return locked_inode_to_wb_and_lock_list(inode);
}
+struct inode_switch_wbs_context {
+ struct inode *inode;
+ struct bdi_writeback *new_wb;
+
+ struct rcu_head rcu_head;
+ struct work_struct work;
+};
+
+static void inode_switch_wbs_work_fn(struct work_struct *work)
+{
+ struct inode_switch_wbs_context *isw =
+ container_of(work, struct inode_switch_wbs_context, work);
+ struct inode *inode = isw->inode;
+ struct bdi_writeback *new_wb = isw->new_wb;
+
+ /*
+ * By the time control reaches here, RCU grace period has passed
+ * since I_WB_SWITCH assertion and all wb stat update transactions
+ * between unlocked_inode_to_wb_begin/end() are guaranteed to be
+ * synchronizing against mapping->tree_lock.
+ */
+ spin_lock(&inode->i_lock);
+
+ inode->i_wb_frn_winner = 0;
+ inode->i_wb_frn_avg_time = 0;
+ inode->i_wb_frn_history = 0;
+
+ /*
+ * Paired with load_acquire in unlocked_inode_to_wb_begin() and
+ * ensures that the new wb is visible if they see !I_WB_SWITCH.
+ */
+ smp_store_release(&inode->i_state, inode->i_state & ~I_WB_SWITCH);
+
+ spin_unlock(&inode->i_lock);
+
+ iput(inode);
+ wb_put(new_wb);
+ kfree(isw);
+}
+
+static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head)
+{
+ struct inode_switch_wbs_context *isw = container_of(rcu_head,
+ struct inode_switch_wbs_context, rcu_head);
+
+ /* needs to grab bh-unsafe locks, bounce to work item */
+ INIT_WORK(&isw->work, inode_switch_wbs_work_fn);
+ schedule_work(&isw->work);
+}
+
+/**
+ * inode_switch_wbs - change the wb association of an inode
+ * @inode: target inode
+ * @new_wb_id: ID of the new wb
+ *
+ * Switch @inode's wb association to the wb identified by @new_wb_id. The
+ * switching is performed asynchronously and may fail silently.
+ */
+static void inode_switch_wbs(struct inode *inode, int new_wb_id)
+{
+ struct backing_dev_info *bdi = inode_to_bdi(inode);
+ struct cgroup_subsys_state *memcg_css;
+ struct inode_switch_wbs_context *isw;
+
+ /* noop if seems to be already in progress */
+ if (inode->i_state & I_WB_SWITCH)
+ return;
+
+ isw = kzalloc(sizeof(*isw), GFP_ATOMIC);
+ if (!isw)
+ return;
+
+ /* find and pin the new wb */
+ rcu_read_lock();
+ memcg_css = css_from_id(new_wb_id, &memory_cgrp_subsys);
+ if (memcg_css)
+ isw->new_wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC);
+ rcu_read_unlock();
+ if (!isw->new_wb)
+ goto out_free;
+
+ /* while holding I_WB_SWITCH, no one else can update the association */
+ spin_lock(&inode->i_lock);
+ if (inode->i_state & (I_WB_SWITCH | I_FREEING) ||
+ inode_to_wb(inode) == isw->new_wb) {
+ spin_unlock(&inode->i_lock);
+ goto out_free;
+ }
+ inode->i_state |= I_WB_SWITCH;
+ spin_unlock(&inode->i_lock);
+
+ ihold(inode);
+ isw->inode = inode;
+
+ /*
+ * In addition to synchronizing among switchers, I_WB_SWITCH tells
+ * the RCU protected stat update paths to grab the mapping's
+ * tree_lock so that stat transfer can synchronize against them.
+ * Let's continue after I_WB_SWITCH is guaranteed to be visible.
+ */
+ call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn);
+ return;
+
+out_free:
+ if (isw->new_wb)
+ wb_put(isw->new_wb);
+ kfree(isw);
+}
+
/**
* wbc_attach_and_unlock_inode - associate wbc with target inode and unlock it
* @wbc: writeback_control of interest
* is okay. The main goal is avoiding keeping an inode on
* the wrong wb for an extended period of time.
*/
- if (hweight32(history) > WB_FRN_HIST_THR_SLOTS) {
- /* switch */
- max_id = 0;
- avg_time = 0;
- history = 0;
- }
+ if (hweight32(history) > WB_FRN_HIST_THR_SLOTS)
+ inode_switch_wbs(inode, max_id);
}
/*
return inode->i_wb;
}
+/**
+ * unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction
+ * @inode: target inode
+ * @lockedp: temp bool output param, to be passed to the end function
+ *
+ * The caller wants to access the wb associated with @inode but isn't
+ * holding inode->i_lock, mapping->tree_lock or wb->list_lock. This
+ * function determines the wb associated with @inode and ensures that the
+ * association doesn't change until the transaction is finished with
+ * unlocked_inode_to_wb_end().
+ *
+ * The caller must call unlocked_inode_to_wb_end() with *@lockdep
+ * afterwards and can't sleep during transaction. IRQ may or may not be
+ * disabled on return.
+ */
+static inline struct bdi_writeback *
+unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp)
+{
+ rcu_read_lock();
+
+ /*
+ * Paired with store_release in inode_switch_wb_work_fn() and
+ * ensures that we see the new wb if we see cleared I_WB_SWITCH.
