From cb829624867b5ab10bc6a7036d183b1b82bfe9f8 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Thu, 30 Jan 2020 22:14:29 -0800 Subject: mm/huge_memory.c: use head to check huge zero page The page could be a tail page, if this is the case, this BUG_ON will never be triggered. Link: http://lkml.kernel.org/r/20200110032610.26499-1-richardw.yang@linux.intel.com Fixes: e9b61f19858a ("thp: reintroduce split_huge_page()") Signed-off-by: Wei Yang Acked-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm/huge_memory.c') diff --git a/mm/huge_memory.c b/mm/huge_memory.c index a88093213674..ee1dafedd8fe 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2712,7 +2712,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) unsigned long flags; pgoff_t end; - VM_BUG_ON_PAGE(is_huge_zero_page(page), page); + VM_BUG_ON_PAGE(is_huge_zero_page(head), head); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(!PageCompound(page), page); -- cgit v1.2.3 From a8803e6c177f490fe5624397b07f4eb05a15f532 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Thu, 30 Jan 2020 22:14:32 -0800 Subject: mm/huge_memory.c: use head to emphasize the purpose of page During split huge page, it checks the property of the page. Currently we do the check on page and head without emphasizing the check is on the compound page. In case the page passed to split_huge_page_to_list is a tail page, audience would take some time to think about whether the check is on compound page or tail page itself. To make it explicit, use head instead of page for those checks. After this, audience would be more clear about the checks are on compound page and the page is used to do the split and dump error message if failed. Link: http://lkml.kernel.org/r/20200110032610.26499-2-richardw.yang@linux.intel.com Signed-off-by: Wei Yang Acked-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'mm/huge_memory.c') diff --git a/mm/huge_memory.c b/mm/huge_memory.c index ee1dafedd8fe..4439e91f8443 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2704,7 +2704,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) { struct page *head = compound_head(page); struct pglist_data *pgdata = NODE_DATA(page_to_nid(head)); - struct deferred_split *ds_queue = get_deferred_split_queue(page); + struct deferred_split *ds_queue = get_deferred_split_queue(head); struct anon_vma *anon_vma = NULL; struct address_space *mapping = NULL; int count, mapcount, extra_pins, ret; @@ -2713,10 +2713,10 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) pgoff_t end; VM_BUG_ON_PAGE(is_huge_zero_page(head), head); - VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(!PageCompound(page), page); + VM_BUG_ON_PAGE(!PageLocked(head), head); + VM_BUG_ON_PAGE(!PageCompound(head), head); - if (PageWriteback(page)) + if (PageWriteback(head)) return -EBUSY; if (PageAnon(head)) { @@ -2767,7 +2767,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) goto out_unlock; } - mlocked = PageMlocked(page); + mlocked = PageMlocked(head); unmap_page(head); VM_BUG_ON_PAGE(compound_mapcount(head), head); @@ -2800,10 +2800,10 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) list_del(page_deferred_list(head)); } if (mapping) { - if (PageSwapBacked(page)) - __dec_node_page_state(page, NR_SHMEM_THPS); + if (PageSwapBacked(head)) + __dec_node_page_state(head, NR_SHMEM_THPS); else - __dec_node_page_state(page, NR_FILE_THPS); + __dec_node_page_state(head, NR_FILE_THPS); } spin_unlock(&ds_queue->split_queue_lock); -- cgit v1.2.3 From afb971729a0bca7676606013e913025bc5619301 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Thu, 30 Jan 2020 22:14:35 -0800 Subject: mm/huge_memory.c: reduce critical section protected by split_queue_lock split_queue_lock protects data in struct deferred_split. We can release the lock after delete the page from deferred_split_queue. This patch moves the THP accounting out of the lock protection, which is introduced in commit 65c453778aea ("mm, rmap: account shmem thp pages"). Link: http://lkml.kernel.org/r/20200110025516.23996-1-richardw.yang@linux.intel.com Signed-off-by: Wei Yang Reviewed-by: Andrew Morton Acked-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm/huge_memory.c') diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 4439e91f8443..5b2876942639 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2799,6 +2799,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) ds_queue->split_queue_len--; list_del(page_deferred_list(head)); } + spin_unlock(&ds_queue->split_queue_lock); if (mapping) { if (PageSwapBacked(head)) __dec_node_page_state(head, NR_SHMEM_THPS); @@ -2806,7 +2807,6 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) __dec_node_page_state(head, NR_FILE_THPS); } - spin_unlock(&ds_queue->split_queue_lock); __split_huge_page(page, list, end, flags); if (PageSwapCache(head)) { swp_entry_t entry = { .val = page_private(head) }; -- cgit v1.2.3 From f42f25526502d851d0e3ca1e46297da8aafce8a7 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Thu, 30 Jan 2020 22:14:48 -0800 Subject: mm, thp: fix defrag setting if newline is not used If thp defrag setting "defer" is used and a newline is *not* used when writing to the sysfs file, this is interpreted as the "defer+madvise" option. This is because we do prefix matching and if five characters are written without a newline, the current code ends up comparing to the first five bytes of the "defer+madvise" option and using that instead. Use the more appropriate sysfs_streq() that handles the trailing newline for us. Since this doubles as a nice cleanup, do it in enabled_store() as well. The current implementation relies on prefix matching: the number of bytes compared is either the number of bytes written or the length of the option being compared. With a newline, "defer\n" does not match "defer+"madvise"; without a newline, however, "defer" is considered to match "defer+madvise" (prefix matching is only comparing the first five bytes). End result is that writing "defer" is broken unless it has an additional trailing character. This means that writing "madv" in the past would match and set "madvise". With strict checking, that no longer is the case but it is unlikely anybody is currently doing this. Link: http://lkml.kernel.org/r/alpine.DEB.2.21.2001171411020.56385@chino.kir.corp.google.com Fixes: 21440d7eb904 ("mm, thp: add new defer+madvise defrag option") Signed-off-by: David Rientjes Suggested-by: Andrew Morton Acked-by: Vlastimil Babka Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 24 ++++++++---------------- 1 file changed, 8 insertions(+), 16 deletions(-) (limited to 'mm/huge_memory.c') diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 5b2876942639..ad521011734d 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -177,16 +177,13 @@ static ssize_t enabled_store(struct kobject *kobj, { ssize_t ret = count; - if (!memcmp("always", buf, - min(sizeof("always")-1, count))) { + if (sysfs_streq(buf, "always")) { clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); - } else if (!memcmp("madvise", buf, - min(sizeof("madvise")-1, count))) { + } else if (sysfs_streq(buf, "madvise")) { clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); - } else if (!memcmp("never", buf, - min(sizeof("never")-1, count))) { + } else if (sysfs_streq(buf, "never")) { clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); } else @@ -250,32 +247,27 @@ static ssize_t defrag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { - if (!memcmp("always", buf, - min(sizeof("always")-1, count))) { + if (sysfs_streq(buf, "always")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); - } else if (!memcmp("defer+madvise", buf, - min(sizeof("defer+madvise")-1, count))) { + } else if (sysfs_streq(buf, "defer+madvise")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); - } else if (!memcmp("defer", buf, - min(sizeof("defer")-1, count))) { + } else if (sysfs_streq(buf, "defer")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); - } else if (!memcmp("madvise", buf, - min(sizeof("madvise")-1, count))) { + } else if (sysfs_streq(buf, "madvise")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); - } else if (!memcmp("never", buf, - min(sizeof("never")-1, count))) { + } else if (sysfs_streq(buf, "never")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); -- cgit v1.2.3