[RFC][PATCH 5/6] ia64, mm: Convert ia64 to generic tlb

[Peter Zijlstra <a.p.zijlstra@chello.nl>]

[-- Attachment #1: mm-ia64-tlb-range.patch --]
[-- Type: text/plain, Size: 8148 bytes --]

Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 arch/ia64/Kconfig           |    1 
 arch/ia64/include/asm/tlb.h |  216 ++++----------------------------------------
 2 files changed, 24 insertions(+), 193 deletions(-)

Index: linux-2.6/arch/ia64/Kconfig
===================================================================
--- linux-2.6.orig/arch/ia64/Kconfig
+++ linux-2.6/arch/ia64/Kconfig
@@ -25,6 +25,7 @@ config IA64
 	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_IRQ_PROBE
 	select GENERIC_PENDING_IRQ if SMP
+	select HAVE_MMU_GATHER_RANGE
 	select IRQ_PER_CPU
 	default y
 	help
Index: linux-2.6/arch/ia64/include/asm/tlb.h
===================================================================
--- linux-2.6.orig/arch/ia64/include/asm/tlb.h
+++ linux-2.6/arch/ia64/include/asm/tlb.h
@@ -46,77 +46,48 @@
 #include <asm/tlbflush.h>
 #include <asm/machvec.h>
 
-#ifdef CONFIG_SMP
-# define tlb_fast_mode(tlb)	((tlb)->nr == ~0U)
-#else
-# define tlb_fast_mode(tlb)	(1)
-#endif
-
-/*
- * If we can't allocate a page to make a big batch of page pointers
- * to work on, then just handle a few from the on-stack structure.
- */
-#define	IA64_GATHER_BUNDLE	8
-
-struct mmu_gather {
-	struct mm_struct	*mm;
-	unsigned int		nr;		/* == ~0U => fast mode */
-	unsigned int		max;
-	unsigned char		fullmm;		/* non-zero means full mm flush */
-	unsigned char		need_flush;	/* really unmapped some PTEs? */
-	unsigned long		start_addr;
-	unsigned long		end_addr;
-	struct page		**pages;
-	struct page		*local[IA64_GATHER_BUNDLE];
-};
-
 struct ia64_tr_entry {
-	u64 ifa;
-	u64 itir;
-	u64 pte;
-	u64 rr;
+       u64 ifa;
+       u64 itir;
+       u64 pte;
+       u64 rr;
 }; /*Record for tr entry!*/
 
 extern int ia64_itr_entry(u64 target_mask, u64 va, u64 pte, u64 log_size);
 extern void ia64_ptr_entry(u64 target_mask, int slot);
-
 extern struct ia64_tr_entry *ia64_idtrs[NR_CPUS];
 
 /*
  region register macros
 */
 #define RR_TO_VE(val)   (((val) >> 0) & 0x0000000000000001)
-#define RR_VE(val)	(((val) & 0x0000000000000001) << 0)
-#define RR_VE_MASK	0x0000000000000001L
-#define RR_VE_SHIFT	0
-#define RR_TO_PS(val)	(((val) >> 2) & 0x000000000000003f)
-#define RR_PS(val)	(((val) & 0x000000000000003f) << 2)
-#define RR_PS_MASK	0x00000000000000fcL
-#define RR_PS_SHIFT	2
-#define RR_RID_MASK	0x00000000ffffff00L
-#define RR_TO_RID(val) 	((val >> 8) & 0xffffff)
+#define RR_VE(val)     (((val) & 0x0000000000000001) << 0)
+#define RR_VE_MASK     0x0000000000000001L
+#define RR_VE_SHIFT    0
+#define RR_TO_PS(val)  (((val) >> 2) & 0x000000000000003f)
+#define RR_PS(val)     (((val) & 0x000000000000003f) << 2)
+#define RR_PS_MASK     0x00000000000000fcL
+#define RR_PS_SHIFT    2
+#define RR_RID_MASK    0x00000000ffffff00L
+#define RR_TO_RID(val)         ((val >> 8) & 0xffffff)
+
+static inline void tlb_flush(struct mmu_gather *tlb);
+
+#define __tlb_remove_tlb_entry(tlb, ptep, addr) do { } while (0)
+#define tlb_migrate_finish(mm)	platform_tlb_migrate_finish(mm)
+
+#include <asm-generic/tlb.h>
 
 /*
  * Flush the TLB for address range START to END and, if not in fast mode, release the
  * freed pages that where gathered up to this point.
  */
 static inline void
-ia64_tlb_flush_mmu (struct mmu_gather *tlb, unsigned long start, unsigned long end)
+tlb_flush(struct mmu_gather *tlb)
 {
-	unsigned int nr;
+	unsigned long start = tlb->start, end = tlb->end;
 
