 		queue->syncwait.kmap = NULL;
 	}
 
@@ -808,7 +866,7 @@ panthor_queue_get_syncwait_obj(struct panthor_group *group, struct panthor_queue
 		goto err_put_syncwait_obj;
 
 	queue->syncwait.obj = &bo->base.base;
-	ret = drm_gem_vmap_unlocked(queue->syncwait.obj, &map);
+	ret = drm_gem_vmap(queue->syncwait.obj, &map);
 	if (drm_WARN_ON(&ptdev->base, ret))
 		goto err_put_syncwait_obj;
 
@@ -838,6 +896,7 @@ static void group_free_queue(struct panthor_group *group, struct panthor_queue *
 
 	panthor_kernel_bo_destroy(queue->ringbuf);
 	panthor_kernel_bo_destroy(queue->iface.mem);
+	panthor_kernel_bo_destroy(queue->profiling.slots);
 
 	/* Release the last_fence we were holding, if any. */
 	dma_fence_put(queue->fence_ctx.last_fence);
@@ -1988,8 +2047,6 @@ tick_ctx_init(struct panthor_scheduler *sched,
 	}
 }
 
-#define NUM_INSTRS_PER_SLOT		16
-
 static void
 group_term_post_processing(struct panthor_group *group)
 {
@@ -2306,7 +2363,7 @@ static void tick_work(struct work_struct *work)
 	if (!drm_dev_enter(&ptdev->base, &cookie))
 		return;
 
-	ret = pm_runtime_resume_and_get(ptdev->base.dev);
+	ret = panthor_device_resume_and_get(ptdev);
 	if (drm_WARN_ON(&ptdev->base, ret))
 		goto out_dev_exit;
 
@@ -2545,7 +2602,7 @@ static void queue_start(struct panthor_queue *queue)
 	list_for_each_entry(job, &queue->scheduler.pending_list, base.list)
 		job->base.s_fence->parent = dma_fence_get(job->done_fence);
 
-	drm_sched_start(&queue->scheduler);
+	drm_sched_start(&queue->scheduler, 0);
 }
 
 static void panthor_group_stop(struct panthor_group *group)
@@ -2640,6 +2697,18 @@ void panthor_sched_suspend(struct panthor_device *ptdev)
 		csgs_upd_ctx_init(&upd_ctx);
 		while (slot_mask) {
 			u32 csg_id = ffs(slot_mask) - 1;
+			struct panthor_csg_slot *csg_slot = &sched->csg_slots[csg_id];
+
+			/* If the group was still usable before that point, we consider
+			 * it innocent.
+			 */
+			if (group_can_run(csg_slot->group))
+				csg_slot->group->innocent = true;
+
+			/* We consider group suspension failures as fatal and flag the
+			 * group as unusable by setting timedout=true.
+			 */
+			csg_slot->group->timedout = true;
 
 			csgs_upd_ctx_queue_reqs(ptdev, &upd_ctx, csg_id,
 						CSG_STATE_TERMINATE,
@@ -2783,6 +2852,42 @@ void panthor_sched_post_reset(struct panthor_device *ptdev, bool reset_failed)
 	}
 }
 
+static void update_fdinfo_stats(struct panthor_job *job)
+{
+	struct panthor_group *group = job->group;
+	struct panthor_queue *queue = group->queues[job->queue_idx];
+	struct panthor_gpu_usage *fdinfo = &group->fdinfo.data;
+	struct panthor_job_profiling_data *slots = queue->profiling.slots->kmap;
+	struct panthor_job_profiling_data *data = &slots[job->profiling.slot];
+
+	scoped_guard(spinlock, &group->fdinfo.lock) {
+		if (job->profiling.mask & PANTHOR_DEVICE_PROFILING_CYCLES)
+			fdinfo->cycles += data->cycles.after - data->cycles.before;
+		if (job->profiling.mask & PANTHOR_DEVICE_PROFILING_TIMESTAMP)
+			fdinfo->time += data->time.after - data->time.before;
+	}
+}
+
+void panthor_fdinfo_gather_group_samples(struct panthor_file *pfile)
+{
+	struct panthor_group_pool *gpool = pfile->groups;
+	struct panthor_group *group;
+	unsigned long i;
+
+	if (IS_ERR_OR_NULL(gpool))
+		return;
+
+	xa_lock(&gpool->xa);
+	xa_for_each(&gpool->xa, i, group) {
+		guard(spinlock)(&group->fdinfo.lock);
+		pfile->stats.cycles += group->fdinfo.data.cycles;
+		pfile->stats.time += group->fdinfo.data.time;
+		group->fdinfo.data.cycles = 0;
+		group->fdinfo.data.time = 0;
+	}
+	xa_unlock(&gpool->xa);
+}
+
 static void group_sync_upd_work(struct work_struct *work)
 {
 	struct panthor_group *group =
@@ -2815,6 +2920,8 @@ static void group_sync_upd_work(struct work_struct *work)
 	dma_fence_end_signalling(cookie);
 
