[ARM] Feroceon: L2 cache support

This patch adds support for the unified Feroceon L2 cache controller
as found in e.g. the Marvell Kirkwood and Marvell Discovery Duo
families of ARM SoCs.

Note that:

- Page table walks are outer uncacheable on Kirkwood and Discovery
  Duo, since the ARMv5 spec provides no way to indicate outer
  cacheability of page table walks (specifying it in TTBR[4:3] is
  an ARMv6+ feature).

  This requires adding L2 cache clean instructions to
  proc-feroceon.S (dcache_clean_area(), set_pte()) as well as to
  tlbflush.h ({flush,clean}_pmd_entry()).  The latter case is handled
  by defining a new TLB type (TLB_FEROCEON) which is almost identical
  to the v4wbi one but provides a TLB_L2CLEAN_FR flag.

- The Feroceon L2 cache controller supports L2 range (i.e. 'clean L2
  range by MVA' and 'invalidate L2 range by MVA') operations, and this
  patch uses those range operations for all Linux outer cache
  operations, as they are faster than the regular per-line operations.

  L2 range operations are not interruptible on this hardware, which
  avoids potential livelock issues, but can be bad for interrupt
  latency, so there is a compile-time tunable (MAX_RANGE_SIZE) which
  allows you to select the maximum range size to operate on at once.
  (Valid range is between one cache line and one 4KiB page, and must
  be a multiple of the line size.)

Signed-off-by: Lennert Buytenhek <buytenh@marvell.com>

arch/arm/mm/proc-feroceon.S

@@ -79,6 +79,13 @@ ENTRY(cpu_feroceon_proc_fin)
 	mov	ip, #PSR_F_BIT | PSR_I_BIT | SVC_MODE
 	msr	cpsr_c, ip
 	bl	feroceon_flush_kern_cache_all
+
+#if defined(CONFIG_CACHE_FEROCEON_L2) && !defined(CONFIG_L2_CACHE_WRITETHROUGH)
+	mov	r0, #0
+	mcr	p15, 1, r0, c15, c9, 0		@ clean L2
+	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
+#endif
+
 	mrc	p15, 0, r0, c1, c0, 0		@ ctrl register
 	bic	r0, r0, #0x1000			@ ...i............
 	bic	r0, r0, #0x000e			@ ............wca.
@@ -382,10 +389,20 @@ ENTRY(feroceon_range_cache_fns)
 
 	.align	5
 ENTRY(cpu_feroceon_dcache_clean_area)
+#if defined(CONFIG_CACHE_FEROCEON_L2) && !defined(CONFIG_L2_CACHE_WRITETHROUGH)
+	mov	r2, r0
+	mov	r3, r1
+#endif
 1:	mcr	p15, 0, r0, c7, c10, 1		@ clean D entry
 	add	r0, r0, #CACHE_DLINESIZE
 	subs	r1, r1, #CACHE_DLINESIZE
 	bhi	1b
+#if defined(CONFIG_CACHE_FEROCEON_L2) && !defined(CONFIG_L2_CACHE_WRITETHROUGH)
+1:	mcr	p15, 1, r2, c15, c9, 1		@ clean L2 entry
+	add	r2, r2, #CACHE_DLINESIZE
+	subs	r3, r3, #CACHE_DLINESIZE
+	bhi	1b
+#endif
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
 	mov	pc, lr
 
@@ -449,6 +466,9 @@ ENTRY(cpu_feroceon_set_pte_ext)
 	str	r2, [r0]			@ hardware version
 	mov	r0, r0
 	mcr	p15, 0, r0, c7, c10, 1		@ clean D entry
+#if defined(CONFIG_CACHE_FEROCEON_L2) && !defined(CONFIG_L2_CACHE_WRITETHROUGH)
+	mcr	p15, 1, r0, c15, c9, 1		@ clean L2 entry
+#endif
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
 #endif
 	mov	pc, lr