summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/block_dev.c11
-rw-r--r--fs/iomap.c18
-rw-r--r--fs/jbd2/journal.c9
-rw-r--r--fs/jbd2/transaction.c12
-rw-r--r--fs/ocfs2/cluster/heartbeat.c8
-rw-r--r--fs/ocfs2/cluster/tcp.c7
-rw-r--r--fs/proc/task_mmu.c8
-rw-r--r--fs/xfs/kmem.c12
-rw-r--r--fs/xfs/kmem.h2
-rw-r--r--fs/xfs/libxfs/xfs_btree.c2
-rw-r--r--fs/xfs/xfs_aops.c6
-rw-r--r--fs/xfs/xfs_buf.c8
-rw-r--r--fs/xfs/xfs_trans.c12
13 files changed, 69 insertions, 46 deletions
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 9ccabe3bb7de..0d435c794d76 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -103,12 +103,11 @@ void invalidate_bdev(struct block_device *bdev)
{
struct address_space *mapping = bdev->bd_inode->i_mapping;
- if (mapping->nrpages == 0)
- return;
-
- invalidate_bh_lrus();
- lru_add_drain_all(); /* make sure all lru add caches are flushed */
- invalidate_mapping_pages(mapping, 0, -1);
+ if (mapping->nrpages) {
+ invalidate_bh_lrus();
+ lru_add_drain_all(); /* make sure all lru add caches are flushed */
+ invalidate_mapping_pages(mapping, 0, -1);
+ }
/* 99% of the time, we don't need to flush the cleancache on the bdev.
* But, for the strange corners, lets be cautious
*/
diff --git a/fs/iomap.c b/fs/iomap.c
index 141c3cd55a8b..1c25ae30500e 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -887,16 +887,14 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
flags |= IOMAP_WRITE;
}
- if (mapping->nrpages) {
- ret = filemap_write_and_wait_range(mapping, start, end);
- if (ret)
- goto out_free_dio;
+ ret = filemap_write_and_wait_range(mapping, start, end);
+ if (ret)
+ goto out_free_dio;
- ret = invalidate_inode_pages2_range(mapping,
- start >> PAGE_SHIFT, end >> PAGE_SHIFT);
- WARN_ON_ONCE(ret);
- ret = 0;
- }
+ ret = invalidate_inode_pages2_range(mapping,
+ start >> PAGE_SHIFT, end >> PAGE_SHIFT);
+ WARN_ON_ONCE(ret);
+ ret = 0;
inode_dio_begin(inode);
@@ -951,7 +949,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
* one is a pretty crazy thing to do, so we don't support it 100%. If
* this invalidation fails, tough, the write still worked...
*/
- if (iov_iter_rw(iter) == WRITE && mapping->nrpages) {
+ if (iov_iter_rw(iter) == WRITE) {
int err = invalidate_inode_pages2_range(mapping,
start >> PAGE_SHIFT, end >> PAGE_SHIFT);
WARN_ON_ONCE(err);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 5adc2fb62b0f..c43fe83ee708 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -43,6 +43,7 @@
#include <linux/backing-dev.h>
#include <linux/bitops.h>
#include <linux/ratelimit.h>
+#include <linux/sched/mm.h>
#define CREATE_TRACE_POINTS
#include <trace/events/jbd2.h>
@@ -206,6 +207,14 @@ static int kjournald2(void *arg)
wake_up(&journal->j_wait_done_commit);
/*
+ * Make sure that no allocations from this kernel thread will ever
+ * recurse to the fs layer because we are responsible for the
+ * transaction commit and any fs involvement might get stuck waiting for
+ * the trasn. commit.
+ */
+ memalloc_nofs_save();
+
+ /*
* And now, wait forever for commit wakeup events.
