diff options
Diffstat (limited to 'mm/page-writeback.c')
| -rw-r--r-- | mm/page-writeback.c | 49 |
1 files changed, 27 insertions, 22 deletions
diff --git a/mm/page-writeback.c b/mm/page-writeback.c index db00a66d8b84..d213ead95675 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -54,7 +54,7 @@ #define DIRTY_POLL_THRESH (128 >> (PAGE_SHIFT - 10)) /* - * Estimate write bandwidth at 200ms intervals. + * Estimate write bandwidth or update dirty limit at 200ms intervals. */ #define BANDWIDTH_INTERVAL max(HZ/5, 1) @@ -586,7 +586,7 @@ static void wb_domain_writeout_add(struct wb_domain *dom, /* First event after period switching was turned off? */ if (unlikely(!dom->period_time)) { /* - * We can race with other __bdi_writeout_inc calls here but + * We can race with other wb_domain_writeout_add calls here but * it does not cause any harm since the resulting time when * timer will fire and what is in writeout_period_time will be * roughly the same. @@ -917,7 +917,9 @@ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc, unsigned long thresh) { struct wb_domain *dom = dtc_dom(dtc); + struct bdi_writeback *wb = dtc->wb; u64 wb_thresh; + u64 wb_max_thresh; unsigned long numerator, denominator; unsigned long wb_min_ratio, wb_max_ratio; @@ -931,11 +933,28 @@ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc, wb_thresh *= numerator; wb_thresh = div64_ul(wb_thresh, denominator); - wb_min_max_ratio(dtc->wb, &wb_min_ratio, &wb_max_ratio); + wb_min_max_ratio(wb, &wb_min_ratio, &wb_max_ratio); wb_thresh += (thresh * wb_min_ratio) / (100 * BDI_RATIO_SCALE); - if (wb_thresh > (thresh * wb_max_ratio) / (100 * BDI_RATIO_SCALE)) - wb_thresh = thresh * wb_max_ratio / (100 * BDI_RATIO_SCALE); + wb_max_thresh = thresh * wb_max_ratio / (100 * BDI_RATIO_SCALE); + if (wb_thresh > wb_max_thresh) + wb_thresh = wb_max_thresh; + + /* + * With strictlimit flag, the wb_thresh is treated as + * a hard limit in balance_dirty_pages() and wb_position_ratio(). + * It's possible that wb_thresh is close to zero, not because + * the device is slow, but because it has been inactive. + * To prevent occasional writes from being blocked, we raise wb_thresh. + */ + if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { + unsigned long limit = hard_dirty_limit(dom, dtc->thresh); + u64 wb_scale_thresh = 0; + + if (limit > dtc->dirty) + wb_scale_thresh = (limit - dtc->dirty) / 100; + wb_thresh = max(wb_thresh, min(wb_scale_thresh, wb_max_thresh / 4)); + } return wb_thresh; } @@ -2724,8 +2743,6 @@ EXPORT_SYMBOL(noop_dirty_folio); /* * Helper function for set_page_dirty family. * - * Caller must hold folio_memcg_lock(). - * * NOTE: This relies on being atomic wrt interrupts. */ static void folio_account_dirtied(struct folio *folio, @@ -2758,7 +2775,6 @@ static void folio_account_dirtied(struct folio *folio, /* * Helper function for deaccounting dirty page without writeback. * - * Caller must hold folio_memcg_lock(). */ void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb) { @@ -2776,9 +2792,8 @@ void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb) * If warn is true, then emit a warning if the folio is not uptodate and has * not been truncated. * - * The caller must hold folio_memcg_lock(). It is the caller's - * responsibility to prevent the folio from being truncated while - * this function is in progress, although it may have been truncated + * It is the caller's responsibility to prevent the folio from being truncated + * while this function is in progress, although it may have been truncated * before this function is called. Most callers have the folio locked. * A few have the folio blocked from truncation through other means (e.g. * zap_vma_pages() has it mapped and is holding the page table lock). @@ -2822,14 +2837,10 @@ void __folio_mark_dirty(struct folio *folio, struct address_space *mapping, */ bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio) { - folio_memcg_lock(folio); - if (folio_test_set_dirty(folio)) { - folio_memcg_unlock(folio); + if (folio_test_set_dirty(folio)) return false; - } __folio_mark_dirty(folio, mapping, !folio_test_private(folio)); - folio_memcg_unlock(folio); if (mapping->host) { /* !PageAnon && !swapper_space */ @@ -2956,14 +2967,12 @@ void __folio_cancel_dirty(struct folio *folio) struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; - folio_memcg_lock(folio); wb = unlocked_inode_to_wb_begin(inode, &cookie); if (folio_test_clear_dirty(folio)) folio_account_cleaned(folio, wb); unlocked_inode_to_wb_end(inode, &cookie); - folio_memcg_unlock(folio); } else { folio_clear_dirty(folio); } @@ -3074,7 +3083,6 @@ bool __folio_end_writeback(struct folio *folio) struct address_space *mapping = folio_mapping(folio); bool ret; - folio_memcg_lock(folio); if (mapping && mapping_use_writeback_tags(mapping)) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); @@ -3105,7 +3113,6 @@ bool __folio_end_writeback(struct folio *folio) lruvec_stat_mod_folio(folio, NR_WRITEBACK, -nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); node_stat_mod_folio(folio, NR_WRITTEN, nr); - folio_memcg_unlock(folio); return ret; } @@ -3118,7 +3125,6 @@ void __folio_start_writeback(struct folio *folio, bool keep_write) VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); - folio_memcg_lock(folio); if (mapping && mapping_use_writeback_tags(mapping)) { XA_STATE(xas, &mapping->i_pages, folio_index(folio)); struct inode *inode = mapping->host; @@ -3159,7 +3165,6 @@ void __folio_start_writeback(struct folio *folio, bool keep_write) lruvec_stat_mod_folio(folio, NR_WRITEBACK, nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr); - folio_memcg_unlock(folio); access_ret = arch_make_folio_accessible(folio); /* |