Skip to contentSkip to conversation

KVM: x86: async_pf: check earlier if can deliver async pf

PATCH In review Nikita Kalyazin 3 participants 13 messages Nov 18, 2024 – Nov 27, 2024

Subsystems (4)
lore
Share & tools
lore
#0 lore raw

PATCH 1/1 KVM: x86: async_pf: check earlier if can deliver async pf

On x86, async pagefault events can only be delivered if the page fault was triggered by guest userspace, not kernel. This is because the guest may be in non-sleepable context and will not be able to reschedule.

However existing implementation pays the following overhead even for the kernel-originated faults, even though it is known in advance that they cannot be processed asynchronously:
- allocate async PF token
- create and schedule an async work

This patch avoids the overhead above in case of kernel-originated faults by moving the kvm_can_deliver_async_pf check from kvm_arch_async_page_not_present to __kvm_faultin_pfn.

Note that the existing check kvm_can_do_async_pf already calls kvm_can_deliver_async_pf internally, however it only does that if the kvm_hlt_in_guest check is true, ie userspace requested KVM not to exit on guest halts via KVM_CAP_X86_DISABLE_EXITS. In that case the code proceeds with the async fault processing with the following justification in 1dfdb45ec510ba27e366878f97484e9c9e728902 ("KVM: x86:
clean up conditions for asynchronous page fault handling"):

"Even when asynchronous page fault is disabled, KVM does not want to pause the host if a guest triggers a page fault; instead it will put it into an artificial HLT state that allows running other host processes while allowing interrupt delivery into the guest."

---
 arch/x86/kvm/mmu/mmu.c | 3 ++-
 arch/x86/kvm/x86.c     | 5 ++---
 arch/x86/kvm/x86.h     | 2 ++
 3 files changed, 6 insertions(+), 4 deletions(-)
arch/x86/kvm/mmu/mmu.c +2 -1
index 22e7ad235123..11d29d15b6cd 100644
@@ -4369,7 +4369,8 @@ static int __kvm_mmu_faultin_pfn(struct kvm_vcpu *vcpu,
 			trace_kvm_async_pf_repeated_fault(fault->addr, fault->gfn);
 			kvm_make_request(KVM_REQ_APF_HALT, vcpu);
 			return RET_PF_RETRY;
-		} else if (kvm_arch_setup_async_pf(vcpu, fault)) {
+		} else if (kvm_can_deliver_async_pf(vcpu) &&
+			kvm_arch_setup_async_pf(vcpu, fault)) {
 			return RET_PF_RETRY;
 		}
 	}
arch/x86/kvm/x86.c +2 -3
index 2e713480933a..8edae75b39f7 100644
@@ -13355,7 +13355,7 @@ static inline bool apf_pageready_slot_free(struct kvm_vcpu *vcpu)
 	return !val;
 }
 
-static bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu)
+bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu)
 {
 
 	if (!kvm_pv_async_pf_enabled(vcpu))
@@ -13406,8 +13406,7 @@ bool kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
 	trace_kvm_async_pf_not_present(work->arch.token, work->cr2_or_gpa);
 	kvm_add_async_pf_gfn(vcpu, work->arch.gfn);
 
-	if (kvm_can_deliver_async_pf(vcpu) &&
-	    !apf_put_user_notpresent(vcpu)) {
+	if (!apf_put_user_notpresent(vcpu)) {
 		fault.vector = PF_VECTOR;
 		fault.error_code_valid = true;
 		fault.error_code = 0;
arch/x86/kvm/x86.h +2 -0
index ec623d23d13d..9647f41e5c49 100644
@@ -387,6 +387,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu);
 fastpath_t handle_fastpath_hlt(struct kvm_vcpu *vcpu);
 
+bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu);
+
 extern struct kvm_caps kvm_caps;
 extern struct kvm_host_values kvm_host;
 

base-commit: d96c77bd4eeba469bddbbb14323d2191684da82a

Signature · 1 line
2.40.1
#1 lore raw
Quoted 4 lines · Nikita Kalyazin

On x86, async pagefault events can only be delivered if the page fault was triggered by guest userspace, not kernel. This is because the guest may be in non-sleepable context and will not be able to reschedule.

