[PATCH] freepgt: hugetlb_free_pgd_range

ia64 and ppc64 had hugetlb_free_pgtables functions which were no longer being
called, and it wasn't obvious what to do about them.

The ppc64 case turns out to be easy: the associated tables are noted elsewhere
and freed later, safe to either skip its hugetlb areas or go through the
motions of freeing nothing.  Since ia64 does need a special case, restore to
ppc64 the special case of skipping them.

The ia64 hugetlb case has been broken since pgd_addr_end went in, though it
probably appeared to work okay if you just had one such area; in fact it's
been broken much longer if you consider a long munmap spanning from another
region into the hugetlb region.

In the ia64 hugetlb region, more virtual address bits are available than in
the other regions, yet the page tables are structured the same way: the page
at the bottom is larger.  Here we need to scale down each addr before passing
it to the standard free_pgd_range.  Was about to write a hugely_scaled_down
macro, but found htlbpage_to_page already exists for just this purpose.  Fixed
off-by-one in ia64 is_hugepage_only_range.

Uninline free_pgd_range to make it available to ia64.  Make sure the
vma-gathering loop in free_pgtables cannot join a hugepage_only_range to any
other (safe to join huges?  probably but don't bother).

Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

5 files changed, 19 insertions, 9 deletions

diff --git a/include/asm-ia64/page.h b/include/asm-ia64/page.h
index 24aab801a8ca..08894f73abf0 100644
--- a/include/asm-ia64/page.h
+++ b/include/asm-ia64/page.h
@@ -139,7 +139,7 @@ typedef union ia64_va {
 # define HUGETLB_PAGE_ORDER     (HPAGE_SHIFT - PAGE_SHIFT)
 # define is_hugepage_only_range(mm, addr, len)          \
          (REGION_NUMBER(addr) == REGION_HPAGE &&        \
-          REGION_NUMBER((addr)+(len)) == REGION_HPAGE)
+          REGION_NUMBER((addr)+(len)-1) == REGION_HPAGE)
 extern unsigned int hpage_shift;
 #endif
 
diff --git a/include/asm-ia64/pgtable.h b/include/asm-ia64/pgtable.h
index 1757a811f436..bbf6dd757003 100644
--- a/include/asm-ia64/pgtable.h
+++ b/include/asm-ia64/pgtable.h
@@ -472,8 +472,8 @@ extern struct page *zero_page_memmap_ptr;
 #define HUGETLB_PGDIR_SIZE      (__IA64_UL(1) << HUGETLB_PGDIR_SHIFT)
 #define HUGETLB_PGDIR_MASK      (~(HUGETLB_PGDIR_SIZE-1))
 struct mmu_gather;
-extern void hugetlb_free_pgtables(struct mmu_gather *tlb,
-        struct vm_area_struct * prev, unsigned long start, unsigned long end);
+void hugetlb_free_pgd_range(struct mmu_gather **tlb, unsigned long addr,
+                unsigned long end, unsigned long floor, unsigned long ceiling);
 #endif
 
 /*
diff --git a/include/asm-ppc64/pgtable.h b/include/asm-ppc64/pgtable.h
index 4c4824653e80..33b90e2aa47d 100644
--- a/include/asm-ppc64/pgtable.h
+++ b/include/asm-ppc64/pgtable.h
@@ -500,9 +500,15 @@ extern pgd_t ioremap_dir[1024];
 
 extern void paging_init(void);
 
-struct mmu_gather;
-void hugetlb_free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *prev,
-                           unsigned long start, unsigned long end);
+/*
+ * Because the huge pgtables are only 2 level, they can take
+ * at most around 4M, much less than one hugepage which the
+ * process is presumably entitled to use.  So we don't bother
+ * freeing up the pagetables on unmap, and wait until
+ * destroy_context() to clean up the lot.
+ */
+#define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) \
+                                                do { } while (0)
 
 /*
  * This gets called at the end of handling a page fault, when
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index ae45676d27ba..6af1ae4a8211 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -37,7 +37,8 @@ extern int sysctl_hugetlb_shm_group;
 
 #ifndef ARCH_HAS_HUGEPAGE_ONLY_RANGE
 #define is_hugepage_only_range(mm, addr, len)   0
-#define hugetlb_free_pgtables(tlb, prev, start, end) do { } while (0)
+#define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) \
+                                                do { } while (0)
 #endif
 
 #ifndef ARCH_HAS_PREPARE_HUGEPAGE_RANGE
@@ -72,7 +73,8 @@ static inline unsigned long hugetlb_total_pages(void)
 #define prepare_hugepage_range(addr, len)       (-EINVAL)
 #define pmd_huge(x)     0
 #define is_hugepage_only_range(mm, addr, len)   0
-#define hugetlb_free_pgtables(tlb, prev, start, end) do { } while (0)
+#define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) \
+                                                do { } while (0)
 #define alloc_huge_page()                       ({ NULL; })
 #define free_huge_page(p)                       ({ (void)(p); BUG(); })
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 59eca28b5ae2..c74a74ca401d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -587,7 +587,9 @@ unsigned long unmap_vmas(struct mmu_gather **tlb, struct mm_struct *mm,
                 struct vm_area_struct *start_vma, unsigned long start_addr,
                 unsigned long end_addr, unsigned long *nr_accounted,
                 struct zap_details *);
-void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma,
+void free_pgd_range(struct mmu_gather **tlb, unsigned long addr,
+                unsigned long end, unsigned long floor, unsigned long ceiling);
+void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *start_vma,
                 unsigned long floor, unsigned long ceiling);
 int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
                         struct vm_area_struct *vma);