Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel os linux

ARM: mvebu: use DT properties to fine-tune the L2 configuration

In order to optimize the L2 cache performance, this commit adjusts the
configuration of the L2 on the Cortex-A9 based Marvell EBU processors
(Armada 375, 38x and 39x), using the appropriate DT properties.

We enable double linefill, incr double linefill, data prefetch and
disable double linefill on wrap. This matches the configuration that
was fine tuned in the Marvell BSP.

Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Acked-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>

authored by

Thomas Petazzoni and committed by
Gregory CLEMENT
c8f5a878 449e1d64

+12
+4
arch/arm/boot/dts/armada-375.dtsi
··· 176 176 reg = <0x8000 0x1000>; 177 177 cache-unified; 178 178 cache-level = <2>; 179 + arm,double-linefill-incr = <1>; 180 + arm,double-linefill-wrap = <0>; 181 + arm,double-linefill = <1>; 182 + prefetch-data = <1>; 179 183 }; 180 184 181 185 scu@c000 {
+4
arch/arm/boot/dts/armada-38x.dtsi
··· 143 143 reg = <0x8000 0x1000>; 144 144 cache-unified; 145 145 cache-level = <2>; 146 + arm,double-linefill-incr = <1>; 147 + arm,double-linefill-wrap = <0>; 148 + arm,double-linefill = <1>; 149 + prefetch-data = <1>; 146 150 }; 147 151 148 152 scu@c000 {
+4
arch/arm/boot/dts/armada-39x.dtsi
··· 104 104 reg = <0x8000 0x1000>; 105 105 cache-unified; 106 106 cache-level = <2>; 107 + arm,double-linefill-incr = <1>; 108 + arm,double-linefill-wrap = <0>; 109 + arm,double-linefill = <1>; 110 + prefetch-data = <1>; 107 111 }; 108 112 109 113 scu@c000 {