IF YOU WOULD LIKE TO GET AN ACCOUNT, please write an
email to Administrator. User accounts are meant only to access repo
and report issues and/or generate pull requests.
This is a purpose-specific Git hosting for
BaseALT
projects. Thank you for your understanding!
Только зарегистрированные пользователи имеют доступ к сервису!
Для получения аккаунта, обратитесь к администратору.
This borrows some code from NAPI and implements a polled completion
mode for block devices. The idea is the same as NAPI - instead of
doing the command completion when the irq occurs, schedule a dedicated
softirq in the hopes that we will complete more IO when the iopoll
handler is invoked. Devices have a budget of commands assigned, and will
stay in polled mode as long as they continue to consume their budget
from the iopoll softirq handler. If they do not, the device is set back
to interrupt completion mode.
This patch holds the core bits for blk-iopoll, device driver support
sold separately.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Instead of just checking whether this device uses block layer
tagging, we can improve the detection by looking at the maximum
queue depth it has reached. If that crosses 4, then deem it a
queuing device.
This is important on high IOPS devices, since plugging hurts
the performance there (it can be as much as 10-15% of the sys
time).
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Get rid of any functions that test for these bits and make callers
use bio_rw_flagged() directly. Then it is at least directly apparent
what variable and flag they check.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Failfast has characteristics from other attributes. When issuing,
executing and successuflly completing requests, failfast doesn't make
any difference. It only affects how a request is handled on failure.
Allowing requests with different failfast settings to be merged cause
normal IOs to fail prematurely while not allowing has performance
penalties as failfast is used for read aheads which are likely to be
located near in-flight or to-be-issued normal IOs.
This patch introduces the concept of 'mixed merge'. A request is a
mixed merge if it is merge of segments which require different
handling on failure. Currently the only mixable attributes are
failfast ones (or lack thereof).
When a bio with different failfast settings is added to an existing
request or requests of different failfast settings are merged, the
merged request is marked mixed. Each bio carries failfast settings
and the request always tracks failfast state of the first bio. When
the request fails, blk_rq_err_bytes() can be used to determine how
many bytes can be safely failed without crossing into an area which
requires further retrials.
This allows request merging regardless of failfast settings while
keeping the failure handling correct.
This patch only implements mixed merge but doesn't enable it. The
next one will update SCSI to make use of mixed merge.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Niel Lambrechts <niel.lambrechts@gmail.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
bio and request use the same set of failfast bits. This patch makes
the following changes to simplify things.
* enumify BIO_RW* bits and reorder bits such that BIOS_RW_FAILFAST_*
bits coincide with __REQ_FAILFAST_* bits.
* The above pushes BIO_RW_AHEAD out of sync with __REQ_FAILFAST_DEV
but the matching is useless anyway. init_request_from_bio() is
responsible for setting FAILFAST bits on FS requests and non-FS
requests never use BIO_RW_AHEAD. Drop the code and comment from
blk_rq_bio_prep().
* Define REQ_FAILFAST_MASK which is OR of all FAILFAST bits and
simplify FAILFAST flags handling in init_request_from_bio().
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Also a debugging aid. We want to catch dirty inodes being added to
backing devices that don't do writeback.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
This enables us to track who does what and print info. Its main use
is catching dirty inodes on the default_backing_dev_info, so we can
fix that up.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
This gets rid of pdflush for bdi writeout and kupdated style cleaning.
pdflush writeout suffers from lack of locality and also requires more
threads to handle the same workload, since it has to work in a
non-blocking fashion against each queue. This also introduces lumpy
behaviour and potential request starvation, since pdflush can be starved
for queue access if others are accessing it. A sample ffsb workload that
does random writes to files is about 8% faster here on a simple SATA drive
during the benchmark phase. File layout also seems a LOT more smooth in
vmstat:
r b swpd free buff cache si so bi bo in cs us sy id wa
0 1 0 608848 2652 375372 0 0 0 71024 604 24 1 10 48 42
0 1 0 549644 2712 433736 0 0 0 60692 505 27 1 8 48 44
1 0 0 476928 2784 505192 0 0 4 29540 553 24 0 9 53 37
0 1 0 457972 2808 524008 0 0 0 54876 331 16 0 4 38 58
0 1 0 366128 2928 614284 0 0 4 92168 710 58 0 13 53 34
0 1 0 295092 3000 684140 0 0 0 62924 572 23 0 9 53 37
0 1 0 236592 3064 741704 0 0 4 58256 523 17 0 8 48 44
0 1 0 165608 3132 811464 0 0 0 57460 560 21 0 8 54 38
0 1 0 102952 3200 873164 0 0 4 74748 540 29 1 10 48 41
0 1 0 48604 3252 926472 0 0 0 53248 469 29 0 7 47 45
where vanilla tends to fluctuate a lot in the creation phase:
r b swpd free buff cache si so bi bo in cs us sy id wa
1 1 0 678716 5792 303380 0 0 0 74064 565 50 1 11 52 36
1 0 0 662488 5864 319396 0 0 4 352 302 329 0 2 47 51
0 1 0 599312 5924 381468 0 0 0 78164 516 55 0 9 51 40
0 1 0 519952 6008 459516 0 0 4 78156 622 56 1 11 52 37
1 1 0 436640 6092 541632 0 0 0 82244 622 54 0 11 48 41
0 1 0 436640 6092 541660 0 0 0 8 152 39 0 0 51 49
0 1 0 332224 6200 644252 0 0 4 102800 728 46 1 13 49 36
1 0 0 274492 6260 701056 0 0 4 12328 459 49 0 7 50 43
0 1 0 211220 6324 763356 0 0 0 106940 515 37 1 10 51 39
1 0 0 160412 6376 813468 0 0 0 8224 415 43 0 6 49 45
1 1 0 85980 6452 886556 0 0 4 113516 575 39 1 11 54 34
0 2 0 85968 6452 886620 0 0 0 1640 158 211 0 0 46 54
A 10 disk test with btrfs performs 26% faster with per-bdi flushing. A
SSD based writeback test on XFS performs over 20% better as well, with
the throughput being very stable around 1GB/sec, where pdflush only
manages 750MB/sec and fluctuates wildly while doing so. Random buffered
writes to many files behave a lot better as well, as does random mmap'ed
writes.
A separate thread is added to sync the super blocks. In the long term,
adding sync_supers_bdi() functionality could get rid of this thread again.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
This is a first step at introducing per-bdi flusher threads. We should
have no change in behaviour, although sb_has_dirty_inodes() is now
ridiculously expensive, as there's no easy way to answer that question.
Not a huge problem, since it'll be deleted in subsequent patches.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
This adds two new exported functions:
- writeback_inodes_sb(), which only attempts to writeback dirty inodes on
this super_block, for WB_SYNC_NONE writeout.
- sync_inodes_sb(), which writes out all dirty inodes on this super_block
and also waits for the IO to complete.
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
When an RSCN indicates changes to individual remote ports,
don't blindly log them out and then back in. Instead, determine
whether they're still in the directory, by doing GPN_ID.
If that is successful, call login, which will send ADISC and reverify,
otherwise, call logoff. Perhaps we should just delete the rport,
not send LOGO, but it seems safer.
Also, fix a possible issue where if a mix of records in the RSCN
cause us to queue disc_ports for disc_single and then we decide
to do full rediscovery, we leak memory for those disc_ports queued.
So, go through the list of disc_ports even if doing full discovery.
Free the disc_ports in any case. If any of the disc_single() calls
return error, do a full discovery.
The ability to fill in GPN_ID requests was added to fc_ct_fill().
For this, it needs the FC_ID to be passed in as an arg.
The did parameter for fc_elsct_send() is used for that, since the
actual D_DID will always be 0xfffffc for all CT requests so far.
Signed-off-by: Joe Eykholt <jeykholt@cisco.com>
Signed-off-by: Robert Love <robert.w.love@intel.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
When rport_login is called on an rport that is already thought
to be logged in, use ADISC. If that fails, redo PLOGI.
This is less disruptive after fabric changes that don't affect
the state of the target.
Implement the sending of ADISC via fc_els_fill.
Add ADISC state to the rport state machine. This is entered from READY
and returns to READY after successful completion. If it fails, the rport
is either logged off and deleted or re-does PLOGI.
Signed-off-by: Joe Eykholt <jeykholt@cisco.com>
Signed-off-by: Robert Love <robert.w.love@intel.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
Improve lport and rport debug messages to indicate whether
the response is LS_ACC, LS_RJT, closed, or timeout.
Signed-off-by: Joe Eykholt <jeykholt@cisco.com>
Signed-off-by: Robert Love <robert.w.love@intel.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
This moves the remote port lookup for incoming ELS requests into
fc_rport.c, in preparation for handing PLOGI and LOGO from
unknown rports.
This changes the arg to rport_recv_req from an rdata to an lport.
Signed-off-by: Joe Eykholt <jeykholt@cisco.com>
Signed-off-by: Robert Love <robert.w.love@intel.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
Currently these values are initialized by the callers. This was exposed
by a later patch that adds PLOGI request support. The patch failed to
initialize the new remote port's roles and it caused problems. This patch
has the rport_create routine initialize the identifiers and then the
callers can override them with real values.
Signed-off-by: Robert Love <robert.w.love@intel.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
On some switches, an empty zone causes GPN_FT to be rejected
with reason 9 (unable) explanation 7 (FC-4 types not registered),
which causes discovery to be retried endlessly. Treat this as
just an empty response and consider discovery complete.
Signed-off-by: Joe Eykholt <jeykholt@cisco.com>
Signed-off-by: Robert Love <robert.w.love@intel.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
When receiving an RSCN, do not log off all rports. This is
extremely disruptive. If, after the GPN_FT response, some
rports haven't been listed, delete them.
Add field disc_id to structs fc_rport_priv and fc_disc.
disc_id is an arbitrary serial number used to identify the
rports found by the latest discovery. This eliminates the need
to go through the rport list when restarting discovery.
Signed-off-by: Joe Eykholt <jeykholt@cisco.com>
Signed-off-by: Robert Love <robert.w.love@intel.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
Delete unused disc->delay element.
Signed-off-by: Joe Eykholt <jeykholt@cisco.com>
Signed-off-by: Robert Love <robert.w.love@intel.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
There was no need to have the discovery status stored in struct fc_disc.
Change fc_disc_done() to take the discovery status as an argument
and just pass it on to the discovery callback.
Signed-off-by: Joe Eykholt <jeykholt@cisco.com>
Signed-off-by: Robert Love <robert.w.love@intel.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
Don't create a "dummy" remote port to go with fc_rport_priv.
Make the rport truly optional by allocating fc_rport_priv separately
and not requiring a dummy rport to be there if we haven't yet done
fc_remote_port_add().
The fc_rport_libfc_priv remains as a structure attached to the
rport for I/O purposes.
Be sure to hold references on rdata when the lock is dropped in
fc_rport_work().
Signed-off-by: Joe Eykholt <jeykholt@cisco.com>
Signed-off-by: Robert Love <robert.w.love@intel.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
Remote ports will become READY more than once after
ADISC is implemented in a later patch.
The event callback that has been called "CREATED" will mean "READY".
Rename it now in preparation for those changes.
Signed-off-by: Joe Eykholt <jeykholt@cisco.com>
Signed-off-by: Robert Love <robert.w.love@intel.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
Allow a struct fc_rport_priv to have no fc_rport associated with it.
This sets up to remove the need for "rogue" rports.
Add a few fields to fc_rport_priv that are needed before the fc_rport
is created. These are the ids, maxframe_size, classes, and rport pointer.
Remove the macro PRIV_TO_RPORT(). Just use rdata->rport where appropriate.
To take the place of the get_device()/put_device ops that were used to
hold both the rport and rdata, add a reference count to rdata structures
using kref. When kref_get decrements the refcount to zero, a new template
function releasing the rdata should be called. This will take care of
freeing the rdata and releasing the hold on the rport (for now). After
subsequent patches make the rport truly optional, this release function
will simply free the rdata.
Remove the simple inline function fc_rport_set_name(), which becomes
semanticly ambiguous otherwise. The caller will set the port_name and
node_name in the rdata->Ids, which will later be copied to the rport
when it its created.
Signed-off-by: Joe Eykholt <jeykholt@cisco.com>
Signed-off-by: Robert Love <robert.w.love@intel.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
tt.elsct_send is used by both FCP and by the rport state machine.
After further patches, these two modules will use different
structures for the remote port.
So, change elsct_send to use the FC_ID instead of the fc_rport_priv
as its argument. It currently only uses the FC_ID anyway.
For CT requests the destination FC_ID is still implicitly 0xfffffc.