We used to set KVM_ASYNC_PF_SEND_ALWAYS for Linux guests before

commit 3a7c8fafd1b42adea229fd204132f6a2fb3cd2d9

Author: Thomas Gleixner <[email protected]>
Date:   Fri Apr 24 09:57:56 2020 +0200

x86/kvm: Restrict ASYNC_PF to user space

but KVM side of the feature is kind of still there, namely

kvm_pv_enable_async_pf() sets

    vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS);

and then we check it in

kvm_can_deliver_async_pf():

     if (vcpu->arch.apf.send_user_only &&
         kvm_x86_call(get_cpl)(vcpu) == 0)
             return false;

and this can still be used by some legacy guests I suppose. How about we start with removing this completely? It does not matter if some legacy guest wants to get an APF for CPL0, we are never obliged to actually use the mechanism.

Quoted 83 lines

However existing implementation pays the following overhead even for the kernel-originated faults, even though it is known in advance that they cannot be processed asynchronously:
- allocate async PF token
- create and schedule an async work

This patch avoids the overhead above in case of kernel-originated faults by moving the kvm_can_deliver_async_pf check from kvm_arch_async_page_not_present to __kvm_faultin_pfn.

Note that the existing check kvm_can_do_async_pf already calls kvm_can_deliver_async_pf internally, however it only does that if the kvm_hlt_in_guest check is true, ie userspace requested KVM not to exit on guest halts via KVM_CAP_X86_DISABLE_EXITS. In that case the code proceeds with the async fault processing with the following justification in 1dfdb45ec510ba27e366878f97484e9c9e728902 ("KVM: x86:
clean up conditions for asynchronous page fault handling"):

"Even when asynchronous page fault is disabled, KVM does not want to pause the host if a guest triggers a page fault; instead it will put it into an artificial HLT state that allows running other host processes while allowing interrupt delivery into the guest."

---
 arch/x86/kvm/mmu/mmu.c | 3 ++-
 arch/x86/kvm/x86.c     | 5 ++---
 arch/x86/kvm/x86.h     | 2 ++
 3 files changed, 6 insertions(+), 4 deletions(-)
arch/x86/kvm/mmu/mmu.c +2 -1
index 22e7ad235123..11d29d15b6cd 100644
@@ -4369,7 +4369,8 @@ static int __kvm_mmu_faultin_pfn(struct kvm_vcpu *vcpu,
 			trace_kvm_async_pf_repeated_fault(fault->addr, fault->gfn);
 			kvm_make_request(KVM_REQ_APF_HALT, vcpu);
 			return RET_PF_RETRY;
-		} else if (kvm_arch_setup_async_pf(vcpu, fault)) {
+		} else if (kvm_can_deliver_async_pf(vcpu) &&
+			kvm_arch_setup_async_pf(vcpu, fault)) {
 			return RET_PF_RETRY;
 		}
 	}
arch/x86/kvm/x86.c +2 -3
index 2e713480933a..8edae75b39f7 100644
@@ -13355,7 +13355,7 @@ static inline bool apf_pageready_slot_free(struct kvm_vcpu *vcpu)
 	return !val;
 }
 
-static bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu)
+bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu)
 {
 
 	if (!kvm_pv_async_pf_enabled(vcpu))
@@ -13406,8 +13406,7 @@ bool kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
 	trace_kvm_async_pf_not_present(work->arch.token, work->cr2_or_gpa);
 	kvm_add_async_pf_gfn(vcpu, work->arch.gfn);
 
-	if (kvm_can_deliver_async_pf(vcpu) &&
-	    !apf_put_user_notpresent(vcpu)) {
+	if (!apf_put_user_notpresent(vcpu)) {
 		fault.vector = PF_VECTOR;
 		fault.error_code_valid = true;
 		fault.error_code = 0;
arch/x86/kvm/x86.h +2 -0
index ec623d23d13d..9647f41e5c49 100644
@@ -387,6 +387,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu);
 fastpath_t handle_fastpath_hlt(struct kvm_vcpu *vcpu);
 
+bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu);
+
 extern struct kvm_caps kvm_caps;
 extern struct kvm_host_values kvm_host;
 

base-commit: d96c77bd4eeba469bddbbb14323d2191684da82a

Signature · 1 line
Vitaly
#2 lore raw
Quoted 25 lines · Vitaly Kuznetsov
Quoted 4 lines · Nikita Kalyazin

On x86, async pagefault events can only be delivered if the page fault was triggered by guest userspace, not kernel. This is because the guest may be in non-sleepable context and will not be able to reschedule.

