Re: [PATCH v8 6/6] LoongArch: Add pv ipi support on guest kernel side

2024-05-06 Thread Huacai Chen 
On Mon, May 6, 2024 at 3:00 PM maobibo  wrote:
>
>
>
> On 2024/5/6 上午9:53, Huacai Chen wrote:
> > Hi, Bibo,
> >
> > On Sun, Apr 28, 2024 at 6:05 PM Bibo Mao  wrote:
> >>
> >> PARAVIRT option and pv ipi is added on guest kernel side, function
> >> pv_ipi_init() is to add ipi sending and ipi receiving hooks. This function
> >> firstly checks whether system runs on VM mode. If kernel runs on VM mode,
> >> it will call function kvm_para_available() to detect current hypervirsor
> >> type. Now only KVM type detection is supported, the paravirt function can
> >> work only if current hypervisor type is KVM, since there is only KVM
> >> supported on LoongArch now.
> >>
> >> PV IPI uses virtual IPI sender and virtual IPI receiver function. With
> >> virutal IPI sender, ipi message is stored in DDR memory rather than
> >> emulated HW. IPI multicast is supported, and 128 vcpus can received IPIs
> >> at the same time like X86 KVM method. Hypercall method is used for IPI
> >> sending.
> >>
> >> With virtual IPI receiver, HW SW0 is used rather than real IPI HW. Since
> >> VCPU has separate HW SW0 like HW timer, there is no trap in IPI interrupt
> >> acknowledge. And IPI message is stored in DDR, no trap in get IPI message.
> >>
> >> Signed-off-by: Bibo Mao 
> >> ---
> >>   arch/loongarch/Kconfig|   9 ++
> >>   arch/loongarch/include/asm/hardirq.h  |   1 +
> >>   arch/loongarch/include/asm/paravirt.h |  27 
> >>   .../include/asm/paravirt_api_clock.h  |   1 +
> >>   arch/loongarch/kernel/Makefile|   1 +
> >>   arch/loongarch/kernel/irq.c   |   2 +-
> >>   arch/loongarch/kernel/paravirt.c  | 151 ++
> >>   arch/loongarch/kernel/smp.c   |   4 +-
> >>   8 files changed, 194 insertions(+), 2 deletions(-)
> >>   create mode 100644 arch/loongarch/include/asm/paravirt.h
> >>   create mode 100644 arch/loongarch/include/asm/paravirt_api_clock.h
> >>   create mode 100644 arch/loongarch/kernel/paravirt.c
> >>
> >> diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
> >> index 54ad04dacdee..0a1540a8853e 100644
> >> --- a/arch/loongarch/Kconfig
> >> +++ b/arch/loongarch/Kconfig
> >> @@ -583,6 +583,15 @@ config CPU_HAS_PREFETCH
> >>  bool
> >>  default y
> >>
> >> +config PARAVIRT
> >> +   bool "Enable paravirtualization code"
> >> +   depends on AS_HAS_LVZ_EXTENSION
> >> +   help
