Regards,
Anthony Liguori
Subject: [PATCH] KVM: Add hypercall queue for paravirt_ops implementation
Author: Anthony Liguori <[EMAIL PROTECTED]>
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 <[EMAIL PROTECTED]>
diff --git a/arch/i386/kernel/kvm.c b/arch/i386/kernel/kvm.c
index 21133e4..52eb50d 100644
--- a/arch/i386/kernel/kvm.c
+++ b/arch/i386/kernel/kvm.c
@@ -34,6 +34,7 @@
#include <linux/init.h>
#include <linux/dmi.h>
#include <linux/acpi_pmtmr.h>
+#include <linux/hardirq.h>
#include "mach_timer.h"
@@ -46,8 +47,12 @@ 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;
+ int queue_index;
+ int max_queue_index;
+
+ struct kvm_vmca *vmca;
void (*hypercall)(void);
u64 vmca_gpa;
@@ -55,18 +60,18 @@ 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 int do_paravirt_clock;
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"
@@ -83,6 +88,69 @@ 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) {
+ switch (nr) {
+ case KVM_HYPERCALL_MMU_WRITE:
+ case KVM_HYPERCALL_FLUSH_TLB:
+ case KVM_HYPERCALL_FLUSH_TLB_SINGLE:
+ return 1;
+ }
+ } else if (state->mode == PARAVIRT_LAZY_CPU) {
+ if (nr == KVM_HYPERCALL_SET_CR)
+ return 1;
+ }
+
+ return 0;
+}
+
+static void hypercall_queue_flush(struct kvm_paravirt_state *state)
+{
+ if (state->queue_index) {
+ _kvm_hypercall(state, KVM_HYPERCALL_FLUSH, __pa(state->queue),
+ state->queue_index, 0, 0);
+ state->queue_index = 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;
+
+ BUG_ON(preemptible());
+
+ if (state->queue_index == state->max_queue_index)
+ hypercall_queue_flush(state);
+
+ entry = &state->queue[state->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 = get_cpu_var(paravirt_state);
+ 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);
+
+ put_cpu_var(paravirt_state);
+ return ret;
+}
+
static cycle_t kvm_clocksource_read(void)
{
struct kvm_paravirt_state *state = get_cpu_var(paravirt_state);
@@ -146,18 +214,22 @@ static __always_inline void kvm_write_cr(int reg, unsigned long value)
state->cr_valid[reg] = 1;
state->cached_cr[reg] = value;
- switch (reg) {
- case 0:
- native_write_cr0(value);
- break;
- case 3:
- native_write_cr3(value);
- break;
- case 4:
- native_write_cr4(value);
- break;
- default:
- BUG();
+ if (state->mode == PARAVIRT_LAZY_CPU)
+ kvm_hypercall(KVM_HYPERCALL_SET_CR, reg, value, 0, 0);
+ else {
+ switch (reg) {
+ case 0:
+ native_write_cr0(value);
+ break;
+ case 3:
+ native_write_cr3(value);
+ break;
+ case 4:
+ native_write_cr4(value);
+ break;
+ default:
+ BUG();
+ }
}
}
@@ -269,7 +341,24 @@ static void kvm_flush_tlb(void)
static void kvm_flush_tlb_single(unsigned long addr)
{
- kvm_hypercall(KVM_HYPERCALL_FLUSH_TLB_SINGLE, addr, 0, 0, 0);
+ int mode = x86_read_percpu(paravirt_state)->mode;
+
+ if (mode == PARAVIRT_LAZY_MMU)
+ kvm_hypercall(KVM_HYPERCALL_FLUSH_TLB_SINGLE, addr, 0, 0, 0);
+ else
+ __native_flush_tlb_single(addr);
+}
+
+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)
+ hypercall_queue_flush(state);
+
+ if (mode != PARAVIRT_LAZY_FLUSH)
+ state->mode = mode;
}
static void kvm_release_pt(u32 pfn)
@@ -320,6 +409,9 @@ static void paravirt_ops_setup(void)
paravirt_ops.release_pd = kvm_release_pt;
}
+ if (do_hypercall_batching)
+ paravirt_ops.set_lazy_mode = kvm_set_lazy_mode;
+
paravirt_ops.paravirt_enabled = 1;
}
@@ -365,6 +457,9 @@ 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;
@@ -375,6 +470,9 @@ 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));
