Zhenzhong Duan <zhenzhong.d...@oracle.com> writes:
> There are cases where a guest tries to switch spinlocks to bare metal
> behavior (e.g. by setting "xen_nopvspin" on XEN platform and
> "hv_nopvspin" on HYPER_V).
>
> That feature is missed on KVM, add a new parameter "nopvspin" to disable
> PV spinlocks for KVM guest.
>
> This new parameter is also intended to replace "xen_nopvspin" and
> "hv_nopvspin" in the future.
Any reason to not do it right now? We will probably need to have compat
code to support xen_nopvspin/hv_nopvspin too but emit a 'is deprecated'
warning.
>
> The global variable pvspin isn't defined as __initdata as it's used at
> runtime by XEN guest.
>
> Refactor the print stuff with pr_* which is preferred.
Please do it in a separate patch.
>
> Signed-off-by: Zhenzhong Duan <zhenzhong.d...@oracle.com>
> Cc: Jonathan Corbet <cor...@lwn.net>
> Cc: Thomas Gleixner <t...@linutronix.de>
> Cc: Ingo Molnar <mi...@redhat.com>
> Cc: Borislav Petkov <b...@alien8.de>
> Cc: "H. Peter Anvin" <h...@zytor.com>
> Cc: Paolo Bonzini <pbonz...@redhat.com>
> Cc: Radim Krcmar <rkrc...@redhat.com>
> Cc: Sean Christopherson <sean.j.christopher...@intel.com>
> Cc: Vitaly Kuznetsov <vkuzn...@redhat.com>
> Cc: Wanpeng Li <wanpen...@tencent.com>
> Cc: Jim Mattson <jmatt...@google.com>
> Cc: Joerg Roedel <j...@8bytes.org>
> Cc: Peter Zijlstra <pet...@infradead.org>
> Cc: Will Deacon <w...@kernel.org>
> ---
> Documentation/admin-guide/kernel-parameters.txt | 4 ++++
> arch/x86/include/asm/qspinlock.h | 1 +
> arch/x86/kernel/kvm.c | 27
> ++++++++++++++++---------
> kernel/locking/qspinlock.c | 7 +++++++
> 4 files changed, 30 insertions(+), 9 deletions(-)
>
> diff --git a/Documentation/admin-guide/kernel-parameters.txt
> b/Documentation/admin-guide/kernel-parameters.txt
> index c7ac2f3..4b956d8 100644
> --- a/Documentation/admin-guide/kernel-parameters.txt
> +++ b/Documentation/admin-guide/kernel-parameters.txt
> @@ -5330,6 +5330,10 @@
> as generic guest with no PV drivers. Currently support
> XEN HVM, KVM, HYPER_V and VMWARE guest.
>
> + nopvspin [X86,KVM] Disables the qspinlock slow path
> + using PV optimizations which allow the hypervisor to
> + 'idle' the guest on lock contention.
> +
> xirc2ps_cs= [NET,PCMCIA]
> Format:
>
> <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]]
> diff --git a/arch/x86/include/asm/qspinlock.h
> b/arch/x86/include/asm/qspinlock.h
> index 444d6fd..34a4484 100644
> --- a/arch/x86/include/asm/qspinlock.h
> +++ b/arch/x86/include/asm/qspinlock.h
> @@ -32,6 +32,7 @@ static __always_inline u32
> queued_fetch_set_pending_acquire(struct qspinlock *lo
> extern void __pv_init_lock_hash(void);
> extern void __pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
> extern void __raw_callee_save___pv_queued_spin_unlock(struct qspinlock
> *lock);
> +extern bool pvspin;
>
> #define queued_spin_unlock queued_spin_unlock
> /**
> diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
> index e820568..7b8cf0d 100644
> --- a/arch/x86/kernel/kvm.c
> +++ b/arch/x86/kernel/kvm.c
> @@ -7,6 +7,8 @@
> * Authors: Anthony Liguori <aligu...@us.ibm.com>
> */
>
> +#define pr_fmt(fmt) "KVM: " fmt
> +
> #include <linux/context_tracking.h>
> #include <linux/init.h>
> #include <linux/kernel.h>
> @@ -286,7 +288,7 @@ static void kvm_register_steal_time(void)
