drm/xe/pf: Make the late-initialization really late

While the late PF per-GT initialization is done quite late in the
single GT initialization flow, in case of multi-GT platforms, it
may still be done before other GT early initialization. That leads
to some issues during unwind, when there are cross-GT dependencies,
like resource cleanup that is shared by both GTs, but the other GT
may already be sanitized or disabled.

The following errors could be observed when trying to unload the PF
driver with some LMEM/VRAM already provisioned for few VFs:

 [ ] xe 0000:03:00.0: DEVRES REL ffff88814708f240 fini_config (16 bytes)
 [ ] xe 0000:03:00.0: [drm:lmtt_write_pte [xe]] PF: LMTT: WRITE level=2 index=1 pte=0x0
 [ ] xe 0000:03:00.0: [drm:lmtt_invalidate_hw [xe]] PF: LMTT: num_fences=2 err=-19
 [ ] xe 0000:03:00.0: [drm:lmtt_pt_free [xe]] PF: LMTT: level=0 addr=53a470000
 [ ] xe 0000:03:00.0: [drm:lmtt_pt_free [xe]] PF: LMTT: level=1 addr=53a4b0000
 [ ] xe 0000:03:00.0: [drm:lmtt_invalidate_hw [xe]] PF: LMTT: num_fences=2 err=-19
 [ ] xe 0000:03:00.0: [drm] PF: LMTT0 invalidation failed (-ENODEV)
 [ ] xe 0000:03:00.0: [drm:lmtt_write_pte [xe]] PF: LMTT: WRITE level=2 index=2 pte=0x0
 [ ] xe 0000:03:00.0: [drm:lmtt_invalidate_hw [xe]] PF: LMTT: num_fences=2 err=-19
 [ ] xe 0000:03:00.0: [drm:lmtt_pt_free [xe]] PF: LMTT: level=0 addr=539b70000
 [ ] xe 0000:03:00.0: [drm:lmtt_pt_free [xe]] PF: LMTT: level=1 addr=539bf0000
 [ ] xe 0000:03:00.0: [drm:lmtt_invalidate_hw [xe]] PF: LMTT: num_fences=2 err=-19
 [ ] xe 0000:03:00.0: [drm] PF: LMTT0 invalidation failed (-ENODEV)

Move all PF per-GT late initialization to the already defined late
SR-IOV initialization function to allow proper order of the cleanup
actions.

While around, format all PF function stubs as one-liners, like many
other stubs are defined in the Xe driver.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Reviewed-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Link: https://lore.kernel.org/r/20251004162008.1782-1-michal.wajdeczko@intel.com

diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index b77572a195486d5e0b527b830f120008ef0e24e9..8fc3a6929d6cb2d70efb0be8454cf21299a2d0f4 100644 (file)
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -573,10 +573,8 @@ static int gt_init_with_all_forcewake(struct xe_gt *gt)
        if (IS_SRIOV_PF(gt_to_xe(gt)) && xe_gt_is_main_type(gt))
                xe_lmtt_init_hw(&gt_to_tile(gt)->sriov.pf.lmtt);
 
-       if (IS_SRIOV_PF(gt_to_xe(gt))) {
-               xe_gt_sriov_pf_init(gt);
+       if (IS_SRIOV_PF(gt_to_xe(gt)))
                xe_gt_sriov_pf_init_hw(gt);
-       }
 
        xe_force_wake_put(gt_to_fw(gt), fw_ref);
 

diff --git a/drivers/gpu/drm/xe/xe_sriov.c b/drivers/gpu/drm/xe/xe_sriov.c
index 7d2d6de2aabfeea3dee99829dac6e5e264fe1037..ea411944609b21aa07ab36df9e8fd9c9f18bfdcc 100644 (file)
--- a/drivers/gpu/drm/xe/xe_sriov.c
+++ b/drivers/gpu/drm/xe/xe_sriov.c
@@ -167,6 +167,8 @@ const char *xe_sriov_function_name(unsigned int n, char *buf, size_t size)
  */
 int xe_sriov_init_late(struct xe_device *xe)
 {
+       if (IS_SRIOV_PF(xe))
+               return xe_sriov_pf_init_late(xe);
        if (IS_SRIOV_VF(xe))
                return xe_sriov_vf_init_late(xe);
 

diff --git a/drivers/gpu/drm/xe/xe_sriov_pf.c b/drivers/gpu/drm/xe/xe_sriov_pf.c
index 4698348c010a2a0d746a8b5080ea8734821afd69..2814f29f1093272e5a375c1df7049f23d2c2ed1a 100644 (file)
--- a/drivers/gpu/drm/xe/xe_sriov_pf.c
+++ b/drivers/gpu/drm/xe/xe_sriov_pf.c
@@ -103,6 +103,31 @@ int xe_sriov_pf_init_early(struct xe_device *xe)
        return 0;
 }
 
+/**
+ * xe_sriov_pf_init_late() - Late initialization of the SR-IOV PF.
+ * @xe: the &xe_device to initialize
+ *
+ * This function can only be called on PF.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int xe_sriov_pf_init_late(struct xe_device *xe)
+{
+       struct xe_gt *gt;
+       unsigned int id;
+       int err;
+
+       xe_assert(xe, IS_SRIOV_PF(xe));
+
+       for_each_gt(gt, xe, id) {
+               err = xe_gt_sriov_pf_init(gt);
+               if (err)
+                       return err;
+       }
+
+       return 0;
+}
+
 /**
  * xe_sriov_pf_wait_ready() - Wait until PF is ready to operate.
  * @xe: the &xe_device to test

diff --git a/drivers/gpu/drm/xe/xe_sriov_pf.h b/drivers/gpu/drm/xe/xe_sriov_pf.h
index e6cf930ecde48bdab057bba62f6fae97036a28df..cba3fde9581fa33c3496a44483531faaa43f68ef 100644 (file)
--- a/drivers/gpu/drm/xe/xe_sriov_pf.h
+++ b/drivers/gpu/drm/xe/xe_sriov_pf.h
@@ -15,18 +15,13 @@ struct xe_device;
 #ifdef CONFIG_PCI_IOV
 bool xe_sriov_pf_readiness(struct xe_device *xe);
 int xe_sriov_pf_init_early(struct xe_device *xe);
+int xe_sriov_pf_init_late(struct xe_device *xe);
 int xe_sriov_pf_wait_ready(struct xe_device *xe);
 void xe_sriov_pf_print_vfs_summary(struct xe_device *xe, struct drm_printer *p);
 #else
-static inline bool xe_sriov_pf_readiness(struct xe_device *xe)
-{
-       return false;
-}
-
-static inline int xe_sriov_pf_init_early(struct xe_device *xe)
-{
-       return 0;
-}
+static inline bool xe_sriov_pf_readiness(struct xe_device *xe) { return false; }
+static inline int xe_sriov_pf_init_early(struct xe_device *xe) { return 0; }
+static inline int xe_sriov_pf_init_late(struct xe_device *xe) { return 0; }
 #endif
 
 #endif