[Qemu-devel] [PULL 0/5] KVM changes for 2013-07-03

[Qemu-devel] [PULL 0/5] KVM changes for 2013-07-03

[Paolo Bonzini]

Anthony,

The following changes since commit 1acd5a373905ddb28957842256a038956941f332:

  Merge remote-tracking branch 'agraf/ppc-for-upstream' into staging (2013-07-01 09:03:04 -0500)

are available in the git repository at:

  git://git.kernel.org/pub/scm/virt/kvm/qemu-kvm.git uq/master

for you to fetch changes up to 00f4d64ee76e873be881a82d893a591487aa7950:

  kvmclock: clock should count only if vm is running (2013-07-03 10:41:32 +0200)

Thanks,

Paolo
----------------------------------------------------------------
Amos Kong (1):
      kvm: add detail error message when fail to add ioeventfd

Marcelo Tosatti (1):
      kvmclock: clock should count only if vm is running

Michael S. Tsirkin (2):
      kvm: zero-initialize KVM_SET_GSI_ROUTING input
      kvm: skip system call when msi route is unchanged

Wanlong Gao (1):
      pci-assign: remove the duplicate function name in debug message

 hw/i386/kvm/clock.c      | 64 +++++++++++++++++++++++-------------------------
 hw/i386/kvm/pci-assign.c | 12 ++++-----
 kvm-all.c                | 27 +++++++++++---------
 3 files changed, 51 insertions(+), 52 deletions(-)
-- 
1.8.1.4

[Qemu-devel] [PATCH 1/5] kvm: add detail error message when fail to add ioeventfd

[Paolo Bonzini]

From: Amos Kong <akong@redhat.com>

I try to hotplug 28 * 8 multiple-function devices to guest with
old host kernel, ioeventfds in host kernel will be exhausted, then
qemu fails to allocate ioeventfds for blk/nic devices.

It's better to add detail error here.

Signed-off-by: Amos Kong <akong@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
---
 kvm-all.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/kvm-all.c b/kvm-all.c
index c757dd2..12042f7 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -837,6 +837,8 @@ static void kvm_mem_ioeventfd_add(MemoryListener *listener,
                                data, true, int128_get64(section->size),
                                match_data);
     if (r < 0) {
+        fprintf(stderr, "%s: error adding ioeventfd: %s\n",
+                __func__, strerror(-r));
         abort();
     }
 }
@@ -869,6 +871,8 @@ static void kvm_io_ioeventfd_add(MemoryListener *listener,
                               data, true, int128_get64(section->size),
                               match_data);
     if (r < 0) {
+        fprintf(stderr, "%s: error adding ioeventfd: %s\n",
+                __func__, strerror(-r));
         abort();
     }
 }
-- 
1.8.1.4

[Qemu-devel] [PATCH 2/5] kvm: zero-initialize KVM_SET_GSI_ROUTING input

[Paolo Bonzini]

From: "Michael S. Tsirkin" <mst@redhat.com>

kvm_add_routing_entry makes an attempt to
zero-initialize any new routing entry.
However, it fails to initialize padding
within the u field of the structure
kvm_irq_routing_entry.

Other functions like kvm_irqchip_update_msi_route
also fail to initialize the padding field in
kvm_irq_routing_entry.

It's better to just make sure all input is initialized.

Once it is, we can also drop complex field by field assignment and just
do the simple *a = *b to update a route entry.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
---
 kvm-all.c | 19 +++++++------------
 1 file changed, 7 insertions(+), 12 deletions(-)

diff --git a/kvm-all.c b/kvm-all.c
index 12042f7..745b501 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -1016,11 +1016,8 @@ static void kvm_add_routing_entry(KVMState *s,
     }
     n = s->irq_routes->nr++;
     new = &s->irq_routes->entries[n];
-    memset(new, 0, sizeof(*new));
-    new->gsi = entry->gsi;
-    new->type = entry->type;
-    new->flags = entry->flags;
-    new->u = entry->u;
+
+    *new = *entry;
 
     set_gsi(s, entry->gsi);
 }
@@ -1037,9 +1034,7 @@ static int kvm_update_routing_entry(KVMState *s,
             continue;
         }
 
-        entry->type = new_entry->type;
-        entry->flags = new_entry->flags;
-        entry->u = new_entry->u;
+        *entry = *new_entry;
 
         kvm_irqchip_commit_routes(s);
 
@@ -1051,7 +1046,7 @@ static int kvm_update_routing_entry(KVMState *s,
 
 void kvm_irqchip_add_irq_route(KVMState *s, int irq, int irqchip, int pin)
 {
-    struct kvm_irq_routing_entry e;
+    struct kvm_irq_routing_entry e = {};
 
     assert(pin < s->gsi_count);
 
@@ -1164,7 +1159,7 @@ int kvm_irqchip_send_msi(KVMState *s, MSIMessage msg)
             return virq;
         }
 
