aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Documentation/feature-removal-schedule.txt27
-rw-r--r--Documentation/filesystems/Locking2
-rw-r--r--fs/gfs2/ops_address.c2
-rw-r--r--fs/gfs2/ops_file.c2
-rw-r--r--fs/gfs2/ops_vm.c36
-rw-r--r--fs/ncpfs/mmap.c23
-rw-r--r--fs/ocfs2/aops.c2
-rw-r--r--fs/ocfs2/mmap.c17
-rw-r--r--fs/xfs/linux-2.6/xfs_file.c23
-rw-r--r--include/linux/mm.h41
-rw-r--r--ipc/shm.c9
-rw-r--r--mm/filemap.c94
-rw-r--r--mm/filemap_xip.c54
-rw-r--r--mm/fremap.c103
-rw-r--r--mm/memory.c132
-rw-r--r--mm/mmap.c8
-rw-r--r--mm/nommu.c3
-rw-r--r--mm/rmap.c4
-rw-r--r--mm/shmem.c82
-rw-r--r--mm/truncate.c2
20 files changed, 394 insertions, 272 deletions
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 66c8b4b165c..716568afdff 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -135,6 +135,33 @@ Who: Greg Kroah-Hartman <gregkh@suse.de>
---------------------------
+What: filemap_nopage, filemap_populate
+When: April 2007
+Why: These legacy interfaces no longer have any callers in the kernel and
+ any functionality provided can be provided with filemap_fault. The
+ removal schedule is short because they are a big maintainence burden
+ and have some bugs.
+Who: Nick Piggin <npiggin@suse.de>
+
+---------------------------
+
+What: vm_ops.populate, install_page
+When: April 2007
+Why: These legacy interfaces no longer have any callers in the kernel and
+ any functionality provided can be provided with vm_ops.fault.
+Who: Nick Piggin <npiggin@suse.de>
+
+---------------------------
+
+What: vm_ops.nopage
+When: February 2008, provided in-kernel callers have been converted
+Why: This interface is replaced by vm_ops.fault, but it has been around
+ forever, is used by a lot of drivers, and doesn't cost much to
+ maintain.
+Who: Nick Piggin <npiggin@suse.de>
+
+---------------------------
+
What: Interrupt only SA_* flags
When: September 2007
Why: The interrupt related SA_* flags are replaced by IRQF_* to move them
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index d866551be03..970c8ec1a05 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -510,12 +510,14 @@ More details about quota locking can be found in fs/dquot.c.
prototypes:
void (*open)(struct vm_area_struct*);
void (*close)(struct vm_area_struct*);
+ struct page *(*fault)(struct vm_area_struct*, struct fault_data *);
struct page *(*nopage)(struct vm_area_struct*, unsigned long, int *);
locking rules:
BKL mmap_sem
open: no yes
close: no yes
+fault: no yes
nopage: no yes
================================================================================
diff --git a/fs/gfs2/ops_address.c b/fs/gfs2/ops_address.c
index 26c888890c2..ce90032c010 100644
--- a/fs/gfs2/ops_address.c
+++ b/fs/gfs2/ops_address.c
@@ -251,7 +251,7 @@ static int gfs2_readpage(struct file *file, struct page *page)
if (file) {
gf = file->private_data;
if (test_bit(GFF_EXLOCK, &gf->f_flags))
- /* gfs2_sharewrite_nopage has grabbed the ip->i_gl already */
+ /* gfs2_sharewrite_fault has grabbed the ip->i_gl already */
goto skip_lock;
}
gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME|LM_FLAG_TRY_1CB, &gh);
diff --git a/fs/gfs2/ops_file.c b/fs/gfs2/ops_file.c
index bad0b24cb77..581ac11b265 100644
--- a/fs/gfs2/ops_file.c
+++ b/fs/gfs2/ops_file.c
@@ -364,7 +364,7 @@ static int gfs2_mmap(struct file *file, struct vm_area_struct *vma)
else
vma->vm_ops = &gfs2_vm_ops_private;
- vma->vm_flags |= VM_CAN_INVALIDATE;
+ vma->vm_flags |= VM_CAN_INVALIDATE|VM_CAN_NONLINEAR;
gfs2_glock_dq_uninit(&i_gh);
diff --git a/fs/gfs2/ops_vm.c b/fs/gfs2/ops_vm.c
index d5a98cbfebd..e9fe6eb74e7 100644
--- a/fs/gfs2/ops_vm.c
+++ b/fs/gfs2/ops_vm.c
@@ -27,13 +27,13 @@
#include "trans.h"
#include "util.h"
