Demand faulting for hugetlb

diff -upN reference/mm/hugetlb.c current/mm/hugetlb.c
@@ -392,57 +392,3 @@ out:
 	spin_unlock(&mm->page_table_lock);
 	return ret;
 }
-
-int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
-			struct page **pages, struct vm_area_struct **vmas,
-			unsigned long *position, int *length, int i)
-{
-	unsigned long vpfn, vaddr = *position;
-	int remainder = *length;
-
-	BUG_ON(!is_vm_hugetlb_page(vma));
-
-	vpfn = vaddr/PAGE_SIZE;
-	spin_lock(&mm->page_table_lock);
-	while (vaddr < vma->vm_end && remainder) {
-
-		if (pages) {
-			pte_t *pte;
-			struct page *page;
-
-			/* Some archs (sparc64, sh*) have multiple
-			 * pte_ts to each hugepage.  We have to make
-			 * sure we get the first, for the page
-			 * indexing below to work. */
-			pte = huge_pte_offset(mm, vaddr & HPAGE_MASK);
-
-			/* the hugetlb file might have been truncated */
-			if (!pte || pte_none(*pte)) {
-				remainder = 0;
-				if (!i)
-					i = -EFAULT;
-				break;
-			}
-
-			page = &pte_page(*pte)[vpfn % (HPAGE_SIZE/PAGE_SIZE)];
-
-			WARN_ON(!PageCompound(page));
-
-			get_page(page);
-			pages[i] = page;
-		}
-
-		if (vmas)
-			vmas[i] = vma;
-
-		vaddr += PAGE_SIZE;
-		++vpfn;
-		--remainder;
-		++i;
-	}
-	spin_unlock(&mm->page_table_lock);
-	*length = remainder;
-	*position = vaddr;
-
-	return i;
-}

diff -upN reference/mm/memory.c current/mm/memory.c
@@ -971,11 +971,6 @@ int get_user_pages(struct task_struct *t
 				|| !(flags & vma->vm_flags))
 			return i ? : -EFAULT;
 
-		if (is_vm_hugetlb_page(vma)) {
-			i = follow_hugetlb_page(mm, vma, pages, vmas,
-						&start, &len, i);
-			continue;
-		}
 		spin_lock(&mm->page_table_lock);
 		do {
 			int write_access = write;

diff -upN reference/fs/hugetlbfs/inode.c current/fs/hugetlbfs/inode.c
@@ -45,9 +45,67 @@ static struct backing_dev_info hugetlbfs
 
 int sysctl_hugetlb_shm_group;
 
+static void huge_pagevec_release(struct pagevec *pvec)
+{
+	int i;
+
+	for (i = 0; i < pagevec_count(pvec); ++i)
+		put_page(pvec->pages[i]);
+
+	pagevec_reinit(pvec);
+}
+
+/*
+ * huge_pages_needed tries to determine the number of new huge pages that
+ * will be required to fully populate this VMA.  This will be equal to
+ * the size of the VMA in huge pages minus the number of huge pages 
+ * (covered by this VMA) that are found in the page cache.
+ *
+ * Result is in bytes to be compatible with is_hugepage_mem_enough()
+ */
+unsigned long
+huge_pages_needed(struct address_space *mapping, struct vm_area_struct *vma)
+{
+	int i;
+	struct pagevec pvec;
+	unsigned long start = vma->vm_start;
+	unsigned long end = vma->vm_end;
+	unsigned long hugepages = (end - start) >> HPAGE_SHIFT;
+	pgoff_t next = vma->vm_pgoff;
+	pgoff_t endpg = next + ((end - start) >> PAGE_SHIFT);
+	struct inode *inode = vma->vm_file->f_dentry->d_inode;
+
+	/*
+	 * Shared memory segments are accounted for at shget time,
+	 * not at shmat (when the mapping is actually created) so 
+	 * check here if the memory has already been accounted for.
+	 */
+	if (inode->i_blocks != 0)
+		return 0;
+
+	pagevec_init(&pvec, 0);
+	while (next < endpg) {
+		if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE))
+			break;
+		for (i = 0; i < pagevec_count(&pvec); i++) {
+			struct page *page = pvec.pages[i];
+			if (page->index > next)
+				next = page->index;
+			if (page->index >= endpg)
+				break;
+			next++;
+			hugepages--;
+		}
+		huge_pagevec_release(&pvec);
+	}
+	return hugepages << HPAGE_SHIFT;
+}
+
 static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct inode *inode = file->f_dentry->d_inode;
+	struct address_space *mapping = inode->i_mapping;
+	unsigned long bytes;
 	loff_t len, vma_len;
 	int ret;
 

