optimize the downtime for vfio migration
cover optimize the downtime for vfio migration
In vfio migration resume phase, the cost would increase if the vfio device has more unmasked vectors. We try to optimize it in this series.
Patch 1 & 2 are simple code cleanups. Patch 3 defers to set irqs to vfio core. Patch 4 & 5 defer to commit the route to KVM core.
The test VM has 128 vcpus and 8 VF (with 65 vectors enabled), we mesure the cost of the vfio_msix_enable for each one, and we can see the total cost can be significantly reduced.
Origin Apply Patch 3 Apply Patch 3/4/5 1st 8 4 2 2nd 15 11 2 3rd 22 18 2 4th 24 25 3 5th 36 33 2 6th 44 40 3 7th 51 47 3 8th 58 54 4 Total 258ms 232ms 21ms
Longpeng (Mike) (5):
vfio: use helper to simplfy the failure path in vfio_msi_enable
msix: simplfy the conditional in msix_set/unset_vector_notifiers
vfio: defer to enable msix in migration resume phase
kvm: irqchip: support defer to commit the route
vfio: defer to commit kvm route in migraiton resume phase
accel/kvm/kvm-all.c | 10 +++-- accel/stubs/kvm-stub.c | 3 +- hw/misc/ivshmem.c | 2 +- hw/pci/msix.c | 7 ++-- hw/vfio/pci.c | 99 ++++++++++++++++++++++++++++++++++++++------------ hw/vfio/pci.h | 1 + hw/virtio/virtio-pci.c | 2 +- include/sysemu/kvm.h | 4 +- target/i386/kvm/kvm.c | 2 +- 9 files changed, 95 insertions(+), 35 deletions(-)
Signature · 1 line
1.8.3.1
PATCH 1/5 vfio: use helper to simplfy the failure path in vfio_msi_enable
The main difference of the failure path in vfio_msi_enable and vfio_msi_disable_common is enable INTX or not.
Extend the vfio_msi_disable_common to provide a arg to decide whether need to fallback, and then we can use this helper to instead the redundant code in vfio_msi_enable.
--- hw/vfio/pci.c | 34 ++++++++++++---------------------- 1 file changed, 12 insertions(+), 22 deletions(-)
hw/vfio/pci.c +12 -22
@@ -47,6 +47,7 @@static void vfio_disable_interrupts (VFIOPCIDevice *vdev);static void vfio_mmap_set_enabled (VFIOPCIDevice *vdev,bool enabled); +static void vfio_msi_disable_common (VFIOPCIDevice *vdev,bool enable_intx);/* * Disabling BAR mmaping can be slow, but toggling it around INTx can
@@ -650,29 +651,17 @@ retry:if (ret) {if (ret <0 ) {error_report ("vfio: Error: Failed to setup MSI fds: %m" ); - }else if (ret != vdev->nr_vectors) { + }else {error_report ("vfio: Error: Failed to enable %d " "MSI vectors, retry with %d" , vdev->nr_vectors, ret); } -for (i =0 ; i < vdev->nr_vectors; i++) { -VFIOMSIVector *vector = &vdev->msi_vectors[i]; -if (vector->virq >=0 ) { -vfio_remove_kvm_msi_virq (vector); - } -qemu_set_fd_handler (event_notifier_get_fd (&vector->interrupt), -NULL ,NULL ,NULL ); -event_notifier_cleanup (&vector->interrupt); - } - -g_free (vdev->msi_vectors); - vdev->msi_vectors =NULL ; +vfio_msi_disable_common (vdev, false); -if (ret >0 && ret != vdev->nr_vectors) { +if (ret >0 ) { vdev->nr_vectors = ret; goto retry; } - vdev->nr_vectors =0 ;/* * Failing to setup MSI doesn't really fall within any specification.
@@ -680,7 +669,6 @@ retry:* out to fall back to INTx for this device. */ error_report ("vfio: Error: Failed to enable MSI" ); - vdev->interrupt =VFIO_INT_NONE ;return ; }
@@ -688,7 +676,7 @@ retry:trace_vfio_msi_enable (vdev->vbasedev.name, vdev->nr_vectors); } -static void vfio_msi_disable_common (VFIOPCIDevice *vdev) +static void vfio_msi_disable_common (VFIOPCIDevice *vdev,bool enable_intx) {Error *err =NULL ;int i;
@@ -710,9 +698,11 @@ static void vfio_msi_disable_common(VFIOPCIDevice *vdev) vdev->nr_vectors =0 ; vdev->interrupt =VFIO_INT_NONE ; -vfio_intx_enable (vdev, &err); -if (err) { -error_reportf_err (err,VFIO_MSG_PREFIX , vdev->vbasedev.name); +if (enable_intx) { +vfio_intx_enable (vdev, &err); +if (err) { +error_reportf_err (err,VFIO_MSG_PREFIX , vdev->vbasedev.name); + } } }
@@ -737,7 +727,7 @@ static void vfio_msix_disable(VFIOPCIDevice *vdev)vfio_disable_irqindex (&vdev->vbasedev,VFIO_PCI_MSIX_IRQ_INDEX ); } -vfio_msi_disable_common (vdev); +vfio_msi_disable_common (vdev, true);memset (vdev->msix->pending,0 ,BITS_TO_LONGS (vdev->msix->entries) *sizeof (unsigned long ));
@@ -748,7 +738,7 @@ static void vfio_msix_disable(VFIOPCIDevice *vdev)static void vfio_msi_disable (VFIOPCIDevice *vdev) {vfio_disable_irqindex (&vdev->vbasedev,VFIO_PCI_MSI_IRQ_INDEX ); -vfio_msi_disable_common (vdev); +vfio_msi_disable_common (vdev, true);trace_vfio_msi_disable (vdev->vbasedev.name); }
Signature · 1 line
1.8.3.1
Re: [PATCH 1/5] vfio: use helper to simplfy the failure path in vfio_msi_enable
Quoted 4 lines · On Wed, 25 Aug 2021 15:56:16 +0800 "Longpeng(Mike)" <[email protected]>…
The main difference of the failure path in
vfio_msi_enableandvfio_msi_disable_commonis enable INTX or not.Extend the
vfio_msi_disable_commonto provide a arg to decide
"an arg"
Quoted 2 lines
whether need to fallback, and then we can use this helper to instead the redundant code in
vfio_msi_enable.
Do you mean s/instead/replace/?
Quoted 19 lines
Signed-off-by Longpeng(Mike) <[email protected]>--- hw/vfio/pci.c | 34 ++++++++++++---------------------- 1 file changed, 12 insertions(+), 22 deletions(-)hw/vfio/pci.c +1
-0@@ -47,6 +47,7 @@static void vfio_disable_interrupts (VFIOPCIDevice *vdev);static void vfio_mmap_set_enabled (VFIOPCIDevice *vdev,bool enabled); +static void vfio_msi_disable_common (VFIOPCIDevice *vdev,bool enable_intx);/* * Disabling BAR mmaping can be slow, but toggling it around INTx can
hw/vfio/pci.c retry: · line 653
Quoted 4 lines
hw/vfio/pci.c +0
-1@@ -650,29 +651,17 @@ retry:if (ret) {if (ret <0 ) {error_report ("vfio: Error: Failed to setup MSI fds: %m" ); - }else if (ret != vdev->nr_vectors) {
This part of the change is subtle and not mentioned in the commit log. It does seem unnecessary to test against this specific return value since any positive return is an error indicating the number of vectors we should retry with, but this change should be described in a separate patch.
Quoted 37 lines
hw/vfio/pci.c +3
-15+ }else {error_report ("vfio: Error: Failed to enable %d " "MSI vectors, retry with %d" , vdev->nr_vectors, ret); } -for (i =0 ; i < vdev->nr_vectors; i++) { -VFIOMSIVector *vector = &vdev->msi_vectors[i]; -if (vector->virq >=0 ) { -vfio_remove_kvm_msi_virq (vector); - } -qemu_set_fd_handler (event_notifier_get_fd (&vector->interrupt), -NULL ,NULL ,NULL ); -event_notifier_cleanup (&vector->interrupt); - } - -g_free (vdev->msi_vectors); - vdev->msi_vectors =NULL ; +vfio_msi_disable_common (vdev, false); -if (ret >0 && ret != vdev->nr_vectors) { +if (ret >0 ) { vdev->nr_vectors = ret; goto retry; } - vdev->nr_vectors =0 ;/* * Failing to setup MSI doesn't really fall within any specification. @@ -680,7 +669,6 @@ retry:* out to fall back to INTx for this device. */ error_report ("vfio: Error: Failed to enable MSI" ); - vdev->interrupt =VFIO_INT_NONE ;return ; }
hw/vfio/pci.c retry: · line 679
Quoted 5 lines
hw/vfio/pci.c +1
-1@@ -688,7 +676,7 @@ retry:trace_vfio_msi_enable (vdev->vbasedev.name, vdev->nr_vectors); } -static void vfio_msi_disable_common (VFIOPCIDevice *vdev) +static void vfio_msi_disable_common (VFIOPCIDevice *vdev,bool enable_intx)
I'd rather avoid these sort of modal options to functions where we can. Maybe this suggests instead that re-enabling INTx should be removed from the common helper and callers needing to do so should do it outside of the common helper. Thanks,
Alex
Quoted 36 lines
hw/vfio/pci.c +7
-5{Error *err =NULL ;int i;@@ -710,9 +698,11 @@ static void vfio_msi_disable_common(VFIOPCIDevice *vdev) vdev->nr_vectors =0 ; vdev->interrupt =VFIO_INT_NONE ; -vfio_intx_enable (vdev, &err); -if (err) { -error_reportf_err (err,VFIO_MSG_PREFIX , vdev->vbasedev.name); +if (enable_intx) { +vfio_intx_enable (vdev, &err); +if (err) { +error_reportf_err (err,VFIO_MSG_PREFIX , vdev->vbasedev.name); + } } }@@ -737,7 +727,7 @@ static void vfio_msix_disable(VFIOPCIDevice *vdev)vfio_disable_irqindex (&vdev->vbasedev,VFIO_PCI_MSIX_IRQ_INDEX ); } -vfio_msi_disable_common (vdev); +vfio_msi_disable_common (vdev, true);memset (vdev->msix->pending,0 ,BITS_TO_LONGS (vdev->msix->entries) *sizeof (unsigned long ));@@ -748,7 +738,7 @@ static void vfio_msix_disable(VFIOPCIDevice *vdev)static void vfio_msi_disable (VFIOPCIDevice *vdev) {vfio_disable_irqindex (&vdev->vbasedev,VFIO_PCI_MSI_IRQ_INDEX ); -vfio_msi_disable_common (vdev); +vfio_msi_disable_common (vdev, true);trace_vfio_msi_disable (vdev->vbasedev.name); }
Re: [PATCH 1/5] vfio: use helper to simplfy the failure path in vfio_msi_enable
Quoted 10 lines · Alex Williamson
Quoted 4 lines · On Wed, 25 Aug 2021 15:56:16 +0800 "Longpeng(Mike)" <[email protected]>…
The main difference of the failure path in
vfio_msi_enableandvfio_msi_disable_commonis enable INTX or not.Extend the
vfio_msi_disable_commonto provide a arg to decide"an arg"
Thanks a lot, I'll fix all of the grammatical errors and typos in this version together.
