memcg: charge fs_context and legacy_fs_context

mainline inclusion
from mainline-v5.15-rc1
commit bb902cb4
bugzilla: 181858 https://gitee.com/openeuler/kernel/issues/I4DDEL

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=bb902cb47cf93b33cd92b3b7a4019330a03ef57f

--------------------------------

This patch adds accounting flags to fs_context and legacy_fs_context
allocation sites so that kernel could correctly charge these objects.

We have written a PoC to demonstrate the effect of the missing-charging
bugs.  The PoC takes around 1,200MB unaccounted memory, while it is
charged for only 362MB memory usage.  We evaluate the PoC on QEMU x86_64
v5.2.90 + Linux kernel v5.10.19 + Debian buster.  All the limitations
including ulimits and sysctl variables are set as default.  Specifically,
the hard NOFILE limit and nr_open in sysctl are both 1,048,576.

/*------------------------- POC code ----------------------------*/

                        } while (0)

static inline int fsopen(const char *fs_name, unsigned int flags)
{
        return syscall(__NR_fsopen, fs_name, flags);
}

static char thread_stack[512][STACK_SIZE];

int thread_fn(void* arg)
{
  for (int i = 0; i< 800000; ++i) {
    int fsfd = fsopen("nfs", FSOPEN_CLOEXEC);
    if (fsfd == -1) {
      errExit("fsopen");
    }
  }
  while(1);
  return 0;
}

int main(int argc, char *argv[]) {
  int thread_pid;
  for (int i = 0; i < 1; ++i) {
    thread_pid = clone(thread_fn, thread_stack[i] + STACK_SIZE, \
      SIGCHLD, NULL);
  }
  while(1);
  return 0;
}

/*-------------------------- end --------------------------------*/

Link: https://lkml.kernel.org/r/1626517201-24086-1-git-send-email-nglaive@gmail.comSigned-off-by: NYutian Yang <nglaive@gmail.com>
Reviewed-by: NShakeel Butt <shakeelb@google.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: <shenwenbo@zju.edu.cn>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: NLi Ming <limingming.li@huawei.com>
Signed-off-by: NLu Jialin <lujialin4@huawei.com>
Reviewed-by: NXiu Jianfeng <xiujianfeng@huawei.com>
Signed-off-by: NChen Jun <chenjun102@huawei.com>
Signed-off-by: NZheng Zengkai <zhengzengkai@huawei.com>

fs/fs_context.c

@@ -231,7 +231,7 @@ static struct fs_context *alloc_fs_context(struct file_system_type *fs_type,
 	struct fs_context *fc;
 	int ret = -ENOMEM;
 
-	fc = kzalloc(sizeof(struct fs_context), GFP_KERNEL);
+	fc = kzalloc(sizeof(struct fs_context), GFP_KERNEL_ACCOUNT);
 	if (!fc)
 		return ERR_PTR(-ENOMEM);
 
@@ -631,7 +631,7 @@ const struct fs_context_operations legacy_fs_context_ops = {
  */
 static int legacy_init_fs_context(struct fs_context *fc)
 {
-	fc->fs_private = kzalloc(sizeof(struct legacy_fs_context), GFP_KERNEL);
+	fc->fs_private = kzalloc(sizeof(struct legacy_fs_context), GFP_KERNEL_ACCOUNT);
 	if (!fc->fs_private)
 		return -ENOMEM;
 	fc->ops = &legacy_fs_context_ops;