@@ -66,6 +124,10 @@ static int hugetlbfs_file_mmap(struct fi
 	if (vma->vm_end - vma->vm_start < HPAGE_SIZE)
 		return -EINVAL;
 
+	bytes = huge_pages_needed(mapping, vma);
+	if (!is_hugepage_mem_enough(bytes))
+		return -ENOMEM;
+
 	vma_len = (loff_t)(vma->vm_end - vma->vm_start);
 
 	down(&inode->i_sem);

@@ -167,16 +229,6 @@ static int hugetlbfs_commit_write(struct
 	return -EINVAL;
 }
 
-static void huge_pagevec_release(struct pagevec *pvec)
-{
-	int i;
-
-	for (i = 0; i < pagevec_count(pvec); ++i)
-		put_page(pvec->pages[i]);
-
-	pagevec_reinit(pvec);
-}
-
 static void truncate_huge_page(struct page *page)
 {
 	clear_page_dirty(page);

@@ -792,6 +844,7 @@ struct file *hugetlb_zero_setup(size_t s
 	d_instantiate(dentry, inode);
 	inode->i_size = size;
 	inode->i_nlink = 0;
+	inode->i_blocks = 1;
 	file->f_vfsmnt = mntget(hugetlbfs_vfsmount);
 	file->f_dentry = dentry;
 	file->f_mapping = inode->i_mapping;

diff -upN reference/fs/hugetlbfs/inode.c current/fs/hugetlbfs/inode.c
@@ -48,7 +48,6 @@ int sysctl_hugetlb_shm_group;
 static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct inode *inode = file->f_dentry->d_inode;
-	struct address_space *mapping = inode->i_mapping;
 	loff_t len, vma_len;
 	int ret;
 

@@ -79,10 +78,7 @@ static int hugetlbfs_file_mmap(struct fi
 	if (!(vma->vm_flags & VM_WRITE) && len > inode->i_size)
 		goto out;
 
-	ret = hugetlb_prefault(mapping, vma);
-	if (ret)
-		goto out;
-
+	ret = 0;
 	if (inode->i_size < len)
 		inode->i_size = len;
 out:

diff -upN reference/include/linux/hugetlb.h current/include/linux/hugetlb.h
@@ -25,6 +25,8 @@ int is_hugepage_mem_enough(size_t);
 unsigned long hugetlb_total_pages(void);
 struct page *alloc_huge_page(void);
 void free_huge_page(struct page *);
+int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct * vma,
+			unsigned long address, int write_access);
 
 extern unsigned long max_huge_pages;
 extern const unsigned long hugetlb_zero, hugetlb_infinity;

160 lines not on this page · raw message

diff -upN reference/mm/memory.c current/mm/memory.c
@@ -2040,7 +2040,7 @@ int __handle_mm_fault(struct mm_struct *
 	inc_page_state(pgfault);
 
 	if (is_vm_hugetlb_page(vma))
-		return VM_FAULT_SIGBUS;	/* mapping truncation does this. */
+		return hugetlb_fault(mm, vma, address, write_access);
 
 	/*
 	 * We need the page table lock to synchronize with kswapd

Index: working-2.6/fs/hugetlbfs/inode.c
===================================================================
@@ -48,7 +48,6 @@
 static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct inode *inode = file->f_dentry->d_inode;
-	struct address_space *mapping = inode->i_mapping;
 	loff_t len, vma_len;
 	int ret;
 

@@ -79,10 +78,7 @@
 	if (!(vma->vm_flags & VM_WRITE) && len > inode->i_size)
 		goto out;
 
-	ret = hugetlb_prefault(mapping, vma);
-	if (ret)
-		goto out;
-
+	ret = 0;
 	if (inode->i_size < len)
 		inode->i_size = len;
 out:

Index: working-2.6/include/linux/hugetlb.h
===================================================================
@@ -25,6 +25,8 @@
 unsigned long hugetlb_total_pages(void);
 struct page *alloc_huge_page(void);
 void free_huge_page(struct page *);
+int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct * vma,
+			unsigned long address, int write_access);
 
 extern unsigned long max_huge_pages;
 extern const unsigned long hugetlb_zero, hugetlb_infinity;

179 lines not on this page · raw message

Index: working-2.6/mm/memory.c
===================================================================
@@ -2040,7 +2040,7 @@
 	inc_page_state(pgfault);
 
 	if (is_vm_hugetlb_page(vma))
-		return VM_FAULT_SIGBUS;	/* mapping truncation does this. */
+		return hugetlb_fault(mm, vma, address, write_access);
 
 	/*
 	 * We need the page table lock to synchronize with kswapd

Index: working-2.6/fs/hugetlbfs/inode.c
===================================================================
@@ -48,7 +48,6 @@
 static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct inode *inode = file->f_dentry->d_inode;
-	struct address_space *mapping = inode->i_mapping;
 	loff_t len, vma_len;
 	int ret;
 

