mm: rework virtual memory accounting

When inspecting a vague code inside prctl(PR_SET_MM_MEM) call (which
testing the RLIMIT_DATA value to figure out if we're allowed to assign
new @start_brk, @brk, @start_data, @end_data from mm_struct) it's been
commited that RLIMIT_DATA in a form it's implemented now doesn't do
anything useful because most of user-space libraries use mmap() syscall
for dynamic memory allocations.

Linus suggested to convert RLIMIT_DATA rlimit into something suitable
for anonymous memory accounting.  But in this patch we go further, and
the changes are bundled together as:

 * keep vma counting if CONFIG_PROC_FS=n, will be used for limits
 * replace mm->shared_vm with better defined mm->data_vm
 * account anonymous executable areas as executable
 * account file-backed growsdown/up areas as stack
 * drop struct file* argument from vm_stat_account
 * enforce RLIMIT_DATA for size of data areas

This way code looks cleaner: now code/stack/data classification depends
only on vm_flags state:

 VM_EXEC & ~VM_WRITE            -> code  (VmExe + VmLib in proc)
 VM_GROWSUP | VM_GROWSDOWN      -> stack (VmStk)
 VM_WRITE & ~VM_SHARED & !stack -> data  (VmData)

The rest (VmSize - VmData - VmStk - VmExe - VmLib) could be called
"shared", but that might be strange beast like readonly-private or VM_IO
area.

 - RLIMIT_AS            limits whole address space "VmSize"
 - RLIMIT_STACK         limits stack "VmStk" (but each vma individually)
 - RLIMIT_DATA          now limits "VmData"

Signed-off-by: Konstantin Khlebnikov <koct9i@gmail.com>
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Quentin Casasnovas <quentin.casasnovas@oracle.com>
Cc: Vegard Nossum <vegard.nossum@oracle.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Willy Tarreau <w@1wt.eu>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Kees Cook <keescook@google.com>
Cc: Vladimir Davydov <vdavydov@virtuozzo.com>
Cc: Pavel Emelyanov <xemul@virtuozzo.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 44 insertions, 38 deletions

diff --git a/mm/debug.c b/mm/debug.c
index 668aa35191ca..5d2072ed8d5e 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -175,7 +175,7 @@ void dump_mm(const struct mm_struct *mm)
 		"mmap_base %lu mmap_legacy_base %lu highest_vm_end %lu\n"
 		"pgd %p mm_users %d mm_count %d nr_ptes %lu nr_pmds %lu map_count %d\n"
 		"hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n"
-		"pinned_vm %lx shared_vm %lx exec_vm %lx stack_vm %lx\n"
+		"pinned_vm %lx data_vm %lx exec_vm %lx stack_vm %lx\n"
 		"start_code %lx end_code %lx start_data %lx end_data %lx\n"
 		"start_brk %lx brk %lx start_stack %lx\n"
 		"arg_start %lx arg_end %lx env_start %lx env_end %lx\n"
@@ -209,7 +209,7 @@ void dump_mm(const struct mm_struct *mm)
 		mm_nr_pmds((struct mm_struct *)mm),
 		mm->map_count,
 		mm->hiwater_rss, mm->hiwater_vm, mm->total_vm, mm->locked_vm,
-		mm->pinned_vm, mm->shared_vm, mm->exec_vm, mm->stack_vm,
+		mm->pinned_vm, mm->data_vm, mm->exec_vm, mm->stack_vm,
 		mm->start_code, mm->end_code, mm->start_data, mm->end_data,
 		mm->start_brk, mm->brk, mm->start_stack,
 		mm->arg_start, mm->arg_end, mm->env_start, mm->env_end,
diff --git a/mm/mmap.c b/mm/mmap.c
index f32b84ad621a..b3f00b616b81 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1220,24 +1220,6 @@ none:
 	return NULL;
 }
 
