mm, powerpc: move the RCU page-table freeing into generic code
In case other architectures require RCU freed page-tables to implement
gup_fast() and software filled hashes and similar things, provide the
means to do so by moving the logic into generic code.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Requested-by: David Miller <davem@davemloft.net>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Jeff Dike <jdike@addtoit.com>
Cc: Richard Weinberger <richard@nod.at>
Cc: Tony Luck <tony.luck@intel.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Nick Piggin <npiggin@kernel.dk>
Cc: Namhyung Kim <namhyung@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/arch/Kconfig b/arch/Kconfig
index 8d24bac..26b0e239 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -175,4 +175,7 @@
config HAVE_ARCH_MUTEX_CPU_RELAX
bool
+config HAVE_RCU_TABLE_FREE
+ bool
+
source "kernel/gcov/Kconfig"
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index a3128ca..423145a6 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -140,6 +140,7 @@
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/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h
index df1b4cb..bf301ac 100644
--- a/arch/powerpc/include/asm/pgalloc.h
+++ b/arch/powerpc/include/asm/pgalloc.h
@@ -31,14 +31,29 @@
#endif
#ifdef CONFIG_SMP
-extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift);
-extern void pte_free_finish(struct mmu_gather *tlb);
+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(struct mmu_gather *tlb) { }
#endif /* !CONFIG_SMP */
static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *ptepage,
diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index 8f0ed7a..e2b428b 100644
--- a/arch/powerpc/include/asm/tlb.h
+++ b/arch/powerpc/include/asm/tlb.h
@@ -28,16 +28,6 @@
#define tlb_start_vma(tlb, vma) do { } while (0)
#define tlb_end_vma(tlb, vma) do { } while (0)
-#define HAVE_ARCH_MMU_GATHER 1
-
-struct pte_freelist_batch;
-
-struct arch_mmu_gather {
- struct pte_freelist_batch *batch;
-};
-
-#define ARCH_MMU_GATHER_INIT (struct arch_mmu_gather){ .batch = NULL, }
-
extern void tlb_flush(struct mmu_gather *tlb);
/* Get the generic bits... */
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index 6e72788..af40c87 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -33,104 +33,6 @@
#include "mmu_decl.h"
-#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 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)
-{
- struct pte_freelist_batch **batchp = &tlb->arch.batch;
- unsigned long pgf;
-
- if (atomic_read(&tlb->mm->mm_users) < 2) {
- 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(struct mmu_gather *tlb)
-{
- struct pte_freelist_batch **batchp = &tlb->arch.batch;
-
- 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 d555cdb..27b863c 100644
--- a/arch/powerpc/mm/tlb_hash32.c
+++ b/arch/powerpc/mm/tlb_hash32.c
@@ -71,9 +71,6 @@
*/
_tlbia();
}
-
- /* Push out batch of freed page tables */
- pte_free_finish(tlb);
}
/*
diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c
index 5c94ca3..31f1820 100644
--- a/arch/powerpc/mm/tlb_hash64.c
+++ b/arch/powerpc/mm/tlb_hash64.c
@@ -165,9 +165,6 @@
__flush_tlb_pending(tlbbatch);
put_cpu_var(ppc64_tlb_batch);
-
- /* Push out batch of freed page tables */
- pte_free_finish(tlb);
}
/**
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index 8eaf67d..0bdad3a 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -299,9 +299,6 @@
void tlb_flush(struct mmu_gather *tlb)
{
flush_tlb_mm(tlb->mm);
-
- /* Push out batch of freed page tables */
- pte_free_finish(tlb);
}
/*
