fix !PRINTK config build.
(Reported-by: kbuild test robot ).
From: Sergey Senozhatsky
Subject: [PATCH 2/5] printk: introduce printing kernel thread
printk() is quite complex internally and, basically, it does two
slightly
fix !PRINTK config build.
(Reported-by: kbuild test robot ).
From: Sergey Senozhatsky
Subject: [PATCH 2/5] printk: introduce printing kernel thread
printk() is quite complex internally and, basically, it does two
slightly independent things:
a) adds a new message to a
* Thomas Gleixner wrote:
> On Sun, 7 May 2017, Andy Lutomirski wrote:
> > /* context.lock is held for us, so we don't need any locking. */
> > static void flush_ldt(void *current_mm)
> > {
> > + struct mm_struct *mm = current_mm;
> > mm_context_t *pc;
> >
> > -
* Thomas Gleixner wrote:
> On Sun, 7 May 2017, Andy Lutomirski wrote:
> > /* context.lock is held for us, so we don't need any locking. */
> > static void flush_ldt(void *current_mm)
> > {
> > + struct mm_struct *mm = current_mm;
> > mm_context_t *pc;
> >
> > - if
Hi,
On Wed, May 03, 2017 at 11:35:36PM +0200, Milian Wolff wrote:
> When different functions get inlined into the same function, we
> want to show them individually in the reports. But when we group by
> function, we would aggregate all IPs and would only keep the first
> one in that function.
Hi,
On Wed, May 03, 2017 at 11:35:36PM +0200, Milian Wolff wrote:
> When different functions get inlined into the same function, we
> want to show them individually in the reports. But when we group by
> function, we would aggregate all IPs and would only keep the first
> one in that function.
On Tue 09-05-17 21:43:16, Dan Williams wrote:
> On Fri, Apr 21, 2017 at 5:05 AM, Michal Hocko wrote:
> > Hi,
> > The last version of this series has been posted here [1]. It has seen
> > some more testing (thanks to Reza Arbab and Igor Mammedov[2]), Jerome's
> > and Vlastimil's
Please disregard this patch. I think I may have found a bug in Clang,
or at least an incompatibility with GCC 7.1.
Clang bug: https://bugs.llvm.org/show_bug.cgi?id=32985
On Tue 09-05-17 21:43:16, Dan Williams wrote:
> On Fri, Apr 21, 2017 at 5:05 AM, Michal Hocko wrote:
> > Hi,
> > The last version of this series has been posted here [1]. It has seen
> > some more testing (thanks to Reza Arbab and Igor Mammedov[2]), Jerome's
> > and Vlastimil's review resulted in
Please disregard this patch. I think I may have found a bug in Clang,
or at least an incompatibility with GCC 7.1.
Clang bug: https://bugs.llvm.org/show_bug.cgi?id=32985
Please disregard this patch. I think I may have found a bug in Clang,
or at least an incompatibility with GCC 7.1.
Clang bug: https://bugs.llvm.org/show_bug.cgi?id=32985
Please disregard this patch. I think I may have found a bug in Clang,
or at least an incompatibility with GCC 7.1.
Clang bug: https://bugs.llvm.org/show_bug.cgi?id=32985
* Rafael J. Wysocki wrote:
> On Tuesday, May 09, 2017 02:00:51 PM Kees Cook wrote:
> > This switches the hibernate_64.S function names into character arrays
> > to match other areas of the kernel where this is done (e.g., linker
> > scripts). Specifically this fixes a
* Rafael J. Wysocki wrote:
> On Tuesday, May 09, 2017 02:00:51 PM Kees Cook wrote:
> > This switches the hibernate_64.S function names into character arrays
> > to match other areas of the kernel where this is done (e.g., linker
> > scripts). Specifically this fixes a compile-time error noticed
Mr.Torokhov
Hi.
> Could you please test the version of the patch I sent to you? It had
> more changes than the 2 you mentioned above.
Sorry, what did you mail to me with the patch?
I searched old mails, but I couldn't find it.
Please tell me time when you mailed the patch?
Thanks.
---
Mr.Torokhov
Hi.
> Could you please test the version of the patch I sent to you? It had
> more changes than the 2 you mentioned above.
Sorry, what did you mail to me with the patch?
