summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/admin-guide/cgroup-v2.rst97
-rw-r--r--Documentation/admin-guide/kernel-parameters.txt6
-rw-r--r--Documentation/admin-guide/kernel-per-CPU-kthreads.rst8
-rw-r--r--Documentation/block/null_blk.rst33
-rw-r--r--Documentation/block/switching-sched.rst4
-rw-r--r--block/Kconfig13
-rw-r--r--block/Makefile1
-rw-r--r--block/bfq-cgroup.c156
-rw-r--r--block/bfq-iosched.h3
-rw-r--r--block/bfq-wf2q.c2
-rw-r--r--block/bio.c60
-rw-r--r--block/blk-cgroup.c73
-rw-r--r--block/blk-core.c37
-rw-r--r--block/blk-iocost.c2457
-rw-r--r--block/blk-iolatency.c8
-rw-r--r--block/blk-merge.c151
-rw-r--r--block/blk-mq-cpumap.c29
-rw-r--r--block/blk-mq-sysfs.c23
-rw-r--r--block/blk-mq-tag.c32
-rw-r--r--block/blk-mq.c69
-rw-r--r--block/blk-pm.c12
-rw-r--r--block/blk-rq-qos.c18
-rw-r--r--block/blk-rq-qos.h28
-rw-r--r--block/blk-settings.c18
-rw-r--r--block/blk-sysfs.c50
-rw-r--r--block/blk-throttle.c9
-rw-r--r--block/blk-wbt.c20
-rw-r--r--block/blk-wbt.h4
-rw-r--r--block/blk-zoned.c39
-rw-r--r--block/blk.h4
-rw-r--r--block/elevator.c217
-rw-r--r--block/genhd.c9
-rw-r--r--block/mq-deadline.c20
-rw-r--r--block/opal_proto.h5
-rw-r--r--block/sed-opal.c49
-rw-r--r--drivers/block/floppy.c4
-rw-r--r--drivers/block/loop.c1
-rw-r--r--drivers/block/nbd.c127
-rw-r--r--drivers/block/null_blk.h18
-rw-r--r--drivers/block/null_blk_main.c183
-rw-r--r--drivers/block/null_blk_zoned.c59
-rw-r--r--drivers/block/paride/pcd.c12
-rw-r--r--drivers/block/paride/pf.c2
-rw-r--r--drivers/lightnvm/core.c97
-rw-r--r--drivers/lightnvm/pblk-core.c116
-rw-r--r--drivers/lightnvm/pblk-gc.c19
-rw-r--r--drivers/lightnvm/pblk-init.c38
-rw-r--r--drivers/lightnvm/pblk-read.c26
-rw-r--r--drivers/lightnvm/pblk-recovery.c42
-rw-r--r--drivers/lightnvm/pblk-write.c20
-rw-r--r--drivers/lightnvm/pblk.h31
-rw-r--r--drivers/md/bcache/closure.c10
-rw-r--r--drivers/md/bcache/debug.c5
-rw-r--r--drivers/md/bcache/sysfs.c1
-rw-r--r--drivers/md/dm-rq.c3
-rw-r--r--drivers/md/md-linear.c5
-rw-r--r--drivers/md/md.c96
-rw-r--r--drivers/md/md.h20
-rw-r--r--drivers/md/raid0.c41
-rw-r--r--drivers/md/raid0.h14
-rw-r--r--drivers/md/raid1.c89
-rw-r--r--drivers/md/raid10.c32
-rw-r--r--drivers/md/raid5.c27
-rw-r--r--drivers/md/raid5.h5
-rw-r--r--drivers/nvme/host/Kconfig1
-rw-r--r--drivers/nvme/host/core.c201
-rw-r--r--drivers/nvme/host/fabrics.c38
-rw-r--r--drivers/nvme/host/fabrics.h3
-rw-r--r--drivers/nvme/host/fc.c73
-rw-r--r--drivers/nvme/host/lightnvm.c45
-rw-r--r--drivers/nvme/host/multipath.c8
-rw-r--r--drivers/nvme/host/nvme.h36
-rw-r--r--drivers/nvme/host/pci.c102
-rw-r--r--drivers/nvme/host/rdma.c61
-rw-r--r--drivers/nvme/host/tcp.c144
-rw-r--r--drivers/nvme/host/trace.c18
-rw-r--r--drivers/nvme/target/admin-cmd.c22
-rw-r--r--drivers/nvme/target/discovery.c4
-rw-r--r--drivers/nvme/target/loop.c30
-rw-r--r--drivers/nvme/target/tcp.c24
-rw-r--r--drivers/nvme/target/trace.c18
-rw-r--r--drivers/scsi/scsi_lib.c13
-rw-r--r--drivers/scsi/scsi_pm.c3
-rw-r--r--drivers/scsi/sd.c5
-rw-r--r--drivers/scsi/sd.h5
-rw-r--r--drivers/scsi/sd_zbc.c12
-rw-r--r--fs/fs-writeback.c174
-rw-r--r--include/linux/backing-dev-defs.h23
-rw-r--r--include/linux/backing-dev.h5
-rw-r--r--include/linux/blk-cgroup.h6
-rw-r--r--include/linux/blk-mq.h20
-rw-r--r--include/linux/blk_types.h6
-rw-r--r--include/linux/blkdev.h73
-rw-r--r--include/linux/elevator.h8
-rw-r--r--include/linux/lightnvm.h8
-rw-r--r--include/linux/memcontrol.h39
-rw-r--r--include/linux/nvme.h5
-rw-r--r--include/linux/writeback.h2
-rw-r--r--include/trace/events/iocost.h178
-rw-r--r--include/trace/events/writeback.h126
-rw-r--r--include/uapi/linux/raid/md_p.h2
-rw-r--r--lib/sg_split.c12
-rw-r--r--mm/backing-dev.c120
-rw-r--r--mm/memcontrol.c139
-rw-r--r--mm/page-writeback.c4
-rw-r--r--tools/cgroup/iocost_coef_gen.py178
-rw-r--r--tools/cgroup/iocost_monitor.py277
107 files changed, 5895 insertions, 1283 deletions
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 5f1c266131b0..0fa8c0e615c2 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1469,6 +1469,103 @@ IO Interface Files
8:16 rbytes=1459200 wbytes=314773504 rios=192 wios=353 dbytes=0 dios=0
8:0 rbytes=90430464 wbytes=299008000 rios=8950 wios=1252 dbytes=50331648 dios=3021
+ io.cost.qos
+ A read-write nested-keyed file with exists only on the root
+ cgroup.
+
+ This file configures the Quality of Service of the IO cost
+ model based controller (CONFIG_BLK_CGROUP_IOCOST) which
+ currently implements "io.weight" proportional control. Lines
+ are keyed by $MAJ:$MIN device numbers and not ordered. The
+ line for a given device is populated on the first write for
+ the device on "io.cost.qos" or "io.cost.model". The following
+ nested keys are defined.
+
+ ====== =====================================
+ enable Weight-based control enable
+ ctrl "auto" or "user"
+ rpct Read latency percentile [0, 100]
+ rlat Read latency threshold
+ wpct Write latency percentile [0, 100]
+ wlat Write latency threshold
+ min Minimum scaling percentage [1, 10000]
+ max Maximum scaling percentage [1, 10000]
+ ====== =====================================
+
+ The controller is disabled by default and can be enabled by
+ setting "enable" to 1. "rpct" and "wpct" parameters default
+ to zero and the controller uses internal device saturation
+ state to adjust the overall IO rate between "min" and "max".
+
+ When a better control quality is needed, latency QoS
+ parameters can be configured. For example::
+
+ 8:16 enable=1 ctrl=auto rpct=95.00 rlat=75000 wpct=95.00 wlat=150000 min=50.00 max=150.0
+
+ shows that on sdb, the controller is enabled, will consider
+ the device saturated if the 95th percentile of read completion
+ latencies is above 75ms or write 150ms, and adjust the overall
+ IO issue rate between 50% and 150% accordingly.
+
+ The lower the saturation point, the better the latency QoS at
+ the cost of aggregate bandwidth. The narrower the allowed
+ adjustment range between "min" and "max", the more conformant
+ to the cost model the IO behavior. Note that the IO issue
+ base rate may be far off from 100% and setting "min" and "max"
+ blindly can lead to a significant loss of device capacity or
+ control quality. "min" and "max" are useful for regulating
+ devices which show wide temporary behavior changes - e.g. a
+ ssd which accepts writes at the line speed for a while and
+ then completely stalls for multiple seconds.
+
+ When "ctrl" is "auto", the parameters are controlled by the
+ kernel and may change automatically. Setting "ctrl" to "user"
+ or setting any of the percentile and latency parameters puts
+ it into "user" mode and disables the automatic changes. The
+ automatic mode can be restored by setting "ctrl" to "auto".
+
+ io.cost.model
+ A read-write nested-keyed file with exists only on the root
+ cgroup.
+
+ This file configures the cost model of the IO cost model based
+ controller (CONFIG_BLK_CGROUP_IOCOST) which currently
+ implements "io.weight" proportional control. Lines are keyed
+ by $MAJ:$MIN device numbers and not ordered. The line for a
+ given device is populated on the first write for the device on
+ "io.cost.qos" or "io.cost.model". The following nested keys
+ are defined.
+
+ ===== ================================
+ ctrl "auto" or "user"
+ model The cost model in use - "linear"
+ ===== ================================
+
+ When "ctrl" is "auto", the kernel may change all parameters
+ dynamically. When "ctrl" is set to "user" or any other
+ parameters are written to, "ctrl" become "user" and the
+ automatic changes are disabled.
+
+ When "model" is "linear", the following model parameters are
+ defined.
+
+ ============= ========================================
+ [r|w]bps The maximum sequential IO throughput
+ [r|w]seqiops The maximum 4k sequential IOs per second
+ [r|w]randiops The maximum 4k random IOs per second
+ ============= ========================================
+
+ From the above, the builtin linear model determines the base
+ costs of a sequential and random IO and the cost coefficient
+ for the IO size. While simple, this model can cover most
+ common device classes acceptably.
+
+ The IO cost model isn't expected to be accurate in absolute
+ sense and is scaled to the device behavior dynamically.
+
+ If needed, tools/cgroup/iocost_coef_gen.py can be used to
+ generate device-specific coefficients.
+
io.weight
A read-write flat-keyed file which exists on non-root cgroups.
The default is "default 100".
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 3e2d22eb5e59..6ef205fd7c97 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1201,12 +1201,6 @@
See comment before function elanfreq_setup() in
arch/x86/kernel/cpu/cpufreq/elanfreq.c.
- elevator= [IOSCHED]
- Format: { "mq-deadline" | "kyber" | "bfq" }
- See Documentation/block/deadline-iosched.rst,
- Documentation/block/kyber-iosched.rst and
- Documentation/block/bfq-iosched.rst for details.
-
elfcorehdr=[size[KMG]@]offset[KMG] [IA64,PPC,SH,X86,S390]
Specifies physical address of start of kernel core
image elf header and optionally the size. Generally
diff --git a/Documentation/admin-guide/kernel-per-CPU-kthreads.rst b/Documentation/admin-guide/kernel-per-CPU-kthreads.rst
index 4f18456dd3b1..baeeba8762ae 100644
--- a/Documentation/admin-guide/kernel-per-CPU-kthreads.rst
+++ b/Documentation/admin-guide/kernel-per-CPU-kthreads.rst
@@ -274,9 +274,7 @@ To reduce its OS jitter, do any of the following:
(based on an earlier one from Gilad Ben-Yossef) that
reduces or even eliminates vmstat overhead for some
workloads at https://lkml.org/lkml/2013/9/4/379.
- e. Boot with "elevator=noop" to avoid workqueue use by
- the block layer.
- f. If running on high-end powerpc servers, build with
+ e. If running on high-end powerpc servers, build with
CONFIG_PPC_RTAS_DAEMON=n. This prevents the RTAS
daemon from running on each CPU every second or so.
(This will require editing Kconfig files and will defeat
@@ -284,12 +282,12 @@ To reduce its OS jitter, do any of the following:
due to the rtas_event_scan() function.
WARNING: Please check your CPU specifications to
make sure that this is safe on your particular system.
- g. If running on Cell Processor, build your kernel with
+ f. If running on Cell Processor, build your kernel with
CBE_CPUFREQ_SPU_GOVERNOR=n to avoid OS jitter from
spu_gov_work().
WARNING: Please check your CPU specifications to
make sure that this is safe on your particular system.
- h. If running on PowerMAC, build your kernel with
+ g. If running on PowerMAC, build your kernel with
CONFIG_PMAC_RACKMETER=n to disable the CPU-meter,
avoiding OS jitter from rackmeter_do_timer().
diff --git a/Documentation/block/null_blk.rst b/Documentation/block/null_blk.rst
index 31451d80783c..edbbab2f12f8 100644
--- a/Documentation/block/null_blk.rst
+++ b/Documentation/block/null_blk.rst
@@ -1,19 +1,16 @@
+.. SPDX-License-Identifier: GPL-2.0
+
========================
Null block device driver
========================
-1. Overview
-===========
+Overview
+========
-The null block device (/dev/nullb*) is used for benchmarking the various
+The null block device (``/dev/nullb*``) is used for benchmarking the various
block-layer implementations. It emulates a block device of X gigabytes in size.
-The following instances are possible:
-
- Single-queue block-layer
-
- - Request-based.
- - Single submission queue per device.
- - Implements IO scheduling algorithms (CFQ, Deadline, noop).
+It does not execute any read/write operation, just mark them as complete in
+the request queue. The following instances are possible:
Multi-queue block-layer
@@ -27,15 +24,15 @@ The following instances are possible:
All of them have a completion queue for each core in the system.
-2. Module parameters applicable for all instances
-=================================================
+Module parameters
+=================
queue_mode=[0-2]: Default: 2-Multi-queue
Selects which block-layer the module should instantiate with.
= ============
0 Bio-based
- 1 Single-queue
+ 1 Single-queue (deprecated)
2 Multi-queue
= ============
@@ -67,7 +64,7 @@ irqmode=[0-2]: Default: 1-Soft-irq
completion_nsec=[ns]: Default: 10,000ns
Combined with irqmode=2 (timer). The time each completion event must wait.
-submit_queues=[1..nr_cpus]:
+submit_queues=[1..nr_cpus]: Default: 1
The number of submission queues attached to the device driver. If unset, it
defaults to 1. For multi-queue, it is ignored when use_per_node_hctx module
parameter is 1.
@@ -75,9 +72,11 @@ submit_queues=[1..nr_cpus]:
hw_queue_depth=[0..qdepth]: Default: 64
The hardware queue depth of the device.
-III: Multi-queue specific parameters
+Multi-queue specific parameters
+-------------------------------
use_per_node_hctx=[0/1]: Default: 0
+ Number of hardware context queues.
= =====================================================================
0 The number of submit queues are set to the value of the submit_queues
@@ -87,6 +86,7 @@ use_per_node_hctx=[0/1]: Default: 0
= =====================================================================
no_sched=[0/1]: Default: 0
+ Enable/disable the io scheduler.
= ======================================
0 nullb* use default blk-mq io scheduler
@@ -94,6 +94,7 @@ no_sched=[0/1]: Default: 0
= ======================================
blocking=[0/1]: Default: 0
+ Blocking behavior of the request queue.
= ===============================================================
0 Register as a non-blocking blk-mq driver device.
@@ -103,6 +104,7 @@ blocking=[0/1]: Default: 0
= ===============================================================
shared_tags=[0/1]: Default: 0
+ Sharing tags between devices.
= ================================================================
0 Tag set is not shared.
@@ -111,6 +113,7 @@ shared_tags=[0/1]: Default: 0
= ================================================================
zoned=[0/1]: Default: 0
+ Device is a random-access or a zoned block device.
= ======================================================================
0 Block device is exposed as a random-access block device.
diff --git a/Documentation/block/switching-sched.rst b/Documentation/block/switching-sched.rst
index 42042417380e..520f6b857544 100644
--- a/Documentation/block/switching-sched.rst
+++ b/Documentation/block/switching-sched.rst
@@ -2,10 +2,6 @@
Switching Scheduler
===================
-To choose IO schedulers at boot time, use the argument 'elevator=deadline'.
-'noop' and 'cfq' (the default) are also available. IO schedulers are assigned
-globally at boot time only presently.
-
Each io queue has a set of io scheduler tunables associated with it. These
tunables control how the io scheduler works. You can find these entries
in::
diff --git a/block/Kconfig b/block/Kconfig
index 8b5f8e560eb4..41c0917ce622 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -26,6 +26,9 @@ menuconfig BLOCK
if BLOCK
+config BLK_RQ_ALLOC_TIME
+ bool
+
config BLK_SCSI_REQUEST
bool
@@ -132,6 +135,16 @@ config BLK_CGROUP_IOLATENCY
Note, this is an experimental interface and could be changed someday.
+config BLK_CGROUP_IOCOST
+ bool "Enable support for cost model based cgroup IO controller"
+ depends on BLK_CGROUP=y
+ select BLK_RQ_ALLOC_TIME
+ ---help---
+ Enabling this option enables the .weight interface for cost
+ model based proportional IO control. The IO controller
+ distributes IO capacity between different groups based on
+ their share of the overall weight distribution.
+
config BLK_WBT_MQ
bool "Multiqueue writeback throttling"
default y
diff --git a/block/Makefile b/block/Makefile
index eee1b4ceecf9..9ef57ace90d4 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -18,6 +18,7 @@ obj-$(CONFIG_BLK_DEV_BSGLIB) += bsg-lib.o
obj-$(CONFIG_BLK_CGROUP) += blk-cgroup.o
obj-$(CONFIG_BLK_DEV_THROTTLING) += blk-throttle.o
obj-$(CONFIG_BLK_CGROUP_IOLATENCY) += blk-iolatency.o
+obj-$(CONFIG_BLK_CGROUP_IOCOST) += blk-iocost.o
obj-$(CONFIG_MQ_IOSCHED_DEADLINE) += mq-deadline.o
obj-$(CONFIG_MQ_IOSCHED_KYBER) += kyber-iosched.o
bfq-y := bfq-iosched.o bfq-wf2q.o bfq-cgroup.o
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 0f6cd688924f..86a607cf19a1 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -501,11 +501,12 @@ 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)
+static struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, struct request_queue *q,
+ struct blkcg *blkcg)
{
struct bfq_group *bfqg;
- bfqg = kzalloc_node(sizeof(*bfqg), gfp, node);
+ bfqg = kzalloc_node(sizeof(*bfqg), gfp, q->node);
if (!bfqg)
return NULL;
@@ -904,7 +905,7 @@ void bfq_end_wr_async(struct bfq_data *bfqd)
bfq_end_wr_async_queues(bfqd, bfqd->root_group);
}
-static int bfq_io_show_weight(struct seq_file *sf, void *v)
+static int bfq_io_show_weight_legacy(struct seq_file *sf, void *v)
{
struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg);
@@ -918,6 +919,60 @@ static int bfq_io_show_weight(struct seq_file *sf, void *v)
return 0;
}
+static u64 bfqg_prfill_weight_device(struct seq_file *sf,
+ struct blkg_policy_data *pd, int off)
+{
+ struct bfq_group *bfqg = pd_to_bfqg(pd);
+
+ if (!bfqg->entity.dev_weight)
+ return 0;
+ return __blkg_prfill_u64(sf, pd, bfqg->entity.dev_weight);
+}
+
+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);
+
+ seq_printf(sf, "default %u\n", bfqgd->weight);
+ blkcg_print_blkgs(sf, blkcg, bfqg_prfill_weight_device,
+ &blkcg_policy_bfq, 0, false);
+ return 0;
+}
+
+static void bfq_group_set_weight(struct bfq_group *bfqg, u64 weight, u64 dev_weight)
+{
+ weight = dev_weight ?: weight;
+
+ bfqg->entity.dev_weight = dev_weight;
+ /*
+ * 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)weight != bfqg->entity.new_weight) {
+ bfqg->entity.new_weight = (unsigned short)weight;
+ /*
+ * 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;
+ }
+}
+
static int bfq_io_set_weight_legacy(struct cgroup_subsys_state *css,
struct cftype *cftype,
u64 val)
@@ -936,55 +991,72 @@ static int bfq_io_set_weight_legacy(struct cgroup_subsys_state *css,
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;
- }
+ if (bfqg)
+ bfq_group_set_weight(bfqg, val, 0);
}
spin_unlock_irq(&blkcg->lock);
return ret;
}
-static ssize_t bfq_io_set_weight(struct kernfs_open_file *of,
- char *buf, size_t nbytes,
- loff_t off)
+static ssize_t bfq_io_set_device_weight(struct kernfs_open_file *of,
+ char *buf, size_t nbytes,
+ loff_t off)
{
- u64 weight;
- /* First unsigned long found in the file is used */
- int ret = kstrtoull(strim(buf), 0, &weight);
+ int ret;
+ struct blkg_conf_ctx ctx;
+ struct blkcg *blkcg = css_to_blkcg(of_css(of));
+ struct bfq_group *bfqg;
+ u64 v;
+ ret = blkg_conf_prep(blkcg, &blkcg_policy_bfq, buf, &ctx);
if (ret)
return ret;
- ret = bfq_io_set_weight_legacy(of_css(of), NULL, weight);
+ if (sscanf(ctx.body, "%llu", &v) == 1) {
+ /* require "default" on dfl */
+ ret = -ERANGE;
+ if (!v)
+ goto out;
+ } else if (!strcmp(strim(ctx.body), "default")) {
+ v = 0;
+ } else {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ bfqg = blkg_to_bfqg(ctx.blkg);
+
+ ret = -ERANGE;
+ if (!v || (v >= BFQ_MIN_WEIGHT && v <= BFQ_MAX_WEIGHT)) {
+ bfq_group_set_weight(bfqg, bfqg->entity.weight, v);
+ ret = 0;
+ }
+out:
+ blkg_conf_finish(&ctx);
return ret ?: nbytes;
}
+static ssize_t bfq_io_set_weight(struct kernfs_open_file *of,
+ char *buf, size_t nbytes,
+ loff_t off)
+{
+ char *endp;
+ int ret;
+ u64 v;
+
+ buf = strim(buf);
+
+ /* "WEIGHT" or "default WEIGHT" sets the default weight */
+ v = simple_strtoull(buf, &endp, 0);
+ if (*endp == '\0' || sscanf(buf, "default %llu", &v) == 1) {
+ ret = bfq_io_set_weight_legacy(of_css(of), NULL, v);
+ return ret ?: nbytes;
+ }
+
+ return bfq_io_set_device_weight(of, buf, nbytes, off);
+}
+
#ifdef CONFIG_BFQ_CGROUP_DEBUG
static int bfqg_print_stat(struct seq_file *sf, void *v)
{
@@ -1141,9 +1213,15 @@ struct cftype bfq_blkcg_legacy_files[] = {
{
.name = "bfq.weight",
.flags = CFTYPE_NOT_ON_ROOT,
- .seq_show = bfq_io_show_weight,
+ .seq_show = bfq_io_show_weight_legacy,
.write_u64 = bfq_io_set_weight_legacy,
},
+ {
+ .name = "bfq.weight_device",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = bfq_io_show_weight,
+ .write = bfq_io_set_weight,
+ },
/* statistics, covers only the tasks in the bfqg */
{
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index e80adf822bbe..5d1a519640f6 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -168,6 +168,9 @@ struct bfq_entity {
/* budget, used also to calculate F_i: F_i = S_i + @budget / @weight */
int budget;
+ /* device weight, if non-zero, it overrides the default weight of
+ * bfq_group_data */
+ int dev_weight;
/* weight of the queue */
int weight;
/* next weight if a change is in progress */
diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
index c9ba225081ce..05f0bf4a1144 100644
--- a/block/bfq-wf2q.c
+++ b/block/bfq-wf2q.c
@@ -744,6 +744,8 @@ __bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
}
#endif
+ /* Matches the smp_wmb() in bfq_group_set_weight. */
+ smp_rmb();
old_st->wsum -= entity->weight;
if (entity->new_weight != entity->orig_weight) {
diff --git a/block/bio.c b/block/bio.c
index 299a0e7651ec..8f0ed6228fc5 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -646,25 +646,20 @@ static inline bool page_is_mergeable(const struct bio_vec *bv,
return true;
}
-/*
- * Check if the @page can be added to the current segment(@bv), and make
- * sure to call it only if page_is_mergeable(@bv, @page) is true
- */
-static bool can_add_page_to_seg(struct request_queue *q,
- struct bio_vec *bv, struct page *page, unsigned len,
- unsigned offset)
+static bool bio_try_merge_pc_page(struct request_queue *q, struct bio *bio,
+ struct page *page, unsigned len, unsigned offset,
+ bool *same_page)
{
+ struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
unsigned long mask = queue_segment_boundary(q);
phys_addr_t addr1 = page_to_phys(bv->bv_page) + bv->bv_offset;
phys_addr_t addr2 = page_to_phys(page) + offset + len - 1;
if ((addr1 | mask) != (addr2 | mask))
return false;
-
if (bv->bv_len + len > queue_max_segment_size(q))
return false;
-
- return true;
+ return __bio_try_merge_page(bio, page, len, offset, same_page);
}
/**
@@ -674,7 +669,7 @@ static bool can_add_page_to_seg(struct request_queue *q,
* @page: page to add
* @len: vec entry length
* @offset: vec entry offset
- * @put_same_page: put the page if it is same with last added page
+ * @same_page: return if the merge happen inside the same page
*
* Attempt to add a page to the bio_vec maplist. This can fail for a
* number of reasons, such as the bio being full or target block device
@@ -685,10 +680,9 @@ static bool can_add_page_to_seg(struct request_queue *q,
*/
static int __bio_add_pc_page(struct request_queue *q, struct bio *bio,
struct page *page, unsigned int len, unsigned int offset,
- bool put_same_page)
+ bool *same_page)
{
struct bio_vec *bvec;
- bool same_page = false;
/*
* cloned bio must not modify vec list
@@ -700,28 +694,16 @@ static int __bio_add_pc_page(struct request_queue *q, struct bio *bio,
return 0;
if (bio->bi_vcnt > 0) {
- bvec = &bio->bi_io_vec[bio->bi_vcnt - 1];
-
- if (page == bvec->bv_page &&
- offset == bvec->bv_offset + bvec->bv_len) {
- if (put_same_page)
- put_page(page);
- bvec->bv_len += len;
- goto done;
- }
+ if (bio_try_merge_pc_page(q, bio, page, len, offset, same_page))
+ return len;
/*
- * If the queue doesn't support SG gaps and adding this
- * offset would create a gap, disallow it.
+ * If the queue doesn't support SG gaps and adding this segment
+ * would create a gap, disallow it.
*/
+ bvec = &bio->bi_io_vec[bio->bi_vcnt - 1];
if (bvec_gap_to_prev(q, bvec, offset))
return 0;
-
- if (page_is_mergeable(bvec, page, len, offset, &same_page) &&
- can_add_page_to_seg(q, bvec, page, len, offset)) {
- bvec->bv_len += len;
- goto done;
- }
}
if (bio_full(bio, len))
@@ -735,7 +717,6 @@ static int __bio_add_pc_page(struct request_queue *q, struct bio *bio,
bvec->bv_len = len;
bvec->bv_offset = offset;
bio->bi_vcnt++;
- done:
bio->bi_iter.bi_size += len;
return len;
}
@@ -743,7 +724,8 @@ static int __bio_add_pc_page(struct request_queue *q, struct bio *bio,
int bio_add_pc_page(struct request_queue *q, struct bio *bio,
struct page *page, unsigned int len, unsigned int offset)
{
- return __bio_add_pc_page(q, bio, page, len, offset, false);
+ bool same_page = false;
+ return __bio_add_pc_page(q, bio, page, len, offset, &same_page);
}
EXPORT_SYMBOL(bio_add_pc_page);
@@ -806,6 +788,9 @@ void __bio_add_page(struct bio *bio, struct page *page,
bio->bi_iter.bi_size += len;
bio->bi_vcnt++;
+
+ if (!bio_flagged(bio, BIO_WORKINGSET) && unlikely(PageWorkingset(page)))
+ bio_set_flag(bio, BIO_WORKINGSET);
}
EXPORT_SYMBOL_GPL(__bio_add_page);
@@ -1384,13 +1369,17 @@ struct bio *bio_map_user_iov(struct request_queue *q,
for (j = 0; j < npages; j++) {
struct page *page = pages[j];
unsigned int n = PAGE_SIZE - offs;
+ bool same_page = false;
if (n > bytes)
n = bytes;
if (!__bio_add_pc_page(q, bio, page, n, offs,
- true))
+ &same_page)) {
+ if (same_page)
+ put_page(page);
break;
+ }
added += n;
bytes -= n;
@@ -1521,7 +1510,6 @@ struct bio *bio_map_kern(struct request_queue *q, void *data, unsigned int len,
bio->bi_end_io = bio_map_kern_endio;
return bio;
}
-EXPORT_SYMBOL(bio_map_kern);
static void bio_copy_kern_endio(struct bio *bio)
{
@@ -1842,8 +1830,8 @@ EXPORT_SYMBOL(bio_endio);
* @bio, and updates @bio to represent the remaining sectors.
*
* Unless this is a discard request the newly allocated bio will point
- * to @bio's bi_io_vec; it is the caller's responsibility to ensure that
- * @bio is not freed before the split.
+ * to @bio's bi_io_vec. It is the caller's responsibility to ensure that
+ * neither @bio nor @bs are freed before the split bio.
*/
struct bio *bio_split(struct bio *bio, int sectors,
gfp_t gfp, struct bio_set *bs)
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 55a7dc227dfb..b6f20be0fc78 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -175,7 +175,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
continue;
/* alloc per-policy data and attach it to blkg */
- pd = pol->pd_alloc_fn(gfp_mask, q->node);
+ pd = pol->pd_alloc_fn(gfp_mask, q, blkcg);
if (!pd)
goto err_free;
@@ -755,6 +755,44 @@ static struct blkcg_gq *blkg_lookup_check(struct blkcg *blkcg,
/**
* blkg_conf_prep - parse and prepare for per-blkg config update
+ * @inputp: input string pointer
+ *
+ * Parse the device node prefix part, MAJ:MIN, of per-blkg config update
+ * from @input and get and return the matching gendisk. *@inputp is
+ * updated to point past the device node prefix. Returns an ERR_PTR()
+ * value on error.
+ *
+ * Use this function iff blkg_conf_prep() can't be used for some reason.
+ */
+struct gendisk *blkcg_conf_get_disk(char **inputp)
+{
+ char *input = *inputp;
+ unsigned int major, minor;
+ struct gendisk *disk;
+ int key_len, part;
+
+ if (sscanf(input, "%u:%u%n", &major, &minor, &key_len) != 2)
+ return ERR_PTR(-EINVAL);
+
+ input += key_len;
+ if (!isspace(*input))
+ return ERR_PTR(-EINVAL);
+ input = skip_spaces(input);
+
+ disk = get_gendisk(MKDEV(major, minor), &part);
+ if (!disk)
+ return ERR_PTR(-ENODEV);
+ if (part) {
+ put_disk_and_module(disk);
+ return ERR_PTR(-ENODEV);
+ }
+
+ *inputp = input;
+ return disk;
+}
+
+/**
+ * blkg_conf_prep - parse and prepare for per-blkg config update
* @blkcg: target block cgroup
* @pol: target policy
* @input: input string
@@ -772,25 +810,11 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
struct gendisk *disk;
struct request_queue *q;
struct blkcg_gq *blkg;
- unsigned int major, minor;
- int key_len, part, ret;
- char *body;
-
- if (sscanf(input, "%u:%u%n", &major, &minor, &key_len) != 2)
- return -EINVAL;
-
- body = input + key_len;
- if (!isspace(*body))
- return -EINVAL;
- body = skip_spaces(body);
+ int ret;
- disk = get_gendisk(MKDEV(major, minor), &part);
- if (!disk)
- return -ENODEV;
- if (part) {
- ret = -ENODEV;
- goto fail;
- }
+ disk = blkcg_conf_get_disk(&input);
+ if (IS_ERR(disk))
+ return PTR_ERR(disk);
q = disk->queue;
@@ -856,7 +880,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
success:
ctx->disk = disk;
ctx->blkg = blkg;
- ctx->body = body;
+ ctx->body = input;
return 0;
fail_unlock:
@@ -876,6 +900,7 @@ fail:
}
return ret;
}
+EXPORT_SYMBOL_GPL(blkg_conf_prep);
/**
* blkg_conf_finish - finish up per-blkg config update
@@ -891,6 +916,7 @@ void blkg_conf_finish(struct blkg_conf_ctx *ctx)
rcu_read_unlock();
put_disk_and_module(ctx->disk);
}
+EXPORT_SYMBOL_GPL(blkg_conf_finish);
static int blkcg_print_stat(struct seq_file *sf, void *v)
{
@@ -1346,7 +1372,7 @@ int blkcg_activate_policy(struct request_queue *q,
blk_mq_freeze_queue(q);
pd_prealloc:
if (!pd_prealloc) {
- pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q->node);
+ pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q, &blkcg_root);
if (!pd_prealloc) {
ret = -ENOMEM;
goto out_bypass_end;
@@ -1362,7 +1388,7 @@ pd_prealloc:
if (blkg->pd[pol->plid])
continue;
- pd = pol->pd_alloc_fn(GFP_NOWAIT | __GFP_NOWARN, q->node);
+ pd = pol->pd_alloc_fn(GFP_NOWAIT | __GFP_NOWARN, q, &blkcg_root);
if (!pd)
swap(pd, pd_prealloc);
if (!pd) {
@@ -1475,7 +1501,8 @@ int blkcg_policy_register(struct blkcg_policy *pol)
blkcg->cpd[pol->plid] = cpd;
cpd->blkcg = blkcg;
cpd->plid = pol->plid;
- pol->cpd_init_fn(cpd);
+ if (pol->cpd_init_fn)
+ pol->cpd_init_fn(cpd);
}
}
diff --git a/block/blk-core.c b/block/blk-core.c
index d0cc6e14d2f0..875e8d105067 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -36,6 +36,7 @@
#include <linux/blk-cgroup.h>
#include <linux/debugfs.h>
#include <linux/bpf.h>
+#include <linux/psi.h>
#define CREATE_TRACE_POINTS
#include <trace/events/block.h>
@@ -129,6 +130,7 @@ static const char *const blk_op_name[] = {
REQ_OP_NAME(DISCARD),
REQ_OP_NAME(SECURE_ERASE),
REQ_OP_NAME(ZONE_RESET),
+ REQ_OP_NAME(ZONE_RESET_ALL),
REQ_OP_NAME(WRITE_SAME),
REQ_OP_NAME(WRITE_ZEROES),
REQ_OP_NAME(SCSI_IN),
@@ -344,7 +346,8 @@ void blk_cleanup_queue(struct request_queue *q)
/*
* Drain all requests queued before DYING marking. Set DEAD flag to
- * prevent that q->request_fn() gets invoked after draining finished.
+ * prevent that blk_mq_run_hw_queues() accesses the hardware queues
+ * after draining finished.
*/
blk_freeze_queue(q);
@@ -479,7 +482,6 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
if (!q)
return NULL;
- INIT_LIST_HEAD(&q->queue_head);
q->last_merge = NULL;
q->id = ida_simple_get(&blk_queue_ida, 0, 0, gfp_mask);
@@ -518,6 +520,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
mutex_init(&q->blk_trace_mutex);
#endif
mutex_init(&q->sysfs_lock);
+ mutex_init(&q->sysfs_dir_lock);
spin_lock_init(&q->queue_lock);
init_waitqueue_head(&q->mq_freeze_wq);
@@ -601,6 +604,7 @@ bool bio_attempt_back_merge(struct request *req, struct bio *bio,
return false;
trace_block_bio_backmerge(req->q, req, bio);
+ rq_qos_merge(req->q, req, bio);
if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
blk_rq_set_mixed_merge(req);
@@ -622,6 +626,7 @@ bool bio_attempt_front_merge(struct request *req, struct bio *bio,
return false;
trace_block_bio_frontmerge(req->q, req, bio);
+ rq_qos_merge(req->q, req, bio);
if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
blk_rq_set_mixed_merge(req);
@@ -647,6 +652,8 @@ bool bio_attempt_discard_merge(struct request_queue *q, struct request *req,
blk_rq_get_max_sectors(req, blk_rq_pos(req)))
goto no_merge;
+ rq_qos_merge(q, req, bio);
+
req->biotail->bi_next = bio;
req->biotail = bio;
req->__data_len += bio->bi_iter.bi_size;
@@ -931,6 +938,10 @@ generic_make_request_checks(struct bio *bio)
if (!blk_queue_is_zoned(q))
goto not_supported;
break;
+ case REQ_OP_ZONE_RESET_ALL:
+ if (!blk_queue_is_zoned(q) || !blk_queue_zone_resetall(q))
+ goto not_supported;
+ break;
case REQ_OP_WRITE_ZEROES:
if (!q->limits.max_write_zeroes_sectors)
goto not_supported;
@@ -1128,6 +1139,10 @@ EXPORT_SYMBOL_GPL(direct_make_request);
*/
blk_qc_t submit_bio(struct bio *bio)
{
+ bool workingset_read = false;
+ unsigned long pflags;
+ blk_qc_t ret;
+
if (blkcg_punt_bio_submit(bio))
return BLK_QC_T_NONE;
@@ -1146,6 +1161,8 @@ blk_qc_t submit_bio(struct bio *bio)
if (op_is_write(bio_op(bio))) {
count_vm_events(PGPGOUT, count);
} else {
+ if (bio_flagged(bio, BIO_WORKINGSET))
+ workingset_read = true;
task_io_account_read(bio->bi_iter.bi_size);
count_vm_events(PGPGIN, count);
}
@@ -1160,7 +1177,21 @@ blk_qc_t submit_bio(struct bio *bio)
}
}
- return generic_make_request(bio);
+ /*
+ * If we're reading data that is part of the userspace
+ * workingset, count submission time as memory stall. When the
+ * device is congested, or the submitting cgroup IO-throttled,
+ * submission can be a significant part of overall IO time.
+ */
+ if (workingset_read)
+ psi_memstall_enter(&pflags);
+
+ ret = generic_make_request(bio);
+
+ if (workingset_read)
+ psi_memstall_leave(&pflags);
+
+ return ret;
}
EXPORT_SYMBOL(submit_bio);
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
new file mode 100644
index 000000000000..3b39deb8b9f8
--- /dev/null
+++ b/block/blk-iocost.c
@@ -0,0 +1,2457 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * IO cost model based controller.
+ *
+ * Copyright (C) 2019 Tejun Heo <tj@kernel.org>
+ * Copyright (C) 2019 Andy Newell <newella@fb.com>
+ * Copyright (C) 2019 Facebook
+ *
+ * One challenge of controlling IO resources is the lack of trivially
+ * observable cost metric. This is distinguished from CPU and memory where
+ * wallclock time and the number of bytes can serve as accurate enough
+ * approximations.
+ *
+ * Bandwidth and iops are the most commonly used metrics for IO devices but
+ * depending on the type and specifics of the device, different IO patterns
+ * easily lead to multiple orders of magnitude variations rendering them
+ * useless for the purpose of IO capacity distribution. While on-device
+ * time, with a lot of clutches, could serve as a useful approximation for
+ * non-queued rotational devices, this is no longer viable with modern
+ * devices, even the rotational ones.
+ *
+ * While there is no cost metric we can trivially observe, it isn't a
+ * complete mystery. For example, on a rotational device, seek cost
+ * dominates while a contiguous transfer contributes a smaller amount
+ * proportional to the size. If we can characterize at least the relative
+ * costs of these different types of IOs, it should be possible to
+ * implement a reasonable work-conserving proportional IO resource
+ * distribution.
+ *
+ * 1. IO Cost Model
+ *
+ * IO cost model estimates the cost of an IO given its basic parameters and
+ * history (e.g. the end sector of the last IO). The cost is measured in
+ * device time. If a given IO is estimated to cost 10ms, the device should
+ * be able to process ~100 of those IOs in a second.
+ *
+ * Currently, there's only one builtin cost model - linear. Each IO is
+ * classified as sequential or random and given a base cost accordingly.
+ * On top of that, a size cost proportional to the length of the IO is
+ * added. While simple, this model captures the operational
+ * characteristics of a wide varienty of devices well enough. Default
+ * paramters for several different classes of devices are provided and the
+ * parameters can be configured from userspace via
+ * /sys/fs/cgroup/io.cost.model.
+ *
+ * If needed, tools/cgroup/iocost_coef_gen.py can be used to generate
+ * device-specific coefficients.
+ *
+ * If needed, tools/cgroup/iocost_coef_gen.py can be used to generate
+ * device-specific coefficients.
+ *
+ * 2. Control Strategy
+ *
+ * The device virtual time (vtime) is used as the primary control metric.
+ * The control strategy is composed of the following three parts.
+ *
+ * 2-1. Vtime Distribution
+ *
+ * When a cgroup becomes active in terms of IOs, its hierarchical share is
+ * calculated. Please consider the following hierarchy where the numbers
+ * inside parentheses denote the configured weights.
+ *
+ * root
+ * / \
+ * A (w:100) B (w:300)
+ * / \
+ * A0 (w:100) A1 (w:100)
+ *
+ * If B is idle and only A0 and A1 are actively issuing IOs, as the two are
+ * of equal weight, each gets 50% share. If then B starts issuing IOs, B
+ * gets 300/(100+300) or 75% share, and A0 and A1 equally splits the rest,
+ * 12.5% each. The distribution mechanism only cares about these flattened
+ * shares. They're called hweights (hierarchical weights) and always add
+ * upto 1 (HWEIGHT_WHOLE).
+ *
+ * A given cgroup's vtime runs slower in inverse proportion to its hweight.
+ * For example, with 12.5% weight, A0's time runs 8 times slower (100/12.5)
+ * against the device vtime - an IO which takes 10ms on the underlying
+ * device is considered to take 80ms on A0.
+ *
+ * This constitutes the basis of IO capacity distribution. Each cgroup's
+ * vtime is running at a rate determined by its hweight. A cgroup tracks
+ * the vtime consumed by past IOs and can issue a new IO iff doing so
+ * wouldn't outrun the current device vtime. Otherwise, the IO is
+ * suspended until the vtime has progressed enough to cover it.
+ *
+ * 2-2. Vrate Adjustment
+ *
+ * It's unrealistic to expect the cost model to be perfect. There are too
+ * many devices and even on the same device the overall performance
+ * fluctuates depending on numerous factors such as IO mixture and device
+ * internal garbage collection. The controller needs to adapt dynamically.
+ *
+ * This is achieved by adjusting the overall IO rate according to how busy
+ * the device is. If the device becomes overloaded, we're sending down too
+ * many IOs and should generally slow down. If there are waiting issuers
+ * but the device isn't saturated, we're issuing too few and should
+ * generally speed up.
+ *
+ * To slow down, we lower the vrate - the rate at which the device vtime
+ * passes compared to the wall clock. For example, if the vtime is running
+ * at the vrate of 75%, all cgroups added up would only be able to issue
+ * 750ms worth of IOs per second, and vice-versa for speeding up.
+ *
+ * Device business is determined using two criteria - rq wait and
+ * completion latencies.
+ *
+ * When a device gets saturated, the on-device and then the request queues
+ * fill up and a bio which is ready to be issued has to wait for a request
+ * to become available. When this delay becomes noticeable, it's a clear
+ * indication that the device is saturated and we lower the vrate. This
+ * saturation signal is fairly conservative as it only triggers when both
+ * hardware and software queues are filled up, and is used as the default
+ * busy signal.
+ *
+ * As devices can have deep queues and be unfair in how the queued commands
+ * are executed, soley depending on rq wait may not result in satisfactory
+ * control quality. For a better control quality, completion latency QoS
+ * parameters can be configured so that the device is considered saturated
+ * if N'th percentile completion latency rises above the set point.
+ *
+ * The completion latency requirements are a function of both the
+ * underlying device characteristics and the desired IO latency quality of
+ * service. There is an inherent trade-off - the tighter the latency QoS,
+ * the higher the bandwidth lossage. Latency QoS is disabled by default
+ * and can be set through /sys/fs/cgroup/io.cost.qos.
+ *
+ * 2-3. Work Conservation
+ *
+ * Imagine two cgroups A and B with equal weights. A is issuing a small IO
+ * periodically while B is sending out enough parallel IOs to saturate the
+ * device on its own. Let's say A's usage amounts to 100ms worth of IO
+ * cost per second, i.e., 10% of the device capacity. The naive
+ * distribution of half and half would lead to 60% utilization of the
+ * device, a significant reduction in the total amount of work done
+ * compared to free-for-all competition. This is too high a cost to pay
+ * for IO control.
+ *
+ * To conserve the total amount of work done, we keep track of how much
+ * each active cgroup is actually using and yield part of its weight if
+ * there are other cgroups which can make use of it. In the above case,
+ * A's weight will be lowered so that it hovers above the actual usage and
+ * B would be able to use the rest.
+ *
+ * As we don't want to penalize a cgroup for donating its weight, the
+ * surplus weight adjustment factors in a margin and has an immediate
+ * snapback mechanism in case the cgroup needs more IO vtime for itself.
+ *
+ * Note that adjusting down surplus weights has the same effects as
+ * accelerating vtime for other cgroups and work conservation can also be
+ * implemented by adjusting vrate dynamically. However, squaring who can
+ * donate and should take back how much requires hweight propagations
+ * anyway making it easier to implement and understand as a separate
+ * mechanism.
+ *
+ * 3. Monitoring
+ *
+ * Instead of debugfs or other clumsy monitoring mechanisms, this
+ * controller uses a drgn based monitoring script -
+ * tools/cgroup/iocost_monitor.py. For details on drgn, please see
+ * https://github.com/osandov/drgn. The ouput looks like the following.
+ *
+ * sdb RUN per=300ms cur_per=234.218:v203.695 busy= +1 vrate= 62.12%
+ * active weight hweight% inflt% dbt delay usages%
+ * test/a * 50/ 50 33.33/ 33.33 27.65 2 0*041 033:033:033
+ * test/b * 100/ 100 66.67/ 66.67 17.56 0 0*000 066:079:077
+ *
+ * - per : Timer period
+ * - cur_per : Internal wall and device vtime clock
+ * - vrate : Device virtual time rate against wall clock
+ * - weight : Surplus-adjusted and configured weights
+ * - hweight : Surplus-adjusted and configured hierarchical weights
+ * - inflt : The percentage of in-flight IO cost at the end of last period
+ * - del_ms : Deferred issuer delay induction level and duration
+ * - usages : Usage history
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/timer.h>
+#include <linux/time64.h>
+#include <linux/parser.h>
+#include <linux/sched/signal.h>
+#include <linux/blk-cgroup.h>
+#include "blk-rq-qos.h"
+#include "blk-stat.h"
+#include "blk-wbt.h"
+
+#ifdef CONFIG_TRACEPOINTS
+
+/* copied from TRACE_CGROUP_PATH, see cgroup-internal.h */
+#define TRACE_IOCG_PATH_LEN 1024
+static DEFINE_SPINLOCK(trace_iocg_path_lock);
+static char trace_iocg_path[TRACE_IOCG_PATH_LEN];
+
+#define TRACE_IOCG_PATH(type, iocg, ...) \
+ do { \
+ unsigned long flags; \
+ if (trace_iocost_##type##_enabled()) { \
+ spin_lock_irqsave(&trace_iocg_path_lock, flags); \
+ cgroup_path(iocg_to_blkg(iocg)->blkcg->css.cgroup, \
+ trace_iocg_path, TRACE_IOCG_PATH_LEN); \
+ trace_iocost_##type(iocg, trace_iocg_path, \
+ ##__VA_ARGS__); \
+ spin_unlock_irqrestore(&trace_iocg_path_lock, flags); \
+ } \
+ } while (0)
+
+#else /* CONFIG_TRACE_POINTS */
+#define TRACE_IOCG_PATH(type, iocg, ...) do { } while (0)
+#endif /* CONFIG_TRACE_POINTS */
+
+enum {
+ MILLION = 1000000,
+
+ /* timer period is calculated from latency requirements, bound it */
+ MIN_PERIOD = USEC_PER_MSEC,
+ MAX_PERIOD = USEC_PER_SEC,
+
+ /*
+ * A cgroup's vtime can run 50% behind the device vtime, which
+ * serves as its IO credit buffer. Surplus weight adjustment is
+ * immediately canceled if the vtime margin runs below 10%.
+ */
+ MARGIN_PCT = 50,
+ INUSE_MARGIN_PCT = 10,
+
+ /* Have some play in waitq timer operations */
+ WAITQ_TIMER_MARGIN_PCT = 5,
+
+ /*
+ * vtime can wrap well within a reasonable uptime when vrate is
+ * consistently raised. Don't trust recorded cgroup vtime if the
+ * period counter indicates that it's older than 5mins.
+ */
+ VTIME_VALID_DUR = 300 * USEC_PER_SEC,
+
+ /*
+ * Remember the past three non-zero usages and use the max for
+ * surplus calculation. Three slots guarantee that we remember one
+ * full period usage from the last active stretch even after
+ * partial deactivation and re-activation periods. Don't start
+ * giving away weight before collecting two data points to prevent
+ * hweight adjustments based on one partial activation period.
+ */
+ NR_USAGE_SLOTS = 3,
+ MIN_VALID_USAGES = 2,
+
+ /* 1/64k is granular enough and can easily be handled w/ u32 */
+ HWEIGHT_WHOLE = 1 << 16,
+
+ /*
+ * As vtime is used to calculate the cost of each IO, it needs to
+ * be fairly high precision. For example, it should be able to
+ * represent the cost of a single page worth of discard with
+ * suffificient accuracy. At the same time, it should be able to
+ * represent reasonably long enough durations to be useful and
+ * convenient during operation.
+ *
+ * 1s worth of vtime is 2^37. This gives us both sub-nanosecond
+ * granularity and days of wrap-around time even at extreme vrates.
+ */
+ VTIME_PER_SEC_SHIFT = 37,
+ VTIME_PER_SEC = 1LLU << VTIME_PER_SEC_SHIFT,
+ VTIME_PER_USEC = VTIME_PER_SEC / USEC_PER_SEC,
+
+ /* bound vrate adjustments within two orders of magnitude */
+ VRATE_MIN_PPM = 10000, /* 1% */
+ VRATE_MAX_PPM = 100000000, /* 10000% */
+
+ VRATE_MIN = VTIME_PER_USEC * VRATE_MIN_PPM / MILLION,
+ VRATE_CLAMP_ADJ_PCT = 4,
+
+ /* if IOs end up waiting for requests, issue less */
+ RQ_WAIT_BUSY_PCT = 5,
+
+ /* unbusy hysterisis */
+ UNBUSY_THR_PCT = 75,
+
+ /* don't let cmds which take a very long time pin lagging for too long */
+ MAX_LAGGING_PERIODS = 10,
+
+ /*
+ * If usage% * 1.25 + 2% is lower than hweight% by more than 3%,
+ * donate the surplus.
+ */
+ SURPLUS_SCALE_PCT = 125, /* * 125% */
+ SURPLUS_SCALE_ABS = HWEIGHT_WHOLE / 50, /* + 2% */
+ SURPLUS_MIN_ADJ_DELTA = HWEIGHT_WHOLE / 33, /* 3% */
+
+ /* switch iff the conditions are met for longer than this */
+ AUTOP_CYCLE_NSEC = 10LLU * NSEC_PER_SEC,
+
+ /*
+ * Count IO size in 4k pages. The 12bit shift helps keeping
+ * size-proportional components of cost calculation in closer
+ * numbers of digits to per-IO cost components.
+ */
+ IOC_PAGE_SHIFT = 12,
+ IOC_PAGE_SIZE = 1 << IOC_PAGE_SHIFT,
+ IOC_SECT_TO_PAGE_SHIFT = IOC_PAGE_SHIFT - SECTOR_SHIFT,
+
+ /* if apart further than 16M, consider randio for linear model */
+ LCOEF_RANDIO_PAGES = 4096,
+};
+
+enum ioc_running {
+ IOC_IDLE,
+ IOC_RUNNING,
+ IOC_STOP,
+};
+
+/* io.cost.qos controls including per-dev enable of the whole controller */
+enum {
+ QOS_ENABLE,
+ QOS_CTRL,
+ NR_QOS_CTRL_PARAMS,
+};
+
+/* io.cost.qos params */
+enum {
+ QOS_RPPM,
+ QOS_RLAT,
+ QOS_WPPM,
+ QOS_WLAT,
+ QOS_MIN,
+ QOS_MAX,
+ NR_QOS_PARAMS,
+};
+
+/* io.cost.model controls */
+enum {
+ COST_CTRL,
+ COST_MODEL,
+ NR_COST_CTRL_PARAMS,
+};
+
+/* builtin linear cost model coefficients */
+enum {
+ I_LCOEF_RBPS,
+ I_LCOEF_RSEQIOPS,
+ I_LCOEF_RRANDIOPS,
+ I_LCOEF_WBPS,
+ I_LCOEF_WSEQIOPS,
+ I_LCOEF_WRANDIOPS,
+ NR_I_LCOEFS,
+};
+
+enum {
+ LCOEF_RPAGE,
+ LCOEF_RSEQIO,
+ LCOEF_RRANDIO,
+ LCOEF_WPAGE,
+ LCOEF_WSEQIO,
+ LCOEF_WRANDIO,
+ NR_LCOEFS,
+};
+
+enum {
+ AUTOP_INVALID,
+ AUTOP_HDD,
+ AUTOP_SSD_QD1,
+ AUTOP_SSD_DFL,
+ AUTOP_SSD_FAST,
+};
+
+struct ioc_gq;
+
+struct ioc_params {
+ u32 qos[NR_QOS_PARAMS];
+ u64 i_lcoefs[NR_I_LCOEFS];
+ u64 lcoefs[NR_LCOEFS];
+ u32 too_fast_vrate_pct;
+ u32 too_slow_vrate_pct;
+};
+
+struct ioc_missed {
+ u32 nr_met;
+ u32 nr_missed;
+ u32 last_met;
+ u32 last_missed;
+};
+
+struct ioc_pcpu_stat {
+ struct ioc_missed missed[2];
+
+ u64 rq_wait_ns;
+ u64 last_rq_wait_ns;
+};
+
+/* per device */
+struct ioc {
+ struct rq_qos rqos;
+
+ bool enabled;
+
+ struct ioc_params params;
+ u32 period_us;
+ u32 margin_us;
+ u64 vrate_min;
+ u64 vrate_max;
+
+ spinlock_t lock;
+ struct timer_list timer;
+ struct list_head active_iocgs; /* active cgroups */
+ struct ioc_pcpu_stat __percpu *pcpu_stat;
+
+ enum ioc_running running;
+ atomic64_t vtime_rate;
+
+ seqcount_t period_seqcount;
+ u32 period_at; /* wallclock starttime */
+ u64 period_at_vtime; /* vtime starttime */
+
+ atomic64_t cur_period; /* inc'd each period */
+ int busy_level; /* saturation history */
+
+ u64 inuse_margin_vtime;
+ bool weights_updated;
+ atomic_t hweight_gen; /* for lazy hweights */
+
+ u64 autop_too_fast_at;
+ u64 autop_too_slow_at;
+ int autop_idx;
+ bool user_qos_params:1;
+ bool user_cost_model:1;
+};
+
+/* per device-cgroup pair */
+struct ioc_gq {
+ struct blkg_policy_data pd;
+ struct ioc *ioc;
+
+ /*
+ * A iocg can get its weight from two sources - an explicit
+ * per-device-cgroup configuration or the default weight of the
+ * cgroup. `cfg_weight` is the explicit per-device-cgroup
+ * configuration. `weight` is the effective considering both
+ * sources.
+ *
+ * When an idle cgroup becomes active its `active` goes from 0 to
+ * `weight`. `inuse` is the surplus adjusted active weight.
+ * `active` and `inuse` are used to calculate `hweight_active` and
+ * `hweight_inuse`.
+ *
+ * `last_inuse` remembers `inuse` while an iocg is idle to persist
+ * surplus adjustments.
+ */
+ u32 cfg_weight;
+ u32 weight;
+ u32 active;
+ u32 inuse;
+ u32 last_inuse;
+
+ sector_t cursor; /* to detect randio */
+
+ /*
+ * `vtime` is this iocg's vtime cursor which progresses as IOs are
+ * issued. If lagging behind device vtime, the delta represents
+ * the currently available IO budget. If runnning ahead, the
+ * overage.
+ *
+ * `vtime_done` is the same but progressed on completion rather
+ * than issue. The delta behind `vtime` represents the cost of
+ * currently in-flight IOs.
+ *
+ * `last_vtime` is used to remember `vtime` at the end of the last
+ * period to calculate utilization.
+ */
+ atomic64_t vtime;
+ atomic64_t done_vtime;
+ atomic64_t abs_vdebt;
+ u64 last_vtime;
+
+ /*
+ * The period this iocg was last active in. Used for deactivation
+ * and invalidating `vtime`.
