linux.git/drivers/nvme/host/core.c, branch v4.12

nvme: relax APST default max latency to 100ms

2017-06-07T09:08:55+00:00

Christoph Hellwig suggests we should to make APST work out of the box.
Hence relax the the default max latency to make them able to enter
deepest power state on default.

Here are id-ctrl excerpts from two high latency NVMes:

vid     : 0x14a4
ssvid   : 0x1b4b
mn      : CX2-GB1024-Q11 NVMe LITEON 1024GB
ps    3 : mp:0.1000W non-operational enlat:5000 exlat:5000 rrt:3 rrl:3
          rwt:3 rwl:3 idle_power:- active_power:-
ps    4 : mp:0.0100W non-operational enlat:50000 exlat:100000 rrt:4 rrl:4
          rwt:4 rwl:4 idle_power:- active_power:-

vid     : 0x15b7
ssvid   : 0x1b4b
mn      : A400 NVMe SanDisk 512GB
ps    3 : mp:0.0500W non-operational enlat:51000 exlat:10000 rrt:0 rrl:0
          rwt:0 rwl:0 idle_power:- active_power:-
ps    4 : mp:0.0055W non-operational enlat:1000000 exlat:100000 rrt:0 rrl:0
          rwt:0 rwl:0 idle_power:- active_power:-

Signed-off-by: Kai-Heng Feng 
Signed-off-by: Christoph Hellwig

nvme: only consider exit latency when choosing useful non-op power states

2017-06-07T09:08:54+00:00

When a NVMe is in non-op states, the latency is exlat.
The latency will be enlat + exlat only when the NVMe tries to transit
from operational state right atfer it begins to transit to
non-operational state, which should be a rare case.

Therefore, as Andy Lutomirski suggests, use exlat only when deciding power
states to trainsit to.

Signed-off-by: Kai-Heng Feng 
Signed-off-by: Christoph Hellwig

nvme: fix hang in remove path

2017-06-07T09:08:49+00:00

We need to start admin queues too in nvme_kill_queues()
for avoiding hang in remove path[1].

This patch is very similar with 806f026f9b901eaf(nvme: use
blk_mq_start_hw_queues() in nvme_kill_queues()).

[1] hang stack trace
[] blk_execute_rq+0x56/0x80
[] __nvme_submit_sync_cmd+0x89/0xf0
[] nvme_set_features+0x5e/0x90
[] nvme_configure_apst+0x166/0x200
[] nvme_set_latency_tolerance+0x35/0x50
[] apply_constraint+0xb1/0xc0
[] dev_pm_qos_constraints_destroy+0xf4/0x1f0
[] dpm_sysfs_remove+0x2a/0x60
[] device_del+0x101/0x320
[] device_unregister+0x1a/0x60
[] device_destroy+0x3c/0x50
[] nvme_uninit_ctrl+0x45/0xa0
[] nvme_remove+0x78/0x110
[] pci_device_remove+0x39/0xb0
[] device_release_driver_internal+0x155/0x210
[] device_release_driver+0x12/0x20
[] nvme_remove_dead_ctrl_work+0x6b/0x70
[] process_one_work+0x18c/0x3a0
[] worker_thread+0x4e/0x3b0
[] kthread+0x109/0x140
[] ret_from_fork+0x2c/0x40
[] 0xffffffffffffffff

Fixes: c5552fde102fc("nvme: Enable autonomous power state transitions")
Reported-by: Rakesh Pandit 
Tested-by: Rakesh Pandit 
Reviewed-by: Sagi Grimberg 
Signed-off-by: Ming Lei 
Signed-off-by: Christoph Hellwig

nvme: only setup block integrity if supported by the driver

2017-05-26T06:54:23+00:00

Currently only the PCIe driver supports metadata, so we should not claim
integrity support for the other drivers.  This prevents nasty crashes
with targets that advertise metadata support on fabrics.

Also use the opportunity to factor out some code into a separate helper
that isn't even compiled if CONFIG_BLK_DEV_INTEGRITY is disabled.

Signed-off-by: Christoph Hellwig 
Reviewed-by: Keith Busch

nvme: replace is_flags field in nvme_ctrl_ops with a flags field

2017-05-26T06:54:16+00:00

So that we can have more flags for transport-specific behavior.

Signed-off-by: Christoph Hellwig 
Reviewed-by: Keith Busch

nvme: avoid to use blk_mq_abort_requeue_list()

2017-05-22T18:50:10+00:00

NVMe may add request into requeue list simply and not kick off the
requeue if hw queues are stopped. Then blk_mq_abort_requeue_list()
is called in both nvme_kill_queues() and nvme_ns_remove() for
dealing with this issue.

Unfortunately blk_mq_abort_requeue_list() is absolutely a
race maker, for example, one request may be requeued during
the aborting. So this patch just calls blk_mq_kick_requeue_list() in
nvme_kill_queues() to handle this issue like what nvme_start_queues()
does. Now all requests in requeue list when queues are stopped will be
handled by blk_mq_kick_requeue_list() when queues are restarted, either
in nvme_start_queues() or in nvme_kill_queues().

Cc: stable@vger.kernel.org
Reported-by: Zhang Yi 
Reviewed-by: Keith Busch 
Reviewed-by: Johannes Thumshirn 
Signed-off-by: Ming Lei 
Signed-off-by: Christoph Hellwig

nvme: use blk_mq_start_hw_queues() in nvme_kill_queues()

2017-05-22T18:50:09+00:00

Inside nvme_kill_queues(), we have to start hw queues for
draining requests in sw queues, .dispatch list and requeue list,
so use blk_mq_start_hw_queues() instead of blk_mq_start_stopped_hw_queues()
which only run queues if queues are stopped, but the queues may have
been started already, for example nvme_start_queues() is called in reset work
function.

blk_mq_start_hw_queues() run hw queues in current context, instead
of running asynchronously like before. Given nvme_kill_queues() is
run from either remove context or reset worker context, both are fine
to run hw queue directly. And the mutex of namespaces_mutex isn't a
problem too becasue nvme_start_freeze() runs hw queue in this way
already.

Cc: stable@vger.kernel.org
Reported-by: Zhang Yi 
Reviewed-by: Keith Busch 
Reviewed-by: Johannes Thumshirn 
Signed-off-by: Ming Lei 
Signed-off-by: Christoph Hellwig

nvme: Add nvme_core.force_apst to ignore the NO_APST quirk

2017-04-25T04:03:46+00:00

We're probably going to be stuck quirking APST off on an over-broad
range of devices for 4.11.  Let's make it easy to override the quirk
for testing.

Signed-off-by: Andy Lutomirski 
Reviewed-by: Christoph Hellwig 
Signed-off-by: Jens Axboe

nvme: Display raw APST configuration via DYNAMIC_DEBUG

2017-04-25T04:03:46+00:00

Debugging APST is currently a bit of a pain.  This gives optional
simple log messages that describe the APST state.

The easiest way to use this is probably with the nvme_core.dyndbg=+p
module parameter.

Signed-off-by: Andy Lutomirski 
Reviewed-by: Christoph Hellwig 
Signed-off-by: Jens Axboe

nvme: Fix APST comment

2017-04-25T04:03:46+00:00

There was a typo in the description of the timeout heuristic.

Signed-off-by: Andy Lutomirski 
Reviewed-by: Christoph Hellwig 
Signed-off-by: Jens Axboe