From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753124Ab1ASRSF (ORCPT ); Wed, 19 Jan 2011 12:18:05 -0500 Received: from e6.ny.us.ibm.com ([32.97.182.146]:55404 "EHLO e6.ny.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753009Ab1ASRSD (ORCPT ); Wed, 19 Jan 2011 12:18:03 -0500 Date: Wed, 19 Jan 2011 22:47:57 +0530 From: Srivatsa Vaddagiri To: Jeremy Fitzhardinge Cc: Peter Zijlstra , Linux Kernel Mailing List , Nick Piggin , Mathieu Desnoyers , =?iso-8859-1?Q?Am=E9rico?= Wang , Eric Dumazet , Jan Beulich , Avi Kivity , Xen-devel , "H. Peter Anvin" , Linux Virtualization , Jeremy Fitzhardinge , kvm@vger.kernel.org, suzuki@in.ibm.com Subject: [PATCH 3/3] kvm guest : Add support for pv-ticketlocks Message-ID: <20110119171757.GC726@linux.vnet.ibm.com> Reply-To: vatsa@linux.vnet.ibm.com References: <20110119164432.GA30669@linux.vnet.ibm.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20110119164432.GA30669@linux.vnet.ibm.com> User-Agent: Mutt/1.5.20 (2009-06-14) X-Content-Scanned: Fidelis XPS MAILER Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org This patch extends Linux guests running on KVM hypervisor to support pv-ticketlocks. Very early during bootup, paravirtualied KVM guest detects if the hypervisor has required feature (KVM_FEATURE_WAIT_FOR_KICK) to support pv-ticketlocks. If so, support for pv-ticketlocks is registered via pv_lock_ops. Signed-off-by: Srivatsa Vaddagiri Signed-off-by: Suzuki Poulose --- arch/x86/Kconfig | 9 + arch/x86/include/asm/kvm_para.h | 8 + arch/x86/kernel/head64.c | 3 arch/x86/kernel/kvm.c | 208 ++++++++++++++++++++++++++++++++++++++++ 4 files changed, 228 insertions(+) Index: linux-2.6.37/arch/x86/Kconfig =================================================================== --- linux-2.6.37.orig/arch/x86/Kconfig +++ linux-2.6.37/arch/x86/Kconfig @@ -508,6 +508,15 @@ config KVM_GUEST This option enables various optimizations for running under the KVM hypervisor. +config KVM_DEBUG_FS + bool "Enable debug information for KVM Guests in debugfs" + depends on KVM_GUEST + default n + ---help--- + This option enables collection of various statistics for KVM guest. + Statistics are displayed in debugfs filesystem. Enabling this option + may incur significant overhead. + source "arch/x86/lguest/Kconfig" config PARAVIRT Index: linux-2.6.37/arch/x86/include/asm/kvm_para.h =================================================================== --- linux-2.6.37.orig/arch/x86/include/asm/kvm_para.h +++ linux-2.6.37/arch/x86/include/asm/kvm_para.h @@ -162,8 +162,16 @@ static inline unsigned int kvm_arch_para #ifdef CONFIG_KVM_GUEST void __init kvm_guest_init(void); + +#ifdef CONFIG_PARAVIRT_SPINLOCKS +void __init kvm_guest_early_init(void); +#else +#define kvm_guest_early_init() do { } while (0) +#endif + #else #define kvm_guest_init() do { } while (0) +#define kvm_guest_early_init() do { } while (0) #endif #endif /* __KERNEL__ */ Index: linux-2.6.37/arch/x86/kernel/head64.c =================================================================== --- linux-2.6.37.orig/arch/x86/kernel/head64.c +++ linux-2.6.37/arch/x86/kernel/head64.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -118,6 +119,8 @@ void __init x86_64_start_reservations(ch reserve_ebda_region(); + kvm_guest_early_init(); + /* * At this point everything still needed from the boot loader * or BIOS or kernel text should be early reserved or marked not Index: linux-2.6.37/arch/x86/kernel/kvm.c =================================================================== --- linux-2.6.37.orig/arch/x86/kernel/kvm.c +++ linux-2.6.37/arch/x86/kernel/kvm.c @@ -238,3 +238,211 @@ void __init kvm_guest_init(void) paravirt_ops_setup(); } + +#ifdef CONFIG_PARAVIRT_SPINLOCKS + +#ifdef CONFIG_KVM_DEBUG_FS + +#include +#include + +static struct kvm_spinlock_stats +{ + u32 taken_slow; + u32 taken_slow_pickup; + + u32 released_slow; + u32 released_slow_kicked; + +#define HISTO_BUCKETS 30 + u32 histo_spin_blocked[HISTO_BUCKETS+1]; + + u64 time_blocked; +} spinlock_stats; + +static u8 zero_stats; + +static inline void check_zero(void) +{ + if (unlikely(zero_stats)) { + memset(&spinlock_stats, 0, sizeof(spinlock_stats)); + zero_stats = 0; + } +} + +#define ADD_STATS(elem, val) \ + do { check_zero(); spinlock_stats.elem += (val); } while (0) + +static inline u64 spin_time_start(void) +{ + return sched_clock(); +} + +static void __spin_time_accum(u64 delta, u32 *array) +{ + unsigned index = ilog2(delta); + + check_zero(); + + if (index < HISTO_BUCKETS) + array[index]++; + else + array[HISTO_BUCKETS]++; +} + +static inline void spin_time_accum_blocked(u64 start) +{ + u32 delta = sched_clock() - start; + + __spin_time_accum(delta, spinlock_stats.histo_spin_blocked); + spinlock_stats.time_blocked += delta; +} + +static struct dentry *d_spin_debug; +static struct dentry *d_kvm_debug; + +struct dentry *kvm_init_debugfs(void) +{ + d_kvm_debug = debugfs_create_dir("kvm", NULL); + if (!d_kvm_debug) + printk(KERN_WARNING "Could not create 'kvm' debugfs directory\n"); + + return d_kvm_debug; +} + +static int __init kvm_spinlock_debugfs(void) +{ + struct dentry *d_kvm = kvm_init_debugfs(); + + if (d_kvm == NULL) + return -ENOMEM; + + d_spin_debug = debugfs_create_dir("spinlocks", d_kvm); + + debugfs_create_u8("zero_stats", 0644, d_spin_debug, &zero_stats); + + debugfs_create_u32("taken_slow", 0444, d_spin_debug, + &spinlock_stats.taken_slow); + debugfs_create_u32("taken_slow_pickup", 0444, d_spin_debug, + &spinlock_stats.taken_slow_pickup); + + debugfs_create_u32("released_slow", 0444, d_spin_debug, + &spinlock_stats.released_slow); + debugfs_create_u32("released_slow_kicked", 0444, d_spin_debug, + &spinlock_stats.released_slow_kicked); + + debugfs_create_u64("time_blocked", 0444, d_spin_debug, + &spinlock_stats.time_blocked); + + debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug, + spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1); + + return 0; +} +fs_initcall(kvm_spinlock_debugfs); +#else /* !CONFIG_KVM_DEBUG_FS */ +#define TIMEOUT (1 << 10) +#define ADD_STATS(elem, val) do { (void)(val); } while (0) + +static inline u64 spin_time_start(void) +{ + return 0; +} + +static inline void spin_time_accum_blocked(u64 start) +{ +} +#endif /* CONFIG_KVM_DEBUG_FS */ + +struct kvm_lock_waiting { + struct arch_spinlock *lock; + __ticket_t want; +}; + +/* cpus 'waiting' on a spinlock to become available */ +static cpumask_t waiting_cpus; + +/* Track spinlock on which a cpu is waiting */ +static DEFINE_PER_CPU(struct kvm_lock_waiting, lock_waiting); + +static inline void kvm_wait_for_kick(void) +{ + kvm_hypercall0(KVM_HC_WAIT_FOR_KICK); +} + +static void kvm_lock_spinning(struct arch_spinlock *lock, unsigned want) +{ + struct kvm_lock_waiting *w = &__get_cpu_var(lock_waiting); + int cpu = smp_processor_id(); + u64 start; + + start = spin_time_start(); + + w->want = want; + w->lock = lock; + + ADD_STATS(taken_slow, 1); + + cpumask_set_cpu(cpu, &waiting_cpus); + + /* Mark entry to slowpath before doing the pickup test to make + sure we don't deadlock with an unlocker. */ + __ticket_enter_slowpath(lock); + + /* check again make sure it didn't become free while + we weren't looking */ + if (ACCESS_ONCE(lock->tickets.head) == want) { + ADD_STATS(taken_slow_pickup, 1); + goto out; + } + + kvm_wait_for_kick(); + +out: + cpumask_clear_cpu(cpu, &waiting_cpus); + w->lock = NULL; + spin_time_accum_blocked(start); +} +PV_CALLEE_SAVE_REGS_THUNK(kvm_lock_spinning); + +/* Kick a cpu */ +static inline void kvm_kick_cpu(int cpu) +{ + kvm_hypercall1(KVM_HC_KICK_CPU, cpu); +} + +/* Kick vcpu waiting on @lock->head to reach value @ticket */ +static void kvm_unlock_kick(struct arch_spinlock *lock, unsigned ticket) +{ + int cpu; + + ADD_STATS(released_slow, 1); + + for_each_cpu(cpu, &waiting_cpus) { + const struct kvm_lock_waiting *w = &per_cpu(lock_waiting, cpu); + if (w->lock == lock && w->want == ticket) { + ADD_STATS(released_slow_kicked, 1); + kvm_kick_cpu(cpu); + break; + } + } +} + +/* + * Setup pv_lock_ops to exploit KVM_FEATURE_WAIT_FOR_KICK if present. + * This needs to be setup really early in boot, before the first call to + * spinlock is issued! + */ +void __init kvm_guest_early_init(void) +{ + if (!kvm_para_available()) + return; + + /* Does host kernel support KVM_FEATURE_WAIT_FOR_KICK? */ + if (!kvm_para_has_feature(KVM_FEATURE_WAIT_FOR_KICK)) + return; + + pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning); + pv_lock_ops.unlock_kick = kvm_unlock_kick; +} +#endif /* CONFIG_PARAVIRT_SPINLOCKS */