> >> +  This changes the kernel so it can modify itself when it is run
> >> + under a hypervisor, potentially improving performance 
> >> significantly
> >> + over full virtualization.  However, when run without a hypervisor
> >> + the kernel is theoretically slower and slightly larger.
> >> +
> >>   config ARCH_SUPPORTS_KEXEC
> >>  def_bool y
> >>
> >> diff --git a/arch/loongarch/include/asm/hardirq.h 
> >> b/arch/loongarch/include/asm/hardirq.h
> >> index 9f0038e19c7f..b26d596a73aa 100644
> >> --- a/arch/loongarch/include/asm/hardirq.h
> >> +++ b/arch/loongarch/include/asm/hardirq.h
> >> @@ -21,6 +21,7 @@ enum ipi_msg_type {
> >>   typedef struct {
> >>  unsigned int ipi_irqs[NR_IPI];
> >>  unsigned int __softirq_pending;
> >> +   atomic_t message cacheline_aligned_in_smp;
> >>   } cacheline_aligned irq_cpustat_t;
> >>
> >>   DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
> >> diff --git a/arch/loongarch/include/asm/paravirt.h 
> >> b/arch/loongarch/include/asm/paravirt.h
> >> new file mode 100644
> >> index ..58f7b7b89f2c
> >> --- /dev/null
> >> +++ b/arch/loongarch/include/asm/paravirt.h
> >> @@ -0,0 +1,27 @@
> >> +/* SPDX-License-Identifier: GPL-2.0 */
> >> +#ifndef _ASM_LOONGARCH_PARAVIRT_H
> >> +#define _ASM_LOONGARCH_PARAVIRT_H
> >> +
> >> +#ifdef CONFIG_PARAVIRT
> >> +#include 
> >> +struct static_key;
> >> +extern struct static_key paravirt_steal_enabled;
> >> +extern struct static_key paravirt_steal_rq_enabled;
> >> +
> >> +u64 dummy_steal_clock(int cpu);
> >> +DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock);
> >> +
> >> +static inline u64 paravirt_steal_clock(int cpu)
> >> +{
> >> +   return static_call(pv_steal_clock)(cpu);
> >> +}
> >> +
> >> +int pv_ipi_init(void);
> >> +#else
> >> +static inline int pv_ipi_init(void)
> >> +{
> >> +   return 0;
> >> +}
> >> +
> >> +#endif // CONFIG_PARAVIRT
> >> +#endif
> >> diff --git a/arch/loongarch/include/asm/paravirt_api_clock.h 
> >> b/arch/loongarch/include/asm/paravirt_api_clock.h
> >> new file mode 100644
> >> index ..65ac7cee0dad
> >> --- /dev/null
> >> +++ b/arch/loongarch/include/asm/paravirt_api_clock.h
> >> @@ -0,0 +1 @@
> >> +#include 
> >> diff --git a/arch/loongarch/kernel/Makefile 
> >> b/arch/loongarch/kernel/Makefile
> >> index 3a7620b66bc6..c9bfeda89e40 100644
> >> --- a/arch/loongarch/kernel/Makefile
> >> +++ b/arch/loongarch/kernel/Makefile
> >> @@ -51,6 +51,7 @@ obj-$(CONFIG_MODULES) += module.o 
> >>