Quoted 21 lines
Quoted 2 lines
whether need to fallback, and then we can use this helper to instead the redundant code in
vfio_msi_enable.Do you mean s/instead/replace/?
Quoted 16 lines
Signed-off-by Longpeng(Mike) <[email protected]>--- hw/vfio/pci.c | 34 ++++++++++++---------------------- 1 file changed, 12 insertions(+), 22 deletions(-)hw/vfio/pci.c +1
-0@@ -47,6 +47,7 @@static void vfio_disable_interrupts (VFIOPCIDevice *vdev);static void vfio_mmap_set_enabled (VFIOPCIDevice *vdev,bool enabled); +static void vfio_msi_disable_common (VFIOPCIDevice *vdev,bool enable_intx);
Quoted 14 lines
hw/vfio/pci.c retry: · line 653
Quoted 7 lines
hw/vfio/pci.c +0
-1/* * Disabling BAR mmaping can be slow, but toggling it around INTx can @@ -650,29 +651,17 @@ retry:if (ret) {if (ret <0 ) {error_report ("vfio: Error: Failed to setup MSI fds: %m" ); - }else if (ret != vdev->nr_vectors) {This part of the change is subtle and not mentioned in the commit log. It does seem unnecessary to test against this specific return value since any positive return is an error indicating the number of vectors we should retry with, but this change should be described in a separate patch.
Ok, thanks, I'll split in the next version.
Quoted 40 lines
Quoted 40 lines
hw/vfio/pci.c +3
-15+ }else {error_report ("vfio: Error: Failed to enable %d " "MSI vectors, retry with %d" , vdev->nr_vectors, ret); } -for (i =0 ; i < vdev->nr_vectors; i++) { -VFIOMSIVector *vector = &vdev->msi_vectors[i]; -if (vector->virq >=0 ) { -vfio_remove_kvm_msi_virq (vector); - } -qemu_set_fd_handler (event_notifier_get_fd (&vector->interrupt), -NULL ,NULL ,NULL ); -event_notifier_cleanup (&vector->interrupt); - } - -g_free (vdev->msi_vectors); - vdev->msi_vectors =NULL ; +vfio_msi_disable_common (vdev, false); -if (ret >0 && ret != vdev->nr_vectors) { +if (ret >0 ) { vdev->nr_vectors = ret; goto retry; } - vdev->nr_vectors =0 ;/* * Failing to setup MSI doesn't really fall within any specification. @@ -680,7 +669,6 @@ retry:* out to fall back to INTx for this device. */ error_report ("vfio: Error: Failed to enable MSI" ); - vdev->interrupt =VFIO_INT_NONE ;return ; }@@ -688,7 +676,7 @@ retry:trace_vfio_msi_enable (vdev->vbasedev.name, vdev->nr_vectors); }
Quoted 8 lines
hw/vfio/pci.c retry: · line 679
Quoted 2 lines
hw/vfio/pci.c +1
-1-static void vfio_msi_disable_common (VFIOPCIDevice *vdev) +static void vfio_msi_disable_common (VFIOPCIDevice *vdev,bool enable_intx)I'd rather avoid these sort of modal options to functions where we can. Maybe this suggests instead that re-enabling INTx should be removed from the common helper and callers needing to do so should do it outside of the common helper. Thanks,
Ok, thanks.
Quoted 42 lines
Alex
Quoted 28 lines
hw/vfio/pci.c +6
-4{Error *err =NULL ;int i;@@ -710,9 +698,11 @@ static void vfio_msi_disable_common(VFIOPCIDevice *vdev) vdev->nr_vectors =0 ; vdev->interrupt =VFIO_INT_NONE ; -vfio_intx_enable (vdev, &err); -if (err) { -error_reportf_err (err,VFIO_MSG_PREFIX , vdev->vbasedev.name); +if (enable_intx) { +vfio_intx_enable (vdev, &err); +if (err) { +error_reportf_err (err,VFIO_MSG_PREFIX , vdev->vbasedev.name); + } } }@@ -737,7 +727,7 @@ static void vfio_msix_disable(VFIOPCIDevice *vdev)vfio_disable_irqindex (&vdev->vbasedev,VFIO_PCI_MSIX_IRQ_INDEX ); } -vfio_msi_disable_common (vdev); +vfio_msi_disable_common (vdev, true);memset (vdev->msix->pending,0 ,BITS_TO_LONGS (vdev->msix->entries) *sizeof (unsigned long ));hw/vfio/pci.c static void vfio_msix_disable(VFIOPCIDevice *vdev) · line 744
Quoted 8 lines
hw/vfio/pci.c +1
-1@@ -748,7 +738,7 @@ static void vfio_msix_disable(VFIOPCIDevice *vdev)static void vfio_msi_disable (VFIOPCIDevice *vdev) {vfio_disable_irqindex (&vdev->vbasedev,VFIO_PCI_MSI_IRQ_INDEX ); -vfio_msi_disable_common (vdev); +vfio_msi_disable_common (vdev, true);trace_vfio_msi_disable (vdev->vbasedev.name); }.
PATCH 2/5 msix: simplfy the conditional in msix_set/unset_vector_notifiers
In reply to Longpeng(Mike)'msix_function_masked' is kept pace with the device's config, we can use it to replace the complex conditional in msix_set/unset_vector_notifiers.
poll_notifier should be reset to NULL in the error path in msix_set_vector_notifiers, fix it incidentally.
--- hw/pci/msix.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-)
hw/pci/msix.c +3 -4
@@ -592,8 +592,7 @@ int msix_set_vector_notifiers(PCIDevice *dev, dev->msix_vector_release_notifier = release_notifier; dev->msix_vector_poll_notifier = poll_notifier; -if ((dev->config[dev->msix_cap +MSIX_CONTROL_OFFSET ] & - (MSIX_ENABLE_MASK |MSIX_MASKALL_MASK )) ==MSIX_ENABLE_MASK ) { +if (!dev->msix_function_masked) {for (vector =0 ; vector < dev->msix_entries_nr; vector++) { ret =msix_set_notifier_for_vector (dev, vector);if (ret <0 ) {
@@ -612,6 +611,7 @@ undo: } dev->msix_vector_use_notifier =NULL ; dev->msix_vector_release_notifier =NULL ; + dev->msix_vector_poll_notifier =NULL ;return ret; }
@@ -622,8 +622,7 @@ void msix_unset_vector_notifiers(PCIDevice *dev)assert (dev->msix_vector_use_notifier && dev->msix_vector_release_notifier); -if ((dev->config[dev->msix_cap +MSIX_CONTROL_OFFSET ] & - (MSIX_ENABLE_MASK |MSIX_MASKALL_MASK )) ==MSIX_ENABLE_MASK ) { +if (!dev->msix_function_masked) {for (vector =0 ; vector < dev->msix_entries_nr; vector++) {msix_unset_notifier_for_vector (dev, vector); }
Signature · 1 line
1.8.3.1
Re: [PATCH 2/5] msix: simplfy the conditional in msix_set/unset_vector_notifiers
Quoted 3 lines · Longpeng(Mike)
'
msix_function_masked' is kept pace with the device's config, we can use it to replace the complex conditional in msix_set/unset_vector_notifiers.
Typo 'simplfy' -> 'simplify' in this/previous patch subject.
Quoted 2 lines
poll_notifiershould be reset to NULL in the error path inmsix_set_vector_notifiers, fix it incidentally.
I'd rather see this fix in a different patch, being unrelated to the msix_function_masked optimization.
Quoted 38 lines
Signed-off-by Longpeng(Mike) <[email protected]>--- hw/pci/msix.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-)hw/pci/msix.c +3
-4@@ -592,8 +592,7 @@ int msix_set_vector_notifiers(PCIDevice *dev, dev->msix_vector_release_notifier = release_notifier; dev->msix_vector_poll_notifier = poll_notifier; -if ((dev->config[dev->msix_cap +MSIX_CONTROL_OFFSET ] & - (MSIX_ENABLE_MASK |MSIX_MASKALL_MASK )) ==MSIX_ENABLE_MASK ) { +if (!dev->msix_function_masked) {for (vector =0 ; vector < dev->msix_entries_nr; vector++) { ret =msix_set_notifier_for_vector (dev, vector);if (ret <0 ) {@@ -612,6 +611,7 @@ undo: } dev->msix_vector_use_notifier =NULL ; dev->msix_vector_release_notifier =NULL ; + dev->msix_vector_poll_notifier =NULL ;return ret; }@@ -622,8 +622,7 @@ void msix_unset_vector_notifiers(PCIDevice *dev)assert (dev->msix_vector_use_notifier && dev->msix_vector_release_notifier); -if ((dev->config[dev->msix_cap +MSIX_CONTROL_OFFSET ] & - (MSIX_ENABLE_MASK |MSIX_MASKALL_MASK )) ==MSIX_ENABLE_MASK ) { +if (!dev->msix_function_masked) {for (vector =0 ; vector < dev->msix_entries_nr; vector++) {msix_unset_notifier_for_vector (dev, vector); }
Re: [PATCH 2/5] msix: simplfy the conditional in msix_set/unset_vector_notifiers
Quoted 5 lines · Philippe Mathieu-Daudé
Quoted 3 lines · Longpeng(Mike)
'
msix_function_masked' is kept pace with the device's config, we can use it to replace the complex conditional in msix_set/unset_vector_notifiers.
Quoted 9 lines
Typo 'simplfy' -> 'simplify' in this/previous patch subject. Ok.
Quoted 2 lines
poll_notifiershould be reset to NULL in the error path inmsix_set_vector_notifiers, fix it incidentally.I'd rather see this fix in a different patch, being unrelated to the
msix_function_maskedoptimization.
Ok, will split in next version. Thanks.
