Re: [PATCH V11 08/17] riscv: qspinlock: Add virt_spin_lock() support for KVM guest

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Tue, Sep 19, 2023 at 04:04:48PM +0800, Guo Ren wrote:
> On Tue, Sep 19, 2023 at 1:30 PM Leonardo Bras <leobras@xxxxxxxxxx> wrote:
> >
> > On Sun, Sep 17, 2023 at 11:12:31PM +0800, Guo Ren wrote:
> > > On Thu, Sep 14, 2023 at 4:02 PM Leonardo Bras <leobras@xxxxxxxxxx> wrote:
> > > >
> > > > On Sun, Sep 10, 2023 at 04:29:02AM -0400, guoren@xxxxxxxxxx wrote:
> > > > > From: Guo Ren <guoren@xxxxxxxxxxxxxxxxx>
> > > > >
> > > > > Add a static key controlling whether virt_spin_lock() should be
> > > > > called or not. When running on bare metal set the new key to
> > > > > false.
> > > > >
> > > > > The KVM guests fall back to a Test-and-Set spinlock, because fair
> > > > > locks have horrible lock 'holder' preemption issues. The
> > > > > virt_spin_lock_key would shortcut for the
> > > > > queued_spin_lock_slowpath() function that allow virt_spin_lock to
> > > > > hijack it.
> > > > >
> > > > > Signed-off-by: Guo Ren <guoren@xxxxxxxxxxxxxxxxx>
> > > > > Signed-off-by: Guo Ren <guoren@xxxxxxxxxx>
> > > > > ---
> > > > >  .../admin-guide/kernel-parameters.txt         |  4 +++
> > > > >  arch/riscv/include/asm/sbi.h                  |  8 +++++
> > > > >  arch/riscv/include/asm/spinlock.h             | 22 ++++++++++++++
> > > > >  arch/riscv/kernel/sbi.c                       |  2 +-
> > > > >  arch/riscv/kernel/setup.c                     | 30 ++++++++++++++++++-
> > > > >  5 files changed, 64 insertions(+), 2 deletions(-)
> > > > >
> > > > > diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
> > > > > index 61cacb8dfd0e..f75bedc50e00 100644
> > > > > --- a/Documentation/admin-guide/kernel-parameters.txt
> > > > > +++ b/Documentation/admin-guide/kernel-parameters.txt
> > > > > @@ -3927,6 +3927,10 @@
> > > > >       no_uaccess_flush
> > > > >                       [PPC] Don't flush the L1-D cache after accessing user data.
> > > > >
> > > > > +     no_virt_spin    [RISC-V] Disable virt_spin_lock in KVM guest to use
> > > > > +                     native_queued_spinlock when the nopvspin option is enabled.
> > > > > +                     This would help vcpu=pcpu scenarios.
> > > > > +
> > > > >       novmcoredd      [KNL,KDUMP]
> > > > >                       Disable device dump. Device dump allows drivers to
> > > > >                       append dump data to vmcore so you can collect driver
> > > > > diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h
> > > > > index 501e06e52078..e0233b3d7a5f 100644
> > > > > --- a/arch/riscv/include/asm/sbi.h
> > > > > +++ b/arch/riscv/include/asm/sbi.h
> > > > > @@ -50,6 +50,13 @@ enum sbi_ext_base_fid {
> > > > >       SBI_EXT_BASE_GET_MIMPID,
> > > > >  };
> > > > >
> > > > > +enum sbi_ext_base_impl_id {
> > > > > +     SBI_EXT_BASE_IMPL_ID_BBL = 0,
> > > > > +     SBI_EXT_BASE_IMPL_ID_OPENSBI,
> > > > > +     SBI_EXT_BASE_IMPL_ID_XVISOR,
> > > > > +     SBI_EXT_BASE_IMPL_ID_KVM,
> > > > > +};
> > > > > +
> > > > >  enum sbi_ext_time_fid {
> > > > >       SBI_EXT_TIME_SET_TIMER = 0,
> > > > >  };
> > > > > @@ -269,6 +276,7 @@ int sbi_console_getchar(void);
> > > > >  long sbi_get_mvendorid(void);
> > > > >  long sbi_get_marchid(void);
> > > > >  long sbi_get_mimpid(void);
> > > > > +long sbi_get_firmware_id(void);
> > > > >  void sbi_set_timer(uint64_t stime_value);
> > > > >  void sbi_shutdown(void);
> > > > >  void sbi_send_ipi(unsigned int cpu);
> > > > > diff --git a/arch/riscv/include/asm/spinlock.h b/arch/riscv/include/asm/spinlock.h
> > > > > index 8ea0fee80652..6b38d6616f14 100644
> > > > > --- a/arch/riscv/include/asm/spinlock.h
> > > > > +++ b/arch/riscv/include/asm/spinlock.h
> > > > > @@ -4,6 +4,28 @@
> > > > >  #define __ASM_RISCV_SPINLOCK_H
> > > > >
> > > > >  #ifdef CONFIG_QUEUED_SPINLOCKS
> > > > > +/*
> > > > > + * The KVM guests fall back to a Test-and-Set spinlock, because fair locks
> > > > > + * have horrible lock 'holder' preemption issues. The virt_spin_lock_key
