aboutsummaryrefslogtreecommitdiff
path: root/fs/xfs/linux-2.6
diff options
context:
space:
mode:
Diffstat (limited to 'fs/xfs/linux-2.6')
-rw-r--r--fs/xfs/linux-2.6/xfs_acl.c2
-rw-r--r--fs/xfs/linux-2.6/xfs_aops.c611
-rw-r--r--fs/xfs/linux-2.6/xfs_aops.h4
-rw-r--r--fs/xfs/linux-2.6/xfs_buf.c67
-rw-r--r--fs/xfs/linux-2.6/xfs_buf.h119
-rw-r--r--fs/xfs/linux-2.6/xfs_dmapi_priv.h28
-rw-r--r--fs/xfs/linux-2.6/xfs_export.c15
-rw-r--r--fs/xfs/linux-2.6/xfs_file.c104
-rw-r--r--fs/xfs/linux-2.6/xfs_fs_subr.c4
-rw-r--r--fs/xfs/linux-2.6/xfs_fs_subr.h25
-rw-r--r--fs/xfs/linux-2.6/xfs_ioctl.c34
-rw-r--r--fs/xfs/linux-2.6/xfs_ioctl32.c21
-rw-r--r--fs/xfs/linux-2.6/xfs_iops.c10
-rw-r--r--fs/xfs/linux-2.6/xfs_linux.h1
-rw-r--r--fs/xfs/linux-2.6/xfs_quotaops.c1
-rw-r--r--fs/xfs/linux-2.6/xfs_super.c173
-rw-r--r--fs/xfs/linux-2.6/xfs_super.h7
-rw-r--r--fs/xfs/linux-2.6/xfs_sync.c179
-rw-r--r--fs/xfs/linux-2.6/xfs_sync.h5
-rw-r--r--fs/xfs/linux-2.6/xfs_trace.c4
-rw-r--r--fs/xfs/linux-2.6/xfs_trace.h131
21 files changed, 579 insertions, 966 deletions
diff --git a/fs/xfs/linux-2.6/xfs_acl.c b/fs/xfs/linux-2.6/xfs_acl.c
index 9f769b5b38f..b2771862fd3 100644
--- a/fs/xfs/linux-2.6/xfs_acl.c
+++ b/fs/xfs/linux-2.6/xfs_acl.c
@@ -225,7 +225,7 @@ xfs_check_acl(struct inode *inode, int mask)
struct posix_acl *acl;
int error = -EAGAIN;
- xfs_itrace_entry(ip);
+ trace_xfs_check_acl(ip);
/*
* If there is no attribute fork no ACL exists on this inode and
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 34640d6dbdc..d24e78f32f3 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -21,19 +21,12 @@
#include "xfs_inum.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
-#include "xfs_dir2.h"
#include "xfs_trans.h"
-#include "xfs_dmapi.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dir2_sf.h"
-#include "xfs_attr_sf.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_alloc.h"
-#include "xfs_btree.h"
#include "xfs_error.h"
#include "xfs_rw.h"
#include "xfs_iomap.h"
@@ -92,18 +85,15 @@ void
xfs_count_page_state(
struct page *page,
int *delalloc,
- int *unmapped,
int *unwritten)
{
struct buffer_head *bh, *head;
- *delalloc = *unmapped = *unwritten = 0;
+ *delalloc = *unwritten = 0;
bh = head = page_buffers(page);
do {
- if (buffer_uptodate(bh) && !buffer_mapped(bh))
- (*unmapped) = 1;
- else if (buffer_unwritten(bh))
+ if (buffer_unwritten(bh))
(*unwritten) = 1;
else if (buffer_delay(bh))
(*delalloc) = 1;
@@ -212,23 +202,17 @@ xfs_setfilesize(
}
/*
- * Schedule IO completion handling on a xfsdatad if this was
- * the final hold on this ioend. If we are asked to wait,
- * flush the workqueue.
+ * Schedule IO completion handling on the final put of an ioend.
*/
STATIC void
xfs_finish_ioend(
- xfs_ioend_t *ioend,
- int wait)
+ struct xfs_ioend *ioend)
{
if (atomic_dec_and_test(&ioend->io_remaining)) {
- struct workqueue_struct *wq;
-
- wq = (ioend->io_type == IO_UNWRITTEN) ?
- xfsconvertd_workqueue : xfsdatad_workqueue;
- queue_work(wq, &ioend->io_work);
- if (wait)
- flush_workqueue(wq);
+ if (ioend->io_type == IO_UNWRITTEN)
+ queue_work(xfsconvertd_workqueue, &ioend->io_work);
+ else
+ queue_work(xfsdatad_workqueue, &ioend->io_work);
}
}
@@ -272,11 +256,25 @@ xfs_end_io(
*/
if (error == EAGAIN) {
atomic_inc(&ioend->io_remaining);
- xfs_finish_ioend(ioend, 0);
+ xfs_finish_ioend(ioend);
/* ensure we don't spin on blocked ioends */
delay(1);
- } else
+ } else {
+ if (ioend->io_iocb)
+ aio_complete(ioend->io_iocb, ioend->io_result, 0);
xfs_destroy_ioend(ioend);
+ }
+}
+
+/*
+ * Call IO completion handling in caller context on the final put of an ioend.
+ */
+STATIC void
+xfs_finish_ioend_sync(
+ struct xfs_ioend *ioend)
+{
+ if (atomic_dec_and_test(&ioend->io_remaining))
+ xfs_end_io(&ioend->io_work);
}
/*
@@ -309,6 +307,8 @@ xfs_alloc_ioend(
atomic_inc(&XFS_I(ioend->io_inode)->i_iocount);
ioend->io_offset = 0;
ioend->io_size = 0;
+ ioend->io_iocb = NULL;
+ ioend->io_result = 0;
INIT_WORK(&ioend->io_work, xfs_end_io);
return ioend;
@@ -358,7 +358,7 @@ xfs_end_bio(
bio->bi_end_io = NULL;
bio_put(bio);
- xfs_finish_ioend(ioend, 0);
+ xfs_finish_ioend(ioend);
}
STATIC void
@@ -500,7 +500,7 @@ xfs_submit_ioend(
}
if (bio)
xfs_submit_ioend_bio(wbc, ioend, bio);
- xfs_finish_ioend(ioend, 0);
+ xfs_finish_ioend(ioend);
} while ((ioend = next) != NULL);
}
@@ -614,31 +614,30 @@ xfs_map_at_offset(
STATIC unsigned int
xfs_probe_page(
struct page *page,
- unsigned int pg_offset,
- int mapped)
+ unsigned int pg_offset)
{
+ struct buffer_head *bh, *head;
int ret = 0;
if (PageWriteback(page))
return 0;
+ if (!PageDirty(page))
+ return 0;
+ if (!page->mapping)
+ return 0;
+ if (!page_has_buffers(page))
+ return 0;
- if (page->mapping && PageDirty(page)) {
- if (page_has_buffers(page)) {
- struct buffer_head *bh, *head;
-
- bh = head = page_buffers(page);
- do {
- if (!buffer_uptodate(bh))
- break;
- if (mapped != buffer_mapped(bh))
- break;
- ret += bh->b_size;
- if (ret >= pg_offset)
- break;
- } while ((bh = bh->b_this_page) != head);
- } else
- ret = mapped ? 0 : PAGE_CACHE_SIZE;
- }
+ bh = head = page_buffers(page);
+ do {
+ if (!buffer_uptodate(bh))
+ break;
+ if (!buffer_mapped(bh))
+ break;
+ ret += bh->b_size;
+ if (ret >= pg_offset)
+ break;
+ } while ((bh = bh->b_this_page) != head);
return ret;
}
@@ -648,8 +647,7 @@ xfs_probe_cluster(
struct inode *inode,
struct page *startpage,
struct buffer_head *bh,
- struct buffer_head *head,
- int mapped)
+ struct buffer_head *head)
{
struct pagevec pvec;
pgoff_t tindex, tlast, tloff;
@@ -658,7 +656,7 @@ xfs_probe_cluster(
/* First sum forwards in this page */
do {
- if (!buffer_uptodate(bh) || (mapped != buffer_mapped(bh)))
+ if (!buffer_uptodate(bh) || !buffer_mapped(bh))
return total;
total += bh->b_size;
} while ((bh = bh->b_this_page) != head);
@@ -692,7 +690,7 @@ xfs_probe_cluster(
pg_offset = PAGE_CACHE_SIZE;
if (page->index == tindex && trylock_page(page)) {
- pg_len = xfs_probe_page(page, pg_offset, mapped);
+ pg_len = xfs_probe_page(page, pg_offset);
unlock_page(page);
}
@@ -761,7 +759,6 @@ xfs_convert_page(
struct xfs_bmbt_irec *imap,
xfs_ioend_t **ioendp,
struct writeback_control *wbc,
- int startio,
int all_bh)
{
struct buffer_head *bh, *head;
@@ -832,19 +829,14 @@ xfs_convert_page(
ASSERT(imap->br_startblock != DELAYSTARTBLOCK);
xfs_map_at_offset(inode, bh, imap, offset);
- if (startio) {
- xfs_add_to_ioend(inode, bh, offset,
- type, ioendp, done);
- } else {
- set_buffer_dirty(bh);
- unlock_buffer(bh);
- mark_buffer_dirty(bh);
- }
+ xfs_add_to_ioend(inode, bh, offset, type,
+ ioendp, done);
+
page_dirty--;
count++;
} else {
type = IO_NEW;
- if (buffer_mapped(bh) && all_bh && startio) {
+ if (buffer_mapped(bh) && all_bh) {
lock_buffer(bh);
xfs_add_to_ioend(inode, bh, offset,
type, ioendp, done);
@@ -859,14 +851,12 @@ xfs_convert_page(
if (uptodate && bh == head)
SetPageUptodate(page);
- if (startio) {
- if (count) {
- wbc->nr_to_write--;
- if (wbc->nr_to_write <= 0)
- done = 1;
- }
- xfs_start_page_writeback(page, !page_dirty, count);
+ if (count) {
+ wbc->nr_to_write--;
+ if (wbc->nr_to_write <= 0)
+ done = 1;
}
+ xfs_start_page_writeback(page, !page_dirty, count);
return done;
fail_unlock_page:
@@ -886,7 +876,6 @@ xfs_cluster_write(
struct xfs_bmbt_irec *imap,
xfs_ioend_t **ioendp,
struct writeback_control *wbc,
- int startio,
int all_bh,
pgoff_t tlast)
{
@@ -902,7 +891,7 @@ xfs_cluster_write(
for (i = 0; i < pagevec_count(&pvec); i++) {
done = xfs_convert_page(inode, pvec.pages[i], tindex++,
- imap, ioendp, wbc, startio, all_bh);
+ imap, ioendp, wbc, all_bh);
if (done)
break;
}
@@ -981,7 +970,7 @@ xfs_aops_discard_page(
*/
error = xfs_bmapi(NULL, ip, offset_fsb, 1,
XFS_BMAPI_ENTIRE, NULL, 0, &imap,
- &nimaps, NULL, NULL);
+ &nimaps, NULL);
if (error) {
/* something screwed, just bail */
@@ -1009,7 +998,7 @@ xfs_aops_discard_page(
*/
xfs_bmap_init(&flist, &firstblock);
error = xfs_bunmapi(NULL, ip, offset_fsb, 1, 0, 1, &firstblock,
- &flist, NULL, &done);
+ &flist, &done);
ASSERT(!flist.xbf_count && !flist.xbf_first);
if (error) {
@@ -1032,50 +1021,66 @@ out_invalidate:
}
/*
- * Calling this without startio set means we are being asked to make a dirty
- * page ready for freeing it's buffers. When called with startio set then
- * we are coming from writepage.
+ * Write out a dirty page.
+ *
+ * For delalloc space on the page we need to allocate space and flush it.
+ * For unwritten space on the page we need to start the conversion to
+ * regular allocated space.
+ * For any other dirty buffer heads on the page we should flush them.
*
- * When called with startio set it is important that we write the WHOLE
- * page if possible.
- * The bh->b_state's cannot know if any of the blocks or which block for
- * that matter are dirty due to mmap writes, and therefore bh uptodate is
- * only valid if the page itself isn't completely uptodate. Some layers
- * may clear the page dirty flag prior to calling write page, under the
- * assumption the entire page will be written out; by not writing out the
- * whole page the page can be reused before all valid dirty data is
- * written out. Note: in the case of a page that has been dirty'd by
- * mapwrite and but partially setup by block_prepare_write the
- * bh->b_states's will not agree and only ones setup by BPW/BCW will have
- * valid state, thus the whole page must be written out thing.
+ * If we detect that a transaction would be required to flush the page, we
+ * have to check the process flags first, if we are already in a transaction
+ * or disk I/O during allocations is off, we need to fail the writepage and
+ * redirty the page.
*/
-
STATIC int
-xfs_page_state_convert(
- struct inode *inode,
- struct page *page,
- struct writeback_control *wbc,
- int startio,
- int unmapped) /* also implies page uptodate */
+xfs_vm_writepage(
+ struct page *page,
+ struct writeback_control *wbc)
{
+ struct inode *inode = page->mapping->host;
+ int delalloc, unwritten;
struct buffer_head *bh, *head;
struct xfs_bmbt_irec imap;
xfs_ioend_t *ioend = NULL, *iohead = NULL;
loff_t offset;
- unsigned long p_offset = 0;
unsigned int type;
__uint64_t end_offset;
pgoff_t end_index, last_index;
ssize_t size, len;
int flags, err, imap_valid = 0, uptodate = 1;
- int page_dirty, count = 0;
- int trylock = 0;
- int all_bh = unmapped;
+ int count = 0;
+ int all_bh = 0;
- if (startio) {
- if (wbc->sync_mode == WB_SYNC_NONE && wbc->nonblocking)
- trylock |= BMAPI_TRYLOCK;
- }
+ trace_xfs_writepage(inode, page, 0);
+
+ ASSERT(page_has_buffers(page));
+
+ /*
+ * Refuse to write the page out if we are called from reclaim context.
