hugetlb: use same fault hash key for shared and private mappings

hugetlb uses a fault mutex hash table to prevent page faults of the
same pages concurrently.  The key for shared and private mappings is
different.  Shared keys off address_space and file index.  Private keys
off mm and virtual address.  Consider a private mappings of a populated
hugetlbfs file.  A fault will map the page from the file and if needed
do a COW to map a writable page.

Hugetlbfs hole punch uses the fault mutex to prevent mappings of file
pages.  It uses the address_space file index key.  However, private
mappings will use a different key and could race with this code to map
the file page.  This causes problems (BUG) for the page cache remove
code as it expects the page to be unmapped.  A sample stack is:

page dumped because: VM_BUG_ON_PAGE(page_mapped(page))
kernel BUG at mm/filemap.c:169!
...
RIP: 0010:unaccount_page_cache_page+0x1b8/0x200
...
Call Trace:
__delete_from_page_cache+0x39/0x220
delete_from_page_cache+0x45/0x70
remove_inode_hugepages+0x13c/0x380
? __add_to_page_cache_locked+0x162/0x380
hugetlbfs_fallocate+0x403/0x540
? _cond_resched+0x15/0x30
? __inode_security_revalidate+0x5d/0x70
? selinux_file_permission+0x100/0x130
vfs_fallocate+0x13f/0x270
ksys_fallocate+0x3c/0x80
__x64_sys_fallocate+0x1a/0x20
do_syscall_64+0x5b/0x180
entry_SYSCALL_64_after_hwframe+0x44/0xa9

There seems to be another potential COW issue/race with this approach
of different private and shared keys as noted in commit 8382d914ebf7
("mm, hugetlb: improve page-fault scalability").

Since every hugetlb mapping (even anon and private) is actually a file
mapping, just use the address_space index key for all mappings.  This
results in potentially more hash collisions.  However, this should not
be the common case.

Link: http://lkml.kernel.org/r/20190328234704.27083-3-mike.kravetz@oracle.com
Link: http://lkml.kernel.org/r/20190412165235.t4sscoujczfhuiyt@linux-r8p5
Fixes: b5cec28d36f5 ("hugetlbfs: truncate_hugepages() takes a range of pages")
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Reviewed-by: Davidlohr Bueso <dbueso@suse.de>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index c74ef4426282ecf5d64bc0f63f3c5ed617a49e08..f23237135163a23b3799ae037fc70b438e676bf0 100644 (file)
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -440,9 +440,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
                        u32 hash;
 
                        index = page->index;
-                       hash = hugetlb_fault_mutex_hash(h, current->mm,
-                                                       &pseudo_vma,
-                                                       mapping, index, 0);
+                       hash = hugetlb_fault_mutex_hash(h, mapping, index, 0);
                        mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
                        /*
@@ -639,8 +637,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
                addr = index * hpage_size;
 
                /* mutex taken here, fault path and hole punch */
-               hash = hugetlb_fault_mutex_hash(h, mm, &pseudo_vma, mapping,
-                                               index, addr);
+               hash = hugetlb_fault_mutex_hash(h, mapping, index, addr);
                mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
                /* See if already present in mapping to avoid alloc/free */

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 11943b60f2084cb5e69c6dd5553f2adf0ea4f8ca..edf476c8cfb9c0ddc11da72d091bc0077091745e 100644 (file)
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -123,9 +123,7 @@ void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason);
 void free_huge_page(struct page *page);
 void hugetlb_fix_reserve_counts(struct inode *inode);
 extern struct mutex *hugetlb_fault_mutex_table;
-u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm,
-                               struct vm_area_struct *vma,
-                               struct address_space *mapping,
+u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping,
                                pgoff_t idx, unsigned long address);
 
 pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud);

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index c33c5cbb67ff3d28731d1a5b66ea983bce6722ef..98a3c7c224cbef41f7c730c2d4beae0dfb648140 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3824,8 +3824,7 @@ retry:
                         * handling userfault.  Reacquire after handling
                         * fault to make calling code simpler.
                         */
-                       hash = hugetlb_fault_mutex_hash(h, mm, vma, mapping,
-                                                       idx, haddr);
+                       hash = hugetlb_fault_mutex_hash(h, mapping, idx, haddr);
                        mutex_unlock(&hugetlb_fault_mutex_table[hash]);
                        ret = handle_userfault(&vmf, VM_UFFD_MISSING);
                        mutex_lock(&hugetlb_fault_mutex_table[hash]);
@@ -3933,21 +3932,14 @@ backout_unlocked:
 }
 
 #ifdef CONFIG_SMP
-u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm,
-                           struct vm_area_struct *vma,
-                           struct address_space *mapping,
+u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping,
                            pgoff_t idx, unsigned long address)
 {
        unsigned long key[2];
        u32 hash;
 
-       if (vma->vm_flags & VM_SHARED) {
-               key[0] = (unsigned long) mapping;
-               key[1] = idx;
-       } else {
-               key[0] = (unsigned long) mm;
-               key[1] = address >> huge_page_shift(h);
-       }
+       key[0] = (unsigned long) mapping;
+       key[1] = idx;
 
        hash = jhash2((u32 *)&key, sizeof(key)/sizeof(u32), 0);
 
@@ -3958,9 +3950,7 @@ u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm,
  * For uniprocesor systems we always use a single mutex, so just
  * return 0 and avoid the hashing overhead.
  */
-u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm,
-                           struct vm_area_struct *vma,
-                           struct address_space *mapping,
+u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping,
                            pgoff_t idx, unsigned long address)
 {
        return 0;
@@ -4005,7 +3995,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
         * get spurious allocation failures if two CPUs race to instantiate
         * the same page in the page cache.
         */
-       hash = hugetlb_fault_mutex_hash(h, mm, vma, mapping, idx, haddr);
+       hash = hugetlb_fault_mutex_hash(h, mapping, idx, haddr);
        mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
        entry = huge_ptep_get(ptep);

diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index d59b5a73dfb38b1301092578c6704eb10eb5ecb2..9932d5755e4cba2a7e9b42df7918b5c5c123d6ec 100644 (file)
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -271,8 +271,7 @@ retry:
                 */
                idx = linear_page_index(dst_vma, dst_addr);
                mapping = dst_vma->vm_file->f_mapping;
-               hash = hugetlb_fault_mutex_hash(h, dst_mm, dst_vma, mapping,
-                                                               idx, dst_addr);
+               hash = hugetlb_fault_mutex_hash(h, mapping, idx, dst_addr);
                mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
                err = -ENOMEM;