> -Original Message-
> From: Daniel P. Berrangé
> Sent: Friday, June 17, 2022 4:05 PM
> To: Zhang, Chen
> Cc: Jason Wang ; qemu-dev de...@nongnu.org>; Paolo Bonzini ; Eduardo
> Habkost ; Eric Blake ; Markus
> Armbruster ; Peter Maydell
> ; Thomas Huth ; Laurent
> Vivier ; Yuri
When originally implemented, zero_copy_send was designed as a Migration
paramenter.
But taking into account how is that supposed to work, and how
the difference between a capability and a parameter, it only makes sense
that zero-copy-send would work better as a capability.
Taking into account
Somewhere between v6 and v7 the of the zero-copy-send patchset a crucial
part of the flushing mechanism got missing: incrementing zero_copy_queued.
Without that, the flushing interface becomes a no-op, and there is no
guarantee the buffer is really sent.
This can go as bad as causing a
CC: Jiri Denemark
On Mon, Jun 20, 2022 at 2:40 AM Leonardo Bras wrote:
>
> When originally implemented, zero_copy_send was designed as a Migration
> paramenter.
>
> But taking into account how is that supposed to work, and how
> the difference between a capability and a parameter, it only makes
Patches 1 & 2 are about a fix needed to make zero-copy flush work.
The code that incremented the sendmsg counter ended up missing in
the last versions of the patchset, causing the flush to never
happen.
Patch 3 is about an improvement on flushing that improves
sending performance.
Patch 4 is
When sending memory pages with MSG_ZEROCOPY, it's necessary to flush
to make sure all dirty pages are sent before a future version of them
happens to be sent.
Currently, the flush happens every time at the end of ram_save_iterate(),
which usually happens around 20x per second, due to a timeout.
During implementation of MSG_ZEROCOPY feature, a lot of #ifdefs were
introduced, particularly at qio_channel_socket_writev().
Rewrite some of those changes so it's easier to read.
Also, introduce an assert to help detect incorrect zero-copy usage is when
it's disabled on build.
Signed-off-by:
On Fri, Jun 17, 2022 at 4:17 PM Eugenio Perez Martin
wrote:
>
> On Fri, Jun 17, 2022 at 3:29 AM Jason Wang wrote:
> >
> > On Wed, Jun 15, 2022 at 6:03 PM Eugenio Perez Martin
> > wrote:
> > >
> > > On Wed, Jun 15, 2022 at 5:04 AM Jason Wang wrote:
> > > >
> > > > On Tue, Jun 14, 2022 at 5:32
On 6/18/22 02:50, Daniel Henrique Barboza wrote:
On 6/17/22 03:07, Alexey Kardashevskiy wrote:
It keeps repeating, move it to the header. This uses __builtin_ctzl() to
allow using the macros in #define.
Signed-off-by: Alexey Kardashevskiy
---
Reviewed-by: Daniel Henrique Barboza
Fix some mistakes before. It can report a range of zones now.
Signed-off-by: Sam Li
---
block/block-backend.c | 22
block/coroutines.h| 5 +
block/file-posix.c| 182 ++
block/io.c| 23
On 6/18/22 21:01, Cédric Le Goater wrote:
On 6/17/22 08:07, Alexey Kardashevskiy wrote:
The new PAPR 2.12 defines a watchdog facility managed via the new
H_WATCHDOG hypercall.
This adds H_WATCHDOG support which a proposed driver for pseries uses:
This patch series adds support for zoned device to virtio-blk emulation.
Zoned storage can support sequential writes, which reduces write
amplification in SSD, leading to higher write throughput and increased
capacity.
v1:
- add block layer APIs resembling Linux ZoneBlockDevice ioctls.
By
On 6/19/22 11:05, Warner Losh wrote:
The following changes since commit dcb40541ebca7ec98a14d461593b3cd7282b4fac:
Merge tag 'mips-20220611' of https://github.com/philmd/qemu into staging
(2022-06-11 21:13:27 -0700)
are available in the Git repository at:
Am 12. Juni 2022 19:28:00 UTC schrieb Bernhard Beschow :
>pi440fx_state is an out-parameter which is never read by the caller.
>
>Signed-off-by: Bernhard Beschow
Ping
>---
> hw/i386/pc_piix.c| 3 ---
> hw/pci-host/i440fx.c | 4 +---
> include/hw/pci-host/i440fx.h | 1 -
> 3
Implemenet rmdir and __getcwd. __getcwd is the undocumented
back end to getcwd(3).
Signed-off-by: Stacey Son
Signed-off-by: Jung-uk Kim
Signed-off-by: Warner Losh
Reviewed-by: Richard Henderson
---
bsd-user/bsd-file.h | 29 +
Signed-off-by: Stacey Son
Signed-off-by: Warner Losh
Reviewed-by: Richard Henderson
---
bsd-user/bsd-file.h | 23 +++
bsd-user/freebsd/os-syscall.c | 8
2 files changed, 31 insertions(+)
diff --git a/bsd-user/bsd-file.h b/bsd-user/bsd-file.h
index
Signed-off-by: Stacey Son
Signed-off-by: Warner Losh
Reviewed-by: Richard Henderson
---
bsd-user/bsd-file.h | 27 +++
bsd-user/freebsd/os-syscall.c | 8
2 files changed, 35 insertions(+)
diff --git a/bsd-user/bsd-file.h b/bsd-user/bsd-file.h
index
Signed-off-by: Stacey Son
Signed-off-by: Warner Losh
Reviewed-by: Richard Henderson
---
bsd-user/bsd-file.h | 12
bsd-user/freebsd/os-syscall.c | 8
2 files changed, 20 insertions(+)
diff --git a/bsd-user/bsd-file.h b/bsd-user/bsd-file.h
index
Plus the helper LOCK_PATH2 and UNLOCK_PATH2 macros.
Signed-off-by: Stacey Son
Signed-off-by: Jung-uk Kim
Signed-off-by: Warner Losh
Reviewed-by: Richard Henderson
---
bsd-user/bsd-file.h | 45 +++
bsd-user/freebsd/os-syscall.c | 8 +++
2 files
Signed-off-by: Stacey Son
Signed-off-by: Warner Losh
Reviewed-by: Richard Henderson
---
bsd-user/bsd-file.h | 29 +
bsd-user/freebsd/os-syscall.c | 8
2 files changed, 37 insertions(+)
diff --git a/bsd-user/bsd-file.h b/bsd-user/bsd-file.h
index
Signed-off-by: Stacey Son
Signed-off-by: Warner Losh
Reviewed-by: Richard Henderson
---
bsd-user/bsd-file.h | 53 +++
bsd-user/freebsd/os-syscall.c | 16 +++
2 files changed, 69 insertions(+)
diff --git a/bsd-user/bsd-file.h
Signed-off-by: Stacey Son
Signed-off-by: Jung-uk Kim
Signed-off-by: Warner Losh
Reviewed-by: Richard Henderson
---
bsd-user/bsd-file.h | 54 +++
bsd-user/freebsd/os-syscall.c | 16 +++
2 files changed, 70 insertions(+)
diff --git
Signed-off-by: Stacey Son
Signed-off-by: Warner Losh
Reviewed-by: Richard Henderson
---
bsd-user/bsd-file.h | 19 +++
bsd-user/freebsd/os-syscall.c | 8
2 files changed, 27 insertions(+)
diff --git a/bsd-user/bsd-file.h b/bsd-user/bsd-file.h
index
Implement fdatasync(2), fsync(2) and close_from(2).
Signed-off-by: Stacey Son
Signed-off-by: Jung-uk Kim
Signed-off-by: Warner Losh
Reviewed-by: Richard Henderson
---
bsd-user/bsd-file.h | 19 +++
bsd-user/freebsd/os-syscall.c | 12
2 files changed, 31
Add the open, openat and close system calls. We need to lock paths, so
implmenent that as well.
Signed-off-by: Stacey Son
Signed-off-by: Jung-uk Kim
Signed-off-by: Kyle Evans
Signed-off-by: Warner Losh
Reviewed-by: Richard Henderson
---
bsd-user/bsd-file.h | 49
The following changes since commit dcb40541ebca7ec98a14d461593b3cd7282b4fac:
Merge tag 'mips-20220611' of https://github.com/philmd/qemu into staging
(2022-06-11 21:13:27 -0700)
are available in the Git repository at:
ssh://g...@github.com/qemu-bsd-user/qemu-bsd-user.git
Hello Corey,
On 6/6/22 17:07, Cédric Le Goater wrote:
Hello,
Here is a series aggregating recent changes proposed on the Aspeed
ast2600 I2C controller model.
First comes a large set of changes converting the model to use the
registerfield interface and adding the I2C new register mode
(Joe).
On 6/18/22 01:07, Iris Chen wrote:
Hey everyone,
I discovered that some of the tests in tests/qtest/aspeed_smc-test.c were
failing when run in isolation due to dependencies between the tests. For
example, one test would test the reading of a block of memory written
in the test before it.
I
On Fri, Jun 17, 2022 at 10:44 PM Ani Sinha wrote:
>
> oops, Phil's redhat email bounced!
>
> On Fri, Jun 17, 2022 at 10:41 PM Ani Sinha wrote:
> >
> > Hi :
> > I am trying to write a new ACPI/smbios test framework that uses bios
> > bits (https://biosbits.org/ ).
> > This test will effectively:
Hi,
Many thanks for the feedback. Actually I have investigated this by writing
printfs in between statements to print out the 'self rect' values, and
apparently the statement [normalWindow setFrame:NSMakeRect([normalWindow
frame].origin.x, ... modifies this 'self rect' values, for reason I am not
This applies only on macOS using cocoa UI library.
In zoom-to-fit fullscreen mode, upon graphics mode switch,
the viewport size is wrong, and the usual consequence
is only a part of the screen is visible. One have to exit
and reenter fullscreen mode to fix this.
This is reproducible by setting
On 6/18/22 13:02, Daniel Henrique Barboza wrote:
It's inneficient to scroll all child objects when we have all PHBs
available in chip8->phbs[].
pnv_chip_power8_pic_print_info_child() ended up folded into
pic_print_info() for simplicity.
Reviewed-by: Frederic Barrat
Signed-off-by: Daniel
On 6/18/22 11:01, Joel Stanley wrote:
Signed-off-by: Joel Stanley
Reviewed-by: Cédric Le Goater
Thanks,
C.
---
hw/misc/aspeed_hace.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/hw/misc/aspeed_hace.c b/hw/misc/aspeed_hace.c
index 4b5997e18fad..731234b78c4c
On 6/18/22 13:01, Daniel Henrique Barboza wrote:
pnv_ics_resend() is scrolling through all the child objects of the chip
to search for the PHBs. It's faster and simpler to just use the phbs[]
array.
pnv_ics_resend_child() was folded into pnv_ics_resend() since it's too
simple to justify its own
On 6/18/22 13:01, Daniel Henrique Barboza wrote:
The function is working today by getting all the child objects of the
chip, interacting with each of them to check whether the child is a PHB,
and then doing what needs to be done.
We have all the chip PHBs in the phbs[] array so interacting with
On Wed, 26 Jan 2022 at 23:43, Richard Henderson
wrote:
>
> Reviewed-by: Richard Henderson
>
> r~
Hey, I believe this patch might have accidentally been missed?
Thanks,
Idan Horowitz
36 matches
Mail list logo