Anton Vorontsov [Fri, 17 Jun 2011 16:10:46 +0000 (20:10 +0400)]
kvm tools: Fix broken terminal when kvm exits because of a signal
Issuing 'killall kvm' leaves the terminal on which kvm was running in
a broken state. This is because atexit(3) handlers are not called if
a process terminates because of a signal.
Installing a proper handler for the TERM signal fixes the issue.
p.s. The rest of the kvm tools use signal(2), and not sigaction(2), so
I continue the tradition.
Signed-off-by: Anton Vorontsov <cbouatmailru@gmail.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
Pekka Enberg [Thu, 16 Jun 2011 14:18:58 +0000 (17:18 +0300)]
kvm tools, qcow: Use fdatasync() instead of sync_file_range()
As explained by Christoph Hellwig, sync_file_range() is not sufficient to
guarantee that Qcow image metadata is never corrupted:
On Thu, Jun 16, 2011 at 12:34:04PM +0300, Pekka Enberg wrote:
> Hi Christoph,
>
> On Thu, Jun 16, 2011 at 09:21:03AM +0300, Pekka Enberg wrote:
> >> And btw, we use sync_file_range()
>
> On Thu, Jun 16, 2011 at 12:24 PM, Christoph Hellwig <hch@infradead.org> wrote:
> > Which doesn't help you at all. ?sync_file_range is just a hint for VM
> > writeback, but never commits filesystem metadata nor the physical
> > disk's write cache. ?In short it's a completely dangerous interface, and
> > that is pretty well documented in the man page.
>
> Doh - I didn't read it carefully enough and got hung up with:
>
> Therefore, unless the application is strictly performing overwrites of
> already-instantiated disk blocks, there are no guarantees that the data will
> be available after a crash.
>
> without noticing that it obviously doesn't work with filesystems like
> btrfs that do copy-on-write.
You also missed:
" This system call does not flush disk write caches and thus does not
provide any data integrity on systems with volatile disk write
caches."
so it's not safe if you either have a cache, or are using btrfs, or
are using a sparse image, or are using an image preallocated using
fallocate/posix_fallocate.
> What's the right thing to do here? Is fdatasync() sufficient?
Yes.
Cc: Ingo Molnar <mingo@elte.hu> Cc: Prasad Joshi <prasadjoshi124@gmail.com> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Pekka Enberg <penberg@kernel.org>
Prasad Joshi [Fri, 10 Jun 2011 10:35:20 +0000 (11:35 +0100)]
kvm tools: Add IO delay option
Add a command line debug option to add a fix amount of delay in read and
write operation.
From Ingo "the delays are *constant* [make sure you use a high-res timers
kernel], so they do not result in nearly as much measurement noise as real
block IO does.
[...]
This way you are basically 'emulating' a real disk drive but you will
emulate uniform latencies, which makes measurements a lot more
reliable - while still relevant to the end result."
Cyrill Gorcunov [Tue, 7 Jun 2011 19:41:16 +0000 (23:41 +0400)]
kvm tools: Reform bios make rules
Put bios code into bios.s and adjust makefile
rules accordingly. It's more natural than bios-rom.S
(which is now simply a container over real bios code).
Also improve bios deps in Makefile.
Signed-off-by: Cyrill Gorcunov <gorcunov@gmail.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
Pekka Enberg [Tue, 7 Jun 2011 19:48:32 +0000 (22:48 +0300)]
kvm, ui: Kill fb_write() function
This patch kills fb_write() and related functions because they're no longer
called as of commit 6768f73 ("kvm tools, vesa: Use guest-mapped memory for
framebuffer").
Cc: Cyrill Gorcunov <gorcunov@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: John Floren <john@jfloren.net> Cc: Sasha Levin <levinsasha928@gmail.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
Prasad Joshi [Mon, 6 Jun 2011 19:58:24 +0000 (20:58 +0100)]
kvm tools: Add QCOW level2 caching support
QCOW uses two tables level1 (L1) table and level2 (L2) table. The L1 table
points to offset of L2 table. When a QCOW image is probed, the L1 table is
cached in the memory to avoid reading it from disk on every access. This
caching improves the performance.
The similar performance improvement can be observed when L2 tables are cached.
It is impossible to cache all of the L2 tables because of the memory
constraint. The patch adds L2 table caching capability for up to 32 L2 tables,
it uses combination of RB tree and List to manage the L2 cached tables. The
link list implementation helps in building simple LRU structure and RB tree
helps to search cached table efficiently.
To calculate the performance numbers, the VM was started with following
command line arguments
Run status group 1 (all jobs):
READ: io=409600KB, aggrb=231151KB/s, minb=59174KB/s, maxb=96111KB/s,
mint=1091msec, maxt=1772msec
WRITE: io=141936KB, aggrb=137268KB/s, minb=32340KB/s, maxb=44496KB/s,
mint=813msec, maxt=1034msec
Run status group 2 (all jobs):
READ: io=409600KB, aggrb=9211KB/s, minb=2358KB/s, maxb=2363KB/s,
mint=44367msec, maxt=44468msec
WRITE: io=129808KB, aggrb=2931KB/s, minb=707KB/s, maxb=797KB/s,
mint=43331msec, maxt=44285msec
Run status group 3 (all jobs):
READ: io=409600KB, aggrb=170453KB/s, minb=43636KB/s, maxb=78545KB/s,
mint=1335msec, maxt=2403msec
WRITE: io=138256KB, aggrb=108012KB/s, minb=27648KB/s, maxb=37931KB/s,
mint=879msec, maxt=1280msec
Disk stats (read/write):
vda: ios=120698/16690, merge=0/114742, ticks=113170/304480, in_queue=417560,
util=93.26%
[...]
Summary
=======
Read bandwidth increased by 1.2 to 1.8 times
Write bandwidth increased by 1.1 to 2.9 times
Read latency decreased by small margin of 0.2
Write latency decreased by 0.4
Signed-off-by: Prasad Joshi <prasadjoshi124@gmail.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
Pekka Enberg [Mon, 6 Jun 2011 13:48:50 +0000 (16:48 +0300)]
kvm tools, vesa: Use guest-mapped memory for framebuffer
This patch converts hw/vesa.c to use guest-mapped memory for framebuffer and
drops the slow MMIO emulation. This speeds up framebuffer accesses
considerably. Please note that this can be optimized even more with the
KVM_GET_DIRTY_LOG ioctl() as explained by Alexander Graf.
Cc: Alexander Graf <agraf@suse.de> Cc: Cyrill Gorcunov <gorcunov@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: John Floren <john@jfloren.net> Cc: Sasha Levin <levinsasha928@gmail.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
Sasha Levin [Fri, 3 Jun 2011 19:51:08 +0000 (22:51 +0300)]
kvm tools: Add MMIO coalescing support
Coalescing MMIO allows us to avoid an exit every time we have a
MMIO write, instead - MMIO writes are coalesced in a ring which
can be flushed once an exit for a different reason is needed.
A MMIO exit is also trigged once the ring is full.
Coalesce all MMIO regions registered in the MMIO mapper.
Add a coalescing handler under kvm_cpu.
Signed-off-by: Sasha Levin <levinsasha928@gmail.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
The kbd_out() function was taking 32 bits instead of 8 bits for 'outb'. This
caused kbd_write_command() to receive bogus 'val' which meant that
I8042_CMD_CTL_RCTR case in the switch statement was never executed.
Pekka Enberg [Thu, 2 Jun 2011 10:47:44 +0000 (13:47 +0300)]
kvm tools, i8042: Use kernel command names
This patch renames the command constants in hw/i8042.c to use similar names as
in <linux/i8042.h>. Note: we cannot use <linux/i8042.h> constants directly
because they include the command and data.
John Floren [Wed, 1 Jun 2011 14:53:56 +0000 (17:53 +0300)]
kvm tools: Add support for PS/2 keyboard system
Add support for PS/2 keyboard system with AUX device (aka mouse).
The device works with vnc, the guest must be started with the
'--vnc' parameter for the device to be initialized.
Signed-off-by: John Floren <john@jfloren.net>
[ turn into patch and clean up code ] Signed-off-by: Sasha Levin <levinsasha928@gmail.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
Sasha Levin [Mon, 30 May 2011 17:27:57 +0000 (20:27 +0300)]
kvm tools: Add debug mode to brlock
Adds a debug mode which allows to switch the brlock into
a big rwlock.
