From: Linus Torvalds Date: Wed, 14 Dec 2022 03:29:45 +0000 (-0800) Subject: Merge tag 'mm-stable-2022-12-13' of git://git.kernel.org/pub/scm/linux/kernel/git... X-Git-Url: http://git.maquefel.me/?a=commitdiff_plain;h=e2ca6ba6ba0152361aa4fcbf6067db71b2c7a770;p=linux.git Merge tag 'mm-stable-2022-12-13' of git://git./linux/kernel/git/akpm/mm Pull MM updates from Andrew Morton: - More userfaultfs work from Peter Xu - Several convert-to-folios series from Sidhartha Kumar and Huang Ying - Some filemap cleanups from Vishal Moola - David Hildenbrand added the ability to selftest anon memory COW handling - Some cpuset simplifications from Liu Shixin - Addition of vmalloc tracing support by Uladzislau Rezki - Some pagecache folioifications and simplifications from Matthew Wilcox - A pagemap cleanup from Kefeng Wang: we have VM_ACCESS_FLAGS, so use it - Miguel Ojeda contributed some cleanups for our use of the __no_sanitize_thread__ gcc keyword. This series should have been in the non-MM tree, my bad - Naoya Horiguchi improved the interaction between memory poisoning and memory section removal for huge pages - DAMON cleanups and tuneups from SeongJae Park - Tony Luck fixed the handling of COW faults against poisoned pages - Peter Xu utilized the PTE marker code for handling swapin errors - Hugh Dickins reworked compound page mapcount handling, simplifying it and making it more efficient - Removal of the autonuma savedwrite infrastructure from Nadav Amit and David Hildenbrand - zram support for multiple compression streams from Sergey Senozhatsky - David Hildenbrand reworked the GUP code's R/O long-term pinning so that drivers no longer need to use the FOLL_FORCE workaround which didn't work very well anyway - Mel Gorman altered the page allocator so that local IRQs can remnain enabled during per-cpu page allocations - Vishal Moola removed the try_to_release_page() wrapper - Stefan Roesch added some per-BDI sysfs tunables which are used to prevent network block devices from dirtying excessive amounts of pagecache - David Hildenbrand did some cleanup and repair work on KSM COW breaking - Nhat Pham and Johannes Weiner have implemented writeback in zswap's zsmalloc backend - Brian Foster has fixed a longstanding corner-case oddity in file[map]_write_and_wait_range() - sparse-vmemmap changes for MIPS, LoongArch and NIOS2 from Feiyang Chen - Shiyang Ruan has done some work on fsdax, to make its reflink mode work better under xfstests. Better, but still not perfect - Christoph Hellwig has removed the .writepage() method from several filesystems. They only need .writepages() - Yosry Ahmed wrote a series which fixes the memcg reclaim target beancounting - David Hildenbrand has fixed some of our MM selftests for 32-bit machines - Many singleton patches, as usual * tag 'mm-stable-2022-12-13' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (313 commits) mm/hugetlb: set head flag before setting compound_order in __prep_compound_gigantic_folio mm: mmu_gather: allow more than one batch of delayed rmaps mm: fix typo in struct pglist_data code comment kmsan: fix memcpy tests mm: add cond_resched() in swapin_walk_pmd_entry() mm: do not show fs mm pc for VM_LOCKONFAULT pages selftests/vm: ksm_functional_tests: fixes for 32bit selftests/vm: cow: fix compile warning on 32bit selftests/vm: madv_populate: fix missing MADV_POPULATE_(READ|WRITE) definitions mm/gup_test: fix PIN_LONGTERM_TEST_READ with highmem mm,thp,rmap: fix races between updates of subpages_mapcount mm: memcg: fix swapcached stat accounting mm: add nodes= arg to memory.reclaim mm: disable top-tier fallback to reclaim on proactive reclaim selftests: cgroup: make sure reclaim target memcg is unprotected selftests: cgroup: refactor proactive reclaim code to reclaim_until() mm: memcg: fix stale protection of reclaim target memcg mm/mmap: properly unaccount memory on mas_preallocate() failure omfs: remove ->writepage jfs: remove ->writepage ... --- e2ca6ba6ba0152361aa4fcbf6067db71b2c7a770 diff --cc arch/arm64/mm/mmu.c index 