From: Oscar Salvador <osalvador@xxxxxxx> Subject: mm,hwpoison: disable pcplists before grabbing a refcount Currently, we have a sort of retry mechanism to make sure pages in pcp-lists are spilled to the buddy system, so we can handle those. We can save us this extra checks with the new disable-pcplist mechanism that is available with [1]. zone_pcplist_disable makes sure to 1) disable pcplists, so any page that is freed up from that point onwards will end up in the buddy system and 2) drain pcplists, so those pages that already in pcplists are spilled to buddy. With that, we can make a common entry point for grabbing a refcount from both soft_offline and memory_failure paths that is guarded by zone_pcplist_disable/zone_pcplist_enable. [1] https://patchwork.kernel.org/project/linux-mm/cover/20201111092812.11329-1-vbabka@xxxxxxx/ Link: https://lkml.kernel.org/r/20201204102558.31607-3-osalvador@xxxxxxx Signed-off-by: Oscar Salvador <osalvador@xxxxxxx> Acked-by: Naoya Horiguchi <naoya.horiguchi@xxxxxxx> Acked-by: Vlastimil Babka <vbabka@xxxxxxx> Cc: Qian Cai <qcai@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/memory-failure.c | 132 ++++++++++++++++++++---------------------- 1 file changed, 65 insertions(+), 67 deletions(-) --- a/mm/memory-failure.c~mmhwpoison-disable-pcplists-before-grabbing-a-refcount +++ a/mm/memory-failure.c @@ -985,26 +985,73 @@ static int __get_hwpoison_page(struct pa return 0; } -static int get_hwpoison_page(struct page *p) +/* + * Safely get reference count of an arbitrary page. + * + * Returns 0 for a free page, 1 for an in-use page, + * -EIO for a page-type we cannot handle and -EBUSY if we raced with an + * allocation. + * We only incremented refcount in case the page was already in-use and it + * is a known type we can handle. + */ +static int get_any_page(struct page *p, unsigned long flags) { - int ret; - bool drained = false; + int ret = 0, pass = 0; + bool count_increased = false; -retry: - ret = __get_hwpoison_page(p); - if (!ret && !is_free_buddy_page(p) && !page_count(p) && !drained) { - /* - * The page might be in a pcplist, so try to drain those - * and see if we are lucky. - */ - drain_all_pages(page_zone(p)); - drained = true; - goto retry; + if (flags & MF_COUNT_INCREASED) + count_increased = true; + +try_again: + if (!count_increased && !__get_hwpoison_page(p)) { + if (page_count(p)) { + /* We raced with an allocation, retry. */ + if (pass++ < 3) + goto try_again; + ret = -EBUSY; + } else if (!PageHuge(p) && !is_free_buddy_page(p)) { + /* We raced with put_page, retry. */ + if (pass++ < 3) + goto try_again; + ret = -EIO; + } + } else { + if (PageHuge(p) || PageLRU(p) || __PageMovable(p)) { + ret = 1; + } else { + /* + * A page we cannot handle. Check whether we can turn + * it into something we can handle. + */ + if (pass++ < 3) { + put_page(p); + shake_page(p, 1); + count_increased = false; + goto try_again; + } + put_page(p); + ret = -EIO; + } } return ret; } +static int get_hwpoison_page(struct page *p, unsigned long flags, + enum mf_flags ctxt) +{ + int ret; + + zone_pcp_disable(page_zone(p)); + if (ctxt == MF_SOFT_OFFLINE) + ret = get_any_page(p, flags); + else + ret = __get_hwpoison_page(p); + zone_pcp_enable(page_zone(p)); + + return ret; +} + /* * Do all that is necessary to remove user space mappings. Unmap * the pages and send SIGBUS to the processes if the data was dirty. @@ -1185,7 +1232,7 @@ static int memory_failure_hugetlb(unsign num_poisoned_pages_inc(); - if (!(flags & MF_COUNT_INCREASED) && !get_hwpoison_page(p)) { + if (!(flags & MF_COUNT_INCREASED) && !get_hwpoison_page(p, flags, 0)) { /* * Check "filter hit" and "race with other subpage." */ @@ -1387,7 +1434,7 @@ try_again: * In fact it's dangerous to directly bump up page count from 0, * that may make page_ref_freeze()/page_ref_unfreeze() mismatch. */ - if (!(flags & MF_COUNT_INCREASED) && !get_hwpoison_page(p)) { + if (!(flags & MF_COUNT_INCREASED) && !get_hwpoison_page(p, flags, 0)) { if (is_free_buddy_page(p)) { if (take_page_off_buddy(p)) { page_ref_inc(p); @@ -1630,6 +1677,7 @@ int unpoison_memory(unsigned long pfn) struct page *page; struct page *p; int freeit = 0; + unsigned long flags = 0; static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); @@ -1674,7 +1722,7 @@ int unpoison_memory(unsigned long pfn) return 0; } - if (!get_hwpoison_page(p)) { + if (!get_hwpoison_page(p, flags, 0)) { if (TestClearPageHWPoison(p)) num_poisoned_pages_dec(); unpoison_pr_info("Unpoison: Software-unpoisoned free page %#lx\n", @@ -1705,56 +1753,6 @@ int unpoison_memory(unsigned long pfn) } EXPORT_SYMBOL(unpoison_memory); -/* - * Safely get reference count of an arbitrary page. - * Returns 0 for a free page, 1 for an in-use page, -EIO for a page-type we - * cannot handle and -EBUSY if we raced with an allocation. - * We only incremented refcount in case the page was already in-use and it is - * a known type we can handle. - */ -static int get_any_page(struct page *p, int flags) -{ - int ret = 0, pass = 0; - bool count_increased = false; - - if (flags & MF_COUNT_INCREASED) - count_increased = true; - -try_again: - if (!count_increased && !get_hwpoison_page(p)) { - if (page_count(p)) { - /* We raced with an allocation, retry. */ - if (pass++ < 3) - goto try_again; - ret = -EBUSY; - } else if (!PageHuge(p) && !is_free_buddy_page(p)) { - /* We raced with put_page, retry. */ - if (pass++ < 3) - goto try_again; - ret = -EIO; - } - } else { - if (PageHuge(p) || PageLRU(p) || __PageMovable(p)) { - ret = 1; - } else { - /* - * A page we cannot handle. Check whether we can turn - * it into something we can handle. - */ - if (pass++ < 3) { - put_page(p); - shake_page(p, 1); - count_increased = false; - goto try_again; - } - put_page(p); - ret = -EIO; - } - } - - return ret; -} - static bool isolate_page(struct page *page, struct list_head *pagelist) { bool isolated = false; @@ -1928,7 +1926,7 @@ int soft_offline_page(unsigned long pfn, retry: get_online_mems(); - ret = get_any_page(page, flags); + ret = get_hwpoison_page(page, flags, MF_SOFT_OFFLINE); put_online_mems(); if (ret > 0) { _
