xtensa: limit offsets in __loop_cache_{all,page}

When building kernel for xtensa cores with big cache lines (e.g. 128
bytes or more) __loop_cache_all and __loop_cache_page may generate
assembly instructions with immediate fields that are too big. This
results in the following build errors:

  arch/xtensa/mm/misc.S: Assembler messages:
  arch/xtensa/mm/misc.S:464: Error: operand 2 of 'diwbi' has invalid value '256'
  arch/xtensa/mm/misc.S:464: Error: operand 2 of 'diwbi' has invalid value '384'
  arch/xtensa/kernel/head.S: Assembler messages:
  arch/xtensa/kernel/head.S:172: Error: operand 2 of 'diu' has invalid value '256'
  arch/xtensa/kernel/head.S:172: Error: operand 2 of 'diu' has invalid value '384'
  arch/xtensa/kernel/head.S:176: Error: operand 2 of 'iiu' has invalid value '256'
  arch/xtensa/kernel/head.S:176: Error: operand 2 of 'iiu' has invalid value '384'
  arch/xtensa/kernel/head.S:255: Error: operand 2 of 'diwb' has invalid value '256'
  arch/xtensa/kernel/head.S:255: Error: operand 2 of 'diwb' has invalid value '384'

Add parameter max_immed to these macros and use it to limit values of
immediate operands. Extract common code of these macros into the new
macro __loop_cache_unroll.

Cc: stable@vger.kernel.org
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>

arch/xtensa/include/asm/cacheasm.h

@@ -31,16 +31,32 @@
  *
  */
 
-	.macro	__loop_cache_all ar at insn size line_width
 
-	movi	\ar, 0
+	.macro	__loop_cache_unroll ar at insn size line_width max_immed
+
+	.if	(1 << (\line_width)) > (\max_immed)
+	.set	_reps, 1
+	.elseif	(2 << (\line_width)) > (\max_immed)
+	.set	_reps, 2
+	.else
+	.set	_reps, 4
+	.endif
+
+	__loopi	\ar, \at, \size, (_reps << (\line_width))
+	.set	_index, 0
+	.rep	_reps
+	\insn	\ar, _index << (\line_width)
+	.set	_index, _index + 1
+	.endr
+	__endla	\ar, \at, _reps << (\line_width)
+
+	.endm
+
 
-	__loopi	\ar, \at, \size, (4 << (\line_width))
-	\insn	\ar, 0 << (\line_width)
-	\insn	\ar, 1 << (\line_width)
-	\insn	\ar, 2 << (\line_width)
-	\insn	\ar, 3 << (\line_width)
-	__endla	\ar, \at, 4 << (\line_width)
+	.macro	__loop_cache_all ar at insn size line_width max_immed
+
+	movi	\ar, 0
+	__loop_cache_unroll \ar, \at, \insn, \size, \line_width, \max_immed
 
 	.endm
 
@@ -57,14 +73,9 @@
 	.endm
 
 
-	.macro	__loop_cache_page ar at insn line_width
+	.macro	__loop_cache_page ar at insn line_width max_immed
 
-	__loopi	\ar, \at, PAGE_SIZE, 4 << (\line_width)
-	\insn	\ar, 0 << (\line_width)
-	\insn	\ar, 1 << (\line_width)
-	\insn	\ar, 2 << (\line_width)
-	\insn	\ar, 3 << (\line_width)
-	__endla	\ar, \at, 4 << (\line_width)
+	__loop_cache_unroll \ar, \at, \insn, PAGE_SIZE, \line_width, \max_immed
 
 	.endm
 
@@ -72,7 +83,8 @@
 	.macro	___unlock_dcache_all ar at
 
 #if XCHAL_DCACHE_LINE_LOCKABLE && XCHAL_DCACHE_SIZE
-	__loop_cache_all \ar \at diu XCHAL_DCACHE_SIZE XCHAL_DCACHE_LINEWIDTH
+	__loop_cache_all \ar \at diu XCHAL_DCACHE_SIZE \
+		XCHAL_DCACHE_LINEWIDTH 240
 #endif
 
