* [PATCH v8 01/28] vfio/container: pass MemoryRegion to DMA operations
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
@ 2025-02-19 14:48 ` John Levon
2025-04-02 16:44 ` Cédric Le Goater
2025-02-19 14:48 ` [PATCH v8 02/28] vfio/container: pass listener_begin/commit callbacks John Levon
` (29 subsequent siblings)
30 siblings, 1 reply; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin, Jagannathan Raman, John Johnson,
Elena Ufimtseva
From: Jagannathan Raman <jag.raman@oracle.com>
Pass through the MemoryRegion to DMA operation handlers of vfio
containers. The vfio-user container will need this later.
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>
---
hw/vfio/common.c | 17 ++++++++++-------
hw/vfio/container-base.c | 4 ++--
hw/vfio/container.c | 3 ++-
hw/vfio/iommufd.c | 3 ++-
hw/virtio/vhost-vdpa.c | 2 +-
include/exec/memory.h | 4 +++-
include/hw/vfio/vfio-container-base.h | 4 ++--
system/memory.c | 7 ++++++-
8 files changed, 28 insertions(+), 16 deletions(-)
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index abbdc56b6d..8d3d425c63 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -248,12 +248,12 @@ static bool vfio_listener_skipped_section(MemoryRegionSection *section)
/* Called with rcu_read_lock held. */
static bool vfio_get_xlat_addr(IOMMUTLBEntry *iotlb, void **vaddr,
ram_addr_t *ram_addr, bool *read_only,
- Error **errp)
+ MemoryRegion **mrp, Error **errp)
{
bool ret, mr_has_discard_manager;
ret = memory_get_xlat_addr(iotlb, vaddr, ram_addr, read_only,
- &mr_has_discard_manager, errp);
+ &mr_has_discard_manager, mrp, errp);
if (ret && mr_has_discard_manager) {
/*
* Malicious VMs might trigger discarding of IOMMU-mapped memory. The
@@ -281,6 +281,7 @@ static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, n);
VFIOContainerBase *bcontainer = giommu->bcontainer;
hwaddr iova = iotlb->iova + giommu->iommu_offset;
+ MemoryRegion *mrp;
void *vaddr;
int ret;
Error *local_err = NULL;
@@ -300,7 +301,8 @@ static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
if ((iotlb->perm & IOMMU_RW) != IOMMU_NONE) {
bool read_only;
- if (!vfio_get_xlat_addr(iotlb, &vaddr, NULL, &read_only, &local_err)) {
+ if (!vfio_get_xlat_addr(iotlb, &vaddr, NULL, &read_only, &mrp,
+ &local_err)) {
error_report_err(local_err);
goto out;
}
@@ -313,7 +315,7 @@ 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, mrp);
if (ret) {
error_report("vfio_container_dma_map(%p, 0x%"HWADDR_PRIx", "
"0x%"HWADDR_PRIx", %p) = %d (%s)",
@@ -378,7 +380,7 @@ 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);
@@ -675,7 +677,7 @@ 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)",
@@ -1232,7 +1234,8 @@ static void vfio_iommu_map_dirty_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
}
rcu_read_lock();
- if (!vfio_get_xlat_addr(iotlb, NULL, &translated_addr, NULL, &local_err)) {
+ if (!vfio_get_xlat_addr(iotlb, NULL, &translated_addr, NULL, NULL,
+ &local_err)) {
error_report_err(local_err);
goto out_unlock;
}
diff --git a/hw/vfio/container-base.c b/hw/vfio/container-base.c
index 749a3fd29d..5e0c9700d9 100644
--- a/hw/vfio/container-base.c
+++ b/hw/vfio/container-base.c
@@ -17,12 +17,12 @@
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 7c57bdd27b..0db0055f39 100644
--- a/hw/vfio/container.c
+++ b/hw/vfio/container.c
@@ -175,7 +175,8 @@ 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 df61edffc0..583b063707 100644
--- a/hw/vfio/iommufd.c
+++ b/hw/vfio/iommufd.c
@@ -28,7 +28,8 @@
#include "exec/ram_addr.h"
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/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c
index 3cdaa12ed5..a1866bb396 100644
--- a/hw/virtio/vhost-vdpa.c
+++ b/hw/virtio/vhost-vdpa.c
@@ -228,7 +228,7 @@ static void vhost_vdpa_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
if ((iotlb->perm & IOMMU_RW) != IOMMU_NONE) {
bool read_only;
- if (!memory_get_xlat_addr(iotlb, &vaddr, NULL, &read_only, NULL,
+ if (!memory_get_xlat_addr(iotlb, &vaddr, NULL, &read_only, NULL, NULL,
&local_err)) {
error_report_err(local_err);
return;
diff --git a/include/exec/memory.h b/include/exec/memory.h
index 9f73b59867..adaf1d1ca4 100644
--- a/include/exec/memory.h
+++ b/include/exec/memory.h
@@ -747,13 +747,15 @@ void ram_discard_manager_unregister_listener(RamDiscardManager *rdm,
* @read_only: indicates if writes are allowed
* @mr_has_discard_manager: indicates memory is controlled by a
* RamDiscardManager
+ * @mrp: if non-NULL, fill in with MemoryRegion
* @errp: pointer to Error*, to store an error if it happens.
*
* Return: true on success, else false setting @errp with error.
*/
bool memory_get_xlat_addr(IOMMUTLBEntry *iotlb, void **vaddr,
ram_addr_t *ram_addr, bool *read_only,
- bool *mr_has_discard_manager, Error **errp);
+ bool *mr_has_discard_manager, MemoryRegion **mrp,
+ Error **errp);
typedef struct CoalescedMemoryRange CoalescedMemoryRange;
typedef struct MemoryRegionIoeventfd MemoryRegionIoeventfd;
diff --git a/include/hw/vfio/vfio-container-base.h b/include/hw/vfio/vfio-container-base.h
index 4cff9943ab..c9d339383e 100644
--- a/include/hw/vfio/vfio-container-base.h
+++ b/include/hw/vfio/vfio-container-base.h
@@ -73,7 +73,7 @@ typedef struct VFIORamDiscardListener {
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);
@@ -113,7 +113,7 @@ struct VFIOIOMMUClass {
bool (*setup)(VFIOContainerBase *bcontainer, Error **errp);
int (*dma_map)(const VFIOContainerBase *bcontainer,
hwaddr iova, ram_addr_t size,
- void *vaddr, bool readonly);
+ void *vaddr, bool readonly, MemoryRegion *mrp);
int (*dma_unmap)(const VFIOContainerBase *bcontainer,
hwaddr iova, ram_addr_t size,
IOMMUTLBEntry *iotlb);
diff --git a/system/memory.c b/system/memory.c
index 4c829793a0..de4f955a66 100644
--- a/system/memory.c
+++ b/system/memory.c
@@ -2185,7 +2185,8 @@ void ram_discard_manager_unregister_listener(RamDiscardManager *rdm,
/* Called with rcu_read_lock held. */
bool memory_get_xlat_addr(IOMMUTLBEntry *iotlb, void **vaddr,
ram_addr_t *ram_addr, bool *read_only,
- bool *mr_has_discard_manager, Error **errp)
+ bool *mr_has_discard_manager, MemoryRegion **mrp,
+ Error **errp)
{
MemoryRegion *mr;
hwaddr xlat;
@@ -2250,6 +2251,10 @@ bool memory_get_xlat_addr(IOMMUTLBEntry *iotlb, void **vaddr,
*read_only = !writable || mr->readonly;
}
+ if (mrp != NULL) {
+ *mrp = mr;
+ }
+
return true;
}
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* Re: [PATCH v8 01/28] vfio/container: pass MemoryRegion to DMA operations
2025-02-19 14:48 ` [PATCH v8 01/28] vfio/container: pass MemoryRegion to DMA operations John Levon
@ 2025-04-02 16:44 ` Cédric Le Goater
0 siblings, 0 replies; 64+ messages in thread
From: Cédric Le Goater @ 2025-04-02 16:44 UTC (permalink / raw)
To: John Levon, qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin,
Jagannathan Raman, John Johnson, Elena Ufimtseva
On 2/19/25 15:48, John Levon wrote:
> From: Jagannathan Raman <jag.raman@oracle.com>
>
> Pass through the MemoryRegion to DMA operation handlers of vfio
> containers. The vfio-user container will need this later.
>
> 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>
FYI, in case you didn't see the discussion here :
https://lore.kernel.org/qemu-devel/1739542467-226739-29-git-send-email-steven.sistare@oracle.com/
Thanks,
C.
