diff options
55 files changed, 875 insertions, 435 deletions
@@ -2808,8 +2808,7 @@ S: Ottawa, Ontario S: Canada K2P 0X8 N: Mikael Pettersson -E: mikpe@it.uu.se -W: http://user.it.uu.se/~mikpe/linux/ +E: mikpelinux@gmail.com D: Miscellaneous fixes N: Reed H. Petty diff --git a/MAINTAINERS b/MAINTAINERS index e61c2e83fc2..c53fe955964 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1812,7 +1812,8 @@ S: Supported F: drivers/net/ethernet/broadcom/bnx2x/ BROADCOM BCM281XX/BCM11XXX ARM ARCHITECTURE -M: Christian Daudt <csd@broadcom.com> +M: Christian Daudt <bcm@fixthebug.org> +L: bcm-kernel-feedback-list@broadcom.com T: git git://git.github.com/broadcom/bcm11351 S: Maintained F: arch/arm/mach-bcm/ @@ -6595,7 +6596,7 @@ S: Obsolete F: drivers/net/wireless/prism54/ PROMISE SATA TX2/TX4 CONTROLLER LIBATA DRIVER -M: Mikael Pettersson <mikpe@it.uu.se> +M: Mikael Pettersson <mikpelinux@gmail.com> L: linux-ide@vger.kernel.org S: Maintained F: drivers/ata/sata_promise.* diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 8355c84b972..a9c606bb494 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1883,9 +1883,9 @@ static struct pmu pmu = { void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) { - userpg->cap_usr_time = 0; - userpg->cap_usr_time_zero = 0; - userpg->cap_usr_rdpmc = x86_pmu.attr_rdpmc; + userpg->cap_user_time = 0; + userpg->cap_user_time_zero = 0; + userpg->cap_user_rdpmc = x86_pmu.attr_rdpmc; userpg->pmc_width = x86_pmu.cntval_bits; if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) @@ -1894,13 +1894,13 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC)) return; - userpg->cap_usr_time = 1; + userpg->cap_user_time = 1; userpg->time_mult = this_cpu_read(cyc2ns); userpg->time_shift = CYC2NS_SCALE_FACTOR; userpg->time_offset = this_cpu_read(cyc2ns_offset) - now; if (sched_clock_stable && !check_tsc_disabled()) { - userpg->cap_usr_time_zero = 1; + userpg->cap_user_time_zero = 1; userpg->time_zero = this_cpu_read(cyc2ns_offset); } } diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 9db76c31b3c..f31a1655d1f 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -2325,6 +2325,7 @@ __init int intel_pmu_init(void) break; case 55: /* Atom 22nm "Silvermont" */ + case 77: /* Avoton "Silvermont" */ memcpy(hw_cache_event_ids, slm_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs, diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 8ed44589b0e..4118f9f6831 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -2706,14 +2706,14 @@ static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box) box->hrtimer.function = uncore_pmu_hrtimer; } -struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int cpu) +static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int node) { struct intel_uncore_box *box; int i, size; size = sizeof(*box) + type->num_shared_regs * sizeof(struct intel_uncore_extra_reg); - box = kzalloc_node(size, GFP_KERNEL, cpu_to_node(cpu)); + box = kzalloc_node(size, GFP_KERNEL, node); if (!box) return NULL; @@ -3031,7 +3031,7 @@ static int uncore_validate_group(struct intel_uncore_pmu *pmu, struct intel_uncore_box *fake_box; int ret = -EINVAL, n; - fake_box = uncore_alloc_box(pmu->type, smp_processor_id()); + fake_box = uncore_alloc_box(pmu->type, NUMA_NO_NODE); if (!fake_box) return -ENOMEM; @@ -3294,7 +3294,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id } type = pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)]; - box = uncore_alloc_box(type, 0); + box = uncore_alloc_box(type, NUMA_NO_NODE); if (!box) return -ENOMEM; @@ -3499,7 +3499,7 @@ static int uncore_cpu_prepare(int cpu, int phys_id) if (pmu->func_id < 0) pmu->func_id = j; - box = uncore_alloc_box(type, cpu); + box = uncore_alloc_box(type, cpu_to_node(cpu)); if (!box) return -ENOMEM; diff --git a/drivers/ata/sata_promise.c b/drivers/ata/sata_promise.c index 958ba2a420c..97f4acb54ad 100644 --- a/drivers/ata/sata_promise.c +++ b/drivers/ata/sata_promise.c @@ -2,7 +2,7 @@ * sata_promise.c - Promise SATA * * Maintained by: Tejun Heo <tj@kernel.org> - * Mikael Pettersson <mikpe@it.uu.se> + * Mikael Pettersson * Please ALWAYS copy linux-ide@vger.kernel.org * on emails. * diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index d2d95ff5353..edfa2515bc8 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -1189,6 +1189,7 @@ static int cciss_ioctl32_passthru(struct block_device *bdev, fmode_t mode, int err; u32 cp; + memset(&arg64, 0, sizeof(arg64)); err = 0; err |= copy_from_user(&arg64.LUN_info, &arg32->LUN_info, diff --git a/drivers/block/cpqarray.c b/drivers/block/cpqarray.c index 639d26b90b9..2b944038453 100644 --- a/drivers/block/cpqarray.c +++ b/drivers/block/cpqarray.c @@ -1193,6 +1193,7 @@ out_passthru: ida_pci_info_struct pciinfo; if (!arg) return -EINVAL; + memset(&pciinfo, 0, sizeof(pciinfo)); pciinfo.bus = host->pci_dev->bus->number; pciinfo.dev_fn = host->pci_dev->devfn; pciinfo.board_id = host->board_id; diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c index b1f8fc69023..60e84043aa3 100644 --- a/drivers/gpu/drm/i2c/tda998x_drv.c +++ b/drivers/gpu/drm/i2c/tda998x_drv.c @@ -707,8 +707,7 @@ tda998x_encoder_dpms(struct drm_encoder *encoder, int mode) reg_write(encoder, REG_VIP_CNTRL_2, priv->vip_cntrl_2); break; case DRM_MODE_DPMS_OFF: - /* disable audio and video ports */ - reg_write(encoder, REG_ENA_AP, 0x00); + /* disable video ports */ reg_write(encoder, REG_ENA_VP_0, 0x00); reg_write(encoder, REG_ENA_VP_1, 0x00); reg_write(encoder, REG_ENA_VP_2, 0x00); diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index b39f6f0b45f..0f12382aa35 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -498,7 +498,7 @@ struct cached_dev { */ atomic_t has_dirty; - struct ratelimit writeback_rate; + struct bch_ratelimit writeback_rate; struct delayed_work writeback_rate_update; /* @@ -507,10 +507,9 @@ struct cached_dev { */ sector_t last_read; - /* Number of writeback bios in flight */ - atomic_t in_flight; + /* Limit number of writeback bios in flight */ + struct semaphore in_flight; struct closure_with_timer writeback; - struct closure_waitlist writeback_wait; struct keybuf writeback_keys; diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c index 8010eed06a5..22d1ae72c28 100644 --- a/drivers/md/bcache/bset.c +++ b/drivers/md/bcache/bset.c @@ -926,28 +926,45 @@ struct bkey *bch_next_recurse_key(struct btree *b, struct bkey *search) /* Mergesort */ +static void sort_key_next(struct btree_iter *iter, + struct btree_iter_set *i) +{ + i->k = bkey_next(i->k); + + if (i->k == i->end) + *i = iter->data[--iter->used]; +} + static void btree_sort_fixup(struct btree_iter *iter) { while (iter->used > 1) { struct btree_iter_set *top = iter->data, *i = top + 1; - struct bkey *k; if (iter->used > 2 && btree_iter_cmp(i[0], i[1])) i++; - for (k = i->k; - k != i->end && bkey_cmp(top->k, &START_KEY(k)) > 0; - k = bkey_next(k)) - if (top->k > i->k) - __bch_cut_front(top->k, k); - else if (KEY_SIZE(k)) - bch_cut_back(&START_KEY(k), top->k); - - if (top->k < i->k || k == i->k) + if (bkey_cmp(top->k, &START_KEY(i->k)) <= 0) break; - heap_sift(iter, i - top, btree_iter_cmp); + if (!KEY_SIZE(i->k)) { + sort_key_next(iter, i); + heap_sift(iter, i - top, btree_iter_cmp); + continue; + } + + if (top->k > i->k) { + if (bkey_cmp(top->k, i->k) >= 0) + sort_key_next(iter, i); + else + bch_cut_front(top->k, i->k); + + heap_sift(iter, i - top, btree_iter_cmp); + } else { + /* can't happen because of comparison func */ + BUG_ON(!bkey_cmp(&START_KEY(top->k), &START_KEY(i->k))); + bch_cut_back(&START_KEY(i->k), top->k); + } } } diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index f9764e61978..f42fc7ed9cd 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -255,7 +255,7 @@ void bch_btree_node_read(struct btree *b) return; err: - bch_cache_set_error(b->c, "io error reading bucket %lu", + bch_cache_set_error(b->c, "io error reading bucket %zu", PTR_BUCKET_NR(b->c, &b->key, 0)); } @@ -612,7 +612,7 @@ static unsigned long bch_mca_scan(struct shrinker *shrink, return SHRINK_STOP; /* Return -1 if we can't do anything right now */ - if (sc->gfp_mask & __GFP_WAIT) + if (sc->gfp_mask & __GFP_IO) mutex_lock(&c->bucket_lock); else if (!mutex_trylock(&c->bucket_lock)) return -1; diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c index ba95ab84b2b..8435f81e5d8 100644 --- a/drivers/md/bcache/journal.c +++ b/drivers/md/bcache/journal.c @@ -153,7 +153,8 @@ int bch_journal_read(struct cache_set *c, struct list_head *list, bitmap_zero(bitmap, SB_JOURNAL_BUCKETS); pr_debug("%u journal buckets", ca->sb.njournal_buckets); - /* Read journal buckets ordered by golden ratio hash to quickly + /* + * Read journal buckets ordered by golden ratio hash to quickly * find a sequence of buckets with valid journal entries */ for (i = 0; i < ca->sb.njournal_buckets; i++) { @@ -166,18 +167,20 @@ int bch_journal_read(struct cache_set *c, struct list_head *list, goto bsearch; } - /* If that fails, check all the buckets we haven't checked + /* + * If that fails, check all the buckets we haven't checked * already */ pr_debug("falling back to linear search"); - for (l = 0; l < ca->sb.njournal_buckets; l++) { - if (test_bit(l, bitmap)) - continue; - + for (l = find_first_zero_bit(bitmap, ca->sb.njournal_buckets); + l < ca->sb.njournal_buckets; + l = find_next_zero_bit(bitmap, ca->sb.njournal_buckets, l + 1)) if (read_bucket(l)) goto bsearch; - } + + if (list_empty(list)) + continue; bsearch: /* Binary search */ m = r = find_next_bit(bitmap, ca->sb.njournal_buckets, l + 1); @@ -197,10 +200,12 @@ bsearch: r = m; } - /* Read buckets in reverse order until we stop finding more + /* + * Read buckets in reverse order until we stop finding more * journal entries */ - pr_debug("finishing up"); + pr_debug("finishing up: m %u njournal_buckets %u", + m, ca->sb.njournal_buckets); l = m; while (1) { @@ -228,9 +233,10 @@ bsearch: } } - c->journal.seq = list_entry(list->prev, - struct journal_replay, - list)->j.seq; + if (!list_empty(list)) + c->journal.seq = list_entry(list->prev, + struct journal_replay, + list)->j.seq; return 0; #undef read_bucket @@ -428,7 +434,7 @@ static void do_journal_discard(struct cache *ca) return; } - switch (atomic_read(&ja->discard_in_flight) == DISCARD_IN_FLIGHT) { + switch (atomic_read(&ja->discard_in_flight)) { case DISCARD_IN_FLIGHT: return; @@ -689,6 +695,7 @@ void bch_journal_meta(struct cache_set *c, struct closure *cl) if (cl) BUG_ON(!closure_wait(&w->wait, cl)); + closure_flush(&c->journal.io); __journal_try_write(c, true); } } diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 786a1a4f74d..71eb233b9ac 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -997,14 +997,17 @@ static void request_write(struct cached_dev *dc, struct search *s) } else { bch_writeback_add(dc); - if (s->op.flush_journal) { + if (bio->bi_rw & REQ_FLUSH) { /* Also need to send a flush to the backing device */ - s->op.cache_bio = bio_clone_bioset(bio, GFP_NOIO, - dc->disk.bio_split); + struct bio *flush = bio_alloc_bioset(0, GFP_NOIO, + dc->disk.bio_split); - bio->bi_size = 0; - bio->bi_vcnt = 0; - closure_bio_submit(bio, cl, s->d); + flush->bi_rw = WRITE_FLUSH; + flush->bi_bdev = bio->bi_bdev; + flush->bi_end_io = request_endio; + flush->bi_private = cl; + + closure_bio_submit(flush, cl, s->d); } else { s->op.cache_bio = bio; } diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index 4fe6ab2fbe2..924dcfdae11 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -223,8 +223,13 @@ STORE(__cached_dev) } if (attr == &sysfs_label) { - /* note: endlines are preserved */ - memcpy(dc->sb.label, buf, SB_LABEL_SIZE); + if (size > SB_LABEL_SIZE) + return -EINVAL; + memcpy(dc->sb.label, buf, size); + if (size < SB_LABEL_SIZE) + dc->sb.label[size] = '\0'; + if (size && dc->sb.label[size - 1] == '\n') + dc->sb.label[size - 1] = '\0'; bch_write_bdev_super(dc, NULL); if (dc->disk.c) { memcpy(dc->disk.c->uuids[dc->disk.id].label, diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c index 98eb81159a2..420dad545c7 100644 --- a/drivers/md/bcache/util.c +++ b/drivers/md/bcache/util.c @@ -190,7 +190,16 @@ void bch_time_stats_update(struct time_stats *stats, uint64_t start_time) stats->last = now ?: 1; } -unsigned bch_next_delay(struct ratelimit *d, uint64_t done) +/** + * bch_next_delay() - increment @d by the amount of work done, and return how + * long to delay until the next time to do some work. + * + * @d - the struct bch_ratelimit to update + * @done - the amount of work done, in arbitrary units + * + * Returns the amount of time to delay by, in jiffies + */ +uint64_t bch_next_delay(struct bch_ratelimit *d, uint64_t done) { uint64_t now = local_clock(); diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h index 1ae2a73ad85..ea345c6896f 100644 --- a/drivers/md/bcache/util.h +++ b/drivers/md/bcache/util.h @@ -450,17 +450,23 @@ read_attribute(name ## _last_ ## frequency_units) (ewma) >> factor; \ }) -struct ratelimit { +struct bch_ratelimit { + /* Next time we want to do some work, in nanoseconds */ uint64_t next; + + /* + * Rate at which we want to do work, in units per nanosecond + * The units here correspond to the units passed to bch_next_delay() + */ unsigned rate; }; -static inline void ratelimit_reset(struct ratelimit *d) +static inline void bch_ratelimit_reset(struct bch_ratelimit *d) { d->next = local_clock(); } -unsigned bch_next_delay(struct ratelimit *d, uint64_t done); +uint64_t bch_next_delay(struct bch_ratelimit *d, uint64_t done); #define __DIV_SAFE(n, d, zero) \ ({ \ diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index 22cbff55162..ba3ee48320f 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -94,11 +94,15 @@ static void update_writeback_rate(struct work_struct *work) static unsigned writeback_delay(struct cached_dev *dc, unsigned sectors) { + uint64_t ret; + if (atomic_read(&dc->disk.detaching) || !dc->writeback_percent) return 0; - return bch_next_delay(&dc->writeback_rate, sectors * 10000000ULL); + ret = bch_next_delay(&dc->writeback_rate, sectors * 10000000ULL); + + return min_t(uint64_t, ret, HZ); } /* Background writeback */ @@ -208,7 +212,7 @@ normal_refill: up_write(&dc->writeback_lock); - ratelimit_reset(&dc->writeback_rate); + bch_ratelimit_reset(&dc->writeback_rate); /* Punt to workqueue only so we don't recurse and blow the stack */ continue_at(cl, read_dirty, dirty_wq); @@ -318,9 +322,7 @@ static void write_dirty_finish(struct closure *cl) } bch_keybuf_del(&dc->writeback_keys, w); - atomic_dec_bug(&dc->in_flight); - - closure_wake_up(&dc->writeback_wait); + up(&dc->in_flight); closure_return_with_destructor(cl, dirty_io_destructor); } @@ -349,7 +351,7 @@ static void write_dirty(struct closure *cl) closure_bio_submit(&io->bio, cl, &io->dc->disk); - continue_at(cl, write_dirty_finish, dirty_wq); + continue_at(cl, write_dirty_finish, system_wq); } static void read_dirty_endio(struct bio *bio, int error) @@ -369,7 +371,7 @@ static void read_dirty_submit(struct closure *cl) closure_bio_submit(&io->bio, cl, &io->dc->disk); - continue_at(cl, write_dirty, dirty_wq); + continue_at(cl, write_dirty, system_wq); } static void read_dirty(struct closure *cl) @@ -394,12 +396,8 @@ static void read_dirty(struct closure *cl) if (delay > 0 && (KEY_START(&w->key) != dc->last_read || - jiffies_to_msecs(delay) > 50)) { - w->private = NULL; - - closure_delay(&dc->writeback, delay); - continue_at(cl, read_dirty, dirty_wq); - } + jiffies_to_msecs(delay) > 50)) + delay = schedule_timeout_uninterruptible(delay); dc->last_read = KEY_OFFSET(&w->key); @@ -424,15 +422,10 @@ static void read_dirty(struct closure *cl) trace_bcache_writeback(&w->key); - closure_call(&io->cl, read_dirty_submit, NULL, &dc->disk.cl); + down(&dc->in_flight); + closure_call(&io->cl, read_dirty_submit, NULL, cl); delay = writeback_delay(dc, KEY_SIZE(&w->key)); - - atomic_inc(&dc->in_flight); - - if (!closure_wait_event(&dc->writeback_wait, cl, - atomic_read(&dc->in_flight) < 64)) - continue_at(cl, read_dirty, dirty_wq); } if (0) { @@ -442,7 +435,11 @@ err: bch_keybuf_del(&dc->writeback_keys, w); } - refill_dirty(cl); + /* + * Wait for outstanding writeback IOs to finish (and keybuf slots to be + * freed) before refilling again + */ + continue_at(cl, refill_dirty, dirty_wq); } /* Init */ @@ -484,6 +481,7 @@ void bch_sectors_dirty_init(struct cached_dev *dc) void bch_cached_dev_writeback_init(struct cached_dev *dc) { + sema_init(&dc->in_flight, 64); closure_init_unlocked(&dc->writeback); init_rwsem(&dc->writeback_lock); @@ -513,7 +511,7 @@ void bch_writeback_exit(void) int __init bch_writeback_init(void) { - dirty_wq = create_singlethread_workqueue("bcache_writeback"); + dirty_wq = create_workqueue("bcache_writeback"); if (!dirty_wq) return -ENOMEM; @@ -917,8 +917,8 @@ void bio_copy_data(struct bio *dst, struct bio *src) src_p = kmap_atomic(src_bv->bv_page); dst_p = kmap_atomic(dst_bv->bv_page); - memcpy(dst_p + dst_bv->bv_offset, - src_p + src_bv->bv_offset, + memcpy(dst_p + dst_offset, + src_p + src_offset, bytes); kunmap_atomic(dst_p); diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 121da2dc3be..d4e81e4a9b0 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1924,7 +1924,7 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err) { int tmp, hangup_needed = 0; struct ocfs2_super *osb = NULL; - char nodestr[8]; + char nodestr[12]; trace_ocfs2_dismount_volume(sb); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 60e95872da2..ecc82b37c4c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -53,23 +53,6 @@ struct mem_cgroup_reclaim_cookie { unsigned int generation; }; -enum mem_cgroup_filter_t { - VISIT, /* visit current node */ - SKIP, /* skip the current node and continue traversal */ - SKIP_TREE, /* skip the whole subtree and continue traversal */ -}; - -/* - * mem_cgroup_filter_t predicate might instruct mem_cgroup_iter_cond how to - * iterate through the hierarchy tree. Each tree element is checked by the - * predicate before it is returned by the iterator. If a filter returns - * SKIP or SKIP_TREE then the iterator code continues traversal (with the - * next node down the hierarchy or the next node that doesn't belong under the - * memcg's subtree). - */ -typedef enum mem_cgroup_filter_t -(*mem_cgroup_iter_filter)(struct mem_cgroup *memcg, struct mem_cgroup *root); - #ifdef CONFIG_MEMCG /* * All "charge" functions with gfp_mask should use GFP_KERNEL or @@ -137,18 +120,9 @@ mem_cgroup_prepare_migration(struct page *page, struct page *newpage, extern void mem_cgroup_end_migration(struct mem_cgroup *memcg, struct page *oldpage, struct page *newpage, bool migration_ok); -struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root, - struct mem_cgroup *prev, - struct mem_cgroup_reclaim_cookie *reclaim, - mem_cgroup_iter_filter cond); - -static inline struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, - struct mem_cgroup *prev, - struct mem_cgroup_reclaim_cookie *reclaim) -{ - return mem_cgroup_iter_cond(root, prev, reclaim, NULL); -} - +struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, + struct mem_cgroup *, + struct mem_cgroup_reclaim_cookie *); void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); /* @@ -260,9 +234,9 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, mem_cgroup_update_page_stat(page, idx, -1); } -enum mem_cgroup_filter_t -mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, - struct mem_cgroup *root); +unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, + gfp_t gfp_mask, + unsigned long *total_scanned); void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx); static inline void mem_cgroup_count_vm_event(struct mm_struct *mm, @@ -376,15 +350,6 @@ static inline void mem_cgroup_end_migration(struct mem_cgroup *memcg, struct page *oldpage, struct page *newpage, bool migration_ok) { } -static inline struct mem_cgroup * -mem_cgroup_iter_cond(struct mem_cgroup *root, - struct mem_cgroup *prev, - struct mem_cgroup_reclaim_cookie *reclaim, - mem_cgroup_iter_filter cond) -{ - /* first call must return non-NULL, second return NULL */ - return (struct mem_cgroup *)(unsigned long)!prev; -} static inline struct mem_cgroup * mem_cgroup_iter(struct mem_cgroup *root, @@ -471,11 +436,11 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, } static inline -enum mem_cgroup_filter_t -mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, - struct mem_cgroup *root) +unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, + gfp_t gfp_mask, + unsigned long *total_scanned) { - return VISIT; + return 0; } static inline void mem_cgroup_split_huge_fixup(struct page *head) diff --git a/include/linux/smp.h b/include/linux/smp.h index cfb7ca094b3..731f5237d5f 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -155,6 +155,12 @@ smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, static inline void kick_all_cpus_sync(void) { } +static inline void __smp_call_function_single(int cpuid, + struct call_single_data *data, int wait) +{ + on_each_cpu(data->func, data->info, wait); +} + #endif /* !SMP */ /* diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 40a1fb80739..009a655a5d3 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -380,10 +380,13 @@ struct perf_event_mmap_page { union { __u64 capabilities; struct { - __u64 cap_usr_time : 1, - cap_usr_rdpmc : 1, - cap_usr_time_zero : 1, - cap_____res : 61; + __u64 cap_bit0 : 1, /* Always 0, deprecated, see commit 860f085b74e9 */ + cap_bit0_is_deprecated : 1, /* Always 1, signals that bit 0 is zero */ + + cap_user_rdpmc : 1, /* The RDPMC instruction can be used to read counts */ + cap_user_time : 1, /* The time_* fields are used */ + cap_user_time_zero : 1, /* The time_zero field is used */ + cap_____res : 59; }; }; @@ -442,12 +445,13 @@ struct perf_event_mmap_page { * ((rem * time_mult) >> time_shift); */ __u64 time_zero; + __u32 size; /* Header size up to __reserved[] fields. */ /* * Hole for extension of the self monitor capabilities */ - __u64 __reserved[119]; /* align to 1k */ + __u8 __reserved[118*8+4]; /* align to 1k. */ /* * Control data for the mmap() data buffer. @@ -528,6 +532,7 @@ enum perf_event_type { * u64 len; * u64 pgoff; * char filename[]; + * struct sample_id sample_id; * }; */ PERF_RECORD_MMAP = 1, diff --git a/ipc/msg.c b/ipc/msg.c index b0d541d4267..9e4310c546a 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -165,6 +165,15 @@ static inline void msg_rmid(struct ipc_namespace *ns, struct msg_queue *s) ipc_rmid(&msg_ids(ns), &s->q_perm); } +static void msg_rcu_free(struct rcu_head *head) +{ + struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu); + struct msg_queue *msq = ipc_rcu_to_struct(p); + + security_msg_queue_free(msq); + ipc_rcu_free(head); +} + /** * newque - Create a new msg queue * @ns: namespace @@ -189,15 +198,14 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params) msq->q_perm.security = NULL; retval = security_msg_queue_alloc(msq); if (retval) { - ipc_rcu_putref(msq); + ipc_rcu_putref(msq, ipc_rcu_free); return retval; } /* ipc_addid() locks msq upon success. */ id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni); if (id < 0) { - security_msg_queue_free(msq); - ipc_rcu_putref(msq); + ipc_rcu_putref(msq, msg_rcu_free); return id; } @@ -276,8 +284,7 @@ static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) free_msg(msg); } atomic_sub(msq->q_cbytes, &ns->msg_bytes); - security_msg_queue_free(msq); - ipc_rcu_putref(msq); + ipc_rcu_putref(msq, msg_rcu_free); } /* @@ -717,7 +724,7 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext, rcu_read_lock(); ipc_lock_object(&msq->q_perm); - ipc_rcu_putref(msq); + ipc_rcu_putref(msq, ipc_rcu_free); if (msq->q_perm.deleted) { err = -EIDRM; goto out_unlock0; diff --git a/ipc/sem.c b/ipc/sem.c index 69b6a21f384..19c8b980d1f 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -243,6 +243,15 @@ static void merge_queues(struct sem_array *sma) } } +static void sem_rcu_free(struct rcu_head *head) +{ + struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu); + struct sem_array *sma = ipc_rcu_to_struct(p); + + security_sem_free(sma); + ipc_rcu_free(head); +} + /* * If the request contains only one semaphore operation, and there are * no complex transactions pending, lock only the semaphore involved. @@ -374,12 +383,7 @@ static inline struct sem_array *sem_obtain_object_check(struct ipc_namespace *ns static inline void sem_lock_and_putref(struct sem_array *sma) { sem_lock(sma, NULL, -1); - ipc_rcu_putref(sma); -} - -static inline void sem_putref(struct sem_array *sma) -{ - ipc_rcu_putref(sma); + ipc_rcu_putref(sma, ipc_rcu_free); } static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s) @@ -458,14 +462,13 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params) sma->sem_perm.security = NULL; retval = security_sem_alloc(sma); if (retval) { - ipc_rcu_putref(sma); + ipc_rcu_putref(sma, ipc_rcu_free); return retval; } id = ipc_addid(&sem_ids(ns), &sma->sem_perm, ns->sc_semmni); if (id < 0) { - security_sem_free(sma); - ipc_rcu_putref(sma); + ipc_rcu_putref(sma, sem_rcu_free); return id; } ns->used_sems += nsems; @@ -1047,8 +1050,7 @@ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) wake_up_sem_queue_do(&tasks); ns->used_sems -= sma->sem_nsems; - security_sem_free(sma); - ipc_rcu_putref(sma); + ipc_rcu_putref(sma, sem_rcu_free); } static unsigned long copy_semid_to_user(void __user *buf, struct semid64_ds *in, int version) @@ -1292,7 +1294,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, rcu_read_unlock(); sem_io = ipc_alloc(sizeof(ushort)*nsems); if(sem_io == NULL) { - sem_putref(sma); + ipc_rcu_putref(sma, ipc_rcu_free); return -ENOMEM; } @@ -1328,20 +1330,20 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, if(nsems > SEMMSL_FAST) { sem_io = ipc_alloc(sizeof(ushort)*nsems); if(sem_io == NULL) { - sem_putref(sma); + ipc_rcu_putref(sma, ipc_rcu_free); return -ENOMEM; } } if (copy_from_user (sem_io, p, nsems*sizeof(ushort))) { - sem_putref(sma); + ipc_rcu_putref(sma, ipc_rcu_free); err = -EFAULT; goto out_free; } for (i = 0; i < nsems; i++) { if (sem_io[i] > SEMVMX) { - sem_putref(sma); + ipc_rcu_putref(sma, ipc_rcu_free); err = -ERANGE; goto out_free; } @@ -1629,7 +1631,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid) /* step 2: allocate new undo structure */ new = kzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL); if (!new) { - sem_putref(sma); + ipc_rcu_putref(sma, ipc_rcu_free); return ERR_PTR(-ENOMEM); } diff --git a/ipc/shm.c b/ipc/shm.c index 2821cdf93ad..d69739610fd 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -167,6 +167,15 @@ static inline void shm_lock_by_ptr(struct shmid_kernel *ipcp) ipc_lock_object(&ipcp->shm_perm); } +static void shm_rcu_free(struct rcu_head *head) +{ + struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu); + struct shmid_kernel *shp = ipc_rcu_to_struct(p); + + security_shm_free(shp); + ipc_rcu_free(head); +} + static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s) { ipc_rmid(&shm_ids(ns), &s->shm_perm); @@ -208,8 +217,7 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp) user_shm_unlock(file_inode(shp->shm_file)->i_size, shp->mlock_user); fput (shp->shm_file); - security_shm_free(shp); - ipc_rcu_putref(shp); + ipc_rcu_putref(shp, shm_rcu_free); } /* @@ -497,7 +505,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) shp->shm_perm.security = NULL; error = security_shm_alloc(shp); if (error) { - ipc_rcu_putref(shp); + ipc_rcu_putref(shp, ipc_rcu_free); return error; } @@ -566,8 +574,7 @@ no_id: user_shm_unlock(size, shp->mlock_user); fput(file); no_file: - security_shm_free(shp); - ipc_rcu_putref(shp); + ipc_rcu_putref(shp, shm_rcu_free); return error; } diff --git a/ipc/util.c b/ipc/util.c index e829da9ed01..fdb8ae74077 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -474,11 +474,6 @@ void ipc_free(void* ptr, int size) kfree(ptr); } -struct ipc_rcu { - struct rcu_head rcu; - atomic_t refcount; -} ____cacheline_aligned_in_smp; - /** * ipc_rcu_alloc - allocate ipc and rcu space * @size: size desired @@ -505,27 +500,24 @@ int ipc_rcu_getref(void *ptr) return atomic_inc_not_zero(&p->refcount); } -/** - * ipc_schedule_free - free ipc + rcu space - * @head: RCU callback structure for queued work - */ -static void ipc_schedule_free(struct rcu_head *head) -{ - vfree(container_of(head, struct ipc_rcu, rcu)); -} - -void ipc_rcu_putref(void *ptr) +void ipc_rcu_putref(void *ptr, void (*func)(struct rcu_head *head)) { struct ipc_rcu *p = ((struct ipc_rcu *)ptr) - 1; if (!atomic_dec_and_test(&p->refcount)) return; - if (is_vmalloc_addr(ptr)) { - call_rcu(&p->rcu, ipc_schedule_free); - } else { - kfree_rcu(p, rcu); - } + call_rcu(&p->rcu, func); +} + +void ipc_rcu_free(struct rcu_head *head) +{ + struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu); + + if (is_vmalloc_addr(p)) + vfree(p); + else + kfree(p); } /** diff --git a/ipc/util.h b/ipc/util.h index c5f3338ba1f..f2f5036f2ee 100644 --- a/ipc/util.h +++ b/ipc/util.h @@ -47,6 +47,13 @@ static inline void msg_exit_ns(struct ipc_namespace *ns) { } static inline void shm_exit_ns(struct ipc_namespace *ns) { } #endif +struct ipc_rcu { + struct rcu_head rcu; + atomic_t refcount; +} ____cacheline_aligned_in_smp; + +#define ipc_rcu_to_struct(p) ((void *)(p+1)) + /* * Structure that holds the parameters needed by the ipc operations * (see after) @@ -120,7 +127,8 @@ void ipc_free(void* ptr, int size); */ void* ipc_rcu_alloc(int size); int ipc_rcu_getref(void *ptr); -void ipc_rcu_putref(void *ptr); +void ipc_rcu_putref(void *ptr, void (*func)(struct rcu_head *head)); +void ipc_rcu_free(struct rcu_head *head); struct kern_ipc_perm *ipc_lock(struct ipc_ids *, int); struct kern_ipc_perm *ipc_obtain_object(struct ipc_ids *ids, int id); diff --git a/kernel/audit.c b/kernel/audit.c index 91e53d04b6a..7b0e23a740c 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1117,9 +1117,10 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, sleep_time = timeout_start + audit_backlog_wait_time - jiffies; - if ((long)sleep_time > 0) + if ((long)sleep_time > 0) { wait_for_auditd(sleep_time); - continue; + continue; + } } if (audit_rate_check() && printk_ratelimit()) printk(KERN_WARNING diff --git a/kernel/events/core.c b/kernel/events/core.c index dd236b66ca3..cb4238e85b3 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3660,6 +3660,26 @@ static void calc_timer_values(struct perf_event *event, *running = ctx_time - event->tstamp_running; } +static void perf_event_init_userpage(struct perf_event *event) +{ + struct perf_event_mmap_page *userpg; + struct ring_buffer *rb; + + rcu_read_lock(); + rb = rcu_dereference(event->rb); + if (!rb) + goto unlock; + + userpg = rb->user_page; + + /* Allow new userspace to detect that bit 0 is deprecated */ + userpg->cap_bit0_is_deprecated = 1; + userpg->size = offsetof(struct perf_event_mmap_page, __reserved); + +unlock: + rcu_read_unlock(); +} + void __weak arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) { } @@ -4044,6 +4064,7 @@ again: ring_buffer_attach(event, rb); rcu_assign_pointer(event->rb, rb); + perf_event_init_userpage(event); perf_event_update_userpage(event); unlock: diff --git a/kernel/reboot.c b/kernel/reboot.c index 269ed9384cc..f813b347464 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -32,7 +32,14 @@ EXPORT_SYMBOL(cad_pid); #endif enum reboot_mode reboot_mode DEFAULT_REBOOT_MODE; -int reboot_default; +/* + * This variable is used privately to keep track of whether or not + * reboot_type is still set to its default value (i.e., reboot= hasn't + * been set on the command line). This is needed so that we can + * suppress DMI scanning for reboot quirks. Without it, it's + * impossible to override a faulty reboot quirk without recompiling. + */ +int reboot_default = 1; int reboot_cpu; enum reboot_type reboot_type = BOOT_ACPI; int reboot_force; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 11cd1366735..7c70201fbc6 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4242,7 +4242,7 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq) } if (!se) { - cfs_rq->h_load = rq->avg.load_avg_contrib; + cfs_rq->h_load = cfs_rq->runnable_load_avg; cfs_rq->last_h_load_update = now; } @@ -4823,8 +4823,8 @@ void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds) (busiest->load_per_task * SCHED_POWER_SCALE) / busiest->group_power; - if (busiest->avg_load - local->avg_load + scaled_busy_load_per_task >= - (scaled_busy_load_per_task * imbn)) { + if (busiest->avg_load + scaled_busy_load_per_task >= + local->avg_load + (scaled_busy_load_per_task * imbn)) { env->imbalance = busiest->load_per_task; return; } @@ -4896,7 +4896,8 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * max load less than avg load(as we skip the groups at or below * its cpu_power, while calculating max_load..) */ - if (busiest->avg_load < sds->avg_load) { + if (busiest->avg_load <= sds->avg_load || + local->avg_load >= sds->avg_load) { env->imbalance = 0; return fix_small_imbalance(env, sds); } diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 51c4f34d258..4431610f049 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -486,7 +486,52 @@ static struct smp_hotplug_thread watchdog_threads = { .unpark = watchdog_enable, }; -static int watchdog_enable_all_cpus(void) +static void restart_watchdog_hrtimer(void *info) +{ + struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer); + int ret; + + /* + * No need to cancel and restart hrtimer if it is currently executing + * because it will reprogram itself with the new period now. + * We should never see it unqueued here because we are running per-cpu + * with interrupts disabled. + */ + ret = hrtimer_try_to_cancel(hrtimer); + if (ret == 1) + hrtimer_start(hrtimer, ns_to_ktime(sample_period), + HRTIMER_MODE_REL_PINNED); +} + +static void update_timers(int cpu) +{ + struct call_single_data data = {.func = restart_watchdog_hrtimer}; + /* + * Make sure that perf event counter will adopt to a new + * sampling period. Updating the sampling period directly would + * be much nicer but we do not have an API for that now so + * let's use a big hammer. + * Hrtimer will adopt the new period on the next tick but this + * might be late already so we have to restart the timer as well. + */ + watchdog_nmi_disable(cpu); + __smp_call_function_single(cpu, &data, 1); + watchdog_nmi_enable(cpu); +} + +static void update_timers_all_cpus(void) +{ + int cpu; + + get_online_cpus(); + preempt_disable(); + for_each_online_cpu(cpu) + update_timers(cpu); + preempt_enable(); + put_online_cpus(); +} + +static int watchdog_enable_all_cpus(bool sample_period_changed) { int err = 0; @@ -496,6 +541,8 @@ static int watchdog_enable_all_cpus(void) pr_err("Failed to create watchdog threads, disabled\n"); else watchdog_running = 1; + } else if (sample_period_changed) { + update_timers_all_cpus(); } return err; @@ -520,13 +567,15 @@ int proc_dowatchdog(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int err, old_thresh, old_enabled; + static DEFINE_MUTEX(watchdog_proc_mutex); + mutex_lock(&watchdog_proc_mutex); old_thresh = ACCESS_ONCE(watchdog_thresh); old_enabled = ACCESS_ONCE(watchdog_user_enabled); err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (err || !write) - return err; + goto out; set_sample_period(); /* @@ -535,7 +584,7 @@ int proc_dowatchdog(struct ctl_table *table, int write, * watchdog_*_all_cpus() function takes care of this. */ if (watchdog_user_enabled && watchdog_thresh) - err = watchdog_enable_all_cpus(); + err = watchdog_enable_all_cpus(old_thresh != watchdog_thresh); else watchdog_disable_all_cpus(); @@ -544,7 +593,8 @@ int proc_dowatchdog(struct ctl_table *table, int write, watchdog_thresh = old_thresh; watchdog_user_enabled = old_enabled; } - +out: + mutex_unlock(&watchdog_proc_mutex); return err; } #endif /* CONFIG_SYSCTL */ @@ -554,5 +604,5 @@ void __init lockup_detector_init(void) set_sample_period(); if (watchdog_user_enabled) - watchdog_enable_all_cpus(); + watchdog_enable_all_cpus(false); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index d5ff3ce1302..1c52ddbc839 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -39,6 +39,7 @@ #include <linux/limits.h> #include <linux/export.h> #include <linux/mutex.h> +#include <linux/rbtree.h> #include <linux/slab.h> #include <linux/swap.h> #include <linux/swapops.h> @@ -160,6 +161,10 @@ struct mem_cgroup_per_zone { struct mem_cgroup_reclaim_iter reclaim_iter[DEF_PRIORITY + 1]; + struct rb_node tree_node; /* RB tree node */ + unsigned long long usage_in_excess;/* Set to the value by which */ + /* the soft limit is exceeded*/ + bool on_tree; struct mem_cgroup *memcg; /* Back pointer, we cannot */ /* use container_of */ }; @@ -168,6 +173,26 @@ struct mem_cgroup_per_node { struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES]; }; +/* + * Cgroups above their limits are maintained in a RB-Tree, independent of + * their hierarchy representation + */ + +struct mem_cgroup_tree_per_zone { + struct rb_root rb_root; + spinlock_t lock; +}; + +struct mem_cgroup_tree_per_node { + struct mem_cgroup_tree_per_zone rb_tree_per_zone[MAX_NR_ZONES]; +}; + +struct mem_cgroup_tree { + struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES]; +}; + +static struct mem_cgroup_tree soft_limit_tree __read_mostly; + struct mem_cgroup_threshold { struct eventfd_ctx *eventfd; u64 threshold; @@ -303,22 +328,6 @@ struct mem_cgroup { atomic_t numainfo_events; atomic_t numainfo_updating; #endif - /* - * Protects soft_contributed transitions. - * See mem_cgroup_update_soft_limit - */ - spinlock_t soft_lock; - - /* - * If true then this group has increased parents' children_in_excess - * when it got over the soft limit. - * When a group falls bellow the soft limit, parents' children_in_excess - * is decreased and soft_contributed changed to false. - */ - bool soft_contributed; - - /* Number of children that are in soft limit excess */ - atomic_t children_in_excess; struct mem_cgroup_per_node *nodeinfo[0]; /* WARNING: nodeinfo must be the last member here */ @@ -422,6 +431,7 @@ static bool move_file(void) * limit reclaim to prevent infinite loops, if they ever occur. */ #define MEM_CGROUP_MAX_RECLAIM_LOOPS 