I searched old mails, but I couldn't find it.
Please tell me time when you mailed the patch?
Thanks.
---
> On Tue May 09, 2017 at 02:02:58PM +0100, Robin Murphy wrote:
> > On 09/05/17 12:45, Geetha sowjanya wrote:
> > > From: Linu Cherian
> > >
> > > Cavium ThunderX2 SMMU implementation doesn't support page 1 register space
> > > and PAGE0_REGS_ONLY option is enabled as an
> On Tue May 09, 2017 at 02:02:58PM +0100, Robin Murphy wrote:
> > On 09/05/17 12:45, Geetha sowjanya wrote:
> > > From: Linu Cherian
> > >
> > > Cavium ThunderX2 SMMU implementation doesn't support page 1 register space
> > > and PAGE0_REGS_ONLY option is enabled as an errata workaround.
> > >
> On 10.5.2017, at 0.14, Colin Ian King wrote:
>
> On 09/05/17 22:03, J . Bruce Fields wrote:
>> On Tue, May 09, 2017 at 05:04:14PM +0300, Dan Carpenter wrote:
>>> On Tue, May 09, 2017 at 02:31:21PM +0100, Colin King wrote:
diff --git a/fs/nfsd/nfs4proc.c
> On 10.5.2017, at 0.14, Colin Ian King wrote:
>
> On 09/05/17 22:03, J . Bruce Fields wrote:
>> On Tue, May 09, 2017 at 05:04:14PM +0300, Dan Carpenter wrote:
>>> On Tue, May 09, 2017 at 02:31:21PM +0100, Colin King wrote:
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index
From: Yanjiang Jin
Kexec's second kernel would hang if CPU1 isn't reset.
Signed-off-by: Yanjiang Jin
---
arch/arm/mach-socfpga/platsmp.c | 12 +++-
1 file changed, 11 insertions(+), 1 deletion(-)
diff --git
From: Yanjiang Jin
Kexec's second kernel would hang if CPU1 isn't reset.
Signed-off-by: Yanjiang Jin
---
arch/arm/mach-socfpga/platsmp.c | 12 +++-
1 file changed, 11 insertions(+), 1 deletion(-)
diff --git a/arch/arm/mach-socfpga/platsmp.c b/arch/arm/mach-socfpga/platsmp.c
index
On Tue, May 09, 2017 at 04:16:39PM -0700, Darren Hart wrote:
> Linus and Greg,
>
> We are in the process of redesigning the Windows Management Instrumentation
> (WMI) [1] system in the kernel. WMI is the Microsoft implementation of
> Web-Based
> Enterprise Management (WBEM). We are looking to
On Tue, May 09, 2017 at 04:16:39PM -0700, Darren Hart wrote:
> Linus and Greg,
>
> We are in the process of redesigning the Windows Management Instrumentation
> (WMI) [1] system in the kernel. WMI is the Microsoft implementation of
> Web-Based
> Enterprise Management (WBEM). We are looking to
From: Yanjiang Jin
I guess socfpga's other boards may need this patch, but I have Arria10
board only.
So add a new function socfpga_a10_cpu_kill(), keep the old function
socfpga_cpu_kill() for other boards.
I also verified CPU_HOTPLUG after applying this patch,
From: Yanjiang Jin
I guess socfpga's other boards may need this patch, but I have Arria10
board only.
So add a new function socfpga_a10_cpu_kill(), keep the old function
socfpga_cpu_kill() for other boards.
I also verified CPU_HOTPLUG after applying this patch, everything seems well.
Test
p_assert_hotplug_held();
> jump_label_lock();
> if (atomic_read(>enabled) == 0) {
> atomic_set(>enabled, -1);
I seem to be hitting this assert from the ftrace event selftests,
enabled at boot with CONFIG_FTRACE_STARTUP_TEST=y, using next-20170509
(on powerpc).
[ 842.6
jump_label_lock();
> if (atomic_read(>enabled) == 0) {
> atomic_set(>enabled, -1);
I seem to be hitting this assert from the ftrace event selftests,
enabled at boot with CONFIG_FTRACE_STARTUP_TEST=y, using next-20170509
(on powerpc).
