summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2017-02-25 10:29:09 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2017-02-25 10:29:09 -0800
commit7b46588f364f4f40c25f43ceabb6f705d20793e2 (patch)
tree29e80019ee791abe58176161f3ae2b766749b808 /fs
parent915f3e3f76c05b2da93c4cc278eebc2d9219d9f4 (diff)
parent95330473636e5e4546f94874c957c3be66bb2140 (diff)
downloadlinux-7b46588f364f4f40c25f43ceabb6f705d20793e2.tar.bz2
Merge branch 'akpm' (patches from Andrew)
Merge more updates from Andrew Morton: - almost all of the rest of MM - misc bits - KASAN updates - procfs - lib/ updates - checkpatch updates * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (124 commits) checkpatch: remove false unbalanced braces warning checkpatch: notice unbalanced else braces in a patch checkpatch: add another old address for the FSF checkpatch: update $logFunctions checkpatch: warn on logging continuations checkpatch: warn on embedded function names lib/lz4: remove back-compat wrappers fs/pstore: fs/squashfs: change usage of LZ4 to work with new LZ4 version crypto: change LZ4 modules to work with new LZ4 module version lib/decompress_unlz4: change module to work with new LZ4 module version lib: update LZ4 compressor module lib/test_sort.c: make it explicitly non-modular lib: add CONFIG_TEST_SORT to enable self-test of sort() rbtree: use designated initializers linux/kernel.h: fix DIV_ROUND_CLOSEST to support negative divisors lib/find_bit.c: micro-optimise find_next_*_bit lib: add module support to atomic64 tests lib: add module support to glob tests lib: add module support to crc32 tests kernel/ksysfs.c: add __ro_after_init to bin_attribute structure ...
Diffstat (limited to 'fs')
-rw-r--r--fs/9p/vfs_file.c4
-rw-r--r--fs/aio.c2
-rw-r--r--fs/btrfs/ctree.h2
-rw-r--r--fs/btrfs/inode.c6
-rw-r--r--fs/ceph/addr.c8
-rw-r--r--fs/cifs/file.c2
-rw-r--r--fs/dax.c59
-rw-r--r--fs/ext2/file.c19
-rw-r--r--fs/ext4/ext4.h4
-rw-r--r--fs/ext4/file.c40
-rw-r--r--fs/ext4/inode.c9
-rw-r--r--fs/f2fs/file.c7
-rw-r--r--fs/fuse/file.c6
-rw-r--r--fs/gfs2/file.c8
-rw-r--r--fs/iomap.c5
-rw-r--r--fs/kernfs/file.c13
-rw-r--r--fs/ncpfs/mmap.c7
-rw-r--r--fs/nfs/file.c4
-rw-r--r--fs/nilfs2/file.c3
-rw-r--r--fs/ocfs2/mmap.c15
-rw-r--r--fs/proc/base.c152
-rw-r--r--fs/proc/generic.c11
-rw-r--r--fs/proc/inode.c2
-rw-r--r--fs/proc/root.c3
-rw-r--r--fs/proc/vmcore.c8
-rw-r--r--fs/pstore/platform.c22
-rw-r--r--fs/squashfs/lz4_wrapper.c12
-rw-r--r--fs/ubifs/file.c5
-rw-r--r--fs/userfaultfd.c109
-rw-r--r--fs/xfs/xfs_file.c38
-rw-r--r--fs/xfs/xfs_trace.h2
31 files changed, 327 insertions, 260 deletions
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 6a0f3fa85ef7..3de3b4a89d89 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -534,11 +534,11 @@ v9fs_mmap_file_mmap(struct file *filp, struct vm_area_struct *vma)
}
static int
-v9fs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+v9fs_vm_page_mkwrite(struct vm_fault *vmf)
{
struct v9fs_inode *v9inode;
struct page *page = vmf->page;
- struct file *filp = vma->vm_file;
+ struct file *filp = vmf->vma->vm_file;
struct inode *inode = file_inode(filp);
diff --git a/fs/aio.c b/fs/aio.c
index 873b4ca82ccb..7e2ab9c8e39c 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -512,7 +512,7 @@ static int aio_setup_ring(struct kioctx *ctx)
ctx->mmap_base = do_mmap_pgoff(ctx->aio_ring_file, 0, ctx->mmap_size,
PROT_READ | PROT_WRITE,
- MAP_SHARED, 0, &unused);
+ MAP_SHARED, 0, &unused, NULL);
up_write(&mm->mmap_sem);
if (IS_ERR((void *)ctx->mmap_base)) {
ctx->mmap_size = 0;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 6a823719b6c5..adf16307842a 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3147,7 +3147,7 @@ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
int btrfs_merge_bio_hook(struct page *page, unsigned long offset,
size_t size, struct bio *bio,
unsigned long bio_flags);
-int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
+int btrfs_page_mkwrite(struct vm_fault *vmf);
int btrfs_readpage(struct file *file, struct page *page);
void btrfs_evict_inode(struct inode *inode);
int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 1e861a063721..ea1d500cfba6 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -8964,10 +8964,10 @@ again:
* beyond EOF, then the page is guaranteed safe against truncation until we
* unlock the page.
*/
-int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+int btrfs_page_mkwrite(struct vm_fault *vmf)
{
struct page *page = vmf->page;
- struct inode *inode = file_inode(vma->vm_file);
+ struct inode *inode = file_inode(vmf->vma->vm_file);
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
struct btrfs_ordered_extent *ordered;
@@ -9000,7 +9000,7 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
ret = btrfs_delalloc_reserve_space(inode, page_start,
reserved_space);
if (!ret) {
- ret = file_update_time(vma->vm_file);
+ ret = file_update_time(vmf->vma->vm_file);
reserved = 1;
}
if (ret) {
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index e4b066cd912a..09860c0ec7c1 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1386,8 +1386,9 @@ static void ceph_restore_sigs(sigset_t *oldset)
/*
* vm ops
*/
-static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int ceph_filemap_fault(struct vm_fault *vmf)
{
+ struct vm_area_struct *vma = vmf->vma;
struct inode *inode = file_inode(vma->vm_file);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_file_info *fi = vma->vm_file->private_data;
@@ -1416,7 +1417,7 @@ static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
if ((got & (CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO)) ||
ci->i_inline_version == CEPH_INLINE_NONE) {
current->journal_info = vma->vm_file;
- ret = filemap_fault(vma, vmf);
+ ret = filemap_fault(vmf);
current->journal_info = NULL;
} else
ret = -EAGAIN;
@@ -1477,8 +1478,9 @@ out_restore:
/*
* Reuse write_begin here for simplicity.
