Use the integrity API to pass through metadata from userspace.  For PI
enabled devices this means that we now validate the reftag, which seems
like an unintentional ommission in the old code.

Thanks to Keith Busch for testing and fixes.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
[Skip metadata setup on admin commands]
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Add a separate nvme_submit_user_cmd for commands that directly DMA
to or from userspace.  We'll add metadata support to that soon and
the common version would become too messy.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

And mark them inline so that we don't slow down the I/O submission path by
having to turn it into a forced out of line call.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

And mark it inline so that we don't slow down the completion path by
having to turn it into a forced out of line call.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

This is the counter part to nvme_map_data.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@fb.com>

This "backports" the structure I've used for the fabrics driver.  It
mostly started out as a cleanup so that I could actually understand
the code, but I think it also qualifies as a micro-optimization due
to the reduced time we hold q_lock and disable interrupts.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Pass back a true/false value instead of the length which needs a compare
with the bytes in the request and drop the pointless gfp_t argument.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

The new struct nvme_ctrl will be used by the common NVMe code that sits
on top of struct request_queue and the new nvme_ctrl_ops abstraction.
It only contains the bare minimum required, which consists of values
sampled during controller probe, the admin queue pointer and a second
struct device pointer at the moment, but more will follow later.  Only
values that are not used in the I/O fast path should be moved to
struct nvme_ctrl so that drivers can optimize their cache line usage
easily.  That's also the reason why we have two device pointers as
the struct device is used for DMA mapping purposes.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Acked-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Use the vendor ID from the identify data instead of the PCI device to
make the SCSI translation layer independent from the PCI driver.  The NVMe
spec defines them as having the same value for current PCIe devices.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@fb.com>

Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@fb.com>

This makes life easier for future non-PCI drivers where access to the
registers might be more complicated.  Note that Linux drivers are
pretty evenly split between the two versions, and in fact the NVMe
driver already uses offsets for the doorbells.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Acked-by: NKeith Busch <keith.busch@intel.com>
[Fixed CMBSZ offset]
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Create a new core.c and start by adding the command submission helpers
to it, which are already abstracted away from the actual hardware queues
by the block layer.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Acked-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

This structure is specific to the PCIe driver internals and should be moved
to pci.c.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Acked-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

We already have the reserved flag, and a nowait flag awkwardly encoded as
a gfp_t.  Add a real flags argument to make the scheme more extensible and
allow for a nicer calling convention.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@fb.com>

When we fail various metadata related operations in nvme_queue_rq we
need to unmap the data SGL.

Cc: stable@vger.kernel.org
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

We received a bug report recently when DDW (64-bit direct DMA on Power)
is not enabled for NVMe devices. In that case, we fall back to 32-bit
DMA via the IOMMU, which is always done via 4K TCEs (Translation Control
Entries).

The NVMe device driver, though, assumes that the DMA alignment for the
PRP entries will match the device's page size, and that the DMA aligment
matches the kernel's page aligment. On Power, the the IOMMU page size,
as mentioned above, can be 4K, while the device can have a page size of
8K, while the kernel has a page size of 64K. This eventually trips the
BUG_ON in nvme_setup_prps(), as we have a 'dma_len' that is a multiple
of 4K but not 8K (e.g., 0xF000).

In this particular case of page sizes, we clearly want to use the
IOMMU's page size in the driver. And generally, the NVMe driver in this
function should be using the IOMMU's page size for the default device
page size, rather than the kernel's page size. There is not currently an
API to obtain the IOMMU's page size across all architectures and in the
interest of a stop-gap fix to this functional issue, default the NVMe
device page size to 4K, with the intent of adding such an API and
implementation across all architectures in the next merge window.

With the functionally equivalent v3 of this patch, our hardware test
exerciser survives when using 32-bit DMA; without the patch, the kernel
will BUG within a few minutes.

Signed-off-by: Nishanth Aravamudan <nacc at linux.vnet.ibm.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Make sure that there are no unprocesssed entries on a completion
queue before deleting it, and check for validity of the CQ
door bell before writing completions to it.

This fixes problems with doing a sysfs reset of the device while
it's handling IO.
Tested-by: NJon Derrick <jonathan.derrick@intel.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

According to the Open-Channel SSD Specification, the NVMe-NVM admin
commands use vendor specific opcodes of NVMe, so use the NVMe admin
queue to dispatch these commands.
Signed-off-by: NWenwei Tao <ww.tao0320@gmail.com>
Updated by me to include set bad block table as well and also use
the admin queue for l2p len calculation.
Signed-off-by: NMatias Bjørling <m@bjorling.me>
Signed-off-by: NJens Axboe <axboe@fb.com>

Reported-by: NPaul Grabinar <paul.grabinar@ranbarg.com>
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

The specification was updated the remove the double word just after
number of configuration groups and capabilities. Update the identify
structure to reflect it.
Signed-off-by: NMatias Bjørling <m@bjorling.me>
Signed-off-by: NJens Axboe <axboe@fb.com>

The ppa format was not copied from the NVMe specific ppa format to the
lightnvm specific ppa format. This led to the ppa format not being
communicated to the layers above.
Signed-off-by: NMatias Bjørling <m@bjorling.me>
Signed-off-by: NJens Axboe <axboe@fb.com>

The linear and device specific address modes can be replaced with a
simple offset and bit length conversion that is generic across all
devices.

