Re: [PATCH] KVM: arm/arm64: don't set vtimer->cnt_ctl in kvm_arch_timer_handler

Hi Christoffer On 12/14/2017 9:09 PM, Christoffer Dall Wrote: On Thu, Dec 14, 2017 at 12:57:54PM +0800, Jia He wrote: Hi Jia, I have tried your newer level-mapped-v7 branch, but bug is still there. There is no special load in both host and guest. The guest (kernel 4.14) is often hanging

Re: [PATCH] KVM: arm/arm64: don't set vtimer->cnt_ctl in kvm_arch_timer_handler

Hi Christoffer On 12/14/2017 9:09 PM, Christoffer Dall Wrote: On Thu, Dec 14, 2017 at 12:57:54PM +0800, Jia He wrote: Hi Jia, I have tried your newer level-mapped-v7 branch, but bug is still there. There is no special load in both host and guest. The guest (kernel 4.14) is often hanging

Re: [PATCH] KVM: arm/arm64: don't set vtimer->cnt_ctl in kvm_arch_timer_handler

Hi On 12/14/2017 12:57 PM, Jia He Wrote: Hi Christoffer I have tried your newer level-mapped-v7 branch, but bug is still there. There is no special load in both host and guest. The guest (kernel 4.14) is often hanging when booting the guest kernel log [ OK ] Reached target Remote File

Re: [PATCH] KVM: arm/arm64: don't set vtimer->cnt_ctl in kvm_arch_timer_handler

Hi On 12/14/2017 12:57 PM, Jia He Wrote: Hi Christoffer I have tried your newer level-mapped-v7 branch, but bug is still there. There is no special load in both host and guest. The guest (kernel 4.14) is often hanging when booting the guest kernel log [ OK ] Reached target Remote File

Re: [PATCH] KVM: arm/arm64: don't set vtimer->cnt_ctl in kvm_arch_timer_handler

stoffer Dall Wrote: On Tue, Dec 12, 2017 at 11:00:07PM -0800, Jia He wrote: In our Armv8a server (qualcomm Amberwing, non VHE), after applying Christoffer's timer optimizing patchset(Optimize arch timer register handling), the guest is hang during kernel booting. The erro

Re: [PATCH] KVM: arm/arm64: don't set vtimer->cnt_ctl in kvm_arch_timer_handler

stoffer Dall Wrote: On Tue, Dec 12, 2017 at 11:00:07PM -0800, Jia He wrote: In our Armv8a server (qualcomm Amberwing, non VHE), after applying Christoffer's timer optimizing patchset(Optimize arch timer register handling), the guest is hang during kernel booting. The erro

[PATCH] KVM: arm/arm64: don't set vtimer->cnt_ctl in kvm_arch_timer_handler

mer kvm_timer_is_pending kvm_timer_should_fire 3. Thus, the kvm hyp code can not break the loop in kvm_vcpu_block (halt poll process) and the guest is hang forever Fixes: b103cc3f10c0 ("KVM: arm/arm64: Avoid timer save/restore in vcpu entry/exit") Signed-off-by: Jia H

[PATCH] KVM: arm/arm64: don't set vtimer->cnt_ctl in kvm_arch_timer_handler

mer kvm_timer_is_pending kvm_timer_should_fire 3. Thus, the kvm hyp code can not break the loop in kvm_vcpu_block (halt poll process) and the guest is hang forever Fixes: b103cc3f10c0 ("KVM: arm/arm64: Avoid timer save/restore in vcpu entry/exit") Signed-off-by: Jia He

Re: [PATCH] drivers/perf: arm_pmu: save/restore cpu cycle counter in cpu_pm_pmu_notify

Thanks, got it Cheers, Jia On 11/20/2017 10:04 PM, Mark Rutland Wrote: On Mon, Nov 20, 2017 at 09:50:15PM +0800, Jia He wrote: On 11/20/2017 8:32 PM, Mark Rutland Wrote: On Thu, Nov 16, 2017 at 06:27:28AM +, Jia He wrote: Sometimes userspace need a high resolution cycle counter

Re: [PATCH] drivers/perf: arm_pmu: save/restore cpu cycle counter in cpu_pm_pmu_notify

Thanks, got it Cheers, Jia On 11/20/2017 10:04 PM, Mark Rutland Wrote: On Mon, Nov 20, 2017 at 09:50:15PM +0800, Jia He wrote: On 11/20/2017 8:32 PM, Mark Rutland Wrote: On Thu, Nov 16, 2017 at 06:27:28AM +, Jia He wrote: Sometimes userspace need a high resolution cycle counter

Re: [PATCH] drivers/perf: arm_pmu: save/restore cpu cycle counter in cpu_pm_pmu_notify

