Re: [PATCH] x86/paravirt: Disable virt spinlock when CONFIG_PARAVIRT_SPINLOCKS disabled
On 2024-05-23 at 09:30:59 -0700, Dave Hansen wrote: > On 5/16/24 06:02, Chen Yu wrote: > > Performance drop is reported when running encode/decode workload and > > BenchSEE cache sub-workload. > > Bisect points to commit ce0a1b608bfc ("x86/paravirt: Silence unused > > native_pv_lock_init() function warning"). When CONFIG_PARAVIRT_SPINLOCKS > > is disabled the virt_spin_lock_key is set to true on bare-metal. > > The qspinlock degenerates to test-and-set spinlock, which decrease the > > performance on bare-metal. > > > > Fix this by disabling virt_spin_lock_key if CONFIG_PARAVIRT_SPINLOCKS > > is not set, or it is on bare-metal. > > This is missing some background: > > The kernel can change spinlock behavior when running as a guest. But > this guest-friendly behavior causes performance problems on bare metal. > So there's a 'virt_spin_lock_key' static key to switch between the two > modes. > > The static key is always enabled by default (run in guest mode) and > should be disabled for bare metal (and in some guests that want native > behavior). > > ... then describe the regression and the fix > Thanks Juergen for your review. And thanks Dave for the write up, I'll refine the log according to your suggestion. > > diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c > > index 5358d43886ad..ee51c0949ed8 100644 > > --- a/arch/x86/kernel/paravirt.c > > +++ b/arch/x86/kernel/paravirt.c > > @@ -55,7 +55,7 @@ DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key); > > > > void __init native_pv_lock_init(void) > > { > > - if (IS_ENABLED(CONFIG_PARAVIRT_SPINLOCKS) && > > + if (!IS_ENABLED(CONFIG_PARAVIRT_SPINLOCKS) || > > !boot_cpu_has(X86_FEATURE_HYPERVISOR)) > > static_branch_disable(&virt_spin_lock_key); > > } > This gets used at a single site: > > if (pv_enabled()) > goto pv_queue; > > if (virt_spin_lock(lock)) > return; > > which is logically: > > if (IS_ENABLED(CONFIG_PARAVIRT_SPINLOCKS)) > goto ...; // don't look at virt_spin_lock_key > > if (virt_spin_lock_key) > return; // On virt, but non-paravirt. Did Test-and-Set > // spinlock. > Thanks for the description in detail, my original change might break the "X86_FEATURE_HYPERVISOR + NO_CONFIG_PARAVIRT_SPINLOCKS " case that, the guest can not fall into test-and-set. > So I _think_ Arnd was trying to optimize native_pv_lock_init() away when > it's going to get skipped over anyway by the 'goto'. > > But this took me at least 30 minutes of scratching my head and trying to > untangle the whole thing. It's all far too subtle for my taste, and all > of that to save a few bytes of init text in a configuration that's > probably not even used very often (PARAVIRT=y, but PARAVIRT_SPINLOCKS=n). > > Let's just keep it simple. How about the attached patch? Yes, this one works, I'll refine it. thanks, Chenyu
Re: [PATCH] x86/paravirt: Disable virt spinlock when CONFIG_PARAVIRT_SPINLOCKS disabled
On 5/23/24 11:39, Jürgen Groß wrote: >> >> Let's just keep it simple. How about the attached patch? > > Simple indeed. The attachment is empty. 😛 Let's try this again.diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 5358d43886ad..c193c9e60a1b 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -55,8 +55,7 @@ DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key); void __init native_pv_lock_init(void) { - if (IS_ENABLED(CONFIG_PARAVIRT_SPINLOCKS) && - !boot_cpu_has(X86_FEATURE_HYPERVISOR)) + if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) static_branch_disable(&virt_spin_lock_key); }
Re: [PATCH] x86/paravirt: Disable virt spinlock when CONFIG_PARAVIRT_SPINLOCKS disabled