> ---
> hw/vfio/common.c | 17 ++++++++++-------
> hw/vfio/container-base.c | 4 ++--
> hw/vfio/container.c | 3 ++-
> hw/vfio/iommufd.c | 3 ++-
> hw/virtio/vhost-vdpa.c | 2 +-
> include/exec/memory.h | 4 +++-
> include/hw/vfio/vfio-container-base.h | 4 ++--
> system/memory.c | 7 ++++++-
> 8 files changed, 28 insertions(+), 16 deletions(-)
>
> diff --git a/hw/vfio/common.c b/hw/vfio/common.c
> index abbdc56b6d..8d3d425c63 100644
> --- a/hw/vfio/common.c
> +++ b/hw/vfio/common.c
> @@ -248,12 +248,12 @@ static bool vfio_listener_skipped_section(MemoryRegionSection *section)
> /* Called with rcu_read_lock held. */
> static bool vfio_get_xlat_addr(IOMMUTLBEntry *iotlb, void **vaddr,
> ram_addr_t *ram_addr, bool *read_only,
> - Error **errp)
> + MemoryRegion **mrp, Error **errp)
> {
> bool ret, mr_has_discard_manager;
>
> ret = memory_get_xlat_addr(iotlb, vaddr, ram_addr, read_only,
> - &mr_has_discard_manager, errp);
> + &mr_has_discard_manager, mrp, errp);
> if (ret && mr_has_discard_manager) {
> /*
> * Malicious VMs might trigger discarding of IOMMU-mapped memory. The
> @@ -281,6 +281,7 @@ static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
> VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, n);
> VFIOContainerBase *bcontainer = giommu->bcontainer;
> hwaddr iova = iotlb->iova + giommu->iommu_offset;
> + MemoryRegion *mrp;
> void *vaddr;
> int ret;
> Error *local_err = NULL;
> @@ -300,7 +301,8 @@ static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
> if ((iotlb->perm & IOMMU_RW) != IOMMU_NONE) {
> bool read_only;
>
> - if (!vfio_get_xlat_addr(iotlb, &vaddr, NULL, &read_only, &local_err)) {
> + if (!vfio_get_xlat_addr(iotlb, &vaddr, NULL, &read_only, &mrp,
> + &local_err)) {
> error_report_err(local_err);
> goto out;
> }
> @@ -313,7 +315,7 @@ 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, mrp);
> if (ret) {
> error_report("vfio_container_dma_map(%p, 0x%"HWADDR_PRIx", "
> "0x%"HWADDR_PRIx", %p) = %d (%s)",
> @@ -378,7 +380,7 @@ 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);
> @@ -675,7 +677,7 @@ 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)",
> @@ -1232,7 +1234,8 @@ static void vfio_iommu_map_dirty_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
> }
>
> rcu_read_lock();
> - if (!vfio_get_xlat_addr(iotlb, NULL, &translated_addr, NULL, &local_err)) {
> + if (!vfio_get_xlat_addr(iotlb, NULL, &translated_addr, NULL, NULL,
> + &local_err)) {
> error_report_err(local_err);
> goto out_unlock;
> }
> diff --git a/hw/vfio/container-base.c b/hw/vfio/container-base.c
> index 749a3fd29d..5e0c9700d9 100644
> --- a/hw/vfio/container-base.c
> +++ b/hw/vfio/container-base.c
> @@ -17,12 +17,12 @@
>
> 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 7c57bdd27b..0db0055f39 100644
> --- a/hw/vfio/container.c
> +++ b/hw/vfio/container.c
> @@ -175,7 +175,8 @@ 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 df61edffc0..583b063707 100644
> --- a/hw/vfio/iommufd.c
> +++ b/hw/vfio/iommufd.c
> @@ -28,7 +28,8 @@
> #include "exec/ram_addr.h"
>
> 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/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c
> index 3cdaa12ed5..a1866bb396 100644
> --- a/hw/virtio/vhost-vdpa.c
> +++ b/hw/virtio/vhost-vdpa.c
> @@ -228,7 +228,7 @@ static void vhost_vdpa_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
> if ((iotlb->perm & IOMMU_RW) != IOMMU_NONE) {
> bool read_only;
>
> - if (!memory_get_xlat_addr(iotlb, &vaddr, NULL, &read_only, NULL,
> + if (!memory_get_xlat_addr(iotlb, &vaddr, NULL, &read_only, NULL, NULL,
> &local_err)) {
> error_report_err(local_err);
> return;
> diff --git a/include/exec/memory.h b/include/exec/memory.h
> index 9f73b59867..adaf1d1ca4 100644
> --- a/include/exec/memory.h
> +++ b/include/exec/memory.h
> @@ -747,13 +747,15 @@ void ram_discard_manager_unregister_listener(RamDiscardManager *rdm,
> * @read_only: indicates if writes are allowed
> * @mr_has_discard_manager: indicates memory is controlled by a
> * RamDiscardManager
> + * @mrp: if non-NULL, fill in with MemoryRegion
> * @errp: pointer to Error*, to store an error if it happens.
> *
> * Return: true on success, else false setting @errp with error.
> */
> bool memory_get_xlat_addr(IOMMUTLBEntry *iotlb, void **vaddr,
> ram_addr_t *ram_addr, bool *read_only,
> - bool *mr_has_discard_manager, Error **errp);
> + bool *mr_has_discard_manager, MemoryRegion **mrp,
> + Error **errp);
>
> typedef struct CoalescedMemoryRange CoalescedMemoryRange;
> typedef struct MemoryRegionIoeventfd MemoryRegionIoeventfd;
> diff --git a/include/hw/vfio/vfio-container-base.h b/include/hw/vfio/vfio-container-base.h
> index 4cff9943ab..c9d339383e 100644
> --- a/include/hw/vfio/vfio-container-base.h
> +++ b/include/hw/vfio/vfio-container-base.h
> @@ -73,7 +73,7 @@ typedef struct VFIORamDiscardListener {
>
> 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);
> @@ -113,7 +113,7 @@ struct VFIOIOMMUClass {
> bool (*setup)(VFIOContainerBase *bcontainer, Error **errp);
> int (*dma_map)(const VFIOContainerBase *bcontainer,
> hwaddr iova, ram_addr_t size,
> - void *vaddr, bool readonly);
> + void *vaddr, bool readonly, MemoryRegion *mrp);
> int (*dma_unmap)(const VFIOContainerBase *bcontainer,
> hwaddr iova, ram_addr_t size,
> IOMMUTLBEntry *iotlb);
> diff --git a/system/memory.c b/system/memory.c
> index 4c829793a0..de4f955a66 100644
> --- a/system/memory.c
> +++ b/system/memory.c
> @@ -2185,7 +2185,8 @@ void ram_discard_manager_unregister_listener(RamDiscardManager *rdm,
> /* Called with rcu_read_lock held. */
> bool memory_get_xlat_addr(IOMMUTLBEntry *iotlb, void **vaddr,
> ram_addr_t *ram_addr, bool *read_only,
> - bool *mr_has_discard_manager, Error **errp)
> + bool *mr_has_discard_manager, MemoryRegion **mrp,
> + Error **errp)
> {
> MemoryRegion *mr;
> hwaddr xlat;
> @@ -2250,6 +2251,10 @@ bool memory_get_xlat_addr(IOMMUTLBEntry *iotlb, void **vaddr,
> *read_only = !writable || mr->readonly;
> }
>
> + if (mrp != NULL) {
> + *mrp = mr;
> + }
> +
> return true;
> }
>
^ permalink raw reply [flat|nested] 64+ messages in thread
* [PATCH v8 02/28] vfio/container: pass listener_begin/commit callbacks
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
2025-02-19 14:48 ` [PATCH v8 01/28] vfio/container: pass MemoryRegion to DMA operations John Levon
@ 2025-02-19 14:48 ` John Levon
2025-04-02 12:30 ` Cédric Le Goater
2025-02-19 14:48 ` [PATCH v8 03/28] vfio/container: support VFIO_DMA_UNMAP_FLAG_ALL John Levon
` (28 subsequent siblings)
30 siblings, 1 reply; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin, John Levon
From: John Levon <levon@movementarian.org>
The vfio-user container will later need to hook into these callbacks;
set up vfio to use them, and optionally pass them through to the
container.
Signed-off-by: John Levon <john.levon@nutanix.com>
---
hw/vfio/common.c | 28 +++++++++++++++++++++++++++
include/hw/vfio/vfio-container-base.h | 2 ++
2 files changed, 30 insertions(+)
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 8d3d425c63..6f106167fd 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -557,6 +557,32 @@ static bool vfio_get_section_iova_range(VFIOContainerBase *bcontainer,
return true;
}
+static void vfio_listener_begin(MemoryListener *listener)
+{
+ VFIOContainerBase *bcontainer = container_of(listener, VFIOContainerBase,
+ listener);
+ void (*listener_begin)(VFIOContainerBase *bcontainer);
+
+ listener_begin = VFIO_IOMMU_GET_CLASS(bcontainer)->listener_begin;
+
+ if (listener_begin) {
+ listener_begin(bcontainer);
+ }
+}
+
+static void vfio_listener_commit(MemoryListener *listener)
+{
+ VFIOContainerBase *bcontainer = container_of(listener, VFIOContainerBase,
+ listener);
+ void (*listener_commit)(VFIOContainerBase *bcontainer);
+
+ listener_commit = VFIO_IOMMU_GET_CLASS(bcontainer)->listener_begin;
+
+ if (listener_commit) {
+ listener_commit(bcontainer);
+ }
+}
+
static void vfio_device_error_append(VFIODevice *vbasedev, Error **errp)
{
/*
@@ -1396,6 +1422,8 @@ static void vfio_listener_log_sync(MemoryListener *listener,
const MemoryListener vfio_memory_listener = {
.name = "vfio",
+ .begin = vfio_listener_begin,
+ .commit = vfio_listener_commit,
.region_add = vfio_listener_region_add,
.region_del = vfio_listener_region_del,
.log_global_start = vfio_listener_log_global_start,
diff --git a/include/hw/vfio/vfio-container-base.h b/include/hw/vfio/vfio-container-base.h
index c9d339383e..0a863df0dc 100644
--- a/include/hw/vfio/vfio-container-base.h
+++ b/include/hw/vfio/vfio-container-base.h
@@ -111,6 +111,8 @@ struct VFIOIOMMUClass {
/* basic feature */
bool (*setup)(VFIOContainerBase *bcontainer, Error **errp);
+ void (*listener_begin)(VFIOContainerBase *bcontainer);
+ void (*listener_commit)(VFIOContainerBase *bcontainer);
int (*dma_map)(const VFIOContainerBase *bcontainer,
hwaddr iova, ram_addr_t size,
void *vaddr, bool readonly, MemoryRegion *mrp);
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* Re: [PATCH v8 02/28] vfio/container: pass listener_begin/commit callbacks
2025-02-19 14:48 ` [PATCH v8 02/28] vfio/container: pass listener_begin/commit callbacks John Levon
@ 2025-04-02 12:30 ` Cédric Le Goater
0 siblings, 0 replies; 64+ messages in thread
From: Cédric Le Goater @ 2025-04-02 12:30 UTC (permalink / raw)
To: John Levon, qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin, John Levon
On 2/19/25 15:48, John Levon wrote:
> From: John Levon <levon@movementarian.org>
>
> The vfio-user container will later need to hook into these callbacks;
> set up vfio to use them, and optionally pass them through to the
> container.