Hi Mark Thanks for your review. On 11/20/2017 8:32 PM, Mark Rutland Wrote: Hi, On Thu, Nov 16, 2017 at 06:27:28AM +, Jia He wrote: Sometimes userspace need a high resolution cycle counter by reading pmccntr_el0. In commit da4e4f18afe0 ("drivers/perf: arm_pmu: implement CPU_PM not

Re: [PATCH] drivers/perf: arm_pmu: save/restore cpu cycle counter in cpu_pm_pmu_notify

Hi Mark Thanks for your review. On 11/20/2017 8:32 PM, Mark Rutland Wrote: Hi, On Thu, Nov 16, 2017 at 06:27:28AM +, Jia He wrote: Sometimes userspace need a high resolution cycle counter by reading pmccntr_el0. In commit da4e4f18afe0 ("drivers/perf: arm_pmu: implement CPU_PM not

[PATCH] drivers/perf: arm_pmu: save/restore cpu cycle counter in cpu_pm_pmu_notify

registers and counter before CPU_PM_ENTER and restore them after CPU_PM_EXIT. Fixes: da4e4f18afe0 ("drivers/perf: arm_pmu: implement CPU_PM notifier") Signed-off-by: Jia He <jia...@hxt-semitech.com> --- drivers/perf/arm_pmu.c | 72

[PATCH] drivers/perf: arm_pmu: save/restore cpu cycle counter in cpu_pm_pmu_notify

registers and counter before CPU_PM_ENTER and restore them after CPU_PM_EXIT. Fixes: da4e4f18afe0 ("drivers/perf: arm_pmu: implement CPU_PM notifier") Signed-off-by: Jia He --- drivers/perf/arm_pmu.c | 72 +- 1 file changed, 66 insert

Re: Possible gcc 4.8.5 bug about RELOC_HIDE marcro

Thanks Mikael It is a known gcc bug, please see https://gcc.gnu.org/ml/gcc-patches/2017-03/msg00790.html Cheers, Jusitn(Jia He) 在 9/21/2017 3:53 PM, Mikael Pettersson Wrote: Jia He writes: > I tried to build kernel 4.14-rc1 on a arm64 server in distro centos 7.3. > The gcc v

Re: Possible gcc 4.8.5 bug about RELOC_HIDE marcro

Thanks Mikael It is a known gcc bug, please see https://gcc.gnu.org/ml/gcc-patches/2017-03/msg00790.html Cheers, Jusitn(Jia He) 在 9/21/2017 3:53 PM, Mikael Pettersson Wrote: Jia He writes: > I tried to build kernel 4.14-rc1 on a arm64 server in distro centos 7.3. > The gcc v

Possible gcc 4.8.5 bug about RELOC_HIDE marcro

h cause the compiler bug: commit    c350c008297643dad3c395c2fd92230142da5cf6 srcu: Prevent sdp->srcu_gp_seq_needed counter wrap In this bug, srcu uses a percpu ptr which will call RELOC_HIDE. After I remove the RELOC_HIDE code, this bug disappearred. This bug is not in latest gcc version Cheers, Justin(Jia He)

Possible gcc 4.8.5 bug about RELOC_HIDE marcro

dad3c395c2fd92230142da5cf6 srcu: Prevent sdp->srcu_gp_seq_needed counter wrap In this bug, srcu uses a percpu ptr which will call RELOC_HIDE. After I remove the RELOC_HIDE code, this bug disappearred. This bug is not in latest gcc version Cheers, Justin(Jia He)

[PATCH] powerpc/time: use get_tb instead of get_vtb in running_clock

s to also include the time elapsed in host. get_vtb is not correct in this case. Also, the TB_OFFSET is well saved and restored by qemu after commit [1]. So we can use get_tb here. [1] http://git.qemu.org/?p=qemu.git;a=commit;h=42043e4f1 Signed-off-by: Jia He <hejia...@gmail.com> --- arch

[PATCH] powerpc/time: use get_tb instead of get_vtb in running_clock

s to also include the time elapsed in host. get_vtb is not correct in this case. Also, the TB_OFFSET is well saved and restored by qemu after commit [1]. So we can use get_tb here. [1] http://git.qemu.org/?p=qemu.git;a=commit;h=42043e4f1 Signed-off-by: Jia He --- arch/powerpc/kernel/time.c | 7 +

[PATCH v2] mm/vmscan: fix high cpu usage of kswapd if there are no reclaimable pages

ion better Signed-off-by: Jia He <hejia...@gmail.com> --- mm/vmscan.c | 11 ++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index 532a2a7..7c5a563 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3139,7 +3139,8 @@ static bool prepare_ksw