-static struct page *gfs2_private_nopage(struct vm_area_struct *area,
- unsigned long address, int *type)
+static struct page *gfs2_private_fault(struct vm_area_struct *vma,
+ struct fault_data *fdata)
{
- struct gfs2_inode *ip = GFS2_I(area->vm_file->f_mapping->host);
+ struct gfs2_inode *ip = GFS2_I(vma->vm_file->f_mapping->host);
set_bit(GIF_PAGED, &ip->i_flags);
- return filemap_nopage(area, address, type);
+ return filemap_fault(vma, fdata);
}
static int alloc_page_backing(struct gfs2_inode *ip, struct page *page)
@@ -104,16 +104,14 @@ out:
return error;
}
-static struct page *gfs2_sharewrite_nopage(struct vm_area_struct *area,
- unsigned long address, int *type)
+static struct page *gfs2_sharewrite_fault(struct vm_area_struct *vma,
+ struct fault_data *fdata)
{
- struct file *file = area->vm_file;
+ struct file *file = vma->vm_file;
struct gfs2_file *gf = file->private_data;
struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
struct gfs2_holder i_gh;
struct page *result = NULL;
- unsigned long index = ((address - area->vm_start) >> PAGE_CACHE_SHIFT) +
- area->vm_pgoff;
int alloc_required;
int error;
@@ -124,23 +122,27 @@ static struct page *gfs2_sharewrite_nopage(struct vm_area_struct *area,
set_bit(GIF_PAGED, &ip->i_flags);
set_bit(GIF_SW_PAGED, &ip->i_flags);
- error = gfs2_write_alloc_required(ip, (u64)index << PAGE_CACHE_SHIFT,
- PAGE_CACHE_SIZE, &alloc_required);
- if (error)
+ error = gfs2_write_alloc_required(ip,
+ (u64)fdata->pgoff << PAGE_CACHE_SHIFT,
+ PAGE_CACHE_SIZE, &alloc_required);
+ if (error) {
+ fdata->type = VM_FAULT_OOM; /* XXX: are these right? */
goto out;
+ }
set_bit(GFF_EXLOCK, &gf->f_flags);
- result = filemap_nopage(area, address, type);
+ result = filemap_fault(vma, fdata);
clear_bit(GFF_EXLOCK, &gf->f_flags);
- if (!result || result == NOPAGE_OOM)
+ if (!result)
goto out;
if (alloc_required) {
error = alloc_page_backing(ip, result);
if (error) {
- if (area->vm_flags & VM_CAN_INVALIDATE)
+ if (vma->vm_flags & VM_CAN_INVALIDATE)
unlock_page(result);
page_cache_release(result);
+ fdata->type = VM_FAULT_OOM;
result = NULL;
goto out;
}
@@ -154,10 +156,10 @@ out:
}
struct vm_operations_struct gfs2_vm_ops_private = {
- .nopage = gfs2_private_nopage,
+ .fault = gfs2_private_fault,
};
struct vm_operations_struct gfs2_vm_ops_sharewrite = {
- .nopage = gfs2_sharewrite_nopage,
+ .fault = gfs2_sharewrite_fault,
};
diff --git a/fs/ncpfs/mmap.c b/fs/ncpfs/mmap.c
index 5416673418b..af48b792ca0 100644
--- a/fs/ncpfs/mmap.c
+++ b/fs/ncpfs/mmap.c
@@ -25,8 +25,8 @@
/*
* Fill in the supplied page for mmap
*/
-static struct page* ncp_file_mmap_nopage(struct vm_area_struct *area,
- unsigned long address, int *type)
+static struct page* ncp_file_mmap_fault(struct vm_area_struct *area,
+ struct fault_data *fdata)
{
struct file *file = area->vm_file;
struct dentry *dentry = file->f_path.dentry;
@@ -40,15 +40,17 @@ static struct page* ncp_file_mmap_nopage(struct vm_area_struct *area,
page = alloc_page(GFP_HIGHUSER); /* ncpfs has nothing against high pages
as long as recvmsg and memset works on it */
- if (!page)
- return page;
+ if (!page) {
+ fdata->type = VM_FAULT_OOM;
+ return NULL;
+ }
pg_addr = kmap(page);
- address &= PAGE_MASK;
- pos = address - area->vm_start + (area->vm_pgoff << PAGE_SHIFT);
+ pos = fdata->pgoff << PAGE_SHIFT;
count = PAGE_SIZE;
- if (address + PAGE_SIZE > area->vm_end) {
- count = area->vm_end - address;
+ if (fdata->address + PAGE_SIZE > area->vm_end) {
+ WARN_ON(1); /* shouldn't happen? */
+ count = area->vm_end - fdata->address;
}
/* what we can read in one go */
bufsize = NCP_SERVER(inode)->buffer_size;
@@ -91,15 +93,14 @@ static struct page* ncp_file_mmap_nopage(struct vm_area_struct *area,
* fetches from the network, here the analogue of disk.
