Re: [PATCH V3 07/11] accel/amdxdna: Add command execution

2024-10-07 Thread Lizhi Hou 



On 10/4/24 11:01, Jeffrey Hugo wrote:

On 9/11/2024 12:06 PM, Lizhi Hou wrote:

+enum amdxdna_cmd_type {
+    AMDXDNA_CMD_SUBMIT_EXEC_BUF = 0,
+    AMDXDNA_CMD_SUBMIT_DEPENDENCY,
+    AMDXDNA_CMD_SUBMIT_SIGNAL,
+};
+
+/**
+ * struct amdxdna_drm_exec_cmd - Execute command.
+ * @ext: MBZ.
+ * @ext_flags: MBZ.


I see a check for ext_flags, but not ext


I will add the check.


Thanks,

Lizhi




+ * @hwctx: Hardware context handle.
+ * @type: One of command type in enum amdxdna_cmd_type.
+ * @cmd_handles: Array of command handles or the command handle itself
+ *   in case of just one.
+ * @args: Array of arguments for all command handles.
+ * @cmd_count: Number of command handles in the cmd_handles array.
+ * @arg_count: Number of arguments in the args array.
+ * @seq: Returned sequence number for this command.
+ */
+struct amdxdna_drm_exec_cmd {
+    __u64 ext;
+    __u64 ext_flags;
+    __u32 hwctx;
+    __u32 type;
+    __u64 cmd_handles;
+    __u64 args;
+    __u32 cmd_count;
+    __u32 arg_count;
+    __u64 seq;
+};

Re: [PATCH V3 07/11] accel/amdxdna: Add command execution

2024-10-04 Thread Jeffrey Hugo 

On 9/11/2024 12:06 PM, Lizhi Hou wrote:

+enum amdxdna_cmd_type {
+   AMDXDNA_CMD_SUBMIT_EXEC_BUF = 0,
+   AMDXDNA_CMD_SUBMIT_DEPENDENCY,
+   AMDXDNA_CMD_SUBMIT_SIGNAL,
+};
+
+/**
+ * struct amdxdna_drm_exec_cmd - Execute command.
+ * @ext: MBZ.
+ * @ext_flags: MBZ.


I see a check for ext_flags, but not ext


+ * @hwctx: Hardware context handle.
+ * @type: One of command type in enum amdxdna_cmd_type.
+ * @cmd_handles: Array of command handles or the command handle itself
+ *   in case of just one.
+ * @args: Array of arguments for all command handles.
+ * @cmd_count: Number of command handles in the cmd_handles array.
+ * @arg_count: Number of arguments in the args array.
+ * @seq: Returned sequence number for this command.
+ */
+struct amdxdna_drm_exec_cmd {
+   __u64 ext;
+   __u64 ext_flags;
+   __u32 hwctx;
+   __u32 type;
+   __u64 cmd_handles;
+   __u64 args;
+   __u32 cmd_count;
+   __u32 arg_count;
+   __u64 seq;
+};

[PATCH V3 07/11] accel/amdxdna: Add command execution

2024-09-11 Thread Lizhi Hou 
Add interfaces for user application to submit command and wait for its
completion.

Co-developed-by: Min Ma 
Signed-off-by: Min Ma 
Signed-off-by: Lizhi Hou 
---
 drivers/accel/amdxdna/aie2_ctx.c  | 626 +-
 drivers/accel/amdxdna/aie2_message.c  | 343 ++
 drivers/accel/amdxdna/aie2_pci.c  |   6 +
 drivers/accel/amdxdna/aie2_pci.h  |  34 +
 drivers/accel/amdxdna/aie2_psp.c  |   2 +
 drivers/accel/amdxdna/aie2_smu.c  |   2 +
 drivers/accel/amdxdna/amdxdna_ctx.c   | 375 ++-
 drivers/accel/amdxdna/amdxdna_ctx.h   | 110 +++
 drivers/accel/amdxdna/amdxdna_gem.c   |   1 +
 .../accel/amdxdna/amdxdna_mailbox_helper.c|   5 +
 drivers/accel/amdxdna/amdxdna_pci_drv.c   |   6 +
 drivers/accel/amdxdna/amdxdna_pci_drv.h   |   5 +
 drivers/accel/amdxdna/amdxdna_sysfs.c |   5 +
 drivers/accel/amdxdna/npu1_regs.c |   1 +
 drivers/accel/amdxdna/npu2_regs.c |   1 +
 drivers/accel/amdxdna/npu4_regs.c |   1 +
 drivers/accel/amdxdna/npu5_regs.c |   1 +
 include/trace/events/amdxdna.h|  41 ++
 include/uapi/drm/amdxdna_accel.h  |  59 ++
 19 files changed, 1614 insertions(+), 10 deletions(-)

diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c
index 7904ccd36518..7395ec1367ea 100644
--- a/drivers/accel/amdxdna/aie2_ctx.c
+++ b/drivers/accel/amdxdna/aie2_ctx.c
@@ -8,14 +8,372 @@
 #include 
 #include 
 #include 
+#include 
 #include 
+#include 
 
