diff options
Diffstat (limited to 'mm')
-rw-r--r-- | mm/backing-dev.c | 17 | ||||
-rw-r--r-- | mm/memcontrol.c | 4 | ||||
-rw-r--r-- | mm/mempolicy.c | 9 | ||||
-rw-r--r-- | mm/page-writeback.c | 38 | ||||
-rw-r--r-- | mm/percpu.c | 36 | ||||
-rw-r--r-- | mm/shmem.c | 5 | ||||
-rw-r--r-- | mm/vmscan.c | 29 |
7 files changed, 84 insertions, 54 deletions
diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 660a87a22511..123bcef13e51 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -104,15 +104,13 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v) "b_more_io: %8lu\n" "bdi_list: %8u\n" "state: %8lx\n" - "wb_mask: %8lx\n" - "wb_list: %8u\n" - "wb_cnt: %8u\n", + "wb_list: %8u\n", (unsigned long) K(bdi_stat(bdi, BDI_WRITEBACK)), (unsigned long) K(bdi_stat(bdi, BDI_RECLAIMABLE)), K(bdi_thresh), K(dirty_thresh), K(background_thresh), nr_wb, nr_dirty, nr_io, nr_more_io, - !list_empty(&bdi->bdi_list), bdi->state, bdi->wb_mask, - !list_empty(&bdi->wb_list), bdi->wb_cnt); + !list_empty(&bdi->bdi_list), bdi->state, + !list_empty(&bdi->wb_list)); #undef K return 0; @@ -340,14 +338,13 @@ int bdi_has_dirty_io(struct backing_dev_info *bdi) static void bdi_flush_io(struct backing_dev_info *bdi) { struct writeback_control wbc = { - .bdi = bdi, .sync_mode = WB_SYNC_NONE, .older_than_this = NULL, .range_cyclic = 1, .nr_to_write = 1024, }; - writeback_inodes_wbc(&wbc); + writeback_inodes_wb(&bdi->wb, &wbc); } /* @@ -675,12 +672,6 @@ int bdi_init(struct backing_dev_info *bdi) bdi_wb_init(&bdi->wb, bdi); - /* - * Just one thread support for now, hard code mask and count - */ - bdi->wb_mask = 1; - bdi->wb_cnt = 1; - for (i = 0; i < NR_BDI_STAT_ITEMS; i++) { err = percpu_counter_init(&bdi->bdi_stat[i], 0); if (err) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c6ece0a57595..20a8193a7af8 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1370,7 +1370,7 @@ static void memcg_wakeup_oom(struct mem_cgroup *mem) static void memcg_oom_recover(struct mem_cgroup *mem) { - if (mem->oom_kill_disable && atomic_read(&mem->oom_lock)) + if (atomic_read(&mem->oom_lock)) memcg_wakeup_oom(mem); } @@ -3781,6 +3781,8 @@ static int mem_cgroup_oom_control_write(struct cgroup *cgrp, return -EINVAL; } mem->oom_kill_disable = val; + if (!val) + memcg_oom_recover(mem); cgroup_unlock(); return 0; } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 5d6fb339de03..5bc0a96beb51 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2094,7 +2094,7 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) NODEMASK_SCRATCH(scratch); if (!scratch) - return; + goto put_mpol; /* contextualize the tmpfs mount point mempolicy */ new = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask); if (IS_ERR(new)) @@ -2103,19 +2103,20 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) task_lock(current); ret = mpol_set_nodemask(new, &mpol->w.user_nodemask, scratch); task_unlock(current); - mpol_put(mpol); /* drop our ref on sb mpol */ if (ret) - goto put_free; + goto put_new; /* Create pseudo-vma that contains just the policy */ memset(&pvma, 0, sizeof(struct vm_area_struct)); pvma.vm_end = TASK_SIZE; /* policy covers entire file */ mpol_set_shared_policy(sp, &pvma, new); /* adds ref */ -put_free: +put_new: mpol_put(new); /* drop initial ref */ free_scratch: NODEMASK_SCRATCH_FREE(scratch); +put_mpol: + mpol_put(mpol); /* drop our incoming ref on sb mpol */ } } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index b289310e2c89..37498ef61548 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -495,7 +495,6 @@ static void balance_dirty_pages(struct address_space *mapping, for (;;) { struct writeback_control wbc = { - .bdi = bdi, .sync_mode = WB_SYNC_NONE, .older_than_this = NULL, .nr_to_write = write_chunk, @@ -537,7 +536,7 @@ static void balance_dirty_pages(struct address_space *mapping, * up. */ if (bdi_nr_reclaimable > bdi_thresh) { - writeback_inodes_wbc(&wbc); + writeback_inodes_wb(&bdi->wb, &wbc); pages_written += write_chunk - wbc.nr_to_write; get_dirty_limits(&background_thresh, &dirty_thresh, &bdi_thresh, bdi); @@ -597,7 +596,7 @@ static void balance_dirty_pages(struct address_space *mapping, (!laptop_mode && ((global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS)) > background_thresh))) - bdi_start_writeback(bdi, NULL, 0, 0); + bdi_start_background_writeback(bdi); } void set_page_dirty_balance(struct page *page, int page_mkwrite) @@ -705,9 +704,8 @@ void laptop_mode_timer_fn(unsigned long data) * We want to write everything out, not just down to the dirty * threshold */ - if (bdi_has_dirty_io(&q->backing_dev_info)) - bdi_start_writeback(&q->backing_dev_info, NULL, nr_pages, 0); + bdi_start_writeback(&q->backing_dev_info, nr_pages); } /* @@ -835,7 +833,6 @@ int write_cache_pages(struct address_space *mapping, pgoff_t done_index; int cycled; int range_whole = 0; - long nr_to_write = wbc->nr_to_write; pagevec_init(&pvec, 0); if (wbc->range_cyclic) { @@ -852,7 +849,22 @@ int write_cache_pages(struct address_space *mapping, if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; cycled = 1; /* ignore range_cyclic tests */ + + /* + * If this is a data integrity sync, cap the writeback to the + * current end of file. Any extension to the file that occurs + * after this is a new write and we don't need to write those + * pages out to fulfil our data integrity requirements. If we + * try to write them out, we can get stuck in this scan until + * the concurrent writer stops adding dirty pages and extending + * EOF. + */ + if (wbc->sync_mode == WB_SYNC_ALL && + wbc->range_end == LLONG_MAX) { + end = i_size_read(mapping->host) >> PAGE_CACHE_SHIFT; + } } + retry: done_index = index; while (!done && (index <= end)) { @@ -935,11 +947,10 @@ continue_unlock: done = 1; break; } - } + } - if (nr_to_write > 0) { - nr_to_write--; - if (nr_to_write == 0 && + if (wbc->nr_to_write > 0) { + if (--wbc->nr_to_write == 0 && wbc->sync_mode == WB_SYNC_NONE) { /* * We stop writing back only if we are @@ -970,11 +981,8 @@ continue_unlock: end = writeback_index - 1; goto retry; } - if (!wbc->no_nrwrite_index_update) { - if (wbc->range_cyclic || (range_whole && nr_to_write > 0)) - mapping->writeback_index = done_index; - wbc->nr_to_write = nr_to_write; - } + if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) + mapping->writeback_index = done_index; return ret; } diff --git a/mm/percpu.c b/mm/percpu.c index 39f7dfd59585..6470e7710231 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -229,8 +229,8 @@ static int __maybe_unused pcpu_page_idx(unsigned int cpu, int page_idx) return pcpu_unit_map[cpu] * pcpu_unit_pages + page_idx; } -static unsigned long __maybe_unused pcpu_chunk_addr(struct pcpu_chunk *chunk, - unsigned int cpu, int page_idx) +static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk, + unsigned int cpu, int page_idx) { return (unsigned long)chunk->base_addr + pcpu_unit_offsets[cpu] + (page_idx << PAGE_SHIFT); @@ -978,7 +978,32 @@ bool is_kernel_percpu_address(unsigned long addr) */ phys_addr_t per_cpu_ptr_to_phys(void *addr) { - if (pcpu_addr_in_first_chunk(addr)) { + void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr); + bool in_first_chunk = false; + unsigned long first_start, first_end; + unsigned int cpu; + + /* + * The following test on first_start/end isn't strictly + * necessary but will speed up lookups of addresses which + * aren't in the first chunk. + */ + first_start = pcpu_chunk_addr(pcpu_first_chunk, pcpu_first_unit_cpu, 0); + first_end = pcpu_chunk_addr(pcpu_first_chunk, pcpu_last_unit_cpu, + pcpu_unit_pages); + if ((unsigned long)addr >= first_start && + (unsigned long)addr < first_end) { + for_each_possible_cpu(cpu) { + void *start = per_cpu_ptr(base, cpu); + + if (addr >= start && addr < start + pcpu_unit_size) { + in_first_chunk = true; + break; + } + } + } + + if (in_first_chunk) { if ((unsigned long)addr < VMALLOC_START || (unsigned long)addr >= VMALLOC_END) return __pa(addr); @@ -1086,7 +1111,7 @@ struct pcpu_alloc_info * __init