arm: Add v7_invalidate_l1 to cache-v7.S

mach-socfpga is another platform that needs to use
v7_invalidate_l1 to bringup additional cores. There was a comment that
the ideal place for v7_invalidate_l1 should be in arm/mm/cache-v7.S

Signed-off-by: Dinh Nguyen <dinguyen@altera.com>
Acked-by: Simon Horman <horms+renesas@verge.net.au>
Acked-by: Stephen Warren <swarren@nvidia.com>
Reviewed-by: Pavel Machek <pavel@denx.de>
Reviewed-by: Santosh Shilimkar <santosh.shilimkar@ti.com>
Tested-by: Pavel Machek <pavel@denx.de>
Tested-by: Stephen Warren <swarren@nvidia.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Olof Johansson <olof@lixom.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Rob Herring <rob.herring@calxeda.com>
Cc: Sascha Hauer <kernel@pengutronix.de>
Cc: Magnus Damm <magnus.damm@gmail.com>
Signed-off-by: Olof Johansson <olof@lixom.net>

1 files changed, 46 insertions, 0 deletions

diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 7539ec2..15451ee 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -19,6 +19,52 @@
 #include "proc-macros.S"
 
 /*
+ * The secondary kernel init calls v7_flush_dcache_all before it enables
+ * the L1; however, the L1 comes out of reset in an undefined state, so
+ * the clean + invalidate performed by v7_flush_dcache_all causes a bunch
+ * of cache lines with uninitialized data and uninitialized tags to get
+ * written out to memory, which does really unpleasant things to the main
+ * processor.  We fix this by performing an invalidate, rather than a
+ * clean + invalidate, before jumping into the kernel.
+ *
+ * This function is cloned from arch/arm/mach-tegra/headsmp.S, and needs
+ * to be called for both secondary cores startup and primary core resume
+ * procedures.
+ */
+ENTRY(v7_invalidate_l1)
+       mov     r0, #0
+       mcr     p15, 2, r0, c0, c0, 0
+       mrc     p15, 1, r0, c0, c0, 0
+
+       ldr     r1, =0x7fff
+       and     r2, r1, r0, lsr #13
+
+       ldr     r1, =0x3ff
+
+       and     r3, r1, r0, lsr #3      @ NumWays - 1
+       add     r2, r2, #1              @ NumSets
+
+       and     r0, r0, #0x7
+       add     r0, r0, #4      @ SetShift
+
+       clz     r1, r3          @ WayShift
+       add     r4, r3, #1      @ NumWays
+1:     sub     r2, r2, #1      @ NumSets--
+       mov     r3, r4          @ Temp = NumWays
+2:     subs    r3, r3, #1      @ Temp--
+       mov     r5, r3, lsl r1
+       mov     r6, r2, lsl r0
+       orr     r5, r5, r6      @ Reg = (Temp<<WayShift)|(NumSets<<SetShift)
+       mcr     p15, 0, r5, c7, c6, 2
+       bgt     2b
+       cmp     r2, #0
+       bgt     1b
+       dsb
+       isb
+       mov     pc, lr
+ENDPROC(v7_invalidate_l1)
+
+/*
  *	v7_flush_icache_all()
  *
  *	Flush the whole I-cache.