Hi Peter, Thank you for the patch! Yet something to improve: [auto build test ERROR on kselftest/next] [also build test ERROR on linus/master v5.14-rc2 next-20210720] [cannot apply to hnaz-linux-mm/master asm-generic/master arm64/for-next/core linux/master tip/x86/core] [If your patch is applied to the wrong git tree, kindly drop us a note. And when submitting patch, we suggest to use '--base' as documented in https://git-scm.com/docs/git-format-patch] url: https://github.com/0day-ci/linux/commits/Peter-Xu/userfaultfd-wp-Support-shmem-and-hugetlbfs/20210716-041947 base: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git next config: s390-randconfig-r023-20210716 (attached as .config) compiler: clang version 13.0.0 (https://github.com/llvm/llvm-project 5d5b08761f944d5b9822d582378333cc4b36a0a7) reproduce (this is a W=1 build): wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross chmod +x ~/bin/make.cross # install s390 cross compiling tool for clang build # apt-get install binutils-s390x-linux-gnu # https://github.com/0day-ci/linux/commit/071935856c8e636cafde633db59259d75069cc8f git remote add linux-review https://github.com/0day-ci/linux git fetch --no-tags linux-review Peter-Xu/userfaultfd-wp-Support-shmem-and-hugetlbfs/20210716-041947 git checkout 071935856c8e636cafde633db59259d75069cc8f # save the attached .config to linux build tree COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross ARCH=s390 If you fix the issue, kindly add following tag as appropriate Reported-by: kernel test robot All errors (new ones prefixed by >>): In file included from mm/hugetlb.c:19: In file included from include/linux/memblock.h:14: In file included from arch/s390/include/asm/dma.h:5: In file included from arch/s390/include/asm/io.h:75: include/asm-generic/io.h:464:31: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] val = __raw_readb(PCI_IOBASE + addr); ~~~~~~~~~~ ^ include/asm-generic/io.h:477:61: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] val = __le16_to_cpu((__le16 __force)__raw_readw(PCI_IOBASE + addr)); ~~~~~~~~~~ ^ include/uapi/linux/byteorder/big_endian.h:36:59: note: expanded from macro '__le16_to_cpu' #define __le16_to_cpu(x) __swab16((__force __u16)(__le16)(x)) ^ include/uapi/linux/swab.h:102:54: note: expanded from macro '__swab16' #define __swab16(x) (__u16)__builtin_bswap16((__u16)(x)) ^ In file included from mm/hugetlb.c:19: In file included from include/linux/memblock.h:14: In file included from arch/s390/include/asm/dma.h:5: In file included from arch/s390/include/asm/io.h:75: include/asm-generic/io.h:490:61: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] val = __le32_to_cpu((__le32 __force)__raw_readl(PCI_IOBASE + addr)); ~~~~~~~~~~ ^ include/uapi/linux/byteorder/big_endian.h:34:59: note: expanded from macro '__le32_to_cpu' #define __le32_to_cpu(x) __swab32((__force __u32)(__le32)(x)) ^ include/uapi/linux/swab.h:115:54: note: expanded from macro '__swab32' #define __swab32(x) (__u32)__builtin_bswap32((__u32)(x)) ^ In file included from mm/hugetlb.c:19: In file included from include/linux/memblock.h:14: In file included from arch/s390/include/asm/dma.h:5: In file included from arch/s390/include/asm/io.h:75: include/asm-generic/io.h:501:33: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] __raw_writeb(value, PCI_IOBASE + addr); ~~~~~~~~~~ ^ include/asm-generic/io.h:511:59: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] __raw_writew((u16 __force)cpu_to_le16(value), PCI_IOBASE + addr); ~~~~~~~~~~ ^ include/asm-generic/io.h:521:59: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] __raw_writel((u32 __force)cpu_to_le32(value), PCI_IOBASE + addr); ~~~~~~~~~~ ^ include/asm-generic/io.h:609:20: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] readsb(PCI_IOBASE + addr, buffer, count); ~~~~~~~~~~ ^ include/asm-generic/io.h:617:20: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] readsw(PCI_IOBASE + addr, buffer, count); ~~~~~~~~~~ ^ include/asm-generic/io.h:625:20: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] readsl(PCI_IOBASE + addr, buffer, count); ~~~~~~~~~~ ^ include/asm-generic/io.h:634:21: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] writesb(PCI_IOBASE + addr, buffer, count); ~~~~~~~~~~ ^ include/asm-generic/io.h:643:21: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] writesw(PCI_IOBASE + addr, buffer, count); ~~~~~~~~~~ ^ include/asm-generic/io.h:652:21: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] writesl(PCI_IOBASE + addr, buffer, count); ~~~~~~~~~~ ^ >> mm/hugetlb.c:5063:29: error: implicit declaration of function 'huge_pte_uffd_wp' [-Werror,-Wimplicit-function-declaration] if (userfaultfd_wp(vma) && huge_pte_uffd_wp(huge_ptep_get(ptep)) && ^ 12 warnings and 1 error generated. vim +/huge_pte_uffd_wp +5063 mm/hugetlb.c 4957 4958 vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, 4959 unsigned long address, unsigned int flags) 4960 { 4961 pte_t *ptep, entry; 4962 spinlock_t *ptl; 4963 vm_fault_t ret; 4964 u32 hash; 4965 pgoff_t idx; 4966 struct page *page = NULL; 4967 struct page *pagecache_page = NULL; 4968 struct hstate *h = hstate_vma(vma); 4969 struct address_space *mapping; 4970 int need_wait_lock = 0; 4971 unsigned long haddr = address & huge_page_mask(h); 4972 4973 ptep = huge_pte_offset(mm, haddr, huge_page_size(h)); 4974 if (ptep) { 4975 /* 4976 * Since we hold no locks, ptep could be stale. That is 4977 * OK as we are only making decisions based on content and 4978 * not actually modifying content here. 4979 */ 4980 entry = huge_ptep_get(ptep); 4981 if (unlikely(is_hugetlb_entry_migration(entry))) { 4982 migration_entry_wait_huge(vma, mm, ptep); 4983 return 0; 4984 } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) 4985 return VM_FAULT_HWPOISON_LARGE | 4986 VM_FAULT_SET_HINDEX(hstate_index(h)); 4987 } 4988 4989 /* 4990 * Acquire i_mmap_rwsem before calling huge_pte_alloc and hold 4991 * until finished with ptep. This serves two purposes: 4992 * 1) It prevents huge_pmd_unshare from being called elsewhere 4993 * and making the ptep no longer valid. 4994 * 2) It synchronizes us with i_size modifications during truncation. 4995 * 4996 * ptep could have already be assigned via huge_pte_offset. That 4997 * is OK, as huge_pte_alloc will return the same value unless 4998 * something has changed. 4999 */ 5000 mapping = vma->vm_file->f_mapping; 5001 i_mmap_lock_read(mapping); 5002 ptep = huge_pte_alloc(mm, vma, haddr, huge_page_size(h)); 5003 if (!ptep) { 5004 i_mmap_unlock_read(mapping); 5005 return VM_FAULT_OOM; 5006 } 5007 5008 /* 5009 * Serialize hugepage allocation and instantiation, so that we don't 5010 * get spurious allocation failures if two CPUs race to instantiate 5011 * the same page in the page cache. 