10 files changed, 46 insertions, 139 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index a3128ca0fe11..423145a6f7ba 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -140,6 +140,7 @@ config PPC
         select IRQ_PER_CPU
         select GENERIC_IRQ_SHOW
         select GENERIC_IRQ_SHOW_LEVEL
+        select HAVE_RCU_TABLE_FREE if SMP
 
 config EARLY_PRINTK
         bool
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index a597dd77b903..e72dcf6a421d 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -35,27 +35,6 @@ config DEBUG_STACKOVERFLOW
           This option will cause messages to be printed if free stack space
           drops below a certain limit.
 
-config DEBUG_STACK_USAGE
-        bool "Stack utilization instrumentation"
-        depends on DEBUG_KERNEL
-        help
-          Enables the display of the minimum amount of free stack which each
-          task has ever had available in the sysrq-T and sysrq-P debug output.
-
-          This option will slow down process creation somewhat.
-
-config DEBUG_PER_CPU_MAPS
-        bool "Debug access to per_cpu maps"
-        depends on DEBUG_KERNEL
-        depends on SMP
-        default n
-        ---help---
-          Say Y to verify that the per_cpu map being accessed has
-          been setup.  Adds a fair amount of code to kernel memory
-          and decreases performance.
-
-          Say N if unsure.
-
 config HCALL_STATS
         bool "Hypervisor call instrumentation"
         depends on PPC_PSERIES && DEBUG_FS && TRACEPOINTS
diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h
index abe8532bd14e..bf301ac62f35 100644
--- a/arch/powerpc/include/asm/pgalloc.h
+++ b/arch/powerpc/include/asm/pgalloc.h
@@ -31,14 +31,29 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
 #endif
 
 #ifdef CONFIG_SMP
-extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift);
-extern void pte_free_finish(void);
+struct mmu_gather;
+extern void tlb_remove_table(struct mmu_gather *, void *);
+
+static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
+{
+        unsigned long pgf = (unsigned long)table;
+        BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
+        pgf |= shift;
+        tlb_remove_table(tlb, (void *)pgf);
+}
+
+static inline void __tlb_remove_table(void *_table)
+{
+        void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
+        unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;
+
+        pgtable_free(table, shift);
+}
 #else /* CONFIG_SMP */
 static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift)
 {
         pgtable_free(table, shift);
 }
-static inline void pte_free_finish(void) { }
 #endif /* !CONFIG_SMP */
 
 static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *ptepage,
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index d8529ef13b23..37c353e8af7c 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -139,10 +139,12 @@ static inline struct thread_info *current_thread_info(void)
 #define TLF_NAPPING             0       /* idle thread enabled NAP mode */
 #define TLF_SLEEPING            1       /* suspend code enabled SLEEP mode */
 #define TLF_RESTORE_SIGMASK     2       /* Restore signal mask in do_signal */
+#define TLF_LAZY_MMU            3       /* tlb_batch is active */
 
 #define _TLF_NAPPING            (1 << TLF_NAPPING)
 #define _TLF_SLEEPING           (1 << TLF_SLEEPING)
 #define _TLF_RESTORE_SIGMASK    (1 << TLF_RESTORE_SIGMASK)
+#define _TLF_LAZY_MMU           (1 << TLF_LAZY_MMU)
 
 #ifndef __ASSEMBLY__
 #define HAVE_SET_RESTORE_SIGMASK        1
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 095043d79946..91e52df3d81d 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -395,6 +395,9 @@ struct task_struct *__switch_to(struct task_struct *prev,
         struct thread_struct *new_thread, *old_thread;
         unsigned long flags;
         struct task_struct *last;
+#ifdef CONFIG_PPC_BOOK3S_64
+        struct ppc64_tlb_batch *batch;
+#endif
 
 #ifdef CONFIG_SMP
         /* avoid complexity of lazy save/restore of fpu
@@ -513,7 +516,17 @@ struct task_struct *__switch_to(struct task_struct *prev,
                 old_thread->accum_tb += (current_tb - start_tb);
                 new_thread->start_tb = current_tb;
         }
-#endif
+#endif /* CONFIG_PPC64 */
+
+#ifdef CONFIG_PPC_BOOK3S_64
+        batch = &__get_cpu_var(ppc64_tlb_batch);
+        if (batch->active) {
+                current_thread_info()->local_flags |= _TLF_LAZY_MMU;
+                if (batch->index)
+                        __flush_tlb_pending(batch);
+                batch->active = 0;
+        }
+#endif /* CONFIG_PPC_BOOK3S_64 */
 
         local_irq_save(flags);
 
@@ -528,6 +541,14 @@ struct task_struct *__switch_to(struct task_struct *prev,
         hard_irq_disable();
         last = _switch(old_thread, new_thread);
 
+#ifdef CONFIG_PPC_BOOK3S_64
+        if (current_thread_info()->local_flags & _TLF_LAZY_MMU) {
+                current_thread_info()->local_flags &= ~_TLF_LAZY_MMU;
+                batch = &__get_cpu_var(ppc64_tlb_batch);
+                batch->active = 1;
+        }
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
         local_irq_restore(flags);
 
         return last;
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index b9150f07d266..920276c0f6a1 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -160,7 +160,7 @@ SECTIONS
                 INIT_RAM_FS
         }
 
-        PERCPU(L1_CACHE_BYTES, PAGE_SIZE)
+        PERCPU_SECTION(L1_CACHE_BYTES)
 