> > > > > + * would shortcut for the queued_spin_lock_slowpath() function that allow
> > > > > + * virt_spin_lock to hijack it.
> > > > > + */
> > > > > +DECLARE_STATIC_KEY_TRUE(virt_spin_lock_key);
> > > > > +
> > > > > +#define virt_spin_lock virt_spin_lock
> > > > > +static inline bool virt_spin_lock(struct qspinlock *lock)
> > > > > +{
> > > > > +     if (!static_branch_likely(&virt_spin_lock_key))
> > > > > +             return false;
> > > > > +
> > > > > +     do {
> > > > > +             while (atomic_read(&lock->val) != 0)
> > > > > +                     cpu_relax();
> > > > > +     } while (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) != 0);
> > > > > +
> > > > > +     return true;
> > > > > +}
> > > > > +
> > > > >  #define _Q_PENDING_LOOPS     (1 << 9)
> > > > >  #endif
> > > > >
> > > > > diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c
> > > > > index 88eea3a99ee0..cdd45edc8db4 100644
> > > > > --- a/arch/riscv/kernel/sbi.c
> > > > > +++ b/arch/riscv/kernel/sbi.c
> > > > > @@ -555,7 +555,7 @@ static inline long sbi_get_spec_version(void)
> > > > >       return __sbi_base_ecall(SBI_EXT_BASE_GET_SPEC_VERSION);
> > > > >  }
> > > > >
> > > > > -static inline long sbi_get_firmware_id(void)
> > > > > +long sbi_get_firmware_id(void)
> > > > >  {
> > > > >       return __sbi_base_ecall(SBI_EXT_BASE_GET_IMP_ID);
> > > > >  }
> > > > > diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
> > > > > index 0f084f037651..c57d15b05160 100644
> > > > > --- a/arch/riscv/kernel/setup.c
> > > > > +++ b/arch/riscv/kernel/setup.c
> > > > > @@ -26,6 +26,7 @@
> > > > >  #include <asm/alternative.h>
> > > > >  #include <asm/cacheflush.h>
> > > > >  #include <asm/cpu_ops.h>
> > > > > +#include <asm/cpufeature.h>
> > > > >  #include <asm/early_ioremap.h>
> > > > >  #include <asm/pgtable.h>
> > > > >  #include <asm/setup.h>
> > > > > @@ -283,16 +284,43 @@ DEFINE_STATIC_KEY_TRUE(combo_qspinlock_key);
> > > > >  EXPORT_SYMBOL(combo_qspinlock_key);
> > > > >  #endif
> > > > >
> > > > > +#ifdef CONFIG_QUEUED_SPINLOCKS
> > > > > +static bool no_virt_spin_key = false;
> > > >
> > > > I suggest no _key, also there is no need for "= false".
> > > > To be consistent with enable_qspinlock, I also suggest
> > > > adding __ro_after_init:
> > > >
> > > > static bool no_virt_spin __ro_after_init;
> > > okay.
> > >
> > > >
> > > >
> > > >
> > > > > +DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key);
> > > > > +
> > > > > +static int __init no_virt_spin_setup(char *p)
> > > > > +{
> > > > > +     no_virt_spin_key = true;
> > > > > +
> > > > > +     return 0;
> > > > > +}
> > > > > +early_param("no_virt_spin", no_virt_spin_setup);
> > > > > +
> > > > > +static void __init virt_spin_lock_init(void)
> > > > > +{
> > > > > +     if (sbi_get_firmware_id() != SBI_EXT_BASE_IMPL_ID_KVM ||
> > > > > +         no_virt_spin_key)
> > > > > +             static_branch_disable(&virt_spin_lock_key);
> > > > > +     else
> > > > > +             pr_info("Enable virt_spin_lock\n");
> > > > > +}
> > > > > +#endif
> > > > > +
> > > >
> > > > A new virt_no_spin kernel parameter was introduced, but without
> > > > CONFIG_QUEUED_SPINLOCKS it will silently fail.
> > > >
> > > > I would suggest an #else clause here with a function to print an error /
> > > > warning message about no_virt_spin being invalid in this scenario.
> > > > It will probably help future debugging.
> > > If CONFIG_QUEUED_SPINLOCKS=n, no_virt_spin should be quiet. The
> > > no_virt_spin is one path of qspinlock.
> >
> > IIUC having no_virt_spin being passed as parameter to a kernel with
> > CONFIG_QUEUED_SPINLOCKS=n is not supposed to have any warning this
> > parameter is useless.
> >
> > I was just thinking it would be nice to have this warning during debugging,
> > but if it's standard practice then I am ok with this.
> Yes, I think it's okay, e.g.,
> x86: early_param("hv_nopvspin", hv_parse_nopvspin);
> depends on CONFIG_PARAVIRT_SPINLOCKS=y

