This reduces IRQ pressure by about one third on a saturated link
by disabling the PMQ mechanism. We currently don't use that mechanism.
Signed-off-by: Michael Buesch <mb@xxxxxxxxx>
---
If we implement PMQ in the future, we need to re-enable it, but only
for AP mode. See the comment in the sourcecode.
Index: wireless-testing/drivers/net/wireless/b43/main.c
===================================================================
--- wireless-testing.orig/drivers/net/wireless/b43/main.c 2009-09-12 00:31:44.000000000 +0200
+++ wireless-testing/drivers/net/wireless/b43/main.c 2009-09-12 00:41:27.000000000 +0200
@@ -2675,6 +2675,20 @@ static void b43_adjust_opmode(struct b43
cfp_pretbtt = 50;
}
b43_write16(dev, 0x612, cfp_pretbtt);
+
+ /* FIXME: We don't currently implement the PMQ mechanism,
+ * so always disable it. If we want to implement PMQ,
+ * we need to enable it here (clear DISCPMQ) in AP mode.
+ */
+ if (0 /* ctl & B43_MACCTL_AP */) {
+ b43_write32(dev, B43_MMIO_MACCTL,
+ b43_read32(dev, B43_MMIO_MACCTL)
+ & ~B43_MACCTL_DISCPMQ);
+ } else {
+ b43_write32(dev, B43_MMIO_MACCTL,
+ b43_read32(dev, B43_MMIO_MACCTL)
+ | B43_MACCTL_DISCPMQ);
+ }
}
static void b43_rate_memory_write(struct b43_wldev *dev, u16 rate, int is_ofdm)
--
Greetings, Michael.
--
To unsubscribe from this list: send the line "unsubscribe linux-wireless" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