-        route = g_malloc(sizeof(KVMMSIRoute));
+        route = g_malloc0(sizeof(KVMMSIRoute));
         route->kroute.gsi = virq;
         route->kroute.type = KVM_IRQ_ROUTING_MSI;
         route->kroute.flags = 0;
@@ -1186,7 +1181,7 @@ int kvm_irqchip_send_msi(KVMState *s, MSIMessage msg)
 
 int kvm_irqchip_add_msi_route(KVMState *s, MSIMessage msg)
 {
-    struct kvm_irq_routing_entry kroute;
+    struct kvm_irq_routing_entry kroute = {};
     int virq;
 
     if (!kvm_gsi_routing_enabled()) {
@@ -1213,7 +1208,7 @@ int kvm_irqchip_add_msi_route(KVMState *s, MSIMessage msg)
 
 int kvm_irqchip_update_msi_route(KVMState *s, int virq, MSIMessage msg)
 {
-    struct kvm_irq_routing_entry kroute;
+    struct kvm_irq_routing_entry kroute = {};
 
     if (!kvm_irqchip_in_kernel()) {
         return -ENOSYS;
-- 
1.8.1.4

[Qemu-devel] [PATCH 3/5] kvm: skip system call when msi route is unchanged

[Paolo Bonzini]

From: "Michael S. Tsirkin" <mst@redhat.com>

Some guests do a large number of mask/unmask
calls which currently trigger expensive route update
system calls.
Detect that route in unchanged and skip the system call.

Reported-by: "Zhanghaoyu (A)" <haoyu.zhang@huawei.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
---
 kvm-all.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/kvm-all.c b/kvm-all.c
index 745b501..3ee0ac7 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -1034,6 +1034,10 @@ static int kvm_update_routing_entry(KVMState *s,
             continue;
         }
 
+        if(!memcmp(entry, new_entry, sizeof *entry)) {
+            return 0;
+        }
+
         *entry = *new_entry;
 
         kvm_irqchip_commit_routes(s);
-- 
1.8.1.4

[Qemu-devel] [PATCH 4/5] pci-assign: remove the duplicate function name in debug message

[Paolo Bonzini]

From: Wanlong Gao <gaowanlong@cn.fujitsu.com>

While DEBUG() already includes the function name.

Signed-off-by: Wanlong Gao <gaowanlong@cn.fujitsu.com>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 hw/i386/kvm/pci-assign.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/hw/i386/kvm/pci-assign.c b/hw/i386/kvm/pci-assign.c
index 1fb7ad4..eab2d3e 100644
--- a/hw/i386/kvm/pci-assign.c
+++ b/hw/i386/kvm/pci-assign.c
@@ -226,7 +226,7 @@ static uint32_t slow_bar_readb(void *opaque, hwaddr addr)
     uint32_t r;
 
     r = *in;
-    DEBUG("slow_bar_readl addr=0x" TARGET_FMT_plx " val=0x%08x\n", addr, r);
+    DEBUG("addr=0x" TARGET_FMT_plx " val=0x%08x\n", addr, r);
 
     return r;
 }
@@ -238,7 +238,7 @@ static uint32_t slow_bar_readw(void *opaque, hwaddr addr)
     uint32_t r;
 
     r = *in;
-    DEBUG("slow_bar_readl addr=0x" TARGET_FMT_plx " val=0x%08x\n", addr, r);
+    DEBUG("addr=0x" TARGET_FMT_plx " val=0x%08x\n", addr, r);
 
     return r;
 }
@@ -250,7 +250,7 @@ static uint32_t slow_bar_readl(void *opaque, hwaddr addr)
     uint32_t r;
 
     r = *in;
-    DEBUG("slow_bar_readl addr=0x" TARGET_FMT_plx " val=0x%08x\n", addr, r);
+    DEBUG("addr=0x" TARGET_FMT_plx " val=0x%08x\n", addr, r);
 
     return r;
 }
@@ -260,7 +260,7 @@ static void slow_bar_writeb(void *opaque, hwaddr addr, uint32_t val)
     AssignedDevRegion *d = opaque;
     uint8_t *out = d->u.r_virtbase + addr;
 
-    DEBUG("slow_bar_writeb addr=0x" TARGET_FMT_plx " val=0x%02x\n", addr, val);
+    DEBUG("addr=0x" TARGET_FMT_plx " val=0x%02x\n", addr, val);
     *out = val;
 }
 
@@ -269,7 +269,7 @@ static void slow_bar_writew(void *opaque, hwaddr addr, uint32_t val)
     AssignedDevRegion *d = opaque;
     uint16_t *out = (uint16_t *)(d->u.r_virtbase + addr);
 
-    DEBUG("slow_bar_writew addr=0x" TARGET_FMT_plx " val=0x%04x\n", addr, val);
+    DEBUG("addr=0x" TARGET_FMT_plx " val=0x%04x\n", addr, val);
     *out = val;
 }
 