+ *
+ * This avoids stack overflows when called from deeply used stacks in
+ * random callers for direct reclaim or memcg reclaim. We explicitly
+ * allow reclaim from kswapd as the stack usage there is relatively low.
+ *
+ * This should really be done by the core VM, but until that happens
+ * filesystems like XFS, btrfs and ext4 have to take care of this
+ * by themselves.
+ */
+ if ((current->flags & (PF_MEMALLOC|PF_KSWAPD)) == PF_MEMALLOC)
+ goto out_fail;
+
+ /*
+ * We need a transaction if there are delalloc or unwritten buffers
+ * on the page.
+ *
+ * If we need a transaction and the process flags say we are already
+ * in a transaction, or no IO is allowed then mark the page dirty
+ * again and leave the page as is.
+ */
+ xfs_count_page_state(page, &delalloc, &unwritten);
+ if ((current->flags & PF_FSTRANS) && (delalloc || unwritten))
+ goto out_fail;
/* Is this page beyond the end of the file? */
offset = i_size_read(inode);
@@ -1084,50 +1089,33 @@ xfs_page_state_convert(
if (page->index >= end_index) {
if ((page->index >= end_index + 1) ||
!(i_size_read(inode) & (PAGE_CACHE_SIZE - 1))) {
- if (startio)
- unlock_page(page);
+ unlock_page(page);
return 0;
}
}
- /*
- * page_dirty is initially a count of buffers on the page before
- * EOF and is decremented as we move each into a cleanable state.
- *
- * Derivation:
- *
- * End offset is the highest offset that this page should represent.
- * If we are on the last page, (end_offset & (PAGE_CACHE_SIZE - 1))
- * will evaluate non-zero and be less than PAGE_CACHE_SIZE and
- * hence give us the correct page_dirty count. On any other page,
- * it will be zero and in that case we need page_dirty to be the
- * count of buffers on the page.
- */
end_offset = min_t(unsigned long long,
- (xfs_off_t)(page->index + 1) << PAGE_CACHE_SHIFT, offset);
+ (xfs_off_t)(page->index + 1) << PAGE_CACHE_SHIFT,
+ offset);
len = 1 << inode->i_blkbits;
- p_offset = min_t(unsigned long, end_offset & (PAGE_CACHE_SIZE - 1),
- PAGE_CACHE_SIZE);
- p_offset = p_offset ? roundup(p_offset, len) : PAGE_CACHE_SIZE;
- page_dirty = p_offset / len;
bh = head = page_buffers(page);
offset = page_offset(page);
flags = BMAPI_READ;
type = IO_NEW;
- /* TODO: cleanup count and page_dirty */
-
do {
if (offset >= end_offset)
break;
if (!buffer_uptodate(bh))
uptodate = 0;
- if (!(PageUptodate(page) || buffer_uptodate(bh)) && !startio) {
- /*
- * the iomap is actually still valid, but the ioend
- * isn't. shouldn't happen too often.
- */
+
+ /*
+ * A hole may still be marked uptodate because discard_buffer
+ * leaves the flag set.
+ */
+ if (!buffer_mapped(bh) && buffer_uptodate(bh)) {
+ ASSERT(!buffer_dirty(bh));
imap_valid = 0;
continue;
}
@@ -1135,19 +1123,7 @@ xfs_page_state_convert(
if (imap_valid)
imap_valid = xfs_imap_valid(inode, &imap, offset);
- /*
- * First case, map an unwritten extent and prepare for
- * extent state conversion transaction on completion.
- *
- * Second case, allocate space for a delalloc buffer.
- * We can return EAGAIN here in the release page case.
- *
- * Third case, an unmapped buffer was found, and we are
- * in a path where we need to write the whole page out.
- */
- if (buffer_unwritten(bh) || buffer_delay(bh) ||
- ((buffer_uptodate(bh) || PageUptodate(page)) &&
- !buffer_mapped(bh) && (unmapped || startio))) {
+ if (buffer_unwritten(bh) || buffer_delay(bh)) {
int new_ioend = 0;
/*
@@ -1161,15 +1137,16 @@ xfs_page_state_convert(
flags = BMAPI_WRITE | BMAPI_IGNSTATE;
} else if (buffer_delay(bh)) {
type = IO_DELAY;
- flags = BMAPI_ALLOCATE | trylock;
- } else {
- type = IO_NEW;
- flags = BMAPI_WRITE | BMAPI_MMAP;
+ flags = BMAPI_ALLOCATE;
+
+ if (wbc->sync_mode == WB_SYNC_NONE &&
+ wbc->nonblocking)
+ flags |= BMAPI_TRYLOCK;
}
if (!imap_valid) {
/*
- * if we didn't have a valid mapping then we
+ * If we didn't have a valid mapping then we
* need to ensure that we put the new mapping
* in a new ioend structure. This needs to be
* done to ensure that the ioends correctly
@@ -1177,14 +1154,7 @@ xfs_page_state_convert(
* for unwritten extent conversion.
*/
new_ioend = 1;
- if (type == IO_NEW) {
- size = xfs_probe_cluster(inode,
- page, bh, head, 0);
- } else {
- size = len;
- }
-
- err = xfs_map_blocks(inode, offset, size,
+ err = xfs_map_blocks(inode, offset, len,
&imap, flags);
if (err)
goto error;
@@ -1193,19 +1163,11 @@ xfs_page_state_convert(
}
if (imap_valid) {
xfs_map_at_offset(inode, bh, &imap, offset);
- if (startio) {
- xfs_add_to_ioend(inode, bh, offset,
- type, &ioend,
- new_ioend);
- } else {
- set_buffer_dirty(bh);
- unlock_buffer(bh);
- mark_buffer_dirty(bh);
- }
- page_dirty--;
+ xfs_add_to_ioend(inode, bh, offset, type,
+ &ioend, new_ioend);
count++;
}
- } else if (buffer_uptodate(bh) && startio) {
+ } else if (buffer_uptodate(bh)) {
/*
* we got here because the buffer is already mapped.
* That means it must already have extents allocated
@@ -1213,8 +1175,7 @@ xfs_page_state_convert(
*/
if (!imap_valid || flags != BMAPI_READ) {
flags = BMAPI_READ;
- size = xfs_probe_cluster(inode, page, bh,
- head, 1);
+ size = xfs_probe_cluster(inode, page, bh, head);
err = xfs_map_blocks(inode, offset, size,
&imap, flags);
if (err)
@@ -1233,18 +1194,16 @@ xfs_page_state_convert(
*/
type = IO_NEW;
if (trylock_buffer(bh)) {
- ASSERT(buffer_mapped(bh));
if (imap_valid)
all_bh = 1;
xfs_add_to_ioend(inode, bh, offset, type,
&ioend, !imap_valid);
- page_dirty--;
count++;
} else {
imap_valid = 0;
}
- } else if ((buffer_uptodate(bh) || PageUptodate(page)) &&
- (unmapped || startio)) {
+ } else if (PageUptodate(page)) {
+ ASSERT(buffer_mapped(bh));
imap_valid = 0;
}
@@ -1256,8 +1215,7 @@ xfs_page_state_convert(
if (uptodate && bh == head)
SetPageUptodate(page);
- if (startio)
- xfs_start_page_writeback(page, 1, count);
+ xfs_start_page_writeback(page, 1, count);
if (ioend && imap_valid) {
xfs_off_t end_index;
@@ -1275,131 +1233,27 @@ xfs_page_state_convert(
end_index = last_index;
xfs_cluster_write(inode, page->index + 1, &imap, &ioend,
- wbc, startio, all_bh, end_index);
+ wbc, all_bh, end_index);
}
if (iohead)
xfs_submit_ioend(wbc, iohead);
- return page_dirty;
+ return 0;
error:
if (iohead)
xfs_cancel_ioend(iohead);
- /*
- * If it's delalloc and we have nowhere to put it,
- * throw it away, unless the lower layers told
- * us to try again.
- */
- if (err != -EAGAIN) {
- if (!unmapped)
- xfs_aops_discard_page(page);
- ClearPageUptodate(page);
- }
+ xfs_aops_discard_page(page);
+ ClearPageUptodate(page);
+ unlock_page(page);
return err;
-}
-
-/*
- * writepage: Called from one of two places:
- *
- * 1. we are flushing a delalloc buffer head.
- *
- * 2. we are writing out a dirty page. Typically the page dirty
- * state is cleared before we get here. In this case is it
- * conceivable we have no buffer heads.
- *
- * For delalloc space on the page we need to allocate space and
- * flush it. For unmapped buffer heads on the page we should
- * allocate space if the page is uptodate. For any other dirty
- * buffer heads on the page we should flush them.
- *
- * If we detect that a transaction would be required to flush
- * the page, we have to check the process flags first, if we
- * are already in a transaction or disk I/O during allocations
- * is off, we need to fail the writepage and redirty the page.
- */
-
-STATIC int
-xfs_vm_writepage(
- struct page *page,
- struct writeback_control *wbc)
-{
- int error;
- int need_trans;
- int delalloc, unmapped, unwritten;
- struct inode *inode = page->mapping->host;
-
- trace_xfs_writepage(inode, page, 0);
-
- /*
- * Refuse to write the page out if we are called from reclaim context.
- *
- * This is primarily to avoid stack overflows when called from deep
- * used stacks in random callers for direct reclaim, but disabling
- * reclaim for kswap is a nice side-effect as kswapd causes rather
- * suboptimal I/O patters, too.
- *
- * This should really be done by the core VM, but until that happens
- * filesystems like XFS, btrfs and ext4 have to take care of this
- * by themselves.
- */
- if (current->flags & PF_MEMALLOC)
- goto out_fail;
-
- /*
- * We need a transaction if:
- * 1. There are delalloc buffers on the page
- * 2. The page is uptodate and we have unmapped buffers
- * 3. The page is uptodate and we have no buffers
- * 4. There are unwritten buffers on the page
- */
-
- if (!page_has_buffers(page)) {
- unmapped = 1;
- need_trans = 1;
- } else {
- xfs_count_page_state(page, &delalloc, &unmapped, &unwritten);
- if (!PageUptodate(page))
- unmapped = 0;
- need_trans = delalloc + unmapped + unwritten;
- }
-
- /*
- * If we need a transaction and the process flags say
- * we are already in a transaction, or no IO is allowed
- * then mark the page dirty again and leave the page
- * as is.
- */
- if (current_test_flags(PF_FSTRANS) && need_trans)
- goto out_fail;
-
- /*
- * Delay hooking up buffer heads until we have
- * made our go/no-go decision.
- */
- if (!page_has_buffers(page))
- create_empty_buffers(page, 1 << inode->i_blkbits, 0);
-
- /*
- * Convert delayed allocate, unwritten or unmapped space
- * to real space and flush out to disk.
- */
- error = xfs_page_state_convert(inode, page, wbc, 1, unmapped);
- if (error == -EAGAIN)
- goto out_fail;
- if (unlikely(error < 0))
- goto out_unlock;
-
- return 0;
out_fail:
redirty_page_for_writepage(wbc, page);
unlock_page(page);
return 0;
-out_unlock:
- unlock_page(page);
- return error;
}
STATIC int
@@ -1413,65 +1267,27 @@ xfs_vm_writepages(
/*
* Called to move a page into cleanable state - and from there
- * to be released. Possibly the page is already clean. We always
+ * to be released. The page should already be clean. We always
* have buffer heads in this call.
*
- * Returns 0 if the page is ok to release, 1 otherwise.
- *
- * Possible scenarios are:
- *
- * 1. We are being called to release a page which has been written
- * to via regular I/O. buffer heads will be dirty and possibly
- * delalloc. If no delalloc buffer heads in this case then we
- * can just return zero.
- *
- * 2. We are called to release a page which has been written via
- * mmap, all we need to do is ensure there is no delalloc
- * state in the buffer heads, if not we can let the caller
- * free them and we should come back later via writepage.
+ * Returns 1 if the page is ok to release, 0 otherwise.
*/
STATIC int
xfs_vm_releasepage(
struct page *page,
gfp_t gfp_mask)
{
- struct inode *inode = page->mapping->host;
- int dirty, delalloc, unmapped, unwritten;
- struct writeback_control wbc = {
- .sync_mode = WB_SYNC_ALL,
- .nr_to_write = 1,
- };
+ int delalloc, unwritten;
- trace_xfs_releasepage(inode, page, 0);
-
- if (!page_has_buffers(page))
- return 0;
+ trace_xfs_releasepage(page->mapping->host, page, 0);
- xfs_count_page_state(page, &delalloc, &unmapped, &unwritten);
- if (!delalloc && !unwritten)
- goto free_buffers;
+ xfs_count_page_state(page, &delalloc, &unwritten);
- if (!(gfp_mask & __GFP_FS))
+ if (WARN_ON(delalloc))
return 0;
-
- /* If we are already inside a transaction or the thread cannot
- * do I/O, we cannot release this page.
- */
- if (current_test_flags(PF_FSTRANS))
+ if (WARN_ON(unwritten))
return 0;
- /*
- * Convert delalloc space to real space, do not flush the
- * data out to disk, that will be done by the caller.
- * Never need to allocate space here - we will always
- * come back to writepage in that case.