+ */
+ atomic64_t active_period;
+ struct list_head active_list;
+
+ /* see __propagate_active_weight() and current_hweight() for details */
+ u64 child_active_sum;
+ u64 child_inuse_sum;
+ int hweight_gen;
+ u32 hweight_active;
+ u32 hweight_inuse;
+ bool has_surplus;
+
+ struct wait_queue_head waitq;
+ struct hrtimer waitq_timer;
+ struct hrtimer delay_timer;
+
+ /* usage is recorded as fractions of HWEIGHT_WHOLE */
+ int usage_idx;
+ u32 usages[NR_USAGE_SLOTS];
+
+ /* this iocg's depth in the hierarchy and ancestors including self */
+ int level;
+ struct ioc_gq *ancestors[];
+};
+
+/* per cgroup */
+struct ioc_cgrp {
+ struct blkcg_policy_data cpd;
+ unsigned int dfl_weight;
+};
+
+struct ioc_now {
+ u64 now_ns;
+ u32 now;
+ u64 vnow;
+ u64 vrate;
+};
+
+struct iocg_wait {
+ struct wait_queue_entry wait;
+ struct bio *bio;
+ u64 abs_cost;
+ bool committed;
+};
+
+struct iocg_wake_ctx {
+ struct ioc_gq *iocg;
+ u32 hw_inuse;
+ s64 vbudget;
+};
+
+static const struct ioc_params autop[] = {
+ [AUTOP_HDD] = {
+ .qos = {
+ [QOS_RLAT] = 50000, /* 50ms */
+ [QOS_WLAT] = 50000,
+ [QOS_MIN] = VRATE_MIN_PPM,
+ [QOS_MAX] = VRATE_MAX_PPM,
+ },
+ .i_lcoefs = {
+ [I_LCOEF_RBPS] = 174019176,
+ [I_LCOEF_RSEQIOPS] = 41708,
+ [I_LCOEF_RRANDIOPS] = 370,
+ [I_LCOEF_WBPS] = 178075866,
+ [I_LCOEF_WSEQIOPS] = 42705,
+ [I_LCOEF_WRANDIOPS] = 378,
+ },
+ },
+ [AUTOP_SSD_QD1] = {
+ .qos = {
+ [QOS_RLAT] = 25000, /* 25ms */
+ [QOS_WLAT] = 25000,
+ [QOS_MIN] = VRATE_MIN_PPM,
+ [QOS_MAX] = VRATE_MAX_PPM,
+ },
+ .i_lcoefs = {
+ [I_LCOEF_RBPS] = 245855193,
+ [I_LCOEF_RSEQIOPS] = 61575,
+ [I_LCOEF_RRANDIOPS] = 6946,
+ [I_LCOEF_WBPS] = 141365009,
+ [I_LCOEF_WSEQIOPS] = 33716,
+ [I_LCOEF_WRANDIOPS] = 26796,
+ },
+ },
+ [AUTOP_SSD_DFL] = {
+ .qos = {
+ [QOS_RLAT] = 25000, /* 25ms */
+ [QOS_WLAT] = 25000,
+ [QOS_MIN] = VRATE_MIN_PPM,
+ [QOS_MAX] = VRATE_MAX_PPM,
+ },
+ .i_lcoefs = {
+ [I_LCOEF_RBPS] = 488636629,
+ [I_LCOEF_RSEQIOPS] = 8932,
+ [I_LCOEF_RRANDIOPS] = 8518,
+ [I_LCOEF_WBPS] = 427891549,
+ [I_LCOEF_WSEQIOPS] = 28755,
+ [I_LCOEF_WRANDIOPS] = 21940,
+ },
+ .too_fast_vrate_pct = 500,
+ },
+ [AUTOP_SSD_FAST] = {
+ .qos = {
+ [QOS_RLAT] = 5000, /* 5ms */
+ [QOS_WLAT] = 5000,
+ [QOS_MIN] = VRATE_MIN_PPM,
+ [QOS_MAX] = VRATE_MAX_PPM,
+ },
+ .i_lcoefs = {
+ [I_LCOEF_RBPS] = 3102524156LLU,
+ [I_LCOEF_RSEQIOPS] = 724816,
+ [I_LCOEF_RRANDIOPS] = 778122,
+ [I_LCOEF_WBPS] = 1742780862LLU,
+ [I_LCOEF_WSEQIOPS] = 425702,
+ [I_LCOEF_WRANDIOPS] = 443193,
+ },
+ .too_slow_vrate_pct = 10,
+ },
+};
+
+/*
+ * vrate adjust percentages indexed by ioc->busy_level. We adjust up on
+ * vtime credit shortage and down on device saturation.
+ */
+static u32 vrate_adj_pct[] =
+ { 0, 0, 0, 0,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 4, 4, 4, 4, 4, 4, 4, 4, 8, 8, 8, 8, 8, 8, 8, 8, 16 };
+
+static struct blkcg_policy blkcg_policy_iocost;
+
+/* accessors and helpers */
+static struct ioc *rqos_to_ioc(struct rq_qos *rqos)
+{
+ return container_of(rqos, struct ioc, rqos);
+}
+
+static struct ioc *q_to_ioc(struct request_queue *q)
+{
+ return rqos_to_ioc(rq_qos_id(q, RQ_QOS_COST));
+}
+
+static const char *q_name(struct request_queue *q)
+{
+ if (test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags))
+ return kobject_name(q->kobj.parent);
+ else
+ return "<unknown>";
+}
+
+static const char __maybe_unused *ioc_name(struct ioc *ioc)
+{
+ return q_name(ioc->rqos.q);
+}
+
+static struct ioc_gq *pd_to_iocg(struct blkg_policy_data *pd)
+{
+ return pd ? container_of(pd, struct ioc_gq, pd) : NULL;
+}
+
+static struct ioc_gq *blkg_to_iocg(struct blkcg_gq *blkg)
+{
+ return pd_to_iocg(blkg_to_pd(blkg, &blkcg_policy_iocost));
+}
+
+static struct blkcg_gq *iocg_to_blkg(struct ioc_gq *iocg)
+{
+ return pd_to_blkg(&iocg->pd);
+}
+
+static struct ioc_cgrp *blkcg_to_iocc(struct blkcg *blkcg)
+{
+ return container_of(blkcg_to_cpd(blkcg, &blkcg_policy_iocost),
+ struct ioc_cgrp, cpd);
+}
+
+/*
+ * Scale @abs_cost to the inverse of @hw_inuse. The lower the hierarchical
+ * weight, the more expensive each IO. Must round up.
+ */
+static u64 abs_cost_to_cost(u64 abs_cost, u32 hw_inuse)
+{
+ return DIV64_U64_ROUND_UP(abs_cost * HWEIGHT_WHOLE, hw_inuse);
+}
+
+/*
+ * The inverse of abs_cost_to_cost(). Must round up.
+ */
+static u64 cost_to_abs_cost(u64 cost, u32 hw_inuse)
+{
+ return DIV64_U64_ROUND_UP(cost * hw_inuse, HWEIGHT_WHOLE);
+}
+
+static void iocg_commit_bio(struct ioc_gq *iocg, struct bio *bio, u64 cost)
+{
+ bio->bi_iocost_cost = cost;
+ atomic64_add(cost, &iocg->vtime);
+}
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/iocost.h>
+
+/* latency Qos params changed, update period_us and all the dependent params */
+static void ioc_refresh_period_us(struct ioc *ioc)
+{
+ u32 ppm, lat, multi, period_us;
+
+ lockdep_assert_held(&ioc->lock);
+
+ /* pick the higher latency target */
+ if (ioc->params.qos[QOS_RLAT] >= ioc->params.qos[QOS_WLAT]) {
+ ppm = ioc->params.qos[QOS_RPPM];
+ lat = ioc->params.qos[QOS_RLAT];
+ } else {
+ ppm = ioc->params.qos[QOS_WPPM];
+ lat = ioc->params.qos[QOS_WLAT];
+ }
+
+ /*
+ * We want the period to be long enough to contain a healthy number
+ * of IOs while short enough for granular control. Define it as a
+ * multiple of the latency target. Ideally, the multiplier should
+ * be scaled according to the percentile so that it would nominally
+ * contain a certain number of requests. Let's be simpler and
+ * scale it linearly so that it's 2x >= pct(90) and 10x at pct(50).
+ */
+ if (ppm)
+ multi = max_t(u32, (MILLION - ppm) / 50000, 2);
+ else
+ multi = 2;
+ period_us = multi * lat;
+ period_us = clamp_t(u32, period_us, MIN_PERIOD, MAX_PERIOD);
+
+ /* calculate dependent params */
+ ioc->period_us = period_us;
+ ioc->margin_us = period_us * MARGIN_PCT / 100;
+ ioc->inuse_margin_vtime = DIV64_U64_ROUND_UP(
+ period_us * VTIME_PER_USEC * INUSE_MARGIN_PCT, 100);
+}
+
+static int ioc_autop_idx(struct ioc *ioc)
+{
+ int idx = ioc->autop_idx;
+ const struct ioc_params *p = &autop[idx];
+ u32 vrate_pct;
+ u64 now_ns;
+
+ /* rotational? */
+ if (!blk_queue_nonrot(ioc->rqos.q))
+ return AUTOP_HDD;
+
+ /* handle SATA SSDs w/ broken NCQ */
+ if (blk_queue_depth(ioc->rqos.q) == 1)
+ return AUTOP_SSD_QD1;
+
+ /* use one of the normal ssd sets */
+ if (idx < AUTOP_SSD_DFL)
+ return AUTOP_SSD_DFL;
+
+ /* if user is overriding anything, maintain what was there */
+ if (ioc->user_qos_params || ioc->user_cost_model)
+ return idx;
+
+ /* step up/down based on the vrate */
+ vrate_pct = div64_u64(atomic64_read(&ioc->vtime_rate) * 100,
+ VTIME_PER_USEC);
+ now_ns = ktime_get_ns();
+
+ if (p->too_fast_vrate_pct && p->too_fast_vrate_pct <= vrate_pct) {
+ if (!ioc->autop_too_fast_at)
+ ioc->autop_too_fast_at = now_ns;
+ if (now_ns - ioc->autop_too_fast_at >= AUTOP_CYCLE_NSEC)
+ return idx + 1;
+ } else {
+ ioc->autop_too_fast_at = 0;
+ }
+
+ if (p->too_slow_vrate_pct && p->too_slow_vrate_pct >= vrate_pct) {
+ if (!ioc->autop_too_slow_at)
+ ioc->autop_too_slow_at = now_ns;
+ if (now_ns - ioc->autop_too_slow_at >= AUTOP_CYCLE_NSEC)
+ return idx - 1;
+ } else {
+ ioc->autop_too_slow_at = 0;
+ }
+
+ return idx;
+}
+
+/*
+ * Take the followings as input
+ *
+ * @bps maximum sequential throughput
+ * @seqiops maximum sequential 4k iops
+ * @randiops maximum random 4k iops
+ *
+ * and calculate the linear model cost coefficients.
+ *
+ * *@page per-page cost 1s / (@bps / 4096)
+ * *@seqio base cost of a seq IO max((1s / @seqiops) - *@page, 0)
+ * @randiops base cost of a rand IO max((1s / @randiops) - *@page, 0)
+ */
+static void calc_lcoefs(u64 bps, u64 seqiops, u64 randiops,
+ u64 *page, u64 *seqio, u64 *randio)
+{
+ u64 v;
+
+ *page = *seqio = *randio = 0;
+
+ if (bps)
+ *page = DIV64_U64_ROUND_UP(VTIME_PER_SEC,
+ DIV_ROUND_UP_ULL(bps, IOC_PAGE_SIZE));
+
+ if (seqiops) {
+ v = DIV64_U64_ROUND_UP(VTIME_PER_SEC, seqiops);
+ if (v > *page)
+ *seqio = v - *page;
+ }
+
+ if (randiops) {
+ v = DIV64_U64_ROUND_UP(VTIME_PER_SEC, randiops);
+ if (v > *page)
+ *randio = v - *page;
+ }
+}
+
+static void ioc_refresh_lcoefs(struct ioc *ioc)
+{
+ u64 *u = ioc->params.i_lcoefs;
+ u64 *c = ioc->params.lcoefs;
+
+ calc_lcoefs(u[I_LCOEF_RBPS], u[I_LCOEF_RSEQIOPS], u[I_LCOEF_RRANDIOPS],
+ &c[LCOEF_RPAGE], &c[LCOEF_RSEQIO], &c[LCOEF_RRANDIO]);
+ calc_lcoefs(u[I_LCOEF_WBPS], u[I_LCOEF_WSEQIOPS], u[I_LCOEF_WRANDIOPS],
+ &c[LCOEF_WPAGE], &c[LCOEF_WSEQIO], &c[LCOEF_WRANDIO]);
+}
+
+static bool ioc_refresh_params(struct ioc *ioc, bool force)
+{
+ const struct ioc_params *p;
+ int idx;
+
+ lockdep_assert_held(&ioc->lock);
+
+ idx = ioc_autop_idx(ioc);
+ p = &autop[idx];
+
+ if (idx == ioc->autop_idx && !force)
+ return false;
+
+ if (idx != ioc->autop_idx)
+ atomic64_set(&ioc->vtime_rate, VTIME_PER_USEC);
+
+ ioc->autop_idx = idx;
+ ioc->autop_too_fast_at = 0;
+ ioc->autop_too_slow_at = 0;
+
+ if (!ioc->user_qos_params)
+ memcpy(ioc->params.qos, p->qos, sizeof(p->qos));
+ if (!ioc->user_cost_model)
+ memcpy(ioc->params.i_lcoefs, p->i_lcoefs, sizeof(p->i_lcoefs));
+
+ ioc_refresh_period_us(ioc);
+ ioc_refresh_lcoefs(ioc);
+
+ ioc->vrate_min = DIV64_U64_ROUND_UP((u64)ioc->params.qos[QOS_MIN] *
+ VTIME_PER_USEC, MILLION);
+ ioc->vrate_max = div64_u64((u64)ioc->params.qos[QOS_MAX] *
+ VTIME_PER_USEC, MILLION);
+
+ return true;
+}
+
+/* take a snapshot of the current [v]time and vrate */
+static void ioc_now(struct ioc *ioc, struct ioc_now *now)
+{
+ unsigned seq;
+
+ now->now_ns = ktime_get();
+ now->now = ktime_to_us(now->now_ns);
+ now->vrate = atomic64_read(&ioc->vtime_rate);
+
+ /*
+ * The current vtime is
+ *
+ * vtime at period start + (wallclock time since the start) * vrate
+ *
+ * As a consistent snapshot of `period_at_vtime` and `period_at` is
+ * needed, they're seqcount protected.
+ */
+ do {
+ seq = read_seqcount_begin(&ioc->period_seqcount);
+ now->vnow = ioc->period_at_vtime +
+ (now->now - ioc->period_at) * now->vrate;
+ } while (read_seqcount_retry(&ioc->period_seqcount, seq));
+}
+
+static void ioc_start_period(struct ioc *ioc, struct ioc_now *now)
+{
+ lockdep_assert_held(&ioc->lock);
+ WARN_ON_ONCE(ioc->running != IOC_RUNNING);
+
+ write_seqcount_begin(&ioc->period_seqcount);
+ ioc->period_at = now->now;
+ ioc->period_at_vtime = now->vnow;
+ write_seqcount_end(&ioc->period_seqcount);
+
+ ioc->timer.expires = jiffies + usecs_to_jiffies(ioc->period_us);
+ add_timer(&ioc->timer);
+}
+
+/*
+ * Update @iocg's `active` and `inuse` to @active and @inuse, update level
+ * weight sums and propagate upwards accordingly.
+ */
+static void __propagate_active_weight(struct ioc_gq *iocg, u32 active, u32 inuse)
+{
+ struct ioc *ioc = iocg->ioc;
+ int lvl;
+
+ lockdep_assert_held(&ioc->lock);
+
+ inuse = min(active, inuse);
+
+ for (lvl = iocg->level - 1; lvl >= 0; lvl--) {
+ struct ioc_gq *parent = iocg->ancestors[lvl];
+ struct ioc_gq *child = iocg->ancestors[lvl + 1];
+ u32 parent_active = 0, parent_inuse = 0;
+
+ /* update the level sums */
+ parent->child_active_sum += (s32)(active - child->active);
+ parent->child_inuse_sum += (s32)(inuse - child->inuse);
+ /* apply the udpates */
+ child->active = active;
+ child->inuse = inuse;
+
+ /*
+ * The delta between inuse and active sums indicates that
+ * that much of weight is being given away. Parent's inuse
+ * and active should reflect the ratio.
+ */
+ if (parent->child_active_sum) {
+ parent_active = parent->weight;
+ parent_inuse = DIV64_U64_ROUND_UP(
+ parent_active * parent->child_inuse_sum,
+ parent->child_active_sum);
+ }
+
+ /* do we need to keep walking up? */
+ if (parent_active == parent->active &&
+ parent_inuse == parent->inuse)
+ break;
+
+ active = parent_active;
+ inuse = parent_inuse;
+ }
+
+ ioc->weights_updated = true;
+}
+
+static void commit_active_weights(struct ioc *ioc)
+{
+ lockdep_assert_held(&ioc->lock);
+
+ if (ioc->weights_updated) {
+ /* paired with rmb in current_hweight(), see there */
+ smp_wmb();
+ atomic_inc(&ioc->hweight_gen);
+ ioc->weights_updated = false;
+ }
+}
+
+static void propagate_active_weight(struct ioc_gq *iocg, u32 active, u32 inuse)
+{
+ __propagate_active_weight(iocg, active, inuse);
+ commit_active_weights(iocg->ioc);
+}
+
+static void current_hweight(struct ioc_gq *iocg, u32 *hw_activep, u32 *hw_inusep)
+{
+ struct ioc *ioc = iocg->ioc;
+ int lvl;
+ u32 hwa, hwi;
+ int ioc_gen;
+
+ /* hot path - if uptodate, use cached */
+ ioc_gen = atomic_read(&ioc->hweight_gen);
+ if (ioc_gen == iocg->hweight_gen)
+ goto out;
+
+ /*
+ * Paired with wmb in commit_active_weights(). If we saw the
+ * updated hweight_gen, all the weight updates from
+ * __propagate_active_weight() are visible too.
+ *
+ * We can race with weight updates during calculation and get it
+ * wrong. However, hweight_gen would have changed and a future
+ * reader will recalculate and we're guaranteed to discard the
+ * wrong result soon.
+ */
+ smp_rmb();
+
+ hwa = hwi = HWEIGHT_WHOLE;
+ for (lvl = 0; lvl <= iocg->level - 1; lvl++) {
+ struct ioc_gq *parent = iocg->ancestors[lvl];
+ struct ioc_gq *child = iocg->ancestors[lvl + 1];
+ u32 active_sum = READ_ONCE(parent->child_active_sum);
+ u32 inuse_sum = READ_ONCE(parent->child_inuse_sum);
+ u32 active = READ_ONCE(child->active);
+ u32 inuse = READ_ONCE(child->inuse);
+
+ /* we can race with deactivations and either may read as zero */
+ if (!active_sum || !inuse_sum)
+ continue;
+
+ active_sum = max(active, active_sum);
+ hwa = hwa * active / active_sum; /* max 16bits * 10000 */
+
+ inuse_sum = max(inuse, inuse_sum);
+ hwi = hwi * inuse / inuse_sum; /* max 16bits * 10000 */
+ }
+
+ iocg->hweight_active = max_t(u32, hwa, 1);
+ iocg->hweight_inuse = max_t(u32, hwi, 1);
+ iocg->hweight_gen = ioc_gen;
+out:
+ if (hw_activep)
+ *hw_activep = iocg->hweight_active;
+ if (hw_inusep)
+ *hw_inusep = iocg->hweight_inuse;
+}
+
+static void weight_updated(struct ioc_gq *iocg)
+{
+ struct ioc *ioc = iocg->ioc;
+ struct blkcg_gq *blkg = iocg_to_blkg(iocg);
+ struct ioc_cgrp *iocc = blkcg_to_iocc(blkg->blkcg);
+ u32 weight;
+
+ lockdep_assert_held(&ioc->lock);
+
+ weight = iocg->cfg_weight ?: iocc->dfl_weight;
+ if (weight != iocg->weight && iocg->active)
+ propagate_active_weight(iocg, weight,
+ DIV64_U64_ROUND_UP(iocg->inuse * weight, iocg->weight));
+ iocg->weight = weight;
+}
+
+static bool iocg_activate(struct ioc_gq *iocg, struct ioc_now *now)
+{
+ struct ioc *ioc = iocg->ioc;
+ u64 last_period, cur_period, max_period_delta;
+ u64 vtime, vmargin, vmin;
+ int i;
+
+ /*
+ * If seem to be already active, just update the stamp to tell the
+ * timer that we're still active. We don't mind occassional races.
+ */
+ if (!list_empty(&iocg->active_list)) {
+ ioc_now(ioc, now);
+ cur_period = atomic64_read(&ioc->cur_period);
+ if (atomic64_read(&iocg->active_period) != cur_period)
+ atomic64_set(&iocg->active_period, cur_period);
+ return true;
+ }
+
+ /* racy check on internal node IOs, treat as root level IOs */
+ if (iocg->child_active_sum)
+ return false;
+
+ spin_lock_irq(&ioc->lock);
+
+ ioc_now(ioc, now);
+
+ /* update period */
+ cur_period = atomic64_read(&ioc->cur_period);
+ last_period = atomic64_read(&iocg->active_period);
+ atomic64_set(&iocg->active_period, cur_period);
+
+ /* already activated or breaking leaf-only constraint? */
+ for (i = iocg->level; i > 0; i--)
+ if (!list_empty(&iocg->active_list))
+ goto fail_unlock;
+ if (iocg->child_active_sum)
+ goto fail_unlock;
+
+ /*
+ * vtime may wrap when vrate is raised substantially due to
+ * underestimated IO costs. Look at the period and ignore its
+ * vtime if the iocg has been idle for too long. Also, cap the
+ * budget it can start with to the margin.
+ */
+ max_period_delta = DIV64_U64_ROUND_UP(VTIME_VALID_DUR, ioc->period_us);
+ vtime = atomic64_read(&iocg->vtime);
+ vmargin = ioc->margin_us * now->vrate;
+ vmin = now->vnow - vmargin;
+
+ if (last_period + max_period_delta < cur_period ||
+ time_before64(vtime, vmin)) {
+ atomic64_add(vmin - vtime, &iocg->vtime);
+ atomic64_add(vmin - vtime, &iocg->done_vtime);
+ vtime = vmin;
+ }
+
+ /*
+ * Activate, propagate weight and start period timer if not
+ * running. Reset hweight_gen to avoid accidental match from
+ * wrapping.
+ */
+ iocg->hweight_gen = atomic_read(&ioc->hweight_gen) - 1;
+ list_add(&iocg->active_list, &ioc->active_iocgs);
+ propagate_active_weight(iocg, iocg->weight,
+ iocg->last_inuse ?: iocg->weight);
+
+ TRACE_IOCG_PATH(iocg_activate, iocg, now,
+ last_period, cur_period, vtime);
+
+ iocg->last_vtime = vtime;
+
+ if (ioc->running == IOC_IDLE) {
+ ioc->running = IOC_RUNNING;
+ ioc_start_period(ioc, now);
+ }
+
+ spin_unlock_irq(&ioc->lock);
+ return true;
+
+fail_unlock:
+ spin_unlock_irq(&ioc->lock);
+ return false;
+}
+
+static int iocg_wake_fn(struct wait_queue_entry *wq_entry, unsigned mode,
+ int flags, void *key)
+{
+ struct iocg_wait *wait = container_of(wq_entry, struct iocg_wait, wait);
+ struct iocg_wake_ctx *ctx = (struct iocg_wake_ctx *)key;
+ u64 cost = abs_cost_to_cost(wait->abs_cost, ctx->hw_inuse);
+
+ ctx->vbudget -= cost;
+
+ if (ctx->vbudget < 0)
+ return -1;
+
+ iocg_commit_bio(ctx->iocg, wait->bio, cost);
+
+ /*
+ * autoremove_wake_function() removes the wait entry only when it
+ * actually changed the task state. We want the wait always
+ * removed. Remove explicitly and use default_wake_function().
+ */
+ list_del_init(&wq_entry->entry);
+ wait->committed = true;
+
+ default_wake_function(wq_entry, mode, flags, key);
+ return 0;
+}
+
+static void iocg_kick_waitq(struct ioc_gq *iocg, struct ioc_now *now)
+{
+ struct ioc *ioc = iocg->ioc;
+ struct iocg_wake_ctx ctx = { .iocg = iocg };
+ u64 margin_ns = (u64)(ioc->period_us *
+ WAITQ_TIMER_MARGIN_PCT / 100) * NSEC_PER_USEC;
+ u64 abs_vdebt, vdebt, vshortage, expires, oexpires;
+ s64 vbudget;
+ u32 hw_inuse;
+
+ lockdep_assert_held(&iocg->waitq.lock);
+
+ current_hweight(iocg, NULL, &hw_inuse);
+ vbudget = now->vnow - atomic64_read(&iocg->vtime);
+
+ /* pay off debt */
+ abs_vdebt = atomic64_read(&iocg->abs_vdebt);
+ vdebt = abs_cost_to_cost(abs_vdebt, hw_inuse);
+ if (vdebt && vbudget > 0) {
+ u64 delta = min_t(u64, vbudget, vdebt);
+ u64 abs_delta = min(cost_to_abs_cost(delta, hw_inuse),
+ abs_vdebt);
+
+ atomic64_add(delta, &iocg->vtime);
+ atomic64_add(delta, &iocg->done_vtime);
+ atomic64_sub(abs_delta, &iocg->abs_vdebt);
+ if (WARN_ON_ONCE(atomic64_read(&iocg->abs_vdebt) < 0))
+ atomic64_set(&iocg->abs_vdebt, 0);
+ }
+
+ /*
+ * Wake up the ones which are due and see how much vtime we'll need
+ * for the next one.
+ */
+ ctx.hw_inuse = hw_inuse;
+ ctx.vbudget = vbudget - vdebt;
+ __wake_up_locked_key(&iocg->waitq, TASK_NORMAL, &ctx);
+ if (!waitqueue_active(&iocg->waitq))
+ return;
+ if (WARN_ON_ONCE(ctx.vbudget >= 0))
+ return;
+
+ /* determine next wakeup, add a quarter margin to guarantee chunking */
+ vshortage = -ctx.vbudget;
+ expires = now->now_ns +
+ DIV64_U64_ROUND_UP(vshortage, now->vrate) * NSEC_PER_USEC;
+ expires += margin_ns / 4;
+
+ /* if already active and close enough, don't bother */
+ oexpires = ktime_to_ns(hrtimer_get_softexpires(&iocg->waitq_timer));
+ if (hrtimer_is_queued(&iocg->waitq_timer) &&
+ abs(oexpires - expires) <= margin_ns / 4)
+ return;
+
+ hrtimer_start_range_ns(&iocg->waitq_timer, ns_to_ktime(expires),
+ margin_ns / 4, HRTIMER_MODE_ABS);
+}
+
+static enum hrtimer_restart iocg_waitq_timer_fn(struct hrtimer *timer)
+{
+ struct ioc_gq *iocg = container_of(timer, struct ioc_gq, waitq_timer);
+ struct ioc_now now;
+ unsigned long flags;
+
+ ioc_now(iocg->ioc, &now);
+
+ spin_lock_irqsave(&iocg->waitq.lock, flags);
+ iocg_kick_waitq(iocg, &now);
+ spin_unlock_irqrestore(&iocg->waitq.lock, flags);
+
+ return HRTIMER_NORESTART;
+}
+
+static void iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now, u64 cost)
+{
+ struct ioc *ioc = iocg->ioc;
+ struct blkcg_gq *blkg = iocg_to_blkg(iocg);
+ u64 vtime = atomic64_read(&iocg->vtime);
+ u64 vmargin = ioc->margin_us * now->vrate;
+ u64 margin_ns = ioc->margin_us * NSEC_PER_USEC;
+ u64 expires, oexpires;
+ u32 hw_inuse;
+
+ /* debt-adjust vtime */
+ current_hweight(iocg, NULL, &hw_inuse);
+ vtime += abs_cost_to_cost(atomic64_read(&iocg->abs_vdebt), hw_inuse);
+
+ /* clear or maintain depending on the overage */
+ if (time_before_eq64(vtime, now->vnow)) {
+ blkcg_clear_delay(blkg);
+ return;
+ }
+ if (!atomic_read(&blkg->use_delay) &&
+ time_before_eq64(vtime, now->vnow + vmargin))
+ return;
+
+ /* use delay */
+ if (cost) {
+ u64 cost_ns = DIV64_U64_ROUND_UP(cost * NSEC_PER_USEC,
+ now->vrate);
+ blkcg_add_delay(blkg, now->now_ns, cost_ns);
+ }
+ blkcg_use_delay(blkg);
+
+ expires = now->now_ns + DIV64_U64_ROUND_UP(vtime - now->vnow,
+ now->vrate) * NSEC_PER_USEC;
+
+ /* if already active and close enough, don't bother */
+ oexpires = ktime_to_ns(hrtimer_get_softexpires(&iocg->delay_timer));
+ if (hrtimer_is_queued(&iocg->delay_timer) &&
+ abs(oexpires - expires) <= margin_ns / 4)
+ return;
+
+ hrtimer_start_range_ns(&iocg->delay_timer, ns_to_ktime(expires),
+ margin_ns / 4, HRTIMER_MODE_ABS);
+}
+
+static enum hrtimer_restart iocg_delay_timer_fn(struct hrtimer *timer)
+{
+ struct ioc_gq *iocg = container_of(timer, struct ioc_gq, delay_timer);
+ struct ioc_now now;
+
+ ioc_now(iocg->ioc, &now);
+ iocg_kick_delay(iocg, &now, 0);
+
+ return HRTIMER_NORESTART;
+}
+
+static void ioc_lat_stat(struct ioc *ioc, u32 *missed_ppm_ar, u32 *rq_wait_pct_p)
+{
+ u32 nr_met[2] = { };
+ u32 nr_missed[2] = { };
+ u64 rq_wait_ns = 0;
+ int cpu, rw;
+
+ for_each_online_cpu(cpu) {
+ struct ioc_pcpu_stat *stat = per_cpu_ptr(ioc->pcpu_stat, cpu);
+ u64 this_rq_wait_ns;
+
+ for (rw = READ; rw <= WRITE; rw++) {
+ u32 this_met = READ_ONCE(stat->missed[rw].nr_met);
+ u32 this_missed = READ_ONCE(stat->missed[rw].nr_missed);
+
+ nr_met[rw] += this_met - stat->missed[rw].last_met;
+ nr_missed[rw] += this_missed - stat->missed[rw].last_missed;
+ stat->missed[rw].last_met = this_met;
+ stat->missed[rw].last_missed = this_missed;
+ }
+
+ this_rq_wait_ns = READ_ONCE(stat->rq_wait_ns);
+ rq_wait_ns += this_rq_wait_ns - stat->last_rq_wait_ns;
+ stat->last_rq_wait_ns = this_rq_wait_ns;
+ }
+
+ for (rw = READ; rw <= WRITE; rw++) {
+ if (nr_met[rw] + nr_missed[rw])
+ missed_ppm_ar[rw] =
+ DIV64_U64_ROUND_UP((u64)nr_missed[rw] * MILLION,
+ nr_met[rw] + nr_missed[rw]);
+ else
+ missed_ppm_ar[rw] = 0;
+ }
+
+ *rq_wait_pct_p = div64_u64(rq_wait_ns * 100,
+ ioc->period_us * NSEC_PER_USEC);
+}
+
+/* was iocg idle this period? */
+static bool iocg_is_idle(struct ioc_gq *iocg)
+{
+ struct ioc *ioc = iocg->ioc;
+
+ /* did something get issued this period? */
+ if (atomic64_read(&iocg->active_period) ==
+ atomic64_read(&ioc->cur_period))
+ return false;
+
+ /* is something in flight? */
+ if (atomic64_read(&iocg->done_vtime) < atomic64_read(&iocg->vtime))
+ return false;
+
+ return true;
+}
+
+/* returns usage with margin added if surplus is large enough */
+static u32 surplus_adjusted_hweight_inuse(u32 usage, u32 hw_inuse)
+{
+ /* add margin */
+ usage = DIV_ROUND_UP(usage * SURPLUS_SCALE_PCT, 100);
+ usage += SURPLUS_SCALE_ABS;
+
+ /* don't bother if the surplus is too small */
+ if (usage + SURPLUS_MIN_ADJ_DELTA > hw_inuse)
+ return 0;
+
+ return usage;
+}
+
+static void ioc_timer_fn(struct timer_list *timer)
+{
+ struct ioc *ioc = container_of(timer, struct ioc, timer);
+ struct ioc_gq *iocg, *tiocg;
+ struct ioc_now now;
+ int nr_surpluses = 0, nr_shortages = 0, nr_lagging = 0;
+ u32 ppm_rthr = MILLION - ioc->params.qos[QOS_RPPM];
+ u32 ppm_wthr = MILLION - ioc->params.qos[QOS_WPPM];
+ u32 missed_ppm[2], rq_wait_pct;
+ u64 period_vtime;
+ int i;
+
+ /* how were the latencies during the period? */
+ ioc_lat_stat(ioc, missed_ppm, &rq_wait_pct);
+
+ /* take care of active iocgs */
+ spin_lock_irq(&ioc->lock);
+
+ ioc_now(ioc, &now);
+
+ period_vtime = now.vnow - ioc->period_at_vtime;
+ if (WARN_ON_ONCE(!period_vtime)) {
+ spin_unlock_irq(&ioc->lock);
+ return;
+ }
+
+ /*
+ * Waiters determine the sleep durations based on the vrate they
+ * saw at the time of sleep. If vrate has increased, some waiters
+ * could be sleeping for too long. Wake up tardy waiters which
+ * should have woken up in the last period and expire idle iocgs.
+ */
+ list_for_each_entry_safe(iocg, tiocg, &ioc->active_iocgs, active_list) {
+ if (!waitqueue_active(&iocg->waitq) &&
+ !atomic64_read(&iocg->abs_vdebt) && !iocg_is_idle(iocg))
+ continue;
+
+ spin_lock(&iocg->waitq.lock);
+
+ if (waitqueue_active(&iocg->waitq) ||
+ atomic64_read(&iocg->abs_vdebt)) {
+ /* might be oversleeping vtime / hweight changes, kick */
+ iocg_kick_waitq(iocg, &now);
+ iocg_kick_delay(iocg, &now, 0);
+ } else if (iocg_is_idle(iocg)) {
+ /* no waiter and idle, deactivate */
+ iocg->last_inuse = iocg->inuse;
+ __propagate_active_weight(iocg, 0, 0);
+ list_del_init(&iocg->active_list);
+ }
+
+ spin_unlock(&iocg->waitq.lock);
+ }
+ commit_active_weights(ioc);
+
+ /* calc usages and see whether some weights need to be moved around */
+ list_for_each_entry(iocg, &ioc->active_iocgs, active_list) {
+ u64 vdone, vtime, vusage, vmargin, vmin;
+ u32 hw_active, hw_inuse, usage;
+
+ /*
+ * Collect unused and wind vtime closer to vnow to prevent
+ * iocgs from accumulating a large amount of budget.
+ */
+ vdone = atomic64_read(&iocg->done_vtime);
+ vtime = atomic64_read(&iocg->vtime);
+ current_hweight(iocg, &hw_active, &hw_inuse);
+
+ /*
+ * Latency QoS detection doesn't account for IOs which are
+ * in-flight for longer than a period. Detect them by
+ * comparing vdone against period start. If lagging behind
+ * IOs from past periods, don't increase vrate.
+ */
+ if (!atomic_read(&iocg_to_blkg(iocg)->use_delay) &&
+ time_after64(vtime, vdone) &&
+ time_after64(vtime, now.vnow -
+ MAX_LAGGING_PERIODS * period_vtime) &&
+ time_before64(vdone, now.vnow - period_vtime))
+ nr_lagging++;
+
+ if (waitqueue_active(&iocg->waitq))
+ vusage = now.vnow - iocg->last_vtime;
+ else if (time_before64(iocg->last_vtime, vtime))
+ vusage = vtime - iocg->last_vtime;
+ else
+ vusage = 0;
+
+ iocg->last_vtime += vusage;
+ /*
+ * Factor in in-flight vtime into vusage to avoid
+ * high-latency completions appearing as idle. This should
+ * be done after the above ->last_time adjustment.
+ */
+ vusage = max(vusage, vtime - vdone);
+
+ /* calculate hweight based usage ratio and record */
+ if (vusage) {
+ usage = DIV64_U64_ROUND_UP(vusage * hw_inuse,
+ period_vtime);
+ iocg->usage_idx = (iocg->usage_idx + 1) % NR_USAGE_SLOTS;
+ iocg->usages[iocg->usage_idx] = usage;
+ } else {
+ usage = 0;
+ }
+
+ /* see whether there's surplus vtime */
+ vmargin = ioc->margin_us * now.vrate;
+ vmin = now.vnow - vmargin;
+
+ iocg->has_surplus = false;
+
+ if (!waitqueue_active(&iocg->waitq) &&
+ time_before64(vtime, vmin)) {
+ u64 delta = vmin - vtime;
+
+ /* throw away surplus vtime */
+ atomic64_add(delta, &iocg->vtime);
+ atomic64_add(delta, &iocg->done_vtime);
+ iocg->last_vtime += delta;
+ /* if usage is sufficiently low, maybe it can donate */
+ if (surplus_adjusted_hweight_inuse(usage, hw_inuse)) {
+ iocg->has_surplus = true;
+ nr_surpluses++;
+ }
+ } else if (hw_inuse < hw_active) {
+ u32 new_hwi, new_inuse;
+
+ /* was donating but might need to take back some */
+ if (waitqueue_active(&iocg->waitq)) {
+ new_hwi = hw_active;
+ } else {
+ new_hwi = max(hw_inuse,
+ usage * SURPLUS_SCALE_PCT / 100 +
+ SURPLUS_SCALE_ABS);
+ }
+
+ new_inuse = div64_u64((u64)iocg->inuse * new_hwi,
+ hw_inuse);
+ new_inuse = clamp_t(u32, new_inuse, 1, iocg->active);
+
+ if (new_inuse > iocg->inuse) {
+ TRACE_IOCG_PATH(inuse_takeback, iocg, &now,
+ iocg->inuse, new_inuse,
+ hw_inuse, new_hwi);
+ __propagate_active_weight(iocg, iocg->weight,
+ new_inuse);
+ }
+ } else {
+ /* genuninely out of vtime */
+ nr_shortages++;
+ }
+ }
+
+ if (!nr_shortages || !nr_surpluses)
+ goto skip_surplus_transfers;
+
+ /* there are both shortages and surpluses, transfer surpluses */
+ list_for_each_entry(iocg, &ioc->active_iocgs, active_list) {
+ u32 usage, hw_active, hw_inuse, new_hwi, new_inuse;
+ int nr_valid = 0;
+
+ if (!iocg->has_surplus)
+ continue;
+
+ /* base the decision on max historical usage */
+ for (i = 0, usage = 0; i < NR_USAGE_SLOTS; i++) {
+ if (iocg->usages[i]) {
+ usage = max(usage, iocg->usages[i]);
+ nr_valid++;
+ }
+ }
+ if (nr_valid < MIN_VALID_USAGES)
+ continue;
+
+ current_hweight(iocg, &hw_active, &hw_inuse);
+ new_hwi = surplus_adjusted_hweight_inuse(usage, hw_inuse);
+ if (!new_hwi)
+ continue;
+
+ new_inuse = DIV64_U64_ROUND_UP((u64)iocg->inuse * new_hwi,
+ hw_inuse);
+ if (new_inuse < iocg->inuse) {
+ TRACE_IOCG_PATH(inuse_giveaway, iocg, &now,
+ iocg->inuse, new_inuse,
+ hw_inuse, new_hwi);
+ __propagate_active_weight(iocg, iocg->weight, new_inuse);
+ }
+ }
+skip_surplus_transfers:
+ commit_active_weights(ioc);
+
+ /*
+ * If q is getting clogged or we're missing too much, we're issuing
+ * too much IO and should lower vtime rate. If we're not missing
+ * and experiencing shortages but not surpluses, we're too stingy
+ * and should increase vtime rate.
+ */
+ if (rq_wait_pct > RQ_WAIT_BUSY_PCT ||
+ missed_ppm[READ] > ppm_rthr ||
+ missed_ppm[WRITE] > ppm_wthr) {
+ ioc->busy_level = max(ioc->busy_level, 0);
+ ioc->busy_level++;
+ } else if (nr_lagging) {
+ ioc->busy_level = max(ioc->busy_level, 0);
+ } else if (nr_shortages && !nr_surpluses &&
+ rq_wait_pct <= RQ_WAIT_BUSY_PCT * UNBUSY_THR_PCT / 100 &&
+ missed_ppm[READ] <= ppm_rthr * UNBUSY_THR_PCT / 100 &&
+ missed_ppm[WRITE] <= ppm_wthr * UNBUSY_THR_PCT / 100) {
+ ioc->busy_level = min(ioc->busy_level, 0);
+ ioc->busy_level--;
+ } else {
+ ioc->busy_level = 0;
+ }
+
+ ioc->busy_level = clamp(ioc->busy_level, -1000, 1000);
+
+ if (ioc->busy_level) {
+ u64 vrate = atomic64_read(&ioc->vtime_rate);
+ u64 vrate_min = ioc->vrate_min, vrate_max = ioc->vrate_max;
+
+ /* rq_wait signal is always reliable, ignore user vrate_min */
+ if (rq_wait_pct > RQ_WAIT_BUSY_PCT)
+ vrate_min = VRATE_MIN;
+
+ /*
+ * If vrate is out of bounds, apply clamp gradually as the
+ * bounds can change abruptly. Otherwise, apply busy_level
+ * based adjustment.
+ */
+ if (vrate < vrate_min) {
+ vrate = div64_u64(vrate * (100 + VRATE_CLAMP_ADJ_PCT),
+ 100);
+ vrate = min(vrate, vrate_min);
+ } else if (vrate > vrate_max) {
+ vrate = div64_u64(vrate * (100 - VRATE_CLAMP_ADJ_PCT),
+ 100);
+ vrate = max(vrate, vrate_max);
+ } else {
+ int idx = min_t(int, abs(ioc->busy_level),
+ ARRAY_SIZE(vrate_adj_pct) - 1);
+ u32 adj_pct = vrate_adj_pct[idx];
+
+ if (ioc->busy_level > 0)
+ adj_pct = 100 - adj_pct;
+ else
+ adj_pct = 100 + adj_pct;
+
+ vrate = clamp(DIV64_U64_ROUND_UP(vrate * adj_pct, 100),
+ vrate_min, vrate_max);
+ }
+
+ trace_iocost_ioc_vrate_adj(ioc, vrate, &missed_ppm, rq_wait_pct,
+ nr_lagging, nr_shortages,
+ nr_surpluses);
+
+ atomic64_set(&ioc->vtime_rate, vrate);
+ ioc->inuse_margin_vtime = DIV64_U64_ROUND_UP(
+ ioc->period_us * vrate * INUSE_MARGIN_PCT, 100);
+ }
+
+ ioc_refresh_params(ioc, false);
+
+ /*
+ * This period is done. Move onto the next one. If nothing's
+ * going on with the device, stop the timer.
+ */
+ atomic64_inc(&ioc->cur_period);
+
+ if (ioc->running != IOC_STOP) {
+ if (!list_empty(&ioc->active_iocgs)) {
+ ioc_start_period(ioc, &now);
+ } else {
+ ioc->busy_level = 0;
+ ioc->running = IOC_IDLE;
+ }
+ }
+
+ spin_unlock_irq(&ioc->lock);
+}
+
+static void calc_vtime_cost_builtin(struct bio *bio, struct ioc_gq *iocg,
+ bool is_merge, u64 *costp)
+{
+ struct ioc *ioc = iocg->ioc;
+ u64 coef_seqio, coef_randio, coef_page;
+ u64 pages = max_t(u64, bio_sectors(bio) >> IOC_SECT_TO_PAGE_SHIFT, 1);
+ u64 seek_pages = 0;
+ u64 cost = 0;
+
+ switch (bio_op(bio)) {
+ case REQ_OP_READ:
+ coef_seqio = ioc->params.lcoefs[LCOEF_RSEQIO];
+ coef_randio = ioc->params.lcoefs[LCOEF_RRANDIO];
+ coef_page = ioc->params.lcoefs[LCOEF_RPAGE];
+ break;
+ case REQ_OP_WRITE:
+ coef_seqio = ioc->params.lcoefs[LCOEF_WSEQIO];
+ coef_randio = ioc->params.lcoefs[LCOEF_WRANDIO];
+ coef_page = ioc->params.lcoefs[LCOEF_WPAGE];
+ break;
+ default:
+ goto out;
+ }
+
+ if (iocg->cursor) {
+ seek_pages = abs(bio->bi_iter.bi_sector - iocg->cursor);
+ seek_pages >>= IOC_SECT_TO_PAGE_SHIFT;
+ }
+
+ if (!is_merge) {
+ if (seek_pages > LCOEF_RANDIO_PAGES) {
+ cost += coef_randio;
+ } else {
+ cost += coef_seqio;
+ }
+ }
+ cost += pages * coef_page;
+out:
+ *costp = cost;
+}
+
+static u64 calc_vtime_cost(struct bio *bio, struct ioc_gq *iocg, bool is_merge)
+{
+ u64 cost;
+
+ calc_vtime_cost_builtin(bio, iocg, is_merge, &cost);
+ return cost;
+}
+
+static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio)
+{
+ struct blkcg_gq *blkg = bio->bi_blkg;
+ struct ioc *ioc = rqos_to_ioc(rqos);
+ struct ioc_gq *iocg = blkg_to_iocg(blkg);
+ struct ioc_now now;
+ struct iocg_wait wait;
+ u32 hw_active, hw_inuse;
+ u64 abs_cost, cost, vtime;
+
+ /* bypass IOs if disabled or for root cgroup */
+ if (!ioc->enabled || !iocg->level)
+ return;
+
+ /* always activate so that even 0 cost IOs get protected to some level */
+ if (!iocg_activate(iocg, &now))
+ return;
+
+ /* calculate the absolute vtime cost */
+ abs_cost = calc_vtime_cost(bio, iocg, false);
+ if (!abs_cost)
+ return;
+
+ iocg->cursor = bio_end_sector(bio);
+
+ vtime = atomic64_read(&iocg->vtime);
+ current_hweight(iocg, &hw_active, &hw_inuse);
+
+ if (hw_inuse < hw_active &&
+ time_after_eq64(vtime + ioc->inuse_margin_vtime, now.vnow)) {
+ TRACE_IOCG_PATH(inuse_reset, iocg, &now,
+ iocg->inuse, iocg->weight, hw_inuse, hw_active);
+ spin_lock_irq(&ioc->lock);
+ propagate_active_weight(iocg, iocg->weight, iocg->weight);
+ spin_unlock_irq(&ioc->lock);
+ current_hweight(iocg, &hw_active, &hw_inuse);
+ }
+
+ cost = abs_cost_to_cost(abs_cost, hw_inuse);
+
+ /*
+ * If no one's waiting and within budget, issue right away. The
+ * tests are racy but the races aren't systemic - we only miss once
+ * in a while which is fine.
+ */
+ if (!waitqueue_active(&iocg->waitq) &&
+ !atomic64_read(&iocg->abs_vdebt) &&
+ time_before_eq64(vtime + cost, now.vnow)) {
+ iocg_commit_bio(iocg, bio, cost);
+ return;
+ }
+
+ /*
+ * We're over budget. If @bio has to be issued regardless,
+ * remember the abs_cost instead of advancing vtime.
+ * iocg_kick_waitq() will pay off the debt before waking more IOs.
+ * This way, the debt is continuously paid off each period with the
+ * actual budget available to the cgroup. If we just wound vtime,
+ * we would incorrectly use the current hw_inuse for the entire
+ * amount which, for example, can lead to the cgroup staying
+ * blocked for a long time even with substantially raised hw_inuse.
+ */
+ if (bio_issue_as_root_blkg(bio) || fatal_signal_pending(current)) {
+ atomic64_add(abs_cost, &iocg->abs_vdebt);
+ iocg_kick_delay(iocg, &now, cost);
+ return;
+ }
+
+ /*
+ * Append self to the waitq and schedule the wakeup timer if we're
+ * the first waiter. The timer duration is calculated based on the
+ * current vrate. vtime and hweight changes can make it too short
+ * or too long. Each wait entry records the absolute cost it's
+ * waiting for to allow re-evaluation using a custom wait entry.
+ *
+ * If too short, the timer simply reschedules itself. If too long,
+ * the period timer will notice and trigger wakeups.
+ *
+ * All waiters are on iocg->waitq and the wait states are
+ * synchronized using waitq.lock.
+ */
+ spin_lock_irq(&iocg->waitq.lock);
+
+ /*
+ * We activated above but w/o any synchronization. Deactivation is
+ * synchronized with waitq.lock and we won't get deactivated as
+ * long as we're waiting, so we're good if we're activated here.
+ * In the unlikely case that we are deactivated, just issue the IO.
+ */
+ if (unlikely(list_empty(&iocg->active_list))) {
+ spin_unlock_irq(&iocg->waitq.lock);
+ iocg_commit_bio(iocg, bio, cost);
+ return;
+ }
+
+ init_waitqueue_func_entry(&wait.wait, iocg_wake_fn);
+ wait.wait.private = current;
+ wait.bio = bio;
+ wait.abs_cost = abs_cost;
+ wait.committed = false; /* will be set true by waker */
+
+ __add_wait_queue_entry_tail(&iocg->waitq, &wait.wait);
+ iocg_kick_waitq(iocg, &now);
+
+ spin_unlock_irq(&iocg->waitq.lock);
+
+ while (true) {
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ if (wait.committed)
+ break;
+ io_schedule();
+ }
+
+ /* waker already committed us, proceed */
+ finish_wait(&iocg->waitq, &wait.wait);
+}
+
+static void ioc_rqos_merge(struct rq_qos *rqos, struct request *rq,
+ struct bio *bio)
+{
+ struct ioc_gq *iocg = blkg_to_iocg(bio->bi_blkg);
+ struct ioc *ioc = iocg->ioc;
+ sector_t bio_end = bio_end_sector(bio);
+ struct ioc_now now;
+ u32 hw_inuse;
+ u64 abs_cost, cost;
+
+ /* bypass if disabled or for root cgroup */
+ if (!ioc->enabled || !iocg->level)
+ return;
+
+ abs_cost = calc_vtime_cost(bio, iocg, true);
+ if (!abs_cost)
+ return;
+
+ ioc_now(ioc, &now);
+ current_hweight(iocg, NULL, &hw_inuse);
+ cost = abs_cost_to_cost(abs_cost, hw_inuse);
+
+ /* update cursor if backmerging into the request at the cursor */
+ if (blk_rq_pos(rq) < bio_end &&
+ blk_rq_pos(rq) + blk_rq_sectors(rq) == iocg->cursor)
+ iocg->cursor = bio_end;
+
+ /*
+ * Charge if there's enough vtime budget and the existing request
+ * has cost assigned. Otherwise, account it as debt. See debt
+ * handling in ioc_rqos_throttle() for details.
