* [PATCH v4] blkcg: allocate struct blkcg_gq outside request queue spinlock
From: Tahsin Erdogan @ 2017-03-05 14:12 UTC (permalink / raw)
To: Tejun Heo, Jens Axboe
Cc: linux-block, David Rientjes, linux-kernel, Tahsin Erdogan
In-Reply-To: <20170304192303.GA29316@wtj.duckdns.org>
blkg_conf_prep() currently calls blkg_lookup_create() while holding
request queue spinlock. This means allocating memory for struct
blkcg_gq has to be made non-blocking. This causes occasional -ENOMEM
failures in call paths like below:
pcpu_alloc+0x68f/0x710
__alloc_percpu_gfp+0xd/0x10
__percpu_counter_init+0x55/0xc0
cfq_pd_alloc+0x3b2/0x4e0
blkg_alloc+0x187/0x230
blkg_create+0x489/0x670
blkg_lookup_create+0x9a/0x230
blkg_conf_prep+0x1fb/0x240
__cfqg_set_weight_device.isra.105+0x5c/0x180
cfq_set_weight_on_dfl+0x69/0xc0
cgroup_file_write+0x39/0x1c0
kernfs_fop_write+0x13f/0x1d0
__vfs_write+0x23/0x120
vfs_write+0xc2/0x1f0
SyS_write+0x44/0xb0
entry_SYSCALL_64_fastpath+0x18/0xad
In the code path above, percpu allocator cannot call vmalloc() due to
queue spinlock.
A failure in this call path gives grief to tools which are trying to
configure io weights. We see occasional failures happen shortly after
reboots even when system is not under any memory pressure. Machines
with a lot of cpus are more vulnerable to this condition.
Update blkg_create() function to temporarily drop the rcu and queue
locks when it is allowed by gfp mask.
Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Tahsin Erdogan <tahsin@google.com>
---
v4:
Simplified error checking in blkg_create()
Factored out __blkg_lookup_create()
v3:
Pushed down all blkg allocations into blkg_create()
v2:
Moved blkg creation into blkg_lookup_create() to avoid duplicating
blkg_lookup_create() logic.
block/blk-cgroup.c | 119 ++++++++++++++++++++++++++++++---------------
include/linux/blk-cgroup.h | 6 ++-
2 files changed, 83 insertions(+), 42 deletions(-)
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 295e98c2c8cc..f7bc93928818 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -164,16 +164,17 @@ struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg,
EXPORT_SYMBOL_GPL(blkg_lookup_slowpath);
/*
- * If @new_blkg is %NULL, this function tries to allocate a new one as
- * necessary using %GFP_NOWAIT. @new_blkg is always consumed on return.
+ * If gfp mask allows blocking, this function temporarily drops rcu and queue
+ * locks to allocate memory.
*/
static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
- struct request_queue *q,
- struct blkcg_gq *new_blkg)
+ struct request_queue *q, gfp_t gfp,
+ const struct blkcg_policy *pol)
{
- struct blkcg_gq *blkg;
+ struct blkcg_gq *blkg = NULL;
struct bdi_writeback_congested *wb_congested;
int i, ret;
+ const bool drop_locks = gfpflags_allow_blocking(gfp);
WARN_ON_ONCE(!rcu_read_lock_held());
lockdep_assert_held(q->queue_lock);
@@ -184,31 +185,52 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
goto err_free_blkg;
}
+ if (drop_locks) {
+ spin_unlock_irq(q->queue_lock);
+ rcu_read_unlock();
+ }
+
wb_congested = wb_congested_get_create(q->backing_dev_info,
- blkcg->css.id,
- GFP_NOWAIT | __GFP_NOWARN);
- if (!wb_congested) {
+ blkcg->css.id, gfp);
+ blkg = blkg_alloc(blkcg, q, gfp);
+
+ if (drop_locks) {
+ rcu_read_lock();
+ spin_lock_irq(q->queue_lock);
+ }
+
+ if (unlikely(!wb_congested || !blkg)) {
ret = -ENOMEM;
- goto err_put_css;
+ goto err_put;
}
- /* allocate */
- if (!new_blkg) {
- new_blkg = blkg_alloc(blkcg, q, GFP_NOWAIT | __GFP_NOWARN);
- if (unlikely(!new_blkg)) {
- ret = -ENOMEM;
- goto err_put_congested;
+ blkg->wb_congested = wb_congested;
+
+ if (pol) {
+ WARN_ON(!drop_locks);
+
+ if (!blkcg_policy_enabled(q, pol)) {
+ ret = -EOPNOTSUPP;
+ goto err_put;
+ }
+
+ /*
+ * This could be the first entry point of blkcg implementation
+ * and we shouldn't allow anything to go through for a bypassing
+ * queue.
+ */
+ if (unlikely(blk_queue_bypass(q))) {
+ ret = blk_queue_dying(q) ? -ENODEV : -EBUSY;
+ goto err_put;
}
}
- blkg = new_blkg;
- blkg->wb_congested = wb_congested;
/* link parent */
if (blkcg_parent(blkcg)) {
blkg->parent = __blkg_lookup(blkcg_parent(blkcg), q, false);
if (WARN_ON_ONCE(!blkg->parent)) {
ret = -ENODEV;
- goto err_put_congested;
+ goto err_put;
}
blkg_get(blkg->parent);
}
@@ -245,44 +267,43 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
blkg_put(blkg);
return ERR_PTR(ret);
-err_put_congested:
- wb_congested_put(wb_congested);
-err_put_css:
+err_put:
+ if (wb_congested)
+ wb_congested_put(wb_congested);
css_put(&blkcg->css);
err_free_blkg:
- blkg_free(new_blkg);
+ blkg_free(blkg);
return ERR_PTR(ret);
}
/**
- * blkg_lookup_create - lookup blkg, try to create one if not there
+ * __blkg_lookup_create - lookup blkg, try to create one if not there
* @blkcg: blkcg of interest
* @q: request_queue of interest
+ * @gfp: gfp mask
+ * @pol: blkcg policy (optional)
*
* Lookup blkg for the @blkcg - @q pair. If it doesn't exist, try to
* create one. blkg creation is performed recursively from blkcg_root such
* that all non-root blkg's have access to the parent blkg. This function
* should be called under RCU read lock and @q->queue_lock.
*
+ * When gfp mask allows blocking, rcu and queue locks may be dropped for
+ * allocating memory. In this case, the locks will be reacquired on return.
+ *
* Returns pointer to the looked up or created blkg on success, ERR_PTR()
* value on error. If @q is dead, returns ERR_PTR(-EINVAL). If @q is not
* dead and bypassing, returns ERR_PTR(-EBUSY).
*/
-struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
- struct request_queue *q)
+struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg,
+ struct request_queue *q, gfp_t gfp,
+ const struct blkcg_policy *pol)
{
struct blkcg_gq *blkg;
WARN_ON_ONCE(!rcu_read_lock_held());
lockdep_assert_held(q->queue_lock);
- /*
- * This could be the first entry point of blkcg implementation and
- * we shouldn't allow anything to go through for a bypassing queue.
- */
- if (unlikely(blk_queue_bypass(q)))
- return ERR_PTR(blk_queue_dying(q) ? -ENODEV : -EBUSY);
-
blkg = __blkg_lookup(blkcg, q, true);
if (blkg)
return blkg;
@@ -300,12 +321,35 @@ struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
parent = blkcg_parent(parent);
}
- blkg = blkg_create(pos, q, NULL);
+ blkg = blkg_create(pos, q, gfp, pol);
if (pos == blkcg || IS_ERR(blkg))
return blkg;
}
}
+/**
+ * blkg_lookup_create - lookup blkg, try to create one if not there
+ *
+ * Performs an initial queue bypass check and then passes control to
+ * __blkg_lookup_create().
+ */
+struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
+ struct request_queue *q, gfp_t gfp,
+ const struct blkcg_policy *pol)
+{
+ WARN_ON_ONCE(!rcu_read_lock_held());
+ lockdep_assert_held(q->queue_lock);
+
+ /*
+ * This could be the first entry point of blkcg implementation and
+ * we shouldn't allow anything to go through for a bypassing queue.
+ */
+ if (unlikely(blk_queue_bypass(q)))
+ return ERR_PTR(blk_queue_dying(q) ? -ENODEV : -EBUSY);
+
+ return __blkg_lookup_create(blkcg, q, gfp, pol);
+}
+
static void blkg_destroy(struct blkcg_gq *blkg)
{
struct blkcg *blkcg = blkg->blkcg;
@@ -816,7 +860,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
spin_lock_irq(disk->queue->queue_lock);
if (blkcg_policy_enabled(disk->queue, pol))
- blkg = blkg_lookup_create(blkcg, disk->queue);
+ blkg = blkg_lookup_create(blkcg, disk->queue, GFP_KERNEL, pol);
else
blkg = ERR_PTR(-EOPNOTSUPP);
@@ -1065,14 +1109,9 @@ int blkcg_init_queue(struct request_queue *q)
preloaded = !radix_tree_preload(GFP_KERNEL);
- /*
- * Make sure the root blkg exists and count the existing blkgs. As
- * @q is bypassing at this point, blkg_lookup_create() can't be
- * used. Open code insertion.
- */
rcu_read_lock();
spin_lock_irq(q->queue_lock);
- blkg = blkg_create(&blkcg_root, q, new_blkg);
+ blkg = __blkg_lookup_create(&blkcg_root, q, GFP_KERNEL, NULL);
spin_unlock_irq(q->queue_lock);
rcu_read_unlock();
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 01b62e7bac74..955903a8f6cb 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -172,7 +172,8 @@ extern struct cgroup_subsys_state * const blkcg_root_css;
struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg,
struct request_queue *q, bool update_hint);
struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
- struct request_queue *q);
+ struct request_queue *q, gfp_t gfp,
+ const struct blkcg_policy *pol);
int blkcg_init_queue(struct request_queue *q);
void blkcg_drain_queue(struct request_queue *q);
void blkcg_exit_queue(struct request_queue *q);
@@ -694,7 +695,8 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q,
blkg = blkg_lookup(blkcg, q);
if (unlikely(!blkg)) {
spin_lock_irq(q->queue_lock);
- blkg = blkg_lookup_create(blkcg, q);
+ blkg = blkg_lookup_create(blkcg, q, GFP_NOWAIT | __GFP_NOWARN,
+ NULL);
if (IS_ERR(blkg))
blkg = NULL;
spin_unlock_irq(q->queue_lock);
--
2.12.0.rc1.440.g5b76565f74-goog
^ permalink raw reply related
* [bdi_unregister] 165a5e22fa BUG kmalloc-512 (Not tainted): Poison overwritten
From: Fengguang Wu @ 2017-03-05 2:24 UTC (permalink / raw)
To: Jan Kara; +Cc: Jens Axboe, linux-block, linux-kernel, LKP
In-Reply-To: <20170305022111.yqtwyd6ognmco4gx@wfg-t540p.sh.intel.com>
[-- Attachment #1: Type: text/plain, Size: 7877 bytes --]
Hi Jan,
Here is another bisect result.
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
commit 165a5e22fafb127ecb5914e12e8c32a1f0d3f820
Author: Jan Kara <jack@suse.cz>
AuthorDate: Wed Feb 8 08:05:56 2017 +0100
Commit: Jens Axboe <axboe@fb.com>
CommitDate: Thu Mar 2 16:08:35 2017 -0700
block: Move bdi_unregister() to del_gendisk()
Commit 6cd18e711dd8 "block: destroy bdi before blockdev is
unregistered." moved bdi unregistration (at that time through
bdi_destroy()) from blk_release_queue() to blk_cleanup_queue() because
it needs to happen before blk_unregister_region() call in del_gendisk()
for MD. SCSI though will free up the device number from sd_remove()
called through a maze of callbacks from device_del() in
__scsi_remove_device() before blk_cleanup_queue() and thus similar races
as described in 6cd18e711dd8 can happen for SCSI as well as reported by
Omar [1].
Moving bdi_unregister() to del_gendisk() works for MD and fixes the
problem for SCSI since del_gendisk() gets called from sd_remove() before
freeing the device number.
This also makes device_add_disk() (calling bdi_register_owner()) more
symmetric with del_gendisk().
[1] http://marc.info/?l=linux-block&m=148554717109098&w=2
Tested-by: Lekshmi Pillai <lekshmicpillai@in.ibm.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jan Kara <jack@suse.cz>
Tested-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
113285b473 blk-mq: ensure that bd->last is always set correctly
165a5e22fa block: Move bdi_unregister() to del_gendisk()
+-------------------------------------------------+------------+------------+
| | 113285b473 | 165a5e22fa |
+-------------------------------------------------+------------+------------+
| boot_successes | 434 | 20 |
| boot_failures | 0 | 116 |
| BUG_kmalloc-#(Not_tainted):Poison_overwritten | 0 | 116 |
| INFO:#-#.First_byte#instead_of | 0 | 116 |
| INFO:Allocated_in_bdi_alloc_node_age=#cpu=#pid= | 0 | 89 |
| INFO:Freed_in_release_bdi_age=#cpu=#pid= | 0 | 89 |
| INFO:Slab#objects=#used=#fp=0x(null)flags= | 0 | 116 |
| INFO:Object#@offset=#fp= | 0 | 116 |
| INFO:Allocated_in_load_elf_phdrs_age=#cpu=#pid= | 0 | 27 |
| INFO:Freed_in_load_elf_binary_age=#cpu=#pid= | 0 | 27 |
+-------------------------------------------------+------------+------------+
[ 2.573289] Write protecting the kernel read-only data: 2676k
[ 2.574616] NX-protecting the kernel data: 5812k
[ 2.576021] rodata_test: all tests were successful
[ 2.583146] random: init: uninitialized urandom read (12 bytes read)
[ 2.596347] =============================================================================
[ 2.596676] BUG kmalloc-512 (Not tainted): Poison overwritten
[ 2.596676] -----------------------------------------------------------------------------
[ 2.596676]
[ 2.596676] Disabling lock debugging due to kernel taint
[ 2.596676] INFO: 0xd6840cac-0xd6840caf. First byte 0x0 instead of 0x6b
[ 2.596676] INFO: Allocated in load_elf_phdrs+0x3e/0x73 age=3 cpu=1 pid=132
[ 2.596676] ___slab_alloc+0x4c6/0x4d8
[ 2.596676] __slab_alloc+0x40/0x6a
[ 2.596676] __kmalloc+0x103/0x1cd
[ 2.596676] load_elf_phdrs+0x3e/0x73
[ 2.596676] load_elf_binary+0xa3/0x9f7
# HH:MM RESULT GOOD BAD GOOD_BUT_DIRTY DIRTY_NOT_BAD
git bisect start a8abdd4d4ab9bb6c1d94c1f528e91e2abe823912 c470abd4fde40ea6a0846a2beab642a578c0b8cd --
git bisect bad f875f31a067fbad4a9f8cc8addcb83ee2890829a # 07:14 B 13 1 13 65 Merge 'linux-review/Georgios-Emmanouil/Staging-wilc1000-linux_wlan-Modified-the-if-else-statement/20170304-041306' into devel-spot-201703041408
git bisect bad 6740c9bb3604e0be1db08f0e81d02843cd057775 # 07:24 B 38 3 37 100 Merge 'linux-review/Arnd-Bergmann/scsi-qedi-fix-build-error-without-DEBUG_FS/20170304-083336' into devel-spot-201703041408
git bisect bad 040c12521a4ab55b0cf5f12494d4d1974f492dbf # 07:38 B 50 1 50 89 Merge 'cifs/for-next' into devel-spot-201703041408
git bisect good feeeb3990cc4b5372c326a235deeb0921938854b # 07:54 G 128 0 1 1 Merge 'linux-review/Alban/mtd-Add-support-for-reading-MTD-devices-via-the-nvmem-API/20170304-124946' into devel-spot-201703041408
git bisect good 8fe21608956d7be06f0d97d352313f7bfd157ac7 # 08:10 G 119 0 0 0 Merge 'linux-review/Wenyou-Yang/can-m_can-support-transmit-frame-in-CAN-FD-format/20170304-123621' into devel-spot-201703041408
git bisect good 16e7a33d62c254187926a64d2c03351ca516677d # 08:24 G 128 0 0 0 Merge 'linux-review/Jeffy-Chen/pinctrl-rockchip-add-irq_enable-irq_disable-ops/20170304-115926' into devel-spot-201703041408
git bisect good c82be9d2244aacea9851c86f4fb74694c99cd874 # 08:30 G 121 0 0 0 Merge tag 'pm-turbostat-4.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
git bisect good ac4e620967bb72f86371154935aa8b67cf54e225 # 08:48 G 122 0 0 0 sched/headers: Remove #include <linux/capability.h> from <linux/sched.h>
git bisect bad 4e66c42c60fdf9be81837857454a41b39bf1b773 # 08:48 B 0 1 49 25 Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse
git bisect good 1827adb11ad26b2290dc9fe2aaf54976b2439865 # 08:57 G 128 0 2 2 Merge branch 'WIP.sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
git bisect good 113285b473824922498d07d7f82459507b9792eb # 09:05 G 127 0 1 1 blk-mq: ensure that bd->last is always set correctly
git bisect good 51f8f3c4e22535933ef9aecc00e9a6069e051b57 # 09:11 G 119 0 0 0 ovl: drop CAP_SYS_RESOURCE from saved mounter's credentials
git bisect bad 590dce2d4934fb909b112cd80c80486362337744 # 09:12 B 12 2 12 19 Merge branch 'rebased-statx' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs
git bisect bad e0d072250a54669dce876d8ade70e417356aae74 # 09:13 B 3 1 3 9 Merge branch 'for-linus' of git://git.kernel.dk/linux-block
git bisect bad 165a5e22fafb127ecb5914e12e8c32a1f0d3f820 # 09:14 B 7 3 7 15 block: Move bdi_unregister() to del_gendisk()
# first bad commit: [165a5e22fafb127ecb5914e12e8c32a1f0d3f820] block: Move bdi_unregister() to del_gendisk()
git bisect good 113285b473824922498d07d7f82459507b9792eb # 09:27 G 364 0 0 1 blk-mq: ensure that bd->last is always set correctly
# extra tests on HEAD of linux-devel/devel-spot-201703041408
git bisect bad a8abdd4d4ab9bb6c1d94c1f528e91e2abe823912 # 09:28 B 1 2 0 10 0day head guard for 'devel-spot-201703041408'
# extra tests on tree/branch linus/master
git bisect bad 2d62e0768d3c28536d4cfe4c40ba1e5e8e442a93 # 09:28 B 1 1 1 20 Merge tag 'kvm-4.11-2' of git://git.kernel.org/pub/scm/virt/kvm/kvm
# extra tests with first bad commit reverted
git bisect good 0895b8dbd26fccb96a39a50cb9796da6f819feb7 # 09:44 G 127 0 0 0 Revert "block: Move bdi_unregister() to del_gendisk()"
# extra tests on tree/branch linux-next/master
git bisect good c0b7b2b33bd17f7155956d0338ce92615da686c9 # 09:50 G 121 0 0 0 Add linux-next specific files for 20170303
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/lkp Intel Corporation
[-- Attachment #2: dmesg-quantal-ivb41-14:20170305091836:i386-randconfig-i0-201709:4.10.0-11089-g165a5e2:346.gz --]
[-- Type: application/gzip, Size: 13345 bytes --]
[-- Attachment #3: reproduce-quantal-ivb41-14:20170305091836:i386-randconfig-i0-201709:4.10.0-11089-g165a5e2:346 --]
[-- Type: text/plain, Size: 886 bytes --]
#!/bin/bash
kernel=$1
initrd=quantal-core-i386.cgz
wget --no-clobber https://github.com/fengguang/reproduce-kernel-bug/raw/master/initrd/$initrd
kvm=(
qemu-system-x86_64
-enable-kvm
-cpu kvm64
-kernel $kernel
-initrd $initrd
-m 369
-smp 2
-device e1000,netdev=net0
-netdev user,id=net0
-boot order=nc
-no-reboot
-watchdog i6300esb
-watchdog-action debug
-rtc base=localtime
-serial stdio
-display none
-monitor null
)
append=(
root=/dev/ram0
hung_task_panic=1
debug
apic=debug
sysrq_always_enabled
rcupdate.rcu_cpu_stall_timeout=100
net.ifnames=0
printk.devkmsg=on
panic=-1
softlockup_panic=1
nmi_watchdog=panic
oops=panic
load_ramdisk=2
prompt_ramdisk=0
drbd.minor_count=8
systemd.log_level=err
ignore_loglevel
earlyprintk=ttyS0,115200
console=ttyS0,115200
console=tty0
vga=normal
rw
drbd.minor_count=8
)
"${kvm[@]}" -append "${append[*]}"
[-- Attachment #4: config-4.10.0-11089-g165a5e2 --]
[-- Type: text/plain, Size: 98519 bytes --]
#
# Automatically generated file; DO NOT EDIT.
# Linux/i386 4.10.0 Kernel Configuration
#
# CONFIG_64BIT is not set
CONFIG_X86_32=y
CONFIG_X86=y
CONFIG_INSTRUCTION_DECODER=y
CONFIG_OUTPUT_FORMAT="elf32-i386"
CONFIG_ARCH_DEFCONFIG="arch/x86/configs/i386_defconfig"
CONFIG_LOCKDEP_SUPPORT=y
CONFIG_STACKTRACE_SUPPORT=y
CONFIG_MMU=y
CONFIG_ARCH_MMAP_RND_BITS_MIN=8
CONFIG_ARCH_MMAP_RND_BITS_MAX=16
CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MIN=8
CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX=16
CONFIG_NEED_DMA_MAP_STATE=y
CONFIG_NEED_SG_DMA_LENGTH=y
CONFIG_GENERIC_ISA_DMA=y
CONFIG_GENERIC_BUG=y
CONFIG_GENERIC_HWEIGHT=y
CONFIG_ARCH_MAY_HAVE_PC_FDC=y
CONFIG_RWSEM_XCHGADD_ALGORITHM=y
CONFIG_GENERIC_CALIBRATE_DELAY=y
CONFIG_ARCH_HAS_CPU_RELAX=y
CONFIG_ARCH_HAS_CACHE_LINE_SIZE=y
CONFIG_HAVE_SETUP_PER_CPU_AREA=y
CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK=y
CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK=y
CONFIG_ARCH_HIBERNATION_POSSIBLE=y
CONFIG_ARCH_SUSPEND_POSSIBLE=y
CONFIG_ARCH_WANT_HUGE_PMD_SHARE=y
CONFIG_ARCH_WANT_GENERAL_HUGETLB=y
CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING=y
CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC=y
CONFIG_X86_32_SMP=y
CONFIG_ARCH_SUPPORTS_UPROBES=y
CONFIG_FIX_EARLYCON_MEM=y
CONFIG_PGTABLE_LEVELS=3
CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
CONFIG_IRQ_WORK=y
CONFIG_BUILDTIME_EXTABLE_SORT=y
CONFIG_THREAD_INFO_IN_TASK=y
#
# General setup
#
CONFIG_INIT_ENV_ARG_LIMIT=32
CONFIG_CROSS_COMPILE=""
# CONFIG_COMPILE_TEST is not set
CONFIG_LOCALVERSION=""
CONFIG_LOCALVERSION_AUTO=y
CONFIG_HAVE_KERNEL_GZIP=y
CONFIG_HAVE_KERNEL_BZIP2=y
CONFIG_HAVE_KERNEL_LZMA=y
CONFIG_HAVE_KERNEL_XZ=y
CONFIG_HAVE_KERNEL_LZO=y
CONFIG_HAVE_KERNEL_LZ4=y
# CONFIG_KERNEL_GZIP is not set
CONFIG_KERNEL_BZIP2=y
# CONFIG_KERNEL_LZMA is not set
# CONFIG_KERNEL_XZ is not set
# CONFIG_KERNEL_LZO is not set
# CONFIG_KERNEL_LZ4 is not set
CONFIG_DEFAULT_HOSTNAME="(none)"
CONFIG_SWAP=y
CONFIG_SYSVIPC=y
CONFIG_SYSVIPC_SYSCTL=y
# CONFIG_POSIX_MQUEUE is not set
CONFIG_CROSS_MEMORY_ATTACH=y
CONFIG_FHANDLE=y
CONFIG_USELIB=y
# CONFIG_AUDIT is not set
CONFIG_HAVE_ARCH_AUDITSYSCALL=y
#
# IRQ subsystem
#
CONFIG_GENERIC_IRQ_PROBE=y
CONFIG_GENERIC_IRQ_SHOW=y
CONFIG_GENERIC_PENDING_IRQ=y
CONFIG_GENERIC_IRQ_CHIP=y
CONFIG_IRQ_DOMAIN=y
CONFIG_IRQ_DOMAIN_HIERARCHY=y
# CONFIG_IRQ_DOMAIN_DEBUG is not set
CONFIG_IRQ_FORCED_THREADING=y
CONFIG_SPARSE_IRQ=y
CONFIG_CLOCKSOURCE_WATCHDOG=y
CONFIG_ARCH_CLOCKSOURCE_DATA=y
CONFIG_CLOCKSOURCE_VALIDATE_LAST_CYCLE=y
CONFIG_GENERIC_TIME_VSYSCALL=y
CONFIG_GENERIC_CLOCKEVENTS=y
CONFIG_GENERIC_CLOCKEVENTS_BROADCAST=y
CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST=y
CONFIG_GENERIC_CMOS_UPDATE=y
#
# Timers subsystem
#
CONFIG_TICK_ONESHOT=y
CONFIG_HZ_PERIODIC=y
# CONFIG_NO_HZ_IDLE is not set
CONFIG_NO_HZ=y
CONFIG_HIGH_RES_TIMERS=y
#
# CPU/Task time and stats accounting
#
CONFIG_TICK_CPU_ACCOUNTING=y
# CONFIG_IRQ_TIME_ACCOUNTING is not set
CONFIG_BSD_PROCESS_ACCT=y
# CONFIG_BSD_PROCESS_ACCT_V3 is not set
# CONFIG_TASKSTATS is not set
#
# RCU Subsystem
#
CONFIG_TREE_RCU=y
# CONFIG_RCU_EXPERT is not set
CONFIG_SRCU=y
# CONFIG_TASKS_RCU is not set
CONFIG_RCU_STALL_COMMON=y
CONFIG_TREE_RCU_TRACE=y
CONFIG_BUILD_BIN2C=y
CONFIG_IKCONFIG=y
CONFIG_IKCONFIG_PROC=y
CONFIG_LOG_BUF_SHIFT=17
CONFIG_LOG_CPU_MAX_BUF_SHIFT=12
CONFIG_PRINTK_SAFE_LOG_BUF_SHIFT=13
CONFIG_HAVE_UNSTABLE_SCHED_CLOCK=y
CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH=y
CONFIG_CGROUPS=y
CONFIG_PAGE_COUNTER=y
CONFIG_MEMCG=y
# CONFIG_MEMCG_SWAP is not set
CONFIG_BLK_CGROUP=y
# CONFIG_DEBUG_BLK_CGROUP is not set
CONFIG_CGROUP_WRITEBACK=y
CONFIG_CGROUP_SCHED=y
CONFIG_FAIR_GROUP_SCHED=y
# CONFIG_CFS_BANDWIDTH is not set
# CONFIG_RT_GROUP_SCHED is not set
CONFIG_CGROUP_PIDS=y
# CONFIG_CGROUP_RDMA is not set
CONFIG_CGROUP_FREEZER=y
CONFIG_CPUSETS=y
# CONFIG_PROC_PID_CPUSET is not set
CONFIG_CGROUP_DEVICE=y
# CONFIG_CGROUP_CPUACCT is not set
CONFIG_CGROUP_PERF=y
# CONFIG_CGROUP_BPF is not set
# CONFIG_CGROUP_DEBUG is not set
# CONFIG_SOCK_CGROUP_DATA is not set
# CONFIG_CHECKPOINT_RESTORE is not set
CONFIG_NAMESPACES=y
CONFIG_UTS_NS=y
# CONFIG_IPC_NS is not set
# CONFIG_USER_NS is not set
CONFIG_PID_NS=y
CONFIG_NET_NS=y
CONFIG_SCHED_AUTOGROUP=y
# CONFIG_SYSFS_DEPRECATED is not set
# CONFIG_RELAY is not set
CONFIG_BLK_DEV_INITRD=y
CONFIG_INITRAMFS_SOURCE=""
CONFIG_RD_GZIP=y
CONFIG_RD_BZIP2=y
CONFIG_RD_LZMA=y
CONFIG_RD_XZ=y
CONFIG_RD_LZO=y
CONFIG_RD_LZ4=y
CONFIG_INITRAMFS_COMPRESSION=".gz"
# CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE is not set
CONFIG_CC_OPTIMIZE_FOR_SIZE=y
CONFIG_SYSCTL=y
CONFIG_ANON_INODES=y
CONFIG_HAVE_UID16=y
CONFIG_SYSCTL_EXCEPTION_TRACE=y
CONFIG_HAVE_PCSPKR_PLATFORM=y
CONFIG_BPF=y
# CONFIG_EXPERT is not set
CONFIG_UID16=y
CONFIG_MULTIUSER=y
CONFIG_SGETMASK_SYSCALL=y
CONFIG_SYSFS_SYSCALL=y
# CONFIG_SYSCTL_SYSCALL is not set
CONFIG_POSIX_TIMERS=y
CONFIG_KALLSYMS=y
# CONFIG_KALLSYMS_ALL is not set
# CONFIG_KALLSYMS_ABSOLUTE_PERCPU is not set
CONFIG_KALLSYMS_BASE_RELATIVE=y
CONFIG_PRINTK=y
CONFIG_PRINTK_NMI=y
CONFIG_BUG=y
CONFIG_ELF_CORE=y
CONFIG_PCSPKR_PLATFORM=y
CONFIG_BASE_FULL=y
CONFIG_FUTEX=y
CONFIG_EPOLL=y
CONFIG_SIGNALFD=y
CONFIG_TIMERFD=y
CONFIG_EVENTFD=y
CONFIG_BPF_SYSCALL=y
CONFIG_SHMEM=y
CONFIG_AIO=y
CONFIG_ADVISE_SYSCALLS=y
CONFIG_USERFAULTFD=y
CONFIG_PCI_QUIRKS=y
CONFIG_MEMBARRIER=y
# CONFIG_EMBEDDED is not set
CONFIG_HAVE_PERF_EVENTS=y
CONFIG_PC104=y
#
# Kernel Performance Events And Counters
#
CONFIG_PERF_EVENTS=y
# CONFIG_DEBUG_PERF_USE_VMALLOC is not set
CONFIG_VM_EVENT_COUNTERS=y
CONFIG_SLUB_DEBUG=y
# CONFIG_SLUB_MEMCG_SYSFS_ON is not set
CONFIG_COMPAT_BRK=y
# CONFIG_SLAB is not set
CONFIG_SLUB=y
CONFIG_SLAB_FREELIST_RANDOM=y
# CONFIG_SLUB_CPU_PARTIAL is not set
# CONFIG_SYSTEM_DATA_VERIFICATION is not set
# CONFIG_PROFILING is not set
CONFIG_TRACEPOINTS=y
CONFIG_HAVE_OPROFILE=y
CONFIG_OPROFILE_NMI_TIMER=y
CONFIG_KPROBES=y
CONFIG_JUMP_LABEL=y
# CONFIG_STATIC_KEYS_SELFTEST is not set
CONFIG_OPTPROBES=y
CONFIG_UPROBES=y
# CONFIG_HAVE_64BIT_ALIGNED_ACCESS is not set
CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS=y
CONFIG_ARCH_USE_BUILTIN_BSWAP=y
CONFIG_KRETPROBES=y
CONFIG_HAVE_IOREMAP_PROT=y
CONFIG_HAVE_KPROBES=y
CONFIG_HAVE_KRETPROBES=y
CONFIG_HAVE_OPTPROBES=y
CONFIG_HAVE_KPROBES_ON_FTRACE=y
CONFIG_HAVE_NMI=y
CONFIG_HAVE_ARCH_TRACEHOOK=y
CONFIG_HAVE_DMA_CONTIGUOUS=y
CONFIG_GENERIC_SMP_IDLE_THREAD=y
CONFIG_ARCH_HAS_SET_MEMORY=y
CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT=y
CONFIG_HAVE_REGS_AND_STACK_ACCESS_API=y
CONFIG_HAVE_CLK=y
CONFIG_HAVE_DMA_API_DEBUG=y
CONFIG_HAVE_HW_BREAKPOINT=y
CONFIG_HAVE_MIXED_BREAKPOINTS_REGS=y
CONFIG_HAVE_USER_RETURN_NOTIFIER=y
CONFIG_HAVE_PERF_EVENTS_NMI=y
CONFIG_HAVE_PERF_REGS=y
CONFIG_HAVE_PERF_USER_STACK_DUMP=y
CONFIG_HAVE_ARCH_JUMP_LABEL=y
CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG=y
CONFIG_HAVE_ALIGNED_STRUCT_PAGE=y
CONFIG_HAVE_CMPXCHG_LOCAL=y
CONFIG_HAVE_CMPXCHG_DOUBLE=y
CONFIG_ARCH_WANT_IPC_PARSE_VERSION=y
CONFIG_HAVE_ARCH_SECCOMP_FILTER=y
CONFIG_HAVE_GCC_PLUGINS=y
# CONFIG_GCC_PLUGINS is not set
CONFIG_HAVE_CC_STACKPROTECTOR=y
CONFIG_CC_STACKPROTECTOR=y
# CONFIG_CC_STACKPROTECTOR_NONE is not set
CONFIG_CC_STACKPROTECTOR_REGULAR=y
# CONFIG_CC_STACKPROTECTOR_STRONG is not set
CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES=y
CONFIG_HAVE_IRQ_TIME_ACCOUNTING=y
CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE=y
CONFIG_HAVE_ARCH_HUGE_VMAP=y
CONFIG_MODULES_USE_ELF_REL=y
CONFIG_ARCH_HAS_ELF_RANDOMIZE=y
CONFIG_HAVE_ARCH_MMAP_RND_BITS=y
CONFIG_HAVE_EXIT_THREAD=y
CONFIG_ARCH_MMAP_RND_BITS=8
CONFIG_HAVE_COPY_THREAD_TLS=y
# CONFIG_HAVE_ARCH_HASH is not set
# CONFIG_ISA_BUS_API is not set
CONFIG_CLONE_BACKWARDS=y
CONFIG_OLD_SIGSUSPEND3=y
CONFIG_OLD_SIGACTION=y
# CONFIG_CPU_NO_EFFICIENT_FFS is not set
# CONFIG_HAVE_ARCH_VMAP_STACK is not set
# CONFIG_ARCH_OPTIONAL_KERNEL_RWX is not set
# CONFIG_ARCH_OPTIONAL_KERNEL_RWX_DEFAULT is not set
CONFIG_ARCH_HAS_STRICT_KERNEL_RWX=y
CONFIG_STRICT_KERNEL_RWX=y
CONFIG_ARCH_HAS_STRICT_MODULE_RWX=y
CONFIG_STRICT_MODULE_RWX=y
#
# GCOV-based kernel profiling
#
# CONFIG_GCOV_KERNEL is not set
CONFIG_ARCH_HAS_GCOV_PROFILE_ALL=y
CONFIG_HAVE_GENERIC_DMA_COHERENT=y
CONFIG_SLABINFO=y
CONFIG_RT_MUTEXES=y
CONFIG_BASE_SMALL=0
CONFIG_MODULES=y
# CONFIG_MODULE_FORCE_LOAD is not set
# CONFIG_MODULE_UNLOAD is not set
# CONFIG_MODVERSIONS is not set
# CONFIG_MODULE_SRCVERSION_ALL is not set
# CONFIG_MODULE_SIG is not set
CONFIG_MODULE_COMPRESS=y
CONFIG_MODULE_COMPRESS_GZIP=y
# CONFIG_MODULE_COMPRESS_XZ is not set
CONFIG_MODULES_TREE_LOOKUP=y
CONFIG_BLOCK=y
CONFIG_LBDAF=y
CONFIG_BLK_SCSI_REQUEST=y
CONFIG_BLK_DEV_BSG=y
CONFIG_BLK_DEV_BSGLIB=y
CONFIG_BLK_DEV_INTEGRITY=y
CONFIG_BLK_DEV_ZONED=y
CONFIG_BLK_DEV_THROTTLING=y
CONFIG_BLK_CMDLINE_PARSER=y
# CONFIG_BLK_WBT is not set
# CONFIG_BLK_DEBUG_FS is not set
CONFIG_BLK_SED_OPAL=y
#
# Partition Types
#
CONFIG_PARTITION_ADVANCED=y
# CONFIG_ACORN_PARTITION is not set
# CONFIG_AIX_PARTITION is not set
# CONFIG_OSF_PARTITION is not set
# CONFIG_AMIGA_PARTITION is not set
CONFIG_ATARI_PARTITION=y
# CONFIG_MAC_PARTITION is not set
# CONFIG_MSDOS_PARTITION is not set
CONFIG_LDM_PARTITION=y
CONFIG_LDM_DEBUG=y
CONFIG_SGI_PARTITION=y
CONFIG_ULTRIX_PARTITION=y
# CONFIG_SUN_PARTITION is not set
# CONFIG_KARMA_PARTITION is not set
CONFIG_EFI_PARTITION=y
# CONFIG_SYSV68_PARTITION is not set
CONFIG_CMDLINE_PARTITION=y
CONFIG_BLK_MQ_PCI=y
#
# IO Schedulers
#
CONFIG_IOSCHED_NOOP=y
# CONFIG_IOSCHED_DEADLINE is not set
CONFIG_IOSCHED_CFQ=y
# CONFIG_CFQ_GROUP_IOSCHED is not set
CONFIG_DEFAULT_CFQ=y
# CONFIG_DEFAULT_NOOP is not set
CONFIG_DEFAULT_IOSCHED="cfq"
CONFIG_MQ_IOSCHED_DEADLINE=m
CONFIG_PADATA=y
CONFIG_ASN1=y
CONFIG_INLINE_SPIN_UNLOCK_IRQ=y
CONFIG_INLINE_READ_UNLOCK=y
CONFIG_INLINE_READ_UNLOCK_IRQ=y
CONFIG_INLINE_WRITE_UNLOCK=y
CONFIG_INLINE_WRITE_UNLOCK_IRQ=y
CONFIG_ARCH_SUPPORTS_ATOMIC_RMW=y
CONFIG_MUTEX_SPIN_ON_OWNER=y
CONFIG_RWSEM_SPIN_ON_OWNER=y
CONFIG_LOCK_SPIN_ON_OWNER=y
CONFIG_ARCH_USE_QUEUED_SPINLOCKS=y
CONFIG_QUEUED_SPINLOCKS=y
CONFIG_ARCH_USE_QUEUED_RWLOCKS=y
CONFIG_QUEUED_RWLOCKS=y
CONFIG_FREEZER=y
#
# Processor type and features
#
CONFIG_ZONE_DMA=y
CONFIG_SMP=y
CONFIG_X86_FEATURE_NAMES=y
CONFIG_X86_FAST_FEATURE_TESTS=y
CONFIG_X86_MPPARSE=y
CONFIG_X86_BIGSMP=y
# CONFIG_GOLDFISH is not set
CONFIG_INTEL_RDT_A=y
# CONFIG_X86_EXTENDED_PLATFORM is not set
CONFIG_X86_INTEL_LPSS=y
CONFIG_X86_AMD_PLATFORM_DEVICE=y
CONFIG_IOSF_MBI=y
# CONFIG_IOSF_MBI_DEBUG is not set
CONFIG_X86_SUPPORTS_MEMORY_FAILURE=y
# CONFIG_X86_32_IRIS is not set
# CONFIG_SCHED_OMIT_FRAME_POINTER is not set
CONFIG_HYPERVISOR_GUEST=y
CONFIG_PARAVIRT=y
# CONFIG_PARAVIRT_DEBUG is not set
# CONFIG_PARAVIRT_SPINLOCKS is not set
# CONFIG_XEN is not set
CONFIG_KVM_GUEST=y
# CONFIG_KVM_DEBUG_FS is not set
# CONFIG_LGUEST_GUEST is not set
# CONFIG_PARAVIRT_TIME_ACCOUNTING is not set
CONFIG_PARAVIRT_CLOCK=y
CONFIG_NO_BOOTMEM=y
# CONFIG_M486 is not set
# CONFIG_M586 is not set
# CONFIG_M586TSC is not set
# CONFIG_M586MMX is not set
CONFIG_M686=y
# CONFIG_MPENTIUMII is not set
# CONFIG_MPENTIUMIII is not set
# CONFIG_MPENTIUMM is not set
# CONFIG_MPENTIUM4 is not set
# CONFIG_MK6 is not set
# CONFIG_MK7 is not set
# CONFIG_MK8 is not set
# CONFIG_MCRUSOE is not set
# CONFIG_MEFFICEON is not set
# CONFIG_MWINCHIPC6 is not set
# CONFIG_MWINCHIP3D is not set
# CONFIG_MELAN is not set
# CONFIG_MGEODEGX1 is not set
# CONFIG_MGEODE_LX is not set
# CONFIG_MCYRIXIII is not set
# CONFIG_MVIAC3_2 is not set
# CONFIG_MVIAC7 is not set
# CONFIG_MCORE2 is not set
# CONFIG_MATOM is not set
CONFIG_X86_GENERIC=y
CONFIG_X86_INTERNODE_CACHE_SHIFT=6
CONFIG_X86_L1_CACHE_SHIFT=6
# CONFIG_X86_PPRO_FENCE is not set
CONFIG_X86_INTEL_USERCOPY=y
CONFIG_X86_USE_PPRO_CHECKSUM=y
CONFIG_X86_TSC=y
CONFIG_X86_CMPXCHG64=y
CONFIG_X86_CMOV=y
CONFIG_X86_MINIMUM_CPU_FAMILY=5
CONFIG_X86_DEBUGCTLMSR=y
CONFIG_CPU_SUP_INTEL=y
CONFIG_CPU_SUP_AMD=y
CONFIG_CPU_SUP_CENTAUR=y
CONFIG_CPU_SUP_TRANSMETA_32=y
CONFIG_HPET_TIMER=y
CONFIG_DMI=y
CONFIG_SWIOTLB=y
CONFIG_IOMMU_HELPER=y
CONFIG_NR_CPUS=32
# CONFIG_SCHED_SMT is not set
# CONFIG_SCHED_MC is not set
# CONFIG_PREEMPT_NONE is not set
CONFIG_PREEMPT_VOLUNTARY=y
# CONFIG_PREEMPT is not set
CONFIG_PREEMPT_COUNT=y
CONFIG_X86_LOCAL_APIC=y
CONFIG_X86_IO_APIC=y
CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS=y
CONFIG_X86_MCE=y
# CONFIG_X86_MCE_INTEL is not set
# CONFIG_X86_MCE_AMD is not set
# CONFIG_X86_ANCIENT_MCE is not set
CONFIG_X86_MCE_INJECT=y
#
# Performance monitoring
#
CONFIG_PERF_EVENTS_INTEL_UNCORE=m
CONFIG_PERF_EVENTS_INTEL_RAPL=m
CONFIG_PERF_EVENTS_INTEL_CSTATE=m
# CONFIG_PERF_EVENTS_AMD_POWER is not set
CONFIG_X86_LEGACY_VM86=y
CONFIG_VM86=y
CONFIG_X86_16BIT=y
CONFIG_X86_ESPFIX32=y
CONFIG_TOSHIBA=y
# CONFIG_I8K is not set
# CONFIG_X86_REBOOTFIXUPS is not set
CONFIG_MICROCODE=y
CONFIG_MICROCODE_INTEL=y
CONFIG_MICROCODE_AMD=y
CONFIG_MICROCODE_OLD_INTERFACE=y
CONFIG_X86_MSR=m
CONFIG_X86_CPUID=y
# CONFIG_NOHIGHMEM is not set
# CONFIG_HIGHMEM4G is not set
CONFIG_HIGHMEM64G=y
CONFIG_PAGE_OFFSET=0xC0000000
CONFIG_HIGHMEM=y
CONFIG_X86_PAE=y
CONFIG_ARCH_PHYS_ADDR_T_64BIT=y
CONFIG_ARCH_DMA_ADDR_T_64BIT=y
CONFIG_NUMA=y
# CONFIG_NUMA_EMU is not set
CONFIG_NODES_SHIFT=3
CONFIG_ARCH_HAVE_MEMORY_PRESENT=y
CONFIG_NEED_NODE_MEMMAP_SIZE=y
CONFIG_ARCH_DISCONTIGMEM_ENABLE=y
CONFIG_ARCH_DISCONTIGMEM_DEFAULT=y
CONFIG_ARCH_SPARSEMEM_ENABLE=y
CONFIG_ARCH_SELECT_MEMORY_MODEL=y
CONFIG_ILLEGAL_POINTER_VALUE=0
CONFIG_SELECT_MEMORY_MODEL=y
CONFIG_DISCONTIGMEM_MANUAL=y
# CONFIG_SPARSEMEM_MANUAL is not set
CONFIG_DISCONTIGMEM=y
CONFIG_FLAT_NODE_MEM_MAP=y
CONFIG_NEED_MULTIPLE_NODES=y
CONFIG_HAVE_MEMORY_PRESENT=y
CONFIG_SPARSEMEM_STATIC=y
CONFIG_HAVE_MEMBLOCK=y
CONFIG_HAVE_MEMBLOCK_NODE_MAP=y
CONFIG_ARCH_DISCARD_MEMBLOCK=y
CONFIG_MEMORY_ISOLATION=y
# CONFIG_HAVE_BOOTMEM_INFO_NODE is not set
CONFIG_SPLIT_PTLOCK_CPUS=4
CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK=y
CONFIG_MEMORY_BALLOON=y
CONFIG_BALLOON_COMPACTION=y
CONFIG_COMPACTION=y
CONFIG_MIGRATION=y
CONFIG_PHYS_ADDR_T_64BIT=y
# CONFIG_BOUNCE is not set
CONFIG_VIRT_TO_BUS=y
# CONFIG_KSM is not set
CONFIG_DEFAULT_MMAP_MIN_ADDR=4096
CONFIG_ARCH_SUPPORTS_MEMORY_FAILURE=y
# CONFIG_MEMORY_FAILURE is not set
CONFIG_TRANSPARENT_HUGEPAGE=y
# CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS is not set
CONFIG_TRANSPARENT_HUGEPAGE_MADVISE=y
CONFIG_TRANSPARENT_HUGE_PAGECACHE=y
# CONFIG_CLEANCACHE is not set
# CONFIG_FRONTSWAP is not set
CONFIG_CMA=y
# CONFIG_CMA_DEBUG is not set
CONFIG_CMA_DEBUGFS=y
CONFIG_CMA_AREAS=7
CONFIG_ZPOOL=y
# CONFIG_ZBUD is not set
CONFIG_Z3FOLD=y
# CONFIG_ZSMALLOC is not set
CONFIG_GENERIC_EARLY_IOREMAP=y
CONFIG_ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT=y
CONFIG_IDLE_PAGE_TRACKING=y
CONFIG_FRAME_VECTOR=y
CONFIG_X86_PMEM_LEGACY_DEVICE=y
CONFIG_X86_PMEM_LEGACY=m
CONFIG_HIGHPTE=y
CONFIG_X86_CHECK_BIOS_CORRUPTION=y
CONFIG_X86_BOOTPARAM_MEMORY_CORRUPTION_CHECK=y
CONFIG_X86_RESERVE_LOW=64
# CONFIG_MATH_EMULATION is not set
CONFIG_MTRR=y
# CONFIG_MTRR_SANITIZER is not set
CONFIG_X86_PAT=y
CONFIG_ARCH_USES_PG_UNCACHED=y
CONFIG_ARCH_RANDOM=y
CONFIG_X86_SMAP=y
# CONFIG_X86_INTEL_MPX is not set
# CONFIG_EFI is not set
# CONFIG_SECCOMP is not set
# CONFIG_HZ_100 is not set
# CONFIG_HZ_250 is not set
CONFIG_HZ_300=y
# CONFIG_HZ_1000 is not set
CONFIG_HZ=300
CONFIG_SCHED_HRTICK=y
# CONFIG_KEXEC is not set
# CONFIG_CRASH_DUMP is not set
CONFIG_PHYSICAL_START=0x1000000
# CONFIG_RELOCATABLE is not set
CONFIG_PHYSICAL_ALIGN=0x200000
CONFIG_HOTPLUG_CPU=y
CONFIG_BOOTPARAM_HOTPLUG_CPU0=y
CONFIG_DEBUG_HOTPLUG_CPU0=y
# CONFIG_COMPAT_VDSO is not set
# CONFIG_CMDLINE_BOOL is not set
CONFIG_MODIFY_LDT_SYSCALL=y
CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y
CONFIG_USE_PERCPU_NUMA_NODE_ID=y
#
# Power management and ACPI options
#
CONFIG_SUSPEND=y
CONFIG_SUSPEND_FREEZER=y
# CONFIG_HIBERNATION is not set
CONFIG_PM_SLEEP=y
CONFIG_PM_SLEEP_SMP=y
CONFIG_PM_AUTOSLEEP=y
# CONFIG_PM_WAKELOCKS is not set
CONFIG_PM=y
# CONFIG_PM_DEBUG is not set
CONFIG_PM_CLK=y
CONFIG_WQ_POWER_EFFICIENT_DEFAULT=y
CONFIG_ACPI=y
CONFIG_ACPI_LEGACY_TABLES_LOOKUP=y
CONFIG_ARCH_MIGHT_HAVE_ACPI_PDC=y
CONFIG_ACPI_SYSTEM_POWER_STATES_SUPPORT=y
CONFIG_ACPI_DEBUGGER=y
CONFIG_ACPI_DEBUGGER_USER=y
CONFIG_ACPI_SLEEP=y
# CONFIG_ACPI_PROCFS_POWER is not set
CONFIG_ACPI_REV_OVERRIDE_POSSIBLE=y
# CONFIG_ACPI_EC_DEBUGFS is not set
CONFIG_ACPI_AC=y
CONFIG_ACPI_BATTERY=y
CONFIG_ACPI_BUTTON=m
# CONFIG_ACPI_VIDEO is not set
CONFIG_ACPI_FAN=m
# CONFIG_ACPI_DOCK is not set
CONFIG_ACPI_CPU_FREQ_PSS=y
CONFIG_ACPI_PROCESSOR_CSTATE=y
CONFIG_ACPI_PROCESSOR_IDLE=y
CONFIG_ACPI_PROCESSOR=m
CONFIG_ACPI_HOTPLUG_CPU=y
CONFIG_ACPI_PROCESSOR_AGGREGATOR=m
# CONFIG_ACPI_THERMAL is not set
# CONFIG_ACPI_NUMA is not set
# CONFIG_ACPI_CUSTOM_DSDT is not set
CONFIG_ARCH_HAS_ACPI_TABLE_UPGRADE=y
CONFIG_ACPI_TABLE_UPGRADE=y
CONFIG_ACPI_DEBUG=y
CONFIG_ACPI_PCI_SLOT=y
CONFIG_X86_PM_TIMER=y
CONFIG_ACPI_CONTAINER=y
CONFIG_ACPI_HOTPLUG_IOAPIC=y
CONFIG_ACPI_SBS=m
CONFIG_ACPI_HED=y
# CONFIG_ACPI_CUSTOM_METHOD is not set
# CONFIG_ACPI_REDUCED_HARDWARE_ONLY is not set
CONFIG_ACPI_NFIT=m
CONFIG_ACPI_NFIT_DEBUG=y
CONFIG_HAVE_ACPI_APEI=y
CONFIG_HAVE_ACPI_APEI_NMI=y
# CONFIG_ACPI_APEI is not set
# CONFIG_DPTF_POWER is not set
CONFIG_ACPI_WATCHDOG=y
# CONFIG_ACPI_EXTLOG is not set
CONFIG_PMIC_OPREGION=y
# CONFIG_CRC_PMIC_OPREGION is not set
# CONFIG_BXT_WC_PMIC_OPREGION is not set
# CONFIG_ACPI_CONFIGFS is not set
# CONFIG_SFI is not set
CONFIG_X86_APM_BOOT=y
CONFIG_APM=m
CONFIG_APM_IGNORE_USER_SUSPEND=y
# CONFIG_APM_DO_ENABLE is not set
# CONFIG_APM_CPU_IDLE is not set
# CONFIG_APM_DISPLAY_BLANK is not set
# CONFIG_APM_ALLOW_INTS is not set
#
# CPU Frequency scaling
#
# CONFIG_CPU_FREQ is not set
#
# CPU Idle
#
CONFIG_CPU_IDLE=y
CONFIG_CPU_IDLE_GOV_LADDER=y
CONFIG_CPU_IDLE_GOV_MENU=y
# CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED is not set
# CONFIG_INTEL_IDLE is not set
#
# Bus options (PCI etc.)
#
CONFIG_PCI=y
# CONFIG_PCI_GOBIOS is not set
# CONFIG_PCI_GOMMCONFIG is not set
CONFIG_PCI_GODIRECT=y
# CONFIG_PCI_GOANY is not set
CONFIG_PCI_DIRECT=y
CONFIG_PCI_DOMAINS=y
CONFIG_PCIEPORTBUS=y
# CONFIG_PCIEAER is not set
CONFIG_PCIEASPM=y
CONFIG_PCIEASPM_DEBUG=y
# CONFIG_PCIEASPM_DEFAULT is not set
# CONFIG_PCIEASPM_POWERSAVE is not set
# CONFIG_PCIEASPM_POWER_SUPERSAVE is not set
CONFIG_PCIEASPM_PERFORMANCE=y
CONFIG_PCIE_PME=y
# CONFIG_PCIE_DPC is not set
# CONFIG_PCIE_PTM is not set
CONFIG_PCI_BUS_ADDR_T_64BIT=y
# CONFIG_PCI_MSI is not set
# CONFIG_PCI_DEBUG is not set
CONFIG_PCI_REALLOC_ENABLE_AUTO=y
# CONFIG_PCI_STUB is not set
# CONFIG_HT_IRQ is not set
CONFIG_PCI_ATS=y
CONFIG_PCI_IOV=y
CONFIG_PCI_PRI=y
# CONFIG_PCI_PASID is not set
CONFIG_PCI_LABEL=y
# CONFIG_HOTPLUG_PCI is not set
#
# DesignWare PCI Core Support
#
#
# PCI host controller drivers
#
CONFIG_ISA_DMA_API=y
# CONFIG_ISA is not set
CONFIG_SCx200=m
CONFIG_SCx200HR_TIMER=m
CONFIG_ALIX=y
# CONFIG_NET5501 is not set
CONFIG_GEOS=y
CONFIG_AMD_NB=y
CONFIG_PCCARD=m
# CONFIG_PCMCIA is not set
CONFIG_CARDBUS=y
#
# PC-card bridges
#
CONFIG_YENTA=m
CONFIG_YENTA_O2=y
CONFIG_YENTA_RICOH=y
CONFIG_YENTA_TI=y
CONFIG_YENTA_ENE_TUNE=y
CONFIG_YENTA_TOSHIBA=y
# CONFIG_RAPIDIO is not set
# CONFIG_X86_SYSFB is not set
#
# Executable file formats / Emulations
#
CONFIG_BINFMT_ELF=y
CONFIG_ELFCORE=y
CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS=y
CONFIG_BINFMT_SCRIPT=y
CONFIG_HAVE_AOUT=y
# CONFIG_BINFMT_AOUT is not set
# CONFIG_BINFMT_MISC is not set
CONFIG_COREDUMP=y
CONFIG_COMPAT_32=y
CONFIG_HAVE_ATOMIC_IOMAP=y
CONFIG_NET=y
#
# Networking options
#
# CONFIG_PACKET is not set
CONFIG_UNIX=y
# CONFIG_UNIX_DIAG is not set
# CONFIG_NET_KEY is not set
# CONFIG_INET is not set
# CONFIG_NETWORK_SECMARK is not set
# CONFIG_NET_PTP_CLASSIFY is not set
# CONFIG_NETWORK_PHY_TIMESTAMPING is not set
# CONFIG_NETFILTER is not set
# CONFIG_ATM is not set
# CONFIG_BRIDGE is not set
# CONFIG_VLAN_8021Q is not set
# CONFIG_DECNET is not set
# CONFIG_LLC2 is not set
# CONFIG_IPX is not set
# CONFIG_ATALK is not set
# CONFIG_X25 is not set
# CONFIG_LAPB is not set
# CONFIG_PHONET is not set
# CONFIG_IEEE802154 is not set
# CONFIG_NET_SCHED is not set
# CONFIG_DCB is not set
# CONFIG_DNS_RESOLVER is not set
# CONFIG_BATMAN_ADV is not set
# CONFIG_VSOCKETS is not set
# CONFIG_NETLINK_DIAG is not set
# CONFIG_MPLS is not set
# CONFIG_HSR is not set
CONFIG_RPS=y
CONFIG_RFS_ACCEL=y
CONFIG_XPS=y
# CONFIG_CGROUP_NET_PRIO is not set
# CONFIG_CGROUP_NET_CLASSID is not set
CONFIG_NET_RX_BUSY_POLL=y
CONFIG_BQL=y
CONFIG_NET_FLOW_LIMIT=y
#
# Network testing
#
# CONFIG_HAMRADIO is not set
# CONFIG_CAN is not set
# CONFIG_IRDA is not set
# CONFIG_BT is not set
# CONFIG_STREAM_PARSER is not set
CONFIG_WIRELESS=y
# CONFIG_CFG80211 is not set
# CONFIG_LIB80211 is not set
#
# CFG80211 needs to be enabled for MAC80211
#
CONFIG_MAC80211_STA_HASH_MAX_SIZE=0
# CONFIG_WIMAX is not set
# CONFIG_RFKILL is not set
# CONFIG_NET_9P is not set
# CONFIG_CAIF is not set
# CONFIG_NFC is not set
# CONFIG_PSAMPLE is not set
# CONFIG_NET_IFE is not set
# CONFIG_LWTUNNEL is not set
# CONFIG_DST_CACHE is not set
# CONFIG_GRO_CELLS is not set
# CONFIG_NET_DEVLINK is not set
CONFIG_MAY_USE_DEVLINK=y
#
# Device Drivers
#
#
# Generic Driver Options
#
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
# CONFIG_DEVTMPFS_MOUNT is not set
CONFIG_STANDALONE=y
CONFIG_PREVENT_FIRMWARE_BUILD=y
CONFIG_FW_LOADER=y
CONFIG_FIRMWARE_IN_KERNEL=y
CONFIG_EXTRA_FIRMWARE=""
CONFIG_FW_LOADER_USER_HELPER=y
# CONFIG_FW_LOADER_USER_HELPER_FALLBACK is not set
CONFIG_ALLOW_DEV_COREDUMP=y
# CONFIG_DEBUG_DRIVER is not set
# CONFIG_DEBUG_DEVRES is not set
# CONFIG_DEBUG_TEST_DRIVER_REMOVE is not set
CONFIG_TEST_ASYNC_DRIVER_PROBE=m
# CONFIG_SYS_HYPERVISOR is not set
# CONFIG_GENERIC_CPU_DEVICES is not set
CONFIG_GENERIC_CPU_AUTOPROBE=y
CONFIG_REGMAP=y
CONFIG_REGMAP_I2C=y
CONFIG_REGMAP_SPI=y
CONFIG_REGMAP_MMIO=y
CONFIG_REGMAP_IRQ=y
CONFIG_DMA_SHARED_BUFFER=y
CONFIG_DMA_FENCE_TRACE=y
# CONFIG_DMA_CMA is not set
#
# Bus devices
#
# CONFIG_CONNECTOR is not set
CONFIG_MTD=m
# CONFIG_MTD_TESTS is not set
CONFIG_MTD_REDBOOT_PARTS=m
CONFIG_MTD_REDBOOT_DIRECTORY_BLOCK=-1
# CONFIG_MTD_REDBOOT_PARTS_UNALLOCATED is not set
# CONFIG_MTD_REDBOOT_PARTS_READONLY is not set
CONFIG_MTD_CMDLINE_PARTS=m
CONFIG_MTD_AR7_PARTS=m
#
# User Modules And Translation Layers
#
CONFIG_MTD_BLKDEVS=m
CONFIG_MTD_BLOCK=m
CONFIG_MTD_BLOCK_RO=m
CONFIG_FTL=m
# CONFIG_NFTL is not set
CONFIG_INFTL=m
# CONFIG_RFD_FTL is not set
CONFIG_SSFDC=m
CONFIG_SM_FTL=m
CONFIG_MTD_OOPS=m
# CONFIG_MTD_SWAP is not set
# CONFIG_MTD_PARTITIONED_MASTER is not set
#
# RAM/ROM/Flash chip drivers
#
CONFIG_MTD_CFI=m
# CONFIG_MTD_JEDECPROBE is not set
CONFIG_MTD_GEN_PROBE=m
CONFIG_MTD_CFI_ADV_OPTIONS=y
# CONFIG_MTD_CFI_NOSWAP is not set
# CONFIG_MTD_CFI_BE_BYTE_SWAP is not set
CONFIG_MTD_CFI_LE_BYTE_SWAP=y
CONFIG_MTD_CFI_GEOMETRY=y
# CONFIG_MTD_MAP_BANK_WIDTH_1 is not set
CONFIG_MTD_MAP_BANK_WIDTH_2=y
CONFIG_MTD_MAP_BANK_WIDTH_4=y
CONFIG_MTD_MAP_BANK_WIDTH_8=y
# CONFIG_MTD_MAP_BANK_WIDTH_16 is not set
# CONFIG_MTD_MAP_BANK_WIDTH_32 is not set
# CONFIG_MTD_CFI_I1 is not set
CONFIG_MTD_CFI_I2=y
# CONFIG_MTD_CFI_I4 is not set
# CONFIG_MTD_CFI_I8 is not set
# CONFIG_MTD_OTP is not set
CONFIG_MTD_CFI_INTELEXT=m
CONFIG_MTD_CFI_AMDSTD=m
CONFIG_MTD_CFI_STAA=m
CONFIG_MTD_CFI_UTIL=m
CONFIG_MTD_RAM=m
CONFIG_MTD_ROM=m
# CONFIG_MTD_ABSENT is not set
#
# Mapping drivers for chip access
#
# CONFIG_MTD_COMPLEX_MAPPINGS is not set
CONFIG_MTD_PHYSMAP=m
# CONFIG_MTD_PHYSMAP_COMPAT is not set
CONFIG_MTD_SCx200_DOCFLASH=m
# CONFIG_MTD_INTEL_VR_NOR is not set
CONFIG_MTD_PLATRAM=m
#
# Self-contained MTD device drivers
#
CONFIG_MTD_PMC551=m
CONFIG_MTD_PMC551_BUGFIX=y
# CONFIG_MTD_PMC551_DEBUG is not set
# CONFIG_MTD_DATAFLASH is not set
CONFIG_MTD_SST25L=m
# CONFIG_MTD_SLRAM is not set
CONFIG_MTD_PHRAM=m
# CONFIG_MTD_MTDRAM is not set
# CONFIG_MTD_BLOCK2MTD is not set
#
# Disk-On-Chip Device Drivers
#
# CONFIG_MTD_DOCG3 is not set
CONFIG_MTD_NAND_ECC=m
CONFIG_MTD_NAND_ECC_SMC=y
CONFIG_MTD_NAND=m
CONFIG_MTD_NAND_BCH=m
CONFIG_MTD_NAND_ECC_BCH=y
# CONFIG_MTD_SM_COMMON is not set
CONFIG_MTD_NAND_DENALI=m
CONFIG_MTD_NAND_DENALI_PCI=m
CONFIG_MTD_NAND_DENALI_SCRATCH_REG_ADDR=0xFF108018
CONFIG_MTD_NAND_GPIO=m
# CONFIG_MTD_NAND_OMAP_BCH_BUILD is not set
CONFIG_MTD_NAND_IDS=m
# CONFIG_MTD_NAND_RICOH is not set
# CONFIG_MTD_NAND_DISKONCHIP is not set
# CONFIG_MTD_NAND_DOCG4 is not set
# CONFIG_MTD_NAND_CAFE is not set
CONFIG_MTD_NAND_CS553X=m
CONFIG_MTD_NAND_NANDSIM=m
CONFIG_MTD_NAND_PLATFORM=m
CONFIG_MTD_NAND_HISI504=m
# CONFIG_MTD_NAND_MTK is not set
CONFIG_MTD_ONENAND=m
# CONFIG_MTD_ONENAND_VERIFY_WRITE is not set
# CONFIG_MTD_ONENAND_GENERIC is not set
CONFIG_MTD_ONENAND_OTP=y
# CONFIG_MTD_ONENAND_2X_PROGRAM is not set
#
# LPDDR & LPDDR2 PCM memory drivers
#
CONFIG_MTD_LPDDR=m
CONFIG_MTD_QINFO_PROBE=m
# CONFIG_MTD_SPI_NOR is not set
# CONFIG_MTD_UBI is not set
# CONFIG_OF is not set
CONFIG_ARCH_MIGHT_HAVE_PC_PARPORT=y
CONFIG_PARPORT=y
CONFIG_PARPORT_PC=y
CONFIG_PARPORT_SERIAL=m
# CONFIG_PARPORT_PC_FIFO is not set
# CONFIG_PARPORT_PC_SUPERIO is not set
# CONFIG_PARPORT_GSC is not set
# CONFIG_PARPORT_AX88796 is not set
# CONFIG_PARPORT_1284 is not set
CONFIG_PNP=y
# CONFIG_PNP_DEBUG_MESSAGES is not set
#
# Protocols
#
CONFIG_PNPACPI=y
CONFIG_BLK_DEV=y
# CONFIG_BLK_DEV_NULL_BLK is not set
CONFIG_BLK_DEV_FD=y
# CONFIG_PARIDE is not set
CONFIG_BLK_DEV_PCIESSD_MTIP32XX=m
CONFIG_BLK_CPQ_CISS_DA=y
# CONFIG_CISS_SCSI_TAPE is not set
# CONFIG_BLK_DEV_DAC960 is not set
CONFIG_BLK_DEV_UMEM=y
# CONFIG_BLK_DEV_COW_COMMON is not set
CONFIG_BLK_DEV_LOOP=m
CONFIG_BLK_DEV_LOOP_MIN_COUNT=8
CONFIG_BLK_DEV_CRYPTOLOOP=m
#
# DRBD disabled because PROC_FS or INET not selected
#
# CONFIG_BLK_DEV_NBD is not set
CONFIG_BLK_DEV_OSD=m
CONFIG_BLK_DEV_SX8=m
CONFIG_BLK_DEV_RAM=m
CONFIG_BLK_DEV_RAM_COUNT=16
CONFIG_BLK_DEV_RAM_SIZE=4096
CONFIG_CDROM_PKTCDVD=y
CONFIG_CDROM_PKTCDVD_BUFFERS=8
CONFIG_CDROM_PKTCDVD_WCACHE=y
# CONFIG_ATA_OVER_ETH is not set
CONFIG_VIRTIO_BLK=y
# CONFIG_VIRTIO_BLK_SCSI is not set
CONFIG_BLK_DEV_HD=y
CONFIG_BLK_DEV_RSXX=m
CONFIG_NVME_CORE=y
CONFIG_BLK_DEV_NVME=y
CONFIG_BLK_DEV_NVME_SCSI=y
# CONFIG_NVME_FC is not set
# CONFIG_NVME_TARGET is not set
#
# Misc devices
#
# CONFIG_SENSORS_LIS3LV02D is not set
CONFIG_AD525X_DPOT=y
CONFIG_AD525X_DPOT_I2C=m
# CONFIG_AD525X_DPOT_SPI is not set
# CONFIG_DUMMY_IRQ is not set
CONFIG_IBM_ASM=m
# CONFIG_PHANTOM is not set
# CONFIG_SGI_IOC4 is not set
CONFIG_TIFM_CORE=m
# CONFIG_TIFM_7XX1 is not set
CONFIG_ICS932S401=y
CONFIG_ENCLOSURE_SERVICES=y
# CONFIG_CS5535_MFGPT is not set
CONFIG_HP_ILO=m
# CONFIG_APDS9802ALS is not set
CONFIG_ISL29003=m
CONFIG_ISL29020=m
# CONFIG_SENSORS_TSL2550 is not set
# CONFIG_SENSORS_BH1770 is not set
# CONFIG_SENSORS_APDS990X is not set
CONFIG_HMC6352=m
# CONFIG_DS1682 is not set
CONFIG_TI_DAC7512=m
# CONFIG_VMWARE_BALLOON is not set
# CONFIG_PCH_PHUB is not set
# CONFIG_USB_SWITCH_FSA9480 is not set
# CONFIG_LATTICE_ECP3_CONFIG is not set
CONFIG_SRAM=y
# CONFIG_PANEL is not set
CONFIG_C2PORT=y
CONFIG_C2PORT_DURAMAR_2150=y
#
# EEPROM support
#
# CONFIG_EEPROM_AT24 is not set
CONFIG_EEPROM_AT25=y
CONFIG_EEPROM_LEGACY=y
# CONFIG_EEPROM_MAX6875 is not set
CONFIG_EEPROM_93CX6=m
CONFIG_EEPROM_93XX46=y
# CONFIG_EEPROM_IDT_89HPESX is not set
CONFIG_CB710_CORE=m
# CONFIG_CB710_DEBUG is not set
CONFIG_CB710_DEBUG_ASSUMPTIONS=y
#
# Texas Instruments shared transport line discipline
#
# CONFIG_TI_ST is not set
# CONFIG_SENSORS_LIS3_I2C is not set
#
# Altera FPGA firmware download module
#
CONFIG_ALTERA_STAPL=m
CONFIG_INTEL_MEI=m
CONFIG_INTEL_MEI_ME=m
CONFIG_INTEL_MEI_TXE=m
CONFIG_VMWARE_VMCI=y
#
# Intel MIC Bus Driver
#
#
# SCIF Bus Driver
#
#
# VOP Bus Driver
#
#
# Intel MIC Host Driver
#
#
# Intel MIC Card Driver
#
#
# SCIF Driver
#
#
# Intel MIC Coprocessor State Management (COSM) Drivers
#
#
# VOP Driver
#
# CONFIG_ECHO is not set
# CONFIG_CXL_BASE is not set
# CONFIG_CXL_AFU_DRIVER_OPS is not set
CONFIG_HAVE_IDE=y
CONFIG_IDE=m
#
# Please see Documentation/ide/ide.txt for help/info on IDE drives
#
CONFIG_IDE_XFER_MODE=y
CONFIG_IDE_TIMINGS=y
CONFIG_IDE_ATAPI=y
# CONFIG_BLK_DEV_IDE_SATA is not set
CONFIG_IDE_GD=m
# CONFIG_IDE_GD_ATA is not set
CONFIG_IDE_GD_ATAPI=y
CONFIG_BLK_DEV_DELKIN=m
# CONFIG_BLK_DEV_IDECD is not set
CONFIG_BLK_DEV_IDETAPE=m
# CONFIG_BLK_DEV_IDEACPI is not set
CONFIG_IDE_TASK_IOCTL=y
CONFIG_IDE_PROC_FS=y
#
# IDE chipset support/bugfixes
#
CONFIG_IDE_GENERIC=m
CONFIG_BLK_DEV_PLATFORM=m
CONFIG_BLK_DEV_CMD640=m
# CONFIG_BLK_DEV_CMD640_ENHANCED is not set
CONFIG_BLK_DEV_IDEPNP=m
CONFIG_BLK_DEV_IDEDMA_SFF=y
#
# PCI IDE chipsets support
#
CONFIG_BLK_DEV_IDEPCI=y
# CONFIG_BLK_DEV_OFFBOARD is not set
# CONFIG_BLK_DEV_GENERIC is not set
# CONFIG_BLK_DEV_OPTI621 is not set
CONFIG_BLK_DEV_RZ1000=m
CONFIG_BLK_DEV_IDEDMA_PCI=y
# CONFIG_BLK_DEV_AEC62XX is not set
# CONFIG_BLK_DEV_ALI15X3 is not set
CONFIG_BLK_DEV_AMD74XX=m
# CONFIG_BLK_DEV_ATIIXP is not set
# CONFIG_BLK_DEV_CMD64X is not set
CONFIG_BLK_DEV_TRIFLEX=m
# CONFIG_BLK_DEV_CS5520 is not set
# CONFIG_BLK_DEV_CS5530 is not set
CONFIG_BLK_DEV_CS5535=m
CONFIG_BLK_DEV_CS5536=m
CONFIG_BLK_DEV_HPT366=m
CONFIG_BLK_DEV_JMICRON=m
CONFIG_BLK_DEV_SC1200=m
CONFIG_BLK_DEV_PIIX=m
CONFIG_BLK_DEV_IT8172=m
CONFIG_BLK_DEV_IT8213=m
CONFIG_BLK_DEV_IT821X=m
CONFIG_BLK_DEV_NS87415=m
CONFIG_BLK_DEV_PDC202XX_OLD=m
# CONFIG_BLK_DEV_PDC202XX_NEW is not set
# CONFIG_BLK_DEV_SVWKS is not set
CONFIG_BLK_DEV_SIIMAGE=m
CONFIG_BLK_DEV_SIS5513=m
CONFIG_BLK_DEV_SLC90E66=m
# CONFIG_BLK_DEV_TRM290 is not set
CONFIG_BLK_DEV_VIA82CXXX=m
CONFIG_BLK_DEV_TC86C001=m
CONFIG_BLK_DEV_IDEDMA=y
#
# SCSI device support
#
CONFIG_SCSI_MOD=y
CONFIG_RAID_ATTRS=m
CONFIG_SCSI=y
CONFIG_SCSI_DMA=y
# CONFIG_SCSI_NETLINK is not set
# CONFIG_SCSI_MQ_DEFAULT is not set
CONFIG_SCSI_PROC_FS=y
#
# SCSI support type (disk, tape, CD-ROM)
#
CONFIG_BLK_DEV_SD=m
CONFIG_CHR_DEV_ST=m
CONFIG_CHR_DEV_OSST=m
# CONFIG_BLK_DEV_SR is not set
CONFIG_CHR_DEV_SG=y
CONFIG_CHR_DEV_SCH=y
# CONFIG_SCSI_ENCLOSURE is not set
# CONFIG_SCSI_CONSTANTS is not set
CONFIG_SCSI_LOGGING=y
# CONFIG_SCSI_SCAN_ASYNC is not set
#
# SCSI Transports
#
CONFIG_SCSI_SPI_ATTRS=y
# CONFIG_SCSI_FC_ATTRS is not set
# CONFIG_SCSI_ISCSI_ATTRS is not set
CONFIG_SCSI_SAS_ATTRS=y
CONFIG_SCSI_SAS_LIBSAS=y
# CONFIG_SCSI_SAS_ATA is not set
CONFIG_SCSI_SAS_HOST_SMP=y
# CONFIG_SCSI_SRP_ATTRS is not set
# CONFIG_SCSI_LOWLEVEL is not set
CONFIG_SCSI_DH=y
CONFIG_SCSI_DH_RDAC=m
CONFIG_SCSI_DH_HP_SW=y
# CONFIG_SCSI_DH_EMC is not set
CONFIG_SCSI_DH_ALUA=y
CONFIG_SCSI_OSD_INITIATOR=m
CONFIG_SCSI_OSD_ULD=m
CONFIG_SCSI_OSD_DPRINT_SENSE=1
# CONFIG_SCSI_OSD_DEBUG is not set
CONFIG_ATA=y
# CONFIG_ATA_NONSTANDARD is not set
# CONFIG_ATA_VERBOSE_ERROR is not set
CONFIG_ATA_ACPI=y
# CONFIG_SATA_ZPODD is not set
# CONFIG_SATA_PMP is not set
#
# Controllers with non-SFF native interface
#
CONFIG_SATA_AHCI=m
CONFIG_SATA_AHCI_PLATFORM=y
CONFIG_SATA_INIC162X=m
# CONFIG_SATA_ACARD_AHCI is not set
# CONFIG_SATA_SIL24 is not set
CONFIG_ATA_SFF=y
#
# SFF controllers with custom DMA interface
#
# CONFIG_PDC_ADMA is not set
CONFIG_SATA_QSTOR=y
CONFIG_SATA_SX4=m
# CONFIG_ATA_BMDMA is not set
#
# PIO-only SFF controllers
#
# CONFIG_PATA_CMD640_PCI is not set
# CONFIG_PATA_MPIIX is not set
CONFIG_PATA_NS87410=y
CONFIG_PATA_OPTI=m
CONFIG_PATA_RZ1000=y
#
# Generic fallback / legacy drivers
#
CONFIG_PATA_LEGACY=m
# CONFIG_MD is not set
CONFIG_TARGET_CORE=y
CONFIG_TCM_IBLOCK=m
CONFIG_TCM_FILEIO=y
# CONFIG_TCM_PSCSI is not set
# CONFIG_LOOPBACK_TARGET is not set
# CONFIG_ISCSI_TARGET is not set
# CONFIG_FUSION is not set
#
# IEEE 1394 (FireWire) support
#
# CONFIG_FIREWIRE is not set
CONFIG_FIREWIRE_NOSY=y
CONFIG_MACINTOSH_DRIVERS=y
# CONFIG_MAC_EMUMOUSEBTN is not set
# CONFIG_NETDEVICES is not set
CONFIG_NVM=y
# CONFIG_NVM_DEBUG is not set
CONFIG_NVM_RRPC=m
#
# Input device support
#
CONFIG_INPUT=y
CONFIG_INPUT_LEDS=m
CONFIG_INPUT_FF_MEMLESS=y
CONFIG_INPUT_POLLDEV=y
# CONFIG_INPUT_SPARSEKMAP is not set
CONFIG_INPUT_MATRIXKMAP=y
#
# Userland interfaces
#
CONFIG_INPUT_MOUSEDEV=y
# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
CONFIG_INPUT_JOYDEV=y
CONFIG_INPUT_EVDEV=m
# CONFIG_INPUT_EVBUG is not set
#
# Input Device Drivers
#
CONFIG_INPUT_KEYBOARD=y
# CONFIG_KEYBOARD_ADC is not set
CONFIG_KEYBOARD_ADP5520=m
CONFIG_KEYBOARD_ADP5588=m
CONFIG_KEYBOARD_ADP5589=m
CONFIG_KEYBOARD_ATKBD=y
CONFIG_KEYBOARD_QT1070=y
# CONFIG_KEYBOARD_QT2160 is not set
# CONFIG_KEYBOARD_LKKBD is not set
# CONFIG_KEYBOARD_GPIO is not set
CONFIG_KEYBOARD_GPIO_POLLED=y
# CONFIG_KEYBOARD_TCA6416 is not set
# CONFIG_KEYBOARD_TCA8418 is not set
CONFIG_KEYBOARD_MATRIX=m
CONFIG_KEYBOARD_LM8323=m
CONFIG_KEYBOARD_LM8333=y
CONFIG_KEYBOARD_MAX7359=m
CONFIG_KEYBOARD_MCS=m
# CONFIG_KEYBOARD_MPR121 is not set
CONFIG_KEYBOARD_NEWTON=y
CONFIG_KEYBOARD_OPENCORES=y
CONFIG_KEYBOARD_SAMSUNG=m
# CONFIG_KEYBOARD_STOWAWAY is not set
CONFIG_KEYBOARD_SUNKBD=m
CONFIG_KEYBOARD_TM2_TOUCHKEY=m
CONFIG_KEYBOARD_TWL4030=y
CONFIG_KEYBOARD_XTKBD=m
CONFIG_KEYBOARD_CROS_EC=m
CONFIG_INPUT_MOUSE=y
CONFIG_MOUSE_PS2=y
CONFIG_MOUSE_PS2_ALPS=y
CONFIG_MOUSE_PS2_BYD=y
CONFIG_MOUSE_PS2_LOGIPS2PP=y
CONFIG_MOUSE_PS2_SYNAPTICS=y
CONFIG_MOUSE_PS2_CYPRESS=y
CONFIG_MOUSE_PS2_LIFEBOOK=y
CONFIG_MOUSE_PS2_TRACKPOINT=y
CONFIG_MOUSE_PS2_ELANTECH=y
# CONFIG_MOUSE_PS2_SENTELIC is not set
CONFIG_MOUSE_PS2_TOUCHKIT=y
CONFIG_MOUSE_PS2_FOCALTECH=y
# CONFIG_MOUSE_PS2_VMMOUSE is not set
# CONFIG_MOUSE_SERIAL is not set
# CONFIG_MOUSE_APPLETOUCH is not set
# CONFIG_MOUSE_BCM5974 is not set
CONFIG_MOUSE_CYAPA=m
CONFIG_MOUSE_ELAN_I2C=m
# CONFIG_MOUSE_ELAN_I2C_I2C is not set
CONFIG_MOUSE_ELAN_I2C_SMBUS=y
CONFIG_MOUSE_VSXXXAA=y
CONFIG_MOUSE_GPIO=m
# CONFIG_MOUSE_SYNAPTICS_I2C is not set
# CONFIG_MOUSE_SYNAPTICS_USB is not set
CONFIG_INPUT_JOYSTICK=y
CONFIG_JOYSTICK_ANALOG=y
# CONFIG_JOYSTICK_A3D is not set
CONFIG_JOYSTICK_ADI=y
# CONFIG_JOYSTICK_COBRA is not set
CONFIG_JOYSTICK_GF2K=m
CONFIG_JOYSTICK_GRIP=y
CONFIG_JOYSTICK_GRIP_MP=m
# CONFIG_JOYSTICK_GUILLEMOT is not set
CONFIG_JOYSTICK_INTERACT=m
# CONFIG_JOYSTICK_SIDEWINDER is not set
CONFIG_JOYSTICK_TMDC=m
# CONFIG_JOYSTICK_IFORCE is not set
CONFIG_JOYSTICK_WARRIOR=m
CONFIG_JOYSTICK_MAGELLAN=m
CONFIG_JOYSTICK_SPACEORB=y
CONFIG_JOYSTICK_SPACEBALL=m
CONFIG_JOYSTICK_STINGER=m
CONFIG_JOYSTICK_TWIDJOY=m
# CONFIG_JOYSTICK_ZHENHUA is not set
CONFIG_JOYSTICK_DB9=y
# CONFIG_JOYSTICK_GAMECON is not set
CONFIG_JOYSTICK_TURBOGRAFX=m
CONFIG_JOYSTICK_AS5011=m
# CONFIG_JOYSTICK_JOYDUMP is not set
# CONFIG_JOYSTICK_XPAD is not set
# CONFIG_JOYSTICK_WALKERA0701 is not set
CONFIG_INPUT_TABLET=y
# CONFIG_TABLET_USB_ACECAD is not set
# CONFIG_TABLET_USB_AIPTEK is not set
# CONFIG_TABLET_USB_HANWANG is not set
# CONFIG_TABLET_USB_KBTAB is not set
# CONFIG_TABLET_USB_PEGASUS is not set
# CONFIG_TABLET_SERIAL_WACOM4 is not set
CONFIG_INPUT_TOUCHSCREEN=y
CONFIG_TOUCHSCREEN_PROPERTIES=y
CONFIG_TOUCHSCREEN_ADS7846=m
CONFIG_TOUCHSCREEN_AD7877=y
CONFIG_TOUCHSCREEN_AD7879=y
CONFIG_TOUCHSCREEN_AD7879_I2C=m
CONFIG_TOUCHSCREEN_AD7879_SPI=m
CONFIG_TOUCHSCREEN_ATMEL_MXT=m
# CONFIG_TOUCHSCREEN_ATMEL_MXT_T37 is not set
CONFIG_TOUCHSCREEN_AUO_PIXCIR=y
CONFIG_TOUCHSCREEN_BU21013=m
# CONFIG_TOUCHSCREEN_CY8CTMG110 is not set
CONFIG_TOUCHSCREEN_CYTTSP_CORE=y
# CONFIG_TOUCHSCREEN_CYTTSP_I2C is not set
# CONFIG_TOUCHSCREEN_CYTTSP_SPI is not set
# CONFIG_TOUCHSCREEN_CYTTSP4_CORE is not set
CONFIG_TOUCHSCREEN_DA9034=m
CONFIG_TOUCHSCREEN_DA9052=m
CONFIG_TOUCHSCREEN_DYNAPRO=y
CONFIG_TOUCHSCREEN_HAMPSHIRE=y
CONFIG_TOUCHSCREEN_EETI=m
CONFIG_TOUCHSCREEN_EGALAX_SERIAL=m
CONFIG_TOUCHSCREEN_FUJITSU=m
CONFIG_TOUCHSCREEN_GOODIX=m
CONFIG_TOUCHSCREEN_ILI210X=y
CONFIG_TOUCHSCREEN_GUNZE=y
CONFIG_TOUCHSCREEN_EKTF2127=y
CONFIG_TOUCHSCREEN_ELAN=y
CONFIG_TOUCHSCREEN_ELO=m
CONFIG_TOUCHSCREEN_WACOM_W8001=m
CONFIG_TOUCHSCREEN_WACOM_I2C=y
CONFIG_TOUCHSCREEN_MAX11801=y
CONFIG_TOUCHSCREEN_MCS5000=y
CONFIG_TOUCHSCREEN_MMS114=m
CONFIG_TOUCHSCREEN_MELFAS_MIP4=y
CONFIG_TOUCHSCREEN_MTOUCH=m
CONFIG_TOUCHSCREEN_INEXIO=m
# CONFIG_TOUCHSCREEN_MK712 is not set
CONFIG_TOUCHSCREEN_PENMOUNT=y
CONFIG_TOUCHSCREEN_EDT_FT5X06=m
CONFIG_TOUCHSCREEN_TOUCHRIGHT=y
# CONFIG_TOUCHSCREEN_TOUCHWIN is not set
# CONFIG_TOUCHSCREEN_TI_AM335X_TSC is not set
CONFIG_TOUCHSCREEN_PIXCIR=y
CONFIG_TOUCHSCREEN_WDT87XX_I2C=y
# CONFIG_TOUCHSCREEN_USB_COMPOSITE is not set
CONFIG_TOUCHSCREEN_MC13783=y
CONFIG_TOUCHSCREEN_TOUCHIT213=m
CONFIG_TOUCHSCREEN_TSC_SERIO=m
CONFIG_TOUCHSCREEN_TSC200X_CORE=y
CONFIG_TOUCHSCREEN_TSC2004=m
CONFIG_TOUCHSCREEN_TSC2005=y
# CONFIG_TOUCHSCREEN_TSC2007 is not set
CONFIG_TOUCHSCREEN_RM_TS=y
CONFIG_TOUCHSCREEN_SILEAD=y
CONFIG_TOUCHSCREEN_SIS_I2C=y
CONFIG_TOUCHSCREEN_ST1232=y
# CONFIG_TOUCHSCREEN_SURFACE3_SPI is not set
# CONFIG_TOUCHSCREEN_SX8654 is not set
CONFIG_TOUCHSCREEN_TPS6507X=y
# CONFIG_TOUCHSCREEN_ZET6223 is not set
# CONFIG_TOUCHSCREEN_ZFORCE is not set
CONFIG_TOUCHSCREEN_ROHM_BU21023=y
# CONFIG_INPUT_MISC is not set
CONFIG_RMI4_CORE=m
CONFIG_RMI4_I2C=m
CONFIG_RMI4_SPI=m
CONFIG_RMI4_SMB=m
# CONFIG_RMI4_F03 is not set
CONFIG_RMI4_2D_SENSOR=y
# CONFIG_RMI4_F11 is not set
CONFIG_RMI4_F12=y
# CONFIG_RMI4_F30 is not set
# CONFIG_RMI4_F34 is not set
CONFIG_RMI4_F54=y
CONFIG_RMI4_F55=y
#
# Hardware I/O ports
#
CONFIG_SERIO=y
CONFIG_ARCH_MIGHT_HAVE_PC_SERIO=y
CONFIG_SERIO_I8042=y
CONFIG_SERIO_SERPORT=m
CONFIG_SERIO_CT82C710=m
CONFIG_SERIO_PARKBD=m
CONFIG_SERIO_PCIPS2=y
CONFIG_SERIO_LIBPS2=y
# CONFIG_SERIO_RAW is not set
CONFIG_SERIO_ALTERA_PS2=m
CONFIG_SERIO_PS2MULT=y
CONFIG_SERIO_ARC_PS2=y
# CONFIG_USERIO is not set
CONFIG_GAMEPORT=y
# CONFIG_GAMEPORT_NS558 is not set
# CONFIG_GAMEPORT_L4 is not set
CONFIG_GAMEPORT_EMU10K1=m
# CONFIG_GAMEPORT_FM801 is not set
#
# Character devices
#
CONFIG_TTY=y
CONFIG_VT=y
CONFIG_CONSOLE_TRANSLATIONS=y
CONFIG_VT_CONSOLE=y
CONFIG_VT_CONSOLE_SLEEP=y
CONFIG_HW_CONSOLE=y
# CONFIG_VT_HW_CONSOLE_BINDING is not set
CONFIG_UNIX98_PTYS=y
# CONFIG_LEGACY_PTYS is not set
# CONFIG_SERIAL_NONSTANDARD is not set
# CONFIG_NOZOMI is not set
# CONFIG_N_GSM is not set
CONFIG_TRACE_ROUTER=m
CONFIG_TRACE_SINK=m
CONFIG_DEVMEM=y
# CONFIG_DEVKMEM is not set
#
# Serial drivers
#
CONFIG_SERIAL_EARLYCON=y
CONFIG_SERIAL_8250=y
# CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set
CONFIG_SERIAL_8250_PNP=y
CONFIG_SERIAL_8250_FINTEK=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_SERIAL_8250_DMA=y