-#ifdef CONFIG_PROC_FS
-void vm_stat_account(struct mm_struct *mm, unsigned long flags,
-						struct file *file, long pages)
-{
-	const unsigned long stack_flags
-		= VM_STACK_FLAGS & (VM_GROWSUP|VM_GROWSDOWN);
-
-	mm->total_vm += pages;
-
-	if (file) {
-		mm->shared_vm += pages;
-		if ((flags & (VM_EXEC|VM_WRITE)) == VM_EXEC)
-			mm->exec_vm += pages;
-	} else if (flags & stack_flags)
-		mm->stack_vm += pages;
-}
-#endif /* CONFIG_PROC_FS */
-
 /*
  * If a hint addr is less than mmap_min_addr change hint to be as
  * low as possible but still greater than mmap_min_addr
@@ -1556,7 +1538,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 	unsigned long charged = 0;
 
 	/* Check against address space limit. */
-	if (!may_expand_vm(mm, len >> PAGE_SHIFT)) {
+	if (!may_expand_vm(mm, vm_flags, len >> PAGE_SHIFT)) {
 		unsigned long nr_pages;
 
 		/*
@@ -1565,7 +1547,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 		 */
 		nr_pages = count_vma_pages_range(mm, addr, addr + len);
 
-		if (!may_expand_vm(mm, (len >> PAGE_SHIFT) - nr_pages))
+		if (!may_expand_vm(mm, vm_flags,
+					(len >> PAGE_SHIFT) - nr_pages))
 			return -ENOMEM;
 	}
 
@@ -1664,7 +1647,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 out:
 	perf_event_mmap(vma);
 
-	vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT);
+	vm_stat_account(mm, vm_flags, len >> PAGE_SHIFT);
 	if (vm_flags & VM_LOCKED) {
 		if (!((vm_flags & VM_SPECIAL) || is_vm_hugetlb_page(vma) ||
 					vma == get_gate_vma(current->mm)))
@@ -2111,7 +2094,7 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns
 	unsigned long new_start, actual_size;
 
 	/* address space limit tests */
-	if (!may_expand_vm(mm, grow))
+	if (!may_expand_vm(mm, vma->vm_flags, grow))
 		return -ENOMEM;
 
 	/* Stack limit test */
@@ -2208,8 +2191,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 				spin_lock(&mm->page_table_lock);
 				if (vma->vm_flags & VM_LOCKED)
 					mm->locked_vm += grow;
-				vm_stat_account(mm, vma->vm_flags,
-						vma->vm_file, grow);
+				vm_stat_account(mm, vma->vm_flags, grow);
 				anon_vma_interval_tree_pre_update_vma(vma);
 				vma->vm_end = address;
 				anon_vma_interval_tree_post_update_vma(vma);
@@ -2284,8 +2266,7 @@ int expand_downwards(struct vm_area_struct *vma,
 				spin_lock(&mm->page_table_lock);
 				if (vma->vm_flags & VM_LOCKED)
 					mm->locked_vm += grow;
-				vm_stat_account(mm, vma->vm_flags,
-						vma->vm_file, grow);
+				vm_stat_account(mm, vma->vm_flags, grow);
 				anon_vma_interval_tree_pre_update_vma(vma);
 				vma->vm_start = address;
 				vma->vm_pgoff -= grow;
@@ -2399,7 +2380,7 @@ static void remove_vma_list(struct mm_struct *mm, struct vm_area_struct *vma)
 
 		if (vma->vm_flags & VM_ACCOUNT)
 			nr_accounted += nrpages;
-		vm_stat_account(mm, vma->vm_flags, vma->vm_file, -nrpages);
+		vm_stat_account(mm, vma->vm_flags, -nrpages);
 		vma = remove_vma(vma);
 	} while (vma);
 	vm_unacct_memory(nr_accounted);
@@ -2769,7 +2750,7 @@ static unsigned long do_brk(unsigned long addr, unsigned long len)
 	}
 
 	/* Check against address space limits *after* clearing old maps... */
-	if (!may_expand_vm(mm, len >> PAGE_SHIFT))
+	if (!may_expand_vm(mm, flags, len >> PAGE_SHIFT))
 		return -ENOMEM;
 