 	list_for_each_entry_safe(job, job_tmp, &done_jobs, node) {
+		if (job->profiling.mask)
+			update_fdinfo_stats(job);
 		list_del_init(&job->node);
 		panthor_job_put(&job->base);
 	}
@@ -2822,65 +2929,198 @@ static void group_sync_upd_work(struct work_struct *work)
 	group_put(group);
 }
 
-static struct dma_fence *
-queue_run_job(struct drm_sched_job *sched_job)
+struct panthor_job_ringbuf_instrs {
+	u64 buffer[MAX_INSTRS_PER_JOB];
+	u32 count;
+};
+
+struct panthor_job_instr {
+	u32 profile_mask;
+	u64 instr;
+};
+
+#define JOB_INSTR(__prof, __instr) \
+	{ \
+		.profile_mask = __prof, \
+		.instr = __instr, \
+	}
+
+static void
+copy_instrs_to_ringbuf(struct panthor_queue *queue,
+		       struct panthor_job *job,
+		       struct panthor_job_ringbuf_instrs *instrs)
+{
+	u64 ringbuf_size = panthor_kernel_bo_size(queue->ringbuf);
+	u64 start = job->ringbuf.start & (ringbuf_size - 1);
+	u64 size, written;
+
+	/*
+	 * We need to write a whole slot, including any trailing zeroes
+	 * that may come at the end of it. Also, because instrs.buffer has
+	 * been zero-initialised, there's no need to pad it with 0's
+	 */
+	instrs->count = ALIGN(instrs->count, NUM_INSTRS_PER_CACHE_LINE);
+	size = instrs->count * sizeof(u64);
+	WARN_ON(size > ringbuf_size);
+	written = min(ringbuf_size - start, size);
+
+	memcpy(queue->ringbuf->kmap + start, instrs->buffer, written);
+
+	if (written < size)
+		memcpy(queue->ringbuf->kmap,
+		       &instrs->buffer[written / sizeof(u64)],
+		       size - written);
+}
+
+struct panthor_job_cs_params {
+	u32 profile_mask;
+	u64 addr_reg; u64 val_reg;
+	u64 cycle_reg; u64 time_reg;
+	u64 sync_addr; u64 times_addr;
+	u64 cs_start; u64 cs_size;
+	u32 last_flush; u32 waitall_mask;
+};
+
+static void
+get_job_cs_params(struct panthor_job *job, struct panthor_job_cs_params *params)
 {
-	struct panthor_job *job = container_of(sched_job, struct panthor_job, base);
 	struct panthor_group *group = job->group;
 	struct panthor_queue *queue = group->queues[job->queue_idx];
 	struct panthor_device *ptdev = group->ptdev;
 	struct panthor_scheduler *sched = ptdev->scheduler;
-	u32 ringbuf_size = panthor_kernel_bo_size(queue->ringbuf);
-	u32 ringbuf_insert = queue->iface.input->insert & (ringbuf_size - 1);
-	u64 addr_reg = ptdev->csif_info.cs_reg_count -
-		       ptdev->csif_info.unpreserved_cs_reg_count;
-	u64 val_reg = addr_reg + 2;
-	u64 sync_addr = panthor_kernel_bo_gpuva(group->syncobjs) +
-			job->queue_idx * sizeof(struct panthor_syncobj_64b);
-	u32 waitall_mask = GENMASK(sched->sb_slot_count - 1, 0);
-	struct dma_fence *done_fence;
-	int ret;
 