+ */
+ *lockedp = smp_load_acquire(&inode->i_state) & I_WB_SWITCH;
+
+ if (unlikely(*lockedp))
+ spin_lock_irq(&inode->i_mapping->tree_lock);
+ return inode_to_wb(inode);
+}
+
+/**
+ * unlocked_inode_to_wb_end - end inode wb access transaction
+ * @inode: target inode
+ * @locked: *@lockedp from unlocked_inode_to_wb_begin()
+ */
+static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked)
+{
+ if (unlikely(locked))
+ spin_unlock_irq(&inode->i_mapping->tree_lock);
+
+ rcu_read_unlock();
+}
+
struct wb_iter {
int start_blkcg_id;
struct radix_tree_iter tree_iter;
return &inode_to_bdi(inode)->wb;
}
+static inline struct bdi_writeback *
+unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp)
+{
+ return inode_to_wb(inode);
+}
+
+static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked)
+{
+}
+
static inline void wb_memcg_offline(struct mem_cgroup *memcg)
{
}
*
* I_DIO_WAKEUP Never set. Only used as a key for wait_on_bit().
*
+ * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to
+ * synchronize competing switching instances and to tell
+ * wb stat updates to grab mapping->tree_lock. See
+ * inode_switch_wb_work_fn() for details.
+ *
* Q: What is the difference between I_WILL_FREE and I_FREEING?
*/
#define I_DIRTY_SYNC (1 << 0)
#define I_DIRTY_TIME (1 << 11)
#define __I_DIRTY_TIME_EXPIRED 12
#define I_DIRTY_TIME_EXPIRED (1 << __I_DIRTY_TIME_EXPIRED)
+#define I_WB_SWITCH (1 << 13)
#define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES)
#define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME)
struct file_ra_state;
struct user_struct;
struct writeback_control;
+struct bdi_writeback;
#ifndef CONFIG_NEED_MULTIPLE_NODES /* Don't use mapnrs, do it properly */
extern unsigned long max_mapnr;
void account_page_dirtied(struct page *page, struct address_space *mapping,
struct mem_cgroup *memcg);
void account_page_cleaned(struct page *page, struct address_space *mapping,
- struct mem_cgroup *memcg);
+ struct mem_cgroup *memcg, struct bdi_writeback *wb);
int set_page_dirty(struct page *page);
int set_page_dirty_lock(struct page *page);
void cancel_dirty_page(struct page *page);
* anyway will be cleared before returning page into buddy allocator.
*/
if (WARN_ON_ONCE(PageDirty(page)))
- account_page_cleaned(page, mapping, memcg);
+ account_page_cleaned(page, mapping, memcg,
+ inode_to_wb(mapping->host));
}
/**
* Caller must hold mem_cgroup_begin_page_stat().
*/
void account_page_cleaned(struct page *page, struct address_space *mapping,
- struct mem_cgroup *memcg)
+ struct mem_cgroup *memcg, struct bdi_writeback *wb)
{
if (mapping_cap_account_dirty(mapping)) {
mem_cgroup_dec_page_stat(memcg, MEM_CGROUP_STAT_DIRTY);
dec_zone_page_state(page, NR_FILE_DIRTY);
- dec_wb_stat(inode_to_wb(mapping->host), WB_RECLAIMABLE);
+ dec_wb_stat(wb, WB_RECLAIMABLE);
task_io_account_cancelled_write(PAGE_CACHE_SIZE);
}
}
struct address_space *mapping = page->mapping;
if (mapping && mapping_cap_account_dirty(mapping)) {
- struct bdi_writeback *wb = inode_to_wb(mapping->host);
+ struct inode *inode = mapping->host;
+ struct bdi_writeback *wb;
+ bool locked;
+ wb = unlocked_inode_to_wb_begin(inode, &locked);
current->nr_dirtied--;
dec_zone_page_state(page, NR_DIRTIED);
dec_wb_stat(wb, WB_DIRTIED);
+ unlocked_inode_to_wb_end(inode, locked);
}
}
EXPORT_SYMBOL(account_page_redirty);
struct address_space *mapping = page_mapping(page);
if (mapping_cap_account_dirty(mapping)) {
+ struct inode *inode = mapping->host;
+ struct bdi_writeback *wb;
struct mem_cgroup *memcg;
+ bool locked;
memcg = mem_cgroup_begin_page_stat(page);
+ wb = unlocked_inode_to_wb_begin(inode, &locked);
if (TestClearPageDirty(page))
- account_page_cleaned(page, mapping, memcg);
+ account_page_cleaned(page, mapping, memcg, wb);
+ unlocked_inode_to_wb_end(inode, locked);
mem_cgroup_end_page_stat(memcg);
} else {
ClearPageDirty(page);
int clear_page_dirty_for_io(struct page *page)
{
struct address_space *mapping = page_mapping(page);
- struct mem_cgroup *memcg;
int ret = 0;
BUG_ON(!PageLocked(page));
if (mapping && mapping_cap_account_dirty(mapping)) {
+ struct inode *inode = mapping->host;
+ struct bdi_writeback *wb;
+ struct mem_cgroup *memcg;
+ bool locked;
+
/*
* Yes, Virginia, this is indeed insane.
*
* exclusion.
*/
memcg = mem_cgroup_begin_page_stat(page);
+ wb = unlocked_inode_to_wb_begin(inode, &locked);
if (TestClearPageDirty(page)) {
mem_cgroup_dec_page_stat(memcg, MEM_CGROUP_STAT_DIRTY);
dec_zone_page_state(page, NR_FILE_DIRTY);
- dec_wb_stat(inode_to_wb(mapping->host), WB_RECLAIMABLE);
+ dec_wb_stat(wb, WB_RECLAIMABLE);
ret = 1;
}
+ unlocked_inode_to_wb_end(inode, locked);
mem_cgroup_end_page_stat(memcg);
return ret;
}
projects / GitHub / LineageOS / G12 / android_kernel_amlogic_linux-4.9.git / commitdiff