*/
-static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int ceph_page_mkwrite(struct vm_fault *vmf)
{
+ struct vm_area_struct *vma = vmf->vma;
struct inode *inode = file_inode(vma->vm_file);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_file_info *fi = vma->vm_file->private_data;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 98dc842e7245..aa3debbba826 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -3282,7 +3282,7 @@ cifs_read(struct file *file, char *read_data, size_t read_size, loff_t *offset)
* sure that it doesn't change while being written back.
*/
static int
-cifs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+cifs_page_mkwrite(struct vm_fault *vmf)
{
struct page *page = vmf->page;
diff --git a/fs/dax.c b/fs/dax.c
index 3f1181563fb1..5ae8b71ebadc 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -925,12 +925,11 @@ static int dax_insert_mapping(struct address_space *mapping,
/**
* dax_pfn_mkwrite - handle first write to DAX page
- * @vma: The virtual memory area where the fault occurred
* @vmf: The description of the fault
*/
-int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+int dax_pfn_mkwrite(struct vm_fault *vmf)
{
- struct file *file = vma->vm_file;
+ struct file *file = vmf->vma->vm_file;
struct address_space *mapping = file->f_mapping;
void *entry, **slot;
pgoff_t index = vmf->pgoff;
@@ -1119,20 +1118,10 @@ static int dax_fault_return(int error)
return VM_FAULT_SIGBUS;
}
-/**
- * dax_iomap_fault - handle a page fault on a DAX file
- * @vma: The virtual memory area where the fault occurred
- * @vmf: The description of the fault
- * @ops: iomap ops passed from the file system
- *
- * When a page fault occurs, filesystems may call this helper in their fault
- * or mkwrite handler for DAX files. Assumes the caller has done all the
- * necessary locking for the page fault to proceed successfully.
- */
-int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
- const struct iomap_ops *ops)
+static int dax_iomap_pte_fault(struct vm_fault *vmf,
+ const struct iomap_ops *ops)
{
- struct address_space *mapping = vma->vm_file->f_mapping;
+ struct address_space *mapping = vmf->vma->vm_file->f_mapping;
struct inode *inode = mapping->host;
unsigned long vaddr = vmf->address;
loff_t pos = (loff_t)vmf->pgoff << PAGE_SHIFT;
@@ -1205,11 +1194,11 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
case IOMAP_MAPPED:
if (iomap.flags & IOMAP_F_NEW) {
count_vm_event(PGMAJFAULT);
- mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+ mem_cgroup_count_vm_event(vmf->vma->vm_mm, PGMAJFAULT);
major = VM_FAULT_MAJOR;
}
error = dax_insert_mapping(mapping, iomap.bdev, sector,
- PAGE_SIZE, &entry, vma, vmf);
+ PAGE_SIZE, &entry, vmf->vma, vmf);
/* -EBUSY is fine, somebody else faulted on the same PTE */
if (error == -EBUSY)
error = 0;
@@ -1247,7 +1236,6 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
}
return vmf_ret;
}
-EXPORT_SYMBOL_GPL(dax_iomap_fault);
#ifdef CONFIG_FS_DAX_PMD
/*
@@ -1338,7 +1326,8 @@ fallback:
return VM_FAULT_FALLBACK;
}
-int dax_iomap_pmd_fault(struct vm_fault *vmf, const struct iomap_ops *ops)
+static int dax_iomap_pmd_fault(struct vm_fault *vmf,
+ const struct iomap_ops *ops)
{
struct vm_area_struct *vma = vmf->vma;
struct address_space *mapping = vma->vm_file->f_mapping;
@@ -1446,5 +1435,33 @@ out:
trace_dax_pmd_fault_done(inode, vmf, max_pgoff, result);
return result;
}
-EXPORT_SYMBOL_GPL(dax_iomap_pmd_fault);
+#else
+static int dax_iomap_pmd_fault(struct vm_fault *vmf, struct iomap_ops *ops)
+{
+ return VM_FAULT_FALLBACK;
+}
#endif /* CONFIG_FS_DAX_PMD */
+
+/**
+ * dax_iomap_fault - handle a page fault on a DAX file
+ * @vmf: The description of the fault
+ * @ops: iomap ops passed from the file system
+ *
+ * When a page fault occurs, filesystems may call this helper in
+ * their fault handler for DAX files. dax_iomap_fault() assumes the caller
+ * has done all the necessary locking for page fault to proceed
+ * successfully.
+ */
+int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
+ const struct iomap_ops *ops)
+{
+ switch (pe_size) {
+ case PE_SIZE_PTE:
+ return dax_iomap_pte_fault(vmf, ops);
+ case PE_SIZE_PMD:
+ return dax_iomap_pmd_fault(vmf, ops);
+ default:
+ return VM_FAULT_FALLBACK;
+ }
+}
+EXPORT_SYMBOL_GPL(dax_iomap_fault);
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index b0f241528a30..b21891a6bfca 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -87,19 +87,19 @@ out_unlock:
* The default page_lock and i_size verification done by non-DAX fault paths
* is sufficient because ext2 doesn't support hole punching.