Quoted 41 lines
Quoted 29 lines
Signed-off-by Longpeng(Mike) <[email protected]>--- hw/pci/msix.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-)hw/pci/msix.c +2
-2@@ -592,8 +592,7 @@ int msix_set_vector_notifiers(PCIDevice *dev, dev->msix_vector_release_notifier = release_notifier; dev->msix_vector_poll_notifier = poll_notifier; -if ((dev->config[dev->msix_cap +MSIX_CONTROL_OFFSET ] & - (MSIX_ENABLE_MASK |MSIX_MASKALL_MASK )) ==MSIX_ENABLE_MASK ) { +if (!dev->msix_function_masked) {for (vector =0 ; vector < dev->msix_entries_nr; vector++) { ret =msix_set_notifier_for_vector (dev, vector);if (ret <0 ) {@@ -612,6 +611,7 @@ undo: } dev->msix_vector_use_notifier =NULL ; dev->msix_vector_release_notifier =NULL ; + dev->msix_vector_poll_notifier =NULL ;return ret; }hw/pci/msix.c void msix_unset_vector_notifiers(PCIDevice *dev) · line 628
Quoted 9 lines
hw/pci/msix.c +1
-2@@ -622,8 +622,7 @@ void msix_unset_vector_notifiers(PCIDevice *dev)assert (dev->msix_vector_use_notifier && dev->msix_vector_release_notifier); -if ((dev->config[dev->msix_cap +MSIX_CONTROL_OFFSET ] & - (MSIX_ENABLE_MASK |MSIX_MASKALL_MASK )) ==MSIX_ENABLE_MASK ) { +if (!dev->msix_function_masked) {for (vector =0 ; vector < dev->msix_entries_nr; vector++) {msix_unset_notifier_for_vector (dev, vector); }.
Re: [PATCH 2/5] msix: simplfy the conditional in msix_set/unset_vector_notifiers
In reply to Longpeng(Mike)Quoted 1 line · On Wed, 25 Aug 2021 15:56:17 +0800 "Longpeng(Mike)" <[email protected]>…
'
msix_function_masked' is kept pace with the device's config,
s/pace/synchronized/?
Quoted 5 lines
we can use it to replace the complex conditional in msix_set/unset_vector_notifiers.
poll_notifiershould be reset to NULL in the error path inmsix_set_vector_notifiers, fix it incidentally.
Agree with Philippe, separate patch.
Quoted 37 lines
Signed-off-by Longpeng(Mike) <[email protected]>--- hw/pci/msix.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-)hw/pci/msix.c +3
-4@@ -592,8 +592,7 @@ int msix_set_vector_notifiers(PCIDevice *dev, dev->msix_vector_release_notifier = release_notifier; dev->msix_vector_poll_notifier = poll_notifier; -if ((dev->config[dev->msix_cap +MSIX_CONTROL_OFFSET ] & - (MSIX_ENABLE_MASK |MSIX_MASKALL_MASK )) ==MSIX_ENABLE_MASK ) { +if (!dev->msix_function_masked) {for (vector =0 ; vector < dev->msix_entries_nr; vector++) { ret =msix_set_notifier_for_vector (dev, vector);if (ret <0 ) {@@ -612,6 +611,7 @@ undo: } dev->msix_vector_use_notifier =NULL ; dev->msix_vector_release_notifier =NULL ; + dev->msix_vector_poll_notifier =NULL ;return ret; }@@ -622,8 +622,7 @@ void msix_unset_vector_notifiers(PCIDevice *dev)assert (dev->msix_vector_use_notifier && dev->msix_vector_release_notifier); -if ((dev->config[dev->msix_cap +MSIX_CONTROL_OFFSET ] & - (MSIX_ENABLE_MASK |MSIX_MASKALL_MASK )) ==MSIX_ENABLE_MASK ) { +if (!dev->msix_function_masked) {for (vector =0 ; vector < dev->msix_entries_nr; vector++) {msix_unset_notifier_for_vector (dev, vector); }
PATCH 3/5 vfio: defer to enable msix in migration resume phase
In reply to Longpeng(Mike)The vf's unmasked msix vectors will be enable one by one in migraiton resume phase, VFIO_DEVICE_SET_IRQS will be called for each vector, it's a bit expensive if the vf has more vectors.
We can call VFIO_DEVICE_SET_IRQS once outside the loop of set vector notifiers to reduce the cost.
The test VM has 128 vcpus and 8 VF (with 65 vectors enabled), we mesure the cost of the vfio_msix_enable for each one, and we can see 10% costs can be reduced.
Origin Apply this patch 1st 8 4 2nd 15 11 3rd 22 18 4th 24 25 5th 36 33 6th 44 40 7th 51 47 8th 58 54 Total 258ms 232ms
--- hw/vfio/pci.c | 22 ++++++++++++++++++++++ hw/vfio/pci.h | 1 + 2 files changed, 23 insertions(+)
hw/vfio/pci.c +22 -0
@@ -372,6 +372,10 @@ static int vfio_enable_vectors(VFIOPCIDevice *vdev, bool msix)int ret =0 , i, argsz;int32_t *fds; +if (!vdev->nr_vectors) { +return 0 ; + } + argsz =sizeof (*irq_set) + (vdev->nr_vectors *sizeof (*fds)); irq_set =g_malloc0 (argsz);
@@ -495,6 +499,11 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr, } } +if (vdev->defer_add_virq) { + vdev->nr_vectors =MAX (vdev->nr_vectors, nr +1 ); + goto clear_pending; + } +/* * We don't want to have the host allocate all possible MSI vectors * for a device if they're not in use, so we shutdown and incrementally
@@ -524,6 +533,7 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr, } } +clear_pending:/* Disable PBA emulation when nothing more is pending. */ clear_bit (nr, vdev->msix->pending); if (find_first_bit(vdev->msix->pending,
@@ -608,6 +618,16 @@ static void vfio_msix_enable(VFIOPCIDevice *vdev)if (msix_set_vector_notifiers (pdev, vfio_msix_vector_use, vfio_msix_vector_release,NULL )) {error_report ("vfio: msix_set_vector_notifiers failed" ); +return ; + } + +if (!pdev->msix_function_masked && vdev->defer_add_virq) { +int ret; +vfio_disable_irqindex (&vdev->vbasedev,VFIO_PCI_MSIX_IRQ_INDEX ); + ret =vfio_enable_vectors (vdev, true); +if (ret) { +error_report ("vfio: failed to enable vectors, %d" , ret); + } }trace_vfio_msix_enable (vdev->vbasedev.name);
@@ -2456,7 +2476,9 @@ static int vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f)if (msi_enabled (pdev)) {vfio_msi_enable (vdev); }else if (msix_enabled (pdev)) { + vdev->defer_add_virq = true;vfio_msix_enable (vdev); + vdev->defer_add_virq = false; }return ret;
hw/vfio/pci.h +1 -0
@@ -171,6 +171,7 @@ struct VFIOPCIDevice {bool no_kvm_ioeventfd;bool no_vfio_ioeventfd;bool enable_ramfb; +bool defer_add_virq;VFIODisplay *dpy;Notifier irqchip_change_notifier; };
Signature · 1 line
1.8.3.1
Re: [PATCH 3/5] vfio: defer to enable msix in migration resume phase
Quoted 2 lines · Longpeng(Mike)
The vf's unmasked msix vectors will be enable one by one in migraiton resume phase,
VFIO_DEVICE_SET_IRQSwill be called
Typo "migration"
Quoted 8 lines
for each vector, it's a bit expensive if the vf has more vectors.
We can call
VFIO_DEVICE_SET_IRQSonce outside the loop of set vector notifiers to reduce the cost.The test VM has 128 vcpus and 8 VF (with 65 vectors enabled), we mesure the cost of the
vfio_msix_enablefor each one, and
Typo "measure"
Quoted 72 lines
we can see 10% costs can be reduced.
Origin Apply this patch 1st 8 4 2nd 15 11 3rd 22 18 4th 24 25 5th 36 33 6th 44 40 7th 51 47 8th 58 54 Total 258ms 232msSigned-off-by Longpeng(Mike) <[email protected]>--- hw/vfio/pci.c | 22 ++++++++++++++++++++++ hw/vfio/pci.h | 1 + 2 files changed, 23 insertions(+)hw/vfio/pci.c +20
-0@@ -372,6 +372,10 @@ static int vfio_enable_vectors(VFIOPCIDevice *vdev, bool msix)int ret =0 , i, argsz;int32_t *fds; +if (!vdev->nr_vectors) { +return 0 ; + } + argsz =sizeof (*irq_set) + (vdev->nr_vectors *sizeof (*fds)); irq_set =g_malloc0 (argsz);@@ -495,6 +499,11 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr, } } +if (vdev->defer_add_virq) { + vdev->nr_vectors =MAX (vdev->nr_vectors, nr +1 ); + goto clear_pending; + } +/* * We don't want to have the host allocate all possible MSI vectors * for a device if they're not in use, so we shutdown and incrementally @@ -524,6 +533,7 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr, } } +clear_pending:/* Disable PBA emulation when nothing more is pending. */ clear_bit (nr, vdev->msix->pending); if (find_first_bit(vdev->msix->pending,@@ -608,6 +618,16 @@ static void vfio_msix_enable(VFIOPCIDevice *vdev)if (msix_set_vector_notifiers (pdev, vfio_msix_vector_use, vfio_msix_vector_release,NULL )) {error_report ("vfio: msix_set_vector_notifiers failed" ); +return ; + } + +if (!pdev->msix_function_masked && vdev->defer_add_virq) { +int ret; +vfio_disable_irqindex (&vdev->vbasedev,VFIO_PCI_MSIX_IRQ_INDEX ); + ret =vfio_enable_vectors (vdev, true); +if (ret) { +error_report ("vfio: failed to enable vectors, %d" , ret); + } }trace_vfio_msix_enable (vdev->vbasedev.name);
hw/vfio/pci.c static int vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f) · line 2480
Quoted 5 lines
hw/vfio/pci.c +1
-0@@ -2456,7 +2476,9 @@ static int vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f)if (msi_enabled (pdev)) {vfio_msi_enable (vdev); }else if (msix_enabled (pdev)) { + vdev->defer_add_virq = true;vfio_msix_enable (vdev);
What about passing defer_add_virq as boolean argument to vfio_msix_enable()?
Quoted 17 lines
hw/vfio/pci.c +1
-0+ vdev->defer_add_virq = false; }return ret;hw/vfio/pci.h +1
-0@@ -171,6 +171,7 @@ struct VFIOPCIDevice {bool no_kvm_ioeventfd;bool no_vfio_ioeventfd;bool enable_ramfb; +bool defer_add_virq;VFIODisplay *dpy;Notifier irqchip_change_notifier; };
Re: [PATCH 3/5] vfio: defer to enable msix in migration resume phase
Quoted 6 lines · Philippe Mathieu-Daudé
Quoted 2 lines · Longpeng(Mike)
The vf's unmasked msix vectors will be enable one by one in migraiton resume phase,
VFIO_DEVICE_SET_IRQSwill be calledTypo "migration"
Ok.
Quoted 11 lines
Quoted 8 lines
for each vector, it's a bit expensive if the vf has more vectors.
We can call
VFIO_DEVICE_SET_IRQSonce outside the loop of set vector notifiers to reduce the cost.The test VM has 128 vcpus and 8 VF (with 65 vectors enabled), we mesure the cost of the
vfio_msix_enablefor each one, andTypo "measure"
Ok.