>
> Signed-off-by: John Levon <john.levon@nutanix.com>
Looks ok. The future respin of this series will need to add routines
to register the begin and commit callbacks.
> ---
> hw/vfio/common.c | 28 +++++++++++++++++++++++++++
> include/hw/vfio/vfio-container-base.h | 2 ++
> 2 files changed, 30 insertions(+)
>
> diff --git a/hw/vfio/common.c b/hw/vfio/common.c
> index 8d3d425c63..6f106167fd 100644
> --- a/hw/vfio/common.c
> +++ b/hw/vfio/common.c
> @@ -557,6 +557,32 @@ static bool vfio_get_section_iova_range(VFIOContainerBase *bcontainer,
> return true;
> }
>
> +static void vfio_listener_begin(MemoryListener *listener)
> +{
> + VFIOContainerBase *bcontainer = container_of(listener, VFIOContainerBase,
> + listener);
> + void (*listener_begin)(VFIOContainerBase *bcontainer);
> +
> + listener_begin = VFIO_IOMMU_GET_CLASS(bcontainer)->listener_begin;
> +
> + if (listener_begin) {
> + listener_begin(bcontainer);
> + }
> +}
> +
> +static void vfio_listener_commit(MemoryListener *listener)
> +{
> + VFIOContainerBase *bcontainer = container_of(listener, VFIOContainerBase,
> + listener);
> + void (*listener_commit)(VFIOContainerBase *bcontainer);
> +
> + listener_commit = VFIO_IOMMU_GET_CLASS(bcontainer)->listener_begin;
> +
> + if (listener_commit) {
> + listener_commit(bcontainer);
> + }
> +}
> +
> static void vfio_device_error_append(VFIODevice *vbasedev, Error **errp)
> {
> /*
> @@ -1396,6 +1422,8 @@ static void vfio_listener_log_sync(MemoryListener *listener,
>
> const MemoryListener vfio_memory_listener = {
> .name = "vfio",
> + .begin = vfio_listener_begin,
> + .commit = vfio_listener_commit,
> .region_add = vfio_listener_region_add,
> .region_del = vfio_listener_region_del,
> .log_global_start = vfio_listener_log_global_start,
> diff --git a/include/hw/vfio/vfio-container-base.h b/include/hw/vfio/vfio-container-base.h
> index c9d339383e..0a863df0dc 100644
> --- a/include/hw/vfio/vfio-container-base.h
> +++ b/include/hw/vfio/vfio-container-base.h
> @@ -111,6 +111,8 @@ struct VFIOIOMMUClass {
>
> /* basic feature */
> bool (*setup)(VFIOContainerBase *bcontainer, Error **errp);
> + void (*listener_begin)(VFIOContainerBase *bcontainer);
> + void (*listener_commit)(VFIOContainerBase *bcontainer);
> int (*dma_map)(const VFIOContainerBase *bcontainer,
> hwaddr iova, ram_addr_t size,
> void *vaddr, bool readonly, MemoryRegion *mrp);
VFIOIOMMUClass needs more documentation. Please add some for
these new callbacks. Adding a comment saying that these callbacks
are for vfio-user would be appreciated.
Thanks,
C.
^ permalink raw reply [flat|nested] 64+ messages in thread
* [PATCH v8 03/28] vfio/container: support VFIO_DMA_UNMAP_FLAG_ALL
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
2025-02-19 14:48 ` [PATCH v8 01/28] vfio/container: pass MemoryRegion to DMA operations John Levon
2025-02-19 14:48 ` [PATCH v8 02/28] vfio/container: pass listener_begin/commit callbacks John Levon
@ 2025-02-19 14:48 ` John Levon
2025-04-02 16:49 ` Cédric Le Goater
2025-02-19 14:48 ` [PATCH v8 04/28] vfio: add vfio_attach_device_by_iommu_type() John Levon
` (27 subsequent siblings)
30 siblings, 1 reply; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin, John Johnson, Elena Ufimtseva,
Jagannathan Raman
Some containers can directly implement unmapping all regions;
add a new flag to support this.
Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
---
hw/vfio/common.c | 24 +++++++----------
hw/vfio/container-base.c | 4 +--
hw/vfio/container.c | 38 +++++++++++++++++++++++++--
hw/vfio/iommufd.c | 19 +++++++++++++-
include/hw/vfio/vfio-common.h | 1 +
include/hw/vfio/vfio-container-base.h | 4 +--
6 files changed, 68 insertions(+), 22 deletions(-)
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 6f106167fd..b49aafc40c 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -324,7 +324,7 @@ static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
}
} else {
ret = vfio_container_dma_unmap(bcontainer, iova,
- iotlb->addr_mask + 1, iotlb);
+ iotlb->addr_mask + 1, iotlb, 0);
if (ret) {
error_report("vfio_container_dma_unmap(%p, 0x%"HWADDR_PRIx", "
"0x%"HWADDR_PRIx") = %d (%s)",
@@ -348,7 +348,7 @@ static void vfio_ram_discard_notify_discard(RamDiscardListener *rdl,
int ret;
/* Unmap with a single call. */
- ret = vfio_container_dma_unmap(bcontainer, iova, size , NULL);
+ ret = vfio_container_dma_unmap(bcontainer, iova, size, NULL, 0);
if (ret) {
error_report("%s: vfio_container_dma_unmap() failed: %s", __func__,
strerror(-ret));
@@ -806,21 +806,15 @@ static void vfio_listener_region_del(MemoryListener *listener,
}
if (try_unmap) {
+ int flags = 0;
+
if (int128_eq(llsize, int128_2_64())) {
- /* The unmap ioctl doesn't accept a full 64-bit span. */
- llsize = int128_rshift(llsize, 1);
- ret = vfio_container_dma_unmap(bcontainer, iova,
- int128_get64(llsize), NULL);
- if (ret) {
- error_report("vfio_container_dma_unmap(%p, 0x%"HWADDR_PRIx", "
- "0x%"HWADDR_PRIx") = %d (%s)",
- bcontainer, iova, int128_get64(llsize), ret,
- strerror(-ret));
- }
- iova += int128_get64(llsize);
+ flags = VFIO_DMA_UNMAP_FLAG_ALL;
}
- ret = vfio_container_dma_unmap(bcontainer, iova,
- int128_get64(llsize), NULL);
+
+ ret = vfio_container_dma_unmap(bcontainer, iova, int128_get64(llsize),
+ NULL, flags);
+
if (ret) {
error_report("vfio_container_dma_unmap(%p, 0x%"HWADDR_PRIx", "
"0x%"HWADDR_PRIx") = %d (%s)",
diff --git a/hw/vfio/container-base.c b/hw/vfio/container-base.c
index 5e0c9700d9..db27e9c31d 100644
--- a/hw/vfio/container-base.c
+++ b/hw/vfio/container-base.c
@@ -27,12 +27,12 @@ int vfio_container_dma_map(VFIOContainerBase *bcontainer,
int vfio_container_dma_unmap(VFIOContainerBase *bcontainer,
hwaddr iova, ram_addr_t size,
- IOMMUTLBEntry *iotlb)
+ IOMMUTLBEntry *iotlb, int flags)
{
VFIOIOMMUClass *vioc = VFIO_IOMMU_GET_CLASS(bcontainer);
g_assert(vioc->dma_unmap);
- return vioc->dma_unmap(bcontainer, iova, size, iotlb);
+ return vioc->dma_unmap(bcontainer, iova, size, iotlb, flags);
}
bool vfio_container_add_section_window(VFIOContainerBase *bcontainer,
diff --git a/hw/vfio/container.c b/hw/vfio/container.c
index 0db0055f39..82987063e5 100644
--- a/hw/vfio/container.c
+++ b/hw/vfio/container.c
@@ -117,7 +117,7 @@ unmap_exit:
*/
static int vfio_legacy_dma_unmap(const VFIOContainerBase *bcontainer,
hwaddr iova, ram_addr_t size,
- IOMMUTLBEntry *iotlb)
+ IOMMUTLBEntry *iotlb, int flags)
{
const VFIOContainer *container = container_of(bcontainer, VFIOContainer,
bcontainer);
@@ -140,6 +140,34 @@ static int vfio_legacy_dma_unmap(const VFIOContainerBase *bcontainer,
need_dirty_sync = true;
}
+ /* use unmap all if supported */
+ if (flags & VFIO_DMA_UNMAP_FLAG_ALL) {
+ unmap.iova = 0;
+ unmap.size = 0;
+ if (container->unmap_all_supported) {
+ ret = ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, unmap);
+ } else {
+ /* unmap in halves */
+ Int128 llsize = int128_rshift(int128_2_64(), 1);
+
+ unmap.size = int128_get64(llsize);
+
+ ret = ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, unmap);
+
+ if (ret == 0) {
+ unmap.iova += int128_get64(llsize);
+
+ ret = ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, unmap);
+ }
+ }
+
+ if (ret != 0) {
+ return -errno;
+ }
+
+ goto out;
+ }
+
while (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) {
/*
* The type1 backend has an off-by-one bug in the kernel (71a7d3d78e3c
@@ -162,6 +190,7 @@ static int vfio_legacy_dma_unmap(const VFIOContainerBase *bcontainer,
return -errno;
}
+out:
if (need_dirty_sync) {
ret = vfio_get_dirty_bitmap(bcontainer, iova, size,
iotlb->translated_addr, &local_err);
@@ -199,7 +228,7 @@ static int vfio_legacy_dma_map(const VFIOContainerBase *bcontainer, hwaddr iova,
*/
if (ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0 ||
(errno == EBUSY &&
- vfio_legacy_dma_unmap(bcontainer, iova, size, NULL) == 0 &&
+ vfio_legacy_dma_unmap(bcontainer, iova, size, NULL, 0) == 0 &&
ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0)) {
