[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <1455201262-5259-11-git-send-email-eric.auger@linaro.org>
Date: Thu, 11 Feb 2016 14:34:17 +0000
From: Eric Auger <eric.auger@...aro.org>
To: eric.auger@...com, eric.auger@...aro.org,
alex.williamson@...hat.com, will.deacon@....com, joro@...tes.org,
tglx@...utronix.de, jason@...edaemon.net, marc.zyngier@....com,
christoffer.dall@...aro.org, linux-arm-kernel@...ts.infradead.org,
kvmarm@...ts.cs.columbia.edu, kvm@...r.kernel.org
Cc: suravee.suthikulpanit@....com, patches@...aro.org,
linux-kernel@...r.kernel.org, Manish.Jaggi@...iumnetworks.com,
Bharat.Bhushan@...escale.com, pranav.sawargaonkar@...il.com,
p.fedin@...sung.com, iommu@...ts.linux-foundation.org,
sherry.hurwitz@....com, brijesh.singh@....com, leo.duran@....com,
Thomas.Lendacky@....com
Subject: [RFC v2 10/15] vfio: allow the user to register reserved iova range for MSI mapping
The user is allowed to register a reserved IOVA range by using the
DMA MAP API and setting the new flag: VFIO_DMA_MAP_FLAG_MSI_RESERVED_IOVA.
It provides the base address and the size. This region is stored in the
vfio_dma rb tree. At that point the iova range is not mapped to any target
address yet. The host kernel will use those iova when needed, typically
when the VFIO-PCI device allocates its MSI's.
This patch also handles the destruction of the reserved binding RB-tree and
domain's iova_domains.
Signed-off-by: Eric Auger <eric.auger@...aro.org>
Signed-off-by: Bharat Bhushan <Bharat.Bhushan@...escale.com>
---
v1 -> v2:
- set returned value according to alloc_reserved_iova_domain result
- free the iova domains in case any error occurs
RFC v1 -> v1:
- takes into account Alex comments, based on
[RFC PATCH 1/6] vfio: Add interface for add/del reserved iova region:
- use the existing dma map/unmap ioctl interface with a flag to register
a reserved IOVA range. A single reserved iova region is allowed.
---
drivers/vfio/vfio_iommu_type1.c | 75 ++++++++++++++++++++++++++++++++++++++++-
include/uapi/linux/vfio.h | 9 +++++
2 files changed, 83 insertions(+), 1 deletion(-)
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index b9326c9..c5d3b48 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -673,6 +673,75 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
return ret;
}
+static int vfio_register_reserved_iova_range(struct vfio_iommu *iommu,
+ struct vfio_iommu_type1_dma_map *map)
+{
+ dma_addr_t iova = map->iova;
+ size_t size = map->size;
+ uint64_t mask;
+ struct vfio_dma *dma;
+ int ret = 0;
+ struct vfio_domain *d;
+ unsigned long order;
+
+ /* Verify that none of our __u64 fields overflow */
+ if (map->size != size || map->iova != iova)
+ return -EINVAL;
+
+ order = __ffs(vfio_pgsize_bitmap(iommu));
+ mask = ((uint64_t)1 << order) - 1;
+
+ WARN_ON(mask & PAGE_MASK);
+
+ /* we currently only support MSI_RESERVED_IOVA */
+ if (!(map->flags & VFIO_DMA_MAP_FLAG_MSI_RESERVED_IOVA))
+ return -EINVAL;
+
+ if (!size || (size | iova) & mask)
+ return -EINVAL;
+
+ /* Don't allow IOVA address wrap */
+ if (iova + size - 1 < iova)
+ return -EINVAL;
+
+ mutex_lock(&iommu->lock);
+
+ /* check if the iova domain has not been instantiated already*/
+ d = list_first_entry(&iommu->domain_list,
+ struct vfio_domain, next);
+
+ if (vfio_find_dma(iommu, iova, size)) {
+ ret = -EEXIST;
+ goto out;
+ }
+
+ dma = kzalloc(sizeof(*dma), GFP_KERNEL);
+ if (!dma) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ dma->iova = iova;
+ dma->size = size;
+ dma->type = VFIO_IOVA_RESERVED;
+
+ list_for_each_entry(d, &iommu->domain_list, next)
+ ret |= iommu_alloc_reserved_iova_domain(d->domain, iova,
+ size, order);
+
+ if (ret) {
+ list_for_each_entry(d, &iommu->domain_list, next)
+ iommu_free_reserved_iova_domain(d->domain);
+ goto out;
+ }
+
+ vfio_link_dma(iommu, dma);
+
+out:
+ mutex_unlock(&iommu->lock);
+ return ret;
+}
+
static int vfio_bus_type(struct device *dev, void *data)
{
struct bus_type **bus = data;
@@ -1045,7 +1114,8 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
} else if (cmd == VFIO_IOMMU_MAP_DMA) {
struct vfio_iommu_type1_dma_map map;
uint32_t mask = VFIO_DMA_MAP_FLAG_READ |
- VFIO_DMA_MAP_FLAG_WRITE;
+ VFIO_DMA_MAP_FLAG_WRITE |
+ VFIO_DMA_MAP_FLAG_MSI_RESERVED_IOVA;
minsz = offsetofend(struct vfio_iommu_type1_dma_map, size);
@@ -1055,6 +1125,9 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
if (map.argsz < minsz || map.flags & ~mask)
return -EINVAL;
+ if (map.flags & VFIO_DMA_MAP_FLAG_MSI_RESERVED_IOVA)
+ return vfio_register_reserved_iova_range(iommu, &map);
+
return vfio_dma_do_map(iommu, &map);
} else if (cmd == VFIO_IOMMU_UNMAP_DMA) {
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 43e183b..982e326 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -411,12 +411,21 @@ struct vfio_iommu_type1_info {
*
* Map process virtual addresses to IO virtual addresses using the
* provided struct vfio_dma_map. Caller sets argsz. READ &/ WRITE required.
+ *
+ * In case MSI_RESERVED_IOVA is set, the API only aims at registering an IOVA
+ * region which will be used on some platforms to map the host MSI frame.
+ * in that specific case, vaddr and prot are ignored. The requirement for
+ * provisioning such IOVA range can be checked by calling VFIO_IOMMU_GET_INFO
+ * with the VFIO_IOMMU_INFO_REQUIRE_MSI_MAP attribute. A single
+ * MSI_RESERVED_IOVA region can be registered
*/
struct vfio_iommu_type1_dma_map {
__u32 argsz;
__u32 flags;
#define VFIO_DMA_MAP_FLAG_READ (1 << 0) /* readable from device */
#define VFIO_DMA_MAP_FLAG_WRITE (1 << 1) /* writable from device */
+/* reserved iova for MSI vectors*/
+#define VFIO_DMA_MAP_FLAG_MSI_RESERVED_IOVA (1 << 2)
__u64 vaddr; /* Process virtual address */
__u64 iova; /* IO virtual address */
__u64 size; /* Size of mapping (bytes) */
--
1.9.1
Powered by blists - more mailing lists