 #include "amdxdna_ctx.h"
+#include "amdxdna_gem.h"
 #include "amdxdna_mailbox.h"
 #include "amdxdna_pci_drv.h"
+#include "aie2_msg_priv.h"
 #include "aie2_pci.h"
 #include "aie2_solver.h"
-#include "amdxdna_gem.h"
+
+bool force_cmdlist;
+module_param(force_cmdlist, bool, 0600);
+MODULE_PARM_DESC(force_cmdlist, "Force use command list (Default false)");
+
+#define HWCTX_MAX_TIMEOUT  6 /* miliseconds */
+
+static int
+aie2_hwctx_add_job(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job)
+{
+   struct amdxdna_sched_job *other;
+   int idx;
+
+   idx = get_job_idx(hwctx->priv->seq);
+   /* When pending list full, hwctx->seq points to oldest fence */
+   other = hwctx->priv->pending[idx];
+   if (other && other->fence)
+   return -EAGAIN;
+
+   if (other) {
+   dma_fence_put(other->out_fence);
+   amdxdna_job_put(other);
+   }
+
+   hwctx->priv->pending[idx] = job;
+   job->seq = hwctx->priv->seq++;
+   kref_get(&job->refcnt);
+
+   return 0;
+}
+
+static struct amdxdna_sched_job *
+aie2_hwctx_get_job(struct amdxdna_hwctx *hwctx, u64 seq)
+{
+   int idx;
+
+   /* Special sequence number for oldest fence if exist */
+   if (seq == AMDXDNA_INVALID_CMD_HANDLE) {
+   idx = get_job_idx(hwctx->priv->seq);
+   goto out;
+   }
+
+   if (seq >= hwctx->priv->seq)
+   return ERR_PTR(-EINVAL);
+
+   if (seq + HWCTX_MAX_CMDS < hwctx->priv->seq)
+   return NULL;
+
+   idx = get_job_idx(seq);
+
+out:
+   return hwctx->priv->pending[idx];
+}
+
+/* The bad_job is used in aie2_sched_job_timedout, otherwise, set it to NULL */
+static void aie2_hwctx_stop(struct amdxdna_dev *xdna, struct amdxdna_hwctx 
*hwctx,
+   struct drm_sched_job *bad_job)
+{
+   drm_sched_stop(&hwctx->priv->sched, bad_job);
+   aie2_destroy_context(xdna->dev_handle, hwctx);
+}
+
+static int aie2_hwctx_restart(struct amdxdna_dev *xdna, struct amdxdna_hwctx 
*hwctx)
+{
+   struct amdxdna_gem_obj *heap = hwctx->priv->heap;
+   int ret;
+
+   ret = aie2_create_context(xdna->dev_handle, hwctx);
+   if (ret) {
+   XDNA_ERR(xdna, "Create hwctx failed, ret %d", ret);
+   goto out;
+   }
+
+   ret = aie2_map_host_buf(xdna->dev_handle, hwctx->fw_ctx_id,
+   heap->mem.userptr, heap->mem.size);
+   if (ret) {
+   XDNA_ERR(xdna, "Map host buf failed, ret %d", ret);
+   goto out;
+   }
+
+   if (hwctx->status != HWCTX_STAT_READY) {
+   XDNA_DBG(xdna, "hwctx is not ready, status %d", hwctx->status);
+   goto out;
+   }
+
+   ret = aie2_config_cu(hwctx);
+   if (ret) {
+   XDNA_ERR(xdna, "Config cu failed, ret %d", ret);
+   goto out;
+   }
+
+out:
+   drm_sched_start(&hwctx->priv->sched, true);
+   XDNA_DBG(xdna, "%s restarted, ret %d", hwctx->name, ret);
+   return ret;
+}
+
+void aie2_stop_ctx_by_col_map(struct amdxdna_client *client, u32 col_map)
+{
+   struct amdxdna_dev *xdna = client->xdna;
+   struct amdxdna_hwctx *hwctx;
+   int next = 0;
+
+   drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock));
+   mutex_lock(&client->hwctx_lock);
+   idr_for_each_entry_continue(&client->hwctx_id