We used to set KVM_ASYNC_PF_SEND_ALWAYS for Linux guests before

commit 3a7c8fafd1b42adea229fd204132f6a2fb3cd2d9

Author: Thomas Gleixner <[email protected]>
Date:   Fri Apr 24 09:57:56 2020 +0200

x86/kvm: Restrict ASYNC_PF to user space

but KVM side of the feature is kind of still there, namely

kvm_pv_enable_async_pf() sets

     vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS);

and then we check it in

kvm_can_deliver_async_pf():

Quoted 8 lines
      if (vcpu->arch.apf.send_user_only &&
          kvm_x86_call(get_cpl)(vcpu) == 0)
              return false;

and this can still be used by some legacy guests I suppose. How about we start with removing this completely? It does not matter if some legacy guest wants to get an APF for CPL0, we are never obliged to actually use the mechanism.

If I understand you correctly, the change you propose is rather orthogonal to the original one as the check is performed after the work has been already allocated (in kvm_setup_async_pf). Would you expect tangible savings from omitting the send_user_only check?

Quoted 3 lines

--
Vitaly

#3 lore raw
Quoted 35 lines · Nikita Kalyazin
Quoted 25 lines · Vitaly Kuznetsov
Quoted 4 lines · Nikita Kalyazin

On x86, async pagefault events can only be delivered if the page fault was triggered by guest userspace, not kernel. This is because the guest may be in non-sleepable context and will not be able to reschedule.

We used to set KVM_ASYNC_PF_SEND_ALWAYS for Linux guests before

commit 3a7c8fafd1b42adea229fd204132f6a2fb3cd2d9

Author: Thomas Gleixner <[email protected]>
Date:   Fri Apr 24 09:57:56 2020 +0200

x86/kvm: Restrict ASYNC_PF to user space

but KVM side of the feature is kind of still there, namely

kvm_pv_enable_async_pf() sets

     vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS);

and then we check it in

kvm_can_deliver_async_pf():

Quoted 8 lines
      if (vcpu->arch.apf.send_user_only &&
          kvm_x86_call(get_cpl)(vcpu) == 0)
              return false;

and this can still be used by some legacy guests I suppose. How about we start with removing this completely? It does not matter if some legacy guest wants to get an APF for CPL0, we are never obliged to actually use the mechanism.

Quoted 5 lines

If I understand you correctly, the change you propose is rather orthogonal to the original one as the check is performed after the work has been already allocated (in kvm_setup_async_pf). Would you expect tangible savings from omitting the send_user_only check?

No, I don't expect any performance benefits. Basically, I was referring to the description of your patch: "On x86, async pagefault events can only be delivered if the page fault was triggered by guest userspace, not kernel" and strictly speaking this is not true today as we still support KVM_ASYNC_PF_SEND_ALWAYS in KVM. Yes, modern Linux guest don't use it but the flag is there. Basically, my suggestion is to start with a cleanup (untested):

arch/x86/include/asm/kvm_host.h +0 -1
index 6d9f763a7bb9..d0906830a9fb 100644
@@ -974,7 +974,6 @@ struct kvm_vcpu_arch {
                u64 msr_int_val; /* MSR_KVM_ASYNC_PF_INT */
                u16 vec;
                u32 id;
-               bool send_user_only;
                u32 host_apf_flags;
                bool delivery_as_pf_vmexit;
                bool pageready_pending;
arch/x86/include/uapi/asm/kvm_para.h +1 -1
index a1efa7907a0b..5558a1ec3dc9 100644
@@ -87,7 +87,7 @@ struct kvm_clock_pairing {
 #define KVM_MAX_MMU_OP_BATCH           32
 
 #define KVM_ASYNC_PF_ENABLED                   (1 << 0)
-#define KVM_ASYNC_PF_SEND_ALWAYS               (1 << 1)
+#define KVM_ASYNC_PF_SEND_ALWAYS               (1 << 1) /* deprecated */
 #define KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT     (1 << 2)
 #define KVM_ASYNC_PF_DELIVERY_AS_INT           (1 << 3)
 
arch/x86/kvm/x86.c +1 -3
index 83fe0a78146f..cd15e738ca9b 100644
@@ -3585,7 +3585,6 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
                                        sizeof(u64)))
                return 1;
 
-       vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS);
        vcpu->arch.apf.delivery_as_pf_vmexit = data & KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT;
 
        kvm_async_pf_wakeup_all(vcpu);
@@ -13374,8 +13373,7 @@ static bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu)
        if (!kvm_pv_async_pf_enabled(vcpu))
                return false;
 
