Support Asynchronous Page Fault
Subsystems (7)
v4 cover Support Asynchronous Page Fault
There are two stages of page fault. The guest kernel is responsible for handling stage-1 page fault, while the host kernel is to take care of the stage-2 page fault. When the guest is trapped to host because of stage-2 page fault, the guest is suspended until the requested memory (page) is populated. Sometimes, the cost to populate the requested page isn't cheap and can take hundreds of milliseconds in extreme cases. Similarly, the guest has to wait until the requested memory is ready in the scenario of post-copy live migration.
This series introduces the feature (Asynchronous Page Fault) to improve situation, so that the guest needn't have to wait in the scenarios. With it, the overall performance is improved on the guest. This series depends on the feature "SDEI virtualization" and QEMU changes. All code changes can be found from github:
https://github.com/gwshan/linux ("kvm/arm64_sdei") # SDEI virtualization
https://github.com/gwshan/linux ("kvm/arm64_apf") # This series + "sdei"
https://github.com/gwshan/qemu ("kvm/arm64_apf") # QEMU code changes
About the design, the details can be found from last patch. Generally, it's driven by two notifications: page-not-present and page-ready. They are delivered from the host to guest via SDEI event and PPI separately. In the mean while, each notification is always associated with a token, used to identify the notification. The token is passed by the shared memory between host/guest. Besides, the SMCCC and ioctl interface are mitigated by VMM and guest to configure, enable, disable, even migrate the functionality.
When the guest is trapped to host because of stage-2 page fault, a page-not-present notification is raised by the host, and sent to the guest through dedicated SDEI event (0x40400001) if the requested page can't be populated immediately. In the mean while, a (background) worker is also started to populate the requested page. On receiving the SDEI event, the guest marks the current running process with special flag (TIF_ASYNC_PF) and associates it with a pre-allocated waitqueue. At same time, a (reschedule) IPI is sent to current CPU. After the SDEI event is acknowledged by the guest, the (reschedule) IPI is delivered and it causes context switch from that process tagged with TIF_ASYNC_PF to another process.
Later on, a page-ready notification is sent to guest after the requested page is populated by the (background) worker. On receiving the interrupt, the guest uses the associated token to locate the process, which was previously suspended because of page-not-present. The flag (TIF_ASYNC_PF) is cleared for the suspended process and it's waken up.
The series is organized as below:
PATCH[01-04] makes the GFN hash table management generic so that it
can be shared by x86/arm64.
PATCH[05-06] preparatory work to support asynchronous page fault. PATCH[07-08] support asynchronous page fault.
PATCH[09-11] support ioctl and SMCCC interfaces for the functionality. PATHC[12-14] supoort asynchronous page fault for guest
PATCH[15] adds document to explain the design and internals
Testing
=======
The tests are taken using program "testsuite", which is written by myself. The program basically does two things: (a) Starts a thread to allocate all the available memory, write to them by the specified times. (b) The parallel thread is started to do calculation while the memory is written for the specified times.
Besides, there are two testing scenarios: (a) the QEMU process is put into cgroup where the memory is limited. With this, we should have asynchronous page fault activities. The total used time for "testsuite" to finish is measured. The calculation capacity is also measured if the corresponding thread is started. (b) To measure the total used time and calculation capacity in scenario of migrating the workload.
(a) Running "testsuite" with (cgroup) memory limitation to QEMU process. When the calculation thread isn't started, the consumed time is slightly increased because of overhead introduced by asynchronous page fault. The total used time drops by ~40% when the calculation thread is started. It means the parallelism is greatly improved by the asynchronous page fault.
vCPU: 1 Memory: 1024MB cgroupv2.limit: 512MB
Command: testsuite test async_pf -l 1 [-t] -q
Time- Calculation- Time+ Calculation+ Output
--------------------------------------------------------------------
14.592s 15.010s +2.8% 15.726s 15.185s +3.4% 15.742s 15.192s +3.4% 15.827s 15.270s +3.5% 15.831s 15.291s +3.4% 27.880s 2108m 16.539s 1104m -40.6% -47.6% 27.972s 2111m 16.588s 1110m -40.6% -47.4% 28.020s 2114m 16.656s 1117m -40.5% -47.1% 28.227s 2135m 16.722s 1105m -40.7% -48.2% 28.918s 2194m 16.767s 1113m -42.0% -49.2%
Asynchronous page faults: 55000
(b) Migrating the workload ("testsuite"). The total used time is dropped a bit since the migration is completed in very short period (~1.5s). There are not too much asynchronous page fault activies during the migration. It's overall beneficial to migration performance if guest experices high work load. However, the used time is increased by ~14% because of the overhead introduced by asynchronous page fault when guest doesn't have high work load.
vCPU: 1 Memory: 1024MB cgroupv2.limit: unlimited
Command: testsuite test async_pf -l 50 [-t] -q
Time- Calculation- Time+ Calculation+ Output
--------------------------------------------------------------------
11.132s 12.655s +13.6% 11.135s 12.707s +14.1% 11.143s 12.728s +14.2% 11.167s 12.746s +14.1% 11.172s 12.821s +14.7% 27.308s 2252m 25.827s 2131m -5.4% 27.440s 2275m 26.517s 2333m -3.3% 28.069s 2364m 26.520s 2356m -5.5% 28.777s 2427m 26.726s 2383m -7.1% 28.915s 2452m 27.632s 2508m -4.4%
migrate.total_time: ~1.6s
Asynchronous page faults: ~100 times
Changelog
=========
v4:
* Rebase to v5.14.rc5 and retest (Gavin)
v3:
* Rebase to v5.13.rc1 (Gavin) * Drop patches from Will to detected SMCCC KVM service (Gavin) * Retest and recapture the benchmarks (Gavin)
v2:
* Rebase to v5.11.rc6 (Gavin)
* Split the patches (James)
* Allocate "struct kvm_arch_async_control" dymaicall and use it to check if the feature has been enabled. The kernel
option (CONFIG_KVM_ASYNC_PF) isn't used. (James)
* Add document to explain the design (James) * Make GFN hash table management generic (James) * Add ioctl commands to support migration (Gavin)
Gavin Shan (15):
KVM: async_pf: Move struct kvm_async_pf around
KVM: async_pf: Add helper function to check completion queue
KVM: async_pf: Make GFN slot management generic
KVM: x86: Use generic async PF slot management
KVM: arm64: Export kvm_handle_user_mem_abort()
KVM: arm64: Add paravirtualization header files
KVM: arm64: Support page-not-present notification
KVM: arm64: Support page-ready notification
KVM: arm64: Support async PF hypercalls
KVM: arm64: Support async PF ioctl commands
KVM: arm64: Export async PF capability
arm64: Detect async PF para-virtualization feature
arm64: Reschedule process on aync PF
arm64: Enable async PF
KVM: arm64: Add async PF document
Documentation/virt/kvm/arm/apf.rst | 143 +++++++ Documentation/virt/kvm/arm/index.rst | 1 + arch/arm64/Kconfig | 11 + arch/arm64/include/asm/esr.h | 6 + arch/arm64/include/asm/kvm_emulate.h | 27 +- arch/arm64/include/asm/kvm_host.h | 85 ++++ arch/arm64/include/asm/kvm_para.h | 37 ++ arch/arm64/include/asm/processor.h | 1 + arch/arm64/include/asm/thread_info.h | 4 +- arch/arm64/include/uapi/asm/Kbuild | 2 - arch/arm64/include/uapi/asm/kvm.h | 19 + arch/arm64/include/uapi/asm/kvm_para.h | 23 ++ arch/arm64/include/uapi/asm/kvm_sdei.h | 1 + arch/arm64/kernel/Makefile | 1 + arch/arm64/kernel/kvm.c | 452 +++++++++++++++++++++ arch/arm64/kernel/signal.c | 17 + arch/arm64/kvm/Kconfig | 2 + arch/arm64/kvm/Makefile | 1 + arch/arm64/kvm/arm.c | 37 +- arch/arm64/kvm/async_pf.c | 533 +++++++++++++++++++++++++ arch/arm64/kvm/hypercalls.c | 5 + arch/arm64/kvm/mmu.c | 76 +++- arch/arm64/kvm/sdei.c | 5 + arch/x86/include/asm/kvm_host.h | 2 - arch/x86/kvm/Kconfig | 1 + arch/x86/kvm/mmu/mmu.c | 2 +- arch/x86/kvm/x86.c | 88 +--- include/linux/arm-smccc.h | 15 + include/linux/kvm_host.h | 72 +++- include/uapi/linux/kvm.h | 3 + virt/kvm/Kconfig | 3 + virt/kvm/async_pf.c | 95 ++++- virt/kvm/kvm_main.c | 4 +- 33 files changed, 1621 insertions(+), 153 deletions(-) create mode 100644 Documentation/virt/kvm/arm/apf.rst create mode 100644 arch/arm64/include/asm/kvm_para.h create mode 100644 arch/arm64/include/uapi/asm/kvm_para.h create mode 100644 arch/arm64/kernel/kvm.c create mode 100644 arch/arm64/kvm/async_pf.c
Signature · 1 line
2.23.0
PATCH v4 1/15 KVM: async_pf: Move struct kvm_async_pf around
This moves the definition of "struct kvm_async_pf" and the related functions after "struct kvm_vcpu" so that newly added inline functions in the subsequent patches can dereference "struct kvm_vcpu" properly. Otherwise, the unexpected build error will be raised:
error: dereferencing pointer to incomplete type ‘struct kvm_vcpu’
return !list_empty_careful(&vcpu->async_pf.done);
^~Since we're here, the sepator between type and field in "struct kvm_vcpu" is replaced by tab. The empty stub kvm_check_async_pf_completion() is also added on !CONFIG_KVM_ASYNC_PF, which is needed by subsequent patches to support asynchronous page fault on ARM64.
--- include/linux/kvm_host.h | 44 +++++++++++++++++++++------------------- 1 file changed, 23 insertions(+), 21 deletions(-)
include/linux/kvm_host.h +23 -21
@@ -199,27 +199,6 @@ int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,struct kvm_io_device *kvm_io_bus_get_dev (struct kvm *kvm,enum kvm_bus bus_idx,gpa_t addr); -#ifdef CONFIG_KVM_ASYNC_PF -struct kvm_async_pf { -struct work_struct work; -struct list_head link; -struct list_head queue; -struct kvm_vcpu *vcpu; -struct mm_struct *mm; -gpa_t cr2_or_gpa; -unsigned long addr; -struct kvm_arch_async_pf arch; -bool wakeup_all; -bool notpresent_injected; -}; - -void kvm_clear_async_pf_completion_queue (struct kvm_vcpu *vcpu); -void kvm_check_async_pf_completion (struct kvm_vcpu *vcpu); -bool kvm_setup_async_pf (struct kvm_vcpu *vcpu,gpa_t cr2_or_gpa, -unsigned long hva,struct kvm_arch_async_pf *arch); -int kvm_async_pf_wakeup_all (struct kvm_vcpu *vcpu); -#endif - #ifdef KVM_ARCH_WANT_MMU_NOTIFIER struct kvm_gfn_range { struct kvm_memory_slot *slot;
@@ -346,6 +325,29 @@ struct kvm_vcpu {struct kvm_dirty_ring dirty_ring; }; +#ifdef CONFIG_KVM_ASYNC_PF +struct kvm_async_pf { +struct work_struct work; +struct list_head link; +struct list_head queue; +struct kvm_vcpu *vcpu; +struct mm_struct *mm; +gpa_t cr2_or_gpa; +unsigned long addr; +struct kvm_arch_async_pf arch; +bool wakeup_all; +bool notpresent_injected; +}; + +void kvm_clear_async_pf_completion_queue (struct kvm_vcpu *vcpu); +void kvm_check_async_pf_completion (struct kvm_vcpu *vcpu); +bool kvm_setup_async_pf (struct kvm_vcpu *vcpu,gpa_t cr2_or_gpa, +unsigned long hva,struct kvm_arch_async_pf *arch); +int kvm_async_pf_wakeup_all (struct kvm_vcpu *vcpu); +#else +static inline void kvm_check_async_pf_completion (struct kvm_vcpu *vcpu) { } +#endif +/* must be called with irqs disabled */ static __always_inline void guest_enter_irqoff(void) {
Signature · 1 line
2.23.0
Re: [PATCH v4 01/15] KVM: async_pf: Move struct kvm_async_pf around
Hi Gavin,
Quoted 9 lines · Gavin Shan
This moves the definition of "struct
kvm_async_pf" and the related functions after "structkvm_vcpu" so that newly added inline functions in the subsequent patches can dereference "structkvm_vcpu" properly. Otherwise, the unexpected build error will be raised:error: dereferencing pointer to incomplete type ‘struct kvm_vcpu’ return !list_empty_careful(&vcpu->async_pf.done); ^~Since we're here, the sepator between type and field in "struct
kvm_vcpu"
separator
Quoted 56 lines
is replaced by tab. The empty stub
kvm_check_async_pf_completion()is also added on !CONFIG_KVM_ASYNC_PF, which is needed by subsequent patches to support asynchronous page fault on ARM64.Signed-off-by Gavin Shan <[email protected]>--- include/linux/kvm_host.h | 44 +++++++++++++++++++++------------------- 1 file changed, 23 insertions(+), 21 deletions(-)include/linux/kvm_host.h +11
-21@@ -199,27 +199,6 @@ int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,struct kvm_io_device *kvm_io_bus_get_dev (struct kvm *kvm,enum kvm_bus bus_idx,gpa_t addr); -#ifdef CONFIG_KVM_ASYNC_PF -struct kvm_async_pf { -struct work_struct work; -struct list_head link; -struct list_head queue; -struct kvm_vcpu *vcpu; -struct mm_struct *mm; -gpa_t cr2_or_gpa; -unsigned long addr; -struct kvm_arch_async_pf arch; -bool wakeup_all; -bool notpresent_injected; -}; - -void kvm_clear_async_pf_completion_queue (struct kvm_vcpu *vcpu); -void kvm_check_async_pf_completion (struct kvm_vcpu *vcpu); -bool kvm_setup_async_pf (struct kvm_vcpu *vcpu,gpa_t cr2_or_gpa, -unsigned long hva,struct kvm_arch_async_pf *arch); -int kvm_async_pf_wakeup_all (struct kvm_vcpu *vcpu); -#endif - #ifdef KVM_ARCH_WANT_MMU_NOTIFIER struct kvm_gfn_range { struct kvm_memory_slot *slot;@@ -346,6 +325,29 @@ struct kvm_vcpu {struct kvm_dirty_ring dirty_ring; }; +#ifdef CONFIG_KVM_ASYNC_PF +struct kvm_async_pf { + struct work_struct work; + struct list_head link; + struct list_head queue; + struct kvm_vcpu *vcpu; + struct mm_struct *mm; + gpa_t cr2_or_gpa; + unsigned long addr; + struct kvm_arch_async_pf arch; + bool wakeup_all;
include/linux/kvm_host.h struct kvm_vcpu { · line 348
Quoted 10 lines
include/linux/kvm_host.h +10
-0+ bool notpresent_injected; +}; + +void kvm_clear_async_pf_completion_queue (struct kvm_vcpu *vcpu); +void kvm_check_async_pf_completion (struct kvm_vcpu *vcpu); +bool kvm_setup_async_pf (struct kvm_vcpu *vcpu,gpa_t cr2_or_gpa, +unsigned long hva,struct kvm_arch_async_pf *arch); +int kvm_async_pf_wakeup_all (struct kvm_vcpu *vcpu); +#else +static inline void kvm_check_async_pf_completion (struct kvm_vcpu *vcpu) { }
why is that stub needed on ARM64 and not on the other archs?
Eric
Quoted 6 lines
include/linux/kvm_host.h +2
-0+#endif +/* must be called with irqs disabled */ static __always_inline void guest_enter_irqoff(void) {
Re: [PATCH v4 01/15] KVM: async_pf: Move struct kvm_async_pf around
Hi Eric,
Quoted 11 lines · Eric Auger
Quoted 9 lines · Gavin Shan
This moves the definition of "struct
kvm_async_pf" and the related functions after "structkvm_vcpu" so that newly added inline functions in the subsequent patches can dereference "structkvm_vcpu" properly. Otherwise, the unexpected build error will be raised:error: dereferencing pointer to incomplete type ‘struct kvm_vcpu’ return !list_empty_careful(&vcpu->async_pf.done); ^~Since we're here, the sepator between type and field in "struct
kvm_vcpu"separator
Thanks, It will be fixed in next respin.
Quoted 59 lines
Quoted 59 lines
is replaced by tab. The empty stub
kvm_check_async_pf_completion()is also added on !CONFIG_KVM_ASYNC_PF, which is needed by subsequent patches to support asynchronous page fault on ARM64.Signed-off-by Gavin Shan <[email protected]>--- include/linux/kvm_host.h | 44 +++++++++++++++++++++------------------- 1 file changed, 23 insertions(+), 21 deletions(-)include/linux/kvm_host.h +14
-21@@ -199,27 +199,6 @@ int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,struct kvm_io_device *kvm_io_bus_get_dev (struct kvm *kvm,enum kvm_bus bus_idx,gpa_t addr); -#ifdef CONFIG_KVM_ASYNC_PF -struct kvm_async_pf { -struct work_struct work; -struct list_head link; -struct list_head queue; -struct kvm_vcpu *vcpu; -struct mm_struct *mm; -gpa_t cr2_or_gpa; -unsigned long addr; -struct kvm_arch_async_pf arch; -bool wakeup_all; -bool notpresent_injected; -}; - -void kvm_clear_async_pf_completion_queue (struct kvm_vcpu *vcpu); -void kvm_check_async_pf_completion (struct kvm_vcpu *vcpu); -bool kvm_setup_async_pf (struct kvm_vcpu *vcpu,gpa_t cr2_or_gpa, -unsigned long hva,struct kvm_arch_async_pf *arch); -int kvm_async_pf_wakeup_all (struct kvm_vcpu *vcpu); -#endif - #ifdef KVM_ARCH_WANT_MMU_NOTIFIER struct kvm_gfn_range { struct kvm_memory_slot *slot;@@ -346,6 +325,29 @@ struct kvm_vcpu {struct kvm_dirty_ring dirty_ring; }; +#ifdef CONFIG_KVM_ASYNC_PF +struct kvm_async_pf { +struct work_struct work; +struct list_head link; +struct list_head queue; +struct kvm_vcpu *vcpu; +struct mm_struct *mm; +gpa_t cr2_or_gpa; +unsigned long addr; +struct kvm_arch_async_pf arch; +bool wakeup_all; +bool notpresent_injected; +}; +
Quoted 9 lines
include/linux/kvm_host.h struct kvm_vcpu { · line 348
Quoted 7 lines
include/linux/kvm_host.h +7
-0+void kvm_clear_async_pf_completion_queue (struct kvm_vcpu *vcpu); +void kvm_check_async_pf_completion (struct kvm_vcpu *vcpu); +bool kvm_setup_async_pf (struct kvm_vcpu *vcpu,gpa_t cr2_or_gpa, +unsigned long hva,struct kvm_arch_async_pf *arch); +int kvm_async_pf_wakeup_all (struct kvm_vcpu *vcpu); +#else +static inline void kvm_check_async_pf_completion (struct kvm_vcpu *vcpu) { }why is that stub needed on ARM64 and not on the other archs?
We use the following pattern, suggested by James Morse.
int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
{
int r;
switch (ext) {
:
case KVM_CAP_ASYNC_PF:
case KVM_CAP_ASYNC_PF_INT:
r = IS_ENABLED(CONFIG_KVM_ASYNC_PF) ? 1 : 0;
break;
default:
r = 0;
}
return r;
}Thanks,
Gavin
Quoted 7 lines
Quoted 6 lines
include/linux/kvm_host.h +2
-0+#endif +/* must be called with irqs disabled */ static __always_inline void guest_enter_irqoff(void) {
PATCH v4 2/15 KVM: async_pf: Add helper function to check completion queue
In reply to Gavin ShanThis adds inline helper kvm_check_async_pf_completion_queue() to check if there are pending completion in the queue. The empty stub is also added on !CONFIG_KVM_ASYNC_PF so that the caller needn't consider if CONFIG_KVM_ASYNC_PF is enabled.
All checks on the completion queue is done by the newly added inline function since list_empty() and list_empty_careful() are interchangeable.
--- arch/x86/kvm/x86.c | 2 +- include/linux/kvm_host.h | 10 ++++++++++ virt/kvm/async_pf.c | 10 +++++----- virt/kvm/kvm_main.c | 4 +--- 4 files changed, 17 insertions(+), 9 deletions(-)
arch/x86/kvm/x86.c +1 -1
@@ -11591,7 +11591,7 @@ static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)static inline bool kvm_vcpu_has_events (struct kvm_vcpu *vcpu) { -if (!list_empty_careful (&vcpu->async_pf.done)) +if (kvm_check_async_pf_completion_queue (vcpu))return true;if (kvm_apic_has_events (vcpu))
include/linux/kvm_host.h +10 -0
@@ -339,12 +339,22 @@ struct kvm_async_pf { bool notpresent_injected; }; +static inline bool kvm_check_async_pf_completion_queue (struct kvm_vcpu *vcpu) +{ +return !list_empty_careful (&vcpu->async_pf.done); +} +void kvm_clear_async_pf_completion_queue (struct kvm_vcpu *vcpu);void kvm_check_async_pf_completion (struct kvm_vcpu *vcpu);bool kvm_setup_async_pf (struct kvm_vcpu *vcpu,gpa_t cr2_or_gpa,unsigned long hva,struct kvm_arch_async_pf *arch);int kvm_async_pf_wakeup_all (struct kvm_vcpu *vcpu);#else +static inline bool kvm_check_async_pf_completion_queue (struct kvm_vcpu *vcpu) +{ +return false; +} +static inline void kvm_check_async_pf_completion (struct kvm_vcpu *vcpu) { }#endif
virt/kvm/async_pf.c +5 -5
@@ -70,7 +70,7 @@ static void async_pf_execute(struct work_struct *work)kvm_arch_async_page_present (vcpu, apf);spin_lock (&vcpu->async_pf.lock); - first =list_empty (&vcpu->async_pf.done); + first = !kvm_check_async_pf_completion_queue (vcpu);list_add_tail (&apf->link, &vcpu->async_pf.done); apf->vcpu =NULL ;spin_unlock (&vcpu->async_pf.lock);
@@ -122,7 +122,7 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)spin_lock (&vcpu->async_pf.lock); } -while (!list_empty (&vcpu->async_pf.done)) { +while (kvm_check_async_pf_completion_queue (vcpu)) {struct kvm_async_pf *work =list_first_entry (&vcpu->async_pf.done,typeof (*work), link);
@@ -138,7 +138,7 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu) {struct kvm_async_pf *work; -while (!list_empty_careful (&vcpu->async_pf.done) && +while (kvm_check_async_pf_completion_queue (vcpu) &&kvm_arch_can_dequeue_async_page_present (vcpu)) {spin_lock (&vcpu->async_pf.lock); work = list_first_entry(&vcpu->async_pf.done, typeof(*work),
@@ -205,7 +205,7 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu)struct kvm_async_pf *work;bool first; -if (!list_empty_careful (&vcpu->async_pf.done)) +if (kvm_check_async_pf_completion_queue (vcpu))return 0 ; work =kmem_cache_zalloc (async_pf_cache,GFP_ATOMIC );
@@ -216,7 +216,7 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu)INIT_LIST_HEAD (&work->queue);/* for list_del to work */ spin_lock (&vcpu->async_pf.lock); - first =list_empty (&vcpu->async_pf.done); + first = !kvm_check_async_pf_completion_queue (vcpu);list_add_tail (&work->link, &vcpu->async_pf.done);spin_unlock (&vcpu->async_pf.lock);
virt/kvm/kvm_main.c +1 -3
@@ -3282,10 +3282,8 @@ static bool vcpu_dy_runnable(struct kvm_vcpu *vcpu)if (kvm_arch_dy_runnable (vcpu))return true; -#ifdef CONFIG_KVM_ASYNC_PF -if (!list_empty_careful (&vcpu->async_pf.done)) +if (kvm_check_async_pf_completion_queue (vcpu))return true; -#endif return false; }
Signature · 1 line
2.23.0
Re: [PATCH v4 02/15] KVM: async_pf: Add helper function to check completion queue
Quoted 34 lines · Gavin Shan
This adds inline helper
kvm_check_async_pf_completion_queue()to check if there are pending completion in the queue. The empty stub is also added on !CONFIG_KVM_ASYNC_PF so that the caller needn't consider ifCONFIG_KVM_ASYNC_PFis enabled.All checks on the completion queue is done by the newly added inline function since
list_empty()andlist_empty_careful()are interchangeable.Signed-off-by Gavin Shan <[email protected]>--- arch/x86/kvm/x86.c | 2 +- include/linux/kvm_host.h | 10 ++++++++++ virt/kvm/async_pf.c | 10 +++++----- virt/kvm/kvm_main.c | 4 +--- 4 files changed, 17 insertions(+), 9 deletions(-)arch/x86/kvm/x86.c +1
-1@@ -11591,7 +11591,7 @@ static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)static inline bool kvm_vcpu_has_events (struct kvm_vcpu *vcpu) { -if (!list_empty_careful (&vcpu->async_pf.done)) +if (kvm_check_async_pf_completion_queue (vcpu))return true;if (kvm_apic_has_events (vcpu))include/linux/kvm_host.h +0
-0
include/linux/kvm_host.h struct kvm_async_pf { · line 342
Quoted 4 lines
include/linux/kvm_host.h +1
-0@@ -339,12 +339,22 @@ struct kvm_async_pf {bool notpresent_injected; }; +static inline bool kvm_check_async_pf_completion_queue (struct kvm_vcpu *vcpu)
Nitpicking: When not reading the implementation, I'm not exactly sure what this function returns as 'check' is too ambiguous ('true' when the queue is full? when it's empty? when it's not empty? when it was properly set up?). I'd suggest we go with a more specific:
kvm_async_pf_completion_queue_empty() or something like that instead (we'll have to invert the logic everywhere then).
Side note: x86 seems to already use a shortened 'apf' instead of 'async_pf' in a number of places (e.g. 'apf_put_user_ready()'), we may want to either fight this practice or support the rebelion by renaming all functions from below instead :-)
Quoted 83 lines
include/linux/kvm_host.h +9
-0+{ +return !list_empty_careful (&vcpu->async_pf.done); +} +void kvm_clear_async_pf_completion_queue (struct kvm_vcpu *vcpu);void kvm_check_async_pf_completion (struct kvm_vcpu *vcpu);bool kvm_setup_async_pf (struct kvm_vcpu *vcpu,gpa_t cr2_or_gpa,unsigned long hva,struct kvm_arch_async_pf *arch);int kvm_async_pf_wakeup_all (struct kvm_vcpu *vcpu);#else +static inline bool kvm_check_async_pf_completion_queue (struct kvm_vcpu *vcpu) +{ +return false; +} +static inline void kvm_check_async_pf_completion (struct kvm_vcpu *vcpu) { }#endif virt/kvm/async_pf.c +5
-5@@ -70,7 +70,7 @@ static void async_pf_execute(struct work_struct *work)kvm_arch_async_page_present (vcpu, apf);spin_lock (&vcpu->async_pf.lock); - first =list_empty (&vcpu->async_pf.done); + first = !kvm_check_async_pf_completion_queue (vcpu);list_add_tail (&apf->link, &vcpu->async_pf.done); apf->vcpu =NULL ;spin_unlock (&vcpu->async_pf.lock);@@ -122,7 +122,7 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)spin_lock (&vcpu->async_pf.lock); } -while (!list_empty (&vcpu->async_pf.done)) { +while (kvm_check_async_pf_completion_queue (vcpu)) {struct kvm_async_pf *work =list_first_entry (&vcpu->async_pf.done,typeof (*work), link);@@ -138,7 +138,7 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu) {struct kvm_async_pf *work; -while (!list_empty_careful (&vcpu->async_pf.done) && +while (kvm_check_async_pf_completion_queue (vcpu) &&kvm_arch_can_dequeue_async_page_present (vcpu)) {spin_lock (&vcpu->async_pf.lock); work = list_first_entry(&vcpu->async_pf.done, typeof(*work),@@ -205,7 +205,7 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu)struct kvm_async_pf *work;bool first; -if (!list_empty_careful (&vcpu->async_pf.done)) +if (kvm_check_async_pf_completion_queue (vcpu))return 0 ; work =kmem_cache_zalloc (async_pf_cache,GFP_ATOMIC );@@ -216,7 +216,7 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu)INIT_LIST_HEAD (&work->queue);/* for list_del to work */ spin_lock (&vcpu->async_pf.lock); - first =list_empty (&vcpu->async_pf.done); + first = !kvm_check_async_pf_completion_queue (vcpu);list_add_tail (&work->link, &vcpu->async_pf.done);spin_unlock (&vcpu->async_pf.lock);virt/kvm/kvm_main.c +1
-3@@ -3282,10 +3282,8 @@ static bool vcpu_dy_runnable(struct kvm_vcpu *vcpu)if (kvm_arch_dy_runnable (vcpu))return true; -#ifdef CONFIG_KVM_ASYNC_PF -if (!list_empty_careful (&vcpu->async_pf.done)) +if (kvm_check_async_pf_completion_queue (vcpu))return true; -#endif return false; }
Signature · 1 line
Vitaly
Re: [PATCH v4 02/15] KVM: async_pf: Add helper function to check completion queue
Hi Vitaly,
Quoted 46 lines · Vitaly Kuznetsov
Quoted 34 lines · Gavin Shan
This adds inline helper
kvm_check_async_pf_completion_queue()to check if there are pending completion in the queue. The empty stub is also added on !CONFIG_KVM_ASYNC_PF so that the caller needn't consider ifCONFIG_KVM_ASYNC_PFis enabled.All checks on the completion queue is done by the newly added inline function since
list_empty()andlist_empty_careful()are interchangeable.Signed-off-by Gavin Shan <[email protected]>--- arch/x86/kvm/x86.c | 2 +- include/linux/kvm_host.h | 10 ++++++++++ virt/kvm/async_pf.c | 10 +++++----- virt/kvm/kvm_main.c | 4 +--- 4 files changed, 17 insertions(+), 9 deletions(-)arch/x86/kvm/x86.c +1
-1@@ -11591,7 +11591,7 @@ static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)static inline bool kvm_vcpu_has_events (struct kvm_vcpu *vcpu) { -if (!list_empty_careful (&vcpu->async_pf.done)) +if (kvm_check_async_pf_completion_queue (vcpu))return true;if (kvm_apic_has_events (vcpu))include/linux/kvm_host.h +0
-0include/linux/kvm_host.h struct kvm_async_pf { · line 342
Quoted 4 lines
include/linux/kvm_host.h +1
-0@@ -339,12 +339,22 @@ struct kvm_async_pf {bool notpresent_injected; }; +static inline bool kvm_check_async_pf_completion_queue (struct kvm_vcpu *vcpu)Nitpicking: When not reading the implementation, I'm not exactly sure what this function returns as 'check' is too ambiguous ('true' when the queue is full? when it's empty? when it's not empty? when it was properly set up?). I'd suggest we go with a more specific:
Quoted 8 lines
kvm_async_pf_completion_queue_empty()or something like that instead (we'll have to invert the logic everywhere then).Side note: x86 seems to already use a shortened 'apf' instead of '
async_pf' in a number of places (e.g. 'apf_put_user_ready()'), we may want to either fight this practice or support the rebelion by renaming all functions from below instead :-)
Yeah, I was wandering if the name is ambiguous when I had it. The reason why I had the name is to be consistent with the existing one, which is kvm_check_async_pf_completion().