-	u64 call_instrs[NUM_INSTRS_PER_SLOT] = {
-		/* MOV32 rX+2, cs.latest_flush */
-		(2ull << 56) | (val_reg << 48) | job->call_info.latest_flush,
+	params->addr_reg = ptdev->csif_info.cs_reg_count -
+			   ptdev->csif_info.unpreserved_cs_reg_count;
+	params->val_reg = params->addr_reg + 2;
+	params->cycle_reg = params->addr_reg;
+	params->time_reg = params->val_reg;
 
-		/* FLUSH_CACHE2.clean_inv_all.no_wait.signal(0) rX+2 */
-		(36ull << 56) | (0ull << 48) | (val_reg << 40) | (0 << 16) | 0x233,
+	params->sync_addr = panthor_kernel_bo_gpuva(group->syncobjs) +
+			    job->queue_idx * sizeof(struct panthor_syncobj_64b);
+	params->times_addr = panthor_kernel_bo_gpuva(queue->profiling.slots) +
+			     (job->profiling.slot * sizeof(struct panthor_job_profiling_data));
+	params->waitall_mask = GENMASK(sched->sb_slot_count - 1, 0);
 
-		/* MOV48 rX:rX+1, cs.start */
-		(1ull << 56) | (addr_reg << 48) | job->call_info.start,
+	params->cs_start = job->call_info.start;
+	params->cs_size = job->call_info.size;
+	params->last_flush = job->call_info.latest_flush;
 
-		/* MOV32 rX+2, cs.size */
-		(2ull << 56) | (val_reg << 48) | job->call_info.size,
+	params->profile_mask = job->profiling.mask;
+}
 
-		/* WAIT(0) => waits for FLUSH_CACHE2 instruction */
-		(3ull << 56) | (1 << 16),
+#define JOB_INSTR_ALWAYS(instr) \
+	JOB_INSTR(PANTHOR_DEVICE_PROFILING_DISABLED, (instr))
+#define JOB_INSTR_TIMESTAMP(instr) \
+	JOB_INSTR(PANTHOR_DEVICE_PROFILING_TIMESTAMP, (instr))
+#define JOB_INSTR_CYCLES(instr) \
+	JOB_INSTR(PANTHOR_DEVICE_PROFILING_CYCLES, (instr))
 
