The discussion[1] with Sergey shows there are some cleanup works to do in get/set_zspage_mapping(): - the fullness returned from get_zspage_mapping() is not stable outside pool->lock, this usage pattern is confusing, but should be ok in this free_zspage path. - we seldom use the class_idx returned from get_zspage_mapping(), only free_zspage path use to get its class. - set_zspage_mapping() always set the zspage->class, but it's never changed after zspage allocated. [1] https://lore.kernel.org/all/a6c22e30-cf10-4122-91bc-ceb9fb57a5d6@xxxxxxxxxxxxx/ Signed-off-by: Chengming Zhou <zhouchengming@xxxxxxxxxxxxx> --- Chengming Zhou (3): mm/zsmalloc: remove set_zspage_mapping() mm/zsmalloc: remove_zspage() don't need fullness parameter mm/zsmalloc: remove get_zspage_mapping() mm/zsmalloc.c | 55 +++++++++++++------------------------------------------ 1 file changed, 13 insertions(+), 42 deletions(-) --- base-commit: 207636f0f52428f3b46540b212d6f93c6ac484cf change-id: 20240220-b4-zsmalloc-cleanup-560a4159bb6b Best regards, -- Chengming Zhou <zhouchengming@xxxxxxxxxxxxx>
