summaryrefslogtreecommitdiff
path: root/sys-kernel/kogaion-sources
diff options
context:
space:
mode:
Diffstat (limited to 'sys-kernel/kogaion-sources')
-rw-r--r--sys-kernel/kogaion-sources/Manifest1
-rw-r--r--sys-kernel/kogaion-sources/files/desktop/0001-block-cgroups-kconfig-build-bits-for-BFQ-v7-3.10.patch103
-rw-r--r--sys-kernel/kogaion-sources/files/desktop/0002-block-introduce-the-BFQ-v7-I-O-sched-for-3.10.patch5969
-rw-r--r--sys-kernel/kogaion-sources/files/desktop/0003-block-bfq-add-Early-Queue-Merge-EQM-to-BFQ-v7-for-3.10.0.patch1034
-rw-r--r--sys-kernel/kogaion-sources/files/desktop/3.10-ck1.patch8732
-rw-r--r--sys-kernel/kogaion-sources/files/desktop/change-default-console-loglevel.patch13
-rw-r--r--sys-kernel/kogaion-sources/files/desktop/criu-no-expert.patch23
-rw-r--r--sys-kernel/kogaion-sources/files/desktop/enable_haswell_pstate_driver.patch33
-rw-r--r--sys-kernel/kogaion-sources/files/desktop/set_kogaion_extraversion_in_makefile.patch12
-rw-r--r--sys-kernel/kogaion-sources/files/desktop/uksm-0.1.2.2-for-v3.10.patch7064
-rw-r--r--sys-kernel/kogaion-sources/files/security/0001-x86-x32-Correct-invalid-use-of-user-timespec-in-the-.patch80
-rw-r--r--sys-kernel/kogaion-sources/kogaion-sources-3.10.25.ebuild55
12 files changed, 23119 insertions, 0 deletions
diff --git a/sys-kernel/kogaion-sources/Manifest b/sys-kernel/kogaion-sources/Manifest
new file mode 100644
index 00000000..58c1ec81
--- /dev/null
+++ b/sys-kernel/kogaion-sources/Manifest
@@ -0,0 +1 @@
+DIST linux-3.10.25.tar.xz 73225500 SHA256 a6c46d88deaf4f0af9038d2d23b4ed617f901c5de38f1886b865c432f22ac7cd SHA512 843b117c44ce1622d07b7e566ab80a931bfc7ed9cf6f2837e62e0dc3e1d87ef504d8566ceed9cd8d68d6616b9495de7e8dfc59c34af20a61b99260694ae31b93 WHIRLPOOL cedfd73a3bb5ea680b59e18f5d8c714bf8a71e0441a29809c0db1bf79d16e167fc524f0387d3cd6044ff07132d1b7d168690f62aca1241e1a4149658e33ca5e6
diff --git a/sys-kernel/kogaion-sources/files/desktop/0001-block-cgroups-kconfig-build-bits-for-BFQ-v7-3.10.patch b/sys-kernel/kogaion-sources/files/desktop/0001-block-cgroups-kconfig-build-bits-for-BFQ-v7-3.10.patch
new file mode 100644
index 00000000..f92978cf
--- /dev/null
+++ b/sys-kernel/kogaion-sources/files/desktop/0001-block-cgroups-kconfig-build-bits-for-BFQ-v7-3.10.patch
@@ -0,0 +1,103 @@
+From 3ded69bee018e94b1cf5e13af9ff557f0f61ab30 Mon Sep 17 00:00:00 2001
+From: Arianna Avanzini <avanzini.arianna@gmail.com>
+Date: Mon, 27 Jan 2014 23:50:08 +0100
+Subject: [PATCH 1/3] block: cgroups, kconfig, build bits for BFQ-v7-3.10
+
+Update Kconfig.iosched and do the related Makefile changes to include
+kernel configuration options for BFQ. Also add the bfqio controller
+to the cgroups subsystem.
+
+Signed-off-by: Paolo Valente <paolo.valente@unimore.it>
+Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
+---
+ block/Kconfig.iosched | 32 ++++++++++++++++++++++++++++++++
+ block/Makefile | 1 +
+ include/linux/cgroup_subsys.h | 6 ++++++
+ 3 files changed, 39 insertions(+)
+
+diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
+index 421bef9..8f552ba 100644
+--- a/block/Kconfig.iosched
++++ b/block/Kconfig.iosched
+@@ -39,6 +39,27 @@ config CFQ_GROUP_IOSCHED
+ ---help---
+ Enable group IO scheduling in CFQ.
+
++config IOSCHED_BFQ
++ tristate "BFQ I/O scheduler"
++ default n
++ ---help---
++ The BFQ I/O scheduler tries to distribute bandwidth among
++ all processes according to their weights.
++ It aims at distributing the bandwidth as desired, independently of
++ the disk parameters and with any workload. It also tries to
++ guarantee low latency to interactive and soft real-time
++ applications. If compiled built-in (saying Y here), BFQ can
++ be configured to support hierarchical scheduling.
++
++config CGROUP_BFQIO
++ bool "BFQ hierarchical scheduling support"
++ depends on CGROUPS && IOSCHED_BFQ=y
++ default n
++ ---help---
++ Enable hierarchical scheduling in BFQ, using the cgroups
++ filesystem interface. The name of the subsystem will be
++ bfqio.
++
+ choice
+ prompt "Default I/O scheduler"
+ default DEFAULT_CFQ
+@@ -52,6 +73,16 @@ choice
+ config DEFAULT_CFQ
+ bool "CFQ" if IOSCHED_CFQ=y
+
++ config DEFAULT_BFQ
++ bool "BFQ" if IOSCHED_BFQ=y
++ help
++ Selects BFQ as the default I/O scheduler which will be
++ used by default for all block devices.
++ The BFQ I/O scheduler aims at distributing the bandwidth
++ as desired, independently of the disk parameters and with
++ any workload. It also tries to guarantee low latency to
++ interactive and soft real-time applications.
++
+ config DEFAULT_NOOP
+ bool "No-op"
+
+@@ -61,6 +92,7 @@ config DEFAULT_IOSCHED
+ string
+ default "deadline" if DEFAULT_DEADLINE
+ default "cfq" if DEFAULT_CFQ
++ default "bfq" if DEFAULT_BFQ
+ default "noop" if DEFAULT_NOOP
+
+ endmenu
+diff --git a/block/Makefile b/block/Makefile
+index 39b76ba..c0d20fa 100644
+--- a/block/Makefile
++++ b/block/Makefile
+@@ -15,6 +15,7 @@ obj-$(CONFIG_BLK_DEV_THROTTLING) += blk-throttle.o
+ obj-$(CONFIG_IOSCHED_NOOP) += noop-iosched.o
+ obj-$(CONFIG_IOSCHED_DEADLINE) += deadline-iosched.o
+ obj-$(CONFIG_IOSCHED_CFQ) += cfq-iosched.o
++obj-$(CONFIG_IOSCHED_BFQ) += bfq-iosched.o
+
+ obj-$(CONFIG_BLOCK_COMPAT) += compat_ioctl.o
+ obj-$(CONFIG_BLK_DEV_INTEGRITY) += blk-integrity.o
+diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
+index 6e7ec64..e5e6b0d 100644
+--- a/include/linux/cgroup_subsys.h
++++ b/include/linux/cgroup_subsys.h
+@@ -84,3 +84,9 @@ SUBSYS(bcache)
+ #endif
+
+ /* */
++
++#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_BFQIO)
++SUBSYS(bfqio)
++#endif
++
++/* */
+--
+1.8.5.2
+
diff --git a/sys-kernel/kogaion-sources/files/desktop/0002-block-introduce-the-BFQ-v7-I-O-sched-for-3.10.patch b/sys-kernel/kogaion-sources/files/desktop/0002-block-introduce-the-BFQ-v7-I-O-sched-for-3.10.patch
new file mode 100644
index 00000000..0a2c5079
--- /dev/null
+++ b/sys-kernel/kogaion-sources/files/desktop/0002-block-introduce-the-BFQ-v7-I-O-sched-for-3.10.patch
@@ -0,0 +1,5969 @@
+From d40506359ff7f890adac4bd75541de73044a121e Mon Sep 17 00:00:00 2001
+From: Paolo Valente <paolo.valente@unimore.it>
+Date: Thu, 9 May 2013 19:10:02 +0200
+Subject: [PATCH 2/3] block: introduce the BFQ-v7 I/O sched for 3.10
+
+Add the BFQ-v7 I/O scheduler to 3.10.
+The general structure is borrowed from CFQ, as much of the code for
+handling I/O contexts Over time, several useful features have been
+ported from CFQ as well (details in the changelog in README.BFQ). A
+(bfq_)queue is associated to each task doing I/O on a device, and each
+time a scheduling decision has to be made a queue is selected and served
+until it expires.
+
+ - Slices are given in the service domain: tasks are assigned
+ budgets, measured in number of sectors. Once got the disk, a task
+ must however consume its assigned budget within a configurable
+ maximum time (by default, the maximum possible value of the
+ budgets is automatically computed to comply with this timeout).
+ This allows the desired latency vs "throughput boosting" tradeoff
+ to be set.
+
+ - Budgets are scheduled according to a variant of WF2Q+, implemented
+ using an augmented rb-tree to take eligibility into account while
+ preserving an O(log N) overall complexity.
+
+ - A low-latency tunable is provided; if enabled, both interactive
+ and soft real-time applications are guaranteed a very low latency.
+
+ - Latency guarantees are preserved also in the presence of NCQ.
+
+ - Also with flash-based devices, a high throughput is achieved
+ while still preserving latency guarantees.
+
+ - BFQ features Early Queue Merge (EQM), a sort of fusion of the
+ cooperating-queue-merging and the preemption mechanisms present
+ in CFQ. EQM is in fact a unified mechanism that tries to get a
+ sequential read pattern, and hence a high throughput, with any
+ set of processes performing interleaved I/O over a contiguous
+ sequence of sectors.
+
+ - BFQ supports full hierarchical scheduling, exporting a cgroups
+ interface. Since each node has a full scheduler, each group can
+ be assigned its own weight.
+
+ - If the cgroups interface is not used, only I/O priorities can be
+ assigned to processes, with ioprio values mapped to weights
+ with the relation weight = IOPRIO_BE_NR - ioprio.
+
+ - ioprio classes are served in strict priority order, i.e., lower
+ priority queues are not served as long as there are higher
+ priority queues. Among queues in the same class the bandwidth is
+ distributed in proportion to the weight of each queue. A very
+ thin extra bandwidth is however guaranteed to the Idle class, to
+ prevent it from starving.
+
+Signed-off-by: Paolo Valente <paolo.valente@unimore.it>
+Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
+---
+ block/bfq-cgroup.c | 885 ++++++++++++++
+ block/bfq-ioc.c | 36 +
+ block/bfq-iosched.c | 3256 +++++++++++++++++++++++++++++++++++++++++++++++++++
+ block/bfq-sched.c | 1077 +++++++++++++++++
+ block/bfq.h | 612 ++++++++++
+ 5 files changed, 5866 insertions(+)
+ create mode 100644 block/bfq-cgroup.c
+ create mode 100644 block/bfq-ioc.c
+ create mode 100644 block/bfq-iosched.c
+ create mode 100644 block/bfq-sched.c
+ create mode 100644 block/bfq.h
+
+diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
+new file mode 100644
+index 0000000..5a117ad
+--- /dev/null
++++ b/block/bfq-cgroup.c
+@@ -0,0 +1,885 @@
++/*
++ * BFQ: CGROUPS support.
++ *
++ * Based on ideas and code from CFQ:
++ * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
++ *
++ * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
++ * Paolo Valente <paolo.valente@unimore.it>
++ *
++ * Copyright (C) 2010 Paolo Valente <paolo.valente@unimore.it>
++ *
++ * Licensed under the GPL-2 as detailed in the accompanying COPYING.BFQ file.
++ */
++
++#ifdef CONFIG_CGROUP_BFQIO
++
++static DEFINE_MUTEX(bfqio_mutex);
++
++static bool bfqio_is_removed(struct cgroup *cgroup)
++{
++ return test_bit(CGRP_REMOVED, &cgroup->flags);
++}
++
++static struct bfqio_cgroup bfqio_root_cgroup = {
++ .weight = BFQ_DEFAULT_GRP_WEIGHT,
++ .ioprio = BFQ_DEFAULT_GRP_IOPRIO,
++ .ioprio_class = BFQ_DEFAULT_GRP_CLASS,
++};
++
++static inline void bfq_init_entity(struct bfq_entity *entity,
++ struct bfq_group *bfqg)
++{
++ entity->weight = entity->new_weight;
++ entity->orig_weight = entity->new_weight;
++ entity->ioprio = entity->new_ioprio;
++ entity->ioprio_class = entity->new_ioprio_class;
++ entity->parent = bfqg->my_entity;
++ entity->sched_data = &bfqg->sched_data;
++}
++
++static struct bfqio_cgroup *cgroup_to_bfqio(struct cgroup *cgroup)
++{
++ return container_of(cgroup_subsys_state(cgroup, bfqio_subsys_id),
++ struct bfqio_cgroup, css);
++}
++
++/*
++ * Search the bfq_group for bfqd into the hash table (by now only a list)
++ * of bgrp. Must be called under rcu_read_lock().
++ */
++static struct bfq_group *bfqio_lookup_group(struct bfqio_cgroup *bgrp,
++ struct bfq_data *bfqd)
++{
++ struct bfq_group *bfqg;
++ void *key;
++
++ hlist_for_each_entry_rcu(bfqg, &bgrp->group_data, group_node) {
++ key = rcu_dereference(bfqg->bfqd);
++ if (key == bfqd)
++ return bfqg;
++ }
++
++ return NULL;
++}
++
++static inline void bfq_group_init_entity(struct bfqio_cgroup *bgrp,
++ struct bfq_group *bfqg)
++{
++ struct bfq_entity *entity = &bfqg->entity;
++
++ /*
++ * If the weight of the entity has never been set via the sysfs
++ * interface, then bgrp->weight == 0. In this case we initialize
++ * the weight from the current ioprio value. Otherwise, the group
++ * weight, if set, has priority over the ioprio value.
++ */
++ if (bgrp->weight == 0) {
++ entity->new_weight = bfq_ioprio_to_weight(bgrp->ioprio);
++ entity->new_ioprio = bgrp->ioprio;
++ } else {
++ entity->new_weight = bgrp->weight;
++ entity->new_ioprio = bfq_weight_to_ioprio(bgrp->weight);
++ }
++ entity->orig_weight = entity->weight = entity->new_weight;
++ entity->ioprio = entity->new_ioprio;
++ entity->ioprio_class = entity->new_ioprio_class = bgrp->ioprio_class;
++ entity->my_sched_data = &bfqg->sched_data;
++}
++
++static inline void bfq_group_set_parent(struct bfq_group *bfqg,
++ struct bfq_group *parent)
++{
++ struct bfq_entity *entity;
++
++ BUG_ON(parent == NULL);
++ BUG_ON(bfqg == NULL);
++
++ entity = &bfqg->entity;
++ entity->parent = parent->my_entity;
++ entity->sched_data = &parent->sched_data;
++}
++
++/**
++ * bfq_group_chain_alloc - allocate a chain of groups.
++ * @bfqd: queue descriptor.
++ * @cgroup: the leaf cgroup this chain starts from.
++ *
++ * Allocate a chain of groups starting from the one belonging to
++ * @cgroup up to the root cgroup. Stop if a cgroup on the chain
++ * to the root has already an allocated group on @bfqd.
++ */
++static struct bfq_group *bfq_group_chain_alloc(struct bfq_data *bfqd,
++ struct cgroup *cgroup)
++{
++ struct bfqio_cgroup *bgrp;
++ struct bfq_group *bfqg, *prev = NULL, *leaf = NULL;
++
++ for (; cgroup != NULL; cgroup = cgroup->parent) {
++ bgrp = cgroup_to_bfqio(cgroup);
++
++ bfqg = bfqio_lookup_group(bgrp, bfqd);
++ if (bfqg != NULL) {
++ /*
++ * All the cgroups in the path from there to the
++ * root must have a bfq_group for bfqd, so we don't
++ * need any more allocations.
++ */
++ break;
++ }
++
++ bfqg = kzalloc(sizeof(*bfqg), GFP_ATOMIC);
++ if (bfqg == NULL)
++ goto cleanup;
++
++ bfq_group_init_entity(bgrp, bfqg);
++ bfqg->my_entity = &bfqg->entity;
++
++ if (leaf == NULL) {
++ leaf = bfqg;
++ prev = leaf;
++ } else {
++ bfq_group_set_parent(prev, bfqg);
++ /*
++ * Build a list of allocated nodes using the bfqd
++ * filed, that is still unused and will be initialized
++ * only after the node will be connected.
++ */
++ prev->bfqd = bfqg;
++ prev = bfqg;
++ }
++ }
++
++ return leaf;
++
++cleanup:
++ while (leaf != NULL) {
++ prev = leaf;
++ leaf = leaf->bfqd;
++ kfree(prev);
++ }
++
++ return NULL;
++}
++
++/**
++ * bfq_group_chain_link - link an allocatd group chain to a cgroup hierarchy.
++ * @bfqd: the queue descriptor.
++ * @cgroup: the leaf cgroup to start from.
++ * @leaf: the leaf group (to be associated to @cgroup).
++ *
++ * Try to link a chain of groups to a cgroup hierarchy, connecting the
++ * nodes bottom-up, so we can be sure that when we find a cgroup in the
++ * hierarchy that already as a group associated to @bfqd all the nodes
++ * in the path to the root cgroup have one too.
++ *
++ * On locking: the queue lock protects the hierarchy (there is a hierarchy
++ * per device) while the bfqio_cgroup lock protects the list of groups
++ * belonging to the same cgroup.
++ */
++static void bfq_group_chain_link(struct bfq_data *bfqd, struct cgroup *cgroup,
++ struct bfq_group *leaf)
++{
++ struct bfqio_cgroup *bgrp;
++ struct bfq_group *bfqg, *next, *prev = NULL;
++ unsigned long flags;
++
++ assert_spin_locked(bfqd->queue->queue_lock);
++
++ for (; cgroup != NULL && leaf != NULL; cgroup = cgroup->parent) {
++ bgrp = cgroup_to_bfqio(cgroup);
++ next = leaf->bfqd;
++
++ bfqg = bfqio_lookup_group(bgrp, bfqd);
++ BUG_ON(bfqg != NULL);
++
++ spin_lock_irqsave(&bgrp->lock, flags);
++
++ rcu_assign_pointer(leaf->bfqd, bfqd);
++ hlist_add_head_rcu(&leaf->group_node, &bgrp->group_data);
++ hlist_add_head(&leaf->bfqd_node, &bfqd->group_list);
++
++ spin_unlock_irqrestore(&bgrp->lock, flags);
++
++ prev = leaf;
++ leaf = next;
++ }
++
++ BUG_ON(cgroup == NULL && leaf != NULL);
++ if (cgroup != NULL && prev != NULL) {
++ bgrp = cgroup_to_bfqio(cgroup);
++ bfqg = bfqio_lookup_group(bgrp, bfqd);
++ bfq_group_set_parent(prev, bfqg);
++ }
++}
++
++/**
++ * bfq_find_alloc_group - return the group associated to @bfqd in @cgroup.
++ * @bfqd: queue descriptor.
++ * @cgroup: cgroup being searched for.
++ *
++ * Return a group associated to @bfqd in @cgroup, allocating one if
++ * necessary. When a group is returned all the cgroups in the path
++ * to the root have a group associated to @bfqd.
++ *
++ * If the allocation fails, return the root group: this breaks guarantees
++ * but is a safe fallbak. If this loss becames a problem it can be
++ * mitigated using the equivalent weight (given by the product of the
++ * weights of the groups in the path from @group to the root) in the
++ * root scheduler.
++ *
++ * We allocate all the missing nodes in the path from the leaf cgroup
++ * to the root and we connect the nodes only after all the allocations
++ * have been successful.
++ */
++static struct bfq_group *bfq_find_alloc_group(struct bfq_data *bfqd,
++ struct cgroup *cgroup)
++{
++ struct bfqio_cgroup *bgrp = cgroup_to_bfqio(cgroup);
++ struct bfq_group *bfqg;
++
++ bfqg = bfqio_lookup_group(bgrp, bfqd);
++ if (bfqg != NULL)
++ return bfqg;
++
++ bfqg = bfq_group_chain_alloc(bfqd, cgroup);
++ if (bfqg != NULL)
++ bfq_group_chain_link(bfqd, cgroup, bfqg);
++ else
++ bfqg = bfqd->root_group;
++
++ return bfqg;
++}
++
++/**
++ * bfq_bfqq_move - migrate @bfqq to @bfqg.
++ * @bfqd: queue descriptor.
++ * @bfqq: the queue to move.
++ * @entity: @bfqq's entity.
++ * @bfqg: the group to move to.
++ *
++ * Move @bfqq to @bfqg, deactivating it from its old group and reactivating
++ * it on the new one. Avoid putting the entity on the old group idle tree.
++ *
++ * Must be called under the queue lock; the cgroup owning @bfqg must
++ * not disappear (by now this just means that we are called under
++ * rcu_read_lock()).
++ */
++static void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
++ struct bfq_entity *entity, struct bfq_group *bfqg)
++{
++ int busy, resume;
++
++ busy = bfq_bfqq_busy(bfqq);
++ resume = !RB_EMPTY_ROOT(&bfqq->sort_list);
++
++ BUG_ON(resume && !entity->on_st);
++ BUG_ON(busy && !resume && entity->on_st &&
++ bfqq != bfqd->in_service_queue);
++
++ if (busy) {
++ BUG_ON(atomic_read(&bfqq->ref) < 2);
++
++ if (!resume)
++ bfq_del_bfqq_busy(bfqd, bfqq, 0);
++ else
++ bfq_deactivate_bfqq(bfqd, bfqq, 0);
++ } else if (entity->on_st)
++ bfq_put_idle_entity(bfq_entity_service_tree(entity), entity);
++
++ /*
++ * Here we use a reference to bfqg. We don't need a refcounter
++ * as the cgroup reference will not be dropped, so that its
++ * destroy() callback will not be invoked.
++ */
++ entity->parent = bfqg->my_entity;
++ entity->sched_data = &bfqg->sched_data;
++
++ if (busy && resume)
++ bfq_activate_bfqq(bfqd, bfqq);
++
++ if (bfqd->in_service_queue == NULL && !bfqd->rq_in_driver)
++ bfq_schedule_dispatch(bfqd);
++}
++
++/**
++ * __bfq_bic_change_cgroup - move @bic to @cgroup.
++ * @bfqd: the queue descriptor.
++ * @bic: the bic to move.
++ * @cgroup: the cgroup to move to.
++ *
++ * Move bic to cgroup, assuming that bfqd->queue is locked; the caller
++ * has to make sure that the reference to cgroup is valid across the call.
++ *
++ * NOTE: an alternative approach might have been to store the current
++ * cgroup in bfqq and getting a reference to it, reducing the lookup
++ * time here, at the price of slightly more complex code.
++ */
++static struct bfq_group *__bfq_bic_change_cgroup(struct bfq_data *bfqd,
++ struct bfq_io_cq *bic,
++ struct cgroup *cgroup)
++{
++ struct bfq_queue *async_bfqq = bic_to_bfqq(bic, 0);
++ struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, 1);
++ struct bfq_entity *entity;
++ struct bfq_group *bfqg;
++ struct bfqio_cgroup *bgrp;
++
++ bgrp = cgroup_to_bfqio(cgroup);
++
++ bfqg = bfq_find_alloc_group(bfqd, cgroup);
++ if (async_bfqq != NULL) {
++ entity = &async_bfqq->entity;
++
++ if (entity->sched_data != &bfqg->sched_data) {
++ bic_set_bfqq(bic, NULL, 0);
++ bfq_log_bfqq(bfqd, async_bfqq,
++ "bic_change_group: %p %d",
++ async_bfqq, atomic_read(&async_bfqq->ref));
++ bfq_put_queue(async_bfqq);
++ }
++ }
++
++ if (sync_bfqq != NULL) {
++ entity = &sync_bfqq->entity;
++ if (entity->sched_data != &bfqg->sched_data)
++ bfq_bfqq_move(bfqd, sync_bfqq, entity, bfqg);
++ }
++
++ return bfqg;
++}
++
++/**
++ * bfq_bic_change_cgroup - move @bic to @cgroup.
++ * @bic: the bic being migrated.
++ * @cgroup: the destination cgroup.
++ *
++ * When the task owning @bic is moved to @cgroup, @bic is immediately
++ * moved into its new parent group.
++ */
++static void bfq_bic_change_cgroup(struct bfq_io_cq *bic,
++ struct cgroup *cgroup)
++{
++ struct bfq_data *bfqd;
++ unsigned long uninitialized_var(flags);
++
++ bfqd = bfq_get_bfqd_locked(&(bic->icq.q->elevator->elevator_data),
++ &flags);
++ if (bfqd != NULL) {
++ __bfq_bic_change_cgroup(bfqd, bic, cgroup);
++ bfq_put_bfqd_unlock(bfqd, &flags);
++ }
++}
++
++/**
++ * bfq_bic_update_cgroup - update the cgroup of @bic.
++ * @bic: the @bic to update.
++ *
++ * Make sure that @bic is enqueued in the cgroup of the current task.
++ * We need this in addition to moving bics during the cgroup attach
++ * phase because the task owning @bic could be at its first disk
++ * access or we may end up in the root cgroup as the result of a
++ * memory allocation failure and here we try to move to the right
++ * group.
++ *
++ * Must be called under the queue lock. It is safe to use the returned
++ * value even after the rcu_read_unlock() as the migration/destruction
++ * paths act under the queue lock too. IOW it is impossible to race with
++ * group migration/destruction and end up with an invalid group as:
++ * a) here cgroup has not yet been destroyed, nor its destroy callback
++ * has started execution, as current holds a reference to it,
++ * b) if it is destroyed after rcu_read_unlock() [after current is
++ * migrated to a different cgroup] its attach() callback will have
++ * taken care of remove all the references to the old cgroup data.
++ */
++static struct bfq_group *bfq_bic_update_cgroup(struct bfq_io_cq *bic)
++{
++ struct bfq_data *bfqd = bic_to_bfqd(bic);
++ struct bfq_group *bfqg;
++ struct cgroup *cgroup;
++
++ BUG_ON(bfqd == NULL);
++
++ rcu_read_lock();
++ cgroup = task_cgroup(current, bfqio_subsys_id);
++ bfqg = __bfq_bic_change_cgroup(bfqd, bic, cgroup);
++ rcu_read_unlock();
++
++ return bfqg;
++}
++
++/**
++ * bfq_flush_idle_tree - deactivate any entity on the idle tree of @st.
++ * @st: the service tree being flushed.
++ */
++static inline void bfq_flush_idle_tree(struct bfq_service_tree *st)
++{
++ struct bfq_entity *entity = st->first_idle;
++
++ for (; entity != NULL; entity = st->first_idle)
++ __bfq_deactivate_entity(entity, 0);
++}
++
++/**
++ * bfq_reparent_leaf_entity - move leaf entity to the root_group.
++ * @bfqd: the device data structure with the root group.
++ * @entity: the entity to move.
++ */
++static inline void bfq_reparent_leaf_entity(struct bfq_data *bfqd,
++ struct bfq_entity *entity)
++{
++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
++
++ BUG_ON(bfqq == NULL);
++ bfq_bfqq_move(bfqd, bfqq, entity, bfqd->root_group);
++ return;
++}
++
++/**
++ * bfq_reparent_active_entities - move to the root group all active entities.
++ * @bfqd: the device data structure with the root group.
++ * @bfqg: the group to move from.
++ * @st: the service tree with the entities.
++ *
++ * Needs queue_lock to be taken and reference to be valid over the call.
++ */
++static inline void bfq_reparent_active_entities(struct bfq_data *bfqd,
++ struct bfq_group *bfqg,
++ struct bfq_service_tree *st)
++{
++ struct rb_root *active = &st->active;
++ struct bfq_entity *entity = NULL;
++
++ if (!RB_EMPTY_ROOT(&st->active))
++ entity = bfq_entity_of(rb_first(active));
++
++ for (; entity != NULL; entity = bfq_entity_of(rb_first(active)))
++ bfq_reparent_leaf_entity(bfqd, entity);
++
++ if (bfqg->sched_data.active_entity != NULL)
++ bfq_reparent_leaf_entity(bfqd, bfqg->sched_data.active_entity);
++
++ return;
++}
++
++/**
++ * bfq_destroy_group - destroy @bfqg.
++ * @bgrp: the bfqio_cgroup containing @bfqg.
++ * @bfqg: the group being destroyed.
++ *
++ * Destroy @bfqg, making sure that it is not referenced from its parent.
++ */
++static void bfq_destroy_group(struct bfqio_cgroup *bgrp, struct bfq_group *bfqg)
++{
++ struct bfq_data *bfqd;
++ struct bfq_service_tree *st;
++ struct bfq_entity *entity = bfqg->my_entity;
++ unsigned long uninitialized_var(flags);
++ int i;
++
++ hlist_del(&bfqg->group_node);
++
++ /*
++ * Empty all service_trees belonging to this group before deactivating
++ * the group itself.
++ */
++ for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) {
++ st = bfqg->sched_data.service_tree + i;
++
++ /*
++ * The idle tree may still contain bfq_queues belonging
++ * to exited task because they never migrated to a different
++ * cgroup from the one being destroyed now. Noone else
++ * can access them so it's safe to act without any lock.
++ */
++ bfq_flush_idle_tree(st);
++
++ /*
++ * It may happen that some queues are still active
++ * (busy) upon group destruction (if the corresponding
++ * processes have been forced to terminate). We move
++ * all the leaf entities corresponding to these queues
++ * to the root_group.
++ * Also, it may happen that the group has an entity
++ * under service, which is disconnected from the active
++ * tree: it must be moved, too.
++ * There is no need to put the sync queues, as the
++ * scheduler has taken no reference.
++ */
++ bfqd = bfq_get_bfqd_locked(&bfqg->bfqd, &flags);
++ if (bfqd != NULL) {
++ bfq_reparent_active_entities(bfqd, bfqg, st);
++ bfq_put_bfqd_unlock(bfqd, &flags);
++ }
++ BUG_ON(!RB_EMPTY_ROOT(&st->active));
++ BUG_ON(!RB_EMPTY_ROOT(&st->idle));
++ }
++ BUG_ON(bfqg->sched_data.next_active != NULL);
++ BUG_ON(bfqg->sched_data.active_entity != NULL);
++
++ /*
++ * We may race with device destruction, take extra care when
++ * dereferencing bfqg->bfqd.
++ */
++ bfqd = bfq_get_bfqd_locked(&bfqg->bfqd, &flags);
++ if (bfqd != NULL) {
++ hlist_del(&bfqg->bfqd_node);
++ __bfq_deactivate_entity(entity, 0);
++ bfq_put_async_queues(bfqd, bfqg);
++ bfq_put_bfqd_unlock(bfqd, &flags);
++ }
++ BUG_ON(entity->tree != NULL);
++
++ /*
++ * No need to defer the kfree() to the end of the RCU grace
++ * period: we are called from the destroy() callback of our
++ * cgroup, so we can be sure that noone is a) still using
++ * this cgroup or b) doing lookups in it.
++ */
++ kfree(bfqg);
++}
++
++static void bfq_end_raising_async(struct bfq_data *bfqd)
++{
++ struct hlist_node *tmp;
++ struct bfq_group *bfqg;
++
++ hlist_for_each_entry_safe(bfqg, tmp, &bfqd->group_list, bfqd_node)
++ bfq_end_raising_async_queues(bfqd, bfqg);
++ bfq_end_raising_async_queues(bfqd, bfqd->root_group);
++}
++
++/**
++ * bfq_disconnect_groups - diconnect @bfqd from all its groups.
++ * @bfqd: the device descriptor being exited.
++ *
++ * When the device exits we just make sure that no lookup can return
++ * the now unused group structures. They will be deallocated on cgroup
++ * destruction.
++ */
++static void bfq_disconnect_groups(struct bfq_data *bfqd)
++{
++ struct hlist_node *tmp;
++ struct bfq_group *bfqg;
++
++ bfq_log(bfqd, "disconnect_groups beginning");
++ hlist_for_each_entry_safe(bfqg, tmp, &bfqd->group_list, bfqd_node) {
++ hlist_del(&bfqg->bfqd_node);
++
++ __bfq_deactivate_entity(bfqg->my_entity, 0);
++
++ /*
++ * Don't remove from the group hash, just set an
++ * invalid key. No lookups can race with the
++ * assignment as bfqd is being destroyed; this
++ * implies also that new elements cannot be added
++ * to the list.
++ */
++ rcu_assign_pointer(bfqg->bfqd, NULL);
++
++ bfq_log(bfqd, "disconnect_groups: put async for group %p",
++ bfqg);
++ bfq_put_async_queues(bfqd, bfqg);
++ }
++}
++
++static inline void bfq_free_root_group(struct bfq_data *bfqd)
++{
++ struct bfqio_cgroup *bgrp = &bfqio_root_cgroup;
++ struct bfq_group *bfqg = bfqd->root_group;
++
++ bfq_put_async_queues(bfqd, bfqg);
++
++ spin_lock_irq(&bgrp->lock);
++ hlist_del_rcu(&bfqg->group_node);
++ spin_unlock_irq(&bgrp->lock);
++
++ /*
++ * No need to synchronize_rcu() here: since the device is gone
++ * there cannot be any read-side access to its root_group.
++ */
++ kfree(bfqg);
++}
++
++static struct bfq_group *bfq_alloc_root_group(struct bfq_data *bfqd, int node)
++{
++ struct bfq_group *bfqg;
++ struct bfqio_cgroup *bgrp;
++ int i;
++
++ bfqg = kzalloc_node(sizeof(*bfqg), GFP_KERNEL, node);
++ if (bfqg == NULL)
++ return NULL;
++
++ bfqg->entity.parent = NULL;
++ for (i = 0; i < BFQ_IOPRIO_CLASSES; i++)
++ bfqg->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT;
++
++ bgrp = &bfqio_root_cgroup;
++ spin_lock_irq(&bgrp->lock);
++ rcu_assign_pointer(bfqg->bfqd, bfqd);
++ hlist_add_head_rcu(&bfqg->group_node, &bgrp->group_data);
++ spin_unlock_irq(&bgrp->lock);
++
++ return bfqg;
++}
++
++#define SHOW_FUNCTION(__VAR) \
++static u64 bfqio_cgroup_##__VAR##_read(struct cgroup *cgroup, \
++ struct cftype *cftype) \
++{ \
++ struct bfqio_cgroup *bgrp; \
++ u64 ret = -ENODEV; \
++ \
++ mutex_lock(&bfqio_mutex); \
++ if (bfqio_is_removed(cgroup)) \
++ goto out_unlock; \
++ \
++ bgrp = cgroup_to_bfqio(cgroup); \
++ spin_lock_irq(&bgrp->lock); \
++ ret = bgrp->__VAR; \
++ spin_unlock_irq(&bgrp->lock); \
++ \
++out_unlock: \
++ mutex_unlock(&bfqio_mutex); \
++ return ret; \
++}
++
++SHOW_FUNCTION(weight);
++SHOW_FUNCTION(ioprio);
++SHOW_FUNCTION(ioprio_class);
++#undef SHOW_FUNCTION
++
++#define STORE_FUNCTION(__VAR, __MIN, __MAX) \
++static int bfqio_cgroup_##__VAR##_write(struct cgroup *cgroup, \
++ struct cftype *cftype, \
++ u64 val) \
++{ \
++ struct bfqio_cgroup *bgrp; \
++ struct bfq_group *bfqg; \
++ int ret = -EINVAL; \
++ \
++ if (val < (__MIN) || val > (__MAX)) \
++ return ret; \
++ \
++ ret = -ENODEV; \
++ mutex_lock(&bfqio_mutex); \
++ if (bfqio_is_removed(cgroup)) \
++ goto out_unlock; \
++ ret = 0; \
++ \
++ bgrp = cgroup_to_bfqio(cgroup); \
++ \
++ spin_lock_irq(&bgrp->lock); \
++ bgrp->__VAR = (unsigned short)val; \
++ hlist_for_each_entry(bfqg, &bgrp->group_data, group_node) { \
++ /* \
++ * Setting the ioprio_changed flag of the entity \
++ * to 1 with new_##__VAR == ##__VAR would re-set \
++ * the value of the weight to its ioprio mapping. \
++ * Set the flag only if necessary. \
++ */ \
++ if ((unsigned short)val != bfqg->entity.new_##__VAR) { \
++ bfqg->entity.new_##__VAR = (unsigned short)val; \
++ smp_wmb(); \
++ bfqg->entity.ioprio_changed = 1; \
++ } \
++ } \
++ spin_unlock_irq(&bgrp->lock); \
++ \
++out_unlock: \
++ mutex_unlock(&bfqio_mutex); \
++ return ret; \
++}
++
++STORE_FUNCTION(weight, BFQ_MIN_WEIGHT, BFQ_MAX_WEIGHT);
++STORE_FUNCTION(ioprio, 0, IOPRIO_BE_NR - 1);
++STORE_FUNCTION(ioprio_class, IOPRIO_CLASS_RT, IOPRIO_CLASS_IDLE);
++#undef STORE_FUNCTION
++
++static struct cftype bfqio_files[] = {
++ {
++ .name = "weight",
++ .read_u64 = bfqio_cgroup_weight_read,
++ .write_u64 = bfqio_cgroup_weight_write,
++ },
++ {
++ .name = "ioprio",
++ .read_u64 = bfqio_cgroup_ioprio_read,
++ .write_u64 = bfqio_cgroup_ioprio_write,
++ },
++ {
++ .name = "ioprio_class",
++ .read_u64 = bfqio_cgroup_ioprio_class_read,
++ .write_u64 = bfqio_cgroup_ioprio_class_write,
++ },
++ { }, /* terminate */
++};
++
++static struct cgroup_subsys_state *bfqio_create(struct cgroup *cgroup)
++{
++ struct bfqio_cgroup *bgrp;
++
++ if (cgroup->parent != NULL) {
++ bgrp = kzalloc(sizeof(*bgrp), GFP_KERNEL);
++ if (bgrp == NULL)
++ return ERR_PTR(-ENOMEM);
++ } else
++ bgrp = &bfqio_root_cgroup;
++
++ spin_lock_init(&bgrp->lock);
++ INIT_HLIST_HEAD(&bgrp->group_data);
++ bgrp->ioprio = BFQ_DEFAULT_GRP_IOPRIO;
++ bgrp->ioprio_class = BFQ_DEFAULT_GRP_CLASS;
++
++ return &bgrp->css;
++}
++
++/*
++ * We cannot support shared io contexts, as we have no means to support
++ * two tasks with the same ioc in two different groups without major rework
++ * of the main bic/bfqq data structures. By now we allow a task to change
++ * its cgroup only if it's the only owner of its ioc; the drawback of this
++ * behavior is that a group containing a task that forked using CLONE_IO
++ * will not be destroyed until the tasks sharing the ioc die.
++ */
++static int bfqio_can_attach(struct cgroup *cgroup, struct cgroup_taskset *tset)
++{
++ struct task_struct *task;
++ struct io_context *ioc;
++ int ret = 0;
++
++ cgroup_taskset_for_each(task, cgroup, tset) {
++ /* task_lock() is needed to avoid races with exit_io_context() */
++ task_lock(task);
++ ioc = task->io_context;
++ if (ioc != NULL && atomic_read(&ioc->nr_tasks) > 1)
++ /*
++ * ioc == NULL means that the task is either too young or
++ * exiting: if it has still no ioc the ioc can't be shared,
++ * if the task is exiting the attach will fail anyway, no
++ * matter what we return here.
++ */
++ ret = -EINVAL;
++ task_unlock(task);
++ if (ret)
++ break;
++ }
++
++ return ret;
++}
++
++static void bfqio_attach(struct cgroup *cgroup, struct cgroup_taskset *tset)
++{
++ struct task_struct *task;
++ struct io_context *ioc;
++ struct io_cq *icq;
++
++ /*
++ * IMPORTANT NOTE: The move of more than one process at a time to a
++ * new group has not yet been tested.
++ */
++ cgroup_taskset_for_each(task, cgroup, tset) {
++ ioc = get_task_io_context(task, GFP_ATOMIC, NUMA_NO_NODE);
++ if (ioc) {
++ /*
++ * Handle cgroup change here.
++ */
++ rcu_read_lock();
++ hlist_for_each_entry_rcu(icq, &ioc->icq_list, ioc_node)
++ if (!strncmp(
++ icq->q->elevator->type->elevator_name,
++ "bfq", ELV_NAME_MAX))
++ bfq_bic_change_cgroup(icq_to_bic(icq),
++ cgroup);
++ rcu_read_unlock();
++ put_io_context(ioc);
++ }
++ }
++}
++
++static void bfqio_destroy(struct cgroup *cgroup)
++{
++ struct bfqio_cgroup *bgrp = cgroup_to_bfqio(cgroup);
++ struct hlist_node *tmp;
++ struct bfq_group *bfqg;
++
++ /*
++ * Since we are destroying the cgroup, there are no more tasks
++ * referencing it, and all the RCU grace periods that may have
++ * referenced it are ended (as the destruction of the parent
++ * cgroup is RCU-safe); bgrp->group_data will not be accessed by
++ * anything else and we don't need any synchronization.
++ */
++ hlist_for_each_entry_safe(bfqg, tmp, &bgrp->group_data, group_node)
++ bfq_destroy_group(bgrp, bfqg);
++
++ BUG_ON(!hlist_empty(&bgrp->group_data));
++
++ kfree(bgrp);
++}
++
++struct cgroup_subsys bfqio_subsys = {
++ .name = "bfqio",
++ .css_alloc = bfqio_create,
++ .can_attach = bfqio_can_attach,
++ .attach = bfqio_attach,
++ .css_free = bfqio_destroy,
++ .subsys_id = bfqio_subsys_id,
++ .base_cftypes = bfqio_files,
++};
++#else
++static inline void bfq_init_entity(struct bfq_entity *entity,
++ struct bfq_group *bfqg)
++{
++ entity->weight = entity->new_weight;
++ entity->orig_weight = entity->new_weight;
++ entity->ioprio = entity->new_ioprio;
++ entity->ioprio_class = entity->new_ioprio_class;
++ entity->sched_data = &bfqg->sched_data;
++}
++
++static inline struct bfq_group *
++bfq_bic_update_cgroup(struct bfq_io_cq *bic)
++{
++ struct bfq_data *bfqd = bic_to_bfqd(bic);
++ return bfqd->root_group;
++}
++
++static inline void bfq_bfqq_move(struct bfq_data *bfqd,
++ struct bfq_queue *bfqq,
++ struct bfq_entity *entity,
++ struct bfq_group *bfqg)
++{
++}
++
++static void bfq_end_raising_async(struct bfq_data *bfqd)
++{
++ bfq_end_raising_async_queues(bfqd, bfqd->root_group);
++}
++
++static inline void bfq_disconnect_groups(struct bfq_data *bfqd)
++{
++ bfq_put_async_queues(bfqd, bfqd->root_group);
++}
++
++static inline void bfq_free_root_group(struct bfq_data *bfqd)
++{
++ kfree(bfqd->root_group);
++}
++
++static struct bfq_group *bfq_alloc_root_group(struct bfq_data *bfqd, int node)
++{
++ struct bfq_group *bfqg;
++ int i;
++
++ bfqg = kmalloc_node(sizeof(*bfqg), GFP_KERNEL | __GFP_ZERO, node);
++ if (bfqg == NULL)
++ return NULL;
++
++ for (i = 0; i < BFQ_IOPRIO_CLASSES; i++)
++ bfqg->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT;
++
++ return bfqg;
++}
++#endif
+diff --git a/block/bfq-ioc.c b/block/bfq-ioc.c
+new file mode 100644
+index 0000000..7f6b000
+--- /dev/null
++++ b/block/bfq-ioc.c
+@@ -0,0 +1,36 @@
++/*
++ * BFQ: I/O context handling.
++ *
++ * Based on ideas and code from CFQ:
++ * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
++ *
++ * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
++ * Paolo Valente <paolo.valente@unimore.it>
++ *
++ * Copyright (C) 2010 Paolo Valente <paolo.valente@unimore.it>
++ */
++
++/**
++ * icq_to_bic - convert iocontext queue structure to bfq_io_cq.
++ * @icq: the iocontext queue.
++ */
++static inline struct bfq_io_cq *icq_to_bic(struct io_cq *icq)
++{
++ /* bic->icq is the first member, %NULL will convert to %NULL */
++ return container_of(icq, struct bfq_io_cq, icq);
++}
++
++/**
++ * bfq_bic_lookup - search into @ioc a bic associated to @bfqd.
++ * @bfqd: the lookup key.
++ * @ioc: the io_context of the process doing I/O.
++ *
++ * Queue lock must be held.
++ */
++static inline struct bfq_io_cq *bfq_bic_lookup(struct bfq_data *bfqd,
++ struct io_context *ioc)
++{
++ if (ioc)
++ return icq_to_bic(ioc_lookup_icq(ioc, bfqd->queue));
++ return NULL;
++}
+diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
+new file mode 100644
+index 0000000..96abb81
+--- /dev/null
++++ b/block/bfq-iosched.c
+@@ -0,0 +1,3256 @@
++/*
++ * BFQ, or Budget Fair Queueing, disk scheduler.
++ *
++ * Based on ideas and code from CFQ:
++ * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
++ *
++ * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
++ * Paolo Valente <paolo.valente@unimore.it>
++ *
++ * Copyright (C) 2010 Paolo Valente <paolo.valente@unimore.it>
++ *
++ * Licensed under the GPL-2 as detailed in the accompanying COPYING.BFQ file.
++ *
++ * BFQ is a proportional share disk scheduling algorithm based on the
++ * slice-by-slice service scheme of CFQ. But BFQ assigns budgets, measured in
++ * number of sectors, to tasks instead of time slices. The disk is not granted
++ * to the in-service task for a given time slice, but until it has exahusted
++ * its assigned budget. This change from the time to the service domain allows
++ * BFQ to distribute the disk bandwidth among tasks as desired, without any
++ * distortion due to ZBR, workload fluctuations or other factors. BFQ uses an
++ * ad hoc internal scheduler, called B-WF2Q+, to schedule tasks according to
++ * their budgets (more precisely BFQ schedules queues associated to tasks).
++ * Thanks to this accurate scheduler, BFQ can afford to assign high budgets to
++ * disk-bound non-seeky tasks (to boost the throughput), and yet guarantee low
++ * latencies to interactive and soft real-time applications.
++ *
++ * BFQ is described in [1], where also a reference to the initial, more
++ * theoretical paper on BFQ can be found. The interested reader can find in
++ * the latter paper full details on the main algorithm as well as formulas of
++ * the guarantees, plus formal proofs of all the properties. With respect to
++ * the version of BFQ presented in these papers, this implementation adds a
++ * few more heuristics, such as the one that guarantees a low latency to soft
++ * real-time applications, and a hierarchical extension based on H-WF2Q+.
++ *
++ * B-WF2Q+ is based on WF2Q+, that is described in [2], together with
++ * H-WF2Q+, while the augmented tree used to implement B-WF2Q+ with O(log N)
++ * complexity derives from the one introduced with EEVDF in [3].
++ *
++ * [1] P. Valente and M. Andreolini, ``Improving Application Responsiveness
++ * with the BFQ Disk I/O Scheduler'',
++ * Proceedings of the 5th Annual International Systems and Storage
++ * Conference (SYSTOR '12), June 2012.
++ *
++ * http://algogroup.unimo.it/people/paolo/disk_sched/bf1-v1-suite-results.pdf
++ *
++ * [2] Jon C.R. Bennett and H. Zhang, ``Hierarchical Packet Fair Queueing
++ * Algorithms,'' IEEE/ACM Transactions on Networking, 5(5):675-689,
++ * Oct 1997.
++ *
++ * http://www.cs.cmu.edu/~hzhang/papers/TON-97-Oct.ps.gz
++ *
++ * [3] I. Stoica and H. Abdel-Wahab, ``Earliest Eligible Virtual Deadline
++ * First: A Flexible and Accurate Mechanism for Proportional Share
++ * Resource Allocation,'' technical report.
++ *
++ * http://www.cs.berkeley.edu/~istoica/papers/eevdf-tr-95.pdf
++ */
++#include <linux/module.h>
++#include <linux/slab.h>
++#include <linux/blkdev.h>
++#include <linux/cgroup.h>
++#include <linux/elevator.h>
++#include <linux/jiffies.h>
++#include <linux/rbtree.h>
++#include <linux/ioprio.h>
++#include "bfq.h"
++#include "blk.h"
++
++/* Max number of dispatches in one round of service. */
++static const int bfq_quantum = 4;
++
++/* Expiration time of sync (0) and async (1) requests, in jiffies. */
++static const int bfq_fifo_expire[2] = { HZ / 4, HZ / 8 };
++
++/* Maximum backwards seek, in KiB. */
++static const int bfq_back_max = 16 * 1024;
++
++/* Penalty of a backwards seek, in number of sectors. */
++static const int bfq_back_penalty = 2;
++
++/* Idling period duration, in jiffies. */
++static int bfq_slice_idle = HZ / 125;
++
++/* Default maximum budget values, in sectors and number of requests. */
++static const int bfq_default_max_budget = 16 * 1024;
++static const int bfq_max_budget_async_rq = 4;
++
++/*
++ * Async to sync throughput distribution is controlled as follows:
++ * when an async request is served, the entity is charged the number
++ * of sectors of the request, multipled by the factor below
++ */
++static const int bfq_async_charge_factor = 10;
++
++/* Default timeout values, in jiffies, approximating CFQ defaults. */
++static const int bfq_timeout_sync = HZ / 8;
++static int bfq_timeout_async = HZ / 25;
++
++struct kmem_cache *bfq_pool;
++
++/* Below this threshold (in ms), we consider thinktime immediate. */
++#define BFQ_MIN_TT 2
++
++/* hw_tag detection: parallel requests threshold and min samples needed. */
++#define BFQ_HW_QUEUE_THRESHOLD 4
++#define BFQ_HW_QUEUE_SAMPLES 32
++
++#define BFQQ_SEEK_THR (sector_t)(8 * 1024)
++#define BFQQ_SEEKY(bfqq) ((bfqq)->seek_mean > BFQQ_SEEK_THR)
++
++/* Min samples used for peak rate estimation (for autotuning). */
++#define BFQ_PEAK_RATE_SAMPLES 32
++
++/* Shift used for peak rate fixed precision calculations. */
++#define BFQ_RATE_SHIFT 16
++
++/*
++ * The duration of the weight raising for interactive applications is
++ * computed automatically (as default behaviour), using the following
++ * formula: duration = (R / r) * T, where r is the peak rate of the
++ * disk, and R and T are two reference parameters. In particular, R is
++ * the peak rate of a reference disk, and T is about the maximum time
++ * for starting popular large applications on that disk, under BFQ and
++ * while reading two files in parallel. Finally, BFQ uses two
++ * different pairs (R, T) depending on whether the disk is rotational
++ * or non-rotational.
++ */
++#define T_rot (msecs_to_jiffies(5500))
++#define T_nonrot (msecs_to_jiffies(2000))
++/* Next two quantities are in sectors/usec, left-shifted by BFQ_RATE_SHIFT */
++#define R_rot 17415
++#define R_nonrot 34791
++
++#define BFQ_SERVICE_TREE_INIT ((struct bfq_service_tree) \
++ { RB_ROOT, RB_ROOT, NULL, NULL, 0, 0 })
++
++#define RQ_BIC(rq) ((struct bfq_io_cq *) (rq)->elv.priv[0])
++#define RQ_BFQQ(rq) ((rq)->elv.priv[1])
++
++static inline void bfq_schedule_dispatch(struct bfq_data *bfqd);
++
++#include "bfq-ioc.c"
++#include "bfq-sched.c"
++#include "bfq-cgroup.c"
++
++#define bfq_class_idle(bfqq) ((bfqq)->entity.ioprio_class ==\
++ IOPRIO_CLASS_IDLE)
++#define bfq_class_rt(bfqq) ((bfqq)->entity.ioprio_class ==\
++ IOPRIO_CLASS_RT)
++
++#define bfq_sample_valid(samples) ((samples) > 80)
++
++/*
++ * We regard a request as SYNC, if either it's a read or has the SYNC bit
++ * set (in which case it could also be a direct WRITE).
++ */
++static inline int bfq_bio_sync(struct bio *bio)
++{
++ if (bio_data_dir(bio) == READ || (bio->bi_rw & REQ_SYNC))
++ return 1;
++
++ return 0;
++}
++
++/*
++ * Scheduler run of queue, if there are requests pending and no one in the
++ * driver that will restart queueing.
++ */
++static inline void bfq_schedule_dispatch(struct bfq_data *bfqd)
++{
++ if (bfqd->queued != 0) {
++ bfq_log(bfqd, "schedule dispatch");
++ kblockd_schedule_work(bfqd->queue, &bfqd->unplug_work);
++ }
++}
++
++/*
++ * Lifted from AS - choose which of rq1 and rq2 that is best served now.
++ * We choose the request that is closesr to the head right now. Distance
++ * behind the head is penalized and only allowed to a certain extent.
++ */
++static struct request *bfq_choose_req(struct bfq_data *bfqd,
++ struct request *rq1,
++ struct request *rq2,
++ sector_t last)
++{
++ sector_t s1, s2, d1 = 0, d2 = 0;
++ unsigned long back_max;
++#define BFQ_RQ1_WRAP 0x01 /* request 1 wraps */
++#define BFQ_RQ2_WRAP 0x02 /* request 2 wraps */
++ unsigned wrap = 0; /* bit mask: requests behind the disk head? */
++
++ if (rq1 == NULL || rq1 == rq2)
++ return rq2;
++ if (rq2 == NULL)
++ return rq1;
++
++ if (rq_is_sync(rq1) && !rq_is_sync(rq2))
++ return rq1;
++ else if (rq_is_sync(rq2) && !rq_is_sync(rq1))
++ return rq2;
++ if ((rq1->cmd_flags & REQ_META) && !(rq2->cmd_flags & REQ_META))
++ return rq1;
++ else if ((rq2->cmd_flags & REQ_META) && !(rq1->cmd_flags & REQ_META))
++ return rq2;
++
++ s1 = blk_rq_pos(rq1);
++ s2 = blk_rq_pos(rq2);
++
++ /*
++ * By definition, 1KiB is 2 sectors.
++ */
++ back_max = bfqd->bfq_back_max * 2;
++
++ /*
++ * Strict one way elevator _except_ in the case where we allow
++ * short backward seeks which are biased as twice the cost of a
++ * similar forward seek.
++ */
++ if (s1 >= last)
++ d1 = s1 - last;
++ else if (s1 + back_max >= last)
++ d1 = (last - s1) * bfqd->bfq_back_penalty;
++ else
++ wrap |= BFQ_RQ1_WRAP;
++
++ if (s2 >= last)
++ d2 = s2 - last;
++ else if (s2 + back_max >= last)
++ d2 = (last - s2) * bfqd->bfq_back_penalty;
++ else
++ wrap |= BFQ_RQ2_WRAP;
++
++ /* Found required data */
++
++ /*
++ * By doing switch() on the bit mask "wrap" we avoid having to
++ * check two variables for all permutations: --> faster!
++ */
++ switch (wrap) {
++ case 0: /* common case for CFQ: rq1 and rq2 not wrapped */
++ if (d1 < d2)
++ return rq1;
++ else if (d2 < d1)
++ return rq2;
++ else {
++ if (s1 >= s2)
++ return rq1;
++ else
++ return rq2;
++ }
++
++ case BFQ_RQ2_WRAP:
++ return rq1;
++ case BFQ_RQ1_WRAP:
++ return rq2;
++ case (BFQ_RQ1_WRAP|BFQ_RQ2_WRAP): /* both rqs wrapped */
++ default:
++ /*
++ * Since both rqs are wrapped,
++ * start with the one that's further behind head
++ * (--> only *one* back seek required),
++ * since back seek takes more time than forward.
++ */
++ if (s1 <= s2)
++ return rq1;
++ else
++ return rq2;
++ }
++}
++
++static struct bfq_queue *
++bfq_rq_pos_tree_lookup(struct bfq_data *bfqd, struct rb_root *root,
++ sector_t sector, struct rb_node **ret_parent,
++ struct rb_node ***rb_link)
++{
++ struct rb_node **p, *parent;
++ struct bfq_queue *bfqq = NULL;
++
++ parent = NULL;
++ p = &root->rb_node;
++ while (*p) {
++ struct rb_node **n;
++
++ parent = *p;
++ bfqq = rb_entry(parent, struct bfq_queue, pos_node);
++
++ /*
++ * Sort strictly based on sector. Smallest to the left,
++ * largest to the right.
++ */
++ if (sector > blk_rq_pos(bfqq->next_rq))
++ n = &(*p)->rb_right;
++ else if (sector < blk_rq_pos(bfqq->next_rq))
++ n = &(*p)->rb_left;
++ else
++ break;
++ p = n;
++ bfqq = NULL;
++ }
++
++ *ret_parent = parent;
++ if (rb_link)
++ *rb_link = p;
++
++ bfq_log(bfqd, "rq_pos_tree_lookup %llu: returning %d",
++ (long long unsigned)sector,
++ bfqq != NULL ? bfqq->pid : 0);
++
++ return bfqq;
++}
++
++static void bfq_rq_pos_tree_add(struct bfq_data *bfqd, struct bfq_queue *bfqq)
++{
++ struct rb_node **p, *parent;
++ struct bfq_queue *__bfqq;
++
++ if (bfqq->pos_root != NULL) {
++ rb_erase(&bfqq->pos_node, bfqq->pos_root);
++ bfqq->pos_root = NULL;
++ }
++
++ if (bfq_class_idle(bfqq))
++ return;
++ if (!bfqq->next_rq)
++ return;
++
++ bfqq->pos_root = &bfqd->rq_pos_tree;
++ __bfqq = bfq_rq_pos_tree_lookup(bfqd, bfqq->pos_root,
++ blk_rq_pos(bfqq->next_rq), &parent, &p);
++ if (__bfqq == NULL) {
++ rb_link_node(&bfqq->pos_node, parent, p);
++ rb_insert_color(&bfqq->pos_node, bfqq->pos_root);
++ } else
++ bfqq->pos_root = NULL;
++}
++
++static struct request *bfq_find_next_rq(struct bfq_data *bfqd,
++ struct bfq_queue *bfqq,
++ struct request *last)
++{
++ struct rb_node *rbnext = rb_next(&last->rb_node);
++ struct rb_node *rbprev = rb_prev(&last->rb_node);
++ struct request *next = NULL, *prev = NULL;
++
++ BUG_ON(RB_EMPTY_NODE(&last->rb_node));
++
++ if (rbprev != NULL)
++ prev = rb_entry_rq(rbprev);
++
++ if (rbnext != NULL)
++ next = rb_entry_rq(rbnext);
++ else {
++ rbnext = rb_first(&bfqq->sort_list);
++ if (rbnext && rbnext != &last->rb_node)
++ next = rb_entry_rq(rbnext);
++ }
++
++ return bfq_choose_req(bfqd, next, prev, blk_rq_pos(last));
++}
++
++static void bfq_del_rq_rb(struct request *rq)
++{
++ struct bfq_queue *bfqq = RQ_BFQQ(rq);
++ struct bfq_data *bfqd = bfqq->bfqd;
++ const int sync = rq_is_sync(rq);
++
++ BUG_ON(bfqq->queued[sync] == 0);
++ bfqq->queued[sync]--;
++ bfqd->queued--;
++
++ elv_rb_del(&bfqq->sort_list, rq);
++
++ if (RB_EMPTY_ROOT(&bfqq->sort_list)) {
++ if (bfq_bfqq_busy(bfqq) && bfqq != bfqd->in_service_queue)
++ bfq_del_bfqq_busy(bfqd, bfqq, 1);
++ /*
++ * Remove queue from request-position tree as it is empty.
++ */
++ if (bfqq->pos_root != NULL) {
++ rb_erase(&bfqq->pos_node, bfqq->pos_root);
++ bfqq->pos_root = NULL;
++ }
++ }
++}
++
++/* see the definition of bfq_async_charge_factor for details */
++static inline unsigned long bfq_serv_to_charge(struct request *rq,
++ struct bfq_queue *bfqq)
++{
++ return blk_rq_sectors(rq) *
++ (1 + ((!bfq_bfqq_sync(bfqq)) * (bfqq->raising_coeff == 1) *
++ bfq_async_charge_factor));
++}
++
++/**
++ * bfq_updated_next_req - update the queue after a new next_rq selection.
++ * @bfqd: the device data the queue belongs to.
++ * @bfqq: the queue to update.
++ *
++ * If the first request of a queue changes we make sure that the queue
++ * has enough budget to serve at least its first request (if the
++ * request has grown). We do this because if the queue has not enough
++ * budget for its first request, it has to go through two dispatch
++ * rounds to actually get it dispatched.
++ */
++static void bfq_updated_next_req(struct bfq_data *bfqd,
++ struct bfq_queue *bfqq)
++{
++ struct bfq_entity *entity = &bfqq->entity;
++ struct bfq_service_tree *st = bfq_entity_service_tree(entity);
++ struct request *next_rq = bfqq->next_rq;
++ unsigned long new_budget;
++
++ if (next_rq == NULL)
++ return;
++
++ if (bfqq == bfqd->in_service_queue)
++ /*
++ * In order not to break guarantees, budgets cannot be
++ * changed after an entity has been selected.
++ */
++ return;
++
++ BUG_ON(entity->tree != &st->active);
++ BUG_ON(entity == entity->sched_data->active_entity);
++
++ new_budget = max_t(unsigned long, bfqq->max_budget,
++ bfq_serv_to_charge(next_rq, bfqq));
++ entity->budget = new_budget;
++ bfq_log_bfqq(bfqd, bfqq, "updated next rq: new budget %lu", new_budget);
++ bfq_activate_bfqq(bfqd, bfqq);
++}
++
++static inline unsigned int bfq_wrais_duration(struct bfq_data *bfqd)
++{
++ u64 dur;
++
++ if (bfqd->bfq_raising_max_time > 0)
++ return bfqd->bfq_raising_max_time;
++
++ dur = bfqd->RT_prod;
++ do_div(dur, bfqd->peak_rate);
++
++ return dur;
++}
++
++static void bfq_add_rq_rb(struct request *rq)
++{
++ struct bfq_queue *bfqq = RQ_BFQQ(rq);
++ struct bfq_entity *entity = &bfqq->entity;
++ struct bfq_data *bfqd = bfqq->bfqd;
++ struct request *next_rq, *prev;
++ unsigned long old_raising_coeff = bfqq->raising_coeff;
++ int idle_for_long_time = 0;
++
++ bfq_log_bfqq(bfqd, bfqq, "add_rq_rb %d", rq_is_sync(rq));
++ bfqq->queued[rq_is_sync(rq)]++;
++ bfqd->queued++;
++
++ elv_rb_add(&bfqq->sort_list, rq);
++
++ /*
++ * Check if this request is a better next-serve candidate.
++ */
++ prev = bfqq->next_rq;
++ next_rq = bfq_choose_req(bfqd, bfqq->next_rq, rq, bfqd->last_position);
++ BUG_ON(next_rq == NULL);
++ bfqq->next_rq = next_rq;
++
++ /*
++ * Adjust priority tree position, if next_rq changes.
++ */
++ if (prev != bfqq->next_rq)
++ bfq_rq_pos_tree_add(bfqd, bfqq);
++
++ if (!bfq_bfqq_busy(bfqq)) {
++ int soft_rt = bfqd->bfq_raising_max_softrt_rate > 0 &&
++ time_is_before_jiffies(bfqq->soft_rt_next_start);
++ idle_for_long_time = time_is_before_jiffies(
++ bfqq->budget_timeout +
++ bfqd->bfq_raising_min_idle_time);
++ entity->budget = max_t(unsigned long, bfqq->max_budget,
++ bfq_serv_to_charge(next_rq, bfqq));
++
++ if (!bfqd->low_latency)
++ goto add_bfqq_busy;
++
++ /*
++ * If the queue is not being boosted and has been idle
++ * for enough time, start a weight-raising period
++ */
++ if (old_raising_coeff == 1 &&
++ (idle_for_long_time || soft_rt)) {
++ bfqq->raising_coeff = bfqd->bfq_raising_coeff;
++ if (idle_for_long_time)
++ bfqq->raising_cur_max_time =
++ bfq_wrais_duration(bfqd);
++ else
++ bfqq->raising_cur_max_time =
++ bfqd->bfq_raising_rt_max_time;
++ bfq_log_bfqq(bfqd, bfqq,
++ "wrais starting at %llu msec,"
++ "rais_max_time %u",
++ bfqq->last_rais_start_finish,
++ jiffies_to_msecs(bfqq->
++ raising_cur_max_time));
++ } else if (old_raising_coeff > 1) {
++ if (idle_for_long_time)
++ bfqq->raising_cur_max_time =
++ bfq_wrais_duration(bfqd);
++ else if (bfqq->raising_cur_max_time ==
++ bfqd->bfq_raising_rt_max_time &&
++ !soft_rt) {
++ bfqq->raising_coeff = 1;
++ bfq_log_bfqq(bfqd, bfqq,
++ "wrais ending at %llu msec,"
++ "rais_max_time %u",
++ bfqq->last_rais_start_finish,
++ jiffies_to_msecs(bfqq->
++ raising_cur_max_time));
++ } else if ((bfqq->last_rais_start_finish +
++ bfqq->raising_cur_max_time <
++ jiffies + bfqd->bfq_raising_rt_max_time) &&
++ soft_rt) {
++ /*
++ *
++ * The remaining weight-raising time is lower
++ * than bfqd->bfq_raising_rt_max_time, which
++ * means that the application is enjoying
++ * weight raising either because deemed soft rt
++ * in the near past, or because deemed
++ * interactive a long ago. In both cases,
++ * resetting now the current remaining weight-
++ * raising time for the application to the
++ * weight-raising duration for soft rt
++ * applications would not cause any latency
++ * increase for the application (as the new
++ * duration would be higher than the remaining
++ * time).
++ *
++ * In addition, the application is now meeting
++ * the requirements for being deemed soft rt.
++ * In the end we can correctly and safely
++ * (re)charge the weight-raising duration for
++ * the application with the weight-raising
++ * duration for soft rt applications.
++ *
++ * In particular, doing this recharge now, i.e.,
++ * before the weight-raising period for the
++ * application finishes, reduces the probability
++ * of the following negative scenario:
++ * 1) the weight of a soft rt application is
++ * raised at startup (as for any newly
++ * created application),
++ * 2) since the application is not interactive,
++ * at a certain time weight-raising is
++ * stopped for the application,
++ * 3) at that time the application happens to
++ * still have pending requests, and hence
++ * is destined to not have a chance to be
++ * deemed soft rt before these requests are
++ * completed (see the comments to the
++ * function bfq_bfqq_softrt_next_start()
++ * for details on soft rt detection),
++ * 4) these pending requests experience a high
++ * latency because the application is not
++ * weight-raised while they are pending.
++ */
++ bfqq->last_rais_start_finish = jiffies;
++ bfqq->raising_cur_max_time =
++ bfqd->bfq_raising_rt_max_time;
++ }
++ }
++ if (old_raising_coeff != bfqq->raising_coeff)
++ entity->ioprio_changed = 1;
++add_bfqq_busy:
++ bfqq->last_idle_bklogged = jiffies;
++ bfqq->service_from_backlogged = 0;
++ bfq_clear_bfqq_softrt_update(bfqq);
++ bfq_add_bfqq_busy(bfqd, bfqq);
++ } else {
++ if (bfqd->low_latency && old_raising_coeff == 1 &&
++ !rq_is_sync(rq) &&
++ bfqq->last_rais_start_finish +
++ time_is_before_jiffies(
++ bfqd->bfq_raising_min_inter_arr_async)) {
++ bfqq->raising_coeff = bfqd->bfq_raising_coeff;
++ bfqq->raising_cur_max_time = bfq_wrais_duration(bfqd);
++
++ bfqd->raised_busy_queues++;
++ entity->ioprio_changed = 1;
++ bfq_log_bfqq(bfqd, bfqq,
++ "non-idle wrais starting at %llu msec,"
++ "rais_max_time %u",
++ bfqq->last_rais_start_finish,
++ jiffies_to_msecs(bfqq->
++ raising_cur_max_time));
++ }
++ bfq_updated_next_req(bfqd, bfqq);
++ }
++
++ if (bfqd->low_latency &&
++ (old_raising_coeff == 1 || bfqq->raising_coeff == 1 ||
++ idle_for_long_time))
++ bfqq->last_rais_start_finish = jiffies;
++}
++
++static void bfq_reposition_rq_rb(struct bfq_queue *bfqq, struct request *rq)
++{
++ elv_rb_del(&bfqq->sort_list, rq);
++ bfqq->queued[rq_is_sync(rq)]--;
++ bfqq->bfqd->queued--;
++ bfq_add_rq_rb(rq);
++}
++
++static struct request *bfq_find_rq_fmerge(struct bfq_data *bfqd,
++ struct bio *bio)
++{
++ struct task_struct *tsk = current;
++ struct bfq_io_cq *bic;
++ struct bfq_queue *bfqq;
++
++ bic = bfq_bic_lookup(bfqd, tsk->io_context);
++ if (bic == NULL)
++ return NULL;
++
++ bfqq = bic_to_bfqq(bic, bfq_bio_sync(bio));
++ if (bfqq != NULL)
++ return elv_rb_find(&bfqq->sort_list, bio_end_sector(bio));
++
++ return NULL;
++}
++
++static void bfq_activate_request(struct request_queue *q, struct request *rq)
++{
++ struct bfq_data *bfqd = q->elevator->elevator_data;
++
++ bfqd->rq_in_driver++;
++ bfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq);
++ bfq_log(bfqd, "activate_request: new bfqd->last_position %llu",
++ (long long unsigned)bfqd->last_position);
++}
++
++static void bfq_deactivate_request(struct request_queue *q, struct request *rq)
++{
++ struct bfq_data *bfqd = q->elevator->elevator_data;
++
++ WARN_ON(bfqd->rq_in_driver == 0);
++ bfqd->rq_in_driver--;
++}
++
++static void bfq_remove_request(struct request *rq)
++{
++ struct bfq_queue *bfqq = RQ_BFQQ(rq);
++ struct bfq_data *bfqd = bfqq->bfqd;
++
++ if (bfqq->next_rq == rq) {
++ bfqq->next_rq = bfq_find_next_rq(bfqd, bfqq, rq);
++ bfq_updated_next_req(bfqd, bfqq);
++ }
++
++ list_del_init(&rq->queuelist);
++ bfq_del_rq_rb(rq);
++
++ if (rq->cmd_flags & REQ_META) {
++ WARN_ON(bfqq->meta_pending == 0);
++ bfqq->meta_pending--;
++ }
++}
++
++static int bfq_merge(struct request_queue *q, struct request **req,
++ struct bio *bio)
++{
++ struct bfq_data *bfqd = q->elevator->elevator_data;
++ struct request *__rq;
++
++ __rq = bfq_find_rq_fmerge(bfqd, bio);
++ if (__rq != NULL && elv_rq_merge_ok(__rq, bio)) {
++ *req = __rq;
++ return ELEVATOR_FRONT_MERGE;
++ }
++
++ return ELEVATOR_NO_MERGE;
++}
++
++static void bfq_merged_request(struct request_queue *q, struct request *req,
++ int type)
++{
++ if (type == ELEVATOR_FRONT_MERGE) {
++ struct bfq_queue *bfqq = RQ_BFQQ(req);
++
++ bfq_reposition_rq_rb(bfqq, req);
++ }
++}
++
++static void bfq_merged_requests(struct request_queue *q, struct request *rq,
++ struct request *next)
++{
++ struct bfq_queue *bfqq = RQ_BFQQ(rq);
++
++ /*
++ * Reposition in fifo if next is older than rq.
++ */
++ if (!list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
++ time_before(rq_fifo_time(next), rq_fifo_time(rq))) {
++ list_move(&rq->queuelist, &next->queuelist);
++ rq_set_fifo_time(rq, rq_fifo_time(next));
++ }
++
++ if (bfqq->next_rq == next)
++ bfqq->next_rq = rq;
++
++ bfq_remove_request(next);
++}
++
++/* Must be called with bfqq != NULL */
++static inline void bfq_bfqq_end_raising(struct bfq_queue *bfqq)
++{
++ BUG_ON(bfqq == NULL);
++ if (bfq_bfqq_busy(bfqq))
++ bfqq->bfqd->raised_busy_queues--;
++ bfqq->raising_coeff = 1;
++ bfqq->raising_cur_max_time = 0;
++ /* Trigger a weight change on the next activation of the queue */
++ bfqq->entity.ioprio_changed = 1;
++}
++
++static void bfq_end_raising_async_queues(struct bfq_data *bfqd,
++ struct bfq_group *bfqg)
++{
++ int i, j;
++
++ for (i = 0; i < 2; i++)
++ for (j = 0; j < IOPRIO_BE_NR; j++)
++ if (bfqg->async_bfqq[i][j] != NULL)
++ bfq_bfqq_end_raising(bfqg->async_bfqq[i][j]);
++ if (bfqg->async_idle_bfqq != NULL)
++ bfq_bfqq_end_raising(bfqg->async_idle_bfqq);
++}
++
++static void bfq_end_raising(struct bfq_data *bfqd)
++{
++ struct bfq_queue *bfqq;
++
++ spin_lock_irq(bfqd->queue->queue_lock);
++
++ list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list)
++ bfq_bfqq_end_raising(bfqq);
++ list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list)
++ bfq_bfqq_end_raising(bfqq);
++ bfq_end_raising_async(bfqd);
++
++ spin_unlock_irq(bfqd->queue->queue_lock);
++}
++
++static int bfq_allow_merge(struct request_queue *q, struct request *rq,
++ struct bio *bio)
++{
++ struct bfq_data *bfqd = q->elevator->elevator_data;
++ struct bfq_io_cq *bic;
++ struct bfq_queue *bfqq;
++
++ /*
++ * Disallow merge of a sync bio into an async request.
++ */
++ if (bfq_bio_sync(bio) && !rq_is_sync(rq))
++ return 0;
++
++ /*
++ * Lookup the bfqq that this bio will be queued with. Allow
++ * merge only if rq is queued there.
++ * Queue lock is held here.
++ */
++ bic = bfq_bic_lookup(bfqd, current->io_context);
++ if (bic == NULL)
++ return 0;
++
++ bfqq = bic_to_bfqq(bic, bfq_bio_sync(bio));
++ return bfqq == RQ_BFQQ(rq);
++}
++
++static void __bfq_set_in_service_queue(struct bfq_data *bfqd,
++ struct bfq_queue *bfqq)
++{
++ if (bfqq != NULL) {
++ bfq_mark_bfqq_must_alloc(bfqq);
++ bfq_mark_bfqq_budget_new(bfqq);
++ bfq_clear_bfqq_fifo_expire(bfqq);
++
++ bfqd->budgets_assigned = (bfqd->budgets_assigned*7 + 256) / 8;
++
++ bfq_log_bfqq(bfqd, bfqq,
++ "set_in_service_queue, cur-budget = %lu",
++ bfqq->entity.budget);
++ }
++
++ bfqd->in_service_queue = bfqq;
++}
++
++/*
++ * Get and set a new queue for service.
++ */
++static struct bfq_queue *bfq_set_in_service_queue(struct bfq_data *bfqd,
++ struct bfq_queue *bfqq)
++{
++ if (!bfqq)
++ bfqq = bfq_get_next_queue(bfqd);
++ else
++ bfq_get_next_queue_forced(bfqd, bfqq);
++
++ __bfq_set_in_service_queue(bfqd, bfqq);
++ return bfqq;
++}
++
++static inline sector_t bfq_dist_from_last(struct bfq_data *bfqd,
++ struct request *rq)
++{
++ if (blk_rq_pos(rq) >= bfqd->last_position)
++ return blk_rq_pos(rq) - bfqd->last_position;
++ else
++ return bfqd->last_position - blk_rq_pos(rq);
++}
++
++/*
++ * Return true if bfqq has no request pending and rq is close enough to
++ * bfqd->last_position, or if rq is closer to bfqd->last_position than
++ * bfqq->next_rq
++ */
++static inline int bfq_rq_close(struct bfq_data *bfqd, struct request *rq)
++{
++ return bfq_dist_from_last(bfqd, rq) <= BFQQ_SEEK_THR;
++}
++
++static struct bfq_queue *bfqq_close(struct bfq_data *bfqd)
++{
++ struct rb_root *root = &bfqd->rq_pos_tree;
++ struct rb_node *parent, *node;
++ struct bfq_queue *__bfqq;
++ sector_t sector = bfqd->last_position;
++
++ if (RB_EMPTY_ROOT(root))
++ return NULL;
++
++ /*
++ * First, if we find a request starting at the end of the last
++ * request, choose it.
++ */
++ __bfqq = bfq_rq_pos_tree_lookup(bfqd, root, sector, &parent, NULL);
++ if (__bfqq != NULL)
++ return __bfqq;
++
++ /*
++ * If the exact sector wasn't found, the parent of the NULL leaf
++ * will contain the closest sector (rq_pos_tree sorted by next_request
++ * position).
++ */
++ __bfqq = rb_entry(parent, struct bfq_queue, pos_node);
++ if (bfq_rq_close(bfqd, __bfqq->next_rq))
++ return __bfqq;
++
++ if (blk_rq_pos(__bfqq->next_rq) < sector)
++ node = rb_next(&__bfqq->pos_node);
++ else
++ node = rb_prev(&__bfqq->pos_node);
++ if (node == NULL)
++ return NULL;
++
++ __bfqq = rb_entry(node, struct bfq_queue, pos_node);
++ if (bfq_rq_close(bfqd, __bfqq->next_rq))
++ return __bfqq;
++
++ return NULL;
++}
++
++/*
++ * bfqd - obvious
++ * cur_bfqq - passed in so that we don't decide that the current queue
++ * is closely cooperating with itself.
++ *
++ * We are assuming that cur_bfqq has dispatched at least one request,
++ * and that bfqd->last_position reflects a position on the disk associated
++ * with the I/O issued by cur_bfqq.
++ */
++static struct bfq_queue *bfq_close_cooperator(struct bfq_data *bfqd,
++ struct bfq_queue *cur_bfqq)
++{
++ struct bfq_queue *bfqq;
++
++ if (bfq_class_idle(cur_bfqq))
++ return NULL;
++ if (!bfq_bfqq_sync(cur_bfqq))
++ return NULL;
++ if (BFQQ_SEEKY(cur_bfqq))
++ return NULL;
++
++ /* If device has only one backlogged bfq_queue, don't search. */
++ if (bfqd->busy_queues == 1)
++ return NULL;
++
++ /*
++ * We should notice if some of the queues are cooperating, e.g.
++ * working closely on the same area of the disk. In that case,
++ * we can group them together and don't waste time idling.
++ */
++ bfqq = bfqq_close(bfqd);
++ if (bfqq == NULL || bfqq == cur_bfqq)
++ return NULL;
++
++ /*
++ * Do not merge queues from different bfq_groups.
++ */
++ if (bfqq->entity.parent != cur_bfqq->entity.parent)
++ return NULL;
++
++ /*
++ * It only makes sense to merge sync queues.
++ */
++ if (!bfq_bfqq_sync(bfqq))
++ return NULL;
++ if (BFQQ_SEEKY(bfqq))
++ return NULL;
++
++ /*
++ * Do not merge queues of different priority classes.
++ */
++ if (bfq_class_rt(bfqq) != bfq_class_rt(cur_bfqq))
++ return NULL;
++
++ return bfqq;
++}
++
++/*
++ * If enough samples have been computed, return the current max budget
++ * stored in bfqd, which is dynamically updated according to the
++ * estimated disk peak rate; otherwise return the default max budget
++ */
++static inline unsigned long bfq_max_budget(struct bfq_data *bfqd)
++{
++ if (bfqd->budgets_assigned < 194)
++ return bfq_default_max_budget;
++ else
++ return bfqd->bfq_max_budget;
++}
++
++/*
++ * Return min budget, which is a fraction of the current or default
++ * max budget (trying with 1/32)
++ */
++static inline unsigned long bfq_min_budget(struct bfq_data *bfqd)
++{
++ if (bfqd->budgets_assigned < 194)
++ return bfq_default_max_budget / 32;
++ else
++ return bfqd->bfq_max_budget / 32;
++}
++
++/*
++ * Decides whether idling should be done for given device and
++ * given in-service queue.
++ */
++static inline bool bfq_queue_nonrot_noidle(struct bfq_data *bfqd,
++ struct bfq_queue *in_service_bfqq)
++{
++ if (in_service_bfqq == NULL)
++ return false;
++ /*
++ * If device is SSD it has no seek penalty, disable idling; but
++ * do so only if:
++ * - device does not support queuing, otherwise we still have
++ * a problem with sync vs async workloads;
++ * - the queue is not weight-raised, to preserve guarantees.
++ */
++ return (blk_queue_nonrot(bfqd->queue) && bfqd->hw_tag &&
++ in_service_bfqq->raising_coeff == 1);
++}
++
++static void bfq_arm_slice_timer(struct bfq_data *bfqd)
++{
++ struct bfq_queue *bfqq = bfqd->in_service_queue;
++ struct bfq_io_cq *bic;
++ unsigned long sl;
++
++ WARN_ON(!RB_EMPTY_ROOT(&bfqq->sort_list));
++
++ /* Tasks have exited, don't wait. */
++ bic = bfqd->in_service_bic;
++ if (bic == NULL || atomic_read(&bic->icq.ioc->active_ref) == 0)
++ return;
++
++ bfq_mark_bfqq_wait_request(bfqq);
++
++ /*
++ * We don't want to idle for seeks, but we do want to allow
++ * fair distribution of slice time for a process doing back-to-back
++ * seeks. So allow a little bit of time for him to submit a new rq.
++ *
++ * To prevent processes with (partly) seeky workloads from
++ * being too ill-treated, grant them a small fraction of the
++ * assigned budget before reducing the waiting time to
++ * BFQ_MIN_TT. This happened to help reduce latency.
++ */
++ sl = bfqd->bfq_slice_idle;
++ if (bfq_sample_valid(bfqq->seek_samples) && BFQQ_SEEKY(bfqq) &&
++ bfqq->entity.service > bfq_max_budget(bfqd) / 8 &&
++ bfqq->raising_coeff == 1)
++ sl = min(sl, msecs_to_jiffies(BFQ_MIN_TT));
++ else if (bfqq->raising_coeff > 1)
++ sl = sl * 3;
++ bfqd->last_idling_start = ktime_get();
++ mod_timer(&bfqd->idle_slice_timer, jiffies + sl);
++ bfq_log(bfqd, "arm idle: %u/%u ms",
++ jiffies_to_msecs(sl), jiffies_to_msecs(bfqd->bfq_slice_idle));
++}
++
++/*
++ * Set the maximum time for the in-service queue to consume its
++ * budget. This prevents seeky processes from lowering the disk
++ * throughput (always guaranteed with a time slice scheme as in CFQ).
++ */
++static void bfq_set_budget_timeout(struct bfq_data *bfqd)
++{
++ struct bfq_queue *bfqq = bfqd->in_service_queue;
++ unsigned int timeout_coeff;
++ if (bfqq->raising_cur_max_time == bfqd->bfq_raising_rt_max_time)
++ timeout_coeff = 1;
++ else
++ timeout_coeff = bfqq->entity.weight / bfqq->entity.orig_weight;
++
++ bfqd->last_budget_start = ktime_get();
++
++ bfq_clear_bfqq_budget_new(bfqq);
++ bfqq->budget_timeout = jiffies +
++ bfqd->bfq_timeout[bfq_bfqq_sync(bfqq)] * timeout_coeff;
++
++ bfq_log_bfqq(bfqd, bfqq, "set budget_timeout %u",
++ jiffies_to_msecs(bfqd->bfq_timeout[bfq_bfqq_sync(bfqq)] *
++ timeout_coeff));
++}
++
++/*
++ * Move request from internal lists to the request queue dispatch list.
++ */
++static void bfq_dispatch_insert(struct request_queue *q, struct request *rq)
++{
++ struct bfq_data *bfqd = q->elevator->elevator_data;
++ struct bfq_queue *bfqq = RQ_BFQQ(rq);
++
++ bfq_remove_request(rq);
++ bfqq->dispatched++;
++ elv_dispatch_sort(q, rq);
++
++ if (bfq_bfqq_sync(bfqq))
++ bfqd->sync_flight++;
++}
++
++/*
++ * Return expired entry, or NULL to just start from scratch in rbtree.
++ */
++static struct request *bfq_check_fifo(struct bfq_queue *bfqq)
++{
++ struct request *rq = NULL;
++
++ if (bfq_bfqq_fifo_expire(bfqq))
++ return NULL;
++
++ bfq_mark_bfqq_fifo_expire(bfqq);
++
++ if (list_empty(&bfqq->fifo))
++ return NULL;
++
++ rq = rq_entry_fifo(bfqq->fifo.next);
++
++ if (time_before(jiffies, rq_fifo_time(rq)))
++ return NULL;
++
++ return rq;
++}
++
++/*
++ * Must be called with the queue_lock held.
++ */
++static int bfqq_process_refs(struct bfq_queue *bfqq)
++{
++ int process_refs, io_refs;
++
++ io_refs = bfqq->allocated[READ] + bfqq->allocated[WRITE];
++ process_refs = atomic_read(&bfqq->ref) - io_refs - bfqq->entity.on_st;
++ BUG_ON(process_refs < 0);
++ return process_refs;
++}
++
++static void bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
++{
++ int process_refs, new_process_refs;
++ struct bfq_queue *__bfqq;
++
++ /*
++ * If there are no process references on the new_bfqq, then it is
++ * unsafe to follow the ->new_bfqq chain as other bfqq's in the chain
++ * may have dropped their last reference (not just their last process
++ * reference).
++ */
++ if (!bfqq_process_refs(new_bfqq))
++ return;
++
++ /* Avoid a circular list and skip interim queue merges. */
++ while ((__bfqq = new_bfqq->new_bfqq)) {
++ if (__bfqq == bfqq)
++ return;
++ new_bfqq = __bfqq;
++ }
++
++ process_refs = bfqq_process_refs(bfqq);
++ new_process_refs = bfqq_process_refs(new_bfqq);
++ /*
++ * If the process for the bfqq has gone away, there is no
++ * sense in merging the queues.
++ */
++ if (process_refs == 0 || new_process_refs == 0)
++ return;
++
++ /*
++ * Merge in the direction of the lesser amount of work.
++ */
++ if (new_process_refs >= process_refs) {
++ bfqq->new_bfqq = new_bfqq;
++ atomic_add(process_refs, &new_bfqq->ref);
++ } else {
++ new_bfqq->new_bfqq = bfqq;
++ atomic_add(new_process_refs, &bfqq->ref);
++ }
++ bfq_log_bfqq(bfqq->bfqd, bfqq, "scheduling merge with queue %d",
++ new_bfqq->pid);
++}
++
++static inline unsigned long bfq_bfqq_budget_left(struct bfq_queue *bfqq)
++{
++ struct bfq_entity *entity = &bfqq->entity;
++ return entity->budget - entity->service;
++}
++
++static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
++{
++ BUG_ON(bfqq != bfqd->in_service_queue);
++
++ __bfq_bfqd_reset_in_service(bfqd);
++
++ /*
++ * If this bfqq is shared between multiple processes, check
++ * to make sure that those processes are still issuing I/Os
++ * within the mean seek distance. If not, it may be time to
++ * break the queues apart again.
++ */
++ if (bfq_bfqq_coop(bfqq) && BFQQ_SEEKY(bfqq))
++ bfq_mark_bfqq_split_coop(bfqq);
++
++ if (RB_EMPTY_ROOT(&bfqq->sort_list)) {
++ /*
++ * overloading budget_timeout field to store when
++ * the queue remains with no backlog, used by
++ * the weight-raising mechanism
++ */
++ bfqq->budget_timeout = jiffies;
++ bfq_del_bfqq_busy(bfqd, bfqq, 1);
++ } else {
++ bfq_activate_bfqq(bfqd, bfqq);
++ /*
++ * Resort priority tree of potential close cooperators.
++ */
++ bfq_rq_pos_tree_add(bfqd, bfqq);
++ }
++}
++
++/**
++ * __bfq_bfqq_recalc_budget - try to adapt the budget to the @bfqq behavior.
++ * @bfqd: device data.
++ * @bfqq: queue to update.
++ * @reason: reason for expiration.
++ *
++ * Handle the feedback on @bfqq budget. See the body for detailed
++ * comments.
++ */
++static void __bfq_bfqq_recalc_budget(struct bfq_data *bfqd,
++ struct bfq_queue *bfqq,
++ enum bfqq_expiration reason)
++{
++ struct request *next_rq;
++ unsigned long budget, min_budget;
++
++ budget = bfqq->max_budget;
++ min_budget = bfq_min_budget(bfqd);
++
++ BUG_ON(bfqq != bfqd->in_service_queue);
++
++ bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last budg %lu, budg left %lu",
++ bfqq->entity.budget, bfq_bfqq_budget_left(bfqq));
++ bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last max_budg %lu, min budg %lu",
++ budget, bfq_min_budget(bfqd));
++ bfq_log_bfqq(bfqd, bfqq, "recalc_budg: sync %d, seeky %d",
++ bfq_bfqq_sync(bfqq), BFQQ_SEEKY(bfqd->in_service_queue));
++
++ if (bfq_bfqq_sync(bfqq)) {
++ switch (reason) {
++ /*
++ * Caveat: in all the following cases we trade latency
++ * for throughput.
++ */
++ case BFQ_BFQQ_TOO_IDLE:
++ /*
++ * This is the only case where we may reduce
++ * the budget: if there is no requets of the
++ * process still waiting for completion, then
++ * we assume (tentatively) that the timer has
++ * expired because the batch of requests of
++ * the process could have been served with a
++ * smaller budget. Hence, betting that
++ * process will behave in the same way when it
++ * becomes backlogged again, we reduce its
++ * next budget. As long as we guess right,
++ * this budget cut reduces the latency
++ * experienced by the process.
++ *
++ * However, if there are still outstanding
++ * requests, then the process may have not yet
++ * issued its next request just because it is
++ * still waiting for the completion of some of
++ * the still oustanding ones. So in this
++ * subcase we do not reduce its budget, on the
++ * contrary we increase it to possibly boost
++ * the throughput, as discussed in the
++ * comments to the BUDGET_TIMEOUT case.
++ */
++ if (bfqq->dispatched > 0) /* still oustanding reqs */
++ budget = min(budget * 2, bfqd->bfq_max_budget);
++ else {
++ if (budget > 5 * min_budget)
++ budget -= 4 * min_budget;
++ else
++ budget = min_budget;
++ }
++ break;
++ case BFQ_BFQQ_BUDGET_TIMEOUT:
++ /*
++ * We double the budget here because: 1) it
++ * gives the chance to boost the throughput if
++ * this is not a seeky process (which may have
++ * bumped into this timeout because of, e.g.,
++ * ZBR), 2) together with charge_full_budget
++ * it helps give seeky processes higher
++ * timestamps, and hence be served less
++ * frequently.
++ */
++ budget = min(budget * 2, bfqd->bfq_max_budget);
++ break;
++ case BFQ_BFQQ_BUDGET_EXHAUSTED:
++ /*
++ * The process still has backlog, and did not
++ * let either the budget timeout or the disk
++ * idling timeout expire. Hence it is not
++ * seeky, has a short thinktime and may be
++ * happy with a higher budget too. So
++ * definitely increase the budget of this good
++ * candidate to boost the disk throughput.
++ */
++ budget = min(budget * 4, bfqd->bfq_max_budget);
++ break;
++ case BFQ_BFQQ_NO_MORE_REQUESTS:
++ /*
++ * Leave the budget unchanged.
++ */
++ default:
++ return;
++ }
++ } else /* async queue */
++ /* async queues get always the maximum possible budget
++ * (their ability to dispatch is limited by
++ * @bfqd->bfq_max_budget_async_rq).
++ */
++ budget = bfqd->bfq_max_budget;
++
++ bfqq->max_budget = budget;
++
++ if (bfqd->budgets_assigned >= 194 && bfqd->bfq_user_max_budget == 0 &&
++ bfqq->max_budget > bfqd->bfq_max_budget)
++ bfqq->max_budget = bfqd->bfq_max_budget;
++
++ /*
++ * Make sure that we have enough budget for the next request.
++ * Since the finish time of the bfqq must be kept in sync with
++ * the budget, be sure to call __bfq_bfqq_expire() after the
++ * update.
++ */
++ next_rq = bfqq->next_rq;
++ if (next_rq != NULL)
++ bfqq->entity.budget = max_t(unsigned long, bfqq->max_budget,
++ bfq_serv_to_charge(next_rq, bfqq));
++ else
++ bfqq->entity.budget = bfqq->max_budget;
++
++ bfq_log_bfqq(bfqd, bfqq, "head sect: %u, new budget %lu",
++ next_rq != NULL ? blk_rq_sectors(next_rq) : 0,
++ bfqq->entity.budget);
++}
++
++static unsigned long bfq_calc_max_budget(u64 peak_rate, u64 timeout)
++{
++ unsigned long max_budget;
++
++ /*
++ * The max_budget calculated when autotuning is equal to the
++ * amount of sectors transfered in timeout_sync at the
++ * estimated peak rate.
++ */
++ max_budget = (unsigned long)(peak_rate * 1000 *
++ timeout >> BFQ_RATE_SHIFT);
++
++ return max_budget;
++}
++
++/*
++ * In addition to updating the peak rate, checks whether the process
++ * is "slow", and returns 1 if so. This slow flag is used, in addition
++ * to the budget timeout, to reduce the amount of service provided to
++ * seeky processes, and hence reduce their chances to lower the
++ * throughput. See the code for more details.
++ */
++static int bfq_update_peak_rate(struct bfq_data *bfqd, struct bfq_queue *bfqq,
++ int compensate, enum bfqq_expiration reason)
++{
++ u64 bw, usecs, expected, timeout;
++ ktime_t delta;
++ int update = 0;
++
++ if (!bfq_bfqq_sync(bfqq) || bfq_bfqq_budget_new(bfqq))
++ return 0;
++
++ if (compensate)
++ delta = bfqd->last_idling_start;
++ else
++ delta = ktime_get();
++ delta = ktime_sub(delta, bfqd->last_budget_start);
++ usecs = ktime_to_us(delta);
++
++ /* Don't trust short/unrealistic values. */
++ if (usecs < 100 || usecs >= LONG_MAX)
++ return 0;
++
++ /*
++ * Calculate the bandwidth for the last slice. We use a 64 bit
++ * value to store the peak rate, in sectors per usec in fixed
++ * point math. We do so to have enough precision in the estimate
++ * and to avoid overflows.
++ */
++ bw = (u64)bfqq->entity.service << BFQ_RATE_SHIFT;
++ do_div(bw, (unsigned long)usecs);
++
++ timeout = jiffies_to_msecs(bfqd->bfq_timeout[BLK_RW_SYNC]);
++
++ /*
++ * Use only long (> 20ms) intervals to filter out spikes for
++ * the peak rate estimation.
++ */
++ if (usecs > 20000) {
++ if (bw > bfqd->peak_rate ||
++ (!BFQQ_SEEKY(bfqq) &&
++ reason == BFQ_BFQQ_BUDGET_TIMEOUT)) {
++ bfq_log(bfqd, "measured bw =%llu", bw);
++ /*
++ * To smooth oscillations use a low-pass filter with
++ * alpha=7/8, i.e.,
++ * new_rate = (7/8) * old_rate + (1/8) * bw
++ */
++ do_div(bw, 8);
++ if (bw == 0)
++ return 0;
++ bfqd->peak_rate *= 7;
++ do_div(bfqd->peak_rate, 8);
++ bfqd->peak_rate += bw;
++ update = 1;
++ bfq_log(bfqd, "new peak_rate=%llu", bfqd->peak_rate);
++ }
++
++ update |= bfqd->peak_rate_samples == BFQ_PEAK_RATE_SAMPLES - 1;
++
++ if (bfqd->peak_rate_samples < BFQ_PEAK_RATE_SAMPLES)
++ bfqd->peak_rate_samples++;
++
++ if (bfqd->peak_rate_samples == BFQ_PEAK_RATE_SAMPLES &&
++ update && bfqd->bfq_user_max_budget == 0) {
++ bfqd->bfq_max_budget =
++ bfq_calc_max_budget(bfqd->peak_rate, timeout);
++ bfq_log(bfqd, "new max_budget=%lu",
++ bfqd->bfq_max_budget);
++ }
++ }
++
++ /*
++ * If the process has been served for a too short time
++ * interval to let its possible sequential accesses prevail on
++ * the initial seek time needed to move the disk head on the
++ * first sector it requested, then give the process a chance
++ * and for the moment return false.
++ */
++ if (bfqq->entity.budget <= bfq_max_budget(bfqd) / 8)
++ return 0;
++
++ /*
++ * A process is considered ``slow'' (i.e., seeky, so that we
++ * cannot treat it fairly in the service domain, as it would
++ * slow down too much the other processes) if, when a slice
++ * ends for whatever reason, it has received service at a
++ * rate that would not be high enough to complete the budget
++ * before the budget timeout expiration.
++ */
++ expected = bw * 1000 * timeout >> BFQ_RATE_SHIFT;
++
++ /*
++ * Caveat: processes doing IO in the slower disk zones will
++ * tend to be slow(er) even if not seeky. And the estimated
++ * peak rate will actually be an average over the disk
++ * surface. Hence, to not be too harsh with unlucky processes,
++ * we keep a budget/3 margin of safety before declaring a
++ * process slow.
++ */
++ return expected > (4 * bfqq->entity.budget) / 3;
++}
++
++/*
++ * To be deemed as soft real-time, an application must meet two requirements.
++ * The first is that the application must not require an average bandwidth
++ * higher than the approximate bandwidth required to playback or record a
++ * compressed high-definition video.
++ * The next function is invoked on the completion of the last request of a
++ * batch, to compute the next-start time instant, soft_rt_next_start, such
++ * that, if the next request of the application does not arrive before
++ * soft_rt_next_start, then the above requirement on the bandwidth is met.
++ *
++ * The second requirement is that the request pattern of the application is
++ * isochronous, i.e., that, after issuing a request or a batch of requests, the
++ * application stops for a while, then issues a new batch, and so on. For this
++ * reason the next function is invoked to compute soft_rt_next_start only for
++ * applications that meet this requirement, whereas soft_rt_next_start is set
++ * to infinity for applications that do not.