pcpu_build_alloc_info( static int group_map[NR_CPUS] __initdata; static int group_cnt[NR_CPUS] __initdata; const size_t static_size = __per_cpu_end - __per_cpu_start; - int group_cnt_max = 0, nr_groups = 1, nr_units = 0; + int nr_groups = 1, nr_units = 0; size_t size_sum, min_unit_size, alloc_size; int upa, max_upa, uninitialized_var(best_upa); /* units_per_alloc */ int last_allocs, group, unit; @@ -1096,7 +1121,7 @@ struct pcpu_alloc_info * __init pcpu_build_alloc_info( /* this function may be called multiple times */ memset(group_map, 0, sizeof(group_map)); - memset(group_cnt, 0, sizeof(group_map)); + memset(group_cnt, 0, sizeof(group_cnt)); /* * Determine min_unit_size, alloc_size and max_upa such that @@ -1130,7 +1155,6 @@ struct pcpu_alloc_info * __init pcpu_build_alloc_info( } group_map[cpu] = group; group_cnt[group]++; - group_cnt_max = max(group_cnt_max, group_cnt[group]); } /* diff --git a/mm/shmem.c b/mm/shmem.c index 7e5030ae18ff..f65f84062db5 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -764,10 +764,11 @@ done2: static int shmem_notify_change(struct dentry *dentry, struct iattr *attr) { struct inode *inode = dentry->d_inode; + loff_t newsize = attr->ia_size; int error; - if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) { - loff_t newsize = attr->ia_size; + if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE) + && newsize != inode->i_size) { struct page *page = NULL; if (newsize < inode->i_size) { diff --git a/mm/vmscan.c b/mm/vmscan.c index 915dceb487c1..9c7e57cc63a3 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1724,13 +1724,13 @@ static void shrink_zone(int priority, struct zone *zone, * If a zone is deemed to be full of pinned pages then just give it a light * scan then give up on it. */ -static int shrink_zones(int priority, struct zonelist *zonelist, +static bool shrink_zones(int priority, struct zonelist *zonelist, struct scan_control *sc) { enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask); struct zoneref *z; struct zone *zone; - int progress = 0; + bool all_unreclaimable = true; for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx, sc->nodemask) { @@ -1757,9 +1757,9 @@ static int shrink_zones(int priority, struct zonelist *zonelist, } shrink_zone(priority, zone, sc); - progress = 1; + all_unreclaimable = false; } - return progress; + return all_unreclaimable; } /* @@ -1782,7 +1782,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, struct scan_control *sc) { int priority; - unsigned long ret = 0; + bool all_unreclaimable; unsigned long total_scanned = 0; struct reclaim_state *reclaim_state = current->reclaim_state; unsigned long lru_pages = 0; @@ -1813,7 +1813,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, sc->nr_scanned = 0; if (!priority) disable_swap_token(); - ret = shrink_zones(priority, zonelist, sc); + all_unreclaimable = shrink_zones(priority, zonelist, sc); /* * Don't shrink slabs when reclaiming memory from * over limit cgroups @@ -1826,10 +1826,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, } } total_scanned += sc->nr_scanned; - if (sc->nr_reclaimed >= sc->nr_to_reclaim) { - ret = sc->nr_reclaimed; + if (sc->nr_reclaimed >= sc->nr_to_reclaim) goto out; - } /* * Try to write back as many pages as we just scanned. This @@ -1849,9 +1847,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, priority < DEF_PRIORITY - 2) congestion_wait(BLK_RW_ASYNC, HZ/10); } - /* top priority shrink_zones still had more to do? don't OOM, then */ - if (ret && scanning_global_lru(sc)) - ret = sc->nr_reclaimed; + out: /* * Now that we've scanned all the zones at this priority level, note @@ -1877,7 +1873,14 @@ out: delayacct_freepages_end(); put_mems_allowed(); - return ret; + if (sc->nr_reclaimed) + return sc->nr_reclaimed; + + /* top priority shrink_zones still had more to do? don't OOM, then */ + if (scanning_global_lru(sc) && !all_unreclaimable) + return 1; + + return 0; } unsigned long try_to_free_pages(struct zonelist *zonelist, int order, |