[PATCH v2] mm/vmscan: fix high cpu usage of kswapd if there are no reclaimable pages

ion better Signed-off-by: Jia He --- mm/vmscan.c | 11 ++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index 532a2a7..7c5a563 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3139,7 +3139,8 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int or

[RFC PATCH] mm/vmscan: fix high cpu usage of kswapd if there

4 used, 6206720 free. 131328 cached Mem PID USER PR NIVIRTRESSHR S %CPU %MEM TIME+ COMMAND 77 root 20 0 0 0 0 S 0.000 0.000 0:00.00 kswapd3 Signed-off-by: Jia He <hejia...@gmail.com> --- mm/vmscan.c | 11 ++- 1 file changed, 1

[RFC PATCH] mm/vmscan: fix high cpu usage of kswapd if there

4 used, 6206720 free. 131328 cached Mem PID USER PR NIVIRTRESSHR S %CPU %MEM TIME+ COMMAND 77 root 20 0 0 0 0 S 0.000 0.000 0:00.00 kswapd3 Signed-off-by: Jia He --- mm/vmscan.c | 11 ++- 1 file changed, 10 insertions(+), 1 de

[PATCH RFC 1/3] mm/hugetlb: split alloc_fresh_huge_page_node into fast and slow path

40 40 40 10 In this case node 5 has less memory and we will alloc the hugepages from these nodes one by one. After this patch, we will not trigger too early direct memory/kswap reclaim for node 5 if there are enough memory in other nodes. Signed-off-by: Jia He <hejia...@gmail.com> -

[PATCH RFC 1/3] mm/hugetlb: split alloc_fresh_huge_page_node into fast and slow path

40 40 40 10 In this case node 5 has less memory and we will alloc the hugepages from these nodes one by one. After this patch, we will not trigger too early direct memory/kswap reclaim for node 5 if there are enough memory in other nodes. Signed-off-by: Jia He --- mm/hugetlb.c | 9

[PATCH RFC 2/3] mm, vmscan: limit kswapd loop if no progress is made

e 4 size: 24815 MB node 4 free: 20704 MB node 5 cpus: node 5 size: 4095 MB node 5 free: 61 MB node 6 cpus: node 6 size: 22750 MB node 6 free: 18716 MB The cause is kswapd will loop for long time even if there is no progress in balance_pgdat. Signed-off-by: Jia He <hejia...@gmail.com> --- mm

[PATCH RFC 2/3] mm, vmscan: limit kswapd loop if no progress is made

e 4 size: 24815 MB node 4 free: 20704 MB node 5 cpus: node 5 size: 4095 MB node 5 free: 61 MB node 6 cpus: node 6 size: 22750 MB node 6 free: 18716 MB The cause is kswapd will loop for long time even if there is no progress in balance_pgdat. Signed-off-by: Jia He --- mm/vmscan.c |

[PATCH RFC 3/3] mm, vmscan: correct prepare_kswapd_sleep return value

When there is no reclaimable pages in the zone, even the zone is not balanced, we let kswapd go sleeping. That is prepare_kswapd_sleep will return true in this case. Signed-off-by: Jia He <hejia...@gmail.com> --- mm/vmscan.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff

[PATCH RFC 0/3] optimize kswapd when it does reclaim for hugepage

4000 > /proc/sys/vm/nr_hugepages Then the kswapd5 will take 100% cpu for a long time. This is a livelock issue in kswapd. This patch set fixes it. The 3rd patch improves the kswapd's bad performance significantly. Jia He (3): mm/hugetlb: split alloc_fresh_huge_page_node into fast and slow p

[PATCH RFC 0/3] optimize kswapd when it does reclaim for hugepage

4000 > /proc/sys/vm/nr_hugepages Then the kswapd5 will take 100% cpu for a long time. This is a livelock issue in kswapd. This patch set fixes it. The 3rd patch improves the kswapd's bad performance significantly. Jia He (3): mm/hugetlb: split alloc_fresh_huge_page_node into fast and slow p

[PATCH RFC 3/3] mm, vmscan: correct prepare_kswapd_sleep return value

When there is no reclaimable pages in the zone, even the zone is not balanced, we let kswapd go sleeping. That is prepare_kswapd_sleep will return true in this case. Signed-off-by: Jia He --- mm/vmscan.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/vmscan.c b/mm

[PATCH v5 0/2] change the proc handler for nsm_use_hostnames

use_hostnames=1 [root@bigendian my]# cat /proc/sys/mysysctl/nsm_use_hostnames 1 In little endian system, there is no such issue. Already tested in both of big and little endian(ppc64 and ppc64le) Jia He (2): sysctl: introduce new proc handler proc_dobool lockd: change the proc_handle