*/
-static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int ext2_dax_fault(struct vm_fault *vmf)
{
- struct inode *inode = file_inode(vma->vm_file);
+ struct inode *inode = file_inode(vmf->vma->vm_file);
struct ext2_inode_info *ei = EXT2_I(inode);
int ret;
if (vmf->flags & FAULT_FLAG_WRITE) {
sb_start_pagefault(inode->i_sb);
- file_update_time(vma->vm_file);
+ file_update_time(vmf->vma->vm_file);
}
down_read(&ei->dax_sem);
- ret = dax_iomap_fault(vma, 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)
@@ -107,16 +107,15 @@ static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
return ret;
}
-static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
- struct vm_fault *vmf)
+static int ext2_dax_pfn_mkwrite(struct vm_fault *vmf)
{
- struct inode *inode = file_inode(vma->vm_file);
+ struct inode *inode = file_inode(vmf->vma->vm_file);
struct ext2_inode_info *ei = EXT2_I(inode);
loff_t size;
int ret;
sb_start_pagefault(inode->i_sb);
- file_update_time(vma->vm_file);
+ file_update_time(vmf->vma->vm_file);
down_read(&ei->dax_sem);
/* check that the faulting page hasn't raced with truncate */
@@ -124,7 +123,7 @@ static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
if (vmf->pgoff >= size)
ret = VM_FAULT_SIGBUS;
else
- ret = dax_pfn_mkwrite(vma, vmf);
+ ret = dax_pfn_mkwrite(vmf);
up_read(&ei->dax_sem);
sb_end_pagefault(inode->i_sb);
@@ -134,7 +133,7 @@ static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
static const struct vm_operations_struct ext2_dax_vm_ops = {
.fault = ext2_dax_fault,
/*
- * .pmd_fault is not supported for DAX because allocation in ext2
+ * .huge_fault is not supported for DAX because allocation in ext2
* cannot be reliably aligned to huge page sizes and so pmd faults
* will always fail and fail back to regular faults.
*/
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index cee23b684f47..2fd17e8e4984 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2483,8 +2483,8 @@ extern int ext4_writepage_trans_blocks(struct inode *);
extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
loff_t lstart, loff_t lend);
-extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
-extern int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf);
+extern int ext4_page_mkwrite(struct vm_fault *vmf);
+extern int ext4_filemap_fault(struct vm_fault *vmf);
extern qsize_t *ext4_get_reserved_space(struct inode *inode);
extern int ext4_get_projid(struct inode *inode, kprojid_t *projid);
extern void ext4_da_update_reserve_space(struct inode *inode,
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 13021a054fc0..8210c1f43556 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -253,19 +253,20 @@ out:
}
#ifdef CONFIG_FS_DAX
-static int ext4_dax_fault(struct vm_area_struct *vma, 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(vma->vm_file);
+ struct inode *inode = file_inode(vmf->vma->vm_file);
struct super_block *sb = inode->i_sb;
bool write = vmf->flags & FAULT_FLAG_WRITE;
if (write) {
sb_start_pagefault(sb);
- file_update_time(vma->vm_file);
+ file_update_time(vmf->vma->vm_file);
}
down_read(&EXT4_I(inode)->i_mmap_sem);
- result = dax_iomap_fault(vma, 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);
@@ -273,25 +274,9 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
return result;
}
-static int
-ext4_dax_pmd_fault(struct vm_fault *vmf)
+static int ext4_dax_fault(struct vm_fault *vmf)
{
- int result;
- struct inode *inode = file_inode(vmf->vma->vm_file);
- struct super_block *sb = inode->i_sb;
- bool write = vmf->flags & FAULT_FLAG_WRITE;
-
- if (write) {
- sb_start_pagefault(sb);
- file_update_time(vmf->vma->vm_file);
- }
- down_read(&EXT4_I(inode)->i_mmap_sem);
- result = dax_iomap_pmd_fault(vmf, &ext4_iomap_ops);
- up_read(&EXT4_I(inode)->i_mmap_sem);
- if (write)
- sb_end_pagefault(sb);
-
- return result;
+ return ext4_dax_huge_fault(vmf, PE_SIZE_PTE);
}
/*
@@ -303,22 +288,21 @@ ext4_dax_pmd_fault(struct vm_fault *vmf)
* wp_pfn_shared() fails. Thus fault gets retried and things work out as
* desired.
*/
-static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma,
- struct vm_fault *vmf)
+static int ext4_dax_pfn_mkwrite(struct vm_fault *vmf)
{
- struct inode *inode = file_inode(vma->vm_file);
+ struct inode *inode = file_inode(vmf->vma->vm_file);
struct super_block *sb = inode->i_sb;
loff_t size;
int ret;
sb_start_pagefault(sb);
- file_update_time(vma->vm_file);
+ file_update_time(vmf->vma->vm_file);
down_read(&EXT4_I(inode)->i_mmap_sem);
size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (vmf->pgoff >= size)
ret = VM_FAULT_SIGBUS;
else
- ret = dax_pfn_mkwrite(vma, vmf);
+ ret = dax_pfn_mkwrite(vmf);
up_read(&EXT4_I(inode)->i_mmap_sem);
sb_end_pagefault(sb);
@@ -327,7 +311,7 @@ static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma,
static const struct vm_operations_struct ext4_dax_vm_ops = {
.fault = ext4_dax_fault,
- .pmd_fault = ext4_dax_pmd_fault,
+ .huge_fault = ext4_dax_huge_fault,
.page_mkwrite = ext4_dax_fault,
.pfn_mkwrite = ext4_dax_pfn_mkwrite,
};
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 75212a6e69f8..41d8e53e5a7f 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5821,8 +5821,9 @@ static int ext4_bh_unmapped(handle_t *handle, struct buffer_head *bh)
return !buffer_mapped(bh);
}
-int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+int ext4_page_mkwrite(struct vm_fault *vmf)
{
+ struct vm_area_struct *vma = vmf->vma;
struct page *page = vmf->page;
loff_t size;
unsigned long len;
@@ -5912,13 +5913,13 @@ out:
return ret;
}
-int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+int ext4_filemap_fault(struct vm_fault *vmf)
{
- struct inode *inode = file_inode(vma->vm_file);
+ struct inode *inode = file_inode(vmf->vma->vm_file);
int err;
down_read(&EXT4_I(inode)->i_mmap_sem);
- err = filemap_fault(vma, vmf);
+ err = filemap_fault(vmf);
up_read(&EXT4_I(inode)->i_mmap_sem);
return err;
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 49f10dce817d..1edc86e874e3 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -32,11 +32,10 @@
#include "trace.h"
#include <trace/events/f2fs.h>
-static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
- struct vm_fault *vmf)
+static int f2fs_vm_page_mkwrite(struct vm_fault *vmf)
{
struct page *page = vmf->page;
- struct inode *inode = file_inode(vma->vm_file);
+ struct inode *inode = file_inode(vmf->vma->vm_file);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
int err;
@@ -58,7 +57,7 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
f2fs_balance_fs(sbi, dn.node_changed);
- file_update_time(vma->vm_file);
+ file_update_time(vmf->vma->vm_file);
lock_page(page);
if (unlikely(page->mapping != inode->i_mapping ||
page_offset(page) > i_size_read(inode) ||
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 2401c5dabb2a..e80bfd06daf5 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2043,12 +2043,12 @@ static void fuse_vma_close(struct vm_area_struct *vma)
* - sync(2)
* - try_to_free_pages() with order > PAGE_ALLOC_COSTLY_ORDER
*/
-static int fuse_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int fuse_page_mkwrite(struct vm_fault *vmf)
{
struct page *page = vmf->page;
- struct inode *inode = file_inode(vma->vm_file);
+ struct inode *inode = file_inode(vmf->vma->vm_file);
- file_update_time(vma->vm_file);
+ file_update_time(vmf->vma->vm_file);
lock_page(page);
if (page->mapping != inode->i_mapping) {
unlock_page(page);
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 016c11eaca7c..6fe2a59c6a9a 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -379,10 +379,10 @@ static int gfs2_allocate_page_backing(struct page *page)
* blocks allocated on disk to back that page.
