linux-toradex.git/drivers/nvme, branch v4.4.93

nvme: protect against simultaneous shutdown invocations

2017-10-12T09:27:35+00:00

commit 77bf25ea70200cddf083f74b7f617e5f07fac8bd upstream.

[Back-ported to 4.4. The difference is the file location of the struct
definition that's adding the mutex.

This fixes reported kernel panics in 4.4-stable from simultaneous
controller resets that was never supposed to be allowed to happen.]

Signed-off-by: Keith Busch 
[hch: split from a larger patch]
Signed-off-by: Christoph Hellwig 
Signed-off-by: Jens Axboe 
Signed-off-by: Greg Kroah-Hartman

nvme: apply DELAY_BEFORE_CHK_RDY quirk at probe time too

2017-06-29T10:48:53+00:00

commit b5a10c5f7532b7473776da87e67f8301bbc32693 upstream.

Commit 54adc01055b7 ("nvme/quirk: Add a delay before checking for adapter
readiness") introduced a quirk to adapters that cannot read the bit
NVME_CSTS_RDY right after register NVME_REG_CC is set; these adapters
need a delay or else the action of reading the bit NVME_CSTS_RDY could
somehow corrupt adapter's registers state and it never recovers.

When this quirk was added, we checked ctrl->tagset in order to avoid
quirking in probe time, supposing we would never require such delay
during probe. Well, it was too optimistic; we in fact need this quirk
at probe time in some cases, like after a kexec.

In some experiments, after abnormal shutdown of machine (aka power cord
unplug), we booted into our bootloader in Power, which is a Linux kernel,
and kexec'ed into another distro. If this kexec is too quick, we end up
reaching the probe of NVMe adapter in that distro when adapter is in
bad state (not fully initialized on our bootloader). What happens next
is that nvme_wait_ready() is unable to complete, except if the quirk is
enabled.

So, this patch removes the original ctrl->tagset verification in order
to enable the quirk even on probe time.

Fixes: 54adc01055b7 ("nvme/quirk: Add a delay before checking for adapter readiness")
Reported-by: Andrew Byrne 
Reported-by: Jaime A. H. Gomez 
Reported-by: Zachary D. Myers 
Signed-off-by: Guilherme G. Piccoli 
Acked-by: Jeffrey Lien 
Signed-off-by: Christoph Hellwig 
[mauricfo: backport to v4.4.70 without nvme quirk handling & nvme_ctrl]
Signed-off-by: Mauricio Faria de Oliveira 
Tested-by: Narasimhan Vaidyanathan 
Signed-off-by: Greg Kroah-Hartman

nvme/quirk: Add a delay before checking for adapter readiness

2017-06-29T10:48:53+00:00

commit 54adc01055b75ec8769c5a36574c7a0895c0c0b2 upstream.

When disabling the controller, the specification says the register
NVME_REG_CC should be written and then driver needs to wait the
adapter to be ready, which is checked by reading another register
bit (NVME_CSTS_RDY). There's a timeout validation in this checking,
so in case this timeout is reached the driver gives up and removes
the adapter from the system.

After a firmware activation procedure, the PCI_DEVICE(0x1c58, 0x0003)
(HGST adapter) end up being removed if we issue a reset_controller,
because driver keeps verifying the NVME_REG_CSTS until the timeout is
reached. This patch adds a necessary quirk for this adapter, by
introducing a delay before nvme_wait_ready(), so the reset procedure
is able to be completed. This quirk is needed because just increasing
the timeout is not enough in case of this adapter - the driver must
wait before start reading NVME_REG_CSTS register on this specific
device.

Signed-off-by: Guilherme G. Piccoli 
Reviewed-by: Christoph Hellwig 
Signed-off-by: Jens Axboe 
[mauricfo: backport to v4.4.70 without nvme quirk handling & nvme_ctrl]
Signed-off-by: Mauricio Faria de Oliveira 
Tested-by: Narasimhan Vaidyanathan 
Signed-off-by: Greg Kroah-Hartman

nvme: Call pci_disable_device on the error path.

2016-09-15T06:27:51+00:00

Commit 5706aca74fe4 ("NVMe: Don't unmap controller registers on reset"),
which backported b00a726a9fd8 to the 4.4.y kernel introduced a
regression in which it didn't call pci_disable_device in the error path
of nvme_pci_enable.

Reported-by: Jiri Slaby 
Embarassed-developer: Gabriel Krisman Bertazi 
Signed-off-by: Gabriel Krisman Bertazi 
Signed-off-by: Greg Kroah-Hartman

NVMe: Don't unmap controller registers on reset

2016-09-07T06:32:37+00:00

Commit b00a726a9fd82ddd4c10344e46f0d371e1674303 upstream.

