powerpc: Hugetlb for BookE

Enable hugepages on Freescale BookE processors.  This allows the kernel to
use huge TLB entries to map pages, which can greatly reduce the number of
TLB misses and the amount of TLB thrashing experienced by applications with
large memory footprints.  Care should be taken when using this on FSL
processors, as the number of large TLB entries supported by the core is low
(16-64) on current processors.

The supported set of hugepage sizes include 4m, 16m, 64m, 256m, and 1g.
Page sizes larger than the max zone size are called "gigantic" pages and
must be allocated on the command line (and cannot be deallocated).

This is currently only fully implemented for Freescale 32-bit BookE
processors, but there is some infrastructure in the code for
64-bit BooKE.

Signed-off-by: Becky Bruce <beckyb@kernel.crashing.org>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

1 files changed, 61 insertions, 2 deletions

diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index 5856a66ab404..86004930a78e 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -1,15 +1,60 @@
 #ifndef _ASM_POWERPC_HUGETLB_H
 #define _ASM_POWERPC_HUGETLB_H
 
+#ifdef CONFIG_HUGETLB_PAGE
 #include <asm/page.h>
 
+extern struct kmem_cache *hugepte_cache;
+extern void __init reserve_hugetlb_gpages(void);
+
+static inline pte_t *hugepd_page(hugepd_t hpd)
+{
+	BUG_ON(!hugepd_ok(hpd));
+	return (pte_t *)((hpd.pd & ~HUGEPD_SHIFT_MASK) | PD_HUGE);
+}
+
+static inline unsigned int hugepd_shift(hugepd_t hpd)
+{
+	return hpd.pd & HUGEPD_SHIFT_MASK;
+}
+
+static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr,
+				    unsigned pdshift)
+{
+	/*
+	 * On 32-bit, we have multiple higher-level table entries that point to
+	 * the same hugepte.  Just use the first one since they're all
+	 * identical.  So for that case, idx=0.
+	 */
+	unsigned long idx = 0;
+
+	pte_t *dir = hugepd_page(*hpdp);
+#ifdef CONFIG_PPC64
+	idx = (addr & ((1UL << pdshift) - 1)) >> hugepd_shift(*hpdp);
+#endif
+
+	return dir + idx;
+}
+
 pte_t *huge_pte_offset_and_shift(struct mm_struct *mm,
 				 unsigned long addr, unsigned *shift);
 
 void flush_dcache_icache_hugepage(struct page *page);
 
+#if defined(CONFIG_PPC_MM_SLICES) || defined(CONFIG_PPC_SUBPAGE_PROT)
 int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
 			   unsigned long len);
+#else
+static inline int is_hugepage_only_range(struct mm_struct *mm,
+					 unsigned long addr,
+					 unsigned long len)
+{
+	return 0;
+}
+#endif
+
+void book3e_hugetlb_preload(struct mm_struct *mm, unsigned long ea, pte_t pte);
+void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
 
 void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 			    unsigned long end, unsigned long floor,
@@ -50,8 +95,11 @@ static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 					    unsigned long addr, pte_t *ptep)
 {
-	unsigned long old = pte_update(mm, addr, ptep, ~0UL, 1);
-	return __pte(old);
+#ifdef CONFIG_PPC64
+	return __pte(pte_update(mm, addr, ptep, ~0UL, 1));
+#else
+	return __pte(pte_update(ptep, ~0UL, 0));
+#endif
 }
 
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
@@ -93,4 +141,15 @@ static inline void arch_release_hugepage(struct page *page)
 {
 }
 
+#else /* ! CONFIG_HUGETLB_PAGE */
+static inline void reserve_hugetlb_gpages(void)
+{
+	pr_err("Cannot reserve gpages without hugetlb enabled\n");
+}
+static inline void flush_hugetlb_page(struct vm_area_struct *vma,
+				      unsigned long vmaddr)
+{
+}
+#endif
+
 #endif /* _ASM_POWERPC_HUGETLB_H */