@@ -28,6 +28,7 @@
#include <linux/sched/task.h>
#include <linux/sched/debug.h>
#include <linux/swap.h>
+#include <linux/syscalls.h>
#include <linux/timex.h>
#include <linux/jiffies.h>
#include <linux/cpuset.h>
@@ -1141,3 +1142,68 @@ void pagefault_out_of_memory(void)
out_of_memory(&oc);
mutex_unlock(&oom_lock);
}
+
+SYSCALL_DEFINE2(process_mrelease, int, pidfd, unsigned int, flags)
+{
+#ifdef CONFIG_MMU
+ struct mm_struct *mm = NULL;
+ struct task_struct *task;
+ unsigned int f_flags;
+ struct pid *pid;
+ long ret = 0;
+
+ if (flags)
+ return -EINVAL;
+
+ pid = pidfd_get_pid(pidfd, &f_flags);
+ if (IS_ERR(pid))
+ return PTR_ERR(pid);
+
+ task = get_pid_task(pid, PIDTYPE_PID);
+ if (!task) {
+ ret = -ESRCH;
+ goto put_pid;
+ }
+
+ /*
+ * If the task is dying and in the process of releasing its memory
+ * then get its mm.
+ */
+ task = find_lock_task_mm(task);
+ if (!task) {
+ ret = -ESRCH;
+ goto put_pid;
+ }
+ if (task_will_free_mem(task) && (task->flags & PF_KTHREAD) == 0) {
+ mm = task->mm;
+ mmget(mm);
+ }
+ task_unlock(task);
+ if (!mm) {
+ ret = -EINVAL;
+ goto put_task;
+ }
+ if (test_bit(MMF_OOM_SKIP, &mm->flags)) {
+ ret = -ESRCH;
+ goto put_mm;
+ }
+
+ if (mmap_read_lock_killable(mm)) {
+ ret = -EINTR;
+ goto put_mm;
+ }
+ if (!__oom_reap_task_mm(mm))
+ ret = -EAGAIN;
+ mmap_read_unlock(mm);
+
+put_mm:
+ mmput(mm);
+put_task:
+ put_task_struct(task);
+put_pid:
+ put_pid(pid);
+ return ret;
+#else
+ return -ENOSYS;
+#endif /* CONFIG_MMU */
+}
In modern systems it's not unusual to have a system component monitoring memory conditions of the system and tasked with keeping system memory pressure under control. One way to accomplish that is to kill non-essential processes to free up memory for more important ones. Examples of this are Facebook's OOM killer daemon called oomd and Android's low memory killer daemon called lmkd. For such system component it's important to be able to free memory quickly and efficiently. Unfortunately the time process takes to free up its memory after receiving a SIGKILL might vary based on the state of the process (uninterruptible sleep), size and OPP level of the core the process is running. A mechanism to free resources of the target process in a more predictable way would improve system's ability to control its memory pressure. Introduce process_mrelease system call that releases memory of a dying process from the context of the caller. This way the memory is freed in a more controllable way with CPU affinity and priority of the caller. The workload of freeing the memory will also be charged to the caller. The operation is allowed only on a dying process. After previous discussions [1, 2, 3] the decision was made [4] to introduce a dedicated system call to cover this use case. The API is as follows, int process_mrelease(int pidfd, unsigned int flags); DESCRIPTION The process_mrelease() system call is used to free the memory of an exiting process. The pidfd selects the process referred to by the PID file descriptor. (See pidofd_open(2) for further information) The flags argument is reserved for future use; currently, this argument must be specified as 0. RETURN VALUE On success, process_mrelease() returns 0. On error, -1 is returned and errno is set to indicate the error. ERRORS EBADF pidfd is not a valid PID file descriptor. EAGAIN Failed to release part of the address space. EINTR The call was interrupted by a signal; see signal(7). EINVAL flags is not 0. EINVAL The memory of the task cannot be released because the process is not exiting, the address space is shared with another live process or there is a core dump in progress. ENOSYS This system call is not supported, for example, without MMU support built into Linux. ESRCH The target process does not exist (i.e., it has terminated and been waited on). [1] https://lore.kernel.org/lkml/20190411014353.113252-3-surenb@google.com/ [2] https://lore.kernel.org/linux-api/20201113173448.1863419-1-surenb@google.com/ [3] https://lore.kernel.org/linux-api/20201124053943.1684874-3-surenb@google.com/ [4] https://lore.kernel.org/linux-api/20201223075712.GA4719@lst.de/ Signed-off-by: Suren Baghdasaryan <surenb@google.com> --- changes in v5: - Changed links, per David Hildenbrand and Michal Hocko - Condensed the background section in the description, per David Hildenbrand - Changed flags check, per David Hildenbrand - Changed description for ENOSYS in the manual pages, per David Hildenbrand - Changed wording from "SIGKILLed" to "exiting" process in the manual pages description, per Michal Hocko - Used find_lock_task_mm() to lock the task_struct, per Michal Hocko - Added check for MMF_OOM_SKIP, per Michal Hocko mm/oom_kill.c | 66 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 66 insertions(+)