redonkable
/
alistair23-linux
1
0
Fork 0
Code Releases Activity

orangefs: write range tracking 

Attach the actual range of bytes written to plus the responsible uid/gid
to each dirty page.  This information must be sent to the server when
the page is written out.

Now write_begin, page_mkwrite, and invalidatepage keep up with this
information.  There are several conditions where they must write out the
page immediately to store the new range.  Two non-contiguous ranges
cannot be stored on a single page.

Signed-off-by: Martin Brandenburg <martin@omnibond.com>
Signed-off-by: Mike Marshall <hubcap@omnibond.com>
hifive-unleashed-5.2
Martin Brandenburg 2018-12-14 15:24:43 -05:00 committed by Mike Marshall
parent 90fc07065a
commit 52e2d0a380
3 changed files with 274 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
fs/orangefs/file.c
View File

@ -46,8 +46,8 @@ static int flush_racache(struct inode *inode)
* Post and wait for the I/O upcall to finish
*/
ssize_t wait_for_direct_io(enum ORANGEFS_io_type type, struct inode *inode,
loff_t *offset, struct iov_iter *iter,
size_t total_size, loff_t readahead_size)
loff_t *offset, struct iov_iter *iter, size_t total_size,
loff_t readahead_size, struct orangefs_write_range *wr)
{
struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
struct orangefs_khandle *handle = &orangefs_inode->refn.khandle;
@ -85,6 +85,10 @@ populate_shared_memory:
new_op->upcall.req.io.buf_index = buffer_index;
new_op->upcall.req.io.count = total_size;
new_op->upcall.req.io.offset = *offset;
if (type == ORANGEFS_IO_WRITE && wr) {
new_op->upcall.uid = from_kuid(&init_user_ns, wr->uid);
new_op->upcall.gid = from_kgid(&init_user_ns, wr->gid);
}
gossip_debug(GOSSIP_FILE_DEBUG,
"%s(%pU): offset: %llu total_size: %zd\n",
@ -329,7 +333,7 @@ static vm_fault_t orangefs_fault(struct vm_fault *vmf)
static const struct vm_operations_struct orangefs_file_vm_ops = {
.fault = orangefs_fault,
.map_pages = filemap_map_pages,
.page_mkwrite = filemap_page_mkwrite,
.page_mkwrite = orangefs_page_mkwrite,
};
/*