*/
-static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int gfs2_page_mkwrite(struct vm_fault *vmf)
{
struct page *page = vmf->page;
- struct inode *inode = file_inode(vma->vm_file);
+ struct inode *inode = file_inode(vmf->vma->vm_file);
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct gfs2_alloc_parms ap = { .aflags = 0, };
@@ -399,7 +399,7 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
if (ret)
goto out;
- gfs2_size_hint(vma->vm_file, pos, PAGE_SIZE);
+ gfs2_size_hint(vmf->vma->vm_file, pos, PAGE_SIZE);
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
ret = gfs2_glock_nq(&gh);
@@ -407,7 +407,7 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
goto out_uninit;
/* Update file times before taking page lock */
- file_update_time(vma->vm_file);
+ file_update_time(vmf->vma->vm_file);
set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);
set_bit(GIF_SW_PAGED, &ip->i_flags);
diff --git a/fs/iomap.c b/fs/iomap.c
index d89f70bbb952..d209f42cdcb8 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -445,11 +445,10 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length,
return length;
}
-int iomap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
- const struct iomap_ops *ops)
+int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops)
{
struct page *page = vmf->page;
- struct inode *inode = file_inode(vma->vm_file);
+ struct inode *inode = file_inode(vmf->vma->vm_file);
unsigned long length;
loff_t offset, size;
ssize_t ret;
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 78219d5644e9..4f0535890b30 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -348,9 +348,9 @@ static void kernfs_vma_open(struct vm_area_struct *vma)
kernfs_put_active(of->kn);
}
-static int kernfs_vma_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int kernfs_vma_fault(struct vm_fault *vmf)
{
- struct file *file = vma->vm_file;
+ struct file *file = vmf->vma->vm_file;
struct kernfs_open_file *of = kernfs_of(file);
int ret;
@@ -362,16 +362,15 @@ static int kernfs_vma_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
ret = VM_FAULT_SIGBUS;
if (of->vm_ops->fault)
- ret = of->vm_ops->fault(vma, vmf);
+ ret = of->vm_ops->fault(vmf);
kernfs_put_active(of->kn);
return ret;
}
-static int kernfs_vma_page_mkwrite(struct vm_area_struct *vma,
- struct vm_fault *vmf)
+static int kernfs_vma_page_mkwrite(struct vm_fault *vmf)
{
- struct file *file = vma->vm_file;
+ struct file *file = vmf->vma->vm_file;
struct kernfs_open_file *of = kernfs_of(file);
int ret;
@@ -383,7 +382,7 @@ static int kernfs_vma_page_mkwrite(struct vm_area_struct *vma,
ret = 0;
if (of->vm_ops->page_mkwrite)
- ret = of->vm_ops->page_mkwrite(vma, vmf);
+ ret = of->vm_ops->page_mkwrite(vmf);
else
file_update_time(file);
diff --git a/fs/ncpfs/mmap.c b/fs/ncpfs/mmap.c
index 39f57bef8531..0c3905e0542e 100644
--- a/fs/ncpfs/mmap.c
+++ b/fs/ncpfs/mmap.c
@@ -27,10 +27,9 @@
* XXX: how are we excluding truncate/invalidate here? Maybe need to lock
* page?