+static void
+prepare_job_instrs(const struct panthor_job_cs_params *params,
+		   struct panthor_job_ringbuf_instrs *instrs)
+{
+	const struct panthor_job_instr instr_seq[] = {
+		/* MOV32 rX+2, cs.latest_flush */
+		JOB_INSTR_ALWAYS((2ull << 56) | (params->val_reg << 48) | params->last_flush),
+		/* FLUSH_CACHE2.clean_inv_all.no_wait.signal(0) rX+2 */
+		JOB_INSTR_ALWAYS((36ull << 56) | (0ull << 48) | (params->val_reg << 40) |
+				 (0 << 16) | 0x233),
+		/* MOV48 rX:rX+1, cycles_offset */
+		JOB_INSTR_CYCLES((1ull << 56) | (params->cycle_reg << 48) |
+				 (params->times_addr +
+				  offsetof(struct panthor_job_profiling_data, cycles.before))),
+		/* STORE_STATE cycles */
+		JOB_INSTR_CYCLES((40ull << 56) | (params->cycle_reg << 40) | (1ll << 32)),
+		/* MOV48 rX:rX+1, time_offset */
+		JOB_INSTR_TIMESTAMP((1ull << 56) | (params->time_reg << 48) |
+				    (params->times_addr +
+				     offsetof(struct panthor_job_profiling_data, time.before))),
+		/* STORE_STATE timer */
+		JOB_INSTR_TIMESTAMP((40ull << 56) | (params->time_reg << 40) | (0ll << 32)),
+		/* MOV48 rX:rX+1, cs.start */
+		JOB_INSTR_ALWAYS((1ull << 56) | (params->addr_reg << 48) | params->cs_start),
+		/* MOV32 rX+2, cs.size */
+		JOB_INSTR_ALWAYS((2ull << 56) | (params->val_reg << 48) | params->cs_size),
+		/* WAIT(0) => waits for FLUSH_CACHE2 instruction */
+		JOB_INSTR_ALWAYS((3ull << 56) | (1 << 16)),
 		/* CALL rX:rX+1, rX+2 */
-		(32ull << 56) | (addr_reg << 40) | (val_reg << 32),
-
+		JOB_INSTR_ALWAYS((32ull << 56) | (params->addr_reg << 40) |
+				 (params->val_reg << 32)),
+		/* MOV48 rX:rX+1, cycles_offset */
+		JOB_INSTR_CYCLES((1ull << 56) | (params->cycle_reg << 48) |
+				 (params->times_addr +
+				  offsetof(struct panthor_job_profiling_data, cycles.after))),
+		/* STORE_STATE cycles */
+		JOB_INSTR_CYCLES((40ull << 56) | (params->cycle_reg << 40) | (1ll << 32)),
+		/* MOV48 rX:rX+1, time_offset */
+		JOB_INSTR_TIMESTAMP((1ull << 56) | (params->time_reg << 48) |
+			  (params->times_addr +
+			   offsetof(struct panthor_job_profiling_data, time.after))),
+		/* STORE_STATE timer */
+		JOB_INSTR_TIMESTAMP((40ull << 56) | (params->time_reg << 40) | (0ll << 32)),
 		/* MOV48 rX:rX+1, sync_addr */
-		(1ull << 56) | (addr_reg << 48) | sync_addr,
-
+		JOB_INSTR_ALWAYS((1ull << 56) | (params->addr_reg << 48) | params->sync_addr),
 		/* MOV48 rX+2, #1 */
-		(1ull << 56) | (val_reg << 48) | 1,
-
+		JOB_INSTR_ALWAYS((1ull << 56) | (params->val_reg << 48) | 1),
 		/* WAIT(all) */
-		(3ull << 56) | (waitall_mask << 16),
-
+		JOB_INSTR_ALWAYS((3ull << 56) | (params->waitall_mask << 16)),
 		/* SYNC_ADD64.system_scope.propage_err.nowait rX:rX+1, rX+2*/
-		(51ull << 56) | (0ull << 48) | (addr_reg << 40) | (val_reg << 32) | (0 << 16) | 1,
+		JOB_INSTR_ALWAYS((51ull << 56) | (0ull << 48) | (params->addr_reg << 40) |
+				 (params->val_reg << 32) | (0 << 16) | 1),
+		/* ERROR_BARRIER, so we can recover from faults at job boundaries. */
+		JOB_INSTR_ALWAYS((47ull << 56)),
+	};
+	u32 pad;
 
-		/* ERROR_BARRIER, so we can recover from faults at job
-		 * boundaries.
-		 */
-		(47ull << 56),
+	instrs->count = 0;
+
+	/* NEED to be cacheline aligned to please the prefetcher. */
+	static_assert(sizeof(instrs->buffer) % 64 == 0,
+		      "panthor_job_ringbuf_instrs::buffer is not aligned on a cacheline");
+
+	/* Make sure we have enough storage to store the whole sequence. */
+	static_assert(ALIGN(ARRAY_SIZE(instr_seq), NUM_INSTRS_PER_CACHE_LINE) ==
+		      ARRAY_SIZE(instrs->buffer),
+		      "instr_seq vs panthor_job_ringbuf_instrs::buffer size mismatch");
+
+	for (u32 i = 0; i < ARRAY_SIZE(instr_seq); i++) {
+		/* If the profile mask of this instruction is not enabled, skip it. */
+		if (instr_seq[i].profile_mask &&
+		    !(instr_seq[i].profile_mask & params->profile_mask))
+			continue;
+
+		instrs->buffer[instrs->count++] = instr_seq[i].instr;
+	}
+
+	pad = ALIGN(instrs->count, NUM_INSTRS_PER_CACHE_LINE);
+	memset(&instrs->buffer[instrs->count], 0,
+	       (pad - instrs->count) * sizeof(instrs->buffer[0]));
+	instrs->count = pad;
+}
+
+static u32 calc_job_credits(u32 profile_mask)
+{
+	struct panthor_job_ringbuf_instrs instrs;
+	struct panthor_job_cs_params params = {
+		.profile_mask = profile_mask,
 	};
 
