drm/v3d: Flush MMU TLB and cache during runtime resume

v3d_mmu_set_page_table() ends by calling v3d_mmu_flush_all() to flush the
MMU cache and clear the TLB after reprogramming V3D_MMU_PT_PA_BASE.
v3d_mmu_flush_all() is gated by pm_runtime_get_if_active(), which returns
0 unless runtime_status == RPM_ACTIVE.

v3d_mmu_set_page_table() is called from two paths that *know* V3D is
reachable, but where the runtime PM status might be wrong:

  1. v3d_power_resume(): the runtime resume callback itself, where
     runtime_status is RPM_RESUMING.

  2. v3d_reset(): called from the DRM scheduler timeout handler with the
     hung job's pm_runtime reference held, so RPM_ACTIVE, but here we
     don't need to take an extra reference for the duration of the flush
     either.

In the first case pm_runtime_get_if_active() returns 0, the flush is
silently skipped, and V3D resumes executing with whatever MMUC/TLB state
happened to survive the last reset. This can leave stale translations
live across runtime PM cycles, manifesting as random GPU hangs.

Split the actual flush sequence into a helper that does the writes
unconditionally, and have v3d_mmu_set_page_table() call it directly.

Fixes: 458f2a712ab4 ("drm/v3d: Introduce Runtime Power Management")
Link: https://patch.msgid.link/20260530-v3d-fix-rpi4-freezes-v1-2-c2c8307da6ce@igalia.com
Signed-off-by: Maíra Canal <mcanal@igalia.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>

diff --git a/drivers/gpu/drm/v3d/v3d_mmu.c b/drivers/gpu/drm/v3d/v3d_mmu.c
index 630c64e51d2f2ad30e59fa2b175487efe0bfba49..94f6676d5633f1643bddb8ddd63b4555a4bb072a 100644 (file)
--- a/drivers/gpu/drm/v3d/v3d_mmu.c
+++ b/drivers/gpu/drm/v3d/v3d_mmu.c
@@ -37,13 +37,14 @@ static bool v3d_mmu_is_aligned(u32 page, u32 page_address, size_t alignment)
                IS_ALIGNED(page_address, alignment >> V3D_MMU_PAGE_SHIFT);
 }
 
-int v3d_mmu_flush_all(struct v3d_dev *v3d)
+/*
+ * Issue the MMUC flush and TLB clear unconditionally. The caller must
+ * already know that V3D is reachable. In particular, this is used from
+ * the runtime resume callback.
+ */
+static int v3d_mmu_flush_all_locked(struct v3d_dev *v3d)
 {
-       int ret = 0;
-
-       /* Flush the PTs only if we're already awake */
-       if (!pm_runtime_get_if_active(v3d->drm.dev))
-               return 0;
+       int ret;
 
        V3D_WRITE(V3D_MMUC_CONTROL, V3D_MMUC_CONTROL_FLUSH |
                  V3D_MMUC_CONTROL_ENABLE);
@@ -52,7 +53,7 @@ int v3d_mmu_flush_all(struct v3d_dev *v3d)
                         V3D_MMUC_CONTROL_FLUSHING), 100);
        if (ret) {
                dev_err(v3d->drm.dev, "MMUC flush wait idle failed\n");
-               goto pm_put;
+               return ret;
        }
 
        V3D_WRITE(V3D_MMU_CTL, V3D_READ(V3D_MMU_CTL) |
@@ -63,7 +64,19 @@ int v3d_mmu_flush_all(struct v3d_dev *v3d)
        if (ret)
                dev_err(v3d->drm.dev, "MMU TLB clear wait idle failed\n");
 
-pm_put:
+       return ret;
+}
+
+int v3d_mmu_flush_all(struct v3d_dev *v3d)
+{
+       int ret;
+
+       /* Flush the PTs only if we're already awake */
+       if (!pm_runtime_get_if_active(v3d->drm.dev))
+               return 0;
+
+       ret = v3d_mmu_flush_all_locked(v3d);
+
        v3d_pm_runtime_put(v3d);
        return ret;
 }
@@ -85,7 +98,7 @@ int v3d_mmu_set_page_table(struct v3d_dev *v3d)
                  V3D_MMU_ILLEGAL_ADDR_ENABLE);
        V3D_WRITE(V3D_MMUC_CONTROL, V3D_MMUC_CONTROL_ENABLE);
 
-       return v3d_mmu_flush_all(v3d);
+       return v3d_mmu_flush_all_locked(v3d);
 }
 
 void v3d_mmu_insert_ptes(struct v3d_bo *bo)