+ */
+ if (rq->bio && rq->bio->bi_iocost_cost &&
+ time_before_eq64(atomic64_read(&iocg->vtime) + cost, now.vnow))
+ iocg_commit_bio(iocg, bio, cost);
+ else
+ atomic64_add(abs_cost, &iocg->abs_vdebt);
+}
+
+static void ioc_rqos_done_bio(struct rq_qos *rqos, struct bio *bio)
+{
+ struct ioc_gq *iocg = blkg_to_iocg(bio->bi_blkg);
+
+ if (iocg && bio->bi_iocost_cost)
+ atomic64_add(bio->bi_iocost_cost, &iocg->done_vtime);
+}
+
+static void ioc_rqos_done(struct rq_qos *rqos, struct request *rq)
+{
+ struct ioc *ioc = rqos_to_ioc(rqos);
+ u64 on_q_ns, rq_wait_ns;
+ int pidx, rw;
+
+ if (!ioc->enabled || !rq->alloc_time_ns || !rq->start_time_ns)
+ return;
+
+ switch (req_op(rq) & REQ_OP_MASK) {
+ case REQ_OP_READ:
+ pidx = QOS_RLAT;
+ rw = READ;
+ break;
+ case REQ_OP_WRITE:
+ pidx = QOS_WLAT;
+ rw = WRITE;
+ break;
+ default:
+ return;
+ }
+
+ on_q_ns = ktime_get_ns() - rq->alloc_time_ns;
+ rq_wait_ns = rq->start_time_ns - rq->alloc_time_ns;
+
+ if (on_q_ns <= ioc->params.qos[pidx] * NSEC_PER_USEC)
+ this_cpu_inc(ioc->pcpu_stat->missed[rw].nr_met);
+ else
+ this_cpu_inc(ioc->pcpu_stat->missed[rw].nr_missed);
+
+ this_cpu_add(ioc->pcpu_stat->rq_wait_ns, rq_wait_ns);
+}
+
+static void ioc_rqos_queue_depth_changed(struct rq_qos *rqos)
+{
+ struct ioc *ioc = rqos_to_ioc(rqos);
+
+ spin_lock_irq(&ioc->lock);
+ ioc_refresh_params(ioc, false);
+ spin_unlock_irq(&ioc->lock);
+}
+
+static void ioc_rqos_exit(struct rq_qos *rqos)
+{
+ struct ioc *ioc = rqos_to_ioc(rqos);
+
+ blkcg_deactivate_policy(rqos->q, &blkcg_policy_iocost);
+
+ spin_lock_irq(&ioc->lock);
+ ioc->running = IOC_STOP;
+ spin_unlock_irq(&ioc->lock);
+
+ del_timer_sync(&ioc->timer);
+ free_percpu(ioc->pcpu_stat);
+ kfree(ioc);
+}
+
+static struct rq_qos_ops ioc_rqos_ops = {
+ .throttle = ioc_rqos_throttle,
+ .merge = ioc_rqos_merge,
+ .done_bio = ioc_rqos_done_bio,
+ .done = ioc_rqos_done,
+ .queue_depth_changed = ioc_rqos_queue_depth_changed,
+ .exit = ioc_rqos_exit,
+};
+
+static int blk_iocost_init(struct request_queue *q)
+{
+ struct ioc *ioc;
+ struct rq_qos *rqos;
+ int ret;
+
+ ioc = kzalloc(sizeof(*ioc), GFP_KERNEL);
+ if (!ioc)
+ return -ENOMEM;
+
+ ioc->pcpu_stat = alloc_percpu(struct ioc_pcpu_stat);
+ if (!ioc->pcpu_stat) {
+ kfree(ioc);
+ return -ENOMEM;
+ }
+
+ rqos = &ioc->rqos;
+ rqos->id = RQ_QOS_COST;
+ rqos->ops = &ioc_rqos_ops;
+ rqos->q = q;
+
+ spin_lock_init(&ioc->lock);
+ timer_setup(&ioc->timer, ioc_timer_fn, 0);
+ INIT_LIST_HEAD(&ioc->active_iocgs);
+
+ ioc->running = IOC_IDLE;
+ atomic64_set(&ioc->vtime_rate, VTIME_PER_USEC);
+ seqcount_init(&ioc->period_seqcount);
+ ioc->period_at = ktime_to_us(ktime_get());
+ atomic64_set(&ioc->cur_period, 0);
+ atomic_set(&ioc->hweight_gen, 0);
+
+ spin_lock_irq(&ioc->lock);
+ ioc->autop_idx = AUTOP_INVALID;
+ ioc_refresh_params(ioc, true);
+ spin_unlock_irq(&ioc->lock);
+
+ rq_qos_add(q, rqos);
+ ret = blkcg_activate_policy(q, &blkcg_policy_iocost);
+ if (ret) {
+ rq_qos_del(q, rqos);
+ free_percpu(ioc->pcpu_stat);
+ kfree(ioc);
+ return ret;
+ }
+ return 0;
+}
+
+static struct blkcg_policy_data *ioc_cpd_alloc(gfp_t gfp)
+{
+ struct ioc_cgrp *iocc;
+
+ iocc = kzalloc(sizeof(struct ioc_cgrp), gfp);
+ if (!iocc)
+ return NULL;
+
+ iocc->dfl_weight = CGROUP_WEIGHT_DFL;
+ return &iocc->cpd;
+}
+
+static void ioc_cpd_free(struct blkcg_policy_data *cpd)
+{
+ kfree(container_of(cpd, struct ioc_cgrp, cpd));
+}
+
+static struct blkg_policy_data *ioc_pd_alloc(gfp_t gfp, struct request_queue *q,
+ struct blkcg *blkcg)
+{
+ int levels = blkcg->css.cgroup->level + 1;
+ struct ioc_gq *iocg;
+
+ iocg = kzalloc_node(sizeof(*iocg) + levels * sizeof(iocg->ancestors[0]),
+ gfp, q->node);
+ if (!iocg)
+ return NULL;
+
+ return &iocg->pd;
+}
+
+static void ioc_pd_init(struct blkg_policy_data *pd)
+{
+ struct ioc_gq *iocg = pd_to_iocg(pd);
+ struct blkcg_gq *blkg = pd_to_blkg(&iocg->pd);
+ struct ioc *ioc = q_to_ioc(blkg->q);
+ struct ioc_now now;
+ struct blkcg_gq *tblkg;
+ unsigned long flags;
+
+ ioc_now(ioc, &now);
+
+ iocg->ioc = ioc;
+ atomic64_set(&iocg->vtime, now.vnow);
+ atomic64_set(&iocg->done_vtime, now.vnow);
+ atomic64_set(&iocg->abs_vdebt, 0);
+ atomic64_set(&iocg->active_period, atomic64_read(&ioc->cur_period));
+ INIT_LIST_HEAD(&iocg->active_list);
+ iocg->hweight_active = HWEIGHT_WHOLE;
+ iocg->hweight_inuse = HWEIGHT_WHOLE;
+
+ init_waitqueue_head(&iocg->waitq);
+ hrtimer_init(&iocg->waitq_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+ iocg->waitq_timer.function = iocg_waitq_timer_fn;
+ hrtimer_init(&iocg->delay_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+ iocg->delay_timer.function = iocg_delay_timer_fn;
+
+ iocg->level = blkg->blkcg->css.cgroup->level;
+
+ for (tblkg = blkg; tblkg; tblkg = tblkg->parent) {
+ struct ioc_gq *tiocg = blkg_to_iocg(tblkg);
+ iocg->ancestors[tiocg->level] = tiocg;
+ }
+
+ spin_lock_irqsave(&ioc->lock, flags);
+ weight_updated(iocg);
+ spin_unlock_irqrestore(&ioc->lock, flags);
+}
+
+static void ioc_pd_free(struct blkg_policy_data *pd)
+{
+ struct ioc_gq *iocg = pd_to_iocg(pd);
+ struct ioc *ioc = iocg->ioc;
+
+ if (ioc) {
+ spin_lock(&ioc->lock);
+ if (!list_empty(&iocg->active_list)) {
+ propagate_active_weight(iocg, 0, 0);
+ list_del_init(&iocg->active_list);
+ }
+ spin_unlock(&ioc->lock);
+
+ hrtimer_cancel(&iocg->waitq_timer);
+ hrtimer_cancel(&iocg->delay_timer);
+ }
+ kfree(iocg);
+}
+
+static u64 ioc_weight_prfill(struct seq_file *sf, struct blkg_policy_data *pd,
+ int off)
+{
+ const char *dname = blkg_dev_name(pd->blkg);
+ struct ioc_gq *iocg = pd_to_iocg(pd);
+
+ if (dname && iocg->cfg_weight)
+ seq_printf(sf, "%s %u\n", dname, iocg->cfg_weight);
+ return 0;
+}
+
+
+static int ioc_weight_show(struct seq_file *sf, void *v)
+{
+ struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
+ struct ioc_cgrp *iocc = blkcg_to_iocc(blkcg);
+
+ seq_printf(sf, "default %u\n", iocc->dfl_weight);
+ blkcg_print_blkgs(sf, blkcg, ioc_weight_prfill,
+ &blkcg_policy_iocost, seq_cft(sf)->private, false);
+ return 0;
+}
+
+static ssize_t ioc_weight_write(struct kernfs_open_file *of, char *buf,
+ size_t nbytes, loff_t off)
+{
+ struct blkcg *blkcg = css_to_blkcg(of_css(of));
+ struct ioc_cgrp *iocc = blkcg_to_iocc(blkcg);
+ struct blkg_conf_ctx ctx;
+ struct ioc_gq *iocg;
+ u32 v;
+ int ret;
+
+ if (!strchr(buf, ':')) {
+ struct blkcg_gq *blkg;
+
+ if (!sscanf(buf, "default %u", &v) && !sscanf(buf, "%u", &v))
+ return -EINVAL;
+
+ if (v < CGROUP_WEIGHT_MIN || v > CGROUP_WEIGHT_MAX)
+ return -EINVAL;
+
+ spin_lock(&blkcg->lock);
+ iocc->dfl_weight = v;
+ hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
+ struct ioc_gq *iocg = blkg_to_iocg(blkg);
+
+ if (iocg) {
+ spin_lock_irq(&iocg->ioc->lock);
+ weight_updated(iocg);
+ spin_unlock_irq(&iocg->ioc->lock);
+ }
+ }
+ spin_unlock(&blkcg->lock);
+
+ return nbytes;
+ }
+
+ ret = blkg_conf_prep(blkcg, &blkcg_policy_iocost, buf, &ctx);
+ if (ret)
+ return ret;
+
+ iocg = blkg_to_iocg(ctx.blkg);
+
+ if (!strncmp(ctx.body, "default", 7)) {
+ v = 0;
+ } else {
+ if (!sscanf(ctx.body, "%u", &v))
+ goto einval;
+ if (v < CGROUP_WEIGHT_MIN || v > CGROUP_WEIGHT_MAX)
+ goto einval;
+ }
+
+ spin_lock_irq(&iocg->ioc->lock);
+ iocg->cfg_weight = v;
+ weight_updated(iocg);
+ spin_unlock_irq(&iocg->ioc->lock);
+
+ blkg_conf_finish(&ctx);
+ return nbytes;
+
+einval:
+ blkg_conf_finish(&ctx);
+ return -EINVAL;
+}
+
+static u64 ioc_qos_prfill(struct seq_file *sf, struct blkg_policy_data *pd,
+ int off)
+{
+ const char *dname = blkg_dev_name(pd->blkg);
+ struct ioc *ioc = pd_to_iocg(pd)->ioc;
+
+ if (!dname)
+ return 0;
+
+ seq_printf(sf, "%s enable=%d ctrl=%s rpct=%u.%02u rlat=%u wpct=%u.%02u wlat=%u min=%u.%02u max=%u.%02u\n",
+ dname, ioc->enabled, ioc->user_qos_params ? "user" : "auto",
+ ioc->params.qos[QOS_RPPM] / 10000,
+ ioc->params.qos[QOS_RPPM] % 10000 / 100,
+ ioc->params.qos[QOS_RLAT],
+ ioc->params.qos[QOS_WPPM] / 10000,
+ ioc->params.qos[QOS_WPPM] % 10000 / 100,
+ ioc->params.qos[QOS_WLAT],
+ ioc->params.qos[QOS_MIN] / 10000,
+ ioc->params.qos[QOS_MIN] % 10000 / 100,
+ ioc->params.qos[QOS_MAX] / 10000,
+ ioc->params.qos[QOS_MAX] % 10000 / 100);
+ return 0;
+}
+
+static int ioc_qos_show(struct seq_file *sf, void *v)
+{
+ struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
+
+ blkcg_print_blkgs(sf, blkcg, ioc_qos_prfill,
+ &blkcg_policy_iocost, seq_cft(sf)->private, false);
+ return 0;
+}
+
+static const match_table_t qos_ctrl_tokens = {
+ { QOS_ENABLE, "enable=%u" },
+ { QOS_CTRL, "ctrl=%s" },
+ { NR_QOS_CTRL_PARAMS, NULL },
+};
+
+static const match_table_t qos_tokens = {
+ { QOS_RPPM, "rpct=%s" },
+ { QOS_RLAT, "rlat=%u" },
+ { QOS_WPPM, "wpct=%s" },
+ { QOS_WLAT, "wlat=%u" },
+ { QOS_MIN, "min=%s" },
+ { QOS_MAX, "max=%s" },
+ { NR_QOS_PARAMS, NULL },
+};
+
+static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input,
+ size_t nbytes, loff_t off)
+{
+ struct gendisk *disk;
+ struct ioc *ioc;
+ u32 qos[NR_QOS_PARAMS];
+ bool enable, user;
+ char *p;
+ int ret;
+
+ disk = blkcg_conf_get_disk(&input);
+ if (IS_ERR(disk))
+ return PTR_ERR(disk);
+
+ ioc = q_to_ioc(disk->queue);
+ if (!ioc) {
+ ret = blk_iocost_init(disk->queue);
+ if (ret)
+ goto err;
+ ioc = q_to_ioc(disk->queue);
+ }
+
+ spin_lock_irq(&ioc->lock);
+ memcpy(qos, ioc->params.qos, sizeof(qos));
+ enable = ioc->enabled;
+ user = ioc->user_qos_params;
+ spin_unlock_irq(&ioc->lock);
+
+ while ((p = strsep(&input, " \t\n"))) {
+ substring_t args[MAX_OPT_ARGS];
+ char buf[32];
+ int tok;
+ s64 v;
+
+ if (!*p)
+ continue;
+
+ switch (match_token(p, qos_ctrl_tokens, args)) {
+ case QOS_ENABLE:
+ match_u64(&args[0], &v);
+ enable = v;
+ continue;
+ case QOS_CTRL:
+ match_strlcpy(buf, &args[0], sizeof(buf));
+ if (!strcmp(buf, "auto"))
+ user = false;
+ else if (!strcmp(buf, "user"))
+ user = true;
+ else
+ goto einval;
+ continue;
+ }
+
+ tok = match_token(p, qos_tokens, args);
+ switch (tok) {
+ case QOS_RPPM:
+ case QOS_WPPM:
+ if (match_strlcpy(buf, &args[0], sizeof(buf)) >=
+ sizeof(buf))
+ goto einval;
+ if (cgroup_parse_float(buf, 2, &v))
+ goto einval;
+ if (v < 0 || v > 10000)
+ goto einval;
+ qos[tok] = v * 100;
+ break;
+ case QOS_RLAT:
+ case QOS_WLAT:
+ if (match_u64(&args[0], &v))
+ goto einval;
+ qos[tok] = v;
+ break;
+ case QOS_MIN:
+ case QOS_MAX:
+ if (match_strlcpy(buf, &args[0], sizeof(buf)) >=
+ sizeof(buf))
+ goto einval;
+ if (cgroup_parse_float(buf, 2, &v))
+ goto einval;
+ if (v < 0)
+ goto einval;
+ qos[tok] = clamp_t(s64, v * 100,
+ VRATE_MIN_PPM, VRATE_MAX_PPM);
+ break;
+ default:
+ goto einval;
+ }
+ user = true;
+ }
+
+ if (qos[QOS_MIN] > qos[QOS_MAX])
+ goto einval;
+
+ spin_lock_irq(&ioc->lock);
+
+ if (enable) {
+ blk_queue_flag_set(QUEUE_FLAG_RQ_ALLOC_TIME, ioc->rqos.q);
+ ioc->enabled = true;
+ } else {
+ blk_queue_flag_clear(QUEUE_FLAG_RQ_ALLOC_TIME, ioc->rqos.q);
+ ioc->enabled = false;
+ }
+
+ if (user) {
+ memcpy(ioc->params.qos, qos, sizeof(qos));
+ ioc->user_qos_params = true;
+ } else {
+ ioc->user_qos_params = false;
+ }
+
+ ioc_refresh_params(ioc, true);
+ spin_unlock_irq(&ioc->lock);
+
+ put_disk_and_module(disk);
+ return nbytes;
+einval:
+ ret = -EINVAL;
+err:
+ put_disk_and_module(disk);
+ return ret;
+}
+
+static u64 ioc_cost_model_prfill(struct seq_file *sf,
+ struct blkg_policy_data *pd, int off)
+{
+ const char *dname = blkg_dev_name(pd->blkg);
+ struct ioc *ioc = pd_to_iocg(pd)->ioc;
+ u64 *u = ioc->params.i_lcoefs;
+
+ if (!dname)
+ return 0;
+
+ seq_printf(sf, "%s ctrl=%s model=linear "
+ "rbps=%llu rseqiops=%llu rrandiops=%llu "
+ "wbps=%llu wseqiops=%llu wrandiops=%llu\n",
+ dname, ioc->user_cost_model ? "user" : "auto",
+ u[I_LCOEF_RBPS], u[I_LCOEF_RSEQIOPS], u[I_LCOEF_RRANDIOPS],
+ u[I_LCOEF_WBPS], u[I_LCOEF_WSEQIOPS], u[I_LCOEF_WRANDIOPS]);
+ return 0;
+}
+
+static int ioc_cost_model_show(struct seq_file *sf, void *v)
+{
+ struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
+
+ blkcg_print_blkgs(sf, blkcg, ioc_cost_model_prfill,
+ &blkcg_policy_iocost, seq_cft(sf)->private, false);
+ return 0;
+}
+
+static const match_table_t cost_ctrl_tokens = {
+ { COST_CTRL, "ctrl=%s" },
+ { COST_MODEL, "model=%s" },
+ { NR_COST_CTRL_PARAMS, NULL },
+};
+
+static const match_table_t i_lcoef_tokens = {
+ { I_LCOEF_RBPS, "rbps=%u" },
+ { I_LCOEF_RSEQIOPS, "rseqiops=%u" },
+ { I_LCOEF_RRANDIOPS, "rrandiops=%u" },
+ { I_LCOEF_WBPS, "wbps=%u" },
+ { I_LCOEF_WSEQIOPS, "wseqiops=%u" },
+ { I_LCOEF_WRANDIOPS, "wrandiops=%u" },
+ { NR_I_LCOEFS, NULL },
+};
+
+static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input,
+ size_t nbytes, loff_t off)
+{
+ struct gendisk *disk;
+ struct ioc *ioc;
+ u64 u[NR_I_LCOEFS];
+ bool user;
+ char *p;
+ int ret;
+
+ disk = blkcg_conf_get_disk(&input);
+ if (IS_ERR(disk))
+ return PTR_ERR(disk);
+
+ ioc = q_to_ioc(disk->queue);
+ if (!ioc) {
+ ret = blk_iocost_init(disk->queue);
+ if (ret)
+ goto err;
+ ioc = q_to_ioc(disk->queue);
+ }
+
+ spin_lock_irq(&ioc->lock);
+ memcpy(u, ioc->params.i_lcoefs, sizeof(u));
+ user = ioc->user_cost_model;
+ spin_unlock_irq(&ioc->lock);
+
+ while ((p = strsep(&input, " \t\n"))) {
+ substring_t args[MAX_OPT_ARGS];
+ char buf[32];
+ int tok;
+ u64 v;
+
+ if (!*p)
+ continue;
+
+ switch (match_token(p, cost_ctrl_tokens, args)) {
+ case COST_CTRL:
+ match_strlcpy(buf, &args[0], sizeof(buf));
+ if (!strcmp(buf, "auto"))
+ user = false;
+ else if (!strcmp(buf, "user"))
+ user = true;
+ else
+ goto einval;
+ continue;
+ case COST_MODEL:
+ match_strlcpy(buf, &args[0], sizeof(buf));
+ if (strcmp(buf, "linear"))
+ goto einval;
+ continue;
+ }
+
+ tok = match_token(p, i_lcoef_tokens, args);
+ if (tok == NR_I_LCOEFS)
+ goto einval;
+ if (match_u64(&args[0], &v))
+ goto einval;
+ u[tok] = v;
+ user = true;
+ }
+
+ spin_lock_irq(&ioc->lock);
+ if (user) {
+ memcpy(ioc->params.i_lcoefs, u, sizeof(u));
+ ioc->user_cost_model = true;
+ } else {
+ ioc->user_cost_model = false;
+ }
+ ioc_refresh_params(ioc, true);
+ spin_unlock_irq(&ioc->lock);
+
+ put_disk_and_module(disk);
+ return nbytes;
+
+einval:
+ ret = -EINVAL;
+err:
+ put_disk_and_module(disk);
+ return ret;
+}
+
+static struct cftype ioc_files[] = {
+ {
+ .name = "weight",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = ioc_weight_show,
+ .write = ioc_weight_write,
+ },
+ {
+ .name = "cost.qos",
+ .flags = CFTYPE_ONLY_ON_ROOT,
+ .seq_show = ioc_qos_show,
+ .write = ioc_qos_write,
+ },
+ {
+ .name = "cost.model",
+ .flags = CFTYPE_ONLY_ON_ROOT,
+ .seq_show = ioc_cost_model_show,
+ .write = ioc_cost_model_write,
+ },
+ {}
+};
+
+static struct blkcg_policy blkcg_policy_iocost = {
+ .dfl_cftypes = ioc_files,
+ .cpd_alloc_fn = ioc_cpd_alloc,
+ .cpd_free_fn = ioc_cpd_free,
+ .pd_alloc_fn = ioc_pd_alloc,
+ .pd_init_fn = ioc_pd_init,
+ .pd_free_fn = ioc_pd_free,
+};
+
+static int __init ioc_init(void)
+{
+ return blkcg_policy_register(&blkcg_policy_iocost);
+}
+
+static void __exit ioc_exit(void)
+{
+ return blkcg_policy_unregister(&blkcg_policy_iocost);
+}
+
+module_init(ioc_init);
+module_exit(ioc_exit);
diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index 0fff7b56df0e..c128d50cb410 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -725,7 +725,7 @@ int blk_iolatency_init(struct request_queue *q)
return -ENOMEM;
rqos = &blkiolat->rqos;
- rqos->id = RQ_QOS_CGROUP;
+ rqos->id = RQ_QOS_LATENCY;
rqos->ops = &blkcg_iolatency_ops;
rqos->q = q;
@@ -934,11 +934,13 @@ static size_t iolatency_pd_stat(struct blkg_policy_data *pd, char *buf,
}
-static struct blkg_policy_data *iolatency_pd_alloc(gfp_t gfp, int node)
+static struct blkg_policy_data *iolatency_pd_alloc(gfp_t gfp,
+ struct request_queue *q,
+ struct blkcg *blkcg)
{
struct iolatency_grp *iolat;
- iolat = kzalloc_node(sizeof(*iolat), gfp, node);
+ iolat = kzalloc_node(sizeof(*iolat), gfp, q->node);
if (!iolat)
return NULL;
iolat->stats = __alloc_percpu_gfp(sizeof(struct latency_stat),
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 57f7990b342d..48e6725b32ee 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -132,19 +132,32 @@ static struct bio *blk_bio_write_same_split(struct request_queue *q,
return bio_split(bio, q->limits.max_write_same_sectors, GFP_NOIO, bs);
}
+/*
+ * Return the maximum number of sectors from the start of a bio that may be
+ * submitted as a single request to a block device. If enough sectors remain,
+ * align the end to the physical block size. Otherwise align the end to the
+ * logical block size. This approach minimizes the number of non-aligned
+ * requests that are submitted to a block device if the start of a bio is not
+ * aligned to a physical block boundary.
+ */
static inline unsigned get_max_io_size(struct request_queue *q,
struct bio *bio)
{
unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector);
- unsigned mask = queue_logical_block_size(q) - 1;
+ unsigned max_sectors = sectors;
+ unsigned pbs = queue_physical_block_size(q) >> SECTOR_SHIFT;
+ unsigned lbs = queue_logical_block_size(q) >> SECTOR_SHIFT;
+ unsigned start_offset = bio->bi_iter.bi_sector & (pbs - 1);
- /* aligned to logical block size */
- sectors &= ~(mask >> 9);
+ max_sectors += start_offset;
+ max_sectors &= ~(pbs - 1);
+ if (max_sectors > start_offset)
+ return max_sectors - start_offset;
- return sectors;
+ return sectors & (lbs - 1);
}
-static unsigned get_max_segment_size(struct request_queue *q,
+static unsigned get_max_segment_size(const struct request_queue *q,
unsigned offset)
{
unsigned long mask = queue_segment_boundary(q);
@@ -157,26 +170,41 @@ static unsigned get_max_segment_size(struct request_queue *q,
queue_max_segment_size(q));
}
-/*
- * Split the bvec @bv into segments, and update all kinds of
- * variables.
+/**
+ * bvec_split_segs - verify whether or not a bvec should be split in the middle
+ * @q: [in] request queue associated with the bio associated with @bv
+ * @bv: [in] bvec to examine
+ * @nsegs: [in,out] Number of segments in the bio being built. Incremented
+ * by the number of segments from @bv that may be appended to that
+ * bio without exceeding @max_segs
+ * @sectors: [in,out] Number of sectors in the bio being built. Incremented
+ * by the number of sectors from @bv that may be appended to that
+ * bio without exceeding @max_sectors
+ * @max_segs: [in] upper bound for *@nsegs
+ * @max_sectors: [in] upper bound for *@sectors
+ *
+ * When splitting a bio, it can happen that a bvec is encountered that is too
+ * big to fit in a single segment and hence that it has to be split in the
+ * middle. This function verifies whether or not that should happen. The value
+ * %true is returned if and only if appending the entire @bv to a bio with
+ * *@nsegs segments and *@sectors sectors would make that bio unacceptable for
+ * the block driver.
*/
-static bool bvec_split_segs(struct request_queue *q, struct bio_vec *bv,
- unsigned *nsegs, unsigned *sectors, unsigned max_segs)
+static bool bvec_split_segs(const struct request_queue *q,
+ const struct bio_vec *bv, unsigned *nsegs,
+ unsigned *sectors, unsigned max_segs,
+ unsigned max_sectors)
{
- unsigned len = bv->bv_len;
+ unsigned max_len = (min(max_sectors, UINT_MAX >> 9) - *sectors) << 9;
+ unsigned len = min(bv->bv_len, max_len);
unsigned total_len = 0;
- unsigned new_nsegs = 0, seg_size = 0;
+ unsigned seg_size = 0;
- /*
- * Multi-page bvec may be too big to hold in one segment, so the
- * current bvec has to be splitted as multiple segments.
- */
- while (len && new_nsegs + *nsegs < max_segs) {
+ while (len && *nsegs < max_segs) {
seg_size = get_max_segment_size(q, bv->bv_offset + total_len);
seg_size = min(seg_size, len);
- new_nsegs++;
+ (*nsegs)++;
total_len += seg_size;
len -= seg_size;
@@ -184,16 +212,31 @@ static bool bvec_split_segs(struct request_queue *q, struct bio_vec *bv,
break;
}
- if (new_nsegs) {
- *nsegs += new_nsegs;
- if (sectors)
- *sectors += total_len >> 9;
- }
+ *sectors += total_len >> 9;
- /* split in the middle of the bvec if len != 0 */
- return !!len;
+ /* tell the caller to split the bvec if it is too big to fit */
+ return len > 0 || bv->bv_len > max_len;
}
+/**
+ * blk_bio_segment_split - split a bio in two bios
+ * @q: [in] request queue pointer
+ * @bio: [in] bio to be split
+ * @bs: [in] bio set to allocate the clone from
+ * @segs: [out] number of segments in the bio with the first half of the sectors
+ *
+ * Clone @bio, update the bi_iter of the clone to represent the first sectors
+ * of @bio and update @bio->bi_iter to represent the remaining sectors. The
+ * following is guaranteed for the cloned bio:
+ * - That it has at most get_max_io_size(@q, @bio) sectors.
+ * - That it has at most queue_max_segments(@q) segments.
+ *
+ * Except for discard requests the cloned bio will point at the bi_io_vec of
+ * the original bio. It is the responsibility of the caller to ensure that the
+ * original bio is not freed before the cloned bio. The caller is also
+ * responsible for ensuring that @bs is only destroyed after processing of the
+ * split bio has finished.
+ */
static struct bio *blk_bio_segment_split(struct request_queue *q,
struct bio *bio,
struct bio_set *bs,
@@ -213,34 +256,18 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
if (bvprvp && bvec_gap_to_prev(q, bvprvp, bv.bv_offset))
goto split;
- if (sectors + (bv.bv_len >> 9) > max_sectors) {
- /*
- * Consider this a new segment if we're splitting in
- * the middle of this vector.
- */
- if (nsegs < max_segs &&
- sectors < max_sectors) {
- /* split in the middle of bvec */
- bv.bv_len = (max_sectors - sectors) << 9;
- bvec_split_segs(q, &bv, &nsegs,
- &sectors, max_segs);
- }
+ if (nsegs < max_segs &&
+ sectors + (bv.bv_len >> 9) <= max_sectors &&
+ bv.bv_offset + bv.bv_len <= PAGE_SIZE) {
+ nsegs++;
+ sectors += bv.bv_len >> 9;
+ } else if (bvec_split_segs(q, &bv, &nsegs, &sectors, max_segs,
+ max_sectors)) {
goto split;
}
- if (nsegs == max_segs)
- goto split;
-
bvprv = bv;
bvprvp = &bvprv;
-
- if (bv.bv_offset + bv.bv_len <= PAGE_SIZE) {
- nsegs++;
- sectors += bv.bv_len >> 9;
- } else if (bvec_split_segs(q, &bv, &nsegs, &sectors,
- max_segs)) {
- goto split;
- }
}
*segs = nsegs;
@@ -250,6 +277,19 @@ split:
return bio_split(bio, sectors, GFP_NOIO, bs);
}
+/**
+ * __blk_queue_split - split a bio and submit the second half
+ * @q: [in] request queue pointer
+ * @bio: [in, out] bio to be split
+ * @nr_segs: [out] number of segments in the first bio
+ *
+ * Split a bio into two bios, chain the two bios, submit the second half and
+ * store a pointer to the first half in *@bio. If the second bio is still too
+ * big it will be split by a recursive call to this function. Since this
+ * function may allocate a new bio from @q->bio_split, it is the responsibility
+ * of the caller to ensure that @q is only released after processing of the
+ * split bio has finished.
+ */
void __blk_queue_split(struct request_queue *q, struct bio **bio,
unsigned int *nr_segs)
{
@@ -294,6 +334,17 @@ void __blk_queue_split(struct request_queue *q, struct bio **bio,
}
}
+/**
+ * blk_queue_split - split a bio and submit the second half
+ * @q: [in] request queue pointer
+ * @bio: [in, out] bio to be split
+ *
+ * Split a bio into two bios, chains the two bios, submit the second half and
+ * store a pointer to the first half in *@bio. Since this function may allocate
+ * a new bio from @q->bio_split, it is the responsibility of the caller to
+ * ensure that @q is only released after processing of the split bio has
+ * finished.
+ */
void blk_queue_split(struct request_queue *q, struct bio **bio)
{
unsigned int nr_segs;
@@ -305,6 +356,7 @@ EXPORT_SYMBOL(blk_queue_split);
unsigned int blk_recalc_rq_segments(struct request *rq)
{
unsigned int nr_phys_segs = 0;
+ unsigned int nr_sectors = 0;
struct req_iterator iter;
struct bio_vec bv;
@@ -321,7 +373,8 @@ unsigned int blk_recalc_rq_segments(struct request *rq)
}
rq_for_each_bvec(bv, rq, iter)
- bvec_split_segs(rq->q, &bv, &nr_phys_segs, NULL, UINT_MAX);
+ bvec_split_segs(rq->q, &bv, &nr_phys_segs, &nr_sectors,
+ UINT_MAX, UINT_MAX);
return nr_phys_segs;
}
diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index f945621a0e8f..0157f2b3485a 100644
--- a/block/blk-mq-cpumap.c
+++ b/block/blk-mq-cpumap.c
@@ -15,10 +15,10 @@
#include "blk.h"
#include "blk-mq.h"
-static int cpu_to_queue_index(struct blk_mq_queue_map *qmap,
- unsigned int nr_queues, const int cpu)
+static int queue_index(struct blk_mq_queue_map *qmap,
+ unsigned int nr_queues, const int q)
{
- return qmap->queue_offset + (cpu % nr_queues);
+ return qmap->queue_offset + (q % nr_queues);
}
static int get_first_sibling(unsigned int cpu)
@@ -36,21 +36,36 @@ int blk_mq_map_queues(struct blk_mq_queue_map *qmap)
{
unsigned int *map = qmap->mq_map;
unsigned int nr_queues = qmap->nr_queues;
- unsigned int cpu, first_sibling;
+ unsigned int cpu, first_sibling, q = 0;
+
+ for_each_possible_cpu(cpu)
+ map[cpu] = -1;
+
+ /*
+ * Spread queues among present CPUs first for minimizing
+ * count of dead queues which are mapped by all un-present CPUs
+ */
+ for_each_present_cpu(cpu) {
+ if (q >= nr_queues)
+ break;
+ map[cpu] = queue_index(qmap, nr_queues, q++);
+ }
for_each_possible_cpu(cpu) {
+ if (map[cpu] != -1)
+ continue;
/*
* First do sequential mapping between CPUs and queues.
* In case we still have CPUs to map, and we have some number of
* threads per cores then map sibling threads to the same queue
* for performance optimizations.
*/
- if (cpu < nr_queues) {
- map[cpu] = cpu_to_queue_index(qmap, nr_queues, cpu);
+ if (q < nr_queues) {
+ map[cpu] = queue_index(qmap, nr_queues, q++);
} else {
first_sibling = get_first_sibling(cpu);
if (first_sibling == cpu)
- map[cpu] = cpu_to_queue_index(qmap, nr_queues, cpu);
+ map[cpu] = queue_index(qmap, nr_queues, q++);
else
map[cpu] = map[first_sibling];
}
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index d6e1a9bd7131..a0d3ce30fa08 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -270,7 +270,7 @@ void blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
struct blk_mq_hw_ctx *hctx;
int i;
- lockdep_assert_held(&q->sysfs_lock);
+ lockdep_assert_held(&q->sysfs_dir_lock);
queue_for_each_hw_ctx(q, hctx, i)
blk_mq_unregister_hctx(hctx);
@@ -320,7 +320,7 @@ int __blk_mq_register_dev(struct device *dev, struct request_queue *q)
int ret, i;
WARN_ON_ONCE(!q->kobj.parent);
- lockdep_assert_held(&q->sysfs_lock);
+ lockdep_assert_held(&q->sysfs_dir_lock);
ret = kobject_add(q->mq_kobj, kobject_get(&dev->kobj), "%s", "mq");
if (ret < 0)
@@ -349,23 +349,12 @@ unreg:
return ret;
}
-int blk_mq_register_dev(struct device *dev, struct request_queue *q)
-{
- int ret;
-
- mutex_lock(&q->sysfs_lock);
- ret = __blk_mq_register_dev(dev, q);
- mutex_unlock(&q->sysfs_lock);
-
- return ret;
-}
-
void blk_mq_sysfs_unregister(struct request_queue *q)
{
struct blk_mq_hw_ctx *hctx;
int i;
- mutex_lock(&q->sysfs_lock);
+ mutex_lock(&q->sysfs_dir_lock);
if (!q->mq_sysfs_init_done)
goto unlock;
@@ -373,7 +362,7 @@ void blk_mq_sysfs_unregister(struct request_queue *q)
blk_mq_unregister_hctx(hctx);
unlock:
- mutex_unlock(&q->sysfs_lock);
+ mutex_unlock(&q->sysfs_dir_lock);
}
int blk_mq_sysfs_register(struct request_queue *q)
@@ -381,7 +370,7 @@ int blk_mq_sysfs_register(struct request_queue *q)
struct blk_mq_hw_ctx *hctx;
int i, ret = 0;
- mutex_lock(&q->sysfs_lock);
+ mutex_lock(&q->sysfs_dir_lock);
if (!q->mq_sysfs_init_done)
goto unlock;
@@ -392,7 +381,7 @@ int blk_mq_sysfs_register(struct request_queue *q)
}
unlock:
- mutex_unlock(&q->sysfs_lock);
+ mutex_unlock(&q->sysfs_dir_lock);
return ret;
}
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index da19f0bc8876..008388e82b5c 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -10,6 +10,7 @@
#include <linux/module.h>
#include <linux/blk-mq.h>
+#include <linux/delay.h>
#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-tag.h"
@@ -354,6 +355,37 @@ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
}
EXPORT_SYMBOL(blk_mq_tagset_busy_iter);
+static bool blk_mq_tagset_count_completed_rqs(struct request *rq,
+ void *data, bool reserved)
+{
+ unsigned *count = data;
+
+ if (blk_mq_request_completed(rq))
+ (*count)++;
+ return true;
+}
+
+/**
+ * blk_mq_tagset_wait_completed_request - wait until all completed req's
+ * complete funtion is run
+ * @tagset: Tag set to drain completed request
+ *
+ * Note: This function has to be run after all IO queues are shutdown
+ */
+void blk_mq_tagset_wait_completed_request(struct blk_mq_tag_set *tagset)
+{
+ while (true) {
+ unsigned count = 0;
+
+ blk_mq_tagset_busy_iter(tagset,
+ blk_mq_tagset_count_completed_rqs, &count);
+ if (!count)
+ break;
+ msleep(5);
+ }
+}
+EXPORT_SYMBOL(blk_mq_tagset_wait_completed_request);
+
/**
* blk_mq_queue_tag_busy_iter - iterate over all requests with a driver tag
* @q: Request queue to examine.
diff --git a/block/blk-mq.c b/block/blk-mq.c
index e0b849bfe74d..20a49be536b5 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -44,12 +44,12 @@ static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);
static int blk_mq_poll_stats_bkt(const struct request *rq)
{
- int ddir, bytes, bucket;
+ int ddir, sectors, bucket;
ddir = rq_data_dir(rq);
- bytes = blk_rq_bytes(rq);
+ sectors = blk_rq_stats_sectors(rq);
- bucket = ddir + 2*(ilog2(bytes) - 9);
+ bucket = ddir + 2 * ilog2(sectors);
if (bucket < 0)
return -1;
@@ -282,16 +282,16 @@ bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
EXPORT_SYMBOL(blk_mq_can_queue);
/*
- * Only need start/end time stamping if we have stats enabled, or using
- * an IO scheduler.
+ * Only need start/end time stamping if we have iostat or
+ * blk stats enabled, or using an IO scheduler.
*/
static inline bool blk_mq_need_time_stamp(struct request *rq)
{
- return (rq->rq_flags & RQF_IO_STAT) || rq->q->elevator;
+ return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS)) || rq->q->elevator;
}
static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
- unsigned int tag, unsigned int op)
+ unsigned int tag, unsigned int op, u64 alloc_time_ns)
{
struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
struct request *rq = tags->static_rqs[tag];
@@ -325,11 +325,15 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
RB_CLEAR_NODE(&rq->rb_node);
rq->rq_disk = NULL;
rq->part = NULL;
+#ifdef CONFIG_BLK_RQ_ALLOC_TIME
+ rq->alloc_time_ns = alloc_time_ns;
+#endif
if (blk_mq_need_time_stamp(rq))
rq->start_time_ns = ktime_get_ns();
else
rq->start_time_ns = 0;
rq->io_start_time_ns = 0;
+ rq->stats_sectors = 0;
rq->nr_phys_segments = 0;
#if defined(CONFIG_BLK_DEV_INTEGRITY)
rq->nr_integrity_segments = 0;
@@ -356,8 +360,14 @@ static struct request *blk_mq_get_request(struct request_queue *q,
struct request *rq;
unsigned int tag;
bool clear_ctx_on_error = false;
+ u64 alloc_time_ns = 0;
blk_queue_enter_live(q);
+
+ /* alloc_time includes depth and tag waits */
+ if (blk_queue_rq_alloc_time(q))
+ alloc_time_ns = ktime_get_ns();
+
data->q = q;
if (likely(!data->ctx)) {
data->ctx = blk_mq_get_ctx(q);
@@ -393,7 +403,7 @@ static struct request *blk_mq_get_request(struct request_queue *q,
return NULL;
}
- rq = blk_mq_rq_ctx_init(data, tag, data->cmd_flags);
+ rq = blk_mq_rq_ctx_init(data, tag, data->cmd_flags, alloc_time_ns);
if (!op_is_flush(data->cmd_flags)) {
rq->elv.icq = NULL;
if (e && e->type->ops.prepare_request) {
@@ -652,19 +662,18 @@ bool blk_mq_complete_request(struct request *rq)
}
EXPORT_SYMBOL(blk_mq_complete_request);
-void blk_mq_complete_request_sync(struct request *rq)
-{
- WRITE_ONCE(rq->state, MQ_RQ_COMPLETE);
- rq->q->mq_ops->complete(rq);
-}
-EXPORT_SYMBOL_GPL(blk_mq_complete_request_sync);
-
int blk_mq_request_started(struct request *rq)
{
return blk_mq_rq_state(rq) != MQ_RQ_IDLE;
}
EXPORT_SYMBOL_GPL(blk_mq_request_started);
+int blk_mq_request_completed(struct request *rq)
+{
+ return blk_mq_rq_state(rq) == MQ_RQ_COMPLETE;
+}
+EXPORT_SYMBOL_GPL(blk_mq_request_completed);
+
void blk_mq_start_request(struct request *rq)
{
struct request_queue *q = rq->q;
@@ -673,9 +682,7 @@ void blk_mq_start_request(struct request *rq)
if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
rq->io_start_time_ns = ktime_get_ns();
-#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
- rq->throtl_size = blk_rq_sectors(rq);
-#endif
+ rq->stats_sectors = blk_rq_sectors(rq);
rq->rq_flags |= RQF_STATS;
rq_qos_issue(q, rq);
}
@@ -2453,11 +2460,6 @@ static void blk_mq_map_swqueue(struct request_queue *q)
struct blk_mq_ctx *ctx;
struct blk_mq_tag_set *set = q->tag_set;
- /*
- * Avoid others reading imcomplete hctx->cpumask through sysfs
- */
- mutex_lock(&q->sysfs_lock);
-
queue_for_each_hw_ctx(q, hctx, i) {
cpumask_clear(hctx->cpumask);
hctx->nr_ctx = 0;
@@ -2518,8 +2520,6 @@ static void blk_mq_map_swqueue(struct request_queue *q)
HCTX_TYPE_DEFAULT, i);
}
- mutex_unlock(&q->sysfs_lock);
-
queue_for_each_hw_ctx(q, hctx, i) {
/*
* If no software queues are mapped to this hardware queue,
@@ -2688,7 +2688,11 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
if (!uninit_q)
return ERR_PTR(-ENOMEM);
- q = blk_mq_init_allocated_queue(set, uninit_q);
+ /*
+ * Initialize the queue without an elevator. device_add_disk() will do
+ * the initialization.
+ */
+ q = blk_mq_init_allocated_queue(set, uninit_q, false);
if (IS_ERR(q))
blk_cleanup_queue(uninit_q);
@@ -2839,7 +2843,8 @@ static unsigned int nr_hw_queues(struct blk_mq_tag_set *set)
}
struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
- struct request_queue *q)
+ struct request_queue *q,
+ bool elevator_init)
{
/* mark the queue as mq asap */
q->mq_ops = set->ops;
@@ -2901,18 +2906,14 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
blk_mq_add_queue_tag_set(set, q);
blk_mq_map_swqueue(q);
- if (!(set->flags & BLK_MQ_F_NO_SCHED)) {
- int ret;
-
- ret = elevator_init_mq(q);
- if (ret)
- return ERR_PTR(ret);
- }
+ if (elevator_init)
+ elevator_init_mq(q);
return q;
err_hctxs:
kfree(q->queue_hw_ctx);
+ q->nr_hw_queues = 0;
err_sys_init:
blk_mq_sysfs_deinit(q);
err_poll:
diff --git a/block/blk-pm.c b/block/blk-pm.c
index 0a028c189897..1adc1cd748b4 100644
--- a/block/blk-pm.c
+++ b/block/blk-pm.c
@@ -207,10 +207,12 @@ EXPORT_SYMBOL(blk_post_runtime_resume);
*/
void blk_set_runtime_active(struct request_queue *q)
{
- spin_lock_irq(&q->queue_lock);
- q->rpm_status = RPM_ACTIVE;
- pm_runtime_mark_last_busy(q->dev);
- pm_request_autosuspend(q->dev);
- spin_unlock_irq(&q->queue_lock);
+ if (q->dev) {
+ spin_lock_irq(&q->queue_lock);
+ q->rpm_status = RPM_ACTIVE;
+ pm_runtime_mark_last_busy(q->dev);
+ pm_request_autosuspend(q->dev);
+ spin_unlock_irq(&q->queue_lock);
+ }
}
EXPORT_SYMBOL(blk_set_runtime_active);
diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c
index 3954c0dc1443..61b635bc2a31 100644
--- a/block/blk-rq-qos.c
+++ b/block/blk-rq-qos.c
@@ -83,6 +83,15 @@ void __rq_qos_track(struct rq_qos *rqos, struct request *rq, struct bio *bio)
} while (rqos);
}
+void __rq_qos_merge(struct rq_qos *rqos, struct request *rq, struct bio *bio)
+{
+ do {
+ if (rqos->ops->merge)
+ rqos->ops->merge(rqos, rq, bio);
+ rqos = rqos->next;
+ } while (rqos);
+}
+
void __rq_qos_done_bio(struct rq_qos *rqos, struct bio *bio)
{
do {
@@ -92,6 +101,15 @@ void __rq_qos_done_bio(struct rq_qos *rqos, struct bio *bio)
} while (rqos);
}
+void __rq_qos_queue_depth_changed(struct rq_qos *rqos)
+{
+ do {
+ if (rqos->ops->queue_depth_changed)
+ rqos->ops->queue_depth_changed(rqos);
+ rqos = rqos->next;
+ } while (rqos);
+}
+
/*
* Return true, if we can't increase the depth further by scaling
*/
diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h
index 2300e038b9fa..08a09dbe0f4b 100644
--- a/block/blk-rq-qos.h
+++ b/block/blk-rq-qos.h
@@ -14,7 +14,8 @@ struct blk_mq_debugfs_attr;
enum rq_qos_id {
RQ_QOS_WBT,
- RQ_QOS_CGROUP,
+ RQ_QOS_LATENCY,
+ RQ_QOS_COST,
};
struct rq_wait {
@@ -35,11 +36,13 @@ struct rq_qos {
struct rq_qos_ops {
void (*throttle)(struct rq_qos *, struct bio *);
void (*track)(struct rq_qos *, struct request *, struct bio *);
+ void (*merge)(struct rq_qos *, struct request *, struct bio *);
void (*issue)(struct rq_qos *, struct request *);
void (*requeue)(struct rq_qos *, struct request *);
void (*done)(struct rq_qos *, struct request *);
void (*done_bio)(struct rq_qos *, struct bio *);
void (*cleanup)(struct rq_qos *, struct bio *);
+ void (*queue_depth_changed)(struct rq_qos *);
void (*exit)(struct rq_qos *);
const struct blk_mq_debugfs_attr *debugfs_attrs;
};
@@ -72,7 +75,7 @@ static inline struct rq_qos *wbt_rq_qos(struct request_queue *q)
static inline struct rq_qos *blkcg_rq_qos(struct request_queue *q)
{
- return rq_qos_id(q, RQ_QOS_CGROUP);
+ return rq_qos_id(q, RQ_QOS_LATENCY);
}
static inline const char *rq_qos_id_to_name(enum rq_qos_id id)
@@ -80,8 +83,10 @@ static inline const char *rq_qos_id_to_name(enum rq_qos_id id)
switch (id) {
case RQ_QOS_WBT:
return "wbt";
- case RQ_QOS_CGROUP:
- return "cgroup";
+ case RQ_QOS_LATENCY:
+ return "latency";
+ case RQ_QOS_COST:
+ return "cost";
}
return "unknown";
}
@@ -135,7 +140,9 @@ void __rq_qos_issue(struct rq_qos *rqos, struct request *rq);
void __rq_qos_requeue(struct rq_qos *rqos, struct request *rq);
void __rq_qos_throttle(struct rq_qos *rqos, struct bio *bio);
void __rq_qos_track(struct rq_qos *rqos, struct request *rq, struct bio *bio);
+void __rq_qos_merge(struct rq_qos *rqos, struct request *rq, struct bio *bio);
void __rq_qos_done_bio(struct rq_qos *rqos, struct bio *bio);
+void __rq_qos_queue_depth_changed(struct rq_qos *rqos);
static inline void rq_qos_cleanup(struct request_queue *q, struct bio *bio)
{
@@ -185,6 +192,19 @@ static inline void rq_qos_track(struct request_queue *q, struct request *rq,
__rq_qos_track(q->rq_qos, rq, bio);
}
+static inline void rq_qos_merge(struct request_queue *q, struct request *rq,
+ struct bio *bio)
+{
+ if (q->rq_qos)
+ __rq_qos_merge(q->rq_qos, rq, bio);
+}
+
+static inline void rq_qos_queue_depth_changed(struct request_queue *q)
+{
+ if (q->rq_qos)
+ __rq_qos_queue_depth_changed(q->rq_qos);
+}
+
void rq_qos_exit(struct request_queue *);
#endif
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 2c1831207a8f..6bd1e3b082d8 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -805,7 +805,7 @@ EXPORT_SYMBOL(blk_queue_update_dma_alignment);
void blk_set_queue_depth(struct request_queue *q, unsigned int depth)
{
q->queue_depth = depth;
- wbt_set_queue_depth(q, depth);
+ rq_qos_queue_depth_changed(q);
}
EXPORT_SYMBOL(blk_set_queue_depth);
@@ -832,6 +832,22 @@ void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua)
}
EXPORT_SYMBOL_GPL(blk_queue_write_cache);
+/**
+ * blk_queue_required_elevator_features - Set a queue required elevator features
+ * @q: the request queue for the target device
+ * @features: Required elevator features OR'ed together
+ *
+ * Tell the block layer that for the device controlled through @q, only the
+ * only elevators that can be used are those that implement at least the set of
+ * features specified by @features.
+ */
+void blk_queue_required_elevator_features(struct request_queue *q,
+ unsigned int features)
+{
+ q->required_elevator_features = features;
+}
+EXPORT_SYMBOL_GPL(blk_queue_required_elevator_features);
+
static int __init blk_settings_init(void)
{
blk_max_low_pfn = max_low_pfn - 1;
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 9bfa3ea4ed63..b82736c781c5 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -941,14 +941,14 @@ int blk_register_queue(struct gendisk *disk)
int ret;
struct device *dev = disk_to_dev(disk);
struct request_queue *q = disk->queue;
+ bool has_elevator = false;
if (WARN_ON(!q))
return -ENXIO;
- WARN_ONCE(test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags),
+ WARN_ONCE(blk_queue_registered(q),
"%s is registering an already registered queue\n",
kobject_name(&dev->kobj));
- blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q);
/*
* SCSI probing may synchronously create and destroy a lot of
@@ -968,8 +968,7 @@ int blk_register_queue(struct gendisk *disk)
if (ret)
return ret;
- /* Prevent changes through sysfs until registration is completed. */
- mutex_lock(&q->sysfs_lock);
+ mutex_lock(&q->sysfs_dir_lock);
ret = kobject_add(&q->kobj, kobject_get(&dev->kobj), "%s", "queue");
if (ret < 0) {
@@ -990,26 +989,36 @@ int blk_register_queue(struct gendisk *disk)
blk_mq_debugfs_register(q);
}
- kobject_uevent(&q->kobj, KOBJ_ADD);
-
- wbt_enable_default(q);
-
- blk_throtl_register_queue(q);
-
+ /*
+ * The flag of QUEUE_FLAG_REGISTERED isn't set yet, so elevator
+ * switch won't happen at all.
+ */
if (q->elevator) {
- ret = elv_register_queue(q);
+ ret = elv_register_queue(q, false);
if (ret) {
- mutex_unlock(&q->sysfs_lock);
- kobject_uevent(&q->kobj, KOBJ_REMOVE);
+ mutex_unlock(&q->sysfs_dir_lock);
kobject_del(&q->kobj);
blk_trace_remove_sysfs(dev);
kobject_put(&dev->kobj);
return ret;
}
+ has_elevator = true;
}
+
+ mutex_lock(&q->sysfs_lock);
+ blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q);
+ wbt_enable_default(q);
+ blk_throtl_register_queue(q);
+
+ /* Now everything is ready and send out KOBJ_ADD uevent */
+ kobject_uevent(&q->kobj, KOBJ_ADD);
+ if (has_elevator)
+ kobject_uevent(&q->elevator->kobj, KOBJ_ADD);
+ mutex_unlock(&q->sysfs_lock);
+
ret = 0;
unlock:
- mutex_unlock(&q->sysfs_lock);
+ mutex_unlock(&q->sysfs_dir_lock);
return ret;
}
EXPORT_SYMBOL_GPL(blk_register_queue);
@@ -1029,7 +1038,7 @@ void blk_unregister_queue(struct gendisk *disk)
return;
/* Return early if disk->queue was never registered. */
- if (!test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags))
+ if (!blk_queue_registered(q))
return;
/*
@@ -1038,25 +1047,28 @@ void blk_unregister_queue(struct gendisk *disk)
* concurrent elv_iosched_store() calls.
*/
mutex_lock(&q->sysfs_lock);
-
blk_queue_flag_clear(QUEUE_FLAG_REGISTERED, q);
+ mutex_unlock(&q->sysfs_lock);
+ mutex_lock(&q->sysfs_dir_lock);
/*
* Remove the sysfs attributes before unregistering the queue data
* structures that can be modified through sysfs.
*/
if (queue_is_mq(q))
blk_mq_unregister_dev(disk_to_dev(disk), q);
- mutex_unlock(&q->sysfs_lock);
kobject_uevent(&q->kobj, KOBJ_REMOVE);
kobject_del(&q->kobj);
blk_trace_remove_sysfs(disk_to_dev(disk));
- mutex_lock(&q->sysfs_lock);
+ /*
+ * q->kobj has been removed, so it is safe to check if elevator
+ * exists without holding q->sysfs_lock.
+ */
if (q->elevator)
elv_unregister_queue(q);
- mutex_unlock(&q->sysfs_lock);
+ mutex_unlock(&q->sysfs_dir_lock);
kobject_put(&disk_to_dev(disk)->kobj);
}
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 8ab6c8153223..18f773e52dfb 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -478,12 +478,14 @@ static void throtl_service_queue_init(struct throtl_service_queue *sq)
timer_setup(&sq->pending_timer, throtl_pending_timer_fn, 0);
}
-static struct blkg_policy_data *throtl_pd_alloc(gfp_t gfp, int node)
+static struct blkg_policy_data *throtl_pd_alloc(gfp_t gfp,
+ struct request_queue *q,
+ struct blkcg *blkcg)
{
struct throtl_grp *tg;
int rw;
- tg = kzalloc_node(sizeof(*tg), gfp, node);
+ tg = kzalloc_node(sizeof(*tg), gfp, q->node);
if (!tg)
return NULL;
@@ -2246,7 +2248,8 @@ void blk_throtl_stat_add(struct request *rq, u64 time_ns)
struct request_queue *q = rq->q;
struct throtl_data *td = q->td;
- throtl_track_latency(td, rq->throtl_size, req_op(rq), time_ns >> 10);
+ throtl_track_latency(td, blk_rq_stats_sectors(rq), req_op(rq),
+ time_ns >> 10);
}
void blk_throtl_bio_endio(struct bio *bio)
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 313f45a37e9d..8af553a0ba00 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -629,15 +629,6 @@ static void wbt_requeue(struct rq_qos *rqos, struct request *rq)
}
}
-void wbt_set_queue_depth(struct request_queue *q, unsigned int depth)
-{
- struct rq_qos *rqos = wbt_rq_qos(q);
- if (rqos) {
- RQWB(rqos)->rq_depth.queue_depth = depth;
- __wbt_update_limits(RQWB(rqos));
- }
-}
-
void wbt_set_write_cache(struct request_queue *q, bool write_cache_on)
{
struct rq_qos *rqos = wbt_rq_qos(q);
@@ -656,7 +647,7 @@ void wbt_enable_default(struct request_queue *q)
return;
/* Queue not registered? Maybe shutting down... */
- if (!test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags))
+ if (!blk_queue_registered(q))
return;
if (queue_is_mq(q) && IS_ENABLED(CONFIG_BLK_WBT_MQ))
@@ -689,6 +680,12 @@ static int wbt_data_dir(const struct request *rq)
return -1;
}
+static void wbt_queue_depth_changed(struct rq_qos *rqos)
+{
+ RQWB(rqos)->rq_depth.queue_depth = blk_queue_depth(rqos->q);
+ __wbt_update_limits(RQWB(rqos));
+}
+
static void wbt_exit(struct rq_qos *rqos)
{
struct rq_wb *rwb = RQWB(rqos);
@@ -811,6 +808,7 @@ static struct rq_qos_ops wbt_rqos_ops = {
.requeue = wbt_requeue,
.done = wbt_done,
.cleanup = wbt_cleanup,
+ .queue_depth_changed = wbt_queue_depth_changed,
.exit = wbt_exit,
#ifdef CONFIG_BLK_DEBUG_FS
.debugfs_attrs = wbt_debugfs_attrs,
@@ -853,7 +851,7 @@ int wbt_init(struct request_queue *q)
rwb->min_lat_nsec = wbt_default_latency_nsec(q);
- wbt_set_queue_depth(q, blk_queue_depth(q));
+ wbt_queue_depth_changed(&rwb->rqos);
wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
return 0;
diff --git a/block/blk-wbt.h b/block/blk-wbt.h
index f47218d5b3b2..8e4e37660971 100644
--- a/block/blk-wbt.h
+++ b/block/blk-wbt.h
@@ -95,7 +95,6 @@ void wbt_enable_default(struct request_queue *);
u64 wbt_get_min_lat(struct request_queue *q);
void wbt_set_min_lat(struct request_queue *q, u64 val);
-void wbt_set_queue_depth(struct request_queue *, unsigned int);
void wbt_set_write_cache(struct request_queue *, bool);
u64 wbt_default_latency_nsec(struct request_queue *);
@@ -118,9 +117,6 @@ static inline void wbt_disable_default(struct request_queue *q)
static inline void wbt_enable_default(struct request_queue *q)
{
}
-static inline void wbt_set_queue_depth(struct request_queue *q, unsigned int depth)
-{
-}
static inline void wbt_set_write_cache(struct request_queue *q, bool wc)
{
}
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 6c503824ba3f..4bc5f260248a 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -202,6 +202,42 @@ int blkdev_report_zones(struct block_device *bdev, sector_t sector,
}
EXPORT_SYMBOL_GPL(blkdev_report_zones);
+/*
+ * Special case of zone reset operation to reset all zones in one command,
+ * useful for applications like mkfs.
+ */
+static int __blkdev_reset_all_zones(struct block_device *bdev, gfp_t gfp_mask)
+{
+ struct bio *bio = bio_alloc(gfp_mask, 0);
+ int ret;
+
+ /* across the zones operations, don't need any sectors */
+ bio_set_dev(bio, bdev);
+ bio_set_op_attrs(bio, REQ_OP_ZONE_RESET_ALL, 0);
+
+ ret = submit_bio_wait(bio);
+ bio_put(bio);
+
+ return ret;
+}
+
+static inline bool blkdev_allow_reset_all_zones(struct block_device *bdev,
+ sector_t nr_sectors)
+{
+ if (!blk_queue_zone_resetall(bdev_get_queue(bdev)))
+ return false;
+
+ if (nr_sectors != part_nr_sects_read(bdev->bd_part))
+ return false;
+ /*
+ * REQ_OP_ZONE_RESET_ALL can be executed only if the block device is
+ * the entire disk, that is, if the blocks device start offset is 0 and
+ * its capacity is the same as the entire disk.
+ */
+ return get_start_sect(bdev) == 0 &&
+ part_nr_sects_read(bdev->bd_part) == get_capacity(bdev->bd_disk);
+}
+
/**
* blkdev_reset_zones - Reset zones write pointer
* @bdev: Target block device
@@ -235,6 +271,9 @@ int blkdev_reset_zones(struct block_device *bdev,
/* Out of range */
return -EINVAL;
+ if (blkdev_allow_reset_all_zones(bdev, nr_sectors))
+ return __blkdev_reset_all_zones(bdev, gfp_mask);
+
/* Check alignment (handle eventual smaller last zone) */
zone_sectors = blk_queue_zone_sectors(q);
if (sector & (zone_sectors - 1))
diff --git a/block/blk.h b/block/blk.h
index de6b2e146d6e..ed347f7a97b1 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -184,11 +184,11 @@ void blk_account_io_done(struct request *req, u64 now);
void blk_insert_flush(struct request *rq);
-int elevator_init_mq(struct request_queue *q);
+void elevator_init_mq(struct request_queue *q);
int elevator_switch_mq(struct request_queue *q,
struct elevator_type *new_e);
void __elevator_exit(struct request_queue *, struct elevator_queue *);
-int elv_register_queue(struct request_queue *q);
+int elv_register_queue(struct request_queue *q, bool uevent);
void elv_unregister_queue(struct request_queue *q);
static inline void elevator_exit(struct request_queue *q,
diff --git a/block/elevator.c b/block/elevator.c
index 2f17d66d0e61..bba10e83478a 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -83,8 +83,26 @@ bool elv_bio_merge_ok(struct request *rq, struct bio *bio)
}
EXPORT_SYMBOL(elv_bio_merge_ok);
-static bool elevator_match(const struct elevator_type *e, const char *name)
+static inline bool elv_support_features(unsigned int elv_features,
+ unsigned int required_features)
{
+ return (required_features & elv_features) == required_features;
+}
+
+/**
+ * elevator_match - Test an elevator name and features
+ * @e: Scheduler to test
+ * @name: Elevator name to test
+ * @required_features: Features that the elevator must provide
+ *
+ * Return true is the elevator @e name matches @name and if @e provides all the
+ * the feratures spcified by @required_features.
+ */
+static bool elevator_match(const struct elevator_type *e, const char *name,
+ unsigned int required_features)
+{
+ if (!elv_support_features(e->elevator_features, required_features))
+ return false;
if (!strcmp(e->elevator_name, name))
return true;
if (e->elevator_alias && !strcmp(e->elevator_alias, name))
@@ -93,15 +111,21 @@ static bool elevator_match(const struct elevator_type *e, const char *name)
return false;
}
-/*
- * Return scheduler with name 'name'
+/**
+ * elevator_find - Find an elevator
+ * @name: Name of the elevator to find
+ * @required_features: Features that the elevator must provide
+ *
+ * Return the first registered scheduler with name @name and supporting the
+ * features @required_features and NULL otherwise.
*/
-static struct elevator_type *elevator_find(const char *name)
+static struct elevator_type *elevator_find(const char *name,
+ unsigned int required_features)
{
struct elevator_type *e;
list_for_each_entry(e, &elv_list, list) {
- if (elevator_match(e, name))
+ if (elevator_match(e, name, required_features))
return e;
}
@@ -120,12 +144,12 @@ static struct elevator_type *elevator_get(struct request_queue *q,
spin_lock(&elv_list_lock);
- e = elevator_find(name);
+ e = elevator_find(name, q->required_elevator_features);
if (!e && try_loading) {
spin_unlock(&elv_list_lock);
request_module("%s-iosched", name);
spin_lock(&elv_list_lock);
- e = elevator_find(name);
+ e = elevator_find(name, q->required_elevator_features);
}
if (e && !try_module_get(e->elevator_owner))
@@ -135,20 +159,6 @@ static struct elevator_type *elevator_get(struct request_queue *q,
return e;
}
-static char chosen_elevator[ELV_NAME_MAX];
-
-static int __init elevator_setup(char *str)
-{
- /*
- * Be backwards-compatible with previous kernels, so users
- * won't get the wrong elevator.
- */
- strncpy(chosen_elevator, str, sizeof(chosen_elevator) - 1);
- return 1;
-}
-
-__setup("elevator=", elevator_setup);
-
static struct kobj_type elv_ktype;
struct elevator_queue *elevator_alloc(struct request_queue *q,
@@ -470,13 +480,16 @@ static struct kobj_type elv_ktype = {
.release = elevator_release,
};
-int elv_register_queue(struct request_queue *q)
+/*
+ * elv_register_queue is called from either blk_register_queue or
+ * elevator_switch, elevator switch is prevented from being happen
+ * in the two paths, so it is safe to not hold q->sysfs_lock.
+ */
+int elv_register_queue(struct request_queue *q, bool uevent)
{
struct elevator_queue *e = q->elevator;
int error;
- lockdep_assert_held(&q->sysfs_lock);
-
error = kobject_add(&e->kobj, &q->kobj, "%s", "iosched");
if (!error) {
struct elv_fs_entry *attr = e->type->elevator_attrs;
@@ -487,24 +500,34 @@ int elv_register_queue(struct request_queue *q)
attr++;
}
}
- kobject_uevent(&e->kobj, KOBJ_ADD);
+ if (uevent)
+ kobject_uevent(&e->kobj, KOBJ_ADD);
+
+ mutex_lock(&q->sysfs_lock);
e->registered = 1;
+ mutex_unlock(&q->sysfs_lock);
}
return error;
}
+/*
+ * elv_unregister_queue is called from either blk_unregister_queue or
+ * elevator_switch, elevator switch is prevented from being happen
+ * in the two paths, so it is safe to not hold q->sysfs_lock.
+ */
void elv_unregister_queue(struct request_queue *q)
{
- lockdep_assert_held(&q->sysfs_lock);
-
if (q) {
struct elevator_queue *e = q->elevator;
kobject_uevent(&e->kobj, KOBJ_REMOVE);
kobject_del(&e->kobj);
+
+ mutex_lock(&q->sysfs_lock);
e->registered = 0;
/* Re-enable throttling in case elevator disabled it */
wbt_enable_default(q);
+ mutex_unlock(&q->sysfs_lock);
}
}
@@ -526,7 +549,7 @@ int elv_register(struct elevator_type *e)
/* register, don't allow duplicate names */
spin_lock(&elv_list_lock);
- if (elevator_find(e->elevator_name)) {
+ if (elevator_find(e->elevator_name, 0)) {
spin_unlock(&elv_list_lock);
kmem_cache_destroy(e->icq_cache);
return -EBUSY;
@@ -567,10 +590,32 @@ int elevator_switch_mq(struct request_queue *q,
lockdep_assert_held(&q->sysfs_lock);
if (q->elevator) {
- if (q->elevator->registered)
+ if (q->elevator->registered) {
+ mutex_unlock(&q->sysfs_lock);
+
+ /*
+ * Concurrent elevator switch can't happen becasue
+ * sysfs write is always exclusively on same file.
+ *
+ * Also the elevator queue won't be freed after
+ * sysfs_lock is released becasue kobject_del() in
+ * blk_unregister_queue() waits for completion of
+ * .store & .show on its attributes.
+ */
elv_unregister_queue(q);
+
+ mutex_lock(&q->sysfs_lock);
+ }
ioc_clear_queue(q);
elevator_exit(q, q->elevator);
+
+ /*
+ * sysfs_lock may be dropped, so re-check if queue is
+ * unregistered. If yes, don't switch to new elevator
+ * any more
+ */
+ if (!blk_queue_registered(q))
+ return 0;
}
ret = blk_mq_init_sched(q, new_e);
@@ -578,7 +623,11 @@ int elevator_switch_mq(struct request_queue *q,
goto out;
if (new_e) {
- ret = elv_register_queue(q);
+ mutex_unlock(&q->sysfs_lock);
+
+ ret = elv_register_queue(q, true);
+
+ mutex_lock(&q->sysfs_lock);
if (ret) {
elevator_exit(q, q->elevator);
goto out;
@@ -594,37 +643,89 @@ out:
return ret;
}
+static inline bool elv_support_iosched(struct request_queue *q)
+{
+ if (q->tag_set && (q->tag_set->flags & BLK_MQ_F_NO_SCHED))
+ return false;
+ return true;
+}
+
/*
- * 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 single queue devices, default to using mq-deadline. If we have multiple
+ * queues or mq-deadline is not available, default to "none".