- */
- dirty = xfs_page_state_convert(inode, page, &wbc, 0, 0);
- if (dirty == 0 && !unwritten)
- goto free_buffers;
- return 0;
-
-free_buffers:
return try_to_free_buffers(page);
}
@@ -1481,9 +1297,9 @@ __xfs_get_blocks(
sector_t iblock,
struct buffer_head *bh_result,
int create,
- int direct,
- bmapi_flags_t flags)
+ int direct)
{
+ int flags = create ? BMAPI_WRITE : BMAPI_READ;
struct xfs_bmbt_irec imap;
xfs_off_t offset;
ssize_t size;
@@ -1498,8 +1314,11 @@ __xfs_get_blocks(
if (!create && direct && offset >= i_size_read(inode))
return 0;
- error = xfs_iomap(XFS_I(inode), offset, size,
- create ? flags : BMAPI_READ, &imap, &nimap, &new);
+ if (direct && create)
+ flags |= BMAPI_DIRECT;
+
+ error = xfs_iomap(XFS_I(inode), offset, size, flags, &imap, &nimap,
+ &new);
if (error)
return -error;
if (nimap == 0)
@@ -1579,8 +1398,7 @@ xfs_get_blocks(
struct buffer_head *bh_result,
int create)
{
- return __xfs_get_blocks(inode, iblock,
- bh_result, create, 0, BMAPI_WRITE);
+ return __xfs_get_blocks(inode, iblock, bh_result, create, 0);
}
STATIC int
@@ -1590,61 +1408,59 @@ xfs_get_blocks_direct(
struct buffer_head *bh_result,
int create)
{
- return __xfs_get_blocks(inode, iblock,
- bh_result, create, 1, BMAPI_WRITE|BMAPI_DIRECT);
+ return __xfs_get_blocks(inode, iblock, bh_result, create, 1);
}
+/*
+ * Complete a direct I/O write request.
+ *
+ * If the private argument is non-NULL __xfs_get_blocks signals us that we
+ * need to issue a transaction to convert the range from unwritten to written
+ * extents. In case this is regular synchronous I/O we just call xfs_end_io
+ * to do this and we are done. But in case this was a successfull AIO
+ * request this handler is called from interrupt context, from which we
+ * can't start transactions. In that case offload the I/O completion to
+ * the workqueues we also use for buffered I/O completion.
+ */
STATIC void
-xfs_end_io_direct(
- struct kiocb *iocb,
- loff_t offset,
- ssize_t size,
- void *private)
+xfs_end_io_direct_write(
+ struct kiocb *iocb,
+ loff_t offset,
+ ssize_t size,
+ void *private,
+ int ret,
+ bool is_async)
{
- xfs_ioend_t *ioend = iocb->private;
+ struct xfs_ioend *ioend = iocb->private;
/*
- * Non-NULL private data means we need to issue a transaction to
- * convert a range from unwritten to written extents. This needs
- * to happen from process context but aio+dio I/O completion
- * happens from irq context so we need to defer it to a workqueue.
- * This is not necessary for synchronous direct I/O, but we do
- * it anyway to keep the code uniform and simpler.
- *
- * Well, if only it were that simple. Because synchronous direct I/O
- * requires extent conversion to occur *before* we return to userspace,
- * we have to wait for extent conversion to complete. Look at the
- * iocb that has been passed to us to determine if this is AIO or
- * not. If it is synchronous, tell xfs_finish_ioend() to kick the
- * workqueue and wait for it to complete.
- *
- * The core direct I/O code might be changed to always call the
- * completion handler in the future, in which case all this can
- * go away.
+ * blockdev_direct_IO can return an error even after the I/O
+ * completion handler was called. Thus we need to protect
+ * against double-freeing.
*/
+ iocb->private = NULL;
+
ioend->io_offset = offset;
ioend->io_size = size;
- if (ioend->io_type == IO_READ) {
- xfs_finish_ioend(ioend, 0);
- } else if (private && size > 0) {
- xfs_finish_ioend(ioend, is_sync_kiocb(iocb));
- } else {
+ if (private && size > 0)
+ ioend->io_type = IO_UNWRITTEN;
+
+ if (is_async) {
/*
- * A direct I/O write ioend starts it's life in unwritten
- * state in case they map an unwritten extent. This write
- * didn't map an unwritten extent so switch it's completion
- * handler.
+ * If we are converting an unwritten extent we need to delay
+ * the AIO completion until after the unwrittent extent
+ * conversion has completed, otherwise do it ASAP.
*/
- ioend->io_type = IO_NEW;
- xfs_finish_ioend(ioend, 0);
+ if (ioend->io_type == IO_UNWRITTEN) {
+ ioend->io_iocb = iocb;
+ ioend->io_result = ret;
+ } else {
+ aio_complete(iocb, ret, 0);
+ }
+ xfs_finish_ioend(ioend);
+ } else {
+ xfs_finish_ioend_sync(ioend);
}
-
- /*
- * blockdev_direct_IO can return an error even after the I/O
- * completion handler was called. Thus we need to protect
- * against double-freeing.
- */
- iocb->private = NULL;
}
STATIC ssize_t
@@ -1655,23 +1471,26 @@ xfs_vm_direct_IO(
loff_t offset,
unsigned long nr_segs)
{
- struct file *file = iocb->ki_filp;
- struct inode *inode = file->f_mapping->host;
- struct block_device *bdev;
- ssize_t ret;
-
- bdev = xfs_find_bdev_for_inode(inode);
-
- iocb->private = xfs_alloc_ioend(inode, rw == WRITE ?
- IO_UNWRITTEN : IO_READ);
-
- ret = blockdev_direct_IO_no_locking(rw, iocb, inode, bdev, iov,
- offset, nr_segs,
- xfs_get_blocks_direct,
- xfs_end_io_direct);
+ struct inode *inode = iocb->ki_filp->f_mapping->host;
+ struct block_device *bdev = xfs_find_bdev_for_inode(inode);
+ ssize_t ret;
+
+ if (rw & WRITE) {
+ iocb->private = xfs_alloc_ioend(inode, IO_NEW);
+
+ ret = blockdev_direct_IO_no_locking(rw, iocb, inode, bdev, iov,
+ offset, nr_segs,
+ xfs_get_blocks_direct,
+ xfs_end_io_direct_write);
+ if (ret != -EIOCBQUEUED && iocb->private)
+ xfs_destroy_ioend(iocb->private);
+ } else {
+ ret = blockdev_direct_IO_no_locking(rw, iocb, inode, bdev, iov,
+ offset, nr_segs,
+ xfs_get_blocks_direct,
+ NULL);
+ }
- if (unlikely(ret != -EIOCBQUEUED && iocb->private))
- xfs_destroy_ioend(iocb->private);
return ret;
}
@@ -1686,8 +1505,8 @@ xfs_vm_write_begin(
void **fsdata)
{
*pagep = NULL;
- return block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
- xfs_get_blocks);
+ return block_write_begin(file, mapping, pos, len, flags | AOP_FLAG_NOFS,
+ pagep, fsdata, xfs_get_blocks);
}
STATIC sector_t
@@ -1698,7 +1517,7 @@ xfs_vm_bmap(
struct inode *inode = (struct inode *)mapping->host;
struct xfs_inode *ip = XFS_I(inode);
- xfs_itrace_entry(XFS_I(inode));
+ trace_xfs_vm_bmap(XFS_I(inode));
xfs_ilock(ip, XFS_IOLOCK_SHARED);
xfs_flush_pages(ip, (xfs_off_t)0, -1, 0, FI_REMAPF);
xfs_iunlock(ip, XFS_IOLOCK_SHARED);
diff --git a/fs/xfs/linux-2.6/xfs_aops.h b/fs/xfs/linux-2.6/xfs_aops.h
index 4cfc6ea87df..c5057fb6237 100644
--- a/fs/xfs/linux-2.6/xfs_aops.h
+++ b/fs/xfs/linux-2.6/xfs_aops.h
@@ -37,6 +37,8 @@ typedef struct xfs_ioend {
size_t io_size; /* size of the extent */
xfs_off_t io_offset; /* offset in the file */
struct work_struct io_work; /* xfsdatad work queue */
+ struct kiocb *io_iocb;
+ int io_result;
} xfs_ioend_t;
extern const struct address_space_operations xfs_address_space_operations;
@@ -45,6 +47,6 @@ extern int xfs_get_blocks(struct inode *, sector_t, struct buffer_head *, int);
extern void xfs_ioend_init(void);
extern void xfs_ioend_wait(struct xfs_inode *);
-extern void xfs_count_page_state(struct page *, int *, int *, int *);
+extern void xfs_count_page_state(struct page *, int *, int *);
#endif /* __XFS_AOPS_H__ */
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 649ade8ef59..ea79072f521 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -39,13 +39,12 @@
#include "xfs_inum.h"
#include "xfs_log.h"
#include "xfs_ag.h"
-#include "xfs_dmapi.h"
#include "xfs_mount.h"
#include "xfs_trace.h"
static kmem_zone_t *xfs_buf_zone;
STATIC int xfsbufd(void *);
-STATIC int xfsbufd_wakeup(int, gfp_t);
+STATIC int xfsbufd_wakeup(struct shrinker *, int, gfp_t);
STATIC void xfs_buf_delwri_queue(xfs_buf_t *, int);
static struct shrinker xfs_buf_shake = {
.shrink = xfsbufd_wakeup,
@@ -340,7 +339,7 @@ _xfs_buf_lookup_pages(
__func__, gfp_mask);
XFS_STATS_INC(xb_page_retries);
- xfsbufd_wakeup(0, gfp_mask);
+ xfsbufd_wakeup(NULL, 0, gfp_mask);
congestion_wait(BLK_RW_ASYNC, HZ/50);
goto retry;
}
@@ -579,9 +578,9 @@ _xfs_buf_read(
XBF_READ_AHEAD | _XBF_RUN_QUEUES);
status = xfs_buf_iorequest(bp);
- if (!status && !(flags & XBF_ASYNC))
- status = xfs_buf_iowait(bp);
- return status;
+ if (status || XFS_BUF_ISERROR(bp) || (flags & XBF_ASYNC))
+ return status;
+ return xfs_buf_iowait(bp);
}
xfs_buf_t *
@@ -897,36 +896,6 @@ xfs_buf_unlock(
trace_xfs_buf_unlock(bp, _RET_IP_);
}
-
-/*
- * Pinning Buffer Storage in Memory
- * Ensure that no attempt to force a buffer to disk will succeed.
- */
-void
-xfs_buf_pin(
- xfs_buf_t *bp)
-{
- trace_xfs_buf_pin(bp, _RET_IP_);
- atomic_inc(&bp->b_pin_count);
-}
-
-void
-xfs_buf_unpin(
- xfs_buf_t *bp)
-{
- trace_xfs_buf_unpin(bp, _RET_IP_);
-
- if (atomic_dec_and_test(&bp->b_pin_count))
- wake_up_all(&bp->b_waiters);
-}
-
-int
-xfs_buf_ispin(
- xfs_buf_t *bp)
-{
- return atomic_read(&bp->b_pin_count);
-}
-
STATIC void
xfs_buf_wait_unpin(
xfs_buf_t *bp)
@@ -1018,13 +987,12 @@ xfs_bwrite(
{
int error;
- bp->b_strat = xfs_bdstrat_cb;
bp->b_mount = mp;
bp->b_flags |= XBF_WRITE;
bp->b_flags &= ~(XBF_ASYNC | XBF_READ);
xfs_buf_delwri_dequeue(bp);
- xfs_buf_iostrategy(bp);
+ xfs_bdstrat_cb(bp);
error = xfs_buf_iowait(bp);
if (error)
@@ -1040,7 +1008,6 @@ xfs_bdwrite(
{
trace_xfs_buf_bdwrite(bp, _RET_IP_);
- bp->b_strat = xfs_bdstrat_cb;
bp->b_mount = mp;
bp->b_flags &= ~XBF_READ;
@@ -1075,7 +1042,6 @@ xfs_bioerror(
XFS_BUF_UNDONE(bp);
XFS_BUF_STALE(bp);
- XFS_BUF_CLR_BDSTRAT_FUNC(bp);
xfs_biodone(bp);
return EIO;
@@ -1105,7 +1071,6 @@ xfs_bioerror_relse(
XFS_BUF_DONE(bp);
XFS_BUF_STALE(bp);
XFS_BUF_CLR_IODONE_FUNC(bp);
- XFS_BUF_CLR_BDSTRAT_FUNC(bp);
if (!(fl & XBF_ASYNC)) {
/*
* Mark b_error and B_ERROR _both_.
@@ -1311,8 +1276,19 @@ submit_io:
if (size)
goto next_chunk;
} else {
- bio_put(bio);
+ /*
+ * if we get here, no pages were added to the bio. However,
+ * we can't just error out here - if the pages are locked then
+ * we have to unlock them otherwise we can hang on a later
+ * access to the page.
+ */
xfs_buf_ioerror(bp, EIO);
+ if (bp->b_flags & _XBF_PAGE_LOCKED) {
+ int i;
+ for (i = 0; i < bp->b_page_count; i++)
+ unlock_page(bp->b_pages[i]);
+ }
+ bio_put(bio);
}
}
@@ -1762,6 +1738,7 @@ xfs_buf_runall_queues(
STATIC int
xfsbufd_wakeup(
+ struct shrinker *shrink,
int priority,
gfp_t mask)
{
@@ -1803,7 +1780,7 @@ xfs_buf_delwri_split(
trace_xfs_buf_delwri_split(bp, _RET_IP_);
ASSERT(bp->b_flags & XBF_DELWRI);
- if (!xfs_buf_ispin(bp) && !xfs_buf_cond_lock(bp)) {
+ if (!XFS_BUF_ISPINNED(bp) && !xfs_buf_cond_lock(bp)) {
if (!force &&
time_before(jiffies, bp->b_queuetime + age)) {
xfs_buf_unlock(bp);
@@ -1888,7 +1865,7 @@ xfsbufd(
struct xfs_buf *bp;
bp = list_first_entry(&tmp, struct xfs_buf, b_list);
list_del_init(&bp->b_list);
- xfs_buf_iostrategy(bp);
+ xfs_bdstrat_cb(bp);
count++;
}
if (count)
@@ -1935,7 +1912,7 @@ xfs_flush_buftarg(
bp->b_flags &= ~XBF_ASYNC;
list_add(&bp->b_list, &wait_list);
}
- xfs_buf_iostrategy(bp);
+ xfs_bdstrat_cb(bp);
}
if (wait) {
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index 5fbecefa5df..d072e5ff923 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -44,57 +44,57 @@ typedef enum {
XBRW_ZERO = 3, /* Zero target memory */
} xfs_buf_rw_t;
-typedef enum {
- XBF_READ = (1 << 0), /* buffer intended for reading from device */
- XBF_WRITE = (1 << 1), /* buffer intended for writing to device */
- XBF_MAPPED = (1 << 2), /* buffer mapped (b_addr valid) */
- XBF_ASYNC = (1 << 4), /* initiator will not wait for completion */
- XBF_DONE = (1 << 5), /* all pages in the buffer uptodate */
- XBF_DELWRI = (1 << 6), /* buffer has dirty pages */
- XBF_STALE = (1 << 7), /* buffer has been staled, do not find it */
- XBF_FS_MANAGED = (1 << 8), /* filesystem controls freeing memory */
- XBF_ORDERED = (1 << 11), /* use ordered writes */
- XBF_READ_AHEAD = (1 << 12), /* asynchronous read-ahead */
- XBF_LOG_BUFFER = (1 << 13), /* this is a buffer used for the log */
-
- /* flags used only as arguments to access routines */
- XBF_LOCK = (1 << 14), /* lock requested */
- XBF_TRYLOCK = (1 << 15), /* lock requested, but do not wait */
- XBF_DONT_BLOCK = (1 << 16), /* do not block in current thread */
-
- /* flags used only internally */
- _XBF_PAGE_CACHE = (1 << 17),/* backed by pagecache */
- _XBF_PAGES = (1 << 18), /* backed by refcounted pages */
- _XBF_RUN_QUEUES = (1 << 19),/* run block device task queue */
- _XBF_DELWRI_Q = (1 << 21), /* buffer on delwri queue */
-
- /*
- * Special flag for supporting metadata blocks smaller than a FSB.
- *
- * In this case we can have multiple xfs_buf_t on a single page and
- * need to lock out concurrent xfs_buf_t readers as they only
- * serialise access to the buffer.
- *
- * If the FSB size >= PAGE_CACHE_SIZE case, we have no serialisation
- * between reads of the page. Hence we can have one thread read the
- * page and modify it, but then race with another thread that thinks
- * the page is not up-to-date and hence reads it again.
- *
- * The result is that the first modifcation to the page is lost.
- * This sort of AGF/AGI reading race can happen when unlinking inodes
- * that require truncation and results in the AGI unlinked list
- * modifications being lost.
- */
- _XBF_PAGE_LOCKED = (1 << 22),
-
- /*
- * If we try a barrier write, but it fails we have to communicate
- * this to the upper layers. Unfortunately b_error gets overwritten
- * when the buffer is re-issued so we have to add another flag to
- * keep this information.
- */
- _XFS_BARRIER_FAILED = (1 << 23),
-} xfs_buf_flags_t;
+#define XBF_READ (1 << 0) /* buffer intended for reading from device */
+#define XBF_WRITE (1 << 1) /* buffer intended for writing to device */
+#define XBF_MAPPED (1 << 2) /* buffer mapped (b_addr valid) */
+#define XBF_ASYNC (1 << 4) /* initiator will not wait for completion */
+#define XBF_DONE (1 << 5) /* all pages in the buffer uptodate */
+#define XBF_DELWRI (1 << 6) /* buffer has dirty pages */
+#define XBF_STALE (1 << 7) /* buffer has been staled, do not find it */
+#define XBF_FS_MANAGED (1 << 8) /* filesystem controls freeing memory */
+#define XBF_ORDERED (1 << 11)/* use ordered writes */
+#define XBF_READ_AHEAD (1 << 12)/* asynchronous read-ahead */
+#define XBF_LOG_BUFFER (1 << 13)/* this is a buffer used for the log */
+
+/* flags used only as arguments to access routines */
+#define XBF_LOCK (1 << 14)/* lock requested */
+#define XBF_TRYLOCK (1 << 15)/* lock requested, but do not wait */
+#define XBF_DONT_BLOCK (1 << 16)/* do not block in current thread */
+
+/* flags used only internally */
+#define _XBF_PAGE_CACHE (1 << 17)/* backed by pagecache */
+#define _XBF_PAGES (1 << 18)/* backed by refcounted pages */
+#define _XBF_RUN_QUEUES (1 << 19)/* run block device task queue */
+#define _XBF_DELWRI_Q (1 << 21)/* buffer on delwri queue */
+
+/*
+ * Special flag for supporting metadata blocks smaller than a FSB.
+ *
+ * In this case we can have multiple xfs_buf_t on a single page and
+ * need to lock out concurrent xfs_buf_t readers as they only
+ * serialise access to the buffer.
+ *
+ * If the FSB size >= PAGE_CACHE_SIZE case, we have no serialisation
+ * between reads of the page. Hence we can have one thread read the
+ * page and modify it, but then race with another thread that thinks
+ * the page is not up-to-date and hence reads it again.
+ *
+ * The result is that the first modifcation to the page is lost.
+ * This sort of AGF/AGI reading race can happen when unlinking inodes
+ * that require truncation and results in the AGI unlinked list
+ * modifications being lost.
+ */
+#define _XBF_PAGE_LOCKED (1 << 22)
+
+/*
+ * If we try a barrier write, but it fails we have to communicate
+ * this to the upper layers. Unfortunately b_error gets overwritten
+ * when the buffer is re-issued so we have to add another flag to
+ * keep this information.
+ */
+#define _XFS_BARRIER_FAILED (1 << 23)
+
+typedef unsigned int xfs_buf_flags_t;
#define XFS_BUF_FLAGS \
{ XBF_READ, "READ" }, \
@@ -187,7 +187,6 @@ typedef struct xfs_buf {
atomic_t b_io_remaining; /* #outstanding I/O requests */
xfs_buf_iodone_t b_iodone; /* I/O completion function */
xfs_buf_relse_t b_relse; /* releasing function */
- xfs_buf_bdstrat_t b_strat; /* pre-write function */
struct completion b_iowait; /* queue for I/O waiters */
void *b_fspriv;
void *b_fspriv2;
@@ -245,11 +244,6 @@ extern int xfs_buf_iowait(xfs_buf_t *);
extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *,
xfs_buf_rw_t);
-static inline int xfs_buf_iostrategy(xfs_buf_t *bp)
-{
- return bp->b_strat ? bp->b_strat(bp) : xfs_buf_iorequest(bp);
-}
-
static inline int xfs_buf_geterror(xfs_buf_t *bp)
{
return bp ? bp->b_error : ENOMEM;
@@ -258,11 +252,6 @@ static inline int xfs_buf_geterror(xfs_buf_t *bp)
/* Buffer Utility Routines */
extern xfs_caddr_t xfs_buf_offset(xfs_buf_t *, size_t);
-/* Pinning Buffer Storage in Memory */
-extern void xfs_buf_pin(xfs_buf_t *);
-extern void xfs_buf_unpin(xfs_buf_t *);
-extern int xfs_buf_ispin(xfs_buf_t *);
-
/* Delayed Write Buffer Routines */
extern void xfs_buf_delwri_dequeue(xfs_buf_t *);
extern void xfs_buf_delwri_promote(xfs_buf_t *);
@@ -326,8 +315,6 @@ extern void xfs_buf_terminate(void);
#define XFS_BUF_IODONE_FUNC(bp) ((bp)->b_iodone)
#define XFS_BUF_SET_IODONE_FUNC(bp, func) ((bp)->b_iodone = (func))
#define XFS_BUF_CLR_IODONE_FUNC(bp) ((bp)->b_iodone = NULL)
-#define XFS_BUF_SET_BDSTRAT_FUNC(bp, func) ((bp)->b_strat = (func))
-#define XFS_BUF_CLR_BDSTRAT_FUNC(bp) ((bp)->b_strat = NULL)
#define XFS_BUF_FSPRIVATE(bp, type) ((type)(bp)->b_fspriv)
#define XFS_BUF_SET_FSPRIVATE(bp, val) ((bp)->b_fspriv = (void*)(val))
@@ -351,7 +338,7 @@ extern void xfs_buf_terminate(void);
#define XFS_BUF_SET_VTYPE(bp, type) do { } while (0)
#define XFS_BUF_SET_REF(bp, ref) do { } while (0)
-#define XFS_BUF_ISPINNED(bp) xfs_buf_ispin(bp)
+#define XFS_BUF_ISPINNED(bp) atomic_read(&((bp)->b_pin_count))
#define XFS_BUF_VALUSEMA(bp) xfs_buf_lock_value(bp)
#define XFS_BUF_CPSEMA(bp) (xfs_buf_cond_lock(bp) == 0)
@@ -370,8 +357,6 @@ static inline void xfs_buf_relse(xfs_buf_t *bp)
xfs_buf_rele(bp);
}
-#define xfs_bpin(bp) xfs_buf_pin(bp)
-#define xfs_bunpin(bp) xfs_buf_unpin(bp)
#define xfs_biodone(bp) xfs_buf_ioend(bp, 0)
#define xfs_biomove(bp, off, len, data, rw) \
diff --git a/fs/xfs/linux-2.6/xfs_dmapi_priv.h b/fs/xfs/linux-2.6/xfs_dmapi_priv.h
deleted file mode 100644
index a8b0b1685ee..00000000000
--- a/fs/xfs/linux-2.6/xfs_dmapi_priv.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- * Copyright (c) 2000-2006 Silicon Graphics, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- */
-#ifndef __XFS_DMAPI_PRIV_H__
-#define __XFS_DMAPI_PRIV_H__
-
-/*
- * Based on IO_ISDIRECT, decide which i_ flag is set.
- */
-#define DM_SEM_FLAG_RD(ioflags) (((ioflags) & IO_ISDIRECT) ? \
- DM_FLAGS_IMUX : 0)
-#define DM_SEM_FLAG_WR (DM_FLAGS_IALLOCSEM_WR | DM_FLAGS_IMUX)
-
-#endif /*__XFS_DMAPI_PRIV_H__*/
diff --git a/fs/xfs/linux-2.6/xfs_export.c b/fs/xfs/linux-2.6/xfs_export.c
index 846b75aeb2a..3764d74790e 100644
--- a/fs/xfs/linux-2.6/xfs_export.c
+++ b/fs/xfs/linux-2.6/xfs_export.c
@@ -23,13 +23,13 @@
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_dir2.h"
-#include "xfs_dmapi.h"
#include "xfs_mount.h"
#include "xfs_export.h"
#include "xfs_vnodeops.h"
#include "xfs_bmap_btree.h"
#include "xfs_inode.h"
#include "xfs_inode_item.h"
+#include "xfs_trace.h"
/*
* Note that we only accept fileids which are long enough rather than allow
@@ -128,13 +128,11 @@ xfs_nfs_get_inode(
return ERR_PTR(-ESTALE);
/*
- * The XFS_IGET_BULKSTAT means that an invalid inode number is just
- * fine and not an indication of a corrupted filesystem. Because
- * clients can send any kind of invalid file handle, e.g. after
- * a restore on the server we have to deal with this case gracefully.
+ * The XFS_IGET_UNTRUSTED means that an invalid inode number is just
+ * fine and not an indication of a corrupted filesystem as clients can
+ * send invalid file handles and we have to handle it gracefully..
*/
- error = xfs_iget(mp, NULL, ino, XFS_IGET_BULKSTAT,
- XFS_ILOCK_SHARED, &ip, 0);
+ error = xfs_iget(mp, NULL, ino, XFS_IGET_UNTRUSTED, 0, &ip);
if (error) {
/*
* EINVAL means the inode cluster doesn't exist anymore.
@@ -149,11 +147,10 @@ xfs_nfs_get_inode(
}
if (ip->i_d.di_gen != generation) {
- xfs_iput_new(ip, XFS_ILOCK_SHARED);
+ IRELE(ip);
return ERR_PTR(-ENOENT);
}
- xfs_iunlock(ip, XFS_ILOCK_SHARED);
return VFS_I(ip);
}
diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c
index 257a56b127c..ba8ad422a16 100644
--- a/fs/xfs/linux-2.6/xfs_file.c
+++ b/fs/xfs/linux-2.6/xfs_file.c
@@ -22,23 +22,15 @@
#include "xfs_inum.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
-#include "xfs_dir2.h"
#include "xfs_trans.h"
-#include "xfs_dmapi.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
#include "xfs_alloc.h"
-#include "xfs_btree.h"
-#include "xfs_attr_sf.h"
-#include "xfs_dir2_sf.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_inode_item.h"
#include "xfs_bmap.h"
#include "xfs_error.h"
-#include "xfs_rw.h"
#include "xfs_vnodeops.h"
#include "xfs_da_btree.h"
#include "xfs_ioctl.h"
@@ -108,7 +100,7 @@ xfs_file_fsync(
int error = 0;
int log_flushed = 0;
- xfs_itrace_entry(ip);
+ trace_xfs_file_fsync(ip);
if (XFS_FORCED_SHUTDOWN(ip->i_mount))
return -XFS_ERROR(EIO);
@@ -166,8 +158,7 @@ xfs_file_fsync(
* transaction. So we play it safe and fire off the
* transaction anyway.
