[PATCH v3 14/18] fuse,dax: add DAX mmap support

From: Vivek Goyal
Date: Wed Aug 19 2020 - 18:22:05 EST


From: Stefan Hajnoczi <stefanha@xxxxxxxxxx>

Add DAX mmap() support.

Signed-off-by: Stefan Hajnoczi <stefanha@xxxxxxxxxx>
---
fs/fuse/file.c | 62 +++++++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 61 insertions(+), 1 deletion(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 99457d0b14b9..f1ad8b95b546 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2841,10 +2841,15 @@ static const struct vm_operations_struct fuse_file_vm_ops = {
.page_mkwrite = fuse_page_mkwrite,
};

+static int fuse_dax_mmap(struct file *file, struct vm_area_struct *vma);
static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma)
{
struct fuse_file *ff = file->private_data;

+ /* DAX mmap is superior to direct_io mmap */
+ if (IS_DAX(file_inode(file)))
+ return fuse_dax_mmap(file, vma);
+
if (ff->open_flags & FOPEN_DIRECT_IO) {
/* Can't provide the coherency needed for MAP_SHARED */
if (vma->vm_flags & VM_MAYSHARE)
@@ -2863,9 +2868,63 @@ static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma)
return 0;
}

+static vm_fault_t __fuse_dax_fault(struct vm_fault *vmf,
+ enum page_entry_size pe_size, bool write)
+{
+ vm_fault_t ret;
+ struct inode *inode = file_inode(vmf->vma->vm_file);
+ struct super_block *sb = inode->i_sb;
+ pfn_t pfn;
+
+ if (write)
+ sb_start_pagefault(sb);
+
+ ret = dax_iomap_fault(vmf, pe_size, &pfn, NULL, &fuse_iomap_ops);
+
+ if (ret & VM_FAULT_NEEDDSYNC)
+ ret = dax_finish_sync_fault(vmf, pe_size, pfn);
+
+ if (write)
+ sb_end_pagefault(sb);
+
+ return ret;
+}
+
+static vm_fault_t fuse_dax_fault(struct vm_fault *vmf)
+{
+ return __fuse_dax_fault(vmf, PE_SIZE_PTE,
+ vmf->flags & FAULT_FLAG_WRITE);
+}
+
+static vm_fault_t fuse_dax_huge_fault(struct vm_fault *vmf,
+ enum page_entry_size pe_size)
+{
+ return __fuse_dax_fault(vmf, pe_size, vmf->flags & FAULT_FLAG_WRITE);
+}
+
+static vm_fault_t fuse_dax_page_mkwrite(struct vm_fault *vmf)
+{
+ return __fuse_dax_fault(vmf, PE_SIZE_PTE, true);
+}
+
+static vm_fault_t fuse_dax_pfn_mkwrite(struct vm_fault *vmf)
+{
+ return __fuse_dax_fault(vmf, PE_SIZE_PTE, true);
+}
+
+static const struct vm_operations_struct fuse_dax_vm_ops = {
+ .fault = fuse_dax_fault,
+ .huge_fault = fuse_dax_huge_fault,
+ .page_mkwrite = fuse_dax_page_mkwrite,
+ .pfn_mkwrite = fuse_dax_pfn_mkwrite,
+};
+
static int fuse_dax_mmap(struct file *file, struct vm_area_struct *vma)
{
- return -EINVAL; /* TODO */
+ file_accessed(file);
+ vma->vm_ops = &fuse_dax_vm_ops;
+ vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
+ return 0;
}

static int convert_fuse_file_lock(struct fuse_conn *fc,
@@ -3938,6 +3997,7 @@ static const struct file_operations fuse_file_operations = {
.release = fuse_release,
.fsync = fuse_fsync,
.lock = fuse_file_lock,
+ .get_unmapped_area = thp_get_unmapped_area,
.flock = fuse_file_flock,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
--
2.25.4