diff mbox series

[V12,07/14] riscv: qspinlock: Add virt_spin_lock() support for VM guest

Message ID 20231225125847.2778638-8-guoren@kernel.org (mailing list archive)
State New, archived
Headers show
Series riscv: Add Native/Paravirt qspinlock support | expand

Commit Message

Guo Ren Dec. 25, 2023, 12:58 p.m. UTC
From: Guo Ren <guoren@linux.alibaba.com>

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 VM guests should 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@linux.alibaba.com>
Signed-off-by: Guo Ren <guoren@kernel.org>
---
 .../admin-guide/kernel-parameters.txt         |  4 +++
 arch/riscv/include/asm/spinlock.h             | 22 ++++++++++++++++
 arch/riscv/kernel/setup.c                     | 26 +++++++++++++++++++
 3 files changed, 52 insertions(+)

Comments

Leonardo Bras Jan. 4, 2024, 5:06 a.m. UTC | #1
On Mon, Dec 25, 2023 at 07:58:40AM -0500, guoren@kernel.org wrote:
> From: Guo Ren <guoren@linux.alibaba.com>
> 
> 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 VM guests should 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@linux.alibaba.com>
> Signed-off-by: Guo Ren <guoren@kernel.org>
> ---
>  .../admin-guide/kernel-parameters.txt         |  4 +++
>  arch/riscv/include/asm/spinlock.h             | 22 ++++++++++++++++
>  arch/riscv/kernel/setup.c                     | 26 +++++++++++++++++++
>  3 files changed, 52 insertions(+)
> 
> diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
> index 2ac9f1511774..b7794c96d91e 100644
> --- a/Documentation/admin-guide/kernel-parameters.txt
> +++ b/Documentation/admin-guide/kernel-parameters.txt
> @@ -3997,6 +3997,10 @@
>  	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 VM 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/spinlock.h b/arch/riscv/include/asm/spinlock.h
> index d07643c07aae..7bbcf3d9fff0 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/setup.c b/arch/riscv/kernel/setup.c
> index d9072a59831c..0bafb9fd6ea3 100644
> --- a/arch/riscv/kernel/setup.c
> +++ b/arch/riscv/kernel/setup.c
> @@ -27,6 +27,7 @@
>  #include <asm/cacheflush.h>
>  #include <asm/cpufeature.h>
>  #include <asm/cpu_ops.h>
> +#include <asm/cpufeature.h>
>  #include <asm/early_ioremap.h>
>  #include <asm/pgtable.h>
>  #include <asm/setup.h>
> @@ -266,6 +267,27 @@ early_param("qspinlock", queued_spinlock_setup);
>  DEFINE_STATIC_KEY_TRUE(combo_qspinlock_key);
>  EXPORT_SYMBOL(combo_qspinlock_key);
>  
> +#ifdef CONFIG_QUEUED_SPINLOCKS
> +static bool no_virt_spin __ro_after_init;
> +static int __init no_virt_spin_setup(char *p)
> +{
> +	no_virt_spin = true;
> +
> +	return 0;
> +}
> +early_param("no_virt_spin", no_virt_spin_setup);
> +
> +DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key);
> +
> +static void __init virt_spin_lock_init(void)
> +{
> +	if (no_virt_spin)
> +		static_branch_disable(&virt_spin_lock_key);
> +	else
> +		pr_info("Enable virt_spin_lock\n");
> +}
> +#endif
> +
>  static void __init riscv_spinlock_init(void)
>  {
>  	if (!enable_qspinlock) {
> @@ -274,6 +296,10 @@ static void __init riscv_spinlock_init(void)
>  	} else {
>  		pr_info("Queued spinlock: enabled\n");
>  	}
> +
> +#ifdef CONFIG_QUEUED_SPINLOCKS
> +	virt_spin_lock_init();
> +#endif
>  }
>  #endif
>  
> -- 
> 2.40.1
> 

LGTM:
Reviewed-by: Leonardo Bras <leobras@redhat.com>
diff mbox series

Patch

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 2ac9f1511774..b7794c96d91e 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3997,6 +3997,10 @@ 
 	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 VM 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/spinlock.h b/arch/riscv/include/asm/spinlock.h
index d07643c07aae..7bbcf3d9fff0 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/setup.c b/arch/riscv/kernel/setup.c
index d9072a59831c..0bafb9fd6ea3 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -27,6 +27,7 @@ 
 #include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
+#include <asm/cpufeature.h>
 #include <asm/early_ioremap.h>
 #include <asm/pgtable.h>
 #include <asm/setup.h>
@@ -266,6 +267,27 @@  early_param("qspinlock", queued_spinlock_setup);
 DEFINE_STATIC_KEY_TRUE(combo_qspinlock_key);
 EXPORT_SYMBOL(combo_qspinlock_key);
 
+#ifdef CONFIG_QUEUED_SPINLOCKS
+static bool no_virt_spin __ro_after_init;
+static int __init no_virt_spin_setup(char *p)
+{
+	no_virt_spin = true;
+
+	return 0;
+}
+early_param("no_virt_spin", no_virt_spin_setup);
+
+DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key);
+
+static void __init virt_spin_lock_init(void)
+{
+	if (no_virt_spin)
+		static_branch_disable(&virt_spin_lock_key);
+	else
+		pr_info("Enable virt_spin_lock\n");
+}
+#endif
+
 static void __init riscv_spinlock_init(void)
 {
 	if (!enable_qspinlock) {
@@ -274,6 +296,10 @@  static void __init riscv_spinlock_init(void)
 	} else {
 		pr_info("Queued spinlock: enabled\n");
 	}
+
+#ifdef CONFIG_QUEUED_SPINLOCKS
+	virt_spin_lock_init();
+#endif
 }
 #endif