[POWERPC] Make tlb flush batch use lazy MMU mode

The current tlb flush code on powerpc 64 bits has a subtle race since we
lost the page table lock due to the possible faulting in of new PTEs
after a previous one has been removed but before the corresponding hash
entry has been evicted, which can leads to all sort of fatal problems.

This patch reworks the batch code completely. It doesn't use the mmu_gather
stuff anymore. Instead, we use the lazy mmu hooks that were added by the
paravirt code. They have the nice property that the enter/leave lazy mmu
mode pair is always fully contained by the PTE lock for a given range
of PTEs. Thus we can guarantee that all batches are flushed on a given
CPU before it drops that lock.

We also generalize batching for any PTE update that require a flush.

Batching is now enabled on a CPU by arch_enter_lazy_mmu_mode() and
disabled by arch_leave_lazy_mmu_mode(). The code epects that this is
always contained within a PTE lock section so no preemption can happen
and no PTE insertion in that range from another CPU. When batching
is enabled on a CPU, every PTE updates that need a hash flush will
use the batch for that flush.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>

1 files changed, 25 insertions, 14 deletions

diff --git a/include/asm-powerpc/tlbflush.h b/include/asm-powerpc/tlbflush.h
index 93c7d0c7230f..0bc5a5e506be 100644
--- a/include/asm-powerpc/tlbflush.h
+++ b/include/asm-powerpc/tlbflush.h
@@ -28,25 +28,41 @@ struct mm_struct;
 #define PPC64_TLB_BATCH_NR 192
 
 struct ppc64_tlb_batch {
-        unsigned long index;
-        struct mm_struct *mm;
-        real_pte_t pte[PPC64_TLB_BATCH_NR];
-        unsigned long vaddr[PPC64_TLB_BATCH_NR];
-        unsigned int psize;
+        int                     active;
+        unsigned long           index;
+        struct mm_struct        *mm;
+        real_pte_t              pte[PPC64_TLB_BATCH_NR];
+        unsigned long           vaddr[PPC64_TLB_BATCH_NR];
+        unsigned int            psize;
 };
 DECLARE_PER_CPU(struct ppc64_tlb_batch, ppc64_tlb_batch);
 
 extern void __flush_tlb_pending(struct ppc64_tlb_batch *batch);
 
-static inline void flush_tlb_pending(void)
+extern void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
+                            pte_t *ptep, unsigned long pte, int huge);
+
+#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
+
+static inline void arch_enter_lazy_mmu_mode(void)
+{
+        struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch);
+
+        batch->active = 1;
+}
+
+static inline void arch_leave_lazy_mmu_mode(void)
 {
-        struct ppc64_tlb_batch *batch = &get_cpu_var(ppc64_tlb_batch);
+        struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch);
 
         if (batch->index)
                 __flush_tlb_pending(batch);
-        put_cpu_var(ppc64_tlb_batch);
+        batch->active = 0;
 }
 
+#define arch_flush_lazy_mmu_mode()      do {} while (0)
+
+
 extern void flush_hash_page(unsigned long va, real_pte_t pte, int psize,
                             int local);
 extern void flush_hash_range(unsigned long number, int local);
@@ -88,15 +104,12 @@ extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t);
 
 static inline void flush_tlb_mm(struct mm_struct *mm)
 {
-        flush_tlb_pending();
 }
 
 static inline void flush_tlb_page(struct vm_area_struct *vma,
                                 unsigned long vmaddr)
 {
-#ifdef CONFIG_PPC64
-        flush_tlb_pending();
-#else
+#ifndef CONFIG_PPC64
         _tlbie(vmaddr);
 #endif
 }
@@ -112,13 +125,11 @@ static inline void flush_tlb_page_nohash(struct vm_area_struct *vma,
 static inline void flush_tlb_range(struct vm_area_struct *vma,
                 unsigned long start, unsigned long end)
 {
-        flush_tlb_pending();
 }
 
 static inline void flush_tlb_kernel_range(unsigned long start,
                 unsigned long end)
 {
-        flush_tlb_pending();
 }
 
 #else   /* 6xx, 7xx, 7xxx cpus */