The patch titled
From: Konstantin Khlebnikov <koct9i@xxxxxxxxx>
has been added to the -mm tree. Its filename is
mm-warn-about-vmdata-over-rlimit_data.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-warn-about-vmdata-over-rlimit_data.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-warn-about-vmdata-over-rlimit_data.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Konstantin Khlebnikov <koct9i@xxxxxxxxx>
Subject: mm: warn about VmData over RLIMIT_DATA
This patch provides a way of working around a slight regression introduced
by 84638335900f ("mm: rework virtual memory accounting").
Before that commit RLIMIT_DATA have control only over size of the brk
region. But that change have caused problems with all existing versions
of valgrind, because it set RLIMIT_DATA to zero.
This patch fixes rlimit check (limit actually in bytes, not pages) and by
default turns it into warning which prints at first VmData misuse: "mmap:
top (795): VmData 516096 exceed data ulimit 512000. Will be forbidden
soon."
Behavior is controlled by boot param ignore_rlimit_data=y/n and by sysfs
/sys/module/kernel/parameters/ignore_rlimit_data. For now it set to "y".
Signed-off-by: Konstantin Khlebnikov <koct9i@xxxxxxxxx>
Link: http://lkml.kernel.org/r/20151228211015.GL2194@uranus
Reported-by: Christian Borntraeger <borntraeger@xxxxxxxxxx>
Cc: Cyrill Gorcunov <gorcunov@xxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Vegard Nossum <vegard.nossum@xxxxxxxxxx>
Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Cc: Vladimir Davydov <vdavydov@xxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
Cc: Quentin Casasnovas <quentin.casasnovas@xxxxxxxxxx>
Cc: Kees Cook <keescook@xxxxxxxxxx>
Cc: Willy Tarreau <w@xxxxxx>
Cc: Pavel Emelyanov <xemul@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
Documentation/kernel-parameters.txt | 5 +++++
mm/internal.h | 16 ++++++++++++++++
mm/mmap.c | 23 +++++++++++++++++------
3 files changed, 38 insertions(+), 6 deletions(-)
diff -puN Documentation/kernel-parameters.txt~mm-warn-about-vmdata-over-rlimit_data Documentation/kernel-parameters.txt
--- a/Documentation/kernel-parameters.txt~mm-warn-about-vmdata-over-rlimit_data
+++ a/Documentation/kernel-parameters.txt
@@ -1496,6 +1496,11 @@ bytes respectively. Such letter suffixes
could change it dynamically, usually by
/sys/module/printk/parameters/ignore_loglevel.
+ ignore_rlimit_data
+ Ignore RLIMIT_DATA setting for data mappings,
+ print warning at first misuse. Could be changed by
+ /sys/module/kernel/parameters/ignore_rlimit_data.
+
ihash_entries= [KNL]
Set number of hash buckets for inode cache.
diff -puN mm/internal.h~mm-warn-about-vmdata-over-rlimit_data mm/internal.h
--- a/mm/internal.h~mm-warn-about-vmdata-over-rlimit_data
+++ a/mm/internal.h
@@ -216,6 +216,22 @@ static inline bool is_cow_mapping(vm_fla
return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
}
+static inline bool is_exec_mapping(vm_flags_t flags)
+{
+ return (flags & (VM_EXEC | VM_WRITE)) == VM_EXEC;
+}
+
+static inline bool is_stack_mapping(vm_flags_t flags)
+{
+ return (flags & (VM_STACK_FLAGS & (VM_GROWSUP | VM_GROWSDOWN))) != 0;
+}
+
+static inline bool is_data_mapping(vm_flags_t flags)
+{
+ return (flags & ((VM_STACK_FLAGS & (VM_GROWSUP | VM_GROWSDOWN)) |
+ VM_WRITE | VM_SHARED)) == VM_WRITE;
+}
+
/* mm/util.c */
void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
struct vm_area_struct *prev, struct rb_node *rb_parent);
diff -puN mm/mmap.c~mm-warn-about-vmdata-over-rlimit_data mm/mmap.c
--- a/mm/mmap.c~mm-warn-about-vmdata-over-rlimit_data
+++ a/mm/mmap.c
@@ -42,6 +42,7 @@
#include <linux/memory.h>
#include <linux/printk.h>
#include <linux/userfaultfd_k.h>
+#include <linux/moduleparam.h>
#include <asm/uaccess.h>
#include <asm/cacheflush.h>
@@ -69,6 +70,8 @@ const int mmap_rnd_compat_bits_max = CON
int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS;
#endif
+static bool ignore_rlimit_data = true;
+core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644);
static void unmap_region(struct mm_struct *mm,
struct vm_area_struct *vma, struct vm_area_struct *prev,
@@ -2982,9 +2985,17 @@ bool may_expand_vm(struct mm_struct *mm,
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);
+ if (is_data_mapping(flags) &&
+ mm->data_vm + npages > rlimit(RLIMIT_DATA) >> PAGE_SHIFT) {
+ if (ignore_rlimit_data)
+ pr_warn_once("%s (%d): VmData %lu exceed data ulimit "
+ "%lu. Will be forbidden soon.\n",
+ current->comm, current->pid,
+ (mm->data_vm + npages) << PAGE_SHIFT,
+ rlimit(RLIMIT_DATA));
+ else
+ return false;
+ }
return true;
}
@@ -2993,11 +3004,11 @@ void vm_stat_account(struct mm_struct *m
{
mm->total_vm += npages;
- if ((flags & (VM_EXEC | VM_WRITE)) == VM_EXEC)
+ if (is_exec_mapping(flags))
mm->exec_vm += npages;
- else if (flags & (VM_STACK_FLAGS & (VM_GROWSUP | VM_GROWSDOWN)))
+ else if (is_stack_mapping(flags))
mm->stack_vm += npages;
- else if ((flags & (VM_WRITE | VM_SHARED)) == VM_WRITE)
+ else if (is_data_mapping(flags))
mm->data_vm += npages;
}
_
Patches currently in -mm which might be from koct9i@xxxxxxxxx are
mm-warn-about-vmdata-over-rlimit_data.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
