Commit graph

2103 commits

Author SHA1 Message Date
Matthew Wilcox
7f53f9d242 NVMe: Correct the Controller Configuration settings
The arbitration field was extended by one bit, shifting the shutdown
notification bits by one.  Also, the SQ/CQ entry size was made
configurable for future extensions.

Reported-by: Paul Luse <paul.e.luse@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:53:01 -04:00
Matthew Wilcox
8ef700678f NVMe: Version 0.5
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:53:01 -04:00
Matthew Wilcox
6c7d49455c NVMe: Change the definition of nvme_user_io
The read and write commands don't define a 'result', so there's no need
to copy it back to userspace.

Remove the ability of the ioctl to submit commands to a different
namespace; it's just asking for trouble, and the use case I have in mind
will be addressed througha  different ioctl in the future.  That removes
the need for both the block_shift and nsid arguments.

Check that the opcode is one of 'read' or 'write'.  Future opcodes may
be added in the future, but we will need a different structure definition
for them.

The nblocks field is redefined to be 0-based.  This allows the user to
request the full 65536 blocks.

Don't byteswap the reftag, apptag and appmask.  Martin Petersen tells
me these are calculated in big-endian and are transmitted to the device
in big-endian.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:53:01 -04:00
Matthew Wilcox
4948168280 NVMe: Add compat_ioctl
Make ioctls work for 32-bit applications on 64-bit kernels.  The structures
are defined to be the same for both 32- and 64-bit applications, so
we can use the same handler for both.

Reported-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:53:01 -04:00
Matthew Wilcox
9ecdc94621 NVMe: Simplify queue lookup
Fill in all the num_possible_cpus() entries with duplicate pointers.
This reduces the complexity of the frequently-called get_nvmeq(), as
well as avoiding a bug in it when there are fewer queues than CPUs.

Reported-by: Shane Michael Matthews <shane.matthews@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:53:01 -04:00
Matthew Wilcox
3cb967c039 NVMe: Remove the kthread from the wait queue
Once there are no more bios on the congestion list, we can stop waking
up the nvme kthread every time a completion happens.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:53:00 -04:00
Matthew Wilcox
7523d834dd NVMe: Fix off-by-one when filling in PRP lists
If the last element in the PRP list fits on the end of the page, there's
no need to allocate an extra page to put that single element in.  It can
fit on the end of the page.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:53:00 -04:00
Matthew Wilcox
ac88c36a38 NVMe: Fix interpretation of 'Number of Namespaces' field
The spec says this is a 0s based value.  We don't need to handle the
maximal value because it's reserved to mean "every namespace".

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:53:00 -04:00
Matthew Wilcox
19e899b2f9 NVMe: Remove outdated comments
The head can never overrun the tail since we won't allocate enough command
IDs to let that happen.  The status codes are in sync with the spec.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:53:00 -04:00
Matthew Wilcox
fa92282149 NVMe: Fix comment formatting
Reported-by: Randy Dunlap <rdunlap@xenotime.net>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:53:00 -04:00
Matthew Wilcox
714a7a2288 NVMe: Convert comments to kernel-doc notation
Reported-by: Randy Dunlap <rdunlap@xenotime.net>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:53:00 -04:00
Matthew Wilcox
b57ab0fada NVMe: Version 0.4
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:59 -04:00
Matthew Wilcox
e6d15f79f9 NVMe: Reduce maximum queue depth by 1
The spec says we're not allowed to completely fill the submission queue.
Solve this by reducing the number of allocatable cmdids by 1.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:59 -04:00
Matthew Wilcox
d8ee9d69f2 NVMe: Fix discontiguous accesses
When we submit subsequent portions of the I/O, we need to access the
updated block, not start reading again from the original position.
This was showing up as miscompares in the XFS randholes testcase.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:59 -04:00
Matthew Wilcox
1ad2f8932a NVMe: Handle bios that contain non-virtually contiguous addresses
NVMe scatterlists must be virtually contiguous, like almost all I/Os.
However, when the filesystem lays out files with a hole, it can be that
adjacent LBAs map to non-adjacent virtual addresses.  Handle this by
submitting one NVMe command at a time for each virtually discontiguous
range.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:59 -04:00
Matthew Wilcox
00df5cb4eb NVMe: Implement Flush
Linux implements Flush as a bit in the bio.  That means there may also be
data associated with the flush; if so the flush should be sent before the
data.  To avoid completing the bio twice, I add CMD_CTX_FLUSH to indicate
the completion routine should do nothing.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:59 -04:00
Matthew Wilcox
c42705592b NVMe: Mark CMD_CTX_CANCELLED as being unlikely
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:59 -04:00
Matthew Wilcox
7547881d09 NVMe: Correct SQ doorbell semantics
The value written to the doorbell needs to be the first free index in
the queue, not the most recently used index in the queue.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:58 -04:00
Matthew Wilcox
740216fc59 NVMe: Let the kthread take care of devices earlier
If interrupts are misconfigured, the kthread will be needed to process
admin queue completions.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:58 -04:00
Matthew Wilcox
b348b7d543 NVMe: Rename nr_queues to nr_io_queues
I got confused about whether this included the admin queue or not, and
had to resort to reading the spec.  It doesn't include the admin queue,
so make that clear in the name.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:58 -04:00
Matthew Wilcox
ca1615424c NVMe: Remove setting of 'flags' in rw command
This was the data transfer bit until spec rev 0.92