* -- wli
*/
- if (type)
- *type = VM_FAULT_MAJOR;
+ fdata->type = VM_FAULT_MAJOR;
count_vm_event(PGMAJFAULT);
return page;
}
static struct vm_operations_struct ncp_file_mmap =
{
- .nopage = ncp_file_mmap_nopage,
+ .fault = ncp_file_mmap_fault,
};
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 84bf6e79de2..460d440310f 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -232,7 +232,7 @@ static int ocfs2_readpage(struct file *file, struct page *page)
* might now be discovering a truncate that hit on another node.
* block_read_full_page->get_block freaks out if it is asked to read
* beyond the end of a file, so we check here. Callers
- * (generic_file_read, fault->nopage) are clever enough to check i_size
+ * (generic_file_read, vm_ops->fault) are clever enough to check i_size
* and notice that the page they just read isn't needed.
*
* XXX sys_readahead() seems to get that wrong?
diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c
index 904f39ff534..cd75508b1c8 100644
--- a/fs/ocfs2/mmap.c
+++ b/fs/ocfs2/mmap.c
@@ -60,24 +60,23 @@ static inline int ocfs2_vm_op_unblock_sigs(sigset_t *oldset)
return sigprocmask(SIG_SETMASK, oldset, NULL);
}
-static struct page *ocfs2_nopage(struct vm_area_struct * area,
- unsigned long address,
- int *type)
+static struct page *ocfs2_fault(struct vm_area_struct *area,
+ struct fault_data *fdata)
{
- struct page *page = NOPAGE_SIGBUS;
+ struct page *page = NULL;
sigset_t blocked, oldset;
int ret;
- mlog_entry("(area=%p, address=%lu, type=%p)\n", area, address,
- type);
+ mlog_entry("(area=%p, page offset=%lu)\n", area, fdata->pgoff);
ret = ocfs2_vm_op_block_sigs(&blocked, &oldset);
if (ret < 0) {
+ fdata->type = VM_FAULT_SIGBUS;
mlog_errno(ret);
goto out;
}
- page = filemap_nopage(area, address, type);
+ page = filemap_fault(area, fdata);
ret = ocfs2_vm_op_unblock_sigs(&oldset);
if (ret < 0)
@@ -209,7 +208,7 @@ out:
}
static struct vm_operations_struct ocfs2_file_vm_ops = {
- .nopage = ocfs2_nopage,
+ .fault = ocfs2_fault,
.page_mkwrite = ocfs2_page_mkwrite,
};
@@ -226,7 +225,7 @@ int ocfs2_mmap(struct file *file, struct vm_area_struct *vma)
ocfs2_meta_unlock(file->f_dentry->d_inode, lock_level);
out:
vma->vm_ops = &ocfs2_file_vm_ops;
- vma->vm_flags |= VM_CAN_INVALIDATE;
+ vma->vm_flags |= VM_CAN_INVALIDATE | VM_CAN_NONLINEAR;
return 0;
}
diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c
index 92b2f225712..f12e80a69c6 100644
--- a/fs/xfs/linux-2.6/xfs_file.c
+++ b/fs/xfs/linux-2.6/xfs_file.c
@@ -213,18 +213,19 @@ xfs_file_fsync(
#ifdef CONFIG_XFS_DMAPI
STATIC struct page *
-xfs_vm_nopage(
- struct vm_area_struct *area,
- unsigned long address,
- int *type)
+xfs_vm_fault(
+ struct vm_area_struct *vma,
+ struct fault_data *fdata)
{
- struct inode *inode = area->vm_file->f_path.dentry->d_inode;
+ struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
bhv_vnode_t *vp = vn_from_inode(inode);
ASSERT_ALWAYS(vp->v_vfsp->vfs_flag & VFS_DMI);
- if (XFS_SEND_MMAP(XFS_VFSTOM(vp->v_vfsp), area, 0))
+ if (XFS_SEND_MMAP(XFS_VFSTOM(vp->v_vfsp), vma, 0)) {
+ fdata->type = VM_FAULT_SIGBUS;
return NULL;
- return filemap_nopage(area, address, type);
+ }
+ return filemap_fault(vma, fdata);
}
#endif /* CONFIG_XFS_DMAPI */
@@ -310,7 +311,7 @@ xfs_file_mmap(
struct vm_area_struct *vma)
{
vma->vm_ops = &xfs_file_vm_ops;
- vma->vm_flags |= VM_CAN_INVALIDATE;
+ vma->vm_flags |= VM_CAN_INVALIDATE | VM_CAN_NONLINEAR;
#ifdef CONFIG_XFS_DMAPI
if (vn_from_inode(filp->f_path.dentry->d_inode)->v_vfsp->vfs_flag & VFS_DMI)
@@ -465,14 +466,12 @@ const struct file_operations xfs_dir_file_operations = {
};
static struct vm_operations_struct xfs_file_vm_ops = {