[ 842.691191] Testing event r
Le 10/05/2017 à 06:46, Julia Lawall a écrit :
On Wed, 10 May 2017, Christophe JAILLET wrote:
Le 09/05/2017 à 17:18, Joe Perches a écrit :
On Mon, 2017-05-08 at 17:35 -0700, Florian Fainelli wrote:
On 05/08/2017 04:46 PM, Julia Lawall wrote:
On Mon, 8 May 2017, Joe Perches wrote:
Each
Le 10/05/2017 à 06:46, Julia Lawall a écrit :
On Wed, 10 May 2017, Christophe JAILLET wrote:
Le 09/05/2017 à 17:18, Joe Perches a écrit :
On Mon, 2017-05-08 at 17:35 -0700, Florian Fainelli wrote:
On 05/08/2017 04:46 PM, Julia Lawall wrote:
On Mon, 8 May 2017, Joe Perches wrote:
Each
On 2017-05-09 06:39, David Miller wrote:
> From: Stefan Agner
> Date: Mon, 8 May 2017 22:37:08 -0700
>
>> Since the addition of the multi queue code with commit 59d0f7465644
>> ("net: fec: init multi queue date structure") the queue selection
>> has been handelt by the default
On 2017-05-09 06:39, David Miller wrote:
> From: Stefan Agner
> Date: Mon, 8 May 2017 22:37:08 -0700
>
>> Since the addition of the multi queue code with commit 59d0f7465644
>> ("net: fec: init multi queue date structure") the queue selection
>> has been handelt by the default transmit queue
On Wed, 10 May 2017, Christophe JAILLET wrote:
> Le 09/05/2017 à 17:18, Joe Perches a écrit :
> > On Mon, 2017-05-08 at 17:35 -0700, Florian Fainelli wrote:
> > > On 05/08/2017 04:46 PM, Julia Lawall wrote:
> > > > On Mon, 8 May 2017, Joe Perches wrote:
> > > > > Each time -EPROBE_DEFER occurs,
On Wed, 10 May 2017, Christophe JAILLET wrote:
> Le 09/05/2017 à 17:18, Joe Perches a écrit :
> > On Mon, 2017-05-08 at 17:35 -0700, Florian Fainelli wrote:
> > > On 05/08/2017 04:46 PM, Julia Lawall wrote:
> > > > On Mon, 8 May 2017, Joe Perches wrote:
> > > > > Each time -EPROBE_DEFER occurs,
On Fri, Apr 21, 2017 at 5:05 AM, Michal Hocko wrote:
> Hi,
> The last version of this series has been posted here [1]. It has seen
> some more testing (thanks to Reza Arbab and Igor Mammedov[2]), Jerome's
> and Vlastimil's review resulted in few fixes mostly folded in their
>
On Fri, Apr 21, 2017 at 5:05 AM, Michal Hocko wrote:
> Hi,
> The last version of this series has been posted here [1]. It has seen
> some more testing (thanks to Reza Arbab and Igor Mammedov[2]), Jerome's
> and Vlastimil's review resulted in few fixes mostly folded in their
> respected patches.
>
Fix the following sparse warnings about incorrect type usage:
tcpci.c:290:38: warning: incorrect type in argument 1 (different base types)
tcpci.c:290:38:expected unsigned short [unsigned] [usertype] header
tcpci.c:290:38:got restricted __le16 const [usertype] header
tcpci.c:295:16:
Fix the following sparse warnings about incorrect type usage:
tcpci.c:290:38: warning: incorrect type in argument 1 (different base types)
tcpci.c:290:38:expected unsigned short [unsigned] [usertype] header
tcpci.c:290:38:got restricted __le16 const [usertype] header
tcpci.c:295:16:
Le 09/05/2017 à 17:18, Joe Perches a écrit :
On Mon, 2017-05-08 at 17:35 -0700, Florian Fainelli wrote:
On 05/08/2017 04:46 PM, Julia Lawall wrote:
On Mon, 8 May 2017, Joe Perches wrote:
Each time -EPROBE_DEFER occurs, another set of calls to
dsa_switch_alloc and dev_kzalloc also occurs.
