linux_dsm_epyc7002/ipc/msgutil.c
Li Rongqing d6a2946a88 ipc: prevent lockup on alloc_msg and free_msg
msgctl10 of ltp triggers the following lockup When CONFIG_KASAN is
enabled on large memory SMP systems, the pages initialization can take a
long time, if msgctl10 requests a huge block memory, and it will block
rcu scheduler, so release cpu actively.

After adding schedule() in free_msg, free_msg can not be called when
holding spinlock, so adding msg to a tmp list, and free it out of
spinlock

  rcu: INFO: rcu_preempt detected stalls on CPUs/tasks:
  rcu:     Tasks blocked on level-1 rcu_node (CPUs 16-31): P32505
  rcu:     Tasks blocked on level-1 rcu_node (CPUs 48-63): P34978
  rcu:     (detected by 11, t=35024 jiffies, g=44237529, q=16542267)
  msgctl10        R  running task    21608 32505   2794 0x00000082
  Call Trace:
   preempt_schedule_irq+0x4c/0xb0
   retint_kernel+0x1b/0x2d
  RIP: 0010:__is_insn_slot_addr+0xfb/0x250
  Code: 82 1d 00 48 8b 9b 90 00 00 00 4c 89 f7 49 c1 ee 03 e8 59 83 1d 00 48 b8 00 00 00 00 00 fc ff df 4c 39 eb 48 89 9d 58 ff ff ff <41> c6 04 06 f8 74 66 4c 8d 75 98 4c 89 f1 48 c1 e9 03 48 01 c8 48
  RSP: 0018:ffff88bce041f758 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13
  RAX: dffffc0000000000 RBX: ffffffff8471bc50 RCX: ffffffff828a2a57
  RDX: dffffc0000000000 RSI: dffffc0000000000 RDI: ffff88bce041f780
  RBP: ffff88bce041f828 R08: ffffed15f3f4c5b3 R09: ffffed15f3f4c5b3
  R10: 0000000000000001 R11: ffffed15f3f4c5b2 R12: 000000318aee9b73
  R13: ffffffff8471bc50 R14: 1ffff1179c083ef0 R15: 1ffff1179c083eec
   kernel_text_address+0xc1/0x100
   __kernel_text_address+0xe/0x30
   unwind_get_return_address+0x2f/0x50
   __save_stack_trace+0x92/0x100
   create_object+0x380/0x650
   __kmalloc+0x14c/0x2b0
   load_msg+0x38/0x1a0
   do_msgsnd+0x19e/0xcf0
   do_syscall_64+0x117/0x400
   entry_SYSCALL_64_after_hwframe+0x49/0xbe

  rcu: INFO: rcu_preempt detected stalls on CPUs/tasks:
  rcu:     Tasks blocked on level-1 rcu_node (CPUs 0-15): P32170
  rcu:     (detected by 14, t=35016 jiffies, g=44237525, q=12423063)
  msgctl10        R  running task    21608 32170  32155 0x00000082
  Call Trace:
   preempt_schedule_irq+0x4c/0xb0
   retint_kernel+0x1b/0x2d
  RIP: 0010:lock_acquire+0x4d/0x340
  Code: 48 81 ec c0 00 00 00 45 89 c6 4d 89 cf 48 8d 6c 24 20 48 89 3c 24 48 8d bb e4 0c 00 00 89 74 24 0c 48 c7 44 24 20 b3 8a b5 41 <48> c1 ed 03 48 c7 44 24 28 b4 25 18 84 48 c7 44 24 30 d0 54 7a 82
  RSP: 0018:ffff88af83417738 EFLAGS: 00000282 ORIG_RAX: ffffffffffffff13
  RAX: dffffc0000000000 RBX: ffff88bd335f3080 RCX: 0000000000000002
  RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88bd335f3d64
  RBP: ffff88af83417758 R08: 0000000000000000 R09: 0000000000000000
  R10: 0000000000000001 R11: ffffed13f3f745b2 R12: 0000000000000000
  R13: 0000000000000002 R14: 0000000000000000 R15: 0000000000000000
   is_bpf_text_address+0x32/0xe0
   kernel_text_address+0xec/0x100
   __kernel_text_address+0xe/0x30
   unwind_get_return_address+0x2f/0x50
   __save_stack_trace+0x92/0x100
   save_stack+0x32/0xb0
   __kasan_slab_free+0x130/0x180
   kfree+0xfa/0x2d0
   free_msg+0x24/0x50
   do_msgrcv+0x508/0xe60
   do_syscall_64+0x117/0x400
   entry_SYSCALL_64_after_hwframe+0x49/0xbe

Davidlohr said:
 "So after releasing the lock, the msg rbtree/list is empty and new
  calls will not see those in the newly populated tmp_msg list, and
  therefore they cannot access the delayed msg freeing pointers, which
  is good. Also the fact that the node_cache is now freed before the
  actual messages seems to be harmless as this is wanted for
  msg_insert() avoiding GFP_ATOMIC allocations, and after releasing the
  info->lock the thing is freed anyway so it should not change things"