This can be used to verify we don't end up with a BKL kind
of lock with the current brlock implementation.
Signed-off-by: Sasha Levin <levinsasha928@gmail.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
Sasha Levin [Mon, 30 May 2011 17:27:55 +0000 (20:27 +0300)]
kvm tools: Add a brlock
brlock is a lock which is very cheap for reads, but very expensive
for writes.
This lock will be used when updates are very rare and reads are
common.
This lock is currently implemented by stopping the guest while
performing the updates. We assume that the only threads which
read from the locked data are VCPU threads, and the only writer
isn't a VCPU thread.
Signed-off-by: Sasha Levin <levinsasha928@gmail.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
Sasha Levin [Mon, 30 May 2011 17:27:52 +0000 (20:27 +0300)]
kvm tools: Add APIs to allow pausing guests
Allow pausing and unpausing guests running on the host.
Pausing a guest means that none of the VCPU threads are running
KVM_RUN until they are unpaused.
The following API functions are added:
void kvm__pause(void);
void kvm__continue(void);
void kvm__notify_paused(void);
Signed-off-by: Sasha Levin <levinsasha928@gmail.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
Ingo Molnar [Sun, 29 May 2011 12:51:48 +0000 (14:51 +0200)]
kvm tools: Fix virtio net build breakage on 32-bit
* Sasha Levin <levinsasha928@gmail.com> wrote:
> Use ioeventfds to receive notifications of IO events in virtio-net.
> Doing so prevents an exit every time we receive/send a packet.
>
> Signed-off-by: Sasha Levin <levinsasha928@gmail.com>
> ---
> tools/kvm/virtio/net.c | 22 ++++++++++++++++++++++
> 1 files changed, 22 insertions(+), 0 deletions(-)
This needs the fix below to build on 32-bit.
Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Pekka Enberg <penberg@kernel.org>
Sasha Levin [Fri, 27 May 2011 16:18:37 +0000 (19:18 +0300)]
kvm tools: Add ioeventfd support
ioeventfd is way provided by KVM to receive notifications about
reads and writes to PIO and MMIO areas within the guest.
Such notifications are usefull if all we need to know is that
a specific area of the memory has been changed, and we don't need
a heavyweight exit to happen.
The implementation uses epoll to scale to large number of ioeventfds.
Benchmarks ran on a seperate (non boot) 1GB virtio-blk device, formatted
as ext4, using bonnie++.
Sasha Levin [Thu, 26 May 2011 14:25:46 +0000 (17:25 +0300)]
kvm tools: Exit VCPU thread only when SIGKVMEXIT is received
Currently the VCPU loop would exit when the thread received any signal.
Change behaviour to exit only when SIGKVMEXIT is received. This change
prevents from the guest to terminate when unrelated signals are processed
by the thread (for example, when attaching a debugger).
Signed-off-by: Sasha Levin <levinsasha928@gmail.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
Sasha Levin [Thu, 26 May 2011 10:30:07 +0000 (13:30 +0300)]
kvm tools: Add support for multiple virtio-rng devices
Since multiple hardware rng devices of the same type are currently
unsupported by the kernel, this serves more as an example of a basic
virtio driver under kvm tools and can be used to debug the PCI layer.
Signed-off-by: Sasha Levin <levinsasha928@gmail.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
Sasha Levin [Thu, 26 May 2011 10:30:06 +0000 (13:30 +0300)]
kvm tools: Use ioport context to control blk devices
Since ioports now has the ability to pass context to its
callbacks, we can implement multiple blk devices more efficiently.
We can get a ptr to the 'current' blk dev on each ioport call, which
means that we don't need to keep track of the blk device allocation
and ioport distribution within the module.
The advantages are easier management of multiple blk devices and
removal of any hardcoded limits to the amount of possible blk
devices.
Signed-off-by: Sasha Levin <levinsasha928@gmail.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
Sasha Levin [Thu, 26 May 2011 10:30:04 +0000 (13:30 +0300)]
kvm tools: Add optional parameter used in ioport callbacks
Allow specifying an optional parameter when registering an
ioport range. The callback functions provided by the registering
module will be called with the same parameter.
This may be used to keep context during callbacks on IO operations.
Signed-off-by: Sasha Levin <levinsasha928@gmail.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
Cyrill Gorcunov [Mon, 23 May 2011 14:39:17 +0000 (18:39 +0400)]
kvm tools: Drop unused vars from int10.c code
There is a couple of functions which defines 'ah' variable but
never use it in real so that gcc 4.6.x series does complain on
me as
CC bios/bios-rom.bin
bios/int10.c: In function ‘int10_putchar’:
bios/int10.c:86:9: error: variable ‘ah’ set but not used [-Werror=unused-but-set-variable]
bios/int10.c: In function ‘int10_vesa’:
bios/int10.c:96:9: error: variable ‘ah’ set but not used [-Werror=unused-but-set-variable]
cc1: all warnings being treated as errors
Start VNC server by starting kvm tools with "--vnc".
Connect to the VNC server by running: "vncviewer :0".
Since there is no support for input devices at this time,
it may be useful starting kvm tools with an additional
' -p "console=ttyS0" ' parameter so that it would be possible
to use a serial console alongside with a graphic one.
Signed-off-by: John Floren <john@jfloren.net>
[ turning code into patches and cleanup ] Signed-off-by: Sasha Levin <levinsasha928@gmail.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
John Floren [Mon, 23 May 2011 12:15:17 +0000 (15:15 +0300)]
kvm tools: Update makefile and feature tests
Update feature tests to test for libvncserver.
VESA support doesn't get compiled in unless libvncserver
is installed.
Signed-off-by: John Floren <john@jfloren.net>
[ turning code into patches and cleanup ] Signed-off-by: Sasha Levin <levinsasha928@gmail.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
John Floren [Mon, 23 May 2011 12:15:16 +0000 (15:15 +0300)]
kvm tools: Add VESA device
Add a simple VESA device which simply moves a framebuffer
from guest kernel to a VNC server.
VESA device PCI code is very similar to virtio-* PCI code.
Signed-off-by: John Floren <john@jfloren.net>
[ turning code into patches and cleanup ] Signed-off-by: Sasha Levin <levinsasha928@gmail.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
John Floren [Mon, 23 May 2011 12:15:15 +0000 (15:15 +0300)]
kvm tools: Add video mode to kernel initialization
Allow setting video mode in guest kernel.
For possible values see Documentation/fb/vesafb.txt
Signed-off-by: John Floren <john@jfloren.net>
[ turning code into patches and cleanup ] Signed-off-by: Sasha Levin <levinsasha928@gmail.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
John Floren [Mon, 23 May 2011 12:15:14 +0000 (15:15 +0300)]
kvm tools: Add BIOS INT10 handler
INT10 handler is a basic implementation of BIOS video services.
The handler implements a VESA interface which is initialized at
the very beginning of loading the kernel.
Signed-off-by: John Floren <john@jfloren.net>
[ turning code into patches and cleanup ] Signed-off-by: Sasha Levin <levinsasha928@gmail.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
Prasad Joshi [Sun, 22 May 2011 16:24:04 +0000 (17:24 +0100)]
kvm tools: Add a wrapper function to open disk images
The patch was suggested by Ingo to move the disk image subsystem code
from the kvm-run.c file. The code to open all of the specified disk
images is now moved to a wrapper function in disk/core.c.
Cyrill Gorcunov [Sat, 21 May 2011 12:10:34 +0000 (16:10 +0400)]
kvm tools, 9p: Test for tuncation result
Without 'ret' usage I get
| cyrill@sun kvm $ make
| CC virtio/9p.o
| virtio/9p.c: In function ‘virtio_p9_wstat’:
| virtio/9p.c:448:6: error: variable ‘res’ set but not used [-Werror=unused-but-set-variable]
| cc1: all warnings being treated as errors
| make: *** [virtio/9p.o] Error 1
so add a basic check for ftruncate result, this eliminate warning and
we might need to use 'res' status later in caller code.