return 0;
}
@@ -533,6 +562,11 @@ static bool vfio_legacy_setup(VFIOContainerBase *bcontainer, Error **errp)
vfio_get_info_iova_range(info, bcontainer);
vfio_get_iommu_info_migration(container, info);
+
+ ret = ioctl(container->fd, VFIO_CHECK_EXTENSION, VFIO_UNMAP_ALL);
+
+ container->unmap_all_supported = (ret != 0);
+
return true;
}
diff --git a/hw/vfio/iommufd.c b/hw/vfio/iommufd.c
index 583b063707..e295f251c0 100644
--- a/hw/vfio/iommufd.c
+++ b/hw/vfio/iommufd.c
@@ -41,11 +41,28 @@ static int iommufd_cdev_map(const VFIOContainerBase *bcontainer, hwaddr iova,
static int iommufd_cdev_unmap(const VFIOContainerBase *bcontainer,
hwaddr iova, ram_addr_t size,
- IOMMUTLBEntry *iotlb)
+ IOMMUTLBEntry *iotlb, int flags)
{
const VFIOIOMMUFDContainer *container =
container_of(bcontainer, VFIOIOMMUFDContainer, bcontainer);
+ /* unmap in halves */
+ if (flags & VFIO_DMA_UNMAP_FLAG_ALL) {
+ Int128 llsize = int128_rshift(int128_2_64(), 1);
+ int ret;
+
+ ret = iommufd_backend_unmap_dma(container->be, container->ioas_id,
+ iova, int128_get64(llsize));
+ iova += int128_get64(llsize);
+
+ if (ret == 0) {
+ ret = iommufd_backend_unmap_dma(container->be, container->ioas_id,
+ iova, int128_get64(llsize));
+ }
+
+ return ret;
+ }
+
/* TODO: Handle dma_unmap_bitmap with iotlb args (migration) */
return iommufd_backend_unmap_dma(container->be,
container->ioas_id, iova, size);
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index ac35136a11..f4f08eb8a6 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -84,6 +84,7 @@ typedef struct VFIOContainer {
VFIOContainerBase bcontainer;
int fd; /* /dev/vfio/vfio, empowered by the attached groups */
unsigned iommu_type;
+ bool unmap_all_supported;
QLIST_HEAD(, VFIOGroup) group_list;
} VFIOContainer;
diff --git a/include/hw/vfio/vfio-container-base.h b/include/hw/vfio/vfio-container-base.h
index 0a863df0dc..24e48e3a07 100644
--- a/include/hw/vfio/vfio-container-base.h
+++ b/include/hw/vfio/vfio-container-base.h
@@ -76,7 +76,7 @@ int vfio_container_dma_map(VFIOContainerBase *bcontainer,
void *vaddr, bool readonly, MemoryRegion *mrp);
int vfio_container_dma_unmap(VFIOContainerBase *bcontainer,
hwaddr iova, ram_addr_t size,
- IOMMUTLBEntry *iotlb);
+ IOMMUTLBEntry *iotlb, int flags);
bool vfio_container_add_section_window(VFIOContainerBase *bcontainer,
MemoryRegionSection *section,
Error **errp);
@@ -118,7 +118,7 @@ struct VFIOIOMMUClass {
void *vaddr, bool readonly, MemoryRegion *mrp);
int (*dma_unmap)(const VFIOContainerBase *bcontainer,
hwaddr iova, ram_addr_t size,
- IOMMUTLBEntry *iotlb);
+ IOMMUTLBEntry *iotlb, int flags);
bool (*attach_device)(const char *name, VFIODevice *vbasedev,
AddressSpace *as, Error **errp);
void (*detach_device)(VFIODevice *vbasedev);
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* Re: [PATCH v8 03/28] vfio/container: support VFIO_DMA_UNMAP_FLAG_ALL
2025-02-19 14:48 ` [PATCH v8 03/28] vfio/container: support VFIO_DMA_UNMAP_FLAG_ALL John Levon
@ 2025-04-02 16:49 ` Cédric Le Goater
2025-04-03 9:45 ` John Levon
0 siblings, 1 reply; 64+ messages in thread
From: Cédric Le Goater @ 2025-04-02 16:49 UTC (permalink / raw)
To: John Levon, qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin, John Johnson,
Elena Ufimtseva, Jagannathan Raman
On 2/19/25 15:48, John Levon wrote:
> Some containers can directly implement unmapping all regions;
> add a new flag to support this.
>
> Originally-by: John Johnson <john.g.johnson@oracle.com>
> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
> Signed-off-by: John Levon <john.levon@nutanix.com>
> ---
> hw/vfio/common.c | 24 +++++++----------
> hw/vfio/container-base.c | 4 +--
> hw/vfio/container.c | 38 +++++++++++++++++++++++++--
> hw/vfio/iommufd.c | 19 +++++++++++++-
> include/hw/vfio/vfio-common.h | 1 +
> include/hw/vfio/vfio-container-base.h | 4 +--
> 6 files changed, 68 insertions(+), 22 deletions(-)
This is difficult to understand. There are no functional changes right ?
I think it should be broken down further to clarify the changes.
Thanks,
C.
> diff --git a/hw/vfio/common.c b/hw/vfio/common.c
> index 6f106167fd..b49aafc40c 100644
> --- a/hw/vfio/common.c
> +++ b/hw/vfio/common.c
> @@ -324,7 +324,7 @@ static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
> }
> } else {
> ret = vfio_container_dma_unmap(bcontainer, iova,
> - iotlb->addr_mask + 1, iotlb);
> + iotlb->addr_mask + 1, iotlb, 0);
> if (ret) {
> error_report("vfio_container_dma_unmap(%p, 0x%"HWADDR_PRIx", "
> "0x%"HWADDR_PRIx") = %d (%s)",
> @@ -348,7 +348,7 @@ static void vfio_ram_discard_notify_discard(RamDiscardListener *rdl,
> int ret;
>
> /* Unmap with a single call. */
> - ret = vfio_container_dma_unmap(bcontainer, iova, size , NULL);
> + ret = vfio_container_dma_unmap(bcontainer, iova, size, NULL, 0);
> if (ret) {
> error_report("%s: vfio_container_dma_unmap() failed: %s", __func__,
> strerror(-ret));
> @@ -806,21 +806,15 @@ static void vfio_listener_region_del(MemoryListener *listener,
> }
>
> if (try_unmap) {
> + int flags = 0;
> +
> if (int128_eq(llsize, int128_2_64())) {
> - /* The unmap ioctl doesn't accept a full 64-bit span. */
> - llsize = int128_rshift(llsize, 1);
> - ret = vfio_container_dma_unmap(bcontainer, iova,
> - int128_get64(llsize), NULL);
> - if (ret) {
> - error_report("vfio_container_dma_unmap(%p, 0x%"HWADDR_PRIx", "
> - "0x%"HWADDR_PRIx") = %d (%s)",
> - bcontainer, iova, int128_get64(llsize), ret,
> - strerror(-ret));
> - }
> - iova += int128_get64(llsize);
> + flags = VFIO_DMA_UNMAP_FLAG_ALL;
> }
> - ret = vfio_container_dma_unmap(bcontainer, iova,
> - int128_get64(llsize), NULL);
> +
> + ret = vfio_container_dma_unmap(bcontainer, iova, int128_get64(llsize),
> + NULL, flags);
> +
> if (ret) {
> error_report("vfio_container_dma_unmap(%p, 0x%"HWADDR_PRIx", "
> "0x%"HWADDR_PRIx") = %d (%s)",
> diff --git a/hw/vfio/container-base.c b/hw/vfio/container-base.c
> index 5e0c9700d9..db27e9c31d 100644
> --- a/hw/vfio/container-base.c
> +++ b/hw/vfio/container-base.c
> @@ -27,12 +27,12 @@ int vfio_container_dma_map(VFIOContainerBase *bcontainer,
>
> int vfio_container_dma_unmap(VFIOContainerBase *bcontainer,
> hwaddr iova, ram_addr_t size,
> - IOMMUTLBEntry *iotlb)
> + IOMMUTLBEntry *iotlb, int flags)
> {
> VFIOIOMMUClass *vioc = VFIO_IOMMU_GET_CLASS(bcontainer);
>
> g_assert(vioc->dma_unmap);
> - return vioc->dma_unmap(bcontainer, iova, size, iotlb);
> + return vioc->dma_unmap(bcontainer, iova, size, iotlb, flags);
> }
>
> bool vfio_container_add_section_window(VFIOContainerBase *bcontainer,
> diff --git a/hw/vfio/container.c b/hw/vfio/container.c
> index 0db0055f39..82987063e5 100644
> --- a/hw/vfio/container.c
> +++ b/hw/vfio/container.c
> @@ -117,7 +117,7 @@ unmap_exit:
> */
> static int vfio_legacy_dma_unmap(const VFIOContainerBase *bcontainer,
> hwaddr iova, ram_addr_t size,
> - IOMMUTLBEntry *iotlb)
> + IOMMUTLBEntry *iotlb, int flags)
> {
> const VFIOContainer *container = container_of(bcontainer, VFIOContainer,
> bcontainer);
> @@ -140,6 +140,34 @@ static int vfio_legacy_dma_unmap(const VFIOContainerBase *bcontainer,
> need_dirty_sync = true;
> }
>
> + /* use unmap all if supported */
> + if (flags & VFIO_DMA_UNMAP_FLAG_ALL) {
> + unmap.iova = 0;
> + unmap.size = 0;
> + if (container->unmap_all_supported) {
> + ret = ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, unmap);
> + } else {
> + /* unmap in halves */
> + Int128 llsize = int128_rshift(int128_2_64(), 1);
> +
> + unmap.size = int128_get64(llsize);
> +
> + ret = ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, unmap);
> +
> + if (ret == 0) {
> + unmap.iova += int128_get64(llsize);
> +
> + ret = ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, unmap);
> + }
> + }
> +
> + if (ret != 0) {
> + return -errno;
> + }
> +
> + goto out;
> + }
> +
> while (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) {
> /*
> * The type1 backend has an off-by-one bug in the kernel (71a7d3d78e3c