Quoted 70 lines
Quoted 70 lines
we can see 10% costs can be reduced.
Origin Apply this patch 1st 8 4 2nd 15 11 3rd 22 18 4th 24 25 5th 36 33 6th 44 40 7th 51 47 8th 58 54 Total 258ms 232msSigned-off-by Longpeng(Mike) <[email protected]>--- hw/vfio/pci.c | 22 ++++++++++++++++++++++ hw/vfio/pci.h | 1 + 2 files changed, 23 insertions(+)hw/vfio/pci.c +20
-0@@ -372,6 +372,10 @@ static int vfio_enable_vectors(VFIOPCIDevice *vdev, bool msix)int ret =0 , i, argsz;int32_t *fds; +if (!vdev->nr_vectors) { +return 0 ; + } + argsz =sizeof (*irq_set) + (vdev->nr_vectors *sizeof (*fds)); irq_set =g_malloc0 (argsz);@@ -495,6 +499,11 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr, } } +if (vdev->defer_add_virq) { + vdev->nr_vectors =MAX (vdev->nr_vectors, nr +1 ); + goto clear_pending; + } +/* * We don't want to have the host allocate all possible MSI vectors * for a device if they're not in use, so we shutdown and incrementally @@ -524,6 +533,7 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr, } } +clear_pending:/* Disable PBA emulation when nothing more is pending. */ clear_bit (nr, vdev->msix->pending); if (find_first_bit(vdev->msix->pending,@@ -608,6 +618,16 @@ static void vfio_msix_enable(VFIOPCIDevice *vdev)if (msix_set_vector_notifiers (pdev, vfio_msix_vector_use, vfio_msix_vector_release,NULL )) {error_report ("vfio: msix_set_vector_notifiers failed" ); +return ; + } + +if (!pdev->msix_function_masked && vdev->defer_add_virq) { +int ret; +vfio_disable_irqindex (&vdev->vbasedev,VFIO_PCI_MSIX_IRQ_INDEX ); + ret =vfio_enable_vectors (vdev, true); +if (ret) { +error_report ("vfio: failed to enable vectors, %d" , ret); + } }
Quoted 11 lines
hw/vfio/pci.c static int vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f) · line 2480
Quoted 7 lines
hw/vfio/pci.c +1
-0trace_vfio_msix_enable (vdev->vbasedev.name);@@ -2456,7 +2476,9 @@ static int vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f)if (msi_enabled (pdev)) {vfio_msi_enable (vdev); }else if (msix_enabled (pdev)) { + vdev->defer_add_virq = true;vfio_msix_enable (vdev);What about passing
defer_add_virqas boolean argument tovfio_msix_enable()?
We'll use defer_add_virq in the deep of the calltrace, it need to change more functions to support the parameter passing in this way.
Quoted 20 lines
Quoted 10 lines
hw/vfio/pci.c +1
-0+ vdev->defer_add_virq = false; }return ret;hw/vfio/pci.h +0
-0hw/vfio/pci.h struct VFIOPCIDevice { · line 177
Quoted 7 lines
hw/vfio/pci.h +1
-0@@ -171,6 +171,7 @@ struct VFIOPCIDevice {bool no_kvm_ioeventfd;bool no_vfio_ioeventfd;bool enable_ramfb; +bool defer_add_virq;VFIODisplay *dpy;Notifier irqchip_change_notifier; };.
Re: [PATCH 3/5] vfio: defer to enable msix in migration resume phase
In reply to Longpeng(Mike)Quoted 5 lines · On Wed, 25 Aug 2021 15:56:18 +0800 "Longpeng(Mike)" <[email protected]>…
The vf's unmasked msix vectors will be enable one by one in migraiton resume phase,
VFIO_DEVICE_SET_IRQSwill be called for each vector, it's a bit expensive if the vf has more vectors.
Quoted 8 lines
We can call
VFIO_DEVICE_SET_IRQSonce outside the loop of set vector notifiers to reduce the cost.The test VM has 128 vcpus and 8 VF (with 65 vectors enabled), we mesure the cost of the
vfio_msix_enablefor each one, and we can see 10% costs can be reduced.Origin Apply this patch
Original?
Quoted 9 lines
1st 8 4 2nd 15 11 3rd 22 18 4th 24 25 5th 36 33 6th 44 40 7th 51 47 8th 58 54 Total 258ms 232ms
If the values here are ms for execution of vfio_msix_enable() per VF, why are the values increasing per VF? Do we have 65 vectors per VF or do we have 65 vectors total, weighted towards to higher VFs? This doesn't make sense without the data from the last patch in the series.
Quoted 12 lines
Signed-off-by Longpeng(Mike) <[email protected]>--- hw/vfio/pci.c | 22 ++++++++++++++++++++++ hw/vfio/pci.h | 1 + 2 files changed, 23 insertions(+)hw/vfio/pci.c +0
-0
hw/vfio/pci.c static int vfio_enable_vectors(VFIOPCIDevice *vdev, bool msix) · line 377
Quoted 6 lines
hw/vfio/pci.c +3
-0@@ -372,6 +372,10 @@ static int vfio_enable_vectors(VFIOPCIDevice *vdev, bool msix)int ret =0 , i, argsz;int32_t *fds; +if (!vdev->nr_vectors) { +return 0 ; + }
How would this occur? Via the new call below? But then we'd leave vfio_msix_enabled() with MSI-X DISABLED???
hw/vfio/pci.c static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr, · line 505
Quoted 12 lines
hw/vfio/pci.c +5
-0+ argsz =sizeof (*irq_set) + (vdev->nr_vectors *sizeof (*fds)); irq_set =g_malloc0 (argsz);@@ -495,6 +499,11 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr, } } +if (vdev->defer_add_virq) { + vdev->nr_vectors =MAX (vdev->nr_vectors, nr +1 ); + goto clear_pending; + }
This is a really ugly use of 'goto' to simply jump around code you'd like to skip rather than reformat the function with branches to conditionalize that code. Gotos for consolidated error paths, retries, hard to break loops are ok, not this.
Quoted 30 lines
hw/vfio/pci.c +12
-0+/* * We don't want to have the host allocate all possible MSI vectors * for a device if they're not in use, so we shutdown and incrementally @@ -524,6 +533,7 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr, } } +clear_pending:/* Disable PBA emulation when nothing more is pending. */ clear_bit (nr, vdev->msix->pending); if (find_first_bit(vdev->msix->pending,@@ -608,6 +618,16 @@ static void vfio_msix_enable(VFIOPCIDevice *vdev)if (msix_set_vector_notifiers (pdev, vfio_msix_vector_use, vfio_msix_vector_release,NULL )) {error_report ("vfio: msix_set_vector_notifiers failed" ); +return ; + } + +if (!pdev->msix_function_masked && vdev->defer_add_virq) { +int ret; +vfio_disable_irqindex (&vdev->vbasedev,VFIO_PCI_MSIX_IRQ_INDEX ); + ret =vfio_enable_vectors (vdev, true); +if (ret) { +error_report ("vfio: failed to enable vectors, %d" , ret); + } }trace_vfio_msix_enable (vdev->vbasedev.name);
hw/vfio/pci.c static int vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f) · line 2481
Quoted 6 lines
hw/vfio/pci.c +2
-0@@ -2456,7 +2476,9 @@ static int vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f)if (msi_enabled (pdev)) {vfio_msi_enable (vdev); }else if (msix_enabled (pdev)) { + vdev->defer_add_virq = true;vfio_msix_enable (vdev); + vdev->defer_add_virq = false;
Ick. Why is this a special case for vfio_msix_enable()? Wouldn't we prefer to always batch vector-use work while we're in the process of enabling MSI-X?
Quoted 15 lines
hw/vfio/pci.c +0
-0}return ret;hw/vfio/pci.h +1
-0@@ -171,6 +171,7 @@ struct VFIOPCIDevice {bool no_kvm_ioeventfd;bool no_vfio_ioeventfd;bool enable_ramfb; +bool defer_add_virq;VFIODisplay *dpy;Notifier irqchip_change_notifier; };
Re: [PATCH 3/5] vfio: defer to enable msix in migration resume phase
Quoted 29 lines · Alex Williamson
Quoted 5 lines · On Wed, 25 Aug 2021 15:56:18 +0800 "Longpeng(Mike)" <[email protected]>…
The vf's unmasked msix vectors will be enable one by one in migraiton resume phase,
VFIO_DEVICE_SET_IRQSwill be called for each vector, it's a bit expensive if the vf has more vectors.Quoted 8 lines
We can call
VFIO_DEVICE_SET_IRQSonce outside the loop of set vector notifiers to reduce the cost.The test VM has 128 vcpus and 8 VF (with 65 vectors enabled), we mesure the cost of the
vfio_msix_enablefor each one, and we can see 10% costs can be reduced.Origin Apply this patch
Original?
Quoted 9 lines
1st 8 4 2nd 15 11 3rd 22 18 4th 24 25 5th 36 33 6th 44 40 7th 51 47 8th 58 54 Total 258ms 232ms
Quoted 1 line
If the values here are ms for execution of
vfio_msix_enable()per VF,
Yes.
Quoted 2 lines
why are the values increasing per VF? Do we have 65 vectors per VF or do we have 65 vectors total, weighted towards to higher VFs?
We have 65 vectors per VF.
The KVM_SET_GSI_ROUTING scans and updates all of the assigned irqfds unconditionally, so it will spend more time if there are more irqfds.
We have 65 irqfds when process the 1st VF, 130 irqfds when process the 2nd VF, 195 irqfds when process the 3rd VF ... so we'll see the values are increasing as a result.
Quoted 33 lines
This doesn't make sense without the data from the last patch in the series.
Quoted 12 lines
Signed-off-by Longpeng(Mike) <[email protected]>--- hw/vfio/pci.c | 22 ++++++++++++++++++++++ hw/vfio/pci.h | 1 + 2 files changed, 23 insertions(+)hw/vfio/pci.c +0
-0hw/vfio/pci.c static int vfio_enable_vectors(VFIOPCIDevice *vdev, bool msix) · line 377
Quoted 6 lines
hw/vfio/pci.c +3
-0@@ -372,6 +372,10 @@ static int vfio_enable_vectors(VFIOPCIDevice *vdev, bool msix)int ret =0 , i, argsz;int32_t *fds; +if (!vdev->nr_vectors) { +return 0 ; + }How would this occur? Via the new call below? But then we'd leave
vfio_msix_enabled()with MSI-X DISABLED???Quoted 8 lines
hw/vfio/pci.c +1
-0+ argsz =sizeof (*irq_set) + (vdev->nr_vectors *sizeof (*fds)); irq_set =g_malloc0 (argsz);@@ -495,6 +499,11 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr, } }
Quoted 10 lines
hw/vfio/pci.c static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr, · line 505
Quoted 4 lines
hw/vfio/pci.c +4
-0+if (vdev->defer_add_virq) { + vdev->nr_vectors =MAX (vdev->nr_vectors, nr +1 ); + goto clear_pending; + }This is a really ugly use of 'goto' to simply jump around code you'd like to skip rather than reformat the function with branches to conditionalize that code. Gotos for consolidated error paths, retries, hard to break loops are ok, not this.
