[PATCH v5] vp_vdpa: don't allocate unused msix vectors
From: Yuxue Liu
When there is a ctlq and it doesn't require interrupt
callbacks,the original method of calculating vectors
wastes hardware msi or msix resources as well as system
IRQ resources.
When conducting performance testing using testpmd in the
guest os, it was found that the performance was lower compared
to directly using vfio-pci to passthrough the device
In scenarios where the virtio device in the guest os does
not utilize interrupts, the vdpa driver still configures
the hardware's msix vector. Therefore, the hardware still
sends interrupts to the host os. Because of this unnecessary
action by the hardware, hardware performance decreases, and
it also affects the performance of the host os.
Before modification:(interrupt mode)
32: 0 0 0 0 PCI-MSI 32768-edgevp-vdpa[:00:02.0]-0
33: 0 0 0 0 PCI-MSI 32769-edgevp-vdpa[:00:02.0]-1
34: 0 0 0 0 PCI-MSI 32770-edgevp-vdpa[:00:02.0]-2
35: 0 0 0 0 PCI-MSI 32771-edgevp-vdpa[:00:02.0]-config
After modification:(interrupt mode)
32: 0 0 1 7 PCI-MSI 32768-edge vp-vdpa[:00:02.0]-0
33: 36 0 3 0 PCI-MSI 32769-edge vp-vdpa[:00:02.0]-1
34: 0 0 0 0 PCI-MSI 32770-edge vp-vdpa[:00:02.0]-config
Before modification:(virtio pmd mode for guest os)
32: 0 0 0 0 PCI-MSI 32768-edgevp-vdpa[:00:02.0]-0
33: 0 0 0 0 PCI-MSI 32769-edgevp-vdpa[:00:02.0]-1
34: 0 0 0 0 PCI-MSI 32770-edgevp-vdpa[:00:02.0]-2
35: 0 0 0 0 PCI-MSI 32771-edgevp-vdpa[:00:02.0]-config
After modification:(virtio pmd mode for guest os)
32: 0 0 0 0 PCI-MSI 32768-edge vp-vdpa[:00:02.0]-config
To verify the use of the virtio PMD mode in the guest operating
system, the following patch needs to be applied to QEMU:
https://lore.kernel.org/all/20240408073311.2049-1-yuxue@jaguarmicro.com
Signed-off-by: Yuxue Liu
Acked-by: Jason Wang
Reviewed-by: Heng Qi
---
V5: modify the description of the printout when an exception occurs
V4: update the title and assign values to uninitialized variables
V3: delete unused variables and add validation records
V2: fix when allocating IRQs, scan all queues
drivers/vdpa/virtio_pci/vp_vdpa.c | 22 --
1 file changed, 16 insertions(+), 6 deletions(-)
diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c
b/drivers/vdpa/virtio_pci/vp_vdpa.c
index df5f4a3bccb5..8de0224e9ec2 100644
--- a/drivers/vdpa/virtio_pci/vp_vdpa.c
+++ b/drivers/vdpa/virtio_pci/vp_vdpa.c
@@ -160,7 +160,13 @@ static int vp_vdpa_request_irq(struct vp_vdpa *vp_vdpa)
struct pci_dev *pdev = mdev->pci_dev;
int i, ret, irq;
int queues = vp_vdpa->queues;
- int vectors = queues + 1;
+ int vectors = 1;
+ int msix_vec = 0;
+
+ for (i = 0; i < queues; i++) {
+ if (vp_vdpa->vring[i].cb.callback)
+ vectors++;
+ }
ret = pci_alloc_irq_vectors(pdev, vectors, vectors, PCI_IRQ_MSIX);
if (ret != vectors) {
@@ -173,9 +179,12 @@ static int vp_vdpa_request_irq(struct vp_vdpa *vp_vdpa)
vp_vdpa->vectors = vectors;
for (i = 0; i < queues; i++) {
