accel/amdxdna: Add query functions

Add GET_INFO ioctl to retrieve hardware information, including
AIE, clock, hardware context etc.

Co-developed-by: Min Ma <min.ma@amd.com>
Signed-off-by: Min Ma <min.ma@amd.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241118172942.2014541-11-lizhi.hou@amd.com

drivers/accel/amdxdna/aie2_message.c

@@ -308,6 +308,71 @@ int aie2_map_host_buf(struct amdxdna_dev_hdl *ndev, u32 context_id, u64 addr, u6
 	return 0;
 }
 
+int aie2_query_status(struct amdxdna_dev_hdl *ndev, char __user *buf,
+		      u32 size, u32 *cols_filled)
+{
+	DECLARE_AIE2_MSG(aie_column_info, MSG_OP_QUERY_COL_STATUS);
+	struct amdxdna_dev *xdna = ndev->xdna;
+	struct amdxdna_client *client;
+	struct amdxdna_hwctx *hwctx;
+	dma_addr_t dma_addr;
+	u32 aie_bitmap = 0;
+	u8 *buff_addr;
+	int next = 0;
+	int ret, idx;
+
+	buff_addr = dma_alloc_noncoherent(xdna->ddev.dev, size, &dma_addr,
+					  DMA_FROM_DEVICE, GFP_KERNEL);
+	if (!buff_addr)
+		return -ENOMEM;
+
+	/* Go through each hardware context and mark the AIE columns that are active */
+	list_for_each_entry(client, &xdna->client_list, node) {
+		idx = srcu_read_lock(&client->hwctx_srcu);
+		idr_for_each_entry_continue(&client->hwctx_idr, hwctx, next)
+			aie_bitmap |= amdxdna_hwctx_col_map(hwctx);
+		srcu_read_unlock(&client->hwctx_srcu, idx);
+	}
+
+	*cols_filled = 0;
+	req.dump_buff_addr = dma_addr;
+	req.dump_buff_size = size;
+	req.num_cols = hweight32(aie_bitmap);
+	req.aie_bitmap = aie_bitmap;
+
+	drm_clflush_virt_range(buff_addr, size); /* device can access */
+	ret = aie2_send_mgmt_msg_wait(ndev, &msg);
+	if (ret) {
+		XDNA_ERR(xdna, "Error during NPU query, status %d", ret);
+		goto fail;
+	}
+
+	if (resp.status != AIE2_STATUS_SUCCESS) {
+		XDNA_ERR(xdna, "Query NPU status failed, status 0x%x", resp.status);
+		ret = -EINVAL;
+		goto fail;
+	}
+	XDNA_DBG(xdna, "Query NPU status completed");
+
+	if (size < resp.size) {
+		ret = -EINVAL;
+		XDNA_ERR(xdna, "Bad buffer size. Available: %u. Needs: %u", size, resp.size);
+		goto fail;
+	}
+
+	if (copy_to_user(buf, buff_addr, resp.size)) {
+		ret = -EFAULT;
+		XDNA_ERR(xdna, "Failed to copy NPU status to user space");
+		goto fail;
+	}
+
+	*cols_filled = aie_bitmap;
+
+fail:
+	dma_free_noncoherent(xdna->ddev.dev, size, buff_addr, dma_addr, DMA_FROM_DEVICE);
+	return ret;
+}
+
 int aie2_register_asyn_event_msg(struct amdxdna_dev_hdl *ndev, dma_addr_t addr, u32 size,
 				 void *handle, int (*cb)(void*, const u32 *, size_t))
 {

drivers/accel/amdxdna/aie2_pci.c

@@ -5,6 +5,7 @@
 
 #include <drm/amdxdna_accel.h>
 #include <drm/drm_device.h>
+#include <drm/drm_drv.h>
 #include <drm/drm_gem_shmem_helper.h>
 #include <drm/drm_managed.h>
 #include <drm/drm_print.h>
@@ -525,11 +526,232 @@ static void aie2_fini(struct amdxdna_dev *xdna)
 	pci_free_irq_vectors(pdev);
 }
 
+static int aie2_get_aie_status(struct amdxdna_client *client,
+			       struct amdxdna_drm_get_info *args)
+{
+	struct amdxdna_drm_query_aie_status status;
+	struct amdxdna_dev *xdna = client->xdna;
+	struct amdxdna_dev_hdl *ndev;
+	int ret;
+
+	ndev = xdna->dev_handle;
+	if (copy_from_user(&status, u64_to_user_ptr(args->buffer), sizeof(status))) {
+		XDNA_ERR(xdna, "Failed to copy AIE request into kernel");
+		return -EFAULT;
+	}
+
+	if (ndev->metadata.cols * ndev->metadata.size < status.buffer_size) {
+		XDNA_ERR(xdna, "Invalid buffer size. Given Size: %u. Need Size: %u.",
+			 status.buffer_size, ndev->metadata.cols * ndev->metadata.size);
+		return -EINVAL;
+	}
+
+	ret = aie2_query_status(ndev, u64_to_user_ptr(status.buffer),
+				status.buffer_size, &status.cols_filled);
+	if (ret) {
+		XDNA_ERR(xdna, "Failed to get AIE status info. Ret: %d", ret);
+		return ret;
+	}
+
+	if (copy_to_user(u64_to_user_ptr(args->buffer), &status, sizeof(status))) {
+		XDNA_ERR(xdna, "Failed to copy AIE request info to user space");
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+static int aie2_get_aie_metadata(struct amdxdna_client *client,
+				 struct amdxdna_drm_get_info *args)
+{
+	struct amdxdna_drm_query_aie_metadata *meta;
+	struct amdxdna_dev *xdna = client->xdna;
+	struct amdxdna_dev_hdl *ndev;
+	int ret = 0;
+
+	ndev = xdna->dev_handle;
+	meta = kzalloc(sizeof(*meta), GFP_KERNEL);
+	if (!meta)
+		return -ENOMEM;
+
+	meta->col_size = ndev->metadata.size;
+	meta->cols = ndev->metadata.cols;
+	meta->rows = ndev->metadata.rows;
+
+	meta->version.major = ndev->metadata.version.major;
+	meta->version.minor = ndev->metadata.version.minor;
+
+	meta->core.row_count = ndev->metadata.core.row_count;
+	meta->core.row_start = ndev->metadata.core.row_start;
+	meta->core.dma_channel_count = ndev->metadata.core.dma_channel_count;
+	meta->core.lock_count = ndev->metadata.core.lock_count;
+	meta->core.event_reg_count = ndev->metadata.core.event_reg_count;
+
+	meta->mem.row_count = ndev->metadata.mem.row_count;
+	meta->mem.row_start = ndev->metadata.mem.row_start;
+	meta->mem.dma_channel_count = ndev->metadata.mem.dma_channel_count;
+	meta->mem.lock_count = ndev->metadata.mem.lock_count;
+	meta->mem.event_reg_count = ndev->metadata.mem.event_reg_count;
+
+	meta->shim.row_count = ndev->metadata.shim.row_count;
+	meta->shim.row_start = ndev->metadata.shim.row_start;
+	meta->shim.dma_channel_count = ndev->metadata.shim.dma_channel_count;
+	meta->shim.lock_count = ndev->metadata.shim.lock_count;
+	meta->shim.event_reg_count = ndev->metadata.shim.event_reg_count;
+
+	if (copy_to_user(u64_to_user_ptr(args->buffer), meta, sizeof(*meta)))
+		ret = -EFAULT;
+
+	kfree(meta);
+	return ret;
+}
+
+static int aie2_get_aie_version(struct amdxdna_client *client,
+				struct amdxdna_drm_get_info *args)
+{
+	struct amdxdna_drm_query_aie_version version;
+	struct amdxdna_dev *xdna = client->xdna;
+	struct amdxdna_dev_hdl *ndev;
+
+	ndev = xdna->dev_handle;
+	version.major = ndev->version.major;
+	version.minor = ndev->version.minor;
+
+	if (copy_to_user(u64_to_user_ptr(args->buffer), &version, sizeof(version)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int aie2_get_clock_metadata(struct amdxdna_client *client,
+				   struct amdxdna_drm_get_info *args)
+{
+	struct amdxdna_drm_query_clock_metadata *clock;
+	struct amdxdna_dev *xdna = client->xdna;
+	struct amdxdna_dev_hdl *ndev;
+	int ret = 0;
