Compute the page's NUMA node in page_owner_next_eligible() while the page is still valid, and store it in scan->nid.
The debugfs nid filter reads scan->nid instead of recomputing it, and a BPF program iterating the cursor reads the node straight from scan->nid. Resolve nid at scan time to avoid dereferencing a possibly-unmapped page. Keep it in the transient scan cursor rather than struct page_owner, so nid does not add per-page memory overhead. Signed-off-by: Zhen Ni <[email protected]> --- Changes in v2: - Removes the v1 get_nid() kfunc. The node is now stored in scan->nid. v1: https://lore.kernel.org/linux-mm/[email protected]/ --- mm/page_owner.c | 28 ++++++++++++++++------------ mm/page_owner.h | 1 + mm/page_owner_iter.c | 5 ++++- 3 files changed, 21 insertions(+), 13 deletions(-) diff --git a/mm/page_owner.c b/mm/page_owner.c index 617346a4ab22..113e4e7e0b3a 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -711,6 +711,19 @@ void __dump_page_owner(const struct page *page) page_ext_put(page_ext); } +/* + * NUMA node of @page, bypassing PF_POISONED_CHECK() in page_to_nid() to + * avoid VM_BUG_ON on poisoned pages; -1 for poisoned pages. + */ +static int page_owner_get_nid(struct page *page) +{ + memdesc_flags_t page_flags = READ_ONCE(page->flags); + + if (page_flags.f == PAGE_POISON_PATTERN) + return -1; + return memdesc_nid(&page_flags); +} + /* * Advance @scan to the next page eligible for page_owner output. * On a hit, fill scan->pfn/page/po_snap and return true; the caller @@ -782,6 +795,7 @@ bool page_owner_next_eligible(struct page_owner_scan *scan) if (!scan->po_snap.handle) goto ext_put_continue; + scan->nid = page_owner_get_nid(page); page_ext_put(page_ext); return true; @@ -810,18 +824,8 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos) /* Find an allocated page */ while (page_owner_next_eligible(&scan)) { if (state->nid_filter_enabled) { - int nid; - memdesc_flags_t page_flags = - READ_ONCE(scan.page->flags); - - /* - * Bypass PF_POISONED_CHECK() in page_to_nid() to avoid - * VM_BUG_ON when accessing poisoned pages. - */ - if (page_flags.f == PAGE_POISON_PATTERN) - goto skip_continue; - nid = memdesc_nid(&page_flags); - if (!node_isset(nid, state->nid_filter)) + if (scan.nid < 0 || + !node_isset(scan.nid, state->nid_filter)) goto skip_continue; } diff --git a/mm/page_owner.h b/mm/page_owner.h index fda83be69275..e8e52d22abed 100644 --- a/mm/page_owner.h +++ b/mm/page_owner.h @@ -36,6 +36,7 @@ struct page_owner_scan { unsigned long pfn; struct page *page; struct page_owner po_snap; + int nid; }; bool page_owner_next_eligible(struct page_owner_scan *scan); diff --git a/mm/page_owner_iter.c b/mm/page_owner_iter.c index ac7e69ba0cef..a2b90c874852 100644 --- a/mm/page_owner_iter.c +++ b/mm/page_owner_iter.c @@ -13,10 +13,12 @@ struct bpf_iter__page_owner { __bpf_md_ptr(struct page *, page); __bpf_md_ptr(struct page_owner *, po); u64 pfn; + int nid; }; DEFINE_BPF_ITER_FUNC(page_owner, struct bpf_iter_meta *meta, - struct page *page, struct page_owner *po, u64 pfn) + struct page *page, struct page_owner *po, u64 pfn, + int nid) static void *page_owner_seq_start(struct seq_file *seq, loff_t *posp) { @@ -54,6 +56,7 @@ static int page_owner_prog_seq_show(struct bpf_prog *prog, /* @po: hit-time snapshot, no RCU window needed. */ ctx.po = &scan->po_snap; ctx.pfn = scan->pfn; + ctx.nid = scan->nid; } return bpf_iter_run_prog(prog, &ctx); -- 2.20.1