Le 09/05/2017 à 17:18, Joe Perches a écrit :
On Mon, 2017-05-08 at 17:35 -0700, Florian Fainelli wrote:
On 05/08/2017 04:46 PM, Julia Lawall wrote:
On Mon, 8 May 2017, Joe Perches wrote:
Each time -EPROBE_DEFER occurs, another set of calls to
dsa_switch_alloc and dev_kzalloc also occurs.
On Tue, 2017-05-09 at 16:23 -0700, Kees Cook wrote:
> Using memcpy() from a string that is shorter than the length copied means
> the destination buffer is being filled with arbitrary data from the kernel
> rodata segment. Instead, use strncpy() which will fill the trailing bytes
> with zeros.
On Tue, 2017-05-09 at 16:23 -0700, Kees Cook wrote:
> Using memcpy() from a string that is shorter than the length copied means
> the destination buffer is being filled with arbitrary data from the kernel
> rodata segment. Instead, use strncpy() which will fill the trailing bytes
> with zeros.
On Wed, 10 May 2017, Christophe JAILLET wrote:
> Free some devm'allocated memory in case of deferred driver initialization.
> This avoid to waste some memory in such a case.
I really think it would be helpful to mention the special behavior of
-EPROBE_DEFER. It doesn't take much space, and it
On Wed, 10 May 2017, Christophe JAILLET wrote:
> Free some devm'allocated memory in case of deferred driver initialization.
> This avoid to waste some memory in such a case.
I really think it would be helpful to mention the special behavior of
-EPROBE_DEFER. It doesn't take much space, and it
Looks correct.
Acked-by: Shirish Pargaonkar
On Sun, May 7, 2017 at 3:31 AM, Joe Perches via samba-technical
wrote:
> Create an ops variable to store tcon->ses->server->ops and cache
> indirections and reduce code size a trivial bit.
Looks correct.
Acked-by: Shirish Pargaonkar
On Sun, May 7, 2017 at 3:31 AM, Joe Perches via samba-technical
wrote:
> Create an ops variable to store tcon->ses->server->ops and cache
> indirections and reduce code size a trivial bit.
>
> $ size fs/cifs/cifsacl.o*
>textdata bss
Hi all,
Please do not add any v4.13 destined material in your linux-next
included branches until after v4.12-rc1 has been released.
Changes since 20170509:
The tpmdd tree gaind a build failure for which I applied a fix patch.
Non-merge commits (relative to Linus' tree): 1220
1257 files
Hi all,
Please do not add any v4.13 destined material in your linux-next
included branches until after v4.12-rc1 has been released.
Changes since 20170509:
The tpmdd tree gaind a build failure for which I applied a fix patch.
Non-merge commits (relative to Linus' tree): 1220
1257 files
Some of the autofs miscellaneous device ioctls need to be accessable to
user space applications without CAP_SYS_ADMIN to get information about
autofs mounts.
Start by making the autofs miscellaneous device ioctl header available
and allow applications to use version and ismountpoint ioctls.
The fstatat(2) and statx() calls can pass the flag AT_NO_AUTOMOUNT
which is meant to clear the LOOKUP_AUTOMOUNT flag and prevent triggering
of an automount by the call. But this flag is unconditionally cleared
for all stat family system calls except statx().
stat family system calls have always
The autofs miscellanous device ioctls that shouldn't require
CAP_SYS_ADMIN need to be accessible to user space applications in
order to be able to get information about autofs mounts.
The module checks capabilities so the miscelaneous device should
be fine with broad permissions.
Signed-off-by:
Some of the autofs miscellaneous device ioctls need to be accessable to
user space applications without CAP_SYS_ADMIN to get information about
autofs mounts.
Start by making the autofs miscellaneous device ioctl header available
and allow applications to use version and ismountpoint ioctls.
The fstatat(2) and statx() calls can pass the flag AT_NO_AUTOMOUNT
which is meant to clear the LOOKUP_AUTOMOUNT flag and prevent triggering
of an automount by the call. But this flag is unconditionally cleared
for all stat family system calls except statx().
stat family system calls have always
The autofs miscellanous device ioctls that shouldn't require
CAP_SYS_ADMIN need to be accessible to user space applications in
order to be able to get information about autofs mounts.
The module checks capabilities so the miscelaneous device should
be fine with broad permissions.
Signed-off-by:
Free some devm'allocated memory in case of deferred driver initialization.
This avoid to waste some memory in such a case.
Suggested-by: Joe Perches
Signed-off-by: Christophe JAILLET
---
drivers/net/dsa/dsa_loop.c | 5 -
1 file changed, 4
Free some devm'allocated memory in case of deferred driver initialization.
This avoid to waste some memory in such a case.
Suggested-by: Joe Perches
Signed-off-by: Christophe JAILLET
---
drivers/net/dsa/dsa_loop.c | 5 -
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git
On 2017-05-09 00:50, Dong Aisheng wrote:
> The lpuart of imx7ulp is basically the same as ls1021a. It's also
> 32 bit width register, but unlike ls1021a, it's little endian.
> Besides that, imx7ulp lpuart has a minor different register layout
> from ls1021a that it has four extra registers (verid,
On 2017-05-09 00:50, Dong Aisheng wrote:
> The lpuart of imx7ulp is basically the same as ls1021a. It's also
> 32 bit width register, but unlike ls1021a, it's little endian.
> Besides that, imx7ulp lpuart has a minor different register layout
> from ls1021a that it has four extra registers (verid,
When booted as pv-guest the p2m list presented by the Xen is already
mapped to virtual addresses. In dom0 case the hypervisor might make use
of 2M- or 1G-pages for this mapping. Unfortunately while being properly
aligned in virtual and machine address space, those pages might not be
aligned
When booted as pv-guest the p2m list presented by the Xen is already
mapped to virtual addresses. In dom0 case the hypervisor might make use
of 2M- or 1G-pages for this mapping. Unfortunately while being properly
aligned in virtual and machine address space, those pages might not be
aligned
On 2017-05-09 00:50, Dong Aisheng wrote:
> It's based on the exist lpuart32 read/write implementation.
>
> Cc: Greg Kroah-Hartman
> Cc: Jiri Slaby (supporter:TTY LAYER)
> Cc: Fugang Duan
> Cc: Stefan Agner
>
On 2017-05-09 00:50, Dong Aisheng wrote:
> It's based on the exist lpuart32 read/write implementation.
>
> Cc: Greg Kroah-Hartman
> Cc: Jiri Slaby (supporter:TTY LAYER)
> Cc: Fugang Duan
> Cc: Stefan Agner
> Cc: Mingkai Hu
> Cc: Yangbo Lu
> Signed-off-by: Dong Aisheng
> ---
>
If one 'drm_gem_handle_create()' fails, we leak somes handles and some
memory.
In order to fix it:
- move the 'free(bo_state)' at the end of the function in the error
handling path. This has the side effect to also try to free it if the
first 'kcalloc' fails. This is harmless.
-
If one 'drm_gem_handle_create()' fails, we leak somes handles and some
memory.
In order to fix it:
- move the 'free(bo_state)' at the end of the function in the error
handling path. This has the side effect to also try to free it if the
first 'kcalloc' fails. This is harmless.
-
On Tue, May 02, 2017 at 03:16:18PM +, Eugeniy Paltsev wrote:
> Hi Vinod,
>
> On Mon, 2017-05-01 at 11:21 +0530, Vinod Koul wrote:
> > On Fri, Apr 28, 2017 at 04:37:46PM +0300, Eugeniy Paltsev wrote:
> > > In the current implementation dma_get_slave_caps is used to check
> > > state of
On Tue, May 02, 2017 at 03:16:18PM +, Eugeniy Paltsev wrote:
> Hi Vinod,
>
> On Mon, 2017-05-01 at 11:21 +0530, Vinod Koul wrote:
> > On Fri, Apr 28, 2017 at 04:37:46PM +0300, Eugeniy Paltsev wrote:
> > > In the current implementation dma_get_slave_caps is used to check
> > > state of
On 2017-05-09 00:50, Dong Aisheng wrote:
> This is used to dynamically check the SoC specific lpuart properies.
> Currently only the checking of 32 bit register width is added which
> functions the same as before. More will be added later for supporting
> new chips.
>
> Cc: Greg Kroah-Hartman
On 2017-05-09 00:50, Dong Aisheng wrote:
> This is used to dynamically check the SoC specific lpuart properies.
> Currently only the checking of 32 bit register width is added which
> functions the same as before. More will be added later for supporting
> new chips.