+
+	ndev = xdna->dev_handle;
+	clock = kzalloc(sizeof(*clock), GFP_KERNEL);
+	if (!clock)
+		return -ENOMEM;
+
+	memcpy(clock->mp_npu_clock.name, ndev->mp_npu_clock.name,
+	       sizeof(clock->mp_npu_clock.name));
+	clock->mp_npu_clock.freq_mhz = ndev->mp_npu_clock.freq_mhz;
+	memcpy(clock->h_clock.name, ndev->h_clock.name, sizeof(clock->h_clock.name));
+	clock->h_clock.freq_mhz = ndev->h_clock.freq_mhz;
+
+	if (copy_to_user(u64_to_user_ptr(args->buffer), clock, sizeof(*clock)))
+		ret = -EFAULT;
+
+	kfree(clock);
+	return ret;
+}
+
+static int aie2_get_hwctx_status(struct amdxdna_client *client,
+				 struct amdxdna_drm_get_info *args)
+{
+	struct amdxdna_drm_query_hwctx __user *buf;
+	struct amdxdna_dev *xdna = client->xdna;
+	struct amdxdna_drm_query_hwctx *tmp;
+	struct amdxdna_client *tmp_client;
+	struct amdxdna_hwctx *hwctx;
+	bool overflow = false;
+	u32 req_bytes = 0;
+	u32 hw_i = 0;
+	int ret = 0;
+	int next;
+	int idx;
+
+	drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock));
+
+	tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
+	buf = u64_to_user_ptr(args->buffer);
+	list_for_each_entry(tmp_client, &xdna->client_list, node) {
+		idx = srcu_read_lock(&tmp_client->hwctx_srcu);
+		next = 0;
+		idr_for_each_entry_continue(&tmp_client->hwctx_idr, hwctx, next) {
+			req_bytes += sizeof(*tmp);
+			if (args->buffer_size < req_bytes) {
+				/* Continue iterating to get the required size */
+				overflow = true;
+				continue;
+			}
+
+			memset(tmp, 0, sizeof(*tmp));
+			tmp->pid = tmp_client->pid;
+			tmp->context_id = hwctx->id;
+			tmp->start_col = hwctx->start_col;
+			tmp->num_col = hwctx->num_col;
+			tmp->command_submissions = hwctx->priv->seq;
+			tmp->command_completions = hwctx->priv->completed;
+
+			if (copy_to_user(&buf[hw_i], tmp, sizeof(*tmp))) {
+				ret = -EFAULT;
+				srcu_read_unlock(&tmp_client->hwctx_srcu, idx);
+				goto out;
+			}
+			hw_i++;
+		}
+		srcu_read_unlock(&tmp_client->hwctx_srcu, idx);
+	}
+
+	if (overflow) {
+		XDNA_ERR(xdna, "Invalid buffer size. Given: %u Need: %u.",
+			 args->buffer_size, req_bytes);
+		ret = -EINVAL;
+	}
+
+out:
+	kfree(tmp);
+	args->buffer_size = req_bytes;
+	return ret;
+}
+
+static int aie2_get_info(struct amdxdna_client *client, struct amdxdna_drm_get_info *args)
+{
+	struct amdxdna_dev *xdna = client->xdna;
+	int ret, idx;
+
+	if (!drm_dev_enter(&xdna->ddev, &idx))
+		return -ENODEV;
+
+	switch (args->param) {
+	case DRM_AMDXDNA_QUERY_AIE_STATUS:
+		ret = aie2_get_aie_status(client, args);
+		break;
+	case DRM_AMDXDNA_QUERY_AIE_METADATA:
+		ret = aie2_get_aie_metadata(client, args);
+		break;
+	case DRM_AMDXDNA_QUERY_AIE_VERSION:
+		ret = aie2_get_aie_version(client, args);
+		break;
+	case DRM_AMDXDNA_QUERY_CLOCK_METADATA:
+		ret = aie2_get_clock_metadata(client, args);
+		break;
+	case DRM_AMDXDNA_QUERY_HW_CONTEXTS:
+		ret = aie2_get_hwctx_status(client, args);
+		break;
+	default:
+		XDNA_ERR(xdna, "Not supported request parameter %u", args->param);
+		ret = -EOPNOTSUPP;
+	}
+	XDNA_DBG(xdna, "Got param %d", args->param);
+
+	drm_dev_exit(idx);
+	return ret;
+}
+
 const struct amdxdna_dev_ops aie2_ops = {
 	.init           = aie2_init,
 	.fini           = aie2_fini,
 	.resume         = aie2_hw_start,
 	.suspend        = aie2_hw_stop,
+	.get_aie_info   = aie2_get_info,
 	.hwctx_init     = aie2_hwctx_init,
 	.hwctx_fini     = aie2_hwctx_fini,
 	.hwctx_config   = aie2_hwctx_config,