> @@ -162,6 +190,7 @@ static int vfio_legacy_dma_unmap(const VFIOContainerBase *bcontainer,
> return -errno;
> }
>
> +out:
> if (need_dirty_sync) {
> ret = vfio_get_dirty_bitmap(bcontainer, iova, size,
> iotlb->translated_addr, &local_err);
> @@ -199,7 +228,7 @@ static int vfio_legacy_dma_map(const VFIOContainerBase *bcontainer, hwaddr iova,
> */
> if (ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0 ||
> (errno == EBUSY &&
> - vfio_legacy_dma_unmap(bcontainer, iova, size, NULL) == 0 &&
> + vfio_legacy_dma_unmap(bcontainer, iova, size, NULL, 0) == 0 &&
> ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0)) {
> return 0;
> }
> @@ -533,6 +562,11 @@ static bool vfio_legacy_setup(VFIOContainerBase *bcontainer, Error **errp)
> vfio_get_info_iova_range(info, bcontainer);
>
> vfio_get_iommu_info_migration(container, info);
> +
> + ret = ioctl(container->fd, VFIO_CHECK_EXTENSION, VFIO_UNMAP_ALL);
> +
> + container->unmap_all_supported = (ret != 0);
> +
> return true;
> }
>
> diff --git a/hw/vfio/iommufd.c b/hw/vfio/iommufd.c
> index 583b063707..e295f251c0 100644
> --- a/hw/vfio/iommufd.c
> +++ b/hw/vfio/iommufd.c
> @@ -41,11 +41,28 @@ static int iommufd_cdev_map(const VFIOContainerBase *bcontainer, hwaddr iova,
>
> static int iommufd_cdev_unmap(const VFIOContainerBase *bcontainer,
> hwaddr iova, ram_addr_t size,
> - IOMMUTLBEntry *iotlb)
> + IOMMUTLBEntry *iotlb, int flags)
> {
> const VFIOIOMMUFDContainer *container =
> container_of(bcontainer, VFIOIOMMUFDContainer, bcontainer);
>
> + /* unmap in halves */
> + if (flags & VFIO_DMA_UNMAP_FLAG_ALL) {
> + Int128 llsize = int128_rshift(int128_2_64(), 1);
> + int ret;
> +
> + ret = iommufd_backend_unmap_dma(container->be, container->ioas_id,
> + iova, int128_get64(llsize));
> + iova += int128_get64(llsize);
> +
> + if (ret == 0) {
> + ret = iommufd_backend_unmap_dma(container->be, container->ioas_id,
> + iova, int128_get64(llsize));
> + }
> +
> + return ret;
> + }
> +
> /* TODO: Handle dma_unmap_bitmap with iotlb args (migration) */
> return iommufd_backend_unmap_dma(container->be,
> container->ioas_id, iova, size);
> diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
> index ac35136a11..f4f08eb8a6 100644
> --- a/include/hw/vfio/vfio-common.h
> +++ b/include/hw/vfio/vfio-common.h
> @@ -84,6 +84,7 @@ typedef struct VFIOContainer {
> VFIOContainerBase bcontainer;
> int fd; /* /dev/vfio/vfio, empowered by the attached groups */
> unsigned iommu_type;
> + bool unmap_all_supported;
> QLIST_HEAD(, VFIOGroup) group_list;
> } VFIOContainer;
>
> diff --git a/include/hw/vfio/vfio-container-base.h b/include/hw/vfio/vfio-container-base.h
> index 0a863df0dc..24e48e3a07 100644
> --- a/include/hw/vfio/vfio-container-base.h
> +++ b/include/hw/vfio/vfio-container-base.h
> @@ -76,7 +76,7 @@ int vfio_container_dma_map(VFIOContainerBase *bcontainer,
> void *vaddr, bool readonly, MemoryRegion *mrp);
> int vfio_container_dma_unmap(VFIOContainerBase *bcontainer,
> hwaddr iova, ram_addr_t size,
> - IOMMUTLBEntry *iotlb);
> + IOMMUTLBEntry *iotlb, int flags);
> bool vfio_container_add_section_window(VFIOContainerBase *bcontainer,
> MemoryRegionSection *section,
> Error **errp);
> @@ -118,7 +118,7 @@ struct VFIOIOMMUClass {
> void *vaddr, bool readonly, MemoryRegion *mrp);
> int (*dma_unmap)(const VFIOContainerBase *bcontainer,
> hwaddr iova, ram_addr_t size,
> - IOMMUTLBEntry *iotlb);
> + IOMMUTLBEntry *iotlb, int flags);
> bool (*attach_device)(const char *name, VFIODevice *vbasedev,
> AddressSpace *as, Error **errp);
> void (*detach_device)(VFIODevice *vbasedev);
^ permalink raw reply [flat|nested] 64+ messages in thread* Re: [PATCH v8 03/28] vfio/container: support VFIO_DMA_UNMAP_FLAG_ALL
2025-04-02 16:49 ` Cédric Le Goater
@ 2025-04-03 9:45 ` John Levon
2025-04-04 15:43 ` Cédric Le Goater
0 siblings, 1 reply; 64+ messages in thread
From: John Levon @ 2025-04-03 9:45 UTC (permalink / raw)
To: Cédric Le Goater
Cc: qemu-devel, Jason Herne, Thanos Makatos, Halil Pasic,
Daniel P. Berrangé, Eric Farman, Tony Krowiak, Thomas Huth,
qemu-s390x, Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin, John Johnson,
Elena Ufimtseva, Jagannathan Raman
On Wed, Apr 02, 2025 at 06:49:50PM +0200, Cédric Le Goater wrote:
> On 2/19/25 15:48, John Levon wrote:
> > Some containers can directly implement unmapping all regions;
> > add a new flag to support this.
> >
> > Originally-by: John Johnson <john.g.johnson@oracle.com>
> > Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
> > Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
> > Signed-off-by: John Levon <john.levon@nutanix.com>
> > ---
> > hw/vfio/common.c | 24 +++++++----------
> > hw/vfio/container-base.c | 4 +--
> > hw/vfio/container.c | 38 +++++++++++++++++++++++++--
> > hw/vfio/iommufd.c | 19 +++++++++++++-
> > include/hw/vfio/vfio-common.h | 1 +
> > include/hw/vfio/vfio-container-base.h | 4 +--
> > 6 files changed, 68 insertions(+), 22 deletions(-)
>
> This is difficult to understand. There are no functional changes right ?
+ ret = ioctl(container->fd, VFIO_CHECK_EXTENSION, VFIO_UNMAP_ALL);
This is new, we previously never even tried to use this.
> I think it should be broken down further to clarify the changes.
patch 1: add a flags param to the callbacks, always zero
patch 2: pass through unmap all flag to callbacks
patch 3: check for unmap_all extension and use it
That sound better?
regards
john
^ permalink raw reply [flat|nested] 64+ messages in thread
* Re: [PATCH v8 03/28] vfio/container: support VFIO_DMA_UNMAP_FLAG_ALL
2025-04-03 9:45 ` John Levon
@ 2025-04-04 15:43 ` Cédric Le Goater
0 siblings, 0 replies; 64+ messages in thread
From: Cédric Le Goater @ 2025-04-04 15:43 UTC (permalink / raw)
To: John Levon
Cc: qemu-devel, Jason Herne, Thanos Makatos, Halil Pasic,
Daniel P. Berrangé, Eric Farman, Tony Krowiak, Thomas Huth,
qemu-s390x, Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin, John Johnson,
Elena Ufimtseva, Jagannathan Raman
On 4/3/25 11:45, John Levon wrote:
> On Wed, Apr 02, 2025 at 06:49:50PM +0200, Cédric Le Goater wrote:
>
>> On 2/19/25 15:48, John Levon wrote:
>>> Some containers can directly implement unmapping all regions;
>>> add a new flag to support this.
>>>
>>> Originally-by: John Johnson <john.g.johnson@oracle.com>
>>> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
>>> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
>>> Signed-off-by: John Levon <john.levon@nutanix.com>
>>> ---
>>> hw/vfio/common.c | 24 +++++++----------
>>> hw/vfio/container-base.c | 4 +--
>>> hw/vfio/container.c | 38 +++++++++++++++++++++++++--
>>> hw/vfio/iommufd.c | 19 +++++++++++++-
>>> include/hw/vfio/vfio-common.h | 1 +
>>> include/hw/vfio/vfio-container-base.h | 4 +--
>>> 6 files changed, 68 insertions(+), 22 deletions(-)
>>
>> This is difficult to understand. There are no functional changes right ?
>
> + ret = ioctl(container->fd, VFIO_CHECK_EXTENSION, VFIO_UNMAP_ALL);
>
> This is new, we previously never even tried to use this.
>
>> I think it should be broken down further to clarify the changes.
>
> patch 1: add a flags param to the callbacks, always zero
> patch 2: pass through unmap all flag to callbacks
> patch 3: check for unmap_all extension and use it
>
> That sound better?
yes. Let's see at next respin.
Thanks,
C.
^ permalink raw reply [flat|nested] 64+ messages in thread
* [PATCH v8 04/28] vfio: add vfio_attach_device_by_iommu_type()
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (2 preceding siblings ...)
2025-02-19 14:48 ` [PATCH v8 03/28] vfio/container: support VFIO_DMA_UNMAP_FLAG_ALL John Levon
@ 2025-02-19 14:48 ` John Levon
2025-04-02 16:52 ` Cédric Le Goater
2025-02-19 14:48 ` [PATCH v8 05/28] vfio: add vfio_prepare_device() John Levon
` (26 subsequent siblings)
30 siblings, 1 reply; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin
Allow attachment by explicitly passing a TYPE_VFIO_IOMMU_* string;
vfio-user will use this later.
