sparc: mmu_gather rework

Rework the sparc mmu_gather usage to conform to the new world order :-)

Sparc mmu_gather does two things:
 - tracks vaddrs to unhash
 - tracks pages to free

Split these two things like powerpc has done and keep the vaddrs
in per-cpu data structures and flush them on context switch.

The remaining bits can then use the generic mmu_gather.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-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>

4 files changed, 31 insertions, 90 deletions

diff --git a/arch/sparc/include/asm/pgalloc_64.h b/arch/sparc/include/asm/pgalloc_64.h
index 5bdfa2c..4e5e087 100644
--- a/arch/sparc/include/asm/pgalloc_64.h
+++ b/arch/sparc/include/asm/pgalloc_64.h
@@ -78,4 +78,7 @@ static inline void check_pgt_cache(void)
 	quicklist_trim(0, NULL, 25, 16);
 }
 
+#define __pte_free_tlb(tlb, pte, addr)	pte_free((tlb)->mm, pte)
+#define __pmd_free_tlb(tlb, pmd, addr)	pmd_free((tlb)->mm, pmd)
+
 #endif /* _SPARC64_PGALLOC_H */
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index b77128c..1e03c5a 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -655,9 +655,11 @@ static inline int pte_special(pte_t pte)
 #define pte_unmap(pte)			do { } while (0)
 
 /* Actual page table PTE updates.  */
-extern void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr, pte_t *ptep, pte_t orig);
+extern void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
+			  pte_t *ptep, pte_t orig, int fullmm);
 
-static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte)
+static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
+			     pte_t *ptep, pte_t pte, int fullmm)
 {
 	pte_t orig = *ptep;
 
@@ -670,12 +672,19 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *p
 	 *             and SUN4V pte layout, so this inline test is fine.
 	 */
 	if (likely(mm != &init_mm) && (pte_val(orig) & _PAGE_VALID))
-		tlb_batch_add(mm, addr, ptep, orig);
+		tlb_batch_add(mm, addr, ptep, orig, fullmm);
 }
 
+#define set_pte_at(mm,addr,ptep,pte)	\
+	__set_pte_at((mm), (addr), (ptep), (pte), 0)
+
 #define pte_clear(mm,addr,ptep)		\
 	set_pte_at((mm), (addr), (ptep), __pte(0UL))
 
+#define __HAVE_ARCH_PTE_CLEAR_NOT_PRESENT_FULL
+#define pte_clear_not_present_full(mm,addr,ptep,fullmm)	\
+	__set_pte_at((mm), (addr), (ptep), __pte(0UL), (fullmm))
+
 #ifdef DCACHE_ALIASING_POSSIBLE
 #define __HAVE_ARCH_MOVE_PTE
 #define move_pte(pte, prot, old_addr, new_addr)				\
diff --git a/arch/sparc/include/asm/tlb_64.h b/arch/sparc/include/asm/tlb_64.h
index dca406b..190e189 100644
--- a/arch/sparc/include/asm/tlb_64.h
+++ b/arch/sparc/include/asm/tlb_64.h
@@ -7,66 +7,11 @@
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
 
-#define TLB_BATCH_NR	192
-
-/*
- * For UP we don't need to worry about TLB flush
- * and page free order so much..
- */
-#ifdef CONFIG_SMP
-  #define FREE_PTE_NR	506
-  #define tlb_fast_mode(bp) ((bp)->pages_nr == ~0U)
-#else
-  #define FREE_PTE_NR	1
-  #define tlb_fast_mode(bp) 1
-#endif
-
-struct mmu_gather {
-	struct mm_struct *mm;
-	unsigned int pages_nr;
-	unsigned int need_flush;
-	unsigned int fullmm;
-	unsigned int tlb_nr;
-	unsigned long vaddrs[TLB_BATCH_NR];
-	struct page *pages[FREE_PTE_NR];
-};
-
-DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 #ifdef CONFIG_SMP
 extern void smp_flush_tlb_pending(struct mm_struct *,
 				  unsigned long, unsigned long *);
 #endif
 