This both simplifies the specification and removes the special case for
qemu nvme, that previously relied on the linear address mapping.
Signed-off-by: NMatias Bjørling <m@bjorling.me>
Signed-off-by: NJens Axboe <axboe@fb.com>

The mccap field is required for I/O command option support. It defines the
following flash access modes:

 * SLC mode
 * Erase/Program Suspension
 * Scramble On/Off
 * Encryption

It is slotted in between mpos and cpar, changing the offset for
cpar as well.
Signed-off-by: NMatias Bjørling <m@bjorling.me>
Signed-off-by: NJens Axboe <axboe@fb.com>

A single 8 bit and 16 bit reserve field were inserted in the
specification to align fields appropriately. Reflect this in the
identify group structure.
Signed-off-by: NMatias Bjørling <m@bjorling.me>
Signed-off-by: NJens Axboe <axboe@fb.com>

The specification was changed to reflect a multi-value bad block table.
Instead of bit-based bad block table, the bad block table now allows
eight bad block categories. Currently four are defined:

 * Factory bad blocks
 * Grown bad blocks
 * Device-side reserved blocks
 * Host-side reserved blocks

The factory and grown bad blocks are the regular bad blocks. The
reserved blocks are either for internal use or external use. In
particular, the device-side reserved blocks allows the host to
bootstrap from a limited number of flash blocks. Reducing the flash
blocks to scan upon super block initialization.

Support for both get bad block table and set bad block table is added.
Signed-off-by: NMatias Bjørling <m@bjorling.me>
Signed-off-by: NJens Axboe <axboe@fb.com>

Add PCI ID of Apple's NVMe controller.
Signed-off-by: NStephan Guenther <guenther@tum.de>
Signed-off-by: NMaurice Leclaire <leclaire@in.tum.de>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@fb.com>

Some controllers may require ordered split transfers even on 64bit
machines, e.g. Apple's NVMe controller as found in the MacBook8,1 and
MacBookAir7,1 (256/512GB models).

This patch enforces ordered split transfers on 64bit platforms, which
works around that issue for all controllers. As pointed out by Christoph
[1] there should be no performance impact due to that modification.

[1] http://lists.infradead.org/pipermail/linux-nvme/2015-November/002965.htmlSigned-off-by: NStephan Guenther <guenther@tum.de>
Signed-off-by: NMaurice Leclaire <leclaire@in.tum.de>
Reviewed-by: NChristoph Hellwig <hch@lst.de>

Updated by me to explicitly use lo_hi_read/writeq instead of playing
define tricks.
Signed-off-by: NJens Axboe <axboe@fb.com>

This patch address the issue when IO with 128KB from FIO is split into
two parts, 124KB and 4KB, due to max transfer size(127KB). This degrades
the device performance.
Signed-off-by: NSathyavathi M <sathya.m@samsung.com>
Acked-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Add nvme_poll(), which will check a specific completion queue for
command completions. Wire that up to the new block layer poll
mechanism.
Signed-off-by: NJens Axboe <axboe@fb.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Acked-by: NKeith Busch <keith.busch@intel.com>

__GFP_WAIT was used to signal that the caller was in atomic context and
could not sleep.  Now it is possible to distinguish between true atomic
context and callers that are not willing to sleep.  The latter should
clear __GFP_DIRECT_RECLAIM so kswapd will still wake.  As clearing
__GFP_WAIT behaves differently, there is a risk that people will clear the
wrong flags.  This patch renames __GFP_WAIT to __GFP_RECLAIM to clearly
indicate what it does -- setting it allows all reclaim activity, clearing
them prevents it.

[akpm@linux-foundation.org: fix build]
[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: NMel Gorman <mgorman@techsingularity.net>
Acked-by: NMichal Hocko <mhocko@suse.com>
Acked-by: NVlastimil Babka <vbabka@suse.cz>
Acked-by: NJohannes Weiner <hannes@cmpxchg.org>
Cc: Christoph Lameter <cl@linux.com>
Acked-by: NDavid Rientjes <rientjes@google.com>
Cc: Vitaly Wool <vitalywool@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

"nlb_pr_rq" can't be more than u32 because "len" is a u32.  Later we
truncate it to u32 anyway when we calculate min_t().
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

The original code is equivalent to:

	u32 cdw10 = (1 | key) ? 1 << 3 : 0;

But we want:

	u32 cdw10 = 1 | (key ? 1 << 3 : 0);

Fixes: 1d277a63: ('NVMe: Add persistent reservation ops')
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

The first generation of Open-Channel SSDs is based on NVMe. The NVMe
driver is extended with support for the LightNVM command set.