Signed-off-by: John Levon <john.levon@nutanix.com>
---
hw/vfio/common.c | 30 +++++++++++++++++++-----------
include/hw/vfio/vfio-common.h | 3 +++
2 files changed, 22 insertions(+), 11 deletions(-)
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index b49aafc40c..eefd735bc6 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -1569,25 +1569,20 @@ retry:
return info;
}
-bool vfio_attach_device(char *name, VFIODevice *vbasedev,
- AddressSpace *as, Error **errp)
+bool vfio_attach_device_by_iommu_type(const char *iommu_type, char *name,
+ VFIODevice *vbasedev, AddressSpace *as,
+ Error **errp)
{
- const VFIOIOMMUClass *ops =
- VFIO_IOMMU_CLASS(object_class_by_name(TYPE_VFIO_IOMMU_LEGACY));
HostIOMMUDevice *hiod = NULL;
-
- if (vbasedev->iommufd) {
- ops = VFIO_IOMMU_CLASS(object_class_by_name(TYPE_VFIO_IOMMU_IOMMUFD));
- }
-
- assert(ops);
-
+ const VFIOIOMMUClass *ops =
+ VFIO_IOMMU_CLASS(object_class_by_name(iommu_type));
if (!vbasedev->mdev) {
hiod = HOST_IOMMU_DEVICE(object_new(ops->hiod_typename));
vbasedev->hiod = hiod;
}
+
if (!ops->attach_device(name, vbasedev, as, errp)) {
object_unref(hiod);
vbasedev->hiod = NULL;
@@ -1597,6 +1592,19 @@ bool vfio_attach_device(char *name, VFIODevice *vbasedev,
return true;
}
+bool vfio_attach_device(char *name, VFIODevice *vbasedev,
+ AddressSpace *as, Error **errp)
+{
+ const char *iommu_type = TYPE_VFIO_IOMMU_LEGACY;
+
+ if (vbasedev->iommufd) {
+ iommu_type = TYPE_VFIO_IOMMU_IOMMUFD;
+ }
+
+ return vfio_attach_device_by_iommu_type(iommu_type, name, vbasedev,
+ as, errp);
+}
+
void vfio_detach_device(VFIODevice *vbasedev)
{
if (!vbasedev->bcontainer) {
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index f4f08eb8a6..c40f8de6bc 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -252,6 +252,9 @@ bool vfio_device_is_mdev(VFIODevice *vbasedev);
bool vfio_device_hiod_realize(VFIODevice *vbasedev, Error **errp);
bool vfio_attach_device(char *name, VFIODevice *vbasedev,
AddressSpace *as, Error **errp);
+bool vfio_attach_device_by_iommu_type(const char *iommu_type, char *name,
+ VFIODevice *vbasedev, AddressSpace *as,
+ Error **errp);
void vfio_detach_device(VFIODevice *vbasedev);
VFIODevice *vfio_get_vfio_device(Object *obj);
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* Re: [PATCH v8 04/28] vfio: add vfio_attach_device_by_iommu_type()
2025-02-19 14:48 ` [PATCH v8 04/28] vfio: add vfio_attach_device_by_iommu_type() John Levon
@ 2025-04-02 16:52 ` Cédric Le Goater
0 siblings, 0 replies; 64+ messages in thread
From: Cédric Le Goater @ 2025-04-02 16:52 UTC (permalink / raw)
To: John Levon, qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin
On 2/19/25 15:48, John Levon wrote:
> Allow attachment by explicitly passing a TYPE_VFIO_IOMMU_* string;
> vfio-user will use this later.
>
> Signed-off-by: John Levon <john.levon@nutanix.com>
> ---
> hw/vfio/common.c | 30 +++++++++++++++++++-----------
> include/hw/vfio/vfio-common.h | 3 +++
> 2 files changed, 22 insertions(+), 11 deletions(-)
>
> diff --git a/hw/vfio/common.c b/hw/vfio/common.c
> index b49aafc40c..eefd735bc6 100644
> --- a/hw/vfio/common.c
> +++ b/hw/vfio/common.c
> @@ -1569,25 +1569,20 @@ retry:
> return info;
> }
>
> -bool vfio_attach_device(char *name, VFIODevice *vbasedev,
> - AddressSpace *as, Error **errp)
> +bool vfio_attach_device_by_iommu_type(const char *iommu_type, char *name,
> + VFIODevice *vbasedev, AddressSpace *as,
> + Error **errp)
> {
> - const VFIOIOMMUClass *ops =
> - VFIO_IOMMU_CLASS(object_class_by_name(TYPE_VFIO_IOMMU_LEGACY));
> HostIOMMUDevice *hiod = NULL;
> -
> - if (vbasedev->iommufd) {
> - ops = VFIO_IOMMU_CLASS(object_class_by_name(TYPE_VFIO_IOMMU_IOMMUFD));
> - }
> -
> - assert(ops);
> -
> + const VFIOIOMMUClass *ops =
> + VFIO_IOMMU_CLASS(object_class_by_name(iommu_type));
>
> if (!vbasedev->mdev) {
> hiod = HOST_IOMMU_DEVICE(object_new(ops->hiod_typename));
> vbasedev->hiod = hiod;
> }
>
> +
please drop the extra line.
> if (!ops->attach_device(name, vbasedev, as, errp)) {
> object_unref(hiod);
> vbasedev->hiod = NULL;
> @@ -1597,6 +1592,19 @@ bool vfio_attach_device(char *name, VFIODevice *vbasedev,
> return true;
> }
>
> +bool vfio_attach_device(char *name, VFIODevice *vbasedev,
> + AddressSpace *as, Error **errp)
> +{
> + const char *iommu_type = TYPE_VFIO_IOMMU_LEGACY;
> +
> + if (vbasedev->iommufd) {
> + iommu_type = TYPE_VFIO_IOMMU_IOMMUFD;
> + }
May be use a ternary operator.
> + return vfio_attach_device_by_iommu_type(iommu_type, name, vbasedev,
> + as, errp);
> +}
> +
> void vfio_detach_device(VFIODevice *vbasedev)
> {
> if (!vbasedev->bcontainer) {
> diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
> index f4f08eb8a6..c40f8de6bc 100644
> --- a/include/hw/vfio/vfio-common.h
> +++ b/include/hw/vfio/vfio-common.h
> @@ -252,6 +252,9 @@ bool vfio_device_is_mdev(VFIODevice *vbasedev);
> bool vfio_device_hiod_realize(VFIODevice *vbasedev, Error **errp);
> bool vfio_attach_device(char *name, VFIODevice *vbasedev,
> AddressSpace *as, Error **errp);
> +bool vfio_attach_device_by_iommu_type(const char *iommu_type, char *name,
> + VFIODevice *vbasedev, AddressSpace *as,
> + Error **errp);
> void vfio_detach_device(VFIODevice *vbasedev);
> VFIODevice *vfio_get_vfio_device(Object *obj);
>
Looks OK. It will need a refresh because of the spring cleanup.
Thanks,
C.
^ permalink raw reply [flat|nested] 64+ messages in thread
* [PATCH v8 05/28] vfio: add vfio_prepare_device()
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (3 preceding siblings ...)
2025-02-19 14:48 ` [PATCH v8 04/28] vfio: add vfio_attach_device_by_iommu_type() John Levon
@ 2025-02-19 14:48 ` John Levon
2025-04-03 9:19 ` Cédric Le Goater
2025-02-19 14:48 ` [PATCH v8 06/28] vfio: refactor out vfio_interrupt_setup() John Levon
` (25 subsequent siblings)
30 siblings, 1 reply; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin
Commonize some initialization code shared by the legacy and iommufd vfio
implementations (and later by vfio-user).
