diff mbox

[09/10] vfio-pci: create an iommu mapping for msi address

Message ID 1453813968-2024-10-git-send-email-eric.auger@linaro.org (mailing list archive)
State New, archived
Headers show

Commit Message

Eric Auger Jan. 26, 2016, 1:12 p.m. UTC 
Some platforms require the MSI address programmed in the PCI
device to be an IOVA and not a host physical address.
This is typically the case for ARM and PowerPC, as opposed
to x86. This patch allocates an IOVA page and maps it onto
the physical page which contains the target MSI write transaction
address. In case an IOMMU binding already exists between those 2,
simply reprogram the device.

The binding is destroyed by the VFIO IOMMU backend.

Signed-off-by: Bharat Bhushan <Bharat.Bhushan@freescale.com>
Signed-off-by: Eric Auger <eric.auger@linaro.org>

---
---
 drivers/vfio/pci/vfio_pci_intrs.c | 73 ++++++++++++++++++++++++++++++++++++---
 1 file changed, 68 insertions(+), 5 deletions(-)

Comments

kernel test robot Jan. 26, 2016, 2:43 p.m. UTC | #1 
Hi Eric,

[auto build test WARNING on v4.5-rc1]
[also build test WARNING on next-20160125]
[cannot apply to iommu/next]
[if your patch is applied to the wrong git tree, please drop us a note to help improving the system]

url:    https://github.com/0day-ci/linux/commits/Eric-Auger/KVM-PCIe-MSI-passthrough-on-ARM-ARM64/20160126-211921
config: i386-allmodconfig (attached as .config)
reproduce:
        # save the attached .config to linux build tree
        make ARCH=i386 

All warnings (new ones prefixed by >>):

   drivers/vfio/pci/vfio_pci_intrs.c: In function 'vfio_set_mapped_msi_addr':
>> drivers/vfio/pci/vfio_pci_intrs.c:324:43: warning: left shift count >= width of type [-Wshift-count-overflow]
     msi_addr = (phys_addr_t)(msg.address_hi) << 32 |
                                              ^
>> drivers/vfio/pci/vfio_pci_intrs.c:333:34: warning: right shift count >= width of type [-Wshift-count-overflow]
     msg.address_hi = (u32)(msi_iova >> 32);
                                     ^

vim +324 drivers/vfio/pci/vfio_pci_intrs.c

   318		dma_addr_t msi_iova;
   319		struct vfio_group *group = vdev->vfio_group;
   320		struct msi_msg msg;
   321		int ret;
   322	
   323		get_cached_msi_msg(irq, &msg);
 > 324		msi_addr = (phys_addr_t)(msg.address_hi) << 32 |
   325				(phys_addr_t)(msg.address_lo);
   326	
   327		ret = vfio_group_alloc_map_reserved_iova(group, msi_addr,
   328							 IOMMU_WRITE, &msi_iova);
   329		if (ret)
   330			goto out;
   331	
   332		/* Re-program the msi-address with the iova */
 > 333		msg.address_hi = (u32)(msi_iova >> 32);
   334		msg.address_lo = (u32)(msi_iova & 0xffffffff);
   335		pci_write_msi_msg(irq, &msg);
   336	

---
0-DAY kernel test infrastructure                Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all                   Intel Corporation
Eric Auger Jan. 26, 2016, 3:14 p.m. UTC | #2 
Hi,
On 01/26/2016 03:43 PM, kbuild test robot wrote:
> Hi Eric,
> 
> [auto build test WARNING on v4.5-rc1]
> [also build test WARNING on next-20160125]
> [cannot apply to iommu/next]
> [if your patch is applied to the wrong git tree, please drop us a note to help improving the system]
> 
> url:    https://github.com/0day-ci/linux/commits/Eric-Auger/KVM-PCIe-MSI-passthrough-on-ARM-ARM64/20160126-211921
> config: i386-allmodconfig (attached as .config)
> reproduce:
>         # save the attached .config to linux build tree
>         make ARCH=i386 
> 
> All warnings (new ones prefixed by >>):
> 
>    drivers/vfio/pci/vfio_pci_intrs.c: In function 'vfio_set_mapped_msi_addr':
>>> drivers/vfio/pci/vfio_pci_intrs.c:324:43: warning: left shift count >= width of type [-Wshift-count-overflow]
>      msi_addr = (phys_addr_t)(msg.address_hi) << 32 |
>                                               ^
>>> drivers/vfio/pci/vfio_pci_intrs.c:333:34: warning: right shift count >= width of type [-Wshift-count-overflow]
>      msg.address_hi = (u32)(msi_iova >> 32);
I definitively need to revisit that code. I Better understand Alex'
comment now :-(