         . = ALIGN(8);
         .machine.desc : AT(ADDR(.machine.desc) - LOAD_OFFSET) {
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index 6a3997f98dfb..af40c8768a78 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -33,110 +33,6 @@
 
 #include "mmu_decl.h"
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
-#ifdef CONFIG_SMP
-
-/*
- * Handle batching of page table freeing on SMP. Page tables are
- * queued up and send to be freed later by RCU in order to avoid
- * freeing a page table page that is being walked without locks
- */
-
-static DEFINE_PER_CPU(struct pte_freelist_batch *, pte_freelist_cur);
-static unsigned long pte_freelist_forced_free;
-
-struct pte_freelist_batch
-{
-        struct rcu_head rcu;
-        unsigned int    index;
-        unsigned long   tables[0];
-};
-
-#define PTE_FREELIST_SIZE \
-        ((PAGE_SIZE - sizeof(struct pte_freelist_batch)) \
-          / sizeof(unsigned long))
-
-static void pte_free_smp_sync(void *arg)
-{
-        /* Do nothing, just ensure we sync with all CPUs */
-}
-
-/* This is only called when we are critically out of memory
- * (and fail to get a page in pte_free_tlb).
- */
-static void pgtable_free_now(void *table, unsigned shift)
-{
-        pte_freelist_forced_free++;
-
-        smp_call_function(pte_free_smp_sync, NULL, 1);
-
-        pgtable_free(table, shift);
-}
-
-static void pte_free_rcu_callback(struct rcu_head *head)
-{
-        struct pte_freelist_batch *batch =
-                container_of(head, struct pte_freelist_batch, rcu);
-        unsigned int i;
-
-        for (i = 0; i < batch->index; i++) {
-                void *table = (void *)(batch->tables[i] & ~MAX_PGTABLE_INDEX_SIZE);
-                unsigned shift = batch->tables[i] & MAX_PGTABLE_INDEX_SIZE;
-
-                pgtable_free(table, shift);
-        }
-
-        free_page((unsigned long)batch);
-}
-
-static void pte_free_submit(struct pte_freelist_batch *batch)
-{
-        call_rcu_sched(&batch->rcu, pte_free_rcu_callback);
-}
-
-void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift)
-{
-        /* This is safe since tlb_gather_mmu has disabled preemption */
-        struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);
-        unsigned long pgf;
-
-        if (atomic_read(&tlb->mm->mm_users) < 2 ||
-            cpumask_equal(mm_cpumask(tlb->mm), cpumask_of(smp_processor_id()))){
-                pgtable_free(table, shift);
-                return;
-        }
-
-        if (*batchp == NULL) {
-                *batchp = (struct pte_freelist_batch *)__get_free_page(GFP_ATOMIC);
-                if (*batchp == NULL) {
-                        pgtable_free_now(table, shift);
-                        return;
-                }
-                (*batchp)->index = 0;
-        }
-        BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
-        pgf = (unsigned long)table | shift;
-        (*batchp)->tables[(*batchp)->index++] = pgf;
-        if ((*batchp)->index == PTE_FREELIST_SIZE) {
-                pte_free_submit(*batchp);
-                *batchp = NULL;
-        }
-}
-
-void pte_free_finish(void)
-{
-        /* This is safe since tlb_gather_mmu has disabled preemption */
-        struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);
-
-        if (*batchp == NULL)
-                return;
-        pte_free_submit(*batchp);
-        *batchp = NULL;
-}
-
-#endif /* CONFIG_SMP */
-
 static inline int is_exec_fault(void)
 {
         return current->thread.regs && TRAP(current->thread.regs) == 0x400;
diff --git a/arch/powerpc/mm/tlb_hash32.c b/arch/powerpc/mm/tlb_hash32.c
index 690566b66e8e..27b863c14941 100644
--- a/arch/powerpc/mm/tlb_hash32.c
+++ b/arch/powerpc/mm/tlb_hash32.c
@@ -71,9 +71,6 @@ void tlb_flush(struct mmu_gather *tlb)
                  */
                 _tlbia();
         }
-
-        /* Push out batch of freed page tables */
-        pte_free_finish();
 }
 
 /*
diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c
index c14d09f614f3..31f18207970b 100644
--- a/arch/powerpc/mm/tlb_hash64.c
+++ b/arch/powerpc/mm/tlb_hash64.c
@@ -155,7 +155,7 @@ void __flush_tlb_pending(struct ppc64_tlb_batch *batch)
 
 void tlb_flush(struct mmu_gather *tlb)
 {
-        struct ppc64_tlb_batch *tlbbatch = &__get_cpu_var(ppc64_tlb_batch);
+        struct ppc64_tlb_batch *tlbbatch = &get_cpu_var(ppc64_tlb_batch);
 
         /* If there's a TLB batch pending, then we must flush it because the
          * pages are going to be freed and we really don't want to have a CPU
@@ -164,8 +164,7 @@ void tlb_flush(struct mmu_gather *tlb)
         if (tlbbatch->index)
                 __flush_tlb_pending(tlbbatch);
 
-        /* Push out batch of freed page tables */
-        pte_free_finish();
+        put_cpu_var(ppc64_tlb_batch);
 }
 
 /**
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index 2a030d89bbc6..0bdad3aecc67 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -299,9 +299,6 @@ EXPORT_SYMBOL(flush_tlb_range);
 void tlb_flush(struct mmu_gather *tlb)
 {
         flush_tlb_mm(tlb->mm);
-
-        /* Push out batch of freed page tables */
-        pte_free_finish();
 }
 
 /*