gpu: host1x: Skip redundant syncpoint loads in host1x_syncpt_wait()

In host1x_syncpt_wait(), the hardware syncpoint value was loaded
initially for expiry check, and then loaded a second time to
populate the caller's value pointer. Reuse a single load for
both purposes.

After dma_fence_wait_timeout(), the previous code reloaded the syncpoint
value for the expiry check, which is only required in the timeout case.
On success (i.e., return value > 0, or return value == 0 with zero
jiffies remaining), the ISR has already cached the value before
signaling the fence. The value pointer can therefore be populated using
the cached value using host1x_syncpt_read_min() without MMIO access.
Only the timeout path requires a fresh load, move host1x_syncpt_load()
under that path.

Measured Syncpoint wait latency (50000 samples):
  Average latency:   12.2 us  -> 10.6 us
  99.99 pct latency: 62.96 us -> 51.90 us

Signed-off-by: Tanmay Patil <tanmayp@nvidia.com>
Acked-by: Mikko Perttunen <mperttunen@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patch.msgid.link/20260514103153.766343-2-tanmayp@nvidia.com

diff --git a/drivers/gpu/host1x/syncpt.c b/drivers/gpu/host1x/syncpt.c
index acc7d82e0585e83db2da82933ada4c817114b16e..807c74fc6a0aca90393198eeb593228f12fe305e 100644 (file)
--- a/drivers/gpu/host1x/syncpt.c
+++ b/drivers/gpu/host1x/syncpt.c
@@ -222,11 +222,12 @@ int host1x_syncpt_wait(struct host1x_syncpt *sp, u32 thresh, long timeout,
 {
        struct dma_fence *fence;
        long wait_err;
+       u32 curr;
 
-       host1x_hw_syncpt_load(sp->host, sp);
+       curr = host1x_syncpt_load(sp);
 
        if (value)
-               *value = host1x_syncpt_load(sp);
+               *value = curr;
 
        if (host1x_syncpt_is_expired(sp, thresh))
                return 0;
@@ -245,21 +246,25 @@ int host1x_syncpt_wait(struct host1x_syncpt *sp, u32 thresh, long timeout,
                host1x_fence_cancel(fence);
        dma_fence_put(fence);
 
-       if (value)
-               *value = host1x_syncpt_load(sp);
-
        /*
         * Don't rely on dma_fence_wait_timeout return value,
         * since it returns zero both on timeout and if the
         * wait completed with 0 jiffies left.
         */
-       host1x_hw_syncpt_load(sp->host, sp);
-       if (wait_err == 0 && !host1x_syncpt_is_expired(sp, thresh))
+       if (wait_err == 0 && !host1x_syncpt_is_expired(sp, thresh)) {
+               if (value)
+                       *value = host1x_syncpt_load(sp);
+
                return -EAGAIN;
-       else if (wait_err < 0)
+       } else if (wait_err < 0) {
                return wait_err;
-       else
+       } else {
+               /* Success, read the value cached by ISR */
+               if (value)
+                       *value = host1x_syncpt_read_min(sp);
+
                return 0;
+       }
 }
 EXPORT_SYMBOL(host1x_syncpt_wait);