Link: http://lkml.kernel.org/r/1552029161-4957-1-git-send-email-lirongqing@baidu.com
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: Zhang Yu <zhangyu31@baidu.com>
Reviewed-by: Davidlohr Bueso <dbueso@suse.de>
Cc: Manfred Spraul <manfred@colorfullife.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 19:52:52 -07:00

189 lines
3.7 KiB
C

/*
* linux/ipc/msgutil.c
* Copyright (C) 1999, 2004 Manfred Spraul
*
* This file is released under GNU General Public Licence version 2 or
* (at your option) any later version.
*
* See the file COPYING for more details.
*/
#include <linux/spinlock.h>
#include <linux/init.h>
#include <linux/security.h>
#include <linux/slab.h>
#include <linux/ipc.h>
#include <linux/msg.h>
#include <linux/ipc_namespace.h>
#include <linux/utsname.h>
#include <linux/proc_ns.h>
#include <linux/uaccess.h>
#include <linux/sched.h>
#include "util.h"
DEFINE_SPINLOCK(mq_lock);
/*
* The next 2 defines are here bc this is the only file
* compiled when either CONFIG_SYSVIPC and CONFIG_POSIX_MQUEUE
* and not CONFIG_IPC_NS.
*/
struct ipc_namespace init_ipc_ns = {
.count = REFCOUNT_INIT(1),
.user_ns = &init_user_ns,
.ns.inum = PROC_IPC_INIT_INO,
#ifdef CONFIG_IPC_NS
.ns.ops = &ipcns_operations,
#endif
};
struct msg_msgseg {
struct msg_msgseg *next;
/* the next part of the message follows immediately */
};
#define DATALEN_MSG ((size_t)PAGE_SIZE-sizeof(struct msg_msg))
#define DATALEN_SEG ((size_t)PAGE_SIZE-sizeof(struct msg_msgseg))
static struct msg_msg *alloc_msg(size_t len)
{
struct msg_msg *msg;
struct msg_msgseg **pseg;
size_t alen;
alen = min(len, DATALEN_MSG);
msg = kmalloc(sizeof(*msg) + alen, GFP_KERNEL_ACCOUNT);
if (msg == NULL)
return NULL;
msg->next = NULL;
msg->security = NULL;
len -= alen;
pseg = &msg->next;
while (len > 0) {
struct msg_msgseg *seg;
cond_resched();
alen = min(len, DATALEN_SEG);
seg = kmalloc(sizeof(*seg) + alen, GFP_KERNEL_ACCOUNT);
if (seg == NULL)
goto out_err;
*pseg = seg;
seg->next = NULL;
pseg = &seg->next;
len -= alen;
}
return msg;
out_err:
free_msg(msg);
return NULL;
}
struct msg_msg *load_msg(const void __user *src, size_t len)
{
struct msg_msg *msg;
struct msg_msgseg *seg;
int err = -EFAULT;
size_t alen;
msg = alloc_msg(len);
if (msg == NULL)
return ERR_PTR(-ENOMEM);
alen = min(len, DATALEN_MSG);
if (copy_from_user(msg + 1, src, alen))
goto out_err;
for (seg = msg->next; seg != NULL; seg = seg->next) {
len -= alen;
src = (char __user *)src + alen;
alen = min(len, DATALEN_SEG);
if (copy_from_user(seg + 1, src, alen))
goto out_err;
}
err = security_msg_msg_alloc(msg);
if (err)
goto out_err;
return msg;
out_err:
free_msg(msg);
return ERR_PTR(err);
}
#ifdef CONFIG_CHECKPOINT_RESTORE
struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst)
{
struct msg_msgseg *dst_pseg, *src_pseg;
size_t len = src->m_ts;
size_t alen;
if (src->m_ts > dst->m_ts)
return ERR_PTR(-EINVAL);
alen = min(len, DATALEN_MSG);
memcpy(dst + 1, src + 1, alen);
for (dst_pseg = dst->next, src_pseg = src->next;
src_pseg != NULL;
dst_pseg = dst_pseg->next, src_pseg = src_pseg->next) {
len -= alen;
alen = min(len, DATALEN_SEG);
memcpy(dst_pseg + 1, src_pseg + 1, alen);
}
dst->m_type = src->m_type;
dst->m_ts = src->m_ts;
return dst;
}
#else
struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst)
{
return ERR_PTR(-ENOSYS);
}
#endif
int store_msg(void __user *dest, struct msg_msg *msg, size_t len)
{
size_t alen;
struct msg_msgseg *seg;
alen = min(len, DATALEN_MSG);
if (copy_to_user(dest, msg + 1, alen))
return -1;
for (seg = msg->next; seg != NULL; seg = seg->next) {
len -= alen;
dest = (char __user *)dest + alen;
alen = min(len, DATALEN_SEG);
if (copy_to_user(dest, seg + 1, alen))
return -1;
}
return 0;
}
void free_msg(struct msg_msg *msg)
{
struct msg_msgseg *seg;
security_msg_msg_free(msg);
seg = msg->next;
kfree(msg);
while (seg != NULL) {
struct msg_msgseg *tmp = seg->next;
cond_resched();
kfree(seg);
seg = tmp;
}
}