drivers/accel/amdxdna/aie2_pci.h

@@ -231,6 +231,7 @@ int aie2_query_firmware_version(struct amdxdna_dev_hdl *ndev,
 int aie2_create_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwctx);
 int aie2_destroy_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwctx);
 int aie2_map_host_buf(struct amdxdna_dev_hdl *ndev, u32 context_id, u64 addr, u64 size);
+int aie2_query_status(struct amdxdna_dev_hdl *ndev, char *buf, u32 size, u32 *cols_filled);
 int aie2_register_asyn_event_msg(struct amdxdna_dev_hdl *ndev, dma_addr_t addr, u32 size,
 				 void *handle, int (*cb)(void*, const u32 *, size_t));
 int aie2_config_cu(struct amdxdna_hwctx *hwctx);

drivers/accel/amdxdna/amdxdna_pci_drv.c

@@ -143,6 +143,23 @@ static int amdxdna_flush(struct file *f, fl_owner_t id)
 	return 0;
 }
 
+static int amdxdna_drm_get_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
+{
+	struct amdxdna_client *client = filp->driver_priv;
+	struct amdxdna_dev *xdna = to_xdna_dev(dev);
+	struct amdxdna_drm_get_info *args = data;
+	int ret;
+
+	if (!xdna->dev_info->ops->get_aie_info)
+		return -EOPNOTSUPP;
+
+	XDNA_DBG(xdna, "Request parameter %u", args->param);
+	mutex_lock(&xdna->dev_lock);
+	ret = xdna->dev_info->ops->get_aie_info(client, args);
+	mutex_unlock(&xdna->dev_lock);
+	return ret;
+}
+
 static const struct drm_ioctl_desc amdxdna_drm_ioctls[] = {
 	/* Context */
 	DRM_IOCTL_DEF_DRV(AMDXDNA_CREATE_HWCTX, amdxdna_drm_create_hwctx_ioctl, 0),
@@ -154,6 +171,8 @@ static const struct drm_ioctl_desc amdxdna_drm_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(AMDXDNA_SYNC_BO, amdxdna_drm_sync_bo_ioctl, 0),
 	/* Execution */
 	DRM_IOCTL_DEF_DRV(AMDXDNA_EXEC_CMD, amdxdna_drm_submit_cmd_ioctl, 0),
+	/* AIE hardware */
+	DRM_IOCTL_DEF_DRV(AMDXDNA_GET_INFO, amdxdna_drm_get_info_ioctl, 0),
 };
 
 static const struct file_operations amdxdna_fops = {

drivers/accel/amdxdna/amdxdna_pci_drv.h

@@ -17,7 +17,9 @@
 
 extern const struct drm_driver amdxdna_drm_drv;
 