+ if (!vp_vdpa->vring[i].cb.callback)
+ continue;
+
snprintf(vp_vdpa->vring[i].msix_name, VP_VDPA_NAME_SIZE,
"vp-vdpa[%s]-%d\n", pci_name(pdev), i);
- irq = pci_irq_vector(pdev, i);
+ irq = pci_irq_vector(pdev, msix_vec);
ret = devm_request_irq(>dev, irq,
vp_vdpa_vq_handler,
0, vp_vdpa->vring[i].msix_name,
@@ -185,21 +194,22 @@ static int vp_vdpa_request_irq(struct vp_vdpa *vp_vdpa)
"vp_vdpa: fail to request irq for vq %d\n", i);
goto err;
}
- vp_modern_queue_vector(mdev, i, i);
+ vp_modern_queue_vector(mdev, i, msix_vec);
vp_vdpa->vring[i].irq = irq;
+ msix_vec++;
}
snprintf(vp_vdpa->msix_name, VP_VDPA_NAME_SIZE, "vp-vdpa[%s]-config\n",
pci_name(pdev));
- irq = pci_irq_vector(pdev, queues);
+ irq = pci_irq_vector(pdev, msix_vec);
ret = devm_request_irq(>dev, irq, vp_vdpa_config_handler, 0,
vp_vdpa->msix_name, vp_vdpa);
if (ret) {
dev_err(>dev,
- "vp_vdpa: fail to request irq for vq %d\n", i);
+ "vp_vdpa: fail to request irq for config: %d\n", ret);
goto err;
}
- vp_modern_config_vector(mdev, queues);
+ vp_modern_config_vector(mdev, msix_vec);
vp_vdpa->config_irq = irq;
return 0;
--
2.43.0
[PATCH v4] vp_vdpa: don't allocate unused msix vectors
From: Yuxue Liu
When there is a ctlq and it doesn't require interrupt
callbacks,the original method of calculating vectors
wastes hardware msi or msix resources as well as system
IRQ resources.
When conducting performance testing using testpmd in the
guest os, it was found that the performance was lower compared
to directly using vfio-pci to passthrough the device
In scenarios where the virtio device in the guest os does
not utilize interrupts, the vdpa driver still configures
the hardware's msix vector. Therefore, the hardware still
sends interrupts to the host os. Because of this unnecessary
action by the hardware, hardware performance decreases, and
it also affects the performance of the host os.
Before modification:(interrupt mode)
32: 0 0 0 0 PCI-MSI 32768-edgevp-vdpa[:00:02.0]-0
33: 0 0 0 0 PCI-MSI 32769-edgevp-vdpa[:00:02.0]-1
34: 0 0 0 0 PCI-MSI 32770-edgevp-vdpa[:00:02.0]-2
35: 0 0 0 0 PCI-MSI 32771-edgevp-vdpa[:00:02.0]-config
After modification:(interrupt mode)
32: 0 0 1 7 PCI-MSI 32768-edge vp-vdpa[:00:02.0]-0
33: 36 0 3 0 PCI-MSI 32769-edge vp-vdpa[:00:02.0]-1
34: 0 0 0 0 PCI-MSI 32770-edge vp-vdpa[:00:02.0]-config
Before modification:(virtio pmd mode for guest os)
32: 0 0 0 0 PCI-MSI 32768-edgevp-vdpa[:00:02.0]-0
33: 0 0 0 0 PCI-MSI 32769-edgevp-vdpa[:00:02.0]-1
34: 0 0 0 0 PCI-MSI 32770-edgevp-vdpa[:00:02.0]-2
35: 0 0 0 0 PCI-MSI 32771-edgevp-vdpa[:00:02.0]-config
After modification:(virtio pmd mode for guest os)
32: 0 0 0 0 PCI-MSI 32768-edge vp-vdpa[:00:02.0]-config
To verify the use of the virtio PMD mode in the guest operating
system, the following patch needs to be applied to QEMU:
https://lore.kernel.org/all/20240408073311.2049-1-yuxue@jaguarmicro.com
Signed-off-by: Yuxue Liu
Acked-by: Jason Wang