-extern void __flush_tlb_pending(unsigned long, unsigned long, unsigned long *);
-extern void flush_tlb_pending(void);
-
-static inline struct mmu_gather *tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush)
-{
-	struct mmu_gather *mp = &get_cpu_var(mmu_gathers);
-
-	BUG_ON(mp->tlb_nr);
-
-	mp->mm = mm;
-	mp->pages_nr = num_online_cpus() > 1 ? 0U : ~0U;
-	mp->fullmm = full_mm_flush;
-
-	return mp;
-}
-
-
-static inline void tlb_flush_mmu(struct mmu_gather *mp)
-{
-	if (!mp->fullmm)
-		flush_tlb_pending();
-	if (mp->need_flush) {
-		free_pages_and_swap_cache(mp->pages, mp->pages_nr);
-		mp->pages_nr = 0;
-		mp->need_flush = 0;
-	}
-
-}
-
 #ifdef CONFIG_SMP
 extern void smp_flush_tlb_mm(struct mm_struct *mm);
 #define do_flush_tlb_mm(mm) smp_flush_tlb_mm(mm)
@@ -74,38 +19,14 @@ extern void smp_flush_tlb_mm(struct mm_struct *mm);
 #define do_flush_tlb_mm(mm) __flush_tlb_mm(CTX_HWBITS(mm->context), SECONDARY_CONTEXT)
 #endif
 
-static inline void tlb_finish_mmu(struct mmu_gather *mp, unsigned long start, unsigned long end)
-{
-	tlb_flush_mmu(mp);
-
-	if (mp->fullmm)
-		mp->fullmm = 0;
-
-	/* keep the page table cache within bounds */
-	check_pgt_cache();
-
-	put_cpu_var(mmu_gathers);
-}
-
-static inline void tlb_remove_page(struct mmu_gather *mp, struct page *page)
-{
-	if (tlb_fast_mode(mp)) {
-		free_page_and_swap_cache(page);
-		return;
-	}
-	mp->need_flush = 1;
-	mp->pages[mp->pages_nr++] = page;
-	if (mp->pages_nr >= FREE_PTE_NR)
-		tlb_flush_mmu(mp);
-}
-
-#define tlb_remove_tlb_entry(mp,ptep,addr) do { } while (0)
-#define pte_free_tlb(mp, ptepage, addr) pte_free((mp)->mm, ptepage)
-#define pmd_free_tlb(mp, pmdp, addr) pmd_free((mp)->mm, pmdp)
-#define pud_free_tlb(tlb,pudp, addr) __pud_free_tlb(tlb,pudp,addr)
+extern void __flush_tlb_pending(unsigned long, unsigned long, unsigned long *);
+extern void flush_tlb_pending(void);
 
-#define tlb_migrate_finish(mm)	do { } while (0)
 #define tlb_start_vma(tlb, vma) do { } while (0)
 #define tlb_end_vma(tlb, vma)	do { } while (0)
+#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
+#define tlb_flush(tlb)	flush_tlb_pending()
+
+#include <asm-generic/tlb.h>
 
 #endif /* _SPARC64_TLB_H */
diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h
index fbb675d..2ef4634 100644
--- a/arch/sparc/include/asm/tlbflush_64.h
+++ b/arch/sparc/include/asm/tlbflush_64.h
@@ -5,9 +5,17 @@
 #include <asm/mmu_context.h>
 
 /* TSB flush operations. */
-struct mmu_gather;
+
+#define TLB_BATCH_NR	192
+
+struct tlb_batch {
+	struct mm_struct *mm;
+	unsigned long tlb_nr;
+	unsigned long vaddrs[TLB_BATCH_NR];
+};
+
 extern void flush_tsb_kernel_range(unsigned long start, unsigned long end);
-extern void flush_tsb_user(struct mmu_gather *mp);
+extern void flush_tsb_user(struct tlb_batch *tb);
 
 /* TLB flush operations. */