+struct amdxdna_client;
 struct amdxdna_dev;
+struct amdxdna_drm_get_info;
 struct amdxdna_gem_obj;
 struct amdxdna_hwctx;
 struct amdxdna_sched_job;
@@ -37,6 +39,7 @@ struct amdxdna_dev_ops {
 	void (*hwctx_suspend)(struct amdxdna_hwctx *hwctx);
 	void (*hwctx_resume)(struct amdxdna_hwctx *hwctx);
 	int (*cmd_submit)(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job, u64 *seq);
+	int (*get_aie_info)(struct amdxdna_client *client, struct amdxdna_drm_get_info *args);
 };
 
 /*

include/uapi/drm/amdxdna_accel.h

@@ -32,6 +32,7 @@ enum amdxdna_drm_ioctl_id {
 	DRM_AMDXDNA_GET_BO_INFO,
 	DRM_AMDXDNA_SYNC_BO,
 	DRM_AMDXDNA_EXEC_CMD,
+	DRM_AMDXDNA_GET_INFO,
 };
 
 /**
@@ -235,6 +236,167 @@ struct amdxdna_drm_exec_cmd {
 	__u64 seq;
 };
 
+/**
+ * struct amdxdna_drm_query_aie_status - Query the status of the AIE hardware
+ * @buffer: The user space buffer that will return the AIE status.
+ * @buffer_size: The size of the user space buffer.
+ * @cols_filled: A bitmap of AIE columns whose data has been returned in the buffer.
+ */
+struct amdxdna_drm_query_aie_status {
+	__u64 buffer; /* out */
+	__u32 buffer_size; /* in */
+	__u32 cols_filled; /* out */
+};
+
+/**
+ * struct amdxdna_drm_query_aie_version - Query the version of the AIE hardware
+ * @major: The major version number.
+ * @minor: The minor version number.
+ */
+struct amdxdna_drm_query_aie_version {
+	__u32 major; /* out */
+	__u32 minor; /* out */
+};
+
+/**
+ * struct amdxdna_drm_query_aie_tile_metadata - Query the metadata of AIE tile (core, mem, shim)
+ * @row_count: The number of rows.
+ * @row_start: The starting row number.
+ * @dma_channel_count: The number of dma channels.
+ * @lock_count: The number of locks.
+ * @event_reg_count: The number of events.
+ * @pad: Structure padding.
+ */
+struct amdxdna_drm_query_aie_tile_metadata {
+	__u16 row_count;
+	__u16 row_start;
+	__u16 dma_channel_count;
+	__u16 lock_count;
+	__u16 event_reg_count;
+	__u16 pad[3];
+};
+
+/**
+ * struct amdxdna_drm_query_aie_metadata - Query the metadata of the AIE hardware
+ * @col_size: The size of a column in bytes.
+ * @cols: The total number of columns.
+ * @rows: The total number of rows.
+ * @version: The version of the AIE hardware.
+ * @core: The metadata for all core tiles.
+ * @mem: The metadata for all mem tiles.
+ * @shim: The metadata for all shim tiles.
+ */
+struct amdxdna_drm_query_aie_metadata {
+	__u32 col_size;
+	__u16 cols;
+	__u16 rows;
+	struct amdxdna_drm_query_aie_version version;
+	struct amdxdna_drm_query_aie_tile_metadata core;
+	struct amdxdna_drm_query_aie_tile_metadata mem;
+	struct amdxdna_drm_query_aie_tile_metadata shim;
+};
+
+/**
+ * struct amdxdna_drm_query_clock - Metadata for a clock
+ * @name: The clock name.
+ * @freq_mhz: The clock frequency.
+ * @pad: Structure padding.
+ */
+struct amdxdna_drm_query_clock {
+	__u8 name[16];
+	__u32 freq_mhz;
+	__u32 pad;
+};
+
+/**
+ * struct amdxdna_drm_query_clock_metadata - Query metadata for clocks
+ * @mp_npu_clock: The metadata for MP-NPU clock.
+ * @h_clock: The metadata for H clock.
+ */
+struct amdxdna_drm_query_clock_metadata {
+	struct amdxdna_drm_query_clock mp_npu_clock;