[PATCH v5 2/2] lockd: change the proc_handler for nsm_use_hostnames

. This patch use a new proc_handler proc_dobool to fixe it. Signed-off-by: Jia He <hejia...@gmail.com> --- fs/lockd/svc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index fc4084e..bd6fcf9 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd

[PATCH v5 1/2] sysctl: introduce new proc handler proc_dobool

This is to let bool variable could be correctly displayed in big/little endian sysctl procfs. sizeof(bool) is arch dependent, proc_dobool should work in all arches. Suggested-by: Pan Xinhui <xin...@linux.vnet.ibm.com> Signed-off-by: Jia He <hejia...@gmail.com> --- include/linux/s

[PATCH v5 0/2] change the proc handler for nsm_use_hostnames

use_hostnames=1 [root@bigendian my]# cat /proc/sys/mysysctl/nsm_use_hostnames 1 In little endian system, there is no such issue. Already tested in both of big and little endian(ppc64 and ppc64le) Jia He (2): sysctl: introduce new proc handler proc_dobool lockd: change the proc_handle

[PATCH v5 2/2] lockd: change the proc_handler for nsm_use_hostnames

. This patch use a new proc_handler proc_dobool to fixe it. Signed-off-by: Jia He --- fs/lockd/svc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index fc4084e..bd6fcf9 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -561,7 +561,7

[PATCH v5 1/2] sysctl: introduce new proc handler proc_dobool

This is to let bool variable could be correctly displayed in big/little endian sysctl procfs. sizeof(bool) is arch dependent, proc_dobool should work in all arches. Suggested-by: Pan Xinhui Signed-off-by: Jia He --- include/linux/sysctl.h | 2 ++ kernel/sysctl.c| 41

[RESEND PATCH v4 0/2] change the proc handler for nsm_use_hostnames

-f /root/my/hello.ko nsm_use_hostnames=1 [root@bigendian my]# cat /proc/sys/mysysctl/nsm_use_hostnames 1 In little endian system, there is no such issue. Already tested v4 in both of big and little endian(ppc64 and ppc64le) Jia He (2): sysctl: introduce new proc handler proc_dobool lockd: chang

[RESEND PATCH v4 0/2] change the proc handler for nsm_use_hostnames

-f /root/my/hello.ko nsm_use_hostnames=1 [root@bigendian my]# cat /proc/sys/mysysctl/nsm_use_hostnames 1 In little endian system, there is no such issue. Already tested v4 in both of big and little endian(ppc64 and ppc64le) Jia He (2): sysctl: introduce new proc handler proc_dobool lockd: chang

[RESEND PATCH v4 1/2] sysctl: introduce new proc handler proc_dobool

This is to let bool variable could be correctly displayed in big/little endian sysctl procfs. sizeof(bool) is arch dependent, proc_dobool should work in all arches. Suggested-by: Pan Xinhui <xin...@linux.vnet.ibm.com> Signed-off-by: Jia He <hejia...@gmail.com> --- include/linux/s

[RESEND PATCH v4 2/2] lockd: change the proc_handler for nsm_use_hostnames

. This patch use a new proc_handler proc_dobool. Signed-off-by: Jia He <hejia...@gmail.com> --- fs/lockd/svc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index fc4084e..bd6fcf9 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@

[RESEND PATCH v4 1/2] sysctl: introduce new proc handler proc_dobool

This is to let bool variable could be correctly displayed in big/little endian sysctl procfs. sizeof(bool) is arch dependent, proc_dobool should work in all arches. Suggested-by: Pan Xinhui Signed-off-by: Jia He --- include/linux/sysctl.h | 2 ++ kernel/sysctl.c| 35

[RESEND PATCH v4 2/2] lockd: change the proc_handler for nsm_use_hostnames

. This patch use a new proc_handler proc_dobool. Signed-off-by: Jia He --- fs/lockd/svc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index fc4084e..bd6fcf9 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -561,7 +561,7 @@ static struct

[PATCH RFC 1/1] mm, page_alloc: fix incorrect zone_statistics data

be incorrect. Fixes: commit b9f00e147f27 ("mm, page_alloc: reduce branches in zone_statistics") Signed-off-by: Jia He <hejia...@gmail.com> --- mm/page_alloc.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6de9440..474757e 1

[PATCH RFC 1/1] mm, page_alloc: fix incorrect zone_statistics data

be incorrect. Fixes: commit b9f00e147f27 ("mm, page_alloc: reduce branches in zone_statistics") Signed-off-by: Jia He --- mm/page_alloc.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6de9440..474757e 100644 --- a/mm/page_alloc.c ++