>
> Cc: Greg Kroah-Hartman
>
On Wed, May 10, 2017 at 04:21:37AM +0100, Al Viro wrote:
> On Wed, May 10, 2017 at 04:12:54AM +0100, Al Viro wrote:
>
> > Broken commit: "net: don't play with address limits in kernel_recvmsg".
> > It would be OK if it was only about data. Unfortunately, that's not
> > true in one case:
On Wed, May 10, 2017 at 04:21:37AM +0100, Al Viro wrote:
> On Wed, May 10, 2017 at 04:12:54AM +0100, Al Viro wrote:
>
> > Broken commit: "net: don't play with address limits in kernel_recvmsg".
> > It would be OK if it was only about data. Unfortunately, that's not
> > true in one case:
ah seems like there's more of these:
drivers/gpu/drm/drm_mm.c:922
surprised compiling drivers/gpu/drm/drm_mm.o did not catch this the
first time...
ah seems like there's more of these:
drivers/gpu/drm/drm_mm.c:922
surprised compiling drivers/gpu/drm/drm_mm.o did not catch this the
first time...
Signed-off-by: Jason Wang
---
include/linux/skb_array.h | 25 +
1 file changed, 25 insertions(+)
diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h
index 79850b6..35226cd 100644
--- a/include/linux/skb_array.h
+++
Signed-off-by: Jason Wang
---
include/linux/skb_array.h | 25 +
1 file changed, 25 insertions(+)
diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h
index 79850b6..35226cd 100644
--- a/include/linux/skb_array.h
+++ b/include/linux/skb_array.h
@@ -97,21
This patch exports skb_array through tun_get_skb_array(). Caller can
then manipulate skb array directly.
Signed-off-by: Jason Wang
---
drivers/net/tun.c | 13 +
include/linux/if_tun.h | 5 +
2 files changed, 18 insertions(+)
diff --git
This patch exports skb_array through tun_get_skb_array(). Caller can
then manipulate skb array directly.
Signed-off-by: Jason Wang
---
drivers/net/tun.c | 13 +
include/linux/if_tun.h | 5 +
2 files changed, 18 insertions(+)
diff --git a/drivers/net/tun.c
We used to dequeue one skb during recvmsg() from skb_array, this could
be inefficient because of the bad cache utilization and spinlock
touching for each packet. This patch tries to batch them by calling
batch dequeuing helpers explicitly on the exported skb array and pass
the skb back through
We used to dequeue one skb during recvmsg() from skb_array, this could
be inefficient because of the bad cache utilization and spinlock
touching for each packet. This patch tries to batch them by calling
batch dequeuing helpers explicitly on the exported skb array and pass
the skb back through
This patch exports skb_array through tap_get_skb_array(). Caller can
then manipulate skb array directly.
Signed-off-by: Jason Wang
---
drivers/net/tap.c | 13 +
include/linux/if_tap.h | 5 +
2 files changed, 18 insertions(+)
diff --git
This patch makes tun_recvmsg() can receive from skb from its caller
through msg_control. Vhost_net will be the first user.
Signed-off-by: Jason Wang
---
drivers/net/tun.c | 18 ++
1 file changed, 10 insertions(+), 8 deletions(-)
diff --git
This patch makes tap_recvmsg() can receive from skb from its caller
through msg_control. Vhost_net will be the first user.
Signed-off-by: Jason Wang
---
drivers/net/tap.c | 12
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/drivers/net/tap.c
This patch exports skb_array through tap_get_skb_array(). Caller can
then manipulate skb array directly.
Signed-off-by: Jason Wang
---
drivers/net/tap.c | 13 +
include/linux/if_tap.h | 5 +
2 files changed, 18 insertions(+)
diff --git a/drivers/net/tap.c
This patch makes tun_recvmsg() can receive from skb from its caller
through msg_control. Vhost_net will be the first user.
Signed-off-by: Jason Wang
---
drivers/net/tun.c | 18 ++
1 file changed, 10 insertions(+), 8 deletions(-)
diff --git a/drivers/net/tun.c
This patch makes tap_recvmsg() can receive from skb from its caller
through msg_control. Vhost_net will be the first user.
