drm/panthor: Support 64-bit endpoint_req register for Mali-G1

Add support for the 64-bit endpoint_req register introduced in CSF v4.0+
GPUs. Unlike a simple register widening, the 64-bit variant occupies the
next 64 bits after the original 32-bit field, requiring
version-dependent access.

This change introduces helper functions to read, write, and update the
endpoint_req register, ensuring correct handling on both pre-v4.0 and
v4.0+ firmwares.

Reviewed-by: Steven Price <steven.price@arm.com>
Signed-off-by: Karunika Choo <karunika.choo@arm.com>
Link: https://patch.msgid.link/20251125125548.3282320-8-karunika.choo@arm.com
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>

drivers/gpu/drm/panthor/panthor_fw.c

@@ -326,6 +326,42 @@ static bool panthor_fw_has_glb_state(struct panthor_device *ptdev)
 	return glb_iface->control->version >= CSF_IFACE_VERSION(4, 1, 0);
 }
 
+static bool panthor_fw_has_64bit_ep_req(struct panthor_device *ptdev)
+{
+	struct panthor_fw_global_iface *glb_iface = panthor_fw_get_glb_iface(ptdev);
+
+	return glb_iface->control->version >= CSF_IFACE_VERSION(4, 0, 0);
+}
+
+u64 panthor_fw_csg_endpoint_req_get(struct panthor_device *ptdev,
+				    struct panthor_fw_csg_iface *csg_iface)
+{
+	if (panthor_fw_has_64bit_ep_req(ptdev))
+		return csg_iface->input->endpoint_req2;
+	else
+		return csg_iface->input->endpoint_req;
+}
+
+void panthor_fw_csg_endpoint_req_set(struct panthor_device *ptdev,
+				     struct panthor_fw_csg_iface *csg_iface, u64 value)
+{
+	if (panthor_fw_has_64bit_ep_req(ptdev))
+		csg_iface->input->endpoint_req2 = value;
+	else
+		csg_iface->input->endpoint_req = lower_32_bits(value);
+}
+
+void panthor_fw_csg_endpoint_req_update(struct panthor_device *ptdev,
+					struct panthor_fw_csg_iface *csg_iface, u64 value,
+					u64 mask)
+{
+	if (panthor_fw_has_64bit_ep_req(ptdev))
+		panthor_fw_update_reqs64(csg_iface, endpoint_req2, value, mask);
+	else
+		panthor_fw_update_reqs(csg_iface, endpoint_req, lower_32_bits(value),
+				       lower_32_bits(mask));
+}
+
 /**
  * panthor_fw_conv_timeout() - Convert a timeout into a cycle-count
  * @ptdev: Device.

drivers/gpu/drm/panthor/panthor_fw.h

@@ -167,10 +167,11 @@ struct panthor_fw_csg_input_iface {
 #define CSG_EP_REQ_TILER(x)			(((x) << 16) & GENMASK(19, 16))
 #define CSG_EP_REQ_EXCL_COMPUTE			BIT(20)
 #define CSG_EP_REQ_EXCL_FRAGMENT		BIT(21)
-#define CSG_EP_REQ_PRIORITY(x)			(((x) << 28) & GENMASK(31, 28))
 #define CSG_EP_REQ_PRIORITY_MASK		GENMASK(31, 28)
+#define CSG_EP_REQ_PRIORITY(x)			(((x) << 28) & CSG_EP_REQ_PRIORITY_MASK)
+#define CSG_EP_REQ_PRIORITY_GET(x)		(((x) & CSG_EP_REQ_PRIORITY_MASK) >> 28)
 	u32 endpoint_req;
-	u32 reserved2[2];
+	u64 endpoint_req2;
 	u64 suspend_buf;
 	u64 protm_suspend_buf;
 	u32 config;
@@ -464,6 +465,16 @@ struct panthor_fw_global_iface {
 		spin_unlock(&(__iface)->lock); \
 	} while (0)
 