[PATCH RFC 0/1] mm, page_alloc: fix incorrect zone_statistics data

718 711 726 858 712 719 Jia He (1): mm, page_alloc: fix incorrect zone_statistics data mm/page_alloc.c | 3 +++ 1 file changed, 3 insertions(+) -- 2.5.5

[PATCH RFC 0/1] mm, page_alloc: fix incorrect zone_statistics data

718 711 726 858 712 719 Jia He (1): mm, page_alloc: fix incorrect zone_statistics data mm/page_alloc.c | 3 +++ 1 file changed, 3 insertions(+) -- 2.5.5

[PATCH v2 0/1] lockd: Change nsm_use_hostnames from bool to u32

gendian my]# insmod -f /root/my/hello.ko nsm_use_hostnames=1 [root@bigendian my]# cat /proc/sys/mysysctl/nsm_use_hostnames 1 In little endian system, there is no such issue. Jia He (1): lockd: Change nsm_use_hostnames from bool to u32 fs/lockd/mon.c | 2 +- fs/lockd/svc.c | 2 +

[PATCH v2 0/1] lockd: Change nsm_use_hostnames from bool to u32

gendian my]# insmod -f /root/my/hello.ko nsm_use_hostnames=1 [root@bigendian my]# cat /proc/sys/mysysctl/nsm_use_hostnames 1 In little endian system, there is no such issue. Jia He (1): lockd: Change nsm_use_hostnames from bool to u32 fs/lockd/mon.c | 2 +- fs/lockd/svc.c | 2 +

[PATCH v2 1/1] lockd: Change nsm_use_hostnames from bool to u32

. This patch changes the type definition of nsm_use_hostnames. V2: Changes extern type in lockd.h Signed-off-by: Jia He <hejia...@gmail.com> --- fs/lockd/mon.c | 2 +- fs/lockd/svc.c | 2 +- include/linux/lockd/lockd.h | 2 +- 3 files changed, 3 insertions(+), 3 del

[PATCH v2 1/1] lockd: Change nsm_use_hostnames from bool to u32

. This patch changes the type definition of nsm_use_hostnames. V2: Changes extern type in lockd.h Signed-off-by: Jia He --- fs/lockd/mon.c | 2 +- fs/lockd/svc.c | 2 +- include/linux/lockd/lockd.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/fs

[PATCH 1/1] lockd: Change nsm_use_hostnames from bool to u32

. This patch changes the type definition of nsm_use_hostnames. Signed-off-by: Jia He <hejia...@gmail.com> --- fs/lockd/mon.c | 2 +- fs/lockd/svc.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 19166d4..3e7ff4d 100644 --- a/fs

[PATCH 1/1] lockd: Change nsm_use_hostnames from bool to u32

. This patch changes the type definition of nsm_use_hostnames. Signed-off-by: Jia He --- fs/lockd/mon.c | 2 +- fs/lockd/svc.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 19166d4..3e7ff4d 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd

[PATCH 0/1] lockd: Change nsm_use_hostnames from bool to u32

gendian my]# insmod -f /root/my/hello.ko nsm_use_hostnames=1 [root@bigendian my]# cat /proc/sys/mysysctl/nsm_use_hostnames 1 In little endian system, there is no such issue. Jia He (1): lockd: Change nsm_use_hostnames from bool to u32 fs/lockd/mon.c | 2 +- fs/lockd/svc.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) -- 2.5.5

[PATCH 0/1] lockd: Change nsm_use_hostnames from bool to u32

gendian my]# insmod -f /root/my/hello.ko nsm_use_hostnames=1 [root@bigendian my]# cat /proc/sys/mysysctl/nsm_use_hostnames 1 In little endian system, there is no such issue. Jia He (1): lockd: Change nsm_use_hostnames from bool to u32 fs/lockd/mon.c | 2 +- fs/lockd/svc.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) -- 2.5.5

[PATCH] powerpc: Fix LPCR_VRMASD definition

Fixes: a4b349540a ("powerpc/mm: Cleanup LPCR defines") Signed-off-by: Jia He <hejia...@gmail.com> --- arch/powerpc/include/asm/reg.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 9e1499f

[PATCH] powerpc: Fix LPCR_VRMASD definition

Fixes: a4b349540a ("powerpc/mm: Cleanup LPCR defines") Signed-off-by: Jia He --- arch/powerpc/include/asm/reg.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 9e1499f..93ec25e 100644 --- a/ar

[PATCH v6 7/7] net: Suppress the "Comparison to NULL could be written" warnings

This is to suppress the checkpatch.pl warning "Comparison to NULL could be written". No functional changes here. Signed-off-by: Jia He <hejia...@gmail.com> --- net/ipv4/proc.c | 32 net/sctp/proc.c | 2 +- 2 files changed, 17 insertions(+), 17 de