CONFIG_SERIAL_8250_PCI=m
# CONFIG_SERIAL_8250_EXAR is not set
CONFIG_SERIAL_8250_NR_UARTS=4
CONFIG_SERIAL_8250_RUNTIME_UARTS=4
CONFIG_SERIAL_8250_EXTENDED=y
# CONFIG_SERIAL_8250_MANY_PORTS is not set
CONFIG_SERIAL_8250_SHARE_IRQ=y
# CONFIG_SERIAL_8250_DETECT_IRQ is not set
CONFIG_SERIAL_8250_RSA=y
# CONFIG_SERIAL_8250_FSL is not set
CONFIG_SERIAL_8250_DW=m
CONFIG_SERIAL_8250_RT288X=y
CONFIG_SERIAL_8250_LPSS=m
CONFIG_SERIAL_8250_MID=m
CONFIG_SERIAL_8250_MOXA=m
#
# Non-8250 serial port support
#
CONFIG_SERIAL_MAX3100=m
CONFIG_SERIAL_MAX310X=y
CONFIG_SERIAL_UARTLITE=y
CONFIG_SERIAL_UARTLITE_CONSOLE=y
CONFIG_SERIAL_CORE=y
CONFIG_SERIAL_CORE_CONSOLE=y
CONFIG_SERIAL_JSM=m
CONFIG_SERIAL_SCCNXP=y
# CONFIG_SERIAL_SCCNXP_CONSOLE is not set
# CONFIG_SERIAL_SC16IS7XX is not set
CONFIG_SERIAL_TIMBERDALE=m
# CONFIG_SERIAL_ALTERA_JTAGUART is not set
CONFIG_SERIAL_ALTERA_UART=m
CONFIG_SERIAL_ALTERA_UART_MAXPORTS=4
CONFIG_SERIAL_ALTERA_UART_BAUDRATE=115200
# CONFIG_SERIAL_IFX6X60 is not set
CONFIG_SERIAL_PCH_UART=m
CONFIG_SERIAL_ARC=m
CONFIG_SERIAL_ARC_NR_PORTS=1
# CONFIG_SERIAL_RP2 is not set
CONFIG_SERIAL_FSL_LPUART=y
# CONFIG_SERIAL_FSL_LPUART_CONSOLE is not set
# CONFIG_SERIAL_MEN_Z135 is not set
# CONFIG_SERIAL_DEV_BUS is not set
CONFIG_PRINTER=y
CONFIG_LP_CONSOLE=y
CONFIG_PPDEV=m
# CONFIG_VIRTIO_CONSOLE is not set
CONFIG_IPMI_HANDLER=m
# CONFIG_IPMI_PANIC_EVENT is not set
# CONFIG_IPMI_DEVICE_INTERFACE is not set
# CONFIG_IPMI_SI is not set
CONFIG_IPMI_SSIF=m
CONFIG_IPMI_WATCHDOG=m
CONFIG_IPMI_POWEROFF=m
CONFIG_HW_RANDOM=m
# CONFIG_HW_RANDOM_TIMERIOMEM is not set
CONFIG_HW_RANDOM_INTEL=m
# CONFIG_HW_RANDOM_AMD is not set
CONFIG_HW_RANDOM_GEODE=m
CONFIG_HW_RANDOM_VIA=m
CONFIG_HW_RANDOM_VIRTIO=m
CONFIG_HW_RANDOM_TPM=m
CONFIG_NVRAM=y
# CONFIG_R3964 is not set
# CONFIG_APPLICOM is not set
CONFIG_SONYPI=y
CONFIG_MWAVE=m
CONFIG_SCx200_GPIO=m
# CONFIG_PC8736x_GPIO is not set
CONFIG_NSC_GPIO=m
# CONFIG_RAW_DRIVER is not set
# CONFIG_HPET is not set
# CONFIG_HANGCHECK_TIMER is not set
CONFIG_TCG_TPM=y
CONFIG_TCG_TIS_CORE=y
CONFIG_TCG_TIS=y
# CONFIG_TCG_TIS_SPI is not set
# CONFIG_TCG_TIS_I2C_ATMEL is not set
CONFIG_TCG_TIS_I2C_INFINEON=y
# CONFIG_TCG_TIS_I2C_NUVOTON is not set
CONFIG_TCG_NSC=y
CONFIG_TCG_ATMEL=m
CONFIG_TCG_INFINEON=y
CONFIG_TCG_CRB=y
# CONFIG_TCG_VTPM_PROXY is not set
CONFIG_TCG_TIS_ST33ZP24=y
CONFIG_TCG_TIS_ST33ZP24_I2C=y
CONFIG_TCG_TIS_ST33ZP24_SPI=m
# CONFIG_TELCLOCK is not set
CONFIG_DEVPORT=y
# CONFIG_XILLYBUS is not set
#
# I2C support
#
CONFIG_I2C=y
CONFIG_ACPI_I2C_OPREGION=y
CONFIG_I2C_BOARDINFO=y
# CONFIG_I2C_COMPAT is not set
# CONFIG_I2C_CHARDEV is not set
CONFIG_I2C_MUX=y
#
# Multiplexer I2C Chip support
#
# CONFIG_I2C_MUX_GPIO is not set
CONFIG_I2C_MUX_PCA9541=y
CONFIG_I2C_MUX_PCA954x=y
# CONFIG_I2C_MUX_PINCTRL is not set
# CONFIG_I2C_MUX_REG is not set
CONFIG_I2C_MUX_MLXCPLD=m
# CONFIG_I2C_HELPER_AUTO is not set
CONFIG_I2C_SMBUS=y
#
# I2C Algorithms
#
CONFIG_I2C_ALGOBIT=y
CONFIG_I2C_ALGOPCF=y
CONFIG_I2C_ALGOPCA=y
#
# I2C Hardware Bus support
#
#
# PC SMBus host controller drivers
#
# CONFIG_I2C_ALI1535 is not set
CONFIG_I2C_ALI1563=y
CONFIG_I2C_ALI15X3=y
CONFIG_I2C_AMD756=m
CONFIG_I2C_AMD756_S4882=m
CONFIG_I2C_AMD8111=m
CONFIG_I2C_I801=m
CONFIG_I2C_ISCH=m
# CONFIG_I2C_ISMT is not set
# CONFIG_I2C_PIIX4 is not set
# CONFIG_I2C_NFORCE2 is not set
# CONFIG_I2C_SIS5595 is not set
CONFIG_I2C_SIS630=m
CONFIG_I2C_SIS96X=m
# CONFIG_I2C_VIA is not set
CONFIG_I2C_VIAPRO=m
#
# ACPI drivers
#
CONFIG_I2C_SCMI=m
#
# I2C system bus drivers (mostly embedded / system-on-chip)
#
# CONFIG_I2C_CBUS_GPIO is not set
CONFIG_I2C_DESIGNWARE_CORE=m
CONFIG_I2C_DESIGNWARE_PLATFORM=m
CONFIG_I2C_DESIGNWARE_PCI=m
# CONFIG_I2C_DESIGNWARE_BAYTRAIL is not set
CONFIG_I2C_EG20T=y
CONFIG_I2C_EMEV2=y
CONFIG_I2C_GPIO=y
CONFIG_I2C_KEMPLD=m
CONFIG_I2C_OCORES=m
CONFIG_I2C_PCA_PLATFORM=m
# CONFIG_I2C_PXA_PCI is not set
CONFIG_I2C_SIMTEC=m
CONFIG_I2C_XILINX=y
#
# External I2C/SMBus adapter drivers
#
# CONFIG_I2C_PARPORT is not set
CONFIG_I2C_PARPORT_LIGHT=m
# CONFIG_I2C_TAOS_EVM is not set
#
# Other I2C/SMBus bus drivers
#
CONFIG_I2C_CROS_EC_TUNNEL=y
# CONFIG_SCx200_ACB is not set
CONFIG_I2C_STUB=m
CONFIG_I2C_SLAVE=y
CONFIG_I2C_SLAVE_EEPROM=y
# CONFIG_I2C_DEBUG_CORE is not set
# CONFIG_I2C_DEBUG_ALGO is not set
# CONFIG_I2C_DEBUG_BUS is not set
CONFIG_SPI=y
# CONFIG_SPI_DEBUG is not set
CONFIG_SPI_MASTER=y
#
# SPI Master Controller Drivers
#
CONFIG_SPI_ALTERA=m
CONFIG_SPI_AXI_SPI_ENGINE=y
CONFIG_SPI_BITBANG=y
CONFIG_SPI_BUTTERFLY=y
CONFIG_SPI_CADENCE=y
# CONFIG_SPI_DESIGNWARE is not set
# CONFIG_SPI_GPIO is not set
# CONFIG_SPI_LM70_LLP is not set
CONFIG_SPI_OC_TINY=y
CONFIG_SPI_PXA2XX=m
CONFIG_SPI_PXA2XX_PCI=m
# CONFIG_SPI_ROCKCHIP is not set
CONFIG_SPI_SC18IS602=y
CONFIG_SPI_TOPCLIFF_PCH=m
CONFIG_SPI_XCOMM=y
CONFIG_SPI_XILINX=y
CONFIG_SPI_ZYNQMP_GQSPI=y
#
# SPI Protocol Masters
#
# CONFIG_SPI_SPIDEV is not set
CONFIG_SPI_LOOPBACK_TEST=m
CONFIG_SPI_TLE62X0=y
# CONFIG_SPMI is not set
# CONFIG_HSI is not set
#
# PPS support
#
CONFIG_PPS=y
# CONFIG_PPS_DEBUG is not set
# CONFIG_NTP_PPS is not set
#
# PPS clients support
#
CONFIG_PPS_CLIENT_KTIMER=m
# CONFIG_PPS_CLIENT_LDISC is not set
CONFIG_PPS_CLIENT_PARPORT=y
CONFIG_PPS_CLIENT_GPIO=m
#
# PPS generators support
#
#
# PTP clock support
#
# CONFIG_PTP_1588_CLOCK is not set
#
# Enable PHYLIB and NETWORK_PHY_TIMESTAMPING to see the additional clocks.
#
# CONFIG_PTP_1588_CLOCK_PCH is not set
CONFIG_PINCTRL=y
#
# Pin controllers
#
CONFIG_PINMUX=y
CONFIG_PINCONF=y
CONFIG_GENERIC_PINCONF=y
# CONFIG_DEBUG_PINCTRL is not set
CONFIG_PINCTRL_AMD=m
CONFIG_PINCTRL_SX150X=y
# CONFIG_PINCTRL_BAYTRAIL is not set
CONFIG_PINCTRL_CHERRYVIEW=m
CONFIG_PINCTRL_INTEL=y
# CONFIG_PINCTRL_BROXTON is not set
CONFIG_PINCTRL_GEMINILAKE=y
CONFIG_PINCTRL_SUNRISEPOINT=m
CONFIG_GPIOLIB=y
CONFIG_GPIO_ACPI=y
CONFIG_GPIOLIB_IRQCHIP=y
# CONFIG_DEBUG_GPIO is not set
CONFIG_GPIO_SYSFS=y
CONFIG_GPIO_GENERIC=m
CONFIG_GPIO_MAX730X=m
#
# Memory mapped GPIO drivers
#
# CONFIG_GPIO_AMDPT is not set
# CONFIG_GPIO_AXP209 is not set
# CONFIG_GPIO_DWAPB is not set
# CONFIG_GPIO_GENERIC_PLATFORM is not set
# CONFIG_GPIO_ICH is not set
CONFIG_GPIO_LYNXPOINT=m
CONFIG_GPIO_MENZ127=m
# CONFIG_GPIO_MOCKUP is not set
CONFIG_GPIO_VX855=m
#
# Port-mapped I/O GPIO drivers
#
CONFIG_GPIO_F7188X=y
CONFIG_GPIO_IT87=y
# CONFIG_GPIO_SCH is not set
# CONFIG_GPIO_SCH311X is not set
#
# I2C GPIO expanders
#
# CONFIG_GPIO_ADP5588 is not set
CONFIG_GPIO_MAX7300=m
CONFIG_GPIO_MAX732X=m
CONFIG_GPIO_PCA953X=m
CONFIG_GPIO_PCF857X=y
CONFIG_GPIO_SX150X=y
CONFIG_GPIO_TPIC2810=y
#
# MFD GPIO expanders
#
CONFIG_GPIO_ADP5520=y
CONFIG_GPIO_ARIZONA=m
CONFIG_GPIO_CRYSTAL_COVE=y
CONFIG_GPIO_CS5535=y
CONFIG_GPIO_DA9052=m
CONFIG_GPIO_KEMPLD=y
# CONFIG_GPIO_LP873X is not set
# CONFIG_GPIO_PALMAS is not set
# CONFIG_GPIO_TIMBERDALE is not set
CONFIG_GPIO_TPS65086=m
CONFIG_GPIO_TPS65218=m
CONFIG_GPIO_TPS65912=y
CONFIG_GPIO_TWL4030=m
# CONFIG_GPIO_WHISKEY_COVE is not set
CONFIG_GPIO_WM8350=y
#
# PCI GPIO expanders
#
CONFIG_GPIO_AMD8111=m
CONFIG_GPIO_BT8XX=m
CONFIG_GPIO_ML_IOH=y
CONFIG_GPIO_PCH=m
CONFIG_GPIO_PCI_IDIO_16=m
CONFIG_GPIO_RDC321X=y
#
# SPI GPIO expanders
#
# CONFIG_GPIO_MAX7301 is not set
CONFIG_GPIO_MC33880=y
# CONFIG_GPIO_PISOSR is not set
#
# SPI or I2C GPIO expanders
#
CONFIG_W1=y
#
# 1-wire Bus Masters
#
CONFIG_W1_MASTER_MATROX=y
CONFIG_W1_MASTER_DS2482=m
# CONFIG_W1_MASTER_DS1WM is not set
# CONFIG_W1_MASTER_GPIO is not set
#
# 1-wire Slaves
#
CONFIG_W1_SLAVE_THERM=m
CONFIG_W1_SLAVE_SMEM=y
CONFIG_W1_SLAVE_DS2405=m
CONFIG_W1_SLAVE_DS2408=y
# CONFIG_W1_SLAVE_DS2408_READBACK is not set
CONFIG_W1_SLAVE_DS2413=y
CONFIG_W1_SLAVE_DS2406=y
CONFIG_W1_SLAVE_DS2423=y
CONFIG_W1_SLAVE_DS2431=y
CONFIG_W1_SLAVE_DS2433=y
CONFIG_W1_SLAVE_DS2433_CRC=y
CONFIG_W1_SLAVE_DS2760=y
CONFIG_W1_SLAVE_DS2780=y
CONFIG_W1_SLAVE_DS2781=m
CONFIG_W1_SLAVE_DS28E04=y
CONFIG_W1_SLAVE_BQ27000=m
CONFIG_POWER_AVS=y
# CONFIG_POWER_RESET is not set
CONFIG_POWER_SUPPLY=y
# CONFIG_POWER_SUPPLY_DEBUG is not set
CONFIG_PDA_POWER=y
CONFIG_GENERIC_ADC_BATTERY=m
CONFIG_WM8350_POWER=m
CONFIG_TEST_POWER=m
# CONFIG_BATTERY_DS2760 is not set
# CONFIG_BATTERY_DS2780 is not set
CONFIG_BATTERY_DS2781=m
CONFIG_BATTERY_DS2782=y
CONFIG_BATTERY_SBS=y
CONFIG_CHARGER_SBS=y
CONFIG_BATTERY_BQ27XXX=y
# CONFIG_BATTERY_BQ27XXX_I2C is not set
CONFIG_BATTERY_DA9030=m
CONFIG_BATTERY_DA9052=m
# CONFIG_BATTERY_DA9150 is not set
CONFIG_AXP288_FUEL_GAUGE=m
CONFIG_BATTERY_MAX17040=y
CONFIG_BATTERY_MAX17042=m
CONFIG_CHARGER_PCF50633=m
CONFIG_CHARGER_MAX8903=y
CONFIG_CHARGER_TWL4030=m
CONFIG_CHARGER_LP8727=y
CONFIG_CHARGER_GPIO=y
CONFIG_CHARGER_MANAGER=y
CONFIG_CHARGER_MAX14577=m
CONFIG_CHARGER_MAX77693=m
CONFIG_CHARGER_BQ2415X=y
# CONFIG_CHARGER_BQ24190 is not set
CONFIG_CHARGER_BQ24257=y
# CONFIG_CHARGER_BQ24735 is not set
CONFIG_CHARGER_BQ25890=y
CONFIG_CHARGER_SMB347=y
CONFIG_CHARGER_TPS65090=y
CONFIG_CHARGER_TPS65217=m
# CONFIG_BATTERY_GAUGE_LTC2941 is not set
CONFIG_BATTERY_RT5033=y
# CONFIG_CHARGER_RT9455 is not set
# CONFIG_AXP20X_POWER is not set
# CONFIG_HWMON is not set
CONFIG_THERMAL=y
CONFIG_THERMAL_WRITABLE_TRIPS=y
# CONFIG_THERMAL_DEFAULT_GOV_STEP_WISE is not set
# CONFIG_THERMAL_DEFAULT_GOV_FAIR_SHARE is not set
# CONFIG_THERMAL_DEFAULT_GOV_USER_SPACE is not set
CONFIG_THERMAL_DEFAULT_GOV_POWER_ALLOCATOR=y
CONFIG_THERMAL_GOV_FAIR_SHARE=y
CONFIG_THERMAL_GOV_STEP_WISE=y
CONFIG_THERMAL_GOV_BANG_BANG=y
# CONFIG_THERMAL_GOV_USER_SPACE is not set
CONFIG_THERMAL_GOV_POWER_ALLOCATOR=y
CONFIG_THERMAL_EMULATION=y
CONFIG_INTEL_POWERCLAMP=m
CONFIG_INTEL_SOC_DTS_IOSF_CORE=y
CONFIG_INTEL_SOC_DTS_THERMAL=y
#
# ACPI INT340X thermal drivers
#
# CONFIG_INT340X_THERMAL is not set
CONFIG_INTEL_BXT_PMIC_THERMAL=m
CONFIG_INTEL_PCH_THERMAL=m
# CONFIG_GENERIC_ADC_THERMAL is not set
CONFIG_WATCHDOG=y
CONFIG_WATCHDOG_CORE=y
# CONFIG_WATCHDOG_NOWAYOUT is not set
# CONFIG_WATCHDOG_SYSFS is not set
#
# Watchdog Device Drivers
#
# CONFIG_SOFT_WATCHDOG is not set
# CONFIG_DA9052_WATCHDOG is not set
# CONFIG_DA9063_WATCHDOG is not set
CONFIG_DA9062_WATCHDOG=m
CONFIG_WDAT_WDT=y
CONFIG_WM8350_WATCHDOG=y
# CONFIG_XILINX_WATCHDOG is not set
CONFIG_ZIIRAVE_WATCHDOG=y
# CONFIG_CADENCE_WATCHDOG is not set
# CONFIG_DW_WATCHDOG is not set
# CONFIG_TWL4030_WATCHDOG is not set
CONFIG_MAX63XX_WATCHDOG=m
# CONFIG_RETU_WATCHDOG is not set
# CONFIG_ACQUIRE_WDT is not set
# CONFIG_ADVANTECH_WDT is not set
CONFIG_ALIM1535_WDT=m
CONFIG_ALIM7101_WDT=m
CONFIG_F71808E_WDT=y
CONFIG_SP5100_TCO=y
# CONFIG_SBC_FITPC2_WATCHDOG is not set
# CONFIG_EUROTECH_WDT is not set
# CONFIG_IB700_WDT is not set
CONFIG_IBMASR=m
CONFIG_WAFER_WDT=y
CONFIG_I6300ESB_WDT=m
CONFIG_IE6XX_WDT=y
# CONFIG_ITCO_WDT is not set
CONFIG_IT8712F_WDT=y
CONFIG_IT87_WDT=y
# CONFIG_HP_WATCHDOG is not set
CONFIG_KEMPLD_WDT=y
# CONFIG_SC1200_WDT is not set
CONFIG_SCx200_WDT=m
CONFIG_PC87413_WDT=y
# CONFIG_NV_TCO is not set
CONFIG_60XX_WDT=m
CONFIG_SBC8360_WDT=y
# CONFIG_SBC7240_WDT is not set
CONFIG_CPU5_WDT=m
# CONFIG_SMSC_SCH311X_WDT is not set
# CONFIG_SMSC37B787_WDT is not set
CONFIG_VIA_WDT=y
CONFIG_W83627HF_WDT=y
# CONFIG_W83877F_WDT is not set
CONFIG_W83977F_WDT=y
CONFIG_MACHZ_WDT=y
CONFIG_SBC_EPX_C3_WATCHDOG=y
CONFIG_INTEL_MEI_WDT=m
CONFIG_NI903X_WDT=y
# CONFIG_NIC7018_WDT is not set
# CONFIG_MEN_A21_WDT is not set
#
# PCI-based Watchdog Cards
#
CONFIG_PCIPCWATCHDOG=y
# CONFIG_WDTPCI is not set
#
# Watchdog Pretimeout Governors
#
# CONFIG_WATCHDOG_PRETIMEOUT_GOV is not set
CONFIG_SSB_POSSIBLE=y
#
# Sonics Silicon Backplane
#
# CONFIG_SSB is not set
CONFIG_BCMA_POSSIBLE=y
#
# Broadcom specific AMBA
#
CONFIG_BCMA=m
CONFIG_BCMA_HOST_PCI_POSSIBLE=y
# CONFIG_BCMA_HOST_PCI is not set
# CONFIG_BCMA_HOST_SOC is not set
# CONFIG_BCMA_DRIVER_PCI is not set
CONFIG_BCMA_DRIVER_GMAC_CMN=y
# CONFIG_BCMA_DRIVER_GPIO is not set
# CONFIG_BCMA_DEBUG is not set
#
# Multifunction device drivers
#
CONFIG_MFD_CORE=y
CONFIG_MFD_CS5535=y
# CONFIG_MFD_AS3711 is not set
CONFIG_PMIC_ADP5520=y
CONFIG_MFD_AAT2870_CORE=y
# CONFIG_MFD_BCM590XX is not set
CONFIG_MFD_AXP20X=m
CONFIG_MFD_AXP20X_I2C=m
CONFIG_MFD_CROS_EC=y
CONFIG_MFD_CROS_EC_I2C=m
CONFIG_MFD_CROS_EC_SPI=m
CONFIG_PMIC_DA903X=y
CONFIG_PMIC_DA9052=y
CONFIG_MFD_DA9052_SPI=y
# CONFIG_MFD_DA9052_I2C is not set
# CONFIG_MFD_DA9055 is not set
CONFIG_MFD_DA9062=m
CONFIG_MFD_DA9063=m
CONFIG_MFD_DA9150=m
CONFIG_MFD_MC13XXX=y
CONFIG_MFD_MC13XXX_SPI=y
CONFIG_MFD_MC13XXX_I2C=m
CONFIG_HTC_PASIC3=y
CONFIG_HTC_I2CPLD=y
# CONFIG_MFD_INTEL_QUARK_I2C_GPIO is not set
# CONFIG_LPC_ICH is not set
CONFIG_LPC_SCH=y
CONFIG_INTEL_SOC_PMIC=y
CONFIG_MFD_INTEL_LPSS=m
# CONFIG_MFD_INTEL_LPSS_ACPI is not set
CONFIG_MFD_INTEL_LPSS_PCI=m
# CONFIG_MFD_JANZ_CMODIO is not set
CONFIG_MFD_KEMPLD=y
# CONFIG_MFD_88PM800 is not set
# CONFIG_MFD_88PM805 is not set
# CONFIG_MFD_88PM860X is not set
CONFIG_MFD_MAX14577=m
CONFIG_MFD_MAX77693=m
CONFIG_MFD_MAX77843=y
CONFIG_MFD_MAX8907=m
# CONFIG_MFD_MAX8925 is not set
# CONFIG_MFD_MAX8997 is not set
CONFIG_MFD_MAX8998=y
CONFIG_MFD_MT6397=y
# CONFIG_MFD_MENF21BMC is not set
# CONFIG_EZX_PCAP is not set
CONFIG_MFD_RETU=m
CONFIG_MFD_PCF50633=m
CONFIG_PCF50633_ADC=m
CONFIG_PCF50633_GPIO=m
CONFIG_MFD_RDC321X=y
# CONFIG_MFD_RTSX_PCI is not set
CONFIG_MFD_RT5033=y
# CONFIG_MFD_RC5T583 is not set
CONFIG_MFD_SEC_CORE=y
CONFIG_MFD_SI476X_CORE=m
CONFIG_MFD_SM501=y
# CONFIG_MFD_SM501_GPIO is not set
CONFIG_MFD_SKY81452=m
# CONFIG_MFD_SMSC is not set
# CONFIG_ABX500_CORE is not set
CONFIG_MFD_SYSCON=y
CONFIG_MFD_TI_AM335X_TSCADC=m
# CONFIG_MFD_LP3943 is not set
CONFIG_MFD_LP8788=y
CONFIG_MFD_PALMAS=y
CONFIG_TPS6105X=m
# CONFIG_TPS65010 is not set
# CONFIG_TPS6507X is not set
CONFIG_MFD_TPS65086=y
CONFIG_MFD_TPS65090=y
CONFIG_MFD_TPS65217=m
CONFIG_MFD_TI_LP873X=y
CONFIG_MFD_TPS65218=m
# CONFIG_MFD_TPS6586X is not set
# CONFIG_MFD_TPS65910 is not set
CONFIG_MFD_TPS65912=y
CONFIG_MFD_TPS65912_I2C=y
# CONFIG_MFD_TPS65912_SPI is not set
CONFIG_MFD_TPS80031=y
CONFIG_TWL4030_CORE=y
CONFIG_MFD_TWL4030_AUDIO=y
# CONFIG_TWL6040_CORE is not set
CONFIG_MFD_WL1273_CORE=y
# CONFIG_MFD_LM3533 is not set
CONFIG_MFD_TIMBERDALE=y
# CONFIG_MFD_TMIO is not set
CONFIG_MFD_VX855=m
CONFIG_MFD_ARIZONA=y
CONFIG_MFD_ARIZONA_I2C=m
CONFIG_MFD_ARIZONA_SPI=m
CONFIG_MFD_CS47L24=y
# CONFIG_MFD_WM5102 is not set
CONFIG_MFD_WM5110=y
CONFIG_MFD_WM8997=y
# CONFIG_MFD_WM8998 is not set
CONFIG_MFD_WM8400=y
# CONFIG_MFD_WM831X_I2C is not set
# CONFIG_MFD_WM831X_SPI is not set
CONFIG_MFD_WM8350=y
CONFIG_MFD_WM8350_I2C=y
# CONFIG_MFD_WM8994 is not set
CONFIG_REGULATOR=y
# CONFIG_REGULATOR_DEBUG is not set
CONFIG_REGULATOR_FIXED_VOLTAGE=y
CONFIG_REGULATOR_VIRTUAL_CONSUMER=m
# CONFIG_REGULATOR_USERSPACE_CONSUMER is not set
# CONFIG_REGULATOR_ACT8865 is not set
# CONFIG_REGULATOR_AD5398 is not set
# CONFIG_REGULATOR_ANATOP is not set
CONFIG_REGULATOR_AAT2870=y
# CONFIG_REGULATOR_AXP20X is not set
CONFIG_REGULATOR_DA903X=y
CONFIG_REGULATOR_DA9052=m
CONFIG_REGULATOR_DA9062=m
# CONFIG_REGULATOR_DA9063 is not set
# CONFIG_REGULATOR_DA9210 is not set
CONFIG_REGULATOR_DA9211=y
# CONFIG_REGULATOR_FAN53555 is not set
CONFIG_REGULATOR_GPIO=y
# CONFIG_REGULATOR_ISL9305 is not set
CONFIG_REGULATOR_ISL6271A=y
CONFIG_REGULATOR_LP3971=y
CONFIG_REGULATOR_LP3972=y
CONFIG_REGULATOR_LP872X=m
CONFIG_REGULATOR_LP8755=y
CONFIG_REGULATOR_LP8788=m
CONFIG_REGULATOR_LTC3589=m
CONFIG_REGULATOR_LTC3676=m
CONFIG_REGULATOR_MAX14577=m
CONFIG_REGULATOR_MAX1586=y
CONFIG_REGULATOR_MAX8649=m
CONFIG_REGULATOR_MAX8660=m
CONFIG_REGULATOR_MAX8907=m
CONFIG_REGULATOR_MAX8952=y
# CONFIG_REGULATOR_MAX8998 is not set
CONFIG_REGULATOR_MAX77693=y
CONFIG_REGULATOR_MC13XXX_CORE=m
CONFIG_REGULATOR_MC13783=m
# CONFIG_REGULATOR_MC13892 is not set
CONFIG_REGULATOR_MT6311=y
CONFIG_REGULATOR_MT6323=m
# CONFIG_REGULATOR_MT6397 is not set
CONFIG_REGULATOR_PALMAS=y
CONFIG_REGULATOR_PCF50633=m
CONFIG_REGULATOR_PFUZE100=m
CONFIG_REGULATOR_PV88060=m
CONFIG_REGULATOR_PV88080=m
# CONFIG_REGULATOR_PV88090 is not set
# CONFIG_REGULATOR_PWM is not set
# CONFIG_REGULATOR_RT5033 is not set
CONFIG_REGULATOR_S2MPA01=m
CONFIG_REGULATOR_S2MPS11=m
CONFIG_REGULATOR_S5M8767=m
CONFIG_REGULATOR_SKY81452=m
# CONFIG_REGULATOR_TPS51632 is not set
CONFIG_REGULATOR_TPS6105X=m
# CONFIG_REGULATOR_TPS62360 is not set
# CONFIG_REGULATOR_TPS65023 is not set
CONFIG_REGULATOR_TPS6507X=m
# CONFIG_REGULATOR_TPS65086 is not set
CONFIG_REGULATOR_TPS65090=y
CONFIG_REGULATOR_TPS65217=m
# CONFIG_REGULATOR_TPS6524X is not set
# CONFIG_REGULATOR_TPS65912 is not set
# CONFIG_REGULATOR_TPS80031 is not set
CONFIG_REGULATOR_TWL4030=y
CONFIG_REGULATOR_WM8350=m
CONFIG_REGULATOR_WM8400=m
CONFIG_MEDIA_SUPPORT=y
#
# Multimedia core support
#
CONFIG_MEDIA_CAMERA_SUPPORT=y
CONFIG_MEDIA_ANALOG_TV_SUPPORT=y
# CONFIG_MEDIA_DIGITAL_TV_SUPPORT is not set
# CONFIG_MEDIA_RADIO_SUPPORT is not set
# CONFIG_MEDIA_SDR_SUPPORT is not set
CONFIG_MEDIA_RC_SUPPORT=y
CONFIG_MEDIA_CEC_SUPPORT=y
# CONFIG_MEDIA_CEC_DEBUG is not set
CONFIG_MEDIA_CEC_EDID=y
# CONFIG_MEDIA_CONTROLLER is not set
CONFIG_VIDEO_DEV=y
CONFIG_VIDEO_V4L2=y
# CONFIG_VIDEO_ADV_DEBUG is not set
# CONFIG_VIDEO_FIXED_MINOR_RANGES is not set
# CONFIG_VIDEO_PCI_SKELETON is not set
CONFIG_V4L2_MEM2MEM_DEV=y
CONFIG_VIDEOBUF2_CORE=y
CONFIG_VIDEOBUF2_MEMOPS=y
CONFIG_VIDEOBUF2_DMA_CONTIG=y
CONFIG_VIDEOBUF2_VMALLOC=y
# CONFIG_TTPCI_EEPROM is not set
#
# Media drivers
#
CONFIG_RC_CORE=y
# CONFIG_RC_MAP is not set
# CONFIG_RC_DECODERS is not set
CONFIG_RC_DEVICES=y
# CONFIG_RC_ATI_REMOTE is not set
CONFIG_IR_ENE=y
CONFIG_IR_HIX5HD2=y
# CONFIG_IR_IMON is not set
# CONFIG_IR_MCEUSB is not set
# CONFIG_IR_ITE_CIR is not set
# CONFIG_IR_FINTEK is not set
CONFIG_IR_NUVOTON=m
# CONFIG_IR_REDRAT3 is not set
# CONFIG_IR_STREAMZAP is not set
# CONFIG_IR_WINBOND_CIR is not set
# CONFIG_IR_IGORPLUGUSB is not set
# CONFIG_IR_IGUANA is not set
# CONFIG_IR_TTUSBIR is not set
CONFIG_RC_LOOPBACK=m
CONFIG_IR_GPIO_CIR=y
# CONFIG_IR_SERIAL is not set
# CONFIG_MEDIA_PCI_SUPPORT is not set
# CONFIG_V4L_PLATFORM_DRIVERS is not set
CONFIG_V4L_MEM2MEM_DRIVERS=y
CONFIG_VIDEO_MEM2MEM_DEINTERLACE=y
CONFIG_VIDEO_SH_VEU=m
CONFIG_V4L_TEST_DRIVERS=y
CONFIG_VIDEO_VIVID=m
CONFIG_VIDEO_VIVID_CEC=y
CONFIG_VIDEO_VIVID_MAX_DEVS=64
CONFIG_VIDEO_VIM2M=y
#
# Supported MMC/SDIO adapters
#
CONFIG_VIDEO_V4L2_TPG=m
#
# Media ancillary drivers (tuners, sensors, i2c, spi, frontends)
#
CONFIG_MEDIA_SUBDRV_AUTOSELECT=y
CONFIG_MEDIA_ATTACH=y
CONFIG_VIDEO_IR_I2C=y
#
# Audio decoders, processors and mixers
#
#
# RDS decoders
#
#
# Video decoders
#
#
# Video and audio decoders
#
#
# Video encoders
#
#
# Camera sensor devices
#
#
# Flash devices
#
#
# Video improvement chips
#
#
# Audio/Video compression chips
#
#
# Miscellaneous helper chips
#
#
# Sensors used on soc_camera driver
#
CONFIG_MEDIA_TUNER=y
CONFIG_MEDIA_TUNER_SIMPLE=y
CONFIG_MEDIA_TUNER_TDA8290=y
CONFIG_MEDIA_TUNER_TDA827X=y
CONFIG_MEDIA_TUNER_TDA18271=y
CONFIG_MEDIA_TUNER_TDA9887=y
CONFIG_MEDIA_TUNER_MT20XX=y
CONFIG_MEDIA_TUNER_XC2028=y
CONFIG_MEDIA_TUNER_XC5000=y
CONFIG_MEDIA_TUNER_XC4000=y
CONFIG_MEDIA_TUNER_MC44S803=y
#
# Tools to develop new frontends
#
#
# Graphics support
#
CONFIG_AGP=m
CONFIG_AGP_ALI=m
# CONFIG_AGP_ATI is not set
# CONFIG_AGP_AMD is not set
# CONFIG_AGP_AMD64 is not set
CONFIG_AGP_INTEL=m
CONFIG_AGP_NVIDIA=m
CONFIG_AGP_SIS=m
CONFIG_AGP_SWORKS=m
# CONFIG_AGP_VIA is not set
CONFIG_AGP_EFFICEON=m
CONFIG_INTEL_GTT=m
CONFIG_VGA_ARB=y
CONFIG_VGA_ARB_MAX_GPUS=16
CONFIG_VGA_SWITCHEROO=y
# CONFIG_DRM is not set
#
# ACP (Audio CoProcessor) Configuration
#
# CONFIG_DRM_LIB_RANDOM is not set
#
# Frame buffer Devices
#
CONFIG_FB=m
# CONFIG_FIRMWARE_EDID is not set
CONFIG_FB_CMDLINE=y
CONFIG_FB_NOTIFY=y
CONFIG_FB_DDC=m
# CONFIG_FB_BOOT_VESA_SUPPORT is not set
CONFIG_FB_CFB_FILLRECT=m
CONFIG_FB_CFB_COPYAREA=m
CONFIG_FB_CFB_IMAGEBLIT=m
# CONFIG_FB_CFB_REV_PIXELS_IN_BYTE is not set
CONFIG_FB_SYS_FILLRECT=m
CONFIG_FB_SYS_COPYAREA=m
CONFIG_FB_SYS_IMAGEBLIT=m
# CONFIG_FB_PROVIDE_GET_FB_UNMAPPED_AREA is not set
# CONFIG_FB_FOREIGN_ENDIAN is not set
CONFIG_FB_SYS_FOPS=m
CONFIG_FB_DEFERRED_IO=y
CONFIG_FB_HECUBA=m
CONFIG_FB_SVGALIB=m
# CONFIG_FB_MACMODES is not set
CONFIG_FB_BACKLIGHT=y
CONFIG_FB_MODE_HELPERS=y
CONFIG_FB_TILEBLITTING=y
#
# Frame buffer hardware drivers
#
CONFIG_FB_CIRRUS=m
CONFIG_FB_PM2=m
CONFIG_FB_PM2_FIFO_DISCONNECT=y
CONFIG_FB_CYBER2000=m
CONFIG_FB_CYBER2000_DDC=y
# CONFIG_FB_ARC is not set
# CONFIG_FB_VGA16 is not set
CONFIG_FB_N411=m
# CONFIG_FB_HGA is not set
CONFIG_FB_OPENCORES=m
CONFIG_FB_S1D13XXX=m
# CONFIG_FB_NVIDIA is not set
CONFIG_FB_RIVA=m
CONFIG_FB_RIVA_I2C=y
CONFIG_FB_RIVA_DEBUG=y
CONFIG_FB_RIVA_BACKLIGHT=y
CONFIG_FB_I740=m
CONFIG_FB_I810=m
CONFIG_FB_I810_GTF=y
CONFIG_FB_I810_I2C=y
CONFIG_FB_LE80578=m
CONFIG_FB_CARILLO_RANCH=m
# CONFIG_FB_MATROX is not set
CONFIG_FB_RADEON=m
# CONFIG_FB_RADEON_I2C is not set
CONFIG_FB_RADEON_BACKLIGHT=y
CONFIG_FB_RADEON_DEBUG=y
# CONFIG_FB_ATY128 is not set
CONFIG_FB_ATY=m
# CONFIG_FB_ATY_CT is not set
# CONFIG_FB_ATY_GX is not set
# CONFIG_FB_ATY_BACKLIGHT is not set
CONFIG_FB_S3=m
# CONFIG_FB_S3_DDC is not set
# CONFIG_FB_SAVAGE is not set
CONFIG_FB_SIS=m
CONFIG_FB_SIS_300=y
CONFIG_FB_SIS_315=y
# CONFIG_FB_VIA is not set
CONFIG_FB_NEOMAGIC=m
CONFIG_FB_KYRO=m
# CONFIG_FB_3DFX is not set
# CONFIG_FB_VOODOO1 is not set
# CONFIG_FB_VT8623 is not set
CONFIG_FB_TRIDENT=m
CONFIG_FB_ARK=m
# CONFIG_FB_PM3 is not set
CONFIG_FB_CARMINE=m
# CONFIG_FB_CARMINE_DRAM_EVAL is not set
CONFIG_CARMINE_DRAM_CUSTOM=y
# CONFIG_FB_GEODE is not set
CONFIG_FB_SM501=m
# CONFIG_FB_IBM_GXT4500 is not set
CONFIG_FB_VIRTUAL=m
CONFIG_FB_METRONOME=m
CONFIG_FB_MB862XX=m
CONFIG_FB_MB862XX_PCI_GDC=y
CONFIG_FB_MB862XX_I2C=y
# CONFIG_FB_BROADSHEET is not set
# CONFIG_FB_AUO_K190X is not set
# CONFIG_FB_SM712 is not set
CONFIG_BACKLIGHT_LCD_SUPPORT=y
# CONFIG_LCD_CLASS_DEVICE is not set
CONFIG_BACKLIGHT_CLASS_DEVICE=m
CONFIG_BACKLIGHT_GENERIC=m
CONFIG_BACKLIGHT_PWM=m
CONFIG_BACKLIGHT_DA903X=m
CONFIG_BACKLIGHT_DA9052=m
# CONFIG_BACKLIGHT_APPLE is not set
# CONFIG_BACKLIGHT_PM8941_WLED is not set
CONFIG_BACKLIGHT_SAHARA=m
# CONFIG_BACKLIGHT_ADP5520 is not set
# CONFIG_BACKLIGHT_ADP8860 is not set
# CONFIG_BACKLIGHT_ADP8870 is not set
CONFIG_BACKLIGHT_PCF50633=m
# CONFIG_BACKLIGHT_AAT2870 is not set
CONFIG_BACKLIGHT_LM3630A=m
CONFIG_BACKLIGHT_LM3639=m
# CONFIG_BACKLIGHT_LP855X is not set
# CONFIG_BACKLIGHT_LP8788 is not set
# CONFIG_BACKLIGHT_PANDORA is not set
CONFIG_BACKLIGHT_SKY81452=m
CONFIG_BACKLIGHT_TPS65217=m
CONFIG_BACKLIGHT_GPIO=m
CONFIG_BACKLIGHT_LV5207LP=m
# CONFIG_BACKLIGHT_BD6107 is not set
CONFIG_VGASTATE=m
#
# Console display driver support
#
CONFIG_VGA_CONSOLE=y
CONFIG_VGACON_SOFT_SCROLLBACK=y
CONFIG_VGACON_SOFT_SCROLLBACK_SIZE=64
# CONFIG_VGACON_SOFT_SCROLLBACK_PERSISTENT_ENABLE_BY_DEFAULT is not set
CONFIG_DUMMY_CONSOLE=y
CONFIG_DUMMY_CONSOLE_COLUMNS=80
CONFIG_DUMMY_CONSOLE_ROWS=25
# CONFIG_FRAMEBUFFER_CONSOLE is not set
CONFIG_LOGO=y
# CONFIG_LOGO_LINUX_MONO is not set
CONFIG_LOGO_LINUX_VGA16=y
# CONFIG_LOGO_LINUX_CLUT224 is not set
# CONFIG_SOUND is not set
#
# HID support
#
CONFIG_HID=y
# CONFIG_HID_BATTERY_STRENGTH is not set
# CONFIG_HIDRAW is not set
CONFIG_UHID=m
CONFIG_HID_GENERIC=y
#
# Special HID drivers
#
CONFIG_HID_A4TECH=m
# CONFIG_HID_ACRUX is not set
CONFIG_HID_APPLE=m
CONFIG_HID_ASUS=y
CONFIG_HID_AUREAL=y
# CONFIG_HID_BELKIN is not set
CONFIG_HID_CHERRY=m
# CONFIG_HID_CHICONY is not set
CONFIG_HID_CMEDIA=m
CONFIG_HID_CYPRESS=y
CONFIG_HID_DRAGONRISE=m
CONFIG_DRAGONRISE_FF=y
# CONFIG_HID_EMS_FF is not set
CONFIG_HID_ELECOM=y
# CONFIG_HID_EZKEY is not set
CONFIG_HID_GEMBIRD=y
CONFIG_HID_GFRM=m
CONFIG_HID_KEYTOUCH=y
# CONFIG_HID_KYE is not set
# CONFIG_HID_WALTOP is not set
CONFIG_HID_GYRATION=y
# CONFIG_HID_ICADE is not set
# CONFIG_HID_TWINHAN is not set
CONFIG_HID_KENSINGTON=m
CONFIG_HID_LCPOWER=m
CONFIG_HID_LED=m
CONFIG_HID_LENOVO=y
CONFIG_HID_LOGITECH=y
CONFIG_HID_LOGITECH_HIDPP=y
CONFIG_LOGITECH_FF=y
# CONFIG_LOGIRUMBLEPAD2_FF is not set
CONFIG_LOGIG940_FF=y
# CONFIG_LOGIWHEELS_FF is not set
# CONFIG_HID_MAGICMOUSE is not set
CONFIG_HID_MAYFLASH=y
# CONFIG_HID_MICROSOFT is not set
CONFIG_HID_MONTEREY=y
# CONFIG_HID_MULTITOUCH is not set
CONFIG_HID_ORTEK=m
# CONFIG_HID_PANTHERLORD is not set
# CONFIG_HID_PETALYNX is not set
# CONFIG_HID_PICOLCD is not set
CONFIG_HID_PLANTRONICS=y
# CONFIG_HID_PRIMAX is not set
CONFIG_HID_SAITEK=y
# CONFIG_HID_SAMSUNG is not set
CONFIG_HID_SPEEDLINK=y
CONFIG_HID_STEELSERIES=y
# CONFIG_HID_SUNPLUS is not set
# CONFIG_HID_RMI is not set
CONFIG_HID_GREENASIA=y
CONFIG_GREENASIA_FF=y
# CONFIG_HID_SMARTJOYPLUS is not set
CONFIG_HID_TIVO=y
# CONFIG_HID_TOPSEED is not set
# CONFIG_HID_THINGM is not set
# CONFIG_HID_THRUSTMASTER is not set
# CONFIG_HID_UDRAW_PS3 is not set
# CONFIG_HID_WACOM is not set
CONFIG_HID_WIIMOTE=m
CONFIG_HID_XINMO=m
CONFIG_HID_ZEROPLUS=y
CONFIG_ZEROPLUS_FF=y
# CONFIG_HID_ZYDACRON is not set
CONFIG_HID_SENSOR_HUB=y
CONFIG_HID_SENSOR_CUSTOM_SENSOR=y
# CONFIG_HID_ALPS is not set
#
# I2C HID support
#
CONFIG_I2C_HID=y
CONFIG_USB_OHCI_LITTLE_ENDIAN=y
CONFIG_USB_SUPPORT=y
CONFIG_USB_ARCH_HAS_HCD=y
# CONFIG_USB is not set
#
# USB port drivers
#
#
# USB Physical Layer drivers
#
# CONFIG_USB_PHY is not set
# CONFIG_NOP_USB_XCEIV is not set
# CONFIG_USB_GPIO_VBUS is not set
# CONFIG_TAHVO_USB is not set
# CONFIG_USB_GADGET is not set
# CONFIG_USB_ULPI_BUS is not set
CONFIG_UWB=m
CONFIG_UWB_WHCI=m
CONFIG_MMC=y
CONFIG_MMC_DEBUG=y
CONFIG_MMC_BLOCK=y
CONFIG_MMC_BLOCK_MINORS=8
# CONFIG_MMC_BLOCK_BOUNCE is not set
CONFIG_SDIO_UART=m
# CONFIG_MMC_TEST is not set
#
# MMC/SD/SDIO Host Controller Drivers
#
CONFIG_MMC_SDHCI=y
CONFIG_MMC_SDHCI_PCI=m
# CONFIG_MMC_RICOH_MMC is not set
CONFIG_MMC_SDHCI_ACPI=m
CONFIG_MMC_SDHCI_PLTFM=y
CONFIG_MMC_WBSD=m
CONFIG_MMC_TIFM_SD=m
CONFIG_MMC_CB710=m
# CONFIG_MMC_VIA_SDMMC is not set
CONFIG_MMC_USDHI6ROL0=y
CONFIG_MMC_TOSHIBA_PCI=m
# CONFIG_MMC_MTK is not set
CONFIG_MEMSTICK=y
# CONFIG_MEMSTICK_DEBUG is not set
#
# MemoryStick drivers
#
CONFIG_MEMSTICK_UNSAFE_RESUME=y
CONFIG_MSPRO_BLOCK=m
CONFIG_MS_BLOCK=m
#
# MemoryStick Host Controller Drivers
#
CONFIG_MEMSTICK_TIFM_MS=m
CONFIG_MEMSTICK_JMICRON_38X=m
CONFIG_MEMSTICK_R592=m
CONFIG_NEW_LEDS=y
CONFIG_LEDS_CLASS=y
CONFIG_LEDS_CLASS_FLASH=y
# CONFIG_LEDS_BRIGHTNESS_HW_CHANGED is not set
#
# LED drivers
#
CONFIG_LEDS_LM3530=y
CONFIG_LEDS_LM3642=y
# CONFIG_LEDS_NET48XX is not set
CONFIG_LEDS_WRAP=m
CONFIG_LEDS_PCA9532=y
# CONFIG_LEDS_PCA9532_GPIO is not set
# CONFIG_LEDS_GPIO is not set
CONFIG_LEDS_LP3944=y
CONFIG_LEDS_LP3952=y
CONFIG_LEDS_LP55XX_COMMON=y
CONFIG_LEDS_LP5521=m
CONFIG_LEDS_LP5523=m
# CONFIG_LEDS_LP5562 is not set
CONFIG_LEDS_LP8501=y
CONFIG_LEDS_LP8788=m
CONFIG_LEDS_LP8860=m
CONFIG_LEDS_CLEVO_MAIL=y
CONFIG_LEDS_PCA955X=y
# CONFIG_LEDS_PCA963X is not set
# CONFIG_LEDS_WM8350 is not set
CONFIG_LEDS_DA903X=m
CONFIG_LEDS_DA9052=y
CONFIG_LEDS_DAC124S085=y
CONFIG_LEDS_PWM=m
CONFIG_LEDS_REGULATOR=m
CONFIG_LEDS_BD2802=m
CONFIG_LEDS_INTEL_SS4200=m
CONFIG_LEDS_LT3593=m
CONFIG_LEDS_ADP5520=y
CONFIG_LEDS_MC13783=y
CONFIG_LEDS_TCA6507=m
CONFIG_LEDS_TLC591XX=y
CONFIG_LEDS_LM355x=y
CONFIG_LEDS_OT200=m
#
# LED driver for blink(1) USB RGB LED is under Special HID drivers (HID_THINGM)
#
CONFIG_LEDS_BLINKM=y
CONFIG_LEDS_USER=y
CONFIG_LEDS_NIC78BX=y
#
# LED Triggers
#
# CONFIG_LEDS_TRIGGERS is not set
CONFIG_ACCESSIBILITY=y
# CONFIG_A11Y_BRAILLE_CONSOLE is not set
CONFIG_EDAC_ATOMIC_SCRUB=y
CONFIG_EDAC_SUPPORT=y
# CONFIG_EDAC is not set
CONFIG_RTC_LIB=y
CONFIG_RTC_MC146818_LIB=y
# CONFIG_RTC_CLASS is not set
CONFIG_DMADEVICES=y
# CONFIG_DMADEVICES_DEBUG is not set
#
# DMA Devices
#
CONFIG_DMA_ENGINE=y
CONFIG_DMA_VIRTUAL_CHANNELS=m
CONFIG_DMA_ACPI=y
CONFIG_INTEL_IDMA64=m
# CONFIG_PCH_DMA is not set
# CONFIG_TIMB_DMA is not set
# CONFIG_QCOM_HIDMA_MGMT is not set
# CONFIG_QCOM_HIDMA is not set
CONFIG_DW_DMAC_CORE=y
CONFIG_DW_DMAC=y
CONFIG_DW_DMAC_PCI=m
CONFIG_HSU_DMA=m
#
# DMA Clients
#
# CONFIG_ASYNC_TX_DMA is not set
CONFIG_DMATEST=y
#
# DMABUF options
#
CONFIG_SYNC_FILE=y
# CONFIG_SW_SYNC is not set
CONFIG_AUXDISPLAY=y
CONFIG_KS0108=y
CONFIG_KS0108_PORT=0x378
CONFIG_KS0108_DELAY=2
CONFIG_CFAG12864B=m
CONFIG_CFAG12864B_RATE=20
# CONFIG_IMG_ASCII_LCD is not set
# CONFIG_UIO is not set
# CONFIG_VIRT_DRIVERS is not set
CONFIG_VIRTIO=y
#
# Virtio drivers
#
# CONFIG_VIRTIO_PCI is not set
CONFIG_VIRTIO_BALLOON=y
CONFIG_VIRTIO_INPUT=y
CONFIG_VIRTIO_MMIO=y
CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y
#
# Microsoft Hyper-V guest support
#
# CONFIG_HYPERV is not set
CONFIG_STAGING=y
CONFIG_COMEDI=m
# CONFIG_COMEDI_DEBUG is not set
CONFIG_COMEDI_DEFAULT_BUF_SIZE_KB=2048
CONFIG_COMEDI_DEFAULT_BUF_MAXSIZE_KB=20480
CONFIG_COMEDI_MISC_DRIVERS=y
CONFIG_COMEDI_BOND=m
# CONFIG_COMEDI_TEST is not set
CONFIG_COMEDI_PARPORT=m
CONFIG_COMEDI_SERIAL2002=m
CONFIG_COMEDI_SSV_DNP=m
# CONFIG_COMEDI_ISA_DRIVERS is not set
CONFIG_COMEDI_PCI_DRIVERS=m
# CONFIG_COMEDI_8255_PCI is not set
CONFIG_COMEDI_ADDI_WATCHDOG=m
# CONFIG_COMEDI_ADDI_APCI_1032 is not set
CONFIG_COMEDI_ADDI_APCI_1500=m
CONFIG_COMEDI_ADDI_APCI_1516=m
CONFIG_COMEDI_ADDI_APCI_1564=m
CONFIG_COMEDI_ADDI_APCI_16XX=m
CONFIG_COMEDI_ADDI_APCI_2032=m
CONFIG_COMEDI_ADDI_APCI_2200=m
# CONFIG_COMEDI_ADDI_APCI_3120 is not set
CONFIG_COMEDI_ADDI_APCI_3501=m
CONFIG_COMEDI_ADDI_APCI_3XXX=m
CONFIG_COMEDI_ADL_PCI6208=m
CONFIG_COMEDI_ADL_PCI7X3X=m
# CONFIG_COMEDI_ADL_PCI8164 is not set
CONFIG_COMEDI_ADL_PCI9111=m
# CONFIG_COMEDI_ADL_PCI9118 is not set
CONFIG_COMEDI_ADV_PCI1710=m
CONFIG_COMEDI_ADV_PCI1720=m
CONFIG_COMEDI_ADV_PCI1723=m
# CONFIG_COMEDI_ADV_PCI1724 is not set
CONFIG_COMEDI_ADV_PCI1760=m
# CONFIG_COMEDI_ADV_PCI_DIO is not set
CONFIG_COMEDI_AMPLC_DIO200_PCI=m
CONFIG_COMEDI_AMPLC_PC236_PCI=m
CONFIG_COMEDI_AMPLC_PC263_PCI=m
# CONFIG_COMEDI_AMPLC_PCI224 is not set
CONFIG_COMEDI_AMPLC_PCI230=m
CONFIG_COMEDI_CONTEC_PCI_DIO=m
CONFIG_COMEDI_DAS08_PCI=m
CONFIG_COMEDI_DT3000=m
CONFIG_COMEDI_DYNA_PCI10XX=m
CONFIG_COMEDI_GSC_HPDI=m
CONFIG_COMEDI_MF6X4=m
CONFIG_COMEDI_ICP_MULTI=m
CONFIG_COMEDI_DAQBOARD2000=m
CONFIG_COMEDI_JR3_PCI=m
CONFIG_COMEDI_KE_COUNTER=m
# CONFIG_COMEDI_CB_PCIDAS64 is not set
# CONFIG_COMEDI_CB_PCIDAS is not set
CONFIG_COMEDI_CB_PCIDDA=m
# CONFIG_COMEDI_CB_PCIMDAS is not set
CONFIG_COMEDI_CB_PCIMDDA=m
CONFIG_COMEDI_ME4000=m
CONFIG_COMEDI_ME_DAQ=m
CONFIG_COMEDI_NI_6527=m
# CONFIG_COMEDI_NI_65XX is not set
CONFIG_COMEDI_NI_660X=m
CONFIG_COMEDI_NI_670X=m
CONFIG_COMEDI_NI_LABPC_PCI=m
# CONFIG_COMEDI_NI_PCIDIO is not set
CONFIG_COMEDI_NI_PCIMIO=m
CONFIG_COMEDI_RTD520=m
CONFIG_COMEDI_S626=m
CONFIG_COMEDI_MITE=m
CONFIG_COMEDI_NI_TIOCMD=m
CONFIG_COMEDI_8254=m
CONFIG_COMEDI_8255=m
CONFIG_COMEDI_8255_SA=m
CONFIG_COMEDI_KCOMEDILIB=m
CONFIG_COMEDI_AMPLC_DIO200=m
CONFIG_COMEDI_AMPLC_PC236=m
CONFIG_COMEDI_DAS08=m
CONFIG_COMEDI_NI_LABPC=m
CONFIG_COMEDI_NI_TIO=m
CONFIG_RTS5208=m
#
# IIO staging drivers
#
#
# Accelerometers
#
CONFIG_ADIS16201=m
CONFIG_ADIS16203=m
CONFIG_ADIS16209=m
# CONFIG_ADIS16240 is not set
#
# Analog to digital converters
#
# CONFIG_AD7606 is not set
CONFIG_AD7780=m
# CONFIG_AD7816 is not set
# CONFIG_AD7192 is not set
CONFIG_AD7280=m
#
# Analog digital bi-direction converters
#
# CONFIG_ADT7316 is not set
#
# Capacitance to digital converters
#
CONFIG_AD7150=m
CONFIG_AD7152=m
CONFIG_AD7746=m
#
# Direct Digital Synthesis
#
# CONFIG_AD9832 is not set
# CONFIG_AD9834 is not set
#
# Digital gyroscope sensors
#
CONFIG_ADIS16060=m
#
# Network Analyzer, Impedance Converters
#
CONFIG_AD5933=m
#
# Light sensors
#
# CONFIG_SENSORS_ISL29028 is not set
CONFIG_TSL2x7x=m
#
# Active energy metering IC
#
# CONFIG_ADE7753 is not set
# CONFIG_ADE7754 is not set
CONFIG_ADE7758=m
# CONFIG_ADE7759 is not set
CONFIG_ADE7854=m
CONFIG_ADE7854_I2C=m
CONFIG_ADE7854_SPI=m
#
# Resolver to digital converters
#
CONFIG_AD2S90=m
# CONFIG_AD2S1200 is not set
# CONFIG_AD2S1210 is not set
#
# Triggers - standalone
#
# CONFIG_FB_SM750 is not set
# CONFIG_FB_XGI is not set
#
# Speakup console speech
#
# CONFIG_SPEAKUP is not set
# CONFIG_STAGING_MEDIA is not set
#
# Android
#
# CONFIG_MTD_SPINAND_MT29F is not set
# CONFIG_DGNC is not set
CONFIG_GS_FPGABOOT=y
CONFIG_FB_TFT=m
CONFIG_FB_TFT_AGM1264K_FL=m
CONFIG_FB_TFT_BD663474=m
# CONFIG_FB_TFT_HX8340BN is not set
CONFIG_FB_TFT_HX8347D=m
CONFIG_FB_TFT_HX8353D=m
CONFIG_FB_TFT_HX8357D=m
# CONFIG_FB_TFT_ILI9163 is not set
# CONFIG_FB_TFT_ILI9320 is not set
# CONFIG_FB_TFT_ILI9325 is not set
CONFIG_FB_TFT_ILI9340=m
# CONFIG_FB_TFT_ILI9341 is not set
CONFIG_FB_TFT_ILI9481=m
# CONFIG_FB_TFT_ILI9486 is not set
CONFIG_FB_TFT_PCD8544=m
# CONFIG_FB_TFT_RA8875 is not set
CONFIG_FB_TFT_S6D02A1=m
# CONFIG_FB_TFT_S6D1121 is not set
CONFIG_FB_TFT_SSD1289=m
CONFIG_FB_TFT_SSD1305=m
CONFIG_FB_TFT_SSD1306=m
CONFIG_FB_TFT_SSD1325=m
# CONFIG_FB_TFT_SSD1331 is not set
CONFIG_FB_TFT_SSD1351=m
# CONFIG_FB_TFT_ST7735R is not set
CONFIG_FB_TFT_ST7789V=m
CONFIG_FB_TFT_TINYLCD=m
CONFIG_FB_TFT_TLS8204=m
CONFIG_FB_TFT_UC1611=m
# CONFIG_FB_TFT_UC1701 is not set
# CONFIG_FB_TFT_UPD161704 is not set
# CONFIG_FB_TFT_WATTEROTT is not set
# CONFIG_FB_FLEX is not set
CONFIG_FB_TFT_FBTFT_DEVICE=m
CONFIG_MOST=y
CONFIG_MOSTCORE=y
CONFIG_AIM_CDEV=m
# CONFIG_AIM_NETWORK is not set
# CONFIG_AIM_V4L2 is not set
# CONFIG_HDM_I2C is not set
# CONFIG_KS7010 is not set
CONFIG_GREYBUS=y
CONFIG_GREYBUS_BOOTROM=y
CONFIG_GREYBUS_FIRMWARE=y
# CONFIG_GREYBUS_HID is not set
CONFIG_GREYBUS_LIGHT=y
CONFIG_GREYBUS_LOG=y
# CONFIG_GREYBUS_LOOPBACK is not set
CONFIG_GREYBUS_POWER=y
CONFIG_GREYBUS_RAW=y
CONFIG_GREYBUS_VIBRATOR=m
CONFIG_GREYBUS_BRIDGED_PHY=m
CONFIG_GREYBUS_GPIO=m
CONFIG_GREYBUS_I2C=m
CONFIG_GREYBUS_PWM=m
CONFIG_GREYBUS_SDIO=m
# CONFIG_GREYBUS_SPI is not set
CONFIG_GREYBUS_UART=m
# CONFIG_X86_PLATFORM_DEVICES is not set
CONFIG_PMC_ATOM=y
CONFIG_CHROME_PLATFORMS=y
CONFIG_CHROMEOS_LAPTOP=m
CONFIG_CHROMEOS_PSTORE=m
# CONFIG_CROS_EC_CHARDEV is not set
CONFIG_CROS_EC_LPC=m
CONFIG_CROS_EC_PROTO=y
CONFIG_CROS_KBD_LED_BACKLIGHT=m
CONFIG_CLKDEV_LOOKUP=y
CONFIG_HAVE_CLK_PREPARE=y
CONFIG_COMMON_CLK=y
#
# Common Clock Framework
#
CONFIG_COMMON_CLK_SI5351=m
# CONFIG_COMMON_CLK_CDCE706 is not set
# CONFIG_COMMON_CLK_CS2000_CP is not set
CONFIG_COMMON_CLK_S2MPS11=y
# CONFIG_COMMON_CLK_NXP is not set
CONFIG_COMMON_CLK_PALMAS=y
CONFIG_COMMON_CLK_PWM=y
# CONFIG_COMMON_CLK_PXA is not set
# CONFIG_COMMON_CLK_PIC32 is not set
#
# Hardware Spinlock drivers
#
#
# Clock Source drivers
#
CONFIG_CLKSRC_I8253=y
CONFIG_CLKEVT_I8253=y
CONFIG_I8253_LOCK=y
CONFIG_CLKBLD_I8253=y
# CONFIG_ATMEL_PIT is not set
# CONFIG_SH_TIMER_CMT is not set
# CONFIG_SH_TIMER_MTU2 is not set
# CONFIG_SH_TIMER_TMU is not set
# CONFIG_EM_TIMER_STI is not set
# CONFIG_MAILBOX is not set
# CONFIG_IOMMU_SUPPORT is not set
#
# Remoteproc drivers
#
CONFIG_REMOTEPROC=y
#
# Rpmsg drivers
#
#
# SOC (System On Chip) specific Drivers
#
#
# Broadcom SoC drivers
#
# CONFIG_SUNXI_SRAM is not set
CONFIG_SOC_TI=y
CONFIG_SOC_ZTE=y
# CONFIG_PM_DEVFREQ is not set
CONFIG_EXTCON=y
#
# Extcon Device Drivers
#
CONFIG_EXTCON_ADC_JACK=m
# CONFIG_EXTCON_GPIO is not set
CONFIG_EXTCON_INTEL_INT3496=y
CONFIG_EXTCON_MAX14577=m
CONFIG_EXTCON_MAX3355=m
# CONFIG_EXTCON_MAX77693 is not set
CONFIG_EXTCON_MAX77843=m
CONFIG_EXTCON_PALMAS=y
CONFIG_EXTCON_QCOM_SPMI_MISC=y
CONFIG_EXTCON_RT8973A=y
CONFIG_EXTCON_SM5502=y
CONFIG_EXTCON_USB_GPIO=y
CONFIG_MEMORY=y
CONFIG_IIO=m
CONFIG_IIO_BUFFER=y
CONFIG_IIO_BUFFER_CB=m
CONFIG_IIO_KFIFO_BUF=m
CONFIG_IIO_TRIGGERED_BUFFER=m
CONFIG_IIO_CONFIGFS=m
CONFIG_IIO_TRIGGER=y
CONFIG_IIO_CONSUMERS_PER_TRIGGER=2
CONFIG_IIO_SW_DEVICE=m
CONFIG_IIO_SW_TRIGGER=m
CONFIG_IIO_TRIGGERED_EVENT=m
#
# Accelerometers
#
CONFIG_BMA180=m
CONFIG_BMA220=m
CONFIG_BMC150_ACCEL=m
CONFIG_BMC150_ACCEL_I2C=m
CONFIG_BMC150_ACCEL_SPI=m
# CONFIG_DA280 is not set
CONFIG_DA311=m
CONFIG_DMARD09=m
CONFIG_DMARD10=m
CONFIG_HID_SENSOR_ACCEL_3D=m
CONFIG_IIO_ST_ACCEL_3AXIS=m
CONFIG_IIO_ST_ACCEL_I2C_3AXIS=m
CONFIG_IIO_ST_ACCEL_SPI_3AXIS=m
CONFIG_KXSD9=m
CONFIG_KXSD9_SPI=m
# CONFIG_KXSD9_I2C is not set
CONFIG_KXCJK1013=m
CONFIG_MC3230=m
CONFIG_MMA7455=m
CONFIG_MMA7455_I2C=m
CONFIG_MMA7455_SPI=m
# CONFIG_MMA7660 is not set
CONFIG_MMA8452=m
CONFIG_MMA9551_CORE=m
CONFIG_MMA9551=m
# CONFIG_MMA9553 is not set
CONFIG_MXC4005=m
# CONFIG_MXC6255 is not set
CONFIG_SCA3000=m
# CONFIG_STK8312 is not set
CONFIG_STK8BA50=m
#
# Analog to digital converters
#
CONFIG_AD_SIGMA_DELTA=m
CONFIG_AD7266=m
CONFIG_AD7291=m
CONFIG_AD7298=m
# CONFIG_AD7476 is not set
# CONFIG_AD7766 is not set
CONFIG_AD7791=m
# CONFIG_AD7793 is not set
CONFIG_AD7887=m
CONFIG_AD7923=m
CONFIG_AD799X=m
# CONFIG_AXP288_ADC is not set
CONFIG_CC10001_ADC=m
# CONFIG_DA9150_GPADC is not set
CONFIG_HI8435=m
CONFIG_HX711=m
CONFIG_INA2XX_ADC=m
# CONFIG_LP8788_ADC is not set
CONFIG_LTC2485=m
# CONFIG_MAX1027 is not set
# CONFIG_MAX11100 is not set
CONFIG_MAX1363=m
# CONFIG_MCP320X is not set
CONFIG_MCP3422=m
CONFIG_MEN_Z188_ADC=m
CONFIG_NAU7802=m
# CONFIG_PALMAS_GPADC is not set
# CONFIG_TI_ADC081C is not set
CONFIG_TI_ADC0832=m
CONFIG_TI_ADC12138=m
CONFIG_TI_ADC128S052=m
CONFIG_TI_ADC161S626=m
CONFIG_TI_ADS1015=m
CONFIG_TI_ADS7950=m
CONFIG_TI_AM335X_ADC=m
CONFIG_TI_TLC4541=m
# CONFIG_TWL4030_MADC is not set
CONFIG_TWL6030_GPADC=m
#
# Amplifiers
#
# CONFIG_AD8366 is not set
#
# Chemical Sensors
#
CONFIG_ATLAS_PH_SENSOR=m
# CONFIG_IAQCORE is not set
CONFIG_VZ89X=m
CONFIG_IIO_CROS_EC_SENSORS_CORE=m
CONFIG_IIO_CROS_EC_SENSORS=m
#
# Hid Sensor IIO Common
#
CONFIG_HID_SENSOR_IIO_COMMON=m
CONFIG_HID_SENSOR_IIO_TRIGGER=m
CONFIG_IIO_MS_SENSORS_I2C=m
#
# SSP Sensor Common
#
# CONFIG_IIO_SSP_SENSORS_COMMONS is not set
CONFIG_IIO_SSP_SENSORHUB=m
CONFIG_IIO_ST_SENSORS_I2C=m
CONFIG_IIO_ST_SENSORS_SPI=m
CONFIG_IIO_ST_SENSORS_CORE=m
#
# Counters
#
#
# Digital to analog converters
#
CONFIG_AD5064=m
CONFIG_AD5360=m
# CONFIG_AD5380 is not set
# CONFIG_AD5421 is not set
CONFIG_AD5446=m
CONFIG_AD5449=m
CONFIG_AD5592R_BASE=m
CONFIG_AD5592R=m
CONFIG_AD5593R=m
CONFIG_AD5504=m
# CONFIG_AD5624R_SPI is not set
CONFIG_AD5686=m
CONFIG_AD5755=m
CONFIG_AD5761=m
CONFIG_AD5764=m
# CONFIG_AD5791 is not set
CONFIG_AD7303=m
CONFIG_AD8801=m
CONFIG_M62332=m
CONFIG_MAX517=m
CONFIG_MCP4725=m
# CONFIG_MCP4922 is not set
#
# IIO dummy driver
#
# CONFIG_IIO_SIMPLE_DUMMY is not set
#
# Frequency Synthesizers DDS/PLL
#
#
# Clock Generator/Distribution
#
CONFIG_AD9523=m
#
# Phase-Locked Loop (PLL) frequency synthesizers
#
# CONFIG_ADF4350 is not set
#
# Digital gyroscope sensors
#
CONFIG_ADIS16080=m
CONFIG_ADIS16130=m
# CONFIG_ADIS16136 is not set
# CONFIG_ADIS16260 is not set
CONFIG_ADXRS450=m
# CONFIG_BMG160 is not set
# CONFIG_HID_SENSOR_GYRO_3D is not set
# CONFIG_MPU3050_I2C is not set
CONFIG_IIO_ST_GYRO_3AXIS=m
CONFIG_IIO_ST_GYRO_I2C_3AXIS=m
CONFIG_IIO_ST_GYRO_SPI_3AXIS=m
CONFIG_ITG3200=m
#
# Health Sensors
#
#
# Heart Rate Monitors
#
# CONFIG_AFE4403 is not set
CONFIG_AFE4404=m
CONFIG_MAX30100=m
#
# Humidity sensors
#
# CONFIG_AM2315 is not set
# CONFIG_DHT11 is not set
CONFIG_HDC100X=m
# CONFIG_HTS221 is not set
# CONFIG_HTU21 is not set
CONFIG_SI7005=m
# CONFIG_SI7020 is not set
#
# Inertial measurement units
#
CONFIG_ADIS16400=m
CONFIG_ADIS16480=m
CONFIG_BMI160=m
CONFIG_BMI160_I2C=m
CONFIG_BMI160_SPI=m
# CONFIG_KMX61 is not set
CONFIG_INV_MPU6050_IIO=m
CONFIG_INV_MPU6050_I2C=m
CONFIG_INV_MPU6050_SPI=m
# CONFIG_IIO_ST_LSM6DSX is not set
CONFIG_IIO_ADIS_LIB=m
CONFIG_IIO_ADIS_LIB_BUFFER=y
#
# Light sensors
#
CONFIG_ACPI_ALS=m
CONFIG_ADJD_S311=m
CONFIG_AL3320A=m
CONFIG_APDS9300=m
# CONFIG_APDS9960 is not set
# CONFIG_BH1750 is not set
CONFIG_BH1780=m
# CONFIG_CM32181 is not set
# CONFIG_CM3232 is not set
CONFIG_CM3323=m
CONFIG_CM36651=m
CONFIG_GP2AP020A00F=m
CONFIG_SENSORS_ISL29018=m
CONFIG_ISL29125=m
CONFIG_HID_SENSOR_ALS=m
CONFIG_HID_SENSOR_PROX=m
CONFIG_JSA1212=m
CONFIG_RPR0521=m
CONFIG_LTR501=m
CONFIG_MAX44000=m
CONFIG_OPT3001=m
CONFIG_PA12203001=m
CONFIG_SI1145=m
CONFIG_STK3310=m
CONFIG_TCS3414=m
# CONFIG_TCS3472 is not set
# CONFIG_SENSORS_TSL2563 is not set
CONFIG_TSL2583=m
CONFIG_TSL4531=m
# CONFIG_US5182D is not set
# CONFIG_VCNL4000 is not set
# CONFIG_VEML6070 is not set
#
# Magnetometer sensors
#
# CONFIG_AK8975 is not set
# CONFIG_AK09911 is not set
CONFIG_BMC150_MAGN=m
# CONFIG_BMC150_MAGN_I2C is not set
CONFIG_BMC150_MAGN_SPI=m
CONFIG_MAG3110=m
CONFIG_HID_SENSOR_MAGNETOMETER_3D=m
# CONFIG_MMC35240 is not set
CONFIG_IIO_ST_MAGN_3AXIS=m
CONFIG_IIO_ST_MAGN_I2C_3AXIS=m
CONFIG_IIO_ST_MAGN_SPI_3AXIS=m
CONFIG_SENSORS_HMC5843=m
CONFIG_SENSORS_HMC5843_I2C=m
CONFIG_SENSORS_HMC5843_SPI=m
#
# Inclinometer sensors
#
CONFIG_HID_SENSOR_INCLINOMETER_3D=m
CONFIG_HID_SENSOR_DEVICE_ROTATION=m
#
# Triggers - standalone
#
# CONFIG_IIO_HRTIMER_TRIGGER is not set
CONFIG_IIO_INTERRUPT_TRIGGER=m
CONFIG_IIO_TIGHTLOOP_TRIGGER=m
CONFIG_IIO_SYSFS_TRIGGER=m
#
# Digital potentiometers
#
CONFIG_DS1803=m
# CONFIG_MAX5481 is not set
CONFIG_MAX5487=m
CONFIG_MCP4131=m
CONFIG_MCP4531=m
CONFIG_TPL0102=m
#
# Digital potentiostats
#
CONFIG_LMP91000=m
#
# Pressure sensors
#
# CONFIG_ABP060MG is not set
CONFIG_BMP280=m
CONFIG_BMP280_I2C=m
CONFIG_BMP280_SPI=m
CONFIG_IIO_CROS_EC_BARO=m
CONFIG_HID_SENSOR_PRESS=m
CONFIG_HP03=m
CONFIG_MPL115=m
CONFIG_MPL115_I2C=m
CONFIG_MPL115_SPI=m
CONFIG_MPL3115=m
# CONFIG_MS5611 is not set
CONFIG_MS5637=m
# CONFIG_IIO_ST_PRESS is not set
# CONFIG_T5403 is not set
CONFIG_HP206C=m
CONFIG_ZPA2326=m
CONFIG_ZPA2326_I2C=m
CONFIG_ZPA2326_SPI=m
#
# Lightning sensors
#
CONFIG_AS3935=m
#
# Proximity and distance sensors
#
CONFIG_LIDAR_LITE_V2=m
CONFIG_SX9500=m
CONFIG_SRF08=m
#
# Temperature sensors
#
# CONFIG_MAXIM_THERMOCOUPLE is not set
CONFIG_MLX90614=m
# CONFIG_TMP006 is not set
CONFIG_TMP007=m
CONFIG_TSYS01=m
CONFIG_TSYS02D=m
CONFIG_NTB=y
CONFIG_NTB_PINGPONG=m
# CONFIG_NTB_TOOL is not set
CONFIG_NTB_PERF=y
CONFIG_NTB_TRANSPORT=m
# CONFIG_VME_BUS is not set
CONFIG_PWM=y
CONFIG_PWM_SYSFS=y
CONFIG_PWM_CRC=y
CONFIG_PWM_CROS_EC=y
CONFIG_PWM_LPSS=y
CONFIG_PWM_LPSS_PCI=y
CONFIG_PWM_LPSS_PLATFORM=y
CONFIG_PWM_PCA9685=y
CONFIG_PWM_TWL=y
# CONFIG_PWM_TWL_LED is not set
CONFIG_ARM_GIC_MAX_NR=1
CONFIG_IPACK_BUS=y
CONFIG_BOARD_TPCI200=m
CONFIG_SERIAL_IPOCTAL=m
CONFIG_RESET_CONTROLLER=y
# CONFIG_RESET_ATH79 is not set
# CONFIG_RESET_BERLIN is not set
# CONFIG_RESET_LPC18XX is not set
# CONFIG_RESET_MESON is not set
# CONFIG_RESET_PISTACHIO is not set
# CONFIG_RESET_SOCFPGA is not set
# CONFIG_RESET_STM32 is not set
# CONFIG_RESET_SUNXI is not set
# CONFIG_TI_SYSCON_RESET is not set
# CONFIG_RESET_ZYNQ is not set
# CONFIG_RESET_TEGRA_BPMP is not set
# CONFIG_FMC is not set
#
# PHY Subsystem
#
CONFIG_GENERIC_PHY=y
# CONFIG_PHY_PXA_28NM_HSIC is not set
CONFIG_PHY_PXA_28NM_USB2=y
# CONFIG_BCM_KONA_USB2_PHY is not set
CONFIG_POWERCAP=y
CONFIG_INTEL_RAPL=y
CONFIG_MCB=y
# CONFIG_MCB_PCI is not set
CONFIG_MCB_LPC=m
#
# Performance monitor support
#
# CONFIG_RAS is not set
CONFIG_THUNDERBOLT=y
#
# Android
#
# CONFIG_ANDROID is not set
CONFIG_LIBNVDIMM=m
CONFIG_BLK_DEV_PMEM=m
# CONFIG_ND_BLK is not set
# CONFIG_BTT is not set
CONFIG_DEV_DAX=y
CONFIG_NR_DEV_DAX=32768
CONFIG_NVMEM=y
CONFIG_STM=m
CONFIG_STM_DUMMY=m
CONFIG_STM_SOURCE_CONSOLE=m
# CONFIG_STM_SOURCE_HEARTBEAT is not set
CONFIG_STM_SOURCE_FTRACE=m
CONFIG_INTEL_TH=m
CONFIG_INTEL_TH_PCI=m
CONFIG_INTEL_TH_GTH=m
CONFIG_INTEL_TH_STH=m
CONFIG_INTEL_TH_MSU=m
# CONFIG_INTEL_TH_PTI is not set
CONFIG_INTEL_TH_DEBUG=y
#
# FPGA Configuration Support
#
CONFIG_FPGA=y
#
# FSI support
#
CONFIG_FSI=m
#
# Firmware Drivers
#
CONFIG_EDD=m
CONFIG_EDD_OFF=y
CONFIG_FIRMWARE_MEMMAP=y
# CONFIG_DELL_RBU is not set
CONFIG_DCDBAS=y
CONFIG_DMIID=y
CONFIG_DMI_SYSFS=m
CONFIG_DMI_SCAN_MACHINE_NON_EFI_FALLBACK=y
CONFIG_ISCSI_IBFT_FIND=y
CONFIG_FW_CFG_SYSFS=m
CONFIG_FW_CFG_SYSFS_CMDLINE=y
# CONFIG_GOOGLE_FIRMWARE is not set
# CONFIG_EFI_DEV_PATH_PARSER is not set
#
# Tegra firmware driver
#
#
# File systems
#
CONFIG_DCACHE_WORD_ACCESS=y
CONFIG_EXT2_FS=y
# CONFIG_EXT2_FS_XATTR is not set
CONFIG_EXT3_FS=y
CONFIG_EXT3_FS_POSIX_ACL=y
CONFIG_EXT3_FS_SECURITY=y
CONFIG_EXT4_FS=y
CONFIG_EXT4_FS_POSIX_ACL=y
CONFIG_EXT4_FS_SECURITY=y
CONFIG_EXT4_ENCRYPTION=y
CONFIG_EXT4_FS_ENCRYPTION=y
CONFIG_EXT4_DEBUG=y
CONFIG_JBD2=y
CONFIG_JBD2_DEBUG=y
CONFIG_FS_MBCACHE=y
CONFIG_REISERFS_FS=y
# CONFIG_REISERFS_CHECK is not set
# CONFIG_REISERFS_PROC_INFO is not set
CONFIG_REISERFS_FS_XATTR=y
CONFIG_REISERFS_FS_POSIX_ACL=y
CONFIG_REISERFS_FS_SECURITY=y
CONFIG_JFS_FS=y
CONFIG_JFS_POSIX_ACL=y
# CONFIG_JFS_SECURITY is not set
CONFIG_JFS_DEBUG=y
CONFIG_JFS_STATISTICS=y
# CONFIG_XFS_FS is not set
CONFIG_GFS2_FS=y
# CONFIG_OCFS2_FS is not set
# CONFIG_BTRFS_FS is not set
CONFIG_NILFS2_FS=y
# CONFIG_F2FS_FS is not set
# CONFIG_FS_DAX is not set
CONFIG_FS_POSIX_ACL=y
CONFIG_EXPORTFS=y
# CONFIG_EXPORTFS_BLOCK_OPS is not set
CONFIG_FILE_LOCKING=y
# CONFIG_MANDATORY_FILE_LOCKING is not set
CONFIG_FS_ENCRYPTION=y
CONFIG_FSNOTIFY=y
CONFIG_DNOTIFY=y
CONFIG_INOTIFY_USER=y
# CONFIG_FANOTIFY is not set
CONFIG_QUOTA=y
# CONFIG_QUOTA_NETLINK_INTERFACE is not set
# CONFIG_PRINT_QUOTA_WARNING is not set
CONFIG_QUOTA_DEBUG=y
CONFIG_QUOTA_TREE=y
# CONFIG_QFMT_V1 is not set
CONFIG_QFMT_V2=y
CONFIG_QUOTACTL=y
# CONFIG_AUTOFS4_FS is not set
CONFIG_FUSE_FS=m
# CONFIG_CUSE is not set
CONFIG_OVERLAY_FS=y
CONFIG_OVERLAY_FS_REDIRECT_DIR=y
#
# Caches
#
CONFIG_FSCACHE=y
CONFIG_FSCACHE_STATS=y
CONFIG_FSCACHE_HISTOGRAM=y
# CONFIG_FSCACHE_DEBUG is not set
CONFIG_FSCACHE_OBJECT_LIST=y
# CONFIG_CACHEFILES is not set
#
# CD-ROM/DVD Filesystems
#
CONFIG_ISO9660_FS=m
# CONFIG_JOLIET is not set
# CONFIG_ZISOFS is not set
CONFIG_UDF_FS=y
CONFIG_UDF_NLS=y
#
# DOS/FAT/NT Filesystems
#
CONFIG_FAT_FS=y
CONFIG_MSDOS_FS=m
CONFIG_VFAT_FS=y
CONFIG_FAT_DEFAULT_CODEPAGE=437
CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1"
CONFIG_FAT_DEFAULT_UTF8=y
# CONFIG_NTFS_FS is not set
#
# Pseudo filesystems
#
CONFIG_PROC_FS=y
# CONFIG_PROC_KCORE is not set
CONFIG_PROC_SYSCTL=y
CONFIG_PROC_PAGE_MONITOR=y
CONFIG_PROC_CHILDREN=y
CONFIG_KERNFS=y
CONFIG_SYSFS=y
CONFIG_TMPFS=y
# CONFIG_TMPFS_POSIX_ACL is not set
# CONFIG_TMPFS_XATTR is not set
# CONFIG_HUGETLBFS is not set
# CONFIG_HUGETLB_PAGE is not set
CONFIG_CONFIGFS_FS=y
# CONFIG_MISC_FILESYSTEMS is not set
CONFIG_NETWORK_FILESYSTEMS=y
CONFIG_NLS=y
CONFIG_NLS_DEFAULT="iso8859-1"
# CONFIG_NLS_CODEPAGE_437 is not set
CONFIG_NLS_CODEPAGE_737=m
CONFIG_NLS_CODEPAGE_775=m
# CONFIG_NLS_CODEPAGE_850 is not set
CONFIG_NLS_CODEPAGE_852=y
CONFIG_NLS_CODEPAGE_855=m
CONFIG_NLS_CODEPAGE_857=y
# CONFIG_NLS_CODEPAGE_860 is not set
CONFIG_NLS_CODEPAGE_861=m
CONFIG_NLS_CODEPAGE_862=y
# CONFIG_NLS_CODEPAGE_863 is not set
CONFIG_NLS_CODEPAGE_864=m
CONFIG_NLS_CODEPAGE_865=y
CONFIG_NLS_CODEPAGE_866=m
# CONFIG_NLS_CODEPAGE_869 is not set
CONFIG_NLS_CODEPAGE_936=m
CONFIG_NLS_CODEPAGE_950=m
CONFIG_NLS_CODEPAGE_932=y
CONFIG_NLS_CODEPAGE_949=y
# CONFIG_NLS_CODEPAGE_874 is not set
CONFIG_NLS_ISO8859_8=m
CONFIG_NLS_CODEPAGE_1250=y
CONFIG_NLS_CODEPAGE_1251=m
CONFIG_NLS_ASCII=m
# CONFIG_NLS_ISO8859_1 is not set
CONFIG_NLS_ISO8859_2=m
# CONFIG_NLS_ISO8859_3 is not set
# CONFIG_NLS_ISO8859_4 is not set
CONFIG_NLS_ISO8859_5=m
CONFIG_NLS_ISO8859_6=y
CONFIG_NLS_ISO8859_7=m
CONFIG_NLS_ISO8859_9=m
CONFIG_NLS_ISO8859_13=y
CONFIG_NLS_ISO8859_14=y
CONFIG_NLS_ISO8859_15=m
# CONFIG_NLS_KOI8_R is not set
CONFIG_NLS_KOI8_U=m
CONFIG_NLS_MAC_ROMAN=y
CONFIG_NLS_MAC_CELTIC=m
CONFIG_NLS_MAC_CENTEURO=m
CONFIG_NLS_MAC_CROATIAN=m
CONFIG_NLS_MAC_CYRILLIC=m
# CONFIG_NLS_MAC_GAELIC is not set
CONFIG_NLS_MAC_GREEK=m
# CONFIG_NLS_MAC_ICELAND is not set
CONFIG_NLS_MAC_INUIT=m
# CONFIG_NLS_MAC_ROMANIAN is not set
CONFIG_NLS_MAC_TURKISH=m
CONFIG_NLS_UTF8=y
#
# Kernel hacking
#
CONFIG_TRACE_IRQFLAGS_SUPPORT=y
#
# printk and dmesg options
#
CONFIG_PRINTK_TIME=y
CONFIG_CONSOLE_LOGLEVEL_DEFAULT=7
CONFIG_MESSAGE_LOGLEVEL_DEFAULT=4
# CONFIG_BOOT_PRINTK_DELAY is not set
CONFIG_DYNAMIC_DEBUG=y
#
# Compile-time checks and compiler options
#
# CONFIG_DEBUG_INFO is not set
# CONFIG_ENABLE_WARN_DEPRECATED is not set
# CONFIG_ENABLE_MUST_CHECK is not set
CONFIG_FRAME_WARN=1024
# CONFIG_STRIP_ASM_SYMS is not set
# CONFIG_READABLE_ASM is not set
CONFIG_UNUSED_SYMBOLS=y
# CONFIG_PAGE_OWNER is not set
CONFIG_DEBUG_FS=y
CONFIG_HEADERS_CHECK=y
CONFIG_DEBUG_SECTION_MISMATCH=y
CONFIG_SECTION_MISMATCH_WARN_ONLY=y
CONFIG_ARCH_WANT_FRAME_POINTERS=y
CONFIG_FRAME_POINTER=y
# CONFIG_DEBUG_FORCE_WEAK_PER_CPU is not set
CONFIG_MAGIC_SYSRQ=y
CONFIG_MAGIC_SYSRQ_DEFAULT_ENABLE=0x1
CONFIG_MAGIC_SYSRQ_SERIAL=y
CONFIG_DEBUG_KERNEL=y
#
# Memory Debugging
#
CONFIG_PAGE_EXTENSION=y
# CONFIG_DEBUG_PAGEALLOC is not set
CONFIG_PAGE_POISONING=y
# CONFIG_PAGE_POISONING_NO_SANITY is not set
CONFIG_PAGE_POISONING_ZERO=y
# CONFIG_DEBUG_PAGE_REF is not set
CONFIG_DEBUG_RODATA_TEST=y
# CONFIG_DEBUG_OBJECTS is not set
CONFIG_SLUB_DEBUG_ON=y
CONFIG_SLUB_STATS=y
CONFIG_HAVE_DEBUG_KMEMLEAK=y
# CONFIG_DEBUG_KMEMLEAK is not set
# CONFIG_DEBUG_STACK_USAGE is not set
# CONFIG_DEBUG_VM is not set
CONFIG_ARCH_HAS_DEBUG_VIRTUAL=y
# CONFIG_DEBUG_VIRTUAL is not set
CONFIG_DEBUG_MEMORY_INIT=y
# CONFIG_DEBUG_PER_CPU_MAPS is not set
# CONFIG_DEBUG_HIGHMEM is not set
CONFIG_HAVE_DEBUG_STACKOVERFLOW=y
# CONFIG_DEBUG_STACKOVERFLOW is not set
CONFIG_HAVE_ARCH_KMEMCHECK=y
# CONFIG_DEBUG_SHIRQ is not set
#
# Debug Lockups and Hangs
#
# CONFIG_LOCKUP_DETECTOR is not set
# CONFIG_DETECT_HUNG_TASK is not set
# CONFIG_WQ_WATCHDOG is not set
CONFIG_PANIC_ON_OOPS=y
CONFIG_PANIC_ON_OOPS_VALUE=1
CONFIG_PANIC_TIMEOUT=0
CONFIG_SCHED_DEBUG=y
# CONFIG_SCHED_INFO is not set
# CONFIG_SCHEDSTATS is not set
# CONFIG_SCHED_STACK_END_CHECK is not set
# CONFIG_DEBUG_TIMEKEEPING is not set
#
# Lock Debugging (spinlocks, mutexes, etc...)
#
# CONFIG_DEBUG_RT_MUTEXES is not set
# CONFIG_DEBUG_SPINLOCK is not set
# CONFIG_DEBUG_MUTEXES is not set
# CONFIG_DEBUG_WW_MUTEX_SLOWPATH is not set
# CONFIG_DEBUG_LOCK_ALLOC is not set
# CONFIG_PROVE_LOCKING is not set
# CONFIG_LOCK_STAT is not set
CONFIG_DEBUG_ATOMIC_SLEEP=y
# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
# CONFIG_LOCK_TORTURE_TEST is not set
# CONFIG_WW_MUTEX_SELFTEST is not set
CONFIG_TRACE_IRQFLAGS=y
CONFIG_STACKTRACE=y
# CONFIG_DEBUG_KOBJECT is not set
CONFIG_DEBUG_BUGVERBOSE=y
CONFIG_DEBUG_LIST=y
# CONFIG_DEBUG_PI_LIST is not set
# CONFIG_DEBUG_SG is not set
# CONFIG_DEBUG_NOTIFIERS is not set
# CONFIG_DEBUG_CREDENTIALS is not set
#
# RCU Debugging
#
# CONFIG_PROVE_RCU is not set
# CONFIG_SPARSE_RCU_POINTER is not set
# CONFIG_TORTURE_TEST is not set
# CONFIG_RCU_PERF_TEST is not set
# CONFIG_RCU_TORTURE_TEST is not set
CONFIG_RCU_CPU_STALL_TIMEOUT=21
CONFIG_RCU_TRACE=y
# CONFIG_RCU_EQS_DEBUG is not set
# CONFIG_DEBUG_WQ_FORCE_RR_CPU is not set
# CONFIG_DEBUG_BLOCK_EXT_DEVT is not set
# CONFIG_CPU_HOTPLUG_STATE_CONTROL is not set
# CONFIG_NOTIFIER_ERROR_INJECTION is not set
# CONFIG_FAULT_INJECTION is not set
# CONFIG_LATENCYTOP is not set
CONFIG_USER_STACKTRACE_SUPPORT=y
CONFIG_NOP_TRACER=y
CONFIG_HAVE_FUNCTION_TRACER=y
CONFIG_HAVE_FUNCTION_GRAPH_TRACER=y
CONFIG_HAVE_DYNAMIC_FTRACE=y
CONFIG_HAVE_DYNAMIC_FTRACE_WITH_REGS=y
CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
CONFIG_HAVE_SYSCALL_TRACEPOINTS=y
CONFIG_HAVE_C_RECORDMCOUNT=y
CONFIG_TRACER_MAX_TRACE=y
CONFIG_TRACE_CLOCK=y
CONFIG_RING_BUFFER=y
CONFIG_EVENT_TRACING=y
CONFIG_CONTEXT_SWITCH_TRACER=y
CONFIG_RING_BUFFER_ALLOW_SWAP=y
CONFIG_TRACING=y
CONFIG_GENERIC_TRACER=y
CONFIG_TRACING_SUPPORT=y
CONFIG_FTRACE=y
CONFIG_FUNCTION_TRACER=y
CONFIG_IRQSOFF_TRACER=y
# CONFIG_SCHED_TRACER is not set
CONFIG_HWLAT_TRACER=y
CONFIG_FTRACE_SYSCALLS=y
CONFIG_TRACER_SNAPSHOT=y
CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y
CONFIG_TRACE_BRANCH_PROFILING=y
# CONFIG_BRANCH_PROFILE_NONE is not set
CONFIG_PROFILE_ANNOTATED_BRANCHES=y
# CONFIG_PROFILE_ALL_BRANCHES is not set
# CONFIG_BRANCH_TRACER is not set
CONFIG_STACK_TRACER=y
# CONFIG_BLK_DEV_IO_TRACE is not set
# CONFIG_KPROBE_EVENT is not set
CONFIG_UPROBE_EVENT=y
CONFIG_BPF_EVENTS=y
CONFIG_PROBE_EVENTS=y
# CONFIG_DYNAMIC_FTRACE is not set
# CONFIG_FUNCTION_PROFILER is not set
# CONFIG_FTRACE_STARTUP_TEST is not set
CONFIG_MMIOTRACE=y
# CONFIG_HIST_TRIGGERS is not set
# CONFIG_MMIOTRACE_TEST is not set
# CONFIG_TRACEPOINT_BENCHMARK is not set
# CONFIG_RING_BUFFER_BENCHMARK is not set
# CONFIG_RING_BUFFER_STARTUP_TEST is not set
# CONFIG_TRACE_ENUM_MAP_FILE is not set
# CONFIG_TRACING_EVENTS_GPIO is not set
#
# Runtime Testing
#
CONFIG_LKDTM=m
# CONFIG_TEST_LIST_SORT is not set
# CONFIG_TEST_SORT is not set
# CONFIG_KPROBES_SANITY_TEST is not set
# CONFIG_BACKTRACE_SELF_TEST is not set
# CONFIG_RBTREE_TEST is not set
# CONFIG_INTERVAL_TREE_TEST is not set
# CONFIG_PERCPU_TEST is not set
CONFIG_ATOMIC64_SELFTEST=y
CONFIG_TEST_HEXDUMP=y
# CONFIG_TEST_STRING_HELPERS is not set
CONFIG_TEST_KSTRTOX=y
CONFIG_TEST_PRINTF=m
# CONFIG_TEST_BITMAP is not set
CONFIG_TEST_UUID=m
CONFIG_TEST_RHASHTABLE=m
# CONFIG_TEST_HASH is not set
CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
# CONFIG_DMA_API_DEBUG is not set
CONFIG_TEST_LKM=m
# CONFIG_TEST_USER_COPY is not set
# CONFIG_TEST_BPF is not set
CONFIG_TEST_FIRMWARE=y
# CONFIG_TEST_UDELAY is not set
# CONFIG_MEMTEST is not set
CONFIG_TEST_STATIC_KEYS=m
CONFIG_BUG_ON_DATA_CORRUPTION=y
# CONFIG_SAMPLES is not set
CONFIG_HAVE_ARCH_KGDB=y
# CONFIG_KGDB is not set
CONFIG_ARCH_HAS_UBSAN_SANITIZE_ALL=y
# CONFIG_ARCH_WANTS_UBSAN_NO_NULL is not set
# CONFIG_UBSAN is not set
CONFIG_ARCH_HAS_DEVMEM_IS_ALLOWED=y
CONFIG_STRICT_DEVMEM=y
CONFIG_IO_STRICT_DEVMEM=y
CONFIG_X86_VERBOSE_BOOTUP=y
CONFIG_EARLY_PRINTK=y
# CONFIG_EARLY_PRINTK_DBGP is not set
# CONFIG_X86_PTDUMP_CORE is not set
# CONFIG_X86_PTDUMP is not set
# CONFIG_DEBUG_WX is not set
CONFIG_DOUBLEFAULT=y
# CONFIG_DEBUG_TLBFLUSH is not set
CONFIG_IOMMU_STRESS=y
CONFIG_HAVE_MMIOTRACE_SUPPORT=y
# CONFIG_X86_DECODER_SELFTEST is not set
CONFIG_IO_DELAY_TYPE_0X80=0
CONFIG_IO_DELAY_TYPE_0XED=1
CONFIG_IO_DELAY_TYPE_UDELAY=2
CONFIG_IO_DELAY_TYPE_NONE=3
# CONFIG_IO_DELAY_0X80 is not set
CONFIG_IO_DELAY_0XED=y
# CONFIG_IO_DELAY_UDELAY is not set
# CONFIG_IO_DELAY_NONE is not set
CONFIG_DEFAULT_IO_DELAY_TYPE=1
# CONFIG_DEBUG_BOOT_PARAMS is not set
# CONFIG_CPA_DEBUG is not set
CONFIG_OPTIMIZE_INLINING=y
# CONFIG_DEBUG_ENTRY is not set
# CONFIG_DEBUG_NMI_SELFTEST is not set
CONFIG_X86_DEBUG_FPU=y
# CONFIG_PUNIT_ATOM_DEBUG is not set
#
# Security options
#
CONFIG_KEYS=y
CONFIG_PERSISTENT_KEYRINGS=y
# CONFIG_BIG_KEYS is not set
CONFIG_TRUSTED_KEYS=y
# CONFIG_ENCRYPTED_KEYS is not set
CONFIG_KEY_DH_OPERATIONS=y
# CONFIG_SECURITY_DMESG_RESTRICT is not set
CONFIG_SECURITY=y
CONFIG_SECURITYFS=y
CONFIG_SECURITY_NETWORK=y
CONFIG_SECURITY_PATH=y
CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR=y
CONFIG_HAVE_ARCH_HARDENED_USERCOPY=y
# CONFIG_HARDENED_USERCOPY is not set
# CONFIG_STATIC_USERMODEHELPER is not set
# CONFIG_SECURITY_TOMOYO is not set
# CONFIG_SECURITY_APPARMOR is not set
CONFIG_SECURITY_LOADPIN=y
# CONFIG_SECURITY_LOADPIN_ENABLED is not set
# CONFIG_SECURITY_YAMA is not set
CONFIG_INTEGRITY=y
CONFIG_INTEGRITY_SIGNATURE=y
CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
CONFIG_IMA=y
CONFIG_IMA_MEASURE_PCR_IDX=10
CONFIG_IMA_TEMPLATE=y
# CONFIG_IMA_NG_TEMPLATE is not set
# CONFIG_IMA_SIG_TEMPLATE is not set
CONFIG_IMA_DEFAULT_TEMPLATE="ima"
CONFIG_IMA_DEFAULT_HASH_SHA1=y
CONFIG_IMA_DEFAULT_HASH="sha1"
# CONFIG_IMA_WRITE_POLICY is not set
# CONFIG_IMA_READ_POLICY is not set
CONFIG_IMA_APPRAISE=y
# CONFIG_EVM is not set
CONFIG_DEFAULT_SECURITY_DAC=y
CONFIG_DEFAULT_SECURITY=""
CONFIG_CRYPTO=y
#
# Crypto core or helper
#
CONFIG_CRYPTO_ALGAPI=y
CONFIG_CRYPTO_ALGAPI2=y
CONFIG_CRYPTO_AEAD=y
CONFIG_CRYPTO_AEAD2=y
CONFIG_CRYPTO_BLKCIPHER=y
CONFIG_CRYPTO_BLKCIPHER2=y
CONFIG_CRYPTO_HASH=y
CONFIG_CRYPTO_HASH2=y
CONFIG_CRYPTO_RNG=y
CONFIG_CRYPTO_RNG2=y
CONFIG_CRYPTO_RNG_DEFAULT=y
CONFIG_CRYPTO_AKCIPHER2=y
CONFIG_CRYPTO_AKCIPHER=y
CONFIG_CRYPTO_KPP2=y
CONFIG_CRYPTO_KPP=y
CONFIG_CRYPTO_ACOMP2=y
CONFIG_CRYPTO_RSA=y
CONFIG_CRYPTO_DH=y
CONFIG_CRYPTO_ECDH=y
CONFIG_CRYPTO_MANAGER=y
CONFIG_CRYPTO_MANAGER2=y
# CONFIG_CRYPTO_USER is not set
CONFIG_CRYPTO_MANAGER_DISABLE_TESTS=y
CONFIG_CRYPTO_GF128MUL=y
CONFIG_CRYPTO_NULL=y
CONFIG_CRYPTO_NULL2=y
CONFIG_CRYPTO_PCRYPT=y
CONFIG_CRYPTO_WORKQUEUE=y
CONFIG_CRYPTO_CRYPTD=y
# CONFIG_CRYPTO_MCRYPTD is not set
CONFIG_CRYPTO_AUTHENC=y
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_ABLK_HELPER=y
CONFIG_CRYPTO_SIMD=y
CONFIG_CRYPTO_GLUE_HELPER_X86=y
#
# Authenticated Encryption with Associated Data
#
CONFIG_CRYPTO_CCM=m
CONFIG_CRYPTO_GCM=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
CONFIG_CRYPTO_SEQIV=y
# CONFIG_CRYPTO_ECHAINIV is not set
#
# Block modes
#
CONFIG_CRYPTO_CBC=y
CONFIG_CRYPTO_CTR=y
CONFIG_CRYPTO_CTS=y
CONFIG_CRYPTO_ECB=y
CONFIG_CRYPTO_LRW=y
# CONFIG_CRYPTO_PCBC is not set
CONFIG_CRYPTO_XTS=y
# CONFIG_CRYPTO_KEYWRAP is not set
#
# Hash modes
#
CONFIG_CRYPTO_CMAC=m
CONFIG_CRYPTO_HMAC=y
CONFIG_CRYPTO_XCBC=y
CONFIG_CRYPTO_VMAC=y
#
# Digest
#
CONFIG_CRYPTO_CRC32C=y
# CONFIG_CRYPTO_CRC32C_INTEL is not set
# CONFIG_CRYPTO_CRC32 is not set
# CONFIG_CRYPTO_CRC32_PCLMUL is not set
CONFIG_CRYPTO_CRCT10DIF=y
CONFIG_CRYPTO_GHASH=m
CONFIG_CRYPTO_POLY1305=m
# CONFIG_CRYPTO_MD4 is not set
CONFIG_CRYPTO_MD5=y
CONFIG_CRYPTO_MICHAEL_MIC=y
# CONFIG_CRYPTO_RMD128 is not set
CONFIG_CRYPTO_RMD160=y
CONFIG_CRYPTO_RMD256=y
# CONFIG_CRYPTO_RMD320 is not set
CONFIG_CRYPTO_SHA1=y
CONFIG_CRYPTO_SHA256=y
CONFIG_CRYPTO_SHA512=m
CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=y
CONFIG_CRYPTO_WP512=y
#
# Ciphers
#
CONFIG_CRYPTO_AES=y
# CONFIG_CRYPTO_AES_TI is not set
CONFIG_CRYPTO_AES_586=y
CONFIG_CRYPTO_AES_NI_INTEL=y
# CONFIG_CRYPTO_ANUBIS is not set
CONFIG_CRYPTO_ARC4=m
CONFIG_CRYPTO_BLOWFISH=y
CONFIG_CRYPTO_BLOWFISH_COMMON=y
CONFIG_CRYPTO_CAMELLIA=m
CONFIG_CRYPTO_CAST_COMMON=m
# CONFIG_CRYPTO_CAST5 is not set
CONFIG_CRYPTO_CAST6=m
CONFIG_CRYPTO_DES=m
CONFIG_CRYPTO_FCRYPT=m
CONFIG_CRYPTO_KHAZAD=m
CONFIG_CRYPTO_SALSA20=y
# CONFIG_CRYPTO_SALSA20_586 is not set
CONFIG_CRYPTO_CHACHA20=m
# CONFIG_CRYPTO_SEED is not set
CONFIG_CRYPTO_SERPENT=y
CONFIG_CRYPTO_SERPENT_SSE2_586=y
CONFIG_CRYPTO_TEA=y
CONFIG_CRYPTO_TWOFISH=m
CONFIG_CRYPTO_TWOFISH_COMMON=y
CONFIG_CRYPTO_TWOFISH_586=y
#
# Compression
#
# CONFIG_CRYPTO_DEFLATE is not set
CONFIG_CRYPTO_LZO=m
CONFIG_CRYPTO_842=m
# CONFIG_CRYPTO_LZ4 is not set
# CONFIG_CRYPTO_LZ4HC is not set
#
# Random Number Generation
#
CONFIG_CRYPTO_ANSI_CPRNG=y
CONFIG_CRYPTO_DRBG_MENU=y
CONFIG_CRYPTO_DRBG_HMAC=y
CONFIG_CRYPTO_DRBG_HASH=y
# CONFIG_CRYPTO_DRBG_CTR is not set
CONFIG_CRYPTO_DRBG=y
CONFIG_CRYPTO_JITTERENTROPY=y
# CONFIG_CRYPTO_USER_API_HASH is not set
# CONFIG_CRYPTO_USER_API_SKCIPHER is not set
# CONFIG_CRYPTO_USER_API_RNG is not set
# CONFIG_CRYPTO_USER_API_AEAD is not set
CONFIG_CRYPTO_HASH_INFO=y
# CONFIG_CRYPTO_HW is not set
CONFIG_ASYMMETRIC_KEY_TYPE=y
CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=y
CONFIG_X509_CERTIFICATE_PARSER=y
# CONFIG_PKCS7_MESSAGE_PARSER is not set
#
# Certificates for signature checking
#
# CONFIG_SYSTEM_TRUSTED_KEYRING is not set
CONFIG_HAVE_KVM=y
CONFIG_VIRTUALIZATION=y
# CONFIG_KVM is not set
# CONFIG_VHOST_NET is not set
CONFIG_VHOST_SCSI=m
CONFIG_VHOST=m
# CONFIG_VHOST_CROSS_ENDIAN_LEGACY is not set
# CONFIG_LGUEST is not set
CONFIG_BINARY_PRINTF=y
#
# Library routines
#
CONFIG_BITREVERSE=y
# CONFIG_HAVE_ARCH_BITREVERSE is not set
CONFIG_RATIONAL=y
CONFIG_GENERIC_STRNCPY_FROM_USER=y
CONFIG_GENERIC_STRNLEN_USER=y
CONFIG_GENERIC_NET_UTILS=y
CONFIG_GENERIC_FIND_FIRST_BIT=y
CONFIG_GENERIC_PCI_IOMAP=y
CONFIG_GENERIC_IOMAP=y
CONFIG_GENERIC_IO=y
CONFIG_ARCH_HAS_FAST_MULTIPLIER=y
CONFIG_CRC_CCITT=y
CONFIG_CRC16=y
CONFIG_CRC_T10DIF=y
CONFIG_CRC_ITU_T=y
CONFIG_CRC32=y
CONFIG_CRC32_SELFTEST=m
CONFIG_CRC32_SLICEBY8=y
# CONFIG_CRC32_SLICEBY4 is not set
# CONFIG_CRC32_SARWATE is not set
# CONFIG_CRC32_BIT is not set
CONFIG_CRC7=y
# CONFIG_LIBCRC32C is not set
CONFIG_CRC8=m
# CONFIG_AUDIT_ARCH_COMPAT_GENERIC is not set
CONFIG_RANDOM32_SELFTEST=y
CONFIG_842_COMPRESS=m
CONFIG_842_DECOMPRESS=m
CONFIG_ZLIB_INFLATE=y
CONFIG_LZO_COMPRESS=y
CONFIG_LZO_DECOMPRESS=y
CONFIG_LZ4_DECOMPRESS=y
CONFIG_XZ_DEC=y
CONFIG_XZ_DEC_X86=y
CONFIG_XZ_DEC_POWERPC=y
CONFIG_XZ_DEC_IA64=y
CONFIG_XZ_DEC_ARM=y
CONFIG_XZ_DEC_ARMTHUMB=y
CONFIG_XZ_DEC_SPARC=y
CONFIG_XZ_DEC_BCJ=y
# CONFIG_XZ_DEC_TEST is not set
CONFIG_DECOMPRESS_GZIP=y
CONFIG_DECOMPRESS_BZIP2=y
CONFIG_DECOMPRESS_LZMA=y
CONFIG_DECOMPRESS_XZ=y
CONFIG_DECOMPRESS_LZO=y
CONFIG_DECOMPRESS_LZ4=y
CONFIG_GENERIC_ALLOCATOR=y
CONFIG_BCH=m
CONFIG_RADIX_TREE_MULTIORDER=y
CONFIG_ASSOCIATIVE_ARRAY=y
CONFIG_HAS_IOMEM=y
CONFIG_HAS_IOPORT_MAP=y
CONFIG_HAS_DMA=y
# CONFIG_DMA_NOOP_OPS is not set
# CONFIG_DMA_VIRT_OPS is not set
CONFIG_CHECK_SIGNATURE=y
CONFIG_CPU_RMAP=y
CONFIG_DQL=y
CONFIG_GLOB=y
CONFIG_GLOB_SELFTEST=y
CONFIG_NLATTR=y
CONFIG_CLZ_TAB=y
# CONFIG_CORDIC is not set
CONFIG_DDR=y
CONFIG_IRQ_POLL=y
CONFIG_MPILIB=y
CONFIG_SIGNATURE=y
CONFIG_OID_REGISTRY=y
CONFIG_FONT_SUPPORT=m
CONFIG_FONT_8x16=y
CONFIG_FONT_AUTOSELECT=y
# CONFIG_SG_SPLIT is not set
CONFIG_SG_POOL=y
CONFIG_ARCH_HAS_SG_CHAIN=y
CONFIG_ARCH_HAS_MMIO_FLUSH=y
CONFIG_SBITMAP=y
^ permalink raw reply
* [bdi_unregister] 165a5e22fa INFO: task swapper:1 blocked for more than 120 seconds.
From: Fengguang Wu @ 2017-03-05 2:21 UTC (permalink / raw)
To: Jan Kara; +Cc: Jens Axboe, linux-block, linux-kernel, LKP
[-- Attachment #1: Type: text/plain, Size: 14708 bytes --]
Hi Jan,
FYI next-20170303 is good while mainline is bad with this error.
The attached reproduce-* may help reproduce the issue.
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
commit 165a5e22fafb127ecb5914e12e8c32a1f0d3f820
Author: Jan Kara <jack@suse.cz>
AuthorDate: Wed Feb 8 08:05:56 2017 +0100
Commit: Jens Axboe <axboe@fb.com>
CommitDate: Thu Mar 2 16:08:35 2017 -0700
block: Move bdi_unregister() to del_gendisk()
Commit 6cd18e711dd8 "block: destroy bdi before blockdev is
unregistered." moved bdi unregistration (at that time through
bdi_destroy()) from blk_release_queue() to blk_cleanup_queue() because
it needs to happen before blk_unregister_region() call in del_gendisk()
for MD. SCSI though will free up the device number from sd_remove()
called through a maze of callbacks from device_del() in
__scsi_remove_device() before blk_cleanup_queue() and thus similar races
as described in 6cd18e711dd8 can happen for SCSI as well as reported by
Omar [1].
Moving bdi_unregister() to del_gendisk() works for MD and fixes the
problem for SCSI since del_gendisk() gets called from sd_remove() before
freeing the device number.
This also makes device_add_disk() (calling bdi_register_owner()) more
symmetric with del_gendisk().
[1] http://marc.info/?l=linux-block&m=148554717109098&w=2
Tested-by: Lekshmi Pillai <lekshmicpillai@in.ibm.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jan Kara <jack@suse.cz>
Tested-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
113285b473 blk-mq: ensure that bd->last is always set correctly
165a5e22fa block: Move bdi_unregister() to del_gendisk()
+--------------------------------------------------+------------+------------+
| | 113285b473 | 165a5e22fa |
+--------------------------------------------------+------------+------------+
| boot_successes | 35 | 0 |
| boot_failures | 0 | 15 |
| INFO:task_blocked_for_more_than#seconds | 0 | 15 |
| Kernel_panic-not_syncing:hung_task:blocked_tasks | 0 | 15 |
+--------------------------------------------------+------------+------------+
[ 187.365491] rcu_preempt: wait state: 1 ->state: 0x1
[ 187.366039] rcu_sched: wait state: 1 ->state: 0x1
[ 187.366039] rcu_sched: wait state: 1 ->state: 0x1
[ 187.366564] rcu_bh: wait state: 1 ->state: 0x1
[ 187.366564] rcu_bh: wait state: 1 ->state: 0x1
[ 243.680303] INFO: task swapper:1 blocked for more than 120 seconds.
[ 243.680303] INFO: task swapper:1 blocked for more than 120 seconds.
[ 243.682035] Not tainted 4.10.0-11089-g165a5e2 #2
[ 243.682035] Not tainted 4.10.0-11089-g165a5e2 #2
[ 243.683000] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[ 243.683000] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[ 243.684306] swapper D 0 1 0 0x00000000
[ 243.684306] swapper D 0 1 0 0x00000000
[ 243.685246] Call Trace:
[ 243.685246] Call Trace:
[ 243.685650] __schedule+0x31a/0xc00
[ 243.685650] __schedule+0x31a/0xc00
[ 243.686236] schedule+0x7b/0x170
[ 243.686236] schedule+0x7b/0x170
[ 243.686803] bdi_unregister+0x3a3/0x430
[ 243.686803] bdi_unregister+0x3a3/0x430
[ 243.687447] ? woken_wake_function+0x40/0x40
[ 243.687447] ? woken_wake_function+0x40/0x40
[ 243.688150] del_gendisk+0x232/0x370
[ 243.688150] del_gendisk+0x232/0x370
[ 243.688721] sd_remove+0x97/0x140
[ 243.688721] sd_remove+0x97/0x140
[ 243.689260] device_release_driver_internal+0x4b8/0x4d0
[ 243.689260] device_release_driver_internal+0x4b8/0x4d0
[ 243.690065] device_release_driver+0x1a/0x30
[ 243.690065] device_release_driver+0x1a/0x30
[ 243.690928] bus_remove_device+0x15a/0x1f0
[ 243.690928] bus_remove_device+0x15a/0x1f0
[ 243.691558] device_del+0x34d/0x5a0
[ 243.691558] device_del+0x34d/0x5a0
[ 243.692155] ? kobject_put+0xf6/0x1d0
[ 243.692155] ? kobject_put+0xf6/0x1d0
[ 243.692700] __scsi_remove_device+0x1a3/0x1c0
[ 243.692700] __scsi_remove_device+0x1a3/0x1c0
[ 243.693665] scsi_forget_host+0xb7/0x120
[ 243.693665] scsi_forget_host+0xb7/0x120
[ 243.694301] scsi_remove_host+0xf1/0x300
[ 243.694301] scsi_remove_host+0xf1/0x300
[ 243.694973] sdebug_driver_remove+0x34/0x120
[ 243.694973] sdebug_driver_remove+0x34/0x120
[ 243.695621] ? devices_kset_move_last+0x9d/0x100
[ 243.695621] ? devices_kset_move_last+0x9d/0x100
[ 243.696430] driver_probe_device+0x172/0x6b0
[ 243.696430] driver_probe_device+0x172/0x6b0
[ 243.697413] __device_attach_driver+0x15d/0x1d0
[ 243.697413] __device_attach_driver+0x15d/0x1d0
[ 243.698460] ? __driver_attach+0x1b0/0x1b0
[ 243.698460] ? __driver_attach+0x1b0/0x1b0
[ 243.699111] bus_for_each_drv+0xb1/0x110
[ 243.699111] bus_for_each_drv+0xb1/0x110
[ 243.699856] __device_attach+0x14d/0x210
[ 243.699856] __device_attach+0x14d/0x210
[ 243.700643] ? __driver_attach+0x1b0/0x1b0
[ 243.700643] ? __driver_attach+0x1b0/0x1b0
[ 243.701362] device_initial_probe+0x1b/0x30
[ 243.701362] device_initial_probe+0x1b/0x30
[ 243.701886] bus_probe_device+0xe5/0x100
[ 243.701886] bus_probe_device+0xe5/0x100
[ 243.702447] device_add+0x822/0xc20
[ 243.702447] device_add+0x822/0xc20
[ 243.702879] ? pm_runtime_init+0x125/0x140
[ 243.702879] ? pm_runtime_init+0x125/0x140
[ 243.703366] device_register+0x2e/0x40
[ 243.703366] device_register+0x2e/0x40
[ 243.703823] sdebug_add_adapter+0x144/0x2e0
[ 243.703823] sdebug_add_adapter+0x144/0x2e0
[ 243.704381] ? kobject_uevent+0x18/0x30
[ 243.704381] ? kobject_uevent+0x18/0x30
[ 243.704881] scsi_debug_init+0x955/0xb9d
[ 243.704881] scsi_debug_init+0x955/0xb9d
[ 243.705372] ? init_sg+0x1a9/0x212
[ 243.705372] ? init_sg+0x1a9/0x212
[ 243.705763] ? init_sg+0x212/0x212
[ 243.705763] ? init_sg+0x212/0x212
[ 243.706166] do_one_initcall+0x5d/0x2b0
[ 243.706166] do_one_initcall+0x5d/0x2b0
[ 243.706634] ? parse_args+0x44e/0x710
[ 243.706634] ? parse_args+0x44e/0x710
[ 243.707059] ? kernel_init_freeable+0x20b/0x3ab
[ 243.707059] ? kernel_init_freeable+0x20b/0x3ab
[ 243.707569] kernel_init_freeable+0x23c/0x3ab
[ 243.707569] kernel_init_freeable+0x23c/0x3ab
[ 243.708076] ? rest_init+0x270/0x270
[ 243.708076] ? rest_init+0x270/0x270
[ 243.708543] kernel_init+0x16/0x250
[ 243.708543] kernel_init+0x16/0x250
[ 243.708978] ret_from_fork+0x21/0x30
[ 243.708978] ret_from_fork+0x21/0x30
[ 243.709399]
[ 243.709399] Showing all locks held in the system:
[ 243.709399]
[ 243.709399] Showing all locks held in the system:
[ 243.710265] 3 locks held by swapper/1:
[ 243.710265] 3 locks held by swapper/1:
[ 243.710785] #0: (&dev->mutex){......}, at: [<987efeb8>] __device_attach+0x28/0x210
[ 243.710785] #0: (&dev->mutex){......}, at: [<987efeb8>] __device_attach+0x28/0x210
[ 243.711670] #1: (&shost->scan_mutex){+.+.+.}, at: [<9883cac1>] scsi_remove_host+0x21/0x300
[ 243.711670] #1: (&shost->scan_mutex){+.+.+.}, at: [<9883cac1>] scsi_remove_host+0x21/0x300
[ 243.712674] #2: (&dev->mutex){......}, at: [<987f0d94>] device_release_driver_internal+0x54/0x4d0
[ 243.712674] #2: (&dev->mutex){......}, at: [<987f0d94>] device_release_driver_internal+0x54/0x4d0
[ 243.713807] 2 locks held by khungtaskd/13:
[ 243.713807] 2 locks held by khungtaskd/13:
[ 243.714297] #0: (rcu_read_lock){......}, at: [<97f5f626>] watchdog+0x126/0x8c0
[ 243.714297] #0: (rcu_read_lock){......}, at: [<97f5f626>] watchdog+0x126/0x8c0
[ 243.715168] #1: (tasklist_lock){.+.+..}, at: [<97ee6d62>] debug_show_all_locks+0x52/0x320
[ 243.715168] #1: (tasklist_lock){.+.+..}, at: [<97ee6d62>] debug_show_all_locks+0x52/0x320
[ 243.716128]
[ 243.716128]
[ 243.716372] =============================================
[ 243.716372]
[ 243.716372] =============================================
[ 243.716372]
[ 243.717191] Kernel panic - not syncing: hung_task: blocked tasks
[ 243.717191] Kernel panic - not syncing: hung_task: blocked tasks
[ 243.717889] CPU: 0 PID: 13 Comm: khungtaskd Not tainted 4.10.0-11089-g165a5e2 #2
[ 243.717889] CPU: 0 PID: 13 Comm: khungtaskd Not tainted 4.10.0-11089-g165a5e2 #2
[ 243.718742] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.9.3-20161025_171302-gandalf 04/01/2014
[ 243.718742] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.9.3-20161025_171302-gandalf 04/01/2014
[ 243.719871] Call Trace:
[ 243.719871] Call Trace:
[ 243.720185] dump_stack+0x32/0x43
[ 243.720185] dump_stack+0x32/0x43
[ 243.720185] panic+0x135/0x408
[ 243.720185] panic+0x135/0x408
[ 243.720185] watchdog+0x6d3/0x8c0
[ 243.720185] watchdog+0x6d3/0x8c0
[ 243.720185] kthread+0x151/0x1d0
[ 243.720185] kthread+0x151/0x1d0
[ 243.720185] ? hung_task_panic+0x20/0x20
[ 243.720185] ? hung_task_panic+0x20/0x20
[ 243.720185] ? kthread_worker_fn+0x220/0x220
[ 243.720185] ? kthread_worker_fn+0x220/0x220
[ 243.720185] ret_from_fork+0x21/0x30
[ 243.720185] ret_from_fork+0x21/0x30
[ 243.720185] Kernel Offset: 0x16e00000 from 0x81000000 (relocation range: 0x80000000-0xa07dffff)
[ 243.720185] Kernel Offset: 0x16e00000 from 0x81000000 (relocation range: 0x80000000-0xa07dffff)
# HH:MM RESULT GOOD BAD GOOD_BUT_DIRTY DIRTY_NOT_BAD
git bisect start 0724f5d8ca3a89134a8c248aa4c311ce43d53512 c470abd4fde40ea6a0846a2beab642a578c0b8cd --
git bisect bad 304f9c7ff9aabc9a3cec12bf88f29d24139ac370 # 14:12 B 0 4 15 0 Merge 'linux-review/Roger-Quadros/Revert-usb-gadget-uvc-Add-missing-call-for-additional-setup-data/20170303-232925' into devel-spot-201703040603
git bisect bad a28ca518ffc36daf89550978066ad20094c19e51 # 14:33 B 0 8 22 3 Merge 'linux-review/Arushi-Singhal/staging-speakup-Alignment-match-open-parenthesis/20170304-030809' into devel-spot-201703040603
git bisect bad 93354ede964ded2791d3b573635d538b14590545 # 14:55 B 0 4 15 0 Merge 'linux-review/Georgios-Emmanouil/Staging-wilc1000-wilc_sdio-Modified-comment-style-to-preferred-kernel-comment-style/20170304-050826' into devel-spot-201703040603
git bisect bad 402decdec94a2e4e2635ef662e57f6217a305d81 # 15:36 B 0 11 22 0 Merge 'linux-review/Heiner-Kallweit/staging-fbtft-improve-a-syslog-message-in-fbtft_register_framebuffer/20170304-054107' into devel-spot-201703040603
git bisect bad 1735b51c4dda1ca7f2c239c4b790c3c638281f54 # 15:53 B 0 6 17 0 Merge 'block/for-linus' into devel-spot-201703040603
git bisect good cf5f16969d36dfa64e92cf19594b94de0c381519 # 16:05 G 11 0 0 0 0day base guard for 'devel-spot-201703040603'
git bisect good caa59428971d5ad81d19512365c9ba580d83268c # 16:23 G 11 0 0 0 Merge tag 'staging-4.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging
git bisect good d5500a074741b78b7f778b4ab3415d5ecdcda0a7 # 16:48 G 11 0 0 0 Merge tag 'usercopy-v4.11-rc1.fix' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux
git bisect good 7067739df23ffd641ca99c967830e0ed2ba39eab # 17:13 G 11 0 0 0 Merge branch 'i2c/for-4.11' of git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux
git bisect good b2deee2dc06db7cdf99b84346e69bdb9db9baa85 # 17:47 G 11 0 0 0 Merge tag 'ceph-for-4.11-rc1' of git://github.com/ceph/ceph-client
git bisect good 010426079ec1228a7f980d2eef766a84c0f9241a # 18:03 G 11 0 0 0 sched/headers: Prepare for new header dependencies before moving more code to <linux/sched/mm.h>
git bisect good 3f80dd67c367878aaad16e458eebc3c8980bb841 # 18:28 G 11 0 0 0 Merge tag 'acpi-extra-4.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
git bisect good e26512fea5bcd6602dbf02a551ed073cd4529449 # 18:42 G 10 0 0 0 sched/headers: Remove <linux/cred.h> inclusion from <linux/sched.h>
git bisect good 78769912f680fc0a79a67e798a0ae76f07e63a7b # 19:08 G 11 0 0 0 Merge tag 'linux-kselftest-4.11-rc1-urgent_fix' of git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest
git bisect good 1827adb11ad26b2290dc9fe2aaf54976b2439865 # 19:21 G 11 0 0 0 Merge branch 'WIP.sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
git bisect bad 165a5e22fafb127ecb5914e12e8c32a1f0d3f820 # 19:39 B 0 11 22 0 block: Move bdi_unregister() to del_gendisk()
git bisect good 6a8a21546507a3ec88e81c2ec927a3fb63efa8ff # 19:55 G 11 0 0 0 nbd: stop leaking sockets
git bisect good e02898b423802b1f3a3aaa7f16e896da069ba8f7 # 20:36 G 11 0 0 0 loop: fix LO_FLAGS_PARTSCAN hang
git bisect good 7b36a7189fc320f0b783dd51bd1f541db56cfbdd # 20:53 G 11 0 0 0 block: don't call ioc_exit_icq() with the queue lock held for blk-mq
git bisect good 113285b473824922498d07d7f82459507b9792eb # 21:37 G 11 0 0 0 blk-mq: ensure that bd->last is always set correctly
# first bad commit: [165a5e22fafb127ecb5914e12e8c32a1f0d3f820] block: Move bdi_unregister() to del_gendisk()
git bisect good 113285b473824922498d07d7f82459507b9792eb # 21:41 G 31 0 0 0 blk-mq: ensure that bd->last is always set correctly
# extra tests with CONFIG_DEBUG_INFO_REDUCED
git bisect bad 165a5e22fafb127ecb5914e12e8c32a1f0d3f820 # 22:16 B 0 10 22 1 block: Move bdi_unregister() to del_gendisk()
# extra tests on HEAD of linux-devel/devel-spot-201703040603
git bisect bad 0724f5d8ca3a89134a8c248aa4c311ce43d53512 # 22:16 B 0 39 55 2 0day head guard for 'devel-spot-201703040603'
# extra tests on tree/branch linus/master
git bisect bad 0710f3ff91ecc4a715db6e4d0690472b13c4dac6 # 22:42 B 0 7 18 0 Merge branch 'work.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs
# extra tests with first bad commit reverted
git bisect good 8b222187187cd9372d0d1ee036f1966e142bbd42 # 23:09 G 10 0 0 0 Revert "block: Move bdi_unregister() to del_gendisk()"
# extra tests on tree/branch linux-next/master
git bisect good c0b7b2b33bd17f7155956d0338ce92615da686c9 # 23:28 G 11 0 0 0 Add linux-next specific files for 20170303
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/lkp Intel Corporation
[-- Attachment #2: dmesg-quantal-lkp-hsw01-19:20170304193900:i386-randconfig-h0-03040625:4.10.0-11089-g165a5e2:2.gz --]
[-- Type: application/gzip, Size: 18882 bytes --]
[-- Attachment #3: reproduce-quantal-lkp-hsw01-19:20170304193900:i386-randconfig-h0-03040625:4.10.0-11089-g165a5e2:2 --]
[-- Type: text/plain, Size: 886 bytes --]
#!/bin/bash
kernel=$1
initrd=quantal-core-i386.cgz
wget --no-clobber https://github.com/fengguang/reproduce-kernel-bug/raw/master/initrd/$initrd
kvm=(
qemu-system-x86_64
-enable-kvm
-cpu kvm64
-kernel $kernel
-initrd $initrd
-m 512
-smp 2
-device e1000,netdev=net0
-netdev user,id=net0
-boot order=nc
-no-reboot
-watchdog i6300esb
-watchdog-action debug
-rtc base=localtime
-serial stdio
-display none
-monitor null
)
append=(
root=/dev/ram0
hung_task_panic=1
debug
apic=debug
sysrq_always_enabled
rcupdate.rcu_cpu_stall_timeout=100
net.ifnames=0
printk.devkmsg=on
panic=-1
softlockup_panic=1
nmi_watchdog=panic
oops=panic
load_ramdisk=2
prompt_ramdisk=0
drbd.minor_count=8
systemd.log_level=err
ignore_loglevel
earlyprintk=ttyS0,115200
console=ttyS0,115200
console=tty0
vga=normal
rw
drbd.minor_count=8
)
"${kvm[@]}" -append "${append[*]}"
[-- Attachment #4: config-4.10.0-11089-g165a5e2 --]
[-- Type: text/plain, Size: 113429 bytes --]
