drm/v3d: Fix Indirect Dispatch configuration for V3D 7.1.6 and later

This commit is a resubmission of commit 1fe1c66274fb ("drm/v3d: Fix
Indirect Dispatch configuration for V3D 7.1.6 and later"), which was
accidentally reverted by commit 91dae758bdb8 ("Merge tag
'drm-misc-next-2024-08-01' of https://gitlab.freedesktop.org/drm/misc/kernel
into drm-next"), likely due to an unfortunate conflict resolution.

From the original commit message:

```
`args->cfg[4]` is configured in Indirect Dispatch using the number of
batches. Currently, for all V3D tech versions, `args->cfg[4]` equals the
number of batches subtracted by 1. But, for V3D 7.1.6 and later, we must not
subtract 1 from the number of batches.

Implement the fix by checking the V3D tech version and revision.

Fixes several `dEQP-VK.synchronization*` CTS tests related to Indirect Dispatch.
```

Fixes: 91dae758bdb8 ("Merge tag 'drm-misc-next-2024-08-01' of https://gitlab.freedesktop.org/drm/misc/kernel into drm-next")
Signed-off-by: Maíra Canal <mcanal@igalia.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Link: https://lore.kernel.org/r/20250409205051.9639-1-mcanal@igalia.com

diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index 34c42d6e12cde656d3b51a18be324976199eceae..4a7701a33cf8d76c8f527e496966c6689673012f 100644 (file)
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -428,7 +428,8 @@ v3d_rewrite_csd_job_wg_counts_from_indirect(struct v3d_cpu_job *job)
        struct v3d_bo *bo = to_v3d_bo(job->base.bo[0]);
        struct v3d_bo *indirect = to_v3d_bo(indirect_csd->indirect);
        struct drm_v3d_submit_csd *args = &indirect_csd->job->args;
-       u32 *wg_counts;
+       struct v3d_dev *v3d = job->base.v3d;
+       u32 num_batches, *wg_counts;
 
        v3d_get_bo_vaddr(bo);
        v3d_get_bo_vaddr(indirect);
@@ -441,8 +442,17 @@ v3d_rewrite_csd_job_wg_counts_from_indirect(struct v3d_cpu_job *job)
        args->cfg[0] = wg_counts[0] << V3D_CSD_CFG012_WG_COUNT_SHIFT;
        args->cfg[1] = wg_counts[1] << V3D_CSD_CFG012_WG_COUNT_SHIFT;
        args->cfg[2] = wg_counts[2] << V3D_CSD_CFG012_WG_COUNT_SHIFT;
-       args->cfg[4] = DIV_ROUND_UP(indirect_csd->wg_size, 16) *
-                      (wg_counts[0] * wg_counts[1] * wg_counts[2]) - 1;
+
+       num_batches = DIV_ROUND_UP(indirect_csd->wg_size, 16) *
+                     (wg_counts[0] * wg_counts[1] * wg_counts[2]);
+
+       /* V3D 7.1.6 and later don't subtract 1 from the number of batches */
+       if (v3d->ver < 71 || (v3d->ver == 71 && v3d->rev < 6))
+               args->cfg[4] = num_batches - 1;
+       else
+               args->cfg[4] = num_batches;
+
+       WARN_ON(args->cfg[4] == ~0);
 
        for (int i = 0; i < 3; i++) {
                /* 0xffffffff indicates that the uniform rewrite is not needed */