- .nopage = filemap_nopage,
- .populate = filemap_populate,
+ .fault = filemap_fault,
};
#ifdef CONFIG_XFS_DMAPI
static struct vm_operations_struct xfs_dmapi_file_vm_ops = {
- .nopage = xfs_vm_nopage,
- .populate = filemap_populate,
+ .fault = xfs_vm_fault,
#ifdef HAVE_VMOP_MPROTECT
.mprotect = xfs_vm_mprotect,
#endif
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ca9536a348c..f28a1b3e63a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -173,6 +173,7 @@ extern unsigned int kobjsize(const void *objp);
* In this case, do_no_page must
* return with the page locked.
*/
+#define VM_CAN_NONLINEAR 0x10000000 /* Has ->fault & does nonlinear pages */
#ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */
#define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS
@@ -196,6 +197,25 @@ extern unsigned int kobjsize(const void *objp);
*/
extern pgprot_t protection_map[16];
+#define FAULT_FLAG_WRITE 0x01
+#define FAULT_FLAG_NONLINEAR 0x02
+
+/*
+ * fault_data is filled in the the pagefault handler and passed to the
+ * vma's ->fault function. That function is responsible for filling in
+ * 'type', which is the type of fault if a page is returned, or the type
+ * of error if NULL is returned.
+ *
+ * pgoff should be used in favour of address, if possible. If pgoff is
+ * used, one may set VM_CAN_NONLINEAR in the vma->vm_flags to get
+ * nonlinear mapping support.
+ */
+struct fault_data {
+ unsigned long address;
+ pgoff_t pgoff;
+ unsigned int flags;
+ int type;
+};
/*
* These are the virtual MM functions - opening of an area, closing and
@@ -205,9 +225,15 @@ extern pgprot_t protection_map[16];
struct vm_operations_struct {
void (*open)(struct vm_area_struct * area);
void (*close)(struct vm_area_struct * area);
- struct page * (*nopage)(struct vm_area_struct * area, unsigned long address, int *type);
- unsigned long (*nopfn)(struct vm_area_struct * area, unsigned long address);
- int (*populate)(struct vm_area_struct * area, unsigned long address, unsigned long len, pgprot_t prot, unsigned long pgoff, int nonblock);
+ struct page *(*fault)(struct vm_area_struct *vma,
+ struct fault_data *fdata);
+ struct page *(*nopage)(struct vm_area_struct *area,
+ unsigned long address, int *type);
+ unsigned long (*nopfn)(struct vm_area_struct *area,
+ unsigned long address);
+ int (*populate)(struct vm_area_struct *area, unsigned long address,
+ unsigned long len, pgprot_t prot, unsigned long pgoff,
+ int nonblock);
/* notification that a previously read-only page is about to become
* writable, if an error is returned it will cause a SIGBUS */
@@ -661,7 +687,6 @@ static inline int page_mapped(struct page *page)
*/
#define NOPAGE_SIGBUS (NULL)
#define NOPAGE_OOM ((struct page *) (-1))
-#define NOPAGE_REFAULT ((struct page *) (-2)) /* Return to userspace, rerun */
/*
* Error return values for the *_nopfn functions
@@ -1110,9 +1135,11 @@ extern void truncate_inode_pages_range(struct address_space *,
loff_t lstart, loff_t lend);
/* generic vm_area_ops exported for stackable file systems */
-extern struct page *filemap_nopage(struct vm_area_struct *, unsigned long, int *);
-extern int filemap_populate(struct vm_area_struct *, unsigned long,
- unsigned long, pgprot_t, unsigned long, int);
+extern struct page *filemap_fault(struct vm_area_struct *, struct fault_data *);
+extern struct page * __deprecated_for_modules
+filemap_nopage(struct vm_area_struct *, unsigned long, int *);
+extern int __deprecated_for_modules filemap_populate(struct vm_area_struct *,
+ unsigned long, unsigned long, pgprot_t, unsigned long, int);
/* mm/page-writeback.c */
