ipc/shm.c add ->pagesize function to shm_vm_ops

Commit 05ea88608d4e ("mm, hugetlbfs: introduce ->pagesize() to
vm_operations_struct") adds a new ->pagesize() function to
hugetlb_vm_ops, intended to cover all hugetlbfs backed files.

With System V shared memory model, if "huge page" is specified, the
"shared memory" is backed by hugetlbfs files, but the mappings initiated
via shmget/shmat have their original vm_ops overwritten with shm_vm_ops,
so we need to add a ->pagesize function to shm_vm_ops.  Otherwise,
vma_kernel_pagesize() returns PAGE_SIZE given a hugetlbfs backed vma,
result in below BUG:

  fs/hugetlbfs/inode.c
        443             if (unlikely(page_mapped(page))) {
        444                     BUG_ON(truncate_op);

resulting in

  hugetlbfs: oracle (4592): Using mlock ulimits for SHM_HUGETLB is deprecated
  ------------[ cut here ]------------
  kernel BUG at fs/hugetlbfs/inode.c:444!
  Modules linked in: nfsv3 rpcsec_gss_krb5 nfsv4 ...
  CPU: 35 PID: 5583 Comm: oracle_5583_sbt Not tainted 4.14.35-1829.el7uek.x86_64 #2
  RIP: 0010:remove_inode_hugepages+0x3db/0x3e2
  ....
  Call Trace:
    hugetlbfs_evict_inode+0x1e/0x3e
    evict+0xdb/0x1af
    iput+0x1a2/0x1f7
    dentry_unlink_inode+0xc6/0xf0
    __dentry_kill+0xd8/0x18d
    dput+0x1b5/0x1ed
    __fput+0x18b/0x216
    ____fput+0xe/0x10
    task_work_run+0x90/0xa7
    exit_to_usermode_loop+0xdd/0x116
    do_syscall_64+0x187/0x1ae
    entry_SYSCALL_64_after_hwframe+0x150/0x0

[jane.chu@oracle.com: relocate comment]
  Link: http://lkml.kernel.org/r/20180731044831.26036-1-jane.chu@oracle.com
Link: http://lkml.kernel.org/r/20180727211727.5020-1-jane.chu@oracle.com
Fixes: 05ea88608d4e13 ("mm, hugetlbfs: introduce ->pagesize() to vm_operations_struct")
Signed-off-by: Jane Chu <jane.chu@oracle.com>
Suggested-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Acked-by: Davidlohr Bueso <dave@stgolabs.net>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Manfred Spraul <manfred@colorfullife.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 19 insertions, 0 deletions

diff --git a/ipc/shm.c b/ipc/shm.c
index 051a3e1fb8df..fefa00d310fb 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -427,6 +427,17 @@ static int shm_split(struct vm_area_struct *vma, unsigned long addr)
 	return 0;
 }
 
+static unsigned long shm_pagesize(struct vm_area_struct *vma)
+{
+	struct file *file = vma->vm_file;
+	struct shm_file_data *sfd = shm_file_data(file);
+
+	if (sfd->vm_ops->pagesize)
+		return sfd->vm_ops->pagesize(vma);
+
+	return PAGE_SIZE;
+}
+
 #ifdef CONFIG_NUMA
 static int shm_set_policy(struct vm_area_struct *vma, struct mempolicy *new)
 {
@@ -554,6 +565,7 @@ static const struct vm_operations_struct shm_vm_ops = {
 	.close	= shm_close,	/* callback for when the vm-area is released */
 	.fault	= shm_fault,
 	.split	= shm_split,
+	.pagesize = shm_pagesize,
 #if defined(CONFIG_NUMA)
 	.set_policy = shm_set_policy,
 	.get_policy = shm_get_policy,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 039ddbc574e9..3103099f64fd 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3167,6 +3167,13 @@ static vm_fault_t hugetlb_vm_op_fault(struct vm_fault *vmf)
 	return 0;
 }
 
+/*
+ * When a new function is introduced to vm_operations_struct and added
+ * to hugetlb_vm_ops, please consider adding the function to shm_vm_ops.
+ * This is because under System V memory model, mappings created via
+ * shmget/shmat with "huge page" specified are backed by hugetlbfs files,
+ * their original vm_ops are overwritten with shm_vm_ops.
+ */
 const struct vm_operations_struct hugetlb_vm_ops = {
 	.fault = hugetlb_vm_op_fault,
 	.open = hugetlb_vm_op_open,