[PATCH v6 6/7] ipv6: Remove useless parameter in __snmp6_fill_statsdev

The parameter items(is always ICMP6_MIB_MAX) is useless for __snmp6_fill_statsdev Signed-off-by: Jia He <hejia...@gmail.com> --- net/ipv6/addrconf.c | 12 ++-- 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 2f1f5d4..3

[PATCH v6 4/7] proc: Reduce cache miss in sctp_snmp_seq_show

This is to use the generic interfaces snmp_get_cpu_field{,64}_batch to aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: Jia He <hejia...@gmail.com> --- net/sctp/proc.c | 8 ++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/ne

[PATCH v6 7/7] net: Suppress the "Comparison to NULL could be written" warnings

This is to suppress the checkpatch.pl warning "Comparison to NULL could be written". No functional changes here. Signed-off-by: Jia He --- net/ipv4/proc.c | 32 net/sctp/proc.c | 2 +- 2 files changed, 17 insertions(+), 17 deletions(-) diff --git

[PATCH v6 6/7] ipv6: Remove useless parameter in __snmp6_fill_statsdev

The parameter items(is always ICMP6_MIB_MAX) is useless for __snmp6_fill_statsdev Signed-off-by: Jia He --- net/ipv6/addrconf.c | 12 ++-- 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 2f1f5d4..35d4baa 100644 --- a/net

[PATCH v6 4/7] proc: Reduce cache miss in sctp_snmp_seq_show

This is to use the generic interfaces snmp_get_cpu_field{,64}_batch to aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: Jia He --- net/sctp/proc.c | 8 ++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/net/sctp/proc.c b/net/sctp

[PATCH v6 5/7] proc: Reduce cache miss in xfrm_statistics_seq_show

This is to use the generic interfaces snmp_get_cpu_field{,64}_batch to aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: Jia He <hejia...@gmail.com> --- net/xfrm/xfrm_proc.c | 10 -- 1 file changed, 8 insertions(+), 2 deletions(-) diff

[PATCH v6 5/7] proc: Reduce cache miss in xfrm_statistics_seq_show

This is to use the generic interfaces snmp_get_cpu_field{,64}_batch to aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: Jia He --- net/xfrm/xfrm_proc.c | 10 -- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/net/xfrm/xfrm_proc.c b

[PATCH v6 1/7] net:snmp: Introduce generic interfaces for snmp_get_cpu_field{,64}

This is to introduce the generic interfaces for snmp_get_cpu_field{,64}. It exchanges the two for-loops for collecting the percpu statistics data. This can aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: Jia He <hejia...@gmail.com> Suggested-by: M

[PATCH v6 1/7] net:snmp: Introduce generic interfaces for snmp_get_cpu_field{,64}

This is to introduce the generic interfaces for snmp_get_cpu_field{,64}. It exchanges the two for-loops for collecting the percpu statistics data. This can aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: Jia He Suggested-by: Marcelo Ricardo Leitner

[PATCH v6 2/7] proc: Reduce cache miss in snmp_seq_show

This is to use the generic interfaces snmp_get_cpu_field{,64}_batch to aggregate the data by going through all the items of each cpu sequentially. Then snmp_seq_show is split into 2 parts to avoid build warning "the frame size" larger than 1024. Signed-off-by: Jia He <hejia...@gmail.

[PATCH v6 0/7] Reduce cache miss for snmp_fold_field

eq_show considerred the stack usage is too large v3: - introduce generic interface (suggested by Marcelo Ricardo Leitner) - use max_t instead of self defined macro (suggested by David Miller) v2: - fix bug in udplite statistics. - snmp_seq_show is split into 2 parts Jia He (7): net:snmp: Introduce

[PATCH v6 2/7] proc: Reduce cache miss in snmp_seq_show

This is to use the generic interfaces snmp_get_cpu_field{,64}_batch to aggregate the data by going through all the items of each cpu sequentially. Then snmp_seq_show is split into 2 parts to avoid build warning "the frame size" larger than 1024. Signed-off-by: Jia He --- net/ipv4/p

[PATCH v6 0/7] Reduce cache miss for snmp_fold_field

eq_show considerred the stack usage is too large v3: - introduce generic interface (suggested by Marcelo Ricardo Leitner) - use max_t instead of self defined macro (suggested by David Miller) v2: - fix bug in udplite statistics. - snmp_seq_show is split into 2 parts Jia He (7): net:snmp: Introduce

