By default, device-backed private node memory may not be safe to migrate without coordination.
Do not attempt to hotunplug private node memory, instead fail the hotunplug attempt, and require the owner to drain the folios safely before allowing hotunplug to proceed. Unlike transient / longterm pins causing failures, this is not a transient condition - so we can break out of the hotunplug attempt entirely instead of spinning forever on a failed migration attempt. Signed-off-by: Gregory Price <[email protected]> --- mm/memory_hotplug.c | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 226ab9cb078ad..2b9c0830821e6 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -34,6 +34,7 @@ #include <linux/memblock.h> #include <linux/compaction.h> #include <linux/rmap.h> +#include <linux/node_private.h> #include <linux/module.h> #include <linux/node.h> @@ -1843,11 +1844,12 @@ static int scan_movable_pages(unsigned long start, unsigned long end, return 0; } -static void do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) +static int do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) { struct folio *folio; unsigned long pfn; LIST_HEAD(source); + int err = 0; static DEFINE_RATELIMIT_STATE(migrate_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); @@ -1884,6 +1886,15 @@ static void do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) goto put_folio; } + /* Private node folios cannot migrate, fail outright */ + if (folio_is_private_node(folio)) { + pr_info_ratelimited("memory offline refused: node %d pfn %lx\n", + folio_nid(folio), pfn); + folio_put(folio); + err = -EBUSY; + break; + } + if (!isolate_folio_to_list(folio, &source)) { if (__ratelimit(&migrate_rs)) { pr_warn("failed to isolate pfn %lx\n", @@ -1931,6 +1942,7 @@ static void do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) putback_movable_pages(&source); } } + return err; } static int __init cmdline_parse_movable_node(char *p) @@ -2067,10 +2079,11 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages, ret = scan_movable_pages(pfn, end_pfn, &pfn); if (!ret) { /* - * TODO: fatal migration failures should bail - * out + * A fatal migration failure (e.g. a folio on a + * non-migratable private node) bails out; transient + * failures leave ret zero and are retried below. */ - do_migrate_range(pfn, end_pfn); + ret = do_migrate_range(pfn, end_pfn); } } while (!ret); -- 2.53.0-Meta