*/
- xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
- xfs_trans_ihold(tp, ip);
+ xfs_trans_ijoin(tp, ip);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
xfs_trans_set_sync(tp);
error = _xfs_trans_commit(tp, 0, &log_flushed);
@@ -275,20 +266,6 @@ xfs_file_aio_read(
mutex_lock(&inode->i_mutex);
xfs_ilock(ip, XFS_IOLOCK_SHARED);
- if (DM_EVENT_ENABLED(ip, DM_EVENT_READ) && !(ioflags & IO_INVIS)) {
- int dmflags = FILP_DELAY_FLAG(file) | DM_SEM_FLAG_RD(ioflags);
- int iolock = XFS_IOLOCK_SHARED;
-
- ret = -XFS_SEND_DATA(mp, DM_EVENT_READ, ip, iocb->ki_pos, size,
- dmflags, &iolock);
- if (ret) {
- xfs_iunlock(ip, XFS_IOLOCK_SHARED);
- if (unlikely(ioflags & IO_ISDIRECT))
- mutex_unlock(&inode->i_mutex);
- return ret;
- }
- }
-
if (unlikely(ioflags & IO_ISDIRECT)) {
if (inode->i_mapping->nrpages) {
ret = -xfs_flushinval_pages(ip,
@@ -321,7 +298,6 @@ xfs_file_splice_read(
unsigned int flags)
{
struct xfs_inode *ip = XFS_I(infilp->f_mapping->host);
- struct xfs_mount *mp = ip->i_mount;
int ioflags = 0;
ssize_t ret;
@@ -335,18 +311,6 @@ xfs_file_splice_read(
xfs_ilock(ip, XFS_IOLOCK_SHARED);
- if (DM_EVENT_ENABLED(ip, DM_EVENT_READ) && !(ioflags & IO_INVIS)) {
- int iolock = XFS_IOLOCK_SHARED;
- int error;
-
- error = XFS_SEND_DATA(mp, DM_EVENT_READ, ip, *ppos, count,
- FILP_DELAY_FLAG(infilp), &iolock);
- if (error) {
- xfs_iunlock(ip, XFS_IOLOCK_SHARED);
- return -error;
- }
- }
-
trace_xfs_file_splice_read(ip, count, *ppos, ioflags);
ret = generic_file_splice_read(infilp, ppos, pipe, count, flags);
@@ -367,7 +331,6 @@ xfs_file_splice_write(
{
struct inode *inode = outfilp->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
- struct xfs_mount *mp = ip->i_mount;
xfs_fsize_t isize, new_size;
int ioflags = 0;
ssize_t ret;
@@ -382,18 +345,6 @@ xfs_file_splice_write(
xfs_ilock(ip, XFS_IOLOCK_EXCL);
- if (DM_EVENT_ENABLED(ip, DM_EVENT_WRITE) && !(ioflags & IO_INVIS)) {
- int iolock = XFS_IOLOCK_EXCL;
- int error;
-
- error = XFS_SEND_DATA(mp, DM_EVENT_WRITE, ip, *ppos, count,
- FILP_DELAY_FLAG(outfilp), &iolock);
- if (error) {
- xfs_iunlock(ip, XFS_IOLOCK_EXCL);
- return -error;
- }
- }
-
new_size = *ppos + count;
xfs_ilock(ip, XFS_ILOCK_EXCL);
@@ -463,7 +414,7 @@ xfs_zero_last_block(
last_fsb = XFS_B_TO_FSBT(mp, isize);
nimaps = 1;
error = xfs_bmapi(NULL, ip, last_fsb, 1, 0, NULL, 0, &imap,
- &nimaps, NULL, NULL);
+ &nimaps, NULL);
if (error) {
return error;
}
@@ -558,7 +509,7 @@ xfs_zero_eof(
nimaps = 1;
zero_count_fsb = end_zero_fsb - start_zero_fsb + 1;
error = xfs_bmapi(NULL, ip, start_zero_fsb, zero_count_fsb,
- 0, NULL, 0, &imap, &nimaps, NULL, NULL);
+ 0, NULL, 0, &imap, &nimaps, NULL);
if (error) {
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
return error;
@@ -627,7 +578,6 @@ xfs_file_aio_write(
int ioflags = 0;
xfs_fsize_t isize, new_size;
int iolock;
- int eventsent = 0;
size_t ocount = 0, count;
int need_i_mutex;
@@ -673,33 +623,6 @@ start:
goto out_unlock_mutex;
}
- if ((DM_EVENT_ENABLED(ip, DM_EVENT_WRITE) &&
- !(ioflags & IO_INVIS) && !eventsent)) {
- int dmflags = FILP_DELAY_FLAG(file);
-
- if (need_i_mutex)
- dmflags |= DM_FLAGS_IMUX;
-
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- error = XFS_SEND_DATA(ip->i_mount, DM_EVENT_WRITE, ip,
- pos, count, dmflags, &iolock);
- if (error) {
- goto out_unlock_internal;
- }
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- eventsent = 1;
-
- /*
- * The iolock was dropped and reacquired in XFS_SEND_DATA
- * so we have to recheck the size when appending.
- * We will only "goto start;" once, since having sent the
- * event prevents another call to XFS_SEND_DATA, which is
- * what allows the size to change in the first place.
- */
- if ((file->f_flags & O_APPEND) && pos != ip->i_size)
- goto start;
- }
-
if (ioflags & IO_ISDIRECT) {
xfs_buftarg_t *target =
XFS_IS_REALTIME_INODE(ip) ?
@@ -830,22 +753,6 @@ write_retry:
xfs_iunlock(ip, XFS_ILOCK_EXCL);
}
- if (ret == -ENOSPC &&
- DM_EVENT_ENABLED(ip, DM_EVENT_NOSPACE) && !(ioflags & IO_INVIS)) {
- xfs_iunlock(ip, iolock);
- if (need_i_mutex)
- mutex_unlock(&inode->i_mutex);
- error = XFS_SEND_NAMESP(ip->i_mount, DM_EVENT_NOSPACE, ip,
- DM_RIGHT_NULL, ip, DM_RIGHT_NULL, NULL, NULL,
- 0, 0, 0); /* Delay flag intentionally unused */
- if (need_i_mutex)
- mutex_lock(&inode->i_mutex);
- xfs_ilock(ip, iolock);
- if (error)
- goto out_unlock_internal;
- goto start;
- }
-
error = -ret;
if (ret <= 0)
goto out_unlock_internal;
@@ -1014,9 +921,6 @@ const struct file_operations xfs_file_operations = {
.open = xfs_file_open,
.release = xfs_file_release,
.fsync = xfs_file_fsync,
-#ifdef HAVE_FOP_OPEN_EXEC
- .open_exec = xfs_file_open_exec,
-#endif
};
const struct file_operations xfs_dir_file_operations = {
diff --git a/fs/xfs/linux-2.6/xfs_fs_subr.c b/fs/xfs/linux-2.6/xfs_fs_subr.c
index b6918d76bc7..1f279b012f9 100644
--- a/fs/xfs/linux-2.6/xfs_fs_subr.c
+++ b/fs/xfs/linux-2.6/xfs_fs_subr.c
@@ -21,10 +21,6 @@
#include "xfs_inode.h"
#include "xfs_trace.h"
-int fs_noerr(void) { return 0; }
-int fs_nosys(void) { return ENOSYS; }
-void fs_noval(void) { return; }
-
/*
* note: all filemap functions return negative error codes. These
* need to be inverted before returning to the xfs core functions.
diff --git a/fs/xfs/linux-2.6/xfs_fs_subr.h b/fs/xfs/linux-2.6/xfs_fs_subr.h
deleted file mode 100644
index 82bb19b2599..00000000000
--- a/fs/xfs/linux-2.6/xfs_fs_subr.h
+++ /dev/null
@@ -1,25 +0,0 @@
-/*
- * Copyright (c) 2000,2002,2005 Silicon Graphics, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- */
-#ifndef __XFS_FS_SUBR_H__
-#define __XFS_FS_SUBR_H__
-
-extern int fs_noerr(void);
-extern int fs_nosys(void);
-extern void fs_noval(void);
-
-#endif /* __XFS_FS_SUBR_H__ */
diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c
index 699b60cbab9..237f5ffb2ee 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl.c
@@ -23,24 +23,15 @@
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
-#include "xfs_dir2.h"
#include "xfs_alloc.h"
-#include "xfs_dmapi.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_attr_sf.h"
-#include "xfs_dir2_sf.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_ioctl.h"
-#include "xfs_btree.h"
-#include "xfs_ialloc.h"
#include "xfs_rtalloc.h"
#include "xfs_itable.h"
#include "xfs_error.h"
-#include "xfs_rw.h"
#include "xfs_attr.h"
#include "xfs_bmap.h"
#include "xfs_buf_item.h"
@@ -679,10 +670,9 @@ xfs_ioc_bulkstat(
error = xfs_bulkstat_single(mp, &inlast,
bulkreq.ubuffer, &done);
else /* XFS_IOC_FSBULKSTAT */
- error = xfs_bulkstat(mp, &inlast, &count,
- (bulkstat_one_pf)xfs_bulkstat_one, NULL,
- sizeof(xfs_bstat_t), bulkreq.ubuffer,
- BULKSTAT_FG_QUICK, &done);
+ error = xfs_bulkstat(mp, &inlast, &count, xfs_bulkstat_one,
+ sizeof(xfs_bstat_t), bulkreq.ubuffer,
+ &done);
if (error)
return -error;
@@ -909,7 +899,7 @@ xfs_ioctl_setattr(
struct xfs_dquot *olddquot = NULL;
int code;
- xfs_itrace_entry(ip);
+ trace_xfs_ioctl_setattr(ip);
if (mp->m_flags & XFS_MOUNT_RDONLY)
return XFS_ERROR(EROFS);
@@ -1044,8 +1034,7 @@ xfs_ioctl_setattr(
}
}
- xfs_trans_ijoin(tp, ip, lock_flags);
- xfs_trans_ihold(tp, ip);
+ xfs_trans_ijoin(tp, ip);
/*
* Change file ownership. Must be the owner or privileged.
@@ -1117,16 +1106,7 @@ xfs_ioctl_setattr(
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);
- if (code)
- return code;
-
- if (DM_EVENT_ENABLED(ip, DM_EVENT_ATTRIBUTE)) {
- XFS_SEND_NAMESP(mp, DM_EVENT_ATTRIBUTE, ip, DM_RIGHT_NULL,
- NULL, DM_RIGHT_NULL, NULL, NULL, 0, 0,
- (mask & FSX_NONBLOCK) ? DM_FLAGS_NDELAY : 0);
- }
-
- return 0;
+ return code;
error_return:
xfs_qm_dqrele(udqp);
@@ -1302,7 +1282,7 @@ xfs_file_ioctl(
if (filp->f_mode & FMODE_NOCMTIME)
ioflags |= IO_INVIS;
- xfs_itrace_entry(ip);
+ trace_xfs_file_ioctl(ip);
switch (cmd) {
case XFS_IOC_ALLOCSP:
diff --git a/fs/xfs/linux-2.6/xfs_ioctl32.c b/fs/xfs/linux-2.6/xfs_ioctl32.c
index 9287135e9bf..6c83f7f62dc 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl32.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl32.c
@@ -28,12 +28,8 @@
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
-#include "xfs_dir2.h"
-#include "xfs_dmapi.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
-#include "xfs_attr_sf.h"
-#include "xfs_dir2_sf.h"
#include "xfs_vnode.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
@@ -237,15 +233,12 @@ xfs_bulkstat_one_compat(
xfs_ino_t ino, /* inode number to get data for */
void __user *buffer, /* buffer to place output in */
int ubsize, /* size of buffer */
- void *private_data, /* my private data */
- xfs_daddr_t bno, /* starting bno of inode cluster */
int *ubused, /* bytes used by me */
- void *dibuff, /* on-disk inode buffer */
int *stat) /* BULKSTAT_RV_... */
{
return xfs_bulkstat_one_int(mp, ino, buffer, ubsize,
- xfs_bulkstat_one_fmt_compat, bno,
- ubused, dibuff, stat);
+ xfs_bulkstat_one_fmt_compat,
+ ubused, stat);
}
/* copied from xfs_ioctl.c */
@@ -298,13 +291,11 @@ xfs_compat_ioc_bulkstat(
int res;
error = xfs_bulkstat_one_compat(mp, inlast, bulkreq.ubuffer,
- sizeof(compat_xfs_bstat_t),
- NULL, 0, NULL, NULL, &res);
+ sizeof(compat_xfs_bstat_t), 0, &res);
} else if (cmd == XFS_IOC_FSBULKSTAT_32) {
error = xfs_bulkstat(mp, &inlast, &count,
- xfs_bulkstat_one_compat, NULL,
- sizeof(compat_xfs_bstat_t), bulkreq.ubuffer,
- BULKSTAT_FG_QUICK, &done);
+ xfs_bulkstat_one_compat, sizeof(compat_xfs_bstat_t),
+ bulkreq.ubuffer, &done);
} else
error = XFS_ERROR(EINVAL);
if (error)
@@ -549,7 +540,7 @@ xfs_file_compat_ioctl(
if (filp->f_mode & FMODE_NOCMTIME)
ioflags |= IO_INVIS;
- xfs_itrace_entry(ip);
+ trace_xfs_file_compat_ioctl(ip);
switch (cmd) {
/* No size or alignment issues on any arch */
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
index 44f0b2de153..536b81e63a3 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -24,21 +24,13 @@
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
-#include "xfs_dir2.h"
#include "xfs_alloc.h"
-#include "xfs_dmapi.h"
#include "xfs_quota.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dir2_sf.h"
-#include "xfs_attr_sf.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_bmap.h"
-#include "xfs_btree.h"
-#include "xfs_ialloc.h"
#include "xfs_rtalloc.h"
#include "xfs_error.h"
#include "xfs_itable.h"
@@ -496,7 +488,7 @@ xfs_vn_getattr(
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
- xfs_itrace_entry(ip);
+ trace_xfs_getattr(ip);
if (XFS_FORCED_SHUTDOWN(mp))
return XFS_ERROR(EIO);
diff --git a/fs/xfs/linux-2.6/xfs_linux.h b/fs/xfs/linux-2.6/xfs_linux.h
index facfb323a70..998a9d7fb9c 100644
