forked from Minki/linux
88aa7cc688
mmap_sem is on the hot path of kernel, and it very contended, but it is
abused too. It is used to protect arg_start|end and evn_start|end when
reading /proc/$PID/cmdline and /proc/$PID/environ, but it doesn't make
sense since those proc files just expect to read 4 values atomically and
not related to VM, they could be set to arbitrary values by C/R.
And, the mmap_sem contention may cause unexpected issue like below:
INFO: task ps:14018 blocked for more than 120 seconds.
Tainted: G E 4.9.79-009.ali3000.alios7.x86_64 #1
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this
message.
ps D 0 14018 1 0x00000004
Call Trace:
schedule+0x36/0x80
rwsem_down_read_failed+0xf0/0x150
call_rwsem_down_read_failed+0x18/0x30
down_read+0x20/0x40
proc_pid_cmdline_read+0xd9/0x4e0
__vfs_read+0x37/0x150
vfs_read+0x96/0x130
SyS_read+0x55/0xc0
entry_SYSCALL_64_fastpath+0x1a/0xc5
Both Alexey Dobriyan and Michal Hocko suggested to use dedicated lock
for them to mitigate the abuse of mmap_sem.
So, introduce a new spinlock in mm_struct to protect the concurrent
access to arg_start|end, env_start|end and others, as well as replace
write map_sem to read to protect the race condition between prctl and
sys_brk which might break check_data_rlimit(), and makes prctl more
friendly to other VM operations.
This patch just eliminates the abuse of mmap_sem, but it can't resolve
the above hung task warning completely since the later
access_remote_vm() call needs acquire mmap_sem. The mmap_sem
scalability issue will be solved in the future.
[yang.shi@linux.alibaba.com: add comment about mmap_sem and arg_lock]
Link: http://lkml.kernel.org/r/1524077799-80690-1-git-send-email-yang.shi@linux.alibaba.com
Link: http://lkml.kernel.org/r/1523730291-109696-1-git-send-email-yang.shi@linux.alibaba.com
Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com>
Reviewed-by: Cyrill Gorcunov <gorcunov@openvz.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mateusz Guzik <mguzik@redhat.com>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
30 lines
770 B
C
30 lines
770 B
C
// SPDX-License-Identifier: GPL-2.0
|
|
#include <linux/mm_types.h>
|
|
#include <linux/rbtree.h>
|
|
#include <linux/rwsem.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/list.h>
|
|
#include <linux/cpumask.h>
|
|
|
|
#include <linux/atomic.h>
|
|
#include <linux/user_namespace.h>
|
|
#include <asm/pgtable.h>
|
|
#include <asm/mmu.h>
|
|
|
|
#ifndef INIT_MM_CONTEXT
|
|
#define INIT_MM_CONTEXT(name)
|
|
#endif
|
|
|
|
struct mm_struct init_mm = {
|
|
.mm_rb = RB_ROOT,
|
|
.pgd = swapper_pg_dir,
|
|
.mm_users = ATOMIC_INIT(2),
|
|
.mm_count = ATOMIC_INIT(1),
|
|
.mmap_sem = __RWSEM_INITIALIZER(init_mm.mmap_sem),
|
|
.page_table_lock = __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock),
|
|
.arg_lock = __SPIN_LOCK_UNLOCKED(init_mm.arg_lock),
|
|
.mmlist = LIST_HEAD_INIT(init_mm.mmlist),
|
|
.user_ns = &init_user_ns,
|
|
INIT_MM_CONTEXT(init_mm)
|
|
};
|