++ *
++ * Unfortunately, even a greedy application may happen to behave in an
++ * isochronous way if several processes are competing for the CPUs. In fact,
++ * in this scenario the application stops issuing requests while the CPUs are
++ * busy serving other processes, then restarts, then stops again for a while,
++ * and so on. In addition, if the disk achieves a low enough throughput with
++ * the request pattern issued by the application, then the above bandwidth
++ * requirement may happen to be met too. To prevent such a greedy application
++ * to be deemed as soft real-time, a further rule is used in the computation
++ * of soft_rt_next_start: soft_rt_next_start must be higher than the current
++ * time plus the maximum time for which the arrival of a request is waited
++ * for when a sync queue becomes idle, namely bfqd->bfq_slice_idle. This
++ * filters out greedy applications, as the latter issue instead their next
++ * request as soon as possible after the last one has been completed (in
++ * contrast, when a batch of requests is completed, a soft real-time
++ * application spends some time processing data).
++ *
++ * Actually, the last filter may easily generate false positives if: only
++ * bfqd->bfq_slice_idle is used as a reference time interval, and one or
++ * both the following two cases occur:
++ * 1) HZ is so low that the duration of a jiffie is comparable to or higher
++ * than bfqd->bfq_slice_idle. This happens, e.g., on slow devices with
++ * HZ=100.
++ * 2) jiffies, instead of increasing at a constant rate, may stop increasing
++ * for a while, then suddenly 'jump' by several units to recover the lost
++ * increments. This seems to happen, e.g., inside virtual machines.
++ * To address this issue, we do not use as a reference time interval just
++ * bfqd->bfq_slice_idle, but bfqd->bfq_slice_idle plus a few jiffies. In
++ * particular we add the minimum number of jiffies for which the filter seems
++ * to be quite precise also in embedded systems and KVM/QEMU virtual machines.
++ */
++static inline u64 bfq_bfqq_softrt_next_start(struct bfq_data *bfqd,
++ struct bfq_queue *bfqq)
++{
++ return max(bfqq->last_idle_bklogged +
++ HZ * bfqq->service_from_backlogged /
++ bfqd->bfq_raising_max_softrt_rate,
++ (u64)jiffies + bfqq->bfqd->bfq_slice_idle + 4);
++}
++
++/**
++ * bfq_bfqq_expire - expire a queue.
++ * @bfqd: device owning the queue.
++ * @bfqq: the queue to expire.
++ * @compensate: if true, compensate for the time spent idling.
++ * @reason: the reason causing the expiration.
++ *
++ *
++ * If the process associated to the queue is slow (i.e., seeky), or in
++ * case of budget timeout, or, finally, if it is async, we
++ * artificially charge it an entire budget (independently of the
++ * actual service it received). As a consequence, the queue will get
++ * higher timestamps than the correct ones upon reactivation, and
++ * hence it will be rescheduled as if it had received more service
++ * than what it actually received. In the end, this class of processes
++ * will receive less service in proportion to how slowly they consume
++ * their budgets (and hence how seriously they tend to lower the
++ * throughput).
++ *
++ * In contrast, when a queue expires because it has been idling for
++ * too much or because it exhausted its budget, we do not touch the
++ * amount of service it has received. Hence when the queue will be
++ * reactivated and its timestamps updated, the latter will be in sync
++ * with the actual service received by the queue until expiration.
++ *
++ * Charging a full budget to the first type of queues and the exact
++ * service to the others has the effect of using the WF2Q+ policy to
++ * schedule the former on a timeslice basis, without violating the
++ * service domain guarantees of the latter.
++ */
++static void bfq_bfqq_expire(struct bfq_data *bfqd,
++ struct bfq_queue *bfqq,
++ int compensate,
++ enum bfqq_expiration reason)
++{
++ int slow;
++ BUG_ON(bfqq != bfqd->in_service_queue);
++
++ /* Update disk peak rate for autotuning and check whether the
++ * process is slow (see bfq_update_peak_rate).
++ */
++ slow = bfq_update_peak_rate(bfqd, bfqq, compensate, reason);
++
++ /*
++ * As above explained, 'punish' slow (i.e., seeky), timed-out
++ * and async queues, to favor sequential sync workloads.
++ *
++ * Processes doing IO in the slower disk zones will tend to be
++ * slow(er) even if not seeky. Hence, since the estimated peak
++ * rate is actually an average over the disk surface, these
++ * processes may timeout just for bad luck. To avoid punishing
++ * them we do not charge a full budget to a process that
++ * succeeded in consuming at least 2/3 of its budget.
++ */
++ if (slow || (reason == BFQ_BFQQ_BUDGET_TIMEOUT &&
++ bfq_bfqq_budget_left(bfqq) >= bfqq->entity.budget / 3))
++ bfq_bfqq_charge_full_budget(bfqq);
++
++ bfqq->service_from_backlogged += bfqq->entity.service;
++
++ if (bfqd->low_latency && bfqq->raising_coeff == 1)
++ bfqq->last_rais_start_finish = jiffies;
++
++ if (bfqd->low_latency && bfqd->bfq_raising_max_softrt_rate > 0) {
++ if (reason != BFQ_BFQQ_BUDGET_TIMEOUT &&
++ reason != BFQ_BFQQ_BUDGET_EXHAUSTED) {
++ /*
++ * If we get here, then the request pattern is
++ * isochronous (see the comments to the function
++ * bfq_bfqq_softrt_next_start()). However, if the
++ * queue still has in-flight requests, then it is
++ * better to postpone the computation of next_start
++ * to the next request completion. In fact, if we
++ * computed it now, then the application might pass
++ * the greedy-application filter improperly, because
++ * the arrival of its next request may happen to be
++ * higher than (jiffies + bfqq->bfqd->bfq_slice_idle)
++ * not because the application is truly soft real-
++ * time, but just because the application is currently
++ * waiting for the completion of some request before
++ * issuing, as quickly as possible, its next request.
++ */
++ if (bfqq->dispatched > 0) {
++ bfqq->soft_rt_next_start = -1;
++ bfq_mark_bfqq_softrt_update(bfqq);
++ } else
++ bfqq->soft_rt_next_start =
++ bfq_bfqq_softrt_next_start(bfqd, bfqq);
++ } else
++ bfqq->soft_rt_next_start = -1; /* infinity */
++ }
++
++ bfq_log_bfqq(bfqd, bfqq,
++ "expire (%d, slow %d, num_disp %d, idle_win %d)", reason, slow,
++ bfqq->dispatched, bfq_bfqq_idle_window(bfqq));
++
++ /* Increase, decrease or leave budget unchanged according to reason */
++ __bfq_bfqq_recalc_budget(bfqd, bfqq, reason);
++ __bfq_bfqq_expire(bfqd, bfqq);
++}
++
++/*
++ * Budget timeout is not implemented through a dedicated timer, but
++ * just checked on request arrivals and completions, as well as on
++ * idle timer expirations.
++ */
++static int bfq_bfqq_budget_timeout(struct bfq_queue *bfqq)
++{
++ if (bfq_bfqq_budget_new(bfqq))
++ return 0;
++
++ if (time_before(jiffies, bfqq->budget_timeout))
++ return 0;
++
++ return 1;
++}
++
++/*
++ * If we expire a queue that is waiting for the arrival of a new
++ * request, we may prevent the fictitious timestamp backshifting that
++ * allows the guarantees of the queue to be preserved (see [1] for
++ * this tricky aspect). Hence we return true only if this condition
++ * does not hold, or if the queue is slow enough to deserve only to be
++ * kicked off for preserving a high throughput.
++*/
++static inline int bfq_may_expire_for_budg_timeout(struct bfq_queue *bfqq)
++{
++ bfq_log_bfqq(bfqq->bfqd, bfqq,
++ "may_budget_timeout: wr %d left %d timeout %d",
++ bfq_bfqq_wait_request(bfqq),
++ bfq_bfqq_budget_left(bfqq) >= bfqq->entity.budget / 3,
++ bfq_bfqq_budget_timeout(bfqq));
++
++ return (!bfq_bfqq_wait_request(bfqq) ||
++ bfq_bfqq_budget_left(bfqq) >= bfqq->entity.budget / 3)
++ &&
++ bfq_bfqq_budget_timeout(bfqq);
++}
++
++/*
++ * For weight-raised queues issuing sync requests, idling is always performed,
++ * as this is instrumental in guaranteeing a high fraction of the throughput
++ * to these queues, and hence in guaranteeing a lower latency for their
++ * requests. See [1] for details.
++ *
++ * For non-weight-raised queues, idling is instead disabled if the device is
++ * NCQ-enabled and non-rotational, as this boosts the throughput on such
++ * devices.
++ */
++static inline bool bfq_bfqq_must_not_expire(struct bfq_queue *bfqq)
++{
++ struct bfq_data *bfqd = bfqq->bfqd;
++
++ return bfq_bfqq_sync(bfqq) && (
++ bfqq->raising_coeff > 1 ||
++ (bfq_bfqq_idle_window(bfqq) &&
++ !(bfqd->hw_tag &&
++ (blk_queue_nonrot(bfqd->queue) ||
++ /*
++ * If there are weight-raised busy queues, then do not idle
++ * the disk for a sync non-weight-raised queue, and hence
++ * expire the queue immediately if empty. Combined with the
++ * timestamping rules of BFQ (see [1] for details), this
++ * causes sync non-weight-raised queues to get a lower
++ * fraction of the disk throughput, and hence reduces the rate
++ * at which the processes associated to these queues ask for
++ * requests from the request pool.
++ *
++ * This is beneficial for weight-raised processes, when the
++ * system operates in request-pool saturation conditions
++ * (e.g., in the presence of write hogs). In fact, if
++ * non-weight-raised processes ask for requests at a lower
++ * rate, then weight-raised processes have a higher
++ * probability to get a request from the pool immediately
++ * (or at least soon) when they need one. Hence they have a
++ * higher probability to actually get a fraction of the disk
++ * throughput proportional to their high weight. This is
++ * especially true with NCQ-enabled drives, which enqueue
++ * several requests in advance and further reorder
++ * internally-queued requests.
++ *
++ * Mistreating non-weight-raised queues in the above-described
++ * way, when there are busy weight-raised queues, seems to
++ * mitigate starvation problems in the presence of heavy write
++ * workloads and NCQ, and hence to guarantee a higher
++ * application and system responsiveness in these hostile
++ * scenarios.
++ */
++ bfqd->raised_busy_queues > 0)
++ )
++ )
++ );
++}
++
++/*
++ * If the in-service queue is empty, but it is sync and either of the following
++ * conditions holds, then: 1) the queue must remain in service and cannot be
++ * expired, and 2) the disk must be idled to wait for the possible arrival
++ * of a new request for the queue. The conditions are:
++ * - the device is rotational and not performing NCQ, and the queue has its
++ * idle window set (in this case, waiting for a new request for the queue
++ * is likely to boost the disk throughput);
++ * - the queue is weight-raised (waiting for the request is necessary to
++ * provide the queue with fairness and latency guarantees, see [1] for
++ * details).
++ */
++static inline bool bfq_bfqq_must_idle(struct bfq_queue *bfqq)
++{
++ struct bfq_data *bfqd = bfqq->bfqd;
++
++ return (RB_EMPTY_ROOT(&bfqq->sort_list) && bfqd->bfq_slice_idle != 0 &&
++ bfq_bfqq_must_not_expire(bfqq) &&
++ !bfq_queue_nonrot_noidle(bfqd, bfqq));
++}
++
++/*
++ * Select a queue for service. If we have a current queue in service,
++ * check whether to continue servicing it, or retrieve and set a new one.
++ */
++static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
++{
++ struct bfq_queue *bfqq, *new_bfqq = NULL;
++ struct request *next_rq;
++ enum bfqq_expiration reason = BFQ_BFQQ_BUDGET_TIMEOUT;
++
++ bfqq = bfqd->in_service_queue;
++ if (bfqq == NULL)
++ goto new_queue;
++
++ bfq_log_bfqq(bfqd, bfqq, "select_queue: already in-service queue");
++
++ /*
++ * If another queue has a request waiting within our mean seek
++ * distance, let it run. The expire code will check for close
++ * cooperators and put the close queue at the front of the
++ * service tree. If possible, merge the expiring queue with the
++ * new bfqq.
++ */
++ new_bfqq = bfq_close_cooperator(bfqd, bfqq);
++ if (new_bfqq != NULL && bfqq->new_bfqq == NULL)
++ bfq_setup_merge(bfqq, new_bfqq);
++
++ if (bfq_may_expire_for_budg_timeout(bfqq) &&
++ !timer_pending(&bfqd->idle_slice_timer) &&
++ !bfq_bfqq_must_idle(bfqq))
++ goto expire;
++
++ next_rq = bfqq->next_rq;
++ /*
++ * If bfqq has requests queued and it has enough budget left to
++ * serve them, keep the queue, otherwise expire it.
++ */
++ if (next_rq != NULL) {
++ if (bfq_serv_to_charge(next_rq, bfqq) >
++ bfq_bfqq_budget_left(bfqq)) {
++ reason = BFQ_BFQQ_BUDGET_EXHAUSTED;
++ goto expire;
++ } else {
++ /*
++ * The idle timer may be pending because we may not
++ * disable disk idling even when a new request arrives
++ */
++ if (timer_pending(&bfqd->idle_slice_timer)) {
++ /*
++ * If we get here: 1) at least a new request
++ * has arrived but we have not disabled the
++ * timer because the request was too small,
++ * 2) then the block layer has unplugged the
++ * device, causing the dispatch to be invoked.
++ *
++ * Since the device is unplugged, now the
++ * requests are probably large enough to
++ * provide a reasonable throughput.
++ * So we disable idling.
++ */
++ bfq_clear_bfqq_wait_request(bfqq);
++ del_timer(&bfqd->idle_slice_timer);
++ }
++ if (new_bfqq == NULL)
++ goto keep_queue;
++ else
++ goto expire;
++ }
++ }
++
++ /*
++ * No requests pending. If the in-service queue has no cooperator and
++ * still has requests in flight (possibly waiting for a completion)
++ * or is idling for a new request, then keep it.
++ */
++ if (new_bfqq == NULL && (timer_pending(&bfqd->idle_slice_timer) ||
++ (bfqq->dispatched != 0 && bfq_bfqq_must_not_expire(bfqq)))) {
++ bfqq = NULL;
++ goto keep_queue;
++ } else if (new_bfqq != NULL && timer_pending(&bfqd->idle_slice_timer)) {
++ /*
++ * Expiring the queue because there is a close cooperator,
++ * cancel timer.
++ */
++ bfq_clear_bfqq_wait_request(bfqq);
++ del_timer(&bfqd->idle_slice_timer);
++ }
++
++ reason = BFQ_BFQQ_NO_MORE_REQUESTS;
++expire:
++ bfq_bfqq_expire(bfqd, bfqq, 0, reason);
++new_queue:
++ bfqq = bfq_set_in_service_queue(bfqd, new_bfqq);
++ bfq_log(bfqd, "select_queue: new queue %d returned",
++ bfqq != NULL ? bfqq->pid : 0);
++keep_queue:
++ return bfqq;
++}
++
++static void bfq_update_raising_data(struct bfq_data *bfqd,
++ struct bfq_queue *bfqq)
++{
++ if (bfqq->raising_coeff > 1) { /* queue is being boosted */
++ struct bfq_entity *entity = &bfqq->entity;
++
++ bfq_log_bfqq(bfqd, bfqq,
++ "raising period dur %u/%u msec, "
++ "old raising coeff %u, w %d(%d)",
++ jiffies_to_msecs(jiffies -
++ bfqq->last_rais_start_finish),
++ jiffies_to_msecs(bfqq->raising_cur_max_time),
++ bfqq->raising_coeff,
++ bfqq->entity.weight, bfqq->entity.orig_weight);
++
++ BUG_ON(bfqq != bfqd->in_service_queue && entity->weight !=
++ entity->orig_weight * bfqq->raising_coeff);
++ if (entity->ioprio_changed)
++ bfq_log_bfqq(bfqd, bfqq,
++ "WARN: pending prio change");
++ /*
++ * If too much time has elapsed from the beginning
++ * of this weight-raising, stop it.
++ */
++ if (jiffies - bfqq->last_rais_start_finish >
++ bfqq->raising_cur_max_time) {
++ bfqq->last_rais_start_finish = jiffies;
++ bfq_log_bfqq(bfqd, bfqq,
++ "wrais ending at %llu msec,"
++ "rais_max_time %u",
++ bfqq->last_rais_start_finish,
++ jiffies_to_msecs(bfqq->
++ raising_cur_max_time));
++ bfq_bfqq_end_raising(bfqq);
++ __bfq_entity_update_weight_prio(
++ bfq_entity_service_tree(entity),
++ entity);
++ }
++ }
++}
++
++/*
++ * Dispatch one request from bfqq, moving it to the request queue
++ * dispatch list.
++ */
++static int bfq_dispatch_request(struct bfq_data *bfqd,
++ struct bfq_queue *bfqq)
++{
++ int dispatched = 0;
++ struct request *rq;
++ unsigned long service_to_charge;
++
++ BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list));
++
++ /* Follow expired path, else get first next available. */
++ rq = bfq_check_fifo(bfqq);
++ if (rq == NULL)
++ rq = bfqq->next_rq;
++ service_to_charge = bfq_serv_to_charge(rq, bfqq);
++
++ if (service_to_charge > bfq_bfqq_budget_left(bfqq)) {
++ /*
++ * This may happen if the next rq is chosen
++ * in fifo order instead of sector order.
++ * The budget is properly dimensioned
++ * to be always sufficient to serve the next request
++ * only if it is chosen in sector order. The reason is
++ * that it would be quite inefficient and little useful
++ * to always make sure that the budget is large enough
++ * to serve even the possible next rq in fifo order.
++ * In fact, requests are seldom served in fifo order.
++ *
++ * Expire the queue for budget exhaustion, and
++ * make sure that the next act_budget is enough
++ * to serve the next request, even if it comes
++ * from the fifo expired path.
++ */
++ bfqq->next_rq = rq;
++ /*
++ * Since this dispatch is failed, make sure that
++ * a new one will be performed
++ */
++ if (!bfqd->rq_in_driver)
++ bfq_schedule_dispatch(bfqd);
++ goto expire;
++ }
++
++ /* Finally, insert request into driver dispatch list. */
++ bfq_bfqq_served(bfqq, service_to_charge);
++ bfq_dispatch_insert(bfqd->queue, rq);
++
++ bfq_update_raising_data(bfqd, bfqq);
++
++ bfq_log_bfqq(bfqd, bfqq,
++ "dispatched %u sec req (%llu), budg left %lu",
++ blk_rq_sectors(rq),
++ (long long unsigned)blk_rq_pos(rq),
++ bfq_bfqq_budget_left(bfqq));
++
++ dispatched++;
++
++ if (bfqd->in_service_bic == NULL) {
++ atomic_long_inc(&RQ_BIC(rq)->icq.ioc->refcount);
++ bfqd->in_service_bic = RQ_BIC(rq);
++ }
++
++ if (bfqd->busy_queues > 1 && ((!bfq_bfqq_sync(bfqq) &&
++ dispatched >= bfqd->bfq_max_budget_async_rq) ||
++ bfq_class_idle(bfqq)))
++ goto expire;
++
++ return dispatched;
++
++expire:
++ bfq_bfqq_expire(bfqd, bfqq, 0, BFQ_BFQQ_BUDGET_EXHAUSTED);
++ return dispatched;
++}
++
++static int __bfq_forced_dispatch_bfqq(struct bfq_queue *bfqq)
++{
++ int dispatched = 0;
++
++ while (bfqq->next_rq != NULL) {
++ bfq_dispatch_insert(bfqq->bfqd->queue, bfqq->next_rq);
++ dispatched++;
++ }
++
++ BUG_ON(!list_empty(&bfqq->fifo));
++ return dispatched;
++}
++
++/*
++ * Drain our current requests. Used for barriers and when switching
++ * io schedulers on-the-fly.
++ */
++static int bfq_forced_dispatch(struct bfq_data *bfqd)
++{
++ struct bfq_queue *bfqq, *n;
++ struct bfq_service_tree *st;
++ int dispatched = 0;
++
++ bfqq = bfqd->in_service_queue;
++ if (bfqq != NULL)
++ __bfq_bfqq_expire(bfqd, bfqq);
++
++ /*
++ * Loop through classes, and be careful to leave the scheduler
++ * in a consistent state, as feedback mechanisms and vtime
++ * updates cannot be disabled during the process.
++ */
++ list_for_each_entry_safe(bfqq, n, &bfqd->active_list, bfqq_list) {
++ st = bfq_entity_service_tree(&bfqq->entity);
++
++ dispatched += __bfq_forced_dispatch_bfqq(bfqq);
++ bfqq->max_budget = bfq_max_budget(bfqd);
++
++ bfq_forget_idle(st);
++ }
++
++ BUG_ON(bfqd->busy_queues != 0);
++
++ return dispatched;
++}
++
++static int bfq_dispatch_requests(struct request_queue *q, int force)
++{
++ struct bfq_data *bfqd = q->elevator->elevator_data;
++ struct bfq_queue *bfqq;
++ int max_dispatch;
++
++ bfq_log(bfqd, "dispatch requests: %d busy queues", bfqd->busy_queues);
++ if (bfqd->busy_queues == 0)
++ return 0;
++
++ if (unlikely(force))
++ return bfq_forced_dispatch(bfqd);
++
++ bfqq = bfq_select_queue(bfqd);
++ if (bfqq == NULL)
++ return 0;
++
++ max_dispatch = bfqd->bfq_quantum;
++ if (bfq_class_idle(bfqq))
++ max_dispatch = 1;
++
++ if (!bfq_bfqq_sync(bfqq))
++ max_dispatch = bfqd->bfq_max_budget_async_rq;
++
++ if (bfqq->dispatched >= max_dispatch) {
++ if (bfqd->busy_queues > 1)
++ return 0;
++ if (bfqq->dispatched >= 4 * max_dispatch)
++ return 0;
++ }
++
++ if (bfqd->sync_flight != 0 && !bfq_bfqq_sync(bfqq))
++ return 0;
++
++ bfq_clear_bfqq_wait_request(bfqq);
++ BUG_ON(timer_pending(&bfqd->idle_slice_timer));
++
++ if (!bfq_dispatch_request(bfqd, bfqq))
++ return 0;
++
++ bfq_log_bfqq(bfqd, bfqq, "dispatched one request of %d (max_disp %d)",
++ bfqq->pid, max_dispatch);
++
++ return 1;
++}
++
++/*
++ * Task holds one reference to the queue, dropped when task exits. Each rq
++ * in-flight on this queue also holds a reference, dropped when rq is freed.
++ *
++ * Queue lock must be held here.
++ */
++static void bfq_put_queue(struct bfq_queue *bfqq)
++{
++ struct bfq_data *bfqd = bfqq->bfqd;
++
++ BUG_ON(atomic_read(&bfqq->ref) <= 0);
++
++ bfq_log_bfqq(bfqd, bfqq, "put_queue: %p %d", bfqq,
++ atomic_read(&bfqq->ref));
++ if (!atomic_dec_and_test(&bfqq->ref))
++ return;
++
++ BUG_ON(rb_first(&bfqq->sort_list) != NULL);
++ BUG_ON(bfqq->allocated[READ] + bfqq->allocated[WRITE] != 0);
++ BUG_ON(bfqq->entity.tree != NULL);
++ BUG_ON(bfq_bfqq_busy(bfqq));
++ BUG_ON(bfqd->in_service_queue == bfqq);
++
++ bfq_log_bfqq(bfqd, bfqq, "put_queue: %p freed", bfqq);
++
++ kmem_cache_free(bfq_pool, bfqq);
++}
++
++static void bfq_put_cooperator(struct bfq_queue *bfqq)
++{
++ struct bfq_queue *__bfqq, *next;
++
++ /*
++ * If this queue was scheduled to merge with another queue, be
++ * sure to drop the reference taken on that queue (and others in
++ * the merge chain). See bfq_setup_merge and bfq_merge_bfqqs.
++ */
++ __bfqq = bfqq->new_bfqq;
++ while (__bfqq) {
++ if (__bfqq == bfqq) {
++ WARN(1, "bfqq->new_bfqq loop detected.\n");
++ break;
++ }
++ next = __bfqq->new_bfqq;
++ bfq_put_queue(__bfqq);
++ __bfqq = next;
++ }
++}
++
++static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
++{
++ if (bfqq == bfqd->in_service_queue) {
++ __bfq_bfqq_expire(bfqd, bfqq);
++ bfq_schedule_dispatch(bfqd);
++ }
++
++ bfq_log_bfqq(bfqd, bfqq, "exit_bfqq: %p, %d", bfqq,
++ atomic_read(&bfqq->ref));
++
++ bfq_put_cooperator(bfqq);
++
++ bfq_put_queue(bfqq);
++}
++
++static void bfq_init_icq(struct io_cq *icq)
++{
++ struct bfq_io_cq *bic = icq_to_bic(icq);
++
++ bic->ttime.last_end_request = jiffies;
++}
++
++static void bfq_exit_icq(struct io_cq *icq)
++{
++ struct bfq_io_cq *bic = icq_to_bic(icq);
++ struct bfq_data *bfqd = bic_to_bfqd(bic);
++
++ if (bic->bfqq[BLK_RW_ASYNC]) {
++ bfq_exit_bfqq(bfqd, bic->bfqq[BLK_RW_ASYNC]);
++ bic->bfqq[BLK_RW_ASYNC] = NULL;
++ }
++
++ if (bic->bfqq[BLK_RW_SYNC]) {
++ bfq_exit_bfqq(bfqd, bic->bfqq[BLK_RW_SYNC]);
++ bic->bfqq[BLK_RW_SYNC] = NULL;
++ }
++}
++
++/*
++ * Update the entity prio values; note that the new values will not
++ * be used until the next (re)activation.
++ */
++static void bfq_init_prio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
++{
++ struct task_struct *tsk = current;
++ int ioprio_class;
++
++ if (!bfq_bfqq_prio_changed(bfqq))
++ return;
++
++ ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio);
++ switch (ioprio_class) {
++ default:
++ dev_err(bfqq->bfqd->queue->backing_dev_info.dev,
++ "bfq: bad prio %x\n", ioprio_class);
++ case IOPRIO_CLASS_NONE:
++ /*
++ * No prio set, inherit CPU scheduling settings.
++ */
++ bfqq->entity.new_ioprio = task_nice_ioprio(tsk);
++ bfqq->entity.new_ioprio_class = task_nice_ioclass(tsk);
++ break;
++ case IOPRIO_CLASS_RT:
++ bfqq->entity.new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
++ bfqq->entity.new_ioprio_class = IOPRIO_CLASS_RT;
++ break;
++ case IOPRIO_CLASS_BE:
++ bfqq->entity.new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
++ bfqq->entity.new_ioprio_class = IOPRIO_CLASS_BE;
++ break;
++ case IOPRIO_CLASS_IDLE:
++ bfqq->entity.new_ioprio_class = IOPRIO_CLASS_IDLE;
++ bfqq->entity.new_ioprio = 7;
++ bfq_clear_bfqq_idle_window(bfqq);
++ break;
++ }
++
++ bfqq->entity.ioprio_changed = 1;
++
++ /*
++ * Keep track of original prio settings in case we have to temporarily
++ * elevate the priority of this queue.
++ */
++ bfqq->org_ioprio = bfqq->entity.new_ioprio;
++ bfq_clear_bfqq_prio_changed(bfqq);
++}
++
++static void bfq_changed_ioprio(struct bfq_io_cq *bic)
++{
++ struct bfq_data *bfqd;
++ struct bfq_queue *bfqq, *new_bfqq;
++ struct bfq_group *bfqg;
++ unsigned long uninitialized_var(flags);
++ int ioprio = bic->icq.ioc->ioprio;
++
++ bfqd = bfq_get_bfqd_locked(&(bic->icq.q->elevator->elevator_data),
++ &flags);
++ /*
++ * This condition may trigger on a newly created bic, be sure to drop
++ * the lock before returning.
++ */
++ if (unlikely(bfqd == NULL) || likely(bic->ioprio == ioprio))
++ goto out;
++
++ bfqq = bic->bfqq[BLK_RW_ASYNC];
++ if (bfqq != NULL) {
++ bfqg = container_of(bfqq->entity.sched_data, struct bfq_group,
++ sched_data);
++ new_bfqq = bfq_get_queue(bfqd, bfqg, BLK_RW_ASYNC, bic,
++ GFP_ATOMIC);
++ if (new_bfqq != NULL) {
++ bic->bfqq[BLK_RW_ASYNC] = new_bfqq;
++ bfq_log_bfqq(bfqd, bfqq,
++ "changed_ioprio: bfqq %p %d",
++ bfqq, atomic_read(&bfqq->ref));
++ bfq_put_queue(bfqq);
++ }
++ }
++
++ bfqq = bic->bfqq[BLK_RW_SYNC];
++ if (bfqq != NULL)
++ bfq_mark_bfqq_prio_changed(bfqq);
++
++ bic->ioprio = ioprio;
++
++out:
++ bfq_put_bfqd_unlock(bfqd, &flags);
++}
++
++static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
++ pid_t pid, int is_sync)
++{
++ RB_CLEAR_NODE(&bfqq->entity.rb_node);
++ INIT_LIST_HEAD(&bfqq->fifo);
++
++ atomic_set(&bfqq->ref, 0);
++ bfqq->bfqd = bfqd;
++
++ bfq_mark_bfqq_prio_changed(bfqq);
++
++ if (is_sync) {
++ if (!bfq_class_idle(bfqq))
++ bfq_mark_bfqq_idle_window(bfqq);
++ bfq_mark_bfqq_sync(bfqq);
++ }
++
++ /* Tentative initial value to trade off between thr and lat */
++ bfqq->max_budget = (2 * bfq_max_budget(bfqd)) / 3;
++ bfqq->pid = pid;
++
++ bfqq->raising_coeff = 1;
++ bfqq->last_rais_start_finish = 0;
++ bfqq->soft_rt_next_start = -1;
++}
++
++static struct bfq_queue *bfq_find_alloc_queue(struct bfq_data *bfqd,
++ struct bfq_group *bfqg,
++ int is_sync,
++ struct bfq_io_cq *bic,
++ gfp_t gfp_mask)
++{
++ struct bfq_queue *bfqq, *new_bfqq = NULL;
++
++retry:
++ /* bic always exists here */
++ bfqq = bic_to_bfqq(bic, is_sync);
++
++ /*
++ * Always try a new alloc if we fall back to the OOM bfqq
++ * originally, since it should just be a temporary situation.
++ */
++ if (bfqq == NULL || bfqq == &bfqd->oom_bfqq) {
++ bfqq = NULL;
++ if (new_bfqq != NULL) {
++ bfqq = new_bfqq;
++ new_bfqq = NULL;
++ } else if (gfp_mask & __GFP_WAIT) {
++ spin_unlock_irq(bfqd->queue->queue_lock);
++ new_bfqq = kmem_cache_alloc_node(bfq_pool,
++ gfp_mask | __GFP_ZERO,
++ bfqd->queue->node);
++ spin_lock_irq(bfqd->queue->queue_lock);
++ if (new_bfqq != NULL)
++ goto retry;
++ } else {
++ bfqq = kmem_cache_alloc_node(bfq_pool,
++ gfp_mask | __GFP_ZERO,
++ bfqd->queue->node);
++ }
++
++ if (bfqq != NULL) {
++ bfq_init_bfqq(bfqd, bfqq, current->pid, is_sync);
++ bfq_log_bfqq(bfqd, bfqq, "allocated");
++ } else {
++ bfqq = &bfqd->oom_bfqq;
++ bfq_log_bfqq(bfqd, bfqq, "using oom bfqq");
++ }
++
++ bfq_init_prio_data(bfqq, bic);
++ bfq_init_entity(&bfqq->entity, bfqg);
++ }
++
++ if (new_bfqq != NULL)
++ kmem_cache_free(bfq_pool, new_bfqq);
++
++ return bfqq;
++}
++
++static struct bfq_queue **bfq_async_queue_prio(struct bfq_data *bfqd,
++ struct bfq_group *bfqg,
++ int ioprio_class, int ioprio)
++{
++ switch (ioprio_class) {
++ case IOPRIO_CLASS_RT:
++ return &bfqg->async_bfqq[0][ioprio];
++ case IOPRIO_CLASS_NONE:
++ ioprio = IOPRIO_NORM;
++ /* fall through */
++ case IOPRIO_CLASS_BE:
++ return &bfqg->async_bfqq[1][ioprio];
++ case IOPRIO_CLASS_IDLE:
++ return &bfqg->async_idle_bfqq;
++ default:
++ BUG();
++ }
++}
++
++static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
++ struct bfq_group *bfqg, int is_sync,
++ struct bfq_io_cq *bic, gfp_t gfp_mask)
++{
++ const int ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
++ const int ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio);
++ struct bfq_queue **async_bfqq = NULL;
++ struct bfq_queue *bfqq = NULL;
++
++ if (!is_sync) {
++ async_bfqq = bfq_async_queue_prio(bfqd, bfqg, ioprio_class,
++ ioprio);
++ bfqq = *async_bfqq;
++ }
++
++ if (bfqq == NULL)
++ bfqq = bfq_find_alloc_queue(bfqd, bfqg, is_sync, bic, gfp_mask);
++
++ /*
++ * Pin the queue now that it's allocated, scheduler exit will prune it.
++ */
++ if (!is_sync && *async_bfqq == NULL) {
++ atomic_inc(&bfqq->ref);
++ bfq_log_bfqq(bfqd, bfqq, "get_queue, bfqq not in async: %p, %d",
++ bfqq, atomic_read(&bfqq->ref));
++ *async_bfqq = bfqq;
++ }
++
++ atomic_inc(&bfqq->ref);
++ bfq_log_bfqq(bfqd, bfqq, "get_queue, at end: %p, %d", bfqq,
++ atomic_read(&bfqq->ref));
++ return bfqq;
++}
++
++static void bfq_update_io_thinktime(struct bfq_data *bfqd,
++ struct bfq_io_cq *bic)
++{
++ unsigned long elapsed = jiffies - bic->ttime.last_end_request;
++ unsigned long ttime = min(elapsed, 2UL * bfqd->bfq_slice_idle);
++
++ bic->ttime.ttime_samples = (7*bic->ttime.ttime_samples + 256) / 8;
++ bic->ttime.ttime_total = (7*bic->ttime.ttime_total + 256*ttime) / 8;
++ bic->ttime.ttime_mean = (bic->ttime.ttime_total + 128) /
++ bic->ttime.ttime_samples;
++}
++
++static void bfq_update_io_seektime(struct bfq_data *bfqd,
++ struct bfq_queue *bfqq,
++ struct request *rq)
++{
++ sector_t sdist;
++ u64 total;
++
++ if (bfqq->last_request_pos < blk_rq_pos(rq))
++ sdist = blk_rq_pos(rq) - bfqq->last_request_pos;
++ else
++ sdist = bfqq->last_request_pos - blk_rq_pos(rq);
++
++ /*
++ * Don't allow the seek distance to get too large from the
++ * odd fragment, pagein, etc.
++ */
++ if (bfqq->seek_samples == 0) /* first request, not really a seek */
++ sdist = 0;
++ else if (bfqq->seek_samples <= 60) /* second & third seek */
++ sdist = min(sdist, (bfqq->seek_mean * 4) + 2*1024*1024);
++ else
++ sdist = min(sdist, (bfqq->seek_mean * 4) + 2*1024*64);
++
++ bfqq->seek_samples = (7*bfqq->seek_samples + 256) / 8;
++ bfqq->seek_total = (7*bfqq->seek_total + (u64)256*sdist) / 8;
++ total = bfqq->seek_total + (bfqq->seek_samples/2);
++ do_div(total, bfqq->seek_samples);
++ bfqq->seek_mean = (sector_t)total;
++
++ bfq_log_bfqq(bfqd, bfqq, "dist=%llu mean=%llu", (u64)sdist,
++ (u64)bfqq->seek_mean);
++}
++
++/*
++ * Disable idle window if the process thinks too long or seeks so much that
++ * it doesn't matter.
++ */
++static void bfq_update_idle_window(struct bfq_data *bfqd,
++ struct bfq_queue *bfqq,
++ struct bfq_io_cq *bic)
++{
++ int enable_idle;
++
++ /* Don't idle for async or idle io prio class. */
++ if (!bfq_bfqq_sync(bfqq) || bfq_class_idle(bfqq))
++ return;
++
++ enable_idle = bfq_bfqq_idle_window(bfqq);
++
++ if (atomic_read(&bic->icq.ioc->active_ref) == 0 ||
++ bfqd->bfq_slice_idle == 0 ||
++ (bfqd->hw_tag && BFQQ_SEEKY(bfqq) &&
++ bfqq->raising_coeff == 1))
++ enable_idle = 0;
++ else if (bfq_sample_valid(bic->ttime.ttime_samples)) {
++ if (bic->ttime.ttime_mean > bfqd->bfq_slice_idle &&
++ bfqq->raising_coeff == 1)
++ enable_idle = 0;
++ else
++ enable_idle = 1;
++ }
++ bfq_log_bfqq(bfqd, bfqq, "update_idle_window: enable_idle %d",
++ enable_idle);
++
++ if (enable_idle)
++ bfq_mark_bfqq_idle_window(bfqq);
++ else
++ bfq_clear_bfqq_idle_window(bfqq);
++}
++
++/*
++ * Called when a new fs request (rq) is added to bfqq. Check if there's
++ * something we should do about it.
++ */
++static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq,
++ struct request *rq)
++{
++ struct bfq_io_cq *bic = RQ_BIC(rq);
++
++ if (rq->cmd_flags & REQ_META)
++ bfqq->meta_pending++;
++
++ bfq_update_io_thinktime(bfqd, bic);
++ bfq_update_io_seektime(bfqd, bfqq, rq);
++ if (bfqq->entity.service > bfq_max_budget(bfqd) / 8 ||
++ !BFQQ_SEEKY(bfqq))
++ bfq_update_idle_window(bfqd, bfqq, bic);
++
++ bfq_log_bfqq(bfqd, bfqq,
++ "rq_enqueued: idle_window=%d (seeky %d, mean %llu)",
++ bfq_bfqq_idle_window(bfqq), BFQQ_SEEKY(bfqq),
++ (long long unsigned)bfqq->seek_mean);
++
++ bfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);
++
++ if (bfqq == bfqd->in_service_queue && bfq_bfqq_wait_request(bfqq)) {
++ int small_req = bfqq->queued[rq_is_sync(rq)] == 1 &&
++ blk_rq_sectors(rq) < 32;
++ int budget_timeout = bfq_bfqq_budget_timeout(bfqq);
++
++ /*
++ * There is just this request queued: if the request
++ * is small and the queue is not to be expired, then
++ * just exit.
++ *
++ * In this way, if the disk is being idled to wait for
++ * a new request from the in-service queue, we avoid
++ * unplugging the device and committing the disk to serve
++ * just a small request. On the contrary, we wait for
++ * the block layer to decide when to unplug the device:
++ * hopefully, new requests will be merged to this one
++ * quickly, then the device will be unplugged and
++ * larger requests will be dispatched.
++ */
++ if (small_req && !budget_timeout)
++ return;
++
++ /*
++ * A large enough request arrived, or the queue is to
++ * be expired: in both cases disk idling is to be
++ * stopped, so clear wait_request flag and reset
++ * timer.
++ */
++ bfq_clear_bfqq_wait_request(bfqq);
++ del_timer(&bfqd->idle_slice_timer);
++
++ /*
++ * The queue is not empty, because a new request just
++ * arrived. Hence we can safely expire the queue, in
++ * case of budget timeout, without risking that the
++ * timestamps of the queue are not updated correctly.
++ * See [1] for more details.
++ */
++ if (budget_timeout)
++ bfq_bfqq_expire(bfqd, bfqq, 0, BFQ_BFQQ_BUDGET_TIMEOUT);
++
++ /*
++ * Let the request rip immediately, or let a new queue be
++ * selected if bfqq has just been expired.
++ */
++ __blk_run_queue(bfqd->queue);
++ }
++}
++
++static void bfq_insert_request(struct request_queue *q, struct request *rq)
++{
++ struct bfq_data *bfqd = q->elevator->elevator_data;
++ struct bfq_queue *bfqq = RQ_BFQQ(rq);
++
++ assert_spin_locked(bfqd->queue->queue_lock);
++ bfq_init_prio_data(bfqq, RQ_BIC(rq));
++
++ bfq_add_rq_rb(rq);
++
++ rq_set_fifo_time(rq, jiffies + bfqd->bfq_fifo_expire[rq_is_sync(rq)]);
++ list_add_tail(&rq->queuelist, &bfqq->fifo);
++
++ bfq_rq_enqueued(bfqd, bfqq, rq);
++}
++
++static void bfq_update_hw_tag(struct bfq_data *bfqd)
++{
++ bfqd->max_rq_in_driver = max(bfqd->max_rq_in_driver,
++ bfqd->rq_in_driver);
++
++ if (bfqd->hw_tag == 1)
++ return;
++
++ /*
++ * This sample is valid if the number of outstanding requests
++ * is large enough to allow a queueing behavior. Note that the
++ * sum is not exact, as it's not taking into account deactivated
++ * requests.
++ */
++ if (bfqd->rq_in_driver + bfqd->queued < BFQ_HW_QUEUE_THRESHOLD)
++ return;
++
++ if (bfqd->hw_tag_samples++ < BFQ_HW_QUEUE_SAMPLES)
++ return;
++
++ bfqd->hw_tag = bfqd->max_rq_in_driver > BFQ_HW_QUEUE_THRESHOLD;
++ bfqd->max_rq_in_driver = 0;
++ bfqd->hw_tag_samples = 0;
++}
++
++static void bfq_completed_request(struct request_queue *q, struct request *rq)
++{
++ struct bfq_queue *bfqq = RQ_BFQQ(rq);
++ struct bfq_data *bfqd = bfqq->bfqd;
++ const int sync = rq_is_sync(rq);
++
++ bfq_log_bfqq(bfqd, bfqq, "completed %u sects req (%d)",
++ blk_rq_sectors(rq), sync);
++
++ bfq_update_hw_tag(bfqd);
++
++ WARN_ON(!bfqd->rq_in_driver);
++ WARN_ON(!bfqq->dispatched);
++ bfqd->rq_in_driver--;
++ bfqq->dispatched--;
++
++ if (bfq_bfqq_sync(bfqq))
++ bfqd->sync_flight--;
++
++ if (sync)
++ RQ_BIC(rq)->ttime.last_end_request = jiffies;
++
++ /*
++ * The computation of softrt_next_start was scheduled for the next
++ * request completion: it is now time to compute it.
++ */
++ if (bfq_bfqq_softrt_update(bfqq) && RB_EMPTY_ROOT(&bfqq->sort_list))
++ bfqq->soft_rt_next_start =
++ bfq_bfqq_softrt_next_start(bfqd, bfqq);
++
++ /*
++ * If this is the in-service queue, check if it needs to be expired,
++ * or if we want to idle in case it has no pending requests.
++ */
++ if (bfqd->in_service_queue == bfqq) {
++ if (bfq_bfqq_budget_new(bfqq))
++ bfq_set_budget_timeout(bfqd);
++
++ if (bfq_bfqq_must_idle(bfqq)) {
++ bfq_arm_slice_timer(bfqd);
++ goto out;
++ } else if (bfq_may_expire_for_budg_timeout(bfqq))
++ bfq_bfqq_expire(bfqd, bfqq, 0, BFQ_BFQQ_BUDGET_TIMEOUT);
++ else if (RB_EMPTY_ROOT(&bfqq->sort_list) &&
++ (bfqq->dispatched == 0 ||
++ !bfq_bfqq_must_not_expire(bfqq)))
++ bfq_bfqq_expire(bfqd, bfqq, 0,
++ BFQ_BFQQ_NO_MORE_REQUESTS);
++ }
++
++ if (!bfqd->rq_in_driver)
++ bfq_schedule_dispatch(bfqd);
++
++out:
++ return;
++}
++
++static inline int __bfq_may_queue(struct bfq_queue *bfqq)
++{
++ if (bfq_bfqq_wait_request(bfqq) && bfq_bfqq_must_alloc(bfqq)) {
++ bfq_clear_bfqq_must_alloc(bfqq);
++ return ELV_MQUEUE_MUST;
++ }
++
++ return ELV_MQUEUE_MAY;
++}
++
++static int bfq_may_queue(struct request_queue *q, int rw)
++{
++ struct bfq_data *bfqd = q->elevator->elevator_data;
++ struct task_struct *tsk = current;
++ struct bfq_io_cq *bic;
++ struct bfq_queue *bfqq;
++
++ /*
++ * Don't force setup of a queue from here, as a call to may_queue
++ * does not necessarily imply that a request actually will be queued.
++ * So just lookup a possibly existing queue, or return 'may queue'
++ * if that fails.
++ */
++ bic = bfq_bic_lookup(bfqd, tsk->io_context);
++ if (bic == NULL)
++ return ELV_MQUEUE_MAY;
++
++ bfqq = bic_to_bfqq(bic, rw_is_sync(rw));
++ if (bfqq != NULL) {
++ bfq_init_prio_data(bfqq, bic);
++
++ return __bfq_may_queue(bfqq);
++ }
++
++ return ELV_MQUEUE_MAY;
++}
++
++/*
++ * Queue lock held here.
++ */
++static void bfq_put_request(struct request *rq)
++{
++ struct bfq_queue *bfqq = RQ_BFQQ(rq);
++
++ if (bfqq != NULL) {
++ const int rw = rq_data_dir(rq);
++
++ BUG_ON(!bfqq->allocated[rw]);
++ bfqq->allocated[rw]--;
++
++ rq->elv.priv[0] = NULL;
++ rq->elv.priv[1] = NULL;
++
++ bfq_log_bfqq(bfqq->bfqd, bfqq, "put_request %p, %d",
++ bfqq, atomic_read(&bfqq->ref));
++ bfq_put_queue(bfqq);
++ }
++}
++
++static struct bfq_queue *
++bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
++ struct bfq_queue *bfqq)
++{
++ bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu",
++ (long unsigned)bfqq->new_bfqq->pid);
++ bic_set_bfqq(bic, bfqq->new_bfqq, 1);
++ bfq_mark_bfqq_coop(bfqq->new_bfqq);
++ bfq_put_queue(bfqq);
++ return bic_to_bfqq(bic, 1);
++}
++
++/*
++ * Returns NULL if a new bfqq should be allocated, or the old bfqq if this
++ * was the last process referring to said bfqq.
++ */
++static struct bfq_queue *
++bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq)
++{
++ bfq_log_bfqq(bfqq->bfqd, bfqq, "splitting queue");
++ if (bfqq_process_refs(bfqq) == 1) {
++ bfqq->pid = current->pid;
++ bfq_clear_bfqq_coop(bfqq);
++ bfq_clear_bfqq_split_coop(bfqq);
++ return bfqq;
++ }
++
++ bic_set_bfqq(bic, NULL, 1);
++
++ bfq_put_cooperator(bfqq);
++
++ bfq_put_queue(bfqq);
++ return NULL;
++}
++
++/*
++ * Allocate bfq data structures associated with this request.
++ */
++static int bfq_set_request(struct request_queue *q, struct request *rq,
++ struct bio *bio, gfp_t gfp_mask)
++{
++ struct bfq_data *bfqd = q->elevator->elevator_data;
++ struct bfq_io_cq *bic = icq_to_bic(rq->elv.icq);
++ const int rw = rq_data_dir(rq);
++ const int is_sync = rq_is_sync(rq);
++ struct bfq_queue *bfqq;
++ struct bfq_group *bfqg;
++ unsigned long flags;
++
++ might_sleep_if(gfp_mask & __GFP_WAIT);
++
++ bfq_changed_ioprio(bic);
++
++ spin_lock_irqsave(q->queue_lock, flags);
++
++ if (bic == NULL)
++ goto queue_fail;
++
++ bfqg = bfq_bic_update_cgroup(bic);
++
++new_queue:
++ bfqq = bic_to_bfqq(bic, is_sync);
++ if (bfqq == NULL || bfqq == &bfqd->oom_bfqq) {
++ bfqq = bfq_get_queue(bfqd, bfqg, is_sync, bic, gfp_mask);
++ bic_set_bfqq(bic, bfqq, is_sync);
++ } else {
++ /*
++ * If the queue was seeky for too long, break it apart.
++ */
++ if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq)) {
++ bfq_log_bfqq(bfqd, bfqq, "breaking apart bfqq");
++ bfqq = bfq_split_bfqq(bic, bfqq);
++ if (!bfqq)
++ goto new_queue;
++ }
++
++ /*
++ * Check to see if this queue is scheduled to merge with
++ * another closely cooperating queue. The merging of queues
++ * happens here as it must be done in process context.
++ * The reference on new_bfqq was taken in merge_bfqqs.
++ */
++ if (bfqq->new_bfqq != NULL)
++ bfqq = bfq_merge_bfqqs(bfqd, bic, bfqq);
++ }
++
++ bfqq->allocated[rw]++;
++ atomic_inc(&bfqq->ref);
++ bfq_log_bfqq(bfqd, bfqq, "set_request: bfqq %p, %d", bfqq,
++ atomic_read(&bfqq->ref));
++
++ rq->elv.priv[0] = bic;
++ rq->elv.priv[1] = bfqq;
++
++ spin_unlock_irqrestore(q->queue_lock, flags);
++
++ return 0;
++
++queue_fail:
++ bfq_schedule_dispatch(bfqd);
++ spin_unlock_irqrestore(q->queue_lock, flags);
++
++ return 1;
++}
++
++static void bfq_kick_queue(struct work_struct *work)
++{
++ struct bfq_data *bfqd =
++ container_of(work, struct bfq_data, unplug_work);
++ struct request_queue *q = bfqd->queue;
++
++ spin_lock_irq(q->queue_lock);
++ __blk_run_queue(q);
++ spin_unlock_irq(q->queue_lock);
++}
++
++/*
++ * Handler of the expiration of the timer running if the in-service queue
++ * is idling inside its time slice.
++ */
++static void bfq_idle_slice_timer(unsigned long data)
++{
++ struct bfq_data *bfqd = (struct bfq_data *)data;
++ struct bfq_queue *bfqq;
++ unsigned long flags;
++ enum bfqq_expiration reason;
++
++ spin_lock_irqsave(bfqd->queue->queue_lock, flags);
++
++ bfqq = bfqd->in_service_queue;
++ /*
++ * Theoretical race here: the in-service queue can be NULL or different
++ * from the queue that was idling if the timer handler spins on
++ * the queue_lock and a new request arrives for the current
++ * queue and there is a full dispatch cycle that changes the
++ * in-service queue. This can hardly happen, but in the worst case
++ * we just expire a queue too early.
++ */
++ if (bfqq != NULL) {
++ bfq_log_bfqq(bfqd, bfqq, "slice_timer expired");
++ if (bfq_bfqq_budget_timeout(bfqq))
++ /*
++ * Also here the queue can be safely expired
++ * for budget timeout without wasting
++ * guarantees
++ */
++ reason = BFQ_BFQQ_BUDGET_TIMEOUT;
++ else if (bfqq->queued[0] == 0 && bfqq->queued[1] == 0)
++ /*
++ * The queue may not be empty upon timer expiration,
++ * because we may not disable the timer when the first
++ * request of the in-service queue arrives during
++ * disk idling
++ */
++ reason = BFQ_BFQQ_TOO_IDLE;
++ else
++ goto schedule_dispatch;
++
++ bfq_bfqq_expire(bfqd, bfqq, 1, reason);
++ }
++
++schedule_dispatch:
++ bfq_schedule_dispatch(bfqd);
++
++ spin_unlock_irqrestore(bfqd->queue->queue_lock, flags);
++}
++
++static void bfq_shutdown_timer_wq(struct bfq_data *bfqd)
++{
++ del_timer_sync(&bfqd->idle_slice_timer);
++ cancel_work_sync(&bfqd->unplug_work);
++}
++
++static inline void __bfq_put_async_bfqq(struct bfq_data *bfqd,
++ struct bfq_queue **bfqq_ptr)
++{
++ struct bfq_group *root_group = bfqd->root_group;
++ struct bfq_queue *bfqq = *bfqq_ptr;
++
++ bfq_log(bfqd, "put_async_bfqq: %p", bfqq);
++ if (bfqq != NULL) {
++ bfq_bfqq_move(bfqd, bfqq, &bfqq->entity, root_group);
++ bfq_log_bfqq(bfqd, bfqq, "put_async_bfqq: putting %p, %d",
++ bfqq, atomic_read(&bfqq->ref));
++ bfq_put_queue(bfqq);
++ *bfqq_ptr = NULL;
++ }
++}
++
++/*
++ * Release all the bfqg references to its async queues. If we are
++ * deallocating the group these queues may still contain requests, so
++ * we reparent them to the root cgroup (i.e., the only one that will
++ * exist for sure untill all the requests on a device are gone).
++ */
++static void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg)
++{
++ int i, j;
++
++ for (i = 0; i < 2; i++)
++ for (j = 0; j < IOPRIO_BE_NR; j++)
++ __bfq_put_async_bfqq(bfqd, &bfqg->async_bfqq[i][j]);
++
++ __bfq_put_async_bfqq(bfqd, &bfqg->async_idle_bfqq);
++}
++
++static void bfq_exit_queue(struct elevator_queue *e)
++{
++ struct bfq_data *bfqd = e->elevator_data;
++ struct request_queue *q = bfqd->queue;
++ struct bfq_queue *bfqq, *n;
++
++ bfq_shutdown_timer_wq(bfqd);
++
++ spin_lock_irq(q->queue_lock);
++
++ BUG_ON(bfqd->in_service_queue != NULL);
++ list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list)
++ bfq_deactivate_bfqq(bfqd, bfqq, 0);
++
++ bfq_disconnect_groups(bfqd);
++ spin_unlock_irq(q->queue_lock);
++
++ bfq_shutdown_timer_wq(bfqd);
++
++ synchronize_rcu();
++
++ BUG_ON(timer_pending(&bfqd->idle_slice_timer));
++
++ bfq_free_root_group(bfqd);
++ kfree(bfqd);
++}
++
++static int bfq_init_queue(struct request_queue *q)
++{
++ struct bfq_group *bfqg;
++ struct bfq_data *bfqd;
++
++ bfqd = kzalloc_node(sizeof(*bfqd), GFP_KERNEL, q->node);
++ if (bfqd == NULL)
++ return -ENOMEM;
++
++ /*
++ * Our fallback bfqq if bfq_find_alloc_queue() runs into OOM issues.
++ * Grab a permanent reference to it, so that the normal code flow
++ * will not attempt to free it.
++ */
++ bfq_init_bfqq(bfqd, &bfqd->oom_bfqq, 1, 0);
++ atomic_inc(&bfqd->oom_bfqq.ref);
++
++ bfqd->queue = q;
++ q->elevator->elevator_data = bfqd;
++
++ bfqg = bfq_alloc_root_group(bfqd, q->node);
++ if (bfqg == NULL) {
++ kfree(bfqd);
++ return -ENOMEM;
++ }
++
++ bfqd->root_group = bfqg;
++
++ init_timer(&bfqd->idle_slice_timer);
++ bfqd->idle_slice_timer.function = bfq_idle_slice_timer;
++ bfqd->idle_slice_timer.data = (unsigned long)bfqd;
++
++ bfqd->rq_pos_tree = RB_ROOT;
++
++ INIT_WORK(&bfqd->unplug_work, bfq_kick_queue);
++
++ INIT_LIST_HEAD(&bfqd->active_list);
++ INIT_LIST_HEAD(&bfqd->idle_list);
++
++ bfqd->hw_tag = -1;
++
++ bfqd->bfq_max_budget = bfq_default_max_budget;
++
++ bfqd->bfq_quantum = bfq_quantum;
++ bfqd->bfq_fifo_expire[0] = bfq_fifo_expire[0];
++ bfqd->bfq_fifo_expire[1] = bfq_fifo_expire[1];
++ bfqd->bfq_back_max = bfq_back_max;
++ bfqd->bfq_back_penalty = bfq_back_penalty;
++ bfqd->bfq_slice_idle = bfq_slice_idle;
++ bfqd->bfq_class_idle_last_service = 0;
++ bfqd->bfq_max_budget_async_rq = bfq_max_budget_async_rq;
++ bfqd->bfq_timeout[BLK_RW_ASYNC] = bfq_timeout_async;
++ bfqd->bfq_timeout[BLK_RW_SYNC] = bfq_timeout_sync;
++
++ bfqd->low_latency = true;
++
++ bfqd->bfq_raising_coeff = 20;
++ bfqd->bfq_raising_rt_max_time = msecs_to_jiffies(300);
++ bfqd->bfq_raising_max_time = 0;
++ bfqd->bfq_raising_min_idle_time = msecs_to_jiffies(2000);
++ bfqd->bfq_raising_min_inter_arr_async = msecs_to_jiffies(500);
++ bfqd->bfq_raising_max_softrt_rate = 7000; /*
++ * Approximate rate required
++ * to playback or record a
++ * high-definition compressed
++ * video.
++ */
++ bfqd->raised_busy_queues = 0;
++
++ /* Initially estimate the device's peak rate as the reference rate */
++ if (blk_queue_nonrot(bfqd->queue)) {
++ bfqd->RT_prod = R_nonrot * T_nonrot;
++ bfqd->peak_rate = R_nonrot;
++ } else {
++ bfqd->RT_prod = R_rot * T_rot;
++ bfqd->peak_rate = R_rot;
++ }
++
++ return 0;
++}
++
++static void bfq_slab_kill(void)
++{
++ if (bfq_pool != NULL)
++ kmem_cache_destroy(bfq_pool);
++}
++
++static int __init bfq_slab_setup(void)
++{
++ bfq_pool = KMEM_CACHE(bfq_queue, 0);
++ if (bfq_pool == NULL)
++ return -ENOMEM;
++ return 0;
++}
++
++static ssize_t bfq_var_show(unsigned int var, char *page)
++{
++ return sprintf(page, "%d\n", var);
++}
++
++static ssize_t bfq_var_store(unsigned long *var, const char *page, size_t count)
++{
++ unsigned long new_val;
++ int ret = kstrtoul(page, 10, &new_val);
++
++ if (ret == 0)
++ *var = new_val;
++
++ return count;
++}
++
++static ssize_t bfq_raising_max_time_show(struct elevator_queue *e, char *page)
++{
++ struct bfq_data *bfqd = e->elevator_data;
++ return sprintf(page, "%d\n", bfqd->bfq_raising_max_time > 0 ?
++ jiffies_to_msecs(bfqd->bfq_raising_max_time) :
++ jiffies_to_msecs(bfq_wrais_duration(bfqd)));
++}
++
++static ssize_t bfq_weights_show(struct elevator_queue *e, char *page)
++{
++ struct bfq_queue *bfqq;
++ struct bfq_data *bfqd = e->elevator_data;
++ ssize_t num_char = 0;
++
++ num_char += sprintf(page + num_char, "Tot reqs queued %d\n\n",
++ bfqd->queued);
++
++ spin_lock_irq(bfqd->queue->queue_lock);
++
++ num_char += sprintf(page + num_char, "Active:\n");
++ list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list) {
++ num_char += sprintf(page + num_char,
++ "pid%d: weight %hu, nr_queued %d %d,"
++ " dur %d/%u\n",
++ bfqq->pid,
++ bfqq->entity.weight,
++ bfqq->queued[0],
++ bfqq->queued[1],
++ jiffies_to_msecs(jiffies -
++ bfqq->last_rais_start_finish),
++ jiffies_to_msecs(bfqq->raising_cur_max_time));
++ }
++
++ num_char += sprintf(page + num_char, "Idle:\n");
++ list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list) {
++ num_char += sprintf(page + num_char,
++ "pid%d: weight %hu, dur %d/%u\n",
++ bfqq->pid,
++ bfqq->entity.weight,
++ jiffies_to_msecs(jiffies -
++ bfqq->last_rais_start_finish),
++ jiffies_to_msecs(bfqq->raising_cur_max_time));
++ }
++
++ spin_unlock_irq(bfqd->queue->queue_lock);
++
++ return num_char;
++}
++
++#define SHOW_FUNCTION(__FUNC, __VAR, __CONV) \
++static ssize_t __FUNC(struct elevator_queue *e, char *page) \
++{ \
++ struct bfq_data *bfqd = e->elevator_data; \
++ unsigned int __data = __VAR; \
++ if (__CONV) \
++ __data = jiffies_to_msecs(__data); \
++ return bfq_var_show(__data, (page)); \
++}
++SHOW_FUNCTION(bfq_quantum_show, bfqd->bfq_quantum, 0);
++SHOW_FUNCTION(bfq_fifo_expire_sync_show, bfqd->bfq_fifo_expire[1], 1);
++SHOW_FUNCTION(bfq_fifo_expire_async_show, bfqd->bfq_fifo_expire[0], 1);
++SHOW_FUNCTION(bfq_back_seek_max_show, bfqd->bfq_back_max, 0);
++SHOW_FUNCTION(bfq_back_seek_penalty_show, bfqd->bfq_back_penalty, 0);
++SHOW_FUNCTION(bfq_slice_idle_show, bfqd->bfq_slice_idle, 1);
++SHOW_FUNCTION(bfq_max_budget_show, bfqd->bfq_user_max_budget, 0);
++SHOW_FUNCTION(bfq_max_budget_async_rq_show, bfqd->bfq_max_budget_async_rq, 0);
++SHOW_FUNCTION(bfq_timeout_sync_show, bfqd->bfq_timeout[BLK_RW_SYNC], 1);
++SHOW_FUNCTION(bfq_timeout_async_show, bfqd->bfq_timeout[BLK_RW_ASYNC], 1);
++SHOW_FUNCTION(bfq_low_latency_show, bfqd->low_latency, 0);
++SHOW_FUNCTION(bfq_raising_coeff_show, bfqd->bfq_raising_coeff, 0);
++SHOW_FUNCTION(bfq_raising_rt_max_time_show, bfqd->bfq_raising_rt_max_time, 1);
++SHOW_FUNCTION(bfq_raising_min_idle_time_show, bfqd->bfq_raising_min_idle_time,
++ 1);
++SHOW_FUNCTION(bfq_raising_min_inter_arr_async_show,
++ bfqd->bfq_raising_min_inter_arr_async,
++ 1);
++SHOW_FUNCTION(bfq_raising_max_softrt_rate_show,
++ bfqd->bfq_raising_max_softrt_rate, 0);
++#undef SHOW_FUNCTION
++
++#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV) \
++static ssize_t \
++__FUNC(struct elevator_queue *e, const char *page, size_t count) \
++{ \
++ struct bfq_data *bfqd = e->elevator_data; \
++ unsigned long uninitialized_var(__data); \
++ int ret = bfq_var_store(&__data, (page), count); \
++ if (__data < (MIN)) \
++ __data = (MIN); \
++ else if (__data > (MAX)) \
++ __data = (MAX); \
++ if (__CONV) \
++ *(__PTR) = msecs_to_jiffies(__data); \
++ else \
++ *(__PTR) = __data; \
++ return ret; \
++}
++STORE_FUNCTION(bfq_quantum_store, &bfqd->bfq_quantum, 1, INT_MAX, 0);
++STORE_FUNCTION(bfq_fifo_expire_sync_store, &bfqd->bfq_fifo_expire[1], 1,
++ INT_MAX, 1);
++STORE_FUNCTION(bfq_fifo_expire_async_store, &bfqd->bfq_fifo_expire[0], 1,
++ INT_MAX, 1);
++STORE_FUNCTION(bfq_back_seek_max_store, &bfqd->bfq_back_max, 0, INT_MAX, 0);
++STORE_FUNCTION(bfq_back_seek_penalty_store, &bfqd->bfq_back_penalty, 1,
++ INT_MAX, 0);
++STORE_FUNCTION(bfq_slice_idle_store, &bfqd->bfq_slice_idle, 0, INT_MAX, 1);
++STORE_FUNCTION(bfq_max_budget_async_rq_store, &bfqd->bfq_max_budget_async_rq,
++ 1, INT_MAX, 0);
++STORE_FUNCTION(bfq_timeout_async_store, &bfqd->bfq_timeout[BLK_RW_ASYNC], 0,
++ INT_MAX, 1);
++STORE_FUNCTION(bfq_raising_coeff_store, &bfqd->bfq_raising_coeff, 1,
++ INT_MAX, 0);
++STORE_FUNCTION(bfq_raising_max_time_store, &bfqd->bfq_raising_max_time, 0,
++ INT_MAX, 1);
++STORE_FUNCTION(bfq_raising_rt_max_time_store, &bfqd->bfq_raising_rt_max_time, 0,
++ INT_MAX, 1);
++STORE_FUNCTION(bfq_raising_min_idle_time_store,
++ &bfqd->bfq_raising_min_idle_time, 0, INT_MAX, 1);
++STORE_FUNCTION(bfq_raising_min_inter_arr_async_store,
++ &bfqd->bfq_raising_min_inter_arr_async, 0, INT_MAX, 1);
++STORE_FUNCTION(bfq_raising_max_softrt_rate_store,
++ &bfqd->bfq_raising_max_softrt_rate, 0, INT_MAX, 0);
++#undef STORE_FUNCTION
++
++/* do nothing for the moment */
++static ssize_t bfq_weights_store(struct elevator_queue *e,
++ const char *page, size_t count)
++{
++ return count;
++}
++
++static inline unsigned long bfq_estimated_max_budget(struct bfq_data *bfqd)
++{
++ u64 timeout = jiffies_to_msecs(bfqd->bfq_timeout[BLK_RW_SYNC]);
++
++ if (bfqd->peak_rate_samples >= BFQ_PEAK_RATE_SAMPLES)
++ return bfq_calc_max_budget(bfqd->peak_rate, timeout);
++ else
++ return bfq_default_max_budget;
++}
++
++static ssize_t bfq_max_budget_store(struct elevator_queue *e,
++ const char *page, size_t count)
++{
++ struct bfq_data *bfqd = e->elevator_data;
++ unsigned long uninitialized_var(__data);
++ int ret = bfq_var_store(&__data, (page), count);
++
++ if (__data == 0)
++ bfqd->bfq_max_budget = bfq_estimated_max_budget(bfqd);
++ else {
++ if (__data > INT_MAX)
++ __data = INT_MAX;
++ bfqd->bfq_max_budget = __data;
++ }
++
++ bfqd->bfq_user_max_budget = __data;
++
++ return ret;
++}
++
++static ssize_t bfq_timeout_sync_store(struct elevator_queue *e,
++ const char *page, size_t count)
++{
++ struct bfq_data *bfqd = e->elevator_data;
++ unsigned long uninitialized_var(__data);
++ int ret = bfq_var_store(&__data, (page), count);
++
++ if (__data < 1)
++ __data = 1;
++ else if (__data > INT_MAX)
++ __data = INT_MAX;
++
++ bfqd->bfq_timeout[BLK_RW_SYNC] = msecs_to_jiffies(__data);
++ if (bfqd->bfq_user_max_budget == 0)
++ bfqd->bfq_max_budget = bfq_estimated_max_budget(bfqd);
++
++ return ret;
++}
++
++static ssize_t bfq_low_latency_store(struct elevator_queue *e,
++ const char *page, size_t count)
++{
++ struct bfq_data *bfqd = e->elevator_data;
++ unsigned long uninitialized_var(__data);
++ int ret = bfq_var_store(&__data, (page), count);
++
++ if (__data > 1)
++ __data = 1;
++ if (__data == 0 && bfqd->low_latency != 0)
++ bfq_end_raising(bfqd);
++ bfqd->low_latency = __data;
++
++ return ret;
++}
++
++#define BFQ_ATTR(name) \
++ __ATTR(name, S_IRUGO|S_IWUSR, bfq_##name##_show, bfq_##name##_store)
++
++static struct elv_fs_entry bfq_attrs[] = {
++ BFQ_ATTR(quantum),
++ BFQ_ATTR(fifo_expire_sync),
++ BFQ_ATTR(fifo_expire_async),
++ BFQ_ATTR(back_seek_max),
++ BFQ_ATTR(back_seek_penalty),
++ BFQ_ATTR(slice_idle),
++ BFQ_ATTR(max_budget),
++ BFQ_ATTR(max_budget_async_rq),
++ BFQ_ATTR(timeout_sync),
++ BFQ_ATTR(timeout_async),
++ BFQ_ATTR(low_latency),
++ BFQ_ATTR(raising_coeff),
++ BFQ_ATTR(raising_max_time),
++ BFQ_ATTR(raising_rt_max_time),
++ BFQ_ATTR(raising_min_idle_time),
++ BFQ_ATTR(raising_min_inter_arr_async),
++ BFQ_ATTR(raising_max_softrt_rate),
++ BFQ_ATTR(weights),
++ __ATTR_NULL
++};
++
++static struct elevator_type iosched_bfq = {
++ .ops = {
++ .elevator_merge_fn = bfq_merge,
++ .elevator_merged_fn = bfq_merged_request,
++ .elevator_merge_req_fn = bfq_merged_requests,
++ .elevator_allow_merge_fn = bfq_allow_merge,
++ .elevator_dispatch_fn = bfq_dispatch_requests,
++ .elevator_add_req_fn = bfq_insert_request,
++ .elevator_activate_req_fn = bfq_activate_request,
++ .elevator_deactivate_req_fn = bfq_deactivate_request,
++ .elevator_completed_req_fn = bfq_completed_request,
++ .elevator_former_req_fn = elv_rb_former_request,
++ .elevator_latter_req_fn = elv_rb_latter_request,
++ .elevator_init_icq_fn = bfq_init_icq,
++ .elevator_exit_icq_fn = bfq_exit_icq,
++ .elevator_set_req_fn = bfq_set_request,
++ .elevator_put_req_fn = bfq_put_request,
++ .elevator_may_queue_fn = bfq_may_queue,
++ .elevator_init_fn = bfq_init_queue,
++ .elevator_exit_fn = bfq_exit_queue,
++ },
++ .icq_size = sizeof(struct bfq_io_cq),
++ .icq_align = __alignof__(struct bfq_io_cq),
++ .elevator_attrs = bfq_attrs,
++ .elevator_name = "bfq",
++ .elevator_owner = THIS_MODULE,
++};
++
++static int __init bfq_init(void)
++{
++ /*
++ * Can be 0 on HZ < 1000 setups.
++ */
++ if (bfq_slice_idle == 0)
++ bfq_slice_idle = 1;
++
++ if (bfq_timeout_async == 0)
++ bfq_timeout_async = 1;
++
++ if (bfq_slab_setup())
++ return -ENOMEM;
++
++ elv_register(&iosched_bfq);
++ printk(KERN_INFO "BFQ I/O-scheduler version: v7");
++
++ return 0;
++}
++
++static void __exit bfq_exit(void)
++{
++ elv_unregister(&iosched_bfq);
++ bfq_slab_kill();
++}
++
++module_init(bfq_init);
++module_exit(bfq_exit);
++
++MODULE_AUTHOR("Fabio Checconi, Paolo Valente");
++MODULE_LICENSE("GPL");
++MODULE_DESCRIPTION("Budget Fair Queueing IO scheduler");
+diff --git a/block/bfq-sched.c b/block/bfq-sched.c
+new file mode 100644
+index 0000000..30df81c
+--- /dev/null
++++ b/block/bfq-sched.c
+@@ -0,0 +1,1077 @@
++/*
++ * BFQ: Hierarchical B-WF2Q+ scheduler.
++ *
++ * Based on ideas and code from CFQ:
++ * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
++ *
++ * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
++ * Paolo Valente <paolo.valente@unimore.it>
++ *
++ * Copyright (C) 2010 Paolo Valente <paolo.valente@unimore.it>
++ */
++
++#ifdef CONFIG_CGROUP_BFQIO
++#define for_each_entity(entity) \
++ for (; entity != NULL; entity = entity->parent)
++
++#define for_each_entity_safe(entity, parent) \
++ for (; entity && ({ parent = entity->parent; 1; }); entity = parent)
++
++static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd,
++ int extract,
++ struct bfq_data *bfqd);
++
++static inline void bfq_update_budget(struct bfq_entity *next_active)
++{
++ struct bfq_entity *bfqg_entity;
++ struct bfq_group *bfqg;
++ struct bfq_sched_data *group_sd;
++
++ BUG_ON(next_active == NULL);
++
++ group_sd = next_active->sched_data;
++
++ bfqg = container_of(group_sd, struct bfq_group, sched_data);
++ /*
++ * bfq_group's my_entity field is not NULL only if the group
++ * is not the root group. We must not touch the root entity
++ * as it must never become an active entity.
++ */
++ bfqg_entity = bfqg->my_entity;
++ if (bfqg_entity != NULL)
++ bfqg_entity->budget = next_active->budget;
++}
++
++static int bfq_update_next_active(struct bfq_sched_data *sd)
++{
++ struct bfq_entity *next_active;
++
++ if (sd->active_entity != NULL)
++ /* will update/requeue at the end of service */
++ return 0;
++
++ /*
++ * NOTE: this can be improved in many ways, such as returning
++ * 1 (and thus propagating upwards the update) only when the
++ * budget changes, or caching the bfqq that will be scheduled
++ * next from this subtree. By now we worry more about
++ * correctness than about performance...
++ */
++ next_active = bfq_lookup_next_entity(sd, 0, NULL);
++ sd->next_active = next_active;
++
++ if (next_active != NULL)
++ bfq_update_budget(next_active);
++
++ return 1;
++}
++
++static inline void bfq_check_next_active(struct bfq_sched_data *sd,
++ struct bfq_entity *entity)
++{
++ BUG_ON(sd->next_active != entity);
++}
++#else
++#define for_each_entity(entity) \
++ for (; entity != NULL; entity = NULL)
++
++#define for_each_entity_safe(entity, parent) \
++ for (parent = NULL; entity != NULL; entity = parent)
++
++static inline int bfq_update_next_active(struct bfq_sched_data *sd)
++{
++ return 0;
++}
++
++static inline void bfq_check_next_active(struct bfq_sched_data *sd,
++ struct bfq_entity *entity)
++{
++}
++
++static inline void bfq_update_budget(struct bfq_entity *next_active)
++{
++}
++#endif
++
++/*
++ * Shift for timestamp calculations. This actually limits the maximum
++ * service allowed in one timestamp delta (small shift values increase it),
++ * the maximum total weight that can be used for the queues in the system
++ * (big shift values increase it), and the period of virtual time wraparounds.
++ */
++#define WFQ_SERVICE_SHIFT 22
++
++/**
++ * bfq_gt - compare two timestamps.
++ * @a: first ts.
++ * @b: second ts.
++ *
++ * Return @a > @b, dealing with wrapping correctly.
++ */
++static inline int bfq_gt(u64 a, u64 b)
++{
++ return (s64)(a - b) > 0;
++}
++
++static inline struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity)
++{
++ struct bfq_queue *bfqq = NULL;
++
++ BUG_ON(entity == NULL);
++
++ if (entity->my_sched_data == NULL)
++ bfqq = container_of(entity, struct bfq_queue, entity);
++
++ return bfqq;
++}
++
++
++/**
++ * bfq_delta - map service into the virtual time domain.
++ * @service: amount of service.
++ * @weight: scale factor (weight of an entity or weight sum).
++ */
++static inline u64 bfq_delta(unsigned long service,
++ unsigned long weight)
++{
++ u64 d = (u64)service << WFQ_SERVICE_SHIFT;
++
++ do_div(d, weight);
++ return d;
++}
++
++/**
++ * bfq_calc_finish - assign the finish time to an entity.
++ * @entity: the entity to act upon.
++ * @service: the service to be charged to the entity.
++ */
++static inline void bfq_calc_finish(struct bfq_entity *entity,
++ unsigned long service)
++{
++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
++
++ BUG_ON(entity->weight == 0);
++
++ entity->finish = entity->start +
++ bfq_delta(service, entity->weight);
++
++ if (bfqq != NULL) {
++ bfq_log_bfqq(bfqq->bfqd, bfqq,
++ "calc_finish: serv %lu, w %d",
++ service, entity->weight);
++ bfq_log_bfqq(bfqq->bfqd, bfqq,
++ "calc_finish: start %llu, finish %llu, delta %llu",
++ entity->start, entity->finish,
++ bfq_delta(service, entity->weight));
++ }
++}
++
++/**
++ * bfq_entity_of - get an entity from a node.
++ * @node: the node field of the entity.
++ *
++ * Convert a node pointer to the relative entity. This is used only
++ * to simplify the logic of some functions and not as the generic
++ * conversion mechanism because, e.g., in the tree walking functions,
++ * the check for a %NULL value would be redundant.
++ */
++static inline struct bfq_entity *bfq_entity_of(struct rb_node *node)
++{
++ struct bfq_entity *entity = NULL;
++
++ if (node != NULL)
++ entity = rb_entry(node, struct bfq_entity, rb_node);
++
++ return entity;
++}
++
++/**
++ * bfq_extract - remove an entity from a tree.
++ * @root: the tree root.
++ * @entity: the entity to remove.
++ */
++static inline void bfq_extract(struct rb_root *root,
++ struct bfq_entity *entity)
++{
++ BUG_ON(entity->tree != root);
++
++ entity->tree = NULL;
++ rb_erase(&entity->rb_node, root);
++}
++
++/**
++ * bfq_idle_extract - extract an entity from the idle tree.
++ * @st: the service tree of the owning @entity.
++ * @entity: the entity being removed.
++ */
++static void bfq_idle_extract(struct bfq_service_tree *st,
++ struct bfq_entity *entity)
++{
++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
++ struct rb_node *next;
++
++ BUG_ON(entity->tree != &st->idle);
++
++ if (entity == st->first_idle) {
++ next = rb_next(&entity->rb_node);
++ st->first_idle = bfq_entity_of(next);
++ }
++
++ if (entity == st->last_idle) {
++ next = rb_prev(&entity->rb_node);
++ st->last_idle = bfq_entity_of(next);
++ }
++
++ bfq_extract(&st->idle, entity);
++
++ if (bfqq != NULL)
++ list_del(&bfqq->bfqq_list);
++}
++
++/**
++ * bfq_insert - generic tree insertion.
++ * @root: tree root.
++ * @entity: entity to insert.
++ *
++ * This is used for the idle and the active tree, since they are both
++ * ordered by finish time.
++ */
++static void bfq_insert(struct rb_root *root, struct bfq_entity *entity)
++{
++ struct bfq_entity *entry;
++ struct rb_node **node = &root->rb_node;
++ struct rb_node *parent = NULL;
++
++ BUG_ON(entity->tree != NULL);
++
++ while (*node != NULL) {
++ parent = *node;
++ entry = rb_entry(parent, struct bfq_entity, rb_node);
++
++ if (bfq_gt(entry->finish, entity->finish))
++ node = &parent->rb_left;
++ else
++ node = &parent->rb_right;
++ }
++
++ rb_link_node(&entity->rb_node, parent, node);
++ rb_insert_color(&entity->rb_node, root);
++
++ entity->tree = root;
++}
++
++/**
++ * bfq_update_min - update the min_start field of a entity.
++ * @entity: the entity to update.
++ * @node: one of its children.
++ *
++ * This function is called when @entity may store an invalid value for
++ * min_start due to updates to the active tree. The function assumes
++ * that the subtree rooted at @node (which may be its left or its right
++ * child) has a valid min_start value.
++ */
++static inline void bfq_update_min(struct bfq_entity *entity,
++ struct rb_node *node)
++{
++ struct bfq_entity *child;
++
++ if (node != NULL) {
++ child = rb_entry(node, struct bfq_entity, rb_node);
++ if (bfq_gt(entity->min_start, child->min_start))
++ entity->min_start = child->min_start;
++ }
++}
++
++/**
++ * bfq_update_active_node - recalculate min_start.
++ * @node: the node to update.
++ *
++ * @node may have changed position or one of its children may have moved,
++ * this function updates its min_start value. The left and right subtrees
++ * are assumed to hold a correct min_start value.
++ */
++static inline void bfq_update_active_node(struct rb_node *node)
++{
++ struct bfq_entity *entity = rb_entry(node, struct bfq_entity, rb_node);
++
++ entity->min_start = entity->start;
++ bfq_update_min(entity, node->rb_right);
++ bfq_update_min(entity, node->rb_left);
++}
++
++/**
++ * bfq_update_active_tree - update min_start for the whole active tree.
++ * @node: the starting node.
++ *
++ * @node must be the deepest modified node after an update. This function
++ * updates its min_start using the values held by its children, assuming
++ * that they did not change, and then updates all the nodes that may have
++ * changed in the path to the root. The only nodes that may have changed
++ * are the ones in the path or their siblings.
++ */
++static void bfq_update_active_tree(struct rb_node *node)
++{
++ struct rb_node *parent;
++
++up:
++ bfq_update_active_node(node);
++
++ parent = rb_parent(node);
++ if (parent == NULL)
++ return;
++
++ if (node == parent->rb_left && parent->rb_right != NULL)
++ bfq_update_active_node(parent->rb_right);
++ else if (parent->rb_left != NULL)
++ bfq_update_active_node(parent->rb_left);
++
++ node = parent;
++ goto up;
++}
++
++/**
++ * bfq_active_insert - insert an entity in the active tree of its group/device.
++ * @st: the service tree of the entity.
++ * @entity: the entity being inserted.
++ *
++ * The active tree is ordered by finish time, but an extra key is kept
++ * per each node, containing the minimum value for the start times of
++ * its children (and the node itself), so it's possible to search for
++ * the eligible node with the lowest finish time in logarithmic time.
++ */
++static void bfq_active_insert(struct bfq_service_tree *st,
++ struct bfq_entity *entity)
++{
++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
++ struct rb_node *node = &entity->rb_node;
++
++ bfq_insert(&st->active, entity);
++
++ if (node->rb_left != NULL)
++ node = node->rb_left;
++ else if (node->rb_right != NULL)
++ node = node->rb_right;
++
++ bfq_update_active_tree(node);
++
++ if (bfqq != NULL)
++ list_add(&bfqq->bfqq_list, &bfqq->bfqd->active_list);
++}
++
++/**
++ * bfq_ioprio_to_weight - calc a weight from an ioprio.
++ * @ioprio: the ioprio value to convert.
++ */
++static unsigned short bfq_ioprio_to_weight(int ioprio)
++{
++ WARN_ON(ioprio < 0 || ioprio >= IOPRIO_BE_NR);
++ return IOPRIO_BE_NR - ioprio;
++}
++
++/**
++ * bfq_weight_to_ioprio - calc an ioprio from a weight.
++ * @weight: the weight value to convert.
++ *
++ * To preserve as mush as possible the old only-ioprio user interface,
++ * 0 is used as an escape ioprio value for weights (numerically) equal or
++ * larger than IOPRIO_BE_NR
++ */
++static unsigned short bfq_weight_to_ioprio(int weight)
++{
++ WARN_ON(weight < BFQ_MIN_WEIGHT || weight > BFQ_MAX_WEIGHT);
++ return IOPRIO_BE_NR - weight < 0 ? 0 : IOPRIO_BE_NR - weight;
++}
++
++static inline void bfq_get_entity(struct bfq_entity *entity)
++{
++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
++ struct bfq_sched_data *sd;
++
++ if (bfqq != NULL) {
++ sd = entity->sched_data;
++ atomic_inc(&bfqq->ref);
++ bfq_log_bfqq(bfqq->bfqd, bfqq, "get_entity: %p %d",
++ bfqq, atomic_read(&bfqq->ref));
++ }
++}
++
++/**
++ * bfq_find_deepest - find the deepest node that an extraction can modify.
++ * @node: the node being removed.
++ *
++ * Do the first step of an extraction in an rb tree, looking for the
++ * node that will replace @node, and returning the deepest node that
++ * the following modifications to the tree can touch. If @node is the
++ * last node in the tree return %NULL.
++ */
++static struct rb_node *bfq_find_deepest(struct rb_node *node)
++{
++ struct rb_node *deepest;
++
++ if (node->rb_right == NULL && node->rb_left == NULL)
++ deepest = rb_parent(node);
++ else if (node->rb_right == NULL)
++ deepest = node->rb_left;
++ else if (node->rb_left == NULL)
++ deepest = node->rb_right;
++ else {
++ deepest = rb_next(node);
++ if (deepest->rb_right != NULL)
++ deepest = deepest->rb_right;
++ else if (rb_parent(deepest) != node)
++ deepest = rb_parent(deepest);
++ }
++
++ return deepest;
++}
++
++/**
++ * bfq_active_extract - remove an entity from the active tree.
++ * @st: the service_tree containing the tree.
++ * @entity: the entity being removed.
++ */
++static void bfq_active_extract(struct bfq_service_tree *st,
++ struct bfq_entity *entity)
++{
++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
++ struct rb_node *node;
++
++ node = bfq_find_deepest(&entity->rb_node);
++ bfq_extract(&st->active, entity);
++
++ if (node != NULL)
++ bfq_update_active_tree(node);
++
++ if (bfqq != NULL)
++ list_del(&bfqq->bfqq_list);
++}
++
++/**
++ * bfq_idle_insert - insert an entity into the idle tree.
++ * @st: the service tree containing the tree.
++ * @entity: the entity to insert.
++ */
++static void bfq_idle_insert(struct bfq_service_tree *st,
++ struct bfq_entity *entity)
++{
++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
++ struct bfq_entity *first_idle = st->first_idle;
++ struct bfq_entity *last_idle = st->last_idle;
++
++ if (first_idle == NULL || bfq_gt(first_idle->finish, entity->finish))
++ st->first_idle = entity;
++ if (last_idle == NULL || bfq_gt(entity->finish, last_idle->finish))
++ st->last_idle = entity;
++
++ bfq_insert(&st->idle, entity);
++
++ if (bfqq != NULL)
++ list_add(&bfqq->bfqq_list, &bfqq->bfqd->idle_list);
++}
++
++/**
++ * bfq_forget_entity - remove an entity from the wfq trees.
++ * @st: the service tree.
++ * @entity: the entity being removed.
++ *
++ * Update the device status and forget everything about @entity, putting
++ * the device reference to it, if it is a queue. Entities belonging to
++ * groups are not refcounted.
++ */
++static void bfq_forget_entity(struct bfq_service_tree *st,
++ struct bfq_entity *entity)
++{
++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
++ struct bfq_sched_data *sd;
++
++ BUG_ON(!entity->on_st);
++
++ entity->on_st = 0;
++ st->wsum -= entity->weight;
++ if (bfqq != NULL) {
++ sd = entity->sched_data;
++ bfq_log_bfqq(bfqq->bfqd, bfqq, "forget_entity: %p %d",
++ bfqq, atomic_read(&bfqq->ref));
++ bfq_put_queue(bfqq);
++ }
++}
++
++/**
++ * bfq_put_idle_entity - release the idle tree ref of an entity.
++ * @st: service tree for the entity.
++ * @entity: the entity being released.
++ */
++static void bfq_put_idle_entity(struct bfq_service_tree *st,
++ struct bfq_entity *entity)
++{
++ bfq_idle_extract(st, entity);
++ bfq_forget_entity(st, entity);
++}
++
++/**
++ * bfq_forget_idle - update the idle tree if necessary.
++ * @st: the service tree to act upon.
++ *
++ * To preserve the global O(log N) complexity we only remove one entry here;
++ * as the idle tree will not grow indefinitely this can be done safely.
++ */
++static void bfq_forget_idle(struct bfq_service_tree *st)
++{
++ struct bfq_entity *first_idle = st->first_idle;
++ struct bfq_entity *last_idle = st->last_idle;
++
++ if (RB_EMPTY_ROOT(&st->active) && last_idle != NULL &&
++ !bfq_gt(last_idle->finish, st->vtime)) {
++ /*
++ * Forget the whole idle tree, increasing the vtime past
++ * the last finish time of idle entities.
++ */
++ st->vtime = last_idle->finish;
++ }
++
++ if (first_idle != NULL && !bfq_gt(first_idle->finish, st->vtime))
++ bfq_put_idle_entity(st, first_idle);
++}
++
++static struct bfq_service_tree *
++__bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
++ struct bfq_entity *entity)
++{
++ struct bfq_service_tree *new_st = old_st;
++
++ if (entity->ioprio_changed) {
++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
++
++ BUG_ON(old_st->wsum < entity->weight);
++ old_st->wsum -= entity->weight;
++
++ if (entity->new_weight != entity->orig_weight) {
++ entity->orig_weight = entity->new_weight;
++ entity->ioprio =
++ bfq_weight_to_ioprio(entity->orig_weight);
++ } else if (entity->new_ioprio != entity->ioprio) {
++ entity->ioprio = entity->new_ioprio;
++ entity->orig_weight =
++ bfq_ioprio_to_weight(entity->ioprio);
++ } else
++ entity->new_weight = entity->orig_weight =
++ bfq_ioprio_to_weight(entity->ioprio);
++
++ entity->ioprio_class = entity->new_ioprio_class;
++ entity->ioprio_changed = 0;
++
++ /*
++ * NOTE: here we may be changing the weight too early,
++ * this will cause unfairness. The correct approach
++ * would have required additional complexity to defer
++ * weight changes to the proper time instants (i.e.,
++ * when entity->finish <= old_st->vtime).
++ */
++ new_st = bfq_entity_service_tree(entity);
++ entity->weight = entity->orig_weight *
++ (bfqq != NULL ? bfqq->raising_coeff : 1);
++ new_st->wsum += entity->weight;
++
++ if (new_st != old_st)
++ entity->start = new_st->vtime;
++ }
++
++ return new_st;
++}
++
++/**
++ * bfq_bfqq_served - update the scheduler status after selection for service.
++ * @bfqq: the queue being served.
++ * @served: bytes to transfer.
++ *
++ * NOTE: this can be optimized, as the timestamps of upper level entities
++ * are synchronized every time a new bfqq is selected for service. By now,
++ * we keep it to better check consistency.
++ */
++static void bfq_bfqq_served(struct bfq_queue *bfqq, unsigned long served)
++{
++ struct bfq_entity *entity = &bfqq->entity;
++ struct bfq_service_tree *st;
++
++ for_each_entity(entity) {
++ st = bfq_entity_service_tree(entity);
++
++ entity->service += served;
++ BUG_ON(entity->service > entity->budget);
++ BUG_ON(st->wsum == 0);
++
++ st->vtime += bfq_delta(served, st->wsum);
++ bfq_forget_idle(st);
++ }
++ bfq_log_bfqq(bfqq->bfqd, bfqq, "bfqq_served %lu secs", served);
++}
++
++/**
++ * bfq_bfqq_charge_full_budget - set the service to the entity budget.
++ * @bfqq: the queue that needs a service update.
++ *
++ * When it's not possible to be fair in the service domain, because
++ * a queue is not consuming its budget fast enough (the meaning of
++ * fast depends on the timeout parameter), we charge it a full
++ * budget. In this way we should obtain a sort of time-domain
++ * fairness among all the seeky/slow queues.
++ */
++static inline void bfq_bfqq_charge_full_budget(struct bfq_queue *bfqq)
++{
++ struct bfq_entity *entity = &bfqq->entity;
++
++ bfq_log_bfqq(bfqq->bfqd, bfqq, "charge_full_budget");
++
++ bfq_bfqq_served(bfqq, entity->budget - entity->service);
++}
++
++/**
++ * __bfq_activate_entity - activate an entity.
++ * @entity: the entity being activated.
++ *
++ * Called whenever an entity is activated, i.e., it is not active and one
++ * of its children receives a new request, or has to be reactivated due to
++ * budget exhaustion. It uses the current budget of the entity (and the
++ * service received if @entity is active) of the queue to calculate its
++ * timestamps.
++ */
++static void __bfq_activate_entity(struct bfq_entity *entity)
++{
++ struct bfq_sched_data *sd = entity->sched_data;
++ struct bfq_service_tree *st = bfq_entity_service_tree(entity);
++
++ if (entity == sd->active_entity) {
++ BUG_ON(entity->tree != NULL);
++ /*
++ * If we are requeueing the current entity we have
++ * to take care of not charging to it service it has
++ * not received.
++ */
++ bfq_calc_finish(entity, entity->service);
++ entity->start = entity->finish;
++ sd->active_entity = NULL;
++ } else if (entity->tree == &st->active) {
++ /*
++ * Requeueing an entity due to a change of some
++ * next_active entity below it. We reuse the old
++ * start time.
++ */
++ bfq_active_extract(st, entity);
++ } else if (entity->tree == &st->idle) {
++ /*
++ * Must be on the idle tree, bfq_idle_extract() will
++ * check for that.
++ */
++ bfq_idle_extract(st, entity);
++ entity->start = bfq_gt(st->vtime, entity->finish) ?
++ st->vtime : entity->finish;
++ } else {
++ /*
++ * The finish time of the entity may be invalid, and
++ * it is in the past for sure, otherwise the queue
++ * would have been on the idle tree.
++ */
++ entity->start = st->vtime;
++ st->wsum += entity->weight;
++ bfq_get_entity(entity);
++
++ BUG_ON(entity->on_st);
++ entity->on_st = 1;
++ }
++
++ st = __bfq_entity_update_weight_prio(st, entity);
++ bfq_calc_finish(entity, entity->budget);
++ bfq_active_insert(st, entity);
++}
++
++/**
++ * bfq_activate_entity - activate an entity and its ancestors if necessary.
++ * @entity: the entity to activate.
++ *
++ * Activate @entity and all the entities on the path from it to the root.
++ */
++static void bfq_activate_entity(struct bfq_entity *entity)
++{
++ struct bfq_sched_data *sd;
++
++ for_each_entity(entity) {
++ __bfq_activate_entity(entity);
++
++ sd = entity->sched_data;
++ if (!bfq_update_next_active(sd))
++ /*
++ * No need to propagate the activation to the
++ * upper entities, as they will be updated when
++ * the active entity is rescheduled.
++ */
++ break;
++ }
++}
++
++/**
++ * __bfq_deactivate_entity - deactivate an entity from its service tree.
++ * @entity: the entity to deactivate.
++ * @requeue: if false, the entity will not be put into the idle tree.
++ *
++ * Deactivate an entity, independently from its previous state. If the
++ * entity was not on a service tree just return, otherwise if it is on
++ * any scheduler tree, extract it from that tree, and if necessary
++ * and if the caller did not specify @requeue, put it on the idle tree.
++ *
++ * Return %1 if the caller should update the entity hierarchy, i.e.,
++ * if the entity was under service or if it was the next_active for
++ * its sched_data; return %0 otherwise.
++ */
++static int __bfq_deactivate_entity(struct bfq_entity *entity, int requeue)
++{
++ struct bfq_sched_data *sd = entity->sched_data;
++ struct bfq_service_tree *st = bfq_entity_service_tree(entity);
++ int was_active = entity == sd->active_entity;
++ int ret = 0;
++
++ if (!entity->on_st)
++ return 0;
++
++ BUG_ON(was_active && entity->tree != NULL);
++
++ if (was_active) {
++ bfq_calc_finish(entity, entity->service);
++ sd->active_entity = NULL;
++ } else if (entity->tree == &st->active)
++ bfq_active_extract(st, entity);
++ else if (entity->tree == &st->idle)
++ bfq_idle_extract(st, entity);
++ else if (entity->tree != NULL)
++ BUG();
++
++ if (was_active || sd->next_active == entity)
++ ret = bfq_update_next_active(sd);
++
++ if (!requeue || !bfq_gt(entity->finish, st->vtime))
++ bfq_forget_entity(st, entity);
++ else
++ bfq_idle_insert(st, entity);
++
++ BUG_ON(sd->active_entity == entity);
++ BUG_ON(sd->next_active == entity);
++
++ return ret;
++}
++
++/**
++ * bfq_deactivate_entity - deactivate an entity.
++ * @entity: the entity to deactivate.
++ * @requeue: true if the entity can be put on the idle tree
++ */
++static void bfq_deactivate_entity(struct bfq_entity *entity, int requeue)
++{
++ struct bfq_sched_data *sd;
++ struct bfq_entity *parent;
++
++ for_each_entity_safe(entity, parent) {
++ sd = entity->sched_data;
++
++ if (!__bfq_deactivate_entity(entity, requeue))
++ /*
++ * The parent entity is still backlogged, and
++ * we don't need to update it as it is still
++ * under service.
++ */
++ break;
++
++ if (sd->next_active != NULL)
++ /*
++ * The parent entity is still backlogged and
++ * the budgets on the path towards the root
++ * need to be updated.
++ */
++ goto update;
++
++ /*
++ * If we reach there the parent is no more backlogged and
++ * we want to propagate the dequeue upwards.
++ */
++ requeue = 1;
++ }
++
++ return;
++
++update:
++ entity = parent;
++ for_each_entity(entity) {
++ __bfq_activate_entity(entity);
++
++ sd = entity->sched_data;
++ if (!bfq_update_next_active(sd))
++ break;
++ }
++}
++
++/**
++ * bfq_update_vtime - update vtime if necessary.
++ * @st: the service tree to act upon.
++ *
++ * If necessary update the service tree vtime to have at least one
++ * eligible entity, skipping to its start time. Assumes that the
++ * active tree of the device is not empty.
++ *
++ * NOTE: this hierarchical implementation updates vtimes quite often,
++ * we may end up with reactivated tasks getting timestamps after a
++ * vtime skip done because we needed a ->first_active entity on some
++ * intermediate node.
++ */
++static void bfq_update_vtime(struct bfq_service_tree *st)
++{
++ struct bfq_entity *entry;
++ struct rb_node *node = st->active.rb_node;
++
++ entry = rb_entry(node, struct bfq_entity, rb_node);
++ if (bfq_gt(entry->min_start, st->vtime)) {
++ st->vtime = entry->min_start;
++ bfq_forget_idle(st);
++ }
++}
++
++/**
++ * bfq_first_active - find the eligible entity with the smallest finish time
++ * @st: the service tree to select from.
++ *
++ * This function searches the first schedulable entity, starting from the
++ * root of the tree and going on the left every time on this side there is
++ * a subtree with at least one eligible (start >= vtime) entity. The path
++ * on the right is followed only if a) the left subtree contains no eligible
++ * entities and b) no eligible entity has been found yet.
++ */
++static struct bfq_entity *bfq_first_active_entity(struct bfq_service_tree *st)
++{
++ struct bfq_entity *entry, *first = NULL;
++ struct rb_node *node = st->active.rb_node;
++
++ while (node != NULL) {
++ entry = rb_entry(node, struct bfq_entity, rb_node);
++left:
++ if (!bfq_gt(entry->start, st->vtime))
++ first = entry;
++
++ BUG_ON(bfq_gt(entry->min_start, st->vtime));
++
++ if (node->rb_left != NULL) {
++ entry = rb_entry(node->rb_left,
++ struct bfq_entity, rb_node);
++ if (!bfq_gt(entry->min_start, st->vtime)) {
++ node = node->rb_left;
++ goto left;
++ }
++ }
++ if (first != NULL)
++ break;
++ node = node->rb_right;
++ }
++
++ BUG_ON(first == NULL && !RB_EMPTY_ROOT(&st->active));
++ return first;
++}
++
++/**
++ * __bfq_lookup_next_entity - return the first eligible entity in @st.
