[RFC,v3,1/3] mm: Add f_op->populate() for populating memory outside of core mm

Commit Message

Jarkko Sakkinen March 8, 2022, 11:28 a.m. UTC

SGX memory is managed outside the core mm.  It doesn't have a 'struct
page' and get_user_pages() doesn't work on it.  Its VMAs are marked with
VM_IO.  So, none of the existing methods for avoiding page faults work
on SGX memory.

Add f_op->populate() to overcome this issue:

int (*populate)(struct file *, unsigned long start, unsigned long end);

Then in populate_vma_page_range(), allow it to be used in the place of
get_user_pages() for memory that falls outside of its scope.

Signed-off-by: Jarkko Sakkinen <[e-mail]>
---
v5:
* In v4, one diff was left out of staging area in __mm_populate(). It
  was unintentional to remove the conditional statement.
v4:
* Reimplement based on Dave's suggestion:
  https://lore.kernel.org/linux-sgx/[e-mail]/
* Copy the text from the suggestion as part of the commit message (and
  cover letter).
v3:
-       if (!ret && do_populate && file->f_op->populate)
+       if (!ret && do_populate && file->f_op->populate &&
+           !!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
(reported by Matthew Wilcox)
v2:
-       if (!ret && do_populate)
+       if (!ret && do_populate && file->f_op->populate)
(reported by Jan Harkes)
---
 include/linux/fs.h |  1 +
 mm/gup.c           | 11 ++++++++---
 2 files changed, 9 insertions(+), 3 deletions(-)

Patch

diff --git a/include/linux/fs.h b/include/linux/fs.h
index e2d892b201b0..54151af88ee0 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1993,6 +1993,7 @@  struct file_operations {
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
 	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
 	int (*mmap) (struct file *, struct vm_area_struct *);
+	int (*populate)(struct file *, unsigned long start, unsigned long end);
 	unsigned long mmap_supported_flags;
 	int (*open) (struct inode *, struct file *);
 	int (*flush) (struct file *, fl_owner_t id);
diff --git a/mm/gup.c b/mm/gup.c
index a9d4d724aef7..1f3a1d0b6e0d 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1519,8 +1519,11 @@  long populate_vma_page_range(struct vm_area_struct *vma,
 	 * We made sure addr is within a VMA, so the following will
 	 * not result in a stack expansion that recurses back here.
 	 */
-	return __get_user_pages(mm, start, nr_pages, gup_flags,
-				NULL, NULL, locked);
+	if ((vma->vm_flags & (VM_IO | VM_PFNMAP)) && vma->vm_file->f_op->populate)
+		return vma->vm_file->f_op->populate(vma->vm_file, start, end);
+	else
+		return __get_user_pages(mm, start, nr_pages, gup_flags,
+					NULL, NULL, locked);
 }
 
 /*
@@ -1598,6 +1601,7 @@  int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
 	struct vm_area_struct *vma = NULL;
 	int locked = 0;
 	long ret = 0;
+	bool is_io;
 
 	end = start + len;
 
@@ -1619,7 +1623,8 @@  int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
 		 * range with the first VMA. Also, skip undesirable VMA types.
 		 */
 		nend = min(end, vma->vm_end);
-		if (vma->vm_flags & (VM_IO | VM_PFNMAP))
+		is_io = !!(vma->vm_flags & (VM_IO | VM_PFNMAP));
+		if (is_io && !(is_io && vma->vm_file->f_op->populate))
 			continue;
 		if (nstart < vma->vm_start)
 			nstart = vma->vm_start;