100 +#define MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS 2 enum charge_type { MEM_CGROUP_CHARGE_TYPE_CACHE = 0, @@ -648,6 +658,164 @@ page_cgroup_zoneinfo(struct mem_cgroup *memcg, struct page *page) return mem_cgroup_zoneinfo(memcg, nid, zid); } +static struct mem_cgroup_tree_per_zone * +soft_limit_tree_node_zone(int nid, int zid) +{ + return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid]; +} + +static struct mem_cgroup_tree_per_zone * +soft_limit_tree_from_page(struct page *page) +{ + int nid = page_to_nid(page); + int zid = page_zonenum(page); + + return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid]; +} + +static void +__mem_cgroup_insert_exceeded(struct mem_cgroup *memcg, + struct mem_cgroup_per_zone *mz, + struct mem_cgroup_tree_per_zone *mctz, + unsigned long long new_usage_in_excess) +{ + struct rb_node **p = &mctz->rb_root.rb_node; + struct rb_node *parent = NULL; + struct mem_cgroup_per_zone *mz_node; + + if (mz->on_tree) + return; + + mz->usage_in_excess = new_usage_in_excess; + if (!mz->usage_in_excess) + return; + while (*p) { + parent = *p; + mz_node = rb_entry(parent, struct mem_cgroup_per_zone, + tree_node); + if (mz->usage_in_excess < mz_node->usage_in_excess) + p = &(*p)->rb_left; + /* + * We can't avoid mem cgroups that are over their soft + * limit by the same amount + */ + else if (mz->usage_in_excess >= mz_node->usage_in_excess) + p = &(*p)->rb_right; + } + rb_link_node(&mz->tree_node, parent, p); + rb_insert_color(&mz->tree_node, &mctz->rb_root); + mz->on_tree = true; +} + +static void +__mem_cgroup_remove_exceeded(struct mem_cgroup *memcg, + struct mem_cgroup_per_zone *mz, + struct mem_cgroup_tree_per_zone *mctz) +{ + if (!mz->on_tree) + return; + rb_erase(&mz->tree_node, &mctz->rb_root); + mz->on_tree = false; +} + +static void +mem_cgroup_remove_exceeded(struct mem_cgroup *memcg, + struct mem_cgroup_per_zone *mz, + struct mem_cgroup_tree_per_zone *mctz) +{ + spin_lock(&mctz->lock); + __mem_cgroup_remove_exceeded(memcg, mz, mctz); + spin_unlock(&mctz->lock); +} + + +static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) +{ + unsigned long long excess; + struct mem_cgroup_per_zone *mz; + struct mem_cgroup_tree_per_zone *mctz; + int nid = page_to_nid(page); + int zid = page_zonenum(page); + mctz = soft_limit_tree_from_page(page); + + /* + * Necessary to update all ancestors when hierarchy is used. + * because their event counter is not touched. + */ + for (; memcg; memcg = parent_mem_cgroup(memcg)) { + mz = mem_cgroup_zoneinfo(memcg, nid, zid); + excess = res_counter_soft_limit_excess(&memcg->res); + /* + * We have to update the tree if mz is on RB-tree or + * mem is over its softlimit. + */ + if (excess || mz->on_tree) { + spin_lock(&mctz->lock); + /* if on-tree, remove it */ + if (mz->on_tree) + __mem_cgroup_remove_exceeded(memcg, mz, mctz); + /* + * Insert again. mz->usage_in_excess will be updated. + * If excess is 0, no tree ops. + */ + __mem_cgroup_insert_exceeded(memcg, mz, mctz, excess); + spin_unlock(&mctz->lock); + } + } +} + +static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg) +{ + int node, zone; + struct mem_cgroup_per_zone *mz; + struct mem_cgroup_tree_per_zone *mctz; + + for_each_node(node) { + for (zone = 0; zone < MAX_NR_ZONES; zone++) { + mz = mem_cgroup_zoneinfo(memcg, node, zone); + mctz = soft_limit_tree_node_zone(node, zone); + mem_cgroup_remove_exceeded(memcg, mz, mctz); + } + } +} + +static struct mem_cgroup_per_zone * +__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz) +{ + struct rb_node *rightmost = NULL; + struct mem_cgroup_per_zone *mz; + +retry: + mz = NULL; + rightmost = rb_last(&mctz->rb_root); + if (!rightmost) + goto done; /* Nothing to reclaim from */ + + mz = rb_entry(rightmost, struct mem_cgroup_per_zone, tree_node); + /* + * Remove the node now but someone else can add it back, + * we will to add it back at the end of reclaim to its correct + * position in the tree. + */ + __mem_cgroup_remove_exceeded(mz->memcg, mz, mctz); + if (!res_counter_soft_limit_excess(&mz->memcg->res) || + !css_tryget(&mz->memcg->css)) + goto retry; +done: + return mz; +} + +static struct mem_cgroup_per_zone * +mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz) +{ + struct mem_cgroup_per_zone *mz; + + spin_lock(&mctz->lock); + mz = __mem_cgroup_largest_soft_limit_node(mctz); + spin_unlock(&mctz->lock); + return mz; +} + /* * Implementation Note: reading percpu statistics for memcg. * @@ -822,48 +990,6 @@ static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg, } /* - * Called from rate-limited memcg_check_events when enough - * MEM_CGROUP_TARGET_SOFTLIMIT events are accumulated and it makes sure - * that all the parents up the hierarchy will be notified that this group - * is in excess or that it is not in excess anymore. mmecg->soft_contributed - * makes the transition a single action whenever the state flips from one to - * the other. - */ -static void mem_cgroup_update_soft_limit(struct mem_cgroup *memcg) -{ - unsigned long long excess = res_counter_soft_limit_excess(&memcg->res); - struct mem_cgroup *parent = memcg; - int delta = 0; - - spin_lock(&memcg->soft_lock); - if (excess) { - if (!memcg->soft_contributed) { - delta = 1; - memcg->soft_contributed = true; - } - } else { - if (memcg->soft_contributed) { - delta = -1; - memcg->soft_contributed = false; - } - } - - /* - * Necessary to update all ancestors when hierarchy is used - * because their event counter is not touched. - * We track children even outside the hierarchy for the root - * cgroup because tree walk starting at root should visit - * all cgroups and we want to prevent from pointless tree - * walk if no children is below the limit. - */ - while (delta && (parent = parent_mem_cgroup(parent))) - atomic_add(delta, &parent->children_in_excess); - if (memcg != root_mem_cgroup && !root_mem_cgroup->use_hierarchy) - atomic_add(delta, &root_mem_cgroup->children_in_excess); - spin_unlock(&memcg->soft_lock); -} - -/* * Check events in order. * */ @@ -886,7 +1012,7 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) mem_cgroup_threshold(memcg); if (unlikely(do_softlimit)) - mem_cgroup_update_soft_limit(memcg); + mem_cgroup_update_tree(memcg, page); #if MAX_NUMNODES > 1 if (unlikely(do_numainfo)) atomic_inc(&memcg->numainfo_events); @@ -929,15 +1055,6 @@ struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) return memcg; } -static enum mem_cgroup_filter_t -mem_cgroup_filter(struct mem_cgroup *memcg, struct mem_cgroup *root, - mem_cgroup_iter_filter cond) -{ - if (!cond) - return VISIT; - return cond(memcg, root); -} - /* * Returns a next (in a pre-order walk) alive memcg (with elevated css * ref. count) or NULL if the whole root's subtree has been visited. @@ -945,7 +1062,7 @@ mem_cgroup_filter(struct mem_cgroup *memcg, struct mem_cgroup *root, * helper function to be used by mem_cgroup_iter */ static struct mem_cgroup *__mem_cgroup_iter_next(struct mem_cgroup *root, - struct mem_cgroup *last_visited, mem_cgroup_iter_filter cond) + struct mem_cgroup *last_visited) { struct cgroup_subsys_state *prev_css, *next_css; @@ -963,31 +1080,11 @@ skip_node: if (next_css) { struct mem_cgroup *mem = mem_cgroup_from_css(next_css); - switch (mem_cgroup_filter(mem, root, cond)) { - case SKIP: + if (css_tryget(&mem->css)) + return mem; + else { prev_css = next_css; goto skip_node; - case SKIP_TREE: - if (mem == root) - return NULL; - /* - * css_rightmost_descendant is not an optimal way to - * skip through a subtree (especially for imbalanced - * trees leaning to right) but that's what we have right - * now. More effective solution would be traversing - * right-up for first non-NULL without calling - * css_next_descendant_pre afterwards. - */ - prev_css = css_rightmost_descendant(next_css); - goto skip_node; - case VISIT: - if (css_tryget(&mem->css)) - return mem; - else { - prev_css = next_css; - goto skip_node; - } - break; } } @@ -1051,7 +1148,6 @@ static void mem_cgroup_iter_update(struct mem_cgroup_reclaim_iter *iter, * @root: hierarchy root * @prev: previously returned memcg, NULL on first invocation * @reclaim: cookie for shared reclaim walks, NULL for full walks - * @cond: filter for visited nodes, NULL for no filter * * Returns references to children of the hierarchy below @root, or * @root itself, or %NULL after a full round-trip. @@ -1064,18 +1160,15 @@ static void mem_cgroup_iter_update(struct mem_cgroup_reclaim_iter *iter, * divide up the memcgs in the hierarchy among all concurrent * reclaimers operating on the same zone and priority. */ -struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root, +struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup *prev, - struct mem_cgroup_reclaim_cookie *reclaim, - mem_cgroup_iter_filter cond) + struct mem_cgroup_reclaim_cookie *reclaim) { struct mem_cgroup *memcg = NULL; struct mem_cgroup *last_visited = NULL; - if (mem_cgroup_disabled()) { - /* first call must return non-NULL, second return NULL */ - return (struct mem_cgroup *)(unsigned long)!prev; - } + if (mem_cgroup_disabled()) + return NULL; if (!root) root = root_mem_cgroup; @@ -1086,9 +1179,7 @@ struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root, if (!root->use_hierarchy && root != root_mem_cgroup) { if (prev) goto out_css_put; - if (mem_cgroup_filter(root, root, cond) == VISIT) - return root; - return NULL; + return root; } rcu_read_lock(); @@ -1111,7 +1202,7 @@ struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root, last_visited = mem_cgroup_iter_load(iter, root, &seq); } - memcg = __mem_cgroup_iter_next(root, last_visited, cond); + memcg = __mem_cgroup_iter_next(root, last_visited); if (reclaim) { mem_cgroup_iter_update(iter, last_visited, memcg, seq); @@ -1122,11 +1213,7 @@ struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root, reclaim->generation = iter->generation; } - /* - * We have finished the whole tree walk or no group has been - * visited because filter told us to skip the root node. - */ - if (!memcg && (prev || (cond && !last_visited))) + if (prev && !memcg) goto out_unlock; } out_unlock: @@ -1767,7 +1854,6 @@ static unsigned long mem_cgroup_reclaim(struct mem_cgroup *memcg, return total; } -#if MAX_NUMNODES > 1 /** * test_mem_cgroup_node_reclaimable * @memcg: the target memcg @@ -1790,6 +1876,7 @@ static bool test_mem_cgroup_node_reclaimable(struct mem_cgroup *memcg, return false; } +#if MAX_NUMNODES > 1 /* * Always updating the nodemask is not very good - even if we have an empty @@ -1857,50 +1944,104 @@ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg) return node; } +/* + * Check all nodes whether it contains reclaimable pages or not. + * For quick scan, we make use of scan_nodes. This will allow us to skip + * unused nodes. But scan_nodes is lazily updated and may not cotain + * enough new information. We need to do double check. + */ +static bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap) +{ + int nid; + + /* + * quick check...making use of scan_node. + * We can skip unused nodes. + */ + if (!nodes_empty(memcg->scan_nodes)) { + for (nid = first_node(memcg->scan_nodes); + nid < MAX_NUMNODES; + nid = next_node(nid, memcg->scan_nodes)) { + + if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap)) + return true; + } + } + /* + * Check rest of nodes. + */ + for_each_node_state(nid, N_MEMORY) { + if (node_isset(nid, memcg->scan_nodes)) + continue; + if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap)) + return true; + } + return false; +} + #else int mem_cgroup_select_victim_node(struct mem_cgroup *memcg) { return 0; } -#endif - -/* - * A group is eligible for the soft limit reclaim under the given root - * hierarchy if - * a) it is over its soft limit - * b) any parent up the hierarchy is over its soft limit - * - * If the given group doesn't have any children over the limit then it - * doesn't make any sense to iterate its subtree. - */ -enum mem_cgroup_filter_t -mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, - struct mem_cgroup *root) +static bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap) { - struct mem_cgroup *parent; - - if (!memcg) - memcg = root_mem_cgroup; - parent = memcg; - - if (res_counter_soft_limit_excess(&memcg->res)) - return VISIT; + return test_mem_cgroup_node_reclaimable(memcg, 0, noswap); +} +#endif - /* - * If any parent up to the root in the hierarchy is over its soft limit - * then we have to obey and reclaim from this group as well. - */ - while ((parent = parent_mem_cgroup(parent))) { - if (res_counter_soft_limit_excess(&parent->res)) - return VISIT; - if (parent == root) +static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg, + struct zone *zone, + gfp_t gfp_mask, + unsigned long *total_scanned) +{ + struct mem_cgroup *victim = NULL; + int total = 0; + int loop = 0; + unsigned long excess; + unsigned long nr_scanned; + struct mem_cgroup_reclaim_cookie reclaim = { + .zone = zone, + .priority = 0, + }; + + excess = res_counter_soft_limit_excess(&root_memcg->res) >> PAGE_SHIFT; + + while (1) { + victim = mem_cgroup_iter(root_memcg, victim, &reclaim); + if (!victim) { + loop++; + if (loop >= 2) { + /* + * If we have not been able to reclaim + * anything, it might because there are + * no reclaimable pages under this hierarchy + */ + if (!total) + break; + /* + * We want to do more targeted reclaim. + * excess >> 2 is not to excessive so as to + * reclaim too much, nor too less that we keep + * coming back to reclaim from this cgroup + */ + if (total >= (excess >> 2) || + (loop > MEM_CGROUP_MAX_RECLAIM_LOOPS)) + break; + } + continue; + } + if (!mem_cgroup_reclaimable(victim, false)) + continue; + total += mem_cgroup_shrink_node_zone(victim, gfp_mask, false, + zone, &nr_scanned); + *total_scanned += nr_scanned; + if (!res_counter_soft_limit_excess(&root_memcg->res)) break; } - - if (!atomic_read(&memcg->children_in_excess)) - return SKIP_TREE; - return SKIP; + mem_cgroup_iter_break(root_memcg, victim); + return total; } static DEFINE_SPINLOCK(memcg_oom_lock); @@ -2812,7 +2953,9 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, unlock_page_cgroup(pc); /* - * "charge_statistics" updated event counter. + * "charge_statistics" updated event counter. Then, check it. + * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree. + * if they exceeds softlimit. */ memcg_check_events(memcg, page); } @@ -4647,6 +4790,98 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, return ret; } +unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, + gfp_t gfp_mask, + unsigned long *total_scanned) +{ + unsigned long nr_reclaimed = 0; + struct mem_cgroup_per_zone *mz, *next_mz = NULL; + unsigned long reclaimed; + int loop = 0; + struct mem_cgroup_tree_per_zone *mctz; + unsigned long long excess; + unsigned long nr_scanned; + + if (order > 0) + return 0; + + mctz = soft_limit_tree_node_zone(zone_to_nid(zone), zone_idx(zone)); + /* + * This loop can run a while, specially if mem_cgroup's continuously + * keep exceeding their soft limit and putting the system under + * pressure + */ + do { + if (next_mz) + mz = next_mz; + else + mz = mem_cgroup_largest_soft_limit_node(mctz); + if (!mz) + break; + + nr_scanned = 0; + reclaimed = mem_cgroup_soft_reclaim(mz->memcg, zone, + gfp_mask, &nr_scanned); + nr_reclaimed += reclaimed; + *total_scanned += nr_scanned; + spin_lock(&mctz->lock); + + /* + * If we failed to reclaim anything from this memory cgroup + * it is time to move on to the next cgroup + */ + next_mz = NULL; + if (!reclaimed) { + do { + /* + * Loop until we find yet another one. + * + * By the time we get the soft_limit lock + * again, someone might have aded the + * group back on the RB tree. Iterate to + * make sure we get a different mem. + * mem_cgroup_largest_soft_limit_node returns + * NULL if no other cgroup is present on + * the tree + */ + next_mz = + __mem_cgroup_largest_soft_limit_node(mctz); + if (next_mz == mz) + css_put(&next_mz->memcg->css); + else /* next_mz == NULL or other memcg */ + break; + } while (1); + } + __mem_cgroup_remove_exceeded(mz->memcg, mz, mctz); + excess = res_counter_soft_limit_excess(&mz->memcg->res); + /* + * One school of thought says that we should not add + * back the node to the tree if reclaim returns 0. + * But our reclaim could return 0, simply because due + * to priority we are exposing a smaller subset of + * memory to reclaim from. Consider this as a longer + * term TODO. + */ + /* If excess == 0, no tree ops */ + __mem_cgroup_insert_exceeded(mz->memcg, mz, mctz, excess); + spin_unlock(&mctz->lock); + css_put(&mz->memcg->css); + loop++; + /* + * Could not reclaim anything and there are no more + * mem cgroups to try or we seem to be looping without + * reclaiming anything. + */ + if (!nr_reclaimed && + (next_mz == NULL || + loop > MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS)) + break; + } while (!nr_reclaimed); + if (next_mz) + css_put(&next_mz->memcg->css); + return nr_reclaimed; +} + /** * mem_cgroup_force_empty_list - clears LRU of a group * @memcg: group to clear @@ -5911,6 +6146,8 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) for (zone = 0; zone < MAX_NR_ZONES; zone++) { mz = &pn->zoneinfo[zone]; lruvec_init(&mz->lruvec); + mz->usage_in_excess = 0; + mz->on_tree = false; mz->memcg = memcg; } memcg->nodeinfo[node] = pn; @@ -5966,6 +6203,7 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) int node; size_t size = memcg_size(); + mem_cgroup_remove_from_trees(memcg); free_css_id(&mem_cgroup_subsys, &memcg->css); for_each_node(node) @@ -6002,6 +6240,29 @@ struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) } EXPORT_SYMBOL(parent_mem_cgroup); +static void __init mem_cgroup_soft_limit_tree_init(void) +{ + struct mem_cgroup_tree_per_node *rtpn; + struct mem_cgroup_tree_per_zone *rtpz; + int tmp, node, zone; + + for_each_node(node) { + tmp = node; + if (!node_state(node, N_NORMAL_MEMORY)) + tmp = -1; + rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, tmp); + BUG_ON(!rtpn); + + soft_limit_tree.rb_tree_per_node[node] = rtpn; + + for (zone = 0; zone < MAX_NR_ZONES; zone++) { + rtpz = &rtpn->rb_tree_per_zone[zone]; + rtpz->rb_root = RB_ROOT; + spin_lock_init(&rtpz->lock); + } + } +} + static struct cgroup_subsys_state * __ref mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) { @@ -6031,7 +6292,6 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) mutex_init(&memcg->thresholds_lock); spin_lock_init(&memcg->move_lock); vmpressure_init(&memcg->vmpressure); - spin_lock_init(&memcg->soft_lock); return &memcg->css; @@ -6109,13 +6369,6 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) mem_cgroup_invalidate_reclaim_iterators(memcg); mem_cgroup_reparent_charges(memcg); - if (memcg->soft_contributed) { - while ((memcg = parent_mem_cgroup(memcg))) - atomic_dec(&memcg->children_in_excess); - - if (memcg != root_mem_cgroup && !root_mem_cgroup->use_hierarchy) - atomic_dec(&root_mem_cgroup->children_in_excess); - } mem_cgroup_destroy_all_caches(memcg); vmpressure_cleanup(&memcg->vmpressure); } @@ -6790,6 +7043,7 @@ static