| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Fri, 11 Dec 2015 23:49:39 +0300
From: Cyrill Gorcunov <gorcunov@...il.com>
To: LKML <linux-kernel@...r.kernel.org>, Linux MM <linux-mm@...ck.org>
Cc: Quentin Casasnovas <quentin.casasnovas@...cle.com>,
Vegard Nossum <vegard.nossum@...cle.com>,
Linus Torvalds <torvalds@...ux-foundation.org>,
Willy Tarreau <w@....eu>,
Andy Lutomirski <luto@...capital.net>,
Kees Cook <keescook@...gle.com>,
Vladimir Davydov <vdavydov@...tuozzo.com>,
Konstantin Khlebnikov <koct9i@...il.com>,
Pavel Emelyanov <xemul@...tuozzo.com>,
Peter Zijlstra <a.p.zijlstra@...llo.nl>
Subject: [RFC] mm: Account anon mappings as RLIMIT_DATA
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.
So Linus suggested to convert RLIMIT_DATA rlimit into something
suitable for anonymous memory accounting. Here we introduce
new @anon_vm member into mm descriptor which is updated
every vm_stat_account call. When mmap_region() is called
we test if current RLIMIT_DATA limit is not exceeded.
This should give a way to control the amount of anonymous
memory allocated.
p.s.: This rfc not for application, I would like to
hear if I move in right direction in general. In
particular I need to add hugetlb anon mappings here
as well and update docs and etc.
So comments are highly appreciated.
CC: Quentin Casasnovas <quentin.casasnovas@...cle.com>
CC: Vegard Nossum <vegard.nossum@...cle.com>
CC: Linus Torvalds <torvalds@...ux-foundation.org>
CC: Willy Tarreau <w@....eu>
CC: Andy Lutomirski <luto@...capital.net>
CC: Kees Cook <keescook@...gle.com>
CC: Vladimir Davydov <vdavydov@...tuozzo.com>
CC: Konstantin Khlebnikov <koct9i@...il.com>
CC: Pavel Emelyanov <xemul@...tuozzo.com>
CC: Vladimir Davydov <vdavydov@...tuozzo.com>
CC: Peter Zijlstra <a.p.zijlstra@...llo.nl>
Signed-off-by: Cyrill Gorcunov <gorcunov@...nvz.org>
---
fs/proc/task_mmu.c | 2 ++
include/linux/mm_types.h | 1 +
mm/mmap.c | 22 ++++++++++++++++++++++
3 files changed, 25 insertions(+)
Index: linux-ml.git/fs/proc/task_mmu.c
===================================================================
--- linux-ml.git.orig/fs/proc/task_mmu.c
+++ linux-ml.git/fs/proc/task_mmu.c
@@ -53,6 +53,7 @@ void task_mem(struct seq_file *m, struct
"VmHWM:\t%8lu kB\n"
"VmRSS:\t%8lu kB\n"
"VmData:\t%8lu kB\n"
+ "VmAnon:\t%8lu kB\n"
"VmStk:\t%8lu kB\n"
"VmExe:\t%8lu kB\n"
"VmLib:\t%8lu kB\n"
@@ -66,6 +67,7 @@ void task_mem(struct seq_file *m, struct
hiwater_rss << (PAGE_SHIFT-10),
total_rss << (PAGE_SHIFT-10),
data << (PAGE_SHIFT-10),
+ mm->anon_vm << (PAGE_SHIFT-10),
mm->stack_vm << (PAGE_SHIFT-10), text, lib,
ptes >> 10,
pmds >> 10,
Index: linux-ml.git/include/linux/mm_types.h
===================================================================
--- linux-ml.git.orig/include/linux/mm_types.h
+++ linux-ml.git/include/linux/mm_types.h
@@ -429,6 +429,7 @@ struct mm_struct {
unsigned long shared_vm; /* Shared pages (files) */
unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE */
unsigned long stack_vm; /* VM_GROWSUP/DOWN */
+ unsigned long anon_vm; /* Anonymous pages mapped */
unsigned long def_flags;
unsigned long start_code, end_code, start_data, end_data;
unsigned long start_brk, brk, start_stack;
Index: linux-ml.git/mm/mmap.c
===================================================================
--- linux-ml.git.orig/mm/mmap.c
+++ linux-ml.git/mm/mmap.c
@@ -1214,6 +1214,8 @@ void vm_stat_account(struct mm_struct *m
{
const unsigned long stack_flags
= VM_STACK_FLAGS & (VM_GROWSUP|VM_GROWSDOWN);
+ const unsigned long not_anon_acc
+ = VM_GROWSUP | VM_GROWSDOWN | VM_SHARED | VM_MAYSHARE;
mm->total_vm += pages;
@@ -1223,6 +1225,9 @@ void vm_stat_account(struct mm_struct *m
mm->exec_vm += pages;
} else if (flags & stack_flags)
mm->stack_vm += pages;
+
+ if (!file && (flags & not_anon_acc) == 0)
+ mm->anon_vm += pages;
}
#endif /* CONFIG_PROC_FS */
@@ -1534,6 +1539,13 @@ static inline int accountable_mapping(st
return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE;
}
+static inline int anon_accountable_mapping(struct file *file, vm_flags_t vm_flags)
+{
+ return !file &&
+ (vm_flags & (VM_GROWSDOWN | VM_GROWSUP |
+ VM_SHARED | VM_MAYSHARE)) == 0;
+}
+
unsigned long mmap_region(struct file *file, unsigned long addr,
unsigned long len, vm_flags_t vm_flags, unsigned long pgoff)
{
@@ -1578,6 +1590,16 @@ unsigned long mmap_region(struct file *f
}
/*
+ * For anon mappings make sure we don't exceed the limit.
+ */
+ if (anon_accountable_mapping(file, vm_flags)) {
+ unsigned long lim = rlimit(RLIMIT_DATA) >> PAGE_SHIFT;
+
+ if (lim < (mm->anon_vm + (len >> PAGE_SHIFT)))
+ return -ENOMEM;
+ }
+
+ /*
* Can we just expand an old mapping?
*/
vma = vma_merge(mm, prev, addr, addr + len, vm_flags,
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists