Pass through the MemoryRegion to DMA operation handlers of vfio
containers. The vfio-user container will need this later, to translate
the vaddr into an offset for the dma map vfio-user message.
Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
---
include/hw/vfio/vfio-container-base.h | 9 +++++----
hw/vfio/container-base.c | 4 ++--
hw/vfio/container.c | 3 ++-
hw/vfio/iommufd.c | 3 ++-
hw/vfio/listener.c | 6 +++---
5 files changed, 14 insertions(+), 11 deletions(-)
diff --git a/include/hw/vfio/vfio-container-base.h b/include/hw/vfio/vfio-container-base.h
index 41c49b2aa5..c18986a621 100644
--- a/include/hw/vfio/vfio-container-base.h
+++ b/include/hw/vfio/vfio-container-base.h
@@ -78,7 +78,7 @@ void vfio_address_space_insert(VFIOAddressSpace *space,
int vfio_container_dma_map(VFIOContainerBase *bcontainer,
hwaddr iova, ram_addr_t size,
- void *vaddr, bool readonly);
+ void *vaddr, bool readonly, MemoryRegion *mrp);
int vfio_container_dma_unmap(VFIOContainerBase *bcontainer,
hwaddr iova, ram_addr_t size,
IOMMUTLBEntry *iotlb, bool unmap_all);
@@ -149,18 +149,19 @@ struct VFIOIOMMUClass {
/**
* @dma_map
*
- * Map an address range into the container.
+ * Map an address range into the container. Note that @mrp will within an
+ * RCU read lock region across this call.
*
* @bcontainer: #VFIOContainerBase to use
* @iova: start address to map
* @size: size of the range to map
* @vaddr: process virtual address of mapping
* @readonly: true if mapping should be readonly
+ * @mrp: the memory region for this mapping
*/
int (*dma_map)(const VFIOContainerBase *bcontainer,
hwaddr iova, ram_addr_t size,
- void *vaddr, bool readonly);
-
+ void *vaddr, bool readonly, MemoryRegion *mrp);
/**
* @dma_unmap
*
diff --git a/hw/vfio/container-base.c b/hw/vfio/container-base.c
index 1c6ca94b60..a677bb6694 100644
--- a/hw/vfio/container-base.c
+++ b/hw/vfio/container-base.c
@@ -75,12 +75,12 @@ void vfio_address_space_insert(VFIOAddressSpace *space,
int vfio_container_dma_map(VFIOContainerBase *bcontainer,
hwaddr iova, ram_addr_t size,
- void *vaddr, bool readonly)
+ void *vaddr, bool readonly, MemoryRegion *mrp)
{
VFIOIOMMUClass *vioc = VFIO_IOMMU_GET_CLASS(bcontainer);
g_assert(vioc->dma_map);
- return vioc->dma_map(bcontainer, iova, size, vaddr, readonly);
+ return vioc->dma_map(bcontainer, iova, size, vaddr, readonly, mrp);
}
int vfio_container_dma_unmap(VFIOContainerBase *bcontainer,
diff --git a/hw/vfio/container.c b/hw/vfio/container.c
index a9f0dbaec4..98d6b9f90c 100644
--- a/hw/vfio/container.c
+++ b/hw/vfio/container.c
@@ -207,7 +207,8 @@ static int vfio_legacy_dma_unmap(const VFIOContainerBase *bcontainer,
}
static int vfio_legacy_dma_map(const VFIOContainerBase *bcontainer, hwaddr iova,
- ram_addr_t size, void *vaddr, bool readonly)
+ ram_addr_t size, void *vaddr, bool readonly,
+ MemoryRegion *mrp)
{
const VFIOContainer *container = container_of(bcontainer, VFIOContainer,
bcontainer);
diff --git a/hw/vfio/iommufd.c b/hw/vfio/iommufd.c
index af1c7ab10a..a2518c4a5d 100644
--- a/hw/vfio/iommufd.c
+++ b/hw/vfio/iommufd.c
@@ -34,7 +34,8 @@
TYPE_HOST_IOMMU_DEVICE_IOMMUFD "-vfio"
static int iommufd_cdev_map(const VFIOContainerBase *bcontainer, hwaddr iova,
- ram_addr_t size, void *vaddr, bool readonly)
+ ram_addr_t size, void *vaddr, bool readonly,
+ MemoryRegion *mrp)
{
const VFIOIOMMUFDContainer *container =
container_of(bcontainer, VFIOIOMMUFDContainer, bcontainer);
diff --git a/hw/vfio/listener.c b/hw/vfio/listener.c
index 0afafe3464..a1d2d2561d 100644
--- a/hw/vfio/listener.c
+++ b/hw/vfio/listener.c
@@ -170,7 +170,7 @@ static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
*/
ret = vfio_container_dma_map(bcontainer, iova,
iotlb->addr_mask + 1, vaddr,
- read_only);
+ read_only, mr);
if (ret) {
error_report("vfio_container_dma_map(%p, 0x%"HWADDR_PRIx", "
"0x%"HWADDR_PRIx", %p) = %d (%s)",
@@ -240,7 +240,7 @@ static int vfio_ram_discard_notify_populate(RamDiscardListener *rdl,
vaddr = memory_region_get_ram_ptr(section->mr) + start;
ret = vfio_container_dma_map(bcontainer, iova, next - start,
- vaddr, section->readonly);
+ vaddr, section->readonly, section->mr);
if (ret) {
/* Rollback */
vfio_ram_discard_notify_discard(rdl, section);
@@ -564,7 +564,7 @@ static void vfio_listener_region_add(MemoryListener *listener,
}
ret = vfio_container_dma_map(bcontainer, iova, int128_get64(llsize),
- vaddr, section->readonly);
+ vaddr, section->readonly, section->mr);
if (ret) {
error_setg(&err, "vfio_container_dma_map(%p, 0x%"HWADDR_PRIx", "
"0x%"HWADDR_PRIx", %p) = %d (%s)",
--
2.43.0+Steven,
On 5/20/25 17:03, John Levon wrote:
> Pass through the MemoryRegion to DMA operation handlers of vfio
> containers. The vfio-user container will need this later, to translate
> the vaddr into an offset for the dma map vfio-user message.
>
> Originally-by: John Johnson <john.g.johnson@oracle.com>
> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
> Signed-off-by: John Levon <john.levon@nutanix.com>
This change conflicts with :
https://lore.kernel.org/qemu-devel/1747063973-124548-28-git-send-email-steven.sistare@oracle.com
Steven,
Could we use this version instead for the "live update" series ?
Thanks,
C.
> ---
> include/hw/vfio/vfio-container-base.h | 9 +++++----
> hw/vfio/container-base.c | 4 ++--
> hw/vfio/container.c | 3 ++-
> hw/vfio/iommufd.c | 3 ++-
> hw/vfio/listener.c | 6 +++---
> 5 files changed, 14 insertions(+), 11 deletions(-)
>
> diff --git a/include/hw/vfio/vfio-container-base.h b/include/hw/vfio/vfio-container-base.h
> index 41c49b2aa5..c18986a621 100644
> --- a/include/hw/vfio/vfio-container-base.h
> +++ b/include/hw/vfio/vfio-container-base.h
> @@ -78,7 +78,7 @@ void vfio_address_space_insert(VFIOAddressSpace *space,
>
> int vfio_container_dma_map(VFIOContainerBase *bcontainer,
> hwaddr iova, ram_addr_t size,
> - void *vaddr, bool readonly);
> + void *vaddr, bool readonly, MemoryRegion *mrp);
> int vfio_container_dma_unmap(VFIOContainerBase *bcontainer,
> hwaddr iova, ram_addr_t size,
> IOMMUTLBEntry *iotlb, bool unmap_all);
> @@ -149,18 +149,19 @@ struct VFIOIOMMUClass {
> /**
> * @dma_map
> *
> - * Map an address range into the container.
> + * Map an address range into the container. Note that @mrp will within an
> + * RCU read lock region across this call.