Pekka Enberg [Sat, 21 May 2011 12:04:10 +0000 (15:04 +0300)]
kvm tools, serial: Register 0x2e8 ioport
We already register ioports for 0x2f8 and 0x3e8 and mark them as inactive so
mark 0x2e8 ioport as such as well. This is a preparational step to dropping
serial port dummy registrations from ioport__setup_legacy().
Sasha Levin [Fri, 20 May 2011 14:23:05 +0000 (17:23 +0300)]
kvm tools: Cleanup e820 code
Several cleanups in the patch:
- Use kernel headers for e820 types and definitions.
- A byte sized entry count for e820 enteries was used,
this should be dword sized. Update in-memory layout and
bios code to fix it.
- Use struct e820map to calculate offsets used by bios code.
Sasha Levin [Fri, 20 May 2011 08:37:09 +0000 (11:37 +0300)]
kvm tools: Add virtio-9p
Overview:
9p allows for simple RPC based resource sharing over
different transports (in our case, virtio).
This is the implementation of (most of) the original
9p2000 protocol, without the .u or the .l extensions.
How to use:
1. Make sure kernel is compiled with:
CONFIG_NET_9P=y
CONFIG_NET_9P_VIRTIO=y
CONFIG_NET_9P_DEBUG=y (At least until code is stable)
CONFIG_9P_FS=y
2. Start KVM with '--virtio-9p <dirname>'. What happens now is that
a virtio transport with the name 'kvm_9p' is created. The server side
of the transport maps dirname to the root of the file system.
3. Within the guest, mount the fs:
mount -t 9p -otrans=virtio kvm_9p <local_dir> -oversion=9p2000
This will mount the 9p server to local_dir.
Signed-off-by: Sasha Levin <levinsasha928@gmail.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
Sasha Levin [Fri, 20 May 2011 08:37:08 +0000 (11:37 +0300)]
kvm tools: Copy net/9p/9p.h
Header could not be included directly because among some minor
issues, the original header declared the same function twice:
int p9_errstr2errno(char *errstr, int len);
int p9_errstr2errno(char *, int);
A patch has been sent to 9P maintainers, this header should
be removed once the patch is in.
Until then, use a modified copy of the header.
Signed-off-by: Sasha Levin <levinsasha928@gmail.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
Cyrill Gorcunov [Wed, 18 May 2011 19:40:51 +0000 (23:40 +0400)]
kvm tools: Fix alignment for mpf_intel table
Thomas and Asias reported that kernel doesn't find MP
tables on 32 bit host. This is because previously the
alignment was done on address obtained from calloc
missing the fact that MP tables are put into guest
memory *with* offset and MP signature should be
calculated keeping this offset in midn as well and
then aligned.
Reported-by: Thomas Heil <heil@terminal-consulting.de> Reported-by: Asias He <asias.hejun@gmail.com> Tested-by: Thomas Heil <heil@terminal-consulting.de> Tested-by: Asias He <asias.hejun@gmail.com> Signed-off-by: Cyrill Gorcunov <gorcunov@gmail.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
Pekka Enberg [Wed, 18 May 2011 19:19:40 +0000 (22:19 +0300)]
kvm tools: Fail if passed initrd is not really an initrd
We recently changed the meaning of "-i" from disk image to initrd. This has
confused many users because kvm just reports:
Fatal: mmap() failed.
if a disk image is passed as initrd. This patch fixes that by checking for the
first two ID bytes in initrd:
$ ./kvm run -i ~/images/linux-0.2.qcow
# kvm run -k ../../arch/x86/boot/bzImage -m 256 -c 1
Fatal: /home/penberg/images/linux-0.2.qcow is not an initrd
Reported-by: Thomas Heil <heil@terminal-consulting.de> Suggested-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Pekka Enberg <penberg@kernel.org>
Cyrill Gorcunov [Wed, 18 May 2011 19:08:57 +0000 (22:08 +0300)]
kvm tools: Add conditional compilation of symbol resolving
Thomas reported that on some systems there might be no bdf
library installed. So we take perf approach and check for
library presence at compilation time.
Reported-by: Thomas Heil <heil@terminal-consulting.de> Tested-by: Thomas Heil <heil@terminal-consulting.de> Signed-off-by: Cyrill Gorcunov <gorcunov@gmail.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
projects / karo-tx-linux.git / log