-	/* Need to be cacheline aligned to please the prefetcher. */
-	static_assert(sizeof(call_instrs) % 64 == 0,
-		      "call_instrs is not aligned on a cacheline");
+	prepare_job_instrs(&params, &instrs);
+	return instrs.count;
+}
+
+static struct dma_fence *
+queue_run_job(struct drm_sched_job *sched_job)
+{
+	struct panthor_job *job = container_of(sched_job, struct panthor_job, base);
+	struct panthor_group *group = job->group;
+	struct panthor_queue *queue = group->queues[job->queue_idx];
+	struct panthor_device *ptdev = group->ptdev;
+	struct panthor_scheduler *sched = ptdev->scheduler;
+	struct panthor_job_ringbuf_instrs instrs;
+	struct panthor_job_cs_params cs_params;
+	struct dma_fence *done_fence;
+	int ret;
 
 	/* Stream size is zero, nothing to do except making sure all previously
 	 * submitted jobs are done before we signal the
@@ -2891,7 +3131,7 @@ queue_run_job(struct drm_sched_job *sched_job)
 		return dma_fence_get(job->done_fence);
 	}
 
-	ret = pm_runtime_resume_and_get(ptdev->base.dev);
+	ret = panthor_device_resume_and_get(ptdev);
 	if (drm_WARN_ON(&ptdev->base, ret))
 		return ERR_PTR(ret);
 
@@ -2907,17 +3147,23 @@ queue_run_job(struct drm_sched_job *sched_job)
 		       queue->fence_ctx.id,
 		       atomic64_inc_return(&queue->fence_ctx.seqno));
 
-	memcpy(queue->ringbuf->kmap + ringbuf_insert,
-	       call_instrs, sizeof(call_instrs));
+	job->profiling.slot = queue->profiling.seqno++;
+	if (queue->profiling.seqno == queue->profiling.slot_count)
+		queue->profiling.seqno = 0;
+
+	job->ringbuf.start = queue->iface.input->insert;
+
+	get_job_cs_params(job, &cs_params);
+	prepare_job_instrs(&cs_params, &instrs);
+	copy_instrs_to_ringbuf(queue, job, &instrs);
+
+	job->ringbuf.end = job->ringbuf.start + (instrs.count * sizeof(u64));
 
 	panthor_job_get(&job->base);
 	spin_lock(&queue->fence_ctx.lock);
 	list_add_tail(&job->node, &queue->fence_ctx.in_flight_jobs);
 	spin_unlock(&queue->fence_ctx.lock);
 
-	job->ringbuf.start = queue->iface.input->insert;
-	job->ringbuf.end = job->ringbuf.start + sizeof(call_instrs);
-
 	/* Make sure the ring buffer is updated before the INSERT
 	 * register.
 	 */
@@ -3010,10 +3256,53 @@ static const struct drm_sched_backend_ops panthor_queue_sched_ops = {
 	.free_job = queue_free_job,
 };
 