Detection is made through PCI IDs. Current supported devices are the
qemu nvme simulator and CNEX Labs Westlake SSD. The qemu nvme enables
support through vendor specific bits in the namespace identification and
the CNEX Labs Westlake SSD implements a LightNVM compatible firmware and
is detected using the same method as qemu.

After detection, vendor specific codes are used to identify the device
and enumerate supported features.
Reviewed-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NJavier González <jg@lightnvm.io>
Signed-off-by: NMatias Bjørling <m@bjorling.me>
Signed-off-by: NJens Axboe <axboe@fb.com>

Reported-by: Nkbuild test robot <fengguang.wu@intel.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Fixes: ad4fd3610c27 ("NVMe: Add persistent reservation ops")
Signed-off-by: NJens Axboe <axboe@fb.com>

Signed-off-by: NKeith Busch <keith.busch@intel.com>
[hch: rebased, set PTPL=1]
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@fb.com>

The libnvidmm-btt and nvme drivers use blk_integrity to reserve space
for per-sector metadata, but sometimes without protection checksums.
This property is generically useful, so teach the block core to
internally specify a nop profile if one is not provided at registration
time.

Cc: Keith Busch <keith.busch@intel.com>
Cc: Matthew Wilcox <willy@linux.intel.com>
Suggested-by: NChristoph Hellwig <hch@lst.de>
[hch: kill the local nvme nop profile as well]
Acked-by: NMartin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

A trace like the following proceeds a crash in bio_integrity_process()
when it goes to use an already freed blk_integrity profile.

 BUG: unable to handle kernel paging request at ffff8800d31b10d8
 IP: [<ffff8800d31b10d8>] 0xffff8800d31b10d8
 PGD 2f65067 PUD 21fffd067 PMD 80000000d30001e3
 Oops: 0011 [#1] SMP
 Dumping ftrace buffer:
 ---------------------------------
    ndctl-2222    2.... 44526245us : disk_release: pmem1s
 systemd--2223    4.... 44573945us : bio_integrity_endio: pmem1s
    <...>-409     4.... 44574005us : bio_integrity_process: pmem1s
 ---------------------------------
[..]
  Call Trace:
  [<ffffffff8144e0f9>] ? bio_integrity_process+0x159/0x2d0
  [<ffffffff8144e4f6>] bio_integrity_verify_fn+0x36/0x60
  [<ffffffff810bd2dc>] process_one_work+0x1cc/0x4e0

Given that a request_queue is pinned while i/o is in flight and that a
gendisk is allowed to have a shorter lifetime, move blk_integrity to
request_queue to satisfy requests arriving after the gendisk has been
torn down.

Cc: Christoph Hellwig <hch@lst.de>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
[martin: fix the CONFIG_BLK_DEV_INTEGRITY=n case]
Tested-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Synchronize pending i/o against a change in the integrity profile to
avoid the possibility of spurious integrity errors.

Cc: Matthew Wilcox <willy@linux.intel.com>
Acked-by: NKeith Busch <keith.busch@intel.com>
[keith: also protect dynamic integrity registration]
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Now that the integrity profile is statically allocated there is no work
to do when shutting down an integrity enabled block device.

Cc: Matthew Wilcox <willy@linux.intel.com>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: James Bottomley <JBottomley@Odin.com>
Acked-by: NNeilBrown <neilb@suse.com>
Acked-by: NKeith Busch <keith.busch@intel.com>
Acked-by: NVishal Verma <vishal.l.verma@intel.com>
Tested-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Up until now the_integrity profile has been dynamically allocated and
attached to struct gendisk after the disk has been made active.

This causes problems because NVMe devices need to register the profile
prior to the partition table being read due to a mandatory metadata
buffer requirement. In addition, DM goes through hoops to deal with
preallocating, but not initializing integrity profiles.

Since the integrity profile is small (4 bytes + a pointer), Christoph
suggested moving it to struct gendisk proper. This requires several
changes:

 - Moving the blk_integrity definition to genhd.h.

 - Inlining blk_integrity in struct gendisk.

 - Removing the dynamic allocation code.

 - Adding helper functions which allow gendisk to set up and tear down
   the integrity sysfs dir when a disk is added/deleted.

 - Adding a blk_integrity_revalidate() callback for updating the stable
   pages bdi setting.

 - The calls that depend on whether a device has an integrity profile or
   not now key off of the bi->profile pointer.

 - Simplifying the integrity support routines in DM (Mike Snitzer).
Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>
Reported-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NSagi Grimberg <sagig@mellanox.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Signed-off-by: NJens Axboe <axboe@fb.com>