++ * @st: the service tree.
++ *
++ * Update the virtual time in @st and return the first eligible entity
++ * it contains.
++ */
++static struct bfq_entity *__bfq_lookup_next_entity(struct bfq_service_tree *st,
++ bool force)
++{
++ struct bfq_entity *entity, *new_next_active = NULL;
++
++ if (RB_EMPTY_ROOT(&st->active))
++ return NULL;
++
++ bfq_update_vtime(st);
++ entity = bfq_first_active_entity(st);
++ BUG_ON(bfq_gt(entity->start, st->vtime));
++
++ /*
++ * If the chosen entity does not match with the sched_data's
++ * next_active and we are forcedly serving the IDLE priority
++ * class tree, bubble up budget update.
++ */
++ if (unlikely(force && entity != entity->sched_data->next_active)) {
++ new_next_active = entity;
++ for_each_entity(new_next_active)
++ bfq_update_budget(new_next_active);
++ }
++
++ return entity;
++}
++
++/**
++ * bfq_lookup_next_entity - return the first eligible entity in @sd.
++ * @sd: the sched_data.
++ * @extract: if true the returned entity will be also extracted from @sd.
++ *
++ * NOTE: since we cache the next_active entity at each level of the
++ * hierarchy, the complexity of the lookup can be decreased with
++ * absolutely no effort just returning the cached next_active value;
++ * we prefer to do full lookups to test the consistency of * the data
++ * structures.
++ */
++static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd,
++ int extract,
++ struct bfq_data *bfqd)
++{
++ struct bfq_service_tree *st = sd->service_tree;
++ struct bfq_entity *entity;
++ int i = 0;
++
++ BUG_ON(sd->active_entity != NULL);
++
++ if (bfqd != NULL &&
++ jiffies - bfqd->bfq_class_idle_last_service > BFQ_CL_IDLE_TIMEOUT) {
++ entity = __bfq_lookup_next_entity(st + BFQ_IOPRIO_CLASSES - 1,
++ true);
++ if (entity != NULL) {
++ i = BFQ_IOPRIO_CLASSES - 1;
++ bfqd->bfq_class_idle_last_service = jiffies;
++ sd->next_active = entity;
++ }
++ }
++ for (; i < BFQ_IOPRIO_CLASSES; i++) {
++ entity = __bfq_lookup_next_entity(st + i, false);
++ if (entity != NULL) {
++ if (extract) {
++ bfq_check_next_active(sd, entity);
++ bfq_active_extract(st + i, entity);
++ sd->active_entity = entity;
++ sd->next_active = NULL;
++ }
++ break;
++ }
++ }
++
++ return entity;
++}
++
++/*
++ * Get next queue for service.
++ */
++static struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd)
++{
++ struct bfq_entity *entity = NULL;
++ struct bfq_sched_data *sd;
++ struct bfq_queue *bfqq;
++
++ BUG_ON(bfqd->in_service_queue != NULL);
++
++ if (bfqd->busy_queues == 0)
++ return NULL;
++
++ sd = &bfqd->root_group->sched_data;
++ for (; sd != NULL; sd = entity->my_sched_data) {
++ entity = bfq_lookup_next_entity(sd, 1, bfqd);
++ BUG_ON(entity == NULL);
++ entity->service = 0;
++ }
++
++ bfqq = bfq_entity_to_bfqq(entity);
++ BUG_ON(bfqq == NULL);
++
++ return bfqq;
++}
++
++/*
++ * Forced extraction of the given queue.
++ */
++static void bfq_get_next_queue_forced(struct bfq_data *bfqd,
++ struct bfq_queue *bfqq)
++{
++ struct bfq_entity *entity;
++ struct bfq_sched_data *sd;
++
++ BUG_ON(bfqd->in_service_queue != NULL);
++
++ entity = &bfqq->entity;
++ /*
++ * Bubble up extraction/update from the leaf to the root.
++ */
++ for_each_entity(entity) {
++ sd = entity->sched_data;
++ bfq_update_budget(entity);
++ bfq_update_vtime(bfq_entity_service_tree(entity));
++ bfq_active_extract(bfq_entity_service_tree(entity), entity);
++ sd->active_entity = entity;
++ sd->next_active = NULL;
++ entity->service = 0;
++ }
++
++ return;
++}
++
++static void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
++{
++ if (bfqd->in_service_bic != NULL) {
++ put_io_context(bfqd->in_service_bic->icq.ioc);
++ bfqd->in_service_bic = NULL;
++ }
++
++ bfqd->in_service_queue = NULL;
++ del_timer(&bfqd->idle_slice_timer);
++}
++
++static void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
++ int requeue)
++{
++ struct bfq_entity *entity = &bfqq->entity;
++
++ if (bfqq == bfqd->in_service_queue)
++ __bfq_bfqd_reset_in_service(bfqd);
++
++ bfq_deactivate_entity(entity, requeue);
++}
++
++static void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
++{
++ struct bfq_entity *entity = &bfqq->entity;
++
++ bfq_activate_entity(entity);
++}
++
++/*
++ * Called when the bfqq no longer has requests pending, remove it from
++ * the service tree.
++ */
++static void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
++ int requeue)
++{
++ BUG_ON(!bfq_bfqq_busy(bfqq));
++ BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list));
++
++ bfq_log_bfqq(bfqd, bfqq, "del from busy");
++
++ bfq_clear_bfqq_busy(bfqq);
++
++ BUG_ON(bfqd->busy_queues == 0);
++ bfqd->busy_queues--;
++ if (bfqq->raising_coeff > 1)
++ bfqd->raised_busy_queues--;
++
++ bfq_deactivate_bfqq(bfqd, bfqq, requeue);
++}
++
++/*
++ * Called when an inactive queue receives a new request.
++ */
++static void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq)
++{
++ BUG_ON(bfq_bfqq_busy(bfqq));
++ BUG_ON(bfqq == bfqd->in_service_queue);
++
++ bfq_log_bfqq(bfqd, bfqq, "add to busy");
++
++ bfq_activate_bfqq(bfqd, bfqq);
++
++ bfq_mark_bfqq_busy(bfqq);
++ bfqd->busy_queues++;
++ if (bfqq->raising_coeff > 1)
++ bfqd->raised_busy_queues++;
++}
+diff --git a/block/bfq.h b/block/bfq.h
+new file mode 100644
+index 0000000..78da7d2
+--- /dev/null
++++ b/block/bfq.h
+@@ -0,0 +1,612 @@
++/*
++ * BFQ-v7 for 3.10.0: data structures and common functions prototypes.
++ *
++ * Based on ideas and code from CFQ:
++ * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
++ *
++ * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
++ * Paolo Valente <paolo.valente@unimore.it>
++ *
++ * Copyright (C) 2010 Paolo Valente <paolo.valente@unimore.it>
++ */
++
++#ifndef _BFQ_H
++#define _BFQ_H
++
++#include <linux/blktrace_api.h>
++#include <linux/hrtimer.h>
++#include <linux/ioprio.h>
++#include <linux/rbtree.h>
++
++#define BFQ_IOPRIO_CLASSES 3
++#define BFQ_CL_IDLE_TIMEOUT (HZ/5)
++
++#define BFQ_MIN_WEIGHT 1
++#define BFQ_MAX_WEIGHT 1000
++
++#define BFQ_DEFAULT_GRP_WEIGHT 10
++#define BFQ_DEFAULT_GRP_IOPRIO 0
++#define BFQ_DEFAULT_GRP_CLASS IOPRIO_CLASS_BE
++
++struct bfq_entity;
++
++/**
++ * struct bfq_service_tree - per ioprio_class service tree.
++ * @active: tree for active entities (i.e., those backlogged).
++ * @idle: tree for idle entities (i.e., those not backlogged, with V <= F_i).
++ * @first_idle: idle entity with minimum F_i.
++ * @last_idle: idle entity with maximum F_i.
++ * @vtime: scheduler virtual time.
++ * @wsum: scheduler weight sum; active and idle entities contribute to it.
++ *
++ * Each service tree represents a B-WF2Q+ scheduler on its own. Each
++ * ioprio_class has its own independent scheduler, and so its own
++ * bfq_service_tree. All the fields are protected by the queue lock
++ * of the containing bfqd.
++ */
++struct bfq_service_tree {
++ struct rb_root active;
++ struct rb_root idle;
++
++ struct bfq_entity *first_idle;
++ struct bfq_entity *last_idle;
++
++ u64 vtime;
++ unsigned long wsum;
++};
++
++/**
++ * struct bfq_sched_data - multi-class scheduler.
++ * @active_entity: entity under service.
++ * @next_active: head-of-the-line entity in the scheduler.
++ * @service_tree: array of service trees, one per ioprio_class.
++ *
++ * bfq_sched_data is the basic scheduler queue. It supports three
++ * ioprio_classes, and can be used either as a toplevel queue or as
++ * an intermediate queue on a hierarchical setup.
++ * @next_active points to the active entity of the sched_data service
++ * trees that will be scheduled next.
++ *
++ * The supported ioprio_classes are the same as in CFQ, in descending
++ * priority order, IOPRIO_CLASS_RT, IOPRIO_CLASS_BE, IOPRIO_CLASS_IDLE.
++ * Requests from higher priority queues are served before all the
++ * requests from lower priority queues; among requests of the same
++ * queue requests are served according to B-WF2Q+.
++ * All the fields are protected by the queue lock of the containing bfqd.
++ */
++struct bfq_sched_data {
++ struct bfq_entity *active_entity;
++ struct bfq_entity *next_active;
++ struct bfq_service_tree service_tree[BFQ_IOPRIO_CLASSES];
++};
++
++/**
++ * struct bfq_entity - schedulable entity.
++ * @rb_node: service_tree member.
++ * @on_st: flag, true if the entity is on a tree (either the active or
++ * the idle one of its service_tree).
++ * @finish: B-WF2Q+ finish timestamp (aka F_i).
++ * @start: B-WF2Q+ start timestamp (aka S_i).
++ * @tree: tree the entity is enqueued into; %NULL if not on a tree.
++ * @min_start: minimum start time of the (active) subtree rooted at
++ * this entity; used for O(log N) lookups into active trees.
++ * @service: service received during the last round of service.
++ * @budget: budget used to calculate F_i; F_i = S_i + @budget / @weight.
++ * @weight: weight of the queue
++ * @parent: parent entity, for hierarchical scheduling.
++ * @my_sched_data: for non-leaf nodes in the cgroup hierarchy, the
++ * associated scheduler queue, %NULL on leaf nodes.
++ * @sched_data: the scheduler queue this entity belongs to.
++ * @ioprio: the ioprio in use.
++ * @new_weight: when a weight change is requested, the new weight value.
++ * @orig_weight: original weight, used to implement weight boosting
++ * @new_ioprio: when an ioprio change is requested, the new ioprio value.
++ * @ioprio_class: the ioprio_class in use.
++ * @new_ioprio_class: when an ioprio_class change is requested, the new
++ * ioprio_class value.
++ * @ioprio_changed: flag, true when the user requested a weight, ioprio or
++ * ioprio_class change.
++ *
++ * A bfq_entity is used to represent either a bfq_queue (leaf node in the
++ * cgroup hierarchy) or a bfq_group into the upper level scheduler. Each
++ * entity belongs to the sched_data of the parent group in the cgroup
++ * hierarchy. Non-leaf entities have also their own sched_data, stored
++ * in @my_sched_data.
++ *
++ * Each entity stores independently its priority values; this would
++ * allow different weights on different devices, but this
++ * functionality is not exported to userspace by now. Priorities and
++ * weights are updated lazily, first storing the new values into the
++ * new_* fields, then setting the @ioprio_changed flag. As soon as
++ * there is a transition in the entity state that allows the priority
++ * update to take place the effective and the requested priority
++ * values are synchronized.
++ *
++ * Unless cgroups are used, the weight value is calculated from the
++ * ioprio to export the same interface as CFQ. When dealing with
++ * ``well-behaved'' queues (i.e., queues that do not spend too much
++ * time to consume their budget and have true sequential behavior, and
++ * when there are no external factors breaking anticipation) the
++ * relative weights at each level of the cgroups hierarchy should be
++ * guaranteed. All the fields are protected by the queue lock of the
++ * containing bfqd.
++ */
++struct bfq_entity {
++ struct rb_node rb_node;
++
++ int on_st;
++
++ u64 finish;
++ u64 start;
++
++ struct rb_root *tree;
++
++ u64 min_start;
++
++ unsigned long service, budget;
++ unsigned short weight, new_weight;
++ unsigned short orig_weight;
++
++ struct bfq_entity *parent;
++
++ struct bfq_sched_data *my_sched_data;
++ struct bfq_sched_data *sched_data;
++
++ unsigned short ioprio, new_ioprio;
++ unsigned short ioprio_class, new_ioprio_class;
++
++ int ioprio_changed;
++};
++
++struct bfq_group;
++
++/**
++ * struct bfq_queue - leaf schedulable entity.
++ * @ref: reference counter.
++ * @bfqd: parent bfq_data.
++ * @new_bfqq: shared bfq_queue if queue is cooperating with
++ * one or more other queues.
++ * @pos_node: request-position tree member (see bfq_data's @rq_pos_tree).
++ * @pos_root: request-position tree root (see bfq_data's @rq_pos_tree).
++ * @sort_list: sorted list of pending requests.
++ * @next_rq: if fifo isn't expired, next request to serve.
++ * @queued: nr of requests queued in @sort_list.
++ * @allocated: currently allocated requests.
++ * @meta_pending: pending metadata requests.
++ * @fifo: fifo list of requests in sort_list.
++ * @entity: entity representing this queue in the scheduler.
++ * @max_budget: maximum budget allowed from the feedback mechanism.
++ * @budget_timeout: budget expiration (in jiffies).
++ * @dispatched: number of requests on the dispatch list or inside driver.
++ * @org_ioprio: saved ioprio during boosted periods.
++ * @flags: status flags.
++ * @bfqq_list: node for active/idle bfqq list inside our bfqd.
++ * @seek_samples: number of seeks sampled
++ * @seek_total: sum of the distances of the seeks sampled
++ * @seek_mean: mean seek distance
++ * @last_request_pos: position of the last request enqueued
++ * @pid: pid of the process owning the queue, used for logging purposes.
++ * @last_rais_start_time: last (idle -> weight-raised) transition attempt
++ * @raising_cur_max_time: current max raising time for this queue
++ * @last_idle_bklogged: time of the last transition of the @bfq_queue from
++ * idle to backlogged
++ * @service_from_backlogged: cumulative service received from the @bfq_queue
++ * since the last transition from idle to backlogged
++ *
++ * A bfq_queue is a leaf request queue; it can be associated to an io_context
++ * or more (if it is an async one). @cgroup holds a reference to the
++ * cgroup, to be sure that it does not disappear while a bfqq still
++ * references it (mostly to avoid races between request issuing and task
++ * migration followed by cgroup distruction).
++ * All the fields are protected by the queue lock of the containing bfqd.
++ */
++struct bfq_queue {
++ atomic_t ref;
++ struct bfq_data *bfqd;
++
++ /* fields for cooperating queues handling */
++ struct bfq_queue *new_bfqq;
++ struct rb_node pos_node;
++ struct rb_root *pos_root;
++
++ struct rb_root sort_list;
++ struct request *next_rq;
++ int queued[2];
++ int allocated[2];
++ int meta_pending;
++ struct list_head fifo;
++
++ struct bfq_entity entity;
++
++ unsigned long max_budget;
++ unsigned long budget_timeout;
++
++ int dispatched;
++
++ unsigned short org_ioprio;
++
++ unsigned int flags;
++
++ struct list_head bfqq_list;
++
++ unsigned int seek_samples;
++ u64 seek_total;
++ sector_t seek_mean;
++ sector_t last_request_pos;
++
++ pid_t pid;
++
++ /* weight-raising fields */
++ unsigned int raising_cur_max_time;
++ unsigned long soft_rt_next_start;
++ u64 last_rais_start_finish;
++ unsigned int raising_coeff;
++ u64 last_idle_bklogged;
++ unsigned long service_from_backlogged;
++};
++
++/**
++ * struct bfq_ttime - per process thinktime stats.
++ * @ttime_total: total process thinktime
++ * @ttime_samples: number of thinktime samples
++ * @ttime_mean: average process thinktime
++ */
++struct bfq_ttime {
++ unsigned long last_end_request;
++
++ unsigned long ttime_total;
++ unsigned long ttime_samples;
++ unsigned long ttime_mean;
++};
++
++/**
++ * struct bfq_io_cq - per (request_queue, io_context) structure.
++ * @icq: associated io_cq structure
++ * @bfqq: array of two process queues, the sync and the async
++ * @ttime: associated @bfq_ttime struct
++ */
++struct bfq_io_cq {
++ struct io_cq icq; /* must be the first member */
++ struct bfq_queue *bfqq[2];
++ struct bfq_ttime ttime;
++ int ioprio;
++};
++
++/**
++ * struct bfq_data - per device data structure.
++ * @queue: request queue for the managed device.
++ * @root_group: root bfq_group for the device.
++ * @rq_pos_tree: rbtree sorted by next_request position,
++ * used when determining if two or more queues
++ * have interleaving requests (see bfq_close_cooperator).
++ * @busy_queues: number of bfq_queues containing requests (including the
++ * queue under service, even if it is idling).
++ * @raised_busy_queues: number of weight-raised busy bfq_queues.
++ * @queued: number of queued requests.
++ * @rq_in_driver: number of requests dispatched and waiting for completion.
++ * @sync_flight: number of sync requests in the driver.
++ * @max_rq_in_driver: max number of reqs in driver in the last @hw_tag_samples
++ * completed requests .
++ * @hw_tag_samples: nr of samples used to calculate hw_tag.
++ * @hw_tag: flag set to one if the driver is showing a queueing behavior.
++ * @budgets_assigned: number of budgets assigned.
++ * @idle_slice_timer: timer set when idling for the next sequential request
++ * from the queue under service.
++ * @unplug_work: delayed work to restart dispatching on the request queue.
++ * @in_service_queue: bfq_queue under service.
++ * @in_service_bic: bfq_io_cq (bic) associated with the @in_service_queue.
++ * @last_position: on-disk position of the last served request.
++ * @last_budget_start: beginning of the last budget.
++ * @last_idling_start: beginning of the last idle slice.
++ * @peak_rate: peak transfer rate observed for a budget.
++ * @peak_rate_samples: number of samples used to calculate @peak_rate.
++ * @bfq_max_budget: maximum budget allotted to a bfq_queue before rescheduling.
++ * @group_list: list of all the bfq_groups active on the device.
++ * @active_list: list of all the bfq_queues active on the device.
++ * @idle_list: list of all the bfq_queues idle on the device.
++ * @bfq_quantum: max number of requests dispatched per dispatch round.
++ * @bfq_fifo_expire: timeout for async/sync requests; when it expires
++ * requests are served in fifo order.
++ * @bfq_back_penalty: weight of backward seeks wrt forward ones.
++ * @bfq_back_max: maximum allowed backward seek.
++ * @bfq_slice_idle: maximum idling time.
++ * @bfq_user_max_budget: user-configured max budget value (0 for auto-tuning).
++ * @bfq_max_budget_async_rq: maximum budget (in nr of requests) allotted to
++ * async queues.
++ * @bfq_timeout: timeout for bfq_queues to consume their budget; used to
++ * to prevent seeky queues to impose long latencies to well
++ * behaved ones (this also implies that seeky queues cannot
++ * receive guarantees in the service domain; after a timeout
++ * they are charged for the whole allocated budget, to try
++ * to preserve a behavior reasonably fair among them, but
++ * without service-domain guarantees).
++ * @bfq_raising_coeff: Maximum factor by which the weight of a boosted
++ * queue is multiplied
++ * @bfq_raising_max_time: maximum duration of a weight-raising period (jiffies)
++ * @bfq_raising_rt_max_time: maximum duration for soft real-time processes
++ * @bfq_raising_min_idle_time: minimum idle period after which weight-raising
++ * may be reactivated for a queue (in jiffies)
++ * @bfq_raising_min_inter_arr_async: minimum period between request arrivals
++ * after which weight-raising may be
++ * reactivated for an already busy queue
++ * (in jiffies)
++ * @bfq_raising_max_softrt_rate: max service-rate for a soft real-time queue,
++ * sectors per seconds
++ * @RT_prod: cached value of the product R*T used for computing the maximum
++ * duration of the weight raising automatically
++ * @oom_bfqq: fallback dummy bfqq for extreme OOM conditions
++ *
++ * All the fields are protected by the @queue lock.
++ */
++struct bfq_data {
++ struct request_queue *queue;
++
++ struct bfq_group *root_group;
++
++ struct rb_root rq_pos_tree;
++
++ int busy_queues;
++ int raised_busy_queues;
++ int queued;
++ int rq_in_driver;
++ int sync_flight;
++
++ int max_rq_in_driver;
++ int hw_tag_samples;
++ int hw_tag;
++
++ int budgets_assigned;
++
++ struct timer_list idle_slice_timer;
++ struct work_struct unplug_work;
++
++ struct bfq_queue *in_service_queue;
++ struct bfq_io_cq *in_service_bic;
++
++ sector_t last_position;
++
++ ktime_t last_budget_start;
++ ktime_t last_idling_start;
++ int peak_rate_samples;
++ u64 peak_rate;
++ unsigned long bfq_max_budget;
++
++ struct hlist_head group_list;
++ struct list_head active_list;
++ struct list_head idle_list;
++
++ unsigned int bfq_quantum;
++ unsigned int bfq_fifo_expire[2];
++ unsigned int bfq_back_penalty;
++ unsigned int bfq_back_max;
++ unsigned int bfq_slice_idle;
++ u64 bfq_class_idle_last_service;
++
++ unsigned int bfq_user_max_budget;
++ unsigned int bfq_max_budget_async_rq;
++ unsigned int bfq_timeout[2];
++
++ bool low_latency;
++
++ /* parameters of the low_latency heuristics */
++ unsigned int bfq_raising_coeff;
++ unsigned int bfq_raising_max_time;
++ unsigned int bfq_raising_rt_max_time;
++ unsigned int bfq_raising_min_idle_time;
++ unsigned long bfq_raising_min_inter_arr_async;
++ unsigned int bfq_raising_max_softrt_rate;
++ u64 RT_prod;
++
++ struct bfq_queue oom_bfqq;
++};
++
++enum bfqq_state_flags {
++ BFQ_BFQQ_FLAG_busy = 0, /* has requests or is under service */
++ BFQ_BFQQ_FLAG_wait_request, /* waiting for a request */
++ BFQ_BFQQ_FLAG_must_alloc, /* must be allowed rq alloc */
++ BFQ_BFQQ_FLAG_fifo_expire, /* FIFO checked in this slice */
++ BFQ_BFQQ_FLAG_idle_window, /* slice idling enabled */
++ BFQ_BFQQ_FLAG_prio_changed, /* task priority has changed */
++ BFQ_BFQQ_FLAG_sync, /* synchronous queue */
++ BFQ_BFQQ_FLAG_budget_new, /* no completion with this budget */
++ BFQ_BFQQ_FLAG_coop, /* bfqq is shared */
++ BFQ_BFQQ_FLAG_split_coop, /* shared bfqq will be splitted */
++ BFQ_BFQQ_FLAG_softrt_update, /* needs softrt-next-start update */
++};
++
++#define BFQ_BFQQ_FNS(name) \
++static inline void bfq_mark_bfqq_##name(struct bfq_queue *bfqq) \
++{ \
++ (bfqq)->flags |= (1 << BFQ_BFQQ_FLAG_##name); \
++} \
++static inline void bfq_clear_bfqq_##name(struct bfq_queue *bfqq) \
++{ \
++ (bfqq)->flags &= ~(1 << BFQ_BFQQ_FLAG_##name); \
++} \
++static inline int bfq_bfqq_##name(const struct bfq_queue *bfqq) \
++{ \
++ return ((bfqq)->flags & (1 << BFQ_BFQQ_FLAG_##name)) != 0; \
++}
++
++BFQ_BFQQ_FNS(busy);
++BFQ_BFQQ_FNS(wait_request);
++BFQ_BFQQ_FNS(must_alloc);
++BFQ_BFQQ_FNS(fifo_expire);
++BFQ_BFQQ_FNS(idle_window);
++BFQ_BFQQ_FNS(prio_changed);
++BFQ_BFQQ_FNS(sync);
++BFQ_BFQQ_FNS(budget_new);
++BFQ_BFQQ_FNS(coop);
++BFQ_BFQQ_FNS(split_coop);
++BFQ_BFQQ_FNS(softrt_update);
++#undef BFQ_BFQQ_FNS
++
++/* Logging facilities. */
++#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) \
++ blk_add_trace_msg((bfqd)->queue, "bfq%d " fmt, (bfqq)->pid, ##args)
++
++#define bfq_log(bfqd, fmt, args...) \
++ blk_add_trace_msg((bfqd)->queue, "bfq " fmt, ##args)
++
++/* Expiration reasons. */
++enum bfqq_expiration {
++ BFQ_BFQQ_TOO_IDLE = 0, /* queue has been idling for too long */
++ BFQ_BFQQ_BUDGET_TIMEOUT, /* budget took too long to be used */
++ BFQ_BFQQ_BUDGET_EXHAUSTED, /* budget consumed */
++ BFQ_BFQQ_NO_MORE_REQUESTS, /* the queue has no more requests */
++};
++
++#ifdef CONFIG_CGROUP_BFQIO
++/**
++ * struct bfq_group - per (device, cgroup) data structure.
++ * @entity: schedulable entity to insert into the parent group sched_data.
++ * @sched_data: own sched_data, to contain child entities (they may be
++ * both bfq_queues and bfq_groups).
++ * @group_node: node to be inserted into the bfqio_cgroup->group_data
++ * list of the containing cgroup's bfqio_cgroup.
++ * @bfqd_node: node to be inserted into the @bfqd->group_list list
++ * of the groups active on the same device; used for cleanup.
++ * @bfqd: the bfq_data for the device this group acts upon.
++ * @async_bfqq: array of async queues for all the tasks belonging to
++ * the group, one queue per ioprio value per ioprio_class,
++ * except for the idle class that has only one queue.
++ * @async_idle_bfqq: async queue for the idle class (ioprio is ignored).
++ * @my_entity: pointer to @entity, %NULL for the toplevel group; used
++ * to avoid too many special cases during group creation/migration.
++ *
++ * Each (device, cgroup) pair has its own bfq_group, i.e., for each cgroup
++ * there is a set of bfq_groups, each one collecting the lower-level
++ * entities belonging to the group that are acting on the same device.
++ *
++ * Locking works as follows:
++ * o @group_node is protected by the bfqio_cgroup lock, and is accessed
++ * via RCU from its readers.
++ * o @bfqd is protected by the queue lock, RCU is used to access it
++ * from the readers.
++ * o All the other fields are protected by the @bfqd queue lock.
++ */
++struct bfq_group {
++ struct bfq_entity entity;
++ struct bfq_sched_data sched_data;
++
++ struct hlist_node group_node;
++ struct hlist_node bfqd_node;
++
++ void *bfqd;
++
++ struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR];
++ struct bfq_queue *async_idle_bfqq;
++
++ struct bfq_entity *my_entity;
++};
++
++/**
++ * struct bfqio_cgroup - bfq cgroup data structure.
++ * @css: subsystem state for bfq in the containing cgroup.
++ * @weight: cgroup weight.
++ * @ioprio: cgroup ioprio.
++ * @ioprio_class: cgroup ioprio_class.
++ * @lock: spinlock that protects @ioprio, @ioprio_class and @group_data.
++ * @group_data: list containing the bfq_group belonging to this cgroup.
++ *
++ * @group_data is accessed using RCU, with @lock protecting the updates,
++ * @ioprio and @ioprio_class are protected by @lock.
++ */
++struct bfqio_cgroup {
++ struct cgroup_subsys_state css;
++
++ unsigned short weight, ioprio, ioprio_class;
++
++ spinlock_t lock;
++ struct hlist_head group_data;
++};
++#else
++struct bfq_group {
++ struct bfq_sched_data sched_data;
++
++ struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR];
++ struct bfq_queue *async_idle_bfqq;
++};
++#endif
++
++static inline struct bfq_service_tree *
++bfq_entity_service_tree(struct bfq_entity *entity)
++{
++ struct bfq_sched_data *sched_data = entity->sched_data;
++ unsigned int idx = entity->ioprio_class - 1;
++
++ BUG_ON(idx >= BFQ_IOPRIO_CLASSES);
++ BUG_ON(sched_data == NULL);
++
++ return sched_data->service_tree + idx;
++}
++
++static inline struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic,
++ int is_sync)
++{
++ return bic->bfqq[!!is_sync];
++}
++
++static inline void bic_set_bfqq(struct bfq_io_cq *bic,
++ struct bfq_queue *bfqq, int is_sync)
++{
++ bic->bfqq[!!is_sync] = bfqq;
++}
++
++static inline struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic)
++{
++ return bic->icq.q->elevator->elevator_data;
++}
++
++/**
++ * bfq_get_bfqd_locked - get a lock to a bfqd using a RCU protected pointer.
++ * @ptr: a pointer to a bfqd.
++ * @flags: storage for the flags to be saved.
++ *
++ * This function allows bfqg->bfqd to be protected by the
++ * queue lock of the bfqd they reference; the pointer is dereferenced
++ * under RCU, so the storage for bfqd is assured to be safe as long
++ * as the RCU read side critical section does not end. After the
++ * bfqd->queue->queue_lock is taken the pointer is rechecked, to be
++ * sure that no other writer accessed it. If we raced with a writer,
++ * the function returns NULL, with the queue unlocked, otherwise it
++ * returns the dereferenced pointer, with the queue locked.
++ */
++static inline struct bfq_data *bfq_get_bfqd_locked(void **ptr,
++ unsigned long *flags)
++{
++ struct bfq_data *bfqd;
++
++ rcu_read_lock();
++ bfqd = rcu_dereference(*(struct bfq_data **)ptr);
++
++ if (bfqd != NULL) {
++ spin_lock_irqsave(bfqd->queue->queue_lock, *flags);
++ if (*ptr == bfqd)
++ goto out;
++ spin_unlock_irqrestore(bfqd->queue->queue_lock, *flags);
++ }
++
++ bfqd = NULL;
++out:
++ rcu_read_unlock();
++ return bfqd;
++}
++
++static inline void bfq_put_bfqd_unlock(struct bfq_data *bfqd,
++ unsigned long *flags)
++{
++ spin_unlock_irqrestore(bfqd->queue->queue_lock, *flags);
++}
++
++static void bfq_changed_ioprio(struct bfq_io_cq *bic);
++static void bfq_put_queue(struct bfq_queue *bfqq);
++static void bfq_dispatch_insert(struct request_queue *q, struct request *rq);
++static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
++ struct bfq_group *bfqg, int is_sync,
++ struct bfq_io_cq *bic, gfp_t gfp_mask);
++static void bfq_end_raising_async_queues(struct bfq_data *bfqd,
++ struct bfq_group *bfqg);
++static void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
++static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
++#endif
+--
+1.8.5.2
+
diff --git a/sys-kernel/kogaion-sources/files/desktop/0003-block-bfq-add-Early-Queue-Merge-EQM-to-BFQ-v7-for-3.10.0.patch b/sys-kernel/kogaion-sources/files/desktop/0003-block-bfq-add-Early-Queue-Merge-EQM-to-BFQ-v7-for-3.10.0.patch
new file mode 100644
index 00000000..ea585f02
--- /dev/null
+++ b/sys-kernel/kogaion-sources/files/desktop/0003-block-bfq-add-Early-Queue-Merge-EQM-to-BFQ-v7-for-3.10.0.patch
@@ -0,0 +1,1034 @@
+From efc499347ea3827417cf00718616bf61a090afec Mon Sep 17 00:00:00 2001
+From: Mauro Andreolini <mauro.andreolini@unimore.it>
+Date: Thu, 23 Jan 2014 16:54:44 +0100
+Subject: [PATCH 3/3] block, bfq: add Early Queue Merge (EQM) to BFQ-v7 for
+ 3.10.0
+
+A set of processes may happen to perform interleaved reads, i.e., requests
+whose union would give rise to a sequential read pattern. There are two
+typical cases: in the first case, processes read fixed-size chunks of
+data at a fixed distance from each other, while in the second case processes
+may read variable-size chunks at variable distances. The latter case occurs
+for example with KVM, which splits the I/O generated by the guest into
+multiple chunks, and lets these chunks be served by a pool of cooperating
+processes, iteratively assigning the next chunk of I/O to the first
+available process. CFQ uses actual queue merging for the first type of
+rocesses, whereas it uses preemption to get a sequential read pattern out
+of the read requests performed by the second type of processes. In the end
+it uses two different mechanisms to achieve the same goal: boosting the
+throughput with interleaved I/O.
+
+This patch introduces Early Queue Merge (EQM), a unified mechanism to get a
+sequential read pattern with both types of processes. The main idea is
+checking newly arrived requests against the next request of the active queue
+both in case of actual request insert and in case of request merge. By doing
+so, both the types of processes can be handled by just merging their queues.
+EQM is then simpler and more compact than the pair of mechanisms used in
+CFQ.
+
+Finally, EQM also preserves the typical low-latency properties of BFQ, by
+properly restoring the weight-raising state of a queue when it gets back to
+a non-merged state.
+
+Signed-off-by: Mauro Andreolini <mauro.andreolini@unimore.it>
+Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
+Reviewed-by: Paolo Valente <paolo.valente@unimore.it>
+---
+ block/bfq-iosched.c | 657 ++++++++++++++++++++++++++++++++++++----------------
+ block/bfq-sched.c | 28 ---
+ block/bfq.h | 16 ++
+ 3 files changed, 474 insertions(+), 227 deletions(-)
+
+diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
+index 96abb81..99083be6 100644
+--- a/block/bfq-iosched.c
++++ b/block/bfq-iosched.c
+@@ -445,6 +445,46 @@ static inline unsigned int bfq_wrais_duration(struct bfq_data *bfqd)
+ return dur;
+ }
+
++static inline void
++bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
++{
++ if (bic->saved_idle_window)
++ bfq_mark_bfqq_idle_window(bfqq);
++ else
++ bfq_clear_bfqq_idle_window(bfqq);
++ if (bic->raising_time_left && bfqq->bfqd->low_latency) {
++ /*
++ * Start a weight raising period with the duration given by
++ * the raising_time_left snapshot.
++ */
++ if (bfq_bfqq_busy(bfqq))
++ bfqq->bfqd->raised_busy_queues++;
++ bfqq->raising_coeff = bfqq->bfqd->bfq_raising_coeff;
++ bfqq->raising_cur_max_time = bic->raising_time_left;
++ bfqq->last_rais_start_finish = jiffies;
++ bfqq->entity.ioprio_changed = 1;
++ }
++ /*
++ * Clear raising_time_left to prevent bfq_bfqq_save_state() from
++ * getting confused about the queue's need of a weight-raising
++ * period.
++ */
++ bic->raising_time_left = 0;
++}
++
++/*
++ * Must be called with the queue_lock held.
++ */
++static int bfqq_process_refs(struct bfq_queue *bfqq)
++{
++ int process_refs, io_refs;
++
++ io_refs = bfqq->allocated[READ] + bfqq->allocated[WRITE];
++ process_refs = atomic_read(&bfqq->ref) - io_refs - bfqq->entity.on_st;
++ BUG_ON(process_refs < 0);
++ return process_refs;
++}
++
+ static void bfq_add_rq_rb(struct request *rq)
+ {
+ struct bfq_queue *bfqq = RQ_BFQQ(rq);
+@@ -486,12 +526,20 @@ static void bfq_add_rq_rb(struct request *rq)
+ if (!bfqd->low_latency)
+ goto add_bfqq_busy;
+
++ if (bfq_bfqq_just_split(bfqq))
++ goto set_ioprio_changed;
++
+ /*
+- * If the queue is not being boosted and has been idle
+- * for enough time, start a weight-raising period
++ * If the queue:
++ * - is not being boosted,
++ * - has been idle for enough time,
++ * - is not a sync queue or is linked to a bfq_io_cq (it is
++ * shared "for its nature" or it is not shared and its
++ * requests have not been redirected to a shared queue)
++ * start a weight-raising period.
+ */
+- if (old_raising_coeff == 1 &&
+- (idle_for_long_time || soft_rt)) {
++ if (old_raising_coeff == 1 && (idle_for_long_time || soft_rt) &&
++ (!bfq_bfqq_sync(bfqq) || bfqq->bic != NULL)) {
+ bfqq->raising_coeff = bfqd->bfq_raising_coeff;
+ if (idle_for_long_time)
+ bfqq->raising_cur_max_time =
+@@ -572,6 +620,7 @@ static void bfq_add_rq_rb(struct request *rq)
+ bfqd->bfq_raising_rt_max_time;
+ }
+ }
++set_ioprio_changed:
+ if (old_raising_coeff != bfqq->raising_coeff)
+ entity->ioprio_changed = 1;
+ add_bfqq_busy:
+@@ -754,90 +803,35 @@ static void bfq_end_raising(struct bfq_data *bfqd)
+ spin_unlock_irq(bfqd->queue->queue_lock);
+ }
+
+-static int bfq_allow_merge(struct request_queue *q, struct request *rq,
+- struct bio *bio)
+-{
+- struct bfq_data *bfqd = q->elevator->elevator_data;
+- struct bfq_io_cq *bic;
+- struct bfq_queue *bfqq;
+-
+- /*
+- * Disallow merge of a sync bio into an async request.
+- */
+- if (bfq_bio_sync(bio) && !rq_is_sync(rq))
+- return 0;
+-
+- /*
+- * Lookup the bfqq that this bio will be queued with. Allow
+- * merge only if rq is queued there.
+- * Queue lock is held here.
+- */
+- bic = bfq_bic_lookup(bfqd, current->io_context);
+- if (bic == NULL)
+- return 0;
+-
+- bfqq = bic_to_bfqq(bic, bfq_bio_sync(bio));
+- return bfqq == RQ_BFQQ(rq);
+-}
+-
+-static void __bfq_set_in_service_queue(struct bfq_data *bfqd,
+- struct bfq_queue *bfqq)
+-{
+- if (bfqq != NULL) {
+- bfq_mark_bfqq_must_alloc(bfqq);
+- bfq_mark_bfqq_budget_new(bfqq);
+- bfq_clear_bfqq_fifo_expire(bfqq);
+-
+- bfqd->budgets_assigned = (bfqd->budgets_assigned*7 + 256) / 8;
+-
+- bfq_log_bfqq(bfqd, bfqq,
+- "set_in_service_queue, cur-budget = %lu",
+- bfqq->entity.budget);
+- }
+-
+- bfqd->in_service_queue = bfqq;
+-}
+-
+-/*
+- * Get and set a new queue for service.
+- */
+-static struct bfq_queue *bfq_set_in_service_queue(struct bfq_data *bfqd,
+- struct bfq_queue *bfqq)
++static inline sector_t bfq_io_struct_pos(void *io_struct, bool request)
+ {
+- if (!bfqq)
+- bfqq = bfq_get_next_queue(bfqd);
++ if (request)
++ return blk_rq_pos(io_struct);
+ else
+- bfq_get_next_queue_forced(bfqd, bfqq);
+-
+- __bfq_set_in_service_queue(bfqd, bfqq);
+- return bfqq;
++ return ((struct bio *)io_struct)->bi_sector;
+ }
+
+-static inline sector_t bfq_dist_from_last(struct bfq_data *bfqd,
+- struct request *rq)
++static inline sector_t bfq_dist_from(sector_t pos1,
++ sector_t pos2)
+ {
+- if (blk_rq_pos(rq) >= bfqd->last_position)
+- return blk_rq_pos(rq) - bfqd->last_position;
++ if (pos1 >= pos2)
++ return pos1 - pos2;
+ else
+- return bfqd->last_position - blk_rq_pos(rq);
++ return pos2 - pos1;
+ }
+
+-/*
+- * Return true if bfqq has no request pending and rq is close enough to
+- * bfqd->last_position, or if rq is closer to bfqd->last_position than
+- * bfqq->next_rq
+- */
+-static inline int bfq_rq_close(struct bfq_data *bfqd, struct request *rq)
++static inline int bfq_rq_close_to_sector(void *io_struct, bool request,
++ sector_t sector)
+ {
+- return bfq_dist_from_last(bfqd, rq) <= BFQQ_SEEK_THR;
++ return bfq_dist_from(bfq_io_struct_pos(io_struct, request), sector) <=
++ BFQQ_SEEK_THR;
+ }
+
+-static struct bfq_queue *bfqq_close(struct bfq_data *bfqd)
++static struct bfq_queue *bfqq_close(struct bfq_data *bfqd, sector_t sector)
+ {
+ struct rb_root *root = &bfqd->rq_pos_tree;
+ struct rb_node *parent, *node;
+ struct bfq_queue *__bfqq;
+- sector_t sector = bfqd->last_position;
+
+ if (RB_EMPTY_ROOT(root))
+ return NULL;
+@@ -856,7 +850,7 @@ static struct bfq_queue *bfqq_close(struct bfq_data *bfqd)
+ * position).
+ */
+ __bfqq = rb_entry(parent, struct bfq_queue, pos_node);
+- if (bfq_rq_close(bfqd, __bfqq->next_rq))
++ if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector))
+ return __bfqq;
+
+ if (blk_rq_pos(__bfqq->next_rq) < sector)
+@@ -867,7 +861,7 @@ static struct bfq_queue *bfqq_close(struct bfq_data *bfqd)
+ return NULL;
+
+ __bfqq = rb_entry(node, struct bfq_queue, pos_node);
+- if (bfq_rq_close(bfqd, __bfqq->next_rq))
++ if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector))
+ return __bfqq;
+
+ return NULL;
+@@ -876,14 +870,12 @@ static struct bfq_queue *bfqq_close(struct bfq_data *bfqd)
+ /*
+ * bfqd - obvious
+ * cur_bfqq - passed in so that we don't decide that the current queue
+- * is closely cooperating with itself.
+- *
+- * We are assuming that cur_bfqq has dispatched at least one request,
+- * and that bfqd->last_position reflects a position on the disk associated
+- * with the I/O issued by cur_bfqq.
++ * is closely cooperating with itself
++ * sector - used as a reference point to search for a close queue
+ */
+ static struct bfq_queue *bfq_close_cooperator(struct bfq_data *bfqd,
+- struct bfq_queue *cur_bfqq)
++ struct bfq_queue *cur_bfqq,
++ sector_t sector)
+ {
+ struct bfq_queue *bfqq;
+
+@@ -903,7 +895,7 @@ static struct bfq_queue *bfq_close_cooperator(struct bfq_data *bfqd,
+ * working closely on the same area of the disk. In that case,
+ * we can group them together and don't waste time idling.
+ */
+- bfqq = bfqq_close(bfqd);
++ bfqq = bfqq_close(bfqd, sector);
+ if (bfqq == NULL || bfqq == cur_bfqq)
+ return NULL;
+
+@@ -930,6 +922,282 @@ static struct bfq_queue *bfq_close_cooperator(struct bfq_data *bfqd,
+ return bfqq;
+ }
+
++static struct bfq_queue *
++bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
++{
++ int process_refs, new_process_refs;
++ struct bfq_queue *__bfqq;
++
++ /*
++ * If there are no process references on the new_bfqq, then it is
++ * unsafe to follow the ->new_bfqq chain as other bfqq's in the chain
++ * may have dropped their last reference (not just their last process
++ * reference).
++ */
++ if (!bfqq_process_refs(new_bfqq))
++ return NULL;
++
++ /* Avoid a circular list and skip interim queue merges. */
++ while ((__bfqq = new_bfqq->new_bfqq)) {
++ if (__bfqq == bfqq)
++ return NULL;
++ new_bfqq = __bfqq;
++ }
++
++ process_refs = bfqq_process_refs(bfqq);
++ new_process_refs = bfqq_process_refs(new_bfqq);
++ /*
++ * If the process for the bfqq has gone away, there is no
++ * sense in merging the queues.
++ */
++ if (process_refs == 0 || new_process_refs == 0)
++ return NULL;
++
++ bfq_log_bfqq(bfqq->bfqd, bfqq, "scheduling merge with queue %d",
++ new_bfqq->pid);
++
++ /*
++ * Merging is just a redirection: the requests of the process owning
++ * one of the two queues are redirected to the other queue. The latter
++ * queue, in its turn, is set as shared if this is the first time that
++ * the requests of some process are redirected to it.
++ *
++ * We redirect bfqq to new_bfqq and not the opposite, because we
++ * are in the context of the process owning bfqq, hence we have the
++ * io_cq of this process. So we can immediately configure this io_cq
++ * to redirect the requests of the process to new_bfqq.
++ *
++ * NOTE, even if new_bfqq coincides with the in-service queue, the
++ * io_cq of new_bfqq is not available, because, if the in-service queue
++ * is shared, bfqd->in_service_bic may not point to the io_cq of the
++ * in-service queue.
++ * Redirecting the requests of the process owning bfqq to the currently
++ * in-service queue is in any case the best option, as we feed the
++ * in-service queue with new requests close to the last request served
++ * and, by doing so, hopefully increase the throughput.
++ */
++ bfqq->new_bfqq = new_bfqq;
++ atomic_add(process_refs, &new_bfqq->ref);
++ return new_bfqq;
++}
++
++/*
++ * Attempt to schedule a merge of bfqq with the currently in-service queue or
++ * with a close queue among the scheduled queues.
++ * Return NULL if no merge was scheduled, a pointer to the shared bfq_queue
++ * structure otherwise.
++ */
++static struct bfq_queue *
++bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
++ void *io_struct, bool request)
++{
++ struct bfq_queue *in_service_bfqq, *new_bfqq;
++
++ if (bfqq->new_bfqq)
++ return bfqq->new_bfqq;
++
++ if (!io_struct)
++ return NULL;
++
++ in_service_bfqq = bfqd->in_service_queue;
++
++ if (in_service_bfqq == NULL || in_service_bfqq == bfqq ||
++ !bfqd->in_service_bic)
++ goto check_scheduled;
++
++ if (bfq_class_idle(in_service_bfqq) || bfq_class_idle(bfqq))
++ goto check_scheduled;
++
++ if (bfq_class_rt(in_service_bfqq) != bfq_class_rt(bfqq))
++ goto check_scheduled;
++
++ if (in_service_bfqq->entity.parent != bfqq->entity.parent)
++ goto check_scheduled;
++
++ if (bfq_rq_close_to_sector(io_struct, request, bfqd->last_position) &&
++ bfq_bfqq_sync(in_service_bfqq) && bfq_bfqq_sync(bfqq)) {
++ new_bfqq = bfq_setup_merge(bfqq, in_service_bfqq);
++ if (new_bfqq != NULL)
++ return new_bfqq; /* Merge with the in-service queue */
++ }
++
++ /*
++ * Check whether there is a cooperator among currently scheduled
++ * queues. The only thing we need is that the bio/request is not
++ * NULL, as we need it to establish whether a cooperator exists.
++ */
++check_scheduled:
++ new_bfqq = bfq_close_cooperator(bfqd, bfqq,
++ bfq_io_struct_pos(io_struct, request));
++ if (new_bfqq)
++ return bfq_setup_merge(bfqq, new_bfqq);
++
++ return NULL;
++}
++
++static inline void
++bfq_bfqq_save_state(struct bfq_queue *bfqq)
++{
++ /*
++ * If bfqq->bic == NULL, the queue is already shared or its requests
++ * have already been redirected to a shared queue; both idle window
++ * and weight raising state have already been saved. Do nothing.
++ */
++ if (bfqq->bic == NULL)
++ return;
++ if (bfqq->bic->raising_time_left)
++ /*
++ * This is the queue of a just-started process, and would
++ * deserve weight raising: we set raising_time_left to the full
++ * weight-raising duration to trigger weight-raising when and
++ * if the queue is split and the first request of the queue
++ * is enqueued.
++ */
++ bfqq->bic->raising_time_left = bfq_wrais_duration(bfqq->bfqd);
++ else if (bfqq->raising_coeff > 1) {
++ unsigned long wrais_duration =
++ jiffies - bfqq->last_rais_start_finish;
++ /*
++ * It may happen that a queue's weight raising period lasts
++ * longer than its raising_cur_max_time, as weight raising is
++ * handled only when a request is enqueued or dispatched (it
++ * does not use any timer). If the weight raising period is
++ * about to end, don't save it.
++ */
++ if (bfqq->raising_cur_max_time <= wrais_duration)
++ bfqq->bic->raising_time_left = 0;
++ else
++ bfqq->bic->raising_time_left =
++ bfqq->raising_cur_max_time - wrais_duration;
++ /*
++ * The bfq_queue is becoming shared or the requests of the
++ * process owning the queue are being redirected to a shared
++ * queue. Stop the weight raising period of the queue, as in
++ * both cases it should not be owned by an interactive or soft
++ * real-time application.
++ */
++ bfq_bfqq_end_raising(bfqq);
++ } else
++ bfqq->bic->raising_time_left = 0;
++ bfqq->bic->saved_idle_window = bfq_bfqq_idle_window(bfqq);
++}
++
++static inline void
++bfq_get_bic_reference(struct bfq_queue *bfqq)
++{
++ /*
++ * If bfqq->bic has a non-NULL value, the bic to which it belongs
++ * is about to begin using a shared bfq_queue.
++ */
++ if (bfqq->bic)
++ atomic_long_inc(&bfqq->bic->icq.ioc->refcount);
++}
++
++static void
++bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
++ struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
++{
++ bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu",
++ (long unsigned)new_bfqq->pid);
++ /* Save weight raising and idle window of the merged queues */
++ bfq_bfqq_save_state(bfqq);
++ bfq_bfqq_save_state(new_bfqq);
++ /*
++ * Grab a reference to the bic, to prevent it from being destroyed
++ * before being possibly touched by a bfq_split_bfqq().
++ */
++ bfq_get_bic_reference(bfqq);
++ bfq_get_bic_reference(new_bfqq);
++ /* Merge queues (that is, let bic redirect its requests to new_bfqq) */
++ bic_set_bfqq(bic, new_bfqq, 1);
++ bfq_mark_bfqq_coop(new_bfqq);
++ /*
++ * new_bfqq now belongs to at least two bics (it is a shared queue): set
++ * new_bfqq->bic to NULL. bfqq either:
++ * - does not belong to any bic any more, and hence bfqq->bic must
++ * be set to NULL, or
++ * - is a queue whose owning bics have already been redirected to a
++ * different queue, hence the queue is destined to not belong to any
++ * bic soon and bfqq->bic is already NULL (therefore the next
++ * assignment causes no harm).
++ */
++ new_bfqq->bic = NULL;
++ bfqq->bic = NULL;
++ bfq_put_queue(bfqq);
++}
++
++static int bfq_allow_merge(struct request_queue *q, struct request *rq,
++ struct bio *bio)
++{
++ struct bfq_data *bfqd = q->elevator->elevator_data;
++ struct bfq_io_cq *bic;
++ struct bfq_queue *bfqq, *new_bfqq;
++
++ /*
++ * Disallow merge of a sync bio into an async request.
++ */
++ if (bfq_bio_sync(bio) && !rq_is_sync(rq))
++ return 0;
++
++ /*
++ * Lookup the bfqq that this bio will be queued with. Allow
++ * merge only if rq is queued there.
++ * Queue lock is held here.
++ */
++ bic = bfq_bic_lookup(bfqd, current->io_context);
++ if (bic == NULL)
++ return 0;
++
++ bfqq = bic_to_bfqq(bic, bfq_bio_sync(bio));
++ /*
++ * We take advantage of this function to perform an early merge
++ * of the queues of possible cooperating processes.
++ */
++ if (bfqq != NULL) {
++ new_bfqq = bfq_setup_cooperator(bfqd, bfqq, bio, false);
++ if (new_bfqq != NULL) {
++ bfq_merge_bfqqs(bfqd, bic, bfqq, new_bfqq);
++ /*
++ * If we get here, the bio will be queued in the shared queue,
++ * i.e., new_bfqq, so use new_bfqq to decide whether bio and
++ * rq can be merged.
++ */
++ bfqq = new_bfqq;
++ }
++ }
++
++ return bfqq == RQ_BFQQ(rq);
++}
++
++static void __bfq_set_in_service_queue(struct bfq_data *bfqd,
++ struct bfq_queue *bfqq)
++{
++ if (bfqq != NULL) {
++ bfq_mark_bfqq_must_alloc(bfqq);
++ bfq_mark_bfqq_budget_new(bfqq);
++ bfq_clear_bfqq_fifo_expire(bfqq);
++
++ bfqd->budgets_assigned = (bfqd->budgets_assigned*7 + 256) / 8;
++
++ bfq_log_bfqq(bfqd, bfqq,
++ "set_in_service_queue, cur-budget = %lu",
++ bfqq->entity.budget);
++ }
++
++ bfqd->in_service_queue = bfqq;
++}
++
++/*
++ * Get and set a new queue for service.
++ */
++static struct bfq_queue *bfq_set_in_service_queue(struct bfq_data *bfqd)
++{
++ struct bfq_queue *bfqq = bfq_get_next_queue(bfqd);
++
++ __bfq_set_in_service_queue(bfqd, bfqq);
++ return bfqq;
++}
++
+ /*
+ * If enough samples have been computed, return the current max budget
+ * stored in bfqd, which is dynamically updated according to the
+@@ -1077,63 +1345,6 @@ static struct request *bfq_check_fifo(struct bfq_queue *bfqq)
+ return rq;
+ }
+
+-/*
+- * Must be called with the queue_lock held.
+- */
+-static int bfqq_process_refs(struct bfq_queue *bfqq)
+-{
+- int process_refs, io_refs;
+-
+- io_refs = bfqq->allocated[READ] + bfqq->allocated[WRITE];
+- process_refs = atomic_read(&bfqq->ref) - io_refs - bfqq->entity.on_st;
+- BUG_ON(process_refs < 0);
+- return process_refs;
+-}
+-
+-static void bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
+-{
+- int process_refs, new_process_refs;
+- struct bfq_queue *__bfqq;
+-
+- /*
+- * If there are no process references on the new_bfqq, then it is
+- * unsafe to follow the ->new_bfqq chain as other bfqq's in the chain
+- * may have dropped their last reference (not just their last process
+- * reference).
+- */
+- if (!bfqq_process_refs(new_bfqq))
+- return;
+-
+- /* Avoid a circular list and skip interim queue merges. */
+- while ((__bfqq = new_bfqq->new_bfqq)) {
+- if (__bfqq == bfqq)
+- return;
+- new_bfqq = __bfqq;
+- }
+-
+- process_refs = bfqq_process_refs(bfqq);
+- new_process_refs = bfqq_process_refs(new_bfqq);
+- /*
+- * If the process for the bfqq has gone away, there is no
+- * sense in merging the queues.
+- */
+- if (process_refs == 0 || new_process_refs == 0)
+- return;
+-
+- /*
+- * Merge in the direction of the lesser amount of work.
+- */
+- if (new_process_refs >= process_refs) {
+- bfqq->new_bfqq = new_bfqq;
+- atomic_add(process_refs, &new_bfqq->ref);
+- } else {
+- new_bfqq->new_bfqq = bfqq;
+- atomic_add(new_process_refs, &bfqq->ref);
+- }
+- bfq_log_bfqq(bfqq->bfqd, bfqq, "scheduling merge with queue %d",
+- new_bfqq->pid);
+-}
+-
+ static inline unsigned long bfq_bfqq_budget_left(struct bfq_queue *bfqq)
+ {
+ struct bfq_entity *entity = &bfqq->entity;
+@@ -1703,7 +1914,7 @@ static inline bool bfq_bfqq_must_idle(struct bfq_queue *bfqq)
+ */
+ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
+ {
+- struct bfq_queue *bfqq, *new_bfqq = NULL;
++ struct bfq_queue *bfqq;
+ struct request *next_rq;
+ enum bfqq_expiration reason = BFQ_BFQQ_BUDGET_TIMEOUT;
+
+@@ -1713,17 +1924,6 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
+
+ bfq_log_bfqq(bfqd, bfqq, "select_queue: already in-service queue");
+
+- /*
+- * If another queue has a request waiting within our mean seek
+- * distance, let it run. The expire code will check for close
+- * cooperators and put the close queue at the front of the
+- * service tree. If possible, merge the expiring queue with the
+- * new bfqq.
+- */
+- new_bfqq = bfq_close_cooperator(bfqd, bfqq);
+- if (new_bfqq != NULL && bfqq->new_bfqq == NULL)
+- bfq_setup_merge(bfqq, new_bfqq);
+-
+ if (bfq_may_expire_for_budg_timeout(bfqq) &&
+ !timer_pending(&bfqd->idle_slice_timer) &&
+ !bfq_bfqq_must_idle(bfqq))
+@@ -1760,36 +1960,26 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
+ bfq_clear_bfqq_wait_request(bfqq);
+ del_timer(&bfqd->idle_slice_timer);
+ }
+- if (new_bfqq == NULL)
+- goto keep_queue;
+- else
+- goto expire;
++ goto keep_queue;
+ }
+ }
+
+ /*
+- * No requests pending. If the in-service queue has no cooperator and
+- * still has requests in flight (possibly waiting for a completion)
+- * or is idling for a new request, then keep it.
++ * No requests pending. If the in-service queue still has requests in
++ * flight (possibly waiting for a completion) or is idling for a new
++ * request, then keep it.
+ */
+- if (new_bfqq == NULL && (timer_pending(&bfqd->idle_slice_timer) ||
+- (bfqq->dispatched != 0 && bfq_bfqq_must_not_expire(bfqq)))) {
++ if (timer_pending(&bfqd->idle_slice_timer) ||
++ (bfqq->dispatched != 0 && bfq_bfqq_must_not_expire(bfqq))) {
+ bfqq = NULL;
+ goto keep_queue;
+- } else if (new_bfqq != NULL && timer_pending(&bfqd->idle_slice_timer)) {
+- /*
+- * Expiring the queue because there is a close cooperator,
+- * cancel timer.
+- */
+- bfq_clear_bfqq_wait_request(bfqq);
+- del_timer(&bfqd->idle_slice_timer);
+ }
+
+ reason = BFQ_BFQQ_NO_MORE_REQUESTS;
+ expire:
+ bfq_bfqq_expire(bfqd, bfqq, 0, reason);
+ new_queue:
+- bfqq = bfq_set_in_service_queue(bfqd, new_bfqq);
++ bfqq = bfq_set_in_service_queue(bfqd);
+ bfq_log(bfqd, "select_queue: new queue %d returned",
+ bfqq != NULL ? bfqq->pid : 0);
+ keep_queue:
+@@ -1799,9 +1989,8 @@ keep_queue:
+ static void bfq_update_raising_data(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq)
+ {
++ struct bfq_entity *entity = &bfqq->entity;
+ if (bfqq->raising_coeff > 1) { /* queue is being boosted */
+- struct bfq_entity *entity = &bfqq->entity;
+-
+ bfq_log_bfqq(bfqd, bfqq,
+ "raising period dur %u/%u msec, "
+ "old raising coeff %u, w %d(%d)",
+@@ -1818,7 +2007,7 @@ static void bfq_update_raising_data(struct bfq_data *bfqd,
+ "WARN: pending prio change");
+ /*
+ * If too much time has elapsed from the beginning
+- * of this weight-raising, stop it.
++ * of this weight-raising period, stop it.
+ */
+ if (jiffies - bfqq->last_rais_start_finish >
+ bfqq->raising_cur_max_time) {
+@@ -1830,11 +2019,13 @@ static void bfq_update_raising_data(struct bfq_data *bfqd,
+ jiffies_to_msecs(bfqq->
+ raising_cur_max_time));
+ bfq_bfqq_end_raising(bfqq);
+- __bfq_entity_update_weight_prio(
+- bfq_entity_service_tree(entity),
+- entity);
+ }
+ }
++ /* Update weight both if it must be raised and if it must be lowered */
++ if ((entity->weight > entity->orig_weight) != (bfqq->raising_coeff > 1))
++ __bfq_entity_update_weight_prio(
++ bfq_entity_service_tree(entity),
++ entity);
+ }
+
+ /*
+@@ -2075,6 +2266,25 @@ static void bfq_init_icq(struct io_cq *icq)
+ struct bfq_io_cq *bic = icq_to_bic(icq);
+
+ bic->ttime.last_end_request = jiffies;
++ /*
++ * A newly created bic indicates that the process has just
++ * started doing I/O, and is probably mapping into memory its
++ * executable and libraries: it definitely needs weight raising.
++ * There is however the possibility that the process performs,
++ * for a while, I/O close to some other process. EQM intercepts
++ * this behavior and may merge the queue corresponding to the
++ * process with some other queue, BEFORE the weight of the queue
++ * is raised. Merged queues are not weight-raised (they are assumed
++ * to belong to processes that benefit only from high throughput).
++ * If the merge is basically the consequence of an accident, then
++ * the queue will be split soon and will get back its old weight.
++ * It is then important to write down somewhere that this queue
++ * does need weight raising, even if it did not make it to get its
++ * weight raised before being merged. To this purpose, we overload
++ * the field raising_time_left and assign 1 to it, to mark the queue
++ * as needing weight raising.
++ */
++ bic->raising_time_left = 1;
+ }
+
+ static void bfq_exit_icq(struct io_cq *icq)
+@@ -2088,6 +2298,13 @@ static void bfq_exit_icq(struct io_cq *icq)
+ }
+
+ if (bic->bfqq[BLK_RW_SYNC]) {
++ /*
++ * If the bic is using a shared queue, put the reference
++ * taken on the io_context when the bic started using a
++ * shared bfq_queue.
++ */
++ if (bfq_bfqq_coop(bic->bfqq[BLK_RW_SYNC]))
++ put_io_context(icq->ioc);
+ bfq_exit_bfqq(bfqd, bic->bfqq[BLK_RW_SYNC]);
+ bic->bfqq[BLK_RW_SYNC] = NULL;
+ }
+@@ -2375,6 +2592,10 @@ static void bfq_update_idle_window(struct bfq_data *bfqd,
+ if (!bfq_bfqq_sync(bfqq) || bfq_class_idle(bfqq))
+ return;
+
++ /* Idle window just restored, statistics are meaningless. */
++ if (bfq_bfqq_just_split(bfqq))
++ return;
++
+ enable_idle = bfq_bfqq_idle_window(bfqq);
+
+ if (atomic_read(&bic->icq.ioc->active_ref) == 0 ||
+@@ -2415,6 +2636,7 @@ static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ if (bfqq->entity.service > bfq_max_budget(bfqd) / 8 ||
+ !BFQQ_SEEKY(bfqq))
+ bfq_update_idle_window(bfqd, bfqq, bic);
++ bfq_clear_bfqq_just_split(bfqq);
+
+ bfq_log_bfqq(bfqd, bfqq,
+ "rq_enqueued: idle_window=%d (seeky %d, mean %llu)",
+@@ -2475,13 +2697,48 @@ static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ static void bfq_insert_request(struct request_queue *q, struct request *rq)
+ {
+ struct bfq_data *bfqd = q->elevator->elevator_data;
+- struct bfq_queue *bfqq = RQ_BFQQ(rq);
++ struct bfq_queue *bfqq = RQ_BFQQ(rq), *new_bfqq;
+
+ assert_spin_locked(bfqd->queue->queue_lock);
++
++ /*
++ * An unplug may trigger a requeue of a request from the device
++ * driver: make sure we are in process context while trying to
++ * merge two bfq_queues.
++ */
++ if (!in_interrupt()) {
++ new_bfqq = bfq_setup_cooperator(bfqd, bfqq, rq, true);
++ if (new_bfqq != NULL) {
++ if (bic_to_bfqq(RQ_BIC(rq), 1) != bfqq)
++ new_bfqq = bic_to_bfqq(RQ_BIC(rq), 1);
++ /*
++ * Release the request's reference to the old bfqq
++ * and make sure one is taken to the shared queue.
++ */
++ new_bfqq->allocated[rq_data_dir(rq)]++;
++ bfqq->allocated[rq_data_dir(rq)]--;
++ atomic_inc(&new_bfqq->ref);
++ bfq_put_queue(bfqq);
++ if (bic_to_bfqq(RQ_BIC(rq), 1) == bfqq)
++ bfq_merge_bfqqs(bfqd, RQ_BIC(rq),
++ bfqq, new_bfqq);
++ rq->elv.priv[1] = new_bfqq;
++ bfqq = new_bfqq;
++ }
++ }
++
+ bfq_init_prio_data(bfqq, RQ_BIC(rq));
+
+ bfq_add_rq_rb(rq);
+
++ /*
++ * Here a newly-created bfq_queue has already started a weight-raising
++ * period: clear raising_time_left to prevent bfq_bfqq_save_state()
++ * from assigning it a full weight-raising period. See the detailed
++ * comments about this field in bfq_init_icq().
++ */
++ if (bfqq->bic != NULL)
++ bfqq->bic->raising_time_left = 0;
+ rq_set_fifo_time(rq, jiffies + bfqd->bfq_fifo_expire[rq_is_sync(rq)]);
+ list_add_tail(&rq->queuelist, &bfqq->fifo);
+
+@@ -2629,18 +2886,6 @@ static void bfq_put_request(struct request *rq)
+ }
+ }
+
+-static struct bfq_queue *
+-bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
+- struct bfq_queue *bfqq)
+-{
+- bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu",
+- (long unsigned)bfqq->new_bfqq->pid);
+- bic_set_bfqq(bic, bfqq->new_bfqq, 1);
+- bfq_mark_bfqq_coop(bfqq->new_bfqq);
+- bfq_put_queue(bfqq);
+- return bic_to_bfqq(bic, 1);
+-}
+-
+ /*
+ * Returns NULL if a new bfqq should be allocated, or the old bfqq if this
+ * was the last process referring to said bfqq.
+@@ -2649,6 +2894,9 @@ static struct bfq_queue *
+ bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq)
+ {
+ bfq_log_bfqq(bfqq->bfqd, bfqq, "splitting queue");
++
++ put_io_context(bic->icq.ioc);
++
+ if (bfqq_process_refs(bfqq) == 1) {
+ bfqq->pid = current->pid;
+ bfq_clear_bfqq_coop(bfqq);
+@@ -2677,6 +2925,7 @@ static int bfq_set_request(struct request_queue *q, struct request *rq,
+ struct bfq_queue *bfqq;
+ struct bfq_group *bfqg;
+ unsigned long flags;
++ bool split = false;
+
+ might_sleep_if(gfp_mask & __GFP_WAIT);
+
+@@ -2695,24 +2944,14 @@ new_queue:
+ bfqq = bfq_get_queue(bfqd, bfqg, is_sync, bic, gfp_mask);
+ bic_set_bfqq(bic, bfqq, is_sync);
+ } else {
+- /*
+- * If the queue was seeky for too long, break it apart.
+- */
++ /* If the queue was seeky for too long, break it apart. */
+ if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq)) {
+ bfq_log_bfqq(bfqd, bfqq, "breaking apart bfqq");
+ bfqq = bfq_split_bfqq(bic, bfqq);
++ split = true;
+ if (!bfqq)
+ goto new_queue;
+ }
+-
+- /*
+- * Check to see if this queue is scheduled to merge with
+- * another closely cooperating queue. The merging of queues
+- * happens here as it must be done in process context.
+- * The reference on new_bfqq was taken in merge_bfqqs.
+- */
+- if (bfqq->new_bfqq != NULL)
+- bfqq = bfq_merge_bfqqs(bfqd, bic, bfqq);
+ }
+
+ bfqq->allocated[rw]++;
+@@ -2723,6 +2962,26 @@ new_queue:
+ rq->elv.priv[0] = bic;
+ rq->elv.priv[1] = bfqq;
+
++ /*
++ * If a bfq_queue has only one process reference, it is owned
++ * by only one bfq_io_cq: we can set the bic field of the
++ * bfq_queue to the address of that structure. Also, if the
++ * queue has just been split, mark a flag so that the
++ * information is available to the other scheduler hooks.
++ */
++ if (bfqq_process_refs(bfqq) == 1) {
++ bfqq->bic = bic;
++ if (split) {
++ bfq_mark_bfqq_just_split(bfqq);
++ /*
++ * If the queue has just been split from a shared queue,
++ * restore the idle window and the possible weight
++ * raising period.
++ */
++ bfq_bfqq_resume_state(bfqq, bic);
++ }
++ }
++
+ spin_unlock_irqrestore(q->queue_lock, flags);
+
+ return 0;
+diff --git a/block/bfq-sched.c b/block/bfq-sched.c
+index 30df81c..47e66a8 100644
+--- a/block/bfq-sched.c
++++ b/block/bfq-sched.c
+@@ -979,34 +979,6 @@ static struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd)
+ return bfqq;
+ }
+
+-/*
+- * Forced extraction of the given queue.
+- */
+-static void bfq_get_next_queue_forced(struct bfq_data *bfqd,
+- struct bfq_queue *bfqq)
+-{
+- struct bfq_entity *entity;
+- struct bfq_sched_data *sd;
+-
+- BUG_ON(bfqd->in_service_queue != NULL);
+-
+- entity = &bfqq->entity;
+- /*
+- * Bubble up extraction/update from the leaf to the root.
+- */
+- for_each_entity(entity) {
+- sd = entity->sched_data;
+- bfq_update_budget(entity);
+- bfq_update_vtime(bfq_entity_service_tree(entity));
+- bfq_active_extract(bfq_entity_service_tree(entity), entity);
+- sd->active_entity = entity;
+- sd->next_active = NULL;
+- entity->service = 0;
+- }
+-
+- return;
+-}
+-
+ static void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
+ {
+ if (bfqd->in_service_bic != NULL) {
+diff --git a/block/bfq.h b/block/bfq.h
+index 78da7d2..b6ebc1d 100644
+--- a/block/bfq.h
++++ b/block/bfq.h
+@@ -192,6 +192,8 @@ struct bfq_group;
+ * idle to backlogged
+ * @service_from_backlogged: cumulative service received from the @bfq_queue
+ * since the last transition from idle to backlogged
++ * @bic: pointer to the bfq_io_cq owning the bfq_queue, set to %NULL if the
++ * queue is shared
+ *
+ * A bfq_queue is a leaf request queue; it can be associated to an io_context
+ * or more (if it is an async one). @cgroup holds a reference to the
+@@ -235,6 +237,7 @@ struct bfq_queue {
+ sector_t last_request_pos;
+
+ pid_t pid;
++ struct bfq_io_cq *bic;
+
+ /* weight-raising fields */
+ unsigned int raising_cur_max_time;
+@@ -264,12 +267,23 @@ struct bfq_ttime {
+ * @icq: associated io_cq structure
+ * @bfqq: array of two process queues, the sync and the async
+ * @ttime: associated @bfq_ttime struct
++ * @raising_time_left: snapshot of the time left before weight raising ends
++ * for the sync queue associated to this process; this
++ * snapshot is taken to remember this value while the weight
++ * raising is suspended because the queue is merged with a
++ * shared queue, and is used to set @raising_cur_max_time
++ * when the queue is split from the shared queue and its
++ * weight is raised again
++ * @saved_idle_window: same purpose as the previous field for the idle window
+ */
+ struct bfq_io_cq {
+ struct io_cq icq; /* must be the first member */
+ struct bfq_queue *bfqq[2];
+ struct bfq_ttime ttime;
+ int ioprio;
++
++ unsigned int raising_time_left;
++ unsigned int saved_idle_window;
+ };
+
+ /**
+@@ -411,6 +425,7 @@ enum bfqq_state_flags {
+ BFQ_BFQQ_FLAG_budget_new, /* no completion with this budget */
+ BFQ_BFQQ_FLAG_coop, /* bfqq is shared */
+ BFQ_BFQQ_FLAG_split_coop, /* shared bfqq will be splitted */
++ BFQ_BFQQ_FLAG_just_split, /* queue has just been split */
+ BFQ_BFQQ_FLAG_softrt_update, /* needs softrt-next-start update */
+ };
+
+@@ -438,6 +453,7 @@ BFQ_BFQQ_FNS(sync);
+ BFQ_BFQQ_FNS(budget_new);
+ BFQ_BFQQ_FNS(coop);
+ BFQ_BFQQ_FNS(split_coop);
++BFQ_BFQQ_FNS(just_split);
+ BFQ_BFQQ_FNS(softrt_update);
+ #undef BFQ_BFQQ_FNS
+
+--
+1.8.5.2
+
diff --git a/sys-kernel/kogaion-sources/files/desktop/3.10-ck1.patch b/sys-kernel/kogaion-sources/files/desktop/3.10-ck1.patch
new file mode 100644
index 00000000..1a9feb96
--- /dev/null
+++ b/sys-kernel/kogaion-sources/files/desktop/3.10-ck1.patch
@@ -0,0 +1,8732 @@
+// patch-3.10-ck1.patch
+Index: linux-3.10-ck1/arch/powerpc/platforms/cell/spufs/sched.c
+===================================================================
+--- linux-3.10-ck1.orig/arch/powerpc/platforms/cell/spufs/sched.c 2013-07-09 17:28:57.209502080 +1000
++++ linux-3.10-ck1/arch/powerpc/platforms/cell/spufs/sched.c 2013-07-09 17:29:00.837501924 +1000
+@@ -64,11 +64,6 @@
+ static struct timer_list spuloadavg_timer;
+
+ /*
+- * Priority of a normal, non-rt, non-niced'd process (aka nice level 0).
+- */
+-#define NORMAL_PRIO 120
+-
+-/*
+ * Frequency of the spu scheduler tick. By default we do one SPU scheduler
+ * tick for every 10 CPU scheduler ticks.
+ */
+Index: linux-3.10-ck1/Documentation/scheduler/sched-BFS.txt
+===================================================================
+--- /dev/null 1970-01-01 00:00:00.000000000 +0000
++++ linux-3.10-ck1/Documentation/scheduler/sched-BFS.txt 2013-07-09 17:29:00.837501924 +1000
+@@ -0,0 +1,347 @@
++BFS - The Brain Fuck Scheduler by Con Kolivas.
++
++Goals.
++
++The goal of the Brain Fuck Scheduler, referred to as BFS from here on, is to
++completely do away with the complex designs of the past for the cpu process
++scheduler and instead implement one that is very simple in basic design.
++The main focus of BFS is to achieve excellent desktop interactivity and
++responsiveness without heuristics and tuning knobs that are difficult to
++understand, impossible to model and predict the effect of, and when tuned to
++one workload cause massive detriment to another.
++
++
++Design summary.
++
++BFS is best described as a single runqueue, O(n) lookup, earliest effective
++virtual deadline first design, loosely based on EEVDF (earliest eligible virtual
++deadline first) and my previous Staircase Deadline scheduler. Each component
++shall be described in order to understand the significance of, and reasoning for
++it. The codebase when the first stable version was released was approximately
++9000 lines less code than the existing mainline linux kernel scheduler (in
++2.6.31). This does not even take into account the removal of documentation and
++the cgroups code that is not used.
++
++Design reasoning.
++
++The single runqueue refers to the queued but not running processes for the
++entire system, regardless of the number of CPUs. The reason for going back to
++a single runqueue design is that once multiple runqueues are introduced,
++per-CPU or otherwise, there will be complex interactions as each runqueue will
++be responsible for the scheduling latency and fairness of the tasks only on its
++own runqueue, and to achieve fairness and low latency across multiple CPUs, any
++advantage in throughput of having CPU local tasks causes other disadvantages.
++This is due to requiring a very complex balancing system to at best achieve some
++semblance of fairness across CPUs and can only maintain relatively low latency
++for tasks bound to the same CPUs, not across them. To increase said fairness
++and latency across CPUs, the advantage of local runqueue locking, which makes
++for better scalability, is lost due to having to grab multiple locks.
++
++A significant feature of BFS is that all accounting is done purely based on CPU
++used and nowhere is sleep time used in any way to determine entitlement or
++interactivity. Interactivity "estimators" that use some kind of sleep/run
++algorithm are doomed to fail to detect all interactive tasks, and to falsely tag
++tasks that aren't interactive as being so. The reason for this is that it is
++close to impossible to determine that when a task is sleeping, whether it is
++doing it voluntarily, as in a userspace application waiting for input in the
++form of a mouse click or otherwise, or involuntarily, because it is waiting for
++another thread, process, I/O, kernel activity or whatever. Thus, such an
++estimator will introduce corner cases, and more heuristics will be required to
++cope with those corner cases, introducing more corner cases and failed
++interactivity detection and so on. Interactivity in BFS is built into the design
++by virtue of the fact that tasks that are waking up have not used up their quota
++of CPU time, and have earlier effective deadlines, thereby making it very likely
++they will preempt any CPU bound task of equivalent nice level. See below for
++more information on the virtual deadline mechanism. Even if they do not preempt
++a running task, because the rr interval is guaranteed to have a bound upper
++limit on how long a task will wait for, it will be scheduled within a timeframe
++that will not cause visible interface jitter.
++
++
++Design details.
++
++Task insertion.
++
++BFS inserts tasks into each relevant queue as an O(1) insertion into a double
++linked list. On insertion, *every* running queue is checked to see if the newly
++queued task can run on any idle queue, or preempt the lowest running task on the
++system. This is how the cross-CPU scheduling of BFS achieves significantly lower
++latency per extra CPU the system has. In this case the lookup is, in the worst
++case scenario, O(n) where n is the number of CPUs on the system.
++
++Data protection.
++
++BFS has one single lock protecting the process local data of every task in the
++global queue. Thus every insertion, removal and modification of task data in the
++global runqueue needs to grab the global lock. However, once a task is taken by
++a CPU, the CPU has its own local data copy of the running process' accounting
++information which only that CPU accesses and modifies (such as during a
++timer tick) thus allowing the accounting data to be updated lockless. Once a
++CPU has taken a task to run, it removes it from the global queue. Thus the
++global queue only ever has, at most,
++
++ (number of tasks requesting cpu time) - (number of logical CPUs) + 1
++
++tasks in the global queue. This value is relevant for the time taken to look up
++tasks during scheduling. This will increase if many tasks with CPU affinity set
++in their policy to limit which CPUs they're allowed to run on if they outnumber
++the number of CPUs. The +1 is because when rescheduling a task, the CPU's
++currently running task is put back on the queue. Lookup will be described after
++the virtual deadline mechanism is explained.
++
++Virtual deadline.
++
++The key to achieving low latency, scheduling fairness, and "nice level"
++distribution in BFS is entirely in the virtual deadline mechanism. The one
++tunable in BFS is the rr_interval, or "round robin interval". This is the
++maximum time two SCHED_OTHER (or SCHED_NORMAL, the common scheduling policy)
++tasks of the same nice level will be running for, or looking at it the other
++way around, the longest duration two tasks of the same nice level will be
++delayed for. When a task requests cpu time, it is given a quota (time_slice)
++equal to the rr_interval and a virtual deadline. The virtual deadline is
++offset from the current time in jiffies by this equation:
++
++ jiffies + (prio_ratio * rr_interval)
++
++The prio_ratio is determined as a ratio compared to the baseline of nice -20
++and increases by 10% per nice level. The deadline is a virtual one only in that
++no guarantee is placed that a task will actually be scheduled by this time, but
++it is used to compare which task should go next. There are three components to
++how a task is next chosen. First is time_slice expiration. If a task runs out
++of its time_slice, it is descheduled, the time_slice is refilled, and the
++deadline reset to that formula above. Second is sleep, where a task no longer
++is requesting CPU for whatever reason. The time_slice and deadline are _not_
++adjusted in this case and are just carried over for when the task is next
++scheduled. Third is preemption, and that is when a newly waking task is deemed
++higher priority than a currently running task on any cpu by virtue of the fact
++that it has an earlier virtual deadline than the currently running task. The
++earlier deadline is the key to which task is next chosen for the first and
++second cases. Once a task is descheduled, it is put back on the queue, and an
++O(n) lookup of all queued-but-not-running tasks is done to determine which has
++the earliest deadline and that task is chosen to receive CPU next.
++
++The CPU proportion of different nice tasks works out to be approximately the
++
++ (prio_ratio difference)^2
++
++The reason it is squared is that a task's deadline does not change while it is
++running unless it runs out of time_slice. Thus, even if the time actually
++passes the deadline of another task that is queued, it will not get CPU time
++unless the current running task deschedules, and the time "base" (jiffies) is
++constantly moving.
++
++Task lookup.
++
++BFS has 103 priority queues. 100 of these are dedicated to the static priority
++of realtime tasks, and the remaining 3 are, in order of best to worst priority,
++SCHED_ISO (isochronous), SCHED_NORMAL, and SCHED_IDLEPRIO (idle priority
++scheduling). When a task of these priorities is queued, a bitmap of running
++priorities is set showing which of these priorities has tasks waiting for CPU
++time. When a CPU is made to reschedule, the lookup for the next task to get
++CPU time is performed in the following way:
++
++First the bitmap is checked to see what static priority tasks are queued. If
++any realtime priorities are found, the corresponding queue is checked and the
++first task listed there is taken (provided CPU affinity is suitable) and lookup
++is complete. If the priority corresponds to a SCHED_ISO task, they are also
++taken in FIFO order (as they behave like SCHED_RR). If the priority corresponds
++to either SCHED_NORMAL or SCHED_IDLEPRIO, then the lookup becomes O(n). At this
++stage, every task in the runlist that corresponds to that priority is checked
++to see which has the earliest set deadline, and (provided it has suitable CPU
++affinity) it is taken off the runqueue and given the CPU. If a task has an
++expired deadline, it is taken and the rest of the lookup aborted (as they are
++chosen in FIFO order).
++
++Thus, the lookup is O(n) in the worst case only, where n is as described
++earlier, as tasks may be chosen before the whole task list is looked over.
++
++
++Scalability.
++
++The major limitations of BFS will be that of scalability, as the separate
++runqueue designs will have less lock contention as the number of CPUs rises.
++However they do not scale linearly even with separate runqueues as multiple
++runqueues will need to be locked concurrently on such designs to be able to
++achieve fair CPU balancing, to try and achieve some sort of nice-level fairness
++across CPUs, and to achieve low enough latency for tasks on a busy CPU when
++other CPUs would be more suited. BFS has the advantage that it requires no
++balancing algorithm whatsoever, as balancing occurs by proxy simply because
++all CPUs draw off the global runqueue, in priority and deadline order. Despite
++the fact that scalability is _not_ the prime concern of BFS, it both shows very
++good scalability to smaller numbers of CPUs and is likely a more scalable design
++at these numbers of CPUs.
++
++It also has some very low overhead scalability features built into the design
++when it has been deemed their overhead is so marginal that they're worth adding.
++The first is the local copy of the running process' data to the CPU it's running
++on to allow that data to be updated lockless where possible. Then there is
++deference paid to the last CPU a task was running on, by trying that CPU first
++when looking for an idle CPU to use the next time it's scheduled. Finally there
++is the notion of "sticky" tasks that are flagged when they are involuntarily
++descheduled, meaning they still want further CPU time. This sticky flag is
++used to bias heavily against those tasks being scheduled on a different CPU
++unless that CPU would be otherwise idle. When a cpu frequency governor is used
++that scales with CPU load, such as ondemand, sticky tasks are not scheduled
++on a different CPU at all, preferring instead to go idle. This means the CPU
++they were bound to is more likely to increase its speed while the other CPU
++will go idle, thus speeding up total task execution time and likely decreasing
++power usage. This is the only scenario where BFS will allow a CPU to go idle
++in preference to scheduling a task on the earliest available spare CPU.
++
++The real cost of migrating a task from one CPU to another is entirely dependant
++on the cache footprint of the task, how cache intensive the task is, how long
++it's been running on that CPU to take up the bulk of its cache, how big the CPU
++cache is, how fast and how layered the CPU cache is, how fast a context switch
++is... and so on. In other words, it's close to random in the real world where we
++do more than just one sole workload. The only thing we can be sure of is that
++it's not free. So BFS uses the principle that an idle CPU is a wasted CPU and
++utilising idle CPUs is more important than cache locality, and cache locality
++only plays a part after that.
++
++When choosing an idle CPU for a waking task, the cache locality is determined
++according to where the task last ran and then idle CPUs are ranked from best
++to worst to choose the most suitable idle CPU based on cache locality, NUMA
++node locality and hyperthread sibling business. They are chosen in the
++following preference (if idle):
++
++* Same core, idle or busy cache, idle threads
++* Other core, same cache, idle or busy cache, idle threads.
++* Same node, other CPU, idle cache, idle threads.
++* Same node, other CPU, busy cache, idle threads.
++* Same core, busy threads.
++* Other core, same cache, busy threads.
++* Same node, other CPU, busy threads.
++* Other node, other CPU, idle cache, idle threads.
++* Other node, other CPU, busy cache, idle threads.
++* Other node, other CPU, busy threads.
++
++This shows the SMT or "hyperthread" awareness in the design as well which will
++choose a real idle core first before a logical SMT sibling which already has
++tasks on the physical CPU.
++
++Early benchmarking of BFS suggested scalability dropped off at the 16 CPU mark.
++However this benchmarking was performed on an earlier design that was far less
++scalable than the current one so it's hard to know how scalable it is in terms
++of both CPUs (due to the global runqueue) and heavily loaded machines (due to
++O(n) lookup) at this stage. Note that in terms of scalability, the number of
++_logical_ CPUs matters, not the number of _physical_ CPUs. Thus, a dual (2x)
++quad core (4X) hyperthreaded (2X) machine is effectively a 16X. Newer benchmark
++results are very promising indeed, without needing to tweak any knobs, features
++or options. Benchmark contributions are most welcome.
++
++
++Features
++
++As the initial prime target audience for BFS was the average desktop user, it
++was designed to not need tweaking, tuning or have features set to obtain benefit
++from it. Thus the number of knobs and features has been kept to an absolute
++minimum and should not require extra user input for the vast majority of cases.
++There are precisely 2 tunables, and 2 extra scheduling policies. The rr_interval
++and iso_cpu tunables, and the SCHED_ISO and SCHED_IDLEPRIO policies. In addition
++to this, BFS also uses sub-tick accounting. What BFS does _not_ now feature is
++support for CGROUPS. The average user should neither need to know what these
++are, nor should they need to be using them to have good desktop behaviour.
++
++rr_interval
++
++There is only one "scheduler" tunable, the round robin interval. This can be
++accessed in
++
++ /proc/sys/kernel/rr_interval
++
++The value is in milliseconds, and the default value is set to 6ms. Valid values
++are from 1 to 1000. Decreasing the value will decrease latencies at the cost of
++decreasing throughput, while increasing it will improve throughput, but at the
++cost of worsening latencies. The accuracy of the rr interval is limited by HZ
++resolution of the kernel configuration. Thus, the worst case latencies are
++usually slightly higher than this actual value. BFS uses "dithering" to try and
++minimise the effect the Hz limitation has. The default value of 6 is not an
++arbitrary one. It is based on the fact that humans can detect jitter at
++approximately 7ms, so aiming for much lower latencies is pointless under most
++circumstances. It is worth noting this fact when comparing the latency
++performance of BFS to other schedulers. Worst case latencies being higher than
++7ms are far worse than average latencies not being in the microsecond range.
++Experimentation has shown that rr intervals being increased up to 300 can
++improve throughput but beyond that, scheduling noise from elsewhere prevents
++further demonstrable throughput.
++
++Isochronous scheduling.
++
++Isochronous scheduling is a unique scheduling policy designed to provide
++near-real-time performance to unprivileged (ie non-root) users without the
++ability to starve the machine indefinitely. Isochronous tasks (which means
++"same time") are set using, for example, the schedtool application like so:
++
++ schedtool -I -e amarok
++
++This will start the audio application "amarok" as SCHED_ISO. How SCHED_ISO works
++is that it has a priority level between true realtime tasks and SCHED_NORMAL
++which would allow them to preempt all normal tasks, in a SCHED_RR fashion (ie,
++if multiple SCHED_ISO tasks are running, they purely round robin at rr_interval
++rate). However if ISO tasks run for more than a tunable finite amount of time,
++they are then demoted back to SCHED_NORMAL scheduling. This finite amount of
++time is the percentage of _total CPU_ available across the machine, configurable
++as a percentage in the following "resource handling" tunable (as opposed to a
++scheduler tunable):
++
++ /proc/sys/kernel/iso_cpu
++
++and is set to 70% by default. It is calculated over a rolling 5 second average
++Because it is the total CPU available, it means that on a multi CPU machine, it
++is possible to have an ISO task running as realtime scheduling indefinitely on
++just one CPU, as the other CPUs will be available. Setting this to 100 is the
++equivalent of giving all users SCHED_RR access and setting it to 0 removes the
++ability to run any pseudo-realtime tasks.
++
++A feature of BFS is that it detects when an application tries to obtain a
++realtime policy (SCHED_RR or SCHED_FIFO) and the caller does not have the
++appropriate privileges to use those policies. When it detects this, it will
++give the task SCHED_ISO policy instead. Thus it is transparent to the user.
++Because some applications constantly set their policy as well as their nice
++level, there is potential for them to undo the override specified by the user
++on the command line of setting the policy to SCHED_ISO. To counter this, once
++a task has been set to SCHED_ISO policy, it needs superuser privileges to set
++it back to SCHED_NORMAL. This will ensure the task remains ISO and all child
++processes and threads will also inherit the ISO policy.
++
++Idleprio scheduling.
++
++Idleprio scheduling is a scheduling policy designed to give out CPU to a task
++_only_ when the CPU would be otherwise idle. The idea behind this is to allow
++ultra low priority tasks to be run in the background that have virtually no
++effect on the foreground tasks. This is ideally suited to distributed computing
++clients (like setiathome, folding, mprime etc) but can also be used to start
++a video encode or so on without any slowdown of other tasks. To avoid this
++policy from grabbing shared resources and holding them indefinitely, if it
++detects a state where the task is waiting on I/O, the machine is about to
++suspend to ram and so on, it will transiently schedule them as SCHED_NORMAL. As
++per the Isochronous task management, once a task has been scheduled as IDLEPRIO,
++it cannot be put back to SCHED_NORMAL without superuser privileges. Tasks can
++be set to start as SCHED_IDLEPRIO with the schedtool command like so:
++
++ schedtool -D -e ./mprime
++
++Subtick accounting.
++
++It is surprisingly difficult to get accurate CPU accounting, and in many cases,
++the accounting is done by simply determining what is happening at the precise
++moment a timer tick fires off. This becomes increasingly inaccurate as the
++timer tick frequency (HZ) is lowered. It is possible to create an application
++which uses almost 100% CPU, yet by being descheduled at the right time, records
++zero CPU usage. While the main problem with this is that there are possible
++security implications, it is also difficult to determine how much CPU a task
++really does use. BFS tries to use the sub-tick accounting from the TSC clock,
++where possible, to determine real CPU usage. This is not entirely reliable, but
++is far more likely to produce accurate CPU usage data than the existing designs
++and will not show tasks as consuming no CPU usage when they actually are. Thus,
++the amount of CPU reported as being used by BFS will more accurately represent
++how much CPU the task itself is using (as is shown for example by the 'time'
++application), so the reported values may be quite different to other schedulers.
++Values reported as the 'load' are more prone to problems with this design, but
++per process values are closer to real usage. When comparing throughput of BFS
++to other designs, it is important to compare the actual completed work in terms
++of total wall clock time taken and total work done, rather than the reported
++"cpu usage".
++
++
++Con Kolivas <kernel@kolivas.org> Tue, 5 Apr 2011
+Index: linux-3.10-ck1/Documentation/sysctl/kernel.txt
+===================================================================
+--- linux-3.10-ck1.orig/Documentation/sysctl/kernel.txt 2013-07-09 17:28:57.123502084 +1000
++++ linux-3.10-ck1/Documentation/sysctl/kernel.txt 2013-07-09 17:29:00.837501924 +1000
+@@ -33,6 +33,7 @@
+ - domainname
+ - hostname
+ - hotplug
++- iso_cpu
+ - kptr_restrict
+ - kstack_depth_to_print [ X86 only ]
+ - l2cr [ PPC only ]
+@@ -60,6 +61,7 @@
+ - randomize_va_space
+ - real-root-dev ==> Documentation/initrd.txt
+ - reboot-cmd [ SPARC only ]
++- rr_interval
+ - rtsig-max
+ - rtsig-nr
+ - sem
+@@ -306,6 +308,16 @@
+
+ ==============================================================
+
++iso_cpu: (BFS CPU scheduler only).
++
++This sets the percentage cpu that the unprivileged SCHED_ISO tasks can
++run effectively at realtime priority, averaged over a rolling five
++seconds over the -whole- system, meaning all cpus.
++
++Set to 70 (percent) by default.
++
++==============================================================
++
+ l2cr: (PPC only)
+
+ This flag controls the L2 cache of G3 processor boards. If
+@@ -538,6 +550,20 @@
+
+ ==============================================================
+
++rr_interval: (BFS CPU scheduler only)
++
++This is the smallest duration that any cpu process scheduling unit
++will run for. Increasing this value can increase throughput of cpu
++bound tasks substantially but at the expense of increased latencies
++overall. Conversely decreasing it will decrease average and maximum
++latencies but at the expense of throughput. This value is in
++milliseconds and the default value chosen depends on the number of
++cpus available at scheduler initialisation with a minimum of 6.
++
++Valid values are from 1-1000.
++
++==============================================================
++
+ rtsig-max & rtsig-nr:
+
+ The file rtsig-max can be used to tune the maximum number
+Index: linux-3.10-ck1/fs/proc/base.c
+===================================================================
+--- linux-3.10-ck1.orig/fs/proc/base.c 2013-07-09 17:28:57.169502082 +1000
++++ linux-3.10-ck1/fs/proc/base.c 2013-07-09 17:29:00.838501924 +1000
+@@ -339,7 +339,7 @@
+ static int proc_pid_schedstat(struct task_struct *task, char *buffer)
+ {
+ return sprintf(buffer, "%llu %llu %lu\n",
+- (unsigned long long)task->se.sum_exec_runtime,
++ (unsigned long long)tsk_seruntime(task),
+ (unsigned long long)task->sched_info.run_delay,
+ task->sched_info.pcount);
+ }
+Index: linux-3.10-ck1/include/linux/init_task.h
+===================================================================
+--- linux-3.10-ck1.orig/include/linux/init_task.h 2013-07-09 17:28:57.154502083 +1000
++++ linux-3.10-ck1/include/linux/init_task.h 2013-07-09 17:29:00.838501924 +1000
+@@ -152,12 +152,70 @@
+ # define INIT_VTIME(tsk)
+ #endif
+
+-#define INIT_TASK_COMM "swapper"
+-
+ /*
+ * INIT_TASK is used to set up the first task table, touch at
+ * your own risk!. Base=0, limit=0x1fffff (=2MB)
+ */
++#ifdef CONFIG_SCHED_BFS
++#define INIT_TASK_COMM "BFS"
++#define INIT_TASK(tsk) \
++{ \
++ .state = 0, \
++ .stack = &init_thread_info, \
++ .usage = ATOMIC_INIT(2), \
++ .flags = PF_KTHREAD, \
++ .prio = NORMAL_PRIO, \
++ .static_prio = MAX_PRIO-20, \
++ .normal_prio = NORMAL_PRIO, \
++ .deadline = 0, \
++ .policy = SCHED_NORMAL, \
++ .cpus_allowed = CPU_MASK_ALL, \
++ .mm = NULL, \
++ .active_mm = &init_mm, \
++ .run_list = LIST_HEAD_INIT(tsk.run_list), \
++ .time_slice = HZ, \
++ .tasks = LIST_HEAD_INIT(tsk.tasks), \
++ INIT_PUSHABLE_TASKS(tsk) \
++ .ptraced = LIST_HEAD_INIT(tsk.ptraced), \
++ .ptrace_entry = LIST_HEAD_INIT(tsk.ptrace_entry), \
++ .real_parent = &tsk, \
++ .parent = &tsk, \
++ .children = LIST_HEAD_INIT(tsk.children), \
++ .sibling = LIST_HEAD_INIT(tsk.sibling), \
++ .group_leader = &tsk, \
++ RCU_POINTER_INITIALIZER(real_cred, &init_cred), \
++ RCU_POINTER_INITIALIZER(cred, &init_cred), \
++ .comm = INIT_TASK_COMM, \
++ .thread = INIT_THREAD, \
++ .fs = &init_fs, \
++ .files = &init_files, \
++ .signal = &init_signals, \
++ .sighand = &init_sighand, \
++ .nsproxy = &init_nsproxy, \
++ .pending = { \
++ .list = LIST_HEAD_INIT(tsk.pending.list), \
++ .signal = {{0}}}, \
++ .blocked = {{0}}, \
++ .alloc_lock = __SPIN_LOCK_UNLOCKED(tsk.alloc_lock), \
++ .journal_info = NULL, \
++ .cpu_timers = INIT_CPU_TIMERS(tsk.cpu_timers), \
++ .pi_lock = __RAW_SPIN_LOCK_UNLOCKED(tsk.pi_lock), \
++ .timer_slack_ns = 50000, /* 50 usec default slack */ \
++ .pids = { \
++ [PIDTYPE_PID] = INIT_PID_LINK(PIDTYPE_PID), \
++ [PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID), \
++ [PIDTYPE_SID] = INIT_PID_LINK(PIDTYPE_SID), \
++ }, \
++ INIT_IDS \
++ INIT_PERF_EVENTS(tsk) \
++ INIT_TRACE_IRQFLAGS \
++ INIT_LOCKDEP \
++ INIT_FTRACE_GRAPH \
++ INIT_TRACE_RECURSION \
++ INIT_TASK_RCU_PREEMPT(tsk) \
++}
++#else /* CONFIG_SCHED_BFS */
++#define INIT_TASK_COMM "swapper"
+ #define INIT_TASK(tsk) \
+ { \
+ .state = 0, \
+@@ -223,7 +281,7 @@
+ INIT_CPUSET_SEQ \
+ INIT_VTIME(tsk) \
+ }
+-
++#endif /* CONFIG_SCHED_BFS */
+
+ #define INIT_CPU_TIMERS(cpu_timers) \
+ { \
+Index: linux-3.10-ck1/include/linux/ioprio.h
+===================================================================
+--- linux-3.10-ck1.orig/include/linux/ioprio.h 2013-07-09 17:28:57.146502083 +1000
++++ linux-3.10-ck1/include/linux/ioprio.h 2013-07-09 17:29:00.838501924 +1000
+@@ -52,6 +52,8 @@
+ */
+ static inline int task_nice_ioprio(struct task_struct *task)
+ {
++ if (iso_task(task))
++ return 0;
+ return (task_nice(task) + 20) / 5;
+ }
+
+Index: linux-3.10-ck1/include/linux/sched.h
+===================================================================
+--- linux-3.10-ck1.orig/include/linux/sched.h 2013-07-09 17:28:57.163502082 +1000
++++ linux-3.10-ck1/include/linux/sched.h 2013-07-09 17:29:00.839501924 +1000
+@@ -229,8 +229,6 @@
+ extern void init_idle(struct task_struct *idle, int cpu);
+ extern void init_idle_bootup_task(struct task_struct *idle);
+
+-extern int runqueue_is_locked(int cpu);
+-
+ #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+ extern void nohz_balance_enter_idle(int cpu);
+ extern void set_cpu_sd_state_idle(void);
+@@ -1040,18 +1038,35 @@
+
+ #ifdef CONFIG_SMP
+ struct llist_node wake_entry;
+- int on_cpu;
+ #endif
+- int on_rq;
++#if defined(CONFIG_SMP) || defined(CONFIG_SCHED_BFS)
++ bool on_cpu;
++#endif
++#ifndef CONFIG_SCHED_BFS
++ bool on_rq;
++#endif
+
+ int prio, static_prio, normal_prio;
+ unsigned int rt_priority;
++#ifdef CONFIG_SCHED_BFS
++ int time_slice;
++ u64 deadline;
++ struct list_head run_list;
++ u64 last_ran;
++ u64 sched_time; /* sched_clock time spent running */
++#ifdef CONFIG_SMP
++ bool sticky; /* Soft affined flag */
++#endif
++ unsigned long rt_timeout;
++#else /* CONFIG_SCHED_BFS */
+ const struct sched_class *sched_class;
+ struct sched_entity se;
+ struct sched_rt_entity rt;
++
+ #ifdef CONFIG_CGROUP_SCHED
+ struct task_group *sched_task_group;
+ #endif
++#endif
+
+ #ifdef CONFIG_PREEMPT_NOTIFIERS
+ /* list of struct preempt_notifier: */
+@@ -1162,6 +1177,9 @@
+ int __user *clear_child_tid; /* CLONE_CHILD_CLEARTID */
+
+ cputime_t utime, stime, utimescaled, stimescaled;
++#ifdef CONFIG_SCHED_BFS
++ unsigned long utime_pc, stime_pc;
++#endif
+ cputime_t gtime;
+ #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+ struct cputime prev_cputime;
+@@ -1418,6 +1436,64 @@
+ #endif
+ };
+
++#ifdef CONFIG_SCHED_BFS
++bool grunqueue_is_locked(void);
++void grq_unlock_wait(void);
++void cpu_scaling(int cpu);
++void cpu_nonscaling(int cpu);
++bool above_background_load(void);
++#define tsk_seruntime(t) ((t)->sched_time)
++#define tsk_rttimeout(t) ((t)->rt_timeout)
++
++static inline void tsk_cpus_current(struct task_struct *p)
++{
++}
++
++static inline int runqueue_is_locked(int cpu)
++{
++ return grunqueue_is_locked();
++}
++
++void print_scheduler_version(void);
++
++static inline bool iso_task(struct task_struct *p)
++{
++ return (p->policy == SCHED_ISO);
++}
++#else /* CFS */
++extern int runqueue_is_locked(int cpu);
++static inline void cpu_scaling(int cpu)
++{
++}
++
++static inline void cpu_nonscaling(int cpu)
++{
++}
++#define tsk_seruntime(t) ((t)->se.sum_exec_runtime)
++#define tsk_rttimeout(t) ((t)->rt.timeout)
++
++static inline void tsk_cpus_current(struct task_struct *p)
++{
++ p->nr_cpus_allowed = current->nr_cpus_allowed;
++}
++
++static inline void print_scheduler_version(void)
++{
++ printk(KERN_INFO"CFS CPU scheduler.\n");
++}
++
++static inline bool iso_task(struct task_struct *p)
++{
++ return false;
++}
++
++/* Anyone feel like implementing this? */
++static inline bool above_background_load(void)
++{
++ return false;
++}
++#endif /* CONFIG_SCHED_BFS */
++
+ /* Future-safe accessor for struct task_struct's cpus_allowed. */
+ #define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
+
+@@ -1844,7 +1920,7 @@
+ task_sched_runtime(struct task_struct *task);
+
+ /* sched_exec is called by processes performing an exec */
+-#ifdef CONFIG_SMP
++#if defined(CONFIG_SMP) && !defined(CONFIG_SCHED_BFS)
+ extern void sched_exec(void);
+ #else
+ #define sched_exec() {}
+@@ -2549,7 +2625,7 @@
+ return 0;
+ }
+
+-static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
++static inline void set_task_cpu(struct task_struct *p, int cpu)
+ {
+ }
+
+Index: linux-3.10-ck1/init/Kconfig
+===================================================================
+--- linux-3.10-ck1.orig/init/Kconfig 2013-07-09 17:28:57.132502084 +1000
++++ linux-3.10-ck1/init/Kconfig 2013-07-09 17:29:00.839501924 +1000
+@@ -28,6 +28,20 @@
+
+ menu "General setup"
+
++config SCHED_BFS
++ bool "BFS cpu scheduler"
++ ---help---
++ The Brain Fuck CPU Scheduler for excellent interactivity and
++ responsiveness on the desktop and solid scalability on normal
++ hardware and commodity servers. Not recommended for 4096 CPUs.