--- a/fs/xfs/linux-2.6/xfs_linux.h
+++ b/fs/xfs/linux-2.6/xfs_linux.h
@@ -87,7 +87,6 @@
#include <xfs_aops.h>
#include <xfs_super.h>
#include <xfs_globals.h>
-#include <xfs_fs_subr.h>
#include <xfs_buf.h>
/*
diff --git a/fs/xfs/linux-2.6/xfs_quotaops.c b/fs/xfs/linux-2.6/xfs_quotaops.c
index 067cafbfc63..bfd5ac9d1f6 100644
--- a/fs/xfs/linux-2.6/xfs_quotaops.c
+++ b/fs/xfs/linux-2.6/xfs_quotaops.c
@@ -16,7 +16,6 @@
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "xfs.h"
-#include "xfs_dmapi.h"
#include "xfs_sb.h"
#include "xfs_inum.h"
#include "xfs_log.h"
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index f2d1718c916..758df94690e 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -25,14 +25,11 @@
#include "xfs_ag.h"
#include "xfs_dir2.h"
#include "xfs_alloc.h"
-#include "xfs_dmapi.h"
#include "xfs_quota.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc_btree.h"
-#include "xfs_dir2_sf.h"
-#include "xfs_attr_sf.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_btree.h"
@@ -43,7 +40,6 @@
#include "xfs_error.h"
#include "xfs_itable.h"
#include "xfs_fsops.h"
-#include "xfs_rw.h"
#include "xfs_attr.h"
#include "xfs_buf_item.h"
#include "xfs_utils.h"
@@ -94,7 +90,6 @@ mempool_t *xfs_ioend_pool;
#define MNTOPT_BARRIER "barrier" /* use writer barriers for log write and
* unwritten extent conversion */
#define MNTOPT_NOBARRIER "nobarrier" /* .. disable */
-#define MNTOPT_OSYNCISOSYNC "osyncisosync" /* o_sync is REALLY o_sync */
#define MNTOPT_64BITINODE "inode64" /* inodes can be allocated anywhere */
#define MNTOPT_IKEEP "ikeep" /* do not free empty inode clusters */
#define MNTOPT_NOIKEEP "noikeep" /* free empty inode clusters */
@@ -116,9 +111,6 @@ mempool_t *xfs_ioend_pool;
#define MNTOPT_GQUOTANOENF "gqnoenforce"/* group quota limit enforcement */
#define MNTOPT_PQUOTANOENF "pqnoenforce"/* project quota limit enforcement */
#define MNTOPT_QUOTANOENF "qnoenforce" /* same as uqnoenforce */
-#define MNTOPT_DMAPI "dmapi" /* DMI enabled (DMAPI / XDSM) */
-#define MNTOPT_XDSM "xdsm" /* DMI enabled (DMAPI / XDSM) */
-#define MNTOPT_DMI "dmi" /* DMI enabled (DMAPI / XDSM) */
#define MNTOPT_DELAYLOG "delaylog" /* Delayed loging enabled */
#define MNTOPT_NODELAYLOG "nodelaylog" /* Delayed loging disabled */
@@ -172,15 +164,13 @@ suffix_strtoul(char *s, char **endp, unsigned int base)
STATIC int
xfs_parseargs(
struct xfs_mount *mp,
- char *options,
- char **mtpt)
+ char *options)
{
struct super_block *sb = mp->m_super;
char *this_char, *value, *eov;
int dsunit = 0;
int dswidth = 0;
int iosize = 0;
- int dmapi_implies_ikeep = 1;
__uint8_t iosizelog = 0;
/*
@@ -243,15 +233,10 @@ xfs_parseargs(
if (!mp->m_logname)
return ENOMEM;
} else if (!strcmp(this_char, MNTOPT_MTPT)) {
- if (!value || !*value) {
- cmn_err(CE_WARN,
- "XFS: %s option requires an argument",
- this_char);
- return EINVAL;
- }
- *mtpt = kstrndup(value, MAXNAMELEN, GFP_KERNEL);
- if (!*mtpt)
- return ENOMEM;
+ cmn_err(CE_WARN,
+ "XFS: %s option not allowed on this system",
+ this_char);
+ return EINVAL;
} else if (!strcmp(this_char, MNTOPT_RTDEV)) {
if (!value || !*value) {
cmn_err(CE_WARN,
@@ -288,8 +273,6 @@ xfs_parseargs(
mp->m_flags &= ~XFS_MOUNT_GRPID;
} else if (!strcmp(this_char, MNTOPT_WSYNC)) {
mp->m_flags |= XFS_MOUNT_WSYNC;
- } else if (!strcmp(this_char, MNTOPT_OSYNCISOSYNC)) {
- mp->m_flags |= XFS_MOUNT_OSYNCISOSYNC;
} else if (!strcmp(this_char, MNTOPT_NORECOVERY)) {
mp->m_flags |= XFS_MOUNT_NORECOVERY;
} else if (!strcmp(this_char, MNTOPT_NOALIGN)) {
@@ -329,7 +312,6 @@ xfs_parseargs(
} else if (!strcmp(this_char, MNTOPT_IKEEP)) {
mp->m_flags |= XFS_MOUNT_IKEEP;
} else if (!strcmp(this_char, MNTOPT_NOIKEEP)) {
- dmapi_implies_ikeep = 0;
mp->m_flags &= ~XFS_MOUNT_IKEEP;
} else if (!strcmp(this_char, MNTOPT_LARGEIO)) {
mp->m_flags &= ~XFS_MOUNT_COMPAT_IOSIZE;
@@ -370,12 +352,6 @@ xfs_parseargs(
} else if (!strcmp(this_char, MNTOPT_GQUOTANOENF)) {
mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE);
mp->m_qflags &= ~XFS_OQUOTA_ENFD;
- } else if (!strcmp(this_char, MNTOPT_DMAPI)) {
- mp->m_flags |= XFS_MOUNT_DMAPI;
- } else if (!strcmp(this_char, MNTOPT_XDSM)) {
- mp->m_flags |= XFS_MOUNT_DMAPI;
- } else if (!strcmp(this_char, MNTOPT_DMI)) {
- mp->m_flags |= XFS_MOUNT_DMAPI;
} else if (!strcmp(this_char, MNTOPT_DELAYLOG)) {
mp->m_flags |= XFS_MOUNT_DELAYLOG;
cmn_err(CE_WARN,
@@ -387,9 +363,11 @@ xfs_parseargs(
cmn_err(CE_WARN,
"XFS: ihashsize no longer used, option is deprecated.");
} else if (!strcmp(this_char, "osyncisdsync")) {
- /* no-op, this is now the default */
cmn_err(CE_WARN,
- "XFS: osyncisdsync is now the default, option is deprecated.");
+ "XFS: osyncisdsync has no effect, option is deprecated.");
+ } else if (!strcmp(this_char, "osyncisosync")) {
+ cmn_err(CE_WARN,
+ "XFS: osyncisosync has no effect, option is deprecated.");
} else if (!strcmp(this_char, "irixsgid")) {
cmn_err(CE_WARN,
"XFS: irixsgid is now a sysctl(2) variable, option is deprecated.");
@@ -430,12 +408,6 @@ xfs_parseargs(
return EINVAL;
}
- if ((mp->m_flags & XFS_MOUNT_DMAPI) && (!*mtpt || *mtpt[0] == '\0')) {
- printk("XFS: %s option needs the mount point option as well\n",
- MNTOPT_DMAPI);
- return EINVAL;
- }
-
if ((dsunit && !dswidth) || (!dsunit && dswidth)) {
cmn_err(CE_WARN,
"XFS: sunit and swidth must be specified together");
@@ -449,18 +421,6 @@ xfs_parseargs(
return EINVAL;
}
- /*
- * Applications using DMI filesystems often expect the
- * inode generation number to be monotonically increasing.
- * If we delete inode chunks we break this assumption, so
- * keep unused inode chunks on disk for DMI filesystems
- * until we come up with a better solution.
- * Note that if "ikeep" or "noikeep" mount options are
- * supplied, then they are honored.
- */
- if ((mp->m_flags & XFS_MOUNT_DMAPI) && dmapi_implies_ikeep)
- mp->m_flags |= XFS_MOUNT_IKEEP;
-
done:
if (!(mp->m_flags & XFS_MOUNT_NOALIGN)) {
/*
@@ -539,10 +499,8 @@ xfs_showargs(
{ XFS_MOUNT_SWALLOC, "," MNTOPT_SWALLOC },
{ XFS_MOUNT_NOUUID, "," MNTOPT_NOUUID },
{ XFS_MOUNT_NORECOVERY, "," MNTOPT_NORECOVERY },
- { XFS_MOUNT_OSYNCISOSYNC, "," MNTOPT_OSYNCISOSYNC },
{ XFS_MOUNT_ATTR2, "," MNTOPT_ATTR2 },
{ XFS_MOUNT_FILESTREAMS, "," MNTOPT_FILESTREAM },
- { XFS_MOUNT_DMAPI, "," MNTOPT_DMAPI },
{ XFS_MOUNT_GRPID, "," MNTOPT_GRPID },
{ XFS_MOUNT_DELAYLOG, "," MNTOPT_DELAYLOG },
{ 0, NULL }
@@ -947,7 +905,7 @@ xfs_fs_destroy_inode(
{
struct xfs_inode *ip = XFS_I(inode);
- xfs_itrace_entry(ip);
+ trace_xfs_destroy_inode(ip);
XFS_STATS_INC(vn_reclaim);
@@ -1063,10 +1021,8 @@ xfs_log_inode(
* an inode in another recent transaction. So we play it safe and
* fire off the transaction anyway.
*/
- xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
- xfs_trans_ihold(tp, ip);
+ xfs_trans_ijoin(tp, ip);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
- xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp, 0);
xfs_ilock_demote(ip, XFS_ILOCK_EXCL);
@@ -1082,27 +1038,18 @@ xfs_fs_write_inode(
struct xfs_mount *mp = ip->i_mount;
int error = EAGAIN;
- xfs_itrace_entry(ip);
+ trace_xfs_write_inode(ip);
if (XFS_FORCED_SHUTDOWN(mp))
return XFS_ERROR(EIO);
if (wbc->sync_mode == WB_SYNC_ALL) {
/*
- * Make sure the inode has hit stable storage. By using the
- * log and the fsync transactions we reduce the IOs we have
- * to do here from two (log and inode) to just the log.
- *
- * Note: We still need to do a delwri write of the inode after
- * this to flush it to the backing buffer so that bulkstat
- * works properly if this is the first time the inode has been
- * written. Because we hold the ilock atomically over the
- * transaction commit and the inode flush we are guaranteed
- * that the inode is not pinned when it returns. If the flush
- * lock is already held, then the inode has already been
- * flushed once and we don't need to flush it again. Hence
- * the code will only flush the inode if it isn't already
- * being flushed.
+ * Make sure the inode has made it it into the log. Instead
+ * of forcing it all the way to stable storage using a
+ * synchronous transaction we let the log force inside the
+ * ->sync_fs call do that for thus, which reduces the number
+ * of synchronous log foces dramatically.
*/
xfs_ioend_wait(ip);
xfs_ilock(ip, XFS_ILOCK_SHARED);
@@ -1116,27 +1063,29 @@ xfs_fs_write_inode(
* We make this non-blocking if the inode is contended, return
* EAGAIN to indicate to the caller that they did not succeed.
* This prevents the flush path from blocking on inodes inside
- * another operation right now, they get caught later by xfs_sync.
+ * another operation right now, they get caught later by
+ * xfs_sync.
*/
if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED))
goto out;
- }
- if (xfs_ipincount(ip) || !xfs_iflock_nowait(ip))
- goto out_unlock;
+ if (xfs_ipincount(ip) || !xfs_iflock_nowait(ip))
+ goto out_unlock;
- /*
- * Now we have the flush lock and the inode is not pinned, we can check
- * if the inode is really clean as we know that there are no pending
- * transaction completions, it is not waiting on the delayed write
- * queue and there is no IO in progress.
- */
- if (xfs_inode_clean(ip)) {
- xfs_ifunlock(ip);
- error = 0;
- goto out_unlock;
+ /*
+ * Now we have the flush lock and the inode is not pinned, we
+ * can check if the inode is really clean as we know that
+ * there are no pending transaction completions, it is not
+ * waiting on the delayed write queue and there is no IO in
+ * progress.
+ */
+ if (xfs_inode_clean(ip)) {
+ xfs_ifunlock(ip);
+ error = 0;
+ goto out_unlock;
+ }
+ error = xfs_iflush(ip, 0);
}
- error = xfs_iflush(ip, 0);
out_unlock:
xfs_iunlock(ip, XFS_ILOCK_SHARED);
@@ -1156,7 +1105,8 @@ xfs_fs_clear_inode(
{
xfs_inode_t *ip = XFS_I(inode);
- xfs_itrace_entry(ip);
+ trace_xfs_clear_inode(ip);
+
XFS_STATS_INC(vn_rele);
XFS_STATS_INC(vn_remove);
XFS_STATS_DEC(vn_active);
@@ -1193,22 +1143,13 @@ xfs_fs_put_super(
{
struct xfs_mount *mp = XFS_M(sb);
+ /*
+ * Unregister the memory shrinker before we tear down the mount
+ * structure so we don't have memory reclaim racing with us here.
+ */
+ xfs_inode_shrinker_unregister(mp);
xfs_syncd_stop(mp);
- if (!(sb->s_flags & MS_RDONLY)) {
- /*
- * XXX(hch): this should be SYNC_WAIT.
- *
- * Or more likely not needed at all because the VFS is already
- * calling ->sync_fs after shutting down all filestem
- * operations and just before calling ->put_super.
- */
- xfs_sync_data(mp, 0);
- xfs_sync_attr(mp, 0);
- }
-
- XFS_SEND_PREUNMOUNT(mp);
-
/*
* Blow away any referenced inode in the filestreams cache.