int __init mem_cgroup_init(void) { hotcpu_notifier(memcg_cpu_hotplug_callback, 0); enable_swap_cgroup(); + mem_cgroup_soft_limit_tree_init(); memcg_stock_init(); return 0; } diff --git a/mm/mlock.c b/mm/mlock.c index d6380266324..67ba6da7d0e 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -736,6 +736,7 @@ static int do_mlockall(int flags) /* Ignore errors */ mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags); + cond_resched(); } out: return 0; diff --git a/mm/vmscan.c b/mm/vmscan.c index 8ed1b775bdc..beb35778c69 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -139,23 +139,11 @@ static bool global_reclaim(struct scan_control *sc) { return !sc->target_mem_cgroup; } - -static bool mem_cgroup_should_soft_reclaim(struct scan_control *sc) -{ - struct mem_cgroup *root = sc->target_mem_cgroup; - return !mem_cgroup_disabled() && - mem_cgroup_soft_reclaim_eligible(root, root) != SKIP_TREE; -} #else static bool global_reclaim(struct scan_control *sc) { return true; } - -static bool mem_cgroup_should_soft_reclaim(struct scan_control *sc) -{ - return false; -} #endif unsigned long zone_reclaimable_pages(struct zone *zone) @@ -2176,11 +2164,9 @@ static inline bool should_continue_reclaim(struct zone *zone, } } -static int -__shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim) +static void shrink_zone(struct zone *zone, struct scan_control *sc) { unsigned long nr_reclaimed, nr_scanned; - int groups_scanned = 0; do { struct mem_cgroup *root = sc->target_mem_cgroup; @@ -2188,17 +2174,15 @@ __shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim) .zone = zone, .priority = sc->priority, }; - struct mem_cgroup *memcg = NULL; - mem_cgroup_iter_filter filter = (soft_reclaim) ? - mem_cgroup_soft_reclaim_eligible : NULL; + struct mem_cgroup *memcg; nr_reclaimed = sc->nr_reclaimed; nr_scanned = sc->nr_scanned; - while ((memcg = mem_cgroup_iter_cond(root, memcg, &reclaim, filter))) { + memcg = mem_cgroup_iter(root, NULL, &reclaim); + do { struct lruvec *lruvec; - groups_scanned++; lruvec = mem_cgroup_zone_lruvec(zone, memcg); shrink_lruvec(lruvec, sc); @@ -2218,7 +2202,8 @@ __shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim) mem_cgroup_iter_break(root, memcg); break; } - } + memcg = mem_cgroup_iter(root, memcg, &reclaim); + } while (memcg); vmpressure(sc->gfp_mask, sc->target_mem_cgroup, sc->nr_scanned - nr_scanned, @@ -2226,37 +2211,6 @@ __shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim) } while (should_continue_reclaim(zone, sc->nr_reclaimed - nr_reclaimed, sc->nr_scanned - nr_scanned, sc)); - - return groups_scanned; -} - - -static void shrink_zone(struct zone *zone, struct scan_control *sc) -{ - bool do_soft_reclaim = mem_cgroup_should_soft_reclaim(sc); - unsigned long nr_scanned = sc->nr_scanned; - int scanned_groups; - - scanned_groups = __shrink_zone(zone, sc, do_soft_reclaim); - /* - * memcg iterator might race with other reclaimer or start from - * a incomplete tree walk so the tree walk in __shrink_zone - * might have missed groups that are above the soft limit. Try - * another loop to catch up with others. Do it just once to - * prevent from reclaim latencies when other reclaimers always - * preempt this one. - */ - if (do_soft_reclaim && !scanned_groups) - __shrink_zone(zone, sc, do_soft_reclaim); - - /* - * No group is over the soft limit or those that are do not have - * pages in the zone we are reclaiming so we have to reclaim everybody - */ - if (do_soft_reclaim && (sc->nr_scanned == nr_scanned)) { - __shrink_zone(zone, sc, false); - return; - } } /* Returns true if compaction should go ahead for a high-order request */ @@ -2320,6 +2274,8 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) { struct zoneref *z; struct zone *zone; + unsigned long nr_soft_reclaimed; + unsigned long nr_soft_scanned; bool aborted_reclaim = false; /* @@ -2359,6 +2315,18 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) continue; } } + /* + * This steals pages from memory cgroups over softlimit + * and returns the number of reclaimed pages and + * scanned pages. This works for global memory pressure + * and balancing, not for a memcg's limit. + */ + nr_soft_scanned = 0; + nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone, + sc->order, sc->gfp_mask, + &nr_soft_scanned); + sc->nr_reclaimed += nr_soft_reclaimed; + sc->nr_scanned += nr_soft_scanned; /* need some check for avoid more shrink_zone() */ } @@ -2952,6 +2920,8 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order, { int i; int end_zone = 0; /* Inclusive. 0 = ZONE_DMA */ + unsigned long nr_soft_reclaimed; + unsigned long nr_soft_scanned; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .priority = DEF_PRIORITY, @@ -3066,6 +3036,15 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order, sc.nr_scanned = 0; + nr_soft_scanned = 0; + /* + * Call soft limit reclaim before calling shrink_zone. + */ + nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone, + order, sc.gfp_mask, + &nr_soft_scanned); + sc.nr_reclaimed += nr_soft_reclaimed; + /* * There should be no need to raise the scanning * priority if enough pages are already being scanned diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 47016c304c8..66cad506b8a 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -3975,8 +3975,8 @@ sub string_find_replace { # check for new externs in .h files. if ($realfile =~ /\.h$/ && $line =~ /^\+\s*(extern\s+)$Type\s*$Ident\s*\(/s) { - if (WARN("AVOID_EXTERNS", - "extern prototypes should be avoided in .h files\n" . $herecurr) && + if (CHK("AVOID_EXTERNS", + "extern prototypes should be avoided in .h files\n" . $herecurr) && $fix) { $fixed[$linenr - 1] =~ s/(.*)\bextern\b\s*(.*)/$1$2/; } diff --git a/tools/lib/lk/debugfs.c b/tools/lib/lk/debugfs.c index 099e7cd022e..7c434796235 100644 --- a/tools/lib/lk/debugfs.c +++ b/tools/lib/lk/debugfs.c @@ -5,7 +5,6 @@ #include <stdbool.h> #include <sys/vfs.h> #include <sys/mount.h> -#include <linux/magic.h> #include <linux/kernel.h> #include "debugfs.h" diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c index 9570c2b0f83..b2519e49424 100644 --- a/tools/perf/arch/x86/util/tsc.c +++ b/tools/perf/arch/x86/util/tsc.c @@ -32,7 +32,7 @@ u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc) int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, struct perf_tsc_conversion *tc) { - bool cap_usr_time_zero; + bool cap_user_time_zero; u32 seq; int i = 0; @@ -42,7 +42,7 @@ int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, tc->time_mult = pc->time_mult; tc->time_shift = pc->time_shift; tc->time_zero = pc->time_zero; - cap_usr_time_zero = pc->cap_usr_time_zero; + cap_user_time_zero = pc->cap_user_time_zero; rmb(); if (pc->lock == seq && !(seq & 1)) break; @@ -52,7 +52,7 @@ int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, } } - if (!cap_usr_time_zero) + if (!cap_user_time_zero) return -EOPNOTSUPP; return 0; diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 423875c999b..afe377b2884 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -321,8 +321,6 @@ found: return perf_event__repipe(tool, event_sw, &sample_sw, machine); } -extern volatile int session_done; - static void sig_handler(int sig __maybe_unused) { session_done = 1; diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 8e50d8d7741..72eae7498c0 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -401,8 +401,6 @@ static int perf_report__setup_sample_type(struct perf_report *rep) return 0; } -extern volatile int session_done; - static void sig_handler(int sig __maybe_unused) { session_done = 1; @@ -568,6 +566,9 @@ static int __cmd_report(struct perf_report *rep) } } + if (session_done()) + return 0; + if (nr_samples == 0) { ui__error("The %s file has no samples!\n", session->filename); return 0; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 7f31a3ded1b..9c333ff3dfe 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -553,8 +553,6 @@ static struct perf_tool perf_script = { .ordering_requires_timestamps = true, }; -extern volatile int session_done; - static void sig_handler(int sig __maybe_unused) { session_done = 1; diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index f5aa6375e3e..fd485340472 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -16,6 +16,23 @@ #include <sys/mman.h> #include <linux/futex.h> +/* For older distros: */ +#ifndef MAP_STACK +# define MAP_STACK 0x20000 +#endif + +#ifndef MADV_HWPOISON +# define MADV_HWPOISON 100 +#endif + +#ifndef MADV_MERGEABLE +# define MADV_MERGEABLE 12 +#endif + +#ifndef MADV_UNMERGEABLE +# define MADV_UNMERGEABLE 13 +#endif + static size_t syscall_arg__scnprintf_hex(char *bf, size_t size, unsigned long arg, u8 arg_idx __maybe_unused, diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index 214e17e97e5..346ee929d25 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -180,6 +180,9 @@ FLAGS_LIBELF=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_LIBELF),-DLIBELF_MMAP),y) CFLAGS += -DLIBELF_MMAP endif +ifeq ($(call try-cc,$(SOURCE_ELF_GETPHDRNUM),$(FLAGS_LIBELF),-DHAVE_ELF_GETPHDRNUM),y) + CFLAGS += -DHAVE_ELF_GETPHDRNUM +endif # include ARCH specific config -include $(src-perf)/arch/$(ARCH)/Makefile diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak index 708fb8e9822..d5a8dd44945 100644 --- a/tools/perf/config/feature-tests.mak +++ b/tools/perf/config/feature-tests.mak @@ -61,6 +61,15 @@ int main(void) } endef +define SOURCE_ELF_GETPHDRNUM +#include <libelf.h> +int main(void) +{ + size_t dst; + return elf_getphdrnum(0, &dst); +} +endef + ifndef NO_SLANG define