#
# Automatically generated file; DO NOT EDIT.
# Linux/i386 4.10.0 Kernel Configuration
#
# CONFIG_64BIT is not set
CONFIG_X86_32=y
CONFIG_X86=y
CONFIG_INSTRUCTION_DECODER=y
CONFIG_OUTPUT_FORMAT="elf32-i386"
CONFIG_ARCH_DEFCONFIG="arch/x86/configs/i386_defconfig"
CONFIG_LOCKDEP_SUPPORT=y
CONFIG_STACKTRACE_SUPPORT=y
CONFIG_MMU=y
CONFIG_ARCH_MMAP_RND_BITS_MIN=8
CONFIG_ARCH_MMAP_RND_BITS_MAX=16
CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MIN=8
CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX=16
CONFIG_NEED_DMA_MAP_STATE=y
CONFIG_NEED_SG_DMA_LENGTH=y
CONFIG_GENERIC_ISA_DMA=y
CONFIG_GENERIC_BUG=y
CONFIG_GENERIC_HWEIGHT=y
CONFIG_ARCH_MAY_HAVE_PC_FDC=y
CONFIG_RWSEM_XCHGADD_ALGORITHM=y
CONFIG_GENERIC_CALIBRATE_DELAY=y
CONFIG_ARCH_HAS_CPU_RELAX=y
CONFIG_ARCH_HAS_CACHE_LINE_SIZE=y
CONFIG_HAVE_SETUP_PER_CPU_AREA=y
CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK=y
CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK=y
CONFIG_ARCH_HIBERNATION_POSSIBLE=y
CONFIG_ARCH_SUSPEND_POSSIBLE=y
CONFIG_ARCH_WANT_HUGE_PMD_SHARE=y
CONFIG_ARCH_WANT_GENERAL_HUGETLB=y
CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING=y
CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC=y
CONFIG_X86_32_LAZY_GS=y
CONFIG_ARCH_SUPPORTS_UPROBES=y
CONFIG_FIX_EARLYCON_MEM=y
CONFIG_PGTABLE_LEVELS=3
CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
CONFIG_CONSTRUCTORS=y
CONFIG_IRQ_WORK=y
CONFIG_BUILDTIME_EXTABLE_SORT=y
CONFIG_THREAD_INFO_IN_TASK=y
#
# General setup
#
CONFIG_BROKEN_ON_SMP=y
CONFIG_INIT_ENV_ARG_LIMIT=32
CONFIG_CROSS_COMPILE=""
# CONFIG_COMPILE_TEST is not set
CONFIG_LOCALVERSION=""
CONFIG_LOCALVERSION_AUTO=y
CONFIG_HAVE_KERNEL_GZIP=y
CONFIG_HAVE_KERNEL_BZIP2=y
CONFIG_HAVE_KERNEL_LZMA=y
CONFIG_HAVE_KERNEL_XZ=y
CONFIG_HAVE_KERNEL_LZO=y
CONFIG_HAVE_KERNEL_LZ4=y
# CONFIG_KERNEL_GZIP is not set
# CONFIG_KERNEL_BZIP2 is not set
# CONFIG_KERNEL_LZMA is not set
# CONFIG_KERNEL_XZ is not set
CONFIG_KERNEL_LZO=y
# CONFIG_KERNEL_LZ4 is not set
CONFIG_DEFAULT_HOSTNAME="(none)"
# CONFIG_SWAP is not set
# CONFIG_SYSVIPC is not set
# CONFIG_POSIX_MQUEUE is not set
CONFIG_CROSS_MEMORY_ATTACH=y
CONFIG_FHANDLE=y
# CONFIG_USELIB is not set
# CONFIG_AUDIT is not set
CONFIG_HAVE_ARCH_AUDITSYSCALL=y
#
# IRQ subsystem
#
CONFIG_GENERIC_IRQ_PROBE=y
CONFIG_GENERIC_IRQ_SHOW=y
CONFIG_GENERIC_IRQ_CHIP=y
CONFIG_IRQ_DOMAIN=y
# CONFIG_IRQ_DOMAIN_DEBUG is not set
CONFIG_IRQ_FORCED_THREADING=y
CONFIG_SPARSE_IRQ=y
CONFIG_CLOCKSOURCE_WATCHDOG=y
CONFIG_ARCH_CLOCKSOURCE_DATA=y
CONFIG_CLOCKSOURCE_VALIDATE_LAST_CYCLE=y
CONFIG_GENERIC_TIME_VSYSCALL=y
CONFIG_GENERIC_CLOCKEVENTS=y
CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST=y
CONFIG_GENERIC_CMOS_UPDATE=y
#
# Timers subsystem
#
CONFIG_TICK_ONESHOT=y
CONFIG_HZ_PERIODIC=y
# CONFIG_NO_HZ_IDLE is not set
# CONFIG_NO_HZ is not set
CONFIG_HIGH_RES_TIMERS=y
#
# CPU/Task time and stats accounting
#
CONFIG_TICK_CPU_ACCOUNTING=y
# CONFIG_IRQ_TIME_ACCOUNTING is not set
# CONFIG_BSD_PROCESS_ACCT is not set
# CONFIG_TASKSTATS is not set
#
# RCU Subsystem
#
CONFIG_PREEMPT_RCU=y
CONFIG_RCU_EXPERT=y
CONFIG_SRCU=y
CONFIG_TASKS_RCU=y
CONFIG_RCU_STALL_COMMON=y
CONFIG_RCU_FANOUT=32
CONFIG_RCU_FANOUT_LEAF=16
CONFIG_TREE_RCU_TRACE=y
# CONFIG_RCU_BOOST is not set
CONFIG_RCU_KTHREAD_PRIO=0
# CONFIG_RCU_NOCB_CPU is not set
CONFIG_BUILD_BIN2C=y
CONFIG_IKCONFIG=y
CONFIG_IKCONFIG_PROC=y
CONFIG_LOG_BUF_SHIFT=17
CONFIG_PRINTK_SAFE_LOG_BUF_SHIFT=13
CONFIG_HAVE_UNSTABLE_SCHED_CLOCK=y
CONFIG_CGROUPS=y
CONFIG_PAGE_COUNTER=y
CONFIG_MEMCG=y
CONFIG_BLK_CGROUP=y
# CONFIG_DEBUG_BLK_CGROUP is not set
CONFIG_CGROUP_WRITEBACK=y
CONFIG_CGROUP_SCHED=y
CONFIG_FAIR_GROUP_SCHED=y
CONFIG_CFS_BANDWIDTH=y
CONFIG_RT_GROUP_SCHED=y
CONFIG_CGROUP_PIDS=y
# CONFIG_CGROUP_RDMA is not set
# CONFIG_CGROUP_FREEZER is not set
# CONFIG_CPUSETS is not set
CONFIG_CGROUP_DEVICE=y
# CONFIG_CGROUP_CPUACCT is not set
CONFIG_CGROUP_PERF=y
# CONFIG_CGROUP_BPF is not set
CONFIG_CGROUP_DEBUG=y
CONFIG_SOCK_CGROUP_DATA=y
# CONFIG_CHECKPOINT_RESTORE is not set
# CONFIG_NAMESPACES is not set
CONFIG_SCHED_AUTOGROUP=y
# CONFIG_SYSFS_DEPRECATED is not set
# CONFIG_RELAY is not set
CONFIG_BLK_DEV_INITRD=y
CONFIG_INITRAMFS_SOURCE=""
CONFIG_RD_GZIP=y
# CONFIG_RD_BZIP2 is not set
CONFIG_RD_LZMA=y
# CONFIG_RD_XZ is not set
# CONFIG_RD_LZO is not set
# CONFIG_RD_LZ4 is not set
CONFIG_INITRAMFS_COMPRESSION=".gz"
CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE=y
# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
CONFIG_SYSCTL=y
CONFIG_ANON_INODES=y
CONFIG_HAVE_UID16=y
CONFIG_SYSCTL_EXCEPTION_TRACE=y
CONFIG_HAVE_PCSPKR_PLATFORM=y
CONFIG_BPF=y
CONFIG_EXPERT=y
CONFIG_UID16=y
CONFIG_MULTIUSER=y
CONFIG_SGETMASK_SYSCALL=y
CONFIG_SYSFS_SYSCALL=y
# CONFIG_SYSCTL_SYSCALL is not set
# CONFIG_POSIX_TIMERS is not set
CONFIG_KALLSYMS=y
CONFIG_KALLSYMS_ALL=y
# CONFIG_KALLSYMS_ABSOLUTE_PERCPU is not set
CONFIG_KALLSYMS_BASE_RELATIVE=y
CONFIG_PRINTK=y
CONFIG_PRINTK_NMI=y
CONFIG_BUG=y
CONFIG_PCSPKR_PLATFORM=y
# CONFIG_BASE_FULL is not set
CONFIG_FUTEX=y
CONFIG_EPOLL=y
CONFIG_SIGNALFD=y
CONFIG_TIMERFD=y
CONFIG_EVENTFD=y
CONFIG_BPF_SYSCALL=y
CONFIG_SHMEM=y
# CONFIG_AIO is not set
# CONFIG_ADVISE_SYSCALLS is not set
# CONFIG_USERFAULTFD is not set
CONFIG_PCI_QUIRKS=y
# CONFIG_MEMBARRIER is not set
CONFIG_EMBEDDED=y
CONFIG_HAVE_PERF_EVENTS=y
CONFIG_PERF_USE_VMALLOC=y
# CONFIG_PC104 is not set
#
# Kernel Performance Events And Counters
#
CONFIG_PERF_EVENTS=y
CONFIG_DEBUG_PERF_USE_VMALLOC=y
# CONFIG_VM_EVENT_COUNTERS is not set
# CONFIG_COMPAT_BRK is not set
# CONFIG_SLAB is not set
# CONFIG_SLUB is not set
CONFIG_SLOB=y
# CONFIG_SYSTEM_DATA_VERIFICATION is not set
# CONFIG_PROFILING is not set
CONFIG_KEXEC_CORE=y
CONFIG_HAVE_OPROFILE=y
CONFIG_OPROFILE_NMI_TIMER=y
CONFIG_KPROBES=y
# CONFIG_JUMP_LABEL is not set
# CONFIG_UPROBES is not set
# CONFIG_HAVE_64BIT_ALIGNED_ACCESS is not set
CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS=y
CONFIG_ARCH_USE_BUILTIN_BSWAP=y
CONFIG_KRETPROBES=y
CONFIG_HAVE_IOREMAP_PROT=y
CONFIG_HAVE_KPROBES=y
CONFIG_HAVE_KRETPROBES=y
CONFIG_HAVE_OPTPROBES=y
CONFIG_HAVE_KPROBES_ON_FTRACE=y
CONFIG_HAVE_NMI=y
CONFIG_HAVE_ARCH_TRACEHOOK=y
CONFIG_HAVE_DMA_CONTIGUOUS=y
CONFIG_GENERIC_SMP_IDLE_THREAD=y
CONFIG_ARCH_HAS_SET_MEMORY=y
CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT=y
CONFIG_HAVE_REGS_AND_STACK_ACCESS_API=y
CONFIG_HAVE_CLK=y
CONFIG_HAVE_DMA_API_DEBUG=y
CONFIG_HAVE_HW_BREAKPOINT=y
CONFIG_HAVE_MIXED_BREAKPOINTS_REGS=y
CONFIG_HAVE_USER_RETURN_NOTIFIER=y
CONFIG_HAVE_PERF_EVENTS_NMI=y
CONFIG_HAVE_PERF_REGS=y
CONFIG_HAVE_PERF_USER_STACK_DUMP=y
CONFIG_HAVE_ARCH_JUMP_LABEL=y
CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG=y
CONFIG_HAVE_CMPXCHG_LOCAL=y
CONFIG_HAVE_CMPXCHG_DOUBLE=y
CONFIG_ARCH_WANT_IPC_PARSE_VERSION=y
CONFIG_HAVE_ARCH_SECCOMP_FILTER=y
CONFIG_HAVE_GCC_PLUGINS=y
# CONFIG_GCC_PLUGINS is not set
CONFIG_HAVE_CC_STACKPROTECTOR=y
# CONFIG_CC_STACKPROTECTOR is not set
CONFIG_CC_STACKPROTECTOR_NONE=y
# CONFIG_CC_STACKPROTECTOR_REGULAR is not set
# CONFIG_CC_STACKPROTECTOR_STRONG is not set
CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES=y
CONFIG_HAVE_IRQ_TIME_ACCOUNTING=y
CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE=y
CONFIG_HAVE_ARCH_HUGE_VMAP=y
CONFIG_MODULES_USE_ELF_REL=y
CONFIG_ARCH_HAS_ELF_RANDOMIZE=y
CONFIG_HAVE_ARCH_MMAP_RND_BITS=y
CONFIG_HAVE_EXIT_THREAD=y
CONFIG_ARCH_MMAP_RND_BITS=8
CONFIG_HAVE_COPY_THREAD_TLS=y
# CONFIG_HAVE_ARCH_HASH is not set
CONFIG_ISA_BUS_API=y
CONFIG_CLONE_BACKWARDS=y
CONFIG_OLD_SIGSUSPEND3=y
CONFIG_OLD_SIGACTION=y
# CONFIG_CPU_NO_EFFICIENT_FFS is not set
# CONFIG_HAVE_ARCH_VMAP_STACK is not set
# CONFIG_ARCH_OPTIONAL_KERNEL_RWX is not set
# CONFIG_ARCH_OPTIONAL_KERNEL_RWX_DEFAULT is not set
CONFIG_ARCH_HAS_STRICT_KERNEL_RWX=y
CONFIG_STRICT_KERNEL_RWX=y
CONFIG_ARCH_HAS_STRICT_MODULE_RWX=y
CONFIG_STRICT_MODULE_RWX=y
#
# GCOV-based kernel profiling
#
CONFIG_GCOV_KERNEL=y
CONFIG_ARCH_HAS_GCOV_PROFILE_ALL=y
CONFIG_GCOV_PROFILE_ALL=y
CONFIG_GCOV_FORMAT_AUTODETECT=y
# CONFIG_GCOV_FORMAT_3_4 is not set
# CONFIG_GCOV_FORMAT_4_7 is not set
CONFIG_HAVE_GENERIC_DMA_COHERENT=y
CONFIG_RT_MUTEXES=y
CONFIG_BASE_SMALL=1
CONFIG_MODULES=y
# CONFIG_MODULE_FORCE_LOAD is not set
# CONFIG_MODULE_UNLOAD is not set
# CONFIG_MODVERSIONS is not set
# CONFIG_MODULE_SRCVERSION_ALL is not set
# CONFIG_MODULE_SIG is not set
CONFIG_MODULE_COMPRESS=y
CONFIG_MODULE_COMPRESS_GZIP=y
# CONFIG_MODULE_COMPRESS_XZ is not set
CONFIG_TRIM_UNUSED_KSYMS=y
CONFIG_MODULES_TREE_LOOKUP=y
CONFIG_BLOCK=y
# CONFIG_LBDAF is not set
CONFIG_BLK_SCSI_REQUEST=y
CONFIG_BLK_DEV_BSG=y
CONFIG_BLK_DEV_BSGLIB=y
CONFIG_BLK_DEV_INTEGRITY=y
# CONFIG_BLK_DEV_ZONED is not set
# CONFIG_BLK_DEV_THROTTLING is not set
CONFIG_BLK_CMDLINE_PARSER=y
CONFIG_BLK_WBT=y
# CONFIG_BLK_WBT_SQ is not set
# CONFIG_BLK_WBT_MQ is not set
CONFIG_BLK_DEBUG_FS=y
# CONFIG_BLK_SED_OPAL is not set
#
# Partition Types
#
# CONFIG_PARTITION_ADVANCED is not set
CONFIG_MSDOS_PARTITION=y
CONFIG_EFI_PARTITION=y
CONFIG_BLK_MQ_PCI=y
#
# IO Schedulers
#
CONFIG_IOSCHED_NOOP=y
CONFIG_IOSCHED_DEADLINE=m
CONFIG_IOSCHED_CFQ=m
CONFIG_CFQ_GROUP_IOSCHED=y
CONFIG_DEFAULT_NOOP=y
CONFIG_DEFAULT_IOSCHED="noop"
CONFIG_MQ_IOSCHED_DEADLINE=y
CONFIG_ASN1=y
CONFIG_UNINLINE_SPIN_UNLOCK=y
CONFIG_ARCH_SUPPORTS_ATOMIC_RMW=y
CONFIG_ARCH_USE_QUEUED_SPINLOCKS=y
CONFIG_ARCH_USE_QUEUED_RWLOCKS=y
# CONFIG_FREEZER is not set
#
# Processor type and features
#
CONFIG_ZONE_DMA=y
# CONFIG_SMP is not set
CONFIG_X86_FEATURE_NAMES=y
# CONFIG_X86_FAST_FEATURE_TESTS is not set
# CONFIG_GOLDFISH is not set
CONFIG_INTEL_RDT_A=y
CONFIG_X86_EXTENDED_PLATFORM=y
# CONFIG_X86_GOLDFISH is not set
# CONFIG_X86_INTEL_LPSS is not set
# CONFIG_X86_AMD_PLATFORM_DEVICE is not set
CONFIG_IOSF_MBI=m
CONFIG_IOSF_MBI_DEBUG=y
# CONFIG_X86_RDC321X is not set
# CONFIG_X86_32_IRIS is not set
# CONFIG_SCHED_OMIT_FRAME_POINTER is not set
CONFIG_HYPERVISOR_GUEST=y
CONFIG_PARAVIRT=y
# CONFIG_PARAVIRT_DEBUG is not set
CONFIG_KVM_GUEST=y
# CONFIG_KVM_DEBUG_FS is not set
# CONFIG_LGUEST_GUEST is not set
# CONFIG_PARAVIRT_TIME_ACCOUNTING is not set
CONFIG_PARAVIRT_CLOCK=y
CONFIG_NO_BOOTMEM=y
# CONFIG_M486 is not set
# CONFIG_M586 is not set
# CONFIG_M586TSC is not set
CONFIG_M586MMX=y
# CONFIG_M686 is not set
# CONFIG_MPENTIUMII is not set
# CONFIG_MPENTIUMIII is not set
# CONFIG_MPENTIUMM is not set
# CONFIG_MPENTIUM4 is not set
# CONFIG_MK6 is not set
# CONFIG_MK7 is not set
# CONFIG_MK8 is not set
# CONFIG_MCRUSOE is not set
# CONFIG_MEFFICEON is not set
# CONFIG_MWINCHIPC6 is not set
# CONFIG_MWINCHIP3D is not set
# CONFIG_MELAN is not set
# CONFIG_MGEODEGX1 is not set
# CONFIG_MGEODE_LX is not set
# CONFIG_MCYRIXIII is not set
# CONFIG_MVIAC3_2 is not set
# CONFIG_MVIAC7 is not set
# CONFIG_MCORE2 is not set
# CONFIG_MATOM is not set
CONFIG_X86_GENERIC=y
CONFIG_X86_INTERNODE_CACHE_SHIFT=6
CONFIG_X86_L1_CACHE_SHIFT=6
CONFIG_X86_PPRO_FENCE=y
CONFIG_X86_F00F_BUG=y
CONFIG_X86_ALIGNMENT_16=y
CONFIG_X86_INTEL_USERCOPY=y
CONFIG_X86_TSC=y
CONFIG_X86_CMPXCHG64=y
CONFIG_X86_MINIMUM_CPU_FAMILY=5
# CONFIG_PROCESSOR_SELECT is not set
CONFIG_CPU_SUP_INTEL=y
CONFIG_CPU_SUP_CYRIX_32=y
CONFIG_CPU_SUP_AMD=y
CONFIG_CPU_SUP_CENTAUR=y
CONFIG_CPU_SUP_TRANSMETA_32=y
CONFIG_CPU_SUP_UMC_32=y
CONFIG_HPET_TIMER=y
CONFIG_DMI=y
CONFIG_SWIOTLB=y
CONFIG_IOMMU_HELPER=y
CONFIG_NR_CPUS=1
# CONFIG_PREEMPT_NONE is not set
# CONFIG_PREEMPT_VOLUNTARY is not set
CONFIG_PREEMPT=y
CONFIG_PREEMPT_COUNT=y
# CONFIG_X86_UP_APIC is not set
# CONFIG_X86_MCE is not set
#
# Performance monitoring
#
CONFIG_PERF_EVENTS_INTEL_UNCORE=y
CONFIG_PERF_EVENTS_INTEL_RAPL=y
CONFIG_PERF_EVENTS_INTEL_CSTATE=y
CONFIG_PERF_EVENTS_AMD_POWER=y
# CONFIG_X86_LEGACY_VM86 is not set
# CONFIG_VM86 is not set
CONFIG_X86_16BIT=y
CONFIG_X86_ESPFIX32=y
CONFIG_TOSHIBA=m
CONFIG_I8K=m
# CONFIG_X86_REBOOTFIXUPS is not set
CONFIG_MICROCODE=y
# CONFIG_MICROCODE_INTEL is not set
# CONFIG_MICROCODE_AMD is not set
CONFIG_MICROCODE_OLD_INTERFACE=y
CONFIG_X86_MSR=m
CONFIG_X86_CPUID=m
# CONFIG_NOHIGHMEM is not set
# CONFIG_HIGHMEM4G is not set
CONFIG_HIGHMEM64G=y
# CONFIG_VMSPLIT_3G is not set
CONFIG_VMSPLIT_2G=y
# CONFIG_VMSPLIT_1G is not set
CONFIG_PAGE_OFFSET=0x80000000
CONFIG_HIGHMEM=y
CONFIG_X86_PAE=y
CONFIG_ARCH_PHYS_ADDR_T_64BIT=y
CONFIG_ARCH_DMA_ADDR_T_64BIT=y
CONFIG_ARCH_FLATMEM_ENABLE=y
CONFIG_ARCH_SPARSEMEM_ENABLE=y
CONFIG_ARCH_SELECT_MEMORY_MODEL=y
CONFIG_ILLEGAL_POINTER_VALUE=0
CONFIG_SELECT_MEMORY_MODEL=y
CONFIG_FLATMEM_MANUAL=y
# CONFIG_SPARSEMEM_MANUAL is not set
CONFIG_FLATMEM=y
CONFIG_FLAT_NODE_MEM_MAP=y
CONFIG_SPARSEMEM_STATIC=y
CONFIG_HAVE_MEMBLOCK=y
CONFIG_HAVE_MEMBLOCK_NODE_MAP=y
CONFIG_ARCH_DISCARD_MEMBLOCK=y
# CONFIG_HAVE_BOOTMEM_INFO_NODE is not set
CONFIG_SPLIT_PTLOCK_CPUS=4
CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK=y
CONFIG_MEMORY_BALLOON=y
# CONFIG_BALLOON_COMPACTION is not set
CONFIG_COMPACTION=y
CONFIG_MIGRATION=y
CONFIG_PHYS_ADDR_T_64BIT=y
# CONFIG_BOUNCE is not set
CONFIG_VIRT_TO_BUS=y
# CONFIG_KSM is not set
CONFIG_DEFAULT_MMAP_MIN_ADDR=4096
CONFIG_TRANSPARENT_HUGEPAGE=y
# CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS is not set
CONFIG_TRANSPARENT_HUGEPAGE_MADVISE=y
CONFIG_TRANSPARENT_HUGE_PAGECACHE=y
CONFIG_NEED_PER_CPU_KM=y
# CONFIG_CLEANCACHE is not set
# CONFIG_CMA is not set
# CONFIG_ZPOOL is not set
CONFIG_ZBUD=y
CONFIG_ZSMALLOC=y
CONFIG_PGTABLE_MAPPING=y
# CONFIG_ZSMALLOC_STAT is not set
CONFIG_GENERIC_EARLY_IOREMAP=y
CONFIG_ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT=y
CONFIG_IDLE_PAGE_TRACKING=y
# CONFIG_X86_PMEM_LEGACY is not set
CONFIG_HIGHPTE=y
# CONFIG_X86_CHECK_BIOS_CORRUPTION is not set
CONFIG_X86_RESERVE_LOW=64
# CONFIG_MATH_EMULATION is not set
# CONFIG_MTRR is not set
# CONFIG_ARCH_RANDOM is not set
# CONFIG_X86_SMAP is not set
CONFIG_X86_INTEL_MPX=y
# CONFIG_EFI is not set
# CONFIG_SECCOMP is not set
CONFIG_HZ_100=y
# CONFIG_HZ_250 is not set
# CONFIG_HZ_300 is not set
# CONFIG_HZ_1000 is not set
CONFIG_HZ=100
CONFIG_SCHED_HRTICK=y
CONFIG_KEXEC=y
# CONFIG_CRASH_DUMP is not set
CONFIG_PHYSICAL_START=0x1000000
CONFIG_RELOCATABLE=y
CONFIG_RANDOMIZE_BASE=y
CONFIG_X86_NEED_RELOCS=y
CONFIG_PHYSICAL_ALIGN=0x200000
# CONFIG_COMPAT_VDSO is not set
# CONFIG_CMDLINE_BOOL is not set
CONFIG_MODIFY_LDT_SYSCALL=y
CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y
#
# Power management and ACPI options
#
# CONFIG_SUSPEND is not set
CONFIG_PM=y
CONFIG_PM_DEBUG=y
# CONFIG_PM_ADVANCED_DEBUG is not set
CONFIG_PM_CLK=y
CONFIG_WQ_POWER_EFFICIENT_DEFAULT=y
CONFIG_ACPI=y
CONFIG_ACPI_LEGACY_TABLES_LOOKUP=y
CONFIG_ARCH_MIGHT_HAVE_ACPI_PDC=y
CONFIG_ACPI_SYSTEM_POWER_STATES_SUPPORT=y
# CONFIG_ACPI_DEBUGGER is not set
# CONFIG_ACPI_PROCFS_POWER is not set
CONFIG_ACPI_REV_OVERRIDE_POSSIBLE=y
# CONFIG_ACPI_EC_DEBUGFS is not set
CONFIG_ACPI_AC=y
CONFIG_ACPI_BATTERY=y
CONFIG_ACPI_BUTTON=y
# CONFIG_ACPI_VIDEO is not set
CONFIG_ACPI_FAN=y
# CONFIG_ACPI_DOCK is not set
CONFIG_ACPI_CPU_FREQ_PSS=y
CONFIG_ACPI_PROCESSOR_CSTATE=y
CONFIG_ACPI_PROCESSOR_IDLE=y
CONFIG_ACPI_PROCESSOR=y
# CONFIG_ACPI_PROCESSOR_AGGREGATOR is not set
CONFIG_ACPI_THERMAL=y
CONFIG_ACPI_CUSTOM_DSDT_FILE=""
# CONFIG_ACPI_CUSTOM_DSDT is not set
CONFIG_ARCH_HAS_ACPI_TABLE_UPGRADE=y
CONFIG_ACPI_TABLE_UPGRADE=y
# CONFIG_ACPI_DEBUG is not set
# CONFIG_ACPI_PCI_SLOT is not set
CONFIG_X86_PM_TIMER=y
# CONFIG_ACPI_CONTAINER is not set
# CONFIG_ACPI_SBS is not set
# CONFIG_ACPI_HED is not set
# CONFIG_ACPI_CUSTOM_METHOD is not set
# CONFIG_ACPI_REDUCED_HARDWARE_ONLY is not set
# CONFIG_ACPI_NFIT is not set
CONFIG_HAVE_ACPI_APEI=y
CONFIG_HAVE_ACPI_APEI_NMI=y
# CONFIG_ACPI_APEI is not set
# CONFIG_DPTF_POWER is not set
# CONFIG_PMIC_OPREGION is not set
# CONFIG_ACPI_CONFIGFS is not set
# CONFIG_SFI is not set
#
# CPU Frequency scaling
#
# CONFIG_CPU_FREQ is not set
#
# CPU Idle
#
CONFIG_CPU_IDLE=y
CONFIG_CPU_IDLE_GOV_LADDER=y
# CONFIG_CPU_IDLE_GOV_MENU is not set
# CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED is not set
CONFIG_INTEL_IDLE=y
#
# Bus options (PCI etc.)
#
CONFIG_PCI=y
# CONFIG_PCI_GOBIOS is not set
# CONFIG_PCI_GOMMCONFIG is not set
# CONFIG_PCI_GODIRECT is not set
CONFIG_PCI_GOANY=y
CONFIG_PCI_BIOS=y
CONFIG_PCI_DIRECT=y
CONFIG_PCI_MMCONFIG=y
CONFIG_PCI_DOMAINS=y
# CONFIG_PCI_CNB20LE_QUIRK is not set
# CONFIG_PCIEPORTBUS is not set
CONFIG_PCI_BUS_ADDR_T_64BIT=y
# CONFIG_PCI_MSI is not set
# CONFIG_PCI_DEBUG is not set
# CONFIG_PCI_REALLOC_ENABLE_AUTO is not set
# CONFIG_PCI_STUB is not set
# CONFIG_PCI_IOV is not set
# CONFIG_PCI_PRI is not set
# CONFIG_PCI_PASID is not set
CONFIG_PCI_LABEL=y
# CONFIG_HOTPLUG_PCI is not set
#
# DesignWare PCI Core Support
#
#
# PCI host controller drivers
#
CONFIG_ISA_BUS=y
CONFIG_ISA_DMA_API=y
CONFIG_ISA=y
# CONFIG_EISA is not set
# CONFIG_SCx200 is not set
CONFIG_ALIX=y
CONFIG_NET5501=y
# CONFIG_GEOS is not set
CONFIG_AMD_NB=y
CONFIG_PCCARD=y
CONFIG_PCMCIA=m
# CONFIG_PCMCIA_LOAD_CIS is not set
CONFIG_CARDBUS=y
#
# PC-card bridges
#
# CONFIG_YENTA is not set
# CONFIG_PD6729 is not set
# CONFIG_I82092 is not set
CONFIG_I82365=m
CONFIG_TCIC=m
CONFIG_PCMCIA_PROBE=y
CONFIG_PCCARD_NONSTATIC=y
# CONFIG_RAPIDIO is not set
CONFIG_X86_SYSFB=y
#
# Executable file formats / Emulations
#
CONFIG_BINFMT_ELF=y
CONFIG_ELFCORE=y
CONFIG_BINFMT_SCRIPT=y
CONFIG_HAVE_AOUT=y
# CONFIG_BINFMT_AOUT is not set
CONFIG_BINFMT_MISC=m
# CONFIG_COREDUMP is not set
CONFIG_COMPAT_32=y
CONFIG_HAVE_ATOMIC_IOMAP=y
CONFIG_NET=y
CONFIG_NET_INGRESS=y
#
# Networking options
#
CONFIG_PACKET=m
CONFIG_PACKET_DIAG=m
CONFIG_UNIX=y
# CONFIG_UNIX_DIAG is not set
CONFIG_XFRM=y
CONFIG_XFRM_ALGO=y
CONFIG_XFRM_USER=y
CONFIG_XFRM_SUB_POLICY=y
CONFIG_XFRM_MIGRATE=y
# CONFIG_XFRM_STATISTICS is not set
CONFIG_XFRM_IPCOMP=m
CONFIG_NET_KEY=y
# CONFIG_NET_KEY_MIGRATE is not set
CONFIG_INET=y
CONFIG_IP_MULTICAST=y
# CONFIG_IP_ADVANCED_ROUTER is not set
CONFIG_IP_PNP=y
CONFIG_IP_PNP_DHCP=y
# CONFIG_IP_PNP_BOOTP is not set
# CONFIG_IP_PNP_RARP is not set
# CONFIG_NET_IPIP is not set
CONFIG_NET_IPGRE_DEMUX=y
CONFIG_NET_IP_TUNNEL=y
CONFIG_NET_IPGRE=m
# CONFIG_NET_IPGRE_BROADCAST is not set
# CONFIG_IP_MROUTE is not set
# CONFIG_SYN_COOKIES is not set
CONFIG_NET_UDP_TUNNEL=y
CONFIG_NET_FOU=m
CONFIG_NET_FOU_IP_TUNNELS=y
# CONFIG_INET_AH is not set
CONFIG_INET_ESP=y
# CONFIG_INET_ESP_OFFLOAD is not set
CONFIG_INET_IPCOMP=m
CONFIG_INET_XFRM_TUNNEL=m
CONFIG_INET_TUNNEL=m
# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
# CONFIG_INET_XFRM_MODE_TUNNEL is not set
CONFIG_INET_XFRM_MODE_BEET=m
CONFIG_INET_DIAG=m
CONFIG_INET_TCP_DIAG=m
CONFIG_INET_UDP_DIAG=m
CONFIG_INET_RAW_DIAG=m
CONFIG_INET_DIAG_DESTROY=y
CONFIG_TCP_CONG_ADVANCED=y
CONFIG_TCP_CONG_BIC=y
CONFIG_TCP_CONG_CUBIC=y
# CONFIG_TCP_CONG_WESTWOOD is not set
# CONFIG_TCP_CONG_HTCP is not set
# CONFIG_TCP_CONG_HSTCP is not set
CONFIG_TCP_CONG_HYBLA=m
CONFIG_TCP_CONG_VEGAS=y
CONFIG_TCP_CONG_NV=m
CONFIG_TCP_CONG_SCALABLE=m
CONFIG_TCP_CONG_LP=y
# CONFIG_TCP_CONG_VENO is not set
CONFIG_TCP_CONG_YEAH=y
CONFIG_TCP_CONG_ILLINOIS=y
# CONFIG_TCP_CONG_DCTCP is not set
CONFIG_TCP_CONG_CDG=y
# CONFIG_TCP_CONG_BBR is not set
# CONFIG_DEFAULT_BIC is not set
# CONFIG_DEFAULT_CUBIC is not set
CONFIG_DEFAULT_VEGAS=y
# CONFIG_DEFAULT_CDG is not set
# CONFIG_DEFAULT_RENO is not set
CONFIG_DEFAULT_TCP_CONG="vegas"
# CONFIG_TCP_MD5SIG is not set
CONFIG_IPV6=y
# CONFIG_IPV6_ROUTER_PREF is not set
# CONFIG_IPV6_OPTIMISTIC_DAD is not set
CONFIG_INET6_AH=y
CONFIG_INET6_ESP=y
# CONFIG_INET6_ESP_OFFLOAD is not set
# CONFIG_INET6_IPCOMP is not set
# CONFIG_IPV6_MIP6 is not set
# CONFIG_IPV6_ILA is not set
# CONFIG_INET6_XFRM_TUNNEL is not set
CONFIG_INET6_TUNNEL=y
# CONFIG_INET6_XFRM_MODE_TRANSPORT is not set
CONFIG_INET6_XFRM_MODE_TUNNEL=m
CONFIG_INET6_XFRM_MODE_BEET=m
CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m
CONFIG_IPV6_VTI=m
# CONFIG_IPV6_SIT is not set
CONFIG_IPV6_TUNNEL=y
CONFIG_IPV6_GRE=m
CONFIG_IPV6_FOU=m
CONFIG_IPV6_FOU_TUNNEL=m
CONFIG_IPV6_MULTIPLE_TABLES=y
CONFIG_IPV6_SUBTREES=y
# CONFIG_IPV6_MROUTE is not set
CONFIG_IPV6_SEG6_LWTUNNEL=y
# CONFIG_IPV6_SEG6_INLINE is not set
CONFIG_IPV6_SEG6_HMAC=y
CONFIG_NETWORK_SECMARK=y
CONFIG_NET_PTP_CLASSIFY=y
CONFIG_NETWORK_PHY_TIMESTAMPING=y
CONFIG_NETFILTER=y
CONFIG_NETFILTER_DEBUG=y
# CONFIG_NETFILTER_ADVANCED is not set
#
# Core Netfilter Configuration
#
CONFIG_NETFILTER_INGRESS=y
CONFIG_NETFILTER_NETLINK=y
CONFIG_NETFILTER_NETLINK_LOG=y
CONFIG_NF_CONNTRACK=m
CONFIG_NF_LOG_COMMON=y
# CONFIG_NF_LOG_NETDEV is not set
# CONFIG_NF_CONNTRACK_SECMARK is not set
CONFIG_NF_CONNTRACK_PROCFS=y
# CONFIG_NF_CONNTRACK_FTP is not set
CONFIG_NF_CONNTRACK_IRC=m
CONFIG_NF_CONNTRACK_BROADCAST=m
CONFIG_NF_CONNTRACK_NETBIOS_NS=m
# CONFIG_NF_CONNTRACK_SIP is not set
CONFIG_NF_CT_NETLINK=m
CONFIG_NETFILTER_NETLINK_GLUE_CT=y
CONFIG_NF_TABLES=m
CONFIG_NF_TABLES_INET=m
CONFIG_NF_TABLES_NETDEV=m
CONFIG_NFT_EXTHDR=m
CONFIG_NFT_META=m
CONFIG_NFT_RT=m
CONFIG_NFT_NUMGEN=m
CONFIG_NFT_CT=m
# CONFIG_NFT_SET_RBTREE is not set
CONFIG_NFT_SET_HASH=m
# CONFIG_NFT_SET_BITMAP is not set
CONFIG_NFT_COUNTER=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
# CONFIG_NFT_NAT is not set
CONFIG_NFT_OBJREF=m
CONFIG_NFT_QUOTA=m
CONFIG_NFT_REJECT=m
CONFIG_NFT_REJECT_INET=m
# CONFIG_NFT_COMPAT is not set
CONFIG_NFT_HASH=m
CONFIG_NFT_FIB=m
CONFIG_NFT_FIB_INET=m
CONFIG_NF_DUP_NETDEV=m
CONFIG_NFT_DUP_NETDEV=m
CONFIG_NFT_FWD_NETDEV=m
CONFIG_NETFILTER_XTABLES=m
#
# Xtables combined modules
#
# CONFIG_NETFILTER_XT_MARK is not set
#
# Xtables targets
#
CONFIG_NETFILTER_XT_TARGET_LOG=m
CONFIG_NETFILTER_XT_TARGET_NFLOG=m
CONFIG_NETFILTER_XT_TARGET_SECMARK=m
# CONFIG_NETFILTER_XT_TARGET_TCPMSS is not set
#
# Xtables matches
#
# CONFIG_NETFILTER_XT_MATCH_ADDRTYPE is not set
CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
CONFIG_NETFILTER_XT_MATCH_POLICY=m
CONFIG_NETFILTER_XT_MATCH_STATE=m
CONFIG_IP_SET=y
CONFIG_IP_SET_MAX=256
CONFIG_IP_SET_BITMAP_IP=m
CONFIG_IP_SET_BITMAP_IPMAC=m
CONFIG_IP_SET_BITMAP_PORT=m
CONFIG_IP_SET_HASH_IP=y
CONFIG_IP_SET_HASH_IPMARK=m
CONFIG_IP_SET_HASH_IPPORT=m
CONFIG_IP_SET_HASH_IPPORTIP=y
CONFIG_IP_SET_HASH_IPPORTNET=m
CONFIG_IP_SET_HASH_IPMAC=y
# CONFIG_IP_SET_HASH_MAC is not set
# CONFIG_IP_SET_HASH_NETPORTNET is not set
CONFIG_IP_SET_HASH_NET=y
CONFIG_IP_SET_HASH_NETNET=y
CONFIG_IP_SET_HASH_NETPORT=m
CONFIG_IP_SET_HASH_NETIFACE=y
# CONFIG_IP_SET_LIST_SET is not set
CONFIG_IP_VS=m
CONFIG_IP_VS_IPV6=y
CONFIG_IP_VS_DEBUG=y
CONFIG_IP_VS_TAB_BITS=12
#
# IPVS transport protocol load balancing support
#
CONFIG_IP_VS_PROTO_TCP=y
# CONFIG_IP_VS_PROTO_UDP is not set
# CONFIG_IP_VS_PROTO_AH_ESP is not set
# CONFIG_IP_VS_PROTO_ESP is not set
# CONFIG_IP_VS_PROTO_AH is not set
# CONFIG_IP_VS_PROTO_SCTP is not set
#
# IPVS scheduler
#
# CONFIG_IP_VS_RR is not set
CONFIG_IP_VS_WRR=m
CONFIG_IP_VS_LC=m
CONFIG_IP_VS_WLC=m
CONFIG_IP_VS_FO=m
CONFIG_IP_VS_OVF=m
# CONFIG_IP_VS_LBLC is not set
CONFIG_IP_VS_LBLCR=m
# CONFIG_IP_VS_DH is not set
CONFIG_IP_VS_SH=m
CONFIG_IP_VS_SED=m
# CONFIG_IP_VS_NQ is not set
#
# IPVS SH scheduler
#
CONFIG_IP_VS_SH_TAB_BITS=8
#
# IPVS application helper
#
CONFIG_IP_VS_NFCT=y
#
# IP: Netfilter Configuration
#
# CONFIG_NF_DEFRAG_IPV4 is not set
# CONFIG_NF_CONNTRACK_IPV4 is not set
CONFIG_NF_SOCKET_IPV4=y
CONFIG_NF_TABLES_IPV4=m
# CONFIG_NFT_CHAIN_ROUTE_IPV4 is not set
CONFIG_NFT_REJECT_IPV4=m
CONFIG_NFT_DUP_IPV4=m
CONFIG_NFT_FIB_IPV4=m
CONFIG_NF_TABLES_ARP=m
CONFIG_NF_DUP_IPV4=m
CONFIG_NF_LOG_ARP=y
CONFIG_NF_LOG_IPV4=m
CONFIG_NF_REJECT_IPV4=m
# CONFIG_IP_NF_IPTABLES is not set
#
# IPv6: Netfilter Configuration
#
# CONFIG_NF_DEFRAG_IPV6 is not set
# CONFIG_NF_CONNTRACK_IPV6 is not set
CONFIG_NF_SOCKET_IPV6=m
CONFIG_NF_TABLES_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
CONFIG_NFT_REJECT_IPV6=m
CONFIG_NFT_DUP_IPV6=m
CONFIG_NFT_FIB_IPV6=m
CONFIG_NF_DUP_IPV6=m
CONFIG_NF_REJECT_IPV6=m
CONFIG_NF_LOG_IPV6=m
CONFIG_IP6_NF_IPTABLES=m
# CONFIG_IP6_NF_MATCH_IPV6HEADER is not set
CONFIG_IP6_NF_FILTER=m
# CONFIG_IP6_NF_TARGET_REJECT is not set
CONFIG_IP6_NF_MANGLE=m
CONFIG_IP6_NF_RAW=m
CONFIG_IP_DCCP=y
CONFIG_INET_DCCP_DIAG=m
#
# DCCP CCIDs Configuration
#
# CONFIG_IP_DCCP_CCID2_DEBUG is not set
# CONFIG_IP_DCCP_CCID3 is not set
#
# DCCP Kernel Hacking
#
CONFIG_IP_DCCP_DEBUG=y
# CONFIG_NET_DCCPPROBE is not set
CONFIG_IP_SCTP=y
# CONFIG_NET_SCTPPROBE is not set
# CONFIG_SCTP_DBG_OBJCNT is not set
# CONFIG_SCTP_DEFAULT_COOKIE_HMAC_MD5 is not set
# CONFIG_SCTP_DEFAULT_COOKIE_HMAC_SHA1 is not set
CONFIG_SCTP_DEFAULT_COOKIE_HMAC_NONE=y
CONFIG_SCTP_COOKIE_HMAC_MD5=y
# CONFIG_SCTP_COOKIE_HMAC_SHA1 is not set
CONFIG_INET_SCTP_DIAG=m
# CONFIG_RDS is not set
# CONFIG_TIPC is not set
# CONFIG_ATM is not set
CONFIG_L2TP=y
# CONFIG_L2TP_DEBUGFS is not set
CONFIG_L2TP_V3=y
CONFIG_L2TP_IP=y
CONFIG_L2TP_ETH=y
CONFIG_MRP=y
# CONFIG_BRIDGE is not set
CONFIG_VLAN_8021Q=y
# CONFIG_VLAN_8021Q_GVRP is not set
CONFIG_VLAN_8021Q_MVRP=y
CONFIG_DECNET=y
# CONFIG_DECNET_ROUTER is not set
CONFIG_LLC=y
CONFIG_LLC2=m
CONFIG_IPX=y
# CONFIG_IPX_INTERN is not set
# CONFIG_ATALK is not set
# CONFIG_X25 is not set
CONFIG_LAPB=y
CONFIG_PHONET=m
CONFIG_6LOWPAN=m
CONFIG_6LOWPAN_DEBUGFS=y
# CONFIG_6LOWPAN_NHC is not set
CONFIG_IEEE802154=y
CONFIG_IEEE802154_NL802154_EXPERIMENTAL=y
# CONFIG_IEEE802154_SOCKET is not set
CONFIG_IEEE802154_6LOWPAN=m
# CONFIG_MAC802154 is not set
CONFIG_NET_SCHED=y
#
# Queueing/Scheduling
#
CONFIG_NET_SCH_CBQ=y
CONFIG_NET_SCH_HTB=m
CONFIG_NET_SCH_HFSC=m
CONFIG_NET_SCH_PRIO=m
CONFIG_NET_SCH_MULTIQ=m
CONFIG_NET_SCH_RED=y
CONFIG_NET_SCH_SFB=y
CONFIG_NET_SCH_SFQ=m
# CONFIG_NET_SCH_TEQL is not set
# CONFIG_NET_SCH_TBF is not set
# CONFIG_NET_SCH_GRED is not set
CONFIG_NET_SCH_DSMARK=m
CONFIG_NET_SCH_NETEM=y
# CONFIG_NET_SCH_DRR is not set
# CONFIG_NET_SCH_MQPRIO is not set
CONFIG_NET_SCH_CHOKE=m
CONFIG_NET_SCH_QFQ=y
CONFIG_NET_SCH_CODEL=y
CONFIG_NET_SCH_FQ_CODEL=m
CONFIG_NET_SCH_FQ=y
CONFIG_NET_SCH_HHF=y
CONFIG_NET_SCH_PIE=y
CONFIG_NET_SCH_PLUG=y
#
# Classification
#
CONFIG_NET_CLS=y
CONFIG_NET_CLS_BASIC=y
CONFIG_NET_CLS_TCINDEX=m
# CONFIG_NET_CLS_ROUTE4 is not set
# CONFIG_NET_CLS_FW is not set
# CONFIG_NET_CLS_U32 is not set
CONFIG_NET_CLS_RSVP=y
CONFIG_NET_CLS_RSVP6=m
CONFIG_NET_CLS_FLOW=y
CONFIG_NET_CLS_CGROUP=y
CONFIG_NET_CLS_BPF=y
CONFIG_NET_CLS_FLOWER=y
CONFIG_NET_CLS_MATCHALL=y
# CONFIG_NET_EMATCH is not set
# CONFIG_NET_CLS_ACT is not set
CONFIG_NET_SCH_FIFO=y
CONFIG_DCB=y
CONFIG_DNS_RESOLVER=y
# CONFIG_BATMAN_ADV is not set
# CONFIG_OPENVSWITCH is not set
CONFIG_VSOCKETS=m
CONFIG_VIRTIO_VSOCKETS=m
CONFIG_VIRTIO_VSOCKETS_COMMON=m
CONFIG_NETLINK_DIAG=m
CONFIG_MPLS=y
# CONFIG_NET_MPLS_GSO is not set
CONFIG_MPLS_ROUTING=m
CONFIG_MPLS_IPTUNNEL=m
# CONFIG_HSR is not set
CONFIG_NET_SWITCHDEV=y
# CONFIG_NET_L3_MASTER_DEV is not set
# CONFIG_NET_NCSI is not set
CONFIG_CGROUP_NET_PRIO=y
CONFIG_CGROUP_NET_CLASSID=y
CONFIG_NET_RX_BUSY_POLL=y
CONFIG_BQL=y
#
# Network testing
#
# CONFIG_NET_PKTGEN is not set
# CONFIG_NET_TCPPROBE is not set
CONFIG_HAMRADIO=y
#
# Packet Radio protocols
#
CONFIG_AX25=m
# CONFIG_AX25_DAMA_SLAVE is not set
CONFIG_NETROM=m
# CONFIG_ROSE is not set
#
# AX.25 network device drivers
#
# CONFIG_MKISS is not set
# CONFIG_6PACK is not set
# CONFIG_BPQETHER is not set
CONFIG_DMASCC=m
CONFIG_SCC=m
# CONFIG_SCC_DELAY is not set
CONFIG_SCC_TRXECHO=y
# CONFIG_BAYCOM_SER_FDX is not set
# CONFIG_BAYCOM_SER_HDX is not set
CONFIG_BAYCOM_PAR=m
CONFIG_BAYCOM_EPP=m
# CONFIG_YAM is not set
CONFIG_CAN=y
CONFIG_CAN_RAW=m
CONFIG_CAN_BCM=m
# CONFIG_CAN_GW is not set
#
# CAN Device Drivers
#
CONFIG_CAN_VCAN=y
# CONFIG_CAN_SLCAN is not set
# CONFIG_CAN_DEV is not set
# CONFIG_CAN_DEBUG_DEVICES is not set
CONFIG_IRDA=y
#
# IrDA protocols
#
CONFIG_IRLAN=m
# CONFIG_IRCOMM is not set
CONFIG_IRDA_ULTRA=y
#
# IrDA options
#
# CONFIG_IRDA_CACHE_LAST_LSAP is not set
# CONFIG_IRDA_FAST_RR is not set
CONFIG_IRDA_DEBUG=y
#
# Infrared-port device drivers
#
#
# SIR device drivers
#
# CONFIG_IRTTY_SIR is not set
#
# Dongle support
#
CONFIG_KINGSUN_DONGLE=m
CONFIG_KSDAZZLE_DONGLE=y
CONFIG_KS959_DONGLE=y
#
# FIR device drivers
#
CONFIG_USB_IRDA=y
# CONFIG_SIGMATEL_FIR is not set
CONFIG_NSC_FIR=y
CONFIG_WINBOND_FIR=y
# CONFIG_TOSHIBA_FIR is not set
CONFIG_SMC_IRCC_FIR=y
CONFIG_ALI_FIR=y
# CONFIG_VLSI_FIR is not set
CONFIG_VIA_FIR=y
CONFIG_MCS_FIR=y
CONFIG_BT=y
# CONFIG_BT_BREDR is not set
# CONFIG_BT_LE is not set
CONFIG_BT_LEDS=y
# CONFIG_BT_SELFTEST is not set
CONFIG_BT_DEBUGFS=y
#
# Bluetooth device drivers
#
# CONFIG_BT_HCIBTUSB is not set
# CONFIG_BT_HCIBTSDIO is not set
# CONFIG_BT_HCIUART is not set
# CONFIG_BT_HCIBCM203X is not set
# CONFIG_BT_HCIBFUSB is not set
CONFIG_BT_HCIDTL1=m
CONFIG_BT_HCIBT3C=m
CONFIG_BT_HCIBLUECARD=m
CONFIG_BT_HCIBTUART=m
# CONFIG_BT_HCIVHCI is not set
CONFIG_BT_MRVL=m
CONFIG_BT_MRVL_SDIO=m
CONFIG_AF_RXRPC=m
CONFIG_AF_RXRPC_IPV6=y
# CONFIG_AF_RXRPC_INJECT_LOSS is not set
CONFIG_AF_RXRPC_DEBUG=y
# CONFIG_RXKAD is not set
# CONFIG_AF_KCM is not set
# CONFIG_STREAM_PARSER is not set
CONFIG_FIB_RULES=y
# CONFIG_WIRELESS is not set
CONFIG_WIMAX=m
CONFIG_WIMAX_DEBUG_LEVEL=8
CONFIG_RFKILL=y
CONFIG_RFKILL_LEDS=y
# CONFIG_RFKILL_INPUT is not set
# CONFIG_RFKILL_GPIO is not set
CONFIG_NET_9P=m
# CONFIG_NET_9P_VIRTIO is not set
CONFIG_NET_9P_DEBUG=y
CONFIG_CAIF=m
CONFIG_CAIF_DEBUG=y
CONFIG_CAIF_NETDEV=m
CONFIG_CAIF_USB=m
CONFIG_CEPH_LIB=y
# CONFIG_CEPH_LIB_PRETTYDEBUG is not set
CONFIG_CEPH_LIB_USE_DNS_RESOLVER=y
# CONFIG_NFC is not set
# CONFIG_PSAMPLE is not set
# CONFIG_NET_IFE is not set
CONFIG_LWTUNNEL=y
# CONFIG_LWTUNNEL_BPF is not set
CONFIG_DST_CACHE=y
CONFIG_GRO_CELLS=y
# CONFIG_NET_DEVLINK is not set
CONFIG_MAY_USE_DEVLINK=y
#
# Device Drivers
#
#
# Generic Driver Options
#
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
# CONFIG_DEVTMPFS_MOUNT is not set
# CONFIG_STANDALONE is not set
# CONFIG_PREVENT_FIRMWARE_BUILD is not set
CONFIG_FW_LOADER=y
# CONFIG_FIRMWARE_IN_KERNEL is not set
CONFIG_EXTRA_FIRMWARE=""
CONFIG_FW_LOADER_USER_HELPER=y
# CONFIG_FW_LOADER_USER_HELPER_FALLBACK is not set
CONFIG_WANT_DEV_COREDUMP=y
CONFIG_ALLOW_DEV_COREDUMP=y
CONFIG_DEV_COREDUMP=y
# CONFIG_DEBUG_DRIVER is not set
CONFIG_DEBUG_DEVRES=y
CONFIG_DEBUG_TEST_DRIVER_REMOVE=y
# CONFIG_TEST_ASYNC_DRIVER_PROBE is not set
# CONFIG_SYS_HYPERVISOR is not set
# CONFIG_GENERIC_CPU_DEVICES is not set
CONFIG_GENERIC_CPU_AUTOPROBE=y
CONFIG_REGMAP=y
CONFIG_REGMAP_I2C=y
CONFIG_REGMAP_SPMI=m
CONFIG_REGMAP_MMIO=y
CONFIG_REGMAP_IRQ=y
CONFIG_DMA_SHARED_BUFFER=y
# CONFIG_DMA_FENCE_TRACE is not set
#
# Bus devices
#
CONFIG_CONNECTOR=y
CONFIG_PROC_EVENTS=y
CONFIG_MTD=m
# CONFIG_MTD_TESTS is not set
CONFIG_MTD_REDBOOT_PARTS=m
CONFIG_MTD_REDBOOT_DIRECTORY_BLOCK=-1
CONFIG_MTD_REDBOOT_PARTS_UNALLOCATED=y
CONFIG_MTD_REDBOOT_PARTS_READONLY=y
CONFIG_MTD_CMDLINE_PARTS=m
CONFIG_MTD_AR7_PARTS=m
#
# User Modules And Translation Layers
#
CONFIG_MTD_BLKDEVS=m
CONFIG_MTD_BLOCK=m
CONFIG_MTD_BLOCK_RO=m
# CONFIG_FTL is not set
CONFIG_NFTL=m
# CONFIG_NFTL_RW is not set
CONFIG_INFTL=m
# CONFIG_RFD_FTL is not set
CONFIG_SSFDC=m
CONFIG_SM_FTL=m
# CONFIG_MTD_OOPS is not set
CONFIG_MTD_PARTITIONED_MASTER=y
#
# RAM/ROM/Flash chip drivers
#
CONFIG_MTD_CFI=m
CONFIG_MTD_JEDECPROBE=m
CONFIG_MTD_GEN_PROBE=m
CONFIG_MTD_CFI_ADV_OPTIONS=y
CONFIG_MTD_CFI_NOSWAP=y
# CONFIG_MTD_CFI_BE_BYTE_SWAP is not set
# CONFIG_MTD_CFI_LE_BYTE_SWAP is not set
# CONFIG_MTD_CFI_GEOMETRY is not set
CONFIG_MTD_MAP_BANK_WIDTH_1=y
CONFIG_MTD_MAP_BANK_WIDTH_2=y
CONFIG_MTD_MAP_BANK_WIDTH_4=y
# CONFIG_MTD_MAP_BANK_WIDTH_8 is not set
# CONFIG_MTD_MAP_BANK_WIDTH_16 is not set
# CONFIG_MTD_MAP_BANK_WIDTH_32 is not set
CONFIG_MTD_CFI_I1=y
CONFIG_MTD_CFI_I2=y
# CONFIG_MTD_CFI_I4 is not set
# CONFIG_MTD_CFI_I8 is not set
CONFIG_MTD_OTP=y
# CONFIG_MTD_CFI_INTELEXT is not set
# CONFIG_MTD_CFI_AMDSTD is not set
CONFIG_MTD_CFI_STAA=m
CONFIG_MTD_CFI_UTIL=m
CONFIG_MTD_RAM=m
CONFIG_MTD_ROM=m
# CONFIG_MTD_ABSENT is not set
#
# Mapping drivers for chip access
#
# CONFIG_MTD_COMPLEX_MAPPINGS is not set
# CONFIG_MTD_PHYSMAP is not set
CONFIG_MTD_AMD76XROM=m
CONFIG_MTD_ICHXROM=m
# CONFIG_MTD_ESB2ROM is not set
# CONFIG_MTD_CK804XROM is not set
# CONFIG_MTD_SCB2_FLASH is not set
# CONFIG_MTD_NETtel is not set
CONFIG_MTD_L440GX=m
# CONFIG_MTD_INTEL_VR_NOR is not set
# CONFIG_MTD_PLATRAM is not set
#
# Self-contained MTD device drivers
#
# CONFIG_MTD_PMC551 is not set
CONFIG_MTD_SLRAM=m
CONFIG_MTD_PHRAM=m
CONFIG_MTD_MTDRAM=m
CONFIG_MTDRAM_TOTAL_SIZE=4096
CONFIG_MTDRAM_ERASE_SIZE=128
CONFIG_MTD_BLOCK2MTD=m
#
# Disk-On-Chip Device Drivers
#
# CONFIG_MTD_DOCG3 is not set
CONFIG_MTD_NAND_ECC=m
# CONFIG_MTD_NAND_ECC_SMC is not set
# CONFIG_MTD_NAND is not set
CONFIG_MTD_ONENAND=m
CONFIG_MTD_ONENAND_VERIFY_WRITE=y
# CONFIG_MTD_ONENAND_GENERIC is not set
# CONFIG_MTD_ONENAND_OTP is not set
CONFIG_MTD_ONENAND_2X_PROGRAM=y
#
# LPDDR & LPDDR2 PCM memory drivers
#
CONFIG_MTD_LPDDR=m
CONFIG_MTD_QINFO_PROBE=m
# CONFIG_MTD_SPI_NOR is not set
# CONFIG_MTD_UBI is not set
# CONFIG_OF is not set
CONFIG_ARCH_MIGHT_HAVE_PC_PARPORT=y
CONFIG_PARPORT=m
# CONFIG_PARPORT_PC is not set
# CONFIG_PARPORT_GSC is not set
CONFIG_PARPORT_AX88796=m
CONFIG_PARPORT_1284=y
CONFIG_PARPORT_NOT_PC=y
CONFIG_PNP=y
# CONFIG_PNP_DEBUG_MESSAGES is not set
#
# Protocols
#
# CONFIG_ISAPNP is not set
# CONFIG_PNPBIOS is not set
CONFIG_PNPACPI=y
CONFIG_BLK_DEV=y
# CONFIG_BLK_DEV_NULL_BLK is not set
# CONFIG_BLK_DEV_FD is not set
# CONFIG_BLK_DEV_PCIESSD_MTIP32XX is not set
# CONFIG_ZRAM is not set
# CONFIG_BLK_CPQ_CISS_DA is not set
# CONFIG_BLK_DEV_DAC960 is not set
# CONFIG_BLK_DEV_UMEM is not set
# CONFIG_BLK_DEV_COW_COMMON is not set
# CONFIG_BLK_DEV_LOOP is not set
# CONFIG_BLK_DEV_DRBD is not set
# CONFIG_BLK_DEV_NBD is not set
# CONFIG_BLK_DEV_SX8 is not set
# CONFIG_BLK_DEV_RAM is not set
# CONFIG_CDROM_PKTCDVD is not set
# CONFIG_ATA_OVER_ETH is not set
# CONFIG_VIRTIO_BLK is not set
# CONFIG_BLK_DEV_HD is not set
# CONFIG_BLK_DEV_RBD is not set
# CONFIG_BLK_DEV_RSXX is not set
CONFIG_NVME_CORE=y
# CONFIG_BLK_DEV_NVME is not set
CONFIG_BLK_DEV_NVME_SCSI=y
CONFIG_NVME_FABRICS=y
CONFIG_NVME_FC=y
CONFIG_NVME_TARGET=m
CONFIG_NVME_TARGET_LOOP=m
# CONFIG_NVME_TARGET_FC is not set
#
# Misc devices
#
# CONFIG_SENSORS_LIS3LV02D is not set
CONFIG_AD525X_DPOT=m
CONFIG_AD525X_DPOT_I2C=m
CONFIG_DUMMY_IRQ=m
# CONFIG_IBM_ASM is not set
# CONFIG_PHANTOM is not set
# CONFIG_SGI_IOC4 is not set
# CONFIG_TIFM_CORE is not set
# CONFIG_ICS932S401 is not set
# CONFIG_ENCLOSURE_SERVICES is not set
# CONFIG_HP_ILO is not set
CONFIG_APDS9802ALS=m
CONFIG_ISL29003=m
CONFIG_ISL29020=m
CONFIG_SENSORS_TSL2550=m
CONFIG_SENSORS_BH1770=m
CONFIG_SENSORS_APDS990X=y
# CONFIG_HMC6352 is not set
# CONFIG_DS1682 is not set
# CONFIG_PCH_PHUB is not set
# CONFIG_USB_SWITCH_FSA9480 is not set
CONFIG_SRAM=y
CONFIG_PANEL=m
CONFIG_PANEL_PARPORT=0
CONFIG_PANEL_PROFILE=5
CONFIG_PANEL_CHANGE_MESSAGE=y
CONFIG_PANEL_BOOT_MESSAGE=""
