drm/xe/pf: Save VF GuC state when pausing VF

Since usually pausing the VF is done as a first step to migrate
that VF, immediately save VF GuC state as a final step of the VF
pausing to have that data ready to export when needed.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Tomasz Lis <tomasz.lis@intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240912203817.1880-5-michal.wajdeczko@intel.com

diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.c
index b4fd5a81aff1f91c01c422d329989a806d4b6427..1f50aec3a059ec0c8f0c65d8fdff7696c2a319de 100644 (file)
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.c
@@ -13,6 +13,7 @@
 #include "xe_gt_sriov_pf_config.h"
 #include "xe_gt_sriov_pf_control.h"
 #include "xe_gt_sriov_pf_helpers.h"
+#include "xe_gt_sriov_pf_migration.h"
 #include "xe_gt_sriov_pf_monitor.h"
 #include "xe_gt_sriov_pf_service.h"
 #include "xe_gt_sriov_printk.h"
@@ -177,6 +178,7 @@ static const char *control_bit_to_string(enum xe_gt_sriov_control_bits bit)
        CASE2STR(PAUSE_SEND_PAUSE);
        CASE2STR(PAUSE_WAIT_GUC);
        CASE2STR(PAUSE_GUC_DONE);
+       CASE2STR(PAUSE_SAVE_GUC);
        CASE2STR(PAUSE_FAILED);
        CASE2STR(PAUSED);
        CASE2STR(RESUME_WIP);
@@ -416,6 +418,10 @@ static void pf_enter_vf_ready(struct xe_gt *gt, unsigned int vfid)
  *     :        |                                      :             /
  *     :        v                                      :            /
  *     :       PAUSE_GUC_DONE                          o-----restart
+ *     :        |                                      :
+ *     :        |   o---<--busy                        :
+ *     :        v  /         /                         :
+ *     :       PAUSE_SAVE_GUC                          :
  *     :      /                                        :
  *     :     /                                         :
  *     :....o..............o...............o...........:
@@ -435,6 +441,7 @@ static void pf_exit_vf_pause_wip(struct xe_gt *gt, unsigned int vfid)
                pf_escape_vf_state(gt, vfid, XE_GT_SRIOV_STATE_PAUSE_SEND_PAUSE);
                pf_escape_vf_state(gt, vfid, XE_GT_SRIOV_STATE_PAUSE_WAIT_GUC);
                pf_escape_vf_state(gt, vfid, XE_GT_SRIOV_STATE_PAUSE_GUC_DONE);
+               pf_escape_vf_state(gt, vfid, XE_GT_SRIOV_STATE_PAUSE_SAVE_GUC);
        }
 }
 
@@ -465,12 +472,41 @@ static void pf_enter_vf_pause_rejected(struct xe_gt *gt, unsigned int vfid)
        pf_enter_vf_pause_failed(gt, vfid);
 }
 
+static void pf_enter_vf_pause_save_guc(struct xe_gt *gt, unsigned int vfid)
+{
+       if (!pf_enter_vf_state(gt, vfid, XE_GT_SRIOV_STATE_PAUSE_SAVE_GUC))
+               pf_enter_vf_state_machine_bug(gt, vfid);
+}
+
+static bool pf_exit_vf_pause_save_guc(struct xe_gt *gt, unsigned int vfid)
+{
+       int err;
+
+       if (!pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_PAUSE_SAVE_GUC))
+               return false;
+
+       err = xe_gt_sriov_pf_migration_save_guc_state(gt, vfid);
+       if (err) {
+               /* retry if busy */
+               if (err == -EBUSY) {
+                       pf_enter_vf_pause_save_guc(gt, vfid);
+                       return true;
+               }
+               /* give up on error */
+               if (err == -EIO)
+                       pf_enter_vf_mismatch(gt, vfid);
+       }
+
+       pf_enter_vf_pause_completed(gt, vfid);
+       return true;
+}
+
 static bool pf_exit_vf_pause_guc_done(struct xe_gt *gt, unsigned int vfid)
 {
        if (!pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_PAUSE_GUC_DONE))
                return false;
 
-       pf_enter_vf_pause_completed(gt, vfid);
+       pf_enter_vf_pause_save_guc(gt, vfid);
        return true;
 }
 
@@ -1339,6 +1375,9 @@ static bool pf_process_vf_state_machine(struct xe_gt *gt, unsigned int vfid)
        if (pf_exit_vf_pause_guc_done(gt, vfid))
                return true;
 
+       if (pf_exit_vf_pause_save_guc(gt, vfid))
+               return true;
+
        if (pf_exit_vf_resume_send_resume(gt, vfid))
                return true;
 

diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_control_types.h b/drivers/gpu/drm/xe/xe_gt_sriov_pf_control_types.h
index 11830aafea4505f4334c20d361bfbc762338178d..f02f941b4ad21a57a2b7f94bfc89480078a31b0d 100644 (file)
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_control_types.h
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_control_types.h
@@ -27,6 +27,7 @@
  * @XE_GT_SRIOV_STATE_PAUSE_SEND_PAUSE: indicates that the PF is about to send a PAUSE command.
  * @XE_GT_SRIOV_STATE_PAUSE_WAIT_GUC: indicates that the PF awaits for a response from the GuC.
  * @XE_GT_SRIOV_STATE_PAUSE_GUC_DONE: indicates that the PF has received a response from the GuC.
+ * @XE_GT_SRIOV_STATE_PAUSE_SAVE_GUC: indicates that the PF needs to save the VF GuC state.
  * @XE_GT_SRIOV_STATE_PAUSE_FAILED: indicates that a VF pause operation has failed.
  * @XE_GT_SRIOV_STATE_PAUSED: indicates that the VF is paused.
  * @XE_GT_SRIOV_STATE_RESUME_WIP: indicates the a VF resume operation is in progress.
@@ -56,6 +57,7 @@ enum xe_gt_sriov_control_bits {
        XE_GT_SRIOV_STATE_PAUSE_SEND_PAUSE,
        XE_GT_SRIOV_STATE_PAUSE_WAIT_GUC,
        XE_GT_SRIOV_STATE_PAUSE_GUC_DONE,
+       XE_GT_SRIOV_STATE_PAUSE_SAVE_GUC,
        XE_GT_SRIOV_STATE_PAUSE_FAILED,
        XE_GT_SRIOV_STATE_PAUSED,