int write_one_page(struct page *page, int wait);
diff --git a/ipc/shm.c b/ipc/shm.c
index 242c3f66493..e2d090348b1 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -224,13 +224,13 @@ static void shm_close(struct vm_area_struct *vma)
mutex_unlock(&shm_ids(ns).mutex);
}
-static struct page *shm_nopage(struct vm_area_struct *vma,
- unsigned long address, int *type)
+static struct page *shm_fault(struct vm_area_struct *vma,
+ struct fault_data *fdata)
{
struct file *file = vma->vm_file;
struct shm_file_data *sfd = shm_file_data(file);
- return sfd->vm_ops->nopage(vma, address, type);
+ return sfd->vm_ops->fault(vma, fdata);
}
#ifdef CONFIG_NUMA
@@ -269,6 +269,7 @@ static int shm_mmap(struct file * file, struct vm_area_struct * vma)
if (ret != 0)
return ret;
sfd->vm_ops = vma->vm_ops;
+ BUG_ON(!sfd->vm_ops->fault);
vma->vm_ops = &shm_vm_ops;
shm_open(vma);
@@ -327,7 +328,7 @@ static const struct file_operations shm_file_operations = {
static struct vm_operations_struct shm_vm_ops = {
.open = shm_open, /* callback for a new vm-area open */
.close = shm_close, /* callback for when the vm-area is released */
- .nopage = shm_nopage,
+ .fault = shm_fault,
#if defined(CONFIG_NUMA)
.set_policy = shm_set_policy,
.get_policy = shm_get_policy,
diff --git a/mm/filemap.c b/mm/filemap.c
index 462cda58a18..26b992d169e 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1301,40 +1301,38 @@ static int fastcall page_cache_read(struct file * file, unsigned long offset)
#define MMAP_LOTSAMISS (100)
/**
- * filemap_nopage - read in file data for page fault handling
- * @area: the applicable vm_area
- * @address: target address to read in
- * @type: returned with VM_FAULT_{MINOR,MAJOR} if not %NULL
+ * filemap_fault - read in file data for page fault handling
+ * @vma: user vma (not used)
+ * @fdata: the applicable fault_data
*
- * filemap_nopage() is invoked via the vma operations vector for a
+ * filemap_fault() is invoked via the vma operations vector for a
* mapped memory region to read in file data during a page fault.
*
* The goto's are kind of ugly, but this streamlines the normal case of having
* it in the page cache, and handles the special cases reasonably without
* having a lot of duplicated code.
*/
-struct page *filemap_nopage(struct vm_area_struct *area,
- unsigned long address, int *type)
+struct page *filemap_fault(struct vm_area_struct *vma, struct fault_data *fdata)
{
int error;
- struct file *file = area->vm_file;
+ struct file *file = vma->vm_file;
struct address_space *mapping = file->f_mapping;
struct file_ra_state *ra = &file->f_ra;
struct inode *inode = mapping->host;
struct page *page;
- unsigned long size, pgoff;
- int did_readaround = 0, majmin = VM_FAULT_MINOR;
+ unsigned long size;
+ int did_readaround = 0;
- BUG_ON(!(area->vm_flags & VM_CAN_INVALIDATE));
+ fdata->type = VM_FAULT_MINOR;
- pgoff = ((address-area->vm_start) >> PAGE_CACHE_SHIFT) + area->vm_pgoff;
+ BUG_ON(!(vma->vm_flags & VM_CAN_INVALIDATE));
size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
- if (pgoff >= size)
+ if (fdata->pgoff >= size)
goto outside_data_content;
/* If we don't want any read-ahead, don't bother */
- if (VM_RandomReadHint(area))
+ if (VM_RandomReadHint(vma))
goto no_cached_page;
/*
@@ -1343,19 +1341,19 @@ struct page *filemap_nopage(struct vm_area_struct *area,
*
* For sequential accesses, we use the generic readahead logic.
*/
- if (VM_SequentialReadHint(area))
- page_cache_readahead(mapping, ra, file, pgoff, 1);
+ if (VM_SequentialReadHint(vma))
+ page_cache_readahead(mapping, ra, file, fdata->pgoff, 1);
/*
* Do we have something in the page cache already?