CONFIG_C2PORT=m
# CONFIG_C2PORT_DURAMAR_2150 is not set
#
# EEPROM support
#
CONFIG_EEPROM_AT24=y
# CONFIG_EEPROM_LEGACY is not set
CONFIG_EEPROM_MAX6875=m
# CONFIG_EEPROM_93CX6 is not set
# CONFIG_EEPROM_IDT_89HPESX is not set
# CONFIG_CB710_CORE is not set
#
# Texas Instruments shared transport line discipline
#
# CONFIG_TI_ST is not set
# CONFIG_SENSORS_LIS3_I2C is not set
#
# Altera FPGA firmware download module
#
# CONFIG_ALTERA_STAPL is not set
# CONFIG_INTEL_MEI is not set
# CONFIG_INTEL_MEI_ME is not set
# CONFIG_INTEL_MEI_TXE is not set
# CONFIG_VMWARE_VMCI is not set
#
# Intel MIC Bus Driver
#
#
# SCIF Bus Driver
#
#
# VOP Bus Driver
#
#
# Intel MIC Host Driver
#
#
# Intel MIC Card Driver
#
#
# SCIF Driver
#
#
# Intel MIC Coprocessor State Management (COSM) Drivers
#
#
# VOP Driver
#
CONFIG_ECHO=m
# CONFIG_CXL_BASE is not set
# CONFIG_CXL_AFU_DRIVER_OPS is not set
CONFIG_HAVE_IDE=y
# CONFIG_IDE is not set
#
# SCSI device support
#
CONFIG_SCSI_MOD=y
CONFIG_RAID_ATTRS=y
CONFIG_SCSI=y
CONFIG_SCSI_DMA=y
CONFIG_SCSI_NETLINK=y
# CONFIG_SCSI_MQ_DEFAULT is not set
CONFIG_SCSI_PROC_FS=y
#
# SCSI support type (disk, tape, CD-ROM)
#
CONFIG_BLK_DEV_SD=y
# CONFIG_CHR_DEV_ST is not set
CONFIG_CHR_DEV_OSST=y
# CONFIG_BLK_DEV_SR is not set
CONFIG_CHR_DEV_SG=y
CONFIG_CHR_DEV_SCH=m
# CONFIG_SCSI_CONSTANTS is not set
# CONFIG_SCSI_LOGGING is not set
# CONFIG_SCSI_SCAN_ASYNC is not set
#
# SCSI Transports
#
CONFIG_SCSI_SPI_ATTRS=y
CONFIG_SCSI_FC_ATTRS=y
# CONFIG_SCSI_ISCSI_ATTRS is not set
CONFIG_SCSI_SAS_ATTRS=y
CONFIG_SCSI_SAS_LIBSAS=m
CONFIG_SCSI_SAS_ATA=y
CONFIG_SCSI_SAS_HOST_SMP=y
# CONFIG_SCSI_SRP_ATTRS is not set
CONFIG_SCSI_LOWLEVEL=y
# CONFIG_ISCSI_TCP is not set
CONFIG_ISCSI_BOOT_SYSFS=m
# CONFIG_SCSI_CXGB3_ISCSI is not set
# CONFIG_SCSI_CXGB4_ISCSI is not set
# CONFIG_SCSI_BNX2_ISCSI is not set
# CONFIG_SCSI_BNX2X_FCOE is not set
# CONFIG_BE2ISCSI is not set
# CONFIG_BLK_DEV_3W_XXXX_RAID is not set
# CONFIG_SCSI_HPSA is not set
# CONFIG_SCSI_3W_9XXX is not set
# CONFIG_SCSI_3W_SAS is not set
# CONFIG_SCSI_ACARD is not set
CONFIG_SCSI_AHA152X=y
# CONFIG_SCSI_AHA1542 is not set
# CONFIG_SCSI_AACRAID is not set
# CONFIG_SCSI_AIC7XXX is not set
# CONFIG_SCSI_AIC79XX is not set
# CONFIG_SCSI_AIC94XX is not set
# CONFIG_SCSI_MVSAS is not set
# CONFIG_SCSI_MVUMI is not set
# CONFIG_SCSI_DPT_I2O is not set
CONFIG_SCSI_ADVANSYS=y
# CONFIG_SCSI_ARCMSR is not set
# CONFIG_SCSI_ESAS2R is not set
# CONFIG_MEGARAID_NEWGEN is not set
# CONFIG_MEGARAID_LEGACY is not set
# CONFIG_MEGARAID_SAS is not set
# CONFIG_SCSI_MPT3SAS is not set
# CONFIG_SCSI_MPT2SAS is not set
# CONFIG_SCSI_SMARTPQI is not set
CONFIG_SCSI_UFSHCD=y
# CONFIG_SCSI_UFSHCD_PCI is not set
CONFIG_SCSI_UFSHCD_PLATFORM=m
CONFIG_SCSI_UFS_DWC_TC_PLATFORM=m
# CONFIG_SCSI_HPTIOP is not set
CONFIG_SCSI_BUSLOGIC=m
# CONFIG_SCSI_FLASHPOINT is not set
# CONFIG_VMWARE_PVSCSI is not set
CONFIG_LIBFC=m
CONFIG_LIBFCOE=m
# CONFIG_FCOE is not set
# CONFIG_FCOE_FNIC is not set
# CONFIG_SCSI_SNIC is not set
# CONFIG_SCSI_DMX3191D is not set
CONFIG_SCSI_EATA=m
CONFIG_SCSI_EATA_TAGGED_QUEUE=y
# CONFIG_SCSI_EATA_LINKED_COMMANDS is not set
CONFIG_SCSI_EATA_MAX_TAGS=16
CONFIG_SCSI_FUTURE_DOMAIN=m
CONFIG_SCSI_GDTH=m
# CONFIG_SCSI_ISCI is not set
CONFIG_SCSI_GENERIC_NCR5380=y
# CONFIG_SCSI_IPS is not set
# CONFIG_SCSI_INITIO is not set
# CONFIG_SCSI_INIA100 is not set
# CONFIG_SCSI_NCR53C406A is not set
# CONFIG_SCSI_STEX is not set
# CONFIG_SCSI_SYM53C8XX_2 is not set
# CONFIG_SCSI_IPR is not set
CONFIG_SCSI_QLOGIC_FAS=m
# CONFIG_SCSI_QLOGIC_1280 is not set
# CONFIG_SCSI_QLA_FC is not set
# CONFIG_SCSI_QLA_ISCSI is not set
# CONFIG_SCSI_LPFC is not set
CONFIG_SCSI_SYM53C416=y
# CONFIG_SCSI_DC395x is not set
# CONFIG_SCSI_AM53C974 is not set
# CONFIG_SCSI_NSP32 is not set
# CONFIG_SCSI_WD719X is not set
CONFIG_SCSI_DEBUG=y
# CONFIG_SCSI_PMCRAID is not set
# CONFIG_SCSI_PM8001 is not set
# CONFIG_SCSI_BFA_FC is not set
CONFIG_SCSI_VIRTIO=m
# CONFIG_SCSI_CHELSIO_FCOE is not set
# CONFIG_SCSI_LOWLEVEL_PCMCIA is not set
CONFIG_SCSI_DH=y
# CONFIG_SCSI_DH_RDAC is not set
# CONFIG_SCSI_DH_HP_SW is not set
CONFIG_SCSI_DH_EMC=m
# CONFIG_SCSI_DH_ALUA is not set
# CONFIG_SCSI_OSD_INITIATOR is not set
CONFIG_ATA=m
# CONFIG_ATA_NONSTANDARD is not set
# CONFIG_ATA_VERBOSE_ERROR is not set
CONFIG_ATA_ACPI=y
# CONFIG_SATA_ZPODD is not set
# CONFIG_SATA_PMP is not set
#
# Controllers with non-SFF native interface
#
# CONFIG_SATA_AHCI is not set
# CONFIG_SATA_AHCI_PLATFORM is not set
# CONFIG_SATA_INIC162X is not set
# CONFIG_SATA_ACARD_AHCI is not set
# CONFIG_SATA_SIL24 is not set
# CONFIG_ATA_SFF is not set
CONFIG_MD=y
CONFIG_BLK_DEV_MD=y
# CONFIG_MD_AUTODETECT is not set
# CONFIG_MD_LINEAR is not set
# CONFIG_MD_RAID0 is not set
CONFIG_MD_RAID1=y
CONFIG_MD_RAID10=y
CONFIG_MD_RAID456=y
CONFIG_MD_MULTIPATH=y
CONFIG_MD_FAULTY=m
# CONFIG_MD_CLUSTER is not set
# CONFIG_BCACHE is not set
CONFIG_BLK_DEV_DM_BUILTIN=y
CONFIG_BLK_DEV_DM=y
# CONFIG_DM_MQ_DEFAULT is not set
# CONFIG_DM_DEBUG is not set
CONFIG_DM_BUFIO=y
# CONFIG_DM_DEBUG_BLOCK_MANAGER_LOCKING is not set
CONFIG_DM_BIO_PRISON=m
CONFIG_DM_PERSISTENT_DATA=m
CONFIG_DM_CRYPT=y
CONFIG_DM_SNAPSHOT=y
# CONFIG_DM_THIN_PROVISIONING is not set
# CONFIG_DM_CACHE is not set
CONFIG_DM_ERA=m
CONFIG_DM_MIRROR=y
CONFIG_DM_LOG_USERSPACE=y
CONFIG_DM_RAID=y
CONFIG_DM_ZERO=m
CONFIG_DM_MULTIPATH=m
CONFIG_DM_MULTIPATH_QL=m
CONFIG_DM_MULTIPATH_ST=m
CONFIG_DM_DELAY=m
CONFIG_DM_UEVENT=y
CONFIG_DM_FLAKEY=m
CONFIG_DM_VERITY=m
# CONFIG_DM_VERITY_FEC is not set
CONFIG_DM_SWITCH=y
# CONFIG_DM_LOG_WRITES is not set
CONFIG_TARGET_CORE=m
CONFIG_TCM_IBLOCK=m
# CONFIG_TCM_FILEIO is not set
CONFIG_TCM_PSCSI=m
CONFIG_TCM_USER2=m
CONFIG_LOOPBACK_TARGET=m
CONFIG_TCM_FC=m
# CONFIG_ISCSI_TARGET is not set
# CONFIG_FUSION is not set
#
# IEEE 1394 (FireWire) support
#
# CONFIG_FIREWIRE is not set
# CONFIG_FIREWIRE_NOSY is not set
CONFIG_MACINTOSH_DRIVERS=y
# CONFIG_MAC_EMUMOUSEBTN is not set
# CONFIG_NETDEVICES is not set
CONFIG_NVM=y
# CONFIG_NVM_DEBUG is not set
# CONFIG_NVM_RRPC is not set
#
# Input device support
#
CONFIG_INPUT=y
CONFIG_INPUT_LEDS=m
# CONFIG_INPUT_FF_MEMLESS is not set
# CONFIG_INPUT_POLLDEV is not set
# CONFIG_INPUT_SPARSEKMAP is not set
# CONFIG_INPUT_MATRIXKMAP is not set
#
# Userland interfaces
#
CONFIG_INPUT_MOUSEDEV=y
CONFIG_INPUT_MOUSEDEV_PSAUX=y
CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
# CONFIG_INPUT_JOYDEV is not set
# CONFIG_INPUT_EVDEV is not set
# CONFIG_INPUT_EVBUG is not set
#
# Input Device Drivers
#
CONFIG_INPUT_KEYBOARD=y
# CONFIG_KEYBOARD_ADC is not set
# CONFIG_KEYBOARD_ADP5520 is not set
# CONFIG_KEYBOARD_ADP5588 is not set
# CONFIG_KEYBOARD_ADP5589 is not set
CONFIG_KEYBOARD_ATKBD=y
# CONFIG_KEYBOARD_QT1070 is not set
# CONFIG_KEYBOARD_QT2160 is not set
# CONFIG_KEYBOARD_LKKBD is not set
# CONFIG_KEYBOARD_GPIO is not set
# CONFIG_KEYBOARD_GPIO_POLLED is not set
# CONFIG_KEYBOARD_TCA6416 is not set
# CONFIG_KEYBOARD_TCA8418 is not set
# CONFIG_KEYBOARD_MATRIX is not set
# CONFIG_KEYBOARD_LM8323 is not set
# CONFIG_KEYBOARD_LM8333 is not set
# CONFIG_KEYBOARD_MAX7359 is not set
# CONFIG_KEYBOARD_MCS is not set
# CONFIG_KEYBOARD_MPR121 is not set
# CONFIG_KEYBOARD_NEWTON is not set
# CONFIG_KEYBOARD_OPENCORES is not set
# CONFIG_KEYBOARD_SAMSUNG is not set
# CONFIG_KEYBOARD_STOWAWAY is not set
# CONFIG_KEYBOARD_SUNKBD is not set
# CONFIG_KEYBOARD_TM2_TOUCHKEY is not set
# CONFIG_KEYBOARD_XTKBD is not set
# CONFIG_KEYBOARD_CROS_EC is not set
CONFIG_INPUT_MOUSE=y
CONFIG_MOUSE_PS2=y
CONFIG_MOUSE_PS2_ALPS=y
CONFIG_MOUSE_PS2_BYD=y
CONFIG_MOUSE_PS2_LOGIPS2PP=y
CONFIG_MOUSE_PS2_SYNAPTICS=y
CONFIG_MOUSE_PS2_CYPRESS=y
CONFIG_MOUSE_PS2_LIFEBOOK=y
CONFIG_MOUSE_PS2_TRACKPOINT=y
# CONFIG_MOUSE_PS2_ELANTECH is not set
# CONFIG_MOUSE_PS2_SENTELIC is not set
# CONFIG_MOUSE_PS2_TOUCHKIT is not set
CONFIG_MOUSE_PS2_FOCALTECH=y
# CONFIG_MOUSE_PS2_VMMOUSE is not set
# CONFIG_MOUSE_SERIAL is not set
# CONFIG_MOUSE_APPLETOUCH is not set
# CONFIG_MOUSE_BCM5974 is not set
# CONFIG_MOUSE_CYAPA is not set
# CONFIG_MOUSE_ELAN_I2C is not set
# CONFIG_MOUSE_INPORT is not set
# CONFIG_MOUSE_LOGIBM is not set
# CONFIG_MOUSE_PC110PAD is not set
# CONFIG_MOUSE_VSXXXAA is not set
# CONFIG_MOUSE_GPIO is not set
# CONFIG_MOUSE_SYNAPTICS_I2C is not set
# CONFIG_MOUSE_SYNAPTICS_USB is not set
# CONFIG_INPUT_JOYSTICK is not set
# CONFIG_INPUT_TABLET is not set
# CONFIG_INPUT_TOUCHSCREEN is not set
# CONFIG_INPUT_MISC is not set
# CONFIG_RMI4_CORE is not set
#
# Hardware I/O ports
#
CONFIG_SERIO=y
CONFIG_ARCH_MIGHT_HAVE_PC_SERIO=y
CONFIG_SERIO_I8042=y
CONFIG_SERIO_SERPORT=y
CONFIG_SERIO_CT82C710=y
# CONFIG_SERIO_PARKBD is not set
# CONFIG_SERIO_PCIPS2 is not set
CONFIG_SERIO_LIBPS2=y
CONFIG_SERIO_RAW=y
CONFIG_SERIO_ALTERA_PS2=m
CONFIG_SERIO_PS2MULT=m
# CONFIG_SERIO_ARC_PS2 is not set
CONFIG_USERIO=y
CONFIG_GAMEPORT=y
CONFIG_GAMEPORT_NS558=m
# CONFIG_GAMEPORT_L4 is not set
# CONFIG_GAMEPORT_EMU10K1 is not set
# CONFIG_GAMEPORT_FM801 is not set
#
# Character devices
#
CONFIG_TTY=y
# CONFIG_VT is not set
CONFIG_UNIX98_PTYS=y
CONFIG_LEGACY_PTYS=y
CONFIG_LEGACY_PTY_COUNT=256
# CONFIG_SERIAL_NONSTANDARD is not set
# CONFIG_NOZOMI is not set
# CONFIG_N_GSM is not set
# CONFIG_TRACE_SINK is not set
CONFIG_DEVMEM=y
# CONFIG_DEVKMEM is not set
#
# Serial drivers
#
CONFIG_SERIAL_EARLYCON=y
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_DEPRECATED_OPTIONS=y
CONFIG_SERIAL_8250_PNP=y
# CONFIG_SERIAL_8250_FINTEK is not set
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_SERIAL_8250_DMA=y
CONFIG_SERIAL_8250_PCI=y
CONFIG_SERIAL_8250_EXAR=y
# CONFIG_SERIAL_8250_CS is not set
CONFIG_SERIAL_8250_NR_UARTS=4
CONFIG_SERIAL_8250_RUNTIME_UARTS=4
# CONFIG_SERIAL_8250_EXTENDED is not set
# CONFIG_SERIAL_8250_FSL is not set
# CONFIG_SERIAL_8250_DW is not set
# CONFIG_SERIAL_8250_RT288X is not set
CONFIG_SERIAL_8250_LPSS=y
CONFIG_SERIAL_8250_MID=y
# CONFIG_SERIAL_8250_MOXA is not set
#
# Non-8250 serial port support
#
# CONFIG_SERIAL_UARTLITE is not set
CONFIG_SERIAL_CORE=y
CONFIG_SERIAL_CORE_CONSOLE=y
# CONFIG_SERIAL_JSM is not set
# CONFIG_SERIAL_SCCNXP is not set
# CONFIG_SERIAL_SC16IS7XX is not set
# CONFIG_SERIAL_TIMBERDALE is not set
# CONFIG_SERIAL_ALTERA_JTAGUART is not set
# CONFIG_SERIAL_ALTERA_UART is not set
# CONFIG_SERIAL_PCH_UART is not set
# CONFIG_SERIAL_ARC is not set
# CONFIG_SERIAL_RP2 is not set
# CONFIG_SERIAL_FSL_LPUART is not set
# CONFIG_SERIAL_DEV_BUS is not set
# CONFIG_TTY_PRINTK is not set
# CONFIG_PRINTER is not set
# CONFIG_PPDEV is not set
# CONFIG_VIRTIO_CONSOLE is not set
# CONFIG_IPMI_HANDLER is not set
CONFIG_HW_RANDOM=m
CONFIG_HW_RANDOM_TIMERIOMEM=m
CONFIG_HW_RANDOM_INTEL=m
CONFIG_HW_RANDOM_AMD=m
CONFIG_HW_RANDOM_GEODE=m
CONFIG_HW_RANDOM_VIA=m
CONFIG_HW_RANDOM_VIRTIO=m
# CONFIG_HW_RANDOM_TPM is not set
CONFIG_NVRAM=y
CONFIG_DTLK=y
# CONFIG_R3964 is not set
# CONFIG_APPLICOM is not set
# CONFIG_SONYPI is not set
#
# PCMCIA character devices
#
# CONFIG_SYNCLINK_CS is not set
# CONFIG_CARDMAN_4000 is not set
# CONFIG_CARDMAN_4040 is not set
CONFIG_SCR24X=m
# CONFIG_MWAVE is not set
CONFIG_PC8736x_GPIO=m
CONFIG_NSC_GPIO=m
CONFIG_RAW_DRIVER=y
CONFIG_MAX_RAW_DEVS=256
# CONFIG_HPET is not set
# CONFIG_HANGCHECK_TIMER is not set
CONFIG_TCG_TPM=m
# CONFIG_TCG_TIS is not set
CONFIG_TCG_TIS_I2C_ATMEL=m
CONFIG_TCG_TIS_I2C_INFINEON=m
# CONFIG_TCG_TIS_I2C_NUVOTON is not set
CONFIG_TCG_NSC=m
# CONFIG_TCG_ATMEL is not set
CONFIG_TCG_INFINEON=m
# CONFIG_TCG_CRB is not set
# CONFIG_TCG_VTPM_PROXY is not set
CONFIG_TCG_TIS_ST33ZP24=m
CONFIG_TCG_TIS_ST33ZP24_I2C=m
CONFIG_TELCLOCK=y
CONFIG_DEVPORT=y
# CONFIG_XILLYBUS is not set
#
# I2C support
#
CONFIG_I2C=y
CONFIG_ACPI_I2C_OPREGION=y
CONFIG_I2C_BOARDINFO=y
# CONFIG_I2C_COMPAT is not set
# CONFIG_I2C_CHARDEV is not set
CONFIG_I2C_MUX=y
#
# Multiplexer I2C Chip support
#
CONFIG_I2C_MUX_GPIO=y
CONFIG_I2C_MUX_PCA9541=m
# CONFIG_I2C_MUX_PCA954x is not set
CONFIG_I2C_MUX_REG=m
CONFIG_I2C_MUX_MLXCPLD=m
# CONFIG_I2C_HELPER_AUTO is not set
CONFIG_I2C_SMBUS=m
#
# I2C Algorithms
#
CONFIG_I2C_ALGOBIT=y
CONFIG_I2C_ALGOPCF=m
CONFIG_I2C_ALGOPCA=m
#
# I2C Hardware Bus support
#
#
# PC SMBus host controller drivers
#
# CONFIG_I2C_ALI1535 is not set
# CONFIG_I2C_ALI1563 is not set
# CONFIG_I2C_ALI15X3 is not set
# CONFIG_I2C_AMD756 is not set
# CONFIG_I2C_AMD8111 is not set
# CONFIG_I2C_I801 is not set
# CONFIG_I2C_ISCH is not set
# CONFIG_I2C_ISMT is not set
# CONFIG_I2C_PIIX4 is not set
# CONFIG_I2C_NFORCE2 is not set
# CONFIG_I2C_SIS5595 is not set
# CONFIG_I2C_SIS630 is not set
# CONFIG_I2C_SIS96X is not set
# CONFIG_I2C_VIA is not set
# CONFIG_I2C_VIAPRO is not set
#
# ACPI drivers
#
# CONFIG_I2C_SCMI is not set
#
# I2C system bus drivers (mostly embedded / system-on-chip)
#
CONFIG_I2C_CBUS_GPIO=m
# CONFIG_I2C_DESIGNWARE_PLATFORM is not set
# CONFIG_I2C_DESIGNWARE_PCI is not set
# CONFIG_I2C_EG20T is not set
# CONFIG_I2C_EMEV2 is not set
CONFIG_I2C_GPIO=m
# CONFIG_I2C_KEMPLD is not set
CONFIG_I2C_OCORES=m
CONFIG_I2C_PCA_PLATFORM=m
# CONFIG_I2C_PXA_PCI is not set
CONFIG_I2C_SIMTEC=m
CONFIG_I2C_XILINX=y
#
# External I2C/SMBus adapter drivers
#
# CONFIG_I2C_DIOLAN_U2C is not set
CONFIG_I2C_DLN2=y
CONFIG_I2C_PARPORT=m
# CONFIG_I2C_PARPORT_LIGHT is not set
CONFIG_I2C_ROBOTFUZZ_OSIF=y
# CONFIG_I2C_TAOS_EVM is not set
CONFIG_I2C_TINY_USB=m
#
# Other I2C/SMBus bus drivers
#
# CONFIG_I2C_ELEKTOR is not set
# CONFIG_I2C_PCA_ISA is not set
# CONFIG_I2C_CROS_EC_TUNNEL is not set
# CONFIG_SCx200_ACB is not set
CONFIG_I2C_STUB=m
CONFIG_I2C_SLAVE=y
CONFIG_I2C_SLAVE_EEPROM=y
# CONFIG_I2C_DEBUG_CORE is not set
# CONFIG_I2C_DEBUG_ALGO is not set
# CONFIG_I2C_DEBUG_BUS is not set
# CONFIG_SPI is not set
CONFIG_SPMI=y
# CONFIG_HSI is not set
#
# PPS support
#
CONFIG_PPS=y
# CONFIG_PPS_DEBUG is not set
CONFIG_NTP_PPS=y
#
# PPS clients support
#
# CONFIG_PPS_CLIENT_KTIMER is not set
# CONFIG_PPS_CLIENT_LDISC is not set
CONFIG_PPS_CLIENT_PARPORT=m
# CONFIG_PPS_CLIENT_GPIO is not set
#
# PPS generators support
#
#
# PTP clock support
#
#
# Enable PHYLIB and NETWORK_PHY_TIMESTAMPING to see the additional clocks.
#
# CONFIG_PTP_1588_CLOCK_PCH is not set
CONFIG_GPIOLIB=y
CONFIG_GPIO_ACPI=y
CONFIG_GPIOLIB_IRQCHIP=y
CONFIG_DEBUG_GPIO=y
CONFIG_GPIO_SYSFS=y
CONFIG_GPIO_GENERIC=y
CONFIG_GPIO_MAX730X=y
#
# Memory mapped GPIO drivers
#
# CONFIG_GPIO_AMDPT is not set
# CONFIG_GPIO_AXP209 is not set
CONFIG_GPIO_DWAPB=m
# CONFIG_GPIO_EXAR is not set
CONFIG_GPIO_GENERIC_PLATFORM=y
# CONFIG_GPIO_ICH is not set
# CONFIG_GPIO_LYNXPOINT is not set
# CONFIG_GPIO_MOCKUP is not set
# CONFIG_GPIO_VX855 is not set
#
# Port-mapped I/O GPIO drivers
#
CONFIG_GPIO_104_DIO_48E=m
CONFIG_GPIO_104_IDIO_16=m
CONFIG_GPIO_104_IDI_48=y
# CONFIG_GPIO_F7188X is not set
CONFIG_GPIO_GPIO_MM=m
CONFIG_GPIO_IT87=m
# CONFIG_GPIO_SCH is not set
# CONFIG_GPIO_SCH311X is not set
CONFIG_GPIO_WS16C48=m
#
# I2C GPIO expanders
#
CONFIG_GPIO_ADP5588=y
# CONFIG_GPIO_ADP5588_IRQ is not set
CONFIG_GPIO_MAX7300=y
CONFIG_GPIO_MAX732X=y
CONFIG_GPIO_MAX732X_IRQ=y
CONFIG_GPIO_PCA953X=y
CONFIG_GPIO_PCA953X_IRQ=y
CONFIG_GPIO_PCF857X=m
CONFIG_GPIO_TPIC2810=m
#
# MFD GPIO expanders
#
# CONFIG_GPIO_ADP5520 is not set
CONFIG_GPIO_DA9055=y
# CONFIG_GPIO_DLN2 is not set
CONFIG_GPIO_KEMPLD=y
CONFIG_GPIO_LP3943=m
CONFIG_GPIO_LP873X=m
CONFIG_GPIO_PALMAS=y
# CONFIG_GPIO_RC5T583 is not set
CONFIG_GPIO_TPS6586X=y
# CONFIG_GPIO_TPS65910 is not set
# CONFIG_GPIO_TWL6040 is not set
# CONFIG_GPIO_UCB1400 is not set
CONFIG_GPIO_WM8994=m
#
# PCI GPIO expanders
#
# CONFIG_GPIO_AMD8111 is not set
# CONFIG_GPIO_BT8XX is not set
# CONFIG_GPIO_ML_IOH is not set
# CONFIG_GPIO_PCH is not set
# CONFIG_GPIO_PCI_IDIO_16 is not set
# CONFIG_GPIO_RDC321X is not set
#
# SPI or I2C GPIO expanders
#
#
# USB GPIO expanders
#
CONFIG_W1=y
CONFIG_W1_CON=y
#
# 1-wire Bus Masters
#
# CONFIG_W1_MASTER_MATROX is not set
# CONFIG_W1_MASTER_DS2490 is not set
# CONFIG_W1_MASTER_DS2482 is not set
CONFIG_W1_MASTER_DS1WM=y
CONFIG_W1_MASTER_GPIO=y
#
# 1-wire Slaves
#
# CONFIG_W1_SLAVE_THERM is not set
CONFIG_W1_SLAVE_SMEM=y
# CONFIG_W1_SLAVE_DS2405 is not set
CONFIG_W1_SLAVE_DS2408=y
# CONFIG_W1_SLAVE_DS2408_READBACK is not set
CONFIG_W1_SLAVE_DS2413=m
# CONFIG_W1_SLAVE_DS2406 is not set
# CONFIG_W1_SLAVE_DS2423 is not set
# CONFIG_W1_SLAVE_DS2431 is not set
# CONFIG_W1_SLAVE_DS2433 is not set
CONFIG_W1_SLAVE_DS2760=y
# CONFIG_W1_SLAVE_DS2780 is not set
CONFIG_W1_SLAVE_DS2781=y
CONFIG_W1_SLAVE_DS28E04=y
CONFIG_W1_SLAVE_BQ27000=y
# CONFIG_POWER_AVS is not set
# CONFIG_POWER_RESET is not set
CONFIG_POWER_SUPPLY=y
# CONFIG_POWER_SUPPLY_DEBUG is not set
# CONFIG_PDA_POWER is not set
# CONFIG_GENERIC_ADC_BATTERY is not set
# CONFIG_TEST_POWER is not set
# CONFIG_BATTERY_DS2760 is not set
# CONFIG_BATTERY_DS2780 is not set
# CONFIG_BATTERY_DS2781 is not set
# CONFIG_BATTERY_DS2782 is not set
# CONFIG_BATTERY_SBS is not set
# CONFIG_CHARGER_SBS is not set
# CONFIG_BATTERY_BQ27XXX is not set
# CONFIG_AXP288_FUEL_GAUGE is not set
# CONFIG_BATTERY_MAX17040 is not set
# CONFIG_BATTERY_MAX17042 is not set
# CONFIG_CHARGER_PCF50633 is not set
# CONFIG_CHARGER_ISP1704 is not set
# CONFIG_CHARGER_MAX8903 is not set
# CONFIG_CHARGER_LP8727 is not set
# CONFIG_CHARGER_LP8788 is not set
# CONFIG_CHARGER_GPIO is not set
# CONFIG_CHARGER_MAX77693 is not set
# CONFIG_CHARGER_BQ2415X is not set
# CONFIG_CHARGER_BQ24190 is not set
# CONFIG_CHARGER_BQ24257 is not set
# CONFIG_CHARGER_BQ24735 is not set
# CONFIG_CHARGER_BQ25890 is not set
# CONFIG_CHARGER_SMB347 is not set
# CONFIG_CHARGER_TPS65090 is not set
# CONFIG_CHARGER_TPS65217 is not set
# CONFIG_BATTERY_GAUGE_LTC2941 is not set
# CONFIG_BATTERY_RT5033 is not set
# CONFIG_CHARGER_RT9455 is not set
# CONFIG_AXP20X_POWER is not set
CONFIG_HWMON=m
CONFIG_HWMON_VID=m
# CONFIG_HWMON_DEBUG_CHIP is not set
#
# Native drivers
#
# CONFIG_SENSORS_ABITUGURU is not set
# CONFIG_SENSORS_ABITUGURU3 is not set
# CONFIG_SENSORS_AD7414 is not set
# CONFIG_SENSORS_AD7418 is not set
# CONFIG_SENSORS_ADM1021 is not set
# CONFIG_SENSORS_ADM1025 is not set
CONFIG_SENSORS_ADM1026=m
CONFIG_SENSORS_ADM1029=m
CONFIG_SENSORS_ADM1031=m
CONFIG_SENSORS_ADM9240=m
# CONFIG_SENSORS_ADT7410 is not set
CONFIG_SENSORS_ADT7411=m
# CONFIG_SENSORS_ADT7462 is not set
# CONFIG_SENSORS_ADT7470 is not set
# CONFIG_SENSORS_ADT7475 is not set
CONFIG_SENSORS_ASC7621=m
# CONFIG_SENSORS_K8TEMP is not set
# CONFIG_SENSORS_K10TEMP is not set
# CONFIG_SENSORS_FAM15H_POWER is not set
# CONFIG_SENSORS_APPLESMC is not set
CONFIG_SENSORS_ASB100=m
# CONFIG_SENSORS_ATXP1 is not set
CONFIG_SENSORS_DS620=m
CONFIG_SENSORS_DS1621=m
CONFIG_SENSORS_DELL_SMM=m
# CONFIG_SENSORS_DA9055 is not set
# CONFIG_SENSORS_I5K_AMB is not set
CONFIG_SENSORS_F71805F=m
# CONFIG_SENSORS_F71882FG is not set
CONFIG_SENSORS_F75375S=m
# CONFIG_SENSORS_FSCHMD is not set
CONFIG_SENSORS_FTSTEUTATES=m
CONFIG_SENSORS_GL518SM=m
# CONFIG_SENSORS_GL520SM is not set
# CONFIG_SENSORS_G760A is not set
# CONFIG_SENSORS_G762 is not set
CONFIG_SENSORS_GPIO_FAN=m
# CONFIG_SENSORS_HIH6130 is not set
CONFIG_SENSORS_IIO_HWMON=m
# CONFIG_SENSORS_I5500 is not set
CONFIG_SENSORS_CORETEMP=m
CONFIG_SENSORS_IT87=m
# CONFIG_SENSORS_JC42 is not set
# CONFIG_SENSORS_POWR1220 is not set
CONFIG_SENSORS_LINEAGE=m
CONFIG_SENSORS_LTC2945=m
CONFIG_SENSORS_LTC2990=m
CONFIG_SENSORS_LTC4151=m
CONFIG_SENSORS_LTC4215=m
CONFIG_SENSORS_LTC4222=m
CONFIG_SENSORS_LTC4245=m
CONFIG_SENSORS_LTC4260=m
CONFIG_SENSORS_LTC4261=m
CONFIG_SENSORS_MAX16065=m
CONFIG_SENSORS_MAX1619=m
# CONFIG_SENSORS_MAX1668 is not set
CONFIG_SENSORS_MAX197=m
CONFIG_SENSORS_MAX6639=m
CONFIG_SENSORS_MAX6642=m
CONFIG_SENSORS_MAX6650=m
# CONFIG_SENSORS_MAX6697 is not set
CONFIG_SENSORS_MAX31790=m
CONFIG_SENSORS_MCP3021=m
CONFIG_SENSORS_TC654=m
CONFIG_SENSORS_MENF21BMC_HWMON=m
# CONFIG_SENSORS_LM63 is not set
CONFIG_SENSORS_LM73=m
# CONFIG_SENSORS_LM75 is not set
CONFIG_SENSORS_LM77=m
CONFIG_SENSORS_LM78=m
# CONFIG_SENSORS_LM80 is not set
CONFIG_SENSORS_LM83=m
# CONFIG_SENSORS_LM85 is not set
# CONFIG_SENSORS_LM87 is not set
CONFIG_SENSORS_LM90=m
CONFIG_SENSORS_LM92=m
# CONFIG_SENSORS_LM93 is not set
CONFIG_SENSORS_LM95234=m
CONFIG_SENSORS_LM95241=m
# CONFIG_SENSORS_LM95245 is not set
CONFIG_SENSORS_PC87360=m
# CONFIG_SENSORS_PC87427 is not set
CONFIG_SENSORS_NTC_THERMISTOR=m
# CONFIG_SENSORS_NCT6683 is not set
CONFIG_SENSORS_NCT6775=m
CONFIG_SENSORS_NCT7802=m
CONFIG_SENSORS_NCT7904=m
CONFIG_SENSORS_PCF8591=m
CONFIG_PMBUS=m
CONFIG_SENSORS_PMBUS=m
CONFIG_SENSORS_ADM1275=m
CONFIG_SENSORS_LM25066=m
CONFIG_SENSORS_LTC2978=m
CONFIG_SENSORS_LTC3815=m
CONFIG_SENSORS_MAX16064=m
CONFIG_SENSORS_MAX20751=m
CONFIG_SENSORS_MAX34440=m
CONFIG_SENSORS_MAX8688=m
CONFIG_SENSORS_TPS40422=m
# CONFIG_SENSORS_UCD9000 is not set
CONFIG_SENSORS_UCD9200=m
CONFIG_SENSORS_ZL6100=m
# CONFIG_SENSORS_SHT15 is not set
CONFIG_SENSORS_SHT21=m
CONFIG_SENSORS_SHT3x=m
# CONFIG_SENSORS_SHTC1 is not set
# CONFIG_SENSORS_SIS5595 is not set
CONFIG_SENSORS_DME1737=m
# CONFIG_SENSORS_EMC1403 is not set
# CONFIG_SENSORS_EMC2103 is not set
CONFIG_SENSORS_EMC6W201=m
CONFIG_SENSORS_SMSC47M1=m
CONFIG_SENSORS_SMSC47M192=m
CONFIG_SENSORS_SMSC47B397=m
CONFIG_SENSORS_SCH56XX_COMMON=m
CONFIG_SENSORS_SCH5627=m
CONFIG_SENSORS_SCH5636=m
# CONFIG_SENSORS_STTS751 is not set
CONFIG_SENSORS_SMM665=m
# CONFIG_SENSORS_ADC128D818 is not set
CONFIG_SENSORS_ADS1015=m
CONFIG_SENSORS_ADS7828=m
# CONFIG_SENSORS_AMC6821 is not set
# CONFIG_SENSORS_INA209 is not set
# CONFIG_SENSORS_INA2XX is not set
CONFIG_SENSORS_INA3221=m
# CONFIG_SENSORS_TC74 is not set
CONFIG_SENSORS_THMC50=m
CONFIG_SENSORS_TMP102=m
CONFIG_SENSORS_TMP103=m
CONFIG_SENSORS_TMP108=m
CONFIG_SENSORS_TMP401=m
CONFIG_SENSORS_TMP421=m
CONFIG_SENSORS_VIA_CPUTEMP=m
# CONFIG_SENSORS_VIA686A is not set
CONFIG_SENSORS_VT1211=m
# CONFIG_SENSORS_VT8231 is not set
CONFIG_SENSORS_W83781D=m
CONFIG_SENSORS_W83791D=m
# CONFIG_SENSORS_W83792D is not set
# CONFIG_SENSORS_W83793 is not set
CONFIG_SENSORS_W83795=m
# CONFIG_SENSORS_W83795_FANCTRL is not set
# CONFIG_SENSORS_W83L785TS is not set
CONFIG_SENSORS_W83L786NG=m
# CONFIG_SENSORS_W83627HF is not set
# CONFIG_SENSORS_W83627EHF is not set
#
# ACPI drivers
#
# CONFIG_SENSORS_ACPI_POWER is not set
# CONFIG_SENSORS_ATK0110 is not set
CONFIG_THERMAL=y
CONFIG_THERMAL_WRITABLE_TRIPS=y
# CONFIG_THERMAL_DEFAULT_GOV_STEP_WISE is not set
CONFIG_THERMAL_DEFAULT_GOV_FAIR_SHARE=y
# CONFIG_THERMAL_DEFAULT_GOV_USER_SPACE is not set
# CONFIG_THERMAL_DEFAULT_GOV_POWER_ALLOCATOR is not set
CONFIG_THERMAL_GOV_FAIR_SHARE=y
CONFIG_THERMAL_GOV_STEP_WISE=y
CONFIG_THERMAL_GOV_BANG_BANG=y
CONFIG_THERMAL_GOV_USER_SPACE=y
CONFIG_THERMAL_GOV_POWER_ALLOCATOR=y
# CONFIG_THERMAL_EMULATION is not set
CONFIG_INTEL_POWERCLAMP=m
CONFIG_INTEL_SOC_DTS_IOSF_CORE=m
CONFIG_INTEL_SOC_DTS_THERMAL=m
#
# ACPI INT340X thermal drivers
#
# CONFIG_INT340X_THERMAL is not set
# CONFIG_INTEL_PCH_THERMAL is not set
CONFIG_GENERIC_ADC_THERMAL=m
CONFIG_WATCHDOG=y
CONFIG_WATCHDOG_CORE=y
CONFIG_WATCHDOG_NOWAYOUT=y
CONFIG_WATCHDOG_SYSFS=y
#
# Watchdog Device Drivers
#
# CONFIG_SOFT_WATCHDOG is not set
CONFIG_DA9055_WATCHDOG=m
CONFIG_DA9063_WATCHDOG=m
CONFIG_DA9062_WATCHDOG=m
# CONFIG_MENF21BMC_WATCHDOG is not set
# CONFIG_WDAT_WDT is not set
CONFIG_XILINX_WATCHDOG=m
CONFIG_ZIIRAVE_WATCHDOG=m
# CONFIG_CADENCE_WATCHDOG is not set
# CONFIG_DW_WATCHDOG is not set
CONFIG_MAX63XX_WATCHDOG=y
CONFIG_ACQUIRE_WDT=y
CONFIG_ADVANTECH_WDT=m
# CONFIG_ALIM1535_WDT is not set
# CONFIG_ALIM7101_WDT is not set
# CONFIG_EBC_C384_WDT is not set
# CONFIG_F71808E_WDT is not set
# CONFIG_SP5100_TCO is not set
CONFIG_SBC_FITPC2_WATCHDOG=m
# CONFIG_EUROTECH_WDT is not set
CONFIG_IB700_WDT=m
# CONFIG_IBMASR is not set
CONFIG_WAFER_WDT=m
# CONFIG_I6300ESB_WDT is not set
# CONFIG_IE6XX_WDT is not set
# CONFIG_ITCO_WDT is not set
CONFIG_IT8712F_WDT=y
CONFIG_IT87_WDT=y
# CONFIG_HP_WATCHDOG is not set
CONFIG_KEMPLD_WDT=y
CONFIG_SC1200_WDT=m
CONFIG_PC87413_WDT=y
# CONFIG_NV_TCO is not set
# CONFIG_60XX_WDT is not set
# CONFIG_SBC8360_WDT is not set
# CONFIG_SBC7240_WDT is not set
CONFIG_CPU5_WDT=y
CONFIG_SMSC_SCH311X_WDT=y
CONFIG_SMSC37B787_WDT=y
# CONFIG_VIA_WDT is not set
# CONFIG_W83627HF_WDT is not set
CONFIG_W83877F_WDT=m
# CONFIG_W83977F_WDT is not set
# CONFIG_MACHZ_WDT is not set
CONFIG_SBC_EPX_C3_WATCHDOG=y
# CONFIG_NI903X_WDT is not set
# CONFIG_NIC7018_WDT is not set
CONFIG_MEN_A21_WDT=m
#
# ISA-based Watchdog Cards
#
# CONFIG_PCWATCHDOG is not set
CONFIG_MIXCOMWD=y
# CONFIG_WDT is not set
#
# PCI-based Watchdog Cards
#
# CONFIG_PCIPCWATCHDOG is not set
# CONFIG_WDTPCI is not set
#
# USB-based Watchdog Cards
#
CONFIG_USBPCWATCHDOG=m
#
# Watchdog Pretimeout Governors
#
CONFIG_WATCHDOG_PRETIMEOUT_GOV=y
# CONFIG_WATCHDOG_PRETIMEOUT_DEFAULT_GOV_NOOP is not set
CONFIG_WATCHDOG_PRETIMEOUT_DEFAULT_GOV_PANIC=y
CONFIG_WATCHDOG_PRETIMEOUT_GOV_NOOP=y
CONFIG_WATCHDOG_PRETIMEOUT_GOV_PANIC=y
CONFIG_SSB_POSSIBLE=y
#
# Sonics Silicon Backplane
#
# CONFIG_SSB is not set
CONFIG_BCMA_POSSIBLE=y
#
# Broadcom specific AMBA
#
CONFIG_BCMA=m
CONFIG_BCMA_HOST_PCI_POSSIBLE=y
CONFIG_BCMA_HOST_PCI=y
CONFIG_BCMA_HOST_SOC=y
CONFIG_BCMA_DRIVER_PCI=y
CONFIG_BCMA_SFLASH=y
# CONFIG_BCMA_DRIVER_GMAC_CMN is not set
# CONFIG_BCMA_DRIVER_GPIO is not set
CONFIG_BCMA_DEBUG=y
#
# Multifunction device drivers
#
CONFIG_MFD_CORE=y
# CONFIG_MFD_CS5535 is not set
CONFIG_MFD_AS3711=y
CONFIG_PMIC_ADP5520=y
# CONFIG_MFD_AAT2870_CORE is not set
# CONFIG_MFD_BCM590XX is not set
CONFIG_MFD_AXP20X=m
CONFIG_MFD_AXP20X_I2C=m
CONFIG_MFD_CROS_EC=m
CONFIG_MFD_CROS_EC_I2C=m
# CONFIG_PMIC_DA903X is not set
# CONFIG_MFD_DA9052_I2C is not set
CONFIG_MFD_DA9055=y
CONFIG_MFD_DA9062=y
CONFIG_MFD_DA9063=m
# CONFIG_MFD_DA9150 is not set
CONFIG_MFD_DLN2=y
# CONFIG_MFD_MC13XXX_I2C is not set
# CONFIG_HTC_PASIC3 is not set
# CONFIG_HTC_I2CPLD is not set
# CONFIG_MFD_INTEL_QUARK_I2C_GPIO is not set
# CONFIG_LPC_ICH is not set
# CONFIG_LPC_SCH is not set
# CONFIG_INTEL_SOC_PMIC is not set
# CONFIG_MFD_INTEL_LPSS_ACPI is not set
# CONFIG_MFD_INTEL_LPSS_PCI is not set
# CONFIG_MFD_JANZ_CMODIO is not set
CONFIG_MFD_KEMPLD=y
CONFIG_MFD_88PM800=m
CONFIG_MFD_88PM805=y
# CONFIG_MFD_88PM860X is not set
# CONFIG_MFD_MAX14577 is not set
CONFIG_MFD_MAX77693=m
CONFIG_MFD_MAX77843=y
# CONFIG_MFD_MAX8907 is not set
# CONFIG_MFD_MAX8925 is not set
# CONFIG_MFD_MAX8997 is not set
CONFIG_MFD_MAX8998=y
CONFIG_MFD_MT6397=m
CONFIG_MFD_MENF21BMC=m
# CONFIG_MFD_VIPERBOARD is not set
# CONFIG_MFD_RETU is not set
CONFIG_MFD_PCF50633=y
CONFIG_PCF50633_ADC=m
CONFIG_PCF50633_GPIO=y
CONFIG_UCB1400_CORE=m
# CONFIG_MFD_RDC321X is not set
# CONFIG_MFD_RTSX_PCI is not set
CONFIG_MFD_RT5033=y
CONFIG_MFD_RTSX_USB=m
CONFIG_MFD_RC5T583=y
CONFIG_MFD_SEC_CORE=y
# CONFIG_MFD_SI476X_CORE is not set
CONFIG_MFD_SM501=m
# CONFIG_MFD_SM501_GPIO is not set
CONFIG_MFD_SKY81452=y
# CONFIG_MFD_SMSC is not set
CONFIG_ABX500_CORE=y
# CONFIG_AB3100_CORE is not set
CONFIG_MFD_SYSCON=y
CONFIG_MFD_TI_AM335X_TSCADC=m
CONFIG_MFD_LP3943=m
CONFIG_MFD_LP8788=y
CONFIG_MFD_PALMAS=y
# CONFIG_TPS6105X is not set
# CONFIG_TPS65010 is not set
CONFIG_TPS6507X=y
# CONFIG_MFD_TPS65086 is not set
CONFIG_MFD_TPS65090=y
CONFIG_MFD_TPS65217=m
CONFIG_MFD_TI_LP873X=y
# CONFIG_MFD_TPS65218 is not set
CONFIG_MFD_TPS6586X=y
CONFIG_MFD_TPS65910=y
# CONFIG_MFD_TPS65912_I2C is not set
CONFIG_MFD_TPS80031=y
# CONFIG_TWL4030_CORE is not set
CONFIG_TWL6040_CORE=y
CONFIG_MFD_WL1273_CORE=y
CONFIG_MFD_LM3533=y
# CONFIG_MFD_TIMBERDALE is not set
# CONFIG_MFD_TMIO is not set
# CONFIG_MFD_VX855 is not set
# CONFIG_MFD_ARIZONA_I2C is not set
CONFIG_MFD_WM8400=y
# CONFIG_MFD_WM831X_I2C is not set
# CONFIG_MFD_WM8350_I2C is not set
CONFIG_MFD_WM8994=m
# CONFIG_REGULATOR is not set
CONFIG_MEDIA_SUPPORT=y
#
# Multimedia core support
#
# CONFIG_MEDIA_CAMERA_SUPPORT is not set
# CONFIG_MEDIA_ANALOG_TV_SUPPORT is not set
CONFIG_MEDIA_DIGITAL_TV_SUPPORT=y
CONFIG_MEDIA_RADIO_SUPPORT=y
CONFIG_MEDIA_SDR_SUPPORT=y
# CONFIG_MEDIA_RC_SUPPORT is not set
CONFIG_MEDIA_CEC_SUPPORT=y
CONFIG_MEDIA_CEC_DEBUG=y
CONFIG_MEDIA_CEC_EDID=y
CONFIG_MEDIA_CONTROLLER=y
# CONFIG_MEDIA_CONTROLLER_DVB is not set
CONFIG_VIDEO_DEV=y
CONFIG_VIDEO_V4L2_SUBDEV_API=y
CONFIG_VIDEO_V4L2=y
CONFIG_VIDEO_ADV_DEBUG=y
# CONFIG_VIDEO_FIXED_MINOR_RANGES is not set
CONFIG_V4L2_FLASH_LED_CLASS=m
CONFIG_DVB_CORE=y
# CONFIG_DVB_NET is not set
# CONFIG_TTPCI_EEPROM is not set
CONFIG_DVB_MAX_ADAPTERS=16
# CONFIG_DVB_DYNAMIC_MINORS is not set
# CONFIG_DVB_DEMUX_SECTION_LOSS_LOG is not set
#
# Media drivers
#
# CONFIG_MEDIA_USB_SUPPORT is not set
# CONFIG_MEDIA_PCI_SUPPORT is not set
# CONFIG_DVB_PLATFORM_DRIVERS is not set
#
# Supported MMC/SDIO adapters
#
CONFIG_SMS_SDIO_DRV=y
CONFIG_RADIO_ADAPTERS=y
CONFIG_RADIO_SI470X=y
CONFIG_USB_SI470X=y
# CONFIG_RADIO_SI4713 is not set
# CONFIG_USB_MR800 is not set
# CONFIG_USB_DSBR is not set
# CONFIG_RADIO_MAXIRADIO is not set
# CONFIG_RADIO_SHARK is not set
# CONFIG_RADIO_SHARK2 is not set
CONFIG_USB_KEENE=y
# CONFIG_USB_RAREMONO is not set
CONFIG_USB_MA901=y
# CONFIG_RADIO_TEA5764 is not set
CONFIG_RADIO_SAA7706H=y
CONFIG_RADIO_TEF6862=y
CONFIG_RADIO_WL1273=y
#
# Texas Instruments WL128x FM driver (ST based)
#
# CONFIG_V4L_RADIO_ISA_DRIVERS is not set
CONFIG_MEDIA_COMMON_OPTIONS=y
#
# common driver options
#
CONFIG_CYPRESS_FIRMWARE=m
CONFIG_SMS_SIANO_MDTV=y
#
# Media ancillary drivers (tuners, sensors, i2c, spi, frontends)
#
CONFIG_MEDIA_SUBDRV_AUTOSELECT=y
CONFIG_MEDIA_ATTACH=y
#
# Audio decoders, processors and mixers
#
#
# RDS decoders
#
#
# Video decoders
#
#
# Video and audio decoders
#
#
# Video encoders
#
#
# Camera sensor devices
#
#
# Flash devices
#
#
# Video improvement chips
#
#
# Audio/Video compression chips
#
#
# Miscellaneous helper chips
#
#
# Sensors used on soc_camera driver
#
CONFIG_MEDIA_TUNER=y
CONFIG_MEDIA_TUNER_SIMPLE=y
CONFIG_MEDIA_TUNER_TDA8290=y
CONFIG_MEDIA_TUNER_TDA827X=y
CONFIG_MEDIA_TUNER_TDA18271=y
CONFIG_MEDIA_TUNER_TDA9887=y
CONFIG_MEDIA_TUNER_TEA5761=y
CONFIG_MEDIA_TUNER_TEA5767=y
CONFIG_MEDIA_TUNER_MT20XX=y
CONFIG_MEDIA_TUNER_XC2028=y
CONFIG_MEDIA_TUNER_XC5000=y
CONFIG_MEDIA_TUNER_XC4000=y
CONFIG_MEDIA_TUNER_MC44S803=y
#
# Multistandard (satellite) frontends
#
#
# Multistandard (cable + terrestrial) frontends
#
#
# DVB-S (satellite) frontends
#
#
# DVB-T (terrestrial) frontends
#
# CONFIG_DVB_AS102_FE is not set
# CONFIG_DVB_GP8PSK_FE is not set
#
# DVB-C (cable) frontends
#
#
# ATSC (North American/Korean Terrestrial/Cable DTV) frontends
#
#
# ISDB-T (terrestrial) frontends
#
#
# ISDB-S (satellite) & ISDB-T (terrestrial) frontends
#
#
# Digital terrestrial only tuners/PLL
#
#
# SEC control devices for DVB-S
#
#
# Tools to develop new frontends
#
# CONFIG_DVB_DUMMY_FE is not set
#
# Graphics support
#
# CONFIG_AGP is not set
CONFIG_VGA_ARB=y
CONFIG_VGA_ARB_MAX_GPUS=16
# CONFIG_VGA_SWITCHEROO is not set
# CONFIG_DRM is not set
#
# ACP (Audio CoProcessor) Configuration
#
# CONFIG_DRM_LIB_RANDOM is not set
#
# Frame buffer Devices
#
# CONFIG_FB is not set
CONFIG_BACKLIGHT_LCD_SUPPORT=y
CONFIG_LCD_CLASS_DEVICE=m
CONFIG_LCD_PLATFORM=m
CONFIG_BACKLIGHT_CLASS_DEVICE=m
CONFIG_BACKLIGHT_GENERIC=m
CONFIG_BACKLIGHT_LM3533=m
# CONFIG_BACKLIGHT_APPLE is not set
CONFIG_BACKLIGHT_PM8941_WLED=m
CONFIG_BACKLIGHT_SAHARA=m
CONFIG_BACKLIGHT_ADP5520=m
CONFIG_BACKLIGHT_ADP8860=m
CONFIG_BACKLIGHT_ADP8870=m
CONFIG_BACKLIGHT_PCF50633=m
CONFIG_BACKLIGHT_LM3639=m
CONFIG_BACKLIGHT_SKY81452=m
# CONFIG_BACKLIGHT_TPS65217 is not set
CONFIG_BACKLIGHT_AS3711=m
CONFIG_BACKLIGHT_GPIO=m
# CONFIG_BACKLIGHT_LV5207LP is not set
CONFIG_BACKLIGHT_BD6107=m
# CONFIG_VGASTATE is not set
CONFIG_SOUND=m
CONFIG_SOUND_OSS_CORE=y
CONFIG_SOUND_OSS_CORE_PRECLAIM=y
CONFIG_SND=m
CONFIG_SND_TIMER=m
CONFIG_SND_PCM=m
CONFIG_SND_DMAENGINE_PCM=m
CONFIG_SND_HWDEP=m
CONFIG_SND_RAWMIDI=m
CONFIG_SND_JACK=y
CONFIG_SND_JACK_INPUT_DEV=y
CONFIG_SND_SEQUENCER=m
CONFIG_SND_SEQ_DUMMY=m
CONFIG_SND_OSSEMUL=y
CONFIG_SND_MIXER_OSS=m
CONFIG_SND_PCM_OSS=m
CONFIG_SND_PCM_OSS_PLUGINS=y
# CONFIG_SND_PCM_TIMER is not set
# CONFIG_SND_SEQUENCER_OSS is not set
# CONFIG_SND_HRTIMER is not set
CONFIG_SND_DYNAMIC_MINORS=y
CONFIG_SND_MAX_CARDS=32
# CONFIG_SND_SUPPORT_OLD_API is not set
CONFIG_SND_PROC_FS=y
CONFIG_SND_VERBOSE_PROCFS=y
# CONFIG_SND_VERBOSE_PRINTK is not set
# CONFIG_SND_DEBUG is not set
CONFIG_SND_VMASTER=y
CONFIG_SND_DMA_SGBUF=y
CONFIG_SND_RAWMIDI_SEQ=m
# CONFIG_SND_OPL3_LIB_SEQ is not set
# CONFIG_SND_OPL4_LIB_SEQ is not set
# CONFIG_SND_SBAWE_SEQ is not set
# CONFIG_SND_EMU10K1_SEQ is not set
CONFIG_SND_MPU401_UART=m
CONFIG_SND_VX_LIB=m
CONFIG_SND_AC97_CODEC=m
CONFIG_SND_DRIVERS=y
# CONFIG_SND_PCSP is not set
# CONFIG_SND_DUMMY is not set
CONFIG_SND_ALOOP=m
CONFIG_SND_VIRMIDI=m
# CONFIG_SND_MTPAV is not set
CONFIG_SND_MTS64=m
CONFIG_SND_SERIAL_U16550=m
CONFIG_SND_MPU401=m
CONFIG_SND_PORTMAN2X4=m
# CONFIG_SND_AC97_POWER_SAVE is not set
# CONFIG_SND_ISA is not set
CONFIG_SND_PCI=y
# CONFIG_SND_AD1889 is not set
# CONFIG_SND_ALS300 is not set
# CONFIG_SND_ALS4000 is not set
# CONFIG_SND_ALI5451 is not set
# CONFIG_SND_ASIHPI is not set
# CONFIG_SND_ATIIXP is not set
# CONFIG_SND_ATIIXP_MODEM is not set
# CONFIG_SND_AU8810 is not set
# CONFIG_SND_AU8820 is not set
# CONFIG_SND_AU8830 is not set
# CONFIG_SND_AW2 is not set
# CONFIG_SND_AZT3328 is not set
# CONFIG_SND_BT87X is not set
# CONFIG_SND_CA0106 is not set
# CONFIG_SND_CMIPCI is not set
# CONFIG_SND_OXYGEN is not set
# CONFIG_SND_CS4281 is not set
# CONFIG_SND_CS46XX is not set
# CONFIG_SND_CS5530 is not set
# CONFIG_SND_CS5535AUDIO is not set
# CONFIG_SND_CTXFI is not set
# CONFIG_SND_DARLA20 is not set
# CONFIG_SND_GINA20 is not set
# CONFIG_SND_LAYLA20 is not set
# CONFIG_SND_DARLA24 is not set
# CONFIG_SND_GINA24 is not set
# CONFIG_SND_LAYLA24 is not set
# CONFIG_SND_MONA is not set
# CONFIG_SND_MIA is not set
# CONFIG_SND_ECHO3G is not set
# CONFIG_SND_INDIGO is not set
# CONFIG_SND_INDIGOIO is not set
# CONFIG_SND_INDIGODJ is not set
# CONFIG_SND_INDIGOIOX is not set
# CONFIG_SND_INDIGODJX is not set
# CONFIG_SND_EMU10K1 is not set
# CONFIG_SND_EMU10K1X is not set
# CONFIG_SND_ENS1370 is not set
# CONFIG_SND_ENS1371 is not set
# CONFIG_SND_ES1938 is not set
# CONFIG_SND_ES1968 is not set
# CONFIG_SND_FM801 is not set
# CONFIG_SND_HDSP is not set
# CONFIG_SND_HDSPM is not set
# CONFIG_SND_ICE1712 is not set
# CONFIG_SND_ICE1724 is not set
# CONFIG_SND_INTEL8X0 is not set
# CONFIG_SND_INTEL8X0M is not set
# CONFIG_SND_KORG1212 is not set
# CONFIG_SND_LOLA is not set
# CONFIG_SND_LX6464ES is not set
# CONFIG_SND_MAESTRO3 is not set
# CONFIG_SND_MIXART is not set
# CONFIG_SND_NM256 is not set
# CONFIG_SND_PCXHR is not set
# CONFIG_SND_RIPTIDE is not set
# CONFIG_SND_RME32 is not set
# CONFIG_SND_RME96 is not set
# CONFIG_SND_RME9652 is not set
# CONFIG_SND_SE6X is not set
# CONFIG_SND_SIS7019 is not set
# CONFIG_SND_SONICVIBES is not set
# CONFIG_SND_TRIDENT is not set
# CONFIG_SND_VIA82XX is not set
# CONFIG_SND_VIA82XX_MODEM is not set
# CONFIG_SND_VIRTUOSO is not set
# CONFIG_SND_VX222 is not set
# CONFIG_SND_YMFPCI is not set
#
# HD-Audio
#
# CONFIG_SND_HDA_INTEL is not set
CONFIG_SND_HDA_PREALLOC_SIZE=64
# CONFIG_SND_USB is not set
CONFIG_SND_PCMCIA=y
CONFIG_SND_VXPOCKET=m
# CONFIG_SND_PDAUDIOCF is not set
CONFIG_SND_SOC=m
CONFIG_SND_SOC_AC97_BUS=y
CONFIG_SND_SOC_GENERIC_DMAENGINE_PCM=y
CONFIG_SND_SOC_AMD_ACP=m
CONFIG_SND_ATMEL_SOC=m
# CONFIG_SND_DESIGNWARE_I2S is not set
#
# SoC Audio for Freescale CPUs
#
#
# Common SoC Audio options for Freescale CPUs:
#
CONFIG_SND_SOC_FSL_ASRC=m
CONFIG_SND_SOC_FSL_SAI=m
CONFIG_SND_SOC_FSL_SSI=m
# CONFIG_SND_SOC_FSL_SPDIF is not set
CONFIG_SND_SOC_FSL_ESAI=m
# CONFIG_SND_SOC_IMX_AUDMUX is not set
# CONFIG_SND_SOC_IMG is not set
# CONFIG_SND_SOC_INTEL_BXT_DA7219_MAX98357A_MACH is not set
# CONFIG_SND_SOC_INTEL_BXT_RT298_MACH is not set
# CONFIG_SND_SOC_INTEL_BYTCR_RT5640_MACH is not set
# CONFIG_SND_SOC_INTEL_BYTCR_RT5651_MACH is not set
# CONFIG_SND_SOC_INTEL_SKL_RT286_MACH is not set
CONFIG_SND_SOC_XTFPGA_I2S=m
CONFIG_SND_SOC_I2C_AND_SPI=m
#
# CODEC drivers
#
CONFIG_SND_SOC_AC97_CODEC=m
# CONFIG_SND_SOC_ADAU1701 is not set
# CONFIG_SND_SOC_ADAU7002 is not set
CONFIG_SND_SOC_AK4554=m
CONFIG_SND_SOC_AK4613=m
CONFIG_SND_SOC_AK4642=m
# CONFIG_SND_SOC_AK5386 is not set
CONFIG_SND_SOC_ALC5623=m
CONFIG_SND_SOC_BT_SCO=m
# CONFIG_SND_SOC_CS35L32 is not set
CONFIG_SND_SOC_CS35L33=m
CONFIG_SND_SOC_CS35L34=m
CONFIG_SND_SOC_CS42L42=m
CONFIG_SND_SOC_CS42L51=m
CONFIG_SND_SOC_CS42L51_I2C=m
# CONFIG_SND_SOC_CS42L52 is not set
# CONFIG_SND_SOC_CS42L56 is not set
CONFIG_SND_SOC_CS42L73=m
CONFIG_SND_SOC_CS4265=m
# CONFIG_SND_SOC_CS4270 is not set
CONFIG_SND_SOC_CS4271=m
CONFIG_SND_SOC_CS4271_I2C=m
CONFIG_SND_SOC_CS42XX8=m
CONFIG_SND_SOC_CS42XX8_I2C=m
# CONFIG_SND_SOC_CS4349 is not set
# CONFIG_SND_SOC_CS53L30 is not set
# CONFIG_SND_SOC_ES8328_I2C is not set
CONFIG_SND_SOC_GTM601=m
# CONFIG_SND_SOC_INNO_RK3036 is not set
CONFIG_SND_SOC_MAX98504=m
CONFIG_SND_SOC_MAX9860=m
CONFIG_SND_SOC_MSM8916_WCD_ANALOG=m
CONFIG_SND_SOC_MSM8916_WCD_DIGITAL=m
CONFIG_SND_SOC_PCM1681=m
CONFIG_SND_SOC_PCM179X=m
CONFIG_SND_SOC_PCM179X_I2C=m
CONFIG_SND_SOC_PCM3168A=m
CONFIG_SND_SOC_PCM3168A_I2C=m
# CONFIG_SND_SOC_PCM512x_I2C is not set
# CONFIG_SND_SOC_RT5616 is not set
CONFIG_SND_SOC_RT5631=m
# CONFIG_SND_SOC_RT5677_SPI is not set
# CONFIG_SND_SOC_SGTL5000 is not set
CONFIG_SND_SOC_SIRF_AUDIO_CODEC=m
CONFIG_SND_SOC_SPDIF=m
CONFIG_SND_SOC_SSM2602=m
CONFIG_SND_SOC_SSM2602_I2C=m
CONFIG_SND_SOC_SSM4567=m
CONFIG_SND_SOC_STA32X=m
CONFIG_SND_SOC_STA350=m
CONFIG_SND_SOC_STI_SAS=m
# CONFIG_SND_SOC_TAS2552 is not set
CONFIG_SND_SOC_TAS5086=m
CONFIG_SND_SOC_TAS571X=m
CONFIG_SND_SOC_TAS5720=m
CONFIG_SND_SOC_TFA9879=m
CONFIG_SND_SOC_TLV320AIC23=m
CONFIG_SND_SOC_TLV320AIC23_I2C=m
# CONFIG_SND_SOC_TLV320AIC31XX is not set
# CONFIG_SND_SOC_TLV320AIC3X is not set
# CONFIG_SND_SOC_TS3A227E is not set
CONFIG_SND_SOC_WM8510=m
# CONFIG_SND_SOC_WM8523 is not set
# CONFIG_SND_SOC_WM8580 is not set
CONFIG_SND_SOC_WM8711=m
# CONFIG_SND_SOC_WM8728 is not set
CONFIG_SND_SOC_WM8731=m
# CONFIG_SND_SOC_WM8737 is not set
# CONFIG_SND_SOC_WM8741 is not set
CONFIG_SND_SOC_WM8750=m
CONFIG_SND_SOC_WM8753=m
# CONFIG_SND_SOC_WM8776 is not set
# CONFIG_SND_SOC_WM8804_I2C is not set
CONFIG_SND_SOC_WM8903=m
CONFIG_SND_SOC_WM8960=m
# CONFIG_SND_SOC_WM8962 is not set
# CONFIG_SND_SOC_WM8974 is not set
CONFIG_SND_SOC_WM8978=m
CONFIG_SND_SOC_WM8985=m
# CONFIG_SND_SOC_NAU8540 is not set
CONFIG_SND_SOC_NAU8810=m
# CONFIG_SND_SOC_TPA6130A2 is not set
CONFIG_SND_SIMPLE_CARD_UTILS=m
CONFIG_SND_SIMPLE_CARD=m
# CONFIG_SND_X86 is not set
CONFIG_SOUND_PRIME=m
# CONFIG_SOUND_MSNDCLAS is not set
# CONFIG_SOUND_MSNDPIN is not set
CONFIG_SOUND_OSS=m
# CONFIG_SOUND_TRACEINIT is not set
# CONFIG_SOUND_DMAP is not set
# CONFIG_SOUND_VMIDI is not set
CONFIG_SOUND_TRIX=m
# CONFIG_SOUND_MSS is not set
CONFIG_SOUND_MPU401=m
CONFIG_SOUND_PAS=m
CONFIG_SOUND_PSS=m
CONFIG_PSS_MIXER=y
# CONFIG_PSS_HAVE_BOOT is not set
CONFIG_SOUND_SB=m
# CONFIG_SOUND_YM3812 is not set
# CONFIG_SOUND_UART6850 is not set
CONFIG_SOUND_AEDSP16=m
CONFIG_SC6600=y
CONFIG_SC6600_JOY=y
CONFIG_SC6600_CDROM=4
CONFIG_SC6600_CDROMBASE=0
CONFIG_SOUND_KAHLUA=m
CONFIG_AC97_BUS=m
#
# HID support
#
CONFIG_HID=y
# CONFIG_HID_BATTERY_STRENGTH is not set
# CONFIG_HIDRAW is not set
# CONFIG_UHID is not set
CONFIG_HID_GENERIC=y
#
# Special HID drivers
#
# CONFIG_HID_A4TECH is not set
# CONFIG_HID_ACRUX is not set
# CONFIG_HID_APPLE is not set
# CONFIG_HID_APPLEIR is not set
# CONFIG_HID_AUREAL is not set
# CONFIG_HID_BELKIN is not set
# CONFIG_HID_BETOP_FF is not set
# CONFIG_HID_CHERRY is not set
# CONFIG_HID_CHICONY is not set
# CONFIG_HID_CORSAIR is not set
# CONFIG_HID_PRODIKEYS is not set
# CONFIG_HID_CMEDIA is not set
# CONFIG_HID_CP2112 is not set
# CONFIG_HID_CYPRESS is not set
# CONFIG_HID_DRAGONRISE is not set
# CONFIG_HID_EMS_FF is not set
# CONFIG_HID_ELECOM is not set
# CONFIG_HID_ELO is not set
# CONFIG_HID_EZKEY is not set
# CONFIG_HID_GEMBIRD is not set
# CONFIG_HID_GFRM is not set
# CONFIG_HID_HOLTEK is not set
# CONFIG_HID_GT683R is not set
# CONFIG_HID_KEYTOUCH is not set
# CONFIG_HID_KYE is not set
# CONFIG_HID_UCLOGIC is not set
# CONFIG_HID_WALTOP is not set
# CONFIG_HID_GYRATION is not set
# CONFIG_HID_ICADE is not set
# CONFIG_HID_TWINHAN is not set
# CONFIG_HID_KENSINGTON is not set
# CONFIG_HID_LCPOWER is not set
# CONFIG_HID_LED is not set
# CONFIG_HID_LENOVO is not set
# CONFIG_HID_LOGITECH is not set
# CONFIG_HID_MAGICMOUSE is not set
# CONFIG_HID_MAYFLASH is not set
# CONFIG_HID_MICROSOFT is not set
# CONFIG_HID_MONTEREY is not set
# CONFIG_HID_MULTITOUCH is not set
# CONFIG_HID_NTRIG is not set
# CONFIG_HID_ORTEK is not set
# CONFIG_HID_PANTHERLORD is not set
# CONFIG_HID_PENMOUNT is not set
# CONFIG_HID_PETALYNX is not set
# CONFIG_HID_PICOLCD is not set
# CONFIG_HID_PLANTRONICS is not set
# CONFIG_HID_PRIMAX is not set
# CONFIG_HID_ROCCAT is not set
# CONFIG_HID_SAITEK is not set
# CONFIG_HID_SAMSUNG is not set
# CONFIG_HID_SONY is not set
# CONFIG_HID_SPEEDLINK is not set
# CONFIG_HID_STEELSERIES is not set
# CONFIG_HID_SUNPLUS is not set
# CONFIG_HID_RMI is not set
# CONFIG_HID_GREENASIA is not set
# CONFIG_HID_SMARTJOYPLUS is not set
# CONFIG_HID_TIVO is not set
# CONFIG_HID_TOPSEED is not set
# CONFIG_HID_THINGM is not set
# CONFIG_HID_THRUSTMASTER is not set
# CONFIG_HID_UDRAW_PS3 is not set
# CONFIG_HID_WACOM is not set
# CONFIG_HID_WIIMOTE is not set
# CONFIG_HID_XINMO is not set
# CONFIG_HID_ZEROPLUS is not set
# CONFIG_HID_ZYDACRON is not set
# CONFIG_HID_SENSOR_HUB is not set
# CONFIG_HID_ALPS is not set
#
# USB HID support
#
CONFIG_USB_HID=y
# CONFIG_HID_PID is not set
# CONFIG_USB_HIDDEV is not set
#
# I2C HID support
#
# CONFIG_I2C_HID is not set
CONFIG_USB_OHCI_LITTLE_ENDIAN=y
CONFIG_USB_SUPPORT=y
CONFIG_USB_COMMON=y
CONFIG_USB_ARCH_HAS_HCD=y
CONFIG_USB=y
# CONFIG_USB_ANNOUNCE_NEW_DEVICES is not set
#
# Miscellaneous USB options
#
# CONFIG_USB_DEFAULT_PERSIST is not set
# CONFIG_USB_DYNAMIC_MINORS is not set
CONFIG_USB_OTG=y
# CONFIG_USB_OTG_WHITELIST is not set
CONFIG_USB_OTG_BLACKLIST_HUB=y
CONFIG_USB_OTG_FSM=y
CONFIG_USB_LEDS_TRIGGER_USBPORT=m
CONFIG_USB_MON=y
# CONFIG_USB_WUSB_CBAF is not set
#
# USB Host Controller Drivers
#
CONFIG_USB_C67X00_HCD=y
CONFIG_USB_XHCI_HCD=y
CONFIG_USB_XHCI_PCI=y
CONFIG_USB_XHCI_PLATFORM=y
CONFIG_USB_EHCI_HCD=m
CONFIG_USB_EHCI_ROOT_HUB_TT=y
CONFIG_USB_EHCI_TT_NEWSCHED=y
CONFIG_USB_EHCI_PCI=m
CONFIG_USB_EHCI_HCD_PLATFORM=m
# CONFIG_USB_OXU210HP_HCD is not set
CONFIG_USB_ISP116X_HCD=m
CONFIG_USB_ISP1362_HCD=m
# CONFIG_USB_FOTG210_HCD is not set
# CONFIG_USB_OHCI_HCD is not set
# CONFIG_USB_UHCI_HCD is not set
CONFIG_USB_SL811_HCD=y
CONFIG_USB_SL811_HCD_ISO=y
# CONFIG_USB_SL811_CS is not set
CONFIG_USB_R8A66597_HCD=m
CONFIG_USB_HCD_BCMA=m
# CONFIG_USB_HCD_TEST_MODE is not set
#
# USB Device Class drivers
#
# CONFIG_USB_ACM is not set
CONFIG_USB_PRINTER=m
# CONFIG_USB_WDM is not set
CONFIG_USB_TMC=y
#
# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may
#
#
# also be needed; see USB_STORAGE Help for more info
#
# CONFIG_USB_STORAGE is not set
#
# USB Imaging devices
#
CONFIG_USB_MDC800=m
CONFIG_USB_MICROTEK=y
CONFIG_USBIP_CORE=m
CONFIG_USBIP_VHCI_HCD=m
CONFIG_USBIP_VHCI_HC_PORTS=8
CONFIG_USBIP_VHCI_NR_HCS=1
CONFIG_USBIP_HOST=m
CONFIG_USBIP_VUDC=m
CONFIG_USBIP_DEBUG=y
CONFIG_USB_MUSB_HDRC=m
# CONFIG_USB_MUSB_HOST is not set
# CONFIG_USB_MUSB_GADGET is not set
CONFIG_USB_MUSB_DUAL_ROLE=y
#
# Platform Glue Layer
#
#
# MUSB DMA mode
#
# CONFIG_MUSB_PIO_ONLY is not set
CONFIG_USB_DWC3=y
CONFIG_USB_DWC3_HOST=y
#
# Platform Glue Driver Support
#
CONFIG_USB_DWC3_PCI=y
# CONFIG_USB_DWC2 is not set
CONFIG_USB_CHIPIDEA=m
CONFIG_USB_CHIPIDEA_PCI=m
# CONFIG_USB_CHIPIDEA_UDC is not set
CONFIG_USB_CHIPIDEA_HOST=y
# CONFIG_USB_CHIPIDEA_ULPI is not set
CONFIG_USB_ISP1760=m
CONFIG_USB_ISP1761_UDC=y
# CONFIG_USB_ISP1760_HOST_ROLE is not set
CONFIG_USB_ISP1760_GADGET_ROLE=y
# CONFIG_USB_ISP1760_DUAL_ROLE is not set
#
# USB port drivers
#
CONFIG_USB_USS720=m
# CONFIG_USB_SERIAL is not set
#
# USB Miscellaneous drivers
#
# CONFIG_USB_EMI62 is not set
# CONFIG_USB_EMI26 is not set
# CONFIG_USB_ADUTUX is not set
CONFIG_USB_SEVSEG=y
CONFIG_USB_RIO500=m
# CONFIG_USB_LEGOTOWER is not set
CONFIG_USB_LCD=m
CONFIG_USB_CYPRESS_CY7C63=m
CONFIG_USB_CYTHERM=y
CONFIG_USB_IDMOUSE=m
# CONFIG_USB_FTDI_ELAN is not set
CONFIG_USB_APPLEDISPLAY=m
# CONFIG_USB_SISUSBVGA is not set
CONFIG_USB_LD=y
CONFIG_USB_TRANCEVIBRATOR=m
CONFIG_USB_IOWARRIOR=y
CONFIG_USB_TEST=m
CONFIG_USB_EHSET_TEST_FIXTURE=y
CONFIG_USB_ISIGHTFW=m
# CONFIG_USB_YUREX is not set
CONFIG_USB_EZUSB_FX2=m
# CONFIG_USB_HUB_USB251XB is not set
# CONFIG_USB_HSIC_USB3503 is not set
CONFIG_USB_HSIC_USB4604=y
CONFIG_USB_LINK_LAYER_TEST=y
# CONFIG_USB_CHAOSKEY is not set
# CONFIG_UCSI is not set
#
# USB Physical Layer drivers
#
CONFIG_USB_PHY=y
CONFIG_NOP_USB_XCEIV=m
# CONFIG_USB_GPIO_VBUS is not set
CONFIG_USB_ISP1301=y
CONFIG_USB_GADGET=m
CONFIG_USB_GADGET_DEBUG=y
# CONFIG_USB_GADGET_VERBOSE is not set
# CONFIG_USB_GADGET_DEBUG_FILES is not set
# CONFIG_USB_GADGET_DEBUG_FS is not set
CONFIG_USB_GADGET_VBUS_DRAW=2
CONFIG_USB_GADGET_STORAGE_NUM_BUFFERS=2
#
# USB Peripheral Controller
#
# CONFIG_USB_FOTG210_UDC is not set
CONFIG_USB_GR_UDC=m
# CONFIG_USB_R8A66597 is not set
# CONFIG_USB_PXA27X is not set
CONFIG_USB_MV_UDC=m
CONFIG_USB_MV_U3D=m
# CONFIG_USB_M66592 is not set
CONFIG_USB_BDC_UDC=m
#
# Platform Support
#
CONFIG_USB_BDC_PCI=m
# CONFIG_USB_AMD5536UDC is not set
CONFIG_USB_NET2272=m
CONFIG_USB_NET2272_DMA=y
# CONFIG_USB_NET2280 is not set
# CONFIG_USB_GOKU is not set
# CONFIG_USB_EG20T is not set
CONFIG_USB_DUMMY_HCD=m
CONFIG_USB_LIBCOMPOSITE=m
CONFIG_USB_F_SS_LB=m
CONFIG_USB_U_ETHER=m
CONFIG_USB_F_ECM=m
CONFIG_USB_F_SUBSET=m
CONFIG_USB_F_MASS_STORAGE=m
CONFIG_USB_F_FS=m
CONFIG_USB_F_UAC2=m
CONFIG_USB_F_MIDI=m
CONFIG_USB_F_HID=m
CONFIG_USB_F_PRINTER=m
CONFIG_USB_F_TCM=m
# CONFIG_USB_CONFIGFS is not set
CONFIG_USB_ZERO=m
CONFIG_USB_ZERO_HNPTEST=y
CONFIG_USB_AUDIO=m
# CONFIG_GADGET_UAC1 is not set
CONFIG_USB_ETH=m
# CONFIG_USB_ETH_RNDIS is not set
# CONFIG_USB_ETH_EEM is not set
# CONFIG_USB_G_NCM is not set
# CONFIG_USB_GADGETFS is not set
CONFIG_USB_FUNCTIONFS=m
# CONFIG_USB_FUNCTIONFS_ETH is not set
# CONFIG_USB_FUNCTIONFS_RNDIS is not set
CONFIG_USB_FUNCTIONFS_GENERIC=y
CONFIG_USB_MASS_STORAGE=m
CONFIG_USB_GADGET_TARGET=m
# CONFIG_USB_G_SERIAL is not set
CONFIG_USB_MIDI_GADGET=m
CONFIG_USB_G_PRINTER=m
# CONFIG_USB_CDC_COMPOSITE is not set
# CONFIG_USB_G_NOKIA is not set
# CONFIG_USB_G_ACM_MS is not set
# CONFIG_USB_G_MULTI is not set
CONFIG_USB_G_HID=m
# CONFIG_USB_G_DBGP is not set
# CONFIG_USB_G_WEBCAM is not set
# CONFIG_USB_LED_TRIG is not set
CONFIG_USB_ULPI_BUS=m
# CONFIG_UWB is not set
CONFIG_MMC=y
CONFIG_MMC_DEBUG=y
CONFIG_MMC_BLOCK=m
CONFIG_MMC_BLOCK_MINORS=8
# CONFIG_MMC_BLOCK_BOUNCE is not set
# CONFIG_SDIO_UART is not set
CONFIG_MMC_TEST=y
#
# MMC/SD/SDIO Host Controller Drivers
#
CONFIG_MMC_SDHCI=m
# CONFIG_MMC_SDHCI_PCI is not set
# CONFIG_MMC_SDHCI_ACPI is not set
# CONFIG_MMC_SDHCI_PLTFM is not set
CONFIG_MMC_WBSD=y
# CONFIG_MMC_TIFM_SD is not set
# CONFIG_MMC_SDRICOH_CS is not set
# CONFIG_MMC_CB710 is not set
# CONFIG_MMC_VIA_SDMMC is not set
# CONFIG_MMC_VUB300 is not set
CONFIG_MMC_USHC=m
# CONFIG_MMC_USDHI6ROL0 is not set
CONFIG_MMC_REALTEK_USB=m
# CONFIG_MMC_TOSHIBA_PCI is not set
CONFIG_MMC_MTK=y
CONFIG_MEMSTICK=m
# CONFIG_MEMSTICK_DEBUG is not set
#
# MemoryStick drivers
#
CONFIG_MEMSTICK_UNSAFE_RESUME=y
CONFIG_MSPRO_BLOCK=m
CONFIG_MS_BLOCK=m
#
# MemoryStick Host Controller Drivers
#
# CONFIG_MEMSTICK_TIFM_MS is not set
# CONFIG_MEMSTICK_JMICRON_38X is not set
# CONFIG_MEMSTICK_R592 is not set
# CONFIG_MEMSTICK_REALTEK_USB is not set
CONFIG_NEW_LEDS=y
CONFIG_LEDS_CLASS=m
CONFIG_LEDS_CLASS_FLASH=m
# CONFIG_LEDS_BRIGHTNESS_HW_CHANGED is not set
#
# LED drivers
#
# CONFIG_LEDS_LM3530 is not set
CONFIG_LEDS_LM3533=m
CONFIG_LEDS_LM3642=m
# CONFIG_LEDS_PCA9532 is not set
# CONFIG_LEDS_GPIO is not set
CONFIG_LEDS_LP3944=m
# CONFIG_LEDS_LP3952 is not set
CONFIG_LEDS_LP55XX_COMMON=m
CONFIG_LEDS_LP5521=m
CONFIG_LEDS_LP5523=m
# CONFIG_LEDS_LP5562 is not set
CONFIG_LEDS_LP8501=m
CONFIG_LEDS_LP8788=m
CONFIG_LEDS_LP8860=m
# CONFIG_LEDS_CLEVO_MAIL is not set
CONFIG_LEDS_PCA955X=m
CONFIG_LEDS_PCA963X=m
CONFIG_LEDS_BD2802=m
# CONFIG_LEDS_INTEL_SS4200 is not set
# CONFIG_LEDS_LT3593 is not set
CONFIG_LEDS_ADP5520=m
# CONFIG_LEDS_TCA6507 is not set
CONFIG_LEDS_TLC591XX=m
CONFIG_LEDS_LM355x=m
CONFIG_LEDS_OT200=m
CONFIG_LEDS_MENF21BMC=m
#
# LED driver for blink(1) USB RGB LED is under Special HID drivers (HID_THINGM)
#
CONFIG_LEDS_BLINKM=m
CONFIG_LEDS_USER=m
# CONFIG_LEDS_NIC78BX is not set
#
# LED Triggers
#
CONFIG_LEDS_TRIGGERS=y
CONFIG_LEDS_TRIGGER_TIMER=y
# CONFIG_LEDS_TRIGGER_ONESHOT is not set
# CONFIG_LEDS_TRIGGER_DISK is not set
CONFIG_LEDS_TRIGGER_MTD=y
# CONFIG_LEDS_TRIGGER_HEARTBEAT is not set
# CONFIG_LEDS_TRIGGER_BACKLIGHT is not set
# CONFIG_LEDS_TRIGGER_CPU is not set
CONFIG_LEDS_TRIGGER_GPIO=m
CONFIG_LEDS_TRIGGER_DEFAULT_ON=m
#
# iptables trigger is under Netfilter config (LED target)
#
CONFIG_LEDS_TRIGGER_TRANSIENT=m
CONFIG_LEDS_TRIGGER_CAMERA=m
CONFIG_LEDS_TRIGGER_PANIC=y
CONFIG_ACCESSIBILITY=y
# CONFIG_INFINIBAND is not set
CONFIG_EDAC_ATOMIC_SCRUB=y
CONFIG_EDAC_SUPPORT=y
# CONFIG_EDAC is not set
CONFIG_RTC_LIB=y
CONFIG_RTC_MC146818_LIB=y
CONFIG_RTC_CLASS=y
# CONFIG_RTC_HCTOSYS is not set
CONFIG_RTC_SYSTOHC=y
CONFIG_RTC_SYSTOHC_DEVICE="rtc0"
# CONFIG_RTC_DEBUG is not set
#
# RTC interfaces
#
# CONFIG_RTC_INTF_SYSFS is not set
CONFIG_RTC_INTF_PROC=y
# CONFIG_RTC_INTF_DEV is not set
CONFIG_RTC_DRV_TEST=m
#
# I2C RTC drivers
#
# CONFIG_RTC_DRV_88PM80X is not set
CONFIG_RTC_DRV_ABB5ZES3=y
# CONFIG_RTC_DRV_ABX80X is not set
CONFIG_RTC_DRV_DS1307=m
CONFIG_RTC_DRV_DS1307_HWMON=y
# CONFIG_RTC_DRV_DS1307_CENTURY is not set
CONFIG_RTC_DRV_DS1374=m
# CONFIG_RTC_DRV_DS1374_WDT is not set
CONFIG_RTC_DRV_DS1672=y
# CONFIG_RTC_DRV_LP8788 is not set
CONFIG_RTC_DRV_MAX6900=y
# CONFIG_RTC_DRV_MAX8998 is not set
CONFIG_RTC_DRV_RS5C372=m
CONFIG_RTC_DRV_ISL1208=m
# CONFIG_RTC_DRV_ISL12022 is not set
CONFIG_RTC_DRV_X1205=y
# CONFIG_RTC_DRV_PCF8523 is not set
CONFIG_RTC_DRV_PCF85063=m
CONFIG_RTC_DRV_PCF8563=m
CONFIG_RTC_DRV_PCF8583=m
# CONFIG_RTC_DRV_M41T80 is not set
CONFIG_RTC_DRV_BQ32K=m
# CONFIG_RTC_DRV_PALMAS is not set
CONFIG_RTC_DRV_TPS6586X=m
CONFIG_RTC_DRV_TPS65910=y
CONFIG_RTC_DRV_TPS80031=m
CONFIG_RTC_DRV_RC5T583=y
# CONFIG_RTC_DRV_S35390A is not set
CONFIG_RTC_DRV_FM3130=y
# CONFIG_RTC_DRV_RX8010 is not set
CONFIG_RTC_DRV_RX8581=y
CONFIG_RTC_DRV_RX8025=y
CONFIG_RTC_DRV_EM3027=m
# CONFIG_RTC_DRV_RV8803 is not set
CONFIG_RTC_DRV_S5M=y
#
# SPI RTC drivers
#
CONFIG_RTC_I2C_AND_SPI=y
#
# SPI and I2C RTC drivers
#
CONFIG_RTC_DRV_DS3232=y
CONFIG_RTC_DRV_PCF2127=m
CONFIG_RTC_DRV_RV3029C2=m
CONFIG_RTC_DRV_RV3029_HWMON=y
#
# Platform RTC drivers
#
# CONFIG_RTC_DRV_CMOS is not set
CONFIG_RTC_DRV_DS1286=m
# CONFIG_RTC_DRV_DS1511 is not set
CONFIG_RTC_DRV_DS1553=m
CONFIG_RTC_DRV_DS1685_FAMILY=y
# CONFIG_RTC_DRV_DS1685 is not set
# CONFIG_RTC_DRV_DS1689 is not set
# CONFIG_RTC_DRV_DS17285 is not set
# CONFIG_RTC_DRV_DS17485 is not set
CONFIG_RTC_DRV_DS17885=y
# CONFIG_RTC_DS1685_PROC_REGS is not set
CONFIG_RTC_DS1685_SYSFS_REGS=y
CONFIG_RTC_DRV_DS1742=m
# CONFIG_RTC_DRV_DS2404 is not set
CONFIG_RTC_DRV_DA9055=m
CONFIG_RTC_DRV_DA9063=y
CONFIG_RTC_DRV_STK17TA8=m
# CONFIG_RTC_DRV_M48T86 is not set
CONFIG_RTC_DRV_M48T35=m
CONFIG_RTC_DRV_M48T59=m
# CONFIG_RTC_DRV_MSM6242 is not set
CONFIG_RTC_DRV_BQ4802=y
# CONFIG_RTC_DRV_RP5C01 is not set
# CONFIG_RTC_DRV_V3020 is not set
CONFIG_RTC_DRV_PCF50633=y
#
# on-CPU RTC drivers
#
# CONFIG_RTC_DRV_MT6397 is not set
#
# HID Sensor RTC drivers
#
# CONFIG_RTC_DRV_HID_SENSOR_TIME is not set
CONFIG_DMADEVICES=y
# CONFIG_DMADEVICES_DEBUG is not set
#
# DMA Devices
#
CONFIG_DMA_ENGINE=y
CONFIG_DMA_VIRTUAL_CHANNELS=y
CONFIG_DMA_ACPI=y
# CONFIG_INTEL_IDMA64 is not set
# CONFIG_PCH_DMA is not set
CONFIG_QCOM_HIDMA_MGMT=y
CONFIG_QCOM_HIDMA=y
CONFIG_DW_DMAC_CORE=y
CONFIG_DW_DMAC=y
# CONFIG_DW_DMAC_PCI is not set
CONFIG_HSU_DMA=y
#
# DMA Clients
#
CONFIG_ASYNC_TX_DMA=y
CONFIG_DMATEST=y
#
# DMABUF options
#
CONFIG_SYNC_FILE=y
CONFIG_SW_SYNC=y
# CONFIG_AUXDISPLAY is not set
CONFIG_UIO=y
# CONFIG_UIO_CIF is not set
# CONFIG_UIO_PDRV_GENIRQ is not set
CONFIG_UIO_DMEM_GENIRQ=m
# CONFIG_UIO_AEC is not set
# CONFIG_UIO_SERCOS3 is not set
# CONFIG_UIO_PCI_GENERIC is not set
# CONFIG_UIO_NETX is not set
CONFIG_UIO_PRUSS=m
# CONFIG_UIO_MF624 is not set
CONFIG_VIRT_DRIVERS=y
CONFIG_VIRTIO=y
#
# Virtio drivers
#
# CONFIG_VIRTIO_PCI is not set
CONFIG_VIRTIO_BALLOON=m
# CONFIG_VIRTIO_INPUT is not set
# CONFIG_VIRTIO_MMIO is not set
#
# Microsoft Hyper-V guest support
#
# CONFIG_STAGING is not set
# CONFIG_X86_PLATFORM_DEVICES is not set
CONFIG_PMC_ATOM=y
CONFIG_CHROME_PLATFORMS=y
CONFIG_CHROMEOS_LAPTOP=y
CONFIG_CHROMEOS_PSTORE=m
CONFIG_CROS_EC_CHARDEV=m
CONFIG_CROS_EC_LPC=m
CONFIG_CROS_EC_PROTO=y
# CONFIG_CROS_KBD_LED_BACKLIGHT is not set
CONFIG_CLKDEV_LOOKUP=y
CONFIG_HAVE_CLK_PREPARE=y
CONFIG_COMMON_CLK=y
#
# Common Clock Framework
#
# CONFIG_COMMON_CLK_SI5351 is not set
# CONFIG_COMMON_CLK_CDCE706 is not set
# CONFIG_COMMON_CLK_CS2000_CP is not set
# CONFIG_COMMON_CLK_S2MPS11 is not set
# CONFIG_CLK_TWL6040 is not set
# CONFIG_COMMON_CLK_NXP is not set
# CONFIG_COMMON_CLK_PALMAS is not set
# CONFIG_COMMON_CLK_PXA is not set
# CONFIG_COMMON_CLK_PIC32 is not set
#
# Hardware Spinlock drivers
#
#
# Clock Source drivers
#
CONFIG_CLKSRC_I8253=y
CONFIG_CLKEVT_I8253=y
CONFIG_I8253_LOCK=y
CONFIG_CLKBLD_I8253=y
# CONFIG_ATMEL_PIT is not set
# CONFIG_SH_TIMER_CMT is not set
# CONFIG_SH_TIMER_MTU2 is not set
# CONFIG_SH_TIMER_TMU is not set
# CONFIG_EM_TIMER_STI is not set
# CONFIG_MAILBOX is not set
CONFIG_IOMMU_SUPPORT=y
#
# Generic IOMMU Pagetable Support
#
#
# Remoteproc drivers
#
CONFIG_REMOTEPROC=y
#
# Rpmsg drivers
#
#
# SOC (System On Chip) specific Drivers
#
#
# Broadcom SoC drivers
#
# CONFIG_SUNXI_SRAM is not set
CONFIG_SOC_TI=y
# CONFIG_SOC_ZTE is not set
CONFIG_PM_DEVFREQ=y
#
# DEVFREQ Governors
#
CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND=y
# CONFIG_DEVFREQ_GOV_PERFORMANCE is not set
CONFIG_DEVFREQ_GOV_POWERSAVE=m
CONFIG_DEVFREQ_GOV_USERSPACE=y
# CONFIG_DEVFREQ_GOV_PASSIVE is not set
#
# DEVFREQ Drivers
#
# CONFIG_PM_DEVFREQ_EVENT is not set
CONFIG_EXTCON=y
#
# Extcon Device Drivers
#
CONFIG_EXTCON_ADC_JACK=y
# CONFIG_EXTCON_AXP288 is not set
CONFIG_EXTCON_GPIO=y
# CONFIG_EXTCON_INTEL_INT3496 is not set
CONFIG_EXTCON_MAX3355=m
# CONFIG_EXTCON_MAX77693 is not set
# CONFIG_EXTCON_MAX77843 is not set
# CONFIG_EXTCON_PALMAS is not set
CONFIG_EXTCON_QCOM_SPMI_MISC=y
CONFIG_EXTCON_RT8973A=y
# CONFIG_EXTCON_SM5502 is not set
CONFIG_EXTCON_USB_GPIO=m
# CONFIG_MEMORY is not set
CONFIG_IIO=y
CONFIG_IIO_BUFFER=y
CONFIG_IIO_BUFFER_CB=y
CONFIG_IIO_KFIFO_BUF=y
CONFIG_IIO_TRIGGERED_BUFFER=y
CONFIG_IIO_CONFIGFS=y
CONFIG_IIO_TRIGGER=y
CONFIG_IIO_CONSUMERS_PER_TRIGGER=2
CONFIG_IIO_SW_DEVICE=y
CONFIG_IIO_SW_TRIGGER=y
#
# Accelerometers
#
# CONFIG_BMA180 is not set
CONFIG_BMC150_ACCEL=y
CONFIG_BMC150_ACCEL_I2C=y
CONFIG_DA280=y
# CONFIG_DA311 is not set
CONFIG_DMARD09=m
CONFIG_DMARD10=m
CONFIG_IIO_ST_ACCEL_3AXIS=m
CONFIG_IIO_ST_ACCEL_I2C_3AXIS=m
CONFIG_KXSD9=y
# CONFIG_KXSD9_I2C is not set
CONFIG_KXCJK1013=y
CONFIG_MC3230=y
CONFIG_MMA7455=m
CONFIG_MMA7455_I2C=m
# CONFIG_MMA7660 is not set
# CONFIG_MMA8452 is not set
CONFIG_MMA9551_CORE=y
# CONFIG_MMA9551 is not set
CONFIG_MMA9553=y
CONFIG_MXC4005=y
CONFIG_MXC6255=y
# CONFIG_STK8312 is not set
# CONFIG_STK8BA50 is not set
#
# Analog to digital converters
#
CONFIG_AD7291=y
CONFIG_AD799X=y
CONFIG_AXP288_ADC=m
# CONFIG_HX711 is not set
CONFIG_INA2XX_ADC=m
CONFIG_LP8788_ADC=m
# CONFIG_LTC2485 is not set
# CONFIG_MAX1363 is not set
# CONFIG_MCP3422 is not set
CONFIG_NAU7802=m
CONFIG_PALMAS_GPADC=y
CONFIG_QCOM_SPMI_IADC=m
# CONFIG_QCOM_SPMI_VADC is not set
CONFIG_STX104=y
CONFIG_TI_ADC081C=m
CONFIG_TI_ADS1015=m
CONFIG_TI_AM335X_ADC=m
#
# Amplifiers
#
#
# Chemical Sensors
#
CONFIG_ATLAS_PH_SENSOR=m
CONFIG_IAQCORE=y
CONFIG_VZ89X=m
CONFIG_IIO_CROS_EC_SENSORS_CORE=m
CONFIG_IIO_CROS_EC_SENSORS=m
#
# Hid Sensor IIO Common
#
CONFIG_IIO_MS_SENSORS_I2C=y
#
# SSP Sensor Common
#
CONFIG_IIO_ST_SENSORS_I2C=y
CONFIG_IIO_ST_SENSORS_CORE=y
#
# Counters
#
# CONFIG_104_QUAD_8 is not set
#
# Digital to analog converters
#
CONFIG_AD5064=m
CONFIG_AD5380=y
CONFIG_AD5446=y
# CONFIG_AD5593R is not set
CONFIG_CIO_DAC=y
# CONFIG_M62332 is not set
# CONFIG_MAX517 is not set
# CONFIG_MCP4725 is not set
#
# IIO dummy driver
#
CONFIG_IIO_SIMPLE_DUMMY=m
# CONFIG_IIO_SIMPLE_DUMMY_EVENTS is not set
# CONFIG_IIO_SIMPLE_DUMMY_BUFFER is not set
#
# Frequency Synthesizers DDS/PLL
#
#
# Clock Generator/Distribution
#
#
# Phase-Locked Loop (PLL) frequency synthesizers
#
#
# Digital gyroscope sensors
#
CONFIG_BMG160=y
CONFIG_BMG160_I2C=y
# CONFIG_MPU3050_I2C is not set
CONFIG_IIO_ST_GYRO_3AXIS=y
CONFIG_IIO_ST_GYRO_I2C_3AXIS=y
CONFIG_ITG3200=y
#
# Health Sensors
#
#
# Heart Rate Monitors
#
# CONFIG_AFE4404 is not set
# CONFIG_MAX30100 is not set
#
# Humidity sensors
#
CONFIG_AM2315=y
CONFIG_DHT11=m
CONFIG_HDC100X=m
CONFIG_HTS221=y
CONFIG_HTS221_I2C=y
CONFIG_HTU21=m
CONFIG_SI7005=m
CONFIG_SI7020=m
#
# Inertial measurement units
#
CONFIG_BMI160=y
CONFIG_BMI160_I2C=y
CONFIG_KMX61=m
# CONFIG_INV_MPU6050_I2C is not set
# CONFIG_IIO_ST_LSM6DSX is not set
#
# Light sensors
#
# CONFIG_ACPI_ALS is not set
# CONFIG_ADJD_S311 is not set
CONFIG_AL3320A=y
# CONFIG_APDS9300 is not set
CONFIG_APDS9960=m
# CONFIG_BH1750 is not set
CONFIG_BH1780=m
CONFIG_CM32181=m
CONFIG_CM3232=y
# CONFIG_CM3323 is not set
# CONFIG_CM36651 is not set
# CONFIG_GP2AP020A00F is not set
# CONFIG_SENSORS_ISL29018 is not set
CONFIG_ISL29125=m
CONFIG_JSA1212=y
CONFIG_RPR0521=m
CONFIG_SENSORS_LM3533=m
# CONFIG_LTR501 is not set
CONFIG_MAX44000=y
# CONFIG_OPT3001 is not set
CONFIG_PA12203001=y
CONFIG_SI1145=y
# CONFIG_STK3310 is not set
# CONFIG_TCS3414 is not set
CONFIG_TCS3472=m
CONFIG_SENSORS_TSL2563=y
CONFIG_TSL2583=y
CONFIG_TSL4531=m
CONFIG_US5182D=y
CONFIG_VCNL4000=m
# CONFIG_VEML6070 is not set
#
# Magnetometer sensors
#
CONFIG_AK8975=m
# CONFIG_AK09911 is not set
# CONFIG_BMC150_MAGN_I2C is not set
# CONFIG_MAG3110 is not set
CONFIG_MMC35240=y
# CONFIG_IIO_ST_MAGN_3AXIS is not set
# CONFIG_SENSORS_HMC5843_I2C is not set
#
# Inclinometer sensors
#
#
# Triggers - standalone
#
CONFIG_IIO_HRTIMER_TRIGGER=m
CONFIG_IIO_INTERRUPT_TRIGGER=y
CONFIG_IIO_TIGHTLOOP_TRIGGER=y
CONFIG_IIO_SYSFS_TRIGGER=m
#
# Digital potentiometers
#
# CONFIG_DS1803 is not set
# CONFIG_MCP4531 is not set
# CONFIG_TPL0102 is not set
#
# Digital potentiostats
#
CONFIG_LMP91000=y
#
# Pressure sensors
#
CONFIG_ABP060MG=m
CONFIG_BMP280=y
CONFIG_BMP280_I2C=y
# CONFIG_IIO_CROS_EC_BARO is not set
# CONFIG_HP03 is not set
# CONFIG_MPL115_I2C is not set
# CONFIG_MPL3115 is not set
CONFIG_MS5611=m
CONFIG_MS5611_I2C=m
CONFIG_MS5637=m
# CONFIG_IIO_ST_PRESS is not set
# CONFIG_T5403 is not set
# CONFIG_HP206C is not set
CONFIG_ZPA2326=y
CONFIG_ZPA2326_I2C=y
#
# Lightning sensors
#
#
# Proximity and distance sensors
#
# CONFIG_LIDAR_LITE_V2 is not set
# CONFIG_SX9500 is not set
# CONFIG_SRF08 is not set
#
# Temperature sensors
#
CONFIG_MLX90614=y
# CONFIG_TMP006 is not set
# CONFIG_TMP007 is not set
CONFIG_TSYS01=y
# CONFIG_TSYS02D is not set
# CONFIG_NTB is not set
# CONFIG_VME_BUS is not set
# CONFIG_PWM is not set
CONFIG_ARM_GIC_MAX_NR=1
CONFIG_IPACK_BUS=y
# CONFIG_BOARD_TPCI200 is not set
# CONFIG_SERIAL_IPOCTAL is not set
CONFIG_RESET_CONTROLLER=y
# CONFIG_RESET_ATH79 is not set
# CONFIG_RESET_BERLIN is not set
# CONFIG_RESET_LPC18XX is not set
# CONFIG_RESET_MESON is not set
# CONFIG_RESET_PISTACHIO is not set
# CONFIG_RESET_SOCFPGA is not set
# CONFIG_RESET_STM32 is not set
# CONFIG_RESET_SUNXI is not set
CONFIG_TI_SYSCON_RESET=m
# CONFIG_RESET_ZYNQ is not set
# CONFIG_RESET_TEGRA_BPMP is not set
CONFIG_FMC=m
CONFIG_FMC_FAKEDEV=m
CONFIG_FMC_TRIVIAL=m
CONFIG_FMC_WRITE_EEPROM=m
CONFIG_FMC_CHARDEV=m
#
# PHY Subsystem
#
CONFIG_GENERIC_PHY=y
# CONFIG_PHY_PXA_28NM_HSIC is not set
# CONFIG_PHY_PXA_28NM_USB2 is not set
CONFIG_BCM_KONA_USB2_PHY=m
# CONFIG_PHY_QCOM_USB_HS is not set
# CONFIG_PHY_QCOM_USB_HSIC is not set
CONFIG_PHY_TUSB1210=m
# CONFIG_POWERCAP is not set
# CONFIG_MCB is not set
#
# Performance monitor support
#
CONFIG_RAS=y
# CONFIG_THUNDERBOLT is not set
#
# Android
#
# CONFIG_ANDROID is not set
# CONFIG_LIBNVDIMM is not set
CONFIG_DEV_DAX=y
CONFIG_NR_DEV_DAX=32768
CONFIG_NVMEM=y
CONFIG_STM=y
# CONFIG_STM_DUMMY is not set
CONFIG_STM_SOURCE_CONSOLE=y
# CONFIG_STM_SOURCE_HEARTBEAT is not set
CONFIG_INTEL_TH=m
# CONFIG_INTEL_TH_PCI is not set
# CONFIG_INTEL_TH_GTH is not set
# CONFIG_INTEL_TH_STH is not set
# CONFIG_INTEL_TH_MSU is not set
CONFIG_INTEL_TH_PTI=m
# CONFIG_INTEL_TH_DEBUG is not set
#
# FPGA Configuration Support
#
CONFIG_FPGA=y
#
# FSI support
#
# CONFIG_FSI is not set
#
# Firmware Drivers
#
CONFIG_EDD=m
# CONFIG_EDD_OFF is not set
CONFIG_FIRMWARE_MEMMAP=y
# CONFIG_DELL_RBU is not set
CONFIG_DCDBAS=y
CONFIG_DMIID=y
CONFIG_DMI_SYSFS=m
CONFIG_DMI_SCAN_MACHINE_NON_EFI_FALLBACK=y
# CONFIG_ISCSI_IBFT_FIND is not set
# CONFIG_FW_CFG_SYSFS is not set
# CONFIG_GOOGLE_FIRMWARE is not set
# CONFIG_EFI_DEV_PATH_PARSER is not set
#
# Tegra firmware driver
#
#
# File systems
#
CONFIG_DCACHE_WORD_ACCESS=y
CONFIG_EXT2_FS=y
# CONFIG_EXT2_FS_XATTR is not set
CONFIG_EXT3_FS=y
CONFIG_EXT3_FS_POSIX_ACL=y
CONFIG_EXT3_FS_SECURITY=y
CONFIG_EXT4_FS=y
CONFIG_EXT4_FS_POSIX_ACL=y
CONFIG_EXT4_FS_SECURITY=y
CONFIG_EXT4_ENCRYPTION=y
CONFIG_EXT4_FS_ENCRYPTION=y
CONFIG_EXT4_DEBUG=y
CONFIG_JBD2=y
CONFIG_JBD2_DEBUG=y
CONFIG_FS_MBCACHE=y
CONFIG_REISERFS_FS=y
# CONFIG_REISERFS_CHECK is not set
# CONFIG_REISERFS_PROC_INFO is not set
CONFIG_REISERFS_FS_XATTR=y
CONFIG_REISERFS_FS_POSIX_ACL=y
# CONFIG_REISERFS_FS_SECURITY is not set
CONFIG_JFS_FS=m
CONFIG_JFS_POSIX_ACL=y
CONFIG_JFS_SECURITY=y
# CONFIG_JFS_DEBUG is not set
# CONFIG_JFS_STATISTICS is not set
CONFIG_OCFS2_FS=y
CONFIG_OCFS2_FS_O2CB=y
CONFIG_OCFS2_FS_USERSPACE_CLUSTER=y
# CONFIG_OCFS2_FS_STATS is not set
CONFIG_OCFS2_DEBUG_MASKLOG=y
CONFIG_OCFS2_DEBUG_FS=y
CONFIG_BTRFS_FS=y
# CONFIG_BTRFS_FS_POSIX_ACL is not set
CONFIG_BTRFS_FS_CHECK_INTEGRITY=y
# CONFIG_BTRFS_FS_RUN_SANITY_TESTS is not set
# CONFIG_BTRFS_DEBUG is not set
# CONFIG_BTRFS_ASSERT is not set
CONFIG_NILFS2_FS=y
CONFIG_F2FS_FS=m
# CONFIG_F2FS_STAT_FS is not set
# CONFIG_F2FS_FS_XATTR is not set
CONFIG_F2FS_CHECK_FS=y
CONFIG_F2FS_FAULT_INJECTION=y
# CONFIG_FS_DAX is not set
CONFIG_FS_POSIX_ACL=y
CONFIG_EXPORTFS=y
CONFIG_EXPORTFS_BLOCK_OPS=y
CONFIG_FILE_LOCKING=y
# CONFIG_MANDATORY_FILE_LOCKING is not set
CONFIG_FS_ENCRYPTION=y
CONFIG_FSNOTIFY=y
CONFIG_DNOTIFY=y
CONFIG_INOTIFY_USER=y
# CONFIG_FANOTIFY is not set
CONFIG_QUOTA=y
CONFIG_QUOTA_NETLINK_INTERFACE=y
# CONFIG_PRINT_QUOTA_WARNING is not set
CONFIG_QUOTA_DEBUG=y
CONFIG_QUOTA_TREE=y
# CONFIG_QFMT_V1 is not set
# CONFIG_QFMT_V2 is not set
CONFIG_QUOTACTL=y
CONFIG_AUTOFS4_FS=m
CONFIG_FUSE_FS=y
# CONFIG_CUSE is not set
# CONFIG_OVERLAY_FS is not set
#
# Caches
#
CONFIG_FSCACHE=m
# CONFIG_FSCACHE_STATS is not set
# CONFIG_FSCACHE_HISTOGRAM is not set
CONFIG_FSCACHE_DEBUG=y
# CONFIG_FSCACHE_OBJECT_LIST is not set
CONFIG_CACHEFILES=m
CONFIG_CACHEFILES_DEBUG=y
# CONFIG_CACHEFILES_HISTOGRAM is not set
#
# CD-ROM/DVD Filesystems
#
CONFIG_ISO9660_FS=y
# CONFIG_JOLIET is not set
# CONFIG_ZISOFS is not set
# CONFIG_UDF_FS is not set
#
# DOS/FAT/NT Filesystems
#
CONFIG_FAT_FS=y
CONFIG_MSDOS_FS=m
CONFIG_VFAT_FS=y
CONFIG_FAT_DEFAULT_CODEPAGE=437
CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1"
CONFIG_FAT_DEFAULT_UTF8=y
CONFIG_NTFS_FS=y
CONFIG_NTFS_DEBUG=y
CONFIG_NTFS_RW=y
#
# Pseudo filesystems
#
CONFIG_PROC_FS=y
# CONFIG_PROC_KCORE is not set
CONFIG_PROC_SYSCTL=y
CONFIG_PROC_PAGE_MONITOR=y
CONFIG_PROC_CHILDREN=y
CONFIG_KERNFS=y
CONFIG_SYSFS=y
CONFIG_TMPFS=y
# CONFIG_TMPFS_POSIX_ACL is not set
# CONFIG_TMPFS_XATTR is not set
# CONFIG_HUGETLBFS is not set
# CONFIG_HUGETLB_PAGE is not set
CONFIG_CONFIGFS_FS=y
# CONFIG_MISC_FILESYSTEMS is not set
CONFIG_NETWORK_FILESYSTEMS=y
CONFIG_NFS_FS=m
CONFIG_NFS_V2=m
CONFIG_NFS_V3=m
# CONFIG_NFS_V3_ACL is not set
CONFIG_NFS_V4=m
# CONFIG_NFS_SWAP is not set
# CONFIG_NFS_V4_1 is not set
# CONFIG_NFS_FSCACHE is not set
# CONFIG_NFS_USE_LEGACY_DNS is not set
CONFIG_NFS_USE_KERNEL_DNS=y
# CONFIG_NFSD is not set
CONFIG_GRACE_PERIOD=m
CONFIG_LOCKD=m
CONFIG_LOCKD_V4=y
CONFIG_NFS_COMMON=y
CONFIG_SUNRPC=m
CONFIG_SUNRPC_GSS=m
CONFIG_RPCSEC_GSS_KRB5=m
# CONFIG_SUNRPC_DEBUG is not set
CONFIG_CEPH_FS=y
CONFIG_CEPH_FS_POSIX_ACL=y
CONFIG_CIFS=m
# CONFIG_CIFS_STATS is not set
# CONFIG_CIFS_WEAK_PW_HASH is not set
CONFIG_CIFS_UPCALL=y
# CONFIG_CIFS_XATTR is not set
# CONFIG_CIFS_DEBUG is not set
# CONFIG_CIFS_DFS_UPCALL is not set
CONFIG_CIFS_SMB2=y
# CONFIG_CIFS_SMB311 is not set
# CONFIG_CIFS_FSCACHE is not set
CONFIG_NCP_FS=y
# CONFIG_NCPFS_PACKET_SIGNING is not set
# CONFIG_NCPFS_IOCTL_LOCKING is not set
CONFIG_NCPFS_STRONG=y
CONFIG_NCPFS_NFS_NS=y
CONFIG_NCPFS_OS2_NS=y
# CONFIG_NCPFS_SMALLDOS is not set
# CONFIG_NCPFS_NLS is not set
# CONFIG_NCPFS_EXTRAS is not set
CONFIG_CODA_FS=m
# CONFIG_AFS_FS is not set
# CONFIG_9P_FS is not set
CONFIG_NLS=y
CONFIG_NLS_DEFAULT="iso8859-1"
CONFIG_NLS_CODEPAGE_437=m
CONFIG_NLS_CODEPAGE_737=y
CONFIG_NLS_CODEPAGE_775=y
# CONFIG_NLS_CODEPAGE_850 is not set
# CONFIG_NLS_CODEPAGE_852 is not set
CONFIG_NLS_CODEPAGE_855=y
CONFIG_NLS_CODEPAGE_857=y
CONFIG_NLS_CODEPAGE_860=y
# CONFIG_NLS_CODEPAGE_861 is not set
# CONFIG_NLS_CODEPAGE_862 is not set
CONFIG_NLS_CODEPAGE_863=y
CONFIG_NLS_CODEPAGE_864=m
CONFIG_NLS_CODEPAGE_865=y
# CONFIG_NLS_CODEPAGE_866 is not set
CONFIG_NLS_CODEPAGE_869=y
CONFIG_NLS_CODEPAGE_936=m
CONFIG_NLS_CODEPAGE_950=y
# CONFIG_NLS_CODEPAGE_932 is not set
CONFIG_NLS_CODEPAGE_949=y
CONFIG_NLS_CODEPAGE_874=m
CONFIG_NLS_ISO8859_8=m
CONFIG_NLS_CODEPAGE_1250=y
# CONFIG_NLS_CODEPAGE_1251 is not set
CONFIG_NLS_ASCII=m
CONFIG_NLS_ISO8859_1=m
# CONFIG_NLS_ISO8859_2 is not set
CONFIG_NLS_ISO8859_3=y
CONFIG_NLS_ISO8859_4=m
# CONFIG_NLS_ISO8859_5 is not set
# CONFIG_NLS_ISO8859_6 is not set
CONFIG_NLS_ISO8859_7=m
# CONFIG_NLS_ISO8859_9 is not set
CONFIG_NLS_ISO8859_13=m
CONFIG_NLS_ISO8859_14=m
CONFIG_NLS_ISO8859_15=m
CONFIG_NLS_KOI8_R=m
# CONFIG_NLS_KOI8_U is not set
# CONFIG_NLS_MAC_ROMAN is not set
CONFIG_NLS_MAC_CELTIC=m
# CONFIG_NLS_MAC_CENTEURO is not set
# CONFIG_NLS_MAC_CROATIAN is not set
CONFIG_NLS_MAC_CYRILLIC=y
# CONFIG_NLS_MAC_GAELIC is not set
CONFIG_NLS_MAC_GREEK=m
# CONFIG_NLS_MAC_ICELAND is not set
CONFIG_NLS_MAC_INUIT=y
CONFIG_NLS_MAC_ROMANIAN=m
# CONFIG_NLS_MAC_TURKISH is not set
# CONFIG_NLS_UTF8 is not set
CONFIG_DLM=y
CONFIG_DLM_DEBUG=y
#
# Kernel hacking
#
CONFIG_TRACE_IRQFLAGS_SUPPORT=y
#
# printk and dmesg options
#
CONFIG_PRINTK_TIME=y
CONFIG_CONSOLE_LOGLEVEL_DEFAULT=7
CONFIG_MESSAGE_LOGLEVEL_DEFAULT=4
# CONFIG_BOOT_PRINTK_DELAY is not set
# CONFIG_DYNAMIC_DEBUG is not set
#
# Compile-time checks and compiler options
#
# CONFIG_DEBUG_INFO is not set
# CONFIG_ENABLE_WARN_DEPRECATED is not set
# CONFIG_ENABLE_MUST_CHECK is not set
CONFIG_FRAME_WARN=1024
CONFIG_STRIP_ASM_SYMS=y
# CONFIG_READABLE_ASM is not set
# CONFIG_UNUSED_SYMBOLS is not set
CONFIG_PAGE_OWNER=y
CONFIG_DEBUG_FS=y
CONFIG_HEADERS_CHECK=y
# CONFIG_DEBUG_SECTION_MISMATCH is not set
CONFIG_SECTION_MISMATCH_WARN_ONLY=y
CONFIG_ARCH_WANT_FRAME_POINTERS=y
CONFIG_FRAME_POINTER=y
CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_MAGIC_SYSRQ_DEFAULT_ENABLE=0x1
CONFIG_MAGIC_SYSRQ_SERIAL=y
CONFIG_DEBUG_KERNEL=y
#
# Memory Debugging
#
CONFIG_PAGE_EXTENSION=y
# CONFIG_DEBUG_PAGEALLOC is not set
CONFIG_PAGE_POISONING=y
# CONFIG_PAGE_POISONING_NO_SANITY is not set
# CONFIG_PAGE_POISONING_ZERO is not set
# CONFIG_DEBUG_RODATA_TEST is not set
CONFIG_DEBUG_OBJECTS=y
# CONFIG_DEBUG_OBJECTS_SELFTEST is not set
# CONFIG_DEBUG_OBJECTS_FREE is not set
CONFIG_DEBUG_OBJECTS_TIMERS=y
CONFIG_DEBUG_OBJECTS_WORK=y
CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER=y
CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT=1
CONFIG_HAVE_DEBUG_KMEMLEAK=y
# CONFIG_DEBUG_KMEMLEAK is not set
# CONFIG_DEBUG_STACK_USAGE is not set
CONFIG_DEBUG_VM=y
# CONFIG_DEBUG_VM_VMACACHE is not set
CONFIG_DEBUG_VM_RB=y
# CONFIG_DEBUG_VM_PGFLAGS is not set
CONFIG_ARCH_HAS_DEBUG_VIRTUAL=y
CONFIG_DEBUG_VIRTUAL=y
# CONFIG_DEBUG_MEMORY_INIT is not set
CONFIG_DEBUG_HIGHMEM=y
CONFIG_HAVE_DEBUG_STACKOVERFLOW=y
CONFIG_DEBUG_STACKOVERFLOW=y
CONFIG_HAVE_ARCH_KMEMCHECK=y
# CONFIG_DEBUG_SHIRQ is not set
#
# Debug Lockups and Hangs
#
# CONFIG_LOCKUP_DETECTOR is not set
CONFIG_DETECT_HUNG_TASK=y
CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=120
CONFIG_BOOTPARAM_HUNG_TASK_PANIC=y
CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE=1
CONFIG_WQ_WATCHDOG=y
CONFIG_PANIC_ON_OOPS=y
CONFIG_PANIC_ON_OOPS_VALUE=1
CONFIG_PANIC_TIMEOUT=0
CONFIG_SCHED_DEBUG=y
# CONFIG_SCHED_INFO is not set
# CONFIG_SCHEDSTATS is not set
# CONFIG_SCHED_STACK_END_CHECK is not set
CONFIG_DEBUG_TIMEKEEPING=y
CONFIG_DEBUG_PREEMPT=y
#
# Lock Debugging (spinlocks, mutexes, etc...)
#
CONFIG_DEBUG_RT_MUTEXES=y
CONFIG_DEBUG_SPINLOCK=y
CONFIG_DEBUG_MUTEXES=y
CONFIG_DEBUG_WW_MUTEX_SLOWPATH=y
CONFIG_DEBUG_LOCK_ALLOC=y
CONFIG_PROVE_LOCKING=y
CONFIG_LOCKDEP=y
# CONFIG_LOCK_STAT is not set
# CONFIG_DEBUG_LOCKDEP is not set
CONFIG_DEBUG_ATOMIC_SLEEP=y
CONFIG_DEBUG_LOCKING_API_SELFTESTS=y
CONFIG_LOCK_TORTURE_TEST=m
# CONFIG_WW_MUTEX_SELFTEST is not set
CONFIG_TRACE_IRQFLAGS=y
CONFIG_STACKTRACE=y
# CONFIG_DEBUG_KOBJECT is not set
# CONFIG_DEBUG_KOBJECT_RELEASE is not set
CONFIG_DEBUG_BUGVERBOSE=y
CONFIG_DEBUG_LIST=y
CONFIG_DEBUG_PI_LIST=y
CONFIG_DEBUG_SG=y
# CONFIG_DEBUG_NOTIFIERS is not set
CONFIG_DEBUG_CREDENTIALS=y
#
# RCU Debugging
#
CONFIG_PROVE_RCU=y
CONFIG_PROVE_RCU_REPEATEDLY=y
# CONFIG_SPARSE_RCU_POINTER is not set
CONFIG_TORTURE_TEST=y
# CONFIG_RCU_PERF_TEST is not set
CONFIG_RCU_TORTURE_TEST=y
# CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT is not set
# CONFIG_RCU_TORTURE_TEST_SLOW_INIT is not set
CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y
CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP_DELAY=3
CONFIG_RCU_CPU_STALL_TIMEOUT=21
CONFIG_RCU_TRACE=y
# CONFIG_RCU_EQS_DEBUG is not set
CONFIG_DEBUG_WQ_FORCE_RR_CPU=y
# CONFIG_DEBUG_BLOCK_EXT_DEVT is not set
CONFIG_NOTIFIER_ERROR_INJECTION=y
CONFIG_PM_NOTIFIER_ERROR_INJECT=y
CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m
CONFIG_FAULT_INJECTION=y
CONFIG_FAIL_PAGE_ALLOC=y
# CONFIG_FAIL_MAKE_REQUEST is not set
CONFIG_FAIL_IO_TIMEOUT=y
CONFIG_FAIL_FUTEX=y
# CONFIG_FAULT_INJECTION_DEBUG_FS is not set
# CONFIG_LATENCYTOP is not set
CONFIG_USER_STACKTRACE_SUPPORT=y
CONFIG_HAVE_FUNCTION_TRACER=y
CONFIG_HAVE_FUNCTION_GRAPH_TRACER=y
CONFIG_HAVE_DYNAMIC_FTRACE=y
CONFIG_HAVE_DYNAMIC_FTRACE_WITH_REGS=y
CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
CONFIG_HAVE_SYSCALL_TRACEPOINTS=y
CONFIG_HAVE_C_RECORDMCOUNT=y
CONFIG_TRACE_CLOCK=y
CONFIG_TRACING_SUPPORT=y
# CONFIG_FTRACE is not set
#
# Runtime Testing
#
# CONFIG_LKDTM is not set
# CONFIG_TEST_LIST_SORT is not set
# CONFIG_TEST_SORT is not set
# CONFIG_KPROBES_SANITY_TEST is not set
# CONFIG_BACKTRACE_SELF_TEST is not set
# CONFIG_RBTREE_TEST is not set
CONFIG_INTERVAL_TREE_TEST=m
CONFIG_PERCPU_TEST=m
# CONFIG_ATOMIC64_SELFTEST is not set
# CONFIG_ASYNC_RAID6_TEST is not set
CONFIG_TEST_HEXDUMP=y
CONFIG_TEST_STRING_HELPERS=m
# CONFIG_TEST_KSTRTOX is not set
CONFIG_TEST_PRINTF=m
CONFIG_TEST_BITMAP=m
CONFIG_TEST_UUID=m
CONFIG_TEST_RHASHTABLE=y
CONFIG_TEST_HASH=m
# CONFIG_PROVIDE_OHCI1394_DMA_INIT is not set
# CONFIG_DMA_API_DEBUG is not set
# CONFIG_TEST_LKM is not set
CONFIG_TEST_USER_COPY=m
CONFIG_TEST_BPF=m
CONFIG_TEST_FIRMWARE=y
# CONFIG_TEST_UDELAY is not set
# CONFIG_MEMTEST is not set
CONFIG_TEST_STATIC_KEYS=m
# CONFIG_BUG_ON_DATA_CORRUPTION is not set
# CONFIG_SAMPLES is not set
CONFIG_HAVE_ARCH_KGDB=y
# CONFIG_KGDB is not set
CONFIG_ARCH_HAS_UBSAN_SANITIZE_ALL=y
# CONFIG_ARCH_WANTS_UBSAN_NO_NULL is not set
CONFIG_UBSAN=y
# CONFIG_UBSAN_SANITIZE_ALL is not set
# CONFIG_UBSAN_ALIGNMENT is not set
CONFIG_UBSAN_NULL=y
CONFIG_ARCH_HAS_DEVMEM_IS_ALLOWED=y
CONFIG_STRICT_DEVMEM=y
# CONFIG_IO_STRICT_DEVMEM is not set
CONFIG_X86_VERBOSE_BOOTUP=y
CONFIG_EARLY_PRINTK=y
# CONFIG_EARLY_PRINTK_DBGP is not set
CONFIG_X86_PTDUMP_CORE=y
CONFIG_X86_PTDUMP=m
# CONFIG_DEBUG_WX is not set
CONFIG_DOUBLEFAULT=y
# CONFIG_DEBUG_TLBFLUSH is not set
# CONFIG_IOMMU_STRESS is not set
CONFIG_HAVE_MMIOTRACE_SUPPORT=y
# CONFIG_X86_DECODER_SELFTEST is not set
CONFIG_IO_DELAY_TYPE_0X80=0
CONFIG_IO_DELAY_TYPE_0XED=1
CONFIG_IO_DELAY_TYPE_UDELAY=2
CONFIG_IO_DELAY_TYPE_NONE=3
CONFIG_IO_DELAY_0X80=y
# CONFIG_IO_DELAY_0XED is not set
# CONFIG_IO_DELAY_UDELAY is not set
# CONFIG_IO_DELAY_NONE is not set
CONFIG_DEFAULT_IO_DELAY_TYPE=0
CONFIG_DEBUG_BOOT_PARAMS=y
# CONFIG_CPA_DEBUG is not set
# CONFIG_OPTIMIZE_INLINING is not set
CONFIG_DEBUG_ENTRY=y
# CONFIG_X86_DEBUG_FPU is not set
# CONFIG_PUNIT_ATOM_DEBUG is not set
#
# Security options
#
CONFIG_KEYS=y
# CONFIG_PERSISTENT_KEYRINGS is not set
# CONFIG_BIG_KEYS is not set
CONFIG_TRUSTED_KEYS=m
CONFIG_ENCRYPTED_KEYS=m
# CONFIG_KEY_DH_OPERATIONS is not set
CONFIG_SECURITY_DMESG_RESTRICT=y
# CONFIG_SECURITY is not set
CONFIG_SECURITYFS=y
CONFIG_HAVE_ARCH_HARDENED_USERCOPY=y
# CONFIG_STATIC_USERMODEHELPER is not set
CONFIG_DEFAULT_SECURITY_DAC=y
CONFIG_DEFAULT_SECURITY=""
CONFIG_XOR_BLOCKS=y
CONFIG_ASYNC_CORE=y
CONFIG_ASYNC_MEMCPY=y
CONFIG_ASYNC_XOR=y
CONFIG_ASYNC_PQ=y
CONFIG_ASYNC_RAID6_RECOV=y
CONFIG_CRYPTO=y
#
# Crypto core or helper
#
CONFIG_CRYPTO_ALGAPI=y
CONFIG_CRYPTO_ALGAPI2=y
CONFIG_CRYPTO_AEAD=y
CONFIG_CRYPTO_AEAD2=y
CONFIG_CRYPTO_BLKCIPHER=y
CONFIG_CRYPTO_BLKCIPHER2=y
CONFIG_CRYPTO_HASH=y
CONFIG_CRYPTO_HASH2=y
CONFIG_CRYPTO_RNG=y
CONFIG_CRYPTO_RNG2=y
CONFIG_CRYPTO_RNG_DEFAULT=y
CONFIG_CRYPTO_AKCIPHER2=y
CONFIG_CRYPTO_AKCIPHER=y
CONFIG_CRYPTO_KPP2=y
CONFIG_CRYPTO_KPP=y
CONFIG_CRYPTO_ACOMP2=y
CONFIG_CRYPTO_RSA=y
CONFIG_CRYPTO_DH=y
# CONFIG_CRYPTO_ECDH is not set
CONFIG_CRYPTO_MANAGER=y
CONFIG_CRYPTO_MANAGER2=y
# CONFIG_CRYPTO_USER is not set
CONFIG_CRYPTO_MANAGER_DISABLE_TESTS=y
CONFIG_CRYPTO_GF128MUL=y
CONFIG_CRYPTO_NULL=y
CONFIG_CRYPTO_NULL2=y
CONFIG_CRYPTO_WORKQUEUE=y
CONFIG_CRYPTO_CRYPTD=y
CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_AUTHENC=y
# CONFIG_CRYPTO_TEST is not set
CONFIG_CRYPTO_ABLK_HELPER=y
CONFIG_CRYPTO_SIMD=y
CONFIG_CRYPTO_GLUE_HELPER_X86=y
CONFIG_CRYPTO_ENGINE=m
#
# Authenticated Encryption with Associated Data
#
CONFIG_CRYPTO_CCM=m
CONFIG_CRYPTO_GCM=m
CONFIG_CRYPTO_CHACHA20POLY1305=y
CONFIG_CRYPTO_SEQIV=y
CONFIG_CRYPTO_ECHAINIV=y
#
# Block modes
#
CONFIG_CRYPTO_CBC=y
CONFIG_CRYPTO_CTR=y
CONFIG_CRYPTO_CTS=y
CONFIG_CRYPTO_ECB=y
CONFIG_CRYPTO_LRW=y
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_XTS=y
CONFIG_CRYPTO_KEYWRAP=m
#
# Hash modes
#
CONFIG_CRYPTO_CMAC=y
CONFIG_CRYPTO_HMAC=y
CONFIG_CRYPTO_XCBC=y
# CONFIG_CRYPTO_VMAC is not set
#
# Digest
#
CONFIG_CRYPTO_CRC32C=y
CONFIG_CRYPTO_CRC32C_INTEL=m
CONFIG_CRYPTO_CRC32=m
CONFIG_CRYPTO_CRC32_PCLMUL=y
CONFIG_CRYPTO_CRCT10DIF=y
CONFIG_CRYPTO_GHASH=y
CONFIG_CRYPTO_POLY1305=y
CONFIG_CRYPTO_MD4=m
CONFIG_CRYPTO_MD5=y
# CONFIG_CRYPTO_MICHAEL_MIC is not set
# CONFIG_CRYPTO_RMD128 is not set
CONFIG_CRYPTO_RMD160=y
# CONFIG_CRYPTO_RMD256 is not set
# CONFIG_CRYPTO_RMD320 is not set
CONFIG_CRYPTO_SHA1=y
CONFIG_CRYPTO_SHA256=y
CONFIG_CRYPTO_SHA512=y
# CONFIG_CRYPTO_SHA3 is not set
# CONFIG_CRYPTO_TGR192 is not set
CONFIG_CRYPTO_WP512=m
#
# Ciphers
#
CONFIG_CRYPTO_AES=y
# CONFIG_CRYPTO_AES_TI is not set
CONFIG_CRYPTO_AES_586=y
CONFIG_CRYPTO_AES_NI_INTEL=y
# CONFIG_CRYPTO_ANUBIS is not set
CONFIG_CRYPTO_ARC4=y
# CONFIG_CRYPTO_BLOWFISH is not set
CONFIG_CRYPTO_CAMELLIA=y
CONFIG_CRYPTO_CAST_COMMON=m
# CONFIG_CRYPTO_CAST5 is not set
CONFIG_CRYPTO_CAST6=m
CONFIG_CRYPTO_DES=y
CONFIG_CRYPTO_FCRYPT=m
CONFIG_CRYPTO_KHAZAD=y
CONFIG_CRYPTO_SALSA20=y
CONFIG_CRYPTO_SALSA20_586=m
CONFIG_CRYPTO_CHACHA20=y
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=y
CONFIG_CRYPTO_SERPENT_SSE2_586=y
CONFIG_CRYPTO_TEA=y
# CONFIG_CRYPTO_TWOFISH is not set
CONFIG_CRYPTO_TWOFISH_COMMON=m
CONFIG_CRYPTO_TWOFISH_586=m
#
# Compression
#
CONFIG_CRYPTO_DEFLATE=m
# CONFIG_CRYPTO_LZO is not set
CONFIG_CRYPTO_842=m
# CONFIG_CRYPTO_LZ4 is not set
CONFIG_CRYPTO_LZ4HC=m
#
# Random Number Generation
#
CONFIG_CRYPTO_ANSI_CPRNG=y
CONFIG_CRYPTO_DRBG_MENU=y
CONFIG_CRYPTO_DRBG_HMAC=y
# CONFIG_CRYPTO_DRBG_HASH is not set
CONFIG_CRYPTO_DRBG_CTR=y
CONFIG_CRYPTO_DRBG=y
CONFIG_CRYPTO_JITTERENTROPY=y
CONFIG_CRYPTO_USER_API=m
# CONFIG_CRYPTO_USER_API_HASH is not set
CONFIG_CRYPTO_USER_API_SKCIPHER=m
CONFIG_CRYPTO_USER_API_RNG=m
CONFIG_CRYPTO_USER_API_AEAD=m
CONFIG_CRYPTO_HASH_INFO=y
CONFIG_CRYPTO_HW=y
CONFIG_CRYPTO_DEV_PADLOCK=m
# CONFIG_CRYPTO_DEV_PADLOCK_AES is not set
# CONFIG_CRYPTO_DEV_PADLOCK_SHA is not set
# CONFIG_CRYPTO_DEV_GEODE is not set
# CONFIG_CRYPTO_DEV_FSL_CAAM_CRYPTO_API_DESC is not set
# CONFIG_CRYPTO_DEV_CCP is not set
# CONFIG_CRYPTO_DEV_QAT_DH895xCC is not set
# CONFIG_CRYPTO_DEV_QAT_C3XXX is not set
# CONFIG_CRYPTO_DEV_QAT_C62X is not set
# CONFIG_CRYPTO_DEV_QAT_DH895xCCVF is not set
# CONFIG_CRYPTO_DEV_QAT_C3XXXVF is not set
# CONFIG_CRYPTO_DEV_QAT_C62XVF is not set
CONFIG_CRYPTO_DEV_VIRTIO=m
CONFIG_ASYMMETRIC_KEY_TYPE=y
CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=y
CONFIG_X509_CERTIFICATE_PARSER=y
CONFIG_PKCS7_MESSAGE_PARSER=y
#
# Certificates for signature checking
#
CONFIG_SYSTEM_TRUSTED_KEYRING=y
CONFIG_SYSTEM_TRUSTED_KEYS=""
CONFIG_SYSTEM_EXTRA_CERTIFICATE=y
CONFIG_SYSTEM_EXTRA_CERTIFICATE_SIZE=4096
# CONFIG_SECONDARY_TRUSTED_KEYRING is not set
CONFIG_HAVE_KVM=y
CONFIG_VIRTUALIZATION=y
# CONFIG_KVM is not set
# CONFIG_VHOST_NET is not set
CONFIG_VHOST_SCSI=m
CONFIG_VHOST_VSOCK=m
CONFIG_VHOST=m
CONFIG_VHOST_CROSS_ENDIAN_LEGACY=y
# CONFIG_LGUEST is not set
# CONFIG_BINARY_PRINTF is not set
#
# Library routines
#
CONFIG_RAID6_PQ=y
CONFIG_BITREVERSE=y
# CONFIG_HAVE_ARCH_BITREVERSE is not set
CONFIG_RATIONAL=y
CONFIG_GENERIC_STRNCPY_FROM_USER=y
CONFIG_GENERIC_STRNLEN_USER=y
CONFIG_GENERIC_NET_UTILS=y
CONFIG_GENERIC_FIND_FIRST_BIT=y
CONFIG_GENERIC_PCI_IOMAP=y
CONFIG_GENERIC_IOMAP=y
CONFIG_GENERIC_IO=y
CONFIG_ARCH_HAS_FAST_MULTIPLIER=y
CONFIG_CRC_CCITT=y
CONFIG_CRC16=y
CONFIG_CRC_T10DIF=y
# CONFIG_CRC_ITU_T is not set
CONFIG_CRC32=y
# CONFIG_CRC32_SELFTEST is not set
CONFIG_CRC32_SLICEBY8=y
# CONFIG_CRC32_SLICEBY4 is not set
# CONFIG_CRC32_SARWATE is not set
# CONFIG_CRC32_BIT is not set
CONFIG_CRC7=m
CONFIG_LIBCRC32C=y
CONFIG_CRC8=m
# CONFIG_AUDIT_ARCH_COMPAT_GENERIC is not set
CONFIG_RANDOM32_SELFTEST=y
CONFIG_842_COMPRESS=m
CONFIG_842_DECOMPRESS=m
CONFIG_ZLIB_INFLATE=y
CONFIG_ZLIB_DEFLATE=y
CONFIG_LZO_COMPRESS=y
CONFIG_LZO_DECOMPRESS=y
CONFIG_LZ4HC_COMPRESS=m
CONFIG_LZ4_DECOMPRESS=m
# CONFIG_XZ_DEC is not set
# CONFIG_XZ_DEC_BCJ is not set
CONFIG_DECOMPRESS_GZIP=y
CONFIG_DECOMPRESS_LZMA=y
CONFIG_GENERIC_ALLOCATOR=y
CONFIG_INTERVAL_TREE=y
CONFIG_RADIX_TREE_MULTIORDER=y
CONFIG_ASSOCIATIVE_ARRAY=y
CONFIG_HAS_IOMEM=y
CONFIG_HAS_IOPORT_MAP=y
CONFIG_HAS_DMA=y
# CONFIG_DMA_NOOP_OPS is not set
# CONFIG_DMA_VIRT_OPS is not set
CONFIG_CHECK_SIGNATURE=y
CONFIG_DQL=y
CONFIG_GLOB=y
CONFIG_GLOB_SELFTEST=y
CONFIG_NLATTR=y
CONFIG_CLZ_TAB=y
# CONFIG_CORDIC is not set
CONFIG_DDR=y
CONFIG_IRQ_POLL=y
CONFIG_MPILIB=y
CONFIG_OID_REGISTRY=y
# CONFIG_SG_SPLIT is not set
CONFIG_SG_POOL=y
CONFIG_ARCH_HAS_SG_CHAIN=y
CONFIG_ARCH_HAS_MMIO_FLUSH=y
CONFIG_STACKDEPOT=y
CONFIG_SBITMAP=y
^ permalink raw reply
* Re: [PATCH v3] blkcg: allocate struct blkcg_gq outside request queue spinlock
From: Tejun Heo @ 2017-03-04 19:23 UTC (permalink / raw)
To: Tahsin Erdogan; +Cc: Jens Axboe, linux-block, David Rientjes, linux-kernel
In-Reply-To: <20170304014005.23773-1-tahsin@google.com>
Hello, Tahsin.
Generally looks good. Please see below.
> @@ -184,24 +185,48 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
> + if (unlikely(!wb_congested)) {
> ret = -ENOMEM;
> goto err_put_css;
> + } else if (unlikely(!blkg)) {
> + ret = -ENOMEM;
> + goto err_put_congested;
> }
I'm not sure this error handling logic is correct. We can have any
combo of alloc failure here, right?
> @@ -694,9 +695,20 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q,
> blkg = blkg_lookup(blkcg, q);
> if (unlikely(!blkg)) {
> spin_lock_irq(q->queue_lock);
> - blkg = blkg_lookup_create(blkcg, q);
> - if (IS_ERR(blkg))
> - blkg = NULL;
> +
> + /*
> + * This could be the first entry point of blkcg implementation
> + * and we shouldn't allow anything to go through for a bypassing
> + * queue.
> + */
> + if (likely(!blk_queue_bypass(q))) {
> + blkg = blkg_lookup_create(blkcg, q,
> + GFP_NOWAIT | __GFP_NOWARN,
> + NULL);
> + if (IS_ERR(blkg))
> + blkg = NULL;
> + }
Heh, this seems a bit too fragile. I get that this covers both call
paths into lookup_create which needs the checking, but it seems a bit
too nasty to do it this way. Would it be ugly if we factor out both
policy enabled and bypass tests into a helper and have inner
__blkg_lookup_create() which skips it? We can call the same helper
from blkg_create() when @pol. Sorry that this is involving so much
bikeshedding.
Thanks!
--
tejun
^ permalink raw reply
* [PATCH RFC 14/14] block, bfq: handle bursts of queue activations
From: Paolo Valente @ 2017-03-04 16:01 UTC (permalink / raw)
To: Jens Axboe, Tejun Heo
Cc: Fabio Checconi, Arianna Avanzini, linux-block, linux-kernel,
ulf.hansson, linus.walleij, broonie, Paolo Valente
In-Reply-To: <20170304160131.57366-1-paolo.valente@linaro.org>
From: Arianna Avanzini <avanzini.arianna@gmail.com>
Many popular I/O-intensive services or applications spawn or
reactivate many parallel threads/processes during short time
intervals. Examples are systemd during boot or git grep. These
services or applications benefit mostly from a high throughput: the
quicker the I/O generated by their processes is cumulatively served,
the sooner the target job of these services or applications gets
completed. As a consequence, it is almost always counterproductive to
weight-raise any of the queues associated to the processes of these
services or applications: in most cases it would just lower the
throughput, mainly because weight-raising also implies device idling.
To address this issue, an I/O scheduler needs, first, to detect which
queues are associated with these services or applications. In this
respect, we have that, from the I/O-scheduler standpoint, these
services or applications cause bursts of activations, i.e.,
activations of different queues occurring shortly after each
other. However, a shorter burst of activations may be caused also by
the start of an application that does not consist in a lot of parallel
I/O-bound threads (see the comments on the function bfq_handle_burst
for details).
In view of these facts, this commit introduces:
1) an heuristic to detect (only) bursts of queue activations caused by
services or applications consisting in many parallel I/O-bound
threads;
2) the prevention of device idling and weight-raising for the queues
belonging to these bursts.
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
block/bfq-iosched.c | 406 +++++++++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 390 insertions(+), 16 deletions(-)
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 10d550b..83fd100 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -341,6 +341,10 @@ struct bfq_queue {
/* bit vector: a 1 for each seeky requests in history */
u32 seek_history;
+
+ /* node for the device's burst list */
+ struct hlist_node burst_list_node;
+
/* position of the last request enqueued */
sector_t last_request_pos;
@@ -424,6 +428,17 @@ struct bfq_io_cq {
bool saved_IO_bound;
/*
+ * Same purpose as the previous fields for the value of the
+ * field keeping the queue's belonging to a large burst
+ */
+ bool saved_in_large_burst;
+ /*
+ * True if the queue belonged to a burst list before its merge
+ * with another cooperating queue.
+ */
+ bool was_in_burst_list;
+
+ /*
* Similar to previous fields: save wr information.
*/
unsigned long saved_wr_coeff;
@@ -585,6 +600,36 @@ struct bfq_data {
*/
bool strict_guarantees;
+ /*
+ * Last time at which a queue entered the current burst of
+ * queues being activated shortly after each other; for more
+ * details about this and the following parameters related to
+ * a burst of activations, see the comments on the function
+ * bfq_handle_burst.
+ */
+ unsigned long last_ins_in_burst;
+ /*
+ * Reference time interval used to decide whether a queue has
+ * been activated shortly after @last_ins_in_burst.
+ */
+ unsigned long bfq_burst_interval;
+ /* number of queues in the current burst of queue activations */
+ int burst_size;
+
+ /* common parent entity for the queues in the burst */
+ struct bfq_entity *burst_parent_entity;
+ /* Maximum burst size above which the current queue-activation
+ * burst is deemed as 'large'.
+ */
+ unsigned long bfq_large_burst_thresh;
+ /* true if a large queue-activation burst is in progress */
+ bool large_burst;
+ /*
+ * Head of the burst list (as for the above fields, more
+ * details in the comments on the function bfq_handle_burst).
+ */
+ struct hlist_head burst_list;
+
/* if set to true, low-latency heuristics are enabled */
bool low_latency;
/*
@@ -647,7 +692,8 @@ struct bfq_data {
};
enum bfqq_state_flags {
- BFQ_BFQQ_FLAG_busy = 0, /* has requests or is in service */
+ BFQ_BFQQ_FLAG_just_created = 0, /* queue just allocated */
+ BFQ_BFQQ_FLAG_busy, /* has requests or is in service */
BFQ_BFQQ_FLAG_wait_request, /* waiting for a request */
BFQ_BFQQ_FLAG_non_blocking_wait_rq, /*
* waiting for a request
@@ -661,6 +707,10 @@ enum bfqq_state_flags {
* having consumed at most 2/10 of
* its budget
*/
+ BFQ_BFQQ_FLAG_in_large_burst, /*
+ * bfqq activated in a large burst,
+ * see comments to bfq_handle_burst.
+ */
BFQ_BFQQ_FLAG_softrt_update, /*
* may need softrt-next-start
* update
@@ -683,6 +733,7 @@ static int bfq_bfqq_##name(const struct bfq_queue *bfqq) \
return ((bfqq)->flags & (1 << BFQ_BFQQ_FLAG_##name)) != 0; \
}
+BFQ_BFQQ_FNS(just_created);
BFQ_BFQQ_FNS(busy);
BFQ_BFQQ_FNS(wait_request);
BFQ_BFQQ_FNS(non_blocking_wait_rq);
@@ -690,6 +741,7 @@ BFQ_BFQQ_FNS(fifo_expire);
BFQ_BFQQ_FNS(idle_window);
BFQ_BFQQ_FNS(sync);
BFQ_BFQQ_FNS(IO_bound);
+BFQ_BFQQ_FNS(in_large_burst);
BFQ_BFQQ_FNS(coop);
BFQ_BFQQ_FNS(split_coop);
BFQ_BFQQ_FNS(softrt_update);
@@ -4233,9 +4285,9 @@ bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
bfqq->last_wr_start_finish = bic->saved_last_wr_start_finish;
bfqq->wr_cur_max_time = bic->saved_wr_cur_max_time;
- if (bfqq->wr_coeff > 1 &&
+ if (bfqq->wr_coeff > 1 && (bfq_bfqq_in_large_burst(bfqq) ||
time_is_before_jiffies(bfqq->last_wr_start_finish +
- bfqq->wr_cur_max_time)) {
+ bfqq->wr_cur_max_time))) {
bfq_log_bfqq(bfqq->bfqd, bfqq,
"resume state: switching off wr");
@@ -4251,6 +4303,232 @@ static int bfqq_process_refs(struct bfq_queue *bfqq)
return bfqq->ref - bfqq->allocated - bfqq->entity.on_st;
}
+/* Empty burst list and add just bfqq (see comments on bfq_handle_burst) */
+static void bfq_reset_burst_list(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+ struct bfq_queue *item;
+ struct hlist_node *n;
+
+ hlist_for_each_entry_safe(item, n, &bfqd->burst_list, burst_list_node)
+ hlist_del_init(&item->burst_list_node);
+ hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list);
+ bfqd->burst_size = 1;
+ bfqd->burst_parent_entity = bfqq->entity.parent;
+}
+
+/* Add bfqq to the list of queues in current burst (see bfq_handle_burst) */
+static void bfq_add_to_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+ /* Increment burst size to take into account also bfqq */
+ bfqd->burst_size++;
+
+ if (bfqd->burst_size == bfqd->bfq_large_burst_thresh) {
+ struct bfq_queue *pos, *bfqq_item;
+ struct hlist_node *n;
+
+ /*
+ * Enough queues have been activated shortly after each
+ * other to consider this burst as large.
+ */
+ bfqd->large_burst = true;
+
+ /*
+ * We can now mark all queues in the burst list as
+ * belonging to a large burst.
+ */
+ hlist_for_each_entry(bfqq_item, &bfqd->burst_list,
+ burst_list_node)
+ bfq_mark_bfqq_in_large_burst(bfqq_item);
+ bfq_mark_bfqq_in_large_burst(bfqq);
+
+ /*
+ * From now on, and until the current burst finishes, any
+ * new queue being activated shortly after the last queue
+ * was inserted in the burst can be immediately marked as
+ * belonging to a large burst. So the burst list is not
+ * needed any more. Remove it.
+ */
+ hlist_for_each_entry_safe(pos, n, &bfqd->burst_list,
+ burst_list_node)
+ hlist_del_init(&pos->burst_list_node);
+ } else /*
+ * Burst not yet large: add bfqq to the burst list. Do
+ * not increment the ref counter for bfqq, because bfqq
+ * is removed from the burst list before freeing bfqq
+ * in put_queue.
+ */
+ hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list);
+}
+
+/*
+ * If many queues belonging to the same group happen to be created
+ * shortly after each other, then the processes associated with these
+ * queues have typically a common goal. In particular, bursts of queue
+ * creations are usually caused by services or applications that spawn
+ * many parallel threads/processes. Examples are systemd during boot,
+ * or git grep. To help these processes get their job done as soon as
+ * possible, it is usually better to not grant either weight-raising
+ * or device idling to their queues.
+ *
+ * In this comment we describe, firstly, the reasons why this fact
+ * holds, and, secondly, the next function, which implements the main
+ * steps needed to properly mark these queues so that they can then be
+ * treated in a different way.
+ *
+ * The above services or applications benefit mostly from a high
+ * throughput: the quicker the requests of the activated queues are
+ * cumulatively served, the sooner the target job of these queues gets
+ * completed. As a consequence, weight-raising any of these queues,
+ * which also implies idling the device for it, is almost always
+ * counterproductive. In most cases it just lowers throughput.
+ *
+ * On the other hand, a burst of queue creations may be caused also by
+ * the start of an application that does not consist of a lot of
+ * parallel I/O-bound threads. In fact, with a complex application,
+ * several short processes may need to be executed to start-up the
+ * application. In this respect, to start an application as quickly as
+ * possible, the best thing to do is in any case to privilege the I/O
+ * related to the application with respect to all other
+ * I/O. Therefore, the best strategy to start as quickly as possible
+ * an application that causes a burst of queue creations is to
+ * weight-raise all the queues created during the burst. This is the
+ * exact opposite of the best strategy for the other type of bursts.
+ *
+ * In the end, to take the best action for each of the two cases, the
+ * two types of bursts need to be distinguished. Fortunately, this
+ * seems relatively easy, by looking at the sizes of the bursts. In
+ * particular, we found a threshold such that only bursts with a
+ * larger size than that threshold are apparently caused by
+ * services or commands such as systemd or git grep. For brevity,
+ * hereafter we call just 'large' these bursts. BFQ *does not*
+ * weight-raise queues whose creation occurs in a large burst. In
+ * addition, for each of these queues BFQ performs or does not perform
+ * idling depending on which choice boosts the throughput more. The
+ * exact choice depends on the device and request pattern at
+ * hand.
+ *
+ * Unfortunately, false positives may occur while an interactive task
+ * is starting (e.g., an application is being started). The
+ * consequence is that the queues associated with the task do not
+ * enjoy weight raising as expected. Fortunately these false positives
+ * are very rare. They typically occur if some service happens to
+ * start doing I/O exactly when the interactive task starts.
+ *
+ * Turning back to the next function, it implements all the steps
+ * needed to detect the occurrence of a large burst and to properly
+ * mark all the queues belonging to it (so that they can then be
+ * treated in a different way). This goal is achieved by maintaining a
+ * "burst list" that holds, temporarily, the queues that belong to the
+ * burst in progress. The list is then used to mark these queues as
+ * belonging to a large burst if the burst does become large. The main
+ * steps are the following.
+ *
+ * . when the very first queue is created, the queue is inserted into the
+ * list (as it could be the first queue in a possible burst)
+ *
+ * . if the current burst has not yet become large, and a queue Q that does
+ * not yet belong to the burst is activated shortly after the last time
+ * at which a new queue entered the burst list, then the function appends
+ * Q to the burst list
+ *
+ * . if, as a consequence of the previous step, the burst size reaches
+ * the large-burst threshold, then
+ *
+ * . all the queues in the burst list are marked as belonging to a
+ * large burst
+ *
+ * . the burst list is deleted; in fact, the burst list already served
+ * its purpose (keeping temporarily track of the queues in a burst,
+ * so as to be able to mark them as belonging to a large burst in the
+ * previous sub-step), and now is not needed any more
+ *
+ * . the device enters a large-burst mode
+ *
+ * . if a queue Q that does not belong to the burst is created while
+ * the device is in large-burst mode and shortly after the last time
+ * at which a queue either entered the burst list or was marked as
+ * belonging to the current large burst, then Q is immediately marked
+ * as belonging to a large burst.
+ *
+ * . if a queue Q that does not belong to the burst is created a while
+ * later, i.e., not shortly after, than the last time at which a queue
+ * either entered the burst list or was marked as belonging to the
+ * current large burst, then the current burst is deemed as finished and:
+ *
+ * . the large-burst mode is reset if set
+ *
+ * . the burst list is emptied
+ *
+ * . Q is inserted in the burst list, as Q may be the first queue
+ * in a possible new burst (then the burst list contains just Q
+ * after this step).
+ */
+static void bfq_handle_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+ /*
+ * If bfqq is already in the burst list or is part of a large
+ * burst, or finally has just been split, then there is
+ * nothing else to do.
+ */
+ if (!hlist_unhashed(&bfqq->burst_list_node) ||
+ bfq_bfqq_in_large_burst(bfqq) ||
+ time_is_after_eq_jiffies(bfqq->split_time +
+ msecs_to_jiffies(10)))
+ return;
+
+ /*
+ * If bfqq's creation happens late enough, or bfqq belongs to
+ * a different group than the burst group, then the current
+ * burst is finished, and related data structures must be
+ * reset.
+ *
+ * In this respect, consider the special case where bfqq is
+ * the very first queue created after BFQ is selected for this
+ * device. In this case, last_ins_in_burst and
+ * burst_parent_entity are not yet significant when we get
+ * here. But it is easy to verify that, whether or not the
+ * following condition is true, bfqq will end up being
+ * inserted into the burst list. In particular the list will
+ * happen to contain only bfqq. And this is exactly what has
+ * to happen, as bfqq may be the first queue of the first
+ * burst.
+ */
+ if (time_is_before_jiffies(bfqd->last_ins_in_burst +
+ bfqd->bfq_burst_interval) ||
+ bfqq->entity.parent != bfqd->burst_parent_entity) {
+ bfqd->large_burst = false;
+ bfq_reset_burst_list(bfqd, bfqq);
+ goto end;
+ }
+
+ /*
+ * If we get here, then bfqq is being activated shortly after the
+ * last queue. So, if the current burst is also large, we can mark
+ * bfqq as belonging to this large burst immediately.
+ */
+ if (bfqd->large_burst) {
+ bfq_mark_bfqq_in_large_burst(bfqq);
+ goto end;
+ }
+
+ /*
+ * If we get here, then a large-burst state has not yet been
+ * reached, but bfqq is being activated shortly after the last
+ * queue. Then we add bfqq to the burst.
+ */
+ bfq_add_to_burst(bfqd, bfqq);
+end:
+ /*
+ * At this point, bfqq either has been added to the current
+ * burst or has caused the current burst to terminate and a
+ * possible new burst to start. In particular, in the second
+ * case, bfqq has become the first queue in the possible new
+ * burst. In both cases last_ins_in_burst needs to be moved
+ * forward.
+ */
+ bfqd->last_ins_in_burst = jiffies;
+}
+
static int bfq_bfqq_budget_left(struct bfq_queue *bfqq)
{
struct bfq_entity *entity = &bfqq->entity;
@@ -4464,6 +4742,7 @@ static void bfq_update_bfqq_wr_on_rq_arrival(struct bfq_data *bfqd,
unsigned int old_wr_coeff,
bool wr_or_deserves_wr,
bool interactive,
+ bool in_burst,
bool soft_rt)
{
if (old_wr_coeff == 1 && wr_or_deserves_wr) {
@@ -4495,7 +4774,9 @@ static void bfq_update_bfqq_wr_on_rq_arrival(struct bfq_data *bfqd,
if (interactive) { /* update wr coeff and duration */
bfqq->wr_coeff = bfqd->bfq_wr_coeff;
bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
- } else if (soft_rt) {
+ } else if (in_burst)
+ bfqq->wr_coeff = 1;
+ else if (soft_rt) {
/*
* The application is now or still meeting the
* requirements for being deemed soft rt. We
@@ -4555,7 +4836,8 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
struct request *rq,
bool *interactive)
{
- bool soft_rt, wr_or_deserves_wr, bfqq_wants_to_preempt,
+ bool soft_rt, in_burst, wr_or_deserves_wr,
+ bfqq_wants_to_preempt,
idle_for_long_time = bfq_bfqq_idle_for_long_time(bfqd, bfqq),
/*
* See the comments on
@@ -4571,12 +4853,15 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
/*
* bfqq deserves to be weight-raised if:
* - it is sync,
+ * - it does not belong to a large burst,
* - it has been idle for enough time or is soft real-time,
* - is linked to a bfq_io_cq (it is not shared in any sense).
*/
+ in_burst = bfq_bfqq_in_large_burst(bfqq);
soft_rt = bfqd->bfq_wr_max_softrt_rate > 0 &&
+ !in_burst &&
time_is_before_jiffies(bfqq->soft_rt_next_start);
- *interactive = idle_for_long_time;
+ *interactive = !in_burst && idle_for_long_time;
wr_or_deserves_wr = bfqd->low_latency &&
(bfqq->wr_coeff > 1 ||
(bfq_bfqq_sync(bfqq) &&
@@ -4591,6 +4876,31 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
arrived_in_time,
wr_or_deserves_wr);
+ /*
+ * If bfqq happened to be activated in a burst, but has been
+ * idle for much more than an interactive queue, then we
+ * assume that, in the overall I/O initiated in the burst, the
+ * I/O associated with bfqq is finished. So bfqq does not need
+ * to be treated as a queue belonging to a burst
+ * anymore. Accordingly, we reset bfqq's in_large_burst flag
+ * if set, and remove bfqq from the burst list if it's
+ * there. We do not decrement burst_size, because the fact
+ * that bfqq does not need to belong to the burst list any
+ * more does not invalidate the fact that bfqq was created in
+ * a burst.
+ */
+ if (likely(!bfq_bfqq_just_created(bfqq)) &&
+ idle_for_long_time &&
+ time_is_before_jiffies(
+ bfqq->budget_timeout +
+ msecs_to_jiffies(10000))) {
+ hlist_del_init(&bfqq->burst_list_node);
+ bfq_clear_bfqq_in_large_burst(bfqq);
+ }
+
+ bfq_clear_bfqq_just_created(bfqq);
+
+
if (!bfq_bfqq_IO_bound(bfqq)) {
if (arrived_in_time) {
bfqq->requests_within_timer++;
@@ -4613,6 +4923,7 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
old_wr_coeff,
wr_or_deserves_wr,
*interactive,
+ in_burst,
soft_rt);
if (old_wr_coeff != bfqq->wr_coeff)
@@ -5248,6 +5559,8 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
bic->saved_ttime = bfqq->ttime;
bic->saved_idle_window = bfq_bfqq_idle_window(bfqq);
bic->saved_IO_bound = bfq_bfqq_IO_bound(bfqq);
+ bic->saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq);
+ bic->was_in_burst_list = !hlist_unhashed(&bfqq->burst_list_node);
bic->saved_wr_coeff = bfqq->wr_coeff;
bic->saved_wr_start_at_switch_to_srt = bfqq->wr_start_at_switch_to_srt;
bic->saved_last_wr_start_finish = bfqq->last_wr_start_finish;
@@ -5283,7 +5596,8 @@ bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
* where bfqq has just been created, but has not yet made it
* to be weight-raised (which may happen because EQM may merge
* bfqq even before bfq_add_request is executed for the first
- * time for bfqq).
+ * time for bfqq). Handling this case would however be very
+ * easy, thanks to the flag just_created.
*/
if (new_bfqq->wr_coeff == 1 && bfqq->wr_coeff > 1) {
new_bfqq->wr_coeff = bfqq->wr_coeff;
@@ -6363,6 +6677,7 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
{
struct bfq_data *bfqd = bfqq->bfqd;
bool idling_boosts_thr, idling_boosts_thr_without_issues,
+ idling_needed_for_service_guarantees,
asymmetric_scenario;
if (bfqd->strict_guarantees)
@@ -6543,6 +6858,23 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
!bfq_symmetric_scenario(bfqd);
/*
+ * Finally, there is a case where maximizing throughput is the
+ * best choice even if it may cause unfairness toward
+ * bfqq. Such a case is when bfqq became active in a burst of
+ * queue activations. Queues that became active during a large
+ * burst benefit only from throughput, as discussed in the
+ * comments on bfq_handle_burst. Thus, if bfqq became active
+ * in a burst and not idling the device maximizes throughput,
+ * then the device must no be idled, because not idling the
+ * device provides bfqq and all other queues in the burst with
+ * maximum benefit. Combining this and the above case, we can
+ * now establish when idling is actually needed to preserve
+ * service guarantees.
