hugetlb: modular state for hugetlb page size

The goal of this patchset is to support multiple hugetlb page sizes.  This
is achieved by introducing a new struct hstate structure, which
encapsulates the important hugetlb state and constants (eg.  huge page
size, number of huge pages currently allocated, etc).

The hstate structure is then passed around the code which requires these
fields, they will do the right thing regardless of the exact hstate they
are operating on.

This patch adds the hstate structure, with a single global instance of it
(default_hstate), and does the basic work of converting hugetlb to use the
hstate.

Future patches will add more hstate structures to allow for different
hugetlbfs mounts to have different page sizes.

[akpm@linux-foundation.org: coding-style fixes]
Acked-by: Adam Litke <agl@us.ibm.com>
Acked-by: Nishanth Aravamudan <nacc@us.ibm.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

7 files changed, 98 insertions, 13 deletions

diff --git a/include/asm-ia64/hugetlb.h b/include/asm-ia64/hugetlb.h
index e9d1e5e2382..da55c63728e 100644
--- a/include/asm-ia64/hugetlb.h
+++ b/include/asm-ia64/hugetlb.h
@@ -8,7 +8,8 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 			    unsigned long end, unsigned long floor,
 			    unsigned long ceiling);
 
-int prepare_hugepage_range(unsigned long addr, unsigned long len);
+int prepare_hugepage_range(struct file *file,
+			unsigned long addr, unsigned long len);
 
 static inline int is_hugepage_only_range(struct mm_struct *mm,
 					 unsigned long addr,
diff --git a/include/asm-powerpc/hugetlb.h b/include/asm-powerpc/hugetlb.h
index 0a37aa5ecaa..ca37c4af27b 100644
--- a/include/asm-powerpc/hugetlb.h
+++ b/include/asm-powerpc/hugetlb.h
@@ -21,7 +21,8 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
  * If the arch doesn't supply something else, assume that hugepage
  * size aligned regions are ok without further preparation.
  */
-static inline int prepare_hugepage_range(unsigned long addr, unsigned long len)
+static inline int prepare_hugepage_range(struct file *file,
+			unsigned long addr, unsigned long len)
 {
 	if (len & ~HPAGE_MASK)
 		return -EINVAL;
diff --git a/include/asm-s390/hugetlb.h b/include/asm-s390/hugetlb.h
index 600a776f8f7..670a1d1745d 100644
--- a/include/asm-s390/hugetlb.h
+++ b/include/asm-s390/hugetlb.h
@@ -22,7 +22,8 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
  * If the arch doesn't supply something else, assume that hugepage
  * size aligned regions are ok without further preparation.
  */
-static inline int prepare_hugepage_range(unsigned long addr, unsigned long len)
+static inline int prepare_hugepage_range(struct file *file,
+			unsigned long addr, unsigned long len)
 {
 	if (len & ~HPAGE_MASK)
 		return -EINVAL;
diff --git a/include/asm-sh/hugetlb.h b/include/asm-sh/hugetlb.h
index fb30018938c..967068fb79a 100644
--- a/include/asm-sh/hugetlb.h
+++ b/include/asm-sh/hugetlb.h
@@ -14,7 +14,8 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
  * If the arch doesn't supply something else, assume that hugepage
  * size aligned regions are ok without further preparation.
  */
-static inline int prepare_hugepage_range(unsigned long addr, unsigned long len)
+static inline int prepare_hugepage_range(struct file *file,
+			unsigned long addr, unsigned long len)
 {
 	if (len & ~HPAGE_MASK)
 		return -EINVAL;
diff --git a/include/asm-sparc/hugetlb.h b/include/asm-sparc/hugetlb.h
index aeb92374ca3..177061064ee 100644
--- a/include/asm-sparc/hugetlb.h
+++ b/include/asm-sparc/hugetlb.h
@@ -22,7 +22,8 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
  * If the arch doesn't supply something else, assume that hugepage
  * size aligned regions are ok without further preparation.
  */
-static inline int prepare_hugepage_range(unsigned long addr, unsigned long len)
+static inline int prepare_hugepage_range(struct file *file,
+			unsigned long addr, unsigned long len)
 {
 	if (len & ~HPAGE_MASK)
 		return -EINVAL;
diff --git a/include/asm-x86/hugetlb.h b/include/asm-x86/hugetlb.h
index 7eed6e0883b..439a9acc132 100644
--- a/include/asm-x86/hugetlb.h
+++ b/include/asm-x86/hugetlb.h
@@ -14,11 +14,13 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
  * If the arch doesn't supply something else, assume that hugepage
  * size aligned regions are ok without further preparation.
  */
-static inline int prepare_hugepage_range(unsigned long addr, unsigned long len)
+static inline int prepare_hugepage_range(struct file *file,
+			unsigned long addr, unsigned long len)
 {
-	if (len & ~HPAGE_MASK)
+	struct hstate *h = hstate_file(file);
+	if (len & ~huge_page_mask(h))
 		return -EINVAL;
-	if (addr & ~HPAGE_MASK)
+	if (addr & ~huge_page_mask(h))
 		return -EINVAL;
 	return 0;
 }
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index abbc187193a..ad2271e11f9 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -8,7 +8,6 @@
 #include <linux/mempolicy.h>
 #include <linux/shm.h>
 #include <asm/tlbflush.h>
-#include <asm/hugetlb.h>
 