Got it, thanks.
Quoted 29 lines
Quoted 29 lines
hw/vfio/pci.c +12
-0+/* * We don't want to have the host allocate all possible MSI vectors * for a device if they're not in use, so we shutdown and incrementally @@ -524,6 +533,7 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr, } } +clear_pending:/* Disable PBA emulation when nothing more is pending. */ clear_bit (nr, vdev->msix->pending); if (find_first_bit(vdev->msix->pending,@@ -608,6 +618,16 @@ static void vfio_msix_enable(VFIOPCIDevice *vdev)if (msix_set_vector_notifiers (pdev, vfio_msix_vector_use, vfio_msix_vector_release,NULL )) {error_report ("vfio: msix_set_vector_notifiers failed" ); +return ; + } + +if (!pdev->msix_function_masked && vdev->defer_add_virq) { +int ret; +vfio_disable_irqindex (&vdev->vbasedev,VFIO_PCI_MSIX_IRQ_INDEX ); + ret =vfio_enable_vectors (vdev, true); +if (ret) { +error_report ("vfio: failed to enable vectors, %d" , ret); + } }
Quoted 14 lines
hw/vfio/pci.c static int vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f) · line 2481
Quoted 8 lines
hw/vfio/pci.c +2
-0trace_vfio_msix_enable (vdev->vbasedev.name);@@ -2456,7 +2476,9 @@ static int vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f)if (msi_enabled (pdev)) {vfio_msi_enable (vdev); }else if (msix_enabled (pdev)) { + vdev->defer_add_virq = true;vfio_msix_enable (vdev); + vdev->defer_add_virq = false;Ick. Why is this a special case for
vfio_msix_enable()? Wouldn't we prefer to always batch vector-use work while we're in the process of enabling MSI-X?
Ok, will do in next version.
In addition, I'll rename the field to 'defer_kvm_irq_routing' as you suggested in another earlier thread.
'''
> - vfio_add_kvm_msi_virq(vdev, vector, nr, true);
> + if (unlikely(vdev->defer_set_virq)) {
Likewise this could be "vdev->defer_kvm_irq_routing" and we could apply
it to all IRQ types.
> + vector->need_switch = true;
> + } else {
'''Quoted 18 lines
Quoted 8 lines
hw/vfio/pci.c +0
-0}return ret;hw/vfio/pci.h +0
-0hw/vfio/pci.h struct VFIOPCIDevice { · line 177
Quoted 7 lines
hw/vfio/pci.h +1
-0@@ -171,6 +171,7 @@ struct VFIOPCIDevice {bool no_kvm_ioeventfd;bool no_vfio_ioeventfd;bool enable_ramfb; +bool defer_add_virq;VFIODisplay *dpy;Notifier irqchip_change_notifier; };.
PATCH 4/5 kvm: irqchip: support defer to commit the route
In reply to Longpeng(Mike)The kvm_irqchip_commit_routes() is relatively expensive, so provide the users a choice to commit the route immediately or not when they add msi/msix route.
--- accel/kvm/kvm-all.c | 10 +++++++--- accel/stubs/kvm-stub.c | 3 ++- hw/misc/ivshmem.c | 2 +- hw/vfio/pci.c | 2 +- hw/virtio/virtio-pci.c | 2 +- include/sysemu/kvm.h | 4 +++- target/i386/kvm/kvm.c | 2 +- 7 files changed, 16 insertions(+), 9 deletions(-)
accel/kvm/kvm-all.c +7 -3
@@ -1950,7 +1950,8 @@ int kvm_irqchip_send_msi(KVMState *s, MSIMessage msg)return kvm_set_irq (s, route->kroute.gsi,1 ); } -int kvm_irqchip_add_msi_route (KVMState *s,int vector,PCIDevice *dev) +int kvm_irqchip_add_msi_route (KVMState *s,int vector,PCIDevice *dev, +bool defer_commit) {struct kvm_irq_routing_entry kroute = {};int virq;
@@ -1993,7 +1994,9 @@ int kvm_irqchip_add_msi_route(KVMState *s, int vector, PCIDevice *dev)kvm_add_routing_entry (s, &kroute);kvm_arch_add_msi_route_post (&kroute, vector, dev); -kvm_irqchip_commit_routes (s); +if (!defer_commit) { +kvm_irqchip_commit_routes (s); + }return virq; }
@@ -2151,7 +2154,8 @@ int kvm_irqchip_send_msi(KVMState *s, MSIMessage msg)abort (); } -int kvm_irqchip_add_msi_route (KVMState *s,int vector,PCIDevice *dev) +int kvm_irqchip_add_msi_route (KVMState *s,int vector,PCIDevice *dev, +bool defer_commit) {return -ENOSYS ; }
accel/stubs/kvm-stub.c +2 -1
@@ -81,7 +81,8 @@ int kvm_on_sigbus(int code, void *addr) }#ifndef CONFIG_USER_ONLY -int kvm_irqchip_add_msi_route (KVMState *s,int vector,PCIDevice *dev) +int kvm_irqchip_add_msi_route (KVMState *s,int vector,PCIDevice *dev, +bool defer_commit) {return -ENOSYS ; }
hw/misc/ivshmem.c +1 -1
@@ -429,7 +429,7 @@ static void ivshmem_add_kvm_msi_virq(IVShmemState *s, int vector,IVSHMEM_DPRINTF ("ivshmem_add_kvm_msi_virq vector:%d\n" , vector);assert (!s->msi_vectors[vector].pdev); - ret =kvm_irqchip_add_msi_route (kvm_state, vector, pdev); + ret =kvm_irqchip_add_msi_route (kvm_state, vector, pdev, false);if (ret <0 ) {error_setg (errp,"kvm_irqchip_add_msi_route failed" );return ;
hw/vfio/pci.c +1 -1
@@ -427,7 +427,7 @@ static void vfio_add_kvm_msi_virq(VFIOPCIDevice *vdev, VFIOMSIVector *vector,return ; } - virq =kvm_irqchip_add_msi_route (kvm_state, vector_n, &vdev->pdev); + virq =kvm_irqchip_add_msi_route (kvm_state, vector_n, &vdev->pdev, false);if (virq <0 ) {event_notifier_cleanup (&vector->kvm_interrupt);return ;
hw/virtio/virtio-pci.c +1 -1
@@ -684,7 +684,7 @@ static int kvm_virtio_pci_vq_vector_use(VirtIOPCIProxy *proxy,int ret;if (irqfd->users ==0 ) { - ret =kvm_irqchip_add_msi_route (kvm_state, vector, &proxy->pci_dev); + ret =kvm_irqchip_add_msi_route (kvm_state, vector, &proxy->pci_dev, false);if (ret <0 ) {return ret; }
include/sysemu/kvm.h +3 -1
@@ -473,9 +473,11 @@ void kvm_init_cpu_signals(CPUState *cpu);* message. * @dev: Owner PCI device to add the route. If @dev is specified * as @NULL, an empty MSI message will be inited. +* @defer_commit: Defer to commit new route to the KVM core. * @return: virq (>=0) when success, errno (<0) when failed. */ -int kvm_irqchip_add_msi_route (KVMState *s,int vector,PCIDevice *dev); +int kvm_irqchip_add_msi_route (KVMState *s,int vector,PCIDevice *dev, +bool defer_commit);int kvm_irqchip_update_msi_route (KVMState *s,int virq,MSIMessage msg,PCIDevice *dev);void kvm_irqchip_commit_routes (KVMState *s);
target/i386/kvm/kvm.c +1 -1
@@ -4724,7 +4724,7 @@ void kvm_arch_init_irq_routing(KVMState *s)/* If the ioapic is in QEMU and the lapics are in KVM, reserve MSI routes for signaling interrupts to the local apics. */ for (i =0 ; i <IOAPIC_NUM_PINS ; i++) { -if (kvm_irqchip_add_msi_route (s,0 ,NULL ) <0 ) { +if (kvm_irqchip_add_msi_route (s,0 ,NULL , false) <0 ) {error_report ("Could not enable split IRQ mode." );exit (1 ); }
Signature · 1 line
1.8.3.1
Re: [PATCH 4/5] kvm: irqchip: support defer to commit the route
Quoted 30 lines · On Wed, 25 Aug 2021 15:56:19 +0800 "Longpeng(Mike)" <[email protected]>…
The
kvm_irqchip_commit_routes()is relatively expensive, so provide the users a choice to commit the route immediately or not when they add msi/msix route.Signed-off-by Longpeng(Mike) <[email protected]>--- accel/kvm/kvm-all.c | 10 +++++++--- accel/stubs/kvm-stub.c | 3 ++- hw/misc/ivshmem.c | 2 +- hw/vfio/pci.c | 2 +- hw/virtio/virtio-pci.c | 2 +- include/sysemu/kvm.h | 4 +++- target/i386/kvm/kvm.c | 2 +- 7 files changed, 16 insertions(+), 9 deletions(-)accel/kvm/kvm-all.c +2
-1@@ -1950,7 +1950,8 @@ int kvm_irqchip_send_msi(KVMState *s, MSIMessage msg)return kvm_set_irq (s, route->kroute.gsi,1 ); } -int kvm_irqchip_add_msi_route (KVMState *s,int vector,PCIDevice *dev) +int kvm_irqchip_add_msi_route (KVMState *s,int vector,PCIDevice *dev, +bool defer_commit) {struct kvm_irq_routing_entry kroute = {};int virq;
accel/kvm/kvm-all.c int kvm_irqchip_add_msi_route(KVMState *s, int vector, PCIDevice *dev) · line 1999
Quoted 7 lines
accel/kvm/kvm-all.c +3
-1@@ -1993,7 +1994,9 @@ int kvm_irqchip_add_msi_route(KVMState *s, int vector, PCIDevice *dev)kvm_add_routing_entry (s, &kroute);kvm_arch_add_msi_route_post (&kroute, vector, dev); -kvm_irqchip_commit_routes (s); +if (!defer_commit) { +kvm_irqchip_commit_routes (s); + }
Personally I'd rather rename the function to kvm_irqchip_add_deferred_msi_route() and kvm_irqchip_add_msi_route() becomes a wrapper appending kvm_irqchip_commit_routes() to that. Thanks,
Alex
Quoted 96 lines
accel/kvm/kvm-all.c +2
-1return virq; }@@ -2151,7 +2154,8 @@ int kvm_irqchip_send_msi(KVMState *s, MSIMessage msg)abort (); } -int kvm_irqchip_add_msi_route (KVMState *s,int vector,PCIDevice *dev) +int kvm_irqchip_add_msi_route (KVMState *s,int vector,PCIDevice *dev, +bool defer_commit) {return -ENOSYS ; }accel/stubs/kvm-stub.c +2
