1. Patchew
  2. linux
  3. [PATCH 0/3] KVM: s390: Couple of small cmpxchg() optimizations
  4. View patch

[PATCH 1/3] KVM: s390: Use try_cmpxchg() instead of cmpxchg() loops

Heiko Carstens posted 3 patches 1 year, 2 months ago
There is a newer version of this series
[PATCH 1/3] KVM: s390: Use try_cmpxchg() instead of cmpxchg() loops
Posted by Heiko Carstens 1 year, 2 months ago 
Convert all cmpxchg() loops to try_cmpxchg() loops. With gcc 14 and the
usage of flag output operands in try_cmpxchg() this allows the compiler to
generate slightly better code.

Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/kvm/gaccess.c   | 16 ++++++++--------
 arch/s390/kvm/interrupt.c | 12 ++++++------
 arch/s390/kvm/kvm-s390.c  |  4 ++--
 arch/s390/kvm/pci.c       |  5 ++---
 4 files changed, 18 insertions(+), 19 deletions(-)

diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index a688351f4ab5..9816b0060fbe 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -129,8 +129,8 @@ static void ipte_lock_simple(struct kvm *kvm)
 retry:
 	read_lock(&kvm->arch.sca_lock);
 	ic = kvm_s390_get_ipte_control(kvm);
+	old = READ_ONCE(*ic);
 	do {
-		old = READ_ONCE(*ic);
 		if (old.k) {
 			read_unlock(&kvm->arch.sca_lock);
 			cond_resched();
@@ -138,7 +138,7 @@ static void ipte_lock_simple(struct kvm *kvm)
 		}
 		new = old;
 		new.k = 1;
-	} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+	} while (!try_cmpxchg(&ic->val, &old.val, new.val));
 	read_unlock(&kvm->arch.sca_lock);
 out:
 	mutex_unlock(&kvm->arch.ipte_mutex);
@@ -154,11 +154,11 @@ static void ipte_unlock_simple(struct kvm *kvm)
 		goto out;
 	read_lock(&kvm->arch.sca_lock);
 	ic = kvm_s390_get_ipte_control(kvm);
+	old = READ_ONCE(*ic);
 	do {
-		old = READ_ONCE(*ic);
 		new = old;
 		new.k = 0;
-	} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+	} while (!try_cmpxchg(&ic->val, &old.val, new.val));
 	read_unlock(&kvm->arch.sca_lock);
 	wake_up(&kvm->arch.ipte_wq);
 out:
@@ -172,8 +172,8 @@ static void ipte_lock_siif(struct kvm *kvm)
 retry:
 	read_lock(&kvm->arch.sca_lock);
 	ic = kvm_s390_get_ipte_control(kvm);
+	old = READ_ONCE(*ic);
 	do {
-		old = READ_ONCE(*ic);
 		if (old.kg) {
 			read_unlock(&kvm->arch.sca_lock);
 			cond_resched();
@@ -182,7 +182,7 @@ static void ipte_lock_siif(struct kvm *kvm)
 		new = old;
 		new.k = 1;
 		new.kh++;
-	} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+	} while (!try_cmpxchg(&ic->val, &old.val, new.val));
 	read_unlock(&kvm->arch.sca_lock);
 }
 
@@ -192,13 +192,13 @@ static void ipte_unlock_siif(struct kvm *kvm)
 
 	read_lock(&kvm->arch.sca_lock);
 	ic = kvm_s390_get_ipte_control(kvm);
+	old = READ_ONCE(*ic);
 	do {
-		old = READ_ONCE(*ic);
 		new = old;
 		new.kh--;
 		if (!new.kh)
 			new.k = 0;
-	} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+	} while (!try_cmpxchg(&ic->val, &old.val, new.val));
 	read_unlock(&kvm->arch.sca_lock);
 	if (!new.kh)
 		wake_up(&kvm->arch.ipte_wq);
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 4f0e7f61edf7..eff69018cbeb 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -247,12 +247,12 @@ static inline int gisa_set_iam(struct kvm_s390_gisa *gisa, u8 iam)
 {
 	u64 word, _word;
 