SOURCE_SLANG #include <slang.h> @@ -210,6 +219,7 @@ define SOURCE_LIBAUDIT int main(void) { + printf(\"error message: %s\n\", audit_errno_to_name(0)); return audit_open(); } endef diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index bfc5a27597d..7eae5488ece 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -809,7 +809,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, end = map__rip_2objdump(map, sym->end); offset = line_ip - start; - if (offset < 0 || (u64)line_ip > end) + if ((u64)line_ip < start || (u64)line_ip > end) offset = -1; else parsed_line = tmp2 + 1; diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index 3e5f5430a28..e23bde19d59 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -263,6 +263,21 @@ bool die_is_signed_type(Dwarf_Die *tp_die) } /** + * die_is_func_def - Ensure that this DIE is a subprogram and definition + * @dw_die: a DIE + * + * Ensure that this DIE is a subprogram and NOT a declaration. This + * returns true if @dw_die is a function definition. + **/ +bool die_is_func_def(Dwarf_Die *dw_die) +{ + Dwarf_Attribute attr; + + return (dwarf_tag(dw_die) == DW_TAG_subprogram && + dwarf_attr(dw_die, DW_AT_declaration, &attr) == NULL); +} + +/** * die_get_data_member_location - Get the data-member offset * @mb_die: a DIE of a member of a data structure * @offs: The offset of the member in the data structure @@ -392,6 +407,10 @@ static int __die_search_func_cb(Dwarf_Die *fn_die, void *data) { struct __addr_die_search_param *ad = data; + /* + * Since a declaration entry doesn't has given pc, this always returns + * function definition entry. + */ if (dwarf_tag(fn_die) == DW_TAG_subprogram && dwarf_haspc(fn_die, ad->addr)) { memcpy(ad->die_mem, fn_die, sizeof(Dwarf_Die)); diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h index 6ce1717784b..8658d41697d 100644 --- a/tools/perf/util/dwarf-aux.h +++ b/tools/perf/util/dwarf-aux.h @@ -38,6 +38,9 @@ extern int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr, extern int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr, int (*callback)(Dwarf_Die *, void *), void *data); +/* Ensure that this DIE is a subprogram and definition (not declaration) */ +extern bool die_is_func_def(Dwarf_Die *dw_die); + /* Compare diename and tname */ extern bool die_compare_name(Dwarf_Die *dw_die, const char *tname); diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 26441d0e571..ce69901176d 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -199,9 +199,11 @@ static int write_buildid(char *name, size_t name_len, u8 *build_id, return write_padded(fd, name, name_len + 1, len); } -static int __dsos__write_buildid_table(struct list_head *head, pid_t pid, - u16 misc, int fd) +static int __dsos__write_buildid_table(struct list_head *head, + struct machine *machine, + pid_t pid, u16 misc, int fd) { + char nm[PATH_MAX]; struct dso *pos; dsos__for_each_with_build_id(pos, head) { @@ -215,6 +217,10 @@ static int __dsos__write_buildid_table(struct list_head *head, pid_t pid, if (is_vdso_map(pos->short_name)) { name = (char *) VDSO__MAP_NAME; name_len = sizeof(VDSO__MAP_NAME) + 1; + } else if (dso__is_kcore(pos)) { + machine__mmap_name(machine, nm, sizeof(nm)); + name = nm; + name_len = strlen(nm) + 1; } else { name = pos->long_name; name_len = pos->long_name_len + 1; @@ -240,10 +246,10 @@ static int machine__write_buildid_table(struct machine *machine, int fd) umisc = PERF_RECORD_MISC_GUEST_USER; } - err = __dsos__write_buildid_table(&machine->kernel_dsos, machine->pid, - kmisc, fd); + err = __dsos__write_buildid_table(&machine->kernel_dsos, machine, + machine->pid, kmisc, fd); if (err == 0) - err = __dsos__write_buildid_table(&machine->user_dsos, + err = __dsos__write_buildid_table(&machine->user_dsos, machine, machine->pid, umisc, fd); return err; } @@ -375,23 +381,31 @@ out_free: return err; } -static int dso__cache_build_id(struct dso *dso, const char *debugdir) +static int dso__cache_build_id(struct dso *dso, struct machine *machine, + const char *debugdir) { bool is_kallsyms = dso->kernel && dso->long_name[0] != '/'; bool is_vdso = is_vdso_map(dso->short_name); + char *name = dso->long_name; + char nm[PATH_MAX]; - return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), - dso->long_name, debugdir, - is_kallsyms, is_vdso); + if (dso__is_kcore(dso)) { + is_kallsyms = true; + machine__mmap_name(machine, nm, sizeof(nm)); + name = nm; + } + return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name, + debugdir, is_kallsyms, is_vdso); } -static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir) +static int __dsos__cache_build_ids(struct list_head *head, + struct machine *machine, const char *debugdir) { struct dso *pos; int err = 0; dsos__for_each_with_build_id(pos, head) - if (dso__cache_build_id(pos, debugdir)) + if (dso__cache_build_id(pos, machine, debugdir)) err = -1; return err; @@ -399,8 +413,9 @@ static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir) static int machine__cache_build_ids(struct machine *machine, const char *debugdir) { - int ret = __dsos__cache_build_ids(&machine->kernel_dsos, debugdir); - ret |= __dsos__cache_build_ids(&machine->user_dsos, debugdir); + int ret = __dsos__cache_build_ids(&machine->kernel_dsos, machine, + debugdir); + ret |= __dsos__cache_build_ids(&machine->user_dsos, machine, debugdir); return ret; } diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 46a0d35a05e..9ff6cf3e9a9 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -611,6 +611,8 @@ void hists__collapse_resort(struct hists *hists) next = rb_first(root); while (next) { + if (session_done()) + break; n = rb_entry(next, struct hist_entry, rb_node_in); next = rb_next(&n->rb_node_in); diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index be0329394d5..20c7299a9d4 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -734,7 +734,7 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf) } /* If not a real subprogram, find a real one */ - if (dwarf_tag(sc_die) != DW_TAG_subprogram) { + if (!die_is_func_def(sc_die)) { if (!die_find_realfunc(&pf->cu_die, pf->addr, &pf->sp_die)) { pr_warning("Failed to find probe point in any " "functions.\n"); @@ -980,12 +980,10 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data) struct dwarf_callback_param *param = data; struct probe_finder *pf = param->data; struct perf_probe_point *pp = &pf->pev->point; - Dwarf_Attribute attr; /* Check tag and diename */ - if (dwarf_tag(sp_die) != DW_TAG_subprogram || - !die_compare_name(sp_die, pp->function) || - dwarf_attr(sp_die, DW_AT_declaration, &attr)) + if (!die_is_func_def(sp_die) || + !die_compare_name(sp_die, pp->function)) return DWARF_CB_OK; /* Check declared file */ @@ -1474,7 +1472,7 @@ static int line_range_inline_cb(Dwarf_Die *in_die, void *data) return 0; } -/* Search function from function name */ +/* Search function definition from function name */ static int line_range_search_cb(Dwarf_Die *sp_die, void *data) { struct dwarf_callback_param *param = data; @@ -1485,7 +1483,7 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data) if (lr->file && strtailcmp(lr->file, dwarf_decl_file(sp_die))) return DWARF_CB_OK; - if (dwarf_tag(sp_die) == DW_TAG_subprogram && + if (die_is_func_def(sp_die) && die_compare_name(sp_die, lr->function)) { lf->fname = dwarf_decl_file(sp_die); dwarf_decl_line(sp_die, &lr->offset); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 51f5edf2a6d..70ffa41518f 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -531,6 +531,9 @@ static int flush_sample_queue(struct perf_session *s, return 0; list_for_each_entry_safe(iter, tmp, head, list) { + if (session_done()) + return 0; + if (iter->timestamp > limit) break; @@ -1160,7 +1163,6 @@ static void perf_session__warn_about_errors(const struct perf_session *session, } } -#define session_done() (*(volatile int *)(&session_done)) volatile int session_done; static int __perf_session__process_pipe_events(struct perf_session *self, @@ -1372,10 +1374,13 @@ more: "Processing events..."); } + err = 0; + if (session_done()) + goto out_err; + if (file_pos < file_size) goto more; - err = 0; /* do the final flush for ordered samples */ session->ordered_samples.next_flush = ULLONG_MAX; err = flush_sample_queue(session, tool); diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 3aa75fb2225..04bf7373a7e 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -124,4 +124,8 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session, #define perf_session__set_tracepoints_handlers(session, array) \ __perf_session__set_tracepoints_handlers(session, array, ARRAY_SIZE(array)) + +extern volatile int session_done; + +#define session_done() (*(volatile int *)(&session_done)) #endif /* __PERF_SESSION_H */ diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index a7b9ab55738..a9c829be521 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -8,6 +8,22 @@ #include "symbol.h" #include "debug.h" +#ifndef HAVE_ELF_GETPHDRNUM +static int elf_getphdrnum(Elf *elf, size_t *dst) +{ + GElf_Ehdr gehdr; + GElf_Ehdr *ehdr; + + ehdr = gelf_getehdr(elf, &gehdr); + if (!ehdr) + return -1; + + *dst = ehdr->e_phnum; + + return 0; +} +#endif + #ifndef NT_GNU_BUILD_ID #define NT_GNU_BUILD_ID 3 #endif diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index fe7a27d67d2..e9e1c03f927 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -186,7 +186,7 @@ void parse_proc_kallsyms(struct pevent *pevent, char *next = NULL; char *addr_str; char *mod; - char *fmt; + char *fmt = NULL; line = strtok_r(file, "\n", &next); while (line) { |