-1@@ -81,7 +81,8 @@ int kvm_on_sigbus(int code, void *addr) }#ifndef CONFIG_USER_ONLY -int kvm_irqchip_add_msi_route (KVMState *s,int vector,PCIDevice *dev) +int kvm_irqchip_add_msi_route (KVMState *s,int vector,PCIDevice *dev, +bool defer_commit) {return -ENOSYS ; }hw/misc/ivshmem.c +1
-1@@ -429,7 +429,7 @@ static void ivshmem_add_kvm_msi_virq(IVShmemState *s, int vector,IVSHMEM_DPRINTF ("ivshmem_add_kvm_msi_virq vector:%d\n" , vector);assert (!s->msi_vectors[vector].pdev); - ret =kvm_irqchip_add_msi_route (kvm_state, vector, pdev); + ret =kvm_irqchip_add_msi_route (kvm_state, vector, pdev, false);if (ret <0 ) {error_setg (errp,"kvm_irqchip_add_msi_route failed" );return ;hw/vfio/pci.c +1
-1@@ -427,7 +427,7 @@ static void vfio_add_kvm_msi_virq(VFIOPCIDevice *vdev, VFIOMSIVector *vector,return ; } - virq =kvm_irqchip_add_msi_route (kvm_state, vector_n, &vdev->pdev); + virq =kvm_irqchip_add_msi_route (kvm_state, vector_n, &vdev->pdev, false);if (virq <0 ) {event_notifier_cleanup (&vector->kvm_interrupt);return ;hw/virtio/virtio-pci.c +1
-1@@ -684,7 +684,7 @@ static int kvm_virtio_pci_vq_vector_use(VirtIOPCIProxy *proxy,int ret;if (irqfd->users ==0 ) { - ret =kvm_irqchip_add_msi_route (kvm_state, vector, &proxy->pci_dev); + ret =kvm_irqchip_add_msi_route (kvm_state, vector, &proxy->pci_dev, false);if (ret <0 ) {return ret; }include/sysemu/kvm.h +3
-1@@ -473,9 +473,11 @@ void kvm_init_cpu_signals(CPUState *cpu);* message. * @dev: Owner PCI device to add the route. If @dev is specified * as @NULL, an empty MSI message will be inited. +* @defer_commit: Defer to commit new route to the KVM core. * @return: virq (>=0) when success, errno (<0) when failed. */ -int kvm_irqchip_add_msi_route (KVMState *s,int vector,PCIDevice *dev); +int kvm_irqchip_add_msi_route (KVMState *s,int vector,PCIDevice *dev, +bool defer_commit);int kvm_irqchip_update_msi_route (KVMState *s,int virq,MSIMessage msg,PCIDevice *dev);void kvm_irqchip_commit_routes (KVMState *s);target/i386/kvm/kvm.c +1
-1@@ -4724,7 +4724,7 @@ void kvm_arch_init_irq_routing(KVMState *s)/* If the ioapic is in QEMU and the lapics are in KVM, reserve MSI routes for signaling interrupts to the local apics. */ for (i =0 ; i <IOAPIC_NUM_PINS ; i++) { -if (kvm_irqchip_add_msi_route (s,0 ,NULL ) <0 ) { +if (kvm_irqchip_add_msi_route (s,0 ,NULL , false) <0 ) {error_report ("Could not enable split IRQ mode." );exit (1 ); }
Re: [PATCH 4/5] kvm: irqchip: support defer to commit the route
Quoted 34 lines · Alex Williamson
Quoted 31 lines · On Wed, 25 Aug 2021 15:56:19 +0800 "Longpeng(Mike)" <[email protected]>…
The
kvm_irqchip_commit_routes()is relatively expensive, so provide the users a choice to commit the route immediately or not when they add msi/msix route.Signed-off-by Longpeng(Mike) <[email protected]>--- accel/kvm/kvm-all.c | 10 +++++++--- accel/stubs/kvm-stub.c | 3 ++- hw/misc/ivshmem.c | 2 +- hw/vfio/pci.c | 2 +- hw/virtio/virtio-pci.c | 2 +- include/sysemu/kvm.h | 4 +++- target/i386/kvm/kvm.c | 2 +- 7 files changed, 16 insertions(+), 9 deletions(-)accel/kvm/kvm-all.c +2
-1@@ -1950,7 +1950,8 @@ int kvm_irqchip_send_msi(KVMState *s, MSIMessage msg)return kvm_set_irq (s, route->kroute.gsi,1 ); } -int kvm_irqchip_add_msi_route (KVMState *s,int vector,PCIDevice *dev) +int kvm_irqchip_add_msi_route (KVMState *s,int vector,PCIDevice *dev, +bool defer_commit) {struct kvm_irq_routing_entry kroute = {};int virq;@@ -1993,7 +1994,9 @@ int kvm_irqchip_add_msi_route(KVMState *s, int vector, PCIDevice *dev)
Quoted 13 lines
accel/kvm/kvm-all.c int kvm_irqchip_add_msi_route(KVMState *s, int vector, PCIDevice *dev) · line 1999
Quoted 6 lines
accel/kvm/kvm-all.c +3
-1kvm_add_routing_entry (s, &kroute);kvm_arch_add_msi_route_post (&kroute, vector, dev); -kvm_irqchip_commit_routes (s); +if (!defer_commit) { +kvm_irqchip_commit_routes (s); + }Personally I'd rather rename the function to
kvm_irqchip_add_deferred_msi_route()andkvm_irqchip_add_msi_route()becomes a wrapper appendingkvm_irqchip_commit_routes()to that. Thanks,
Ok, will do in the next version.
Quoted 101 lines
Alex
Quoted 88 lines
accel/kvm/kvm-all.c +2
-1return virq; }@@ -2151,7 +2154,8 @@ int kvm_irqchip_send_msi(KVMState *s, MSIMessage msg)abort (); } -int kvm_irqchip_add_msi_route (KVMState *s,int vector,PCIDevice *dev) +int kvm_irqchip_add_msi_route (KVMState *s,int vector,PCIDevice *dev, +bool defer_commit) {return -ENOSYS ; }accel/stubs/kvm-stub.c +2
-1@@ -81,7 +81,8 @@ int kvm_on_sigbus(int code, void *addr) }#ifndef CONFIG_USER_ONLY -int kvm_irqchip_add_msi_route (KVMState *s,int vector,PCIDevice *dev) +int kvm_irqchip_add_msi_route (KVMState *s,int vector,PCIDevice *dev, +bool defer_commit) {return -ENOSYS ; }hw/misc/ivshmem.c +1
-1@@ -429,7 +429,7 @@ static void ivshmem_add_kvm_msi_virq(IVShmemState *s, int vector,IVSHMEM_DPRINTF ("ivshmem_add_kvm_msi_virq vector:%d\n" , vector);assert (!s->msi_vectors[vector].pdev); - ret =kvm_irqchip_add_msi_route (kvm_state, vector, pdev); + ret =kvm_irqchip_add_msi_route (kvm_state, vector, pdev, false);if (ret <0 ) {error_setg (errp,"kvm_irqchip_add_msi_route failed" );return ;hw/vfio/pci.c +1
-1@@ -427,7 +427,7 @@ static void vfio_add_kvm_msi_virq(VFIOPCIDevice *vdev, VFIOMSIVector *vector,return ; } - virq =kvm_irqchip_add_msi_route (kvm_state, vector_n, &vdev->pdev); + virq =kvm_irqchip_add_msi_route (kvm_state, vector_n, &vdev->pdev, false);if (virq <0 ) {event_notifier_cleanup (&vector->kvm_interrupt);return ;hw/virtio/virtio-pci.c +1
-1@@ -684,7 +684,7 @@ static int kvm_virtio_pci_vq_vector_use(VirtIOPCIProxy *proxy,int ret;if (irqfd->users ==0 ) { - ret =kvm_irqchip_add_msi_route (kvm_state, vector, &proxy->pci_dev); + ret =kvm_irqchip_add_msi_route (kvm_state, vector, &proxy->pci_dev, false);if (ret <0 ) {return ret; }include/sysemu/kvm.h +3
-1@@ -473,9 +473,11 @@ void kvm_init_cpu_signals(CPUState *cpu);* message. * @dev: Owner PCI device to add the route. If @dev is specified * as @NULL, an empty MSI message will be inited. +* @defer_commit: Defer to commit new route to the KVM core. * @return: virq (>=0) when success, errno (<0) when failed. */ -int kvm_irqchip_add_msi_route (KVMState *s,int vector,PCIDevice *dev); +int kvm_irqchip_add_msi_route (KVMState *s,int vector,PCIDevice *dev, +bool defer_commit);int kvm_irqchip_update_msi_route (KVMState *s,int virq,MSIMessage msg,PCIDevice *dev);void kvm_irqchip_commit_routes (KVMState *s);target/i386/kvm/kvm.c +0
-0target/i386/kvm/kvm.c void kvm_arch_init_irq_routing(KVMState *s) · line 4730
Quoted 8 lines
target/i386/kvm/kvm.c +1
-1@@ -4724,7 +4724,7 @@ void kvm_arch_init_irq_routing(KVMState *s)/* If the ioapic is in QEMU and the lapics are in KVM, reserve MSI routes for signaling interrupts to the local apics. */ for (i =0 ; i <IOAPIC_NUM_PINS ; i++) { -if (kvm_irqchip_add_msi_route (s,0 ,NULL ) <0 ) { +if (kvm_irqchip_add_msi_route (s,0 ,NULL , false) <0 ) {error_report ("Could not enable split IRQ mode." );exit (1 ); }.
PATCH 5/5 vfio: defer to commit kvm route in migraiton resume phase
In reply to Longpeng(Mike)In migration resume phase, all unmasked msix vectors need to be setup when load the VF state. However, the setup operation would takes longer if the VF has more unmasked vectors.
In our case, the VF has 65 vectors and each one spend at most 0.8ms on setup operation the total cost of the VF is about 8-58ms. For a VM that has 8 VFs of this type, the total cost is more than 250ms.
vfio_pci_load_config
vfio_msix_enable
msix_set_vector_notifiers
for (vector = 0; vector < dev->msix_entries_nr; vector++) {
vfio_msix_vector_do_use
vfio_add_kvm_msi_virq
kvm_irqchip_commit_routes <-- expensive
}We can reduce the cost by only commit once outside the loop. The routes is cached in kvm_state, we commit them first and then bind irqfd for each vector.
The test VM has 128 vcpus and 8 VF (with 65 vectors enabled), we mesure the cost of the vfio_msix_enable for each one, and we can see 90+% costs can be reduce.