++
++ Currently incompatible with the Group CPU scheduler, and RCU TORTURE
++ TEST so these options are disabled.
++
++ Say Y here.
++ default y
++
++
+ config BROKEN
+ bool
+
+@@ -302,7 +316,7 @@
+ # Kind of a stub config for the pure tick based cputime accounting
+ config TICK_CPU_ACCOUNTING
+ bool "Simple tick based cputime accounting"
+- depends on !S390 && !NO_HZ_FULL
++ depends on !S390 && !NO_HZ_FULL && !SCHED_BFS
+ help
+ This is the basic tick based cputime accounting that maintains
+ statistics about user, system and idle time spent on per jiffies
+@@ -325,7 +339,7 @@
+
+ config VIRT_CPU_ACCOUNTING_GEN
+ bool "Full dynticks CPU time accounting"
+- depends on HAVE_CONTEXT_TRACKING && 64BIT
++ depends on HAVE_CONTEXT_TRACKING && 64BIT && !SCHED_BFS
+ select VIRT_CPU_ACCOUNTING
+ select CONTEXT_TRACKING
+ help
+@@ -795,6 +809,7 @@
+ depends on ARCH_SUPPORTS_NUMA_BALANCING
+ depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY
+ depends on SMP && NUMA && MIGRATION
++ depends on !SCHED_BFS
+ help
+ This option adds support for automatic NUMA aware memory/task placement.
+ The mechanism is quite primitive and is based on migrating memory when
+@@ -857,6 +872,7 @@
+
+ config CGROUP_CPUACCT
+ bool "Simple CPU accounting cgroup subsystem"
++ depends on !SCHED_BFS
+ help
+ Provides a simple Resource Controller for monitoring the
+ total CPU consumed by the tasks in a cgroup.
+@@ -959,6 +975,7 @@
+
+ menuconfig CGROUP_SCHED
+ bool "Group CPU scheduler"
++ depends on !SCHED_BFS
+ default n
+ help
+ This feature lets CPU scheduler recognize task groups and control CPU
+@@ -1123,6 +1140,7 @@
+
+ config SCHED_AUTOGROUP
+ bool "Automatic process group scheduling"
++ depends on !SCHED_BFS
+ select EVENTFD
+ select CGROUPS
+ select CGROUP_SCHED
+@@ -1526,38 +1544,8 @@
+
+ On non-ancient distros (post-2000 ones) N is usually a safe choice.
+
+-choice
+- prompt "Choose SLAB allocator"
+- default SLUB
+- help
+- This option allows to select a slab allocator.
+-
+-config SLAB
+- bool "SLAB"
+- help
+- The regular slab allocator that is established and known to work
+- well in all environments. It organizes cache hot objects in
+- per cpu and per node queues.
+-
+ config SLUB
+- bool "SLUB (Unqueued Allocator)"
+- help
+- SLUB is a slab allocator that minimizes cache line usage
+- instead of managing queues of cached objects (SLAB approach).
+- Per cpu caching is realized using slabs of objects instead
+- of queues of objects. SLUB can use memory efficiently
+- and has enhanced diagnostics. SLUB is the default choice for
+- a slab allocator.
+-
+-config SLOB
+- depends on EXPERT
+- bool "SLOB (Simple Allocator)"
+- help
+- SLOB replaces the stock allocator with a drastically simpler
+- allocator. SLOB is generally more space efficient but
+- does not perform as well on large systems.
+-
+-endchoice
++ def_bool y
+
+ config MMAP_ALLOW_UNINITIALIZED
+ bool "Allow mmapped anonymous memory to be uninitialized"
+Index: linux-3.10-ck1/init/main.c
+===================================================================
+--- linux-3.10-ck1.orig/init/main.c 2013-07-09 17:28:57.127502084 +1000
++++ linux-3.10-ck1/init/main.c 2013-07-09 17:29:00.839501924 +1000
+@@ -700,7 +700,6 @@
+ return ret;
+ }
+
+-
+ extern initcall_t __initcall_start[];
+ extern initcall_t __initcall0_start[];
+ extern initcall_t __initcall1_start[];
+@@ -820,6 +819,8 @@
+
+ flush_delayed_fput();
+
++ print_scheduler_version();
++
+ if (ramdisk_execute_command) {
+ if (!run_init_process(ramdisk_execute_command))
+ return 0;
+Index: linux-3.10-ck1/kernel/delayacct.c
+===================================================================
+--- linux-3.10-ck1.orig/kernel/delayacct.c 2013-07-09 17:28:57.202502081 +1000
++++ linux-3.10-ck1/kernel/delayacct.c 2013-07-09 17:29:00.839501924 +1000
+@@ -133,7 +133,7 @@
+ */
+ t1 = tsk->sched_info.pcount;
+ t2 = tsk->sched_info.run_delay;
+- t3 = tsk->se.sum_exec_runtime;
++ t3 = tsk_seruntime(tsk);
+
+ d->cpu_count += t1;
+
+Index: linux-3.10-ck1/kernel/exit.c
+===================================================================
+--- linux-3.10-ck1.orig/kernel/exit.c 2013-07-09 17:28:57.186502081 +1000
++++ linux-3.10-ck1/kernel/exit.c 2013-07-09 17:29:00.839501924 +1000
+@@ -135,7 +135,7 @@
+ sig->inblock += task_io_get_inblock(tsk);
+ sig->oublock += task_io_get_oublock(tsk);
+ task_io_accounting_add(&sig->ioac, &tsk->ioac);
+- sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
++ sig->sum_sched_runtime += tsk_seruntime(tsk);
+ }
+
+ sig->nr_threads--;
+Index: linux-3.10-ck1/kernel/posix-cpu-timers.c
+===================================================================
+--- linux-3.10-ck1.orig/kernel/posix-cpu-timers.c 2013-07-09 17:28:57.182502082 +1000
++++ linux-3.10-ck1/kernel/posix-cpu-timers.c 2013-07-09 17:29:00.840501924 +1000
+@@ -498,11 +498,11 @@
+ {
+ cputime_t utime, stime;
+
+- add_device_randomness((const void*) &tsk->se.sum_exec_runtime,
++ add_device_randomness((const void*) &tsk_seruntime(tsk),
+ sizeof(unsigned long long));
+ task_cputime(tsk, &utime, &stime);
+ cleanup_timers(tsk->cpu_timers,
+- utime, stime, tsk->se.sum_exec_runtime);
++ utime, stime, tsk_seruntime(tsk));
+
+ }
+ void posix_cpu_timers_exit_group(struct task_struct *tsk)
+@@ -513,7 +513,7 @@
+ task_cputime(tsk, &utime, &stime);
+ cleanup_timers(tsk->signal->cpu_timers,
+ utime + sig->utime, stime + sig->stime,
+- tsk->se.sum_exec_runtime + sig->sum_sched_runtime);
++ tsk_seruntime(tsk) + sig->sum_sched_runtime);
+ }
+
+ static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now)
+@@ -976,7 +976,7 @@
+ struct cpu_timer_list *t = list_first_entry(timers,
+ struct cpu_timer_list,
+ entry);
+- if (!--maxfire || tsk->se.sum_exec_runtime < t->expires.sched) {
++ if (!--maxfire || tsk_seruntime(tsk) < t->expires.sched) {
+ tsk->cputime_expires.sched_exp = t->expires.sched;
+ break;
+ }
+@@ -993,7 +993,7 @@
+ ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_max);
+
+ if (hard != RLIM_INFINITY &&
+- tsk->rt.timeout > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) {
++ tsk_rttimeout(tsk) > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) {
+ /*
+ * At the hard limit, we just die.
+ * No need to calculate anything else now.
+@@ -1001,7 +1001,7 @@
+ __group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk);
+ return;
+ }
+- if (tsk->rt.timeout > DIV_ROUND_UP(soft, USEC_PER_SEC/HZ)) {
++ if (tsk_rttimeout(tsk) > DIV_ROUND_UP(soft, USEC_PER_SEC/HZ)) {
+ /*
+ * At the soft limit, send a SIGXCPU every second.
+ */
+@@ -1282,7 +1282,7 @@
+ struct task_cputime task_sample = {
+ .utime = utime,
+ .stime = stime,
+- .sum_exec_runtime = tsk->se.sum_exec_runtime
++ .sum_exec_runtime = tsk_seruntime(tsk)
+ };
+
+ if (task_cputime_expired(&task_sample, &tsk->cputime_expires))
+Index: linux-3.10-ck1/kernel/sysctl.c
+===================================================================
+--- linux-3.10-ck1.orig/kernel/sysctl.c 2013-07-09 17:28:57.173502082 +1000
++++ linux-3.10-ck1/kernel/sysctl.c 2013-07-09 17:29:00.840501924 +1000
+@@ -128,7 +128,12 @@
+ static int __maybe_unused two = 2;
+ static int __maybe_unused three = 3;
+ static unsigned long one_ul = 1;
+-static int one_hundred = 100;
++static int __maybe_unused one_hundred = 100;
++#ifdef CONFIG_SCHED_BFS
++extern int rr_interval;
++extern int sched_iso_cpu;
++static int __read_mostly one_thousand = 1000;
++#endif
+ #ifdef CONFIG_PRINTK
+ static int ten_thousand = 10000;
+ #endif
+@@ -256,7 +261,7 @@
+ { }
+ };
+
+-#ifdef CONFIG_SCHED_DEBUG
++#if defined(CONFIG_SCHED_DEBUG) && !defined(CONFIG_SCHED_BFS)
+ static int min_sched_granularity_ns = 100000; /* 100 usecs */
+ static int max_sched_granularity_ns = NSEC_PER_SEC; /* 1 second */
+ static int min_wakeup_granularity_ns; /* 0 usecs */
+@@ -273,6 +278,7 @@
+ #endif
+
+ static struct ctl_table kern_table[] = {
++#ifndef CONFIG_SCHED_BFS
+ {
+ .procname = "sched_child_runs_first",
+ .data = &sysctl_sched_child_runs_first,
+@@ -436,6 +442,7 @@
+ .extra1 = &one,
+ },
+ #endif
++#endif /* !CONFIG_SCHED_BFS */
+ #ifdef CONFIG_PROVE_LOCKING
+ {
+ .procname = "prove_locking",
+@@ -907,6 +914,26 @@
+ .proc_handler = proc_dointvec,
+ },
+ #endif
++#ifdef CONFIG_SCHED_BFS
++ {
++ .procname = "rr_interval",
++ .data = &rr_interval,
++ .maxlen = sizeof (int),
++ .mode = 0644,
++ .proc_handler = &proc_dointvec_minmax,
++ .extra1 = &one,
++ .extra2 = &one_thousand,
++ },
++ {
++ .procname = "iso_cpu",
++ .data = &sched_iso_cpu,
++ .maxlen = sizeof (int),
++ .mode = 0644,
++ .proc_handler = &proc_dointvec_minmax,
++ .extra1 = &zero,
++ .extra2 = &one_hundred,
++ },
++#endif
+ #if defined(CONFIG_S390) && defined(CONFIG_SMP)
+ {
+ .procname = "spin_retry",
+Index: linux-3.10-ck1/lib/Kconfig.debug
+===================================================================
+--- linux-3.10-ck1.orig/lib/Kconfig.debug 2013-07-09 17:28:57.137502083 +1000
++++ linux-3.10-ck1/lib/Kconfig.debug 2013-07-09 17:29:00.840501924 +1000
+@@ -940,7 +940,7 @@
+
+ config RCU_TORTURE_TEST
+ tristate "torture tests for RCU"
+- depends on DEBUG_KERNEL
++ depends on DEBUG_KERNEL && !SCHED_BFS
+ default n
+ help
+ This option provides a kernel module that runs torture tests
+Index: linux-3.10-ck1/include/linux/jiffies.h
+===================================================================
+--- linux-3.10-ck1.orig/include/linux/jiffies.h 2013-07-09 17:28:57.150502083 +1000
++++ linux-3.10-ck1/include/linux/jiffies.h 2013-07-09 17:29:00.840501924 +1000
+@@ -159,7 +159,7 @@
+ * Have the 32 bit jiffies value wrap 5 minutes after boot
+ * so jiffies wrap bugs show up earlier.
+ */
+-#define INITIAL_JIFFIES ((unsigned long)(unsigned int) (-300*HZ))
++#define INITIAL_JIFFIES ((unsigned long)(unsigned int) (-10*HZ))
+
+ /*
+ * Change timeval to jiffies, trying to avoid the
+Index: linux-3.10-ck1/drivers/cpufreq/cpufreq.c
+===================================================================
+--- linux-3.10-ck1.orig/drivers/cpufreq/cpufreq.c 2013-07-09 17:28:57.224502080 +1000
++++ linux-3.10-ck1/drivers/cpufreq/cpufreq.c 2013-07-09 17:29:00.841501924 +1000
+@@ -30,6 +30,7 @@
+ #include <linux/cpu.h>
+ #include <linux/completion.h>
+ #include <linux/mutex.h>
++#include <linux/sched.h>
+ #include <linux/syscore_ops.h>
+
+ #include <trace/events/power.h>
+@@ -1473,6 +1474,12 @@
+
+ if (cpufreq_driver->target)
+ retval = cpufreq_driver->target(policy, target_freq, relation);
++ if (likely(retval != -EINVAL)) {
++ if (target_freq == policy->max)
++ cpu_nonscaling(policy->cpu);
++ else
++ cpu_scaling(policy->cpu);
++ }
+
+ return retval;
+ }
+Index: linux-3.10-ck1/drivers/cpufreq/cpufreq_ondemand.c
+===================================================================
+--- linux-3.10-ck1.orig/drivers/cpufreq/cpufreq_ondemand.c 2013-07-09 17:28:57.214502080 +1000
++++ linux-3.10-ck1/drivers/cpufreq/cpufreq_ondemand.c 2013-07-09 17:29:00.841501924 +1000
+@@ -29,8 +29,8 @@
+ #include "cpufreq_governor.h"
+
+ /* On-demand governor macros */
+-#define DEF_FREQUENCY_DOWN_DIFFERENTIAL (10)
+-#define DEF_FREQUENCY_UP_THRESHOLD (80)
++#define DEF_FREQUENCY_DOWN_DIFFERENTIAL (26)
++#define DEF_FREQUENCY_UP_THRESHOLD (63)
+ #define DEF_SAMPLING_DOWN_FACTOR (1)
+ #define MAX_SAMPLING_DOWN_FACTOR (100000)
+ #define MICRO_FREQUENCY_DOWN_DIFFERENTIAL (3)
+@@ -160,10 +160,10 @@
+ }
+
+ /*
+- * Every sampling_rate, we check, if current idle time is less than 20%
++ * Every sampling_rate, we check, if current idle time is less than 37%
+ * (default), then we try to increase frequency. Every sampling_rate, we look
+ * for the lowest frequency which can sustain the load while keeping idle time
+- * over 30%. If such a frequency exist, we try to decrease to this frequency.
++ * over 63%. If such a frequency exist, we try to decrease to this frequency.
+ *
+ * Any frequency increase takes it to the maximum frequency. Frequency reduction
+ * happens at minimum steps of 5% (default) of current frequency
+Index: linux-3.10-ck1/kernel/sched/bfs.c
+===================================================================
+--- /dev/null 1970-01-01 00:00:00.000000000 +0000
++++ linux-3.10-ck1/kernel/sched/bfs.c 2013-07-09 17:29:00.843501924 +1000
+@@ -0,0 +1,7423 @@
++/*
++ * kernel/sched/bfs.c, was kernel/sched.c
++ *
++ * Kernel scheduler and related syscalls
++ *
++ * Copyright (C) 1991-2002 Linus Torvalds
++ *
++ * 1996-12-23 Modified by Dave Grothe to fix bugs in semaphores and
++ * make semaphores SMP safe
++ * 1998-11-19 Implemented schedule_timeout() and related stuff
++ * by Andrea Arcangeli
++ * 2002-01-04 New ultra-scalable O(1) scheduler by Ingo Molnar:
++ * hybrid priority-list and round-robin design with
++ * an array-switch method of distributing timeslices
++ * and per-CPU runqueues. Cleanups and useful suggestions
++ * by Davide Libenzi, preemptible kernel bits by Robert Love.
++ * 2003-09-03 Interactivity tuning by Con Kolivas.
++ * 2004-04-02 Scheduler domains code by Nick Piggin
++ * 2007-04-15 Work begun on replacing all interactivity tuning with a
++ * fair scheduling design by Con Kolivas.
++ * 2007-05-05 Load balancing (smp-nice) and other improvements
++ * by Peter Williams
++ * 2007-05-06 Interactivity improvements to CFS by Mike Galbraith
++ * 2007-07-01 Group scheduling enhancements by Srivatsa Vaddagiri
++ * 2007-11-29 RT balancing improvements by Steven Rostedt, Gregory Haskins,
++ * Thomas Gleixner, Mike Kravetz
++ * now Brainfuck deadline scheduling policy by Con Kolivas deletes
++ * a whole lot of those previous things.
++ */
++
++#include <linux/mm.h>
++#include <linux/module.h>
++#include <linux/nmi.h>
++#include <linux/init.h>
++#include <asm/uaccess.h>
++#include <linux/highmem.h>
++#include <asm/mmu_context.h>
++#include <linux/interrupt.h>
++#include <linux/capability.h>
++#include <linux/completion.h>
++#include <linux/kernel_stat.h>
++#include <linux/debug_locks.h>
++#include <linux/perf_event.h>
++#include <linux/security.h>
++#include <linux/notifier.h>
++#include <linux/profile.h>
++#include <linux/freezer.h>
++#include <linux/vmalloc.h>
++#include <linux/blkdev.h>
++#include <linux/delay.h>
++#include <linux/smp.h>
++#include <linux/threads.h>
++#include <linux/timer.h>
++#include <linux/rcupdate.h>
++#include <linux/cpu.h>
++#include <linux/cpuset.h>
++#include <linux/cpumask.h>
++#include <linux/percpu.h>
++#include <linux/proc_fs.h>
++#include <linux/seq_file.h>
++#include <linux/syscalls.h>
++#include <linux/times.h>
++#include <linux/tsacct_kern.h>
++#include <linux/kprobes.h>
++#include <linux/delayacct.h>
++#include <linux/log2.h>
++#include <linux/bootmem.h>
++#include <linux/ftrace.h>
++#include <linux/slab.h>
++#include <linux/init_task.h>
++#include <linux/binfmts.h>
++#include <linux/context_tracking.h>
++
++#include <asm/switch_to.h>
++#include <asm/tlb.h>
++#include <asm/unistd.h>
++#include <asm/mutex.h>
++#ifdef CONFIG_PARAVIRT
++#include <asm/paravirt.h>
++#endif
++
++#include "cpupri.h"
++#include "../workqueue_internal.h"
++#include "../smpboot.h"
++
++#define CREATE_TRACE_POINTS
++#include <trace/events/sched.h>
++
++#define rt_prio(prio) unlikely((prio) < MAX_RT_PRIO)
++#define rt_task(p) rt_prio((p)->prio)
++#define rt_queue(rq) rt_prio((rq)->rq_prio)
++#define batch_task(p) (unlikely((p)->policy == SCHED_BATCH))
++#define is_rt_policy(policy) ((policy) == SCHED_FIFO || \
++ (policy) == SCHED_RR)
++#define has_rt_policy(p) unlikely(is_rt_policy((p)->policy))
++#define idleprio_task(p) unlikely((p)->policy == SCHED_IDLEPRIO)
++#define iso_task(p) unlikely((p)->policy == SCHED_ISO)
++#define iso_queue(rq) unlikely((rq)->rq_policy == SCHED_ISO)
++#define rq_running_iso(rq) ((rq)->rq_prio == ISO_PRIO)
++
++#define ISO_PERIOD ((5 * HZ * grq.noc) + 1)
++
++/*
++ * Convert user-nice values [ -20 ... 0 ... 19 ]
++ * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
++ * and back.
++ */
++#define NICE_TO_PRIO(nice) (MAX_RT_PRIO + (nice) + 20)
++#define PRIO_TO_NICE(prio) ((prio) - MAX_RT_PRIO - 20)
++#define TASK_NICE(p) PRIO_TO_NICE((p)->static_prio)
++
++/*
++ * 'User priority' is the nice value converted to something we
++ * can work with better when scaling various scheduler parameters,
++ * it's a [ 0 ... 39 ] range.
++ */
++#define USER_PRIO(p) ((p) - MAX_RT_PRIO)
++#define TASK_USER_PRIO(p) USER_PRIO((p)->static_prio)
++#define MAX_USER_PRIO (USER_PRIO(MAX_PRIO))
++#define SCHED_PRIO(p) ((p) + MAX_RT_PRIO)
++#define STOP_PRIO (MAX_RT_PRIO - 1)
++
++/*
++ * Some helpers for converting to/from various scales. Use shifts to get
++ * approximate multiples of ten for less overhead.
++ */
++#define JIFFIES_TO_NS(TIME) ((TIME) * (1000000000 / HZ))
++#define JIFFY_NS (1000000000 / HZ)
++#define HALF_JIFFY_NS (1000000000 / HZ / 2)
++#define HALF_JIFFY_US (1000000 / HZ / 2)
++#define MS_TO_NS(TIME) ((TIME) << 20)
++#define MS_TO_US(TIME) ((TIME) << 10)
++#define NS_TO_MS(TIME) ((TIME) >> 20)
++#define NS_TO_US(TIME) ((TIME) >> 10)
++
++#define RESCHED_US (100) /* Reschedule if less than this many μs left */
++
++void print_scheduler_version(void)
++{
++ printk(KERN_INFO "BFS CPU scheduler v0.440 by Con Kolivas.\n");
++}
++
++/*
++ * This is the time all tasks within the same priority round robin.
++ * Value is in ms and set to a minimum of 6ms. Scales with number of cpus.
++ * Tunable via /proc interface.
++ */
++int rr_interval __read_mostly = 6;
++
++/*
++ * sched_iso_cpu - sysctl which determines the cpu percentage SCHED_ISO tasks
++ * are allowed to run five seconds as real time tasks. This is the total over
++ * all online cpus.
++ */
++int sched_iso_cpu __read_mostly = 70;
++
++/*
++ * The relative length of deadline for each priority(nice) level.
++ */
++static int prio_ratios[PRIO_RANGE] __read_mostly;
++
++/*
++ * The quota handed out to tasks of all priority levels when refilling their
++ * time_slice.
++ */
++static inline int timeslice(void)
++{
++ return MS_TO_US(rr_interval);
++}
++
++/*
++ * The global runqueue data that all CPUs work off. Data is protected either
++ * by the global grq lock, or the discrete lock that precedes the data in this
++ * struct.
++ */
++struct global_rq {
++ raw_spinlock_t lock;
++ unsigned long nr_running;
++ unsigned long nr_uninterruptible;
++ unsigned long long nr_switches;
++ struct list_head queue[PRIO_LIMIT];
++ DECLARE_BITMAP(prio_bitmap, PRIO_LIMIT + 1);
++#ifdef CONFIG_SMP
++ unsigned long qnr; /* queued not running */
++ cpumask_t cpu_idle_map;
++ bool idle_cpus;
++#endif
++ int noc; /* num_online_cpus stored and updated when it changes */
++ u64 niffies; /* Nanosecond jiffies */
++ unsigned long last_jiffy; /* Last jiffy we updated niffies */
++
++ raw_spinlock_t iso_lock;
++ int iso_ticks;
++ bool iso_refractory;
++};
++
++#ifdef CONFIG_SMP
++
++/*
++ * We add the notion of a root-domain which will be used to define per-domain
++ * variables. Each exclusive cpuset essentially defines an island domain by
++ * fully partitioning the member cpus from any other cpuset. Whenever a new
++ * exclusive cpuset is created, we also create and attach a new root-domain
++ * object.
++ *
++ */
++struct root_domain {
++ atomic_t refcount;
++ atomic_t rto_count;
++ struct rcu_head rcu;
++ cpumask_var_t span;
++ cpumask_var_t online;
++
++ /*
++ * The "RT overload" flag: it gets set if a CPU has more than
++ * one runnable RT task.
++ */
++ cpumask_var_t rto_mask;
++ struct cpupri cpupri;
++};
++
++/*
++ * By default the system creates a single root-domain with all cpus as
++ * members (mimicking the global state we have today).
++ */
++static struct root_domain def_root_domain;
++
++#endif /* CONFIG_SMP */
++
++/* There can be only one */
++static struct global_rq grq;
++
++/*
++ * This is the main, per-CPU runqueue data structure.
++ * This data should only be modified by the local cpu.
++ */
++struct rq {
++ struct task_struct *curr, *idle, *stop;
++ struct mm_struct *prev_mm;
++
++ /* Stored data about rq->curr to work outside grq lock */
++ u64 rq_deadline;
++ unsigned int rq_policy;
++ int rq_time_slice;
++ u64 rq_last_ran;
++ int rq_prio;
++ bool rq_running; /* There is a task running */
++
++ /* Accurate timekeeping data */
++ u64 timekeep_clock;
++ unsigned long user_pc, nice_pc, irq_pc, softirq_pc, system_pc,
++ iowait_pc, idle_pc;
++ atomic_t nr_iowait;
++
++#ifdef CONFIG_SMP
++ int cpu; /* cpu of this runqueue */
++ bool online;
++ bool scaling; /* This CPU is managed by a scaling CPU freq governor */
++ struct task_struct *sticky_task;
++
++ struct root_domain *rd;
++ struct sched_domain *sd;
++ int *cpu_locality; /* CPU relative cache distance */
++#ifdef CONFIG_SCHED_SMT
++ bool (*siblings_idle)(int cpu);
++ /* See if all smt siblings are idle */
++ cpumask_t smt_siblings;
++#endif /* CONFIG_SCHED_SMT */
++#ifdef CONFIG_SCHED_MC
++ bool (*cache_idle)(int cpu);
++ /* See if all cache siblings are idle */
++ cpumask_t cache_siblings;
++#endif /* CONFIG_SCHED_MC */
++ u64 last_niffy; /* Last time this RQ updated grq.niffies */
++#endif /* CONFIG_SMP */
++#ifdef CONFIG_IRQ_TIME_ACCOUNTING
++ u64 prev_irq_time;
++#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
++#ifdef CONFIG_PARAVIRT
++ u64 prev_steal_time;
++#endif /* CONFIG_PARAVIRT */
++#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
++ u64 prev_steal_time_rq;
++#endif /* CONFIG_PARAVIRT_TIME_ACCOUNTING */
++
++ u64 clock, old_clock, last_tick;
++ u64 clock_task;
++ bool dither;
++
++#ifdef CONFIG_SCHEDSTATS
++
++ /* latency stats */
++ struct sched_info rq_sched_info;
++ unsigned long long rq_cpu_time;
++ /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */
++
++ /* sys_sched_yield() stats */
++ unsigned int yld_count;
++
++ /* schedule() stats */
++ unsigned int sched_switch;
++ unsigned int sched_count;
++ unsigned int sched_goidle;
++
++ /* try_to_wake_up() stats */
++ unsigned int ttwu_count;
++ unsigned int ttwu_local;
++#endif /* CONFIG_SCHEDSTATS */
++};
++
++DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
++static DEFINE_MUTEX(sched_hotcpu_mutex);
++
++#ifdef CONFIG_SMP
++#define cpu_rq(cpu) (&per_cpu(runqueues, (cpu)))
++#define this_rq() (&__get_cpu_var(runqueues))
++#define task_rq(p) cpu_rq(task_cpu(p))
++#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
++/*
++ * sched_domains_mutex serialises calls to init_sched_domains,
++ * detach_destroy_domains and partition_sched_domains.
++ */
++static DEFINE_MUTEX(sched_domains_mutex);
++
++/*
++ * By default the system creates a single root-domain with all cpus as
++ * members (mimicking the global state we have today).
++ */
++static struct root_domain def_root_domain;
++
++int __weak arch_sd_sibling_asym_packing(void)
++{
++ return 0*SD_ASYM_PACKING;
++}
++#endif /* CONFIG_SMP */
++
++#define rcu_dereference_check_sched_domain(p) \
++ rcu_dereference_check((p), \
++ lockdep_is_held(&sched_domains_mutex))
++
++/*
++ * The domain tree (rq->sd) is protected by RCU's quiescent state transition.
++ * See detach_destroy_domains: synchronize_sched for details.
++ *
++ * The domain tree of any CPU may only be accessed from within
++ * preempt-disabled sections.
++ */
++#define for_each_domain(cpu, __sd) \
++ for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); __sd; __sd = __sd->parent)
++
++static inline void update_rq_clock(struct rq *rq);
++
++/*
++ * Sanity check should sched_clock return bogus values. We make sure it does
++ * not appear to go backwards, and use jiffies to determine the maximum and
++ * minimum it could possibly have increased, and round down to the nearest
++ * jiffy when it falls outside this.
++ */
++static inline void niffy_diff(s64 *niff_diff, int jiff_diff)
++{
++ unsigned long min_diff, max_diff;
++
++ if (jiff_diff > 1)
++ min_diff = JIFFIES_TO_NS(jiff_diff - 1);
++ else
++ min_diff = 1;
++ /* Round up to the nearest tick for maximum */
++ max_diff = JIFFIES_TO_NS(jiff_diff + 1);
++
++ if (unlikely(*niff_diff < min_diff || *niff_diff > max_diff))
++ *niff_diff = min_diff;
++}
++
++#ifdef CONFIG_SMP
++static inline int cpu_of(struct rq *rq)
++{
++ return rq->cpu;
++}
++
++/*
++ * Niffies are a globally increasing nanosecond counter. Whenever a runqueue
++ * clock is updated with the grq.lock held, it is an opportunity to update the
++ * niffies value. Any CPU can update it by adding how much its clock has
++ * increased since it last updated niffies, minus any added niffies by other
++ * CPUs.
++ */
++static inline void update_clocks(struct rq *rq)
++{
++ s64 ndiff;
++ long jdiff;
++
++ update_rq_clock(rq);
++ ndiff = rq->clock - rq->old_clock;
++ /* old_clock is only updated when we are updating niffies */
++ rq->old_clock = rq->clock;
++ ndiff -= grq.niffies - rq->last_niffy;
++ jdiff = jiffies - grq.last_jiffy;
++ niffy_diff(&ndiff, jdiff);
++ grq.last_jiffy += jdiff;
++ grq.niffies += ndiff;
++ rq->last_niffy = grq.niffies;
++}
++#else /* CONFIG_SMP */
++static struct rq *uprq;
++#define cpu_rq(cpu) (uprq)
++#define this_rq() (uprq)
++#define task_rq(p) (uprq)
++#define cpu_curr(cpu) ((uprq)->curr)
++static inline int cpu_of(struct rq *rq)
++{
++ return 0;
++}
++
++static inline void update_clocks(struct rq *rq)
++{
++ s64 ndiff;
++ long jdiff;
++
++ update_rq_clock(rq);
++ ndiff = rq->clock - rq->old_clock;
++ rq->old_clock = rq->clock;
++ jdiff = jiffies - grq.last_jiffy;
++ niffy_diff(&ndiff, jdiff);
++ grq.last_jiffy += jdiff;
++ grq.niffies += ndiff;
++}
++#endif
++#define raw_rq() (&__raw_get_cpu_var(runqueues))
++
++#include "stats.h"
++
++#ifndef prepare_arch_switch
++# define prepare_arch_switch(next) do { } while (0)
++#endif
++#ifndef finish_arch_switch
++# define finish_arch_switch(prev) do { } while (0)
++#endif
++#ifndef finish_arch_post_lock_switch
++# define finish_arch_post_lock_switch() do { } while (0)
++#endif
++
++/*
++ * All common locking functions performed on grq.lock. rq->clock is local to
++ * the CPU accessing it so it can be modified just with interrupts disabled
++ * when we're not updating niffies.
++ * Looking up task_rq must be done under grq.lock to be safe.
++ */
++static void update_rq_clock_task(struct rq *rq, s64 delta);
++
++static inline void update_rq_clock(struct rq *rq)
++{
++ s64 delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
++
++ rq->clock += delta;
++ update_rq_clock_task(rq, delta);
++}
++
++static inline bool task_running(struct task_struct *p)
++{
++ return p->on_cpu;
++}
++
++static inline void grq_lock(void)
++ __acquires(grq.lock)
++{
++ raw_spin_lock(&grq.lock);
++}
++
++static inline void grq_unlock(void)
++ __releases(grq.lock)
++{
++ raw_spin_unlock(&grq.lock);
++}
++
++static inline void grq_lock_irq(void)
++ __acquires(grq.lock)
++{
++ raw_spin_lock_irq(&grq.lock);
++}
++
++static inline void time_lock_grq(struct rq *rq)
++ __acquires(grq.lock)
++{
++ grq_lock();
++ update_clocks(rq);
++}
++
++static inline void grq_unlock_irq(void)
++ __releases(grq.lock)
++{
++ raw_spin_unlock_irq(&grq.lock);
++}
++
++static inline void grq_lock_irqsave(unsigned long *flags)
++ __acquires(grq.lock)
++{
++ raw_spin_lock_irqsave(&grq.lock, *flags);
++}
++
++static inline void grq_unlock_irqrestore(unsigned long *flags)
++ __releases(grq.lock)
++{
++ raw_spin_unlock_irqrestore(&grq.lock, *flags);
++}
++
++static inline struct rq
++*task_grq_lock(struct task_struct *p, unsigned long *flags)
++ __acquires(grq.lock)
++{
++ grq_lock_irqsave(flags);
++ return task_rq(p);
++}
++
++static inline struct rq
++*time_task_grq_lock(struct task_struct *p, unsigned long *flags)
++ __acquires(grq.lock)
++{
++ struct rq *rq = task_grq_lock(p, flags);
++ update_clocks(rq);
++ return rq;
++}
++
++static inline struct rq *task_grq_lock_irq(struct task_struct *p)
++ __acquires(grq.lock)
++{
++ grq_lock_irq();
++ return task_rq(p);
++}
++
++static inline void time_task_grq_lock_irq(struct task_struct *p)
++ __acquires(grq.lock)
++{
++ struct rq *rq = task_grq_lock_irq(p);
++ update_clocks(rq);
++}
++
++static inline void task_grq_unlock_irq(void)
++ __releases(grq.lock)
++{
++ grq_unlock_irq();
++}
++
++static inline void task_grq_unlock(unsigned long *flags)
++ __releases(grq.lock)
++{
++ grq_unlock_irqrestore(flags);
++}
++
++/**
++ * grunqueue_is_locked
++ *
++ * Returns true if the global runqueue is locked.
++ * This interface allows printk to be called with the runqueue lock
++ * held and know whether or not it is OK to wake up the klogd.
++ */
++bool grunqueue_is_locked(void)
++{
++ return raw_spin_is_locked(&grq.lock);
++}
++
++void grq_unlock_wait(void)
++ __releases(grq.lock)
++{
++ smp_mb(); /* spin-unlock-wait is not a full memory barrier */
++ raw_spin_unlock_wait(&grq.lock);
++}
++
++static inline void time_grq_lock(struct rq *rq, unsigned long *flags)
++ __acquires(grq.lock)
++{
++ local_irq_save(*flags);
++ time_lock_grq(rq);
++}
++
++static inline struct rq *__task_grq_lock(struct task_struct *p)
++ __acquires(grq.lock)
++{
++ grq_lock();
++ return task_rq(p);
++}
++
++static inline void __task_grq_unlock(void)
++ __releases(grq.lock)
++{
++ grq_unlock();
++}
++
++/*
++ * Look for any tasks *anywhere* that are running nice 0 or better. We do
++ * this lockless for overhead reasons since the occasional wrong result
++ * is harmless.
++ */
++bool above_background_load(void)
++{
++ int cpu;
++
++ for_each_online_cpu(cpu) {
++ struct task_struct *cpu_curr = cpu_rq(cpu)->curr;
++
++ if (unlikely(!cpu_curr))
++ continue;
++ if (PRIO_TO_NICE(cpu_curr->static_prio) < 1) {
++ return true;
++ }
++ }
++ return false;
++}
++
++#ifndef __ARCH_WANT_UNLOCKED_CTXSW
++static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
++{
++}
++
++static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
++{
++#ifdef CONFIG_DEBUG_SPINLOCK
++ /* this is a valid case when another task releases the spinlock */
++ grq.lock.owner = current;
++#endif
++ /*
++ * If we are tracking spinlock dependencies then we have to
++ * fix up the runqueue lock - which gets 'carried over' from
++ * prev into current:
++ */
++ spin_acquire(&grq.lock.dep_map, 0, 0, _THIS_IP_);
++
++ grq_unlock_irq();
++}
++
++#else /* __ARCH_WANT_UNLOCKED_CTXSW */
++
++static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
++{
++#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
++ grq_unlock_irq();
++#else
++ grq_unlock();
++#endif
++}
++
++static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
++{
++ smp_wmb();
++#ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW
++ local_irq_enable();
++#endif
++}
++#endif /* __ARCH_WANT_UNLOCKED_CTXSW */
++
++static inline bool deadline_before(u64 deadline, u64 time)
++{
++ return (deadline < time);
++}
++
++static inline bool deadline_after(u64 deadline, u64 time)
++{
++ return (deadline > time);
++}
++
++/*
++ * A task that is queued but not running will be on the grq run list.
++ * A task that is not running or queued will not be on the grq run list.
++ * A task that is currently running will have ->on_cpu set but not on the
++ * grq run list.
++ */
++static inline bool task_queued(struct task_struct *p)
++{
++ return (!list_empty(&p->run_list));
++}
++
++/*
++ * Removing from the global runqueue. Enter with grq locked.
++ */
++static void dequeue_task(struct task_struct *p)
++{
++ list_del_init(&p->run_list);
++ if (list_empty(grq.queue + p->prio))
++ __clear_bit(p->prio, grq.prio_bitmap);
++}
++
++/*
++ * To determine if it's safe for a task of SCHED_IDLEPRIO to actually run as
++ * an idle task, we ensure none of the following conditions are met.
++ */
++static bool idleprio_suitable(struct task_struct *p)
++{
++ return (!freezing(p) && !signal_pending(p) &&
++ !(task_contributes_to_load(p)) && !(p->flags & (PF_EXITING)));
++}
++
++/*
++ * To determine if a task of SCHED_ISO can run in pseudo-realtime, we check
++ * that the iso_refractory flag is not set.
++ */
++static bool isoprio_suitable(void)
++{
++ return !grq.iso_refractory;
++}
++
++/*
++ * Adding to the global runqueue. Enter with grq locked.
++ */
++static void enqueue_task(struct task_struct *p)
++{
++ if (!rt_task(p)) {
++ /* Check it hasn't gotten rt from PI */
++ if ((idleprio_task(p) && idleprio_suitable(p)) ||
++ (iso_task(p) && isoprio_suitable()))
++ p->prio = p->normal_prio;
++ else
++ p->prio = NORMAL_PRIO;
++ }
++ __set_bit(p->prio, grq.prio_bitmap);
++ list_add_tail(&p->run_list, grq.queue + p->prio);
++ sched_info_queued(p);
++}
++
++/* Only idle task does this as a real time task*/
++static inline void enqueue_task_head(struct task_struct *p)
++{
++ __set_bit(p->prio, grq.prio_bitmap);
++ list_add(&p->run_list, grq.queue + p->prio);
++ sched_info_queued(p);
++}
++
++static inline void requeue_task(struct task_struct *p)
++{
++ sched_info_queued(p);
++}
++
++/*
++ * Returns the relative length of deadline all compared to the shortest
++ * deadline which is that of nice -20.
++ */
++static inline int task_prio_ratio(struct task_struct *p)
++{
++ return prio_ratios[TASK_USER_PRIO(p)];
++}
++
++/*
++ * task_timeslice - all tasks of all priorities get the exact same timeslice
++ * length. CPU distribution is handled by giving different deadlines to
++ * tasks of different priorities. Use 128 as the base value for fast shifts.
++ */
++static inline int task_timeslice(struct task_struct *p)
++{
++ return (rr_interval * task_prio_ratio(p) / 128);
++}
++
++#ifdef CONFIG_SMP
++/*
++ * qnr is the "queued but not running" count which is the total number of
++ * tasks on the global runqueue list waiting for cpu time but not actually
++ * currently running on a cpu.
++ */
++static inline void inc_qnr(void)
++{
++ grq.qnr++;
++}
++
++static inline void dec_qnr(void)
++{
++ grq.qnr--;
++}
++
++static inline int queued_notrunning(void)
++{
++ return grq.qnr;
++}
++
++/*
++ * The cpu_idle_map stores a bitmap of all the CPUs currently idle to
++ * allow easy lookup of whether any suitable idle CPUs are available.
++ * It's cheaper to maintain a binary yes/no if there are any idle CPUs on the
++ * idle_cpus variable than to do a full bitmask check when we are busy.
++ */
++static inline void set_cpuidle_map(int cpu)
++{
++ if (likely(cpu_online(cpu))) {
++ cpu_set(cpu, grq.cpu_idle_map);
++ grq.idle_cpus = true;
++ }
++}
++
++static inline void clear_cpuidle_map(int cpu)
++{
++ cpu_clear(cpu, grq.cpu_idle_map);
++ if (cpus_empty(grq.cpu_idle_map))
++ grq.idle_cpus = false;
++}
++
++static bool suitable_idle_cpus(struct task_struct *p)
++{
++ if (!grq.idle_cpus)
++ return false;
++ return (cpus_intersects(p->cpus_allowed, grq.cpu_idle_map));
++}
++
++#define CPUIDLE_DIFF_THREAD (1)
++#define CPUIDLE_DIFF_CORE (2)
++#define CPUIDLE_CACHE_BUSY (4)
++#define CPUIDLE_DIFF_CPU (8)
++#define CPUIDLE_THREAD_BUSY (16)
++#define CPUIDLE_DIFF_NODE (32)
++
++static void resched_task(struct task_struct *p);
++
++/*
++ * The best idle CPU is chosen according to the CPUIDLE ranking above where the
++ * lowest value would give the most suitable CPU to schedule p onto next. The
++ * order works out to be the following:
++ *
++ * Same core, idle or busy cache, idle or busy threads
++ * Other core, same cache, idle or busy cache, idle threads.
++ * Same node, other CPU, idle cache, idle threads.
++ * Same node, other CPU, busy cache, idle threads.
++ * Other core, same cache, busy threads.
++ * Same node, other CPU, busy threads.
++ * Other node, other CPU, idle cache, idle threads.
++ * Other node, other CPU, busy cache, idle threads.
++ * Other node, other CPU, busy threads.
++ */
++static void
++resched_best_mask(int best_cpu, struct rq *rq, cpumask_t *tmpmask)
++{
++ unsigned int best_ranking = CPUIDLE_DIFF_NODE | CPUIDLE_THREAD_BUSY |
++ CPUIDLE_DIFF_CPU | CPUIDLE_CACHE_BUSY | CPUIDLE_DIFF_CORE |
++ CPUIDLE_DIFF_THREAD;
++ int cpu_tmp;
++
++ if (cpu_isset(best_cpu, *tmpmask))
++ goto out;
++
++ for_each_cpu_mask(cpu_tmp, *tmpmask) {
++ unsigned int ranking;
++ struct rq *tmp_rq;
++
++ ranking = 0;
++ tmp_rq = cpu_rq(cpu_tmp);
++
++#ifdef CONFIG_NUMA
++ if (rq->cpu_locality[cpu_tmp] > 3)
++ ranking |= CPUIDLE_DIFF_NODE;
++ else
++#endif
++ if (rq->cpu_locality[cpu_tmp] > 2)
++ ranking |= CPUIDLE_DIFF_CPU;
++#ifdef CONFIG_SCHED_MC
++ if (rq->cpu_locality[cpu_tmp] == 2)
++ ranking |= CPUIDLE_DIFF_CORE;
++ if (!(tmp_rq->cache_idle(cpu_tmp)))
++ ranking |= CPUIDLE_CACHE_BUSY;
++#endif
++#ifdef CONFIG_SCHED_SMT
++ if (rq->cpu_locality[cpu_tmp] == 1)
++ ranking |= CPUIDLE_DIFF_THREAD;
++ if (!(tmp_rq->siblings_idle(cpu_tmp)))
++ ranking |= CPUIDLE_THREAD_BUSY;
++#endif
++ if (ranking < best_ranking) {
++ best_cpu = cpu_tmp;
++ best_ranking = ranking;
++ }
++ }
++out:
++ resched_task(cpu_rq(best_cpu)->curr);
++}
++
++bool cpus_share_cache(int this_cpu, int that_cpu)
++{
++ struct rq *this_rq = cpu_rq(this_cpu);
++
++ return (this_rq->cpu_locality[that_cpu] < 3);
++}
++
++static void resched_best_idle(struct task_struct *p)
++{
++ cpumask_t tmpmask;
++
++ cpus_and(tmpmask, p->cpus_allowed, grq.cpu_idle_map);
++ resched_best_mask(task_cpu(p), task_rq(p), &tmpmask);
++}
++
++static inline void resched_suitable_idle(struct task_struct *p)
++{
++ if (suitable_idle_cpus(p))
++ resched_best_idle(p);
++}
++/*
++ * Flags to tell us whether this CPU is running a CPU frequency governor that
++ * has slowed its speed or not. No locking required as the very rare wrongly
++ * read value would be harmless.
++ */
++void cpu_scaling(int cpu)
++{
++ cpu_rq(cpu)->scaling = true;
++}
++
++void cpu_nonscaling(int cpu)
++{
++ cpu_rq(cpu)->scaling = false;
++}
++
++static inline bool scaling_rq(struct rq *rq)
++{
++ return rq->scaling;
++}
++
++static inline int locality_diff(struct task_struct *p, struct rq *rq)
++{
++ return rq->cpu_locality[task_cpu(p)];
++}
++#else /* CONFIG_SMP */
++static inline void inc_qnr(void)
++{
++}
++
++static inline void dec_qnr(void)
++{
++}
++
++static inline int queued_notrunning(void)
++{
++ return grq.nr_running;
++}
++
++static inline void set_cpuidle_map(int cpu)
++{
++}
++
++static inline void clear_cpuidle_map(int cpu)
++{
++}
++
++static inline bool suitable_idle_cpus(struct task_struct *p)
++{
++ return uprq->curr == uprq->idle;
++}
++
++static inline void resched_suitable_idle(struct task_struct *p)
++{
++}
++
++void cpu_scaling(int __unused)
++{
++}
++
++void cpu_nonscaling(int __unused)
++{
++}
++
++/*
++ * Although CPUs can scale in UP, there is nowhere else for tasks to go so this
++ * always returns 0.
++ */
++static inline bool scaling_rq(struct rq *rq)
++{
++ return false;
++}
++
++static inline int locality_diff(struct task_struct *p, struct rq *rq)
++{
++ return 0;
++}
++#endif /* CONFIG_SMP */
++EXPORT_SYMBOL_GPL(cpu_scaling);
++EXPORT_SYMBOL_GPL(cpu_nonscaling);
++
++/*
++ * activate_idle_task - move idle task to the _front_ of runqueue.
++ */
++static inline void activate_idle_task(struct task_struct *p)
++{
++ enqueue_task_head(p);
++ grq.nr_running++;
++ inc_qnr();
++}
++
++static inline int normal_prio(struct task_struct *p)
++{
++ if (has_rt_policy(p))
++ return MAX_RT_PRIO - 1 - p->rt_priority;
++ if (idleprio_task(p))
++ return IDLE_PRIO;
++ if (iso_task(p))
++ return ISO_PRIO;
++ return NORMAL_PRIO;
++}
++
++/*
++ * Calculate the current priority, i.e. the priority
++ * taken into account by the scheduler. This value might
++ * be boosted by RT tasks as it will be RT if the task got
++ * RT-boosted. If not then it returns p->normal_prio.
++ */
++static int effective_prio(struct task_struct *p)
++{
++ p->normal_prio = normal_prio(p);
++ /*
++ * If we are RT tasks or we were boosted to RT priority,
++ * keep the priority unchanged. Otherwise, update priority
++ * to the normal priority:
++ */
++ if (!rt_prio(p->prio))
++ return p->normal_prio;
++ return p->prio;
++}
++
++/*
++ * activate_task - move a task to the runqueue. Enter with grq locked.
++ */
++static void activate_task(struct task_struct *p, struct rq *rq)
++{
++ update_clocks(rq);
++
++ /*
++ * Sleep time is in units of nanosecs, so shift by 20 to get a
++ * milliseconds-range estimation of the amount of time that the task
++ * spent sleeping:
++ */
++ if (unlikely(prof_on == SLEEP_PROFILING)) {
++ if (p->state == TASK_UNINTERRUPTIBLE)
++ profile_hits(SLEEP_PROFILING, (void *)get_wchan(p),
++ (rq->clock_task - p->last_ran) >> 20);
++ }
++
++ p->prio = effective_prio(p);
++ if (task_contributes_to_load(p))
++ grq.nr_uninterruptible--;
++ enqueue_task(p);
++ grq.nr_running++;
++ inc_qnr();
++}
++
++static inline void clear_sticky(struct task_struct *p);
++
++/*
++ * deactivate_task - If it's running, it's not on the grq and we can just
++ * decrement the nr_running. Enter with grq locked.
++ */
++static inline void deactivate_task(struct task_struct *p)
++{
++ if (task_contributes_to_load(p))
++ grq.nr_uninterruptible++;
++ grq.nr_running--;
++ clear_sticky(p);
++}
++
++static ATOMIC_NOTIFIER_HEAD(task_migration_notifier);
++
++void register_task_migration_notifier(struct notifier_block *n)
++{
++ atomic_notifier_chain_register(&task_migration_notifier, n);
++}
++
++#ifdef CONFIG_SMP
++void set_task_cpu(struct task_struct *p, unsigned int cpu)
++{
++#ifdef CONFIG_LOCKDEP
++ /*
++ * The caller should hold grq lock.
++ */
++ WARN_ON_ONCE(debug_locks && !lockdep_is_held(&grq.lock));
++#endif
++ trace_sched_migrate_task(p, cpu);
++ if (task_cpu(p) != cpu)
++ perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, NULL, 0);
++
++ /*
++ * After ->cpu is set up to a new value, task_grq_lock(p, ...) can be
++ * successfully executed on another CPU. We must ensure that updates of
++ * per-task data have been completed by this moment.
++ */
++ smp_wmb();
++ task_thread_info(p)->cpu = cpu;
++}
++
++static inline void clear_sticky(struct task_struct *p)
++{
++ p->sticky = false;
++}
++
++static inline bool task_sticky(struct task_struct *p)
++{
++ return p->sticky;
++}
++
++/* Reschedule the best idle CPU that is not this one. */
++static void
++resched_closest_idle(struct rq *rq, int cpu, struct task_struct *p)
++{
++ cpumask_t tmpmask;
++
++ cpus_and(tmpmask, p->cpus_allowed, grq.cpu_idle_map);
++ cpu_clear(cpu, tmpmask);
++ if (cpus_empty(tmpmask))
++ return;
++ resched_best_mask(cpu, rq, &tmpmask);
++}
++
++/*
++ * We set the sticky flag on a task that is descheduled involuntarily meaning
++ * it is awaiting further CPU time. If the last sticky task is still sticky
++ * but unlucky enough to not be the next task scheduled, we unstick it and try
++ * to find it an idle CPU. Realtime tasks do not stick to minimise their
++ * latency at all times.
++ */
++static inline void
++swap_sticky(struct rq *rq, int cpu, struct task_struct *p)
++{
++ if (rq->sticky_task) {
++ if (rq->sticky_task == p) {
++ p->sticky = true;
++ return;
++ }
++ if (task_sticky(rq->sticky_task)) {
++ clear_sticky(rq->sticky_task);
++ resched_closest_idle(rq, cpu, rq->sticky_task);
++ }
++ }
++ if (!rt_task(p)) {
++ p->sticky = true;
++ rq->sticky_task = p;
++ } else {
++ resched_closest_idle(rq, cpu, p);
++ rq->sticky_task = NULL;
++ }
++}
++
++static inline void unstick_task(struct rq *rq, struct task_struct *p)
++{
++ rq->sticky_task = NULL;
++ clear_sticky(p);
++}
++#else
++static inline void clear_sticky(struct task_struct *p)
++{
++}
++
++static inline bool task_sticky(struct task_struct *p)
++{
++ return false;
++}
++
++static inline void
++swap_sticky(struct rq *rq, int cpu, struct task_struct *p)
++{
++}
++
++static inline void unstick_task(struct rq *rq, struct task_struct *p)
++{
++}
++#endif
++
++/*
++ * Move a task off the global queue and take it to a cpu for it will
++ * become the running task.
++ */
++static inline void take_task(int cpu, struct task_struct *p)
++{
++ set_task_cpu(p, cpu);
++ dequeue_task(p);
++ clear_sticky(p);
++ dec_qnr();
++}
++
++/*
++ * Returns a descheduling task to the grq runqueue unless it is being
++ * deactivated.
++ */
++static inline void return_task(struct task_struct *p, bool deactivate)
++{
++ if (deactivate)
++ deactivate_task(p);
++ else {
++ inc_qnr();
++ enqueue_task(p);
++ }
++}
++
++/*
++ * resched_task - mark a task 'to be rescheduled now'.
++ *
++ * On UP this means the setting of the need_resched flag, on SMP it
++ * might also involve a cross-CPU call to trigger the scheduler on
++ * the target CPU.
++ */
++#ifdef CONFIG_SMP
++
++#ifndef tsk_is_polling
++#define tsk_is_polling(t) 0
++#endif
++
++static void resched_task(struct task_struct *p)
++{
++ int cpu;
++
++ assert_raw_spin_locked(&grq.lock);
++
++ if (unlikely(test_tsk_thread_flag(p, TIF_NEED_RESCHED)))
++ return;
++
++ set_tsk_thread_flag(p, TIF_NEED_RESCHED);
++
++ cpu = task_cpu(p);
++ if (cpu == smp_processor_id())
++ return;
++
++ /* NEED_RESCHED must be visible before we test polling */
++ smp_mb();
++ if (!tsk_is_polling(p))
++ smp_send_reschedule(cpu);
++}
++
++#else
++static inline void resched_task(struct task_struct *p)
++{
++ assert_raw_spin_locked(&grq.lock);
++ set_tsk_need_resched(p);
++}
++#endif
++
++/**
++ * task_curr - is this task currently executing on a CPU?
++ * @p: the task in question.
++ */
++inline int task_curr(const struct task_struct *p)
++{
++ return cpu_curr(task_cpu(p)) == p;
++}
++
++#ifdef CONFIG_SMP
++struct migration_req {
++ struct task_struct *task;
++ int dest_cpu;
++};
++
++/*
++ * wait_task_inactive - wait for a thread to unschedule.
++ *
++ * If @match_state is nonzero, it's the @p->state value just checked and
++ * not expected to change. If it changes, i.e. @p might have woken up,
++ * then return zero. When we succeed in waiting for @p to be off its CPU,
++ * we return a positive number (its total switch count). If a second call
++ * a short while later returns the same number, the caller can be sure that
++ * @p has remained unscheduled the whole time.
++ *
++ * The caller must ensure that the task *will* unschedule sometime soon,
++ * else this function might spin for a *long* time. This function can't
++ * be called with interrupts off, or it may introduce deadlock with
++ * smp_call_function() if an IPI is sent by the same process we are
++ * waiting to become inactive.
++ */
++unsigned long wait_task_inactive(struct task_struct *p, long match_state)
++{
++ unsigned long flags;
++ bool running, on_rq;
++ unsigned long ncsw;
++ struct rq *rq;
++
++ for (;;) {
++ /*
++ * We do the initial early heuristics without holding
++ * any task-queue locks at all. We'll only try to get
++ * the runqueue lock when things look like they will
++ * work out! In the unlikely event rq is dereferenced
++ * since we're lockless, grab it again.
++ */
++#ifdef CONFIG_SMP
++retry_rq:
++ rq = task_rq(p);
++ if (unlikely(!rq))
++ goto retry_rq;
++#else /* CONFIG_SMP */
++ rq = task_rq(p);
++#endif
++ /*
++ * If the task is actively running on another CPU
++ * still, just relax and busy-wait without holding
++ * any locks.
++ *
++ * NOTE! Since we don't hold any locks, it's not
++ * even sure that "rq" stays as the right runqueue!
++ * But we don't care, since this will return false
++ * if the runqueue has changed and p is actually now
++ * running somewhere else!
++ */
++ while (task_running(p) && p == rq->curr) {
++ if (match_state && unlikely(p->state != match_state))
++ return 0;
++ cpu_relax();
++ }
++
++ /*
++ * Ok, time to look more closely! We need the grq
++ * lock now, to be *sure*. If we're wrong, we'll
++ * just go back and repeat.
++ */
++ rq = task_grq_lock(p, &flags);
++ trace_sched_wait_task(p);
++ running = task_running(p);
++ on_rq = task_queued(p);
++ ncsw = 0;
++ if (!match_state || p->state == match_state)
++ ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
++ task_grq_unlock(&flags);
++
++ /*
++ * If it changed from the expected state, bail out now.
++ */
++ if (unlikely(!ncsw))
++ break;
++
++ /*
++ * Was it really running after all now that we
++ * checked with the proper locks actually held?
++ *
++ * Oops. Go back and try again..
++ */
++ if (unlikely(running)) {
++ cpu_relax();
++ continue;
++ }
++
++ /*
++ * It's not enough that it's not actively running,
++ * it must be off the runqueue _entirely_, and not
++ * preempted!
++ *
++ * So if it was still runnable (but just not actively
++ * running right now), it's preempted, and we should
++ * yield - it could be a while.
++ */
++ if (unlikely(on_rq)) {
++ ktime_t to = ktime_set(0, NSEC_PER_SEC / HZ);
++
++ set_current_state(TASK_UNINTERRUPTIBLE);
++ schedule_hrtimeout(&to, HRTIMER_MODE_REL);
++ continue;
++ }
++
++ /*
++ * Ahh, all good. It wasn't running, and it wasn't
++ * runnable, which means that it will never become
++ * running in the future either. We're all done!
++ */
++ break;
++ }
++
++ return ncsw;
++}
++
++/***
++ * kick_process - kick a running thread to enter/exit the kernel
++ * @p: the to-be-kicked thread
++ *
++ * Cause a process which is running on another CPU to enter
++ * kernel-mode, without any delay. (to get signals handled.)
++ *
++ * NOTE: this function doesn't have to take the runqueue lock,
++ * because all it wants to ensure is that the remote task enters
++ * the kernel. If the IPI races and the task has been migrated
++ * to another CPU then no harm is done and the purpose has been
++ * achieved as well.
++ */
++void kick_process(struct task_struct *p)
++{
++ int cpu;
++
++ preempt_disable();
++ cpu = task_cpu(p);
++ if ((cpu != smp_processor_id()) && task_curr(p))
++ smp_send_reschedule(cpu);
++ preempt_enable();
++}
++EXPORT_SYMBOL_GPL(kick_process);
++#endif
++
++#define rq_idle(rq) ((rq)->rq_prio == PRIO_LIMIT)
++
++/*
++ * RT tasks preempt purely on priority. SCHED_NORMAL tasks preempt on the
++ * basis of earlier deadlines. SCHED_IDLEPRIO don't preempt anything else or
++ * between themselves, they cooperatively multitask. An idle rq scores as
++ * prio PRIO_LIMIT so it is always preempted.
++ */
++static inline bool
++can_preempt(struct task_struct *p, int prio, u64 deadline)
++{
++ /* Better static priority RT task or better policy preemption */
++ if (p->prio < prio)
++ return true;
++ if (p->prio > prio)
++ return false;
++ /* SCHED_NORMAL, BATCH and ISO will preempt based on deadline */
++ if (!deadline_before(p->deadline, deadline))
++ return false;
++ return true;
++}
++
++#ifdef CONFIG_SMP
++#define cpu_online_map (*(cpumask_t *)cpu_online_mask)
++#ifdef CONFIG_HOTPLUG_CPU
++/*
++ * Check to see if there is a task that is affined only to offline CPUs but
++ * still wants runtime. This happens to kernel threads during suspend/halt and
++ * disabling of CPUs.
++ */
++static inline bool online_cpus(struct task_struct *p)
++{
++ return (likely(cpus_intersects(cpu_online_map, p->cpus_allowed)));
++}
++#else /* CONFIG_HOTPLUG_CPU */
++/* All available CPUs are always online without hotplug. */
++static inline bool online_cpus(struct task_struct *p)
++{
++ return true;
++}
++#endif
++
++/*
++ * Check to see if p can run on cpu, and if not, whether there are any online
++ * CPUs it can run on instead.
++ */
++static inline bool needs_other_cpu(struct task_struct *p, int cpu)
++{
++ if (unlikely(!cpu_isset(cpu, p->cpus_allowed)))
++ return true;
++ return false;
++}
++
++/*
++ * When all else is equal, still prefer this_rq.
++ */
++static void try_preempt(struct task_struct *p, struct rq *this_rq)
++{
++ struct rq *highest_prio_rq = NULL;
++ int cpu, highest_prio;
++ u64 latest_deadline;
++ cpumask_t tmp;
++
++ /*
++ * We clear the sticky flag here because for a task to have called
++ * try_preempt with the sticky flag enabled means some complicated
++ * re-scheduling has occurred and we should ignore the sticky flag.
++ */
++ clear_sticky(p);
++
++ if (suitable_idle_cpus(p)) {
++ resched_best_idle(p);
++ return;
++ }
++
++ /* IDLEPRIO tasks never preempt anything but idle */
++ if (p->policy == SCHED_IDLEPRIO)
++ return;
++
++ if (likely(online_cpus(p)))
++ cpus_and(tmp, cpu_online_map, p->cpus_allowed);
++ else
++ return;
++
++ highest_prio = latest_deadline = 0;
++
++ for_each_cpu_mask(cpu, tmp) {
++ struct rq *rq;
++ int rq_prio;
++
++ rq = cpu_rq(cpu);
++ rq_prio = rq->rq_prio;
++ if (rq_prio < highest_prio)
++ continue;
++
++ if (rq_prio > highest_prio ||
++ deadline_after(rq->rq_deadline, latest_deadline)) {
++ latest_deadline = rq->rq_deadline;
++ highest_prio = rq_prio;
++ highest_prio_rq = rq;
++ }
++ }
++
++ if (likely(highest_prio_rq)) {
++ if (can_preempt(p, highest_prio, highest_prio_rq->rq_deadline))
++ resched_task(highest_prio_rq->curr);
++ }
++}
++#else /* CONFIG_SMP */
++static inline bool needs_other_cpu(struct task_struct *p, int cpu)
++{
++ return false;
++}
++
++static void try_preempt(struct task_struct *p, struct rq *this_rq)
++{
++ if (p->policy == SCHED_IDLEPRIO)
++ return;
++ if (can_preempt(p, uprq->rq_prio, uprq->rq_deadline))
++ resched_task(uprq->curr);
++}
++#endif /* CONFIG_SMP */
++
++static void
++ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
++{
++#ifdef CONFIG_SCHEDSTATS
++ struct rq *rq = this_rq();
++
++#ifdef CONFIG_SMP
++ int this_cpu = smp_processor_id();
++
++ if (cpu == this_cpu)
++ schedstat_inc(rq, ttwu_local);
++ else {
++ struct sched_domain *sd;
++
++ rcu_read_lock();
++ for_each_domain(this_cpu, sd) {
++ if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
++ schedstat_inc(sd, ttwu_wake_remote);
++ break;
++ }
++ }
++ rcu_read_unlock();
++ }
++
++#endif /* CONFIG_SMP */
++
++ schedstat_inc(rq, ttwu_count);
++#endif /* CONFIG_SCHEDSTATS */
++}
++
++static inline void ttwu_activate(struct task_struct *p, struct rq *rq,
++ bool is_sync)
++{
++ activate_task(p, rq);
++
++ /*
++ * Sync wakeups (i.e. those types of wakeups where the waker
++ * has indicated that it will leave the CPU in short order)
++ * don't trigger a preemption if there are no idle cpus,
++ * instead waiting for current to deschedule.
++ */
++ if (!is_sync || suitable_idle_cpus(p))
++ try_preempt(p, rq);
++}
++
++static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq,
++ bool success)
++{
++ trace_sched_wakeup(p, success);
++ p->state = TASK_RUNNING;
++
++ /*
++ * if a worker is waking up, notify workqueue. Note that on BFS, we
++ * don't really know what cpu it will be, so we fake it for
++ * wq_worker_waking_up :/
++ */
++ if ((p->flags & PF_WQ_WORKER) && success)
++ wq_worker_waking_up(p, cpu_of(rq));
++}
++
++#ifdef CONFIG_SMP
++void scheduler_ipi(void)
++{
++}
++#endif /* CONFIG_SMP */
++
++/*
++ * wake flags
++ */
++#define WF_SYNC 0x01 /* waker goes to sleep after wakeup */
++#define WF_FORK 0x02 /* child wakeup after fork */
++#define WF_MIGRATED 0x4 /* internal use, task got migrated */
++
++/***
++ * try_to_wake_up - wake up a thread
++ * @p: the thread to be awakened
++ * @state: the mask of task states that can be woken
++ * @wake_flags: wake modifier flags (WF_*)
++ *
++ * Put it on the run-queue if it's not already there. The "current"
++ * thread is always on the run-queue (except when the actual
++ * re-schedule is in progress), and as such you're allowed to do
++ * the simpler "current->state = TASK_RUNNING" to mark yourself
++ * runnable without the overhead of this.
++ *
++ * Returns %true if @p was woken up, %false if it was already running
++ * or @state didn't match @p's state.
++ */
++static bool try_to_wake_up(struct task_struct *p, unsigned int state,
++ int wake_flags)
++{
++ bool success = false;
++ unsigned long flags;
++ struct rq *rq;
++ int cpu;
++
++ get_cpu();
++
++ /* This barrier is undocumented, probably for p->state? くそ */
++ smp_wmb();
++
++ /*
++ * No need to do time_lock_grq as we only need to update the rq clock
++ * if we activate the task
++ */
++ rq = task_grq_lock(p, &flags);
++ cpu = task_cpu(p);
++
++ /* state is a volatile long, どうして、分からない */
++ if (!((unsigned int)p->state & state))
++ goto out_unlock;
++
++ if (task_queued(p) || task_running(p))
++ goto out_running;
++
++ ttwu_activate(p, rq, wake_flags & WF_SYNC);
++ success = true;
++
++out_running:
++ ttwu_post_activation(p, rq, success);
++out_unlock:
++ task_grq_unlock(&flags);
++
++ ttwu_stat(p, cpu, wake_flags);
++
++ put_cpu();
++
++ return success;
++}
++
++/**
++ * try_to_wake_up_local - try to wake up a local task with grq lock held
++ * @p: the thread to be awakened
++ *
++ * Put @p on the run-queue if it's not already there. The caller must
++ * ensure that grq is locked and, @p is not the current task.
++ * grq stays locked over invocation.
++ */
++static void try_to_wake_up_local(struct task_struct *p)
++{
++ struct rq *rq = task_rq(p);
++ bool success = false;
++
++ lockdep_assert_held(&grq.lock);
++
++ if (!(p->state & TASK_NORMAL))
++ return;
++
++ if (!task_queued(p)) {
++ if (likely(!task_running(p))) {
++ schedstat_inc(rq, ttwu_count);
++ schedstat_inc(rq, ttwu_local);
++ }
++ ttwu_activate(p, rq, false);
++ ttwu_stat(p, smp_processor_id(), 0);
++ success = true;
++ }
++ ttwu_post_activation(p, rq, success);
++}
++
++/**
++ * wake_up_process - Wake up a specific process
++ * @p: The process to be woken up.
++ *
++ * Attempt to wake up the nominated process and move it to the set of runnable
++ * processes. Returns 1 if the process was woken up, 0 if it was already
++ * running.
++ *
++ * It may be assumed that this function implies a write memory barrier before
++ * changing the task state if and only if any tasks are woken up.
++ */
++int wake_up_process(struct task_struct *p)
++{
++ WARN_ON(task_is_stopped_or_traced(p));
++ return try_to_wake_up(p, TASK_NORMAL, 0);
++}
++EXPORT_SYMBOL(wake_up_process);
++
++int wake_up_state(struct task_struct *p, unsigned int state)
++{
++ return try_to_wake_up(p, state, 0);
++}
++
++static void time_slice_expired(struct task_struct *p);
++
++/*
++ * Perform scheduler related setup for a newly forked process p.
++ * p is forked by current.
++ */
++void sched_fork(struct task_struct *p)
++{
++#ifdef CONFIG_PREEMPT_NOTIFIERS
++ INIT_HLIST_HEAD(&p->preempt_notifiers);
++#endif
++ /*
++ * The process state is set to the same value of the process executing
++ * do_fork() code. That is running. This guarantees that nobody will
++ * actually run it, and a signal or other external event cannot wake
++ * it up and insert it on the runqueue either.
++ */
++
++ /* Should be reset in fork.c but done here for ease of bfs patching */
++ p->utime =
++ p->stime =
++ p->utimescaled =
++ p->stimescaled =
++ p->sched_time =
++ p->stime_pc =
++ p->utime_pc = 0;
++
++ /*
++ * Revert to default priority/policy on fork if requested.
++ */
++ if (unlikely(p->sched_reset_on_fork)) {
++ if (p->policy == SCHED_FIFO || p->policy == SCHED_RR) {
++ p->policy = SCHED_NORMAL;
++ p->normal_prio = normal_prio(p);
++ }
++
++ if (PRIO_TO_NICE(p->static_prio) < 0) {
++ p->static_prio = NICE_TO_PRIO(0);
++ p->normal_prio = p->static_prio;
++ }
++
++ /*
++ * We don't need the reset flag anymore after the fork. It has
++ * fulfilled its duty:
++ */
++ p->sched_reset_on_fork = 0;
++ }
++
++ INIT_LIST_HEAD(&p->run_list);
++#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
++ if (unlikely(sched_info_on()))
++ memset(&p->sched_info, 0, sizeof(p->sched_info));
++#endif
++ p->on_cpu = false;
++ clear_sticky(p);
++
++#ifdef CONFIG_PREEMPT_COUNT
++ /* Want to start with kernel preemption disabled. */
++ task_thread_info(p)->preempt_count = 1;
++#endif
++}
++
++/*
++ * wake_up_new_task - wake up a newly created task for the first time.
++ *
++ * This function will do some initial scheduler statistics housekeeping
++ * that must be done for every newly created context, then puts the task
++ * on the runqueue and wakes it.
++ */
++void wake_up_new_task(struct task_struct *p)
++{
++ struct task_struct *parent;
++ unsigned long flags;
++ struct rq *rq;
++
++ parent = p->parent;
++ rq = task_grq_lock(p, &flags);
++
++ /*
++ * Reinit new task deadline as its creator deadline could have changed
++ * since call to dup_task_struct().
++ */
++ p->deadline = rq->rq_deadline;
++
++ /*
++ * If the task is a new process, current and parent are the same. If
++ * the task is a new thread in the thread group, it will have much more
++ * in common with current than with the parent.
++ */
++ set_task_cpu(p, task_cpu(rq->curr));
++
++ /*
++ * Make sure we do not leak PI boosting priority to the child.
++ */
++ p->prio = rq->curr->normal_prio;
++
++ activate_task(p, rq);
++ trace_sched_wakeup_new(p, 1);
++ if (unlikely(p->policy == SCHED_FIFO))
++ goto after_ts_init;
++
++ /*
++ * Share the timeslice between parent and child, thus the
++ * total amount of pending timeslices in the system doesn't change,
++ * resulting in more scheduling fairness. If it's negative, it won't
++ * matter since that's the same as being 0. current's time_slice is
++ * actually in rq_time_slice when it's running, as is its last_ran
++ * value. rq->rq_deadline is only modified within schedule() so it
++ * is always equal to current->deadline.
++ */
++ p->last_ran = rq->rq_last_ran;
++ if (likely(rq->rq_time_slice >= RESCHED_US * 2)) {
++ rq->rq_time_slice /= 2;
++ p->time_slice = rq->rq_time_slice;
++after_ts_init:
++ if (rq->curr == parent && !suitable_idle_cpus(p)) {
++ /*
++ * The VM isn't cloned, so we're in a good position to
++ * do child-runs-first in anticipation of an exec. This
++ * usually avoids a lot of COW overhead.
++ */
++ set_tsk_need_resched(parent);
++ } else
++ try_preempt(p, rq);
++ } else {
++ if (rq->curr == parent) {
++ /*
++ * Forking task has run out of timeslice. Reschedule it and
++ * start its child with a new time slice and deadline. The
++ * child will end up running first because its deadline will
++ * be slightly earlier.
++ */
++ rq->rq_time_slice = 0;
++ set_tsk_need_resched(parent);
++ }
++ time_slice_expired(p);
++ }
++ task_grq_unlock(&flags);
++}
++
++#ifdef CONFIG_PREEMPT_NOTIFIERS
++
++/**
++ * preempt_notifier_register - tell me when current is being preempted & rescheduled
++ * @notifier: notifier struct to register
++ */
++void preempt_notifier_register(struct preempt_notifier *notifier)
++{
++ hlist_add_head(&notifier->link, &current->preempt_notifiers);
++}
++EXPORT_SYMBOL_GPL(preempt_notifier_register);
++
++/**
++ * preempt_notifier_unregister - no longer interested in preemption notifications
++ * @notifier: notifier struct to unregister
++ *
++ * This is safe to call from within a preemption notifier.
++ */
++void preempt_notifier_unregister(struct preempt_notifier *notifier)
++{
++ hlist_del(&notifier->link);
++}
++EXPORT_SYMBOL_GPL(preempt_notifier_unregister);
++
++static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
++{
++ struct preempt_notifier *notifier;
++
++ hlist_for_each_entry(notifier, &curr->preempt_notifiers, link)
++ notifier->ops->sched_in(notifier, raw_smp_processor_id());
++}
++
++static void
++fire_sched_out_preempt_notifiers(struct task_struct *curr,
++ struct task_struct *next)
++{
++ struct preempt_notifier *notifier;
++
++ hlist_for_each_entry(notifier, &curr->preempt_notifiers, link)
++ notifier->ops->sched_out(notifier, next);
++}
++
++#else /* !CONFIG_PREEMPT_NOTIFIERS */
++
++static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
++{
++}
++
++static void
++fire_sched_out_preempt_notifiers(struct task_struct *curr,
++ struct task_struct *next)
++{
++}
++
++#endif /* CONFIG_PREEMPT_NOTIFIERS */
++
++/**
++ * prepare_task_switch - prepare to switch tasks
++ * @rq: the runqueue preparing to switch
++ * @next: the task we are going to switch to.
++ *
++ * This is called with the rq lock held and interrupts off. It must
++ * be paired with a subsequent finish_task_switch after the context
++ * switch.
++ *
++ * prepare_task_switch sets up locking and calls architecture specific
++ * hooks.
++ */
++static inline void
++prepare_task_switch(struct rq *rq, struct task_struct *prev,
++ struct task_struct *next)
++{
++ sched_info_switch(prev, next);
++ perf_event_task_sched_out(prev, next);
++ fire_sched_out_preempt_notifiers(prev, next);
++ prepare_lock_switch(rq, next);
++ prepare_arch_switch(next);
++ trace_sched_switch(prev, next);
++}
++
++/**
++ * finish_task_switch - clean up after a task-switch
++ * @rq: runqueue associated with task-switch
++ * @prev: the thread we just switched away from.
++ *
++ * finish_task_switch must be called after the context switch, paired
++ * with a prepare_task_switch call before the context switch.
++ * finish_task_switch will reconcile locking set up by prepare_task_switch,
++ * and do any other architecture-specific cleanup actions.
++ *
++ * Note that we may have delayed dropping an mm in context_switch(). If
++ * so, we finish that here outside of the runqueue lock. (Doing it
++ * with the lock held can cause deadlocks; see schedule() for
++ * details.)
++ */
++static inline void finish_task_switch(struct rq *rq, struct task_struct *prev)
++ __releases(grq.lock)
++{
++ struct mm_struct *mm = rq->prev_mm;
++ long prev_state;
++
++ rq->prev_mm = NULL;
++
++ /*
++ * A task struct has one reference for the use as "current".
++ * If a task dies, then it sets TASK_DEAD in tsk->state and calls
++ * schedule one last time. The schedule call will never return, and
++ * the scheduled task must drop that reference.
++ * The test for TASK_DEAD must occur while the runqueue locks are
++ * still held, otherwise prev could be scheduled on another cpu, die
++ * there before we look at prev->state, and then the reference would
++ * be dropped twice.
++ * Manfred Spraul <manfred@colorfullife.com>
++ */
++ prev_state = prev->state;
++ vtime_task_switch(prev);
++ finish_arch_switch(prev);
++ perf_event_task_sched_in(prev, current);
++ finish_lock_switch(rq, prev);
++ finish_arch_post_lock_switch();
++
++ fire_sched_in_preempt_notifiers(current);
++ if (mm)
++ mmdrop(mm);
++ if (unlikely(prev_state == TASK_DEAD)) {
++ /*
++ * Remove function-return probe instances associated with this
++ * task and put them back on the free list.
++ */
++ kprobe_flush_task(prev);
++ put_task_struct(prev);
++ }
++}
++
++/**
++ * schedule_tail - first thing a freshly forked thread must call.
++ * @prev: the thread we just switched away from.
++ */
++asmlinkage void schedule_tail(struct task_struct *prev)
++ __releases(grq.lock)
++{
++ struct rq *rq = this_rq();
++
++ finish_task_switch(rq, prev);
++#ifdef __ARCH_WANT_UNLOCKED_CTXSW
++ /* In this case, finish_task_switch does not reenable preemption */
++ preempt_enable();
++#endif
++ if (current->set_child_tid)
++ put_user(current->pid, current->set_child_tid);
++}
++
++/*
++ * context_switch - switch to the new MM and the new
++ * thread's register state.
++ */
++static inline void
++context_switch(struct rq *rq, struct task_struct *prev,
++ struct task_struct *next)
++{
++ struct mm_struct *mm, *oldmm;
++
++ prepare_task_switch(rq, prev, next);
++
++ mm = next->mm;
++ oldmm = prev->active_mm;
++ /*
++ * For paravirt, this is coupled with an exit in switch_to to
++ * combine the page table reload and the switch backend into
++ * one hypercall.
++ */
++ arch_start_context_switch(prev);
++
++ if (!mm) {
++ next->active_mm = oldmm;
++ atomic_inc(&oldmm->mm_count);
++ enter_lazy_tlb(oldmm, next);
++ } else
++ switch_mm(oldmm, mm, next);
++
++ if (!prev->mm) {
++ prev->active_mm = NULL;
++ rq->prev_mm = oldmm;
++ }
++ /*
++ * Since the runqueue lock will be released by the next
++ * task (which is an invalid locking op but in the case
++ * of the scheduler it's an obvious special-case), so we
++ * do an early lockdep release here:
++ */
++#ifndef __ARCH_WANT_UNLOCKED_CTXSW
++ spin_release(&grq.lock.dep_map, 1, _THIS_IP_);
++#endif
++
++ /* Here we just switch the register state and the stack. */
++ context_tracking_task_switch(prev, next);
++ switch_to(prev, next, prev);
++
++ barrier();
++ /*
++ * this_rq must be evaluated again because prev may have moved
++ * CPUs since it called schedule(), thus the 'rq' on its stack
++ * frame will be invalid.
++ */
++ finish_task_switch(this_rq(), prev);
++}
++
++/*
++ * nr_running, nr_uninterruptible and nr_context_switches:
++ *
++ * externally visible scheduler statistics: current number of runnable
++ * threads, total number of context switches performed since bootup. All are
++ * measured without grabbing the grq lock but the occasional inaccurate result
++ * doesn't matter so long as it's positive.
++ */
++unsigned long nr_running(void)
++{
++ long nr = grq.nr_running;
++
++ if (unlikely(nr < 0))
++ nr = 0;
++ return (unsigned long)nr;
++}
++
++static unsigned long nr_uninterruptible(void)
++{
++ long nu = grq.nr_uninterruptible;
++
++ if (unlikely(nu < 0))
++ nu = 0;
++ return nu;
++}
++
++unsigned long long nr_context_switches(void)
++{
++ long long ns = grq.nr_switches;
++
++ /* This is of course impossible */
++ if (unlikely(ns < 0))
++ ns = 1;
++ return (unsigned long long)ns;
++}
++
++unsigned long nr_iowait(void)
++{
++ unsigned long i, sum = 0;
++
++ for_each_possible_cpu(i)
++ sum += atomic_read(&cpu_rq(i)->nr_iowait);
++
++ return sum;
++}
++
++unsigned long nr_iowait_cpu(int cpu)
++{
++ struct rq *this = cpu_rq(cpu);
++ return atomic_read(&this->nr_iowait);
++}
++
++unsigned long nr_active(void)
++{
++ return nr_running() + nr_uninterruptible();
++}
++
++/* Beyond a task running on this CPU, load is equal everywhere on BFS */
++unsigned long this_cpu_load(void)
++{
++ return this_rq()->rq_running +
++ ((queued_notrunning() + nr_uninterruptible()) / grq.noc);
++}
++
++/* Variables and functions for calc_load */
++static unsigned long calc_load_update;
++unsigned long avenrun[3];
++EXPORT_SYMBOL(avenrun);
++
++/**
++ * get_avenrun - get the load average array
++ * @loads: pointer to dest load array
++ * @offset: offset to add
++ * @shift: shift count to shift the result left
++ *
++ * These values are estimates at best, so no need for locking.
++ */
++void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
++{
++ loads[0] = (avenrun[0] + offset) << shift;
++ loads[1] = (avenrun[1] + offset) << shift;
++ loads[2] = (avenrun[2] + offset) << shift;
++}
++
++static unsigned long
++calc_load(unsigned long load, unsigned long exp, unsigned long active)
++{
++ load *= exp;
++ load += active * (FIXED_1 - exp);
++ return load >> FSHIFT;
++}
++
++/*
++ * calc_load - update the avenrun load estimates every LOAD_FREQ seconds.
++ */
++void calc_global_load(unsigned long ticks)
++{
++ long active;
++
++ if (time_before(jiffies, calc_load_update))
++ return;
++ active = nr_active() * FIXED_1;
++
++ avenrun[0] = calc_load(avenrun[0], EXP_1, active);
++ avenrun[1] = calc_load(avenrun[1], EXP_5, active);
++ avenrun[2] = calc_load(avenrun[2], EXP_15, active);
++
++ calc_load_update = jiffies + LOAD_FREQ;
++}
++
++DEFINE_PER_CPU(struct kernel_stat, kstat);
++DEFINE_PER_CPU(struct kernel_cpustat, kernel_cpustat);
++
++EXPORT_PER_CPU_SYMBOL(kstat);
++EXPORT_PER_CPU_SYMBOL(kernel_cpustat);
++
++#ifdef CONFIG_IRQ_TIME_ACCOUNTING
++
++/*
++ * There are no locks covering percpu hardirq/softirq time.
++ * They are only modified in account_system_vtime, on corresponding CPU
++ * with interrupts disabled. So, writes are safe.
++ * They are read and saved off onto struct rq in update_rq_clock().
++ * This may result in other CPU reading this CPU's irq time and can
++ * race with irq/account_system_vtime on this CPU. We would either get old
++ * or new value with a side effect of accounting a slice of irq time to wrong
++ * task when irq is in progress while we read rq->clock. That is a worthy
++ * compromise in place of having locks on each irq in account_system_time.
++ */
++static DEFINE_PER_CPU(u64, cpu_hardirq_time);
++static DEFINE_PER_CPU(u64, cpu_softirq_time);
++
++static DEFINE_PER_CPU(u64, irq_start_time);
++static int sched_clock_irqtime;
++
++void enable_sched_clock_irqtime(void)
++{
++ sched_clock_irqtime = 1;
++}
++
++void disable_sched_clock_irqtime(void)
++{
++ sched_clock_irqtime = 0;
++}
++
++#ifndef CONFIG_64BIT
++static DEFINE_PER_CPU(seqcount_t, irq_time_seq);
++
++static inline void irq_time_write_begin(void)
++{
++ __this_cpu_inc(irq_time_seq.sequence);
++ smp_wmb();
++}
++
++static inline void irq_time_write_end(void)
++{
++ smp_wmb();
++ __this_cpu_inc(irq_time_seq.sequence);
++}
++
++static inline u64 irq_time_read(int cpu)
++{
++ u64 irq_time;
++ unsigned seq;
++
++ do {
++ seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu));
++ irq_time = per_cpu(cpu_softirq_time, cpu) +
++ per_cpu(cpu_hardirq_time, cpu);
++ } while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq));
++
++ return irq_time;
++}
++#else /* CONFIG_64BIT */
++static inline void irq_time_write_begin(void)
++{
++}
++
++static inline void irq_time_write_end(void)
++{
++}
++
++static inline u64 irq_time_read(int cpu)
++{
++ return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu);
++}
++#endif /* CONFIG_64BIT */
++
++/*
++ * Called before incrementing preempt_count on {soft,}irq_enter
++ * and before decrementing preempt_count on {soft,}irq_exit.
++ */
++void irqtime_account_irq(struct task_struct *curr)
++{
++ unsigned long flags;
++ s64 delta;
++ int cpu;
++
++ if (!sched_clock_irqtime)
++ return;
++
++ local_irq_save(flags);
++
++ cpu = smp_processor_id();
++ delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time);
++ __this_cpu_add(irq_start_time, delta);
++
++ irq_time_write_begin();
++ /*
++ * We do not account for softirq time from ksoftirqd here.
++ * We want to continue accounting softirq time to ksoftirqd thread
++ * in that case, so as not to confuse scheduler with a special task
++ * that do not consume any time, but still wants to run.
++ */
++ if (hardirq_count())
++ __this_cpu_add(cpu_hardirq_time, delta);
++ else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
++ __this_cpu_add(cpu_softirq_time, delta);
++
++ irq_time_write_end();
++ local_irq_restore(flags);
++}
++EXPORT_SYMBOL_GPL(irqtime_account_irq);
++
++#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
++
++#ifdef CONFIG_PARAVIRT
++static inline u64 steal_ticks(u64 steal)
++{
++ if (unlikely(steal > NSEC_PER_SEC))
++ return div_u64(steal, TICK_NSEC);
++
++ return __iter_div_u64_rem(steal, TICK_NSEC, &steal);
++}
++#endif
++
++static void update_rq_clock_task(struct rq *rq, s64 delta)
++{
++/*
++ * In theory, the compile should just see 0 here, and optimize out the call
++ * to sched_rt_avg_update. But I don't trust it...
++ */
++#ifdef CONFIG_IRQ_TIME_ACCOUNTING
++ s64 irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
++
++ /*
++ * Since irq_time is only updated on {soft,}irq_exit, we might run into
++ * this case when a previous update_rq_clock() happened inside a
++ * {soft,}irq region.
++ *
++ * When this happens, we stop ->clock_task and only update the
++ * prev_irq_time stamp to account for the part that fit, so that a next
++ * update will consume the rest. This ensures ->clock_task is
++ * monotonic.
++ *
++ * It does however cause some slight miss-attribution of {soft,}irq
++ * time, a more accurate solution would be to update the irq_time using
++ * the current rq->clock timestamp, except that would require using
++ * atomic ops.
++ */
++ if (irq_delta > delta)
++ irq_delta = delta;
++
++ rq->prev_irq_time += irq_delta;
++ delta -= irq_delta;
++#endif
++#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
++ if (static_key_false((&paravirt_steal_rq_enabled))) {
++ s64 steal = paravirt_steal_clock(cpu_of(rq));
++ u64 st;
++
++ steal -= rq->prev_steal_time_rq;
++
++ if (unlikely(steal > delta))
++ steal = delta;
++
++ st = steal_ticks(steal);
++ steal = st * TICK_NSEC;
++
++ rq->prev_steal_time_rq += steal;
++
++ delta -= steal;
++ }
++#endif
++
++ rq->clock_task += delta;
++}
++
++#ifndef nsecs_to_cputime
++# define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs)
++#endif
++
++#ifdef CONFIG_IRQ_TIME_ACCOUNTING
++static void irqtime_account_hi_si(void)
++{
++ u64 *cpustat = kcpustat_this_cpu->cpustat;
++ u64 latest_ns;
++
++ latest_ns = nsecs_to_cputime64(this_cpu_read(cpu_hardirq_time));
++ if (latest_ns > cpustat[CPUTIME_IRQ])
++ cpustat[CPUTIME_IRQ] += (__force u64)cputime_one_jiffy;
++
++ latest_ns = nsecs_to_cputime64(this_cpu_read(cpu_softirq_time));
++ if (latest_ns > cpustat[CPUTIME_SOFTIRQ])
++ cpustat[CPUTIME_SOFTIRQ] += (__force u64)cputime_one_jiffy;
++}
++#else /* CONFIG_IRQ_TIME_ACCOUNTING */
++
++#define sched_clock_irqtime (0)
++
++static inline void irqtime_account_hi_si(void)
++{
++}
++#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
++
++static __always_inline bool steal_account_process_tick(void)
++{
++#ifdef CONFIG_PARAVIRT
++ if (static_key_false(&paravirt_steal_enabled)) {
++ u64 steal, st = 0;
++
++ steal = paravirt_steal_clock(smp_processor_id());
++ steal -= this_rq()->prev_steal_time;
++
++ st = steal_ticks(steal);
++ this_rq()->prev_steal_time += st * TICK_NSEC;
++
++ account_steal_time(st);
++ return st;
++ }
++#endif
++ return false;
++}
++
++/*
++ * Accumulate raw cputime values of dead tasks (sig->[us]time) and live
++ * tasks (sum on group iteration) belonging to @tsk's group.
++ */
++void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
++{
++ struct signal_struct *sig = tsk->signal;
++ cputime_t utime, stime;
++ struct task_struct *t;
++
++ times->utime = sig->utime;
++ times->stime = sig->stime;
++ times->sum_exec_runtime = sig->sum_sched_runtime;
++
++ rcu_read_lock();
++ /* make sure we can trust tsk->thread_group list */
++ if (!likely(pid_alive(tsk)))
++ goto out;
++
++ t = tsk;
++ do {
++ task_cputime(t, &utime, &stime);
++ times->utime += utime;
++ times->stime += stime;
++ times->sum_exec_runtime += task_sched_runtime(t);
++ } while_each_thread(tsk, t);
++out:
++ rcu_read_unlock();
++}
++
++/*
++ * On each tick, see what percentage of that tick was attributed to each
++ * component and add the percentage to the _pc values. Once a _pc value has
++ * accumulated one tick's worth, account for that. This means the total
++ * percentage of load components will always be 128 (pseudo 100) per tick.
++ */
++static void pc_idle_time(struct rq *rq, struct task_struct *idle, unsigned long pc)
++{
++ u64 *cpustat = kcpustat_this_cpu->cpustat;
++
++ if (atomic_read(&rq->nr_iowait) > 0) {
++ rq->iowait_pc += pc;
++ if (rq->iowait_pc >= 128) {
++ cpustat[CPUTIME_IOWAIT] += (__force u64)cputime_one_jiffy * rq->iowait_pc / 128;
++ rq->iowait_pc %= 128;
++ }
++ } else {
++ rq->idle_pc += pc;
++ if (rq->idle_pc >= 128) {
++ cpustat[CPUTIME_IDLE] += (__force u64)cputime_one_jiffy * rq->idle_pc / 128;
++ rq->idle_pc %= 128;
++ }
++ }
++ acct_update_integrals(idle);
++}
++
++static void
++pc_system_time(struct rq *rq, struct task_struct *p, int hardirq_offset,
++ unsigned long pc, unsigned long ns)
++{
++ u64 *cpustat = kcpustat_this_cpu->cpustat;
++ cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
++
++ p->stime_pc += pc;
++ if (p->stime_pc >= 128) {
++ int jiffs = p->stime_pc / 128;
++
++ p->stime_pc %= 128;
++ p->stime += (__force u64)cputime_one_jiffy * jiffs;
++ p->stimescaled += one_jiffy_scaled * jiffs;
++ account_group_system_time(p, cputime_one_jiffy * jiffs);
++ }
++ p->sched_time += ns;
++ /*
++ * Do not update the cputimer if the task is already released by
++ * release_task().
++ *
++ * This could be executed if a tick happens when a task is inside
++ * do_exit() between the call to release_task() and its final
++ * schedule() call for autoreaping tasks.
++ */
++ if (likely(p->sighand))
++ account_group_exec_runtime(p, ns);
++
++ if (hardirq_count() - hardirq_offset) {
++ rq->irq_pc += pc;
++ if (rq->irq_pc >= 128) {
++ cpustat[CPUTIME_IRQ] += (__force u64)cputime_one_jiffy * rq->irq_pc / 128;
++ rq->irq_pc %= 128;
++ }
++ } else if (in_serving_softirq()) {
++ rq->softirq_pc += pc;
++ if (rq->softirq_pc >= 128) {
++ cpustat[CPUTIME_SOFTIRQ] += (__force u64)cputime_one_jiffy * rq->softirq_pc / 128;
++ rq->softirq_pc %= 128;
++ }
++ } else {
++ rq->system_pc += pc;
++ if (rq->system_pc >= 128) {
++ cpustat[CPUTIME_SYSTEM] += (__force u64)cputime_one_jiffy * rq->system_pc / 128;
++ rq->system_pc %= 128;
++ }
++ }
++ acct_update_integrals(p);
++}
++
++static void pc_user_time(struct rq *rq, struct task_struct *p,
++ unsigned long pc, unsigned long ns)
++{
++ u64 *cpustat = kcpustat_this_cpu->cpustat;
++ cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
++
++ p->utime_pc += pc;
++ if (p->utime_pc >= 128) {
++ int jiffs = p->utime_pc / 128;
++
++ p->utime_pc %= 128;
++ p->utime += (__force u64)cputime_one_jiffy * jiffs;
++ p->utimescaled += one_jiffy_scaled * jiffs;
++ account_group_user_time(p, cputime_one_jiffy * jiffs);
++ }
++ p->sched_time += ns;
++ /*
++ * Do not update the cputimer if the task is already released by
++ * release_task().
