mm: introduce get_user_pages_longterm

Patch series "introduce get_user_pages_longterm()", v2.

Here is a new get_user_pages api for cases where a driver intends to
keep an elevated page count indefinitely.  This is distinct from usages
like iov_iter_get_pages where the elevated page counts are transient.
The iov_iter_get_pages cases immediately turn around and submit the
pages to a device driver which will put_page when the i/o operation
completes (under kernel control).

In the longterm case userspace is responsible for dropping the page
reference at some undefined point in the future.  This is untenable for
filesystem-dax case where the filesystem is in control of the lifetime
of the block / page and needs reasonable limits on how long it can wait
for pages in a mapping to become idle.

Fixing filesystems to actually wait for dax pages to be idle before
blocks from a truncate/hole-punch operation are repurposed is saved for
a later patch series.

Also, allowing longterm registration of dax mappings is a future patch
series that introduces a "map with lease" semantic where the kernel can
revoke a lease and force userspace to drop its page references.

I have also tagged these for -stable to purposely break cases that might
assume that longterm memory registrations for filesystem-dax mappings
were supported by the kernel.  The behavior regression this policy
change implies is one of the reasons we maintain the "dax enabled.
Warning: EXPERIMENTAL, use at your own risk" notification when mounting
a filesystem in dax mode.

It is worth noting the device-dax interface does not suffer the same
constraints since it does not support file space management operations
like hole-punch.

This patch (of 4):

Until there is a solution to the dma-to-dax vs truncate problem it is
not safe to allow long standing memory registrations against
filesytem-dax vmas.  Device-dax vmas do not have this problem and are
explicitly allowed.

This is temporary until a "memory registration with layout-lease"
mechanism can be implemented for the affected sub-systems (RDMA and
V4L2).

[akpm@linux-foundation.org: use kcalloc()]
Link: http://lkml.kernel.org/r/151068939435.7446.13560129395419350737.stgit@dwillia2-desk3.amr.corp.intel.com
Fixes: 3565fce3a659 ("mm, x86: get_user_pages() for dax mappings")
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Suggested-by: Christoph Hellwig <hch@lst.de>
Cc: Doug Ledford <dledford@redhat.com>
Cc: Hal Rosenstock <hal.rosenstock@gmail.com>
Cc: Inki Dae <inki.dae@samsung.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Joonyoung Shim <jy0922.shim@samsung.com>
Cc: Kyungmin Park <kyungmin.park@samsung.com>
Cc: Mauro Carvalho Chehab <mchehab@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Sean Hefty <sean.hefty@intel.com>
Cc: Seung-Woo Kim <sw0312.kim@samsung.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
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/include/linux/fs.h b/include/linux/fs.h
index bbd92da0946e1c20ede60bc27780844dfbde8c26..9dc498d16cc147e9fbee218163598863cd785074 100644 (file)
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3194,6 +3194,20 @@ static inline bool vma_is_dax(struct vm_area_struct *vma)
        return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host);
 }
 
+static inline bool vma_is_fsdax(struct vm_area_struct *vma)
+{
+       struct inode *inode;
+
+       if (!vma->vm_file)
+               return false;
+       if (!vma_is_dax(vma))
+               return false;
+       inode = file_inode(vma->vm_file);
+       if (inode->i_mode == S_IFCHR)
+               return false; /* device-dax */
+       return true;
+}
+
 static inline int iocb_flags(struct file *file)
 {
        int res = 0;

diff --git a/include/linux/mm.h b/include/linux/mm.h
index b3b6a7e313e947d9db18855e21b6d624419e7f8d..ea818ff739cdfbb433fc10634ed5ac77eacbc5b7 100644 (file)
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1380,6 +1380,19 @@ long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
                    unsigned int gup_flags, struct page **pages, int *locked);
 long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
                    struct page **pages, unsigned int gup_flags);
+#ifdef CONFIG_FS_DAX
+long get_user_pages_longterm(unsigned long start, unsigned long nr_pages,
+                           unsigned int gup_flags, struct page **pages,
+                           struct vm_area_struct **vmas);
+#else
+static inline long get_user_pages_longterm(unsigned long start,
+               unsigned long nr_pages, unsigned int gup_flags,
+               struct page **pages, struct vm_area_struct **vmas)
+{
+       return get_user_pages(start, nr_pages, gup_flags, pages, vmas);
+}
+#endif /* CONFIG_FS_DAX */
+
 int get_user_pages_fast(unsigned long start, int nr_pages, int write,
                        struct page **pages);
 

diff --git a/mm/gup.c b/mm/gup.c
index 85cc822fd403c50a46e773f118c1554c68158913..d3fb60e5bfacd4c733957dc526c28c41bd2321d1 100644 (file)
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1095,6 +1095,70 @@ long get_user_pages(unsigned long start, unsigned long nr_pages,
 }
 EXPORT_SYMBOL(get_user_pages);
 
+#ifdef CONFIG_FS_DAX
+/*
+ * This is the same as get_user_pages() in that it assumes we are
+ * operating on the current task's mm, but it goes further to validate
+ * that the vmas associated with the address range are suitable for
+ * longterm elevated page reference counts. For example, filesystem-dax
+ * mappings are subject to the lifetime enforced by the filesystem and
+ * we need guarantees that longterm users like RDMA and V4L2 only
+ * establish mappings that have a kernel enforced revocation mechanism.
+ *
+ * "longterm" == userspace controlled elevated page count lifetime.
+ * Contrast this to iov_iter_get_pages() usages which are transient.
+ */
+long get_user_pages_longterm(unsigned long start, unsigned long nr_pages,
+               unsigned int gup_flags, struct page **pages,
+               struct vm_area_struct **vmas_arg)
+{
+       struct vm_area_struct **vmas = vmas_arg;
+       struct vm_area_struct *vma_prev = NULL;
+       long rc, i;
+
+       if (!pages)
+               return -EINVAL;
+
+       if (!vmas) {
+               vmas = kcalloc(nr_pages, sizeof(struct vm_area_struct *),
+                              GFP_KERNEL);
+               if (!vmas)
+                       return -ENOMEM;
+       }
+
+       rc = get_user_pages(start, nr_pages, gup_flags, pages, vmas);
+
+       for (i = 0; i < rc; i++) {
+               struct vm_area_struct *vma = vmas[i];
+
+               if (vma == vma_prev)
+                       continue;
+
+               vma_prev = vma;
+
+               if (vma_is_fsdax(vma))
+                       break;
+       }
+
+       /*
+        * Either get_user_pages() failed, or the vma validation
+        * succeeded, in either case we don't need to put_page() before
+        * returning.
+        */
+       if (i >= rc)
+               goto out;
+
+       for (i = 0; i < rc; i++)
+               put_page(pages[i]);
+       rc = -EOPNOTSUPP;
+out:
+       if (vmas != vmas_arg)
+               kfree(vmas);
+       return rc;
+}
+EXPORT_SYMBOL(get_user_pages_longterm);
+#endif /* CONFIG_FS_DAX */
+
 /**
  * populate_vma_page_range() -  populate a range of pages in the vma.
  * @vma:   target vma