[PATCH v6 3/7] proc: Reduce cache miss in snmp6_seq_show

This is to use the generic interfaces snmp_get_cpu_field{,64}_batch to aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: Jia He <hejia...@gmail.com> --- net/ipv6/proc.c | 30 ++ 1 file changed, 22 insertions(+), 8 del

[PATCH v6 3/7] proc: Reduce cache miss in snmp6_seq_show

This is to use the generic interfaces snmp_get_cpu_field{,64}_batch to aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: Jia He --- net/ipv6/proc.c | 30 ++ 1 file changed, 22 insertions(+), 8 deletions(-) diff --git a/net

[PATCH v5 2/7] proc: Reduce cache miss in snmp_seq_show

This is to use the generic interfaces snmp_get_cpu_field{,64}_batch to aggregate the data by going through all the items of each cpu sequentially. Then snmp_seq_show is split into 2 parts to avoid build warning "the frame size" larger than 1024. Signed-off-by: Jia He <hejia...@gmail.

[PATCH v5 7/7] net: Suppress the "Comparison to NULL could be written" warnings

This is to suppress the checkpatch.pl warning "Comparison to NULL could be written". No functional changes here. Signed-off-by: Jia He <hejia...@gmail.com> --- net/ipv4/proc.c | 32 net/sctp/proc.c | 2 +- 2 files changed, 17 insertions(+), 17 de

[PATCH v5 2/7] proc: Reduce cache miss in snmp_seq_show

This is to use the generic interfaces snmp_get_cpu_field{,64}_batch to aggregate the data by going through all the items of each cpu sequentially. Then snmp_seq_show is split into 2 parts to avoid build warning "the frame size" larger than 1024. Signed-off-by: Jia He --- net/ipv4/p

[PATCH v5 7/7] net: Suppress the "Comparison to NULL could be written" warnings

This is to suppress the checkpatch.pl warning "Comparison to NULL could be written". No functional changes here. Signed-off-by: Jia He --- net/ipv4/proc.c | 32 net/sctp/proc.c | 2 +- 2 files changed, 17 insertions(+), 17 deletions(-) diff --git

[PATCH v5 4/7] proc: Reduce cache miss in sctp_snmp_seq_show

This is to use the generic interfaces snmp_get_cpu_field{,64}_batch to aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: Jia He <hejia...@gmail.com> --- net/sctp/proc.c | 10 +++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git

[PATCH v5 6/7] ipv6: Remove useless parameter in __snmp6_fill_statsdev

The parameter items(always ICMP6_MIB_MAX) is useless for __snmp6_fill_statsdev. Signed-off-by: Jia He <hejia...@gmail.com> --- net/ipv6/addrconf.c | 12 ++-- 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 2f1f5d4..3

[PATCH v5 5/7] proc: Reduce cache miss in xfrm_statistics_seq_show

This is to use the generic interfaces snmp_get_cpu_field{,64}_batch to aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: Jia He <hejia...@gmail.com> --- net/xfrm/xfrm_proc.c | 12 +--- 1 file changed, 9 insertions(+), 3 deletions(-) diff

[PATCH v5 4/7] proc: Reduce cache miss in sctp_snmp_seq_show

This is to use the generic interfaces snmp_get_cpu_field{,64}_batch to aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: Jia He --- net/sctp/proc.c | 10 +++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/net/sctp/proc.c b/net/sctp

[PATCH v5 6/7] ipv6: Remove useless parameter in __snmp6_fill_statsdev

The parameter items(always ICMP6_MIB_MAX) is useless for __snmp6_fill_statsdev. Signed-off-by: Jia He --- net/ipv6/addrconf.c | 12 ++-- 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 2f1f5d4..35d4baa 100644 --- a/net/ipv6

[PATCH v5 5/7] proc: Reduce cache miss in xfrm_statistics_seq_show

This is to use the generic interfaces snmp_get_cpu_field{,64}_batch to aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: Jia He --- net/xfrm/xfrm_proc.c | 12 +--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/net/xfrm/xfrm_proc.c

[PATCH v5 0/7] Reduce cache miss for snmp_fold_field

nsiderred the stack usage is too large v3: - introduce generic interface (suggested by Marcelo Ricardo Leitner) - use max_t instead of self defined macro (suggested by David Miller) v2: - fix bug in udplite statistics. - snmp_seq_show is split into 2 parts Jia He (7): net:snmp: Introduce generic interfaces

[PATCH v5 1/7] net:snmp: Introduce generic interfaces for snmp_get_cpu_field{,64}

This is to introduce the generic interfaces for snmp_get_cpu_field{,64}. It exchanges the two for-loops for collecting the percpu statistics data. This can aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: Jia He <hejia...@gmail.com> Suggested-by: M