Re: [PATCH v8 6/6] LoongArch: Add pv ipi support on guest kernel side

2024-05-06 Thread maobibo 




On 2024/5/6 上午9:53, Huacai Chen wrote:

Hi, Bibo,

On Sun, Apr 28, 2024 at 6:05 PM Bibo Mao  wrote:


PARAVIRT option and pv ipi is added on guest kernel side, function
pv_ipi_init() is to add ipi sending and ipi receiving hooks. This function
firstly checks whether system runs on VM mode. If kernel runs on VM mode,
it will call function kvm_para_available() to detect current hypervirsor
type. Now only KVM type detection is supported, the paravirt function can
work only if current hypervisor type is KVM, since there is only KVM
supported on LoongArch now.

PV IPI uses virtual IPI sender and virtual IPI receiver function. With
virutal IPI sender, ipi message is stored in DDR memory rather than
emulated HW. IPI multicast is supported, and 128 vcpus can received IPIs
at the same time like X86 KVM method. Hypercall method is used for IPI
sending.

With virtual IPI receiver, HW SW0 is used rather than real IPI HW. Since
VCPU has separate HW SW0 like HW timer, there is no trap in IPI interrupt
acknowledge. And IPI message is stored in DDR, no trap in get IPI message.

Signed-off-by: Bibo Mao 
---
  arch/loongarch/Kconfig|   9 ++
  arch/loongarch/include/asm/hardirq.h  |   1 +
  arch/loongarch/include/asm/paravirt.h |  27 
  .../include/asm/paravirt_api_clock.h  |   1 +
  arch/loongarch/kernel/Makefile|   1 +
  arch/loongarch/kernel/irq.c   |   2 +-
  arch/loongarch/kernel/paravirt.c  | 151 ++
  arch/loongarch/kernel/smp.c   |   4 +-
  8 files changed, 194 insertions(+), 2 deletions(-)
  create mode 100644 arch/loongarch/include/asm/paravirt.h
  create mode 100644 arch/loongarch/include/asm/paravirt_api_clock.h
  create mode 100644 arch/loongarch/kernel/paravirt.c

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 54ad04dacdee..0a1540a8853e 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -583,6 +583,15 @@ config CPU_HAS_PREFETCH
 bool
 default y

+config PARAVIRT
+   bool "Enable paravirtualization code"
+   depends on AS_HAS_LVZ_EXTENSION
+   help
+  This changes the kernel so it can modify itself when it is run
+ under a hypervisor, potentially improving performance significantly
+ over full virtualization.  However, when run without a hypervisor
+ the kernel is theoretically slower and slightly larger.
+
  config ARCH_SUPPORTS_KEXEC
 def_bool y

diff --git a/arch/loongarch/include/asm/hardirq.h 
b/arch/loongarch/include/asm/hardirq.h
index 9f0038e19c7f..b26d596a73aa 100644
--- a/arch/loongarch/include/asm/hardirq.h
+++ b/arch/loongarch/include/asm/hardirq.h
@@ -21,6 +21,7 @@ enum ipi_msg_type {
  typedef struct {
 unsigned int ipi_irqs[NR_IPI];
 unsigned int __softirq_pending;
+   atomic_t message cacheline_aligned_in_smp;
  } cacheline_aligned irq_cpustat_t;

  DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
diff --git a/arch/loongarch/include/asm/paravirt.h 
b/arch/loongarch/include/asm/paravirt.h
new file mode 100644
index ..58f7b7b89f2c
--- /dev/null
+++ b/arch/loongarch/include/asm/paravirt.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_LOONGARCH_PARAVIRT_H
+#define _ASM_LOONGARCH_PARAVIRT_H
+
+#ifdef CONFIG_PARAVIRT
+#include 
+struct static_key;
+extern struct static_key paravirt_steal_enabled;
+extern struct static_key paravirt_steal_rq_enabled;
+
+u64 dummy_steal_clock(int cpu);
+DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock);
+
+static inline u64 paravirt_steal_clock(int cpu)
+{
+   return static_call(pv_steal_clock)(cpu);
+}
+
+int pv_ipi_init(void);
+#else
+static inline int pv_ipi_init(void)
+{
+   return 0;
+}
+
+#endif // CONFIG_PARAVIRT
+#endif
diff --git a/arch/loongarch/include/asm/paravirt_api_clock.h 
b/arch/loongarch/include/asm/paravirt_api_clock.h
new file mode 100644
index ..65ac7cee0dad
--- /dev/null
+++ b/arch/loongarch/include/asm/paravirt_api_clock.h
@@ -0,0 +1 @@
+#include 
diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile
index 3a7620b66bc6..c9bfeda89e40 100644
--- a/arch/loongarch/kernel/Makefile
+++ b/arch/loongarch/kernel/Makefile
@@ -51,6 +51,7 @@ obj-$(CONFIG_MODULES) += module.o module-sections.o
  obj-$(CONFIG_STACKTRACE)   += stacktrace.o

  obj-$(CONFIG_PROC_FS)  += proc.o
+obj-$(CONFIG_PARAVIRT) += paravirt.o

  obj-$(CONFIG_SMP)  += smp.o

diff --git a/arch/loongarch/kernel/irq.c b/arch/loongarch/kernel/irq.c
index ce36897d1e5a..4863e6c1b739 100644
--- a/arch/loongarch/kernel/irq.c
+++ b/arch/loongarch/kernel/irq.c
@@ -113,5 +113,5 @@ void __init init_IRQ(void)
 per_cpu(irq_stack, i), per_cpu(irq_stack, i) + 
IRQ_STACK_SIZE);
 }

