summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--drivers/dax/dax.c18
-rw-r--r--fs/dax.c9
-rw-r--r--fs/ext2/file.c2
-rw-r--r--fs/ext4/file.c12
-rw-r--r--fs/xfs/xfs_file.c9
-rw-r--r--include/linux/dax.h3
-rw-r--r--include/linux/mm.h14
-rw-r--r--mm/memory.c17
8 files changed, 46 insertions, 38 deletions
diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
index b90bb30..b75c772 100644
--- a/drivers/dax/dax.c
+++ b/drivers/dax/dax.c
@@ -538,7 +538,8 @@ static int __dax_dev_pud_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
}
#endif /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
-static int dax_dev_fault(struct vm_fault *vmf)
+static int dax_dev_huge_fault(struct vm_fault *vmf,
+ enum page_entry_size pe_size)
{
int rc;
struct file *filp = vmf->vma->vm_file;
@@ -550,14 +551,14 @@ static int dax_dev_fault(struct vm_fault *vmf)
vmf->vma->vm_start, vmf->vma->vm_end);
rcu_read_lock();
- switch (vmf->flags & FAULT_FLAG_SIZE_MASK) {
- case FAULT_FLAG_SIZE_PTE:
+ switch (pe_size) {
+ case PE_SIZE_PTE:
rc = __dax_dev_pte_fault(dax_dev, vmf);
break;
- case FAULT_FLAG_SIZE_PMD:
+ case PE_SIZE_PMD:
rc = __dax_dev_pmd_fault(dax_dev, vmf);
break;
- case FAULT_FLAG_SIZE_PUD:
+ case PE_SIZE_PUD:
rc = __dax_dev_pud_fault(dax_dev, vmf);
break;
default:
@@ -568,9 +569,14 @@ static int dax_dev_fault(struct vm_fault *vmf)
return rc;
}
+static int dax_dev_fault(struct vm_fault *vmf)
+{
+ return dax_dev_huge_fault(vmf, PE_SIZE_PTE);
+}
+
static const struct vm_operations_struct dax_dev_vm_ops = {
.fault = dax_dev_fault,
- .huge_fault = dax_dev_fault,
+ .huge_fault = dax_dev_huge_fault,
};
static int dax_mmap(struct file *filp, struct vm_area_struct *vma)
diff --git a/fs/dax.c b/fs/dax.c
index c3c29fb..5ae8b71 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1452,12 +1452,13 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf, struct iomap_ops *ops)
* has done all the necessary locking for page fault to proceed
* successfully.
*/
-int dax_iomap_fault(struct vm_fault *vmf, const struct iomap_ops *ops)
+int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
+ const struct iomap_ops *ops)
{
- switch (vmf->flags & FAULT_FLAG_SIZE_MASK) {
- case FAULT_FLAG_SIZE_PTE:
+ switch (pe_size) {
+ case PE_SIZE_PTE:
return dax_iomap_pte_fault(vmf, ops);
- case FAULT_FLAG_SIZE_PMD:
+ case PE_SIZE_PMD:
return dax_iomap_pmd_fault(vmf, ops);
default:
return VM_FAULT_FALLBACK;
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 6873883..b21891a 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -99,7 +99,7 @@ static int ext2_dax_fault(struct vm_fault *vmf)
}
down_read(&ei->dax_sem);
- ret = dax_iomap_fault(vmf, &ext2_iomap_ops);
+ ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &ext2_iomap_ops);
up_read(&ei->dax_sem);
if (vmf->flags & FAULT_FLAG_WRITE)
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 502d2d0..8210c1f 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -253,7 +253,8 @@ out:
}
#ifdef CONFIG_FS_DAX
-static int ext4_dax_fault(struct vm_fault *vmf)
+static int ext4_dax_huge_fault(struct vm_fault *vmf,
+ enum page_entry_size pe_size)
{
int result;
struct inode *inode = file_inode(vmf->vma->vm_file);
@@ -265,7 +266,7 @@ static int ext4_dax_fault(struct vm_fault *vmf)
file_update_time(vmf->vma->vm_file);
}
down_read(&EXT4_I(inode)->i_mmap_sem);
- result = dax_iomap_fault(vmf, &ext4_iomap_ops);
+ result = dax_iomap_fault(vmf, pe_size, &ext4_iomap_ops);
up_read(&EXT4_I(inode)->i_mmap_sem);
if (write)
sb_end_pagefault(sb);
