Regards,
Anthony Liguori
Subject: [PATCH] KVM: Add hypercall queue for paravirt_ops implementation
Author: Anthony Liguori <aliguori@xxxxxxxxxx>
Implemented a hypercall queue that can be used when paravirt_ops lazy mode
is enabled. This patch enables queueing of MMU write operations and CR
updates. This results in about a 50% bump in kernbench performance.
Signed-off-by: Anthony Liguori <aliguori@xxxxxxxxxx>
diff --git a/arch/i386/kernel/kvm.c b/arch/i386/kernel/kvm.c
index 07ce38e..4b323f1 100644
--- a/arch/i386/kernel/kvm.c
+++ b/arch/i386/kernel/kvm.c
@@ -33,8 +33,10 @@ struct kvm_paravirt_state
unsigned long cached_cr[5];
int cr_valid[5];
- struct kvm_vmca *vmca;
+ enum paravirt_lazy_mode mode;
struct kvm_hypercall_entry *queue;
+
+ struct kvm_vmca *vmca;
void (*hypercall)(void);
u64 vmca_gpa;
@@ -42,17 +44,17 @@ struct kvm_paravirt_state
static DEFINE_PER_CPU(struct kvm_paravirt_state *, paravirt_state);
+static int do_hypercall_batching;
static int do_mmu_write;
static int do_cr_read_caching;
static int do_nop_io_delay;
static u64 msr_set_vmca;
-static long kvm_hypercall(unsigned int nr, unsigned long p1,
- unsigned long p2, unsigned long p3,
- unsigned long p4)
+static long _kvm_hypercall(struct kvm_paravirt_state *state,
+ unsigned int nr, unsigned long p1,
+ unsigned long p2, unsigned long p3,
+ unsigned long p4)
{
- struct kvm_paravirt_state *state
- = per_cpu(paravirt_state, smp_processor_id());
long ret;
asm volatile("call *(%6) \n\t"
@@ -69,6 +71,55 @@ static long kvm_hypercall(unsigned int nr, unsigned long p1,
return ret;
}
+static int can_defer_hypercall(struct kvm_paravirt_state *state,
+ unsigned int nr)
+{
+ if (state->mode == PARAVIRT_LAZY_MMU) {
+ if (nr == KVM_HYPERCALL_MMU_WRITE)
+ return 1;
+ } else if (state->mode == PARAVIRT_LAZY_CPU) {
+ if (nr == KVM_HYPERCALL_SET_CR)
+ return 1;
+ }
+
+ return 0;
+}
+
+static void _kvm_hypercall_defer(struct kvm_paravirt_state *state,
+ unsigned int nr,
+ unsigned long p1, unsigned long p2,
+ unsigned long p3, unsigned long p4)
+{
+ struct kvm_hypercall_entry *entry;
+
+ if (state->vmca->queue_index == state->vmca->max_queue_index)
+ _kvm_hypercall(state, KVM_HYPERCALL_FLUSH, 0, 0, 0, 0);
+
+ /* FIXME: are we preempt safe here? */
+ entry = &state->queue[state->vmca->queue_index++];
+ entry->nr = nr;
+ entry->p1 = p1;
+ entry->p2 = p2;
+ entry->p3 = p3;
+ entry->p4 = p4;
+}
+
+static long kvm_hypercall(unsigned int nr, unsigned long p1,
+ unsigned long p2, unsigned long p3,
+ unsigned long p4)
+{
+ struct kvm_paravirt_state *state
+ = per_cpu(paravirt_state, smp_processor_id());
+ long ret = 0;
+
+ if (can_defer_hypercall(state, nr))
+ _kvm_hypercall_defer(state, nr, p1, p2, p3, p4);
+ else
+ ret = _kvm_hypercall(state, nr, p1, p2, p3, p4);
+
+ return ret;
+}
+
/*
* No need for any "IO delay" on KVM
*/
@@ -107,7 +158,9 @@ static void kvm_write_cr(int reg, unsigned long value)
state->cr_valid[reg] = 1;
state->cached_cr[reg] = value;
- if (reg == 0)
+ if (state->mode == PARAVIRT_LAZY_CPU)
+ kvm_hypercall(KVM_HYPERCALL_SET_CR, reg, value, 0, 0);
+ else if (reg == 0)
native_write_cr0(value);
else if (reg == 3)
native_write_cr3(value);