Okay then, thanks for sharing this info!

> 
> >
> > >
> > > >
> > > >
> > > > >  static void __init riscv_spinlock_init(void)
> > > > >  {
> > > > >  #ifdef CONFIG_RISCV_COMBO_SPINLOCKS
> > > > > -     if (!enable_qspinlock_key) {
> > > > > +     if (!enable_qspinlock_key &&
> > > > > +         (sbi_get_firmware_id() != SBI_EXT_BASE_IMPL_ID_KVM)) {
> > > > >               static_branch_disable(&combo_qspinlock_key);
> > > > >               pr_info("Ticket spinlock: enabled\n");
> > > > >       } else {
> > > > >               pr_info("Queued spinlock: enabled\n");
> > > > >       }
> > > > >  #endif
> > > > > +
> > > > > +#ifdef CONFIG_QUEUED_SPINLOCKS
> > > > > +     virt_spin_lock_init();
> > > > > +#endif
> > > > >  }
> > > > >
> > > > >  extern void __init init_rt_signal_env(void);
> > > > > --
> > > > > 2.36.1
> > > > >
> > > >
> > > > I am probably missing something out, but it looks to me that this patch is
> > > > causing 2 different changes:
> > > > 1 - Enabling no_virt_spin parameter
> > > > 2 - Disabling queued spinlocks for some firmware_id
> > > >
> > > > Wouldn't be better to split those changes in multiple patches?
> > > > Or am I missing the point on why they need to be together?
> >
> > ^ Want your input on this
> Sorry, I missed that. Okay, I would split those changes.

Thanks!
Leo

> 
> >
> > Thanks!
> > Leo
> >
> > > >
> > > > Thanks!
> > > > Leo
> > > >
> > >
> > >
> > > --
> > > Best Regards
> > >  Guo Ren
> > >
> >
> 
> 
> -- 
> Best Regards
>  Guo Ren
> 




[Index of Archives]     [Kernel Newbies]     [Security]     [Netfilter]     [Bugtraq]     [Linux FS]     [Yosemite Forum]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Samba]     [Video 4 Linux]     [Device Mapper]     [Linux Resources]

  Powered by Linux