[PATCH 05/10] guestmemfs: add file mmap callback

[James Gowans <jgowans@amazon.com>]

Make the file data usable to userspace by adding mmap. That's all that
QEMU needs for guest RAM, so that's all be bother implementing for now.

When mmaping the file the VMA is marked as PFNMAP to indicate that there
are no struct pages for the memory in this VMA. Remap_pfn_range() is
used to actually populate the page tables. All PTEs are pre-faulted into
the pgtables at mmap time so that the pgtables are usable when this
virtual address range is given to VFIO's MAP_DMA.

Signed-off-by: James Gowans <jgowans@amazon.com>
---
 fs/guestmemfs/file.c       | 43 +++++++++++++++++++++++++++++++++++++-
 fs/guestmemfs/guestmemfs.c |  2 +-
 fs/guestmemfs/guestmemfs.h |  3 +++
 3 files changed, 46 insertions(+), 2 deletions(-)

diff --git a/fs/guestmemfs/file.c b/fs/guestmemfs/file.c
index 618c93b12196..b1a52abcde65 100644
--- a/fs/guestmemfs/file.c
+++ b/fs/guestmemfs/file.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 
 #include "guestmemfs.h"
+#include <linux/mm.h>
 
 static int truncate(struct inode *inode, loff_t newsize)
 {
@@ -41,6 +42,46 @@ static int inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct
 	return 0;
 }
 
+/*
+ * To be able to use PFNMAP VMAs for VFIO DMA mapping we need the page tables
+ * populated with mappings. Pre-fault everything.
+ */
+static int mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	int rc;
+	unsigned long *mappings_block;
+	struct guestmemfs_inode *guestmemfs_inode;
+
+	guestmemfs_inode = guestmemfs_get_persisted_inode(filp->f_inode->i_sb,
+			filp->f_inode->i_ino);
+
+	mappings_block = guestmemfs_inode->mappings;
+
+	/* Remap-pfn-range will mark the range VM_IO */
+	for (unsigned long vma_addr_offset = vma->vm_start;
+			vma_addr_offset < vma->vm_end;
+			vma_addr_offset += PMD_SIZE) {
+		int block, mapped_block;
+		unsigned long map_size = min(PMD_SIZE, vma->vm_end - vma_addr_offset);
+
+		block = (vma_addr_offset - vma->vm_start) / PMD_SIZE;
+		mapped_block = *(mappings_block + block);
+		/*
+		 * It's wrong to use rempa_pfn_range; this will install PTE-level entries.
+		 * The whole point of 2 MiB allocs is to improve TLB perf!
+		 * We should use something like mm/huge_memory.c#insert_pfn_pmd
+		 * but that is currently static.
+		 * TODO: figure out the best way to install PMDs.
+		 */
+		rc = remap_pfn_range(vma,
+				vma_addr_offset,
+				(guestmemfs_base >> PAGE_SHIFT) + (mapped_block * 512),
+				map_size,
+				vma->vm_page_prot);
+	}
+	return 0;
+}
+
 const struct inode_operations guestmemfs_file_inode_operations = {
 	.setattr = inode_setattr,
 	.getattr = simple_getattr,
@@ -48,5 +89,5 @@ const struct inode_operations guestmemfs_file_inode_operations = {
 
 const struct file_operations guestmemfs_file_fops = {
 	.owner = THIS_MODULE,
-	.iterate_shared = NULL,
+	.mmap = mmap,
 };
diff --git a/fs/guestmemfs/guestmemfs.c b/fs/guestmemfs/guestmemfs.c
index c45c796c497a..38f20ad25286 100644
--- a/fs/guestmemfs/guestmemfs.c
+++ b/fs/guestmemfs/guestmemfs.c
@@ -9,7 +9,7 @@
 #include <linux/memblock.h>
 #include <linux/statfs.h>
 
-static phys_addr_t guestmemfs_base, guestmemfs_size;
+phys_addr_t guestmemfs_base, guestmemfs_size;
 struct guestmemfs_sb *psb;
 
 static int statfs(struct dentry *root, struct kstatfs *buf)
diff --git a/fs/guestmemfs/guestmemfs.h b/fs/guestmemfs/guestmemfs.h
index 7ea03ac8ecca..0f2788ce740e 100644
--- a/fs/guestmemfs/guestmemfs.h
+++ b/fs/guestmemfs/guestmemfs.h
@@ -8,6 +8,9 @@
 #define GUESTMEMFS_FILENAME_LEN 255
 #define GUESTMEMFS_PSB(sb) ((struct guestmemfs_sb *)sb->s_fs_info)
 
+/* Units of bytes */
+extern phys_addr_t guestmemfs_base, guestmemfs_size;
+
 struct guestmemfs_sb {
 	/* Inode number */
 	unsigned long next_free_ino;
-- 
2.34.1