*/
write_lock(&journal->j_state_lock);
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 5e659ee08d6a..9ee4832b6f8b 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -29,6 +29,7 @@
#include <linux/backing-dev.h>
#include <linux/bug.h>
#include <linux/module.h>
+#include <linux/sched/mm.h>
#include <trace/events/jbd2.h>
@@ -388,6 +389,11 @@ repeat:
rwsem_acquire_read(&journal->j_trans_commit_map, 0, 0, _THIS_IP_);
jbd2_journal_free_transaction(new_transaction);
+ /*
+ * Ensure that no allocations done while the transaction is open are
+ * going to recurse back to the fs layer.
+ */
+ handle->saved_alloc_context = memalloc_nofs_save();
return 0;
}
@@ -466,6 +472,7 @@ handle_t *jbd2__journal_start(journal_t *journal, int nblocks, int rsv_blocks,
trace_jbd2_handle_start(journal->j_fs_dev->bd_dev,
handle->h_transaction->t_tid, type,
line_no, nblocks);
+
return handle;
}
EXPORT_SYMBOL(jbd2__journal_start);
@@ -1760,6 +1767,11 @@ int jbd2_journal_stop(handle_t *handle)
if (handle->h_rsv_handle)
jbd2_journal_free_reserved(handle->h_rsv_handle);
free_and_exit:
+ /*
+ * Scope of the GFP_NOFS context is over here and so we can restore the
+ * original alloc context.
+ */
+ memalloc_nofs_restore(handle->saved_alloc_context);
jbd2_free_handle(handle);
return err;
}
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index f6e871760f8d..0da0332725aa 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -2242,13 +2242,13 @@ unlock:
spin_unlock(&o2hb_live_lock);
}
-static ssize_t o2hb_heartbeat_group_threshold_show(struct config_item *item,
+static ssize_t o2hb_heartbeat_group_dead_threshold_show(struct config_item *item,
char *page)
{
return sprintf(page, "%u\n", o2hb_dead_threshold);
}
-static ssize_t o2hb_heartbeat_group_threshold_store(struct config_item *item,
+static ssize_t o2hb_heartbeat_group_dead_threshold_store(struct config_item *item,
const char *page, size_t count)
{
unsigned long tmp;
@@ -2297,11 +2297,11 @@ static ssize_t o2hb_heartbeat_group_mode_store(struct config_item *item,
}
-CONFIGFS_ATTR(o2hb_heartbeat_group_, threshold);
+CONFIGFS_ATTR(o2hb_heartbeat_group_, dead_threshold);
CONFIGFS_ATTR(o2hb_heartbeat_group_, mode);
static struct configfs_attribute *o2hb_heartbeat_group_attrs[] = {
- &o2hb_heartbeat_group_attr_threshold,
+ &o2hb_heartbeat_group_attr_dead_threshold,
&o2hb_heartbeat_group_attr_mode,
NULL,
};
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 5b51c31c892d..8d779227370a 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -450,9 +450,8 @@ static struct o2net_sock_container *sc_alloc(struct o2nm_node *node)
INIT_WORK(&sc->sc_shutdown_work, o2net_shutdown_sc);
INIT_DELAYED_WORK(&sc->sc_keepalive_work, o2net_sc_send_keep_req);
- init_timer(&sc->sc_idle_timeout);
- sc->sc_idle_timeout.function = o2net_idle_timer;
- sc->sc_idle_timeout.data = (unsigned long)sc;
+ setup_timer(&sc->sc_idle_timeout, o2net_idle_timer,
+ (unsigned long)sc);
sclog(sc, "alloced\n");
@@ -956,7 +955,7 @@ static void o2net_sendpage(struct o2net_sock_container *sc,
mutex_lock(&sc->sc_send_lock);
ret = sc->sc_sock->ops->sendpage(sc->sc_sock,
virt_to_page(kmalloced_virt),
- (long)kmalloced_virt & ~PAGE_MASK,
+ offset_in_page(kmalloced_virt),
size, MSG_DONTWAIT);
mutex_unlock(&sc->sc_send_lock);
if (ret == size)
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 312578089544..f0c8b33d99b1 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -441,6 +441,7 @@ struct mem_size_stats {