Signed-off-by: John Levon <john.levon@nutanix.com>
---
hw/vfio/common.c | 19 +++++++++++++++++++
hw/vfio/container.c | 14 +-------------
hw/vfio/iommufd.c | 9 +--------
include/hw/vfio/vfio-common.h | 2 ++
4 files changed, 23 insertions(+), 21 deletions(-)
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index eefd735bc6..4434e0a0a2 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -1569,6 +1569,25 @@ retry:
return info;
}
+void vfio_prepare_device(VFIODevice *vbasedev, VFIOContainerBase *bcontainer,
+ VFIOGroup *group, struct vfio_device_info *info)
+{
+ vbasedev->group = group;
+
+ vbasedev->num_irqs = info->num_irqs;
+ vbasedev->num_regions = info->num_regions;
+ vbasedev->flags = info->flags;
+ vbasedev->reset_works = !!(info->flags & VFIO_DEVICE_FLAGS_RESET);
+
+ vbasedev->bcontainer = bcontainer;
+ QLIST_INSERT_HEAD(&bcontainer->device_list, vbasedev, container_next);
+ if (group) {
+ QLIST_INSERT_HEAD(&group->device_list, vbasedev, next);
+ }
+
+ QLIST_INSERT_HEAD(&vfio_device_list, vbasedev, global_next);
+}
+
bool vfio_attach_device_by_iommu_type(const char *iommu_type, char *name,
VFIODevice *vbasedev, AddressSpace *as,
Error **errp)
diff --git a/hw/vfio/container.c b/hw/vfio/container.c
index 82987063e5..37a3befbc5 100644
--- a/hw/vfio/container.c
+++ b/hw/vfio/container.c
@@ -876,17 +876,11 @@ static bool vfio_get_device(VFIOGroup *group, const char *name,
}
vbasedev->fd = fd;
- vbasedev->group = group;
- QLIST_INSERT_HEAD(&group->device_list, vbasedev, next);
- vbasedev->num_irqs = info->num_irqs;
- vbasedev->num_regions = info->num_regions;
- vbasedev->flags = info->flags;
+ vfio_prepare_device(vbasedev, &group->container->bcontainer, group, info);
trace_vfio_get_device(name, info->flags, info->num_regions, info->num_irqs);
- vbasedev->reset_works = !!(info->flags & VFIO_DEVICE_FLAGS_RESET);
-
return true;
}
@@ -939,7 +933,6 @@ static bool vfio_legacy_attach_device(const char *name, VFIODevice *vbasedev,
int groupid = vfio_device_groupid(vbasedev, errp);
VFIODevice *vbasedev_iter;
VFIOGroup *group;
- VFIOContainerBase *bcontainer;
if (groupid < 0) {
return false;
@@ -968,11 +961,6 @@ static bool vfio_legacy_attach_device(const char *name, VFIODevice *vbasedev,
return false;
}
- bcontainer = &group->container->bcontainer;
- vbasedev->bcontainer = bcontainer;
- QLIST_INSERT_HEAD(&bcontainer->device_list, vbasedev, container_next);
- QLIST_INSERT_HEAD(&vfio_device_list, vbasedev, global_next);
-
return true;
}
diff --git a/hw/vfio/iommufd.c b/hw/vfio/iommufd.c
index e295f251c0..85c70eae37 100644
--- a/hw/vfio/iommufd.c
+++ b/hw/vfio/iommufd.c
@@ -604,14 +604,7 @@ found_container:
iommufd_cdev_ram_block_discard_disable(false);
}
- vbasedev->group = 0;
- vbasedev->num_irqs = dev_info.num_irqs;
- vbasedev->num_regions = dev_info.num_regions;
- vbasedev->flags = dev_info.flags;
- vbasedev->reset_works = !!(dev_info.flags & VFIO_DEVICE_FLAGS_RESET);
- vbasedev->bcontainer = bcontainer;
- QLIST_INSERT_HEAD(&bcontainer->device_list, vbasedev, container_next);
- QLIST_INSERT_HEAD(&vfio_device_list, vbasedev, global_next);
+ vfio_prepare_device(vbasedev, bcontainer, NULL, &dev_info);
trace_iommufd_cdev_device_info(vbasedev->name, devfd, vbasedev->num_irqs,
vbasedev->num_regions, vbasedev->flags);
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index c40f8de6bc..ae3ecbd9f6 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -250,6 +250,8 @@ void vfio_reset_handler(void *opaque);
struct vfio_device_info *vfio_get_device_info(int fd);
bool vfio_device_is_mdev(VFIODevice *vbasedev);
bool vfio_device_hiod_realize(VFIODevice *vbasedev, Error **errp);
+void vfio_prepare_device(VFIODevice *vbasedev, VFIOContainerBase *bcontainer,
+ VFIOGroup *group, struct vfio_device_info *info);
bool vfio_attach_device(char *name, VFIODevice *vbasedev,
AddressSpace *as, Error **errp);
bool vfio_attach_device_by_iommu_type(const char *iommu_type, char *name,
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* Re: [PATCH v8 05/28] vfio: add vfio_prepare_device()
2025-02-19 14:48 ` [PATCH v8 05/28] vfio: add vfio_prepare_device() John Levon
@ 2025-04-03 9:19 ` Cédric Le Goater
2025-04-03 9:34 ` John Levon
0 siblings, 1 reply; 64+ messages in thread
From: Cédric Le Goater @ 2025-04-03 9:19 UTC (permalink / raw)
To: John Levon, qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin
On 2/19/25 15:48, John Levon wrote:
> Commonize some initialization code shared by the legacy and iommufd vfio
> implementations (and later by vfio-user).
>
> Signed-off-by: John Levon <john.levon@nutanix.com>
> ---
> hw/vfio/common.c | 19 +++++++++++++++++++
> hw/vfio/container.c | 14 +-------------
> hw/vfio/iommufd.c | 9 +--------
> include/hw/vfio/vfio-common.h | 2 ++
> 4 files changed, 23 insertions(+), 21 deletions(-)
>
> diff --git a/hw/vfio/common.c b/hw/vfio/common.c
> index eefd735bc6..4434e0a0a2 100644
> --- a/hw/vfio/common.c
> +++ b/hw/vfio/common.c
> @@ -1569,6 +1569,25 @@ retry:
> return info;
> }
>
> +void vfio_prepare_device(VFIODevice *vbasedev, VFIOContainerBase *bcontainer,
> + VFIOGroup *group, struct vfio_device_info *info)
I would prefer that the first version did not have a 'group' parameter.
Let's add it when needed.
Thanks,
C.
> +{
> + vbasedev->group = group;
> +
> + vbasedev->num_irqs = info->num_irqs;
> + vbasedev->num_regions = info->num_regions;
> + vbasedev->flags = info->flags;
> + vbasedev->reset_works = !!(info->flags & VFIO_DEVICE_FLAGS_RESET);
> +
> + vbasedev->bcontainer = bcontainer;
> + QLIST_INSERT_HEAD(&bcontainer->device_list, vbasedev, container_next);
> + if (group) {
> + QLIST_INSERT_HEAD(&group->device_list, vbasedev, next);
> + }
> +
> + QLIST_INSERT_HEAD(&vfio_device_list, vbasedev, global_next);
> +}
> +
> bool vfio_attach_device_by_iommu_type(const char *iommu_type, char *name,
> VFIODevice *vbasedev, AddressSpace *as,
> Error **errp)
> diff --git a/hw/vfio/container.c b/hw/vfio/container.c
> index 82987063e5..37a3befbc5 100644
> --- a/hw/vfio/container.c
> +++ b/hw/vfio/container.c
> @@ -876,17 +876,11 @@ static bool vfio_get_device(VFIOGroup *group, const char *name,
> }
>
> vbasedev->fd = fd;
> - vbasedev->group = group;
> - QLIST_INSERT_HEAD(&group->device_list, vbasedev, next);
>
> - vbasedev->num_irqs = info->num_irqs;
> - vbasedev->num_regions = info->num_regions;
> - vbasedev->flags = info->flags;
> + vfio_prepare_device(vbasedev, &group->container->bcontainer, group, info);
>
> trace_vfio_get_device(name, info->flags, info->num_regions, info->num_irqs);
>
> - vbasedev->reset_works = !!(info->flags & VFIO_DEVICE_FLAGS_RESET);
> -
> return true;
> }
>
> @@ -939,7 +933,6 @@ static bool vfio_legacy_attach_device(const char *name, VFIODevice *vbasedev,
> int groupid = vfio_device_groupid(vbasedev, errp);
> VFIODevice *vbasedev_iter;
> VFIOGroup *group;
> - VFIOContainerBase *bcontainer;
>
> if (groupid < 0) {
> return false;
> @@ -968,11 +961,6 @@ static bool vfio_legacy_attach_device(const char *name, VFIODevice *vbasedev,
> return false;
> }
>
> - bcontainer = &group->container->bcontainer;
> - vbasedev->bcontainer = bcontainer;
> - QLIST_INSERT_HEAD(&bcontainer->device_list, vbasedev, container_next);
> - QLIST_INSERT_HEAD(&vfio_device_list, vbasedev, global_next);
> -
> return true;
> }
>
> diff --git a/hw/vfio/iommufd.c b/hw/vfio/iommufd.c
> index e295f251c0..85c70eae37 100644
> --- a/hw/vfio/iommufd.c
> +++ b/hw/vfio/iommufd.c
> @@ -604,14 +604,7 @@ found_container:
> iommufd_cdev_ram_block_discard_disable(false);
> }
>
> - vbasedev->group = 0;
> - vbasedev->num_irqs = dev_info.num_irqs;
> - vbasedev->num_regions = dev_info.num_regions;
> - vbasedev->flags = dev_info.flags;
> - vbasedev->reset_works = !!(dev_info.flags & VFIO_DEVICE_FLAGS_RESET);
> - vbasedev->bcontainer = bcontainer;
> - QLIST_INSERT_HEAD(&bcontainer->device_list, vbasedev, container_next);
> - QLIST_INSERT_HEAD(&vfio_device_list, vbasedev, global_next);
> + vfio_prepare_device(vbasedev, bcontainer, NULL, &dev_info);
>
> trace_iommufd_cdev_device_info(vbasedev->name, devfd, vbasedev->num_irqs,
> vbasedev->num_regions, vbasedev->flags);
> diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
> index c40f8de6bc..ae3ecbd9f6 100644
> --- a/include/hw/vfio/vfio-common.h
> +++ b/include/hw/vfio/vfio-common.h
> @@ -250,6 +250,8 @@ void vfio_reset_handler(void *opaque);
> struct vfio_device_info *vfio_get_device_info(int fd);
> bool vfio_device_is_mdev(VFIODevice *vbasedev);
> bool vfio_device_hiod_realize(VFIODevice *vbasedev, Error **errp);
> +void vfio_prepare_device(VFIODevice *vbasedev, VFIOContainerBase *bcontainer,
> + VFIOGroup *group, struct vfio_device_info *info);
> bool vfio_attach_device(char *name, VFIODevice *vbasedev,
> AddressSpace *as, Error **errp);
> bool vfio_attach_device_by_iommu_type(const char *iommu_type, char *name,
^ permalink raw reply [flat|nested] 64+ messages in thread* Re: [PATCH v8 05/28] vfio: add vfio_prepare_device()
2025-04-03 9:19 ` Cédric Le Goater
@ 2025-04-03 9:34 ` John Levon
2025-04-04 15:41 ` Cédric Le Goater
0 siblings, 1 reply; 64+ messages in thread
From: John Levon @ 2025-04-03 9:34 UTC (permalink / raw)
To: Cédric Le Goater
Cc: qemu-devel, Jason Herne, Thanos Makatos, Halil Pasic,
Daniel P. Berrangé, Eric Farman, Tony Krowiak, Thomas Huth,
qemu-s390x, Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin
On Thu, Apr 03, 2025 at 11:19:34AM +0200, Cédric Le Goater wrote:
> On 2/19/25 15:48, John Levon wrote:
> > Commonize some initialization code shared by the legacy and iommufd vfio
> > implementations (and later by vfio-user).