++ *
++ * it would preferable to defer the autoreap release_task
++ * after the last context switch but harder to do.
++ */
++ if (likely(p->sighand))
++ account_group_exec_runtime(p, ns);
++
++ if (this_cpu_ksoftirqd() == p) {
++ /*
++ * ksoftirqd time do not get accounted in cpu_softirq_time.
++ * So, we have to handle it separately here.
++ */
++ rq->softirq_pc += pc;
++ if (rq->softirq_pc >= 128) {
++ cpustat[CPUTIME_SOFTIRQ] += (__force u64)cputime_one_jiffy * rq->softirq_pc / 128;
++ rq->softirq_pc %= 128;
++ }
++ }
++
++ if (TASK_NICE(p) > 0 || idleprio_task(p)) {
++ rq->nice_pc += pc;
++ if (rq->nice_pc >= 128) {
++ cpustat[CPUTIME_NICE] += (__force u64)cputime_one_jiffy * rq->nice_pc / 128;
++ rq->nice_pc %= 128;
++ }
++ } else {
++ rq->user_pc += pc;
++ if (rq->user_pc >= 128) {
++ cpustat[CPUTIME_USER] += (__force u64)cputime_one_jiffy * rq->user_pc / 128;
++ rq->user_pc %= 128;
++ }
++ }
++ acct_update_integrals(p);
++}
++
++/*
++ * Convert nanoseconds to pseudo percentage of one tick. Use 128 for fast
++ * shifts instead of 100
++ */
++#define NS_TO_PC(NS) (NS * 128 / JIFFY_NS)
++
++/*
++ * This is called on clock ticks.
++ * Bank in p->sched_time the ns elapsed since the last tick or switch.
++ * CPU scheduler quota accounting is also performed here in microseconds.
++ */
++static void
++update_cpu_clock_tick(struct rq *rq, struct task_struct *p)
++{
++ long account_ns = rq->clock_task - rq->rq_last_ran;
++ struct task_struct *idle = rq->idle;
++ unsigned long account_pc;
++
++ if (unlikely(account_ns < 0) || steal_account_process_tick())
++ goto ts_account;
++
++ account_pc = NS_TO_PC(account_ns);
++
++ /* Accurate tick timekeeping */
++ if (user_mode(get_irq_regs()))
++ pc_user_time(rq, p, account_pc, account_ns);
++ else if (p != idle || (irq_count() != HARDIRQ_OFFSET))
++ pc_system_time(rq, p, HARDIRQ_OFFSET,
++ account_pc, account_ns);
++ else
++ pc_idle_time(rq, idle, account_pc);
++
++ if (sched_clock_irqtime)
++ irqtime_account_hi_si();
++
++ts_account:
++ /* time_slice accounting is done in usecs to avoid overflow on 32bit */
++ if (rq->rq_policy != SCHED_FIFO && p != idle) {
++ s64 time_diff = rq->clock - rq->timekeep_clock;
++
++ niffy_diff(&time_diff, 1);
++ rq->rq_time_slice -= NS_TO_US(time_diff);
++ }
++
++ rq->rq_last_ran = rq->clock_task;
++ rq->timekeep_clock = rq->clock;
++}
++
++/*
++ * This is called on context switches.
++ * Bank in p->sched_time the ns elapsed since the last tick or switch.
++ * CPU scheduler quota accounting is also performed here in microseconds.
++ */
++static void
++update_cpu_clock_switch(struct rq *rq, struct task_struct *p)
++{
++ long account_ns = rq->clock_task - rq->rq_last_ran;
++ struct task_struct *idle = rq->idle;
++ unsigned long account_pc;
++
++ if (unlikely(account_ns < 0))
++ goto ts_account;
++
++ account_pc = NS_TO_PC(account_ns);
++
++ /* Accurate subtick timekeeping */
++ if (p != idle) {
++ pc_user_time(rq, p, account_pc, account_ns);
++ }
++ else
++ pc_idle_time(rq, idle, account_pc);
++
++ts_account:
++ /* time_slice accounting is done in usecs to avoid overflow on 32bit */
++ if (rq->rq_policy != SCHED_FIFO && p != idle) {
++ s64 time_diff = rq->clock - rq->timekeep_clock;
++
++ niffy_diff(&time_diff, 1);
++ rq->rq_time_slice -= NS_TO_US(time_diff);
++ }
++
++ rq->rq_last_ran = rq->clock_task;
++ rq->timekeep_clock = rq->clock;
++}
++
++/*
++ * Return any ns on the sched_clock that have not yet been accounted in
++ * @p in case that task is currently running.
++ *
++ * Called with task_grq_lock() held.
++ */
++static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq)
++{
++ u64 ns = 0;
++
++ if (p == rq->curr) {
++ update_clocks(rq);
++ ns = rq->clock_task - rq->rq_last_ran;
++ if (unlikely((s64)ns < 0))
++ ns = 0;
++ }
++
++ return ns;
++}
++
++unsigned long long task_delta_exec(struct task_struct *p)
++{
++ unsigned long flags;
++ struct rq *rq;
++ u64 ns;
++
++ rq = task_grq_lock(p, &flags);
++ ns = do_task_delta_exec(p, rq);
++ task_grq_unlock(&flags);
++
++ return ns;
++}
++
++/*
++ * Return accounted runtime for the task.
++ * Return separately the current's pending runtime that have not been
++ * accounted yet.
++ *
++ * grq lock already acquired.
++ */
++unsigned long long task_sched_runtime(struct task_struct *p)
++{
++ unsigned long flags;
++ struct rq *rq;
++ u64 ns;
++
++ rq = task_grq_lock(p, &flags);
++ ns = p->sched_time + do_task_delta_exec(p, rq);
++ task_grq_unlock(&flags);
++
++ return ns;
++}
++
++/*
++ * Return accounted runtime for the task.
++ * Return separately the current's pending runtime that have not been
++ * accounted yet.
++ */
++unsigned long long task_sched_runtime_nodelta(struct task_struct *p, unsigned long long *delta)
++{
++ unsigned long flags;
++ struct rq *rq;
++ u64 ns;
++
++ rq = task_grq_lock(p, &flags);
++ ns = p->sched_time;
++ *delta = do_task_delta_exec(p, rq);
++ task_grq_unlock(&flags);
++
++ return ns;
++}
++
++/* Compatibility crap */
++void account_user_time(struct task_struct *p, cputime_t cputime,
++ cputime_t cputime_scaled)
++{
++}
++
++void account_idle_time(cputime_t cputime)
++{
++}
++
++void update_cpu_load_nohz(void)
++{
++}
++
++#ifdef CONFIG_NO_HZ_COMMON
++void calc_load_enter_idle(void)
++{
++}
++
++void calc_load_exit_idle(void)
++{
++}
++#endif /* CONFIG_NO_HZ_COMMON */
++
++/*
++ * Account guest cpu time to a process.
++ * @p: the process that the cpu time gets accounted to
++ * @cputime: the cpu time spent in virtual machine since the last update
++ * @cputime_scaled: cputime scaled by cpu frequency
++ */
++static void account_guest_time(struct task_struct *p, cputime_t cputime,
++ cputime_t cputime_scaled)
++{
++ u64 *cpustat = kcpustat_this_cpu->cpustat;
++
++ /* Add guest time to process. */
++ p->utime += (__force u64)cputime;
++ p->utimescaled += (__force u64)cputime_scaled;
++ account_group_user_time(p, cputime);
++ p->gtime += (__force u64)cputime;
++
++ /* Add guest time to cpustat. */
++ if (TASK_NICE(p) > 0) {
++ cpustat[CPUTIME_NICE] += (__force u64)cputime;
++ cpustat[CPUTIME_GUEST_NICE] += (__force u64)cputime;
++ } else {
++ cpustat[CPUTIME_USER] += (__force u64)cputime;
++ cpustat[CPUTIME_GUEST] += (__force u64)cputime;
++ }
++}
++
++/*
++ * Account system cpu time to a process and desired cpustat field
++ * @p: the process that the cpu time gets accounted to
++ * @cputime: the cpu time spent in kernel space since the last update
++ * @cputime_scaled: cputime scaled by cpu frequency
++ * @target_cputime64: pointer to cpustat field that has to be updated
++ */
++static inline
++void __account_system_time(struct task_struct *p, cputime_t cputime,
++ cputime_t cputime_scaled, cputime64_t *target_cputime64)
++{
++ /* Add system time to process. */
++ p->stime += (__force u64)cputime;
++ p->stimescaled += (__force u64)cputime_scaled;
++ account_group_system_time(p, cputime);
++
++ /* Add system time to cpustat. */
++ *target_cputime64 += (__force u64)cputime;
++
++ /* Account for system time used */
++ acct_update_integrals(p);
++}
++
++/*
++ * Account system cpu time to a process.
++ * @p: the process that the cpu time gets accounted to
++ * @hardirq_offset: the offset to subtract from hardirq_count()
++ * @cputime: the cpu time spent in kernel space since the last update
++ * @cputime_scaled: cputime scaled by cpu frequency
++ * This is for guest only now.
++ */
++void account_system_time(struct task_struct *p, int hardirq_offset,
++ cputime_t cputime, cputime_t cputime_scaled)
++{
++
++ if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0))
++ account_guest_time(p, cputime, cputime_scaled);
++}
++
++/*
++ * Account for involuntary wait time.
++ * @steal: the cpu time spent in involuntary wait
++ */
++void account_steal_time(cputime_t cputime)
++{
++ u64 *cpustat = kcpustat_this_cpu->cpustat;
++
++ cpustat[CPUTIME_STEAL] += (__force u64)cputime;
++}
++
++/*
++ * Account for idle time.
++ * @cputime: the cpu time spent in idle wait
++ */
++static void account_idle_times(cputime_t cputime)
++{
++ u64 *cpustat = kcpustat_this_cpu->cpustat;
++ struct rq *rq = this_rq();
++
++ if (atomic_read(&rq->nr_iowait) > 0)
++ cpustat[CPUTIME_IOWAIT] += (__force u64)cputime;
++ else
++ cpustat[CPUTIME_IDLE] += (__force u64)cputime;
++}
++
++#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
++
++void account_process_tick(struct task_struct *p, int user_tick)
++{
++}
++
++/*
++ * Account multiple ticks of steal time.
++ * @p: the process from which the cpu time has been stolen
++ * @ticks: number of stolen ticks
++ */
++void account_steal_ticks(unsigned long ticks)
++{
++ account_steal_time(jiffies_to_cputime(ticks));
++}
++
++/*
++ * Account multiple ticks of idle time.
++ * @ticks: number of stolen ticks
++ */
++void account_idle_ticks(unsigned long ticks)
++{
++ account_idle_times(jiffies_to_cputime(ticks));
++}
++#endif
++
++static inline void grq_iso_lock(void)
++ __acquires(grq.iso_lock)
++{
++ raw_spin_lock(&grq.iso_lock);
++}
++
++static inline void grq_iso_unlock(void)
++ __releases(grq.iso_lock)
++{
++ raw_spin_unlock(&grq.iso_lock);
++}
++
++/*
++ * Functions to test for when SCHED_ISO tasks have used their allocated
++ * quota as real time scheduling and convert them back to SCHED_NORMAL.
++ * Where possible, the data is tested lockless, to avoid grabbing iso_lock
++ * because the occasional inaccurate result won't matter. However the
++ * tick data is only ever modified under lock. iso_refractory is only simply
++ * set to 0 or 1 so it's not worth grabbing the lock yet again for that.
++ */
++static bool set_iso_refractory(void)
++{
++ grq.iso_refractory = true;
++ return grq.iso_refractory;
++}
++
++static bool clear_iso_refractory(void)
++{
++ grq.iso_refractory = false;
++ return grq.iso_refractory;
++}
++
++/*
++ * Test if SCHED_ISO tasks have run longer than their alloted period as RT
++ * tasks and set the refractory flag if necessary. There is 10% hysteresis
++ * for unsetting the flag. 115/128 is ~90/100 as a fast shift instead of a
++ * slow division.
++ */
++static bool test_ret_isorefractory(struct rq *rq)
++{
++ if (likely(!grq.iso_refractory)) {
++ if (grq.iso_ticks > ISO_PERIOD * sched_iso_cpu)
++ return set_iso_refractory();
++ } else {
++ if (grq.iso_ticks < ISO_PERIOD * (sched_iso_cpu * 115 / 128))
++ return clear_iso_refractory();
++ }
++ return grq.iso_refractory;
++}
++
++static void iso_tick(void)
++{
++ grq_iso_lock();
++ grq.iso_ticks += 100;
++ grq_iso_unlock();
++}
++
++/* No SCHED_ISO task was running so decrease rq->iso_ticks */
++static inline void no_iso_tick(void)
++{
++ if (grq.iso_ticks) {
++ grq_iso_lock();
++ grq.iso_ticks -= grq.iso_ticks / ISO_PERIOD + 1;
++ if (unlikely(grq.iso_refractory && grq.iso_ticks <
++ ISO_PERIOD * (sched_iso_cpu * 115 / 128)))
++ clear_iso_refractory();
++ grq_iso_unlock();
++ }
++}
++
++/* This manages tasks that have run out of timeslice during a scheduler_tick */
++static void task_running_tick(struct rq *rq)
++{
++ struct task_struct *p;
++
++ /*
++ * If a SCHED_ISO task is running we increment the iso_ticks. In
++ * order to prevent SCHED_ISO tasks from causing starvation in the
++ * presence of true RT tasks we account those as iso_ticks as well.
++ */
++ if ((rt_queue(rq) || (iso_queue(rq) && !grq.iso_refractory))) {
++ if (grq.iso_ticks <= (ISO_PERIOD * 128) - 128)
++ iso_tick();
++ } else
++ no_iso_tick();
++
++ if (iso_queue(rq)) {
++ if (unlikely(test_ret_isorefractory(rq))) {
++ if (rq_running_iso(rq)) {
++ /*
++ * SCHED_ISO task is running as RT and limit
++ * has been hit. Force it to reschedule as
++ * SCHED_NORMAL by zeroing its time_slice
++ */
++ rq->rq_time_slice = 0;
++ }
++ }
++ }
++
++ /* SCHED_FIFO tasks never run out of timeslice. */
++ if (rq->rq_policy == SCHED_FIFO)
++ return;
++ /*
++ * Tasks that were scheduled in the first half of a tick are not
++ * allowed to run into the 2nd half of the next tick if they will
++ * run out of time slice in the interim. Otherwise, if they have
++ * less than RESCHED_US μs of time slice left they will be rescheduled.
++ */
++ if (rq->dither) {
++ if (rq->rq_time_slice > HALF_JIFFY_US)
++ return;
++ else
++ rq->rq_time_slice = 0;
++ } else if (rq->rq_time_slice >= RESCHED_US)
++ return;
++
++ /* p->time_slice < RESCHED_US. We only modify task_struct under grq lock */
++ p = rq->curr;
++ grq_lock();
++ requeue_task(p);
++ set_tsk_need_resched(p);
++ grq_unlock();
++}
++
++/*
++ * This function gets called by the timer code, with HZ frequency.
++ * We call it with interrupts disabled. The data modified is all
++ * local to struct rq so we don't need to grab grq lock.
++ */
++void scheduler_tick(void)
++{
++ int cpu __maybe_unused = smp_processor_id();
++ struct rq *rq = cpu_rq(cpu);
++
++ sched_clock_tick();
++ /* grq lock not grabbed, so only update rq clock */
++ update_rq_clock(rq);
++ update_cpu_clock_tick(rq, rq->curr);
++ if (!rq_idle(rq))
++ task_running_tick(rq);
++ else
++ no_iso_tick();
++ rq->last_tick = rq->clock;
++ perf_event_task_tick();
++}
++
++notrace unsigned long get_parent_ip(unsigned long addr)
++{
++ if (in_lock_functions(addr)) {
++ addr = CALLER_ADDR2;
++ if (in_lock_functions(addr))
++ addr = CALLER_ADDR3;
++ }
++ return addr;
++}
++
++#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
++ defined(CONFIG_PREEMPT_TRACER))
++void __kprobes add_preempt_count(int val)
++{
++#ifdef CONFIG_DEBUG_PREEMPT
++ /*
++ * Underflow?
++ */
++ if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0)))
++ return;
++#endif
++ preempt_count() += val;
++#ifdef CONFIG_DEBUG_PREEMPT
++ /*
++ * Spinlock count overflowing soon?
++ */
++ DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >=
++ PREEMPT_MASK - 10);
++#endif
++ if (preempt_count() == val)
++ trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
++}
++EXPORT_SYMBOL(add_preempt_count);
++
++void __kprobes sub_preempt_count(int val)
++{
++#ifdef CONFIG_DEBUG_PREEMPT
++ /*
++ * Underflow?
++ */
++ if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
++ return;
++ /*
++ * Is the spinlock portion underflowing?
++ */
++ if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) &&
++ !(preempt_count() & PREEMPT_MASK)))
++ return;
++#endif
++
++ if (preempt_count() == val)
++ trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
++ preempt_count() -= val;
++}
++EXPORT_SYMBOL(sub_preempt_count);
++#endif
++
++/*
++ * Deadline is "now" in niffies + (offset by priority). Setting the deadline
++ * is the key to everything. It distributes cpu fairly amongst tasks of the
++ * same nice value, it proportions cpu according to nice level, it means the
++ * task that last woke up the longest ago has the earliest deadline, thus
++ * ensuring that interactive tasks get low latency on wake up. The CPU
++ * proportion works out to the square of the virtual deadline difference, so
++ * this equation will give nice 19 3% CPU compared to nice 0.
++ */
++static inline u64 prio_deadline_diff(int user_prio)
++{
++ return (prio_ratios[user_prio] * rr_interval * (MS_TO_NS(1) / 128));
++}
++
++static inline u64 task_deadline_diff(struct task_struct *p)
++{
++ return prio_deadline_diff(TASK_USER_PRIO(p));
++}
++
++static inline u64 static_deadline_diff(int static_prio)
++{
++ return prio_deadline_diff(USER_PRIO(static_prio));
++}
++
++static inline int longest_deadline_diff(void)
++{
++ return prio_deadline_diff(39);
++}
++
++static inline int ms_longest_deadline_diff(void)
++{
++ return NS_TO_MS(longest_deadline_diff());
++}
++
++/*
++ * The time_slice is only refilled when it is empty and that is when we set a
++ * new deadline.
++ */
++static void time_slice_expired(struct task_struct *p)
++{
++ p->time_slice = timeslice();
++ p->deadline = grq.niffies + task_deadline_diff(p);
++}
++
++/*
++ * Timeslices below RESCHED_US are considered as good as expired as there's no
++ * point rescheduling when there's so little time left. SCHED_BATCH tasks
++ * have been flagged be not latency sensitive and likely to be fully CPU
++ * bound so every time they're rescheduled they have their time_slice
++ * refilled, but get a new later deadline to have little effect on
++ * SCHED_NORMAL tasks.
++
++ */
++static inline void check_deadline(struct task_struct *p)
++{
++ if (p->time_slice < RESCHED_US || batch_task(p))
++ time_slice_expired(p);
++}
++
++#define BITOP_WORD(nr) ((nr) / BITS_PER_LONG)
++
++/*
++ * Scheduler queue bitmap specific find next bit.
++ */
++static inline unsigned long
++next_sched_bit(const unsigned long *addr, unsigned long offset)
++{
++ const unsigned long *p;
++ unsigned long result;
++ unsigned long size;
++ unsigned long tmp;
++
++ size = PRIO_LIMIT;
++ if (offset >= size)
++ return size;
++
++ p = addr + BITOP_WORD(offset);
++ result = offset & ~(BITS_PER_LONG-1);
++ size -= result;
++ offset %= BITS_PER_LONG;
++ if (offset) {
++ tmp = *(p++);
++ tmp &= (~0UL << offset);
++ if (size < BITS_PER_LONG)
++ goto found_first;
++ if (tmp)
++ goto found_middle;
++ size -= BITS_PER_LONG;
++ result += BITS_PER_LONG;
++ }
++ while (size & ~(BITS_PER_LONG-1)) {
++ if ((tmp = *(p++)))
++ goto found_middle;
++ result += BITS_PER_LONG;
++ size -= BITS_PER_LONG;
++ }
++ if (!size)
++ return result;
++ tmp = *p;
++
++found_first:
++ tmp &= (~0UL >> (BITS_PER_LONG - size));
++ if (tmp == 0UL) /* Are any bits set? */
++ return result + size; /* Nope. */
++found_middle:
++ return result + __ffs(tmp);
++}
++
++/*
++ * O(n) lookup of all tasks in the global runqueue. The real brainfuck
++ * of lock contention and O(n). It's not really O(n) as only the queued,
++ * but not running tasks are scanned, and is O(n) queued in the worst case
++ * scenario only because the right task can be found before scanning all of
++ * them.
++ * Tasks are selected in this order:
++ * Real time tasks are selected purely by their static priority and in the
++ * order they were queued, so the lowest value idx, and the first queued task
++ * of that priority value is chosen.
++ * If no real time tasks are found, the SCHED_ISO priority is checked, and
++ * all SCHED_ISO tasks have the same priority value, so they're selected by
++ * the earliest deadline value.
++ * If no SCHED_ISO tasks are found, SCHED_NORMAL tasks are selected by the
++ * earliest deadline.
++ * Finally if no SCHED_NORMAL tasks are found, SCHED_IDLEPRIO tasks are
++ * selected by the earliest deadline.
++ */
++static inline struct
++task_struct *earliest_deadline_task(struct rq *rq, int cpu, struct task_struct *idle)
++{
++ struct task_struct *edt = NULL;
++ unsigned long idx = -1;
++
++ do {
++ struct list_head *queue;
++ struct task_struct *p;
++ u64 earliest_deadline;
++
++ idx = next_sched_bit(grq.prio_bitmap, ++idx);
++ if (idx >= PRIO_LIMIT)
++ return idle;
++ queue = grq.queue + idx;
++
++ if (idx < MAX_RT_PRIO) {
++ /* We found an rt task */
++ list_for_each_entry(p, queue, run_list) {
++ /* Make sure cpu affinity is ok */
++ if (needs_other_cpu(p, cpu))
++ continue;
++ edt = p;
++ goto out_take;
++ }
++ /*
++ * None of the RT tasks at this priority can run on
++ * this cpu
++ */
++ continue;
++ }
++
++ /*
++ * No rt tasks. Find the earliest deadline task. Now we're in
++ * O(n) territory.
++ */
++ earliest_deadline = ~0ULL;
++ list_for_each_entry(p, queue, run_list) {
++ u64 dl;
++
++ /* Make sure cpu affinity is ok */
++ if (needs_other_cpu(p, cpu))
++ continue;
++
++ /*
++ * Soft affinity happens here by not scheduling a task
++ * with its sticky flag set that ran on a different CPU
++ * last when the CPU is scaling, or by greatly biasing
++ * against its deadline when not, based on cpu cache
++ * locality.
++ */
++ if (task_sticky(p) && task_rq(p) != rq) {
++ if (scaling_rq(rq))
++ continue;
++ dl = p->deadline << locality_diff(p, rq);
++ } else
++ dl = p->deadline;
++
++ if (deadline_before(dl, earliest_deadline)) {
++ earliest_deadline = dl;
++ edt = p;
++ }
++ }
++ } while (!edt);
++
++out_take:
++ take_task(cpu, edt);
++ return edt;
++}
++
++
++/*
++ * Print scheduling while atomic bug:
++ */
++static noinline void __schedule_bug(struct task_struct *prev)
++{
++ if (oops_in_progress)
++ return;
++
++ printk(KERN_ERR "BUG: scheduling while atomic: %s/%d/0x%08x\n",
++ prev->comm, prev->pid, preempt_count());
++
++ debug_show_held_locks(prev);
++ print_modules();
++ if (irqs_disabled())
++ print_irqtrace_events(prev);
++ dump_stack();
++ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
++}
++
++/*
++ * Various schedule()-time debugging checks and statistics:
++ */
++static inline void schedule_debug(struct task_struct *prev)
++{
++ /*
++ * Test if we are atomic. Since do_exit() needs to call into
++ * schedule() atomically, we ignore that path for now.
++ * Otherwise, whine if we are scheduling when we should not be.
++ */
++ if (unlikely(in_atomic_preempt_off() && !prev->exit_state))
++ __schedule_bug(prev);
++ rcu_sleep_check();
++
++ profile_hit(SCHED_PROFILING, __builtin_return_address(0));
++
++ schedstat_inc(this_rq(), sched_count);
++}
++
++/*
++ * The currently running task's information is all stored in rq local data
++ * which is only modified by the local CPU, thereby allowing the data to be
++ * changed without grabbing the grq lock.
++ */
++static inline void set_rq_task(struct rq *rq, struct task_struct *p)
++{
++ rq->rq_time_slice = p->time_slice;
++ rq->rq_deadline = p->deadline;
++ rq->rq_last_ran = p->last_ran = rq->clock_task;
++ rq->rq_policy = p->policy;
++ rq->rq_prio = p->prio;
++ if (p != rq->idle)
++ rq->rq_running = true;
++ else
++ rq->rq_running = false;
++}
++
++static void reset_rq_task(struct rq *rq, struct task_struct *p)
++{
++ rq->rq_policy = p->policy;
++ rq->rq_prio = p->prio;
++}
++
++/*
++ * schedule() is the main scheduler function.
++ *
++ * The main means of driving the scheduler and thus entering this function are:
++ *
++ * 1. Explicit blocking: mutex, semaphore, waitqueue, etc.
++ *
++ * 2. TIF_NEED_RESCHED flag is checked on interrupt and userspace return
++ * paths. For example, see arch/x86/entry_64.S.
++ *
++ * To drive preemption between tasks, the scheduler sets the flag in timer
++ * interrupt handler scheduler_tick().
++ *
++ * 3. Wakeups don't really cause entry into schedule(). They add a
++ * task to the run-queue and that's it.
++ *
++ * Now, if the new task added to the run-queue preempts the current
++ * task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets
++ * called on the nearest possible occasion:
++ *
++ * - If the kernel is preemptible (CONFIG_PREEMPT=y):
++ *
++ * - in syscall or exception context, at the next outmost
++ * preempt_enable(). (this might be as soon as the wake_up()'s
++ * spin_unlock()!)
++ *
++ * - in IRQ context, return from interrupt-handler to
++ * preemptible context
++ *
++ * - If the kernel is not preemptible (CONFIG_PREEMPT is not set)
++ * then at the next:
++ *
++ * - cond_resched() call
++ * - explicit schedule() call
++ * - return from syscall or exception to user-space
++ * - return from interrupt-handler to user-space
++ */
++asmlinkage void __sched schedule(void)
++{
++ struct task_struct *prev, *next, *idle;
++ unsigned long *switch_count;
++ bool deactivate;
++ struct rq *rq;
++ int cpu;
++
++need_resched:
++ preempt_disable();
++ cpu = smp_processor_id();
++ rq = cpu_rq(cpu);
++ rcu_note_context_switch(cpu);
++ prev = rq->curr;
++
++ deactivate = false;
++ schedule_debug(prev);
++
++ grq_lock_irq();
++
++ switch_count = &prev->nivcsw;
++ if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
++ if (unlikely(signal_pending_state(prev->state, prev))) {
++ prev->state = TASK_RUNNING;
++ } else {
++ deactivate = true;
++ /*
++ * If a worker is going to sleep, notify and
++ * ask workqueue whether it wants to wake up a
++ * task to maintain concurrency. If so, wake
++ * up the task.
++ */
++ if (prev->flags & PF_WQ_WORKER) {
++ struct task_struct *to_wakeup;
++
++ to_wakeup = wq_worker_sleeping(prev, cpu);
++ if (to_wakeup) {
++ /* This shouldn't happen, but does */
++ if (unlikely(to_wakeup == prev))
++ deactivate = false;
++ else
++ try_to_wake_up_local(to_wakeup);
++ }
++ }
++ }
++ switch_count = &prev->nvcsw;
++ }
++
++ /*
++ * If we are going to sleep and we have plugged IO queued, make
++ * sure to submit it to avoid deadlocks.
++ */
++ if (unlikely(deactivate && blk_needs_flush_plug(prev))) {
++ grq_unlock_irq();
++ preempt_enable_no_resched();
++ blk_schedule_flush_plug(prev);
++ goto need_resched;
++ }
++
++ update_clocks(rq);
++ update_cpu_clock_switch(rq, prev);
++ if (rq->clock - rq->last_tick > HALF_JIFFY_NS)
++ rq->dither = false;
++ else
++ rq->dither = true;
++
++ clear_tsk_need_resched(prev);
++
++ idle = rq->idle;
++ if (idle != prev) {
++ /* Update all the information stored on struct rq */
++ prev->time_slice = rq->rq_time_slice;
++ prev->deadline = rq->rq_deadline;
++ check_deadline(prev);
++ prev->last_ran = rq->clock_task;
++
++ /* Task changed affinity off this CPU */
++ if (needs_other_cpu(prev, cpu)) {
++ if (!deactivate)
++ resched_suitable_idle(prev);
++ } else if (!deactivate) {
++ if (!queued_notrunning()) {
++ /*
++ * We now know prev is the only thing that is
++ * awaiting CPU so we can bypass rechecking for
++ * the earliest deadline task and just run it
++ * again.
++ */
++ set_rq_task(rq, prev);
++ grq_unlock_irq();
++ goto rerun_prev_unlocked;
++ } else
++ swap_sticky(rq, cpu, prev);
++ }
++ return_task(prev, deactivate);
++ }
++
++ if (unlikely(!queued_notrunning())) {
++ /*
++ * This CPU is now truly idle as opposed to when idle is
++ * scheduled as a high priority task in its own right.
++ */
++ next = idle;
++ schedstat_inc(rq, sched_goidle);
++ set_cpuidle_map(cpu);
++ } else {
++ next = earliest_deadline_task(rq, cpu, idle);
++ if (likely(next->prio != PRIO_LIMIT))
++ clear_cpuidle_map(cpu);
++ else
++ set_cpuidle_map(cpu);
++ }
++
++ if (likely(prev != next)) {
++ resched_suitable_idle(prev);
++ /*
++ * Don't stick tasks when a real time task is going to run as
++ * they may literally get stuck.
++ */
++ if (rt_task(next))
++ unstick_task(rq, prev);
++ set_rq_task(rq, next);
++ grq.nr_switches++;
++ prev->on_cpu = false;
++ next->on_cpu = true;
++ rq->curr = next;
++ ++*switch_count;
++
++ context_switch(rq, prev, next); /* unlocks the grq */
++ /*
++ * The context switch have flipped the stack from under us
++ * and restored the local variables which were saved when
++ * this task called schedule() in the past. prev == current
++ * is still correct, but it can be moved to another cpu/rq.
++ */
++ cpu = smp_processor_id();
++ rq = cpu_rq(cpu);
++ idle = rq->idle;
++ } else
++ grq_unlock_irq();
++
++rerun_prev_unlocked:
++ sched_preempt_enable_no_resched();
++ if (unlikely(need_resched()))
++ goto need_resched;
++}
++EXPORT_SYMBOL(schedule);
++
++#ifdef CONFIG_RCU_USER_QS
++asmlinkage void __sched schedule_user(void)
++{
++ /*
++ * If we come here after a random call to set_need_resched(),
++ * or we have been woken up remotely but the IPI has not yet arrived,
++ * we haven't yet exited the RCU idle mode. Do it here manually until
++ * we find a better solution.
++ */
++ user_exit();
++ schedule();
++ user_enter();
++}
++#endif
++
++/**
++ * schedule_preempt_disabled - called with preemption disabled
++ *
++ * Returns with preemption disabled. Note: preempt_count must be 1
++ */
++void __sched schedule_preempt_disabled(void)
++{
++ sched_preempt_enable_no_resched();
++ schedule();
++ preempt_disable();
++}
++
++#ifdef CONFIG_PREEMPT
++/*
++ * this is the entry point to schedule() from in-kernel preemption
++ * off of preempt_enable. Kernel preemptions off return from interrupt
++ * occur there and call schedule directly.
++ */
++asmlinkage void __sched notrace preempt_schedule(void)
++{
++ struct thread_info *ti = current_thread_info();
++
++ /*
++ * If there is a non-zero preempt_count or interrupts are disabled,
++ * we do not want to preempt the current task. Just return..
++ */
++ if (likely(ti->preempt_count || irqs_disabled()))
++ return;
++
++ do {
++ add_preempt_count_notrace(PREEMPT_ACTIVE);
++ schedule();
++ sub_preempt_count_notrace(PREEMPT_ACTIVE);
++
++ /*
++ * Check again in case we missed a preemption opportunity
++ * between schedule and now.
++ */
++ barrier();
++ } while (need_resched());
++}
++EXPORT_SYMBOL(preempt_schedule);
++
++/*
++ * this is the entry point to schedule() from kernel preemption
++ * off of irq context.
++ * Note, that this is called and return with irqs disabled. This will
++ * protect us against recursive calling from irq.
++ */
++asmlinkage void __sched preempt_schedule_irq(void)
++{
++ struct thread_info *ti = current_thread_info();
++ enum ctx_state prev_state;
++
++ /* Catch callers which need to be fixed */
++ BUG_ON(ti->preempt_count || !irqs_disabled());
++
++ prev_state = exception_enter();
++
++ do {
++ add_preempt_count(PREEMPT_ACTIVE);
++ local_irq_enable();
++ schedule();
++ local_irq_disable();
++ sub_preempt_count(PREEMPT_ACTIVE);
++
++ /*
++ * Check again in case we missed a preemption opportunity
++ * between schedule and now.
++ */
++ barrier();
++ } while (need_resched());
++
++ exception_exit(prev_state);
++}
++
++#endif /* CONFIG_PREEMPT */
++
++int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags,
++ void *key)
++{
++ return try_to_wake_up(curr->private, mode, wake_flags);
++}
++EXPORT_SYMBOL(default_wake_function);
++
++/*
++ * The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just
++ * wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve
++ * number) then we wake all the non-exclusive tasks and one exclusive task.
++ *
++ * There are circumstances in which we can try to wake a task which has already
++ * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
++ * zero in this (rare) case, and we handle it by continuing to scan the queue.
++ */
++static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
++ int nr_exclusive, int wake_flags, void *key)
++{
++ struct list_head *tmp, *next;
++
++ list_for_each_safe(tmp, next, &q->task_list) {
++ wait_queue_t *curr = list_entry(tmp, wait_queue_t, task_list);
++ unsigned int flags = curr->flags;
++
++ if (curr->func(curr, mode, wake_flags, key) &&
++ (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
++ break;
++ }
++}
++
++/**
++ * __wake_up - wake up threads blocked on a waitqueue.
++ * @q: the waitqueue
++ * @mode: which threads
++ * @nr_exclusive: how many wake-one or wake-many threads to wake up
++ * @key: is directly passed to the wakeup function
++ *
++ * It may be assumed that this function implies a write memory barrier before
++ * changing the task state if and only if any tasks are woken up.
++ */
++void __wake_up(wait_queue_head_t *q, unsigned int mode,
++ int nr_exclusive, void *key)
++{
++ unsigned long flags;
++
++ spin_lock_irqsave(&q->lock, flags);
++ __wake_up_common(q, mode, nr_exclusive, 0, key);
++ spin_unlock_irqrestore(&q->lock, flags);
++}
++EXPORT_SYMBOL(__wake_up);
++
++/*
++ * Same as __wake_up but called with the spinlock in wait_queue_head_t held.
++ */
++void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr)
++{
++ __wake_up_common(q, mode, nr, 0, NULL);
++}
++EXPORT_SYMBOL_GPL(__wake_up_locked);
++
++void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
++{
++ __wake_up_common(q, mode, 1, 0, key);
++}
++EXPORT_SYMBOL_GPL(__wake_up_locked_key);
++
++/**
++ * __wake_up_sync_key - wake up threads blocked on a waitqueue.
++ * @q: the waitqueue
++ * @mode: which threads
++ * @nr_exclusive: how many wake-one or wake-many threads to wake up
++ * @key: opaque value to be passed to wakeup targets
++ *
++ * The sync wakeup differs that the waker knows that it will schedule
++ * away soon, so while the target thread will be woken up, it will not
++ * be migrated to another CPU - ie. the two threads are 'synchronised'
++ * with each other. This can prevent needless bouncing between CPUs.
++ *
++ * On UP it can prevent extra preemption.
++ *
++ * It may be assumed that this function implies a write memory barrier before
++ * changing the task state if and only if any tasks are woken up.
++ */
++void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode,
++ int nr_exclusive, void *key)
++{
++ unsigned long flags;
++ int wake_flags = WF_SYNC;
++
++ if (unlikely(!q))
++ return;
++
++ if (unlikely(!nr_exclusive))
++ wake_flags = 0;
++
++ spin_lock_irqsave(&q->lock, flags);
++ __wake_up_common(q, mode, nr_exclusive, wake_flags, key);
++ spin_unlock_irqrestore(&q->lock, flags);
++}
++EXPORT_SYMBOL_GPL(__wake_up_sync_key);
++
++/**
++ * __wake_up_sync - wake up threads blocked on a waitqueue.
++ * @q: the waitqueue
++ * @mode: which threads
++ * @nr_exclusive: how many wake-one or wake-many threads to wake up
++ *
++ * The sync wakeup differs that the waker knows that it will schedule
++ * away soon, so while the target thread will be woken up, it will not
++ * be migrated to another CPU - ie. the two threads are 'synchronised'
++ * with each other. This can prevent needless bouncing between CPUs.
++ *
++ * On UP it can prevent extra preemption.
++ */
++void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
++{
++ unsigned long flags;
++ int sync = 1;
++
++ if (unlikely(!q))
++ return;
++
++ if (unlikely(!nr_exclusive))
++ sync = 0;
++
++ spin_lock_irqsave(&q->lock, flags);
++ __wake_up_common(q, mode, nr_exclusive, sync, NULL);
++ spin_unlock_irqrestore(&q->lock, flags);
++}
++EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */
++
++/**
++ * complete: - signals a single thread waiting on this completion
++ * @x: holds the state of this particular completion
++ *
++ * This will wake up a single thread waiting on this completion. Threads will be
++ * awakened in the same order in which they were queued.
++ *
++ * See also complete_all(), wait_for_completion() and related routines.
++ *
++ * It may be assumed that this function implies a write memory barrier before
++ * changing the task state if and only if any tasks are woken up.
++ */
++void complete(struct completion *x)
++{
++ unsigned long flags;
++
++ spin_lock_irqsave(&x->wait.lock, flags);
++ x->done++;
++ __wake_up_common(&x->wait, TASK_NORMAL, 1, 0, NULL);
++ spin_unlock_irqrestore(&x->wait.lock, flags);
++}
++EXPORT_SYMBOL(complete);
++
++/**
++ * complete_all: - signals all threads waiting on this completion
++ * @x: holds the state of this particular completion
++ *
++ * This will wake up all threads waiting on this particular completion event.
++ *
++ * It may be assumed that this function implies a write memory barrier before
++ * changing the task state if and only if any tasks are woken up.
++ */
++void complete_all(struct completion *x)
++{
++ unsigned long flags;
++
++ spin_lock_irqsave(&x->wait.lock, flags);
++ x->done += UINT_MAX/2;
++ __wake_up_common(&x->wait, TASK_NORMAL, 0, 0, NULL);
++ spin_unlock_irqrestore(&x->wait.lock, flags);
++}
++EXPORT_SYMBOL(complete_all);
++
++static inline long __sched
++do_wait_for_common(struct completion *x,
++ long (*action)(long), long timeout, int state)
++{
++ if (!x->done) {
++ DECLARE_WAITQUEUE(wait, current);
++
++ __add_wait_queue_tail_exclusive(&x->wait, &wait);
++ do {
++ if (signal_pending_state(state, current)) {
++ timeout = -ERESTARTSYS;
++ break;
++ }
++ __set_current_state(state);
++ spin_unlock_irq(&x->wait.lock);
++ timeout = action(timeout);
++ spin_lock_irq(&x->wait.lock);
++ } while (!x->done && timeout);
++ __remove_wait_queue(&x->wait, &wait);
++ if (!x->done)
++ return timeout;
++ }
++ x->done--;
++ return timeout ?: 1;
++}
++
++static inline long __sched
++__wait_for_common(struct completion *x,
++ long (*action)(long), long timeout, int state)
++{
++ might_sleep();
++
++ spin_lock_irq(&x->wait.lock);
++ timeout = do_wait_for_common(x, action, timeout, state);
++ spin_unlock_irq(&x->wait.lock);
++ return timeout;
++}
++
++static long __sched
++wait_for_common(struct completion *x, long timeout, int state)
++{
++ return __wait_for_common(x, schedule_timeout, timeout, state);
++}
++
++static long __sched
++wait_for_common_io(struct completion *x, long timeout, int state)
++{
++ return __wait_for_common(x, io_schedule_timeout, timeout, state);
++}
++
++/**
++ * wait_for_completion: - waits for completion of a task
++ * @x: holds the state of this particular completion
++ *
++ * This waits to be signaled for completion of a specific task. It is NOT
++ * interruptible and there is no timeout.
++ *
++ * See also similar routines (i.e. wait_for_completion_timeout()) with timeout
++ * and interrupt capability. Also see complete().
++ */
++void __sched wait_for_completion(struct completion *x)
++{
++ wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
++}
++EXPORT_SYMBOL(wait_for_completion);
++
++/**
++ * wait_for_completion_timeout: - waits for completion of a task (w/timeout)
++ * @x: holds the state of this particular completion
++ * @timeout: timeout value in jiffies
++ *
++ * This waits for either a completion of a specific task to be signaled or for a
++ * specified timeout to expire. The timeout is in jiffies. It is not
++ * interruptible.
++ *
++ * The return value is 0 if timed out, and positive (at least 1, or number of
++ * jiffies left till timeout) if completed.
++ */
++unsigned long __sched
++wait_for_completion_timeout(struct completion *x, unsigned long timeout)
++{
++ return wait_for_common(x, timeout, TASK_UNINTERRUPTIBLE);
++}
++EXPORT_SYMBOL(wait_for_completion_timeout);
++
++ /**
++ * wait_for_completion_io: - waits for completion of a task
++ * @x: holds the state of this particular completion
++ *
++ * This waits to be signaled for completion of a specific task. It is NOT
++ * interruptible and there is no timeout. The caller is accounted as waiting
++ * for IO.
++ */
++void __sched wait_for_completion_io(struct completion *x)
++{
++ wait_for_common_io(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
++}
++EXPORT_SYMBOL(wait_for_completion_io);
++
++/**
++ * wait_for_completion_io_timeout: - waits for completion of a task (w/timeout)
++ * @x: holds the state of this particular completion
++ * @timeout: timeout value in jiffies
++ *
++ * This waits for either a completion of a specific task to be signaled or for a
++ * specified timeout to expire. The timeout is in jiffies. It is not
++ * interruptible. The caller is accounted as waiting for IO.
++ *
++ * The return value is 0 if timed out, and positive (at least 1, or number of
++ * jiffies left till timeout) if completed.
++ */
++unsigned long __sched
++wait_for_completion_io_timeout(struct completion *x, unsigned long timeout)
++{
++ return wait_for_common_io(x, timeout, TASK_UNINTERRUPTIBLE);
++}
++EXPORT_SYMBOL(wait_for_completion_io_timeout);
++
++/**
++ * wait_for_completion_interruptible: - waits for completion of a task (w/intr)
++ * @x: holds the state of this particular completion
++ *
++ * This waits for completion of a specific task to be signaled. It is
++ * interruptible.
++ *
++ * The return value is -ERESTARTSYS if interrupted, 0 if completed.
++ */
++int __sched wait_for_completion_interruptible(struct completion *x)
++{
++ long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE);
++ if (t == -ERESTARTSYS)
++ return t;
++ return 0;
++}
++EXPORT_SYMBOL(wait_for_completion_interruptible);
++
++/**
++ * wait_for_completion_interruptible_timeout: - waits for completion (w/(to,intr))
++ * @x: holds the state of this particular completion
++ * @timeout: timeout value in jiffies
++ *
++ * This waits for either a completion of a specific task to be signaled or for a
++ * specified timeout to expire. It is interruptible. The timeout is in jiffies.
++ *
++ * The return value is -ERESTARTSYS if interrupted, 0 if timed out,
++ * positive (at least 1, or number of jiffies left till timeout) if completed.
++ */
++long __sched
++wait_for_completion_interruptible_timeout(struct completion *x,
++ unsigned long timeout)
++{
++ return wait_for_common(x, timeout, TASK_INTERRUPTIBLE);
++}
++EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
++
++/**
++ * wait_for_completion_killable: - waits for completion of a task (killable)
++ * @x: holds the state of this particular completion
++ *
++ * This waits to be signaled for completion of a specific task. It can be
++ * interrupted by a kill signal.
++ *
++ * The return value is -ERESTARTSYS if interrupted, 0 if timed out,
++ * positive (at least 1, or number of jiffies left till timeout) if completed.
++ */
++int __sched wait_for_completion_killable(struct completion *x)
++{
++ long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE);
++ if (t == -ERESTARTSYS)
++ return t;
++ return 0;
++}
++EXPORT_SYMBOL(wait_for_completion_killable);
++
++/**
++ * wait_for_completion_killable_timeout: - waits for completion of a task (w/(to,killable))
++ * @x: holds the state of this particular completion
++ * @timeout: timeout value in jiffies
++ *
++ * This waits for either a completion of a specific task to be
++ * signaled or for a specified timeout to expire. It can be
++ * interrupted by a kill signal. The timeout is in jiffies.
++ */
++long __sched
++wait_for_completion_killable_timeout(struct completion *x,
++ unsigned long timeout)
++{
++ return wait_for_common(x, timeout, TASK_KILLABLE);
++}
++EXPORT_SYMBOL(wait_for_completion_killable_timeout);
++
++/**
++ * try_wait_for_completion - try to decrement a completion without blocking
++ * @x: completion structure
++ *
++ * Returns: 0 if a decrement cannot be done without blocking
++ * 1 if a decrement succeeded.
++ *
++ * If a completion is being used as a counting completion,
++ * attempt to decrement the counter without blocking. This
++ * enables us to avoid waiting if the resource the completion
++ * is protecting is not available.
++ */
++bool try_wait_for_completion(struct completion *x)
++{
++ unsigned long flags;
++ int ret = 1;
++
++ spin_lock_irqsave(&x->wait.lock, flags);
++ if (!x->done)
++ ret = 0;
++ else
++ x->done--;
++ spin_unlock_irqrestore(&x->wait.lock, flags);
++ return ret;
++}
++EXPORT_SYMBOL(try_wait_for_completion);
++
++/**
++ * completion_done - Test to see if a completion has any waiters
++ * @x: completion structure
++ *
++ * Returns: 0 if there are waiters (wait_for_completion() in progress)
++ * 1 if there are no waiters.
++ *
++ */
++bool completion_done(struct completion *x)
++{
++ unsigned long flags;
++ int ret = 1;
++
++ spin_lock_irqsave(&x->wait.lock, flags);
++ if (!x->done)
++ ret = 0;
++ spin_unlock_irqrestore(&x->wait.lock, flags);
++ return ret;
++}
++EXPORT_SYMBOL(completion_done);
++
++static long __sched
++sleep_on_common(wait_queue_head_t *q, int state, long timeout)
++{
++ unsigned long flags;
++ wait_queue_t wait;
++
++ init_waitqueue_entry(&wait, current);
++
++ __set_current_state(state);
++
++ spin_lock_irqsave(&q->lock, flags);
++ __add_wait_queue(q, &wait);
++ spin_unlock(&q->lock);
++ timeout = schedule_timeout(timeout);
++ spin_lock_irq(&q->lock);
++ __remove_wait_queue(q, &wait);
++ spin_unlock_irqrestore(&q->lock, flags);
++
++ return timeout;
++}
++
++void __sched interruptible_sleep_on(wait_queue_head_t *q)
++{
++ sleep_on_common(q, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
++}
++EXPORT_SYMBOL(interruptible_sleep_on);
++
++long __sched
++interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout)
++{
++ return sleep_on_common(q, TASK_INTERRUPTIBLE, timeout);
++}
++EXPORT_SYMBOL(interruptible_sleep_on_timeout);
++
++void __sched sleep_on(wait_queue_head_t *q)
++{
++ sleep_on_common(q, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
++}
++EXPORT_SYMBOL(sleep_on);
++
++long __sched sleep_on_timeout(wait_queue_head_t *q, long timeout)
++{
++ return sleep_on_common(q, TASK_UNINTERRUPTIBLE, timeout);
++}
++EXPORT_SYMBOL(sleep_on_timeout);
++
++#ifdef CONFIG_RT_MUTEXES
++
++/*
++ * rt_mutex_setprio - set the current priority of a task
++ * @p: task
++ * @prio: prio value (kernel-internal form)
++ *
++ * This function changes the 'effective' priority of a task. It does
++ * not touch ->normal_prio like __setscheduler().
++ *
++ * Used by the rt_mutex code to implement priority inheritance logic.
++ */
++void rt_mutex_setprio(struct task_struct *p, int prio)
++{
++ unsigned long flags;
++ int queued, oldprio;
++ struct rq *rq;
++
++ BUG_ON(prio < 0 || prio > MAX_PRIO);
++
++ rq = task_grq_lock(p, &flags);
++
++ /*
++ * Idle task boosting is a nono in general. There is one
++ * exception, when PREEMPT_RT and NOHZ is active:
++ *
++ * The idle task calls get_next_timer_interrupt() and holds
++ * the timer wheel base->lock on the CPU and another CPU wants
++ * to access the timer (probably to cancel it). We can safely
++ * ignore the boosting request, as the idle CPU runs this code
++ * with interrupts disabled and will complete the lock
++ * protected section without being interrupted. So there is no
++ * real need to boost.
++ */
++ if (unlikely(p == rq->idle)) {
++ WARN_ON(p != rq->curr);
++ WARN_ON(p->pi_blocked_on);
++ goto out_unlock;
++ }
++
++ trace_sched_pi_setprio(p, prio);
++ oldprio = p->prio;
++ queued = task_queued(p);
++ if (queued)
++ dequeue_task(p);
++ p->prio = prio;
++ if (task_running(p) && prio > oldprio)
++ resched_task(p);
++ if (queued) {
++ enqueue_task(p);
++ try_preempt(p, rq);
++ }
++
++out_unlock:
++ task_grq_unlock(&flags);
++}
++
++#endif
++
++/*
++ * Adjust the deadline for when the priority is to change, before it's
++ * changed.
++ */
++static inline void adjust_deadline(struct task_struct *p, int new_prio)
++{
++ p->deadline += static_deadline_diff(new_prio) - task_deadline_diff(p);
++}
++
++void set_user_nice(struct task_struct *p, long nice)
++{
++ int queued, new_static, old_static;
++ unsigned long flags;
++ struct rq *rq;
++
++ if (TASK_NICE(p) == nice || nice < -20 || nice > 19)
++ return;
++ new_static = NICE_TO_PRIO(nice);
++ /*
++ * We have to be careful, if called from sys_setpriority(),
++ * the task might be in the middle of scheduling on another CPU.
++ */
++ rq = time_task_grq_lock(p, &flags);
++ /*
++ * The RT priorities are set via sched_setscheduler(), but we still
++ * allow the 'normal' nice value to be set - but as expected
++ * it wont have any effect on scheduling until the task is
++ * not SCHED_NORMAL/SCHED_BATCH:
++ */
++ if (has_rt_policy(p)) {
++ p->static_prio = new_static;
++ goto out_unlock;
++ }
++ queued = task_queued(p);
++ if (queued)
++ dequeue_task(p);
++
++ adjust_deadline(p, new_static);
++ old_static = p->static_prio;
++ p->static_prio = new_static;
++ p->prio = effective_prio(p);
++
++ if (queued) {
++ enqueue_task(p);
++ if (new_static < old_static)
++ try_preempt(p, rq);
++ } else if (task_running(p)) {
++ reset_rq_task(rq, p);
++ if (old_static < new_static)
++ resched_task(p);
++ }
++out_unlock:
++ task_grq_unlock(&flags);
++}
++EXPORT_SYMBOL(set_user_nice);
++
++/*
++ * can_nice - check if a task can reduce its nice value
++ * @p: task
++ * @nice: nice value
++ */
++int can_nice(const struct task_struct *p, const int nice)
++{
++ /* convert nice value [19,-20] to rlimit style value [1,40] */
++ int nice_rlim = 20 - nice;
++
++ return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) ||
++ capable(CAP_SYS_NICE));
++}
++
++#ifdef __ARCH_WANT_SYS_NICE
++
++/*
++ * sys_nice - change the priority of the current process.
++ * @increment: priority increment
++ *
++ * sys_setpriority is a more generic, but much slower function that
++ * does similar things.
++ */
++SYSCALL_DEFINE1(nice, int, increment)
++{
++ long nice, retval;
++
++ /*
++ * Setpriority might change our priority at the same moment.
++ * We don't have to worry. Conceptually one call occurs first
++ * and we have a single winner.
++ */
++ if (increment < -40)
++ increment = -40;
++ if (increment > 40)
++ increment = 40;
++
++ nice = TASK_NICE(current) + increment;
++ if (nice < -20)
++ nice = -20;
++ if (nice > 19)
++ nice = 19;
++
++ if (increment < 0 && !can_nice(current, nice))
++ return -EPERM;
++
++ retval = security_task_setnice(current, nice);
++ if (retval)
++ return retval;
++
++ set_user_nice(current, nice);
++ return 0;
++}
++
++#endif
++
++/**
++ * task_prio - return the priority value of a given task.
++ * @p: the task in question.
++ *
++ * This is the priority value as seen by users in /proc.
++ * RT tasks are offset by -100. Normal tasks are centered around 1, value goes
++ * from 0 (SCHED_ISO) up to 82 (nice +19 SCHED_IDLEPRIO).
++ */
++int task_prio(const struct task_struct *p)
++{
++ int delta, prio = p->prio - MAX_RT_PRIO;
++
++ /* rt tasks and iso tasks */
++ if (prio <= 0)
++ goto out;
++
++ /* Convert to ms to avoid overflows */
++ delta = NS_TO_MS(p->deadline - grq.niffies);
++ delta = delta * 40 / ms_longest_deadline_diff();
++ if (delta > 0 && delta <= 80)
++ prio += delta;
++ if (idleprio_task(p))
++ prio += 40;
++out:
++ return prio;
++}
++
++/**
++ * task_nice - return the nice value of a given task.
++ * @p: the task in question.
++ */
++int task_nice(const struct task_struct *p)
++{
++ return TASK_NICE(p);
++}
++EXPORT_SYMBOL_GPL(task_nice);
++
++/**
++ * idle_cpu - is a given cpu idle currently?
++ * @cpu: the processor in question.
++ */
++int idle_cpu(int cpu)
++{
++ return cpu_curr(cpu) == cpu_rq(cpu)->idle;
++}
++
++/**
++ * idle_task - return the idle task for a given cpu.
++ * @cpu: the processor in question.
++ */
++struct task_struct *idle_task(int cpu)
++{
++ return cpu_rq(cpu)->idle;
++}
++
++/**
++ * find_process_by_pid - find a process with a matching PID value.
++ * @pid: the pid in question.
++ */
++static inline struct task_struct *find_process_by_pid(pid_t pid)
++{
++ return pid ? find_task_by_vpid(pid) : current;
++}
++
++/* Actually do priority change: must hold grq lock. */
++static void
++__setscheduler(struct task_struct *p, struct rq *rq, int policy, int prio)
++{
++ int oldrtprio, oldprio;
++
++ p->policy = policy;
++ oldrtprio = p->rt_priority;
++ p->rt_priority = prio;
++ p->normal_prio = normal_prio(p);
++ oldprio = p->prio;
++ /* we are holding p->pi_lock already */
++ p->prio = rt_mutex_getprio(p);
++ if (task_running(p)) {
++ reset_rq_task(rq, p);
++ /* Resched only if we might now be preempted */
++ if (p->prio > oldprio || p->rt_priority > oldrtprio)
++ resched_task(p);
++ }
++}
++
++/*
++ * check the target process has a UID that matches the current process's
++ */
++static bool check_same_owner(struct task_struct *p)
++{
++ const struct cred *cred = current_cred(), *pcred;
++ bool match;
++
++ rcu_read_lock();
++ pcred = __task_cred(p);
++ match = (uid_eq(cred->euid, pcred->euid) ||
++ uid_eq(cred->euid, pcred->uid));
++ rcu_read_unlock();
++ return match;
++}
++
++static int __sched_setscheduler(struct task_struct *p, int policy,
++ const struct sched_param *param, bool user)
++{
++ struct sched_param zero_param = { .sched_priority = 0 };
++ int queued, retval, oldpolicy = -1;
++ unsigned long flags, rlim_rtprio = 0;
++ int reset_on_fork;
++ struct rq *rq;
++
++ /* may grab non-irq protected spin_locks */
++ BUG_ON(in_interrupt());
++
++ if (is_rt_policy(policy) && !capable(CAP_SYS_NICE)) {
++ unsigned long lflags;
++
++ if (!lock_task_sighand(p, &lflags))
++ return -ESRCH;
++ rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO);
++ unlock_task_sighand(p, &lflags);
++ if (rlim_rtprio)
++ goto recheck;
++ /*
++ * If the caller requested an RT policy without having the
++ * necessary rights, we downgrade the policy to SCHED_ISO.
++ * We also set the parameter to zero to pass the checks.
++ */
++ policy = SCHED_ISO;
++ param = &zero_param;
++ }
++recheck:
++ /* double check policy once rq lock held */
++ if (policy < 0) {
++ reset_on_fork = p->sched_reset_on_fork;
++ policy = oldpolicy = p->policy;
++ } else {
++ reset_on_fork = !!(policy & SCHED_RESET_ON_FORK);
++ policy &= ~SCHED_RESET_ON_FORK;
++
++ if (!SCHED_RANGE(policy))
++ return -EINVAL;
++ }
++
++ /*
++ * Valid priorities for SCHED_FIFO and SCHED_RR are
++ * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL and
++ * SCHED_BATCH is 0.
++ */
++ if (param->sched_priority < 0 ||
++ (p->mm && param->sched_priority > MAX_USER_RT_PRIO - 1) ||
++ (!p->mm && param->sched_priority > MAX_RT_PRIO - 1))
++ return -EINVAL;
++ if (is_rt_policy(policy) != (param->sched_priority != 0))
++ return -EINVAL;
++
++ /*
++ * Allow unprivileged RT tasks to decrease priority:
++ */
++ if (user && !capable(CAP_SYS_NICE)) {
++ if (is_rt_policy(policy)) {
++ unsigned long rlim_rtprio =
++ task_rlimit(p, RLIMIT_RTPRIO);
++
++ /* can't set/change the rt policy */
++ if (policy != p->policy && !rlim_rtprio)
++ return -EPERM;
++
++ /* can't increase priority */
++ if (param->sched_priority > p->rt_priority &&
++ param->sched_priority > rlim_rtprio)
++ return -EPERM;
++ } else {
++ switch (p->policy) {
++ /*
++ * Can only downgrade policies but not back to
++ * SCHED_NORMAL
++ */
++ case SCHED_ISO:
++ if (policy == SCHED_ISO)
++ goto out;
++ if (policy == SCHED_NORMAL)
++ return -EPERM;
++ break;
++ case SCHED_BATCH:
++ if (policy == SCHED_BATCH)
++ goto out;
++ if (policy != SCHED_IDLEPRIO)
++ return -EPERM;
++ break;
++ case SCHED_IDLEPRIO:
++ if (policy == SCHED_IDLEPRIO)
++ goto out;
++ return -EPERM;
++ default:
++ break;
++ }
++ }
++
++ /* can't change other user's priorities */
++ if (!check_same_owner(p))
++ return -EPERM;
++
++ /* Normal users shall not reset the sched_reset_on_fork flag */
++ if (p->sched_reset_on_fork && !reset_on_fork)
++ return -EPERM;
++ }
++
++ if (user) {
++ retval = security_task_setscheduler(p);
++ if (retval)
++ return retval;
++ }
++
++ /*
++ * make sure no PI-waiters arrive (or leave) while we are
++ * changing the priority of the task:
++ */
++ raw_spin_lock_irqsave(&p->pi_lock, flags);
++ /*
++ * To be able to change p->policy safely, the grunqueue lock must be
++ * held.
++ */
++ rq = __task_grq_lock(p);
++
++ /*
++ * Changing the policy of the stop threads its a very bad idea
++ */
++ if (p == rq->stop) {
++ __task_grq_unlock();
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++ return -EINVAL;
++ }
++
++ /*
++ * If not changing anything there's no need to proceed further:
++ */
++ if (unlikely(policy == p->policy && (!is_rt_policy(policy) ||
++ param->sched_priority == p->rt_priority))) {
++
++ __task_grq_unlock();
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++ return 0;
++ }
++
++ /* recheck policy now with rq lock held */
++ if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
++ policy = oldpolicy = -1;
++ __task_grq_unlock();
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++ goto recheck;
++ }
++ update_clocks(rq);
++ p->sched_reset_on_fork = reset_on_fork;
++
++ queued = task_queued(p);
++ if (queued)
++ dequeue_task(p);
++ __setscheduler(p, rq, policy, param->sched_priority);
++ if (queued) {
++ enqueue_task(p);
++ try_preempt(p, rq);
++ }
++ __task_grq_unlock();
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++
++ rt_mutex_adjust_pi(p);
++out:
++ return 0;
++}
++
++/**
++ * sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
++ * @p: the task in question.
++ * @policy: new policy.
++ * @param: structure containing the new RT priority.
++ *
++ * NOTE that the task may be already dead.
++ */
++int sched_setscheduler(struct task_struct *p, int policy,
++ const struct sched_param *param)
++{
++ return __sched_setscheduler(p, policy, param, true);
++}
++
++EXPORT_SYMBOL_GPL(sched_setscheduler);
++
++/**
++ * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
++ * @p: the task in question.
++ * @policy: new policy.
++ * @param: structure containing the new RT priority.
++ *
++ * Just like sched_setscheduler, only don't bother checking if the
++ * current context has permission. For example, this is needed in
++ * stop_machine(): we create temporary high priority worker threads,
++ * but our caller might not have that capability.
++ */
++int sched_setscheduler_nocheck(struct task_struct *p, int policy,
++ const struct sched_param *param)
++{
++ return __sched_setscheduler(p, policy, param, false);
++}
++
++static int
++do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
++{
++ struct sched_param lparam;
++ struct task_struct *p;
++ int retval;
++
++ if (!param || pid < 0)
++ return -EINVAL;
++ if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
++ return -EFAULT;
++
++ rcu_read_lock();
++ retval = -ESRCH;
++ p = find_process_by_pid(pid);
++ if (p != NULL)
++ retval = sched_setscheduler(p, policy, &lparam);
++ rcu_read_unlock();
++
++ return retval;
++}
++
++/**
++ * sys_sched_setscheduler - set/change the scheduler policy and RT priority
++ * @pid: the pid in question.
++ * @policy: new policy.
++ * @param: structure containing the new RT priority.
++ */
++asmlinkage long sys_sched_setscheduler(pid_t pid, int policy,
++ struct sched_param __user *param)
++{
++ /* negative values for policy are not valid */
++ if (policy < 0)
++ return -EINVAL;
++
++ return do_sched_setscheduler(pid, policy, param);
++}
++
++/**
++ * sys_sched_setparam - set/change the RT priority of a thread
++ * @pid: the pid in question.
++ * @param: structure containing the new RT priority.
++ */
++SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
++{
++ return do_sched_setscheduler(pid, -1, param);
++}
++
++/**
++ * sys_sched_getscheduler - get the policy (scheduling class) of a thread
++ * @pid: the pid in question.
++ */
++SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
++{
++ struct task_struct *p;
++ int retval = -EINVAL;
++
++ if (pid < 0)
++ goto out_nounlock;
++
++ retval = -ESRCH;
++ rcu_read_lock();
++ p = find_process_by_pid(pid);
++ if (p) {
++ retval = security_task_getscheduler(p);
++ if (!retval)
++ retval = p->policy;
++ }
++ rcu_read_unlock();
++
++out_nounlock:
++ return retval;
++}
++
++/**
++ * sys_sched_getscheduler - get the RT priority of a thread
++ * @pid: the pid in question.
++ * @param: structure containing the RT priority.
++ */
++SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
++{
++ struct sched_param lp;
++ struct task_struct *p;
++ int retval = -EINVAL;
++
++ if (!param || pid < 0)
++ goto out_nounlock;
++
++ rcu_read_lock();
++ p = find_process_by_pid(pid);
++ retval = -ESRCH;
++ if (!p)
++ goto out_unlock;
++
++ retval = security_task_getscheduler(p);
++ if (retval)
++ goto out_unlock;
++
++ lp.sched_priority = p->rt_priority;
++ rcu_read_unlock();
++
++ /*
++ * This one might sleep, we cannot do it with a spinlock held ...
++ */
++ retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;
++
++out_nounlock:
++ return retval;
++
++out_unlock:
++ rcu_read_unlock();
++ return retval;
++}
++
++long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
++{
++ cpumask_var_t cpus_allowed, new_mask;
++ struct task_struct *p;
++ int retval;
++
++ get_online_cpus();
++ rcu_read_lock();
++
++ p = find_process_by_pid(pid);
++ if (!p) {
++ rcu_read_unlock();
++ put_online_cpus();
++ return -ESRCH;
++ }
++
++ /* Prevent p going away */
++ get_task_struct(p);
++ rcu_read_unlock();
++
++ if (p->flags & PF_NO_SETAFFINITY) {
++ retval = -EINVAL;
++ goto out_put_task;
++ }
++ if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) {
++ retval = -ENOMEM;
++ goto out_put_task;
++ }
++ if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) {
++ retval = -ENOMEM;
++ goto out_free_cpus_allowed;
++ }
++ retval = -EPERM;
++ if (!check_same_owner(p)) {
++ rcu_read_lock();
++ if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) {
++ rcu_read_unlock();
++ goto out_unlock;
++ }
++ rcu_read_unlock();
++ }
++
++ retval = security_task_setscheduler(p);
++ if (retval)
++ goto out_unlock;
++
++ cpuset_cpus_allowed(p, cpus_allowed);
++ cpumask_and(new_mask, in_mask, cpus_allowed);
++again:
++ retval = set_cpus_allowed_ptr(p, new_mask);
++
++ if (!retval) {
++ cpuset_cpus_allowed(p, cpus_allowed);
++ if (!cpumask_subset(new_mask, cpus_allowed)) {
++ /*
++ * We must have raced with a concurrent cpuset
++ * update. Just reset the cpus_allowed to the
++ * cpuset's cpus_allowed
++ */
++ cpumask_copy(new_mask, cpus_allowed);
++ goto again;
++ }
++ }
++out_unlock:
++ free_cpumask_var(new_mask);
++out_free_cpus_allowed:
++ free_cpumask_var(cpus_allowed);
++out_put_task:
++ put_task_struct(p);
++ put_online_cpus();
++ return retval;
++}
++
++static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
++ cpumask_t *new_mask)
++{
++ if (len < sizeof(cpumask_t)) {
++ memset(new_mask, 0, sizeof(cpumask_t));
++ } else if (len > sizeof(cpumask_t)) {
++ len = sizeof(cpumask_t);
++ }
++ return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0;
++}
++
++
++/**
++ * sys_sched_setaffinity - set the cpu affinity of a process
++ * @pid: pid of the process
++ * @len: length in bytes of the bitmask pointed to by user_mask_ptr
++ * @user_mask_ptr: user-space pointer to the new cpu mask
++ */
++SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
++ unsigned long __user *, user_mask_ptr)
++{
++ cpumask_var_t new_mask;
++ int retval;
++
++ if (!alloc_cpumask_var(&new_mask, GFP_KERNEL))
++ return -ENOMEM;
++
++ retval = get_user_cpu_mask(user_mask_ptr, len, new_mask);
++ if (retval == 0)
++ retval = sched_setaffinity(pid, new_mask);
++ free_cpumask_var(new_mask);
++ return retval;
++}
++
++long sched_getaffinity(pid_t pid, cpumask_t *mask)
++{
++ struct task_struct *p;
++ unsigned long flags;
++ int retval;
++
++ get_online_cpus();
++ rcu_read_lock();
++
++ retval = -ESRCH;
++ p = find_process_by_pid(pid);
++ if (!p)
++ goto out_unlock;
++
++ retval = security_task_getscheduler(p);
++ if (retval)
++ goto out_unlock;
++
++ grq_lock_irqsave(&flags);
++ cpumask_and(mask, tsk_cpus_allowed(p), cpu_online_mask);
++ grq_unlock_irqrestore(&flags);
++
++out_unlock:
++ rcu_read_unlock();
++ put_online_cpus();
++
++ return retval;
++}
++
++/**
++ * sys_sched_getaffinity - get the cpu affinity of a process
++ * @pid: pid of the process
++ * @len: length in bytes of the bitmask pointed to by user_mask_ptr
++ * @user_mask_ptr: user-space pointer to hold the current cpu mask
++ */
++SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
++ unsigned long __user *, user_mask_ptr)
++{
++ int ret;
++ cpumask_var_t mask;
++
++ if ((len * BITS_PER_BYTE) < nr_cpu_ids)
++ return -EINVAL;
++ if (len & (sizeof(unsigned long)-1))
++ return -EINVAL;
++
++ if (!alloc_cpumask_var(&mask, GFP_KERNEL))
++ return -ENOMEM;
++
++ ret = sched_getaffinity(pid, mask);
++ if (ret == 0) {
++ size_t retlen = min_t(size_t, len, cpumask_size());
++
++ if (copy_to_user(user_mask_ptr, mask, retlen))
++ ret = -EFAULT;
++ else
++ ret = retlen;
++ }
++ free_cpumask_var(mask);
++
++ return ret;
++}
++
++/**
++ * sys_sched_yield - yield the current processor to other threads.
++ *
++ * This function yields the current CPU to other tasks. It does this by
++ * scheduling away the current task. If it still has the earliest deadline
++ * it will be scheduled again as the next task.
++ */
++SYSCALL_DEFINE0(sched_yield)
++{
++ struct task_struct *p;
++
++ p = current;
++ grq_lock_irq();
++ schedstat_inc(task_rq(p), yld_count);
++ requeue_task(p);
++
++ /*
++ * Since we are going to call schedule() anyway, there's
++ * no need to preempt or enable interrupts:
++ */
++ __release(grq.lock);
++ spin_release(&grq.lock.dep_map, 1, _THIS_IP_);
++ do_raw_spin_unlock(&grq.lock);
++ sched_preempt_enable_no_resched();
++
++ schedule();
++
++ return 0;
++}
++
++static inline bool should_resched(void)
++{
++ return need_resched() && !(preempt_count() & PREEMPT_ACTIVE);
++}
++
++static void __cond_resched(void)
++{
++ add_preempt_count(PREEMPT_ACTIVE);
++ schedule();
++ sub_preempt_count(PREEMPT_ACTIVE);
++}
++
++int __sched _cond_resched(void)
++{
++ if (should_resched()) {
++ __cond_resched();
++ return 1;
++ }
++ return 0;
++}
++EXPORT_SYMBOL(_cond_resched);
++
++/*
++ * __cond_resched_lock() - if a reschedule is pending, drop the given lock,
++ * call schedule, and on return reacquire the lock.
++ *
++ * This works OK both with and without CONFIG_PREEMPT. We do strange low-level
++ * operations here to prevent schedule() from being called twice (once via
++ * spin_unlock(), once by hand).
++ */
++int __cond_resched_lock(spinlock_t *lock)
++{
++ int resched = should_resched();
++ int ret = 0;
++
++ lockdep_assert_held(lock);
++
++ if (spin_needbreak(lock) || resched) {
++ spin_unlock(lock);
++ if (resched)
++ __cond_resched();
++ else
++ cpu_relax();
++ ret = 1;
++ spin_lock(lock);
++ }
++ return ret;
++}
++EXPORT_SYMBOL(__cond_resched_lock);
++
++int __sched __cond_resched_softirq(void)
++{
++ BUG_ON(!in_softirq());
++
++ if (should_resched()) {
++ local_bh_enable();
++ __cond_resched();
++ local_bh_disable();
++ return 1;
++ }
++ return 0;
++}
++EXPORT_SYMBOL(__cond_resched_softirq);
++
++/**
++ * yield - yield the current processor to other threads.
++ *
++ * Do not ever use this function, there's a 99% chance you're doing it wrong.
++ *
++ * The scheduler is at all times free to pick the calling task as the most
++ * eligible task to run, if removing the yield() call from your code breaks
++ * it, its already broken.
++ *
++ * Typical broken usage is:
++ *
++ * while (!event)
++ * yield();
++ *
++ * where one assumes that yield() will let 'the other' process run that will
++ * make event true. If the current task is a SCHED_FIFO task that will never
++ * happen. Never use yield() as a progress guarantee!!
++ *
++ * If you want to use yield() to wait for something, use wait_event().
++ * If you want to use yield() to be 'nice' for others, use cond_resched().
++ * If you still want to use yield(), do not!
++ */
++void __sched yield(void)
++{
++ set_current_state(TASK_RUNNING);
++ sys_sched_yield();
++}
++EXPORT_SYMBOL(yield);
++
++/**
++ * yield_to - yield the current processor to another thread in
++ * your thread group, or accelerate that thread toward the
++ * processor it's on.
++ * @p: target task
++ * @preempt: whether task preemption is allowed or not
++ *
++ * It's the caller's job to ensure that the target task struct
++ * can't go away on us before we can do any checks.
++ *
++ * Returns:
++ * true (>0) if we indeed boosted the target task.
++ * false (0) if we failed to boost the target.
++ * -ESRCH if there's no task to yield to.
++ */
++bool __sched yield_to(struct task_struct *p, bool preempt)
++{
++ unsigned long flags;
++ int yielded = 0;
++ struct rq *rq;
++
++ rq = this_rq();
++ grq_lock_irqsave(&flags);
++ if (task_running(p) || p->state) {
++ yielded = -ESRCH;
++ goto out_unlock;
++ }
++ yielded = 1;
++ if (p->deadline > rq->rq_deadline)
++ p->deadline = rq->rq_deadline;
++ p->time_slice += rq->rq_time_slice;
++ rq->rq_time_slice = 0;
++ if (p->time_slice > timeslice())
++ p->time_slice = timeslice();
++ set_tsk_need_resched(rq->curr);
++out_unlock:
++ grq_unlock_irqrestore(&flags);
++
++ if (yielded > 0)
++ schedule();
++ return yielded;
++}
++EXPORT_SYMBOL_GPL(yield_to);
++
++/*
++ * This task is about to go to sleep on IO. Increment rq->nr_iowait so
++ * that process accounting knows that this is a task in IO wait state.
++ *
++ * But don't do that if it is a deliberate, throttling IO wait (this task
++ * has set its backing_dev_info: the queue against which it should throttle)
++ */
++void __sched io_schedule(void)
++{
++ struct rq *rq = raw_rq();
++
++ delayacct_blkio_start();
++ atomic_inc(&rq->nr_iowait);
++ blk_flush_plug(current);
++ current->in_iowait = 1;
++ schedule();
++ current->in_iowait = 0;
++ atomic_dec(&rq->nr_iowait);
++ delayacct_blkio_end();
++}
++EXPORT_SYMBOL(io_schedule);
++
++long __sched io_schedule_timeout(long timeout)
++{
++ struct rq *rq = raw_rq();
++ long ret;
++
++ delayacct_blkio_start();
++ atomic_inc(&rq->nr_iowait);
++ blk_flush_plug(current);
++ current->in_iowait = 1;
++ ret = schedule_timeout(timeout);
++ current->in_iowait = 0;
++ atomic_dec(&rq->nr_iowait);
++ delayacct_blkio_end();
++ return ret;
++}
++
++/**
++ * sys_sched_get_priority_max - return maximum RT priority.
++ * @policy: scheduling class.
++ *
++ * this syscall returns the maximum rt_priority that can be used
++ * by a given scheduling class.
++ */
++SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
++{
++ int ret = -EINVAL;
++
++ switch (policy) {
++ case SCHED_FIFO:
++ case SCHED_RR:
++ ret = MAX_USER_RT_PRIO-1;
++ break;
++ case SCHED_NORMAL:
++ case SCHED_BATCH:
++ case SCHED_ISO:
++ case SCHED_IDLEPRIO:
++ ret = 0;
++ break;
++ }
++ return ret;
++}
++
++/**
++ * sys_sched_get_priority_min - return minimum RT priority.
++ * @policy: scheduling class.
++ *
++ * this syscall returns the minimum rt_priority that can be used
++ * by a given scheduling class.
++ */
++SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
++{
++ int ret = -EINVAL;
++
++ switch (policy) {
++ case SCHED_FIFO:
++ case SCHED_RR:
++ ret = 1;
++ break;
++ case SCHED_NORMAL:
++ case SCHED_BATCH:
++ case SCHED_ISO:
++ case SCHED_IDLEPRIO:
++ ret = 0;
++ break;
++ }
++ return ret;
++}
++
++/**
++ * sys_sched_rr_get_interval - return the default timeslice of a process.
++ * @pid: pid of the process.
++ * @interval: userspace pointer to the timeslice value.
++ *
++ * this syscall writes the default timeslice value of a given process
++ * into the user-space timespec buffer. A value of '0' means infinity.
++ */
++SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
++ struct timespec __user *, interval)
++{
++ struct task_struct *p;
++ unsigned int time_slice;
++ unsigned long flags;
++ int retval;
++ struct timespec t;
++
++ if (pid < 0)
++ return -EINVAL;
++
++ retval = -ESRCH;
++ rcu_read_lock();
++ p = find_process_by_pid(pid);
++ if (!p)
++ goto out_unlock;
++
++ retval = security_task_getscheduler(p);
++ if (retval)
++ goto out_unlock;
++
++ grq_lock_irqsave(&flags);
++ time_slice = p->policy == SCHED_FIFO ? 0 : MS_TO_NS(task_timeslice(p));
++ grq_unlock_irqrestore(&flags);
++
++ rcu_read_unlock();
++ t = ns_to_timespec(time_slice);
++ retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0;
++ return retval;
++
++out_unlock:
++ rcu_read_unlock();
++ return retval;
++}
++
++static const char stat_nam[] = TASK_STATE_TO_CHAR_STR;
++
++void sched_show_task(struct task_struct *p)
++{
++ unsigned long free = 0;
++ int ppid;
++ unsigned state;
++
++ state = p->state ? __ffs(p->state) + 1 : 0;
++ printk(KERN_INFO "%-15.15s %c", p->comm,
++ state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?');
++#if BITS_PER_LONG == 32
++ if (state == TASK_RUNNING)
++ printk(KERN_CONT " running ");
++ else
++ printk(KERN_CONT " %08lx ", thread_saved_pc(p));
++#else
++ if (state == TASK_RUNNING)
++ printk(KERN_CONT " running task ");
++ else
++ printk(KERN_CONT " %016lx ", thread_saved_pc(p));
++#endif
++#ifdef CONFIG_DEBUG_STACK_USAGE
++ free = stack_not_used(p);
++#endif
++ rcu_read_lock();
++ ppid = task_pid_nr(rcu_dereference(p->real_parent));
++ rcu_read_unlock();
++ printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free,
++ task_pid_nr(p), ppid,
++ (unsigned long)task_thread_info(p)->flags);
++
++ print_worker_info(KERN_INFO, p);
++ show_stack(p, NULL);
++}
++
++void show_state_filter(unsigned long state_filter)
++{
++ struct task_struct *g, *p;
++
++#if BITS_PER_LONG == 32
++ printk(KERN_INFO
++ " task PC stack pid father\n");
++#else
++ printk(KERN_INFO
++ " task PC stack pid father\n");
++#endif
++ rcu_read_lock();
++ do_each_thread(g, p) {
++ /*
++ * reset the NMI-timeout, listing all files on a slow
++ * console might take a lot of time:
++ */
++ touch_nmi_watchdog();
++ if (!state_filter || (p->state & state_filter))
++ sched_show_task(p);
++ } while_each_thread(g, p);
++
++ touch_all_softlockup_watchdogs();
++
++ rcu_read_unlock();
++ /*
++ * Only show locks if all tasks are dumped:
++ */
++ if (!state_filter)
++ debug_show_all_locks();
++}
++
++void dump_cpu_task(int cpu)
++{
++ pr_info("Task dump for CPU %d:\n", cpu);
++ sched_show_task(cpu_curr(cpu));
++}
++
++#ifdef CONFIG_SMP
++void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
++{
++ cpumask_copy(tsk_cpus_allowed(p), new_mask);
++}
++#endif
++
++/**
++ * init_idle - set up an idle thread for a given CPU
++ * @idle: task in question
++ * @cpu: cpu the idle task belongs to
++ *
++ * NOTE: this function does not set the idle thread's NEED_RESCHED
++ * flag, to make booting more robust.
++ */
++void init_idle(struct task_struct *idle, int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++ unsigned long flags;
++
++ time_grq_lock(rq, &flags);
++ idle->last_ran = rq->clock_task;
++ idle->state = TASK_RUNNING;
++ /* Setting prio to illegal value shouldn't matter when never queued */
++ idle->prio = PRIO_LIMIT;
++ set_rq_task(rq, idle);
++ do_set_cpus_allowed(idle, &cpumask_of_cpu(cpu));
++ /* Silence PROVE_RCU */
++ rcu_read_lock();
++ set_task_cpu(idle, cpu);
++ rcu_read_unlock();
++ rq->curr = rq->idle = idle;
++ idle->on_cpu = 1;
++ grq_unlock_irqrestore(&flags);
++
++ /* Set the preempt count _outside_ the spinlocks! */
++ task_thread_info(idle)->preempt_count = 0;
++
++ ftrace_graph_init_idle_task(idle, cpu);
++#if defined(CONFIG_SMP)
++ sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
++#endif
++}
++
++#ifdef CONFIG_SMP
++#ifdef CONFIG_NO_HZ_COMMON
++void nohz_balance_enter_idle(int cpu)
++{
++}
++
++void select_nohz_load_balancer(int stop_tick)
++{
++}
++
++void set_cpu_sd_state_idle(void) {}
++#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
++/**
++ * lowest_flag_domain - Return lowest sched_domain containing flag.
++ * @cpu: The cpu whose lowest level of sched domain is to
++ * be returned.
++ * @flag: The flag to check for the lowest sched_domain
++ * for the given cpu.
++ *
++ * Returns the lowest sched_domain of a cpu which contains the given flag.
++ */
++static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
++{
++ struct sched_domain *sd;
++
++ for_each_domain(cpu, sd)
++ if (sd && (sd->flags & flag))
++ break;
++
++ return sd;
++}
++
++/**
++ * for_each_flag_domain - Iterates over sched_domains containing the flag.
++ * @cpu: The cpu whose domains we're iterating over.
++ * @sd: variable holding the value of the power_savings_sd
++ * for cpu.
++ * @flag: The flag to filter the sched_domains to be iterated.
++ *
++ * Iterates over all the scheduler domains for a given cpu that has the 'flag'
++ * set, starting from the lowest sched_domain to the highest.
++ */
++#define for_each_flag_domain(cpu, sd, flag) \
++ for (sd = lowest_flag_domain(cpu, flag); \
++ (sd && (sd->flags & flag)); sd = sd->parent)
++
++#endif /* (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */
++
++static inline void resched_cpu(int cpu)
++{
++ unsigned long flags;
++
++ grq_lock_irqsave(&flags);
++ resched_task(cpu_curr(cpu));
++ grq_unlock_irqrestore(&flags);
++}
++
++/*
++ * In the semi idle case, use the nearest busy cpu for migrating timers
++ * from an idle cpu. This is good for power-savings.
++ *
++ * We don't do similar optimization for completely idle system, as
++ * selecting an idle cpu will add more delays to the timers than intended
++ * (as that cpu's timer base may not be uptodate wrt jiffies etc).
++ */
++int get_nohz_timer_target(void)
++{
++ int cpu = smp_processor_id();
++ int i;
++ struct sched_domain *sd;
++
++ rcu_read_lock();
++ for_each_domain(cpu, sd) {
++ for_each_cpu(i, sched_domain_span(sd)) {
++ if (!idle_cpu(i))
++ cpu = i;
++ goto unlock;
++ }
++ }
++unlock:
++ rcu_read_unlock();
++ return cpu;
++}
++
++/*
++ * When add_timer_on() enqueues a timer into the timer wheel of an
++ * idle CPU then this timer might expire before the next timer event
++ * which is scheduled to wake up that CPU. In case of a completely
++ * idle system the next event might even be infinite time into the
++ * future. wake_up_idle_cpu() ensures that the CPU is woken up and
++ * leaves the inner idle loop so the newly added timer is taken into
++ * account when the CPU goes back to idle and evaluates the timer
++ * wheel for the next timer event.
++ */
++void wake_up_idle_cpu(int cpu)
++{
++ struct task_struct *idle;
++ struct rq *rq;
++
++ if (cpu == smp_processor_id())
++ return;
++
++ rq = cpu_rq(cpu);
++ idle = rq->idle;
++
++ /*
++ * This is safe, as this function is called with the timer
++ * wheel base lock of (cpu) held. When the CPU is on the way
++ * to idle and has not yet set rq->curr to idle then it will
++ * be serialised on the timer wheel base lock and take the new
++ * timer into account automatically.
++ */
++ if (unlikely(rq->curr != idle))
++ return;
++
++ /*
++ * We can set TIF_RESCHED on the idle task of the other CPU
++ * lockless. The worst case is that the other CPU runs the
++ * idle task through an additional NOOP schedule()
++ */
++ set_tsk_need_resched(idle);
++
++ /* NEED_RESCHED must be visible before we test polling */
++ smp_mb();
++ if (!tsk_is_polling(idle))
++ smp_send_reschedule(cpu);
++}
++
++void wake_up_nohz_cpu(int cpu)
++{
++ wake_up_idle_cpu(cpu);
++}
++#endif /* CONFIG_NO_HZ_COMMON */
++
++/*
++ * Change a given task's CPU affinity. Migrate the thread to a
++ * proper CPU and schedule it away if the CPU it's executing on
++ * is removed from the allowed bitmask.
++ *
++ * NOTE: the caller must have a valid reference to the task, the
++ * task must not exit() & deallocate itself prematurely. The
++ * call is not atomic; no spinlocks may be held.
++ */
++int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
++{
++ bool running_wrong = false;
++ bool queued = false;
++ unsigned long flags;
++ struct rq *rq;
++ int ret = 0;
++
++ rq = task_grq_lock(p, &flags);
++
++ if (cpumask_equal(tsk_cpus_allowed(p), new_mask))
++ goto out;
++
++ if (!cpumask_intersects(new_mask, cpu_active_mask)) {
++ ret = -EINVAL;
++ goto out;
++ }
++
++ queued = task_queued(p);
++
++ do_set_cpus_allowed(p, new_mask);
++
++ /* Can the task run on the task's current CPU? If so, we're done */
++ if (cpumask_test_cpu(task_cpu(p), new_mask))
++ goto out;
++
++ if (task_running(p)) {
++ /* Task is running on the wrong cpu now, reschedule it. */
++ if (rq == this_rq()) {
++ set_tsk_need_resched(p);
++ running_wrong = true;
++ } else
++ resched_task(p);
++ } else
++ set_task_cpu(p, cpumask_any_and(cpu_active_mask, new_mask));
++
++out:
++ if (queued)
++ try_preempt(p, rq);
++ task_grq_unlock(&flags);
++
++ if (running_wrong)
++ _cond_resched();
++
++ return ret;
++}
++EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
++
++#ifdef CONFIG_HOTPLUG_CPU
++extern struct task_struct *cpu_stopper_task;
++/* Run through task list and find tasks affined to just the dead cpu, then
++ * allocate a new affinity */
++static void break_sole_affinity(int src_cpu, struct task_struct *idle)
++{
++ struct task_struct *p, *t, *stopper;
++
++ stopper = per_cpu(cpu_stopper_task, src_cpu);
++ do_each_thread(t, p) {
++ if (p != stopper && p != idle && !online_cpus(p)) {
++ cpumask_copy(tsk_cpus_allowed(p), cpu_possible_mask);
++ /*
++ * Don't tell them about moving exiting tasks or
++ * kernel threads (both mm NULL), since they never
++ * leave kernel.
++ */
++ if (p->mm && printk_ratelimit()) {
++ printk(KERN_INFO "process %d (%s) no "
++ "longer affine to cpu %d\n",
++ task_pid_nr(p), p->comm, src_cpu);
++ }
++ }
++ clear_sticky(p);
++ } while_each_thread(t, p);
++}
++
++/*
++ * Ensures that the idle task is using init_mm right before its cpu goes
++ * offline.
++ */
++void idle_task_exit(void)
++{
++ struct mm_struct *mm = current->active_mm;
++
++ BUG_ON(cpu_online(smp_processor_id()));
++
++ if (mm != &init_mm)
++ switch_mm(mm, &init_mm, current);
++ mmdrop(mm);
++}
++#endif /* CONFIG_HOTPLUG_CPU */
++void sched_set_stop_task(int cpu, struct task_struct *stop)
++{
++ struct sched_param stop_param = { .sched_priority = STOP_PRIO };
++ struct sched_param start_param = { .sched_priority = 0 };
++ struct task_struct *old_stop = cpu_rq(cpu)->stop;
++
++ if (stop) {
++ /*
++ * Make it appear like a SCHED_FIFO task, its something
++ * userspace knows about and won't get confused about.
++ *
++ * Also, it will make PI more or less work without too
++ * much confusion -- but then, stop work should not
++ * rely on PI working anyway.
++ */
++ sched_setscheduler_nocheck(stop, SCHED_FIFO, &stop_param);
++ }
++
++ cpu_rq(cpu)->stop = stop;
++
++ if (old_stop) {
++ /*
++ * Reset it back to a normal scheduling policy so that
++ * it can die in pieces.
++ */
++ sched_setscheduler_nocheck(old_stop, SCHED_NORMAL, &start_param);
++ }
++}
++
++
++#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
++
++static struct ctl_table sd_ctl_dir[] = {
++ {
++ .procname = "sched_domain",
++ .mode = 0555,
++ },
++ {}
++};
++
++static struct ctl_table sd_ctl_root[] = {
++ {
++ .procname = "kernel",
++ .mode = 0555,
++ .child = sd_ctl_dir,
++ },
++ {}
++};
++
++static struct ctl_table *sd_alloc_ctl_entry(int n)
++{
++ struct ctl_table *entry =
++ kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL);
++
++ return entry;
++}
++
++static void sd_free_ctl_entry(struct ctl_table **tablep)
++{
++ struct ctl_table *entry;
++
++ /*
++ * In the intermediate directories, both the child directory and
++ * procname are dynamically allocated and could fail but the mode
++ * will always be set. In the lowest directory the names are
++ * static strings and all have proc handlers.
++ */
++ for (entry = *tablep; entry->mode; entry++) {
++ if (entry->child)
++ sd_free_ctl_entry(&entry->child);
++ if (entry->proc_handler == NULL)
++ kfree(entry->procname);
++ }
++
++ kfree(*tablep);
++ *tablep = NULL;
++}
++
++static void
++set_table_entry(struct ctl_table *entry,
++ const char *procname, void *data, int maxlen,
++ mode_t mode, proc_handler *proc_handler)
++{
++ entry->procname = procname;
++ entry->data = data;
++ entry->maxlen = maxlen;
++ entry->mode = mode;
++ entry->proc_handler = proc_handler;
++}
++
++static struct ctl_table *
++sd_alloc_ctl_domain_table(struct sched_domain *sd)
++{
++ struct ctl_table *table = sd_alloc_ctl_entry(13);
++
++ if (table == NULL)
++ return NULL;
++
++ set_table_entry(&table[0], "min_interval", &sd->min_interval,
++ sizeof(long), 0644, proc_doulongvec_minmax);
++ set_table_entry(&table[1], "max_interval", &sd->max_interval,
++ sizeof(long), 0644, proc_doulongvec_minmax);
++ set_table_entry(&table[2], "busy_idx", &sd->busy_idx,
++ sizeof(int), 0644, proc_dointvec_minmax);
++ set_table_entry(&table[3], "idle_idx", &sd->idle_idx,
++ sizeof(int), 0644, proc_dointvec_minmax);
++ set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx,
++ sizeof(int), 0644, proc_dointvec_minmax);
++ set_table_entry(&table[5], "wake_idx", &sd->wake_idx,
++ sizeof(int), 0644, proc_dointvec_minmax);
++ set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx,
++ sizeof(int), 0644, proc_dointvec_minmax);
++ set_table_entry(&table[7], "busy_factor", &sd->busy_factor,
++ sizeof(int), 0644, proc_dointvec_minmax);
++ set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct,
++ sizeof(int), 0644, proc_dointvec_minmax);
++ set_table_entry(&table[9], "cache_nice_tries",
++ &sd->cache_nice_tries,
++ sizeof(int), 0644, proc_dointvec_minmax);
++ set_table_entry(&table[10], "flags", &sd->flags,
++ sizeof(int), 0644, proc_dointvec_minmax);
++ set_table_entry(&table[11], "name", sd->name,
++ CORENAME_MAX_SIZE, 0444, proc_dostring);
++ /* &table[12] is terminator */
++
++ return table;
++}
++
++static ctl_table *sd_alloc_ctl_cpu_table(int cpu)
++{
++ struct ctl_table *entry, *table;
++ struct sched_domain *sd;
++ int domain_num = 0, i;
++ char buf[32];
++
++ for_each_domain(cpu, sd)
++ domain_num++;
++ entry = table = sd_alloc_ctl_entry(domain_num + 1);
++ if (table == NULL)
++ return NULL;
++
++ i = 0;
++ for_each_domain(cpu, sd) {
++ snprintf(buf, 32, "domain%d", i);
++ entry->procname = kstrdup(buf, GFP_KERNEL);
++ entry->mode = 0555;
++ entry->child = sd_alloc_ctl_domain_table(sd);
++ entry++;
++ i++;
++ }
++ return table;
++}
++
++static struct ctl_table_header *sd_sysctl_header;
++static void register_sched_domain_sysctl(void)
++{
++ int i, cpu_num = num_possible_cpus();
++ struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1);
++ char buf[32];
++
++ WARN_ON(sd_ctl_dir[0].child);
++ sd_ctl_dir[0].child = entry;
++
++ if (entry == NULL)
++ return;
++
++ for_each_possible_cpu(i) {
++ snprintf(buf, 32, "cpu%d", i);
++ entry->procname = kstrdup(buf, GFP_KERNEL);
++ entry->mode = 0555;
++ entry->child = sd_alloc_ctl_cpu_table(i);
++ entry++;
++ }
++
++ WARN_ON(sd_sysctl_header);
++ sd_sysctl_header = register_sysctl_table(sd_ctl_root);
++}
++
++/* may be called multiple times per register */
++static void unregister_sched_domain_sysctl(void)
++{
++ if (sd_sysctl_header)
++ unregister_sysctl_table(sd_sysctl_header);
++ sd_sysctl_header = NULL;
++ if (sd_ctl_dir[0].child)
++ sd_free_ctl_entry(&sd_ctl_dir[0].child);
++}
++#else
++static void register_sched_domain_sysctl(void)
++{
++}
++static void unregister_sched_domain_sysctl(void)
++{
++}
++#endif
++
++static void set_rq_online(struct rq *rq)
++{
++ if (!rq->online) {
++ cpumask_set_cpu(cpu_of(rq), rq->rd->online);
++ rq->online = true;
++ }
++}
++
++static void set_rq_offline(struct rq *rq)
++{
++ if (rq->online) {
++ cpumask_clear_cpu(cpu_of(rq), rq->rd->online);
++ rq->online = false;
++ }
++}
++
++/*
++ * migration_call - callback that gets triggered when a CPU is added.
++ */
++static int __cpuinit
++migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
++{
++ int cpu = (long)hcpu;
++ unsigned long flags;
++ struct rq *rq = cpu_rq(cpu);
++#ifdef CONFIG_HOTPLUG_CPU
++ struct task_struct *idle = rq->idle;
++#endif
++
++ switch (action & ~CPU_TASKS_FROZEN) {
++
++ case CPU_UP_PREPARE:
++ break;
++
++ case CPU_ONLINE:
++ /* Update our root-domain */
++ grq_lock_irqsave(&flags);
++ if (rq->rd) {
++ BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
++
++ set_rq_online(rq);
++ }
++ grq.noc = num_online_cpus();
++ grq_unlock_irqrestore(&flags);
++ break;
++
++#ifdef CONFIG_HOTPLUG_CPU
++ case CPU_DEAD:
++ /* Idle task back to normal (off runqueue, low prio) */
++ grq_lock_irq();
++ return_task(idle, true);
++ idle->static_prio = MAX_PRIO;
++ __setscheduler(idle, rq, SCHED_NORMAL, 0);
++ idle->prio = PRIO_LIMIT;
++ set_rq_task(rq, idle);
++ update_clocks(rq);
++ grq_unlock_irq();
++ break;
++
++ case CPU_DYING:
++ /* Update our root-domain */
++ grq_lock_irqsave(&flags);
++ if (rq->rd) {
++ BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
++ set_rq_offline(rq);
++ }
++ break_sole_affinity(cpu, idle);
++ grq.noc = num_online_cpus();
++ grq_unlock_irqrestore(&flags);
++ break;
++#endif
++ }
++ return NOTIFY_OK;
++}
++
++/*
++ * Register at high priority so that task migration (migrate_all_tasks)
++ * happens before everything else. This has to be lower priority than
++ * the notifier in the perf_counter subsystem, though.