Thanks

Eric
>                                      ^
> 
> vim +324 drivers/vfio/pci/vfio_pci_intrs.c
> 
>    318		dma_addr_t msi_iova;
>    319		struct vfio_group *group = vdev->vfio_group;
>    320		struct msi_msg msg;
>    321		int ret;
>    322	
>    323		get_cached_msi_msg(irq, &msg);
>  > 324		msi_addr = (phys_addr_t)(msg.address_hi) << 32 |
>    325				(phys_addr_t)(msg.address_lo);
>    326	
>    327		ret = vfio_group_alloc_map_reserved_iova(group, msi_addr,
>    328							 IOMMU_WRITE, &msi_iova);
>    329		if (ret)
>    330			goto out;
>    331	
>    332		/* Re-program the msi-address with the iova */
>  > 333		msg.address_hi = (u32)(msi_iova >> 32);
>    334		msg.address_lo = (u32)(msi_iova & 0xffffffff);
>    335		pci_write_msi_msg(irq, &msg);
>    336	
> 
> ---
> 0-DAY kernel test infrastructure                Open Source Technology Center
> https://lists.01.org/pipermail/kbuild-all                   Intel Corporation
>
diff mbox

Patch

diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index 3b3ba15..bac24c9 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -305,6 +305,57 @@  static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix)
 	return 0;
 }
 
+/**
+ * vfio_set_mapped_msi_addr: overwrites the msi physical address with an iova
+ *
+ * @pdev: vfio pci device handle
+ * @irq: irq linux number
+ * returns 0 upon success, < 0 on failure
+ */
+static int vfio_set_mapped_msi_addr(struct vfio_pci_device *vdev, int irq)
+{
+	phys_addr_t msi_addr;
+	dma_addr_t msi_iova;
+	struct vfio_group *group = vdev->vfio_group;
+	struct msi_msg msg;
+	int ret;
+
+	get_cached_msi_msg(irq, &msg);
+	msi_addr = (phys_addr_t)(msg.address_hi) << 32 |
+			(phys_addr_t)(msg.address_lo);
+
+	ret = vfio_group_alloc_map_reserved_iova(group, msi_addr,
+						 IOMMU_WRITE, &msi_iova);
+	if (ret)
+		goto out;
+
+	/* Re-program the msi-address with the iova */
+	msg.address_hi = (u32)(msi_iova >> 32);
+	msg.address_lo = (u32)(msi_iova & 0xffffffff);
+	pci_write_msi_msg(irq, &msg);
+
+out:
+	return ret;
+}
+
+/**
+ * vfio_unset_mapped_msi_addr: decrement the ref counter of the msi iova page
+ * associated to the linux irq (in case it is null unmaps and frees resources)
+ *
+ * @pdev: vfio pci device handle
+ * @irq: irq linux number
+ */
+static void vfio_unset_mapped_msi_addr(struct vfio_pci_device *vdev, int irq)
+{
+	dma_addr_t msi_iova;
+	struct vfio_group *group = vdev->vfio_group;
+	struct msi_msg msg;
+
+	get_cached_msi_msg(irq, &msg);
+	msi_iova = (u64)(msg.address_hi) << 32 | (u64)(msg.address_lo);
+	vfio_group_unmap_free_reserved_iova(group, msi_iova);
+}
+
 static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
 				      int vector, int fd, bool msix)
 {
@@ -318,6 +369,7 @@  static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
 		return -EINVAL;
 
 	if (vdev->ctx[vector].trigger) {
+		vfio_unset_mapped_msi_addr(vdev, irq);
 		free_irq(irq, vdev->ctx[vector].trigger);
 		irq_bypass_unregister_producer(&vdev->ctx[vector].producer);
 		kfree(vdev->ctx[vector].name);
@@ -355,11 +407,8 @@  static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
 
 	ret = request_irq(irq, vfio_msihandler, 0,
 			  vdev->ctx[vector].name, trigger);
-	if (ret) {
-		kfree(vdev->ctx[vector].name);
-		eventfd_ctx_put(trigger);
-		return ret;
-	}
+	if (ret)
+		goto error_free;
 
 	vdev->ctx[vector].producer.token = trigger;
 	vdev->ctx[vector].producer.irq = irq;
@@ -369,9 +418,23 @@  static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
 		"irq bypass producer (token %p) registration fails: %d\n",
 		vdev->ctx[vector].producer.token, ret);
 
+	if (vfio_group_require_msi_mapping(vdev->vfio_group)) {
+		ret = vfio_set_mapped_msi_addr(vdev, irq);
+		if (ret)
+			goto error_free_irq;
+	}
+
 	vdev->ctx[vector].trigger = trigger;
 
 	return 0;
+
+error_free_irq:
+	free_irq(irq, vdev->ctx[vector].trigger);
+error_free:
+	kfree(vdev->ctx[vector].name);
+	eventfd_ctx_put(trigger);
+	return ret;
+
 }
 
 static int vfio_msi_set_block(struct vfio_pci_device *vdev, unsigned start,