---
V4: Update the title and assign values to uninitialized variables
V3: delete unused variables and add validation records
V2: fix when allocating IRQs, scan all queues
drivers/vdpa/virtio_pci/vp_vdpa.c | 23 +--
1 file changed, 17 insertions(+), 6 deletions(-)
diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c
b/drivers/vdpa/virtio_pci/vp_vdpa.c
index df5f4a3bccb5..74bc8adfc7e8 100644
--- a/drivers/vdpa/virtio_pci/vp_vdpa.c
+++ b/drivers/vdpa/virtio_pci/vp_vdpa.c
@@ -160,7 +160,14 @@ static int vp_vdpa_request_irq(struct vp_vdpa *vp_vdpa)
struct pci_dev *pdev = mdev->pci_dev;
int i, ret, irq;
int queues = vp_vdpa->queues;
- int vectors = queues + 1;
+ int vectors = 0;
+ int msix_vec = 0;
+
+ for (i = 0; i < queues; i++) {
+ if (vp_vdpa->vring[i].cb.callback)
+ vectors++;
+ }
+ vectors++;
ret = pci_alloc_irq_vectors(pdev, vectors, vectors, PCI_IRQ_MSIX);
if (ret != vectors) {
@@ -173,9 +180,12 @@ static int vp_vdpa_request_irq(struct vp_vdpa *vp_vdpa)
vp_vdpa->vectors = vectors;
for (i = 0; i < queues; i++) {
+ if (!vp_vdpa->vring[i].cb.callback)
+ continue;
+
snprintf(vp_vdpa->vring[i].msix_name, VP_VDPA_NAME_SIZE,
"vp-vdpa[%s]-%d\n", pci_name(pdev), i);
- irq = pci_irq_vector(pdev, i);
+ irq = pci_irq_vector(pdev, msix_vec);
ret = devm_request_irq(>dev, irq,
vp_vdpa_vq_handler,
0, vp_vdpa->vring[i].msix_name,
@@ -185,21 +195,22 @@ static int vp_vdpa_request_irq(struct vp_vdpa *vp_vdpa)
"vp_vdpa: fail to request irq for vq %d\n", i);
goto err;
}
- vp_modern_queue_vector(mdev, i, i);
+ vp_modern_queue_vector(mdev, i, msix_vec);
vp_vdpa->vring[i].irq = irq;
+ msix_vec++;
}
snprintf(vp_vdpa->msix_name, VP_VDPA_NAME_SIZE, "vp-vdpa[%s]-config\n",
pci_name(pdev));
- irq = pci_irq_vector(pdev, queues);
+ irq = pci_irq_vector(pdev, msix_vec);
ret = devm_request_irq(>dev, irq, vp_vdpa_config_handler, 0,
vp_vdpa->msix_name, vp_vdpa);
if (ret) {
dev_err(>dev,
- "vp_vdpa: fail to request irq for vq %d\n", i);
+ "vp_vdpa: fail to request irq for config, ret %d\n",
ret);
goto err;
}
- vp_modern_config_vector(mdev, queues);
+ vp_modern_config_vector(mdev, msix_vec);
vp_vdpa->config_irq = irq;
return 0;
--
2.43.0
[PATCH v3] vp_vdpa: fix the method of calculating vectors
When there is a ctlq and it doesn't require interrupt
callbacks,the original method of calculating vectors
wastes hardware msi or msix resources as well as system
IRQ resources.
When conducting performance testing using testpmd in the
guest os, it was found that the performance was lower compared
to directly using vfio-pci to passthrough the device
In scenarios where the virtio device in the guest os does
not utilize interrupts, the vdpa driver still configures
the hardware's msix vector. Therefore, the hardware still
sends interrupts to the host os. Because of this unnecessary
action by the hardware, hardware performance decreases, and
it also affects the performance of the host os.