-       if (vcpu->arch.apf.send_user_only &&
-           kvm_x86_call(get_cpl)(vcpu) == 0)
+       if (kvm_x86_call(get_cpl)(vcpu) == 0)
                return false;
 
        if (is_guest_mode(vcpu)) {
Signature · 1 line
Vitaly
#4 lore raw
Quoted 26 lines · Vitaly Kuznetsov
arch/x86/include/uapi/asm/kvm_para.h +1 -1
index a1efa7907a0b..5558a1ec3dc9 100644
@@ -87,7 +87,7 @@ struct kvm_clock_pairing {
 #define KVM_MAX_MMU_OP_BATCH           32
 
 #define KVM_ASYNC_PF_ENABLED                   (1 << 0)
-#define KVM_ASYNC_PF_SEND_ALWAYS               (1 << 1)
+#define KVM_ASYNC_PF_SEND_ALWAYS               (1 << 1) /* deprecated */
 #define KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT     (1 << 2)
 #define KVM_ASYNC_PF_DELIVERY_AS_INT           (1 << 3)
 
arch/x86/kvm/x86.c +0 -1
index 83fe0a78146f..cd15e738ca9b 100644
@@ -3585,7 +3585,6 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
                                        sizeof(u64)))
                return 1;
 
-       vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS);
        vcpu->arch.apf.delivery_as_pf_vmexit = data & KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT;
 
        kvm_async_pf_wakeup_all(vcpu);

arch/x86/kvm/x86.c static bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu) · line 13376

Quoted 6 lines
arch/x86/kvm/x86.c +1 -2
@@ -13374,8 +13373,7 @@ static bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu)
        if (!kvm_pv_async_pf_enabled(vcpu))
                return false;
 
-       if (vcpu->arch.apf.send_user_only &&
-           kvm_x86_call(get_cpl)(vcpu) == 0)
+       if (kvm_x86_call(get_cpl)(vcpu) == 0)

By x86's general definition of "user", this should be "!= 3" :-)

#5 lore raw
In reply to Nikita Kalyazin
Quoted 10 lines · Nikita Kalyazin

On x86, async pagefault events can only be delivered if the page fault was triggered by guest userspace, not kernel. This is because the guest may be in non-sleepable context and will not be able to reschedule.

However existing implementation pays the following overhead even for the kernel-originated faults, even though it is known in advance that they cannot be processed asynchronously:
- allocate async PF token
- create and schedule an async work

Very deliberately, because as noted below, async page faults aren't limited to the paravirt case.

Quoted 1 line

This patch avoids the overhead above in case of kernel-originated faults

Please avoid "This patch".

Quoted 11 lines

by moving the kvm_can_deliver_async_pf check from kvm_arch_async_page_not_present to __kvm_faultin_pfn.

Note that the existing check kvm_can_do_async_pf already calls kvm_can_deliver_async_pf internally, however it only does that if the kvm_hlt_in_guest check is true, ie userspace requested KVM not to exit on guest halts via KVM_CAP_X86_DISABLE_EXITS. In that case the code proceeds with the async fault processing with the following justification in 1dfdb45ec510ba27e366878f97484e9c9e728902 ("KVM: x86:
clean up conditions for asynchronous page fault handling"):

Quoted 4 lines

"Even when asynchronous page fault is disabled, KVM does not want to pause the host if a guest triggers a page fault; instead it will put it into an artificial HLT state that allows running other host processes while allowing interrupt delivery into the guest."

None of this justifies breaking host-side, non-paravirt async page faults. If a vCPU hits a missing page, KVM can schedule out the vCPU and let something else run on the pCPU, or enter idle and let the SMT sibling get more cycles, or maybe even enter a low enough sleep state to let other cores turbo a wee bit.

I have no objection to disabling host async page faults, e.g. it's probably a net negative for 1:1 vCPU:pCPU pinned setups, but such disabling needs an opt-in from userspace.

#6 lore raw
Quoted 3 lines · Sean Christopherson
Quoted 1 line

This patch avoids the overhead above in case of kernel-originated faults

Please avoid "This patch".

Ack, thanks.

Quoted 16 lines
Quoted 11 lines

by moving the kvm_can_deliver_async_pf check from kvm_arch_async_page_not_present to __kvm_faultin_pfn.

Note that the existing check kvm_can_do_async_pf already calls kvm_can_deliver_async_pf internally, however it only does that if the kvm_hlt_in_guest check is true, ie userspace requested KVM not to exit on guest halts via KVM_CAP_X86_DISABLE_EXITS. In that case the code proceeds with the async fault processing with the following justification in 1dfdb45ec510ba27e366878f97484e9c9e728902 ("KVM: x86:
clean up conditions for asynchronous page fault handling"):

Quoted 4 lines

"Even when asynchronous page fault is disabled, KVM does not want to pause the host if a guest triggers a page fault; instead it will put it into an artificial HLT state that allows running other host processes while allowing interrupt delivery into the guest."

Quoted 8 lines

None of this justifies breaking host-side, non-paravirt async page faults. If a vCPU hits a missing page, KVM can schedule out the vCPU and let something else run on the pCPU, or enter idle and let the SMT sibling get more cycles, or maybe even enter a low enough sleep state to let other cores turbo a wee bit.

I have no objection to disabling host async page faults, e.g. it's probably a net negative for 1:1 vCPU:pCPU pinned setups, but such disabling needs an opt-in from userspace.

That's a good point, I didn't think about it. The async work would still need to execute somewhere in that case (or sleep in GUP until the page is available). If processing the fault synchronously, the vCPU thread can also sleep in the same way freeing the pCPU for something else, so the amount of work to be done looks equivalent (please correct me otherwise). What's the net gain of moving that to an async work in the host async fault case? "while allowing interrupt delivery into the guest." -- is this the main advantage?

#7 lore raw
Quoted 6 lines · Nikita Kalyazin
Quoted 5 lines · Sean Christopherson

None of this justifies breaking host-side, non-paravirt async page faults. If a vCPU hits a missing page, KVM can schedule out the vCPU and let something else run on the pCPU, or enter idle and let the SMT sibling get more cycles, or maybe even enter a low enough sleep state to let other cores turbo a wee bit.

Quoted 7 lines
Quoted 3 lines

I have no objection to disabling host async page faults, e.g. it's probably a net negative for 1:1 vCPU:pCPU pinned setups, but such disabling needs an opt-in from userspace.

That's a good point, I didn't think about it. The async work would still need to execute somewhere in that case (or sleep in GUP until the page is available).

The "async work" is often an I/O operation, e.g. to pull in the page from disk, or over the network from the source. The *CPU* doesn't need to actively do anything for those operations. The I/O is initiated, so the CPU can do something else, or go idle if there's no other work to be done.

Quoted 2 lines

If processing the fault synchronously, the vCPU thread can also sleep in the same way freeing the pCPU for something else,

If and only if the vCPU can handle a PV async #PF. E.g. if the guest kernel flat out doesn't support PV async #PF, or the fault happened while the guest was in an incompatible mode, etc.

If KVM doesn't do async #PFs of any kind, the vCPU will spin on the fault until the I/O completes and the page is ready.

Quoted 4 lines

so the amount of work to be done looks equivalent (please correct me otherwise). What's the net gain of moving that to an async work in the host async fault case? "while allowing interrupt delivery into the guest." -- is this the main advantage?

#8 lore raw
Quoted 23 lines · Sean Christopherson
Quoted 6 lines · Nikita Kalyazin
Quoted 5 lines · Sean Christopherson

None of this justifies breaking host-side, non-paravirt async page faults. If a vCPU hits a missing page, KVM can schedule out the vCPU and let something else run on the pCPU, or enter idle and let the SMT sibling get more cycles, or maybe even enter a low enough sleep state to let other cores turbo a wee bit.

Quoted 7 lines
Quoted 3 lines

I have no objection to disabling host async page faults, e.g. it's probably a net negative for 1:1 vCPU:pCPU pinned setups, but such disabling needs an opt-in from userspace.

That's a good point, I didn't think about it. The async work would still need to execute somewhere in that case (or sleep in GUP until the page is available).

The "async work" is often an I/O operation, e.g. to pull in the page from disk, or over the network from the source. The *CPU* doesn't need to actively do anything for those operations. The I/O is initiated, so the CPU can do something else, or go idle if there's no other work to be done.

Quoted 2 lines

If processing the fault synchronously, the vCPU thread can also sleep in the same way freeing the pCPU for something else,

Quoted 6 lines

If and only if the vCPU can handle a PV async #PF. E.g. if the guest kernel flat out doesn't support PV async #PF, or the fault happened while the guest was in an incompatible mode, etc.

If KVM doesn't do async #PFs of any kind, the vCPU will spin on the fault until the I/O completes and the page is ready.

I ran a little experiment to see that by backing guest memory by a file on FUSE and delaying response to one of the read operations to emulate a delay in fault processing.

1. Original (the patch isn't applied)

vCPU thread (disk-sleeping):

[<0>] kvm_vcpu_block+0x62/0xe0
[<0>] kvm_arch_vcpu_ioctl_run+0x240/0x1e30
[<0>] kvm_vcpu_ioctl+0x2f1/0x860
[<0>] __x64_sys_ioctl+0x87/0xc0
[<0>] do_syscall_64+0x47/0x110
[<0>] entry_SYSCALL_64_after_hwframe+0x76/0x7e

Async task (disk-sleeping):

[<0>] folio_wait_bit_common+0x116/0x2e0
[<0>] filemap_fault+0xe5/0xcd0
[<0>] __do_fault+0x30/0xc0
[<0>] do_fault+0x9a/0x580
[<0>] __handle_mm_fault+0x684/0x8a0
[<0>] handle_mm_fault+0xc9/0x220
[<0>] __get_user_pages+0x248/0x12c0
[<0>] get_user_pages_remote+0xef/0x470
[<0>] async_pf_execute+0x99/0x1c0
[<0>] process_one_work+0x145/0x360
[<0>] worker_thread+0x294/0x3b0
[<0>] kthread+0xdb/0x110
[<0>] ret_from_fork+0x2d/0x50
[<0>] ret_from_fork_asm+0x1a/0x30

2. With the patch applied (no async task)

vCPU thread (disk-sleeping):

[<0>] folio_wait_bit_common+0x116/0x2e0
[<0>] filemap_fault+0xe5/0xcd0
[<0>] __do_fault+0x30/0xc0
[<0>] do_fault+0x36f/0x580
[<0>] __handle_mm_fault+0x684/0x8a0
[<0>] handle_mm_fault+0xc9/0x220
[<0>] __get_user_pages+0x248/0x12c0
[<0>] get_user_pages_unlocked+0xf7/0x380
[<0>] hva_to_pfn+0x2a2/0x440
[<0>] __kvm_faultin_pfn+0x5e/0x90
[<0>] kvm_mmu_faultin_pfn+0x1ec/0x690
[<0>] kvm_tdp_page_fault+0xba/0x160
[<0>] kvm_mmu_do_page_fault+0x1cc/0x210
[<0>] kvm_mmu_page_fault+0x8e/0x600
[<0>] vmx_handle_exit+0x14c/0x6c0
[<0>] kvm_arch_vcpu_ioctl_run+0xeb1/0x1e30
[<0>] kvm_vcpu_ioctl+0x2f1/0x860
[<0>] __x64_sys_ioctl+0x87/0xc0
[<0>] do_syscall_64+0x47/0x110
[<0>] entry_SYSCALL_64_after_hwframe+0x76/0x7e

In both cases the fault handling code is blocked and the pCPU is free for other tasks. I can't see the vCPU spinning on the IO to get completed if the async task isn't created. I tried that with and without async PF enabled by the guest (MSR_KVM_ASYNC_PF_EN).

What am I missing?

Quoted 4 lines
Quoted 4 lines

so the amount of work to be done looks equivalent (please correct me otherwise). What's the net gain of moving that to an async work in the host async fault case? "while allowing interrupt delivery into the guest." -- is this the main advantage?

#9 lore raw
Quoted 34 lines · Nikita Kalyazin
Quoted 23 lines · Sean Christopherson
Quoted 6 lines · Nikita Kalyazin
Quoted 5 lines · Sean Christopherson

None of this justifies breaking host-side, non-paravirt async page faults. If a vCPU hits a missing page, KVM can schedule out the vCPU and let something else run on the pCPU, or enter idle and let the SMT sibling get more cycles, or maybe even enter a low enough sleep state to let other cores turbo a wee bit.

Quoted 7 lines
Quoted 3 lines

I have no objection to disabling host async page faults, e.g. it's probably a net negative for 1:1 vCPU:pCPU pinned setups, but such disabling needs an opt-in from userspace.

That's a good point, I didn't think about it. The async work would still need to execute somewhere in that case (or sleep in GUP until the page is available).

The "async work" is often an I/O operation, e.g. to pull in the page from disk, or over the network from the source. The *CPU* doesn't need to actively do anything for those operations. The I/O is initiated, so the CPU can do something else, or go idle if there's no other work to be done.

Quoted 2 lines

If processing the fault synchronously, the vCPU thread can also sleep in the same way freeing the pCPU for something else,

Quoted 6 lines

If and only if the vCPU can handle a PV async #PF. E.g. if the guest kernel flat out doesn't support PV async #PF, or the fault happened while the guest was in an incompatible mode, etc.

If KVM doesn't do async #PFs of any kind, the vCPU will spin on the fault until the I/O completes and the page is ready.

I ran a little experiment to see that by backing guest memory by a file on FUSE and delaying response to one of the read operations to emulate a delay in fault processing.

...

Quoted 6 lines

In both cases the fault handling code is blocked and the pCPU is free for other tasks. I can't see the vCPU spinning on the IO to get completed if the async task isn't created. I tried that with and without async PF enabled by the guest (MSR_KVM_ASYNC_PF_EN).

What am I missing?

Ah, I was wrong about the vCPU spinning.

The goal is specifically to schedule() from KVM context, i.e. from kvm_vcpu_block(), so that if a virtual interrupt arrives for the guest, KVM can wake the vCPU and deliver the IRQ, e.g. to reduce latency for interrupt delivery, and possible even to let the guest schedule in a different task if the IRQ is the guest's tick.

Letting mm/ or fs/ do schedule() means the only wake event even for the vCPU task is the completion of the I/O (or whatever the fault is waiting on).

#10 lore raw
Quoted 47 lines · Sean Christopherson
Quoted 34 lines · Nikita Kalyazin
Quoted 23 lines · Sean Christopherson
Quoted 6 lines · Nikita Kalyazin
Quoted 5 lines · Sean Christopherson

None of this justifies breaking host-side, non-paravirt async page faults. If a vCPU hits a missing page, KVM can schedule out the vCPU and let something else run on the pCPU, or enter idle and let the SMT sibling get more cycles, or maybe even enter a low enough sleep state to let other cores turbo a wee bit.

Quoted 7 lines
Quoted 3 lines

I have no objection to disabling host async page faults, e.g. it's probably a net negative for 1:1 vCPU:pCPU pinned setups, but such disabling needs an opt-in from userspace.

That's a good point, I didn't think about it. The async work would still need to execute somewhere in that case (or sleep in GUP until the page is available).

The "async work" is often an I/O operation, e.g. to pull in the page from disk, or over the network from the source. The *CPU* doesn't need to actively do anything for those operations. The I/O is initiated, so the CPU can do something else, or go idle if there's no other work to be done.

Quoted 2 lines

If processing the fault synchronously, the vCPU thread can also sleep in the same way freeing the pCPU for something else,

Quoted 6 lines

If and only if the vCPU can handle a PV async #PF. E.g. if the guest kernel flat out doesn't support PV async #PF, or the fault happened while the guest was in an incompatible mode, etc.

If KVM doesn't do async #PFs of any kind, the vCPU will spin on the fault until the I/O completes and the page is ready.

I ran a little experiment to see that by backing guest memory by a file on FUSE and delaying response to one of the read operations to emulate a delay in fault processing.

...

Quoted 6 lines

In both cases the fault handling code is blocked and the pCPU is free for other tasks. I can't see the vCPU spinning on the IO to get completed if the async task isn't created. I tried that with and without async PF enabled by the guest (MSR_KVM_ASYNC_PF_EN).

What am I missing?

Ah, I was wrong about the vCPU spinning.

Quoted 7 lines

The goal is specifically to schedule() from KVM context, i.e. from kvm_vcpu_block(), so that if a virtual interrupt arrives for the guest, KVM can wake the vCPU and deliver the IRQ, e.g. to reduce latency for interrupt delivery, and possible even to let the guest schedule in a different task if the IRQ is the guest's tick.

Letting mm/ or fs/ do schedule() means the only wake event even for the vCPU task is the completion of the I/O (or whatever the fault is waiting on).

Ok, great, then that's how I understood it last time. The only thing that is not entirely clear to me is like Vitaly says, KVM_ASYNC_PF_SEND_ALWAYS is no longer set, because we don't want to inject IRQs into the guest when it's in kernel mode, but the "host async PF" case would still allow IRQs (eg ticks like you said). Why is it safe to deliver them?

Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines

I have no objection to disabling host async page faults,
e.g. it's probably a net>>>>> negative for 1:1 vCPU:pCPU pinned setups, but such disabling needs an opt-in from>>>>> userspace.

Back to this, I couldn't see a significant effect of this optimisation with the original async PF so happy to give it up, but it does make a difference when applied to async PF user [2] in my setup. Would a new cap be a good way for users to express their opt-in for it?

[1]: https://lore.kernel.org/kvm/[email protected]/T/#ma719a9cb3e036e24ea8512abf9a625ddeaccfc96
[2]: https://lore.kernel.org/kvm/[email protected]/T/

#11 lore raw
Quoted 16 lines · Nikita Kalyazin
Quoted 15 lines · Sean Christopherson
Quoted 6 lines · Nikita Kalyazin

In both cases the fault handling code is blocked and the pCPU is free for other tasks. I can't see the vCPU spinning on the IO to get completed if the async task isn't created. I tried that with and without async PF enabled by the guest (MSR_KVM_ASYNC_PF_EN).

What am I missing?

Ah, I was wrong about the vCPU spinning.

The goal is specifically to schedule() from KVM context, i.e. from kvm_vcpu_block(), so that if a virtual interrupt arrives for the guest, KVM can wake the vCPU and deliver the IRQ, e.g. to reduce latency for interrupt delivery, and possible even to let the guest schedule in a different task if the IRQ is the guest's tick.

Quoted 8 lines
Quoted 2 lines

Letting mm/ or fs/ do schedule() means the only wake event even for the vCPU task is the completion of the I/O (or whatever the fault is waiting on).

Ok, great, then that's how I understood it last time. The only thing that is not entirely clear to me is like Vitaly says, KVM_ASYNC_PF_SEND_ALWAYS is no longer set, because we don't want to inject IRQs into the guest when it's in kernel mode, but the "host async PF" case would still allow IRQs (eg ticks like you said). Why is it safe to deliver them?

IRQs are fine, the problem with PV async #PF is that it directly injects a #PF, which the kernel may not be prepared to handle.

Quoted 7 lines
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines

I have no objection to disabling host async page faults,
e.g. it's probably a net>>>>> negative for 1:1 vCPU:pCPU pinned setups, but such disabling needs an opt-in from>>>>> userspace.

Back to this, I couldn't see a significant effect of this optimisation with the original async PF so happy to give it up, but it does make a difference when applied to async PF user [2] in my setup. Would a new cap be a good way for users to express their opt-in for it?

This probably needs to be handled in the context of the async #PF user series. If that series never lands, adding a new cap is likely a waste. And I suspect that even then, a capability may not be warranted (truly don't know, haven't looked at your other series).

#12 lore raw
Quoted 20 lines · Sean Christopherson
Quoted 19 lines · Nikita Kalyazin
Quoted 17 lines · Sean Christopherson
Quoted 6 lines · Nikita Kalyazin

In both cases the fault handling code is blocked and the pCPU is free for other tasks. I can't see the vCPU spinning on the IO to get completed if the async task isn't created. I tried that with and without async PF enabled by the guest (MSR_KVM_ASYNC_PF_EN).

What am I missing?

Ah, I was wrong about the vCPU spinning.

The goal is specifically to schedule() from KVM context, i.e. from kvm_vcpu_block(), so that if a virtual interrupt arrives for the guest, KVM can wake the vCPU and deliver the IRQ, e.g. to reduce latency for interrupt delivery, and possible even to let the guest schedule in a different task if the IRQ is the guest's tick.

Letting mm/ or fs/ do schedule() means the only wake event even for the vCPU task is the completion of the I/O (or whatever the fault is waiting on).

Quoted 8 lines
Quoted 5 lines

Ok, great, then that's how I understood it last time. The only thing that is not entirely clear to me is like Vitaly says, KVM_ASYNC_PF_SEND_ALWAYS is no longer set, because we don't want to inject IRQs into the guest when it's in kernel mode, but the "host async PF" case would still allow IRQs (eg ticks like you said). Why is it safe to deliver them?

IRQs are fine, the problem with PV async #PF is that it directly injects a #PF, which the kernel may not be prepared to handle.

You're right indeed, I was overfocused on IRQs for some reason.

Quoted 8 lines
Quoted 7 lines
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines

I have no objection to disabling host async page faults,
e.g. it's probably a net>>>>> negative for 1:1 vCPU:pCPU pinned setups, but such disabling needs an opt-in from>>>>> userspace.

Back to this, I couldn't see a significant effect of this optimisation with the original async PF so happy to give it up, but it does make a difference when applied to async PF user [2] in my setup. Would a new cap be a good way for users to express their opt-in for it?

Quoted 4 lines

This probably needs to be handled in the context of the async #PF user series. If that series never lands, adding a new cap is likely a waste. And I suspect that even then, a capability may not be warranted (truly don't know, haven't looked at your other series).

Yes, I meant that to be included in the async #PF user series (if required), not this one. Just wanted to bring it up here, because the thread already had the relevant context. Thanks.