x86: prepare for tlb merge

Impact: clean up, ipi vector number reordering for x86_32

Make the following changes to prepare for tlb merge.

* reorder x86_32 ip vectors

* adjust tlb_32.c and tlb_64.c such that their logics coincide exactly
	- on spurious invalidate ipi, tlb_32 acks the irq
	- tlb_64 now has proper memory barriers around clearing
          flush_cpumask (no change in generated code)

* unexport flush_tlb_page from tlb_32.c, there's no user

* use unsigned int for cpu id

* drop unnecessary includes from tlb_64.c

Signed-off-by: Tejun Heo <tj@kernel.org>

2 files changed, 12 insertions, 16 deletions

diff --git a/arch/x86/kernel/tlb_32.c b/arch/x86/kernel/tlb_32.c
index abf0808d6fc4..93fcb05c7d43 100644
--- a/arch/x86/kernel/tlb_32.c
+++ b/arch/x86/kernel/tlb_32.c
@@ -84,13 +84,15 @@ EXPORT_SYMBOL_GPL(leave_mm);
  *
  * 1) Flush the tlb entries if the cpu uses the mm that's being flushed.
  * 2) Leave the mm if we are in the lazy tlb mode.
+ *
+ * Interrupts are disabled.
  */
 
 void smp_invalidate_interrupt(struct pt_regs *regs)
 {
-        unsigned long cpu;
+        unsigned int cpu;
 
-        cpu = get_cpu();
+        cpu = smp_processor_id();
 
         if (!cpumask_test_cpu(cpu, flush_cpumask))
                 goto out;
@@ -112,12 +114,11 @@ void smp_invalidate_interrupt(struct pt_regs *regs)
                 } else
                         leave_mm(cpu);
         }
+out:
         ack_APIC_irq();
         smp_mb__before_clear_bit();
         cpumask_clear_cpu(cpu, flush_cpumask);
         smp_mb__after_clear_bit();
-out:
-        put_cpu_no_resched();
         inc_irq_stat(irq_tlb_count);
 }
 
@@ -215,7 +216,6 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long va)
                 flush_tlb_others(&mm->cpu_vm_mask, mm, va);
         preempt_enable();
 }
-EXPORT_SYMBOL(flush_tlb_page);
 
 static void do_flush_tlb_all(void *info)
 {
diff --git a/arch/x86/kernel/tlb_64.c b/arch/x86/kernel/tlb_64.c
index b8bed841ad67..19ac661422f7 100644
--- a/arch/x86/kernel/tlb_64.c
+++ b/arch/x86/kernel/tlb_64.c
@@ -1,20 +1,14 @@
 #include <linux/init.h>
 
 #include <linux/mm.h>
-#include <linux/delay.h>
 #include <linux/spinlock.h>
 #include <linux/smp.h>
-#include <linux/kernel_stat.h>
-#include <linux/mc146818rtc.h>
 #include <linux/interrupt.h>
+#include <linux/module.h>
 
-#include <asm/mtrr.h>
-#include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
-#include <asm/proto.h>
-#include <asm/apicdef.h>
-#include <asm/idle.h>
+#include <asm/apic.h>
 #include <asm/uv/uv.h>
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate)
@@ -121,8 +115,8 @@ EXPORT_SYMBOL_GPL(leave_mm);
 
 asmlinkage void smp_invalidate_interrupt(struct pt_regs *regs)
 {
-        int cpu;
-        int sender;
+        unsigned int cpu;
+        unsigned int sender;
         union smp_flush_state *f;
 
         cpu = smp_processor_id();
@@ -155,14 +149,16 @@ asmlinkage void smp_invalidate_interrupt(struct pt_regs *regs)
         }
 out:
         ack_APIC_irq();
+        smp_mb__before_clear_bit();
         cpumask_clear_cpu(cpu, to_cpumask(f->flush_cpumask));
+        smp_mb__after_clear_bit();
         inc_irq_stat(irq_tlb_count);
 }
 
 static void flush_tlb_others_ipi(const struct cpumask *cpumask,
                                  struct mm_struct *mm, unsigned long va)
 {
-        int sender;
+        unsigned int sender;
         union smp_flush_state *f;
 
         /* Caller has disabled preemption */