drm/xe/pf: Synchronize VF FLR between all GTs

The PF part of the VF FLR processing shall be done after all GuCs
confirm that they finished their part VF FLR processing, otherwise
PF may start clearing VF's GGTT that other GuC may still accessing.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Link: https://lore.kernel.org/r/20250930233525.201263-7-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 491918d6b93b119e8ac0fb7d32b41130cae07740..2e6bd3d1fe1da671519fc123329778a06ac6a19a 100644 (file)
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.c
@@ -18,6 +18,7 @@
 #include "xe_gt_sriov_printk.h"
 #include "xe_guc_ct.h"
 #include "xe_sriov.h"
+#include "xe_sriov_pf_control.h"
 #include "xe_sriov_pf_service.h"
 #include "xe_tile.h"
 
@@ -170,6 +171,7 @@ static const char *control_bit_to_string(enum xe_gt_sriov_control_bits bit)
        CASE2STR(FLR_SEND_START);
        CASE2STR(FLR_WAIT_GUC);
        CASE2STR(FLR_GUC_DONE);
+       CASE2STR(FLR_SYNC);
        CASE2STR(FLR_RESET_CONFIG);
        CASE2STR(FLR_RESET_DATA);
        CASE2STR(FLR_RESET_MMIO);
@@ -940,6 +942,10 @@ int xe_gt_sriov_pf_control_stop_vf(struct xe_gt *gt, unsigned int vfid)
  *     :        v                                      :        |           |
  *     :       FLR_GUC_DONE                            :        |           |
  *     :        |                                      :        |           |
+ *     :        | o--<--sync                           :        |           |
+ *     :        |/        /                            :        |           |
+ *     :       FLR_SYNC--o                             :        |           |
+ *     :        |                                      :        |           |
  *     :       FLR_RESET_CONFIG---failed--->-----------o--------+-----------o
  *     :        |                                      :        |           |
  *     :       FLR_RESET_DATA                          :        |           |
@@ -1147,12 +1153,38 @@ static bool pf_exit_vf_flr_send_start(struct xe_gt *gt, unsigned int vfid)
        return true;
 }
 
+static bool pf_exit_vf_flr_sync(struct xe_gt *gt, unsigned int vfid)
+{
+       if (!pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_FLR_SYNC))
+               return false;
+
+       pf_enter_vf_flr_reset_config(gt, vfid);
+       return true;
+}
+
+static void pf_enter_vf_flr_sync(struct xe_gt *gt, unsigned int vfid)
+{
+       int ret;
+
+       if (!pf_enter_vf_state(gt, vfid, XE_GT_SRIOV_STATE_FLR_SYNC))
+               pf_enter_vf_state_machine_bug(gt, vfid);
+
+       ret = xe_sriov_pf_control_sync_flr(gt_to_xe(gt), vfid);
+       if (ret < 0) {
+               xe_gt_sriov_dbg_verbose(gt, "FLR checkpoint %pe\n", ERR_PTR(ret));
+               pf_expect_vf_state(gt, vfid, XE_GT_SRIOV_STATE_FLR_SYNC);
+       } else {
+               xe_gt_sriov_dbg_verbose(gt, "FLR checkpoint pass\n");
+               pf_expect_vf_not_state(gt, vfid, XE_GT_SRIOV_STATE_FLR_SYNC);
+       }
+}
+
 static bool pf_exit_vf_flr_guc_done(struct xe_gt *gt, unsigned int vfid)
 {
        if (!pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_FLR_GUC_DONE))
                return false;
 
-       pf_enter_vf_flr_reset_config(gt, vfid);
+       pf_enter_vf_flr_sync(gt, vfid);
        return true;
 }
 
@@ -1178,6 +1210,28 @@ int xe_gt_sriov_pf_control_trigger_flr(struct xe_gt *gt, unsigned int vfid)
        return 0;
 }
 
+/**
+ * xe_gt_sriov_pf_control_sync_flr() - Synchronize on the VF FLR checkpoint.
+ * @gt: the &xe_gt
+ * @vfid: the VF identifier
+ * @sync: if true it will allow to exit the checkpoint
+ *
+ * Return: non-zero if FLR checkpoint has been reached, zero if the is no FLR
+ *         in progress, or a negative error code on the FLR busy or failed.
+ */
+int xe_gt_sriov_pf_control_sync_flr(struct xe_gt *gt, unsigned int vfid, bool sync)
+{
+       if (sync && pf_exit_vf_flr_sync(gt, vfid))
+               return 1;
+       if (pf_check_vf_state(gt, vfid, XE_GT_SRIOV_STATE_FLR_SYNC))
+               return 1;
+       if (pf_check_vf_state(gt, vfid, XE_GT_SRIOV_STATE_FLR_WIP))
+               return -EBUSY;
+       if (pf_check_vf_state(gt, vfid, XE_GT_SRIOV_STATE_FLR_FAILED))
+               return -EIO;
+       return 0;
+}
+
 /**
  * xe_gt_sriov_pf_control_wait_flr() - Wait for a VF FLR to complete.
  * @gt: the &xe_gt

diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.h b/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.h
index fd256866f6280c076161a5bc3b0c1d8280b88f20..8a72ef3778d47b338b87b93f8d150a953f573a5e 100644 (file)
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.h
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.h
@@ -18,6 +18,7 @@ int xe_gt_sriov_pf_control_pause_vf(struct xe_gt *gt, unsigned int vfid);
 int xe_gt_sriov_pf_control_resume_vf(struct xe_gt *gt, unsigned int vfid);
 int xe_gt_sriov_pf_control_stop_vf(struct xe_gt *gt, unsigned int vfid);
 int xe_gt_sriov_pf_control_trigger_flr(struct xe_gt *gt, unsigned int vfid);
+int xe_gt_sriov_pf_control_sync_flr(struct xe_gt *gt, unsigned int vfid, bool sync);
 int xe_gt_sriov_pf_control_wait_flr(struct xe_gt *gt, unsigned int vfid);
 
 #ifdef CONFIG_PCI_IOV

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 f02f941b4ad21a57a2b7f94bfc89480078a31b0d..c80b7e77f1ad277160e5536c223b7d9695aba0e4 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
@@ -18,6 +18,7 @@
  * @XE_GT_SRIOV_STATE_FLR_SEND_START: indicates that the PF wants to send a FLR START command.
  * @XE_GT_SRIOV_STATE_FLR_WAIT_GUC: indicates that the PF awaits for a response from the GuC.
  * @XE_GT_SRIOV_STATE_FLR_GUC_DONE: indicates that the PF has received a response from the GuC.
+ * @XE_GT_SRIOV_STATE_FLR_SYNC: indicates that the PF awaits to synchronize with other GuCs.
  * @XE_GT_SRIOV_STATE_FLR_RESET_CONFIG: indicates that the PF needs to clear VF's resources.
  * @XE_GT_SRIOV_STATE_FLR_RESET_DATA: indicates that the PF needs to clear VF's data.
  * @XE_GT_SRIOV_STATE_FLR_RESET_MMIO: indicates that the PF needs to reset VF's registers.
@@ -47,6 +48,7 @@ enum xe_gt_sriov_control_bits {
        XE_GT_SRIOV_STATE_FLR_SEND_START,
        XE_GT_SRIOV_STATE_FLR_WAIT_GUC,
        XE_GT_SRIOV_STATE_FLR_GUC_DONE,
+       XE_GT_SRIOV_STATE_FLR_SYNC,
        XE_GT_SRIOV_STATE_FLR_RESET_CONFIG,
        XE_GT_SRIOV_STATE_FLR_RESET_DATA,
        XE_GT_SRIOV_STATE_FLR_RESET_MMIO,

diff --git a/drivers/gpu/drm/xe/xe_sriov_pf_control.c b/drivers/gpu/drm/xe/xe_sriov_pf_control.c
index e1c54a8feb07bd66f20add30583dc4c206b56f58..416d00a03fbb7538e3a8a62f8cbbada45b6bbd51 100644 (file)
--- a/drivers/gpu/drm/xe/xe_sriov_pf_control.c
+++ b/drivers/gpu/drm/xe/xe_sriov_pf_control.c
@@ -120,3 +120,32 @@ int xe_sriov_pf_control_reset_vf(struct xe_device *xe, unsigned int vfid)
 
        return result;
 }
+
+/**
+ * xe_sriov_pf_control_sync_flr() - Synchronize a VF FLR between all GTs.
+ * @xe: the &xe_device
+ * @vfid: the VF identifier
+ *
+ * This function is for PF only.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int xe_sriov_pf_control_sync_flr(struct xe_device *xe, unsigned int vfid)
+{
+       struct xe_gt *gt;
+       unsigned int id;
+       int ret;
+
+       for_each_gt(gt, xe, id) {
+               ret = xe_gt_sriov_pf_control_sync_flr(gt, vfid, false);
+               if (ret < 0)
+                       return ret;
+       }
+       for_each_gt(gt, xe, id) {
+               ret = xe_gt_sriov_pf_control_sync_flr(gt, vfid, true);
+               if (ret < 0)
+                       return ret;
+       }
+
+       return 0;
+}

diff --git a/drivers/gpu/drm/xe/xe_sriov_pf_control.h b/drivers/gpu/drm/xe/xe_sriov_pf_control.h
index 9bf059f746d4501aac2c38974118f154c107ef43..2d52d0ac1b28f5640e4675b202d6a7b93265b6d2 100644 (file)
--- a/drivers/gpu/drm/xe/xe_sriov_pf_control.h
+++ b/drivers/gpu/drm/xe/xe_sriov_pf_control.h
@@ -12,5 +12,6 @@ int xe_sriov_pf_control_pause_vf(struct xe_device *xe, unsigned int vfid);
 int xe_sriov_pf_control_resume_vf(struct xe_device *xe, unsigned int vfid);
 int xe_sriov_pf_control_stop_vf(struct xe_device *xe, unsigned int vfid);
 int xe_sriov_pf_control_reset_vf(struct xe_device *xe, unsigned int vfid);
+int xe_sriov_pf_control_sync_flr(struct xe_device *xe, unsigned int vfid);
 
 #endif