summaryrefslogtreecommitdiff
path: root/fs/dax.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/dax.c')
-rw-r--r--fs/dax.c120
1 files changed, 29 insertions, 91 deletions
diff --git a/fs/dax.c b/fs/dax.c
index 67a08a32fccb..4155a6107fa1 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -24,6 +24,7 @@
#include <linux/sizes.h>
#include <linux/mmu_notifier.h>
#include <linux/iomap.h>
+#include <linux/rmap.h>
#include <asm/pgalloc.h>
#define CREATE_TRACE_POINTS
@@ -721,7 +722,8 @@ static int copy_cow_page_dax(struct vm_fault *vmf, const struct iomap_iter *iter
int id;
id = dax_read_lock();
- rc = dax_direct_access(iter->iomap.dax_dev, pgoff, 1, &kaddr, NULL);
+ rc = dax_direct_access(iter->iomap.dax_dev, pgoff, 1, DAX_ACCESS,
+ &kaddr, NULL);
if (rc < 0) {
dax_read_unlock(id);
return rc;
@@ -789,95 +791,12 @@ static void *dax_insert_entry(struct xa_state *xas,
return entry;
}
-static inline
-unsigned long pgoff_address(pgoff_t pgoff, struct vm_area_struct *vma)
-{
- unsigned long address;
-
- address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
- VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
- return address;
-}
-
-/* Walk all mappings of a given index of a file and writeprotect them */
-static void dax_entry_mkclean(struct address_space *mapping, pgoff_t index,
- unsigned long pfn)
-{
- struct vm_area_struct *vma;
- pte_t pte, *ptep = NULL;
- pmd_t *pmdp = NULL;
- spinlock_t *ptl;
-
- i_mmap_lock_read(mapping);
- vma_interval_tree_foreach(vma, &mapping->i_mmap, index, index) {
- struct mmu_notifier_range range;
- unsigned long address;
-
- cond_resched();
-
- if (!(vma->vm_flags & VM_SHARED))
- continue;
-
- address = pgoff_address(index, vma);
-
- /*
- * follow_invalidate_pte() will use the range to call
- * mmu_notifier_invalidate_range_start() on our behalf before
- * taking any lock.
- */
- if (follow_invalidate_pte(vma->vm_mm, address, &range, &ptep,
- &pmdp, &ptl))
- continue;
-
- /*
- * No need to call mmu_notifier_invalidate_range() as we are
- * downgrading page table protection not changing it to point
- * to a new page.
- *
- * See Documentation/vm/mmu_notifier.rst
- */
- if (pmdp) {
-#ifdef CONFIG_FS_DAX_PMD
- pmd_t pmd;
-
- if (pfn != pmd_pfn(*pmdp))
- goto unlock_pmd;
- if (!pmd_dirty(*pmdp) && !pmd_write(*pmdp))
- goto unlock_pmd;
-
- flush_cache_page(vma, address, pfn);
- pmd = pmdp_invalidate(vma, address, pmdp);
- pmd = pmd_wrprotect(pmd);
- pmd = pmd_mkclean(pmd);
- set_pmd_at(vma->vm_mm, address, pmdp, pmd);
-unlock_pmd:
-#endif
- spin_unlock(ptl);
- } else {
- if (pfn != pte_pfn(*ptep))
- goto unlock_pte;
- if (!pte_dirty(*ptep) && !pte_write(*ptep))
- goto unlock_pte;
-
- flush_cache_page(vma, address, pfn);
- pte = ptep_clear_flush(vma, address, ptep);
- pte = pte_wrprotect(pte);
- pte = pte_mkclean(pte);
- set_pte_at(vma->vm_mm, address, ptep, pte);
-unlock_pte:
- pte_unmap_unlock(ptep, ptl);
- }
-
- mmu_notifier_invalidate_range_end(&range);
- }
- i_mmap_unlock_read(mapping);
-}
-
static int dax_writeback_one(struct xa_state *xas, struct dax_device *dax_dev,
struct address_space *mapping, void *entry)
{
- unsigned long pfn, index, count;
+ unsigned long pfn, index, count, end;
long ret = 0;
+ struct vm_area_struct *vma;
/*
* A page got tagged dirty in DAX mapping? Something is seriously
@@ -935,8 +854,16 @@ static int dax_writeback_one(struct xa_state *xas, struct dax_device *dax_dev,
pfn = dax_to_pfn(entry);
count = 1UL << dax_entry_order(entry);
index = xas->xa_index & ~(count - 1);
+ end = index + count - 1;
+
+ /* Walk all mappings of a given index of a file and writeprotect them */
+ i_mmap_lock_read(mapping);
+ vma_interval_tree_foreach(vma, &mapping->i_mmap, index, end) {
+ pfn_mkclean_range(pfn, count, index, vma);
+ cond_resched();
+ }
+ i_mmap_unlock_read(mapping);
- dax_entry_mkclean(mapping, index, pfn);
dax_flush(dax_dev, page_address(pfn_to_page(pfn)), count * PAGE_SIZE);
/*
* After we have flushed the cache, we can clear the dirty tag. There
@@ -1013,7 +940,7 @@ static int dax_iomap_pfn(const struct iomap *iomap, loff_t pos, size_t size,
id = dax_read_lock();
length = dax_direct_access(iomap->dax_dev, pgoff, PHYS_PFN(size),
- NULL, pfnp);
+ DAX_ACCESS, NULL, pfnp);
if (length < 0) {
rc = length;
goto out;
@@ -1122,7 +1049,7 @@ static int dax_memzero(struct dax_device *dax_dev, pgoff_t pgoff,
void *kaddr;
long ret;
- ret = dax_direct_access(dax_dev, pgoff, 1, &kaddr, NULL);
+ ret = dax_direct_access(dax_dev, pgoff, 1, DAX_ACCESS, &kaddr, NULL);
if (ret > 0) {
memset(kaddr + offset, 0, size);
dax_flush(dax_dev, kaddr + offset, size);
@@ -1239,6 +1166,7 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
const size_t size = ALIGN(length + offset, PAGE_SIZE);
pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
ssize_t map_len;
+ bool recovery = false;
void *kaddr;
if (fatal_signal_pending(current)) {
@@ -1247,7 +1175,14 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
}
map_len = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size),
- &kaddr, NULL);
+ DAX_ACCESS, &kaddr, NULL);
+ if (map_len == -EIO && iov_iter_rw(iter) == WRITE) {
+ map_len = dax_direct_access(dax_dev, pgoff,
+ PHYS_PFN(size), DAX_RECOVERY_WRITE,
+ &kaddr, NULL);
+ if (map_len > 0)
+ recovery = true;
+ }
if (map_len < 0) {
ret = map_len;
break;
@@ -1259,7 +1194,10 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
if (map_len > end - pos)
map_len = end - pos;
- if (iov_iter_rw(iter) == WRITE)
+ if (recovery)
+ xfer = dax_recovery_write(dax_dev, pgoff, kaddr,
+ map_len, iter);
+ else if (iov_iter_rw(iter) == WRITE)
xfer = dax_copy_from_iter(dax_dev, pgoff, kaddr,
map_len, iter);
else
generated by cgit v1.2.3-70-g09d2 (git 2.51.1) at 2025-11-04 02:58:36 +0000