+static u32 calc_profiling_ringbuf_num_slots(struct panthor_device *ptdev,
+					    u32 cs_ringbuf_size)
+{
+	u32 min_profiled_job_instrs = U32_MAX;
+	u32 last_flag = fls(PANTHOR_DEVICE_PROFILING_ALL);
+
+	/*
+	 * We want to calculate the minimum size of a profiled job's CS,
+	 * because since they need additional instructions for the sampling
+	 * of performance metrics, they might take up further slots in
+	 * the queue's ringbuffer. This means we might not need as many job
+	 * slots for keeping track of their profiling information. What we
+	 * need is the maximum number of slots we should allocate to this end,
+	 * which matches the maximum number of profiled jobs we can place
+	 * simultaneously in the queue's ring buffer.
+	 * That has to be calculated separately for every single job profiling
+	 * flag, but not in the case job profiling is disabled, since unprofiled
+	 * jobs don't need to keep track of this at all.
+	 */
+	for (u32 i = 0; i < last_flag; i++) {
+		min_profiled_job_instrs =
+			min(min_profiled_job_instrs, calc_job_credits(BIT(i)));
+	}
+
+	return DIV_ROUND_UP(cs_ringbuf_size, min_profiled_job_instrs * sizeof(u64));
+}
+
 static struct panthor_queue *
 group_create_queue(struct panthor_group *group,
 		   const struct drm_panthor_queue_create *args)
 {
+	const struct drm_sched_init_args sched_args = {
+		.ops = &panthor_queue_sched_ops,
+		.submit_wq = group->ptdev->scheduler->wq,
+		.num_rqs = 1,
+		/*
+		 * The credit limit argument tells us the total number of
+		 * instructions across all CS slots in the ringbuffer, with
+		 * some jobs requiring twice as many as others, depending on
+		 * their profiling status.
+		 */
+		.credit_limit = args->ringbuf_size / sizeof(u64),
+		.timeout = msecs_to_jiffies(JOB_TIMEOUT_MS),
+		.timeout_wq = group->ptdev->reset.wq,
+		.name = "panthor-queue",
+		.dev = group->ptdev->base.dev,
+	};
 	struct drm_gpu_scheduler *drm_sched;
 	struct panthor_queue *queue;
 	int ret;
@@ -3043,7 +3332,8 @@ group_create_queue(struct panthor_group *group,
 						  DRM_PANTHOR_BO_NO_MMAP,
 						  DRM_PANTHOR_VM_BIND_OP_MAP_NOEXEC |
 						  DRM_PANTHOR_VM_BIND_OP_MAP_UNCACHED,
-						  PANTHOR_VM_KERNEL_AUTO_VA);
+						  PANTHOR_VM_KERNEL_AUTO_VA,
+						  "CS ring buffer");
 	if (IS_ERR(queue->ringbuf)) {
 		ret = PTR_ERR(queue->ringbuf);
 		goto err_free_queue;
@@ -3063,12 +3353,29 @@ group_create_queue(struct panthor_group *group,
 		goto err_free_queue;
 	}
 
-	ret = drm_sched_init(&queue->scheduler, &panthor_queue_sched_ops,
-			     group->ptdev->scheduler->wq, 1,
-			     args->ringbuf_size / (NUM_INSTRS_PER_SLOT * sizeof(u64)),
-			     0, msecs_to_jiffies(JOB_TIMEOUT_MS),
-			     group->ptdev->reset.wq,
-			     NULL, "panthor-queue", group->ptdev->base.dev);
+	queue->profiling.slot_count =
+		calc_profiling_ringbuf_num_slots(group->ptdev, args->ringbuf_size);
+
+	queue->profiling.slots =
+		panthor_kernel_bo_create(group->ptdev, group->vm,
+					 queue->profiling.slot_count *
+					 sizeof(struct panthor_job_profiling_data),
+					 DRM_PANTHOR_BO_NO_MMAP,
+					 DRM_PANTHOR_VM_BIND_OP_MAP_NOEXEC |
+					 DRM_PANTHOR_VM_BIND_OP_MAP_UNCACHED,
+					 PANTHOR_VM_KERNEL_AUTO_VA,
+					 "Group job stats");
+
+	if (IS_ERR(queue->profiling.slots)) {
+		ret = PTR_ERR(queue->profiling.slots);
+		goto err_free_queue;
+	}
+
+	ret = panthor_kernel_bo_vmap(queue->profiling.slots);
+	if (ret)
+		goto err_free_queue;
+
+	ret = drm_sched_init(&queue->scheduler, &sched_args);
 	if (ret)
 		goto err_free_queue;
 
@@ -3082,6 +3389,29 @@ err_free_queue:
 	return ERR_PTR(ret);
 }
 
+static void add_group_kbo_sizes(struct panthor_device *ptdev,
+				struct panthor_group *group)
+{
+	struct panthor_queue *queue;
+	int i;
+
+	if (drm_WARN_ON(&ptdev->base, IS_ERR_OR_NULL(group)))
+		return;
+	if (drm_WARN_ON(&ptdev->base, ptdev != group->ptdev))
+		return;
+
+	group->fdinfo.kbo_sizes += group->suspend_buf->obj->size;
+	group->fdinfo.kbo_sizes += group->protm_suspend_buf->obj->size;
+	group->fdinfo.kbo_sizes += group->syncobjs->obj->size;
+
+	for (i = 0; i < group->queue_count; i++) {
+		queue =	group->queues[i];
+		group->fdinfo.kbo_sizes += queue->ringbuf->obj->size;
+		group->fdinfo.kbo_sizes += queue->iface.mem->obj->size;
+		group->fdinfo.kbo_sizes += queue->profiling.slots->obj->size;
+	}
+}
+
 #define MAX_GROUPS_PER_POOL		128
 