*/
-int elevator_init_mq(struct request_queue *q)
+static struct elevator_type *elevator_get_default(struct request_queue *q)
+{
+ if (q->nr_hw_queues != 1)
+ return NULL;
+
+ return elevator_get(q, "mq-deadline", false);
+}
+
+/*
+ * Get the first elevator providing the features required by the request queue.
+ * Default to "none" if no matching elevator is found.
+ */
+static struct elevator_type *elevator_get_by_features(struct request_queue *q)
+{
+ struct elevator_type *e, *found = NULL;
+
+ spin_lock(&elv_list_lock);
+
+ list_for_each_entry(e, &elv_list, list) {
+ if (elv_support_features(e->elevator_features,
+ q->required_elevator_features)) {
+ found = e;
+ break;
+ }
+ }
+
+ if (found && !try_module_get(found->elevator_owner))
+ found = NULL;
+
+ spin_unlock(&elv_list_lock);
+ return found;
+}
+
+/*
+ * For a device queue that has no required features, use the default elevator
+ * settings. Otherwise, use the first elevator available matching the required
+ * features. If no suitable elevator is find or if the chosen elevator
+ * initialization fails, fall back to the "none" elevator (no elevator).
+ */
+void elevator_init_mq(struct request_queue *q)
{
struct elevator_type *e;
- int err = 0;
+ int err;
- if (q->nr_hw_queues != 1)
- return 0;
+ if (!elv_support_iosched(q))
+ return;
+
+ WARN_ON_ONCE(test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags));
- /*
- * q->sysfs_lock must be held to provide mutual exclusion between
- * elevator_switch() and here.
- */
- mutex_lock(&q->sysfs_lock);
if (unlikely(q->elevator))
- goto out_unlock;
+ return;
- e = elevator_get(q, "mq-deadline", false);
+ if (!q->required_elevator_features)
+ e = elevator_get_default(q);
+ else
+ e = elevator_get_by_features(q);
if (!e)
- goto out_unlock;
+ return;
+
+ blk_mq_freeze_queue(q);
+ blk_mq_quiesce_queue(q);
err = blk_mq_init_sched(q, e);
- if (err)
+
+ blk_mq_unquiesce_queue(q);
+ blk_mq_unfreeze_queue(q);
+
+ if (err) {
+ pr_warn("\"%s\" elevator initialization failed, "
+ "falling back to \"none\"\n", e->elevator_name);
elevator_put(e);
-out_unlock:
- mutex_unlock(&q->sysfs_lock);
- return err;
+ }
}
@@ -660,7 +761,7 @@ static int __elevator_change(struct request_queue *q, const char *name)
struct elevator_type *e;
/* Make sure queue is not in the middle of being removed */
- if (!test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags))
+ if (!blk_queue_registered(q))
return -ENOENT;
/*
@@ -677,7 +778,8 @@ static int __elevator_change(struct request_queue *q, const char *name)
if (!e)
return -EINVAL;
- if (q->elevator && elevator_match(q->elevator->type, elevator_name)) {
+ if (q->elevator &&
+ elevator_match(q->elevator->type, elevator_name, 0)) {
elevator_put(e);
return 0;
}
@@ -685,13 +787,6 @@ static int __elevator_change(struct request_queue *q, const char *name)
return elevator_switch(q, e);
}
-static inline bool elv_support_iosched(struct request_queue *q)
-{
- if (q->tag_set && (q->tag_set->flags & BLK_MQ_F_NO_SCHED))
- return false;
- return true;
-}
-
ssize_t elv_iosched_store(struct request_queue *q, const char *name,
size_t count)
{
@@ -724,11 +819,13 @@ ssize_t elv_iosched_show(struct request_queue *q, char *name)
spin_lock(&elv_list_lock);
list_for_each_entry(__e, &elv_list, list) {
- if (elv && elevator_match(elv, __e->elevator_name)) {
+ if (elv && elevator_match(elv, __e->elevator_name, 0)) {
len += sprintf(name+len, "[%s] ", elv->elevator_name);
continue;
}
- if (elv_support_iosched(q))
+ if (elv_support_iosched(q) &&
+ elevator_match(__e, __e->elevator_name,
+ q->required_elevator_features))
len += sprintf(name+len, "%s ", __e->elevator_name);
}
spin_unlock(&elv_list_lock);
diff --git a/block/genhd.c b/block/genhd.c
index 54f1f0d381f4..26b31fcae217 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -695,6 +695,15 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk,
dev_t devt;
int retval;
+ /*
+ * The disk queue should now be all set with enough information about
+ * the device for the elevator code to pick an adequate default
+ * elevator if one is needed, that is, for devices requesting queue
+ * registration.
+ */
+ if (register_queue)
+ elevator_init_mq(disk->queue);
+
/* minors == 0 indicates to use ext devt from part0 and should
* be accompanied with EXT_DEVT flag. Make sure all
* parameters make sense.
diff --git a/block/mq-deadline.c b/block/mq-deadline.c
index 2a2a2e82832e..b490f47fd553 100644
--- a/block/mq-deadline.c
+++ b/block/mq-deadline.c
@@ -377,13 +377,6 @@ done:
* hardware queue, but we may return a request that is for a
* different hardware queue. This is because mq-deadline has shared
* state for all hardware queues, in terms of sorting, FIFOs, etc.
- *
- * For a zoned block device, __dd_dispatch_request() may return NULL
- * if all the queued write requests are directed at zones that are already
- * locked due to on-going write requests. In this case, make sure to mark
- * the queue as needing a restart to ensure that the queue is run again
- * and the pending writes dispatched once the target zones for the ongoing
- * write requests are unlocked in dd_finish_request().
*/
static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
{
@@ -392,9 +385,6 @@ static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
spin_lock(&dd->lock);
rq = __dd_dispatch_request(dd);
- if (!rq && blk_queue_is_zoned(hctx->queue) &&
- !list_empty(&dd->fifo_list[WRITE]))
- blk_mq_sched_mark_restart_hctx(hctx);
spin_unlock(&dd->lock);
return rq;
@@ -561,6 +551,13 @@ static void dd_prepare_request(struct request *rq, struct bio *bio)
* spinlock so that the zone is never unlocked while deadline_fifo_request()
* or deadline_next_request() are executing. This function is called for
* all requests, whether or not these requests complete successfully.
+ *
+ * For a zoned block device, __dd_dispatch_request() may have stopped
+ * dispatching requests if all the queued requests are write requests directed
+ * at zones that are already locked due to on-going write requests. To ensure
+ * write request dispatch progress in this case, mark the queue as needing a
+ * restart to ensure that the queue is run again after completion of the
+ * request and zones being unlocked.
*/
static void dd_finish_request(struct request *rq)
{
@@ -572,6 +569,8 @@ static void dd_finish_request(struct request *rq)
spin_lock_irqsave(&dd->zone_lock, flags);
blk_req_zone_write_unlock(rq);
+ if (!list_empty(&dd->fifo_list[WRITE]))
+ blk_mq_sched_mark_restart_hctx(rq->mq_hctx);
spin_unlock_irqrestore(&dd->zone_lock, flags);
}
}
@@ -795,6 +794,7 @@ static struct elevator_type mq_deadline = {
.elevator_attrs = deadline_attrs,
.elevator_name = "mq-deadline",
.elevator_alias = "deadline",
+ .elevator_features = ELEVATOR_F_ZBD_SEQ_WRITE,
.elevator_owner = THIS_MODULE,
};
MODULE_ALIAS("mq-deadline-iosched");
diff --git a/block/opal_proto.h b/block/opal_proto.h
index 466ec7be16ef..5532412d567c 100644
--- a/block/opal_proto.h
+++ b/block/opal_proto.h
@@ -119,8 +119,6 @@ enum opal_uid {
OPAL_UID_HEXFF,
};
-#define OPAL_METHOD_LENGTH 8
-
/* Enum for indexing the OPALMETHOD array */
enum opal_method {
OPAL_PROPERTIES,
@@ -167,7 +165,6 @@ enum opal_token {
OPAL_TABLE_LASTID = 0x0A,
OPAL_TABLE_MIN = 0x0B,
OPAL_TABLE_MAX = 0x0C,
-
/* authority table */
OPAL_PIN = 0x03,
/* locking tokens */
@@ -182,7 +179,7 @@ enum opal_token {
OPAL_LIFECYCLE = 0x06,
/* locking info table */
OPAL_MAXRANGES = 0x04,
- /* mbr control */
+ /* mbr control */
OPAL_MBRENABLE = 0x01,
OPAL_MBRDONE = 0x02,
/* properties */
diff --git a/block/sed-opal.c b/block/sed-opal.c
index 7e1a444a25b2..4e95a9792162 100644
--- a/block/sed-opal.c
+++ b/block/sed-opal.c
@@ -129,7 +129,6 @@ static const u8 opaluid[][OPAL_UID_LENGTH] = {
{ 0x00, 0x00, 0x00, 0x09, 0x00, 0x00, 0x84, 0x01 },
/* tables */
-
[OPAL_TABLE_TABLE]
{ 0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0x01 },
[OPAL_LOCKINGRANGE_GLOBAL] =
@@ -152,7 +151,6 @@ static const u8 opaluid[][OPAL_UID_LENGTH] = {
{ 0x00, 0x00, 0x08, 0x01, 0x00, 0x00, 0x00, 0x00 },
/* C_PIN_TABLE object ID's */
-
[OPAL_C_PIN_MSID] =
{ 0x00, 0x00, 0x00, 0x0B, 0x00, 0x00, 0x84, 0x02},
[OPAL_C_PIN_SID] =
@@ -161,7 +159,6 @@ static const u8 opaluid[][OPAL_UID_LENGTH] = {
{ 0x00, 0x00, 0x00, 0x0B, 0x00, 0x01, 0x00, 0x01},
/* half UID's (only first 4 bytes used) */
-
[OPAL_HALF_UID_AUTHORITY_OBJ_REF] =
{ 0x00, 0x00, 0x0C, 0x05, 0xff, 0xff, 0xff, 0xff },
[OPAL_HALF_UID_BOOLEAN_ACE] =
@@ -517,6 +514,7 @@ static int opal_discovery0(struct opal_dev *dev, void *data)
ret = opal_recv_cmd(dev);
if (ret)
return ret;
+
return opal_discovery0_end(dev);
}
@@ -525,6 +523,7 @@ static int opal_discovery0_step(struct opal_dev *dev)
const struct opal_step discovery0_step = {
opal_discovery0,
};
+
return execute_step(dev, &discovery0_step, 0);
}
@@ -551,6 +550,7 @@ static void add_token_u8(int *err, struct opal_dev *cmd, u8 tok)
{
if (!can_add(err, cmd, 1))
return;
+
cmd->cmd[cmd->pos++] = tok;
}
@@ -577,6 +577,7 @@ static void add_medium_atom_header(struct opal_dev *cmd, bool bytestring,
header0 |= bytestring ? MEDIUM_ATOM_BYTESTRING : 0;
header0 |= has_sign ? MEDIUM_ATOM_SIGNED : 0;
header0 |= (len >> 8) & MEDIUM_ATOM_LEN_MASK;
+
cmd->cmd[cmd->pos++] = header0;
cmd->cmd[cmd->pos++] = len;
}
@@ -649,6 +650,7 @@ static int build_locking_range(u8 *buffer, size_t length, u8 lr)
if (lr == 0)
return 0;
+
buffer[5] = LOCKING_RANGE_NON_GLOBAL;
buffer[7] = lr;
@@ -903,10 +905,6 @@ static int response_parse(const u8 *buf, size_t length,
num_entries++;
}
- if (num_entries == 0) {
- pr_debug("Couldn't parse response.\n");
- return -EINVAL;
- }
resp->num = num_entries;
return 0;
@@ -945,6 +943,7 @@ static size_t response_get_string(const struct parsed_resp *resp, int n,
}
*store = tok->pos + skip;
+
return tok->len - skip;
}
@@ -1062,6 +1061,7 @@ static int start_opal_session_cont(struct opal_dev *dev)
dev->hsn = hsn;
dev->tsn = tsn;
+
return 0;
}
@@ -1084,6 +1084,7 @@ static int end_session_cont(struct opal_dev *dev)
{
dev->hsn = 0;
dev->tsn = 0;
+
return parse_and_check_status(dev);
}
@@ -1172,6 +1173,7 @@ static int gen_key(struct opal_dev *dev, void *data)
return err;
}
+
return finalize_and_send(dev, parse_and_check_status);
}
@@ -1184,12 +1186,14 @@ static int get_active_key_cont(struct opal_dev *dev)
error = parse_and_check_status(dev);
if (error)
return error;
+
keylen = response_get_string(&dev->parsed, 4, &activekey);
if (!activekey) {
pr_debug("%s: Couldn't extract the Activekey from the response\n",
__func__);
return OPAL_INVAL_PARAM;
}
+
dev->prev_data = kmemdup(activekey, keylen, GFP_KERNEL);
if (!dev->prev_data)
@@ -1251,6 +1255,7 @@ static int generic_lr_enable_disable(struct opal_dev *dev,
add_token_u8(&err, dev, OPAL_ENDLIST);
add_token_u8(&err, dev, OPAL_ENDNAME);
+
return err;
}
@@ -1263,6 +1268,7 @@ static inline int enable_global_lr(struct opal_dev *dev, u8 *uid,
0, 0);
if (err)
pr_debug("Failed to create enable global lr command\n");
+
return err;
}
@@ -1313,7 +1319,6 @@ static int setup_locking_range(struct opal_dev *dev, void *data)
if (err) {
pr_debug("Error building Setup Locking range command.\n");
return err;
-
}
return finalize_and_send(dev, parse_and_check_status);
@@ -1393,6 +1398,7 @@ static int start_SIDASP_opal_session(struct opal_dev *dev, void *data)
kfree(key);
dev->prev_data = NULL;
}
+
return ret;
}
@@ -1518,6 +1524,7 @@ static int erase_locking_range(struct opal_dev *dev, void *data)
pr_debug("Error building Erase Locking Range Command.\n");
return err;
}
+
return finalize_and_send(dev, parse_and_check_status);
}
@@ -1636,6 +1643,7 @@ static int write_shadow_mbr(struct opal_dev *dev, void *data)
off += len;
}
+
return err;
}
@@ -1816,6 +1824,7 @@ static int lock_unlock_locking_range(struct opal_dev *dev, void *data)
pr_debug("Error building SET command.\n");
return err;
}
+
return finalize_and_send(dev, parse_and_check_status);
}
@@ -1857,6 +1866,7 @@ static int lock_unlock_locking_range_sum(struct opal_dev *dev, void *data)
pr_debug("Error building SET command.\n");
return ret;
}
+
return finalize_and_send(dev, parse_and_check_status);
}
@@ -1957,6 +1967,7 @@ static int end_opal_session(struct opal_dev *dev, void *data)
if (err < 0)
return err;
+
return finalize_and_send(dev, end_session_cont);
}
@@ -1965,6 +1976,7 @@ static int end_opal_session_error(struct opal_dev *dev)
const struct opal_step error_end_session = {
end_opal_session,
};
+
return execute_step(dev, &error_end_session, 0);
}
@@ -1984,6 +1996,7 @@ static int check_opal_support(struct opal_dev *dev)
ret = opal_discovery0_step(dev);
dev->supported = !ret;
mutex_unlock(&dev->dev_lock);
+
return ret;
}
@@ -2004,6 +2017,7 @@ void free_opal_dev(struct opal_dev *dev)
{
if (!dev)
return;
+
clean_opal_dev(dev);
kfree(dev);
}
@@ -2026,6 +2040,7 @@ struct opal_dev *init_opal_dev(void *data, sec_send_recv *send_recv)
kfree(dev);
return NULL;
}
+
return dev;
}
EXPORT_SYMBOL(init_opal_dev);
@@ -2045,6 +2060,7 @@ static int opal_secure_erase_locking_range(struct opal_dev *dev,
setup_opal_dev(dev);
ret = execute_steps(dev, erase_steps, ARRAY_SIZE(erase_steps));
mutex_unlock(&dev->dev_lock);
+
return ret;
}
@@ -2062,6 +2078,7 @@ static int opal_erase_locking_range(struct opal_dev *dev,
setup_opal_dev(dev);
ret = execute_steps(dev, erase_steps, ARRAY_SIZE(erase_steps));
mutex_unlock(&dev->dev_lock);
+
return ret;
}
@@ -2089,6 +2106,7 @@ static int opal_enable_disable_shadow_mbr(struct opal_dev *dev,
setup_opal_dev(dev);
ret = execute_steps(dev, mbr_steps, ARRAY_SIZE(mbr_steps));
mutex_unlock(&dev->dev_lock);
+
return ret;
}
@@ -2113,6 +2131,7 @@ static int opal_set_mbr_done(struct opal_dev *dev,
setup_opal_dev(dev);
ret = execute_steps(dev, mbr_steps, ARRAY_SIZE(mbr_steps));
mutex_unlock(&dev->dev_lock);
+
return ret;
}
@@ -2133,6 +2152,7 @@ static int opal_write_shadow_mbr(struct opal_dev *dev,
setup_opal_dev(dev);
ret = execute_steps(dev, mbr_steps, ARRAY_SIZE(mbr_steps));
mutex_unlock(&dev->dev_lock);
+
return ret;
}
@@ -2151,6 +2171,7 @@ static int opal_save(struct opal_dev *dev, struct opal_lock_unlock *lk_unlk)
setup_opal_dev(dev);
add_suspend_info(dev, suspend);
mutex_unlock(&dev->dev_lock);
+
return 0;
}
@@ -2169,12 +2190,14 @@ static int opal_add_user_to_lr(struct opal_dev *dev,
pr_debug("Locking state was not RO or RW\n");
return -EINVAL;
}
+
if (lk_unlk->session.who < OPAL_USER1 ||
lk_unlk->session.who > OPAL_USER9) {
pr_debug("Authority was not within the range of users: %d\n",
lk_unlk->session.who);
return -EINVAL;
}
+
if (lk_unlk->session.sum) {
pr_debug("%s not supported in sum. Use setup locking range\n",
__func__);
@@ -2185,6 +2208,7 @@ static int opal_add_user_to_lr(struct opal_dev *dev,
setup_opal_dev(dev);
ret = execute_steps(dev, steps, ARRAY_SIZE(steps));
mutex_unlock(&dev->dev_lock);
+
return ret;
}
@@ -2267,6 +2291,7 @@ static int opal_lock_unlock(struct opal_dev *dev,
mutex_lock(&dev->dev_lock);
ret = __opal_lock_unlock(dev, lk_unlk);
mutex_unlock(&dev->dev_lock);
+
return ret;
}
@@ -2289,6 +2314,7 @@ static int opal_take_ownership(struct opal_dev *dev, struct opal_key *opal)
setup_opal_dev(dev);
ret = execute_steps(dev, owner_steps, ARRAY_SIZE(owner_steps));
mutex_unlock(&dev->dev_lock);
+
return ret;
}
@@ -2310,6 +2336,7 @@ static int opal_activate_lsp(struct opal_dev *dev,
setup_opal_dev(dev);
ret = execute_steps(dev, active_steps, ARRAY_SIZE(active_steps));
mutex_unlock(&dev->dev_lock);
+
return ret;
}
@@ -2327,6 +2354,7 @@ static int opal_setup_locking_range(struct opal_dev *dev,
setup_opal_dev(dev);
ret = execute_steps(dev, lr_steps, ARRAY_SIZE(lr_steps));
mutex_unlock(&dev->dev_lock);
+
return ret;
}
@@ -2347,6 +2375,7 @@ static int opal_set_new_pw(struct opal_dev *dev, struct opal_new_pw *opal_pw)
setup_opal_dev(dev);
ret = execute_steps(dev, pw_steps, ARRAY_SIZE(pw_steps));
mutex_unlock(&dev->dev_lock);
+
return ret;
}
@@ -2371,6 +2400,7 @@ static int opal_activate_user(struct opal_dev *dev,
setup_opal_dev(dev);
ret = execute_steps(dev, act_steps, ARRAY_SIZE(act_steps));
mutex_unlock(&dev->dev_lock);
+
return ret;
}
@@ -2382,6 +2412,7 @@ bool opal_unlock_from_suspend(struct opal_dev *dev)
if (!dev)
return false;
+
if (!dev->supported)
return false;
@@ -2399,6 +2430,7 @@ bool opal_unlock_from_suspend(struct opal_dev *dev)
suspend->unlk.session.sum);
was_failure = true;
}
+
if (dev->mbr_enabled) {
ret = __opal_set_mbr_done(dev, &suspend->unlk.session.opal_key);
if (ret)
@@ -2406,6 +2438,7 @@ bool opal_unlock_from_suspend(struct opal_dev *dev)
}
}
mutex_unlock(&dev->dev_lock);
+
return was_failure;
}
EXPORT_SYMBOL(opal_unlock_from_suspend);
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 0469aceaa230..485865fd0412 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -3780,7 +3780,7 @@ static int compat_getdrvprm(int drive,
v.native_format = UDP->native_format;
mutex_unlock(&floppy_mutex);
- if (copy_from_user(arg, &v, sizeof(struct compat_floppy_drive_params)))
+ if (copy_to_user(arg, &v, sizeof(struct compat_floppy_drive_params)))
return -EFAULT;
return 0;
}
@@ -3816,7 +3816,7 @@ static int compat_getdrvstat(int drive, bool poll,
v.bufblocks = UDRS->bufblocks;
mutex_unlock(&floppy_mutex);
- if (copy_from_user(arg, &v, sizeof(struct compat_floppy_drive_struct)))
+ if (copy_to_user(arg, &v, sizeof(struct compat_floppy_drive_struct)))
return -EFAULT;
return 0;
Eintr:
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index ab7ca5989097..1410fa893653 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1755,6 +1755,7 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode,
case LOOP_SET_FD:
case LOOP_CHANGE_FD:
case LOOP_SET_BLOCK_SIZE:
+ case LOOP_SET_DIRECT_IO:
err = lo_ioctl(bdev, mode, cmd, arg);
break;
default:
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index e21d2ded732b..a8e3815295fe 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -108,6 +108,7 @@ struct nbd_device {
struct nbd_config *config;
struct mutex config_lock;
struct gendisk *disk;
+ struct workqueue_struct *recv_workq;
struct list_head list;
struct task_struct *task_recv;
@@ -121,6 +122,7 @@ struct nbd_cmd {
struct mutex lock;
int index;
int cookie;
+ int retries;
blk_status_t status;
unsigned long flags;
u32 cmd_cookie;
@@ -138,7 +140,6 @@ static struct dentry *nbd_dbg_dir;
static unsigned int nbds_max = 16;
static int max_part = 16;
-static struct workqueue_struct *recv_workqueue;
static int part_shift;
static int nbd_dev_dbg_init(struct nbd_device *nbd);
@@ -344,6 +345,22 @@ static void sock_shutdown(struct nbd_device *nbd)
dev_warn(disk_to_dev(nbd->disk), "shutting down sockets\n");
}
+static u32 req_to_nbd_cmd_type(struct request *req)
+{
+ switch (req_op(req)) {
+ case REQ_OP_DISCARD:
+ return NBD_CMD_TRIM;
+ case REQ_OP_FLUSH:
+ return NBD_CMD_FLUSH;
+ case REQ_OP_WRITE:
+ return NBD_CMD_WRITE;
+ case REQ_OP_READ:
+ return NBD_CMD_READ;
+ default:
+ return U32_MAX;
+ }
+}
+
static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
bool reserved)
{
@@ -357,8 +374,10 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
}
config = nbd->config;
- if (!mutex_trylock(&cmd->lock))
+ if (!mutex_trylock(&cmd->lock)) {
+ nbd_config_put(nbd);
return BLK_EH_RESET_TIMER;
+ }
if (config->num_connections > 1) {
dev_err_ratelimited(nbd_to_dev(nbd),
@@ -389,10 +408,25 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
nbd_config_put(nbd);
return BLK_EH_DONE;
}
- } else {
- dev_err_ratelimited(nbd_to_dev(nbd),
- "Connection timed out\n");
}
+
+ if (!nbd->tag_set.timeout) {
+ /*
+ * Userspace sets timeout=0 to disable socket disconnection,
+ * so just warn and reset the timer.
+ */
+ cmd->retries++;
+ dev_info(nbd_to_dev(nbd), "Possible stuck request %p: control (%s@%llu,%uB). Runtime %u seconds\n",
+ req, nbdcmd_to_ascii(req_to_nbd_cmd_type(req)),
+ (unsigned long long)blk_rq_pos(req) << 9,
+ blk_rq_bytes(req), (req->timeout / HZ) * cmd->retries);
+
+ mutex_unlock(&cmd->lock);
+ nbd_config_put(nbd);
+ return BLK_EH_RESET_TIMER;
+ }
+
+ dev_err_ratelimited(nbd_to_dev(nbd), "Connection timed out\n");
set_bit(NBD_TIMEDOUT, &config->runtime_flags);
cmd->status = BLK_STS_IOERR;
mutex_unlock(&cmd->lock);
@@ -480,22 +514,9 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
iov_iter_kvec(&from, WRITE, &iov, 1, sizeof(request));
- switch (req_op(req)) {
- case REQ_OP_DISCARD:
- type = NBD_CMD_TRIM;
- break;
- case REQ_OP_FLUSH:
- type = NBD_CMD_FLUSH;
- break;
- case REQ_OP_WRITE:
- type = NBD_CMD_WRITE;
- break;
- case REQ_OP_READ:
- type = NBD_CMD_READ;
- break;
- default:
+ type = req_to_nbd_cmd_type(req);
+ if (type == U32_MAX)
return -EIO;
- }
if (rq_data_dir(req) == WRITE &&
(config->flags & NBD_FLAG_READ_ONLY)) {
@@ -526,6 +547,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
}
cmd->index = index;
cmd->cookie = nsock->cookie;
+ cmd->retries = 0;
request.type = htonl(type | nbd_cmd_flags);
if (type != NBD_CMD_FLUSH) {
request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9);
@@ -1036,7 +1058,7 @@ static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg)
/* We take the tx_mutex in an error path in the recv_work, so we
* need to queue_work outside of the tx_mutex.
*/
- queue_work(recv_workqueue, &args->work);
+ queue_work(nbd->recv_workq, &args->work);
atomic_inc(&config->live_connections);
wake_up(&config->conn_wait);
@@ -1137,6 +1159,10 @@ static void nbd_config_put(struct nbd_device *nbd)
kfree(nbd->config);
nbd->config = NULL;
+ if (nbd->recv_workq)
+ destroy_workqueue(nbd->recv_workq);
+ nbd->recv_workq = NULL;
+
nbd->tag_set.timeout = 0;
nbd->disk->queue->limits.discard_granularity = 0;
nbd->disk->queue->limits.discard_alignment = 0;
@@ -1165,6 +1191,14 @@ static int nbd_start_device(struct nbd_device *nbd)
return -EINVAL;
}
+ nbd->recv_workq = alloc_workqueue("knbd%d-recv",
+ WQ_MEM_RECLAIM | WQ_HIGHPRI |
+ WQ_UNBOUND, 0, nbd->index);
+ if (!nbd->recv_workq) {
+ dev_err(disk_to_dev(nbd->disk), "Could not allocate knbd recv work queue.\n");
+ return -ENOMEM;
+ }
+
blk_mq_update_nr_hw_queues(&nbd->tag_set, config->num_connections);
nbd->task_recv = current;
@@ -1195,7 +1229,7 @@ static int nbd_start_device(struct nbd_device *nbd)
INIT_WORK(&args->work, recv_work);
args->nbd = nbd;
args->index = i;
- queue_work(recv_workqueue, &args->work);
+ queue_work(nbd->recv_workq, &args->work);
}
nbd_size_update(nbd);
return error;
@@ -1215,8 +1249,10 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *b
mutex_unlock(&nbd->config_lock);
ret = wait_event_interruptible(config->recv_wq,
atomic_read(&config->recv_threads) == 0);
- if (ret)
+ if (ret) {
sock_shutdown(nbd);
+ flush_workqueue(nbd->recv_workq);
+ }
mutex_lock(&nbd->config_lock);
nbd_bdev_reset(bdev);
/* user requested, ignore socket errors */
@@ -1246,6 +1282,13 @@ static bool nbd_is_valid_blksize(unsigned long blksize)
return true;
}
+static void nbd_set_cmd_timeout(struct nbd_device *nbd, u64 timeout)
+{
+ nbd->tag_set.timeout = timeout * HZ;
+ if (timeout)
+ blk_queue_rq_timeout(nbd->disk->queue, timeout * HZ);
+}
+
/* Must be called with config_lock held */
static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
unsigned int cmd, unsigned long arg)
@@ -1276,10 +1319,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
nbd_size_set(nbd, config->blksize, arg);
return 0;
case NBD_SET_TIMEOUT:
- if (arg) {
- nbd->tag_set.timeout = arg * HZ;
- blk_queue_rq_timeout(nbd->disk->queue, arg * HZ);
- }
+ nbd_set_cmd_timeout(nbd, arg);
return 0;
case NBD_SET_FLAGS:
@@ -1799,11 +1839,9 @@ again:
if (ret)
goto out;
- if (info->attrs[NBD_ATTR_TIMEOUT]) {
- u64 timeout = nla_get_u64(info->attrs[NBD_ATTR_TIMEOUT]);
- nbd->tag_set.timeout = timeout * HZ;
- blk_queue_rq_timeout(nbd->disk->queue, timeout * HZ);
- }
+ if (info->attrs[NBD_ATTR_TIMEOUT])
+ nbd_set_cmd_timeout(nbd,
+ nla_get_u64(info->attrs[NBD_ATTR_TIMEOUT]));
if (info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]) {
config->dead_conn_timeout =
nla_get_u64(info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]);
@@ -1875,6 +1913,12 @@ static void nbd_disconnect_and_put(struct nbd_device *nbd)
nbd_disconnect(nbd);
nbd_clear_sock(nbd);
mutex_unlock(&nbd->config_lock);
+ /*
+ * Make sure recv thread has finished, so it does not drop the last
+ * config ref and try to destroy the workqueue from inside the work
+ * queue.
+ */
+ flush_workqueue(nbd->recv_workq);
if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
&nbd->config->runtime_flags))
nbd_config_put(nbd);
@@ -1971,11 +2015,9 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
if (ret)
goto out;
- if (info->attrs[NBD_ATTR_TIMEOUT]) {
- u64 timeout = nla_get_u64(info->attrs[NBD_ATTR_TIMEOUT]);
- nbd->tag_set.timeout = timeout * HZ;
- blk_queue_rq_timeout(nbd->disk->queue, timeout * HZ);
- }
+ if (info->attrs[NBD_ATTR_TIMEOUT])
+ nbd_set_cmd_timeout(nbd,
+ nla_get_u64(info->attrs[NBD_ATTR_TIMEOUT]));
if (info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]) {
config->dead_conn_timeout =
nla_get_u64(info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]);
@@ -2261,20 +2303,12 @@ static int __init nbd_init(void)
if (nbds_max > 1UL << (MINORBITS - part_shift))
return -EINVAL;
- recv_workqueue = alloc_workqueue("knbd-recv",
- WQ_MEM_RECLAIM | WQ_HIGHPRI |
- WQ_UNBOUND, 0);
- if (!recv_workqueue)
- return -ENOMEM;
- if (register_blkdev(NBD_MAJOR, "nbd")) {
- destroy_workqueue(recv_workqueue);
+ if (register_blkdev(NBD_MAJOR, "nbd"))
return -EIO;
- }
if (genl_register_family(&nbd_genl_family)) {
unregister_blkdev(NBD_MAJOR, "nbd");
- destroy_workqueue(recv_workqueue);
return -EINVAL;
}
nbd_dbg_init();
@@ -2316,7 +2350,6 @@ static void __exit nbd_cleanup(void)
idr_destroy(&nbd_index_idr);
genl_unregister_family(&nbd_genl_family);
- destroy_workqueue(recv_workqueue);
unregister_blkdev(NBD_MAJOR, "nbd");
}
diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h
index a1b9929bd911..a235c45e22a7 100644
--- a/drivers/block/null_blk.h
+++ b/drivers/block/null_blk.h
@@ -2,6 +2,9 @@
#ifndef __BLK_NULL_BLK_H
#define __BLK_NULL_BLK_H
+#undef pr_fmt
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/blkdev.h>
#include <linux/slab.h>
#include <linux/blk-mq.h>
@@ -90,13 +93,13 @@ int null_zone_init(struct nullb_device *dev);
void null_zone_exit(struct nullb_device *dev);
int null_zone_report(struct gendisk *disk, sector_t sector,
struct blk_zone *zones, unsigned int *nr_zones);
-void null_zone_write(struct nullb_cmd *cmd, sector_t sector,
- unsigned int nr_sectors);
-void null_zone_reset(struct nullb_cmd *cmd, sector_t sector);
+blk_status_t null_handle_zoned(struct nullb_cmd *cmd,
+ enum req_opf op, sector_t sector,
+ sector_t nr_sectors);
#else
static inline int null_zone_init(struct nullb_device *dev)
{
- pr_err("null_blk: CONFIG_BLK_DEV_ZONED not enabled\n");
+ pr_err("CONFIG_BLK_DEV_ZONED not enabled\n");
return -EINVAL;
}
static inline void null_zone_exit(struct nullb_device *dev) {}
@@ -106,10 +109,11 @@ static inline int null_zone_report(struct gendisk *disk, sector_t sector,
{
return -EOPNOTSUPP;
}
-static inline void null_zone_write(struct nullb_cmd *cmd, sector_t sector,
- unsigned int nr_sectors)
+static inline blk_status_t null_handle_zoned(struct nullb_cmd *cmd,
+ enum req_opf op, sector_t sector,
+ sector_t nr_sectors)
{
+ return BLK_STS_NOTSUPP;
}
-static inline void null_zone_reset(struct nullb_cmd *cmd, sector_t sector) {}
#endif /* CONFIG_BLK_DEV_ZONED */
#endif /* __NULL_BLK_H */
diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c
index 99328ded60d1..0e7da5015ccd 100644
--- a/drivers/block/null_blk_main.c
+++ b/drivers/block/null_blk_main.c
@@ -141,8 +141,8 @@ static int g_bs = 512;
module_param_named(bs, g_bs, int, 0444);
MODULE_PARM_DESC(bs, "Block size (in bytes)");
-static int nr_devices = 1;
-module_param(nr_devices, int, 0444);
+static unsigned int nr_devices = 1;
+module_param(nr_devices, uint, 0444);
MODULE_PARM_DESC(nr_devices, "Number of devices to register");
static bool g_blocking;
@@ -1133,93 +1133,61 @@ static void null_restart_queue_async(struct nullb *nullb)
blk_mq_start_stopped_hw_queues(q, true);
}
-static blk_status_t null_handle_cmd(struct nullb_cmd *cmd)
+static inline blk_status_t null_handle_throttled(struct nullb_cmd *cmd)
{
struct nullb_device *dev = cmd->nq->dev;
struct nullb *nullb = dev->nullb;
- int err = 0;
+ blk_status_t sts = BLK_STS_OK;
+ struct request *rq = cmd->rq;
- if (test_bit(NULLB_DEV_FL_THROTTLED, &dev->flags)) {
- struct request *rq = cmd->rq;
-
- if (!hrtimer_active(&nullb->bw_timer))
- hrtimer_restart(&nullb->bw_timer);
-
- if (atomic_long_sub_return(blk_rq_bytes(rq),
- &nullb->cur_bytes) < 0) {
- null_stop_queue(nullb);
- /* race with timer */
- if (atomic_long_read(&nullb->cur_bytes) > 0)
- null_restart_queue_async(nullb);
- /* requeue request */
- return BLK_STS_DEV_RESOURCE;
- }
- }
+ if (!hrtimer_active(&nullb->bw_timer))
+ hrtimer_restart(&nullb->bw_timer);
- if (nullb->dev->badblocks.shift != -1) {
- int bad_sectors;
- sector_t sector, size, first_bad;
- bool is_flush = true;
-
- if (dev->queue_mode == NULL_Q_BIO &&
- bio_op(cmd->bio) != REQ_OP_FLUSH) {
- is_flush = false;
- sector = cmd->bio->bi_iter.bi_sector;
- size = bio_sectors(cmd->bio);
- }
- if (dev->queue_mode != NULL_Q_BIO &&
- req_op(cmd->rq) != REQ_OP_FLUSH) {
- is_flush = false;
- sector = blk_rq_pos(cmd->rq);
- size = blk_rq_sectors(cmd->rq);
- }
- if (!is_flush && badblocks_check(&nullb->dev->badblocks, sector,
- size, &first_bad, &bad_sectors)) {
- cmd->error = BLK_STS_IOERR;
- goto out;
- }
+ if (atomic_long_sub_return(blk_rq_bytes(rq), &nullb->cur_bytes) < 0) {
+ null_stop_queue(nullb);
+ /* race with timer */
+ if (atomic_long_read(&nullb->cur_bytes) > 0)
+ null_restart_queue_async(nullb);
+ /* requeue request */
+ sts = BLK_STS_DEV_RESOURCE;
}
+ return sts;
+}
- if (dev->memory_backed) {
- if (dev->queue_mode == NULL_Q_BIO) {
- if (bio_op(cmd->bio) == REQ_OP_FLUSH)
- err = null_handle_flush(nullb);
- else
- err = null_handle_bio(cmd);
- } else {
- if (req_op(cmd->rq) == REQ_OP_FLUSH)
- err = null_handle_flush(nullb);
- else
- err = null_handle_rq(cmd);
- }
- }
- cmd->error = errno_to_blk_status(err);
+static inline blk_status_t null_handle_badblocks(struct nullb_cmd *cmd,
+ sector_t sector,
+ sector_t nr_sectors)
+{
+ struct badblocks *bb = &cmd->nq->dev->badblocks;
+ sector_t first_bad;
+ int bad_sectors;
- if (!cmd->error && dev->zoned) {
- sector_t sector;
- unsigned int nr_sectors;
- enum req_opf op;
+ if (badblocks_check(bb, sector, nr_sectors, &first_bad, &bad_sectors))
+ return BLK_STS_IOERR;
- if (dev->queue_mode == NULL_Q_BIO) {
- op = bio_op(cmd->bio);
- sector = cmd->bio->bi_iter.bi_sector;
- nr_sectors = cmd->bio->bi_iter.bi_size >> 9;
- } else {
- op = req_op(cmd->rq);
- sector = blk_rq_pos(cmd->rq);
- nr_sectors = blk_rq_sectors(cmd->rq);
- }
+ return BLK_STS_OK;
+}
- if (op == REQ_OP_WRITE)
- null_zone_write(cmd, sector, nr_sectors);
- else if (op == REQ_OP_ZONE_RESET)
- null_zone_reset(cmd, sector);
- }
-out:
+static inline blk_status_t null_handle_memory_backed(struct nullb_cmd *cmd,
+ enum req_opf op)
+{
+ struct nullb_device *dev = cmd->nq->dev;
+ int err;
+
+ if (dev->queue_mode == NULL_Q_BIO)
+ err = null_handle_bio(cmd);
+ else
+ err = null_handle_rq(cmd);
+
+ return errno_to_blk_status(err);
+}
+
+static inline void nullb_complete_cmd(struct nullb_cmd *cmd)
+{
/* Complete IO by inline, softirq or timer */
- switch (dev->irqmode) {
+ switch (cmd->nq->dev->irqmode) {
case NULL_IRQ_SOFTIRQ:
- switch (dev->queue_mode) {
+ switch (cmd->nq->dev->queue_mode) {
case NULL_Q_MQ:
blk_mq_complete_request(cmd->rq);
break;
@@ -1238,6 +1206,40 @@ out:
null_cmd_end_timer(cmd);
break;
}
+}
+
+static blk_status_t null_handle_cmd(struct nullb_cmd *cmd, sector_t sector,
+ sector_t nr_sectors, enum req_opf op)
+{
+ struct nullb_device *dev = cmd->nq->dev;
+ struct nullb *nullb = dev->nullb;
+ blk_status_t sts;
+
+ if (test_bit(NULLB_DEV_FL_THROTTLED, &dev->flags)) {
+ sts = null_handle_throttled(cmd);
+ if (sts != BLK_STS_OK)
+ return sts;
+ }
+
+ if (op == REQ_OP_FLUSH) {
+ cmd->error = errno_to_blk_status(null_handle_flush(nullb));
+ goto out;
+ }
+
+ if (nullb->dev->badblocks.shift != -1) {
+ cmd->error = null_handle_badblocks(cmd, sector, nr_sectors);
+ if (cmd->error != BLK_STS_OK)
+ goto out;
+ }
+
+ if (dev->memory_backed)
+ cmd->error = null_handle_memory_backed(cmd, op);
+
+ if (!cmd->error && dev->zoned)
+ cmd->error = null_handle_zoned(cmd, op, sector, nr_sectors);
+
+out:
+ nullb_complete_cmd(cmd);
return BLK_STS_OK;
}
@@ -1280,6 +1282,8 @@ static struct nullb_queue *nullb_to_queue(struct nullb *nullb)
static blk_qc_t null_queue_bio(struct request_queue *q, struct bio *bio)
{
+ sector_t sector = bio->bi_iter.bi_sector;
+ sector_t nr_sectors = bio_sectors(bio);
struct nullb *nullb = q->queuedata;
struct nullb_queue *nq = nullb_to_queue(nullb);
struct nullb_cmd *cmd;
@@ -1287,7 +1291,7 @@ static blk_qc_t null_queue_bio(struct request_queue *q, struct bio *bio)
cmd = alloc_cmd(nq, 1);
cmd->bio = bio;
- null_handle_cmd(cmd);
+ null_handle_cmd(cmd, sector, nr_sectors, bio_op(bio));
return BLK_QC_T_NONE;
}
@@ -1311,7 +1315,7 @@ static bool should_requeue_request(struct request *rq)
static enum blk_eh_timer_return null_timeout_rq(struct request *rq, bool res)
{
- pr_info("null: rq %p timed out\n", rq);
+ pr_info("rq %p timed out\n", rq);
blk_mq_complete_request(rq);
return BLK_EH_DONE;
}
@@ -1321,6 +1325,8 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
{
struct nullb_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
struct nullb_queue *nq = hctx->driver_data;
+ sector_t nr_sectors = blk_rq_sectors(bd->rq);
+ sector_t sector = blk_rq_pos(bd->rq);
might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING);
@@ -1349,7 +1355,7 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
if (should_timeout_request(bd->rq))
return BLK_STS_OK;
- return null_handle_cmd(cmd);
+ return null_handle_cmd(cmd, sector, nr_sectors, req_op(bd->rq));
}
static const struct blk_mq_ops null_mq_ops = {
@@ -1688,6 +1694,9 @@ static int null_add_dev(struct nullb_device *dev)
blk_queue_chunk_sectors(nullb->q, dev->zone_size_sects);
nullb->q->limits.zoned = BLK_ZONED_HM;
+ blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, nullb->q);
+ blk_queue_required_elevator_features(nullb->q,
+ ELEVATOR_F_ZBD_SEQ_WRITE);
}
nullb->q->queuedata = nullb;
@@ -1739,28 +1748,28 @@ static int __init null_init(void)
struct nullb_device *dev;
if (g_bs > PAGE_SIZE) {
- pr_warn("null_blk: invalid block size\n");
- pr_warn("null_blk: defaults block size to %lu\n", PAGE_SIZE);
+ pr_warn("invalid block size\n");
+ pr_warn("defaults block size to %lu\n", PAGE_SIZE);
g_bs = PAGE_SIZE;
}
if (!is_power_of_2(g_zone_size)) {
- pr_err("null_blk: zone_size must be power-of-two\n");
+ pr_err("zone_size must be power-of-two\n");
return -EINVAL;
}
if (g_home_node != NUMA_NO_NODE && g_home_node >= nr_online_nodes) {
- pr_err("null_blk: invalid home_node value\n");
+ pr_err("invalid home_node value\n");
g_home_node = NUMA_NO_NODE;
}
if (g_queue_mode == NULL_Q_RQ) {
- pr_err("null_blk: legacy IO path no longer available\n");
+ pr_err("legacy IO path no longer available\n");
return -EINVAL;
}
if (g_queue_mode == NULL_Q_MQ && g_use_per_node_hctx) {
if (g_submit_queues != nr_online_nodes) {
- pr_warn("null_blk: submit_queues param is set to %u.\n",
+ pr_warn("submit_queues param is set to %u.\n",
nr_online_nodes);
g_submit_queues = nr_online_nodes;
}
@@ -1803,7 +1812,7 @@ static int __init null_init(void)
}
}
- pr_info("null: module loaded\n");
+ pr_info("module loaded\n");
return 0;
err_dev:
diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c
index cb28d93f2bd1..eabc116832a7 100644
--- a/drivers/block/null_blk_zoned.c
+++ b/drivers/block/null_blk_zoned.c
@@ -17,7 +17,7 @@ int null_zone_init(struct nullb_device *dev)
unsigned int i;
if (!is_power_of_2(dev->zone_size)) {
- pr_err("null_blk: zone_size must be power-of-two\n");
+ pr_err("zone_size must be power-of-two\n");
return -EINVAL;
}
@@ -31,7 +31,7 @@ int null_zone_init(struct nullb_device *dev)
if (dev->zone_nr_conv >= dev->nr_zones) {
dev->zone_nr_conv = dev->nr_zones - 1;
- pr_info("null_blk: changed the number of conventional zones to %u",
+ pr_info("changed the number of conventional zones to %u",
dev->zone_nr_conv);
}
@@ -84,7 +84,7 @@ int null_zone_report(struct gendisk *disk, sector_t sector,
return 0;
}
-void null_zone_write(struct nullb_cmd *cmd, sector_t sector,
+static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
unsigned int nr_sectors)
{
struct nullb_device *dev = cmd->nq->dev;
@@ -95,14 +95,12 @@ void null_zone_write(struct nullb_cmd *cmd, sector_t sector,
case BLK_ZONE_COND_FULL:
/* Cannot write to a full zone */
cmd->error = BLK_STS_IOERR;
- break;
+ return BLK_STS_IOERR;
case BLK_ZONE_COND_EMPTY:
case BLK_ZONE_COND_IMP_OPEN:
/* Writes must be at the write pointer position */
- if (sector != zone->wp) {
- cmd->error = BLK_STS_IOERR;
- break;
- }
+ if (sector != zone->wp)
+ return BLK_STS_IOERR;
if (zone->cond == BLK_ZONE_COND_EMPTY)
zone->cond = BLK_ZONE_COND_IMP_OPEN;
@@ -115,22 +113,51 @@ void null_zone_write(struct nullb_cmd *cmd, sector_t sector,
break;
default:
/* Invalid zone condition */
- cmd->error = BLK_STS_IOERR;
- break;
+ return BLK_STS_IOERR;
}
+ return BLK_STS_OK;
}
-void null_zone_reset(struct nullb_cmd *cmd, sector_t sector)
+static blk_status_t null_zone_reset(struct nullb_cmd *cmd, sector_t sector)
{
struct nullb_device *dev = cmd->nq->dev;
unsigned int zno = null_zone_no(dev, sector);
struct blk_zone *zone = &dev->zones[zno];
+ size_t i;
+
+ switch (req_op(cmd->rq)) {
+ case REQ_OP_ZONE_RESET_ALL:
+ for (i = 0; i < dev->nr_zones; i++) {
+ if (zone[i].type == BLK_ZONE_TYPE_CONVENTIONAL)
+ continue;
+ zone[i].cond = BLK_ZONE_COND_EMPTY;
+ zone[i].wp = zone[i].start;
+ }
+ break;
+ case REQ_OP_ZONE_RESET:
+ if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
+ return BLK_STS_IOERR;
- if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) {
- cmd->error = BLK_STS_IOERR;
- return;
+ zone->cond = BLK_ZONE_COND_EMPTY;
+ zone->wp = zone->start;
+ break;
+ default:
+ cmd->error = BLK_STS_NOTSUPP;
+ break;
}
+ return BLK_STS_OK;
+}
- zone->cond = BLK_ZONE_COND_EMPTY;
- zone->wp = zone->start;
+blk_status_t null_handle_zoned(struct nullb_cmd *cmd, enum req_opf op,
+ sector_t sector, sector_t nr_sectors)
+{
+ switch (op) {
+ case REQ_OP_WRITE:
+ return null_zone_write(cmd, sector, nr_sectors);
+ case REQ_OP_ZONE_RESET:
+ case REQ_OP_ZONE_RESET_ALL:
+ return null_zone_reset(cmd, sector);
+ default:
+ return BLK_STS_OK;
+ }
}
diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c
index 001dbdcbf355..636bfea2de6f 100644
--- a/drivers/block/paride/pcd.c
+++ b/drivers/block/paride/pcd.c
@@ -314,8 +314,8 @@ static void pcd_init_units(void)
disk->queue = blk_mq_init_sq_queue(&cd->tag_set, &pcd_mq_ops,
1, BLK_MQ_F_SHOULD_MERGE);
if (IS_ERR(disk->queue)) {
- put_disk(disk);
disk->queue = NULL;
+ put_disk(disk);
continue;
}
@@ -723,9 +723,9 @@ static int pcd_detect(void)
k = 0;
if (pcd_drive_count == 0) { /* nothing spec'd - so autoprobe for 1 */
cd = pcd;
- if (pi_init(cd->pi, 1, -1, -1, -1, -1, -1, pcd_buffer,
- PI_PCD, verbose, cd->name)) {
- if (!pcd_probe(cd, -1, id) && cd->disk) {
+ if (cd->disk && pi_init(cd->pi, 1, -1, -1, -1, -1, -1,
+ pcd_buffer, PI_PCD, verbose, cd->name)) {
+ if (!pcd_probe(cd, -1, id)) {
cd->present = 1;
k++;
} else
@@ -736,11 +736,13 @@ static int pcd_detect(void)
int *conf = *drives[unit];
if (!conf[D_PRT])
continue;
+ if (!cd->disk)
+ continue;
if (!pi_init(cd->pi, 0, conf[D_PRT], conf[D_MOD],
conf[D_UNI], conf[D_PRO], conf[D_DLY],
pcd_buffer, PI_PCD, verbose, cd->name))
continue;
- if (!pcd_probe(cd, conf[D_SLV], id) && cd->disk) {
+ if (!pcd_probe(cd, conf[D_SLV], id)) {
cd->present = 1;
k++;
} else
diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c
index 1e9c50a7256c..6b7d4cab3687 100644
--- a/drivers/block/paride/pf.c
+++ b/drivers/block/paride/pf.c
@@ -300,8 +300,8 @@ static void __init pf_init_units(void)
disk->queue = blk_mq_init_sq_queue(&pf->tag_set, &pf_mq_ops,
1, BLK_MQ_F_SHOULD_MERGE);
if (IS_ERR(disk->queue)) {
- put_disk(disk);
disk->queue = NULL;
+ put_disk(disk);
continue;
}
diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c
index a600934fdd9c..7543e395a2c6 100644
--- a/drivers/lightnvm/core.c
+++ b/drivers/lightnvm/core.c
@@ -4,6 +4,8 @@
* Initial release: Matias Bjorling <m@bjorling.me>
*/
+#define pr_fmt(fmt) "nvm: " fmt
+
#include <linux/list.h>
#include <linux/types.h>
#include <linux/sem.h>
@@ -74,7 +76,7 @@ static int nvm_reserve_luns(struct nvm_dev *dev, int lun_begin, int lun_end)
for (i = lun_begin; i <= lun_end; i++) {
if (test_and_set_bit(i, dev->lun_map)) {
- pr_err("nvm: lun %d already allocated\n", i);
+ pr_err("lun %d already allocated\n", i);
goto err;
}
}
@@ -264,7 +266,7 @@ static int nvm_config_check_luns(struct nvm_geo *geo, int lun_begin,
int lun_end)
{
if (lun_begin > lun_end || lun_end >= geo->all_luns) {
- pr_err("nvm: lun out of bound (%u:%u > %u)\n",
+ pr_err("lun out of bound (%u:%u > %u)\n",
lun_begin, lun_end, geo->all_luns - 1);
return -EINVAL;
}
@@ -297,7 +299,7 @@ static int __nvm_config_extended(struct nvm_dev *dev,
if (e->op == 0xFFFF) {
e->op = NVM_TARGET_DEFAULT_OP;
} else if (e->op < NVM_TARGET_MIN_OP || e->op > NVM_TARGET_MAX_OP) {
- pr_err("nvm: invalid over provisioning value\n");
+ pr_err("invalid over provisioning value\n");
return -EINVAL;
}
@@ -334,23 +336,23 @@ static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create)
e = create->conf.e;
break;
default:
- pr_err("nvm: config type not valid\n");
+ pr_err("config type not valid\n");
return -EINVAL;
}
tt = nvm_find_target_type(create->tgttype);
if (!tt) {
- pr_err("nvm: target type %s not found\n", create->tgttype);
+ pr_err("target type %s not found\n", create->tgttype);
return -EINVAL;
}
if ((tt->flags & NVM_TGT_F_HOST_L2P) != (dev->geo.dom & NVM_RSP_L2P)) {
- pr_err("nvm: device is incompatible with target L2P type.\n");
+ pr_err("device is incompatible with target L2P type.\n");
return -EINVAL;
}
if (nvm_target_exists(create->tgtname)) {
- pr_err("nvm: target name already exists (%s)\n",
+ pr_err("target name already exists (%s)\n",
create->tgtname);
return -EINVAL;
}
@@ -367,7 +369,7 @@ static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create)
tgt_dev = nvm_create_tgt_dev(dev, e.lun_begin, e.lun_end, e.op);
if (!tgt_dev) {
- pr_err("nvm: could not create target device\n");
+ pr_err("could not create target device\n");
ret = -ENOMEM;
goto err_t;
}
@@ -493,8 +495,11 @@ static int nvm_remove_tgt(struct nvm_ioctl_remove *remove)
}
up_read(&nvm_lock);
- if (!t)
+ if (!t) {
+ pr_err("failed to remove target %s\n",
+ remove->tgtname);
return 1;
+ }
__nvm_remove_target(t, true);
kref_put(&dev->ref, nvm_free);
@@ -686,7 +691,7 @@ static int nvm_set_rqd_ppalist(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd,
rqd->nr_ppas = nr_ppas;
rqd->ppa_list = nvm_dev_dma_alloc(dev, GFP_KERNEL, &rqd->dma_ppa_list);
if (!rqd->ppa_list) {
- pr_err("nvm: failed to allocate dma memory\n");
+ pr_err("failed to allocate dma memory\n");
return -ENOMEM;
}
@@ -731,7 +736,7 @@ static int nvm_set_flags(struct nvm_geo *geo, struct nvm_rq *rqd)
return flags;
}
-int nvm_submit_io(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd)
+int nvm_submit_io(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd, void *buf)
{
struct nvm_dev *dev = tgt_dev->parent;
int ret;
@@ -745,19 +750,45 @@ int nvm_submit_io(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd)
rqd->flags = nvm_set_flags(&tgt_dev->geo, rqd);
/* In case of error, fail with right address format */
- ret = dev->ops->submit_io(dev, rqd);
+ ret = dev->ops->submit_io(dev, rqd, buf);
if (ret)
nvm_rq_dev_to_tgt(tgt_dev, rqd);
return ret;
}
EXPORT_SYMBOL(nvm_submit_io);
-int nvm_submit_io_sync(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd)
+static void nvm_sync_end_io(struct nvm_rq *rqd)
+{
+ struct completion *waiting = rqd->private;
+
+ complete(waiting);
+}
+
+static int nvm_submit_io_wait(struct nvm_dev *dev, struct nvm_rq *rqd,
+ void *buf)
+{
+ DECLARE_COMPLETION_ONSTACK(wait);
+ int ret = 0;
+
+ rqd->end_io = nvm_sync_end_io;
+ rqd->private = &wait;
+
+ ret = dev->ops->submit_io(dev, rqd, buf);
+ if (ret)
+ return ret;
+
+ wait_for_completion_io(&wait);
+
+ return 0;
+}
+
+int nvm_submit_io_sync(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd,
+ void *buf)
{
struct nvm_dev *dev = tgt_dev->parent;
int ret;
- if (!dev->ops->submit_io_sync)
+ if (!dev->ops->submit_io)
return -ENODEV;
nvm_rq_tgt_to_dev(tgt_dev, rqd);
@@ -765,9 +796,7 @@ int nvm_submit_io_sync(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd)
rqd->dev = tgt_dev;
rqd->flags = nvm_set_flags(&tgt_dev->geo, rqd);
- /* In case of error, fail with right address format */
- ret = dev->ops->submit_io_sync(dev, rqd);
- nvm_rq_dev_to_tgt(tgt_dev, rqd);
+ ret = nvm_submit_io_wait(dev, rqd, buf);
return ret;
}
@@ -788,12 +817,13 @@ EXPORT_SYMBOL(nvm_end_io);
static int nvm_submit_io_sync_raw(struct nvm_dev *dev, struct nvm_rq *rqd)
{
- if (!dev->ops->submit_io_sync)
+ if (!dev->ops->submit_io)
return -ENODEV;
+ rqd->dev = NULL;
rqd->flags = nvm_set_flags(&dev->geo, rqd);
- return dev->ops->submit_io_sync(dev, rqd);
+ return nvm_submit_io_wait(dev, rqd, NULL);
}
static int nvm_bb_chunk_sense(struct nvm_dev *dev, struct ppa_addr ppa)
@@ -1048,7 +1078,7 @@ int nvm_set_chunk_meta(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *ppas,
return 0;
if (nr_ppas > NVM_MAX_VLBA) {
- pr_err("nvm: unable to update all blocks atomically\n");
+ pr_err("unable to update all blocks atomically\n");
return -EINVAL;
}
@@ -1111,27 +1141,26 @@ static int nvm_init(struct nvm_dev *dev)
int ret = -EINVAL;
if (dev->ops->identity(dev)) {
- pr_err("nvm: device could not be identified\n");
+ pr_err("device could not be identified\n");
goto err;
}
- pr_debug("nvm: ver:%u.%u nvm_vendor:%x\n",
- geo->major_ver_id, geo->minor_ver_id,
- geo->vmnt);
+ pr_debug("ver:%u.%u nvm_vendor:%x\n", geo->major_ver_id,
+ geo->minor_ver_id, geo->vmnt);
ret = nvm_core_init(dev);
if (ret) {
- pr_err("nvm: could not initialize core structures.\n");
+ pr_err("could not initialize core structures.\n");
goto err;
}
- pr_info("nvm: registered %s [%u/%u/%u/%u/%u]\n",
+ pr_info("registered %s [%u/%u/%u/%u/%u]\n",
dev->name, dev->geo.ws_min, dev->geo.ws_opt,
dev->geo.num_chk, dev->geo.all_luns,
dev->geo.num_ch);
return 0;
err:
- pr_err("nvm: failed to initialize nvm\n");
+ pr_err("failed to initialize nvm\n");
return ret;
}
@@ -1169,7 +1198,7 @@ int nvm_register(struct nvm_dev *dev)
dev->dma_pool = dev->ops->create_dma_pool(dev, "ppalist",
exp_pool_size);
if (!dev->dma_pool) {
- pr_err("nvm: could not create dma pool\n");
+ pr_err("could not create dma pool\n");
kref_put(&dev->ref, nvm_free);
return -ENOMEM;
}
@@ -1214,7 +1243,7 @@ static int __nvm_configure_create(struct nvm_ioctl_create *create)
up_write(&nvm_lock);
if (!dev) {
- pr_err("nvm: device not found\n");
+ pr_err("device not found\n");
return -EINVAL;
}
@@ -1288,7 +1317,7 @@ static long nvm_ioctl_get_devices(struct file *file, void __user *arg)
i++;
if (i > 31) {
- pr_err("nvm: max 31 devices can be reported.\n");
+ pr_err("max 31 devices can be reported.\n");
break;
}
}
@@ -1315,7 +1344,7 @@ static long nvm_ioctl_dev_create(struct file *file, void __user *arg)
if (create.conf.type == NVM_CONFIG_TYPE_EXTENDED &&
create.conf.e.rsv != 0) {
- pr_err("nvm: reserved config field in use\n");
+ pr_err("reserved config field in use\n");
return -EINVAL;
}
@@ -1331,7 +1360,7 @@ static long nvm_ioctl_dev_create(struct file *file, void __user *arg)
flags &= ~NVM_TARGET_FACTORY;
if (flags) {
- pr_err("nvm: flag not supported\n");
+ pr_err("flag not supported\n");
return -EINVAL;
}
}
@@ -1349,7 +1378,7 @@ static long nvm_ioctl_dev_remove(struct file *file, void __user *arg)
remove.tgtname[DISK_NAME_LEN - 1] = '\0';
if (remove.flags != 0) {
- pr_err("nvm: no flags supported\n");
+ pr_err("no flags supported\n");
return -EINVAL;
}
@@ -1365,7 +1394,7 @@ static long nvm_ioctl_dev_init(struct file *file, void __user *arg)
return -EFAULT;
if (init.flags != 0) {
- pr_err("nvm: no flags supported\n");
+ pr_err("no flags supported\n");
return -EINVAL;
}
diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index f546e6f28b8a..b413bafe93fd 100644
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -507,7 +507,7 @@ void pblk_set_sec_per_write(struct pblk *pblk, int sec_per_write)
pblk->sec_per_write = sec_per_write;
}
-int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd)
+int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd, void *buf)
{
struct nvm_tgt_dev *dev = pblk->dev;
@@ -518,7 +518,7 @@ int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd)
return NVM_IO_ERR;
#endif
- return nvm_submit_io(dev, rqd);
+ return nvm_submit_io(dev, rqd, buf);
}
void pblk_check_chunk_state_update(struct pblk *pblk, struct nvm_rq *rqd)
@@ -541,7 +541,7 @@ void pblk_check_chunk_state_update(struct pblk *pblk, struct nvm_rq *rqd)
}
}
-int pblk_submit_io_sync(struct pblk *pblk, struct nvm_rq *rqd)
+int pblk_submit_io_sync(struct pblk *pblk, struct nvm_rq *rqd, void *buf)
{
struct nvm_tgt_dev *dev = pblk->dev;
int ret;
@@ -553,7 +553,7 @@ int pblk_submit_io_sync(struct pblk *pblk, struct nvm_rq *rqd)
return NVM_IO_ERR;
#endif
- ret = nvm_submit_io_sync(dev, rqd);
+ ret = nvm_submit_io_sync(dev, rqd, buf);
if (trace_pblk_chunk_state_enabled() && !ret &&
rqd->opcode == NVM_OP_PWRITE)
@@ -562,65 +562,19 @@ int pblk_submit_io_sync(struct pblk *pblk, struct nvm_rq *rqd)
return ret;
}
-int pblk_submit_io_sync_sem(struct pblk *pblk, struct nvm_rq *rqd)
+static int pblk_submit_io_sync_sem(struct pblk *pblk, struct nvm_rq *rqd,
+ void *buf)
{
struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd);
int ret;
pblk_down_chunk(pblk, ppa_list[0]);
- ret = pblk_submit_io_sync(pblk, rqd);
+ ret = pblk_submit_io_sync(pblk, rqd, buf);
pblk_up_chunk(pblk, ppa_list[0]);
return ret;
}
-static void pblk_bio_map_addr_endio(struct bio *bio)
-{
- bio_put(bio);
-}
-
-struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data,
- unsigned int nr_secs, unsigned int len,
- int alloc_type, gfp_t gfp_mask)
-{
- struct nvm_tgt_dev *dev = pblk->dev;
- void *kaddr = data;
- struct page *page;
- struct bio *bio;
- int i, ret;
-
- if (alloc_type == PBLK_KMALLOC_META)
- return bio_map_kern(dev->q, kaddr, len, gfp_mask);
-
- bio = bio_kmalloc(gfp_mask, nr_secs);
- if (!bio)
- return ERR_PTR(-ENOMEM);
-
- for (i = 0; i < nr_secs; i++) {
- page = vmalloc_to_page(kaddr);
- if (!page) {
- pblk_err(pblk, "could not map vmalloc bio\n");
- bio_put(bio);
- bio = ERR_PTR(-ENOMEM);
- goto out;
- }
-
- ret = bio_add_pc_page(dev->q, bio, page, PAGE_SIZE, 0);
- if (ret != PAGE_SIZE) {
- pblk_err(pblk, "could not add page to bio\n");
- bio_put(bio);
- bio = ERR_PTR(-ENOMEM);
- goto out;
- }
-
- kaddr += PAGE_SIZE;
- }
-
- bio->bi_end_io = pblk_bio_map_addr_endio;
-out:
- return bio;
-}
-
int pblk_calc_secs(struct pblk *pblk, unsigned long secs_avail,
unsigned long secs_to_flush, bool skip_meta)
{
@@ -722,9 +676,7 @@ u64 pblk_line_smeta_start(struct pblk *pblk, struct pblk_line *line)
int pblk_line_smeta_read(struct pblk *pblk, struct pblk_line *line)
{
- struct nvm_tgt_dev *dev = pblk->dev;
struct pblk_line_meta *lm = &pblk->lm;
- struct bio *bio;
struct ppa_addr *ppa_list;
struct nvm_rq rqd;
u64 paddr = pblk_line_smeta_start(pblk, line);
@@ -736,16 +688,6 @@ int pblk_line_smeta_read(struct pblk *pblk, struct pblk_line *line)
if (ret)
return ret;
- bio = bio_map_kern(dev->q, line->smeta, lm->smeta_len, GFP_KERNEL);
- if (IS_ERR(bio)) {
- ret = PTR_ERR(bio);
- goto clear_rqd;
- }
-
- bio->bi_iter.bi_sector = 0; /* internal bio */
- bio_set_op_attrs(bio, REQ_OP_READ, 0);
-
- rqd.bio = bio;
rqd.opcode = NVM_OP_PREAD;
rqd.nr_ppas = lm->smeta_sec;
rqd.is_seq = 1;
@@ -754,10 +696,9 @@ int pblk_line_smeta_read(struct pblk *pblk, struct pblk_line *line)
for (i = 0; i < lm->smeta_sec; i++, paddr++)
ppa_list[i] = addr_to_gen_ppa(pblk, paddr, line->id);
- ret = pblk_submit_io_sync(pblk, &rqd);
+ ret = pblk_submit_io_sync(pblk, &rqd, line->smeta);
if (ret) {
pblk_err(pblk, "smeta I/O submission failed: %d\n", ret);
- bio_put(bio);
goto clear_rqd;
}
@@ -776,9 +717,7 @@ clear_rqd:
static int pblk_line_smeta_write(struct pblk *pblk, struct pblk_line *line,
u64 paddr)
{
- struct nvm_tgt_dev *dev = pblk->dev;
struct pblk_line_meta *lm = &pblk->lm;
- struct bio *bio;
struct ppa_addr *ppa_list;
struct nvm_rq rqd;
__le64 *lba_list = emeta_to_lbas(pblk, line->emeta->buf);
@@ -791,16 +730,6 @@ static int pblk_line_smeta_write(struct pblk *pblk, struct pblk_line *line,
if (ret)
return ret;
- bio = bio_map_kern(dev->q, line->smeta, lm->smeta_len, GFP_KERNEL);
- if (IS_ERR(bio)) {
- ret = PTR_ERR(bio);
- goto clear_rqd;
- }
-
- bio->bi_iter.bi_sector = 0; /* internal bio */
- bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
-
- rqd.bio = bio;
rqd.opcode = NVM_OP_PWRITE;
rqd.nr_ppas = lm->smeta_sec;
rqd.is_seq = 1;
@@ -814,10 +743,9 @@ static int pblk_line_smeta_write(struct pblk *pblk, struct pblk_line *line,
meta->lba = lba_list[paddr] = addr_empty;
}
- ret = pblk_submit_io_sync_sem(pblk, &rqd);
+ ret = pblk_submit_io_sync_sem(pblk, &rqd, line->smeta);
if (ret) {
pblk_err(pblk, "smeta I/O submission failed: %d\n", ret);
- bio_put(bio);
goto clear_rqd;
}
@@ -838,10 +766,8 @@ int pblk_line_emeta_read(struct pblk *pblk, struct pblk_line *line,
{
struct nvm_tgt_dev *dev = pblk->dev;
struct nvm_geo *geo = &dev->geo;
- struct pblk_line_mgmt *l_mg = &pblk->l_mg;
struct pblk_line_meta *lm = &pblk->lm;
void *ppa_list_buf, *meta_list;
- struct bio *bio;
struct ppa_addr *ppa_list;
struct nvm_rq rqd;
u64 paddr = line->emeta_ssec;
@@ -867,17 +793,6 @@ next_rq:
rq_ppas = pblk_calc_secs(pblk, left_ppas, 0, false);
rq_len = rq_ppas * geo->csecs;
- bio = pblk_bio_map_addr(pblk, emeta_buf, rq_ppas, rq_len,
- l_mg->emeta_alloc_type, GFP_KERNEL);
- if (IS_ERR(bio)) {
- ret = PTR_ERR(bio);
- goto free_rqd_dma;
- }
-
- bio->bi_iter.bi_sector = 0; /* internal bio */
- bio_set_op_attrs(bio, REQ_OP_READ, 0);
-
- rqd.bio = bio;
rqd.meta_list = meta_list;
rqd.ppa_list = ppa_list_buf;
rqd.dma_meta_list = dma_meta_list;
@@ -896,7 +811,6 @@ next_rq:
while (test_bit(pos, line->blk_bitmap)) {
paddr += min;
if (pblk_boundary_paddr_checks(pblk, paddr)) {
- bio_put(bio);
ret = -EINTR;
goto free_rqd_dma;
}
@@ -906,7 +820,6 @@ next_rq:
}
if (pblk_boundary_paddr_checks(pblk, paddr + min)) {
- bio_put(bio);
ret = -EINTR;
goto free_rqd_dma;
}
@@ -915,10 +828,9 @@ next_rq:
ppa_list[i] = addr_to_gen_ppa(pblk, paddr, line_id);
}
- ret = pblk_submit_io_sync(pblk, &rqd);
+ ret = pblk_submit_io_sync(pblk, &rqd, emeta_buf);
if (ret) {
pblk_err(pblk, "emeta I/O submission failed: %d\n", ret);
- bio_put(bio);
goto free_rqd_dma;
}
@@ -963,7 +875,7 @@ static int pblk_blk_erase_sync(struct pblk *pblk, struct ppa_addr ppa)
/* The write thread schedules erases so that it minimizes disturbances
* with writes. Thus, there is no need to take the LUN semaphore.