 	if (mm->map_count > sysctl_max_map_count)
@@ -2804,6 +2785,7 @@ static unsigned long do_brk(unsigned long addr, unsigned long len)
 out:
 	perf_event_mmap(vma);
 	mm->total_vm += len >> PAGE_SHIFT;
+	mm->data_vm += len >> PAGE_SHIFT;
 	if (flags & VM_LOCKED)
 		mm->locked_vm += (len >> PAGE_SHIFT);
 	vma->vm_flags |= VM_SOFTDIRTY;
@@ -2995,9 +2977,28 @@ out:
  * Return true if the calling process may expand its vm space by the passed
  * number of pages
  */
-int may_expand_vm(struct mm_struct *mm, unsigned long npages)
+bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags, unsigned long npages)
 {
-	return mm->total_vm + npages <= rlimit(RLIMIT_AS) >> PAGE_SHIFT;
+	if (mm->total_vm + npages > rlimit(RLIMIT_AS) >> PAGE_SHIFT)
+		return false;
+
+	if ((flags & (VM_WRITE | VM_SHARED | (VM_STACK_FLAGS &
+				(VM_GROWSUP | VM_GROWSDOWN)))) == VM_WRITE)
+		return mm->data_vm + npages <= rlimit(RLIMIT_DATA);
+
+	return true;
+}
+
+void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages)
+{
+	mm->total_vm += npages;
+
+	if ((flags & (VM_EXEC | VM_WRITE)) == VM_EXEC)
+		mm->exec_vm += npages;
+	else if (flags & (VM_STACK_FLAGS & (VM_GROWSUP | VM_GROWSDOWN)))
+		mm->stack_vm += npages;
+	else if ((flags & (VM_WRITE | VM_SHARED)) == VM_WRITE)
+		mm->data_vm += npages;
 }
 
 static int special_mapping_fault(struct vm_area_struct *vma,
@@ -3079,7 +3080,7 @@ static struct vm_area_struct *__install_special_mapping(
 	if (ret)
 		goto out;
 
-	mm->total_vm += len >> PAGE_SHIFT;
+	vm_stat_account(mm, vma->vm_flags, len >> PAGE_SHIFT);
 
 	perf_event_mmap(vma);
 
diff --git a/mm/mprotect.c b/mm/mprotect.c
index ef5be8eaab00..c764402c464f 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -278,6 +278,10 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 	 * even if read-only so there is no need to account for them here
 	 */
 	if (newflags & VM_WRITE) {
+		/* Check space limits when area turns into data. */
+		if (!may_expand_vm(mm, newflags, nrpages) &&
+				may_expand_vm(mm, oldflags, nrpages))
+			return -ENOMEM;
 		if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_HUGETLB|
 						VM_SHARED|VM_NORESERVE))) {
 			charged = nrpages;
@@ -334,8 +338,8 @@ success:
 		populate_vma_page_range(vma, start, end, NULL);
 	}
 
-	vm_stat_account(mm, oldflags, vma->vm_file, -nrpages);
-	vm_stat_account(mm, newflags, vma->vm_file, nrpages);
+	vm_stat_account(mm, oldflags, -nrpages);
+	vm_stat_account(mm, newflags, nrpages);
 	perf_event_mmap(vma);
 	return 0;
 
diff --git a/mm/mremap.c b/mm/mremap.c
index de824e72c3e8..e55b157865d5 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -317,7 +317,7 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 	 * If this were a serious issue, we'd add a flag to do_munmap().
 	 */
 	hiwater_vm = mm->hiwater_vm;
-	vm_stat_account(mm, vma->vm_flags, vma->vm_file, new_len>>PAGE_SHIFT);
+	vm_stat_account(mm, vma->vm_flags, new_len >> PAGE_SHIFT);
 
 	/* Tell pfnmap has moved from this vma */
 	if (unlikely(vma->vm_flags & VM_PFNMAP))
@@ -383,7 +383,8 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr,
 			return ERR_PTR(-EAGAIN);
 	}
 
-	if (!may_expand_vm(mm, (new_len - old_len) >> PAGE_SHIFT))
+	if (!may_expand_vm(mm, vma->vm_flags,
+				(new_len - old_len) >> PAGE_SHIFT))
 		return ERR_PTR(-ENOMEM);
 
 	if (vma->vm_flags & VM_ACCOUNT) {
@@ -545,7 +546,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 				goto out;
 			}
 
-			vm_stat_account(mm, vma->vm_flags, vma->vm_file, pages);
+			vm_stat_account(mm, vma->vm_flags, pages);
 			if (vma->vm_flags & VM_LOCKED) {
 				mm->locked_vm += pages;
 				locked = true;