+	struct amdxdna_drm_query_clock h_clock;
+};
+
+enum amdxdna_sensor_type {
+	AMDXDNA_SENSOR_TYPE_POWER
+};
+
+/**
+ * struct amdxdna_drm_query_sensor - The data for single sensor.
+ * @label: The name for a sensor.
+ * @input: The current value of the sensor.
+ * @max: The maximum value possible for the sensor.
+ * @average: The average value of the sensor.
+ * @highest: The highest recorded sensor value for this driver load for the sensor.
+ * @status: The sensor status.
+ * @units: The sensor units.
+ * @unitm: Translates value member variables into the correct unit via (pow(10, unitm) * value).
+ * @type: The sensor type from enum amdxdna_sensor_type.
+ * @pad: Structure padding.
+ */
+struct amdxdna_drm_query_sensor {
+	__u8  label[64];
+	__u32 input;
+	__u32 max;
+	__u32 average;
+	__u32 highest;
+	__u8  status[64];
+	__u8  units[16];
+	__s8  unitm;
+	__u8  type;
+	__u8  pad[6];
+};
+
+/**
+ * struct amdxdna_drm_query_hwctx - The data for single context.
+ * @context_id: The ID for this context.
+ * @start_col: The starting column for the partition assigned to this context.
+ * @num_col: The number of columns in the partition assigned to this context.
+ * @pad: Structure padding.
+ * @pid: The Process ID of the process that created this context.
+ * @command_submissions: The number of commands submitted to this context.
+ * @command_completions: The number of commands completed by this context.
+ * @migrations: The number of times this context has been moved to a different partition.
+ * @preemptions: The number of times this context has been preempted by another context in the
+ *               same partition.
+ * @errors: The errors for this context.
+ */
+struct amdxdna_drm_query_hwctx {
+	__u32 context_id;
+	__u32 start_col;
+	__u32 num_col;
+	__u32 pad;
+	__s64 pid;
+	__u64 command_submissions;
+	__u64 command_completions;
+	__u64 migrations;
+	__u64 preemptions;
+	__u64 errors;
+};
+
+enum amdxdna_drm_get_param {
+	DRM_AMDXDNA_QUERY_AIE_STATUS,
+	DRM_AMDXDNA_QUERY_AIE_METADATA,
+	DRM_AMDXDNA_QUERY_AIE_VERSION,
+	DRM_AMDXDNA_QUERY_CLOCK_METADATA,
+	DRM_AMDXDNA_QUERY_SENSORS,
+	DRM_AMDXDNA_QUERY_HW_CONTEXTS,
+	DRM_AMDXDNA_NUM_GET_PARAM,
+};
+
+/**
+ * struct amdxdna_drm_get_info - Get some information from the AIE hardware.
+ * @param: Value in enum amdxdna_drm_get_param. Specifies the structure passed in the buffer.
+ * @buffer_size: Size of the input buffer. Size needed/written by the kernel.
+ * @buffer: A structure specified by the param struct member.
+ */
+struct amdxdna_drm_get_info {
+	__u32 param; /* in */
+	__u32 buffer_size; /* in/out */
+	__u64 buffer; /* in/out */
+};
+
 #define DRM_IOCTL_AMDXDNA_CREATE_HWCTX \
 	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_CREATE_HWCTX, \
 		 struct amdxdna_drm_create_hwctx)
@@ -263,6 +425,10 @@ struct amdxdna_drm_exec_cmd {
 	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_EXEC_CMD, \
 		 struct amdxdna_drm_exec_cmd)
 
+#define DRM_IOCTL_AMDXDNA_GET_INFO \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_GET_INFO, \
+		 struct amdxdna_drm_get_info)
+
 #if defined(__cplusplus)
 } /* extern c end */
 #endif