Before modification:(interrupt mode)
32: 0 0 0 0 PCI-MSI 32768-edgevp-vdpa[:00:02.0]-0
33: 0 0 0 0 PCI-MSI 32769-edgevp-vdpa[:00:02.0]-1
34: 0 0 0 0 PCI-MSI 32770-edgevp-vdpa[:00:02.0]-2
35: 0 0 0 0 PCI-MSI 32771-edgevp-vdpa[:00:02.0]-config
After modification:(interrupt mode)
32: 0 0 1 7 PCI-MSI 32768-edge vp-vdpa[:00:02.0]-0
33: 36 0 3 0 PCI-MSI 32769-edge vp-vdpa[:00:02.0]-1
34: 0 0 0 0 PCI-MSI 32770-edge vp-vdpa[:00:02.0]-config
Before modification:(virtio pmd mode for guest os)
32: 0 0 0 0 PCI-MSI 32768-edgevp-vdpa[:00:02.0]-0
33: 0 0 0 0 PCI-MSI 32769-edgevp-vdpa[:00:02.0]-1
34: 0 0 0 0 PCI-MSI 32770-edgevp-vdpa[:00:02.0]-2
35: 0 0 0 0 PCI-MSI 32771-edgevp-vdpa[:00:02.0]-config
After modification:(virtio pmd mode for guest os)
32: 0 0 0 0 PCI-MSI 32768-edge vp-vdpa[:00:02.0]-config
To verify the use of the virtio PMD mode in the guest operating
system, the following patch needs to be applied to QEMU:
https://lore.kernel.org/all/20240408073311.2049-1-yuxue@jaguarmicro.com
Signed-off-by: lyx634449800
---
V3: delete unused variables and add validation records
V2: fix when allocating IRQs, scan all queues
drivers/vdpa/virtio_pci/vp_vdpa.c | 35 +++
1 file changed, 22 insertions(+), 13 deletions(-)
diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c
b/drivers/vdpa/virtio_pci/vp_vdpa.c
index df5f4a3bccb5..cd3aeb3b8f21 100644
--- a/drivers/vdpa/virtio_pci/vp_vdpa.c
+++ b/drivers/vdpa/virtio_pci/vp_vdpa.c
@@ -160,22 +160,31 @@ static int vp_vdpa_request_irq(struct vp_vdpa *vp_vdpa)
struct pci_dev *pdev = mdev->pci_dev;
int i, ret, irq;
int queues = vp_vdpa->queues;
- int vectors = queues + 1;
+ int msix_vec, allocated_vectors = 0;
- ret = pci_alloc_irq_vectors(pdev, vectors, vectors, PCI_IRQ_MSIX);
- if (ret != vectors) {
+ for (i = 0; i < queues; i++) {
+ if (vp_vdpa->vring[i].cb.callback)
+ allocated_vectors++;
+ }
+ allocated_vectors = allocated_vectors + 1;
+
+ ret = pci_alloc_irq_vectors(pdev, allocated_vectors, allocated_vectors,
+ PCI_IRQ_MSIX);
+ if (ret != allocated_vectors) {
dev_err(>dev,
"vp_vdpa: fail to allocate irq vectors want %d but
%d\n",
- vectors, ret);
+ allocated_vectors, ret);
return ret;
}
-
- vp_vdpa->vectors = vectors;
+ vp_vdpa->vectors = allocated_vectors;
for (i = 0; i < queues; i++) {
+ if (!vp_vdpa->vring[i].cb.callback)
+ continue;
+
snprintf(vp_vdpa->vring[i].msix_name, VP_VDPA_NAME_SIZE,
"vp-vdpa[%s]-%d\n", pci_name(pdev), i);
- irq = pci_irq_vector(pdev, i);
+ irq = pci_irq_vector(pdev, msix_vec);
ret = devm_request_irq(>dev, irq,
vp_vdpa_vq_handler,
0, vp_vdpa->vring[i].msix_name,
@@ -185,23 +194,23 @@ static int vp_vdpa_request_irq(struct vp_vdpa *vp_vdpa)
"vp_vdpa: fail to request irq for vq %d\n", i);
goto err;
}
- vp_modern_queue_vector(mdev, i, i);
+ vp_modern_queue_vector(mdev, i, msix_vec);
vp_vdpa->vring[i].irq = irq;
+ msix_vec++;
}
snprintf(vp_vdpa->msix_name, VP_VDPA_NAME_SIZE, "vp-vdpa[%s]-config\n",
-pci_name(pdev));
- irq = pci_irq_vector(pdev, queues);
+ pci_name(pdev));
+ irq = pci_irq_vector(pdev, msix_vec);
ret = devm_request_irq(>dev, irq, vp_vdpa_config_handler, 0,
vp_vdpa->msix_name, vp_vdpa);
if (ret) {
dev_err(>dev,
- "vp_vdpa: fail to request irq for vq %d\n", i);
+