5012 */ 5013 idx = vma_hugecache_offset(h, vma, haddr); 5014 hash = hugetlb_fault_mutex_hash(mapping, idx); 5015 mutex_lock(&hugetlb_fault_mutex_table[hash]); 5016 5017 entry = huge_ptep_get(ptep); 5018 if (huge_pte_none(entry)) { 5019 ret = hugetlb_no_page(mm, vma, mapping, idx, address, ptep, flags); 5020 goto out_mutex; 5021 } 5022 5023 ret = 0; 5024 5025 /* 5026 * entry could be a migration/hwpoison entry at this point, so this 5027 * check prevents the kernel from going below assuming that we have 5028 * an active hugepage in pagecache. This goto expects the 2nd page 5029 * fault, and is_hugetlb_entry_(migration|hwpoisoned) check will 5030 * properly handle it. 5031 */ 5032 if (!pte_present(entry)) 5033 goto out_mutex; 5034 5035 /* 5036 * If we are going to COW the mapping later, we examine the pending 5037 * reservations for this page now. This will ensure that any 5038 * allocations necessary to record that reservation occur outside the 5039 * spinlock. For private mappings, we also lookup the pagecache 5040 * page now as it is used to determine if a reservation has been 5041 * consumed. 5042 */ 5043 if ((flags & FAULT_FLAG_WRITE) && !huge_pte_write(entry)) { 5044 if (vma_needs_reservation(h, vma, haddr) < 0) { 5045 ret = VM_FAULT_OOM; 5046 goto out_mutex; 5047 } 5048 /* Just decrements count, does not deallocate */ 5049 vma_end_reservation(h, vma, haddr); 5050 5051 if (!(vma->vm_flags & VM_MAYSHARE)) 5052 pagecache_page = hugetlbfs_pagecache_page(h, 5053 vma, haddr); 5054 } 5055 5056 ptl = huge_pte_lock(h, mm, ptep); 5057 5058 /* Check for a racing update before calling hugetlb_cow */ 5059 if (unlikely(!pte_same(entry, huge_ptep_get(ptep)))) 5060 goto out_ptl; 5061 5062 /* Handle userfault-wp first, before trying to lock more pages */ > 5063 if (userfaultfd_wp(vma) && huge_pte_uffd_wp(huge_ptep_get(ptep)) && 5064 (flags & FAULT_FLAG_WRITE) && !huge_pte_write(entry)) { 5065 struct vm_fault vmf = { 5066 .vma = vma, 5067 .address = haddr, 5068 .flags = flags, 5069 }; 5070 5071 spin_unlock(ptl); 5072 if (pagecache_page) { 5073 unlock_page(pagecache_page); 5074 put_page(pagecache_page); 5075 } 5076 mutex_unlock(&hugetlb_fault_mutex_table[hash]); 5077 i_mmap_unlock_read(mapping); 5078 return handle_userfault(&vmf, VM_UFFD_WP); 5079 } 5080 5081 /* 5082 * hugetlb_cow() requires page locks of pte_page(entry) and 5083 * pagecache_page, so here we need take the former one 5084 * when page != pagecache_page or !pagecache_page. 5085 */ 5086 page = pte_page(entry); 5087 if (page != pagecache_page) 5088 if (!trylock_page(page)) { 5089 need_wait_lock = 1; 5090 goto out_ptl; 5091 } 5092 5093 get_page(page); 5094 5095 if (flags & FAULT_FLAG_WRITE) { 5096 if (!huge_pte_write(entry)) { 5097 ret = hugetlb_cow(mm, vma, address, ptep, 5098 pagecache_page, ptl); 5099 goto out_put_page; 5100 } 5101 entry = huge_pte_mkdirty(entry); 5102 } 5103 entry = pte_mkyoung(entry); 5104 if (huge_ptep_set_access_flags(vma, haddr, ptep, entry, 5105 flags & FAULT_FLAG_WRITE)) 5106 update_mmu_cache(vma, haddr, ptep); 5107 out_put_page: 5108 if (page != pagecache_page) 5109 unlock_page(page); 5110 put_page(page); 5111 out_ptl: 5112 spin_unlock(ptl); 5113 5114 if (pagecache_page) { 5115 unlock_page(pagecache_page); 5116 put_page(pagecache_page); 5117 } 5118 out_mutex: 5119 mutex_unlock(&hugetlb_fault_mutex_table[hash]); 5120 i_mmap_unlock_read(mapping); 5121 /* 5122 * Generally it's safe to hold refcount during waiting page lock. But 5123 * here we just wait to defer the next page fault to avoid busy loop and 5124 * the page is not used after unlocked before returning from the current 5125 * page fault. So we are safe from accessing freed page, even if we wait 5126 * here without taking refcount. 5127 */ 5128 if (need_wait_lock) 5129 wait_on_page_locked(page); 5130 return ret; 5131 } 5132 --- 0-DAY CI Kernel Test Service, Intel Corporation https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org