Merge tag 'kvm-x86-asyncpf_abi-6.9' of https://github.com/kvm-x86/linux into HEAD

Guest-side KVM async #PF ABI cleanup for 6.9

Delete kvm_vcpu_pv_apf_data.enabled to fix a goof in KVM's async #PF ABI where
the enabled field pushes the size of "struct kvm_vcpu_pv_apf_data" from 64 to
68 bytes, i.e. beyond a single cache line.

The enabled field is purely a guest-side flag that Linux-as-a-guest uses to
track whether or not the guest has enabled async #PF support.  The actual flag
that is passed to the host, i.e. to KVM proper, is a single bit in a synthetic
MSR, MSR_KVM_ASYNC_PF_EN, i.e. is in a location completely unrelated to the
shared kvm_vcpu_pv_apf_data structure.

Simply drop the the field and use a dedicated guest-side per-CPU variable to
fix the ABI, as opposed to fixing the documentation to match reality.  KVM has
never consumed kvm_vcpu_pv_apf_data.enabled, so the odds of the ABI change
breaking anything are extremely low.

3 files changed, 15 insertions, 16 deletions

diff --git a/Documentation/virt/kvm/x86/msr.rst b/Documentation/virt/kvm/x86/msr.rst
index 9315fc385fb0..3aecf2a70e7b 100644
--- a/Documentation/virt/kvm/x86/msr.rst
+++ b/Documentation/virt/kvm/x86/msr.rst
@@ -193,8 +193,8 @@ data:
 	Asynchronous page fault (APF) control MSR.
 
 	Bits 63-6 hold 64-byte aligned physical address of a 64 byte memory area
-	which must be in guest RAM and must be zeroed. This memory is expected
-	to hold a copy of the following structure::
+	which must be in guest RAM. This memory is expected to hold the
+	following structure::
 
 	  struct kvm_vcpu_pv_apf_data {
 		/* Used for 'page not present' events delivered via #PF */
@@ -204,7 +204,6 @@ data:
 		__u32 token;
 
 		__u8 pad[56];
-		__u32 enabled;
 	  };
 
 	Bits 5-4 of the MSR are reserved and should be zero. Bit 0 is set to 1
@@ -232,14 +231,14 @@ data:
 	as regular page fault, guest must reset 'flags' to '0' before it does
 	something that can generate normal page fault.
 
-	Bytes 5-7 of 64 byte memory location ('token') will be written to by the
+	Bytes 4-7 of 64 byte memory location ('token') will be written to by the
 	hypervisor at the time of APF 'page ready' event injection. The content
-	of these bytes is a token which was previously delivered as 'page not
-	present' event. The event indicates the page in now available. Guest is
-	supposed to write '0' to 'token' when it is done handling 'page ready'
-	event and to write 1' to MSR_KVM_ASYNC_PF_ACK after clearing the location;
-	writing to the MSR forces KVM to re-scan its queue and deliver the next
-	pending notification.
+	of these bytes is a token which was previously delivered in CR2 as
+	'page not present' event. The event indicates the page is now available.
+	Guest is supposed to write '0' to 'token' when it is done handling
+	'page ready' event and to write '1' to MSR_KVM_ASYNC_PF_ACK after
+	clearing the location; writing to the MSR forces KVM to re-scan its
+	queue and deliver the next pending notification.
 
 	Note, MSR_KVM_ASYNC_PF_INT MSR specifying the interrupt vector for 'page
 	ready' APF delivery needs to be written to before enabling APF mechanism
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 6bc3456a8ebf..a1efa7907a0b 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -142,7 +142,6 @@ struct kvm_vcpu_pv_apf_data {
 	__u32 token;
 
 	__u8 pad[56];
-	__u32 enabled;
 };
 
 #define KVM_PV_EOI_BIT 0
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 4cadfd606e8e..7f0732bc0ccd 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -65,6 +65,7 @@ static int __init parse_no_stealacc(char *arg)
 
 early_param("no-steal-acc", parse_no_stealacc);
 
+static DEFINE_PER_CPU_READ_MOSTLY(bool, async_pf_enabled);
 static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64);
 DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64) __visible;
 static int has_steal_clock = 0;
@@ -244,7 +245,7 @@ noinstr u32 kvm_read_and_reset_apf_flags(void)
 {
 	u32 flags = 0;
 
-	if (__this_cpu_read(apf_reason.enabled)) {
+	if (__this_cpu_read(async_pf_enabled)) {
 		flags = __this_cpu_read(apf_reason.flags);
 		__this_cpu_write(apf_reason.flags, 0);
 	}
@@ -295,7 +296,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_asyncpf_interrupt)
 
 	inc_irq_stat(irq_hv_callback_count);
 
-	if (__this_cpu_read(apf_reason.enabled)) {
+	if (__this_cpu_read(async_pf_enabled)) {
 		token = __this_cpu_read(apf_reason.token);
 		kvm_async_pf_task_wake(token);
 		__this_cpu_write(apf_reason.token, 0);
@@ -362,7 +363,7 @@ static void kvm_guest_cpu_init(void)
 		wrmsrl(MSR_KVM_ASYNC_PF_INT, HYPERVISOR_CALLBACK_VECTOR);
 
 		wrmsrl(MSR_KVM_ASYNC_PF_EN, pa);
-		__this_cpu_write(apf_reason.enabled, 1);
+		__this_cpu_write(async_pf_enabled, true);
 		pr_debug("setup async PF for cpu %d\n", smp_processor_id());
 	}
 
@@ -383,11 +384,11 @@ static void kvm_guest_cpu_init(void)
 
 static void kvm_pv_disable_apf(void)
 {
-	if (!__this_cpu_read(apf_reason.enabled))
+	if (!__this_cpu_read(async_pf_enabled))
 		return;
 
 	wrmsrl(MSR_KVM_ASYNC_PF_EN, 0);
-	__this_cpu_write(apf_reason.enabled, 0);
+	__this_cpu_write(async_pf_enabled, false);
 
 	pr_debug("disable async PF for cpu %d\n", smp_processor_id());
 }