> *
> * @bcontainer: #VFIOContainerBase to use
> * @iova: start address to map
> * @size: size of the range to map
> * @vaddr: process virtual address of mapping
> * @readonly: true if mapping should be readonly
> + * @mrp: the memory region for this mapping
> */
> int (*dma_map)(const VFIOContainerBase *bcontainer,
> hwaddr iova, ram_addr_t size,
> - void *vaddr, bool readonly);
> -
> + void *vaddr, bool readonly, MemoryRegion *mrp);
> /**
> * @dma_unmap
> *
> diff --git a/hw/vfio/container-base.c b/hw/vfio/container-base.c
> index 1c6ca94b60..a677bb6694 100644
> --- a/hw/vfio/container-base.c
> +++ b/hw/vfio/container-base.c
> @@ -75,12 +75,12 @@ void vfio_address_space_insert(VFIOAddressSpace *space,
>
> int vfio_container_dma_map(VFIOContainerBase *bcontainer,
> hwaddr iova, ram_addr_t size,
> - void *vaddr, bool readonly)
> + void *vaddr, bool readonly, MemoryRegion *mrp)
> {
> VFIOIOMMUClass *vioc = VFIO_IOMMU_GET_CLASS(bcontainer);
>
> g_assert(vioc->dma_map);
> - return vioc->dma_map(bcontainer, iova, size, vaddr, readonly);
> + return vioc->dma_map(bcontainer, iova, size, vaddr, readonly, mrp);
> }
>
> int vfio_container_dma_unmap(VFIOContainerBase *bcontainer,
> diff --git a/hw/vfio/container.c b/hw/vfio/container.c
> index a9f0dbaec4..98d6b9f90c 100644
> --- a/hw/vfio/container.c
> +++ b/hw/vfio/container.c
> @@ -207,7 +207,8 @@ static int vfio_legacy_dma_unmap(const VFIOContainerBase *bcontainer,
> }
>
> static int vfio_legacy_dma_map(const VFIOContainerBase *bcontainer, hwaddr iova,
> - ram_addr_t size, void *vaddr, bool readonly)
> + ram_addr_t size, void *vaddr, bool readonly,
> + MemoryRegion *mrp)
> {
> const VFIOContainer *container = container_of(bcontainer, VFIOContainer,
> bcontainer);
> diff --git a/hw/vfio/iommufd.c b/hw/vfio/iommufd.c
> index af1c7ab10a..a2518c4a5d 100644
> --- a/hw/vfio/iommufd.c
> +++ b/hw/vfio/iommufd.c
> @@ -34,7 +34,8 @@
> TYPE_HOST_IOMMU_DEVICE_IOMMUFD "-vfio"
>
> static int iommufd_cdev_map(const VFIOContainerBase *bcontainer, hwaddr iova,
> - ram_addr_t size, void *vaddr, bool readonly)
> + ram_addr_t size, void *vaddr, bool readonly,
> + MemoryRegion *mrp)
> {
> const VFIOIOMMUFDContainer *container =
> container_of(bcontainer, VFIOIOMMUFDContainer, bcontainer);
> diff --git a/hw/vfio/listener.c b/hw/vfio/listener.c
> index 0afafe3464..a1d2d2561d 100644
> --- a/hw/vfio/listener.c
> +++ b/hw/vfio/listener.c
> @@ -170,7 +170,7 @@ static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
> */
> ret = vfio_container_dma_map(bcontainer, iova,
> iotlb->addr_mask + 1, vaddr,
> - read_only);
> + read_only, mr);
> if (ret) {
> error_report("vfio_container_dma_map(%p, 0x%"HWADDR_PRIx", "
> "0x%"HWADDR_PRIx", %p) = %d (%s)",
> @@ -240,7 +240,7 @@ static int vfio_ram_discard_notify_populate(RamDiscardListener *rdl,
> vaddr = memory_region_get_ram_ptr(section->mr) + start;
>
> ret = vfio_container_dma_map(bcontainer, iova, next - start,
> - vaddr, section->readonly);
> + vaddr, section->readonly, section->mr);
> if (ret) {
> /* Rollback */
> vfio_ram_discard_notify_discard(rdl, section);
> @@ -564,7 +564,7 @@ static void vfio_listener_region_add(MemoryListener *listener,
> }
>
> ret = vfio_container_dma_map(bcontainer, iova, int128_get64(llsize),
> - vaddr, section->readonly);
> + vaddr, section->readonly, section->mr);
> if (ret) {
> error_setg(&err, "vfio_container_dma_map(%p, 0x%"HWADDR_PRIx", "
> "0x%"HWADDR_PRIx", %p) = %d (%s)",
On 5/21/2025 3:43 AM, Cédric Le Goater wrote:
> +Steven,
>
> On 5/20/25 17:03, John Levon wrote:
>> Pass through the MemoryRegion to DMA operation handlers of vfio
>> containers. The vfio-user container will need this later, to translate
>> the vaddr into an offset for the dma map vfio-user message.
>>
>> Originally-by: John Johnson <john.g.johnson@oracle.com>
>> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
>> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
>> Signed-off-by: John Levon <john.levon@nutanix.com>
>
>
> This change conflicts with :
>
> https://lore.kernel.org/qemu-devel/1747063973-124548-28-git-send-email-steven.sistare@oracle.com
>
> Steven,
>
> Could we use this version instead for the "live update" series ?
Sure, I will drop my patch and use this.
A few nits, iff there is another version of the series.
I suggest "mrp" be renamed "mr", to be consistent with all other
MemoryRegion* variables. A MemoryRegion is never passed by value,
so the "p" is understood.