*/
-static int ncp_file_mmap_fault(struct vm_area_struct *area,
- struct vm_fault *vmf)
+static int ncp_file_mmap_fault(struct vm_fault *vmf)
{
- struct inode *inode = file_inode(area->vm_file);
+ struct inode *inode = file_inode(vmf->vma->vm_file);
char *pg_addr;
unsigned int already_read;
unsigned int count;
@@ -90,7 +89,7 @@ static int ncp_file_mmap_fault(struct vm_area_struct *area,
* -- nyc
*/
count_vm_event(PGMAJFAULT);
- mem_cgroup_count_vm_event(area->vm_mm, PGMAJFAULT);
+ mem_cgroup_count_vm_event(vmf->vma->vm_mm, PGMAJFAULT);
return VM_FAULT_MAJOR;
}
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 26dbe8b0c10d..668213984d68 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -528,10 +528,10 @@ const struct address_space_operations nfs_file_aops = {
* writable, implying that someone is about to modify the page through a
* shared-writable mapping
*/
-static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int nfs_vm_page_mkwrite(struct vm_fault *vmf)
{
struct page *page = vmf->page;
- struct file *filp = vma->vm_file;
+ struct file *filp = vmf->vma->vm_file;
struct inode *inode = file_inode(filp);
unsigned pagelen;
int ret = VM_FAULT_NOPAGE;
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index 547381f3ce13..c5fa3dee72fc 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -51,8 +51,9 @@ int nilfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
return err;
}
-static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int nilfs_page_mkwrite(struct vm_fault *vmf)
{
+ struct vm_area_struct *vma = vmf->vma;
struct page *page = vmf->page;
struct inode *inode = file_inode(vma->vm_file);
struct nilfs_transaction_info ti;
diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c
index 429088786e93..098f5c712569 100644
--- a/fs/ocfs2/mmap.c
+++ b/fs/ocfs2/mmap.c
@@ -44,17 +44,18 @@
#include "ocfs2_trace.h"
-static int ocfs2_fault(struct vm_area_struct *area, struct vm_fault *vmf)
+static int ocfs2_fault(struct vm_fault *vmf)
{
+ struct vm_area_struct *vma = vmf->vma;
sigset_t oldset;
int ret;
ocfs2_block_signals(&oldset);
- ret = filemap_fault(area, vmf);
+ ret = filemap_fault(vmf);
ocfs2_unblock_signals(&oldset);
- trace_ocfs2_fault(OCFS2_I(area->vm_file->f_mapping->host)->ip_blkno,
- area, vmf->page, vmf->pgoff);
+ trace_ocfs2_fault(OCFS2_I(vma->vm_file->f_mapping->host)->ip_blkno,
+ vma, vmf->page, vmf->pgoff);
return ret;
}
@@ -127,10 +128,10 @@ out:
return ret;
}
-static int ocfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int ocfs2_page_mkwrite(struct vm_fault *vmf)
{
struct page *page = vmf->page;
- struct inode *inode = file_inode(vma->vm_file);
+ struct inode *inode = file_inode(vmf->vma->vm_file);
struct buffer_head *di_bh = NULL;
sigset_t oldset;
int ret;
@@ -160,7 +161,7 @@ static int ocfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
*/
down_write(&OCFS2_I(inode)->ip_alloc_sem);
- ret = __ocfs2_page_mkwrite(vma->vm_file, di_bh, page);
+ ret = __ocfs2_page_mkwrite(vmf->vma->vm_file, di_bh, page);
up_write(&OCFS2_I(inode)->ip_alloc_sem);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index b73b4de8fb36..b8f06273353e 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -292,101 +292,69 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
}
} else {
/*
- * Command line (1 string) occupies ARGV and maybe
- * extends into ENVP.
- */
- if (len1 + len2 <= *pos)
- goto skip_argv_envp;
- if (len1 <= *pos)
- goto skip_argv;
-
- p = arg_start + *pos;
- len = len1 - *pos;
- while (count > 0 && len > 0) {
- unsigned int _count, l;
- int nr_read;
- bool final;
-
- _count = min3(count, len, PAGE_SIZE);
- nr_read = access_remote_vm(mm, p, page, _count, 0);
- if (nr_read < 0)
- rv = nr_read;
- if (nr_read <= 0)
- goto out_free_page;
-
- /*
- * Command line can be shorter than whole ARGV
- * even if last "marker" byte says it is not.
- */
- final = false;
- l = strnlen(page, nr_read);
- if (l < nr_read) {
- nr_read = l;
- final = true;
- }
-
- if (copy_to_user(buf, page, nr_read)) {
- rv = -EFAULT;
- goto out_free_page;
- }
-
- p += nr_read;
- len -= nr_read;
- buf += nr_read;
- count -= nr_read;
- rv += nr_read;
-
- if (final)
- goto out_free_page;
- }
-skip_argv:
- /*
* Command line (1 string) occupies ARGV and
* extends into ENVP.
*/
- if (len1 <= *pos) {
- p = env_start + *pos - len1;
- len = len1 + len2 - *pos;
- } else {
- p = env_start;
- len = len2;
+ struct {
+ unsigned long p;
+ unsigned long len;
+ } cmdline[2] = {
+ { .p = arg_start, .len = len1 },
+ { .p = env_start, .len = len2 },
+ };
+ loff_t pos1 = *pos;
+ unsigned int i;
+
+ i = 0;
+ while (i < 2 && pos1 >= cmdline[i].len) {
+ pos1 -= cmdline[i].len;
+ i++;
}
- while (count > 0 && len > 0) {
- unsigned int _count, l;
- int nr_read;
- bool final;
-
- _count = min3(count, len, PAGE_SIZE);
- nr_read = access_remote_vm(mm, p, page, _count, 0);
- if (nr_read < 0)
- rv = nr_read;
- if (nr_read <= 0)
- goto out_free_page;
-
- /* Find EOS. */
- final = false;
- l = strnlen(page, nr_read);
- if (l < nr_read) {
- nr_read = l;
- final = true;
- }
-
- if (copy_to_user(buf, page, nr_read)) {
- rv = -EFAULT;
- goto out_free_page;
+ while (i < 2) {
+ p = cmdline[i].p + pos1;
+ len = cmdline[i].len - pos1;
+ while (count > 0 && len > 0) {
+ unsigned int _count, l;
+ int nr_read;
+ bool final;
+
+ _count = min3(count, len, PAGE_SIZE);
+ nr_read = access_remote_vm(mm, p, page, _count, 0);
+ if (nr_read < 0)
+ rv = nr_read;
+ if (nr_read <= 0)
+ goto out_free_page;
+
+ /*
+ * Command line can be shorter than whole ARGV
+ * even if last "marker" byte says it is not.
