mm, hugetlb: convert hugetlbfs to use split pmd lock

Hugetlb supports multiple page sizes. We use split lock only for PMD
level, but not for PUD.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: Alex Thorlton <athorlton@sgi.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Dave Jones <davej@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Robin Holt <robinmholt@gmail.com>
Cc: Sedat Dilek <sedat.dilek@gmail.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

fs/proc/meminfo.c

 #include <linux/fs.h>
-#include <linux/hugetlb.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
+#include <linux/hugetlb.h>
 #include <linux/mman.h>
 #include <linux/mmzone.h>
 #include <linux/proc_fs.h>

include/linux/hugetlb.h

@@ -392,6 +392,15 @@ static inline int hugepage_migration_support(struct hstate *h)
 	return pmd_huge_support() && (huge_page_shift(h) == PMD_SHIFT);
 }
 
+static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
+					   struct mm_struct *mm, pte_t *pte)
+{
+	if (huge_page_size(h) == PMD_SIZE)
+		return pmd_lockptr(mm, (pmd_t *) pte);
+	VM_BUG_ON(huge_page_size(h) == PAGE_SIZE);
+	return &mm->page_table_lock;
+}
+
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 #define alloc_huge_page_node(h, nid) NULL
@@ -401,6 +410,7 @@ struct hstate {};
 #define hstate_sizelog(s) NULL
 #define hstate_vma(v) NULL
 #define hstate_inode(i) NULL
+#define page_hstate(page) NULL
 #define huge_page_size(h) PAGE_SIZE
 #define huge_page_mask(h) PAGE_MASK
 #define vma_kernel_pagesize(v) PAGE_SIZE
@@ -421,6 +431,22 @@ static inline pgoff_t basepage_index(struct page *page)
 #define dissolve_free_huge_pages(s, e)	do {} while (0)
 #define pmd_huge_support()	0
 #define hugepage_migration_support(h)	0
+
+static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
+					   struct mm_struct *mm, pte_t *pte)
+{
+	return &mm->page_table_lock;
+}
 #endif	/* CONFIG_HUGETLB_PAGE */
 
+static inline spinlock_t *huge_pte_lock(struct hstate *h,
+					struct mm_struct *mm, pte_t *pte)
+{
+	spinlock_t *ptl;
+
+	ptl = huge_pte_lockptr(h, mm, pte);
+	spin_lock(ptl);
+	return ptl;
+}
+
 #endif /* _LINUX_HUGETLB_H */

include/linux/swapops.h

@@ -139,7 +139,8 @@ static inline void make_migration_entry_read(swp_entry_t *entry)
 
 extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 					unsigned long address);
-extern void migration_entry_wait_huge(struct mm_struct *mm, pte_t *pte);
+extern void migration_entry_wait_huge(struct vm_area_struct *vma,
+		struct mm_struct *mm, pte_t *pte);
 #else
 
 #define make_migration_entry(page, write) swp_entry(0, 0)
@@ -151,8 +152,8 @@ static inline int is_migration_entry(swp_entry_t swp)
 static inline void make_migration_entry_read(swp_entry_t *entryp) { }
 static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 					 unsigned long address) { }
-static inline void migration_entry_wait_huge(struct mm_struct *mm,
-					pte_t *pte) { }
+static inline void migration_entry_wait_huge(struct vm_area_struct *vma,
+		struct mm_struct *mm, pte_t *pte) { }
 static inline int is_write_migration_entry(swp_entry_t entry)
 {
 	return 0;

mm/mempolicy.c

@@ -525,8 +525,9 @@ static void queue_pages_hugetlb_pmd_range(struct vm_area_struct *vma,
 #ifdef CONFIG_HUGETLB_PAGE
 	int nid;
 	struct page *page;
+	spinlock_t *ptl;
 
-	spin_lock(&vma->vm_mm->page_table_lock);
+	ptl = huge_pte_lock(hstate_vma(vma), vma->vm_mm, (pte_t *)pmd);
 	page = pte_page(huge_ptep_get((pte_t *)pmd));
 	nid = page_to_nid(page);
 	if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT))
@@ -536,7 +537,7 @@ static void queue_pages_hugetlb_pmd_range(struct vm_area_struct *vma,
 	    (flags & MPOL_MF_MOVE && page_mapcount(page) == 1))
 		isolate_huge_page(page, private);
 unlock:
-	spin_unlock(&vma->vm_mm->page_table_lock);
+	spin_unlock(ptl);
 #else
 	BUG();
 #endif

mm/migrate.c

@@ -130,7 +130,7 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
 		ptep = huge_pte_offset(mm, addr);
 		if (!ptep)
 			goto out;
-		ptl = &mm->page_table_lock;
+		ptl = huge_pte_lockptr(hstate_vma(vma), mm, ptep);
 	} else {
 		pmd = mm_find_pmd(mm, addr);
 		if (!pmd)
@@ -249,9 +249,10 @@ void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 	__migration_entry_wait(mm, ptep, ptl);
 }
 
-void migration_entry_wait_huge(struct mm_struct *mm, pte_t *pte)
+void migration_entry_wait_huge(struct vm_area_struct *vma,
+		struct mm_struct *mm, pte_t *pte)
 {
-	spinlock_t *ptl = &(mm)->page_table_lock;
+	spinlock_t *ptl = huge_pte_lockptr(hstate_vma(vma), mm, pte);
 	__migration_entry_wait(mm, pte, ptl);
 }
 

mm/rmap.c

@@ -601,7 +601,7 @@ pte_t *__page_check_address(struct page *page, struct mm_struct *mm,
 
 	if (unlikely(PageHuge(page))) {
 		pte = huge_pte_offset(mm, address);
-		ptl = &mm->page_table_lock;
+		ptl = huge_pte_lockptr(page_hstate(page), mm, pte);
 		goto check;
 	}