+ */
+ idling_needed_for_service_guarantees =
+ asymmetric_scenario && !bfq_bfqq_in_large_burst(bfqq);
+
+ /*
* We have now all the components we need to compute the return
* value of the function, which is true only if both the following
* conditions hold:
@@ -6551,7 +6883,8 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
* is necessary to preserve service guarantees.
*/
return bfq_bfqq_sync(bfqq) &&
- (idling_boosts_thr_without_issues || asymmetric_scenario);
+ (idling_boosts_thr_without_issues ||
+ idling_needed_for_service_guarantees);
}
/*
@@ -6690,14 +7023,17 @@ static void bfq_update_wr_data(struct bfq_data *bfqd, struct bfq_queue *bfqq)
bfq_log_bfqq(bfqd, bfqq, "WARN: pending prio change");
/*
- * If too much time has elapsed from the beginning of
- * this weight-raising period, then end weight raising.
+ * If the queue was activated in a burst, or too much
+ * time has elapsed from the beginning of this
+ * weight-raising period, then end weight raising.
*/
- if (time_is_before_jiffies(bfqq->last_wr_start_finish +
- bfqq->wr_cur_max_time)) {
+ if (bfq_bfqq_in_large_burst(bfqq))
+ bfq_bfqq_end_wr(bfqq);
+ else if (time_is_before_jiffies(bfqq->last_wr_start_finish +
+ bfqq->wr_cur_max_time)) {
if (bfqq->wr_cur_max_time != bfqd->bfq_wr_rt_max_time ||
time_is_before_jiffies(bfqq->wr_start_at_switch_to_srt +
- bfq_wr_duration(bfqd)))
+ bfq_wr_duration(bfqd)))
bfq_bfqq_end_wr(bfqq);
else {
/* switch back to interactive wr */
@@ -6894,7 +7230,16 @@ static void bfq_put_queue(struct bfq_queue *bfqq)
if (bfqq->ref)
return;
- bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p freed", bfqq);
+ if (bfq_bfqq_sync(bfqq))
+ /*
+ * The fact that this queue is being destroyed does not
+ * invalidate the fact that this queue may have been
+ * activated during the current burst. As a consequence,
+ * although the queue does not exist anymore, and hence
+ * needs to be removed from the burst list if there,
+ * the burst size has not to be decremented.
+ */
+ hlist_del_init(&bfqq->burst_list_node);
kmem_cache_free(bfq_pool, bfqq);
#ifdef CONFIG_BFQ_GROUP_IOSCHED
@@ -7055,6 +7400,7 @@ static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
{
RB_CLEAR_NODE(&bfqq->entity.rb_node);
INIT_LIST_HEAD(&bfqq->fifo);
+ INIT_HLIST_NODE(&bfqq->burst_list_node);
bfqq->ref = 0;
bfqq->bfqd = bfqd;
@@ -7066,6 +7412,7 @@ static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
if (!bfq_class_idle(bfqq))
bfq_mark_bfqq_idle_window(bfqq);
bfq_mark_bfqq_sync(bfqq);
+ bfq_mark_bfqq_just_created(bfqq);
} else
bfq_clear_bfqq_sync(bfqq);
@@ -7336,6 +7683,7 @@ static void __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
new_bfqq->allocated++;
bfqq->allocated--;
new_bfqq->ref++;
+ bfq_clear_bfqq_just_created(bfqq);
bfq_put_queue(bfqq);
/*
* If the bic associated with the process
@@ -7613,8 +7961,18 @@ static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd,
bfqq = bfq_get_queue(bfqd, bio, is_sync, bic);
bic_set_bfqq(bic, bfqq, is_sync);
- if (split && is_sync)
+ if (split && is_sync) {
+ if ((bic->was_in_burst_list && bfqd->large_burst) ||
+ bic->saved_in_large_burst)
+ bfq_mark_bfqq_in_large_burst(bfqq);
+ else {
+ bfq_clear_bfqq_in_large_burst(bfqq);
+ if (bic->was_in_burst_list)
+ hlist_add_head(&bfqq->burst_list_node,
+ &bfqd->burst_list);
+ }
bfqq->split_time = jiffies;
+ }
return bfqq;
}
@@ -7647,6 +8005,11 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
/* 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");
+
+ /* Update bic before losing reference to bfqq */
+ if (bfq_bfqq_in_large_burst(bfqq))
+ bic->saved_in_large_burst = true;
+
bfqq = bfq_split_bfqq(bic, bfqq);
/*
* A reference to bic->icq.ioc needs to be
@@ -7690,6 +8053,9 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
}
}
+ if (unlikely(bfq_bfqq_just_created(bfqq)))
+ bfq_handle_burst(bfqd, bfqq);
+
bfq_unlock_put_ioc(bfqd);
return 0;
@@ -7869,6 +8235,10 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
bfqd->oom_bfqq.new_ioprio_class = IOPRIO_CLASS_BE;
bfqd->oom_bfqq.entity.new_weight =
bfq_ioprio_to_weight(bfqd->oom_bfqq.new_ioprio);
+
+ /* oom_bfqq does not participate to bursts */
+ bfq_clear_bfqq_just_created(&bfqd->oom_bfqq);
+
/*
* Trigger weight initialization, according to ioprio, at the
* oom_bfqq's first activation. The oom_bfqq's ioprio and ioprio
@@ -7889,6 +8259,7 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
INIT_LIST_HEAD(&bfqd->active_list);
INIT_LIST_HEAD(&bfqd->idle_list);
+ INIT_HLIST_HEAD(&bfqd->burst_list);
bfqd->hw_tag = -1;
@@ -7903,6 +8274,9 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
bfqd->bfq_requests_within_timer = 120;
+ bfqd->bfq_large_burst_thresh = 8;
+ bfqd->bfq_burst_interval = msecs_to_jiffies(180);
+
bfqd->low_latency = true;
/*
@@ -8297,7 +8671,7 @@ static struct blkcg_policy blkcg_policy_bfq = {
static int __init bfq_init(void)
{
int ret;
- char msg[50] = "BFQ I/O-scheduler: v7r3";
+ char msg[60] = "BFQ I/O-scheduler: v8r8";
#ifdef CONFIG_BFQ_GROUP_IOSCHED
ret = blkcg_policy_register(&blkcg_policy_bfq);
--
2.10.0
^ permalink raw reply related
* [PATCH RFC 13/14] block, bfq: boost the throughput with random I/O on NCQ-capable HDDs
From: Paolo Valente @ 2017-03-04 16:01 UTC (permalink / raw)
To: Jens Axboe, Tejun Heo
Cc: Fabio Checconi, Arianna Avanzini, linux-block, linux-kernel,
ulf.hansson, linus.walleij, broonie, Paolo Valente
In-Reply-To: <20170304160131.57366-1-paolo.valente@linaro.org>
This patch is basically the counterpart, for NCQ-capable rotational
devices, of the previous patch. Exactly as the previous patch does on
flash-based devices and for any workload, this patch disables device
idling on rotational devices, but only for random I/O. In fact, only
with these queues disabling idling boosts the throughput on
NCQ-capable rotational devices. To not break service guarantees,
idling is disabled for NCQ-enabled rotational devices only when the
same symmetry conditions considered in the previous patches hold.
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
---
block/bfq-iosched.c | 18 +++++++-----------
1 file changed, 7 insertions(+), 11 deletions(-)
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index e509237..10d550b 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -6372,20 +6372,15 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
* The next variable takes into account the cases where idling
* boosts the throughput.
*
- * The value of the variable is computed considering that
- * idling is usually beneficial for the throughput if:
+ * The value of the variable is computed considering, first, that
+ * idling is virtually always beneficial for the throughput if:
* (a) the device is not NCQ-capable, or
* (b) regardless of the presence of NCQ, the device is rotational
- * and the request pattern for bfqq is I/O-bound (possible
- * throughput losses caused by granting idling to seeky queues
- * are mitigated by the fact that, in all scenarios where
- * boosting throughput is the best thing to do, i.e., in all
- * symmetric scenarios, only a minimal idle time is allowed to
- * seeky queues).
+ * and the request pattern for bfqq is I/O-bound and sequential.
*
* Secondly, and in contrast to the above item (b), idling an
* NCQ-capable flash-based device would not boost the
- * throughput even with intense I/O; rather it would lower
+ * throughput even with sequential I/O; rather it would lower
* the throughput in proportion to how fast the device
* is. Accordingly, the next variable is true if any of the
* above conditions (a) and (b) is true, and, in particular,
@@ -6393,7 +6388,8 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
* device.
*/
idling_boosts_thr = !bfqd->hw_tag ||
- (!blk_queue_nonrot(bfqd->queue) && bfq_bfqq_IO_bound(bfqq));
+ (!blk_queue_nonrot(bfqd->queue) && bfq_bfqq_IO_bound(bfqq) &&
+ bfq_bfqq_idle_window(bfqq));
/*
* The value of the next variable,
@@ -8301,7 +8297,7 @@ static struct blkcg_policy blkcg_policy_bfq = {
static int __init bfq_init(void)
{
int ret;
- char msg[50] = "BFQ I/O-scheduler: v6";
+ char msg[50] = "BFQ I/O-scheduler: v7r3";
#ifdef CONFIG_BFQ_GROUP_IOSCHED
ret = blkcg_policy_register(&blkcg_policy_bfq);
--
2.10.0
^ permalink raw reply related
* [PATCH RFC 12/14] block, bfq: boost the throughput on NCQ-capable flash-based devices
From: Paolo Valente @ 2017-03-04 16:01 UTC (permalink / raw)
To: Jens Axboe, Tejun Heo
Cc: Fabio Checconi, Arianna Avanzini, linux-block, linux-kernel,
ulf.hansson, linus.walleij, broonie, Paolo Valente
In-Reply-To: <20170304160131.57366-1-paolo.valente@linaro.org>
This patch boosts the throughput on NCQ-capable flash-based devices,
while still preserving latency guarantees for interactive and soft
real-time applications. The throughput is boosted by just not idling
the device when the in-service queue remains empty, even if the queue
is sync and has a non-null idle window. This helps to keep the drive's
internal queue full, which is necessary to achieve maximum
performance. This solution to boost the throughput is a port of
commits a68bbdd and f7d7b7a for CFQ.
As already highlighted in a previous patch, allowing the device to
prefetch and internally reorder requests trivially causes loss of
control on the request service order, and hence on service guarantees.
Fortunately, as discussed in detail in the comments on the function
bfq_bfqq_may_idle(), if every process has to receive the same
fraction of the throughput, then the service order enforced by the
internal scheduler of a flash-based device is relatively close to that
enforced by BFQ. In particular, it is close enough to let service
guarantees be substantially preserved.
Things change in an asymmetric scenario, i.e., if not every process
has to receive the same fraction of the throughput. In this case, to
guarantee the desired throughput distribution, the device must be
prevented from prefetching requests. This is exactly what this patch
does in asymmetric scenarios.
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
---
block/bfq-iosched.c | 154 ++++++++++++++++++++++++++++++++++++----------------
1 file changed, 106 insertions(+), 48 deletions(-)
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 6bda6ea..e509237 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -6375,15 +6375,25 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
* The value of the variable is computed considering that
* idling is usually beneficial for the throughput if:
* (a) the device is not NCQ-capable, or
- * (b) regardless of the presence of NCQ, the request pattern
- * for bfqq is I/O-bound (possible throughput losses
- * caused by granting idling to seeky queues are mitigated
- * by the fact that, in all scenarios where boosting
- * throughput is the best thing to do, i.e., in all
- * symmetric scenarios, only a minimal idle time is
- * allowed to seeky queues).
+ * (b) regardless of the presence of NCQ, the device is rotational
+ * and the request pattern for bfqq is I/O-bound (possible
+ * throughput losses caused by granting idling to seeky queues
+ * are mitigated by the fact that, in all scenarios where
+ * boosting throughput is the best thing to do, i.e., in all
+ * symmetric scenarios, only a minimal idle time is allowed to
+ * seeky queues).
+ *
+ * Secondly, and in contrast to the above item (b), idling an
+ * NCQ-capable flash-based device would not boost the
+ * throughput even with intense I/O; rather it would lower
+ * the throughput in proportion to how fast the device
+ * is. Accordingly, the next variable is true if any of the
+ * above conditions (a) and (b) is true, and, in particular,
+ * happens to be false if bfqd is an NCQ-capable flash-based
+ * device.
*/
- idling_boosts_thr = !bfqd->hw_tag || bfq_bfqq_IO_bound(bfqq);
+ idling_boosts_thr = !bfqd->hw_tag ||
+ (!blk_queue_nonrot(bfqd->queue) && bfq_bfqq_IO_bound(bfqq));
/*
* The value of the next variable,
@@ -6424,14 +6434,16 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
bfqd->wr_busy_queues == 0;
/*
- * There is then a case where idling must be performed not for
- * throughput concerns, but to preserve service guarantees. To
- * introduce it, we can note that allowing the drive to
- * enqueue more than one request at a time, and hence
+ * There is then a case where idling must be performed not
+ * for throughput concerns, but to preserve service
+ * guarantees.
+ *
+ * To introduce this case, we can note that allowing the drive
+ * to enqueue more than one request at a time, and hence
* delegating de facto final scheduling decisions to the
- * drive's internal scheduler, causes loss of control on the
+ * drive's internal scheduler, entails loss of control on the
* actual request service order. In particular, the critical
- * situation is when requests from different processes happens
+ * situation is when requests from different processes happen
* to be present, at the same time, in the internal queue(s)
* of the drive. In such a situation, the drive, by deciding
* the service order of the internally-queued requests, does
@@ -6442,51 +6454,97 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
* the service distribution enforced by the drive's internal
* scheduler is likely to coincide with the desired
* device-throughput distribution only in a completely
- * symmetric scenario where: (i) each of these processes must
- * get the same throughput as the others; (ii) all these
- * processes have the same I/O pattern (either sequential or
- * random). In fact, in such a scenario, the drive will tend
- * to treat the requests of each of these processes in about
- * the same way as the requests of the others, and thus to
- * provide each of these processes with about the same
- * throughput (which is exactly the desired throughput
- * distribution). In contrast, in any asymmetric scenario,
- * device idling is certainly needed to guarantee that bfqq
- * receives its assigned fraction of the device throughput
- * (see [1] for details).
+ * symmetric scenario where:
+ * (i) each of these processes must get the same throughput as
+ * the others;
+ * (ii) all these processes have the same I/O pattern
+ (either sequential or random).
+ * In fact, in such a scenario, the drive will tend to treat
+ * the requests of each of these processes in about the same
+ * way as the requests of the others, and thus to provide
+ * each of these processes with about the same throughput
+ * (which is exactly the desired throughput distribution). In
+ * contrast, in any asymmetric scenario, device idling is
+ * certainly needed to guarantee that bfqq receives its
+ * assigned fraction of the device throughput (see [1] for
+ * details).
+ *
+ * We address this issue by controlling, actually, only the
+ * symmetry sub-condition (i), i.e., provided that
+ * sub-condition (i) holds, idling is not performed,
+ * regardless of whether sub-condition (ii) holds. In other
+ * words, only if sub-condition (i) holds, then idling is
+ * allowed, and the device tends to be prevented from queueing
+ * many requests, possibly of several processes. The reason
+ * for not controlling also sub-condition (ii) is that we
+ * exploit preemption to preserve guarantees in case of
+ * symmetric scenarios, even if (ii) does not hold, as
+ * explained in the next two paragraphs.
+ *
+ * Even if a queue, say Q, is expired when it remains idle, Q
+ * can still preempt the new in-service queue if the next
+ * request of Q arrives soon (see the comments on
+ * bfq_bfqq_update_budg_for_activation). If all queues and
+ * groups have the same weight, this form of preemption,
+ * combined with the hole-recovery heuristic described in the
+ * comments on function bfq_bfqq_update_budg_for_activation,
+ * are enough to preserve a correct bandwidth distribution in
+ * the mid term, even without idling. In fact, even if not
+ * idling allows the internal queues of the device to contain
+ * many requests, and thus to reorder requests, we can rather
+ * safely assume that the internal scheduler still preserves a
+ * minimum of mid-term fairness. The motivation for using
+ * preemption instead of idling is that, by not idling,
+ * service guarantees are preserved without minimally
+ * sacrificing throughput. In other words, both a high
+ * throughput and its desired distribution are obtained.
+ *
+ * More precisely, this preemption-based, idleless approach
+ * provides fairness in terms of IOPS, and not sectors per
+ * second. This can be seen with a simple example. Suppose
+ * that there are two queues with the same weight, but that
+ * the first queue receives requests of 8 sectors, while the
+ * second queue receives requests of 1024 sectors. In
+ * addition, suppose that each of the two queues contains at
+ * most one request at a time, which implies that each queue
+ * always remains idle after it is served. Finally, after
+ * remaining idle, each queue receives very quickly a new
+ * request. It follows that the two queues are served
+ * alternatively, preempting each other if needed. This
+ * implies that, although both queues have the same weight,
+ * the queue with large requests receives a service that is
+ * 1024/8 times as high as the service received by the other
+ * queue.
*
- * As for sub-condition (i), actually we check only whether
- * bfqq is being weight-raised. In fact, if bfqq is not being
- * weight-raised, we have that:
- * - if the process associated with bfqq is not I/O-bound, then
- * it is not either latency- or throughput-critical; therefore
- * idling is not needed for bfqq;
- * - if the process asociated with bfqq is I/O-bound, then
- * idling is already granted with bfqq (see the comments on
- * idling_boosts_thr).
+ * On the other hand, device idling is performed, and thus
+ * pure sector-domain guarantees are provided, for the
+ * following queues, which are likely to need stronger
+ * throughput guarantees: weight-raised queues, and queues
+ * with a higher weight than other queues. When such queues
+ * are active, sub-condition (i) is false, which triggers
+ * device idling.
*
- * We do not check sub-condition (ii) at all, i.e., the next
- * variable is true if and only if bfqq is being
- * weight-raised. We do not need to control sub-condition (ii)
- * for the following reason:
- * - if bfqq is being weight-raised, then idling is already
- * guaranteed to bfqq by sub-condition (i);
- * - if bfqq is not being weight-raised, then idling is
- * already guaranteed to bfqq (only) if it matters, i.e., if
- * bfqq is associated to a currently I/O-bound process (see
- * the above comment on sub-condition (i)).
+ * According to the above considerations, the next variable is
+ * true (only) if sub-condition (i) holds. To compute the
+ * value of this variable, we not only use the return value of
+ * the function bfq_symmetric_scenario(), but also check
+ * whether bfqq is being weight-raised, because
+ * bfq_symmetric_scenario() does not take into account also
+ * weight-raised queues (see comments on
+ * bfq_weights_tree_add()).
*
* As a side note, it is worth considering that the above
* device-idling countermeasures may however fail in the
* following unlucky scenario: if idling is (correctly)
- * disabled in a time period during which the symmetry
- * sub-condition holds, and hence the device is allowed to
+ * disabled in a time period during which all symmetry
+ * sub-conditions hold, and hence the device is allowed to
* enqueue many requests, but at some later point in time some
* sub-condition stops to hold, then it may become impossible
* to let requests be served in the desired order until all
* the requests already queued in the device have been served.
*/
- asymmetric_scenario = bfqq->wr_coeff > 1;
+ asymmetric_scenario = bfqq->wr_coeff > 1 ||
+ !bfq_symmetric_scenario(bfqd);
/*
* We have now all the components we need to compute the return
--
2.10.0
^ permalink raw reply related
* [PATCH RFC 11/14] block, bfq: reduce idling only in symmetric scenarios
From: Paolo Valente @ 2017-03-04 16:01 UTC (permalink / raw)
To: Jens Axboe, Tejun Heo
Cc: Fabio Checconi, Arianna Avanzini, linux-block, linux-kernel,
ulf.hansson, linus.walleij, broonie, Riccardo Pizzetti,
Samuele Zecchini, Paolo Valente
In-Reply-To: <20170304160131.57366-1-paolo.valente@linaro.org>
From: Arianna Avanzini <avanzini.arianna@gmail.com>
A seeky queue (i..e, a queue containing random requests) is assigned a
very small device-idling slice, for throughput issues. Unfortunately,
given the process associated with a seeky queue, this behavior causes
the following problem: if the process, say P, performs sync I/O and
has a higher weight than some other processes doing I/O and associated
with non-seeky queues, then BFQ may fail to guarantee to P its
reserved share of the throughput. The reason is that idling is key
for providing service guarantees to processes doing sync I/O [1].
This commit addresses this issue by allowing the device-idling slice
to be reduced for a seeky queue only if the scenario happens to be
symmetric, i.e., if all the queues are to receive the same share of
the throughput.
[1] P. Valente, A. Avanzini, "Evolution of the BFQ Storage I/O
Scheduler", Proceedings of the First Workshop on Mobile System
Technologies (MST-2015), May 2015.
http://algogroup.unimore.it/people/paolo/disk_sched/mst-2015.pdf
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Riccardo Pizzetti <riccardo.pizzetti@gmail.com>
Signed-off-by: Samuele Zecchini <samuele.zecchini92@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
block/bfq-iosched.c | 269 ++++++++++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 263 insertions(+), 6 deletions(-)
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 05b9421..6bda6ea 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -171,6 +171,20 @@ struct bfq_sched_data {
};
/**
+ * struct bfq_weight_counter - counter of the number of all active entities
+ * with a given weight.
+ */
+struct bfq_weight_counter {
+ unsigned int weight; /* weight of the entities this counter refers to */
+ unsigned int num_active; /* nr of active entities with this weight */
+ /*
+ * Weights tree member (see bfq_data's @queue_weights_tree and
+ * @group_weights_tree)
+ */
+ struct rb_node weights_node;
+};
+
+/**
* struct bfq_entity - schedulable entity.
*
* A bfq_entity is used to represent either a bfq_queue (leaf node in the
@@ -199,6 +213,8 @@ struct bfq_sched_data {
*/
struct bfq_entity {
struct rb_node rb_node; /* service_tree member */
+ /* pointer to the weight counter associated with this entity */
+ struct bfq_weight_counter *weight_counter;
/*
* Flag, true if the entity is on a tree (either the active or
@@ -437,6 +453,25 @@ struct bfq_data {
struct bfq_group *root_group;
/*
+ * rbtree of weight counters of @bfq_queues, sorted by
+ * weight. Used to keep track of whether all @bfq_queues have
+ * the same weight. The tree contains one counter for each
+ * distinct weight associated to some active and not
+ * weight-raised @bfq_queue (see the comments to the functions
+ * bfq_weights_tree_[add|remove] for further details).
+ */
+ struct rb_root queue_weights_tree;
+ /*
+ * rbtree of non-queue @bfq_entity weight counters, sorted by
+ * weight. Used to keep track of whether all @bfq_groups have
+ * the same weight. The tree contains one counter for each
+ * distinct weight associated to some active @bfq_group (see
+ * the comments to the functions bfq_weights_tree_[add|remove]
+ * for further details).
+ */
+ struct rb_root group_weights_tree;
+
+ /*
* Number of bfq_queues containing requests (including the
* queue in service, even if it is idling).
*/
@@ -767,6 +802,11 @@ struct bfq_group_data {
* to avoid too many special cases during group creation/
* migration.
* @stats: stats for this bfqg.
+ * @active_entities: number of active entities belonging to the group;
+ * unused for the root group. Used to know whether there
+ * are groups with more than one active @bfq_entity
+ * (see the comments to the function
+ * bfq_bfqq_may_idle()).
* @rq_pos_tree: rbtree sorted by next_request position, used when
* determining if two or more queues have interleaving
* requests (see bfq_find_close_cooperator()).
@@ -794,6 +834,8 @@ struct bfq_group {
struct bfq_entity *my_entity;
+ int active_entities;
+
struct rb_root rq_pos_tree;
struct bfqg_stats stats;
@@ -1224,12 +1266,27 @@ static bool bfq_update_parent_budget(struct bfq_entity *next_in_service)
* a candidate for next service (i.e, a candidate entity to serve
* after the in-service entity is expired). The function then returns
* true.
+ *
+ * In contrast, the entity could stil be a candidate for next service
+ * if it is not a queue, and has more than one child. In fact, even if
+ * one of its children is about to be set in service, other children
+ * may still be the next to serve. As a consequence, a non-queue
+ * entity is not a candidate for next-service only if it has only one
+ * child. And only if this condition holds, then the function returns
+ * true for a non-queue entity.
*/
static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
{
+ struct bfq_group *bfqg;
+
if (bfq_entity_to_bfqq(entity))
return true;
+ bfqg = container_of(entity, struct bfq_group, entity);
+
+ if (bfqg->active_entities == 1)
+ return true;
+
return false;
}
@@ -1463,6 +1520,15 @@ static void bfq_update_active_tree(struct rb_node *node)
goto up;
}
+static void bfq_weights_tree_add(struct bfq_data *bfqd,
+ struct bfq_entity *entity,
+ struct rb_root *root);
+
+static void bfq_weights_tree_remove(struct bfq_data *bfqd,
+ struct bfq_entity *entity,
+ struct rb_root *root);
+
+
/**
* bfq_active_insert - insert an entity in the active tree of its
* group/device.
@@ -1501,6 +1567,13 @@ static void bfq_active_insert(struct bfq_service_tree *st,
#endif
if (bfqq)
list_add(&bfqq->bfqq_list, &bfqq->bfqd->active_list);
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ else /* bfq_group */
+ bfq_weights_tree_add(bfqd, entity, &bfqd->group_weights_tree);
+
+ if (bfqg != bfqd->root_group)
+ bfqg->active_entities++;
+#endif
}
/**
@@ -1596,6 +1669,14 @@ static void bfq_active_extract(struct bfq_service_tree *st,
#endif
if (bfqq)
list_del(&bfqq->bfqq_list);
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ else /* bfq_group */
+ bfq_weights_tree_remove(bfqd, entity,
+ &bfqd->group_weights_tree);
+
+ if (bfqg != bfqd->root_group)
+ bfqg->active_entities--;
+#endif
}
/**
@@ -1693,6 +1774,7 @@ __bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
unsigned int prev_weight, new_weight;
struct bfq_data *bfqd = NULL;
+ struct rb_root *root;
#ifdef CONFIG_BFQ_GROUP_IOSCHED
struct bfq_sched_data *sd;
struct bfq_group *bfqg;
@@ -1742,7 +1824,26 @@ __bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
prev_weight = entity->weight;
new_weight = entity->orig_weight *
(bfqq ? bfqq->wr_coeff : 1);
+ /*
+ * If the weight of the entity changes, remove the entity
+ * from its old weight counter (if there is a counter
+ * associated with the entity), and add it to the counter
+ * associated with its new weight.
+ */
+ if (prev_weight != new_weight) {
+ root = bfqq ? &bfqd->queue_weights_tree :
+ &bfqd->group_weights_tree;
+ bfq_weights_tree_remove(bfqd, entity, root);
+ }
entity->weight = new_weight;
+ /*
+ * Add the entity to its weights tree only if it is
+ * not associated with a weight-raised queue.
+ */
+ if (prev_weight != new_weight &&
+ (bfqq ? bfqq->wr_coeff == 1 : 1))
+ /* If we get here, root has been initialized. */
+ bfq_weights_tree_add(bfqd, entity, root);
new_st->wsum += entity->weight;
@@ -2552,6 +2653,10 @@ static void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
bfqd->busy_queues--;
+ if (!bfqq->dispatched)
+ bfq_weights_tree_remove(bfqd, &bfqq->entity,
+ &bfqd->queue_weights_tree);
+
if (bfqq->wr_coeff > 1)
bfqd->wr_busy_queues--;
@@ -2572,6 +2677,11 @@ static void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq)
bfq_mark_bfqq_busy(bfqq);
bfqd->busy_queues++;
+ if (!bfqq->dispatched)
+ if (bfqq->wr_coeff == 1)
+ bfq_weights_tree_add(bfqd, &bfqq->entity,
+ &bfqd->queue_weights_tree);
+
if (bfqq->wr_coeff > 1)
bfqd->wr_busy_queues++;
}
@@ -2974,6 +3084,7 @@ static void bfq_pd_init(struct blkg_policy_data *pd)
* in bfq_init_queue()
*/
bfqg->bfqd = bfqd;
+ bfqg->active_entities = 0;
bfqg->rq_pos_tree = RB_ROOT;
}
@@ -3862,6 +3973,142 @@ static void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq)
}
/*
+ * Tell whether there are active queues or groups with differentiated weights.
+ */
+static bool bfq_differentiated_weights(struct bfq_data *bfqd)
+{
+ /*
+ * For weights to differ, at least one of the trees must contain
+ * at least two nodes.
+ */
+ return (!RB_EMPTY_ROOT(&bfqd->queue_weights_tree) &&
+ (bfqd->queue_weights_tree.rb_node->rb_left ||
+ bfqd->queue_weights_tree.rb_node->rb_right)
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ ) ||
+ (!RB_EMPTY_ROOT(&bfqd->group_weights_tree) &&
+ (bfqd->group_weights_tree.rb_node->rb_left ||
+ bfqd->group_weights_tree.rb_node->rb_right)
+#endif
+ );
+}
+
+/*
+ * The following function returns true if every queue must receive the
+ * same share of the throughput (this condition is used when deciding
+ * whether idling may be disabled, see the comments in the function
+ * bfq_bfqq_may_idle()).
+ *
+ * Such a scenario occurs when:
+ * 1) all active queues have the same weight,
+ * 2) all active groups at the same level in the groups tree have the same
+ * weight,
+ * 3) all active groups at the same level in the groups tree have the same
+ * number of children.
+ *
+ * Unfortunately, keeping the necessary state for evaluating exactly the
+ * above symmetry conditions would be quite complex and time-consuming.
+ * Therefore this function evaluates, instead, the following stronger
+ * sub-conditions, for which it is much easier to maintain the needed
+ * state:
+ * 1) all active queues have the same weight,
+ * 2) all active groups have the same weight,
+ * 3) all active groups have at most one active child each.
+ * In particular, the last two conditions are always true if hierarchical
+ * support and the cgroups interface are not enabled, thus no state needs
+ * to be maintained in this case.
+ */
+static bool bfq_symmetric_scenario(struct bfq_data *bfqd)
+{
+ return !bfq_differentiated_weights(bfqd);
+}
+
+/*
+ * If the weight-counter tree passed as input contains no counter for
+ * the weight of the input entity, then add that counter; otherwise just
+ * increment the existing counter.
+ *
+ * Note that weight-counter trees contain few nodes in mostly symmetric
+ * scenarios. For example, if all queues have the same weight, then the
+ * weight-counter tree for the queues may contain at most one node.
+ * This holds even if low_latency is on, because weight-raised queues
+ * are not inserted in the tree.
+ * In most scenarios, the rate at which nodes are created/destroyed
+ * should be low too.
+ */
+static void bfq_weights_tree_add(struct bfq_data *bfqd,
+ struct bfq_entity *entity,
+ struct rb_root *root)
+{
+ struct rb_node **new = &(root->rb_node), *parent = NULL;
+
+ /*
+ * Do not insert if the entity is already associated with a
+ * counter, which happens if:
+ * 1) the entity is associated with a queue,
+ * 2) a request arrival has caused the queue to become both
+ * non-weight-raised, and hence change its weight, and
+ * backlogged; in this respect, each of the two events
+ * causes an invocation of this function,
+ * 3) this is the invocation of this function caused by the
+ * second event. This second invocation is actually useless,
+ * and we handle this fact by exiting immediately. More
+ * efficient or clearer solutions might possibly be adopted.
+ */
+ if (entity->weight_counter)
+ return;
+
+ while (*new) {
+ struct bfq_weight_counter *__counter = container_of(*new,
+ struct bfq_weight_counter,
+ weights_node);
+ parent = *new;
+
+ if (entity->weight == __counter->weight) {
+ entity->weight_counter = __counter;
+ goto inc_counter;
+ }
+ if (entity->weight < __counter->weight)
+ new = &((*new)->rb_left);
+ else
+ new = &((*new)->rb_right);
+ }
+
+ entity->weight_counter = kzalloc(sizeof(struct bfq_weight_counter),
+ GFP_ATOMIC);
+ entity->weight_counter->weight = entity->weight;
+ rb_link_node(&entity->weight_counter->weights_node, parent, new);
+ rb_insert_color(&entity->weight_counter->weights_node, root);
+
+inc_counter:
+ entity->weight_counter->num_active++;
+}
+
+/*
+ * Decrement the weight counter associated with the entity, and, if the
+ * counter reaches 0, remove the counter from the tree.
+ * See the comments to the function bfq_weights_tree_add() for considerations
+ * about overhead.
+ */
+static void bfq_weights_tree_remove(struct bfq_data *bfqd,
+ struct bfq_entity *entity,
+ struct rb_root *root)
+{
+ if (!entity->weight_counter)
+ return;
+
+ entity->weight_counter->num_active--;
+ if (entity->weight_counter->num_active > 0)
+ goto reset_entity_pointer;
+
+ rb_erase(&entity->weight_counter->weights_node, root);
+ kfree(entity->weight_counter);
+
+reset_entity_pointer:
+ entity->weight_counter = NULL;
+}
+
+/*
* Return expired entry, or NULL to just start from scratch in rbtree.
*/
static struct request *bfq_check_fifo(struct bfq_queue *bfqq,
@@ -5246,13 +5493,17 @@ static void bfq_arm_slice_timer(struct bfq_data *bfqd)
*/
sl = bfqd->bfq_slice_idle;
/*
- * Unless the queue is being weight-raised, grant only minimum
- * idle time if the queue is seeky. A long idling is preserved
- * for a weight-raised queue, because it is needed for
- * guaranteeing to the queue its reserved share of the
- * throughput.
+ * Unless the queue is being weight-raised or the scenario is
+ * asymmetric, grant only minimum idle time if the queue
+ * is seeky. A long idling is preserved for a weight-raised
+ * queue, or, more in general, in an asymmetric scenario,
+ * because a long idling is needed for guaranteeing to a queue
+ * its reserved share of the throughput (in particular, it is
+ * needed if the queue has a higher weight than some other
+ * queue).
*/
- if (BFQQ_SEEKY(bfqq) && bfqq->wr_coeff == 1)
+ if (BFQQ_SEEKY(bfqq) && bfqq->wr_coeff == 1 &&
+ bfq_symmetric_scenario(bfqd))
sl = min_t(u64, sl, BFQ_MIN_TT);
bfqd->last_idling_start = ktime_get();
@@ -7146,6 +7397,9 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
* mechanism).
*/
bfqq->budget_timeout = jiffies;
+
+ bfq_weights_tree_remove(bfqd, &bfqq->entity,
+ &bfqd->queue_weights_tree);
}
now_ns = ktime_get_ns();
@@ -7576,6 +7830,9 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
HRTIMER_MODE_REL);
bfqd->idle_slice_timer.function = bfq_idle_slice_timer;
+ bfqd->queue_weights_tree = RB_ROOT;
+ bfqd->group_weights_tree = RB_ROOT;
+
INIT_LIST_HEAD(&bfqd->active_list);
INIT_LIST_HEAD(&bfqd->idle_list);
--
2.10.0
^ permalink raw reply related
* [PATCH RFC 10/14] block, bfq: add Early Queue Merge (EQM)
From: Paolo Valente @ 2017-03-04 16:01 UTC (permalink / raw)
To: Jens Axboe, Tejun Heo
Cc: Fabio Checconi, Arianna Avanzini, linux-block, linux-kernel,
ulf.hansson, linus.walleij, broonie, Mauro Andreolini,
Paolo Valente
In-Reply-To: <20170304160131.57366-1-paolo.valente@linaro.org>
From: Arianna Avanzini <avanzini.arianna@gmail.com>
A set of processes may happen to perform interleaved reads, i.e.,
read requests whose union would give rise to a sequential read pattern.
There are two typical cases: first, processes reading fixed-size chunks
of data at a fixed distance from each other; second, processes reading
variable-size chunks at variable distances. The latter case occurs for
example with QEMU, which splits the I/O generated by a guest into
multiple chunks, and lets these chunks be served by a pool of I/O
threads, iteratively assigning the next chunk of I/O to the first
available thread. CFQ denotes as 'cooperating' a set of processes that
are doing interleaved I/O, and when it detects cooperating processes,
it merges their queues to obtain a sequential I/O pattern from the union
of their I/O requests, and hence boost the throughput.
Unfortunately, in the following frequent case, the mechanism
implemented in CFQ for detecting cooperating processes and merging
their queues is not responsive enough to handle also the fluctuating
I/O pattern of the second type of processes. Suppose that one process
of the second type issues a request close to the next request to serve
of another process of the same type. At that time the two processes
would be considered as cooperating. But, if the request issued by the
first process is to be merged with some other already-queued request,
then, from the moment at which this request arrives, to the moment
when CFQ controls whether the two processes are cooperating, the two
processes are likely to be already doing I/O in distant zones of the
disk surface or device memory.
CFQ uses however preemption to get a sequential read pattern out of
the read requests performed by the second type of processes too. As a
consequence, CFQ 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 to immediately check whether a newly-arrived request lets some
pair of processes become cooperating, both in the case of actual
request insertion and, to be responsive with the second type of
processes, in the case of request merge. Both types of processes are
then handled by just merging their queues.
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Mauro Andreolini <mauro.andreolini@unimore.it>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
block/bfq-iosched.c | 885 +++++++++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 843 insertions(+), 42 deletions(-)
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index b22ef42..05b9421 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -263,11 +263,12 @@ struct bfq_ttime {
* struct bfq_queue - leaf schedulable entity.
*
* A bfq_queue is a leaf request queue; it can be associated with an
- * io_context or more, if it is async. @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 destruction). All the fields
- * are protected by the queue lock of the containing bfqd.
+ * io_context or more, if it is async or shared between cooperating
+ * processes. @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
+ * destruction).
+ * All the fields are protected by the queue lock of the containing bfqd.
*/
struct bfq_queue {
/* reference counter */
@@ -280,6 +281,16 @@ struct bfq_queue {
/* next ioprio and ioprio class if a change is in progress */
unsigned short new_ioprio, new_ioprio_class;
+ /*
+ * Shared bfq_queue if queue is cooperating with one or more
+ * other queues.
+ */
+ struct bfq_queue *new_bfqq;
+ /* request-position tree member (see bfq_group's @rq_pos_tree) */
+ struct rb_node pos_node;
+ /* request-position tree root (see bfq_group's @rq_pos_tree) */
+ struct rb_root *pos_root;
+
/* sorted list of pending requests */
struct rb_root sort_list;
/* if fifo isn't expired, next request to serve */
@@ -328,6 +339,12 @@ struct bfq_queue {
/* pid of the process owning the queue, used for logging purposes */
pid_t pid;
+ /*
+ * Pointer to the bfq_io_cq owning the bfq_queue, set to %NULL
+ * if the queue is shared.
+ */
+ struct bfq_io_cq *bic;
+
/* current maximum weight-raising time for this queue */
unsigned long wr_cur_max_time;
/*
@@ -356,10 +373,13 @@ struct bfq_queue {
* last transition from idle to backlogged.
*/
unsigned long service_from_backlogged;
+
/*
* Value of wr start time when switching to soft rt
*/
unsigned long wr_start_at_switch_to_srt;
+
+ unsigned long split_time; /* time of last split */
};
/**
@@ -375,6 +395,26 @@ struct bfq_io_cq {
#ifdef CONFIG_BFQ_GROUP_IOSCHED
uint64_t blkcg_serial_nr; /* the current blkcg serial */
#endif
+ /*
+ * Snapshot of the idle window before merging; taken to
+ * remember this value while the queue is merged, so as to be
+ * able to restore it in case of split.
+ */
+ bool saved_idle_window;
+ /*
+ * Same purpose as the previous two fields for the I/O bound
+ * classification of a queue.
+ */
+ bool saved_IO_bound;
+
+ /*
+ * Similar to previous fields: save wr information.
+ */
+ unsigned long saved_wr_coeff;
+ unsigned long saved_last_wr_start_finish;
+ unsigned long saved_wr_start_at_switch_to_srt;
+ unsigned int saved_wr_cur_max_time;
+ struct bfq_ttime saved_ttime;
};
enum bfq_device_speed {
@@ -560,6 +600,15 @@ struct bfq_data {
struct bfq_io_cq *bio_bic;
/* bfqq associated with the task issuing current bio for merging */
struct bfq_queue *bio_bfqq;
+
+ /*
+ * io context to put right after bfqd->lock is released. This
+ * filed is used to perform put_io_context, when needed, to
+ * after the scheduler lock has been released, and thus
+ * prevent an ioc->lock from being possibly taken while the
+ * scheduler lock is being held.
+ */
+ struct io_context *ioc_to_put;
};
enum bfqq_state_flags {
@@ -581,6 +630,8 @@ enum bfqq_state_flags {
* may need softrt-next-start
* update
*/
+ BFQ_BFQQ_FLAG_coop, /* bfqq is shared */
+ BFQ_BFQQ_FLAG_split_coop /* shared bfqq will be split */
};
#define BFQ_BFQQ_FNS(name) \
@@ -604,6 +655,8 @@ BFQ_BFQQ_FNS(fifo_expire);
BFQ_BFQQ_FNS(idle_window);
BFQ_BFQQ_FNS(sync);
BFQ_BFQQ_FNS(IO_bound);
+BFQ_BFQQ_FNS(coop);
+BFQ_BFQQ_FNS(split_coop);
BFQ_BFQQ_FNS(softrt_update);
#undef BFQ_BFQQ_FNS
@@ -714,6 +767,9 @@ struct bfq_group_data {
* to avoid too many special cases during group creation/
* migration.
* @stats: stats for this bfqg.
+ * @rq_pos_tree: rbtree sorted by next_request position, used when
+ * determining if two or more queues have interleaving
+ * requests (see bfq_find_close_cooperator()).
*
* 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
@@ -738,6 +794,8 @@ struct bfq_group {
struct bfq_entity *my_entity;
+ struct rb_root rq_pos_tree;
+
struct bfqg_stats stats;
};
@@ -787,6 +845,27 @@ static struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic)
return bic->icq.q->elevator->elevator_data;
}
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+
+static struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq)
+{
+ struct bfq_entity *group_entity = bfqq->entity.parent;
+
+ if (!group_entity)
+ group_entity = &bfqq->bfqd->root_group->entity;
+
+ return container_of(group_entity, struct bfq_group, entity);
+}
+
+#else
+
+static struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq)
+{
+ return bfqq->bfqd->root_group;
+}
+
+#endif
+
static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio);
static void bfq_put_queue(struct bfq_queue *bfqq);
static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
@@ -951,6 +1030,34 @@ static void bfq_schedule_dispatch(struct bfq_data *bfqd)
}
}
+/*
+ * Next two functions release bfqd->lock and put the io context
+ * pointed by bfqd->ioc_to_put. This delayed put is used to not risk
+ * to take an ioc->lock while the scheduler lock is being held.
+ */
+static void bfq_unlock_put_ioc(struct bfq_data *bfqd)
+{
+ struct io_context *ioc_to_put = bfqd->ioc_to_put;
+
+ bfqd->ioc_to_put = NULL;
+ spin_unlock_irq(&bfqd->lock);
+
+ if (ioc_to_put)
+ put_io_context(ioc_to_put);
+}
+
+static void bfq_unlock_put_ioc_restore(struct bfq_data *bfqd,
+ unsigned long flags)
+{
+ struct io_context *ioc_to_put = bfqd->ioc_to_put;
+
+ bfqd->ioc_to_put = NULL;
+ spin_unlock_irqrestore(&bfqd->lock, flags);
+
+ if (ioc_to_put)
+ put_io_context(ioc_to_put);
+}
+
/**
* bfq_gt - compare two timestamps.
* @a: first ts.
@@ -2379,7 +2486,14 @@ static void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
struct bfq_entity *entity = &bfqd->in_service_queue->entity;
if (bfqd->in_service_bic) {
- put_io_context(bfqd->in_service_bic->icq.ioc);
+ /*
+ * Schedule the release of a reference to
+ * bfqd->in_service_bic->icq.ioc to right after the
+ * scheduler lock is released. This ioc is not
+ * released immediately, to not risk to possibly take
+ * an ioc->lock while holding the scheduler lock.
+ */
+ bfqd->ioc_to_put = bfqd->in_service_bic->icq.ioc;
bfqd->in_service_bic = NULL;
}
@@ -2860,6 +2974,7 @@ static void bfq_pd_init(struct blkg_policy_data *pd)
* in bfq_init_queue()
*/
bfqg->bfqd = bfqd;
+ bfqg->rq_pos_tree = RB_ROOT;
}
static void bfq_pd_free(struct blkg_policy_data *pd)
@@ -2928,6 +3043,8 @@ static struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
return bfqg;
}
+static void bfq_pos_tree_add_move(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq);
static void bfq_bfqq_expire(struct bfq_data *bfqd,
struct bfq_queue *bfqq,
bool compensate,
@@ -2976,8 +3093,10 @@ static void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
entity->sched_data = &bfqg->sched_data;
bfqg_get(bfqg);
- if (bfq_bfqq_busy(bfqq))
+ if (bfq_bfqq_busy(bfqq)) {
+ bfq_pos_tree_add_move(bfqd, bfqq);
bfq_activate_bfqq(bfqd, bfqq);
+ }
if (!bfqd->in_service_queue && !bfqd->rq_in_driver)
bfq_schedule_dispatch(bfqd);
@@ -3017,8 +3136,7 @@ static struct bfq_group *__bfq_bic_change_cgroup(struct bfq_data *bfqd,
bic_set_bfqq(bic, NULL, 0);
bfq_log_bfqq(bfqd, async_bfqq,
"bic_change_group: %p %d",
- async_bfqq,
- async_bfqq->ref);
+ async_bfqq, async_bfqq->ref);
bfq_put_queue(async_bfqq);
}
}
@@ -3160,7 +3278,7 @@ static void bfq_pd_offline(struct blkg_policy_data *pd)
__bfq_deactivate_entity(entity, false);
bfq_put_async_queues(bfqd, bfqg);
- spin_unlock_irqrestore(&bfqd->lock, flags);
+ bfq_unlock_put_ioc_restore(bfqd, flags);
/*
* @blkg is going offline and will be ignored by
* blkg_[rw]stat_recursive_sum(). Transfer stats to the parent so
@@ -3677,6 +3795,72 @@ static struct request *bfq_choose_req(struct bfq_data *bfqd,
}
}
+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",
+ (unsigned long long)sector,
+ bfqq ? bfqq->pid : 0);
+
+ return bfqq;
+}
+
+static void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+ struct rb_node **p, *parent;
+ struct bfq_queue *__bfqq;
+
+ if (bfqq->pos_root) {
+ 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 = &bfq_bfqq_to_bfqg(bfqq)->rq_pos_tree;
+ __bfqq = bfq_rq_pos_tree_lookup(bfqd, bfqq->pos_root,
+ blk_rq_pos(bfqq->next_rq), &parent, &p);
+ if (!__bfqq) {
+ rb_link_node(&bfqq->pos_node, parent, p);
+ rb_insert_color(&bfqq->pos_node, bfqq->pos_root);
+ } else
+ bfqq->pos_root = NULL;
+}
+
/*
* Return expired entry, or NULL to just start from scratch in rbtree.
*/
@@ -3783,6 +3967,43 @@ static void bfq_updated_next_req(struct bfq_data *bfqd,
}
}
+static 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->saved_IO_bound)
+ bfq_mark_bfqq_IO_bound(bfqq);
+ else
+ bfq_clear_bfqq_IO_bound(bfqq);
+
+ bfqq->ttime = bic->saved_ttime;
+ bfqq->wr_coeff = bic->saved_wr_coeff;
+ bfqq->wr_start_at_switch_to_srt = bic->saved_wr_start_at_switch_to_srt;
+ bfqq->last_wr_start_finish = bic->saved_last_wr_start_finish;
+ bfqq->wr_cur_max_time = bic->saved_wr_cur_max_time;
+
+ if (bfqq->wr_coeff > 1 &&
+ time_is_before_jiffies(bfqq->last_wr_start_finish +
+ bfqq->wr_cur_max_time)) {
+ bfq_log_bfqq(bfqq->bfqd, bfqq,
+ "resume state: switching off wr");
+
+ bfqq->wr_coeff = 1;
+ }
+
+ /* make sure weight will be updated, however we got here */
+ bfqq->entity.prio_changed = 1;
+}
+
+static int bfqq_process_refs(struct bfq_queue *bfqq)
+{
+ return bfqq->ref - bfqq->allocated - bfqq->entity.on_st;
+}
+
static int bfq_bfqq_budget_left(struct bfq_queue *bfqq)
{
struct bfq_entity *entity = &bfqq->entity;
@@ -4103,14 +4324,16 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
/*
* bfqq deserves to be weight-raised if:
* - it is sync,
- * - it has been idle for enough time or is soft real-time.
+ * - it has been idle for enough time or is soft real-time,
+ * - is linked to a bfq_io_cq (it is not shared in any sense).
*/
soft_rt = bfqd->bfq_wr_max_softrt_rate > 0 &&
time_is_before_jiffies(bfqq->soft_rt_next_start);
*interactive = idle_for_long_time;
wr_or_deserves_wr = bfqd->low_latency &&
(bfqq->wr_coeff > 1 ||
- (bfq_bfqq_sync(bfqq) && (*interactive || soft_rt)));
+ (bfq_bfqq_sync(bfqq) &&
+ bfqq->bic && (*interactive || soft_rt)));
/*
* Using the last flag, update budget and check whether bfqq
@@ -4132,14 +4355,22 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
}
if (bfqd->low_latency) {
- bfq_update_bfqq_wr_on_rq_arrival(bfqd, bfqq,
- old_wr_coeff,
- wr_or_deserves_wr,
- *interactive,
- soft_rt);
-
- if (old_wr_coeff != bfqq->wr_coeff)
- bfqq->entity.prio_changed = 1;
+ if (unlikely(time_is_after_jiffies(bfqq->split_time)))
+ /* wraparound */
+ bfqq->split_time =
+ jiffies - bfqd->bfq_wr_min_idle_time - 1;
+
+ if (time_is_before_jiffies(bfqq->split_time +
+ bfqd->bfq_wr_min_idle_time)) {
+ bfq_update_bfqq_wr_on_rq_arrival(bfqd, bfqq,
+ old_wr_coeff,
+ wr_or_deserves_wr,
+ *interactive,
+ soft_rt);
+
+ if (old_wr_coeff != bfqq->wr_coeff)
+ bfqq->entity.prio_changed = 1;
+ }
}
bfqq->last_idle_bklogged = jiffies;
@@ -4186,6 +4417,12 @@ static void bfq_add_request(struct request *rq)
next_rq = bfq_choose_req(bfqd, bfqq->next_rq, rq, bfqd->last_position);
bfqq->next_rq = next_rq;
+ /*
+ * Adjust priority tree position, if next_rq changes.
+ */
+ if (prev != bfqq->next_rq)
+ bfq_pos_tree_add_move(bfqd, bfqq);
+
if (!bfq_bfqq_busy(bfqq)) /* switching to busy ... */
bfq_bfqq_handle_idle_busy_switch(bfqd, bfqq, old_wr_coeff,
rq, &interactive);
@@ -4320,6 +4557,14 @@ static void bfq_remove_request(struct request_queue *q,
*/
bfqq->entity.budget = bfqq->entity.service = 0;
}
+
+ /*
+ * Remove queue from request-position tree as it is empty.
+ */
+ if (bfqq->pos_root) {
+ rb_erase(&bfqq->pos_node, bfqq->pos_root);
+ bfqq->pos_root = NULL;
+ }
}
if (rq->cmd_flags & REQ_META)
@@ -4398,11 +4643,14 @@ static void bfq_request_merged(struct request_queue *q, struct request *req,
bfqd->last_position);
bfqq->next_rq = next_rq;
/*
- * If next_rq changes, update the queue's budget to fit
- * the new request.
+ * If next_rq changes, update both the queue's budget to
+ * fit the new request and the queue's position in its
+ * rq_pos_tree.
*/
- if (prev != bfqq->next_rq)
+ if (prev != bfqq->next_rq) {
bfq_updated_next_req(bfqd, bfqq);
+ bfq_pos_tree_add_move(bfqd, bfqq);
+ }
spin_unlock_irq(&bfqd->lock);
}
}
@@ -4486,12 +4734,363 @@ static void bfq_end_wr(struct bfq_data *bfqd)
spin_unlock_irq(&bfqd->lock);
}
+static sector_t bfq_io_struct_pos(void *io_struct, bool request)
+{
+ if (request)
+ return blk_rq_pos(io_struct);
+ else
+ return ((struct bio *)io_struct)->bi_iter.bi_sector;
+}
+
+static int bfq_rq_close_to_sector(void *io_struct, bool request,
+ sector_t sector)
+{
+ return abs(bfq_io_struct_pos(io_struct, request) - sector) <=
+ BFQQ_CLOSE_THR;
+}
+
+static struct bfq_queue *bfqq_find_close(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq,
+ sector_t sector)
+{
+ struct rb_root *root = &bfq_bfqq_to_bfqg(bfqq)->rq_pos_tree;
+ struct rb_node *parent, *node;
+ struct bfq_queue *__bfqq;
+
+ 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)
+ 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_to_sector(__bfqq->next_rq, true, sector))
+ 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)
+ return NULL;
+
+ __bfqq = rb_entry(node, struct bfq_queue, pos_node);
+ if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector))
+ return __bfqq;
+
+ return NULL;
+}
+
+static struct bfq_queue *bfq_find_close_cooperator(struct bfq_data *bfqd,
+ struct bfq_queue *cur_bfqq,
+ sector_t sector)
+{
+ struct bfq_queue *bfqq;
+
+ /*
+ * We shall notice if some of the queues are cooperating,
+ * e.g., working closely on the same area of the device. In
+ * that case, we can group them together and: 1) don't waste
+ * time idling, and 2) serve the union of their requests in
+ * the best possible order for throughput.
+ */
+ bfqq = bfqq_find_close(bfqd, cur_bfqq, sector);
+ if (!bfqq || bfqq == cur_bfqq)
+ return NULL;
+
+ 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;
+ new_bfqq->ref += process_refs;
+ return new_bfqq;
+}
+
+static bool bfq_may_be_close_cooperator(struct bfq_queue *bfqq,
+ struct bfq_queue *new_bfqq)
+{
+ if (bfq_class_idle(bfqq) || bfq_class_idle(new_bfqq) ||
+ (bfqq->ioprio_class != new_bfqq->ioprio_class))
+ return false;
+
+ /*
+ * If either of the queues has already been detected as seeky,
+ * then merging it with the other queue is unlikely to lead to
+ * sequential I/O.
+ */
+ if (BFQQ_SEEKY(bfqq) || BFQQ_SEEKY(new_bfqq))
+ return false;
+
+ /*
+ * Interleaved I/O is known to be done by (some) applications
+ * only for reads, so it does not make sense to merge async
+ * queues.
+ */
+ if (!bfq_bfqq_sync(bfqq) || !bfq_bfqq_sync(new_bfqq))
+ return false;
+
+ return true;
+}
+
+/*
+ * If this function returns true, then bfqq cannot be merged. The idea
+ * is that true cooperation happens very early after processes start
+ * to do I/O. Usually, late cooperations are just accidental false
+ * positives. In case bfqq is weight-raised, such false positives
+ * would evidently degrade latency guarantees for bfqq.
+ */
+static bool wr_from_too_long(struct bfq_queue *bfqq)
+{
+ return bfqq->wr_coeff > 1 &&
+ time_is_before_jiffies(bfqq->last_wr_start_finish +
+ msecs_to_jiffies(100));
+}
+
+/*
+ * 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.
+ *
+ * The OOM queue is not allowed to participate to cooperation: in fact, since
+ * the requests temporarily redirected to the OOM queue could be redirected
+ * again to dedicated queues at any time, the state needed to correctly
+ * handle merging with the OOM queue would be quite complex and expensive
+ * to maintain. Besides, in such a critical condition as an out of memory,
+ * the benefits of queue merging may be little relevant, or even negligible.
+ *
+ * Weight-raised queues can be merged only if their weight-raising
+ * period has just started. In fact cooperating processes are usually
+ * started together. Thus, with this filter we avoid false positives
+ * that would jeopardize low-latency guarantees.
+ *
+ * WARNING: queue merging may impair fairness among non-weight raised
+ * queues, for at least two reasons: 1) the original weight of a
+ * merged queue may change during the merged state, 2) even being the
+ * weight the same, a merged queue may be bloated with many more
+ * requests than the ones produced by its originally-associated
+ * process.
+ */
+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 ||
+ wr_from_too_long(bfqq) ||
+ unlikely(bfqq == &bfqd->oom_bfqq))
+ return NULL;
+
+ /* If there is only one backlogged queue, don't search. */
+ if (bfqd->busy_queues == 1)
+ return NULL;
+
+ in_service_bfqq = bfqd->in_service_queue;
+
+ if (!in_service_bfqq || in_service_bfqq == bfqq ||
+ !bfqd->in_service_bic || wr_from_too_long(in_service_bfqq) ||
+ unlikely(in_service_bfqq == &bfqd->oom_bfqq))
+ goto check_scheduled;
+
+ if (bfq_rq_close_to_sector(io_struct, request, bfqd->last_position) &&
+ bfqq->entity.parent == in_service_bfqq->entity.parent &&
+ bfq_may_be_close_cooperator(bfqq, in_service_bfqq)) {
+ new_bfqq = bfq_setup_merge(bfqq, in_service_bfqq);
+ if (new_bfqq)
+ return new_bfqq;
+ }
+ /*
+ * 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_find_close_cooperator(bfqd, bfqq,
+ bfq_io_struct_pos(io_struct, request));
+
+ if (new_bfqq && !wr_from_too_long(new_bfqq) &&
+ likely(new_bfqq != &bfqd->oom_bfqq) &&
+ bfq_may_be_close_cooperator(bfqq, new_bfqq))
+ return bfq_setup_merge(bfqq, new_bfqq);
+
+ return NULL;
+}
+
+static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
+{
+ struct bfq_io_cq *bic = bfqq->bic;
+
+ /*
+ * If !bfqq->bic, 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 (!bic)
+ return;
+
+ bic->saved_ttime = bfqq->ttime;
+ bic->saved_idle_window = bfq_bfqq_idle_window(bfqq);
+ bic->saved_IO_bound = bfq_bfqq_IO_bound(bfqq);
+ bic->saved_wr_coeff = bfqq->wr_coeff;
+ bic->saved_wr_start_at_switch_to_srt = bfqq->wr_start_at_switch_to_srt;
+ bic->saved_last_wr_start_finish = bfqq->last_wr_start_finish;
+ bic->saved_wr_cur_max_time = bfqq->wr_cur_max_time;
+}
+
+static 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",
+ (unsigned long)new_bfqq->pid);
+ /* Save weight raising and idle window of the merged queues */
+ bfq_bfqq_save_state(bfqq);
+ bfq_bfqq_save_state(new_bfqq);
+ if (bfq_bfqq_IO_bound(bfqq))
+ bfq_mark_bfqq_IO_bound(new_bfqq);
+ bfq_clear_bfqq_IO_bound(bfqq);
+
+ /*
+ * If bfqq is weight-raised, then let new_bfqq inherit
+ * weight-raising. To reduce false positives, neglect the case
+ * where bfqq has just been created, but has not yet made it
+ * to be weight-raised (which may happen because EQM may merge
+ * bfqq even before bfq_add_request is executed for the first
+ * time for bfqq).
+ */
+ if (new_bfqq->wr_coeff == 1 && bfqq->wr_coeff > 1) {
+ new_bfqq->wr_coeff = bfqq->wr_coeff;
+ new_bfqq->wr_cur_max_time = bfqq->wr_cur_max_time;
+ new_bfqq->last_wr_start_finish = bfqq->last_wr_start_finish;
+ new_bfqq->wr_start_at_switch_to_srt =
+ bfqq->wr_start_at_switch_to_srt;
+ if (bfq_bfqq_busy(new_bfqq))
+ bfqd->wr_busy_queues++;
+ new_bfqq->entity.prio_changed = 1;
+ }
+
+ if (bfqq->wr_coeff > 1) { /* bfqq has given its wr to new_bfqq */
+ bfqq->wr_coeff = 1;
+ bfqq->entity.prio_changed = 1;
+ if (bfq_bfqq_busy(bfqq))
+ bfqd->wr_busy_queues--;
+ }
+
+ bfq_log_bfqq(bfqd, new_bfqq, "merge_bfqqs: wr_busy %d",
+ bfqd->wr_busy_queues);
+
+ /*
+ * 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 bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
struct bio *bio)
{
struct bfq_data *bfqd = q->elevator->elevator_data;
bool is_sync = op_is_sync(bio->bi_opf);
- struct bfq_queue *bfqq = bfqd->bio_bfqq;
+ struct bfq_queue *bfqq = bfqd->bio_bfqq, *new_bfqq;
/*
* Disallow merge of a sync bio into an async request.
@@ -4506,6 +5105,37 @@ static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
if (!bfqq)
return false;
+ /*
+ * We take advantage of this function to perform an early merge
+ * of the queues of possible cooperating processes.
+ */
+ new_bfqq = bfq_setup_cooperator(bfqd, bfqq, bio, false);
+ if (new_bfqq) {
+ /*
+ * bic still points to bfqq, then it has not yet been
+ * redirected to some other bfq_queue, and a queue
+ * merge beween bfqq and new_bfqq can be safely
+ * fulfillled, i.e., bic can be redirected to new_bfqq
+ * and bfqq can be put.
+ */
+ bfq_merge_bfqqs(bfqd, bfqd->bio_bic, bfqq,
+ new_bfqq);
+ /*
+ * If we get here, bio will be queued into new_queue,
+ * so use new_bfqq to decide whether bio and rq can be
+ * merged.
+ */
+ bfqq = new_bfqq;
+
+ /*
+ * Change also bqfd->bio_bfqq, as
+ * bfqd->bio_bic now points to new_bfqq, and
+ * this function may be invoked again (and then may
+ * use again bqfd->bio_bfqq).
+ */
+ bfqd->bio_bfqq = bfqq;
+ }
+
return bfqq == RQ_BFQQ(rq);
}
@@ -4913,6 +5543,15 @@ static void bfq_dispatch_remove(struct request_queue *q, struct request *rq)
static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
{
+ /*
+ * 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)) {
if (bfqq->dispatched == 0)
/*
@@ -4924,8 +5563,13 @@ static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
bfqq->budget_timeout = jiffies;
bfq_del_bfqq_busy(bfqd, bfqq, true);
- } else
+ } else {
bfq_requeue_bfqq(bfqd, bfqq);
+ /*
+ * Resort priority tree of potential close cooperators.
+ */
+ bfq_pos_tree_add_move(bfqd, bfqq);
+ }
/*
* All in-service entities must have been properly deactivated
@@ -5742,8 +6386,7 @@ static void bfq_update_wr_data(struct bfq_data *bfqd, struct bfq_queue *bfqq)
/*
* If too much time has elapsed from the beginning of
- * this weight-raising period, then end weight
- * raising.
+ * this weight-raising period, then end weight raising.
*/
if (time_is_before_jiffies(bfqq->last_wr_start_finish +
bfqq->wr_cur_max_time)) {
@@ -5919,8 +6562,9 @@ static struct request *bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
struct request *rq;
spin_lock_irq(&bfqd->lock);
+
rq = __bfq_dispatch_request(hctx);
- spin_unlock_irq(&bfqd->lock);
+ bfq_unlock_put_ioc(bfqd);
return rq;
}
@@ -5953,6 +6597,25 @@ static void bfq_put_queue(struct bfq_queue *bfqq)
#endif
}
+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)
+ 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) {
@@ -5962,6 +6625,8 @@ static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
bfq_log_bfqq(bfqd, bfqq, "exit_bfqq: %p, %d", bfqq, bfqq->ref);
+ bfq_put_cooperator(bfqq);
+
bfq_put_queue(bfqq);
}
@@ -5977,9 +6642,20 @@ static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync)
unsigned long flags;
spin_lock_irqsave(&bfqd->lock, flags);
+ /*
+ * 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. This put cannot
+ * make ioc->ref_count reach 0, then no ioc->lock
+ * risks to be taken (leading to possible deadlock
+ * scenarios).
+ */
+ if (is_sync && bfq_bfqq_coop(bfqq))
+ put_io_context(bic->icq.ioc);
+
bfq_exit_bfqq(bfqd, bfqq);
bic_set_bfqq(bic, NULL, is_sync);
- spin_unlock_irq(&bfqd->lock);
+ bfq_unlock_put_ioc_restore(bfqd, flags);
}
}
@@ -6099,8 +6775,9 @@ static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
bfqq->budget_timeout = bfq_smallest_from_now();
bfqq->wr_coeff = 1;
- bfqq->last_wr_start_finish = bfq_smallest_from_now();
+ bfqq->last_wr_start_finish = jiffies;
bfqq->wr_start_at_switch_to_srt = bfq_smallest_from_now();
+ bfqq->split_time = bfq_smallest_from_now();
/*
* Set to the value for which bfqq will not be deemed as
@@ -6235,6 +6912,11 @@ 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 (time_is_after_eq_jiffies(bfqq->split_time +
+ bfqd->bfq_wr_min_idle_time))
+ return;
+
enable_idle = bfq_bfqq_idle_window(bfqq);
if (atomic_read(&bic->icq.ioc->active_ref) == 0 ||
@@ -6330,7 +7012,41 @@ static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq,
static void __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
{
- struct bfq_queue *bfqq = RQ_BFQQ(rq);
+ struct bfq_queue *bfqq = RQ_BFQQ(rq), *new_bfqq;
+
+ /*
+ * 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) {
+ 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++;
+ bfqq->allocated--;
+ new_bfqq->ref++;
+ bfq_put_queue(bfqq);
+ /*
+ * If the bic associated with the process
+ * issuing this request still points to bfqq
+ * (and thus has not been already redirected
+ * to new_bfqq or even some other bfq_queue),
+ * then complete the merge and redirect it to
+ * new_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_add_request(rq);
@@ -6372,7 +7088,7 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
}
}
- spin_unlock_irq(&bfqd->lock);
+ bfq_unlock_put_ioc(bfqd);
}
static void bfq_insert_requests(struct blk_mq_hw_ctx *hctx,
@@ -6523,7 +7239,7 @@ static void bfq_put_rq_private(struct request_queue *q, struct request *rq)
bfq_completed_request(bfqq, bfqd);
bfq_put_rq_priv_body(bfqq);
- spin_unlock_irqrestore(&bfqd->lock, flags);
+ bfq_unlock_put_ioc_restore(bfqd, flags);
} else {
/*
* Request rq may be still/already in the scheduler,
@@ -6547,6 +7263,55 @@ static void bfq_put_rq_private(struct request_queue *q, struct request *rq)
}
/*
+ * Returns NULL if a new bfqq should be allocated, or the old bfqq if this
+ * was the last process referring to that 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;
+}
+
+static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd,
+ struct bfq_io_cq *bic,
+ struct bio *bio,
+ bool split, bool is_sync,
+ bool *new_queue)
+{
+ struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync);
+
+ if (likely(bfqq && bfqq != &bfqd->oom_bfqq))
+ return bfqq;
+
+ if (new_queue)
+ *new_queue = true;
+
+ if (bfqq)
+ bfq_put_queue(bfqq);
+ bfqq = bfq_get_queue(bfqd, bio, is_sync, bic);
+
+ bic_set_bfqq(bic, bfqq, is_sync);
+ if (split && is_sync)
+ bfqq->split_time = jiffies;
+
+ return bfqq;
+}
+
+/*
* Allocate bfq data structures associated with this request.
*/
static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
@@ -6556,6 +7321,7 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
struct bfq_io_cq *bic = icq_to_bic(rq->elv.icq);
const int is_sync = rq_is_sync(rq);
struct bfq_queue *bfqq;
+ bool new_queue = false;
spin_lock_irq(&bfqd->lock);
@@ -6566,12 +7332,28 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
bfq_bic_update_cgroup(bic, bio);
- bfqq = bic_to_bfqq(bic, is_sync);
- if (!bfqq || bfqq == &bfqd->oom_bfqq) {
- if (bfqq)
- bfq_put_queue(bfqq);
- bfqq = bfq_get_queue(bfqd, bio, is_sync, bic);
- bic_set_bfqq(bic, bfqq, is_sync);
+ bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio, false, is_sync,
+ &new_queue);
+
+ if (unlikely(!new_queue)) {
+ /* 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);
+ /*
+ * A reference to bic->icq.ioc needs to be
+ * released after a queue split. Do not do it
+ * immediately, to not risk to possibly take
+ * an ioc->lock while holding the scheduler
+ * lock.
+ */
+ bfqd->ioc_to_put = bic->icq.ioc;
+
+ if (!bfqq)
+ bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio,
+ true, is_sync,
+ NULL);
+ }
}
bfqq->allocated++;
@@ -6582,7 +7364,25 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
rq->elv.priv[0] = bic;
rq->elv.priv[1] = bfqq;
- spin_unlock_irq(&bfqd->lock);
+ /*
+ * If a bfq_queue has only one process reference, it is owned
+ * by only this bic: we can then set bfqq->bic = bic. in
+ * addition, if the queue has also just been split, we have to
+ * resume its state.
+ */
+ if (likely(bfqq != &bfqd->oom_bfqq) && bfqq_process_refs(bfqq) == 1) {
+ bfqq->bic = bic;
+ if (bfqd->ioc_to_put) { /* if true, there has been a split */
+ /*
+ * 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);
+ }
+ }
+
+ bfq_unlock_put_ioc(bfqd);
return 0;
@@ -6627,7 +7427,7 @@ static void bfq_idle_slice_timer_body(struct bfq_queue *bfqq)
bfq_bfqq_expire(bfqd, bfqq, true, reason);
schedule_dispatch:
- spin_unlock_irqrestore(&bfqd->lock, flags);
+ bfq_unlock_put_ioc_restore(bfqd, flags);
bfq_schedule_dispatch(bfqd);
}
@@ -6724,6 +7524,7 @@ static void bfq_init_root_group(struct bfq_group *root_group,
root_group->my_entity = NULL;
root_group->bfqd = bfqd;
#endif
+ root_group->rq_pos_tree = RB_ROOT;
for (i = 0; i < BFQ_IOPRIO_CLASSES; i++)
root_group->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT;
root_group->sched_data.bfq_class_idle_last_service = jiffies;
@@ -7185,7 +7986,7 @@ static struct blkcg_policy blkcg_policy_bfq = {
static int __init bfq_init(void)
{
int ret;
- char msg[50] = "BFQ I/O-scheduler: v2";
+ char msg[50] = "BFQ I/O-scheduler: v6";
#ifdef CONFIG_BFQ_GROUP_IOSCHED
ret = blkcg_policy_register(&blkcg_policy_bfq);
--
2.10.0
^ permalink raw reply related
* [PATCH RFC 09/14] block, bfq: reduce latency during request-pool saturation
From: Paolo Valente @ 2017-03-04 16:01 UTC (permalink / raw)
To: Jens Axboe, Tejun Heo
Cc: Fabio Checconi, Arianna Avanzini, linux-block, linux-kernel,
ulf.hansson, linus.walleij, broonie, Paolo Valente
In-Reply-To: <20170304160131.57366-1-paolo.valente@linaro.org>
This patch introduces an heuristic that reduces latency when the
I/O-request pool is saturated. This goal is achieved by disabling
device idling, for non-weight-raised queues, when there are weight-
raised queues with pending or in-flight requests. In fact, as
explained in more detail in the comment on the function
bfq_bfqq_may_idle(), this reduces the rate at which processes
associated with non-weight-raised queues grab requests from the pool,
thereby increasing the probability that processes associated with
weight-raised queues get a request immediately (or at least soon) when
they need one. Along the same line, if there are weight-raised queues,
then this patch halves the service rate of async (write) requests for
non-weight-raised queues.
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
---
block/bfq-iosched.c | 66 ++++++++++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 63 insertions(+), 3 deletions(-)
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index b439779..b22ef42 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -401,6 +401,8 @@ struct bfq_data {
* queue in service, even if it is idling).
*/
int busy_queues;
+ /* number of weight-raised busy @bfq_queues */
+ int wr_busy_queues;
/* number of queued requests */
int queued;
/* number of requests dispatched and waiting for completion */
@@ -2436,6 +2438,9 @@ static void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
bfqd->busy_queues--;
+ if (bfqq->wr_coeff > 1)
+ bfqd->wr_busy_queues--;
+
bfqg_stats_update_dequeue(bfqq_group(bfqq));
bfq_deactivate_bfqq(bfqd, bfqq, true, expiration);
@@ -2452,6 +2457,9 @@ static void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq)
bfq_mark_bfqq_busy(bfqq);
bfqd->busy_queues++;
+
+ if (bfqq->wr_coeff > 1)
+ bfqd->wr_busy_queues++;
}
#ifdef CONFIG_BFQ_GROUP_IOSCHED
@@ -3725,7 +3733,16 @@ static unsigned long bfq_serv_to_charge(struct request *rq,
if (bfq_bfqq_sync(bfqq) || bfqq->wr_coeff > 1)
return blk_rq_sectors(rq);
- return blk_rq_sectors(rq) * bfq_async_charge_factor;
+ /*
+ * If there are no weight-raised queues, then amplify service
+ * by just the async charge factor; otherwise amplify service
+ * by twice the async charge factor, to further reduce latency
+ * for weight-raised queues.
+ */
+ if (bfqq->bfqd->wr_busy_queues == 0)
+ return blk_rq_sectors(rq) * bfq_async_charge_factor;
+
+ return blk_rq_sectors(rq) * 2 * bfq_async_charge_factor;
}
/**
@@ -4180,6 +4197,7 @@ static void bfq_add_request(struct request *rq)
bfqq->wr_coeff = bfqd->bfq_wr_coeff;
bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+ bfqd->wr_busy_queues++;
bfqq->entity.prio_changed = 1;
}
if (prev != bfqq->next_rq)
@@ -4428,6 +4446,8 @@ static void bfq_requests_merged(struct request_queue *q, struct request *rq,
/* Must be called with bfqq != NULL */
static void bfq_bfqq_end_wr(struct bfq_queue *bfqq)
{
+ if (bfq_bfqq_busy(bfqq))
+ bfqq->bfqd->wr_busy_queues--;
bfqq->wr_coeff = 1;
bfqq->wr_cur_max_time = 0;
bfqq->last_wr_start_finish = jiffies;
@@ -5447,7 +5467,8 @@ static bool bfq_may_expire_for_budg_timeout(struct bfq_queue *bfqq)
static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
{
struct bfq_data *bfqd = bfqq->bfqd;
- bool idling_boosts_thr, asymmetric_scenario;
+ bool idling_boosts_thr, idling_boosts_thr_without_issues,
+ asymmetric_scenario;
if (bfqd->strict_guarantees)
return true;
@@ -5470,6 +5491,44 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
idling_boosts_thr = !bfqd->hw_tag || bfq_bfqq_IO_bound(bfqq);
/*
+ * The value of the next variable,
+ * idling_boosts_thr_without_issues, is equal to that of
+ * idling_boosts_thr, unless a special case holds. In this
+ * special case, described below, idling may cause problems to
+ * weight-raised queues.
+ *
+ * When the request pool is saturated (e.g., in the presence
+ * of write hogs), if the processes associated with
+ * non-weight-raised queues ask for requests at a lower rate,
+ * then processes associated with weight-raised queues have a
+ * higher probability to get a request from the pool
+ * immediately (or at least soon) when they need one. Thus
+ * they have a higher probability to actually get a fraction
+ * of the device throughput proportional to their high
+ * weight. This is especially true with NCQ-capable drives,
+ * which enqueue several requests in advance, and further
+ * reorder internally-queued requests.
+ *
+ * For this reason, we force to false the value of
+ * idling_boosts_thr_without_issues if there are weight-raised
+ * busy queues. In this case, and if bfqq is not weight-raised,
+ * this guarantees that the device is not idled for bfqq (if,
+ * instead, bfqq is weight-raised, then idling will be
+ * guaranteed by another variable, see below). Combined with
+ * the timestamping rules of BFQ (see [1] for details), this
+ * behavior causes bfqq, and hence any sync non-weight-raised
+ * queue, to get a lower number of requests served, and thus
+ * to ask for a lower number of requests from the request
+ * pool, before the busy weight-raised queues get served
+ * again. This often mitigates starvation problems in the
+ * presence of heavy write workloads and NCQ, thereby
+ * guaranteeing a higher application and system responsiveness
+ * in these hostile scenarios.
+ */
+ idling_boosts_thr_without_issues = idling_boosts_thr &&
+ bfqd->wr_busy_queues == 0;
+
+ /*
* There is then a case where idling must be performed not for
* throughput concerns, but to preserve service guarantees. To
* introduce it, we can note that allowing the drive to
@@ -5543,7 +5602,7 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
* is necessary to preserve service guarantees.
*/
return bfq_bfqq_sync(bfqq) &&
- (idling_boosts_thr || asymmetric_scenario);
+ (idling_boosts_thr_without_issues || asymmetric_scenario);
}
/*
@@ -6748,6 +6807,7 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
* high-definition compressed
* video.
*/
+ bfqd->wr_busy_queues = 0;
/*
* Begin by assuming, optimistically, that the device is a
--
2.10.0
^ permalink raw reply related
* [PATCH RFC 08/14] block, bfq: preserve a low latency also with NCQ-capable drives
From: Paolo Valente @ 2017-03-04 16:01 UTC (permalink / raw)
To: Jens Axboe, Tejun Heo
Cc: Fabio Checconi, Arianna Avanzini, linux-block, linux-kernel,
ulf.hansson, linus.walleij, broonie, Paolo Valente
In-Reply-To: <20170304160131.57366-1-paolo.valente@linaro.org>
I/O schedulers typically allow NCQ-capable drives to prefetch I/O
requests, as NCQ boosts the throughput exactly by prefetching and
internally reordering requests.
Unfortunately, as discussed in detail and shown experimentally in [1],
this may cause fairness and latency guarantees to be violated. The
main problem is that the internal scheduler of an NCQ-capable drive
may postpone the service of some unlucky (prefetched) requests as long
as it deems serving other requests more appropriate to boost the
throughput.
This patch addresses this issue by not disabling device idling for
weight-raised queues, even if the device supports NCQ. This allows BFQ
to start serving a new queue, and therefore allows the drive to
prefetch new requests, only after the idling timeout expires. At that
time, all the outstanding requests of the expired queue have been most
certainly served.
[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.
Slightly extended version:
http://algogroup.unimore.it/people/paolo/disk_sched/bfq-v1-suite-
results.pdf
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
---
block/bfq-iosched.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index bc47591..b439779 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -6180,7 +6180,8 @@ static void bfq_update_idle_window(struct bfq_data *bfqd,
if (atomic_read(&bic->icq.ioc->active_ref) == 0 ||
bfqd->bfq_slice_idle == 0 ||
- (bfqd->hw_tag && BFQQ_SEEKY(bfqq)))
+ (bfqd->hw_tag && BFQQ_SEEKY(bfqq) &&
+ bfqq->wr_coeff == 1))
enable_idle = 0;
else if (bfq_sample_valid(bfqq->ttime.ttime_samples)) {
if (bfqq->ttime.ttime_mean > bfqd->bfq_slice_idle &&
--
2.10.0
^ permalink raw reply related
* [PATCH RFC 07/14] block, bfq: reduce I/O latency for soft real-time applications
From: Paolo Valente @ 2017-03-04 16:01 UTC (permalink / raw)
To: Jens Axboe, Tejun Heo
Cc: Fabio Checconi, Arianna Avanzini, linux-block, linux-kernel,
ulf.hansson, linus.walleij, broonie, Paolo Valente
In-Reply-To: <20170304160131.57366-1-paolo.valente@linaro.org>
To guarantee a low latency also to the I/O requests issued by soft
real-time applications, this patch introduces a further heuristic,
which weight-raises (in the sense explained in the previous patch)
also the queues associated to applications deemed as soft real-time.
To be deemed as soft real-time, an application must meet two
requirements. First, the application must not require an average
bandwidth higher than the approximate bandwidth required to playback
or record a compressed high-definition video. Second, the request
pattern of the application must be isochronous, i.e., after issuing a
request or a batch of requests, the application must stop issuing new
requests until all its pending requests have been completed. After
that, the application may issue a new batch, and so on.
As for the second requirement, it is critical to require also that,
after all the pending requests of the application have been completed,
an adequate minimum amount of time elapses before the application
starts issuing new requests. This prevents also greedy (i.e.,
I/O-bound) applications from being incorrectly deemed, occasionally,
as soft real-time. In fact, if *any amount of time* is fine, then even
a greedy application may, paradoxically, meet both the above
requirements, if: (1) the application performs random I/O and/or the
device is slow, and (2) the CPU load is high. The reason is the
following. First, if condition (1) is true, then, during the service
of the application, the throughput may be low enough to let the
application meet the bandwidth requirement. Second, if condition (2)
is true as well, then the application may occasionally behave in an
apparently isochronous way, because it may simply stop issuing
requests while the CPUs are busy serving other processes.
To address this issue, the heuristic leverages the simple fact that
greedy applications issue *all* their requests as quickly as they can,
whereas soft real-time applications spend some time processing data
after each batch of requests is completed. In particular, the
heuristic works as follows. First, according to the above isochrony
requirement, the heuristic checks whether an application may be soft
real-time, thereby giving to the application the opportunity to be
deemed as such, only when both the following two conditions happen to
hold: 1) the queue associated with the application has expired and is
empty, 2) there is no outstanding request of the application.
Suppose that both conditions hold at time, say, t_c and that the
application issues its next request at time, say, t_i. At time t_c the
heuristic computes the next time instant, called soft_rt_next_start in
the code, such that, only if t_i >= soft_rt_next_start, then both the
next conditions will hold when the application issues its next
request: 1) the application will meet the above bandwidth requirement,
2) a given minimum time interval, say Delta, will have elapsed from
time t_c (so as to filter out greedy application).
The current value of Delta is a little bit higher than the value that
we have found, experimentally, to be adequate on a real,
general-purpose machine. In particular we had to increase Delta to
make the filter quite precise also in slower, embedded systems, and in
KVM/QEMU virtual machines (details in the comments on the code).
If the application actually issues its next request after time
soft_rt_next_start, then its associated queue will be weight-raised
for a relatively short time interval. If, during this time interval,
the application proves again to meet the bandwidth and isochrony
requirements, then the end of the weight-raising period for the queue
is moved forward, and so on. Note that an application whose associated
queue never happens to be empty when it expires will never have the
opportunity to be deemed as soft real-time.
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
---
block/bfq-iosched.c | 352 +++++++++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 332 insertions(+), 20 deletions(-)
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 98f0ddf..bc47591 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -111,6 +111,13 @@
#define BFQ_DEFAULT_GRP_IOPRIO 0
#define BFQ_DEFAULT_GRP_CLASS IOPRIO_CLASS_BE
+/*
+ * Soft real-time applications are extremely more latency sensitive
+ * than interactive ones. Over-raise the weight of the former to
+ * privilege them against the latter.
+ */
+#define BFQ_SOFTRT_WEIGHT_FACTOR 100
+
struct bfq_entity;
/**
@@ -324,6 +331,14 @@ struct bfq_queue {
/* current maximum weight-raising time for this queue */
unsigned long wr_cur_max_time;
/*
+ * Minimum time instant such that, only if a new request is
+ * enqueued after this time instant in an idle @bfq_queue with
+ * no outstanding requests, then the task associated with the
+ * queue it is deemed as soft real-time (see the comments on
+ * the function bfq_bfqq_softrt_next_start())
+ */
+ unsigned long soft_rt_next_start;
+ /*
* Start time of the current weight-raising period if
* the @bfq-queue is being weight-raised, otherwise
* finish time of the last weight-raising period.
@@ -331,6 +346,20 @@ struct bfq_queue {
unsigned long last_wr_start_finish;
/* factor by which the weight of this queue is multiplied */
unsigned int wr_coeff;
+ /*
+ * Time of the last transition of the @bfq_queue from idle to
+ * backlogged.
+ */
+ unsigned long last_idle_bklogged;
+ /*
+ * Cumulative service received from the @bfq_queue since the
+ * last transition from idle to backlogged.
+ */
+ unsigned long service_from_backlogged;
+ /*
+ * Value of wr start time when switching to soft rt
+ */
+ unsigned long wr_start_at_switch_to_srt;
};
/**
@@ -488,6 +517,9 @@ struct bfq_data {
unsigned int bfq_wr_coeff;
/* maximum duration of a weight-raising period (jiffies) */
unsigned int bfq_wr_max_time;
+
+ /* Maximum weight-raising duration for soft real-time processes */
+ unsigned int bfq_wr_rt_max_time;
/*
* Minimum idle period after which weight-raising may be
* reactivated for a queue (in jiffies).
@@ -499,6 +531,9 @@ struct bfq_data {
* queue (in jiffies).
*/
unsigned long bfq_wr_min_inter_arr_async;
+
+ /* Max service-rate for a soft real-time queue, in sectors/sec */
+ unsigned int bfq_wr_max_softrt_rate;
/*
* Cached value of the product R*T, used for computing the
* maximum duration of weight raising automatically.
@@ -540,6 +575,10 @@ enum bfqq_state_flags {
* having consumed at most 2/10 of
* its budget
*/
+ BFQ_BFQQ_FLAG_softrt_update, /*
+ * may need softrt-next-start
+ * update
+ */
};
#define BFQ_BFQQ_FNS(name) \
@@ -563,6 +602,7 @@ BFQ_BFQQ_FNS(fifo_expire);
BFQ_BFQQ_FNS(idle_window);
BFQ_BFQQ_FNS(sync);
BFQ_BFQQ_FNS(IO_bound);
+BFQ_BFQQ_FNS(softrt_update);
#undef BFQ_BFQQ_FNS
/* Logging facilities. */
@@ -3938,13 +3978,21 @@ static void bfq_update_bfqq_wr_on_rq_arrival(struct bfq_data *bfqd,
struct bfq_queue *bfqq,
unsigned int old_wr_coeff,
bool wr_or_deserves_wr,
- bool interactive)
+ bool interactive,
+ bool soft_rt)
{
if (old_wr_coeff == 1 && wr_or_deserves_wr) {
/* start a weight-raising period */
- bfqq->wr_coeff = bfqd->bfq_wr_coeff;
- /* update wr duration */
- bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+ if (interactive) {
+ bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+ bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+ } else {
+ bfqq->wr_start_at_switch_to_srt = jiffies;
+ bfqq->wr_coeff = bfqd->bfq_wr_coeff *
+ BFQ_SOFTRT_WEIGHT_FACTOR;
+ bfqq->wr_cur_max_time =
+ bfqd->bfq_wr_rt_max_time;
+ }
/*
* If needed, further reduce budget to make sure it is
@@ -3959,8 +4007,51 @@ static void bfq_update_bfqq_wr_on_rq_arrival(struct bfq_data *bfqd,
bfqq->entity.budget,
2 * bfq_min_budget(bfqd));
} else if (old_wr_coeff > 1) {
- /* update wr duration */
- bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+ if (interactive) { /* update wr coeff and duration */
+ bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+ bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+ } else if (soft_rt) {
+ /*
+ * The application is now or still meeting the
+ * requirements for being deemed soft rt. We
+ * can then 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.
+ */
+ if (bfqq->wr_cur_max_time !=
+ bfqd->bfq_wr_rt_max_time) {
+ bfqq->wr_start_at_switch_to_srt =
+ bfqq->last_wr_start_finish;
+
+ bfqq->wr_cur_max_time =
+ bfqd->bfq_wr_rt_max_time;
+ bfqq->wr_coeff = bfqd->bfq_wr_coeff *
+ BFQ_SOFTRT_WEIGHT_FACTOR;
+ }
+ bfqq->last_wr_start_finish = jiffies;
+ }
}
}
@@ -3979,7 +4070,7 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
struct request *rq,
bool *interactive)
{
- bool wr_or_deserves_wr, bfqq_wants_to_preempt,
+ bool soft_rt, wr_or_deserves_wr, bfqq_wants_to_preempt,
idle_for_long_time = bfq_bfqq_idle_for_long_time(bfqd, bfqq),
/*
* See the comments on
@@ -3995,12 +4086,14 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
/*
* bfqq deserves to be weight-raised if:
* - it is sync,
- * - it has been idle for enough time.
+ * - it has been idle for enough time or is soft real-time.
*/
+ soft_rt = bfqd->bfq_wr_max_softrt_rate > 0 &&
+ time_is_before_jiffies(bfqq->soft_rt_next_start);
*interactive = idle_for_long_time;
wr_or_deserves_wr = bfqd->low_latency &&
(bfqq->wr_coeff > 1 ||
- (bfq_bfqq_sync(bfqq) && *interactive));
+ (bfq_bfqq_sync(bfqq) && (*interactive || soft_rt)));
/*
* Using the last flag, update budget and check whether bfqq
@@ -4025,12 +4118,17 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
bfq_update_bfqq_wr_on_rq_arrival(bfqd, bfqq,
old_wr_coeff,
wr_or_deserves_wr,
- *interactive);
+ *interactive,
+ soft_rt);
if (old_wr_coeff != bfqq->wr_coeff)
bfqq->entity.prio_changed = 1;
}
+ bfqq->last_idle_bklogged = jiffies;
+ bfqq->service_from_backlogged = 0;
+ bfq_clear_bfqq_softrt_update(bfqq);
+
bfq_add_bfqq_busy(bfqd, bfqq);
/*
@@ -4044,7 +4142,7 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
* function bfq_bfqq_update_budg_for_activation).
*/
if (bfqd->in_service_queue && bfqq_wants_to_preempt &&
- bfqd->in_service_queue->wr_coeff == 1 &&
+ bfqd->in_service_queue->wr_coeff < bfqq->wr_coeff &&
next_queue_may_preempt(bfqd))
bfq_bfqq_expire(bfqd, bfqd->in_service_queue,
false, BFQ_BFQQ_PREEMPTED);
@@ -4107,6 +4205,12 @@ static void bfq_add_request(struct request *rq)
* period must start or restart (this case is considered
* separately because it is not detected by the above
* conditions, if bfqq is already weight-raised)
+ *
+ * last_wr_start_finish has to be updated also if bfqq is soft
+ * real-time, because the weight-raising period is constantly
+ * restarted on idle-to-busy transitions for these queues, but
+ * this is already done in bfq_bfqq_handle_idle_busy_switch if
+ * needed.
*/
if (bfqd->low_latency &&
(old_wr_coeff == 1 || bfqq->wr_coeff == 1 || interactive))
@@ -4326,6 +4430,7 @@ static void bfq_bfqq_end_wr(struct bfq_queue *bfqq)
{
bfqq->wr_coeff = 1;
bfqq->wr_cur_max_time = 0;
+ bfqq->last_wr_start_finish = jiffies;
/*
* Trigger a weight change on the next invocation of
* __bfq_entity_update_weight_prio.
@@ -4393,11 +4498,17 @@ static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
static void bfq_set_budget_timeout(struct bfq_data *bfqd,
struct bfq_queue *bfqq)
{
+ unsigned int timeout_coeff;
+
+ if (bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time)
+ timeout_coeff = 1;
+ else
+ timeout_coeff = bfqq->entity.weight / bfqq->entity.orig_weight;
+
bfqd->last_budget_start = ktime_get();
bfqq->budget_timeout = jiffies +
- bfqd->bfq_timeout *
- (bfqq->entity.weight / bfqq->entity.orig_weight);
+ bfqd->bfq_timeout * timeout_coeff;
}
static void __bfq_set_in_service_queue(struct bfq_data *bfqd,
@@ -4409,6 +4520,42 @@ static void __bfq_set_in_service_queue(struct bfq_data *bfqd,
bfqd->budgets_assigned = (bfqd->budgets_assigned*7 + 256) / 8;
+ if (time_is_before_jiffies(bfqq->last_wr_start_finish) &&
+ bfqq->wr_coeff > 1 &&
+ bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time &&
+ time_is_before_jiffies(bfqq->budget_timeout)) {
+ /*
+ * For soft real-time queues, move the start
+ * of the weight-raising period forward by the
+ * time the queue has not received any
+ * service. Otherwise, a relatively long
+ * service delay is likely to cause the
+ * weight-raising period of the queue to end,
+ * because of the short duration of the
+ * weight-raising period of a soft real-time
+ * queue. It is worth noting that this move
+ * is not so dangerous for the other queues,
+ * because soft real-time queues are not
+ * greedy.
+ *
+ * To not add a further variable, we use the
+ * overloaded field budget_timeout to
+ * determine for how long the queue has not
+ * received service, i.e., how much time has
+ * elapsed since the queue expired. However,
+ * this is a little imprecise, because
+ * budget_timeout is set to jiffies if bfqq
+ * not only expires, but also remains with no
+ * request.
+ */
+ if (time_after(bfqq->budget_timeout,
+ bfqq->last_wr_start_finish))
+ bfqq->last_wr_start_finish +=
+ jiffies - bfqq->budget_timeout;
+ else
+ bfqq->last_wr_start_finish = jiffies;
+ }
+
bfq_set_budget_timeout(bfqd, bfqq);
bfq_log_bfqq(bfqd, bfqq,
"set_in_service_queue, cur-budget = %d",
@@ -5026,6 +5173,76 @@ static bool bfq_bfqq_is_slow(struct bfq_data *bfqd, struct bfq_queue *bfqq,
}
/*
+ * To be deemed as soft real-time, an application must meet two
+ * requirements. First, 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 issuing new requests until all its pending requests
+ * have been completed. After that, the application may issue 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 the CPU load is high. In fact, the application may
+ * stop issuing requests while the CPUs are busy serving other processes,
+ * then restart, then stop 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 (e.g., because the request pattern is random
+ * and/or the device is slow), then the application may meet the above
+ * bandwidth requirement 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).
+ *
+ * Unfortunately, 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 cases occur:
+ * 1) HZ is so low that the duration of a jiffy 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 unsigned long 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_wr_max_softrt_rate,
+ jiffies + nsecs_to_jiffies(bfqq->bfqd->bfq_slice_idle) + 4);
+}
+
+/*
+ * Return the farthest future time instant according to jiffies
+ * macros.
+ */
+static unsigned long bfq_greatest_from_now(void)
+{
+ return jiffies + MAX_JIFFY_OFFSET;
+}
+
+/*
* Return the farthest past time instant according to jiffies
* macros.
*/
@@ -5075,6 +5292,17 @@ static void bfq_bfqq_expire(struct bfq_data *bfqd,
slow = bfq_bfqq_is_slow(bfqd, bfqq, compensate, reason, &delta);
/*
+ * Increase service_from_backlogged before next statement,
+ * because the possible next invocation of
+ * bfq_bfqq_charge_time would likely inflate
+ * entity->service. In contrast, service_from_backlogged must
+ * contain real service, to enable the soft real-time
+ * heuristic to correctly compute the bandwidth consumed by
+ * bfqq.
+ */
+ bfqq->service_from_backlogged += entity->service;
+
+ /*
* As above explained, charge slow (typically seeky) and
* timed-out queues with the time and not the service
* received, to favor sequential workloads.
@@ -5102,6 +5330,48 @@ static void bfq_bfqq_expire(struct bfq_data *bfqd,
if (bfqd->low_latency && bfqq->wr_coeff == 1)
bfqq->last_wr_start_finish = jiffies;
+ if (bfqd->low_latency && bfqd->bfq_wr_max_softrt_rate > 0 &&
+ RB_EMPTY_ROOT(&bfqq->sort_list)) {
+ /*
+ * If we get here, and there are no outstanding
+ * requests, then the request pattern is isochronous
+ * (see the comments on the function
+ * bfq_bfqq_softrt_next_start()). Thus we can compute
+ * soft_rt_next_start. If, instead, the queue still
+ * has outstanding requests, then we have to wait for
+ * the completion of all the outstanding requests to
+ * discover whether the request pattern is actually
+ * isochronous.
+ */
+ if (bfqq->dispatched == 0)
+ bfqq->soft_rt_next_start =
+ bfq_bfqq_softrt_next_start(bfqd, bfqq);
+ else {
+ /*
+ * The application is still waiting for the
+ * completion of one or more requests:
+ * prevent it from possibly being incorrectly
+ * deemed as soft real-time by setting its
+ * soft_rt_next_start to infinity. In fact,
+ * without this assignment, the application
+ * would be incorrectly deemed as soft
+ * real-time if:
+ * 1) it issued a new request before the
+ * completion of all its in-flight
+ * requests, and
+ * 2) at that time, its soft_rt_next_start
+ * happened to be in the past.
+ */
+ bfqq->soft_rt_next_start =
+ bfq_greatest_from_now();
+ /*
+ * Schedule an update of soft_rt_next_start to when
+ * the task may be discovered to be isochronous.
+ */
+ bfq_mark_bfqq_softrt_update(bfqq);
+ }
+ }
+
bfq_log_bfqq(bfqd, bfqq,
"expire (%d, slow %d, num_disp %d, idle_win %d)", reason,
slow, bfqq->dispatched, bfq_bfqq_idle_window(bfqq));
@@ -5418,12 +5688,18 @@ static void bfq_update_wr_data(struct bfq_data *bfqd, struct bfq_queue *bfqq)
*/
if (time_is_before_jiffies(bfqq->last_wr_start_finish +
bfqq->wr_cur_max_time)) {
- bfqq->last_wr_start_finish = jiffies;
- bfq_log_bfqq(bfqd, bfqq,
- "wrais ending at %lu, rais_max_time %u",
- bfqq->last_wr_start_finish,
- jiffies_to_msecs(bfqq->wr_cur_max_time));
- bfq_bfqq_end_wr(bfqq);
+ if (bfqq->wr_cur_max_time != bfqd->bfq_wr_rt_max_time ||
+ time_is_before_jiffies(bfqq->wr_start_at_switch_to_srt +
+ bfq_wr_duration(bfqd)))
+ bfq_bfqq_end_wr(bfqq);
+ else {
+ /* switch back to interactive wr */
+ bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+ bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+ bfqq->last_wr_start_finish =
+ bfqq->wr_start_at_switch_to_srt;
+ bfqq->entity.prio_changed = 1;
+ }
}
}
/* Update weight both if it must be raised and if it must be lowered */
@@ -5765,6 +6041,13 @@ static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
bfqq->wr_coeff = 1;
bfqq->last_wr_start_finish = bfq_smallest_from_now();
+ bfqq->wr_start_at_switch_to_srt = bfq_smallest_from_now();
+
+ /*
+ * Set to the value for which bfqq will not be deemed as
+ * soft rt when it becomes backlogged.
+ */
+ bfqq->soft_rt_next_start = bfq_greatest_from_now();
/* first request is almost certainly seeky */
bfqq->seek_history = 1;
@@ -6122,6 +6405,20 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
bfqd->last_completion = now_ns;
/*
+ * If we are waiting to discover whether the request pattern
+ * of the task associated with the queue is actually
+ * isochronous, and both requisites for this condition to hold
+ * are now satisfied, then compute soft_rt_next_start (see the
+ * comments on the function bfq_bfqq_softrt_next_start()). We
+ * schedule this delayed check when bfqq expires, if it still
+ * has in-flight requests.
+ */
+ if (bfq_bfqq_softrt_update(bfqq) && bfqq->dispatched == 0 &&
+ 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.
*/
@@ -6440,9 +6737,16 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
* Trade-off between responsiveness and fairness.
*/
bfqd->bfq_wr_coeff = 30;
+ bfqd->bfq_wr_rt_max_time = msecs_to_jiffies(300);
bfqd->bfq_wr_max_time = 0;
bfqd->bfq_wr_min_idle_time = msecs_to_jiffies(2000);
bfqd->bfq_wr_min_inter_arr_async = msecs_to_jiffies(500);
+ bfqd->bfq_wr_max_softrt_rate = 7000; /*
+ * Approximate rate required
+ * to playback or record a
+ * high-definition compressed
+ * video.
+ */
/*
* Begin by assuming, optimistically, that the device is a
@@ -6590,9 +6894,11 @@ SHOW_FUNCTION(bfq_timeout_sync_show, bfqd->bfq_timeout, 1);
SHOW_FUNCTION(bfq_strict_guarantees_show, bfqd->strict_guarantees, 0);
SHOW_FUNCTION(bfq_low_latency_show, bfqd->low_latency, 0);
SHOW_FUNCTION(bfq_wr_coeff_show, bfqd->bfq_wr_coeff, 0);
+SHOW_FUNCTION(bfq_wr_rt_max_time_show, bfqd->bfq_wr_rt_max_time, 1);
SHOW_FUNCTION(bfq_wr_min_idle_time_show, bfqd->bfq_wr_min_idle_time, 1);
SHOW_FUNCTION(bfq_wr_min_inter_arr_async_show, bfqd->bfq_wr_min_inter_arr_async,
1);
+SHOW_FUNCTION(bfq_wr_max_softrt_rate_show, bfqd->bfq_wr_max_softrt_rate, 0);
#undef SHOW_FUNCTION
#define USEC_SHOW_FUNCTION(__FUNC, __VAR) \
@@ -6635,10 +6941,14 @@ STORE_FUNCTION(bfq_back_seek_penalty_store, &bfqd->bfq_back_penalty, 1,
STORE_FUNCTION(bfq_slice_idle_store, &bfqd->bfq_slice_idle, 0, INT_MAX, 2);
STORE_FUNCTION(bfq_wr_coeff_store, &bfqd->bfq_wr_coeff, 1, INT_MAX, 0);
STORE_FUNCTION(bfq_wr_max_time_store, &bfqd->bfq_wr_max_time, 0, INT_MAX, 1);
+STORE_FUNCTION(bfq_wr_rt_max_time_store, &bfqd->bfq_wr_rt_max_time, 0, INT_MAX,
+ 1);
STORE_FUNCTION(bfq_wr_min_idle_time_store, &bfqd->bfq_wr_min_idle_time, 0,
INT_MAX, 1);
STORE_FUNCTION(bfq_wr_min_inter_arr_async_store,
&bfqd->bfq_wr_min_inter_arr_async, 0, INT_MAX, 1);
+STORE_FUNCTION(bfq_wr_max_softrt_rate_store, &bfqd->bfq_wr_max_softrt_rate, 0,
+ INT_MAX, 0);
#undef STORE_FUNCTION
#define USEC_STORE_FUNCTION(__FUNC, __PTR, MIN, MAX) \
@@ -6758,8 +7068,10 @@ static struct elv_fs_entry bfq_attrs[] = {
BFQ_ATTR(low_latency),
BFQ_ATTR(wr_coeff),
BFQ_ATTR(wr_max_time),
+ BFQ_ATTR(wr_rt_max_time),
BFQ_ATTR(wr_min_idle_time),
BFQ_ATTR(wr_min_inter_arr_async),
+ BFQ_ATTR(wr_max_softrt_rate),
BFQ_ATTR(weights),
__ATTR_NULL
};
@@ -6812,7 +7124,7 @@ static struct blkcg_policy blkcg_policy_bfq = {
static int __init bfq_init(void)
{
int ret;
- char msg[50] = "BFQ I/O-scheduler: v1";
+ char msg[50] = "BFQ I/O-scheduler: v2";
#ifdef CONFIG_BFQ_GROUP_IOSCHED
ret = blkcg_policy_register(&blkcg_policy_bfq);
--
2.10.0
^ permalink raw reply related
* [PATCH RFC 06/14] block, bfq: improve responsiveness
From: Paolo Valente @ 2017-03-04 16:01 UTC (permalink / raw)
To: Jens Axboe, Tejun Heo
Cc: Fabio Checconi, Arianna Avanzini, linux-block, linux-kernel,
ulf.hansson, linus.walleij, broonie, Paolo Valente
In-Reply-To: <20170304160131.57366-1-paolo.valente@linaro.org>
This patch introduces a simple heuristic to load applications quickly,
and to perform the I/O requested by interactive applications just as
quickly. To this purpose, both a newly-created queue and a queue
associated with an interactive application (we explain in a moment how
BFQ decides whether the associated application is interactive),
receive the following two special treatments:
1) The weight of the queue is raised.
2) The queue unconditionally enjoys device idling when it empties; in
fact, if the requests of a queue are sync, then performing device
idling for the queue is a necessary condition to guarantee that the
queue receives a fraction of the throughput proportional to its weight
(see [1] for details).
For brevity, we call just weight-raising the combination of these
two preferential treatments. For a newly-created queue,
weight-raising starts immediately and lasts for a time interval that:
1) depends on the device speed and type (rotational or
non-rotational), and 2) is equal to the time needed to load (start up)
a large-size application on that device, with cold caches and with no
additional workload.
Finally, as for guaranteeing a fast execution to interactive,
I/O-related tasks (such as opening a file), consider that any
interactive application blocks and waits for user input both after
starting up and after executing some task. After a while, the user may
trigger new operations, after which the application stops again, and
so on. Accordingly, the low-latency heuristic weight-raises again a
queue in case it becomes backlogged after being idle for a
sufficiently long (configurable) time. The weight-raising then lasts
for the same time as for a just-created queue.
According to our experiments, the combination of this low-latency
heuristic and of the improvements described in the previous patch
allows BFQ to guarantee a high application responsiveness.
[1] P. Valente, A. Avanzini, "Evolution of the BFQ Storage I/O
Scheduler", Proceedings of the First Workshop on Mobile System
Technologies (MST-2015), May 2015.
http://algogroup.unimore.it/people/paolo/disk_sched/mst-2015.pdf
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
---
Documentation/block/bfq-iosched.txt | 9 +
block/bfq-iosched.c | 782 ++++++++++++++++++++++++++++++++----
2 files changed, 710 insertions(+), 81 deletions(-)
diff --git a/Documentation/block/bfq-iosched.txt b/Documentation/block/bfq-iosched.txt
index 934cbe6..13b5248 100644
--- a/Documentation/block/bfq-iosched.txt
+++ b/Documentation/block/bfq-iosched.txt
@@ -374,6 +374,11 @@ default, low latency mode is enabled. If enabled, interactive and soft
real-time applications are privileged and experience a lower latency,
as explained in more detail in the description of how BFQ works.
+DO NOT enable this mode if you need full control on bandwidth
+distribution. In fact, if it is enabled, then BFQ automatically
+increases the bandwidth share of privileged applications, as the main
+means to guarantee a lower latency to them.
+
timeout_sync
------------
@@ -506,6 +511,10 @@ linear mapping between ioprio and weights, described at the beginning
of the tunable section, is still valid, but all weights higher than
IOPRIO_BE_NR*10 are mapped to ioprio 0.
+Recall that, if low-latency is set, then BFQ automatically raises the
+weight of the queues associated with interactive and soft real-time
+applications. Unset this tunable if you need/want to control weights.
+
[1] P. Valente, A. Avanzini, "Evolution of the BFQ Storage I/O
Scheduler", Proceedings of the First Workshop on Mobile System
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index f38d062..98f0ddf 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -217,11 +217,11 @@ struct bfq_entity {
/* budget, used also to calculate F_i: F_i = S_i + @budget / @weight */
int budget;
- unsigned short weight; /* weight of the queue */
- unsigned short new_weight; /* next weight if a change is in progress */
+ unsigned int weight; /* weight of the queue */
+ unsigned int new_weight; /* next weight if a change is in progress */
/* original weight, used to implement weight boosting */
- unsigned short orig_weight;
+ unsigned int orig_weight;
/* parent entity, for hierarchical scheduling */
struct bfq_entity *parent;
@@ -320,6 +320,17 @@ struct bfq_queue {
/* pid of the process owning the queue, used for logging purposes */
pid_t pid;
+
+ /* current maximum weight-raising time for this queue */
+ unsigned long wr_cur_max_time;
+ /*
+ * Start time of the current weight-raising period if
+ * the @bfq-queue is being weight-raised, otherwise
+ * finish time of the last weight-raising period.
+ */
+ unsigned long last_wr_start_finish;
+ /* factor by which the weight of this queue is multiplied */
+ unsigned int wr_coeff;
};
/**
@@ -468,6 +479,34 @@ struct bfq_data {
*/
bool strict_guarantees;
+ /* if set to true, low-latency heuristics are enabled */
+ bool low_latency;
+ /*
+ * Maximum factor by which the weight of a weight-raised queue
+ * is multiplied.
+ */
+ unsigned int bfq_wr_coeff;
+ /* maximum duration of a weight-raising period (jiffies) */
+ unsigned int bfq_wr_max_time;
+ /*
+ * Minimum idle period after which weight-raising may be
+ * reactivated for a queue (in jiffies).
+ */
+ unsigned int bfq_wr_min_idle_time;
+ /*
+ * Minimum period between request arrivals after which
+ * weight-raising may be reactivated for an already busy async
+ * queue (in jiffies).
+ */
+ unsigned long bfq_wr_min_inter_arr_async;
+ /*
+ * Cached value of the product R*T, used for computing the
+ * maximum duration of weight raising automatically.
+ */
+ u64 RT_prod;
+ /* device-speed class for the low-latency heuristic */
+ enum bfq_device_speed device_speed;
+
/* fallback dummy bfqq for extreme OOM conditions */
struct bfq_queue oom_bfqq;
@@ -496,7 +535,6 @@ enum bfqq_state_flags {
BFQ_BFQQ_FLAG_fifo_expire, /* FIFO checked in this slice */
BFQ_BFQQ_FLAG_idle_window, /* slice idling enabled */
BFQ_BFQQ_FLAG_sync, /* synchronous queue */
- BFQ_BFQQ_FLAG_budget_new, /* no completion with this budget */
BFQ_BFQQ_FLAG_IO_bound, /*
* bfqq has timed-out at least once
* having consumed at most 2/10 of
@@ -524,7 +562,6 @@ BFQ_BFQQ_FNS(non_blocking_wait_rq);
BFQ_BFQQ_FNS(fifo_expire);
BFQ_BFQQ_FNS(idle_window);
BFQ_BFQQ_FNS(sync);
-BFQ_BFQQ_FNS(budget_new);
BFQ_BFQQ_FNS(IO_bound);
#undef BFQ_BFQQ_FNS
@@ -618,7 +655,7 @@ struct bfq_group_data {
/* must be the first member */
struct blkcg_policy_data pd;
- unsigned short weight;
+ unsigned int weight;
};
/**
@@ -713,6 +750,8 @@ static void bfq_put_queue(struct bfq_queue *bfqq);
static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
struct bio *bio, bool is_sync,
struct bfq_io_cq *bic);
+static void bfq_end_wr_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);
@@ -768,6 +807,56 @@ static struct kmem_cache *bfq_pool;
/* Shift used for peak rate fixed precision calculations. */
#define BFQ_RATE_SHIFT 16
+/*
+ * By default, BFQ computes the duration of the weight raising for
+ * interactive applications automatically, using the following formula:
+ * duration = (R / r) * T, where r is the peak rate of the device, and
+ * R and T are two reference parameters.