*/
- ret = pblk_submit_io_sync(pblk, &rqd);
+ ret = pblk_submit_io_sync(pblk, &rqd, NULL);
rqd.private = pblk;
__pblk_end_io_erase(pblk, &rqd);
@@ -1792,7 +1704,7 @@ int pblk_blk_erase_async(struct pblk *pblk, struct ppa_addr ppa)
/* The write thread schedules erases so that it minimizes disturbances
* with writes. Thus, there is no need to take the LUN semaphore.
*/
- err = pblk_submit_io(pblk, rqd);
+ err = pblk_submit_io(pblk, rqd, NULL);
if (err) {
struct nvm_tgt_dev *dev = pblk->dev;
struct nvm_geo *geo = &dev->geo;
@@ -1923,13 +1835,11 @@ void pblk_line_close_meta(struct pblk *pblk, struct pblk_line *line)
static void pblk_save_lba_list(struct pblk *pblk, struct pblk_line *line)
{
struct pblk_line_meta *lm = &pblk->lm;
- struct pblk_line_mgmt *l_mg = &pblk->l_mg;
unsigned int lba_list_size = lm->emeta_len[2];
struct pblk_w_err_gc *w_err_gc = line->w_err_gc;
struct pblk_emeta *emeta = line->emeta;
- w_err_gc->lba_list = pblk_malloc(lba_list_size,
- l_mg->emeta_alloc_type, GFP_KERNEL);
+ w_err_gc->lba_list = kvmalloc(lba_list_size, GFP_KERNEL);
memcpy(w_err_gc->lba_list, emeta_to_lbas(pblk, emeta->buf),
lba_list_size);
}
diff --git a/drivers/lightnvm/pblk-gc.c b/drivers/lightnvm/pblk-gc.c
index 63ee205b41c4..2581eebcfc41 100644
--- a/drivers/lightnvm/pblk-gc.c
+++ b/drivers/lightnvm/pblk-gc.c
@@ -132,14 +132,12 @@ static __le64 *get_lba_list_from_emeta(struct pblk *pblk,
struct pblk_line *line)
{
struct line_emeta *emeta_buf;
- struct pblk_line_mgmt *l_mg = &pblk->l_mg;
struct pblk_line_meta *lm = &pblk->lm;
unsigned int lba_list_size = lm->emeta_len[2];
__le64 *lba_list;
int ret;
- emeta_buf = pblk_malloc(lm->emeta_len[0],
- l_mg->emeta_alloc_type, GFP_KERNEL);
+ emeta_buf = kvmalloc(lm->emeta_len[0], GFP_KERNEL);
if (!emeta_buf)
return NULL;
@@ -147,7 +145,7 @@ static __le64 *get_lba_list_from_emeta(struct pblk *pblk,
if (ret) {
pblk_err(pblk, "line %d read emeta failed (%d)\n",
line->id, ret);
- pblk_mfree(emeta_buf, l_mg->emeta_alloc_type);
+ kvfree(emeta_buf);
return NULL;
}
@@ -161,16 +159,16 @@ static __le64 *get_lba_list_from_emeta(struct pblk *pblk,
if (ret) {
pblk_err(pblk, "inconsistent emeta (line %d)\n",
line->id);
- pblk_mfree(emeta_buf, l_mg->emeta_alloc_type);
+ kvfree(emeta_buf);
return NULL;
}
- lba_list = pblk_malloc(lba_list_size,
- l_mg->emeta_alloc_type, GFP_KERNEL);
+ lba_list = kvmalloc(lba_list_size, GFP_KERNEL);
+
if (lba_list)
memcpy(lba_list, emeta_to_lbas(pblk, emeta_buf), lba_list_size);
- pblk_mfree(emeta_buf, l_mg->emeta_alloc_type);
+ kvfree(emeta_buf);
return lba_list;
}
@@ -181,7 +179,6 @@ static void pblk_gc_line_prepare_ws(struct work_struct *work)
ws);
struct pblk *pblk = line_ws->pblk;
struct pblk_line *line = line_ws->line;
- struct pblk_line_mgmt *l_mg = &pblk->l_mg;
struct pblk_line_meta *lm = &pblk->lm;
struct nvm_tgt_dev *dev = pblk->dev;
struct nvm_geo *geo = &dev->geo;
@@ -272,7 +269,7 @@ next_rq:
goto next_rq;
out:
- pblk_mfree(lba_list, l_mg->emeta_alloc_type);
+ kvfree(lba_list);
kfree(line_ws);
kfree(invalid_bitmap);
@@ -286,7 +283,7 @@ fail_free_gc_data:
fail_free_gc_rq:
kfree(gc_rq);
fail_free_lba_list:
- pblk_mfree(lba_list, l_mg->emeta_alloc_type);
+ kvfree(lba_list);
fail_free_invalid_bitmap:
kfree(invalid_bitmap);
fail_free_ws:
diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
index b351c7f002de..9a967a2e83dd 100644
--- a/drivers/lightnvm/pblk-init.c
+++ b/drivers/lightnvm/pblk-init.c
@@ -543,7 +543,7 @@ static void pblk_line_mg_free(struct pblk *pblk)
for (i = 0; i < PBLK_DATA_LINES; i++) {
kfree(l_mg->sline_meta[i]);
- pblk_mfree(l_mg->eline_meta[i]->buf, l_mg->emeta_alloc_type);
+ kvfree(l_mg->eline_meta[i]->buf);
kfree(l_mg->eline_meta[i]);
}
@@ -560,7 +560,7 @@ static void pblk_line_meta_free(struct pblk_line_mgmt *l_mg,
kfree(line->erase_bitmap);
kfree(line->chks);
- pblk_mfree(w_err_gc->lba_list, l_mg->emeta_alloc_type);
+ kvfree(w_err_gc->lba_list);
kfree(w_err_gc);
}
@@ -890,29 +890,14 @@ static int pblk_line_mg_init(struct pblk *pblk)
if (!emeta)
goto fail_free_emeta;
- if (lm->emeta_len[0] > KMALLOC_MAX_CACHE_SIZE) {
- l_mg->emeta_alloc_type = PBLK_VMALLOC_META;
-
- emeta->buf = vmalloc(lm->emeta_len[0]);
- if (!emeta->buf) {
- kfree(emeta);
- goto fail_free_emeta;
- }
-
- emeta->nr_entries = lm->emeta_sec[0];
- l_mg->eline_meta[i] = emeta;
- } else {
- l_mg->emeta_alloc_type = PBLK_KMALLOC_META;
-
- emeta->buf = kmalloc(lm->emeta_len[0], GFP_KERNEL);
- if (!emeta->buf) {
- kfree(emeta);
- goto fail_free_emeta;
- }
-
- emeta->nr_entries = lm->emeta_sec[0];
- l_mg->eline_meta[i] = emeta;
+ emeta->buf = kvmalloc(lm->emeta_len[0], GFP_KERNEL);
+ if (!emeta->buf) {
+ kfree(emeta);
+ goto fail_free_emeta;
}
+
+ emeta->nr_entries = lm->emeta_sec[0];
+ l_mg->eline_meta[i] = emeta;
}
for (i = 0; i < l_mg->nr_lines; i++)
@@ -926,10 +911,7 @@ static int pblk_line_mg_init(struct pblk *pblk)
fail_free_emeta:
while (--i >= 0) {
- if (l_mg->emeta_alloc_type == PBLK_VMALLOC_META)
- vfree(l_mg->eline_meta[i]->buf);
- else
- kfree(l_mg->eline_meta[i]->buf);
+ kvfree(l_mg->eline_meta[i]->buf);
kfree(l_mg->eline_meta[i]);
}
diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
index d98ea392fe33..8efd14e683dc 100644
--- a/drivers/lightnvm/pblk-read.c
+++ b/drivers/lightnvm/pblk-read.c
@@ -342,7 +342,7 @@ split_retry:
bio_put(int_bio);
int_bio = bio_clone_fast(bio, GFP_KERNEL, &pblk_bio_set);
goto split_retry;
- } else if (pblk_submit_io(pblk, rqd)) {
+ } else if (pblk_submit_io(pblk, rqd, NULL)) {
/* Submitting IO to drive failed, let's report an error */
rqd->error = -ENODEV;
pblk_end_io_read(rqd);
@@ -417,11 +417,7 @@ out:
int pblk_submit_read_gc(struct pblk *pblk, struct pblk_gc_rq *gc_rq)
{
- struct nvm_tgt_dev *dev = pblk->dev;
- struct nvm_geo *geo = &dev->geo;
- struct bio *bio;
struct nvm_rq rqd;
- int data_len;
int ret = NVM_IO_OK;
memset(&rqd, 0, sizeof(struct nvm_rq));
@@ -446,26 +442,12 @@ int pblk_submit_read_gc(struct pblk *pblk, struct pblk_gc_rq *gc_rq)
if (!(gc_rq->secs_to_gc))
goto out;
- data_len = (gc_rq->secs_to_gc) * geo->csecs;
- bio = pblk_bio_map_addr(pblk, gc_rq->data, gc_rq->secs_to_gc, data_len,
- PBLK_VMALLOC_META, GFP_KERNEL);
- if (IS_ERR(bio)) {
- pblk_err(pblk, "could not allocate GC bio (%lu)\n",
- PTR_ERR(bio));
- ret = PTR_ERR(bio);
- goto err_free_dma;
- }
-
- bio->bi_iter.bi_sector = 0; /* internal bio */
- bio_set_op_attrs(bio, REQ_OP_READ, 0);
-
rqd.opcode = NVM_OP_PREAD;
rqd.nr_ppas = gc_rq->secs_to_gc;
- rqd.bio = bio;
- if (pblk_submit_io_sync(pblk, &rqd)) {
+ if (pblk_submit_io_sync(pblk, &rqd, gc_rq->data)) {
ret = -EIO;
- goto err_free_bio;
+ goto err_free_dma;
}
pblk_read_check_rand(pblk, &rqd, gc_rq->lba_list, gc_rq->nr_secs);
@@ -489,8 +471,6 @@ out:
pblk_free_rqd_meta(pblk, &rqd);
return ret;
-err_free_bio:
- bio_put(bio);
err_free_dma:
pblk_free_rqd_meta(pblk, &rqd);
return ret;
diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c
index e6dda04de144..299ef47a17b2 100644
--- a/drivers/lightnvm/pblk-recovery.c
+++ b/drivers/lightnvm/pblk-recovery.c
@@ -178,12 +178,11 @@ static int pblk_recov_pad_line(struct pblk *pblk, struct pblk_line *line,
void *meta_list;
struct pblk_pad_rq *pad_rq;
struct nvm_rq *rqd;
- struct bio *bio;
struct ppa_addr *ppa_list;
void *data;
__le64 *lba_list = emeta_to_lbas(pblk, line->emeta->buf);
u64 w_ptr = line->cur_sec;
- int left_line_ppas, rq_ppas, rq_len;
+ int left_line_ppas, rq_ppas;
int i, j;
int ret = 0;
@@ -212,28 +211,15 @@ next_pad_rq:
goto fail_complete;
}
- rq_len = rq_ppas * geo->csecs;
-
- bio = pblk_bio_map_addr(pblk, data, rq_ppas, rq_len,
- PBLK_VMALLOC_META, GFP_KERNEL);
- if (IS_ERR(bio)) {
- ret = PTR_ERR(bio);
- goto fail_complete;
- }
-
- bio->bi_iter.bi_sector = 0; /* internal bio */
- bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
-
rqd = pblk_alloc_rqd(pblk, PBLK_WRITE_INT);
ret = pblk_alloc_rqd_meta(pblk, rqd);
if (ret) {
pblk_free_rqd(pblk, rqd, PBLK_WRITE_INT);
- bio_put(bio);
goto fail_complete;
}
- rqd->bio = bio;
+ rqd->bio = NULL;
rqd->opcode = NVM_OP_PWRITE;
rqd->is_seq = 1;
rqd->nr_ppas = rq_ppas;
@@ -275,13 +261,12 @@ next_pad_rq:
kref_get(&pad_rq->ref);
pblk_down_chunk(pblk, ppa_list[0]);
- ret = pblk_submit_io(pblk, rqd);
+ ret = pblk_submit_io(pblk, rqd, data);
if (ret) {
pblk_err(pblk, "I/O submission failed: %d\n", ret);
pblk_up_chunk(pblk, ppa_list[0]);
kref_put(&pad_rq->ref, pblk_recov_complete);
pblk_free_rqd(pblk, rqd, PBLK_WRITE_INT);
- bio_put(bio);
goto fail_complete;
}
@@ -375,13 +360,12 @@ static int pblk_recov_scan_oob(struct pblk *pblk, struct pblk_line *line,
struct ppa_addr *ppa_list;
void *meta_list;
struct nvm_rq *rqd;
- struct bio *bio;
void *data;
dma_addr_t dma_ppa_list, dma_meta_list;
__le64 *lba_list;
u64 paddr = pblk_line_smeta_start(pblk, line) + lm->smeta_sec;
bool padded = false;
- int rq_ppas, rq_len;
+ int rq_ppas;
int i, j;
int ret;
u64 left_ppas = pblk_sec_in_open_line(pblk, line) - lm->smeta_sec;
@@ -404,18 +388,9 @@ next_rq:
rq_ppas = pblk_calc_secs(pblk, left_ppas, 0, false);
if (!rq_ppas)
rq_ppas = pblk->min_write_pgs;
- rq_len = rq_ppas * geo->csecs;
retry_rq:
- bio = bio_map_kern(dev->q, data, rq_len, GFP_KERNEL);
- if (IS_ERR(bio))
- return PTR_ERR(bio);
-
- bio->bi_iter.bi_sector = 0; /* internal bio */
- bio_set_op_attrs(bio, REQ_OP_READ, 0);
- bio_get(bio);
-
- rqd->bio = bio;
+ rqd->bio = NULL;
rqd->opcode = NVM_OP_PREAD;
rqd->meta_list = meta_list;
rqd->nr_ppas = rq_ppas;
@@ -445,10 +420,9 @@ retry_rq:
addr_to_gen_ppa(pblk, paddr + j, line->id);
}
- ret = pblk_submit_io_sync(pblk, rqd);
+ ret = pblk_submit_io_sync(pblk, rqd, data);
if (ret) {
pblk_err(pblk, "I/O submission failed: %d\n", ret);
- bio_put(bio);
return ret;
}
@@ -460,24 +434,20 @@ retry_rq:
if (padded) {
pblk_log_read_err(pblk, rqd);
- bio_put(bio);
return -EINTR;
}
pad_distance = pblk_pad_distance(pblk, line);
ret = pblk_recov_pad_line(pblk, line, pad_distance);
if (ret) {
- bio_put(bio);
return ret;
}
padded = true;
- bio_put(bio);
goto retry_rq;
}
pblk_get_packed_meta(pblk, rqd);
- bio_put(bio);
for (i = 0; i < rqd->nr_ppas; i++) {
struct pblk_sec_meta *meta = pblk_get_meta(pblk, meta_list, i);
diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
index 4e63f9b5954c..b9a2aeba95ab 100644
--- a/drivers/lightnvm/pblk-write.c
+++ b/drivers/lightnvm/pblk-write.c
@@ -373,7 +373,6 @@ int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line)
struct pblk_emeta *emeta = meta_line->emeta;
struct ppa_addr *ppa_list;
struct pblk_g_ctx *m_ctx;
- struct bio *bio;
struct nvm_rq *rqd;
void *data;
u64 paddr;
@@ -391,20 +390,9 @@ int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line)
rq_len = rq_ppas * geo->csecs;
data = ((void *)emeta->buf) + emeta->mem;
- bio = pblk_bio_map_addr(pblk, data, rq_ppas, rq_len,
- l_mg->emeta_alloc_type, GFP_KERNEL);
- if (IS_ERR(bio)) {
- pblk_err(pblk, "failed to map emeta io");
- ret = PTR_ERR(bio);
- goto fail_free_rqd;
- }
- bio->bi_iter.bi_sector = 0; /* internal bio */
- bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
- rqd->bio = bio;
-
ret = pblk_alloc_w_rq(pblk, rqd, rq_ppas, pblk_end_io_write_meta);
if (ret)
- goto fail_free_bio;
+ goto fail_free_rqd;
ppa_list = nvm_rq_to_ppa_list(rqd);
for (i = 0; i < rqd->nr_ppas; ) {
@@ -423,7 +411,7 @@ int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line)
pblk_down_chunk(pblk, ppa_list[0]);
- ret = pblk_submit_io(pblk, rqd);
+ ret = pblk_submit_io(pblk, rqd, data);
if (ret) {
pblk_err(pblk, "emeta I/O submission failed: %d\n", ret);
goto fail_rollback;
@@ -437,8 +425,6 @@ fail_rollback:
pblk_dealloc_page(pblk, meta_line, rq_ppas);
list_add(&meta_line->list, &meta_line->list);
spin_unlock(&l_mg->close_lock);
-fail_free_bio:
- bio_put(bio);
fail_free_rqd:
pblk_free_rqd(pblk, rqd, PBLK_WRITE_INT);
return ret;
@@ -523,7 +509,7 @@ static int pblk_submit_io_set(struct pblk *pblk, struct nvm_rq *rqd)
meta_line = pblk_should_submit_meta_io(pblk, rqd);
/* Submit data write for current data line */
- err = pblk_submit_io(pblk, rqd);
+ err = pblk_submit_io(pblk, rqd, NULL);
if (err) {
pblk_err(pblk, "data I/O submission failed: %d\n", err);
return NVM_IO_ERR;
diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
index a67855387f53..86ffa875bfe1 100644
--- a/drivers/lightnvm/pblk.h
+++ b/drivers/lightnvm/pblk.h
@@ -482,11 +482,6 @@ struct pblk_line {
#define PBLK_DATA_LINES 4
enum {
- PBLK_KMALLOC_META = 1,
- PBLK_VMALLOC_META = 2,
-};
-
-enum {
PBLK_EMETA_TYPE_HEADER = 1, /* struct line_emeta first sector */
PBLK_EMETA_TYPE_LLBA = 2, /* lba list - type: __le64 */
PBLK_EMETA_TYPE_VSC = 3, /* vsc list - type: __le32 */
@@ -521,9 +516,6 @@ struct pblk_line_mgmt {
__le32 *vsc_list; /* Valid sector counts for all lines */
- /* Metadata allocation type: VMALLOC | KMALLOC */
- int emeta_alloc_type;
-
/* Pre-allocated metadata for data lines */
struct pblk_smeta *sline_meta[PBLK_DATA_LINES];
struct pblk_emeta *eline_meta[PBLK_DATA_LINES];
@@ -783,14 +775,10 @@ struct nvm_chk_meta *pblk_chunk_get_off(struct pblk *pblk,
struct ppa_addr ppa);
void pblk_log_write_err(struct pblk *pblk, struct nvm_rq *rqd);
void pblk_log_read_err(struct pblk *pblk, struct nvm_rq *rqd);
-int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd);
-int pblk_submit_io_sync(struct pblk *pblk, struct nvm_rq *rqd);
-int pblk_submit_io_sync_sem(struct pblk *pblk, struct nvm_rq *rqd);
+int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd, void *buf);
+int pblk_submit_io_sync(struct pblk *pblk, struct nvm_rq *rqd, void *buf);
int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line);
void pblk_check_chunk_state_update(struct pblk *pblk, struct nvm_rq *rqd);
-struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data,
- unsigned int nr_secs, unsigned int len,
- int alloc_type, gfp_t gfp_mask);
struct pblk_line *pblk_line_get(struct pblk *pblk);
struct pblk_line *pblk_line_get_first_data(struct pblk *pblk);
struct pblk_line *pblk_line_replace_data(struct pblk *pblk);
@@ -938,21 +926,6 @@ void pblk_rl_werr_line_out(struct pblk_rl *rl);
int pblk_sysfs_init(struct gendisk *tdisk);
void pblk_sysfs_exit(struct gendisk *tdisk);
-static inline void *pblk_malloc(size_t size, int type, gfp_t flags)
-{
- if (type == PBLK_KMALLOC_META)
- return kmalloc(size, flags);
- return vmalloc(size);
-}
-
-static inline void pblk_mfree(void *ptr, int type)
-{
- if (type == PBLK_KMALLOC_META)
- kfree(ptr);
- else
- vfree(ptr);
-}
-
static inline struct nvm_rq *nvm_rq_from_c_ctx(void *c_ctx)
{
return c_ctx - sizeof(struct nvm_rq);
diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c
index 73f5319295bc..c12cd809ab19 100644
--- a/drivers/md/bcache/closure.c
+++ b/drivers/md/bcache/closure.c
@@ -105,8 +105,14 @@ struct closure_syncer {
static void closure_sync_fn(struct closure *cl)
{
- cl->s->done = 1;
- wake_up_process(cl->s->task);
+ struct closure_syncer *s = cl->s;
+ struct task_struct *p;
+
+ rcu_read_lock();
+ p = READ_ONCE(s->task);
+ s->done = 1;
+ wake_up_process(p);
+ rcu_read_unlock();
}
void __sched __closure_sync(struct closure *cl)
diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c
index 8b123be05254..336f43910383 100644
--- a/drivers/md/bcache/debug.c
+++ b/drivers/md/bcache/debug.c
@@ -178,10 +178,9 @@ static ssize_t bch_dump_read(struct file *file, char __user *buf,
while (size) {
struct keybuf_key *w;
unsigned int bytes = min(i->bytes, size);
- int err = copy_to_user(buf, i->buf, bytes);
- if (err)
- return err;
+ if (copy_to_user(buf, i->buf, bytes))
+ return -EFAULT;
ret += bytes;
buf += bytes;
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index e2059af90791..627dcea0f5b6 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -964,6 +964,7 @@ KTYPE(bch_cache_set_internal);
static int __bch_cache_cmp(const void *l, const void *r)
{
+ cond_resched();
return *((uint16_t *)r) - *((uint16_t *)l);
}
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index c9e44ac1f9a6..3f8577e2c13b 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -408,6 +408,7 @@ static int map_request(struct dm_rq_target_io *tio)
ret = dm_dispatch_clone_request(clone, rq);
if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) {
blk_rq_unprep_clone(clone);
+ blk_mq_cleanup_rq(clone);
tio->ti->type->release_clone_rq(clone, &tio->info);
tio->clone = NULL;
return DM_MAPIO_REQUEUE;
@@ -562,7 +563,7 @@ int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t)
if (err)
goto out_kfree_tag_set;
- q = blk_mq_init_allocated_queue(md->tag_set, md->queue);
+ q = blk_mq_init_allocated_queue(md->tag_set, md->queue, true);
if (IS_ERR(q)) {
err = PTR_ERR(q);
goto out_tag_set;
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index 7354466ddc90..c766c559d36d 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -258,6 +258,11 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio)
bio_sector < start_sector))
goto out_of_bounds;
+ if (unlikely(is_mddev_broken(tmp_dev->rdev, "linear"))) {
+ bio_io_error(bio);
+ return true;
+ }
+
if (unlikely(bio_end_sector(bio) > end_sector)) {
/* This bio crosses a device boundary, so we have to split it */
struct bio *split = bio_split(bio, end_sector - bio_sector,
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 24638ccedce4..1be7abeb24fd 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -376,6 +376,11 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
struct mddev *mddev = q->queuedata;
unsigned int sectors;
+ if (unlikely(test_bit(MD_BROKEN, &mddev->flags)) && (rw == WRITE)) {
+ bio_io_error(bio);
+ return BLK_QC_T_NONE;
+ }
+
blk_queue_split(q, &bio);
if (mddev == NULL || mddev->pers == NULL) {
@@ -1232,6 +1237,8 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev)
mddev->new_layout = mddev->layout;
mddev->new_chunk_sectors = mddev->chunk_sectors;
}
+ if (mddev->level == 0)
+ mddev->layout = -1;
if (sb->state & (1<<MD_SB_CLEAN))
mddev->recovery_cp = MaxSector;
@@ -1647,6 +1654,10 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
rdev->ppl.sector = rdev->sb_start + rdev->ppl.offset;
}
+ if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_RAID0_LAYOUT) &&
+ sb->level != 0)
+ return -EINVAL;
+
if (!refdev) {
ret = 1;
} else {
@@ -1757,6 +1768,10 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
mddev->new_chunk_sectors = mddev->chunk_sectors;
}
+ if (mddev->level == 0 &&
+ !(le32_to_cpu(sb->feature_map) & MD_FEATURE_RAID0_LAYOUT))
+ mddev->layout = -1;
+
if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL)
set_bit(MD_HAS_JOURNAL, &mddev->flags);
@@ -1826,8 +1841,15 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
if (!(le32_to_cpu(sb->feature_map) &
MD_FEATURE_RECOVERY_BITMAP))
rdev->saved_raid_disk = -1;
- } else
- set_bit(In_sync, &rdev->flags);
+ } else {
+ /*
+ * If the array is FROZEN, then the device can't
+ * be in_sync with rest of array.
+ */
+ if (!test_bit(MD_RECOVERY_FROZEN,
+ &mddev->recovery))
+ set_bit(In_sync, &rdev->flags);
+ }
rdev->raid_disk = role;
break;
}
@@ -3664,11 +3686,7 @@ int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale)
return -EINVAL;
if (decimals < 0)
decimals = 0;
- while (decimals < scale) {
- result *= 10;
- decimals ++;
- }
- *res = result;
+ *res = result * int_pow(10, scale - decimals);
return 0;
}
@@ -4155,12 +4173,17 @@ __ATTR_PREALLOC(resync_start, S_IRUGO|S_IWUSR,
* active-idle
* like active, but no writes have been seen for a while (100msec).
*
+ * broken
+ * RAID0/LINEAR-only: same as clean, but array is missing a member.
+ * It's useful because RAID0/LINEAR mounted-arrays aren't stopped
+ * when a member is gone, so this state will at least alert the
+ * user that something is wrong.
*/
enum array_state { clear, inactive, suspended, readonly, read_auto, clean, active,
- write_pending, active_idle, bad_word};
+ write_pending, active_idle, broken, bad_word};
static char *array_states[] = {
"clear", "inactive", "suspended", "readonly", "read-auto", "clean", "active",
- "write-pending", "active-idle", NULL };
+ "write-pending", "active-idle", "broken", NULL };
static int match_word(const char *word, char **list)
{
@@ -4176,7 +4199,7 @@ array_state_show(struct mddev *mddev, char *page)
{
enum array_state st = inactive;
- if (mddev->pers)
+ if (mddev->pers && !test_bit(MD_NOT_READY, &mddev->flags)) {
switch(mddev->ro) {
case 1:
st = readonly;
@@ -4196,7 +4219,10 @@ array_state_show(struct mddev *mddev, char *page)
st = active;
spin_unlock(&mddev->lock);
}
- else {
+
+ if (test_bit(MD_BROKEN, &mddev->flags) && st == clean)
+ st = broken;
+ } else {
if (list_empty(&mddev->disks) &&
mddev->raid_disks == 0 &&
mddev->dev_sectors == 0)
@@ -4310,6 +4336,7 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
break;
case write_pending:
case active_idle:
+ case broken:
/* these cannot be set */
break;
}
@@ -5182,6 +5209,34 @@ static struct md_sysfs_entry md_consistency_policy =
__ATTR(consistency_policy, S_IRUGO | S_IWUSR, consistency_policy_show,
consistency_policy_store);
+static ssize_t fail_last_dev_show(struct mddev *mddev, char *page)
+{
+ return sprintf(page, "%d\n", mddev->fail_last_dev);
+}
+
+/*
+ * Setting fail_last_dev to true to allow last device to be forcibly removed
+ * from RAID1/RAID10.
+ */
+static ssize_t
+fail_last_dev_store(struct mddev *mddev, const char *buf, size_t len)
+{
+ int ret;
+ bool value;
+
+ ret = kstrtobool(buf, &value);
+ if (ret)
+ return ret;
+
+ if (value != mddev->fail_last_dev)
+ mddev->fail_last_dev = value;
+
+ return len;
+}
+static struct md_sysfs_entry md_fail_last_dev =
+__ATTR(fail_last_dev, S_IRUGO | S_IWUSR, fail_last_dev_show,
+ fail_last_dev_store);
+
static struct attribute *md_default_attrs[] = {
&md_level.attr,
&md_layout.attr,
@@ -5198,6 +5253,7 @@ static struct attribute *md_default_attrs[] = {
&md_array_size.attr,
&max_corr_read_errors.attr,
&md_consistency_policy.attr,
+ &md_fail_last_dev.attr,
NULL,
};
@@ -5744,9 +5800,6 @@ int md_run(struct mddev *mddev)
md_update_sb(mddev, 0);
md_new_event(mddev);
- sysfs_notify_dirent_safe(mddev->sysfs_state);
- sysfs_notify_dirent_safe(mddev->sysfs_action);
- sysfs_notify(&mddev->kobj, NULL, "degraded");
return 0;
bitmap_abort:
@@ -5767,6 +5820,7 @@ static int do_md_run(struct mddev *mddev)
{
int err;
+ set_bit(MD_NOT_READY, &mddev->flags);
err = md_run(mddev);
if (err)
goto out;
@@ -5787,9 +5841,14 @@ static int do_md_run(struct mddev *mddev)
set_capacity(mddev->gendisk, mddev->array_sectors);
revalidate_disk(mddev->gendisk);
+ clear_bit(MD_NOT_READY, &mddev->flags);
mddev->changed = 1;
kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
+ sysfs_notify_dirent_safe(mddev->sysfs_state);
+ sysfs_notify_dirent_safe(mddev->sysfs_action);
+ sysfs_notify(&mddev->kobj, NULL, "degraded");
out:
+ clear_bit(MD_NOT_READY, &mddev->flags);
return err;
}
@@ -6849,6 +6908,9 @@ static int set_array_info(struct mddev *mddev, mdu_array_info_t *info)
mddev->external = 0;
mddev->layout = info->layout;
+ if (mddev->level == 0)
+ /* Cannot trust RAID0 layout info here */
+ mddev->layout = -1;
mddev->chunk_sectors = info->chunk_size >> 9;
if (mddev->persistent) {
@@ -8900,6 +8962,7 @@ void md_check_recovery(struct mddev *mddev)
if (mddev_trylock(mddev)) {
int spares = 0;
+ bool try_set_sync = mddev->safemode != 0;
if (!mddev->external && mddev->safemode == 1)
mddev->safemode = 0;
@@ -8945,7 +9008,7 @@ void md_check_recovery(struct mddev *mddev)
}
}
- if (!mddev->external && !mddev->in_sync) {
+ if (try_set_sync && !mddev->external && !mddev->in_sync) {
spin_lock(&mddev->lock);
set_in_sync(mddev);
spin_unlock(&mddev->lock);
@@ -9043,7 +9106,8 @@ void md_reap_sync_thread(struct mddev *mddev)
/* resync has finished, collect result */
md_unregister_thread(&mddev->sync_thread);
if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
- !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
+ !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) &&
+ mddev->degraded != mddev->raid_disks) {
/* success...*/
/* activate any spares */
if (mddev->pers->spare_active(mddev)) {
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 10f98200e2f8..c5e3ff398b59 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -248,6 +248,12 @@ enum mddev_flags {
MD_UPDATING_SB, /* md_check_recovery is updating the metadata
* without explicitly holding reconfig_mutex.
*/
+ MD_NOT_READY, /* do_md_run() is active, so 'array_state'
+ * must not report that array is ready yet
+ */
+ MD_BROKEN, /* This is used in RAID-0/LINEAR only, to stop
+ * I/O in case an array member is gone/failed.
+ */
};
enum mddev_sb_flags {
@@ -487,6 +493,7 @@ struct mddev {
unsigned int good_device_nr; /* good device num within cluster raid */
bool has_superblocks:1;
+ bool fail_last_dev:1;
};
enum recovery_flags {
@@ -735,6 +742,19 @@ extern void mddev_create_wb_pool(struct mddev *mddev, struct md_rdev *rdev,
struct md_rdev *md_find_rdev_nr_rcu(struct mddev *mddev, int nr);
struct md_rdev *md_find_rdev_rcu(struct mddev *mddev, dev_t dev);
+static inline bool is_mddev_broken(struct md_rdev *rdev, const char *md_type)
+{
+ int flags = rdev->bdev->bd_disk->flags;
+
+ if (!(flags & GENHD_FL_UP)) {
+ if (!test_and_set_bit(MD_BROKEN, &rdev->mddev->flags))
+ pr_warn("md: %s: %s array has a missing/failed member\n",
+ mdname(rdev->mddev), md_type);
+ return true;
+ }
+ return false;
+}
+
static inline void rdev_dec_pending(struct md_rdev *rdev, struct mddev *mddev)
{
int faulty = test_bit(Faulty, &rdev->flags);
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index bf5cf184a260..f61693e59684 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -19,6 +19,9 @@
#include "raid0.h"
#include "raid5.h"
+static int default_layout = 0;
+module_param(default_layout, int, 0644);
+
#define UNSUPPORTED_MDDEV_FLAGS \
((1L << MD_HAS_JOURNAL) | \
(1L << MD_JOURNAL_CLEAN) | \
@@ -139,6 +142,22 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
}
pr_debug("md/raid0:%s: FINAL %d zones\n",
mdname(mddev), conf->nr_strip_zones);
+
+ if (conf->nr_strip_zones == 1) {
+ conf->layout = RAID0_ORIG_LAYOUT;
+ } else if (mddev->layout == RAID0_ORIG_LAYOUT ||
+ mddev->layout == RAID0_ALT_MULTIZONE_LAYOUT) {
+ conf->layout = mddev->layout;
+ } else if (default_layout == RAID0_ORIG_LAYOUT ||
+ default_layout == RAID0_ALT_MULTIZONE_LAYOUT) {
+ conf->layout = default_layout;
+ } else {
+ pr_err("md/raid0:%s: cannot assemble multi-zone RAID0 with default_layout setting\n",
+ mdname(mddev));
+ pr_err("md/raid0: please set raid.default_layout to 1 or 2\n");
+ err = -ENOTSUPP;
+ goto abort;
+ }
/*
* now since we have the hard sector sizes, we can make sure
* chunk size is a multiple of that sector size
@@ -547,10 +566,12 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
{
+ struct r0conf *conf = mddev->private;
struct strip_zone *zone;
struct md_rdev *tmp_dev;
sector_t bio_sector;
sector_t sector;
+ sector_t orig_sector;
unsigned chunk_sects;
unsigned sectors;
@@ -584,8 +605,26 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
bio = split;
}
+ orig_sector = sector;
zone = find_zone(mddev->private, &sector);
- tmp_dev = map_sector(mddev, zone, sector, &sector);
+ switch (conf->layout) {
+ case RAID0_ORIG_LAYOUT:
+ tmp_dev = map_sector(mddev, zone, orig_sector, &sector);
+ break;
+ case RAID0_ALT_MULTIZONE_LAYOUT:
+ tmp_dev = map_sector(mddev, zone, sector, &sector);
+ break;
+ default:
+ WARN("md/raid0:%s: Invalid layout\n", mdname(mddev));
+ bio_io_error(bio);
+ return true;
+ }
+
+ if (unlikely(is_mddev_broken(tmp_dev, "raid0"))) {
+ bio_io_error(bio);
+ return true;
+ }
+
bio_set_dev(bio, tmp_dev->bdev);
bio->bi_iter.bi_sector = sector + zone->dev_start +
tmp_dev->data_offset;
diff --git a/drivers/md/raid0.h b/drivers/md/raid0.h
index 540e65d92642..3816e5477db1 100644
--- a/drivers/md/raid0.h
+++ b/drivers/md/raid0.h
@@ -8,11 +8,25 @@ struct strip_zone {
int nb_dev; /* # of devices attached to the zone */
};
+/* Linux 3.14 (20d0189b101) made an unintended change to
+ * the RAID0 layout for multi-zone arrays (where devices aren't all
+ * the same size.
+ * RAID0_ORIG_LAYOUT restores the original layout
+ * RAID0_ALT_MULTIZONE_LAYOUT uses the altered layout
+ * The layouts are identical when there is only one zone (all
+ * devices the same size).
+ */
+
+enum r0layout {
+ RAID0_ORIG_LAYOUT = 1,
+ RAID0_ALT_MULTIZONE_LAYOUT = 2,
+};
struct r0conf {
struct strip_zone *strip_zone;
struct md_rdev **devlist; /* lists of rdevs, pointed to
* by strip_zone->dev */
int nr_strip_zones;
+ enum r0layout layout;
};
#endif
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 34e26834ad28..0466ee2453b4 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -447,19 +447,21 @@ static void raid1_end_write_request(struct bio *bio)
/* We never try FailFast to WriteMostly devices */
!test_bit(WriteMostly, &rdev->flags)) {
md_error(r1_bio->mddev, rdev);
- if (!test_bit(Faulty, &rdev->flags))
- /* This is the only remaining device,
- * We need to retry the write without
- * FailFast
- */
- set_bit(R1BIO_WriteError, &r1_bio->state);
- else {
- /* Finished with this branch */
- r1_bio->bios[mirror] = NULL;
- to_put = bio;
- }
- } else
+ }
+
+ /*
+ * When the device is faulty, it is not necessary to
+ * handle write error.
+ * For failfast, this is the only remaining device,
+ * We need to retry the write without FailFast.
+ */
+ if (!test_bit(Faulty, &rdev->flags))
set_bit(R1BIO_WriteError, &r1_bio->state);
+ else {
+ /* Finished with this branch */
+ r1_bio->bios[mirror] = NULL;
+ to_put = bio;
+ }
} else {
/*
* Set R1BIO_Uptodate in our master bio, so that we
@@ -872,8 +874,11 @@ static void flush_pending_writes(struct r1conf *conf)
* backgroup IO calls must call raise_barrier. Once that returns
* there is no normal IO happeing. It must arrange to call
* lower_barrier when the particular background IO completes.
+ *
+ * If resync/recovery is interrupted, returns -EINTR;
+ * Otherwise, returns 0.
*/
-static sector_t raise_barrier(struct r1conf *conf, sector_t sector_nr)
+static int raise_barrier(struct r1conf *conf, sector_t sector_nr)
{
int idx = sector_to_idx(sector_nr);
@@ -1612,12 +1617,12 @@ static void raid1_error(struct mddev *mddev, struct md_rdev *rdev)
/*
* If it is not operational, then we have already marked it as dead
- * else if it is the last working disks, ignore the error, let the
- * next level up know.
+ * else if it is the last working disks with "fail_last_dev == false",
+ * ignore the error, let the next level up know.
* else mark the drive as failed
*/
spin_lock_irqsave(&conf->device_lock, flags);
- if (test_bit(In_sync, &rdev->flags)
+ if (test_bit(In_sync, &rdev->flags) && !mddev->fail_last_dev
&& (conf->raid_disks - mddev->degraded) == 1) {
/*
* Don't fail the drive, act as though we were just a
@@ -1901,6 +1906,22 @@ static void abort_sync_write(struct mddev *mddev, struct r1bio *r1_bio)
} while (sectors_to_go > 0);
}
+static void put_sync_write_buf(struct r1bio *r1_bio, int uptodate)
+{
+ if (atomic_dec_and_test(&r1_bio->remaining)) {
+ struct mddev *mddev = r1_bio->mddev;
+ int s = r1_bio->sectors;
+
+ if (test_bit(R1BIO_MadeGood, &r1_bio->state) ||
+ test_bit(R1BIO_WriteError, &r1_bio->state))
+ reschedule_retry(r1_bio);
+ else {
+ put_buf(r1_bio);
+ md_done_sync(mddev, s, uptodate);
+ }
+ }
+}
+
static void end_sync_write(struct bio *bio)
{
int uptodate = !bio->bi_status;
@@ -1927,16 +1948,7 @@ static void end_sync_write(struct bio *bio)
)
set_bit(R1BIO_MadeGood, &r1_bio->state);
- if (atomic_dec_and_test(&r1_bio->remaining)) {
- int s = r1_bio->sectors;
- if (test_bit(R1BIO_MadeGood, &r1_bio->state) ||
- test_bit(R1BIO_WriteError, &r1_bio->state))
- reschedule_retry(r1_bio);
- else {
- put_buf(r1_bio);
- md_done_sync(mddev, s, uptodate);
- }
- }
+ put_sync_write_buf(r1_bio, uptodate);
}
static int r1_sync_page_io(struct md_rdev *rdev, sector_t sector,
@@ -2219,17 +2231,7 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio)
generic_make_request(wbio);
}
- if (atomic_dec_and_test(&r1_bio->remaining)) {
- /* if we're here, all write(s) have completed, so clean up */
- int s = r1_bio->sectors;
- if (test_bit(R1BIO_MadeGood, &r1_bio->state) ||
- test_bit(R1BIO_WriteError, &r1_bio->state))
- reschedule_retry(r1_bio);
- else {
- put_buf(r1_bio);
- md_done_sync(mddev, s, 1);
- }
- }
+ put_sync_write_buf(r1_bio, 1);
}
/*
@@ -3127,6 +3129,13 @@ static int raid1_run(struct mddev *mddev)
!test_bit(In_sync, &conf->mirrors[i].rdev->flags) ||
test_bit(Faulty, &conf->mirrors[i].rdev->flags))
mddev->degraded++;
+ /*
+ * RAID1 needs at least one disk in active
+ */
+ if (conf->raid_disks - mddev->degraded < 1) {
+ ret = -EINVAL;
+ goto abort;
+ }
if (conf->raid_disks - mddev->degraded == 1)
mddev->recovery_cp = MaxSector;
@@ -3160,8 +3169,12 @@ static int raid1_run(struct mddev *mddev)
ret = md_integrity_register(mddev);
if (ret) {
md_unregister_thread(&mddev->thread);
- raid1_free(mddev, conf);
+ goto abort;
}
+ return 0;
+
+abort:
+ raid1_free(mddev, conf);
return ret;
}
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 8a1354a08a1a..299c7b1c9718 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -465,19 +465,21 @@ static void raid10_end_write_request(struct bio *bio)
if (test_bit(FailFast, &rdev->flags) &&
(bio->bi_opf & MD_FAILFAST)) {
md_error(rdev->mddev, rdev);
- if (!test_bit(Faulty, &rdev->flags))
- /* This is the only remaining device,
- * We need to retry the write without
- * FailFast
- */
- set_bit(R10BIO_WriteError, &r10_bio->state);
- else {
- r10_bio->devs[slot].bio = NULL;
- to_put = bio;
- dec_rdev = 1;
- }
- } else
+ }
+
+ /*
+ * When the device is faulty, it is not necessary to
+ * handle write error.
+ * For failfast, this is the only remaining device,
+ * We need to retry the write without FailFast.
+ */
+ if (!test_bit(Faulty, &rdev->flags))
set_bit(R10BIO_WriteError, &r10_bio->state);
+ else {
+ r10_bio->devs[slot].bio = NULL;
+ to_put = bio;
+ dec_rdev = 1;
+ }
}
} else {
/*
@@ -1638,12 +1640,12 @@ static void raid10_error(struct mddev *mddev, struct md_rdev *rdev)
/*
* If it is not operational, then we have already marked it as dead
- * else if it is the last working disks, ignore the error, let the
- * next level up know.
+ * else if it is the last working disks with "fail_last_dev == false",
+ * ignore the error, let the next level up know.
* else mark the drive as failed
*/
spin_lock_irqsave(&conf->device_lock, flags);
- if (test_bit(In_sync, &rdev->flags)
+ if (test_bit(In_sync, &rdev->flags) && !mddev->fail_last_dev
&& !enough(conf, rdev->raid_disk)) {
/*
* Don't fail the drive, just return an IO error.