* This can and will cause log traffic as inodes go inactive
@@ -1218,14 +1159,10 @@ xfs_fs_put_super(
XFS_bflush(mp->m_ddev_targp);
- XFS_SEND_UNMOUNT(mp);
-
xfs_unmountfs(mp);
xfs_freesb(mp);
- xfs_inode_shrinker_unregister(mp);
xfs_icsb_destroy_counters(mp);
xfs_close_devices(mp);
- xfs_dmops_put(mp);
xfs_free_fsname(mp);
kfree(mp);
}
@@ -1543,7 +1480,6 @@ xfs_fs_fill_super(
struct inode *root;
struct xfs_mount *mp = NULL;
int flags = 0, error = ENOMEM;
- char *mtpt = NULL;
mp = kzalloc(sizeof(struct xfs_mount), GFP_KERNEL);
if (!mp)
@@ -1559,7 +1495,7 @@ xfs_fs_fill_super(
mp->m_super = sb;
sb->s_fs_info = mp;
- error = xfs_parseargs(mp, (char *)data, &mtpt);
+ error = xfs_parseargs(mp, (char *)data);
if (error)
goto out_free_fsname;
@@ -1571,16 +1507,12 @@ xfs_fs_fill_super(
#endif
sb->s_op = &xfs_super_operations;
- error = xfs_dmops_get(mp);
- if (error)
- goto out_free_fsname;
-
if (silent)
flags |= XFS_MFSI_QUIET;
error = xfs_open_devices(mp);
if (error)
- goto out_put_dmops;
+ goto out_free_fsname;
if (xfs_icsb_init_counters(mp))
mp->m_flags |= XFS_MOUNT_NO_PERCPU_SB;
@@ -1608,8 +1540,6 @@ xfs_fs_fill_super(
if (error)
goto out_filestream_unmount;
- XFS_SEND_MOUNT(mp, DM_RIGHT_NULL, mtpt, mp->m_fsname);
-
sb->s_magic = XFS_SB_MAGIC;
sb->s_blocksize = mp->m_sb.sb_blocksize;
sb->s_blocksize_bits = ffs(sb->s_blocksize) - 1;
@@ -1638,7 +1568,6 @@ xfs_fs_fill_super(
xfs_inode_shrinker_register(mp);
- kfree(mtpt);
return 0;
out_filestream_unmount:
@@ -1648,11 +1577,8 @@ xfs_fs_fill_super(
out_destroy_counters:
xfs_icsb_destroy_counters(mp);
xfs_close_devices(mp);
- out_put_dmops:
- xfs_dmops_put(mp);
out_free_fsname:
xfs_free_fsname(mp);
- kfree(mtpt);
kfree(mp);
out:
return -error;
@@ -1759,6 +1685,12 @@ xfs_init_zones(void)
if (!xfs_trans_zone)
goto out_destroy_ifork_zone;
+ xfs_log_item_desc_zone =
+ kmem_zone_init(sizeof(struct xfs_log_item_desc),
+ "xfs_log_item_desc");
+ if (!xfs_log_item_desc_zone)
+ goto out_destroy_trans_zone;
+
/*
* The size of the zone allocated buf log item is the maximum
* size possible under XFS. This wastes a little bit of memory,
@@ -1768,7 +1700,7 @@ xfs_init_zones(void)
(((XFS_MAX_BLOCKSIZE / XFS_BLF_CHUNK) /
NBWORD) * sizeof(int))), "xfs_buf_item");
if (!xfs_buf_item_zone)
- goto out_destroy_trans_zone;
+ goto out_destroy_log_item_desc_zone;
xfs_efd_zone = kmem_zone_init((sizeof(xfs_efd_log_item_t) +
((XFS_EFD_MAX_FAST_EXTENTS - 1) *
@@ -1805,6 +1737,8 @@ xfs_init_zones(void)
kmem_zone_destroy(xfs_efd_zone);
out_destroy_buf_item_zone:
kmem_zone_destroy(xfs_buf_item_zone);
+ out_destroy_log_item_desc_zone:
+ kmem_zone_destroy(xfs_log_item_desc_zone);
out_destroy_trans_zone:
kmem_zone_destroy(xfs_trans_zone);
out_destroy_ifork_zone:
@@ -1835,6 +1769,7 @@ xfs_destroy_zones(void)
kmem_zone_destroy(xfs_efi_zone);
kmem_zone_destroy(xfs_efd_zone);
kmem_zone_destroy(xfs_buf_item_zone);
+ kmem_zone_destroy(xfs_log_item_desc_zone);
kmem_zone_destroy(xfs_trans_zone);
kmem_zone_destroy(xfs_ifork_zone);
kmem_zone_destroy(xfs_dabuf_zone);
@@ -1883,7 +1818,6 @@ init_xfs_fs(void)
goto out_cleanup_procfs;
vfs_initquota();
- xfs_inode_shrinker_init();
error = register_filesystem(&xfs_fs_type);
if (error)
@@ -1911,7 +1845,6 @@ exit_xfs_fs(void)
{
vfs_exitquota();
unregister_filesystem(&xfs_fs_type);
- xfs_inode_shrinker_destroy();
xfs_sysctl_unregister();
xfs_cleanup_procfs();
xfs_buf_terminate();
diff --git a/fs/xfs/linux-2.6/xfs_super.h b/fs/xfs/linux-2.6/xfs_super.h
index 519618e9279..1ef4a4d2d99 100644
--- a/fs/xfs/linux-2.6/xfs_super.h
+++ b/fs/xfs/linux-2.6/xfs_super.h
@@ -56,12 +56,6 @@ extern void xfs_qm_exit(void);
# define XFS_BIGFS_STRING
#endif
-#ifdef CONFIG_XFS_DMAPI
-# define XFS_DMAPI_STRING "dmapi support, "
-#else
-# define XFS_DMAPI_STRING
-#endif
-
#ifdef DEBUG
# define XFS_DBG_STRING "debug"
#else
@@ -72,7 +66,6 @@ extern void xfs_qm_exit(void);
XFS_SECURITY_STRING \
XFS_REALTIME_STRING \
XFS_BIGFS_STRING \
- XFS_DMAPI_STRING \
XFS_DBG_STRING /* DBG must be last */
struct xfs_inode;
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index ef7f0218bcc..dfcbd98d159 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -24,25 +24,14 @@
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
-#include "xfs_dir2.h"
-#include "xfs_dmapi.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_btree.h"
-#include "xfs_dir2_sf.h"
-#include "xfs_attr_sf.h"
#include "xfs_inode.h"
#include "xfs_dinode.h"
#include "xfs_error.h"
-#include "xfs_mru_cache.h"
#include "xfs_filestream.h"
#include "xfs_vnodeops.h"
-#include "xfs_utils.h"
-#include "xfs_buf_item.h"
#include "xfs_inode_item.h"
-#include "xfs_rw.h"
#include "xfs_quota.h"
#include "xfs_trace.h"
@@ -144,6 +133,41 @@ restart:
return last_error;
}
+/*
+ * Select the next per-ag structure to iterate during the walk. The reclaim
+ * walk is optimised only to walk AGs with reclaimable inodes in them.
+ */
+static struct xfs_perag *
+xfs_inode_ag_iter_next_pag(
+ struct xfs_mount *mp,
+ xfs_agnumber_t *first,
+ int tag)
+{
+ struct xfs_perag *pag = NULL;
+
+ if (tag == XFS_ICI_RECLAIM_TAG) {
+ int found;
+ int ref;
+
+ spin_lock(&mp->m_perag_lock);
+ found = radix_tree_gang_lookup_tag(&mp->m_perag_tree,
+ (void **)&pag, *first, 1, tag);
+ if (found <= 0) {
+ spin_unlock(&mp->m_perag_lock);
+ return NULL;
+ }
+ *first = pag->pag_agno + 1;
+ /* open coded pag reference increment */
+ ref = atomic_inc_return(&pag->pag_ref);
+ spin_unlock(&mp->m_perag_lock);
+ trace_xfs_perag_get_reclaim(mp, pag->pag_agno, ref, _RET_IP_);
+ } else {
+ pag = xfs_perag_get(mp, *first);
+ (*first)++;
+ }
+ return pag;
+}
+
int
xfs_inode_ag_iterator(
struct xfs_mount *mp,
@@ -154,16 +178,15 @@ xfs_inode_ag_iterator(
int exclusive,
int *nr_to_scan)
{
+ struct xfs_perag *pag;
int error = 0;
int last_error = 0;
xfs_agnumber_t ag;
int nr;
nr = nr_to_scan ? *nr_to_scan : INT_MAX;
- for (ag = 0; ag < mp->m_sb.sb_agcount; ag++) {
- struct xfs_perag *pag;
-
- pag = xfs_perag_get(mp, ag);
+ ag = 0;
+ while ((pag = xfs_inode_ag_iter_next_pag(mp, &ag, tag))) {
error = xfs_inode_ag_walk(mp, pag, execute, flags, tag,
exclusive, &nr);
xfs_perag_put(pag);
@@ -285,7 +308,7 @@ xfs_sync_inode_attr(
/*
* Write out pagecache data for the whole filesystem.
*/
-int
+STATIC int
xfs_sync_data(
struct xfs_mount *mp,
int flags)
@@ -306,7 +329,7 @@ xfs_sync_data(
/*
* Write out inode metadata (attributes) for the whole filesystem.
*/
-int
+STATIC int
xfs_sync_attr(
struct xfs_mount *mp,
int flags)
@@ -339,8 +362,7 @@ xfs_commit_dummy_trans(
xfs_ilock(ip, XFS_ILOCK_EXCL);
- xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
- xfs_trans_ihold(tp, ip);
+ xfs_trans_ijoin(tp, ip);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
error = xfs_trans_commit(tp, 0);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
@@ -640,6 +662,17 @@ __xfs_inode_set_reclaim_tag(
radix_tree_tag_set(&pag->pag_ici_root,
XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino),
XFS_ICI_RECLAIM_TAG);
+
+ if (!pag->pag_ici_reclaimable) {
+ /* propagate the reclaim tag up into the perag radix tree */
+ spin_lock(&ip->i_mount->m_perag_lock);
+ radix_tree_tag_set(&ip->i_mount->m_perag_tree,
+ XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino),
+ XFS_ICI_RECLAIM_TAG);
+ spin_unlock(&ip->i_mount->m_perag_lock);
+ trace_xfs_perag_set_reclaim(ip->i_mount, pag->pag_agno,
+ -1, _RET_IP_);
+ }
pag->pag_ici_reclaimable++;
}
@@ -674,6 +707,16 @@ __xfs_inode_clear_reclaim_tag(
radix_tree_tag_clear(&pag->pag_ici_root,
XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG);
pag->pag_ici_reclaimable--;
+ if (!pag->pag_ici_reclaimable) {
+ /* clear the reclaim tag from the perag radix tree */
+ spin_lock(&ip->i_mount->m_perag_lock);
+ radix_tree_tag_clear(&ip->i_mount->m_perag_tree,
+ XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino),
+ XFS_ICI_RECLAIM_TAG);
+ spin_unlock(&ip->i_mount->m_perag_lock);
+ trace_xfs_perag_clear_reclaim(ip->i_mount, pag->pag_agno,
+ -1, _RET_IP_);
+ }
}
/*
@@ -812,7 +855,36 @@ out:
reclaim:
xfs_ifunlock(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
- xfs_ireclaim(ip);
+
+ XFS_STATS_INC(xs_ig_reclaims);
+ /*
+ * Remove the inode from the per-AG radix tree.
+ *
+ * Because radix_tree_delete won't complain even if the item was never
+ * added to the tree assert that it's been there before to catch
+ * problems with the inode life time early on.
+ */
+ write_lock(&pag->pag_ici_lock);
+ if (!radix_tree_delete(&pag->pag_ici_root,
+ XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino)))
+ ASSERT(0);
+ write_unlock(&pag->pag_ici_lock);
+
+ /*
+ * Here we do an (almost) spurious inode lock in order to coordinate
+ * with inode cache radix tree lookups. This is because the lookup
+ * can reference the inodes in the cache without taking references.
+ *
+ * We make that OK here by ensuring that we wait until the inode is
+ * unlocked after the lookup before we go ahead and free it. We get
+ * both the ilock and the iolock because the code may need to drop the
+ * ilock one but will still hold the iolock.
+ */
+ xfs_ilock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+ xfs_qm_dqdetach(ip);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+
+ xfs_inode_free(ip);
return error;
}
@@ -828,83 +900,52 @@ xfs_reclaim_inodes(
/*
* Shrinker infrastructure.
- *
- * This is all far more complex than it needs to be. It adds a global list of
- * mounts because the shrinkers can only call a global context. We need to make
- * the shrinkers pass a context to avoid the need for global state.