Unmapping the registers on reset or shutdown is not necessary. Keeping
the mapping simplifies reset handling.

This was backported to 4.4 stable tree because it prevents a race
between the reset_work and the shutdown hook, that may provoke the Oops
below, in the nvme_wait_ready function.

The Oops is easily reproducible on systems that will kexec/reboot
immediately after booting, which is actually the common use case for
kexec based bootloaders, like Petitboot.  This patch removes the
unnecessary early unmapping of the PCI configuration in the shutdown
hook, allowing a proper handling of the reset work.

Unable to handle kernel paging request for data at address 0x0000001c
Faulting instruction address: 0xd000000000720b38
cpu 0x1b: Vector: 300 (Data Access) at [c000007f7a9a38a0]
    pc: d000000000720b38: nvme_wait_ready+0x50/0x120 [nvme]
    lr: d000000000720b7c: nvme_wait_ready+0x94/0x120 [nvme]
    sp: c000007f7a9a3b20
   msr: 9000000000009033
   dar: 1c
 dsisr: 40000000
  current = 0xc000007f7a926c80
  paca    = 0xc00000000fe85100   softe: 0        irq_happened: 0x01
    pid   = 2608, comm = kworker/27:1
enter ? for help
[c000007f7a9a3bb0] d00000000072572c nvme_setup_io_queues+0xc08/0x1218 [nvme]
[c000007f7a9a3c70] c00000000006bbd8 process_one_work+0x228/0x378
[c000007f7a9a3d00] c00000000006c050 worker_thread+0x2e0/0x420
[c000007f7a9a3d80] c00000000007161c kthread+0xfc/0x108
[c000007f7a9a3e30] c0000000000094b4 ret_from_kernel_thread+0x5c/0xa8

Signed-off-by: Keith Busch 
Reviewed-by: Johannes Thumshirn 
Reviewed-by: Christoph Hellwig 
Signed-off-by: Jens Axboe 
Signed-off-by: Gabriel Krisman Bertazi 
	[Backport to v4.4.y]
Signed-off-by: Greg Kroah-Hartman

NVMe: IO ending fixes on surprise removal

2015-12-22T17:12:04+00:00

This patch fixes a lost request discovered during IO + hot removal.

The driver's pci removal deletes gendisks prior to shutting down the
controller to allow dirty data to sync. Dirty data can not be synced on
a surprise removal, though, and would potentially block indefinitely.

The driver previously had marked the queue as dying in this scenario
to prevent new requests from attempting, however it will still block
for requests that already entered the queue. This patch fixes this by
quiescing IO first, then aborting the requeued requests before deleting
disks.

Reported-by: Sujith Pandel 
Signed-off-by: Keith Busch 
Tested-by: Sujith Pandel 
Signed-off-by: Jens Axboe

lightnvm: replace req queue with nvmdev for lld

2015-12-07T16:14:19+00:00

In the case where a request queue is passed to the low lever lightnvm
device drive integration, the device driver might pass its admin
commands through another queue. Instead pass nvm_dev, and let the
low level drive the appropriate queue.

Reported-by: Christoph Hellwig 
Signed-off-by: Matias Bjørling 
Signed-off-by: Jens Axboe

lightnvm: check mm before use

2015-12-07T16:14:19+00:00

The core can may issue I/Os before a media manager is registered with
the lightnvm subsystem. Make sure that we don't call the media manager
->end_io prematurely with a null pointer.

Signed-off-by: Matias Bjørling 
Signed-off-by: Jens Axboe

nvme: temporary fix for Apple controller reset

2015-12-01T20:23:22+00:00

Recent patches added basic support for the Apple NVMe controller but
still cause resets and data corruption on that particular controller
when a specific pattern of read/flush commands occurs. Limiting the
queue depth to 2 works around that issue.

This patch enforces that limit only for the Apple controller and is
considered a temporary fix until we find the root source of that
problem.

Signed-off-by: Stephan Günther 
Signed-off-by: Maurice Leclaire 
Reviewed-by: Christoph Hellwig 
Signed-off-by: Jens Axboe

lightnvm: unconverted ppa returned in get_bb_tbl

2015-11-29T21:34:58+00:00

The get_bb_tbl function takes ppa as a generic address, which is
converted to the ppa device address within the device driver. When
the update_bbtbl callback is called from get_bb_tbl, the device
specific ppa is used, instead of the generic ppa.

Make sure to pass the generic ppa.

Signed-off-by: Matias Bjørling 
Signed-off-by: Jens Axboe