---

yaml
---
r: 131184
b: refs/heads/master
c: 5a6fe12
h: refs/heads/master
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 4c098bcd55fad34dcf224bf8343db6a9ac58fc68
+refs/heads/master: 5a6fe125950676015f5108fb71b2a67441755003

trunk/fs/hugetlbfs/inode.c

@@ -108,7 +108,8 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 
 	if (hugetlb_reserve_pages(inode,
 				vma->vm_pgoff >> huge_page_order(h),
-				len >> huge_page_shift(h), vma))
+				len >> huge_page_shift(h), vma,
+				vma->vm_flags))
 		goto out;
 
 	ret = 0;
@@ -947,7 +948,7 @@ static int can_do_hugetlb_shm(void)
 			can_do_mlock());
 }
 
-struct file *hugetlb_file_setup(const char *name, size_t size)
+struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag)
 {
 	int error = -ENOMEM;
 	struct file *file;
@@ -981,7 +982,8 @@ struct file *hugetlb_file_setup(const char *name, size_t size)
 
 	error = -ENOMEM;
 	if (hugetlb_reserve_pages(inode, 0,
-			size >> huge_page_shift(hstate_inode(inode)), NULL))
+			size >> huge_page_shift(hstate_inode(inode)), NULL,
+			acctflag))
 		goto out_inode;
 
 	d_instantiate(dentry, inode);

trunk/include/linux/hugetlb.h

@@ -33,7 +33,8 @@ unsigned long hugetlb_total_pages(void);
 int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, int write_access);
 int hugetlb_reserve_pages(struct inode *inode, long from, long to,
-						struct vm_area_struct *vma);
+						struct vm_area_struct *vma,
+						int acctflags);
 void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed);
 
 extern unsigned long hugepages_treat_as_movable;
@@ -138,7 +139,7 @@ static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb)
 
 extern const struct file_operations hugetlbfs_file_operations;
 extern struct vm_operations_struct hugetlb_vm_ops;
-struct file *hugetlb_file_setup(const char *name, size_t);
+struct file *hugetlb_file_setup(const char *name, size_t, int);
 int hugetlb_get_quota(struct address_space *mapping, long delta);
 void hugetlb_put_quota(struct address_space *mapping, long delta);
 

trunk/include/linux/mm.h

@@ -1129,8 +1129,7 @@ extern unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 	unsigned long flag, unsigned long pgoff);
 extern unsigned long mmap_region(struct file *file, unsigned long addr,
 	unsigned long len, unsigned long flags,
-	unsigned int vm_flags, unsigned long pgoff,
-	int accountable);
+	unsigned int vm_flags, unsigned long pgoff);
 
 static inline unsigned long do_mmap(struct file *file, unsigned long addr,
 	unsigned long len, unsigned long prot,

trunk/ipc/shm.c

@@ -340,6 +340,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 	struct file * file;
 	char name[13];
 	int id;
+	int acctflag = 0;
 
 	if (size < SHMMIN || size > ns->shm_ctlmax)
 		return -EINVAL;
@@ -364,11 +365,12 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 
 	sprintf (name, "SYSV%08x", key);
 	if (shmflg & SHM_HUGETLB) {
-		/* hugetlb_file_setup takes care of mlock user accounting */
-		file = hugetlb_file_setup(name, size);
+		/* hugetlb_file_setup applies strict accounting */
+		if (shmflg & SHM_NORESERVE)
+			acctflag = VM_NORESERVE;
+		file = hugetlb_file_setup(name, size, acctflag);
 		shp->mlock_user = current_user();
 	} else {
-		int acctflag = 0;
 		/*
 		 * Do not allow no accounting for OVERCOMMIT_NEVER, even
 	 	 * if it's asked for.

trunk/mm/fremap.c

@@ -198,7 +198,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 			flags &= MAP_NONBLOCK;
 			get_file(file);
 			addr = mmap_region(file, start, size,
-					flags, vma->vm_flags, pgoff, 1);
+					flags, vma->vm_flags, pgoff);
 			fput(file);
 			if (IS_ERR_VALUE(addr)) {
 				err = addr;

trunk/mm/hugetlb.c

@@ -2269,14 +2269,12 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
 
 int hugetlb_reserve_pages(struct inode *inode,
 					long from, long to,
-					struct vm_area_struct *vma)
+					struct vm_area_struct *vma,
+					int acctflag)
 {
-	long ret, chg;
+	long ret = 0, chg;
 	struct hstate *h = hstate_inode(inode);
 
-	if (vma && vma->vm_flags & VM_NORESERVE)
-		return 0;
-
 	/*
 	 * Shared mappings base their reservation on the number of pages that
 	 * are already allocated on behalf of the file. Private mappings need
@@ -2285,29 +2283,42 @@ int hugetlb_reserve_pages(struct inode *inode,
 	 */
 	if (!vma || vma->vm_flags & VM_SHARED)
 		chg = region_chg(&inode->i_mapping->private_list, from, to);
-	else {
-		struct resv_map *resv_map = resv_map_alloc();
-		if (!resv_map)
-			return -ENOMEM;
-
+	else
 		chg = to - from;
 