+	word = READ_ONCE(gisa->u64.word[0]);
 	do {
-		word = READ_ONCE(gisa->u64.word[0]);
 		if ((u64)gisa != word >> 32)
 			return -EBUSY;
 		_word = (word & ~0xffUL) | iam;
-	} while (cmpxchg(&gisa->u64.word[0], word, _word) != word);
+	} while (!try_cmpxchg(&gisa->u64.word[0], &word, _word));
 
 	return 0;
 }
@@ -270,10 +270,10 @@ static inline void gisa_clear_ipm(struct kvm_s390_gisa *gisa)
 {
 	u64 word, _word;
 
+	word = READ_ONCE(gisa->u64.word[0]);
 	do {
-		word = READ_ONCE(gisa->u64.word[0]);
 		_word = word & ~(0xffUL << 24);
-	} while (cmpxchg(&gisa->u64.word[0], word, _word) != word);
+	} while (!try_cmpxchg(&gisa->u64.word[0], &word, _word));
 }
 
 /**
@@ -291,14 +291,14 @@ static inline u8 gisa_get_ipm_or_restore_iam(struct kvm_s390_gisa_interrupt *gi)
 	u8 pending_mask, alert_mask;
 	u64 word, _word;
 
+	word = READ_ONCE(gi->origin->u64.word[0]);
 	do {
-		word = READ_ONCE(gi->origin->u64.word[0]);
 		alert_mask = READ_ONCE(gi->alert.mask);
 		pending_mask = (u8)(word >> 24) & alert_mask;
 		if (pending_mask)
 			return pending_mask;
 		_word = (word & ~0xffUL) | alert_mask;
-	} while (cmpxchg(&gi->origin->u64.word[0], word, _word) != word);
+	} while (!try_cmpxchg(&gi->origin->u64.word[0], &word, _word));
 
 	return 0;
 }
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 442d4a227c0e..d8080c27d45b 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1937,11 +1937,11 @@ static void kvm_s390_update_topology_change_report(struct kvm *kvm, bool val)
 
 	read_lock(&kvm->arch.sca_lock);
 	sca = kvm->arch.sca;
+	old = READ_ONCE(sca->utility);
 	do {
-		old = READ_ONCE(sca->utility);
 		new = old;
 		new.mtcr = val;
-	} while (cmpxchg(&sca->utility.val, old.val, new.val) != old.val);
+	} while (!try_cmpxchg(&sca->utility.val, &old.val, new.val));
 	read_unlock(&kvm->arch.sca_lock);
 }
 
diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c
index a61518b549f0..9b9e7fdd5380 100644
--- a/arch/s390/kvm/pci.c
+++ b/arch/s390/kvm/pci.c
@@ -208,13 +208,12 @@ static inline int account_mem(unsigned long nr_pages)
 
 	page_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
 
+	cur_pages = atomic_long_read(&user->locked_vm);
 	do {
-		cur_pages = atomic_long_read(&user->locked_vm);
 		new_pages = cur_pages + nr_pages;
 		if (new_pages > page_limit)
 			return -ENOMEM;
-	} while (atomic_long_cmpxchg(&user->locked_vm, cur_pages,
-					new_pages) != cur_pages);
+	} while (!atomic_long_try_cmpxchg(&user->locked_vm, &cur_pages, new_pages));
 
 	atomic64_add(nr_pages, &current->mm->pinned_vm);
 
-- 
2.45.2
Re: [PATCH 1/3] KVM: s390: Use try_cmpxchg() instead of cmpxchg() loops
Posted by Claudio Imbrenda 1 year, 2 months ago 
On Mon, 25 Nov 2024 12:50:37 +0100
Heiko Carstens <hca@linux.ibm.com> wrote:

> Convert all cmpxchg() loops to try_cmpxchg() loops. With gcc 14 and the
> usage of flag output operands in try_cmpxchg() this allows the compiler to
> generate slightly better code.
> 
> Signed-off-by: Heiko Carstens <hca@linux.ibm.com>