 int panthor_group_create(struct panthor_file *pfile,
@@ -3165,7 +3495,8 @@ int panthor_group_create(struct panthor_file *pfile,
 						   DRM_PANTHOR_BO_NO_MMAP,
 						   DRM_PANTHOR_VM_BIND_OP_MAP_NOEXEC |
 						   DRM_PANTHOR_VM_BIND_OP_MAP_UNCACHED,
-						   PANTHOR_VM_KERNEL_AUTO_VA);
+						   PANTHOR_VM_KERNEL_AUTO_VA,
+						   "Group sync objects");
 	if (IS_ERR(group->syncobjs)) {
 		ret = PTR_ERR(group->syncobjs);
 		goto err_put_group;
@@ -3206,6 +3537,9 @@ int panthor_group_create(struct panthor_file *pfile,
 	}
 	mutex_unlock(&sched->reset.lock);
 
+	add_group_kbo_sizes(group->ptdev, group);
+	spin_lock_init(&group->fdinfo.lock);
+
 	return gid;
 
 err_put_group:
@@ -3285,6 +3619,8 @@ int panthor_group_get_state(struct panthor_file *pfile,
 		get_state->state |= DRM_PANTHOR_GROUP_STATE_FATAL_FAULT;
 		get_state->fatal_queues = group->fatal_queues;
 	}
+	if (group->innocent)
+		get_state->state |= DRM_PANTHOR_GROUP_STATE_INNOCENT;
 	mutex_unlock(&sched->lock);
 
 	group_put(group);
@@ -3321,6 +3657,33 @@ void panthor_group_pool_destroy(struct panthor_file *pfile)
 	pfile->groups = NULL;
 }
 
+/**
+ * panthor_fdinfo_gather_group_mem_info() - Retrieve aggregate size of all private kernel BO's
+ * belonging to all the groups owned by an open Panthor file
+ * @pfile: File.
+ * @stats: Memory statistics to be updated.
+ *
+ */
+void
+panthor_fdinfo_gather_group_mem_info(struct panthor_file *pfile,
+				     struct drm_memory_stats *stats)
+{
+	struct panthor_group_pool *gpool = pfile->groups;
+	struct panthor_group *group;
+	unsigned long i;
+
+	if (IS_ERR_OR_NULL(gpool))
+		return;
+
+	xa_lock(&gpool->xa);
+	xa_for_each(&gpool->xa, i, group) {
+		stats->resident += group->fdinfo.kbo_sizes;
+		if (group->csg_id >= 0)
+			stats->active += group->fdinfo.kbo_sizes;
+	}
+	xa_unlock(&gpool->xa);
+}
+
 static void job_release(struct kref *ref)
 {
 	struct panthor_job *job = container_of(ref, struct panthor_job, refcount);
@@ -3373,6 +3736,7 @@ panthor_job_create(struct panthor_file *pfile,
 {
 	struct panthor_group_pool *gpool = pfile->groups;
 	struct panthor_job *job;
+	u32 credits;
 	int ret;
 
 	if (qsubmit->pad)
@@ -3409,6 +3773,11 @@ panthor_job_create(struct panthor_file *pfile,
 		goto err_put_job;
 	}
 
+	if (!group_can_run(job->group)) {
+		ret = -EINVAL;
+		goto err_put_job;
+	}
+
 	if (job->queue_idx >= job->group->queue_count ||
 	    !job->group->queues[job->queue_idx]) {
 		ret = -EINVAL;
@@ -3426,9 +3795,16 @@ panthor_job_create(struct panthor_file *pfile,
 		}
 	}
 
+	job->profiling.mask = pfile->ptdev->profile_mask;
+	credits = calc_job_credits(job->profiling.mask);
+	if (credits == 0) {
+		ret = -EINVAL;
+		goto err_put_job;
+	}
+
 	ret = drm_sched_job_init(&job->base,
 				 &job->group->queues[job->queue_idx]->entity,
-				 1, job->group);
+				 credits, job->group);
 	if (ret)
 		goto err_put_job;