289
fs/orangefs/inode.c
View File

@ -15,9 +15,11 @@
#include "orangefs-kernel.h"
#include "orangefs-bufmap.h"
static int orangefs_writepage(struct page *page, struct writeback_control *wbc)
static int orangefs_writepage_locked(struct page *page,
struct writeback_control *wbc)
{
struct inode *inode = page->mapping->host;
struct orangefs_write_range *wr = NULL;
struct iov_iter iter;
struct bio_vec bv;
size_t len, wlen;
@ -26,34 +28,52 @@ static int orangefs_writepage(struct page *page, struct writeback_control *wbc)
set_page_writeback(page);
off = page_offset(page);
len = i_size_read(inode);
if (off > len) {
/* The file was truncated; there is nothing to write. */
unlock_page(page);
end_page_writeback(page);
return 0;
if (PagePrivate(page)) {
wr = (struct orangefs_write_range *)page_private(page);
off = wr->pos;
if (off + wr->len > len)
wlen = len - off;
else
wlen = wr->len;
} else {
WARN_ON(1);
off = page_offset(page);
if (off + PAGE_SIZE > len)
wlen = len - off;
else
wlen = PAGE_SIZE;
}
if (off + PAGE_SIZE > len)
wlen = len - off;
else
wlen = PAGE_SIZE;
/* Should've been handled in orangefs_invalidatepage. */
WARN_ON(off == len || off + wlen > len);
bv.bv_page = page;
bv.bv_len = wlen;
bv.bv_offset = off % PAGE_SIZE;
if (wlen == 0)
dump_stack();
WARN_ON(wlen == 0);
iov_iter_bvec(&iter, WRITE, &bv, 1, wlen);
ret = wait_for_direct_io(ORANGEFS_IO_WRITE, inode, &off, &iter, wlen,
len);
len, wr);
if (ret < 0) {
SetPageError(page);
mapping_set_error(page->mapping, ret);
} else {
ret = 0;
}
if (wr) {
kfree(wr);
set_page_private(page, 0);
ClearPagePrivate(page);
put_page(page);
}
return ret;
}
static int orangefs_writepage(struct page *page, struct writeback_control *wbc)
{
int ret;
ret = orangefs_writepage_locked(page, wbc);
unlock_page(page);
end_page_writeback(page);
return ret;
@ -74,7 +94,7 @@ static int orangefs_readpage(struct file *file, struct page *page)
iov_iter_bvec(&iter, READ, &bv, 1, PAGE_SIZE);
ret = wait_for_direct_io(ORANGEFS_IO_READ, inode, &off, &iter,
PAGE_SIZE, inode->i_size);
PAGE_SIZE, inode->i_size, NULL);
/* this will only zero remaining unread portions of the page data */
iov_iter_zero(~0U, &iter);
/* takes care of potential aliasing */
@ -92,6 +112,73 @@ static int orangefs_readpage(struct file *file, struct page *page)
return ret;
}
static int orangefs_launder_page(struct page *);
static int orangefs_write_begin(struct file *file,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags, struct page **pagep,
void **fsdata)
{
struct orangefs_write_range *wr;
struct page *page;
pgoff_t index;
int ret;
index = pos >> PAGE_SHIFT;
page = grab_cache_page_write_begin(mapping, index, flags);
if (!page)
return -ENOMEM;
*pagep = page;
if (PageDirty(page) && !PagePrivate(page)) {
/*
* Should be impossible. If it happens, launder the page
* since we don't know what's dirty. This will WARN in
* orangefs_writepage_locked.
*/
ret = orangefs_launder_page(page);
if (ret)
return ret;
}
if (PagePrivate(page)) {
struct orangefs_write_range *wr;
wr = (struct orangefs_write_range *)page_private(page);
if (wr->pos + wr->len == pos &&
uid_eq(wr->uid, current_fsuid()) &&
gid_eq(wr->gid, current_fsgid())) {
wr->len += len;
goto okay;
} else {
ret = orangefs_launder_page(page);
if (ret)
return ret;
}
}
wr = kmalloc(sizeof *wr, GFP_KERNEL);
if (!wr)
return -ENOMEM;
wr->pos = pos;
wr->len = len;
wr->uid = current_fsuid();
wr->gid = current_fsgid();
SetPagePrivate(page);
set_page_private(page, (unsigned long)wr);
get_page(page);
okay:
if (!PageUptodate(page) && (len != PAGE_SIZE)) {
unsigned from = pos & (PAGE_SIZE - 1);
zero_user_segments(page, 0, from, from + len, PAGE_SIZE);
}
return 0;
}
static int orangefs_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata)
{
@ -105,24 +192,96 @@ static void orangefs_invalidatepage(struct page *page,
unsigned int offset,
unsigned int length)
{
gossip_debug(GOSSIP_INODE_DEBUG,
"orangefs_invalidatepage called on page %p "
"(offset is %u)\n",
page,
offset);
ClearPageUptodate(page);
ClearPageMappedToDisk(page);
return;
struct orangefs_write_range *wr;
wr = (struct orangefs_write_range *)page_private(page);
if (offset == 0 && length == PAGE_SIZE) {
kfree((struct orangefs_write_range *)page_private(page));
set_page_private(page, 0);
ClearPagePrivate(page);
put_page(page);
/* write range entirely within invalidate range (or equal) */
} else if (page_offset(page) + offset <= wr->pos &&
wr->pos + wr->len <= page_offset(page) + offset + length) {
kfree((struct orangefs_write_range *)page_private(page));
set_page_private(page, 0);
ClearPagePrivate(page);
put_page(page);
/* XXX is this right? only caller in fs */
cancel_dirty_page(page);
/* invalidate range chops off end of write range */
} else if (wr->pos < page_offset(page) + offset &&
wr->pos + wr->len <= page_offset(page) + offset + length &&
page_offset(page) + offset < wr->pos + wr->len) {
size_t x;
x = wr->pos + wr->len - (page_offset(page) + offset);
WARN_ON(x > wr->len);
wr->len -= x;
wr->uid = current_fsuid();
wr->gid = current_fsgid();
/* invalidate range chops off beginning of write range */
} else if (page_offset(page) + offset <= wr->pos &&
page_offset(page) + offset + length < wr->pos + wr->len &&