> return;
>
> wrmsrl(MSR_KVM_STEAL_TIME, (slow_virt_to_phys(st) | KVM_MSR_ENABLED));
> - pr_info("kvm-stealtime: cpu %d, msr %llx\n",
> + pr_info("stealtime: cpu %d, msr %llx\n",
> cpu, (unsigned long long) slow_virt_to_phys(st));
> }
>
> @@ -321,7 +323,7 @@ static void kvm_guest_cpu_init(void)
>
> wrmsrl(MSR_KVM_ASYNC_PF_EN, pa);
> __this_cpu_write(apf_reason.enabled, 1);
> - printk(KERN_INFO"KVM setup async PF for cpu %d\n",
> + pr_info("setup async PF for cpu %d\n",
> smp_processor_id());
> }
>
> @@ -347,7 +349,7 @@ static void kvm_pv_disable_apf(void)
> wrmsrl(MSR_KVM_ASYNC_PF_EN, 0);
> __this_cpu_write(apf_reason.enabled, 0);
>
> - printk(KERN_INFO"Unregister pv shared memory for cpu %d\n",
> + pr_info("Unregister pv shared memory for cpu %d\n",
> smp_processor_id());
> }
>
> @@ -509,7 +511,7 @@ static void kvm_setup_pv_ipi(void)
> {
> apic->send_IPI_mask = kvm_send_ipi_mask;
> apic->send_IPI_mask_allbutself = kvm_send_ipi_mask_allbutself;
> - pr_info("KVM setup pv IPIs\n");
> + pr_info("setup pv IPIs\n");
> }
>
> static void kvm_smp_send_call_func_ipi(const struct cpumask *mask)
> @@ -639,11 +641,11 @@ static void __init kvm_guest_init(void)
> !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
> kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
> smp_ops.send_call_func_ipi = kvm_smp_send_call_func_ipi;
> - pr_info("KVM setup pv sched yield\n");
> + pr_info("setup pv sched yield\n");
> }
> if (cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/kvm:online",
> kvm_cpu_online, kvm_cpu_down_prepare) < 0)
> - pr_err("kvm_guest: Failed to install cpu hotplug callbacks\n");
> + pr_err("failed to install cpu hotplug callbacks\n");
> #else
> sev_map_percpu_data();
> kvm_guest_cpu_init();
> @@ -746,7 +748,7 @@ static __init int kvm_setup_pv_tlb_flush(void)
> zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask,
> cpu),
> GFP_KERNEL, cpu_to_node(cpu));
> }
> - pr_info("KVM setup pv remote TLB flush\n");
> + pr_info("setup pv remote TLB flush\n");
> }
>
> return 0;
> @@ -842,6 +844,13 @@ void __init kvm_spinlock_init(void)
> if (num_possible_cpus() == 1)
> return;
>
> + if (!pvspin) {
> + pr_info("PV spinlocks disabled\n");
> + static_branch_disable(&virt_spin_lock_key);
> + return;
> + }
> + pr_info("PV spinlocks enabled\n");
> +
> __pv_init_lock_hash();
> pv_ops.lock.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
> pv_ops.lock.queued_spin_unlock =
> @@ -872,8 +881,8 @@ static void kvm_enable_host_haltpoll(void *i)
> void arch_haltpoll_enable(unsigned int cpu)
> {
> if (!kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL)) {
> - pr_err_once("kvm: host does not support poll control\n");
> - pr_err_once("kvm: host upgrade recommended\n");
> + pr_err_once("host does not support poll control\n");
> + pr_err_once("host upgrade recommended\n");
> return;
> }
>
> diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
> index 2473f10..945b510 100644
> --- a/kernel/locking/qspinlock.c
> +++ b/kernel/locking/qspinlock.c
> @@ -580,4 +580,11 @@ void queued_spin_lock_slowpath(struct qspinlock *lock,
> u32 val)
> #include "qspinlock_paravirt.h"
> #include "qspinlock.c"
>
> +bool pvspin = true;
> +static __init int parse_nopvspin(char *arg)
> +{
> + pvspin = false;
> + return 0;
> +}
> +early_param("nopvspin", parse_nopvspin);
> #endif
--
Vitaly