On 23.05.24 18:30, Dave Hansen wrote: On 5/16/24 06:02, Chen Yu wrote: Performance drop is reported when running encode/decode workload and BenchSEE cache sub-workload. Bisect points to commit ce0a1b608bfc ("x86/paravirt: Silence unused native_pv_lock_init() function warning"). When CONFIG_PARAVIRT_SPINLOCKS is disabled the virt_spin_lock_key is set to true on bare-metal. The qspinlock degenerates to test-and-set spinlock, which decrease the performance on bare-metal. Fix this by disabling virt_spin_lock_key if CONFIG_PARAVIRT_SPINLOCKS is not set, or it is on bare-metal. This is missing some background: The kernel can change spinlock behavior when running as a guest. But this guest-friendly behavior causes performance problems on bare metal. So there's a 'virt_spin_lock_key' static key to switch between the two modes. The static key is always enabled by default (run in guest mode) and should be disabled for bare metal (and in some guests that want native behavior). ... then describe the regression and the fix diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 5358d43886ad..ee51c0949ed8 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -55,7 +55,7 @@ DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key); void __init native_pv_lock_init(void) { - if (IS_ENABLED(CONFIG_PARAVIRT_SPINLOCKS) && + if (!IS_ENABLED(CONFIG_PARAVIRT_SPINLOCKS) || !boot_cpu_has(X86_FEATURE_HYPERVISOR)) static_branch_disable(&virt_spin_lock_key); } This gets used at a single site: if (pv_enabled()) goto pv_queue; if (virt_spin_lock(lock)) return; which is logically: if (IS_ENABLED(CONFIG_PARAVIRT_SPINLOCKS)) goto ...; // don't look at virt_spin_lock_key if (virt_spin_lock_key) return; // On virt, but non-paravirt. Did Test-and-Set // spinlock. So I _think_ Arnd was trying to optimize native_pv_lock_init() away when it's going to get skipped over anyway by the 'goto'. But this took me at least 30 minutes of scratching my head and trying to untangle the whole thing. It's all far too subtle for my taste, and all of that to save a few bytes of init text in a configuration that's probably not even used very often (PARAVIRT=y, but PARAVIRT_SPINLOCKS=n). Let's just keep it simple. How about the attached patch? Simple indeed. The attachment is empty. :-p Juergen
Re: [PATCH] x86/paravirt: Disable virt spinlock when CONFIG_PARAVIRT_SPINLOCKS disabled
On 5/16/24 06:02, Chen Yu wrote: > Performance drop is reported when running encode/decode workload and > BenchSEE cache sub-workload. > Bisect points to commit ce0a1b608bfc ("x86/paravirt: Silence unused > native_pv_lock_init() function warning"). When CONFIG_PARAVIRT_SPINLOCKS > is disabled the virt_spin_lock_key is set to true on bare-metal. > The qspinlock degenerates to test-and-set spinlock, which decrease the > performance on bare-metal. > > Fix this by disabling virt_spin_lock_key if CONFIG_PARAVIRT_SPINLOCKS > is not set, or it is on bare-metal. This is missing some background: The kernel can change spinlock behavior when running as a guest. But this guest-friendly behavior causes performance problems on bare metal. So there's a 'virt_spin_lock_key' static key to switch between the two modes. The static key is always enabled by default (run in guest mode) and should be disabled for bare metal (and in some guests that want native behavior). ... then describe the regression and the fix > diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c > index 5358d43886ad..ee51c0949ed8 100644 > --- a/arch/x86/kernel/paravirt.c > +++ b/arch/x86/kernel/paravirt.c > @@ -55,7 +55,7 @@ DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key); > > void __init native_pv_lock_init(void) > { > - if (IS_ENABLED(CONFIG_PARAVIRT_SPINLOCKS) && > + if (!IS_ENABLED(CONFIG_PARAVIRT_SPINLOCKS) || > !boot_cpu_has(X86_FEATURE_HYPERVISOR)) > static_branch_disable(&virt_spin_lock_key); > } This gets used at a single site: if (pv_enabled()) goto pv_queue; if (virt_spin_lock(lock)) return; which is logically: if (IS_ENABLED(CONFIG_PARAVIRT_SPINLOCKS)) goto ...; // don't look at virt_spin_lock_key if (virt_spin_lock_key) return; // On virt, but non-paravirt. Did Test-and-Set // spinlock. So I _think_ Arnd was trying to optimize native_pv_lock_init() away when it's going to get skipped over anyway by the 'goto'. But this took me at least 30 minutes of scratching my head and trying to untangle the whole thing. It's all far too subtle for my taste, and all of that to save a few bytes of init text in a configuration that's probably not even used very often (PARAVIRT=y, but PARAVIRT_SPINLOCKS=n). Let's just keep it simple. How about the attached patch?