+ * In particular, R is the peak rate of the reference device (see below),
+ * and T is a reference time: given the systems that are likely to be
+ * installed on the reference device according to its speed class, T is
+ * about the maximum time needed, under BFQ and while reading two files in
+ * parallel, to load typical large applications on these systems.
+ * In practice, the slower/faster the device at hand is, the more/less it
+ * takes to load applications with respect to the reference device.
+ * Accordingly, the longer/shorter BFQ grants weight raising to interactive
+ * applications.
+ *
+ * BFQ uses four different reference pairs (R, T), depending on:
+ * . whether the device is rotational or non-rotational;
+ * . whether the device is slow, such as old or portable HDDs, as well as
+ * SD cards, or fast, such as newer HDDs and SSDs.
+ *
+ * The device's speed class is dynamically (re)detected in
+ * bfq_update_peak_rate() every time the estimated peak rate is updated.
+ *
+ * In the following definitions, R_slow[0]/R_fast[0] and
+ * T_slow[0]/T_fast[0] are the reference values for a slow/fast
+ * rotational device, whereas R_slow[1]/R_fast[1] and
+ * T_slow[1]/T_fast[1] are the reference values for a slow/fast
+ * non-rotational device. Finally, device_speed_thresh are the
+ * thresholds used to switch between speed classes. The reference
+ * rates are not the actual peak rates of the devices used as a
+ * reference, but slightly lower values. The reason for using these
+ * slightly lower values is that the peak-rate estimator tends to
+ * yield slightly lower values than the actual peak rate (it can yield
+ * the actual peak rate only if there is only one process doing I/O,
+ * and the process does sequential I/O).
+ *
+ * Both the reference peak rates and the thresholds are measured in
+ * sectors/usec, left-shifted by BFQ_RATE_SHIFT.
+ */
+static int R_slow[2] = {1000, 10700};
+static int R_fast[2] = {14000, 33000};
+/*
+ * To improve readability, a conversion function is used to initialize the
+ * following arrays, which entails that they can be initialized only in a
+ * function.
+ */
+static int T_slow[2];
+static int T_fast[2];
+static int device_speed_thresh[2];
+
#define BFQ_SERVICE_TREE_INIT ((struct bfq_service_tree) \
{ RB_ROOT, RB_ROOT, NULL, NULL, 0, 0 })
@@ -1453,7 +1542,7 @@ __bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
if (entity->prio_changed) {
struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
- unsigned short prev_weight, new_weight;
+ unsigned int prev_weight, new_weight;
struct bfq_data *bfqd = NULL;
#ifdef CONFIG_BFQ_GROUP_IOSCHED
struct bfq_sched_data *sd;
@@ -1502,7 +1591,8 @@ __bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
new_st = bfq_entity_service_tree(entity);
prev_weight = entity->weight;
- new_weight = entity->orig_weight;
+ new_weight = entity->orig_weight *
+ (bfqq ? bfqq->wr_coeff : 1);
entity->weight = new_weight;
new_st->wsum += entity->weight;
@@ -1597,6 +1687,8 @@ static void bfq_update_fin_time_enqueue(struct bfq_entity *entity,
struct bfq_service_tree *st,
bool backshifted)
{
+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
st = __bfq_entity_update_weight_prio(st, entity);
bfq_calc_finish(entity, entity->budget);
@@ -1626,10 +1718,19 @@ static void bfq_update_fin_time_enqueue(struct bfq_entity *entity,
* time. This may introduce a little unfairness among queues
* with backshifted timestamps, but it does not break
* worst-case fairness guarantees.
+ *
+ * As a special case, if bfqq is weight-raised, push up
+ * timestamps much less, to keep very low the probability that
+ * this push up causes the backshifted finish timestamps of
+ * weight-raised queues to become higher than the backshifted
+ * finish timestamps of non weight-raised queues.
*/
if (backshifted && bfq_gt(st->vtime, entity->finish)) {
unsigned long delta = st->vtime - entity->finish;
+ if (bfqq)
+ delta /= bfqq->wr_coeff;
+
entity->start += delta;
entity->finish += delta;
}
@@ -3021,6 +3122,18 @@ static void bfq_pd_offline(struct blkg_policy_data *pd)
bfqg_stats_xfer_dead(bfqg);
}
+static void bfq_end_wr_async(struct bfq_data *bfqd)
+{
+ struct blkcg_gq *blkg;
+
+ list_for_each_entry(blkg, &bfqd->queue->blkg_list, q_node) {
+ struct bfq_group *bfqg = blkg_to_bfqg(blkg);
+
+ bfq_end_wr_async_queues(bfqd, bfqg);
+ }
+ bfq_end_wr_async_queues(bfqd, bfqd->root_group);
+}
+
static int bfq_io_show_weight(struct seq_file *sf, void *v)
{
struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
@@ -3384,6 +3497,11 @@ static void bfq_init_entity(struct bfq_entity *entity,
static void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio) {}
+static void bfq_end_wr_async(struct bfq_data *bfqd)
+{
+ bfq_end_wr_async_queues(bfqd, bfqd->root_group);
+}
+
static struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
struct blkcg *blkcg)
{
@@ -3564,7 +3682,7 @@ static struct request *bfq_find_next_rq(struct bfq_data *bfqd,
static unsigned long bfq_serv_to_charge(struct request *rq,
struct bfq_queue *bfqq)
{
- if (bfq_bfqq_sync(bfqq))
+ if (bfq_bfqq_sync(bfqq) || bfqq->wr_coeff > 1)
return blk_rq_sectors(rq);
return blk_rq_sectors(rq) * bfq_async_charge_factor;
@@ -3651,12 +3769,12 @@ static void bfq_bfqq_expire(struct bfq_data *bfqd,
* whether the in-service queue should be expired, by returning
* true. The purpose of expiring the in-service queue is to give bfqq
* the chance to possibly preempt the in-service queue, and the reason
- * for preempting the in-service queue is to achieve the following
- * goal: guarantee to bfqq its reserved bandwidth even if bfqq has
- * expired because it has remained idle.
+ * for preempting the in-service queue is to achieve one of the two
+ * goals below.
*
- * In particular, bfqq may have expired for one of the following two
- * reasons:
+ * 1. Guarantee to bfqq its reserved bandwidth even if bfqq has
+ * expired because it has remained idle. In particular, bfqq may have
+ * expired for one of the following two reasons:
*
* - BFQ_BFQQ_NO_MORE_REQUESTS bfqq did not enjoy any device idling
* and did not make it to issue a new request before its last
@@ -3720,10 +3838,36 @@ static void bfq_bfqq_expire(struct bfq_data *bfqd,
* above-described special way, and signals that the in-service queue
* should be expired. Timestamp back-shifting is done later in
* __bfq_activate_entity.
+ *
+ * 2. Reduce latency. Even if timestamps are not backshifted to let
+ * the process associated with bfqq recover a service hole, bfqq may
+ * however happen to have, after being (re)activated, a lower finish
+ * timestamp than the in-service queue. That is, the next budget of
+ * bfqq may have to be completed before the one of the in-service
+ * queue. If this is the case, then preempting the in-service queue
+ * allows this goal to be achieved, apart from the unpreemptible,
+ * outstanding requests mentioned above.
+ *
+ * Unfortunately, regardless of which of the above two goals one wants
+ * to achieve, service trees need first to be updated to know whether
+ * the in-service queue must be preempted. To have service trees
+ * correctly updated, the in-service queue must be expired and
+ * rescheduled, and bfqq must be scheduled too. This is one of the
+ * most costly operations (in future versions, the scheduling
+ * mechanism may be re-designed in such a way to make it possible to
+ * know whether preemption is needed without needing to update service
+ * trees). In addition, queue preemptions almost always cause random
+ * I/O, and thus loss of throughput. Because of these facts, the next
+ * function adopts the following simple scheme to avoid both costly
+ * operations and too frequent preemptions: it requests the expiration
+ * of the in-service queue (unconditionally) only for queues that need
+ * to recover a hole, or that either are weight-raised or deserve to
+ * be weight-raised.
*/
static bool bfq_bfqq_update_budg_for_activation(struct bfq_data *bfqd,
struct bfq_queue *bfqq,
- bool arrived_in_time)
+ bool arrived_in_time,
+ bool wr_or_deserves_wr)
{
struct bfq_entity *entity = &bfqq->entity;
@@ -3758,14 +3902,85 @@ static bool bfq_bfqq_update_budg_for_activation(struct bfq_data *bfqd,
entity->budget = max_t(unsigned long, bfqq->max_budget,
bfq_serv_to_charge(bfqq->next_rq, bfqq));
bfq_clear_bfqq_non_blocking_wait_rq(bfqq);
- return false;
+ return wr_or_deserves_wr;
+}
+
+static unsigned int bfq_wr_duration(struct bfq_data *bfqd)
+{
+ u64 dur;
+
+ if (bfqd->bfq_wr_max_time > 0)
+ return bfqd->bfq_wr_max_time;
+
+ dur = bfqd->RT_prod;
+ do_div(dur, bfqd->peak_rate);
+
+ /*
+ * Limit duration between 3 and 13 seconds. Tests show that
+ * higher values than 13 seconds often yield the opposite of
+ * the desired result, i.e., worsen responsiveness by letting
+ * non-interactive and non-soft-real-time applications
+ * preserve weight raising for a too long time interval.
+ *
+ * On the other end, lower values than 3 seconds make it
+ * difficult for most interactive tasks to complete their jobs
+ * before weight-raising finishes.
+ */
+ if (dur > msecs_to_jiffies(13000))
+ dur = msecs_to_jiffies(13000);
+ else if (dur < msecs_to_jiffies(3000))
+ dur = msecs_to_jiffies(3000);
+
+ return dur;
+}
+
+static void bfq_update_bfqq_wr_on_rq_arrival(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq,
+ unsigned int old_wr_coeff,
+ bool wr_or_deserves_wr,
+ bool interactive)
+{
+ if (old_wr_coeff == 1 && wr_or_deserves_wr) {
+ /* start a weight-raising period */
+ bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+ /* update wr duration */
+ bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+
+ /*
+ * If needed, further reduce budget to make sure it is
+ * close to bfqq's backlog, so as to reduce the
+ * scheduling-error component due to a too large
+ * budget. Do not care about throughput consequences,
+ * but only about latency. Finally, do not assign a
+ * too small budget either, to avoid increasing
+ * latency by causing too frequent expirations.
+ */
+ bfqq->entity.budget = min_t(unsigned long,
+ bfqq->entity.budget,
+ 2 * bfq_min_budget(bfqd));
+ } else if (old_wr_coeff > 1) {
+ /* update wr duration */
+ bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+ }
+}
+
+static bool bfq_bfqq_idle_for_long_time(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq)
+{
+ return bfqq->dispatched == 0 &&
+ time_is_before_jiffies(
+ bfqq->budget_timeout +
+ bfqd->bfq_wr_min_idle_time);
}
static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
struct bfq_queue *bfqq,
- struct request *rq)
+ int old_wr_coeff,
+ struct request *rq,
+ bool *interactive)
{
- bool bfqq_wants_to_preempt,
+ bool wr_or_deserves_wr, bfqq_wants_to_preempt,
+ idle_for_long_time = bfq_bfqq_idle_for_long_time(bfqd, bfqq),
/*
* See the comments on
* bfq_bfqq_update_budg_for_activation for
@@ -3778,12 +3993,23 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
bfqg_stats_update_io_add(bfqq_group(RQ_BFQQ(rq)), bfqq, rq->cmd_flags);
/*
- * Update budget and check whether bfqq may want to preempt
- * the in-service queue.
+ * bfqq deserves to be weight-raised if:
+ * - it is sync,
+ * - it has been idle for enough time.
+ */
+ *interactive = idle_for_long_time;
+ wr_or_deserves_wr = bfqd->low_latency &&
+ (bfqq->wr_coeff > 1 ||
+ (bfq_bfqq_sync(bfqq) && *interactive));
+
+ /*
+ * Using the last flag, update budget and check whether bfqq
+ * may want to preempt the in-service queue.
*/
bfqq_wants_to_preempt =
bfq_bfqq_update_budg_for_activation(bfqd, bfqq,
- arrived_in_time);
+ arrived_in_time,
+ wr_or_deserves_wr);
if (!bfq_bfqq_IO_bound(bfqq)) {
if (arrived_in_time) {
@@ -3795,6 +4021,16 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
bfqq->requests_within_timer = 0;
}
+ if (bfqd->low_latency) {
+ bfq_update_bfqq_wr_on_rq_arrival(bfqd, bfqq,
+ old_wr_coeff,
+ wr_or_deserves_wr,
+ *interactive);
+
+ if (old_wr_coeff != bfqq->wr_coeff)
+ bfqq->entity.prio_changed = 1;
+ }
+
bfq_add_bfqq_busy(bfqd, bfqq);
/*
@@ -3808,6 +4044,7 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
* function bfq_bfqq_update_budg_for_activation).
*/
if (bfqd->in_service_queue && bfqq_wants_to_preempt &&
+ bfqd->in_service_queue->wr_coeff == 1 &&
next_queue_may_preempt(bfqd))
bfq_bfqq_expire(bfqd, bfqd->in_service_queue,
false, BFQ_BFQQ_PREEMPTED);
@@ -3818,6 +4055,8 @@ static void bfq_add_request(struct request *rq)
struct bfq_queue *bfqq = RQ_BFQQ(rq);
struct bfq_data *bfqd = bfqq->bfqd;
struct request *next_rq, *prev;
+ unsigned int old_wr_coeff = bfqq->wr_coeff;
+ bool interactive = false;
bfq_log_bfqq(bfqd, bfqq, "add_request %d", rq_is_sync(rq));
bfqq->queued[rq_is_sync(rq)]++;
@@ -3833,9 +4072,45 @@ static void bfq_add_request(struct request *rq)
bfqq->next_rq = next_rq;
if (!bfq_bfqq_busy(bfqq)) /* switching to busy ... */
- bfq_bfqq_handle_idle_busy_switch(bfqd, bfqq, rq);
- else if (prev != bfqq->next_rq)
- bfq_updated_next_req(bfqd, bfqq);
+ bfq_bfqq_handle_idle_busy_switch(bfqd, bfqq, old_wr_coeff,
+ rq, &interactive);
+ else {
+ if (bfqd->low_latency && old_wr_coeff == 1 && !rq_is_sync(rq) &&
+ time_is_before_jiffies(
+ bfqq->last_wr_start_finish +
+ bfqd->bfq_wr_min_inter_arr_async)) {
+ bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+ bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+
+ bfqq->entity.prio_changed = 1;
+ }
+ if (prev != bfqq->next_rq)
+ bfq_updated_next_req(bfqd, bfqq);
+ }
+
+ /*
+ * Assign jiffies to last_wr_start_finish in the following
+ * cases:
+ *
+ * . if bfqq is not going to be weight-raised, because, for
+ * non weight-raised queues, last_wr_start_finish stores the
+ * arrival time of the last request; as of now, this piece
+ * of information is used only for deciding whether to
+ * weight-raise async queues
+ *
+ * . if bfqq is not weight-raised, because, if bfqq is now
+ * switching to weight-raised, then last_wr_start_finish
+ * stores the time when weight-raising starts
+ *
+ * . if bfqq is interactive, because, regardless of whether
+ * bfqq is currently weight-raised, the weight-raising
+ * period must start or restart (this case is considered
+ * separately because it is not detected by the above
+ * conditions, if bfqq is already weight-raised)
+ */
+ if (bfqd->low_latency &&
+ (old_wr_coeff == 1 || bfqq->wr_coeff == 1 || interactive))
+ bfqq->last_wr_start_finish = jiffies;
}
static struct request *bfq_find_rq_fmerge(struct bfq_data *bfqd,
@@ -4046,6 +4321,46 @@ static void bfq_requests_merged(struct request_queue *q, struct request *rq,
bfqg_stats_update_io_merged(bfqq_group(bfqq), next->cmd_flags);
}
+/* Must be called with bfqq != NULL */
+static void bfq_bfqq_end_wr(struct bfq_queue *bfqq)
+{
+ bfqq->wr_coeff = 1;
+ bfqq->wr_cur_max_time = 0;
+ /*
+ * Trigger a weight change on the next invocation of
+ * __bfq_entity_update_weight_prio.
+ */
+ bfqq->entity.prio_changed = 1;
+}
+
+static void bfq_end_wr_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])
+ bfq_bfqq_end_wr(bfqg->async_bfqq[i][j]);
+ if (bfqg->async_idle_bfqq)
+ bfq_bfqq_end_wr(bfqg->async_idle_bfqq);
+}
+
+static void bfq_end_wr(struct bfq_data *bfqd)
+{
+ struct bfq_queue *bfqq;
+
+ spin_lock_irq(&bfqd->lock);
+
+ list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list)
+ bfq_bfqq_end_wr(bfqq);
+ list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list)
+ bfq_bfqq_end_wr(bfqq);
+ bfq_end_wr_async(bfqd);
+
+ spin_unlock_irq(&bfqd->lock);
+}
+
static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
struct bio *bio)
{
@@ -4069,16 +4384,32 @@ static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
return bfqq == RQ_BFQQ(rq);
}
+/*
+ * Set the maximum time for the in-service queue to consume its
+ * budget. This prevents seeky processes from lowering the throughput.
+ * In practice, a time-slice service scheme is used with seeky
+ * processes.
+ */
+static void bfq_set_budget_timeout(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq)
+{
+ bfqd->last_budget_start = ktime_get();
+
+ bfqq->budget_timeout = jiffies +
+ bfqd->bfq_timeout *
+ (bfqq->entity.weight / bfqq->entity.orig_weight);
+}
+
static void __bfq_set_in_service_queue(struct bfq_data *bfqd,
struct bfq_queue *bfqq)
{
if (bfqq) {
bfqg_stats_update_avg_queue_size(bfqq_group(bfqq));
- bfq_mark_bfqq_budget_new(bfqq);
bfq_clear_bfqq_fifo_expire(bfqq);
bfqd->budgets_assigned = (bfqd->budgets_assigned*7 + 256) / 8;
+ bfq_set_budget_timeout(bfqd, bfqq);
bfq_log_bfqq(bfqd, bfqq,
"set_in_service_queue, cur-budget = %d",
bfqq->entity.budget);
@@ -4118,9 +4449,13 @@ static void bfq_arm_slice_timer(struct bfq_data *bfqd)
*/
sl = bfqd->bfq_slice_idle;
/*
- * Grant only minimum idle time if the queue is seeky.
+ * Unless the queue is being weight-raised, grant only minimum
+ * idle time if the queue is seeky. A long idling is preserved
+ * for a weight-raised queue, because it is needed for
+ * guaranteeing to the queue its reserved share of the
+ * throughput.
*/
- if (BFQQ_SEEKY(bfqq))
+ if (BFQQ_SEEKY(bfqq) && bfqq->wr_coeff == 1)
sl = min_t(u64, sl, BFQ_MIN_TT);
bfqd->last_idling_start = ktime_get();
@@ -4130,27 +4465,6 @@ static void bfq_arm_slice_timer(struct bfq_data *bfqd)
}
/*
- * 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 = 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 * timeout_coeff;
-
- bfq_log_bfqq(bfqd, bfqq, "set budget_timeout %u",
- jiffies_to_msecs(bfqd->bfq_timeout * timeout_coeff));
-}
-
-/*
* In autotuning mode, max_budget is dynamically recomputed as the
* amount of sectors transferred in timeout at the estimated peak
* rate. This enables BFQ to utilize a full timeslice with a full
@@ -4163,6 +4477,42 @@ static unsigned long bfq_calc_max_budget(struct bfq_data *bfqd)
jiffies_to_msecs(bfqd->bfq_timeout)>>BFQ_RATE_SHIFT;
}
+/*
+ * Update parameters related to throughput and responsiveness, as a
+ * function of the estimated peak rate. See comments on
+ * bfq_calc_max_budget(), and on T_slow and T_fast arrays.
+ */
+static void update_thr_responsiveness_params(struct bfq_data *bfqd)
+{
+ int dev_type = blk_queue_nonrot(bfqd->queue);
+
+ if (bfqd->bfq_user_max_budget == 0)
+ bfqd->bfq_max_budget =
+ bfq_calc_max_budget(bfqd);
+
+ if (bfqd->device_speed == BFQ_BFQD_FAST &&
+ bfqd->peak_rate < device_speed_thresh[dev_type]) {
+ bfqd->device_speed = BFQ_BFQD_SLOW;
+ bfqd->RT_prod = R_slow[dev_type] *
+ T_slow[dev_type];
+ } else if (bfqd->device_speed == BFQ_BFQD_SLOW &&
+ bfqd->peak_rate > device_speed_thresh[dev_type]) {
+ bfqd->device_speed = BFQ_BFQD_FAST;
+ bfqd->RT_prod = R_fast[dev_type] *
+ T_fast[dev_type];
+ }
+
+ bfq_log(bfqd,
+"dev_type %s dev_speed_class = %s (%llu sects/sec), thresh %llu setcs/sec",
+ dev_type == 0 ? "ROT" : "NONROT",
+ bfqd->device_speed == BFQ_BFQD_FAST ? "FAST" : "SLOW",
+ bfqd->device_speed == BFQ_BFQD_FAST ?
+ (USEC_PER_SEC*(u64)R_fast[dev_type])>>BFQ_RATE_SHIFT :
+ (USEC_PER_SEC*(u64)R_slow[dev_type])>>BFQ_RATE_SHIFT,
+ (USEC_PER_SEC*(u64)device_speed_thresh[dev_type])>>
+ BFQ_RATE_SHIFT);
+}
+
static void bfq_reset_rate_computation(struct bfq_data *bfqd,
struct request *rq)
{
@@ -4274,9 +4624,7 @@ static void bfq_update_rate_reset(struct bfq_data *bfqd, struct request *rq)
rate /= divisor; /* smoothing constant alpha = 1/divisor */
bfqd->peak_rate += rate;
- if (bfqd->bfq_user_max_budget == 0)
- bfqd->bfq_max_budget =
- bfq_calc_max_budget(bfqd);
+ update_thr_responsiveness_params(bfqd);
reset_computation:
bfq_reset_rate_computation(bfqd, rq);
@@ -4398,9 +4746,18 @@ static void bfq_dispatch_remove(struct request_queue *q, struct request *rq)
static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
{
- if (RB_EMPTY_ROOT(&bfqq->sort_list))
+ if (RB_EMPTY_ROOT(&bfqq->sort_list)) {
+ if (bfqq->dispatched == 0)
+ /*
+ * Overloading budget_timeout field to store
+ * the time at which the queue remains with no
+ * backlog and no outstanding request; used by
+ * the weight-raising mechanism.
+ */
+ bfqq->budget_timeout = jiffies;
+
bfq_del_bfqq_busy(bfqd, bfqq, true);
- else
+ } else
bfq_requeue_bfqq(bfqd, bfqq);
/*
@@ -4427,9 +4784,18 @@ static void __bfq_bfqq_recalc_budget(struct bfq_data *bfqd,
struct request *next_rq;
int budget, min_budget;
- budget = bfqq->max_budget;
min_budget = bfq_min_budget(bfqd);
+ if (bfqq->wr_coeff == 1)
+ budget = bfqq->max_budget;
+ else /*
+ * Use a constant, low budget for weight-raised queues,
+ * to help achieve a low latency. Keep it slightly higher
+ * than the minimum possible budget, to cause a little
+ * bit fewer expirations.
+ */
+ budget = 2 * min_budget;
+
bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last budg %d, budg left %d",
bfqq->entity.budget, bfq_bfqq_budget_left(bfqq));
bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last max_budg %d, min budg %d",
@@ -4437,7 +4803,7 @@ static void __bfq_bfqq_recalc_budget(struct bfq_data *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)) {
+ if (bfq_bfqq_sync(bfqq) && bfqq->wr_coeff == 1) {
switch (reason) {
/*
* Caveat: in all the following cases we trade latency
@@ -4536,7 +4902,7 @@ static void __bfq_bfqq_recalc_budget(struct bfq_data *bfqd,
default:
return;
}
- } else
+ } else if (!bfq_bfqq_sync(bfqq))
/*
* Async queues get always the maximum possible
* budget, as for them we do not care about latency
@@ -4723,15 +5089,19 @@ static void bfq_bfqq_expire(struct bfq_data *bfqd,
* bandwidth, and not time, distribution with little unlucky
* or quasi-sequential processes.
*/
- if (slow ||
- (reason == BFQ_BFQQ_BUDGET_TIMEOUT &&
- bfq_bfqq_budget_left(bfqq) >= entity->budget / 3))
+ if (bfqq->wr_coeff == 1 &&
+ (slow ||
+ (reason == BFQ_BFQQ_BUDGET_TIMEOUT &&
+ bfq_bfqq_budget_left(bfqq) >= entity->budget / 3)))
bfq_bfqq_charge_time(bfqd, bfqq, delta);
if (reason == BFQ_BFQQ_TOO_IDLE &&
entity->service <= 2 * entity->budget / 10)
bfq_clear_bfqq_IO_bound(bfqq);
+ if (bfqd->low_latency && bfqq->wr_coeff == 1)
+ bfqq->last_wr_start_finish = jiffies;
+
bfq_log_bfqq(bfqd, bfqq,
"expire (%d, slow %d, num_disp %d, idle_win %d)", reason,
slow, bfqq->dispatched, bfq_bfqq_idle_window(bfqq));
@@ -4756,10 +5126,7 @@ static void bfq_bfqq_expire(struct bfq_data *bfqd,
*/
static bool bfq_bfqq_budget_timeout(struct bfq_queue *bfqq)
{
- if (bfq_bfqq_budget_new(bfqq) ||
- time_before(jiffies, bfqq->budget_timeout))
- return false;
- return true;
+ return time_is_before_eq_jiffies(bfqq->budget_timeout);
}
/*
@@ -4786,19 +5153,40 @@ static bool bfq_may_expire_for_budg_timeout(struct bfq_queue *bfqq)
/*
* For a queue that becomes empty, device idling is allowed only if
- * this function returns true for the queue. And this function returns
- * true only if idling is beneficial for throughput.
+ * this function returns true for the queue. As a consequence, since
+ * device idling plays a critical role in both throughput boosting and
+ * service guarantees, the return value of this function plays a
+ * critical role in both these aspects as well.
+ *
+ * In a nutshell, this function returns true only if idling is
+ * beneficial for throughput or, even if detrimental for throughput,
+ * idling is however necessary to preserve service guarantees (low
+ * latency, desired throughput distribution, ...). In particular, on
+ * NCQ-capable devices, this function tries to return false, so as to
+ * help keep the drives' internal queues full, whenever this helps the
+ * device boost the throughput without causing any service-guarantee
+ * issue.
+ *
+ * In more detail, the return value of this function is obtained by,
+ * first, computing a number of boolean variables that take into
+ * account throughput and service-guarantee issues, and, then,
+ * combining these variables in a logical expression. Most of the
+ * issues taken into account are not trivial. We discuss these issues
+ * individually while introducing the variables.
*/
static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
{
struct bfq_data *bfqd = bfqq->bfqd;
- bool idling_boosts_thr;
+ bool idling_boosts_thr, asymmetric_scenario;
if (bfqd->strict_guarantees)
return true;
/*
- * The value of the next variable is computed considering that
+ * The next variable takes into account the cases where idling
+ * boosts the throughput.
+ *
+ * The value of the variable is computed considering that
* idling is usually beneficial for the throughput if:
* (a) the device is not NCQ-capable, or
* (b) regardless of the presence of NCQ, the request pattern
@@ -4812,13 +5200,80 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
idling_boosts_thr = !bfqd->hw_tag || bfq_bfqq_IO_bound(bfqq);
/*
- * We have now the components we need to compute the return
- * value of the function, which is true only if both the
- * following conditions hold:
+ * There is then a case where idling must be performed not for
+ * throughput concerns, but to preserve service guarantees. To
+ * introduce it, we can note that allowing the drive to
+ * enqueue more than one request at a time, and hence
+ * delegating de facto final scheduling decisions to the
+ * drive's internal scheduler, causes loss of control on the
+ * actual request service order. In particular, the critical
+ * situation is when requests from different processes happens
+ * to be present, at the same time, in the internal queue(s)
+ * of the drive. In such a situation, the drive, by deciding
+ * the service order of the internally-queued requests, does
+ * determine also the actual throughput distribution among
+ * these processes. But the drive typically has no notion or
+ * concern about per-process throughput distribution, and
+ * makes its decisions only on a per-request basis. Therefore,
+ * the service distribution enforced by the drive's internal
+ * scheduler is likely to coincide with the desired
+ * device-throughput distribution only in a completely
+ * symmetric scenario where: (i) each of these processes must
+ * get the same throughput as the others; (ii) all these
+ * processes have the same I/O pattern (either sequential or
+ * random). In fact, in such a scenario, the drive will tend
+ * to treat the requests of each of these processes in about
+ * the same way as the requests of the others, and thus to
+ * provide each of these processes with about the same
+ * throughput (which is exactly the desired throughput
+ * distribution). In contrast, in any asymmetric scenario,
+ * device idling is certainly needed to guarantee that bfqq
+ * receives its assigned fraction of the device throughput
+ * (see [1] for details).
+ *
+ * As for sub-condition (i), actually we check only whether
+ * bfqq is being weight-raised. In fact, if bfqq is not being
+ * weight-raised, we have that:
+ * - if the process associated with bfqq is not I/O-bound, then
+ * it is not either latency- or throughput-critical; therefore
+ * idling is not needed for bfqq;
+ * - if the process asociated with bfqq is I/O-bound, then
+ * idling is already granted with bfqq (see the comments on
+ * idling_boosts_thr).
+ *
+ * We do not check sub-condition (ii) at all, i.e., the next
+ * variable is true if and only if bfqq is being
+ * weight-raised. We do not need to control sub-condition (ii)
+ * for the following reason:
+ * - if bfqq is being weight-raised, then idling is already
+ * guaranteed to bfqq by sub-condition (i);
+ * - if bfqq is not being weight-raised, then idling is
+ * already guaranteed to bfqq (only) if it matters, i.e., if
+ * bfqq is associated to a currently I/O-bound process (see
+ * the above comment on sub-condition (i)).
+ *
+ * As a side note, it is worth considering that the above
+ * device-idling countermeasures may however fail in the
+ * following unlucky scenario: if idling is (correctly)
+ * disabled in a time period during which the symmetry
+ * sub-condition holds, and hence the device is allowed to
+ * enqueue many requests, but at some later point in time some
+ * sub-condition stops to hold, then it may become impossible
+ * to let requests be served in the desired order until all
+ * the requests already queued in the device have been served.
+ */
+ asymmetric_scenario = bfqq->wr_coeff > 1;
+
+ /*
+ * We have now all the components we need to compute the return
+ * value of the function, which is true only if both the following
+ * conditions hold:
* 1) bfqq is sync, because idling make sense only for sync queues;
- * 2) idling boosts the throughput.
+ * 2) idling either boosts the throughput (without issues), or
+ * is necessary to preserve service guarantees.
*/
- return bfq_bfqq_sync(bfqq) && idling_boosts_thr;
+ return bfq_bfqq_sync(bfqq) &&
+ (idling_boosts_thr || asymmetric_scenario);
}
/*
@@ -4941,6 +5396,43 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
return bfqq;
}
+static void bfq_update_wr_data(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+ struct bfq_entity *entity = &bfqq->entity;
+
+ if (bfqq->wr_coeff > 1) { /* queue is being weight-raised */
+ bfq_log_bfqq(bfqd, bfqq,
+ "raising period dur %u/%u msec, old coeff %u, w %d(%d)",
+ jiffies_to_msecs(jiffies - bfqq->last_wr_start_finish),
+ jiffies_to_msecs(bfqq->wr_cur_max_time),
+ bfqq->wr_coeff,
+ bfqq->entity.weight, bfqq->entity.orig_weight);
+
+ if (entity->prio_changed)
+ bfq_log_bfqq(bfqd, bfqq, "WARN: pending prio change");
+
+ /*
+ * If too much time has elapsed from the beginning of
+ * this weight-raising period, then end weight
+ * raising.
+ */
+ if (time_is_before_jiffies(bfqq->last_wr_start_finish +
+ bfqq->wr_cur_max_time)) {
+ bfqq->last_wr_start_finish = jiffies;
+ bfq_log_bfqq(bfqd, bfqq,
+ "wrais ending at %lu, rais_max_time %u",
+ bfqq->last_wr_start_finish,
+ jiffies_to_msecs(bfqq->wr_cur_max_time));
+ bfq_bfqq_end_wr(bfqq);
+ }
+ }
+ /* Update weight both if it must be raised and if it must be lowered */
+ if ((entity->weight > entity->orig_weight) != (bfqq->wr_coeff > 1))
+ __bfq_entity_update_weight_prio(
+ bfq_entity_service_tree(entity),
+ entity);
+}
+
/*
* Dispatch next request from bfqq.
*/
@@ -4956,6 +5448,19 @@ static struct request *bfq_dispatch_rq_from_bfqq(struct bfq_data *bfqd,
bfq_dispatch_remove(bfqd->queue, rq);
+ /*
+ * If weight raising has to terminate for bfqq, then next
+ * function causes an immediate update of bfqq's weight,
+ * without waiting for next activation. As a consequence, on
+ * expiration, bfqq will be timestamped as if has never been
+ * weight-raised during this service slot, even if it has
+ * received part or even most of the service as a
+ * weight-raised queue. This inflates bfqq's timestamps, which
+ * is beneficial, as bfqq is then more willing to leave the
+ * device immediately to possible other weight-raised queues.
+ */
+ bfq_update_wr_data(bfqd, bfqq);
+
if (!bfqd->in_service_bic) {
atomic_long_inc(&RQ_BIC(rq)->icq.ioc->refcount);
bfqd->in_service_bic = RQ_BIC(rq);
@@ -5258,6 +5763,9 @@ static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
bfqq->max_budget = (2 * bfq_max_budget(bfqd)) / 3;
bfqq->budget_timeout = bfq_smallest_from_now();
+ bfqq->wr_coeff = 1;
+ bfqq->last_wr_start_finish = bfq_smallest_from_now();
+
/* first request is almost certainly seeky */
bfqq->seek_history = 1;
}
@@ -5392,7 +5900,8 @@ static void bfq_update_idle_window(struct bfq_data *bfqd,
(bfqd->hw_tag && BFQQ_SEEKY(bfqq)))
enable_idle = 0;
else if (bfq_sample_valid(bfqq->ttime.ttime_samples)) {
- if (bfqq->ttime.ttime_mean > bfqd->bfq_slice_idle)
+ if (bfqq->ttime.ttime_mean > bfqd->bfq_slice_idle &&
+ bfqq->wr_coeff == 1)
enable_idle = 0;
else
enable_idle = 1;
@@ -5570,6 +6079,16 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
bfqd->rq_in_driver--;
bfqq->dispatched--;
+ if (!bfqq->dispatched && !bfq_bfqq_busy(bfqq)) {
+ /*
+ * Set budget_timeout (which we overload to store the
+ * time at which the queue remains with no backlog and
+ * no outstanding request; used by the weight-raising
+ * mechanism).
+ */
+ bfqq->budget_timeout = jiffies;
+ }
+
now_ns = ktime_get_ns();
bfqq->ttime.last_end_request = now_ns;
@@ -5607,10 +6126,7 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
* 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)) {
+ if (bfqq->dispatched == 0 && bfq_bfqq_must_idle(bfqq)) {
bfq_arm_slice_timer(bfqd);
return;
} else if (bfq_may_expire_for_budg_timeout(bfqq))
@@ -5918,6 +6434,26 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
bfqd->bfq_requests_within_timer = 120;
+ bfqd->low_latency = true;
+
+ /*
+ * Trade-off between responsiveness and fairness.
+ */
+ bfqd->bfq_wr_coeff = 30;
+ bfqd->bfq_wr_max_time = 0;
+ bfqd->bfq_wr_min_idle_time = msecs_to_jiffies(2000);
+ bfqd->bfq_wr_min_inter_arr_async = msecs_to_jiffies(500);
+
+ /*
+ * Begin by assuming, optimistically, that the device is a
+ * high-speed one, and that its peak rate is equal to 2/3 of
+ * the highest reference rate.
+ */
+ bfqd->RT_prod = R_fast[blk_queue_nonrot(bfqd->queue)] *
+ T_fast[blk_queue_nonrot(bfqd->queue)];
+ bfqd->peak_rate = R_fast[blk_queue_nonrot(bfqd->queue)] * 2 / 3;
+ bfqd->device_speed = BFQ_BFQD_FAST;
+
spin_lock_init(&bfqd->lock);
/*
@@ -5980,6 +6516,15 @@ static ssize_t bfq_var_store(unsigned long *var, const char *page,
return count;
}
+static ssize_t bfq_wr_max_time_show(struct elevator_queue *e, char *page)
+{
+ struct bfq_data *bfqd = e->elevator_data;
+
+ return sprintf(page, "%d\n", bfqd->bfq_wr_max_time > 0 ?
+ jiffies_to_msecs(bfqd->bfq_wr_max_time) :
+ jiffies_to_msecs(bfq_wr_duration(bfqd)));
+}
+
static ssize_t bfq_weights_show(struct elevator_queue *e, char *page)
{
struct bfq_queue *bfqq;
@@ -5994,19 +6539,29 @@ static ssize_t bfq_weights_show(struct elevator_queue *e, char *page)
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\n",
+ "pid%d: weight %hu, nr_queued %d %d, ",
bfqq->pid,
bfqq->entity.weight,
bfqq->queued[0],
bfqq->queued[1]);
+ num_char += sprintf(page + num_char,
+ "dur %d/%u\n",
+ jiffies_to_msecs(
+ jiffies -
+ bfqq->last_wr_start_finish),
+ jiffies_to_msecs(bfqq->wr_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\n",
+ "pid%d: weight %hu, dur %d/%u\n",
bfqq->pid,
- bfqq->entity.weight);
+ bfqq->entity.weight,
+ jiffies_to_msecs(
+ jiffies -
+ bfqq->last_wr_start_finish),
+ jiffies_to_msecs(bfqq->wr_cur_max_time));
}
spin_unlock_irq(&bfqd->lock);
@@ -6033,6 +6588,11 @@ SHOW_FUNCTION(bfq_slice_idle_show, bfqd->bfq_slice_idle, 2);
SHOW_FUNCTION(bfq_max_budget_show, bfqd->bfq_user_max_budget, 0);
SHOW_FUNCTION(bfq_timeout_sync_show, bfqd->bfq_timeout, 1);
SHOW_FUNCTION(bfq_strict_guarantees_show, bfqd->strict_guarantees, 0);
+SHOW_FUNCTION(bfq_low_latency_show, bfqd->low_latency, 0);
+SHOW_FUNCTION(bfq_wr_coeff_show, bfqd->bfq_wr_coeff, 0);
+SHOW_FUNCTION(bfq_wr_min_idle_time_show, bfqd->bfq_wr_min_idle_time, 1);
+SHOW_FUNCTION(bfq_wr_min_inter_arr_async_show, bfqd->bfq_wr_min_inter_arr_async,
+ 1);
#undef SHOW_FUNCTION
#define USEC_SHOW_FUNCTION(__FUNC, __VAR) \
@@ -6073,6 +6633,12 @@ 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, 2);
+STORE_FUNCTION(bfq_wr_coeff_store, &bfqd->bfq_wr_coeff, 1, INT_MAX, 0);
+STORE_FUNCTION(bfq_wr_max_time_store, &bfqd->bfq_wr_max_time, 0, INT_MAX, 1);
+STORE_FUNCTION(bfq_wr_min_idle_time_store, &bfqd->bfq_wr_min_idle_time, 0,
+ INT_MAX, 1);
+STORE_FUNCTION(bfq_wr_min_inter_arr_async_store,
+ &bfqd->bfq_wr_min_inter_arr_async, 0, INT_MAX, 1);
#undef STORE_FUNCTION
#define USEC_STORE_FUNCTION(__FUNC, __PTR, MIN, MAX) \
@@ -6160,6 +6726,22 @@ static ssize_t bfq_strict_guarantees_store(struct elevator_queue *e,
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_wr(bfqd);
+ bfqd->low_latency = __data;
+
+ return ret;
+}
+
#define BFQ_ATTR(name) \
__ATTR(name, S_IRUGO|S_IWUSR, bfq_##name##_show, bfq_##name##_store)
@@ -6173,6 +6755,11 @@ static struct elv_fs_entry bfq_attrs[] = {
BFQ_ATTR(max_budget),
BFQ_ATTR(timeout_sync),
BFQ_ATTR(strict_guarantees),
+ BFQ_ATTR(low_latency),
+ BFQ_ATTR(wr_coeff),
+ BFQ_ATTR(wr_max_time),
+ BFQ_ATTR(wr_min_idle_time),
+ BFQ_ATTR(wr_min_inter_arr_async),
BFQ_ATTR(weights),
__ATTR_NULL
};
@@ -6225,7 +6812,7 @@ static struct blkcg_policy blkcg_policy_bfq = {
static int __init bfq_init(void)
{
int ret;
- char msg[50] = "BFQ I/O-scheduler: v0";
+ char msg[50] = "BFQ I/O-scheduler: v1";
#ifdef CONFIG_BFQ_GROUP_IOSCHED
ret = blkcg_policy_register(&blkcg_policy_bfq);
@@ -6237,6 +6824,39 @@ static int __init bfq_init(void)
if (bfq_slab_setup())
goto err_pol_unreg;
+ /*
+ * Times to load large popular applications for the typical
+ * systems installed on the reference devices (see the
+ * comments before the definitions of the next two
+ * arrays). Actually, we use slightly slower values, as the
+ * estimated peak rate tends to be smaller than the actual
+ * peak rate. The reason for this last fact is that estimates
+ * are computed over much shorter time intervals than the long
+ * intervals typically used for benchmarking. Why? First, to
+ * adapt more quickly to variations. Second, because an I/O
+ * scheduler cannot rely on a peak-rate-evaluation workload to
+ * be run for a long time.
+ */
+ T_slow[0] = msecs_to_jiffies(3500); /* actually 4 sec */
+ T_slow[1] = msecs_to_jiffies(6000); /* actually 6.5 sec */
+ T_fast[0] = msecs_to_jiffies(7000); /* actually 8 sec */
+ T_fast[1] = msecs_to_jiffies(2500); /* actually 3 sec */
+
+ /*
+ * Thresholds that determine the switch between speed classes
+ * (see the comments before the definition of the array
+ * device_speed_thresh). These thresholds are biased towards
+ * transitions to the fast class. This is safer than the
+ * opposite bias. In fact, a wrong transition to the slow
+ * class results in short weight-raising periods, because the
+ * speed of the device then tends to be higher that the
+ * reference peak rate. On the opposite end, a wrong
+ * transition to the fast class tends to increase
+ * weight-raising periods, because of the opposite reason.
+ */
+ device_speed_thresh[0] = (4 * R_slow[0]) / 3;
+ device_speed_thresh[1] = (4 * R_slow[1]) / 3;
+
ret = elv_register(&iosched_bfq_mq);
if (ret)
goto err_pol_unreg;
--
2.10.0
^ permalink raw reply related
* [PATCH RFC 05/14] block, bfq: add more fairness with writes and slow processes
From: Paolo Valente @ 2017-03-04 16:01 UTC (permalink / raw)
To: Jens Axboe, Tejun Heo
Cc: Fabio Checconi, Arianna Avanzini, linux-block, linux-kernel,
ulf.hansson, linus.walleij, broonie, Paolo Valente
In-Reply-To: <20170304160131.57366-1-paolo.valente@linaro.org>
This patch deals with two sources of unfairness, which can also cause
high latencies and throughput loss. The first source is related to
write requests. Write requests tend to starve read requests, basically
because, on one side, writes are slower than reads, whereas, on the
other side, storage devices confuse schedulers by deceptively
signaling the completion of write requests immediately after receiving
them. This patch addresses this issue by just throttling writes. In
particular, after a write request is dispatched for a queue, the
budget of the queue is decremented by the number of sectors to write,
multiplied by an (over)charge coefficient. The value of the
coefficient is the result of our tuning with different devices.
The second source of unfairness has to do with slowness detection:
when the in-service queue is expired, BFQ also controls whether the
queue has been "too slow", i.e., has consumed its last-assigned budget
at such a low rate that it would have been impossible to consume all
of this budget within the maximum time slice T_max (Subsec. 3.5 in
[1]). In this case, the queue is always (over)charged the whole
budget, to reduce its utilization of the device. Both this overcharge
and the slowness-detection criterion may cause unfairness.
First, always charging a full budget to a slow queue is too coarse. It
is much more accurate, and this patch lets BFQ do so, to charge an
amount of service 'equivalent' to the amount of time during which the
queue has been in service. As explained in more detail in the comments
on the code, this enables BFQ to provide time fairness among slow
queues.
Secondly, because of ZBR, a queue may be deemed as slow when its
associated process is performing I/O on the slowest zones of a
disk. However, unless the process is truly too slow, not reducing the
disk utilization of the queue is more profitable in terms of disk
throughput than the opposite. A similar problem is caused by logical
block mapping on non-rotational devices. For this reason, this patch
lets a queue be charged time, and not budget, only if the queue has
consumed less than 2/3 of its assigned budget. As an additional,
important benefit, this tolerance allows BFQ to preserve enough
elasticity to still perform bandwidth, and not time, distribution with
little unlucky or quasi-sequential processes.
Finally, for the same reasons as above, this patch makes slowness
detection itself much less harsh: a queue is deemed slow only if it
has consumed its budget at less than half of the peak rate.
[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.
Slightly extended version:
http://algogroup.unimore.it/people/paolo/disk_sched/bfq-v1-suite-
results.pdf
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
---
block/bfq-iosched.c | 120 +++++++++++++++++++++++++++++++++++++---------------
1 file changed, 85 insertions(+), 35 deletions(-)
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index abf7e75..f38d062 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -734,6 +734,13 @@ static const int bfq_stats_min_budgets = 194;
/* Default maximum budget values, in sectors and number of requests. */
static const int bfq_default_max_budget = 16 * 1024;
+/*
+ * 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, multiplied 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 = HZ / 8;
@@ -1538,22 +1545,52 @@ static void bfq_bfqq_served(struct bfq_queue *bfqq, int served)
}
/**
- * bfq_bfqq_charge_full_budget - set the service to the entity budget.
+ * bfq_bfqq_charge_time - charge an amount of service equivalent to the length
+ * of the time interval during which bfqq has been in
+ * service.
+ * @bfqd: the device
* @bfqq: the queue that needs a service update.
+ * @time_ms: the amount of time during which the queue has received service
*
- * 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.
+ * If a queue does not consume its budget fast enough, then providing
+ * the queue with service fairness may impair throughput, more or less
+ * severely. For this reason, queues that consume their budget slowly
+ * are provided with time fairness instead of service fairness. This
+ * goal is achieved through the BFQ scheduling engine, even if such an
+ * engine works in the service, and not in the time domain. The trick
+ * is charging these queues with an inflated amount of service, equal
+ * to the amount of service that they would have received during their
+ * service slot if they had been fast, i.e., if their requests had
+ * been dispatched at a rate equal to the estimated peak rate.
+ *
+ * It is worth noting that time fairness can cause important
+ * distortions in terms of bandwidth distribution, on devices with
+ * internal queueing. The reason is that I/O requests dispatched
+ * during the service slot of a queue may be served after that service
+ * slot is finished, and may have a total processing time loosely
+ * correlated with the duration of the service slot. This is
+ * especially true for short service slots.
*/
-static void bfq_bfqq_charge_full_budget(struct bfq_queue *bfqq)
+static void bfq_bfqq_charge_time(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ unsigned long time_ms)
{
struct bfq_entity *entity = &bfqq->entity;
+ int tot_serv_to_charge = entity->service;
+ unsigned int timeout_ms = jiffies_to_msecs(bfq_timeout);
+
+ if (time_ms > 0 && time_ms < timeout_ms)
+ tot_serv_to_charge =
+ (bfqd->bfq_max_budget * time_ms) / timeout_ms;
- bfq_log_bfqq(bfqq->bfqd, bfqq, "charge_full_budget");
+ if (tot_serv_to_charge < entity->service)
+ tot_serv_to_charge = entity->service;
- bfq_bfqq_served(bfqq, entity->budget - entity->service);
+ /* Increase budget to avoid inconsistencies */
+ if (tot_serv_to_charge > entity->budget)
+ entity->budget = tot_serv_to_charge;
+
+ bfq_bfqq_served(bfqq,
+ max_t(int, 0, tot_serv_to_charge - entity->service));
}
static void bfq_update_fin_time_enqueue(struct bfq_entity *entity,
@@ -3523,10 +3560,14 @@ static struct request *bfq_find_next_rq(struct bfq_data *bfqd,
return bfq_choose_req(bfqd, next, prev, blk_rq_pos(last));
}
+/* see the definition of bfq_async_charge_factor for details */
static unsigned long bfq_serv_to_charge(struct request *rq,
struct bfq_queue *bfqq)
{
- return blk_rq_sectors(rq);
+ if (bfq_bfqq_sync(bfqq))
+ return blk_rq_sectors(rq);
+
+ return blk_rq_sectors(rq) * bfq_async_charge_factor;
}
/**
@@ -4634,28 +4675,24 @@ static unsigned long bfq_smallest_from_now(void)
* @compensate: if true, compensate for the time spent idling.
* @reason: the reason causing the expiration.
*
+ * If the process associated with bfqq does slow I/O (e.g., because it
+ * issues random requests), we charge bfqq with the time it has been
+ * in service instead of the service it has received (see
+ * bfq_bfqq_charge_time for details on how this goal is achieved). As
+ * a consequence, bfqq will typically get higher timestamps upon
+ * reactivation, and hence it will be rescheduled as if it had
+ * received more service than what it has actually received. In the
+ * end, bfqq receives less service in proportion to how slowly its
+ * associated process consumes its budgets (and hence how seriously it
+ * tends to lower the throughput). In addition, this time-charging
+ * strategy guarantees time fairness among slow processes. In
+ * contrast, if the process associated with bfqq is not slow, we
+ * charge bfqq exactly with the service it has received.
*
- * If the process associated with 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.
+ * Charging time to the first type of queues and the exact service to
+ * the other has the effect of using the WF2Q+ policy to schedule the
+ * former on a timeslice basis, without violating service domain
+ * guarantees among the latter.
*/
static void bfq_bfqq_expire(struct bfq_data *bfqd,
struct bfq_queue *bfqq,
@@ -4672,11 +4709,24 @@ static void bfq_bfqq_expire(struct bfq_data *bfqd,
slow = bfq_bfqq_is_slow(bfqd, bfqq, compensate, reason, &delta);
/*
- * As above explained, 'punish' slow (i.e., seeky), timed-out
- * and async queues, to favor sequential sync workloads.
+ * As above explained, charge slow (typically seeky) and
+ * timed-out queues with the time and not the service
+ * received, to favor sequential workloads.
+ *
+ * Processes doing I/O in the slower disk zones will tend to
+ * be slow(er) even if not seeky. Therefore, 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, do not charge time to processes that
+ * succeeded in consuming at least 2/3 of their budget. This
+ * allows BFQ to preserve enough elasticity to still perform
+ * bandwidth, and not time, distribution with little unlucky
+ * or quasi-sequential processes.
*/
- if (slow || reason == BFQ_BFQQ_BUDGET_TIMEOUT)
- bfq_bfqq_charge_full_budget(bfqq);
+ if (slow ||
+ (reason == BFQ_BFQQ_BUDGET_TIMEOUT &&
+ bfq_bfqq_budget_left(bfqq) >= entity->budget / 3))
+ bfq_bfqq_charge_time(bfqd, bfqq, delta);
if (reason == BFQ_BFQQ_TOO_IDLE &&
entity->service <= 2 * entity->budget / 10)
--
2.10.0
^ permalink raw reply related
* [PATCH RFC 04/14] block, bfq: modify the peak-rate estimator
From: Paolo Valente @ 2017-03-04 16:01 UTC (permalink / raw)
To: Jens Axboe, Tejun Heo
Cc: Fabio Checconi, Arianna Avanzini, linux-block, linux-kernel,
ulf.hansson, linus.walleij, broonie, Paolo Valente
In-Reply-To: <20170304160131.57366-1-paolo.valente@linaro.org>
Unless the maximum budget B_max that BFQ can assign to a queue is set
explicitly by the user, BFQ automatically updates B_max. In
particular, BFQ dynamically sets B_max to the number of sectors that
can be read, at the current estimated peak rate, during the maximum
time, T_max, allowed before a budget timeout occurs. In formulas, if
we denote as R_est the estimated peak rate, then B_max = T_max ∗
R_est. Hence, the higher R_est is with respect to the actual device
peak rate, the higher the probability that processes incur budget
timeouts unjustly is. Besides, a too high value of B_max unnecessarily
increases the deviation from an ideal, smooth service.
Unfortunately, it is not trivial to estimate the peak rate correctly:
because of the presence of sw and hw queues between the scheduler and
the device components that finally serve I/O requests, it is hard to
say exactly when a given dispatched request is served inside the
device, and for how long. As a consequence, it is hard to know
precisely at what rate a given set of requests is actually served by
the device.
On the opposite end, the dispatch time of any request is trivially
available, and, from this piece of information, the "dispatch rate"
of requests can be immediately computed. So, the idea in the next
function is to use what is known, namely request dispatch times
(plus, when useful, request completion times), to estimate what is
unknown, namely in-device request service rate.
The main issue is that, because of the above facts, the rate at
which a certain set of requests is dispatched over a certain time
interval can vary greatly with respect to the rate at which the
same requests are then served. But, since the size of any
intermediate queue is limited, and the service scheme is lossless
(no request is silently dropped), the following obvious convergence
property holds: the number of requests dispatched MUST become
closer and closer to the number of requests completed as the
observation interval grows. This is the key property used in
this new version of the peak-rate estimator.
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
---
block/bfq-iosched.c | 498 +++++++++++++++++++++++++++++++++++++++-------------
1 file changed, 378 insertions(+), 120 deletions(-)
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index a7415f4..abf7e75 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -393,14 +393,32 @@ struct bfq_data {
/* on-disk position of the last served request */
sector_t last_position;
+ /* time of last request completion (ns) */
+ u64 last_completion;
+
+ /* time of first rq dispatch in current observation interval (ns) */
+ u64 first_dispatch;
+ /* time of last rq dispatch in current observation interval (ns) */
+ u64 last_dispatch;
+
/* beginning of the last budget */
ktime_t last_budget_start;
/* beginning of the last idle slice */
ktime_t last_idling_start;
- /* number of samples used to calculate @peak_rate */
+
+ /* number of samples in current observation interval */
int peak_rate_samples;
- /* peak transfer rate observed for a budget */
- u64 peak_rate;
+ /* num of samples of seq dispatches in current observation interval */
+ u32 sequential_samples;
+ /* total num of sectors transferred in current observation interval */
+ u64 tot_sectors_dispatched;
+ /* max rq size seen during current observation interval (sectors) */
+ u32 last_rq_max_size;
+ /* time elapsed from first dispatch in current observ. interval (us) */
+ u64 delta_from_first;
+ /* current estimate of device peak rate */
+ u32 peak_rate;
+
/* maximum budget allotted to a bfq_queue before rescheduling */
int bfq_max_budget;
@@ -721,7 +739,7 @@ static const int bfq_timeout = HZ / 8;
static struct kmem_cache *bfq_pool;
-/* Below this threshold (in ms), we consider thinktime immediate. */
+/* Below this threshold (in ns), we consider thinktime immediate. */
#define BFQ_MIN_TT (2 * NSEC_PER_MSEC)
/* hw_tag detection: parallel requests threshold and min samples needed. */
@@ -733,8 +751,12 @@ static struct kmem_cache *bfq_pool;
#define BFQQ_CLOSE_THR (sector_t)(8 * 1024)
#define BFQQ_SEEKY(bfqq) (hweight32(bfqq->seek_history) > 32/8)
-/* Min samples used for peak rate estimation (for autotuning). */
-#define BFQ_PEAK_RATE_SAMPLES 32
+/* Min number of samples required to perform peak-rate update */
+#define BFQ_RATE_MIN_SAMPLES 32
+/* Min observation time interval required to perform a peak-rate update (ns) */
+#define BFQ_RATE_MIN_INTERVAL (300*NSEC_PER_MSEC)
+/* Target observation time interval for a peak-rate update (ns) */
+#define BFQ_RATE_REF_INTERVAL NSEC_PER_SEC
/* Shift used for peak rate fixed precision calculations. */
#define BFQ_RATE_SHIFT 16
@@ -3788,15 +3810,26 @@ static struct request *bfq_find_rq_fmerge(struct bfq_data *bfqd,
return NULL;
}
+static sector_t get_sdist(sector_t last_pos, struct request *rq)
+{
+ sector_t sdist = 0;
+
+ if (last_pos) {
+ if (last_pos < blk_rq_pos(rq))
+ sdist = blk_rq_pos(rq) - last_pos;
+ else
+ sdist = last_pos - blk_rq_pos(rq);
+ }
+
+ return sdist;
+}
+
#if 0 /* Still not clear if we can do without next two functions */
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",
- (unsigned long long)bfqd->last_position);
}
static void bfq_deactivate_request(struct request_queue *q, struct request *rq)
@@ -4077,6 +4110,227 @@ static void bfq_set_budget_timeout(struct bfq_data *bfqd)
}
/*
+ * In autotuning mode, max_budget is dynamically recomputed as the
+ * amount of sectors transferred in timeout at the estimated peak
+ * rate. This enables BFQ to utilize a full timeslice with a full
+ * budget, even if the in-service queue is served at peak rate. And
+ * this maximises throughput with sequential workloads.
+ */
+static unsigned long bfq_calc_max_budget(struct bfq_data *bfqd)
+{
+ return (u64)bfqd->peak_rate * USEC_PER_MSEC *
+ jiffies_to_msecs(bfqd->bfq_timeout)>>BFQ_RATE_SHIFT;
+}
+
+static void bfq_reset_rate_computation(struct bfq_data *bfqd,
+ struct request *rq)
+{
+ if (rq != NULL) { /* new rq dispatch now, reset accordingly */
+ bfqd->last_dispatch = bfqd->first_dispatch = ktime_get_ns();
+ bfqd->peak_rate_samples = 1;
+ bfqd->sequential_samples = 0;
+ bfqd->tot_sectors_dispatched = bfqd->last_rq_max_size =
+ blk_rq_sectors(rq);
+ } else /* no new rq dispatched, just reset the number of samples */
+ bfqd->peak_rate_samples = 0; /* full re-init on next disp. */
+
+ bfq_log(bfqd,
+ "reset_rate_computation at end, sample %u/%u tot_sects %llu",
+ bfqd->peak_rate_samples, bfqd->sequential_samples,
+ bfqd->tot_sectors_dispatched);
+}
+
+static void bfq_update_rate_reset(struct bfq_data *bfqd, struct request *rq)
+{
+ u32 rate, weight, divisor;
+
+ /*
+ * For the convergence property to hold (see comments on
+ * bfq_update_peak_rate()) and for the assessment to be
+ * reliable, a minimum number of samples must be present, and
+ * a minimum amount of time must have elapsed. If not so, do
+ * not compute new rate. Just reset parameters, to get ready
+ * for a new evaluation attempt.
+ */
+ if (bfqd->peak_rate_samples < BFQ_RATE_MIN_SAMPLES ||
+ bfqd->delta_from_first < BFQ_RATE_MIN_INTERVAL)
+ goto reset_computation;
+
+ /*
+ * If a new request completion has occurred after last
+ * dispatch, then, to approximate the rate at which requests
+ * have been served by the device, it is more precise to
+ * extend the observation interval to the last completion.
+ */
+ bfqd->delta_from_first =
+ max_t(u64, bfqd->delta_from_first,
+ bfqd->last_completion - bfqd->first_dispatch);
+
+ /*
+ * Rate computed in sects/usec, and not sects/nsec, for
+ * precision issues.
+ */
+ rate = div64_ul(bfqd->tot_sectors_dispatched<<BFQ_RATE_SHIFT,
+ div_u64(bfqd->delta_from_first, NSEC_PER_USEC));
+
+ /*
+ * Peak rate not updated if:
+ * - the percentage of sequential dispatches is below 3/4 of the
+ * total, and rate is below the current estimated peak rate
+ * - rate is unreasonably high (> 20M sectors/sec)
+ */
+ if ((bfqd->sequential_samples < (3 * bfqd->peak_rate_samples)>>2 &&
+ rate <= bfqd->peak_rate) ||
+ rate > 20<<BFQ_RATE_SHIFT)
+ goto reset_computation;
+
+ /*
+ * We have to update the peak rate, at last! To this purpose,
+ * we use a low-pass filter. We compute the smoothing constant
+ * of the filter as a function of the 'weight' of the new
+ * measured rate.
+ *
+ * As can be seen in next formulas, we define this weight as a
+ * quantity proportional to how sequential the workload is,
+ * and to how long the observation time interval is.
+ *
+ * The weight runs from 0 to 8. The maximum value of the
+ * weight, 8, yields the minimum value for the smoothing
+ * constant. At this minimum value for the smoothing constant,
+ * the measured rate contributes for half of the next value of
+ * the estimated peak rate.
+ *
+ * So, the first step is to compute the weight as a function
+ * of how sequential the workload is. Note that the weight
+ * cannot reach 9, because bfqd->sequential_samples cannot
+ * become equal to bfqd->peak_rate_samples, which, in its
+ * turn, holds true because bfqd->sequential_samples is not
+ * incremented for the first sample.
+ */
+ weight = (9 * bfqd->sequential_samples) / bfqd->peak_rate_samples;
+
+ /*
+ * Second step: further refine the weight as a function of the
+ * duration of the observation interval.
+ */
+ weight = min_t(u32, 8,
+ div_u64(weight * bfqd->delta_from_first,
+ BFQ_RATE_REF_INTERVAL));
+
+ /*
+ * Divisor ranging from 10, for minimum weight, to 2, for
+ * maximum weight.
+ */
+ divisor = 10 - weight;
+
+ /*
+ * Finally, update peak rate:
+ *
+ * peak_rate = peak_rate * (divisor-1) / divisor + rate / divisor
+ */
+ bfqd->peak_rate *= divisor-1;
+ bfqd->peak_rate /= divisor;
+ rate /= divisor; /* smoothing constant alpha = 1/divisor */
+
+ bfqd->peak_rate += rate;
+ if (bfqd->bfq_user_max_budget == 0)
+ bfqd->bfq_max_budget =
+ bfq_calc_max_budget(bfqd);
+
+reset_computation:
+ bfq_reset_rate_computation(bfqd, rq);
+}
+
+/*
+ * Update the read/write peak rate (the main quantity used for
+ * auto-tuning, see update_thr_responsiveness_params()).
+ *
+ * It is not trivial to estimate the peak rate (correctly): because of
+ * the presence of sw and hw queues between the scheduler and the
+ * device components that finally serve I/O requests, it is hard to
+ * say exactly when a given dispatched request is served inside the
+ * device, and for how long. As a consequence, it is hard to know
+ * precisely at what rate a given set of requests is actually served
+ * by the device.
+ *
+ * On the opposite end, the dispatch time of any request is trivially
+ * available, and, from this piece of information, the "dispatch rate"
+ * of requests can be immediately computed. So, the idea in the next
+ * function is to use what is known, namely request dispatch times
+ * (plus, when useful, request completion times), to estimate what is
+ * unknown, namely in-device request service rate.
+ *
+ * The main issue is that, because of the above facts, the rate at
+ * which a certain set of requests is dispatched over a certain time
+ * interval can vary greatly with respect to the rate at which the
+ * same requests are then served. But, since the size of any
+ * intermediate queue is limited, and the service scheme is lossless
+ * (no request is silently dropped), the following obvious convergence
+ * property holds: the number of requests dispatched MUST become
+ * closer and closer to the number of requests completed as the
+ * observation interval grows. This is the key property used in
+ * the next function to estimate the peak service rate as a function
+ * of the observed dispatch rate. The function assumes to be invoked
+ * on every request dispatch.
+ */
+static void bfq_update_peak_rate(struct bfq_data *bfqd, struct request *rq)
+{
+ u64 now_ns = ktime_get_ns();
+
+ if (bfqd->peak_rate_samples == 0) { /* first dispatch */
+ bfq_log(bfqd, "update_peak_rate: goto reset, samples %d",
+ bfqd->peak_rate_samples);
+ bfq_reset_rate_computation(bfqd, rq);
+ goto update_last_values; /* will add one sample */
+ }
+
+ /*
+ * Device idle for very long: the observation interval lasting
+ * up to this dispatch cannot be a valid observation interval
+ * for computing a new peak rate (similarly to the late-
+ * completion event in bfq_completed_request()). Go to
+ * update_rate_and_reset to have the following three steps
+ * taken:
+ * - close the observation interval at the last (previous)
+ * request dispatch or completion
+ * - compute rate, if possible, for that observation interval
+ * - start a new observation interval with this dispatch
+ */
+ if (now_ns - bfqd->last_dispatch > 100*NSEC_PER_MSEC &&
+ bfqd->rq_in_driver == 0)
+ goto update_rate_and_reset;
+
+ /* Update sampling information */
+ bfqd->peak_rate_samples++;
+
+ if ((bfqd->rq_in_driver > 0 ||
+ now_ns - bfqd->last_completion < BFQ_MIN_TT)
+ && get_sdist(bfqd->last_position, rq) < BFQQ_SEEK_THR)
+ bfqd->sequential_samples++;
+
+ bfqd->tot_sectors_dispatched += blk_rq_sectors(rq);
+
+ /* Reset max observed rq size every 32 dispatches */
+ if (likely(bfqd->peak_rate_samples % 32))
+ bfqd->last_rq_max_size =
+ max_t(u32, blk_rq_sectors(rq), bfqd->last_rq_max_size);
+ else
+ bfqd->last_rq_max_size = blk_rq_sectors(rq);
+
+ bfqd->delta_from_first = now_ns - bfqd->first_dispatch;
+
+ /* Target observation interval not yet reached, go on sampling */
+ if (bfqd->delta_from_first < BFQ_RATE_REF_INTERVAL)
+ goto update_last_values;
+
+update_rate_and_reset:
+ bfq_update_rate_reset(bfqd, rq);
+update_last_values:
+ bfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq);
+ bfqd->last_dispatch = now_ns;
+}
+
+/*
* Remove request from internal lists.
*/
static void bfq_dispatch_remove(struct request_queue *q, struct request *rq)
@@ -4096,6 +4350,7 @@ static void bfq_dispatch_remove(struct request_queue *q, struct request *rq)
* happens to be taken into account.
*/
bfqq->dispatched++;
+ bfq_update_peak_rate(q->elevator->elevator_data, rq);
bfq_remove_request(q, rq);
}
@@ -4275,105 +4530,92 @@ static void __bfq_bfqq_recalc_budget(struct bfq_data *bfqd,
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 transferred in timeout 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.
+ * Return true if the process associated with bfqq is "slow". The slow
+ * flag is used, in addition to the budget timeout, to reduce the
+ * amount of service provided to seeky processes, and thus reduce
+ * their chances to lower the throughput. More details in the comments
+ * on the function bfq_bfqq_expire().
+ *
+ * An important observation is in order: as discussed in the comments
+ * on the function bfq_update_peak_rate(), with devices with internal
+ * queues, it is hard if ever possible to know when and for how long
+ * an I/O request is processed by the device (apart from the trivial
+ * I/O pattern where a new request is dispatched only after the
+ * previous one has been completed). This makes it hard to evaluate
+ * the real rate at which the I/O requests of each bfq_queue are
+ * served. In fact, for an I/O scheduler like BFQ, serving a
+ * bfq_queue means just dispatching its requests during its service
+ * slot (i.e., until the budget of the queue is exhausted, or the
+ * queue remains idle, or, finally, a timeout fires). But, during the
+ * service slot of a bfq_queue, around 100 ms at most, the device may
+ * be even still processing requests of bfq_queues served in previous
+ * service slots. On the opposite end, the requests of the in-service
+ * bfq_queue may be completed after the service slot of the queue
+ * finishes.
+ *
+ * Anyway, unless more sophisticated solutions are used
+ * (where possible), the sum of the sizes of the requests dispatched
+ * during the service slot of a bfq_queue is probably the only
+ * approximation available for the service received by the bfq_queue
+ * during its service slot. And this sum is the quantity used in this
+ * function to evaluate the I/O speed of a process.
*/
-static bool bfq_update_peak_rate(struct bfq_data *bfqd, struct bfq_queue *bfqq,
- bool compensate)
+static bool bfq_bfqq_is_slow(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ bool compensate, enum bfqq_expiration reason,
+ unsigned long *delta_ms)
{
- u64 bw, usecs, expected, timeout;
- ktime_t delta;
- int update = 0;
+ ktime_t delta_ktime;
+ u32 delta_usecs;
+ bool slow = BFQQ_SEEKY(bfqq); /* if delta too short, use seekyness */
- if (!bfq_bfqq_sync(bfqq) || bfq_bfqq_budget_new(bfqq))
+ if (!bfq_bfqq_sync(bfqq))
return false;
if (compensate)
- delta = bfqd->last_idling_start;
+ delta_ktime = 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 false;
-
- /*
- * 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);
+ delta_ktime = ktime_get();
+ delta_ktime = ktime_sub(delta_ktime, bfqd->last_budget_start);
+ delta_usecs = ktime_to_us(delta_ktime);
+
+ /* don't trust short/unrealistic values. */
+ if (delta_usecs < 1000 || delta_usecs >= LONG_MAX) {
+ if (blk_queue_nonrot(bfqd->queue))
+ /*
+ * give same worst-case guarantees as idling
+ * for seeky
+ */
+ *delta_ms = BFQ_MIN_TT / NSEC_PER_MSEC;
+ else /* charge at least one seek */
+ *delta_ms = bfq_slice_idle / NSEC_PER_MSEC;
+
+ return slow;
+ }
- timeout = jiffies_to_msecs(bfqd->bfq_timeout);
+ *delta_ms = delta_usecs / USEC_PER_MSEC;
/*
- * Use only long (> 20ms) intervals to filter out spikes for
- * the peak rate estimation.
+ * Use only long (> 20ms) intervals to filter out excessive
+ * spikes in service rate estimation.
*/
- if (usecs > 20000) {
- if (bw > bfqd->peak_rate) {
- bfqd->peak_rate = bw;
- update = 1;
- bfq_log(bfqd, "new peak_rate=%llu", bw);
- }
-
- 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=%d",
- bfqd->bfq_max_budget);
- }
+ if (delta_usecs > 20000) {
+ /*
+ * Caveat for rotational devices: processes doing I/O
+ * in the slower disk zones tend to be slow(er) even
+ * if not seeky. In this respect, the estimated peak
+ * rate is likely to be an average over the disk
+ * surface. Accordingly, to not be too harsh with
+ * unlucky processes, a process is deemed slow only if
+ * its rate has been lower than half of the estimated
+ * peak rate.
+ */
+ slow = bfqq->entity.service < bfqd->bfq_max_budget / 2;
}
- /*
- * 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;
+ bfq_log_bfqq(bfqd, bfqq, "bfq_bfqq_is_slow: slow %d", slow);
- /*
- * 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;
+ return slow;
}
/*
@@ -4421,12 +4663,13 @@ static void bfq_bfqq_expire(struct bfq_data *bfqd,
enum bfqq_expiration reason)
{
bool slow;
+ unsigned long delta = 0;
+ struct bfq_entity *entity = &bfqq->entity;
/*
- * Update device peak rate for autotuning and check whether the
- * process is slow (see bfq_update_peak_rate).
+ * Check whether the process is slow (see bfq_bfqq_is_slow).
*/
- slow = bfq_update_peak_rate(bfqd, bfqq, compensate);
+ slow = bfq_bfqq_is_slow(bfqd, bfqq, compensate, reason, &delta);
/*
* As above explained, 'punish' slow (i.e., seeky), timed-out
@@ -4436,7 +4679,7 @@ static void bfq_bfqq_expire(struct bfq_data *bfqd,
bfq_bfqq_charge_full_budget(bfqq);
if (reason == BFQ_BFQQ_TOO_IDLE &&
- bfqq->entity.service <= 2 * bfqq->entity.budget / 10)
+ entity->service <= 2 * entity->budget / 10)
bfq_clear_bfqq_IO_bound(bfqq);
bfq_log_bfqq(bfqd, bfqq,
@@ -5071,17 +5314,9 @@ static void
bfq_update_io_seektime(struct bfq_data *bfqd, struct bfq_queue *bfqq,
struct request *rq)
{
- sector_t sdist = 0;
-
- if (bfqq->last_request_pos) {
- 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);
- }
-
bfqq->seek_history <<= 1;
- bfqq->seek_history |= sdist > BFQQ_SEEK_THR &&
+ bfqq->seek_history |=
+ get_sdist(bfqq->last_request_pos, rq) > BFQQ_SEEK_THR &&
(!blk_queue_nonrot(bfqd->queue) ||
blk_rq_sectors(rq) < BFQQ_SECT_THR_NONROT);
}
@@ -5277,12 +5512,45 @@ static void bfq_update_hw_tag(struct bfq_data *bfqd)
static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
{
+ u64 now_ns;
+ u32 delta_us;
+
bfq_update_hw_tag(bfqd);
bfqd->rq_in_driver--;
bfqq->dispatched--;
- bfqq->ttime.last_end_request = ktime_get_ns();
+ now_ns = ktime_get_ns();
+
+ bfqq->ttime.last_end_request = now_ns;
+
+ /*
+ * Using us instead of ns, to get a reasonable precision in
+ * computing rate in next check.
+ */
+ delta_us = div_u64(now_ns - bfqd->last_completion, NSEC_PER_USEC);
+
+ /*
+ * If the request took rather long to complete, and, according
+ * to the maximum request size recorded, this completion latency
+ * implies that the request was certainly served at a very low
+ * rate (less than 1M sectors/sec), then the whole observation
+ * interval that lasts up to this time instant cannot be a
+ * valid time interval for computing a new peak rate. Invoke
+ * bfq_update_rate_reset to have the following three steps
+ * taken:
+ * - close the observation interval at the last (previous)
+ * request dispatch or completion
+ * - compute rate, if possible, for that observation interval
+ * - reset to zero samples, which will trigger a proper
+ * re-initialization of the observation interval on next
+ * dispatch
+ */
+ if (delta_us > BFQ_MIN_TT/NSEC_PER_USEC &&
+ (bfqd->last_rq_max_size<<BFQ_RATE_SHIFT)/delta_us <
+ 1UL<<(BFQ_RATE_SHIFT - 10))
+ bfq_update_rate_reset(bfqd, NULL);
+ bfqd->last_completion = now_ns;
/*
* If this is the in-service queue, check if it needs to be expired,
@@ -5781,16 +6049,6 @@ static ssize_t bfq_weights_store(struct elevator_queue *e,
return count;
}
-static unsigned long bfq_estimated_max_budget(struct bfq_data *bfqd)
-{
- u64 timeout = jiffies_to_msecs(bfqd->bfq_timeout);
-
- 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)
{
@@ -5799,7 +6057,7 @@ static ssize_t bfq_max_budget_store(struct elevator_queue *e,
int ret = bfq_var_store(&__data, (page), count);
if (__data == 0)
- bfqd->bfq_max_budget = bfq_estimated_max_budget(bfqd);
+ bfqd->bfq_max_budget = bfq_calc_max_budget(bfqd);
else {
if (__data > INT_MAX)
__data = INT_MAX;
@@ -5829,7 +6087,7 @@ static ssize_t bfq_timeout_sync_store(struct elevator_queue *e,
bfqd->bfq_timeout = msecs_to_jiffies(__data);
if (bfqd->bfq_user_max_budget == 0)
- bfqd->bfq_max_budget = bfq_estimated_max_budget(bfqd);
+ bfqd->bfq_max_budget = bfq_calc_max_budget(bfqd);
return ret;
}
--
2.10.0
^ permalink raw reply related
* [PATCH RFC 03/14] block, bfq: improve throughput boosting
From: Paolo Valente @ 2017-03-04 16:01 UTC (permalink / raw)
To: Jens Axboe, Tejun Heo
Cc: Fabio Checconi, Arianna Avanzini, linux-block, linux-kernel,
ulf.hansson, linus.walleij, broonie, Paolo Valente
In-Reply-To: <20170304160131.57366-1-paolo.valente@linaro.org>
The feedback-loop algorithm used by BFQ to compute queue (process)
budgets is basically a set of three update rules, one for each of the
main reasons why a queue may be expired. If many processes suddenly
switch from sporadic I/O to greedy and sequential I/O, then these
rules are quite slow to assign large budgets to these processes, and
hence to achieve a high throughput. On the opposite side, BFQ assigns
the maximum possible budget B_max to a just-created queue. This allows
a high throughput to be achieved immediately if the associated process
is I/O-bound and performs sequential I/O from the beginning. But it
also increases the worst-case latency experienced by the first
requests issued by the process, because the larger the budget of a
queue waiting for service is, the later the queue will be served by
B-WF2Q+ (Subsec 3.3 in [1]). This is detrimental for an interactive or
soft real-time application.
To tackle these throughput and latency problems, on one hand this
patch changes the initial budget value to B_max/2. On the other hand,
it re-tunes the three rules, adopting a more aggressive,
multiplicative increase/linear decrease scheme. This scheme trades
latency for throughput more than before, and tends to assign large
budgets quickly to processes that are or become I/O-bound. For two of
the expiration reasons, the new version of the rules also contains
some more little improvements, briefly described below.
*No more backlog.* In this case, the budget was larger than the number
of sectors actually read/written by the process before it stopped
doing I/O. Hence, to reduce latency for the possible future I/O
requests of the process, the old rule simply set the next budget to
the number of sectors actually consumed 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 outstanding ones. If this sub-case
holds true, then the new rule, instead of decreasing the budget,
doubles it, proactively, in the hope that: 1) a larger budget will fit
the actual needs of the process, and 2) the process is sequential and
hence a higher throughput will be achieved by serving the process
longer after granting it access to the device.
*Budget timeout*. The original rule set the new budget to the maximum
value B_max, to maximize throughput and let all processes experiencing
budget timeouts receive the same share of the device time. In our
experiments we verified that this sudden jump to B_max did not provide
sensible benefits; rather it increased the latency of processes
performing sporadic and short I/O. The new rule only doubles the
budget.
[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.
Slightly extended version:
http://algogroup.unimore.it/people/paolo/disk_sched/bfq-v1-suite-
results.pdf
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
---
block/bfq-iosched.c | 83 ++++++++++++++++++++++++++---------------------------
1 file changed, 41 insertions(+), 42 deletions(-)
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 35c3dd2..a7415f4 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -733,9 +733,6 @@ static struct kmem_cache *bfq_pool;
#define BFQQ_CLOSE_THR (sector_t)(8 * 1024)
#define BFQQ_SEEKY(bfqq) (hweight32(bfqq->seek_history) > 32/8)
-/* Budget feedback step. */
-#define BFQ_BUDGET_STEP 128
-
/* Min samples used for peak rate estimation (for autotuning). */
#define BFQ_PEAK_RATE_SAMPLES 32
@@ -4027,36 +4024,6 @@ static struct bfq_queue *bfq_set_in_service_queue(struct bfq_data *bfqd)
return bfqq;
}
-/*
- * bfq_default_budget - return the default budget for @bfqq on @bfqd.
- * @bfqd: the device descriptor.
- * @bfqq: the queue to consider.
- *
- * We use 3/4 of the @bfqd maximum budget as the default value
- * for the max_budget field of the queues. This lets the feedback
- * mechanism to start from some middle ground, then the behavior
- * of the process will drive the heuristics towards high values, if
- * it behaves as a greedy sequential reader, or towards small values
- * if it shows a more intermittent behavior.
- */
-static unsigned long bfq_default_budget(struct bfq_data *bfqd,
- struct bfq_queue *bfqq)
-{
- unsigned long budget;
-
- /*
- * When we need an estimate of the peak rate we need to avoid
- * to give budgets that are too short due to previous measurements.
- * So, in the first 10 assignments use a ``safe'' budget value.
- */
- if (bfqd->budgets_assigned < 194 && bfqd->bfq_user_max_budget == 0)
- budget = bfq_default_max_budget;
- else
- budget = bfqd->bfq_max_budget;
-
- return budget - budget / 4;
-}
-
static void bfq_arm_slice_timer(struct bfq_data *bfqd)
{
struct bfq_queue *bfqq = bfqd->in_service_queue;
@@ -4181,13 +4148,47 @@ static void __bfq_bfqq_recalc_budget(struct bfq_data *bfqd,
* for throughput.
*/
case BFQ_BFQQ_TOO_IDLE:
- if (budget > min_budget + BFQ_BUDGET_STEP)
- budget -= BFQ_BUDGET_STEP;
- else
- budget = min_budget;
+ /*
+ * This is the only case where we may reduce
+ * the budget: if there is no request 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 outstanding 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 outstanding 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:
- budget = bfq_default_budget(bfqd, bfqq);
+ /*
+ * We double the budget here because it gives
+ * the chance to boost the throughput if this
+ * is not a seeky process (and has bumped into
+ * this timeout because of, e.g., ZBR).
+ */
+ budget = min(budget * 2, bfqd->bfq_max_budget);
break;
case BFQ_BFQQ_BUDGET_EXHAUSTED:
/*
@@ -4199,8 +4200,7 @@ static void __bfq_bfqq_recalc_budget(struct bfq_data *bfqd,
* definitely increase the budget of this good
* candidate to boost the disk throughput.
*/
- budget = min(budget + 8 * BFQ_BUDGET_STEP,
- bfqd->bfq_max_budget);
+ budget = min(budget * 4, bfqd->bfq_max_budget);
break;
case BFQ_BFQQ_NO_MORE_REQUESTS:
/*
@@ -4962,9 +4962,8 @@ static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
bfqq->pid = pid;
/* Tentative initial value to trade off between thr and lat */
- bfqq->max_budget = bfq_default_budget(bfqd, bfqq);
+ bfqq->max_budget = (2 * bfq_max_budget(bfqd)) / 3;
bfqq->budget_timeout = bfq_smallest_from_now();
- bfqq->pid = pid;
/* first request is almost certainly seeky */
bfqq->seek_history = 1;
--
2.10.0
^ permalink raw reply related
* [PATCH RFC 02/14] block, bfq: add full hierarchical scheduling and cgroups support
From: Paolo Valente @ 2017-03-04 16:01 UTC (permalink / raw)
To: Jens Axboe, Tejun Heo
Cc: Fabio Checconi, Arianna Avanzini, linux-block, linux-kernel,
ulf.hansson, linus.walleij, broonie, Paolo Valente
In-Reply-To: <20170304160131.57366-1-paolo.valente@linaro.org>
From: Arianna Avanzini <avanzini.arianna@gmail.com>
Add complete support for full hierarchical scheduling, with a cgroups
interface. Full hierarchical scheduling is implemented through the
'entity' abstraction: both bfq_queues, i.e., the internal BFQ queues
associated with processes, and groups are represented in general by
entities. Given the bfq_queues associated with the processes belonging
to a given group, the entities representing these queues are sons of
the entity representing the group. At higher levels, if a group, say
G, contains other groups, then the entity representing G is the parent
entity of the entities representing the groups in G.
Hierarchical scheduling is performed as follows: if the timestamps of
a leaf entity (i.e., of a bfq_queue) change, and such a change lets
the entity become the next-to-serve entity for its parent entity, then
the timestamps of the parent entity are recomputed as a function of
the budget of its new next-to-serve leaf entity. If the parent entity
belongs, in its turn, to a group, and its new timestamps let it become
the next-to-serve for its parent entity, then the timestamps of the
latter parent entity are recomputed as well, and so on. When a new
bfq_queue must be set in service, the reverse path is followed: the
next-to-serve highest-level entity is chosen, then its next-to-serve
child entity, and so on, until the next-to-serve leaf entity is
reached, and the bfq_queue that this entity represents is set in
service.
Writeback is accounted for on a per-group basis, i.e., for each group,
the async I/O requests of the processes of the group are enqueued in a
distinct bfq_queue, and the entity associated with this queue is a
child of the entity associated with the group.
Weights can be assigned explicitly to groups and processes through the
cgroups interface, differently from what happens, for single
processes, if the cgroups interface is not used (as explained in the
description of the previous patch). In particular, since each node has
a full scheduler, each group can be assigned its own weight.
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
---
Documentation/block/bfq-iosched.txt | 17 +-
block/Kconfig.iosched | 10 +
block/bfq-iosched.c | 2561 ++++++++++++++++++++++++++++++-----
include/linux/blkdev.h | 2 +-
4 files changed, 2207 insertions(+), 383 deletions(-)
diff --git a/Documentation/block/bfq-iosched.txt b/Documentation/block/bfq-iosched.txt
index 5ba67af..934cbe6 100644
--- a/Documentation/block/bfq-iosched.txt
+++ b/Documentation/block/bfq-iosched.txt
@@ -252,9 +252,14 @@ of slice_idle are copied from CFQ too.
per-process ioprio and weight
-----------------------------
-Unless the cgroups interface is used, weights can be assigned to
-processes only indirectly, through I/O priorities, and according to
-the relation: weight = (IOPRIO_BE_NR - ioprio) * 10.
+Unless the cgroups interface is used (see "4. BFQ group scheduling"),
+weights can be assigned to processes only indirectly, through I/O
+priorities, and according to the relation:
+weight = (IOPRIO_BE_NR - ioprio) * 10.
+
+Beware that, if low-latency is set, then BFQ automatically raises the
+weight of the queues associated with interactive and soft real-time
+applications. Unset this tunable if you need/want to control weights.
slice_idle
----------
@@ -449,9 +454,9 @@ may be reactivated for an already busy async queue (in ms).
4. Group scheduling with BFQ
============================
-BFQ supports both cgroup-v1 and cgroup-v2 io controllers, namely blkio
-and io. In particular, BFQ supports weight-based proportional
-share.
+BFQ supports both cgroups-v1 and cgroups-v2 io controllers, namely
+blkio and io. In particular, BFQ supports weight-based proportional
+share. To activate cgroups support, set BFQ_GROUP_IOSCHED.
4-1 Service guarantees provided
-------------------------------
diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
index 562e30e..a37cd03 100644
--- a/block/Kconfig.iosched
+++ b/block/Kconfig.iosched
@@ -40,6 +40,7 @@ config CFQ_GROUP_IOSCHED
Enable group IO scheduling in CFQ.
choice
+
prompt "Default I/O scheduler"
default DEFAULT_CFQ
help
@@ -80,6 +81,15 @@ config IOSCHED_BFQ
real-time applications. Details in
Documentation/block/bfq-iosched.txt
+config BFQ_GROUP_IOSCHED
+ bool "BFQ hierarchical scheduling support"
+ depends on IOSCHED_BFQ && BLK_CGROUP
+ default n
+ ---help---
+
+ Enable hierarchical scheduling in BFQ, using the blkio
+ (cgroups-v1) or io (cgroups-v2) controller.
+
endmenu
endif
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 4e60fe9..35c3dd2 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -82,6 +82,7 @@
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/blkdev.h>
+#include <linux/cgroup.h>
#include <linux/elevator.h>
#include <linux/ktime.h>
#include <linux/rbtree.h>
@@ -106,7 +107,7 @@
#define BFQ_DEFAULT_QUEUE_IOPRIO 4
-#define BFQ_DEFAULT_GRP_WEIGHT 10
+#define BFQ_WEIGHT_LEGACY_DFL 100
#define BFQ_DEFAULT_GRP_IOPRIO 0
#define BFQ_DEFAULT_GRP_CLASS IOPRIO_CLASS_BE
@@ -138,10 +139,11 @@ struct bfq_service_tree {
* struct bfq_sched_data - multi-class scheduler.
*
* 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_in_service points to the active entity of the sched_data
- * service trees that will be scheduled next.
+ * ioprio_classes, and can be used either as a toplevel queue or as an
+ * intermediate queue on a hierarchical setup. @next_in_service
+ * points to the active entity of the sched_data service trees that
+ * will be scheduled next. It is used to reduce the number of steps
+ * needed for each hierarchical-schedule update.
*
* The supported ioprio_classes are the same as in CFQ, in descending
* priority order, IOPRIO_CLASS_RT, IOPRIO_CLASS_BE, IOPRIO_CLASS_IDLE.
@@ -152,19 +154,23 @@ struct bfq_service_tree {
*/
struct bfq_sched_data {
struct bfq_entity *in_service_entity; /* entity in service */
- /* head-of-the-line entity in the scheduler */
+ /* head-of-the-line entity in the scheduler (see comments above) */
struct bfq_entity *next_in_service;
/* array of service trees, one per ioprio_class */
struct bfq_service_tree service_tree[BFQ_IOPRIO_CLASSES];
+ /* last time CLASS_IDLE was served */
+ unsigned long bfq_class_idle_last_service;
+
};
/**
* struct bfq_entity - schedulable entity.
*
- * A bfq_entity is used to represent a bfq_queue (leaf node in the upper
- * level scheduler). Each entity belongs to the sched_data of the parent
- * group hierarchy. Non-leaf entities have also their own sched_data,
- * stored in @my_sched_data.
+ * 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
@@ -175,22 +181,23 @@ struct bfq_sched_data {
* update to take place the effective and the requested priority
* values are synchronized.
*
- * 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 hierarchy should be guaranteed. All the fields are
- * protected by the queue lock of the containing bfqd.
+ * 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; /* service_tree member */
/*
- * flag, true if the entity is on a tree (either the active or
- * the idle one of its service_tree).
+ * Flag, true if the entity is on a tree (either the active or
+ * the idle one of its service_tree) or is in service.
*/
- int on_st;
+ bool on_st;
u64 finish; /* B-WF2Q+ finish timestamp (aka F_i) */
u64 start; /* B-WF2Q+ start timestamp (aka S_i) */
@@ -231,6 +238,8 @@ struct bfq_entity {
int prio_changed;
};
+struct bfq_group;
+
/**
* struct bfq_ttime - per process thinktime stats.
*/
@@ -247,7 +256,11 @@ struct bfq_ttime {
* struct bfq_queue - leaf schedulable entity.
*
* A bfq_queue is a leaf request queue; it can be associated with an
- * io_context or more, if it is async.
+ * io_context or more, if it is async. @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 destruction). All the fields
+ * are protected by the queue lock of the containing bfqd.
*/
struct bfq_queue {
/* reference counter */
@@ -319,6 +332,9 @@ struct bfq_io_cq {
struct bfq_queue *bfqq[2];
/* per (request_queue, blkcg) ioprio */
int ioprio;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ uint64_t blkcg_serial_nr; /* the current blkcg serial */
+#endif
};
enum bfq_device_speed {
@@ -337,8 +353,8 @@ struct bfq_data {
/* dispatch queue */
struct list_head dispatch;
- /* root @bfq_sched_data for the device */
- struct bfq_sched_data sched_data;
+ /* root bfq_group for the device */
+ struct bfq_group *root_group;
/*
* Number of bfq_queues containing requests (including the
@@ -404,8 +420,6 @@ struct bfq_data {
unsigned int bfq_back_max;
/* maximum idling time */
u32 bfq_slice_idle;
- /* last time CLASS_IDLE was served */
- u64 bfq_class_idle_last_service;
/* user-configured max budget value (0 for auto-tuning) */
int bfq_user_max_budget;
@@ -497,8 +511,35 @@ BFQ_BFQQ_FNS(IO_bound);
#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)
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+static struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
+static struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
+
+#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) do { \
+ char __pbuf[128]; \
+ \
+ blkg_path(bfqg_to_blkg(bfqq_group(bfqq)), __pbuf, sizeof(__pbuf)); \
+ blk_add_trace_msg((bfqd)->queue, "bfq%d%c %s " fmt, (bfqq)->pid, \
+ bfq_bfqq_sync((bfqq)) ? 'S' : 'A', \
+ __pbuf, ##args); \
+} while (0)
+
+#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) do { \
+ char __pbuf[128]; \
+ \
+ blkg_path(bfqg_to_blkg(bfqg), __pbuf, sizeof(__pbuf)); \
+ blk_add_trace_msg((bfqd)->queue, "%s " fmt, __pbuf, ##args); \
+} while (0)
+
+#else /* CONFIG_BFQ_GROUP_IOSCHED */
+
+#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) \
+ blk_add_trace_msg((bfqd)->queue, "bfq%d%c " fmt, (bfqq)->pid, \
+ bfq_bfqq_sync((bfqq)) ? 'S' : 'A', \
+ ##args)
+#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) do {} while (0)
+
+#endif /* CONFIG_BFQ_GROUP_IOSCHED */
#define bfq_log(bfqd, fmt, args...) \
blk_add_trace_msg((bfqd)->queue, "bfq " fmt, ##args)
@@ -515,15 +556,120 @@ enum bfqq_expiration {
BFQ_BFQQ_PREEMPTED /* preemption in progress */
};
+struct bfqg_stats {
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ /* number of ios merged */
+ struct blkg_rwstat merged;
+ /* total time spent on device in ns, may not be accurate w/ queueing */
+ struct blkg_rwstat service_time;
+ /* total time spent waiting in scheduler queue in ns */
+ struct blkg_rwstat wait_time;
+ /* number of IOs queued up */
+ struct blkg_rwstat queued;
+ /* total disk time and nr sectors dispatched by this group */
+ struct blkg_stat time;
+ /* sum of number of ios queued across all samples */
+ struct blkg_stat avg_queue_size_sum;
+ /* count of samples taken for average */
+ struct blkg_stat avg_queue_size_samples;
+ /* how many times this group has been removed from service tree */
+ struct blkg_stat dequeue;
+ /* total time spent waiting for it to be assigned a timeslice. */
+ struct blkg_stat group_wait_time;
+ /* time spent idling for this blkcg_gq */
+ struct blkg_stat idle_time;
+ /* total time with empty current active q with other requests queued */
+ struct blkg_stat empty_time;
+ /* fields after this shouldn't be cleared on stat reset */
+ uint64_t start_group_wait_time;
+ uint64_t start_idle_time;
+ uint64_t start_empty_time;
+ uint16_t flags;
+#endif /* CONFIG_BFQ_GROUP_IOSCHED */
+};
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+
+/*
+ * struct bfq_group_data - per-blkcg storage for the blkio subsystem.
+ *
+ * @ps: @blkcg_policy_storage that this structure inherits
+ * @weight: weight of the bfq_group
+ */
+struct bfq_group_data {
+ /* must be the first member */
+ struct blkcg_policy_data pd;
+
+ unsigned short weight;
+};
+
+/**
+ * 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).
+ * @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.
+ * @stats: stats for this bfqg.
+ *
+ * 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 @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 {
+ /* must be the first member */
+ struct blkg_policy_data pd;
+
+ struct bfq_entity entity;
+ struct bfq_sched_data sched_data;
+
+ void *bfqd;
+
+ struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR];
+ struct bfq_queue *async_idle_bfqq;
+
+ struct bfq_entity *my_entity;
+
+ struct bfqg_stats stats;
+};
+
+#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;
+
+ struct rb_root rq_pos_tree;
+};
+#endif
+
static struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity);
+static unsigned int bfq_class_idx(struct bfq_entity *entity)
+{
+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+ return bfqq ? bfqq->ioprio_class - 1 :
+ BFQ_DEFAULT_GRP_CLASS - 1;
+}
+
static struct bfq_service_tree *
bfq_entity_service_tree(struct bfq_entity *entity)
{
struct bfq_sched_data *sched_data = entity->sched_data;
- struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
- unsigned int idx = bfqq ? bfqq->ioprio_class - 1 :
- BFQ_DEFAULT_GRP_CLASS - 1;
+ unsigned int idx = bfq_class_idx(entity);
return sched_data->service_tree + idx;
}
@@ -549,16 +695,9 @@ static void bfq_put_queue(struct bfq_queue *bfqq);
static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
struct bio *bio, bool is_sync,
struct bfq_io_cq *bic);
+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);
-/*
- * Array of async queues for all the processes, one queue
- * per ioprio value per ioprio_class.
- */
-struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR];
-/* Async queue for the idle class (ioprio is ignored) */
-struct bfq_queue *async_idle_bfqq;
-
/* Expiration time of sync (0) and async (1) requests, in ns. */
static const u64 bfq_fifo_expire[2] = { NSEC_PER_SEC / 4, NSEC_PER_SEC / 8 };
@@ -643,26 +782,212 @@ static struct bfq_io_cq *bfq_bic_lookup(struct bfq_data *bfqd,
return NULL;
}
+/*
+ * Scheduler run of queue, if there are requests pending and no one in the
+ * driver that will restart queueing.
+ */
+static void bfq_schedule_dispatch(struct bfq_data *bfqd)
+{
+ if (bfqd->queued != 0) {
+ bfq_log(bfqd, "schedule dispatch");
+ blk_mq_run_hw_queues(bfqd->queue, true);
+ }
+}
+
+/**
+ * bfq_gt - compare two timestamps.
+ * @a: first ts.
+ * @b: second ts.
+ *
+ * Return @a > @b, dealing with wrapping correctly.
+ */
+static int bfq_gt(u64 a, u64 b)
+{
+ return (s64)(a - b) > 0;
+}
+
+static struct bfq_entity *bfq_root_active_entity(struct rb_root *tree)
+{
+ struct rb_node *node = tree->rb_node;
+
+ return rb_entry(node, struct bfq_entity, rb_node);
+}
+
+static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd);
+
+static bool bfq_update_parent_budget(struct bfq_entity *next_in_service);
+
+/**
+ * bfq_update_next_in_service - update sd->next_in_service
+ * @sd: sched_data for which to perform the update.
+ * @new_entity: if not NULL, pointer to the entity whose activation,
+ * requeueing or repositionig triggered the invocation of
+ * this function.
+ *
+ * This function is called to update sd->next_in_service, which, in
+ * its turn, may change as a consequence of the insertion or
+ * extraction of an entity into/from one of the active trees of
+ * sd. These insertions/extractions occur as a consequence of
+ * activations/deactivations of entities, with some activations being
+ * 'true' activations, and other activations being requeueings (i.e.,
+ * implementing the second, requeueing phase of the mechanism used to
+ * reposition an entity in its active tree; see comments on
+ * __bfq_activate_entity and __bfq_requeue_entity for details). In
+ * both the last two activation sub-cases, new_entity points to the
+ * just activated or requeued entity.
+ *
+ * Returns true if sd->next_in_service changes in such a way that
+ * entity->parent may become the next_in_service for its parent
+ * entity.
+ */
+static bool bfq_update_next_in_service(struct bfq_sched_data *sd,
+ struct bfq_entity *new_entity)
+{
+ struct bfq_entity *next_in_service = sd->next_in_service;
+ bool parent_sched_may_change = false;
+
+ /*
+ * If this update is triggered by the activation, requeueing
+ * or repositiong of an entity that does not coincide with
+ * sd->next_in_service, then a full lookup in the active tree
+ * can be avoided. In fact, it is enough to check whether the
+ * just-modified entity has a higher priority than
+ * sd->next_in_service, or, even if it has the same priority
+ * as sd->next_in_service, is eligible and has a lower virtual
+ * finish time than sd->next_in_service. If this compound
+ * condition holds, then the new entity becomes the new
+ * next_in_service. Otherwise no change is needed.
+ */
+ if (new_entity && new_entity != sd->next_in_service) {
+ /*
+ * Flag used to decide whether to replace
+ * sd->next_in_service with new_entity. Tentatively
+ * set to true, and left as true if
+ * sd->next_in_service is NULL.
+ */
+ bool replace_next = true;
+
+ /*
+ * If there is already a next_in_service candidate
+ * entity, then compare class priorities or timestamps
+ * to decide whether to replace sd->service_tree with
+ * new_entity.
+ */
+ if (next_in_service) {
+ unsigned int new_entity_class_idx =
+ bfq_class_idx(new_entity);
+ struct bfq_service_tree *st =
+ sd->service_tree + new_entity_class_idx;
+
+ /*
+ * For efficiency, evaluate the most likely
+ * sub-condition first.
+ */
+ replace_next =
+ (new_entity_class_idx ==
+ bfq_class_idx(next_in_service)
+ &&
+ !bfq_gt(new_entity->start, st->vtime)
+ &&
+ bfq_gt(next_in_service->finish,
+ new_entity->finish))
+ ||
+ new_entity_class_idx <
+ bfq_class_idx(next_in_service);
+ }
+
+ if (replace_next)
+ next_in_service = new_entity;
+ } else /* invoked because of a deactivation: lookup needed */
+ next_in_service = bfq_lookup_next_entity(sd);
+
+ if (next_in_service) {
+ parent_sched_may_change = !sd->next_in_service ||
+ bfq_update_parent_budget(next_in_service);
+ }
+
+ sd->next_in_service = next_in_service;
+
+ if (!next_in_service)
+ return parent_sched_may_change;
+
+ return parent_sched_may_change;
+}
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+/* both next loops stop at one of the child entities of the root group */
#define for_each_entity(entity) \
- for (; entity ; entity = NULL)
+ for (; entity ; entity = entity->parent)
#define for_each_entity_safe(entity, parent) \
- for (parent = NULL; entity ; entity = parent)
+ for (; entity && ({ parent = entity->parent; 1; }); entity = parent)
-static int bfq_update_next_in_service(struct bfq_sched_data *sd)
+/*
+ * Returns true if this budget changes may let next_in_service->parent
+ * become the next_in_service entity for its parent entity.
+ */
+static bool bfq_update_parent_budget(struct bfq_entity *next_in_service)
{
- return 0;
+ struct bfq_entity *bfqg_entity;
+ struct bfq_group *bfqg;
+ struct bfq_sched_data *group_sd;
+ bool ret = false;
+
+ group_sd = next_in_service->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 in-service entity.
+ */
+ bfqg_entity = bfqg->my_entity;
+ if (bfqg_entity) {
+ if (bfqg_entity->budget > next_in_service->budget)
+ ret = true;
+ bfqg_entity->budget = next_in_service->budget;
+ }
+
+ return ret;
+}
+
+/*
+ * This function tells whether entity stops being a candidate for next
+ * service, according to the following logic.
+ *
+ * This function is invoked for an entity that is about to be set in
+ * service. If such an entity is a queue, then the entity is no longer
+ * a candidate for next service (i.e, a candidate entity to serve
+ * after the in-service entity is expired). The function then returns
+ * true.
+ */
+static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
+{
+ if (bfq_entity_to_bfqq(entity))
+ return true;
+
+ return false;
}
-static void bfq_check_next_in_service(struct bfq_sched_data *sd,
- struct bfq_entity *entity)
+#else /* CONFIG_BFQ_GROUP_IOSCHED */
+#define for_each_entity(entity) \
+ for (; entity ; entity = NULL)
+
+#define for_each_entity_safe(entity, parent) \
+ for (parent = NULL; entity ; entity = parent)
+
+static bool bfq_update_parent_budget(struct bfq_entity *next_in_service)
{
+ return false;
}
-static void bfq_update_budget(struct bfq_entity *next_in_service)
+static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
{
+ return true;
}
+#endif /* CONFIG_BFQ_GROUP_IOSCHED */
+
/*
* Shift for timestamp calculations. This actually limits the maximum
* service allowed in one timestamp delta (small shift values increase it),
@@ -672,18 +997,6 @@ static void bfq_update_budget(struct bfq_entity *next_in_service)
*/
#define WFQ_SERVICE_SHIFT 22
-/**
- * bfq_gt - compare two timestamps.
- * @a: first ts.
- * @b: second ts.
- *
- * Return @a > @b, dealing with wrapping correctly.
- */
-static int bfq_gt(u64 a, u64 b)
-{
- return (s64)(a - b) > 0;
-}
-
static struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity)
{
struct bfq_queue *bfqq = NULL;
@@ -902,6 +1215,11 @@ static void bfq_active_insert(struct bfq_service_tree *st,
{
struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
struct rb_node *node = &entity->rb_node;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ struct bfq_sched_data *sd = NULL;
+ struct bfq_group *bfqg = NULL;
+ struct bfq_data *bfqd = NULL;
+#endif
bfq_insert(&st->active, entity);
@@ -912,6 +1230,11 @@ static void bfq_active_insert(struct bfq_service_tree *st,
bfq_update_active_tree(node);
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ sd = entity->sched_data;
+ bfqg = container_of(sd, struct bfq_group, sched_data);
+ bfqd = (struct bfq_data *)bfqg->bfqd;
+#endif
if (bfqq)
list_add(&bfqq->bfqq_list, &bfqq->bfqd->active_list);
}
@@ -990,6 +1313,11 @@ static void bfq_active_extract(struct bfq_service_tree *st,
{
struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
struct rb_node *node;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ struct bfq_sched_data *sd = NULL;
+ struct bfq_group *bfqg = NULL;
+ struct bfq_data *bfqd = NULL;
+#endif
node = bfq_find_deepest(&entity->rb_node);
bfq_extract(&st->active, entity);
@@ -997,6 +1325,11 @@ static void bfq_active_extract(struct bfq_service_tree *st,
if (node)
bfq_update_active_tree(node);
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ sd = entity->sched_data;
+ bfqg = container_of(sd, struct bfq_group, sched_data);
+ bfqd = (struct bfq_data *)bfqg->bfqd;
+#endif
if (bfqq)
list_del(&bfqq->bfqq_list);
}
@@ -1039,7 +1372,7 @@ static void bfq_forget_entity(struct bfq_service_tree *st,
struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
struct bfq_sched_data *sd;
- entity->on_st = 0;
+ entity->on_st = false;
st->wsum -= entity->weight;
if (bfqq) {
sd = entity->sched_data;
@@ -1088,7 +1421,7 @@ static void bfq_forget_idle(struct bfq_service_tree *st)
static struct bfq_service_tree *
__bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
- struct bfq_entity *entity)
+ struct bfq_entity *entity)
{
struct bfq_service_tree *new_st = old_st;
@@ -1096,9 +1429,20 @@ __bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
unsigned short prev_weight, new_weight;
struct bfq_data *bfqd = NULL;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ struct bfq_sched_data *sd;
+ struct bfq_group *bfqg;
+#endif
if (bfqq)
bfqd = bfqq->bfqd;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ else {
+ sd = entity->my_sched_data;
+ bfqg = container_of(sd, struct bfq_group, sched_data);
+ bfqd = (struct bfq_data *)bfqg->bfqd;
+ }
+#endif
old_st->wsum -= entity->weight;
@@ -1144,6 +1488,9 @@ __bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
return new_st;
}
+static void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg);
+static struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
+
/**
* bfq_bfqq_served - update the scheduler status after selection for
* service.
@@ -1167,6 +1514,7 @@ static void bfq_bfqq_served(struct bfq_queue *bfqq, int served)
st->vtime += bfq_delta(served, st->wsum);
bfq_forget_idle(st);
}
+ bfqg_stats_set_start_empty_time(bfqq_group(bfqq));
bfq_log_bfqq(bfqq->bfqd, bfqq, "bfqq_served %d secs", served);
}
@@ -1189,72 +1537,10 @@ static void bfq_bfqq_charge_full_budget(struct bfq_queue *bfqq)
bfq_bfqq_served(bfqq, entity->budget - entity->service);
}
-/**
- * __bfq_activate_entity - activate an entity.
- * @entity: the entity being activated.
- * @non_blocking_wait_rq: true if this entity was waiting for a request
- *
- * 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,
- bool non_blocking_wait_rq)
+static void bfq_update_fin_time_enqueue(struct bfq_entity *entity,
+ struct bfq_service_tree *st,
+ bool backshifted)
{
- struct bfq_sched_data *sd = entity->sched_data;
- struct bfq_service_tree *st = bfq_entity_service_tree(entity);
- bool backshifted = false;
-
- if (entity == sd->in_service_entity) {
- /*
- * 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->in_service_entity = NULL;
- } else if (entity->tree == &st->active) {
- /*
- * Requeueing an entity due to a change of some
- * next_in_service entity below it. We reuse the
- * old start time.
- */
- bfq_active_extract(st, entity);
- } else {
- unsigned long long min_vstart;
-
- /* See comments on bfq_fqq_update_budg_for_activation */
- if (non_blocking_wait_rq && bfq_gt(st->vtime, entity->finish)) {
- backshifted = true;
- min_vstart = entity->finish;
- } else
- min_vstart = st->vtime;
-
- 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(min_vstart, entity->finish) ?
- min_vstart : 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 = min_vstart;
- st->wsum += entity->weight;
- bfq_get_entity(entity);
-
- entity->on_st = 1;
- }
- }
-
st = __bfq_entity_update_weight_prio(st, entity);
bfq_calc_finish(entity, entity->budget);
@@ -1296,144 +1582,331 @@ static void __bfq_activate_entity(struct bfq_entity *entity,
}
/**
- * bfq_activate_entity - activate an entity and its ancestors if necessary.
- * @entity: the entity to activate.
- * @non_blocking_wait_rq: true if this entity was waiting for a request
+ * __bfq_activate_entity - handle activation of entity.
+ * @entity: the entity being activated.
+ * @non_blocking_wait_rq: true if entity was waiting for a request
+ *
+ * Called for a 'true' activation, i.e., if entity is not active and
+ * one of its children receives a new request.
*
- * Activate @entity and all the entities on the path from it to the root.
+ * Basically, this function updates the timestamps of entity and
+ * inserts entity into its active tree, ater possible extracting it
+ * from its idle tree.
*/
-static void bfq_activate_entity(struct bfq_entity *entity,
- bool non_blocking_wait_rq)
+static void __bfq_activate_entity(struct bfq_entity *entity,
+ bool non_blocking_wait_rq)
{
- struct bfq_sched_data *sd;
+ struct bfq_service_tree *st = bfq_entity_service_tree(entity);
+ bool backshifted = false;
+ unsigned long long min_vstart;
- for_each_entity(entity) {
- __bfq_activate_entity(entity, non_blocking_wait_rq);
+ /* See comments on bfq_fqq_update_budg_for_activation */
+ if (non_blocking_wait_rq && bfq_gt(st->vtime, entity->finish)) {
+ backshifted = true;
+ min_vstart = entity->finish;
+ } else
+ min_vstart = st->vtime;
- sd = entity->sched_data;
- if (!bfq_update_next_in_service(sd))
- /*
- * No need to propagate the activation to the
- * upper entities, as they will be updated when
- * the in-service entity is rescheduled.