After further patches the did arg on CT requests will be used to
specify the FC_ID being inquired about for GPN_ID or other queries.
Signed-off-by: Joe Eykholt <jeykholt@cisco.com>
Signed-off-by: Robert Love <robert.w.love@intel.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
The rport and discovery modules deal with remote ports
before fc_remote_port_add() can be done, because the
full set of rport identifiers is not known at early stages.
In preparation for splitting the fc_rport/fc_rport_priv allocation,
make fc_rport_priv the primary interface for the remote port and
discovery engines.
The FCP / SCSI layers still deal with fc_rport and
fc_rport_libfc_priv, however.
Signed-off-by: Joe Eykholt <jeykholt@cisco.com>
Signed-off-by: Robert Love <robert.w.love@intel.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
These macros introduce extra undesirable semicolons that keep
them from being used in expressions, and they don't protect
against being passed an expression.
Add parens and remove the semicolons.
Signed-off-by: Joe Eykholt <jeykholt@cisco.com>
Signed-off-by: Robert Love <robert.w.love@intel.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
The interface for lport->tt.rport_create() takes a fc_disc_port arg,
which is unnatural for most calls. The only reason for this was
to avoid passing in the local port as an argument, but otherwise
added to complexity.
Simplify by just using lport and fc_rport_identifiers.
Signed-off-by: Joe Eykholt <jeykholt@cisco.com>
Signed-off-by: Robert Love <robert.w.love@intel.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
While the I/O and LLD interfaces use fc_rport_libfc_priv, the
disc and rport interfaces will use fc_rport_priv, which will
be separately allocated.
Change the disc and rport usage of fc_rport_libfc_priv to fc_rport_priv.
Use #define temporarily to make both names equivalent until a
subsequent patch splits them.
Signed-off-by: Joe Eykholt <jeykholt@cisco.com>
Signed-off-by: Robert Love <robert.w.love@intel.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
* topic/tlv-minmax:
ALSA: usb-audio - Correct bogus volume dB information
ALSA: usb-audio - Use the new TLV_DB_MINMAX type
ALSA: Add new TLV types for dBwith min/max
* topic/soundcore-preclaim:
sound: make OSS device number claiming optional and schedule its removal
sound: request char-major-* module aliases for missing OSS devices
chrdev: implement __[un]register_chrdev()
* topic/asoc: (226 commits)
ASoC: au1x: PSC-AC97 bugfixes
ASoC: Fix WM835x Out4 capture enumeration
ASoC: Remove unuused hw_read_t
ASoC: fix pxa2xx-ac97.c breakage
ASoC: Fully specify DC servo bits to update in wm_hubs
ASoC: Debugged improper setting of PLL fields in WM8580 driver
ASoC: new board driver to connect bfin-5xx with ad1836 codec
ASoC: OMAP: Add functionality to set CLKR and FSR sources in McBSP DAI
ASoC: davinci: i2c device creation moved into board files
ASoC: Don't reconfigure WM8350 FLL if not needed
ASoC: Fix s3c-i2s-v2 build
ASoC: Make platform data optional for TLV320AIC3x
ASoC: Add S3C24xx dependencies for Simtec machines
ASoC: SDP3430: Fix TWL GPIO6 pin mux request
ASoC: S3C platform: Fix s3c2410_dma_started() called at improper time
ARM: OMAP: McBSP: Merge two functions into omap_mcbsp_start/_stop
ASoC: OMAP: Fix setup of XCCR and RCCR registers in McBSP DAI
OMAP: McBSP: Use textual values in DMA operating mode sysfs files
ARM: OMAP: DMA: Add support for DMA channel self linking on OMAP1510
ASoC: Select core DMA when building for S3C64xx
...
kvm_para.h contains userspace interface and so
should be exported.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
So far unprivileged guest callers running in ring 3 can issue, e.g., MMU
hypercalls. Normally, such callers cannot provide any hand-crafted MMU
command structure as it has to be passed by its physical address, but
they can still crash the guest kernel by passing random addresses.
To close the hole, this patch considers hypercalls valid only if issued
from guest ring 0. This may still be relaxed on a per-hypercall base in
the future once required.
Cc: stable@kernel.org
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Now KVM allow guest to modify guest's physical address of EPT's identity mapping page.