Signed-off-by: Jason Wang
---
drivers/net/tap.c | 12
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index
From: "Michael S. Tsirkin"
A known weakness in ptr_ring design is that it does not handle well the
situation when ring is almost full: as entries are consumed they are
immediately used again by the producer, so consumer and producer are
writing to a shared cache line.
To fix
From: "Michael S. Tsirkin"
A known weakness in ptr_ring design is that it does not handle well the
situation when ring is almost full: as entries are consumed they are
immediately used again by the producer, so consumer and producer are
writing to a shared cache line.
To fix this, add batching
From: "Michael S. Tsirkin"
Applications that consume a batch of entries in one go
can benefit from ability to return some of them back
into the ring.
Add an API for that - assuming there's space. If there's no space
naturally can't do this and have to drop entries, but this
Signed-off-by: Jason Wang
---
include/linux/skb_array.h | 6 ++
1 file changed, 6 insertions(+)
diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h
index f4dfade..79850b6 100644
--- a/include/linux/skb_array.h
+++ b/include/linux/skb_array.h
@@ -156,6
This series tries to implement rx batching for vhost-net. This is done
by batching the dequeuing from skb_array which was exported by
underlayer socket and pass the sbk back through msg_control to finish
userspace copying. This is also the requirement for more batching
implemention on rx path.
This patch introduce a batched version of consuming, consumer can
dequeue more than one pointers from the ring at a time. We don't care
about the reorder of reading here so no need for compiler barrier.
Signed-off-by: Jason Wang
---
include/linux/ptr_ring.h | 65
Signed-off-by: Jason Wang
---
include/linux/skb_array.h | 6 ++
1 file changed, 6 insertions(+)
diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h
index f4dfade..79850b6 100644
--- a/include/linux/skb_array.h
+++ b/include/linux/skb_array.h
@@ -156,6 +156,12 @@ static void
This series tries to implement rx batching for vhost-net. This is done
by batching the dequeuing from skb_array which was exported by
underlayer socket and pass the sbk back through msg_control to finish
userspace copying. This is also the requirement for more batching
implemention on rx path.
This patch introduce a batched version of consuming, consumer can
dequeue more than one pointers from the ring at a time. We don't care
about the reorder of reading here so no need for compiler barrier.
Signed-off-by: Jason Wang
---
include/linux/ptr_ring.h | 65
From: "Michael S. Tsirkin"
Applications that consume a batch of entries in one go
can benefit from ability to return some of them back
into the ring.
Add an API for that - assuming there's space. If there's no space
naturally can't do this and have to drop entries, but this implies ring
is full
For some greater resolution, the rdma threshold
variable will overflow.
Signed-off-by: Bibby Hsieh
---
drivers/gpu/drm/mediatek/mtk_disp_rdma.c | 7 ---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_rdma.c
For some greater resolution, the rdma threshold
variable will overflow.
Signed-off-by: Bibby Hsieh
---
drivers/gpu/drm/mediatek/mtk_disp_rdma.c | 7 ---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_rdma.c
On 2017年05月09日 21:33, Michael S. Tsirkin wrote:
I love this idea. Reviewed and discussed the idea in-person with MST
during netdevconf[1] at this laptop. I promised I will also run it
through my micro-benchmarking[2] once I return home (hint ptr_ring gets
used in network stack as skb_array).
On 2017年05月09日 21:33, Michael S. Tsirkin wrote:
I love this idea. Reviewed and discussed the idea in-person with MST
during netdevconf[1] at this laptop. I promised I will also run it
through my micro-benchmarking[2] once I return home (hint ptr_ring gets
used in network stack as skb_array).
Hi Markus,
On Wed, 10 May 2017 04:20:54 +0200 Markus Trippelsdorf
wrote:
>
> Yes, it was missing a (void) like "(void)strlcpy(...)". But Jens
> unfortunately removed both warnings, so the following patch should now
> be enough:
>
> diff --git a/block/elevator.c
Hi Markus,
On Wed, 10 May 2017 04:20:54 +0200 Markus Trippelsdorf
wrote:
>
> Yes, it was missing a (void) like "(void)strlcpy(...)". But Jens
> unfortunately removed both warnings, so the following patch should now
> be enough:
>
> diff --git a/block/elevator.c b/block/elevator.c
> index
1 - 100 of 1450 matches
Mail list logo