*/
-static LIST_HEAD(xfs_mount_list);
-static struct rw_semaphore xfs_mount_list_lock;
-
static int
xfs_reclaim_inode_shrink(
+ struct shrinker *shrink,
int nr_to_scan,
gfp_t gfp_mask)
{
struct xfs_mount *mp;
struct xfs_perag *pag;
xfs_agnumber_t ag;
- int reclaimable = 0;
+ int reclaimable;
+ mp = container_of(shrink, struct xfs_mount, m_inode_shrink);
if (nr_to_scan) {
if (!(gfp_mask & __GFP_FS))
return -1;
- down_read(&xfs_mount_list_lock);
- list_for_each_entry(mp, &xfs_mount_list, m_mplist) {
- xfs_inode_ag_iterator(mp, xfs_reclaim_inode, 0,
+ xfs_inode_ag_iterator(mp, xfs_reclaim_inode, 0,
XFS_ICI_RECLAIM_TAG, 1, &nr_to_scan);
- if (nr_to_scan <= 0)
- break;
- }
- up_read(&xfs_mount_list_lock);
- }
+ /* if we don't exhaust the scan, don't bother coming back */
+ if (nr_to_scan > 0)
+ return -1;
+ }
- down_read(&xfs_mount_list_lock);
- list_for_each_entry(mp, &xfs_mount_list, m_mplist) {
- for (ag = 0; ag < mp->m_sb.sb_agcount; ag++) {
- pag = xfs_perag_get(mp, ag);
- reclaimable += pag->pag_ici_reclaimable;
- xfs_perag_put(pag);
- }
+ reclaimable = 0;
+ ag = 0;
+ while ((pag = xfs_inode_ag_iter_next_pag(mp, &ag,
+ XFS_ICI_RECLAIM_TAG))) {
+ reclaimable += pag->pag_ici_reclaimable;
+ xfs_perag_put(pag);
}
- up_read(&xfs_mount_list_lock);
return reclaimable;
}
-static struct shrinker xfs_inode_shrinker = {
- .shrink = xfs_reclaim_inode_shrink,
- .seeks = DEFAULT_SEEKS,
-};
-
-void __init
-xfs_inode_shrinker_init(void)
-{
- init_rwsem(&xfs_mount_list_lock);
- register_shrinker(&xfs_inode_shrinker);
-}
-
-void
-xfs_inode_shrinker_destroy(void)
-{
- ASSERT(list_empty(&xfs_mount_list));
- unregister_shrinker(&xfs_inode_shrinker);
-}
-
void
xfs_inode_shrinker_register(
struct xfs_mount *mp)
{
- down_write(&xfs_mount_list_lock);
- list_add_tail(&mp->m_mplist, &xfs_mount_list);
- up_write(&xfs_mount_list_lock);
+ mp->m_inode_shrink.shrink = xfs_reclaim_inode_shrink;
+ mp->m_inode_shrink.seeks = DEFAULT_SEEKS;
+ register_shrinker(&mp->m_inode_shrink);
}
void
xfs_inode_shrinker_unregister(
struct xfs_mount *mp)
{
- down_write(&xfs_mount_list_lock);
- list_del(&mp->m_mplist);
- up_write(&xfs_mount_list_lock);
+ unregister_shrinker(&mp->m_inode_shrink);
}
diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h
index cdcbaaca988..fe78726196f 100644
--- a/fs/xfs/linux-2.6/xfs_sync.h
+++ b/fs/xfs/linux-2.6/xfs_sync.h
@@ -35,9 +35,6 @@ typedef struct xfs_sync_work {
int xfs_syncd_init(struct xfs_mount *mp);
void xfs_syncd_stop(struct xfs_mount *mp);
-int xfs_sync_attr(struct xfs_mount *mp, int flags);
-int xfs_sync_data(struct xfs_mount *mp, int flags);
-
int xfs_quiesce_data(struct xfs_mount *mp);
void xfs_quiesce_attr(struct xfs_mount *mp);
@@ -55,8 +52,6 @@ int xfs_inode_ag_iterator(struct xfs_mount *mp,
int (*execute)(struct xfs_inode *ip, struct xfs_perag *pag, int flags),
int flags, int tag, int write_lock, int *nr_to_scan);
-void xfs_inode_shrinker_init(void);
-void xfs_inode_shrinker_destroy(void);
void xfs_inode_shrinker_register(struct xfs_mount *mp);
void xfs_inode_shrinker_unregister(struct xfs_mount *mp);
diff --git a/fs/xfs/linux-2.6/xfs_trace.c b/fs/xfs/linux-2.6/xfs_trace.c
index d12be8470cb..88d25d4aa56 100644
--- a/fs/xfs/linux-2.6/xfs_trace.c
+++ b/fs/xfs/linux-2.6/xfs_trace.c
@@ -24,17 +24,13 @@
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
-#include "xfs_dir2.h"
#include "xfs_da_btree.h"
#include "xfs_bmap_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc_btree.h"
-#include "xfs_dir2_sf.h"
-#include "xfs_attr_sf.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_btree.h"
-#include "xfs_dmapi.h"
#include "xfs_mount.h"
#include "xfs_ialloc.h"
#include "xfs_itable.h"
diff --git a/fs/xfs/linux-2.6/xfs_trace.h b/fs/xfs/linux-2.6/xfs_trace.h
index 73d5aa11738..c657cdca2cd 100644
--- a/fs/xfs/linux-2.6/xfs_trace.h
+++ b/fs/xfs/linux-2.6/xfs_trace.h
@@ -124,7 +124,10 @@ DEFINE_EVENT(xfs_perag_class, name, \
unsigned long caller_ip), \
TP_ARGS(mp, agno, refcount, caller_ip))
DEFINE_PERAG_REF_EVENT(xfs_perag_get);
+DEFINE_PERAG_REF_EVENT(xfs_perag_get_reclaim);
DEFINE_PERAG_REF_EVENT(xfs_perag_put);
+DEFINE_PERAG_REF_EVENT(xfs_perag_set_reclaim);
+DEFINE_PERAG_REF_EVENT(xfs_perag_clear_reclaim);
TRACE_EVENT(xfs_attr_list_node_descend,
TP_PROTO(struct xfs_attr_list_context *ctx,
@@ -314,8 +317,6 @@ DEFINE_BUF_EVENT(xfs_buf_init);
DEFINE_BUF_EVENT(xfs_buf_free);
DEFINE_BUF_EVENT(xfs_buf_hold);
DEFINE_BUF_EVENT(xfs_buf_rele);
-DEFINE_BUF_EVENT(xfs_buf_pin);
-DEFINE_BUF_EVENT(xfs_buf_unpin);
DEFINE_BUF_EVENT(xfs_buf_iodone);
DEFINE_BUF_EVENT(xfs_buf_iorequest);
DEFINE_BUF_EVENT(xfs_buf_bawrite);
@@ -538,7 +539,7 @@ DEFINE_LOCK_EVENT(xfs_ilock_nowait);
DEFINE_LOCK_EVENT(xfs_ilock_demote);
DEFINE_LOCK_EVENT(xfs_iunlock);
-DECLARE_EVENT_CLASS(xfs_iget_class,
+DECLARE_EVENT_CLASS(xfs_inode_class,
TP_PROTO(struct xfs_inode *ip),
TP_ARGS(ip),
TP_STRUCT__entry(
@@ -554,16 +555,38 @@ DECLARE_EVENT_CLASS(xfs_iget_class,
__entry->ino)
)
-#define DEFINE_IGET_EVENT(name) \
-DEFINE_EVENT(xfs_iget_class, name, \
+#define DEFINE_INODE_EVENT(name) \
+DEFINE_EVENT(xfs_inode_class, name, \
TP_PROTO(struct xfs_inode *ip), \
TP_ARGS(ip))
-DEFINE_IGET_EVENT(xfs_iget_skip);
-DEFINE_IGET_EVENT(xfs_iget_reclaim);
-DEFINE_IGET_EVENT(xfs_iget_found);
-DEFINE_IGET_EVENT(xfs_iget_alloc);
-
-DECLARE_EVENT_CLASS(xfs_inode_class,
+DEFINE_INODE_EVENT(xfs_iget_skip);
+DEFINE_INODE_EVENT(xfs_iget_reclaim);
+DEFINE_INODE_EVENT(xfs_iget_reclaim_fail);
+DEFINE_INODE_EVENT(xfs_iget_hit);
+DEFINE_INODE_EVENT(xfs_iget_miss);
+
+DEFINE_INODE_EVENT(xfs_getattr);
+DEFINE_INODE_EVENT(xfs_setattr);
+DEFINE_INODE_EVENT(xfs_readlink);
+DEFINE_INODE_EVENT(xfs_alloc_file_space);
+DEFINE_INODE_EVENT(xfs_free_file_space);
+DEFINE_INODE_EVENT(xfs_readdir);
+#ifdef CONFIG_XFS_POSIX_ACL
+DEFINE_INODE_EVENT(xfs_check_acl);
+#endif
+DEFINE_INODE_EVENT(xfs_vm_bmap);
+DEFINE_INODE_EVENT(xfs_file_ioctl);
+DEFINE_INODE_EVENT(xfs_file_compat_ioctl);
+DEFINE_INODE_EVENT(xfs_ioctl_setattr);
+DEFINE_INODE_EVENT(xfs_file_fsync);
+DEFINE_INODE_EVENT(xfs_destroy_inode);
+DEFINE_INODE_EVENT(xfs_write_inode);
+DEFINE_INODE_EVENT(xfs_clear_inode);
+
+DEFINE_INODE_EVENT(xfs_dquot_dqalloc);
+DEFINE_INODE_EVENT(xfs_dquot_dqdetach);
+
+DECLARE_EVENT_CLASS(xfs_iref_class,
TP_PROTO(struct xfs_inode *ip, unsigned long caller_ip),
TP_ARGS(ip, caller_ip),
TP_STRUCT__entry(
@@ -588,20 +611,71 @@ DECLARE_EVENT_CLASS(xfs_inode_class,
(char *)__entry->caller_ip)
)
-#define DEFINE_INODE_EVENT(name) \
-DEFINE_EVENT(xfs_inode_class, name, \
+#define DEFINE_IREF_EVENT(name) \
+DEFINE_EVENT(xfs_iref_class, name, \
TP_PROTO(struct xfs_inode *ip, unsigned long caller_ip), \
TP_ARGS(ip, caller_ip))
-DEFINE_INODE_EVENT(xfs_ihold);
-DEFINE_INODE_EVENT(xfs_irele);
-DEFINE_INODE_EVENT(xfs_inode_pin);
-DEFINE_INODE_EVENT(xfs_inode_unpin);
-DEFINE_INODE_EVENT(xfs_inode_unpin_nowait);
+DEFINE_IREF_EVENT(xfs_ihold);
+DEFINE_IREF_EVENT(xfs_irele);
+DEFINE_IREF_EVENT(xfs_inode_pin);
+DEFINE_IREF_EVENT(xfs_inode_unpin);
+DEFINE_IREF_EVENT(xfs_inode_unpin_nowait);
+
+DECLARE_EVENT_CLASS(xfs_namespace_class,
+ TP_PROTO(struct xfs_inode *dp, struct xfs_name *name),
+ TP_ARGS(dp, name),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, dp_ino)
+ __dynamic_array(char, name, name->len)
+ ),
+ TP_fast_assign(
+ __entry->dev = VFS_I(dp)->i_sb->s_dev;
+ __entry->dp_ino = dp->i_ino;
+ memcpy(__get_str(name), name->name, name->len);
+ ),
+ TP_printk("dev %d:%d dp ino 0x%llx name %s",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->dp_ino,
+ __get_str(name))
+)
-/* the old xfs_itrace_entry tracer - to be replaced by s.th. in the VFS */
-DEFINE_INODE_EVENT(xfs_inode);
-#define xfs_itrace_entry(ip) \
- trace_xfs_inode(ip, _THIS_IP_)
+#define DEFINE_NAMESPACE_EVENT(name) \
+DEFINE_EVENT(xfs_namespace_class, name, \
+ TP_PROTO(struct xfs_inode *dp, struct xfs_name *name), \
+ TP_ARGS(dp, name))
+DEFINE_NAMESPACE_EVENT(xfs_remove);
+DEFINE_NAMESPACE_EVENT(xfs_link);
+DEFINE_NAMESPACE_EVENT(xfs_lookup);
+DEFINE_NAMESPACE_EVENT(xfs_create);
+DEFINE_NAMESPACE_EVENT(xfs_symlink);
+
+TRACE_EVENT(xfs_rename,
+ TP_PROTO(struct xfs_inode *src_dp, struct xfs_inode *target_dp,
+ struct xfs_name *src_name, struct xfs_name *target_name),
+ TP_ARGS(src_dp, target_dp, src_name, target_name),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, src_dp_ino)
+ __field(xfs_ino_t, target_dp_ino)
+ __dynamic_array(char, src_name, src_name->len)
+ __dynamic_array(char, target_name, target_name->len)
+ ),
+ TP_fast_assign(
+ __entry->dev = VFS_I(src_dp)->i_sb->s_dev;
+ __entry->src_dp_ino = src_dp->i_ino;
+ __entry->target_dp_ino = target_dp->i_ino;
+ memcpy(__get_str(src_name), src_name->name, src_name->len);
+ memcpy(__get_str(target_name), target_name->name, target_name->len);
+ ),
+ TP_printk("dev %d:%d src dp ino 0x%llx target dp ino 0x%llx"
+ " src name %s target name %s",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->src_dp_ino,
+ __entry->target_dp_ino,
+ __get_str(src_name),
+ __get_str(target_name))
+)
DECLARE_EVENT_CLASS(xfs_dquot_class,
TP_PROTO(struct xfs_dquot *dqp),
@@ -681,9 +755,6 @@ DEFINE_DQUOT_EVENT(xfs_dqrele);
DEFINE_DQUOT_EVENT(xfs_dqflush);
DEFINE_DQUOT_EVENT(xfs_dqflush_force);
DEFINE_DQUOT_EVENT(xfs_dqflush_done);
-/* not really iget events, but we re-use the format */
-DEFINE_IGET_EVENT(xfs_dquot_dqalloc);
-DEFINE_IGET_EVENT(xfs_dquot_dqdetach);
DECLARE_EVENT_CLASS(xfs_loggrant_class,
TP_PROTO(struct log *log, struct xlog_ticket *tic),
@@ -831,33 +902,29 @@ DECLARE_EVENT_CLASS(xfs_page_class,
__field(loff_t, size)
__field(unsigned long, offset)
__field(int, delalloc)
- __field(int, unmapped)
__field(int, unwritten)
),
TP_fast_assign(
- int delalloc = -1, unmapped = -1, unwritten = -1;
+ int delalloc = -1, unwritten = -1;
if (page_has_buffers(page))
- xfs_count_page_state(page, &delalloc,
- &unmapped, &unwritten);
+ xfs_count_page_state(page, &delalloc, &unwritten);
__entry->dev = inode->i_sb->s_dev;
__entry->ino = XFS_I(inode)->i_ino;
__entry->pgoff = page_offset(page);
__entry->size = i_size_read(inode);
__entry->offset = off;
__entry->delalloc = delalloc;
- __entry->unmapped = unmapped;
__entry->unwritten = unwritten;
),
TP_printk("dev %d:%d ino 0x%llx pgoff 0x%lx size 0x%llx offset %lx "
- "delalloc %d unmapped %d unwritten %d",
+ "delalloc %d unwritten %d",
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->ino,
__entry->pgoff,
__entry->size,
__entry->offset,
__entry->delalloc,
- __entry->unmapped,
__entry->unwritten)
)