function memory_present(). That means only E820_ram space
has mem_map space allocated.
so system crashed in function set_highmem_pages_init(),
if pfn points to E820_reserve space, pfn_to_page(pfn) will
point to unallocated page area.
thanks
bibo,mao
Here is crashing log
I tried 2.6.21 version, it also crashed similarly.
thanks
bibo,mao
Andrew Morton wrote:
On Fri, 31 Aug 2007 09:49:53 +0800 "bibo,mao" <[EMAIL PROTECTED]> wrote:
> Hi,
Let's cc linux-mm.
>I have one machine with 4G memory and 1G pci memory hole
> betwee
his. Any comments
is welcome.
Signed-off-by: bibo, mao <[EMAIL PROTECTED]>
thanks
bibo,mao
arch/ia64/kernel/ptrace.c | 12 ++--
include/asm-ia64/thread_info.h |4 +++-
2 files changed, 9 insertions(+), 7 deletions(-)
hat is different from x86_64 linux convention.
How about adding EFIAPI prefix before efi runtime service function, this
prefix has different definition in different architecture.
thanks
bibo,mao
--- 2.6.20-rc6/include/linux/efi.h.bak 2007-02-01 10:49:13.0 +0800
+++ 2.6.20-rc6/include/l
Frederic Riss wrote:
2007/2/1, bibo,mao <[EMAIL PROTECTED]>:
currently x86_64 kernel does not support efi, efi convention comply to
MS convention. On ia32 parameter is passed on stack, on x86_64 parameter
is passed by registers but that is different from x86_64 linux
convention.
Is an
hi yinghai,
early_ioremap is useful for early firmware access such as efi
memory map table which does not reside at low memory address. efi patch
patch will use this function, initial efi patch has posted.
thanks
bibo,mao
Yinghai Lu wrote:
[PATCH] x86_64: change early_ioremap to static
only
On LoongArch system, hypercall instruction is supported when system
runs on VM mode. This patch adds dummy function with hypercall
instruction emulation, rather than inject EXCCODE_INE invalid
instruction exception.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/Kbuild | 1 -
arch
) 42.4 56665.3 13364.4
Shell Scripts (8 concurrent) 6.0 7412.1 12353.4
System Call Overhead 15000.06962239.6 4641.5
System Benchmarks Index Score7205.8
Bibo Mao (5):
LoongArch: KVM: Add hypercall
-off-by: Bibo Mao
---
arch/loongarch/Kconfig| 8
arch/loongarch/include/asm/kvm_para.h | 7
arch/loongarch/include/asm/paravirt.h | 27
.../include/asm/paravirt_api_clock.h | 1 +
arch/loongarch/kernel/Makefile
System will trap into hypervisor when executing cpucfg instruction.
And now hardware only uses the area 0 - 20 for actual usage, here
one specified area 0x1000 -- 0x10ff is used for KVM hypervisor,
and the area can be extended for other hypervisors in future.
Signed-off-by: Bibo Mao
: Bibo Mao
---
arch/loongarch/include/asm/hardirq.h | 1 +
arch/loongarch/include/asm/kvm_para.h | 124 +
arch/loongarch/include/asm/loongarch.h | 1 +
arch/loongarch/kernel/irq.c| 2 +-
arch/loongarch/kernel/paravirt.c | 103
pv ipi can be used later.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/hardirq.h | 4 ++
arch/loongarch/include/asm/irq.h | 10 -
arch/loongarch/include/asm/smp.h | 31 +++
arch/loongarch/kernel/irq.c | 22 +--
arch/loongarch/kernel/perf_event.c
On LoongArch system, hypercall instruction is supported when system
runs on VM mode. This patch adds dummy function with hypercall
instruction emulation, rather than inject EXCCODE_INE invalid
instruction exception.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/Kbuild | 1 -
arch
System will trap into hypervisor when executing cpucfg instruction.
And now hardware only uses the area 0 - 20 for actual usage, here
one specified area 0x1000 -- 0x10ff is used for KVM hypervisor,
and the area can be extended for other hypervisors in future.
Signed-off-by: Bibo Mao
routing uses hw cpuid
2. Refine changelog description
3. Add hypercall statistic support for vcpu
4. Set percpu pv ipi message buffer aligned with cacheline
5. Refine pv ipi send logic, do not send ipi message with if there is
pending ipi message.
---
Bibo Mao (6):
LoongArch: KVM: Add
pv ipi can be used later.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/hardirq.h | 4 ++
arch/loongarch/include/asm/irq.h | 10 -
arch/loongarch/include/asm/smp.h | 31 +++
arch/loongarch/kernel/irq.c | 22 +--
arch/loongarch/kernel/perf_event.c
KVM hypervisor, and there is only KVM hypervisor
supported on LoongArch now.
Signed-off-by: Bibo Mao
---
arch/loongarch/Kconfig| 9
arch/loongarch/include/asm/kvm_para.h | 7
arch/loongarch/include/asm/paravirt.h | 27
.../include/asm
hypervisor greatly.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/hardirq.h | 1 +
arch/loongarch/include/asm/kvm_host.h | 1 +
arch/loongarch/include/asm/kvm_para.h | 124 +
arch/loongarch/include/asm/loongarch.h | 1 +
arch/loongarch/kernel/irq.c
smallest cpuid from extioi, and
the max cpuid size is defines as 256.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/kvm_host.h | 26
arch/loongarch/include/asm/kvm_vcpu.h | 1 +
arch/loongarch/kvm/vcpu.c | 61 ++-
arch/loongarch/kvm/vm.c
changelog description
3. Add hypercall statistic support for vcpu
4. Set percpu pv ipi message buffer aligned with cacheline
5. Refine pv ipi send logic, do not send ipi message with if there is
pending ipi message.
---
Bibo Mao (6):
LoongArch/smp: Refine ipi ops on LoongArch platform
System will trap into hypervisor when executing cpucfg instruction.
And now hardware only uses the area 0 - 20 for actual usage, here
one specified area 0x1000 -- 0x10ff is used for KVM hypervisor,
and the area can be extended for other hypervisors in future.
Signed-off-by: Bibo Mao
KVM hypervisor, since there is only KVM hypervisor
supported on LoongArch now.
Signed-off-by: Bibo Mao
---
arch/loongarch/Kconfig| 9
arch/loongarch/include/asm/kvm_para.h | 7
arch/loongarch/include/asm/paravirt.h | 27
.../include
hypervisor greatly.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/hardirq.h | 1 +
arch/loongarch/include/asm/kvm_host.h | 1 +
arch/loongarch/include/asm/kvm_para.h | 124 +
arch/loongarch/include/asm/loongarch.h | 1 +
arch/loongarch/kernel/irq.c
On LoongArch system, hypercall instruction is supported when system
runs on VM mode. This patch adds dummy function with hypercall
instruction emulation, rather than inject EXCCODE_INE invalid
instruction exception.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/Kbuild | 1 -
arch
smallest cpuid from extioi, and
the max cpuid size is defines as 256.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/kvm_host.h | 26
arch/loongarch/include/asm/kvm_vcpu.h | 1 +
arch/loongarch/kvm/vcpu.c | 93 ++-
arch/loongarch/kvm/vm.c
pv ipi can be used later.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/hardirq.h | 4 ++
arch/loongarch/include/asm/irq.h | 10 -
arch/loongarch/include/asm/smp.h | 31 +++
arch/loongarch/kernel/irq.c | 22 +--
arch/loongarch/kernel/perf_event.c
structure smp_ops on LoongArch platform so that pv ipi can be used
later.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/hardirq.h | 4 ++
arch/loongarch/include/asm/irq.h | 10 -
arch/loongarch/include/asm/smp.h | 31 +++
arch/loongarch/kernel/irq.c | 22
VM will trap into hypervisor when executing cpucfg instruction. And
hardware only uses the area 0 - 20 for actual usage now, here one
specified area 0x4000 -- 0x40ff is used for KVM hypervisor,
and the area can be extended to use for other hypervisors in future.