@@ -278,7 +278,7 @@ static void slow_bar_writel(void *opaque, hwaddr addr, uint32_t val)
     AssignedDevRegion *d = opaque;
     uint32_t *out = (uint32_t *)(d->u.r_virtbase + addr);
 
-    DEBUG("slow_bar_writel addr=0x" TARGET_FMT_plx " val=0x%08x\n", addr, val);
+    DEBUG("addr=0x" TARGET_FMT_plx " val=0x%08x\n", addr, val);
     *out = val;
 }
 
-- 
1.8.1.4

[Qemu-devel] [PATCH 5/5] kvmclock: clock should count only if vm is running

[Paolo Bonzini]

From: Marcelo Tosatti <mtosatti@redhat.com>

kvmclock should not count while vm is paused, because:

1) if the vm is paused for long periods, timekeeping
math can overflow while converting the (large) clocksource
delta to nanoseconds.

2) Users rely on CLOCK_MONOTONIC to count run time, that is,
time which OS has been in a runnable state (see CLOCK_BOOTTIME).

Change kvmclock driver so as to save clock value when vm transitions
from runnable to stopped state, and to restore clock value from stopped
to runnable transition.

Cc: qemu-stable@nongnu.org
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 hw/i386/kvm/clock.c | 64 +++++++++++++++++++++++++----------------------------
 1 file changed, 30 insertions(+), 34 deletions(-)

diff --git a/hw/i386/kvm/clock.c b/hw/i386/kvm/clock.c
index 87d4d0f..98e5ca5 100644
--- a/hw/i386/kvm/clock.c
+++ b/hw/i386/kvm/clock.c
@@ -28,38 +28,6 @@ typedef struct KVMClockState {
     bool clock_valid;
 } KVMClockState;
 
-static void kvmclock_pre_save(void *opaque)
-{
-    KVMClockState *s = opaque;
-    struct kvm_clock_data data;
-    int ret;
-
-    if (s->clock_valid) {
-        return;
-    }
-    ret = kvm_vm_ioctl(kvm_state, KVM_GET_CLOCK, &data);
-    if (ret < 0) {
-        fprintf(stderr, "KVM_GET_CLOCK failed: %s\n", strerror(ret));
-        data.clock = 0;
-    }
-    s->clock = data.clock;
-    /*
-     * If the VM is stopped, declare the clock state valid to avoid re-reading
-     * it on next vmsave (which would return a different value). Will be reset
-     * when the VM is continued.
-     */
-    s->clock_valid = !runstate_is_running();
-}
-
-static int kvmclock_post_load(void *opaque, int version_id)
-{
-    KVMClockState *s = opaque;
-    struct kvm_clock_data data;
-
-    data.clock = s->clock;
-    data.flags = 0;
-    return kvm_vm_ioctl(kvm_state, KVM_SET_CLOCK, &data);
-}
 
 static void kvmclock_vm_state_change(void *opaque, int running,
                                      RunState state)
@@ -70,8 +38,18 @@ static void kvmclock_vm_state_change(void *opaque, int running,
     int ret;
 
     if (running) {
+        struct kvm_clock_data data;
+
         s->clock_valid = false;
 
+        data.clock = s->clock;
+        data.flags = 0;
+        ret = kvm_vm_ioctl(kvm_state, KVM_SET_CLOCK, &data);
+        if (ret < 0) {
+            fprintf(stderr, "KVM_SET_CLOCK failed: %s\n", strerror(ret));
+            abort();
+        }
+
         if (!cap_clock_ctrl) {
             return;
         }
@@ -84,6 +62,26 @@ static void kvmclock_vm_state_change(void *opaque, int running,
                 return;
             }
         }
+    } else {
+        struct kvm_clock_data data;
+        int ret;
+
+        if (s->clock_valid) {
+            return;
+        }
+        ret = kvm_vm_ioctl(kvm_state, KVM_GET_CLOCK, &data);
+        if (ret < 0) {
+            fprintf(stderr, "KVM_GET_CLOCK failed: %s\n", strerror(ret));
+            abort();
+        }
+        s->clock = data.clock;
+
+        /*
+         * If the VM is stopped, declare the clock state valid to
+         * avoid re-reading it on next vmsave (which would return
+         * a different value). Will be reset when the VM is continued.
+         */
+        s->clock_valid = true;
     }
 }
 
@@ -100,8 +98,6 @@ static const VMStateDescription kvmclock_vmsd = {
     .version_id = 1,
     .minimum_version_id = 1,
     .minimum_version_id_old = 1,
-    .pre_save = kvmclock_pre_save,
-    .post_load = kvmclock_post_load,
     .fields = (VMStateField[]) {
         VMSTATE_UINT64(clock, KVMClockState),
         VMSTATE_END_OF_LIST()
-- 
1.8.1.4