*/
retry_find:
- page = find_lock_page(mapping, pgoff);
+ page = find_lock_page(mapping, fdata->pgoff);
if (!page) {
unsigned long ra_pages;
- if (VM_SequentialReadHint(area)) {
- handle_ra_miss(mapping, ra, pgoff);
+ if (VM_SequentialReadHint(vma)) {
+ handle_ra_miss(mapping, ra, fdata->pgoff);
goto no_cached_page;
}
ra->mmap_miss++;
@@ -1372,7 +1370,7 @@ retry_find:
* check did_readaround, as this is an inner loop.
*/
if (!did_readaround) {
- majmin = VM_FAULT_MAJOR;
+ fdata->type = VM_FAULT_MAJOR;
count_vm_event(PGMAJFAULT);
}
did_readaround = 1;
@@ -1380,11 +1378,11 @@ retry_find:
if (ra_pages) {
pgoff_t start = 0;
- if (pgoff > ra_pages / 2)
- start = pgoff - ra_pages / 2;
+ if (fdata->pgoff > ra_pages / 2)
+ start = fdata->pgoff - ra_pages / 2;
do_page_cache_readahead(mapping, file, start, ra_pages);
}
- page = find_lock_page(mapping, pgoff);
+ page = find_lock_page(mapping, fdata->pgoff);
if (!page)
goto no_cached_page;
}
@@ -1401,7 +1399,7 @@ retry_find:
/* Must recheck i_size under page lock */
size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
- if (unlikely(pgoff >= size)) {
+ if (unlikely(fdata->pgoff >= size)) {
unlock_page(page);
goto outside_data_content;
}
@@ -1410,8 +1408,6 @@ retry_find:
* Found the page and have a reference on it.
*/
mark_page_accessed(page);
- if (type)
- *type = majmin;
return page;
outside_data_content:
@@ -1419,15 +1415,17 @@ outside_data_content:
* An external ptracer can access pages that normally aren't
* accessible..
*/
- if (area->vm_mm == current->mm)
- return NOPAGE_SIGBUS;
+ if (vma->vm_mm == current->mm) {
+ fdata->type = VM_FAULT_SIGBUS;
+ return NULL;
+ }
/* Fall through to the non-read-ahead case */
no_cached_page:
/*
* We're only likely to ever get here if MADV_RANDOM is in
* effect.
*/
- error = page_cache_read(file, pgoff);
+ error = page_cache_read(file, fdata->pgoff);
/*
* The page we want has now been added to the page cache.
@@ -1443,13 +1441,15 @@ no_cached_page:
* to schedule I/O.
*/
if (error == -ENOMEM)
- return NOPAGE_OOM;
- return NOPAGE_SIGBUS;
+ fdata->type = VM_FAULT_OOM;
+ else
+ fdata->type = VM_FAULT_SIGBUS;
+ return NULL;
page_not_uptodate:
/* IO error path */
if (!did_readaround) {
- majmin = VM_FAULT_MAJOR;
+ fdata->type = VM_FAULT_MAJOR;
count_vm_event(PGMAJFAULT);
}
@@ -1468,7 +1468,30 @@ page_not_uptodate:
/* Things didn't work out. Return zero to tell the mm layer so. */
shrink_readahead_size_eio(file, ra);
- return NOPAGE_SIGBUS;
+ fdata->type = VM_FAULT_SIGBUS;
+ return NULL;
+}
+EXPORT_SYMBOL(filemap_fault);
+
+/*
+ * filemap_nopage and filemap_populate are legacy exports that are not used
+ * in tree. Scheduled for removal.
+ */
+struct page *filemap_nopage(struct vm_area_struct *area,
+ unsigned long address, int *type)
+{
+ struct page *page;
+ struct fault_data fdata;
+ fdata.address = address;
+ fdata.pgoff = ((address - area->vm_start) >> PAGE_CACHE_SHIFT)
+ + area->vm_pgoff;
+ fdata.flags = 0;
+
+ page = filemap_fault(area, &fdata);
+ if (type)
+ *type = fdata.type;
+
+ return page;
}
EXPORT_SYMBOL(filemap_nopage);
@@ -1646,8 +1669,7 @@ repeat:
EXPORT_SYMBOL(filemap_populate);
struct vm_operations_struct generic_file_vm_ops = {
- .nopage = filemap_nopage,
- .populate = filemap_populate,
+ .fault = filemap_fault,
};
/* This is used for a general mmap of a disk file */
@@ -1660,7 +1682,7 @@ int generic_file_mmap(struct file * file, struct vm_area_struct * vma)
return -ENOEXEC;
file_accessed(file);
vma->vm_ops = &generic_file_vm_ops;
- vma->vm_flags |= VM_CAN_INVALIDATE;
+ vma->vm_flags |= VM_CAN_INVALIDATE | VM_CAN_NONLINEAR;
return 0;
}
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index 65ffc321f0c..82f4b8e9834 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -205,62 +205,67 @@ __xip_unmap (struct address_space * mapping,
}
/*
- * xip_nopage() is invoked via the vma operations vector for a
+ * xip_fault() is invoked via the vma operations vector for a
* mapped memory region to read in file data during a page fault.