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 3de4e13bde98..223e97ab27e6 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2526,7 +2526,8 @@ static void raid5_end_read_request(struct bio * bi)
int set_bad = 0;
clear_bit(R5_UPTODATE, &sh->dev[i].flags);
- atomic_inc(&rdev->read_errors);
+ if (!(bi->bi_status == BLK_STS_PROTECTION))
+ atomic_inc(&rdev->read_errors);
if (test_bit(R5_ReadRepl, &sh->dev[i].flags))
pr_warn_ratelimited(
"md/raid:%s: read error on replacement device (sector %llu on %s).\n",
@@ -2549,16 +2550,24 @@ static void raid5_end_read_request(struct bio * bi)
(unsigned long long)s,
bdn);
} else if (atomic_read(&rdev->read_errors)
- > conf->max_nr_stripes)
- pr_warn("md/raid:%s: Too many read errors, failing device %s.\n",
- mdname(conf->mddev), bdn);
- else
+ > conf->max_nr_stripes) {
+ if (!test_bit(Faulty, &rdev->flags)) {
+ pr_warn("md/raid:%s: %d read_errors > %d stripes\n",
+ mdname(conf->mddev),
+ atomic_read(&rdev->read_errors),
+ conf->max_nr_stripes);
+ pr_warn("md/raid:%s: Too many read errors, failing device %s.\n",
+ mdname(conf->mddev), bdn);
+ }
+ } else
retry = 1;
if (set_bad && test_bit(In_sync, &rdev->flags)
&& !test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
retry = 1;
if (retry)
- if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags)) {
+ if (sh->qd_idx >= 0 && sh->pd_idx == i)
+ set_bit(R5_ReadError, &sh->dev[i].flags);
+ else if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags)) {
set_bit(R5_ReadError, &sh->dev[i].flags);
clear_bit(R5_ReadNoMerge, &sh->dev[i].flags);
} else
@@ -4612,7 +4621,6 @@ static void break_stripe_batch_list(struct stripe_head *head_sh,
(1 << STRIPE_FULL_WRITE) |
(1 << STRIPE_BIOFILL_RUN) |
(1 << STRIPE_COMPUTE_RUN) |
- (1 << STRIPE_OPS_REQ_PENDING) |
(1 << STRIPE_DISCARD) |
(1 << STRIPE_BATCH_READY) |
(1 << STRIPE_BATCH_ERR) |
@@ -5491,7 +5499,7 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
return;
logical_sector = bi->bi_iter.bi_sector & ~((sector_t)STRIPE_SECTORS-1);
- last_sector = bi->bi_iter.bi_sector + (bi->bi_iter.bi_size>>9);
+ last_sector = bio_end_sector(bi);
bi->bi_next = NULL;
@@ -5718,7 +5726,8 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
do_flush = false;
}
- set_bit(STRIPE_HANDLE, &sh->state);
+ if (!sh->batch_head)
+ set_bit(STRIPE_HANDLE, &sh->state);
clear_bit(STRIPE_DELAYED, &sh->state);
if ((!sh->batch_head || sh == sh->batch_head) &&
(bi->bi_opf & REQ_SYNC) &&
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index cf991f13403e..f90e0704bed9 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -357,7 +357,6 @@ enum {
STRIPE_FULL_WRITE, /* all blocks are set to be overwritten */
STRIPE_BIOFILL_RUN,
STRIPE_COMPUTE_RUN,
- STRIPE_OPS_REQ_PENDING,
STRIPE_ON_UNPLUG_LIST,
STRIPE_DISCARD,
STRIPE_ON_RELEASE_LIST,
@@ -493,9 +492,7 @@ struct disk_info {
*/
static inline struct bio *r5_next_bio(struct bio *bio, sector_t sector)
{
- int sectors = bio_sectors(bio);
-
- if (bio->bi_iter.bi_sector + sectors < sector + STRIPE_SECTORS)
+ if (bio_end_sector(bio) < sector + STRIPE_SECTORS)
return bio->bi_next;
else
return NULL;
diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
index ec43ac9199e2..2b36f052bfb9 100644
--- a/drivers/nvme/host/Kconfig
+++ b/drivers/nvme/host/Kconfig
@@ -64,6 +64,7 @@ config NVME_TCP
depends on INET
depends on BLK_DEV_NVME
select NVME_FABRICS
+ select CRYPTO_CRC32C
help
This provides support for the NVMe over Fabrics protocol using
the TCP transport. This allows you to use remote block devices
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index d3d6b7bd6903..1ede1763a5ee 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -22,12 +22,12 @@
#include <linux/pm_qos.h>
#include <asm/unaligned.h>
-#define CREATE_TRACE_POINTS
-#include "trace.h"
-
#include "nvme.h"
#include "fabrics.h"
+#define CREATE_TRACE_POINTS
+#include "trace.h"
+
#define NVME_MINORS (1U << MINORBITS)
unsigned int admin_timeout = 60;
@@ -81,7 +81,6 @@ EXPORT_SYMBOL_GPL(nvme_reset_wq);
struct workqueue_struct *nvme_delete_wq;
EXPORT_SYMBOL_GPL(nvme_delete_wq);
-static DEFINE_IDA(nvme_subsystems_ida);
static LIST_HEAD(nvme_subsystems);
static DEFINE_MUTEX(nvme_subsystems_lock);
@@ -197,9 +196,9 @@ static inline bool nvme_ns_has_pi(struct nvme_ns *ns)
return ns->pi_type && ns->ms == sizeof(struct t10_pi_tuple);
}
-static blk_status_t nvme_error_status(struct request *req)
+static blk_status_t nvme_error_status(u16 status)
{
- switch (nvme_req(req)->status & 0x7ff) {
+ switch (status & 0x7ff) {
case NVME_SC_SUCCESS:
return BLK_STS_OK;
case NVME_SC_CAP_EXCEEDED:
@@ -226,6 +225,8 @@ static blk_status_t nvme_error_status(struct request *req)
return BLK_STS_PROTECTION;
case NVME_SC_RESERVATION_CONFLICT:
return BLK_STS_NEXUS;
+ case NVME_SC_HOST_PATH_ERROR:
+ return BLK_STS_TRANSPORT;
default:
return BLK_STS_IOERR;
}
@@ -260,7 +261,7 @@ static void nvme_retry_req(struct request *req)
void nvme_complete_rq(struct request *req)
{
- blk_status_t status = nvme_error_status(req);
+ blk_status_t status = nvme_error_status(nvme_req(req)->status);
trace_nvme_complete_rq(req);
@@ -279,6 +280,8 @@ void nvme_complete_rq(struct request *req)
return;
}
}
+
+ nvme_trace_bio_complete(req, status);
blk_mq_end_request(req, status);
}
EXPORT_SYMBOL_GPL(nvme_complete_rq);
@@ -288,8 +291,12 @@ bool nvme_cancel_request(struct request *req, void *data, bool reserved)
dev_dbg_ratelimited(((struct nvme_ctrl *) data)->device,
"Cancelling I/O %d", req->tag);
- nvme_req(req)->status = NVME_SC_ABORT_REQ;
- blk_mq_complete_request_sync(req);
+ /* don't abort one completed request */
+ if (blk_mq_request_completed(req))
+ return true;
+
+ nvme_req(req)->status = NVME_SC_HOST_PATH_ERROR;
+ blk_mq_complete_request(req);
return true;
}
EXPORT_SYMBOL_GPL(nvme_cancel_request);
@@ -1088,10 +1095,9 @@ static int nvme_identify_ns_list(struct nvme_ctrl *dev, unsigned nsid, __le32 *n
NVME_IDENTIFY_DATA_SIZE);
}
-static struct nvme_id_ns *nvme_identify_ns(struct nvme_ctrl *ctrl,
- unsigned nsid)
+static int nvme_identify_ns(struct nvme_ctrl *ctrl,
+ unsigned nsid, struct nvme_id_ns **id)
{
- struct nvme_id_ns *id;
struct nvme_command c = { };
int error;
@@ -1100,18 +1106,17 @@ static struct nvme_id_ns *nvme_identify_ns(struct nvme_ctrl *ctrl,
c.identify.nsid = cpu_to_le32(nsid);
c.identify.cns = NVME_ID_CNS_NS;
- id = kmalloc(sizeof(*id), GFP_KERNEL);
- if (!id)
- return NULL;
+ *id = kmalloc(sizeof(**id), GFP_KERNEL);
+ if (!*id)
+ return -ENOMEM;
- error = nvme_submit_sync_cmd(ctrl->admin_q, &c, id, sizeof(*id));
+ error = nvme_submit_sync_cmd(ctrl->admin_q, &c, *id, sizeof(**id));
if (error) {
dev_warn(ctrl->device, "Identify namespace failed (%d)\n", error);
- kfree(id);
- return NULL;
+ kfree(*id);
}
- return id;
+ return error;
}
static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid,
@@ -1180,7 +1185,8 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count)
EXPORT_SYMBOL_GPL(nvme_set_queue_count);
#define NVME_AEN_SUPPORTED \
- (NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_FW_ACT | NVME_AEN_CFG_ANA_CHANGE)
+ (NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_FW_ACT | \
+ NVME_AEN_CFG_ANA_CHANGE | NVME_AEN_CFG_DISC_CHANGE)
static void nvme_enable_aen(struct nvme_ctrl *ctrl)
{
@@ -1195,6 +1201,8 @@ static void nvme_enable_aen(struct nvme_ctrl *ctrl)
if (status)
dev_warn(ctrl->device, "Failed to configure AEN (cfg %x)\n",
supported_aens);
+
+ queue_work(nvme_wq, &ctrl->async_event_work);
}
static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
@@ -1594,9 +1602,11 @@ static void nvme_config_write_zeroes(struct gendisk *disk, struct nvme_ns *ns)
blk_queue_max_write_zeroes_sectors(disk->queue, max_sectors);
}
-static void nvme_report_ns_ids(struct nvme_ctrl *ctrl, unsigned int nsid,
+static int nvme_report_ns_ids(struct nvme_ctrl *ctrl, unsigned int nsid,
struct nvme_id_ns *id, struct nvme_ns_ids *ids)
{
+ int ret = 0;
+
memset(ids, 0, sizeof(*ids));
if (ctrl->vs >= NVME_VS(1, 1, 0))
@@ -1607,10 +1617,12 @@ static void nvme_report_ns_ids(struct nvme_ctrl *ctrl, unsigned int nsid,
/* Don't treat error as fatal we potentially
* already have a NGUID or EUI-64
*/
- if (nvme_identify_ns_descs(ctrl, nsid, ids))
+ ret = nvme_identify_ns_descs(ctrl, nsid, ids);
+ if (ret)
dev_warn(ctrl->device,
- "%s: Identify Descriptors failed\n", __func__);
+ "Identify Descriptors failed (%d)\n", ret);
}
+ return ret;
}
static bool nvme_ns_ids_valid(struct nvme_ns_ids *ids)
@@ -1738,25 +1750,37 @@ static int nvme_revalidate_disk(struct gendisk *disk)
return -ENODEV;
}
- id = nvme_identify_ns(ctrl, ns->head->ns_id);
- if (!id)
- return -ENODEV;
+ ret = nvme_identify_ns(ctrl, ns->head->ns_id, &id);
+ if (ret)
+ goto out;
if (id->ncap == 0) {
ret = -ENODEV;
- goto out;
+ goto free_id;
}
__nvme_revalidate_disk(disk, id);
- nvme_report_ns_ids(ctrl, ns->head->ns_id, id, &ids);
+ ret = nvme_report_ns_ids(ctrl, ns->head->ns_id, id, &ids);
+ if (ret)
+ goto free_id;
+
if (!nvme_ns_ids_equal(&ns->head->ids, &ids)) {
dev_err(ctrl->device,
"identifiers changed for nsid %d\n", ns->head->ns_id);
ret = -ENODEV;
}
-out:
+free_id:
kfree(id);
+out:
+ /*
+ * Only fail the function if we got a fatal error back from the
+ * device, otherwise ignore the error and just move on.
+ */
+ if (ret == -ENOMEM || (ret > 0 && !(ret & NVME_SC_DNR)))
+ ret = 0;
+ else if (ret > 0)
+ ret = blk_status_to_errno(nvme_error_status(ret));
return ret;
}
@@ -1952,7 +1976,7 @@ static int nvme_wait_ready(struct nvme_ctrl *ctrl, u64 cap, bool enabled)
* bits', but doing so may cause the device to complete commands to the
* admin queue ... and we don't know what memory that might be pointing at!
*/
-int nvme_disable_ctrl(struct nvme_ctrl *ctrl, u64 cap)
+int nvme_disable_ctrl(struct nvme_ctrl *ctrl)
{
int ret;
@@ -1966,20 +1990,27 @@ int nvme_disable_ctrl(struct nvme_ctrl *ctrl, u64 cap)
if (ctrl->quirks & NVME_QUIRK_DELAY_BEFORE_CHK_RDY)
msleep(NVME_QUIRK_DELAY_AMOUNT);
- return nvme_wait_ready(ctrl, cap, false);
+ return nvme_wait_ready(ctrl, ctrl->cap, false);
}
EXPORT_SYMBOL_GPL(nvme_disable_ctrl);
-int nvme_enable_ctrl(struct nvme_ctrl *ctrl, u64 cap)
+int nvme_enable_ctrl(struct nvme_ctrl *ctrl)
{
/*
* Default to a 4K page size, with the intention to update this
* path in the future to accomodate architectures with differing
* kernel and IO page sizes.
*/
- unsigned dev_page_min = NVME_CAP_MPSMIN(cap) + 12, page_shift = 12;
+ unsigned dev_page_min, page_shift = 12;
int ret;
+ ret = ctrl->ops->reg_read64(ctrl, NVME_REG_CAP, &ctrl->cap);
+ if (ret) {
+ dev_err(ctrl->device, "Reading CAP failed (%d)\n", ret);
+ return ret;
+ }
+ dev_page_min = NVME_CAP_MPSMIN(ctrl->cap) + 12;
+
if (page_shift < dev_page_min) {
dev_err(ctrl->device,
"Minimum device page size %u too large for host (%u)\n",
@@ -1998,7 +2029,7 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl, u64 cap)
ret = ctrl->ops->reg_write32(ctrl, NVME_REG_CC, ctrl->ctrl_config);
if (ret)
return ret;
- return nvme_wait_ready(ctrl, cap, true);
+ return nvme_wait_ready(ctrl, ctrl->cap, true);
}
EXPORT_SYMBOL_GPL(nvme_enable_ctrl);
@@ -2332,7 +2363,8 @@ static void nvme_release_subsystem(struct device *dev)
struct nvme_subsystem *subsys =
container_of(dev, struct nvme_subsystem, dev);
- ida_simple_remove(&nvme_subsystems_ida, subsys->instance);
+ if (subsys->instance >= 0)
+ ida_simple_remove(&nvme_instance_ida, subsys->instance);
kfree(subsys);
}
@@ -2361,6 +2393,17 @@ static struct nvme_subsystem *__nvme_find_get_subsystem(const char *subsysnqn)
lockdep_assert_held(&nvme_subsystems_lock);
+ /*
+ * Fail matches for discovery subsystems. This results
+ * in each discovery controller bound to a unique subsystem.
+ * This avoids issues with validating controller values
+ * that can only be true when there is a single unique subsystem.
+ * There may be multiple and completely independent entities
+ * that provide discovery controllers.
+ */
+ if (!strcmp(subsysnqn, NVME_DISC_SUBSYS_NAME))
+ return NULL;
+
list_for_each_entry(subsys, &nvme_subsystems, entry) {
if (strcmp(subsys->subnqn, subsysnqn))
continue;
@@ -2461,12 +2504,8 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
subsys = kzalloc(sizeof(*subsys), GFP_KERNEL);
if (!subsys)
return -ENOMEM;
- ret = ida_simple_get(&nvme_subsystems_ida, 0, 0, GFP_KERNEL);
- if (ret < 0) {
- kfree(subsys);
- return ret;
- }
- subsys->instance = ret;
+
+ subsys->instance = -1;
mutex_init(&subsys->lock);
kref_init(&subsys->ref);
INIT_LIST_HEAD(&subsys->ctrls);
@@ -2485,7 +2524,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
subsys->dev.class = nvme_subsys_class;
subsys->dev.release = nvme_release_subsystem;
subsys->dev.groups = nvme_subsys_attrs_groups;
- dev_set_name(&subsys->dev, "nvme-subsys%d", subsys->instance);
+ dev_set_name(&subsys->dev, "nvme-subsys%d", ctrl->instance);
device_initialize(&subsys->dev);
mutex_lock(&nvme_subsystems_lock);
@@ -2517,6 +2556,8 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
goto out_put_subsystem;
}
+ if (!found)
+ subsys->instance = ctrl->instance;
ctrl->subsys = subsys;
list_add_tail(&ctrl->subsys_entry, &subsys->ctrls);
mutex_unlock(&nvme_subsystems_lock);
@@ -2574,7 +2615,6 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl)
int nvme_init_identify(struct nvme_ctrl *ctrl)
{
struct nvme_id_ctrl *id;
- u64 cap;
int ret, page_shift;
u32 max_hw_sectors;
bool prev_apst_enabled;
@@ -2584,16 +2624,11 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
dev_err(ctrl->device, "Reading VS failed (%d)\n", ret);
return ret;
}
-
- ret = ctrl->ops->reg_read64(ctrl, NVME_REG_CAP, &cap);
- if (ret) {
- dev_err(ctrl->device, "Reading CAP failed (%d)\n", ret);
- return ret;
- }
- page_shift = NVME_CAP_MPSMIN(cap) + 12;
+ page_shift = NVME_CAP_MPSMIN(ctrl->cap) + 12;
+ ctrl->sqsize = min_t(int, NVME_CAP_MQES(ctrl->cap), ctrl->sqsize);
if (ctrl->vs >= NVME_VS(1, 1, 0))
- ctrl->subsystem = NVME_CAP_NSSRC(cap);
+ ctrl->subsystem = NVME_CAP_NSSRC(ctrl->cap);
ret = nvme_identify_ctrl(ctrl, &id);
if (ret) {
@@ -3184,7 +3219,9 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
head->ns_id = nsid;
kref_init(&head->ref);
- nvme_report_ns_ids(ctrl, nsid, id, &head->ids);
+ ret = nvme_report_ns_ids(ctrl, nsid, id, &head->ids);
+ if (ret)
+ goto out_cleanup_srcu;
ret = __nvme_check_ids(ctrl->subsys, head);
if (ret) {
@@ -3209,6 +3246,8 @@ out_ida_remove:
out_free_head:
kfree(head);
out:
+ if (ret > 0)
+ ret = blk_status_to_errno(nvme_error_status(ret));
return ERR_PTR(ret);
}
@@ -3232,7 +3271,10 @@ static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid,
} else {
struct nvme_ns_ids ids;
- nvme_report_ns_ids(ctrl, nsid, id, &ids);
+ ret = nvme_report_ns_ids(ctrl, nsid, id, &ids);
+ if (ret)
+ goto out_unlock;
+
if (!nvme_ns_ids_equal(&head->ids, &ids)) {
dev_err(ctrl->device,
"IDs don't match for shared namespace %d\n",
@@ -3247,6 +3289,8 @@ static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid,
out_unlock:
mutex_unlock(&ctrl->subsys->lock);
+ if (ret > 0)
+ ret = blk_status_to_errno(nvme_error_status(ret));
return ret;
}
@@ -3338,11 +3382,9 @@ static int nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
nvme_set_queue_limits(ctrl, ns->queue);
- id = nvme_identify_ns(ctrl, nsid);
- if (!id) {
- ret = -EIO;
+ ret = nvme_identify_ns(ctrl, nsid, &id);
+ if (ret)
goto out_free_queue;
- }
if (id->ncap == 0) {
ret = -EINVAL;
@@ -3404,6 +3446,8 @@ static int nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
blk_cleanup_queue(ns->queue);
out_free_ns:
kfree(ns);
+ if (ret > 0)
+ ret = blk_status_to_errno(nvme_error_status(ret));
return ret;
}
@@ -3617,6 +3661,33 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl)
}
EXPORT_SYMBOL_GPL(nvme_remove_namespaces);
+static int nvme_class_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+ struct nvme_ctrl *ctrl =
+ container_of(dev, struct nvme_ctrl, ctrl_device);
+ struct nvmf_ctrl_options *opts = ctrl->opts;
+ int ret;
+
+ ret = add_uevent_var(env, "NVME_TRTYPE=%s", ctrl->ops->name);
+ if (ret)
+ return ret;
+
+ if (opts) {
+ ret = add_uevent_var(env, "NVME_TRADDR=%s", opts->traddr);
+ if (ret)
+ return ret;
+
+ ret = add_uevent_var(env, "NVME_TRSVCID=%s",
+ opts->trsvcid ?: "none");
+ if (ret)
+ return ret;
+
+ ret = add_uevent_var(env, "NVME_HOST_TRADDR=%s",
+ opts->host_traddr ?: "none");
+ }
+ return ret;
+}
+
static void nvme_aen_uevent(struct nvme_ctrl *ctrl)
{
char *envp[2] = { NULL, NULL };
@@ -3723,6 +3794,9 @@ static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
queue_work(nvme_wq, &ctrl->ana_work);
break;
#endif
+ case NVME_AER_NOTICE_DISC_CHANGED:
+ ctrl->aen_result = result;
+ break;
default:
dev_warn(ctrl->device, "async event result %08x\n", result);
}
@@ -3769,10 +3843,10 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl)
if (ctrl->kato)
nvme_start_keep_alive(ctrl);
+ nvme_enable_aen(ctrl);
+
if (ctrl->queue_count > 1) {
nvme_queue_scan(ctrl);
- nvme_enable_aen(ctrl);
- queue_work(nvme_wq, &ctrl->async_event_work);
nvme_start_queues(ctrl);
}
}
@@ -3792,7 +3866,9 @@ static void nvme_free_ctrl(struct device *dev)
container_of(dev, struct nvme_ctrl, ctrl_device);
struct nvme_subsystem *subsys = ctrl->subsys;
- ida_simple_remove(&nvme_instance_ida, ctrl->instance);
+ if (subsys && ctrl->instance != subsys->instance)
+ ida_simple_remove(&nvme_instance_ida, ctrl->instance);
+
kfree(ctrl->effects);
nvme_mpath_uninit(ctrl);
__free_page(ctrl->discard_page);
@@ -3992,6 +4068,9 @@ void nvme_sync_queues(struct nvme_ctrl *ctrl)
list_for_each_entry(ns, &ctrl->namespaces, list)
blk_sync_queue(ns->queue);
up_read(&ctrl->namespaces_rwsem);
+
+ if (ctrl->admin_q)
+ blk_sync_queue(ctrl->admin_q);
}
EXPORT_SYMBOL_GPL(nvme_sync_queues);
@@ -4050,6 +4129,7 @@ static int __init nvme_core_init(void)
result = PTR_ERR(nvme_class);
goto unregister_chrdev;
}
+ nvme_class->dev_uevent = nvme_class_uevent;
nvme_subsys_class = class_create(THIS_MODULE, "nvme-subsystem");
if (IS_ERR(nvme_subsys_class)) {
@@ -4074,7 +4154,6 @@ out:
static void __exit nvme_core_exit(void)
{
- ida_destroy(&nvme_subsystems_ida);
class_destroy(nvme_subsys_class);
class_destroy(nvme_class);
unregister_chrdev_region(nvme_chr_devt, NVME_MINORS);
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 1994d5b42f94..74b8818ac9a1 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -150,7 +150,7 @@ int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val)
cmd.prop_get.fctype = nvme_fabrics_type_property_get;
cmd.prop_get.offset = cpu_to_le32(off);
- ret = __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, &res, NULL, 0, 0,
+ ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0, 0,
NVME_QID_ANY, 0, 0, false);
if (ret >= 0)
@@ -197,7 +197,7 @@ int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
cmd.prop_get.attrib = 1;
cmd.prop_get.offset = cpu_to_le32(off);
- ret = __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, &res, NULL, 0, 0,
+ ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0, 0,
NVME_QID_ANY, 0, 0, false);
if (ret >= 0)
@@ -243,7 +243,7 @@ int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val)
cmd.prop_set.offset = cpu_to_le32(off);
cmd.prop_set.value = cpu_to_le64(val);
- ret = __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, NULL, 0, 0,
+ ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, NULL, NULL, 0, 0,
NVME_QID_ANY, 0, 0, false);
if (unlikely(ret))
dev_err(ctrl->device,
@@ -381,8 +381,8 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl)
* Set keep-alive timeout in seconds granularity (ms * 1000)
* and add a grace period for controller kato enforcement
*/
- cmd.connect.kato = ctrl->opts->discovery_nqn ? 0 :
- cpu_to_le32((ctrl->kato + NVME_KATO_GRACE) * 1000);
+ cmd.connect.kato = ctrl->kato ?
+ cpu_to_le32((ctrl->kato + NVME_KATO_GRACE) * 1000) : 0;
if (ctrl->opts->disable_sqflow)
cmd.connect.cattr |= NVME_CONNECT_DISABLE_SQFLOW;
@@ -396,7 +396,7 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl)
strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE);
strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE);
- ret = __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, &res,
+ ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res,
data, sizeof(*data), 0, NVME_QID_ANY, 1,
BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT, false);
if (ret) {
@@ -611,6 +611,7 @@ static const match_table_t opt_tokens = {
{ NVMF_OPT_DATA_DIGEST, "data_digest" },
{ NVMF_OPT_NR_WRITE_QUEUES, "nr_write_queues=%d" },
{ NVMF_OPT_NR_POLL_QUEUES, "nr_poll_queues=%d" },
+ { NVMF_OPT_TOS, "tos=%d" },
{ NVMF_OPT_ERR, NULL }
};
@@ -632,6 +633,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
opts->duplicate_connect = false;
opts->hdr_digest = false;
opts->data_digest = false;
+ opts->tos = -1; /* < 0 == use transport default */
options = o = kstrdup(buf, GFP_KERNEL);
if (!options)
@@ -738,13 +740,6 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
pr_warn("keep_alive_tmo 0 won't execute keep alives!!!\n");
}
opts->kato = token;
-
- if (opts->discovery_nqn && opts->kato) {
- pr_err("Discovery controllers cannot accept KATO != 0\n");
- ret = -EINVAL;
- goto out;
- }
-
break;
case NVMF_OPT_CTRL_LOSS_TMO:
if (match_int(args, &token)) {
@@ -856,6 +851,22 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
}
opts->nr_poll_queues = token;
break;
+ case NVMF_OPT_TOS:
+ if (match_int(args, &token)) {
+ ret = -EINVAL;
+ goto out;
+ }
+ if (token < 0) {
+ pr_err("Invalid type of service %d\n", token);
+ ret = -EINVAL;
+ goto out;
+ }
+ if (token > 255) {
+ pr_warn("Clamping type of service to 255\n");
+ token = 255;
+ }
+ opts->tos = token;
+ break;
default:
pr_warn("unknown parameter or missing value '%s' in ctrl creation request\n",
p);
@@ -865,7 +876,6 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
}
if (opts->discovery_nqn) {
- opts->kato = 0;
opts->nr_io_queues = 0;
opts->nr_write_queues = 0;
opts->nr_poll_queues = 0;
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index 3044d8b99a24..93f08d77c896 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -55,6 +55,7 @@ enum {
NVMF_OPT_DATA_DIGEST = 1 << 16,
NVMF_OPT_NR_WRITE_QUEUES = 1 << 17,
NVMF_OPT_NR_POLL_QUEUES = 1 << 18,
+ NVMF_OPT_TOS = 1 << 19,
};
/**
@@ -87,6 +88,7 @@ enum {
* @data_digest: generate/verify data digest (TCP)
* @nr_write_queues: number of queues for write I/O
* @nr_poll_queues: number of queues for polling I/O
+ * @tos: type of service
*/
struct nvmf_ctrl_options {
unsigned mask;
@@ -108,6 +110,7 @@ struct nvmf_ctrl_options {
bool data_digest;
unsigned int nr_write_queues;
unsigned int nr_poll_queues;
+ int tos;
};
/*
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 232d8094091b..265f89e11d8b 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -1608,9 +1608,13 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
sizeof(op->rsp_iu), DMA_FROM_DEVICE);
if (opstate == FCPOP_STATE_ABORTED)
- status = cpu_to_le16(NVME_SC_ABORT_REQ << 1);
- else if (freq->status)
- status = cpu_to_le16(NVME_SC_INTERNAL << 1);
+ status = cpu_to_le16(NVME_SC_HOST_PATH_ERROR << 1);
+ else if (freq->status) {
+ status = cpu_to_le16(NVME_SC_HOST_PATH_ERROR << 1);
+ dev_info(ctrl->ctrl.device,
+ "NVME-FC{%d}: io failed due to lldd error %d\n",
+ ctrl->cnum, freq->status);
+ }
/*
* For the linux implementation, if we have an unsuccesful
@@ -1637,8 +1641,13 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
* no payload in the CQE by the transport.
*/
if (freq->transferred_length !=
- be32_to_cpu(op->cmd_iu.data_len)) {
- status = cpu_to_le16(NVME_SC_INTERNAL << 1);
+ be32_to_cpu(op->cmd_iu.data_len)) {
+ status = cpu_to_le16(NVME_SC_HOST_PATH_ERROR << 1);
+ dev_info(ctrl->ctrl.device,
+ "NVME-FC{%d}: io failed due to bad transfer "
+ "length: %d vs expected %d\n",
+ ctrl->cnum, freq->transferred_length,
+ be32_to_cpu(op->cmd_iu.data_len));
goto done;
}
result.u64 = 0;
@@ -1655,7 +1664,17 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
freq->transferred_length ||
op->rsp_iu.status_code ||
sqe->common.command_id != cqe->command_id)) {
- status = cpu_to_le16(NVME_SC_INTERNAL << 1);
+ status = cpu_to_le16(NVME_SC_HOST_PATH_ERROR << 1);
+ dev_info(ctrl->ctrl.device,
+ "NVME-FC{%d}: io failed due to bad NVMe_ERSP: "
+ "iu len %d, xfr len %d vs %d, status code "
+ "%d, cmdid %d vs %d\n",
+ ctrl->cnum, be16_to_cpu(op->rsp_iu.iu_len),
+ be32_to_cpu(op->rsp_iu.xfrd_len),
+ freq->transferred_length,
+ op->rsp_iu.status_code,
+ sqe->common.command_id,
+ cqe->command_id);
goto done;
}
result = cqe->result;
@@ -1663,7 +1682,11 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
break;
default:
- status = cpu_to_le16(NVME_SC_INTERNAL << 1);
+ status = cpu_to_le16(NVME_SC_HOST_PATH_ERROR << 1);
+ dev_info(ctrl->ctrl.device,
+ "NVME-FC{%d}: io failed due to odd NVMe_xRSP iu "
+ "len %d\n",
+ ctrl->cnum, freq->rcv_rsplen);
goto done;
}
@@ -2006,6 +2029,7 @@ nvme_fc_ctrl_free(struct kref *ref)
blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
blk_cleanup_queue(ctrl->ctrl.admin_q);
+ blk_cleanup_queue(ctrl->ctrl.fabrics_q);
blk_mq_free_tag_set(&ctrl->admin_tag_set);
kfree(ctrl->queues);
@@ -2107,7 +2131,6 @@ nvme_fc_map_data(struct nvme_fc_ctrl *ctrl, struct request *rq,
struct nvme_fc_fcp_op *op)
{
struct nvmefc_fcp_req *freq = &op->fcp_req;
- enum dma_data_direction dir;
int ret;
freq->sg_cnt = 0;
@@ -2124,9 +2147,8 @@ nvme_fc_map_data(struct nvme_fc_ctrl *ctrl, struct request *rq,
op->nents = blk_rq_map_sg(rq->q, rq, freq->sg_table.sgl);
WARN_ON(op->nents > blk_rq_nr_phys_segments(rq));
- dir = (rq_data_dir(rq) == WRITE) ? DMA_TO_DEVICE : DMA_FROM_DEVICE;
freq->sg_cnt = fc_dma_map_sg(ctrl->lport->dev, freq->sg_table.sgl,
- op->nents, dir);
+ op->nents, rq_dma_dir(rq));
if (unlikely(freq->sg_cnt <= 0)) {
sg_free_table_chained(&freq->sg_table, SG_CHUNK_SIZE);
freq->sg_cnt = 0;
@@ -2149,8 +2171,7 @@ nvme_fc_unmap_data(struct nvme_fc_ctrl *ctrl, struct request *rq,
return;
fc_dma_unmap_sg(ctrl->lport->dev, freq->sg_table.sgl, op->nents,
- ((rq_data_dir(rq) == WRITE) ?
- DMA_TO_DEVICE : DMA_FROM_DEVICE));
+ rq_dma_dir(rq));
nvme_cleanup_cmd(rq);
@@ -2633,8 +2654,6 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
if (ret)
goto out_delete_hw_queue;
- blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
-
ret = nvmf_connect_admin_queue(&ctrl->ctrl);
if (ret)
goto out_disconnect_admin_queue;
@@ -2648,23 +2667,15 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
* prior connection values
*/
- ret = nvmf_reg_read64(&ctrl->ctrl, NVME_REG_CAP, &ctrl->ctrl.cap);
- if (ret) {
- dev_err(ctrl->ctrl.device,
- "prop_get NVME_REG_CAP failed\n");
- goto out_disconnect_admin_queue;
- }
-
- ctrl->ctrl.sqsize =
- min_t(int, NVME_CAP_MQES(ctrl->ctrl.cap), ctrl->ctrl.sqsize);
-
- ret = nvme_enable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap);
+ ret = nvme_enable_ctrl(&ctrl->ctrl);
if (ret)
goto out_disconnect_admin_queue;
ctrl->ctrl.max_hw_sectors =
(ctrl->lport->ops->max_sgl_segments - 1) << (PAGE_SHIFT - 9);
+ blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+
ret = nvme_init_identify(&ctrl->ctrl);
if (ret)
goto out_disconnect_admin_queue;
@@ -2774,6 +2785,7 @@ nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl)
nvme_stop_queues(&ctrl->ctrl);
blk_mq_tagset_busy_iter(&ctrl->tag_set,
nvme_fc_terminate_exchange, &ctrl->ctrl);
+ blk_mq_tagset_wait_completed_request(&ctrl->tag_set);
}
/*
@@ -2796,6 +2808,7 @@ nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl)
blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
nvme_fc_terminate_exchange, &ctrl->ctrl);
+ blk_mq_tagset_wait_completed_request(&ctrl->admin_tag_set);
/* kill the aens as they are a separate path */
nvme_fc_abort_aen_ops(ctrl);
@@ -3109,10 +3122,16 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
goto out_free_queues;
ctrl->ctrl.admin_tagset = &ctrl->admin_tag_set;
+ ctrl->ctrl.fabrics_q = blk_mq_init_queue(&ctrl->admin_tag_set);
+ if (IS_ERR(ctrl->ctrl.fabrics_q)) {
+ ret = PTR_ERR(ctrl->ctrl.fabrics_q);
+ goto out_free_admin_tag_set;
+ }
+
ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set);
if (IS_ERR(ctrl->ctrl.admin_q)) {
ret = PTR_ERR(ctrl->ctrl.admin_q);
- goto out_free_admin_tag_set;
+ goto out_cleanup_fabrics_q;
}
/*
@@ -3184,6 +3203,8 @@ fail_ctrl:
out_cleanup_admin_q:
blk_cleanup_queue(ctrl->ctrl.admin_q);
+out_cleanup_fabrics_q:
+ blk_cleanup_queue(ctrl->ctrl.fabrics_q);
out_free_admin_tag_set:
blk_mq_free_tag_set(&ctrl->admin_tag_set);
out_free_queues:
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index ba009d4c9dfa..ec46693f6b64 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -667,11 +667,14 @@ static struct request *nvme_nvm_alloc_request(struct request_queue *q,
return rq;
}
-static int nvme_nvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
+static int nvme_nvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd,
+ void *buf)
{
+ struct nvm_geo *geo = &dev->geo;
struct request_queue *q = dev->q;
struct nvme_nvm_command *cmd;
struct request *rq;
+ int ret;
cmd = kzalloc(sizeof(struct nvme_nvm_command), GFP_KERNEL);
if (!cmd)
@@ -679,8 +682,15 @@ static int nvme_nvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
rq = nvme_nvm_alloc_request(q, rqd, cmd);
if (IS_ERR(rq)) {
- kfree(cmd);
- return PTR_ERR(rq);
+ ret = PTR_ERR(rq);
+ goto err_free_cmd;
+ }
+
+ if (buf) {
+ ret = blk_rq_map_kern(q, rq, buf, geo->csecs * rqd->nr_ppas,
+ GFP_KERNEL);
+ if (ret)
+ goto err_free_cmd;
}
rq->end_io_data = rqd;
@@ -688,33 +698,9 @@ static int nvme_nvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
blk_execute_rq_nowait(q, NULL, rq, 0, nvme_nvm_end_io);
return 0;
-}
-
-static int nvme_nvm_submit_io_sync(struct nvm_dev *dev, struct nvm_rq *rqd)
-{
- struct request_queue *q = dev->q;
- struct request *rq;
- struct nvme_nvm_command cmd;
- int ret = 0;
-
- memset(&cmd, 0, sizeof(struct nvme_nvm_command));
-
- rq = nvme_nvm_alloc_request(q, rqd, &cmd);
- if (IS_ERR(rq))
- return PTR_ERR(rq);
-
- /* I/Os can fail and the error is signaled through rqd. Callers must
- * handle the error accordingly.
- */
- blk_execute_rq(q, NULL, rq, 0);
- if (nvme_req(rq)->flags & NVME_REQ_CANCELLED)
- ret = -EINTR;
-
- rqd->ppa_status = le64_to_cpu(nvme_req(rq)->result.u64);
- rqd->error = nvme_req(rq)->status;
-
- blk_mq_free_request(rq);
+err_free_cmd:
+ kfree(cmd);
return ret;
}
@@ -754,7 +740,6 @@ static struct nvm_dev_ops nvme_nvm_dev_ops = {
.get_chk_meta = nvme_nvm_get_chk_meta,
.submit_io = nvme_nvm_submit_io,
- .submit_io_sync = nvme_nvm_submit_io_sync,
.create_dma_pool = nvme_nvm_create_dma_pool,
.destroy_dma_pool = nvme_nvm_destroy_dma_pool,
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index af831d3d15d0..30de7efef003 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -509,14 +509,16 @@ static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
down_write(&ctrl->namespaces_rwsem);
list_for_each_entry(ns, &ctrl->namespaces, list) {
- if (ns->head->ns_id != le32_to_cpu(desc->nsids[n]))
+ unsigned nsid = le32_to_cpu(desc->nsids[n]);
+
+ if (ns->head->ns_id < nsid)
continue;
- nvme_update_ns_ana_state(desc, ns);
+ if (ns->head->ns_id == nsid)
+ nvme_update_ns_ana_state(desc, ns);
if (++n == nr_nsids)
break;
}
up_write(&ctrl->namespaces_rwsem);
- WARN_ON_ONCE(n < nr_nsids);
return 0;
}
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 2d678fb968c7..b5013c101b35 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -16,6 +16,8 @@
#include <linux/fault-inject.h>
#include <linux/rcupdate.h>
+#include <trace/events/block.h>
+
extern unsigned int nvme_io_timeout;
#define NVME_IO_TIMEOUT (nvme_io_timeout * HZ)
@@ -97,6 +99,21 @@ enum nvme_quirks {
* Force simple suspend/resume path.
*/
NVME_QUIRK_SIMPLE_SUSPEND = (1 << 10),
+
+ /*
+ * Use only one interrupt vector for all queues
+ */
+ NVME_QUIRK_SINGLE_VECTOR = (1 << 11),
+
+ /*
+ * Use non-standard 128 bytes SQEs.
+ */
+ NVME_QUIRK_128_BYTES_SQES = (1 << 12),
+
+ /*
+ * Prevent tag overlap between queues
+ */
+ NVME_QUIRK_SHARED_TAGS = (1 << 13),
};
/*
@@ -169,6 +186,7 @@ struct nvme_ctrl {
const struct nvme_ctrl_ops *ops;
struct request_queue *admin_q;
struct request_queue *connect_q;
+ struct request_queue *fabrics_q;
struct device *dev;
int instance;
int numa_node;
@@ -431,8 +449,8 @@ void nvme_complete_rq(struct request *req);
bool nvme_cancel_request(struct request *req, void *data, bool reserved);
bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
enum nvme_ctrl_state new_state);
-int nvme_disable_ctrl(struct nvme_ctrl *ctrl, u64 cap);
-int nvme_enable_ctrl(struct nvme_ctrl *ctrl, u64 cap);
+int nvme_disable_ctrl(struct nvme_ctrl *ctrl);
+int nvme_enable_ctrl(struct nvme_ctrl *ctrl);
int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl);
int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
const struct nvme_ctrl_ops *ops, unsigned long quirks);
@@ -520,6 +538,16 @@ static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
kblockd_schedule_work(&head->requeue_work);
}
+static inline void nvme_trace_bio_complete(struct request *req,
+ blk_status_t status)
+{
+ struct nvme_ns *ns = req->q->queuedata;
+
+ if (req->cmd_flags & REQ_NVME_MPATH)
+ trace_block_bio_complete(ns->head->disk->queue,
+ req->bio, status);
+}
+
extern struct device_attribute dev_attr_ana_grpid;
extern struct device_attribute dev_attr_ana_state;
extern struct device_attribute subsys_attr_iopolicy;
@@ -567,6 +595,10 @@ static inline void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
{
}
+static inline void nvme_trace_bio_complete(struct request *req,
+ blk_status_t status)
+{
+}
static inline int nvme_mpath_init(struct nvme_ctrl *ctrl,
struct nvme_id_ctrl *id)
{
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 732d5b63ec05..6b4d7b064b38 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -28,8 +28,8 @@
#include "trace.h"
#include "nvme.h"
-#define SQ_SIZE(depth) (depth * sizeof(struct nvme_command))
-#define CQ_SIZE(depth) (depth * sizeof(struct nvme_completion))
+#define SQ_SIZE(q) ((q)->q_depth << (q)->sqes)
+#define CQ_SIZE(q) ((q)->q_depth * sizeof(struct nvme_completion))
#define SGES_PER_PAGE (PAGE_SIZE / sizeof(struct nvme_sgl_desc))
@@ -100,6 +100,7 @@ struct nvme_dev {
unsigned io_queues[HCTX_MAX_TYPES];
unsigned int num_vecs;
int q_depth;
+ int io_sqes;
u32 db_stride;
void __iomem *bar;
unsigned long bar_mapped_size;
@@ -162,7 +163,7 @@ static inline struct nvme_dev *to_nvme_dev(struct nvme_ctrl *ctrl)
struct nvme_queue {
struct nvme_dev *dev;
spinlock_t sq_lock;
- struct nvme_command *sq_cmds;
+ void *sq_cmds;
/* only used for poll queues: */
spinlock_t cq_poll_lock ____cacheline_aligned_in_smp;
volatile struct nvme_completion *cqes;
@@ -178,6 +179,7 @@ struct nvme_queue {
u16 last_cq_head;
u16 qid;
u8 cq_phase;
+ u8 sqes;
unsigned long flags;
#define NVMEQ_ENABLED 0
#define NVMEQ_SQ_CMB 1
@@ -488,7 +490,8 @@ static void nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd,
bool write_sq)
{
spin_lock(&nvmeq->sq_lock);
- memcpy(&nvmeq->sq_cmds[nvmeq->sq_tail], cmd, sizeof(*cmd));
+ memcpy(nvmeq->sq_cmds + (nvmeq->sq_tail << nvmeq->sqes),
+ cmd, sizeof(*cmd));
if (++nvmeq->sq_tail == nvmeq->q_depth)
nvmeq->sq_tail = 0;
nvme_write_sq_db(nvmeq, write_sq);
@@ -534,14 +537,13 @@ static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req)
static void nvme_unmap_data(struct nvme_dev *dev, struct request *req)
{
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
- enum dma_data_direction dma_dir = rq_data_dir(req) ?
- DMA_TO_DEVICE : DMA_FROM_DEVICE;
const int last_prp = dev->ctrl.page_size / sizeof(__le64) - 1;
dma_addr_t dma_addr = iod->first_dma, next_dma_addr;
int i;
if (iod->dma_len) {
- dma_unmap_page(dev->dev, dma_addr, iod->dma_len, dma_dir);
+ dma_unmap_page(dev->dev, dma_addr, iod->dma_len,
+ rq_dma_dir(req));
return;
}
@@ -1344,16 +1346,16 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
static void nvme_free_queue(struct nvme_queue *nvmeq)
{
- dma_free_coherent(nvmeq->dev->dev, CQ_SIZE(nvmeq->q_depth),
+ dma_free_coherent(nvmeq->dev->dev, CQ_SIZE(nvmeq),
(void *)nvmeq->cqes, nvmeq->cq_dma_addr);
if (!nvmeq->sq_cmds)
return;
if (test_and_clear_bit(NVMEQ_SQ_CMB, &nvmeq->flags)) {
pci_free_p2pmem(to_pci_dev(nvmeq->dev->dev),
- nvmeq->sq_cmds, SQ_SIZE(nvmeq->q_depth));
+ nvmeq->sq_cmds, SQ_SIZE(nvmeq));
} else {
- dma_free_coherent(nvmeq->dev->dev, SQ_SIZE(nvmeq->q_depth),
+ dma_free_coherent(nvmeq->dev->dev, SQ_SIZE(nvmeq),
nvmeq->sq_cmds, nvmeq->sq_dma_addr);
}
}
@@ -1403,7 +1405,7 @@ static void nvme_disable_admin_queue(struct nvme_dev *dev, bool shutdown)
if (shutdown)
nvme_shutdown_ctrl(&dev->ctrl);
else
- nvme_disable_ctrl(&dev->ctrl, dev->ctrl.cap);
+ nvme_disable_ctrl(&dev->ctrl);
nvme_poll_irqdisable(nvmeq, -1);
}
@@ -1433,12 +1435,12 @@ static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues,
}
static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct nvme_queue *nvmeq,
- int qid, int depth)
+ int qid)
{
struct pci_dev *pdev = to_pci_dev(dev->dev);
if (qid && dev->cmb_use_sqes && (dev->cmbsz & NVME_CMBSZ_SQS)) {
- nvmeq->sq_cmds = pci_alloc_p2pmem(pdev, SQ_SIZE(depth));
+ nvmeq->sq_cmds = pci_alloc_p2pmem(pdev, SQ_SIZE(nvmeq));
if (nvmeq->sq_cmds) {
nvmeq->sq_dma_addr = pci_p2pmem_virt_to_bus(pdev,
nvmeq->sq_cmds);
@@ -1447,11 +1449,11 @@ static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct nvme_queue *nvmeq,
return 0;
}
- pci_free_p2pmem(pdev, nvmeq->sq_cmds, SQ_SIZE(depth));
+ pci_free_p2pmem(pdev, nvmeq->sq_cmds, SQ_SIZE(nvmeq));
}
}
- nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth),
+ nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(nvmeq),
&nvmeq->sq_dma_addr, GFP_KERNEL);
if (!nvmeq->sq_cmds)
return -ENOMEM;
@@ -1465,12 +1467,14 @@ static int nvme_alloc_queue(struct nvme_dev *dev, int qid, int depth)
if (dev->ctrl.queue_count > qid)
return 0;
- nvmeq->cqes = dma_alloc_coherent(dev->dev, CQ_SIZE(depth),
+ nvmeq->sqes = qid ? dev->io_sqes : NVME_ADM_SQES;
+ nvmeq->q_depth = depth;
+ nvmeq->cqes = dma_alloc_coherent(dev->dev, CQ_SIZE(nvmeq),
&nvmeq->cq_dma_addr, GFP_KERNEL);
if (!nvmeq->cqes)
goto free_nvmeq;
- if (nvme_alloc_sq_cmds(dev, nvmeq, qid, depth))
+ if (nvme_alloc_sq_cmds(dev, nvmeq, qid))
goto free_cqdma;
nvmeq->dev = dev;
@@ -1479,15 +1483,14 @@ static int nvme_alloc_queue(struct nvme_dev *dev, int qid, int depth)
nvmeq->cq_head = 0;
nvmeq->cq_phase = 1;
nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
- nvmeq->q_depth = depth;
nvmeq->qid = qid;
dev->ctrl.queue_count++;
return 0;
free_cqdma:
- dma_free_coherent(dev->dev, CQ_SIZE(depth), (void *)nvmeq->cqes,
- nvmeq->cq_dma_addr);
+ dma_free_coherent(dev->dev, CQ_SIZE(nvmeq), (void *)nvmeq->cqes,
+ nvmeq->cq_dma_addr);
free_nvmeq:
return -ENOMEM;
}
@@ -1515,7 +1518,7 @@ static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
nvmeq->cq_head = 0;
nvmeq->cq_phase = 1;
nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
- memset((void *)nvmeq->cqes, 0, CQ_SIZE(nvmeq->q_depth));
+ memset((void *)nvmeq->cqes, 0, CQ_SIZE(nvmeq));
nvme_dbbuf_init(dev, nvmeq, qid);
dev->online_queues++;
wmb(); /* ensure the first interrupt sees the initialization */
@@ -1552,7 +1555,6 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid, bool polled)
nvme_init_queue(nvmeq, qid);
if (!polled) {
- nvmeq->cq_vector = vector;
result = queue_request_irq(nvmeq);
if (result < 0)
goto release_sq;
@@ -1679,7 +1681,7 @@ static int nvme_pci_configure_admin_queue(struct nvme_dev *dev)
(readl(dev->bar + NVME_REG_CSTS) & NVME_CSTS_NSSRO))
writel(NVME_CSTS_NSSRO, dev->bar + NVME_REG_CSTS);
- result = nvme_disable_ctrl(&dev->ctrl, dev->ctrl.cap);
+ result = nvme_disable_ctrl(&dev->ctrl);
if (result < 0)
return result;
@@ -1695,7 +1697,7 @@ static int nvme_pci_configure_admin_queue(struct nvme_dev *dev)
lo_hi_writeq(nvmeq->sq_dma_addr, dev->bar + NVME_REG_ASQ);
lo_hi_writeq(nvmeq->cq_dma_addr, dev->bar + NVME_REG_ACQ);
- result = nvme_enable_ctrl(&dev->ctrl, dev->ctrl.cap);
+ result = nvme_enable_ctrl(&dev->ctrl);
if (result)
return result;
@@ -2077,6 +2079,13 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
dev->io_queues[HCTX_TYPE_DEFAULT] = 1;
dev->io_queues[HCTX_TYPE_READ] = 0;
+ /*
+ * Some Apple controllers require all queues to use the
+ * first vector.
+ */
+ if (dev->ctrl.quirks & NVME_QUIRK_SINGLE_VECTOR)
+ irq_queues = 1;
+
return pci_alloc_irq_vectors_affinity(pdev, 1, irq_queues,
PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd);
}
@@ -2095,6 +2104,14 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
unsigned long size;
nr_io_queues = max_io_queues();
+
+ /*
+ * If tags are shared with admin queue (Apple bug), then
+ * make sure we only use one IO queue.
+ */
+ if (dev->ctrl.quirks & NVME_QUIRK_SHARED_TAGS)
+ nr_io_queues = 1;
+
result = nvme_set_queue_count(&dev->ctrl, &nr_io_queues);
if (result < 0)
return result;
@@ -2265,6 +2282,14 @@ static int nvme_dev_add(struct nvme_dev *dev)
dev->tagset.flags = BLK_MQ_F_SHOULD_MERGE;
dev->tagset.driver_data = dev;
+ /*
+ * Some Apple controllers requires tags to be unique
+ * across admin and IO queue, so reserve the first 32
+ * tags of the IO queue.
+ */
+ if (dev->ctrl.quirks & NVME_QUIRK_SHARED_TAGS)
+ dev->tagset.reserved_tags = NVME_AQ_DEPTH;
+
ret = blk_mq_alloc_tag_set(&dev->tagset);
if (ret) {
dev_warn(dev->ctrl.device,
@@ -2314,10 +2339,21 @@ static int nvme_pci_enable(struct nvme_dev *dev)
dev->q_depth = min_t(int, NVME_CAP_MQES(dev->ctrl.cap) + 1,
io_queue_depth);
+ dev->ctrl.sqsize = dev->q_depth - 1; /* 0's based queue depth */
dev->db_stride = 1 << NVME_CAP_STRIDE(dev->ctrl.cap);
dev->dbs = dev->bar + 4096;
/*
+ * Some Apple controllers require a non-standard SQE size.
+ * Interestingly they also seem to ignore the CC:IOSQES register
+ * so we don't bother updating it here.
+ */
+ if (dev->ctrl.quirks & NVME_QUIRK_128_BYTES_SQES)
+ dev->io_sqes = 7;
+ else
+ dev->io_sqes = NVME_NVM_IOSQES;
+
+ /*
* Temporary fix for the Apple controller found in the MacBook8,1 and
* some MacBook7,1 to avoid controller resets and data loss.