Signed-off-by: Bibo Mao
On LoongArch system, hypercall instruction is supported when system
runs on VM mode. This patch adds dummy function with hypercall
instruction emulation, rather than inject EXCCODE_INE invalid
instruction exception.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/Kbuild | 1 -
arch
pending ipi message.
---
Bibo Mao (6):
LoongArch/smp: Refine ipi ops on LoongArch platform
LoongArch: KVM: Add hypercall instruction emulation support
LoongArch: KVM: Add cpucfg area for kvm hypervisor
LoongArch: Add paravirt interface for guest kernel
LoongArch: KVM: Add vcpu search
is KVM hypervisor, since there is only KVM hypervisor
supported on LoongArch now.
This patch only adds paravirt interface for guest kernel, however there
is not effective pv functions added here.
Signed-off-by: Bibo Mao
---
arch/loongarch/Kconfig| 9
arch/loongarch
different size declaration about physical cpuid,
KVM uses the smallest cpuid from extioi irqchip, and the max cpuid size
is defines as 256.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/kvm_host.h | 26
arch/loongarch/include/asm/kvm_vcpu.h | 1 +
arch/loongarch/kvm/vcpu.c
trap times into hypervisor greatly.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/hardirq.h | 1 +
arch/loongarch/include/asm/kvm_host.h | 1 +
arch/loongarch/include/asm/kvm_para.h | 124 +
arch/loongarch/include/asm/loongarch.h | 1 +
arch/loongarch
encoding, the ipi hw will convert it into bitmap in ipi message
buffer.
3. Add structure smp_ops on LoongArch platform so that pv ipi can be used
later.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/hardirq.h | 4 ++
arch/loongarch/include/asm/irq.h | 10 -
arch/loongarch/include
cpu pv ipi message buffer aligned with cacheline
5. Refine pv ipi send logic, do not send ipi message with if there is
pending ipi message.
---
Bibo Mao (6):
LoongArch/smp: Refine some ipi functions on LoongArch platform
LoongArch: KVM: Add hypercall instruction emulation support
LoongArch
PV features, and the area can be extended
for other hypervisors in future. This area will never be used for
real HW, it is only used by software.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/inst.h | 1 +
arch/loongarch/include/asm/loongarch.h | 10 ++
arch/loongarch/kvm/exit.c
value
KVM_HCALL_INVALID_CODE, rather than inject EXCCODE_INE invalid
instruction exception. So VM can continue to executing the next code.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/Kbuild | 1 -
arch/loongarch/include/asm/kvm_para.h | 26 ++
arch
is KVM hypervisor, since there is only KVM hypervisor
supported on LoongArch now.
There is not effective with pv_ipi_init() now, it is dummy function.
Signed-off-by: Bibo Mao
---
arch/loongarch/Kconfig| 9
arch/loongarch/include/asm/kvm_para.h | 7
as 256 by KVM which comes from
extioi irqchip.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/kvm_host.h | 26
arch/loongarch/include/asm/kvm_vcpu.h | 1 +
arch/loongarch/kvm/vcpu.c | 93 ++-
arch/loongarch/kvm/vm.c | 11
4
into hypervisor greatly.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/hardirq.h | 1 +
arch/loongarch/include/asm/kvm_host.h | 1 +
arch/loongarch/include/asm/kvm_para.h | 123 +
arch/loongarch/include/asm/loongarch.h | 1 +
arch/loongarch/kernel/irq.c
value
KVM_HCALL_INVALID_CODE, rather than inject EXCCODE_INE invalid
instruction exception. So VM can continue to executing the next code.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/Kbuild | 1 -
arch/loongarch/include/asm/kvm_para.h | 26 ++
arch
PV features, and the area can be extended
for other hypervisors in future. This area will never be used for
real HW, it is only used by software.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/inst.h | 1 +
arch/loongarch/include/asm/loongarch.h | 10 +
arch/loongarch/kvm/exit.c
age buffer aligned with cacheline
5. Refine pv ipi send logic, do not send ipi message with if there is
pending ipi message.
---
Bibo Mao (7):
LoongArch/smp: Refine some ipi functions on LoongArch platform
LoongArch: KVM: Add hypercall instruction emulation support
LoongArch: KVM: Add cpucf
encoding, the ipi hw will convert it into bitmap in ipi message
buffer.
3. Add structure smp_ops on LoongArch platform so that pv ipi can be used
later.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/hardirq.h | 4 ++
arch/loongarch/include/asm/irq.h | 10 -
arch/loongarch/include
as 256 by KVM which comes from
extioi irqchip.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/kvm_host.h | 26
arch/loongarch/include/asm/kvm_vcpu.h | 1 +
arch/loongarch/kvm/vcpu.c | 93 ++-
arch/loongarch/kvm/vm.c | 11
4
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
into hypervisor greatly.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/kvm_host.h | 1 +
arch/loongarch/include/asm/kvm_para.h | 130 +
arch/loongarch/include/asm/loongarch.h | 1 +
arch/loongarch/kvm/exit.c | 76 ++-
arch/loongarch
Add documentation topic for using pv_virt when running as a guest
on KVM hypervisor.
Signed-off-by: Bibo Mao
---
Documentation/virt/kvm/index.rst | 1 +
.../virt/kvm/loongarch/hypercalls.rst | 79 +++
Documentation/virt/kvm/loongarch/index.rst| 10
value
KVM_HCALL_INVALID_CODE, rather than inject EXCCODE_INE invalid
instruction exception. So VM can continue to executing the next code.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/Kbuild | 1 -
arch/loongarch/include/asm/kvm_para.h | 26 ++
arch
encoding, the ipi hw will convert it into bitmap in ipi message
buffer.
3. Add structure smp_ops on LoongArch platform so that pv ipi can be used
later.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/hardirq.h | 4 ++
arch/loongarch/include/asm/irq.h | 10 -
arch/loongarch/include
ending ipi message.
---
Bibo Mao (7):
LoongArch/smp: Refine some ipi functions on LoongArch platform
LoongArch: KVM: Add hypercall instruction emulation support
LoongArch: KVM: Add cpucfg area for kvm hypervisor
LoongArch: KVM: Add vcpu search support from physical cpuid
LoongArch: KVM: Add pv i
PV features, and the area can be extended
for other hypervisors in future. This area will never be used for
real HW, it is only used by software.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/inst.h | 1 +
arch/loongarch/include/asm/loongarch.h | 10 +
arch/loongarch/kvm/exit.c
as 256 by KVM which comes from
extioi irqchip.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/kvm_host.h | 26
arch/loongarch/include/asm/kvm_vcpu.h | 1 +
arch/loongarch/kvm/vcpu.c | 93 ++-
arch/loongarch/kvm/vm.c | 11
4
into hypervisor
greatly.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/kvm_host.h | 1 +
arch/loongarch/include/asm/kvm_para.h | 129 +
arch/loongarch/include/asm/kvm_vcpu.h | 10 ++
arch/loongarch/include/asm/loongarch.h | 1 +
arch/loongarch/kvm/exit.c
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
Add documentation topic for using pv_virt when running as a guest
on KVM hypervisor.
Signed-off-by: Bibo Mao
---
Documentation/virt/kvm/index.rst | 1 +
.../virt/kvm/loongarch/hypercalls.rst | 82 +++
Documentation/virt/kvm/loongarch/index.rst| 10
Para-virt feature steal time is added in both kvm and guest kernel side.
It is silimar with other architectures, steal time structure comes from
guest memory, also pseduo register is used to save/restore base address
of steal time structure, so that vm migration is supported also.
Bibo Mao (2
hypervisor to enable steal time. When vcpu is offline, physical address
is set as 0 and tells hypervisor to disable steal time.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/paravirt.h | 5 +
arch/loongarch/kernel/paravirt.c | 130 ++
arch/loongarch/kernel/time.c
-maob...@loongson.cn/
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/kvm_host.h | 7 ++
arch/loongarch/include/asm/kvm_para.h | 10 +++
arch/loongarch/include/asm/loongarch.h | 1 +
arch/loongarch/include/uapi/asm/kvm.h | 4 +
arch/loongarch/kvm/exit.c | 35
hypervisor to enable steal time. When vcpu is offline, physical address
is set as 0 and tells hypervisor to disable steal time.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/paravirt.h | 5 +
arch/loongarch/kernel/paravirt.c | 130 ++
arch/loongarch/kernel/time.c
-maob...@loongson.cn/
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/kvm_host.h | 7 ++
arch/loongarch/include/asm/kvm_para.h | 10 +++
arch/loongarch/include/asm/loongarch.h | 1 +
arch/loongarch/include/uapi/asm/kvm.h | 4 +
arch/loongarch/kvm/exit.c | 35
2. Refine changelog description
3. Add hypercall statistic support for vcpu
4. Set percpu pv ipi message buffer aligned with cacheline
5. Refine pv ipi send logic, do not send ipi message with if there is
pending ipi message.
---
Bibo Mao (6):
LoongArch/smp: Refine some ipi functions on LoongArc
encoding, the ipi hw will convert it into bitmap in ipi message
buffer.
3. Add structure smp_ops on LoongArch platform so that pv ipi can be used
later.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/hardirq.h | 4 ++
arch/loongarch/include/asm/irq.h | 10 -
arch/loongarch/include
value
KVM_HCALL_INVALID_CODE, rather than inject EXCCODE_INE invalid
instruction exception. So VM can continue to executing the next code.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/Kbuild | 1 -
arch/loongarch/include/asm/kvm_para.h | 26 ++
arch
as 256 by KVM which comes from
extioi irqchip.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/kvm_host.h | 26
arch/loongarch/include/asm/kvm_vcpu.h | 1 +
arch/loongarch/kvm/vcpu.c | 93 ++-
arch/loongarch/kvm/vm.c | 11
4
PV features, and the area can be extended
for other hypervisors in future. This area will never be used for
real HW, it is only used by software.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/inst.h | 1 +
arch/loongarch/include/asm/loongarch.h | 10 +
arch/loongarch/kvm/exit.c
into hypervisor
greatly.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/kvm_host.h | 1 +
arch/loongarch/include/asm/kvm_para.h | 129 +
arch/loongarch/include/asm/kvm_vcpu.h | 10 ++
arch/loongarch/include/asm/loongarch.h | 1 +
arch/loongarch/kvm/exit.c
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
. Add PARAVIRT_TIME_ACCOUNTING kconfig option in file
arch/loongarch/Kconfig
2. Function name change such as replace pv_register_steal_time with
pv_enable_steal_time etc
---
Bibo Mao (2):
LoongArch: KVM: Add steal time support in kvm side
LoongArch: Add steal time support in guest side
arch
50
16 0 0 7583616 184816 723040 0 6300 6166 4 62 12 2 20
18 0 0 7583632 184480 722400 0 2814 1754 2 58 4 1 35
Signed-off-by: Bibo Mao
---
arch/loongarch/Kconfig| 11 +++
arch/loongarch/include/asm/paravirt.h | 5 +
arch/loongarch/kernel
-maob...@loongson.cn/
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/kvm_host.h | 7 ++
arch/loongarch/include/asm/kvm_para.h | 10 +++
arch/loongarch/include/asm/loongarch.h | 1 +
arch/loongarch/include/uapi/asm/kvm.h | 4 +
arch/loongarch/kvm/exit.c | 29
feature.
One cpu attr ioctl command KVM_LOONGARCH_VCPU_PVTIME_CTRL is added to
save and restore base address of steal time structure when VM is migrated.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/kvm_host.h | 7 ++
arch/loongarch/include/asm/kvm_para.h | 10 ++
arch/loongarch/include
... v2:
1. Add PARAVIRT_TIME_ACCOUNTING kconfig option in file
arch/loongarch/Kconfig
2. Function name change such as replace pv_register_steal_time with
pv_enable_steal_time etc
---
Bibo Mao (2):
LoongArch: KVM: Add steal time support in kvm side
LoongArch: Add steal time support in guest
50
16 0 0 7583616 184816 723040 0 6300 6166 4 62 12 2 20
18 0 0 7583632 184480 722400 0 2814 1754 2 58 4 1 35
Signed-off-by: Bibo Mao
---
.../admin-guide/kernel-parameters.txt | 2 +-
arch/loongarch/Kconfig| 11 ++
arch
PARAVIRT_TIME_ACCOUNTING kconfig option in file
arch/loongarch/Kconfig
2. Function name change such as replace pv_register_steal_time with
pv_enable_steal_time etc
---
Bibo Mao (2):
LoongArch: KVM: Add steal time support in kvm side
LoongArch: Add steal time support in guest side
.../admin-guide
feature.
One cpu attr ioctl command KVM_LOONGARCH_VCPU_PVTIME_CTRL is added to
save and restore base address of steal time structure when VM is migrated.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/kvm_host.h | 7 ++
arch/loongarch/include/asm/kvm_para.h | 10 ++
arch/loongarch/include
16 0 0 7583616 184816 723040 0 6300 6166 4 62 12 2 20
18 0 0 7583632 184480 722400 0 2814 1754 2 58 4 1 35
Signed-off-by: Bibo Mao
---
.../admin-guide/kernel-parameters.txt | 2 +-
arch/loongarch/Kconfig| 11 ++
arch/loongarch
Function kvm_arch_para_features() is to detect supported para features,
it can be used by device driver to detect and enable para features,
such as extioi irqchip driver to detect KVM_FEATURE_VIRT_EXTIOI.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/kvm_para.h | 10 ++
arch
.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/kvm_host.h | 4
arch/loongarch/include/asm/kvm_para.h | 1 +
arch/loongarch/include/asm/loongarch.h | 1 +
arch/loongarch/kvm/exit.c | 24 +++-
arch/loongarch/kvm/vcpu.c | 13
nce impact
Original 173.07 seconds
With patch 171.73 seconds+1%
2. 2 VMs with 32 vCPUs and 2 numa node
kernel compile time performance impact
Original 2362.04 seconds
With patch 354.17 seconds +566%
B
. With kvm_wait()
vCPU thread will exit to hypervisor and give up scheduleing on pCPU,
and with function kvm_kick_cpu() one hypercall function is used
to notify hypervisor to wakeup previously waited vCPU.
Signed-off-by: Bibo Mao
---
arch/loongarch/Kconfig| 14 +++
arch
indicates that the virt EXTIOI can route
interrupts to 256 vCPUs, rather than 4 vCPUs like with real HW.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/kvm_host.h | 9 +
arch/loongarch/include/asm/kvm_para.h | 1 +
arch/loongarch/include/asm/loongarch.h | 13 ---
arch
features.
v1 ... v2:
1. Update changelog suggested by WangXuerui.
2. Fix typo issue in function kvm_loongarch_cpucfg_set_attr(),
usr_features should be assigned directly, also suggested by WangXueRui.
---
Bibo Mao (2):
LoongArch: KVM: Enable paravirt feature control from VMM
LoongArch: KVM
Function kvm_arch_para_features() is to detect supported paravirt features,
it can be used by device driver to detect and enable paravirt features,
such as extioi irqchip driver can detect KVM_FEATURE_VIRT_EXTIOI and do
some optimization.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm
Function kvm_para_has_feature() is to detect supported paravirt features,
it can be used by device driver to detect and enable paravirt features,
such as extioi irqchip driver can detect KVM_FEATURE_VIRT_EXTIOI and do
some optimization.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm
by WangXueRui.
---
Bibo Mao (3):
LoongArch: KVM: Enable paravirt feature control from VMM
LoongArch: KVM: Implement function kvm_para_has_feature
irqchip/loongson-eiointc: Add extioi virt extension support
.../arch/loongarch/irq-chip-model.rst | 64 ++
.../zh_CN/arch
indicates that the virt EXTIOI can route
interrupts to 256 vCPUs, rather than 4 vCPUs like with real HW.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/kvm_host.h | 7
arch/loongarch/include/asm/kvm_para.h | 1 +
arch/loongarch/include/asm/loongarch.h | 13 ---
arch
Interrupts can be routed to maximal four virtual CPUs with one external
hardware interrupt. Add the extioi virt extension support so that
Interrupts can be routed to 256 vcpus on hypervisor mode.
Co-developed-by: Song Gao
Signed-off-by: Song Gao
Signed-off-by: Bibo Mao
---
.../arch/loongarch
Original 2362.04 seconds
With patch 354.73 seconds+565%
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/Kbuild | 1 -
arch/loongarch/include/asm/paravirt.h | 3 ++
arch/loongarch/include/asm/qspinlock.h | 41 ++
arch/loonga
Original 2362.04 seconds
With patch 354.73 seconds+565%
Signed-off-by: Bibo Mao
---
v1 ... v2:
1. Define static key virt_spin_lock_key as false by default
2. Add prefix __init with function smp_prepare_boot_cpu(), since there
is prefix __init with calle
ctly, also suggested by
WangXueRui.
---
Bibo Mao (3):
LoongArch: KVM: Enable paravirt feature control from VMM
LoongArch: KVM: Implement function kvm_para_has_feature
irqchip/loongson-eiointc: Add extioi virt extension support
.../arch/loongarch/irq-chip-model.rst
Function kvm_para_has_feature() is to detect supported paravirt features,
it can be used by device driver to detect and enable paravirt features,
such as extioi irqchip driver can detect KVM_FEATURE_VIRT_EXTIOI and do
some optimization.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm
indicates that the virt EXTIOI can route
interrupts to 256 vCPUs, rather than 4 vCPUs like with real HW.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/kvm_host.h | 7
arch/loongarch/include/asm/kvm_para.h | 1 +
arch/loongarch/include/asm/loongarch.h | 13 ---
arch
Interrupts can be routed to maximal four virtual CPUs with one external
hardware interrupt. Add the extioi virt extension support so that
Interrupts can be routed to 256 vcpus on hypervisor mode.
Co-developed-by: Song Gao
Signed-off-by: Song Gao
Signed-off-by: Bibo Mao
---
.../arch/loongarch
t features.
v1 ... v2:
1. Update changelog suggested by WangXuerui.
2. Fix typo issue in function kvm_loongarch_cpucfg_set_attr(),
usr_features should be assigned directly, also suggested by
WangXueRui.
---
Bibo Mao (3):
LoongArch: KVM: Enable paravirt feature control from VMM
Loon
indicates that the virt EXTIOI can route
interrupts to 256 vCPUs, rather than 4 vCPUs like with real HW.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm/kvm_host.h | 7
arch/loongarch/include/asm/kvm_para.h | 1 +
arch/loongarch/include/asm/kvm_vcpu.h | 4 ++
arch
Function kvm_para_has_feature() is to detect supported paravirt features,
it can be used by device driver to detect and enable paravirt features,
such as extioi irqchip driver can detect KVM_FEATURE_VIRT_EXTIOI and do
some optimization.
Signed-off-by: Bibo Mao
---
arch/loongarch/include/asm
. CPU bitmap is replaced with normal encoding and EIOINTC
node type is removed, so there are 8 bits for cpu selection, at most 256
vCPUs are supported for interrupt routing.
Co-developed-by: Song Gao
Signed-off-by: Song Gao
Signed-off-by: Bibo Mao
---
.../arch/loongarch/irq-chip-model.rst
: KVM: Add PV IPI support on guest side")
Signed-off-by: Bibo Mao
---
arch/loongarch/kernel/paravirt.c | 19 +++
1 file changed, 19 insertions(+)
diff --git a/arch/loongarch/kernel/paravirt.c b/arch/loongarch/kernel/paravirt.c
index 9c9b75b76f62..348920b25460 100644
ggested by
WangXueRui.
---
Bibo Mao (3):
LoongArch: KVM: Enable paravirt feature control from VMM
LoongArch: KVM: Implement function kvm_para_has_feature
irqchip/loongson-eiointc: Add extioi virt extension support
.../arch/loongarch/irq-chip-model.rst | 64 +++
.../zh_CN/arch/loo
1 - 100 of 179 matches
Mail list logo