[PATCH v5 0/7] Reduce cache miss for snmp_fold_field

nsiderred the stack usage is too large v3: - introduce generic interface (suggested by Marcelo Ricardo Leitner) - use max_t instead of self defined macro (suggested by David Miller) v2: - fix bug in udplite statistics. - snmp_seq_show is split into 2 parts Jia He (7): net:snmp: Introduce generic interfaces

[PATCH v5 1/7] net:snmp: Introduce generic interfaces for snmp_get_cpu_field{,64}

This is to introduce the generic interfaces for snmp_get_cpu_field{,64}. It exchanges the two for-loops for collecting the percpu statistics data. This can aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: Jia He Suggested-by: Marcelo Ricardo Leitner

[PATCH v5 3/7] proc: Reduce cache miss in snmp6_seq_show

This is to use the generic interfaces snmp_get_cpu_field{,64}_batch to aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: Jia He <hejia...@gmail.com> --- net/ipv6/proc.c | 32 +++- 1 file changed, 23 insertions(+), 9 del

[PATCH v5 3/7] proc: Reduce cache miss in snmp6_seq_show

This is to use the generic interfaces snmp_get_cpu_field{,64}_batch to aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: Jia He --- net/ipv6/proc.c | 32 +++- 1 file changed, 23 insertions(+), 9 deletions(-) diff --git a/net

[PATCH v4 5/7] proc: Reduce cache miss in xfrm_statistics_seq_show

This is to use the generic interface snmp_get_cpu_field{,64}_batch to aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: Jia He <hejia...@gmail.com> --- net/xfrm/xfrm_proc.c | 10 -- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git

[PATCH v4 5/7] proc: Reduce cache miss in xfrm_statistics_seq_show

This is to use the generic interface snmp_get_cpu_field{,64}_batch to aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: Jia He --- net/xfrm/xfrm_proc.c | 10 -- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/net/xfrm/xfrm_proc.c b

[PATCH v4 3/7] proc: Reduce cache miss in snmp6_seq_show

This is to use the generic interface snmp_get_cpu_field{,64}_batch to aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: Jia He <hejia...@gmail.com> --- net/ipv6/proc.c | 32 +++- 1 file changed, 23 insertions(+), 9 del

[PATCH v4 6/7] ipv6: Remove useless parameter in __snmp6_fill_statsdev

The parameter items(always ICMP6_MIB_MAX) is useless for __snmp6_fill_statsdev. Signed-off-by: Jia He <hejia...@gmail.com> --- net/ipv6/addrconf.c | 12 ++-- 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 2f1f5d4..3

[PATCH v4 3/7] proc: Reduce cache miss in snmp6_seq_show

This is to use the generic interface snmp_get_cpu_field{,64}_batch to aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: Jia He --- net/ipv6/proc.c | 32 +++- 1 file changed, 23 insertions(+), 9 deletions(-) diff --git a/net

[PATCH v4 6/7] ipv6: Remove useless parameter in __snmp6_fill_statsdev

The parameter items(always ICMP6_MIB_MAX) is useless for __snmp6_fill_statsdev. Signed-off-by: Jia He --- net/ipv6/addrconf.c | 12 ++-- 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 2f1f5d4..35d4baa 100644 --- a/net/ipv6

[PATCH v4 7/7] net: Suppress the "Comparison to NULL could be written" warnings

This is to suppress the checkpatch.pl warning "Comparison to NULL could be written". No functional changes here. Signed-off-by: Jia He <hejia...@gmail.com> --- net/ipv4/proc.c | 32 net/sctp/proc.c | 2 +- 2 files changed, 17 insertions(+), 17 de

[PATCH v4 1/7] net:snmp: Introduce generic interfaces for snmp_get_cpu_field{,64}

This is to introduce the generic interfaces for snmp_get_cpu_field{,64}. It exchanges the two for-loops for collecting the percpu statistics data. This can aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: Jia He <hejia...@gmail.com> Suggested-by: M

[PATCH v4 7/7] net: Suppress the "Comparison to NULL could be written" warnings

This is to suppress the checkpatch.pl warning "Comparison to NULL could be written". No functional changes here. Signed-off-by: Jia He --- net/ipv4/proc.c | 32 net/sctp/proc.c | 2 +- 2 files changed, 17 insertions(+), 17 deletions(-) diff --git

[PATCH v4 1/7] net:snmp: Introduce generic interfaces for snmp_get_cpu_field{,64}

This is to introduce the generic interfaces for snmp_get_cpu_field{,64}. It exchanges the two for-loops for collecting the percpu statistics data. This can aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: Jia He Suggested-by: Marcelo Ricardo Leitner

<    1   2   3   4   5   6   7   >