@@ -401,8 +499,15 @@ 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->queue_index = 0;
+ state->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 9a7462a..7e53374 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 91aec56..e3afbde 100644
--- a/drivers/kvm/kvm_main.c
+++ b/drivers/kvm/kvm_main.c
@@ -96,7 +96,7 @@ struct vfsmount *kvmfs_mnt;
#define KVM_PARAVIRT_FEATURES \
(KVM_FEATURE_VMCA | KVM_FEATURE_NOP_IO_DELAY | \
KVM_FEATURE_PARAVIRT_CLOCK | KVM_FEATURE_CR_READ_CACHE | \
- KVM_FEATURE_MMU_WRITE)
+ KVM_FEATURE_MMU_WRITE | KVM_FEATURE_HYPERCALL_BATCHING)
#define KVM_MSR_SET_VMCA 0x87655678
@@ -1410,6 +1410,24 @@ static int kvm_hypercall_release_pt(struct kvm_vcpu *vcpu, gpa_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)
@@ -1419,6 +1437,8 @@ static int dispatch_hypercall(struct kvm_vcpu *vcpu, unsigned long nr,
return kvm_hypercall_mmu_write(vcpu, p1, p2, p3, p4);
case KVM_HYPERCALL_UPDATE_TIME:
return kvm_hypercall_update_time(vcpu);
+ case KVM_HYPERCALL_SET_CR:
+ return kvm_hypercall_set_cr(vcpu, p1, p2);
case KVM_HYPERCALL_FLUSH_TLB:
return kvm_hypercall_flush_tlb(vcpu);
case KVM_HYPERCALL_FLUSH_TLB_SINGLE:
@@ -1429,6 +1449,39 @@ static int dispatch_hypercall(struct kvm_vcpu *vcpu, unsigned long nr,
return -KVM_ENOSYS;
}
+static int kvm_hypercall_flush(struct kvm_vcpu *vcpu, gva_t addr, u32 nb_queue)
+{
+ struct kvm_hypercall_entry *queue;
+ struct page *queue_page;
+ hpa_t queue_hpa;
+ int ret = 0;
+ int i;
+
+ if (nb_queue > (PAGE_SIZE / sizeof(struct kvm_hypercall_entry)))
+ return -KVM_EFAULT;
+
+ queue_hpa = gpa_to_hpa(vcpu, addr);
+ if (is_error_hpa(queue_hpa))
+ return -KVM_EFAULT;
+
+ queue_page = pfn_to_page(queue_hpa >> PAGE_SHIFT);
+ queue = kmap(queue_page);
+
+ for (i = 0; i < nb_queue; i++)
+ ret |= dispatch_hypercall(vcpu, queue[i].nr, queue[i].p1,
+ queue[i].p2, queue[i].p3,
+ queue[i].p4);
+
+ if (ret < 0)
+ ret = -KVM_EINVAL;
+ else
+ ret = 0;
+
+ kunmap(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;
@@ -1456,7 +1509,11 @@ 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, a0, a1);
+ else
+ ret = dispatch_hypercall(vcpu, nr, a0, a1, a2, a3);
+
if (ret == -KVM_ENOSYS) {
run->hypercall.args[0] = a0;
run->hypercall.args[1] = a1;
diff --git a/include/linux/kvm_para.h b/include/linux/kvm_para.h
index 560de6a..e220832 100644
--- a/include/linux/kvm_para.h
+++ b/include/linux/kvm_para.h
@@ -27,6 +27,7 @@ static int __init kvm_guest_init(void)
#define KVM_FEATURE_PARAVIRT_CLOCK (1UL << 2)
#define KVM_FEATURE_CR_READ_CACHE (1UL << 3)
#define KVM_FEATURE_MMU_WRITE (1UL << 4)
+#define KVM_FEATURE_HYPERCALL_BATCHING (1UL << 5)
struct kvm_vmca
{
@@ -34,6 +35,15 @@ struct kvm_vmca
u64 real_nsecs;
};
+struct kvm_hypercall_entry
+{
+ unsigned long nr;
+ unsigned long p1;
+ unsigned long p2;
+ unsigned long p3;
+ unsigned long p4;
+};
+
/*
* Hypercall calling convention:
*
@@ -55,5 +65,7 @@ struct kvm_vmca
#define KVM_HYPERCALL_FLUSH_TLB 2
#define KVM_HYPERCALL_FLUSH_TLB_SINGLE 3
#define KVM_HYPERCALL_RELEASE_PT 4
+#define KVM_HYPERCALL_SET_CR 5
+#define KVM_HYPERCALL_FLUSH 6
#endif
-------------------------------------------------------------------------
This SF.net email is sponsored by DB2 Express
Download DB2 Express C - the FREE version of DB2 express and take
control of your XML. No limits. Just data. Click to get it now.
http://sourceforge.net/powerbar/db2/
_______________________________________________
kvm-devel mailing list
kvm-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/kvm-devel
