similar to: [PATCH v2 0/6] powerpc: queued spinlocks and rwlocks

This series adds an option to use queued spinlocks for powerpc, and makes it the default for the Book3S-64 subarch. This effort starts with the generic code so it's very simple but still very performant. There are optimisations that can be made to slowpaths, but I think it's better to attack those incrementally if/when we find things, and try to add the improvements to generic code as

Updated with everybody's feedback (thanks all), and more performance results. What I've found is I might have been measuring the worst load point for the paravirt case, and by looking at a range of loads it's clear that queued spinlocks are overall better even on PV, doubly so when you look at the generally much improved worst case latencies. I have defaulted it to N even though

v3 is updated to use __pv_queued_spin_unlock, noticed by Waiman (thank you). Thanks, Nick Nicholas Piggin (6): powerpc/powernv: must include hvcall.h to get PAPR defines powerpc/pseries: move some PAPR paravirt functions to their own file powerpc: move spinlock implementation to simple_spinlock powerpc/64s: implement queued spinlocks and rwlocks powerpc/pseries: implement paravirt

v3 is updated to use __pv_queued_spin_unlock, noticed by Waiman (thank you). Thanks, Nick Nicholas Piggin (6): powerpc/powernv: must include hvcall.h to get PAPR defines powerpc/pseries: move some PAPR paravirt functions to their own file powerpc: move spinlock implementation to simple_spinlock powerpc/64s: implement queued spinlocks and rwlocks powerpc/pseries: implement paravirt

To prepare for queued spinlocks. This is a simple rename except to update preprocessor guard name and a file reference. Signed-off-by: Nicholas Piggin <npiggin at gmail.com> --- arch/powerpc/include/asm/simple_spinlock.h | 292 ++++++++++++++++++ .../include/asm/simple_spinlock_types.h | 21 ++ arch/powerpc/include/asm/spinlock.h | 285 +----------------

Hi All, this is the fairlock patchset. You can apply them and build successfully. patches are based on linux-next qspinlock can avoid waiter starved issue. It has about the same speed in single-thread and it can be much faster in high contention situations especially when the spinlock is embedded within the data structure to be protected. v7 -> v8: add one patch to drop a function call

Hi All, this is the fairlock patchset. You can apply them and build successfully. patches are based on linux-next qspinlock can avoid waiter starved issue. It has about the same speed in single-thread and it can be much faster in high contention situations especially when the spinlock is embedded within the data structure to be protected. v7 -> v8: add one patch to drop a function call

From: root <root at ltcalpine2-lp13.aus.stglabs.ibm.com> change from v4: BUG FIX. thanks boqun reporting this issue. struct __qspinlock has different layout in bigendian mahcine. native_queued_spin_unlock() may write value to a wrong address. now fix it. change from v3: a big change in [PATCH v4 4/6] pv-qspinlock: powerpc support pv-qspinlock no other patch changed. and the patch

From: root <root at ltcalpine2-lp13.aus.stglabs.ibm.com> change from v4: BUG FIX. thanks boqun reporting this issue. struct __qspinlock has different layout in bigendian mahcine. native_queued_spin_unlock() may write value to a wrong address. now fix it. change from v3: a big change in [PATCH v4 4/6] pv-qspinlock: powerpc support pv-qspinlock no other patch changed. and the patch

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 |

Hi All, this is the fairlock patchset. You can apply them and build successfully. patches are based on linux-next qspinlock can avoid waiter starved issue. It has about the same speed in single-thread and it can be much faster in high contention situations especially when the spinlock is embedded within the data structure to be protected. v8 -> v9: mv qspinlocm config entry to

Hi All, this is the fairlock patchset. You can apply them and build successfully. patches are based on linux-next qspinlock can avoid waiter starved issue. It has about the same speed in single-thread and it can be much faster in high contention situations especially when the spinlock is embedded within the data structure to be protected. v8 -> v9: mv qspinlocm config entry to

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

change from v4: BUG FIX. thanks boqun reporting this issue. struct __qspinlock has different layout in bigendian mahcine. native_queued_spin_unlock() may write value to a wrong address. now fix it. sorry for not even doing a test on bigendian machine before!!! change from v3: a big change in [PATCH v4 4/6] pv-qspinlock: powerpc support pv-qspinlock no other patch changed. and the patch