*/
@@ -2334,6 +2370,18 @@ static int nvme_pci_enable(struct nvme_dev *dev)
"set queue depth=%u\n", dev->q_depth);
}
+ /*
+ * Controllers with the shared tags quirk need the IO queue to be
+ * big enough so that we get 32 tags for the admin queue
+ */
+ if ((dev->ctrl.quirks & NVME_QUIRK_SHARED_TAGS) &&
+ (dev->q_depth < (NVME_AQ_DEPTH + 2))) {
+ dev->q_depth = NVME_AQ_DEPTH + 2;
+ dev_warn(dev->ctrl.device, "IO queue depth clamped to %d\n",
+ dev->q_depth);
+ }
+
+
nvme_map_cmb(dev);
pci_enable_pcie_error_reporting(pdev);
@@ -2401,6 +2449,8 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
blk_mq_tagset_busy_iter(&dev->tagset, nvme_cancel_request, &dev->ctrl);
blk_mq_tagset_busy_iter(&dev->admin_tagset, nvme_cancel_request, &dev->ctrl);
+ blk_mq_tagset_wait_completed_request(&dev->tagset);
+ blk_mq_tagset_wait_completed_request(&dev->admin_tagset);
/*
* The driver will not be starting up queues again if shutting down so
@@ -3041,6 +3091,10 @@ static const struct pci_device_id nvme_id_table[] = {
{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) },
{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },
+ { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2005),
+ .driver_data = NVME_QUIRK_SINGLE_VECTOR |
+ NVME_QUIRK_128_BYTES_SQES |
+ NVME_QUIRK_SHARED_TAGS },
{ 0, }
};
MODULE_DEVICE_TABLE(pci, nvme_id_table);
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 1a6449bc547b..dfa07bb9dfeb 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -757,6 +757,7 @@ static void nvme_rdma_destroy_admin_queue(struct nvme_rdma_ctrl *ctrl,
{
if (remove) {
blk_cleanup_queue(ctrl->ctrl.admin_q);
+ blk_cleanup_queue(ctrl->ctrl.fabrics_q);
blk_mq_free_tag_set(ctrl->ctrl.admin_tagset);
}
if (ctrl->async_event_sqe.data) {
@@ -798,10 +799,16 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
goto out_free_async_qe;
}
+ ctrl->ctrl.fabrics_q = blk_mq_init_queue(&ctrl->admin_tag_set);
+ if (IS_ERR(ctrl->ctrl.fabrics_q)) {
+ error = PTR_ERR(ctrl->ctrl.fabrics_q);
+ goto out_free_tagset;
+ }
+
ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set);
if (IS_ERR(ctrl->ctrl.admin_q)) {
error = PTR_ERR(ctrl->ctrl.admin_q);
- goto out_free_tagset;
+ goto out_cleanup_fabrics_q;
}
}
@@ -809,24 +816,15 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
if (error)
goto out_cleanup_queue;
- error = ctrl->ctrl.ops->reg_read64(&ctrl->ctrl, NVME_REG_CAP,
- &ctrl->ctrl.cap);
- if (error) {
- dev_err(ctrl->ctrl.device,
- "prop_get NVME_REG_CAP failed\n");
- goto out_stop_queue;
- }
-
- ctrl->ctrl.sqsize =
- min_t(int, NVME_CAP_MQES(ctrl->ctrl.cap), ctrl->ctrl.sqsize);
-
- error = nvme_enable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap);
+ error = nvme_enable_ctrl(&ctrl->ctrl);
if (error)
goto out_stop_queue;
ctrl->ctrl.max_hw_sectors =
(ctrl->max_fr_pages - 1) << (ilog2(SZ_4K) - 9);
+ blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+
error = nvme_init_identify(&ctrl->ctrl);
if (error)
goto out_stop_queue;
@@ -838,6 +836,9 @@ out_stop_queue:
out_cleanup_queue:
if (new)
blk_cleanup_queue(ctrl->ctrl.admin_q);
+out_cleanup_fabrics_q:
+ if (new)
+ blk_cleanup_queue(ctrl->ctrl.fabrics_q);
out_free_tagset:
if (new)
blk_mq_free_tag_set(ctrl->ctrl.admin_tagset);
@@ -907,10 +908,13 @@ static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,
{
blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
nvme_rdma_stop_queue(&ctrl->queues[0]);
- if (ctrl->ctrl.admin_tagset)
+ if (ctrl->ctrl.admin_tagset) {
blk_mq_tagset_busy_iter(ctrl->ctrl.admin_tagset,
nvme_cancel_request, &ctrl->ctrl);
- blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+ blk_mq_tagset_wait_completed_request(ctrl->ctrl.admin_tagset);
+ }
+ if (remove)
+ blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
nvme_rdma_destroy_admin_queue(ctrl, remove);
}
@@ -920,9 +924,11 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
if (ctrl->ctrl.queue_count > 1) {
nvme_stop_queues(&ctrl->ctrl);
nvme_rdma_stop_io_queues(ctrl);
- if (ctrl->ctrl.tagset)
+ if (ctrl->ctrl.tagset) {
blk_mq_tagset_busy_iter(ctrl->ctrl.tagset,
nvme_cancel_request, &ctrl->ctrl);
+ blk_mq_tagset_wait_completed_request(ctrl->ctrl.tagset);
+ }
if (remove)
nvme_start_queues(&ctrl->ctrl);
nvme_rdma_destroy_io_queues(ctrl, remove);
@@ -1059,6 +1065,7 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
nvme_rdma_teardown_io_queues(ctrl, false);
nvme_start_queues(&ctrl->ctrl);
nvme_rdma_teardown_admin_queue(ctrl, false);
+ blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
/* state change failure is ok if we're in DELETING state */
@@ -1145,9 +1152,7 @@ static void nvme_rdma_unmap_data(struct nvme_rdma_queue *queue,
req->mr = NULL;
}
- ib_dma_unmap_sg(ibdev, req->sg_table.sgl,
- req->nents, rq_data_dir(rq) ==
- WRITE ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
+ ib_dma_unmap_sg(ibdev, req->sg_table.sgl, req->nents, rq_dma_dir(rq));
nvme_cleanup_cmd(rq);
sg_free_table_chained(&req->sg_table, SG_CHUNK_SIZE);
@@ -1273,7 +1278,7 @@ static int nvme_rdma_map_data(struct nvme_rdma_queue *queue,
req->nents = blk_rq_map_sg(rq->q, rq, req->sg_table.sgl);
count = ib_dma_map_sg(ibdev, req->sg_table.sgl, req->nents,
- rq_data_dir(rq) == WRITE ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
+ rq_dma_dir(rq));
if (unlikely(count <= 0)) {
ret = -EIO;
goto out_free_table;
@@ -1302,9 +1307,7 @@ out:
return 0;
out_unmap_sg:
- ib_dma_unmap_sg(ibdev, req->sg_table.sgl,
- req->nents, rq_data_dir(rq) ==
- WRITE ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
+ ib_dma_unmap_sg(ibdev, req->sg_table.sgl, req->nents, rq_dma_dir(rq));
out_free_table:
sg_free_table_chained(&req->sg_table, SG_CHUNK_SIZE);
return ret;
@@ -1547,16 +1550,18 @@ static int nvme_rdma_conn_rejected(struct nvme_rdma_queue *queue,
static int nvme_rdma_addr_resolved(struct nvme_rdma_queue *queue)
{
+ struct nvme_ctrl *ctrl = &queue->ctrl->ctrl;
int ret;
ret = nvme_rdma_create_queue_ib(queue);
if (ret)
return ret;
+ if (ctrl->opts->tos >= 0)
+ rdma_set_service_type(queue->cm_id, ctrl->opts->tos);
ret = rdma_resolve_route(queue->cm_id, NVME_RDMA_CONNECT_TIMEOUT_MS);
if (ret) {
- dev_err(queue->ctrl->ctrl.device,
- "rdma_resolve_route failed (%d).\n",
+ dev_err(ctrl->device, "rdma_resolve_route failed (%d).\n",
queue->cm_error);
goto out_destroy_queue;
}
@@ -1869,10 +1874,11 @@ static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown)
cancel_delayed_work_sync(&ctrl->reconnect_work);
nvme_rdma_teardown_io_queues(ctrl, shutdown);
+ blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
if (shutdown)
nvme_shutdown_ctrl(&ctrl->ctrl);
else
- nvme_disable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap);
+ nvme_disable_ctrl(&ctrl->ctrl);
nvme_rdma_teardown_admin_queue(ctrl, shutdown);
}
@@ -2051,7 +2057,8 @@ static struct nvmf_transport_ops nvme_rdma_transport = {
.required_opts = NVMF_OPT_TRADDR,
.allowed_opts = NVMF_OPT_TRSVCID | NVMF_OPT_RECONNECT_DELAY |
NVMF_OPT_HOST_TRADDR | NVMF_OPT_CTRL_LOSS_TMO |
- NVMF_OPT_NR_WRITE_QUEUES | NVMF_OPT_NR_POLL_QUEUES,
+ NVMF_OPT_NR_WRITE_QUEUES | NVMF_OPT_NR_POLL_QUEUES |
+ NVMF_OPT_TOS,
.create_ctrl = nvme_rdma_create_ctrl,
};
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 606b13d35d16..4ffd5957637a 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -13,6 +13,7 @@
#include <net/tcp.h>
#include <linux/blk-mq.h>
#include <crypto/hash.h>
+#include <net/busy_poll.h>
#include "nvme.h"
#include "fabrics.h"
@@ -72,6 +73,7 @@ struct nvme_tcp_queue {
int pdu_offset;
size_t data_remaining;
size_t ddgst_remaining;
+ unsigned int nr_cqe;
/* send state */
struct nvme_tcp_request *request;
@@ -438,6 +440,7 @@ static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue,
}
nvme_end_request(rq, cqe->status, cqe->result);
+ queue->nr_cqe++;
return 0;
}
@@ -608,23 +611,18 @@ static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
switch (hdr->type) {
case nvme_tcp_c2h_data:
- ret = nvme_tcp_handle_c2h_data(queue, (void *)queue->pdu);
- break;
+ return nvme_tcp_handle_c2h_data(queue, (void *)queue->pdu);
case nvme_tcp_rsp:
nvme_tcp_init_recv_ctx(queue);
- ret = nvme_tcp_handle_comp(queue, (void *)queue->pdu);
- break;
+ return nvme_tcp_handle_comp(queue, (void *)queue->pdu);
case nvme_tcp_r2t:
nvme_tcp_init_recv_ctx(queue);
- ret = nvme_tcp_handle_r2t(queue, (void *)queue->pdu);
- break;
+ return nvme_tcp_handle_r2t(queue, (void *)queue->pdu);
default:
dev_err(queue->ctrl->ctrl.device,
"unsupported pdu type (%d)\n", hdr->type);
return -EINVAL;
}
-
- return ret;
}
static inline void nvme_tcp_end_request(struct request *rq, u16 status)
@@ -701,8 +699,10 @@ static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb,
nvme_tcp_ddgst_final(queue->rcv_hash, &queue->exp_ddgst);
queue->ddgst_remaining = NVME_TCP_DIGEST_LENGTH;
} else {
- if (pdu->hdr.flags & NVME_TCP_F_DATA_SUCCESS)
+ if (pdu->hdr.flags & NVME_TCP_F_DATA_SUCCESS) {
nvme_tcp_end_request(rq, NVME_SC_SUCCESS);
+ queue->nr_cqe++;
+ }
nvme_tcp_init_recv_ctx(queue);
}
}
@@ -742,6 +742,7 @@ static int nvme_tcp_recv_ddgst(struct nvme_tcp_queue *queue,
pdu->command_id);
nvme_tcp_end_request(rq, NVME_SC_SUCCESS);
+ queue->nr_cqe++;
}
nvme_tcp_init_recv_ctx(queue);
@@ -841,7 +842,7 @@ static inline void nvme_tcp_done_send_req(struct nvme_tcp_queue *queue)
static void nvme_tcp_fail_request(struct nvme_tcp_request *req)
{
- nvme_tcp_end_request(blk_mq_rq_from_pdu(req), NVME_SC_DATA_XFER_ERROR);
+ nvme_tcp_end_request(blk_mq_rq_from_pdu(req), NVME_SC_HOST_PATH_ERROR);
}
static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)
@@ -1023,14 +1024,16 @@ done:
static int nvme_tcp_try_recv(struct nvme_tcp_queue *queue)
{
- struct sock *sk = queue->sock->sk;
+ struct socket *sock = queue->sock;
+ struct sock *sk = sock->sk;
read_descriptor_t rd_desc;
int consumed;
rd_desc.arg.data = queue;
rd_desc.count = 1;
lock_sock(sk);
- consumed = tcp_read_sock(sk, &rd_desc, nvme_tcp_recv_skb);
+ queue->nr_cqe = 0;
+ consumed = sock->ops->read_sock(sk, &rd_desc, nvme_tcp_recv_skb);
release_sock(sk);
return consumed;
}
@@ -1255,7 +1258,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
queue->queue_size = queue_size;
if (qid > 0)
- queue->cmnd_capsule_len = ctrl->ctrl.ioccsz * 16;
+ queue->cmnd_capsule_len = nctrl->ioccsz * 16;
else
queue->cmnd_capsule_len = sizeof(struct nvme_command) +
NVME_TCP_ADMIN_CCSZ;
@@ -1263,7 +1266,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
ret = sock_create(ctrl->addr.ss_family, SOCK_STREAM,
IPPROTO_TCP, &queue->sock);
if (ret) {
- dev_err(ctrl->ctrl.device,
+ dev_err(nctrl->device,
"failed to create socket: %d\n", ret);
return ret;
}
@@ -1273,7 +1276,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
ret = kernel_setsockopt(queue->sock, IPPROTO_TCP, TCP_SYNCNT,
(char *)&opt, sizeof(opt));
if (ret) {
- dev_err(ctrl->ctrl.device,
+ dev_err(nctrl->device,
"failed to set TCP_SYNCNT sock opt %d\n", ret);
goto err_sock;
}
@@ -1283,7 +1286,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
ret = kernel_setsockopt(queue->sock, IPPROTO_TCP,
TCP_NODELAY, (char *)&opt, sizeof(opt));
if (ret) {
- dev_err(ctrl->ctrl.device,
+ dev_err(nctrl->device,
"failed to set TCP_NODELAY sock opt %d\n", ret);
goto err_sock;
}
@@ -1296,11 +1299,23 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
ret = kernel_setsockopt(queue->sock, SOL_SOCKET, SO_LINGER,
(char *)&sol, sizeof(sol));
if (ret) {
- dev_err(ctrl->ctrl.device,
+ dev_err(nctrl->device,
"failed to set SO_LINGER sock opt %d\n", ret);
goto err_sock;
}
+ /* Set socket type of service */
+ if (nctrl->opts->tos >= 0) {
+ opt = nctrl->opts->tos;
+ ret = kernel_setsockopt(queue->sock, SOL_IP, IP_TOS,
+ (char *)&opt, sizeof(opt));
+ if (ret) {
+ dev_err(nctrl->device,
+ "failed to set IP_TOS sock opt %d\n", ret);
+ goto err_sock;
+ }
+ }
+
queue->sock->sk->sk_allocation = GFP_ATOMIC;
if (!qid)
n = 0;
@@ -1314,11 +1329,11 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
queue->pdu_offset = 0;
sk_set_memalloc(queue->sock->sk);
- if (ctrl->ctrl.opts->mask & NVMF_OPT_HOST_TRADDR) {
+ if (nctrl->opts->mask & NVMF_OPT_HOST_TRADDR) {
ret = kernel_bind(queue->sock, (struct sockaddr *)&ctrl->src_addr,
sizeof(ctrl->src_addr));
if (ret) {
- dev_err(ctrl->ctrl.device,
+ dev_err(nctrl->device,
"failed to bind queue %d socket %d\n",
qid, ret);
goto err_sock;
@@ -1330,7 +1345,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
if (queue->hdr_digest || queue->data_digest) {
ret = nvme_tcp_alloc_crypto(queue);
if (ret) {
- dev_err(ctrl->ctrl.device,
+ dev_err(nctrl->device,
"failed to allocate queue %d crypto\n", qid);
goto err_sock;
}
@@ -1344,13 +1359,13 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
goto err_crypto;
}
- dev_dbg(ctrl->ctrl.device, "connecting queue %d\n",
+ dev_dbg(nctrl->device, "connecting queue %d\n",
nvme_tcp_queue_id(queue));
ret = kernel_connect(queue->sock, (struct sockaddr *)&ctrl->addr,
sizeof(ctrl->addr), 0);
if (ret) {
- dev_err(ctrl->ctrl.device,
+ dev_err(nctrl->device,
"failed to connect socket: %d\n", ret);
goto err_rcv_pdu;
}
@@ -1371,6 +1386,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
queue->sock->sk->sk_data_ready = nvme_tcp_data_ready;
queue->sock->sk->sk_state_change = nvme_tcp_state_change;
queue->sock->sk->sk_write_space = nvme_tcp_write_space;
+ queue->sock->sk->sk_ll_usec = 1;
write_unlock_bh(&queue->sock->sk->sk_callback_lock);
return 0;
@@ -1469,7 +1485,7 @@ static struct blk_mq_tag_set *nvme_tcp_alloc_tagset(struct nvme_ctrl *nctrl,
set->driver_data = ctrl;
set->nr_hw_queues = nctrl->queue_count - 1;
set->timeout = NVME_IO_TIMEOUT;
- set->nr_maps = 2 /* default + read */;
+ set->nr_maps = nctrl->opts->nr_poll_queues ? HCTX_MAX_TYPES : 2;
}
ret = blk_mq_alloc_tag_set(set);
@@ -1568,6 +1584,7 @@ static unsigned int nvme_tcp_nr_io_queues(struct nvme_ctrl *ctrl)
nr_io_queues = min(ctrl->opts->nr_io_queues, num_online_cpus());
nr_io_queues += min(ctrl->opts->nr_write_queues, num_online_cpus());
+ nr_io_queues += min(ctrl->opts->nr_poll_queues, num_online_cpus());
return nr_io_queues;
}
@@ -1599,6 +1616,12 @@ static void nvme_tcp_set_io_queues(struct nvme_ctrl *nctrl,
min(opts->nr_io_queues, nr_io_queues);
nr_io_queues -= ctrl->io_queues[HCTX_TYPE_DEFAULT];
}
+
+ if (opts->nr_poll_queues && nr_io_queues) {
+ /* map dedicated poll queues only if we have queues left */
+ ctrl->io_queues[HCTX_TYPE_POLL] =
+ min(opts->nr_poll_queues, nr_io_queues);
+ }
}
static int nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl)
@@ -1680,6 +1703,7 @@ static void nvme_tcp_destroy_admin_queue(struct nvme_ctrl *ctrl, bool remove)
nvme_tcp_stop_queue(ctrl, 0);
if (remove) {
blk_cleanup_queue(ctrl->admin_q);
+ blk_cleanup_queue(ctrl->fabrics_q);
blk_mq_free_tag_set(ctrl->admin_tagset);
}
nvme_tcp_free_admin_queue(ctrl);
@@ -1700,10 +1724,16 @@ static int nvme_tcp_configure_admin_queue(struct nvme_ctrl *ctrl, bool new)
goto out_free_queue;
}
+ ctrl->fabrics_q = blk_mq_init_queue(ctrl->admin_tagset);
+ if (IS_ERR(ctrl->fabrics_q)) {
+ error = PTR_ERR(ctrl->fabrics_q);
+ goto out_free_tagset;
+ }
+
ctrl->admin_q = blk_mq_init_queue(ctrl->admin_tagset);
if (IS_ERR(ctrl->admin_q)) {
error = PTR_ERR(ctrl->admin_q);
- goto out_free_tagset;
+ goto out_cleanup_fabrics_q;
}
}
@@ -1711,19 +1741,12 @@ static int nvme_tcp_configure_admin_queue(struct nvme_ctrl *ctrl, bool new)
if (error)
goto out_cleanup_queue;
- error = ctrl->ops->reg_read64(ctrl, NVME_REG_CAP, &ctrl->cap);
- if (error) {
- dev_err(ctrl->device,
- "prop_get NVME_REG_CAP failed\n");
- goto out_stop_queue;
- }
-
- ctrl->sqsize = min_t(int, NVME_CAP_MQES(ctrl->cap), ctrl->sqsize);
-
- error = nvme_enable_ctrl(ctrl, ctrl->cap);
+ error = nvme_enable_ctrl(ctrl);
if (error)
goto out_stop_queue;
+ blk_mq_unquiesce_queue(ctrl->admin_q);
+
error = nvme_init_identify(ctrl);
if (error)
goto out_stop_queue;
@@ -1735,6 +1758,9 @@ out_stop_queue:
out_cleanup_queue:
if (new)
blk_cleanup_queue(ctrl->admin_q);
+out_cleanup_fabrics_q:
+ if (new)
+ blk_cleanup_queue(ctrl->fabrics_q);
out_free_tagset:
if (new)
blk_mq_free_tag_set(ctrl->admin_tagset);
@@ -1748,10 +1774,13 @@ static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl,
{
blk_mq_quiesce_queue(ctrl->admin_q);
nvme_tcp_stop_queue(ctrl, 0);
- if (ctrl->admin_tagset)
+ if (ctrl->admin_tagset) {
blk_mq_tagset_busy_iter(ctrl->admin_tagset,
nvme_cancel_request, ctrl);
- blk_mq_unquiesce_queue(ctrl->admin_q);
+ blk_mq_tagset_wait_completed_request(ctrl->admin_tagset);
+ }
+ if (remove)
+ blk_mq_unquiesce_queue(ctrl->admin_q);
nvme_tcp_destroy_admin_queue(ctrl, remove);
}
@@ -1762,9 +1791,11 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
return;
nvme_stop_queues(ctrl);
nvme_tcp_stop_io_queues(ctrl);
- if (ctrl->tagset)
+ if (ctrl->tagset) {
blk_mq_tagset_busy_iter(ctrl->tagset,
nvme_cancel_request, ctrl);
+ blk_mq_tagset_wait_completed_request(ctrl->tagset);
+ }
if (remove)
nvme_start_queues(ctrl);
nvme_tcp_destroy_io_queues(ctrl, remove);
@@ -1793,7 +1824,7 @@ static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl)
static int nvme_tcp_setup_ctrl(struct nvme_ctrl *ctrl, bool new)
{
struct nvmf_ctrl_options *opts = ctrl->opts;
- int ret = -EINVAL;
+ int ret;
ret = nvme_tcp_configure_admin_queue(ctrl, new);
if (ret)
@@ -1876,6 +1907,7 @@ static void nvme_tcp_error_recovery_work(struct work_struct *work)
/* unquiesce to fail fast pending requests */
nvme_start_queues(ctrl);
nvme_tcp_teardown_admin_queue(ctrl, false);
+ blk_mq_unquiesce_queue(ctrl->admin_q);
if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING)) {
/* state change failure is ok if we're in DELETING state */
@@ -1892,10 +1924,11 @@ static void nvme_tcp_teardown_ctrl(struct nvme_ctrl *ctrl, bool shutdown)
cancel_delayed_work_sync(&to_tcp_ctrl(ctrl)->connect_work);
nvme_tcp_teardown_io_queues(ctrl, shutdown);
+ blk_mq_quiesce_queue(ctrl->admin_q);
if (shutdown)
nvme_shutdown_ctrl(ctrl);
else
- nvme_disable_ctrl(ctrl, ctrl->cap);
+ nvme_disable_ctrl(ctrl);
nvme_tcp_teardown_admin_queue(ctrl, shutdown);
}
@@ -2151,14 +2184,36 @@ static int nvme_tcp_map_queues(struct blk_mq_tag_set *set)
blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]);
blk_mq_map_queues(&set->map[HCTX_TYPE_READ]);
+ if (opts->nr_poll_queues && ctrl->io_queues[HCTX_TYPE_POLL]) {
+ /* map dedicated poll queues only if we have queues left */
+ set->map[HCTX_TYPE_POLL].nr_queues =
+ ctrl->io_queues[HCTX_TYPE_POLL];
+ set->map[HCTX_TYPE_POLL].queue_offset =
+ ctrl->io_queues[HCTX_TYPE_DEFAULT] +
+ ctrl->io_queues[HCTX_TYPE_READ];
+ blk_mq_map_queues(&set->map[HCTX_TYPE_POLL]);
+ }
+
dev_info(ctrl->ctrl.device,
- "mapped %d/%d default/read queues.\n",
+ "mapped %d/%d/%d default/read/poll queues.\n",
ctrl->io_queues[HCTX_TYPE_DEFAULT],
- ctrl->io_queues[HCTX_TYPE_READ]);
+ ctrl->io_queues[HCTX_TYPE_READ],
+ ctrl->io_queues[HCTX_TYPE_POLL]);
return 0;
}
+static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx)
+{
+ struct nvme_tcp_queue *queue = hctx->driver_data;
+ struct sock *sk = queue->sock->sk;
+
+ if (sk_can_busy_loop(sk) && skb_queue_empty(&sk->sk_receive_queue))
+ sk_busy_loop(sk, true);
+ nvme_tcp_try_recv(queue);
+ return queue->nr_cqe;
+}
+
static struct blk_mq_ops nvme_tcp_mq_ops = {
.queue_rq = nvme_tcp_queue_rq,
.complete = nvme_complete_rq,
@@ -2167,6 +2222,7 @@ static struct blk_mq_ops nvme_tcp_mq_ops = {
.init_hctx = nvme_tcp_init_hctx,
.timeout = nvme_tcp_timeout,
.map_queues = nvme_tcp_map_queues,
+ .poll = nvme_tcp_poll,
};
static struct blk_mq_ops nvme_tcp_admin_mq_ops = {
@@ -2220,7 +2276,8 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
INIT_LIST_HEAD(&ctrl->list);
ctrl->ctrl.opts = opts;
- ctrl->ctrl.queue_count = opts->nr_io_queues + opts->nr_write_queues + 1;
+ ctrl->ctrl.queue_count = opts->nr_io_queues + opts->nr_write_queues +
+ opts->nr_poll_queues + 1;
ctrl->ctrl.sqsize = opts->queue_size - 1;
ctrl->ctrl.kato = opts->kato;
@@ -2314,7 +2371,8 @@ static struct nvmf_transport_ops nvme_tcp_transport = {
.allowed_opts = NVMF_OPT_TRSVCID | NVMF_OPT_RECONNECT_DELAY |
NVMF_OPT_HOST_TRADDR | NVMF_OPT_CTRL_LOSS_TMO |
NVMF_OPT_HDR_DIGEST | NVMF_OPT_DATA_DIGEST |
- NVMF_OPT_NR_WRITE_QUEUES,
+ NVMF_OPT_NR_WRITE_QUEUES | NVMF_OPT_NR_POLL_QUEUES |
+ NVMF_OPT_TOS,
.create_ctrl = nvme_tcp_create_ctrl,
};
diff --git a/drivers/nvme/host/trace.c b/drivers/nvme/host/trace.c
index 9778eb0406b3..5c3cb6928f3c 100644
--- a/drivers/nvme/host/trace.c
+++ b/drivers/nvme/host/trace.c
@@ -86,6 +86,22 @@ static const char *nvme_trace_admin_get_features(struct trace_seq *p,
return ret;
}
+static const char *nvme_trace_get_lba_status(struct trace_seq *p,
+ u8 *cdw10)
+{
+ const char *ret = trace_seq_buffer_ptr(p);
+ u64 slba = get_unaligned_le64(cdw10);
+ u32 mndw = get_unaligned_le32(cdw10 + 8);
+ u16 rl = get_unaligned_le16(cdw10 + 12);
+ u8 atype = cdw10[15];
+
+ trace_seq_printf(p, "slba=0x%llx, mndw=0x%x, rl=0x%x, atype=%u",
+ slba, mndw, rl, atype);
+ trace_seq_putc(p, 0);
+
+ return ret;
+}
+
static const char *nvme_trace_read_write(struct trace_seq *p, u8 *cdw10)
{
const char *ret = trace_seq_buffer_ptr(p);
@@ -141,6 +157,8 @@ const char *nvme_trace_parse_admin_cmd(struct trace_seq *p,
return nvme_trace_admin_identify(p, cdw10);
case nvme_admin_get_features:
return nvme_trace_admin_get_features(p, cdw10);
+ case nvme_admin_get_lba_status:
+ return nvme_trace_get_lba_status(p, cdw10);
default:
return nvme_trace_common(p, cdw10);
}
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 4dc12ea52f23..831a062d27cb 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -37,7 +37,6 @@ static void nvmet_execute_get_log_page_noop(struct nvmet_req *req)
static void nvmet_execute_get_log_page_error(struct nvmet_req *req)
{
struct nvmet_ctrl *ctrl = req->sq->ctrl;
- u16 status = NVME_SC_SUCCESS;
unsigned long flags;
off_t offset = 0;
u64 slot;
@@ -47,9 +46,8 @@ static void nvmet_execute_get_log_page_error(struct nvmet_req *req)
slot = ctrl->err_counter % NVMET_ERROR_LOG_SLOTS;
for (i = 0; i < NVMET_ERROR_LOG_SLOTS; i++) {
- status = nvmet_copy_to_sgl(req, offset, &ctrl->slots[slot],
- sizeof(struct nvme_error_slot));
- if (status)
+ if (nvmet_copy_to_sgl(req, offset, &ctrl->slots[slot],
+ sizeof(struct nvme_error_slot)))
break;
if (slot == 0)
@@ -59,7 +57,7 @@ static void nvmet_execute_get_log_page_error(struct nvmet_req *req)
offset += sizeof(struct nvme_error_slot);
}
spin_unlock_irqrestore(&ctrl->error_lock, flags);
- nvmet_req_complete(req, status);
+ nvmet_req_complete(req, 0);
}
static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req,
@@ -81,9 +79,11 @@ static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req,
goto out;
host_reads = part_stat_read(ns->bdev->bd_part, ios[READ]);
- data_units_read = part_stat_read(ns->bdev->bd_part, sectors[READ]);
+ data_units_read = DIV_ROUND_UP(part_stat_read(ns->bdev->bd_part,
+ sectors[READ]), 1000);
host_writes = part_stat_read(ns->bdev->bd_part, ios[WRITE]);
- data_units_written = part_stat_read(ns->bdev->bd_part, sectors[WRITE]);
+ data_units_written = DIV_ROUND_UP(part_stat_read(ns->bdev->bd_part,
+ sectors[WRITE]), 1000);
put_unaligned_le64(host_reads, &slog->host_reads[0]);
put_unaligned_le64(data_units_read, &slog->data_units_read[0]);
@@ -111,11 +111,11 @@ static u16 nvmet_get_smart_log_all(struct nvmet_req *req,
if (!ns->bdev)
continue;
host_reads += part_stat_read(ns->bdev->bd_part, ios[READ]);
- data_units_read +=
- part_stat_read(ns->bdev->bd_part, sectors[READ]);
+ data_units_read += DIV_ROUND_UP(
+ part_stat_read(ns->bdev->bd_part, sectors[READ]), 1000);
host_writes += part_stat_read(ns->bdev->bd_part, ios[WRITE]);
- data_units_written +=
- part_stat_read(ns->bdev->bd_part, sectors[WRITE]);
+ data_units_written += DIV_ROUND_UP(
+ part_stat_read(ns->bdev->bd_part, sectors[WRITE]), 1000);
}
rcu_read_unlock();
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
index 8efca26b4776..3764a8900850 100644
--- a/drivers/nvme/target/discovery.c
+++ b/drivers/nvme/target/discovery.c
@@ -381,9 +381,7 @@ int __init nvmet_init_discovery(void)
{
nvmet_disc_subsys =
nvmet_subsys_alloc(NVME_DISC_SUBSYS_NAME, NVME_NQN_DISC);
- if (IS_ERR(nvmet_disc_subsys))
- return PTR_ERR(nvmet_disc_subsys);
- return 0;
+ return PTR_ERR_OR_ZERO(nvmet_disc_subsys);
}
void nvmet_exit_discovery(void)
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 0940c5024a34..748a39fca771 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -253,6 +253,7 @@ static void nvme_loop_destroy_admin_queue(struct nvme_loop_ctrl *ctrl)
clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags);
nvmet_sq_destroy(&ctrl->queues[0].nvme_sq);
blk_cleanup_queue(ctrl->ctrl.admin_q);
+ blk_cleanup_queue(ctrl->ctrl.fabrics_q);
blk_mq_free_tag_set(&ctrl->admin_tag_set);
}
@@ -357,10 +358,16 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
goto out_free_sq;
ctrl->ctrl.admin_tagset = &ctrl->admin_tag_set;
+ ctrl->ctrl.fabrics_q = blk_mq_init_queue(&ctrl->admin_tag_set);
+ if (IS_ERR(ctrl->ctrl.fabrics_q)) {
+ error = PTR_ERR(ctrl->ctrl.fabrics_q);
+ goto out_free_tagset;
+ }
+
ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set);
if (IS_ERR(ctrl->ctrl.admin_q)) {
error = PTR_ERR(ctrl->ctrl.admin_q);
- goto out_free_tagset;
+ goto out_cleanup_fabrics_q;
}
error = nvmf_connect_admin_queue(&ctrl->ctrl);
@@ -369,23 +376,15 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
set_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags);
- error = nvmf_reg_read64(&ctrl->ctrl, NVME_REG_CAP, &ctrl->ctrl.cap);
- if (error) {
- dev_err(ctrl->ctrl.device,
- "prop_get NVME_REG_CAP failed\n");
- goto out_cleanup_queue;
- }
-
- ctrl->ctrl.sqsize =
- min_t(int, NVME_CAP_MQES(ctrl->ctrl.cap), ctrl->ctrl.sqsize);
-
- error = nvme_enable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap);
+ error = nvme_enable_ctrl(&ctrl->ctrl);
if (error)
goto out_cleanup_queue;
ctrl->ctrl.max_hw_sectors =
(NVME_LOOP_MAX_SEGMENTS - 1) << (PAGE_SHIFT - 9);
+ blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+
error = nvme_init_identify(&ctrl->ctrl);
if (error)
goto out_cleanup_queue;
@@ -394,6 +393,8 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
out_cleanup_queue:
blk_cleanup_queue(ctrl->ctrl.admin_q);
+out_cleanup_fabrics_q:
+ blk_cleanup_queue(ctrl->ctrl.fabrics_q);
out_free_tagset:
blk_mq_free_tag_set(&ctrl->admin_tag_set);
out_free_sq:
@@ -407,16 +408,17 @@ static void nvme_loop_shutdown_ctrl(struct nvme_loop_ctrl *ctrl)
nvme_stop_queues(&ctrl->ctrl);
blk_mq_tagset_busy_iter(&ctrl->tag_set,
nvme_cancel_request, &ctrl->ctrl);
+ blk_mq_tagset_wait_completed_request(&ctrl->tag_set);
nvme_loop_destroy_io_queues(ctrl);
}
+ blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
if (ctrl->ctrl.state == NVME_CTRL_LIVE)
nvme_shutdown_ctrl(&ctrl->ctrl);
- blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
nvme_cancel_request, &ctrl->ctrl);
- blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+ blk_mq_tagset_wait_completed_request(&ctrl->admin_tag_set);
nvme_loop_destroy_admin_queue(ctrl);
}
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 69b83fa0c76c..bf4f03474e89 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -348,7 +348,8 @@ static int nvmet_tcp_map_data(struct nvmet_tcp_cmd *cmd)
return 0;
err:
- sgl_free(cmd->req.sg);
+ if (cmd->req.sg_cnt)
+ sgl_free(cmd->req.sg);
return NVME_SC_INTERNAL;
}
@@ -553,7 +554,8 @@ static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd)
if (queue->nvme_sq.sqhd_disabled) {
kfree(cmd->iov);
- sgl_free(cmd->req.sg);
+ if (cmd->req.sg_cnt)
+ sgl_free(cmd->req.sg);
}
return 1;
@@ -584,7 +586,8 @@ static int nvmet_try_send_response(struct nvmet_tcp_cmd *cmd,
return -EAGAIN;
kfree(cmd->iov);
- sgl_free(cmd->req.sg);
+ if (cmd->req.sg_cnt)
+ sgl_free(cmd->req.sg);
cmd->queue->snd_cmd = NULL;
nvmet_tcp_put_cmd(cmd);
return 1;
@@ -1306,7 +1309,9 @@ static void nvmet_tcp_finish_cmd(struct nvmet_tcp_cmd *cmd)
{
nvmet_req_uninit(&cmd->req);
nvmet_tcp_unmap_pdu_iovec(cmd);
- sgl_free(cmd->req.sg);
+ kfree(cmd->iov);
+ if (cmd->req.sg_cnt)
+ sgl_free(cmd->req.sg);
}
static void nvmet_tcp_uninit_data_in_cmds(struct nvmet_tcp_queue *queue)
@@ -1410,6 +1415,7 @@ done:
static int nvmet_tcp_set_queue_sock(struct nvmet_tcp_queue *queue)
{
struct socket *sock = queue->sock;
+ struct inet_sock *inet = inet_sk(sock->sk);
struct linger sol = { .l_onoff = 1, .l_linger = 0 };
int ret;
@@ -1433,6 +1439,16 @@ static int nvmet_tcp_set_queue_sock(struct nvmet_tcp_queue *queue)
if (ret)
return ret;
+ /* Set socket type of service */
+ if (inet->rcv_tos > 0) {
+ int tos = inet->rcv_tos;
+
+ ret = kernel_setsockopt(sock, SOL_IP, IP_TOS,
+ (char *)&tos, sizeof(tos));
+ if (ret)
+ return ret;
+ }
+
write_lock_bh(&sock->sk->sk_callback_lock);
sock->sk->sk_user_data = queue;
queue->data_ready = sock->sk->sk_data_ready;
diff --git a/drivers/nvme/target/trace.c b/drivers/nvme/target/trace.c
index 6af11d493271..1373a3c67962 100644
--- a/drivers/nvme/target/trace.c
+++ b/drivers/nvme/target/trace.c
@@ -33,6 +33,22 @@ static const char *nvmet_trace_admin_get_features(struct trace_seq *p,
return ret;
}
+static const char *nvmet_trace_get_lba_status(struct trace_seq *p,
+ u8 *cdw10)
+{
+ const char *ret = trace_seq_buffer_ptr(p);
+ u64 slba = get_unaligned_le64(cdw10);
+ u32 mndw = get_unaligned_le32(cdw10 + 8);
+ u16 rl = get_unaligned_le16(cdw10 + 12);
+ u8 atype = cdw10[15];
+
+ trace_seq_printf(p, "slba=0x%llx, mndw=0x%x, rl=0x%x, atype=%u",
+ slba, mndw, rl, atype);
+ trace_seq_putc(p, 0);
+
+ return ret;
+}
+
static const char *nvmet_trace_read_write(struct trace_seq *p, u8 *cdw10)
{
const char *ret = trace_seq_buffer_ptr(p);
@@ -80,6 +96,8 @@ const char *nvmet_trace_parse_admin_cmd(struct trace_seq *p,
return nvmet_trace_admin_identify(p, cdw10);
case nvme_admin_get_features:
return nvmet_trace_admin_get_features(p, cdw10);
+ case nvme_admin_get_lba_status:
+ return nvmet_trace_get_lba_status(p, cdw10);
default:
return nvmet_trace_common(p, cdw10);
}
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 11e64b50497f..4e88d7e9cf9a 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1089,6 +1089,18 @@ static void scsi_initialize_rq(struct request *rq)
cmd->retries = 0;
}
+/*
+ * Only called when the request isn't completed by SCSI, and not freed by
+ * SCSI
+ */
+static void scsi_cleanup_rq(struct request *rq)
+{
+ if (rq->rq_flags & RQF_DONTPREP) {
+ scsi_mq_uninit_cmd(blk_mq_rq_to_pdu(rq));
+ rq->rq_flags &= ~RQF_DONTPREP;
+ }
+}
+
/* Add a command to the list used by the aacraid and dpt_i2o drivers */
void scsi_add_cmd_to_list(struct scsi_cmnd *cmd)
{
@@ -1821,6 +1833,7 @@ static const struct blk_mq_ops scsi_mq_ops = {
.init_request = scsi_mq_init_request,
.exit_request = scsi_mq_exit_request,
.initialize_rq_fn = scsi_initialize_rq,
+ .cleanup_rq = scsi_cleanup_rq,
.busy = scsi_mq_lld_busy,
.map_queues = scsi_map_queues,
};
diff --git a/drivers/scsi/scsi_pm.c b/drivers/scsi/scsi_pm.c
index 74ded5f3c236..3717eea37ecb 100644
--- a/drivers/scsi/scsi_pm.c
+++ b/drivers/scsi/scsi_pm.c
@@ -94,8 +94,7 @@ static int scsi_dev_type_resume(struct device *dev,
if (!err && scsi_is_sdev_device(dev)) {
struct scsi_device *sdev = to_scsi_device(dev);
- if (sdev->request_queue->dev)
- blk_set_runtime_active(sdev->request_queue);
+ blk_set_runtime_active(sdev->request_queue);
}
}
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 149d406aacc9..4b925552458f 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1293,7 +1293,9 @@ static blk_status_t sd_init_command(struct scsi_cmnd *cmd)
case REQ_OP_WRITE:
return sd_setup_read_write_cmnd(cmd);
case REQ_OP_ZONE_RESET:
- return sd_zbc_setup_reset_cmnd(cmd);
+ return sd_zbc_setup_reset_cmnd(cmd, false);
+ case REQ_OP_ZONE_RESET_ALL:
+ return sd_zbc_setup_reset_cmnd(cmd, true);
default:
WARN_ON_ONCE(1);
return BLK_STS_NOTSUPP;
@@ -1959,6 +1961,7 @@ static int sd_done(struct scsi_cmnd *SCpnt)
case REQ_OP_WRITE_ZEROES:
case REQ_OP_WRITE_SAME:
case REQ_OP_ZONE_RESET:
+ case REQ_OP_ZONE_RESET_ALL:
if (!result) {
good_bytes = blk_rq_bytes(req);
scsi_set_resid(SCpnt, 0);
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 38c50946fc42..1eab779f812b 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -209,7 +209,7 @@ static inline int sd_is_zoned(struct scsi_disk *sdkp)
extern int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buffer);
extern void sd_zbc_print_zones(struct scsi_disk *sdkp);
-extern blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd);
+extern blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd, bool all);
extern void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
struct scsi_sense_hdr *sshdr);
extern int sd_zbc_report_zones(struct gendisk *disk, sector_t sector,
@@ -225,7 +225,8 @@ static inline int sd_zbc_read_zones(struct scsi_disk *sdkp,
static inline void sd_zbc_print_zones(struct scsi_disk *sdkp) {}
-static inline blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd)
+static inline blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd,
+ bool all)
{
return BLK_STS_TARGET;
}
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index 5d6ff3931632..de4019dc0f0b 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -209,10 +209,11 @@ static inline sector_t sd_zbc_zone_sectors(struct scsi_disk *sdkp)
/**
* sd_zbc_setup_reset_cmnd - Prepare a RESET WRITE POINTER scsi command.
* @cmd: the command to setup
+ * @all: Reset all zones control.
*
* Called from sd_init_command() for a REQ_OP_ZONE_RESET request.
*/
-blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd)
+blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd, bool all)
{
struct request *rq = cmd->request;
struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
@@ -234,7 +235,10 @@ blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd)
memset(cmd->cmnd, 0, cmd->cmd_len);
cmd->cmnd[0] = ZBC_OUT;
cmd->cmnd[1] = ZO_RESET_WRITE_POINTER;
- put_unaligned_be64(block, &cmd->cmnd[2]);
+ if (all)
+ cmd->cmnd[14] = 0x1;
+ else
+ put_unaligned_be64(block, &cmd->cmnd[2]);
rq->timeout = SD_TIMEOUT;
cmd->sc_data_direction = DMA_NONE;
@@ -261,6 +265,7 @@ void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
switch (req_op(rq)) {
case REQ_OP_ZONE_RESET:
+ case REQ_OP_ZONE_RESET_ALL:
if (result &&
sshdr->sense_key == ILLEGAL_REQUEST &&
@@ -487,6 +492,9 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
/* The drive satisfies the kernel restrictions: set it up */
blk_queue_chunk_sectors(sdkp->disk->queue,
logical_to_sectors(sdkp->device, zone_blocks));
+ blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, sdkp->disk->queue);
+ blk_queue_required_elevator_features(sdkp->disk->queue,
+ ELEVATOR_F_ZBD_SEQ_WRITE);
nr_zones = round_up(sdkp->capacity, zone_blocks) >> ilog2(zone_blocks);
/* READ16/WRITE16 is mandatory for ZBC disks */
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 542b02d170f8..8aaa7eec7b74 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -36,10 +36,6 @@
*/
#define MIN_WRITEBACK_PAGES (4096UL >> (PAGE_SHIFT - 10))
-struct wb_completion {
- atomic_t cnt;
-};
-
/*
* Passed into wb_writeback(), essentially a subset of writeback_control
*/
@@ -61,19 +57,6 @@ struct wb_writeback_work {
};
/*
- * If one wants to wait for one or more wb_writeback_works, each work's
- * ->done should be set to a wb_completion defined using the following
- * macro. Once all work items are issued with wb_queue_work(), the caller
- * can wait for the completion of all using wb_wait_for_completion(). Work
- * items which are waited upon aren't freed automatically on completion.
- */
-#define DEFINE_WB_COMPLETION_ONSTACK(cmpl) \
- struct wb_completion cmpl = { \
- .cnt = ATOMIC_INIT(1), \
- }
-
-
-/*
* If an inode is constantly having its pages dirtied, but then the
* updates stop dirtytime_expire_interval seconds in the past, it's
* possible for the worst case time between when an inode has its
@@ -182,7 +165,7 @@ static void finish_writeback_work(struct bdi_writeback *wb,
if (work->auto_free)
kfree(work);
if (done && atomic_dec_and_test(&done->cnt))
- wake_up_all(&wb->bdi->wb_waitq);
+ wake_up_all(done->waitq);
}
static void wb_queue_work(struct bdi_writeback *wb,
@@ -206,28 +189,44 @@ static void wb_queue_work(struct bdi_writeback *wb,
/**
* wb_wait_for_completion - wait for completion of bdi_writeback_works
- * @bdi: bdi work items were issued to
* @done: target wb_completion
*
* Wait for one or more work items issued to @bdi with their ->done field
- * set to @done, which should have been defined with
- * DEFINE_WB_COMPLETION_ONSTACK(). This function returns after all such
- * work items are completed. Work items which are waited upon aren't freed
+ * set to @done, which should have been initialized with
+ * DEFINE_WB_COMPLETION(). This function returns after all such work items
+ * are completed. Work items which are waited upon aren't freed
* automatically on completion.
*/
-static void wb_wait_for_completion(struct backing_dev_info *bdi,
- struct wb_completion *done)
+void wb_wait_for_completion(struct wb_completion *done)
{
atomic_dec(&done->cnt); /* put down the initial count */
- wait_event(bdi->wb_waitq, !atomic_read(&done->cnt));
+ wait_event(*done->waitq, !atomic_read(&done->cnt));
}
#ifdef CONFIG_CGROUP_WRITEBACK
-/* parameters for foreign inode detection, see wb_detach_inode() */
+/*
+ * Parameters for foreign inode detection, see wbc_detach_inode() to see
+ * how they're used.
+ *
+ * These paramters are inherently heuristical as the detection target
+ * itself is fuzzy. All we want to do is detaching an inode from the
+ * current owner if it's being written to by some other cgroups too much.
+ *
+ * The current cgroup writeback is built on the assumption that multiple
+ * cgroups writing to the same inode concurrently is very rare and a mode
+ * of operation which isn't well supported. As such, the goal is not
+ * taking too long when a different cgroup takes over an inode while
+ * avoiding too aggressive flip-flops from occasional foreign writes.
+ *
+ * We record, very roughly, 2s worth of IO time history and if more than
+ * half of that is foreign, trigger the switch. The recording is quantized
+ * to 16 slots. To avoid tiny writes from swinging the decision too much,
+ * writes smaller than 1/8 of avg size are ignored.
+ */
#define WB_FRN_TIME_SHIFT 13 /* 1s = 2^13, upto 8 secs w/ 16bit */
#define WB_FRN_TIME_AVG_SHIFT 3 /* avg = avg * 7/8 + new * 1/8 */
-#define WB_FRN_TIME_CUT_DIV 2 /* ignore rounds < avg / 2 */
+#define WB_FRN_TIME_CUT_DIV 8 /* ignore rounds < avg / 8 */
#define WB_FRN_TIME_PERIOD (2 * (1 << WB_FRN_TIME_SHIFT)) /* 2s */
#define WB_FRN_HIST_SLOTS 16 /* inode->i_wb_frn_history is 16bit */
@@ -237,6 +236,7 @@ static void wb_wait_for_completion(struct backing_dev_info *bdi,
/* if foreign slots >= 8, switch */
#define WB_FRN_HIST_MAX_SLOTS (WB_FRN_HIST_THR_SLOTS / 2 + 1)
/* one round can affect upto 5 slots */
+#define WB_FRN_MAX_IN_FLIGHT 1024 /* don't queue too many concurrently */
static atomic_t isw_nr_in_flight = ATOMIC_INIT(0);
static struct workqueue_struct *isw_wq;
@@ -389,6 +389,8 @@ static void inode_switch_wbs_work_fn(struct work_struct *work)
if (unlikely(inode->i_state & I_FREEING))
goto skip_switch;
+ trace_inode_switch_wbs(inode, old_wb, new_wb);
+
/*
* Count and transfer stats. Note that PAGECACHE_TAG_DIRTY points
* to possibly dirty pages while PAGECACHE_TAG_WRITEBACK points to
@@ -489,18 +491,13 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
if (inode->i_state & I_WB_SWITCH)
return;
- /*
- * Avoid starting new switches while sync_inodes_sb() is in
- * progress. Otherwise, if the down_write protected issue path
- * blocks heavily, we might end up starting a large number of
- * switches which will block on the rwsem.
- */
- if (!down_read_trylock(&bdi->wb_switch_rwsem))
+ /* avoid queueing a new switch if too many are already in flight */
+ if (atomic_read(&isw_nr_in_flight) > WB_FRN_MAX_IN_FLIGHT)
return;
isw = kzalloc(sizeof(*isw), GFP_ATOMIC);
if (!isw)
- goto out_unlock;
+ return;
/* find and pin the new wb */
rcu_read_lock();
@@ -534,15 +531,12 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn);
atomic_inc(&isw_nr_in_flight);
-
- goto out_unlock;
+ return;
out_free:
if (isw->new_wb)
wb_put(isw->new_wb);
kfree(isw);
-out_unlock:
- up_read(&bdi->wb_switch_rwsem);
}
/**
@@ -681,6 +675,9 @@ void wbc_detach_inode(struct writeback_control *wbc)
if (wbc->wb_id != max_id)
history |= (1U << slots) - 1;
+ if (history)
+ trace_inode_foreign_history(inode, wbc, history);
+
/*
* Switch if the current wb isn't the consistent winner.
* If there are multiple closely competing dirtiers, the
@@ -843,7 +840,7 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi,
restart:
rcu_read_lock();
list_for_each_entry_continue_rcu(wb, &bdi->wb_list, bdi_node) {
- DEFINE_WB_COMPLETION_ONSTACK(fallback_work_done);
+ DEFINE_WB_COMPLETION(fallback_work_done, bdi);
struct wb_writeback_work fallback_work;
struct wb_writeback_work *work;
long nr_pages;
@@ -890,7 +887,7 @@ restart:
last_wb = wb;
rcu_read_unlock();
- wb_wait_for_completion(bdi, &fallback_work_done);
+ wb_wait_for_completion(&fallback_work_done);
goto restart;
}
rcu_read_unlock();
@@ -900,6 +897,89 @@ restart:
}
/**
+ * cgroup_writeback_by_id - initiate cgroup writeback from bdi and memcg IDs
+ * @bdi_id: target bdi id
+ * @memcg_id: target memcg css id
+ * @nr_pages: number of pages to write, 0 for best-effort dirty flushing
+ * @reason: reason why some writeback work initiated
+ * @done: target wb_completion
+ *
+ * Initiate flush of the bdi_writeback identified by @bdi_id and @memcg_id
+ * with the specified parameters.
+ */
+int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, unsigned long nr,
+ enum wb_reason reason, struct wb_completion *done)
+{
+ struct backing_dev_info *bdi;
+ struct cgroup_subsys_state *memcg_css;
+ struct bdi_writeback *wb;
+ struct wb_writeback_work *work;
+ int ret;
+
+ /* lookup bdi and memcg */
+ bdi = bdi_get_by_id(bdi_id);
+ if (!bdi)
+ return -ENOENT;
+
+ rcu_read_lock();
+ memcg_css = css_from_id(memcg_id, &memory_cgrp_subsys);
+ if (memcg_css && !css_tryget(memcg_css))
+ memcg_css = NULL;
+ rcu_read_unlock();
+ if (!memcg_css) {
+ ret = -ENOENT;
+ goto out_bdi_put;
+ }
+
+ /*
+ * And find the associated wb. If the wb isn't there already
+ * there's nothing to flush, don't create one.
+ */
+ wb = wb_get_lookup(bdi, memcg_css);
+ if (!wb) {
+ ret = -ENOENT;
+ goto out_css_put;
+ }
+
+ /*
+ * If @nr is zero, the caller is attempting to write out most of
+ * the currently dirty pages. Let's take the current dirty page
+ * count and inflate it by 25% which should be large enough to
+ * flush out most dirty pages while avoiding getting livelocked by
+ * concurrent dirtiers.
+ */
+ if (!nr) {
+ unsigned long filepages, headroom, dirty, writeback;
+
+ mem_cgroup_wb_stats(wb, &filepages, &headroom, &dirty,
+ &writeback);
+ nr = dirty * 10 / 8;
+ }
+
+ /* issue the writeback work */
+ work = kzalloc(sizeof(*work), GFP_NOWAIT | __GFP_NOWARN);
+ if (work) {
+ work->nr_pages = nr;
+ work->sync_mode = WB_SYNC_NONE;
+ work->range_cyclic = 1;
+ work->reason = reason;
+ work->done = done;
+ work->auto_free = 1;
+ wb_queue_work(wb, work);
+ ret = 0;
+ } else {
+ ret = -ENOMEM;
+ }
+
+ wb_put(wb);
+out_css_put:
+ css_put(memcg_css);
+out_bdi_put:
+ bdi_put(bdi);
+ return ret;
+}
+
+/**
* cgroup_writeback_umount - flush inode wb switches for umount
*
* This function is called when a super_block is about to be destroyed and
@@ -2362,7 +2442,8 @@ static void wait_sb_inodes(struct super_block *sb)
static void __writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr,
enum wb_reason reason, bool skip_if_busy)
{
- DEFINE_WB_COMPLETION_ONSTACK(done);
+ struct backing_dev_info *bdi = sb->s_bdi;
+ DEFINE_WB_COMPLETION(done, bdi);
struct wb_writeback_work work = {
.sb = sb,
.sync_mode = WB_SYNC_NONE,
@@ -2371,14 +2452,13 @@ static void __writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr,
.nr_pages = nr,
.reason = reason,
};
- struct backing_dev_info *bdi = sb->s_bdi;
if (!bdi_has_dirty_io(bdi) || bdi == &noop_backing_dev_info)
return;
WARN_ON(!rwsem_is_locked(&sb->s_umount));
bdi_split_work_to_wbs(sb->s_bdi, &work, skip_if_busy);
- wb_wait_for_completion(bdi, &done);
+ wb_wait_for_completion(&done);
}
/**
@@ -2440,7 +2520,8 @@ EXPORT_SYMBOL(try_to_writeback_inodes_sb);
*/
void sync_inodes_sb(struct super_block *sb)
{
- DEFINE_WB_COMPLETION_ONSTACK(done);
+ struct backing_dev_info *bdi = sb->s_bdi;
+ DEFINE_WB_COMPLETION(done, bdi);
struct wb_writeback_work work = {
.sb = sb,
.sync_mode = WB_SYNC_ALL,
@@ -2450,7 +2531,6 @@ void sync_inodes_sb(struct super_block *sb)
.reason = WB_REASON_SYNC,
.for_sync = 1,
};
- struct backing_dev_info *bdi = sb->s_bdi;
/*
* Can't skip on !bdi_has_dirty() because we should wait for !dirty
@@ -2464,7 +2544,7 @@ void sync_inodes_sb(struct super_block *sb)
/* protect against inode wb switch, see inode_switch_wbs_work_fn() */
bdi_down_write_wb_switch_rwsem(bdi);
bdi_split_work_to_wbs(bdi, &work, false);
- wb_wait_for_completion(bdi, &done);
+ wb_wait_for_completion(&done);
bdi_up_write_wb_switch_rwsem(bdi);
wait_sb_inodes(sb);
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index 6a1a8a314d85..4fc87dee005a 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -63,10 +63,31 @@ enum wb_reason {
* so it has a mismatch name.
*/
WB_REASON_FORKER_THREAD,
+ WB_REASON_FOREIGN_FLUSH,
WB_REASON_MAX,
};
+struct wb_completion {
+ atomic_t cnt;
+ wait_queue_head_t *waitq;
+};
+
+#define __WB_COMPLETION_INIT(_waitq) \
+ (struct wb_completion){ .cnt = ATOMIC_INIT(1), .waitq = (_waitq) }
+
+/*
+ * If one wants to wait for one or more wb_writeback_works, each work's
+ * ->done should be set to a wb_completion defined using the following
+ * macro. Once all work items are issued with wb_queue_work(), the caller
+ * can wait for the completion of all using wb_wait_for_completion(). Work
+ * items which are waited upon aren't freed automatically on completion.
+ */
+#define WB_COMPLETION_INIT(bdi) __WB_COMPLETION_INIT(&(bdi)->wb_waitq)
+
+#define DEFINE_WB_COMPLETION(cmpl, bdi) \
+ struct wb_completion cmpl = WB_COMPLETION_INIT(bdi)
+
/*
* For cgroup writeback, multiple wb's may map to the same blkcg. Those
* wb's can operate mostly independently but should share the congested
@@ -165,6 +186,8 @@ struct bdi_writeback {
};
struct backing_dev_info {
+ u64 id;
+ struct rb_node rb_node; /* keyed by ->id */
struct list_head bdi_list;
unsigned long ra_pages; /* max readahead in PAGE_SIZE units */
unsigned long io_pages; /* max allowed IO size */
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 35b31d176f74..97967ce06de3 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -24,6 +24,7 @@ static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi)
return bdi;
}
+struct backing_dev_info *bdi_get_by_id(u64 id);
void bdi_put(struct backing_dev_info *bdi);
__printf(2, 3)
@@ -44,6 +45,8 @@ void wb_start_background_writeback(struct bdi_writeback *wb);
void wb_workfn(struct work_struct *work);
void wb_wakeup_delayed(struct bdi_writeback *wb);
+void wb_wait_for_completion(struct wb_completion *done);
+
extern spinlock_t bdi_lock;
extern struct list_head bdi_list;
@@ -227,6 +230,8 @@ static inline int bdi_sched_wait(void *word)
struct bdi_writeback_congested *
wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp);
void wb_congested_put(struct bdi_writeback_congested *congested);
+struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi,
+ struct cgroup_subsys_state *memcg_css);
struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi,
struct cgroup_subsys_state *memcg_css,
gfp_t gfp);
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 12811091fd50..bed9e43f9426 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -149,7 +149,8 @@ typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp);
typedef void (blkcg_pol_init_cpd_fn)(struct blkcg_policy_data *cpd);
typedef void (blkcg_pol_free_cpd_fn)(struct blkcg_policy_data *cpd);
typedef void (blkcg_pol_bind_cpd_fn)(struct blkcg_policy_data *cpd);
-typedef struct blkg_policy_data *(blkcg_pol_alloc_pd_fn)(gfp_t gfp, int node);
+typedef struct blkg_policy_data *(blkcg_pol_alloc_pd_fn)(gfp_t gfp,
+ struct request_queue *q, struct blkcg *blkcg);
typedef void (blkcg_pol_init_pd_fn)(struct blkg_policy_data *pd);
typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd);
typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd);
@@ -233,6 +234,7 @@ struct blkg_conf_ctx {
char *body;
};
+struct gendisk *blkcg_conf_get_disk(char **inputp);
int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
char *input, struct blkg_conf_ctx *ctx);
void blkg_conf_finish(struct blkg_conf_ctx *ctx);
@@ -375,7 +377,7 @@ static inline struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg,
* @q: request_queue of interest
*
* Lookup blkg for the @blkcg - @q pair. This function should be called
- * under RCU read loc.
+ * under RCU read lock.
*/
static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg,
struct request_queue *q)
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 3fa1fa59f9b2..0bf056de5cc3 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -140,6 +140,7 @@ typedef int (poll_fn)(struct blk_mq_hw_ctx *);
typedef int (map_queues_fn)(struct blk_mq_tag_set *set);
typedef bool (busy_fn)(struct request_queue *);
typedef void (complete_fn)(struct request *);
+typedef void (cleanup_rq_fn)(struct request *);
struct blk_mq_ops {
@@ -201,6 +202,12 @@ struct blk_mq_ops {
void (*initialize_rq_fn)(struct request *rq);
/*
+ * Called before freeing one request which isn't completed yet,
+ * and usually for freeing the driver private data
+ */
+ cleanup_rq_fn *cleanup_rq;
+
+ /*
* If set, returns whether or not this queue currently is busy
*/
busy_fn *busy;
@@ -241,12 +248,12 @@ enum {
struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *);
struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
- struct request_queue *q);
+ struct request_queue *q,
+ bool elevator_init);
struct request_queue *blk_mq_init_sq_queue(struct blk_mq_tag_set *set,
const struct blk_mq_ops *ops,
unsigned int queue_depth,
unsigned int set_flags);
-int blk_mq_register_dev(struct device *, struct request_queue *);
void blk_mq_unregister_dev(struct device *, struct request_queue *);
int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set);
@@ -296,6 +303,7 @@ static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag)
int blk_mq_request_started(struct request *rq);
+int blk_mq_request_completed(struct request *rq);
void blk_mq_start_request(struct request *rq);
void blk_mq_end_request(struct request *rq, blk_status_t error);
void __blk_mq_end_request(struct request *rq, blk_status_t error);
@@ -304,7 +312,6 @@ void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list);
void blk_mq_kick_requeue_list(struct request_queue *q);
void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs);
bool blk_mq_complete_request(struct request *rq);
-void blk_mq_complete_request_sync(struct request *rq);
bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list,
struct bio *bio, unsigned int nr_segs);
bool blk_mq_queue_stopped(struct request_queue *q);
@@ -321,6 +328,7 @@ bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
void blk_mq_run_hw_queues(struct request_queue *q, bool async);
void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
busy_tag_iter_fn *fn, void *priv);
+void blk_mq_tagset_wait_completed_request(struct blk_mq_tag_set *tagset);
void blk_mq_freeze_queue(struct request_queue *q);
void blk_mq_unfreeze_queue(struct request_queue *q);
void blk_freeze_queue_start(struct request_queue *q);
@@ -366,4 +374,10 @@ static inline blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx,
BLK_QC_T_INTERNAL;
}
+static inline void blk_mq_cleanup_rq(struct request *rq)
+{
+ if (rq->q->mq_ops->cleanup_rq)
+ rq->q->mq_ops->cleanup_rq(rq);
+}
+
#endif
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 1b1fa1557e68..d688b96d1d63 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -169,6 +169,9 @@ struct bio {
*/
struct blkcg_gq *bi_blkg;
struct bio_issue bi_issue;
+#ifdef CONFIG_BLK_CGROUP_IOCOST
+ u64 bi_iocost_cost;
+#endif
#endif
union {
#if defined(CONFIG_BLK_DEV_INTEGRITY)
@@ -209,6 +212,7 @@ enum {
BIO_BOUNCED, /* bio is a bounce bio */
BIO_USER_MAPPED, /* contains user pages */
BIO_NULL_MAPPED, /* contains invalid user pages */
+ BIO_WORKINGSET, /* contains userspace workingset pages */
BIO_QUIET, /* Make BIO Quiet */
BIO_CHAIN, /* chained bio, ->bi_remaining in effect */
BIO_REFFED, /* bio has elevated ->bi_cnt */
@@ -282,6 +286,8 @@ enum req_opf {
REQ_OP_ZONE_RESET = 6,
/* write the same sector many times */
REQ_OP_WRITE_SAME = 7,
+ /* reset all the zone present on the device */
+ REQ_OP_ZONE_RESET_ALL = 8,
/* write the zero filled sector many times */
REQ_OP_WRITE_ZEROES = 9,
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 1ef375dafb1c..3094f2d513b2 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -194,7 +194,11 @@ struct request {
struct gendisk *rq_disk;
struct hd_struct *part;
- /* Time that I/O was submitted to the kernel. */
+#ifdef CONFIG_BLK_RQ_ALLOC_TIME
+ /* Time that the first bio started allocating this request. */
+ u64 alloc_time_ns;
+#endif
+ /* Time that this request was allocated for this IO. */
u64 start_time_ns;
/* Time that I/O was submitted to the device. */
u64 io_start_time_ns;
@@ -202,9 +206,12 @@ struct request {
#ifdef CONFIG_BLK_WBT
unsigned short wbt_flags;
#endif
-#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
- unsigned short throtl_size;
-#endif
+ /*
+ * rq sectors used for blk stats. It has the same value
+ * with blk_rq_sectors(rq), except that it never be zeroed
+ * by completion.
+ */
+ unsigned short stats_sectors;
/*
* Number of scatter-gather DMA addr+len pairs after
@@ -391,10 +398,6 @@ static inline int blkdev_reset_zones_ioctl(struct block_device *bdev,
#endif /* CONFIG_BLK_DEV_ZONED */
struct request_queue {
- /*
- * Together with queue_head for cacheline sharing
- */
- struct list_head queue_head;
struct request *last_merge;
struct elevator_queue *elevator;
@@ -496,6 +499,8 @@ struct request_queue {
struct queue_limits limits;
+ unsigned int required_elevator_features;
+
#ifdef CONFIG_BLK_DEV_ZONED
/*
* Zoned block device information for request dispatch control.
@@ -539,6 +544,7 @@ struct request_queue {
struct delayed_work requeue_work;
struct mutex sysfs_lock;
+ struct mutex sysfs_dir_lock;
/*
* for reusing dead hctx instance in case of updating
@@ -611,6 +617,8 @@ struct request_queue {
#define QUEUE_FLAG_SCSI_PASSTHROUGH 23 /* queue supports SCSI commands */
#define QUEUE_FLAG_QUIESCED 24 /* queue has been quiesced */
#define QUEUE_FLAG_PCI_P2PDMA 25 /* device supports PCI p2p requests */
+#define QUEUE_FLAG_ZONE_RESETALL 26 /* supports Zone Reset All */
+#define QUEUE_FLAG_RQ_ALLOC_TIME 27 /* record rq->alloc_time_ns */
#define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \
(1 << QUEUE_FLAG_SAME_COMP))
@@ -630,6 +638,8 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
#define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags)
#define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags)
#define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags)
+#define blk_queue_zone_resetall(q) \
+ test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags)
#define blk_queue_secure_erase(q) \
(test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags))
#define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags)
@@ -637,6 +647,12 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
test_bit(QUEUE_FLAG_SCSI_PASSTHROUGH, &(q)->queue_flags)
#define blk_queue_pci_p2pdma(q) \
test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags)
+#ifdef CONFIG_BLK_RQ_ALLOC_TIME
+#define blk_queue_rq_alloc_time(q) \
+ test_bit(QUEUE_FLAG_RQ_ALLOC_TIME, &(q)->queue_flags)
+#else
+#define blk_queue_rq_alloc_time(q) false
+#endif
#define blk_noretry_request(rq) \
((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \
@@ -644,6 +660,7 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
#define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags)
#define blk_queue_pm_only(q) atomic_read(&(q)->pm_only)
#define blk_queue_fua(q) test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags)
+#define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags)
extern void blk_set_pm_only(struct request_queue *q);
extern void blk_clear_pm_only(struct request_queue *q);
@@ -903,6 +920,7 @@ static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
* blk_rq_err_bytes() : bytes left till the next error boundary
* blk_rq_sectors() : sectors left in the entire request
* blk_rq_cur_sectors() : sectors left in the current segment
+ * blk_rq_stats_sectors() : sectors of the entire request used for stats
*/
static inline sector_t blk_rq_pos(const struct request *rq)
{
@@ -931,6 +949,11 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT;
}
+static inline unsigned int blk_rq_stats_sectors(const struct request *rq)
+{
+ return rq->stats_sectors;
+}
+
#ifdef CONFIG_BLK_DEV_ZONED
static inline unsigned int blk_rq_zone_no(struct request *rq)
{
@@ -1085,6 +1108,8 @@ extern void blk_queue_dma_alignment(struct request_queue *, int);
extern void blk_queue_update_dma_alignment(struct request_queue *, int);
extern void blk_queue_rq_timeout(struct request_queue *, unsigned int);
extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua);
+extern void blk_queue_required_elevator_features(struct request_queue *q,
+ unsigned int features);
/*
* Number of physical segments as sent to the device.