++ */
++static struct notifier_block __cpuinitdata migration_notifier = {
++ .notifier_call = migration_call,
++ .priority = CPU_PRI_MIGRATION,
++};
++
++static int __cpuinit sched_cpu_active(struct notifier_block *nfb,
++ unsigned long action, void *hcpu)
++{
++ switch (action & ~CPU_TASKS_FROZEN) {
++ case CPU_STARTING:
++ case CPU_DOWN_FAILED:
++ set_cpu_active((long)hcpu, true);
++ return NOTIFY_OK;
++ default:
++ return NOTIFY_DONE;
++ }
++}
++
++static int __cpuinit sched_cpu_inactive(struct notifier_block *nfb,
++ unsigned long action, void *hcpu)
++{
++ switch (action & ~CPU_TASKS_FROZEN) {
++ case CPU_DOWN_PREPARE:
++ set_cpu_active((long)hcpu, false);
++ return NOTIFY_OK;
++ default:
++ return NOTIFY_DONE;
++ }
++}
++
++int __init migration_init(void)
++{
++ void *cpu = (void *)(long)smp_processor_id();
++ int err;
++
++ /* Initialise migration for the boot CPU */
++ err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu);
++ BUG_ON(err == NOTIFY_BAD);
++ migration_call(&migration_notifier, CPU_ONLINE, cpu);
++ register_cpu_notifier(&migration_notifier);
++
++ /* Register cpu active notifiers */
++ cpu_notifier(sched_cpu_active, CPU_PRI_SCHED_ACTIVE);
++ cpu_notifier(sched_cpu_inactive, CPU_PRI_SCHED_INACTIVE);
++
++ return 0;
++}
++early_initcall(migration_init);
++#endif
++
++#ifdef CONFIG_SMP
++
++static cpumask_var_t sched_domains_tmpmask; /* sched_domains_mutex */
++
++#ifdef CONFIG_SCHED_DEBUG
++
++static __read_mostly int sched_debug_enabled;
++
++static int __init sched_debug_setup(char *str)
++{
++ sched_debug_enabled = 1;
++
++ return 0;
++}
++early_param("sched_debug", sched_debug_setup);
++
++static inline bool sched_debug(void)
++{
++ return sched_debug_enabled;
++}
++
++static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
++ struct cpumask *groupmask)
++{
++ char str[256];
++
++ cpulist_scnprintf(str, sizeof(str), sched_domain_span(sd));
++ cpumask_clear(groupmask);
++
++ printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
++
++ if (!(sd->flags & SD_LOAD_BALANCE)) {
++ printk("does not load-balance\n");
++ if (sd->parent)
++ printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain"
++ " has parent");
++ return -1;
++ }
++
++ printk(KERN_CONT "span %s level %s\n", str, sd->name);
++
++ if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
++ printk(KERN_ERR "ERROR: domain->span does not contain "
++ "CPU%d\n", cpu);
++ }
++
++ printk(KERN_CONT "\n");
++
++ if (!cpumask_equal(sched_domain_span(sd), groupmask))
++ printk(KERN_ERR "ERROR: groups don't span domain->span\n");
++
++ if (sd->parent &&
++ !cpumask_subset(groupmask, sched_domain_span(sd->parent)))
++ printk(KERN_ERR "ERROR: parent span is not a superset "
++ "of domain->span\n");
++ return 0;
++}
++
++static void sched_domain_debug(struct sched_domain *sd, int cpu)
++{
++ int level = 0;
++
++ if (!sched_debug_enabled)
++ return;
++
++ if (!sd) {
++ printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
++ return;
++ }
++
++ printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
++
++ for (;;) {
++ if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask))
++ break;
++ level++;
++ sd = sd->parent;
++ if (!sd)
++ break;
++ }
++}
++#else /* !CONFIG_SCHED_DEBUG */
++# define sched_domain_debug(sd, cpu) do { } while (0)
++static inline bool sched_debug(void)
++{
++ return false;
++}
++#endif /* CONFIG_SCHED_DEBUG */
++
++static int sd_degenerate(struct sched_domain *sd)
++{
++ if (cpumask_weight(sched_domain_span(sd)) == 1)
++ return 1;
++
++ /* Following flags don't use groups */
++ if (sd->flags & (SD_WAKE_AFFINE))
++ return 0;
++
++ return 1;
++}
++
++static int
++sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
++{
++ unsigned long cflags = sd->flags, pflags = parent->flags;
++
++ if (sd_degenerate(parent))
++ return 1;
++
++ if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent)))
++ return 0;
++
++ if (~cflags & pflags)
++ return 0;
++
++ return 1;
++}
++
++static void free_rootdomain(struct rcu_head *rcu)
++{
++ struct root_domain *rd = container_of(rcu, struct root_domain, rcu);
++
++ cpupri_cleanup(&rd->cpupri);
++ free_cpumask_var(rd->rto_mask);
++ free_cpumask_var(rd->online);
++ free_cpumask_var(rd->span);
++ kfree(rd);
++}
++
++static void rq_attach_root(struct rq *rq, struct root_domain *rd)
++{
++ struct root_domain *old_rd = NULL;
++ unsigned long flags;
++
++ grq_lock_irqsave(&flags);
++
++ if (rq->rd) {
++ old_rd = rq->rd;
++
++ if (cpumask_test_cpu(rq->cpu, old_rd->online))
++ set_rq_offline(rq);
++
++ cpumask_clear_cpu(rq->cpu, old_rd->span);
++
++ /*
++ * If we dont want to free the old_rt yet then
++ * set old_rd to NULL to skip the freeing later
++ * in this function:
++ */
++ if (!atomic_dec_and_test(&old_rd->refcount))
++ old_rd = NULL;
++ }
++
++ atomic_inc(&rd->refcount);
++ rq->rd = rd;
++
++ cpumask_set_cpu(rq->cpu, rd->span);
++ if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
++ set_rq_online(rq);
++
++ grq_unlock_irqrestore(&flags);
++
++ if (old_rd)
++ call_rcu_sched(&old_rd->rcu, free_rootdomain);
++}
++
++static int init_rootdomain(struct root_domain *rd)
++{
++ memset(rd, 0, sizeof(*rd));
++
++ if (!alloc_cpumask_var(&rd->span, GFP_KERNEL))
++ goto out;
++ if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
++ goto free_span;
++ if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
++ goto free_online;
++
++ if (cpupri_init(&rd->cpupri) != 0)
++ goto free_rto_mask;
++ return 0;
++
++free_rto_mask:
++ free_cpumask_var(rd->rto_mask);
++free_online:
++ free_cpumask_var(rd->online);
++free_span:
++ free_cpumask_var(rd->span);
++out:
++ return -ENOMEM;
++}
++
++static void init_defrootdomain(void)
++{
++ init_rootdomain(&def_root_domain);
++
++ atomic_set(&def_root_domain.refcount, 1);
++}
++
++static struct root_domain *alloc_rootdomain(void)
++{
++ struct root_domain *rd;
++
++ rd = kmalloc(sizeof(*rd), GFP_KERNEL);
++ if (!rd)
++ return NULL;
++
++ if (init_rootdomain(rd) != 0) {
++ kfree(rd);
++ return NULL;
++ }
++
++ return rd;
++}
++
++static void free_sched_domain(struct rcu_head *rcu)
++{
++ struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu);
++
++ kfree(sd);
++}
++
++static void destroy_sched_domain(struct sched_domain *sd, int cpu)
++{
++ call_rcu(&sd->rcu, free_sched_domain);
++}
++
++static void destroy_sched_domains(struct sched_domain *sd, int cpu)
++{
++ for (; sd; sd = sd->parent)
++ destroy_sched_domain(sd, cpu);
++}
++
++/*
++ * Attach the domain 'sd' to 'cpu' as its base domain. Callers must
++ * hold the hotplug lock.
++ */
++static void
++cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++ struct sched_domain *tmp;
++
++ /* Remove the sched domains which do not contribute to scheduling. */
++ for (tmp = sd; tmp; ) {
++ struct sched_domain *parent = tmp->parent;
++ if (!parent)
++ break;
++
++ if (sd_parent_degenerate(tmp, parent)) {
++ tmp->parent = parent->parent;
++ if (parent->parent)
++ parent->parent->child = tmp;
++ destroy_sched_domain(parent, cpu);
++ } else
++ tmp = tmp->parent;
++ }
++
++ if (sd && sd_degenerate(sd)) {
++ tmp = sd;
++ sd = sd->parent;
++ destroy_sched_domain(tmp, cpu);
++ if (sd)
++ sd->child = NULL;
++ }
++
++ sched_domain_debug(sd, cpu);
++
++ rq_attach_root(rq, rd);
++ tmp = rq->sd;
++ rcu_assign_pointer(rq->sd, sd);
++ destroy_sched_domains(tmp, cpu);
++}
++
++/* cpus with isolated domains */
++static cpumask_var_t cpu_isolated_map;
++
++/* Setup the mask of cpus configured for isolated domains */
++static int __init isolated_cpu_setup(char *str)
++{
++ alloc_bootmem_cpumask_var(&cpu_isolated_map);
++ cpulist_parse(str, cpu_isolated_map);
++ return 1;
++}
++
++__setup("isolcpus=", isolated_cpu_setup);
++
++static const struct cpumask *cpu_cpu_mask(int cpu)
++{
++ return cpumask_of_node(cpu_to_node(cpu));
++}
++
++struct sd_data {
++ struct sched_domain **__percpu sd;
++};
++
++struct s_data {
++ struct sched_domain ** __percpu sd;
++ struct root_domain *rd;
++};
++
++enum s_alloc {
++ sa_rootdomain,
++ sa_sd,
++ sa_sd_storage,
++ sa_none,
++};
++
++struct sched_domain_topology_level;
++
++typedef struct sched_domain *(*sched_domain_init_f)(struct sched_domain_topology_level *tl, int cpu);
++typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
++
++#define SDTL_OVERLAP 0x01
++
++struct sched_domain_topology_level {
++ sched_domain_init_f init;
++ sched_domain_mask_f mask;
++ int flags;
++ int numa_level;
++ struct sd_data data;
++};
++
++/*
++ * Initializers for schedule domains
++ * Non-inlined to reduce accumulated stack pressure in build_sched_domains()
++ */
++
++#ifdef CONFIG_SCHED_DEBUG
++# define SD_INIT_NAME(sd, type) sd->name = #type
++#else
++# define SD_INIT_NAME(sd, type) do { } while (0)
++#endif
++
++#define SD_INIT_FUNC(type) \
++static noinline struct sched_domain * \
++sd_init_##type(struct sched_domain_topology_level *tl, int cpu) \
++{ \
++ struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu); \
++ *sd = SD_##type##_INIT; \
++ SD_INIT_NAME(sd, type); \
++ sd->private = &tl->data; \
++ return sd; \
++}
++
++SD_INIT_FUNC(CPU)
++#ifdef CONFIG_SCHED_SMT
++ SD_INIT_FUNC(SIBLING)
++#endif
++#ifdef CONFIG_SCHED_MC
++ SD_INIT_FUNC(MC)
++#endif
++#ifdef CONFIG_SCHED_BOOK
++ SD_INIT_FUNC(BOOK)
++#endif
++
++static int default_relax_domain_level = -1;
++int sched_domain_level_max;
++
++static int __init setup_relax_domain_level(char *str)
++{
++ if (kstrtoint(str, 0, &default_relax_domain_level))
++ pr_warn("Unable to set relax_domain_level\n");
++
++ return 1;
++}
++__setup("relax_domain_level=", setup_relax_domain_level);
++
++static void set_domain_attribute(struct sched_domain *sd,
++ struct sched_domain_attr *attr)
++{
++ int request;
++
++ if (!attr || attr->relax_domain_level < 0) {
++ if (default_relax_domain_level < 0)
++ return;
++ else
++ request = default_relax_domain_level;
++ } else
++ request = attr->relax_domain_level;
++ if (request < sd->level) {
++ /* turn off idle balance on this domain */
++ sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
++ } else {
++ /* turn on idle balance on this domain */
++ sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
++ }
++}
++
++static void __sdt_free(const struct cpumask *cpu_map);
++static int __sdt_alloc(const struct cpumask *cpu_map);
++
++static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
++ const struct cpumask *cpu_map)
++{
++ switch (what) {
++ case sa_rootdomain:
++ if (!atomic_read(&d->rd->refcount))
++ free_rootdomain(&d->rd->rcu); /* fall through */
++ case sa_sd:
++ free_percpu(d->sd); /* fall through */
++ case sa_sd_storage:
++ __sdt_free(cpu_map); /* fall through */
++ case sa_none:
++ break;
++ }
++}
++
++static enum s_alloc __visit_domain_allocation_hell(struct s_data *d,
++ const struct cpumask *cpu_map)
++{
++ memset(d, 0, sizeof(*d));
++
++ if (__sdt_alloc(cpu_map))
++ return sa_sd_storage;
++ d->sd = alloc_percpu(struct sched_domain *);
++ if (!d->sd)
++ return sa_sd_storage;
++ d->rd = alloc_rootdomain();
++ if (!d->rd)
++ return sa_sd;
++ return sa_rootdomain;
++}
++
++/*
++ * NULL the sd_data elements we've used to build the sched_domain
++ * structure so that the subsequent __free_domain_allocs()
++ * will not free the data we're using.
++ */
++static void claim_allocations(int cpu, struct sched_domain *sd)
++{
++ struct sd_data *sdd = sd->private;
++
++ WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd);
++ *per_cpu_ptr(sdd->sd, cpu) = NULL;
++}
++
++#ifdef CONFIG_SCHED_SMT
++static const struct cpumask *cpu_smt_mask(int cpu)
++{
++ return topology_thread_cpumask(cpu);
++}
++#endif
++
++/*
++ * Topology list, bottom-up.
++ */
++static struct sched_domain_topology_level default_topology[] = {
++#ifdef CONFIG_SCHED_SMT
++ { sd_init_SIBLING, cpu_smt_mask, },
++#endif
++#ifdef CONFIG_SCHED_MC
++ { sd_init_MC, cpu_coregroup_mask, },
++#endif
++#ifdef CONFIG_SCHED_BOOK
++ { sd_init_BOOK, cpu_book_mask, },
++#endif
++ { sd_init_CPU, cpu_cpu_mask, },
++ { NULL, },
++};
++
++static struct sched_domain_topology_level *sched_domain_topology = default_topology;
++
++#ifdef CONFIG_NUMA
++
++static int sched_domains_numa_levels;
++static int *sched_domains_numa_distance;
++static struct cpumask ***sched_domains_numa_masks;
++static int sched_domains_curr_level;
++
++static inline int sd_local_flags(int level)
++{
++ if (sched_domains_numa_distance[level] > RECLAIM_DISTANCE)
++ return 0;
++
++ return SD_BALANCE_EXEC | SD_BALANCE_FORK | SD_WAKE_AFFINE;
++}
++
++static struct sched_domain *
++sd_numa_init(struct sched_domain_topology_level *tl, int cpu)
++{
++ struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu);
++ int level = tl->numa_level;
++ int sd_weight = cpumask_weight(
++ sched_domains_numa_masks[level][cpu_to_node(cpu)]);
++
++ *sd = (struct sched_domain){
++ .min_interval = sd_weight,
++ .max_interval = 2*sd_weight,
++ .busy_factor = 32,
++ .imbalance_pct = 125,
++ .cache_nice_tries = 2,
++ .busy_idx = 3,
++ .idle_idx = 2,
++ .newidle_idx = 0,
++ .wake_idx = 0,
++ .forkexec_idx = 0,
++
++ .flags = 1*SD_LOAD_BALANCE
++ | 1*SD_BALANCE_NEWIDLE
++ | 0*SD_BALANCE_EXEC
++ | 0*SD_BALANCE_FORK
++ | 0*SD_BALANCE_WAKE
++ | 0*SD_WAKE_AFFINE
++ | 0*SD_SHARE_CPUPOWER
++ | 0*SD_SHARE_PKG_RESOURCES
++ | 1*SD_SERIALIZE
++ | 0*SD_PREFER_SIBLING
++ | sd_local_flags(level)
++ ,
++ .last_balance = jiffies,
++ .balance_interval = sd_weight,
++ };
++ SD_INIT_NAME(sd, NUMA);
++ sd->private = &tl->data;
++
++ /*
++ * Ugly hack to pass state to sd_numa_mask()...
++ */
++ sched_domains_curr_level = tl->numa_level;
++
++ return sd;
++}
++
++static const struct cpumask *sd_numa_mask(int cpu)
++{
++ return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)];
++}
++
++static void sched_numa_warn(const char *str)
++{
++ static int done = false;
++ int i,j;
++
++ if (done)
++ return;
++
++ done = true;
++
++ printk(KERN_WARNING "ERROR: %s\n\n", str);
++
++ for (i = 0; i < nr_node_ids; i++) {
++ printk(KERN_WARNING " ");
++ for (j = 0; j < nr_node_ids; j++)
++ printk(KERN_CONT "%02d ", node_distance(i,j));
++ printk(KERN_CONT "\n");
++ }
++ printk(KERN_WARNING "\n");
++}
++
++static bool find_numa_distance(int distance)
++{
++ int i;
++
++ if (distance == node_distance(0, 0))
++ return true;
++
++ for (i = 0; i < sched_domains_numa_levels; i++) {
++ if (sched_domains_numa_distance[i] == distance)
++ return true;
++ }
++
++ return false;
++}
++
++static void sched_init_numa(void)
++{
++ int next_distance, curr_distance = node_distance(0, 0);
++ struct sched_domain_topology_level *tl;
++ int level = 0;
++ int i, j, k;
++
++ sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL);
++ if (!sched_domains_numa_distance)
++ return;
++
++ /*
++ * O(nr_nodes^2) deduplicating selection sort -- in order to find the
++ * unique distances in the node_distance() table.
++ *
++ * Assumes node_distance(0,j) includes all distances in
++ * node_distance(i,j) in order to avoid cubic time.
++ */
++ next_distance = curr_distance;
++ for (i = 0; i < nr_node_ids; i++) {
++ for (j = 0; j < nr_node_ids; j++) {
++ for (k = 0; k < nr_node_ids; k++) {
++ int distance = node_distance(i, k);
++
++ if (distance > curr_distance &&
++ (distance < next_distance ||
++ next_distance == curr_distance))
++ next_distance = distance;
++
++ /*
++ * While not a strong assumption it would be nice to know
++ * about cases where if node A is connected to B, B is not
++ * equally connected to A.
++ */
++ if (sched_debug() && node_distance(k, i) != distance)
++ sched_numa_warn("Node-distance not symmetric");
++
++ if (sched_debug() && i && !find_numa_distance(distance))
++ sched_numa_warn("Node-0 not representative");
++ }
++ if (next_distance != curr_distance) {
++ sched_domains_numa_distance[level++] = next_distance;
++ sched_domains_numa_levels = level;
++ curr_distance = next_distance;
++ } else break;
++ }
++
++ /*
++ * In case of sched_debug() we verify the above assumption.
++ */
++ if (!sched_debug())
++ break;
++ }
++ /*
++ * 'level' contains the number of unique distances, excluding the
++ * identity distance node_distance(i,i).
++ *
++ * The sched_domains_numa_distance[] array includes the actual distance
++ * numbers.
++ */
++
++ /*
++ * Here, we should temporarily reset sched_domains_numa_levels to 0.
++ * If it fails to allocate memory for array sched_domains_numa_masks[][],
++ * the array will contain less then 'level' members. This could be
++ * dangerous when we use it to iterate array sched_domains_numa_masks[][]
++ * in other functions.
++ *
++ * We reset it to 'level' at the end of this function.
++ */
++ sched_domains_numa_levels = 0;
++
++ sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL);
++ if (!sched_domains_numa_masks)
++ return;
++
++ /*
++ * Now for each level, construct a mask per node which contains all
++ * cpus of nodes that are that many hops away from us.
++ */
++ for (i = 0; i < level; i++) {
++ sched_domains_numa_masks[i] =
++ kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL);
++ if (!sched_domains_numa_masks[i])
++ return;
++
++ for (j = 0; j < nr_node_ids; j++) {
++ struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL);
++ if (!mask)
++ return;
++
++ sched_domains_numa_masks[i][j] = mask;
++
++ for (k = 0; k < nr_node_ids; k++) {
++ if (node_distance(j, k) > sched_domains_numa_distance[i])
++ continue;
++
++ cpumask_or(mask, mask, cpumask_of_node(k));
++ }
++ }
++ }
++
++ tl = kzalloc((ARRAY_SIZE(default_topology) + level) *
++ sizeof(struct sched_domain_topology_level), GFP_KERNEL);
++ if (!tl)
++ return;
++
++ /*
++ * Copy the default topology bits..
++ */
++ for (i = 0; default_topology[i].init; i++)
++ tl[i] = default_topology[i];
++
++ /*
++ * .. and append 'j' levels of NUMA goodness.
++ */
++ for (j = 0; j < level; i++, j++) {
++ tl[i] = (struct sched_domain_topology_level){
++ .init = sd_numa_init,
++ .mask = sd_numa_mask,
++ .flags = SDTL_OVERLAP,
++ .numa_level = j,
++ };
++ }
++
++ sched_domain_topology = tl;
++
++ sched_domains_numa_levels = level;
++}
++
++static void sched_domains_numa_masks_set(int cpu)
++{
++ int i, j;
++ int node = cpu_to_node(cpu);
++
++ for (i = 0; i < sched_domains_numa_levels; i++) {
++ for (j = 0; j < nr_node_ids; j++) {
++ if (node_distance(j, node) <= sched_domains_numa_distance[i])
++ cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]);
++ }
++ }
++}
++
++static void sched_domains_numa_masks_clear(int cpu)
++{
++ int i, j;
++ for (i = 0; i < sched_domains_numa_levels; i++) {
++ for (j = 0; j < nr_node_ids; j++)
++ cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]);
++ }
++}
++
++/*
++ * Update sched_domains_numa_masks[level][node] array when new cpus
++ * are onlined.
++ */
++static int sched_domains_numa_masks_update(struct notifier_block *nfb,
++ unsigned long action,
++ void *hcpu)
++{
++ int cpu = (long)hcpu;
++
++ switch (action & ~CPU_TASKS_FROZEN) {
++ case CPU_ONLINE:
++ sched_domains_numa_masks_set(cpu);
++ break;
++
++ case CPU_DEAD:
++ sched_domains_numa_masks_clear(cpu);
++ break;
++
++ default:
++ return NOTIFY_DONE;
++ }
++
++ return NOTIFY_OK;
++}
++#else
++static inline void sched_init_numa(void)
++{
++}
++
++static int sched_domains_numa_masks_update(struct notifier_block *nfb,
++ unsigned long action,
++ void *hcpu)
++{
++ return 0;
++}
++#endif /* CONFIG_NUMA */
++
++static int __sdt_alloc(const struct cpumask *cpu_map)
++{
++ struct sched_domain_topology_level *tl;
++ int j;
++
++ for (tl = sched_domain_topology; tl->init; tl++) {
++ struct sd_data *sdd = &tl->data;
++
++ sdd->sd = alloc_percpu(struct sched_domain *);
++ if (!sdd->sd)
++ return -ENOMEM;
++
++ for_each_cpu(j, cpu_map) {
++ struct sched_domain *sd;
++
++ sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(),
++ GFP_KERNEL, cpu_to_node(j));
++ if (!sd)
++ return -ENOMEM;
++
++ *per_cpu_ptr(sdd->sd, j) = sd;
++ }
++ }
++
++ return 0;
++}
++
++static void __sdt_free(const struct cpumask *cpu_map)
++{
++ struct sched_domain_topology_level *tl;
++ int j;
++
++ for (tl = sched_domain_topology; tl->init; tl++) {
++ struct sd_data *sdd = &tl->data;
++
++ for_each_cpu(j, cpu_map) {
++ struct sched_domain *sd;
++
++ if (sdd->sd) {
++ sd = *per_cpu_ptr(sdd->sd, j);
++ kfree(*per_cpu_ptr(sdd->sd, j));
++ }
++ }
++ free_percpu(sdd->sd);
++ sdd->sd = NULL;
++ }
++}
++
++struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
++ struct s_data *d, const struct cpumask *cpu_map,
++ struct sched_domain_attr *attr, struct sched_domain *child,
++ int cpu)
++{
++ struct sched_domain *sd = tl->init(tl, cpu);
++ if (!sd)
++ return child;
++
++ cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
++ if (child) {
++ sd->level = child->level + 1;
++ sched_domain_level_max = max(sched_domain_level_max, sd->level);
++ child->parent = sd;
++ }
++ sd->child = child;
++ set_domain_attribute(sd, attr);
++
++ return sd;
++}
++
++/*
++ * Build sched domains for a given set of cpus and attach the sched domains
++ * to the individual cpus
++ */
++static int build_sched_domains(const struct cpumask *cpu_map,
++ struct sched_domain_attr *attr)
++{
++ enum s_alloc alloc_state = sa_none;
++ struct sched_domain *sd;
++ struct s_data d;
++ int i, ret = -ENOMEM;
++
++ alloc_state = __visit_domain_allocation_hell(&d, cpu_map);
++ if (alloc_state != sa_rootdomain)
++ goto error;
++
++ /* Set up domains for cpus specified by the cpu_map. */
++ for_each_cpu(i, cpu_map) {
++ struct sched_domain_topology_level *tl;
++
++ sd = NULL;
++ for (tl = sched_domain_topology; tl->init; tl++) {
++ sd = build_sched_domain(tl, &d, cpu_map, attr, sd, i);
++ if (tl->flags & SDTL_OVERLAP)
++ sd->flags |= SD_OVERLAP;
++ if (cpumask_equal(cpu_map, sched_domain_span(sd)))
++ break;
++ }
++
++ while (sd->child)
++ sd = sd->child;
++
++ *per_cpu_ptr(d.sd, i) = sd;
++ }
++
++ /* Calculate CPU power for physical packages and nodes */
++ for (i = nr_cpumask_bits-1; i >= 0; i--) {
++ if (!cpumask_test_cpu(i, cpu_map))
++ continue;
++
++ for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
++ claim_allocations(i, sd);
++ }
++ }
++
++ /* Attach the domains */
++ rcu_read_lock();
++ for_each_cpu(i, cpu_map) {
++ sd = *per_cpu_ptr(d.sd, i);
++ cpu_attach_domain(sd, d.rd, i);
++ }
++ rcu_read_unlock();
++
++ ret = 0;
++error:
++ __free_domain_allocs(&d, alloc_state, cpu_map);
++ return ret;
++}
++
++static cpumask_var_t *doms_cur; /* current sched domains */
++static int ndoms_cur; /* number of sched domains in 'doms_cur' */
++static struct sched_domain_attr *dattr_cur;
++ /* attribues of custom domains in 'doms_cur' */
++
++/*
++ * Special case: If a kmalloc of a doms_cur partition (array of
++ * cpumask) fails, then fallback to a single sched domain,
++ * as determined by the single cpumask fallback_doms.
++ */
++static cpumask_var_t fallback_doms;
++
++/*
++ * arch_update_cpu_topology lets virtualized architectures update the
++ * cpu core maps. It is supposed to return 1 if the topology changed
++ * or 0 if it stayed the same.
++ */
++int __attribute__((weak)) arch_update_cpu_topology(void)
++{
++ return 0;
++}
++
++cpumask_var_t *alloc_sched_domains(unsigned int ndoms)
++{
++ int i;
++ cpumask_var_t *doms;
++
++ doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL);
++ if (!doms)
++ return NULL;
++ for (i = 0; i < ndoms; i++) {
++ if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) {
++ free_sched_domains(doms, i);
++ return NULL;
++ }
++ }
++ return doms;
++}
++
++void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms)
++{
++ unsigned int i;
++ for (i = 0; i < ndoms; i++)
++ free_cpumask_var(doms[i]);
++ kfree(doms);
++}
++
++/*
++ * Set up scheduler domains and groups. Callers must hold the hotplug lock.
++ * For now this just excludes isolated cpus, but could be used to
++ * exclude other special cases in the future.
++ */
++static int init_sched_domains(const struct cpumask *cpu_map)
++{
++ int err;
++
++ arch_update_cpu_topology();
++ ndoms_cur = 1;
++ doms_cur = alloc_sched_domains(ndoms_cur);
++ if (!doms_cur)
++ doms_cur = &fallback_doms;
++ cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map);
++ err = build_sched_domains(doms_cur[0], NULL);
++ register_sched_domain_sysctl();
++
++ return err;
++}
++
++/*
++ * Detach sched domains from a group of cpus specified in cpu_map
++ * These cpus will now be attached to the NULL domain
++ */
++static void detach_destroy_domains(const struct cpumask *cpu_map)
++{
++ int i;
++
++ rcu_read_lock();
++ for_each_cpu(i, cpu_map)
++ cpu_attach_domain(NULL, &def_root_domain, i);
++ rcu_read_unlock();
++}
++
++/* handle null as "default" */
++static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
++ struct sched_domain_attr *new, int idx_new)
++{
++ struct sched_domain_attr tmp;
++
++ /* fast path */
++ if (!new && !cur)
++ return 1;
++
++ tmp = SD_ATTR_INIT;
++ return !memcmp(cur ? (cur + idx_cur) : &tmp,
++ new ? (new + idx_new) : &tmp,
++ sizeof(struct sched_domain_attr));
++}
++
++/*
++ * Partition sched domains as specified by the 'ndoms_new'
++ * cpumasks in the array doms_new[] of cpumasks. This compares
++ * doms_new[] to the current sched domain partitioning, doms_cur[].
++ * It destroys each deleted domain and builds each new domain.
++ *
++ * 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'.
++ * The masks don't intersect (don't overlap.) We should setup one
++ * sched domain for each mask. CPUs not in any of the cpumasks will
++ * not be load balanced. If the same cpumask appears both in the
++ * current 'doms_cur' domains and in the new 'doms_new', we can leave
++ * it as it is.
++ *
++ * The passed in 'doms_new' should be allocated using
++ * alloc_sched_domains. This routine takes ownership of it and will
++ * free_sched_domains it when done with it. If the caller failed the
++ * alloc call, then it can pass in doms_new == NULL && ndoms_new == 1,
++ * and partition_sched_domains() will fallback to the single partition
++ * 'fallback_doms', it also forces the domains to be rebuilt.
++ *
++ * If doms_new == NULL it will be replaced with cpu_online_mask.
++ * ndoms_new == 0 is a special case for destroying existing domains,
++ * and it will not create the default domain.
++ *
++ * Call with hotplug lock held
++ */
++void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
++ struct sched_domain_attr *dattr_new)
++{
++ int i, j, n;
++ int new_topology;
++
++ mutex_lock(&sched_domains_mutex);
++
++ /* always unregister in case we don't destroy any domains */
++ unregister_sched_domain_sysctl();
++
++ /* Let architecture update cpu core mappings. */
++ new_topology = arch_update_cpu_topology();
++
++ n = doms_new ? ndoms_new : 0;
++
++ /* Destroy deleted domains */
++ for (i = 0; i < ndoms_cur; i++) {
++ for (j = 0; j < n && !new_topology; j++) {
++ if (cpumask_equal(doms_cur[i], doms_new[j])
++ && dattrs_equal(dattr_cur, i, dattr_new, j))
++ goto match1;
++ }
++ /* no match - a current sched domain not in new doms_new[] */
++ detach_destroy_domains(doms_cur[i]);
++match1:
++ ;
++ }
++
++ if (doms_new == NULL) {
++ ndoms_cur = 0;
++ doms_new = &fallback_doms;
++ cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map);
++ WARN_ON_ONCE(dattr_new);
++ }
++
++ /* Build new domains */
++ for (i = 0; i < ndoms_new; i++) {
++ for (j = 0; j < ndoms_cur && !new_topology; j++) {
++ if (cpumask_equal(doms_new[i], doms_cur[j])
++ && dattrs_equal(dattr_new, i, dattr_cur, j))
++ goto match2;
++ }
++ /* no match - add a new doms_new */
++ build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL);
++match2:
++ ;
++ }
++
++ /* Remember the new sched domains */
++ if (doms_cur != &fallback_doms)
++ free_sched_domains(doms_cur, ndoms_cur);
++ kfree(dattr_cur); /* kfree(NULL) is safe */
++ doms_cur = doms_new;
++ dattr_cur = dattr_new;
++ ndoms_cur = ndoms_new;
++
++ register_sched_domain_sysctl();
++
++ mutex_unlock(&sched_domains_mutex);
++}
++
++/*
++ * Update cpusets according to cpu_active mask. If cpusets are
++ * disabled, cpuset_update_active_cpus() becomes a simple wrapper
++ * around partition_sched_domains().
++ */
++static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action,
++ void *hcpu)
++{
++ switch (action & ~CPU_TASKS_FROZEN) {
++ case CPU_ONLINE:
++ case CPU_DOWN_FAILED:
++ cpuset_update_active_cpus(true);
++ return NOTIFY_OK;
++ default:
++ return NOTIFY_DONE;
++ }
++}
++
++static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action,
++ void *hcpu)
++{
++ switch (action & ~CPU_TASKS_FROZEN) {
++ case CPU_DOWN_PREPARE:
++ cpuset_update_active_cpus(false);
++ return NOTIFY_OK;
++ default:
++ return NOTIFY_DONE;
++ }
++}
++
++#if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_MC)
++/*
++ * Cheaper version of the below functions in case support for SMT and MC is
++ * compiled in but CPUs have no siblings.
++ */
++static bool sole_cpu_idle(int cpu)
++{
++ return rq_idle(cpu_rq(cpu));
++}
++#endif
++#ifdef CONFIG_SCHED_SMT
++/* All this CPU's SMT siblings are idle */
++static bool siblings_cpu_idle(int cpu)
++{
++ return cpumask_subset(&(cpu_rq(cpu)->smt_siblings),
++ &grq.cpu_idle_map);
++}
++#endif
++#ifdef CONFIG_SCHED_MC
++/* All this CPU's shared cache siblings are idle */
++static bool cache_cpu_idle(int cpu)
++{
++ return cpumask_subset(&(cpu_rq(cpu)->cache_siblings),
++ &grq.cpu_idle_map);
++}
++#endif
++
++enum sched_domain_level {
++ SD_LV_NONE = 0,
++ SD_LV_SIBLING,
++ SD_LV_MC,
++ SD_LV_BOOK,
++ SD_LV_CPU,
++ SD_LV_NODE,
++ SD_LV_ALLNODES,
++ SD_LV_MAX
++};
++
++void __init sched_init_smp(void)
++{
++ struct sched_domain *sd;
++ int cpu;
++
++ cpumask_var_t non_isolated_cpus;
++
++ alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL);
++ alloc_cpumask_var(&fallback_doms, GFP_KERNEL);
++
++ sched_init_numa();
++
++ get_online_cpus();
++ mutex_lock(&sched_domains_mutex);
++ init_sched_domains(cpu_active_mask);
++ cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
++ if (cpumask_empty(non_isolated_cpus))
++ cpumask_set_cpu(smp_processor_id(), non_isolated_cpus);
++ mutex_unlock(&sched_domains_mutex);
++ put_online_cpus();
++
++ hotcpu_notifier(sched_domains_numa_masks_update, CPU_PRI_SCHED_ACTIVE);
++ hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE);
++ hotcpu_notifier(cpuset_cpu_inactive, CPU_PRI_CPUSET_INACTIVE);
++
++ /* Move init over to a non-isolated CPU */
++ if (set_cpus_allowed_ptr(current, non_isolated_cpus) < 0)
++ BUG();
++ free_cpumask_var(non_isolated_cpus);
++
++ grq_lock_irq();
++ /*
++ * Set up the relative cache distance of each online cpu from each
++ * other in a simple array for quick lookup. Locality is determined
++ * by the closest sched_domain that CPUs are separated by. CPUs with
++ * shared cache in SMT and MC are treated as local. Separate CPUs
++ * (within the same package or physically) within the same node are
++ * treated as not local. CPUs not even in the same domain (different
++ * nodes) are treated as very distant.
++ */
++ for_each_online_cpu(cpu) {
++ struct rq *rq = cpu_rq(cpu);
++
++ mutex_lock(&sched_domains_mutex);
++ for_each_domain(cpu, sd) {
++ int locality, other_cpu;
++
++#ifdef CONFIG_SCHED_SMT
++ if (sd->level == SD_LV_SIBLING) {
++ for_each_cpu_mask(other_cpu, *sched_domain_span(sd))
++ cpumask_set_cpu(other_cpu, &rq->smt_siblings);
++ }
++#endif
++#ifdef CONFIG_SCHED_MC
++ if (sd->level == SD_LV_MC) {
++ for_each_cpu_mask(other_cpu, *sched_domain_span(sd))
++ cpumask_set_cpu(other_cpu, &rq->cache_siblings);
++ }
++#endif
++ if (sd->level <= SD_LV_SIBLING)
++ locality = 1;
++ else if (sd->level <= SD_LV_MC)
++ locality = 2;
++ else if (sd->level <= SD_LV_NODE)
++ locality = 3;
++ else
++ continue;
++
++ for_each_cpu_mask(other_cpu, *sched_domain_span(sd)) {
++ if (locality < rq->cpu_locality[other_cpu])
++ rq->cpu_locality[other_cpu] = locality;
++ }
++ }
++ mutex_unlock(&sched_domains_mutex);
++
++ /*
++ * Each runqueue has its own function in case it doesn't have
++ * siblings of its own allowing mixed topologies.
++ */
++#ifdef CONFIG_SCHED_SMT
++ if (cpus_weight(rq->smt_siblings) > 1)
++ rq->siblings_idle = siblings_cpu_idle;
++#endif
++#ifdef CONFIG_SCHED_MC
++ if (cpus_weight(rq->cache_siblings) > 1)
++ rq->cache_idle = cache_cpu_idle;
++#endif
++ }
++ grq_unlock_irq();
++}
++#else
++void __init sched_init_smp(void)
++{
++}
++#endif /* CONFIG_SMP */
++
++unsigned int sysctl_timer_migration = 1;
++
++int in_sched_functions(unsigned long addr)
++{
++ return in_lock_functions(addr) ||
++ (addr >= (unsigned long)__sched_text_start
++ && addr < (unsigned long)__sched_text_end);
++}
++
++void __init sched_init(void)
++{
++ int i;
++ struct rq *rq;
++
++ prio_ratios[0] = 128;
++ for (i = 1 ; i < PRIO_RANGE ; i++)
++ prio_ratios[i] = prio_ratios[i - 1] * 11 / 10;
++
++ raw_spin_lock_init(&grq.lock);
++ grq.nr_running = grq.nr_uninterruptible = grq.nr_switches = 0;
++ grq.niffies = 0;
++ grq.last_jiffy = jiffies;
++ raw_spin_lock_init(&grq.iso_lock);
++ grq.iso_ticks = 0;
++ grq.iso_refractory = false;
++ grq.noc = 1;
++#ifdef CONFIG_SMP
++ init_defrootdomain();
++ grq.qnr = grq.idle_cpus = 0;
++ cpumask_clear(&grq.cpu_idle_map);
++#else
++ uprq = &per_cpu(runqueues, 0);
++#endif
++ for_each_possible_cpu(i) {
++ rq = cpu_rq(i);
++ rq->user_pc = rq->nice_pc = rq->softirq_pc = rq->system_pc =
++ rq->iowait_pc = rq->idle_pc = 0;
++ rq->dither = false;
++#ifdef CONFIG_SMP
++ rq->sticky_task = NULL;
++ rq->last_niffy = 0;
++ rq->sd = NULL;
++ rq->rd = NULL;
++ rq->online = false;
++ rq->cpu = i;
++ rq_attach_root(rq, &def_root_domain);
++#endif
++ atomic_set(&rq->nr_iowait, 0);
++ }
++
++#ifdef CONFIG_SMP
++ nr_cpu_ids = i;
++ /*
++ * Set the base locality for cpu cache distance calculation to
++ * "distant" (3). Make sure the distance from a CPU to itself is 0.
++ */
++ for_each_possible_cpu(i) {
++ int j;
++
++ rq = cpu_rq(i);
++#ifdef CONFIG_SCHED_SMT
++ cpumask_clear(&rq->smt_siblings);
++ cpumask_set_cpu(i, &rq->smt_siblings);
++ rq->siblings_idle = sole_cpu_idle;
++ cpumask_set_cpu(i, &rq->smt_siblings);
++#endif
++#ifdef CONFIG_SCHED_MC
++ cpumask_clear(&rq->cache_siblings);
++ cpumask_set_cpu(i, &rq->cache_siblings);
++ rq->cache_idle = sole_cpu_idle;
++ cpumask_set_cpu(i, &rq->cache_siblings);
++#endif
++ rq->cpu_locality = kmalloc(nr_cpu_ids * sizeof(int *), GFP_ATOMIC);
++ for_each_possible_cpu(j) {
++ if (i == j)
++ rq->cpu_locality[j] = 0;
++ else
++ rq->cpu_locality[j] = 4;
++ }
++ }
++#endif
++
++ for (i = 0; i < PRIO_LIMIT; i++)
++ INIT_LIST_HEAD(grq.queue + i);
++ /* delimiter for bitsearch */
++ __set_bit(PRIO_LIMIT, grq.prio_bitmap);
++
++#ifdef CONFIG_PREEMPT_NOTIFIERS
++ INIT_HLIST_HEAD(&init_task.preempt_notifiers);
++#endif
++
++#ifdef CONFIG_RT_MUTEXES
++ plist_head_init(&init_task.pi_waiters);
++#endif
++
++ /*
++ * The boot idle thread does lazy MMU switching as well:
++ */
++ atomic_inc(&init_mm.mm_count);
++ enter_lazy_tlb(&init_mm, current);
++
++ /*
++ * Make us the idle thread. Technically, schedule() should not be
++ * called from this thread, however somewhere below it might be,
++ * but because we are the idle thread, we just pick up running again
++ * when this runqueue becomes "idle".
++ */
++ init_idle(current, smp_processor_id());
++
++#ifdef CONFIG_SMP
++ zalloc_cpumask_var(&sched_domains_tmpmask, GFP_NOWAIT);
++ /* May be allocated at isolcpus cmdline parse time */
++ if (cpu_isolated_map == NULL)
++ zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
++ idle_thread_set_boot_cpu();
++#endif /* SMP */
++}
++
++#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
++static inline int preempt_count_equals(int preempt_offset)
++{
++ int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth();
++
++ return (nested == preempt_offset);
++}
++
++void __might_sleep(const char *file, int line, int preempt_offset)
++{
++ static unsigned long prev_jiffy; /* ratelimiting */
++
++ rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */
++ if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) ||
++ system_state != SYSTEM_RUNNING || oops_in_progress)
++ return;
++ if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
++ return;
++ prev_jiffy = jiffies;
++
++ printk(KERN_ERR
++ "BUG: sleeping function called from invalid context at %s:%d\n",
++ file, line);
++ printk(KERN_ERR
++ "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n",
++ in_atomic(), irqs_disabled(),
++ current->pid, current->comm);
++
++ debug_show_held_locks(current);
++ if (irqs_disabled())
++ print_irqtrace_events(current);
++ dump_stack();
++}
++EXPORT_SYMBOL(__might_sleep);
++#endif
++
++#ifdef CONFIG_MAGIC_SYSRQ
++void normalize_rt_tasks(void)
++{
++ struct task_struct *g, *p;
++ unsigned long flags;
++ struct rq *rq;
++ int queued;
++
++ read_lock_irqsave(&tasklist_lock, flags);
++
++ do_each_thread(g, p) {
++ if (!rt_task(p) && !iso_task(p))
++ continue;
++
++ raw_spin_lock(&p->pi_lock);
++ rq = __task_grq_lock(p);
++
++ queued = task_queued(p);
++ if (queued)
++ dequeue_task(p);
++ __setscheduler(p, rq, SCHED_NORMAL, 0);
++ if (queued) {
++ enqueue_task(p);
++ try_preempt(p, rq);
++ }
++
++ __task_grq_unlock();
++ raw_spin_unlock(&p->pi_lock);
++ } while_each_thread(g, p);
++
++ read_unlock_irqrestore(&tasklist_lock, flags);
++}
++#endif /* CONFIG_MAGIC_SYSRQ */
++
++#if defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB)
++/*
++ * These functions are only useful for the IA64 MCA handling, or kdb.
++ *
++ * They can only be called when the whole system has been
++ * stopped - every CPU needs to be quiescent, and no scheduling
++ * activity can take place. Using them for anything else would
++ * be a serious bug, and as a result, they aren't even visible
++ * under any other configuration.
++ */
++
++/**
++ * curr_task - return the current task for a given cpu.
++ * @cpu: the processor in question.
++ *
++ * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
++ */
++struct task_struct *curr_task(int cpu)
++{
++ return cpu_curr(cpu);
++}
++
++#endif /* defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) */
++
++#ifdef CONFIG_IA64
++/**
++ * set_curr_task - set the current task for a given cpu.
++ * @cpu: the processor in question.
++ * @p: the task pointer to set.
++ *
++ * Description: This function must only be used when non-maskable interrupts
++ * are serviced on a separate stack. It allows the architecture to switch the
++ * notion of the current task on a cpu in a non-blocking manner. This function
++ * must be called with all CPU's synchronised, and interrupts disabled, the
++ * and caller must save the original value of the current task (see
++ * curr_task() above) and restore that value before reenabling interrupts and
++ * re-starting the system.
++ *
++ * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
++ */
++void set_curr_task(int cpu, struct task_struct *p)
++{
++ cpu_curr(cpu) = p;
++}
++
++#endif
++
++/*
++ * Use precise platform statistics if available:
++ */
++#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
++void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
++{
++ *ut = p->utime;
++ *st = p->stime;
++}
++
++void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
++{
++ struct task_cputime cputime;
++
++ thread_group_cputime(p, &cputime);
++
++ *ut = cputime.utime;
++ *st = cputime.stime;
++}
++
++void vtime_account_system_irqsafe(struct task_struct *tsk)
++{
++ unsigned long flags;
++
++ local_irq_save(flags);
++ vtime_account_system(tsk);
++ local_irq_restore(flags);
++}
++EXPORT_SYMBOL_GPL(vtime_account_system_irqsafe);
++
++#ifndef __ARCH_HAS_VTIME_TASK_SWITCH
++void vtime_task_switch(struct task_struct *prev)
++{
++ if (is_idle_task(prev))
++ vtime_account_idle(prev);
++ else
++ vtime_account_system(prev);
++
++ vtime_account_user(prev);
++ arch_vtime_task_switch(prev);
++}
++#endif
++
++#else
++/*
++ * Perform (stime * rtime) / total, but avoid multiplication overflow by
++ * losing precision when the numbers are big.
++ */
++static cputime_t scale_stime(u64 stime, u64 rtime, u64 total)
++{
++ u64 scaled;
++
++ for (;;) {
++ /* Make sure "rtime" is the bigger of stime/rtime */
++ if (stime > rtime) {
++ u64 tmp = rtime; rtime = stime; stime = tmp;
++ }
++
++ /* Make sure 'total' fits in 32 bits */
++ if (total >> 32)
++ goto drop_precision;
++
++ /* Does rtime (and thus stime) fit in 32 bits? */
++ if (!(rtime >> 32))
++ break;
++
++ /* Can we just balance rtime/stime rather than dropping bits? */
++ if (stime >> 31)
++ goto drop_precision;
++
++ /* We can grow stime and shrink rtime and try to make them both fit */
++ stime <<= 1;
++ rtime >>= 1;
++ continue;
++
++drop_precision:
++ /* We drop from rtime, it has more bits than stime */
++ rtime >>= 1;
++ total >>= 1;
++ }
++
++ /*
++ * Make sure gcc understands that this is a 32x32->64 multiply,
++ * followed by a 64/32->64 divide.
++ */
++ scaled = div_u64((u64) (u32) stime * (u64) (u32) rtime, (u32)total);
++ return (__force cputime_t) scaled;
++}
++
++/*
++ * Adjust tick based cputime random precision against scheduler
++ * runtime accounting.
++ */
++static void cputime_adjust(struct task_cputime *curr,
++ struct cputime *prev,
++ cputime_t *ut, cputime_t *st)
++{
++ cputime_t rtime, stime, utime, total;
++
++ stime = curr->stime;
++ total = stime + curr->utime;
++
++ /*
++ * Tick based cputime accounting depend on random scheduling
++ * timeslices of a task to be interrupted or not by the timer.
++ * Depending on these circumstances, the number of these interrupts
++ * may be over or under-optimistic, matching the real user and system
++ * cputime with a variable precision.
++ *
++ * Fix this by scaling these tick based values against the total
++ * runtime accounted by the CFS scheduler.
++ */
++ rtime = nsecs_to_cputime(curr->sum_exec_runtime);
++
++ /*
++ * Update userspace visible utime/stime values only if actual execution
++ * time is bigger than already exported. Note that can happen, that we
++ * provided bigger values due to scaling inaccuracy on big numbers.
++ */
++ if (prev->stime + prev->utime >= rtime)
++ goto out;
++
++ if (total) {
++ stime = scale_stime((__force u64)stime,
++ (__force u64)rtime, (__force u64)total);
++ utime = rtime - stime;
++ } else {
++ stime = rtime;
++ utime = 0;
++ }
++
++ /*
++ * If the tick based count grows faster than the scheduler one,
++ * the result of the scaling may go backward.
++ * Let's enforce monotonicity.
++ */
++ prev->stime = max(prev->stime, stime);
++ prev->utime = max(prev->utime, utime);
++
++out:
++ *ut = prev->utime;
++ *st = prev->stime;
++}
++
++void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
++{
++ struct task_cputime cputime = {
++ .sum_exec_runtime = tsk_seruntime(p),
++ };
++
++ task_cputime(p, &cputime.utime, &cputime.stime);
++ cputime_adjust(&cputime, &p->prev_cputime, ut, st);
++}
++
++/*
++ * Must be called with siglock held.
++ */
++void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
++{
++ struct task_cputime cputime;
++
++ thread_group_cputime(p, &cputime);
++ cputime_adjust(&cputime, &p->signal->prev_cputime, ut, st);
++}
++#endif
++
++void __cpuinit init_idle_bootup_task(struct task_struct *idle)
++{}
++
++#ifdef CONFIG_SCHED_DEBUG
++void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
++{}
++
++void proc_sched_set_task(struct task_struct *p)
++{}
++#endif
++
++#ifdef CONFIG_SMP
++#define SCHED_LOAD_SHIFT (10)
++#define SCHED_LOAD_SCALE (1L << SCHED_LOAD_SHIFT)
++
++unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu)
++{
++ return SCHED_LOAD_SCALE;
++}
++
++unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu)
++{
++ unsigned long weight = cpumask_weight(sched_domain_span(sd));
++ unsigned long smt_gain = sd->smt_gain;
++
++ smt_gain /= weight;
++
++ return smt_gain;
++}
++#endif
+Index: linux-3.10-ck1/include/uapi/linux/sched.h
+===================================================================
+--- linux-3.10-ck1.orig/include/uapi/linux/sched.h 2013-07-09 17:28:57.142502083 +1000
++++ linux-3.10-ck1/include/uapi/linux/sched.h 2013-07-09 17:29:00.843501924 +1000
+@@ -37,8 +37,15 @@
+ #define SCHED_FIFO 1
+ #define SCHED_RR 2
+ #define SCHED_BATCH 3
+-/* SCHED_ISO: reserved but not implemented yet */
++/* SCHED_ISO: Implemented on BFS only */
+ #define SCHED_IDLE 5
++#ifdef CONFIG_SCHED_BFS
++#define SCHED_ISO 4
++#define SCHED_IDLEPRIO SCHED_IDLE
++#define SCHED_MAX (SCHED_IDLEPRIO)
++#define SCHED_RANGE(policy) ((policy) <= SCHED_MAX)
++#endif
++
+ /* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */
+ #define SCHED_RESET_ON_FORK 0x40000000
+
+Index: linux-3.10-ck1/include/linux/sched/rt.h
+===================================================================
+--- linux-3.10-ck1.orig/include/linux/sched/rt.h 2013-07-09 17:28:57.158502083 +1000
++++ linux-3.10-ck1/include/linux/sched/rt.h 2013-07-09 17:29:00.844501924 +1000
+@@ -14,11 +14,24 @@
+ * MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO.
+ */
+
++#ifdef CONFIG_SCHED_BFS
++#define MAX_USER_RT_PRIO 100
++#define MAX_RT_PRIO (MAX_USER_RT_PRIO + 1)
++#define DEFAULT_PRIO (MAX_RT_PRIO + 20)
++
++#define PRIO_RANGE (40)
++#define MAX_PRIO (MAX_RT_PRIO + PRIO_RANGE)
++#define ISO_PRIO (MAX_RT_PRIO)
++#define NORMAL_PRIO (MAX_RT_PRIO + 1)
++#define IDLE_PRIO (MAX_RT_PRIO + 2)
++#define PRIO_LIMIT ((IDLE_PRIO) + 1)
++#else /* CONFIG_SCHED_BFS */
+ #define MAX_USER_RT_PRIO 100
+ #define MAX_RT_PRIO MAX_USER_RT_PRIO
+
+ #define MAX_PRIO (MAX_RT_PRIO + 40)
+ #define DEFAULT_PRIO (MAX_RT_PRIO + 20)
++#endif /* CONFIG_SCHED_BFS */
+
+ static inline int rt_prio(int prio)
+ {
+Index: linux-3.10-ck1/kernel/stop_machine.c
+===================================================================
+--- linux-3.10-ck1.orig/kernel/stop_machine.c 2013-07-09 17:28:57.177502082 +1000
++++ linux-3.10-ck1/kernel/stop_machine.c 2013-07-09 17:29:00.844501924 +1000
+@@ -40,7 +40,8 @@
+ };
+
+ static DEFINE_PER_CPU(struct cpu_stopper, cpu_stopper);
+-static DEFINE_PER_CPU(struct task_struct *, cpu_stopper_task);
++DEFINE_PER_CPU(struct task_struct *, cpu_stopper_task);
++
+ static bool stop_machine_initialized = false;
+
+ static void cpu_stop_init_done(struct cpu_stop_done *done, unsigned int nr_todo)
+Index: linux-3.10-ck1/drivers/cpufreq/cpufreq_conservative.c
+===================================================================
+--- linux-3.10-ck1.orig/drivers/cpufreq/cpufreq_conservative.c 2013-07-09 17:28:57.219502080 +1000
++++ linux-3.10-ck1/drivers/cpufreq/cpufreq_conservative.c 2013-07-09 17:29:00.844501924 +1000
+@@ -27,8 +27,8 @@
+ #include "cpufreq_governor.h"
+
+ /* Conservative governor macros */
+-#define DEF_FREQUENCY_UP_THRESHOLD (80)
+-#define DEF_FREQUENCY_DOWN_THRESHOLD (20)
++#define DEF_FREQUENCY_UP_THRESHOLD (63)
++#define DEF_FREQUENCY_DOWN_THRESHOLD (26)
+ #define DEF_FREQUENCY_STEP (5)
+ #define DEF_SAMPLING_DOWN_FACTOR (1)
+ #define MAX_SAMPLING_DOWN_FACTOR (10)
+Index: linux-3.10-ck1/kernel/sched/Makefile
+===================================================================
+--- linux-3.10-ck1.orig/kernel/sched/Makefile 2013-07-09 17:28:57.194502081 +1000
++++ linux-3.10-ck1/kernel/sched/Makefile 2013-07-09 17:29:00.844501924 +1000
+@@ -11,9 +11,13 @@
+ CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer
+ endif
+
++ifdef CONFIG_SCHED_BFS
++obj-y += bfs.o clock.o
++else
+ obj-y += core.o clock.o cputime.o idle_task.o fair.o rt.o stop_task.o
+-obj-$(CONFIG_SMP) += cpupri.o
+ obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
+-obj-$(CONFIG_SCHEDSTATS) += stats.o
+ obj-$(CONFIG_SCHED_DEBUG) += debug.o
+ obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o
++endif
++obj-$(CONFIG_SMP) += cpupri.o
++obj-$(CONFIG_SCHEDSTATS) += stats.o
+Index: linux-3.10-ck1/kernel/time/Kconfig
+===================================================================
+--- linux-3.10-ck1.orig/kernel/time/Kconfig 2013-07-09 17:28:57.190502081 +1000
++++ linux-3.10-ck1/kernel/time/Kconfig 2013-07-09 17:29:00.844501924 +1000
+@@ -94,7 +94,7 @@
+ config NO_HZ_FULL
+ bool "Full dynticks system (tickless)"
+ # NO_HZ_COMMON dependency
+- depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
++ depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS && !SCHED_BFS
+ # We need at least one periodic CPU for timekeeping
+ depends on SMP
+ # RCU_USER_QS dependency
+Index: linux-3.10-ck1/kernel/Kconfig.preempt
+===================================================================
+--- linux-3.10-ck1.orig/kernel/Kconfig.preempt 2013-07-09 17:28:57.103502085 +1000
++++ linux-3.10-ck1/kernel/Kconfig.preempt 2013-07-09 17:29:01.081501914 +1000
+@@ -1,7 +1,7 @@
+
+ choice
+ prompt "Preemption Model"
+- default PREEMPT_NONE
++ default PREEMPT
+
+ config PREEMPT_NONE
+ bool "No Forced Preemption (Server)"
+@@ -17,7 +17,7 @@
+ latencies.
+
+ config PREEMPT_VOLUNTARY
+- bool "Voluntary Kernel Preemption (Desktop)"
++ bool "Voluntary Kernel Preemption (Nothing)"
+ help
+ This option reduces the latency of the kernel by adding more
+ "explicit preemption points" to the kernel code. These new
+@@ -31,7 +31,8 @@
+ applications to run more 'smoothly' even when the system is
+ under load.
+
+- Select this if you are building a kernel for a desktop system.
++ Select this for no system in particular (choose Preemptible
++ instead on a desktop if you know what's good for you).
+
+ config PREEMPT
+ bool "Preemptible Kernel (Low-Latency Desktop)"
+Index: linux-3.10-ck1/kernel/Kconfig.hz
+===================================================================
+--- linux-3.10-ck1.orig/kernel/Kconfig.hz 2013-07-09 17:28:57.088502086 +1000
++++ linux-3.10-ck1/kernel/Kconfig.hz 2013-07-09 17:29:01.287501905 +1000
+@@ -4,7 +4,7 @@
+
+ choice
+ prompt "Timer frequency"
+- default HZ_250
++ default HZ_1000
+ help
+ Allows the configuration of the timer frequency. It is customary
+ to have the timer interrupt run at 1000 Hz but 100 Hz may be more
+@@ -23,13 +23,14 @@
+ with lots of processors that may show reduced performance if
+ too many timer interrupts are occurring.
+
+- config HZ_250
++ config HZ_250_NODEFAULT
+ bool "250 HZ"
+ help
+- 250 Hz is a good compromise choice allowing server performance
+- while also showing good interactive responsiveness even
+- on SMP and NUMA systems. If you are going to be using NTSC video
+- or multimedia, selected 300Hz instead.
++ 250 HZ is a lousy compromise choice allowing server interactivity
++ while also showing desktop throughput and no extra power saving on
++ laptops. No good for anything.
++
++ Recommend 100 or 1000 instead.
+
+ config HZ_300
+ bool "300 HZ"
+@@ -43,14 +44,16 @@
+ bool "1000 HZ"
+ help
+ 1000 Hz is the preferred choice for desktop systems and other
+- systems requiring fast interactive responses to events.
++ systems requiring fast interactive responses to events. Laptops
++ can also benefit from this choice without sacrificing battery life
++ if dynticks is also enabled.
+
+ endchoice
+
+ config HZ
+ int
+ default 100 if HZ_100
+- default 250 if HZ_250
++ default 250 if HZ_250_NODEFAULT
+ default 300 if HZ_300
+ default 1000 if HZ_1000
+
+Index: linux-3.10-ck1/arch/x86/Kconfig
+===================================================================
+--- linux-3.10-ck1.orig/arch/x86/Kconfig 2013-07-09 17:28:57.044502087 +1000
++++ linux-3.10-ck1/arch/x86/Kconfig 2013-07-09 17:29:01.392501900 +1000
+@@ -1149,7 +1149,7 @@
+ endchoice
+
+ choice
+- prompt "Memory split" if EXPERT
++ prompt "Memory split"
+ default VMSPLIT_3G
+ depends on X86_32
+ ---help---
+@@ -1169,17 +1169,17 @@
+ option alone!
+
+ config VMSPLIT_3G
+- bool "3G/1G user/kernel split"
++ bool "Default 896MB lowmem (3G/1G user/kernel split)"
+ config VMSPLIT_3G_OPT
+ depends on !X86_PAE
+- bool "3G/1G user/kernel split (for full 1G low memory)"
++ bool "1GB lowmem (3G/1G user/kernel split)"
+ config VMSPLIT_2G
+- bool "2G/2G user/kernel split"
++ bool "2GB lowmem (2G/2G user/kernel split)"
+ config VMSPLIT_2G_OPT
+ depends on !X86_PAE
+- bool "2G/2G user/kernel split (for full 2G low memory)"
++ bool "2GB lowmem (2G/2G user/kernel split)"
+ config VMSPLIT_1G
+- bool "1G/3G user/kernel split"
++ bool "3GB lowmem (1G/3G user/kernel split)"
+ endchoice
+
+ config PAGE_OFFSET
+Index: linux-3.10-ck1/Makefile
+===================================================================
+--- linux-3.10-ck1.orig/Makefile 2013-07-09 17:28:57.029502088 +1000
++++ linux-3.10-ck1/Makefile 2013-07-09 17:29:01.490501896 +1000
+@@ -10,6 +10,10 @@
+ # Comments in this file are targeted only to the developer, do not
+ # expect to learn how to build the kernel reading this file.
+
++CKVERSION = -ck1
++CKNAME = BFS Powered
++EXTRAVERSION := $(EXTRAVERSION)$(CKVERSION)
++
+ # Do not:
+ # o use make's built-in rules and variables
+ # (this increases performance and avoids hard-to-debug behaviour);
diff --git a/sys-kernel/kogaion-sources/files/desktop/change-default-console-loglevel.patch b/sys-kernel/kogaion-sources/files/desktop/change-default-console-loglevel.patch
new file mode 100644
index 00000000..5f16dee5
--- /dev/null
+++ b/sys-kernel/kogaion-sources/files/desktop/change-default-console-loglevel.patch
@@ -0,0 +1,13 @@
+// change-default-console-loglevel.patch
+diff -upr linux-3.0.orig/kernel/printk.c linux-3.0/kernel/printk.c
+--- linux-3.0.orig/kernel/printk.c 2011-07-22 05:17:23.000000000 +0300
++++ linux-3.0/kernel/printk.c 2011-07-27 14:43:07.000000000 +0300
+@@ -58,7 +58,7 @@ void asmlinkage __attribute__((weak)) ea
+
+ /* We show everything that is MORE important than this.. */
+ #define MINIMUM_CONSOLE_LOGLEVEL 1 /* Minimum loglevel we let people use */
+-#define DEFAULT_CONSOLE_LOGLEVEL 7 /* anything MORE serious than KERN_DEBUG */
++#define DEFAULT_CONSOLE_LOGLEVEL 4 /* anything MORE serious than KERN_WARNING */
+
+ DECLARE_WAIT_QUEUE_HEAD(log_wait);
+
diff --git a/sys-kernel/kogaion-sources/files/desktop/criu-no-expert.patch b/sys-kernel/kogaion-sources/files/desktop/criu-no-expert.patch
new file mode 100644
index 00000000..b22aa9f5
--- /dev/null
+++ b/sys-kernel/kogaion-sources/files/desktop/criu-no-expert.patch
@@ -0,0 +1,23 @@
+// criu-no-expert.patch
+diff --git a/init/Kconfig b/init/Kconfig
+index be8b7f5..7461760 100644
+--- a/init/Kconfig
++++ b/init/Kconfig
+@@ -989,7 +989,7 @@ config DEBUG_BLK_CGROUP
+ endif # CGROUPS
+
+ config CHECKPOINT_RESTORE
+- bool "Checkpoint/restore support" if EXPERT
++ bool "Checkpoint/restore support"
+ default n
+ help
+ Enables additional kernel features in a sake of checkpoint/restore.
+@@ -1000,7 +1000,7 @@ config CHECKPOINT_RESTORE
+ If unsure, say N here.
+
+ menuconfig NAMESPACES
+- bool "Namespaces support" if EXPERT
++ bool "Namespaces support"
+ default !EXPERT
+ help
+ Provides the way to make tasks work with different objects using
diff --git a/sys-kernel/kogaion-sources/files/desktop/enable_haswell_pstate_driver.patch b/sys-kernel/kogaion-sources/files/desktop/enable_haswell_pstate_driver.patch
new file mode 100644
index 00000000..031f8d2f
--- /dev/null
+++ b/sys-kernel/kogaion-sources/files/desktop/enable_haswell_pstate_driver.patch
@@ -0,0 +1,33 @@
+// enable_haswell_pstate_driver.patch
+--- linux-3.10/drivers/cpufreq/intel_pstate.c 2013-06-30 18:13:29.000000000 -0400
++++ linux-3.10.mod/drivers/cpufreq/intel_pstate.c 2013-07-05 03:10:36.164568840 -0400
+@@ -522,6 +522,11 @@
+ ICPU(0x2a, default_policy),
+ ICPU(0x2d, default_policy),
+ ICPU(0x3a, default_policy),
++ ICPU(0x3a, default_policy),
++ ICPU(0x3c, default_policy),
++ ICPU(0x3f, default_policy),
++ ICPU(0x45, default_policy),
++ ICPU(0x46, default_policy),
+ {}
+ };
+ MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);
+--- linux-3.10/drivers/cpufreq/Kconfig.x86 2013-06-30 18:13:29.000000000 -0400
++++ linux-3.10.mod/drivers/cpufreq/Kconfig.x86 2013-07-05 03:13:22.823827792 -0400
+@@ -6,12 +6,12 @@
+ bool "Intel P state control"
+ depends on X86
+ help
+- This driver provides a P state for Intel core processors.
++ This driver provides a P state for Intel Core processors.
+ The driver implements an internal governor and will become
+- the scaling driver and governor for Sandy bridge processors.
++ the scaling driver and governor for Sandy/Ivy Bridge and Haswell processors.
+
+ When this driver is enabled it will become the perferred
+- scaling driver for Sandy bridge processors.
++ scaling driver for Sandy/Ivy Bridge and Haswell processors.
+
+ If in doubt, say N.
+
diff --git a/sys-kernel/kogaion-sources/files/desktop/set_kogaion_extraversion_in_makefile.patch b/sys-kernel/kogaion-sources/files/desktop/set_kogaion_extraversion_in_makefile.patch
new file mode 100644
index 00000000..a20090f8
--- /dev/null
+++ b/sys-kernel/kogaion-sources/files/desktop/set_kogaion_extraversion_in_makefile.patch
@@ -0,0 +1,12 @@
+diff -Nur a/Makefile b/Makefile
+--- a/Makefile 2014-01-30 20:52:03.849613917 +0200
++++ b/Makefile 2014-01-30 20:56:12.859500865 +0200
+@@ -10,7 +10,7 @@
+ # Comments in this file are targeted only to the developer, do not
+ # expect to learn how to build the kernel reading this file.
+
+-CKVERSION = -ck1
++CKVERSION = -kogaion
+ CKNAME = BFS Powered
+ EXTRAVERSION := $(EXTRAVERSION)$(CKVERSION)
+
diff --git a/sys-kernel/kogaion-sources/files/desktop/uksm-0.1.2.2-for-v3.10.patch b/sys-kernel/kogaion-sources/files/desktop/uksm-0.1.2.2-for-v3.10.patch
new file mode 100644
index 00000000..f62addd2
--- /dev/null
+++ b/sys-kernel/kogaion-sources/files/desktop/uksm-0.1.2.2-for-v3.10.patch
@@ -0,0 +1,7064 @@
+diff --git a/Documentation/vm/00-INDEX b/Documentation/vm/00-INDEX
+index 5481c8b..7141876 100644
+--- a/Documentation/vm/00-INDEX
++++ b/Documentation/vm/00-INDEX
+@@ -14,6 +14,8 @@ hwpoison.txt
+ - explains what hwpoison is
+ ksm.txt
+ - how to use the Kernel Samepage Merging feature.
++uksm.txt
++ - Introduction to Ultra KSM
+ locking
+ - info on how locking and synchronization is done in the Linux vm code.
+ map_hugetlb.c
+diff --git a/Documentation/vm/uksm.txt b/Documentation/vm/uksm.txt
+new file mode 100644
+index 0000000..9b2cb51
+--- /dev/null
++++ b/Documentation/vm/uksm.txt
+@@ -0,0 +1,57 @@
++The Ultra Kernel Samepage Merging feature
++----------------------------------------------
++/*
++ * Ultra KSM. Copyright (C) 2011-2012 Nai Xia
++ *
++ * This is an improvement upon KSM. Some basic data structures and routines
++ * are borrowed from ksm.c .
++ *
++ * Its new features:
++ * 1. Full system scan:
++ * It automatically scans all user processes' anonymous VMAs. Kernel-user
++ * interaction to submit a memory area to KSM is no longer needed.
++ *
++ * 2. Rich area detection:
++ * It automatically detects rich areas containing abundant duplicated
++ * pages based. Rich areas are given a full scan speed. Poor areas are
++ * sampled at a reasonable speed with very low CPU consumption.
++ *
++ * 3. Ultra Per-page scan speed improvement:
++ * A new hash algorithm is proposed. As a result, on a machine with
++ * Core(TM)2 Quad Q9300 CPU in 32-bit mode and 800MHZ DDR2 main memory, it
++ * can scan memory areas that does not contain duplicated pages at speed of
++ * 627MB/sec ~ 2445MB/sec and can merge duplicated areas at speed of
++ * 477MB/sec ~ 923MB/sec.
++ *
++ * 4. Thrashing area avoidance:
++ * Thrashing area(an VMA that has frequent Ksm page break-out) can be
++ * filtered out. My benchmark shows it's more efficient than KSM's per-page
++ * hash value based volatile page detection.
++ *
++ *
++ * 5. Misc changes upon KSM:
++ * * It has a fully x86-opitmized memcmp dedicated for 4-byte-aligned page
++ * comparison. It's much faster than default C version on x86.
++ * * rmap_item now has an struct *page member to loosely cache a
++ * address-->page mapping, which reduces too much time-costly
++ * follow_page().
++ * * The VMA creation/exit procedures are hooked to let the Ultra KSM know.
++ * * try_to_merge_two_pages() now can revert a pte if it fails. No break_
++ * ksm is needed for this case.
++ *
++ * 6. Full Zero Page consideration(contributed by Figo Zhang)
++ * Now uksmd consider full zero pages as special pages and merge them to an
++ * special unswappable uksm zero page.
++ */
++
++ChangeLog:
++
++2012-05-05 The creation of this Doc
++2012-05-08 UKSM 0.1.1.1 libc crash bug fix, api clean up, doc clean up.
++2012-05-28 UKSM 0.1.1.2 bug fix release
++2012-06-26 UKSM 0.1.2-beta1 first beta release for 0.1.2
++2012-07-2 UKSM 0.1.2-beta2
++2012-07-10 UKSM 0.1.2-beta3
++2012-07-26 UKSM 0.1.2 Fine grained speed control, more scan optimization.
++2012-10-13 UKSM 0.1.2.1 Bug fixes.
++2012-12-31 UKSM 0.1.2.2 Minor bug fixes
+diff --git a/fs/exec.c b/fs/exec.c
+index ffd7a81..1c4d7d3 100644
+--- a/fs/exec.c
++++ b/fs/exec.c
+@@ -19,7 +19,7 @@
+ * current->executable is only used by the procfs. This allows a dispatch
+ * table to check for several different types of binary formats. We keep
+ * trying until we recognize the file or we run out of supported binary
+- * formats.
++ * formats.
+ */
+
+ #include <linux/slab.h>
+@@ -55,6 +55,7 @@
+ #include <linux/pipe_fs_i.h>
+ #include <linux/oom.h>
+ #include <linux/compat.h>
++#include <linux/ksm.h>
+
+ #include <asm/uaccess.h>
+ #include <asm/mmu_context.h>
+@@ -1139,7 +1140,7 @@ void setup_new_exec(struct linux_binprm * bprm)
+ group */
+
+ current->self_exec_id++;
+-
++
+ flush_signal_handlers(current, 0);
+ do_close_on_exec(current->files);
+ }
+@@ -1265,8 +1266,8 @@ static int check_unsafe_exec(struct linux_binprm *bprm)
+ return res;
+ }
+
+-/*
+- * Fill the binprm structure from the inode.
++/*
++ * Fill the binprm structure from the inode.
+ * Check permissions, then read the first 128 (BINPRM_BUF_SIZE) bytes
+ *
+ * This may be called multiple times for binary chains (scripts for example).
+diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
+index 5aa847a..c6c5553 100644
+--- a/fs/proc/meminfo.c
++++ b/fs/proc/meminfo.c
+@@ -88,6 +88,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
+ "SUnreclaim: %8lu kB\n"
+ "KernelStack: %8lu kB\n"
+ "PageTables: %8lu kB\n"
++#ifdef CONFIG_UKSM
++ "KsmZeroPages: %8lu kB\n"
++#endif
+ #ifdef CONFIG_QUICKLIST
+ "Quicklists: %8lu kB\n"
+ #endif
+@@ -147,6 +150,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
+ K(global_page_state(NR_SLAB_UNRECLAIMABLE)),
+ global_page_state(NR_KERNEL_STACK) * THREAD_SIZE / 1024,
+ K(global_page_state(NR_PAGETABLE)),
++#ifdef CONFIG_UKSM
++ K(global_page_state(NR_UKSM_ZERO_PAGES)),
++#endif
+ #ifdef CONFIG_QUICKLIST
+ K(quicklist_total_size()),
+ #endif
+diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
+index a59ff51..df359cc 100644
+--- a/include/asm-generic/pgtable.h
++++ b/include/asm-generic/pgtable.h
+@@ -453,12 +453,25 @@ extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
+ unsigned long size);
+ #endif
+
++#ifdef CONFIG_UKSM
++static inline int is_uksm_zero_pfn(unsigned long pfn)
++{
++ extern unsigned long uksm_zero_pfn;
++ return pfn == uksm_zero_pfn;
++}
++#else
++static inline int is_uksm_zero_pfn(unsigned long pfn)
++{
++ return 0;
++}
++#endif
++
+ #ifdef __HAVE_COLOR_ZERO_PAGE
+ static inline int is_zero_pfn(unsigned long pfn)
+ {
+ extern unsigned long zero_pfn;
+ unsigned long offset_from_zero_pfn = pfn - zero_pfn;
+- return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT);
++ return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT) || is_uksm_zero_pfn(pfn);
+ }
+
+ #define my_zero_pfn(addr) page_to_pfn(ZERO_PAGE(addr))
+@@ -467,7 +480,7 @@ static inline int is_zero_pfn(unsigned long pfn)
+ static inline int is_zero_pfn(unsigned long pfn)
+ {
+ extern unsigned long zero_pfn;
+- return pfn == zero_pfn;
++ return (pfn == zero_pfn) || (is_uksm_zero_pfn(pfn));
+ }
+
+ static inline unsigned long my_zero_pfn(unsigned long addr)
+diff --git a/include/linux/ksm.h b/include/linux/ksm.h
+index 45c9b6a..c7de7a7 100644
+--- a/include/linux/ksm.h
++++ b/include/linux/ksm.h
+@@ -19,21 +19,6 @@ struct mem_cgroup;
+ #ifdef CONFIG_KSM
+ int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
+ unsigned long end, int advice, unsigned long *vm_flags);
+-int __ksm_enter(struct mm_struct *mm);
+-void __ksm_exit(struct mm_struct *mm);
+-
+-static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
+-{
+- if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags))
+- return __ksm_enter(mm);
+- return 0;
+-}
+-
+-static inline void ksm_exit(struct mm_struct *mm)
+-{
+- if (test_bit(MMF_VM_MERGEABLE, &mm->flags))
+- __ksm_exit(mm);
+-}
+
+ /*
+ * A KSM page is one of those write-protected "shared pages" or "merged pages"
+@@ -80,6 +65,33 @@ int rmap_walk_ksm(struct page *page, int (*rmap_one)(struct page *,
+ struct vm_area_struct *, unsigned long, void *), void *arg);
+ void ksm_migrate_page(struct page *newpage, struct page *oldpage);
+
++#ifdef CONFIG_KSM_LEGACY
++int __ksm_enter(struct mm_struct *mm);
++void __ksm_exit(struct mm_struct *mm);
++static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
++{
++ if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags))
++ return __ksm_enter(mm);
++ return 0;
++}
++
++static inline void ksm_exit(struct mm_struct *mm)
++{
++ if (test_bit(MMF_VM_MERGEABLE, &mm->flags))
++ __ksm_exit(mm);
++}
++
++#elif defined(CONFIG_UKSM)
++static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
++{
++ return 0;
++}
++
++static inline void ksm_exit(struct mm_struct *mm)
++{
++}
++#endif /* !CONFIG_UKSM */
++
+ #else /* !CONFIG_KSM */
+
+ static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
+@@ -132,4 +144,6 @@ static inline void ksm_migrate_page(struct page *newpage, struct page *oldpage)
+ #endif /* CONFIG_MMU */
+ #endif /* !CONFIG_KSM */
+
++#include <linux/uksm.h>
++
+ #endif /* __LINUX_KSM_H */
+diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
+index ace9a5f..6a76d6e 100644
+--- a/include/linux/mm_types.h
++++ b/include/linux/mm_types.h
+@@ -289,6 +289,9 @@ struct vm_area_struct {
+ #ifdef CONFIG_NUMA
+ struct mempolicy *vm_policy; /* NUMA policy for the VMA */
+ #endif
++#ifdef CONFIG_UKSM
++ struct vma_slot *uksm_vma_slot;
++#endif
+ };
+
+ struct core_thread {
+diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
+index 5c76737..a631b29 100644
+--- a/include/linux/mmzone.h
++++ b/include/linux/mmzone.h
+@@ -143,6 +143,9 @@ enum zone_stat_item {
+ #endif
+ NR_ANON_TRANSPARENT_HUGEPAGES,
+ NR_FREE_CMA_PAGES,
++#ifdef CONFIG_UKSM
++ NR_UKSM_ZERO_PAGES,
++#endif
+ NR_VM_ZONE_STAT_ITEMS };
+
+ /*
+@@ -849,7 +852,7 @@ static inline int is_normal_idx(enum zone_type idx)
+ }
+
+ /**
+- * is_highmem - helper function to quickly check if a struct zone is a
++ * is_highmem - helper function to quickly check if a struct zone is a
+ * highmem zone or not. This is an attempt to keep references
+ * to ZONE_{DMA/NORMAL/HIGHMEM/etc} in general code to a minimum.
+ * @zone - pointer to struct zone variable
+diff --git a/include/linux/sradix-tree.h b/include/linux/sradix-tree.h
+new file mode 100644
+index 0000000..6780fdb
+--- /dev/null
++++ b/include/linux/sradix-tree.h
+@@ -0,0 +1,77 @@
++#ifndef _LINUX_SRADIX_TREE_H
++#define _LINUX_SRADIX_TREE_H
++
++
++#define INIT_SRADIX_TREE(root, mask) \
++do { \
++ (root)->height = 0; \
++ (root)->gfp_mask = (mask); \
++ (root)->rnode = NULL; \
++} while (0)
++
++#define ULONG_BITS (sizeof(unsigned long) * 8)
++#define SRADIX_TREE_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(unsigned long))
++//#define SRADIX_TREE_MAP_SHIFT 6
++//#define SRADIX_TREE_MAP_SIZE (1UL << SRADIX_TREE_MAP_SHIFT)
++//#define SRADIX_TREE_MAP_MASK (SRADIX_TREE_MAP_SIZE-1)
++
++struct sradix_tree_node {
++ unsigned int height; /* Height from the bottom */
++ unsigned int count;
++ unsigned int fulls; /* Number of full sublevel trees */
++ struct sradix_tree_node *parent;
++ void *stores[0];
++};
++
++/* A simple radix tree implementation */
++struct sradix_tree_root {
++ unsigned int height;
++ struct sradix_tree_node *rnode;
++
++ /* Where found to have available empty stores in its sublevels */
++ struct sradix_tree_node *enter_node;
++ unsigned int shift;
++ unsigned int stores_size;
++ unsigned int mask;
++ unsigned long min; /* The first hole index */
++ unsigned long num;
++ //unsigned long *height_to_maxindex;
++
++ /* How the node is allocated and freed. */
++ struct sradix_tree_node *(*alloc)(void);
++ void (*free)(struct sradix_tree_node *node);
++
++ /* When a new node is added and removed */
++ void (*extend)(struct sradix_tree_node *parent, struct sradix_tree_node *child);
++ void (*assign)(struct sradix_tree_node *node, unsigned index, void *item);
++ void (*rm)(struct sradix_tree_node *node, unsigned offset);
++};
++
++struct sradix_tree_path {
++ struct sradix_tree_node *node;
++ int offset;
++};
++
++static inline
++void init_sradix_tree_root(struct sradix_tree_root *root, unsigned long shift)
++{
++ root->height = 0;
++ root->rnode = NULL;
++ root->shift = shift;
++ root->stores_size = 1UL << shift;
++ root->mask = root->stores_size - 1;
++}
++
++
++extern void *sradix_tree_next(struct sradix_tree_root *root,
++ struct sradix_tree_node *node, unsigned long index,
++ int (*iter)(void *, unsigned long));
++
++extern int sradix_tree_enter(struct sradix_tree_root *root, void **item, int num);
++
++extern void sradix_tree_delete_from_leaf(struct sradix_tree_root *root,
++ struct sradix_tree_node *node, unsigned long index);
++
++extern void *sradix_tree_lookup(struct sradix_tree_root *root, unsigned long index);
++
++#endif /* _LINUX_SRADIX_TREE_H */
+diff --git a/include/linux/uksm.h b/include/linux/uksm.h
+new file mode 100644
+index 0000000..a644bca
+--- /dev/null
++++ b/include/linux/uksm.h
+@@ -0,0 +1,146 @@
++#ifndef __LINUX_UKSM_H
++#define __LINUX_UKSM_H
++/*
++ * Memory merging support.
++ *
++ * This code enables dynamic sharing of identical pages found in different
++ * memory areas, even if they are not shared by fork().
++ */
++
++/* if !CONFIG_UKSM this file should not be compiled at all. */
++#ifdef CONFIG_UKSM
++
++#include <linux/bitops.h>
++#include <linux/mm.h>
++#include <linux/pagemap.h>
++#include <linux/rmap.h>
++#include <linux/sched.h>
++
++extern unsigned long zero_pfn __read_mostly;
++extern unsigned long uksm_zero_pfn __read_mostly;
++extern struct page *empty_uksm_zero_page;
++
++/* must be done before linked to mm */
++extern void uksm_vma_add_new(struct vm_area_struct *vma);
++extern void uksm_remove_vma(struct vm_area_struct *vma);
++
++#define UKSM_SLOT_NEED_SORT (1 << 0)
++#define UKSM_SLOT_NEED_RERAND (1 << 1)
++#define UKSM_SLOT_SCANNED (1 << 2) /* It's scanned in this round */
++#define UKSM_SLOT_FUL_SCANNED (1 << 3)
++#define UKSM_SLOT_IN_UKSM (1 << 4)
++
++struct vma_slot {
++ struct sradix_tree_node *snode;
++ unsigned long sindex;
++
++ struct list_head slot_list;
++ unsigned long fully_scanned_round;
++ unsigned long dedup_num;
++ unsigned long pages_scanned;
++ unsigned long last_scanned;
++ unsigned long pages_to_scan;
++ struct scan_rung *rung;
++ struct page **rmap_list_pool;
++ unsigned int *pool_counts;
++ unsigned long pool_size;
++ struct vm_area_struct *vma;
++ struct mm_struct *mm;
++ unsigned long ctime_j;
++ unsigned long pages;
++ unsigned long flags;
++ unsigned long pages_cowed; /* pages cowed this round */
++ unsigned long pages_merged; /* pages merged this round */
++ unsigned long pages_bemerged;
++
++ /* when it has page merged in this eval round */
++ struct list_head dedup_list;
++};
++
++static inline void uksm_unmap_zero_page(pte_t pte)
++{
++ if (pte_pfn(pte) == uksm_zero_pfn)
++ __dec_zone_page_state(empty_uksm_zero_page, NR_UKSM_ZERO_PAGES);
++}
++
++static inline void uksm_map_zero_page(pte_t pte)
++{
++ if (pte_pfn(pte) == uksm_zero_pfn)
++ __inc_zone_page_state(empty_uksm_zero_page, NR_UKSM_ZERO_PAGES);
++}
++
++static inline void uksm_cow_page(struct vm_area_struct *vma, struct page *page)
++{
++ if (vma->uksm_vma_slot && PageKsm(page))
++ vma->uksm_vma_slot->pages_cowed++;
++}
++
++static inline void uksm_cow_pte(struct vm_area_struct *vma, pte_t pte)
++{
++ if (vma->uksm_vma_slot && pte_pfn(pte) == uksm_zero_pfn)
++ vma->uksm_vma_slot->pages_cowed++;
++}
++
++static inline int uksm_flags_can_scan(unsigned long vm_flags)
++{
++#ifndef VM_SAO
++#define VM_SAO 0
++#endif
++ return !(vm_flags & (VM_PFNMAP | VM_IO | VM_DONTEXPAND |
++ VM_HUGETLB | VM_NONLINEAR | VM_MIXEDMAP |
++ VM_SHARED | VM_MAYSHARE | VM_GROWSUP | VM_GROWSDOWN | VM_SAO));
++}
++
++static inline void uksm_vm_flags_mod(unsigned long *vm_flags_p)
++{
++ if (uksm_flags_can_scan(*vm_flags_p))
++ *vm_flags_p |= VM_MERGEABLE;
++}
++
++/*
++ * Just a wrapper for BUG_ON for where ksm_zeropage must not be. TODO: it will
++ * be removed when uksm zero page patch is stable enough.
++ */
++static inline void uksm_bugon_zeropage(pte_t pte)
++{
++ BUG_ON(pte_pfn(pte) == uksm_zero_pfn);
++}
++#else
++static inline void uksm_vma_add_new(struct vm_area_struct *vma)
++{
++}
++
++static inline void uksm_remove_vma(struct vm_area_struct *vma)
++{
++}
++
++static inline void uksm_unmap_zero_page(pte_t pte)
++{
++}
++
++static inline void uksm_map_zero_page(pte_t pte)
++{
++}
++
++static inline void uksm_cow_page(struct vm_area_struct *vma, struct page *page)
++{
++}
++
++static inline void uksm_cow_pte(struct vm_area_struct *vma, pte_t pte)
++{
++}
++
++static inline int uksm_flags_can_scan(unsigned long vm_flags)
++{
++ return 0;
++}
++
++static inline void uksm_vm_flags_mod(unsigned long *vm_flags_p)
++{
++}
++
++static inline void uksm_bugon_zeropage(pte_t pte)
++{
++}
++#endif /* !CONFIG_UKSM */
++#endif /* __LINUX_UKSM_H */
+diff --git a/kernel/fork.c b/kernel/fork.c
+index 987b28a..3e89974 100644
+--- a/kernel/fork.c
++++ b/kernel/fork.c
+@@ -397,7 +397,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
+ goto fail_nomem;
+ charge = len;
+ }
+- tmp = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
++ tmp = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+ if (!tmp)
+ goto fail_nomem;
+ *tmp = *mpnt;
+@@ -454,7 +454,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
+ __vma_link_rb(mm, tmp, rb_link, rb_parent);
+ rb_link = &tmp->vm_rb.rb_right;
+ rb_parent = &tmp->vm_rb;
+-
++ uksm_vma_add_new(tmp);
+ mm->map_count++;
+ retval = copy_page_range(mm, oldmm, mpnt);
+
+diff --git a/lib/Makefile b/lib/Makefile
+index c55a037..fcf7e6d 100644
+--- a/lib/Makefile
++++ b/lib/Makefile
+@@ -8,7 +8,7 @@ KBUILD_CFLAGS = $(subst -pg,,$(ORIG_CFLAGS))
+ endif
+
+ lib-y := ctype.o string.o vsprintf.o cmdline.o \
+- rbtree.o radix-tree.o dump_stack.o timerqueue.o\
++ rbtree.o radix-tree.o sradix-tree.o dump_stack.o timerqueue.o\
+ idr.o int_sqrt.o extable.o \
+ sha1.o md5.o irq_regs.o reciprocal_div.o argv_split.o \
+ proportions.o flex_proportions.o prio_heap.o ratelimit.o show_mem.o \
+diff --git a/lib/sradix-tree.c b/lib/sradix-tree.c
+new file mode 100644
+index 0000000..8d06329
+--- /dev/null
++++ b/lib/sradix-tree.c
+@@ -0,0 +1,476 @@
++#include <linux/errno.h>
++#include <linux/mm.h>
++#include <linux/mman.h>
++#include <linux/spinlock.h>
++#include <linux/slab.h>
++#include <linux/gcd.h>
++#include <linux/sradix-tree.h>
++
++static inline int sradix_node_full(struct sradix_tree_root *root, struct sradix_tree_node *node)
++{
++ return node->fulls == root->stores_size ||
++ (node->height == 1 && node->count == root->stores_size);
++}
++
++/*
++ * Extend a sradix tree so it can store key @index.
++ */
++static int sradix_tree_extend(struct sradix_tree_root *root, unsigned long index)
++{
++ struct sradix_tree_node *node;
++ unsigned int height;
++
++ if (unlikely(root->rnode == NULL)) {
++ if (!(node = root->alloc()))
++ return -ENOMEM;
++
++ node->height = 1;
++ root->rnode = node;
++ root->height = 1;
++ }
++
++ /* Figure out what the height should be. */
++ height = root->height;
++ index >>= root->shift * height;
++
++ while (index) {
++ index >>= root->shift;
++ height++;
++ }
++
++ while (height > root->height) {
++ unsigned int newheight;
++ if (!(node = root->alloc()))
++ return -ENOMEM;
++
++ /* Increase the height. */
++ node->stores[0] = root->rnode;
++ root->rnode->parent = node;
++ if (root->extend)
++ root->extend(node, root->rnode);
++
++ newheight = root->height + 1;
++ node->height = newheight;
++ node->count = 1;
++ if (sradix_node_full(root, root->rnode))
++ node->fulls = 1;
++
++ root->rnode = node;
++ root->height = newheight;
++ }
++
++ return 0;
++}
++
++/*
++ * Search the next item from the current node, that is not NULL
++ * and can satify root->iter().
++ */
++void *sradix_tree_next(struct sradix_tree_root *root,
++ struct sradix_tree_node *node, unsigned long index,
++ int (*iter)(void *item, unsigned long height))
++{
++ unsigned long offset;
++ void *item;
++
++ if (unlikely(node == NULL)) {
++ node = root->rnode;
++ for (offset = 0; offset < root->stores_size; offset++) {
++ item = node->stores[offset];
++ if (item && (!iter || iter(item, node->height)))
++ break;
++ }
++
++ if (unlikely(offset >= root->stores_size))
++ return NULL;
++
++ if (node->height == 1)
++ return item;
++ else
++ goto go_down;
++ }
++
++ while (node) {
++ offset = (index & root->mask) + 1;
++ for (;offset < root->stores_size; offset++) {
++ item = node->stores[offset];
++ if (item && (!iter || iter(item, node->height)))
++ break;
++ }
++
++ if (offset < root->stores_size)
++ break;
++
++ node = node->parent;
++ index >>= root->shift;
++ }
++
++ if (!node)
++ return NULL;
++
++ while (node->height > 1) {
++go_down:
++ node = item;
++ for (offset = 0; offset < root->stores_size; offset++) {
++ item = node->stores[offset];
++ if (item && (!iter || iter(item, node->height)))
++ break;
++ }
++
++ if (unlikely(offset >= root->stores_size))
++ return NULL;
++ }
++
++ BUG_ON(offset > root->stores_size);
++
++ return item;
++}
++
++/*
++ * Blindly insert the item to the tree. Typically, we reuse the
++ * first empty store item.
++ */
++int sradix_tree_enter(struct sradix_tree_root *root, void **item, int num)
++{
++ unsigned long index;
++ unsigned int height;
++ struct sradix_tree_node *node, *tmp = NULL;
++ int offset, offset_saved;
++ void **store = NULL;
++ int error, i, j, shift;
++
++go_on:
++ index = root->min;
++
++ if (root->enter_node && !sradix_node_full(root, root->enter_node)) {
++ node = root->enter_node;
++ BUG_ON((index >> (root->shift * root->height)));
++ } else {
++ node = root->rnode;
++ if (node == NULL || (index >> (root->shift * root->height))
++ || sradix_node_full(root, node)) {
++ error = sradix_tree_extend(root, index);
++ if (error)
++ return error;
++
++ node = root->rnode;
++ }
++ }
++
++
++ height = node->height;
++ shift = (height - 1) * root->shift;
++ offset = (index >> shift) & root->mask;
++ while (shift > 0) {
++ offset_saved = offset;
++ for (; offset < root->stores_size; offset++) {
++ store = &node->stores[offset];
++ tmp = *store;
++
++ if (!tmp || !sradix_node_full(root, tmp))
++ break;
++ }
++ BUG_ON(offset >= root->stores_size);
++
++ if (offset != offset_saved) {
++ index += (offset - offset_saved) << shift;
++ index &= ~((1UL << shift) - 1);
++ }
++
++ if (!tmp) {
++ if (!(tmp = root->alloc()))
++ return -ENOMEM;
++
++ tmp->height = shift / root->shift;
++ *store = tmp;
++ tmp->parent = node;
++ node->count++;
++// if (root->extend)
++// root->extend(node, tmp);
++ }
++
++ node = tmp;
++ shift -= root->shift;
++ offset = (index >> shift) & root->mask;
++ }
++
++ BUG_ON(node->height != 1);
++
++
++ store = &node->stores[offset];
++ for (i = 0, j = 0;
++ j < root->stores_size - node->count &&
++ i < root->stores_size - offset && j < num; i++) {
++ if (!store[i]) {
++ store[i] = item[j];
++ if (root->assign)
++ root->assign(node, index + i, item[j]);
++ j++;
++ }
++ }
++
++ node->count += j;
++ root->num += j;
++ num -= j;
++
++ while (sradix_node_full(root, node)) {
++ node = node->parent;
++ if (!node)
++ break;
++
++ node->fulls++;
++ }
++
++ if (unlikely(!node)) {
++ /* All nodes are full */
++ root->min = 1 << (root->height * root->shift);
++ root->enter_node = NULL;
++ } else {
++ root->min = index + i - 1;
++ root->min |= (1UL << (node->height - 1)) - 1;
++ root->min++;
++ root->enter_node = node;
++ }
++
++ if (num) {
++ item += j;
++ goto go_on;
++ }
++
++ return 0;
++}
++
++
++/**
++ * sradix_tree_shrink - shrink height of a sradix tree to minimal
++ * @root sradix tree root
++ *
++ */
++static inline void sradix_tree_shrink(struct sradix_tree_root *root)
++{
++ /* try to shrink tree height */
++ while (root->height > 1) {
++ struct sradix_tree_node *to_free = root->rnode;
++
++ /*
++ * The candidate node has more than one child, or its child
++ * is not at the leftmost store, we cannot shrink.
++ */
++ if (to_free->count != 1 || !to_free->stores[0])
++ break;
++
++ root->rnode = to_free->stores[0];
++ root->rnode->parent = NULL;
++ root->height--;
++ if (unlikely(root->enter_node == to_free)) {
++ root->enter_node = NULL;
++ }
++ root->free(to_free);
++ }
++}
++
++/*
++ * Del the item on the known leaf node and index
++ */
++void sradix_tree_delete_from_leaf(struct sradix_tree_root *root,
++ struct sradix_tree_node *node, unsigned long index)
++{
++ unsigned int offset;
++ struct sradix_tree_node *start, *end;
++
++ BUG_ON(node->height != 1);
++
++ start = node;
++ while (node && !(--node->count))
++ node = node->parent;
++
++ end = node;
++ if (!node) {
++ root->rnode = NULL;
++ root->height = 0;
++ root->min = 0;
++ root->num = 0;
++ root->enter_node = NULL;
++ } else {
++ offset = (index >> (root->shift * (node->height - 1))) & root->mask;
++ if (root->rm)
++ root->rm(node, offset);
++ node->stores[offset] = NULL;
++ root->num--;
++ if (root->min > index) {
++ root->min = index;
++ root->enter_node = node;
++ }
++ }
++
++ if (start != end) {
++ do {
++ node = start;
++ start = start->parent;
++ if (unlikely(root->enter_node == node))
++ root->enter_node = end;
++ root->free(node);
++ } while (start != end);
++
++ /*
++ * Note that shrink may free "end", so enter_node still need to
++ * be checked inside.
++ */
++ sradix_tree_shrink(root);
++ } else if (node->count == root->stores_size - 1) {
++ /* It WAS a full leaf node. Update the ancestors */
++ node = node->parent;
++ while (node) {
++ node->fulls--;
++ if (node->fulls != root->stores_size - 1)
++ break;
++
++ node = node->parent;
++ }
++ }
++}
++
++void *sradix_tree_lookup(struct sradix_tree_root *root, unsigned long index)
++{
++ unsigned int height, offset;
++ struct sradix_tree_node *node;
++ int shift;
++
++ node = root->rnode;
++ if (node == NULL || (index >> (root->shift * root->height)))
++ return NULL;
++
++ height = root->height;
++ shift = (height - 1) * root->shift;
++
++ do {
++ offset = (index >> shift) & root->mask;
++ node = node->stores[offset];
++ if (!node)
++ return NULL;
++
++ shift -= root->shift;
++ } while (shift >= 0);
++
++ return node;
++}
++
++/*
++ * Return the item if it exists, otherwise create it in place
++ * and return the created item.
++ */
++void *sradix_tree_lookup_create(struct sradix_tree_root *root,
++ unsigned long index, void *(*item_alloc)(void))
++{
++ unsigned int height, offset;
++ struct sradix_tree_node *node, *tmp;
++ void *item;
++ int shift, error;
++
++ if (root->rnode == NULL || (index >> (root->shift * root->height))) {
++ if (item_alloc) {
++ error = sradix_tree_extend(root, index);
++ if (error)
++ return NULL;
++ } else {
++ return NULL;
++ }
++ }
++
++ node = root->rnode;
++ height = root->height;
++ shift = (height - 1) * root->shift;
++
++ do {
++ offset = (index >> shift) & root->mask;
++ if (!node->stores[offset]) {
++ if (!(tmp = root->alloc()))
++ return NULL;
++
++ tmp->height = shift / root->shift;
++ node->stores[offset] = tmp;
++ tmp->parent = node;
++ node->count++;
++ node = tmp;
++ } else {
++ node = node->stores[offset];
++ }
++
++ shift -= root->shift;
++ } while (shift > 0);
++
++ BUG_ON(node->height != 1);
++ offset = index & root->mask;
++ if (node->stores[offset]) {
++ return node->stores[offset];
++ } else if (item_alloc) {
++ if (!(item = item_alloc()))
++ return NULL;
++
++ node->stores[offset] = item;
++
++ /*
++ * NOTE: we do NOT call root->assign here, since this item is
++ * newly created by us having no meaning. Caller can call this
++ * if it's necessary to do so.
++ */
++
++ node->count++;
++ root->num++;
++
++ while (sradix_node_full(root, node)) {
++ node = node->parent;
++ if (!node)
++ break;
++
++ node->fulls++;
++ }
++
++ if (unlikely(!node)) {
++ /* All nodes are full */
++ root->min = 1 << (root->height * root->shift);
++ } else {
++ if (root->min == index) {
++ root->min |= (1UL << (node->height - 1)) - 1;
++ root->min++;
++ root->enter_node = node;
++ }
++ }
++
++ return item;
++ } else {
++ return NULL;
++ }
++
++}
++
++int sradix_tree_delete(struct sradix_tree_root *root, unsigned long index)
++{
++ unsigned int height, offset;
++ struct sradix_tree_node *node;
++ int shift;
++
++ node = root->rnode;
++ if (node == NULL || (index >> (root->shift * root->height)))
++ return -ENOENT;
++
++ height = root->height;
++ shift = (height - 1) * root->shift;
++
++ do {
++ offset = (index >> shift) & root->mask;
++ node = node->stores[offset];
++ if (!node)
++ return -ENOENT;
++
++ shift -= root->shift;
++ } while (shift > 0);
++
++ offset = index & root->mask;
++ if (!node->stores[offset])
++ return -ENOENT;
++
++ sradix_tree_delete_from_leaf(root, node, index);
++
++ return 0;
++}
+diff --git a/mm/Kconfig b/mm/Kconfig
+index e742d06..93c2533 100644
+--- a/mm/Kconfig
++++ b/mm/Kconfig
+@@ -315,6 +315,32 @@ config KSM
+ See Documentation/vm/ksm.txt for more information: KSM is inactive
+ until a program has madvised that an area is MADV_MERGEABLE, and
+ root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set).