+ */
+ final = false;
+ l = strnlen(page, nr_read);
+ if (l < nr_read) {
+ nr_read = l;
+ final = true;
+ }
+
+ if (copy_to_user(buf, page, nr_read)) {
+ rv = -EFAULT;
+ goto out_free_page;
+ }
+
+ p += nr_read;
+ len -= nr_read;
+ buf += nr_read;
+ count -= nr_read;
+ rv += nr_read;
+
+ if (final)
+ goto out_free_page;
}
- p += nr_read;
- len -= nr_read;
- buf += nr_read;
- count -= nr_read;
- rv += nr_read;
-
- if (final)
- goto out_free_page;
+ /* Only first chunk can be read partially. */
+ pos1 = 0;
+ i++;
}
-skip_argv_envp:
- ;
}
out_free_page:
@@ -729,11 +697,11 @@ static int proc_pid_permission(struct inode *inode, int mask)
task = get_proc_task(inode);
if (!task)
return -ESRCH;
- has_perms = has_pid_permissions(pid, task, 1);
+ has_perms = has_pid_permissions(pid, task, HIDEPID_NO_ACCESS);
put_task_struct(task);
if (!has_perms) {
- if (pid->hide_pid == 2) {
+ if (pid->hide_pid == HIDEPID_INVISIBLE) {
/*
* Let's make getdents(), stat(), and open()
* consistent with each other. If a process
@@ -1769,7 +1737,7 @@ int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
stat->gid = GLOBAL_ROOT_GID;
task = pid_task(proc_pid(inode), PIDTYPE_PID);
if (task) {
- if (!has_pid_permissions(pid, task, 2)) {
+ if (!has_pid_permissions(pid, task, HIDEPID_INVISIBLE)) {
rcu_read_unlock();
/*
* This doesn't prevent learning whether PID exists,
@@ -3200,7 +3168,7 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx)
int len;
cond_resched();
- if (!has_pid_permissions(ns, iter.task, 2))
+ if (!has_pid_permissions(ns, iter.task, HIDEPID_INVISIBLE))
continue;
len = snprintf(name, sizeof(name), "%d", iter.tgid);
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index f6a01f09f79d..06c73904d497 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -57,9 +57,9 @@ static struct proc_dir_entry *pde_subdir_find(struct proc_dir_entry *dir,
struct rb_node *node = dir->subdir.rb_node;
while (node) {
- struct proc_dir_entry *de = container_of(node,
- struct proc_dir_entry,
- subdir_node);
+ struct proc_dir_entry *de = rb_entry(node,
+ struct proc_dir_entry,
+ subdir_node);
int result = proc_match(len, name, de);
if (result < 0)
@@ -80,8 +80,9 @@ static bool pde_subdir_insert(struct proc_dir_entry *dir,
/* Figure out where to put new node */
while (*new) {
- struct proc_dir_entry *this =
- container_of(*new, struct proc_dir_entry, subdir_node);
+ struct proc_dir_entry *this = rb_entry(*new,
+ struct proc_dir_entry,
+ subdir_node);
int result = proc_match(de->namelen, de->name, this);
parent = *new;
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 7ad9ed7958af..2cc7a8030275 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -107,7 +107,7 @@ static int proc_show_options(struct seq_file *seq, struct dentry *root)
if (!gid_eq(pid->pid_gid, GLOBAL_ROOT_GID))
seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, pid->pid_gid));
- if (pid->hide_pid != 0)
+ if (pid->hide_pid != HIDEPID_OFF)
seq_printf(seq, ",hidepid=%u", pid->hide_pid);
return 0;
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 1988440b2049..b90da888b81a 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -58,7 +58,8 @@ int proc_parse_options(char *options, struct pid_namespace *pid)
case Opt_hidepid:
if (match_int(&args[0], &option))
return 0;
- if (option < 0 || option > 2) {
+ if (option < HIDEPID_OFF ||
+ option > HIDEPID_INVISIBLE) {
pr_err("proc: hidepid value must be between 0 and 2.\n");
return 0;
}
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 5105b1599981..885d445afa0d 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -265,10 +265,10 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
* On s390 the fault handler is used for memory regions that can't be mapped
* directly with remap_pfn_range().
*/
-static int mmap_vmcore_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int mmap_vmcore_fault(struct vm_fault *vmf)
{
#ifdef CONFIG_S390
- struct address_space *mapping = vma->vm_file->f_mapping;
+ struct address_space *mapping = vmf->vma->vm_file->f_mapping;
pgoff_t index = vmf->pgoff;
struct page *page;
loff_t offset;
@@ -388,7 +388,7 @@ static int remap_oldmem_pfn_checked(struct vm_area_struct *vma,
}
return 0;
fail:
- do_munmap(vma->vm_mm, from, len);
+ do_munmap(vma->vm_mm, from, len, NULL);
return -EAGAIN;
}
@@ -481,7 +481,7 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
return 0;
fail:
- do_munmap(vma->vm_mm, vma->vm_start, len);
+ do_munmap(vma->vm_mm, vma->vm_start, len, NULL);
return -EAGAIN;
}
#else
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index 729677e18e36..efab7b64925b 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -342,31 +342,35 @@ static int compress_lz4(const void *in, void *out, size_t inlen, size_t outlen)
{
int ret;
- ret = lz4_compress(in, inlen, out, &outlen, workspace);
- if (ret) {
- pr_err("lz4_compress error, ret = %d!\n", ret);
+ ret = LZ4_compress_default(in, out, inlen, outlen, workspace);
+ if (!ret) {
+ pr_err("LZ4_compress_default error; compression failed!\n");
return -EIO;
}
- return outlen;
+ return ret;
}
static int decompress_lz4(void *in, void *out, size_t inlen, size_t outlen)
{
int ret;
- ret = lz4_decompress_unknownoutputsize(in, inlen, out, &outlen);
- if (ret) {
- pr_err("lz4_decompress error, ret = %d!\n", ret);
+ ret = LZ4_decompress_safe(in, out, inlen, outlen);
+ if (ret < 0) {
+ /*
+ * LZ4_decompress_safe will return an error code
+ * (< 0) if decompression failed
+ */
+ pr_err("LZ4_decompress_safe error, ret = %d!\n", ret);
return -EIO;
}
- return outlen;
+ return ret;
}
static void allocate_lz4(void)
{
- big_oops_buf_sz = lz4_compressbound(psinfo->bufsize);
+ big_oops_buf_sz = LZ4_compressBound(psinfo->bufsize);
big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL);
if (big_oops_buf) {
workspace = kmalloc(LZ4_MEM_COMPRESS, GFP_KERNEL);
diff --git a/fs/squashfs/lz4_wrapper.c b/fs/squashfs/lz4_wrapper.c
index ff4468bd18b0..95da65366548 100644
--- a/fs/squashfs/lz4_wrapper.c
+++ b/fs/squashfs/lz4_wrapper.c
@@ -97,7 +97,6 @@ static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm,
struct squashfs_lz4 *stream = strm;
void *buff = stream->input, *data;
int avail, i, bytes = length, res;
- size_t dest_len = output->length;
for (i = 0; i < b; i++) {
avail = min(bytes, msblk->devblksize - offset);
@@ -108,12 +107,13 @@ static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm,
put_bh(bh[i]);
}
- res = lz4_decompress_unknownoutputsize(stream->input, length,
- stream->output, &dest_len);
- if (res)
+ res = LZ4_decompress_safe(stream->input, stream->output,
+ length, output->length);
+
+ if (res < 0)
return -EIO;
- bytes = dest_len;
+ bytes = res;
data = squashfs_first_page(output);
buff = stream->output;
while (data) {
@@ -128,7 +128,7 @@ static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm,
}
squashfs_finish_page(output);
- return dest_len;
+ return res;
}
const struct squashfs_decompressor squashfs_lz4_comp_ops = {
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index b0d783774c96..d9ae86f96df7 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -1506,11 +1506,10 @@ static int ubifs_releasepage(struct page *page, gfp_t unused_gfp_flags)
* mmap()d file has taken write protection fault and is being made writable.