Origin Apply this patch
and vfio enable optimization
1st 8 2 2nd 15 2 3rd 22 2 4th 24 3 5th 36 2 6th 44 3 7th 51 3 8th 58 4 Total 258ms 21ms
The optimition can be also applied to msi type.
--- hw/vfio/pci.c | 47 ++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 44 insertions(+), 3 deletions(-)
hw/vfio/pci.c +44 -3
@@ -427,12 +427,17 @@ static void vfio_add_kvm_msi_virq(VFIOPCIDevice *vdev, VFIOMSIVector *vector,return ; } - virq =kvm_irqchip_add_msi_route (kvm_state, vector_n, &vdev->pdev, false); + virq =kvm_irqchip_add_msi_route (kvm_state, vector_n, &vdev->pdev, + vdev->defer_add_virq);if (virq <0 ) {event_notifier_cleanup (&vector->kvm_interrupt);return ; } +if (vdev->defer_add_virq) { + goto out; + } +if (kvm_irqchip_add_irqfd_notifier_gsi (kvm_state, &vector->kvm_interrupt,NULL , virq) <0 ) {kvm_irqchip_release_virq (kvm_state, virq);
@@ -440,6 +445,7 @@ static void vfio_add_kvm_msi_virq(VFIOPCIDevice *vdev, VFIOMSIVector *vector,return ; } +out: vector->virq = virq; }
@@ -577,6 +583,36 @@ static void vfio_msix_vector_release(PCIDevice *pdev, unsigned int nr) } } +static void vfio_commit_kvm_msi_virq (VFIOPCIDevice *vdev) +{ +int i; +VFIOMSIVector *vector; +bool commited = false; + +for (i =0 ; i < vdev->nr_vectors; i++) { + vector = &vdev->msi_vectors[i]; + +if (vector->virq <0 ) { +continue ; + } + +/* Commit cached route entries to KVM core first if not yet */ +if (!commited) { +kvm_irqchip_commit_routes (kvm_state); + commited = true; + } + +if (kvm_irqchip_add_irqfd_notifier_gsi (kvm_state, + &vector->kvm_interrupt, +NULL , vector->virq) <0 ) { +kvm_irqchip_release_virq (kvm_state, vector->virq); +event_notifier_cleanup (&vector->kvm_interrupt); + vector->virq =-1 ; +return ; + } + } +} +static void vfio_msix_enable (VFIOPCIDevice *vdev) {PCIDevice *pdev = &vdev->pdev;
@@ -624,6 +660,7 @@ static void vfio_msix_enable(VFIOPCIDevice *vdev)if (!pdev->msix_function_masked && vdev->defer_add_virq) {int ret;vfio_disable_irqindex (&vdev->vbasedev,VFIO_PCI_MSIX_IRQ_INDEX ); +vfio_commit_kvm_msi_virq (vdev); ret =vfio_enable_vectors (vdev, true);if (ret) {error_report ("vfio: failed to enable vectors, %d" , ret);
@@ -664,6 +701,10 @@ retry:vfio_add_kvm_msi_virq (vdev, vector, i, false); } +if (vdev->defer_add_virq){ +vfio_commit_kvm_msi_virq (vdev); + } +/* Set interrupt type prior to possible interrupts */ vdev->interrupt =VFIO_INT_MSI ;
@@ -2473,13 +2514,13 @@ static int vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f)vfio_pci_write_config (pdev,PCI_COMMAND ,pci_get_word (pdev->config +PCI_COMMAND ),2 ); + vdev->defer_add_virq = true;if (msi_enabled (pdev)) {vfio_msi_enable (vdev); }else if (msix_enabled (pdev)) { - vdev->defer_add_virq = true;vfio_msix_enable (vdev); - vdev->defer_add_virq = false; } + vdev->defer_add_virq = false;return ret; }
Signature · 1 line
1.8.3.1
Re: [PATCH 5/5] vfio: defer to commit kvm route in migraiton resume phase
Quoted 27 lines · On Wed, 25 Aug 2021 15:56:20 +0800 "Longpeng(Mike)" <[email protected]>…
In migration resume phase, all unmasked msix vectors need to be setup when load the VF state. However, the setup operation would takes longer if the VF has more unmasked vectors.
In our case, the VF has 65 vectors and each one spend at most 0.8ms on setup operation the total cost of the VF is about 8-58ms. For a VM that has 8 VFs of this type, the total cost is more than 250ms.
vfio_pci_load_config
vfio_msix_enablemsix_set_vector_notifiers for (vector = 0; vector < dev->msix_entries_nr; vector++) { vfio_msix_vector_do_use vfio_add_kvm_msi_virq kvm_irqchip_commit_routes <-- expensive }We can reduce the cost by only commit once outside the loop. The routes is cached in
kvm_state, we commit them first and then bind irqfd for each vector.The test VM has 128 vcpus and 8 VF (with 65 vectors enabled), we mesure the cost of the
vfio_msix_enablefor each one, and we can see 90+% costs can be reduce.Origin Apply this patch
and vfio enable optimization
Quoted 9 lines
1st 8 2 2nd 15 2 3rd 22 2 4th 24 3 5th 36 2 6th 44 3 7th 51 3 8th 58 4 Total 258ms 21ms
Almost seems like we should have started here rather than much more subtle improvements from patch 3.
Quoted 12 lines
The optimition can be also applied to msi type.
Signed-off-by Longpeng(Mike) <[email protected]>--- hw/vfio/pci.c | 47 ++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 44 insertions(+), 3 deletions(-)hw/vfio/pci.c +0
-0
hw/vfio/pci.c static void vfio_add_kvm_msi_virq(VFIOPCIDevice *vdev, VFIOMSIVector *vector, · line 431
Quoted 6 lines
hw/vfio/pci.c +2
-1@@ -427,12 +427,17 @@ static void vfio_add_kvm_msi_virq(VFIOPCIDevice *vdev, VFIOMSIVector *vector,return ; } - virq =kvm_irqchip_add_msi_route (kvm_state, vector_n, &vdev->pdev, false); + virq =kvm_irqchip_add_msi_route (kvm_state, vector_n, &vdev->pdev, + vdev->defer_add_virq);
See comment on previous patch about these bool function args.
hw/vfio/pci.c static void vfio_add_kvm_msi_virq(VFIOPCIDevice *vdev, VFIOMSIVector *vector, · line 439
Quoted 8 lines
hw/vfio/pci.c +3
-0if (virq <0 ) {event_notifier_cleanup (&vector->kvm_interrupt);return ; } +if (vdev->defer_add_virq) { + goto out; + }
See comment on previous patch about this goto flow.
Quoted 24 lines
hw/vfio/pci.c +10
-0+if (kvm_irqchip_add_irqfd_notifier_gsi (kvm_state, &vector->kvm_interrupt,NULL , virq) <0 ) {kvm_irqchip_release_virq (kvm_state, virq);@@ -440,6 +445,7 @@ static void vfio_add_kvm_msi_virq(VFIOPCIDevice *vdev, VFIOMSIVector *vector,return ; } +out: vector->virq = virq; }@@ -577,6 +583,36 @@ static void vfio_msix_vector_release(PCIDevice *pdev, unsigned int nr) } } +static void vfio_commit_kvm_msi_virq (VFIOPCIDevice *vdev) +{ +int i; +VFIOMSIVector *vector; +bool commited = false; + +for (i =0 ; i < vdev->nr_vectors; i++) { + vector = &vdev->msi_vectors[i];
hw/vfio/pci.c static void vfio_msix_vector_release(PCIDevice *pdev, unsigned int nr) · line 603
Quoted 10 lines
hw/vfio/pci.c +10
-0+ +if (vector->virq <0 ) { +continue ; + } + +/* Commit cached route entries to KVM core first if not yet */ +if (!commited) { +kvm_irqchip_commit_routes (kvm_state); + commited = true; + }
Why is this in the loop, shouldn't we just start with:
if (!vdev->nr_vectors) {
return;
}
kvm_irqchip_commit_routes(kvm_state);
for (...hw/vfio/pci.c static void vfio_msix_vector_release(PCIDevice *pdev, unsigned int nr) · line 612
Quoted 9 lines
hw/vfio/pci.c +9
-0+ +if (kvm_irqchip_add_irqfd_notifier_gsi (kvm_state, + &vector->kvm_interrupt, +NULL , vector->virq) <0 ) { +kvm_irqchip_release_virq (kvm_state, vector->virq); +event_notifier_cleanup (&vector->kvm_interrupt); + vector->virq =-1 ; +return ; + }
And all the other vectors we've allocated? Error logging?
Quoted 15 lines
hw/vfio/pci.c +4
-0+ } +} +static void vfio_msix_enable (VFIOPCIDevice *vdev) {PCIDevice *pdev = &vdev->pdev;@@ -624,6 +660,7 @@ static void vfio_msix_enable(VFIOPCIDevice *vdev)if (!pdev->msix_function_masked && vdev->defer_add_virq) {int ret;vfio_disable_irqindex (&vdev->vbasedev,VFIO_PCI_MSIX_IRQ_INDEX ); +vfio_commit_kvm_msi_virq (vdev); ret =vfio_enable_vectors (vdev, true);if (ret) {error_report ("vfio: failed to enable vectors, %d" , ret);
hw/vfio/pci.c retry: · line 706
Quoted 6 lines
hw/vfio/pci.c +3
-0@@ -664,6 +701,10 @@ retry:vfio_add_kvm_msi_virq (vdev, vector, i, false); } +if (vdev->defer_add_virq){ +vfio_commit_kvm_msi_virq (vdev); + }
Again, why is the load_config path unique, shouldn't we always batch on setup?
Quoted 20 lines
hw/vfio/pci.c +3
-2+/* Set interrupt type prior to possible interrupts */ vdev->interrupt =VFIO_INT_MSI ;@@ -2473,13 +2514,13 @@ static int vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f)vfio_pci_write_config (pdev,PCI_COMMAND ,pci_get_word (pdev->config +PCI_COMMAND ),2 ); + vdev->defer_add_virq = true;if (msi_enabled (pdev)) {vfio_msi_enable (vdev); }else if (msix_enabled (pdev)) { - vdev->defer_add_virq = true;vfio_msix_enable (vdev); - vdev->defer_add_virq = false; } + vdev->defer_add_virq = false;return ret; }
Re: [PATCH 5/5] vfio: defer to commit kvm route in migraiton resume phase
Quoted 104 lines · Alex Williamson
Quoted 27 lines · On Wed, 25 Aug 2021 15:56:20 +0800 "Longpeng(Mike)" <[email protected]>…
In migration resume phase, all unmasked msix vectors need to be setup when load the VF state. However, the setup operation would takes longer if the VF has more unmasked vectors.