Looks straightforward

Acked-by: Claudio Imbrenda <imbrenda@linux.ibm.com>

> ---
>  arch/s390/kvm/gaccess.c   | 16 ++++++++--------
>  arch/s390/kvm/interrupt.c | 12 ++++++------
>  arch/s390/kvm/kvm-s390.c  |  4 ++--
>  arch/s390/kvm/pci.c       |  5 ++---
>  4 files changed, 18 insertions(+), 19 deletions(-)
> 
> diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
> index a688351f4ab5..9816b0060fbe 100644
> --- a/arch/s390/kvm/gaccess.c
> +++ b/arch/s390/kvm/gaccess.c
> @@ -129,8 +129,8 @@ static void ipte_lock_simple(struct kvm *kvm)
>  retry:
>  	read_lock(&kvm->arch.sca_lock);
>  	ic = kvm_s390_get_ipte_control(kvm);
> +	old = READ_ONCE(*ic);
>  	do {
> -		old = READ_ONCE(*ic);
>  		if (old.k) {
>  			read_unlock(&kvm->arch.sca_lock);
>  			cond_resched();
> @@ -138,7 +138,7 @@ static void ipte_lock_simple(struct kvm *kvm)
>  		}
>  		new = old;
>  		new.k = 1;
> -	} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
> +	} while (!try_cmpxchg(&ic->val, &old.val, new.val));
>  	read_unlock(&kvm->arch.sca_lock);
>  out:
>  	mutex_unlock(&kvm->arch.ipte_mutex);
> @@ -154,11 +154,11 @@ static void ipte_unlock_simple(struct kvm *kvm)
>  		goto out;
>  	read_lock(&kvm->arch.sca_lock);
>  	ic = kvm_s390_get_ipte_control(kvm);
> +	old = READ_ONCE(*ic);
>  	do {
> -		old = READ_ONCE(*ic);
>  		new = old;
>  		new.k = 0;
> -	} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
> +	} while (!try_cmpxchg(&ic->val, &old.val, new.val));
>  	read_unlock(&kvm->arch.sca_lock);
>  	wake_up(&kvm->arch.ipte_wq);
>  out:
> @@ -172,8 +172,8 @@ static void ipte_lock_siif(struct kvm *kvm)
>  retry:
>  	read_lock(&kvm->arch.sca_lock);
>  	ic = kvm_s390_get_ipte_control(kvm);
> +	old = READ_ONCE(*ic);
>  	do {
> -		old = READ_ONCE(*ic);
>  		if (old.kg) {
>  			read_unlock(&kvm->arch.sca_lock);
>  			cond_resched();
> @@ -182,7 +182,7 @@ static void ipte_lock_siif(struct kvm *kvm)
>  		new = old;
>  		new.k = 1;
>  		new.kh++;
> -	} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
> +	} while (!try_cmpxchg(&ic->val, &old.val, new.val));
>  	read_unlock(&kvm->arch.sca_lock);
>  }
>  
> @@ -192,13 +192,13 @@ static void ipte_unlock_siif(struct kvm *kvm)
>  
>  	read_lock(&kvm->arch.sca_lock);
>  	ic = kvm_s390_get_ipte_control(kvm);
> +	old = READ_ONCE(*ic);
>  	do {
> -		old = READ_ONCE(*ic);
>  		new = old;
>  		new.kh--;
>  		if (!new.kh)
>  			new.k = 0;
> -	} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
> +	} while (!try_cmpxchg(&ic->val, &old.val, new.val));
>  	read_unlock(&kvm->arch.sca_lock);
>  	if (!new.kh)
>  		wake_up(&kvm->arch.ipte_wq);
> diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
> index 4f0e7f61edf7..eff69018cbeb 100644
> --- a/arch/s390/kvm/interrupt.c
> +++ b/arch/s390/kvm/interrupt.c
> @@ -247,12 +247,12 @@ static inline int gisa_set_iam(struct kvm_s390_gisa *gisa, u8 iam)