* UBIFS must ensure page is budgeted for.
*/
-static int ubifs_vm_page_mkwrite(struct vm_area_struct *vma,
- struct vm_fault *vmf)
+static int ubifs_vm_page_mkwrite(struct vm_fault *vmf)
{
struct page *page = vmf->page;
- struct inode *inode = file_inode(vma->vm_file);
+ struct inode *inode = file_inode(vmf->vma->vm_file);
struct ubifs_info *c = inode->i_sb->s_fs_info;
struct timespec now = ubifs_current_time(inode);
struct ubifs_budget_req req = { .new_page = 1 };
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 18406158e13f..625b7285a37b 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -71,6 +71,13 @@ struct userfaultfd_fork_ctx {
struct list_head list;
};
+struct userfaultfd_unmap_ctx {
+ struct userfaultfd_ctx *ctx;
+ unsigned long start;
+ unsigned long end;
+ struct list_head list;
+};
+
struct userfaultfd_wait_queue {
struct uffd_msg msg;
wait_queue_t wq;
@@ -681,16 +688,16 @@ void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx,
userfaultfd_event_wait_completion(ctx, &ewq);
}
-void madvise_userfault_dontneed(struct vm_area_struct *vma,
- struct vm_area_struct **prev,
- unsigned long start, unsigned long end)
+void userfaultfd_remove(struct vm_area_struct *vma,
+ struct vm_area_struct **prev,
+ unsigned long start, unsigned long end)
{
struct mm_struct *mm = vma->vm_mm;
struct userfaultfd_ctx *ctx;
struct userfaultfd_wait_queue ewq;
ctx = vma->vm_userfaultfd_ctx.ctx;
- if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_MADVDONTNEED))
+ if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_REMOVE))
return;
userfaultfd_ctx_get(ctx);
@@ -700,15 +707,101 @@ void madvise_userfault_dontneed(struct vm_area_struct *vma,
msg_init(&ewq.msg);
- ewq.msg.event = UFFD_EVENT_MADVDONTNEED;
- ewq.msg.arg.madv_dn.start = start;
- ewq.msg.arg.madv_dn.end = end;
+ ewq.msg.event = UFFD_EVENT_REMOVE;
+ ewq.msg.arg.remove.start = start;
+ ewq.msg.arg.remove.end = end;
userfaultfd_event_wait_completion(ctx, &ewq);
down_read(&mm->mmap_sem);
}
+static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps,
+ unsigned long start, unsigned long end)
+{
+ struct userfaultfd_unmap_ctx *unmap_ctx;
+
+ list_for_each_entry(unmap_ctx, unmaps, list)
+ if (unmap_ctx->ctx == ctx && unmap_ctx->start == start &&
+ unmap_ctx->end == end)
+ return true;
+
+ return false;
+}
+
+int userfaultfd_unmap_prep(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end,
+ struct list_head *unmaps)
+{
+ for ( ; vma && vma->vm_start < end; vma = vma->vm_next) {
+ struct userfaultfd_unmap_ctx *unmap_ctx;
+ struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx;
+
+ if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_UNMAP) ||
+ has_unmap_ctx(ctx, unmaps, start, end))
+ continue;
+
+ unmap_ctx = kzalloc(sizeof(*unmap_ctx), GFP_KERNEL);
+ if (!unmap_ctx)
+ return -ENOMEM;
+
+ userfaultfd_ctx_get(ctx);
+ unmap_ctx->ctx = ctx;
+ unmap_ctx->start = start;
+ unmap_ctx->end = end;
+ list_add_tail(&unmap_ctx->list, unmaps);
+ }
+
+ return 0;
+}
+
+void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf)
+{
+ struct userfaultfd_unmap_ctx *ctx, *n;
+ struct userfaultfd_wait_queue ewq;
+
+ list_for_each_entry_safe(ctx, n, uf, list) {
+ msg_init(&ewq.msg);
+
+ ewq.msg.event = UFFD_EVENT_UNMAP;
+ ewq.msg.arg.remove.start = ctx->start;
+ ewq.msg.arg.remove.end = ctx->end;
+
+ userfaultfd_event_wait_completion(ctx->ctx, &ewq);
+
+ list_del(&ctx->list);
+ kfree(ctx);
+ }
+}
+
+void userfaultfd_exit(struct mm_struct *mm)
+{
+ struct vm_area_struct *vma = mm->mmap;
+
+ /*
+ * We can do the vma walk without locking because the caller
+ * (exit_mm) knows it now has exclusive access
+ */
+ while (vma) {
+ struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx;
+
+ if (ctx && (ctx->features & UFFD_FEATURE_EVENT_EXIT)) {
+ struct userfaultfd_wait_queue ewq;
+
+ userfaultfd_ctx_get(ctx);
+
+ msg_init(&ewq.msg);
+ ewq.msg.event = UFFD_EVENT_EXIT;
+
+ userfaultfd_event_wait_completion(ctx, &ewq);
+
+ ctx->features &= ~UFFD_FEATURE_EVENT_EXIT;
+ }
+
+ vma = vma->vm_next;
+ }
+}
+
static int userfaultfd_release(struct inode *inode, struct file *file)
{
struct userfaultfd_ctx *ctx = file->private_data;
@@ -1514,6 +1607,8 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
ret = mcopy_atomic(ctx->mm, uffdio_copy.dst, uffdio_copy.src,
uffdio_copy.len);
mmput(ctx->mm);
+ } else {
+ return -ENOSPC;
}
if (unlikely(put_user(ret, &user_uffdio_copy->copy)))