*
- * This function is derived from filemap_nopage, but used for execute in place
+ * This function is derived from filemap_fault, but used for execute in place
*/
-static struct page *
-xip_file_nopage(struct vm_area_struct * area,
- unsigned long address,
- int *type)
+static struct page *xip_file_fault(struct vm_area_struct *area,
+ struct fault_data *fdata)
{
struct file *file = area->vm_file;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
struct page *page;
- unsigned long size, pgoff, endoff;
+ pgoff_t size;
- pgoff = ((address - area->vm_start) >> PAGE_CACHE_SHIFT)
- + area->vm_pgoff;
- endoff = ((area->vm_end - area->vm_start) >> PAGE_CACHE_SHIFT)
- + area->vm_pgoff;
+ /* XXX: are VM_FAULT_ codes OK? */
size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
- if (pgoff >= size)
- return NOPAGE_SIGBUS;
+ if (fdata->pgoff >= size) {
+ fdata->type = VM_FAULT_SIGBUS;
+ return NULL;
+ }
- page = mapping->a_ops->get_xip_page(mapping, pgoff*(PAGE_SIZE/512), 0);
+ page = mapping->a_ops->get_xip_page(mapping,
+ fdata->pgoff*(PAGE_SIZE/512), 0);
if (!IS_ERR(page))
goto out;
- if (PTR_ERR(page) != -ENODATA)
- return NOPAGE_SIGBUS;
+ if (PTR_ERR(page) != -ENODATA) {
+ fdata->type = VM_FAULT_OOM;
+ return NULL;
+ }
/* sparse block */
if ((area->vm_flags & (VM_WRITE | VM_MAYWRITE)) &&
(area->vm_flags & (VM_SHARED| VM_MAYSHARE)) &&
(!(mapping->host->i_sb->s_flags & MS_RDONLY))) {
/* maybe shared writable, allocate new block */
- page = mapping->a_ops->get_xip_page (mapping,
- pgoff*(PAGE_SIZE/512), 1);
- if (IS_ERR(page))
- return NOPAGE_SIGBUS;
+ page = mapping->a_ops->get_xip_page(mapping,
+ fdata->pgoff*(PAGE_SIZE/512), 1);
+ if (IS_ERR(page)) {
+ fdata->type = VM_FAULT_SIGBUS;
+ return NULL;
+ }
/* unmap page at pgoff from all other vmas */
- __xip_unmap(mapping, pgoff);
+ __xip_unmap(mapping, fdata->pgoff);
} else {
/* not shared and writable, use xip_sparse_page() */
page = xip_sparse_page();
- if (!page)
- return NOPAGE_OOM;
+ if (!page) {
+ fdata->type = VM_FAULT_OOM;
+ return NULL;
+ }
}
out:
+ fdata->type = VM_FAULT_MINOR;
page_cache_get(page);
return page;
}
static struct vm_operations_struct xip_file_vm_ops = {
- .nopage = xip_file_nopage,
+ .fault = xip_file_fault,
};
int xip_file_mmap(struct file * file, struct vm_area_struct * vma)
@@ -269,6 +274,7 @@ int xip_file_mmap(struct file * file, struct vm_area_struct * vma)
file_accessed(file);
vma->vm_ops = &xip_file_vm_ops;
+ vma->vm_flags |= VM_CAN_NONLINEAR;
return 0;
}
EXPORT_SYMBOL_GPL(xip_file_mmap);
diff --git a/mm/fremap.c b/mm/fremap.c
index 4e3f53dd5fd..01e51f01b84 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -126,6 +126,25 @@ out:
return err;
}
+static int populate_range(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long addr, unsigned long size, pgoff_t pgoff)
+{
+ int err;
+
+ do {
+ err = install_file_pte(mm, vma, addr, pgoff, vma->vm_page_prot);
+ if (err)
+ return err;
+
+ size -= PAGE_SIZE;
+ addr += PAGE_SIZE;
+ pgoff++;
+ } while (size);
+
+ return 0;
+
+}
+
/***
* sys_remap_file_pages - remap arbitrary pages of a shared backing store
* file within an existing vma.