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:58 -04:00
Matthew Wilcox
ad8a5df97c NVMe: Release 0.3
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:58 -04:00
Matthew Wilcox
1fa6aeadf1 NVMe: Add a kthread to handle the congestion list
Instead of trying to resubmit I/Os in the I/O completion path (in
interrupt context), wake up a kthread which will resubmit I/O from
user context.  This allows mke2fs to run to completion.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:58 -04:00
Matthew Wilcox
eeee322647 NVMe: Handle failures differently in nvme_submit_bio_queue()
Return -EBUSY if the queue is full or -ENOMEM if we failed to allocate
memory (or map a scatterlist).  Also use GFP_ATOMIC to allocate the
nvme_bio and move the locking to the callers of nvme_submit_bio_queue().

In nvme_make_request(), don't permit an I/O to jump the queue -- if the
congestion list already has an entry, just add to the tail, rather than
trying to submit.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:58 -04:00
Matthew Wilcox
768308400f NVMe: Handle physical merging of bvec entries
In order to not overrun the sg array, we have to merge physically
contiguous pages into a single sg entry.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:57 -04:00
Matthew Wilcox
1974b1ae88 NVMe: Check for DMA mapping failure
If dma_map_sg returns 0 (failure), we need to fail the I/O.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:57 -04:00
Matthew Wilcox
d567760c40 NVMe: Pass the nvme_dev to nvme_free_prps and nvme_setup_prps
We were passing the nvme_queue to access the q_dmadev for the
dma_alloc_coherent calls, but since we moved to the dma pool API,
we really only need the nvme_dev.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:57 -04:00
Matthew Wilcox
99802a7aee NVMe: Optimise memory usage for I/Os between 4k and 128k
Add a second memory pool for smaller I/Os.  We can pack 16 of these on a
single page instead of using an entire page for each one.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:57 -04:00
Matthew Wilcox
091b609258 NVMe: Switch to use DMA Pool API
Calling dma_free_coherent from interrupt context causes warnings.
Using the DMA pools delays freeing until pool destruction, so avoids
the problem.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:57 -04:00
Matthew Wilcox
d534df3c73 NVMe: Rename nvme_req_info to nvme_bio
There are too many things called 'info' in this driver.  This data
structure is auxiliary information for a struct bio, so call it nvme_bio,
or nbio when used as a variable.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:56 -04:00
Shane Michael Matthews
e025344c56 NVMe: Initial PRP List support
Add a pointer to the nvme_req_info to hold a new data structure
(nvme_prps) which contains a list of the pages allocated to this
particular request for holding PRP list entries.  nvme_setup_prps()
now returns this pointer.

To allocate and free the memory used for PRP lists, we need a struct
device, so we need to pass the nvme_queue pointer to many functions
which didn't use to need it.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:56 -04:00
Matthew Wilcox
51882d00f0 NVMe: Advance the sg pointer when filling in an sg list
For multipage BIOs, we were always using sg[0] instead of advancing
through the list.  Oops :-)