unsigned long private_dirty;
unsigned long referenced;
unsigned long anonymous;
+ unsigned long lazyfree;
unsigned long anonymous_thp;
unsigned long shmem_thp;
unsigned long swap;
@@ -457,8 +458,11 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page,
int i, nr = compound ? 1 << compound_order(page) : 1;
unsigned long size = nr * PAGE_SIZE;
- if (PageAnon(page))
+ if (PageAnon(page)) {
mss->anonymous += size;
+ if (!PageSwapBacked(page) && !dirty && !PageDirty(page))
+ mss->lazyfree += size;
+ }
mss->resident += size;
/* Accumulate the size in pages that have been accessed. */
@@ -771,6 +775,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
"Private_Dirty: %8lu kB\n"
"Referenced: %8lu kB\n"
"Anonymous: %8lu kB\n"
+ "LazyFree: %8lu kB\n"
"AnonHugePages: %8lu kB\n"
"ShmemPmdMapped: %8lu kB\n"
"Shared_Hugetlb: %8lu kB\n"
@@ -789,6 +794,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
mss.private_dirty >> 10,
mss.referenced >> 10,
mss.anonymous >> 10,
+ mss.lazyfree >> 10,
mss.anonymous_thp >> 10,
mss.shmem_thp >> 10,
mss.shared_hugetlb >> 10,
diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c
index 70a5b55e0870..780fc8986dab 100644
--- a/fs/xfs/kmem.c
+++ b/fs/xfs/kmem.c
@@ -48,7 +48,7 @@ kmem_alloc(size_t size, xfs_km_flags_t flags)
void *
kmem_zalloc_large(size_t size, xfs_km_flags_t flags)
{
- unsigned noio_flag = 0;
+ unsigned nofs_flag = 0;
void *ptr;
gfp_t lflags;
@@ -60,17 +60,17 @@ kmem_zalloc_large(size_t size, xfs_km_flags_t flags)
* __vmalloc() will allocate data pages and auxillary structures (e.g.
* pagetables) with GFP_KERNEL, yet we may be under GFP_NOFS context
* here. Hence we need to tell memory reclaim that we are in such a
- * context via PF_MEMALLOC_NOIO to prevent memory reclaim re-entering
+ * context via PF_MEMALLOC_NOFS to prevent memory reclaim re-entering
* the filesystem here and potentially deadlocking.
*/
- if ((current->flags & PF_FSTRANS) || (flags & KM_NOFS))
- noio_flag = memalloc_noio_save();
+ if (flags & KM_NOFS)
+ nofs_flag = memalloc_nofs_save();
lflags = kmem_flags_convert(flags);
ptr = __vmalloc(size, lflags | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL);
- if ((current->flags & PF_FSTRANS) || (flags & KM_NOFS))
- memalloc_noio_restore(noio_flag);
+ if (flags & KM_NOFS)
+ memalloc_nofs_restore(nofs_flag);
return ptr;
}
diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h
index f0fc84fcaac2..d6ea520162b2 100644
--- a/fs/xfs/kmem.h
+++ b/fs/xfs/kmem.h
@@ -50,7 +50,7 @@ kmem_flags_convert(xfs_km_flags_t flags)
lflags = GFP_ATOMIC | __GFP_NOWARN;
} else {
lflags = GFP_KERNEL | __GFP_NOWARN;
- if ((current->flags & PF_FSTRANS) || (flags & KM_NOFS))
+ if (flags & KM_NOFS)
lflags &= ~__GFP_FS;
}
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index c3decedc9455..3059a3ec7ecb 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -2886,7 +2886,7 @@ xfs_btree_split_worker(
struct xfs_btree_split_args *args = container_of(work,
struct xfs_btree_split_args, work);
unsigned long pflags;
- unsigned long new_pflags = PF_FSTRANS;
+ unsigned long new_pflags = PF_MEMALLOC_NOFS;
/*
* we are in a transaction context here, but may also be doing work
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 61494295d92f..05eca126c688 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -189,7 +189,7 @@ xfs_setfilesize_trans_alloc(
* We hand off the transaction to the completion thread now, so
* clear the flag here.