-	if (!tlb->need_flush)
-		return;
-	tlb->need_flush = 0;
-
-	if (tlb->fullmm) {
-		/*
-		 * Tearing down the entire address space.  This happens both as a result
-		 * of exit() and execve().  The latter case necessitates the call to
-		 * flush_tlb_mm() here.
-		 */
-		flush_tlb_mm(tlb->mm);
-	} else if (unlikely (end - start >= 1024*1024*1024*1024UL
+	if (unlikely (end - start >= 1024*1024*1024*1024UL
 			     || REGION_NUMBER(start) != REGION_NUMBER(end - 1)))
 	{
 		/*
@@ -131,147 +102,6 @@ ia64_tlb_flush_mmu (struct mmu_gather *t
 		/* now flush the virt. page-table area mapping the address range: */
 		flush_tlb_range(tlb->mm, ia64_thash(start), ia64_thash(end));
 	}
-
-	/* lastly, release the freed pages */
-	nr = tlb->nr;
-	if (!tlb_fast_mode(tlb)) {
-		unsigned long i;
-		tlb->nr = 0;
-		tlb->start_addr = ~0UL;
-		for (i = 0; i < nr; ++i)
-			free_page_and_swap_cache(tlb->pages[i]);
-	}
 }
 
-static inline void __tlb_alloc_page(struct mmu_gather *tlb)
-{
-	unsigned long addr = __get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
-
-	if (addr) {
-		tlb->pages = (void *)addr;
-		tlb->max = PAGE_SIZE / sizeof(void *);
-	}
-}
-
-
-static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
-{
-	tlb->mm = mm;
-	tlb->max = ARRAY_SIZE(tlb->local);
-	tlb->pages = tlb->local;
-	/*
-	 * Use fast mode if only 1 CPU is online.
-	 *
-	 * It would be tempting to turn on fast-mode for full_mm_flush as well.  But this
-	 * doesn't work because of speculative accesses and software prefetching: the page
-	 * table of "mm" may (and usually is) the currently active page table and even
-	 * though the kernel won't do any user-space accesses during the TLB shoot down, a
-	 * compiler might use speculation or lfetch.fault on what happens to be a valid
-	 * user-space address.  This in turn could trigger a TLB miss fault (or a VHPT
-	 * walk) and re-insert a TLB entry we just removed.  Slow mode avoids such
-	 * problems.  (We could make fast-mode work by switching the current task to a
-	 * different "mm" during the shootdown.) --davidm 08/02/2002
-	 */
-	tlb->nr = (num_online_cpus() == 1) ? ~0U : 0;
-	tlb->fullmm = full_mm_flush;
-	tlb->start_addr = ~0UL;
-}
-
-/*
- * Called at the end of the shootdown operation to free up any resources that were
- * collected.
- */
-static inline void
-tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
-{
-	/*
-	 * Note: tlb->nr may be 0 at this point, so we can't rely on tlb->start_addr and
-	 * tlb->end_addr.
-	 */
-	ia64_tlb_flush_mmu(tlb, start, end);
-
-	/* keep the page table cache within bounds */
-	check_pgt_cache();
-
-	if (tlb->pages != tlb->local)
-		free_pages((unsigned long)tlb->pages, 0);
-}
-
-/*
- * Logically, this routine frees PAGE.  On MP machines, the actual freeing of the page
- * must be delayed until after the TLB has been flushed (see comments at the beginning of
- * this file).
- */
-static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	tlb->need_flush = 1;
-
-	if (tlb_fast_mode(tlb)) {
-		free_page_and_swap_cache(page);
-		return 0;
-	}
-
-	if (!tlb->nr && tlb->pages == tlb->local)
-		__tlb_alloc_page(tlb);
-
-	tlb->pages[tlb->nr++] = page;
-	if (tlb->nr >= tlb->max)
-		return 1;
-
-	return 0;
-}
-
-static inline void tlb_flush_mmu(struct mmu_gather *tlb)
-{
-	ia64_tlb_flush_mmu(tlb, tlb->start_addr, tlb->end_addr);
-}
-
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	if (__tlb_remove_page(tlb, page))
-		tlb_flush_mmu(tlb);
-}
-
-/*
- * Remove TLB entry for PTE mapped at virtual address ADDRESS.  This is called for any
- * PTE, not just those pointing to (normal) physical memory.
- */
-static inline void
-__tlb_remove_tlb_entry (struct mmu_gather *tlb, pte_t *ptep, unsigned long address)
-{
-	if (tlb->start_addr == ~0UL)
-		tlb->start_addr = address;
-	tlb->end_addr = address + PAGE_SIZE;
-}
-
-#define tlb_migrate_finish(mm)	platform_tlb_migrate_finish(mm)
-
-#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, addr)		\
-do {							\
-	tlb->need_flush = 1;				\
-	__tlb_remove_tlb_entry(tlb, ptep, addr);	\
-} while (0)
-
-#define pte_free_tlb(tlb, ptep, address)		\
-do {							\
-	tlb->need_flush = 1;				\
-	__pte_free_tlb(tlb, ptep, address);		\
-} while (0)
-
-#define pmd_free_tlb(tlb, ptep, address)		\
-do {							\
-	tlb->need_flush = 1;				\
-	__pmd_free_tlb(tlb, ptep, address);		\
-} while (0)
-
-#define pud_free_tlb(tlb, pudp, address)		\
-do {							\
-	tlb->need_flush = 1;				\
-	__pud_free_tlb(tlb, pudp, address);		\
-} while (0)
-
 #endif /* _ASM_IA64_TLB_H */