- */
- break;
+ 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(min_vstart, entity->finish) ?
+ min_vstart : 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 = min_vstart;
+ st->wsum += entity->weight;
+ bfq_get_entity(entity);
+
+ entity->on_st = true;
}
+
+ bfq_update_fin_time_enqueue(entity, st, backshifted);
}
/**
- * __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.
+ * __bfq_requeue_entity - handle requeueing or repositioning of an entity.
+ * @entity: the entity being requeued or repositioned.
*
- * 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.
+ * Requeueing is needed if this entity stops being served, which
+ * happens if a leaf descendant entity has expired. On the other hand,
+ * repositioning is needed if the next_inservice_entity for the child
+ * entity has changed. See the comments inside the function for
+ * details.
*
- * Return %1 if the caller should update the entity hierarchy, i.e.,
- * if the entity was in service or if it was the next_in_service for
- * its sched_data; return %0 otherwise.
+ * Basically, this function: 1) removes entity from its active tree if
+ * present there, 2) updates the timestamps of entity and 3) inserts
+ * entity back into its active tree (in the new, right position for
+ * the new values of the timestamps).
*/
-static int __bfq_deactivate_entity(struct bfq_entity *entity, int requeue)
+static void __bfq_requeue_entity(struct bfq_entity *entity)
{
struct bfq_sched_data *sd = entity->sched_data;
struct bfq_service_tree *st = bfq_entity_service_tree(entity);
- int was_in_service = entity == sd->in_service_entity;
- int ret = 0;
- if (!entity->on_st)
- return 0;
-
- if (was_in_service) {
+ if (entity == sd->in_service_entity) {
+ /*
+ * We are requeueing the current in-service entity,
+ * which may have to be done for one of the following
+ * reasons:
+ * - entity represents the in-service queue, and the
+ * in-service queue is being requeued after an
+ * expiration;
+ * - entity represents a group, and its budget has
+ * changed because one of its child entities has
+ * just been either activated or requeued for some
+ * reason; the timestamps of the entity need then to
+ * be updated, and the entity needs to be enqueued
+ * or repositioned accordingly.
+ *
+ * In particular, before requeueing, the start time of
+ * the entity must be moved forward to account for the
+ * service that the entity has received while in
+ * service. This is done by the next instructions. The
+ * finish time will then be updated according to this
+ * new value of the start time, and to the budget of
+ * the entity.
+ */
bfq_calc_finish(entity, entity->service);
- sd->in_service_entity = NULL;
- } else if (entity->tree == &st->active)
+ entity->start = entity->finish;
+ /*
+ * In addition, if the entity had more than one child
+ * when set in service, then was not extracted from
+ * the active tree. This implies that the position of
+ * the entity in the active tree may need to be
+ * changed now, because we have just updated the start
+ * time of the entity, and we will update its finish
+ * time in a moment (the requeueing is then, more
+ * precisely, a repositioning in this case). To
+ * implement this repositioning, we: 1) dequeue the
+ * entity here, 2) update the finish time and
+ * requeue the entity according to the new
+ * timestamps below.
+ */
+ if (entity->tree)
+ bfq_active_extract(st, entity);
+ } else { /* The entity is already active, and not in service */
+ /*
+ * In this case, this function gets called only if the
+ * next_in_service entity below this entity has
+ * changed, and this change has caused the budget of
+ * this entity to change, which, finally implies that
+ * the finish time of this entity must be
+ * updated. Such an update may cause the scheduling,
+ * i.e., the position in the active tree, of this
+ * entity to change. We handle this change by: 1)
+ * dequeueing the entity here, 2) updating the finish
+ * time and requeueing the entity according to the new
+ * timestamps below. This is the same approach as the
+ * non-extracted-entity sub-case above.
+ */
bfq_active_extract(st, entity);
- else if (entity->tree == &st->idle)
- bfq_idle_extract(st, entity);
+ }
- if (was_in_service || sd->next_in_service == entity)
- ret = bfq_update_next_in_service(sd);
+ bfq_update_fin_time_enqueue(entity, st, false);
+}
- if (!requeue || !bfq_gt(entity->finish, st->vtime))
- bfq_forget_entity(st, entity);
- else
- bfq_idle_insert(st, entity);
+static void __bfq_activate_requeue_entity(struct bfq_entity *entity,
+ struct bfq_sched_data *sd,
+ bool non_blocking_wait_rq)
+{
+ struct bfq_service_tree *st = bfq_entity_service_tree(entity);
- return ret;
+ if (sd->in_service_entity == entity || entity->tree == &st->active)
+ /*
+ * in service or already queued on the active tree,
+ * requeue or reposition
+ */
+ __bfq_requeue_entity(entity);
+ else
+ /*
+ * Not in service and not queued on its active tree:
+ * the activity is idle and this is a true activation.
+ */
+ __bfq_activate_entity(entity, non_blocking_wait_rq);
}
+
/**
- * bfq_deactivate_entity - deactivate an entity.
- * @entity: the entity to deactivate.
- * @requeue: true if the entity can be put on the idle tree
+ * bfq_activate_entity - activate or requeue an entity representing a bfq_queue,
+ * and activate, requeue or reposition all ancestors
+ * for which such an update becomes necessary.
+ * @entity: the entity to activate.
+ * @non_blocking_wait_rq: true if this entity was waiting for a request
+ * @requeue: true if this is a requeue, which implies that bfqq is
+ * being expired; thus ALL its ancestors stop being served and must
+ * therefore be requeued
*/
-static void bfq_deactivate_entity(struct bfq_entity *entity, int requeue)
+static void bfq_activate_requeue_entity(struct bfq_entity *entity,
+ bool non_blocking_wait_rq,
+ bool requeue)
{
struct bfq_sched_data *sd;
- struct bfq_entity *parent = NULL;
- for_each_entity_safe(entity, parent) {
+ for_each_entity(entity) {
sd = entity->sched_data;
+ __bfq_activate_requeue_entity(entity, sd, non_blocking_wait_rq);
- if (!__bfq_deactivate_entity(entity, requeue))
- /*
- * The parent entity is still backlogged, and
- * we don't need to update it as it is still
- * in service.
- */
+ if (!bfq_update_next_in_service(sd, entity) && !requeue)
+ break;
+ }
+}
+
+/**
+ * __bfq_deactivate_entity - deactivate an entity from its service tree.
+ * @entity: the entity to deactivate.
+ * @ins_into_idle_tree: if false, the entity will not be put into the
+ * idle tree.
+ *
+ * Deactivates an entity, independently from its previous state. Must
+ * be invoked only if entity is on a service tree. Extracts the entity
+ * from that tree, and if necessary and allowed, puts it on the idle
+ * tree.
+ */
+static bool __bfq_deactivate_entity(struct bfq_entity *entity,
+ bool ins_into_idle_tree)
+{
+ struct bfq_sched_data *sd = entity->sched_data;
+ struct bfq_service_tree *st = bfq_entity_service_tree(entity);
+ bool was_in_service = entity == sd->in_service_entity;
+
+ if (!entity->on_st) /* entity never activated, or already inactive */
+ return false;
+
+ if (was_in_service)
+ bfq_calc_finish(entity, entity->service);
+
+ if (entity->tree == &st->active)
+ bfq_active_extract(st, entity);
+ else if (!was_in_service && entity->tree == &st->idle)
+ bfq_idle_extract(st, entity);
+
+ if (!ins_into_idle_tree || !bfq_gt(entity->finish, st->vtime))
+ bfq_forget_entity(st, entity);
+ else
+ bfq_idle_insert(st, entity);
+
+ return true;
+}
+
+/**
+ * bfq_deactivate_entity - deactivate an entity representing a bfq_queue.
+ * @entity: the entity to deactivate.
+ * @ins_into_idle_tree: true if the entity can be put on the idle tree
+ */
+static void bfq_deactivate_entity(struct bfq_entity *entity,
+ bool ins_into_idle_tree,
+ bool expiration)
+{
+ struct bfq_sched_data *sd;
+ struct bfq_entity *parent = NULL;
+
+ for_each_entity_safe(entity, parent) {
+ sd = entity->sched_data;
+
+ if (!__bfq_deactivate_entity(entity, ins_into_idle_tree)) {
+ /*
+ * Entity is not any tree any more, so, this
+ * deactivation is a no-op, and there is
+ * nothing to change for upper-level entities
+ * (in case of expiration, this can never
+ * happen).
+ */
+ return;
+ }
+
+ if (sd->next_in_service == entity)
+ /*
+ * entity was the next_in_service entity,
+ * then, since entity has just been
+ * deactivated, a new one must be found.
+ */
+ bfq_update_next_in_service(sd, NULL);
+
+ if (sd->next_in_service)
+ /*
+ * The parent entity is still backlogged,
+ * because next_in_service is not NULL. So, no
+ * further upwards deactivation must be
+ * performed. Yet, next_in_service has
+ * changed. Then the schedule does need to be
+ * updated upwards.
+ */
break;
- if (sd->next_in_service)
- /*
- * The parent entity is still backlogged and
- * the budgets on the path towards the root
- * need to be updated.
- */
- goto update;
-
/*
- * If we get here, then the parent is no more backlogged and
- * we want to propagate the deactivation upwards.
+ * If we get here, then the parent is no more
+ * backlogged and we need to propagate the
+ * deactivation upwards. Thus let the loop go on.
*/
- requeue = 1;
- }
- return;
+ /*
+ * Also let parent be queued into the idle tree on
+ * deactivation, to preserve service guarantees, and
+ * assuming that who invoked this function does not
+ * need parent entities too to be removed completely.
+ */
+ ins_into_idle_tree = true;
+ }
-update:
+ /*
+ * If the deactivation loop is fully executed, then there are
+ * no more entities to touch and next loop is not executed at
+ * all. Otherwise, requeue remaining entities if they are
+ * about to stop receiving service, or reposition them if this
+ * is not the case.
+ */
entity = parent;
for_each_entity(entity) {
- __bfq_activate_entity(entity, false);
+ /*
+ * Invoke __bfq_requeue_entity on entity, even if
+ * already active, to requeue/reposition it in the
+ * active tree (because sd->next_in_service has
+ * changed)
+ */
+ __bfq_requeue_entity(entity);
sd = entity->sched_data;
- if (!bfq_update_next_in_service(sd))
+ if (!bfq_update_next_in_service(sd, entity) &&
+ !expiration)
+ /*
+ * next_in_service unchanged or not causing
+ * any change in entity->parent->sd, and no
+ * requeueing needed for expiration: stop
+ * here.
+ */
break;
}
}
/**
- * bfq_update_vtime - update vtime if necessary.
+ * bfq_calc_vtime_jump - compute the value to which the vtime should jump,
+ * if needed, to have at least one entity eligible.
* @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 processes getting timestamps after a
- * vtime skip done because we needed a ->first_active entity on some
- * intermediate node.
+ * Assumes that st is not empty.
*/
-static void bfq_update_vtime(struct bfq_service_tree *st)
+static u64 bfq_calc_vtime_jump(struct bfq_service_tree *st)
{
- struct bfq_entity *entry;
- struct rb_node *node = st->active.rb_node;
+ struct bfq_entity *root_entity = bfq_root_active_entity(&st->active);
+
+ if (bfq_gt(root_entity->min_start, st->vtime))
+ return root_entity->min_start;
+
+ return st->vtime;
+}
- entry = rb_entry(node, struct bfq_entity, rb_node);
- if (bfq_gt(entry->min_start, st->vtime)) {
- st->vtime = entry->min_start;
+static void bfq_update_vtime(struct bfq_service_tree *st, u64 new_value)
+{
+ if (new_value > st->vtime) {
+ st->vtime = new_value;
bfq_forget_idle(st);
}
}
@@ -1442,6 +1915,7 @@ static void bfq_update_vtime(struct bfq_service_tree *st)
* bfq_first_active_entity - find the eligible entity with
* the smallest finish time
* @st: the service tree to select from.
+ * @vtime: the system virtual to use as a reference for eligibility
*
* 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
@@ -1449,7 +1923,8 @@ static void bfq_update_vtime(struct bfq_service_tree *st)
* 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)
+static struct bfq_entity *bfq_first_active_entity(struct bfq_service_tree *st,
+ u64 vtime)
{
struct bfq_entity *entry, *first = NULL;
struct rb_node *node = st->active.rb_node;
@@ -1457,13 +1932,13 @@ static struct bfq_entity *bfq_first_active_entity(struct bfq_service_tree *st)
while (node) {
entry = rb_entry(node, struct bfq_entity, rb_node);
left:
- if (!bfq_gt(entry->start, st->vtime))
+ if (!bfq_gt(entry->start, vtime))
first = entry;
if (node->rb_left) {
entry = rb_entry(node->rb_left,
struct bfq_entity, rb_node);
- if (!bfq_gt(entry->min_start, st->vtime)) {
+ if (!bfq_gt(entry->min_start, vtime)) {
node = node->rb_left;
goto left;
}
@@ -1473,193 +1948,1413 @@ static struct bfq_entity *bfq_first_active_entity(struct bfq_service_tree *st)
node = node->rb_right;
}
- return first;
+ return first;
+}
+
+/**
+ * __bfq_lookup_next_entity - return the first eligible entity in @st.
+ * @st: the service tree.
+ *
+ * If there is no in-service entity for the sched_data st belongs to,
+ * then return the entity that will be set in service if:
+ * 1) the parent entity this st belongs to is set in service;
+ * 2) no entity belonging to such parent entity undergoes a state change
+ * that would influence the timestamps of the entity (e.g., becomes idle,
+ * becomes backlogged, changes its budget, ...).
+ *
+ * In this first case, update the virtual time in @st too (see the
+ * comments on this update inside the function).
+ *
+ * In constrast, if there is an in-service entity, then return the
+ * entity that would be set in service if not only the above
+ * conditions, but also the next one held true: the currently
+ * in-service entity, on expiration,
+ * 1) gets a finish time equal to the current one, or
+ * 2) is not eligible any more, or
+ * 3) is idle.
+ */
+static struct bfq_entity *
+__bfq_lookup_next_entity(struct bfq_service_tree *st, bool in_service)
+{
+ struct bfq_entity *entity;
+ u64 new_vtime;
+
+ if (RB_EMPTY_ROOT(&st->active))
+ return NULL;
+
+ /*
+ * Get the value of the system virtual time for which at
+ * least one entity is eligible.
+ */
+ new_vtime = bfq_calc_vtime_jump(st);
+
+ /*
+ * If there is no in-service entity for the sched_data this
+ * active tree belongs to, then push the system virtual time
+ * up to the value that guarantees that at least one entity is
+ * eligible. If, instead, there is an in-service entity, then
+ * do not make any such update, because there is already an
+ * eligible entity, namely the in-service one (even if the
+ * entity is not on st, because it was extracted when set in
+ * service).
+ */
+ if (!in_service)
+ bfq_update_vtime(st, new_vtime);
+
+ entity = bfq_first_active_entity(st, new_vtime);
+
+ return entity;
+}
+
+/**
+ * bfq_lookup_next_entity - return the first eligible entity in @sd.
+ * @sd: the sched_data.
+ *
+ * This function is invoked when there has been a change in the trees
+ * for sd, and we need know what is the new next entity after this
+ * change.
+ */
+static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd)
+{
+ struct bfq_service_tree *st = sd->service_tree;
+ struct bfq_service_tree *idle_class_st = st + (BFQ_IOPRIO_CLASSES - 1);
+ struct bfq_entity *entity = NULL;
+ int class_idx = 0;
+
+ /*
+ * Choose from idle class, if needed to guarantee a minimum
+ * bandwidth to this class (and if there is some active entity
+ * in idle class). This should also mitigate
+ * priority-inversion problems in case a low priority task is
+ * holding file system resources.
+ */
+ if (time_is_before_jiffies(sd->bfq_class_idle_last_service +
+ BFQ_CL_IDLE_TIMEOUT)) {
+ if (!RB_EMPTY_ROOT(&idle_class_st->active))
+ class_idx = BFQ_IOPRIO_CLASSES - 1;
+ /* About to be served if backlogged, or not yet backlogged */
+ sd->bfq_class_idle_last_service = jiffies;
+ }
+
+ /*
+ * Find the next entity to serve for the highest-priority
+ * class, unless the idle class needs to be served.
+ */
+ for (; class_idx < BFQ_IOPRIO_CLASSES; class_idx++) {
+ entity = __bfq_lookup_next_entity(st + class_idx,
+ sd->in_service_entity);
+
+ if (entity)
+ break;
+ }
+
+ if (!entity)
+ return NULL;
+
+ return entity;
+}
+
+static bool next_queue_may_preempt(struct bfq_data *bfqd)
+{
+ struct bfq_sched_data *sd = &bfqd->root_group->sched_data;
+
+ return sd->next_in_service != sd->in_service_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;
+
+ if (bfqd->busy_queues == 0)
+ return NULL;
+
+ /*
+ * Traverse the path from the root to the leaf entity to
+ * serve. Set in service all the entities visited along the
+ * way.
+ */
+ sd = &bfqd->root_group->sched_data;
+ for (; sd ; sd = entity->my_sched_data) {
+ /*
+ * WARNING. We are about to set the in-service entity
+ * to sd->next_in_service, i.e., to the (cached) value
+ * returned by bfq_lookup_next_entity(sd) the last
+ * time it was invoked, i.e., the last time when the
+ * service order in sd changed as a consequence of the
+ * activation or deactivation of an entity. In this
+ * respect, if we execute bfq_lookup_next_entity(sd)
+ * in this very moment, it may, although with low
+ * probability, yield a different entity than that
+ * pointed to by sd->next_in_service. This rare event
+ * happens in case there was no CLASS_IDLE entity to
+ * serve for sd when bfq_lookup_next_entity(sd) was
+ * invoked for the last time, while there is now one
+ * such entity.
+ *
+ * If the above event happens, then the scheduling of
+ * such entity in CLASS_IDLE is postponed until the
+ * service of the sd->next_in_service entity
+ * finishes. In fact, when the latter is expired,
+ * bfq_lookup_next_entity(sd) gets called again,
+ * exactly to update sd->next_in_service.
+ */
+
+ /* Make next_in_service entity become in_service_entity */
+ entity = sd->next_in_service;
+ sd->in_service_entity = entity;
+
+ /*
+ * Reset the accumulator of the amount of service that
+ * the entity is about to receive.
+ */
+ entity->service = 0;
+
+ /*
+ * If entity is no longer a candidate for next
+ * service, then we extract it from its active tree,
+ * for the following reason. To further boost the
+ * throughput in some special case, BFQ needs to know
+ * which is the next candidate entity to serve, while
+ * there is already an entity in service. In this
+ * respect, to make it easy to compute/update the next
+ * candidate entity to serve after the current
+ * candidate has been set in service, there is a case
+ * where it is necessary to extract the current
+ * candidate from its service tree. Such a case is
+ * when the entity just set in service cannot be also
+ * a candidate for next service. Details about when
+ * this conditions holds are reported in the comments
+ * on the function bfq_no_longer_next_in_service()
+ * invoked below.
+ */
+ if (bfq_no_longer_next_in_service(entity))
+ bfq_active_extract(bfq_entity_service_tree(entity),
+ entity);
+
+ /*
+ * For the same reason why we may have just extracted
+ * entity from its active tree, we may need to update
+ * next_in_service for the sched_data of entity too,
+ * regardless of whether entity has been extracted.
+ * In fact, even if entity has not been extracted, a
+ * descendant entity may get extracted. Such an event
+ * would cause a change in next_in_service for the
+ * level of the descendant entity, and thus possibly
+ * back to upper levels.
+ *
+ * We cannot perform the resulting needed update
+ * before the end of this loop, because, to know which
+ * is the correct next-to-serve candidate entity for
+ * each level, we need first to find the leaf entity
+ * to set in service. In fact, only after we know
+ * which is the next-to-serve leaf entity, we can
+ * discover whether the parent entity of the leaf
+ * entity becomes the next-to-serve, and so on.
+ */
+
+ }
+
+ bfqq = bfq_entity_to_bfqq(entity);
+
+ /*
+ * We can finally update all next-to-serve entities along the
+ * path from the leaf entity just set in service to the root.
+ */
+ for_each_entity(entity) {
+ struct bfq_sched_data *sd = entity->sched_data;
+
+ if (!bfq_update_next_in_service(sd, NULL))
+ break;
+ }
+
+ return bfqq;
+}
+
+static void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
+{
+ struct bfq_entity *entity = &bfqd->in_service_queue->entity;
+
+ if (bfqd->in_service_bic) {
+ put_io_context(bfqd->in_service_bic->icq.ioc);
+ bfqd->in_service_bic = NULL;
+ }
+
+ bfq_clear_bfqq_wait_request(bfqd->in_service_queue);
+ hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
+ bfqd->in_service_queue = NULL;
+
+ /*
+ * When this function is called, all in-service entities have
+ * been properly deactivated or requeued, so we can safely
+ * execute the final step: reset in_service_entity along the
+ * path from entity to the root.
+ */
+ for_each_entity(entity)
+ entity->sched_data->in_service_entity = NULL;
+}
+
+static void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ bool ins_into_idle_tree, bool expiration)
+{
+ struct bfq_entity *entity = &bfqq->entity;
+
+ bfq_deactivate_entity(entity, ins_into_idle_tree, expiration);
+}
+
+static void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+ struct bfq_entity *entity = &bfqq->entity;
+
+ bfq_activate_requeue_entity(entity, bfq_bfqq_non_blocking_wait_rq(bfqq),
+ false);
+ bfq_clear_bfqq_non_blocking_wait_rq(bfqq);
+}
+
+static void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+ struct bfq_entity *entity = &bfqq->entity;
+
+ bfq_activate_requeue_entity(entity, false,
+ bfqq == bfqd->in_service_queue);
+}
+
+static void bfqg_stats_update_dequeue(struct bfq_group *bfqg);
+
+/*
+ * Called when the bfqq no longer has requests pending, remove it from
+ * the service tree. As a special case, it can be invoked during an
+ * expiration.
+ */
+static void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ bool expiration)
+{
+ bfq_log_bfqq(bfqd, bfqq, "del from busy");
+
+ bfq_clear_bfqq_busy(bfqq);
+
+ bfqd->busy_queues--;
+
+ bfqg_stats_update_dequeue(bfqq_group(bfqq));
+
+ bfq_deactivate_bfqq(bfqd, bfqq, true, expiration);
+}
+
+/*
+ * Called when an inactive queue receives a new request.
+ */
+static void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+ bfq_log_bfqq(bfqd, bfqq, "add to busy");
+
+ bfq_activate_bfqq(bfqd, bfqq);
+
+ bfq_mark_bfqq_busy(bfqq);
+ bfqd->busy_queues++;
+}
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+
+/* bfqg stats flags */
+enum bfqg_stats_flags {
+ BFQG_stats_waiting = 0,
+ BFQG_stats_idling,
+ BFQG_stats_empty,
+};
+
+#define BFQG_FLAG_FNS(name) \
+static void bfqg_stats_mark_##name(struct bfqg_stats *stats) \
+{ \
+ stats->flags |= (1 << BFQG_stats_##name); \
+} \
+static void bfqg_stats_clear_##name(struct bfqg_stats *stats) \
+{ \
+ stats->flags &= ~(1 << BFQG_stats_##name); \
+} \
+static int bfqg_stats_##name(struct bfqg_stats *stats) \
+{ \
+ return (stats->flags & (1 << BFQG_stats_##name)) != 0; \
+} \
+
+BFQG_FLAG_FNS(waiting)
+BFQG_FLAG_FNS(idling)
+BFQG_FLAG_FNS(empty)
+#undef BFQG_FLAG_FNS
+
+/* This should be called with the queue_lock held. */
+static void bfqg_stats_update_group_wait_time(struct bfqg_stats *stats)
+{
+ unsigned long long now;
+
+ if (!bfqg_stats_waiting(stats))
+ return;
+
+ now = sched_clock();
+ if (time_after64(now, stats->start_group_wait_time))
+ blkg_stat_add(&stats->group_wait_time,
+ now - stats->start_group_wait_time);
+ bfqg_stats_clear_waiting(stats);
+}
+
+/* This should be called with the queue_lock held. */
+static void bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg,
+ struct bfq_group *curr_bfqg)
+{
+ struct bfqg_stats *stats = &bfqg->stats;
+
+ if (bfqg_stats_waiting(stats))
+ return;
+ if (bfqg == curr_bfqg)
+ return;
+ stats->start_group_wait_time = sched_clock();
+ bfqg_stats_mark_waiting(stats);
+}
+
+/* This should be called with the queue_lock held. */
+static void bfqg_stats_end_empty_time(struct bfqg_stats *stats)
+{
+ unsigned long long now;
+
+ if (!bfqg_stats_empty(stats))
+ return;
+
+ now = sched_clock();
+ if (time_after64(now, stats->start_empty_time))
+ blkg_stat_add(&stats->empty_time,
+ now - stats->start_empty_time);
+ bfqg_stats_clear_empty(stats);
+}
+
+static void bfqg_stats_update_dequeue(struct bfq_group *bfqg)
+{
+ blkg_stat_add(&bfqg->stats.dequeue, 1);
+}
+
+static void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg)
+{
+ struct bfqg_stats *stats = &bfqg->stats;
+
+ if (blkg_rwstat_total(&stats->queued))
+ return;
+
+ /*
+ * group is already marked empty. This can happen if bfqq got new
+ * request in parent group and moved to this group while being added
+ * to service tree. Just ignore the event and move on.
+ */
+ if (bfqg_stats_empty(stats))
+ return;
+
+ stats->start_empty_time = sched_clock();
+ bfqg_stats_mark_empty(stats);
+}
+
+static void bfqg_stats_update_idle_time(struct bfq_group *bfqg)
+{
+ struct bfqg_stats *stats = &bfqg->stats;
+
+ if (bfqg_stats_idling(stats)) {
+ unsigned long long now = sched_clock();
+
+ if (time_after64(now, stats->start_idle_time))
+ blkg_stat_add(&stats->idle_time,
+ now - stats->start_idle_time);
+ bfqg_stats_clear_idling(stats);
+ }
+}
+
+static void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg)
+{
+ struct bfqg_stats *stats = &bfqg->stats;
+
+ stats->start_idle_time = sched_clock();
+ bfqg_stats_mark_idling(stats);
+}
+
+static void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg)
+{
+ struct bfqg_stats *stats = &bfqg->stats;
+
+ blkg_stat_add(&stats->avg_queue_size_sum,
+ blkg_rwstat_total(&stats->queued));
+ blkg_stat_add(&stats->avg_queue_size_samples, 1);
+ bfqg_stats_update_group_wait_time(stats);
+}
+
+/*
+ * blk-cgroup policy-related handlers
+ * The following functions help in converting between blk-cgroup
+ * internal structures and BFQ-specific structures.
+ */
+
+static struct bfq_group *pd_to_bfqg(struct blkg_policy_data *pd)
+{
+ return pd ? container_of(pd, struct bfq_group, pd) : NULL;
+}
+
+static struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg)
+{
+ return pd_to_blkg(&bfqg->pd);
+}
+
+static struct blkcg_policy blkcg_policy_bfq;
+
+static struct bfq_group *blkg_to_bfqg(struct blkcg_gq *blkg)
+{
+ return pd_to_bfqg(blkg_to_pd(blkg, &blkcg_policy_bfq));
+}
+
+/*
+ * bfq_group handlers
+ * The following functions help in navigating the bfq_group hierarchy
+ * by allowing to find the parent of a bfq_group or the bfq_group
+ * associated to a bfq_queue.
+ */
+
+static struct bfq_group *bfqg_parent(struct bfq_group *bfqg)
+{
+ struct blkcg_gq *pblkg = bfqg_to_blkg(bfqg)->parent;
+
+ return pblkg ? blkg_to_bfqg(pblkg) : NULL;
+}
+
+static struct bfq_group *bfqq_group(struct bfq_queue *bfqq)
+{
+ struct bfq_entity *group_entity = bfqq->entity.parent;
+
+ return group_entity ? container_of(group_entity, struct bfq_group,
+ entity) :
+ bfqq->bfqd->root_group;
+}
+
+/*
+ * The following two functions handle get and put of a bfq_group by
+ * wrapping the related blk-cgroup hooks.
+ */
+
+static void bfqg_get(struct bfq_group *bfqg)
+{
+ return blkg_get(bfqg_to_blkg(bfqg));
+}
+
+static void bfqg_put(struct bfq_group *bfqg)
+{
+ return blkg_put(bfqg_to_blkg(bfqg));
+}
+
+static void bfqg_stats_update_io_add(struct bfq_group *bfqg,
+ struct bfq_queue *bfqq,
+ unsigned int op)
+{
+ blkg_rwstat_add(&bfqg->stats.queued, op, 1);
+ bfqg_stats_end_empty_time(&bfqg->stats);
+ if (!(bfqq == ((struct bfq_data *)bfqg->bfqd)->in_service_queue))
+ bfqg_stats_set_start_group_wait_time(bfqg, bfqq_group(bfqq));
+}
+
+static void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op)
+{
+ blkg_rwstat_add(&bfqg->stats.queued, op, -1);
+}
+
+static void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op)
+{
+ blkg_rwstat_add(&bfqg->stats.merged, op, 1);
+}
+
+static void bfqg_stats_update_completion(struct bfq_group *bfqg,
+ uint64_t start_time, uint64_t io_start_time,
+ unsigned int op)
+{
+ struct bfqg_stats *stats = &bfqg->stats;
+ unsigned long long now = sched_clock();
+
+ if (time_after64(now, io_start_time))
+ blkg_rwstat_add(&stats->service_time, op,
+ now - io_start_time);
+ if (time_after64(io_start_time, start_time))
+ blkg_rwstat_add(&stats->wait_time, op,
+ io_start_time - start_time);
+}
+
+/* @stats = 0 */
+static void bfqg_stats_reset(struct bfqg_stats *stats)
+{
+ /* queued stats shouldn't be cleared */
+ blkg_rwstat_reset(&stats->merged);
+ blkg_rwstat_reset(&stats->service_time);
+ blkg_rwstat_reset(&stats->wait_time);
+ blkg_stat_reset(&stats->time);
+ blkg_stat_reset(&stats->avg_queue_size_sum);
+ blkg_stat_reset(&stats->avg_queue_size_samples);
+ blkg_stat_reset(&stats->dequeue);
+ blkg_stat_reset(&stats->group_wait_time);
+ blkg_stat_reset(&stats->idle_time);
+ blkg_stat_reset(&stats->empty_time);
+}
+
+/* @to += @from */
+static void bfqg_stats_add_aux(struct bfqg_stats *to, struct bfqg_stats *from)
+{
+ if (!to || !from)
+ return;
+
+ /* queued stats shouldn't be cleared */
+ blkg_rwstat_add_aux(&to->merged, &from->merged);
+ blkg_rwstat_add_aux(&to->service_time, &from->service_time);
+ blkg_rwstat_add_aux(&to->wait_time, &from->wait_time);
+ blkg_stat_add_aux(&from->time, &from->time);
+ blkg_stat_add_aux(&to->avg_queue_size_sum, &from->avg_queue_size_sum);
+ blkg_stat_add_aux(&to->avg_queue_size_samples,
+ &from->avg_queue_size_samples);
+ blkg_stat_add_aux(&to->dequeue, &from->dequeue);
+ blkg_stat_add_aux(&to->group_wait_time, &from->group_wait_time);
+ blkg_stat_add_aux(&to->idle_time, &from->idle_time);
+ blkg_stat_add_aux(&to->empty_time, &from->empty_time);
+}
+
+/*
+ * Transfer @bfqg's stats to its parent's aux counts so that the ancestors'
+ * recursive stats can still account for the amount used by this bfqg after
+ * it's gone.
+ */
+static void bfqg_stats_xfer_dead(struct bfq_group *bfqg)
+{
+ struct bfq_group *parent;
+
+ if (!bfqg) /* root_group */
+ return;
+
+ parent = bfqg_parent(bfqg);
+
+ lockdep_assert_held(bfqg_to_blkg(bfqg)->q->queue_lock);
+
+ if (unlikely(!parent))
+ return;
+
+ bfqg_stats_add_aux(&parent->stats, &bfqg->stats);
+ bfqg_stats_reset(&bfqg->stats);
+}
+
+static void bfq_init_entity(struct bfq_entity *entity,
+ struct bfq_group *bfqg)
+{
+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+ entity->weight = entity->new_weight;
+ entity->orig_weight = entity->new_weight;
+ if (bfqq) {
+ bfqq->ioprio = bfqq->new_ioprio;
+ bfqq->ioprio_class = bfqq->new_ioprio_class;
+ bfqg_get(bfqg);
+ }
+ entity->parent = bfqg->my_entity; /* NULL for root group */
+ entity->sched_data = &bfqg->sched_data;
+}
+
+static void bfqg_stats_exit(struct bfqg_stats *stats)
+{
+ blkg_rwstat_exit(&stats->merged);
+ blkg_rwstat_exit(&stats->service_time);
+ blkg_rwstat_exit(&stats->wait_time);
+ blkg_rwstat_exit(&stats->queued);
+ blkg_stat_exit(&stats->time);
+ blkg_stat_exit(&stats->avg_queue_size_sum);
+ blkg_stat_exit(&stats->avg_queue_size_samples);
+ blkg_stat_exit(&stats->dequeue);
+ blkg_stat_exit(&stats->group_wait_time);
+ blkg_stat_exit(&stats->idle_time);
+ blkg_stat_exit(&stats->empty_time);
+}
+
+static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp)
+{
+ if (blkg_rwstat_init(&stats->merged, gfp) ||
+ blkg_rwstat_init(&stats->service_time, gfp) ||
+ blkg_rwstat_init(&stats->wait_time, gfp) ||
+ blkg_rwstat_init(&stats->queued, gfp) ||
+ blkg_stat_init(&stats->time, gfp) ||
+ blkg_stat_init(&stats->avg_queue_size_sum, gfp) ||
+ blkg_stat_init(&stats->avg_queue_size_samples, gfp) ||
+ blkg_stat_init(&stats->dequeue, gfp) ||
+ blkg_stat_init(&stats->group_wait_time, gfp) ||
+ blkg_stat_init(&stats->idle_time, gfp) ||
+ blkg_stat_init(&stats->empty_time, gfp)) {
+ bfqg_stats_exit(stats);
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static struct bfq_group_data *cpd_to_bfqgd(struct blkcg_policy_data *cpd)
+{
+ return cpd ? container_of(cpd, struct bfq_group_data, pd) : NULL;
+}
+
+static struct bfq_group_data *blkcg_to_bfqgd(struct blkcg *blkcg)
+{
+ return cpd_to_bfqgd(blkcg_to_cpd(blkcg, &blkcg_policy_bfq));
+}
+
+static struct blkcg_policy_data *bfq_cpd_alloc(gfp_t gfp)
+{
+ struct bfq_group_data *bgd;
+
+ bgd = kzalloc(sizeof(*bgd), gfp);
+ if (!bgd)
+ return NULL;
+ return &bgd->pd;
+}
+
+static void bfq_cpd_init(struct blkcg_policy_data *cpd)
+{
+ struct bfq_group_data *d = cpd_to_bfqgd(cpd);
+
+ d->weight = cgroup_subsys_on_dfl(io_cgrp_subsys) ?
+ CGROUP_WEIGHT_DFL : BFQ_WEIGHT_LEGACY_DFL;
+}
+
+static void bfq_cpd_free(struct blkcg_policy_data *cpd)
+{
+ kfree(cpd_to_bfqgd(cpd));
+}
+
+static struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, int node)
+{
+ struct bfq_group *bfqg;
+
+ bfqg = kzalloc_node(sizeof(*bfqg), gfp, node);
+ if (!bfqg)
+ return NULL;
+
+ if (bfqg_stats_init(&bfqg->stats, gfp)) {
+ kfree(bfqg);
+ return NULL;
+ }
+
+ return &bfqg->pd;
+}
+
+static void bfq_pd_init(struct blkg_policy_data *pd)
+{
+ struct blkcg_gq *blkg = pd_to_blkg(pd);
+ struct bfq_group *bfqg = blkg_to_bfqg(blkg);
+ struct bfq_data *bfqd = blkg->q->elevator->elevator_data;
+ struct bfq_entity *entity = &bfqg->entity;
+ struct bfq_group_data *d = blkcg_to_bfqgd(blkg->blkcg);
+
+ entity->orig_weight = entity->weight = entity->new_weight = d->weight;
+ entity->my_sched_data = &bfqg->sched_data;
+ bfqg->my_entity = entity; /*
+ * the root_group's will be set to NULL
+ * in bfq_init_queue()
+ */
+ bfqg->bfqd = bfqd;
+}
+
+static void bfq_pd_free(struct blkg_policy_data *pd)
+{
+ struct bfq_group *bfqg = pd_to_bfqg(pd);
+
+ bfqg_stats_exit(&bfqg->stats);
+ return kfree(bfqg);
+}
+
+static void bfq_pd_reset_stats(struct blkg_policy_data *pd)
+{
+ struct bfq_group *bfqg = pd_to_bfqg(pd);
+
+ bfqg_stats_reset(&bfqg->stats);
+}
+
+static void bfq_group_set_parent(struct bfq_group *bfqg,
+ struct bfq_group *parent)
+{
+ struct bfq_entity *entity;
+
+ entity = &bfqg->entity;
+ entity->parent = parent->my_entity;
+ entity->sched_data = &parent->sched_data;
+}
+
+static struct bfq_group *bfq_lookup_bfqg(struct bfq_data *bfqd,
+ struct blkcg *blkcg)
+{
+ struct blkcg_gq *blkg;
+
+ blkg = blkg_lookup(blkcg, bfqd->queue);
+ if (likely(blkg))
+ return blkg_to_bfqg(blkg);
+ return NULL;
+}
+
+static struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
+ struct blkcg *blkcg)
+{
+ struct bfq_group *bfqg, *parent;
+ struct bfq_entity *entity;
+
+ bfqg = bfq_lookup_bfqg(bfqd, blkcg);
+
+ if (unlikely(!bfqg))
+ return NULL;
+
+ /*
+ * Update chain of bfq_groups as we might be handling a leaf group
+ * which, along with some of its relatives, has not been hooked yet
+ * to the private hierarchy of BFQ.
+ */
+ entity = &bfqg->entity;
+ for_each_entity(entity) {
+ bfqg = container_of(entity, struct bfq_group, entity);
+ if (bfqg != bfqd->root_group) {
+ parent = bfqg_parent(bfqg);
+ if (!parent)
+ parent = bfqd->root_group;
+ bfq_group_set_parent(bfqg, parent);
+ }
+ }
+
+ return bfqg;
+}
+
+static void bfq_bfqq_expire(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq,
+ bool compensate,
+ enum bfqq_expiration reason);
+
+/**
+ * bfq_bfqq_move - migrate @bfqq to @bfqg.
+ * @bfqd: queue descriptor.
+ * @bfqq: the queue to move.
+ * @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_group *bfqg)
+{
+ struct bfq_entity *entity = &bfqq->entity;
+
+ /* If bfqq is empty, then bfq_bfqq_expire also invokes
+ * bfq_del_bfqq_busy, thereby removing bfqq and its entity
+ * from data structures related to current group. Otherwise we
+ * need to remove bfqq explicitly with bfq_deactivate_bfqq, as
+ * we do below.
+ */
+ if (bfqq == bfqd->in_service_queue)
+ bfq_bfqq_expire(bfqd, bfqd->in_service_queue,
+ false, BFQ_BFQQ_PREEMPTED);
+
+ if (bfq_bfqq_busy(bfqq))
+ bfq_deactivate_bfqq(bfqd, bfqq, false, false);
+ else if (entity->on_st)
+ bfq_put_idle_entity(bfq_entity_service_tree(entity), entity);
+ bfqg_put(bfqq_group(bfqq));
+
+ /*
+ * 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;
+ bfqg_get(bfqg);
+
+ if (bfq_bfqq_busy(bfqq))
+ bfq_activate_bfqq(bfqd, bfqq);
+
+ if (!bfqd->in_service_queue && !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.
+ * @blkcg: the blk-cgroup to move to.
+ *
+ * Move bic to blkcg, 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 blkcg *blkcg)
+{
+ struct bfq_queue *async_bfqq = bic_to_bfqq(bic, 0);
+ struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, 1);
+ struct bfq_group *bfqg;
+ struct bfq_entity *entity;
+
+ bfqg = bfq_find_set_group(bfqd, blkcg);
+
+ if (unlikely(!bfqg))
+ bfqg = bfqd->root_group;
+
+ if (async_bfqq) {
+ 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,
+ async_bfqq->ref);
+ bfq_put_queue(async_bfqq);
+ }
+ }
+
+ if (sync_bfqq) {
+ entity = &sync_bfqq->entity;
+ if (entity->sched_data != &bfqg->sched_data)
+ bfq_bfqq_move(bfqd, sync_bfqq, bfqg);
+ }
+
+ return bfqg;
+}
+
+static void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio)
+{
+ struct bfq_data *bfqd = bic_to_bfqd(bic);
+ struct bfq_group *bfqg = NULL;
+ uint64_t serial_nr;
+
+ rcu_read_lock();
+ serial_nr = bio_blkcg(bio)->css.serial_nr;
+
+ /*
+ * Check whether blkcg has changed. The condition may trigger
+ * spuriously on a newly created cic but there's no harm.
+ */
+ if (unlikely(!bfqd) || likely(bic->blkcg_serial_nr == serial_nr))
+ goto out;
+
+ bfqg = __bfq_bic_change_cgroup(bfqd, bic, bio_blkcg(bio));
+ bic->blkcg_serial_nr = serial_nr;
+out:
+ rcu_read_unlock();
+}
+
+/**
+ * bfq_flush_idle_tree - deactivate any entity on the idle tree of @st.
+ * @st: the service tree being flushed.
+ */
+static void bfq_flush_idle_tree(struct bfq_service_tree *st)
+{
+ struct bfq_entity *entity = st->first_idle;
+
+ for (; entity ; entity = st->first_idle)
+ __bfq_deactivate_entity(entity, false);
}
/**
- * __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.
+ * 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 struct bfq_entity *__bfq_lookup_next_entity(struct bfq_service_tree *st,
- bool force)
+static void bfq_reparent_leaf_entity(struct bfq_data *bfqd,
+ struct bfq_entity *entity)
{
- struct bfq_entity *entity, *new_next_in_service = NULL;
+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
- if (RB_EMPTY_ROOT(&st->active))
- return NULL;
+ bfq_bfqq_move(bfqd, bfqq, bfqd->root_group);
+}
- bfq_update_vtime(st);
- entity = bfq_first_active_entity(st);
+/**
+ * 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 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 the chosen entity does not match with the sched_data's
- * next_in_service and we are forcedly serving the IDLE priority
- * class tree, bubble up budget update.
- */
- if (unlikely(force && entity != entity->sched_data->next_in_service)) {
- new_next_in_service = entity;
- for_each_entity(new_next_in_service)
- bfq_update_budget(new_next_in_service);
- }
+ if (!RB_EMPTY_ROOT(&st->active))
+ entity = bfq_entity_of(rb_first(active));
- return entity;
+ for (; entity ; entity = bfq_entity_of(rb_first(active)))
+ bfq_reparent_leaf_entity(bfqd, entity);
+
+ if (bfqg->sched_data.in_service_entity)
+ bfq_reparent_leaf_entity(bfqd,
+ bfqg->sched_data.in_service_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.
+ * bfq_pd_offline - deactivate the entity associated with @pd,
+ * and reparent its children entities.
+ * @pd: descriptor of the policy going offline.
*
- * NOTE: since we cache the next_in_service entity at each level of the
- * hierarchy, the complexity of the lookup can be decreased with
- * absolutely no effort just returning the cached next_in_service value;
- * we prefer to do full lookups to test the consistency of the data
- * structures.
+ * blkio already grabs the queue_lock for us, so no need to use
+ * RCU-based magic
*/
-static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd,
- int extract,
- struct bfq_data *bfqd)
+static void bfq_pd_offline(struct blkg_policy_data *pd)
{
- struct bfq_service_tree *st = sd->service_tree;
- struct bfq_entity *entity;
- int i = 0;
+ struct bfq_service_tree *st;
+ struct bfq_group *bfqg = pd_to_bfqg(pd);
+ struct bfq_data *bfqd = bfqg->bfqd;
+ struct bfq_entity *entity = bfqg->my_entity;
+ unsigned long flags;
+ int i;
+
+ if (!entity) /* root group */
+ return;
+ spin_lock_irqsave(&bfqd->lock, flags);
/*
- * Choose from idle class, if needed to guarantee a minimum
- * bandwidth to this class. This should also mitigate
- * priority-inversion problems in case a low priority task is
- * holding file system resources.
+ * Empty all service_trees belonging to this group before
+ * deactivating the group itself.
*/
- if (bfqd &&
- jiffies - bfqd->bfq_class_idle_last_service >
- BFQ_CL_IDLE_TIMEOUT) {
- entity = __bfq_lookup_next_entity(st + BFQ_IOPRIO_CLASSES - 1,
- true);
- if (entity) {
- i = BFQ_IOPRIO_CLASSES - 1;
- bfqd->bfq_class_idle_last_service = jiffies;
- sd->next_in_service = entity;
- }
+ 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. No one 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
+ * in 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.
+ */
+ bfq_reparent_active_entities(bfqd, bfqg, st);
}
- for (; i < BFQ_IOPRIO_CLASSES; i++) {
- entity = __bfq_lookup_next_entity(st + i, false);
- if (entity) {
- if (extract) {
- bfq_check_next_in_service(sd, entity);
- bfq_active_extract(st + i, entity);
- sd->in_service_entity = entity;
- sd->next_in_service = NULL;
- }
- break;
+
+ __bfq_deactivate_entity(entity, false);
+ bfq_put_async_queues(bfqd, bfqg);
+
+ spin_unlock_irqrestore(&bfqd->lock, flags);
+ /*
+ * @blkg is going offline and will be ignored by
+ * blkg_[rw]stat_recursive_sum(). Transfer stats to the parent so
+ * that they don't get lost. If IOs complete after this point, the
+ * stats for them will be lost. Oh well...
+ */
+ bfqg_stats_xfer_dead(bfqg);
+}
+
+static int bfq_io_show_weight(struct seq_file *sf, void *v)
+{
+ struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
+ struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg);
+ unsigned int val = 0;
+
+ if (bfqgd)
+ val = bfqgd->weight;
+
+ seq_printf(sf, "%u\n", val);
+
+ return 0;
+}
+
+static int bfq_io_set_weight_legacy(struct cgroup_subsys_state *css,
+ struct cftype *cftype,
+ u64 val)
+{
+ struct blkcg *blkcg = css_to_blkcg(css);
+ struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg);
+ struct blkcg_gq *blkg;
+ int ret = -ERANGE;
+
+ if (val < BFQ_MIN_WEIGHT || val > BFQ_MAX_WEIGHT)
+ return ret;
+
+ ret = 0;
+ spin_lock_irq(&blkcg->lock);
+ bfqgd->weight = (unsigned short)val;
+ hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
+ struct bfq_group *bfqg = blkg_to_bfqg(blkg);
+
+ if (!bfqg)
+ continue;
+ /*
+ * Setting the prio_changed flag of the entity
+ * to 1 with new_weight == weight 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_weight) {
+ bfqg->entity.new_weight = (unsigned short)val;
+ /*
+ * Make sure that the above new value has been
+ * stored in bfqg->entity.new_weight before
+ * setting the prio_changed flag. In fact,
+ * this flag may be read asynchronously (in
+ * critical sections protected by a different
+ * lock than that held here), and finding this
+ * flag set may cause the execution of the code
+ * for updating parameters whose value may
+ * depend also on bfqg->entity.new_weight (in
+ * __bfq_entity_update_weight_prio).
+ * This barrier makes sure that the new value
+ * of bfqg->entity.new_weight is correctly
+ * seen in that code.
+ */
+ smp_wmb();
+ bfqg->entity.prio_changed = 1;
}
}
+ spin_unlock_irq(&blkcg->lock);
- return entity;
+ return ret;
}
-static bool next_queue_may_preempt(struct bfq_data *bfqd)
+static ssize_t bfq_io_set_weight(struct kernfs_open_file *of,
+ char *buf, size_t nbytes,
+ loff_t off)
{
- struct bfq_sched_data *sd = &bfqd->sched_data;
+ u64 weight;
+ /* First unsigned long found in the file is used */
+ int ret = kstrtoull(strim(buf), 0, &weight);
- return sd->next_in_service != sd->in_service_entity;
+ if (ret)
+ return ret;
+
+ return bfq_io_set_weight_legacy(of_css(of), NULL, weight);
}
+static int bfqg_print_stat(struct seq_file *sf, void *v)
+{
+ blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat,
+ &blkcg_policy_bfq, seq_cft(sf)->private, false);
+ return 0;
+}
-/*
- * Get next queue for service.
- */
-static struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd)
+static int bfqg_print_rwstat(struct seq_file *sf, void *v)
{
- struct bfq_entity *entity = NULL;
- struct bfq_sched_data *sd;
- struct bfq_queue *bfqq;
+ blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat,
+ &blkcg_policy_bfq, seq_cft(sf)->private, true);
+ return 0;
+}
- if (bfqd->busy_queues == 0)
- return NULL;
+static u64 bfqg_prfill_stat_recursive(struct seq_file *sf,
+ struct blkg_policy_data *pd, int off)
+{
+ u64 sum = blkg_stat_recursive_sum(pd_to_blkg(pd),
+ &blkcg_policy_bfq, off);
+ return __blkg_prfill_u64(sf, pd, sum);
+}
- sd = &bfqd->sched_data;
- for (; sd ; sd = entity->my_sched_data) {
- entity = bfq_lookup_next_entity(sd, 1, bfqd);
- entity->service = 0;
- }
+static u64 bfqg_prfill_rwstat_recursive(struct seq_file *sf,
+ struct blkg_policy_data *pd, int off)
+{
+ struct blkg_rwstat sum = blkg_rwstat_recursive_sum(pd_to_blkg(pd),
+ &blkcg_policy_bfq,
+ off);
+ return __blkg_prfill_rwstat(sf, pd, &sum);
+}
- bfqq = bfq_entity_to_bfqq(entity);
+static int bfqg_print_stat_recursive(struct seq_file *sf, void *v)
+{
+ blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+ bfqg_prfill_stat_recursive, &blkcg_policy_bfq,
+ seq_cft(sf)->private, false);
+ return 0;
+}
- return bfqq;
+static int bfqg_print_rwstat_recursive(struct seq_file *sf, void *v)
+{
+ blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+ bfqg_prfill_rwstat_recursive, &blkcg_policy_bfq,
+ seq_cft(sf)->private, true);
+ return 0;
}
-static void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
+static u64 bfqg_prfill_sectors(struct seq_file *sf, struct blkg_policy_data *pd,
+ int off)
{
- if (bfqd->in_service_bic) {
- put_io_context(bfqd->in_service_bic->icq.ioc);
- bfqd->in_service_bic = NULL;
- }
+ u64 sum = blkg_rwstat_total(&pd->blkg->stat_bytes);
- bfq_clear_bfqq_wait_request(bfqd->in_service_queue);
- hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
- bfqd->in_service_queue = NULL;
+ return __blkg_prfill_u64(sf, pd, sum >> 9);
}
-static void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
- int requeue)
+static int bfqg_print_stat_sectors(struct seq_file *sf, void *v)
{
- struct bfq_entity *entity = &bfqq->entity;
-
- bfq_deactivate_entity(entity, requeue);
+ blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+ bfqg_prfill_sectors, &blkcg_policy_bfq, 0, false);
+ return 0;
}
-static void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+static u64 bfqg_prfill_sectors_recursive(struct seq_file *sf,
+ struct blkg_policy_data *pd, int off)
{
- struct bfq_entity *entity = &bfqq->entity;
+ struct blkg_rwstat tmp = blkg_rwstat_recursive_sum(pd->blkg, NULL,
+ offsetof(struct blkcg_gq, stat_bytes));
+ u64 sum = atomic64_read(&tmp.aux_cnt[BLKG_RWSTAT_READ]) +
+ atomic64_read(&tmp.aux_cnt[BLKG_RWSTAT_WRITE]);
- bfq_activate_entity(entity, bfq_bfqq_non_blocking_wait_rq(bfqq));
- bfq_clear_bfqq_non_blocking_wait_rq(bfqq);
+ return __blkg_prfill_u64(sf, pd, sum >> 9);
}
-/*
- * 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)
+static int bfqg_print_stat_sectors_recursive(struct seq_file *sf, void *v)
{
- bfq_log_bfqq(bfqd, bfqq, "del from busy");
+ blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+ bfqg_prfill_sectors_recursive, &blkcg_policy_bfq, 0,
+ false);
+ return 0;
+}
- bfq_clear_bfqq_busy(bfqq);
+static u64 bfqg_prfill_avg_queue_size(struct seq_file *sf,
+ struct blkg_policy_data *pd, int off)
+{
+ struct bfq_group *bfqg = pd_to_bfqg(pd);
+ u64 samples = blkg_stat_read(&bfqg->stats.avg_queue_size_samples);
+ u64 v = 0;
- bfqd->busy_queues--;
+ if (samples) {
+ v = blkg_stat_read(&bfqg->stats.avg_queue_size_sum);
+ v = div64_u64(v, samples);
+ }
+ __blkg_prfill_u64(sf, pd, v);
+ return 0;
+}
- bfq_deactivate_bfqq(bfqd, bfqq, requeue);
+/* print avg_queue_size */
+static int bfqg_print_avg_queue_size(struct seq_file *sf, void *v)
+{
+ blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+ bfqg_prfill_avg_queue_size, &blkcg_policy_bfq,
+ 0, false);
+ return 0;
}
-/*
- * Called when an inactive queue receives a new request.
- */
-static void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+static struct bfq_group *
+bfq_create_group_hierarchy(struct bfq_data *bfqd, int node)
{
- bfq_log_bfqq(bfqd, bfqq, "add to busy");
+ int ret;
- bfq_activate_bfqq(bfqd, bfqq);
+ ret = blkcg_activate_policy(bfqd->queue, &blkcg_policy_bfq);
+ if (ret)
+ return NULL;
- bfq_mark_bfqq_busy(bfqq);
- bfqd->busy_queues++;
+ return blkg_to_bfqg(bfqd->queue->root_blkg);
}
-static void bfq_init_entity(struct bfq_entity *entity)
+static struct cftype bfq_blkcg_legacy_files[] = {
+ {
+ .name = "bfq.weight",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = bfq_io_show_weight,
+ .write_u64 = bfq_io_set_weight_legacy,
+ },
+
+ /* statistics, covers only the tasks in the bfqg */
+ {
+ .name = "bfq.time",
+ .private = offsetof(struct bfq_group, stats.time),
+ .seq_show = bfqg_print_stat,
+ },
+ {
+ .name = "bfq.sectors",
+ .seq_show = bfqg_print_stat_sectors,
+ },
+ {
+ .name = "bfq.io_service_bytes",
+ .private = (unsigned long)&blkcg_policy_bfq,
+ .seq_show = blkg_print_stat_bytes,
+ },
+ {
+ .name = "bfq.io_serviced",
+ .private = (unsigned long)&blkcg_policy_bfq,
+ .seq_show = blkg_print_stat_ios,
+ },
+ {
+ .name = "bfq.io_service_time",
+ .private = offsetof(struct bfq_group, stats.service_time),
+ .seq_show = bfqg_print_rwstat,
+ },
+ {
+ .name = "bfq.io_wait_time",
+ .private = offsetof(struct bfq_group, stats.wait_time),
+ .seq_show = bfqg_print_rwstat,
+ },
+ {
+ .name = "bfq.io_merged",
+ .private = offsetof(struct bfq_group, stats.merged),
+ .seq_show = bfqg_print_rwstat,
+ },
+ {
+ .name = "bfq.io_queued",
+ .private = offsetof(struct bfq_group, stats.queued),
+ .seq_show = bfqg_print_rwstat,
+ },
+
+ /* the same statictics which cover the bfqg and its descendants */
+ {
+ .name = "bfq.time_recursive",
+ .private = offsetof(struct bfq_group, stats.time),
+ .seq_show = bfqg_print_stat_recursive,
+ },
+ {
+ .name = "bfq.sectors_recursive",
+ .seq_show = bfqg_print_stat_sectors_recursive,
+ },
+ {
+ .name = "bfq.io_service_bytes_recursive",
+ .private = (unsigned long)&blkcg_policy_bfq,
+ .seq_show = blkg_print_stat_bytes_recursive,
+ },
+ {
+ .name = "bfq.io_serviced_recursive",
+ .private = (unsigned long)&blkcg_policy_bfq,
+ .seq_show = blkg_print_stat_ios_recursive,
+ },
+ {
+ .name = "bfq.io_service_time_recursive",
+ .private = offsetof(struct bfq_group, stats.service_time),
+ .seq_show = bfqg_print_rwstat_recursive,
+ },
+ {
+ .name = "bfq.io_wait_time_recursive",
+ .private = offsetof(struct bfq_group, stats.wait_time),
+ .seq_show = bfqg_print_rwstat_recursive,
+ },
+ {
+ .name = "bfq.io_merged_recursive",
+ .private = offsetof(struct bfq_group, stats.merged),
+ .seq_show = bfqg_print_rwstat_recursive,
+ },
+ {
+ .name = "bfq.io_queued_recursive",
+ .private = offsetof(struct bfq_group, stats.queued),
+ .seq_show = bfqg_print_rwstat_recursive,
+ },
+ {
+ .name = "bfq.avg_queue_size",
+ .seq_show = bfqg_print_avg_queue_size,
+ },
+ {
+ .name = "bfq.group_wait_time",
+ .private = offsetof(struct bfq_group, stats.group_wait_time),
+ .seq_show = bfqg_print_stat,
+ },
+ {
+ .name = "bfq.idle_time",
+ .private = offsetof(struct bfq_group, stats.idle_time),
+ .seq_show = bfqg_print_stat,
+ },
+ {
+ .name = "bfq.empty_time",
+ .private = offsetof(struct bfq_group, stats.empty_time),
+ .seq_show = bfqg_print_stat,
+ },
+ {
+ .name = "bfq.dequeue",
+ .private = offsetof(struct bfq_group, stats.dequeue),
+ .seq_show = bfqg_print_stat,
+ },
+ { } /* terminate */
+};
+
+static struct cftype bfq_blkg_files[] = {
+ {
+ .name = "bfq.weight",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = bfq_io_show_weight,
+ .write = bfq_io_set_weight,
+ },
+ {} /* terminate */
+};
+
+#else /* CONFIG_BFQ_GROUP_IOSCHED */
+
+static inline void bfqg_stats_update_io_add(struct bfq_group *bfqg,
+ struct bfq_queue *bfqq, unsigned int op) { }
+static inline void
+bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op) { }
+static inline void
+bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op) { }
+static inline void bfqg_stats_update_completion(struct bfq_group *bfqg,
+ uint64_t start_time, uint64_t io_start_time,
+ unsigned int op) { }
+static inline void
+bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg,
+ struct bfq_group *curr_bfqg) { }
+static inline void bfqg_stats_end_empty_time(struct bfqg_stats *stats) { }
+static inline void bfqg_stats_update_dequeue(struct bfq_group *bfqg) { }
+static inline void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg) { }
+static inline void bfqg_stats_update_idle_time(struct bfq_group *bfqg) { }
+static inline void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg) { }
+static inline void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg) { }
+
+static void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ struct bfq_group *bfqg) {}
+
+static void bfq_init_entity(struct bfq_entity *entity,
+ struct bfq_group *bfqg)
{
struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
entity->weight = entity->new_weight;
entity->orig_weight = entity->new_weight;
+ if (bfqq) {
+ bfqq->ioprio = bfqq->new_ioprio;
+ bfqq->ioprio_class = bfqq->new_ioprio_class;
+ }
+ entity->sched_data = &bfqg->sched_data;
+}
+
+static void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio) {}
+
+static struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
+ struct blkcg *blkcg)
+{
+ return bfqd->root_group;
+}
+
+static struct bfq_group *bfqq_group(struct bfq_queue *bfqq)
+{
+ return bfqq->bfqd->root_group;
+}
- bfqq->ioprio = bfqq->new_ioprio;
- bfqq->ioprio_class = bfqq->new_ioprio_class;
+static struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd,
+ int node)
+{
+ struct bfq_group *bfqg;
+ int i;
+
+ bfqg = kmalloc_node(sizeof(*bfqg), GFP_KERNEL | __GFP_ZERO, node);
+ if (!bfqg)
+ return NULL;
- entity->sched_data = &bfqq->bfqd->sched_data;
+ for (i = 0; i < BFQ_IOPRIO_CLASSES; i++)
+ bfqg->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT;
+
+ return bfqg;
}
+#endif /* CONFIG_BFQ_GROUP_IOSCHED */
#define bfq_class_idle(bfqq) ((bfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
#define bfq_class_rt(bfqq) ((bfqq)->ioprio_class == IOPRIO_CLASS_RT)
@@ -1667,18 +3362,6 @@ static void bfq_init_entity(struct bfq_entity *entity)
#define bfq_sample_valid(samples) ((samples) > 80)
/*
- * Scheduler run of queue, if there are requests pending and no one in the
- * driver that will restart queueing.
- */
-static void bfq_schedule_dispatch(struct bfq_data *bfqd)
-{
- if (bfqd->queued != 0) {
- bfq_log(bfqd, "schedule dispatch");
- blk_mq_run_hw_queues(bfqd->queue, true);
- }
-}
-
-/*
* 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.
@@ -1861,7 +3544,7 @@ static void bfq_updated_next_req(struct bfq_data *bfqd,
entity->budget = new_budget;
bfq_log_bfqq(bfqd, bfqq, "updated next rq: new budget %lu",
new_budget);
- bfq_activate_bfqq(bfqd, bfqq);
+ bfq_requeue_bfqq(bfqd, bfqq);
}
}
@@ -2032,6 +3715,8 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
bfqq->ttime.last_end_request +
bfqd->bfq_slice_idle * 3;
+ bfqg_stats_update_io_add(bfqq_group(RQ_BFQQ(rq)), bfqq, rq->cmd_flags);
+
/*
* Update budget and check whether bfqq may want to preempt
* the in-service queue.
@@ -2151,7 +3836,7 @@ static void bfq_remove_request(struct request_queue *q,
bfqq->next_rq = NULL;
if (bfq_bfqq_busy(bfqq) && bfqq != bfqd->in_service_queue) {
- bfq_del_bfqq_busy(bfqd, bfqq, 1);
+ bfq_del_bfqq_busy(bfqd, bfqq, false);
/*
* bfqq emptied. In normal operation, when
@@ -2171,6 +3856,8 @@ static void bfq_remove_request(struct request_queue *q,
if (rq->cmd_flags & REQ_META)
bfqq->meta_pending--;
+
+ bfqg_stats_update_io_remove(bfqq_group(bfqq), rq->cmd_flags);
}
static bool bfq_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio)
@@ -2258,7 +3945,7 @@ static void bfq_requests_merged(struct request_queue *q, struct request *rq,
struct bfq_queue *bfqq = RQ_BFQQ(rq), *next_bfqq = RQ_BFQQ(next);
if (!RB_EMPTY_NODE(&rq->rb_node))
- return;
+ goto end;
spin_lock_irq(&bfqq->bfqd->lock);
/*
@@ -2284,6 +3971,8 @@ static void bfq_requests_merged(struct request_queue *q, struct request *rq,
bfq_remove_request(q, next);
spin_unlock_irq(&bfqq->bfqd->lock);
+end:
+ bfqg_stats_update_io_merged(bfqq_group(bfqq), next->cmd_flags);
}
static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
@@ -2313,6 +4002,7 @@ static void __bfq_set_in_service_queue(struct bfq_data *bfqd,
struct bfq_queue *bfqq)
{
if (bfqq) {
+ bfqg_stats_update_avg_queue_size(bfqq_group(bfqq));
bfq_mark_bfqq_budget_new(bfqq);
bfq_clear_bfqq_fifo_expire(bfqq);
@@ -2395,6 +4085,7 @@ static void bfq_arm_slice_timer(struct bfq_data *bfqd)
bfqd->last_idling_start = ktime_get();
hrtimer_start(&bfqd->idle_slice_timer, ns_to_ktime(sl),
HRTIMER_MODE_REL);
+ bfqg_stats_set_start_idle_time(bfqq_group(bfqq));
}
/*
@@ -2444,12 +4135,17 @@ static void bfq_dispatch_remove(struct request_queue *q, struct request *rq)
static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
{
- __bfq_bfqd_reset_in_service(bfqd);
-
if (RB_EMPTY_ROOT(&bfqq->sort_list))
- bfq_del_bfqq_busy(bfqd, bfqq, 1);
+ bfq_del_bfqq_busy(bfqd, bfqq, true);
else
- bfq_activate_bfqq(bfqd, bfqq);
+ bfq_requeue_bfqq(bfqd, bfqq);
+
+ /*
+ * All in-service entities must have been properly deactivated
+ * or requeued before executing the next function, which
+ * resets all in-service entites as no more in service.
+ */
+ __bfq_bfqd_reset_in_service(bfqd);
}
/**
@@ -2917,6 +4613,7 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
*/
bfq_clear_bfqq_wait_request(bfqq);
hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
+ bfqg_stats_update_idle_time(bfqq_group(bfqq));
}
goto keep_queue;
}
@@ -3103,6 +4800,10 @@ static struct request *bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
*/
static void bfq_put_queue(struct bfq_queue *bfqq)
{
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ struct bfq_group *bfqg = bfqq_group(bfqq);
+#endif
+
if (bfqq->bfqd)
bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p %d",
bfqq, bfqq->ref);
@@ -3111,7 +4812,12 @@ static void bfq_put_queue(struct bfq_queue *bfqq)
if (bfqq->ref)
return;
+ bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p freed", bfqq);
+
kmem_cache_free(bfq_pool, bfqq);
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ bfqg_put(bfqg);
+#endif
}
static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
@@ -3265,18 +4971,19 @@ static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *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 &async_bfqq[0][ioprio];
+ return &bfqg->async_bfqq[0][ioprio];
case IOPRIO_CLASS_NONE:
ioprio = IOPRIO_NORM;
/* fall through */
case IOPRIO_CLASS_BE:
- return &async_bfqq[1][ioprio];
+ return &bfqg->async_bfqq[1][ioprio];
case IOPRIO_CLASS_IDLE:
- return &async_idle_bfqq;
+ return &bfqg->async_idle_bfqq;
default:
return NULL;
}
@@ -3290,11 +4997,18 @@ static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
const int ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio);
struct bfq_queue **async_bfqq = NULL;
struct bfq_queue *bfqq;
+ struct bfq_group *bfqg;
rcu_read_lock();
+ bfqg = bfq_find_set_group(bfqd, bio_blkcg(bio));
+ if (!bfqg) {
+ bfqq = &bfqd->oom_bfqq;
+ goto out;
+ }
+
if (!is_sync) {
- async_bfqq = bfq_async_queue_prio(bfqd, ioprio_class,
+ async_bfqq = bfq_async_queue_prio(bfqd, bfqg, ioprio_class,
ioprio);
bfqq = *async_bfqq;
if (bfqq)
@@ -3308,7 +5022,7 @@ static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
if (bfqq) {
bfq_init_bfqq(bfqd, bfqq, bic, current->pid,
is_sync);
- bfq_init_entity(&bfqq->entity);
+ bfq_init_entity(&bfqq->entity, bfqg);
bfq_log_bfqq(bfqd, bfqq, "allocated");
} else {
bfqq = &bfqd->oom_bfqq;
@@ -3321,9 +5035,14 @@ static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
* prune it.
*/
if (async_bfqq) {
- bfqq->ref++;
- bfq_log_bfqq(bfqd, bfqq,
- "get_queue, bfqq not in async: %p, %d",
+ bfqq->ref++; /*
+ * Extra group reference, w.r.t. sync
+ * queue. This extra reference is removed
+ * only if bfqq->bfqg disappears, to
+ * guarantee that this queue is not freed
+ * until its group goes away.
+ */
+ bfq_log_bfqq(bfqd, bfqq, "get_queue, bfqq not in async: %p, %d",
bfqq, bfqq->ref);
*async_bfqq = bfqq;
}
@@ -3458,6 +5177,7 @@ static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq,
*/
bfq_clear_bfqq_wait_request(bfqq);
hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
+ bfqg_stats_update_idle_time(bfqq_group(bfqq));
/*
* The queue is not empty, because a new request just
@@ -3599,6 +5319,11 @@ static void bfq_put_rq_private(struct request_queue *q, struct request *rq)
struct bfq_queue *bfqq = RQ_BFQQ(rq);
struct bfq_data *bfqd = bfqq->bfqd;
+ if (rq->rq_flags & RQF_STARTED)
+ bfqg_stats_update_completion(bfqq_group(bfqq),
+ rq_start_time_ns(rq),
+ rq_io_start_time_ns(rq),
+ rq->cmd_flags);
if (likely(rq->rq_flags & RQF_STARTED)) {
unsigned long flags;
@@ -3649,6 +5374,8 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
if (!bic)
goto queue_fail;
+ bfq_bic_update_cgroup(bic, bio);
+
bfqq = bic_to_bfqq(bic, is_sync);
if (!bfqq || bfqq == &bfqd->oom_bfqq) {
if (bfqq)
@@ -3745,6 +5472,8 @@ static void __bfq_put_async_bfqq(struct bfq_data *bfqd,
bfq_log(bfqd, "put_async_bfqq: %p", bfqq);
if (bfqq) {
+ bfq_bfqq_move(bfqd, bfqq, bfqd->root_group);
+
bfq_log_bfqq(bfqd, bfqq, "put_async_bfqq: putting %p, %d",
bfqq, bfqq->ref);
bfq_put_queue(bfqq);
@@ -3753,18 +5482,20 @@ static void __bfq_put_async_bfqq(struct bfq_data *bfqd,
}
/*
- * Release the extra reference of the async queues as the device
- * goes away.
+ * 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 until all the requests on a device are gone).
*/
-static void bfq_put_async_queues(struct bfq_data *bfqd)
+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, &async_bfqq[i][j]);
+ __bfq_put_async_bfqq(bfqd, &bfqg->async_bfqq[i][j]);
- __bfq_put_async_bfqq(bfqd, &async_idle_bfqq);
+ __bfq_put_async_bfqq(bfqd, &bfqg->async_idle_bfqq);
}
static void bfq_exit_queue(struct elevator_queue *e)
@@ -3776,20 +5507,42 @@ static void bfq_exit_queue(struct elevator_queue *e)
spin_lock_irq(&bfqd->lock);
list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list)
- bfq_deactivate_bfqq(bfqd, bfqq, false);
- bfq_put_async_queues(bfqd);
+ bfq_deactivate_bfqq(bfqd, bfqq, false, false);
spin_unlock_irq(&bfqd->lock);
hrtimer_cancel(&bfqd->idle_slice_timer);
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ blkcg_deactivate_policy(bfqd->queue, &blkcg_policy_bfq);
+#else
+ spin_lock_irq(&bfqd->lock);
+ bfq_put_async_queues(bfqd, bfqd->root_group);
+ kfree(bfqd->root_group);
+ spin_unlock_irq(&bfqd->lock);
+#endif
+
kfree(bfqd);
}
+static void bfq_init_root_group(struct bfq_group *root_group,
+ struct bfq_data *bfqd)
+{
+ int i;
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ root_group->entity.parent = NULL;
+ root_group->my_entity = NULL;
+ root_group->bfqd = bfqd;
+#endif
+ for (i = 0; i < BFQ_IOPRIO_CLASSES; i++)
+ root_group->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT;
+ root_group->sched_data.bfq_class_idle_last_service = jiffies;
+}
+
static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
{
struct bfq_data *bfqd;
struct elevator_queue *eq;
- int i;
eq = elevator_alloc(q, e);
if (!eq)
@@ -3802,6 +5555,10 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
}
eq->elevator_data = bfqd;
+ spin_lock_irq(q->queue_lock);
+ q->elevator = eq;
+ spin_unlock_irq(q->queue_lock);
+
/*
* Our fallback bfqq if bfq_find_alloc_queue() runs into OOM issues.
* Grab a permanent reference to it, so that the normal code flow
@@ -3822,8 +5579,7 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
bfqd->queue = q;
- for (i = 0; i < BFQ_IOPRIO_CLASSES; i++)
- bfqd->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT;
+ INIT_LIST_HEAD(&bfqd->dispatch);
hrtimer_init(&bfqd->idle_slice_timer, CLOCK_MONOTONIC,
HRTIMER_MODE_REL);
@@ -3841,17 +5597,40 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
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_timeout = bfq_timeout;
bfqd->bfq_requests_within_timer = 120;
spin_lock_init(&bfqd->lock);
- INIT_LIST_HEAD(&bfqd->dispatch);
- q->elevator = eq;
+ /*
+ * The invocation of the next bfq_create_group_hierarchy
+ * function is the head of a chain of function calls
+ * (bfq_create_group_hierarchy->blkcg_activate_policy->
+ * blk_mq_freeze_queue) that may lead to the invocation of the
+ * has_work hook function. For this reason,
+ * bfq_create_group_hierarchy is invoked only after all
+ * scheduler data has been initialized, apart from the fields
+ * that can be initialized only after invoking
+ * bfq_create_group_hierarchy. This, in particular, enables
+ * has_work to correctly return false. Of course, to avoid
+ * other inconsistencies, the blk-mq stack must then refrain
+ * from invoking further scheduler hooks before this init
+ * function is finished.
+ */
+ bfqd->root_group = bfq_create_group_hierarchy(bfqd, q->node);
+ if (!bfqd->root_group)
+ goto out_free;
+ bfq_init_root_group(bfqd->root_group, bfqd);
+ bfq_init_entity(&bfqd->oom_bfqq.entity, bfqd->root_group);
+
return 0;
+
+out_free:
+ kfree(bfqd);
+ kobject_put(&eq->kobj);
+ return -ENOMEM;
}
static void bfq_slab_kill(void)
@@ -4118,11 +5897,35 @@ static struct elevator_type iosched_bfq_mq = {
.elevator_owner = THIS_MODULE,
};
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+static struct blkcg_policy blkcg_policy_bfq = {
+ .dfl_cftypes = bfq_blkg_files,
+ .legacy_cftypes = bfq_blkcg_legacy_files,
+
+ .cpd_alloc_fn = bfq_cpd_alloc,
+ .cpd_init_fn = bfq_cpd_init,
+ .cpd_bind_fn = bfq_cpd_init,
+ .cpd_free_fn = bfq_cpd_free,
+
+ .pd_alloc_fn = bfq_pd_alloc,
+ .pd_init_fn = bfq_pd_init,
+ .pd_offline_fn = bfq_pd_offline,
+ .pd_free_fn = bfq_pd_free,
+ .pd_reset_stats_fn = bfq_pd_reset_stats,
+};
+#endif
+
static int __init bfq_init(void)
{
int ret;
char msg[50] = "BFQ I/O-scheduler: v0";
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ ret = blkcg_policy_register(&blkcg_policy_bfq);
+ if (ret)
+ return ret;
+#endif
+
ret = -ENOMEM;
if (bfq_slab_setup())
goto err_pol_unreg;
@@ -4139,12 +5942,18 @@ static int __init bfq_init(void)
return 0;
err_pol_unreg:
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ blkcg_policy_unregister(&blkcg_policy_bfq);
+#endif
return ret;
}
static void __exit bfq_exit(void)
{
elv_unregister(&iosched_bfq_mq);
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ blkcg_policy_unregister(&blkcg_policy_bfq);
+#endif
bfq_slab_kill();
}
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 796016e..b6cf6ac 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -48,7 +48,7 @@ struct rq_wb;
* Maximum number of blkcg policies allowed to be registered concurrently.
* Defined here to simplify include dependency.
*/
-#define BLKCG_MAX_POLS 2
+#define BLKCG_MAX_POLS 3
typedef void (rq_end_io_fn)(struct request *, int);
--
2.10.0
^ permalink raw reply related
* [PATCH RFC 01/14] block, bfq: introduce the BFQ-v0 I/O scheduler as an extra scheduler
From: Paolo Valente @ 2017-03-04 16:01 UTC (permalink / raw)
To: Jens Axboe, Tejun Heo
Cc: Fabio Checconi, Arianna Avanzini, linux-block, linux-kernel,
ulf.hansson, linus.walleij, broonie, Paolo Valente
In-Reply-To: <20170304160131.57366-1-paolo.valente@linaro.org>
We tag as v0 the version of BFQ containing only BFQ's engine plus
hierarchical support. BFQ's engine is introduced by this commit, while
hierarchical support is added by next commit. We use the v0 tag to
distinguish this minimal version of BFQ from the versions containing
also the features and the improvements added by next commits. BFQ-v0
coincides with the version of BFQ submitted a few years ago [1], apart
from the introduction of preemption, described below.
BFQ is a proportional-share I/O scheduler, whose general structure,
plus a lot of code, are borrowed from CFQ.
- Each process doing I/O on a device is associated with a weight and a
(bfq_)queue.
- BFQ grants exclusive access to the device, for a while, to one queue
(process) at a time, and implements this service model by
associating every queue with a budget, measured in number of
sectors.
- After a queue is granted access to the device, the budget of the
queue is decremented, on each request dispatch, by the size of the
request.
- The in-service queue is expired, i.e., its service is suspended,
only if one of the following events occurs: 1) the queue finishes
its budget, 2) the queue empties, 3) a "budget timeout" fires.
- The budget timeout prevents processes doing random I/O from
holding the device for too long and dramatically reducing
throughput.
- Actually, as in CFQ, a queue associated with a process issuing
sync requests may not be expired immediately when it empties. In
contrast, BFQ may idle the device for a short time interval,
giving the process the chance to go on being served if it issues
a new request in time. Device idling typically boosts the
throughput on rotational devices, if processes do synchronous
and sequential I/O. In addition, under BFQ, device idling is
also instrumental in guaranteeing the desired throughput
fraction to processes issuing sync requests (see [2] for
details).
- With respect to idling for service guarantees, if several
processes are competing for the device at the same time, but
all processes (and groups, after the following commit) have
the same weight, then BFQ guarantees the expected throughput
distribution without ever idling the device. Throughput is
thus as high as possible in this common scenario.
- Queues are scheduled according to a variant of WF2Q+, named
B-WF2Q+, and implemented using an augmented rb-tree to preserve an
O(log N) overall complexity. See [2] for more details. B-WF2Q+ is
also ready for hierarchical scheduling. However, for a cleaner
logical breakdown, the code that enables and completes
hierarchical support is provided in the next commit, which focuses
exactly on this feature.
- B-WF2Q+ guarantees a tight deviation with respect to an ideal,
perfectly fair, and smooth service. In particular, B-WF2Q+
guarantees that each queue receives a fraction of the device
throughput proportional to its weight, even if the throughput
fluctuates, and regardless of: the device parameters, the current
workload and the budgets assigned to the queue.
- The last, budget-independence, property (although probably
counterintuitive in the first place) is definitely beneficial, for
the following reasons:
- First, with any proportional-share scheduler, the maximum
deviation with respect to an ideal service is proportional to
the maximum budget (slice) assigned to queues. As a consequence,
BFQ can keep this deviation tight not only because of the
accurate service of B-WF2Q+, but also because BFQ *does not*
need to assign a larger budget to a queue to let the queue
receive a higher fraction of the device throughput.
- Second, BFQ is free to choose, for every process (queue), the
budget that best fits the needs of the process, or best
leverages the I/O pattern of the process. In particular, BFQ
updates queue budgets with a simple feedback-loop algorithm that
allows a high throughput to be achieved, while still providing
tight latency guarantees to time-sensitive applications. When
the in-service queue expires, this algorithm computes the next
budget of the queue so as to:
- Let large budgets be eventually assigned to the queues
associated with I/O-bound applications performing sequential
I/O: in fact, the longer these applications are served once
got access to the device, the higher the throughput is.
- Let small budgets be eventually assigned to the queues
associated with time-sensitive applications (which typically
perform sporadic and short I/O), because, the smaller the
budget assigned to a queue waiting for service is, the sooner
B-WF2Q+ will serve that queue (Subsec 3.3 in [2]).
- Weights can be assigned to processes only indirectly, through I/O
priorities, and according to the relation:
weight = 10 * (IOPRIO_BE_NR - ioprio).
The next patch provides, instead, a cgroups interface through which
weights can be assigned explicitly.
- If several processes are competing for the device at the same time,
but all processes and groups have the same weight, then BFQ
guarantees the expected throughput distribution without ever idling
the device. It uses preemption instead. Throughput is then much
higher in this common scenario.
- 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.
- If the strict_guarantees parameter is set (default: unset), then BFQ
- always performs idling when the in-service queue becomes empty;
- forces the device to serve one I/O request at a time, by
dispatching a new request only if there is no outstanding
request.
In the presence of differentiated weights or I/O-request sizes,
both the above conditions are needed to guarantee that every
queue receives its allotted share of the bandwidth (see
Documentation/block/bfq-iosched.txt for more details). Setting
strict_guarantees may evidently affect throughput.
[1] https://lkml.org/lkml/2008/4/1/234
https://lkml.org/lkml/2008/11/11/148
[2] 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.
Slightly extended version:
http://algogroup.unimore.it/people/paolo/disk_sched/bfq-v1-suite-
results.pdf
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
---
Documentation/block/00-INDEX | 2 +
Documentation/block/bfq-iosched.txt | 516 +++++
block/Kconfig.iosched | 11 +
block/Makefile | 1 +
block/bfq-iosched.c | 4156 +++++++++++++++++++++++++++++++++++
block/elevator.c | 16 +-
6 files changed, 4697 insertions(+), 5 deletions(-)
create mode 100644 Documentation/block/bfq-iosched.txt
create mode 100644 block/bfq-iosched.c
diff --git a/Documentation/block/00-INDEX b/Documentation/block/00-INDEX
index e55103a..8d55b4b 100644
--- a/Documentation/block/00-INDEX
+++ b/Documentation/block/00-INDEX
@@ -1,5 +1,7 @@
00-INDEX
- This file
+bfq-iosched.txt
+ - BFQ IO scheduler and its tunables
biodoc.txt
- Notes on the Generic Block Layer Rewrite in Linux 2.5
biovecs.txt
diff --git a/Documentation/block/bfq-iosched.txt b/Documentation/block/bfq-iosched.txt
new file mode 100644
index 0000000..5ba67af
--- /dev/null
+++ b/Documentation/block/bfq-iosched.txt
@@ -0,0 +1,516 @@
+BFQ (Budget Fair Queueing)
+==========================
+
+BFQ is a proportional-share I/O scheduler, with some extra
+low-latency capabilities. In addition to cgroups support (blkio or io
+controllers), BFQ's main features are:
+- BFQ guarantees a high system and application responsiveness, and a
+ low latency for time-sensitive applications, such as audio or video
+ players;
+- BFQ distributes bandwidth, and not just time, among processes or
+ groups (switching back to time distribution when needed to keep
+ throughput high).
+
+On average CPUs, the current version of BFQ can handle devices
+performing at most ~30K IOPS; at most ~50 KIOPS on faster CPUs. As a
+reference, 30-50 KIOPS correspond to very high bandwidths with
+sequential I/O (e.g., 8-12 GB/s if I/O requests are 256 KB large), and
+to 120-200 MB/s with 4KB random I/O.
+
+The table of contents follow. Impatients can just jump to Section 3.
+
+CONTENTS
+
+1. When may BFQ be useful?
+ 1-1 Personal systems
+ 1-2 Server systems
+2. How does BFQ work?
+3. What are BFQ's tunable?
+4. BFQ group scheduling
+ 4-1 Service guarantees provided
+ 4-2 Interface
+
+1. When may BFQ be useful?
+==========================
+
+BFQ provides the following benefits on personal and server systems.
+
+1-1 Personal systems
+--------------------
+
+Low latency for interactive applications
+
+Regardless of the actual background workload, BFQ guarantees that, for
+interactive tasks, the storage device is virtually as responsive as if
+it was idle. For example, even if one or more of the following
+background workloads are being executed:
+- one or more large files are being read, written or copied,
+- a tree of source files is being compiled,
+- one or more virtual machines are performing I/O,
+- a software update is in progress,
+- indexing daemons are scanning filesystems and updating their
+ databases,
+starting an application or loading a file from within an application
+takes about the same time as if the storage device was idle. As a
+comparison, with CFQ, NOOP or DEADLINE, and in the same conditions,
+applications experience high latencies, or even become unresponsive
+until the background workload terminates (also on SSDs).
+
+Low latency for soft real-time applications
+
+Also soft real-time applications, such as audio and video
+players/streamers, enjoy a low latency and a low drop rate, regardless
+of the background I/O workload. As a consequence, these applications
+do not suffer from almost any glitch due to the background workload.
+
+Higher speed for code-development tasks
+
+If some additional workload happens to be executed in parallel, then
+BFQ executes the I/O-related components of typical code-development
+tasks (compilation, checkout, merge, ...) much more quickly than CFQ,
+NOOP or DEADLINE.
+
+High throughput
+
+On hard disks, BFQ achieves up to 30% higher throughput than CFQ, and
+up to 150% higher throughput than DEADLINE and NOOP, with all the
+sequential workloads considered in our tests. With random workloads,
+and with all the workloads on flash-based devices, BFQ achieves,
+instead, about the same throughput as the other schedulers.
+
+Strong fairness, bandwidth and delay guarantees
+
+BFQ distributes the device throughput, and not just the device time,
+among I/O-bound applications in proportion their weights, with any
+workload and regardless of the device parameters. From these bandwidth
+guarantees, it is possible to compute tight per-I/O-request delay
+guarantees by a simple formula. If not configured for strict service
+guarantees, BFQ switches to time-based resource sharing (only) for
+applications that would otherwise cause a throughput loss.
+
+1-2 Server systems
+------------------
+
+Most benefits for server systems follow from the same service
+properties as above. In particular, regardless of whether additional,
+possibly heavy workloads are being served, BFQ guarantees:
+
+. audio and video-streaming with zero or very low jitter and drop
+ rate;
+
+. fast retrieval of WEB pages and embedded objects;
+
+. real-time recording of data in live-dumping applications (e.g.,
+ packet logging);
+
+. responsiveness in local and remote access to a server.
+
+
+2. How does BFQ work?
+=====================
+
+BFQ is a proportional-share I/O scheduler, whose general structure,
+plus a lot of code, are borrowed from CFQ.
+
+- Each process doing I/O on a device is associated with a weight and a
+ (bfq_)queue.
+
+- BFQ grants exclusive access to the device, for a while, to one queue
+ (process) at a time, and implements this service model by
+ associating every queue with a budget, measured in number of
+ sectors.
+
+ - After a queue is granted access to the device, the budget of the
+ queue is decremented, on each request dispatch, by the size of the
+ request.
+
+ - The in-service queue is expired, i.e., its service is suspended,
+ only if one of the following events occurs: 1) the queue finishes
+ its budget, 2) the queue empties, 3) a "budget timeout" fires.
+
+ - The budget timeout prevents processes doing random I/O from
+ holding the device for too long and dramatically reducing
+ throughput.
+
+ - Actually, as in CFQ, a queue associated with a process issuing
+ sync requests may not be expired immediately when it empties. In
+ contrast, BFQ may idle the device for a short time interval,
+ giving the process the chance to go on being served if it issues
+ a new request in time. Device idling typically boosts the
+ throughput on rotational devices, if processes do synchronous
+ and sequential I/O. In addition, under BFQ, device idling is
+ also instrumental in guaranteeing the desired throughput
+ fraction to processes issuing sync requests (see the description
+ of the slice_idle tunable in this document, or [1, 2], for more
+ details).
+
+ - With respect to idling for service guarantees, if several
+ processes are competing for the device at the same time, but
+ all processes (and groups, after the following commit) have
+ the same weight, then BFQ guarantees the expected throughput
+ distribution without ever idling the device. Throughput is
+ thus as high as possible in this common scenario.
+
+ - If low-latency mode is enabled (default configuration), BFQ
+ executes some special heuristics to detect interactive and soft
+ real-time applications (e.g., video or audio players/streamers),
+ and to reduce their latency. The most important action taken to
+ achieve this goal is to give to the queues associated with these
+ applications more than their fair share of the device
+ throughput. For brevity, we call just "weight-raising" the whole
+ sets of actions taken by BFQ to privilege these queues. In
+ particular, BFQ provides a milder form of weight-raising for
+ interactive applications, and a stronger form for soft real-time
+ applications.
+
+ - BFQ automatically deactivates idling for queues born in a burst of
+ queue creations. In fact, these queues are usually associated with
+ the processes of applications and services that benefit mostly
+ from a high throughput. Examples are systemd during boot, or git
+ grep.
+
+ - As CFQ, BFQ merges queues performing interleaved I/O, i.e.,
+ performing random I/O that becomes mostly sequential if
+ merged. Differently from CFQ, BFQ achieves this goal with a more
+ reactive mechanism, called Early Queue Merge (EQM). EQM is so
+ responsive in detecting interleaved I/O (cooperating processes),
+ that it enables BFQ to achieve a high throughput, by queue
+ merging, even for queues for which CFQ needs a different
+ mechanism, preemption, to get a high throughput. As such EQM is a
+ unified mechanism to achieve a high throughput with interleaved
+ I/O.
+
+ - Queues are scheduled according to a variant of WF2Q+, named
+ B-WF2Q+, and implemented using an augmented rb-tree to preserve an
+ O(log N) overall complexity. See [2] for more details. B-WF2Q+ is
+ also ready for hierarchical scheduling. However, for a cleaner
+ logical breakdown, the code that enables and completes
+ hierarchical support is provided in the next commit, which focuses
+ exactly on this feature.
+
+ - B-WF2Q+ guarantees a tight deviation with respect to an ideal,
+ perfectly fair, and smooth service. In particular, B-WF2Q+
+ guarantees that each queue receives a fraction of the device
+ throughput proportional to its weight, even if the throughput
+ fluctuates, and regardless of: the device parameters, the current
+ workload and the budgets assigned to the queue.
+
+ - The last, budget-independence, property (although probably
+ counterintuitive in the first place) is definitely beneficial, for
+ the following reasons:
+
+ - First, with any proportional-share scheduler, the maximum
+ deviation with respect to an ideal service is proportional to
+ the maximum budget (slice) assigned to queues. As a consequence,
+ BFQ can keep this deviation tight not only because of the
+ accurate service of B-WF2Q+, but also because BFQ *does not*
+ need to assign a larger budget to a queue to let the queue
+ receive a higher fraction of the device throughput.
+
+ - Second, BFQ is free to choose, for every process (queue), the
+ budget that best fits the needs of the process, or best
+ leverages the I/O pattern of the process. In particular, BFQ
+ updates queue budgets with a simple feedback-loop algorithm that
+ allows a high throughput to be achieved, while still providing
+ tight latency guarantees to time-sensitive applications. When
+ the in-service queue expires, this algorithm computes the next
+ budget of the queue so as to:
+
+ - Let large budgets be eventually assigned to the queues
+ associated with I/O-bound applications performing sequential
+ I/O: in fact, the longer these applications are served once
+ got access to the device, the higher the throughput is.
+
+ - Let small budgets be eventually assigned to the queues
+ associated with time-sensitive applications (which typically
+ perform sporadic and short I/O), because, the smaller the
+ budget assigned to a queue waiting for service is, the sooner
+ B-WF2Q+ will serve that queue (Subsec 3.3 in [2]).
+
+- If several processes are competing for the device at the same time,
+ but all processes and groups have the same weight, then BFQ
+ guarantees the expected throughput distribution without ever idling
+ the device. It uses preemption instead. Throughput is then much
+ higher in this common scenario.
+
+- 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.
+
+
+3. What are BFQ's tunable?
+==========================
+
+The tunables back_seek-max, back_seek_penalty, fifo_expire_async and
+fifo_expire_sync below are the same as in CFQ. Their description is
+just copied from that for CFQ. Some considerations in the description
+of slice_idle are copied from CFQ too.
+
+per-process ioprio and weight
+-----------------------------
+
+Unless the cgroups interface is used, weights can be assigned to
+processes only indirectly, through I/O priorities, and according to
+the relation: weight = (IOPRIO_BE_NR - ioprio) * 10.
+
+slice_idle
+----------
+
+This parameter specifies how long BFQ should idle for next I/O
+request, when certain sync BFQ queues become empty. By default
+slice_idle is a non-zero value. Idling has a double purpose: boosting
+throughput and making sure that the desired throughput distribution is
+respected (see the description of how BFQ works, and, if needed, the
+papers referred there).
+
+As for throughput, idling can be very helpful on highly seeky media
+like single spindle SATA/SAS disks where we can cut down on overall
+number of seeks and see improved throughput.
+
+Setting slice_idle to 0 will remove all the idling on queues and one
+should see an overall improved throughput on faster storage devices
+like multiple SATA/SAS disks in hardware RAID configuration.
+
+So depending on storage and workload, it might be useful to set
+slice_idle=0. In general for SATA/SAS disks and software RAID of
+SATA/SAS disks keeping slice_idle enabled should be useful. For any
+configurations where there are multiple spindles behind single LUN
+(Host based hardware RAID controller or for storage arrays), setting
+slice_idle=0 might end up in better throughput and acceptable
+latencies.
+
+Idling is however necessary to have service guarantees enforced in
+case of differentiated weights or differentiated I/O-request lengths.
+To see why, suppose that a given BFQ queue A must get several I/O
+requests served for each request served for another queue B. Idling
+ensures that, if A makes a new I/O request slightly after becoming
+empty, then no request of B is dispatched in the middle, and thus A
+does not lose the possibility to get more than one request dispatched
+before the next request of B is dispatched. Note that idling
+guarantees the desired differentiated treatment of queues only in
+terms of I/O-request dispatches. To guarantee that the actual service
+order then corresponds to the dispatch order, the strict_guarantees
+tunable must be set too.
+
+There is an important flipside for idling: apart from the above cases
+where it is beneficial also for throughput, idling can severely impact
+throughput. One important case is random workload. Because of this
+issue, BFQ tends to avoid idling as much as possible, when it is not
+beneficial also for throughput. As a consequence of this behavior, and
+of further issues described for the strict_guarantees tunable,
+short-term service guarantees may be occasionally violated. And, in
+some cases, these guarantees may be more important than guaranteeing
+maximum throughput. For example, in video playing/streaming, a very
+low drop rate may be more important than maximum throughput. In these
+cases, consider setting the strict_guarantees parameter.
+
+strict_guarantees
+-----------------
+
+If this parameter is set (default: unset), then BFQ
+
+- always performs idling when the in-service queue becomes empty;
+
+- forces the device to serve one I/O request at a time, by dispatching a
+ new request only if there is no outstanding request.
+
+In the presence of differentiated weights or I/O-request sizes, both
+the above conditions are needed to guarantee that every BFQ queue
+receives its allotted share of the bandwidth. The first condition is
+needed for the reasons explained in the description of the slice_idle
+tunable. The second condition is needed because all modern storage
+devices reorder internally-queued requests, which may trivially break
+the service guarantees enforced by the I/O scheduler.
+
+Setting strict_guarantees may evidently affect throughput.
+
+back_seek_max
+-------------
+
+This specifies, given in Kbytes, the maximum "distance" for backward seeking.
+The distance is the amount of space from the current head location to the
+sectors that are backward in terms of distance.
+
+This parameter allows the scheduler to anticipate requests in the "backward"
+direction and consider them as being the "next" if they are within this
+distance from the current head location.
+
+back_seek_penalty
+-----------------
+
+This parameter is used to compute the cost of backward seeking. If the
+backward distance of request is just 1/back_seek_penalty from a "front"
+request, then the seeking cost of two requests is considered equivalent.
+
+So scheduler will not bias toward one or the other request (otherwise scheduler
+will bias toward front request). Default value of back_seek_penalty is 2.
+
+fifo_expire_async
+-----------------
+
+This parameter is used to set the timeout of asynchronous requests. Default
+value of this is 248ms.
+
+fifo_expire_sync
+----------------
+
+This parameter is used to set the timeout of synchronous requests. Default
+value of this is 124ms. In case to favor synchronous requests over asynchronous
+one, this value should be decreased relative to fifo_expire_async.
+
+low_latency
+-----------
+
+This parameter is used to enable/disable BFQ's low latency mode. By
+default, low latency mode is enabled. If enabled, interactive and soft
+real-time applications are privileged and experience a lower latency,
+as explained in more detail in the description of how BFQ works.
+
+timeout_sync
+------------
+
+Maximum amount of device time that can be given to a task (queue) once
+it has been selected for service. On devices with costly seeks,
+increasing this time usually increases maximum throughput. On the
+opposite end, increasing this time coarsens the granularity of the
+short-term bandwidth and latency guarantees, especially if the
+following parameter is set to zero.
+
+max_budget
+----------
+
+Maximum amount of service, measured in sectors, that can be provided
+to a BFQ queue once it is set in service (of course within the limits
+of the above timeout). According to what said in the description of
+the algorithm, larger values increase the throughput in proportion to
+the percentage of sequential I/O requests issued. The price of larger
+values is that they coarsen the granularity of short-term bandwidth
+and latency guarantees.
+
+The default value is 0, which enables auto-tuning: BFQ sets max_budget
+to the maximum number of sectors that can be served during
+timeout_sync, according to the estimated peak rate.
+
+weights
+-------
+
+Read-only parameter, used to show the weights of the currently active
+BFQ queues.
+
+
+wr_ tunables
+------------
+
+BFQ exports a few parameters to control/tune the behavior of
+low-latency heuristics.
+
+wr_coeff
+
+Factor by which the weight of a weight-raised queue is multiplied. If
+the queue is deemed soft real-time, then the weight is further
+multiplied by an additional, constant factor.
+
+wr_max_time
+
+Maximum duration of a weight-raising period for an interactive task
+(ms). If set to zero (default value), then this value is computed
+automatically, as a function of the peak rate of the device. In any
+case, when the value of this parameter is read, it always reports the
+current duration, regardless of whether it has been set manually or
+computed automatically.
+
+wr_max_softrt_rate
+
+Maximum service rate below which a queue is deemed to be associated
+with a soft real-time application, and is then weight-raised
+accordingly (sectors/sec).
+
+wr_min_idle_time
+
+Minimum idle period after which interactive weight-raising may be
+reactivated for a queue (in ms).
+
+wr_rt_max_time
+
+Maximum weight-raising duration for soft real-time queues (in ms). The
+start time from which this duration is considered is automatically
+moved forward if the queue is detected to be still soft real-time
+before the current soft real-time weight-raising period finishes.
+
+wr_min_inter_arr_async
+
+Minimum period between I/O request arrivals after which weight-raising
+may be reactivated for an already busy async queue (in ms).
+
+
+4. Group scheduling with BFQ
+============================
+
+BFQ supports both cgroup-v1 and cgroup-v2 io controllers, namely blkio
+and io. In particular, BFQ supports weight-based proportional
+share.
+
+4-1 Service guarantees provided
+-------------------------------
+
+With BFQ, proportional share means true proportional share of the
+device bandwidth, according to group weights. For example, a group
+with weight 200 gets twice the bandwidth, and not just twice the time,
+of a group with weight 100.
+
+BFQ supports hierarchies (group trees) of any depth. Bandwidth is
+distributed among groups and processes in the expected way: for each
+group, the children of the group share the whole bandwidth of the
+group in proportion to their weights. In particular, this implies
+that, for each leaf group, every process of the group receives the
+same share of the whole group bandwidth, unless the ioprio of the
+process is modified.
+
+The resource-sharing guarantee for a group may partially or totally
+switch from bandwidth to time, if providing bandwidth guarantees to
+the group lowers the throughput too much. This switch occurs on a
+per-process basis: if a process of a leaf group causes throughput loss
+if served in such a way to receive its share of the bandwidth, then
+BFQ switches back to just time-based proportional share for that
+process.
+
+4-2 Interface
+-------------
+
+To get proportional sharing of bandwidth with BFQ for a given device,
+BFQ must of course be the active scheduler for that device.
+
+Within each group directory, the names of the files associated with
+BFQ-specific cgroup parameters and stats begin with the "bfq."
+prefix. So, with cgroups-v1 or cgroups-v2, the full prefix for
+BFQ-specific files is "blkio.bfq." or "io.bfq." For example, the group
+parameter to set the weight of a group with BFQ is blkio.bfq.weight
+or io.bfq.weight.
+
+Parameters to set
+-----------------
+
+For each group, there is only the following parameter to set.
+
+weight (namely blkio.bfq.weight or io.bfq-weight): the weight of the
+group inside its parent. Available values: 1..10000 (default 100). The
+linear mapping between ioprio and weights, described at the beginning
+of the tunable section, is still valid, but all weights higher than
+IOPRIO_BE_NR*10 are mapped to ioprio 0.
+
+
+[1] P. Valente, A. Avanzini, "Evolution of the BFQ Storage I/O
+ Scheduler", Proceedings of the First Workshop on Mobile System
+ Technologies (MST-2015), May 2015.
+ http://algogroup.unimore.it/people/paolo/disk_sched/mst-2015.pdf
+
+[2] 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.
+ Slightly extended version:
+ http://algogroup.unimore.it/people/paolo/disk_sched/bfq-v1-suite-
+ results.pdf
diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
index 58fc868..562e30e 100644
--- a/block/Kconfig.iosched
+++ b/block/Kconfig.iosched
@@ -69,6 +69,17 @@ config MQ_IOSCHED_DEADLINE
---help---
MQ version of the deadline IO scheduler.
+config IOSCHED_BFQ
+ tristate "BFQ I/O scheduler"
+ default n
+ ---help---
+ BFQ I/O scheduler for BLK-MQ. BFQ distributes the bandwidth of
+ of the device among all processes according to their weights,
+ regardless of the device parameters and with any workload. It
+ also guarantees a low latency to interactive and soft
+ real-time applications. Details in
+ Documentation/block/bfq-iosched.txt
+
endmenu
endif
diff --git a/block/Makefile b/block/Makefile
index 081bb68..91869f2 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -20,6 +20,7 @@ obj-$(CONFIG_IOSCHED_NOOP) += noop-iosched.o
obj-$(CONFIG_IOSCHED_DEADLINE) += deadline-iosched.o
obj-$(CONFIG_IOSCHED_CFQ) += cfq-iosched.o
obj-$(CONFIG_MQ_IOSCHED_DEADLINE) += mq-deadline.o
+obj-$(CONFIG_IOSCHED_BFQ) += bfq-iosched.o
obj-$(CONFIG_BLOCK_COMPAT) += compat_ioctl.o
obj-$(CONFIG_BLK_CMDLINE_PARSER) += cmdline-parser.o
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
new file mode 100644
index 0000000..4e60fe9
--- /dev/null
+++ b/block/bfq-iosched.c
@@ -0,0 +1,4156 @@
+/*
+ * Budget Fair Queueing (BFQ) I/O 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>
+ * Arianna Avanzini <avanzini@google.com>
+ *
+ * Copyright (C) 2017 Paolo Valente <paolo.valente@linaro.org>
+ *
+ * Licensed under GPL-2.
+ *
+ * BFQ is a proportional-share I/O scheduler, with some extra
+ * low-latency capabilities. BFQ also supports full hierarchical
+ * scheduling through cgroups. Next paragraphs provide an introduction
+ * on BFQ inner workings. Details on BFQ benefits and usage can be
+ * found in Documentation/block/bfq-iosched.txt.
+ *
+ * BFQ is a proportional-share storage-I/O scheduling algorithm based
+ * on the slice-by-slice service scheme of CFQ. But BFQ assigns
+ * budgets, measured in number of sectors, to processes instead of
+ * time slices. The device is not granted to the in-service process
+ * for a given time slice, but until it has exhausted its assigned
+ * budget. This change from the time to the service domain enables BFQ
+ * to distribute the device throughput among processes as desired,
+ * without any distortion due to throughput fluctuations, or to device
+ * internal queueing. BFQ uses an ad hoc internal scheduler, called
+ * B-WF2Q+, to schedule processes according to their budgets. More
+ * precisely, BFQ schedules queues associated with processes. Each
+ * process/queue is assigned a user-configurable weight, and B-WF2Q+
+ * guarantees that each queue receives a fraction of the throughput
+ * proportional to its weight. Thanks to the accurate policy of
+ * B-WF2Q+, BFQ can afford to assign high budgets to I/O-bound
+ * processes issuing sequential requests (to boost the throughput),
+ * and yet guarantee a low latency to interactive and soft real-time
+ * applications.
+ *
+ * In particular, to provide these low-latency guarantees, BFQ
+ * explicitly privileges the I/O of two classes of time-sensitive
+ * applications: interactive and soft real-time. This feature enables
+ * BFQ to provide applications in these classes with a very low
+ * latency. Finally, BFQ also features additional heuristics for
+ * preserving both a low latency and a high throughput on NCQ-capable,
+ * rotational or flash-based devices, and to get the job done quickly
+ * for applications consisting in many I/O-bound processes.
+ *
+ * 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 and 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+, which is described in [2], together with
+ * H-WF2Q+, while the augmented tree used here to implement B-WF2Q+
+ * with O(log N) complexity derives from the one introduced with EEVDF
+ * in [3].
+ *
+ * [1] P. Valente, A. Avanzini, "Evolution of the BFQ Storage I/O
+ * Scheduler", Proceedings of the First Workshop on Mobile System
+ * Technologies (MST-2015), May 2015.
+ * http://algogroup.unimore.it/people/paolo/disk_sched/mst-2015.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/elevator.h>
+#include <linux/ktime.h>
+#include <linux/rbtree.h>
+#include <linux/ioprio.h>
+#include <linux/sbitmap.h>
+#include <linux/delay.h>
+
+#include "blk.h"
+#include "blk-mq.h"
+#include "blk-mq-tag.h"
+#include "blk-mq-sched.h"
+#include <linux/blktrace_api.h>
+#include <linux/hrtimer.h>
+#include <linux/blk-cgroup.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_WEIGHT_CONVERSION_COEFF 10
+
+#define BFQ_DEFAULT_QUEUE_IOPRIO 4
+
+#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.
+ *
+ * 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 {
+ /* tree for active entities (i.e., those backlogged) */
+ struct rb_root active;
+ /* tree for idle entities (i.e., not backlogged, with V <= F_i)*/
+ struct rb_root idle;
+
+ struct bfq_entity *first_idle; /* idle entity with minimum F_i */
+ struct bfq_entity *last_idle; /* idle entity with maximum F_i */
+
+ u64 vtime; /* scheduler virtual time */
+ /* scheduler weight sum; active and idle entities contribute to it */
+ unsigned long wsum;
+};
+
+/**
+ * struct bfq_sched_data - multi-class scheduler.
+ *
+ * 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_in_service 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 *in_service_entity; /* entity in service */
+ /* head-of-the-line entity in the scheduler */
+ struct bfq_entity *next_in_service;
+ /* array of service trees, one per ioprio_class */
+ struct bfq_service_tree service_tree[BFQ_IOPRIO_CLASSES];
+};
+
+/**
+ * struct bfq_entity - schedulable entity.
+ *
+ * A bfq_entity is used to represent a bfq_queue (leaf node in the upper
+ * level scheduler). Each entity belongs to the sched_data of the parent
+ * group 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 @prio_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.
+ *
+ * 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 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; /* service_tree member */
+
+ /*
+ * flag, true if the entity is on a tree (either the active or
+ * the idle one of its service_tree).
+ */
+ int on_st;
+
+ u64 finish; /* B-WF2Q+ finish timestamp (aka F_i) */
+ u64 start; /* B-WF2Q+ start timestamp (aka S_i) */
+
+ /* tree the entity is enqueued into; %NULL if not on a tree */
+ struct rb_root *tree;
+
+ /*
+ * minimum start time of the (active) subtree rooted at this
+ * entity; used for O(log N) lookups into active trees
+ */
+ u64 min_start;
+
+ /* amount of service received during the last service slot */
+ int service;
+
+ /* budget, used also to calculate F_i: F_i = S_i + @budget / @weight */
+ int budget;
+
+ unsigned short weight; /* weight of the queue */
+ unsigned short new_weight; /* next weight if a change is in progress */
+
+ /* original weight, used to implement weight boosting */
+ unsigned short orig_weight;
+
+ /* parent entity, for hierarchical scheduling */
+ struct bfq_entity *parent;
+
+ /*
+ * For non-leaf nodes in the hierarchy, the associated
+ * scheduler queue, %NULL on leaf nodes.
+ */
+ struct bfq_sched_data *my_sched_data;
+ /* the scheduler queue this entity belongs to */
+ struct bfq_sched_data *sched_data;
+
+ /* flag, set to request a weight, ioprio or ioprio_class change */
+ int prio_changed;
+};
+
+/**
+ * struct bfq_ttime - per process thinktime stats.
+ */
+struct bfq_ttime {
+ u64 last_end_request; /* completion time of last request */
+
+ u64 ttime_total; /* total process thinktime */
+ unsigned long ttime_samples; /* number of thinktime samples */
+ u64 ttime_mean; /* average process thinktime */
+
+};
+
+/**
+ * struct bfq_queue - leaf schedulable entity.
+ *
+ * A bfq_queue is a leaf request queue; it can be associated with an
+ * io_context or more, if it is async.
+ */
+struct bfq_queue {
+ /* reference counter */
+ int ref;
+ /* parent bfq_data */
+ struct bfq_data *bfqd;
+
+ /* current ioprio and ioprio class */
+ unsigned short ioprio, ioprio_class;
+ /* next ioprio and ioprio class if a change is in progress */
+ unsigned short new_ioprio, new_ioprio_class;
+
+ /* sorted list of pending requests */
+ struct rb_root sort_list;
+ /* if fifo isn't expired, next request to serve */
+ struct request *next_rq;
+ /* number of sync and async requests queued */
+ int queued[2];
+ /* number of requests currently allocated */
+ int allocated;
+ /* number of pending metadata requests */
+ int meta_pending;
+ /* fifo list of requests in sort_list */
+ struct list_head fifo;
+
+ /* entity representing this queue in the scheduler */
+ struct bfq_entity entity;
+
+ /* maximum budget allowed from the feedback mechanism */
+ int max_budget;
+ /* budget expiration (in jiffies) */
+ unsigned long budget_timeout;
+
+ /* number of requests on the dispatch list or inside driver */
+ int dispatched;
+
+ unsigned int flags; /* status flags.*/
+
+ /* node for active/idle bfqq list inside parent bfqd */
+ struct list_head bfqq_list;
+
+ /* associated @bfq_ttime struct */
+ struct bfq_ttime ttime;
+
+ /* bit vector: a 1 for each seeky requests in history */
+ u32 seek_history;
+ /* position of the last request enqueued */
+ sector_t last_request_pos;
+
+ /* Number of consecutive pairs of request completion and
+ * arrival, such that the queue becomes idle after the
+ * completion, but the next request arrives within an idle
+ * time slice; used only if the queue's IO_bound flag has been
+ * cleared.