(change from v1, discard unnecessary check, change ioctl to accept parameter
address rather than value)
Signed-off-by: Sheng Yang <sheng@linux.intel.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Remove kvm_cpu_has_interrupt() and kvm_arch_interrupt_allowed() from
interface between general code and arch code. kvm_arch_vcpu_runnable()
checks for interrupts instead.
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
ioeventfd is a mechanism to register PIO/MMIO regions to trigger an eventfd
signal when written to by a guest. Host userspace can register any
arbitrary IO address with a corresponding eventfd and then pass the eventfd
to a specific end-point of interest for handling.
Normal IO requires a blocking round-trip since the operation may cause
side-effects in the emulated model or may return data to the caller.
Therefore, an IO in KVM traps from the guest to the host, causes a VMX/SVM
"heavy-weight" exit back to userspace, and is ultimately serviced by qemu's
device model synchronously before returning control back to the vcpu.
However, there is a subclass of IO which acts purely as a trigger for
other IO (such as to kick off an out-of-band DMA request, etc). For these
patterns, the synchronous call is particularly expensive since we really
only want to simply get our notification transmitted asychronously and
return as quickly as possible. All the sychronous infrastructure to ensure
proper data-dependencies are met in the normal IO case are just unecessary
overhead for signalling. This adds additional computational load on the
system, as well as latency to the signalling path.
Therefore, we provide a mechanism for registration of an in-kernel trigger
point that allows the VCPU to only require a very brief, lightweight
exit just long enough to signal an eventfd. This also means that any
clients compatible with the eventfd interface (which includes userspace
and kernelspace equally well) can now register to be notified. The end
result should be a more flexible and higher performance notification API
for the backend KVM hypervisor and perhipheral components.
To test this theory, we built a test-harness called "doorbell". This
module has a function called "doorbell_ring()" which simply increments a
counter for each time the doorbell is signaled. It supports signalling
from either an eventfd, or an ioctl().
We then wired up two paths to the doorbell: One via QEMU via a registered
io region and through the doorbell ioctl(). The other is direct via
ioeventfd.
You can download this test harness here:
ftp://ftp.novell.com/dev/ghaskins/doorbell.tar.bz2
The measured results are as follows:
qemu-mmio: 110000 iops, 9.09us rtt
ioeventfd-mmio: 200100 iops, 5.00us rtt
ioeventfd-pio: 367300 iops, 2.72us rtt
I didn't measure qemu-pio, because I have to figure out how to register a
PIO region with qemu's device model, and I got lazy. However, for now we
can extrapolate based on the data from the NULLIO runs of +2.56us for MMIO,
and -350ns for HC, we get:
qemu-pio: 153139 iops, 6.53us rtt
ioeventfd-hc: 412585 iops, 2.37us rtt
these are just for fun, for now, until I can gather more data.
Here is a graph for your convenience:
http://developer.novell.com/wiki/images/7/76/Iofd-chart.png
The conclusion to draw is that we save about 4us by skipping the userspace
hop.
--------------------
Signed-off-by: Gregory Haskins <ghaskins@novell.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Today kvm_io_bus_regsiter_dev() returns void and will internally BUG_ON
if it fails. We want to create dynamic MMIO/PIO entries driven from
userspace later in the series, so we need to enhance the code to be more
robust with the following changes:
1) Add a return value to the registration function
2) Fix up all the callsites to check the return code, handle any
failures, and percolate the error up to the caller.
3) Add an unregister function that collapses holes in the array
Signed-off-by: Gregory Haskins <ghaskins@novell.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
When kvm is in hpet_legacy_mode, the hpet is providing the timer
interrupt and the pit should not be. So in legacy mode, the pit timer
is destroyed, but the *state* of the pit is maintained. So if kvm or
the guest tries to modify the state of the pit, this modification is
accepted, *except* that the timer isn't actually started. When we exit
hpet_legacy_mode, the current state of the pit (which is up to date
since we've been accepting modifications) is used to restart the pit
timer.
The saved_mode code in kvm_pit_load_count temporarily changes mode to
0xff in order to destroy the timer, but then restores the actual
value, again maintaining "current" state of the pit for possible later
reenablement.
[avi: add some reserved storage in the ioctl; make SET_PIT2 IOW]
[marcelo: fix memory corruption due to reserved storage]
Signed-off-by: Beth Kon <eak@us.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