-   set_csr_ecfg(ECFGF_IP0 | ECFGF_IP1 | ECFGF_IP2 | ECFGF_IPI | ECFGF_PMC);
+

Re: [PATCH v8 6/6] LoongArch: Add pv ipi support on guest kernel side

2024-05-05 Thread Huacai Chen 
Hi, Bibo,

On Sun, Apr 28, 2024 at 6:05 PM Bibo Mao  wrote:
>
> PARAVIRT option and pv ipi is added on guest kernel side, function
> pv_ipi_init() is to add ipi sending and ipi receiving hooks. This function
> firstly checks whether system runs on VM mode. If kernel runs on VM mode,
> it will call function kvm_para_available() to detect current hypervirsor
> type. Now only KVM type detection is supported, the paravirt function can
> work only if current hypervisor type is KVM, since there is only KVM
> supported on LoongArch now.
>
> PV IPI uses virtual IPI sender and virtual IPI receiver function. With
> virutal IPI sender, ipi message is stored in DDR memory rather than
> emulated HW. IPI multicast is supported, and 128 vcpus can received IPIs
> at the same time like X86 KVM method. Hypercall method is used for IPI
> sending.
>
> With virtual IPI receiver, HW SW0 is used rather than real IPI HW. Since
> VCPU has separate HW SW0 like HW timer, there is no trap in IPI interrupt
> acknowledge. And IPI message is stored in DDR, no trap in get IPI message.
>
> Signed-off-by: Bibo Mao 
> ---
>  arch/loongarch/Kconfig|   9 ++
>  arch/loongarch/include/asm/hardirq.h  |   1 +
>  arch/loongarch/include/asm/paravirt.h |  27 
>  .../include/asm/paravirt_api_clock.h  |   1 +
>  arch/loongarch/kernel/Makefile|   1 +
>  arch/loongarch/kernel/irq.c   |   2 +-
>  arch/loongarch/kernel/paravirt.c  | 151 ++
>  arch/loongarch/kernel/smp.c   |   4 +-
>  8 files changed, 194 insertions(+), 2 deletions(-)
>  create mode 100644 arch/loongarch/include/asm/paravirt.h
>  create mode 100644 arch/loongarch/include/asm/paravirt_api_clock.h
>  create mode 100644 arch/loongarch/kernel/paravirt.c
>
> diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
> index 54ad04dacdee..0a1540a8853e 100644
> --- a/arch/loongarch/Kconfig
> +++ b/arch/loongarch/Kconfig
> @@ -583,6 +583,15 @@ config CPU_HAS_PREFETCH
> bool
> default y
>
> +config PARAVIRT
> +   bool "Enable paravirtualization code"
> +   depends on AS_HAS_LVZ_EXTENSION
> +   help
> +  This changes the kernel so it can modify itself when it is run
> + under a hypervisor, potentially improving performance significantly
> + over full virtualization.  However, when run without a hypervisor
> + the kernel is theoretically slower and slightly larger.
> +
>  config ARCH_SUPPORTS_KEXEC
> def_bool y
>
> diff --git a/arch/loongarch/include/asm/hardirq.h 
> b/arch/loongarch/include/asm/hardirq.h
> index 9f0038e19c7f..b26d596a73aa 100644
> --- a/arch/loongarch/include/asm/hardirq.h
> +++ b/arch/loongarch/include/asm/hardirq.h
> @@ -21,6 +21,7 @@ enum ipi_msg_type {
>  typedef struct {
> unsigned int ipi_irqs[NR_IPI];
> unsigned int __softirq_pending;
> +   atomic_t message cacheline_aligned_in_smp;
>  } cacheline_aligned irq_cpustat_t;
>
>  DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
> diff --git a/arch/loongarch/include/asm/paravirt.h 
> b/arch/loongarch/include/asm/paravirt.h
> new file mode 100644
> index ..58f7b7b89f2c
> --- /dev/null
> +++ b/arch/loongarch/include/asm/paravirt.h
> @@ -0,0 +1,27 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +#ifndef _ASM_LOONGARCH_PARAVIRT_H
> +#define _ASM_LOONGARCH_PARAVIRT_H
> +
> +#ifdef CONFIG_PARAVIRT
> +#include 
> +struct static_key;
> +extern struct static_key paravirt_steal_enabled;
> +extern struct static_key paravirt_steal_rq_enabled;
> +
> +u64 dummy_steal_clock(int cpu);
> +DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock);
> +
> +static inline u64 paravirt_steal_clock(int cpu)
> +{
> +   return static_call(pv_steal_clock)(cpu);
> +}
> +
> +int pv_ipi_init(void);
> +#else
> +static inline int pv_ipi_init(void)
> +{
> +   return 0;
> +}
> +
> +#endif // CONFIG_PARAVIRT
> +#endif
> diff --git a/arch/loongarch/include/asm/paravirt_api_clock.h 
> b/arch/loongarch/include/asm/paravirt_api_clock.h
> new file mode 100644
> index ..65ac7cee0dad
> --- /dev/null
> +++ b/arch/loongarch/include/asm/paravirt_api_clock.h
> @@ -0,0 +1 @@
> +#include 
> diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile
> index 3a7620b66bc6..c9bfeda89e40 100644
> --- a/arch/loongarch/kernel/Makefile
> +++ b/arch/loongarch/kernel/Makefile
> @@ -51,6 +51,7 @@ obj-$(CONFIG_MODULES) += module.o module-sections.o
>  obj-$(CONFIG_STACKTRACE)   += stacktrace.o
>
>  obj-$(CONFIG_PROC_FS)  += proc.o
> +obj-$(CONFIG_PARAVIRT) += paravirt.o
>
>  obj-$(CONFIG_SMP)  += smp.o
>
> diff --git a/arch/loongarch/kernel/irq.c b/arch/loongarch/kernel/irq.c
> index ce36897d1e5a..4863e6c1b739 100644
> --- a/arch/loongarch/kernel/irq.c
> +++ b/arch/loongarch/kernel/irq.c
> @@ -113,5 +113,5 @@ void __init init_IRQ(void)
>

