drm/xe/vf: Don't try to trigger a full GT reset if VF

VFs don't have access to the GDRST(0x941c) register that driver
uses to reset a GT. Attempt to trigger a reset using debugfs:

 $ cat /sys/kernel/debug/dri/0000:00:02.1/gt0/force_reset

or due to a hang condition detected by the driver leads to:

 [ ] xe 0000:00:02.1: [drm] GT0: trying reset from force_reset [xe]
 [ ] xe 0000:00:02.1: [drm] GT0: reset queued
 [ ] xe 0000:00:02.1: [drm] GT0: reset started
 [ ] ------------[ cut here ]------------
 [ ] xe 0000:00:02.1: [drm] GT0: VF is trying to write 0x1 to an inaccessible register 0x941c+0x0
 [ ] WARNING: CPU: 3 PID: 3069 at drivers/gpu/drm/xe/xe_gt_sriov_vf.c:996 xe_gt_sriov_vf_write32+0xc6/0x580 [xe]
 [ ] RIP: 0010:xe_gt_sriov_vf_write32+0xc6/0x580 [xe]
 [ ] Call Trace:
 [ ]  <TASK>
 [ ]  ? show_regs+0x6c/0x80
 [ ]  ? __warn+0x93/0x1c0
 [ ]  ? xe_gt_sriov_vf_write32+0xc6/0x580 [xe]
 [ ]  ? report_bug+0x182/0x1b0
 [ ]  ? handle_bug+0x6e/0xb0
 [ ]  ? exc_invalid_op+0x18/0x80
 [ ]  ? asm_exc_invalid_op+0x1b/0x20
 [ ]  ? xe_gt_sriov_vf_write32+0xc6/0x580 [xe]
 [ ]  ? xe_gt_sriov_vf_write32+0xc6/0x580 [xe]
 [ ]  ? xe_gt_tlb_invalidation_reset+0xef/0x110 [xe]
 [ ]  ? __mutex_unlock_slowpath+0x41/0x2e0
 [ ]  xe_mmio_write32+0x64/0x150 [xe]
 [ ]  do_gt_reset+0x2f/0xa0 [xe]
 [ ]  gt_reset_worker+0x14e/0x1e0 [xe]
 [ ]  process_one_work+0x21c/0x740
 [ ]  worker_thread+0x1db/0x3c0

Fix that by sending H2G VF_RESET(0x5507) action instead.

Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/4078
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250131182502.852-1-michal.wajdeczko@intel.com

diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 01a4a852b8f43adb6cf15376b64ce54db977e15b..9fb8f1e678dc81d949405d0f97c696bcf1d2e604 100644 (file)
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -32,6 +32,7 @@
 #include "xe_gt_pagefault.h"
 #include "xe_gt_printk.h"
 #include "xe_gt_sriov_pf.h"
+#include "xe_gt_sriov_vf.h"
 #include "xe_gt_sysfs.h"
 #include "xe_gt_tlb_invalidation.h"
 #include "xe_gt_topology.h"
@@ -679,6 +680,9 @@ static int do_gt_reset(struct xe_gt *gt)
 {
        int err;
 
+       if (IS_SRIOV_VF(gt_to_xe(gt)))
+               return xe_gt_sriov_vf_reset(gt);
+
        xe_gsc_wa_14015076503(gt, true);
 
        xe_mmio_write32(&gt->mmio, GDRST, GRDOM_FULL);

diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
index 6671030439fd73b434f4a88151be9c4fe0becb9e..4831549da319aa8c2b929ef7dfa5eaf576433458 100644 (file)
--- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
@@ -58,6 +58,22 @@ static int vf_reset_guc_state(struct xe_gt *gt)
        return err;
 }
 
+/**
+ * xe_gt_sriov_vf_reset - Reset GuC VF internal state.
+ * @gt: the &xe_gt
+ *
+ * It requires functional `GuC MMIO based communication`_.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int xe_gt_sriov_vf_reset(struct xe_gt *gt)
+{
+       if (!xe_device_uc_enabled(gt_to_xe(gt)))
+               return -ENODEV;
+
+       return vf_reset_guc_state(gt);
+}
+
 static int guc_action_match_version(struct xe_guc *guc,
                                    u32 wanted_branch, u32 wanted_major, u32 wanted_minor,
                                    u32 *branch, u32 *major, u32 *minor, u32 *patch)

diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.h b/drivers/gpu/drm/xe/xe_gt_sriov_vf.h
index 912d2081426163ab3caec95a455027180078fa77..ba6c5d74e326f4048d28eb04c3f6b91818b96aba 100644 (file)
--- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.h
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.h
@@ -12,6 +12,7 @@ struct drm_printer;
 struct xe_gt;
 struct xe_reg;
 
+int xe_gt_sriov_vf_reset(struct xe_gt *gt);
 int xe_gt_sriov_vf_bootstrap(struct xe_gt *gt);
 int xe_gt_sriov_vf_query_config(struct xe_gt *gt);
 int xe_gt_sriov_vf_connect(struct xe_gt *gt);