-		set_vma_resv_map(vma, resv_map);
-		set_vma_resv_flags(vma, HPAGE_RESV_OWNER);
-	}
-
 	if (chg < 0)
 		return chg;
 
 	if (hugetlb_get_quota(inode->i_mapping, chg))
 		return -ENOSPC;
+
+	/*
+	 * Only apply hugepage reservation if asked. We still have to
+	 * take the filesystem quota because it is an upper limit
+	 * defined for the mount and not necessarily memory as a whole
+	 */
+	if (acctflag & VM_NORESERVE) {
+		reset_vma_resv_huge_pages(vma);
+		return 0;
+	}
+
 	ret = hugetlb_acct_memory(h, chg);
 	if (ret < 0) {
 		hugetlb_put_quota(inode->i_mapping, chg);
 		return ret;
 	}
 	if (!vma || vma->vm_flags & VM_SHARED)
 		region_add(&inode->i_mapping->private_list, from, to);
+	else {
+		struct resv_map *resv_map = resv_map_alloc();
+
+		if (!resv_map)
+			return -ENOMEM;
+
+		set_vma_resv_map(vma, resv_map);
+		set_vma_resv_flags(vma, HPAGE_RESV_OWNER);
+	}
+
 	return 0;
 }
 

trunk/mm/mmap.c

@@ -918,7 +918,6 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 	struct inode *inode;
 	unsigned int vm_flags;
 	int error;
-	int accountable = 1;
 	unsigned long reqprot = prot;
 
 	/*
@@ -1019,8 +1018,6 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 					return -EPERM;
 				vm_flags &= ~VM_MAYEXEC;
 			}
-			if (is_file_hugepages(file))
-				accountable = 0;
 
 			if (!file->f_op || !file->f_op->mmap)
 				return -ENODEV;
@@ -1053,8 +1050,7 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 	if (error)
 		return error;
 
-	return mmap_region(file, addr, len, flags, vm_flags, pgoff,
-			   accountable);
+	return mmap_region(file, addr, len, flags, vm_flags, pgoff);
 }
 EXPORT_SYMBOL(do_mmap_pgoff);
 
@@ -1092,17 +1088,23 @@ int vma_wants_writenotify(struct vm_area_struct *vma)
 
 /*
  * We account for memory if it's a private writeable mapping,
- * and VM_NORESERVE wasn't set.
+ * not hugepages and VM_NORESERVE wasn't set.
  */
-static inline int accountable_mapping(unsigned int vm_flags)
+static inline int accountable_mapping(struct file *file, unsigned int vm_flags)
 {
+	/*
+	 * hugetlb has its own accounting separate from the core VM
+	 * VM_HUGETLB may not be set yet so we cannot check for that flag.
+	 */
+	if (file && is_file_hugepages(file))
+		return 0;
+
 	return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE;
 }
 
 unsigned long mmap_region(struct file *file, unsigned long addr,
 			  unsigned long len, unsigned long flags,
-			  unsigned int vm_flags, unsigned long pgoff,
-			  int accountable)
+			  unsigned int vm_flags, unsigned long pgoff)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma, *prev;
@@ -1128,18 +1130,22 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 
 	/*
 	 * Set 'VM_NORESERVE' if we should not account for the
-	 * memory use of this mapping. We only honor MAP_NORESERVE
-	 * if we're allowed to overcommit memory.
+	 * memory use of this mapping.
 	 */
-	if ((flags & MAP_NORESERVE) && sysctl_overcommit_memory != OVERCOMMIT_NEVER)
-		vm_flags |= VM_NORESERVE;
-	if (!accountable)
-		vm_flags |= VM_NORESERVE;
+	if ((flags & MAP_NORESERVE)) {
+		/* We honor MAP_NORESERVE if allowed to overcommit */
+		if (sysctl_overcommit_memory != OVERCOMMIT_NEVER)
+			vm_flags |= VM_NORESERVE;
+
+		/* hugetlb applies strict overcommit unless MAP_NORESERVE */
+		if (file && is_file_hugepages(file))
+			vm_flags |= VM_NORESERVE;
+	}
 
 	/*
 	 * Private writable mapping: check memory availability
 	 */
-	if (accountable_mapping(vm_flags)) {
+	if (accountable_mapping(file, vm_flags)) {
 		charged = len >> PAGE_SHIFT;
 		if (security_vm_enough_memory(charged))
 			return -ENOMEM;

trunk/mm/mprotect.c

@@ -151,10 +151,11 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 	/*
 	 * If we make a private mapping writable we increase our commit;
 	 * but (without finer accounting) cannot reduce our commit if we
-	 * make it unwritable again.
+	 * make it unwritable again. hugetlb mapping were accounted for
+	 * even if read-only so there is no need to account for them here
 	 */
 	if (newflags & VM_WRITE) {
-		if (!(oldflags & (VM_ACCOUNT|VM_WRITE|
+		if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_HUGETLB|
 						VM_SHARED|VM_NORESERVE))) {
 			charged = nrpages;
 			if (security_vm_enough_memory(charged))