return -EFAULT;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 022014016d80..a50eca676670 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1379,22 +1379,21 @@ xfs_file_llseek(
*/
STATIC int
xfs_filemap_page_mkwrite(
- struct vm_area_struct *vma,
struct vm_fault *vmf)
{
- struct inode *inode = file_inode(vma->vm_file);
+ struct inode *inode = file_inode(vmf->vma->vm_file);
int ret;
trace_xfs_filemap_page_mkwrite(XFS_I(inode));
sb_start_pagefault(inode->i_sb);
- file_update_time(vma->vm_file);
+ file_update_time(vmf->vma->vm_file);
xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
if (IS_DAX(inode)) {
- ret = dax_iomap_fault(vma, vmf, &xfs_iomap_ops);
+ ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &xfs_iomap_ops);
} else {
- ret = iomap_page_mkwrite(vma, vmf, &xfs_iomap_ops);
+ ret = iomap_page_mkwrite(vmf, &xfs_iomap_ops);
ret = block_page_mkwrite_return(ret);
}
@@ -1406,23 +1405,22 @@ xfs_filemap_page_mkwrite(
STATIC int
xfs_filemap_fault(
- struct vm_area_struct *vma,
struct vm_fault *vmf)
{
- struct inode *inode = file_inode(vma->vm_file);
+ struct inode *inode = file_inode(vmf->vma->vm_file);
int ret;
trace_xfs_filemap_fault(XFS_I(inode));
/* DAX can shortcut the normal fault path on write faults! */
if ((vmf->flags & FAULT_FLAG_WRITE) && IS_DAX(inode))
- return xfs_filemap_page_mkwrite(vma, vmf);
+ return xfs_filemap_page_mkwrite(vmf);
xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
if (IS_DAX(inode))
- ret = dax_iomap_fault(vma, vmf, &xfs_iomap_ops);
+ ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &xfs_iomap_ops);
else
- ret = filemap_fault(vma, vmf);
+ ret = filemap_fault(vmf);
xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
return ret;
@@ -1431,13 +1429,14 @@ xfs_filemap_fault(
/*
* Similar to xfs_filemap_fault(), the DAX fault path can call into here on
* both read and write faults. Hence we need to handle both cases. There is no
- * ->pmd_mkwrite callout for huge pages, so we have a single function here to
+ * ->huge_mkwrite callout for huge pages, so we have a single function here to
* handle both cases here. @flags carries the information on the type of fault
* occuring.
*/
STATIC int
-xfs_filemap_pmd_fault(
- struct vm_fault *vmf)
+xfs_filemap_huge_fault(
+ 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);
@@ -1446,7 +1445,7 @@ xfs_filemap_pmd_fault(
if (!IS_DAX(inode))
return VM_FAULT_FALLBACK;
- trace_xfs_filemap_pmd_fault(ip);
+ trace_xfs_filemap_huge_fault(ip);
if (vmf->flags & FAULT_FLAG_WRITE) {
sb_start_pagefault(inode->i_sb);
@@ -1454,7 +1453,7 @@ xfs_filemap_pmd_fault(
}
xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
- ret = dax_iomap_pmd_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)
@@ -1471,11 +1470,10 @@ xfs_filemap_pmd_fault(
*/
static int
xfs_filemap_pfn_mkwrite(
- struct vm_area_struct *vma,
struct vm_fault *vmf)
{
- struct inode *inode = file_inode(vma->vm_file);
+ struct inode *inode = file_inode(vmf->vma->vm_file);
struct xfs_inode *ip = XFS_I(inode);
int ret = VM_FAULT_NOPAGE;
loff_t size;
@@ -1483,7 +1481,7 @@ xfs_filemap_pfn_mkwrite(
trace_xfs_filemap_pfn_mkwrite(ip);
sb_start_pagefault(inode->i_sb);
- file_update_time(vma->vm_file);
+ file_update_time(vmf->vma->vm_file);
/* check if the faulting page hasn't raced with truncate */
xfs_ilock(ip, XFS_MMAPLOCK_SHARED);
@@ -1491,7 +1489,7 @@ xfs_filemap_pfn_mkwrite(
if (vmf->pgoff >= size)
ret = VM_FAULT_SIGBUS;
else if (IS_DAX(inode))
- ret = dax_pfn_mkwrite(vma, vmf);
+ ret = dax_pfn_mkwrite(vmf);
xfs_iunlock(ip, XFS_MMAPLOCK_SHARED);
sb_end_pagefault(inode->i_sb);
return ret;
@@ -1500,7 +1498,7 @@ xfs_filemap_pfn_mkwrite(
static const struct vm_operations_struct xfs_file_vm_ops = {
.fault = xfs_filemap_fault,
- .pmd_fault = xfs_filemap_pmd_fault,
+ .huge_fault = xfs_filemap_huge_fault,
.map_pages = filemap_map_pages,
.page_mkwrite = xfs_filemap_page_mkwrite,
.pfn_mkwrite = xfs_filemap_pfn_mkwrite,
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index fb7555e73a62..383ac227ce2c 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -687,7 +687,7 @@ DEFINE_INODE_EVENT(xfs_inode_clear_cowblocks_tag);
DEFINE_INODE_EVENT(xfs_inode_free_cowblocks_invalid);
DEFINE_INODE_EVENT(xfs_filemap_fault);
-DEFINE_INODE_EVENT(xfs_filemap_pmd_fault);
+DEFINE_INODE_EVENT(xfs_filemap_huge_fault);
DEFINE_INODE_EVENT(xfs_filemap_page_mkwrite);
DEFINE_INODE_EVENT(xfs_filemap_pfn_mkwrite);