The dax page fault code is too long and a bit difficult to read. And it
is hard to understand when we trying to add new features. Some of the
PTE/PMD codes have similar logic. So, factor them as helper functions to
simplify the code.
Signed-off-by: Shiyang Ruan
Reviewed-by: Christoph Hellwig
---
fs/dax.c | 152 ++-
1 file changed, 84 insertions(+), 68 deletions(-)
diff --git a/fs/dax.c b/fs/dax.c
index 26d5dcd2d69e..7031e4302b13 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1243,6 +1243,52 @@ static bool dax_fault_is_synchronous(unsigned long flags,
&& (iomap->flags & IOMAP_F_DIRTY);
}
+/*
+ * If we are doing synchronous page fault and inode needs fsync, we can insert
+ * PTE/PMD into page tables only after that happens. Skip insertion for now and
+ * return the pfn so that caller can insert it after fsync is done.
+ */
+static vm_fault_t dax_fault_synchronous_pfnp(pfn_t *pfnp, pfn_t pfn)
+{
+ if (WARN_ON_ONCE(!pfnp))
+ return VM_FAULT_SIGBUS;
+
+ *pfnp = pfn;
+ return VM_FAULT_NEEDDSYNC;
+}
+
+static int dax_fault_cow_page(struct vm_fault *vmf, struct iomap *iomap,
+ loff_t pos, vm_fault_t *ret)
+{
+ int error = 0;
+ unsigned long vaddr = vmf->address;
+ sector_t sector = dax_iomap_sector(iomap, pos);
+
+ switch (iomap->type) {
+ case IOMAP_HOLE:
+ case IOMAP_UNWRITTEN:
+ clear_user_highpage(vmf->cow_page, vaddr);
+ break;
+ case IOMAP_MAPPED:
+ error = copy_cow_page_dax(iomap->bdev, iomap->dax_dev,
+ sector, vmf->cow_page, vaddr);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ error = -EIO;
+ break;
+ }
+
+ if (error)
+ return error;
+
+ __SetPageUptodate(vmf->cow_page);
+ *ret = finish_fault(vmf);
+ if (!*ret)
+ *ret = VM_FAULT_DONE_COW;
+ return 0;
+}
+
static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
int *iomap_errp, const struct iomap_ops *ops)
{
@@ -1311,30 +1357,9 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault
*vmf, pfn_t *pfnp,
}
if (vmf->cow_page) {
- sector_t sector = dax_iomap_sector(&iomap, pos);
-
- switch (iomap.type) {
- case IOMAP_HOLE:
- case IOMAP_UNWRITTEN:
- clear_user_highpage(vmf->cow_page, vaddr);
- break;
- case IOMAP_MAPPED:
- error = copy_cow_page_dax(iomap.bdev, iomap.dax_dev,
- sector, vmf->cow_page, vaddr);
- break;
- default:
- WARN_ON_ONCE(1);
- error = -EIO;
- break;
- }
-
+ error = dax_fault_cow_page(vmf, &iomap, pos, &ret);
if (error)
- goto error_finish_iomap;
-
- __SetPageUptodate(vmf->cow_page);
- ret = finish_fault(vmf);
- if (!ret)
- ret = VM_FAULT_DONE_COW;
+ ret = dax_fault_return(error);
goto finish_iomap;
}
@@ -1354,19 +1379,8 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault
*vmf, pfn_t *pfnp,
entry = dax_insert_entry(&xas, mapping, vmf, entry, pfn,
0, write && !sync);
- /*
-* If we are doing synchronous page fault and inode needs fsync,
-* we can insert PTE into page tables only after that happens.
-* Skip insertion for now and return the pfn so that caller can
-* insert it after fsync is done.
-*/
if (sync) {
- if (WARN_ON_ONCE(!pfnp)) {
- error = -EIO;
- goto error_finish_iomap;
- }
- *pfnp = pfn;
- ret = VM_FAULT_NEEDDSYNC | major;
+ ret = dax_fault_synchronous_pfnp(pfnp, pfn);
goto finish_iomap;
}
trace_dax_insert_mapping(inode, vmf, entry);
@@ -1465,13 +1479,45 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state
*xas, struct vm_fault *vmf,
return VM_FAULT_FALLBACK;
}
+static bool dax_fault_check_fallback(struct vm_fault *vmf, struct xa_state
*xas,
+ pgoff_t max_pgoff)
+{
+ unsigned long pmd_addr = vmf->address & PMD_MASK;
+ bool write = vmf->flags & FAULT_FLAG_WRITE;
+
+ /*
+* Make sure that the faulting address's PMD offset (color) matches
+* the PMD offset from the start of the file. This