Yes, kvm_async_pf_completion_queue_empty() is much better and I will include this in next revision.
It's correct that x86 functions include 'apf', but the generic functions, shared by multiple architectures, use 'async_pf' if my understanding is correct. So I wouldn't bother to change the generic function names in this series :)
Quoted 75 lines
Quoted 75 lines
include/linux/kvm_host.h +9
-0+{ +return !list_empty_careful (&vcpu->async_pf.done); +} +void kvm_clear_async_pf_completion_queue (struct kvm_vcpu *vcpu);void kvm_check_async_pf_completion (struct kvm_vcpu *vcpu);bool kvm_setup_async_pf (struct kvm_vcpu *vcpu,gpa_t cr2_or_gpa,unsigned long hva,struct kvm_arch_async_pf *arch);int kvm_async_pf_wakeup_all (struct kvm_vcpu *vcpu);#else +static inline bool kvm_check_async_pf_completion_queue (struct kvm_vcpu *vcpu) +{ +return false; +} +static inline void kvm_check_async_pf_completion (struct kvm_vcpu *vcpu) { }#endif virt/kvm/async_pf.c +5
-5@@ -70,7 +70,7 @@ static void async_pf_execute(struct work_struct *work)kvm_arch_async_page_present (vcpu, apf);spin_lock (&vcpu->async_pf.lock); - first =list_empty (&vcpu->async_pf.done); + first = !kvm_check_async_pf_completion_queue (vcpu);list_add_tail (&apf->link, &vcpu->async_pf.done); apf->vcpu =NULL ;spin_unlock (&vcpu->async_pf.lock);@@ -122,7 +122,7 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)spin_lock (&vcpu->async_pf.lock); } -while (!list_empty (&vcpu->async_pf.done)) { +while (kvm_check_async_pf_completion_queue (vcpu)) {struct kvm_async_pf *work =list_first_entry (&vcpu->async_pf.done,typeof (*work), link);@@ -138,7 +138,7 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu) {struct kvm_async_pf *work; -while (!list_empty_careful (&vcpu->async_pf.done) && +while (kvm_check_async_pf_completion_queue (vcpu) &&kvm_arch_can_dequeue_async_page_present (vcpu)) {spin_lock (&vcpu->async_pf.lock); work = list_first_entry(&vcpu->async_pf.done, typeof(*work),@@ -205,7 +205,7 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu)struct kvm_async_pf *work;bool first; -if (!list_empty_careful (&vcpu->async_pf.done)) +if (kvm_check_async_pf_completion_queue (vcpu))return 0 ; work =kmem_cache_zalloc (async_pf_cache,GFP_ATOMIC );@@ -216,7 +216,7 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu)INIT_LIST_HEAD (&work->queue);/* for list_del to work */ spin_lock (&vcpu->async_pf.lock); - first =list_empty (&vcpu->async_pf.done); + first = !kvm_check_async_pf_completion_queue (vcpu);list_add_tail (&work->link, &vcpu->async_pf.done);spin_unlock (&vcpu->async_pf.lock);virt/kvm/kvm_main.c +0
-0@@ -3282,10 +3282,8 @@ static bool vcpu_dy_runnable(struct kvm_vcpu *vcpu)if (kvm_arch_dy_runnable (vcpu))return true;
Quoted 9 lines
virt/kvm/kvm_main.c static bool vcpu_dy_runnable(struct kvm_vcpu *vcpu) · line 3289
Quoted 8 lines
virt/kvm/kvm_main.c +1
-3-#ifdef CONFIG_KVM_ASYNC_PF -if (!list_empty_careful (&vcpu->async_pf.done)) +if (kvm_check_async_pf_completion_queue (vcpu))return true; -#endif return false; }
Thanks,
Gavin
Re: [PATCH v4 02/15] KVM: async_pf: Add helper function to check completion queue
In reply to Gavin ShanHi Gavin,
Quoted 7 lines · Gavin Shan
This adds inline helper
kvm_check_async_pf_completion_queue()to check if there are pending completion in the queue. The empty stub is also added on !CONFIG_KVM_ASYNC_PF so that the caller needn't consider ifCONFIG_KVM_ASYNC_PFis enabled.All checks on the completion queue is done by the newly added inline function since
list_empty()andlist_empty_careful()are interchangeable.
why is it interchangeable?
Quoted 63 lines
Signed-off-by Gavin Shan <[email protected]>--- arch/x86/kvm/x86.c | 2 +- include/linux/kvm_host.h | 10 ++++++++++ virt/kvm/async_pf.c | 10 +++++----- virt/kvm/kvm_main.c | 4 +--- 4 files changed, 17 insertions(+), 9 deletions(-)arch/x86/kvm/x86.c +1
-1@@ -11591,7 +11591,7 @@ static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)static inline bool kvm_vcpu_has_events (struct kvm_vcpu *vcpu) { -if (!list_empty_careful (&vcpu->async_pf.done)) +if (kvm_check_async_pf_completion_queue (vcpu))return true;if (kvm_apic_has_events (vcpu))include/linux/kvm_host.h +10
-0@@ -339,12 +339,22 @@ struct kvm_async_pf { bool notpresent_injected; }; +static inline bool kvm_check_async_pf_completion_queue (struct kvm_vcpu *vcpu) +{ +return !list_empty_careful (&vcpu->async_pf.done); +} +void kvm_clear_async_pf_completion_queue (struct kvm_vcpu *vcpu);void kvm_check_async_pf_completion (struct kvm_vcpu *vcpu);bool kvm_setup_async_pf (struct kvm_vcpu *vcpu,gpa_t cr2_or_gpa,unsigned long hva,struct kvm_arch_async_pf *arch);int kvm_async_pf_wakeup_all (struct kvm_vcpu *vcpu);#else +static inline bool kvm_check_async_pf_completion_queue (struct kvm_vcpu *vcpu) +{ +return false; +} +static inline void kvm_check_async_pf_completion (struct kvm_vcpu *vcpu) { }#endif virt/kvm/async_pf.c +1
-1@@ -70,7 +70,7 @@ static void async_pf_execute(struct work_struct *work)kvm_arch_async_page_present (vcpu, apf);spin_lock (&vcpu->async_pf.lock); - first =list_empty (&vcpu->async_pf.done); + first = !kvm_check_async_pf_completion_queue (vcpu);list_add_tail (&apf->link, &vcpu->async_pf.done); apf->vcpu =NULL ;spin_unlock (&vcpu->async_pf.lock);
virt/kvm/async_pf.c void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu) · line 125
Quoted 5 lines
virt/kvm/async_pf.c +1
-1@@ -122,7 +122,7 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)spin_lock (&vcpu->async_pf.lock); } -while (!list_empty (&vcpu->async_pf.done)) { +while (kvm_check_async_pf_completion_queue (vcpu)) {
this is replaced by a stronger check. Please can you explain why is it equivalent?
Quoted 37 lines
virt/kvm/async_pf.c +3
-3struct kvm_async_pf *work =list_first_entry (&vcpu->async_pf.done,typeof (*work), link);@@ -138,7 +138,7 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu) {struct kvm_async_pf *work; -while (!list_empty_careful (&vcpu->async_pf.done) && +while (kvm_check_async_pf_completion_queue (vcpu) &&kvm_arch_can_dequeue_async_page_present (vcpu)) {spin_lock (&vcpu->async_pf.lock); work = list_first_entry(&vcpu->async_pf.done, typeof(*work),@@ -205,7 +205,7 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu)struct kvm_async_pf *work;bool first; -if (!list_empty_careful (&vcpu->async_pf.done)) +if (kvm_check_async_pf_completion_queue (vcpu))return 0 ; work =kmem_cache_zalloc (async_pf_cache,GFP_ATOMIC );@@ -216,7 +216,7 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu)INIT_LIST_HEAD (&work->queue);/* for list_del to work */ spin_lock (&vcpu->async_pf.lock); - first =list_empty (&vcpu->async_pf.done); + first = !kvm_check_async_pf_completion_queue (vcpu);list_add_tail (&work->link, &vcpu->async_pf.done);spin_unlock (&vcpu->async_pf.lock);virt/kvm/kvm_main.c +0
-0@@ -3282,10 +3282,8 @@ static bool vcpu_dy_runnable(struct kvm_vcpu *vcpu)if (kvm_arch_dy_runnable (vcpu))
virt/kvm/kvm_main.c static bool vcpu_dy_runnable(struct kvm_vcpu *vcpu) · line 3289
Quoted 10 lines
virt/kvm/kvm_main.c +1
-3return true; -#ifdef CONFIG_KVM_ASYNC_PF -if (!list_empty_careful (&vcpu->async_pf.done)) +if (kvm_check_async_pf_completion_queue (vcpu))return true; -#endif return false; }
Thanks
Eric
Re: [PATCH v4 02/15] KVM: async_pf: Add helper function to check completion queue
Hi Eric,
Quoted 10 lines · Eric Auger
Quoted 7 lines · Gavin Shan
This adds inline helper
kvm_check_async_pf_completion_queue()to check if there are pending completion in the queue. The empty stub is also added on !CONFIG_KVM_ASYNC_PF so that the caller needn't consider ifCONFIG_KVM_ASYNC_PFis enabled.All checks on the completion queue is done by the newly added inline function since
list_empty()andlist_empty_careful()are interchangeable.why is it interchangeable?
I think the commit log is misleading. list_empty_careful() is more strict than list_empty(). In this patch, we replace list_empty() with list_empty_careful(). I will correct the commit log in next respin like below:
All checks on the completion queue is done by the newly added inline function where list_empty_careful() instead of list_empty() is used.
Quoted 66 lines
Quoted 66 lines
Signed-off-by Gavin Shan <[email protected]>--- arch/x86/kvm/x86.c | 2 +- include/linux/kvm_host.h | 10 ++++++++++ virt/kvm/async_pf.c | 10 +++++----- virt/kvm/kvm_main.c | 4 +--- 4 files changed, 17 insertions(+), 9 deletions(-)arch/x86/kvm/x86.c +1
-1@@ -11591,7 +11591,7 @@ static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)static inline bool kvm_vcpu_has_events (struct kvm_vcpu *vcpu) { -if (!list_empty_careful (&vcpu->async_pf.done)) +if (kvm_check_async_pf_completion_queue (vcpu))return true;if (kvm_apic_has_events (vcpu))include/linux/kvm_host.h +10
-0@@ -339,12 +339,22 @@ struct kvm_async_pf { bool notpresent_injected; }; +static inline bool kvm_check_async_pf_completion_queue (struct kvm_vcpu *vcpu) +{ +return !list_empty_careful (&vcpu->async_pf.done); +} +void kvm_clear_async_pf_completion_queue (struct kvm_vcpu *vcpu);void kvm_check_async_pf_completion (struct kvm_vcpu *vcpu);bool kvm_setup_async_pf (struct kvm_vcpu *vcpu,gpa_t cr2_or_gpa,unsigned long hva,struct kvm_arch_async_pf *arch);int kvm_async_pf_wakeup_all (struct kvm_vcpu *vcpu);#else +static inline bool kvm_check_async_pf_completion_queue (struct kvm_vcpu *vcpu) +{ +return false; +} +static inline void kvm_check_async_pf_completion (struct kvm_vcpu *vcpu) { }#endif virt/kvm/async_pf.c +1
-1@@ -70,7 +70,7 @@ static void async_pf_execute(struct work_struct *work)kvm_arch_async_page_present (vcpu, apf);spin_lock (&vcpu->async_pf.lock); - first =list_empty (&vcpu->async_pf.done); + first = !kvm_check_async_pf_completion_queue (vcpu);list_add_tail (&apf->link, &vcpu->async_pf.done); apf->vcpu =NULL ;spin_unlock (&vcpu->async_pf.lock);@@ -122,7 +122,7 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)spin_lock (&vcpu->async_pf.lock); }
Quoted 4 lines
virt/kvm/async_pf.c void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu) · line 125
Quoted 2 lines
virt/kvm/async_pf.c +1
-1-while (!list_empty (&vcpu->async_pf.done)) { +while (kvm_check_async_pf_completion_queue (vcpu)) {this is replaced by a stronger check. Please can you explain why is it equivalent?
Access to the completion queue is protected by spinlock. So the additional check in list_empty_careful() to verify the head's prev/next are modified on the fly shouldn't happen. It means they're same in our case.
Quoted 44 lines
Quoted 44 lines
virt/kvm/async_pf.c +3
-3struct kvm_async_pf *work =list_first_entry (&vcpu->async_pf.done,typeof (*work), link);@@ -138,7 +138,7 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu) {struct kvm_async_pf *work; -while (!list_empty_careful (&vcpu->async_pf.done) && +while (kvm_check_async_pf_completion_queue (vcpu) &&kvm_arch_can_dequeue_async_page_present (vcpu)) {spin_lock (&vcpu->async_pf.lock); work = list_first_entry(&vcpu->async_pf.done, typeof(*work),@@ -205,7 +205,7 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu)struct kvm_async_pf *work;bool first; -if (!list_empty_careful (&vcpu->async_pf.done)) +if (kvm_check_async_pf_completion_queue (vcpu))return 0 ; work =kmem_cache_zalloc (async_pf_cache,GFP_ATOMIC );@@ -216,7 +216,7 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu)INIT_LIST_HEAD (&work->queue);/* for list_del to work */ spin_lock (&vcpu->async_pf.lock); - first =list_empty (&vcpu->async_pf.done); + first = !kvm_check_async_pf_completion_queue (vcpu);list_add_tail (&work->link, &vcpu->async_pf.done);spin_unlock (&vcpu->async_pf.lock);virt/kvm/kvm_main.c +1
-3@@ -3282,10 +3282,8 @@ static bool vcpu_dy_runnable(struct kvm_vcpu *vcpu)if (kvm_arch_dy_runnable (vcpu))return true; -#ifdef CONFIG_KVM_ASYNC_PF -if (!list_empty_careful (&vcpu->async_pf.done)) +if (kvm_check_async_pf_completion_queue (vcpu))return true; -#endif
Quoted 3 lines
virt/kvm/kvm_main.c static bool vcpu_dy_runnable(struct kvm_vcpu *vcpu) · line 3289
Quoted 3 lines
virt/kvm/kvm_main.c +0
-0return false; }
Thanks,
Gavin
PATCH v4 3/15 KVM: async_pf: Make GFN slot management generic
In reply to Gavin ShanIt's not allowed to fire duplicate notification for same GFN on x86 platform, with help of a hash table. This mechanism is going to be used by arm64 and this makes the code generic and shareable by multiple platforms.
* As this mechanism isn't needed by all platforms, a new kernel config option (CONFIG_ASYNC_PF_SLOT) is introduced so that it can be disabled at compiling time.
* The code is basically copied from x86 platform and the functions are renamed to reflect the fact: (a) the input parameters are vCPU and GFN. (b) The operations are resetting, searching, adding and removing.
* Helper stub is also added on !CONFIG_KVM_ASYNC_PF because we're going to use IS_ENABLED() instead of #ifdef on arm64 when the asynchronous page fault is supported.
This is preparatory work to use the newly introduced functions on x86 platform and arm64 in subsequent patches.
--- include/linux/kvm_host.h | 18 +++++++++ virt/kvm/Kconfig | 3 ++ virt/kvm/async_pf.c | 85 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 106 insertions(+)
include/linux/kvm_host.h +18 -0
@@ -298,6 +298,9 @@ struct kvm_vcpu { #ifdef CONFIG_KVM_ASYNC_PF struct { +#ifdef CONFIG_KVM_ASYNC_PF_SLOT + gfn_t gfns[ASYNC_PF_PER_VCPU]; +#endif u32 queued; struct list_head queue; struct list_head done;
@@ -339,6 +342,13 @@ struct kvm_async_pf {bool notpresent_injected; }; +#ifdef CONFIG_KVM_ASYNC_PF_SLOT +void kvm_async_pf_reset_slot (struct kvm_vcpu *vcpu); +void kvm_async_pf_add_slot (struct kvm_vcpu *vcpu,gfn_t gfn); +void kvm_async_pf_remove_slot (struct kvm_vcpu *vcpu,gfn_t gfn); +bool kvm_async_pf_find_slot (struct kvm_vcpu *vcpu,gfn_t gfn); +#endif +static inline bool kvm_check_async_pf_completion_queue (struct kvm_vcpu *vcpu) {return !list_empty_careful (&vcpu->async_pf.done);
@@ -350,6 +360,14 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, unsigned long hva, struct kvm_arch_async_pf *arch);int kvm_async_pf_wakeup_all (struct kvm_vcpu *vcpu);#else +static inline void kvm_async_pf_reset_slot (struct kvm_vcpu *vcpu) { } +static inline void kvm_async_pf_add_slot (struct kvm_vcpu *vcpu,gfn_t gfn) { } +static inline void kvm_async_pf_remove_slot (struct kvm_vcpu *vcpu,gfn_t gfn) { } +static inline bool kvm_async_pf_find_slot (struct kvm_vcpu *vcpu,gfn_t gfn) +{ +return false; +} +static inline bool kvm_check_async_pf_completion_queue (struct kvm_vcpu *vcpu) {return false;
virt/kvm/Kconfig +3 -0
@@ -23,6 +23,9 @@ config KVM_MMIO config KVM_ASYNC_PF bool +config KVM_ASYNC_PF_SLOT + bool + # Toggle to switch between direct notification and batch job config KVM_ASYNC_PF_SYNC bool
virt/kvm/async_pf.c +85 -0
97 lines not on this page · raw message
Signature · 1 line
2.23.0
Re: [PATCH v4 03/15] KVM: async_pf: Make GFN slot management generic
Hi Gavin,
Quoted 2 lines · Gavin Shan
It's not allowed to fire duplicate notification for same GFN on x86 platform, with help of a hash table. This mechanism is going
s/, with help of a hash table/this is achieved through a hash table
Quoted 1 line
to be used by arm64 and this makes the code generic and shareable
s/and this makes/.\n Turn the code generic
Quoted 5 lines
by multiple platforms.
* As this mechanism isn't needed by all platforms, a new kernel config option (
CONFIG_ASYNC_PF_SLOT) is introduced so that it can be disabled at compiling time.
compile time
Quoted 4 lines
* The code is basically copied from x86 platform and the functions are renamed to reflect the fact: (a) the input parameters are vCPU and GFN.
not for reset
(b) The operations are resetting, searching, adding
Quoted 1 line
and removing.
find, add, remove ops are renamed with _slot suffix
Quoted 30 lines
* Helper stub is also added on !CONFIG_KVM_ASYNC_PF because we're going to use
IS_ENABLED()instead of #ifdef on arm64 when the asynchronous page fault is supported.This is preparatory work to use the newly introduced functions on x86 platform and arm64 in subsequent patches.
Signed-off-by Gavin Shan <[email protected]>--- include/linux/kvm_host.h | 18 +++++++++ virt/kvm/Kconfig | 3 ++ virt/kvm/async_pf.c | 85 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 106 insertions(+)include/linux/kvm_host.h +3
-0@@ -298,6 +298,9 @@ struct kvm_vcpu { #ifdef CONFIG_KVM_ASYNC_PF struct { +#ifdef CONFIG_KVM_ASYNC_PF_SLOT + gfn_t gfns[ASYNC_PF_PER_VCPU]; +#endif u32 queued; struct list_head queue; struct list_head done;
include/linux/kvm_host.h struct kvm_async_pf { · line 346
Quoted 5 lines
include/linux/kvm_host.h +2
-0@@ -339,6 +342,13 @@ struct kvm_async_pf {bool notpresent_injected; }; +#ifdef CONFIG_KVM_ASYNC_PF_SLOT +void kvm_async_pf_reset_slot (struct kvm_vcpu *vcpu);
this does not reset a "slot" but the whole hash table. So to me this shouldn't be renamed with _slot suffix. reset_hash or reset_all_slots?
Quoted 130 lines
include/linux/kvm_host.h +13
-0+void kvm_async_pf_add_slot (struct kvm_vcpu *vcpu,gfn_t gfn); +void kvm_async_pf_remove_slot (struct kvm_vcpu *vcpu,gfn_t gfn); +bool kvm_async_pf_find_slot (struct kvm_vcpu *vcpu,gfn_t gfn); +#endif +static inline bool kvm_check_async_pf_completion_queue (struct kvm_vcpu *vcpu) {return !list_empty_careful (&vcpu->async_pf.done);@@ -350,6 +360,14 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, unsigned long hva, struct kvm_arch_async_pf *arch);int kvm_async_pf_wakeup_all (struct kvm_vcpu *vcpu);#else +static inline void kvm_async_pf_reset_slot (struct kvm_vcpu *vcpu) { } +static inline void kvm_async_pf_add_slot (struct kvm_vcpu *vcpu,gfn_t gfn) { } +static inline void kvm_async_pf_remove_slot (struct kvm_vcpu *vcpu,gfn_t gfn) { } +static inline bool kvm_async_pf_find_slot (struct kvm_vcpu *vcpu,gfn_t gfn) +{ +return false; +} +static inline bool kvm_check_async_pf_completion_queue (struct kvm_vcpu *vcpu) {return false;virt/kvm/Kconfig +3
-0@@ -23,6 +23,9 @@ config KVM_MMIO config KVM_ASYNC_PF bool +config KVM_ASYNC_PF_SLOT + bool + # Toggle to switch between direct notification and batch job config KVM_ASYNC_PF_SYNC boolvirt/kvm/async_pf.c +78
-0@@ -13,12 +13,97 @@#include <linux/module.h> #include <linux/mmu_context.h> #include <linux/sched/mm.h> +#ifdef CONFIG_KVM_ASYNC_PF_SLOT +#include <linux/hash.h> +#endif #include "async_pf.h" #include <trace/events/kvm.h> static struct kmem_cache *async_pf_cache; +#ifdef CONFIG_KVM_ASYNC_PF_SLOT +static inline u32 kvm_async_pf_hash (gfn_t gfn) +{ +BUILD_BUG_ON (!is_power_of_2 (ASYNC_PF_PER_VCPU )); + +return hash_32 (gfn &0xffffffff ,order_base_2 (ASYNC_PF_PER_VCPU )); +} + +static inline u32 kvm_async_pf_next_slot (u32 key) +{ +return (key +1 ) & (ASYNC_PF_PER_VCPU -1 ); +} + +static u32 kvm_async_pf_slot (struct kvm_vcpu *vcpu,gfn_t gfn) +{ +u32 key =kvm_async_pf_hash (gfn); +int i; + +for (i =0 ; i <ASYNC_PF_PER_VCPU && + (vcpu->async_pf.gfns[key] != gfn && + vcpu->async_pf.gfns[key] != ~0 ); i++) + key =kvm_async_pf_next_slot (key); + +return key; +} + +void kvm_async_pf_reset_slot (struct kvm_vcpu *vcpu) +{ +int i; + +for (i =0 ; i <ASYNC_PF_PER_VCPU ; i++) + vcpu->async_pf.gfns[i] = ~0 ; +} + +void kvm_async_pf_add_slot (struct kvm_vcpu *vcpu,gfn_t gfn) +{ +u32 key =kvm_async_pf_hash (gfn); + +while (vcpu->async_pf.gfns[key] != ~0 ) + key =kvm_async_pf_next_slot (key); + + vcpu->async_pf.gfns[key] = gfn; +} + +void kvm_async_pf_remove_slot (struct kvm_vcpu *vcpu,gfn_t gfn) +{ +u32 i, j, k; + + i = j =kvm_async_pf_slot (vcpu, gfn); + +if (WARN_ON_ONCE (vcpu->async_pf.gfns[i] != gfn)) +return ; + +while (true) { + vcpu->async_pf.gfns[i] = ~0 ; + +do { + j =kvm_async_pf_next_slot (j); +if (vcpu->async_pf.gfns[j] == ~0 ) +return ; + + k =kvm_async_pf_hash (vcpu->async_pf.gfns[j]); +/* +* k lies cyclically in ]i,j] +* | i.k.j | +* |....j i.k.| or |.k..j i...| +*/ + }while ((i <= j) ? (i < k && k <= j) : (i < k || k <= j)); + + vcpu->async_pf.gfns[i] = vcpu->async_pf.gfns[j]; + i = j; + } +} + +bool kvm_async_pf_find_slot (struct kvm_vcpu *vcpu,gfn_t gfn)
virt/kvm/async_pf.c line 109
Quoted 10 lines
virt/kvm/async_pf.c +7
-0+{ +u32 key =kvm_async_pf_slot (vcpu, gfn); + +return vcpu->async_pf.gfns[key] == gfn; +} +#endif /* CONFIG_KVM_ASYNC_PF_SLOT */ +int kvm_async_pf_init (void ) { async_pf_cache =KMEM_CACHE (kvm_async_pf,0 );
Thanks
Eric
Re: [PATCH v4 03/15] KVM: async_pf: Make GFN slot management generic
Hi Eric,
Quoted 4 lines · Eric Auger
Quoted 2 lines · Gavin Shan
It's not allowed to fire duplicate notification for same GFN on x86 platform, with help of a hash table. This mechanism is going
s/, with help of a hash table/this is achieved through a hash table
Quoted 8 lines
Quoted 1 line
to be used by arm64 and this makes the code generic and shareable
s/and this makes/.\n Turn the code generic
Quoted 5 lines
by multiple platforms.
* As this mechanism isn't needed by all platforms, a new kernel config option (
CONFIG_ASYNC_PF_SLOT) is introduced so that it can be disabled at compiling time.compile time
Ok.
Quoted 6 lines
Quoted 4 lines
* The code is basically copied from x86 platform and the functions are renamed to reflect the fact: (a) the input parameters are vCPU and GFN.
not for reset
(b) The operations are resetting, searching, adding
Ok.
Quoted 2 lines
Quoted 1 line
and removing.
find, add, remove ops are renamed with
_slotsuffix
Ok. The commit log will be improved based on your suggestions in next respin :)
Quoted 33 lines
Quoted 33 lines
* Helper stub is also added on !CONFIG_KVM_ASYNC_PF because we're going to use
IS_ENABLED()instead of #ifdef on arm64 when the asynchronous page fault is supported.This is preparatory work to use the newly introduced functions on x86 platform and arm64 in subsequent patches.
Signed-off-by Gavin Shan <[email protected]>--- include/linux/kvm_host.h | 18 +++++++++ virt/kvm/Kconfig | 3 ++ virt/kvm/async_pf.c | 85 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 106 insertions(+)include/linux/kvm_host.h +3
-0@@ -298,6 +298,9 @@ struct kvm_vcpu { #ifdef CONFIG_KVM_ASYNC_PF struct { +#ifdef CONFIG_KVM_ASYNC_PF_SLOT + gfn_t gfns[ASYNC_PF_PER_VCPU]; +#endif u32 queued; struct list_head queue; struct list_head done;@@ -339,6 +342,13 @@ struct kvm_async_pf {bool notpresent_injected; };
Quoted 4 lines
include/linux/kvm_host.h struct kvm_async_pf { · line 346
Quoted 2 lines
include/linux/kvm_host.h +2
-0+#ifdef CONFIG_KVM_ASYNC_PF_SLOT +void kvm_async_pf_reset_slot (struct kvm_vcpu *vcpu);this does not reset a "slot" but the whole hash table. So to me this shouldn't be renamed with
_slotsuffix.reset_hashorreset_all_slots?
Sure, lets have kvm_async_pf_reset_all_slots() in next respin.
Quoted 132 lines
Quoted 132 lines
include/linux/kvm_host.h +13
-0+void kvm_async_pf_add_slot (struct kvm_vcpu *vcpu,gfn_t gfn); +void kvm_async_pf_remove_slot (struct kvm_vcpu *vcpu,gfn_t gfn); +bool kvm_async_pf_find_slot (struct kvm_vcpu *vcpu,gfn_t gfn); +#endif +static inline bool kvm_check_async_pf_completion_queue (struct kvm_vcpu *vcpu) {return !list_empty_careful (&vcpu->async_pf.done);@@ -350,6 +360,14 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, unsigned long hva, struct kvm_arch_async_pf *arch);int kvm_async_pf_wakeup_all (struct kvm_vcpu *vcpu);#else +static inline void kvm_async_pf_reset_slot (struct kvm_vcpu *vcpu) { } +static inline void kvm_async_pf_add_slot (struct kvm_vcpu *vcpu,gfn_t gfn) { } +static inline void kvm_async_pf_remove_slot (struct kvm_vcpu *vcpu,gfn_t gfn) { } +static inline bool kvm_async_pf_find_slot (struct kvm_vcpu *vcpu,gfn_t gfn) +{ +return false; +} +static inline bool kvm_check_async_pf_completion_queue (struct kvm_vcpu *vcpu) {return false;virt/kvm/Kconfig +3
-0@@ -23,6 +23,9 @@ config KVM_MMIO config KVM_ASYNC_PF bool +config KVM_ASYNC_PF_SLOT + bool + # Toggle to switch between direct notification and batch job config KVM_ASYNC_PF_SYNC boolvirt/kvm/async_pf.c +81
-0@@ -13,12 +13,97 @@#include <linux/module.h> #include <linux/mmu_context.h> #include <linux/sched/mm.h> +#ifdef CONFIG_KVM_ASYNC_PF_SLOT +#include <linux/hash.h> +#endif #include "async_pf.h" #include <trace/events/kvm.h> static struct kmem_cache *async_pf_cache; +#ifdef CONFIG_KVM_ASYNC_PF_SLOT +static inline u32 kvm_async_pf_hash (gfn_t gfn) +{ +BUILD_BUG_ON (!is_power_of_2 (ASYNC_PF_PER_VCPU )); + +return hash_32 (gfn &0xffffffff ,order_base_2 (ASYNC_PF_PER_VCPU )); +} + +static inline u32 kvm_async_pf_next_slot (u32 key) +{ +return (key +1 ) & (ASYNC_PF_PER_VCPU -1 ); +} + +static u32 kvm_async_pf_slot (struct kvm_vcpu *vcpu,gfn_t gfn) +{ +u32 key =kvm_async_pf_hash (gfn); +int i; + +for (i =0 ; i <ASYNC_PF_PER_VCPU && + (vcpu->async_pf.gfns[key] != gfn && + vcpu->async_pf.gfns[key] != ~0 ); i++) + key =kvm_async_pf_next_slot (key); + +return key; +} + +void kvm_async_pf_reset_slot (struct kvm_vcpu *vcpu) +{ +int i; + +for (i =0 ; i <ASYNC_PF_PER_VCPU ; i++) + vcpu->async_pf.gfns[i] = ~0 ; +} + +void kvm_async_pf_add_slot (struct kvm_vcpu *vcpu,gfn_t gfn) +{ +u32 key =kvm_async_pf_hash (gfn); + +while (vcpu->async_pf.gfns[key] != ~0 ) + key =kvm_async_pf_next_slot (key); + + vcpu->async_pf.gfns[key] = gfn; +} + +void kvm_async_pf_remove_slot (struct kvm_vcpu *vcpu,gfn_t gfn) +{ +u32 i, j, k; + + i = j =kvm_async_pf_slot (vcpu, gfn); + +if (WARN_ON_ONCE (vcpu->async_pf.gfns[i] != gfn)) +return ; + +while (true) { + vcpu->async_pf.gfns[i] = ~0 ; + +do { + j =kvm_async_pf_next_slot (j); +if (vcpu->async_pf.gfns[j] == ~0 ) +return ; + + k =kvm_async_pf_hash (vcpu->async_pf.gfns[j]); +/* +* k lies cyclically in ]i,j] +* | i.k.j | +* |....j i.k.| or |.k..j i...| +*/ + }while ((i <= j) ? (i < k && k <= j) : (i < k || k <= j)); + + vcpu->async_pf.gfns[i] = vcpu->async_pf.gfns[j]; + i = j; + } +} + +bool kvm_async_pf_find_slot (struct kvm_vcpu *vcpu,gfn_t gfn) +{ +u32 key =kvm_async_pf_slot (vcpu, gfn); +
Quoted 8 lines
virt/kvm/async_pf.c line 109
Quoted 8 lines
virt/kvm/async_pf.c +4
-0+ return vcpu->async_pf.gfns[key] == gfn; +} +#endif /* CONFIG_KVM_ASYNC_PF_SLOT */ +int kvm_async_pf_init (void ) { async_pf_cache =KMEM_CACHE (kvm_async_pf,0 );
Thanks,
Gavin
Re: [PATCH v4 03/15] KVM: async_pf: Make GFN slot management generic
In reply to Gavin ShanHi Gavin,
Quoted 2 lines · Gavin Shan
It's not allowed to fire duplicate notification for same GFN on x86 platform, with help of a hash table. This mechanism is going
s/, with help of a hash table/this is achieved through a hash table
Quoted 1 line
to be used by arm64 and this makes the code generic and shareable
s/and this makes/.\n Turn the code generic
Quoted 5 lines
by multiple platforms.