++choice
++ prompt "Choose UKSM/KSM strategy"
++ default UKSM
++ depends on KSM
++ help
++ This option allows to select a UKSM/KSM stragety.
++
++config UKSM
++ bool "Ultra-KSM for page merging"
++ depends on KSM
++ help
++ UKSM is inspired by the Linux kernel project \u2014 KSM(Kernel Same
++ page Merging), but with a fundamentally rewritten core algorithm. With
++ an advanced algorithm, UKSM now can transparently scans all anonymously
++ mapped user space applications with an significantly improved scan speed
++ and CPU efficiency. Since KVM is friendly to KSM, KVM can also benefit from
++ UKSM. Now UKSM has its first stable release and first real world enterprise user.
++ For more information, please goto its project page.
++ (www.kerneldedup.org)
++
++config KSM_LEGACY
++ bool "Legacy KSM implementation"
++ depends on KSM
++ help
++ The legacy KSM implementation from Redhat.
++endchoice
+
+ config DEFAULT_MMAP_MIN_ADDR
+ int "Low address space to protect from user allocation"
+diff --git a/mm/Makefile b/mm/Makefile
+index 72c5acb..77882b7 100644
+--- a/mm/Makefile
++++ b/mm/Makefile
+@@ -39,7 +39,8 @@ obj-$(CONFIG_SPARSEMEM) += sparse.o
+ obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o
+ obj-$(CONFIG_SLOB) += slob.o
+ obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o
+-obj-$(CONFIG_KSM) += ksm.o
++obj-$(CONFIG_KSM_LEGACY) += ksm.o
++obj-$(CONFIG_UKSM) += uksm.o
+ obj-$(CONFIG_PAGE_POISONING) += debug-pagealloc.o
+ obj-$(CONFIG_SLAB) += slab.o
+ obj-$(CONFIG_SLUB) += slub.o
+diff --git a/mm/memory.c b/mm/memory.c
+index 61a262b..a506b9d 100644
+--- a/mm/memory.c
++++ b/mm/memory.c
+@@ -118,6 +118,27 @@ __setup("norandmaps", disable_randmaps);
+ unsigned long zero_pfn __read_mostly;
+ unsigned long highest_memmap_pfn __read_mostly;
+
++#ifdef CONFIG_UKSM
++unsigned long uksm_zero_pfn __read_mostly;
++struct page *empty_uksm_zero_page;
++
++static int __init setup_uksm_zero_page(void)
++{
++ unsigned long addr;
++ addr = __get_free_pages(GFP_KERNEL | __GFP_ZERO, 0);
++ if (!addr)
++ panic("Oh boy, that early out of memory?");
++
++ empty_uksm_zero_page = virt_to_page((void *) addr);
++ SetPageReserved(empty_uksm_zero_page);
++
++ uksm_zero_pfn = page_to_pfn(empty_uksm_zero_page);
++
++ return 0;
++}
++core_initcall(setup_uksm_zero_page);
++#endif
++
+ /*
+ * CONFIG_MMU architectures set up ZERO_PAGE in their paging_init()
+ */
+@@ -129,6 +150,7 @@ static int __init init_zero_pfn(void)
+ core_initcall(init_zero_pfn);
+
+
++
+ #if defined(SPLIT_RSS_COUNTING)
+
+ void sync_mm_rss(struct mm_struct *mm)
+@@ -896,6 +918,11 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+ rss[MM_ANONPAGES]++;
+ else
+ rss[MM_FILEPAGES]++;
++
++ /* Should return NULL in vm_normal_page() */
++ uksm_bugon_zeropage(pte);
++ } else {
++ uksm_map_zero_page(pte);
+ }
+
+ out_set_pte:
+@@ -1138,8 +1165,10 @@ again:
+ ptent = ptep_get_and_clear_full(mm, addr, pte,
+ tlb->fullmm);
+ tlb_remove_tlb_entry(tlb, pte, addr);
+- if (unlikely(!page))
++ if (unlikely(!page)) {
++ uksm_unmap_zero_page(ptent);
+ continue;
++ }
+ if (unlikely(details) && details->nonlinear_vma
+ && linear_page_index(details->nonlinear_vma,
+ addr) != page->index)
+@@ -1704,7 +1733,7 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+
+ VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET));
+
+- /*
++ /*
+ * Require read or write permissions.
+ * If FOLL_FORCE is set, we only require the "MAY" flags.
+ */
+@@ -1764,7 +1793,7 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+ page = vm_normal_page(vma, start, *pte);
+ if (!page) {
+ if (!(gup_flags & FOLL_DUMP) &&
+- is_zero_pfn(pte_pfn(*pte)))
++ (is_zero_pfn(pte_pfn(*pte))))
+ page = pte_page(*pte);
+ else {
+ pte_unmap(pte);
+@@ -2579,8 +2608,10 @@ static inline void cow_user_page(struct page *dst, struct page *src, unsigned lo
+ clear_page(kaddr);
+ kunmap_atomic(kaddr);
+ flush_dcache_page(dst);
+- } else
++ } else {
+ copy_user_highpage(dst, src, va, vma);
++ uksm_cow_page(vma, src);
++ }
+ }
+
+ /*
+@@ -2779,6 +2810,7 @@ gotten:
+ new_page = alloc_zeroed_user_highpage_movable(vma, address);
+ if (!new_page)
+ goto oom;
++ uksm_cow_pte(vma, orig_pte);
+ } else {
+ new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
+ if (!new_page)
+@@ -2804,8 +2836,11 @@ gotten:
+ dec_mm_counter_fast(mm, MM_FILEPAGES);
+ inc_mm_counter_fast(mm, MM_ANONPAGES);
+ }
+- } else
++ uksm_bugon_zeropage(orig_pte);
++ } else {
++ uksm_unmap_zero_page(orig_pte);
+ inc_mm_counter_fast(mm, MM_ANONPAGES);
++ }
+ flush_cache_page(vma, address, pte_pfn(orig_pte));
+ entry = mk_pte(new_page, vma->vm_page_prot);
+ entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+diff --git a/mm/mmap.c b/mm/mmap.c
+index f681e18..31ef952 100644
+--- a/mm/mmap.c
++++ b/mm/mmap.c
+@@ -36,6 +36,7 @@
+ #include <linux/sched/sysctl.h>
+ #include <linux/notifier.h>
+ #include <linux/memory.h>
++#include <linux/ksm.h>
+
+ #include <asm/uaccess.h>
+ #include <asm/cacheflush.h>
+@@ -65,7 +66,7 @@ static void unmap_region(struct mm_struct *mm,
+ * MAP_SHARED r: (no) no r: (yes) yes r: (no) yes r: (no) yes
+ * w: (no) no w: (no) no w: (yes) yes w: (no) no
+ * x: (no) no x: (no) yes x: (no) yes x: (yes) yes
+- *
++ *
+ * MAP_PRIVATE r: (no) no r: (yes) yes r: (no) yes r: (no) yes
+ * w: (no) no w: (no) no w: (copy) copy w: (no) no
+ * x: (no) no x: (no) yes x: (no) yes x: (yes) yes
+@@ -252,6 +253,7 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
+ if (vma->vm_file)
+ fput(vma->vm_file);
+ mpol_put(vma_policy(vma));
++ uksm_remove_vma(vma);
+ kmem_cache_free(vm_area_cachep, vma);
+ return next;
+ }
+@@ -707,9 +709,16 @@ int vma_adjust(struct vm_area_struct *vma, unsigned long start,
+ long adjust_next = 0;
+ int remove_next = 0;
+
++/*
++ * to avoid deadlock, ksm_remove_vma must be done before any spin_lock is
++ * acquired
++ */
++ uksm_remove_vma(vma);
++
+ if (next && !insert) {
+ struct vm_area_struct *exporter = NULL;
+
++ uksm_remove_vma(next);
+ if (end >= next->vm_end) {
+ /*
+ * vma expands, overlapping all the next, and
+@@ -803,6 +812,7 @@ again: remove_next = 1 + (end > next->vm_end);
+ end_changed = true;
+ }
+ vma->vm_pgoff = pgoff;
++
+ if (adjust_next) {
+ next->vm_start += adjust_next << PAGE_SHIFT;
+ next->vm_pgoff += adjust_next;
+@@ -873,16 +883,22 @@ again: remove_next = 1 + (end > next->vm_end);
+ * up the code too much to do both in one go.
+ */
+ next = vma->vm_next;
+- if (remove_next == 2)
++ if (remove_next == 2) {
++ uksm_remove_vma(next);
+ goto again;
+- else if (next)
++ } else if (next) {
+ vma_gap_update(next);
+- else
++ } else {
+ mm->highest_vm_end = end;
++ }
++ } else {
++ if (next && !insert)
++ uksm_vma_add_new(next);
+ }
+ if (insert && file)
+ uprobe_mmap(insert);
+
++ uksm_vma_add_new(vma);
+ validate_mm(mm);
+
+ return 0;
+@@ -1250,6 +1266,9 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
+ vm_flags = calc_vm_prot_bits(prot) | calc_vm_flag_bits(flags) |
+ mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;
+
++ /* If uksm is enabled, we add VM_MERGABLE to new VMAs. */
++ uksm_vm_flags_mod(&vm_flags);
++
+ if (flags & MAP_LOCKED)
+ if (!can_do_mlock())
+ return -EPERM;
+@@ -1595,6 +1614,7 @@ munmap_back:
+
+ vma_link(mm, vma, prev, rb_link, rb_parent);
+ file = vma->vm_file;
++ uksm_vma_add_new(vma);
+
+ /* Once vma denies write, undo our temporary denial count */
+ if (correct_wcount)
+@@ -1626,6 +1646,7 @@ unmap_and_free_vma:
+ unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end);
+ charged = 0;
+ free_vma:
++ uksm_remove_vma(vma);
+ kmem_cache_free(vm_area_cachep, vma);
+ unacct_error:
+ if (charged)
+@@ -1874,7 +1895,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
+ info.align_mask = 0;
+ return vm_unmapped_area(&info);
+ }
+-#endif
++#endif
+
+ void arch_unmap_area(struct mm_struct *mm, unsigned long addr)
+ {
+@@ -2452,6 +2473,8 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
+ else
+ err = vma_adjust(vma, vma->vm_start, addr, vma->vm_pgoff, new);
+
++ uksm_vma_add_new(new);
++
+ /* Success. */
+ if (!err)
+ return 0;
+@@ -2617,6 +2640,7 @@ static unsigned long do_brk(unsigned long addr, unsigned long len)
+ return addr;
+
+ flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
++ uksm_vm_flags_mod(&flags);
+
+ error = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED);
+ if (error & ~PAGE_MASK)
+@@ -2684,6 +2708,7 @@ static unsigned long do_brk(unsigned long addr, unsigned long len)
+ vma->vm_flags = flags;
+ vma->vm_page_prot = vm_get_page_prot(flags);
+ vma_link(mm, vma, prev, rb_link, rb_parent);
++ uksm_vma_add_new(vma);
+ out:
+ perf_event_mmap(vma);
+ mm->total_vm += len >> PAGE_SHIFT;
+@@ -2718,6 +2743,12 @@ void exit_mmap(struct mm_struct *mm)
+ /* mm's last user has gone, and its about to be pulled down */
+ mmu_notifier_release(mm);
+
++ /*
++ * Taking write lock on mmap_sem does not harm others,
++ * but it's crucial for uksm to avoid races.
++ */
++ down_write(&mm->mmap_sem);
++
+ if (mm->locked_vm) {
+ vma = mm->mmap;
+ while (vma) {
+@@ -2754,6 +2785,11 @@ void exit_mmap(struct mm_struct *mm)
+ }
+ vm_unacct_memory(nr_accounted);
+
++ mm->mmap = NULL;
++ mm->mm_rb = RB_ROOT;
++ mm->mmap_cache = NULL;
++ up_write(&mm->mmap_sem);
++
+ WARN_ON(mm->nr_ptes > (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT);
+ }
+
+@@ -2864,6 +2900,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
+ new_vma->vm_ops->open(new_vma);
+ vma_link(mm, new_vma, prev, rb_link, rb_parent);
+ *need_rmap_locks = false;
++ uksm_vma_add_new(new_vma);
+ }
+ }
+ return new_vma;
+@@ -2965,10 +3002,10 @@ int install_special_mapping(struct mm_struct *mm,
+ ret = insert_vm_struct(mm, vma);
+ if (ret)
+ goto out;
+-
+ mm->total_vm += len >> PAGE_SHIFT;
+
+ perf_event_mmap(vma);
++ uksm_vma_add_new(vma);
+
+ return 0;
+
+diff --git a/mm/rmap.c b/mm/rmap.c
+index 6280da8..645cf22 100644
+--- a/mm/rmap.c
++++ b/mm/rmap.c
+@@ -973,9 +973,9 @@ void page_move_anon_rmap(struct page *page,
+
+ /**
+ * __page_set_anon_rmap - set up new anonymous rmap
+- * @page: Page to add to rmap
++ * @page: Page to add to rmap
+ * @vma: VM area to add page to.
+- * @address: User virtual address of the mapping
++ * @address: User virtual address of the mapping
+ * @exclusive: the page is exclusively owned by the current process
+ */
+ static void __page_set_anon_rmap(struct page *page,
+diff --git a/mm/uksm.c b/mm/uksm.c
+new file mode 100644
+index 0000000..794867a
+--- /dev/null
++++ b/mm/uksm.c
+@@ -0,0 +1,5640 @@
++/*
++ * Ultra KSM. Copyright (C) 2011-2012 Nai Xia
++ *
++ * This is an improvement upon KSM. Some basic data structures and routines
++ * are borrowed from ksm.c .
++ *
++ * Its new features:
++ * 1. Full system scan:
++ * It automatically scans all user processes' anonymous VMAs. Kernel-user
++ * interaction to submit a memory area to KSM is no longer needed.
++ *
++ * 2. Rich area detection:
++ * It automatically detects rich areas containing abundant duplicated
++ * pages based. Rich areas are given a full scan speed. Poor areas are
++ * sampled at a reasonable speed with very low CPU consumption.
++ *
++ * 3. Ultra Per-page scan speed improvement:
++ * A new hash algorithm is proposed. As a result, on a machine with
++ * Core(TM)2 Quad Q9300 CPU in 32-bit mode and 800MHZ DDR2 main memory, it
++ * can scan memory areas that does not contain duplicated pages at speed of
++ * 627MB/sec ~ 2445MB/sec and can merge duplicated areas at speed of
++ * 477MB/sec ~ 923MB/sec.
++ *
++ * 4. Thrashing area avoidance:
++ * Thrashing area(an VMA that has frequent Ksm page break-out) can be
++ * filtered out. My benchmark shows it's more efficient than KSM's per-page
++ * hash value based volatile page detection.
++ *
++ *
++ * 5. Misc changes upon KSM:
++ * * It has a fully x86-opitmized memcmp dedicated for 4-byte-aligned page
++ * comparison. It's much faster than default C version on x86.
++ * * rmap_item now has an struct *page member to loosely cache a
++ * address-->page mapping, which reduces too much time-costly
++ * follow_page().
++ * * The VMA creation/exit procedures are hooked to let the Ultra KSM know.
++ * * try_to_merge_two_pages() now can revert a pte if it fails. No break_
++ * ksm is needed for this case.
++ *
++ * 6. Full Zero Page consideration(contributed by Figo Zhang)
++ * Now uksmd consider full zero pages as special pages and merge them to an
++ * special unswappable uksm zero page.
++ */
++
++#include <linux/errno.h>
++#include <linux/mm.h>
++#include <linux/fs.h>
++#include <linux/mman.h>
++#include <linux/sched.h>
++#include <linux/rwsem.h>
++#include <linux/pagemap.h>
++#include <linux/rmap.h>
++#include <linux/spinlock.h>
++#include <linux/jhash.h>
++#include <linux/delay.h>
++#include <linux/kthread.h>
++#include <linux/wait.h>
++#include <linux/slab.h>
++#include <linux/rbtree.h>
++#include <linux/memory.h>
++#include <linux/mmu_notifier.h>
++#include <linux/swap.h>
++#include <linux/ksm.h>
++#include <linux/crypto.h>
++#include <linux/scatterlist.h>
++#include <crypto/hash.h>
++#include <linux/random.h>
++#include <linux/math64.h>
++#include <linux/gcd.h>
++#include <linux/freezer.h>
++#include <linux/sradix-tree.h>
++
++#include <asm/tlbflush.h>
++#include "internal.h"
++
++#ifdef CONFIG_X86
++#undef memcmp
++
++#ifdef CONFIG_X86_32
++#define memcmp memcmpx86_32
++/*
++ * Compare 4-byte-aligned address s1 and s2, with length n
++ */
++int memcmpx86_32(void *s1, void *s2, size_t n)
++{
++ size_t num = n / 4;
++ register int res;
++
++ __asm__ __volatile__
++ (
++ "testl %3,%3\n\t"
++ "repe; cmpsd\n\t"
++ "je 1f\n\t"
++ "sbbl %0,%0\n\t"
++ "orl $1,%0\n"
++ "1:"
++ : "=&a" (res), "+&S" (s1), "+&D" (s2), "+&c" (num)
++ : "0" (0)
++ : "cc");
++
++ return res;
++}
++
++/*
++ * Check the page is all zero ?
++ */
++static int is_full_zero(const void *s1, size_t len)
++{
++ unsigned char same;
++
++ len /= 4;
++
++ __asm__ __volatile__
++ ("repe; scasl;"
++ "sete %0"
++ : "=qm" (same), "+D" (s1), "+c" (len)
++ : "a" (0)
++ : "cc");
++
++ return same;
++}
++
++
++#elif defined(CONFIG_X86_64)
++#define memcmp memcmpx86_64
++/*
++ * Compare 8-byte-aligned address s1 and s2, with length n
++ */
++int memcmpx86_64(void *s1, void *s2, size_t n)
++{
++ size_t num = n / 8;
++ register int res;
++
++ __asm__ __volatile__
++ (
++ "testq %q3,%q3\n\t"
++ "repe; cmpsq\n\t"
++ "je 1f\n\t"
++ "sbbq %q0,%q0\n\t"
++ "orq $1,%q0\n"
++ "1:"
++ : "=&a" (res), "+&S" (s1), "+&D" (s2), "+&c" (num)
++ : "0" (0)
++ : "cc");
++
++ return res;
++}
++
++static int is_full_zero(const void *s1, size_t len)
++{
++ unsigned char same;
++
++ len /= 8;
++
++ __asm__ __volatile__
++ ("repe; scasq;"
++ "sete %0"
++ : "=qm" (same), "+D" (s1), "+c" (len)
++ : "a" (0)
++ : "cc");
++
++ return same;
++}
++
++#endif
++#else
++static int is_full_zero(const void *s1, size_t len)
++{
++ unsigned long *src = s1;
++ int i;
++
++ len /= sizeof(*src);
++
++ for (i = 0; i < len; i++) {
++ if (src[i])
++ return 0;
++ }
++
++ return 1;
++}
++#endif
++
++#define U64_MAX (~((u64)0))
++#define UKSM_RUNG_ROUND_FINISHED (1 << 0)
++#define TIME_RATIO_SCALE 10000
++
++#define SLOT_TREE_NODE_SHIFT 8
++#define SLOT_TREE_NODE_STORE_SIZE (1UL << SLOT_TREE_NODE_SHIFT)
++struct slot_tree_node {
++ unsigned long size;
++ struct sradix_tree_node snode;
++ void *stores[SLOT_TREE_NODE_STORE_SIZE];
++};
++
++static struct kmem_cache *slot_tree_node_cachep;
++
++static struct sradix_tree_node *slot_tree_node_alloc(void)
++{
++ struct slot_tree_node *p;
++ p = kmem_cache_zalloc(slot_tree_node_cachep, GFP_KERNEL);
++ if (!p)
++ return NULL;
++
++ return &p->snode;
++}
++
++static void slot_tree_node_free(struct sradix_tree_node *node)
++{
++ struct slot_tree_node *p;
++
++ p = container_of(node, struct slot_tree_node, snode);
++ kmem_cache_free(slot_tree_node_cachep, p);
++}
++
++static void slot_tree_node_extend(struct sradix_tree_node *parent,
++ struct sradix_tree_node *child)
++{
++ struct slot_tree_node *p, *c;
++
++ p = container_of(parent, struct slot_tree_node, snode);
++ c = container_of(child, struct slot_tree_node, snode);
++
++ p->size += c->size;
++}
++
++void slot_tree_node_assign(struct sradix_tree_node *node,
++ unsigned index, void *item)
++{
++ struct vma_slot *slot = item;
++ struct slot_tree_node *cur;
++
++ slot->snode = node;
++ slot->sindex = index;
++
++ while (node) {
++ cur = container_of(node, struct slot_tree_node, snode);
++ cur->size += slot->pages;
++ node = node->parent;
++ }
++}
++
++void slot_tree_node_rm(struct sradix_tree_node *node, unsigned offset)
++{
++ struct vma_slot *slot;
++ struct slot_tree_node *cur;
++ unsigned long pages;
++
++ if (node->height == 1) {
++ slot = node->stores[offset];
++ pages = slot->pages;
++ } else {
++ cur = container_of(node->stores[offset],
++ struct slot_tree_node, snode);
++ pages = cur->size;
++ }
++
++ while (node) {
++ cur = container_of(node, struct slot_tree_node, snode);
++ cur->size -= pages;
++ node = node->parent;
++ }
++}
++
++unsigned long slot_iter_index;
++int slot_iter(void *item, unsigned long height)
++{
++ struct slot_tree_node *node;
++ struct vma_slot *slot;
++
++ if (height == 1) {
++ slot = item;
++ if (slot_iter_index < slot->pages) {
++ /*in this one*/
++ return 1;
++ } else {
++ slot_iter_index -= slot->pages;
++ return 0;
++ }
++
++ } else {
++ node = container_of(item, struct slot_tree_node, snode);
++ if (slot_iter_index < node->size) {
++ /*in this one*/
++ return 1;
++ } else {
++ slot_iter_index -= node->size;
++ return 0;
++ }
++ }
++}
++
++
++static inline void slot_tree_init_root(struct sradix_tree_root *root)
++{
++ init_sradix_tree_root(root, SLOT_TREE_NODE_SHIFT);
++ root->alloc = slot_tree_node_alloc;
++ root->free = slot_tree_node_free;
++ root->extend = slot_tree_node_extend;
++ root->assign = slot_tree_node_assign;
++ root->rm = slot_tree_node_rm;
++}
++
++void slot_tree_init(void)
++{
++ slot_tree_node_cachep = kmem_cache_create("slot_tree_node",
++ sizeof(struct slot_tree_node), 0,
++ SLAB_PANIC | SLAB_RECLAIM_ACCOUNT,
++ NULL);
++}
++
++
++/* Each rung of this ladder is a list of VMAs having a same scan ratio */
++struct scan_rung {
++ //struct list_head scanned_list;
++ struct sradix_tree_root vma_root;
++ struct sradix_tree_root vma_root2;
++
++ struct vma_slot *current_scan;
++ unsigned long current_offset;
++
++ /*
++ * The initial value for current_offset, it should loop over
++ * [0~ step - 1] to let all slot have its chance to be scanned.
++ */
++ unsigned long offset_init;
++ unsigned long step; /* dynamic step for current_offset */
++ unsigned int flags;
++ unsigned long pages_to_scan;
++ //unsigned long fully_scanned_slots;
++ /*
++ * a little bit tricky - if cpu_time_ratio > 0, then the value is the
++ * the cpu time ratio it can spend in rung_i for every scan
++ * period. if < 0, then it is the cpu time ratio relative to the
++ * max cpu percentage user specified. Both in unit of
++ * 1/TIME_RATIO_SCALE
++ */
++ int cpu_ratio;
++
++ /*
++ * How long it will take for all slots in this rung to be fully
++ * scanned? If it's zero, we don't care about the cover time:
++ * it's fully scanned.
++ */
++ unsigned int cover_msecs;
++ //unsigned long vma_num;
++ //unsigned long pages; /* Sum of all slot's pages in rung */
++};
++
++/**
++ * node of either the stable or unstale rbtree
++ *
++ */
++struct tree_node {
++ struct rb_node node; /* link in the main (un)stable rbtree */
++ struct rb_root sub_root; /* rb_root for sublevel collision rbtree */
++ u32 hash;
++ unsigned long count; /* TODO: merged with sub_root */
++ struct list_head all_list; /* all tree nodes in stable/unstable tree */
++};
++
++/**
++ * struct stable_node - node of the stable rbtree
++ * @node: rb node of this ksm page in the stable tree
++ * @hlist: hlist head of rmap_items using this ksm page
++ * @kpfn: page frame number of this ksm page
++ */
++struct stable_node {
++ struct rb_node node; /* link in sub-rbtree */
++ struct tree_node *tree_node; /* it's tree node root in stable tree, NULL if it's in hell list */
++ struct hlist_head hlist;
++ unsigned long kpfn;
++ u32 hash_max; /* if ==0 then it's not been calculated yet */
++ struct list_head all_list; /* in a list for all stable nodes */
++};
++
++/**
++ * struct node_vma - group rmap_items linked in a same stable
++ * node together.
++ */
++struct node_vma {
++ union {
++ struct vma_slot *slot;
++ unsigned long key; /* slot is used as key sorted on hlist */
++ };
++ struct hlist_node hlist;
++ struct hlist_head rmap_hlist;
++ struct stable_node *head;
++};
++
++/**
++ * struct rmap_item - reverse mapping item for virtual addresses
++ * @rmap_list: next rmap_item in mm_slot's singly-linked rmap_list
++ * @anon_vma: pointer to anon_vma for this mm,address, when in stable tree
++ * @mm: the memory structure this rmap_item is pointing into
++ * @address: the virtual address this rmap_item tracks (+ flags in low bits)
++ * @node: rb node of this rmap_item in the unstable tree
++ * @head: pointer to stable_node heading this list in the stable tree
++ * @hlist: link into hlist of rmap_items hanging off that stable_node
++ */
++struct rmap_item {
++ struct vma_slot *slot;
++ struct page *page;
++ unsigned long address; /* + low bits used for flags below */
++ unsigned long hash_round;
++ unsigned long entry_index;
++ union {
++ struct {/* when in unstable tree */
++ struct rb_node node;
++ struct tree_node *tree_node;
++ u32 hash_max;
++ };
++ struct { /* when in stable tree */
++ struct node_vma *head;
++ struct hlist_node hlist;
++ struct anon_vma *anon_vma;
++ };
++ };
++} __attribute__((aligned(4)));
++
++struct rmap_list_entry {
++ union {
++ struct rmap_item *item;
++ unsigned long addr;
++ };
++ /* lowest bit is used for is_addr tag */
++} __attribute__((aligned(4))); /* 4 aligned to fit in to pages*/
++
++
++/* Basic data structure definition ends */
++
++
++/*
++ * Flags for rmap_item to judge if it's listed in the stable/unstable tree.
++ * The flags use the low bits of rmap_item.address
++ */
++#define UNSTABLE_FLAG 0x1
++#define STABLE_FLAG 0x2
++#define get_rmap_addr(x) ((x)->address & PAGE_MASK)
++
++/*
++ * rmap_list_entry helpers
++ */
++#define IS_ADDR_FLAG 1
++#define is_addr(ptr) ((unsigned long)(ptr) & IS_ADDR_FLAG)
++#define set_is_addr(ptr) ((ptr) |= IS_ADDR_FLAG)
++#define get_clean_addr(ptr) (((ptr) & ~(__typeof__(ptr))IS_ADDR_FLAG))
++
++
++/*
++ * High speed caches for frequently allocated and freed structs
++ */
++static struct kmem_cache *rmap_item_cache;
++static struct kmem_cache *stable_node_cache;
++static struct kmem_cache *node_vma_cache;
++static struct kmem_cache *vma_slot_cache;
++static struct kmem_cache *tree_node_cache;
++#define UKSM_KMEM_CACHE(__struct, __flags) kmem_cache_create("uksm_"#__struct,\
++ sizeof(struct __struct), __alignof__(struct __struct),\
++ (__flags), NULL)
++
++/* Array of all scan_rung, uksm_scan_ladder[0] having the minimum scan ratio */
++#define SCAN_LADDER_SIZE 4
++static struct scan_rung uksm_scan_ladder[SCAN_LADDER_SIZE];
++
++/* The evaluation rounds uksmd has finished */
++static unsigned long long uksm_eval_round = 1;
++
++/*
++ * we add 1 to this var when we consider we should rebuild the whole
++ * unstable tree.
++ */
++static unsigned long uksm_hash_round = 1;
++
++/*
++ * How many times the whole memory is scanned.
++ */
++static unsigned long long fully_scanned_round = 1;
++
++/* The total number of virtual pages of all vma slots */
++static u64 uksm_pages_total;
++
++/* The number of pages has been scanned since the start up */
++static u64 uksm_pages_scanned;
++
++static u64 scanned_virtual_pages;
++
++/* The number of pages has been scanned since last encode_benefit call */
++static u64 uksm_pages_scanned_last;
++
++/* If the scanned number is tooo large, we encode it here */
++static u64 pages_scanned_stored;
++
++static unsigned long pages_scanned_base;
++
++/* The number of nodes in the stable tree */
++static unsigned long uksm_pages_shared;
++
++/* The number of page slots additionally sharing those nodes */
++static unsigned long uksm_pages_sharing;
++
++/* The number of nodes in the unstable tree */
++static unsigned long uksm_pages_unshared;
++
++/*
++ * Milliseconds ksmd should sleep between scans,
++ * >= 100ms to be consistent with
++ * scan_time_to_sleep_msec()
++ */
++static unsigned int uksm_sleep_jiffies;
++
++/* The real value for the uksmd next sleep */
++static unsigned int uksm_sleep_real;
++
++/* Saved value for user input uksm_sleep_jiffies when it's enlarged */
++static unsigned int uksm_sleep_saved;
++
++/* Max percentage of cpu utilization ksmd can take to scan in one batch */
++static unsigned int uksm_max_cpu_percentage;
++
++static int uksm_cpu_governor;
++
++static char *uksm_cpu_governor_str[4] = { "full", "medium", "low", "quiet" };
++
++struct uksm_cpu_preset_s {
++ int cpu_ratio[SCAN_LADDER_SIZE];
++ unsigned int cover_msecs[SCAN_LADDER_SIZE];
++ unsigned int max_cpu; /* percentage */
++};
++
++struct uksm_cpu_preset_s uksm_cpu_preset[4] = {
++ { {20, 40, -2500, -10000}, {1000, 500, 200, 50}, 95},
++ { {20, 30, -2500, -10000}, {1000, 500, 400, 100}, 50},
++ { {10, 20, -5000, -10000}, {1500, 1000, 1000, 250}, 20},
++ { {10, 20, 40, 75}, {2000, 1000, 1000, 1000}, 1},
++};
++
++/* The default value for uksm_ema_page_time if it's not initialized */
++#define UKSM_PAGE_TIME_DEFAULT 500
++
++/*cost to scan one page by expotional moving average in nsecs */
++static unsigned long uksm_ema_page_time = UKSM_PAGE_TIME_DEFAULT;
++
++/* The expotional moving average alpha weight, in percentage. */
++#define EMA_ALPHA 20
++
++/*
++ * The threshold used to filter out thrashing areas,
++ * If it == 0, filtering is disabled, otherwise it's the percentage up-bound
++ * of the thrashing ratio of all areas. Any area with a bigger thrashing ratio
++ * will be considered as having a zero duplication ratio.
++ */
++static unsigned int uksm_thrash_threshold = 50;
++
++/* How much dedup ratio is considered to be abundant*/
++static unsigned int uksm_abundant_threshold = 10;
++
++/* All slots having merged pages in this eval round. */
++struct list_head vma_slot_dedup = LIST_HEAD_INIT(vma_slot_dedup);
++
++/* How many times the ksmd has slept since startup */
++static unsigned long long uksm_sleep_times;
++
++#define UKSM_RUN_STOP 0
++#define UKSM_RUN_MERGE 1
++static unsigned int uksm_run = 1;
++
++static DECLARE_WAIT_QUEUE_HEAD(uksm_thread_wait);
++static DEFINE_MUTEX(uksm_thread_mutex);
++
++/*
++ * List vma_slot_new is for newly created vma_slot waiting to be added by
++ * ksmd. If one cannot be added(e.g. due to it's too small), it's moved to
++ * vma_slot_noadd. vma_slot_del is the list for vma_slot whose corresponding
++ * VMA has been removed/freed.
++ */
++struct list_head vma_slot_new = LIST_HEAD_INIT(vma_slot_new);
++struct list_head vma_slot_noadd = LIST_HEAD_INIT(vma_slot_noadd);
++struct list_head vma_slot_del = LIST_HEAD_INIT(vma_slot_del);
++static DEFINE_SPINLOCK(vma_slot_list_lock);
++
++/* The unstable tree heads */
++static struct rb_root root_unstable_tree = RB_ROOT;
++
++/*
++ * All tree_nodes are in a list to be freed at once when unstable tree is
++ * freed after each scan round.
++ */
++static struct list_head unstable_tree_node_list =
++ LIST_HEAD_INIT(unstable_tree_node_list);
++
++/* List contains all stable nodes */
++static struct list_head stable_node_list = LIST_HEAD_INIT(stable_node_list);
++
++/*
++ * When the hash strength is changed, the stable tree must be delta_hashed and
++ * re-structured. We use two set of below structs to speed up the
++ * re-structuring of stable tree.
++ */
++static struct list_head
++stable_tree_node_list[2] = {LIST_HEAD_INIT(stable_tree_node_list[0]),
++ LIST_HEAD_INIT(stable_tree_node_list[1])};
++
++static struct list_head *stable_tree_node_listp = &stable_tree_node_list[0];
++static struct rb_root root_stable_tree[2] = {RB_ROOT, RB_ROOT};
++static struct rb_root *root_stable_treep = &root_stable_tree[0];
++static unsigned long stable_tree_index;
++
++/* The hash strength needed to hash a full page */
++#define HASH_STRENGTH_FULL (PAGE_SIZE / sizeof(u32))
++
++/* The hash strength needed for loop-back hashing */
++#define HASH_STRENGTH_MAX (HASH_STRENGTH_FULL + 10)
++
++/* The random offsets in a page */
++static u32 *random_nums;
++
++/* The hash strength */
++static unsigned long hash_strength = HASH_STRENGTH_FULL >> 4;
++
++/* The delta value each time the hash strength increases or decreases */
++static unsigned long hash_strength_delta;
++#define HASH_STRENGTH_DELTA_MAX 5
++
++/* The time we have saved due to random_sample_hash */
++static u64 rshash_pos;
++
++/* The time we have wasted due to hash collision */
++static u64 rshash_neg;
++
++struct uksm_benefit {
++ u64 pos;
++ u64 neg;
++ u64 scanned;
++ unsigned long base;
++} benefit;
++
++/*
++ * The relative cost of memcmp, compared to 1 time unit of random sample
++ * hash, this value is tested when ksm module is initialized
++ */
++static unsigned long memcmp_cost;
++
++static unsigned long rshash_neg_cont_zero;
++static unsigned long rshash_cont_obscure;
++
++/* The possible states of hash strength adjustment heuristic */
++enum rshash_states {
++ RSHASH_STILL,
++ RSHASH_TRYUP,
++ RSHASH_TRYDOWN,
++ RSHASH_NEW,
++ RSHASH_PRE_STILL,
++};
++
++/* The possible direction we are about to adjust hash strength */
++enum rshash_direct {
++ GO_UP,
++ GO_DOWN,
++ OBSCURE,
++ STILL,
++};
++
++/* random sampling hash state machine */
++static struct {
++ enum rshash_states state;
++ enum rshash_direct pre_direct;
++ u8 below_count;
++ /* Keep a lookup window of size 5, iff above_count/below_count > 3
++ * in this window we stop trying.
++ */
++ u8 lookup_window_index;
++ u64 stable_benefit;
++ unsigned long turn_point_down;
++ unsigned long turn_benefit_down;
++ unsigned long turn_point_up;
++ unsigned long turn_benefit_up;
++ unsigned long stable_point;
++} rshash_state;
++
++/*zero page hash table, hash_strength [0 ~ HASH_STRENGTH_MAX]*/
++static u32 *zero_hash_table;
++
++static inline struct node_vma *alloc_node_vma(void)
++{
++ struct node_vma *node_vma;
++ node_vma = kmem_cache_zalloc(node_vma_cache, GFP_KERNEL);
++ if (node_vma) {
++ INIT_HLIST_HEAD(&node_vma->rmap_hlist);
++ INIT_HLIST_NODE(&node_vma->hlist);
++ }
++ return node_vma;
++}
++
++static inline void free_node_vma(struct node_vma *node_vma)
++{
++ kmem_cache_free(node_vma_cache, node_vma);
++}
++
++
++static inline struct vma_slot *alloc_vma_slot(void)
++{
++ struct vma_slot *slot;
++
++ /*
++ * In case ksm is not initialized by now.
++ * Oops, we need to consider the call site of uksm_init() in the future.
++ */
++ if (!vma_slot_cache)
++ return NULL;
++
++ slot = kmem_cache_zalloc(vma_slot_cache, GFP_KERNEL);
++ if (slot) {
++ INIT_LIST_HEAD(&slot->slot_list);
++ INIT_LIST_HEAD(&slot->dedup_list);
++ slot->flags |= UKSM_SLOT_NEED_RERAND;
++ }
++ return slot;
++}
++
++static inline void free_vma_slot(struct vma_slot *vma_slot)
++{
++ kmem_cache_free(vma_slot_cache, vma_slot);
++}
++
++
++
++static inline struct rmap_item *alloc_rmap_item(void)
++{
++ struct rmap_item *rmap_item;
++
++ rmap_item = kmem_cache_zalloc(rmap_item_cache, GFP_KERNEL);
++ if (rmap_item) {
++ /* bug on lowest bit is not clear for flag use */
++ BUG_ON(is_addr(rmap_item));
++ }
++ return rmap_item;
++}
++
++static inline void free_rmap_item(struct rmap_item *rmap_item)
++{
++ rmap_item->slot = NULL; /* debug safety */
++ kmem_cache_free(rmap_item_cache, rmap_item);
++}
++
++static inline struct stable_node *alloc_stable_node(void)
++{
++ struct stable_node *node;
++ node = kmem_cache_alloc(stable_node_cache, GFP_KERNEL | GFP_ATOMIC);
++ if (!node)
++ return NULL;
++
++ INIT_HLIST_HEAD(&node->hlist);
++ list_add(&node->all_list, &stable_node_list);
++ return node;
++}
++
++static inline void free_stable_node(struct stable_node *stable_node)
++{
++ list_del(&stable_node->all_list);
++ kmem_cache_free(stable_node_cache, stable_node);
++}
++
++static inline struct tree_node *alloc_tree_node(struct list_head *list)
++{
++ struct tree_node *node;
++ node = kmem_cache_zalloc(tree_node_cache, GFP_KERNEL | GFP_ATOMIC);
++ if (!node)
++ return NULL;
++
++ list_add(&node->all_list, list);
++ return node;
++}
++
++static inline void free_tree_node(struct tree_node *node)
++{
++ list_del(&node->all_list);
++ kmem_cache_free(tree_node_cache, node);
++}
++
++static void uksm_drop_anon_vma(struct rmap_item *rmap_item)
++{
++ struct anon_vma *anon_vma = rmap_item->anon_vma;
++
++ put_anon_vma(anon_vma);
++}
++
++
++/**
++ * Remove a stable node from stable_tree, may unlink from its tree_node and
++ * may remove its parent tree_node if no other stable node is pending.
++ *
++ * @stable_node The node need to be removed
++ * @unlink_rb Will this node be unlinked from the rbtree?
++ * @remove_tree_ node Will its tree_node be removed if empty?
++ */
++static void remove_node_from_stable_tree(struct stable_node *stable_node,
++ int unlink_rb, int remove_tree_node)
++{
++ struct node_vma *node_vma;
++ struct rmap_item *rmap_item;
++ struct hlist_node *n;
++
++ if (!hlist_empty(&stable_node->hlist)) {
++ hlist_for_each_entry_safe(node_vma, n,
++ &stable_node->hlist, hlist) {
++ hlist_for_each_entry(rmap_item, &node_vma->rmap_hlist, hlist) {
++ uksm_pages_sharing--;
++
++ uksm_drop_anon_vma(rmap_item);
++ rmap_item->address &= PAGE_MASK;
++ }
++ free_node_vma(node_vma);
++ cond_resched();
++ }
++
++ /* the last one is counted as shared */
++ uksm_pages_shared--;
++ uksm_pages_sharing++;
++ }
++
++ if (stable_node->tree_node && unlink_rb) {
++ rb_erase(&stable_node->node,
++ &stable_node->tree_node->sub_root);
++
++ if (RB_EMPTY_ROOT(&stable_node->tree_node->sub_root) &&
++ remove_tree_node) {
++ rb_erase(&stable_node->tree_node->node,
++ root_stable_treep);
++ free_tree_node(stable_node->tree_node);
++ } else {
++ stable_node->tree_node->count--;
++ }
++ }
++
++ free_stable_node(stable_node);
++}
++
++
++/*
++ * get_uksm_page: checks if the page indicated by the stable node
++ * is still its ksm page, despite having held no reference to it.
++ * In which case we can trust the content of the page, and it
++ * returns the gotten page; but if the page has now been zapped,
++ * remove the stale node from the stable tree and return NULL.
++ *
++ * You would expect the stable_node to hold a reference to the ksm page.
++ * But if it increments the page's count, swapping out has to wait for
++ * ksmd to come around again before it can free the page, which may take
++ * seconds or even minutes: much too unresponsive. So instead we use a
++ * "keyhole reference": access to the ksm page from the stable node peeps
++ * out through its keyhole to see if that page still holds the right key,
++ * pointing back to this stable node. This relies on freeing a PageAnon
++ * page to reset its page->mapping to NULL, and relies on no other use of
++ * a page to put something that might look like our key in page->mapping.
++ *
++ * include/linux/pagemap.h page_cache_get_speculative() is a good reference,
++ * but this is different - made simpler by uksm_thread_mutex being held, but
++ * interesting for assuming that no other use of the struct page could ever
++ * put our expected_mapping into page->mapping (or a field of the union which
++ * coincides with page->mapping). The RCU calls are not for KSM at all, but
++ * to keep the page_count protocol described with page_cache_get_speculative.
++ *
++ * Note: it is possible that get_uksm_page() will return NULL one moment,
++ * then page the next, if the page is in between page_freeze_refs() and
++ * page_unfreeze_refs(): this shouldn't be a problem anywhere, the page
++ * is on its way to being freed; but it is an anomaly to bear in mind.
++ *
++ * @unlink_rb: if the removal of this node will firstly unlink from
++ * its rbtree. stable_node_reinsert will prevent this when restructuring the
++ * node from its old tree.
++ *
++ * @remove_tree_node: if this is the last one of its tree_node, will the
++ * tree_node be freed ? If we are inserting stable node, this tree_node may
++ * be reused, so don't free it.
++ */
++static struct page *get_uksm_page(struct stable_node *stable_node,
++ int unlink_rb, int remove_tree_node)
++{
++ struct page *page;
++ void *expected_mapping;
++
++ page = pfn_to_page(stable_node->kpfn);
++ expected_mapping = (void *)stable_node +
++ (PAGE_MAPPING_ANON | PAGE_MAPPING_KSM);
++ rcu_read_lock();
++ if (page->mapping != expected_mapping)
++ goto stale;
++ if (!get_page_unless_zero(page))
++ goto stale;
++ if (page->mapping != expected_mapping) {
++ put_page(page);
++ goto stale;
++ }
++ rcu_read_unlock();
++ return page;
++stale:
++ rcu_read_unlock();
++ remove_node_from_stable_tree(stable_node, unlink_rb, remove_tree_node);
++
++ return NULL;
++}
++
++/*
++ * Removing rmap_item from stable or unstable tree.
++ * This function will clean the information from the stable/unstable tree.
++ */
++static inline void remove_rmap_item_from_tree(struct rmap_item *rmap_item)
++{
++ if (rmap_item->address & STABLE_FLAG) {
++ struct stable_node *stable_node;
++ struct node_vma *node_vma;
++ struct page *page;
++
++ node_vma = rmap_item->head;
++ stable_node = node_vma->head;
++ page = get_uksm_page(stable_node, 1, 1);
++ if (!page)
++ goto out;
++
++ /*
++ * page lock is needed because it's racing with
++ * try_to_unmap_ksm(), etc.
++ */
++ lock_page(page);
++ hlist_del(&rmap_item->hlist);
++
++ if (hlist_empty(&node_vma->rmap_hlist)) {
++ hlist_del(&node_vma->hlist);
++ free_node_vma(node_vma);
++ }
++ unlock_page(page);
++
++ put_page(page);
++ if (hlist_empty(&stable_node->hlist)) {
++ /* do NOT call remove_node_from_stable_tree() here,
++ * it's possible for a forked rmap_item not in
++ * stable tree while the in-tree rmap_items were
++ * deleted.
++ */
++ uksm_pages_shared--;
++ } else
++ uksm_pages_sharing--;
++
++
++ uksm_drop_anon_vma(rmap_item);
++ } else if (rmap_item->address & UNSTABLE_FLAG) {
++ if (rmap_item->hash_round == uksm_hash_round) {
++
++ rb_erase(&rmap_item->node,
++ &rmap_item->tree_node->sub_root);
++ if (RB_EMPTY_ROOT(&rmap_item->tree_node->sub_root)) {
++ rb_erase(&rmap_item->tree_node->node,
++ &root_unstable_tree);
++
++ free_tree_node(rmap_item->tree_node);
++ } else
++ rmap_item->tree_node->count--;
++ }
++ uksm_pages_unshared--;
++ }
++
++ rmap_item->address &= PAGE_MASK;
++ rmap_item->hash_max = 0;
++
++out:
++ cond_resched(); /* we're called from many long loops */
++}
++
++static inline int slot_in_uksm(struct vma_slot *slot)
++{
++ return list_empty(&slot->slot_list);
++}
++
++/*
++ * Test if the mm is exiting
++ */
++static inline bool uksm_test_exit(struct mm_struct *mm)
++{
++ return atomic_read(&mm->mm_users) == 0;
++}
++
++/**
++ * Need to do two things:
++ * 1. check if slot was moved to del list
++ * 2. make sure the mmap_sem is manipulated under valid vma.
++ *
++ * My concern here is that in some cases, this may make
++ * vma_slot_list_lock() waiters to serialized further by some
++ * sem->wait_lock, can this really be expensive?
++ *
++ *
++ * @return
++ * 0: if successfully locked mmap_sem
++ * -ENOENT: this slot was moved to del list
++ * -EBUSY: vma lock failed
++ */
++static int try_down_read_slot_mmap_sem(struct vma_slot *slot)
++{
++ struct vm_area_struct *vma;
++ struct mm_struct *mm;
++ struct rw_semaphore *sem;
++
++ spin_lock(&vma_slot_list_lock);
++
++ /* the slot_list was removed and inited from new list, when it enters
++ * uksm_list. If now it's not empty, then it must be moved to del list
++ */
++ if (!slot_in_uksm(slot)) {
++ spin_unlock(&vma_slot_list_lock);
++ return -ENOENT;
++ }
++
++ BUG_ON(slot->pages != vma_pages(slot->vma));
++ /* Ok, vma still valid */
++ vma = slot->vma;
++ mm = vma->vm_mm;
++ sem = &mm->mmap_sem;
++
++ if (uksm_test_exit(mm)) {
++ spin_unlock(&vma_slot_list_lock);
++ return -ENOENT;
++ }
++
++ if (down_read_trylock(sem)) {
++ spin_unlock(&vma_slot_list_lock);
++ return 0;
++ }
++
++ spin_unlock(&vma_slot_list_lock);
++ return -EBUSY;
++}
++
++static inline unsigned long
++vma_page_address(struct page *page, struct vm_area_struct *vma)
++{
++ pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
++ unsigned long address;
++
++ address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
++ if (unlikely(address < vma->vm_start || address >= vma->vm_end)) {
++ /* page should be within @vma mapping range */
++ return -EFAULT;
++ }
++ return address;
++}
++
++
++/* return 0 on success with the item's mmap_sem locked */
++static inline int get_mergeable_page_lock_mmap(struct rmap_item *item)
++{
++ struct mm_struct *mm;
++ struct vma_slot *slot = item->slot;
++ int err = -EINVAL;
++
++ struct page *page;
++
++ /*
++ * try_down_read_slot_mmap_sem() returns non-zero if the slot
++ * has been removed by uksm_remove_vma().
++ */
++ if (try_down_read_slot_mmap_sem(slot))
++ return -EBUSY;
++
++ mm = slot->vma->vm_mm;
++
++ if (uksm_test_exit(mm))
++ goto failout_up;
++
++ page = item->page;
++ rcu_read_lock();
++ if (!get_page_unless_zero(page)) {
++ rcu_read_unlock();
++ goto failout_up;
++ }
++
++ /* No need to consider huge page here. */
++ if (item->slot->vma->anon_vma != page_anon_vma(page) ||
++ vma_page_address(page, item->slot->vma) != get_rmap_addr(item)) {
++ /*
++ * TODO:
++ * should we release this item becase of its stale page
++ * mapping?
++ */
++ put_page(page);
++ rcu_read_unlock();
++ goto failout_up;
++ }
++ rcu_read_unlock();
++ return 0;
++
++failout_up:
++ up_read(&mm->mmap_sem);
++ return err;
++}
++
++/*
++ * What kind of VMA is considered ?
++ */
++static inline int vma_can_enter(struct vm_area_struct *vma)
++{
++ return uksm_flags_can_scan(vma->vm_flags);
++}
++
++/*
++ * Called whenever a fresh new vma is created A new vma_slot.
++ * is created and inserted into a global list Must be called.
++ * after vma is inserted to its mm .
++ */
++void uksm_vma_add_new(struct vm_area_struct *vma)
++{
++ struct vma_slot *slot;
++
++ if (!vma_can_enter(vma)) {
++ vma->uksm_vma_slot = NULL;
++ return;
++ }
++
++ slot = alloc_vma_slot();
++ if (!slot) {
++ vma->uksm_vma_slot = NULL;
++ return;
++ }
++
++ vma->uksm_vma_slot = slot;
++ vma->vm_flags |= VM_MERGEABLE;
++ slot->vma = vma;
++ slot->mm = vma->vm_mm;
++ slot->ctime_j = jiffies;
++ slot->pages = vma_pages(vma);
++ spin_lock(&vma_slot_list_lock);
++ list_add_tail(&slot->slot_list, &vma_slot_new);
++ spin_unlock(&vma_slot_list_lock);
++}
++
++/*
++ * Called after vma is unlinked from its mm
++ */
++void uksm_remove_vma(struct vm_area_struct *vma)
++{
++ struct vma_slot *slot;
++
++ if (!vma->uksm_vma_slot)
++ return;
++
++ slot = vma->uksm_vma_slot;
++ spin_lock(&vma_slot_list_lock);
++ if (slot_in_uksm(slot)) {
++ /**
++ * This slot has been added by ksmd, so move to the del list
++ * waiting ksmd to free it.
++ */
++ list_add_tail(&slot->slot_list, &vma_slot_del);
++ } else {
++ /**
++ * It's still on new list. It's ok to free slot directly.
++ */
++ list_del(&slot->slot_list);
++ free_vma_slot(slot);
++ }
++ spin_unlock(&vma_slot_list_lock);
++ vma->uksm_vma_slot = NULL;
++}
++
++/* 32/3 < they < 32/2 */
++#define shiftl 8
++#define shiftr 12
++
++#define HASH_FROM_TO(from, to) \
++for (index = from; index < to; index++) { \
++ pos = random_nums[index]; \
++ hash += key[pos]; \
++ hash += (hash << shiftl); \
++ hash ^= (hash >> shiftr); \
++}
++
++
++#define HASH_FROM_DOWN_TO(from, to) \
++for (index = from - 1; index >= to; index--) { \
++ hash ^= (hash >> shiftr); \
++ hash ^= (hash >> (shiftr*2)); \
++ hash -= (hash << shiftl); \
++ hash += (hash << (shiftl*2)); \
++ pos = random_nums[index]; \
++ hash -= key[pos]; \
++}
++
++/*
++ * The main random sample hash function.
++ */
++static u32 random_sample_hash(void *addr, u32 hash_strength)
++{
++ u32 hash = 0xdeadbeef;
++ int index, pos, loop = hash_strength;
++ u32 *key = (u32 *)addr;
++
++ if (loop > HASH_STRENGTH_FULL)
++ loop = HASH_STRENGTH_FULL;
++
++ HASH_FROM_TO(0, loop);
++
++ if (hash_strength > HASH_STRENGTH_FULL) {
++ loop = hash_strength - HASH_STRENGTH_FULL;
++ HASH_FROM_TO(0, loop);
++ }
++
++ return hash;
++}
++
++
++/**
++ * It's used when hash strength is adjusted
++ *
++ * @addr The page's virtual address
++ * @from The original hash strength
++ * @to The hash strength changed to
++ * @hash The hash value generated with "from" hash value
++ *
++ * return the hash value
++ */
++static u32 delta_hash(void *addr, int from, int to, u32 hash)
++{
++ u32 *key = (u32 *)addr;
++ int index, pos; /* make sure they are int type */
++
++ if (to > from) {
++ if (from >= HASH_STRENGTH_FULL) {
++ from -= HASH_STRENGTH_FULL;
++ to -= HASH_STRENGTH_FULL;
++ HASH_FROM_TO(from, to);
++ } else if (to <= HASH_STRENGTH_FULL) {
++ HASH_FROM_TO(from, to);
++ } else {
++ HASH_FROM_TO(from, HASH_STRENGTH_FULL);
++ HASH_FROM_TO(0, to - HASH_STRENGTH_FULL);
++ }
++ } else {
++ if (from <= HASH_STRENGTH_FULL) {
++ HASH_FROM_DOWN_TO(from, to);
++ } else if (to >= HASH_STRENGTH_FULL) {
++ from -= HASH_STRENGTH_FULL;
++ to -= HASH_STRENGTH_FULL;
++ HASH_FROM_DOWN_TO(from, to);
++ } else {
++ HASH_FROM_DOWN_TO(from - HASH_STRENGTH_FULL, 0);
++ HASH_FROM_DOWN_TO(HASH_STRENGTH_FULL, to);
++ }
++ }
++
++ return hash;
++}
++
++
++
++
++#define CAN_OVERFLOW_U64(x, delta) (U64_MAX - (x) < (delta))
++
++/**
++ *
++ * Called when: rshash_pos or rshash_neg is about to overflow or a scan round
++ * has finished.
++ *
++ * return 0 if no page has been scanned since last call, 1 otherwise.
++ */
++static inline int encode_benefit(void)
++{
++ u64 scanned_delta, pos_delta, neg_delta;
++ unsigned long base = benefit.base;
++
++ scanned_delta = uksm_pages_scanned - uksm_pages_scanned_last;
++
++ if (!scanned_delta)
++ return 0;
++
++ scanned_delta >>= base;
++ pos_delta = rshash_pos >> base;
++ neg_delta = rshash_neg >> base;
++
++ if (CAN_OVERFLOW_U64(benefit.pos, pos_delta) ||
++ CAN_OVERFLOW_U64(benefit.neg, neg_delta) ||
++ CAN_OVERFLOW_U64(benefit.scanned, scanned_delta)) {
++ benefit.scanned >>= 1;
++ benefit.neg >>= 1;
++ benefit.pos >>= 1;
++ benefit.base++;
++ scanned_delta >>= 1;
++ pos_delta >>= 1;
++ neg_delta >>= 1;
++ }
++
++ benefit.pos += pos_delta;
++ benefit.neg += neg_delta;
++ benefit.scanned += scanned_delta;
++
++ BUG_ON(!benefit.scanned);
++
++ rshash_pos = rshash_neg = 0;
++ uksm_pages_scanned_last = uksm_pages_scanned;
++
++ return 1;
++}
++
++static inline void reset_benefit(void)
++{
++ benefit.pos = 0;
++ benefit.neg = 0;
++ benefit.base = 0;
++ benefit.scanned = 0;
++}
++
++static inline void inc_rshash_pos(unsigned long delta)
++{
++ if (CAN_OVERFLOW_U64(rshash_pos, delta))
++ encode_benefit();
++
++ rshash_pos += delta;
++}
++
++static inline void inc_rshash_neg(unsigned long delta)
++{
++ if (CAN_OVERFLOW_U64(rshash_neg, delta))
++ encode_benefit();
++
++ rshash_neg += delta;
++}
++
++
++static inline u32 page_hash(struct page *page, unsigned long hash_strength,
++ int cost_accounting)
++{
++ u32 val;
++ unsigned long delta;
++
++ void *addr = kmap_atomic(page);
++
++ val = random_sample_hash(addr, hash_strength);
++ kunmap_atomic(addr);
++
++ if (cost_accounting) {
++ if (HASH_STRENGTH_FULL > hash_strength)
++ delta = HASH_STRENGTH_FULL - hash_strength;
++ else
++ delta = 0;
++
++ inc_rshash_pos(delta);
++ }
++
++ return val;
++}
++
++static int memcmp_pages(struct page *page1, struct page *page2,
++ int cost_accounting)
++{
++ char *addr1, *addr2;
++ int ret;
++
++ addr1 = kmap_atomic(page1);
++ addr2 = kmap_atomic(page2);
++ ret = memcmp(addr1, addr2, PAGE_SIZE);
++ kunmap_atomic(addr2);
++ kunmap_atomic(addr1);
++
++ if (cost_accounting)
++ inc_rshash_neg(memcmp_cost);
++
++ return ret;
++}
++
++static inline int pages_identical(struct page *page1, struct page *page2)
++{
++ return !memcmp_pages(page1, page2, 0);
++}
++
++static inline int is_page_full_zero(struct page *page)
++{
++ char *addr;
++ int ret;
++
++ addr = kmap_atomic(page);
++ ret = is_full_zero(addr, PAGE_SIZE);
++ kunmap_atomic(addr);
++
++ return ret;
++}
++
++static int write_protect_page(struct vm_area_struct *vma, struct page *page,
++ pte_t *orig_pte, pte_t *old_pte)
++{
++ struct mm_struct *mm = vma->vm_mm;
++ unsigned long addr;
++ pte_t *ptep;
++ spinlock_t *ptl;
++ int swapped;
++ int err = -EFAULT;
++ unsigned long mmun_start; /* For mmu_notifiers */
++ unsigned long mmun_end; /* For mmu_notifiers */
++
++ addr = page_address_in_vma(page, vma);
++ if (addr == -EFAULT)
++ goto out;
++
++ BUG_ON(PageTransCompound(page));
++
++ mmun_start = addr;
++ mmun_end = addr + PAGE_SIZE;
++ mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
++
++ ptep = page_check_address(page, mm, addr, &ptl, 0);
++ if (!ptep)
++ goto out_mn;
++
++ if (old_pte)
++ *old_pte = *ptep;
++
++ if (pte_write(*ptep) || pte_dirty(*ptep)) {
++ pte_t entry;
++
++ swapped = PageSwapCache(page);
++ flush_cache_page(vma, addr, page_to_pfn(page));
++ /*
++ * Ok this is tricky, when get_user_pages_fast() run it doesnt
++ * take any lock, therefore the check that we are going to make
++ * with the pagecount against the mapcount is racey and
++ * O_DIRECT can happen right after the check.
++ * So we clear the pte and flush the tlb before the check
++ * this assure us that no O_DIRECT can happen after the check
++ * or in the middle of the check.
++ */
++ entry = ptep_clear_flush(vma, addr, ptep);
++ /*
++ * Check that no O_DIRECT or similar I/O is in progress on the
++ * page
++ */
++ if (page_mapcount(page) + 1 + swapped != page_count(page)) {
++ set_pte_at(mm, addr, ptep, entry);
++ goto out_unlock;
++ }
++ if (pte_dirty(entry))
++ set_page_dirty(page);
++ entry = pte_mkclean(pte_wrprotect(entry));
++ set_pte_at_notify(mm, addr, ptep, entry);
++ }
++ *orig_pte = *ptep;
++ err = 0;
++
++out_unlock:
++ pte_unmap_unlock(ptep, ptl);
++out_mn:
++ mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
++out:
++ return err;
++}
++
++#define MERGE_ERR_PGERR 1 /* the page is invalid cannot continue */
++#define MERGE_ERR_COLLI 2 /* there is a collision */
++#define MERGE_ERR_COLLI_MAX 3 /* collision at the max hash strength */
++#define MERGE_ERR_CHANGED 4 /* the page has changed since last hash */
++
++
++/**
++ * replace_page - replace page in vma by new ksm page
++ * @vma: vma that holds the pte pointing to page
++ * @page: the page we are replacing by kpage
++ * @kpage: the ksm page we replace page by
++ * @orig_pte: the original value of the pte
++ *
++ * Returns 0 on success, MERGE_ERR_PGERR on failure.
++ */
++static int replace_page(struct vm_area_struct *vma, struct page *page,
++ struct page *kpage, pte_t orig_pte)
++{
++ struct mm_struct *mm = vma->vm_mm;
++ pgd_t *pgd;
++ pud_t *pud;
++ pmd_t *pmd;
++ pte_t *ptep;
++ spinlock_t *ptl;
++ pte_t entry;
++
++ unsigned long addr;
++ int err = MERGE_ERR_PGERR;
++ unsigned long mmun_start; /* For mmu_notifiers */
++ unsigned long mmun_end; /* For mmu_notifiers */
++
++ addr = page_address_in_vma(page, vma);
++ if (addr == -EFAULT)
++ goto out;
++
++ pgd = pgd_offset(mm, addr);
++ if (!pgd_present(*pgd))
++ goto out;
++
++ pud = pud_offset(pgd, addr);
++ if (!pud_present(*pud))
++ goto out;
++
++ pmd = pmd_offset(pud, addr);
++ BUG_ON(pmd_trans_huge(*pmd));
++ if (!pmd_present(*pmd))
++ goto out;
++
++ mmun_start = addr;
++ mmun_end = addr + PAGE_SIZE;
++ mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
++
++ ptep = pte_offset_map_lock(mm, pmd, addr, &ptl);
++ if (!pte_same(*ptep, orig_pte)) {
++ pte_unmap_unlock(ptep, ptl);
++ goto out_mn;
++ }
++
++ flush_cache_page(vma, addr, pte_pfn(*ptep));
++ ptep_clear_flush(vma, addr, ptep);
++ entry = mk_pte(kpage, vma->vm_page_prot);
++
++ /* special treatment is needed for zero_page */
++ if ((page_to_pfn(kpage) == uksm_zero_pfn) ||
++ (page_to_pfn(kpage) == zero_pfn))
++ entry = pte_mkspecial(entry);
++ else {
++ get_page(kpage);
++ page_add_anon_rmap(kpage, vma, addr);
++ }
++
++ set_pte_at_notify(mm, addr, ptep, entry);
++
++ page_remove_rmap(page);
++ if (!page_mapped(page))
++ try_to_free_swap(page);
++ put_page(page);
++
++ pte_unmap_unlock(ptep, ptl);
++ err = 0;
++out_mn:
++ mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
++out:
++ return err;
++}
++
++
++/**
++ * Fully hash a page with HASH_STRENGTH_MAX return a non-zero hash value. The
++ * zero hash value at HASH_STRENGTH_MAX is used to indicated that its
++ * hash_max member has not been calculated.
++ *
++ * @page The page needs to be hashed
++ * @hash_old The hash value calculated with current hash strength
++ *
++ * return the new hash value calculated at HASH_STRENGTH_MAX
++ */
++static inline u32 page_hash_max(struct page *page, u32 hash_old)
++{
++ u32 hash_max = 0;
++ void *addr;
++
++ addr = kmap_atomic(page);
++ hash_max = delta_hash(addr, hash_strength,
++ HASH_STRENGTH_MAX, hash_old);
++
++ kunmap_atomic(addr);
++
++ if (!hash_max)
++ hash_max = 1;
++
++ inc_rshash_neg(HASH_STRENGTH_MAX - hash_strength);
++ return hash_max;
++}
++
++/*
++ * We compare the hash again, to ensure that it is really a hash collision
++ * instead of being caused by page write.
++ */
++static inline int check_collision(struct rmap_item *rmap_item,
++ u32 hash)
++{
++ int err;
++ struct page *page = rmap_item->page;
++
++ /* if this rmap_item has already been hash_maxed, then the collision
++ * must appears in the second-level rbtree search. In this case we check
++ * if its hash_max value has been changed. Otherwise, the collision
++ * happens in the first-level rbtree search, so we check against it's
++ * current hash value.
++ */
++ if (rmap_item->hash_max) {
++ inc_rshash_neg(memcmp_cost);
++ inc_rshash_neg(HASH_STRENGTH_MAX - hash_strength);
++
++ if (rmap_item->hash_max == page_hash_max(page, hash))
++ err = MERGE_ERR_COLLI;
++ else
++ err = MERGE_ERR_CHANGED;
++ } else {
++ inc_rshash_neg(memcmp_cost + hash_strength);
++
++ if (page_hash(page, hash_strength, 0) == hash)
++ err = MERGE_ERR_COLLI;
++ else
++ err = MERGE_ERR_CHANGED;
++ }
++
++ return err;
++}
++
++static struct page *page_trans_compound_anon(struct page *page)
++{
++ if (PageTransCompound(page)) {
++ struct page *head = compound_trans_head(page);
++ /*
++ * head may actually be splitted and freed from under
++ * us but it's ok here.
++ */
++ if (PageAnon(head))
++ return head;
++ }
++ return NULL;
++}
++
++static int page_trans_compound_anon_split(struct page *page)
++{
++ int ret = 0;
++ struct page *transhuge_head = page_trans_compound_anon(page);
++ if (transhuge_head) {
++ /* Get the reference on the head to split it. */
++ if (get_page_unless_zero(transhuge_head)) {
++ /*
++ * Recheck we got the reference while the head
++ * was still anonymous.
++ */
++ if (PageAnon(transhuge_head))
++ ret = split_huge_page(transhuge_head);
++ else
++ /*
++ * Retry later if split_huge_page run
++ * from under us.
++ */
++ ret = 1;
++ put_page(transhuge_head);
++ } else
++ /* Retry later if split_huge_page run from under us. */
++ ret = 1;
++ }
++ return ret;
++}
++
++/**
++ * Try to merge a rmap_item.page with a kpage in stable node. kpage must
++ * already be a ksm page.
++ *
++ * @return 0 if the pages were merged, -EFAULT otherwise.
++ */
++static int try_to_merge_with_uksm_page(struct rmap_item *rmap_item,
++ struct page *kpage, u32 hash)
++{
++ struct vm_area_struct *vma = rmap_item->slot->vma;
++ struct mm_struct *mm = vma->vm_mm;
++ pte_t orig_pte = __pte(0);
++ int err = MERGE_ERR_PGERR;
++ struct page *page;
++
++ if (uksm_test_exit(mm))
++ goto out;
++
++ page = rmap_item->page;
++
++ if (page == kpage) { /* ksm page forked */
++ err = 0;
++ goto out;
++ }
++
++ if (PageTransCompound(page) && page_trans_compound_anon_split(page))
++ goto out;
++ BUG_ON(PageTransCompound(page));
++
++ if (!PageAnon(page) || !PageKsm(kpage))
++ goto out;
++
++ /*
++ * We need the page lock to read a stable PageSwapCache in
++ * write_protect_page(). We use trylock_page() instead of
++ * lock_page() because we don't want to wait here - we
++ * prefer to continue scanning and merging different pages,
++ * then come back to this page when it is unlocked.
++ */
++ if (!trylock_page(page))
++ goto out;
++ /*
++ * If this anonymous page is mapped only here, its pte may need
++ * to be write-protected. If it's mapped elsewhere, all of its
++ * ptes are necessarily already write-protected. But in either
++ * case, we need to lock and check page_count is not raised.
++ */
++ if (write_protect_page(vma, page, &orig_pte, NULL) == 0) {
++ if (pages_identical(page, kpage))
++ err = replace_page(vma, page, kpage, orig_pte);
++ else
++ err = check_collision(rmap_item, hash);
++ }
++
++ if ((vma->vm_flags & VM_LOCKED) && kpage && !err) {
++ munlock_vma_page(page);
++ if (!PageMlocked(kpage)) {
++ unlock_page(page);
++ lock_page(kpage);
++ mlock_vma_page(kpage);
++ page = kpage; /* for final unlock */
++ }
++ }
++
++ unlock_page(page);
++out:
++ return err;
++}
++
++
++
++/**
++ * If two pages fail to merge in try_to_merge_two_pages, then we have a chance
++ * to restore a page mapping that has been changed in try_to_merge_two_pages.
++ *
++ * @return 0 on success.
++ */
++static int restore_uksm_page_pte(struct vm_area_struct *vma, unsigned long addr,
++ pte_t orig_pte, pte_t wprt_pte)
++{
++ struct mm_struct *mm = vma->vm_mm;
++ pgd_t *pgd;
++ pud_t *pud;
++ pmd_t *pmd;
++ pte_t *ptep;
++ spinlock_t *ptl;
++
++ int err = -EFAULT;
++
++ pgd = pgd_offset(mm, addr);
++ if (!pgd_present(*pgd))
++ goto out;
++
++ pud = pud_offset(pgd, addr);
++ if (!pud_present(*pud))
++ goto out;
++
++ pmd = pmd_offset(pud, addr);
++ if (!pmd_present(*pmd))
++ goto out;
++
++ ptep = pte_offset_map_lock(mm, pmd, addr, &ptl);
++ if (!pte_same(*ptep, wprt_pte)) {
++ /* already copied, let it be */
++ pte_unmap_unlock(ptep, ptl);
++ goto out;
++ }
++
++ /*
++ * Good boy, still here. When we still get the ksm page, it does not
++ * return to the free page pool, there is no way that a pte was changed
++ * to other page and gets back to this page. And remind that ksm page
++ * do not reuse in do_wp_page(). So it's safe to restore the original
++ * pte.
++ */
++ flush_cache_page(vma, addr, pte_pfn(*ptep));
++ ptep_clear_flush(vma, addr, ptep);
++ set_pte_at_notify(mm, addr, ptep, orig_pte);
++
++ pte_unmap_unlock(ptep, ptl);
++ err = 0;
++out:
++ return err;
++}
++
++/**
++ * try_to_merge_two_pages() - take two identical pages and prepare
++ * them to be merged into one page(rmap_item->page)
++ *
++ * @return 0 if we successfully merged two identical pages into
++ * one ksm page. MERGE_ERR_COLLI if it's only a hash collision
++ * search in rbtree. MERGE_ERR_CHANGED if rmap_item has been
++ * changed since it's hashed. MERGE_ERR_PGERR otherwise.
++ *
++ */
++static int try_to_merge_two_pages(struct rmap_item *rmap_item,
++ struct rmap_item *tree_rmap_item,
++ u32 hash)
++{
++ pte_t orig_pte1 = __pte(0), orig_pte2 = __pte(0);
++ pte_t wprt_pte1 = __pte(0), wprt_pte2 = __pte(0);
++ struct vm_area_struct *vma1 = rmap_item->slot->vma;
++ struct vm_area_struct *vma2 = tree_rmap_item->slot->vma;
++ struct page *page = rmap_item->page;
++ struct page *tree_page = tree_rmap_item->page;
++ int err = MERGE_ERR_PGERR;
++ struct address_space *saved_mapping;
++
++
++ if (rmap_item->page == tree_rmap_item->page)
++ goto out;
++
++ if (PageTransCompound(page) && page_trans_compound_anon_split(page))
++ goto out;
++ BUG_ON(PageTransCompound(page));
++
++ if (PageTransCompound(tree_page) && page_trans_compound_anon_split(tree_page))
++ goto out;
++ BUG_ON(PageTransCompound(tree_page));
++
++ if (!PageAnon(page) || !PageAnon(tree_page))
++ goto out;
++
++ if (!trylock_page(page))
++ goto out;
++
++
++ if (write_protect_page(vma1, page, &wprt_pte1, &orig_pte1) != 0) {
++ unlock_page(page);
++ goto out;
++ }
++
++ /*
++ * While we hold page lock, upgrade page from
++ * PageAnon+anon_vma to PageKsm+NULL stable_node:
++ * stable_tree_insert() will update stable_node.
++ */
++ saved_mapping = page->mapping;
++ set_page_stable_node(page, NULL);
++ mark_page_accessed(page);
++ unlock_page(page);
++
++ if (!trylock_page(tree_page))
++ goto restore_out;
++
++ if (write_protect_page(vma2, tree_page, &wprt_pte2, &orig_pte2) != 0) {
++ unlock_page(tree_page);
++ goto restore_out;
++ }
++
++ if (pages_identical(page, tree_page)) {
++ err = replace_page(vma2, tree_page, page, wprt_pte2);
++ if (err) {
++ unlock_page(tree_page);
++ goto restore_out;
++ }
++
++ if ((vma2->vm_flags & VM_LOCKED)) {
++ munlock_vma_page(tree_page);
++ if (!PageMlocked(page)) {
++ unlock_page(tree_page);
++ lock_page(page);
++ mlock_vma_page(page);
++ tree_page = page; /* for final unlock */
++ }
++ }
++
++ unlock_page(tree_page);
++
++ goto out; /* success */
++
++ } else {
++ if (tree_rmap_item->hash_max &&
++ tree_rmap_item->hash_max == rmap_item->hash_max) {
++ err = MERGE_ERR_COLLI_MAX;
++ } else if (page_hash(page, hash_strength, 0) ==
++ page_hash(tree_page, hash_strength, 0)) {
++ inc_rshash_neg(memcmp_cost + hash_strength * 2);
++ err = MERGE_ERR_COLLI;
++ } else {
++ err = MERGE_ERR_CHANGED;
++ }
++
++ unlock_page(tree_page);
++ }
++
++restore_out:
++ lock_page(page);
++ if (!restore_uksm_page_pte(vma1, get_rmap_addr(rmap_item),
++ orig_pte1, wprt_pte1))
++ page->mapping = saved_mapping;
++
++ unlock_page(page);
++out:
++ return err;
++}
++
++static inline int hash_cmp(u32 new_val, u32 node_val)
++{
++ if (new_val > node_val)
++ return 1;
++ else if (new_val < node_val)
++ return -1;
++ else
++ return 0;
++}
++
++static inline u32 rmap_item_hash_max(struct rmap_item *item, u32 hash)
++{
++ u32 hash_max = item->hash_max;
++
++ if (!hash_max) {
++ hash_max = page_hash_max(item->page, hash);
++
++ item->hash_max = hash_max;
++ }
++
++ return hash_max;
++}
++
++
++
++/**
++ * stable_tree_search() - search the stable tree for a page
++ *
++ * @item: the rmap_item we are comparing with
++ * @hash: the hash value of this item->page already calculated
++ *
++ * @return the page we have found, NULL otherwise. The page returned has
++ * been gotten.
++ */
++static struct page *stable_tree_search(struct rmap_item *item, u32 hash)
++{
++ struct rb_node *node = root_stable_treep->rb_node;
++ struct tree_node *tree_node;
++ unsigned long hash_max;
++ struct page *page = item->page;
++ struct stable_node *stable_node;
++
++ stable_node = page_stable_node(page);
++ if (stable_node) {
++ /* ksm page forked, that is
++ * if (PageKsm(page) && !in_stable_tree(rmap_item))
++ * it's actually gotten once outside.
++ */
++ get_page(page);
++ return page;
++ }
++
++ while (node) {
++ int cmp;
++
++ tree_node = rb_entry(node, struct tree_node, node);
++
++ cmp = hash_cmp(hash, tree_node->hash);
++
++ if (cmp < 0)
++ node = node->rb_left;
++ else if (cmp > 0)
++ node = node->rb_right;
++ else
++ break;
++ }
++
++ if (!node)
++ return NULL;
++
++ if (tree_node->count == 1) {
++ stable_node = rb_entry(tree_node->sub_root.rb_node,
++ struct stable_node, node);
++ BUG_ON(!stable_node);
++
++ goto get_page_out;
++ }
++
++ /*
++ * ok, we have to search the second
++ * level subtree, hash the page to a
++ * full strength.
++ */
++ node = tree_node->sub_root.rb_node;
++ BUG_ON(!node);
++ hash_max = rmap_item_hash_max(item, hash);
++
++ while (node) {
++ int cmp;
++
++ stable_node = rb_entry(node, struct stable_node, node);
++
++ cmp = hash_cmp(hash_max, stable_node->hash_max);
++
++ if (cmp < 0)
++ node = node->rb_left;
++ else if (cmp > 0)
++ node = node->rb_right;
++ else
++ goto get_page_out;
++ }
++
++ return NULL;
++
++get_page_out:
++ page = get_uksm_page(stable_node, 1, 1);
++ return page;
++}
++
++static int try_merge_rmap_item(struct rmap_item *item,
++ struct page *kpage,
++ struct page *tree_page)
++{
++ spinlock_t *ptl;
++ pte_t *ptep;
++ unsigned long addr;
++ struct vm_area_struct *vma = item->slot->vma;
++
++ addr = get_rmap_addr(item);
++ ptep = page_check_address(kpage, vma->vm_mm, addr, &ptl, 0);
++ if (!ptep)
++ return 0;
++
++ if (pte_write(*ptep)) {
++ /* has changed, abort! */
++ pte_unmap_unlock(ptep, ptl);
++ return 0;
++ }
++
++ get_page(tree_page);
++ page_add_anon_rmap(tree_page, vma, addr);
++
++ flush_cache_page(vma, addr, pte_pfn(*ptep));
++ ptep_clear_flush(vma, addr, ptep);
++ set_pte_at_notify(vma->vm_mm, addr, ptep,
++ mk_pte(tree_page, vma->vm_page_prot));
++
++ page_remove_rmap(kpage);
++ put_page(kpage);
++
++ pte_unmap_unlock(ptep, ptl);
++
++ return 1;
++}
++
++/**
++ * try_to_merge_with_stable_page() - when two rmap_items need to be inserted
++ * into stable tree, the page was found to be identical to a stable ksm page,
++ * this is the last chance we can merge them into one.
++ *
++ * @item1: the rmap_item holding the page which we wanted to insert
++ * into stable tree.
++ * @item2: the other rmap_item we found when unstable tree search
++ * @oldpage: the page currently mapped by the two rmap_items
++ * @tree_page: the page we found identical in stable tree node
++ * @success1: return if item1 is successfully merged
++ * @success2: return if item2 is successfully merged
++ */
++static void try_merge_with_stable(struct rmap_item *item1,
++ struct rmap_item *item2,
++ struct page **kpage,
++ struct page *tree_page,
++ int *success1, int *success2)
++{
++ struct vm_area_struct *vma1 = item1->slot->vma;
++ struct vm_area_struct *vma2 = item2->slot->vma;
++ *success1 = 0;
++ *success2 = 0;
++
++ if (unlikely(*kpage == tree_page)) {
++ /* I don't think this can really happen */
++ printk(KERN_WARNING "UKSM: unexpected condition detected in "
++ "try_merge_with_stable() -- *kpage == tree_page !\n");
++ *success1 = 1;
++ *success2 = 1;
++ return;
++ }
++
++ if (!PageAnon(*kpage) || !PageKsm(*kpage))
++ goto failed;
++
++ if (!trylock_page(tree_page))
++ goto failed;
++
++ /* If the oldpage is still ksm and still pointed
++ * to in the right place, and still write protected,
++ * we are confident it's not changed, no need to
++ * memcmp anymore.
++ * be ware, we cannot take nested pte locks,
++ * deadlock risk.
++ */
++ if (!try_merge_rmap_item(item1, *kpage, tree_page))
++ goto unlock_failed;
++
++ /* ok, then vma2, remind that pte1 already set */
++ if (!try_merge_rmap_item(item2, *kpage, tree_page))
++ goto success_1;
++
++ *success2 = 1;
++success_1:
++ *success1 = 1;
++
++
++ if ((*success1 && vma1->vm_flags & VM_LOCKED) ||
++ (*success2 && vma2->vm_flags & VM_LOCKED)) {
++ munlock_vma_page(*kpage);
++ if (!PageMlocked(tree_page))
++ mlock_vma_page(tree_page);
++ }
++
++ /*
++ * We do not need oldpage any more in the caller, so can break the lock
++ * now.
++ */
++ unlock_page(*kpage);
++ *kpage = tree_page; /* Get unlocked outside. */
++ return;
++
++unlock_failed:
++ unlock_page(tree_page);
++failed:
++ return;
++}
++
++static inline void stable_node_hash_max(struct stable_node *node,
++ struct page *page, u32 hash)
++{
++ u32 hash_max = node->hash_max;
++
++ if (!hash_max) {
++ hash_max = page_hash_max(page, hash);
++ node->hash_max = hash_max;
++ }
++}
++
++static inline
++struct stable_node *new_stable_node(struct tree_node *tree_node,
++ struct page *kpage, u32 hash_max)
++{
++ struct stable_node *new_stable_node;
++
++ new_stable_node = alloc_stable_node();
++ if (!new_stable_node)
++ return NULL;
++
++ new_stable_node->kpfn = page_to_pfn(kpage);
++ new_stable_node->hash_max = hash_max;
++ new_stable_node->tree_node = tree_node;
++ set_page_stable_node(kpage, new_stable_node);
++
++ return new_stable_node;
++}
++
++static inline
++struct stable_node *first_level_insert(struct tree_node *tree_node,
++ struct rmap_item *rmap_item,
++ struct rmap_item *tree_rmap_item,
++ struct page **kpage, u32 hash,
++ int *success1, int *success2)
++{
++ int cmp;
++ struct page *tree_page;
++ u32 hash_max = 0;
++ struct stable_node *stable_node, *new_snode;
++ struct rb_node *parent = NULL, **new;
++
++ /* this tree node contains no sub-tree yet */
++ stable_node = rb_entry(tree_node->sub_root.rb_node,
++ struct stable_node, node);
++
++ tree_page = get_uksm_page(stable_node, 1, 0);
++ if (tree_page) {
++ cmp = memcmp_pages(*kpage, tree_page, 1);
++ if (!cmp) {
++ try_merge_with_stable(rmap_item, tree_rmap_item, kpage,
++ tree_page, success1, success2);
++ put_page(tree_page);
++ if (!*success1 && !*success2)
++ goto failed;
++
++ return stable_node;
++
++ } else {
++ /*
++ * collision in first level try to create a subtree.
++ * A new node need to be created.
++ */
++ put_page(tree_page);
++
++ stable_node_hash_max(stable_node, tree_page,
++ tree_node->hash);
++ hash_max = rmap_item_hash_max(rmap_item, hash);
++ cmp = hash_cmp(hash_max, stable_node->hash_max);
++
++ parent = &stable_node->node;
++ if (cmp < 0) {
++ new = &parent->rb_left;
++ } else if (cmp > 0) {
++ new = &parent->rb_right;
++ } else {
++ goto failed;
++ }
++ }
++
++ } else {
++ /* the only stable_node deleted, we reuse its tree_node.
++ */
++ parent = NULL;
++ new = &tree_node->sub_root.rb_node;
++ }
++
++ new_snode = new_stable_node(tree_node, *kpage, hash_max);
++ if (!new_snode)
++ goto failed;
++
++ rb_link_node(&new_snode->node, parent, new);
++ rb_insert_color(&new_snode->node, &tree_node->sub_root);
++ tree_node->count++;
++ *success1 = *success2 = 1;
++
++ return new_snode;
++
++failed:
++ return NULL;
++}
++
++static inline
++struct stable_node *stable_subtree_insert(struct tree_node *tree_node,
++ struct rmap_item *rmap_item,
++ struct rmap_item *tree_rmap_item,
++ struct page **kpage, u32 hash,
++ int *success1, int *success2)
++{
++ struct page *tree_page;
++ u32 hash_max;
++ struct stable_node *stable_node, *new_snode;
++ struct rb_node *parent, **new;
++
++research:
++ parent = NULL;
++ new = &tree_node->sub_root.rb_node;
++ BUG_ON(!*new);
++ hash_max = rmap_item_hash_max(rmap_item, hash);
++ while (*new) {
++ int cmp;
++
++ stable_node = rb_entry(*new, struct stable_node, node);
++
++ cmp = hash_cmp(hash_max, stable_node->hash_max);
++
++ if (cmp < 0) {
++ parent = *new;
++ new = &parent->rb_left;
++ } else if (cmp > 0) {
++ parent = *new;
++ new = &parent->rb_right;
++ } else {
++ tree_page = get_uksm_page(stable_node, 1, 0);
++ if (tree_page) {
++ cmp = memcmp_pages(*kpage, tree_page, 1);
++ if (!cmp) {
++ try_merge_with_stable(rmap_item,
++ tree_rmap_item, kpage,
++ tree_page, success1, success2);
++
++ put_page(tree_page);
++ if (!*success1 && !*success2)
++ goto failed;
++ /*
++ * successfully merged with a stable
++ * node
++ */
++ return stable_node;
++ } else {
++ put_page(tree_page);
++ goto failed;
++ }
++ } else {
++ /*
++ * stable node may be deleted,
++ * and subtree maybe
++ * restructed, cannot
++ * continue, research it.
++ */
++ if (tree_node->count) {
++ goto research;
++ } else {
++ /* reuse the tree node*/
++ parent = NULL;
++ new = &tree_node->sub_root.rb_node;
++ }
++ }
++ }
++ }
++
++ new_snode = new_stable_node(tree_node, *kpage, hash_max);
++ if (!new_snode)
++ goto failed;
++
++ rb_link_node(&new_snode->node, parent, new);
++ rb_insert_color(&new_snode->node, &tree_node->sub_root);
++ tree_node->count++;
++ *success1 = *success2 = 1;
++
++ return new_snode;
++
++failed:
++ return NULL;
++}
++
++
++/**
++ * stable_tree_insert() - try to insert a merged page in unstable tree to
++ * the stable tree
++ *
++ * @kpage: the page need to be inserted
++ * @hash: the current hash of this page
++ * @rmap_item: the rmap_item being scanned
++ * @tree_rmap_item: the rmap_item found on unstable tree
++ * @success1: return if rmap_item is merged
++ * @success2: return if tree_rmap_item is merged
++ *
++ * @return the stable_node on stable tree if at least one
++ * rmap_item is inserted into stable tree, NULL
++ * otherwise.
++ */
++static struct stable_node *
++stable_tree_insert(struct page **kpage, u32 hash,
++ struct rmap_item *rmap_item,
++ struct rmap_item *tree_rmap_item,
++ int *success1, int *success2)
++{
++ struct rb_node **new = &root_stable_treep->rb_node;
++ struct rb_node *parent = NULL;
++ struct stable_node *stable_node;
++ struct tree_node *tree_node;
++ u32 hash_max = 0;
++
++ *success1 = *success2 = 0;
++
++ while (*new) {
++ int cmp;
++
++ tree_node = rb_entry(*new, struct tree_node, node);
++
++ cmp = hash_cmp(hash, tree_node->hash);
++
++ if (cmp < 0) {
++ parent = *new;
++ new = &parent->rb_left;
++ } else if (cmp > 0) {
++ parent = *new;
++ new = &parent->rb_right;
++ } else
++ break;
++ }
++
++ if (*new) {
++ if (tree_node->count == 1) {
++ stable_node = first_level_insert(tree_node, rmap_item,
++ tree_rmap_item, kpage,
++ hash, success1, success2);
++ } else {
++ stable_node = stable_subtree_insert(tree_node,
++ rmap_item, tree_rmap_item, kpage,
++ hash, success1, success2);
++ }
++ } else {
++
++ /* no tree node found */
++ tree_node = alloc_tree_node(stable_tree_node_listp);
++ if (!tree_node) {
++ stable_node = NULL;
++ goto out;
++ }
++
++ stable_node = new_stable_node(tree_node, *kpage, hash_max);
++ if (!stable_node) {
++ free_tree_node(tree_node);
++ goto out;
++ }
++
++ tree_node->hash = hash;
++ rb_link_node(&tree_node->node, parent, new);
++ rb_insert_color(&tree_node->node, root_stable_treep);
++ parent = NULL;
++ new = &tree_node->sub_root.rb_node;
++
++ rb_link_node(&stable_node->node, parent, new);
++ rb_insert_color(&stable_node->node, &tree_node->sub_root);
++ tree_node->count++;
++ *success1 = *success2 = 1;
++ }
++
++out:
++ return stable_node;
++}
++
++
++/**
++ * get_tree_rmap_item_page() - try to get the page and lock the mmap_sem
++ *
++ * @return 0 on success, -EBUSY if unable to lock the mmap_sem,
++ * -EINVAL if the page mapping has been changed.
++ */
++static inline int get_tree_rmap_item_page(struct rmap_item *tree_rmap_item)
++{
++ int err;
++
++ err = get_mergeable_page_lock_mmap(tree_rmap_item);
++
++ if (err == -EINVAL) {
++ /* its page map has been changed, remove it */
++ remove_rmap_item_from_tree(tree_rmap_item);
++ }
++
++ /* The page is gotten and mmap_sem is locked now. */
++ return err;
++}
++
++
++/**
++ * unstable_tree_search_insert() - search an unstable tree rmap_item with the
++ * same hash value. Get its page and trylock the mmap_sem
++ */
++static inline
++struct rmap_item *unstable_tree_search_insert(struct rmap_item *rmap_item,
++ u32 hash)
++
++{
++ struct rb_node **new = &root_unstable_tree.rb_node;
++ struct rb_node *parent = NULL;
++ struct tree_node *tree_node;
++ u32 hash_max;
++ struct rmap_item *tree_rmap_item;
++
++ while (*new) {
++ int cmp;
++
++ tree_node = rb_entry(*new, struct tree_node, node);
++
++ cmp = hash_cmp(hash, tree_node->hash);
++
++ if (cmp < 0) {
++ parent = *new;
++ new = &parent->rb_left;
++ } else if (cmp > 0) {
++ parent = *new;
++ new = &parent->rb_right;
++ } else
++ break;
++ }
++
++ if (*new) {
++ /* got the tree_node */
++ if (tree_node->count == 1) {
++ tree_rmap_item = rb_entry(tree_node->sub_root.rb_node,
++ struct rmap_item, node);
++ BUG_ON(!tree_rmap_item);
++
++ goto get_page_out;
++ }
++
++ /* well, search the collision subtree */
++ new = &tree_node->sub_root.rb_node;
++ BUG_ON(!*new);
++ hash_max = rmap_item_hash_max(rmap_item, hash);
++
++ while (*new) {
++ int cmp;
++
++ tree_rmap_item = rb_entry(*new, struct rmap_item,
++ node);
++
++ cmp = hash_cmp(hash_max, tree_rmap_item->hash_max);
++ parent = *new;
++ if (cmp < 0)
++ new = &parent->rb_left;
++ else if (cmp > 0)
++ new = &parent->rb_right;
++ else
++ goto get_page_out;
++ }
++ } else {
++ /* alloc a new tree_node */
++ tree_node = alloc_tree_node(&unstable_tree_node_list);
++ if (!tree_node)
++ return NULL;
++
++ tree_node->hash = hash;
++ rb_link_node(&tree_node->node, parent, new);
++ rb_insert_color(&tree_node->node, &root_unstable_tree);
++ parent = NULL;
++ new = &tree_node->sub_root.rb_node;
++ }
++
++ /* did not found even in sub-tree */
++ rmap_item->tree_node = tree_node;
++ rmap_item->address |= UNSTABLE_FLAG;
++ rmap_item->hash_round = uksm_hash_round;
++ rb_link_node(&rmap_item->node, parent, new);
++ rb_insert_color(&rmap_item->node, &tree_node->sub_root);
++
++ uksm_pages_unshared++;
++ return NULL;
++
++get_page_out:
++ if (tree_rmap_item->page == rmap_item->page)
++ return NULL;
++
++ if (get_tree_rmap_item_page(tree_rmap_item))
++ return NULL;
++
++ return tree_rmap_item;
++}
++
++static void hold_anon_vma(struct rmap_item *rmap_item,
++ struct anon_vma *anon_vma)
++{
++ rmap_item->anon_vma = anon_vma;
++ get_anon_vma(anon_vma);
++}
++
++
++/**
++ * stable_tree_append() - append a rmap_item to a stable node. Deduplication
++ * ratio statistics is done in this function.
++ *
++ */
++static void stable_tree_append(struct rmap_item *rmap_item,
++ struct stable_node *stable_node, int logdedup)
++{
++ struct node_vma *node_vma = NULL, *new_node_vma, *node_vma_cont = NULL;
++ unsigned long key = (unsigned long)rmap_item->slot;
++ unsigned long factor = rmap_item->slot->rung->step;
++
++ BUG_ON(!stable_node);
++ rmap_item->address |= STABLE_FLAG;
++
++ if (hlist_empty(&stable_node->hlist)) {
++ uksm_pages_shared++;
++ goto node_vma_new;
++ } else {
++ uksm_pages_sharing++;
++ }
++
++ hlist_for_each_entry(node_vma, &stable_node->hlist, hlist) {
++ if (node_vma->key >= key)
++ break;
++
++ if (logdedup) {
++ node_vma->slot->pages_bemerged += factor;
++ if (list_empty(&node_vma->slot->dedup_list))
++ list_add(&node_vma->slot->dedup_list,
++ &vma_slot_dedup);
++ }
++ }
++
++ if (node_vma) {
++ if (node_vma->key == key) {
++ node_vma_cont = hlist_entry_safe(node_vma->hlist.next, struct node_vma, hlist);
++ goto node_vma_ok;
++ } else if (node_vma->key > key) {
++ node_vma_cont = node_vma;
++ }
++ }
++
++node_vma_new:
++ /* no same vma already in node, alloc a new node_vma */
++ new_node_vma = alloc_node_vma();
++ BUG_ON(!new_node_vma);
++ new_node_vma->head = stable_node;
++ new_node_vma->slot = rmap_item->slot;
++
++ if (!node_vma) {
++ hlist_add_head(&new_node_vma->hlist, &stable_node->hlist);
++ } else if (node_vma->key != key) {
++ if (node_vma->key < key)
++ hlist_add_after(&node_vma->hlist, &new_node_vma->hlist);
++ else {
++ hlist_add_before(&new_node_vma->hlist,
++ &node_vma->hlist);
++ }
++
++ }
++ node_vma = new_node_vma;
++
++node_vma_ok: /* ok, ready to add to the list */
++ rmap_item->head = node_vma;
++ hlist_add_head(&rmap_item->hlist, &node_vma->rmap_hlist);
++ hold_anon_vma(rmap_item, rmap_item->slot->vma->anon_vma);
++ if (logdedup) {
++ rmap_item->slot->pages_merged++;
++ if (node_vma_cont) {
++ node_vma = node_vma_cont;
++ hlist_for_each_entry_continue(node_vma, hlist) {
++ node_vma->slot->pages_bemerged += factor;
++ if (list_empty(&node_vma->slot->dedup_list))
++ list_add(&node_vma->slot->dedup_list,
++ &vma_slot_dedup);
++ }
++ }
++ }
++}
++
++/*
++ * We use break_ksm to break COW on a ksm page: it's a stripped down
++ *
++ * if (get_user_pages(current, mm, addr, 1, 1, 1, &page, NULL) == 1)
++ * put_page(page);
++ *
++ * but taking great care only to touch a ksm page, in a VM_MERGEABLE vma,
++ * in case the application has unmapped and remapped mm,addr meanwhile.
++ * Could a ksm page appear anywhere else? Actually yes, in a VM_PFNMAP
++ * mmap of /dev/mem or /dev/kmem, where we would not want to touch it.
++ */
++static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
++{
++ struct page *page;
++ int ret = 0;
++
++ do {
++ cond_resched();
++ page = follow_page(vma, addr, FOLL_GET);
++ if (IS_ERR_OR_NULL(page))
++ break;
++ if (PageKsm(page)) {
++ ret = handle_mm_fault(vma->vm_mm, vma, addr,
++ FAULT_FLAG_WRITE);
++ } else
++ ret = VM_FAULT_WRITE;
++ put_page(page);
++ } while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_OOM)));
++ /*
++ * We must loop because handle_mm_fault() may back out if there's
++ * any difficulty e.g. if pte accessed bit gets updated concurrently.
++ *
++ * VM_FAULT_WRITE is what we have been hoping for: it indicates that
++ * COW has been broken, even if the vma does not permit VM_WRITE;
++ * but note that a concurrent fault might break PageKsm for us.
++ *
++ * VM_FAULT_SIGBUS could occur if we race with truncation of the
++ * backing file, which also invalidates anonymous pages: that's
++ * okay, that truncation will have unmapped the PageKsm for us.
++ *
++ * VM_FAULT_OOM: at the time of writing (late July 2009), setting
++ * aside mem_cgroup limits, VM_FAULT_OOM would only be set if the
++ * current task has TIF_MEMDIE set, and will be OOM killed on return
++ * to user; and ksmd, having no mm, would never be chosen for that.
++ *
++ * But if the mm is in a limited mem_cgroup, then the fault may fail
++ * with VM_FAULT_OOM even if the current task is not TIF_MEMDIE; and
++ * even ksmd can fail in this way - though it's usually breaking ksm
++ * just to undo a merge it made a moment before, so unlikely to oom.
++ *
++ * That's a pity: we might therefore have more kernel pages allocated
++ * than we're counting as nodes in the stable tree; but uksm_do_scan
++ * will retry to break_cow on each pass, so should recover the page
++ * in due course. The important thing is to not let VM_MERGEABLE
++ * be cleared while any such pages might remain in the area.
++ */
++ return (ret & VM_FAULT_OOM) ? -ENOMEM : 0;
++}
++
++static void break_cow(struct rmap_item *rmap_item)
++{
++ struct vm_area_struct *vma = rmap_item->slot->vma;
++ struct mm_struct *mm = vma->vm_mm;
++ unsigned long addr = get_rmap_addr(rmap_item);
++
++ if (uksm_test_exit(mm))
++ goto out;
++
++ break_ksm(vma, addr);
++out:
++ return;
++}
++
++/*
++ * Though it's very tempting to unmerge in_stable_tree(rmap_item)s rather
++ * than check every pte of a given vma, the locking doesn't quite work for
++ * that - an rmap_item is assigned to the stable tree after inserting ksm
++ * page and upping mmap_sem. Nor does it fit with the way we skip dup'ing
++ * rmap_items from parent to child at fork time (so as not to waste time
++ * if exit comes before the next scan reaches it).