2368e4daa23d3,27217ba12e576..12915f379c22b --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@@ -1187,50 -1153,12 +1153,12 @@@ int __meminit vmemmap_check_pmd(pmd_t * int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap) { - unsigned long addr = start; - unsigned long next; - pgd_t *pgdp; - p4d_t *p4dp; - pud_t *pudp; - pmd_t *pmdp; - WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END)); - if (!ARM64_KERNEL_USES_PMD_MAPS) + if (!IS_ENABLED(CONFIG_ARM64_4K_PAGES)) return vmemmap_populate_basepages(start, end, node, altmap); - - do { - next = pmd_addr_end(addr, end); - - pgdp = vmemmap_pgd_populate(addr, node); - if (!pgdp) - return -ENOMEM; - - p4dp = vmemmap_p4d_populate(pgdp, addr, node); - if (!p4dp) - return -ENOMEM; - - pudp = vmemmap_pud_populate(p4dp, addr, node); - if (!pudp) - return -ENOMEM; - - pmdp = pmd_offset(pudp, addr); - if (pmd_none(READ_ONCE(*pmdp))) { - void *p = NULL; - - p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap); - if (!p) { - if (vmemmap_populate_basepages(addr, next, node, altmap)) - return -ENOMEM; - continue; - } - - pmd_set_huge(pmdp, __pa(p), __pgprot(PROT_SECT_NORMAL)); - } else - vmemmap_verify((pte_t *)pmdp, node, addr, next); - } while (addr = next, addr != end); - - return 0; + else + return vmemmap_populate_hugepages(start, end, node, altmap); } #ifdef CONFIG_MEMORY_HOTPLUG diff --cc drivers/media/common/videobuf2/frame_vector.c index 89eebc3341b84,062e98148c535..0f430ddc1f670 --- a/drivers/media/common/videobuf2/frame_vector.c +++ b/drivers/media/common/videobuf2/frame_vector.c @@@ -33,11 -32,14 +33,11 @@@ * * This function takes care of grabbing mmap_lock as necessary. */ -int get_vaddr_frames(unsigned long start, unsigned int nr_frames, +int get_vaddr_frames(unsigned long start, unsigned int nr_frames, bool write, struct frame_vector *vec) { - struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; - int ret_pin_user_pages_fast = 0; - int ret = 0; - int err; + int ret; - unsigned int gup_flags = FOLL_FORCE | FOLL_LONGTERM; ++ unsigned int gup_flags = FOLL_LONGTERM; if (nr_frames == 0) return 0; diff --cc mm/hugetlb.c index 3d9f4abec17c6,7cdbcc22587bf..f5f445c39dbcb --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@@ -6220,6 -6215,62 +6215,62 @@@ static inline bool __follow_hugetlb_mus return false; } + struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma, + unsigned long address, unsigned int flags) + { + struct hstate *h = hstate_vma(vma); + struct mm_struct *mm = vma->vm_mm; + unsigned long haddr = address & huge_page_mask(h); + struct page *page = NULL; + spinlock_t *ptl; + pte_t *pte, entry; + + /* + * FOLL_PIN is not supported for follow_page(). Ordinary GUP goes via + * follow_hugetlb_page(). + */ + if (WARN_ON_ONCE(flags & FOLL_PIN)) + return NULL; + + retry: + pte = huge_pte_offset(mm, haddr, huge_page_size(h)); + if (!pte) + return NULL; + + ptl = huge_pte_lock(h, mm, pte); + entry = huge_ptep_get(pte); + if (pte_present(entry)) { + page = pte_page(entry) + + ((address & ~huge_page_mask(h)) >> PAGE_SHIFT); + /* + * Note that page may be a sub-page, and with vmemmap + * optimizations the page struct may be read only. + * try_grab_page() will increase the ref count on the + * head page, so this will be OK. + * - * try_grab_page() should always succeed here, because we hold - * the ptl lock and have verified pte_present(). ++ * try_grab_page() should always be able to get the page here, ++ * because we hold the ptl lock and have verified pte_present(). + */ - if (WARN_ON_ONCE(!try_grab_page(page, flags))) { ++ if (try_grab_page(page, flags)) { + page = NULL; + goto out; + } + } else { + if (is_hugetlb_entry_migration(entry)) { + spin_unlock(ptl); + __migration_entry_wait_huge(pte, ptl); + goto retry; + } + /* + * hwpoisoned entry is treated as no_page_table in + * follow_page_mask(). + */ + } + out: + spin_unlock(ptl); + return page; + } + long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, struct page **pages, struct vm_area_struct **vmas, unsigned long *position, unsigned long *nr_pages,