In our case, the VF has 65 vectors and each one spend at most 0.8ms on setup operation the total cost of the VF is about 8-58ms. For a VM that has 8 VFs of this type, the total cost is more than 250ms.
vfio_pci_load_config
vfio_msix_enablemsix_set_vector_notifiers for (vector = 0; vector < dev->msix_entries_nr; vector++) { vfio_msix_vector_do_use vfio_add_kvm_msi_virq kvm_irqchip_commit_routes <-- expensive }We can reduce the cost by only commit once outside the loop. The routes is cached in
kvm_state, we commit them first and then bind irqfd for each vector.The test VM has 128 vcpus and 8 VF (with 65 vectors enabled), we mesure the cost of the
vfio_msix_enablefor each one, and we can see 90+% costs can be reduce.Origin Apply this patch
and vfio enable optimizationQuoted 9 lines
1st 8 2 2nd 15 2 3rd 22 2 4th 24 3 5th 36 2 6th 44 3 7th 51 3 8th 58 4 Total 258ms 21msAlmost seems like we should have started here rather than much more subtle improvements from patch 3.
Quoted 12 lines
The optimition can be also applied to msi type.
Signed-off-by Longpeng(Mike) <[email protected]>--- hw/vfio/pci.c | 47 ++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 44 insertions(+), 3 deletions(-)hw/vfio/pci.c +0
-0hw/vfio/pci.c static void vfio_add_kvm_msi_virq(VFIOPCIDevice *vdev, VFIOMSIVector *vector, · line 431
Quoted 6 lines
hw/vfio/pci.c +2
-1@@ -427,12 +427,17 @@ static void vfio_add_kvm_msi_virq(VFIOPCIDevice *vdev, VFIOMSIVector *vector,return ; } - virq =kvm_irqchip_add_msi_route (kvm_state, vector_n, &vdev->pdev, false); + virq =kvm_irqchip_add_msi_route (kvm_state, vector_n, &vdev->pdev, + vdev->defer_add_virq);See comment on previous patch about these bool function args.
hw/vfio/pci.c static void vfio_add_kvm_msi_virq(VFIOPCIDevice *vdev, VFIOMSIVector *vector, · line 439
Quoted 8 lines
hw/vfio/pci.c +3
-0if (virq <0 ) {event_notifier_cleanup (&vector->kvm_interrupt);return ; } +if (vdev->defer_add_virq) { + goto out; + }See comment on previous patch about this goto flow.
Quoted 28 lines
hw/vfio/pci.c +14
-0+if (kvm_irqchip_add_irqfd_notifier_gsi (kvm_state, &vector->kvm_interrupt,NULL , virq) <0 ) {kvm_irqchip_release_virq (kvm_state, virq);@@ -440,6 +445,7 @@ static void vfio_add_kvm_msi_virq(VFIOPCIDevice *vdev, VFIOMSIVector *vector,return ; } +out: vector->virq = virq; }@@ -577,6 +583,36 @@ static void vfio_msix_vector_release(PCIDevice *pdev, unsigned int nr) } } +static void vfio_commit_kvm_msi_virq (VFIOPCIDevice *vdev) +{ +int i; +VFIOMSIVector *vector; +bool commited = false; + +for (i =0 ; i < vdev->nr_vectors; i++) { + vector = &vdev->msi_vectors[i]; + +if (vector->virq <0 ) { +continue ; + }
Quoted 9 lines
hw/vfio/pci.c static void vfio_msix_vector_release(PCIDevice *pdev, unsigned int nr) · line 603
Quoted 6 lines
hw/vfio/pci.c +6
-0+ +/* Commit cached route entries to KVM core first if not yet */ +if (!commited) { +kvm_irqchip_commit_routes (kvm_state); + commited = true; + }Why is this in the loop, shouldn't we just start with:
The kvm_irqchip_commit_routes won't be called if all of the vector->virq are -1 originally, so I just want to preserve the behavior here.
But it seems no any side effect if we call it directly, I'll take your advice in the next version, thanks.
Quoted 18 lines
if (!vdev->nr_vectors) { return; } kvm_irqchip_commit_routes(kvm_state); for (...hw/vfio/pci.c static void vfio_msix_vector_release(PCIDevice *pdev, unsigned int nr) · line 612
Quoted 9 lines
hw/vfio/pci.c +9
-0+ +if (kvm_irqchip_add_irqfd_notifier_gsi (kvm_state, + &vector->kvm_interrupt, +NULL , vector->virq) <0 ) { +kvm_irqchip_release_virq (kvm_state, vector->virq); +event_notifier_cleanup (&vector->kvm_interrupt); + vector->virq =-1 ; +return ; + }
Quoted 2 lines
And all the other vectors we've allocated? Error logging?
Oh, it's a bug, will fix.
Quoted 48 lines
Quoted 15 lines
hw/vfio/pci.c +4
-0+ } +} +static void vfio_msix_enable (VFIOPCIDevice *vdev) {PCIDevice *pdev = &vdev->pdev;@@ -624,6 +660,7 @@ static void vfio_msix_enable(VFIOPCIDevice *vdev)if (!pdev->msix_function_masked && vdev->defer_add_virq) {int ret;vfio_disable_irqindex (&vdev->vbasedev,VFIO_PCI_MSIX_IRQ_INDEX ); +vfio_commit_kvm_msi_virq (vdev); ret =vfio_enable_vectors (vdev, true);if (ret) {error_report ("vfio: failed to enable vectors, %d" , ret);hw/vfio/pci.c retry: · line 706
Quoted 6 lines
hw/vfio/pci.c +3
-0@@ -664,6 +701,10 @@ retry:vfio_add_kvm_msi_virq (vdev, vector, i, false); } +if (vdev->defer_add_virq){ +vfio_commit_kvm_msi_virq (vdev); + }Again, why is the
load_configpath unique, shouldn't we always batch on setup?Quoted 10 lines
hw/vfio/pci.c +2
-0+/* Set interrupt type prior to possible interrupts */ vdev->interrupt =VFIO_INT_MSI ;@@ -2473,13 +2514,13 @@ static int vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f)vfio_pci_write_config (pdev,PCI_COMMAND ,pci_get_word (pdev->config +PCI_COMMAND ),2 ); + vdev->defer_add_virq = true;if (msi_enabled (pdev)) {hw/vfio/pci.c static int vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f) · line 2526
Quoted 10 lines
hw/vfio/pci.c +1
-2vfio_msi_enable (vdev); }else if (msix_enabled (pdev)) { - vdev->defer_add_virq = true;vfio_msix_enable (vdev); - vdev->defer_add_virq = false; } + vdev->defer_add_virq = false;return ret; }.
Cc'ing David/Juan for migration big picture (just in case).
Quoted 24 lines · Longpeng(Mike)
In vfio migration resume phase, the cost would increase if the vfio device has more unmasked vectors. We try to optimize it in this series.
Patch 1 & 2 are simple code cleanups. Patch 3 defers to set irqs to vfio core. Patch 4 & 5 defer to commit the route to KVM core.
The test VM has 128 vcpus and 8 VF (with 65 vectors enabled), we mesure the cost of the
vfio_msix_enablefor each one, and we can see the total cost can be significantly reduced.Origin Apply Patch 3 Apply Patch 3/4/5 1st 8 4 2 2nd 15 11 2 3rd 22 18 2 4th 24 25 3 5th 36 33 2 6th 44 40 3 7th 51 47 3 8th 58 54 4 Total 258ms 232ms 21ms
Quoted 6 lines
Longpeng (Mike) (5):
vfio: use helper to simplfy the failure path invfio_msi_enable
msix: simplfy the conditional in msix_set/unset_vector_notifiers
vfio: defer to enable msix in migration resume phase
kvm: irqchip: support defer to commit the route
vfio: defer to commit kvm route in migraiton resume phase
Overall makes sense and LGTM but migration/KVM are not my area :/
Quoted 27 lines · Philippe Mathieu-Daudé
Cc'ing David/Juan for migration big picture (just in case).
Quoted 24 lines · Longpeng(Mike)
In vfio migration resume phase, the cost would increase if the vfio device has more unmasked vectors. We try to optimize it in this series.
Patch 1 & 2 are simple code cleanups. Patch 3 defers to set irqs to vfio core. Patch 4 & 5 defer to commit the route to KVM core.
The test VM has 128 vcpus and 8 VF (with 65 vectors enabled), we mesure the cost of the
vfio_msix_enablefor each one, and we can see the total cost can be significantly reduced.Origin Apply Patch 3 Apply Patch 3/4/5 1st 8 4 2 2nd 15 11 2 3rd 22 18 2 4th 24 25 3 5th 36 33 2 6th 44 40 3 7th 51 47 3 8th 58 54 4 Total 258ms 232ms 21ms
Quoted 9 lines
Quoted 6 lines
Longpeng (Mike) (5):
vfio: use helper to simplfy the failure path invfio_msi_enable
msix: simplfy the conditional in msix_set/unset_vector_notifiers
vfio: defer to enable msix in migration resume phase
kvm: irqchip: support defer to commit the route
vfio: defer to commit kvm route in migraiton resume phaseOverall makes sense and LGTM but migration/KVM are not my area :/
Thanks all the same :)
Quoted 2 lines
.
Hi maintainers,
Ping...
Quoted 42 lines · Longpeng(Mike)
In vfio migration resume phase, the cost would increase if the vfio device has more unmasked vectors. We try to optimize it in this series.
Patch 1 & 2 are simple code cleanups. Patch 3 defers to set irqs to vfio core. Patch 4 & 5 defer to commit the route to KVM core.
The test VM has 128 vcpus and 8 VF (with 65 vectors enabled), we mesure the cost of the
vfio_msix_enablefor each one, and we can see the total cost can be significantly reduced.Origin Apply Patch 3 Apply Patch 3/4/5 1st 8 4 2 2nd 15 11 2 3rd 22 18 2 4th 24 25 3 5th 36 33 2 6th 44 40 3 7th 51 47 3 8th 58 54 4 Total 258ms 232ms 21msLongpeng (Mike) (5):
vfio: use helper to simplfy the failure path invfio_msi_enable
msix: simplfy the conditional in msix_set/unset_vector_notifiers
vfio: defer to enable msix in migration resume phase
kvm: irqchip: support defer to commit the route
vfio: defer to commit kvm route in migraiton resume phaseaccel/kvm/kvm-all.c | 10 +++-- accel/stubs/kvm-stub.c | 3 +- hw/misc/ivshmem.c | 2 +- hw/pci/msix.c | 7 ++-- hw/vfio/pci.c | 99 ++++++++++++++++++++++++++++++++++++++------------ hw/vfio/pci.h | 1 + hw/virtio/virtio-pci.c | 2 +- include/sysemu/kvm.h | 4 +- target/i386/kvm/kvm.c | 2 +- 9 files changed, 95 insertions(+), 35 deletions(-)