[PATCH v8 6/6] LoongArch: Add pv ipi support on guest kernel side

2024-04-28 Thread Bibo Mao 
PARAVIRT option and pv ipi is added on guest kernel side, function
pv_ipi_init() is to add ipi sending and ipi receiving hooks. This function
firstly checks whether system runs on VM mode. If kernel runs on VM mode,
it will call function kvm_para_available() to detect current hypervirsor
type. Now only KVM type detection is supported, the paravirt function can
work only if current hypervisor type is KVM, since there is only KVM
supported on LoongArch now.

PV IPI uses virtual IPI sender and virtual IPI receiver function. With
virutal IPI sender, ipi message is stored in DDR memory rather than
emulated HW. IPI multicast is supported, and 128 vcpus can received IPIs
at the same time like X86 KVM method. Hypercall method is used for IPI
sending.

With virtual IPI receiver, HW SW0 is used rather than real IPI HW. Since
VCPU has separate HW SW0 like HW timer, there is no trap in IPI interrupt
acknowledge. And IPI message is stored in DDR, no trap in get IPI message.

Signed-off-by: Bibo Mao 
---
 arch/loongarch/Kconfig|   9 ++
 arch/loongarch/include/asm/hardirq.h  |   1 +
 arch/loongarch/include/asm/paravirt.h |  27 
 .../include/asm/paravirt_api_clock.h  |   1 +
 arch/loongarch/kernel/Makefile|   1 +
 arch/loongarch/kernel/irq.c   |   2 +-
 arch/loongarch/kernel/paravirt.c  | 151 ++
 arch/loongarch/kernel/smp.c   |   4 +-
 8 files changed, 194 insertions(+), 2 deletions(-)
 create mode 100644 arch/loongarch/include/asm/paravirt.h
 create mode 100644 arch/loongarch/include/asm/paravirt_api_clock.h
 create mode 100644 arch/loongarch/kernel/paravirt.c