Re: [PATCH] x86/paravirt: Disable virt spinlock when CONFIG_PARAVIRT_SPINLOCKS disabled
On 16.05.24 15:02, Chen Yu wrote: Performance drop is reported when running encode/decode workload and BenchSEE cache sub-workload. Bisect points to commit ce0a1b608bfc ("x86/paravirt: Silence unused native_pv_lock_init() function warning"). When CONFIG_PARAVIRT_SPINLOCKS is disabled the virt_spin_lock_key is set to true on bare-metal. The qspinlock degenerates to test-and-set spinlock, which decrease the performance on bare-metal. Fix this by disabling virt_spin_lock_key if CONFIG_PARAVIRT_SPINLOCKS is not set, or it is on bare-metal. Fixes: ce0a1b608bfc ("x86/paravirt: Silence unused native_pv_lock_init() function warning") Suggested-by: Qiuxu Zhuo Reported-by: Prem Nath Dey Reported-by: Xiaoping Zhou Signed-off-by: Chen Yu Reviewed-by: Juergen Gross Juergen --- arch/x86/kernel/paravirt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 5358d43886ad..ee51c0949ed8 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -55,7 +55,7 @@ DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key); void __init native_pv_lock_init(void) { - if (IS_ENABLED(CONFIG_PARAVIRT_SPINLOCKS) && + if (!IS_ENABLED(CONFIG_PARAVIRT_SPINLOCKS) || !boot_cpu_has(X86_FEATURE_HYPERVISOR)) static_branch_disable(&virt_spin_lock_key); } OpenPGP_0xB0DE9DD628BF132F.asc Description: OpenPGP public key OpenPGP_signature.asc Description: OpenPGP digital signature
[PATCH] x86/paravirt: Disable virt spinlock when CONFIG_PARAVIRT_SPINLOCKS disabled
Performance drop is reported when running encode/decode workload and BenchSEE cache sub-workload. Bisect points to commit ce0a1b608bfc ("x86/paravirt: Silence unused native_pv_lock_init() function warning"). When CONFIG_PARAVIRT_SPINLOCKS is disabled the virt_spin_lock_key is set to true on bare-metal. The qspinlock degenerates to test-and-set spinlock, which decrease the performance on bare-metal. Fix this by disabling virt_spin_lock_key if CONFIG_PARAVIRT_SPINLOCKS is not set, or it is on bare-metal. Fixes: ce0a1b608bfc ("x86/paravirt: Silence unused native_pv_lock_init() function warning") Suggested-by: Qiuxu Zhuo Reported-by: Prem Nath Dey Reported-by: Xiaoping Zhou Signed-off-by: Chen Yu --- arch/x86/kernel/paravirt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 5358d43886ad..ee51c0949ed8 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -55,7 +55,7 @@ DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key); void __init native_pv_lock_init(void) { - if (IS_ENABLED(CONFIG_PARAVIRT_SPINLOCKS) && + if (!IS_ENABLED(CONFIG_PARAVIRT_SPINLOCKS) || !boot_cpu_has(X86_FEATURE_HYPERVISOR)) static_branch_disable(&virt_spin_lock_key); } -- 2.25.1