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:56 -04:00
Matthew Wilcox
d2d8703481 NVMe: Renumber the special context values
If POISON_POINTER_DELTA isn't defined, ensure they're in page 0 which
should never be mapped.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:56 -04:00
Matthew Wilcox
9294bbed78 NVMe: Handle the congestion list a little better
In the bio completion handler, check for bios on the congestion list
for this NVM queue.  Also, lock the congestion list in the make_request
function as the queue may end up being shared between multiple CPUs.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:56 -04:00
Matthew Wilcox
e85248e516 NVMe: Record the timeout for each command
In addition to recording the completion data for each command, record
the anticipated completion time.  Choose a timeout of 5 seconds for
normal I/Os and 60 seconds for admin I/Os.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:56 -04:00
Matthew Wilcox
ec6ce618d6 NVMe: Need to lock queue during interrupt handling
If we're sharing a queue between multiple CPUs and we cancel a sync I/O,
we must have the queue locked to avoid corrupting the stack of the thread
that submitted the I/O.  It turns out this is the same locking that's needed
for the threaded irq handler, so share that code.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:56 -04:00
Matthew Wilcox
48e3d39816 NVMe: Detect command IDs completing that are out of range
If the adapter completes a command ID that is outside the bounds of
the array, return CMD_CTX_INVALID instead of random data, and print a
message in the sync_completion handler (which is rapidly becoming the
misc completion handler :-)

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:55 -04:00
Matthew Wilcox
b36235df01 NVMe: Detect commands that are completed twice
Set the context value to CMD_CTX_COMPLETED, and print a message in the
sync_completion handler if we see it.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:55 -04:00
Matthew Wilcox
be7b62754e NVMe: Use a symbolic name to represent cancelled commands instead of 0
I have plans for other special values in sync_completion.  Plus, this
is more self-documenting, and lets us detect bogus usages.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:55 -04:00
Matthew Wilcox
58ffacb545 NVMe: Add a module parameter to use a threaded interrupt
We're currently calling bio_endio from hard interrupt context.  This is
not a good idea for preemptible kernels as it will cause longer latencies.
Using a threaded interrupt will run the entire queue processing mechanism
(including bio_endio) in a thread, which can be preempted.  Unfortuantely,
it also adds about 7us of latency to the single-I/O case, so make it a
module parameter for the moment.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:55 -04:00
Matthew Wilcox
b1ad37efca NVMe: Call put_nvmeq() before calling nvme_submit_sync_cmd()
We can't have preemption disabled when we call schedule().  Accept the
possibility that we'll get preempted, and it'll cost us some cacheline
bounces.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:55 -04:00
Matthew Wilcox
3c0cf138d7 NVMe: Allow fatal signals to interrupt I/O
If the user sends a fatal signal, sleeping in the TASK_KILLABLE state
permits the task to be aborted.  The only wrinkle is making sure that
if/when the command completes later that it doesn't upset anything.
Handle this by setting the data pointer to 0, and checking the value
isn't NULL in the sync completion path.  Eventually, bios can be cancelled
through this path too.  Note that the cmdid isn't freed to prevent reuse.

We should also abort the command in the future, but this is a good start.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:55 -04:00
Matthew Wilcox
db5d0c198d NVMe: Release 0.2
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:54 -04:00
Matthew Wilcox
6ee44cdced NVMe: Add download / activate firmware ioctls
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:54 -04:00
Matthew Wilcox
388f037f4e NVMe: Move sysfs entries to the right place
Because I wasn't setting driverfs_dev, the devices were showing up under
/sys/devices/virtual/block.  Now they appear underneath the PCI device
which they belong to.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:54 -04:00
Shane Michael Matthews
5911f20039 NVMe: Disable the device before we write the admin queues
In case the card has been left in a partially-configured state,
write 0 to the Enable bit.

Signed-off-by: Shane Michael Matthews <shane.matthews@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:54 -04:00
Matthew Wilcox
574e8b95bc NVMe: Request I/O regions
Calling pci_request_selected_regions() reserves these regions for our use.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:54 -04:00
Matthew Wilcox
2930353f9f NVMe: Allow queues to be allocated above 4GB
Need to call dma_set_coherent_mask() to allow queues to be allocated
above 4GB.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:53 -04:00
Matthew Wilcox
f64d3365a3 NVMe: Enable device DMA
Need to call pci_set_master() to enable device DMA

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:53 -04:00
Shane Michael Matthews
0ee5a7d7cb NVMe: Enable and disable the PCI device
Call pci_enable_device_mem() at initialisation and pci_disable_device
at exit.

Signed-off-by: Shane Michael Matthews <shane.matthews@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
2011-11-04 15:52:53 -04:00