Define variables to track and throttle memory dirtying for every vcpu.
dirty_count: Number of pages the vcpu has dirtied since its creation,
while dirty logging is enabled.
dirty_quota: Number of pages the vcpu is allowed to dirty. To dirty
more, it needs to request more quota by exiting to
userspace.
Implement the flow for throttling based on dirty quota.
i) Increment dirty_count for the vcpu whenever it dirties a page.
ii) Exit to userspace whenever the dirty quota is exhausted (i.e. dirty
count equals/exceeds dirty quota) to request more dirty quota.
Suggested-by: Shaju Abraham <shaju.abraham@xxxxxxxxxxx>
Suggested-by: Manish Mishra <manish.mishra@xxxxxxxxxxx>
Co-developed-by: Anurag Madnawat <anurag.madnawat@xxxxxxxxxxx>
Signed-off-by: Anurag Madnawat <anurag.madnawat@xxxxxxxxxxx>
Signed-off-by: Shivam Kumar <shivam.kumar1@xxxxxxxxxxx>
---
arch/arm64/kvm/arm.c | 3 +++
arch/s390/kvm/kvm-s390.c | 3 +++
arch/x86/kvm/x86.c | 4 ++++
include/linux/kvm_host.h | 15 +++++++++++++++
include/linux/kvm_types.h | 1 +
include/uapi/linux/kvm.h | 12 ++++++++++++
virt/kvm/kvm_main.c | 7 ++++++-
7 files changed, 44 insertions(+), 1 deletion(-)
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index ecc5958e27fe..5b6a239b83a5 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -848,6 +848,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
ret = 1;
run->exit_reason = KVM_EXIT_UNKNOWN;
while (ret > 0) {
+ ret = kvm_vcpu_check_dirty_quota(vcpu);
+ if (!ret)
+ break;
/*
* Check conditions before entering the guest
*/
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 2296b1ff1e02..9cc0e0583ef4 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -3994,6 +3994,9 @@ static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu)
static int vcpu_pre_run(struct kvm_vcpu *vcpu)
{
int rc, cpuflags;
+ rc = kvm_vcpu_check_dirty_quota(vcpu);
+ if (!rc)
+ return -EREMOTE;
/*
* On s390 notifications for arriving pages will be delivered directly
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index eb4029660bd9..0b35b8cc0274 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -10257,6 +10257,10 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
vcpu->arch.l1tf_flush_l1d = true;
for (;;) {
+ r = kvm_vcpu_check_dirty_quota(vcpu);
+ if (!r)
+ break;
+
if (kvm_vcpu_running(vcpu)) {
r = vcpu_enter_guest(vcpu);
} else {
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index f11039944c08..b1c599c78c42 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -530,6 +530,21 @@ static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)
return cmpxchg(&vcpu->mode, IN_GUEST_MODE, EXITING_GUEST_MODE);
}
+static inline int kvm_vcpu_check_dirty_quota(struct kvm_vcpu *vcpu)
+{
+ u64 dirty_quota = READ_ONCE(vcpu->run->dirty_quota);
+ u64 pages_dirtied = vcpu->stat.generic.pages_dirtied;
+ struct kvm_run *run = vcpu->run;
+
+ if (!dirty_quota || (pages_dirtied < dirty_quota))
+ return 1;
+
+ run->exit_reason = KVM_EXIT_DIRTY_QUOTA_EXHAUSTED;
+ run->dirty_quota_exit.count = pages_dirtied;
+ run->dirty_quota_exit.quota = dirty_quota;
+ return 0;
+}
+
/*
* Some of the bitops functions do not support too long bitmaps.
* This number must be determined not to exceed such limits.
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index dceac12c1ce5..7f42486b0405 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -106,6 +106,7 @@ struct kvm_vcpu_stat_generic {
u64 halt_poll_fail_hist[HALT_POLL_HIST_COUNT];
u64 halt_wait_hist[HALT_POLL_HIST_COUNT];
u64 blocking;
+ u64 pages_dirtied;
};
#define KVM_STATS_NAME_SIZE 48
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 507ee1f2aa96..1d9531efe1fb 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -270,6 +270,7 @@ struct kvm_xen_exit {
#define KVM_EXIT_X86_BUS_LOCK 33
#define KVM_EXIT_XEN 34
#define KVM_EXIT_RISCV_SBI 35
+#define KVM_EXIT_DIRTY_QUOTA_EXHAUSTED 36
/* For KVM_EXIT_INTERNAL_ERROR */
/* Emulate instruction failed. */
@@ -487,6 +488,11 @@ struct kvm_run {
unsigned long args[6];
unsigned long ret[2];
} riscv_sbi;
+ /* KVM_EXIT_DIRTY_QUOTA_EXHAUSTED */
+ struct {
+ __u64 count;
+ __u64 quota;
+ } dirty_quota_exit;
/* Fix the size of the union. */
char padding[256];
};
@@ -508,6 +514,12 @@ struct kvm_run {
struct kvm_sync_regs regs;
char padding[SYNC_REGS_SIZE_BYTES];
} s;
+ /*
+ * Number of pages the vCPU is allowed to have dirtied over its entire
+ * liftime. KVM_RUN exits with KVM_EXIT_DIRTY_QUOTA_EXHAUSTED if the
+ * quota is reached/exceeded.
+ */
+ __u64 dirty_quota;
};
/* for KVM_REGISTER_COALESCED_MMIO / KVM_UNREGISTER_COALESCED_MMIO */
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 0afc016cc54d..041ab464405d 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -3163,7 +3163,12 @@ void mark_page_dirty_in_slot(struct kvm *kvm,
return;
#endif
- if (memslot && kvm_slot_dirty_track_enabled(memslot)) {
+ if (!memslot)
+ return;
+
+ vcpu->stat.generic.pages_dirtied++;
+
+ if (kvm_slot_dirty_track_enabled(memslot)) {
unsigned long rel_gfn = gfn - memslot->base_gfn;
u32 slot = (memslot->as_id << 16) | memslot->id;
--
2.22.3