+#define panthor_fw_update_reqs64(__iface, __in_reg, __val, __mask) \
+	do { \
+		u64 __cur_val, __new_val; \
+		spin_lock(&(__iface)->lock); \
+		__cur_val = READ_ONCE((__iface)->input->__in_reg); \
+		__new_val = (__cur_val & ~(__mask)) | ((__val) & (__mask)); \
+		WRITE_ONCE((__iface)->input->__in_reg, __new_val); \
+		spin_unlock(&(__iface)->lock); \
+	} while (0)
+
 struct panthor_fw_global_iface *
 panthor_fw_get_glb_iface(struct panthor_device *ptdev);
 
@@ -473,6 +484,16 @@ panthor_fw_get_csg_iface(struct panthor_device *ptdev, u32 csg_slot);
 struct panthor_fw_cs_iface *
 panthor_fw_get_cs_iface(struct panthor_device *ptdev, u32 csg_slot, u32 cs_slot);
 
+u64 panthor_fw_csg_endpoint_req_get(struct panthor_device *ptdev,
+				    struct panthor_fw_csg_iface *csg_iface);
+
+void panthor_fw_csg_endpoint_req_set(struct panthor_device *ptdev,
+				     struct panthor_fw_csg_iface *csg_iface, u64 value);
+
+void panthor_fw_csg_endpoint_req_update(struct panthor_device *ptdev,
+					struct panthor_fw_csg_iface *csg_iface, u64 value,
+					u64 mask);
+
 int panthor_fw_csg_wait_acks(struct panthor_device *ptdev, u32 csg_id, u32 req_mask,
 			     u32 *acked, u32 timeout_ms);
 

drivers/gpu/drm/panthor/panthor_sched.c

@@ -1140,11 +1140,13 @@ csg_slot_sync_priority_locked(struct panthor_device *ptdev, u32 csg_id)
 {
 	struct panthor_csg_slot *csg_slot = &ptdev->scheduler->csg_slots[csg_id];
 	struct panthor_fw_csg_iface *csg_iface;
+	u64 endpoint_req;
 
 	lockdep_assert_held(&ptdev->scheduler->lock);
 
 	csg_iface = panthor_fw_get_csg_iface(ptdev, csg_id);
-	csg_slot->priority = (csg_iface->input->endpoint_req & CSG_EP_REQ_PRIORITY_MASK) >> 28;
+	endpoint_req = panthor_fw_csg_endpoint_req_get(ptdev, csg_iface);
+	csg_slot->priority = CSG_EP_REQ_PRIORITY_GET(endpoint_req);
 }
 
 /**
@@ -1304,6 +1306,7 @@ csg_slot_prog_locked(struct panthor_device *ptdev, u32 csg_id, u32 priority)
 	struct panthor_csg_slot *csg_slot;
 	struct panthor_group *group;
 	u32 queue_mask = 0, i;
+	u64 endpoint_req;
 
 	lockdep_assert_held(&ptdev->scheduler->lock);
 
@@ -1330,10 +1333,12 @@ csg_slot_prog_locked(struct panthor_device *ptdev, u32 csg_id, u32 priority)
 	csg_iface->input->allow_compute = group->compute_core_mask;
 	csg_iface->input->allow_fragment = group->fragment_core_mask;
 	csg_iface->input->allow_other = group->tiler_core_mask;
-	csg_iface->input->endpoint_req = CSG_EP_REQ_COMPUTE(group->max_compute_cores) |
+	endpoint_req = CSG_EP_REQ_COMPUTE(group->max_compute_cores) |
 		       CSG_EP_REQ_FRAGMENT(group->max_fragment_cores) |
 		       CSG_EP_REQ_TILER(group->max_tiler_cores) |
 		       CSG_EP_REQ_PRIORITY(priority);
+	panthor_fw_csg_endpoint_req_set(ptdev, csg_iface, endpoint_req);
+
 	csg_iface->input->config = panthor_vm_as(group->vm);
 
 	if (group->suspend_buf)
@@ -2231,7 +2236,7 @@ tick_ctx_apply(struct panthor_scheduler *sched, struct panthor_sched_tick_ctx *c
 				continue;
 			}
 
-			panthor_fw_update_reqs(csg_iface, endpoint_req,
+			panthor_fw_csg_endpoint_req_update(ptdev, csg_iface,
 							   CSG_EP_REQ_PRIORITY(new_csg_prio),
 							   CSG_EP_REQ_PRIORITY_MASK);
 			csgs_upd_ctx_queue_reqs(ptdev, &upd_ctx, csg_id,