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 54ad04dacdee..0a1540a8853e 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -583,6 +583,15 @@ config CPU_HAS_PREFETCH
bool
default y
 
+config PARAVIRT
+   bool "Enable paravirtualization code"
+   depends on AS_HAS_LVZ_EXTENSION
+   help
+  This changes the kernel so it can modify itself when it is run
+ under a hypervisor, potentially improving performance significantly
+ over full virtualization.  However, when run without a hypervisor
+ the kernel is theoretically slower and slightly larger.
+
 config ARCH_SUPPORTS_KEXEC
def_bool y
 
diff --git a/arch/loongarch/include/asm/hardirq.h 
b/arch/loongarch/include/asm/hardirq.h
index 9f0038e19c7f..b26d596a73aa 100644
--- a/arch/loongarch/include/asm/hardirq.h
+++ b/arch/loongarch/include/asm/hardirq.h
@@ -21,6 +21,7 @@ enum ipi_msg_type {
 typedef struct {
unsigned int ipi_irqs[NR_IPI];
unsigned int __softirq_pending;
+   atomic_t message cacheline_aligned_in_smp;
 } cacheline_aligned irq_cpustat_t;
 
 DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
diff --git a/arch/loongarch/include/asm/paravirt.h 
b/arch/loongarch/include/asm/paravirt.h
new file mode 100644
index ..58f7b7b89f2c
--- /dev/null
+++ b/arch/loongarch/include/asm/paravirt.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_LOONGARCH_PARAVIRT_H
+#define _ASM_LOONGARCH_PARAVIRT_H
+
+#ifdef CONFIG_PARAVIRT
+#include 
+struct static_key;
+extern struct static_key paravirt_steal_enabled;
+extern struct static_key paravirt_steal_rq_enabled;
+
+u64 dummy_steal_clock(int cpu);
+DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock);
+
+static inline u64 paravirt_steal_clock(int cpu)
+{
+   return static_call(pv_steal_clock)(cpu);
+}
+
+int pv_ipi_init(void);
+#else
+static inline int pv_ipi_init(void)
+{
+   return 0;
+}
+
+#endif // CONFIG_PARAVIRT
+#endif
diff --git a/arch/loongarch/include/asm/paravirt_api_clock.h 
b/arch/loongarch/include/asm/paravirt_api_clock.h
new file mode 100644
index ..65ac7cee0dad
--- /dev/null
+++ b/arch/loongarch/include/asm/paravirt_api_clock.h
@@ -0,0 +1 @@
+#include 
diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile
index 3a7620b66bc6..c9bfeda89e40 100644
--- a/arch/loongarch/kernel/Makefile
+++ b/arch/loongarch/kernel/Makefile
@@ -51,6 +51,7 @@ obj-$(CONFIG_MODULES) += module.o module-sections.o
 obj-$(CONFIG_STACKTRACE)   += stacktrace.o
 
 obj-$(CONFIG_PROC_FS)  += proc.o
+obj-$(CONFIG_PARAVIRT) += paravirt.o
 
 obj-$(CONFIG_SMP)  += smp.o
 
diff --git a/arch/loongarch/kernel/irq.c b/arch/loongarch/kernel/irq.c
index ce36897d1e5a..4863e6c1b739 100644
--- a/arch/loongarch/kernel/irq.c
+++ b/arch/loongarch/kernel/irq.c
@@ -113,5 +113,5 @@ void __init init_IRQ(void)
per_cpu(irq_stack, i), per_cpu(irq_stack, i) + 
IRQ_STACK_SIZE);
}
 
-   set_csr_ecfg(ECFGF_IP0 | ECFGF_IP1 | ECFGF_IP2 | ECFGF_IPI | ECFGF_PMC);
+   set_csr_ecfg(ECFGF_SIP0 | ECFGF_IP0 | ECFGF_IP1 | ECFGF_IP2 | ECFGF_IPI 
| ECFGF_PMC);
 }
diff --git a/arch/loongarch/kernel/paravirt.c