*/
- current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
+ current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
return 0;
}
@@ -252,7 +252,7 @@ xfs_setfilesize_ioend(
* thus we need to mark ourselves as being in a transaction manually.
* Similarly for freeze protection.
*/
- current_set_flags_nested(&tp->t_pflags, PF_FSTRANS);
+ current_set_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
__sb_writers_acquired(VFS_I(ip)->i_sb, SB_FREEZE_FS);
/* we abort the update if there was an IO error */
@@ -1016,7 +1016,7 @@ xfs_do_writepage(
* Given that we do not allow direct reclaim to call us, we should
* never be called while in a filesystem transaction.
*/
- if (WARN_ON_ONCE(current->flags & PF_FSTRANS))
+ if (WARN_ON_ONCE(current->flags & PF_MEMALLOC_NOFS))
goto redirty;
/*
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index b6208728ba39..ca09061369cb 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -443,17 +443,17 @@ _xfs_buf_map_pages(
bp->b_addr = NULL;
} else {
int retried = 0;
- unsigned noio_flag;
+ unsigned nofs_flag;
/*
* vm_map_ram() will allocate auxillary structures (e.g.
* pagetables) with GFP_KERNEL, yet we are likely to be under
* GFP_NOFS context here. Hence we need to tell memory reclaim
- * that we are in such a context via PF_MEMALLOC_NOIO to prevent
+ * that we are in such a context via PF_MEMALLOC_NOFS to prevent
* memory reclaim re-entering the filesystem here and
* potentially deadlocking.
*/
- noio_flag = memalloc_noio_save();
+ nofs_flag = memalloc_nofs_save();
do {
bp->b_addr = vm_map_ram(bp->b_pages, bp->b_page_count,
-1, PAGE_KERNEL);
@@ -461,7 +461,7 @@ _xfs_buf_map_pages(
break;
vm_unmap_aliases();
} while (retried++ <= 1);
- memalloc_noio_restore(noio_flag);
+ memalloc_nofs_restore(nofs_flag);
if (!bp->b_addr)
return -ENOMEM;
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 70f42ea86dfb..f5969c8274fc 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -134,7 +134,7 @@ xfs_trans_reserve(
bool rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0;
/* Mark this thread as being in a transaction */
- current_set_flags_nested(&tp->t_pflags, PF_FSTRANS);
+ current_set_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
/*
* Attempt to reserve the needed disk blocks by decrementing
@@ -144,7 +144,7 @@ xfs_trans_reserve(
if (blocks > 0) {
error = xfs_mod_fdblocks(tp->t_mountp, -((int64_t)blocks), rsvd);
if (error != 0) {
- current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
+ current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
return -ENOSPC;
}
tp->t_blk_res += blocks;
@@ -221,7 +221,7 @@ undo_blocks:
tp->t_blk_res = 0;
}
- current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
+ current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
return error;
}
@@ -914,7 +914,7 @@ __xfs_trans_commit(
xfs_log_commit_cil(mp, tp, &commit_lsn, regrant);
- current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
+ current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
xfs_trans_free(tp);
/*
@@ -944,7 +944,7 @@ out_unreserve:
if (commit_lsn == -1 && !error)
error = -EIO;
}
- current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
+ current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
xfs_trans_free_items(tp, NULLCOMMITLSN, !!error);
xfs_trans_free(tp);
@@ -998,7 +998,7 @@ xfs_trans_cancel(
xfs_log_done(mp, tp->t_ticket, NULL, false);
/* mark this thread as no longer being in a transaction */
- current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
+ current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
xfs_trans_free_items(tp, NULLCOMMITLSN, dirty);
xfs_trans_free(tp);
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-02 03:37:16 +0000