@@ -79,10 +78,7 @@
 	if (!(vma->vm_flags & VM_WRITE) && len > inode->i_size)
 		goto out;
 
-	ret = hugetlb_prefault(mapping, vma);
-	if (ret)
-		goto out;
-
+	ret = 0;
 	if (inode->i_size < len)
 		inode->i_size = len;
 out:

Index: working-2.6/include/linux/hugetlb.h
===================================================================
@@ -25,6 +25,8 @@
 unsigned long hugetlb_total_pages(void);
 struct page *alloc_huge_page(void);
 void free_huge_page(struct page *);
+int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct * vma,
+			unsigned long address, int write_access);
 
 extern unsigned long max_huge_pages;
 extern const unsigned long hugetlb_zero, hugetlb_infinity;

180 lines not on this page · raw message

Index: working-2.6/mm/memory.c
===================================================================
@@ -2040,7 +2040,7 @@
 	inc_page_state(pgfault);
 
 	if (is_vm_hugetlb_page(vma))
-		return VM_FAULT_SIGBUS;	/* mapping truncation does this. */
+		return hugetlb_fault(mm, vma, address, write_access);
 
 	/*
 	 * We need the page table lock to synchronize with kswapd

diff -upN reference/fs/hugetlbfs/inode.c current/fs/hugetlbfs/inode.c
@@ -45,9 +45,59 @@ static struct backing_dev_info hugetlbfs
 
 int sysctl_hugetlb_shm_group;
 
+static void huge_pagevec_release(struct pagevec *pvec)
+{
+	int i;
+
+	for (i = 0; i < pagevec_count(pvec); ++i)
+		put_page(pvec->pages[i]);
+
+	pagevec_reinit(pvec);
+}
+
+unsigned long
+huge_pages_needed(struct address_space *mapping, struct vm_area_struct *vma)
+{
+	int i;
+	struct pagevec pvec;
+	unsigned long start = vma->vm_start;
+	unsigned long end = vma->vm_end;
+	unsigned long hugepages = (end - start) >> HPAGE_SHIFT;
+	pgoff_t next = vma->vm_pgoff;
+	pgoff_t endpg = next + ((end - start) >> PAGE_SHIFT);
+	struct inode *inode = vma->vm_file->f_dentry->d_inode;
+
+	/*
+	 * Shared memory segments are accounted for at shget time,
+	 * not at shmat (when the mapping is actually created) so 
+	 * check here if the memory has already been accounted for.
+	 */
+	if (inode->i_blocks != 0)
+		return 0;
+
+	pagevec_init(&pvec, 0);
+	while (next < endpg) {
+		if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE))
+			break;
+		for (i = 0; i < pagevec_count(&pvec); i++) {
+			struct page *page = pvec.pages[i];
+			if (page->index > next)
+				next = page->index;
+			if (page->index >= endpg)
+				break;
+			next++;
+			hugepages--;
+		}
+		huge_pagevec_release(&pvec);
+	}
+	return hugepages << HPAGE_SHIFT;
+}
+
 static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct inode *inode = file->f_dentry->d_inode;
+	struct address_space *mapping = inode->i_mapping;
+	unsigned long bytes;
 	loff_t len, vma_len;
 	int ret;
 

@@ -66,6 +116,10 @@ static int hugetlbfs_file_mmap(struct fi
 	if (vma->vm_end - vma->vm_start < HPAGE_SIZE)
 		return -EINVAL;
 
+	bytes = huge_pages_needed(mapping, vma);
+	if (!is_hugepage_mem_enough(bytes))
+		return -ENOMEM;
+
 	vma_len = (loff_t)(vma->vm_end - vma->vm_start);
 
 	down(&inode->i_sem);

@@ -167,16 +221,6 @@ static int hugetlbfs_commit_write(struct
 	return -EINVAL;
 }
 
-static void huge_pagevec_release(struct pagevec *pvec)
-{
-	int i;
-
-	for (i = 0; i < pagevec_count(pvec); ++i)
-		put_page(pvec->pages[i]);
-
-	pagevec_reinit(pvec);
-}
-
 static void truncate_huge_page(struct page *page)
 {
 	clear_page_dirty(page);

@@ -792,6 +836,7 @@ struct file *hugetlb_zero_setup(size_t s
 	d_instantiate(dentry, inode);
 	inode->i_size = size;
 	inode->i_nlink = 0;
+	inode->i_blocks = 1;
 	file->f_vfsmnt = mntget(hugetlbfs_vfsmount);
 	file->f_dentry = dentry;
 	file->f_mapping = inode->i_mapping;