mm: update mark_victim tracepoints fields

The current implementation of the mark_victim tracepoint provides only the
process ID (pid) of the victim process.  This limitation poses challenges
for userspace tools requiring real-time OOM analysis and intervention.
Although this information is available from the kernel logs, it’s not
the appropriate format to provide OOM notifications.  In Android, BPF
programs are used with the mark_victim trace events to notify userspace of
an OOM kill.  For consistency, update the trace event to include the same
information about the OOMed victim as the kernel logs.

- UID
   In Android each installed application has a unique UID. Including
   the `uid` assists in correlating OOM events with specific apps.

- Process Name (comm)
   Enables identification of the affected process.

- OOM Score
  Will allow userspace to get additional insight of the relative kill
  priority of the OOM victim. In Android, the oom_score_adj is used to
  categorize app state (foreground, background, etc.), which aids in
  analyzing user-perceptible impacts of OOM events [1].

- Total VM, RSS Stats, and pgtables
  Amount of memory used by the victim that will, potentially, be freed up
  by killing it.

[1] https://cs.android.com/android/platform/superproject/main/+/246dc8fc95b6d93afcba5c6d6c133307abb3ac2e:frameworks/base/services/core/java/com/android/server/am/ProcessList.java;l=188-283
Signed-off-by: Carlos Galo <carlosgalo@google.com>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/trace/events/oom.h b/include/trace/events/oom.h
index 26a11e4a2c361d21e550ea500df01ec3e10d791a..b799f3bcba8233e7e693e3363b4e576c07d3eefe 100644 (file)
--- a/include/trace/events/oom.h
+++ b/include/trace/events/oom.h
@@ -7,6 +7,8 @@
 #include <linux/tracepoint.h>
 #include <trace/events/mmflags.h>
 
+#define PG_COUNT_TO_KB(x) ((x) << (PAGE_SHIFT - 10))
+
 TRACE_EVENT(oom_score_adj_update,
 
        TP_PROTO(struct task_struct *task),
@@ -72,19 +74,45 @@ TRACE_EVENT(reclaim_retry_zone,
 );
 
 TRACE_EVENT(mark_victim,
-       TP_PROTO(int pid),
+       TP_PROTO(struct task_struct *task, uid_t uid),
 
-       TP_ARGS(pid),
+       TP_ARGS(task, uid),
 
        TP_STRUCT__entry(
                __field(int, pid)
+               __string(comm, task->comm)
+               __field(unsigned long, total_vm)
+               __field(unsigned long, anon_rss)
+               __field(unsigned long, file_rss)
+               __field(unsigned long, shmem_rss)
+               __field(uid_t, uid)
+               __field(unsigned long, pgtables)
+               __field(short, oom_score_adj)
        ),
 
        TP_fast_assign(
-               __entry->pid = pid;
+               __entry->pid = task->pid;
+               __assign_str(comm, task->comm);
+               __entry->total_vm = PG_COUNT_TO_KB(task->mm->total_vm);
+               __entry->anon_rss = PG_COUNT_TO_KB(get_mm_counter(task->mm, MM_ANONPAGES));
+               __entry->file_rss = PG_COUNT_TO_KB(get_mm_counter(task->mm, MM_FILEPAGES));
+               __entry->shmem_rss = PG_COUNT_TO_KB(get_mm_counter(task->mm, MM_SHMEMPAGES));
+               __entry->uid = uid;
+               __entry->pgtables = mm_pgtables_bytes(task->mm) >> 10;
+               __entry->oom_score_adj = task->signal->oom_score_adj;
        ),
 
-       TP_printk("pid=%d", __entry->pid)
+       TP_printk("pid=%d comm=%s total-vm=%lukB anon-rss=%lukB file-rss:%lukB shmem-rss:%lukB uid=%u pgtables=%lukB oom_score_adj=%hd",
+               __entry->pid,
+               __get_str(comm),
+               __entry->total_vm,
+               __entry->anon_rss,
+               __entry->file_rss,
+               __entry->shmem_rss,
+               __entry->uid,
+               __entry->pgtables,
+               __entry->oom_score_adj
+       )
 );
 
 TRACE_EVENT(wake_reaper,

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 91ccd82097c2ba7f9e9eb55437d07c38dfcd25a3..8d6a207c3c59052b93881fb51d4926dbd9d76f37 100644 (file)
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -44,6 +44,7 @@
 #include <linux/kthread.h>
 #include <linux/init.h>
 #include <linux/mmu_notifier.h>
+#include <linux/cred.h>
 
 #include <asm/tlb.h>
 #include "internal.h"
@@ -754,6 +755,7 @@ static inline void queue_oom_reaper(struct task_struct *tsk)
  */
 static void mark_oom_victim(struct task_struct *tsk)
 {
+       const struct cred *cred;
        struct mm_struct *mm = tsk->mm;
 
        WARN_ON(oom_killer_disabled);
@@ -773,7 +775,9 @@ static void mark_oom_victim(struct task_struct *tsk)
         */
        __thaw_task(tsk);
        atomic_inc(&oom_victims);
-       trace_mark_victim(tsk->pid);
+       cred = get_task_cred(tsk);
+       trace_mark_victim(tsk, cred->uid.val);
+       put_cred(cred);
 }
 
 /**