wr->pos < page_offset(page) + offset + length) {
size_t x;
x = page_offset(page) + offset + length - wr->pos;
WARN_ON(x > wr->len);
wr->pos += x;
wr->len -= x;
wr->uid = current_fsuid();
wr->gid = current_fsgid();
/* invalidate range entirely within write range (punch hole) */
} else if (wr->pos < page_offset(page) + offset &&
page_offset(page) + offset + length < wr->pos + wr->len) {
/* XXX what do we do here... should not WARN_ON */
WARN_ON(1);
/* punch hole */
/*
* should we just ignore this and write it out anyway?
* it hardly makes sense
*/
/* non-overlapping ranges */
} else {
/* WARN if they do overlap */
if (!((page_offset(page) + offset + length <= wr->pos) ^
(wr->pos + wr->len <= page_offset(page) + offset))) {
WARN_ON(1);
printk("invalidate range offset %llu length %u\n",
page_offset(page) + offset, length);
printk("write range offset %llu length %zu\n",
wr->pos, wr->len);
}
}
}
static int orangefs_releasepage(struct page *page, gfp_t foo)
{
gossip_debug(GOSSIP_INODE_DEBUG,
"orangefs_releasepage called on page %p\n",
page);
return 0;
return !PagePrivate(page);
}
static void orangefs_freepage(struct page *page)
{
if (PagePrivate(page)) {
kfree((struct orangefs_write_range *)page_private(page));
set_page_private(page, 0);
ClearPagePrivate(page);
put_page(page);
}
}
static int orangefs_launder_page(struct page *page)
{
int r = 0;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = 0,
};
wait_on_page_writeback(page);
if (clear_page_dirty_for_io(page)) {
r = orangefs_writepage_locked(page, &wbc);
end_page_writeback(page);
}
return r;
}
static ssize_t orangefs_direct_IO(struct kiocb *iocb,
@ -145,7 +304,6 @@ static ssize_t orangefs_direct_IO(struct kiocb *iocb,
struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
struct orangefs_khandle *handle = &orangefs_inode->refn.khandle;
size_t count = iov_iter_count(iter);
size_t ORIGINALcount = iov_iter_count(iter);
ssize_t total_count = 0;
ssize_t ret = -EINVAL;
int i = 0;
@ -192,7 +350,7 @@ static ssize_t orangefs_direct_IO(struct kiocb *iocb,
(int)*offset);
ret = wait_for_direct_io(type, inode, offset, iter,
each_count, 0);
each_count, 0, NULL);
gossip_debug(GOSSIP_FILE_DEBUG,
"%s(%pU): return from wait_for_io:%d\n",
__func__,
@ -247,13 +405,82 @@ static const struct address_space_operations orangefs_address_operations = {
.writepage = orangefs_writepage,
.readpage = orangefs_readpage,
.set_page_dirty = __set_page_dirty_nobuffers,
.write_begin = simple_write_begin,
.write_begin = orangefs_write_begin,
.write_end = orangefs_write_end,
.invalidatepage = orangefs_invalidatepage,
.releasepage = orangefs_releasepage,
.freepage = orangefs_freepage,
.launder_page = orangefs_launder_page,
.direct_IO = orangefs_direct_IO,
};
vm_fault_t orangefs_page_mkwrite(struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct inode *inode = file_inode(vmf->vma->vm_file);
vm_fault_t ret = VM_FAULT_LOCKED;
struct orangefs_write_range *wr;
lock_page(page);
if (PageDirty(page) && !PagePrivate(page)) {
/*
* Should be impossible. If it happens, launder the page
* since we don't know what's dirty. This will WARN in
* orangefs_writepage_locked.
*/
if (orangefs_launder_page(page)) {
ret = VM_FAULT_RETRY;
goto out;
}
}
if (PagePrivate(page)) {
wr = (struct orangefs_write_range *)page_private(page);
if (uid_eq(wr->uid, current_fsuid()) &&
gid_eq(wr->gid, current_fsgid())) {
wr->pos = page_offset(page);
wr->len = PAGE_SIZE;
goto okay;
} else {
if (orangefs_launder_page(page)) {
ret = VM_FAULT_RETRY;
goto out;
}
}
}
wr = kmalloc(sizeof *wr, GFP_KERNEL);
if (!wr) {
ret = VM_FAULT_RETRY;
goto out;
}
wr->pos = page_offset(page);
wr->len = PAGE_SIZE;
wr->uid = current_fsuid();
wr->gid = current_fsgid();
SetPagePrivate(page);
set_page_private(page, (unsigned long)wr);
get_page(page);
okay:
sb_start_pagefault(inode->i_sb);
file_update_time(vmf->vma->vm_file);
if (page->mapping != inode->i_mapping) {
unlock_page(page);
ret = VM_FAULT_NOPAGE;
goto out;
}
/*
* We mark the page dirty already here so that when freeze is in
* progress, we are guaranteed that writeback during freezing will
* see the dirty page and writeprotect it again.
*/
set_page_dirty(page);
wait_for_stable_page(page);
out:
sb_end_pagefault(inode->i_sb);
return ret;
}
static int orangefs_setattr_size(struct inode *inode, struct iattr *iattr)
{
struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);

10
fs/orangefs/orangefs-kernel.h
View File

@ -230,6 +230,13 @@ struct orangefs_cached_xattr {
unsigned long timeout;
};
struct orangefs_write_range {
loff_t pos;
size_t len;
kuid_t uid;
kgid_t gid;
};
extern struct orangefs_stats orangefs_stats;
/*
@ -342,6 +349,7 @@ void fsid_key_table_finalize(void);
/*
* defined in inode.c
*/
vm_fault_t orangefs_page_mkwrite(struct vm_fault *);
struct inode *orangefs_new_inode(struct super_block *sb,
struct inode *dir,
int mode,
@ -383,7 +391,7 @@ bool __is_daemon_in_service(void);
* defined in file.c
*/
ssize_t wait_for_direct_io(enum ORANGEFS_io_type, struct inode *, loff_t *,
struct iov_iter *, size_t, loff_t);
struct iov_iter *, size_t, loff_t, struct orangefs_write_range *);
ssize_t do_readv_writev(enum ORANGEFS_io_type, struct file *, loff_t *,
struct iov_iter *);