>  {
>  	u64 word, _word;
>  
> +	word = READ_ONCE(gisa->u64.word[0]);
>  	do {
> -		word = READ_ONCE(gisa->u64.word[0]);
>  		if ((u64)gisa != word >> 32)
>  			return -EBUSY;
>  		_word = (word & ~0xffUL) | iam;
> -	} while (cmpxchg(&gisa->u64.word[0], word, _word) != word);
> +	} while (!try_cmpxchg(&gisa->u64.word[0], &word, _word));
>  
>  	return 0;
>  }
> @@ -270,10 +270,10 @@ static inline void gisa_clear_ipm(struct kvm_s390_gisa *gisa)
>  {
>  	u64 word, _word;
>  
> +	word = READ_ONCE(gisa->u64.word[0]);
>  	do {
> -		word = READ_ONCE(gisa->u64.word[0]);
>  		_word = word & ~(0xffUL << 24);
> -	} while (cmpxchg(&gisa->u64.word[0], word, _word) != word);
> +	} while (!try_cmpxchg(&gisa->u64.word[0], &word, _word));
>  }
>  
>  /**
> @@ -291,14 +291,14 @@ static inline u8 gisa_get_ipm_or_restore_iam(struct kvm_s390_gisa_interrupt *gi)
>  	u8 pending_mask, alert_mask;
>  	u64 word, _word;
>  
> +	word = READ_ONCE(gi->origin->u64.word[0]);
>  	do {
> -		word = READ_ONCE(gi->origin->u64.word[0]);
>  		alert_mask = READ_ONCE(gi->alert.mask);
>  		pending_mask = (u8)(word >> 24) & alert_mask;
>  		if (pending_mask)
>  			return pending_mask;
>  		_word = (word & ~0xffUL) | alert_mask;
> -	} while (cmpxchg(&gi->origin->u64.word[0], word, _word) != word);
> +	} while (!try_cmpxchg(&gi->origin->u64.word[0], &word, _word));
>  
>  	return 0;
>  }
> diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
> index 442d4a227c0e..d8080c27d45b 100644
> --- a/arch/s390/kvm/kvm-s390.c
> +++ b/arch/s390/kvm/kvm-s390.c
> @@ -1937,11 +1937,11 @@ static void kvm_s390_update_topology_change_report(struct kvm *kvm, bool val)
>  
>  	read_lock(&kvm->arch.sca_lock);
>  	sca = kvm->arch.sca;
> +	old = READ_ONCE(sca->utility);
>  	do {
> -		old = READ_ONCE(sca->utility);
>  		new = old;
>  		new.mtcr = val;
> -	} while (cmpxchg(&sca->utility.val, old.val, new.val) != old.val);
> +	} while (!try_cmpxchg(&sca->utility.val, &old.val, new.val));
>  	read_unlock(&kvm->arch.sca_lock);
>  }
>  
> diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c
> index a61518b549f0..9b9e7fdd5380 100644
> --- a/arch/s390/kvm/pci.c
> +++ b/arch/s390/kvm/pci.c
> @@ -208,13 +208,12 @@ static inline int account_mem(unsigned long nr_pages)
>  
>  	page_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
>  
> +	cur_pages = atomic_long_read(&user->locked_vm);
>  	do {
> -		cur_pages = atomic_long_read(&user->locked_vm);
>  		new_pages = cur_pages + nr_pages;
>  		if (new_pages > page_limit)
>  			return -ENOMEM;
> -	} while (atomic_long_cmpxchg(&user->locked_vm, cur_pages,
> -					new_pages) != cur_pages);
> +	} while (!atomic_long_try_cmpxchg(&user->locked_vm, &cur_pages, new_pages));
>  
>  	atomic64_add(nr_pages, &current->mm->pinned_vm);
>

Patchew 2.1-devel-b67e4c2

© 2016 - 2026 Red Hat, Inc.