* As this mechanism isn't needed by all platforms, a new kernel config option (
CONFIG_ASYNC_PF_SLOT) is introduced so that it can be disabled at compiling time.
compile time
Quoted 4 lines
* The code is basically copied from x86 platform and the functions are renamed to reflect the fact: (a) the input parameters are vCPU and GFN.
not for reset
(b) The operations are resetting, searching, adding
Quoted 1 line
and removing.
find, add, remove ops are renamed with _slot suffix
Quoted 30 lines
* Helper stub is also added on !CONFIG_KVM_ASYNC_PF because we're going to use
IS_ENABLED()instead of #ifdef on arm64 when the asynchronous page fault is supported.This is preparatory work to use the newly introduced functions on x86 platform and arm64 in subsequent patches.
Signed-off-by Gavin Shan <[email protected]>--- include/linux/kvm_host.h | 18 +++++++++ virt/kvm/Kconfig | 3 ++ virt/kvm/async_pf.c | 85 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 106 insertions(+)include/linux/kvm_host.h +3
-0@@ -298,6 +298,9 @@ struct kvm_vcpu { #ifdef CONFIG_KVM_ASYNC_PF struct { +#ifdef CONFIG_KVM_ASYNC_PF_SLOT + gfn_t gfns[ASYNC_PF_PER_VCPU]; +#endif u32 queued; struct list_head queue; struct list_head done;
include/linux/kvm_host.h struct kvm_async_pf { · line 346
Quoted 5 lines
include/linux/kvm_host.h +2
-0@@ -339,6 +342,13 @@ struct kvm_async_pf {bool notpresent_injected; }; +#ifdef CONFIG_KVM_ASYNC_PF_SLOT +void kvm_async_pf_reset_slot (struct kvm_vcpu *vcpu);
this does not reset a "slot" but the whole hash table. So to me this shouldn't be renamed with _slot suffix. reset_hash or reset_all_slots?
Quoted 130 lines
include/linux/kvm_host.h +13
-0+void kvm_async_pf_add_slot (struct kvm_vcpu *vcpu,gfn_t gfn); +void kvm_async_pf_remove_slot (struct kvm_vcpu *vcpu,gfn_t gfn); +bool kvm_async_pf_find_slot (struct kvm_vcpu *vcpu,gfn_t gfn); +#endif +static inline bool kvm_check_async_pf_completion_queue (struct kvm_vcpu *vcpu) {return !list_empty_careful (&vcpu->async_pf.done);@@ -350,6 +360,14 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, unsigned long hva, struct kvm_arch_async_pf *arch);int kvm_async_pf_wakeup_all (struct kvm_vcpu *vcpu);#else +static inline void kvm_async_pf_reset_slot (struct kvm_vcpu *vcpu) { } +static inline void kvm_async_pf_add_slot (struct kvm_vcpu *vcpu,gfn_t gfn) { } +static inline void kvm_async_pf_remove_slot (struct kvm_vcpu *vcpu,gfn_t gfn) { } +static inline bool kvm_async_pf_find_slot (struct kvm_vcpu *vcpu,gfn_t gfn) +{ +return false; +} +static inline bool kvm_check_async_pf_completion_queue (struct kvm_vcpu *vcpu) {return false;virt/kvm/Kconfig +3
-0@@ -23,6 +23,9 @@ config KVM_MMIO config KVM_ASYNC_PF bool +config KVM_ASYNC_PF_SLOT + bool + # Toggle to switch between direct notification and batch job config KVM_ASYNC_PF_SYNC boolvirt/kvm/async_pf.c +78
-0@@ -13,12 +13,97 @@#include <linux/module.h> #include <linux/mmu_context.h> #include <linux/sched/mm.h> +#ifdef CONFIG_KVM_ASYNC_PF_SLOT +#include <linux/hash.h> +#endif #include "async_pf.h" #include <trace/events/kvm.h> static struct kmem_cache *async_pf_cache; +#ifdef CONFIG_KVM_ASYNC_PF_SLOT +static inline u32 kvm_async_pf_hash (gfn_t gfn) +{ +BUILD_BUG_ON (!is_power_of_2 (ASYNC_PF_PER_VCPU )); + +return hash_32 (gfn &0xffffffff ,order_base_2 (ASYNC_PF_PER_VCPU )); +} + +static inline u32 kvm_async_pf_next_slot (u32 key) +{ +return (key +1 ) & (ASYNC_PF_PER_VCPU -1 ); +} + +static u32 kvm_async_pf_slot (struct kvm_vcpu *vcpu,gfn_t gfn) +{ +u32 key =kvm_async_pf_hash (gfn); +int i; + +for (i =0 ; i <ASYNC_PF_PER_VCPU && + (vcpu->async_pf.gfns[key] != gfn && + vcpu->async_pf.gfns[key] != ~0 ); i++) + key =kvm_async_pf_next_slot (key); + +return key; +} + +void kvm_async_pf_reset_slot (struct kvm_vcpu *vcpu) +{ +int i; + +for (i =0 ; i <ASYNC_PF_PER_VCPU ; i++) + vcpu->async_pf.gfns[i] = ~0 ; +} + +void kvm_async_pf_add_slot (struct kvm_vcpu *vcpu,gfn_t gfn) +{ +u32 key =kvm_async_pf_hash (gfn); + +while (vcpu->async_pf.gfns[key] != ~0 ) + key =kvm_async_pf_next_slot (key); + + vcpu->async_pf.gfns[key] = gfn; +} + +void kvm_async_pf_remove_slot (struct kvm_vcpu *vcpu,gfn_t gfn) +{ +u32 i, j, k; + + i = j =kvm_async_pf_slot (vcpu, gfn); + +if (WARN_ON_ONCE (vcpu->async_pf.gfns[i] != gfn)) +return ; + +while (true) { + vcpu->async_pf.gfns[i] = ~0 ; + +do { + j =kvm_async_pf_next_slot (j); +if (vcpu->async_pf.gfns[j] == ~0 ) +return ; + + k =kvm_async_pf_hash (vcpu->async_pf.gfns[j]); +/* +* k lies cyclically in ]i,j] +* | i.k.j | +* |....j i.k.| or |.k..j i...| +*/ + }while ((i <= j) ? (i < k && k <= j) : (i < k || k <= j)); + + vcpu->async_pf.gfns[i] = vcpu->async_pf.gfns[j]; + i = j; + } +} + +bool kvm_async_pf_find_slot (struct kvm_vcpu *vcpu,gfn_t gfn)
virt/kvm/async_pf.c line 109
Quoted 10 lines
virt/kvm/async_pf.c +7
-0+{ +u32 key =kvm_async_pf_slot (vcpu, gfn); + +return vcpu->async_pf.gfns[key] == gfn; +} +#endif /* CONFIG_KVM_ASYNC_PF_SLOT */ +int kvm_async_pf_init (void ) { async_pf_cache =KMEM_CACHE (kvm_async_pf,0 );
Thanks
Eric
_______________________________________________
kvmarm mailing list
[email protected]
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
PATCH v4 4/15 KVM: x86: Use generic async PF slot management
In reply to Gavin ShanThis uses the generic slot management mechanism for asynchronous page fault by enabling CONFIG_KVM_ASYNC_PF_SLOT because the private implementation is totally duplicate to the generic one.
The changes introduced by this is pretty mechanical and shouldn't cause any logical changes.
--- arch/x86/include/asm/kvm_host.h | 2 - arch/x86/kvm/Kconfig | 1 + arch/x86/kvm/mmu/mmu.c | 2 +- arch/x86/kvm/x86.c | 86 +++------------------------------ 4 files changed, 8 insertions(+), 83 deletions(-)
arch/x86/include/asm/kvm_host.h +0 -2
@@ -810,7 +810,6 @@ struct kvm_vcpu_arch {struct {bool halted; -gfn_t gfns[ASYNC_PF_PER_VCPU ];struct gfn_to_hva_cache data;u64 msr_en_val;/* MSR_KVM_ASYNC_PF_EN */ u64 msr_int_val;/* MSR_KVM_ASYNC_PF_INT */
@@ -1878,7 +1877,6 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work);void kvm_arch_async_page_present_queued (struct kvm_vcpu *vcpu);bool kvm_arch_can_dequeue_async_page_present (struct kvm_vcpu *vcpu); -extern bool kvm_find_async_pf_gfn (struct kvm_vcpu *vcpu,gfn_t gfn);int kvm_skip_emulated_instruction (struct kvm_vcpu *vcpu);int kvm_complete_insn_gp (struct kvm_vcpu *vcpu,int err);
arch/x86/kvm/Kconfig +1 -0
@@ -32,6 +32,7 @@ config KVM select HAVE_KVM_IRQ_ROUTING select HAVE_KVM_EVENTFD select KVM_ASYNC_PF + select KVM_ASYNC_PF_SLOT select USER_RETURN_NOTIFIER select KVM_MMIO select SCHED_INFO
arch/x86/kvm/mmu/mmu.c +1 -1
@@ -3799,7 +3799,7 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,if (!prefault &&kvm_can_do_async_pf (vcpu)) {trace_kvm_try_async_get_page (cr2_or_gpa, gfn); -if (kvm_find_async_pf_gfn (vcpu, gfn)) { +if (kvm_async_pf_find_slot (vcpu, gfn)) {trace_kvm_async_pf_doublefault (cr2_or_gpa, gfn);kvm_make_request (KVM_REQ_APF_HALT , vcpu);return true;
arch/x86/kvm/x86.c +6 -80
134 lines not on this page · raw message
Signature · 1 line
2.23.0
Re: [PATCH v4 04/15] KVM: x86: Use generic async PF slot management
Hi Gavin,
Quoted 1 line · Gavin Shan
This uses the generic slot management mechanism for asynchronous
Now we have moved the hash table management in the generic code, Use this latter ...
Quoted 5 lines
page fault by enabling
CONFIG_KVM_ASYNC_PF_SLOTbecause the private implementation is totally duplicate to the generic one.The changes introduced by this is pretty mechanical and shouldn't cause any logical changes.
suggest: No functional change intended.
Quoted 193 lines
Signed-off-by Gavin Shan <[email protected]>--- arch/x86/include/asm/kvm_host.h | 2 - arch/x86/kvm/Kconfig | 1 + arch/x86/kvm/mmu/mmu.c | 2 +- arch/x86/kvm/x86.c | 86 +++------------------------------ 4 files changed, 8 insertions(+), 83 deletions(-)arch/x86/include/asm/kvm_host.h +0
-2@@ -810,7 +810,6 @@ struct kvm_vcpu_arch {struct {bool halted; -gfn_t gfns[ASYNC_PF_PER_VCPU ];struct gfn_to_hva_cache data;u64 msr_en_val;/* MSR_KVM_ASYNC_PF_EN */ u64 msr_int_val;/* MSR_KVM_ASYNC_PF_INT */ @@ -1878,7 +1877,6 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work);void kvm_arch_async_page_present_queued (struct kvm_vcpu *vcpu);bool kvm_arch_can_dequeue_async_page_present (struct kvm_vcpu *vcpu); -extern bool kvm_find_async_pf_gfn (struct kvm_vcpu *vcpu,gfn_t gfn);int kvm_skip_emulated_instruction (struct kvm_vcpu *vcpu);int kvm_complete_insn_gp (struct kvm_vcpu *vcpu,int err);arch/x86/kvm/Kconfig +1
-0@@ -32,6 +32,7 @@ config KVM select HAVE_KVM_IRQ_ROUTING select HAVE_KVM_EVENTFD select KVM_ASYNC_PF + select KVM_ASYNC_PF_SLOT select USER_RETURN_NOTIFIER select KVM_MMIO select SCHED_INFOarch/x86/kvm/mmu/mmu.c +1
-1@@ -3799,7 +3799,7 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,if (!prefault &&kvm_can_do_async_pf (vcpu)) {trace_kvm_try_async_get_page (cr2_or_gpa, gfn); -if (kvm_find_async_pf_gfn (vcpu, gfn)) { +if (kvm_async_pf_find_slot (vcpu, gfn)) {trace_kvm_async_pf_doublefault (cr2_or_gpa, gfn);kvm_make_request (KVM_REQ_APF_HALT , vcpu);return true;arch/x86/kvm/x86.c +5
-79@@ -332,13 +332,6 @@ static struct kmem_cache *kvm_alloc_emulator_cache(void)static int emulator_fix_hypercall (struct x86_emulate_ctxt *ctxt); -static inline void kvm_async_pf_hash_reset (struct kvm_vcpu *vcpu) -{ -int i; -for (i =0 ; i <ASYNC_PF_PER_VCPU ; i++) - vcpu->arch.apf.gfns[i] = ~0 ; -} -static void kvm_on_user_return (struct user_return_notifier *urn) {unsigned slot;@@ -854,7 +847,7 @@ void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned lon {if ((cr0 ^ old_cr0) &X86_CR0_PG ) {kvm_clear_async_pf_completion_queue (vcpu); -kvm_async_pf_hash_reset (vcpu); +kvm_async_pf_reset_slot (vcpu); }if ((cr0 ^ old_cr0) &KVM_MMU_CR0_ROLE_BITS )@@ -3118,7 +3111,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)if (!kvm_pv_async_pf_enabled (vcpu)) {kvm_clear_async_pf_completion_queue (vcpu); -kvm_async_pf_hash_reset (vcpu); +kvm_async_pf_reset_slot (vcpu);return 0 ; }@@ -10704,7 +10697,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.pat =MSR_IA32_CR_PAT_DEFAULT ; -kvm_async_pf_hash_reset (vcpu); +kvm_async_pf_reset_slot (vcpu);kvm_pmu_init (vcpu); vcpu->arch.pending_external_vector =-1 ;@@ -10828,7 +10821,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)kvmclock_reset (vcpu);kvm_clear_async_pf_completion_queue (vcpu); -kvm_async_pf_hash_reset (vcpu); +kvm_async_pf_reset_slot (vcpu); vcpu->arch.apf.halted = false;if (vcpu->arch.guest_fpu &&kvm_mpx_supported ()) {@@ -11737,73 +11730,6 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)kvm_mmu_do_page_fault (vcpu, work->cr2_or_gpa,0 , true); } -static inline u32 kvm_async_pf_hash_fn (gfn_t gfn) -{ -BUILD_BUG_ON (!is_power_of_2 (ASYNC_PF_PER_VCPU )); - -return hash_32 (gfn &0xffffffff ,order_base_2 (ASYNC_PF_PER_VCPU )); -} - -static inline u32 kvm_async_pf_next_probe (u32 key) -{ -return (key +1 ) & (ASYNC_PF_PER_VCPU -1 ); -} - -static void kvm_add_async_pf_gfn (struct kvm_vcpu *vcpu,gfn_t gfn) -{ -u32 key =kvm_async_pf_hash_fn (gfn); - -while (vcpu->arch.apf.gfns[key] != ~0 ) - key =kvm_async_pf_next_probe (key); - - vcpu->arch.apf.gfns[key] = gfn; -} - -static u32 kvm_async_pf_gfn_slot (struct kvm_vcpu *vcpu,gfn_t gfn) -{ -int i; -u32 key =kvm_async_pf_hash_fn (gfn); - -for (i =0 ; i <ASYNC_PF_PER_VCPU && - (vcpu->arch.apf.gfns[key] != gfn && - vcpu->arch.apf.gfns[key] != ~0 ); i++) - key =kvm_async_pf_next_probe (key); - -return key; -} - -bool kvm_find_async_pf_gfn (struct kvm_vcpu *vcpu,gfn_t gfn) -{ -return vcpu->arch.apf.gfns[kvm_async_pf_gfn_slot (vcpu, gfn)] == gfn; -} - -static void kvm_del_async_pf_gfn (struct kvm_vcpu *vcpu,gfn_t gfn) -{ -u32 i, j, k; - - i = j =kvm_async_pf_gfn_slot (vcpu, gfn); - -if (WARN_ON_ONCE (vcpu->arch.apf.gfns[i] != gfn)) -return ; - -while (true) { - vcpu->arch.apf.gfns[i] = ~0 ; -do { - j =kvm_async_pf_next_probe (j); -if (vcpu->arch.apf.gfns[j] == ~0 ) -return ; - k =kvm_async_pf_hash_fn (vcpu->arch.apf.gfns[j]); -/* -* k lies cyclically in ]i,j] -* | i.k.j | -* |....j i.k.| or |.k..j i...| -*/ - }while ((i <= j) ? (i < k && k <= j) : (i < k || k <= j)); - vcpu->arch.apf.gfns[i] = vcpu->arch.apf.gfns[j]; - i = j; - } -} -static inline int apf_put_user_notpresent (struct kvm_vcpu *vcpu) {u32 reason =KVM_PV_REASON_PAGE_NOT_PRESENT ;@@ -11867,7 +11793,7 @@ bool kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,struct x86_exception fault;trace_kvm_async_pf_not_present (work->arch.token, work->cr2_or_gpa); -kvm_add_async_pf_gfn (vcpu, work->arch.gfn); +kvm_async_pf_add_slot (vcpu, work->arch.gfn);if (kvm_can_deliver_async_pf (vcpu) && !apf_put_user_notpresent (vcpu)) {
arch/x86/kvm/x86.c void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, · line 11836
Quoted 8 lines
arch/x86/kvm/x86.c +1
-1@@ -11904,7 +11830,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,if (work->wakeup_all) work->arch.token = ~0 ;/* broadcast wakeup */ else -kvm_del_async_pf_gfn (vcpu, work->arch.gfn); +kvm_async_pf_remove_slot (vcpu, work->arch.gfn);trace_kvm_async_pf_ready (work->arch.token, work->cr2_or_gpa); if ((work->wakeup_all || work->notpresent_injected) &&
Looks good to me
Eric
Re: [PATCH v4 04/15] KVM: x86: Use generic async PF slot management
Hi Eric,
Quoted 4 lines · Eric Auger
Quoted 1 line · Gavin Shan
This uses the generic slot management mechanism for asynchronous
Now we have moved the hash table management in the generic code, Use this latter ...
Ok.
Quoted 6 lines
Quoted 5 lines
page fault by enabling
CONFIG_KVM_ASYNC_PF_SLOTbecause the private implementation is totally duplicate to the generic one.The changes introduced by this is pretty mechanical and shouldn't cause any logical changes.
suggest: No functional change intended.
Ok. The commit log will be improved accordingly in next respin.
Quoted 199 lines
Quoted 199 lines
Signed-off-by Gavin Shan <[email protected]>--- arch/x86/include/asm/kvm_host.h | 2 - arch/x86/kvm/Kconfig | 1 + arch/x86/kvm/mmu/mmu.c | 2 +- arch/x86/kvm/x86.c | 86 +++------------------------------ 4 files changed, 8 insertions(+), 83 deletions(-)arch/x86/include/asm/kvm_host.h +0
-2@@ -810,7 +810,6 @@ struct kvm_vcpu_arch {struct {bool halted; -gfn_t gfns[ASYNC_PF_PER_VCPU ];struct gfn_to_hva_cache data;u64 msr_en_val;/* MSR_KVM_ASYNC_PF_EN */ u64 msr_int_val;/* MSR_KVM_ASYNC_PF_INT */ @@ -1878,7 +1877,6 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work);void kvm_arch_async_page_present_queued (struct kvm_vcpu *vcpu);bool kvm_arch_can_dequeue_async_page_present (struct kvm_vcpu *vcpu); -extern bool kvm_find_async_pf_gfn (struct kvm_vcpu *vcpu,gfn_t gfn);int kvm_skip_emulated_instruction (struct kvm_vcpu *vcpu);int kvm_complete_insn_gp (struct kvm_vcpu *vcpu,int err);arch/x86/kvm/Kconfig +1
-0@@ -32,6 +32,7 @@ config KVM select HAVE_KVM_IRQ_ROUTING select HAVE_KVM_EVENTFD select KVM_ASYNC_PF + select KVM_ASYNC_PF_SLOT select USER_RETURN_NOTIFIER select KVM_MMIO select SCHED_INFOarch/x86/kvm/mmu/mmu.c +1
-1@@ -3799,7 +3799,7 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,if (!prefault &&kvm_can_do_async_pf (vcpu)) {trace_kvm_try_async_get_page (cr2_or_gpa, gfn); -if (kvm_find_async_pf_gfn (vcpu, gfn)) { +if (kvm_async_pf_find_slot (vcpu, gfn)) {trace_kvm_async_pf_doublefault (cr2_or_gpa, gfn);kvm_make_request (KVM_REQ_APF_HALT , vcpu);return true;arch/x86/kvm/x86.c +6
-80@@ -332,13 +332,6 @@ static struct kmem_cache *kvm_alloc_emulator_cache(void)static int emulator_fix_hypercall (struct x86_emulate_ctxt *ctxt); -static inline void kvm_async_pf_hash_reset (struct kvm_vcpu *vcpu) -{ -int i; -for (i =0 ; i <ASYNC_PF_PER_VCPU ; i++) - vcpu->arch.apf.gfns[i] = ~0 ; -} -static void kvm_on_user_return (struct user_return_notifier *urn) {unsigned slot;@@ -854,7 +847,7 @@ void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned lon {if ((cr0 ^ old_cr0) &X86_CR0_PG ) {kvm_clear_async_pf_completion_queue (vcpu); -kvm_async_pf_hash_reset (vcpu); +kvm_async_pf_reset_slot (vcpu); }if ((cr0 ^ old_cr0) &KVM_MMU_CR0_ROLE_BITS )@@ -3118,7 +3111,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)if (!kvm_pv_async_pf_enabled (vcpu)) {kvm_clear_async_pf_completion_queue (vcpu); -kvm_async_pf_hash_reset (vcpu); +kvm_async_pf_reset_slot (vcpu);return 0 ; }@@ -10704,7 +10697,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.pat =MSR_IA32_CR_PAT_DEFAULT ; -kvm_async_pf_hash_reset (vcpu); +kvm_async_pf_reset_slot (vcpu);kvm_pmu_init (vcpu); vcpu->arch.pending_external_vector =-1 ;@@ -10828,7 +10821,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)kvmclock_reset (vcpu);kvm_clear_async_pf_completion_queue (vcpu); -kvm_async_pf_hash_reset (vcpu); +kvm_async_pf_reset_slot (vcpu); vcpu->arch.apf.halted = false;if (vcpu->arch.guest_fpu &&kvm_mpx_supported ()) {@@ -11737,73 +11730,6 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)kvm_mmu_do_page_fault (vcpu, work->cr2_or_gpa,0 , true); } -static inline u32 kvm_async_pf_hash_fn (gfn_t gfn) -{ -BUILD_BUG_ON (!is_power_of_2 (ASYNC_PF_PER_VCPU )); - -return hash_32 (gfn &0xffffffff ,order_base_2 (ASYNC_PF_PER_VCPU )); -} - -static inline u32 kvm_async_pf_next_probe (u32 key) -{ -return (key +1 ) & (ASYNC_PF_PER_VCPU -1 ); -} - -static void kvm_add_async_pf_gfn (struct kvm_vcpu *vcpu,gfn_t gfn) -{ -u32 key =kvm_async_pf_hash_fn (gfn); - -while (vcpu->arch.apf.gfns[key] != ~0 ) - key =kvm_async_pf_next_probe (key); - - vcpu->arch.apf.gfns[key] = gfn; -} - -static u32 kvm_async_pf_gfn_slot (struct kvm_vcpu *vcpu,gfn_t gfn) -{ -int i; -u32 key =kvm_async_pf_hash_fn (gfn); - -for (i =0 ; i <ASYNC_PF_PER_VCPU && - (vcpu->arch.apf.gfns[key] != gfn && - vcpu->arch.apf.gfns[key] != ~0 ); i++) - key =kvm_async_pf_next_probe (key); - -return key; -} - -bool kvm_find_async_pf_gfn (struct kvm_vcpu *vcpu,gfn_t gfn) -{ -return vcpu->arch.apf.gfns[kvm_async_pf_gfn_slot (vcpu, gfn)] == gfn; -} - -static void kvm_del_async_pf_gfn (struct kvm_vcpu *vcpu,gfn_t gfn) -{ -u32 i, j, k; - - i = j =kvm_async_pf_gfn_slot (vcpu, gfn); - -if (WARN_ON_ONCE (vcpu->arch.apf.gfns[i] != gfn)) -return ; - -while (true) { - vcpu->arch.apf.gfns[i] = ~0 ; -do { - j =kvm_async_pf_next_probe (j); -if (vcpu->arch.apf.gfns[j] == ~0 ) -return ; - k =kvm_async_pf_hash_fn (vcpu->arch.apf.gfns[j]); -/* -* k lies cyclically in ]i,j] -* | i.k.j | -* |....j i.k.| or |.k..j i...| -*/ - }while ((i <= j) ? (i < k && k <= j) : (i < k || k <= j)); - vcpu->arch.apf.gfns[i] = vcpu->arch.apf.gfns[j]; - i = j; - } -} -static inline int apf_put_user_notpresent (struct kvm_vcpu *vcpu) {u32 reason =KVM_PV_REASON_PAGE_NOT_PRESENT ;@@ -11867,7 +11793,7 @@ bool kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,struct x86_exception fault;trace_kvm_async_pf_not_present (work->arch.token, work->cr2_or_gpa); -kvm_add_async_pf_gfn (vcpu, work->arch.gfn); +kvm_async_pf_add_slot (vcpu, work->arch.gfn);if (kvm_can_deliver_async_pf (vcpu) && !apf_put_user_notpresent (vcpu)) {@@ -11904,7 +11830,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,if (work->wakeup_all) work->arch.token = ~0 ;/* broadcast wakeup */ else -kvm_del_async_pf_gfn (vcpu, work->arch.gfn); +kvm_async_pf_remove_slot (vcpu, work->arch.gfn);trace_kvm_async_pf_ready (work->arch.token, work->cr2_or_gpa);
Quoted 4 lines
arch/x86/kvm/x86.c void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, · line 11836
Quoted 2 lines
arch/x86/kvm/x86.c +0
-0if ((work->wakeup_all || work->notpresent_injected) &&Looks good to me
Ok.
Thanks,
Gavin
PATCH v4 5/15 KVM: arm64: Export kvm_handle_user_mem_abort()
In reply to Gavin ShanThe main work of stage-2 page fault is handled by user_mem_abort(). When asynchronous page fault is supported, one page fault need to be handled with two calls to this function. It means the page fault needs to be replayed asynchronously in that case.
* This renames the function to kvm_handle_user_mem_abort() and exports it.
* Add arguments @esr and @prefault to user_mem_abort(). @esr is the cached value of ESR_EL2 instead of fetching from the current vCPU when the page fault is replayed in scenario of asynchronous page fault. @prefault is used to indicate the page fault is replayed one or not.
* Define helper functions esr_dbat_*() in asm/esr.h to extract or check various fields of the passed ESR_EL2 value because those helper functions defined in asm/kvm_emulate.h assumes the ESR_EL2 value has been cached in vCPU struct. It won't be true on handling the replayed page fault in scenario of asynchronous page fault.
* Some helper functions defined in asm/kvm_emulate.h are used by mmu.c only and seem not to be used by other source file in near future. They are moved to mmu.c and renamed accordingly.
is_exec_fault: kvm_vcpu_trap_is_exec_fault
is_write_fault: kvm_is_write_fault()
esr_abt_fault_level: kvm_vcpu_trap_get_fault_level
--- arch/arm64/include/asm/esr.h | 6 ++++ arch/arm64/include/asm/kvm_emulate.h | 27 ++--------------- arch/arm64/include/asm/kvm_host.h | 4 +++ arch/arm64/kvm/mmu.c | 43 ++++++++++++++++++++++------ 4 files changed, 48 insertions(+), 32 deletions(-)
arch/arm64/include/asm/esr.h +6 -0
@@ -321,8 +321,14 @@ ESR_ELx_CP15_32_ISS_DIR_READ)#ifndef __ASSEMBLY__ +#include <linux/bitfield.h> #include <asm/types.h> +#define esr_dabt_fault_type (esr) (esr & ESR_ELx_FSC_TYPE) +#define esr_dabt_fault_level (esr) (FIELD_GET(ESR_ELx_FSC_LEVEL, esr)) +#define esr_dabt_is_wnr (esr) (!!(FIELD_GET(ESR_ELx_WNR, esr))) +#define esr_dabt_is_s1ptw (esr) (!!(FIELD_GET(ESR_ELx_S1PTW, esr))) +static inline bool esr_is_data_abort (u32 esr) {const u32 ec =ESR_ELx_EC (esr);
arch/arm64/include/asm/kvm_emulate.h +3 -24
@@ -285,13 +285,13 @@ static __always_inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu) static __always_inline bool kvm_vcpu_abt_iss1tw(const struct kvm_vcpu *vcpu) { -return !!(kvm_vcpu_get_esr (vcpu) & ESR_ELx_S1PTW); +return esr_dabt_is_s1ptw (kvm_vcpu_get_esr (vcpu)); }/* Always check for S1PTW *before* using this. */ static __always_inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu) { -return kvm_vcpu_get_esr (vcpu) & ESR_ELx_WNR; +return esr_dabt_is_wnr (kvm_vcpu_get_esr (vcpu)); }static inline bool kvm_vcpu_dabt_is_cm (const struct kvm_vcpu *vcpu)
@@ -320,11 +320,6 @@ static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu)return kvm_vcpu_trap_get_class (vcpu) == ESR_ELx_EC_IABT_LOW; } -static inline bool kvm_vcpu_trap_is_exec_fault (const struct kvm_vcpu *vcpu) -{ -return kvm_vcpu_trap_is_iabt (vcpu) && !kvm_vcpu_abt_iss1tw (vcpu); -} - static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu) {return kvm_vcpu_get_esr (vcpu) & ESR_ELx_FSC;
@@ -332,12 +327,7 @@ static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu) static __always_inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu) { -return kvm_vcpu_get_esr (vcpu) & ESR_ELx_FSC_TYPE; -} - -static __always_inline u8 kvm_vcpu_trap_get_fault_level(const struct kvm_vcpu *vcpu) -{ -return kvm_vcpu_get_esr (vcpu) & ESR_ELx_FSC_LEVEL; +return esr_dabt_fault_type (kvm_vcpu_get_esr (vcpu)); } static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu)
@@ -365,17 +355,6 @@ static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)return ESR_ELx_SYS64_ISS_RT (esr); } -static inline bool kvm_is_write_fault (struct kvm_vcpu *vcpu) -{ -if (kvm_vcpu_abt_iss1tw (vcpu)) -return true; - -if (kvm_vcpu_trap_is_iabt (vcpu)) -return false; - -return kvm_vcpu_dabt_iswrite (vcpu); -} -static inline unsigned long kvm_vcpu_get_mpidr_aff (struct kvm_vcpu *vcpu) {return vcpu_read_sys_reg (vcpu,MPIDR_EL1 ) &MPIDR_HWID_BITMASK ;
arch/arm64/include/asm/kvm_host.h +4 -0
@@ -606,6 +606,10 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,#define KVM_ARCH_WANT_MMU_NOTIFIER +int kvm_handle_user_mem_abort (struct kvm_vcpu *vcpu, +struct kvm_memory_slot *memslot, +phys_addr_t fault_ipa,unsigned long hva, +unsigned int esr,bool prefault);void kvm_arm_halt_guest (struct kvm *kvm);void kvm_arm_resume_guest (struct kvm *kvm);
arch/arm64/kvm/mmu.c +35 -8
72 lines not on this page · raw message
Signature · 1 line
2.23.0
Re: [PATCH v4 05/15] KVM: arm64: Export kvm_handle_user_mem_abort()
Hi Gavin,
Quoted 5 lines · Gavin Shan
The main work of stage-2 page fault is handled by
user_mem_abort(). When asynchronous page fault is supported, one page fault need to be handled with two calls to this function. It means the page fault needs to be replayed asynchronously in that case.
Quoted 8 lines
* This renames the function to
kvm_handle_user_mem_abort()and exports it.* Add arguments @esr and @prefault to
user_mem_abort(). @esr is the cached value ofESR_EL2instead of fetching from the current vCPU when the page fault is replayed in scenario of asynchronous page fault. @prefault is used to indicate the page fault is replayed one or not.
Also explain that fault_status arg is not needed anymore as derived from @esr because otherwise at first sight a distracted reviewer like me may have the impression you replaced fault_status by prefault while it is totally unrelated
Quoted 7 lines
* Define helper functions esr_dbat_*() in
asm/esr.hto extract or check various fields of the passedESR_EL2value because those helper functions defined inasm/kvm_emulate.hassumes theESR_EL2value has been cached in vCPU struct. It won't be true on handling the replayed page fault in scenario of asynchronous page fault.
I would introduce a seperate preliminary patch with those esr macros and changes to the call sites + changes below.
Quoted 142 lines
* Some helper functions defined in
asm/kvm_emulate.hare used bymmu.conly and seem not to be used by other source file in near future. They are moved tommu.cand renamed accordingly.>
is_exec_fault:kvm_vcpu_trap_is_exec_fault
is_write_fault:kvm_is_write_fault()Signed-off-by Gavin Shan <[email protected]>--- arch/arm64/include/asm/esr.h | 6 ++++ arch/arm64/include/asm/kvm_emulate.h | 27 ++--------------- arch/arm64/include/asm/kvm_host.h | 4 +++ arch/arm64/kvm/mmu.c | 43 ++++++++++++++++++++++------ 4 files changed, 48 insertions(+), 32 deletions(-)arch/arm64/include/asm/esr.h +6
-0@@ -321,8 +321,14 @@ ESR_ELx_CP15_32_ISS_DIR_READ)#ifndef __ASSEMBLY__ +#include <linux/bitfield.h> #include <asm/types.h> +#define esr_dabt_fault_type (esr) (esr & ESR_ELx_FSC_TYPE) +#define esr_dabt_fault_level (esr) (FIELD_GET(ESR_ELx_FSC_LEVEL, esr)) +#define esr_dabt_is_wnr (esr) (!!(FIELD_GET(ESR_ELx_WNR, esr))) +#define esr_dabt_is_s1ptw (esr) (!!(FIELD_GET(ESR_ELx_S1PTW, esr))) +static inline bool esr_is_data_abort (u32 esr) {const u32 ec =ESR_ELx_EC (esr);arch/arm64/include/asm/kvm_emulate.h +3
-24@@ -285,13 +285,13 @@ static __always_inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu) static __always_inline bool kvm_vcpu_abt_iss1tw(const struct kvm_vcpu *vcpu) { -return !!(kvm_vcpu_get_esr (vcpu) & ESR_ELx_S1PTW); +return esr_dabt_is_s1ptw (kvm_vcpu_get_esr (vcpu)); }/* Always check for S1PTW *before* using this. */ static __always_inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu) { -return kvm_vcpu_get_esr (vcpu) & ESR_ELx_WNR; +return esr_dabt_is_wnr (kvm_vcpu_get_esr (vcpu)); }static inline bool kvm_vcpu_dabt_is_cm (const struct kvm_vcpu *vcpu)@@ -320,11 +320,6 @@ static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu)return kvm_vcpu_trap_get_class (vcpu) == ESR_ELx_EC_IABT_LOW; } -static inline bool kvm_vcpu_trap_is_exec_fault (const struct kvm_vcpu *vcpu) -{ -return kvm_vcpu_trap_is_iabt (vcpu) && !kvm_vcpu_abt_iss1tw (vcpu); -} - static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu) {return kvm_vcpu_get_esr (vcpu) & ESR_ELx_FSC;@@ -332,12 +327,7 @@ static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu) static __always_inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu) { -return kvm_vcpu_get_esr (vcpu) & ESR_ELx_FSC_TYPE; -} - -static __always_inline u8 kvm_vcpu_trap_get_fault_level(const struct kvm_vcpu *vcpu) -{ -return kvm_vcpu_get_esr (vcpu) & ESR_ELx_FSC_LEVEL; +return esr_dabt_fault_type (kvm_vcpu_get_esr (vcpu)); } static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu)@@ -365,17 +355,6 @@ static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)return ESR_ELx_SYS64_ISS_RT (esr); } -static inline bool kvm_is_write_fault (struct kvm_vcpu *vcpu) -{ -if (kvm_vcpu_abt_iss1tw (vcpu)) -return true; - -if (kvm_vcpu_trap_is_iabt (vcpu)) -return false; - -return kvm_vcpu_dabt_iswrite (vcpu); -} -static inline unsigned long kvm_vcpu_get_mpidr_aff (struct kvm_vcpu *vcpu) {return vcpu_read_sys_reg (vcpu,MPIDR_EL1 ) &MPIDR_HWID_BITMASK ;arch/arm64/include/asm/kvm_host.h +4
-0@@ -606,6 +606,10 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,#define KVM_ARCH_WANT_MMU_NOTIFIER +int kvm_handle_user_mem_abort (struct kvm_vcpu *vcpu, +struct kvm_memory_slot *memslot, +phys_addr_t fault_ipa,unsigned long hva, +unsigned int esr,bool prefault);void kvm_arm_halt_guest (struct kvm *kvm);void kvm_arm_resume_guest (struct kvm *kvm);arch/arm64/kvm/mmu.c +18
-3@@ -892,9 +892,34 @@ static int sanitise_mte_tags(struct kvm *kvm, kvm_pfn_t pfn,return 0 ; } -static int user_mem_abort (struct kvm_vcpu *vcpu,phys_addr_t fault_ipa, -struct kvm_memory_slot *memslot,unsigned long hva, -unsigned long fault_status) +static inline bool is_exec_fault (unsigned int esr) +{ +if (ESR_ELx_EC (esr) != ESR_ELx_EC_IABT_LOW) +return false; + +if (esr_dabt_is_s1ptw (esr)) +return false; + +return true; +} + +static inline bool is_write_fault (unsigned int esr) +{ +if (esr_dabt_is_s1ptw (esr)) +return true; + +if (ESR_ELx_EC (esr) == ESR_ELx_EC_IABT_LOW) +return false;
arch/arm64/kvm/mmu.c static int sanitise_mte_tags(struct kvm *kvm, kvm_pfn_t pfn, · line 922
Quoted 10 lines
arch/arm64/kvm/mmu.c +10
-0+ +return esr_dabt_is_wnr (esr); +} + +int kvm_handle_user_mem_abort (struct kvm_vcpu *vcpu, +struct kvm_memory_slot *memslot, +phys_addr_t fault_ipa, +unsigned long hva, +unsigned int esr, +bool prefault)
you added the prefault arg but this latter is not used in the function? To me you shall introduce that change in a subsequent patch when relevant.
Quoted 32 lines
arch/arm64/kvm/mmu.c +5
-4{int ret =0 ;bool write_fault, writable, force_pte = false;@@ -909,14 +934,15 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,gfn_t gfn;kvm_pfn_t pfn;bool logging_active =memslot_is_logging (memslot); -unsigned long fault_level =kvm_vcpu_trap_get_fault_level (vcpu); +unsigned int fault_status =esr_dabt_fault_type (esr); +unsigned long fault_level =esr_dabt_fault_level (esr);unsigned long vma_pagesize, fault_granule;enum kvm_pgtable_prot prot =KVM_PGTABLE_PROT_R ;struct kvm_pgtable *pgt; fault_granule =1UL <<ARM64_HW_PGTABLE_LEVEL_SHIFT (fault_level); - write_fault =kvm_is_write_fault (vcpu); - exec_fault =kvm_vcpu_trap_is_exec_fault (vcpu); + write_fault =is_write_fault (kvm_vcpu_get_esr (vcpu)); + exec_fault =is_exec_fault (kvm_vcpu_get_esr (vcpu));VM_BUG_ON (write_fault && exec_fault);if (fault_status ==FSC_PERM && !write_fault && !exec_fault) {@@ -1176,7 +1202,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) gfn = fault_ipa >>PAGE_SHIFT ; memslot =gfn_to_memslot (vcpu->kvm, gfn); hva =gfn_to_hva_memslot_prot (memslot, gfn, &writable); - write_fault =kvm_is_write_fault (vcpu); + write_fault =is_write_fault (kvm_vcpu_get_esr (vcpu));if (kvm_is_error_hva (hva) || (write_fault && !writable)) {/* * The guest has put either its instructions or its page-tables
arch/arm64/kvm/mmu.c int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) · line 1264
Quoted 9 lines
arch/arm64/kvm/mmu.c +2
-1@@ -1231,7 +1257,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) goto out_unlock; } - ret =user_mem_abort (vcpu, fault_ipa, memslot, hva, fault_status); + ret =kvm_handle_user_mem_abort (vcpu, memslot, fault_ipa, hva, + kvm_vcpu_get_esr(vcpu), false);> if (ret == 0) ret =1 ; out:
Thanks
Eric
Re: [PATCH v4 05/15] KVM: arm64: Export kvm_handle_user_mem_abort()
Hi Eric,
Quoted 14 lines · Eric Auger
Quoted 5 lines · Gavin Shan
The main work of stage-2 page fault is handled by
user_mem_abort(). When asynchronous page fault is supported, one page fault need to be handled with two calls to this function. It means the page fault needs to be replayed asynchronously in that case.Quoted 8 lines
* This renames the function to
kvm_handle_user_mem_abort()and exports it.* Add arguments @esr and @prefault to
user_mem_abort(). @esr is the cached value ofESR_EL2instead of fetching from the current vCPU when the page fault is replayed in scenario of asynchronous page fault. @prefault is used to indicate the page fault is replayed one or not.
Quoted 4 lines
Also explain that
fault_statusarg is not needed anymore as derived from @esr because otherwise at first sight a distracted reviewer like me may have the impression you replacedfault_statusby prefault while it is totally unrelated
Yep, good point. Will do in next respin.
Quoted 9 lines
Quoted 7 lines
* Define helper functions esr_dbat_*() in
asm/esr.hto extract or check various fields of the passedESR_EL2value because those helper functions defined inasm/kvm_emulate.hassumes theESR_EL2value has been cached in vCPU struct. It won't be true on handling the replayed page fault in scenario of asynchronous page fault.I would introduce a seperate preliminary patch with those esr macros and changes to the call sites + changes below.
Ok. I will split this patch into two.
Quoted 146 lines
Quoted 146 lines
* Some helper functions defined in
asm/kvm_emulate.hare used bymmu.conly and seem not to be used by other source file in near future. They are moved tommu.cand renamed accordingly.>
is_exec_fault:kvm_vcpu_trap_is_exec_fault
is_write_fault:kvm_is_write_fault()Signed-off-by Gavin Shan <[email protected]>--- arch/arm64/include/asm/esr.h | 6 ++++ arch/arm64/include/asm/kvm_emulate.h | 27 ++--------------- arch/arm64/include/asm/kvm_host.h | 4 +++ arch/arm64/kvm/mmu.c | 43 ++++++++++++++++++++++------ 4 files changed, 48 insertions(+), 32 deletions(-)arch/arm64/include/asm/esr.h +6
-0@@ -321,8 +321,14 @@ ESR_ELx_CP15_32_ISS_DIR_READ)#ifndef __ASSEMBLY__ +#include <linux/bitfield.h> #include <asm/types.h> +#define esr_dabt_fault_type (esr) (esr & ESR_ELx_FSC_TYPE) +#define esr_dabt_fault_level (esr) (FIELD_GET(ESR_ELx_FSC_LEVEL, esr)) +#define esr_dabt_is_wnr (esr) (!!(FIELD_GET(ESR_ELx_WNR, esr))) +#define esr_dabt_is_s1ptw (esr) (!!(FIELD_GET(ESR_ELx_S1PTW, esr))) +static inline bool esr_is_data_abort (u32 esr) {const u32 ec =ESR_ELx_EC (esr);arch/arm64/include/asm/kvm_emulate.h +3
-24@@ -285,13 +285,13 @@ static __always_inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu) static __always_inline bool kvm_vcpu_abt_iss1tw(const struct kvm_vcpu *vcpu) { -return !!(kvm_vcpu_get_esr (vcpu) & ESR_ELx_S1PTW); +return esr_dabt_is_s1ptw (kvm_vcpu_get_esr (vcpu)); }/* Always check for S1PTW *before* using this. */ static __always_inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu) { -return kvm_vcpu_get_esr (vcpu) & ESR_ELx_WNR; +return esr_dabt_is_wnr (kvm_vcpu_get_esr (vcpu)); }static inline bool kvm_vcpu_dabt_is_cm (const struct kvm_vcpu *vcpu)@@ -320,11 +320,6 @@ static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu)return kvm_vcpu_trap_get_class (vcpu) == ESR_ELx_EC_IABT_LOW; } -static inline bool kvm_vcpu_trap_is_exec_fault (const struct kvm_vcpu *vcpu) -{ -return kvm_vcpu_trap_is_iabt (vcpu) && !kvm_vcpu_abt_iss1tw (vcpu); -} - static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu) {return kvm_vcpu_get_esr (vcpu) & ESR_ELx_FSC;@@ -332,12 +327,7 @@ static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu) static __always_inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu) { -return kvm_vcpu_get_esr (vcpu) & ESR_ELx_FSC_TYPE; -} - -static __always_inline u8 kvm_vcpu_trap_get_fault_level(const struct kvm_vcpu *vcpu) -{ -return kvm_vcpu_get_esr (vcpu) & ESR_ELx_FSC_LEVEL; +return esr_dabt_fault_type (kvm_vcpu_get_esr (vcpu)); } static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu)@@ -365,17 +355,6 @@ static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)return ESR_ELx_SYS64_ISS_RT (esr); } -static inline bool kvm_is_write_fault (struct kvm_vcpu *vcpu) -{ -if (kvm_vcpu_abt_iss1tw (vcpu)) -return true; - -if (kvm_vcpu_trap_is_iabt (vcpu)) -return false; - -return kvm_vcpu_dabt_iswrite (vcpu); -} -static inline unsigned long kvm_vcpu_get_mpidr_aff (struct kvm_vcpu *vcpu) {return vcpu_read_sys_reg (vcpu,MPIDR_EL1 ) &MPIDR_HWID_BITMASK ;arch/arm64/include/asm/kvm_host.h +4
-0@@ -606,6 +606,10 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,#define KVM_ARCH_WANT_MMU_NOTIFIER +int kvm_handle_user_mem_abort (struct kvm_vcpu *vcpu, +struct kvm_memory_slot *memslot, +phys_addr_t fault_ipa,unsigned long hva, +unsigned int esr,bool prefault);void kvm_arm_halt_guest (struct kvm *kvm);void kvm_arm_resume_guest (struct kvm *kvm);arch/arm64/kvm/mmu.c +22
-3@@ -892,9 +892,34 @@ static int sanitise_mte_tags(struct kvm *kvm, kvm_pfn_t pfn,return 0 ; } -static int user_mem_abort (struct kvm_vcpu *vcpu,phys_addr_t fault_ipa, -struct kvm_memory_slot *memslot,unsigned long hva, -unsigned long fault_status) +static inline bool is_exec_fault (unsigned int esr) +{ +if (ESR_ELx_EC (esr) != ESR_ELx_EC_IABT_LOW) +return false; + +if (esr_dabt_is_s1ptw (esr)) +return false; + +return true; +} + +static inline bool is_write_fault (unsigned int esr) +{ +if (esr_dabt_is_s1ptw (esr)) +return true; + +if (ESR_ELx_EC (esr) == ESR_ELx_EC_IABT_LOW) +return false; + +return esr_dabt_is_wnr (esr); +} +
Quoted 8 lines
arch/arm64/kvm/mmu.c static int sanitise_mte_tags(struct kvm *kvm, kvm_pfn_t pfn, · line 922
Quoted 6 lines
arch/arm64/kvm/mmu.c +6
-0+int kvm_handle_user_mem_abort (struct kvm_vcpu *vcpu, +struct kvm_memory_slot *memslot, +phys_addr_t fault_ipa, +unsigned long hva, +unsigned int esr, +bool prefault)you added the prefault arg but this latter is not used in the function? To me you shall introduce that change in a subsequent patch when relevant.
Yep, it's the preparatory patch for the following one. The other changes included in this patch are also preparatory work. Considering to the complexity of this patch, especially after we split it up into two patches. I think it's fine to keep the change here.
[PATCH v4 08/15] KVM: arm64: Support page-ready notification
Quoted 35 lines
Quoted 35 lines
arch/arm64/kvm/mmu.c +5
-4{int ret =0 ;bool write_fault, writable, force_pte = false;@@ -909,14 +934,15 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,gfn_t gfn;kvm_pfn_t pfn;bool logging_active =memslot_is_logging (memslot); -unsigned long fault_level =kvm_vcpu_trap_get_fault_level (vcpu); +unsigned int fault_status =esr_dabt_fault_type (esr); +unsigned long fault_level =esr_dabt_fault_level (esr);unsigned long vma_pagesize, fault_granule;enum kvm_pgtable_prot prot =KVM_PGTABLE_PROT_R ;struct kvm_pgtable *pgt; fault_granule =1UL <<ARM64_HW_PGTABLE_LEVEL_SHIFT (fault_level); - write_fault =kvm_is_write_fault (vcpu); - exec_fault =kvm_vcpu_trap_is_exec_fault (vcpu); + write_fault =is_write_fault (kvm_vcpu_get_esr (vcpu)); + exec_fault =is_exec_fault (kvm_vcpu_get_esr (vcpu));VM_BUG_ON (write_fault && exec_fault);if (fault_status ==FSC_PERM && !write_fault && !exec_fault) {@@ -1176,7 +1202,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) gfn = fault_ipa >>PAGE_SHIFT ; memslot =gfn_to_memslot (vcpu->kvm, gfn); hva =gfn_to_hva_memslot_prot (memslot, gfn, &writable); - write_fault =kvm_is_write_fault (vcpu); + write_fault =is_write_fault (kvm_vcpu_get_esr (vcpu));if (kvm_is_error_hva (hva) || (write_fault && !writable)) {/* * The guest has put either its instructions or its page-tables @@ -1231,7 +1257,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) goto out_unlock; }
Quoted 6 lines
arch/arm64/kvm/mmu.c int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
Quoted 6 lines
arch/arm64/kvm/mmu.c +2
-1- ret =user_mem_abort (vcpu, fault_ipa, memslot, hva, fault_status); + ret =kvm_handle_user_mem_abort (vcpu, memslot, fault_ipa, hva, + kvm_vcpu_get_esr(vcpu), false);> if (ret == 0) ret =1 ; out:
Thanks,
Gavin
PATCH v4 6/15 KVM: arm64: Add paravirtualization header files
In reply to Gavin ShanWe need put more stuff in the paravirtualization header files when the asynchronous page fault is supported. The generic header files can't meet the goal. This duplicate the generic header files to be our platform specific header files. It's the preparatory work to support the asynchronous page fault in the subsequent patches:
include/uapi/asm-generic/kvm_para.h
include/asm-generic/kvm_para.h
arch/arm64/include/uapi/asm/kvm_para.h
arch/arm64/include/asm/kvm_para.h
--- arch/arm64/include/asm/kvm_para.h | 27 ++++++++++++++++++++++++++ arch/arm64/include/uapi/asm/Kbuild | 2 -- arch/arm64/include/uapi/asm/kvm_para.h | 5 +++++ 3 files changed, 32 insertions(+), 2 deletions(-) create mode 100644 arch/arm64/include/asm/kvm_para.h create mode 100644 arch/arm64/include/uapi/asm/kvm_para.h
arch/arm64/include/asm/kvm_para.h new file +27 -0
@@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_ARM_KVM_PARA_H +#define _ASM_ARM_KVM_PARA_H + +#include <uapi/asm/kvm_para.h> + +static inline bool kvm_check_and_clear_guest_paused (void ) +{ +return false; +} + +static inline unsigned int kvm_arch_para_features (void ) +{ +return 0 ; +} + +static inline unsigned int kvm_arch_para_hints (void ) +{ +return 0 ; +} + +static inline bool kvm_para_available (void ) +{ +return false; +} + +#endif /* _ASM_ARM_KVM_PARA_H */
arch/arm64/include/uapi/asm/Kbuild +0 -2
@@ -1,3 +1 @@ # SPDX-License-Identifier: GPL-2.0 - -generic-y += kvm_para.h
arch/arm64/include/uapi/asm/kvm_para.h new file +5 -0
@@ -0,0 +1,5 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_ASM_ARM_KVM_PARA_H +#define _UAPI_ASM_ARM_KVM_PARA_H + +#endif /* _UAPI_ASM_ARM_KVM_PARA_H */
Signature · 1 line
2.23.0
Re: [PATCH v4 06/15] KVM: arm64: Add paravirtualization header files
Hi Gavin,
Quoted 3 lines · Gavin Shan
We need put more stuff in the paravirtualization header files when the asynchronous page fault is supported. The generic header files can't meet the goal.
you need to explain why
This duplicate the generic header files to be
s/This duplicate/Duplicate
Quoted 2 lines
our platform specific header files. It's the preparatory work to support the asynchronous page fault in the subsequent patches:
why duplication and not move. Shouldn't it be squashed with another subsequent patch?
Eric
Quoted 69 lines
include/uapi/asm-generic/kvm_para.h
include/asm-generic/kvm_para.h
arch/arm64/include/uapi/asm/kvm_para.h
arch/arm64/include/asm/kvm_para.hSigned-off-by Gavin Shan <[email protected]>--- arch/arm64/include/asm/kvm_para.h | 27 ++++++++++++++++++++++++++ arch/arm64/include/uapi/asm/Kbuild | 2 -- arch/arm64/include/uapi/asm/kvm_para.h | 5 +++++ 3 files changed, 32 insertions(+), 2 deletions(-) create mode 100644 arch/arm64/include/asm/kvm_para.h create mode 100644 arch/arm64/include/uapi/asm/kvm_para.harch/arm64/include/asm/kvm_para.h new file +27
-0@@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_ARM_KVM_PARA_H +#define _ASM_ARM_KVM_PARA_H + +#include <uapi/asm/kvm_para.h> + +static inline bool kvm_check_and_clear_guest_paused (void ) +{ +return false; +} + +static inline unsigned int kvm_arch_para_features (void ) +{ +return 0 ; +} + +static inline unsigned int kvm_arch_para_hints (void ) +{ +return 0 ; +} + +static inline bool kvm_para_available (void ) +{ +return false; +} + +#endif /* _ASM_ARM_KVM_PARA_H */ arch/arm64/include/uapi/asm/Kbuild +0
-2@@ -1,3 +1 @@ # SPDX-License-Identifier: GPL-2.0 - -generic-y += kvm_para.harch/arm64/include/uapi/asm/kvm_para.h new file +5
-0@@ -0,0 +1,5 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_ASM_ARM_KVM_PARA_H +#define _UAPI_ASM_ARM_KVM_PARA_H + +#endif /* _UAPI_ASM_ARM_KVM_PARA_H */
Re: [PATCH v4 06/15] KVM: arm64: Add paravirtualization header files
Hi Eric,
Quoted 7 lines · Eric Auger
Quoted 3 lines · Gavin Shan
We need put more stuff in the paravirtualization header files when the asynchronous page fault is supported. The generic header files can't meet the goal.
you need to explain why
This duplicate the generic header files to be
s/This duplicate/Duplicate
Ok.
Quoted 5 lines
Quoted 2 lines
our platform specific header files. It's the preparatory work to support the asynchronous page fault in the subsequent patches:
why duplication and not move. Shouldn't it be squashed with another subsequent patch?
It's also fine to squash this one to PATCH[v4 07/15]. My intent was to keep them separate to make PATCH[v4 07/17] a bit easier to be reviewed. So lets keep it as separate patch :)
Quoted 61 lines
Quoted 61 lines
include/uapi/asm-generic/kvm_para.h
include/asm-generic/kvm_para.h
arch/arm64/include/uapi/asm/kvm_para.h
arch/arm64/include/asm/kvm_para.hSigned-off-by Gavin Shan <[email protected]>--- arch/arm64/include/asm/kvm_para.h | 27 ++++++++++++++++++++++++++ arch/arm64/include/uapi/asm/Kbuild | 2 -- arch/arm64/include/uapi/asm/kvm_para.h | 5 +++++ 3 files changed, 32 insertions(+), 2 deletions(-)create mode 100644
arch/arm64/include/asm/kvm_para.hcreate mode 100644arch/arm64/include/uapi/asm/kvm_para.harch/arm64/include/asm/kvm_para.h new file +27
-0@@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_ARM_KVM_PARA_H +#define _ASM_ARM_KVM_PARA_H + +#include <uapi/asm/kvm_para.h> + +static inline bool kvm_check_and_clear_guest_paused (void ) +{ +return false; +} + +static inline unsigned int kvm_arch_para_features (void ) +{ +return 0 ; +} + +static inline unsigned int kvm_arch_para_hints (void ) +{ +return 0 ; +} + +static inline bool kvm_para_available (void ) +{ +return false; +} + +#endif /* _ASM_ARM_KVM_PARA_H */ arch/arm64/include/uapi/asm/Kbuild +0
-2@@ -1,3 +1 @@ # SPDX-License-Identifier: GPL-2.0 - -generic-y += kvm_para.harch/arm64/include/uapi/asm/kvm_para.h new file +0
-1--- /dev/null
Quoted 8 lines
arch/arm64/include/uapi/asm/kvm_para.h line 5
Quoted 8 lines
+++
b/arch/arm64/include/uapi/asm/kvm_para.harch/arm64/include/uapi/asm/kvm_para.h new file +5
-0@@ -0,0 +1,5 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_ASM_ARM_KVM_PARA_H +#define _UAPI_ASM_ARM_KVM_PARA_H + +#endif /* _UAPI_ASM_ARM_KVM_PARA_H */
Thanks,
Gavin
PATCH v4 7/15 KVM: arm64: Support page-not-present notification
In reply to Gavin ShanThe requested page might be not resident in memory during the stage-2 page fault. For example, the requested page could be resident in swap device (file). In this case, disk I/O is issued in order to fetch the requested page and it could take tens of milliseconds, even hundreds of milliseconds in extreme situation. During the period, the guest's vCPU is suspended until the requested page becomes ready. Actually, the something else on the guest's vCPU could be rescheduled during the period, so that the time slice isn't wasted as the guest's vCPU can see. This is the primary goal of the feature (Asynchronous Page Fault).
This supports delivery of page-not-present notification through SDEI event when the requested page isn't present. When the notification is received on the guest's vCPU, something else (another process) can be scheduled. The design is highlighted as below:
* There is dedicated memory region shared by host and guest. It's represented by "struct kvm_vcpu_pv_apf_data". The field @reason indicates the reason why the SDEI event is triggered, while the unique @token is used by guest to associate the event with the suspended process.
* One control block is associated with each guest's vCPU and it's represented by "struct kvm_arch_async_pf_control". It allows the guest to configure the functionality to indicate the situations where the host can deliver the page-not-present notification to kick off asyncrhonous page fault. Besides, runtime states are also maintained in this struct.
* Before the page-not-present notification is sent to the guest's vCPU, a worker is started and executed asynchronously on host, to fetch the requested page. "struct kvm{_,_arch}async_pf" is associated with the worker, to track the work.
The feature isn't enabled by CONFIG_KVM_ASYNC_PF yet. Also, the page-ready notification delivery and control path isn't implemented and will be done in the subsequent patches.
--- arch/arm64/include/asm/kvm_host.h | 52 +++++++++ arch/arm64/include/uapi/asm/kvm_para.h | 15 +++ arch/arm64/kvm/Makefile | 1 + arch/arm64/kvm/arm.c | 3 + arch/arm64/kvm/async_pf.c | 145 +++++++++++++++++++++++++ arch/arm64/kvm/mmu.c | 33 +++++- 6 files changed, 247 insertions(+), 2 deletions(-) create mode 100644 arch/arm64/kvm/async_pf.c
arch/arm64/include/asm/kvm_host.h +52 -0
@@ -283,6 +283,31 @@ struct vcpu_reset_state {bool reset; }; +/* Should be a power of two number */ +#define ASYNC_PF_PER_VCPU 64 + +/* +* The association of gfn and token. The token will be sent to guest as +* page fault address. Also, the guest could be in aarch32 mode. So its +* length should be 32-bits. +*/ +struct kvm_arch_async_pf { +u32 token; +gfn_t gfn; +u32 esr; +}; + +struct kvm_arch_async_pf_control { +struct gfn_to_hva_cache cache; +u64 control_block; +bool send_user_only; +u64 sdei_event_num; + +u16 id; +bool notpresent_pending; +u32 notpresent_token; +}; +struct kvm_vcpu_arch {struct kvm_cpu_context ctxt;void *sve_state;
@@ -346,6 +371,9 @@ struct kvm_vcpu_arch {/* SDEI support */ struct kvm_sdei_vcpu *sdei; +/* Asynchronous page fault support */ +struct kvm_arch_async_pf_control *apf; +/* * Guest registers we preserve during guest debugging. *
@@ -741,6 +769,30 @@ int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,long kvm_vm_ioctl_mte_copy_tags (struct kvm *kvm,struct kvm_arm_copy_mte_tags *copy_tags); +#ifdef CONFIG_KVM_ASYNC_PF +void kvm_arch_async_pf_create_vcpu (struct kvm_vcpu *vcpu); +bool kvm_arch_async_not_present_allowed (struct kvm_vcpu *vcpu); +bool kvm_arch_setup_async_pf (struct kvm_vcpu *vcpu, +u32 esr,gpa_t gpa,gfn_t gfn); +bool kvm_arch_async_page_not_present (struct kvm_vcpu *vcpu, +struct kvm_async_pf *work); +void kvm_arch_async_pf_destroy_vcpu (struct kvm_vcpu *vcpu); +#else +static inline void kvm_arch_async_pf_create_vcpu (struct kvm_vcpu *vcpu) { } +static inline void kvm_arch_async_pf_destroy_vcpu (struct kvm_vcpu *vcpu) { } + +static inline bool kvm_arch_async_not_present_allowed (struct kvm_vcpu *vcpu) +{ +return false; +} + +static inline bool kvm_arch_setup_async_pf (struct kvm_vcpu *vcpu, +u32 esr,gpa_t gpa,gfn_t gfn) +{ +return false; +} +#endif +/* Guest/host FPSIMD coordination helpers */ int kvm_arch_vcpu_run_map_fp (struct kvm_vcpu *vcpu);void kvm_arch_vcpu_load_fp (struct kvm_vcpu *vcpu);
arch/arm64/include/uapi/asm/kvm_para.h +15 -0
@@ -2,4 +2,19 @@#ifndef _UAPI_ASM_ARM_KVM_PARA_H#define _UAPI_ASM_ARM_KVM_PARA_H +#include <linux/types.h> + +/* Async PF */ +#define KVM_ASYNC_PF_ENABLED (1 << 0) +#define KVM_ASYNC_PF_SEND_ALWAYS (1 << 1) + +#define KVM_PV_REASON_PAGE_NOT_PRESENT 1 + +struct kvm_vcpu_pv_apf_data { +__u32 reason; +__u32 token; +__u8 pad[56 ]; +__u32 enabled; +}; +#endif /* _UAPI_ASM_ARM_KVM_PARA_H */
arch/arm64/kvm/Makefile +1 -0
@@ -25,3 +25,4 @@ kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \ vgic/vgic-its.o vgic/vgic-debug.o kvm-$(CONFIG_HW_PERF_EVENTS) += pmu-emul.o +kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o async_pf.o
arch/arm64/kvm/arm.c +3 -0
@@ -342,6 +342,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)kvm_sdei_create_vcpu (vcpu); +kvm_arch_async_pf_create_vcpu (vcpu); + vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu; err =kvm_vgic_vcpu_init (vcpu);
@@ -363,6 +365,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)kvm_mmu_free_memory_cache (&vcpu->arch.mmu_page_cache);kvm_timer_vcpu_terminate (vcpu);kvm_pmu_vcpu_destroy (vcpu); +kvm_arch_async_pf_destroy_vcpu (vcpu);kvm_sdei_destroy_vcpu (vcpu);kvm_arm_vcpu_destroy (vcpu);
arch/arm64/kvm/async_pf.c new file +145 -0
145 lines not on this page · raw message
arch/arm64/kvm/mmu.c +31 -2
@@ -914,6 +914,33 @@ static inline bool is_write_fault(unsigned int esr)return esr_dabt_is_wnr (esr); } +static bool try_async_pf (struct kvm_vcpu *vcpu,unsigned int esr, +gpa_t gpa,gfn_t gfn,kvm_pfn_t *pfn, +bool write,bool *writable,bool prefault) +{ +struct kvm_arch_async_pf_control *apf = vcpu->arch.apf; +struct kvm_memory_slot *slot =kvm_vcpu_gfn_to_memslot (vcpu, gfn); +bool async = false; + +if (apf) { +/* Bail if *pfn has correct page */ + *pfn =__gfn_to_pfn_memslot (slot, gfn, false, &async, + write, writable,NULL ); +if (!async) +return false; + +if (!prefault &&kvm_arch_async_not_present_allowed (vcpu)) { +if (kvm_async_pf_find_slot (vcpu, gfn) || +kvm_arch_setup_async_pf (vcpu, esr, gpa, gfn)) +return true; + } + } + + *pfn =__gfn_to_pfn_memslot (slot, gfn, false,NULL , + write, writable,NULL ); +return false; +} + int kvm_handle_user_mem_abort(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, phys_addr_t fault_ipa,
@@ -1035,8 +1062,10 @@ int kvm_handle_user_mem_abort(struct kvm_vcpu *vcpu,*/ smp_rmb (); - pfn =__gfn_to_pfn_memslot (memslot, gfn, false,NULL , - write_fault, &writable,NULL ); +if (try_async_pf (vcpu, esr, fault_ipa, gfn, &pfn, + write_fault, &writable, prefault)) +return 1 ; +if (pfn ==KVM_PFN_ERR_HWPOISON ) {kvm_send_hwpoison_signal (hva, vma_shift);return 0 ;
Signature · 6 lines
2.23.0 _______________________________________________ kvmarm mailing list [email protected] https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
Re: [PATCH v4 07/15] KVM: arm64: Support page-not-present notification
Hi Gavin,
Quoted 7 lines · Gavin Shan
The requested page might be not resident in memory during the stage-2 page fault. For example, the requested page could be resident in swap device (file). In this case, disk I/O is issued in order to fetch the requested page and it could take tens of milliseconds, even hundreds of milliseconds in extreme situation. During the period, the guest's vCPU is suspended until the requested page becomes ready. Actually, the something else on the guest's vCPU could be rescheduled during
s/the//
Quoted 15 lines
the period, so that the time slice isn't wasted as the guest's vCPU can see. This is the primary goal of the feature (Asynchronous Page Fault).
This supports delivery of page-not-present notification through SDEI event when the requested page isn't present. When the notification is received on the guest's vCPU, something else (another process) can be scheduled. The design is highlighted as below:
* There is dedicated memory region shared by host and guest. It's represented by "struct
kvm_vcpu_pv_apf_data". The field @reason indicates the reason why the SDEI event is triggered, while the unique @token is used by guest to associate the event with the suspended process.
Quoted 5 lines
* One control block is associated with each guest's vCPU and it's represented by "struct
kvm_arch_async_pf_control". It allows the guest to configure the functionality to indicate the situations where the host can deliver the page-not-present notification to kick off asyncrhonous page fault. Besides, runtime states are
asynchronous
Quoted 27 lines
also maintained in this struct.
* Before the page-not-present notification is sent to the guest's vCPU, a worker is started and executed asynchronously on host, to fetch the requested page. "struct kvm{_,_arch}async_pf" is associated with the worker, to track the work.
The feature isn't enabled by
CONFIG_KVM_ASYNC_PFyet. Also, the page-ready notification delivery and control path isn't implemented and will be done in the subsequent patches.Signed-off-by Gavin Shan <[email protected]>--- arch/arm64/include/asm/kvm_host.h | 52 +++++++++ arch/arm64/include/uapi/asm/kvm_para.h | 15 +++ arch/arm64/kvm/Makefile | 1 + arch/arm64/kvm/arm.c | 3 + arch/arm64/kvm/async_pf.c | 145 +++++++++++++++++++++++++ arch/arm64/kvm/mmu.c | 33 +++++- 6 files changed, 247 insertions(+), 2 deletions(-) create mode 100644 arch/arm64/kvm/async_pf.carch/arm64/include/asm/kvm_host.h +0
-0
arch/arm64/include/asm/kvm_host.h struct vcpu_reset_state { · line 291
Quoted 9 lines
arch/arm64/include/asm/kvm_host.h +6
-0@@ -283,6 +283,31 @@ struct vcpu_reset_state {bool reset; }; +/* Should be a power of two number */ +#define ASYNC_PF_PER_VCPU 64 + +/* +* The association of gfn and token. The token will be sent to guest as +* page fault address. Also, the guest could be in aarch32 mode. So its
s/as page fault address/together with page fault address?
Quoted 4 lines
arch/arm64/include/asm/kvm_host.h +4
-0+* length should be 32-bits. +*/ +struct kvm_arch_async_pf { +u32 token;
arch/arm64/include/asm/kvm_host.h struct vcpu_reset_state { · line 305
Quoted 10 lines
arch/arm64/include/asm/kvm_host.h +10
-0+gfn_t gfn; +u32 esr; +}; + +struct kvm_arch_async_pf_control { +struct gfn_to_hva_cache cache; +u64 control_block; +bool send_user_only; +u64 sdei_event_num; +
nit: spare empty line
Quoted 54 lines
arch/arm64/include/asm/kvm_host.h +32
-0+u16 id; +bool notpresent_pending; +u32 notpresent_token; +}; +struct kvm_vcpu_arch {struct kvm_cpu_context ctxt;void *sve_state;@@ -346,6 +371,9 @@ struct kvm_vcpu_arch {/* SDEI support */ struct kvm_sdei_vcpu *sdei; +/* Asynchronous page fault support */ +struct kvm_arch_async_pf_control *apf; +/* * Guest registers we preserve during guest debugging. * @@ -741,6 +769,30 @@ int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,long kvm_vm_ioctl_mte_copy_tags (struct kvm *kvm,struct kvm_arm_copy_mte_tags *copy_tags); +#ifdef CONFIG_KVM_ASYNC_PF +void kvm_arch_async_pf_create_vcpu (struct kvm_vcpu *vcpu); +bool kvm_arch_async_not_present_allowed (struct kvm_vcpu *vcpu); +bool kvm_arch_setup_async_pf (struct kvm_vcpu *vcpu, +u32 esr,gpa_t gpa,gfn_t gfn); +bool kvm_arch_async_page_not_present (struct kvm_vcpu *vcpu, +struct kvm_async_pf *work); +void kvm_arch_async_pf_destroy_vcpu (struct kvm_vcpu *vcpu); +#else +static inline void kvm_arch_async_pf_create_vcpu (struct kvm_vcpu *vcpu) { } +static inline void kvm_arch_async_pf_destroy_vcpu (struct kvm_vcpu *vcpu) { } + +static inline bool kvm_arch_async_not_present_allowed (struct kvm_vcpu *vcpu) +{ +return false; +} + +static inline bool kvm_arch_setup_async_pf (struct kvm_vcpu *vcpu, +u32 esr,gpa_t gpa,gfn_t gfn) +{ +return false; +} +#endif +/* Guest/host FPSIMD coordination helpers */ int kvm_arch_vcpu_run_map_fp (struct kvm_vcpu *vcpu);void kvm_arch_vcpu_load_fp (struct kvm_vcpu *vcpu);arch/arm64/include/uapi/asm/kvm_para.h +0
-0
arch/arm64/include/uapi/asm/kvm_para.h line 9
Quoted 8 lines
arch/arm64/include/uapi/asm/kvm_para.h +5
-0@@ -2,4 +2,19 @@#ifndef _UAPI_ASM_ARM_KVM_PARA_H#define _UAPI_ASM_ARM_KVM_PARA_H +#include <linux/types.h> + +/* Async PF */ +#define KVM_ASYNC_PF_ENABLED (1 << 0) +#define KVM_ASYNC_PF_SEND_ALWAYS (1 << 1)
The above define is not used in this patch. Besides can you explain what it aims at?
arch/arm64/include/uapi/asm/kvm_para.h line 14
Quoted 5 lines
arch/arm64/include/uapi/asm/kvm_para.h +5
-0+ +#define KVM_PV_REASON_PAGE_NOT_PRESENT 1 + +struct kvm_vcpu_pv_apf_data { +__u32 reason;
on x86 it was renamed into flags. Should we do the same right now?
Quoted 69 lines
arch/arm64/include/uapi/asm/kvm_para.h +5
-0+__u32 token; +__u8 pad[56 ]; + __u32 enabled; +}; +#endif /* _UAPI_ASM_ARM_KVM_PARA_H */ arch/arm64/kvm/Makefile +1
-0@@ -25,3 +25,4 @@ kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \ vgic/vgic-its.o vgic/vgic-debug.o kvm-$(CONFIG_HW_PERF_EVENTS) += pmu-emul.o +kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o async_pf.oarch/arm64/kvm/arm.c +3
-0@@ -342,6 +342,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)kvm_sdei_create_vcpu (vcpu); +kvm_arch_async_pf_create_vcpu (vcpu); + vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu; err =kvm_vgic_vcpu_init (vcpu);@@ -363,6 +365,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)kvm_mmu_free_memory_cache (&vcpu->arch.mmu_page_cache);kvm_timer_vcpu_terminate (vcpu);kvm_pmu_vcpu_destroy (vcpu); +kvm_arch_async_pf_destroy_vcpu (vcpu);kvm_sdei_destroy_vcpu (vcpu);kvm_arm_vcpu_destroy (vcpu);arch/arm64/kvm/async_pf.c new file +27
-0@@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* +* Asynchronous page fault support. +* +* Copyright (C) 2021 Red Hat, Inc. +* +* Author(s): Gavin Shan <[email protected]> +*/ + +#include <linux/arm-smccc.h> +#include <linux/kvm_host.h> +#include <asm/kvm_emulate.h> +#include <kvm/arm_hypercalls.h> +#include <kvm/arm_vgic.h> +#include <asm/kvm_sdei.h> + +static inline int read_cache (struct kvm_vcpu *vcpu,u32 offset,u32 *val) +{ +struct kvm *kvm = vcpu->kvm; +struct kvm_arch_async_pf_control *apf = vcpu->arch.apf; + +return kvm_read_guest_offset_cached (kvm, &apf->cache, + val, offset,sizeof (*val)); +} + +static inline int write_cache (struct kvm_vcpu *vcpu,u32 offset,u32 val) +{
arch/arm64/kvm/async_pf.c line 37
Quoted 10 lines
arch/arm64/kvm/async_pf.c new file +10
-0+struct kvm *kvm = vcpu->kvm; +struct kvm_arch_async_pf_control *apf = vcpu->arch.apf; + +return kvm_write_guest_offset_cached (kvm, &apf->cache, + &val, offset,sizeof (val)); +} + +void kvm_arch_async_pf_create_vcpu (struct kvm_vcpu *vcpu) +{ + vcpu->arch.apf =kzalloc (sizeof (*(vcpu->arch.apf)),GFP_KERNEL );
shouldn't we escalate the alloc failure and fail the vcpu creation instead of checking everywhere that apf is !null which is error prone. By the way I saw that on x86 this is a struct included in the vcpu one instead of a poinnter.
Quoted 8 lines
arch/arm64/kvm/async_pf.c new file +8
-0+} + +bool kvm_arch_async_not_present_allowed (struct kvm_vcpu *vcpu) +{ +struct kvm *kvm = vcpu->kvm; +struct kvm_arch_async_pf_control *apf = vcpu->arch.apf; +struct kvm_sdei_vcpu *vsdei = vcpu->arch.sdei; +u32 reason, token;
arch/arm64/kvm/async_pf.c line 55
Quoted 10 lines
arch/arm64/kvm/async_pf.c new file +10
-0+int ret; + +if (!apf || !(apf->control_block &KVM_ASYNC_PF_ENABLED )) +return false; + +if (apf->send_user_only &&vcpu_mode_priv (vcpu)) +return false; + +if (!irqchip_in_kernel (vcpu->kvm)) +return false;
can you explain why this is needed?
arch/arm64/kvm/async_pf.c line 58
Quoted 3 lines
arch/arm64/kvm/async_pf.c new file +3
-0+ +if (!vsdei || vsdei->critical_event || vsdei->normal_event) +return false;
don't you need some locking mechanism to void that vdsei fields change after that check? At the moment we may have a single SDEI num but nothing prevents from adding others in the future, right?
arch/arm64/kvm/async_pf.c line 67
Quoted 9 lines
arch/arm64/kvm/async_pf.c new file +9
-0+ +/* Pending page fault, which isn't acknowledged by guest */ + ret =read_cache (vcpu, offsetof(struct kvm_vcpu_pv_apf_data , reason), + &reason); +if (ret) { +kvm_err ("%s: Error %d to read reason (%d-%d)\n" , + __func__, ret, kvm->userspace_pid, vcpu->vcpu_idx); +return false; + }
x86 code does not have those kvm_err(). You may simply drop them.
arch/arm64/kvm/async_pf.c line 77
Quoted 10 lines
arch/arm64/kvm/async_pf.c new file +10
-0+ + ret =read_cache (vcpu, offsetof(struct kvm_vcpu_pv_apf_data , token), + &token); +if (ret) { +kvm_err ("%s: Error %d to read token %d-%d\n" , + __func__, ret, kvm->userspace_pid, vcpu->vcpu_idx); +return false; + } + +if (reason || token)
can't the token be null?
Quoted 11 lines
arch/arm64/kvm/async_pf.c new file +11
-0+return false; + +return true; +} + +bool kvm_arch_setup_async_pf (struct kvm_vcpu *vcpu, +u32 esr,gpa_t gpa,gfn_t gfn) +{ +struct kvm_arch_async_pf_control *apf = vcpu->arch.apf; +struct kvm_arch_async_pf arch; +unsigned long hva =kvm_vcpu_gfn_to_hva (vcpu, gfn);
arch/arm64/kvm/async_pf.c line 98
Quoted 10 lines
arch/arm64/kvm/async_pf.c new file +10
-0+ + arch.token = (apf->id++ <<12 ) | vcpu->vcpu_id; + arch.gfn = gfn; + arch.esr = esr; + +return kvm_setup_async_pf (vcpu, gpa, hva, &arch); +} + +/* +* It's guaranteed that no pending asynchronous page fault when this is
that no APF is pending
Quoted 6 lines
arch/arm64/kvm/async_pf.c new file +6
-0+* called. It means all previous issued asynchronous page faults have +* been acknowledged. +*/ +bool kvm_arch_async_page_not_present (struct kvm_vcpu *vcpu, +struct kvm_async_pf *work) +{
arch/arm64/kvm/async_pf.c line 114
Quoted 10 lines
arch/arm64/kvm/async_pf.c new file +10
-0+struct kvm *kvm = vcpu->kvm; +struct kvm_arch_async_pf_control *apf = vcpu->arch.apf; +int ret; + +kvm_async_pf_add_slot (vcpu, work->arch.gfn); + + ret =write_cache (vcpu, offsetof(struct kvm_vcpu_pv_apf_data , token), + work->arch.token); +if (ret) { + kvm_err("%s: Error %d to write token (%d-%d %08x)\n",
kvm_err's may be dropped
Quoted 38 lines
arch/arm64/kvm/async_pf.c new file +31
-0+ __func__, ret, kvm->userspace_pid, + vcpu->vcpu_idx, work->arch.token); + goto fail; + } + + ret =write_cache (vcpu, offsetof(struct kvm_vcpu_pv_apf_data , reason), +KVM_PV_REASON_PAGE_NOT_PRESENT ); +if (ret) { +kvm_err ("%s: Error %d to write reason (%d-%d %08x)\n" , + __func__, ret, kvm->userspace_pid, + vcpu->vcpu_idx, work->arch.token); + goto fail; + } + + apf->notpresent_pending = true; + apf->notpresent_token = work->arch.token; + +return !kvm_sdei_inject (vcpu, apf->sdei_event_num, true); + +fail: +write_cache (vcpu, offsetof(struct kvm_vcpu_pv_apf_data , token),0 ); +write_cache (vcpu, offsetof(struct kvm_vcpu_pv_apf_data , reason),0 ); +kvm_async_pf_remove_slot (vcpu, work->arch.gfn); +return false; +} + +void kvm_arch_async_pf_destroy_vcpu (struct kvm_vcpu *vcpu) +{ +kfree (vcpu->arch.apf); + vcpu->arch.apf =NULL ; +}arch/arm64/kvm/mmu.c +0
-0@@ -914,6 +914,33 @@ static inline bool is_write_fault(unsigned int esr)return esr_dabt_is_wnr (esr); }
arch/arm64/kvm/mmu.c static inline bool is_write_fault(unsigned int esr) · line 925
Quoted 10 lines
arch/arm64/kvm/mmu.c +9
-0+static bool try_async_pf (struct kvm_vcpu *vcpu,unsigned int esr, +gpa_t gpa,gfn_t gfn,kvm_pfn_t *pfn, +bool write,bool *writable,bool prefault) +{ +struct kvm_arch_async_pf_control *apf = vcpu->arch.apf; +struct kvm_memory_slot *slot =kvm_vcpu_gfn_to_memslot (vcpu, gfn); +bool async = false; + +if (apf) {
checking apf each time for a potential kacl of resource at vcpu creation look heavy to me.
arch/arm64/kvm/mmu.c static inline bool is_write_fault(unsigned int esr) · line 926
Quoted 1 line
arch/arm64/kvm/mmu.c +1
-0+/* Bail if *pfn has correct page */
s/bail/bail out? Comment rather related to !async check.
arch/arm64/kvm/mmu.c static inline bool is_write_fault(unsigned int esr) · line 932
Quoted 6 lines
arch/arm64/kvm/mmu.c +6
-0+ *pfn =__gfn_to_pfn_memslot (slot, gfn, false, &async, + write, writable,NULL ); +if (!async) +return false; + +if (!prefault &&kvm_arch_async_not_present_allowed (vcpu)) {
x86 kvm_can_do_async_pf() naming look more straightforward than kvm_arch_async_not_present_allowed
arch/arm64/kvm/mmu.c static inline bool is_write_fault(unsigned int esr) · line 933
Quoted 1 line
arch/arm64/kvm/mmu.c +1
-0+ if (kvm_async_pf_find_slot(vcpu, gfn) ||
x86 has some trace points. You may envision to add some, maybe later on.
Quoted 17 lines
arch/arm64/kvm/mmu.c +10
-0+ kvm_arch_setup_async_pf(vcpu, esr, gpa, gfn)) +return true; + } + } + + *pfn =__gfn_to_pfn_memslot (slot, gfn, false,NULL , + write, writable,NULL ); +return false; +} + int kvm_handle_user_mem_abort(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, phys_addr_t fault_ipa,@@ -1035,8 +1062,10 @@ int kvm_handle_user_mem_abort(struct kvm_vcpu *vcpu,*/ smp_rmb ();
arch/arm64/kvm/mmu.c int kvm_handle_user_mem_abort(struct kvm_vcpu *vcpu, · line 1071
Quoted 10 lines
arch/arm64/kvm/mmu.c +4
-2- pfn =__gfn_to_pfn_memslot (memslot, gfn, false,NULL , - write_fault, &writable,NULL ); +if (try_async_pf (vcpu, esr, fault_ipa, gfn, &pfn, + write_fault, &writable, prefault)) +return 1 ; +if (pfn ==KVM_PFN_ERR_HWPOISON ) {kvm_send_hwpoison_signal (hva, vma_shift);return 0 ;
Eric
Re: [PATCH v4 07/15] KVM: arm64: Support page-not-present notification
Hi Eric,
Quoted 9 lines · Eric Auger
Quoted 7 lines · Gavin Shan
The requested page might be not resident in memory during the stage-2 page fault. For example, the requested page could be resident in swap device (file). In this case, disk I/O is issued in order to fetch the requested page and it could take tens of milliseconds, even hundreds of milliseconds in extreme situation. During the period, the guest's vCPU is suspended until the requested page becomes ready. Actually, the something else on the guest's vCPU could be rescheduled during
s/the//
ok.
Quoted 15 lines
Quoted 15 lines
the period, so that the time slice isn't wasted as the guest's vCPU can see. This is the primary goal of the feature (Asynchronous Page Fault).
This supports delivery of page-not-present notification through SDEI event when the requested page isn't present. When the notification is received on the guest's vCPU, something else (another process) can be scheduled. The design is highlighted as below:
* There is dedicated memory region shared by host and guest. It's represented by "struct
kvm_vcpu_pv_apf_data". The field @reason indicates the reason why the SDEI event is triggered, while the unique @token is used by guest to associate the event with the suspended process.
Quoted 6 lines
Quoted 5 lines
* One control block is associated with each guest's vCPU and it's represented by "struct
kvm_arch_async_pf_control". It allows the guest to configure the functionality to indicate the situations where the host can deliver the page-not-present notification to kick off asyncrhonous page fault. Besides, runtime states areasynchronous
ok.
Quoted 37 lines
Quoted 27 lines
also maintained in this struct.
* Before the page-not-present notification is sent to the guest's vCPU, a worker is started and executed asynchronously on host, to fetch the requested page. "struct kvm{_,_arch}async_pf" is associated with the worker, to track the work.
The feature isn't enabled by
CONFIG_KVM_ASYNC_PFyet. Also, the page-ready notification delivery and control path isn't implemented and will be done in the subsequent patches.Signed-off-by Gavin Shan <[email protected]>--- arch/arm64/include/asm/kvm_host.h | 52 +++++++++ arch/arm64/include/uapi/asm/kvm_para.h | 15 +++ arch/arm64/kvm/Makefile | 1 + arch/arm64/kvm/arm.c | 3 + arch/arm64/kvm/async_pf.c | 145 +++++++++++++++++++++++++ arch/arm64/kvm/mmu.c | 33 +++++- 6 files changed, 247 insertions(+), 2 deletions(-)create mode 100644
arch/arm64/kvm/async_pf.carch/arm64/include/asm/kvm_host.h +0
-0arch/arm64/include/asm/kvm_host.h struct vcpu_reset_state { · line 291
Quoted 9 lines
arch/arm64/include/asm/kvm_host.h +6
-0@@ -283,6 +283,31 @@ struct vcpu_reset_state {bool reset; }; +/* Should be a power of two number */ +#define ASYNC_PF_PER_VCPU 64 + +/* +* The association of gfn and token. The token will be sent to guest as +* page fault address. Also, the guest could be in aarch32 mode. So its s/as page fault address/together with page fault address?
Quoted 15 lines
Quoted 4 lines
arch/arm64/include/asm/kvm_host.h +4
-0+* length should be 32-bits. +*/ +struct kvm_arch_async_pf { +u32 token;arch/arm64/include/asm/kvm_host.h struct vcpu_reset_state { · line 305
Quoted 10 lines
arch/arm64/include/asm/kvm_host.h +10
-0+gfn_t gfn; +u32 esr; +}; + +struct kvm_arch_async_pf_control { +struct gfn_to_hva_cache cache; +u64 control_block; +bool send_user_only; +u64 sdei_event_num; +nit: spare empty line
It's intended because I want to keep two blocks separate due to their usages :)
Quoted 57 lines
Quoted 57 lines
arch/arm64/include/asm/kvm_host.h +32
-0+u16 id; +bool notpresent_pending; +u32 notpresent_token; +}; +struct kvm_vcpu_arch {struct kvm_cpu_context ctxt;void *sve_state;@@ -346,6 +371,9 @@ struct kvm_vcpu_arch {/* SDEI support */ struct kvm_sdei_vcpu *sdei; +/* Asynchronous page fault support */ +struct kvm_arch_async_pf_control *apf; +/* * Guest registers we preserve during guest debugging. * @@ -741,6 +769,30 @@ int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,long kvm_vm_ioctl_mte_copy_tags (struct kvm *kvm,struct kvm_arm_copy_mte_tags *copy_tags); +#ifdef CONFIG_KVM_ASYNC_PF +void kvm_arch_async_pf_create_vcpu (struct kvm_vcpu *vcpu); +bool kvm_arch_async_not_present_allowed (struct kvm_vcpu *vcpu); +bool kvm_arch_setup_async_pf (struct kvm_vcpu *vcpu, +u32 esr,gpa_t gpa,gfn_t gfn); +bool kvm_arch_async_page_not_present (struct kvm_vcpu *vcpu, +struct kvm_async_pf *work); +void kvm_arch_async_pf_destroy_vcpu (struct kvm_vcpu *vcpu); +#else +static inline void kvm_arch_async_pf_create_vcpu (struct kvm_vcpu *vcpu) { } +static inline void kvm_arch_async_pf_destroy_vcpu (struct kvm_vcpu *vcpu) { } + +static inline bool kvm_arch_async_not_present_allowed (struct kvm_vcpu *vcpu) +{ +return false; +} + +static inline bool kvm_arch_setup_async_pf (struct kvm_vcpu *vcpu, +u32 esr,gpa_t gpa,gfn_t gfn) +{ +return false; +} +#endif +/* Guest/host FPSIMD coordination helpers */ int kvm_arch_vcpu_run_map_fp (struct kvm_vcpu *vcpu);void kvm_arch_vcpu_load_fp (struct kvm_vcpu *vcpu);arch/arm64/include/uapi/asm/kvm_para.h +0
-0@@ -2,4 +2,19 @@#ifndef _UAPI_ASM_ARM_KVM_PARA_H#define _UAPI_ASM_ARM_KVM_PARA_H
Quoted 7 lines
arch/arm64/include/uapi/asm/kvm_para.h line 9
Quoted 5 lines
arch/arm64/include/uapi/asm/kvm_para.h +5
-0+#include <linux/types.h> + +/* Async PF */ +#define KVM_ASYNC_PF_ENABLED (1 << 0) +#define KVM_ASYNC_PF_SEND_ALWAYS (1 << 1)The above define is not used in this patch. Besides can you explain what it aims at?
Yep, this should be dropped. When host receives stage-2 page fault, it's unaware what context the guest is in. The guest can be in user or kernel mode. It's safe to preempt (interrupt) the guest if it's in user mode because of async PF. However, it's not safe to do when the guest in kernel mode.
It seems it's supported on x86, but I didn't look into the details. So we don't support it on ARM64 for now. It can be supported in future if needed.
Quoted 81 lines
arch/arm64/include/uapi/asm/kvm_para.h line 14
Quoted 5 lines
arch/arm64/include/uapi/asm/kvm_para.h +5
-0+ +#define KVM_PV_REASON_PAGE_NOT_PRESENT 1 + +struct kvm_vcpu_pv_apf_data { +__u32 reason;on x86 it was renamed into flags. Should we do the same right now?
Quoted 75 lines
arch/arm64/include/uapi/asm/kvm_para.h +5
-0+__u32 token; +__u8 pad[56 ]; + __u32 enabled; +}; +#endif /* _UAPI_ASM_ARM_KVM_PARA_H */ arch/arm64/kvm/Makefile +1
-0@@ -25,3 +25,4 @@ kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \ vgic/vgic-its.o vgic/vgic-debug.o kvm-$(CONFIG_HW_PERF_EVENTS) += pmu-emul.o +kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o async_pf.oarch/arm64/kvm/arm.c +3
-0@@ -342,6 +342,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)kvm_sdei_create_vcpu (vcpu); +kvm_arch_async_pf_create_vcpu (vcpu); + vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu; err =kvm_vgic_vcpu_init (vcpu);@@ -363,6 +365,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)kvm_mmu_free_memory_cache (&vcpu->arch.mmu_page_cache);kvm_timer_vcpu_terminate (vcpu);kvm_pmu_vcpu_destroy (vcpu); +kvm_arch_async_pf_destroy_vcpu (vcpu);kvm_sdei_destroy_vcpu (vcpu);kvm_arm_vcpu_destroy (vcpu);arch/arm64/kvm/async_pf.c new file +33
-0@@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* +* Asynchronous page fault support. +* +* Copyright (C) 2021 Red Hat, Inc. +* +* Author(s): Gavin Shan <[email protected]> +*/ + +#include <linux/arm-smccc.h> +#include <linux/kvm_host.h> +#include <asm/kvm_emulate.h> +#include <kvm/arm_hypercalls.h> +#include <kvm/arm_vgic.h> +#include <asm/kvm_sdei.h> + +static inline int read_cache (struct kvm_vcpu *vcpu,u32 offset,u32 *val) +{ +struct kvm *kvm = vcpu->kvm; +struct kvm_arch_async_pf_control *apf = vcpu->arch.apf; + +return kvm_read_guest_offset_cached (kvm, &apf->cache, + val, offset,sizeof (*val)); +} + +static inline int write_cache (struct kvm_vcpu *vcpu,u32 offset,u32 val) +{ +struct kvm *kvm = vcpu->kvm; +struct kvm_arch_async_pf_control *apf = vcpu->arch.apf; + +return kvm_write_guest_offset_cached (kvm, &apf->cache, + &val, offset,sizeof (val)); +}
Quoted 8 lines
arch/arm64/kvm/async_pf.c line 37
Quoted 4 lines
arch/arm64/kvm/async_pf.c new file +4
-0+ +void kvm_arch_async_pf_create_vcpu (struct kvm_vcpu *vcpu) +{ + vcpu->arch.apf =kzalloc (sizeof (*(vcpu->arch.apf)),GFP_KERNEL );shouldn't we escalate the alloc failure and fail the vcpu creation instead of checking everywhere that apf is !null which is error prone. By the way I saw that on x86 this is a struct included in the vcpu one instead of a poinnter.
Ok. Lets embeded this struct to kvm_vcpu_arch, to avoid memory allocation here. Async PF is a auxillary function and everything should work just fine when it's disabled. It's why I didn't escalate the memory allocation failure.
Quoted 11 lines
Quoted 11 lines
arch/arm64/kvm/async_pf.c new file +11
-0+} + +bool kvm_arch_async_not_present_allowed (struct kvm_vcpu *vcpu) +{ +struct kvm *kvm = vcpu->kvm; +struct kvm_arch_async_pf_control *apf = vcpu->arch.apf; +struct kvm_sdei_vcpu *vsdei = vcpu->arch.sdei; +u32 reason, token; +int ret; + +if (!apf || !(apf->control_block &KVM_ASYNC_PF_ENABLED ))
Quoted 8 lines
arch/arm64/kvm/async_pf.c line 55
Quoted 7 lines
arch/arm64/kvm/async_pf.c new file +7
-0+return false; + +if (apf->send_user_only &&vcpu_mode_priv (vcpu)) +return false; + +if (!irqchip_in_kernel (vcpu->kvm)) +return false;can you explain why this is needed?
Async PF uses SDEI event to deliver page-not-present notification. When the guest receives the SDEI event, the associated handler is invoked. After that, the hyper call (COMPLETE_AND_RESUME) is issued from guest to host. When host receives this hypercall, all pending interrupts should be delivered immediately. Without a in-kernel IRQ chip, we're unable to do that.
Quoted 6 lines
arch/arm64/kvm/async_pf.c line 58
Quoted 3 lines
arch/arm64/kvm/async_pf.c new file +3
-0+ +if (!vsdei || vsdei->critical_event || vsdei->normal_event) +return false;don't you need some locking mechanism to void that vdsei fields change after that check? At the moment we may have a single SDEI num but nothing prevents from adding others in the future, right?
You're right that we currently have only one SDEI event. However, additional inline helper with lock is needed for this in future.
Quoted 10 lines
arch/arm64/kvm/async_pf.c line 67
Quoted 9 lines
arch/arm64/kvm/async_pf.c new file +9
-0+ +/* Pending page fault, which isn't acknowledged by guest */ + ret =read_cache (vcpu, offsetof(struct kvm_vcpu_pv_apf_data , reason), + &reason); +if (ret) { +kvm_err ("%s: Error %d to read reason (%d-%d)\n" , + __func__, ret, kvm->userspace_pid, vcpu->vcpu_idx); +return false; + }x86 code does not have those
kvm_err(). You may simply drop them.
It's useful for debugging. I may introduce a macro for this and it's disabled by default.
Quoted 11 lines
arch/arm64/kvm/async_pf.c line 77
Quoted 10 lines
arch/arm64/kvm/async_pf.c new file +10
-0+ + ret =read_cache (vcpu, offsetof(struct kvm_vcpu_pv_apf_data , token), + &token); +if (ret) { +kvm_err ("%s: Error %d to read token %d-%d\n" , + __func__, ret, kvm->userspace_pid, vcpu->vcpu_idx); +return false; + } + +if (reason || token)can't the token be null?
Nice catch! My intend is @token can't be NULL. However, it's not true in current implementation. Please refer to the explanation below.
Quoted 7 lines
Quoted 7 lines
arch/arm64/kvm/async_pf.c new file +7
-0+return false; + +return true; +} + +bool kvm_arch_setup_async_pf (struct kvm_vcpu *vcpu, +u32 esr,gpa_t gpa,gfn_t gfn)
Quoted 8 lines
arch/arm64/kvm/async_pf.c line 92
Quoted 8 lines
arch/arm64/kvm/async_pf.c new file +8
-0+{ +struct kvm_arch_async_pf_control *apf = vcpu->arch.apf; +struct kvm_arch_async_pf arch; +unsigned long hva =kvm_vcpu_gfn_to_hva (vcpu, gfn); + + arch.token = (apf->id++ <<12 ) | vcpu->vcpu_id; + arch.gfn = gfn; + arch.esr = esr;
@arch.token is spposed not NULL. However, "apf->id++" can overflow. So we need change the code into:
/*
* The token is invalid when it's zero. To avoid that by
* check if overflowing happens.
*/
if (apf->id == USHORT_MAX)
apf->id = 0;
arch.token = (apf->id++ << 12) | vcpu->vcpu_id;
arch.gfn = gfn;
arch.esr = esr;Quoted 7 lines
arch/arm64/kvm/async_pf.c line 98
Quoted 6 lines
arch/arm64/kvm/async_pf.c new file +6
-0+ +return kvm_setup_async_pf (vcpu, gpa, hva, &arch); +} + +/* +* It's guaranteed that no pending asynchronous page fault when this is that no APF is pending
Ok.
Quoted 9 lines
Quoted 9 lines
arch/arm64/kvm/async_pf.c new file +9
-0+* called. It means all previous issued asynchronous page faults have +* been acknowledged. +*/ +bool kvm_arch_async_page_not_present (struct kvm_vcpu *vcpu, +struct kvm_async_pf *work) +{ +struct kvm *kvm = vcpu->kvm; +struct kvm_arch_async_pf_control *apf = vcpu->arch.apf; +int ret;
Quoted 8 lines
arch/arm64/kvm/async_pf.c line 114
Quoted 7 lines
arch/arm64/kvm/async_pf.c new file +7
-0+ +kvm_async_pf_add_slot (vcpu, work->arch.gfn); + + ret =write_cache (vcpu, offsetof(struct kvm_vcpu_pv_apf_data , token), + work->arch.token); +if (ret) { + kvm_err("%s: Error %d to write token (%d-%d %08x)\n",kvm_err's may be dropped
Ok. I will introduce a marco, which is disabled by default.
Quoted 39 lines
Quoted 39 lines
arch/arm64/kvm/async_pf.c new file +31
-0+ __func__, ret, kvm->userspace_pid, + vcpu->vcpu_idx, work->arch.token); + goto fail; + } + + ret =write_cache (vcpu, offsetof(struct kvm_vcpu_pv_apf_data , reason), +KVM_PV_REASON_PAGE_NOT_PRESENT ); +if (ret) { +kvm_err ("%s: Error %d to write reason (%d-%d %08x)\n" , + __func__, ret, kvm->userspace_pid, + vcpu->vcpu_idx, work->arch.token); + goto fail; + } + + apf->notpresent_pending = true; + apf->notpresent_token = work->arch.token; + +return !kvm_sdei_inject (vcpu, apf->sdei_event_num, true); + +fail: +write_cache (vcpu, offsetof(struct kvm_vcpu_pv_apf_data , token),0 ); +write_cache (vcpu, offsetof(struct kvm_vcpu_pv_apf_data , reason),0 ); +kvm_async_pf_remove_slot (vcpu, work->arch.gfn); +return false; +} + +void kvm_arch_async_pf_destroy_vcpu (struct kvm_vcpu *vcpu) +{ +kfree (vcpu->arch.apf); + vcpu->arch.apf =NULL ; +}arch/arm64/kvm/mmu.c +0
-0@@ -914,6 +914,33 @@ static inline bool is_write_fault(unsigned int esr)return esr_dabt_is_wnr (esr); }
Quoted 11 lines
arch/arm64/kvm/mmu.c static inline bool is_write_fault(unsigned int esr) · line 925
Quoted 9 lines
arch/arm64/kvm/mmu.c +9
-0+static bool try_async_pf (struct kvm_vcpu *vcpu,unsigned int esr, +gpa_t gpa,gfn_t gfn,kvm_pfn_t *pfn, +bool write,bool *writable,bool prefault) +{ +struct kvm_arch_async_pf_control *apf = vcpu->arch.apf; +struct kvm_memory_slot *slot =kvm_vcpu_gfn_to_memslot (vcpu, gfn); +bool async = false; + +if (apf) {checking apf each time for a potential kacl of resource at vcpu creation look heavy to me.
Yep, As replied before, lets embedded the struct to kvm_vcpu_arch to avoid the memory allocation. In that case, we needn't check it any more.
Quoted 2 lines
arch/arm64/kvm/mmu.c static inline bool is_write_fault(unsigned int esr) · line 926
Quoted 1 line
arch/arm64/kvm/mmu.c +1
-0+/* Bail if *pfn has correct page */ s/bail/bail out? Comment rather related to !async check.
Ok.
Quoted 8 lines
arch/arm64/kvm/mmu.c static inline bool is_write_fault(unsigned int esr) · line 932
Quoted 6 lines
arch/arm64/kvm/mmu.c +6
-0+ *pfn =__gfn_to_pfn_memslot (slot, gfn, false, &async, + write, writable,NULL ); +if (!async) +return false; + +if (!prefault &&kvm_arch_async_not_present_allowed (vcpu)) {x86
kvm_can_do_async_pf()naming look more straightforward thankvm_arch_async_not_present_allowed
I would keep the function name as I intend to have all function names have prefix "kvm_arch_async". So lets rename it to kvm_arch_async_allowed() in next revision.
Quoted 2 lines
arch/arm64/kvm/mmu.c static inline bool is_write_fault(unsigned int esr) · line 933
Quoted 1 line
arch/arm64/kvm/mmu.c +1
-0+ if (kvm_async_pf_find_slot(vcpu, gfn) ||x86 has some trace points. You may envision to add some, maybe later on.
Yeah, lets ignore this one and we can add it in future.
Quoted 17 lines
Quoted 17 lines
arch/arm64/kvm/mmu.c +10
-0+ kvm_arch_setup_async_pf(vcpu, esr, gpa, gfn)) +return true; + } + } + + *pfn =__gfn_to_pfn_memslot (slot, gfn, false,NULL , + write, writable,NULL ); +return false; +} + int kvm_handle_user_mem_abort(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, phys_addr_t fault_ipa,@@ -1035,8 +1062,10 @@ int kvm_handle_user_mem_abort(struct kvm_vcpu *vcpu,*/ smp_rmb ();
Quoted 10 lines
arch/arm64/kvm/mmu.c int kvm_handle_user_mem_abort(struct kvm_vcpu *vcpu, · line 1071
Quoted 10 lines
arch/arm64/kvm/mmu.c +4
-2- pfn =__gfn_to_pfn_memslot (memslot, gfn, false,NULL , - write_fault, &writable,NULL ); +if (try_async_pf (vcpu, esr, fault_ipa, gfn, &pfn, + write_fault, &writable, prefault)) +return 1 ; +if (pfn ==KVM_PFN_ERR_HWPOISON ) {kvm_send_hwpoison_signal (hva, vma_shift);return 0 ;
Thanks,
Gavin
PATCH v4 8/15 KVM: arm64: Support page-ready notification
In reply to Gavin ShanThe asynchronous page fault starts with a worker when the requested page isn't present. The worker makes the requested page present in the background and the worker, together with the associated information, is queued to the completion queue after that. The worker and the completion queue are checked as below.
* A request (KVM_REQ_ASYNC_PF) is raised if the worker is the first one enqueued to the completion queue. With the request, the completion queue is checked and the worker is dequeued. A PPI is sent to guest as the page-ready notification and the guest should acknowledge the interrupt by SMCCC interface.
* When the notification (PPI) is acknowledged by guest, the completion queue is checked again and next worker is dequeued if we have one. For this particular worker, another notification (PPI) is sent to the guest without raising the request. Once the notification (PPI) is acknowledged by the guest, the completion queue is checked to process next worker, which has been queued to it.
Similar to page-not-present notification, the shared memory region is used to convey the reason and token associated with the page-ready notification. The region is represented by "struct kvm_vcpu_pv_apf_data".
The feature isn't enabled by CONFIG_KVM_ASYNC_PF yet. Also, the control path isn't implemented and will be done in the subsequent patches.
--- arch/arm64/include/asm/kvm_host.h | 15 ++ arch/arm64/include/uapi/asm/kvm_para.h | 1 + arch/arm64/kvm/arm.c | 24 ++- arch/arm64/kvm/async_pf.c | 205 +++++++++++++++++++++++++ arch/arm64/kvm/hypercalls.c | 5 + include/linux/arm-smccc.h | 10 ++ 6 files changed, 257 insertions(+), 3 deletions(-)
arch/arm64/include/asm/kvm_host.h +15 -0
@@ -48,6 +48,7 @@#define KVM_REQ_RELOAD_GICv4 KVM_ARCH_REQ(4)#define KVM_REQ_RELOAD_PMU KVM_ARCH_REQ(5)#define KVM_REQ_SDEI KVM_ARCH_REQ(6) +#define KVM_REQ_ASYNC_PF KVM_ARCH_REQ(7)#define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \ KVM_DIRTY_LOG_INITIALLY_SET)
@@ -302,10 +303,12 @@ struct kvm_arch_async_pf_control {u64 control_block;bool send_user_only;u64 sdei_event_num; +u32 irq;u16 id;bool notpresent_pending;u32 notpresent_token; +bool pageready_pending; };struct kvm_vcpu_arch {
@@ -776,6 +779,13 @@ bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, u32 esr, gpa_t gpa, gfn_t gfn);bool kvm_arch_async_page_not_present (struct kvm_vcpu *vcpu,struct kvm_async_pf *work); +void kvm_arch_async_page_present_queued (struct kvm_vcpu *vcpu); +bool kvm_arch_can_dequeue_async_page_present (struct kvm_vcpu *vcpu); +void kvm_arch_async_page_ready (struct kvm_vcpu *vcpu, +struct kvm_async_pf *work); +void kvm_arch_async_page_present (struct kvm_vcpu *vcpu, +struct kvm_async_pf *work); +void kvm_arch_async_pf_hypercall (struct kvm_vcpu *vcpu,u64 *val);void kvm_arch_async_pf_destroy_vcpu (struct kvm_vcpu *vcpu);#else static inline void kvm_arch_async_pf_create_vcpu (struct kvm_vcpu *vcpu) { }
@@ -791,6 +801,11 @@ static inline bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, {return false; } + +static inline void kvm_arch_async_pf_hypercall (struct kvm_vcpu *vcpu,u64 *val) +{ + val[0 ] =SMCCC_RET_NOT_SUPPORTED ; +}#endif /* Guest/host FPSIMD coordination helpers */
arch/arm64/include/uapi/asm/kvm_para.h +1 -0
@@ -9,6 +9,7 @@#define KVM_ASYNC_PF_SEND_ALWAYS (1 << 1)#define KVM_PV_REASON_PAGE_NOT_PRESENT 1 +#define KVM_PV_REASON_PAGE_READY 2struct kvm_vcpu_pv_apf_data {__u32 reason;
arch/arm64/kvm/arm.c +21 -3
@@ -503,9 +503,23 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,*/ int kvm_arch_vcpu_runnable (struct kvm_vcpu *v) { +struct kvm_arch_async_pf_control *apf = v->arch.apf;bool irq_lines = *vcpu_hcr (v) & (HCR_VI |HCR_VF ); -return ((irq_lines ||kvm_vgic_vcpu_pending_irq (v)) - && !v->arch.power_off && !v->arch.pause); + +if ((irq_lines ||kvm_vgic_vcpu_pending_irq (v)) && + !v->arch.power_off && !v->arch.pause) +return true; + +if (apf && (apf->control_block &KVM_ASYNC_PF_ENABLED )) { +if (kvm_check_async_pf_completion_queue (v)) +return true; + +if (apf->notpresent_pending || + apf->pageready_pending) +return true; + } + +return false; }bool kvm_arch_vcpu_in_kernel (struct kvm_vcpu *vcpu)
@@ -695,6 +709,9 @@ static void check_vcpu_requests(struct kvm_vcpu *vcpu)if (kvm_check_request (KVM_REQ_VCPU_RESET , vcpu))kvm_reset_vcpu (vcpu); +if (kvm_check_request (KVM_REQ_ASYNC_PF , vcpu)) +kvm_check_async_pf_completion (vcpu); +if (kvm_check_request (KVM_REQ_SDEI , vcpu))kvm_sdei_deliver (vcpu);
@@ -825,7 +842,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)smp_store_mb (vcpu->mode,IN_GUEST_MODE );if (ret <=0 ||need_new_vmid_gen (&vcpu->arch.hw_mmu->vmid) || -kvm_request_pending (vcpu)) { + (kvm_request_pending (vcpu) && +READ_ONCE (vcpu->requests) != (1UL <<KVM_REQ_ASYNC_PF ))) { vcpu->mode =OUTSIDE_GUEST_MODE ;isb ();/* Ensure work in x_flush_hwstate is committed */ kvm_pmu_sync_hwstate (vcpu);
arch/arm64/kvm/async_pf.c +205 -0
211 lines not on this page · raw message
arch/arm64/kvm/hypercalls.c +5 -0
@@ -129,10 +129,15 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)case ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID : val[0 ] =BIT (ARM_SMCCC_KVM_FUNC_FEATURES ); val[0 ] |=BIT (ARM_SMCCC_KVM_FUNC_PTP ); +if (vcpu->arch.apf) + val[0 ] |=BIT (ARM_SMCCC_KVM_FUNC_ASYNC_PF );break ;case ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID :kvm_ptp_get_time (vcpu, val);break ; +case ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID : +kvm_arch_async_pf_hypercall (vcpu, val); +break ;case ARM_SMCCC_TRNG_VERSION :case ARM_SMCCC_TRNG_FEATURES :case ARM_SMCCC_TRNG_GET_UUID :
include/linux/arm-smccc.h +10 -0
@@ -107,6 +107,7 @@/* KVM "vendor specific" services */ #define ARM_SMCCC_KVM_FUNC_FEATURES 0#define ARM_SMCCC_KVM_FUNC_PTP 1 +#define ARM_SMCCC_KVM_FUNC_ASYNC_PF 2#define ARM_SMCCC_KVM_FUNC_FEATURES_2 127#define ARM_SMCCC_KVM_NUM_FUNCS 128
@@ -133,6 +134,15 @@#define KVM_PTP_VIRT_COUNTER 0#define KVM_PTP_PHYS_COUNTER 1 +/* Asynchronous page fault service */ +#define ARM_SMCCC_KVM_FUNC_ASYNC_PF_IRQ_ACK 5 + +#define ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_VENDOR_HYP, \ + ARM_SMCCC_KVM_FUNC_ASYNC_PF) +/* Paravirtualised time calls (defined by ARM DEN0057A) */ #define ARM_SMCCC_HV_PV_TIME_FEATURES \ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
Signature · 6 lines
2.23.0 _______________________________________________ kvmarm mailing list [email protected] https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
PATCH v4 9/15 KVM: arm64: Support async PF hypercalls
In reply to Gavin ShanThis introduces (SMCCC) KVM vendor specific services to configure the asynchronous page fault functionality. The following services are introduced:
* ARM_SMCCC_KVM_FUNC_ASYNC_PF_VERSION
Returns the version, which can be used to identify ABI changes in the future.
* ARM_SMCCC_KVM_FUNC_ASYNC_PF_SLOTS
Return maximal number of tokens that current vCPU can have. It's used by guest to allocate the required resources.
* ARM_SMCCC_KVM_FUNC_ASYNC_PF_{SDEI, IRQ}
Return the associated SDEI or (PPI) IRQ number, configured by vCPU ioctl command.
* ARM_SMCCC_KVM_FUNC_ASYNC_PF_ENABLE
Enable or disable asynchronous page fault on current vCPU.
The corresponding SDEI event and (PPI) IRQ are owned by VMM. So they are configured by vCPU ioctl interface and it will be implemented when the asynchronous page fault capability is exported in the subsequent patches.
--- arch/arm64/kvm/async_pf.c | 119 ++++++++++++++++++++++++++++++++++++++ include/linux/arm-smccc.h | 5 ++ 2 files changed, 124 insertions(+)
arch/arm64/kvm/async_pf.c +119 -0
@@ -313,11 +313,114 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,write_cache (vcpu, offsetof(struct kvm_vcpu_pv_apf_data , token),0 ); } +static void kvm_arch_async_sdei_notifier (struct kvm_vcpu *vcpu, +unsigned long num, +unsigned int state) +{ +struct kvm *kvm = vcpu->kvm; +struct kvm_arch_async_pf_control *apf = vcpu->arch.apf; + +if (!apf) +return ; + +if (num != apf->sdei_event_num) { +kvm_err ("%s: Invalid event number (%d-%d %lx-%llx)\n" , + __func__, kvm->userspace_pid, vcpu->vcpu_idx, + num, apf->sdei_event_num); +return ; + } + +switch (state) { +case KVM_SDEI_NOTIFY_DELIVERED : +if (!apf->notpresent_pending) +break ; + + apf->notpresent_token =0 ; + apf->notpresent_pending = false; +break ; +case KVM_SDEI_NOTIFY_COMPLETED : +break ; +default : +kvm_err ("%s: Invalid state (%d-%d %lx-%d)\n" , + __func__, kvm->userspace_pid, vcpu->vcpu_idx, + num, state); + } +} + +static long kvm_arch_async_enable (struct kvm_vcpu *vcpu,u64 data) +{ +struct kvm *kvm = vcpu->kvm; +struct kvm_arch_async_pf_control *apf = vcpu->arch.apf; +gpa_t gpa = (data & ~0x3FUL ); +bool enabled, enable; +int ret; + +if (!apf || !irqchip_in_kernel (kvm)) +return SMCCC_RET_NOT_SUPPORTED ; + +/* Bail if the state transition isn't allowed */ + enabled = !!(apf->control_block &KVM_ASYNC_PF_ENABLED ); + enable = !!(data &KVM_ASYNC_PF_ENABLED ); +if (enable == enabled) { +kvm_debug ("%s: Async PF has been %s on (%d-%d %llx-%llx)\n" , + __func__, enabled ?"enabled" :"disabled" , + kvm->userspace_pid, vcpu->vcpu_idx, + apf->control_block, data); +return SMCCC_RET_NOT_REQUIRED ; + } + +/* To disable the functinality */ +if (!enable) { +kvm_clear_async_pf_completion_queue (vcpu); + apf->control_block = data; +return SMCCC_RET_SUCCESS ; + } + +/* +* The SDEI event and IRQ number should have been given +* prior to enablement. +*/ +if (!apf->sdei_event_num || !apf->irq) { +kvm_err ("%s: Invalid SDEI event or IRQ (%d-%d %llx-%d)\n" , + __func__, kvm->userspace_pid, vcpu->vcpu_idx, + apf->sdei_event_num, apf->irq); +return SMCCC_RET_INVALID_PARAMETER ; + } + +/* Register SDEI event notifier */ + ret =kvm_sdei_register_notifier (kvm, apf->sdei_event_num, + kvm_arch_async_sdei_notifier); +if (ret) { +kvm_err ("%s: Error %d registering SDEI notifier (%d-%d %llx)\n" , + __func__, ret, kvm->userspace_pid, vcpu->vcpu_idx, + apf->sdei_event_num); +return SMCCC_RET_NOT_SUPPORTED ; + } + +/* Initialize cache shared by host and guest */ + ret =kvm_gfn_to_hva_cache_init (kvm, &apf->cache, gpa, + offsetofend(struct kvm_vcpu_pv_apf_data, token)); +if (ret) { +kvm_err ("%s: Error %d initializing cache (%d-%d)\n" , + __func__, ret, kvm->userspace_pid, vcpu->vcpu_idx); +return SMCCC_RET_NOT_SUPPORTED ; + } + +/* Flush the token table */ +kvm_async_pf_reset_slot (vcpu); + apf->send_user_only = !(data &KVM_ASYNC_PF_SEND_ALWAYS ); +kvm_async_pf_wakeup_all (vcpu); + apf->control_block = data; + +return SMCCC_RET_SUCCESS ; +} +void kvm_arch_async_pf_hypercall (struct kvm_vcpu *vcpu,u64 *val) {struct kvm *kvm = vcpu->kvm;struct kvm_arch_async_pf_control *apf = vcpu->arch.apf;u32 func; +u64 data;long ret =SMCCC_RET_SUCCESS ;if (!apf) {
@@ -327,6 +430,22 @@ void kvm_arch_async_pf_hypercall(struct kvm_vcpu *vcpu, u64 *val) func =smccc_get_arg1 (vcpu);switch (func) { +case ARM_SMCCC_KVM_FUNC_ASYNC_PF_VERSION : + val[1 ] =0x010000 ;/* v1.0.0 */ +break ; +case ARM_SMCCC_KVM_FUNC_ASYNC_PF_SLOTS : + val[1 ] =ASYNC_PF_PER_VCPU ; +break ; +case ARM_SMCCC_KVM_FUNC_ASYNC_PF_SDEI : + val[1 ] = apf->sdei_event_num; +break ; +case ARM_SMCCC_KVM_FUNC_ASYNC_PF_IRQ : + val[1 ] = apf->irq; +break ; +case ARM_SMCCC_KVM_FUNC_ASYNC_PF_ENABLE : + data = (smccc_get_arg3 (vcpu) <<32 ) |smccc_get_arg2 (vcpu); + ret =kvm_arch_async_enable (vcpu, data); +break ;case ARM_SMCCC_KVM_FUNC_ASYNC_PF_IRQ_ACK :if (!apf->pageready_pending)break ;
include/linux/arm-smccc.h +5 -0
@@ -135,6 +135,11 @@#define KVM_PTP_PHYS_COUNTER 1/* Asynchronous page fault service */ +#define ARM_SMCCC_KVM_FUNC_ASYNC_PF_VERSION 0 +#define ARM_SMCCC_KVM_FUNC_ASYNC_PF_SLOTS 1 +#define ARM_SMCCC_KVM_FUNC_ASYNC_PF_SDEI 2 +#define ARM_SMCCC_KVM_FUNC_ASYNC_PF_IRQ 3 +#define ARM_SMCCC_KVM_FUNC_ASYNC_PF_ENABLE 4#define ARM_SMCCC_KVM_FUNC_ASYNC_PF_IRQ_ACK 5#define ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID \
Signature · 6 lines
2.23.0 _______________________________________________ kvmarm mailing list [email protected] https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
PATCH v4 10/15 KVM: arm64: Support async PF ioctl commands
In reply to Gavin ShanThis supports ioctl commands for configuration and migration:
KVM_ARM_ASYNC_PF_CMD_GET_VERSION
Return implementation version
KVM_ARM_ASYNC_PF_CMD_GET_SDEI
Return SDEI event number used for page-not-present notification
KVM_ARM_ASYNC_PF_CMD_GET_IRQ
Return IRQ number used for page-ready notification
KVM_ARM_ASYNC_PF_CMD_GET_CONTROL
Get control block when VM is migrated
KVM_ARM_ASYNC_PF_CMD_SET_SDEI
Set SDEI event number when VM is started or migrated
KVM_ARM_ASYNC_PF_CMD_SET_IRQ
Set IRQ number during when VM is started or migrated
KVM_ARM_ASYNC_PF_CMD_SET_CONTROL
Set control block when VM is migrated
--- arch/arm64/include/asm/kvm_host.h | 14 +++++++ arch/arm64/include/uapi/asm/kvm.h | 19 +++++++++ arch/arm64/kvm/arm.c | 6 +++ arch/arm64/kvm/async_pf.c | 64 +++++++++++++++++++++++++++++++ include/uapi/linux/kvm.h | 3 ++ 5 files changed, 106 insertions(+)
arch/arm64/include/asm/kvm_host.h +14 -0
@@ -786,6 +786,8 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu,void kvm_arch_async_page_present (struct kvm_vcpu *vcpu,struct kvm_async_pf *work);void kvm_arch_async_pf_hypercall (struct kvm_vcpu *vcpu,u64 *val); +long kvm_arch_async_pf_vm_ioctl (struct kvm *kvm,unsigned long arg); +long kvm_arch_async_pf_vcpu_ioctl (struct kvm_vcpu *vcpu,unsigned long arg);void kvm_arch_async_pf_destroy_vcpu (struct kvm_vcpu *vcpu);#else static inline void kvm_arch_async_pf_create_vcpu (struct kvm_vcpu *vcpu) { }
@@ -806,6 +808,18 @@ static inline void kvm_arch_async_pf_hypercall(struct kvm_vcpu *vcpu, u64 *val) { val[0 ] =SMCCC_RET_NOT_SUPPORTED ; } + +static inline long kvm_arch_async_pf_vm_ioctl (struct kvm *kvm, +unsigned long arg) +{ +return -EPERM ; +} + +static inline long kvm_arch_async_pf_vcpu_ioctl (struct kvm_vcpu *vcpu, +unsigned long arg) +{ +return -EPERM ; +}#endif /* Guest/host FPSIMD coordination helpers */
arch/arm64/include/uapi/asm/kvm.h +19 -0
@@ -414,6 +414,25 @@ struct kvm_arm_copy_mte_tags {#define KVM_PSCI_RET_INVAL PSCI_RET_INVALID_PARAMS#define KVM_PSCI_RET_DENIED PSCI_RET_DENIED +/* Asynchronous page fault */ +#define KVM_ARM_ASYNC_PF_CMD_GET_VERSION 0 +#define KVM_ARM_ASYNC_PF_CMD_GET_SDEI 1 +#define KVM_ARM_ASYNC_PF_CMD_GET_IRQ 2 +#define KVM_ARM_ASYNC_PF_CMD_GET_CONTROL 3 +#define KVM_ARM_ASYNC_PF_CMD_SET_SDEI 4 +#define KVM_ARM_ASYNC_PF_CMD_SET_IRQ 5 +#define KVM_ARM_ASYNC_PF_CMD_SET_CONTROL 6 + +struct kvm_arm_async_pf_cmd { +__u32 cmd; +union { +__u32 version; +__u64 sdei; +__u32 irq; +__u64 control; + }; +}; +#endif #endif /* __ARM_KVM_H__ */
arch/arm64/kvm/arm.c +6 -0
@@ -1335,6 +1335,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,case KVM_ARM_SDEI_COMMAND : {return kvm_sdei_vcpu_ioctl (vcpu, arg); } +case KVM_ARM_ASYNC_PF_COMMAND : { +return kvm_arch_async_pf_vcpu_ioctl (vcpu, arg); + }default : r = -EINVAL ; }
@@ -1419,6 +1422,9 @@ long kvm_arch_vm_ioctl(struct file *filp,case KVM_ARM_SDEI_COMMAND : {return kvm_sdei_vm_ioctl (kvm, arg); } +case KVM_ARM_ASYNC_PF_COMMAND : { +return kvm_arch_async_pf_vm_ioctl (kvm, arg); + }default :return -EINVAL ; }
arch/arm64/kvm/async_pf.c +64 -0
70 lines not on this page · raw message
include/uapi/linux/kvm.h +3 -0
@@ -1683,6 +1683,9 @@ struct kvm_xen_vcpu_attr {/* Available with KVM_CAP_ARM_SDEI */ #define KVM_ARM_SDEI_COMMAND _IOWR(KVMIO, 0xce, struct kvm_sdei_cmd) +/* Available with KVM_CAP_ASYNC_PF or KVM_CAP_ASYNC_PF_INT */ +#define KVM_ARM_ASYNC_PF_COMMAND _IOWR(KVMIO, 0xcf, struct kvm_arm_async_pf_cmd) +/* Secure Encrypted Virtualization command */ enum sev_cmd_id {/* Guest initialization commands */
Signature · 6 lines
2.23.0 _______________________________________________ kvmarm mailing list [email protected] https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
PATCH v4 11/15 KVM: arm64: Export async PF capability
In reply to Gavin ShanThis exports the asynchronous page fault capability:
* Identify capability KVM_CAP_ASYNC_{PF, PF_INT}.
* Standardize SDEI event for asynchronous page fault.
* Enable kernel config CONFIG_KVM_ASYNC_{PF, PF_SLOT}.
--- arch/arm64/include/uapi/asm/kvm_sdei.h | 1 + arch/arm64/kvm/Kconfig | 2 ++ arch/arm64/kvm/arm.c | 4 ++++ arch/arm64/kvm/sdei.c | 5 +++++ 4 files changed, 12 insertions(+)
arch/arm64/include/uapi/asm/kvm_sdei.h +1 -0
@@ -16,6 +16,7 @@#define KVM_SDEI_MAX_VCPUS 512#define KVM_SDEI_INVALID_NUM 0#define KVM_SDEI_DEFAULT_NUM 0x40400000 +#define KVM_SDEI_ASYNC_PF_NUM 0x40400001struct kvm_sdei_event_state {__u64 num;
arch/arm64/kvm/Kconfig +2 -0
@@ -29,6 +29,8 @@ menuconfig KVM select SRCU select KVM_VFIO select HAVE_KVM_EVENTFD + select KVM_ASYNC_PF + select KVM_ASYNC_PF_SLOT select HAVE_KVM_IRQFD select HAVE_KVM_MSI select HAVE_KVM_IRQCHIP
arch/arm64/kvm/arm.c +4 -0
@@ -281,6 +281,10 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)case KVM_CAP_ARM_SDEI : r =1 ;break ; +case KVM_CAP_ASYNC_PF : +case KVM_CAP_ASYNC_PF_INT : + r =IS_ENABLED (CONFIG_KVM_ASYNC_PF ) ?1 :0 ; +break ;default : r =0 ; }
arch/arm64/kvm/sdei.c +5 -0
@@ -19,6 +19,11 @@ static struct kvm_sdei_event_state defined_kse[] = { 1, SDEI_EVENT_PRIORITY_CRITICAL }, + {KVM_SDEI_ASYNC_PF_NUM , +SDEI_EVENT_TYPE_PRIVATE , +1 , +SDEI_EVENT_PRIORITY_CRITICAL + }, }; static struct kvm_sdei_event *kvm_sdei_find_event(struct kvm *kvm,
Signature · 6 lines
2.23.0 _______________________________________________ kvmarm mailing list [email protected] https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
PATCH v4 12/15 arm64: Detect async PF para-virtualization feature
In reply to Gavin ShanThis implements kvm_para_available() to check if para-virtualization features are available or not. Besides, kvm_para_has_feature() is enhanced to detect the asynchronous page fault para-virtualization feature. These two functions are going to be used by guest kernel to enable the asynchronous page fault.
This also adds kernel option (CONFIG_KVM_GUEST), which is the umbrella for the optimizations related to KVM para-virtualization.
--- arch/arm64/Kconfig | 11 +++++++++++ arch/arm64/include/asm/kvm_para.h | 12 +++++++++++- arch/arm64/include/uapi/asm/kvm_para.h | 2 ++ 3 files changed, 24 insertions(+), 1 deletion(-)
arch/arm64/Kconfig +11 -0
@@ -1081,6 +1081,17 @@ config PARAVIRT_TIME_ACCOUNTING If in doubt, say N here. +config KVM_GUEST + bool "KVM Guest Support" + depends on PARAVIRT + default y + help + This option enables various optimizations for running under the KVM + hypervisor. Overhead for the kernel when not running inside KVM should + be minimal. + + In case of doubt, say Y + config KEXEC depends on PM_SLEEP_SMP select KEXEC_CORE
arch/arm64/include/asm/kvm_para.h +11 -1
@@ -3,6 +3,8 @@#define _ASM_ARM_KVM_PARA_H#include <uapi/asm/kvm_para.h> +#include <linux/of.h> +#include <asm/hypervisor.h> static inline bool kvm_check_and_clear_guest_paused (void ) {
@@ -11,7 +13,12 @@ static inline bool kvm_check_and_clear_guest_paused(void)static inline unsigned int kvm_arch_para_features (void ) { -return 0 ; +unsigned int features =0 ; + +if (kvm_arm_hyp_service_available (ARM_SMCCC_KVM_FUNC_ASYNC_PF )) + features |= (1 <<KVM_FEATURE_ASYNC_PF ); + +return features; }static inline unsigned int kvm_arch_para_hints (void )
@@ -21,6 +28,9 @@ static inline unsigned int kvm_arch_para_hints(void)static inline bool kvm_para_available (void ) { +if (IS_ENABLED (CONFIG_KVM_GUEST )) +return true; +return false; }
arch/arm64/include/uapi/asm/kvm_para.h +2 -0
@@ -4,6 +4,8 @@#include <linux/types.h> +#define KVM_FEATURE_ASYNC_PF 0 +/* Async PF */ #define KVM_ASYNC_PF_ENABLED (1 << 0)#define KVM_ASYNC_PF_SEND_ALWAYS (1 << 1)
Signature · 6 lines
2.23.0 _______________________________________________ kvmarm mailing list [email protected] https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
PATCH v4 13/15 arm64: Reschedule process on aync PF
In reply to Gavin ShanThe page-not-present notification is delivered by SDEI event. The guest reschedules current process to another one when the SDEI event is received. It's not safe to do so in the SDEI event handler because the SDEI event should be acknowledged as soon as possible.
So the rescheduling is postponed until the current process switches from kernel to user mode. In order to trigger the switch, the SDEI event handler sends (reschedule) IPI to current CPU and it's delivered in time after the SDEI event is acknowledged.
A new thread flag (TIF_ASYNC_PF) is introduced in order to track the state for the process, to be rescheduled. With the flag is set, there is a head of wait-queue is associated with the process. The process keeps rescheduling itself until the flag is cleared when page-ready notification is received through (PPI) interrupt.
--- arch/arm64/include/asm/processor.h | 1 + arch/arm64/include/asm/thread_info.h | 4 +++- arch/arm64/kernel/signal.c | 17 +++++++++++++++++ 3 files changed, 21 insertions(+), 1 deletion(-)
arch/arm64/include/asm/processor.h +1 -0
@@ -156,6 +156,7 @@ struct thread_struct {u64 gcr_user_excl;#endif u64 sctlr_user; +void *data; };#define SCTLR_USER_MASK \
arch/arm64/include/asm/thread_info.h +3 -1
@@ -67,6 +67,7 @@ int arch_dup_task_struct(struct task_struct *dst,#define TIF_UPROBE 4/* uprobe breakpoint or singlestep */ #define TIF_MTE_ASYNC_FAULT 5/* MTE Asynchronous Tag Check Fault */ #define TIF_NOTIFY_SIGNAL 6/* signal notifications exist */ +#define TIF_ASYNC_PF 7/* Asynchronous page fault */ #define TIF_SYSCALL_TRACE 8/* syscall trace active */ #define TIF_SYSCALL_AUDIT 9/* syscall auditing */ #define TIF_SYSCALL_TRACEPOINT 10/* syscall tracepoint for ftrace */
@@ -97,11 +98,12 @@ int arch_dup_task_struct(struct task_struct *dst,#define _TIF_SVE (1 << TIF_SVE)#define _TIF_MTE_ASYNC_FAULT (1 << TIF_MTE_ASYNC_FAULT)#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) +#define _TIF_ASYNC_PF (1 << TIF_ASYNC_PF)#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \ _TIF_UPROBE | _TIF_MTE_ASYNC_FAULT | \ - _TIF_NOTIFY_SIGNAL) + _TIF_NOTIFY_SIGNAL | _TIF_ASYNC_PF)#define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \
arch/arm64/kernel/signal.c +17 -0
@@ -929,6 +929,23 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags) { do { + if (thread_flags & _TIF_ASYNC_PF) { + struct swait_queue_head *wq = + READ_ONCE(current->thread.data); + DECLARE_SWAITQUEUE(wait); + + local_daif_restore(DAIF_PROCCTX_NOIRQ); + + do { + prepare_to_swait_exclusive(wq, + &wait, TASK_UNINTERRUPTIBLE); + if (!test_thread_flag(TIF_ASYNC_PF)) + break; + + schedule(); + } while (test_thread_flag(TIF_ASYNC_PF)); + } + if (thread_flags & _TIF_NEED_RESCHED) { /* Unmask Debug and SError for the next task */ local_daif_restore(DAIF_PROCCTX_NOIRQ);
Signature · 6 lines
2.23.0 _______________________________________________ kvmarm mailing list [email protected] https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
PATCH v4 14/15 arm64: Enable async PF
In reply to Gavin ShanThis enables asynchronous page fault from guest side. The design is highlighted as below:
* The per-vCPU shared memory region, which is represented by "struct kvm_vcpu_pv_apf_data", is allocated. The reason and token associated with the received notifications of asynchronous page fault are delivered through it.
* A per-vCPU table, which is represented by "struct kvm_apf_table", is allocated. The process, on which the page-not-present notification is received, is added into the table so that it can reschedule itself on switching from kernel to user mode. Afterwards, the process, identified by token, is removed from the table and put into runnable state when page-ready notification is received.
* During CPU hotplug, the (private) SDEI event is expected to be enabled or disabled on the affected CPU by SDEI client driver. The (PPI) interrupt is enabled or disabled on the affected CPU by ourself. When the system is going to reboot, the SDEI event is disabled and unregistered and the (PPI) interrupt is disabled.
* The SDEI event and (PPI) interrupt number are retrieved from host through SMCCC interface. Besides, the version of the asynchronous page fault is validated when the feature is enabled on the guest.
* The feature is disabled on guest when boot parameter "no-kvmapf" is specified.
--- arch/arm64/kernel/Makefile | 1 + arch/arm64/kernel/kvm.c | 452 +++++++++++++++++++++++++++++++++++++ 2 files changed, 453 insertions(+) create mode 100644 arch/arm64/kernel/kvm.c
arch/arm64/kernel/Makefile +1 -0
@@ -59,6 +59,7 @@ obj-$(CONFIG_ACPI) += acpi.o obj-$(CONFIG_ACPI_NUMA) += acpi_numa.o obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL) += acpi_parking_protocol.o obj-$(CONFIG_PARAVIRT) += paravirt.o +obj-$(CONFIG_KVM_GUEST) += kvm.o obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o obj-$(CONFIG_HIBERNATION) += hibernate.o hibernate-asm.o obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o \
arch/arm64/kernel/kvm.c new file +452 -0
452 lines not on this page · raw message
Signature · 6 lines
2.23.0 _______________________________________________ kvmarm mailing list [email protected] https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
Re: [PATCH v4 14/15] arm64: Enable async PF
Quoted 21 lines · Gavin Shan
This enables asynchronous page fault from guest side. The design is highlighted as below:
* The per-vCPU shared memory region, which is represented by "struct
kvm_vcpu_pv_apf_data", is allocated. The reason and token associated with the received notifications of asynchronous page fault are delivered through it.* A per-vCPU table, which is represented by "struct
kvm_apf_table", is allocated. The process, on which the page-not-present notification is received, is added into the table so that it can reschedule itself on switching from kernel to user mode. Afterwards, the process, identified by token, is removed from the table and put into runnable state when page-ready notification is received.* During CPU hotplug, the (private) SDEI event is expected to be enabled or disabled on the affected CPU by SDEI client driver. The (PPI) interrupt is enabled or disabled on the affected CPU by ourself. When the system is going to reboot, the SDEI event is disabled and unregistered and the (PPI) interrupt is disabled.
Quoted 6 lines
* The SDEI event and (PPI) interrupt number are retrieved from host through SMCCC interface. Besides, the version of the asynchronous page fault is validated when the feature is enabled on the guest.
* The feature is disabled on guest when boot parameter "no-kvmapf" is specified.
Documentation/admin-guide/kernel-parameters.txt states this one is x86-only:
no-kvmapf [X86,KVM] Disable paravirtualized asynchronous page
fault handling.
makes sense to update in this patch I believe.
Quoted 177 lines
Signed-off-by Gavin Shan <[email protected]>--- arch/arm64/kernel/Makefile | 1 + arch/arm64/kernel/kvm.c | 452 +++++++++++++++++++++++++++++++++++++ 2 files changed, 453 insertions(+) create mode 100644 arch/arm64/kernel/kvm.carch/arm64/kernel/Makefile +1
-0@@ -59,6 +59,7 @@ obj-$(CONFIG_ACPI) += acpi.o obj-$(CONFIG_ACPI_NUMA) += acpi_numa.o obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL) += acpi_parking_protocol.o obj-$(CONFIG_PARAVIRT) += paravirt.o +obj-$(CONFIG_KVM_GUEST) += kvm.o obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o obj-$(CONFIG_HIBERNATION) += hibernate.o hibernate-asm.o obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o \arch/arm64/kernel/kvm.c new file +151
-0@@ -0,0 +1,452 @@ +// SPDX-License-Identifier: GPL-2.0 +/* +* Asynchronous page fault support. +* +* Copyright (C) 2021 Red Hat, Inc. +* +* Author(s): Gavin Shan <[email protected]> +*/ + +#include <linux/kernel.h> +#include <linux/spinlock.h> +#include <linux/slab.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/of.h> +#include <linux/of_fdt.h> +#include <linux/arm-smccc.h> +#include <linux/kvm_para.h> +#include <linux/arm_sdei.h> +#include <linux/acpi.h> +#include <linux/cpuhotplug.h> +#include <linux/reboot.h> + +struct kvm_apf_task { +unsigned int token; +struct task_struct *task; +struct swait_queue_head wq; +}; + +struct kvm_apf_table { +raw_spinlock_t lock; +unsigned int count; +struct kvm_apf_task tasks[0 ]; +}; + +static bool async_pf_available = true; +static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_data) __aligned(64); +static struct kvm_apf_table __percpu *apf_tables; +static unsigned int apf_tasks; +static unsigned int apf_sdei_num; +static unsigned int apf_ppi_num; +static int apf_irq; + +static bool kvm_async_pf_add_task (struct task_struct *task, +unsigned int token) +{ +struct kvm_apf_table *table =this_cpu_ptr (apf_tables); +unsigned int i, index = apf_tasks; +bool ret = false; + +raw_spin_lock (&table->lock); + +if (WARN_ON (table->count >= apf_tasks)) + goto unlock; + +for (i =0 ; i < apf_tasks; i++) { +if (!table->tasks[i].task) { +if (index == apf_tasks) { + ret = true; + index = i; + } + }else if (table->tasks[i].task == task) { +WARN_ON (table->tasks[i].token != token); + ret = false; +break ; + } + } + +if (!ret) + goto unlock; + + task->thread.data = &table->tasks[index].wq; +set_tsk_thread_flag (task,TIF_ASYNC_PF ); + + table->count++; + table->tasks[index].task = task; + table->tasks[index].token = token; + +unlock: +raw_spin_unlock (&table->lock); +return ret; +} + +static inline void kvm_async_pf_remove_one_task (struct kvm_apf_table *table, +unsigned int index) +{ +clear_tsk_thread_flag (table->tasks[index].task,TIF_ASYNC_PF ); +WRITE_ONCE (table->tasks[index].task->thread.data,NULL ); + + table->count--; + table->tasks[index].task =NULL ; + table->tasks[index].token =0 ; + +swake_up_one (&table->tasks[index].wq); +} + +static bool kvm_async_pf_remove_task (unsigned int token) +{ +struct kvm_apf_table *table =this_cpu_ptr (apf_tables); +unsigned int i; +bool ret = (token ==UINT_MAX ); + +raw_spin_lock (&table->lock); + +for (i =0 ; i < apf_tasks; i++) { +if (!table->tasks[i].task) +continue ; + +/* Wakeup all */ +if (token ==UINT_MAX ) { +kvm_async_pf_remove_one_task (table, i); +continue ; + } + +if (table->tasks[i].token == token) { +kvm_async_pf_remove_one_task (table, i); + ret = true; +break ; + } + } + +raw_spin_unlock (&table->lock); + +return ret; +} + +static int kvm_async_pf_sdei_handler (unsigned int event, +struct pt_regs *regs, +void *arg) +{ +unsigned int reason =__this_cpu_read (apf_data.reason); +unsigned int token =__this_cpu_read (apf_data.token); +bool ret; + +if (reason !=KVM_PV_REASON_PAGE_NOT_PRESENT ) { +pr_warn ("%s: Bogus notification (%d, 0x%08x)\n" , + __func__, reason, token); +return -EINVAL ; + } + + ret =kvm_async_pf_add_task (current, token); +__this_cpu_write (apf_data.token,0 ); +__this_cpu_write (apf_data.reason,0 ); + +if (!ret) +return -ENOSPC ; + +smp_send_reschedule (smp_processor_id ()); + +return 0 ; +}
arch/arm64/kernel/kvm.c line 161
Quoted 10 lines
arch/arm64/kernel/kvm.c new file +10
-0+ +static irqreturn_t kvm_async_pf_irq_handler (int irq,void *dev_id) +{ +unsigned int reason =__this_cpu_read (apf_data.reason); +unsigned int token =__this_cpu_read (apf_data.token); +struct arm_smccc_res res; + +if (reason !=KVM_PV_REASON_PAGE_READY ) { +pr_warn ("%s: Bogus interrupt %d (%d, 0x%08x)\n" , + __func__, irq, reason, token);
Spurrious interrupt or bogus APF reason set? Could be both I belive.
Quoted 32 lines
arch/arm64/kernel/kvm.c new file +32
-0+return IRQ_HANDLED ; + } + +kvm_async_pf_remove_task (token); + +__this_cpu_write (apf_data.token,0 ); +__this_cpu_write (apf_data.reason,0 ); +arm_smccc_1_1_invoke (ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID , +ARM_SMCCC_KVM_FUNC_ASYNC_PF_IRQ_ACK , &res); + +return IRQ_HANDLED ; +} + +static int __init kvm_async_pf_available (char *arg) +{ + async_pf_available = false; + +return 0 ; +} +early_param ("no-kvmapf" , kvm_async_pf_available); + +static void kvm_async_pf_disable (void ) +{ +struct arm_smccc_res res; +u32 enabled =__this_cpu_read (apf_data.enabled); + +if (!enabled) +return ; + +/* Disable the functionality */ + arm_smccc_1_1_invoke(ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID, + ARM_SMCCC_KVM_FUNC_ASYNC_PF_ENABLE,
arch/arm64/kernel/kvm.c line 203
Quoted 10 lines
arch/arm64/kernel/kvm.c new file +10
-0+ 0, 0, &res); +if (res.a0 !=SMCCC_RET_SUCCESS ) { +pr_warn ("%s: Error %ld to disable on CPU%d\n" , + __func__, res.a0,smp_processor_id ()); +return ; + } + +__this_cpu_write (apf_data.enabled,0 ); + +pr_info ("Async PF disabled on CPU%d\n" ,smp_processor_id ());
Nitpicking: x86 uses
"setup async PF for cpu %d\n" and
"disable async PF for cpu %d\n"
which are not ideal maybe but in any case it would probably make sense to be consistent across arches.
Quoted 249 lines
arch/arm64/kernel/kvm.c new file +249
-0+} + +static void kvm_async_pf_enable (void ) +{ +struct arm_smccc_res res; +u32 enabled =__this_cpu_read (apf_data.enabled); +u64 val =virt_to_phys (this_cpu_ptr (&apf_data)); + +if (enabled) +return ; + + val |=KVM_ASYNC_PF_ENABLED ; +arm_smccc_1_1_invoke (ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID , +ARM_SMCCC_KVM_FUNC_ASYNC_PF_ENABLE , + (u32 )val, (u32)(val >>32 ), &res); +if (res.a0 !=SMCCC_RET_SUCCESS ) { +pr_warn ("%s: Error %ld to enable CPU%d\n" , + __func__, res.a0,smp_processor_id ()); +return ; + } + +__this_cpu_write (apf_data.enabled,1 ); + +pr_info ("Async PF enabled on CPU%d\n" ,smp_processor_id ()); +} + +static void kvm_async_pf_cpu_disable (void *info) +{ +disable_percpu_irq (apf_irq); +kvm_async_pf_disable (); +} + +static void kvm_async_pf_cpu_enable (void *info) +{ +enable_percpu_irq (apf_irq,IRQ_TYPE_LEVEL_HIGH ); +kvm_async_pf_enable (); +} + +static int kvm_async_pf_cpu_reboot_notify (struct notifier_block *nb, +unsigned long code, +void *unused) +{ +if (code ==SYS_RESTART ) { +sdei_event_disable (apf_sdei_num); +sdei_event_unregister (apf_sdei_num); + +on_each_cpu (kvm_async_pf_cpu_disable,NULL ,1 ); + } + +return NOTIFY_DONE ; +} + +static struct notifier_block kvm_async_pf_cpu_reboot_nb = { + .notifier_call = kvm_async_pf_cpu_reboot_notify, +}; + +static int kvm_async_pf_cpu_online (unsigned int cpu) +{ +kvm_async_pf_cpu_enable (NULL ); + +return 0 ; +} + +static int kvm_async_pf_cpu_offline (unsigned int cpu) +{ +kvm_async_pf_cpu_disable (NULL ); + +return 0 ; +} + +static int __init kvm_async_pf_check_version (void ) +{ +struct arm_smccc_res res; + +/* +* Check the version and v1.0.0 or higher version is required +* to support the functionality. +*/ +arm_smccc_1_1_invoke (ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID , +ARM_SMCCC_KVM_FUNC_ASYNC_PF_VERSION , &res); +if (res.a0 !=SMCCC_RET_SUCCESS ) { +pr_warn ("%s: Error %ld to get version\n" , + __func__, res.a0); +return -EPERM ; + } + +if ((res.a1 &0xFFFFFFFFFF000000 ) || + ((res.a1 &0xFF0000 ) >>16 ) <0x1 ) { +pr_warn ("%s: Invalid version (0x%016lx)\n" , + __func__, res.a1); +return -EINVAL ; + } + +return 0 ; +} + +static int __init kvm_async_pf_info (void ) +{ +struct arm_smccc_res res; + +/* Retrieve number of tokens */ +arm_smccc_1_1_invoke (ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID , +ARM_SMCCC_KVM_FUNC_ASYNC_PF_SLOTS , &res); +if (res.a0 !=SMCCC_RET_SUCCESS ) { +pr_warn ("%s: Error %ld to get token number\n" , + __func__, res.a0); +return -EPERM ; + } + + apf_tasks = res.a1 *2 ; + +/* Retrieve SDEI event number */ +arm_smccc_1_1_invoke (ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID , +ARM_SMCCC_KVM_FUNC_ASYNC_PF_SDEI , &res); +if (res.a0 !=SMCCC_RET_SUCCESS ) { +pr_warn ("%s: Error %ld to get SDEI event number\n" , + __func__, res.a0); +return -EPERM ; + } + + apf_sdei_num = res.a1; + +/* Retrieve (PPI) interrupt number */ +arm_smccc_1_1_invoke (ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID , +ARM_SMCCC_KVM_FUNC_ASYNC_PF_IRQ , &res); +if (res.a0 !=SMCCC_RET_SUCCESS ) { +pr_warn ("%s: Error %ld to get IRQ\n" , + __func__, res.a0); +return -EPERM ; + } + + apf_ppi_num = res.a1; + +return 0 ; +} + +static int __init kvm_async_pf_init (void ) +{ +struct kvm_apf_table *table; +size_t size; +int cpu, i, ret; + +if (!kvm_para_has_feature (KVM_FEATURE_ASYNC_PF ) || + !async_pf_available) +return -EPERM ; + + ret =kvm_async_pf_check_version (); +if (ret) +return ret; + + ret =kvm_async_pf_info (); +if (ret) +return ret; + +/* Allocate and initialize the sleeper table */ + size =sizeof (struct kvm_apf_table ) + + apf_tasks *sizeof (struct kvm_apf_task ); + apf_tables =__alloc_percpu (size,0 ); +if (!apf_tables) { +pr_warn ("%s: Unable to alloc async PF table\n" , + __func__); +return -ENOMEM ; + } + +for_each_possible_cpu (cpu) { + table =per_cpu_ptr (apf_tables, cpu); +raw_spin_lock_init (&table->lock); +for (i =0 ; i < apf_tasks; i++) +init_swait_queue_head (&table->tasks[i].wq); + } + +/* +* Initialize SDEI event for page-not-present notification. +* The SDEI event number should have been retrieved from +* the host. +*/ + ret =sdei_event_register (apf_sdei_num, + kvm_async_pf_sdei_handler,NULL ); +if (ret) { +pr_warn ("%s: Error %d to register SDEI event\n" , + __func__, ret); + ret = -EIO ; + goto release_tables; + } + + ret =sdei_event_enable (apf_sdei_num); +if (ret) { +pr_warn ("%s: Error %d to enable SDEI event\n" , + __func__, ret); + goto unregister_event; + } + +/* +* Initialize interrupt for page-ready notification. The +* interrupt number and its properties should have been +* retrieved from the ACPI:APFT table. +*/ + apf_irq =acpi_register_gsi (NULL , apf_ppi_num, +ACPI_LEVEL_SENSITIVE ,ACPI_ACTIVE_HIGH ); +if (apf_irq <=0 ) { + ret = -EIO ; +pr_warn ("%s: Error %d to register IRQ\n" , + __func__, apf_irq); + goto disable_event; + } + + ret =request_percpu_irq (apf_irq, kvm_async_pf_irq_handler, +"Asynchronous Page Fault" , &apf_data); +if (ret) { +pr_warn ("%s: Error %d to request IRQ\n" , + __func__, ret); + goto unregister_irq; + } + +register_reboot_notifier (&kvm_async_pf_cpu_reboot_nb); + ret =cpuhp_setup_state_nocalls (CPUHP_AP_ONLINE_DYN , +"arm/kvm:online" , kvm_async_pf_cpu_online, + kvm_async_pf_cpu_offline); +if (ret <0 ) { +pr_warn ("%s: Error %d to install cpu hotplug callbacks\n" , + __func__, ret); + goto release_irq; + } + +/* Enable async PF on the online CPUs */ +on_each_cpu (kvm_async_pf_cpu_enable,NULL ,1 ); + +return 0 ; + +release_irq: +free_percpu_irq (apf_irq, &apf_data); +unregister_irq: +acpi_unregister_gsi (apf_ppi_num); +disable_event: +sdei_event_disable (apf_sdei_num); +unregister_event: +sdei_event_unregister (apf_sdei_num); +release_tables: +free_percpu (apf_tables); + +return ret; +} + +static int __init kvm_guest_init (void ) +{ +return kvm_async_pf_init (); +} + +fs_initcall (kvm_guest_init);
Signature · 1 line
Vitaly
Re: [PATCH v4 14/15] arm64: Enable async PF
Hi Vitaly,
Quoted 30 lines · Vitaly Kuznetsov
Quoted 21 lines · Gavin Shan
This enables asynchronous page fault from guest side. The design is highlighted as below:
* The per-vCPU shared memory region, which is represented by "struct
kvm_vcpu_pv_apf_data", is allocated. The reason and token associated with the received notifications of asynchronous page fault are delivered through it.* A per-vCPU table, which is represented by "struct
kvm_apf_table", is allocated. The process, on which the page-not-present notification is received, is added into the table so that it can reschedule itself on switching from kernel to user mode. Afterwards, the process, identified by token, is removed from the table and put into runnable state when page-ready notification is received.* During CPU hotplug, the (private) SDEI event is expected to be enabled or disabled on the affected CPU by SDEI client driver. The (PPI) interrupt is enabled or disabled on the affected CPU by ourself. When the system is going to reboot, the SDEI event is disabled and unregistered and the (PPI) interrupt is disabled.
Quoted 6 lines
* The SDEI event and (PPI) interrupt number are retrieved from host through SMCCC interface. Besides, the version of the asynchronous page fault is validated when the feature is enabled on the guest.
* The feature is disabled on guest when boot parameter "no-kvmapf" is specified.
Quoted 8 lines
Documentation/admin-guide/kernel-parameters.txtstates this one is x86-only:no-kvmapf [X86,KVM] Disable paravirtualized asynchronous page
fault handling.makes sense to update in this patch I believe.
Yes, I will update in next revision.
