aboutsummaryrefslogtreecommitdiff
path: root/fs/ceph
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ceph')
-rw-r--r--fs/ceph/addr.c105
-rw-r--r--fs/ceph/cache.h13
-rw-r--r--fs/ceph/inode.c2
-rw-r--r--fs/ceph/super.c1
-rw-r--r--fs/ceph/super.h1
5 files changed, 66 insertions, 56 deletions
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 752c421c9922..c7a0ab0d298b 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -76,18 +76,17 @@ static inline struct ceph_snap_context *page_snap_context(struct page *page)
* Dirty a page. Optimistically adjust accounting, on the assumption
* that we won't race with invalidate. If we do, readjust.
*/
-static int ceph_set_page_dirty(struct page *page)
+static bool ceph_dirty_folio(struct address_space *mapping, struct folio *folio)
{
- struct address_space *mapping = page->mapping;
struct inode *inode;
struct ceph_inode_info *ci;
struct ceph_snap_context *snapc;
- if (PageDirty(page)) {
- dout("%p set_page_dirty %p idx %lu -- already dirty\n",
- mapping->host, page, page->index);
- BUG_ON(!PagePrivate(page));
- return 0;
+ if (folio_test_dirty(folio)) {
+ dout("%p dirty_folio %p idx %lu -- already dirty\n",
+ mapping->host, folio, folio->index);
+ BUG_ON(!folio_get_private(folio));
+ return false;
}
inode = mapping->host;
@@ -111,56 +110,56 @@ static int ceph_set_page_dirty(struct page *page)
if (ci->i_wrbuffer_ref == 0)
ihold(inode);
++ci->i_wrbuffer_ref;
- dout("%p set_page_dirty %p idx %lu head %d/%d -> %d/%d "
+ dout("%p dirty_folio %p idx %lu head %d/%d -> %d/%d "
"snapc %p seq %lld (%d snaps)\n",
- mapping->host, page, page->index,
+ mapping->host, folio, folio->index,
ci->i_wrbuffer_ref-1, ci->i_wrbuffer_ref_head-1,
ci->i_wrbuffer_ref, ci->i_wrbuffer_ref_head,
snapc, snapc->seq, snapc->num_snaps);
spin_unlock(&ci->i_ceph_lock);
/*
- * Reference snap context in page->private. Also set
- * PagePrivate so that we get invalidatepage callback.
+ * Reference snap context in folio->private. Also set
+ * PagePrivate so that we get invalidate_folio callback.
*/
- BUG_ON(PagePrivate(page));
- attach_page_private(page, snapc);
+ BUG_ON(folio_get_private(folio));
+ folio_attach_private(folio, snapc);
- return ceph_fscache_set_page_dirty(page);
+ return ceph_fscache_dirty_folio(mapping, folio);
}
/*
- * If we are truncating the full page (i.e. offset == 0), adjust the
- * dirty page counters appropriately. Only called if there is private
- * data on the page.
+ * If we are truncating the full folio (i.e. offset == 0), adjust the
+ * dirty folio counters appropriately. Only called if there is private
+ * data on the folio.
*/
-static void ceph_invalidatepage(struct page *page, unsigned int offset,
- unsigned int length)
+static void ceph_invalidate_folio(struct folio *folio, size_t offset,
+ size_t length)
{
struct inode *inode;
struct ceph_inode_info *ci;
struct ceph_snap_context *snapc;
- inode = page->mapping->host;
+ inode = folio->mapping->host;
ci = ceph_inode(inode);
- if (offset != 0 || length != thp_size(page)) {
- dout("%p invalidatepage %p idx %lu partial dirty page %u~%u\n",
- inode, page, page->index, offset, length);
+ if (offset != 0 || length != folio_size(folio)) {
+ dout("%p invalidate_folio idx %lu partial dirty page %zu~%zu\n",
+ inode, folio->index, offset, length);
return;
}
- WARN_ON(!PageLocked(page));
- if (PagePrivate(page)) {
- dout("%p invalidatepage %p idx %lu full dirty page\n",
- inode, page, page->index);
+ WARN_ON(!folio_test_locked(folio));
+ if (folio_get_private(folio)) {
+ dout("%p invalidate_folio idx %lu full dirty page\n",
+ inode, folio->index);
- snapc = detach_page_private(page);
+ snapc = folio_detach_private(folio);
ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
ceph_put_snap_context(snapc);
}
- wait_on_page_fscache(page);
+ folio_wait_fscache(folio);
}
static int ceph_releasepage(struct page *page, gfp_t gfp)
@@ -559,6 +558,7 @@ static u64 get_writepages_data_length(struct inode *inode,
*/
static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
{
+ struct folio *folio = page_folio(page);
struct inode *inode = page->mapping->host;
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
@@ -593,8 +593,9 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
/* is this a partial page at end of file? */
if (page_off >= ceph_wbc.i_size) {
- dout("%p page eof %llu\n", page, ceph_wbc.i_size);
- page->mapping->a_ops->invalidatepage(page, 0, thp_size(page));
+ dout("folio at %lu beyond eof %llu\n", folio->index,
+ ceph_wbc.i_size);
+ folio_invalidate(folio, 0, folio_size(folio));
return 0;
}
@@ -606,7 +607,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
if (atomic_long_inc_return(&fsc->writeback_count) >
CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
- set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
+ fsc->write_congested = true;
req = ceph_osdc_new_request(osdc, &ci->i_layout, ceph_vino(inode), page_off, &len, 0, 1,
CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE, snapc,
@@ -666,7 +667,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
