similar to: [PATCH resend] powerpc: enable qspinlock and its virtualization support

From: Pan Xinhui <xinhui.pan at linux.vnet.ibm.com> This path aims to enable qspinlock on PPC. And on pseries platform, it also support paravirt qspinlock. Signed-off-by: Pan Xinhui <xinhui.pan at linux.vnet.ibm.com> --- arch/powerpc/include/asm/qspinlock.h | 37 +++++++++++++++ arch/powerpc/include/asm/qspinlock_paravirt.h | 36 +++++++++++++++

From: Pan Xinhui <xinhui.pan at linux.vnet.ibm.com> This path aims to enable qspinlock on PPC. And on pseries platform, it also support paravirt qspinlock. Signed-off-by: Pan Xinhui <xinhui.pan at linux.vnet.ibm.com> --- arch/powerpc/include/asm/qspinlock.h | 37 +++++++++++++++ arch/powerpc/include/asm/qspinlock_paravirt.h | 36 +++++++++++++++

On Mon, Dec 05, 2016 at 10:19:23AM -0500, Pan Xinhui wrote: > Add two corresponding helper functions to support pv-qspinlock. > > For normal use, __spin_yield_cpu will confer current vcpu slices to the > target vcpu(say, a lock holder). If target vcpu is not specified or it > is in running state, such conferging to lpar happens or not depends. > > Because hcall itself will

On Mon, Dec 05, 2016 at 10:19:23AM -0500, Pan Xinhui wrote: > Add two corresponding helper functions to support pv-qspinlock. > > For normal use, __spin_yield_cpu will confer current vcpu slices to the > target vcpu(say, a lock holder). If target vcpu is not specified or it > is in running state, such conferging to lpar happens or not depends. > > Because hcall itself will

pv-qspinlock core has pv_wait/pv_kick which will give a better performace by yielding and kicking cpu at some cases. lets support them by adding two corresponding helper functions. Signed-off-by: Pan Xinhui <xinhui.pan at linux.vnet.ibm.com> --- arch/powerpc/include/asm/spinlock.h | 4 ++++ arch/powerpc/lib/locks.c | 32 ++++++++++++++++++++++++++++++++ 2 files changed, 36

Add two corresponding helper functions to support pv-qspinlock. For normal use, __spin_yield_cpu will confer current vcpu slices to the target vcpu(say, a lock holder). If target vcpu is not specified or it is in running state, such conferging to lpar happens or not depends. Because hcall itself will introduce latency and a little overhead. And we do NOT want to suffer any latency on some cases,

On Thu, 2016-06-02 at 17:22 +0800, Pan Xinhui wrote: > Base code to enable qspinlock on powerpc. this patch add some #ifdef > here and there. Although there is no paravirt related code, we can > successfully build a qspinlock kernel after apply this patch. This is missing the IO_SYNC stuff ... It means we'll fail to do a full sync to order vs MMIOs. You need to add that back in the

On Thu, 2016-06-02 at 17:22 +0800, Pan Xinhui wrote: > Base code to enable qspinlock on powerpc. this patch add some #ifdef > here and there. Although there is no paravirt related code, we can > successfully build a qspinlock kernel after apply this patch. This is missing the IO_SYNC stuff ... It means we'll fail to do a full sync to order vs MMIOs. You need to add that back in the

On Mon, Dec 05, 2016 at 10:19:21AM -0500, Pan Xinhui wrote: > This patch add basic code to enable qspinlock on powerpc. qspinlock is > one kind of fairlock implementation. And seen some performance improvement > under some scenarios. > > queued_spin_unlock() release the lock by just one write of NULL to the > ::locked field which sits at different places in the two endianness