@@ -183,41 +202,63 @@ asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
* the single existing vma. vm_private_data is used as a
* swapout cursor in a VM_NONLINEAR vma.
*/
- if (vma && (vma->vm_flags & VM_SHARED) &&
- (!vma->vm_private_data || (vma->vm_flags & VM_NONLINEAR)) &&
- vma->vm_ops && vma->vm_ops->populate &&
- end > start && start >= vma->vm_start &&
- end <= vma->vm_end) {
-
- /* Must set VM_NONLINEAR before any pages are populated. */
- if (pgoff != linear_page_index(vma, start) &&
- !(vma->vm_flags & VM_NONLINEAR)) {
- if (!has_write_lock) {
- up_read(&mm->mmap_sem);
- down_write(&mm->mmap_sem);
- has_write_lock = 1;
- goto retry;
+ if (!vma || !(vma->vm_flags & VM_SHARED))
+ goto out;
+
+ if (vma->vm_private_data && !(vma->vm_flags & VM_NONLINEAR))
+ goto out;
+
+ if ((!vma->vm_ops || !vma->vm_ops->populate) &&
+ !(vma->vm_flags & VM_CAN_NONLINEAR))
+ goto out;
+
+ if (end <= start || start < vma->vm_start || end > vma->vm_end)
+ goto out;
+
+ /* Must set VM_NONLINEAR before any pages are populated. */
+ if (!(vma->vm_flags & VM_NONLINEAR)) {
+ /* Don't need a nonlinear mapping, exit success */
+ if (pgoff == linear_page_index(vma, start)) {
+ err = 0;
+ goto out;
+ }
+
+ if (!has_write_lock) {
+ up_read(&mm->mmap_sem);
+ down_write(&mm->mmap_sem);
+ has_write_lock = 1;
+ goto retry;
+ }
+ mapping = vma->vm_file->f_mapping;
+ spin_lock(&mapping->i_mmap_lock);
+ flush_dcache_mmap_lock(mapping);
+ vma->vm_flags |= VM_NONLINEAR;
+ vma_prio_tree_remove(vma, &mapping->i_mmap);
+ vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear);
+ flush_dcache_mmap_unlock(mapping);
+ spin_unlock(&mapping->i_mmap_lock);
+ }
+
+ if (vma->vm_flags & VM_CAN_NONLINEAR) {
+ err = populate_range(mm, vma, start, size, pgoff);
+ if (!err && !(flags & MAP_NONBLOCK)) {
+ if (unlikely(has_write_lock)) {
+ downgrade_write(&mm->mmap_sem);
+ has_write_lock = 0;
}
- mapping = vma->vm_file->f_mapping;
- spin_lock(&mapping->i_mmap_lock);
- flush_dcache_mmap_lock(mapping);
- vma->vm_flags |= VM_NONLINEAR;
- vma_prio_tree_remove(vma, &mapping->i_mmap);
- vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear);
- flush_dcache_mmap_unlock(mapping);
- spin_unlock(&mapping->i_mmap_lock);
+ make_pages_present(start, start+size);
}
+ } else
+ err = vma->vm_ops->populate(vma, start, size, vma->vm_page_prot,
+ pgoff, flags & MAP_NONBLOCK);
- err = vma->vm_ops->populate(vma, start, size,
- vma->vm_page_prot,
- pgoff, flags & MAP_NONBLOCK);
+ /*
+ * We can't clear VM_NONLINEAR because we'd have to do
+ * it after ->populate completes, and that would prevent
+ * downgrading the lock. (Locks can't be upgraded).
+ */
- /*
- * We can't clear VM_NONLINEAR because we'd have to do
- * it after ->populate completes, and that would prevent
- * downgrading the lock. (Locks can't be upgraded).
- */
- }
+out:
if (likely(!has_write_lock))
up_read(&mm->mmap_sem);
else
diff --git a/mm/memory.c b/mm/memory.c
index e6c99f6b564..eee7fec3ab5 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1047,7 +1047,8 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
if (pages)
foll_flags |= FOLL_GET;
if (!write && !(vma->vm_flags & VM_LOCKED) &&
-