From: Mike Rapoport rppt@linux.ibm.com

The check in gup_pte_range() whether a page belongs to a secretmem mapping is performed before grabbing the page reference.

To avoid potential race move the check after try_grab_compound_head().

Signed-off-by: Mike Rapoport rppt@linux.ibm.com --- mm/gup.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c index c3a17b189064..6515f82b0f32 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -2080,13 +2080,15 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte);

- if (page_is_secretmem(page)) - goto pte_unmap; - head = try_grab_compound_head(page, 1, flags); if (!head) goto pte_unmap;

+ if (unlikely(page_is_secretmem(page))) { + put_compound_head(head, 1, flags); + goto pte_unmap; + } + if (unlikely(pte_val(pte) != pte_val(*ptep))) { put_compound_head(head, 1, flags); goto pte_unmap;

From: Mike Rapoport rppt@linux.ibm.com

Kernel test robot reported -4.2% regression of will-it-scale.per_thread_ops due to commit "mm: introduce memfd_secret system call to create "secret" memory areas".

The perf profile of the test indicated that the regression is caused by page_is_secretmem() called from gup_pte_range() (inlined by gup_pgd_range):

27.76 +2.5 30.23 perf-profile.children.cycles-pp.gup_pgd_range 0.00 +3.2 3.19 ± 2% perf-profile.children.cycles-pp.page_mapping 0.00 +3.7 3.66 ± 2% perf-profile.children.cycles-pp.page_is_secretmem

Further analysis showed that the slow down happens because neither page_is_secretmem() nor page_mapping() are not inline and moreover, multiple page flags checks in page_mapping() involve calling compound_head() several times for the same page.

Make page_is_secretmem() inline and replace page_mapping() with page flag checks that do not imply page-to-head conversion.

Reported-by: kernel test robot oliver.sang@intel.com Signed-off-by: Mike Rapoport rppt@linux.ibm.com --- include/linux/secretmem.h | 26 +++++++++++++++++++++++++- mm/secretmem.c | 12 +----------- 2 files changed, 26 insertions(+), 12 deletions(-)

diff --git a/include/linux/secretmem.h b/include/linux/secretmem.h index 907a6734059c..b842b38cbeb1 100644 --- a/include/linux/secretmem.h +++ b/include/linux/secretmem.h @@ -4,8 +4,32 @@

#ifdef CONFIG_SECRETMEM

+extern const struct address_space_operations secretmem_aops; + +static inline bool page_is_secretmem(struct page *page) +{ + struct address_space *mapping; + + /* + * Using page_mapping() is quite slow because of the actual call + * instruction and repeated compound_head(page) inside the + * page_mapping() function. + * We know that secretmem pages are not compound and LRU so we can + * save a couple of cycles here. + */ + if (PageCompound(page) || !PageLRU(page)) + return false; + + mapping = (struct address_space *) + ((unsigned long)page->mapping & ~PAGE_MAPPING_FLAGS); + + if (mapping != page->mapping) + return false; + + return page->mapping->a_ops == &secretmem_aops; +} + bool vma_is_secretmem(struct vm_area_struct *vma); -bool page_is_secretmem(struct page *page); bool secretmem_active(void);

#else diff --git a/mm/secretmem.c b/mm/secretmem.c index 3b1ba3991964..0bcd15e1b549 100644 --- a/mm/secretmem.c +++ b/mm/secretmem.c @@ -151,22 +151,12 @@ static void secretmem_freepage(struct page *page) clear_highpage(page); }

-static const struct address_space_operations secretmem_aops = { +const struct address_space_operations secretmem_aops = { .freepage = secretmem_freepage, .migratepage = secretmem_migratepage, .isolate_page = secretmem_isolate_page, };

-bool page_is_secretmem(struct page *page) -{ - struct address_space *mapping = page_mapping(page); - - if (!mapping) - return false; - - return mapping->a_ops == &secretmem_aops; -} - static struct vfsmount *secretmem_mnt;

static struct file *secretmem_file_create(unsigned long flags)