if (atomic_long_dec_return(&fsc->writeback_count) <
CONGESTION_OFF_THRESH(fsc->mount_options->congestion_kb))
- clear_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
+ fsc->write_congested = false;
return err;
}
@@ -678,6 +679,10 @@ static int ceph_writepage(struct page *page, struct writeback_control *wbc)
BUG_ON(!inode);
ihold(inode);
+ if (wbc->sync_mode == WB_SYNC_NONE &&
+ ceph_inode_to_client(inode)->write_congested)
+ return AOP_WRITEPAGE_ACTIVATE;
+
wait_on_page_fscache(page);
err = writepage_nounlock(page, wbc);
@@ -750,8 +755,7 @@ static void writepages_finish(struct ceph_osd_request *req)
if (atomic_long_dec_return(&fsc->writeback_count) <
CONGESTION_OFF_THRESH(
fsc->mount_options->congestion_kb))
- clear_bdi_congested(inode_to_bdi(inode),
- BLK_RW_ASYNC);
+ fsc->write_congested = false;
ceph_put_snap_context(detach_page_private(page));
end_page_writeback(page);
@@ -803,6 +807,10 @@ static int ceph_writepages_start(struct address_space *mapping,
bool done = false;
bool caching = ceph_is_cache_enabled(inode);
+ if (wbc->sync_mode == WB_SYNC_NONE &&
+ fsc->write_congested)
+ return 0;
+
dout("writepages_start %p (mode=%s)\n", inode,
wbc->sync_mode == WB_SYNC_NONE ? "NONE" :
(wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD"));
@@ -910,14 +918,16 @@ get_more_pages:
continue;
}
if (page_offset(page) >= ceph_wbc.i_size) {
- dout("%p page eof %llu\n",
- page, ceph_wbc.i_size);
+ struct folio *folio = page_folio(page);
+
+ dout("folio at %lu beyond eof %llu\n",
+ folio->index, ceph_wbc.i_size);
if ((ceph_wbc.size_stable ||
- page_offset(page) >= i_size_read(inode)) &&
- clear_page_dirty_for_io(page))
- mapping->a_ops->invalidatepage(page,
- 0, thp_size(page));
- unlock_page(page);
+ folio_pos(folio) >= i_size_read(inode)) &&
+ folio_clear_dirty_for_io(folio))
+ folio_invalidate(folio, 0,
+ folio_size(folio));
+ folio_unlock(folio);
continue;
}
if (strip_unit_end && (page->index > strip_unit_end)) {
@@ -997,11 +1007,8 @@ get_more_pages:
if (atomic_long_inc_return(&fsc->writeback_count) >
CONGESTION_ON_THRESH(
- fsc->mount_options->congestion_kb)) {
- set_bdi_congested(inode_to_bdi(inode),
- BLK_RW_ASYNC);
- }
-
+ fsc->mount_options->congestion_kb))
+ fsc->write_congested = true;
pages[locked_pages++] = page;
pvec.pages[i] = NULL;
@@ -1381,8 +1388,8 @@ const struct address_space_operations ceph_aops = {
.writepages = ceph_writepages_start,
.write_begin = ceph_write_begin,
.write_end = ceph_write_end,
- .set_page_dirty = ceph_set_page_dirty,
- .invalidatepage = ceph_invalidatepage,
+ .dirty_folio = ceph_dirty_folio,
+ .invalidate_folio = ceph_invalidate_folio,
.releasepage = ceph_releasepage,
.direct_IO = noop_direct_IO,
};
diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h
index 09164389fa66..b90f3016994d 100644
--- a/fs/ceph/cache.h
+++ b/fs/ceph/cache.h
@@ -54,12 +54,12 @@ static inline void ceph_fscache_unpin_writeback(struct inode *inode,
fscache_unpin_writeback(wbc, ceph_fscache_cookie(ceph_inode(inode)));
}
-static inline int ceph_fscache_set_page_dirty(struct page *page)
+static inline int ceph_fscache_dirty_folio(struct address_space *mapping,
+ struct folio *folio)
{
- struct inode *inode = page->mapping->host;
- struct ceph_inode_info *ci = ceph_inode(inode);
+ struct ceph_inode_info *ci = ceph_inode(mapping->host);
- return fscache_set_page_dirty(page, ceph_fscache_cookie(ci));
+ return fscache_dirty_folio(mapping, folio, ceph_fscache_cookie(ci));
}
static inline int ceph_begin_cache_operation(struct netfs_read_request *rreq)
@@ -133,9 +133,10 @@ static inline void ceph_fscache_unpin_writeback(struct inode *inode,
{
}
-static inline int ceph_fscache_set_page_dirty(struct page *page)
+static inline int ceph_fscache_dirty_folio(struct address_space *mapping,
+ struct folio *folio)
{
- return __set_page_dirty_nobuffers(page);
+ return filemap_dirty_folio(mapping, folio);
}
static inline bool ceph_is_cache_enabled(struct inode *inode)
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 460a4fbd7a65..d80911dc91c2 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -453,7 +453,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
struct ceph_inode_info *ci;
int i;
- ci = kmem_cache_alloc(ceph_inode_cachep, GFP_NOFS);
+ ci = alloc_inode_sb(sb, ceph_inode_cachep, GFP_NOFS);
if (!ci)
return NULL;
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 978463fa822c..e6987d295079 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -802,6 +802,7 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
fsc->have_copy_from2 = true;
atomic_long_set(&fsc->writeback_count, 0);
+ fsc->write_congested = false;
err = -ENOMEM;
/*
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 0b4b519682f1..a1ecc410a495 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -121,6 +121,7 @@ struct ceph_fs_client {
struct ceph_mds_client *mdsc;
atomic_long_t writeback_count;
+ bool write_congested;
struct workqueue_struct *inode_wq;
struct workqueue_struct *cap_wq;
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-03 13:07:56 +0000