From 1b5c65b64cd417c801945b26a2a50c4d4eefaec8 Mon Sep 17 00:00:00 2001 From: Barry Song <21cnbao@gmail.com> Date: Tue, 14 Nov 2023 16:42:02 +1300 Subject: [PATCH] mm/page_owner: record and dump free_pid and free_tgid While investigating some complex memory allocation and free bugs especially in multi-processes and multi-threads cases, from time to time, I feel the free stack isn't sufficient as a page can be freed by processes or threads other than the one allocating it. And other processes and threads which free the page often have the exactly same free stack with the one allocating the page. We can't know who free the page only through the free stack though the current page_owner does tell us the pid and tgid of the one allocating the page. This makes the bug investigation often hard. So this patch adds free pid and tgid in page_owner, so that we can easily figure out if the freeing is crossing processes or threads. Link: https://lkml.kernel.org/r/20231114034202.73098-1-v-songbaohua@oppo.com Signed-off-by: Barry Song Cc: Audra Mitchell Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Joonsoo Kim Cc: Kassey Li Cc: Kemeng Shi Signed-off-by: Andrew Morton --- mm/page_owner.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/mm/page_owner.c b/mm/page_owner.c index 4f13ce7d2452..e7eba7688881 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -32,6 +32,8 @@ struct page_owner { char comm[TASK_COMM_LEN]; pid_t pid; pid_t tgid; + pid_t free_pid; + pid_t free_tgid; }; static bool page_owner_enabled __initdata; @@ -152,6 +154,8 @@ void __reset_page_owner(struct page *page, unsigned short order) page_owner = get_page_owner(page_ext); page_owner->free_handle = handle; page_owner->free_ts_nsec = free_ts_nsec; + page_owner->free_pid = current->pid; + page_owner->free_tgid = current->tgid; page_ext = page_ext_next(page_ext); } page_ext_put(page_ext); @@ -253,6 +257,8 @@ void __folio_copy_owner(struct folio *newfolio, struct folio *old) new_page_owner->handle = old_page_owner->handle; new_page_owner->pid = old_page_owner->pid; new_page_owner->tgid = old_page_owner->tgid; + new_page_owner->free_pid = old_page_owner->free_pid; + new_page_owner->free_tgid = old_page_owner->free_tgid; new_page_owner->ts_nsec = old_page_owner->ts_nsec; new_page_owner->free_ts_nsec = old_page_owner->ts_nsec; strcpy(new_page_owner->comm, old_page_owner->comm); @@ -495,7 +501,8 @@ void __dump_page_owner(const struct page *page) if (!handle) { pr_alert("page_owner free stack trace missing\n"); } else { - pr_alert("page last free stack trace:\n"); + pr_alert("page last free pid %d tgid %d stack trace:\n", + page_owner->free_pid, page_owner->free_tgid); stack_depot_print(handle); }