The patch titled
munmap(): don't check sysctl_max_mapcount
has been added to the -mm tree. Its filename is
munmap-dont-check-sysctl_max_mapcount.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 ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: munmap(): don't check sysctl_max_mapcount
From: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
On ia64, the following test program exits abnormally, because glibc thread
library called abort().
========================================================
(gdb) bt
#0 0xa000000000010620 in __kernel_syscall_via_break ()
#1 0x20000000003208e0 in raise () from /lib/libc.so.6.1
#2 0x2000000000324090 in abort () from /lib/libc.so.6.1
#3 0x200000000027c3e0 in __deallocate_stack () from /lib/libpthread.so.0
#4 0x200000000027f7c0 in start_thread () from /lib/libpthread.so.0
#5 0x200000000047ef60 in __clone2 () from /lib/libc.so.6.1
========================================================
The fact is, glibc call munmap() when thread exitng time for freeing
stack, and it assume munlock() never fail. However, munmap() often make
vma splitting and it with many mapcount make -ENOMEM.
Stack unfreeing is not reasonable option. Also munlock() via free()
shouldn't fail.
Thus, munmap() shoudn't check max-mapcount. This patch does it.
test_max_mapcount.c
==================================================================
#include<stdio.h>
#include<stdlib.h>
#include<string.h>
#include<pthread.h>
#include<errno.h>
#include<unistd.h>
#define THREAD_NUM 30000
#define MAL_SIZE (100*1024)
void *wait_thread(void *args)
{
void *addr;
addr = malloc(MAL_SIZE);
if(addr)
memset(addr, 1, MAL_SIZE);
sleep(1);
return NULL;
}
void *wait_thread2(void *args)
{
sleep(60);
return NULL;
}
int main(int argc, char *argv[])
{
int i;
pthread_t thread[THREAD_NUM], th;
int ret, count = 0;
pthread_attr_t attr;
ret = pthread_attr_init(&attr);
if(ret) {
perror("pthread_attr_init");
}
ret = pthread_attr_setdetachstate(&attr, PTHREAD_CREATE_DETACHED);
if(ret) {
perror("pthread_attr_setdetachstate");
}
for (i = 0; i < THREAD_NUM; i++) {
ret = pthread_create(&th, &attr, wait_thread, NULL);
if(ret) {
fprintf(stderr, "[%d] ", count);
perror("pthread_create");
} else {
printf("[%d] create OK.\n", count);
}
count++;
ret = pthread_create(&thread[i], &attr, wait_thread2, NULL);
if(ret) {
fprintf(stderr, "[%d] ", count);
perror("pthread_create");
} else {
printf("[%d] create OK.\n", count);
}
count++;
}
sleep(3600);
return 0;
}
==================================================================
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
Cc: Hugh Dickins <hugh.dickins@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
diff -puN mm/mmap.c~munmap-dont-check-sysctl_max_mapcount mm/mmap.c
--- a/mm/mmap.c~munmap-dont-check-sysctl_max_mapcount
+++ a/mm/mmap.c
@@ -1832,7 +1832,7 @@ detach_vmas_to_be_unmapped(struct mm_str
* Split a vma into two pieces at address 'addr', a new vma is allocated
* either for the first part or the tail.
*/
-int split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
+static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
unsigned long addr, int new_below)
{
struct mempolicy *pol;
@@ -1842,9 +1842,6 @@ int split_vma(struct mm_struct * mm, str
~(huge_page_mask(hstate_vma(vma)))))
return -EINVAL;
- if (mm->map_count >= sysctl_max_map_count)
- return -ENOMEM;
-
new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
if (!new)
return -ENOMEM;
@@ -1884,6 +1881,15 @@ int split_vma(struct mm_struct * mm, str
return 0;
}
+int split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
+ unsigned long addr, int new_below)
+{
+ if (mm->map_count >= sysctl_max_map_count)
+ return -ENOMEM;
+
+ return __split_vma(mm, vma, addr, new_below);
+}
+
/* Munmap is split into 2 main parts -- this part which finds
* what needs doing, and the areas themselves, which do the
* work. This now handles partial unmappings.
@@ -1919,7 +1925,7 @@ int do_munmap(struct mm_struct *mm, unsi
* places tmp vma above, and higher split_vma places tmp vma below.
*/
if (start > vma->vm_start) {
- int error = split_vma(mm, vma, start, 0);
+ int error = __split_vma(mm, vma, start, 0);
if (error)
return error;
prev = vma;
@@ -1928,7 +1934,7 @@ int do_munmap(struct mm_struct *mm, unsi
/* Does it split the last one? */
last = find_vma(mm, end);
if (last && end > last->vm_start) {
- int error = split_vma(mm, last, end, 1);
+ int error = __split_vma(mm, last, end, 1);
if (error)
return error;
}
_
Patches currently in -mm which might be from kosaki.motohiro@xxxxxxxxxxxxxx are
linux-next.patch
congestion_wait-dont-use-write.patch
elv_iosched_store-fix-strstrip-misuse.patch
cgroup-fix-strstrip-misuse.patch
strstrip-mark-as-as-must_check.patch
oom-dump-stack-and-vm-state-when-oom-killer-panics.patch
munmap-dont-check-sysctl_max_mapcount.patch
munmap-dont-check-sysctl_max_mapcount-fix.patch
readahead-add-blk_run_backing_dev.patch
mm-vsmcan-check-shrink_active_list-sc-isolate_pages-return-value.patch
fs-symlink-write_begin-allocation-context-fix-reiser4-fix.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