@@ -273,6 +274,11 @@ static int ext4_dax_fault(struct vm_fault *vmf)
return result;
}
+static int ext4_dax_fault(struct vm_fault *vmf)
+{
+ return ext4_dax_huge_fault(vmf, PE_SIZE_PTE);
+}
+
/*
* Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_fault()
* handler we check for races agaist truncate. Note that since we cycle through
@@ -305,7 +311,7 @@ static int ext4_dax_pfn_mkwrite(struct vm_fault *vmf)
static const struct vm_operations_struct ext4_dax_vm_ops = {
.fault = ext4_dax_fault,
- .huge_fault = ext4_dax_fault,
+ .huge_fault = ext4_dax_huge_fault,
.page_mkwrite = ext4_dax_fault,
.pfn_mkwrite = ext4_dax_pfn_mkwrite,
};
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 990e038..a50eca6 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1391,7 +1391,7 @@ xfs_filemap_page_mkwrite(
xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
if (IS_DAX(inode)) {
- ret = dax_iomap_fault(vmf, &xfs_iomap_ops);
+ ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &xfs_iomap_ops);
} else {
ret = iomap_page_mkwrite(vmf, &xfs_iomap_ops);
ret = block_page_mkwrite_return(ret);
@@ -1418,7 +1418,7 @@ xfs_filemap_fault(
xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
if (IS_DAX(inode))
- ret = dax_iomap_fault(vmf, &xfs_iomap_ops);
+ ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &xfs_iomap_ops);
else
ret = filemap_fault(vmf);
xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
@@ -1435,7 +1435,8 @@ xfs_filemap_fault(
*/
STATIC int
xfs_filemap_huge_fault(
- struct vm_fault *vmf)
+ struct vm_fault *vmf,
+ enum page_entry_size pe_size)
{
struct inode *inode = file_inode(vmf->vma->vm_file);
struct xfs_inode *ip = XFS_I(inode);
@@ -1452,7 +1453,7 @@ xfs_filemap_huge_fault(
}
xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
- ret = dax_iomap_fault(vmf, &xfs_iomap_ops);
+ ret = dax_iomap_fault(vmf, pe_size, &xfs_iomap_ops);
xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
if (vmf->flags & FAULT_FLAG_WRITE)
diff --git a/include/linux/dax.h b/include/linux/dax.h
index cf9af22..d8a3dc0 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -38,7 +38,8 @@ static inline void *dax_radix_locked_entry(sector_t sector, unsigned long flags)
ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
const struct iomap_ops *ops);
-int dax_iomap_fault(struct vm_fault *vmf, const struct iomap_ops *ops);
+int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
+ const struct iomap_ops *ops);
int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
int dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index);
int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index d8b75d7..c65aa43 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -285,11 +285,6 @@ extern pgprot_t protection_map[16];
#define FAULT_FLAG_REMOTE 0x80 /* faulting for non current tsk/mm */
#define FAULT_FLAG_INSTRUCTION 0x100 /* The fault was during an instruction fetch */
-#define FAULT_FLAG_SIZE_MASK 0x7000 /* Support up to 8-level page tables */
-#define FAULT_FLAG_SIZE_PTE 0x0000 /* First level (eg 4k) */
-#define FAULT_FLAG_SIZE_PMD 0x1000 /* Second level (eg 2MB) */
-#define FAULT_FLAG_SIZE_PUD 0x2000 /* Third level (eg 1GB) */
-
#define FAULT_FLAG_TRACE \
{ FAULT_FLAG_WRITE, "WRITE" }, \
{ FAULT_FLAG_MKWRITE, "MKWRITE" }, \
@@ -349,6 +344,13 @@ struct vm_fault {
*/
};
+/* page entry size for vm->huge_fault() */
+enum page_entry_size {
+ PE_SIZE_PTE = 0,
+ PE_SIZE_PMD,
+ PE_SIZE_PUD,
+};
+
/*
* These are the virtual MM functions - opening of an area, closing and