Quoted 181 lines
Quoted 181 lines
Signed-off-by Gavin Shan <[email protected]>--- arch/arm64/kernel/Makefile | 1 + arch/arm64/kernel/kvm.c | 452 +++++++++++++++++++++++++++++++++++++ 2 files changed, 453 insertions(+)create mode 100644
arch/arm64/kernel/kvm.carch/arm64/kernel/Makefile +1
-0@@ -59,6 +59,7 @@ obj-$(CONFIG_ACPI) += acpi.o obj-$(CONFIG_ACPI_NUMA) += acpi_numa.o obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL) += acpi_parking_protocol.o obj-$(CONFIG_PARAVIRT) += paravirt.o +obj-$(CONFIG_KVM_GUEST) += kvm.o obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o obj-$(CONFIG_HIBERNATION) += hibernate.o hibernate-asm.o obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o \arch/arm64/kernel/kvm.c new file +155
-0@@ -0,0 +1,452 @@ +// SPDX-License-Identifier: GPL-2.0 +/* +* Asynchronous page fault support. +* +* Copyright (C) 2021 Red Hat, Inc. +* +* Author(s): Gavin Shan <[email protected]> +*/ + +#include <linux/kernel.h> +#include <linux/spinlock.h> +#include <linux/slab.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/of.h> +#include <linux/of_fdt.h> +#include <linux/arm-smccc.h> +#include <linux/kvm_para.h> +#include <linux/arm_sdei.h> +#include <linux/acpi.h> +#include <linux/cpuhotplug.h> +#include <linux/reboot.h> + +struct kvm_apf_task { +unsigned int token; +struct task_struct *task; +struct swait_queue_head wq; +}; + +struct kvm_apf_table { +raw_spinlock_t lock; +unsigned int count; +struct kvm_apf_task tasks[0 ]; +}; + +static bool async_pf_available = true; +static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_data) __aligned(64); +static struct kvm_apf_table __percpu *apf_tables; +static unsigned int apf_tasks; +static unsigned int apf_sdei_num; +static unsigned int apf_ppi_num; +static int apf_irq; + +static bool kvm_async_pf_add_task (struct task_struct *task, +unsigned int token) +{ +struct kvm_apf_table *table =this_cpu_ptr (apf_tables); +unsigned int i, index = apf_tasks; +bool ret = false; + +raw_spin_lock (&table->lock); + +if (WARN_ON (table->count >= apf_tasks)) + goto unlock; + +for (i =0 ; i < apf_tasks; i++) { +if (!table->tasks[i].task) { +if (index == apf_tasks) { + ret = true; + index = i; + } + }else if (table->tasks[i].task == task) { +WARN_ON (table->tasks[i].token != token); + ret = false; +break ; + } + } + +if (!ret) + goto unlock; + + task->thread.data = &table->tasks[index].wq; +set_tsk_thread_flag (task,TIF_ASYNC_PF ); + + table->count++; + table->tasks[index].task = task; + table->tasks[index].token = token; + +unlock: +raw_spin_unlock (&table->lock); +return ret; +} + +static inline void kvm_async_pf_remove_one_task (struct kvm_apf_table *table, +unsigned int index) +{ +clear_tsk_thread_flag (table->tasks[index].task,TIF_ASYNC_PF ); +WRITE_ONCE (table->tasks[index].task->thread.data,NULL ); + + table->count--; + table->tasks[index].task =NULL ; + table->tasks[index].token =0 ; + +swake_up_one (&table->tasks[index].wq); +} + +static bool kvm_async_pf_remove_task (unsigned int token) +{ +struct kvm_apf_table *table =this_cpu_ptr (apf_tables); +unsigned int i; +bool ret = (token ==UINT_MAX ); + +raw_spin_lock (&table->lock); + +for (i =0 ; i < apf_tasks; i++) { +if (!table->tasks[i].task) +continue ; + +/* Wakeup all */ +if (token ==UINT_MAX ) { +kvm_async_pf_remove_one_task (table, i); +continue ; + } + +if (table->tasks[i].token == token) { +kvm_async_pf_remove_one_task (table, i); + ret = true; +break ; + } + } + +raw_spin_unlock (&table->lock); + +return ret; +} + +static int kvm_async_pf_sdei_handler (unsigned int event, +struct pt_regs *regs, +void *arg) +{ +unsigned int reason =__this_cpu_read (apf_data.reason); +unsigned int token =__this_cpu_read (apf_data.token); +bool ret; + +if (reason !=KVM_PV_REASON_PAGE_NOT_PRESENT ) { +pr_warn ("%s: Bogus notification (%d, 0x%08x)\n" , + __func__, reason, token); +return -EINVAL ; + } + + ret =kvm_async_pf_add_task (current, token); +__this_cpu_write (apf_data.token,0 ); +__this_cpu_write (apf_data.reason,0 ); + +if (!ret) +return -ENOSPC ; + +smp_send_reschedule (smp_processor_id ()); + +return 0 ; +} + +static irqreturn_t kvm_async_pf_irq_handler (int irq,void *dev_id) +{ +unsigned int reason =__this_cpu_read (apf_data.reason);
Quoted 9 lines
arch/arm64/kernel/kvm.c line 161
Quoted 6 lines
arch/arm64/kernel/kvm.c new file +6
-0+unsigned int token =__this_cpu_read (apf_data.token); +struct arm_smccc_res res; + +if (reason !=KVM_PV_REASON_PAGE_READY ) { +pr_warn ("%s: Bogus interrupt %d (%d, 0x%08x)\n" , + __func__, irq, reason, token);Spurrious interrupt or bogus APF reason set? Could be both I belive.
Yes, It could be both and the message can be more specific like below:
pr_warn("%s: Wrong interrupt (%d) or state (%d 0x%08x) received\n",
__func__, irq, reason, token);Quoted 45 lines
Quoted 32 lines
arch/arm64/kernel/kvm.c new file +32
-0+return IRQ_HANDLED ; + } + +kvm_async_pf_remove_task (token); + +__this_cpu_write (apf_data.token,0 ); +__this_cpu_write (apf_data.reason,0 ); +arm_smccc_1_1_invoke (ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID , +ARM_SMCCC_KVM_FUNC_ASYNC_PF_IRQ_ACK , &res); + +return IRQ_HANDLED ; +} + +static int __init kvm_async_pf_available (char *arg) +{ + async_pf_available = false; + +return 0 ; +} +early_param ("no-kvmapf" , kvm_async_pf_available); + +static void kvm_async_pf_disable (void ) +{ +struct arm_smccc_res res; +u32 enabled =__this_cpu_read (apf_data.enabled); + +if (!enabled) +return ; + +/* Disable the functionality */ + arm_smccc_1_1_invoke(ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID, + ARM_SMCCC_KVM_FUNC_ASYNC_PF_ENABLE,arch/arm64/kernel/kvm.c line 203
Quoted 10 lines
arch/arm64/kernel/kvm.c new file +10
-0+ 0, 0, &res); +if (res.a0 !=SMCCC_RET_SUCCESS ) { +pr_warn ("%s: Error %ld to disable on CPU%d\n" , + __func__, res.a0,smp_processor_id ()); +return ; + } + +__this_cpu_write (apf_data.enabled,0 ); + +pr_info ("Async PF disabled on CPU%d\n" ,smp_processor_id ());Nitpicking: x86 uses
Quoted 6 lines
"setup async PF for cpu %d\n" and
"disable async PF for cpu %d\n"which are not ideal maybe but in any case it would probably make sense to be consistent across arches.
Yes, It's worthwhile to do so :)
Quoted 242 lines
Quoted 242 lines
arch/arm64/kernel/kvm.c new file +241
-0+} + +static void kvm_async_pf_enable (void ) +{ +struct arm_smccc_res res; +u32 enabled =__this_cpu_read (apf_data.enabled); +u64 val =virt_to_phys (this_cpu_ptr (&apf_data)); + +if (enabled) +return ; + + val |=KVM_ASYNC_PF_ENABLED ; +arm_smccc_1_1_invoke (ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID , +ARM_SMCCC_KVM_FUNC_ASYNC_PF_ENABLE , + (u32 )val, (u32)(val >>32 ), &res); +if (res.a0 !=SMCCC_RET_SUCCESS ) { +pr_warn ("%s: Error %ld to enable CPU%d\n" , + __func__, res.a0,smp_processor_id ()); +return ; + } + +__this_cpu_write (apf_data.enabled,1 ); + +pr_info ("Async PF enabled on CPU%d\n" ,smp_processor_id ()); +} + +static void kvm_async_pf_cpu_disable (void *info) +{ +disable_percpu_irq (apf_irq); +kvm_async_pf_disable (); +} + +static void kvm_async_pf_cpu_enable (void *info) +{ +enable_percpu_irq (apf_irq,IRQ_TYPE_LEVEL_HIGH ); +kvm_async_pf_enable (); +} + +static int kvm_async_pf_cpu_reboot_notify (struct notifier_block *nb, +unsigned long code, +void *unused) +{ +if (code ==SYS_RESTART ) { +sdei_event_disable (apf_sdei_num); +sdei_event_unregister (apf_sdei_num); + +on_each_cpu (kvm_async_pf_cpu_disable,NULL ,1 ); + } + +return NOTIFY_DONE ; +} + +static struct notifier_block kvm_async_pf_cpu_reboot_nb = { + .notifier_call = kvm_async_pf_cpu_reboot_notify, +}; + +static int kvm_async_pf_cpu_online (unsigned int cpu) +{ +kvm_async_pf_cpu_enable (NULL ); + +return 0 ; +} + +static int kvm_async_pf_cpu_offline (unsigned int cpu) +{ +kvm_async_pf_cpu_disable (NULL ); + +return 0 ; +} + +static int __init kvm_async_pf_check_version (void ) +{ +struct arm_smccc_res res; + +/* +* Check the version and v1.0.0 or higher version is required +* to support the functionality. +*/ +arm_smccc_1_1_invoke (ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID , +ARM_SMCCC_KVM_FUNC_ASYNC_PF_VERSION , &res); +if (res.a0 !=SMCCC_RET_SUCCESS ) { +pr_warn ("%s: Error %ld to get version\n" , + __func__, res.a0); +return -EPERM ; + } + +if ((res.a1 &0xFFFFFFFFFF000000 ) || + ((res.a1 &0xFF0000 ) >>16 ) <0x1 ) { +pr_warn ("%s: Invalid version (0x%016lx)\n" , + __func__, res.a1); +return -EINVAL ; + } + +return 0 ; +} + +static int __init kvm_async_pf_info (void ) +{ +struct arm_smccc_res res; + +/* Retrieve number of tokens */ +arm_smccc_1_1_invoke (ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID , +ARM_SMCCC_KVM_FUNC_ASYNC_PF_SLOTS , &res); +if (res.a0 !=SMCCC_RET_SUCCESS ) { +pr_warn ("%s: Error %ld to get token number\n" , + __func__, res.a0); +return -EPERM ; + } + + apf_tasks = res.a1 *2 ; + +/* Retrieve SDEI event number */ +arm_smccc_1_1_invoke (ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID , +ARM_SMCCC_KVM_FUNC_ASYNC_PF_SDEI , &res); +if (res.a0 !=SMCCC_RET_SUCCESS ) { +pr_warn ("%s: Error %ld to get SDEI event number\n" , + __func__, res.a0); +return -EPERM ; + } + + apf_sdei_num = res.a1; + +/* Retrieve (PPI) interrupt number */ +arm_smccc_1_1_invoke (ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID , +ARM_SMCCC_KVM_FUNC_ASYNC_PF_IRQ , &res); +if (res.a0 !=SMCCC_RET_SUCCESS ) { +pr_warn ("%s: Error %ld to get IRQ\n" , + __func__, res.a0); +return -EPERM ; + } + + apf_ppi_num = res.a1; + +return 0 ; +} + +static int __init kvm_async_pf_init (void ) +{ +struct kvm_apf_table *table; +size_t size; +int cpu, i, ret; + +if (!kvm_para_has_feature (KVM_FEATURE_ASYNC_PF ) || + !async_pf_available) +return -EPERM ; + + ret =kvm_async_pf_check_version (); +if (ret) +return ret; + + ret =kvm_async_pf_info (); +if (ret) +return ret; + +/* Allocate and initialize the sleeper table */ + size =sizeof (struct kvm_apf_table ) + + apf_tasks *sizeof (struct kvm_apf_task ); + apf_tables =__alloc_percpu (size,0 ); +if (!apf_tables) { +pr_warn ("%s: Unable to alloc async PF table\n" , + __func__); +return -ENOMEM ; + } + +for_each_possible_cpu (cpu) { + table =per_cpu_ptr (apf_tables, cpu); +raw_spin_lock_init (&table->lock); +for (i =0 ; i < apf_tasks; i++) +init_swait_queue_head (&table->tasks[i].wq); + } + +/* +* Initialize SDEI event for page-not-present notification. +* The SDEI event number should have been retrieved from +* the host. +*/ + ret =sdei_event_register (apf_sdei_num, + kvm_async_pf_sdei_handler,NULL ); +if (ret) { +pr_warn ("%s: Error %d to register SDEI event\n" , + __func__, ret); + ret = -EIO ; + goto release_tables; + } + + ret =sdei_event_enable (apf_sdei_num); +if (ret) { +pr_warn ("%s: Error %d to enable SDEI event\n" , + __func__, ret); + goto unregister_event; + } + +/* +* Initialize interrupt for page-ready notification. The +* interrupt number and its properties should have been +* retrieved from the ACPI:APFT table. +*/ + apf_irq =acpi_register_gsi (NULL , apf_ppi_num, +ACPI_LEVEL_SENSITIVE ,ACPI_ACTIVE_HIGH ); +if (apf_irq <=0 ) { + ret = -EIO ; +pr_warn ("%s: Error %d to register IRQ\n" , + __func__, apf_irq); + goto disable_event; + } + + ret =request_percpu_irq (apf_irq, kvm_async_pf_irq_handler, +"Asynchronous Page Fault" , &apf_data); +if (ret) { +pr_warn ("%s: Error %d to request IRQ\n" , + __func__, ret); + goto unregister_irq; + } + +register_reboot_notifier (&kvm_async_pf_cpu_reboot_nb); + ret =cpuhp_setup_state_nocalls (CPUHP_AP_ONLINE_DYN , +"arm/kvm:online" , kvm_async_pf_cpu_online, + kvm_async_pf_cpu_offline); +if (ret <0 ) { +pr_warn ("%s: Error %d to install cpu hotplug callbacks\n" , + __func__, ret); + goto release_irq; + } + +/* Enable async PF on the online CPUs */ +on_each_cpu (kvm_async_pf_cpu_enable,NULL ,1 ); + +return 0 ; + +release_irq: +free_percpu_irq (apf_irq, &apf_data); +unregister_irq: +acpi_unregister_gsi (apf_ppi_num); +disable_event: +sdei_event_disable (apf_sdei_num); +unregister_event: +sdei_event_unregister (apf_sdei_num); +release_tables: +free_percpu (apf_tables); + +return ret;
Quoted 9 lines
arch/arm64/kernel/kvm.c line 452
Quoted 8 lines
arch/arm64/kernel/kvm.c new file +8
-0+} + +static int __init kvm_guest_init (void ) +{ +return kvm_async_pf_init (); +} + +fs_initcall (kvm_guest_init);
Thanks,
Gavin
PATCH v4 15/15 KVM: arm64: Add async PF document
In reply to Gavin ShanThis adds document to explain the interface for asynchronous page fault and how it works in general.
--- Documentation/virt/kvm/arm/apf.rst | 143 +++++++++++++++++++++++++++ Documentation/virt/kvm/arm/index.rst | 1 + 2 files changed, 144 insertions(+) create mode 100644 Documentation/virt/kvm/arm/apf.rst
Documentation/virt/kvm/arm/apf.rst new file +143 -0
@@ -0,0 +1,143 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Asynchronous Page Fault Support for arm64 +========================================= + +There are two stages of page faults when KVM module is enabled as accelerator +to the guest. The guest is responsible for handling the stage-1 page faults, +while the host handles the stage-2 page faults. During the period of handling +the stage-2 page faults, the guest is suspended until the requested page is +ready. It could take several milliseconds, even hundreds of milliseconds in +extreme situations because I/O might be required to move the requested page +from disk to DRAM. The guest does not do any work when it is suspended. The +feature (Asynchronous Page Fault) is introduced to take advantage of the +suspending period and to improve the overall performance. + +There are two paths in order to fulfil the asynchronous page fault, called +as control path and data path. The control path allows the VMM or guest to +configure the functionality, while the notifications are delivered in data +path. The notifications are classified into page-not-present and page-ready +notifications. + +Data Path +--------- + +There are two types of notifications delivered from host to guest in the +data path: page-not-present and page-ready notification. They are delivered +through SDEI event and (PPI) interrupt separately. Besides, there is a shared +buffer between host and guest to indicate the reason and sequential token, +which is used to identify the asynchronous page fault. The reason and token +resident in the shared buffer is written by host, read and cleared by guest. +An asynchronous page fault is delivered and completed as below. + +(1) When an asynchronous page fault starts, a (workqueue) worker is created + and queued to the vCPU's pending queue. The worker makes the requested + page ready and resident to DRAM in the background. The shared buffer is + updated with reason and sequential token. After that, SDEI event is sent + to guest as page-not-present notification. + +(2) When the SDEI event is received on guest, the current process is tagged + with TIF_ASYNC_PF and associated with a wait queue. The process is ready + to keep rescheduling itself on switching from kernel to user mode. After + that, a reschedule IPI is sent to current CPU and the received SDEI event + is acknowledged. Note that the IPI is delivered when the acknowledgment + on the SDEI event is received on host. + +(3) On the host, the worker is dequeued from the vCPU's pending queue and + enqueued to its completion queue when the requested page becomes ready. + In the mean while, KVM_REQ_ASYNC_PF request is sent the vCPU if the + worker is the first element enqueued to the completion queue. + +(4) With pending KVM_REQ_ASYNC_PF request, the first worker in the completion + queue is dequeued and destroyed. In the mean while, a (PPI) interrupt is + sent to guest with updated reason and token in the shared buffer. + +(5) When the (PPI) interrupt is received on guest, the affected process is + located using the token and waken up after its TIF_ASYNC_PF tag is cleared. + After that, the interrupt is acknowledged through SMCCC interface. The + workers in the completion queue is dequeued and destroyed if any workers + exist, and another (PPI) interrupt is sent to the guest. + +Control Path +------------ + +The configurations are passed through SMCCC or ioctl interface. The SDEI +event and (PPI) interrupt are owned by VMM, so the SDEI event and interrupt +numbers are configured through ioctl command on per-vCPU basis. Besides, +the functionality might be enabled and configured through ioctl interface +by VMM during migration: + + * KVM_ARM_ASYNC_PF_CMD_GET_VERSION + + Returns the current version of the feature, supported by the host. It is + made up of major, minor and revision fields. Each field is one byte in + length. + + * KVM_ARM_ASYNC_PF_CMD_GET_SDEI: + + Retrieve the SDEI event number, used for page-not-present notification, + so that it can be configured on destination VM in the scenario of + migration. + + * KVM_ARM_ASYNC_PF_GET_IRQ: + + Retrieve the IRQ (PPI) number, used for page-ready notification, so that + it can be configured on destination VM in the scenario of migration. + + * KVM_ARM_ASYNC_PF_CMD_GET_CONTROL + + Retrieve the address of control block, so that it can be configured on + destination VM in the scenario of migration. + + * KVM_ARM_ASYNC_PF_CMD_SET_SDEI: + + Used by VMM to configure number of SDEI event, which is used to deliver + page-not-present notification by host. This is used when VM is started + or migrated. + + * KVM_ARM_ASYNC_PF_CMD_SET_IRQ + + Used by VMM to configure number of (PPI) interrupt, which is used to + deliver page-ready notification by host. This is used when VM is started + or migrated. + + * KVM_ARM_ASYNC_PF_CMD_SET_CONTROL + + Set the control block on the destination VM in the scenario of migration. + +The other configurations are passed through SMCCC interface. The host exports +the capability through KVM vendor specific service, which is identified by +ARM_SMCCC_KVM_FUNC_ASYNC_PF_FUNC_ID. There are several functions defined for +this: + + * ARM_SMCCC_KVM_FUNC_ASYNC_PF_VERSION + + Returns the current version of the feature, supported by the host. It is + made up of major, minor and revision fields. Each field is one byte in + length. + + * ARM_SMCCC_KVM_FUNC_ASYNC_PF_SLOTS + + Returns the size of the hashed GFN table. It is used by guest to set up + the capacity of waiting process table. + + * ARM_SMCCC_KVM_FUNC_ASYNC_PF_SDEI + * ARM_SMCCC_KVM_FUNC_ASYNC_PF_IRQ + + Used by the guest to retrieve the SDEI event and (PPI) interrupt number + that are configured by VMM. + + * ARM_SMCCC_KVM_FUNC_ASYNC_PF_ENABLE + + Used by the guest to enable or disable the feature on the specific vCPU. + The argument is made up of shared buffer and flags. The shared buffer + is written by host to indicate the reason about the delivered asynchronous + page fault and token (sequence number) to identify that. There are two + flags are supported: KVM_ASYNC_PF_ENABLED is used to enable or disable + the feature. KVM_ASYNC_PF_SEND_ALWAYS allows to deliver page-not-present + notification regardless of the guest's state. Otherwise, the notification + is delivered only when the guest is in user mode. + + * ARM_SMCCC_KVM_FUNC_ASYNC_PF_IRQ_ACK + + Used by the guest to acknowledge the completion of page-ready notification.
Documentation/virt/kvm/arm/index.rst +1 -0
@@ -7,6 +7,7 @@ ARM .. toctree:: :maxdepth: 2 + apf hyp-abi psci pvtime
Signature · 6 lines
2.23.0 _______________________________________________ kvmarm mailing list [email protected] https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
Re: [PATCH v4 15/15] KVM: arm64: Add async PF document
Hi Gavin,
Quoted 16 lines · Gavin Shan
This adds document to explain the interface for asynchronous page fault and how it works in general.
Signed-off-by Gavin Shan <[email protected]>--- Documentation/virt/kvm/arm/apf.rst | 143 +++++++++++++++++++++++++++ Documentation/virt/kvm/arm/index.rst | 1 + 2 files changed, 144 insertions(+) create mode 100644 Documentation/virt/kvm/arm/apf.rstDocumentation/virt/kvm/arm/apf.rst new file +0
-0
Documentation/virt/kvm/arm/apf.rst line 10
Quoted 10 lines
Documentation/virt/kvm/arm/apf.rst new file +10
-0@@ -0,0 +1,143 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Asynchronous Page Fault Support for arm64 +========================================= + +There are two stages of page faults when KVM module is enabled as accelerator +to the guest. The guest is responsible for handling the stage-1 page faults, +while the host handles the stage-2 page faults. During the period of handling +the stage-2 page faults, the guest is suspended until the requested page is +ready. It could take several milliseconds, even hundreds of milliseconds in
s/It could take several milliseconds, even hundreds of milliseconds/It
could take up to hundreds of milliseconds
Documentation/virt/kvm/arm/apf.rst line 13
Quoted 3 lines
Documentation/virt/kvm/arm/apf.rst new file +3
-0+extreme situations because I/O might be required to move the requested page +from disk to DRAM. The guest does not do any work when it is suspended. The +feature (Asynchronous Page Fault) is introduced to take advantage of the
s/The feature (Asynchronous Page Fault)/ The Asynchronous Page Fault feature allows to improve the overall performance by allowing the guest to reschedule ... ?
Documentation/virt/kvm/arm/apf.rst
Quoted 4 lines
Documentation/virt/kvm/arm/apf.rst new file +4
-0+suspending period and to improve the overall performance. + +There are two paths in order to fulfil the asynchronous page fault, called +as control path and data path.
The asynchronous page fault is implemented upon a control path and a data path?
The control path allows the VMM or guest to
Documentation/virt/kvm/arm/apf.rst
Quoted 10 lines
Documentation/virt/kvm/arm/apf.rst new file +10
-0+configure the functionality, while the notifications are delivered in data +path. The notifications are classified into page-not-present and page-ready +notifications. + +Data Path +--------- + +There are two types of notifications delivered from host to guest in the +data path: page-not-present and page-ready notification. They are delivered +through SDEI event and (PPI) interrupt separately.
s/separately/respectively
Besides, there is a shared
Documentation/virt/kvm/arm/apf.rst line 28
Quoted 1 line
Documentation/virt/kvm/arm/apf.rst new file +1
-0+buffer between host and guest to indicate the reason and sequential token,
s/to indicate/that indicates
Can you clarify 'reason'?
Also a sequential token is used ...
Documentation/virt/kvm/arm/apf.rst line 30
Quoted 2 lines
Documentation/virt/kvm/arm/apf.rst new file +2
-0+which is used to identify the asynchronous page fault. The reason and token +resident in the shared buffer is written by host, read and cleared by guest.
s/is/are
Documentation/virt/kvm/arm/apf.rst line 37
Quoted 7 lines
Documentation/virt/kvm/arm/apf.rst new file +7
-0+An asynchronous page fault is delivered and completed as below. + +(1) When an asynchronous page fault starts, a (workqueue) worker is created + and queued to the vCPU's pending queue. The worker makes the requested + page ready and resident to DRAM in the background. The shared buffer is + updated with reason and sequential token. After that, SDEI event is sent + to guest as page-not-present notification.
This gives the impression the SDEI event is sent after the worker completes the job. I think you should rephrase.
Documentation/virt/kvm/arm/apf.rst line 41
Quoted 4 lines
Documentation/virt/kvm/arm/apf.rst new file +4
-0+ +(2) When the SDEI event is received on guest, the current process is tagged + with TIF_ASYNC_PF and associated with a wait queue. The process is ready + to keep rescheduling itself on switching from kernel to user mode. After
above sentence sounds a bit cryptic to me: ~ waits for being rescheduled later?
Documentation/virt/kvm/arm/apf.rst line 48
Quoted 7 lines
Documentation/virt/kvm/arm/apf.rst new file +7
-0+ that, a reschedule IPI is sent to current CPU and the received SDEI event + is acknowledged. Note that the IPI is delivered when the acknowledgment + on the SDEI event is received on host. + +(3) On the host, the worker is dequeued from the vCPU's pending queue and + enqueued to its completion queue when the requested page becomes ready. + In the mean while, KVM_REQ_ASYNC_PF request is sent the vCPU if the
in the meanwhile here and below
Documentation/virt/kvm/arm/apf.rst line 49
Quoted 1 line
Documentation/virt/kvm/arm/apf.rst new file +1
-0+ worker is the first element enqueued to the completion queue.
I think you should remind what is the intent of this KVM_REQ_ASYNC_PF request, ie. notify that the page is ready.
Documentation/virt/kvm/arm/apf.rst line 58
Quoted 10 lines
Documentation/virt/kvm/arm/apf.rst new file +9
-0+ +(4) With pending KVM_REQ_ASYNC_PF request, the first worker in the completion + queue is dequeued and destroyed. In the mean while, a (PPI) interrupt is + sent to guest with updated reason and token in the shared buffer. + +(5) When the (PPI) interrupt is received on guest, the affected process is + located using the token and waken up after its TIF_ASYNC_PF tag is cleared. + After that, the interrupt is acknowledged through SMCCC interface. The + workers in the completion queue is dequeued and destroyed if any workers
the worker
Isn't it destroyed even if no other worker exist?
Quoted 1 line
+ exist, and another (PPI) interrupt is sent to the guest.
I think you should briefly remind the motivation of SDEI and PPI mechanism for both synchros. Maybe by doing an analogy with x86 implementation?
Documentation/virt/kvm/arm/apf.rst
Quoted 7 lines
Documentation/virt/kvm/arm/apf.rst new file +7
-0+ +Control Path +------------ + +The configurations are passed through SMCCC or ioctl interface. The SDEI +event and (PPI) interrupt are owned by VMM, so the SDEI event and interrupt +numbers are configured through ioctl command on per-vCPU basis.
The "owned" terminology looks weird here. Do you mean the SDEI event number and the PPI ID are defined by the VMM userspace?
Besides,
Quoted 30 lines
Documentation/virt/kvm/arm/apf.rst new file +30
-0+the functionality might be enabled and configured through ioctl interface +by VMM during migration: + + * KVM_ARM_ASYNC_PF_CMD_GET_VERSION + + Returns the current version of the feature, supported by the host. It is + made up of major, minor and revision fields. Each field is one byte in + length. + + * KVM_ARM_ASYNC_PF_CMD_GET_SDEI: + + Retrieve the SDEI event number, used for page-not-present notification, + so that it can be configured on destination VM in the scenario of + migration. + + * KVM_ARM_ASYNC_PF_GET_IRQ: + + Retrieve the IRQ (PPI) number, used for page-ready notification, so that + it can be configured on destination VM in the scenario of migration. + + * KVM_ARM_ASYNC_PF_CMD_GET_CONTROL + + Retrieve the address of control block, so that it can be configured on + destination VM in the scenario of migration. + + * KVM_ARM_ASYNC_PF_CMD_SET_SDEI: + + Used by VMM to configure number of SDEI event, which is used to deliver + page-not-present notification by host. This is used when VM is started + or migrated.
Documentation/virt/kvm/arm/apf.rst line 106
Quoted 10 lines
Documentation/virt/kvm/arm/apf.rst new file +10
-0+ + * KVM_ARM_ASYNC_PF_CMD_SET_IRQ + + Used by VMM to configure number of (PPI) interrupt, which is used to + deliver page-ready notification by host. This is used when VM is started + or migrated. + + * KVM_ARM_ASYNC_PF_CMD_SET_CONTROL + + Set the control block on the destination VM in the scenario of migration.
What is the size of this control block?
Quoted 5 lines
Documentation/virt/kvm/arm/apf.rst new file +5
-0+ +The other configurations are passed through SMCCC interface. The host exports +the capability through KVM vendor specific service, which is identified by +ARM_SMCCC_KVM_FUNC_ASYNC_PF_FUNC_ID. There are several functions defined for +this:
Documentation/virt/kvm/arm/apf.rst line 121
Quoted 10 lines
Documentation/virt/kvm/arm/apf.rst new file +10
-0+ + * ARM_SMCCC_KVM_FUNC_ASYNC_PF_VERSION + + Returns the current version of the feature, supported by the host. It is + made up of major, minor and revision fields. Each field is one byte in + length. + + * ARM_SMCCC_KVM_FUNC_ASYNC_PF_SLOTS + + Returns the size of the hashed GFN table. It is used by guest to set up
by the guest
Documentation/virt/kvm/arm/apf.rst line 128
Quoted 7 lines
Documentation/virt/kvm/arm/apf.rst new file +7
-0+ the capacity of waiting process table. + + * ARM_SMCCC_KVM_FUNC_ASYNC_PF_SDEI + * ARM_SMCCC_KVM_FUNC_ASYNC_PF_IRQ + + Used by the guest to retrieve the SDEI event and (PPI) interrupt number + that are configured by VMM.
How does the guest recognize which SDEI event num it shall register. Same question for PPI? What if we were to expose the guest with several SDEIs?
Documentation/virt/kvm/arm/apf.rst line 141
Quoted 13 lines
Documentation/virt/kvm/arm/apf.rst new file +13
-0+ + * ARM_SMCCC_KVM_FUNC_ASYNC_PF_ENABLE + + Used by the guest to enable or disable the feature on the specific vCPU. + The argument is made up of shared buffer and flags. The shared buffer + is written by host to indicate the reason about the delivered asynchronous + page fault and token (sequence number) to identify that. There are two + flags are supported: KVM_ASYNC_PF_ENABLED is used to enable or disable + the feature. KVM_ASYNC_PF_SEND_ALWAYS allows to deliver page-not-present + notification regardless of the guest's state. Otherwise, the notification + is delivered only when the guest is in user mode. + + * ARM_SMCCC_KVM_FUNC_ASYNC_PF_IRQ_ACK
How does it compare to x86? I mean there are a huger number of IOCTLs and SMCCC calls to achieve the functionaly. Was the x86 implementation as invasive as this implementation?
Thanks
Eric
Quoted 15 lines
Documentation/virt/kvm/arm/apf.rst new file +2
-0+ + Used by the guest to acknowledge the completion of page-ready notification.Documentation/virt/kvm/arm/index.rst +1
-0@@ -7,6 +7,7 @@ ARM .. toctree:: :maxdepth: 2 + apf hyp-abi psci pvtime