 	.endm
@@ -81,7 +93,8 @@
 	.macro	___unlock_icache_all ar at
 
 #if XCHAL_ICACHE_LINE_LOCKABLE && XCHAL_ICACHE_SIZE
-	__loop_cache_all \ar \at iiu XCHAL_ICACHE_SIZE XCHAL_ICACHE_LINEWIDTH
+	__loop_cache_all \ar \at iiu XCHAL_ICACHE_SIZE \
+		XCHAL_ICACHE_LINEWIDTH 240
 #endif
 
 	.endm
@@ -90,7 +103,8 @@
 	.macro	___flush_invalidate_dcache_all ar at
 
 #if XCHAL_DCACHE_SIZE
-	__loop_cache_all \ar \at diwbi XCHAL_DCACHE_SIZE XCHAL_DCACHE_LINEWIDTH
+	__loop_cache_all \ar \at diwbi XCHAL_DCACHE_SIZE \
+		XCHAL_DCACHE_LINEWIDTH 240
 #endif
 
 	.endm
@@ -99,7 +113,8 @@
 	.macro	___flush_dcache_all ar at
 
 #if XCHAL_DCACHE_SIZE
-	__loop_cache_all \ar \at diwb XCHAL_DCACHE_SIZE XCHAL_DCACHE_LINEWIDTH
+	__loop_cache_all \ar \at diwb XCHAL_DCACHE_SIZE \
+		XCHAL_DCACHE_LINEWIDTH 240
 #endif
 
 	.endm
@@ -109,7 +124,7 @@
 
 #if XCHAL_DCACHE_SIZE
 	__loop_cache_all \ar \at dii __stringify(DCACHE_WAY_SIZE) \
-			 XCHAL_DCACHE_LINEWIDTH
+			 XCHAL_DCACHE_LINEWIDTH 1020
 #endif
 
 	.endm
@@ -119,7 +134,7 @@
 
 #if XCHAL_ICACHE_SIZE
 	__loop_cache_all \ar \at iii __stringify(ICACHE_WAY_SIZE) \
-			 XCHAL_ICACHE_LINEWIDTH
+			 XCHAL_ICACHE_LINEWIDTH 1020
 #endif
 
 	.endm
@@ -166,7 +181,7 @@
 	.macro	___flush_invalidate_dcache_page ar as
 
 #if XCHAL_DCACHE_SIZE
-	__loop_cache_page \ar \as dhwbi XCHAL_DCACHE_LINEWIDTH
+	__loop_cache_page \ar \as dhwbi XCHAL_DCACHE_LINEWIDTH 1020
 #endif
 
 	.endm
@@ -175,7 +190,7 @@
 	.macro ___flush_dcache_page ar as
 
 #if XCHAL_DCACHE_SIZE
-	__loop_cache_page \ar \as dhwb XCHAL_DCACHE_LINEWIDTH
+	__loop_cache_page \ar \as dhwb XCHAL_DCACHE_LINEWIDTH 1020
 #endif
 
 	.endm
@@ -184,7 +199,7 @@
 	.macro	___invalidate_dcache_page ar as
 
 #if XCHAL_DCACHE_SIZE
-	__loop_cache_page \ar \as dhi XCHAL_DCACHE_LINEWIDTH
+	__loop_cache_page \ar \as dhi XCHAL_DCACHE_LINEWIDTH 1020
 #endif
 
 	.endm
@@ -193,7 +208,7 @@
 	.macro	___invalidate_icache_page ar as
 
 #if XCHAL_ICACHE_SIZE
-	__loop_cache_page \ar \as ihi XCHAL_ICACHE_LINEWIDTH
+	__loop_cache_page \ar \as ihi XCHAL_ICACHE_LINEWIDTH 1020
 #endif
 
 	.endm