powerpc/mm/radix: Implement tlb mmu gather flush efficiently

Now that we track page size in mmu_gather, we can use address based
tlbie format when doing a tlb_flush(). We don't do this if we are
invalidating the full address space.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
index 00703e7e4c941468c49f9dcdd137d3d6f64971e9..7ee9a195fa9c7b76f49836b07aeb547bae3254ae 100644 (file)
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -10,6 +10,8 @@ static inline int mmu_get_ap(int psize)
        return mmu_psize_defs[psize].ap;
 }
 
+extern void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start,
+                                        unsigned long end, int psize);
 extern void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
                            unsigned long end);
 extern void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end);

diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index e1f22700fb169941b869c1c085c7b284df9d078a..6de05c59b3758152042d803a0c13a7f1220e039e 100644 (file)
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -299,8 +299,65 @@ static int radix_get_mmu_psize(int page_size)
 
 void radix__tlb_flush(struct mmu_gather *tlb)
 {
+       int psize = 0;
        struct mm_struct *mm = tlb->mm;
-       radix__flush_tlb_mm(mm);
+       int page_size = tlb->page_size;
+
+       psize = radix_get_mmu_psize(page_size);
+       /*
+        * if page size is not something we understand, do a full mm flush
+        */
+       if (psize != -1 && !tlb->fullmm && !tlb->need_flush_all)
+               radix__flush_tlb_range_psize(mm, tlb->start, tlb->end, psize);
+       else
+               radix__flush_tlb_mm(mm);
+}
+
+#define TLB_FLUSH_ALL -1UL
+/*
+ * Number of pages above which we will do a bcast tlbie. Just a
+ * number at this point copied from x86
+ */
+static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33;
+
+void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start,
+                                 unsigned long end, int psize)
+{
+       unsigned long pid;
+       unsigned long addr;
+       int local = mm_is_core_local(mm);
+       unsigned long ap = mmu_get_ap(psize);
+       int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
+       unsigned long page_size = 1UL << mmu_psize_defs[psize].shift;
+
+
+       preempt_disable();
+       pid = mm ? mm->context.id : 0;
+       if (unlikely(pid == MMU_NO_CONTEXT))
+               goto err_out;
+
+       if (end == TLB_FLUSH_ALL ||
+           (end - start) > tlb_single_page_flush_ceiling * page_size) {
+               if (local)
+                       _tlbiel_pid(pid, RIC_FLUSH_TLB);
+               else
+                       _tlbie_pid(pid, RIC_FLUSH_TLB);
+               goto err_out;
+       }
+       for (addr = start; addr < end; addr += page_size) {
+
+               if (local)
+                       _tlbiel_va(addr, pid, ap, RIC_FLUSH_TLB);
+               else {
+                       if (lock_tlbie)
+                               raw_spin_lock(&native_tlbie_lock);
+                       _tlbie_va(addr, pid, ap, RIC_FLUSH_TLB);
+                       if (lock_tlbie)
+                               raw_spin_unlock(&native_tlbie_lock);
+               }
+       }
+err_out:
+       preempt_enable();
 }
 
 void radix__flush_tlb_lpid_va(unsigned long lpid, unsigned long gpa,