 struct ctl_table;
 
@@ -45,7 +44,8 @@ extern int sysctl_hugetlb_shm_group;
 
 /* arch callbacks */
 
-pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr);
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+			unsigned long addr, unsigned long sz);
 pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr);
 int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep);
 struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
@@ -80,7 +80,7 @@ static inline unsigned long hugetlb_total_pages(void)
 #define hugetlb_report_meminfo(buf)		0
 #define hugetlb_report_node_meminfo(n, buf)	0
 #define follow_huge_pmd(mm, addr, pmd, write)	NULL
-#define prepare_hugepage_range(addr,len)	(-EINVAL)
+#define prepare_hugepage_range(file, addr, len)	(-EINVAL)
 #define pmd_huge(x)	0
 #define is_hugepage_only_range(mm, addr, len)	0
 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; })
@@ -134,8 +134,6 @@ struct file *hugetlb_file_setup(const char *name, size_t);
 int hugetlb_get_quota(struct address_space *mapping, long delta);
 void hugetlb_put_quota(struct address_space *mapping, long delta);
 
-#define BLOCKS_PER_HUGEPAGE	(HPAGE_SIZE / 512)
-
 static inline int is_file_hugepages(struct file *file)
 {
 	if (file->f_op == &hugetlbfs_file_operations)
@@ -164,4 +162,84 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 					unsigned long flags);
 #endif /* HAVE_ARCH_HUGETLB_UNMAPPED_AREA */
 
+#ifdef CONFIG_HUGETLB_PAGE
+
+/* Defines one hugetlb page size */
+struct hstate {
+	int hugetlb_next_nid;
+	unsigned int order;
+	unsigned long mask;
+	unsigned long max_huge_pages;
+	unsigned long nr_huge_pages;
+	unsigned long free_huge_pages;
+	unsigned long resv_huge_pages;
+	unsigned long surplus_huge_pages;
+	unsigned long nr_overcommit_huge_pages;
+	struct list_head hugepage_freelists[MAX_NUMNODES];
+	unsigned int nr_huge_pages_node[MAX_NUMNODES];
+	unsigned int free_huge_pages_node[MAX_NUMNODES];
+	unsigned int surplus_huge_pages_node[MAX_NUMNODES];
+};
+
+extern struct hstate default_hstate;
+
+static inline struct hstate *hstate_vma(struct vm_area_struct *vma)
+{
+	return &default_hstate;
+}
+
+static inline struct hstate *hstate_file(struct file *f)
+{
+	return &default_hstate;
+}
+
+static inline struct hstate *hstate_inode(struct inode *i)
+{
+	return &default_hstate;
+}
+
+static inline unsigned long huge_page_size(struct hstate *h)
+{
+	return (unsigned long)PAGE_SIZE << h->order;
+}
+
+static inline unsigned long huge_page_mask(struct hstate *h)
+{
+	return h->mask;
+}
+
+static inline unsigned int huge_page_order(struct hstate *h)
+{
+	return h->order;
+}
+
+static inline unsigned huge_page_shift(struct hstate *h)
+{
+	return h->order + PAGE_SHIFT;
+}
+
+static inline unsigned int pages_per_huge_page(struct hstate *h)
+{
+	return 1 << h->order;
+}
+
+static inline unsigned int blocks_per_huge_page(struct hstate *h)
+{
+	return huge_page_size(h) / 512;
+}
+
+#include <asm/hugetlb.h>
+
+#else
+struct hstate {};
+#define hstate_file(f) NULL
+#define hstate_vma(v) NULL
+#define hstate_inode(i) NULL
+#define huge_page_size(h) PAGE_SIZE
+#define huge_page_mask(h) PAGE_MASK
+#define huge_page_order(h) 0
+#define huge_page_shift(h) PAGE_SHIFT
+#define pages_per_huge_page(h) 1
+#endif
+
 #endif /* _LINUX_HUGETLB_H */