* unmapping it (needed to keep files on disk up-to-date etc), pointer
@@ -359,7 +361,7 @@ struct vm_operations_struct {
void (*close)(struct vm_area_struct * area);
int (*mremap)(struct vm_area_struct * area);
int (*fault)(struct vm_fault *vmf);
- int (*huge_fault)(struct vm_fault *vmf);
+ int (*huge_fault)(struct vm_fault *vmf, enum page_entry_size pe_size);
void (*map_pages)(struct vm_fault *vmf,
pgoff_t start_pgoff, pgoff_t end_pgoff);
diff --git a/mm/memory.c b/mm/memory.c
index 41e2a2d..6040b74 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3489,7 +3489,7 @@ static int create_huge_pmd(struct vm_fault *vmf)
if (vma_is_anonymous(vmf->vma))
return do_huge_pmd_anonymous_page(vmf);
if (vmf->vma->vm_ops->huge_fault)
- return vmf->vma->vm_ops->huge_fault(vmf);
+ return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD);
return VM_FAULT_FALLBACK;
}
@@ -3498,7 +3498,7 @@ static int wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd)
if (vma_is_anonymous(vmf->vma))
return do_huge_pmd_wp_page(vmf, orig_pmd);
if (vmf->vma->vm_ops->huge_fault)
- return vmf->vma->vm_ops->huge_fault(vmf);
+ return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD);
/* COW handled on pte level: split pmd */
VM_BUG_ON_VMA(vmf->vma->vm_flags & VM_SHARED, vmf->vma);
@@ -3519,7 +3519,7 @@ static int create_huge_pud(struct vm_fault *vmf)
if (vma_is_anonymous(vmf->vma))
return VM_FAULT_FALLBACK;
if (vmf->vma->vm_ops->huge_fault)
- return vmf->vma->vm_ops->huge_fault(vmf);
+ return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD);
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
return VM_FAULT_FALLBACK;
}
@@ -3531,7 +3531,7 @@ static int wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud)
if (vma_is_anonymous(vmf->vma))
return VM_FAULT_FALLBACK;
if (vmf->vma->vm_ops->huge_fault)
- return vmf->vma->vm_ops->huge_fault(vmf);
+ return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD);
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
return VM_FAULT_FALLBACK;
}
@@ -3659,7 +3659,6 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
if (!vmf.pud)
return VM_FAULT_OOM;
if (pud_none(*vmf.pud) && transparent_hugepage_enabled(vma)) {
- vmf.flags |= FAULT_FLAG_SIZE_PUD;
ret = create_huge_pud(&vmf);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
@@ -3670,8 +3669,6 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
if (pud_trans_huge(orig_pud) || pud_devmap(orig_pud)) {
unsigned int dirty = flags & FAULT_FLAG_WRITE;
- vmf.flags |= FAULT_FLAG_SIZE_PUD;
-
/* NUMA case for anonymous PUDs would go here */
if (dirty && !pud_write(orig_pud)) {
@@ -3689,18 +3686,14 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
if (!vmf.pmd)
return VM_FAULT_OOM;
if (pmd_none(*vmf.pmd) && transparent_hugepage_enabled(vma)) {
- vmf.flags |= FAULT_FLAG_SIZE_PMD;
ret = create_huge_pmd(&vmf);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
- /* fall through path, remove PMD flag */
- vmf.flags &= ~FAULT_FLAG_SIZE_PMD;
} else {
pmd_t orig_pmd = *vmf.pmd;
barrier();
if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) {
- vmf.flags |= FAULT_FLAG_SIZE_PMD;
if (pmd_protnone(orig_pmd) && vma_is_accessible(vma))
return do_huge_pmd_numa_page(&vmf, orig_pmd);
@@ -3709,8 +3702,6 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
ret = wp_huge_pmd(&vmf, orig_pmd);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
- /* fall through path, remove PUD flag */
- vmf.flags &= ~FAULT_FLAG_SIZE_PUD;
} else {
huge_pmd_set_accessed(&vmf, orig_pmd);
return 0;
OpenPOWER on IntegriCloud