On Mon, Dec 05, 2016 at 10:19:21AM -0500, Pan Xinhui wrote: > This patch add basic code to enable qspinlock on powerpc. qspinlock is > one kind of fairlock implementation. And seen some performance improvement > under some scenarios. > > queued_spin_unlock() release the lock by just one write of NULL to the > ::locked field which sits at different places in the two endianness

change fome v1: separate into 6 pathes from one patch some minor code changes. benchmark test results are below. run 3 tests on pseries IBM,8408-E8E with 32cpus, 64GB memory perf bench futex hash perf bench futex lock-pi perf record -advRT || perf bench sched messaging -g 1000 || perf report summary: _____test________________spinlcok______________pv-qspinlcok_____ |futex hash | 556370 ops |

change fome v1: separate into 6 pathes from one patch some minor code changes. benchmark test results are below. run 3 tests on pseries IBM,8408-E8E with 32cpus, 64GB memory perf bench futex hash perf bench futex lock-pi perf record -advRT || perf bench sched messaging -g 1000 || perf report summary: _____test________________spinlcok______________pv-qspinlcok_____ |futex hash | 556370 ops |

On 2016?06?03? 09:32, Benjamin Herrenschmidt wrote: > On Fri, 2016-06-03 at 11:32 +1000, Benjamin Herrenschmidt wrote: >> On Thu, 2016-06-02 at 17:22 +0800, Pan Xinhui wrote: >>> >>> Base code to enable qspinlock on powerpc. this patch add some >>> #ifdef >>> here and there. Although there is no paravirt related code, we can >>> successfully

On 2016?06?03? 09:32, Benjamin Herrenschmidt wrote: > On Fri, 2016-06-03 at 11:32 +1000, Benjamin Herrenschmidt wrote: >> On Thu, 2016-06-02 at 17:22 +0800, Pan Xinhui wrote: >>> >>> Base code to enable qspinlock on powerpc. this patch add some >>> #ifdef >>> here and there. Although there is no paravirt related code, we can >>> successfully

change from v2: __spin_yeild_cpu() will yield slices to lpar if target cpu is running. remove unnecessary rmb() in __spin_yield/wake_cpu. __pv_wait() will check the *ptr == val. some commit message change change fome v1: separate into 6 pathes from one patch some minor code changes. I do several tests on pseries IBM,8408-E8E with 32cpus, 64GB memory. benchmark test results are below. 2

change from v2: __spin_yeild_cpu() will yield slices to lpar if target cpu is running. remove unnecessary rmb() in __spin_yield/wake_cpu. __pv_wait() will check the *ptr == val. some commit message change change fome v1: separate into 6 pathes from one patch some minor code changes. I do several tests on pseries IBM,8408-E8E with 32cpus, 64GB memory. benchmark test results are below. 2

This patch add basic code to enable qspinlock on powerpc. qspinlock is one kind of fairlock implementation. And seen some performance improvement under some scenarios. queued_spin_unlock() release the lock by just one write of NULL to the ::locked field which sits at different places in the two endianness system. We override some arch_spin_XXX as powerpc has io_sync stuff which makes sure the io

On Fri, 2016-06-03 at 11:32 +1000, Benjamin Herrenschmidt wrote: > On Thu, 2016-06-02 at 17:22 +0800, Pan Xinhui wrote: > > > > Base code to enable qspinlock on powerpc. this patch add some > > #ifdef > > here and there. Although there is no paravirt related code, we can > > successfully build a qspinlock kernel after apply this patch. > This is missing the

Base code to enable qspinlock on powerpc. this patch add some #ifdef here and there. Although there is no paravirt related code, we can successfully build a qspinlock kernel after apply this patch. Signed-off-by: Pan Xinhui <xinhui.pan at linux.vnet.ibm.com> --- arch/powerpc/include/asm/qspinlock.h | 26 ++++++++++++++++++++++++++ arch/powerpc/include/asm/spinlock.h | 27

Base code to enable qspinlock on powerpc. this patch add some #ifdef here and there. Although there is no paravirt related code, we can successfully build a qspinlock kernel after apply this patch. Signed-off-by: Pan Xinhui <xinhui.pan at linux.vnet.ibm.com> --- arch/powerpc/include/asm/qspinlock.h | 26 ++++++++++++++++++++++++++ arch/powerpc/include/asm/spinlock.h | 27