+ */
+ unsigned int requests_within_timer;
+
+ /* pid of the process owning the queue, used for logging purposes */
+ pid_t pid;
+};
+
+/**
+ * struct bfq_io_cq - per (request_queue, io_context) structure.
+ */
+struct bfq_io_cq {
+ /* associated io_cq structure */
+ struct io_cq icq; /* must be the first member */
+ /* array of two process queues, the sync and the async */
+ struct bfq_queue *bfqq[2];
+ /* per (request_queue, blkcg) ioprio */
+ int ioprio;
+};
+
+enum bfq_device_speed {
+ BFQ_BFQD_FAST,
+ BFQ_BFQD_SLOW,
+};
+
+/**
+ * struct bfq_data - per-device data structure.
+ *
+ * All the fields are protected by @lock.
+ */
+struct bfq_data {
+ /* device request queue */
+ struct request_queue *queue;
+ /* dispatch queue */
+ struct list_head dispatch;
+
+ /* root @bfq_sched_data for the device */
+ struct bfq_sched_data sched_data;
+
+ /*
+ * Number of bfq_queues containing requests (including the
+ * queue in service, even if it is idling).
+ */
+ int busy_queues;
+ /* number of queued requests */
+ int queued;
+ /* number of requests dispatched and waiting for completion */
+ int rq_in_driver;
+
+ /*
+ * Maximum number of requests in driver in the last
+ * @hw_tag_samples completed requests.
+ */
+ int max_rq_in_driver;
+ /* number of samples used to calculate hw_tag */
+ int hw_tag_samples;
+ /* flag set to one if the driver is showing a queueing behavior */
+ int hw_tag;
+
+ /* number of budgets assigned */
+ int budgets_assigned;
+
+ /*
+ * Timer set when idling (waiting) for the next request from
+ * the queue in service.
+ */
+ struct hrtimer idle_slice_timer;
+
+ /* bfq_queue in service */
+ struct bfq_queue *in_service_queue;
+ /* bfq_io_cq (bic) associated with the @in_service_queue */
+ struct bfq_io_cq *in_service_bic;
+
+ /* on-disk position of the last served request */
+ sector_t last_position;
+
+ /* beginning of the last budget */
+ ktime_t last_budget_start;
+ /* beginning of the last idle slice */
+ ktime_t last_idling_start;
+ /* number of samples used to calculate @peak_rate */
+ int peak_rate_samples;
+ /* peak transfer rate observed for a budget */
+ u64 peak_rate;
+ /* maximum budget allotted to a bfq_queue before rescheduling */
+ int bfq_max_budget;
+
+ /* list of all the bfq_queues active on the device */
+ struct list_head active_list;
+ /* list of all the bfq_queues idle on the device */
+ struct list_head idle_list;
+
+ /*
+ * Timeout for async/sync requests; when it fires, requests
+ * are served in fifo order.
+ */
+ u64 bfq_fifo_expire[2];
+ /* weight of backward seeks wrt forward ones */
+ unsigned int bfq_back_penalty;
+ /* maximum allowed backward seek */
+ unsigned int bfq_back_max;
+ /* maximum idling time */
+ u32 bfq_slice_idle;
+ /* last time CLASS_IDLE was served */
+ u64 bfq_class_idle_last_service;
+
+ /* user-configured max budget value (0 for auto-tuning) */
+ int bfq_user_max_budget;
+ /*
+ * Timeout for bfq_queues to consume their budget; used to
+ * prevent seeky queues from imposing long latencies to
+ * sequential or quasi-sequential ones (this also implies that
+ * seeky queues cannot receive guarantees in the service
+ * domain; after a timeout they are charged for the time they
+ * have been in service, to preserve fairness among them, but
+ * without service-domain guarantees).
+ */
+ unsigned int bfq_timeout;
+
+ /*
+ * Number of consecutive requests that must be issued within
+ * the idle time slice to set again idling to a queue which
+ * was marked as non-I/O-bound (see the definition of the
+ * IO_bound flag for further details).
+ */
+ unsigned int bfq_requests_within_timer;
+
+ /*
+ * Force device idling whenever needed to provide accurate
+ * service guarantees, without caring about throughput
+ * issues. CAVEAT: this may even increase latencies, in case
+ * of useless idling for processes that did stop doing I/O.
+ */
+ bool strict_guarantees;
+
+ /* fallback dummy bfqq for extreme OOM conditions */
+ struct bfq_queue oom_bfqq;
+
+ spinlock_t lock;
+
+ /*
+ * bic associated with the task issuing current bio for
+ * merging. This and the next field are used as a support to
+ * be able to perform the bic lookup, needed by bio-merge
+ * functions, before the scheduler lock is taken, and thus
+ * avoid taking the request-queue lock while the scheduler
+ * lock is being held.
+ */
+ struct bfq_io_cq *bio_bic;
+ /* bfqq associated with the task issuing current bio for merging */
+ struct bfq_queue *bio_bfqq;
+};
+
+enum bfqq_state_flags {
+ BFQ_BFQQ_FLAG_busy = 0, /* has requests or is in service */
+ BFQ_BFQQ_FLAG_wait_request, /* waiting for a request */
+ BFQ_BFQQ_FLAG_non_blocking_wait_rq, /*
+ * waiting for a request
+ * without idling the device
+ */
+ BFQ_BFQQ_FLAG_fifo_expire, /* FIFO checked in this slice */
+ BFQ_BFQQ_FLAG_idle_window, /* slice idling enabled */
+ BFQ_BFQQ_FLAG_sync, /* synchronous queue */
+ BFQ_BFQQ_FLAG_budget_new, /* no completion with this budget */
+ BFQ_BFQQ_FLAG_IO_bound, /*
+ * bfqq has timed-out at least once
+ * having consumed at most 2/10 of
+ * its budget
+ */
+};
+
+#define BFQ_BFQQ_FNS(name) \
+static void bfq_mark_bfqq_##name(struct bfq_queue *bfqq) \
+{ \
+ (bfqq)->flags |= (1 << BFQ_BFQQ_FLAG_##name); \
+} \
+static void bfq_clear_bfqq_##name(struct bfq_queue *bfqq) \
+{ \
+ (bfqq)->flags &= ~(1 << BFQ_BFQQ_FLAG_##name); \
+} \
+static 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(non_blocking_wait_rq);
+BFQ_BFQQ_FNS(fifo_expire);
+BFQ_BFQQ_FNS(idle_window);
+BFQ_BFQQ_FNS(sync);
+BFQ_BFQQ_FNS(budget_new);
+BFQ_BFQQ_FNS(IO_bound);
+#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 */
+ BFQ_BFQQ_PREEMPTED /* preemption in progress */
+};
+
+static struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity);
+
+static struct bfq_service_tree *
+bfq_entity_service_tree(struct bfq_entity *entity)
+{
+ struct bfq_sched_data *sched_data = entity->sched_data;
+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+ unsigned int idx = bfqq ? bfqq->ioprio_class - 1 :
+ BFQ_DEFAULT_GRP_CLASS - 1;
+
+ return sched_data->service_tree + idx;
+}
+
+static struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync)
+{
+ return bic->bfqq[is_sync];
+}
+
+static void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq,
+ bool is_sync)
+{
+ bic->bfqq[is_sync] = bfqq;
+}
+
+static struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic)
+{
+ return bic->icq.q->elevator->elevator_data;
+}
+
+static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio);
+static void bfq_put_queue(struct bfq_queue *bfqq);
+static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
+ struct bio *bio, bool is_sync,
+ struct bfq_io_cq *bic);
+static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
+
+/*
+ * Array of async queues for all the processes, one queue
+ * per ioprio value per ioprio_class.
+ */
+struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR];
+/* Async queue for the idle class (ioprio is ignored) */
+struct bfq_queue *async_idle_bfqq;
+
+/* Expiration time of sync (0) and async (1) requests, in ns. */
+static const u64 bfq_fifo_expire[2] = { NSEC_PER_SEC / 4, NSEC_PER_SEC / 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 ns. */
+static u64 bfq_slice_idle = NSEC_PER_SEC / 125;
+
+/* Minimum number of assigned budgets for which stats are safe to compute. */
+static const int bfq_stats_min_budgets = 194;
+
+/* Default maximum budget values, in sectors and number of requests. */
+static const int bfq_default_max_budget = 16 * 1024;
+
+/* Default timeout values, in jiffies, approximating CFQ defaults. */
+static const int bfq_timeout = HZ / 8;
+
+static struct kmem_cache *bfq_pool;
+
+/* Below this threshold (in ms), we consider thinktime immediate. */
+#define BFQ_MIN_TT (2 * NSEC_PER_MSEC)
+
+/* 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 * 100)
+#define BFQQ_SECT_THR_NONROT (sector_t)(2 * 32)
+#define BFQQ_CLOSE_THR (sector_t)(8 * 1024)
+#define BFQQ_SEEKY(bfqq) (hweight32(bfqq->seek_history) > 32/8)
+
+/* Budget feedback step. */
+#define BFQ_BUDGET_STEP 128
+
+/* 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
+
+#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])
+
+/**
+ * icq_to_bic - convert iocontext queue structure to bfq_io_cq.
+ * @icq: the iocontext queue.
+ */
+static 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.
+ * @q: the request queue.
+ */
+static struct bfq_io_cq *bfq_bic_lookup(struct bfq_data *bfqd,
+ struct io_context *ioc,
+ struct request_queue *q)
+{
+ if (ioc) {
+ unsigned long flags;
+ struct bfq_io_cq *icq;
+
+ spin_lock_irqsave(q->queue_lock, flags);
+ icq = icq_to_bic(ioc_lookup_icq(ioc, q));
+ spin_unlock_irqrestore(q->queue_lock, flags);
+
+ return icq;
+ }
+
+ return NULL;
+}
+
+#define for_each_entity(entity) \
+ for (; entity ; entity = NULL)
+
+#define for_each_entity_safe(entity, parent) \
+ for (parent = NULL; entity ; entity = parent)
+
+static int bfq_update_next_in_service(struct bfq_sched_data *sd)
+{
+ return 0;
+}
+
+static void bfq_check_next_in_service(struct bfq_sched_data *sd,
+ struct bfq_entity *entity)
+{
+}
+
+static void bfq_update_budget(struct bfq_entity *next_in_service)
+{
+}
+
+/*
+ * 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 int bfq_gt(u64 a, u64 b)
+{
+ return (s64)(a - b) > 0;
+}
+
+static struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity)
+{
+ struct bfq_queue *bfqq = NULL;
+
+ if (!entity->my_sched_data)
+ 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 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 void bfq_calc_finish(struct bfq_entity *entity, unsigned long service)
+{
+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+ entity->finish = entity->start +
+ bfq_delta(service, entity->weight);
+
+ if (bfqq) {
+ 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 struct bfq_entity *bfq_entity_of(struct rb_node *node)
+{
+ struct bfq_entity *entity = NULL;
+
+ if (node)
+ 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 void bfq_extract(struct rb_root *root, struct bfq_entity *entity)
+{
+ 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;
+
+ 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)
+ 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;
+
+ while (*node) {
+ 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 void bfq_update_min(struct bfq_entity *entity, struct rb_node *node)
+{
+ struct bfq_entity *child;
+
+ if (node) {
+ 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 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)
+ return;
+
+ if (node == parent->rb_left && parent->rb_right)
+ bfq_update_active_node(parent->rb_right);
+ else if (parent->rb_left)
+ 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)
+ node = node->rb_left;
+ else if (node->rb_right)
+ node = node->rb_right;
+
+ bfq_update_active_tree(node);
+
+ if (bfqq)
+ 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)
+{
+ return (IOPRIO_BE_NR - ioprio) * BFQ_WEIGHT_CONVERSION_COEFF;
+}
+
+/**
+ * bfq_weight_to_ioprio - calc an ioprio from a weight.
+ * @weight: the weight value to convert.
+ *
+ * To preserve as much 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 * BFQ_WEIGHT_CONVERSION_COEFF.
+ */
+static unsigned short bfq_weight_to_ioprio(int weight)
+{
+ return IOPRIO_BE_NR * BFQ_WEIGHT_CONVERSION_COEFF - weight < 0 ?
+ 0 : IOPRIO_BE_NR * BFQ_WEIGHT_CONVERSION_COEFF - weight;
+}
+
+static void bfq_get_entity(struct bfq_entity *entity)
+{
+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+ if (bfqq) {
+ bfqq->ref++;
+ bfq_log_bfqq(bfqq->bfqd, bfqq, "get_entity: %p %d",
+ bfqq, 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 && !node->rb_left)
+ deepest = rb_parent(node);
+ else if (!node->rb_right)
+ deepest = node->rb_left;
+ else if (!node->rb_left)
+ deepest = node->rb_right;
+ else {
+ deepest = rb_next(node);
+ if (deepest->rb_right)
+ 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)
+ bfq_update_active_tree(node);
+
+ if (bfqq)
+ 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 || bfq_gt(first_idle->finish, entity->finish))
+ st->first_idle = entity;
+ if (!last_idle || bfq_gt(entity->finish, last_idle->finish))
+ st->last_idle = entity;
+
+ bfq_insert(&st->idle, entity);
+
+ if (bfqq)
+ 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;
+
+ entity->on_st = 0;
+ st->wsum -= entity->weight;
+ if (bfqq) {
+ sd = entity->sched_data;
+ bfq_log_bfqq(bfqq->bfqd, bfqq, "forget_entity: %p %d",
+ bfqq, 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 &&
+ !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 && !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->prio_changed) {
+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+ unsigned short prev_weight, new_weight;
+ struct bfq_data *bfqd = NULL;
+
+ if (bfqq)
+ bfqd = bfqq->bfqd;
+
+ old_st->wsum -= entity->weight;
+
+ if (entity->new_weight != entity->orig_weight) {
+ if (entity->new_weight < BFQ_MIN_WEIGHT ||
+ entity->new_weight > BFQ_MAX_WEIGHT) {
+ pr_crit("update_weight_prio: new_weight %d\n",
+ entity->new_weight);
+ if (entity->new_weight < BFQ_MIN_WEIGHT)
+ entity->new_weight = BFQ_MIN_WEIGHT;
+ else
+ entity->new_weight = BFQ_MAX_WEIGHT;
+ }
+ entity->orig_weight = entity->new_weight;
+ if (bfqq)
+ bfqq->ioprio =
+ bfq_weight_to_ioprio(entity->orig_weight);
+ }
+
+ if (bfqq)
+ bfqq->ioprio_class = bfqq->new_ioprio_class;
+ entity->prio_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);
+
+ prev_weight = entity->weight;
+ new_weight = entity->orig_weight;
+ entity->weight = new_weight;
+
+ 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, int 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;
+
+ st->vtime += bfq_delta(served, st->wsum);
+ bfq_forget_idle(st);
+ }
+ bfq_log_bfqq(bfqq->bfqd, bfqq, "bfqq_served %d 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 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.
+ * @non_blocking_wait_rq: true if this entity was waiting for a request
+ *
+ * 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,
+ bool non_blocking_wait_rq)
+{
+ struct bfq_sched_data *sd = entity->sched_data;
+ struct bfq_service_tree *st = bfq_entity_service_tree(entity);
+ bool backshifted = false;
+
+ if (entity == sd->in_service_entity) {
+ /*
+ * 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->in_service_entity = NULL;
+ } else if (entity->tree == &st->active) {
+ /*
+ * Requeueing an entity due to a change of some
+ * next_in_service entity below it. We reuse the
+ * old start time.
+ */
+ bfq_active_extract(st, entity);
+ } else {
+ unsigned long long min_vstart;
+
+ /* See comments on bfq_fqq_update_budg_for_activation */
+ if (non_blocking_wait_rq && bfq_gt(st->vtime, entity->finish)) {
+ backshifted = true;
+ min_vstart = entity->finish;
+ } else
+ min_vstart = st->vtime;
+
+ 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(min_vstart, entity->finish) ?
+ min_vstart : 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 = min_vstart;
+ st->wsum += entity->weight;
+ bfq_get_entity(entity);
+
+ entity->on_st = 1;
+ }
+ }
+
+ st = __bfq_entity_update_weight_prio(st, entity);
+ bfq_calc_finish(entity, entity->budget);
+
+ /*
+ * If some queues enjoy backshifting for a while, then their
+ * (virtual) finish timestamps may happen to become lower and
+ * lower than the system virtual time. In particular, if
+ * these queues often happen to be idle for short time
+ * periods, and during such time periods other queues with
+ * higher timestamps happen to be busy, then the backshifted
+ * timestamps of the former queues can become much lower than
+ * the system virtual time. In fact, to serve the queues with
+ * higher timestamps while the ones with lower timestamps are
+ * idle, the system virtual time may be pushed-up to much
+ * higher values than the finish timestamps of the idle
+ * queues. As a consequence, the finish timestamps of all new
+ * or newly activated queues may end up being much larger than
+ * those of lucky queues with backshifted timestamps. The
+ * latter queues may then monopolize the device for a lot of
+ * time. This would simply break service guarantees.
+ *
+ * To reduce this problem, push up a little bit the
+ * backshifted timestamps of the queue associated with this
+ * entity (only a queue can happen to have the backshifted
+ * flag set): just enough to let the finish timestamp of the
+ * queue be equal to the current value of the system virtual
+ * time. This may introduce a little unfairness among queues
+ * with backshifted timestamps, but it does not break
+ * worst-case fairness guarantees.
+ */
+ if (backshifted && bfq_gt(st->vtime, entity->finish)) {
+ unsigned long delta = st->vtime - entity->finish;
+
+ entity->start += delta;
+ entity->finish += delta;
+ }
+
+ bfq_active_insert(st, entity);
+}
+
+/**
+ * bfq_activate_entity - activate an entity and its ancestors if necessary.
+ * @entity: the entity to activate.
+ * @non_blocking_wait_rq: true if this entity was waiting for a request
+ *
+ * Activate @entity and all the entities on the path from it to the root.
+ */
+static void bfq_activate_entity(struct bfq_entity *entity,
+ bool non_blocking_wait_rq)
+{
+ struct bfq_sched_data *sd;
+
+ for_each_entity(entity) {
+ __bfq_activate_entity(entity, non_blocking_wait_rq);
+
+ sd = entity->sched_data;
+ if (!bfq_update_next_in_service(sd))
+ /*
+ * No need to propagate the activation to the
+ * upper entities, as they will be updated when
+ * the in-service 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 in service or if it was the next_in_service 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_in_service = entity == sd->in_service_entity;
+ int ret = 0;
+
+ if (!entity->on_st)
+ return 0;
+
+ if (was_in_service) {
+ bfq_calc_finish(entity, entity->service);
+ sd->in_service_entity = NULL;
+ } else if (entity->tree == &st->active)
+ bfq_active_extract(st, entity);
+ else if (entity->tree == &st->idle)
+ bfq_idle_extract(st, entity);
+
+ if (was_in_service || sd->next_in_service == entity)
+ ret = bfq_update_next_in_service(sd);
+
+ if (!requeue || !bfq_gt(entity->finish, st->vtime))
+ bfq_forget_entity(st, entity);
+ else
+ bfq_idle_insert(st, 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 = NULL;
+
+ 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
+ * in service.
+ */
+ break;
+
+ if (sd->next_in_service)
+ /*
+ * The parent entity is still backlogged and
+ * the budgets on the path towards the root
+ * need to be updated.
+ */
+ goto update;
+
+ /*
+ * If we get here, then the parent is no more backlogged and
+ * we want to propagate the deactivation upwards.
+ */
+ requeue = 1;
+ }
+
+ return;
+
+update:
+ entity = parent;
+ for_each_entity(entity) {
+ __bfq_activate_entity(entity, false);
+
+ sd = entity->sched_data;
+ if (!bfq_update_next_in_service(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 processes 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_entity - 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) {
+ entry = rb_entry(node, struct bfq_entity, rb_node);
+left:
+ if (!bfq_gt(entry->start, st->vtime))
+ first = entry;
+
+ if (node->rb_left) {
+ 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)
+ break;
+ node = node->rb_right;
+ }
+
+ 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_in_service = NULL;
+
+ if (RB_EMPTY_ROOT(&st->active))
+ return NULL;
+
+ bfq_update_vtime(st);
+ entity = bfq_first_active_entity(st);
+
+ /*
+ * If the chosen entity does not match with the sched_data's
+ * next_in_service and we are forcedly serving the IDLE priority
+ * class tree, bubble up budget update.
+ */
+ if (unlikely(force && entity != entity->sched_data->next_in_service)) {
+ new_next_in_service = entity;
+ for_each_entity(new_next_in_service)
+ bfq_update_budget(new_next_in_service);
+ }
+
+ 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_in_service entity at each level of the
+ * hierarchy, the complexity of the lookup can be decreased with
+ * absolutely no effort just returning the cached next_in_service 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;
+
+ /*
+ * Choose from idle class, if needed to guarantee a minimum
+ * bandwidth to this class. This should also mitigate
+ * priority-inversion problems in case a low priority task is
+ * holding file system resources.
+ */
+ if (bfqd &&
+ jiffies - bfqd->bfq_class_idle_last_service >
+ BFQ_CL_IDLE_TIMEOUT) {
+ entity = __bfq_lookup_next_entity(st + BFQ_IOPRIO_CLASSES - 1,
+ true);
+ if (entity) {
+ i = BFQ_IOPRIO_CLASSES - 1;
+ bfqd->bfq_class_idle_last_service = jiffies;
+ sd->next_in_service = entity;
+ }
+ }
+ for (; i < BFQ_IOPRIO_CLASSES; i++) {
+ entity = __bfq_lookup_next_entity(st + i, false);
+ if (entity) {
+ if (extract) {
+ bfq_check_next_in_service(sd, entity);
+ bfq_active_extract(st + i, entity);
+ sd->in_service_entity = entity;
+ sd->next_in_service = NULL;
+ }
+ break;
+ }
+ }
+
+ return entity;
+}
+
+static bool next_queue_may_preempt(struct bfq_data *bfqd)
+{
+ struct bfq_sched_data *sd = &bfqd->sched_data;
+
+ return sd->next_in_service != sd->in_service_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;
+
+ if (bfqd->busy_queues == 0)
+ return NULL;
+
+ sd = &bfqd->sched_data;
+ for (; sd ; sd = entity->my_sched_data) {
+ entity = bfq_lookup_next_entity(sd, 1, bfqd);
+ entity->service = 0;
+ }
+
+ bfqq = bfq_entity_to_bfqq(entity);
+
+ return bfqq;
+}
+
+static void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
+{
+ if (bfqd->in_service_bic) {
+ put_io_context(bfqd->in_service_bic->icq.ioc);
+ bfqd->in_service_bic = NULL;
+ }
+
+ bfq_clear_bfqq_wait_request(bfqd->in_service_queue);
+ hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
+ bfqd->in_service_queue = NULL;
+}
+
+static void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ int requeue)
+{
+ struct bfq_entity *entity = &bfqq->entity;
+
+ 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, bfq_bfqq_non_blocking_wait_rq(bfqq));
+ bfq_clear_bfqq_non_blocking_wait_rq(bfqq);
+}
+
+/*
+ * 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)
+{
+ bfq_log_bfqq(bfqd, bfqq, "del from busy");
+
+ bfq_clear_bfqq_busy(bfqq);
+
+ bfqd->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)
+{
+ bfq_log_bfqq(bfqd, bfqq, "add to busy");
+
+ bfq_activate_bfqq(bfqd, bfqq);
+
+ bfq_mark_bfqq_busy(bfqq);
+ bfqd->busy_queues++;
+}
+
+static void bfq_init_entity(struct bfq_entity *entity)
+{
+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+ entity->weight = entity->new_weight;
+ entity->orig_weight = entity->new_weight;
+
+ bfqq->ioprio = bfqq->new_ioprio;
+ bfqq->ioprio_class = bfqq->new_ioprio_class;
+
+ entity->sched_data = &bfqq->bfqd->sched_data;
+}
+
+#define bfq_class_idle(bfqq) ((bfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
+#define bfq_class_rt(bfqq) ((bfqq)->ioprio_class == IOPRIO_CLASS_RT)
+
+#define bfq_sample_valid(samples) ((samples) > 80)
+
+/*
+ * Scheduler run of queue, if there are requests pending and no one in the
+ * driver that will restart queueing.
+ */
+static void bfq_schedule_dispatch(struct bfq_data *bfqd)
+{
+ if (bfqd->queued != 0) {
+ bfq_log(bfqd, "schedule dispatch");
+ blk_mq_run_hw_queues(bfqd->queue, true);
+ }
+}
+
+/*
+ * 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 int wrap = 0; /* bit mask: requests behind the disk head? */
+
+ if (!rq1 || rq1 == rq2)
+ return rq2;
+ if (!rq2)
+ 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;
+
+ 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;
+ }
+}
+
+/*
+ * Return expired entry, or NULL to just start from scratch in rbtree.
+ */
+static struct request *bfq_check_fifo(struct bfq_queue *bfqq,
+ struct request *last)
+{
+ struct request *rq;
+
+ if (bfq_bfqq_fifo_expire(bfqq))
+ return NULL;
+
+ bfq_mark_bfqq_fifo_expire(bfqq);
+
+ rq = rq_entry_fifo(bfqq->fifo.next);
+
+ if (rq == last || ktime_get_ns() < rq->fifo_time)
+ return NULL;
+
+ bfq_log_bfqq(bfqq->bfqd, bfqq, "check_fifo: returned %p", rq);
+ return rq;
+}
+
+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, *prev = NULL;
+
+ /* Follow expired path, else get first next available. */
+ next = bfq_check_fifo(bfqq, last);
+ if (next)
+ return next;
+
+ if (rbprev)
+ prev = rb_entry_rq(rbprev);
+
+ if (rbnext)
+ 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 unsigned long bfq_serv_to_charge(struct request *rq,
+ struct bfq_queue *bfqq)
+{
+ return blk_rq_sectors(rq);
+}
+
+/**
+ * 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 request *next_rq = bfqq->next_rq;
+ unsigned long new_budget;
+
+ if (!next_rq)
+ return;
+
+ if (bfqq == bfqd->in_service_queue)
+ /*
+ * In order not to break guarantees, budgets cannot be
+ * changed after an entity has been selected.
+ */
+ return;
+
+ new_budget = max_t(unsigned long, bfqq->max_budget,
+ bfq_serv_to_charge(next_rq, bfqq));
+ if (entity->budget != new_budget) {
+ entity->budget = new_budget;
+ bfq_log_bfqq(bfqd, bfqq, "updated next rq: new budget %lu",
+ new_budget);
+ bfq_activate_bfqq(bfqd, bfqq);
+ }
+}
+
+static int bfq_bfqq_budget_left(struct bfq_queue *bfqq)
+{
+ struct bfq_entity *entity = &bfqq->entity;
+
+ return entity->budget - entity->service;
+}
+
+/*
+ * 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 int bfq_max_budget(struct bfq_data *bfqd)
+{
+ if (bfqd->budgets_assigned < bfq_stats_min_budgets)
+ 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 int bfq_min_budget(struct bfq_data *bfqd)
+{
+ if (bfqd->budgets_assigned < bfq_stats_min_budgets)
+ return bfq_default_max_budget / 32;
+ else
+ return bfqd->bfq_max_budget / 32;
+}
+
+static void bfq_bfqq_expire(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq,
+ bool compensate,
+ enum bfqq_expiration reason);
+
+/*
+ * The next function, invoked after the input queue bfqq switches from
+ * idle to busy, updates the budget of bfqq. The function also tells
+ * whether the in-service queue should be expired, by returning
+ * true. The purpose of expiring the in-service queue is to give bfqq
+ * the chance to possibly preempt the in-service queue, and the reason
+ * for preempting the in-service queue is to achieve the following
+ * goal: guarantee to bfqq its reserved bandwidth even if bfqq has
+ * expired because it has remained idle.
+ *
+ * In particular, bfqq may have expired for one of the following two
+ * reasons:
+ *
+ * - BFQ_BFQQ_NO_MORE_REQUESTS bfqq did not enjoy any device idling
+ * and did not make it to issue a new request before its last
+ * request was served;
+ *
+ * - BFQ_BFQQ_TOO_IDLE bfqq did enjoy device idling, but did not issue
+ * a new request before the expiration of the idling-time.
+ *
+ * Even if bfqq has expired for one of the above reasons, the process
+ * associated with the queue may be however issuing requests greedily,
+ * and thus be sensitive to the bandwidth it receives (bfqq may have
+ * remained idle for other reasons: CPU high load, bfqq not enjoying
+ * idling, I/O throttling somewhere in the path from the process to
+ * the I/O scheduler, ...). But if, after every expiration for one of
+ * the above two reasons, bfqq has to wait for the service of at least
+ * one full budget of another queue before being served again, then
+ * bfqq is likely to get a much lower bandwidth or resource time than
+ * its reserved ones. To address this issue, two countermeasures need
+ * to be taken.
+ *
+ * First, the budget and the timestamps of bfqq need to be updated in
+ * a special way on bfqq reactivation: they need to be updated as if
+ * bfqq did not remain idle and did not expire. In fact, if they are
+ * computed as if bfqq expired and remained idle until reactivation,
+ * then the process associated with bfqq is treated as if, instead of
+ * being greedy, it stopped issuing requests when bfqq remained idle,
+ * and restarts issuing requests only on this reactivation. In other
+ * words, the scheduler does not help the process recover the "service
+ * hole" between bfqq expiration and reactivation. As a consequence,
+ * the process receives a lower bandwidth than its reserved one. In
+ * contrast, to recover this hole, the budget must be updated as if
+ * bfqq was not expired at all before this reactivation, i.e., it must
+ * be set to the value of the remaining budget when bfqq was
+ * expired. Along the same line, timestamps need to be assigned the
+ * value they had the last time bfqq was selected for service, i.e.,
+ * before last expiration. Thus timestamps need to be back-shifted
+ * with respect to their normal computation (see [1] for more details
+ * on this tricky aspect).
+ *
+ * Secondly, to allow the process to recover the hole, the in-service
+ * queue must be expired too, to give bfqq the chance to preempt it
+ * immediately. In fact, if bfqq has to wait for a full budget of the
+ * in-service queue to be completed, then it may become impossible to
+ * let the process recover the hole, even if the back-shifted
+ * timestamps of bfqq are lower than those of the in-service queue. If
+ * this happens for most or all of the holes, then the process may not
+ * receive its reserved bandwidth. In this respect, it is worth noting
+ * that, being the service of outstanding requests unpreemptible, a
+ * little fraction of the holes may however be unrecoverable, thereby
+ * causing a little loss of bandwidth.
+ *
+ * The last important point is detecting whether bfqq does need this
+ * bandwidth recovery. In this respect, the next function deems the
+ * process associated with bfqq greedy, and thus allows it to recover
+ * the hole, if: 1) the process is waiting for the arrival of a new
+ * request (which implies that bfqq expired for one of the above two
+ * reasons), and 2) such a request has arrived soon. The first
+ * condition is controlled through the flag non_blocking_wait_rq,
+ * while the second through the flag arrived_in_time. If both
+ * conditions hold, then the function computes the budget in the
+ * above-described special way, and signals that the in-service queue
+ * should be expired. Timestamp back-shifting is done later in
+ * __bfq_activate_entity.
+ */
+static bool bfq_bfqq_update_budg_for_activation(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq,
+ bool arrived_in_time)
+{
+ struct bfq_entity *entity = &bfqq->entity;
+
+ if (bfq_bfqq_non_blocking_wait_rq(bfqq) && arrived_in_time) {
+ /*
+ * We do not clear the flag non_blocking_wait_rq here, as
+ * the latter is used in bfq_activate_bfqq to signal
+ * that timestamps need to be back-shifted (and is
+ * cleared right after).
+ */
+
+ /*
+ * In next assignment we rely on that either
+ * entity->service or entity->budget are not updated
+ * on expiration if bfqq is empty (see
+ * __bfq_bfqq_recalc_budget). Thus both quantities
+ * remain unchanged after such an expiration, and the
+ * following statement therefore assigns to
+ * entity->budget the remaining budget on such an
+ * expiration. For clarity, entity->service is not
+ * updated on expiration in any case, and, in normal
+ * operation, is reset only when bfqq is selected for
+ * service (see bfq_get_next_queue).
+ */
+ entity->budget = min_t(unsigned long,
+ bfq_bfqq_budget_left(bfqq),
+ bfqq->max_budget);
+
+ return true;
+ }
+
+ entity->budget = max_t(unsigned long, bfqq->max_budget,
+ bfq_serv_to_charge(bfqq->next_rq, bfqq));
+ bfq_clear_bfqq_non_blocking_wait_rq(bfqq);
+ return false;
+}
+
+static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq,
+ struct request *rq)
+{
+ bool bfqq_wants_to_preempt,
+ /*
+ * See the comments on
+ * bfq_bfqq_update_budg_for_activation for
+ * details on the usage of the next variable.
+ */
+ arrived_in_time = ktime_get_ns() <=
+ bfqq->ttime.last_end_request +
+ bfqd->bfq_slice_idle * 3;
+
+ /*
+ * Update budget and check whether bfqq may want to preempt
+ * the in-service queue.
+ */
+ bfqq_wants_to_preempt =
+ bfq_bfqq_update_budg_for_activation(bfqd, bfqq,
+ arrived_in_time);
+
+ if (!bfq_bfqq_IO_bound(bfqq)) {
+ if (arrived_in_time) {
+ bfqq->requests_within_timer++;
+ if (bfqq->requests_within_timer >=
+ bfqd->bfq_requests_within_timer)
+ bfq_mark_bfqq_IO_bound(bfqq);
+ } else
+ bfqq->requests_within_timer = 0;
+ }
+
+ bfq_add_bfqq_busy(bfqd, bfqq);
+
+ /*
+ * Expire in-service queue only if preemption may be needed
+ * for guarantees. In this respect, the function
+ * next_queue_may_preempt just checks a simple, necessary
+ * condition, and not a sufficient condition based on
+ * timestamps. In fact, for the latter condition to be
+ * evaluated, timestamps would need first to be updated, and
+ * this operation is quite costly (see the comments on the
+ * function bfq_bfqq_update_budg_for_activation).
+ */
+ if (bfqd->in_service_queue && bfqq_wants_to_preempt &&
+ next_queue_may_preempt(bfqd))
+ bfq_bfqq_expire(bfqd, bfqd->in_service_queue,
+ false, BFQ_BFQQ_PREEMPTED);
+}
+
+static void bfq_add_request(struct request *rq)
+{
+ struct bfq_queue *bfqq = RQ_BFQQ(rq);
+ struct bfq_data *bfqd = bfqq->bfqd;
+ struct request *next_rq, *prev;
+
+ bfq_log_bfqq(bfqd, bfqq, "add_request %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);
+ bfqq->next_rq = next_rq;
+
+ if (!bfq_bfqq_busy(bfqq)) /* switching to busy ... */
+ bfq_bfqq_handle_idle_busy_switch(bfqd, bfqq, rq);
+ else if (prev != bfqq->next_rq)
+ bfq_updated_next_req(bfqd, bfqq);
+}
+
+static struct request *bfq_find_rq_fmerge(struct bfq_data *bfqd,
+ struct bio *bio,
+ struct request_queue *q)
+{
+ struct bfq_queue *bfqq = bfqd->bio_bfqq;
+
+
+ if (bfqq)
+ return elv_rb_find(&bfqq->sort_list, bio_end_sector(bio));
+
+ return NULL;
+}
+
+#if 0 /* Still not clear if we can do without next two functions */
+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",
+ (unsigned long long)bfqd->last_position);
+}
+
+static void bfq_deactivate_request(struct request_queue *q, struct request *rq)
+{
+ struct bfq_data *bfqd = q->elevator->elevator_data;
+
+ bfqd->rq_in_driver--;
+}
+#endif
+
+static void bfq_remove_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);
+
+ if (bfqq->next_rq == rq) {
+ bfqq->next_rq = bfq_find_next_rq(bfqd, bfqq, rq);
+ bfq_updated_next_req(bfqd, bfqq);
+ }
+
+ if (rq->queuelist.prev != &rq->queuelist)
+ list_del_init(&rq->queuelist);
+ bfqq->queued[sync]--;
+ bfqd->queued--;
+ elv_rb_del(&bfqq->sort_list, rq);
+
+ elv_rqhash_del(q, rq);
+ if (q->last_merge == rq)
+ q->last_merge = NULL;
+
+ if (RB_EMPTY_ROOT(&bfqq->sort_list)) {
+ bfqq->next_rq = NULL;
+
+ if (bfq_bfqq_busy(bfqq) && bfqq != bfqd->in_service_queue) {
+ bfq_del_bfqq_busy(bfqd, bfqq, 1);
+
+ /*
+ * bfqq emptied. In normal operation, when
+ * bfqq is empty, bfqq->entity.service and
+ * bfqq->entity.budget must contain,
+ * respectively, the service received and the
+ * budget used last time bfqq emptied. These
+ * facts do not hold in this case, as at least
+ * this last removal occurred while bfqq is
+ * not in service. To avoid inconsistencies,
+ * reset both bfqq->entity.service and
+ * bfqq->entity.budget.
+ */
+ bfqq->entity.budget = bfqq->entity.service = 0;
+ }
+ }
+
+ if (rq->cmd_flags & REQ_META)
+ bfqq->meta_pending--;
+}
+
+static bool bfq_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio)
+{
+ struct request_queue *q = hctx->queue;
+ struct bfq_data *bfqd = q->elevator->elevator_data;
+ struct request *free = NULL;
+ /*
+ * bfq_bic_lookup grabs the queue_lock: invoke it now and
+ * store its return value for later use, to avoid nesting
+ * queue_lock inside the bfqd->lock. We assume that the bic
+ * returned by bfq_bic_lookup does not go away before
+ * bfqd->lock is taken.
+ */
+ struct bfq_io_cq *bic = bfq_bic_lookup(bfqd, current->io_context, q);
+ bool ret;
+
+ spin_lock_irq(&bfqd->lock);
+
+ if (bic)
+ bfqd->bio_bfqq = bic_to_bfqq(bic, op_is_sync(bio->bi_opf));
+ else
+ bfqd->bio_bfqq = NULL;
+ bfqd->bio_bic = bic;
+
+ ret = blk_mq_sched_try_merge(q, bio, &free);
+
+ if (free)
+ blk_mq_free_request(free);
+ spin_unlock_irq(&bfqd->lock);
+
+ return ret;
+}
+
+static int bfq_request_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, q);
+ if (__rq && elv_bio_merge_ok(__rq, bio)) {
+ *req = __rq;
+ return ELEVATOR_FRONT_MERGE;
+ }
+
+ return ELEVATOR_NO_MERGE;
+}
+
+static void bfq_request_merged(struct request_queue *q, struct request *req,
+ enum elv_merge type)
+{
+ if (type == ELEVATOR_FRONT_MERGE &&
+ rb_prev(&req->rb_node) &&
+ blk_rq_pos(req) <
+ blk_rq_pos(container_of(rb_prev(&req->rb_node),
+ struct request, rb_node))) {
+ struct bfq_queue *bfqq = RQ_BFQQ(req);
+ struct bfq_data *bfqd = bfqq->bfqd;
+ struct request *prev, *next_rq;
+
+ /* Reposition request in its sort_list */
+ elv_rb_del(&bfqq->sort_list, req);
+ elv_rb_add(&bfqq->sort_list, req);
+
+ spin_lock_irq(&bfqd->lock);
+ /* Choose next request to be served for bfqq */
+ prev = bfqq->next_rq;
+ next_rq = bfq_choose_req(bfqd, bfqq->next_rq, req,
+ bfqd->last_position);
+ bfqq->next_rq = next_rq;
+ /*
+ * If next_rq changes, update the queue's budget to fit
+ * the new request.
+ */
+ if (prev != bfqq->next_rq)
+ bfq_updated_next_req(bfqd, bfqq);
+ spin_unlock_irq(&bfqd->lock);
+ }
+}
+
+static void bfq_requests_merged(struct request_queue *q, struct request *rq,
+ struct request *next)
+{
+ struct bfq_queue *bfqq = RQ_BFQQ(rq), *next_bfqq = RQ_BFQQ(next);
+
+ if (!RB_EMPTY_NODE(&rq->rb_node))
+ return;
+ spin_lock_irq(&bfqq->bfqd->lock);
+
+ /*
+ * If next and rq belong to the same bfq_queue and next is older
+ * than rq, then reposition rq in the fifo (by substituting next
+ * with rq). Otherwise, if next and rq belong to different
+ * bfq_queues, never reposition rq: in fact, we would have to
+ * reposition it with respect to next's position in its own fifo,
+ * which would most certainly be too expensive with respect to
+ * the benefits.
+ */
+ if (bfqq == next_bfqq &&
+ !list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
+ next->fifo_time < rq->fifo_time) {
+ list_del_init(&rq->queuelist);
+ list_replace_init(&next->queuelist, &rq->queuelist);
+ rq->fifo_time = next->fifo_time;
+ }
+
+ if (bfqq->next_rq == next)
+ bfqq->next_rq = rq;
+
+ bfq_remove_request(q, next);
+
+ spin_unlock_irq(&bfqq->bfqd->lock);
+}
+
+static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
+ struct bio *bio)
+{
+ struct bfq_data *bfqd = q->elevator->elevator_data;
+ bool is_sync = op_is_sync(bio->bi_opf);
+ struct bfq_queue *bfqq = bfqd->bio_bfqq;
+
+ /*
+ * Disallow merge of a sync bio into an async request.
+ */
+ if (is_sync && !rq_is_sync(rq))
+ return false;
+
+ /*
+ * Lookup the bfqq that this bio will be queued with. Allow
+ * merge only if rq is queued there.
+ */
+ if (!bfqq)
+ return false;
+
+ return bfqq == RQ_BFQQ(rq);
+}
+
+static void __bfq_set_in_service_queue(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq)
+{
+ if (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 = %d",
+ 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;
+}
+
+/*
+ * bfq_default_budget - return the default budget for @bfqq on @bfqd.
+ * @bfqd: the device descriptor.
+ * @bfqq: the queue to consider.
+ *
+ * We use 3/4 of the @bfqd maximum budget as the default value
+ * for the max_budget field of the queues. This lets the feedback
+ * mechanism to start from some middle ground, then the behavior
+ * of the process will drive the heuristics towards high values, if
+ * it behaves as a greedy sequential reader, or towards small values
+ * if it shows a more intermittent behavior.
+ */
+static unsigned long bfq_default_budget(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq)
+{
+ unsigned long budget;
+
+ /*
+ * When we need an estimate of the peak rate we need to avoid
+ * to give budgets that are too short due to previous measurements.
+ * So, in the first 10 assignments use a ``safe'' budget value.
+ */
+ if (bfqd->budgets_assigned < 194 && bfqd->bfq_user_max_budget == 0)
+ budget = bfq_default_max_budget;
+ else
+ budget = bfqd->bfq_max_budget;
+
+ return budget - budget / 4;
+}
+
+static void bfq_arm_slice_timer(struct bfq_data *bfqd)
+{
+ struct bfq_queue *bfqq = bfqd->in_service_queue;
+ struct bfq_io_cq *bic;
+ u32 sl;
+
+ /* Processes have exited, don't wait. */
+ bic = bfqd->in_service_bic;
+ if (!bic || 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.
+ */
+ sl = bfqd->bfq_slice_idle;
+ /*
+ * Grant only minimum idle time if the queue is seeky.
+ */
+ if (BFQQ_SEEKY(bfqq))
+ sl = min_t(u64, sl, BFQ_MIN_TT);
+
+ bfqd->last_idling_start = ktime_get();
+ hrtimer_start(&bfqd->idle_slice_timer, ns_to_ktime(sl),
+ HRTIMER_MODE_REL);
+}
+
+/*
+ * 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 = 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 * timeout_coeff;
+
+ bfq_log_bfqq(bfqd, bfqq, "set budget_timeout %u",
+ jiffies_to_msecs(bfqd->bfq_timeout * timeout_coeff));
+}
+
+/*
+ * Remove request from internal lists.
+ */
+static void bfq_dispatch_remove(struct request_queue *q, struct request *rq)
+{
+ struct bfq_queue *bfqq = RQ_BFQQ(rq);
+
+ /*
+ * For consistency, the next instruction should have been
+ * executed after removing the request from the queue and
+ * dispatching it. We execute instead this instruction before
+ * bfq_remove_request() (and hence introduce a temporary
+ * inconsistency), for efficiency. In fact, should this
+ * dispatch occur for a non in-service bfqq, this anticipated
+ * increment prevents two counters related to bfqq->dispatched
+ * from risking to be, first, uselessly decremented, and then
+ * incremented again when the (new) value of bfqq->dispatched
+ * happens to be taken into account.
+ */
+ bfqq->dispatched++;
+
+ bfq_remove_request(q, rq);
+}
+
+static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+ __bfq_bfqd_reset_in_service(bfqd);
+
+ if (RB_EMPTY_ROOT(&bfqq->sort_list))
+ bfq_del_bfqq_busy(bfqd, bfqq, 1);
+ else
+ bfq_activate_bfqq(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 at queue expiration.
+ * 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;
+ int budget, min_budget;
+
+ budget = bfqq->max_budget;
+ min_budget = bfq_min_budget(bfqd);
+
+ bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last budg %d, budg left %d",
+ bfqq->entity.budget, bfq_bfqq_budget_left(bfqq));
+ bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last max_budg %d, min budg %d",
+ 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:
+ if (budget > min_budget + BFQ_BUDGET_STEP)
+ budget -= BFQ_BUDGET_STEP;
+ else
+ budget = min_budget;
+ break;
+ case BFQ_BFQQ_BUDGET_TIMEOUT:
+ budget = bfq_default_budget(bfqd, bfqq);
+ 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 + 8 * BFQ_BUDGET_STEP,
+ bfqd->bfq_max_budget);
+ break;
+ case BFQ_BFQQ_NO_MORE_REQUESTS:
+ /*
+ * For queues that expire for this reason, it
+ * is particularly important to keep the
+ * budget close to the actual service they
+ * need. Doing so reduces the timestamp
+ * misalignment problem described in the
+ * comments in the body of
+ * __bfq_activate_entity. In fact, suppose
+ * that a queue systematically expires for
+ * BFQ_BFQQ_NO_MORE_REQUESTS and presents a
+ * new request in time to enjoy timestamp
+ * back-shifting. The larger the budget of the
+ * queue is with respect to the service the
+ * queue actually requests in each service
+ * slot, the more times the queue can be
+ * reactivated with the same virtual finish
+ * time. It follows that, even if this finish
+ * time is pushed to the system virtual time
+ * to reduce the consequent timestamp
+ * misalignment, the queue unjustly enjoys for
+ * many re-activations a lower finish time
+ * than all newly activated queues.
+ *
+ * The service needed by bfqq is measured
+ * quite precisely by bfqq->entity.service.
+ * Since bfqq does not enjoy device idling,
+ * bfqq->entity.service is equal to the number
+ * of sectors that the process associated with
+ * bfqq requested to read/write before waiting
+ * for request completions, or blocking for
+ * other reasons.
+ */
+ budget = max_t(int, bfqq->entity.service, min_budget);
+ break;
+ default:
+ return;
+ }
+ } else
+ /*
+ * Async queues get always the maximum possible
+ * budget, as for them we do not care about latency
+ * (in addition, their ability to dispatch is limited
+ * by the charging factor).
+ */
+ budget = bfqd->bfq_max_budget;
+
+ bfqq->max_budget = budget;
+
+ if (bfqd->budgets_assigned >= bfq_stats_min_budgets &&
+ !bfqd->bfq_user_max_budget)
+ bfqq->max_budget = min(bfqq->max_budget, bfqd->bfq_max_budget);
+
+ /*
+ * If there is still backlog, then assign a new budget, making
+ * sure that it is large enough for the next request. Since
+ * the finish time of bfqq must be kept in sync with the
+ * budget, be sure to call __bfq_bfqq_expire() *after* this
+ * update.
+ *
+ * If there is no backlog, then no need to update the budget;
+ * it will be updated on the arrival of a new request.
+ */
+ next_rq = bfqq->next_rq;
+ if (next_rq)
+ bfqq->entity.budget = max_t(unsigned long, bfqq->max_budget,
+ bfq_serv_to_charge(next_rq, bfqq));
+
+ bfq_log_bfqq(bfqd, bfqq, "head sect: %u, new budget %d",
+ next_rq ? 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 transferred in timeout 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 bool bfq_update_peak_rate(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ bool compensate)
+{
+ u64 bw, usecs, expected, timeout;
+ ktime_t delta;
+ int update = 0;
+
+ if (!bfq_bfqq_sync(bfqq) || bfq_bfqq_budget_new(bfqq))
+ return false;
+
+ 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 false;
+
+ /*
+ * 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);
+
+ /*
+ * Use only long (> 20ms) intervals to filter out spikes for
+ * the peak rate estimation.
+ */
+ if (usecs > 20000) {
+ if (bw > bfqd->peak_rate) {
+ bfqd->peak_rate = bw;
+ update = 1;
+ bfq_log(bfqd, "new peak_rate=%llu", bw);
+ }
+
+ 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=%d",
+ bfqd->bfq_max_budget);
+ }
+ }
+
+ /*
+ * 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;
+}
+
+/*
+ * Return the farthest past time instant according to jiffies
+ * macros.
+ */
+static unsigned long bfq_smallest_from_now(void)
+{
+ return jiffies - MAX_JIFFY_OFFSET;
+}
+
+/**
+ * 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 with 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,
+ bool compensate,
+ enum bfqq_expiration reason)
+{
+ bool slow;
+
+ /*
+ * Update device peak rate for autotuning and check whether the
+ * process is slow (see bfq_update_peak_rate).
+ */
+ slow = bfq_update_peak_rate(bfqd, bfqq, compensate);
+
+ /*
+ * As above explained, 'punish' slow (i.e., seeky), timed-out
+ * and async queues, to favor sequential sync workloads.
+ */
+ if (slow || reason == BFQ_BFQQ_BUDGET_TIMEOUT)
+ bfq_bfqq_charge_full_budget(bfqq);
+
+ if (reason == BFQ_BFQQ_TOO_IDLE &&
+ bfqq->entity.service <= 2 * bfqq->entity.budget / 10)
+ bfq_clear_bfqq_IO_bound(bfqq);
+
+ 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);
+
+ if (!bfq_bfqq_busy(bfqq) &&
+ reason != BFQ_BFQQ_BUDGET_TIMEOUT &&
+ reason != BFQ_BFQQ_BUDGET_EXHAUSTED)
+ bfq_mark_bfqq_non_blocking_wait_rq(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 bool bfq_bfqq_budget_timeout(struct bfq_queue *bfqq)
+{
+ if (bfq_bfqq_budget_new(bfqq) ||
+ time_before(jiffies, bfqq->budget_timeout))
+ return false;
+ return true;
+}
+
+/*
+ * If we expire a queue that is actively waiting (i.e., with the
+ * device idled) for the arrival of a new request, then we may incur
+ * the timestamp misalignment problem described in the body of the
+ * function __bfq_activate_entity. 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 bool bfq_may_expire_for_budg_timeout(struct bfq_queue *bfqq)
+{
+ bfq_log_bfqq(bfqq->bfqd, bfqq,
+ "may_budget_timeout: wait_request %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 a queue that becomes empty, device idling is allowed only if
+ * this function returns true for the queue. And this function returns
+ * true only if idling is beneficial for throughput.
+ */
+static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
+{
+ struct bfq_data *bfqd = bfqq->bfqd;
+ bool idling_boosts_thr;
+
+ if (bfqd->strict_guarantees)
+ return true;
+
+ /*
+ * The value of the next variable is computed considering that
+ * idling is usually beneficial for the throughput if:
+ * (a) the device is not NCQ-capable, or
+ * (b) regardless of the presence of NCQ, the request pattern
+ * for bfqq is I/O-bound (possible throughput losses
+ * caused by granting idling to seeky queues are mitigated
+ * by the fact that, in all scenarios where boosting
+ * throughput is the best thing to do, i.e., in all
+ * symmetric scenarios, only a minimal idle time is
+ * allowed to seeky queues).
+ */
+ idling_boosts_thr = !bfqd->hw_tag || bfq_bfqq_IO_bound(bfqq);
+
+ /*
+ * We have now the components we need to compute the return
+ * value of the function, which is true only if both the
+ * following conditions hold:
+ * 1) bfqq is sync, because idling make sense only for sync queues;
+ * 2) idling boosts the throughput.
+ */
+ return bfq_bfqq_sync(bfqq) && idling_boosts_thr;
+}
+
+/*
+ * If the in-service queue is empty but the function bfq_bfqq_may_idle
+ * returns true, then:
+ * 1) the queue must remain in service and cannot be expired, and
+ * 2) the device must be idled to wait for the possible arrival of a new
+ * request for the queue.
+ * See the comments on the function bfq_bfqq_may_idle for the reasons
+ * why performing device idling is the best choice to boost the throughput
+ * and preserve service guarantees when bfq_bfqq_may_idle itself
+ * returns true.
+ */
+static 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_may_idle(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;
+ struct request *next_rq;
+ enum bfqq_expiration reason = BFQ_BFQQ_BUDGET_TIMEOUT;
+
+ bfqq = bfqd->in_service_queue;
+ if (!bfqq)
+ goto new_queue;
+
+ bfq_log_bfqq(bfqd, bfqq, "select_queue: already in-service queue");
+
+ if (bfq_may_expire_for_budg_timeout(bfqq) &&
+ !bfq_bfqq_wait_request(bfqq) &&
+ !bfq_bfqq_must_idle(bfqq))
+ goto expire;
+
+check_queue:
+ /*
+ * This loop is rarely executed more than once. Even when it
+ * happens, it is much more convenient to re-execute this loop
+ * than to return NULL and trigger a new dispatch to get a
+ * request served.
+ */
+ 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) {
+ if (bfq_serv_to_charge(next_rq, bfqq) >
+ bfq_bfqq_budget_left(bfqq)) {
+ /*
+ * Expire the queue for budget exhaustion,
+ * which makes sure that the next budget is
+ * enough to serve the next request, even if
+ * it comes from the fifo expired path.
+ */
+ 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 (bfq_bfqq_wait_request(bfqq)) {
+ /*
+ * 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);
+ hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
+ }
+ goto keep_queue;
+ }
+ }
+
+ /*
+ * No requests pending. However, if the in-service queue is idling
+ * for a new request, or has requests waiting for a completion and
+ * may idle after their completion, then keep it anyway.
+ */
+ if (bfq_bfqq_wait_request(bfqq) ||
+ (bfqq->dispatched != 0 && bfq_bfqq_may_idle(bfqq))) {
+ bfqq = NULL;
+ goto keep_queue;
+ }
+
+ reason = BFQ_BFQQ_NO_MORE_REQUESTS;
+expire:
+ bfq_bfqq_expire(bfqd, bfqq, false, reason);
+new_queue:
+ bfqq = bfq_set_in_service_queue(bfqd);
+ if (bfqq) {
+ bfq_log_bfqq(bfqd, bfqq, "select_queue: checking new queue");
+ goto check_queue;
+ }
+keep_queue:
+ if (bfqq)
+ bfq_log_bfqq(bfqd, bfqq, "select_queue: returned this queue");
+ else
+ bfq_log(bfqd, "select_queue: no queue returned");
+
+ return bfqq;
+}
+
+/*
+ * Dispatch next request from bfqq.
+ */
+static struct request *bfq_dispatch_rq_from_bfqq(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq)
+{
+ struct request *rq = bfqq->next_rq;
+ unsigned long service_to_charge;
+
+ service_to_charge = bfq_serv_to_charge(rq, bfqq);
+
+ bfq_bfqq_served(bfqq, service_to_charge);
+
+ bfq_dispatch_remove(bfqd->queue, rq);
+
+ if (!bfqd->in_service_bic) {
+ atomic_long_inc(&RQ_BIC(rq)->icq.ioc->refcount);
+ bfqd->in_service_bic = RQ_BIC(rq);
+ }
+
+ /*
+ * Expire bfqq, pretending that its budget expired, if bfqq
+ * belongs to CLASS_IDLE and other queues are waiting for
+ * service.
+ */
+ if (bfqd->busy_queues > 1 && bfq_class_idle(bfqq))
+ goto expire;
+
+ return rq;
+
+expire:
+ bfq_bfqq_expire(bfqd, bfqq, false, BFQ_BFQQ_BUDGET_EXHAUSTED);
+ return rq;
+}
+
+static bool bfq_has_work(struct blk_mq_hw_ctx *hctx)
+{
+ struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
+
+ /*
+ * Avoiding lock: a race on bfqd->busy_queues should cause at
+ * most a call to dispatch for nothing
+ */
+ return !list_empty_careful(&bfqd->dispatch) ||
+ bfqd->busy_queues > 0;
+}
+
+static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
+{
+ struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
+ struct request *rq = NULL;
+ struct bfq_queue *bfqq = NULL;
+
+ if (!list_empty(&bfqd->dispatch)) {
+ rq = list_first_entry(&bfqd->dispatch, struct request,
+ queuelist);
+ list_del_init(&rq->queuelist);
+
+ bfqq = RQ_BFQQ(rq);
+
+ if (bfqq) {
+ /*
+ * Increment counters here, because this
+ * dispatch does not follow the standard
+ * dispatch flow (where counters are
+ * incremented)
+ */
+ bfqq->dispatched++;
+
+ goto inc_in_driver_start_rq;
+ }
+
+ /*
+ * We exploit the put_rq_private hook to decrement
+ * rq_in_driver, but put_rq_private will not be
+ * invoked on this request. So, to avoid unbalance,
+ * just start this request, without incrementing
+ * rq_in_driver. As a negative consequence,
+ * rq_in_driver is deceptively lower than it should be
+ * while this request is in service. This may cause
+ * bfq_schedule_dispatch to be invoked uselessly.
+ *
+ * As for implementing an exact solution, the
+ * put_request hook, if defined, is probably invoked
+ * also on this request. So, by exploiting this hook,
+ * we could 1) increment rq_in_driver here, and 2)
+ * decrement it in put_request. Such a solution would
+ * let the value of the counter be always accurate,
+ * but it would entail using an extra interface
+ * function. This cost seems higher than the benefit,
+ * being the frequency of non-elevator-private
+ * requests very low.
+ */
+ goto start_rq;
+ }
+
+ bfq_log(bfqd, "dispatch requests: %d busy queues", bfqd->busy_queues);
+
+ if (bfqd->busy_queues == 0)
+ goto exit;
+
+ /*
+ * Force device to serve one request at a time if
+ * strict_guarantees is true. Forcing this service scheme is
+ * currently the ONLY way to guarantee that the request
+ * service order enforced by the scheduler is respected by a
+ * queueing device. Otherwise the device is free even to make
+ * some unlucky request wait for as long as the device
+ * wishes.
+ *
+ * Of course, serving one request at at time may cause loss of
+ * throughput.
+ */
+ if (bfqd->strict_guarantees && bfqd->rq_in_driver > 0)
+ goto exit;
+
+ bfqq = bfq_select_queue(bfqd);
+ if (!bfqq)
+ goto exit;
+
+ rq = bfq_dispatch_rq_from_bfqq(bfqd, bfqq);
+
+ if (rq) {
+inc_in_driver_start_rq:
+ bfqd->rq_in_driver++;
+start_rq:
+ rq->rq_flags |= RQF_STARTED;
+ }
+exit:
+ return rq;
+}
+
+static struct request *bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
+{
+ struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
+ struct request *rq;
+
+ spin_lock_irq(&bfqd->lock);
+ rq = __bfq_dispatch_request(hctx);
+ spin_unlock_irq(&bfqd->lock);
+
+ return rq;
+}
+
+/*
+ * 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.
+ *
+ * Scheduler lock must be held here.
+ */
+static void bfq_put_queue(struct bfq_queue *bfqq)
+{
+ if (bfqq->bfqd)
+ bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p %d",
+ bfqq, bfqq->ref);
+
+ bfqq->ref--;
+ if (bfqq->ref)
+ return;
+
+ kmem_cache_free(bfq_pool, bfqq);
+}
+
+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, bfqq->ref);
+
+ bfq_put_queue(bfqq);
+}
+
+static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync)
+{
+ struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync);
+ struct bfq_data *bfqd;
+
+ if (bfqq)
+ bfqd = bfqq->bfqd; /* NULL if scheduler already exited */
+
+ if (bfqq && bfqd) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&bfqd->lock, flags);
+ bfq_exit_bfqq(bfqd, bfqq);
+ bic_set_bfqq(bic, NULL, is_sync);
+ spin_unlock_irq(&bfqd->lock);
+ }
+}
+
+static void bfq_exit_icq(struct io_cq *icq)
+{
+ struct bfq_io_cq *bic = icq_to_bic(icq);
+
+ bfq_exit_icq_bfqq(bic, true);
+ bfq_exit_icq_bfqq(bic, false);
+}
+
+/*
+ * Update the entity prio values; note that the new values will not
+ * be used until the next (re)activation.
+ */
+static void
+bfq_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
+{
+ struct task_struct *tsk = current;
+ int ioprio_class;
+ struct bfq_data *bfqd = bfqq->bfqd;
+
+ if (!bfqd)
+ return;
+
+ ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio);
+ switch (ioprio_class) {
+ default:
+ dev_err(bfqq->bfqd->queue->backing_dev_info->dev,
+ "bfq: bad prio class %d\n", ioprio_class);
+ case IOPRIO_CLASS_NONE:
+ /*
+ * No prio set, inherit CPU scheduling settings.
+ */
+ bfqq->new_ioprio = task_nice_ioprio(tsk);
+ bfqq->new_ioprio_class = task_nice_ioclass(tsk);
+ break;
+ case IOPRIO_CLASS_RT:
+ bfqq->new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
+ bfqq->new_ioprio_class = IOPRIO_CLASS_RT;
+ break;
+ case IOPRIO_CLASS_BE:
+ bfqq->new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
+ bfqq->new_ioprio_class = IOPRIO_CLASS_BE;
+ break;
+ case IOPRIO_CLASS_IDLE:
+ bfqq->new_ioprio_class = IOPRIO_CLASS_IDLE;
+ bfqq->new_ioprio = 7;
+ bfq_clear_bfqq_idle_window(bfqq);
+ break;
+ }
+
+ if (bfqq->new_ioprio >= IOPRIO_BE_NR) {
+ pr_crit("bfq_set_next_ioprio_data: new_ioprio %d\n",
+ bfqq->new_ioprio);
+ bfqq->new_ioprio = IOPRIO_BE_NR;
+ }
+
+ bfqq->entity.new_weight = bfq_ioprio_to_weight(bfqq->new_ioprio);
+ bfqq->entity.prio_changed = 1;
+}
+
+static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio)
+{
+ struct bfq_data *bfqd = bic_to_bfqd(bic);
+ struct bfq_queue *bfqq;
+ int ioprio = bic->icq.ioc->ioprio;
+
+ /*
+ * This condition may trigger on a newly created bic, be sure to
+ * drop the lock before returning.
+ */
+ if (unlikely(!bfqd) || likely(bic->ioprio == ioprio))
+ return;
+
+ bic->ioprio = ioprio;
+
+ bfqq = bic_to_bfqq(bic, false);
+ if (bfqq) {
+ bfq_put_queue(bfqq);
+ bfqq = bfq_get_queue(bfqd, bio, BLK_RW_ASYNC, bic);
+ bic_set_bfqq(bic, bfqq, false);
+ }
+
+ bfqq = bic_to_bfqq(bic, true);
+ if (bfqq)
+ bfq_set_next_ioprio_data(bfqq, bic);
+}
+
+static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ struct bfq_io_cq *bic, pid_t pid, int is_sync)
+{
+ RB_CLEAR_NODE(&bfqq->entity.rb_node);
+ INIT_LIST_HEAD(&bfqq->fifo);
+
+ bfqq->ref = 0;
+ bfqq->bfqd = bfqd;
+
+ if (bic)
+ bfq_set_next_ioprio_data(bfqq, bic);
+
+ if (is_sync) {
+ if (!bfq_class_idle(bfqq))
+ bfq_mark_bfqq_idle_window(bfqq);
+ bfq_mark_bfqq_sync(bfqq);
+ } else
+ bfq_clear_bfqq_sync(bfqq);
+
+ bfqq->ttime.last_end_request = ktime_get_ns() - (1ULL<<32);
+
+ bfq_mark_bfqq_IO_bound(bfqq);
+
+ bfqq->pid = pid;
+
+ /* Tentative initial value to trade off between thr and lat */
+ bfqq->max_budget = bfq_default_budget(bfqd, bfqq);
+ bfqq->budget_timeout = bfq_smallest_from_now();
+ bfqq->pid = pid;
+
+ /* first request is almost certainly seeky */
+ bfqq->seek_history = 1;
+}
+
+static struct bfq_queue **bfq_async_queue_prio(struct bfq_data *bfqd,
+ int ioprio_class, int ioprio)
+{
+ switch (ioprio_class) {
+ case IOPRIO_CLASS_RT:
+ return &async_bfqq[0][ioprio];
+ case IOPRIO_CLASS_NONE:
+ ioprio = IOPRIO_NORM;
+ /* fall through */
+ case IOPRIO_CLASS_BE:
+ return &async_bfqq[1][ioprio];
+ case IOPRIO_CLASS_IDLE:
+ return &async_idle_bfqq;
+ default:
+ return NULL;
+ }
+}
+
+static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
+ struct bio *bio, bool is_sync,
+ struct bfq_io_cq *bic)
+{
+ 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;
+
+ rcu_read_lock();
+
+ if (!is_sync) {
+ async_bfqq = bfq_async_queue_prio(bfqd, ioprio_class,
+ ioprio);
+ bfqq = *async_bfqq;
+ if (bfqq)
+ goto out;
+ }
+
+ bfqq = kmem_cache_alloc_node(bfq_pool,
+ GFP_NOWAIT | __GFP_ZERO | __GFP_NOWARN,
+ bfqd->queue->node);
+
+ if (bfqq) {
+ bfq_init_bfqq(bfqd, bfqq, bic, current->pid,
+ is_sync);
+ bfq_init_entity(&bfqq->entity);
+ bfq_log_bfqq(bfqd, bfqq, "allocated");
+ } else {
+ bfqq = &bfqd->oom_bfqq;
+ bfq_log_bfqq(bfqd, bfqq, "using oom bfqq");
+ goto out;
+ }
+
+ /*
+ * Pin the queue now that it's allocated, scheduler exit will
+ * prune it.
+ */
+ if (async_bfqq) {
+ bfqq->ref++;
+ bfq_log_bfqq(bfqd, bfqq,
+ "get_queue, bfqq not in async: %p, %d",
+ bfqq, bfqq->ref);
+ *async_bfqq = bfqq;
+ }
+
+out:
+ bfqq->ref++;
+ bfq_log_bfqq(bfqd, bfqq, "get_queue, at end: %p, %d", bfqq, bfqq->ref);
+ rcu_read_unlock();
+ return bfqq;
+}
+
+static void bfq_update_io_thinktime(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq)
+{
+ struct bfq_ttime *ttime = &bfqq->ttime;
+ u64 elapsed = ktime_get_ns() - bfqq->ttime.last_end_request;
+
+ elapsed = min_t(u64, elapsed, 2ULL * bfqd->bfq_slice_idle);
+
+ ttime->ttime_samples = (7*bfqq->ttime.ttime_samples + 256) / 8;
+ ttime->ttime_total = div_u64(7*ttime->ttime_total + 256*elapsed, 8);
+ ttime->ttime_mean = div64_ul(ttime->ttime_total + 128,
+ ttime->ttime_samples);
+}
+
+static void
+bfq_update_io_seektime(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ struct request *rq)
+{
+ sector_t sdist = 0;
+
+ if (bfqq->last_request_pos) {
+ 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);
+ }
+
+ bfqq->seek_history <<= 1;
+ bfqq->seek_history |= sdist > BFQQ_SEEK_THR &&
+ (!blk_queue_nonrot(bfqd->queue) ||
+ blk_rq_sectors(rq) < BFQQ_SECT_THR_NONROT);
+}
+
+/*
+ * 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)))
+ enable_idle = 0;
+ else if (bfq_sample_valid(bfqq->ttime.ttime_samples)) {
+ if (bfqq->ttime.ttime_mean > bfqd->bfq_slice_idle)
+ 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, bfqq);
+ 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)",
+ bfq_bfqq_idle_window(bfqq), BFQQ_SEEKY(bfqq));
+
+ bfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);
+
+ if (bfqq == bfqd->in_service_queue && bfq_bfqq_wait_request(bfqq)) {
+ bool small_req = bfqq->queued[rq_is_sync(rq)] == 1 &&
+ blk_rq_sectors(rq) < 32;
+ bool 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 device is being idled to wait
+ * for a new request from the in-service queue, we
+ * avoid unplugging the device and committing the
+ * device 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);
+ hrtimer_try_to_cancel(&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, false,
+ BFQ_BFQQ_BUDGET_TIMEOUT);
+ }
+}
+
+static void __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
+{
+ struct bfq_queue *bfqq = RQ_BFQQ(rq);
+
+ bfq_add_request(rq);
+
+ rq->fifo_time = ktime_get_ns() + bfqd->bfq_fifo_expire[rq_is_sync(rq)];
+ list_add_tail(&rq->queuelist, &bfqq->fifo);
+
+ bfq_rq_enqueued(bfqd, bfqq, rq);
+}
+
+static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
+ bool at_head)
+{
+ struct request_queue *q = hctx->queue;
+ struct bfq_data *bfqd = q->elevator->elevator_data;
+
+ spin_lock_irq(&bfqd->lock);
+ if (blk_mq_sched_try_insert_merge(q, rq)) {
+ spin_unlock_irq(&bfqd->lock);
+ return;
+ }
+
+ spin_unlock_irq(&bfqd->lock);
+
+ blk_mq_sched_request_inserted(rq);
+
+ spin_lock_irq(&bfqd->lock);
+ if (at_head || blk_rq_is_passthrough(rq)) {
+ if (at_head)
+ list_add(&rq->queuelist, &bfqd->dispatch);
+ else
+ list_add_tail(&rq->queuelist, &bfqd->dispatch);
+ } else {
+ __bfq_insert_request(bfqd, rq);
+
+ if (rq_mergeable(rq)) {
+ elv_rqhash_add(q, rq);
+ if (!q->last_merge)
+ q->last_merge = rq;
+ }
+ }
+
+ spin_unlock_irq(&bfqd->lock);
+}
+
+static void bfq_insert_requests(struct blk_mq_hw_ctx *hctx,
+ struct list_head *list, bool at_head)
+{
+ while (!list_empty(list)) {
+ struct request *rq;
+
+ rq = list_first_entry(list, struct request, queuelist);
+ list_del_init(&rq->queuelist);
+ bfq_insert_request(hctx, rq, at_head);
+ }
+}
+
+static void bfq_update_hw_tag(struct bfq_data *bfqd)
+{
+ bfqd->max_rq_in_driver = max_t(int, 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 bfq_queue *bfqq, struct bfq_data *bfqd)
+{
+ bfq_update_hw_tag(bfqd);
+
+ bfqd->rq_in_driver--;
+ bfqq->dispatched--;
+
+ bfqq->ttime.last_end_request = ktime_get_ns();
+
+ /*
+ * 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);
+ return;
+ } else if (bfq_may_expire_for_budg_timeout(bfqq))
+ bfq_bfqq_expire(bfqd, bfqq, false,
+ BFQ_BFQQ_BUDGET_TIMEOUT);
+ else if (RB_EMPTY_ROOT(&bfqq->sort_list) &&
+ (bfqq->dispatched == 0 ||
+ !bfq_bfqq_may_idle(bfqq)))
+ bfq_bfqq_expire(bfqd, bfqq, false,
+ BFQ_BFQQ_NO_MORE_REQUESTS);
+ }
+}
+
+static void bfq_put_rq_priv_body(struct bfq_queue *bfqq)
+{
+ bfqq->allocated--;
+
+ bfq_put_queue(bfqq);
+}
+
+static void bfq_put_rq_private(struct request_queue *q, struct request *rq)
+{
+ struct bfq_queue *bfqq = RQ_BFQQ(rq);
+ struct bfq_data *bfqd = bfqq->bfqd;
+
+
+ if (likely(rq->rq_flags & RQF_STARTED)) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&bfqd->lock, flags);
+
+ bfq_completed_request(bfqq, bfqd);
+ bfq_put_rq_priv_body(bfqq);
+
+ spin_unlock_irqrestore(&bfqd->lock, flags);
+ } else {
+ /*
+ * Request rq may be still/already in the scheduler,
+ * in which case we need to remove it. And we cannot
+ * defer such a check and removal, to avoid
+ * inconsistencies in the time interval from the end
+ * of this function to the start of the deferred work.
+ * This situation seems to occur only in process
+ * context, as a consequence of a merge. In the
+ * current version of the code, this implies that the
+ * lock is held.
+ */
+
+ if (!RB_EMPTY_NODE(&rq->rb_node))
+ bfq_remove_request(q, rq);
+ bfq_put_rq_priv_body(bfqq);
+ }
+
+ rq->elv.priv[0] = NULL;
+ rq->elv.priv[1] = NULL;
+}
+
+/*
+ * Allocate bfq data structures associated with this request.
+ */
+static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
+ struct bio *bio)
+{
+ struct bfq_data *bfqd = q->elevator->elevator_data;
+ struct bfq_io_cq *bic = icq_to_bic(rq->elv.icq);
+ const int is_sync = rq_is_sync(rq);
+ struct bfq_queue *bfqq;
+
+ spin_lock_irq(&bfqd->lock);
+
+ bfq_check_ioprio_change(bic, bio);
+
+ if (!bic)
+ goto queue_fail;
+
+ bfqq = bic_to_bfqq(bic, is_sync);
+ if (!bfqq || bfqq == &bfqd->oom_bfqq) {
+ if (bfqq)
+ bfq_put_queue(bfqq);
+ bfqq = bfq_get_queue(bfqd, bio, is_sync, bic);
+ bic_set_bfqq(bic, bfqq, is_sync);
+ }
+
+ bfqq->allocated++;
+ bfqq->ref++;
+ bfq_log_bfqq(bfqd, bfqq, "get_request %p: bfqq %p, %d",
+ rq, bfqq, bfqq->ref);
+
+ rq->elv.priv[0] = bic;
+ rq->elv.priv[1] = bfqq;
+
+ spin_unlock_irq(&bfqd->lock);
+
+ return 0;
+
+queue_fail:
+ spin_unlock_irq(&bfqd->lock);
+
+ return 1;
+}
+
+static void bfq_idle_slice_timer_body(struct bfq_queue *bfqq)
+{
+ struct bfq_data *bfqd = bfqq->bfqd;
+ enum bfqq_expiration reason;
+ unsigned long flags;
+
+ spin_lock_irqsave(&bfqd->lock, flags);
+ bfq_clear_bfqq_wait_request(bfqq);
+
+ if (bfqq != bfqd->in_service_queue) {
+ spin_unlock_irqrestore(&bfqd->lock, flags);
+ return;
+ }
+
+ 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, true, reason);
+
+schedule_dispatch:
+ spin_unlock_irqrestore(&bfqd->lock, flags);
+ bfq_schedule_dispatch(bfqd);
+}
+
+/*
+ * Handler of the expiration of the timer running if the in-service queue
+ * is idling inside its time slice.
+ */
+static enum hrtimer_restart bfq_idle_slice_timer(struct hrtimer *timer)
+{
+ struct bfq_data *bfqd = container_of(timer, struct bfq_data,
+ idle_slice_timer);
+ struct bfq_queue *bfqq = bfqd->in_service_queue;
+
+ /*
+ * Theoretical race here: the in-service queue can be NULL or
+ * different from the queue that was idling if 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)
+ bfq_idle_slice_timer_body(bfqq);
+
+ return HRTIMER_NORESTART;
+}
+
+static void __bfq_put_async_bfqq(struct bfq_data *bfqd,
+ struct bfq_queue **bfqq_ptr)
+{
+ struct bfq_queue *bfqq = *bfqq_ptr;
+
+ bfq_log(bfqd, "put_async_bfqq: %p", bfqq);
+ if (bfqq) {
+ bfq_log_bfqq(bfqd, bfqq, "put_async_bfqq: putting %p, %d",
+ bfqq, bfqq->ref);
+ bfq_put_queue(bfqq);
+ *bfqq_ptr = NULL;
+ }
+}
+
+/*
+ * Release the extra reference of the async queues as the device
+ * goes away.
+ */
+static void bfq_put_async_queues(struct bfq_data *bfqd)
+{
+ int i, j;
+
+ for (i = 0; i < 2; i++)
+ for (j = 0; j < IOPRIO_BE_NR; j++)
+ __bfq_put_async_bfqq(bfqd, &async_bfqq[i][j]);
+
+ __bfq_put_async_bfqq(bfqd, &async_idle_bfqq);
+}
+
+static void bfq_exit_queue(struct elevator_queue *e)
+{
+ struct bfq_data *bfqd = e->elevator_data;
+ struct bfq_queue *bfqq, *n;
+
+ hrtimer_cancel(&bfqd->idle_slice_timer);
+
+ spin_lock_irq(&bfqd->lock);
+ list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list)
+ bfq_deactivate_bfqq(bfqd, bfqq, false);
+ bfq_put_async_queues(bfqd);
+ spin_unlock_irq(&bfqd->lock);
+
+ hrtimer_cancel(&bfqd->idle_slice_timer);
+
+ kfree(bfqd);
+}
+
+static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
+{
+ struct bfq_data *bfqd;
+ struct elevator_queue *eq;
+ int i;
+
+ eq = elevator_alloc(q, e);
+ if (!eq)
+ return -ENOMEM;
+
+ bfqd = kzalloc_node(sizeof(*bfqd), GFP_KERNEL, q->node);
+ if (!bfqd) {
+ kobject_put(&eq->kobj);
+ return -ENOMEM;
+ }
+ eq->elevator_data = bfqd;
+
+ /*
+ * 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, NULL, 1, 0);
+ bfqd->oom_bfqq.ref++;
+ bfqd->oom_bfqq.new_ioprio = BFQ_DEFAULT_QUEUE_IOPRIO;
+ bfqd->oom_bfqq.new_ioprio_class = IOPRIO_CLASS_BE;
+ bfqd->oom_bfqq.entity.new_weight =
+ bfq_ioprio_to_weight(bfqd->oom_bfqq.new_ioprio);
+ /*
+ * Trigger weight initialization, according to ioprio, at the
+ * oom_bfqq's first activation. The oom_bfqq's ioprio and ioprio
+ * class won't be changed any more.
+ */
+ bfqd->oom_bfqq.entity.prio_changed = 1;
+
+ bfqd->queue = q;
+
+ for (i = 0; i < BFQ_IOPRIO_CLASSES; i++)
+ bfqd->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT;
+
+ hrtimer_init(&bfqd->idle_slice_timer, CLOCK_MONOTONIC,
+ HRTIMER_MODE_REL);
+ bfqd->idle_slice_timer.function = bfq_idle_slice_timer;
+
+ 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_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_timeout = bfq_timeout;
+
+ bfqd->bfq_requests_within_timer = 120;
+
+ spin_lock_init(&bfqd->lock);
+ INIT_LIST_HEAD(&bfqd->dispatch);
+
+ q->elevator = eq;
+
+ return 0;
+}
+
+static void bfq_slab_kill(void)
+{
+ kmem_cache_destroy(bfq_pool);
+}
+
+static int __init bfq_slab_setup(void)
+{
+ bfq_pool = KMEM_CACHE(bfq_queue, 0);
+ if (!bfq_pool)
+ return -ENOMEM;
+ return 0;
+}
+
+static ssize_t bfq_var_show(unsigned int var, char *page)
+{
+ return sprintf(page, "%u\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_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->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\n",
+ bfqq->pid,
+ bfqq->entity.weight,
+ bfqq->queued[0],
+ bfqq->queued[1]);
+ }
+
+ 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\n",
+ bfqq->pid,
+ bfqq->entity.weight);
+ }
+
+ spin_unlock_irq(&bfqd->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; \
+ u64 __data = __VAR; \
+ if (__CONV == 1) \
+ __data = jiffies_to_msecs(__data); \
+ else if (__CONV == 2) \
+ __data = div_u64(__data, NSEC_PER_MSEC); \
+ return bfq_var_show(__data, (page)); \
+}
+SHOW_FUNCTION(bfq_fifo_expire_sync_show, bfqd->bfq_fifo_expire[1], 2);
+SHOW_FUNCTION(bfq_fifo_expire_async_show, bfqd->bfq_fifo_expire[0], 2);
+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, 2);
+SHOW_FUNCTION(bfq_max_budget_show, bfqd->bfq_user_max_budget, 0);
+SHOW_FUNCTION(bfq_timeout_sync_show, bfqd->bfq_timeout, 1);
+SHOW_FUNCTION(bfq_strict_guarantees_show, bfqd->strict_guarantees, 0);
+#undef SHOW_FUNCTION
+
+#define USEC_SHOW_FUNCTION(__FUNC, __VAR) \
+static ssize_t __FUNC(struct elevator_queue *e, char *page) \
+{ \
+ struct bfq_data *bfqd = e->elevator_data; \
+ u64 __data = __VAR; \
+ __data = div_u64(__data, NSEC_PER_USEC); \
+ return bfq_var_show(__data, (page)); \
+}
+USEC_SHOW_FUNCTION(bfq_slice_idle_us_show, bfqd->bfq_slice_idle);
+#undef USEC_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 == 1) \
+ *(__PTR) = msecs_to_jiffies(__data); \
+ else if (__CONV == 2) \
+ *(__PTR) = (u64)__data * NSEC_PER_MSEC; \
+ else \
+ *(__PTR) = __data; \
+ return ret; \
+}
+STORE_FUNCTION(bfq_fifo_expire_sync_store, &bfqd->bfq_fifo_expire[1], 1,
+ INT_MAX, 2);
+STORE_FUNCTION(bfq_fifo_expire_async_store, &bfqd->bfq_fifo_expire[0], 1,
+ INT_MAX, 2);
+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, 2);
+#undef STORE_FUNCTION
+
+#define USEC_STORE_FUNCTION(__FUNC, __PTR, MIN, MAX) \
+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); \
+ *(__PTR) = (u64)__data * NSEC_PER_USEC; \
+ return ret; \
+}
+USEC_STORE_FUNCTION(bfq_slice_idle_us_store, &bfqd->bfq_slice_idle, 0,
+ UINT_MAX);
+#undef USEC_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 unsigned long bfq_estimated_max_budget(struct bfq_data *bfqd)
+{
+ u64 timeout = jiffies_to_msecs(bfqd->bfq_timeout);
+
+ 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;
+}
+
+/*
+ * Leaving this name to preserve name compatibility with cfq
+ * parameters, but this timeout is used for both sync and async.
+ */
+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 = 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_strict_guarantees_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 (!bfqd->strict_guarantees && __data == 1
+ && bfqd->bfq_slice_idle < 8 * NSEC_PER_MSEC)
+ bfqd->bfq_slice_idle = 8 * NSEC_PER_MSEC;
+
+ bfqd->strict_guarantees = __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(fifo_expire_sync),
+ BFQ_ATTR(fifo_expire_async),
+ BFQ_ATTR(back_seek_max),
+ BFQ_ATTR(back_seek_penalty),
+ BFQ_ATTR(slice_idle),
+ BFQ_ATTR(slice_idle_us),
+ BFQ_ATTR(max_budget),
+ BFQ_ATTR(timeout_sync),
+ BFQ_ATTR(strict_guarantees),
+ BFQ_ATTR(weights),
+ __ATTR_NULL
+};
+
+static struct elevator_type iosched_bfq_mq = {
+ .ops.mq = {
+ .get_rq_priv = bfq_get_rq_private,
+ .put_rq_priv = bfq_put_rq_private,
+ .exit_icq = bfq_exit_icq,
+ .insert_requests = bfq_insert_requests,
+ .dispatch_request = bfq_dispatch_request,
+ .next_request = elv_rb_latter_request,
+ .former_request = elv_rb_former_request,
+ .allow_merge = bfq_allow_bio_merge,
+ .bio_merge = bfq_bio_merge,
+ .request_merge = bfq_request_merge,
+ .requests_merged = bfq_requests_merged,
+ .request_merged = bfq_request_merged,
+ .has_work = bfq_has_work,
+ .init_sched = bfq_init_queue,
+ .exit_sched = bfq_exit_queue,
+ },
+
+ .uses_mq = true,
+ .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)
+{
+ int ret;
+ char msg[50] = "BFQ I/O-scheduler: v0";
+
+ ret = -ENOMEM;
+ if (bfq_slab_setup())
+ goto err_pol_unreg;
+
+ ret = elv_register(&iosched_bfq_mq);
+ if (ret)
+ goto err_pol_unreg;
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ strcat(msg, " (with cgroups support)");
+#endif
+ pr_info("%s", msg);
+
+ return 0;
+
+err_pol_unreg:
+ return ret;
+}
+
+static void __exit bfq_exit(void)
+{
+ elv_unregister(&iosched_bfq_mq);
+ bfq_slab_kill();
+}
+
+module_init(bfq_init);
+module_exit(bfq_exit);
+
+MODULE_AUTHOR("Paolo Valente");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("MQ Budget Fair Queueing I/O Scheduler");
diff --git a/block/elevator.c b/block/elevator.c
index 01139f5..786fdcd 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -221,14 +221,20 @@ int elevator_init(struct request_queue *q, char *name)
if (!e) {
/*
- * For blk-mq devices, we default to using mq-deadline,
- * if available, for single queue devices. If deadline
- * isn't available OR we have multiple queues, default
- * to "none".
+ * For blk-mq devices, we default to using bfq, if
+ * available, for single queue devices. If bfq isn't
+ * available, we try mq-deadline. If neither is
+ * available, OR we have multiple queues, default to
+ * "none".
*/
if (q->mq_ops) {
+ if (q->nr_hw_queues == 1) {
+ e = elevator_get("bfq", false);
+ if (!e)
+ e = elevator_get("mq-deadline", false);
+ }
if (q->nr_hw_queues == 1)
- e = elevator_get("mq-deadline", false);
+ e = elevator_get("bfq", false);
if (!e)
return 0;
} else
--
2.10.0
^ permalink raw reply related
* [PATCH RFC 00/14] Add the BFQ I/O Scheduler to blk-mq
From: Paolo Valente @ 2017-03-04 16:01 UTC (permalink / raw)
To: Jens Axboe, Tejun Heo
Cc: Fabio Checconi, Arianna Avanzini, linux-block, linux-kernel,
ulf.hansson, linus.walleij, broonie, Paolo Valente
Hi,
at last, here is my first patch series meant for merging. It adds BFQ
to blk-mq. Don't worry, in this message I won't bore you again with
the wonderful properties of BFQ :)
A quick update on the status of the code: thanks to Murphy's laws, in
the last handful of days,
1) A kind of rare failure, reported only once by a user, several
months ago, has been reported again. Fortunately, the bug reporter
provided an oops this time.
2) An unexpected bandwidth unbalance between greedy reads and writes
has been noted.
I have chosen however to submit these patches before attacking these
new problems.
Let me also recall the limitations of the current version of BFQ. On
average CPUs, it can handle, without loss of throughput or fairness
guarantees, devices performing at most ~30K IOPS; at most ~50 KIOPS on
faster CPUs. Just to put this into context, these are about the same
limits as CFQ in blk. A second intrinsic problem is the current need
for device idling when differentiated bandwidth distribution must be
guaranteed. Over the last months, I have seen that, fortunately,
there is room for significant improvements with both these
limitations. I plan to work on these improvements after we are done
(and if everything goes well) with merging BFQ.
Finally, a few details on the patchset.
The first two patches introduce BFQ-v0, which is more or less the
first version of BFQ submitted a few years ago [1]. The remaining
patches turn progressively BFQ-v0 into BFQ-v8r8, the current version
of BFQ.
Some patch generates WARNINGS with checkpatch.pl, but these WARNINGS
seem to be either unavoidable for the involved pieces of code (which
the patch just extends), or false positives.
Thanks,
Paolo
[1] https://lkml.org/lkml/2008/4/1/234
Arianna Avanzini (4):
block, bfq: add full hierarchical scheduling and cgroups support
block, bfq: add Early Queue Merge (EQM)
block, bfq: reduce idling only in symmetric scenarios
block, bfq: handle bursts of queue activations
Paolo Valente (10):
block, bfq: introduce the BFQ-v0 I/O scheduler as an extra scheduler
block, bfq: improve throughput boosting
block, bfq: modify the peak-rate estimator
block, bfq: add more fairness with writes and slow processes
block, bfq: improve responsiveness
block, bfq: reduce I/O latency for soft real-time applications
block, bfq: preserve a low latency also with NCQ-capable drives
block, bfq: reduce latency during request-pool saturation
block, bfq: boost the throughput on NCQ-capable flash-based devices
block, bfq: boost the throughput with random I/O on NCQ-capable HDDs
Documentation/block/00-INDEX | 2 +
Documentation/block/bfq-iosched.txt | 530 +++
block/Kconfig.iosched | 21 +
block/Makefile | 1 +
block/bfq-iosched.c | 8751 +++++++++++++++++++++++++++++++++++
block/elevator.c | 16 +-
include/linux/blkdev.h | 2 +-
7 files changed, 9317 insertions(+), 6 deletions(-)
create mode 100644 Documentation/block/bfq-iosched.txt
create mode 100644 block/bfq-iosched.c
--
2.10.0
^ permalink raw reply
* [PATCH v3] blkcg: allocate struct blkcg_gq outside request queue spinlock
From: Tahsin Erdogan @ 2017-03-04 1:40 UTC (permalink / raw)
To: Tejun Heo, Jens Axboe
Cc: linux-block, David Rientjes, linux-kernel, Tahsin Erdogan
In-Reply-To: <20170303192325.GB22962@wtj.duckdns.org>
blkg_conf_prep() currently calls blkg_lookup_create() while holding
request queue spinlock. This means allocating memory for struct
blkcg_gq has to be made non-blocking. This causes occasional -ENOMEM
failures in call paths like below:
pcpu_alloc+0x68f/0x710
__alloc_percpu_gfp+0xd/0x10
__percpu_counter_init+0x55/0xc0
cfq_pd_alloc+0x3b2/0x4e0
blkg_alloc+0x187/0x230
blkg_create+0x489/0x670
blkg_lookup_create+0x9a/0x230
blkg_conf_prep+0x1fb/0x240
__cfqg_set_weight_device.isra.105+0x5c/0x180
cfq_set_weight_on_dfl+0x69/0xc0
cgroup_file_write+0x39/0x1c0
kernfs_fop_write+0x13f/0x1d0
__vfs_write+0x23/0x120
vfs_write+0xc2/0x1f0
SyS_write+0x44/0xb0
entry_SYSCALL_64_fastpath+0x18/0xad
In the code path above, percpu allocator cannot call vmalloc() due to
queue spinlock.
A failure in this call path gives grief to tools which are trying to
configure io weights. We see occasional failures happen shortly after
reboots even when system is not under any memory pressure. Machines
with a lot of cpus are more vulnerable to this condition.
Update blkg_create() function to temporarily drop the rcu and queue
locks when it is allowed by gfp mask.
Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Tahsin Erdogan <tahsin@google.com>
---
v3:
Pushed down all blkg allocations into blkg_create()
v2:
Moved blkg creation into blkg_lookup_create() to avoid duplicating
blkg_lookup_create() logic.
block/blk-cgroup.c | 96 +++++++++++++++++++++++++++++-----------------
include/linux/blk-cgroup.h | 20 ++++++++--
2 files changed, 76 insertions(+), 40 deletions(-)
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 295e98c2c8cc..9bc2b10f3b5a 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -164,16 +164,17 @@ struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg,
EXPORT_SYMBOL_GPL(blkg_lookup_slowpath);
/*
- * If @new_blkg is %NULL, this function tries to allocate a new one as
- * necessary using %GFP_NOWAIT. @new_blkg is always consumed on return.
+ * If gfp mask allows blocking, this function temporarily drops rcu and queue
+ * locks to allocate memory.
*/
static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
- struct request_queue *q,
- struct blkcg_gq *new_blkg)
+ struct request_queue *q, gfp_t gfp,
+ const struct blkcg_policy *pol)
{
- struct blkcg_gq *blkg;
+ struct blkcg_gq *blkg = NULL;
struct bdi_writeback_congested *wb_congested;
int i, ret;
+ const bool drop_locks = gfpflags_allow_blocking(gfp);
WARN_ON_ONCE(!rcu_read_lock_held());
lockdep_assert_held(q->queue_lock);
@@ -184,24 +185,48 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
goto err_free_blkg;
}
+ if (drop_locks) {
+ spin_unlock_irq(q->queue_lock);
+ rcu_read_unlock();
+ }
+
wb_congested = wb_congested_get_create(q->backing_dev_info,
- blkcg->css.id,
- GFP_NOWAIT | __GFP_NOWARN);
- if (!wb_congested) {
+ blkcg->css.id, gfp);
+ blkg = blkg_alloc(blkcg, q, gfp);
+
+ if (drop_locks) {
+ rcu_read_lock();
+ spin_lock_irq(q->queue_lock);
+ }
+
+ if (unlikely(!wb_congested)) {
ret = -ENOMEM;
goto err_put_css;
+ } else if (unlikely(!blkg)) {
+ ret = -ENOMEM;
+ goto err_put_congested;
}
- /* allocate */
- if (!new_blkg) {
- new_blkg = blkg_alloc(blkcg, q, GFP_NOWAIT | __GFP_NOWARN);
- if (unlikely(!new_blkg)) {
- ret = -ENOMEM;
+ blkg->wb_congested = wb_congested;
+
+ if (pol) {
+ WARN_ON(!drop_locks);
+
+ if (!blkcg_policy_enabled(q, pol)) {
+ ret = -EOPNOTSUPP;
+ goto err_put_congested;
+ }
+
+ /*
+ * This could be the first entry point of blkcg implementation
+ * and we shouldn't allow anything to go through for a bypassing
+ * queue.
+ */
+ if (unlikely(blk_queue_bypass(q))) {
+ ret = blk_queue_dying(q) ? -ENODEV : -EBUSY;
goto err_put_congested;
}
}
- blkg = new_blkg;
- blkg->wb_congested = wb_congested;
/* link parent */
if (blkcg_parent(blkcg)) {
@@ -250,7 +275,7 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
err_put_css:
css_put(&blkcg->css);
err_free_blkg:
- blkg_free(new_blkg);
+ blkg_free(blkg);
return ERR_PTR(ret);
}
@@ -258,31 +283,30 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
* blkg_lookup_create - lookup blkg, try to create one if not there
* @blkcg: blkcg of interest
* @q: request_queue of interest
+ * @gfp: gfp mask
+ * @pol: blkcg policy (optional)
*
* Lookup blkg for the @blkcg - @q pair. If it doesn't exist, try to
* create one. blkg creation is performed recursively from blkcg_root such
* that all non-root blkg's have access to the parent blkg. This function
* should be called under RCU read lock and @q->queue_lock.
*
+ * When gfp mask allows blocking, rcu and queue locks may be dropped for
+ * allocating memory. In this case, the locks will be reacquired on return.
+ *
* Returns pointer to the looked up or created blkg on success, ERR_PTR()
* value on error. If @q is dead, returns ERR_PTR(-EINVAL). If @q is not
* dead and bypassing, returns ERR_PTR(-EBUSY).
*/
struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
- struct request_queue *q)
+ struct request_queue *q, gfp_t gfp,
+ const struct blkcg_policy *pol)
{
struct blkcg_gq *blkg;
WARN_ON_ONCE(!rcu_read_lock_held());
lockdep_assert_held(q->queue_lock);
- /*
- * This could be the first entry point of blkcg implementation and
- * we shouldn't allow anything to go through for a bypassing queue.
- */
- if (unlikely(blk_queue_bypass(q)))
- return ERR_PTR(blk_queue_dying(q) ? -ENODEV : -EBUSY);
-
blkg = __blkg_lookup(blkcg, q, true);
if (blkg)
return blkg;
@@ -300,7 +324,7 @@ struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
parent = blkcg_parent(parent);
}
- blkg = blkg_create(pos, q, NULL);
+ blkg = blkg_create(pos, q, gfp, pol);
if (pos == blkcg || IS_ERR(blkg))
return blkg;
}
@@ -789,6 +813,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
{
struct gendisk *disk;
struct blkcg_gq *blkg;
+ struct request_queue *q;
struct module *owner;
unsigned int major, minor;
int key_len, part, ret;
@@ -812,18 +837,22 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
return -ENODEV;
}
+ q = disk->queue;
+
rcu_read_lock();
- spin_lock_irq(disk->queue->queue_lock);
+ spin_lock_irq(q->queue_lock);
- if (blkcg_policy_enabled(disk->queue, pol))
- blkg = blkg_lookup_create(blkcg, disk->queue);
- else
+ if (!blkcg_policy_enabled(q, pol))
blkg = ERR_PTR(-EOPNOTSUPP);
+ else if (unlikely(blk_queue_bypass(q)))
+ blkg = ERR_PTR(blk_queue_dying(q) ? -ENODEV : -EBUSY);
+ else
+ blkg = blkg_lookup_create(blkcg, q, GFP_KERNEL, pol);
if (IS_ERR(blkg)) {
ret = PTR_ERR(blkg);
rcu_read_unlock();
- spin_unlock_irq(disk->queue->queue_lock);
+ spin_unlock_irq(q->queue_lock);
owner = disk->fops->owner;
put_disk(disk);
module_put(owner);
@@ -1065,14 +1094,9 @@ int blkcg_init_queue(struct request_queue *q)
preloaded = !radix_tree_preload(GFP_KERNEL);
- /*
- * Make sure the root blkg exists and count the existing blkgs. As
- * @q is bypassing at this point, blkg_lookup_create() can't be
- * used. Open code insertion.
- */
rcu_read_lock();
spin_lock_irq(q->queue_lock);
- blkg = blkg_create(&blkcg_root, q, new_blkg);
+ blkg = blkg_lookup_create(&blkcg_root, q, GFP_KERNEL, NULL);
spin_unlock_irq(q->queue_lock);
rcu_read_unlock();
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 01b62e7bac74..9dbe552c6ea0 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -172,7 +172,8 @@ extern struct cgroup_subsys_state * const blkcg_root_css;
struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg,
struct request_queue *q, bool update_hint);
struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
- struct request_queue *q);
+ struct request_queue *q, gfp_t gfp,
+ const struct blkcg_policy *pol);
int blkcg_init_queue(struct request_queue *q);
void blkcg_drain_queue(struct request_queue *q);
void blkcg_exit_queue(struct request_queue *q);
@@ -694,9 +695,20 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q,
blkg = blkg_lookup(blkcg, q);
if (unlikely(!blkg)) {
spin_lock_irq(q->queue_lock);
- blkg = blkg_lookup_create(blkcg, q);
- if (IS_ERR(blkg))
- blkg = NULL;
+
+ /*
+ * This could be the first entry point of blkcg implementation
+ * and we shouldn't allow anything to go through for a bypassing
+ * queue.
+ */
+ if (likely(!blk_queue_bypass(q))) {
+ blkg = blkg_lookup_create(blkcg, q,
+ GFP_NOWAIT | __GFP_NOWARN,
+ NULL);
+ if (IS_ERR(blkg))
+ blkg = NULL;
+ }
+
spin_unlock_irq(q->queue_lock);
}
--
2.12.0.rc1.440.g5b76565f74-goog
^ permalink raw reply related
* Re: [PATCH] cfq-iosched: fix the delay of cfq_group's vdisktime under iops mode
From: Vivek Goyal @ 2017-03-03 19:53 UTC (permalink / raw)
To: Hou Tao; +Cc: Jan Kara, axboe, linux-block, jmoyer, stable
In-Reply-To: <cb362b2f-e74a-afa8-02f0-22d061c0e5a6@huawei.com>
On Fri, Mar 03, 2017 at 09:20:44PM +0800, Hou Tao wrote:
[..]
> > Frankly, vdisktime is in fixed-point precision shifted by
> > CFQ_SERVICE_SHIFT so using CFQ_IDLE_DELAY does not make much sense in any
> > case and just adding 1 to maximum vdisktime should be fine in all the
> > cases. But that would require more testing whether I did not miss anything
> > subtle.
I think even 1 will work. But in the beginning IIRC I took the idea
from cpu scheduler. Adding a value bigger than 1 will allow you to add
some other group later before this group. (If you want to give that group
higher priority).
Thanks
Vivek
^ permalink raw reply
* Re: [PATCH v2] blkcg: allocate struct blkcg_gq outside request queue spinlock
From: Tejun Heo @ 2017-03-03 19:23 UTC (permalink / raw)
To: Tahsin Erdogan; +Cc: Jens Axboe, linux-block, David Rientjes, linux-kernel
In-Reply-To: <CAAeU0aO5hD8DHKOyGmskK5icCqf5U8hdMEZSfn6eLcHeL-YH7g@mail.gmail.com>
Hello, Tahsin.
On Thu, Mar 02, 2017 at 02:33:11PM -0800, Tahsin Erdogan wrote:
> > And let blkg_create() verify these conditions after releasing and
> > regrabbing the lock.
> >
> > This also means that the init path can simply pass in GFP_KERNEL.
>
> I tried that approach, but I encountered two issues that complicate things:
>
> 1) Pushing down blk_queue_bypass(q) check in blkg_create() doesn't
> quite work because when blkcg_init_queue() calls blkg_create(), the
> queue is still in bypassing mode.
>
> 2) Pushing down blkcg_policy_enabled() doesn't work well either,
> because blkcg_init_queue() doesn't have a policy to pass down. We
> could let it pass a NULL parameter but that would make blkg_create
> more ugly.
I see. It kinda really bothers me that we'll have two different modes
for non-atomic allocations. Can't we bind both to the policy
parameter? Skip the checks if policy is NULL?
Thanks.
--
tejun
^ permalink raw reply
* Re: [PATCH v2 09/13] md: raid1: use bio_segments_all()
From: Shaohua Li @ 2017-03-03 17:12 UTC (permalink / raw)
To: Ming Lei
Cc: Jens Axboe, open list:SOFTWARE RAID (Multiple Disks) SUPPORT,
linux-block, Christoph Hellwig
In-Reply-To: <CACVXFVNRhekBMAnVN9co-jdkP=+5S+28CyFr9Z_nsJVmdxPxSg@mail.gmail.com>
On Fri, Mar 03, 2017 at 02:22:30PM +0800, Ming Lei wrote:
> On Fri, Mar 3, 2017 at 10:20 AM, Ming Lei <tom.leiming@gmail.com> wrote:
> > On Thu, Mar 2, 2017 at 3:52 PM, Shaohua Li <shli@kernel.org> wrote:
> >> On Thu, Mar 02, 2017 at 10:34:25AM +0800, Ming Lei wrote:
> >>> Hi Shaohua,
> >>>
> >>> On Wed, Mar 1, 2017 at 7:42 AM, Shaohua Li <shli@kernel.org> wrote:
> >>> > On Tue, Feb 28, 2017 at 11:41:39PM +0800, Ming Lei wrote:
> >>> >> Use this helper, instead of direct access to .bi_vcnt.
> >>> >
> >>> > what We really need to do for the behind IO is:
> >>> > - allocate memory and copy bio data to the memory
> >>> > - let behind bio do IO against the memory
> >>> >
> >>> > The behind bio doesn't need to have the exactly same bio_vec setting. If we
> >>> > just track the new memory, we don't need use the bio_segments_all and access
> >>> > bio_vec too.
> >>>
> >>> But we need to figure out how many vecs(each vec store one page) to be
> >>> allocated for the cloned/behind bio, and that is the only value of
> >>> bio_segments_all() here. Or you have idea to avoid that?
> >>
> >> As I said, the behind bio doesn't need to have the exactly same bio_vec
> >> setting. We just allocate memory and copy original bio data to the memory,
> >> then do IO against the new memory. The behind bio
> >> segments == (bio->bi_iter.bi_size + PAGE_SIZE - 1) >> PAGE_SHIFT
> >
> > The equation isn't always correct, especially when bvec includes just
> > part of page, and it is quite often in case of mkfs, in which one bvec often
> > includes 512byte buffer.
>
> Think it further, your idea could be workable and more clean, but the change
> can be a bit big, looks we need to switch handling write behind into
> the following way:
>
> 1) replace bio_clone_bioset_partial() with bio_allocate(nr_vecs), and 'nr_vecs'
> is computed with your equation;
>
> 2) allocate 'nr_vecs' pages once and share them among all created bio in 1)
>
> 3) for each created bio, add each page into the bio via bio_add_page()
>
> 4) only for the 1st created bio, call bio_copy_data() to copy data from
> master bio.
>
> Let me know if you are OK with the above implementaion.
Right, this is exactly what I'd like to do. This way we don't need touch
bvec and should be much cleaner.
Thanks,
Shaohua
^ permalink raw reply
* Re: [PATCH] block: use put_io_context_active() to disassociate bio from a task
From: Tejun Heo @ 2017-03-03 19:12 UTC (permalink / raw)
To: Hou Tao; +Cc: linux-block, axboe
In-Reply-To: <1488524470-570-1-git-send-email-houtao1@huawei.com>
Hello,
On Fri, Mar 03, 2017 at 03:01:10PM +0800, Hou Tao wrote:
> bio_associate_current() invokes get_io_context_active() to tell
> CFQ scheduler that the current io_context is still issuing IOs
> by increasing active_ref. When the bio is done, we also need
> to invoke put_io_context_active() to decrease active_ref else
> the associated io_context will always be active.
>
> Signed-off-by: Hou Tao <houtao1@huawei.com>
Can you please explain how you noticed issue and verified the patch?
Also, the patch will need the following.
Fixes: 852c788f8365 ("block: implement bio_associate_current()")
Cc: stable@vger.kernel.org # v3.5+
I think the failure mode isn't severe. We'll be carrying around ioc's
longer than necessary but that's about it. I wonder whether the logic
can be simplified in general. Anyways, please feel free to add
Acked-by: Tejun Heo <tj@kernel.org>
Thanks.
--
tejun
^ permalink raw reply
* Re: [PATCH v2 06/13] md: raid1: don't use bio's vec table to manage resync pages
From: Shaohua Li @ 2017-03-03 17:38 UTC (permalink / raw)
To: Ming Lei
Cc: Jens Axboe, open list:SOFTWARE RAID (Multiple Disks) SUPPORT,
linux-block, Christoph Hellwig
In-Reply-To: <CACVXFVPQx0rQqQS0PG2MoYh+pGvVQb_H_+fMCGbWeVDM3JNcnQ@mail.gmail.com>
On Fri, Mar 03, 2017 at 10:11:31AM +0800, Ming Lei wrote:
> On Fri, Mar 3, 2017 at 1:48 AM, Shaohua Li <shli@kernel.org> wrote:
> > On Thu, Mar 02, 2017 at 10:25:10AM +0800, Ming Lei wrote:
> >> Hi Shaohua,
> >>
> >> On Wed, Mar 1, 2017 at 7:37 AM, Shaohua Li <shli@kernel.org> wrote:
> >> > On Tue, Feb 28, 2017 at 11:41:36PM +0800, Ming Lei wrote:
> >> >> Now we allocate one page array for managing resync pages, instead
> >> >> of using bio's vec table to do that, and the old way is very hacky
> >> >> and won't work any more if multipage bvec is enabled.
> >> >>
> >> >> The introduced cost is that we need to allocate (128 + 16) * raid_disks
> >> >> bytes per r1_bio, and it is fine because the inflight r1_bio for
> >> >> resync shouldn't be much, as pointed by Shaohua.
> >> >>
> >> >> Also the bio_reset() in raid1_sync_request() is removed because
> >> >> all bios are freshly new now and not necessary to reset any more.
> >> >>
> >> >> This patch can be thought as a cleanup too
> >> >>
> >> >> Suggested-by: Shaohua Li <shli@kernel.org>
> >> >> Signed-off-by: Ming Lei <tom.leiming@gmail.com>
> >> >> ---
> >> >> drivers/md/raid1.c | 83 ++++++++++++++++++++++++++++++++++--------------------
> >> >> 1 file changed, 53 insertions(+), 30 deletions(-)
> >> >>
> >> >> diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
> >> >> index c442b4657e2f..900144f39630 100644
> >> >> --- a/drivers/md/raid1.c
> >> >> +++ b/drivers/md/raid1.c
> >> >> @@ -77,6 +77,16 @@ static void lower_barrier(struct r1conf *conf, sector_t sector_nr);
> >> >> #define raid1_log(md, fmt, args...) \
> >> >> do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid1 " fmt, ##args); } while (0)
> >> >>
> >> >> +static inline struct resync_pages *get_resync_pages(struct bio *bio)
> >> >> +{
> >> >> + return bio->bi_private;
> >> >> +}
> >> >> +
> >> >> +static inline struct r1bio *get_resync_r1bio(struct bio *bio)
> >> >> +{
> >> >> + return get_resync_pages(bio)->raid_bio;
> >> >> +}
> >> >
> >> > This is a weird between bio, r1bio and the resync_pages. I'd like the pages are
> >>
> >> It is only a bit weird inside allocating and freeing r1bio, once all
> >> are allocated, you
> >> can see everthing is clean and simple:
> >>
> >> - r1bio includes lots of bioes,
> >> - and one bio is attached by one resync_pages via .bi_private
> >
> > I don't how complex to let r1bio pointer to the pages, but that's the nartual
> > way. r1bio owns the pages, not the pages own r1bio, so we should let r1bio
> > points to the pages. The bio.bi_private still points to r1bio.
>
> Actually it is bio which owns the pages for doing its own I/O, and the only
> thing related with r10bio is that bios may share these pages, but using
> page refcount trick will make the relation quite implicit.
>
> The only reason to allocate all resync_pages together is for sake of efficiency,
> and just for avoiding to allocate one resync_pages one time for each bio.
>
> We have to make .bi_private point to resync_pages(per bio), otherwise we
> can't fetch pages into one bio at all, thinking about where to store the index
> for each bio's pre-allocated pages, and it has to be per bio.
So the reason is we can't find the corresponding pages of the bio if bi_private
points to r1bio, right? Got it. We don't have many choices in this way. Ok, I
don't insist. Please add some comments in the get_resync_r1bio to describe how
the data structure is organized.
Thanks,
Shaohua
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox