openrisc: initial SMP support

This patch introduces the SMP support for the OpenRISC architecture.
The SMP architecture requires cores which have multi-core features which
have been introduced a few years back including:

 - New SPRS SPR_COREID SPR_NUMCORES
 - Shadow SPRs
 - Atomic Instructions
 - Cache Coherency
 - A wired in IPI controller

This patch adds all of the SMP specific changes to core infrastructure,
it looks big but it needs to go all together as its hard to split this
one up.

Boot loader spinning of second cpu is not supported yet, it's assumed
that Linux is booted straight after cpu reset.

The bulk of these changes are trivial changes to refactor to use per cpu
data structures throughout.  The addition of the smp.c and changes in
time.c are the changes.  Some specific notes:

MM changes
----------
The reason why this is created as an array, and not with DEFINE_PER_CPU
is that doing it this way, we'll save a load in the tlb-miss handler
(the load from __per_cpu_offset).

TLB Flush
---------
The SMP implementation of flush_tlb_* works by sending out a
function-call IPI to all the non-local cpus by using the generic
on_each_cpu() function.

Currently, all flush_tlb_* functions will result in a flush_tlb_all(),
which has always been the behaviour in the UP case.

CPU INFO
--------
This creates a per cpu cpuinfo struct and fills it out accordingly for
each activated cpu.  show_cpuinfo is also updated to reflect new version
information in later versions of the spec.

SMP API
-------
This imitates the arm64 implementation by having a smp_cross_call
callback that can be set by set_smp_cross_call to initiate an IPI and a
handle_IPI function that is expected to be called from an IPI irqchip
driver.

Signed-off-by: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
[shorne@gmail.com: added cpu stop, checkpatch fixes, wrote commit message]
Signed-off-by: Stafford Horne <shorne@gmail.com>

3 files changed, 11 insertions, 11 deletions

diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
index e310ab499385..d0021dfae20a 100644
--- a/arch/openrisc/mm/fault.c
+++ b/arch/openrisc/mm/fault.c
@@ -33,7 +33,7 @@ unsigned long pte_errors;	/* updated by do_page_fault() */
 /* __PHX__ :: - check the vmalloc_fault in do_page_fault()
  *            - also look into include/asm-or32/mmu_context.h
  */
-volatile pgd_t *current_pgd;
+volatile pgd_t *current_pgd[NR_CPUS];
 
 extern void die(char *, struct pt_regs *, long);
 
@@ -319,7 +319,7 @@ vmalloc_fault:
 
 		phx_mmu("vmalloc_fault");
 */
-		pgd = (pgd_t *)current_pgd + offset;
+		pgd = (pgd_t *)current_pgd[smp_processor_id()] + offset;
 		pgd_k = init_mm.pgd + offset;
 
 		/* Since we're two-level, we don't need to do both
diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c
index f67d82b9d22f..6972d5d6f23f 100644
--- a/arch/openrisc/mm/init.c
+++ b/arch/openrisc/mm/init.c
@@ -147,7 +147,7 @@ void __init paging_init(void)
 	 * (even if it is most probably not used until the next
 	 *  switch_mm)
 	 */
-	current_pgd = init_mm.pgd;
+	current_pgd[smp_processor_id()] = init_mm.pgd;
 
 	end = (unsigned long)__va(max_low_pfn * PAGE_SIZE);
 
diff --git a/arch/openrisc/mm/tlb.c b/arch/openrisc/mm/tlb.c
index 683bd4d31c7c..6c253a2e86bc 100644
--- a/arch/openrisc/mm/tlb.c
+++ b/arch/openrisc/mm/tlb.c
@@ -49,7 +49,7 @@
  *
  */
 
-void flush_tlb_all(void)
+void local_flush_tlb_all(void)
 {
 	int i;
 	unsigned long num_tlb_sets;
@@ -86,7 +86,7 @@ void flush_tlb_all(void)
 #define flush_itlb_page_no_eir(addr) \
 	mtspr_off(SPR_ITLBMR_BASE(0), ITLB_OFFSET(addr), 0);
 
-void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
+void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
 {
 	if (have_dtlbeir)
 		flush_dtlb_page_eir(addr);
@@ -99,8 +99,8 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
 		flush_itlb_page_no_eir(addr);
 }
 
-void flush_tlb_range(struct vm_area_struct *vma,
-		     unsigned long start, unsigned long end)
+void local_flush_tlb_range(struct vm_area_struct *vma,
+			   unsigned long start, unsigned long end)
 {
 	int addr;
 	bool dtlbeir;
@@ -129,13 +129,13 @@ void flush_tlb_range(struct vm_area_struct *vma,
  * This should be changed to loop over over mm and call flush_tlb_range.
  */
 
-void flush_tlb_mm(struct mm_struct *mm)
+void local_flush_tlb_mm(struct mm_struct *mm)
 {
 
 	/* Was seeing bugs with the mm struct passed to us. Scrapped most of
 	   this function. */
 	/* Several architctures do this */
-	flush_tlb_all();
+	local_flush_tlb_all();
 }
 
 /* called in schedule() just before actually doing the switch_to */
@@ -149,14 +149,14 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	 * might be invalid at points where we still need to derefer
 	 * the pgd.
 	 */
-	current_pgd = next->pgd;
+	current_pgd[smp_processor_id()] = next->pgd;
 
 	/* We don't have context support implemented, so flush all
 	 * entries belonging to previous map
 	 */
 
 	if (prev != next)
-		flush_tlb_mm(prev);
+		local_flush_tlb_mm(prev);
 
 }