++ *
++ * Similarly, although we'd like to remove rmap_items (so updating counts
++ * and freeing memory) when unmerging an area, it's easier to leave that
++ * to the next pass of ksmd - consider, for example, how ksmd might be
++ * in cmp_and_merge_page on one of the rmap_items we would be removing.
++ */
++inline int unmerge_uksm_pages(struct vm_area_struct *vma,
++ unsigned long start, unsigned long end)
++{
++ unsigned long addr;
++ int err = 0;
++
++ for (addr = start; addr < end && !err; addr += PAGE_SIZE) {
++ if (uksm_test_exit(vma->vm_mm))
++ break;
++ if (signal_pending(current))
++ err = -ERESTARTSYS;
++ else
++ err = break_ksm(vma, addr);
++ }
++ return err;
++}
++
++static inline void inc_uksm_pages_scanned(void)
++{
++ u64 delta;
++
++
++ if (uksm_pages_scanned == U64_MAX) {
++ encode_benefit();
++
++ delta = uksm_pages_scanned >> pages_scanned_base;
++
++ if (CAN_OVERFLOW_U64(pages_scanned_stored, delta)) {
++ pages_scanned_stored >>= 1;
++ delta >>= 1;
++ pages_scanned_base++;
++ }
++
++ pages_scanned_stored += delta;
++
++ uksm_pages_scanned = uksm_pages_scanned_last = 0;
++ }
++
++ uksm_pages_scanned++;
++}
++
++static inline int find_zero_page_hash(int strength, u32 hash)
++{
++ return (zero_hash_table[strength] == hash);
++}
++
++static
++int cmp_and_merge_zero_page(struct vm_area_struct *vma, struct page *page)
++{
++ struct page *zero_page = empty_uksm_zero_page;
++ struct mm_struct *mm = vma->vm_mm;
++ pte_t orig_pte = __pte(0);
++ int err = -EFAULT;
++
++ if (uksm_test_exit(mm))
++ goto out;
++
++ if (PageTransCompound(page) && page_trans_compound_anon_split(page))
++ goto out;
++ BUG_ON(PageTransCompound(page));
++
++ if (!PageAnon(page))
++ goto out;
++
++ if (!trylock_page(page))
++ goto out;
++
++ if (write_protect_page(vma, page, &orig_pte, 0) == 0) {
++ if (is_page_full_zero(page))
++ err = replace_page(vma, page, zero_page, orig_pte);
++ }
++
++ unlock_page(page);
++out:
++ return err;
++}
++
++/*
++ * cmp_and_merge_page() - first see if page can be merged into the stable
++ * tree; if not, compare hash to previous and if it's the same, see if page
++ * can be inserted into the unstable tree, or merged with a page already there
++ * and both transferred to the stable tree.
++ *
++ * @page: the page that we are searching identical page to.
++ * @rmap_item: the reverse mapping into the virtual address of this page
++ */
++static void cmp_and_merge_page(struct rmap_item *rmap_item, u32 hash)
++{
++ struct rmap_item *tree_rmap_item;
++ struct page *page;
++ struct page *kpage = NULL;
++ u32 hash_max;
++ int err;
++ unsigned int success1, success2;
++ struct stable_node *snode;
++ int cmp;
++ struct rb_node *parent = NULL, **new;
++
++ remove_rmap_item_from_tree(rmap_item);
++ page = rmap_item->page;
++
++ /* We first start with searching the page inside the stable tree */
++ kpage = stable_tree_search(rmap_item, hash);
++ if (kpage) {
++ err = try_to_merge_with_uksm_page(rmap_item, kpage,
++ hash);
++ if (!err) {
++ /*
++ * The page was successfully merged, add
++ * its rmap_item to the stable tree.
++ * page lock is needed because it's
++ * racing with try_to_unmap_ksm(), etc.
++ */
++ lock_page(kpage);
++ snode = page_stable_node(kpage);
++ stable_tree_append(rmap_item, snode, 1);
++ unlock_page(kpage);
++ put_page(kpage);
++ return; /* success */
++ }
++ put_page(kpage);
++
++ /*
++ * if it's a collision and it has been search in sub-rbtree
++ * (hash_max != 0), we want to abort, because if it is
++ * successfully merged in unstable tree, the collision trends to
++ * happen again.
++ */
++ if (err == MERGE_ERR_COLLI && rmap_item->hash_max)
++ return;
++ }
++
++ tree_rmap_item =
++ unstable_tree_search_insert(rmap_item, hash);
++ if (tree_rmap_item) {
++ err = try_to_merge_two_pages(rmap_item, tree_rmap_item, hash);
++ /*
++ * As soon as we merge this page, we want to remove the
++ * rmap_item of the page we have merged with from the unstable
++ * tree, and insert it instead as new node in the stable tree.
++ */
++ if (!err) {
++ kpage = page;
++ remove_rmap_item_from_tree(tree_rmap_item);
++ lock_page(kpage);
++ snode = stable_tree_insert(&kpage, hash,
++ rmap_item, tree_rmap_item,
++ &success1, &success2);
++
++ /*
++ * Do not log dedup for tree item, it's not counted as
++ * scanned in this round.
++ */
++ if (success2)
++ stable_tree_append(tree_rmap_item, snode, 0);
++
++ /*
++ * The order of these two stable append is important:
++ * we are scanning rmap_item.
++ */
++ if (success1)
++ stable_tree_append(rmap_item, snode, 1);
++
++ /*
++ * The original kpage may be unlocked inside
++ * stable_tree_insert() already. This page
++ * should be unlocked before doing
++ * break_cow().
++ */
++ unlock_page(kpage);
++
++ if (!success1)
++ break_cow(rmap_item);
++
++ if (!success2)
++ break_cow(tree_rmap_item);
++
++ } else if (err == MERGE_ERR_COLLI) {
++ BUG_ON(tree_rmap_item->tree_node->count > 1);
++
++ rmap_item_hash_max(tree_rmap_item,
++ tree_rmap_item->tree_node->hash);
++
++ hash_max = rmap_item_hash_max(rmap_item, hash);
++ cmp = hash_cmp(hash_max, tree_rmap_item->hash_max);
++ parent = &tree_rmap_item->node;
++ if (cmp < 0)
++ new = &parent->rb_left;
++ else if (cmp > 0)
++ new = &parent->rb_right;
++ else
++ goto put_up_out;
++
++ rmap_item->tree_node = tree_rmap_item->tree_node;
++ rmap_item->address |= UNSTABLE_FLAG;
++ rmap_item->hash_round = uksm_hash_round;
++ rb_link_node(&rmap_item->node, parent, new);
++ rb_insert_color(&rmap_item->node,
++ &tree_rmap_item->tree_node->sub_root);
++ rmap_item->tree_node->count++;
++ } else {
++ /*
++ * either one of the page has changed or they collide
++ * at the max hash, we consider them as ill items.
++ */
++ remove_rmap_item_from_tree(tree_rmap_item);
++ }
++put_up_out:
++ put_page(tree_rmap_item->page);
++ up_read(&tree_rmap_item->slot->vma->vm_mm->mmap_sem);
++ }
++}
++
++
++
++
++static inline unsigned long get_pool_index(struct vma_slot *slot,
++ unsigned long index)
++{
++ unsigned long pool_index;
++
++ pool_index = (sizeof(struct rmap_list_entry *) * index) >> PAGE_SHIFT;
++ if (pool_index >= slot->pool_size)
++ BUG();
++ return pool_index;
++}
++
++static inline unsigned long index_page_offset(unsigned long index)
++{
++ return offset_in_page(sizeof(struct rmap_list_entry *) * index);
++}
++
++static inline
++struct rmap_list_entry *get_rmap_list_entry(struct vma_slot *slot,
++ unsigned long index, int need_alloc)
++{
++ unsigned long pool_index;
++ struct page *page;
++ void *addr;
++
++
++ pool_index = get_pool_index(slot, index);
++ if (!slot->rmap_list_pool[pool_index]) {
++ if (!need_alloc)
++ return NULL;
++
++ page = alloc_page(GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN);
++ if (!page)
++ return NULL;
++
++ slot->rmap_list_pool[pool_index] = page;
++ }
++
++ addr = kmap(slot->rmap_list_pool[pool_index]);
++ addr += index_page_offset(index);
++
++ return addr;
++}
++
++static inline void put_rmap_list_entry(struct vma_slot *slot,
++ unsigned long index)
++{
++ unsigned long pool_index;
++
++ pool_index = get_pool_index(slot, index);
++ BUG_ON(!slot->rmap_list_pool[pool_index]);
++ kunmap(slot->rmap_list_pool[pool_index]);
++}
++
++static inline int entry_is_new(struct rmap_list_entry *entry)
++{
++ return !entry->item;
++}
++
++static inline unsigned long get_index_orig_addr(struct vma_slot *slot,
++ unsigned long index)
++{
++ return slot->vma->vm_start + (index << PAGE_SHIFT);
++}
++
++static inline unsigned long get_entry_address(struct rmap_list_entry *entry)
++{
++ unsigned long addr;
++
++ if (is_addr(entry->addr))
++ addr = get_clean_addr(entry->addr);
++ else if (entry->item)
++ addr = get_rmap_addr(entry->item);
++ else
++ BUG();
++
++ return addr;
++}
++
++static inline struct rmap_item *get_entry_item(struct rmap_list_entry *entry)
++{
++ if (is_addr(entry->addr))
++ return NULL;
++
++ return entry->item;
++}
++
++static inline void inc_rmap_list_pool_count(struct vma_slot *slot,
++ unsigned long index)
++{
++ unsigned long pool_index;
++
++ pool_index = get_pool_index(slot, index);
++ BUG_ON(!slot->rmap_list_pool[pool_index]);
++ slot->pool_counts[pool_index]++;
++}
++
++static inline void dec_rmap_list_pool_count(struct vma_slot *slot,
++ unsigned long index)
++{
++ unsigned long pool_index;
++
++ pool_index = get_pool_index(slot, index);
++ BUG_ON(!slot->rmap_list_pool[pool_index]);
++ BUG_ON(!slot->pool_counts[pool_index]);
++ slot->pool_counts[pool_index]--;
++}
++
++static inline int entry_has_rmap(struct rmap_list_entry *entry)
++{
++ return !is_addr(entry->addr) && entry->item;
++}
++
++static inline void swap_entries(struct rmap_list_entry *entry1,
++ unsigned long index1,
++ struct rmap_list_entry *entry2,
++ unsigned long index2)
++{
++ struct rmap_list_entry tmp;
++
++ /* swapping two new entries is meaningless */
++ BUG_ON(entry_is_new(entry1) && entry_is_new(entry2));
++
++ tmp = *entry1;
++ *entry1 = *entry2;
++ *entry2 = tmp;
++
++ if (entry_has_rmap(entry1))
++ entry1->item->entry_index = index1;
++
++ if (entry_has_rmap(entry2))
++ entry2->item->entry_index = index2;
++
++ if (entry_has_rmap(entry1) && !entry_has_rmap(entry2)) {
++ inc_rmap_list_pool_count(entry1->item->slot, index1);
++ dec_rmap_list_pool_count(entry1->item->slot, index2);
++ } else if (!entry_has_rmap(entry1) && entry_has_rmap(entry2)) {
++ inc_rmap_list_pool_count(entry2->item->slot, index2);
++ dec_rmap_list_pool_count(entry2->item->slot, index1);
++ }
++}
++
++static inline void free_entry_item(struct rmap_list_entry *entry)
++{
++ unsigned long index;
++ struct rmap_item *item;
++
++ if (!is_addr(entry->addr)) {
++ BUG_ON(!entry->item);
++ item = entry->item;
++ entry->addr = get_rmap_addr(item);
++ set_is_addr(entry->addr);
++ index = item->entry_index;
++ remove_rmap_item_from_tree(item);
++ dec_rmap_list_pool_count(item->slot, index);
++ free_rmap_item(item);
++ }
++}
++
++static inline int pool_entry_boundary(unsigned long index)
++{
++ unsigned long linear_addr;
++
++ linear_addr = sizeof(struct rmap_list_entry *) * index;
++ return index && !offset_in_page(linear_addr);
++}
++
++static inline void try_free_last_pool(struct vma_slot *slot,
++ unsigned long index)
++{
++ unsigned long pool_index;
++
++ pool_index = get_pool_index(slot, index);
++ if (slot->rmap_list_pool[pool_index] &&
++ !slot->pool_counts[pool_index]) {
++ __free_page(slot->rmap_list_pool[pool_index]);
++ slot->rmap_list_pool[pool_index] = NULL;
++ slot->flags |= UKSM_SLOT_NEED_SORT;
++ }
++
++}
++
++static inline unsigned long vma_item_index(struct vm_area_struct *vma,
++ struct rmap_item *item)
++{
++ return (get_rmap_addr(item) - vma->vm_start) >> PAGE_SHIFT;
++}
++
++static int within_same_pool(struct vma_slot *slot,
++ unsigned long i, unsigned long j)
++{
++ unsigned long pool_i, pool_j;
++
++ pool_i = get_pool_index(slot, i);
++ pool_j = get_pool_index(slot, j);
++
++ return (pool_i == pool_j);
++}
++
++static void sort_rmap_entry_list(struct vma_slot *slot)
++{
++ unsigned long i, j;
++ struct rmap_list_entry *entry, *swap_entry;
++
++ entry = get_rmap_list_entry(slot, 0, 0);
++ for (i = 0; i < slot->pages; ) {
++
++ if (!entry)
++ goto skip_whole_pool;
++
++ if (entry_is_new(entry))
++ goto next_entry;
++
++ if (is_addr(entry->addr)) {
++ entry->addr = 0;
++ goto next_entry;
++ }
++
++ j = vma_item_index(slot->vma, entry->item);
++ if (j == i)
++ goto next_entry;
++
++ if (within_same_pool(slot, i, j))
++ swap_entry = entry + j - i;
++ else
++ swap_entry = get_rmap_list_entry(slot, j, 1);
++
++ swap_entries(entry, i, swap_entry, j);
++ if (!within_same_pool(slot, i, j))
++ put_rmap_list_entry(slot, j);
++ continue;
++
++skip_whole_pool:
++ i += PAGE_SIZE / sizeof(*entry);
++ if (i < slot->pages)
++ entry = get_rmap_list_entry(slot, i, 0);
++ continue;
++
++next_entry:
++ if (i >= slot->pages - 1 ||
++ !within_same_pool(slot, i, i + 1)) {
++ put_rmap_list_entry(slot, i);
++ if (i + 1 < slot->pages)
++ entry = get_rmap_list_entry(slot, i + 1, 0);
++ } else
++ entry++;
++ i++;
++ continue;
++ }
++
++ /* free empty pool entries which contain no rmap_item */
++ /* CAN be simplied to based on only pool_counts when bug freed !!!!! */
++ for (i = 0; i < slot->pool_size; i++) {
++ unsigned char has_rmap;
++ void *addr;
++
++ if (!slot->rmap_list_pool[i])
++ continue;
++
++ has_rmap = 0;
++ addr = kmap(slot->rmap_list_pool[i]);
++ BUG_ON(!addr);
++ for (j = 0; j < PAGE_SIZE / sizeof(*entry); j++) {
++ entry = (struct rmap_list_entry *)addr + j;
++ if (is_addr(entry->addr))
++ continue;
++ if (!entry->item)
++ continue;
++ has_rmap = 1;
++ }
++ kunmap(slot->rmap_list_pool[i]);
++ if (!has_rmap) {
++ BUG_ON(slot->pool_counts[i]);
++ __free_page(slot->rmap_list_pool[i]);
++ slot->rmap_list_pool[i] = NULL;
++ }
++ }
++
++ slot->flags &= ~UKSM_SLOT_NEED_SORT;
++}
++
++/*
++ * vma_fully_scanned() - if all the pages in this slot have been scanned.
++ */
++static inline int vma_fully_scanned(struct vma_slot *slot)
++{
++ return slot->pages_scanned == slot->pages;
++}
++
++/**
++ * get_next_rmap_item() - Get the next rmap_item in a vma_slot according to
++ * its random permutation. This function is embedded with the random
++ * permutation index management code.
++ */
++static struct rmap_item *get_next_rmap_item(struct vma_slot *slot, u32 *hash)
++{
++ unsigned long rand_range, addr, swap_index, scan_index;
++ struct rmap_item *item = NULL;
++ struct rmap_list_entry *scan_entry, *swap_entry = NULL;
++ struct page *page;
++
++ scan_index = swap_index = slot->pages_scanned % slot->pages;
++
++ if (pool_entry_boundary(scan_index))
++ try_free_last_pool(slot, scan_index - 1);
++
++ if (vma_fully_scanned(slot)) {
++ if (slot->flags & UKSM_SLOT_NEED_SORT)
++ slot->flags |= UKSM_SLOT_NEED_RERAND;
++ else
++ slot->flags &= ~UKSM_SLOT_NEED_RERAND;
++ if (slot->flags & UKSM_SLOT_NEED_SORT)
++ sort_rmap_entry_list(slot);
++ }
++
++ scan_entry = get_rmap_list_entry(slot, scan_index, 1);
++ if (!scan_entry)
++ return NULL;
++
++ if (entry_is_new(scan_entry)) {
++ scan_entry->addr = get_index_orig_addr(slot, scan_index);
++ set_is_addr(scan_entry->addr);
++ }
++
++ if (slot->flags & UKSM_SLOT_NEED_RERAND) {
++ rand_range = slot->pages - scan_index;
++ BUG_ON(!rand_range);
++ swap_index = scan_index + (prandom_u32() % rand_range);
++ }
++
++ if (swap_index != scan_index) {
++ swap_entry = get_rmap_list_entry(slot, swap_index, 1);
++ if (entry_is_new(swap_entry)) {
++ swap_entry->addr = get_index_orig_addr(slot,
++ swap_index);
++ set_is_addr(swap_entry->addr);
++ }
++ swap_entries(scan_entry, scan_index, swap_entry, swap_index);
++ }
++
++ addr = get_entry_address(scan_entry);
++ item = get_entry_item(scan_entry);
++ BUG_ON(addr > slot->vma->vm_end || addr < slot->vma->vm_start);
++
++ page = follow_page(slot->vma, addr, FOLL_GET);
++ if (IS_ERR_OR_NULL(page))
++ goto nopage;
++
++ if (!PageAnon(page) && !page_trans_compound_anon(page))
++ goto putpage;
++
++ /*check is zero_page pfn or uksm_zero_page*/
++ if ((page_to_pfn(page) == zero_pfn)
++ || (page_to_pfn(page) == uksm_zero_pfn))
++ goto putpage;
++
++ flush_anon_page(slot->vma, page, addr);
++ flush_dcache_page(page);
++
++
++ *hash = page_hash(page, hash_strength, 1);
++ inc_uksm_pages_scanned();
++ /*if the page content all zero, re-map to zero-page*/
++ if (find_zero_page_hash(hash_strength, *hash)) {
++ if (!cmp_and_merge_zero_page(slot->vma, page)) {
++ slot->pages_merged++;
++ __inc_zone_page_state(page, NR_UKSM_ZERO_PAGES);
++ dec_mm_counter(slot->mm, MM_ANONPAGES);
++
++ /* For full-zero pages, no need to create rmap item */
++ goto putpage;
++ } else {
++ inc_rshash_neg(memcmp_cost / 2);
++ }
++ }
++
++ if (!item) {
++ item = alloc_rmap_item();
++ if (item) {
++ /* It has already been zeroed */
++ item->slot = slot;
++ item->address = addr;
++ item->entry_index = scan_index;
++ scan_entry->item = item;
++ inc_rmap_list_pool_count(slot, scan_index);
++ } else
++ goto putpage;
++ }
++
++ BUG_ON(item->slot != slot);
++ /* the page may have changed */
++ item->page = page;
++ put_rmap_list_entry(slot, scan_index);
++ if (swap_entry)
++ put_rmap_list_entry(slot, swap_index);
++ return item;
++
++putpage:
++ put_page(page);
++ page = NULL;
++nopage:
++ /* no page, store addr back and free rmap_item if possible */
++ free_entry_item(scan_entry);
++ put_rmap_list_entry(slot, scan_index);
++ if (swap_entry)
++ put_rmap_list_entry(slot, swap_index);
++ return NULL;
++}
++
++static inline int in_stable_tree(struct rmap_item *rmap_item)
++{
++ return rmap_item->address & STABLE_FLAG;
++}
++
++/**
++ * scan_vma_one_page() - scan the next page in a vma_slot. Called with
++ * mmap_sem locked.
++ */
++static noinline void scan_vma_one_page(struct vma_slot *slot)
++{
++ u32 hash;
++ struct mm_struct *mm;
++ struct rmap_item *rmap_item = NULL;
++ struct vm_area_struct *vma = slot->vma;
++
++ mm = vma->vm_mm;
++ BUG_ON(!mm);
++ BUG_ON(!slot);
++
++ rmap_item = get_next_rmap_item(slot, &hash);
++ if (!rmap_item)
++ goto out1;
++
++ if (PageKsm(rmap_item->page) && in_stable_tree(rmap_item))
++ goto out2;
++
++ cmp_and_merge_page(rmap_item, hash);
++out2:
++ put_page(rmap_item->page);
++out1:
++ slot->pages_scanned++;
++ if (slot->fully_scanned_round != fully_scanned_round)
++ scanned_virtual_pages++;
++
++ if (vma_fully_scanned(slot))
++ slot->fully_scanned_round = fully_scanned_round;
++}
++
++static inline unsigned long rung_get_pages(struct scan_rung *rung)
++{
++ struct slot_tree_node *node;
++
++ if (!rung->vma_root.rnode)
++ return 0;
++
++ node = container_of(rung->vma_root.rnode, struct slot_tree_node, snode);
++
++ return node->size;
++}
++
++#define RUNG_SAMPLED_MIN 3
++
++static inline
++void uksm_calc_rung_step(struct scan_rung *rung,
++ unsigned long page_time, unsigned long ratio)
++{
++ unsigned long sampled, pages;
++
++ /* will be fully scanned ? */
++ if (!rung->cover_msecs) {
++ rung->step = 1;
++ return;
++ }
++
++ sampled = rung->cover_msecs * (NSEC_PER_MSEC / TIME_RATIO_SCALE)
++ * ratio / page_time;
++
++ /*
++ * Before we finsish a scan round and expensive per-round jobs,
++ * we need to have a chance to estimate the per page time. So
++ * the sampled number can not be too small.
++ */
++ if (sampled < RUNG_SAMPLED_MIN)
++ sampled = RUNG_SAMPLED_MIN;
++
++ pages = rung_get_pages(rung);
++ if (likely(pages > sampled))
++ rung->step = pages / sampled;
++ else
++ rung->step = 1;
++}
++
++static inline int step_need_recalc(struct scan_rung *rung)
++{
++ unsigned long pages, stepmax;
++
++ pages = rung_get_pages(rung);
++ stepmax = pages / RUNG_SAMPLED_MIN;
++
++ return pages && (rung->step > pages ||
++ (stepmax && rung->step > stepmax));
++}
++
++static inline
++void reset_current_scan(struct scan_rung *rung, int finished, int step_recalc)
++{
++ struct vma_slot *slot;
++
++ if (finished)
++ rung->flags |= UKSM_RUNG_ROUND_FINISHED;
++
++ if (step_recalc || step_need_recalc(rung)) {
++ uksm_calc_rung_step(rung, uksm_ema_page_time, rung->cpu_ratio);
++ BUG_ON(step_need_recalc(rung));
++ }
++
++ slot_iter_index = prandom_u32() % rung->step;
++ BUG_ON(!rung->vma_root.rnode);
++ slot = sradix_tree_next(&rung->vma_root, NULL, 0, slot_iter);
++ BUG_ON(!slot);
++
++ rung->current_scan = slot;
++ rung->current_offset = slot_iter_index;
++}
++
++static inline struct sradix_tree_root *slot_get_root(struct vma_slot *slot)
++{
++ return &slot->rung->vma_root;
++}
++
++/*
++ * return if resetted.
++ */
++static int advance_current_scan(struct scan_rung *rung)
++{
++ unsigned short n;
++ struct vma_slot *slot, *next = NULL;
++
++ BUG_ON(!rung->vma_root.num);
++
++ slot = rung->current_scan;
++ n = (slot->pages - rung->current_offset) % rung->step;
++ slot_iter_index = rung->step - n;
++ next = sradix_tree_next(&rung->vma_root, slot->snode,
++ slot->sindex, slot_iter);
++
++ if (next) {
++ rung->current_offset = slot_iter_index;
++ rung->current_scan = next;
++ return 0;
++ } else {
++ reset_current_scan(rung, 1, 0);
++ return 1;
++ }
++}
++
++static inline void rung_rm_slot(struct vma_slot *slot)
++{
++ struct scan_rung *rung = slot->rung;
++ struct sradix_tree_root *root;
++
++ if (rung->current_scan == slot)
++ advance_current_scan(rung);
++
++ root = slot_get_root(slot);
++ sradix_tree_delete_from_leaf(root, slot->snode, slot->sindex);
++ slot->snode = NULL;
++ if (step_need_recalc(rung)) {
++ uksm_calc_rung_step(rung, uksm_ema_page_time, rung->cpu_ratio);
++ BUG_ON(step_need_recalc(rung));
++ }
++
++ /* In case advance_current_scan loop back to this slot again */
++ if (rung->vma_root.num && rung->current_scan == slot)
++ reset_current_scan(slot->rung, 1, 0);
++}
++
++static inline void rung_add_new_slots(struct scan_rung *rung,
++ struct vma_slot **slots, unsigned long num)
++{
++ int err;
++ struct vma_slot *slot;
++ unsigned long i;
++ struct sradix_tree_root *root = &rung->vma_root;
++
++ err = sradix_tree_enter(root, (void **)slots, num);
++ BUG_ON(err);
++
++ for (i = 0; i < num; i++) {
++ slot = slots[i];
++ slot->rung = rung;
++ BUG_ON(vma_fully_scanned(slot));
++ }
++
++ if (rung->vma_root.num == num)
++ reset_current_scan(rung, 0, 1);
++}
++
++static inline int rung_add_one_slot(struct scan_rung *rung,
++ struct vma_slot *slot)
++{
++ int err;
++
++ err = sradix_tree_enter(&rung->vma_root, (void **)&slot, 1);
++ if (err)
++ return err;
++
++ slot->rung = rung;
++ if (rung->vma_root.num == 1)
++ reset_current_scan(rung, 0, 1);
++
++ return 0;
++}
++
++/*
++ * Return true if the slot is deleted from its rung.
++ */
++static inline int vma_rung_enter(struct vma_slot *slot, struct scan_rung *rung)
++{
++ struct scan_rung *old_rung = slot->rung;
++ int err;
++
++ if (old_rung == rung)
++ return 0;
++
++ rung_rm_slot(slot);
++ err = rung_add_one_slot(rung, slot);
++ if (err) {
++ err = rung_add_one_slot(old_rung, slot);
++ WARN_ON(err); /* OOPS, badly OOM, we lost this slot */
++ }
++
++ return 1;
++}
++
++static inline int vma_rung_up(struct vma_slot *slot)
++{
++ struct scan_rung *rung;
++
++ rung = slot->rung;
++ if (slot->rung != &uksm_scan_ladder[SCAN_LADDER_SIZE-1])
++ rung++;
++
++ return vma_rung_enter(slot, rung);
++}
++
++static inline int vma_rung_down(struct vma_slot *slot)
++{
++ struct scan_rung *rung;
++
++ rung = slot->rung;
++ if (slot->rung != &uksm_scan_ladder[0])
++ rung--;
++
++ return vma_rung_enter(slot, rung);
++}
++
++/**
++ * cal_dedup_ratio() - Calculate the deduplication ratio for this slot.
++ */
++static unsigned long cal_dedup_ratio(struct vma_slot *slot)
++{
++ unsigned long ret;
++
++ BUG_ON(slot->pages_scanned == slot->last_scanned);
++
++ ret = slot->pages_merged;
++
++ /* Thrashing area filtering */
++ if (ret && uksm_thrash_threshold) {
++ if (slot->pages_cowed * 100 / slot->pages_merged
++ > uksm_thrash_threshold) {
++ ret = 0;
++ } else {
++ ret = slot->pages_merged - slot->pages_cowed;
++ }
++ }
++
++ return ret;
++}
++
++/**
++ * cal_dedup_ratio() - Calculate the deduplication ratio for this slot.
++ */
++static unsigned long cal_dedup_ratio_old(struct vma_slot *slot)
++{
++ unsigned long ret;
++ unsigned long pages_scanned;
++
++ pages_scanned = slot->pages_scanned;
++ if (!pages_scanned) {
++ if (uksm_thrash_threshold)
++ return 0;
++ else
++ pages_scanned = slot->pages_scanned;
++ }
++
++ ret = slot->pages_bemerged * 100 / pages_scanned;
++
++ /* Thrashing area filtering */
++ if (ret && uksm_thrash_threshold) {
++ if (slot->pages_cowed * 100 / slot->pages_bemerged
++ > uksm_thrash_threshold) {
++ ret = 0;
++ } else {
++ ret = slot->pages_bemerged - slot->pages_cowed;
++ }
++ }
++
++ return ret;
++}
++
++/**
++ * stable_node_reinsert() - When the hash_strength has been adjusted, the
++ * stable tree need to be restructured, this is the function re-inserting the
++ * stable node.
++ */
++static inline void stable_node_reinsert(struct stable_node *new_node,
++ struct page *page,
++ struct rb_root *root_treep,
++ struct list_head *tree_node_listp,
++ u32 hash)
++{
++ struct rb_node **new = &root_treep->rb_node;
++ struct rb_node *parent = NULL;
++ struct stable_node *stable_node;
++ struct tree_node *tree_node;
++ struct page *tree_page;
++ int cmp;
++
++ while (*new) {
++ int cmp;
++
++ tree_node = rb_entry(*new, struct tree_node, node);
++
++ cmp = hash_cmp(hash, tree_node->hash);
++
++ if (cmp < 0) {
++ parent = *new;
++ new = &parent->rb_left;
++ } else if (cmp > 0) {
++ parent = *new;
++ new = &parent->rb_right;
++ } else
++ break;
++ }
++
++ if (*new) {
++ /* find a stable tree node with same first level hash value */
++ stable_node_hash_max(new_node, page, hash);
++ if (tree_node->count == 1) {
++ stable_node = rb_entry(tree_node->sub_root.rb_node,
++ struct stable_node, node);
++ tree_page = get_uksm_page(stable_node, 1, 0);
++ if (tree_page) {
++ stable_node_hash_max(stable_node,
++ tree_page, hash);
++ put_page(tree_page);
++
++ /* prepare for stable node insertion */
++
++ cmp = hash_cmp(new_node->hash_max,
++ stable_node->hash_max);
++ parent = &stable_node->node;
++ if (cmp < 0)
++ new = &parent->rb_left;
++ else if (cmp > 0)
++ new = &parent->rb_right;
++ else
++ goto failed;
++
++ goto add_node;
++ } else {
++ /* the only stable_node deleted, the tree node
++ * was not deleted.
++ */
++ goto tree_node_reuse;
++ }
++ }
++
++ /* well, search the collision subtree */
++ new = &tree_node->sub_root.rb_node;
++ parent = NULL;
++ BUG_ON(!*new);
++ while (*new) {
++ int cmp;
++
++ stable_node = rb_entry(*new, struct stable_node, node);
++
++ cmp = hash_cmp(new_node->hash_max,
++ stable_node->hash_max);
++
++ if (cmp < 0) {
++ parent = *new;
++ new = &parent->rb_left;
++ } else if (cmp > 0) {
++ parent = *new;
++ new = &parent->rb_right;
++ } else {
++ /* oh, no, still a collision */
++ goto failed;
++ }
++ }
++
++ goto add_node;
++ }
++
++ /* no tree node found */
++ tree_node = alloc_tree_node(tree_node_listp);
++ if (!tree_node) {
++ printk(KERN_ERR "UKSM: memory allocation error!\n");
++ goto failed;
++ } else {
++ tree_node->hash = hash;
++ rb_link_node(&tree_node->node, parent, new);
++ rb_insert_color(&tree_node->node, root_treep);
++
++tree_node_reuse:
++ /* prepare for stable node insertion */
++ parent = NULL;
++ new = &tree_node->sub_root.rb_node;
++ }
++
++add_node:
++ rb_link_node(&new_node->node, parent, new);
++ rb_insert_color(&new_node->node, &tree_node->sub_root);
++ new_node->tree_node = tree_node;
++ tree_node->count++;
++ return;
++
++failed:
++ /* This can only happen when two nodes have collided
++ * in two levels.
++ */
++ new_node->tree_node = NULL;
++ return;
++}
++
++static inline void free_all_tree_nodes(struct list_head *list)
++{
++ struct tree_node *node, *tmp;
++
++ list_for_each_entry_safe(node, tmp, list, all_list) {
++ free_tree_node(node);
++ }
++}
++
++/**
++ * stable_tree_delta_hash() - Delta hash the stable tree from previous hash
++ * strength to the current hash_strength. It re-structures the hole tree.
++ */
++static inline void stable_tree_delta_hash(u32 prev_hash_strength)
++{
++ struct stable_node *node, *tmp;
++ struct rb_root *root_new_treep;
++ struct list_head *new_tree_node_listp;
++
++ stable_tree_index = (stable_tree_index + 1) % 2;
++ root_new_treep = &root_stable_tree[stable_tree_index];
++ new_tree_node_listp = &stable_tree_node_list[stable_tree_index];
++ *root_new_treep = RB_ROOT;
++ BUG_ON(!list_empty(new_tree_node_listp));
++
++ /*
++ * we need to be safe, the node could be removed by get_uksm_page()
++ */
++ list_for_each_entry_safe(node, tmp, &stable_node_list, all_list) {
++ void *addr;
++ struct page *node_page;
++ u32 hash;
++
++ /*
++ * We are completely re-structuring the stable nodes to a new
++ * stable tree. We don't want to touch the old tree unlinks and
++ * old tree_nodes. The old tree_nodes will be freed at once.
++ */
++ node_page = get_uksm_page(node, 0, 0);
++ if (!node_page)
++ continue;
++
++ if (node->tree_node) {
++ hash = node->tree_node->hash;
++
++ addr = kmap_atomic(node_page);
++
++ hash = delta_hash(addr, prev_hash_strength,
++ hash_strength, hash);
++ kunmap_atomic(addr);
++ } else {
++ /*
++ *it was not inserted to rbtree due to collision in last
++ *round scan.
++ */
++ hash = page_hash(node_page, hash_strength, 0);
++ }
++
++ stable_node_reinsert(node, node_page, root_new_treep,
++ new_tree_node_listp, hash);
++ put_page(node_page);
++ }
++
++ root_stable_treep = root_new_treep;
++ free_all_tree_nodes(stable_tree_node_listp);
++ BUG_ON(!list_empty(stable_tree_node_listp));
++ stable_tree_node_listp = new_tree_node_listp;
++}
++
++static inline void inc_hash_strength(unsigned long delta)
++{
++ hash_strength += 1 << delta;
++ if (hash_strength > HASH_STRENGTH_MAX)
++ hash_strength = HASH_STRENGTH_MAX;
++}
++
++static inline void dec_hash_strength(unsigned long delta)
++{
++ unsigned long change = 1 << delta;
++
++ if (hash_strength <= change + 1)
++ hash_strength = 1;
++ else
++ hash_strength -= change;
++}
++
++static inline void inc_hash_strength_delta(void)
++{
++ hash_strength_delta++;
++ if (hash_strength_delta > HASH_STRENGTH_DELTA_MAX)
++ hash_strength_delta = HASH_STRENGTH_DELTA_MAX;
++}
++
++/*
++static inline unsigned long get_current_neg_ratio(void)
++{
++ if (!rshash_pos || rshash_neg > rshash_pos)
++ return 100;
++
++ return div64_u64(100 * rshash_neg , rshash_pos);
++}
++*/
++
++static inline unsigned long get_current_neg_ratio(void)
++{
++ u64 pos = benefit.pos;
++ u64 neg = benefit.neg;
++
++ if (!neg)
++ return 0;
++
++ if (!pos || neg > pos)
++ return 100;
++
++ if (neg > div64_u64(U64_MAX, 100))
++ pos = div64_u64(pos, 100);
++ else
++ neg *= 100;
++
++ return div64_u64(neg, pos);
++}
++
++static inline unsigned long get_current_benefit(void)
++{
++ u64 pos = benefit.pos;
++ u64 neg = benefit.neg;
++ u64 scanned = benefit.scanned;
++
++ if (neg > pos)
++ return 0;
++
++ return div64_u64((pos - neg), scanned);
++}
++
++static inline int judge_rshash_direction(void)
++{
++ u64 current_neg_ratio, stable_benefit;
++ u64 current_benefit, delta = 0;
++ int ret = STILL;
++
++ /* Try to probe a value after the boot, and in case the system
++ are still for a long time. */
++ if ((fully_scanned_round & 0xFFULL) == 10) {
++ ret = OBSCURE;
++ goto out;
++ }
++
++ current_neg_ratio = get_current_neg_ratio();
++
++ if (current_neg_ratio == 0) {
++ rshash_neg_cont_zero++;
++ if (rshash_neg_cont_zero > 2)
++ return GO_DOWN;
++ else
++ return STILL;
++ }
++ rshash_neg_cont_zero = 0;
++
++ if (current_neg_ratio > 90) {
++ ret = GO_UP;
++ goto out;
++ }
++
++ current_benefit = get_current_benefit();
++ stable_benefit = rshash_state.stable_benefit;
++
++ if (!stable_benefit) {
++ ret = OBSCURE;
++ goto out;
++ }
++
++ if (current_benefit > stable_benefit)
++ delta = current_benefit - stable_benefit;
++ else if (current_benefit < stable_benefit)
++ delta = stable_benefit - current_benefit;
++
++ delta = div64_u64(100 * delta , stable_benefit);
++
++ if (delta > 50) {
++ rshash_cont_obscure++;
++ if (rshash_cont_obscure > 2)
++ return OBSCURE;
++ else
++ return STILL;
++ }
++
++out:
++ rshash_cont_obscure = 0;
++ return ret;
++}
++
++/**
++ * rshash_adjust() - The main function to control the random sampling state
++ * machine for hash strength adapting.
++ *
++ * return true if hash_strength has changed.
++ */
++static inline int rshash_adjust(void)
++{
++ unsigned long prev_hash_strength = hash_strength;
++
++ if (!encode_benefit())
++ return 0;
++
++ switch (rshash_state.state) {
++ case RSHASH_STILL:
++ switch (judge_rshash_direction()) {
++ case GO_UP:
++ if (rshash_state.pre_direct == GO_DOWN)
++ hash_strength_delta = 0;
++
++ inc_hash_strength(hash_strength_delta);
++ inc_hash_strength_delta();
++ rshash_state.stable_benefit = get_current_benefit();
++ rshash_state.pre_direct = GO_UP;
++ break;
++
++ case GO_DOWN:
++ if (rshash_state.pre_direct == GO_UP)
++ hash_strength_delta = 0;
++
++ dec_hash_strength(hash_strength_delta);
++ inc_hash_strength_delta();
++ rshash_state.stable_benefit = get_current_benefit();
++ rshash_state.pre_direct = GO_DOWN;
++ break;
++
++ case OBSCURE:
++ rshash_state.stable_point = hash_strength;
++ rshash_state.turn_point_down = hash_strength;
++ rshash_state.turn_point_up = hash_strength;
++ rshash_state.turn_benefit_down = get_current_benefit();
++ rshash_state.turn_benefit_up = get_current_benefit();
++ rshash_state.lookup_window_index = 0;
++ rshash_state.state = RSHASH_TRYDOWN;
++ dec_hash_strength(hash_strength_delta);
++ inc_hash_strength_delta();
++ break;
++
++ case STILL:
++ break;
++ default:
++ BUG();
++ }
++ break;
++
++ case RSHASH_TRYDOWN:
++ if (rshash_state.lookup_window_index++ % 5 == 0)
++ rshash_state.below_count = 0;
++
++ if (get_current_benefit() < rshash_state.stable_benefit)
++ rshash_state.below_count++;
++ else if (get_current_benefit() >
++ rshash_state.turn_benefit_down) {
++ rshash_state.turn_point_down = hash_strength;
++ rshash_state.turn_benefit_down = get_current_benefit();
++ }
++
++ if (rshash_state.below_count >= 3 ||
++ judge_rshash_direction() == GO_UP ||
++ hash_strength == 1) {
++ hash_strength = rshash_state.stable_point;
++ hash_strength_delta = 0;
++ inc_hash_strength(hash_strength_delta);
++ inc_hash_strength_delta();
++ rshash_state.lookup_window_index = 0;
++ rshash_state.state = RSHASH_TRYUP;
++ hash_strength_delta = 0;
++ } else {
++ dec_hash_strength(hash_strength_delta);
++ inc_hash_strength_delta();
++ }
++ break;
++
++ case RSHASH_TRYUP:
++ if (rshash_state.lookup_window_index++ % 5 == 0)
++ rshash_state.below_count = 0;
++
++ if (get_current_benefit() < rshash_state.turn_benefit_down)
++ rshash_state.below_count++;
++ else if (get_current_benefit() > rshash_state.turn_benefit_up) {
++ rshash_state.turn_point_up = hash_strength;
++ rshash_state.turn_benefit_up = get_current_benefit();
++ }
++
++ if (rshash_state.below_count >= 3 ||
++ judge_rshash_direction() == GO_DOWN ||
++ hash_strength == HASH_STRENGTH_MAX) {
++ hash_strength = rshash_state.turn_benefit_up >
++ rshash_state.turn_benefit_down ?
++ rshash_state.turn_point_up :
++ rshash_state.turn_point_down;
++
++ rshash_state.state = RSHASH_PRE_STILL;
++ } else {
++ inc_hash_strength(hash_strength_delta);
++ inc_hash_strength_delta();
++ }
++
++ break;
++
++ case RSHASH_NEW:
++ case RSHASH_PRE_STILL:
++ rshash_state.stable_benefit = get_current_benefit();
++ rshash_state.state = RSHASH_STILL;
++ hash_strength_delta = 0;
++ break;
++ default:
++ BUG();
++ }
++
++ /* rshash_neg = rshash_pos = 0; */
++ reset_benefit();
++
++ if (prev_hash_strength != hash_strength)
++ stable_tree_delta_hash(prev_hash_strength);
++
++ return prev_hash_strength != hash_strength;
++}
++
++/**
++ * round_update_ladder() - The main function to do update of all the
++ * adjustments whenever a scan round is finished.
++ */
++static noinline void round_update_ladder(void)
++{
++ int i;
++ unsigned long dedup;
++ struct vma_slot *slot, *tmp_slot;
++
++ for (i = 0; i < SCAN_LADDER_SIZE; i++) {
++ uksm_scan_ladder[i].flags &= ~UKSM_RUNG_ROUND_FINISHED;
++ }
++
++ list_for_each_entry_safe(slot, tmp_slot, &vma_slot_dedup, dedup_list) {
++
++ /* slot may be rung_rm_slot() when mm exits */
++ if (slot->snode) {
++ dedup = cal_dedup_ratio_old(slot);
++ if (dedup && dedup >= uksm_abundant_threshold)
++ vma_rung_up(slot);
++ }
++
++ slot->pages_bemerged = 0;
++ slot->pages_cowed = 0;
++
++ list_del_init(&slot->dedup_list);
++ }
++}
++
++static void uksm_del_vma_slot(struct vma_slot *slot)
++{
++ int i, j;
++ struct rmap_list_entry *entry;
++
++ if (slot->snode) {
++ /*
++ * In case it just failed when entering the rung, it's not
++ * necessary.
++ */
++ rung_rm_slot(slot);
++ }
++
++ if (!list_empty(&slot->dedup_list))
++ list_del(&slot->dedup_list);
++
++ if (!slot->rmap_list_pool || !slot->pool_counts) {
++ /* In case it OOMed in uksm_vma_enter() */
++ goto out;
++ }
++
++ for (i = 0; i < slot->pool_size; i++) {
++ void *addr;
++
++ if (!slot->rmap_list_pool[i])
++ continue;
++
++ addr = kmap(slot->rmap_list_pool[i]);
++ for (j = 0; j < PAGE_SIZE / sizeof(*entry); j++) {
++ entry = (struct rmap_list_entry *)addr + j;
++ if (is_addr(entry->addr))
++ continue;
++ if (!entry->item)
++ continue;
++
++ remove_rmap_item_from_tree(entry->item);
++ free_rmap_item(entry->item);
++ slot->pool_counts[i]--;
++ }
++ BUG_ON(slot->pool_counts[i]);
++ kunmap(slot->rmap_list_pool[i]);
++ __free_page(slot->rmap_list_pool[i]);
++ }
++ kfree(slot->rmap_list_pool);
++ kfree(slot->pool_counts);
++
++out:
++ slot->rung = NULL;
++ BUG_ON(uksm_pages_total < slot->pages);
++ if (slot->flags & UKSM_SLOT_IN_UKSM)
++ uksm_pages_total -= slot->pages;
++
++ if (slot->fully_scanned_round == fully_scanned_round)
++ scanned_virtual_pages -= slot->pages;
++ else
++ scanned_virtual_pages -= slot->pages_scanned;
++ free_vma_slot(slot);
++}
++
++
++#define SPIN_LOCK_PERIOD 32
++static struct vma_slot *cleanup_slots[SPIN_LOCK_PERIOD];
++static inline void cleanup_vma_slots(void)
++{
++ struct vma_slot *slot;
++ int i;
++
++ i = 0;
++ spin_lock(&vma_slot_list_lock);
++ while (!list_empty(&vma_slot_del)) {
++ slot = list_entry(vma_slot_del.next,
++ struct vma_slot, slot_list);
++ list_del(&slot->slot_list);
++ cleanup_slots[i++] = slot;
++ if (i == SPIN_LOCK_PERIOD) {
++ spin_unlock(&vma_slot_list_lock);
++ while (--i >= 0)
++ uksm_del_vma_slot(cleanup_slots[i]);
++ i = 0;
++ spin_lock(&vma_slot_list_lock);
++ }
++ }
++ spin_unlock(&vma_slot_list_lock);
++
++ while (--i >= 0)
++ uksm_del_vma_slot(cleanup_slots[i]);
++}
++
++/*
++*expotional moving average formula
++*/
++static inline unsigned long ema(unsigned long curr, unsigned long last_ema)
++{
++ /*
++ * For a very high burst, even the ema cannot work well, a false very
++ * high per-page time estimation can result in feedback in very high
++ * overhead of context swith and rung update -- this will then lead
++ * to higher per-paper time, this may not converge.
++ *
++ * Instead, we try to approach this value in a binary manner.
++ */
++ if (curr > last_ema * 10)
++ return last_ema * 2;
++
++ return (EMA_ALPHA * curr + (100 - EMA_ALPHA) * last_ema) / 100;
++}
++
++/*
++ * convert cpu ratio in 1/TIME_RATIO_SCALE configured by user to
++ * nanoseconds based on current uksm_sleep_jiffies.
++ */
++static inline unsigned long cpu_ratio_to_nsec(unsigned int ratio)
++{
++ return NSEC_PER_USEC * jiffies_to_usecs(uksm_sleep_jiffies) /
++ (TIME_RATIO_SCALE - ratio) * ratio;
++}
++
++
++static inline unsigned long rung_real_ratio(int cpu_time_ratio)
++{
++ unsigned long ret;
++
++ BUG_ON(!cpu_time_ratio);
++
++ if (cpu_time_ratio > 0)
++ ret = cpu_time_ratio;
++ else
++ ret = (unsigned long)(-cpu_time_ratio) *
++ uksm_max_cpu_percentage / 100UL;
++
++ return ret ? ret : 1;
++}
++
++static noinline void uksm_calc_scan_pages(void)
++{
++ struct scan_rung *ladder = uksm_scan_ladder;
++ unsigned long sleep_usecs, nsecs;
++ unsigned long ratio;
++ int i;
++ unsigned long per_page;
++
++ if (uksm_ema_page_time > 100000 ||
++ (((unsigned long) uksm_eval_round & (256UL - 1)) == 0UL))
++ uksm_ema_page_time = UKSM_PAGE_TIME_DEFAULT;
++
++ per_page = uksm_ema_page_time;
++ BUG_ON(!per_page);
++
++ /*
++ * For every 8 eval round, we try to probe a uksm_sleep_jiffies value
++ * based on saved user input.
++ */
++ if (((unsigned long) uksm_eval_round & (8UL - 1)) == 0UL)
++ uksm_sleep_jiffies = uksm_sleep_saved;
++
++ /* We require a rung scan at least 1 page in a period. */
++ nsecs = per_page;
++ ratio = rung_real_ratio(ladder[0].cpu_ratio);
++ if (cpu_ratio_to_nsec(ratio) < nsecs) {
++ sleep_usecs = nsecs * (TIME_RATIO_SCALE - ratio) / ratio
++ / NSEC_PER_USEC;
++ uksm_sleep_jiffies = usecs_to_jiffies(sleep_usecs) + 1;
++ }
++
++ for (i = 0; i < SCAN_LADDER_SIZE; i++) {
++ ratio = rung_real_ratio(ladder[i].cpu_ratio);
++ ladder[i].pages_to_scan = cpu_ratio_to_nsec(ratio) /
++ per_page;
++ BUG_ON(!ladder[i].pages_to_scan);
++ uksm_calc_rung_step(&ladder[i], per_page, ratio);
++ }
++}
++
++/*
++ * From the scan time of this round (ns) to next expected min sleep time
++ * (ms), be careful of the possible overflows. ratio is taken from
++ * rung_real_ratio()
++ */
++static inline
++unsigned int scan_time_to_sleep(unsigned long long scan_time, unsigned long ratio)
++{
++ scan_time >>= 20; /* to msec level now */
++ BUG_ON(scan_time > (ULONG_MAX / TIME_RATIO_SCALE));
++
++ return (unsigned int) ((unsigned long) scan_time *
++ (TIME_RATIO_SCALE - ratio) / ratio);
++}
++
++#define __round_mask(x, y) ((__typeof__(x))((y)-1))
++#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1)
++
++static inline unsigned long vma_pool_size(struct vma_slot *slot)
++{
++ return round_up(sizeof(struct rmap_list_entry) * slot->pages,
++ PAGE_SIZE) >> PAGE_SHIFT;
++}
++
++static void uksm_vma_enter(struct vma_slot **slots, unsigned long num)
++{
++ struct scan_rung *rung;
++ unsigned long pool_size, i;
++ struct vma_slot *slot;
++ int failed;
++
++ rung = &uksm_scan_ladder[0];
++
++ failed = 0;
++ for (i = 0; i < num; i++) {
++ slot = slots[i];
++
++ pool_size = vma_pool_size(slot);
++ slot->rmap_list_pool = kzalloc(sizeof(struct page *) *
++ pool_size, GFP_KERNEL);
++ if (!slot->rmap_list_pool)
++ break;
++
++ slot->pool_counts = kzalloc(sizeof(unsigned int) * pool_size,
++ GFP_KERNEL);
++ if (!slot->pool_counts) {
++ kfree(slot->rmap_list_pool);
++ break;
++ }
++
++ slot->pool_size = pool_size;
++ BUG_ON(CAN_OVERFLOW_U64(uksm_pages_total, slot->pages));
++ slot->flags |= UKSM_SLOT_IN_UKSM;
++ uksm_pages_total += slot->pages;
++ }
++
++ if (i)
++ rung_add_new_slots(rung, slots, i);
++
++ return;
++}
++
++static struct vma_slot *batch_slots[SLOT_TREE_NODE_STORE_SIZE];
++
++static void uksm_enter_all_slots(void)
++{
++ struct vma_slot *slot;
++ unsigned long index;
++ struct list_head empty_vma_list;
++ int i;
++
++ i = 0;
++ index = 0;
++ INIT_LIST_HEAD(&empty_vma_list);
++
++ spin_lock(&vma_slot_list_lock);
++ while (!list_empty(&vma_slot_new)) {
++ slot = list_entry(vma_slot_new.next,
++ struct vma_slot, slot_list);
++
++ if (!slot->vma->anon_vma) {
++ list_move(&slot->slot_list, &empty_vma_list);
++ } else if (vma_can_enter(slot->vma)) {
++ batch_slots[index++] = slot;
++ list_del_init(&slot->slot_list);
++ } else {
++ list_move(&slot->slot_list, &vma_slot_noadd);
++ }
++
++ if (++i == SPIN_LOCK_PERIOD ||
++ (index && !(index % SLOT_TREE_NODE_STORE_SIZE))) {
++ spin_unlock(&vma_slot_list_lock);
++
++ if (index && !(index % SLOT_TREE_NODE_STORE_SIZE)) {
++ uksm_vma_enter(batch_slots, index);
++ index = 0;
++ }
++ i = 0;
++ cond_resched();
++ spin_lock(&vma_slot_list_lock);
++ }
++ }
++
++ list_splice(&empty_vma_list, &vma_slot_new);
++
++ spin_unlock(&vma_slot_list_lock);
++
++ if (index)
++ uksm_vma_enter(batch_slots, index);
++
++}
++
++static inline int rung_round_finished(struct scan_rung *rung)
++{
++ return rung->flags & UKSM_RUNG_ROUND_FINISHED;
++}
++
++static inline void judge_slot(struct vma_slot *slot)
++{
++ struct scan_rung *rung = slot->rung;
++ unsigned long dedup;
++ int deleted;
++
++ dedup = cal_dedup_ratio(slot);
++ if (vma_fully_scanned(slot) && uksm_thrash_threshold)
++ deleted = vma_rung_enter(slot, &uksm_scan_ladder[0]);
++ else if (dedup && dedup >= uksm_abundant_threshold)
++ deleted = vma_rung_up(slot);
++ else
++ deleted = vma_rung_down(slot);
++
++ slot->pages_merged = 0;
++ slot->pages_cowed = 0;
++
++ if (vma_fully_scanned(slot))
++ slot->pages_scanned = 0;
++
++ slot->last_scanned = slot->pages_scanned;
++
++ /* If its deleted in above, then rung was already advanced. */
++ if (!deleted)
++ advance_current_scan(rung);
++}
++
++
++static inline int hash_round_finished(void)
++{
++ if (scanned_virtual_pages > (uksm_pages_total >> 2)) {
++ scanned_virtual_pages = 0;
++ if (uksm_pages_scanned)
++ fully_scanned_round++;
++
++ return 1;
++ } else {
++ return 0;
++ }
++}
++
++#define UKSM_MMSEM_BATCH 5
++#define BUSY_RETRY 100
++
++/**
++ * uksm_do_scan() - the main worker function.
++ */
++static noinline void uksm_do_scan(void)
++{
++ struct vma_slot *slot, *iter;
++ struct mm_struct *busy_mm;
++ unsigned char round_finished, all_rungs_emtpy;
++ int i, err, mmsem_batch;
++ unsigned long pcost;
++ long long delta_exec;
++ unsigned long vpages, max_cpu_ratio;
++ unsigned long long start_time, end_time, scan_time;
++ unsigned int expected_jiffies;
++
++ might_sleep();
++
++ vpages = 0;
++
++ start_time = task_sched_runtime(current);
++ max_cpu_ratio = 0;
++ mmsem_batch = 0;
++
++ for (i = 0; i < SCAN_LADDER_SIZE;) {
++ struct scan_rung *rung = &uksm_scan_ladder[i];
++ unsigned long ratio;
++ int busy_retry;
++
++ if (!rung->pages_to_scan) {
++ i++;
++ continue;
++ }
++
++ if (!rung->vma_root.num) {
++ rung->pages_to_scan = 0;
++ i++;
++ continue;
++ }
++
++ ratio = rung_real_ratio(rung->cpu_ratio);
++ if (ratio > max_cpu_ratio)
++ max_cpu_ratio = ratio;
++
++ busy_retry = BUSY_RETRY;
++ /*
++ * Do not consider rung_round_finished() here, just used up the
++ * rung->pages_to_scan quota.
++ */
++ while (rung->pages_to_scan && rung->vma_root.num &&
++ likely(!freezing(current))) {
++ int reset = 0;
++
++ slot = rung->current_scan;
++
++ BUG_ON(vma_fully_scanned(slot));
++
++ if (mmsem_batch) {
++ err = 0;
++ } else {
++ err = try_down_read_slot_mmap_sem(slot);
++ }
++
++ if (err == -ENOENT) {
++rm_slot:
++ rung_rm_slot(slot);
++ continue;
++ }
++
++ busy_mm = slot->mm;
++
++ if (err == -EBUSY) {
++ /* skip other vmas on the same mm */
++ do {
++ reset = advance_current_scan(rung);
++ iter = rung->current_scan;
++ busy_retry--;
++ if (iter->vma->vm_mm != busy_mm ||
++ !busy_retry || reset)
++ break;
++ } while (1);
++
++ if (iter->vma->vm_mm != busy_mm) {
++ continue;
++ } else {
++ /* scan round finsished */
++ break;
++ }
++ }
++
++ BUG_ON(!vma_can_enter(slot->vma));
++ if (uksm_test_exit(slot->vma->vm_mm)) {
++ mmsem_batch = 0;
++ up_read(&slot->vma->vm_mm->mmap_sem);
++ goto rm_slot;
++ }
++
++ if (mmsem_batch)
++ mmsem_batch--;
++ else
++ mmsem_batch = UKSM_MMSEM_BATCH;
++
++ /* Ok, we have take the mmap_sem, ready to scan */
++ scan_vma_one_page(slot);
++ rung->pages_to_scan--;
++ vpages++;
++
++ if (rung->current_offset + rung->step > slot->pages - 1
++ || vma_fully_scanned(slot)) {
++ up_read(&slot->vma->vm_mm->mmap_sem);
++ judge_slot(slot);
++ mmsem_batch = 0;
++ } else {
++ rung->current_offset += rung->step;
++ if (!mmsem_batch)
++ up_read(&slot->vma->vm_mm->mmap_sem);
++ }
++
++ busy_retry = BUSY_RETRY;
++ cond_resched();
++ }
++
++ if (mmsem_batch) {
++ up_read(&slot->vma->vm_mm->mmap_sem);
++ mmsem_batch = 0;
++ }
++
++ if (freezing(current))
++ break;
++
++ cond_resched();
++ }
++ end_time = task_sched_runtime(current);
++ delta_exec = end_time - start_time;
++
++ if (freezing(current))
++ return;
++
++ cleanup_vma_slots();
++ uksm_enter_all_slots();
++
++ round_finished = 1;
++ all_rungs_emtpy = 1;
++ for (i = 0; i < SCAN_LADDER_SIZE; i++) {
++ struct scan_rung *rung = &uksm_scan_ladder[i];
++
++ if (rung->vma_root.num) {
++ all_rungs_emtpy = 0;
++ if (!rung_round_finished(rung))
++ round_finished = 0;
++ }
++ }
++
++ if (all_rungs_emtpy)
++ round_finished = 0;
++
++ if (round_finished) {
++ round_update_ladder();
++ uksm_eval_round++;
++
++ if (hash_round_finished() && rshash_adjust()) {
++ /* Reset the unstable root iff hash strength changed */
++ uksm_hash_round++;
++ root_unstable_tree = RB_ROOT;
++ free_all_tree_nodes(&unstable_tree_node_list);
++ }
++
++ /*
++ * A number of pages can hang around indefinitely on per-cpu
++ * pagevecs, raised page count preventing write_protect_page
++ * from merging them. Though it doesn't really matter much,
++ * it is puzzling to see some stuck in pages_volatile until
++ * other activity jostles them out, and they also prevented
++ * LTP's KSM test from succeeding deterministically; so drain
++ * them here (here rather than on entry to uksm_do_scan(),
++ * so we don't IPI too often when pages_to_scan is set low).
++ */
++ lru_add_drain_all();
++ }
++
++
++ if (vpages && delta_exec > 0) {
++ pcost = (unsigned long) delta_exec / vpages;
++ if (likely(uksm_ema_page_time))
++ uksm_ema_page_time = ema(pcost, uksm_ema_page_time);
++ else
++ uksm_ema_page_time = pcost;
++ }
++
++ uksm_calc_scan_pages();
++ uksm_sleep_real = uksm_sleep_jiffies;
++ /* in case of radical cpu bursts, apply the upper bound */
++ end_time = task_sched_runtime(current);
++ if (max_cpu_ratio && end_time > start_time) {
++ scan_time = end_time - start_time;
++ expected_jiffies = msecs_to_jiffies(
++ scan_time_to_sleep(scan_time, max_cpu_ratio));
++
++ if (expected_jiffies > uksm_sleep_real)
++ uksm_sleep_real = expected_jiffies;
++
++ /* We have a 1 second up bound for responsiveness. */
++ if (jiffies_to_msecs(uksm_sleep_real) > MSEC_PER_SEC)
++ uksm_sleep_real = msecs_to_jiffies(1000);
++ }
++
++ return;
++}
++
++static int ksmd_should_run(void)
++{
++ return uksm_run & UKSM_RUN_MERGE;
++}
++
++static int uksm_scan_thread(void *nothing)
++{
++ set_freezable();
++ set_user_nice(current, 5);
++
++ while (!kthread_should_stop()) {
++ mutex_lock(&uksm_thread_mutex);
++ if (ksmd_should_run()) {
++ uksm_do_scan();
++ }
++ mutex_unlock(&uksm_thread_mutex);
++
++ try_to_freeze();
++
++ if (ksmd_should_run()) {
++ schedule_timeout_interruptible(uksm_sleep_real);
++ uksm_sleep_times++;
++ } else {
++ wait_event_freezable(uksm_thread_wait,
++ ksmd_should_run() || kthread_should_stop());
++ }
++ }
++ return 0;
++}
++
++int page_referenced_ksm(struct page *page, struct mem_cgroup *memcg,
++ unsigned long *vm_flags)
++{
++ struct stable_node *stable_node;
++ struct node_vma *node_vma;
++ struct rmap_item *rmap_item;
++ unsigned int mapcount = page_mapcount(page);
++ int referenced = 0;
++ int search_new_forks = 0;
++ unsigned long address;
++
++ VM_BUG_ON(!PageKsm(page));
++ VM_BUG_ON(!PageLocked(page));
++
++ stable_node = page_stable_node(page);
++ if (!stable_node)
++ return 0;
++
++
++again:
++ hlist_for_each_entry(node_vma, &stable_node->hlist, hlist) {
++ hlist_for_each_entry(rmap_item, &node_vma->rmap_hlist, hlist) {
++ struct anon_vma *anon_vma = rmap_item->anon_vma;
++ struct anon_vma_chain *vmac;
++ struct vm_area_struct *vma;
++
++ anon_vma_lock_read(anon_vma);
++ anon_vma_interval_tree_foreach(vmac, &anon_vma->rb_root,
++ 0, ULONG_MAX) {
++
++ vma = vmac->vma;
++ address = get_rmap_addr(rmap_item);
++
++ if (address < vma->vm_start ||
++ address >= vma->vm_end)
++ continue;
++ /*
++ * Initially we examine only the vma which
++ * covers this rmap_item; but later, if there
++ * is still work to do, we examine covering
++ * vmas in other mms: in case they were forked
++ * from the original since ksmd passed.
++ */
++ if ((rmap_item->slot->vma == vma) ==
++ search_new_forks)
++ continue;
++
++ if (memcg &&
++ !mm_match_cgroup(vma->vm_mm, memcg))
++ continue;
++
++ referenced +=
++ page_referenced_one(page, vma,
++ address, &mapcount, vm_flags);
++ if (!search_new_forks || !mapcount)
++ break;
++ }
++
++ anon_vma_unlock_read(anon_vma);
++ if (!mapcount)
++ goto out;
++ }
++ }
++ if (!search_new_forks++)
++ goto again;
++out:
++ return referenced;
++}
++
++int try_to_unmap_ksm(struct page *page, enum ttu_flags flags)
++{
++ struct stable_node *stable_node;
++ struct node_vma *node_vma;
++ struct rmap_item *rmap_item;
++ int ret = SWAP_AGAIN;
++ int search_new_forks = 0;
++ unsigned long address;
++
++ VM_BUG_ON(!PageKsm(page));
++ VM_BUG_ON(!PageLocked(page));
++
++ stable_node = page_stable_node(page);
++ if (!stable_node)
++ return SWAP_FAIL;
++again:
++ hlist_for_each_entry(node_vma, &stable_node->hlist, hlist) {
++ hlist_for_each_entry(rmap_item, &node_vma->rmap_hlist, hlist) {
++ struct anon_vma *anon_vma = rmap_item->anon_vma;
++ struct anon_vma_chain *vmac;
++ struct vm_area_struct *vma;
++
++ anon_vma_lock_read(anon_vma);
++ anon_vma_interval_tree_foreach(vmac, &anon_vma->rb_root,
++ 0, ULONG_MAX) {
++ vma = vmac->vma;
++ address = get_rmap_addr(rmap_item);
++
++ if (address < vma->vm_start ||
++ address >= vma->vm_end)
++ continue;
++ /*
++ * Initially we examine only the vma which
++ * covers this rmap_item; but later, if there
++ * is still work to do, we examine covering
++ * vmas in other mms: in case they were forked
++ * from the original since ksmd passed.
++ */
++ if ((rmap_item->slot->vma == vma) ==
++ search_new_forks)
++ continue;
++
++ ret = try_to_unmap_one(page, vma,
++ address, flags);
++ if (ret != SWAP_AGAIN || !page_mapped(page)) {
++ anon_vma_unlock_read(anon_vma);
++ goto out;
++ }
++ }
++ anon_vma_unlock_read(anon_vma);
++ }
++ }
++ if (!search_new_forks++)
++ goto again;
++out:
++ return ret;
++}
++
++#ifdef CONFIG_MIGRATION
++int rmap_walk_ksm(struct page *page, int (*rmap_one)(struct page *,
++ struct vm_area_struct *, unsigned long, void *), void *arg)
++{
++ struct stable_node *stable_node;
++ struct node_vma *node_vma;
++ struct rmap_item *rmap_item;
++ int ret = SWAP_AGAIN;
++ int search_new_forks = 0;
++ unsigned long address;
++
++ VM_BUG_ON(!PageKsm(page));
++ VM_BUG_ON(!PageLocked(page));
++
++ stable_node = page_stable_node(page);
++ if (!stable_node)
++ return ret;
++again:
++ hlist_for_each_entry(node_vma, &stable_node->hlist, hlist) {
++ hlist_for_each_entry(rmap_item, &node_vma->rmap_hlist, hlist) {
++ struct anon_vma *anon_vma = rmap_item->anon_vma;
++ struct anon_vma_chain *vmac;
++ struct vm_area_struct *vma;
++
++ anon_vma_lock_read(anon_vma);
++ anon_vma_interval_tree_foreach(vmac, &anon_vma->rb_root,
++ 0, ULONG_MAX) {
++ vma = vmac->vma;
++ address = get_rmap_addr(rmap_item);
++
++ if (address < vma->vm_start ||
++ address >= vma->vm_end)
++ continue;
++
++ if ((rmap_item->slot->vma == vma) ==
++ search_new_forks)
++ continue;
++
++ ret = rmap_one(page, vma, address, arg);
++ if (ret != SWAP_AGAIN) {
++ anon_vma_unlock_read(anon_vma);
++ goto out;
++ }
++ }
++ anon_vma_unlock_read(anon_vma);
++ }
++ }
++ if (!search_new_forks++)
++ goto again;
++out:
++ return ret;
++}
++
++/* Common ksm interface but may be specific to uksm */
++void ksm_migrate_page(struct page *newpage, struct page *oldpage)
++{
++ struct stable_node *stable_node;
++
++ VM_BUG_ON(!PageLocked(oldpage));
++ VM_BUG_ON(!PageLocked(newpage));
++ VM_BUG_ON(newpage->mapping != oldpage->mapping);
++
++ stable_node = page_stable_node(newpage);
++ if (stable_node) {
++ VM_BUG_ON(stable_node->kpfn != page_to_pfn(oldpage));
++ stable_node->kpfn = page_to_pfn(newpage);
++ }
++}
++#endif /* CONFIG_MIGRATION */
++
++#ifdef CONFIG_MEMORY_HOTREMOVE
++static struct stable_node *uksm_check_stable_tree(unsigned long start_pfn,
++ unsigned long end_pfn)
++{
++ struct rb_node *node;
++
++ for (node = rb_first(root_stable_treep); node; node = rb_next(node)) {
++ struct stable_node *stable_node;
++
++ stable_node = rb_entry(node, struct stable_node, node);
++ if (stable_node->kpfn >= start_pfn &&
++ stable_node->kpfn < end_pfn)
++ return stable_node;
++ }
++ return NULL;
++}
++
++static int uksm_memory_callback(struct notifier_block *self,
++ unsigned long action, void *arg)
++{
++ struct memory_notify *mn = arg;
++ struct stable_node *stable_node;
++
++ switch (action) {
++ case MEM_GOING_OFFLINE:
++ /*
++ * Keep it very simple for now: just lock out ksmd and
++ * MADV_UNMERGEABLE while any memory is going offline.
++ * mutex_lock_nested() is necessary because lockdep was alarmed
++ * that here we take uksm_thread_mutex inside notifier chain
++ * mutex, and later take notifier chain mutex inside
++ * uksm_thread_mutex to unlock it. But that's safe because both
++ * are inside mem_hotplug_mutex.
++ */
++ mutex_lock_nested(&uksm_thread_mutex, SINGLE_DEPTH_NESTING);
++ break;
++
++ case MEM_OFFLINE:
++ /*
++ * Most of the work is done by page migration; but there might
++ * be a few stable_nodes left over, still pointing to struct
++ * pages which have been offlined: prune those from the tree.
++ */
++ while ((stable_node = uksm_check_stable_tree(mn->start_pfn,
++ mn->start_pfn + mn->nr_pages)) != NULL)
++ remove_node_from_stable_tree(stable_node, 1, 1);
++ /* fallthrough */
++
++ case MEM_CANCEL_OFFLINE:
++ mutex_unlock(&uksm_thread_mutex);
++ break;
++ }
++ return NOTIFY_OK;
++}
++#endif /* CONFIG_MEMORY_HOTREMOVE */
++
++#ifdef CONFIG_SYSFS
++/*
++ * This all compiles without CONFIG_SYSFS, but is a waste of space.
++ */
++
++#define UKSM_ATTR_RO(_name) \
++ static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
++#define UKSM_ATTR(_name) \
++ static struct kobj_attribute _name##_attr = \
++ __ATTR(_name, 0644, _name##_show, _name##_store)
++
++static ssize_t max_cpu_percentage_show(struct kobject *kobj,
++ struct kobj_attribute *attr, char *buf)
++{
++ return sprintf(buf, "%u\n", uksm_max_cpu_percentage);
++}
++
++static ssize_t max_cpu_percentage_store(struct kobject *kobj,
++ struct kobj_attribute *attr,
++ const char *buf, size_t count)
++{
++ unsigned long max_cpu_percentage;
++ int err;
++
++ err = strict_strtoul(buf, 10, &max_cpu_percentage);
++ if (err || max_cpu_percentage > 100)
++ return -EINVAL;
++
++ if (max_cpu_percentage == 100)
++ max_cpu_percentage = 99;
++ else if (max_cpu_percentage < 10)
++ max_cpu_percentage = 10;
++
++ uksm_max_cpu_percentage = max_cpu_percentage;
++
++ return count;
++}
++UKSM_ATTR(max_cpu_percentage);
++
++static ssize_t sleep_millisecs_show(struct kobject *kobj,
++ struct kobj_attribute *attr, char *buf)
++{
++ return sprintf(buf, "%u\n", jiffies_to_msecs(uksm_sleep_jiffies));
++}
++
++static ssize_t sleep_millisecs_store(struct kobject *kobj,
++ struct kobj_attribute *attr,
++ const char *buf, size_t count)
++{
++ unsigned long msecs;
++ int err;
++
++ err = strict_strtoul(buf, 10, &msecs);
++ if (err || msecs > MSEC_PER_SEC)
++ return -EINVAL;
++
++ uksm_sleep_jiffies = msecs_to_jiffies(msecs);
++ uksm_sleep_saved = uksm_sleep_jiffies;
++
++ return count;
++}
++UKSM_ATTR(sleep_millisecs);
++
++
++static ssize_t cpu_governor_show(struct kobject *kobj,
++ struct kobj_attribute *attr, char *buf)
++{
++ int n = sizeof(uksm_cpu_governor_str) / sizeof(char *);
++ int i;
++
++ buf[0] = '\0';
++ for (i = 0; i < n ; i++) {
++ if (uksm_cpu_governor == i)
++ strcat(buf, "[");
++
++ strcat(buf, uksm_cpu_governor_str[i]);
++
++ if (uksm_cpu_governor == i)
++ strcat(buf, "]");
++
++ strcat(buf, " ");
++ }
++ strcat(buf, "\n");
++
++ return strlen(buf);
++}
++
++static inline void init_performance_values(void)
++{
++ int i;
++ struct scan_rung *rung;
++ struct uksm_cpu_preset_s *preset = uksm_cpu_preset + uksm_cpu_governor;
++
++
++ for (i = 0; i < SCAN_LADDER_SIZE; i++) {
++ rung = uksm_scan_ladder + i;
++ rung->cpu_ratio = preset->cpu_ratio[i];
++ rung->cover_msecs = preset->cover_msecs[i];
++ }
++
++ uksm_max_cpu_percentage = preset->max_cpu;
++}
++
++static ssize_t cpu_governor_store(struct kobject *kobj,
++ struct kobj_attribute *attr,
++ const char *buf, size_t count)
++{
++ int n = sizeof(uksm_cpu_governor_str) / sizeof(char *);
++
++ for (n--; n >=0 ; n--) {
++ if (!strncmp(buf, uksm_cpu_governor_str[n],
++ strlen(uksm_cpu_governor_str[n])))
++ break;
++ }
++
++ if (n < 0)
++ return -EINVAL;
++ else
++ uksm_cpu_governor = n;
++
++ init_performance_values();
++
++ return count;
++}
++UKSM_ATTR(cpu_governor);
++
++static ssize_t run_show(struct kobject *kobj, struct kobj_attribute *attr,
++ char *buf)
++{
++ return sprintf(buf, "%u\n", uksm_run);
++}
++
++static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr,
++ const char *buf, size_t count)
++{
++ int err;
++ unsigned long flags;
++
++ err = strict_strtoul(buf, 10, &flags);
++ if (err || flags > UINT_MAX)
++ return -EINVAL;
++ if (flags > UKSM_RUN_MERGE)
++ return -EINVAL;
++
++ mutex_lock(&uksm_thread_mutex);
++ if (uksm_run != flags) {
++ uksm_run = flags;
++ }
++ mutex_unlock(&uksm_thread_mutex);
++
++ if (flags & UKSM_RUN_MERGE)
++ wake_up_interruptible(&uksm_thread_wait);
++
++ return count;
++}
++UKSM_ATTR(run);
++
++static ssize_t abundant_threshold_show(struct kobject *kobj,
++ struct kobj_attribute *attr, char *buf)
++{
++ return sprintf(buf, "%u\n", uksm_abundant_threshold);
++}
++
++static ssize_t abundant_threshold_store(struct kobject *kobj,
++ struct kobj_attribute *attr,
++ const char *buf, size_t count)
++{
++ int err;
++ unsigned long flags;
++
++ err = strict_strtoul(buf, 10, &flags);
++ if (err || flags > 99)
++ return -EINVAL;
++
++ uksm_abundant_threshold = flags;
++
++ return count;
++}
++UKSM_ATTR(abundant_threshold);
++
++static ssize_t thrash_threshold_show(struct kobject *kobj,
++ struct kobj_attribute *attr, char *buf)
++{
++ return sprintf(buf, "%u\n", uksm_thrash_threshold);
++}
++
++static ssize_t thrash_threshold_store(struct kobject *kobj,
++ struct kobj_attribute *attr,
++ const char *buf, size_t count)
++{
++ int err;
++ unsigned long flags;
++
++ err = strict_strtoul(buf, 10, &flags);
++ if (err || flags > 99)
++ return -EINVAL;
++
++ uksm_thrash_threshold = flags;
++
++ return count;
++}
++UKSM_ATTR(thrash_threshold);
++
++static ssize_t cpu_ratios_show(struct kobject *kobj,
++ struct kobj_attribute *attr, char *buf)
++{
++ int i, size;
++ struct scan_rung *rung;
++ char *p = buf;
++
++ for (i = 0; i < SCAN_LADDER_SIZE; i++) {
++ rung = &uksm_scan_ladder[i];
++
++ if (rung->cpu_ratio > 0)
++ size = sprintf(p, "%d ", rung->cpu_ratio);
++ else
++ size = sprintf(p, "MAX/%d ",
++ TIME_RATIO_SCALE / -rung->cpu_ratio);
++
++ p += size;
++ }
++
++ *p++ = '\n';
++ *p = '\0';
++
++ return p - buf;
++}
++
++static ssize_t cpu_ratios_store(struct kobject *kobj,
++ struct kobj_attribute *attr,
++ const char *buf, size_t count)
++{
++ int i, cpuratios[SCAN_LADDER_SIZE], err;
++ unsigned long value;
++ struct scan_rung *rung;
++ char *p, *end = NULL;
++
++ p = kzalloc(count, GFP_KERNEL);
++ if (!p)
++ return -ENOMEM;
++
++ memcpy(p, buf, count);
++
++ for (i = 0; i < SCAN_LADDER_SIZE; i++) {
++ if (i != SCAN_LADDER_SIZE -1) {
++ end = strchr(p, ' ');
++ if (!end)
++ return -EINVAL;
++
++ *end = '\0';
++ }
++
++ if (strstr(p, "MAX/")) {
++ p = strchr(p, '/') + 1;
++ err = strict_strtoul(p, 10, &value);
++ if (err || value > TIME_RATIO_SCALE || !value)
++ return -EINVAL;
++
++ cpuratios[i] = - (int) (TIME_RATIO_SCALE / value);
++ } else {
++ err = strict_strtoul(p, 10, &value);
++ if (err || value > TIME_RATIO_SCALE || !value)
++ return -EINVAL;
++
++ cpuratios[i] = value;
++ }
++
++ p = end + 1;
++ }
++
++ for (i = 0; i < SCAN_LADDER_SIZE; i++) {
++ rung = &uksm_scan_ladder[i];
++
++ rung->cpu_ratio = cpuratios[i];
++ }
++
++ return count;
++}
++UKSM_ATTR(cpu_ratios);
++
++static ssize_t eval_intervals_show(struct kobject *kobj,
++ struct kobj_attribute *attr, char *buf)
++{
++ int i, size;
++ struct scan_rung *rung;
++ char *p = buf;
++
++ for (i = 0; i < SCAN_LADDER_SIZE; i++) {
++ rung = &uksm_scan_ladder[i];
++ size = sprintf(p, "%u ", rung->cover_msecs);
++ p += size;
++ }
++
++ *p++ = '\n';
++ *p = '\0';
++
++ return p - buf;
++}
++
++static ssize_t eval_intervals_store(struct kobject *kobj,
++ struct kobj_attribute *attr,
++ const char *buf, size_t count)
++{
++ int i, err;
++ unsigned long values[SCAN_LADDER_SIZE];
++ struct scan_rung *rung;
++ char *p, *end = NULL;
++
++ p = kzalloc(count, GFP_KERNEL);
++ if (!p)
++ return -ENOMEM;
++
++ memcpy(p, buf, count);
++
++ for (i = 0; i < SCAN_LADDER_SIZE; i++) {
++ if (i != SCAN_LADDER_SIZE -1) {
++ end = strchr(p, ' ');
++ if (!end)
++ return -EINVAL;
++
++ *end = '\0';
++ }
++
++ err = strict_strtoul(p, 10, &values[i]);
++ if (err)
++ return -EINVAL;
++
++ p = end + 1;
++ }
++
++ for (i = 0; i < SCAN_LADDER_SIZE; i++) {
++ rung = &uksm_scan_ladder[i];
++
++ rung->cover_msecs = values[i];
++ }
++
++ return count;
++}
++UKSM_ATTR(eval_intervals);
++
++static ssize_t ema_per_page_time_show(struct kobject *kobj,
++ struct kobj_attribute *attr, char *buf)
++{
++ return sprintf(buf, "%lu\n", uksm_ema_page_time);
++}
++UKSM_ATTR_RO(ema_per_page_time);
++
++static ssize_t pages_shared_show(struct kobject *kobj,
++ struct kobj_attribute *attr, char *buf)
++{
++ return sprintf(buf, "%lu\n", uksm_pages_shared);
++}
++UKSM_ATTR_RO(pages_shared);
++
++static ssize_t pages_sharing_show(struct kobject *kobj,
++ struct kobj_attribute *attr, char *buf)
++{
++ return sprintf(buf, "%lu\n", uksm_pages_sharing);
++}
++UKSM_ATTR_RO(pages_sharing);
++
++static ssize_t pages_unshared_show(struct kobject *kobj,
++ struct kobj_attribute *attr, char *buf)
++{
++ return sprintf(buf, "%lu\n", uksm_pages_unshared);
++}
++UKSM_ATTR_RO(pages_unshared);
++
++static ssize_t full_scans_show(struct kobject *kobj,
++ struct kobj_attribute *attr, char *buf)
++{
++ return sprintf(buf, "%llu\n", fully_scanned_round);
++}
++UKSM_ATTR_RO(full_scans);
++
++static ssize_t pages_scanned_show(struct kobject *kobj,
++ struct kobj_attribute *attr, char *buf)
++{
++ unsigned long base = 0;
++ u64 delta, ret;
++
++ if (pages_scanned_stored) {
++ base = pages_scanned_base;
++ ret = pages_scanned_stored;
++ delta = uksm_pages_scanned >> base;
++ if (CAN_OVERFLOW_U64(ret, delta)) {
++ ret >>= 1;
++ delta >>= 1;
++ base++;
++ ret += delta;
++ }
++ } else {
++ ret = uksm_pages_scanned;
++ }
++
++ while (ret > ULONG_MAX) {
++ ret >>= 1;
++ base++;
++ }
++
++ if (base)
++ return sprintf(buf, "%lu * 2^%lu\n", (unsigned long)ret, base);
++ else
++ return sprintf(buf, "%lu\n", (unsigned long)ret);
++}
++UKSM_ATTR_RO(pages_scanned);
++
++static ssize_t hash_strength_show(struct kobject *kobj,
++ struct kobj_attribute *attr, char *buf)
++{
++ return sprintf(buf, "%lu\n", hash_strength);
++}
++UKSM_ATTR_RO(hash_strength);
++
++static ssize_t sleep_times_show(struct kobject *kobj,
++ struct kobj_attribute *attr, char *buf)
++{
++ return sprintf(buf, "%llu\n", uksm_sleep_times);
++}
++UKSM_ATTR_RO(sleep_times);
++
++
++static struct attribute *uksm_attrs[] = {
++ &max_cpu_percentage_attr.attr,
++ &sleep_millisecs_attr.attr,
++ &cpu_governor_attr.attr,
++ &run_attr.attr,
++ &ema_per_page_time_attr.attr,
++ &pages_shared_attr.attr,
++ &pages_sharing_attr.attr,
++ &pages_unshared_attr.attr,
++ &full_scans_attr.attr,
++ &pages_scanned_attr.attr,
++ &hash_strength_attr.attr,
++ &sleep_times_attr.attr,
++ &thrash_threshold_attr.attr,
++ &abundant_threshold_attr.attr,
++ &cpu_ratios_attr.attr,
++ &eval_intervals_attr.attr,
++ NULL,
++};
++
++static struct attribute_group uksm_attr_group = {
++ .attrs = uksm_attrs,
++ .name = "uksm",
++};
++#endif /* CONFIG_SYSFS */
++
++static inline void init_scan_ladder(void)
++{
++ int i;
++ struct scan_rung *rung;
++
++ for (i = 0; i < SCAN_LADDER_SIZE; i++) {
++ rung = uksm_scan_ladder + i;
++ slot_tree_init_root(&rung->vma_root);
++ }
++
++ init_performance_values();
++ uksm_calc_scan_pages();
++}
++
++static inline int cal_positive_negative_costs(void)
++{
++ struct page *p1, *p2;
++ unsigned char *addr1, *addr2;
++ unsigned long i, time_start, hash_cost;
++ unsigned long loopnum = 0;
++
++ /*IMPORTANT: volatile is needed to prevent over-optimization by gcc. */
++ volatile u32 hash;
++ volatile int ret;
++
++ p1 = alloc_page(GFP_KERNEL);
++ if (!p1)
++ return -ENOMEM;
++
++ p2 = alloc_page(GFP_KERNEL);
++ if (!p2)
++ return -ENOMEM;
++
++ addr1 = kmap_atomic(p1);
++ addr2 = kmap_atomic(p2);
++ memset(addr1, prandom_u32(), PAGE_SIZE);
++ memcpy(addr2, addr1, PAGE_SIZE);
++
++ /* make sure that the two pages differ in last byte */
++ addr2[PAGE_SIZE-1] = ~addr2[PAGE_SIZE-1];
++ kunmap_atomic(addr2);
++ kunmap_atomic(addr1);
++
++ time_start = jiffies;
++ while (jiffies - time_start < 100) {
++ for (i = 0; i < 100; i++)
++ hash = page_hash(p1, HASH_STRENGTH_FULL, 0);
++ loopnum += 100;
++ }
++ hash_cost = (jiffies - time_start);
++
++ time_start = jiffies;
++ for (i = 0; i < loopnum; i++)
++ ret = pages_identical(p1, p2);
++ memcmp_cost = HASH_STRENGTH_FULL * (jiffies - time_start);
++ memcmp_cost /= hash_cost;
++ printk(KERN_INFO "UKSM: relative memcmp_cost = %lu "
++ "hash=%u cmp_ret=%d.\n",
++ memcmp_cost, hash, ret);
++
++ __free_page(p1);
++ __free_page(p2);
++ return 0;
++}
++
++static int init_zeropage_hash_table(void)
++{
++ struct page *page;
++ char *addr;
++ int i;
++
++ page = alloc_page(GFP_KERNEL);
++ if (!page)
++ return -ENOMEM;
++
++ addr = kmap_atomic(page);
++ memset(addr, 0, PAGE_SIZE);
++ kunmap_atomic(addr);
++
++ zero_hash_table = kmalloc(HASH_STRENGTH_MAX * sizeof(u32),
++ GFP_KERNEL);
++ if (!zero_hash_table)
++ return -ENOMEM;
++
++ for (i = 0; i < HASH_STRENGTH_MAX; i++)
++ zero_hash_table[i] = page_hash(page, i, 0);
++
++ __free_page(page);
++
++ return 0;
++}
++
++static inline int init_random_sampling(void)
++{
++ unsigned long i;
++ random_nums = kmalloc(PAGE_SIZE, GFP_KERNEL);
++ if (!random_nums)
++ return -ENOMEM;
++
++ for (i = 0; i < HASH_STRENGTH_FULL; i++)
++ random_nums[i] = i;
++
++ for (i = 0; i < HASH_STRENGTH_FULL; i++) {
++ unsigned long rand_range, swap_index, tmp;
++
++ rand_range = HASH_STRENGTH_FULL - i;
++ swap_index = i + prandom_u32() % rand_range;
++ tmp = random_nums[i];
++ random_nums[i] = random_nums[swap_index];
++ random_nums[swap_index] = tmp;
++ }
++
++ rshash_state.state = RSHASH_NEW;
++ rshash_state.below_count = 0;
++ rshash_state.lookup_window_index = 0;
++
++ return cal_positive_negative_costs();
++}
++
++static int __init uksm_slab_init(void)
++{
++ rmap_item_cache = UKSM_KMEM_CACHE(rmap_item, 0);
++ if (!rmap_item_cache)
++ goto out;
++
++ stable_node_cache = UKSM_KMEM_CACHE(stable_node, 0);
++ if (!stable_node_cache)
++ goto out_free1;
++
++ node_vma_cache = UKSM_KMEM_CACHE(node_vma, 0);
++ if (!node_vma_cache)
++ goto out_free2;
++
++ vma_slot_cache = UKSM_KMEM_CACHE(vma_slot, 0);
++ if (!vma_slot_cache)
++ goto out_free3;
++
++ tree_node_cache = UKSM_KMEM_CACHE(tree_node, 0);
++ if (!tree_node_cache)
++ goto out_free4;
++
++ return 0;
++
++out_free4:
++ kmem_cache_destroy(vma_slot_cache);
++out_free3:
++ kmem_cache_destroy(node_vma_cache);
++out_free2:
++ kmem_cache_destroy(stable_node_cache);
++out_free1:
++ kmem_cache_destroy(rmap_item_cache);
++out:
++ return -ENOMEM;
++}
++
++static void __init uksm_slab_free(void)
++{
++ kmem_cache_destroy(stable_node_cache);
++ kmem_cache_destroy(rmap_item_cache);
++ kmem_cache_destroy(node_vma_cache);
++ kmem_cache_destroy(vma_slot_cache);
++ kmem_cache_destroy(tree_node_cache);
++}
++
++/* Common interface to ksm, different to it. */
++int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
++ unsigned long end, int advice, unsigned long *vm_flags)
++{
++ int err;
++
++ switch (advice) {
++ case MADV_MERGEABLE:
++ return 0; /* just ignore the advice */
++
++ case MADV_UNMERGEABLE:
++ if (!(*vm_flags & VM_MERGEABLE))
++ return 0; /* just ignore the advice */
++
++ if (vma->anon_vma) {
++ err = unmerge_uksm_pages(vma, start, end);
++ if (err)
++ return err;
++ }
++
++ uksm_remove_vma(vma);
++ *vm_flags &= ~VM_MERGEABLE;
++ break;
++ }
++
++ return 0;
++}
++
++/* Common interface to ksm, actually the same. */
++struct page *ksm_might_need_to_copy(struct page *page,
++ struct vm_area_struct *vma, unsigned long address)
++{
++ struct anon_vma *anon_vma = page_anon_vma(page);
++ struct page *new_page;
++
++ if (PageKsm(page)) {
++ if (page_stable_node(page))
++ return page; /* no need to copy it */
++ } else if (!anon_vma) {
++ return page; /* no need to copy it */
++ } else if (anon_vma->root == vma->anon_vma->root &&
++ page->index == linear_page_index(vma, address)) {
++ return page; /* still no need to copy it */
++ }
++ if (!PageUptodate(page))
++ return page; /* let do_swap_page report the error */
++
++ new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
++ if (new_page) {
++ copy_user_highpage(new_page, page, address, vma);
++
++ SetPageDirty(new_page);
++ __SetPageUptodate(new_page);
++ __set_page_locked(new_page);
++ }
++
++ return new_page;
++}
++
++static int __init uksm_init(void)
++{
++ struct task_struct *uksm_thread;
++ int err;
++
++ uksm_sleep_jiffies = msecs_to_jiffies(100);
++ uksm_sleep_saved = uksm_sleep_jiffies;
++
++ slot_tree_init();
++ init_scan_ladder();
++
++
++ err = init_random_sampling();
++ if (err)
++ goto out_free2;
++
++ err = uksm_slab_init();
++ if (err)
++ goto out_free1;
++
++ err = init_zeropage_hash_table();
++ if (err)
++ goto out_free0;
++
++ uksm_thread = kthread_run(uksm_scan_thread, NULL, "uksmd");
++ if (IS_ERR(uksm_thread)) {
++ printk(KERN_ERR "uksm: creating kthread failed\n");
++ err = PTR_ERR(uksm_thread);
++ goto out_free;
++ }
++
++#ifdef CONFIG_SYSFS
++ err = sysfs_create_group(mm_kobj, &uksm_attr_group);
++ if (err) {
++ printk(KERN_ERR "uksm: register sysfs failed\n");
++ kthread_stop(uksm_thread);
++ goto out_free;
++ }
++#else
++ uksm_run = UKSM_RUN_MERGE; /* no way for user to start it */
++
++#endif /* CONFIG_SYSFS */
++
++#ifdef CONFIG_MEMORY_HOTREMOVE
++ /*
++ * Choose a high priority since the callback takes uksm_thread_mutex:
++ * later callbacks could only be taking locks which nest within that.
++ */
++ hotplug_memory_notifier(uksm_memory_callback, 100);
++#endif
++ return 0;
++
++out_free:
++ kfree(zero_hash_table);
++out_free0:
++ uksm_slab_free();
++out_free1:
++ kfree(random_nums);
++out_free2:
++ kfree(uksm_scan_ladder);
++ return err;
++}
++
++#ifdef MODULE
++module_init(uksm_init)
++#else
++late_initcall(uksm_init);
++#endif
++
+diff --git a/mm/vmstat.c b/mm/vmstat.c
+index f42745e..1796e0c 100644
+--- a/mm/vmstat.c
++++ b/mm/vmstat.c
+@@ -739,6 +739,9 @@ const char * const vmstat_text[] = {
+ #endif
+ "nr_anon_transparent_hugepages",
+ "nr_free_cma",
++#ifdef CONFIG_UKSM
++ "nr_uksm_zero_pages",
++#endif
+ "nr_dirty_threshold",
+ "nr_dirty_background_threshold",
+
diff --git a/sys-kernel/kogaion-sources/files/security/0001-x86-x32-Correct-invalid-use-of-user-timespec-in-the-.patch b/sys-kernel/kogaion-sources/files/security/0001-x86-x32-Correct-invalid-use-of-user-timespec-in-the-.patch
new file mode 100644
index 00000000..3f1bccc8
--- /dev/null
+++ b/sys-kernel/kogaion-sources/files/security/0001-x86-x32-Correct-invalid-use-of-user-timespec-in-the-.patch
@@ -0,0 +1,80 @@
+From 2def2ef2ae5f3990aabdbe8a755911902707d268 Mon Sep 17 00:00:00 2001
+From: PaX Team <pageexec@freemail.hu>
+Date: Thu, 30 Jan 2014 16:59:25 -0800
+Subject: [PATCH] x86, x32: Correct invalid use of user timespec in the kernel
+
+The x32 case for the recvmsg() timout handling is broken:
+
+ asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg,
+ unsigned int vlen, unsigned int flags,
+ struct compat_timespec __user *timeout)
+ {
+ int datagrams;
+ struct timespec ktspec;
+
+ if (flags & MSG_CMSG_COMPAT)
+ return -EINVAL;
+
+ if (COMPAT_USE_64BIT_TIME)
+ return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
+ flags | MSG_CMSG_COMPAT,
+ (struct timespec *) timeout);
+ ...
+
+The timeout pointer parameter is provided by userland (hence the __user
+annotation) but for x32 syscalls it's simply cast to a kernel pointer
+and is passed to __sys_recvmmsg which will eventually directly
+dereference it for both reading and writing. Other callers to
+__sys_recvmmsg properly copy from userland to the kernel first.
+
+The bug was introduced by commit ee4fa23c4bfc ("compat: Use
+COMPAT_USE_64BIT_TIME in net/compat.c") and should affect all kernels
+since 3.4 (and perhaps vendor kernels if they backported x32 support
+along with this code).
+
+Note that CONFIG_X86_X32_ABI gets enabled at build time and only if
+CONFIG_X86_X32 is enabled and ld can build x32 executables.
+
+Other uses of COMPAT_USE_64BIT_TIME seem fine.
+
+This addresses CVE-2014-0038.
+
+Signed-off-by: PaX Team <pageexec@freemail.hu>
+Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
+Cc: <stable@vger.kernel.org> # v3.4+
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+---
+ net/compat.c | 9 ++-------
+ 1 file changed, 2 insertions(+), 7 deletions(-)
+
+diff --git a/net/compat.c b/net/compat.c
+index dd32e34..f50161f 100644
+--- a/net/compat.c
++++ b/net/compat.c
+@@ -780,21 +780,16 @@ asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg,
+ if (flags & MSG_CMSG_COMPAT)
+ return -EINVAL;
+
+- if (COMPAT_USE_64BIT_TIME)
+- return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
+- flags | MSG_CMSG_COMPAT,
+- (struct timespec *) timeout);
+-
+ if (timeout == NULL)
+ return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
+ flags | MSG_CMSG_COMPAT, NULL);
+
+- if (get_compat_timespec(&ktspec, timeout))
++ if (compat_get_timespec(&ktspec, timeout))
+ return -EFAULT;
+
+ datagrams = __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
+ flags | MSG_CMSG_COMPAT, &ktspec);
+- if (datagrams > 0 && put_compat_timespec(&ktspec, timeout))
++ if (datagrams > 0 && compat_put_timespec(&ktspec, timeout))
+ datagrams = -EFAULT;
+
+ return datagrams;
+--
+1.8.5.3
+
diff --git a/sys-kernel/kogaion-sources/kogaion-sources-3.10.25.ebuild b/sys-kernel/kogaion-sources/kogaion-sources-3.10.25.ebuild
new file mode 100644
index 00000000..dedc361b
--- /dev/null
+++ b/sys-kernel/kogaion-sources/kogaion-sources-3.10.25.ebuild
@@ -0,0 +1,55 @@
+# Distributed under the terms of the GNU General Public License v2
+
+EAPI=5
+
+inherit eutils
+
+SLOT=$PVR
+CKV=3.10.25
+KV_FULL=${PN}-${PVR}
+EXTRAVERSION=kogaion
+KERNEL_ARCHIVE="linux-${PV}.tar.xz"
+PATCH_ARCHIVE="linux-${PV}-kogaion.tar.gz"
+RESTRICT="binchecks strip mirror"
+LICENSE="GPL-2"
+KEYWORDS="amd64 x86"
+
+IUSE=""
+DEPEND=""
+RDEPEND=""
+DESCRIPTION="Kogaion Linux Kernel Sources"
+HOMEPAGE="http://www.debian.org"
+SRC_URI="https://www.kernel.org/pub/linux/kernel/v3.x/${KERNEL_ARCHIVE}"
+
+S="$WORKDIR/linux-${CKV}"
+
+pkg_setup() {
+ export REAL_ARCH="$ARCH"
+ unset ARCH ; unset LDFLAGS #will interfere with Makefile if set
+}
+
+src_prepare() {
+
+ for p in $(ls ${FILESDIR}/security); do
+ epatch -p1 "${FILESDIR}/security/$p" || die
+ done
+
+ for p in $(ls ${FILESDIR}/desktop) ; do
+ epatch -p1 "${FILESDIR}/desktop/$p" || die
+ done
+
+ rm -f .config || die
+}
+
+src_compile() {
+ einfo "Preparing kernel sources for real-world use" || die
+ make -s mrproper || die "make mrproper failed"
+}
+
+src_install() {
+ dodir /usr/src/linux-${PV}-kogaion || die
+ insinto /usr/src/linux-${PV}-kogaion || die
+ doins -r "${S}"/* || die
+ cd ${D}/usr/src/linux-${PV}-kogaion || die
+ make mrproper || die
+}