>
> From: Michal Hocko <mhocko@xxxxxxxx>
>
> Currently we have two proc interfaces to set oom_score_adj. The legacy
> /proc/<pid>/oom_adj and /proc/<pid>/oom_score_adj which both have their
> specific handlers. Big part of the logic is duplicated so extract the
> common code into __set_oom_adj helper. Legacy knob still expects some
> details slightly different so make sure those are handled same way - e.g.
> the legacy mode ignores oom_score_adj_min and it warns about the usage.
>
> This patch shouldn't introduce any functional changes.
>
> Acked-by: Oleg Nesterov <oleg@xxxxxxxxxx>
> Signed-off-by: Michal Hocko <mhocko@xxxxxxxx>
> ---
> fs/proc/base.c | 94 +++++++++++++++++++++++++++-------------------------------
> 1 file changed, 43 insertions(+), 51 deletions(-)
>
> diff --git a/fs/proc/base.c b/fs/proc/base.c
> index 968d5ea06e62..a6a8fbdd5a1b 100644
> --- a/fs/proc/base.c
> +++ b/fs/proc/base.c
> @@ -1037,7 +1037,47 @@ static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count,
> return simple_read_from_buffer(buf, count, ppos, buffer, len);
> }
>
> -static DEFINE_MUTEX(oom_adj_mutex);
> +static int __set_oom_adj(struct file *file, int oom_adj, bool legacy)
> +{
> + static DEFINE_MUTEX(oom_adj_mutex);
Writers are not excluded for readers!
Is this a hot path?
> + struct task_struct *task;
> + int err = 0;
> +
> + task = get_proc_task(file_inode(file));
> + if (!task)
> + return -ESRCH;
> +
> + mutex_lock(&oom_adj_mutex);
> + if (legacy) {
> + if (oom_adj < task->signal->oom_score_adj &&
> + !capable(CAP_SYS_RESOURCE)) {
> + err = -EACCES;
> + goto err_unlock;
> + }
> + /*
> + * /proc/pid/oom_adj is provided for legacy purposes, ask users to use
> + * /proc/pid/oom_score_adj instead.
> + */
> + pr_warn_once("%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n",
> + current->comm, task_pid_nr(current), task_pid_nr(task),
> + task_pid_nr(task));
> + } else {
> + if ((short)oom_adj < task->signal->oom_score_adj_min &&
> + !capable(CAP_SYS_RESOURCE)) {
> + err = -EACCES;
> + goto err_unlock;
> + }
> + }
> +
> + task->signal->oom_score_adj = oom_adj;
> + if (!legacy && has_capability_noaudit(current, CAP_SYS_RESOURCE))
> + task->signal->oom_score_adj_min = (short)oom_adj;
> + trace_oom_score_adj_update(task);
> +err_unlock:
> + mutex_unlock(&oom_adj_mutex);
> + put_task_struct(task);
> + return err;
> +}
>
> /*
> * /proc/pid/oom_adj exists solely for backwards compatibility with previous
> @@ -1052,7 +1092,6 @@ static DEFINE_MUTEX(oom_adj_mutex);
> static ssize_t oom_adj_write(struct file *file, const char __user *buf,
> size_t count, loff_t *ppos)
> {
> - struct task_struct *task;
> char buffer[PROC_NUMBUF];
> int oom_adj;
> int err;
> @@ -1074,12 +1113,6 @@ static ssize_t oom_adj_write(struct file *file, const char __user *buf,
> goto out;
> }
>
> - task = get_proc_task(file_inode(file));
> - if (!task) {
> - err = -ESRCH;
> - goto out;
> - }
> -
> /*
> * Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum
> * value is always attainable.
> @@ -1089,26 +1122,7 @@ static ssize_t oom_adj_write(struct file *file, const char __user *buf,
> else
> oom_adj = (oom_adj * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE;
>
> - mutex_lock(&oom_adj_mutex);
> - if (oom_adj < task->signal->oom_score_adj &&
> - !capable(CAP_SYS_RESOURCE)) {
> - err = -EACCES;
> - goto err_unlock;
> - }
> -
> - /*
> - * /proc/pid/oom_adj is provided for legacy purposes, ask users to use
> - * /proc/pid/oom_score_adj instead.
> - */
> - pr_warn_once("%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n",
> - current->comm, task_pid_nr(current), task_pid_nr(task),
> - task_pid_nr(task));
> -
> - task->signal->oom_score_adj = oom_adj;
> - trace_oom_score_adj_update(task);
> -err_unlock:
> - mutex_unlock(&oom_adj_mutex);
> - put_task_struct(task);
> + err = __set_oom_adj(file, oom_adj, true);
> out:
> return err < 0 ? err : count;
> }
> @@ -1138,7 +1152,6 @@ static ssize_t oom_score_adj_read(struct file *file, char __user *buf,
> static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
> size_t count, loff_t *ppos)
> {
> - struct task_struct *task;
> char buffer[PROC_NUMBUF];
> int oom_score_adj;
> int err;
> @@ -1160,28 +1173,7 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
> goto out;
> }
>
> - task = get_proc_task(file_inode(file));
> - if (!task) {
> - err = -ESRCH;
> - goto out;
> - }
> -
> - mutex_lock(&oom_adj_mutex);
> - if ((short)oom_score_adj < task->signal->oom_score_adj_min &&
> - !capable(CAP_SYS_RESOURCE)) {
> - err = -EACCES;
> - goto err_unlock;
> - }
> -
> - task->signal->oom_score_adj = (short)oom_score_adj;
> - if (has_capability_noaudit(current, CAP_SYS_RESOURCE))
> - task->signal->oom_score_adj_min = (short)oom_score_adj;
> -
> - trace_oom_score_adj_update(task);
> -
> -err_unlock:
> - mutex_unlock(&oom_adj_mutex);
> - put_task_struct(task);
> + err = __set_oom_adj(file, oom_score_adj, false);
> out:
> return err < 0 ? err : count;
> }
> --
> 2.8.1
>
>
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>