This comment for @dma_map needs polishing for clarity:
+ * Map an address range into the container. Note that @mrp will within an
+ * RCU read lock region across this call.
- Steve
>> ---
>> include/hw/vfio/vfio-container-base.h | 9 +++++----
>> hw/vfio/container-base.c | 4 ++--
>> hw/vfio/container.c | 3 ++-
>> hw/vfio/iommufd.c | 3 ++-
>> hw/vfio/listener.c | 6 +++---
>> 5 files changed, 14 insertions(+), 11 deletions(-)
>>
>> diff --git a/include/hw/vfio/vfio-container-base.h b/include/hw/vfio/vfio-container-base.h
>> index 41c49b2aa5..c18986a621 100644
>> --- a/include/hw/vfio/vfio-container-base.h
>> +++ b/include/hw/vfio/vfio-container-base.h
>> @@ -78,7 +78,7 @@ void vfio_address_space_insert(VFIOAddressSpace *space,
>> int vfio_container_dma_map(VFIOContainerBase *bcontainer,
>> hwaddr iova, ram_addr_t size,
>> - void *vaddr, bool readonly);
>> + void *vaddr, bool readonly, MemoryRegion *mrp);
>> int vfio_container_dma_unmap(VFIOContainerBase *bcontainer,
>> hwaddr iova, ram_addr_t size,
>> IOMMUTLBEntry *iotlb, bool unmap_all);
>> @@ -149,18 +149,19 @@ struct VFIOIOMMUClass {
>> /**
>> * @dma_map
>> *
>> - * Map an address range into the container.
>> + * Map an address range into the container. Note that @mrp will within an
>> + * RCU read lock region across this call.
>> *
>> * @bcontainer: #VFIOContainerBase to use
>> * @iova: start address to map
>> * @size: size of the range to map
>> * @vaddr: process virtual address of mapping
>> * @readonly: true if mapping should be readonly
>> + * @mrp: the memory region for this mapping
>> */
>> int (*dma_map)(const VFIOContainerBase *bcontainer,
>> hwaddr iova, ram_addr_t size,
>> - void *vaddr, bool readonly);
>> -
>> + void *vaddr, bool readonly, MemoryRegion *mrp);
>> /**
>> * @dma_unmap
>> *
>> diff --git a/hw/vfio/container-base.c b/hw/vfio/container-base.c
>> index 1c6ca94b60..a677bb6694 100644
>> --- a/hw/vfio/container-base.c
>> +++ b/hw/vfio/container-base.c
>> @@ -75,12 +75,12 @@ void vfio_address_space_insert(VFIOAddressSpace *space,
>> int vfio_container_dma_map(VFIOContainerBase *bcontainer,
>> hwaddr iova, ram_addr_t size,
>> - void *vaddr, bool readonly)
>> + void *vaddr, bool readonly, MemoryRegion *mrp)
>> {
>> VFIOIOMMUClass *vioc = VFIO_IOMMU_GET_CLASS(bcontainer);
>> g_assert(vioc->dma_map);
>> - return vioc->dma_map(bcontainer, iova, size, vaddr, readonly);
>> + return vioc->dma_map(bcontainer, iova, size, vaddr, readonly, mrp);
>> }
>> int vfio_container_dma_unmap(VFIOContainerBase *bcontainer,
>> diff --git a/hw/vfio/container.c b/hw/vfio/container.c
>> index a9f0dbaec4..98d6b9f90c 100644
>> --- a/hw/vfio/container.c
>> +++ b/hw/vfio/container.c
>> @@ -207,7 +207,8 @@ static int vfio_legacy_dma_unmap(const VFIOContainerBase *bcontainer,
>> }
>> static int vfio_legacy_dma_map(const VFIOContainerBase *bcontainer, hwaddr iova,
>> - ram_addr_t size, void *vaddr, bool readonly)
>> + ram_addr_t size, void *vaddr, bool readonly,
>> + MemoryRegion *mrp)
>> {
>> const VFIOContainer *container = container_of(bcontainer, VFIOContainer,
>> bcontainer);
>> diff --git a/hw/vfio/iommufd.c b/hw/vfio/iommufd.c
>> index af1c7ab10a..a2518c4a5d 100644
>> --- a/hw/vfio/iommufd.c
>> +++ b/hw/vfio/iommufd.c
>> @@ -34,7 +34,8 @@
>> TYPE_HOST_IOMMU_DEVICE_IOMMUFD "-vfio"
>> static int iommufd_cdev_map(const VFIOContainerBase *bcontainer, hwaddr iova,
>> - ram_addr_t size, void *vaddr, bool readonly)
>> + ram_addr_t size, void *vaddr, bool readonly,
>> + MemoryRegion *mrp)
>> {
>> const VFIOIOMMUFDContainer *container =
>> container_of(bcontainer, VFIOIOMMUFDContainer, bcontainer);
>> diff --git a/hw/vfio/listener.c b/hw/vfio/listener.c
>> index 0afafe3464..a1d2d2561d 100644
>> --- a/hw/vfio/listener.c
>> +++ b/hw/vfio/listener.c
>> @@ -170,7 +170,7 @@ static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
>> */
>> ret = vfio_container_dma_map(bcontainer, iova,
>> iotlb->addr_mask + 1, vaddr,
>> - read_only);
>> + read_only, mr);
>> if (ret) {
>> error_report("vfio_container_dma_map(%p, 0x%"HWADDR_PRIx", "
>> "0x%"HWADDR_PRIx", %p) = %d (%s)",
>> @@ -240,7 +240,7 @@ static int vfio_ram_discard_notify_populate(RamDiscardListener *rdl,
>> vaddr = memory_region_get_ram_ptr(section->mr) + start;
>> ret = vfio_container_dma_map(bcontainer, iova, next - start,
>> - vaddr, section->readonly);
>> + vaddr, section->readonly, section->mr);
>> if (ret) {
>> /* Rollback */
>> vfio_ram_discard_notify_discard(rdl, section);
>> @@ -564,7 +564,7 @@ static void vfio_listener_region_add(MemoryListener *listener,
>> }
>> ret = vfio_container_dma_map(bcontainer, iova, int128_get64(llsize),
>> - vaddr, section->readonly);
>> + vaddr, section->readonly, section->mr);
>> if (ret) {
>> error_setg(&err, "vfio_container_dma_map(%p, 0x%"HWADDR_PRIx", "
>> "0x%"HWADDR_PRIx", %p) = %d (%s)",
>
On Wed, May 21, 2025 at 09:00:29AM -0400, Steven Sistare wrote: > A few nits, iff there is another version of the series. > > I suggest "mrp" be renamed "mr", to be consistent with all other > MemoryRegion* variables. A MemoryRegion is never passed by value, > so the "p" is understood. Sure. > This comment for @dma_map needs polishing for clarity: > > + * Map an address range into the container. Note that @mrp will within an > + * RCU read lock region across this call. Will fix thanks john
On Wed, May 21, 2025 at 09:43:11AM +0200, Cédric Le Goater wrote:
> !-------------------------------------------------------------------|
> CAUTION: External Email
>
> |-------------------------------------------------------------------!
>
> +Steven,
>
> On 5/20/25 17:03, John Levon wrote:
> > Pass through the MemoryRegion to DMA operation handlers of vfio
> > containers. The vfio-user container will need this later, to translate
> > the vaddr into an offset for the dma map vfio-user message.
> >
> > Originally-by: John Johnson <john.g.johnson@oracle.com>
> > Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
> > Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
> > Signed-off-by: John Levon <john.levon@nutanix.com>
>
>
> This change conflicts with :
>
> https://urldefense.proofpoint.com/v2/url?u=https-3A__lore.kernel.org_qemu-2Ddevel_1747063973-2D124548-2D28-2Dgit-2Dsend-2Demail-2Dsteven.sistare-40oracle.com&d=DwICaQ&c=s883GpUCOChKOHiocYtGcg&r=v7SNLJqx7b9Vfc7ZO82Wg4nnZ8O5XkACFQ30bVKxotI&m=ZGgaPL84zJdxC-NJiZdGWRzh1WIXiIKzDUt8YcytF-NfxOT9I_gSOxNCph5DfyVM&s=V-_fptKbd0WpQ_JDJWze9TxsbOrvVfEm2EIPPH6HJ2k&e=
>
> Steven,
>
> Could we use this version instead for the "live update" series ?
I could use the ram block for the offset but the mrp is also used here:
86 int fd = memory_region_get_fd(mrp);
which is
2406 int memory_region_get_fd(MemoryRegion *mr)
2407 {
2408 RCU_READ_LOCK_GUARD();
2409 while (mr->alias) {
2410 mr = mr->alias;
2411 }
2412 return mr->ram_block->fd;
2413 }
In the tests I've done, mr->alias is always NULL, but I don't know enough about
MR handling to be sure this will always be the case? Perhaps others can, in
which case I only need the ram block too.
regards
john
© 2016 - 2025 Red Hat, Inc.