Revert "arm64: kill flush_cache_all()"

This reverts the upstream commit 68234df.
This is required internally for certain use-cases like flushing cache
before reboot to ensure all the data is available in the ramdump.

Signed-off-by: Rohit Vaswani <rvaswani@codeaurora.org>

arch/arm64/include/asm/cacheflush.h

@@ -40,6 +40,10 @@
  *	the implementation assumes non-aliasing VIPT D-cache and (aliasing)
  *	VIPT or ASID-tagged VIVT I-cache.
  *
+ *	flush_cache_all()
+ *
+ *		Unconditionally clean and invalidate the entire cache.
+ *
  *	flush_cache_mm(mm)
  *
  *		Clean and invalidate all user space cache entries
@@ -65,6 +69,7 @@
  *		- kaddr  - page address
  *		- size   - region size
  */
+extern void flush_cache_all(void);
 extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
 extern void flush_icache_range(unsigned long start, unsigned long end);
 extern void __flush_dcache_area(void *addr, size_t len);

arch/arm64/include/asm/proc-fns.h

@@ -28,8 +28,12 @@
 struct mm_struct;
 struct cpu_suspend_ctx;
 
+extern void cpu_cache_off(void);
 extern void cpu_do_idle(void);
 extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
+extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
+void cpu_soft_restart(phys_addr_t cpu_reset,
+		unsigned long addr) __attribute__((noreturn));
 extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr);
 extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
 

arch/arm64/mm/cache.S

@@ -26,6 +26,79 @@
 
 #include "proc-macros.S"
 
+/*
+ *	__flush_dcache_all()
+ *
+ *	Flush the whole D-cache.
+ *
+ *	Corrupted registers: x0-x7, x9-x11
+ */
+__flush_dcache_all:
+	dmb	sy				// ensure ordering with previous memory accesses
+	mrs	x0, clidr_el1			// read clidr
+	and	x3, x0, #0x7000000		// extract loc from clidr
+	lsr	x3, x3, #23			// left align loc bit field
+	cbz	x3, finished			// if loc is 0, then no need to clean
+	mov	x10, #0				// start clean at cache level 0
+loop1:
+	add	x2, x10, x10, lsr #1		// work out 3x current cache level
+	lsr	x1, x0, x2			// extract cache type bits from clidr
+	and	x1, x1, #7			// mask of the bits for current cache only
+	cmp	x1, #2				// see what cache we have at this level
+	b.lt	skip				// skip if no cache, or just i-cache
+	save_and_disable_irqs x9		// make CSSELR and CCSIDR access atomic
+	msr	csselr_el1, x10			// select current cache level in csselr
+	isb					// isb to sych the new cssr&csidr
+	mrs	x1, ccsidr_el1			// read the new ccsidr
+	restore_irqs x9
+	and	x2, x1, #7			// extract the length of the cache lines
+	add	x2, x2, #4			// add 4 (line length offset)
+	mov	x4, #0x3ff
+	and	x4, x4, x1, lsr #3		// find maximum number on the way size
+	clz	w5, w4				// find bit position of way size increment
+	mov	x7, #0x7fff
+	and	x7, x7, x1, lsr #13		// extract max number of the index size
+loop2:
+	mov	x9, x4				// create working copy of max way size
+loop3:
+	lsl	x6, x9, x5
+	orr	x11, x10, x6			// factor way and cache number into x11
+	lsl	x6, x7, x2
+	orr	x11, x11, x6			// factor index number into x11
+	dc	cisw, x11			// clean & invalidate by set/way
+	subs	x9, x9, #1			// decrement the way
+	b.ge	loop3
+	subs	x7, x7, #1			// decrement the index
+	b.ge	loop2
+skip:
+	add	x10, x10, #2			// increment cache number
+	cmp	x3, x10
+	b.gt	loop1
+finished:
+	mov	x10, #0				// swith back to cache level 0
+	msr	csselr_el1, x10			// select current cache level in csselr
+	dsb	sy
+	isb
+	ret
+ENDPROC(__flush_dcache_all)
+
+/*
+ *	flush_cache_all()
+ *
+ *	Flush the entire cache system.  The data cache flush is now achieved
+ *	using atomic clean / invalidates working outwards from L1 cache. This
+ *	is done using Set/Way based cache maintainance instructions.  The
+ *	instruction cache can still be invalidated back to the point of
+ *	unification in a single instruction.
+ */
+ENTRY(flush_cache_all)
+	mov	x12, lr
+	bl	__flush_dcache_all
+	mov	x0, #0
+	ic	ialluis				// I+BTB cache invalidate
+	ret	x12
+ENDPROC(flush_cache_all)
+
 /*
  *	flush_icache_range(start,end)
  *

arch/arm64/mm/flush.c

@@ -98,6 +98,7 @@ EXPORT_SYMBOL(flush_dcache_page);
 /*
  * Additional functions defined in assembly.
  */
+EXPORT_SYMBOL(flush_cache_all);
 EXPORT_SYMBOL(flush_icache_range);
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE

arch/arm64/mm/proc.S

@@ -43,6 +43,52 @@
 
 #define MAIR(attr, mt)	((attr) << ((mt) * 8))
 
+/*
+ *	cpu_cache_off()
+ *
+ *	Turn the CPU D-cache off.
+ */
+ENTRY(cpu_cache_off)
+	mrs	x0, sctlr_el1
+	bic	x0, x0, #1 << 2			// clear SCTLR.C
+	msr	sctlr_el1, x0
+	isb
+	ret
+ENDPROC(cpu_cache_off)
+
+/*
+ *	cpu_reset(loc)
+ *
+ *	Perform a soft reset of the system.  Put the CPU into the same state
+ *	as it would be if it had been reset, and branch to what would be the
+ *	reset vector. It must be executed with the flat identity mapping.
+ *
+ *	- loc   - location to jump to for soft reset
+ */
+	.align	5
+ENTRY(cpu_reset)
+	mrs	x1, sctlr_el1
+	bic	x1, x1, #1
+	msr	sctlr_el1, x1			// disable the MMU
+	isb
+	ret	x0
+ENDPROC(cpu_reset)
+
+ENTRY(cpu_soft_restart)
+	/* Save address of cpu_reset() and reset address */
+	mov	x19, x0
+	mov	x20, x1
+
+	/* Turn D-cache off */
+	bl	cpu_cache_off
+
+	/* Push out all dirty data, and ensure cache is empty */
+	bl	flush_cache_all
+
+	mov	x0, x20
+	ret	x19
+ENDPROC(cpu_soft_restart)
+
 /*
  *	cpu_do_idle()
  *