@@ -1232,42 +1257,42 @@ enum blk_default_limits {
BLK_SEG_BOUNDARY_MASK = 0xFFFFFFFFUL,
};
-static inline unsigned long queue_segment_boundary(struct request_queue *q)
+static inline unsigned long queue_segment_boundary(const struct request_queue *q)
{
return q->limits.seg_boundary_mask;
}
-static inline unsigned long queue_virt_boundary(struct request_queue *q)
+static inline unsigned long queue_virt_boundary(const struct request_queue *q)
{
return q->limits.virt_boundary_mask;
}
-static inline unsigned int queue_max_sectors(struct request_queue *q)
+static inline unsigned int queue_max_sectors(const struct request_queue *q)
{
return q->limits.max_sectors;
}
-static inline unsigned int queue_max_hw_sectors(struct request_queue *q)
+static inline unsigned int queue_max_hw_sectors(const struct request_queue *q)
{
return q->limits.max_hw_sectors;
}
-static inline unsigned short queue_max_segments(struct request_queue *q)
+static inline unsigned short queue_max_segments(const struct request_queue *q)
{
return q->limits.max_segments;
}
-static inline unsigned short queue_max_discard_segments(struct request_queue *q)
+static inline unsigned short queue_max_discard_segments(const struct request_queue *q)
{
return q->limits.max_discard_segments;
}
-static inline unsigned int queue_max_segment_size(struct request_queue *q)
+static inline unsigned int queue_max_segment_size(const struct request_queue *q)
{
return q->limits.max_segment_size;
}
-static inline unsigned short queue_logical_block_size(struct request_queue *q)
+static inline unsigned short queue_logical_block_size(const struct request_queue *q)
{
int retval = 512;
@@ -1282,7 +1307,7 @@ static inline unsigned short bdev_logical_block_size(struct block_device *bdev)
return queue_logical_block_size(bdev_get_queue(bdev));
}
-static inline unsigned int queue_physical_block_size(struct request_queue *q)
+static inline unsigned int queue_physical_block_size(const struct request_queue *q)
{
return q->limits.physical_block_size;
}
@@ -1292,7 +1317,7 @@ static inline unsigned int bdev_physical_block_size(struct block_device *bdev)
return queue_physical_block_size(bdev_get_queue(bdev));
}
-static inline unsigned int queue_io_min(struct request_queue *q)
+static inline unsigned int queue_io_min(const struct request_queue *q)
{
return q->limits.io_min;
}
@@ -1302,7 +1327,7 @@ static inline int bdev_io_min(struct block_device *bdev)
return queue_io_min(bdev_get_queue(bdev));
}
-static inline unsigned int queue_io_opt(struct request_queue *q)
+static inline unsigned int queue_io_opt(const struct request_queue *q)
{
return q->limits.io_opt;
}
@@ -1312,7 +1337,7 @@ static inline int bdev_io_opt(struct block_device *bdev)
return queue_io_opt(bdev_get_queue(bdev));
}
-static inline int queue_alignment_offset(struct request_queue *q)
+static inline int queue_alignment_offset(const struct request_queue *q)
{
if (q->limits.misaligned)
return -1;
@@ -1342,7 +1367,7 @@ static inline int bdev_alignment_offset(struct block_device *bdev)
return q->limits.alignment_offset;
}
-static inline int queue_discard_alignment(struct request_queue *q)
+static inline int queue_discard_alignment(const struct request_queue *q)
{
if (q->limits.discard_misaligned)
return -1;
@@ -1432,7 +1457,7 @@ static inline sector_t bdev_zone_sectors(struct block_device *bdev)
return 0;
}
-static inline int queue_dma_alignment(struct request_queue *q)
+static inline int queue_dma_alignment(const struct request_queue *q)
{
return q ? q->dma_alignment : 511;
}
@@ -1543,7 +1568,7 @@ static inline void blk_queue_max_integrity_segments(struct request_queue *q,
}
static inline unsigned short
-queue_max_integrity_segments(struct request_queue *q)
+queue_max_integrity_segments(const struct request_queue *q)
{
return q->limits.max_integrity_segments;
}
@@ -1626,7 +1651,7 @@ static inline void blk_queue_max_integrity_segments(struct request_queue *q,
unsigned int segs)
{
}
-static inline unsigned short queue_max_integrity_segments(struct request_queue *q)
+static inline unsigned short queue_max_integrity_segments(const struct request_queue *q)
{
return 0;
}
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 1dd014c9c87b..901bda352dcb 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -76,6 +76,7 @@ struct elevator_type
struct elv_fs_entry *elevator_attrs;
const char *elevator_name;
const char *elevator_alias;
+ const unsigned int elevator_features;
struct module *elevator_owner;
#ifdef CONFIG_BLK_DEBUG_FS
const struct blk_mq_debugfs_attr *queue_debugfs_attrs;
@@ -165,5 +166,12 @@ extern struct request *elv_rb_find(struct rb_root *, sector_t);
#define rq_entry_fifo(ptr) list_entry((ptr), struct request, queuelist)
#define rq_fifo_clear(rq) list_del_init(&(rq)->queuelist)
+/*
+ * Elevator features.
+ */
+
+/* Supports zoned block devices sequential write constraint */
+#define ELEVATOR_F_ZBD_SEQ_WRITE (1U << 0)
+
#endif /* CONFIG_BLOCK */
#endif
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index 4d0d5655c7b2..ee8ec2e68055 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -88,8 +88,7 @@ typedef int (nvm_op_bb_tbl_fn)(struct nvm_dev *, struct ppa_addr, u8 *);
typedef int (nvm_op_set_bb_fn)(struct nvm_dev *, struct ppa_addr *, int, int);
typedef int (nvm_get_chk_meta_fn)(struct nvm_dev *, sector_t, int,
struct nvm_chk_meta *);
-typedef int (nvm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *);
-typedef int (nvm_submit_io_sync_fn)(struct nvm_dev *, struct nvm_rq *);
+typedef int (nvm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *, void *);
typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *, int);
typedef void (nvm_destroy_dma_pool_fn)(void *);
typedef void *(nvm_dev_dma_alloc_fn)(struct nvm_dev *, void *, gfp_t,
@@ -104,7 +103,6 @@ struct nvm_dev_ops {
nvm_get_chk_meta_fn *get_chk_meta;
nvm_submit_io_fn *submit_io;
- nvm_submit_io_sync_fn *submit_io_sync;
nvm_create_dma_pool_fn *create_dma_pool;
nvm_destroy_dma_pool_fn *destroy_dma_pool;
@@ -682,8 +680,8 @@ extern int nvm_get_chunk_meta(struct nvm_tgt_dev *, struct ppa_addr,
int, struct nvm_chk_meta *);
extern int nvm_set_chunk_meta(struct nvm_tgt_dev *, struct ppa_addr *,
int, int);
-extern int nvm_submit_io(struct nvm_tgt_dev *, struct nvm_rq *);
-extern int nvm_submit_io_sync(struct nvm_tgt_dev *, struct nvm_rq *);
+extern int nvm_submit_io(struct nvm_tgt_dev *, struct nvm_rq *, void *);
+extern int nvm_submit_io_sync(struct nvm_tgt_dev *, struct nvm_rq *, void *);
extern void nvm_end_io(struct nvm_rq *);
#else /* CONFIG_NVM */
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 2cd4359cb38c..ad8f1a397ae4 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -184,6 +184,23 @@ struct memcg_padding {
#endif
/*
+ * Remember four most recent foreign writebacks with dirty pages in this
+ * cgroup. Inode sharing is expected to be uncommon and, even if we miss
+ * one in a given round, we're likely to catch it later if it keeps
+ * foreign-dirtying, so a fairly low count should be enough.
+ *
+ * See mem_cgroup_track_foreign_dirty_slowpath() for details.
+ */
+#define MEMCG_CGWB_FRN_CNT 4
+
+struct memcg_cgwb_frn {
+ u64 bdi_id; /* bdi->id of the foreign inode */
+ int memcg_id; /* memcg->css.id of foreign inode */
+ u64 at; /* jiffies_64 at the time of dirtying */
+ struct wb_completion done; /* tracks in-flight foreign writebacks */
+};
+
+/*
* The memory controller data structure. The memory controller controls both
* page cache and RSS per cgroup. We would eventually like to provide
* statistics based on the statistics developed by Rik Van Riel for clock-pro,
@@ -307,6 +324,7 @@ struct mem_cgroup {
#ifdef CONFIG_CGROUP_WRITEBACK
struct list_head cgwb_list;
struct wb_domain cgwb_domain;
+ struct memcg_cgwb_frn cgwb_frn[MEMCG_CGWB_FRN_CNT];
#endif
/* List of events which userspace want to receive */
@@ -1237,6 +1255,18 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
unsigned long *pheadroom, unsigned long *pdirty,
unsigned long *pwriteback);
+void mem_cgroup_track_foreign_dirty_slowpath(struct page *page,
+ struct bdi_writeback *wb);
+
+static inline void mem_cgroup_track_foreign_dirty(struct page *page,
+ struct bdi_writeback *wb)
+{
+ if (unlikely(&page->mem_cgroup->css != wb->memcg_css))
+ mem_cgroup_track_foreign_dirty_slowpath(page, wb);
+}
+
+void mem_cgroup_flush_foreign(struct bdi_writeback *wb);
+
#else /* CONFIG_CGROUP_WRITEBACK */
static inline struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb)
@@ -1252,6 +1282,15 @@ static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb,
{
}
+static inline void mem_cgroup_track_foreign_dirty(struct page *page,
+ struct bdi_writeback *wb)
+{
+}
+
+static inline void mem_cgroup_flush_foreign(struct bdi_writeback *wb)
+{
+}
+
#endif /* CONFIG_CGROUP_WRITEBACK */
struct sock;
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 01aa6a6c241d..f61d6906e59d 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -140,6 +140,7 @@ enum {
* Submission and Completion Queue Entry Sizes for the NVM command set.
* (In bytes and specified as a power of two (2^n)).
*/
+#define NVME_ADM_SQES 6
#define NVME_NVM_IOSQES 6
#define NVME_NVM_IOCQES 4
@@ -814,6 +815,7 @@ enum nvme_admin_opcode {
nvme_admin_security_send = 0x81,
nvme_admin_security_recv = 0x82,
nvme_admin_sanitize_nvm = 0x84,
+ nvme_admin_get_lba_status = 0x86,
};
#define nvme_admin_opcode_name(opcode) { opcode, #opcode }
@@ -840,7 +842,8 @@ enum nvme_admin_opcode {
nvme_admin_opcode_name(nvme_admin_format_nvm), \
nvme_admin_opcode_name(nvme_admin_security_send), \
nvme_admin_opcode_name(nvme_admin_security_recv), \
- nvme_admin_opcode_name(nvme_admin_sanitize_nvm))
+ nvme_admin_opcode_name(nvme_admin_sanitize_nvm), \
+ nvme_admin_opcode_name(nvme_admin_get_lba_status))
enum {
NVME_QUEUE_PHYS_CONTIG = (1 << 0),
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 8945aac31392..a19d845dd7eb 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -217,6 +217,8 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
void wbc_detach_inode(struct writeback_control *wbc);
void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page,
size_t bytes);
+int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, unsigned long nr_pages,
+ enum wb_reason reason, struct wb_completion *done);
void cgroup_writeback_umount(void);
/**
diff --git a/include/trace/events/iocost.h b/include/trace/events/iocost.h
new file mode 100644
index 000000000000..7ecaa65b7106
--- /dev/null
+++ b/include/trace/events/iocost.h
@@ -0,0 +1,178 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM iocost
+
+struct ioc;
+struct ioc_now;
+struct ioc_gq;
+
+#if !defined(_TRACE_BLK_IOCOST_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_BLK_IOCOST_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(iocost_iocg_activate,
+
+ TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,
+ u64 last_period, u64 cur_period, u64 vtime),
+
+ TP_ARGS(iocg, path, now, last_period, cur_period, vtime),
+
+ TP_STRUCT__entry (
+ __string(devname, ioc_name(iocg->ioc))
+ __string(cgroup, path)
+ __field(u64, now)
+ __field(u64, vnow)
+ __field(u64, vrate)
+ __field(u64, last_period)
+ __field(u64, cur_period)
+ __field(u64, last_vtime)
+ __field(u64, vtime)
+ __field(u32, weight)
+ __field(u32, inuse)
+ __field(u64, hweight_active)
+ __field(u64, hweight_inuse)
+ ),
+
+ TP_fast_assign(
+ __assign_str(devname, ioc_name(iocg->ioc));
+ __assign_str(cgroup, path);
+ __entry->now = now->now;
+ __entry->vnow = now->vnow;
+ __entry->vrate = now->vrate;
+ __entry->last_period = last_period;
+ __entry->cur_period = cur_period;
+ __entry->last_vtime = iocg->last_vtime;
+ __entry->vtime = vtime;
+ __entry->weight = iocg->weight;
+ __entry->inuse = iocg->inuse;
+ __entry->hweight_active = iocg->hweight_active;
+ __entry->hweight_inuse = iocg->hweight_inuse;
+ ),
+
+ TP_printk("[%s:%s] now=%llu:%llu vrate=%llu "
+ "period=%llu->%llu vtime=%llu->%llu "
+ "weight=%u/%u hweight=%llu/%llu",
+ __get_str(devname), __get_str(cgroup),
+ __entry->now, __entry->vnow, __entry->vrate,
+ __entry->last_period, __entry->cur_period,
+ __entry->last_vtime, __entry->vtime,
+ __entry->inuse, __entry->weight,
+ __entry->hweight_inuse, __entry->hweight_active
+ )
+);
+
+DECLARE_EVENT_CLASS(iocg_inuse_update,
+
+ TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,
+ u32 old_inuse, u32 new_inuse,
+ u64 old_hw_inuse, u64 new_hw_inuse),
+
+ TP_ARGS(iocg, path, now, old_inuse, new_inuse,
+ old_hw_inuse, new_hw_inuse),
+
+ TP_STRUCT__entry (
+ __string(devname, ioc_name(iocg->ioc))
+ __string(cgroup, path)
+ __field(u64, now)
+ __field(u32, old_inuse)
+ __field(u32, new_inuse)
+ __field(u64, old_hweight_inuse)
+ __field(u64, new_hweight_inuse)
+ ),
+
+ TP_fast_assign(
+ __assign_str(devname, ioc_name(iocg->ioc));
+ __assign_str(cgroup, path);
+ __entry->now = now->now;
+ __entry->old_inuse = old_inuse;
+ __entry->new_inuse = new_inuse;
+ __entry->old_hweight_inuse = old_hw_inuse;
+ __entry->new_hweight_inuse = new_hw_inuse;
+ ),
+
+ TP_printk("[%s:%s] now=%llu inuse=%u->%u hw_inuse=%llu->%llu",
+ __get_str(devname), __get_str(cgroup), __entry->now,
+ __entry->old_inuse, __entry->new_inuse,
+ __entry->old_hweight_inuse, __entry->new_hweight_inuse
+ )
+);
+
+DEFINE_EVENT(iocg_inuse_update, iocost_inuse_takeback,
+
+ TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,
+ u32 old_inuse, u32 new_inuse,
+ u64 old_hw_inuse, u64 new_hw_inuse),
+
+ TP_ARGS(iocg, path, now, old_inuse, new_inuse,
+ old_hw_inuse, new_hw_inuse)
+);
+
+DEFINE_EVENT(iocg_inuse_update, iocost_inuse_giveaway,
+
+ TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,
+ u32 old_inuse, u32 new_inuse,
+ u64 old_hw_inuse, u64 new_hw_inuse),
+
+ TP_ARGS(iocg, path, now, old_inuse, new_inuse,
+ old_hw_inuse, new_hw_inuse)
+);
+
+DEFINE_EVENT(iocg_inuse_update, iocost_inuse_reset,
+
+ TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,
+ u32 old_inuse, u32 new_inuse,
+ u64 old_hw_inuse, u64 new_hw_inuse),
+
+ TP_ARGS(iocg, path, now, old_inuse, new_inuse,
+ old_hw_inuse, new_hw_inuse)
+);
+
+TRACE_EVENT(iocost_ioc_vrate_adj,
+
+ TP_PROTO(struct ioc *ioc, u64 new_vrate, u32 (*missed_ppm)[2],
+ u32 rq_wait_pct, int nr_lagging, int nr_shortages,
+ int nr_surpluses),
+
+ TP_ARGS(ioc, new_vrate, missed_ppm, rq_wait_pct, nr_lagging, nr_shortages,
+ nr_surpluses),
+
+ TP_STRUCT__entry (
+ __string(devname, ioc_name(ioc))
+ __field(u64, old_vrate)
+ __field(u64, new_vrate)
+ __field(int, busy_level)
+ __field(u32, read_missed_ppm)
+ __field(u32, write_missed_ppm)
+ __field(u32, rq_wait_pct)
+ __field(int, nr_lagging)
+ __field(int, nr_shortages)
+ __field(int, nr_surpluses)
+ ),
+
+ TP_fast_assign(
+ __assign_str(devname, ioc_name(ioc));
+ __entry->old_vrate = atomic64_read(&ioc->vtime_rate);;
+ __entry->new_vrate = new_vrate;
+ __entry->busy_level = ioc->busy_level;
+ __entry->read_missed_ppm = (*missed_ppm)[READ];
+ __entry->write_missed_ppm = (*missed_ppm)[WRITE];
+ __entry->rq_wait_pct = rq_wait_pct;
+ __entry->nr_lagging = nr_lagging;
+ __entry->nr_shortages = nr_shortages;
+ __entry->nr_surpluses = nr_surpluses;
+ ),
+
+ TP_printk("[%s] vrate=%llu->%llu busy=%d missed_ppm=%u:%u rq_wait_pct=%u lagging=%d shortages=%d surpluses=%d",
+ __get_str(devname), __entry->old_vrate, __entry->new_vrate,
+ __entry->busy_level,
+ __entry->read_missed_ppm, __entry->write_missed_ppm,
+ __entry->rq_wait_pct, __entry->nr_lagging, __entry->nr_shortages,
+ __entry->nr_surpluses
+ )
+);
+
+#endif /* _TRACE_BLK_IOCOST_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index aa7f3aeac740..3a27335fce2c 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -176,6 +176,132 @@ static inline unsigned int __trace_wbc_assign_cgroup(struct writeback_control *w
#endif /* CONFIG_CGROUP_WRITEBACK */
#endif /* CREATE_TRACE_POINTS */
+#ifdef CONFIG_CGROUP_WRITEBACK
+TRACE_EVENT(inode_foreign_history,
+
+ TP_PROTO(struct inode *inode, struct writeback_control *wbc,
+ unsigned int history),
+
+ TP_ARGS(inode, wbc, history),
+
+ TP_STRUCT__entry(
+ __array(char, name, 32)
+ __field(unsigned long, ino)
+ __field(unsigned int, cgroup_ino)
+ __field(unsigned int, history)
+ ),
+
+ TP_fast_assign(
+ strncpy(__entry->name, dev_name(inode_to_bdi(inode)->dev), 32);
+ __entry->ino = inode->i_ino;
+ __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc);
+ __entry->history = history;
+ ),
+
+ TP_printk("bdi %s: ino=%lu cgroup_ino=%u history=0x%x",
+ __entry->name,
+ __entry->ino,
+ __entry->cgroup_ino,
+ __entry->history
+ )
+);
+
+TRACE_EVENT(inode_switch_wbs,
+
+ TP_PROTO(struct inode *inode, struct bdi_writeback *old_wb,
+ struct bdi_writeback *new_wb),
+
+ TP_ARGS(inode, old_wb, new_wb),
+
+ TP_STRUCT__entry(
+ __array(char, name, 32)
+ __field(unsigned long, ino)
+ __field(unsigned int, old_cgroup_ino)
+ __field(unsigned int, new_cgroup_ino)
+ ),
+
+ TP_fast_assign(
+ strncpy(__entry->name, dev_name(old_wb->bdi->dev), 32);
+ __entry->ino = inode->i_ino;
+ __entry->old_cgroup_ino = __trace_wb_assign_cgroup(old_wb);
+ __entry->new_cgroup_ino = __trace_wb_assign_cgroup(new_wb);
+ ),
+
+ TP_printk("bdi %s: ino=%lu old_cgroup_ino=%u new_cgroup_ino=%u",
+ __entry->name,
+ __entry->ino,
+ __entry->old_cgroup_ino,
+ __entry->new_cgroup_ino
+ )
+);
+
+TRACE_EVENT(track_foreign_dirty,
+
+ TP_PROTO(struct page *page, struct bdi_writeback *wb),
+
+ TP_ARGS(page, wb),
+
+ TP_STRUCT__entry(
+ __array(char, name, 32)
+ __field(u64, bdi_id)
+ __field(unsigned long, ino)
+ __field(unsigned int, memcg_id)
+ __field(unsigned int, cgroup_ino)
+ __field(unsigned int, page_cgroup_ino)
+ ),
+
+ TP_fast_assign(
+ struct address_space *mapping = page_mapping(page);
+ struct inode *inode = mapping ? mapping->host : NULL;
+
+ strncpy(__entry->name, dev_name(wb->bdi->dev), 32);
+ __entry->bdi_id = wb->bdi->id;
+ __entry->ino = inode ? inode->i_ino : 0;
+ __entry->memcg_id = wb->memcg_css->id;
+ __entry->cgroup_ino = __trace_wb_assign_cgroup(wb);
+ __entry->page_cgroup_ino = page->mem_cgroup->css.cgroup->kn->id.ino;
+ ),
+
+ TP_printk("bdi %s[%llu]: ino=%lu memcg_id=%u cgroup_ino=%u page_cgroup_ino=%u",
+ __entry->name,
+ __entry->bdi_id,
+ __entry->ino,
+ __entry->memcg_id,
+ __entry->cgroup_ino,
+ __entry->page_cgroup_ino
+ )
+);
+
+TRACE_EVENT(flush_foreign,
+
+ TP_PROTO(struct bdi_writeback *wb, unsigned int frn_bdi_id,
+ unsigned int frn_memcg_id),
+
+ TP_ARGS(wb, frn_bdi_id, frn_memcg_id),
+
+ TP_STRUCT__entry(
+ __array(char, name, 32)
+ __field(unsigned int, cgroup_ino)
+ __field(unsigned int, frn_bdi_id)
+ __field(unsigned int, frn_memcg_id)
+ ),
+
+ TP_fast_assign(
+ strncpy(__entry->name, dev_name(wb->bdi->dev), 32);
+ __entry->cgroup_ino = __trace_wb_assign_cgroup(wb);
+ __entry->frn_bdi_id = frn_bdi_id;
+ __entry->frn_memcg_id = frn_memcg_id;
+ ),
+
+ TP_printk("bdi %s: cgroup_ino=%u frn_bdi_id=%u frn_memcg_id=%u",
+ __entry->name,
+ __entry->cgroup_ino,
+ __entry->frn_bdi_id,
+ __entry->frn_memcg_id
+ )
+);
+#endif
+
DECLARE_EVENT_CLASS(writeback_write_inode_template,
TP_PROTO(struct inode *inode, struct writeback_control *wbc),
diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h
index b0d15c73f6d7..1f2d8c81f0e0 100644
--- a/include/uapi/linux/raid/md_p.h
+++ b/include/uapi/linux/raid/md_p.h
@@ -329,6 +329,7 @@ struct mdp_superblock_1 {
#define MD_FEATURE_JOURNAL 512 /* support write cache */
#define MD_FEATURE_PPL 1024 /* support PPL */
#define MD_FEATURE_MULTIPLE_PPLS 2048 /* support for multiple PPLs */
+#define MD_FEATURE_RAID0_LAYOUT 4096 /* layout is meaningful for RAID0 */
#define MD_FEATURE_ALL (MD_FEATURE_BITMAP_OFFSET \
|MD_FEATURE_RECOVERY_OFFSET \
|MD_FEATURE_RESHAPE_ACTIVE \
@@ -341,6 +342,7 @@ struct mdp_superblock_1 {
|MD_FEATURE_JOURNAL \
|MD_FEATURE_PPL \
|MD_FEATURE_MULTIPLE_PPLS \
+ |MD_FEATURE_RAID0_LAYOUT \
)
struct r5l_payload_header {
diff --git a/lib/sg_split.c b/lib/sg_split.c
index 9982c63d1063..60a0babebf2e 100644
--- a/lib/sg_split.c
+++ b/lib/sg_split.c
@@ -176,11 +176,13 @@ int sg_split(struct scatterlist *in, const int in_mapped_nents,
* The order of these 3 calls is important and should be kept.
*/
sg_split_phys(splitters, nb_splits);
- ret = sg_calculate_split(in, in_mapped_nents, nb_splits, skip,
- split_sizes, splitters, true);
- if (ret < 0)
- goto err;
- sg_split_mapped(splitters, nb_splits);
+ if (in_mapped_nents) {
+ ret = sg_calculate_split(in, in_mapped_nents, nb_splits, skip,
+ split_sizes, splitters, true);
+ if (ret < 0)
+ goto err;
+ sg_split_mapped(splitters, nb_splits);
+ }
for (i = 0; i < nb_splits; i++) {
out[i] = splitters[i].out_sg;
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index e8e89158adec..d9daa3e422d0 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0-only
#include <linux/wait.h>
+#include <linux/rbtree.h>
#include <linux/backing-dev.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
@@ -22,10 +23,12 @@ EXPORT_SYMBOL_GPL(noop_backing_dev_info);
static struct class *bdi_class;
/*
- * bdi_lock protects updates to bdi_list. bdi_list has RCU reader side
- * locking.
+ * bdi_lock protects bdi_tree and updates to bdi_list. bdi_list has RCU
+ * reader side locking.
*/
DEFINE_SPINLOCK(bdi_lock);
+static u64 bdi_id_cursor;
+static struct rb_root bdi_tree = RB_ROOT;
LIST_HEAD(bdi_list);
/* bdi_wq serves all asynchronous writeback tasks */
@@ -615,13 +618,12 @@ out_put:
}
/**
- * wb_get_create - get wb for a given memcg, create if necessary
+ * wb_get_lookup - get wb for a given memcg
* @bdi: target bdi
* @memcg_css: cgroup_subsys_state of the target memcg (must have positive ref)
- * @gfp: allocation mask to use
*
- * Try to get the wb for @memcg_css on @bdi. If it doesn't exist, try to
- * create one. The returned wb has its refcount incremented.
+ * Try to get the wb for @memcg_css on @bdi. The returned wb has its
+ * refcount incremented.
*
* This function uses css_get() on @memcg_css and thus expects its refcnt
* to be positive on invocation. IOW, rcu_read_lock() protection on
@@ -638,6 +640,39 @@ out_put:
* each lookup. On mismatch, the existing wb is discarded and a new one is
* created.
*/
+struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi,
+ struct cgroup_subsys_state *memcg_css)
+{
+ struct bdi_writeback *wb;
+
+ if (!memcg_css->parent)
+ return &bdi->wb;
+
+ rcu_read_lock();
+ wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id);
+ if (wb) {
+ struct cgroup_subsys_state *blkcg_css;
+
+ /* see whether the blkcg association has changed */
+ blkcg_css = cgroup_get_e_css(memcg_css->cgroup, &io_cgrp_subsys);
+ if (unlikely(wb->blkcg_css != blkcg_css || !wb_tryget(wb)))
+ wb = NULL;
+ css_put(blkcg_css);
+ }
+ rcu_read_unlock();
+
+ return wb;
+}
+
+/**
+ * wb_get_create - get wb for a given memcg, create if necessary
+ * @bdi: target bdi
+ * @memcg_css: cgroup_subsys_state of the target memcg (must have positive ref)
+ * @gfp: allocation mask to use
+ *
+ * Try to get the wb for @memcg_css on @bdi. If it doesn't exist, try to
+ * create one. See wb_get_lookup() for more details.
+ */
struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi,
struct cgroup_subsys_state *memcg_css,
gfp_t gfp)
@@ -650,20 +685,7 @@ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi,
return &bdi->wb;
do {
- rcu_read_lock();
- wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id);
- if (wb) {
- struct cgroup_subsys_state *blkcg_css;
-
- /* see whether the blkcg association has changed */
- blkcg_css = cgroup_get_e_css(memcg_css->cgroup,
- &io_cgrp_subsys);
- if (unlikely(wb->blkcg_css != blkcg_css ||
- !wb_tryget(wb)))
- wb = NULL;
- css_put(blkcg_css);
- }
- rcu_read_unlock();
+ wb = wb_get_lookup(bdi, memcg_css);
} while (!wb && !cgwb_create(bdi, memcg_css, gfp));
return wb;
@@ -859,9 +881,58 @@ struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id)
}
EXPORT_SYMBOL(bdi_alloc_node);
+static struct rb_node **bdi_lookup_rb_node(u64 id, struct rb_node **parentp)
+{
+ struct rb_node **p = &bdi_tree.rb_node;
+ struct rb_node *parent = NULL;
+ struct backing_dev_info *bdi;
+
+ lockdep_assert_held(&bdi_lock);
+
+ while (*p) {
+ parent = *p;
+ bdi = rb_entry(parent, struct backing_dev_info, rb_node);
+
+ if (bdi->id > id)
+ p = &(*p)->rb_left;
+ else if (bdi->id < id)
+ p = &(*p)->rb_right;
+ else
+ break;
+ }
+
+ if (parentp)
+ *parentp = parent;
+ return p;
+}
+
+/**
+ * bdi_get_by_id - lookup and get bdi from its id
+ * @id: bdi id to lookup
+ *
+ * Find bdi matching @id and get it. Returns NULL if the matching bdi
+ * doesn't exist or is already unregistered.
+ */
+struct backing_dev_info *bdi_get_by_id(u64 id)
+{
+ struct backing_dev_info *bdi = NULL;
+ struct rb_node **p;
+
+ spin_lock_bh(&bdi_lock);
+ p = bdi_lookup_rb_node(id, NULL);
+ if (*p) {
+ bdi = rb_entry(*p, struct backing_dev_info, rb_node);
+ bdi_get(bdi);
+ }
+ spin_unlock_bh(&bdi_lock);
+
+ return bdi;
+}
+
int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args)
{
struct device *dev;
+ struct rb_node *parent, **p;
if (bdi->dev) /* The driver needs to use separate queues per device */
return 0;
@@ -877,7 +948,15 @@ int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args)
set_bit(WB_registered, &bdi->wb.state);
spin_lock_bh(&bdi_lock);
+
+ bdi->id = ++bdi_id_cursor;
+
+ p = bdi_lookup_rb_node(bdi->id, &parent);
+ rb_link_node(&bdi->rb_node, parent, p);
+ rb_insert_color(&bdi->rb_node, &bdi_tree);
+
list_add_tail_rcu(&bdi->bdi_list, &bdi_list);
+
spin_unlock_bh(&bdi_lock);
trace_writeback_bdi_register(bdi);
@@ -918,6 +997,7 @@ EXPORT_SYMBOL(bdi_register_owner);
static void bdi_remove_from_list(struct backing_dev_info *bdi)
{
spin_lock_bh(&bdi_lock);
+ rb_erase(&bdi->rb_node, &bdi_tree);
list_del_rcu(&bdi->bdi_list);
spin_unlock_bh(&bdi_lock);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9ec5e12486a7..597d58101872 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -87,6 +87,10 @@ int do_swap_account __read_mostly;
#define do_swap_account 0
#endif
+#ifdef CONFIG_CGROUP_WRITEBACK
+static DECLARE_WAIT_QUEUE_HEAD(memcg_cgwb_frn_waitq);
+#endif
+
/* Whether legacy memory+swap accounting is active */
static bool do_memsw_account(void)
{
@@ -4172,6 +4176,8 @@ static int mem_cgroup_oom_control_write(struct cgroup_subsys_state *css,
#ifdef CONFIG_CGROUP_WRITEBACK
+#include <trace/events/writeback.h>
+
static int memcg_wb_domain_init(struct mem_cgroup *memcg, gfp_t gfp)
{
return wb_domain_init(&memcg->cgwb_domain, gfp);
@@ -4255,6 +4261,130 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
}
}
+/*
+ * Foreign dirty flushing
+ *
+ * There's an inherent mismatch between memcg and writeback. The former
+ * trackes ownership per-page while the latter per-inode. This was a
+ * deliberate design decision because honoring per-page ownership in the
+ * writeback path is complicated, may lead to higher CPU and IO overheads
+ * and deemed unnecessary given that write-sharing an inode across
+ * different cgroups isn't a common use-case.
+ *
+ * Combined with inode majority-writer ownership switching, this works well
+ * enough in most cases but there are some pathological cases. For
+ * example, let's say there are two cgroups A and B which keep writing to
+ * different but confined parts of the same inode. B owns the inode and
+ * A's memory is limited far below B's. A's dirty ratio can rise enough to
+ * trigger balance_dirty_pages() sleeps but B's can be low enough to avoid
+ * triggering background writeback. A will be slowed down without a way to
+ * make writeback of the dirty pages happen.
+ *
+ * Conditions like the above can lead to a cgroup getting repatedly and
+ * severely throttled after making some progress after each
+ * dirty_expire_interval while the underyling IO device is almost
+ * completely idle.
+ *
+ * Solving this problem completely requires matching the ownership tracking
+ * granularities between memcg and writeback in either direction. However,
+ * the more egregious behaviors can be avoided by simply remembering the
+ * most recent foreign dirtying events and initiating remote flushes on
+ * them when local writeback isn't enough to keep the memory clean enough.
+ *
+ * The following two functions implement such mechanism. When a foreign
+ * page - a page whose memcg and writeback ownerships don't match - is
+ * dirtied, mem_cgroup_track_foreign_dirty() records the inode owning
+ * bdi_writeback on the page owning memcg. When balance_dirty_pages()
+ * decides that the memcg needs to sleep due to high dirty ratio, it calls
+ * mem_cgroup_flush_foreign() which queues writeback on the recorded
+ * foreign bdi_writebacks which haven't expired. Both the numbers of
+ * recorded bdi_writebacks and concurrent in-flight foreign writebacks are
+ * limited to MEMCG_CGWB_FRN_CNT.
+ *
+ * The mechanism only remembers IDs and doesn't hold any object references.
+ * As being wrong occasionally doesn't matter, updates and accesses to the
+ * records are lockless and racy.
+ */
+void mem_cgroup_track_foreign_dirty_slowpath(struct page *page,
+ struct bdi_writeback *wb)
+{
+ struct mem_cgroup *memcg = page->mem_cgroup;
+ struct memcg_cgwb_frn *frn;
+ u64 now = get_jiffies_64();
+ u64 oldest_at = now;
+ int oldest = -1;
+ int i;
+
+ trace_track_foreign_dirty(page, wb);
+
+ /*
+ * Pick the slot to use. If there is already a slot for @wb, keep
+ * using it. If not replace the oldest one which isn't being
+ * written out.
+ */
+ for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++) {
+ frn = &memcg->cgwb_frn[i];
+ if (frn->bdi_id == wb->bdi->id &&
+ frn->memcg_id == wb->memcg_css->id)
+ break;
+ if (time_before64(frn->at, oldest_at) &&
+ atomic_read(&frn->done.cnt) == 1) {
+ oldest = i;
+ oldest_at = frn->at;
+ }
+ }
+
+ if (i < MEMCG_CGWB_FRN_CNT) {
+ /*
+ * Re-using an existing one. Update timestamp lazily to
+ * avoid making the cacheline hot. We want them to be
+ * reasonably up-to-date and significantly shorter than
+ * dirty_expire_interval as that's what expires the record.
+ * Use the shorter of 1s and dirty_expire_interval / 8.
+ */
+ unsigned long update_intv =
+ min_t(unsigned long, HZ,
+ msecs_to_jiffies(dirty_expire_interval * 10) / 8);
+
+ if (time_before64(frn->at, now - update_intv))
+ frn->at = now;
+ } else if (oldest >= 0) {
+ /* replace the oldest free one */
+ frn = &memcg->cgwb_frn[oldest];
+ frn->bdi_id = wb->bdi->id;
+ frn->memcg_id = wb->memcg_css->id;
+ frn->at = now;
+ }
+}
+
+/* issue foreign writeback flushes for recorded foreign dirtying events */
+void mem_cgroup_flush_foreign(struct bdi_writeback *wb)
+{
+ struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css);
+ unsigned long intv = msecs_to_jiffies(dirty_expire_interval * 10);
+ u64 now = jiffies_64;
+ int i;
+
+ for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++) {
+ struct memcg_cgwb_frn *frn = &memcg->cgwb_frn[i];
+
+ /*
+ * If the record is older than dirty_expire_interval,
+ * writeback on it has already started. No need to kick it
+ * off again. Also, don't start a new one if there's
+ * already one in flight.
+ */
+ if (time_after64(frn->at, now - intv) &&
+ atomic_read(&frn->done.cnt) == 1) {
+ frn->at = 0;
+ trace_flush_foreign(wb, frn->bdi_id, frn->memcg_id);
+ cgroup_writeback_by_id(frn->bdi_id, frn->memcg_id, 0,
+ WB_REASON_FOREIGN_FLUSH,
+ &frn->done);
+ }
+ }
+}
+
#else /* CONFIG_CGROUP_WRITEBACK */
static int memcg_wb_domain_init(struct mem_cgroup *memcg, gfp_t gfp)
@@ -4777,6 +4907,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
struct mem_cgroup *memcg;
unsigned int size;
int node;
+ int __maybe_unused i;
size = sizeof(struct mem_cgroup);
size += nr_node_ids * sizeof(struct mem_cgroup_per_node *);
@@ -4820,6 +4951,9 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
#endif
#ifdef CONFIG_CGROUP_WRITEBACK
INIT_LIST_HEAD(&memcg->cgwb_list);
+ for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++)
+ memcg->cgwb_frn[i].done =
+ __WB_COMPLETION_INIT(&memcg_cgwb_frn_waitq);
#endif
idr_replace(&mem_cgroup_idr, memcg, memcg->id.id);
return memcg;
@@ -4949,7 +5083,12 @@ static void mem_cgroup_css_released(struct cgroup_subsys_state *css)
static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
{
struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+ int __maybe_unused i;
+#ifdef CONFIG_CGROUP_WRITEBACK
+ for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++)
+ wb_wait_for_completion(&memcg->cgwb_frn[i].done);
+#endif
if (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nosocket)
static_branch_dec(&memcg_sockets_enabled_key);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 1804f64ff43c..50055d2e4ea8 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1667,6 +1667,8 @@ static void balance_dirty_pages(struct bdi_writeback *wb,
if (unlikely(!writeback_in_progress(wb)))
wb_start_background_writeback(wb);
+ mem_cgroup_flush_foreign(wb);
+
/*
* Calculate global domain's pos_ratio and select the
* global dtc by default.
@@ -2427,6 +2429,8 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
task_io_account_write(PAGE_SIZE);
current->nr_dirtied++;
this_cpu_inc(bdp_ratelimits);
+
+ mem_cgroup_track_foreign_dirty(page, wb);
}
}
diff --git a/tools/cgroup/iocost_coef_gen.py b/tools/cgroup/iocost_coef_gen.py
new file mode 100644
index 000000000000..df17a2ae80e5
--- /dev/null
+++ b/tools/cgroup/iocost_coef_gen.py
@@ -0,0 +1,178 @@
+#!/usr/bin/env python3
+#
+# Copyright (C) 2019 Tejun Heo <tj@kernel.org>
+# Copyright (C) 2019 Andy Newell <newella@fb.com>
+# Copyright (C) 2019 Facebook
+
+desc = """
+Generate linear IO cost model coefficients used by the blk-iocost
+controller. If the target raw testdev is specified, destructive tests
+are performed against the whole device; otherwise, on
+./iocost-coef-fio.testfile. The result can be written directly to
+/sys/fs/cgroup/io.cost.model.
+
+On high performance devices, --numjobs > 1 is needed to achieve
+saturation.
+
+See Documentation/admin-guide/cgroup-v2.rst and block/blk-iocost.c
+for more details.
+"""
+
+import argparse
+import re
+import json
+import glob
+import os
+import sys
+import atexit
+import shutil
+import tempfile
+import subprocess
+
+parser = argparse.ArgumentParser(description=desc,
+ formatter_class=argparse.RawTextHelpFormatter)
+parser.add_argument('--testdev', metavar='DEV',
+ help='Raw block device to use for testing, ignores --testfile-size')
+parser.add_argument('--testfile-size-gb', type=float, metavar='GIGABYTES', default=16,
+ help='Testfile size in gigabytes (default: %(default)s)')
+parser.add_argument('--duration', type=int, metavar='SECONDS', default=120,
+ help='Individual test run duration in seconds (default: %(default)s)')
+parser.add_argument('--seqio-block-mb', metavar='MEGABYTES', type=int, default=128,
+ help='Sequential test block size in megabytes (default: %(default)s)')
+parser.add_argument('--seq-depth', type=int, metavar='DEPTH', default=64,
+ help='Sequential test queue depth (default: %(default)s)')
+parser.add_argument('--rand-depth', type=int, metavar='DEPTH', default=64,
+ help='Random test queue depth (default: %(default)s)')
+parser.add_argument('--numjobs', type=int, metavar='JOBS', default=1,
+ help='Number of parallel fio jobs to run (default: %(default)s)')
+parser.add_argument('--quiet', action='store_true')
+parser.add_argument('--verbose', action='store_true')
+
+def info(msg):
+ if not args.quiet:
+ print(msg)
+
+def dbg(msg):
+ if args.verbose and not args.quiet:
+ print(msg)
+
+# determine ('DEVNAME', 'MAJ:MIN') for @path
+def dir_to_dev(path):
+ # find the block device the current directory is on
+ devname = subprocess.run(f'findmnt -nvo SOURCE -T{path}',
+ stdout=subprocess.PIPE, shell=True).stdout
+ devname = os.path.basename(devname).decode('utf-8').strip()
+
+ # partition -> whole device
+ parents = glob.glob('/sys/block/*/' + devname)
+ if len(parents):
+ devname = os.path.basename(os.path.dirname(parents[0]))
+ rdev = os.stat(f'/dev/{devname}').st_rdev
+ return (devname, f'{os.major(rdev)}:{os.minor(rdev)}')
+
+def create_testfile(path, size):
+ global args
+
+ if os.path.isfile(path) and os.stat(path).st_size == size:
+ return
+
+ info(f'Creating testfile {path}')
+ subprocess.check_call(f'rm -f {path}', shell=True)
+ subprocess.check_call(f'touch {path}', shell=True)
+ subprocess.call(f'chattr +C {path}', shell=True)
+ subprocess.check_call(
+ f'pv -s {size} -pr /dev/urandom {"-q" if args.quiet else ""} | '
+ f'dd of={path} count={size} '
+ f'iflag=count_bytes,fullblock oflag=direct bs=16M status=none',
+ shell=True)
+
+def run_fio(testfile, duration, iotype, iodepth, blocksize, jobs):
+ global args
+
+ eta = 'never' if args.quiet else 'always'
+ outfile = tempfile.NamedTemporaryFile()
+ cmd = (f'fio --direct=1 --ioengine=libaio --name=coef '
+ f'--filename={testfile} --runtime={round(duration)} '
+ f'--readwrite={iotype} --iodepth={iodepth} --blocksize={blocksize} '
+ f'--eta={eta} --output-format json --output={outfile.name} '
+ f'--time_based --numjobs={jobs}')
+ if args.verbose:
+ dbg(f'Running {cmd}')
+ subprocess.check_call(cmd, shell=True)
+ with open(outfile.name, 'r') as f:
+ d = json.loads(f.read())
+ return sum(j['read']['bw_bytes'] + j['write']['bw_bytes'] for j in d['jobs'])
+
+def restore_elevator_nomerges():
+ global elevator_path, nomerges_path, elevator, nomerges
+
+ info(f'Restoring elevator to {elevator} and nomerges to {nomerges}')
+ with open(elevator_path, 'w') as f:
+ f.write(elevator)
+ with open(nomerges_path, 'w') as f:
+ f.write(nomerges)
+
+
+args = parser.parse_args()
+
+missing = False
+for cmd in [ 'findmnt', 'pv', 'dd', 'fio' ]:
+ if not shutil.which(cmd):
+ print(f'Required command "{cmd}" is missing', file=sys.stderr)
+ missing = True
+if missing:
+ sys.exit(1)
+
+if args.testdev:
+ devname = os.path.basename(args.testdev)
+ rdev = os.stat(f'/dev/{devname}').st_rdev
+ devno = f'{os.major(rdev)}:{os.minor(rdev)}'
+ testfile = f'/dev/{devname}'
+ info(f'Test target: {devname}({devno})')
+else:
+ devname, devno = dir_to_dev('.')
+ testfile = 'iocost-coef-fio.testfile'
+ testfile_size = int(args.testfile_size_gb * 2 ** 30)
+ create_testfile(testfile, testfile_size)
+ info(f'Test target: {testfile} on {devname}({devno})')
+
+elevator_path = f'/sys/block/{devname}/queue/scheduler'
+nomerges_path = f'/sys/block/{devname}/queue/nomerges'
+
+with open(elevator_path, 'r') as f:
+ elevator = re.sub(r'.*\[(.*)\].*', r'\1', f.read().strip())
+with open(nomerges_path, 'r') as f:
+ nomerges = f.read().strip()
+
+info(f'Temporarily disabling elevator and merges')
+atexit.register(restore_elevator_nomerges)
+with open(elevator_path, 'w') as f:
+ f.write('none')
+with open(nomerges_path, 'w') as f:
+ f.write('1')
+
+info('Determining rbps...')
+rbps = run_fio(testfile, args.duration, 'read',
+ 1, args.seqio_block_mb * (2 ** 20), args.numjobs)
+info(f'\nrbps={rbps}, determining rseqiops...')
+rseqiops = round(run_fio(testfile, args.duration, 'read',
+ args.seq_depth, 4096, args.numjobs) / 4096)
+info(f'\nrseqiops={rseqiops}, determining rrandiops...')
+rrandiops = round(run_fio(testfile, args.duration, 'randread',
+ args.rand_depth, 4096, args.numjobs) / 4096)
+info(f'\nrrandiops={rrandiops}, determining wbps...')
+wbps = run_fio(testfile, args.duration, 'write',
+ 1, args.seqio_block_mb * (2 ** 20), args.numjobs)
+info(f'\nwbps={wbps}, determining wseqiops...')
+wseqiops = round(run_fio(testfile, args.duration, 'write',
+ args.seq_depth, 4096, args.numjobs) / 4096)
+info(f'\nwseqiops={wseqiops}, determining wrandiops...')
+wrandiops = round(run_fio(testfile, args.duration, 'randwrite',
+ args.rand_depth, 4096, args.numjobs) / 4096)
+info(f'\nwrandiops={wrandiops}')
+restore_elevator_nomerges()
+atexit.unregister(restore_elevator_nomerges)
+info('')
+
+print(f'{devno} rbps={rbps} rseqiops={rseqiops} rrandiops={rrandiops} '
+ f'wbps={wbps} wseqiops={wseqiops} wrandiops={wrandiops}')
diff --git a/tools/cgroup/iocost_monitor.py b/tools/cgroup/iocost_monitor.py
new file mode 100644
index 000000000000..f79b23582a1d
--- /dev/null
+++ b/tools/cgroup/iocost_monitor.py
@@ -0,0 +1,277 @@
+#!/usr/bin/env drgn
+#
+# Copyright (C) 2019 Tejun Heo <tj@kernel.org>
+# Copyright (C) 2019 Facebook
+
+desc = """
+This is a drgn script to monitor the blk-iocost cgroup controller.
+See the comment at the top of block/blk-iocost.c for more details.
+For drgn, visit https://github.com/osandov/drgn.
+"""
+
+import sys
+import re
+import time
+import json
+import math
+
+import drgn
+from drgn import container_of
+from drgn.helpers.linux.list import list_for_each_entry,list_empty
+from drgn.helpers.linux.radixtree import radix_tree_for_each,radix_tree_lookup
+
+import argparse
+parser = argparse.ArgumentParser(description=desc,
+ formatter_class=argparse.RawTextHelpFormatter)
+parser.add_argument('devname', metavar='DEV',
+ help='Target block device name (e.g. sda)')
+parser.add_argument('--cgroup', action='append', metavar='REGEX',
+ help='Regex for target cgroups, ')
+parser.add_argument('--interval', '-i', metavar='SECONDS', type=float, default=1,
+ help='Monitoring interval in seconds')
+parser.add_argument('--json', action='store_true',
+ help='Output in json')
+args = parser.parse_args()
+
+def err(s):
+ print(s, file=sys.stderr, flush=True)
+ sys.exit(1)
+
+try:
+ blkcg_root = prog['blkcg_root']
+ plid = prog['blkcg_policy_iocost'].plid.value_()
+except:
+ err('The kernel does not have iocost enabled')
+
+IOC_RUNNING = prog['IOC_RUNNING'].value_()
+NR_USAGE_SLOTS = prog['NR_USAGE_SLOTS'].value_()
+HWEIGHT_WHOLE = prog['HWEIGHT_WHOLE'].value_()
+VTIME_PER_SEC = prog['VTIME_PER_SEC'].value_()
+VTIME_PER_USEC = prog['VTIME_PER_USEC'].value_()
+AUTOP_SSD_FAST = prog['AUTOP_SSD_FAST'].value_()
+AUTOP_SSD_DFL = prog['AUTOP_SSD_DFL'].value_()
+AUTOP_SSD_QD1 = prog['AUTOP_SSD_QD1'].value_()
+AUTOP_HDD = prog['AUTOP_HDD'].value_()
+
+autop_names = {
+ AUTOP_SSD_FAST: 'ssd_fast',
+ AUTOP_SSD_DFL: 'ssd_dfl',
+ AUTOP_SSD_QD1: 'ssd_qd1',
+ AUTOP_HDD: 'hdd',
+}
+
+class BlkgIterator:
+ def blkcg_name(blkcg):
+ return blkcg.css.cgroup.kn.name.string_().decode('utf-8')
+
+ def walk(self, blkcg, q_id, parent_path):
+ if not self.include_dying and \
+ not (blkcg.css.flags.value_() & prog['CSS_ONLINE'].value_()):
+ return
+
+ name = BlkgIterator.blkcg_name(blkcg)
+ path = parent_path + '/' + name if parent_path else name
+ blkg = drgn.Object(prog, 'struct blkcg_gq',
+ address=radix_tree_lookup(blkcg.blkg_tree, q_id))
+ if not blkg.address_:
+ return
+
+ self.blkgs.append((path if path else '/', blkg))
+
+ for c in list_for_each_entry('struct blkcg',
+ blkcg.css.children.address_of_(), 'css.sibling'):
+ self.walk(c, q_id, path)
+
+ def __init__(self, root_blkcg, q_id, include_dying=False):
+ self.include_dying = include_dying
+ self.blkgs = []
+ self.walk(root_blkcg, q_id, '')
+
+ def __iter__(self):
+ return iter(self.blkgs)
+
+class IocStat:
+ def __init__(self, ioc):
+ global autop_names
+
+ self.enabled = ioc.enabled.value_()
+ self.running = ioc.running.value_() == IOC_RUNNING
+ self.period_ms = ioc.period_us.value_() / 1_000
+ self.period_at = ioc.period_at.value_() / 1_000_000
+ self.vperiod_at = ioc.period_at_vtime.value_() / VTIME_PER_SEC
+ self.vrate_pct = ioc.vtime_rate.counter.value_() * 100 / VTIME_PER_USEC
+ self.busy_level = ioc.busy_level.value_()
+ self.autop_idx = ioc.autop_idx.value_()
+ self.user_cost_model = ioc.user_cost_model.value_()
+ self.user_qos_params = ioc.user_qos_params.value_()
+
+ if self.autop_idx in autop_names:
+ self.autop_name = autop_names[self.autop_idx]
+ else:
+ self.autop_name = '?'
+
+ def dict(self, now):
+ return { 'device' : devname,
+ 'timestamp' : str(now),
+ 'enabled' : str(int(self.enabled)),
+ 'running' : str(int(self.running)),
+ 'period_ms' : str(self.period_ms),
+ 'period_at' : str(self.period_at),
+ 'period_vtime_at' : str(self.vperiod_at),
+ 'busy_level' : str(self.busy_level),
+ 'vrate_pct' : str(self.vrate_pct), }
+
+ def table_preamble_str(self):
+ state = ('RUN' if self.running else 'IDLE') if self.enabled else 'OFF'
+ output = f'{devname} {state:4} ' \
+ f'per={self.period_ms}ms ' \
+ f'cur_per={self.period_at:.3f}:v{self.vperiod_at:.3f} ' \
+ f'busy={self.busy_level:+3} ' \
+ f'vrate={self.vrate_pct:6.2f}% ' \
+ f'params={self.autop_name}'
+ if self.user_cost_model or self.user_qos_params:
+ output += f'({"C" if self.user_cost_model else ""}{"Q" if self.user_qos_params else ""})'
+ return output
+
+ def table_header_str(self):
+ return f'{"":25} active {"weight":>9} {"hweight%":>13} {"inflt%":>6} ' \
+ f'{"dbt":>3} {"delay":>6} {"usages%"}'
+
+class IocgStat:
+ def __init__(self, iocg):
+ ioc = iocg.ioc
+ blkg = iocg.pd.blkg
+
+ self.is_active = not list_empty(iocg.active_list.address_of_())
+ self.weight = iocg.weight.value_()
+ self.active = iocg.active.value_()
+ self.inuse = iocg.inuse.value_()
+ self.hwa_pct = iocg.hweight_active.value_() * 100 / HWEIGHT_WHOLE
+ self.hwi_pct = iocg.hweight_inuse.value_() * 100 / HWEIGHT_WHOLE
+ self.address = iocg.value_()
+
+ vdone = iocg.done_vtime.counter.value_()
+ vtime = iocg.vtime.counter.value_()
+ vrate = ioc.vtime_rate.counter.value_()
+ period_vtime = ioc.period_us.value_() * vrate
+ if period_vtime:
+ self.inflight_pct = (vtime - vdone) * 100 / period_vtime
+ else:
+ self.inflight_pct = 0
+
+ self.debt_ms = iocg.abs_vdebt.counter.value_() / VTIME_PER_USEC / 1000
+ self.use_delay = blkg.use_delay.counter.value_()
+ self.delay_ms = blkg.delay_nsec.counter.value_() / 1_000_000
+
+ usage_idx = iocg.usage_idx.value_()
+ self.usages = []
+ self.usage = 0
+ for i in range(NR_USAGE_SLOTS):
+ usage = iocg.usages[(usage_idx + i) % NR_USAGE_SLOTS].value_()
+ upct = usage * 100 / HWEIGHT_WHOLE
+ self.usages.append(upct)
+ self.usage = max(self.usage, upct)
+
+ def dict(self, now, path):
+ out = { 'cgroup' : path,
+ 'timestamp' : str(now),
+ 'is_active' : str(int(self.is_active)),
+ 'weight' : str(self.weight),
+ 'weight_active' : str(self.active),
+ 'weight_inuse' : str(self.inuse),
+ 'hweight_active_pct' : str(self.hwa_pct),
+ 'hweight_inuse_pct' : str(self.hwi_pct),
+ 'inflight_pct' : str(self.inflight_pct),
+ 'debt_ms' : str(self.debt_ms),
+ 'use_delay' : str(self.use_delay),
+ 'delay_ms' : str(self.delay_ms),
+ 'usage_pct' : str(self.usage),
+ 'address' : str(hex(self.address)) }
+ for i in range(len(self.usages)):
+ out[f'usage_pct_{i}'] = str(self.usages[i])
+ return out
+
+ def table_row_str(self, path):
+ out = f'{path[-28:]:28} ' \
+ f'{"*" if self.is_active else " "} ' \
+ f'{self.inuse:5}/{self.active:5} ' \
+ f'{self.hwi_pct:6.2f}/{self.hwa_pct:6.2f} ' \
+ f'{self.inflight_pct:6.2f} ' \
+ f'{min(math.ceil(self.debt_ms), 999):3} ' \
+ f'{min(self.use_delay, 99):2}*'\
+ f'{min(math.ceil(self.delay_ms), 999):03} '
+ for u in self.usages:
+ out += f'{min(round(u), 999):03d}:'
+ out = out.rstrip(':')
+ return out
+
+# handle args
+table_fmt = not args.json
+interval = args.interval
+devname = args.devname
+
+if args.json:
+ table_fmt = False
+
+re_str = None
+if args.cgroup:
+ for r in args.cgroup:
+ if re_str is None:
+ re_str = r
+ else:
+ re_str += '|' + r
+
+filter_re = re.compile(re_str) if re_str else None
+
+# Locate the roots
+q_id = None
+root_iocg = None
+ioc = None
+
+for i, ptr in radix_tree_for_each(blkcg_root.blkg_tree):
+ blkg = drgn.Object(prog, 'struct blkcg_gq', address=ptr)
+ try:
+ if devname == blkg.q.kobj.parent.name.string_().decode('utf-8'):
+ q_id = blkg.q.id.value_()
+ if blkg.pd[plid]:
+ root_iocg = container_of(blkg.pd[plid], 'struct ioc_gq', 'pd')
+ ioc = root_iocg.ioc
+ break
+ except:
+ pass
+
+if ioc is None:
+ err(f'Could not find ioc for {devname}');
+
+# Keep printing
+while True:
+ now = time.time()
+ iocstat = IocStat(ioc)
+ output = ''
+
+ if table_fmt:
+ output += '\n' + iocstat.table_preamble_str()
+ output += '\n' + iocstat.table_header_str()
+ else:
+ output += json.dumps(iocstat.dict(now))
+
+ for path, blkg in BlkgIterator(blkcg_root, q_id):
+ if filter_re and not filter_re.match(path):
+ continue
+ if not blkg.pd[plid]:
+ continue
+
+ iocg = container_of(blkg.pd[plid], 'struct ioc_gq', 'pd')
+ iocg_stat = IocgStat(iocg)
+
+ if not filter_re and not iocg_stat.is_active:
+ continue
+
+ if table_fmt:
+ output += '\n' + iocg_stat.table_row_str(path)
+ else:
+ output += '\n' + json.dumps(iocg_stat.dict(now, path))
+
+ print(output)
+ sys.stdout.flush()
+ time.sleep(interval)