@@ -218,6 +271,18 @@ static void kvm_pmd_clear(pmd_t *pmdp)
kvm_mmu_write(pmdp, &pmd, sizeof(pmd));
}
+static void kvm_set_lazy_mode(enum paravirt_lazy_mode mode)
+{
+ struct kvm_paravirt_state *state
+ = per_cpu(paravirt_state, smp_processor_id());
+
+ if (mode == PARAVIRT_LAZY_FLUSH || mode == PARAVIRT_LAZY_NONE) {
+ if (state->vmca->queue_index)
+ _kvm_hypercall(state, KVM_HYPERCALL_FLUSH, 0, 0, 0, 0);
+ }
+ state->mode = mode;
+}
+
static void paravirt_ops_setup(void)
{
paravirt_ops.name = "KVM";
@@ -249,6 +314,9 @@ static void paravirt_ops_setup(void)
paravirt_ops.set_pud = kvm_set_pud;
}
+ if (do_hypercall_batching)
+ paravirt_ops.set_lazy_mode = kvm_set_lazy_mode;
+
paravirt_ops.paravirt_enabled = 1;
apply_paravirt(__parainstructions, __parainstructions_end);
@@ -293,6 +361,9 @@ static int paravirt_initialize(void)
if ((edx & KVM_FEATURE_MMU_WRITE))
do_mmu_write = 1;
+ if ((edx & KVM_FEATURE_HYPERCALL_BATCHING))
+ do_hypercall_batching = 1;
+
on_each_cpu(paravirt_activate, NULL, 0, 1);
return 0;
@@ -303,6 +374,9 @@ static __init void paravirt_free_state(struct kvm_paravirt_state *state)
if (!state)
return;
+ if (state->queue)
+ __free_page(pfn_to_page(__pa(state->queue) >> PAGE_SHIFT));
+
if (state->hypercall)
__free_page(pfn_to_page(__pa(state->hypercall) >> PAGE_SHIFT));
@@ -329,8 +403,15 @@ static __init struct kvm_paravirt_state *paravirt_alloc_state(void)
if (!state->hypercall)
goto err;
+ state->queue = (void *)get_zeroed_page(GFP_KERNEL);
+ if (!state->queue)
+ goto err;
+
state->vmca_gpa = __pa(state->vmca);
state->vmca->hypercall_gpa = __pa(state->hypercall);
+ state->vmca->queue_gpa = __pa(state->queue);
+ state->vmca->max_queue_index
+ = (PAGE_SIZE / sizeof(struct kvm_hypercall_entry));
return state;
diff --git a/drivers/kvm/kvm.h b/drivers/kvm/kvm.h
index b08272b..d531899 100644
--- a/drivers/kvm/kvm.h
+++ b/drivers/kvm/kvm.h
@@ -291,6 +291,7 @@ struct kvm_vcpu {
gpa_t para_state_gpa;
struct page *para_state_page;
gpa_t hypercall_gpa;
+ struct page *queue_page;
unsigned long cr4;
unsigned long cr8;
u64 pdptrs[4]; /* pae */
diff --git a/drivers/kvm/kvm_main.c b/drivers/kvm/kvm_main.c
index 4f65729..79a2a64 100644
--- a/drivers/kvm/kvm_main.c
+++ b/drivers/kvm/kvm_main.c
@@ -94,7 +94,8 @@ struct vfsmount *kvmfs_mnt;
#define KVM_PARAVIRT_FEATURES \
(KVM_FEATURE_VMCA | KVM_FEATURE_NOP_IO_DELAY | \
- KVM_FEATURE_CR_READ_CACHE | KVM_FEATURE_MMU_WRITE)
+ KVM_FEATURE_CR_READ_CACHE | KVM_FEATURE_MMU_WRITE | \
+ KVM_FEATURE_HYPERCALL_BATCHING)
#define KVM_MSR_SET_VMCA 0x87655678
@@ -1369,6 +1370,24 @@ static int kvm_hypercall_mmu_write(struct kvm_vcpu *vcpu, gva_t addr,
return 0;
}
+static int kvm_hypercall_set_cr(struct kvm_vcpu *vcpu,
+ u32 reg, unsigned long value)
+{
+ switch (reg) {
+ case 0:
+ set_cr0(vcpu, value);
+ break;
+ case 3:
+ set_cr3(vcpu, value);
+ break;
+ case 4:
+ set_cr4(vcpu, value);
+ break;
+ }
+
+ return 0;
+}
+
static int dispatch_hypercall(struct kvm_vcpu *vcpu, unsigned long nr,
unsigned long p1, unsigned long p2,
unsigned long p3, unsigned long p4)
@@ -1376,10 +1395,36 @@ static int dispatch_hypercall(struct kvm_vcpu *vcpu, unsigned long nr,
switch (nr) {
case KVM_HYPERCALL_MMU_WRITE:
return kvm_hypercall_mmu_write(vcpu, p1, p2, p3, p4);
+ case KVM_HYPERCALL_SET_CR:
+ return kvm_hypercall_set_cr(vcpu, p1, p2);
}
return -ENOSYS;
}
+static int kvm_hypercall_flush(struct kvm_vcpu *vcpu)
+{
+ struct kvm_hypercall_entry *queue;
+ struct kvm_vmca *vmca;
+ int ret = 0;
+ int i;
+
+ queue = kmap(vcpu->queue_page);
+ vmca = kmap(vcpu->para_state_page);
+
+ for (i = 0; i < vmca->queue_index; i++)
+ ret |= dispatch_hypercall(vcpu, queue[i].nr, queue[i].p1,
+ queue[i].p2, queue[i].p3,
+ queue[i].p4);
+
+ vmca->queue_index = 0;
+ mark_page_dirty(vcpu->kvm, vcpu->para_state_gpa >> PAGE_SHIFT);
+
+ kunmap(vcpu->para_state_page);
+ kunmap(vcpu->queue_page);
+
+ return ret;
+}
+
int kvm_hypercall(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
unsigned long nr, a0, a1, a2, a3, a4, a5, ret;
@@ -1407,7 +1452,11 @@ int kvm_hypercall(struct kvm_vcpu *vcpu, struct kvm_run *run)
a5 = vcpu->regs[VCPU_REGS_RBP] & -1u;
}
- ret = dispatch_hypercall(vcpu, nr, a0, a1, a2, a3);
+ if (nr == KVM_HYPERCALL_FLUSH)
+ ret = kvm_hypercall_flush(vcpu);
+ else
+ ret = dispatch_hypercall(vcpu, nr, a0, a1, a2, a3);
+
if (ret == -ENOSYS) {
run->hypercall.args[0] = a0;
run->hypercall.args[1] = a1;
@@ -1498,8 +1547,8 @@ void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val,
static int vcpu_register_para(struct kvm_vcpu *vcpu, gpa_t para_state_gpa)
{
struct kvm_vmca *para_state;
- hpa_t para_state_hpa, hypercall_hpa;
- struct page *para_state_page;
+ hpa_t para_state_hpa, hypercall_hpa, queue_hpa;
+ struct page *para_state_page, *queue_page;
unsigned char *hypercall;
gpa_t hypercall_gpa;
@@ -1526,10 +1575,16 @@ static int vcpu_register_para(struct kvm_vcpu *vcpu, gpa_t para_state_gpa)
if (is_error_hpa(hypercall_hpa))
goto err_kunmap_skip;
+ queue_hpa = gpa_to_hpa(vcpu, para_state->queue_gpa);
+ if (is_error_hpa(queue_hpa))
+ goto err_kunmap_skip;
+ queue_page = pfn_to_page(queue_hpa >> PAGE_SHIFT);
+
printk(KERN_DEBUG "kvm: para guest successfully registered.\n");
vcpu->para_state_page = para_state_page;
vcpu->para_state_gpa = para_state_gpa;
vcpu->hypercall_gpa = hypercall_gpa;
+ vcpu->queue_page = queue_page;
mark_page_dirty(vcpu->kvm, hypercall_gpa >> PAGE_SHIFT);
hypercall = kmap_atomic(pfn_to_page(hypercall_hpa >> PAGE_SHIFT),
diff --git a/include/linux/kvm_para.h b/include/linux/kvm_para.h
index e8ff676..7dd0cef 100644
--- a/include/linux/kvm_para.h
+++ b/include/linux/kvm_para.h
@@ -15,10 +15,23 @@
#define KVM_FEATURE_NOP_IO_DELAY (1UL << 1)
#define KVM_FEATURE_CR_READ_CACHE (1UL << 2)
#define KVM_FEATURE_MMU_WRITE (1UL << 3)
+#define KVM_FEATURE_HYPERCALL_BATCHING (1UL << 4)
struct kvm_vmca
{
u64 hypercall_gpa;
+ u64 queue_gpa;
+ u32 queue_index;
+ u32 max_queue_index;
+};
+
+struct kvm_hypercall_entry
+{
+ unsigned long nr;
+ unsigned long p1;
+ unsigned long p2;
+ unsigned long p3;
+ unsigned long p4;
};
/*
@@ -33,5 +46,7 @@ struct kvm_vmca
*/
#define KVM_HYPERCALL_MMU_WRITE 0
+#define KVM_HYPERCALL_SET_CR 1
+#define KVM_HYPERCALL_FLUSH 2
#endif
_______________________________________________
Virtualization mailing list
Virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx
https://lists.linux-foundation.org/mailman/listinfo/virtualization
