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, 44 insertions, 2 deletions

diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index d32ec643c231..afc95c7304ae 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -36,14 +36,49 @@
 #include <linux/spinlock.h>
 #include <linux/memblock.h>
 #include <linux/of_fdt.h>
+#include <linux/hugetlb.h>
 
 #include <asm/tlbflush.h>
 #include <asm/tlb.h>
 #include <asm/code-patching.h>
+#include <asm/hugetlb.h>
 
 #include "mmu_decl.h"
 
-#ifdef CONFIG_PPC_BOOK3E
+/*
+ * This struct lists the sw-supported page sizes.  The hardawre MMU may support
+ * other sizes not listed here.   The .ind field is only used on MMUs that have
+ * indirect page table entries.
+ */
+#ifdef CONFIG_PPC_BOOK3E_MMU
+#ifdef CONFIG_FSL_BOOKE
+struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
+        [MMU_PAGE_4K] = {
+                .shift  = 12,
+                .enc    = BOOK3E_PAGESZ_4K,
+        },
+        [MMU_PAGE_4M] = {
+                .shift  = 22,
+                .enc    = BOOK3E_PAGESZ_4M,
+        },
+        [MMU_PAGE_16M] = {
+                .shift  = 24,
+                .enc    = BOOK3E_PAGESZ_16M,
+        },
+        [MMU_PAGE_64M] = {
+                .shift  = 26,
+                .enc    = BOOK3E_PAGESZ_64M,
+        },
+        [MMU_PAGE_256M] = {
+                .shift  = 28,
+                .enc    = BOOK3E_PAGESZ_256M,
+        },
+        [MMU_PAGE_1G] = {
+                .shift  = 30,
+                .enc    = BOOK3E_PAGESZ_1GB,
+        },
+};
+#else
 struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
         [MMU_PAGE_4K] = {
                 .shift  = 12,
@@ -77,6 +112,8 @@ struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
                 .enc    = BOOK3E_PAGESZ_1GB,
         },
 };
+#endif /* CONFIG_FSL_BOOKE */
+
 static inline int mmu_get_tsize(int psize)
 {
         return mmu_psize_defs[psize].enc;
@@ -87,7 +124,7 @@ static inline int mmu_get_tsize(int psize)
         /* This isn't used on !Book3E for now */
         return 0;
 }
-#endif
+#endif /* CONFIG_PPC_BOOK3E_MMU */
 
 /* The variables below are currently only used on 64-bit Book3E
  * though this will probably be made common with other nohash
@@ -266,6 +303,11 @@ void __flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
 
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
 {
+#ifdef CONFIG_HUGETLB_PAGE
+        if (is_vm_hugetlb_page(vma))
+                flush_hugetlb_page(vma, vmaddr);
+#endif
+
         __flush_tlb_page(vma ? vma->vm_mm : NULL, vmaddr,
                          mmu_get_tsize(mmu_virtual_psize), 0);
 }