> >
> > Signed-off-by: John Levon <john.levon@nutanix.com>
> > ---
> > hw/vfio/common.c | 19 +++++++++++++++++++
> > hw/vfio/container.c | 14 +-------------
> > hw/vfio/iommufd.c | 9 +--------
> > include/hw/vfio/vfio-common.h | 2 ++
> > 4 files changed, 23 insertions(+), 21 deletions(-)
> >
> > diff --git a/hw/vfio/common.c b/hw/vfio/common.c
> > index eefd735bc6..4434e0a0a2 100644
> > --- a/hw/vfio/common.c
> > +++ b/hw/vfio/common.c
> > @@ -1569,6 +1569,25 @@ retry:
> > return info;
> > }
> > +void vfio_prepare_device(VFIODevice *vbasedev, VFIOContainerBase *bcontainer,
> > + VFIOGroup *group, struct vfio_device_info *info)
>
> I would prefer that the first version did not have a 'group' parameter.
> Let's add it when needed.
I think you mean something like this in hw/vfio/container.c:
vfio_prepare_device(vbasedev, &group->container->bcontainer, info);
vbasedev->group = group;
QLIST_INSERT_HEAD(&group->device_list, vbasedev, next);
As it's the only consumer that actually wants a group.
thanks
john
^ permalink raw reply [flat|nested] 64+ messages in thread
* Re: [PATCH v8 05/28] vfio: add vfio_prepare_device()
2025-04-03 9:34 ` John Levon
@ 2025-04-04 15:41 ` Cédric Le Goater
2025-04-04 15:45 ` John Levon
0 siblings, 1 reply; 64+ messages in thread
From: Cédric Le Goater @ 2025-04-04 15:41 UTC (permalink / raw)
To: John Levon
Cc: qemu-devel, Jason Herne, Thanos Makatos, Halil Pasic,
Daniel P. Berrangé, Eric Farman, Tony Krowiak, Thomas Huth,
qemu-s390x, Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin
On 4/3/25 11:34, John Levon wrote:
> On Thu, Apr 03, 2025 at 11:19:34AM +0200, Cédric Le Goater wrote:
>
>> On 2/19/25 15:48, John Levon wrote:
>>> Commonize some initialization code shared by the legacy and iommufd vfio
>>> implementations (and later by vfio-user).
>>>
>>> Signed-off-by: John Levon <john.levon@nutanix.com>
>>> ---
>>> hw/vfio/common.c | 19 +++++++++++++++++++
>>> hw/vfio/container.c | 14 +-------------
>>> hw/vfio/iommufd.c | 9 +--------
>>> include/hw/vfio/vfio-common.h | 2 ++
>>> 4 files changed, 23 insertions(+), 21 deletions(-)
>>>
>>> diff --git a/hw/vfio/common.c b/hw/vfio/common.c
>>> index eefd735bc6..4434e0a0a2 100644
>>> --- a/hw/vfio/common.c
>>> +++ b/hw/vfio/common.c
>>> @@ -1569,6 +1569,25 @@ retry:
>>> return info;
>>> }
>>> +void vfio_prepare_device(VFIODevice *vbasedev, VFIOContainerBase *bcontainer,
>>> + VFIOGroup *group, struct vfio_device_info *info)
>>
>> I would prefer that the first version did not have a 'group' parameter.
>> Let's add it when needed.
>
> I think you mean something like this in hw/vfio/container.c:
>
> vfio_prepare_device(vbasedev, &group->container->bcontainer, info);
>
> vbasedev->group = group;
> QLIST_INSERT_HEAD(&group->device_list, vbasedev, next);
>
> As it's the only consumer that actually wants a group.
yes. It's a vfio legacy only construct. We will see what to do
if vfio-user needs it.
Thanks,
C.
^ permalink raw reply [flat|nested] 64+ messages in thread
* Re: [PATCH v8 05/28] vfio: add vfio_prepare_device()
2025-04-04 15:41 ` Cédric Le Goater
@ 2025-04-04 15:45 ` John Levon
0 siblings, 0 replies; 64+ messages in thread
From: John Levon @ 2025-04-04 15:45 UTC (permalink / raw)
To: Cédric Le Goater
Cc: qemu-devel, Jason Herne, Thanos Makatos, Halil Pasic,
Daniel P. Berrangé, Eric Farman, Tony Krowiak, Thomas Huth,
qemu-s390x, Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin
On Fri, Apr 04, 2025 at 05:41:54PM +0200, Cédric Le Goater wrote:
> > > > +void vfio_prepare_device(VFIODevice *vbasedev, VFIOContainerBase *bcontainer,
> > > > + VFIOGroup *group, struct vfio_device_info *info)
> > >
> > > I would prefer that the first version did not have a 'group' parameter.
> > > Let's add it when needed.
> >
> > I think you mean something like this in hw/vfio/container.c:
> >
> > vfio_prepare_device(vbasedev, &group->container->bcontainer, info);
> >
> > vbasedev->group = group;
> > QLIST_INSERT_HEAD(&group->device_list, vbasedev, next);
> >
> > As it's the only consumer that actually wants a group.
> yes. It's a vfio legacy only construct. We will see what to do
> if vfio-user needs it.
vfio-user is not going to need it for sure, so sounds good to me.
regards
john
^ permalink raw reply [flat|nested] 64+ messages in thread
* [PATCH v8 06/28] vfio: refactor out vfio_interrupt_setup()
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (4 preceding siblings ...)
2025-02-19 14:48 ` [PATCH v8 05/28] vfio: add vfio_prepare_device() John Levon
@ 2025-02-19 14:48 ` John Levon
2025-04-03 9:23 ` Cédric Le Goater
2025-02-19 14:48 ` [PATCH v8 07/28] vfio: refactor out vfio_pci_config_setup() John Levon
` (24 subsequent siblings)
30 siblings, 1 reply; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin
Refactor the interrupt setup code out of vfio_realize(), as we will
later need this for vfio-user too.
Signed-off-by: John Levon <john.levon@nutanix.com>
---
hw/vfio/pci.c | 54 +++++++++++++++++++++++++++++++--------------------
1 file changed, 33 insertions(+), 21 deletions(-)
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 89d900e9cf..5fb6c4c4c6 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -2957,6 +2957,37 @@ static void vfio_unregister_req_notifier(VFIOPCIDevice *vdev)
vdev->req_enabled = false;
}
+static bool vfio_interrupt_setup(VFIOPCIDevice *vdev, Error **errp)
+{
+ PCIDevice *pdev = &vdev->pdev;
+
+ /* QEMU emulates all of MSI & MSIX */
+ if (pdev->cap_present & QEMU_PCI_CAP_MSIX) {
+ memset(vdev->emulated_config_bits + pdev->msix_cap, 0xff,
+ MSIX_CAP_LENGTH);
+ }
+
+ if (pdev->cap_present & QEMU_PCI_CAP_MSI) {
+ memset(vdev->emulated_config_bits + pdev->msi_cap, 0xff,
+ vdev->msi_cap_size);
+ }
+
+ if (vfio_pci_read_config(&vdev->pdev, PCI_INTERRUPT_PIN, 1)) {
+ vdev->intx.mmap_timer = timer_new_ms(QEMU_CLOCK_VIRTUAL,
+ vfio_intx_mmap_enable, vdev);
+ pci_device_set_intx_routing_notifier(&vdev->pdev,
+ vfio_intx_routing_notifier);
+ vdev->irqchip_change_notifier.notify = vfio_irqchip_change;
+ kvm_irqchip_add_change_notifier(&vdev->irqchip_change_notifier);
+ if (!vfio_intx_enable(vdev, errp)) {
+ pci_device_set_intx_routing_notifier(&vdev->pdev, NULL);
+ kvm_irqchip_remove_change_notifier(&vdev->irqchip_change_notifier);
+ return false;
+ }
+ }
+ return true;
+}
+
static void vfio_realize(PCIDevice *pdev, Error **errp)
{
ERRP_GUARD();
@@ -3157,27 +3188,8 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
}
}
- /* QEMU emulates all of MSI & MSIX */
- if (pdev->cap_present & QEMU_PCI_CAP_MSIX) {
- memset(vdev->emulated_config_bits + pdev->msix_cap, 0xff,
- MSIX_CAP_LENGTH);
- }
-
- if (pdev->cap_present & QEMU_PCI_CAP_MSI) {
- memset(vdev->emulated_config_bits + pdev->msi_cap, 0xff,
- vdev->msi_cap_size);
- }
-
- if (vfio_pci_read_config(&vdev->pdev, PCI_INTERRUPT_PIN, 1)) {
- vdev->intx.mmap_timer = timer_new_ms(QEMU_CLOCK_VIRTUAL,
- vfio_intx_mmap_enable, vdev);
- pci_device_set_intx_routing_notifier(&vdev->pdev,
- vfio_intx_routing_notifier);
- vdev->irqchip_change_notifier.notify = vfio_irqchip_change;
- kvm_irqchip_add_change_notifier(&vdev->irqchip_change_notifier);
- if (!vfio_intx_enable(vdev, errp)) {
- goto out_deregister;
- }
+ if (!vfio_interrupt_setup(vdev, errp)) {
+ goto out_teardown;
}
if (vdev->display != ON_OFF_AUTO_OFF) {
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* Re: [PATCH v8 06/28] vfio: refactor out vfio_interrupt_setup()
2025-02-19 14:48 ` [PATCH v8 06/28] vfio: refactor out vfio_interrupt_setup() John Levon
@ 2025-04-03 9:23 ` Cédric Le Goater
2025-04-03 9:38 ` John Levon
0 siblings, 1 reply; 64+ messages in thread
From: Cédric Le Goater @ 2025-04-03 9:23 UTC (permalink / raw)
To: John Levon, qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin
On 2/19/25 15:48, John Levon wrote:
> Refactor the interrupt setup code out of vfio_realize(), as we will
> later need this for vfio-user too.
>
> Signed-off-by: John Levon <john.levon@nutanix.com>
> ---
> hw/vfio/pci.c | 54 +++++++++++++++++++++++++++++++--------------------
> 1 file changed, 33 insertions(+), 21 deletions(-)
>
> diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
> index 89d900e9cf..5fb6c4c4c6 100644
> --- a/hw/vfio/pci.c
> +++ b/hw/vfio/pci.c
> @@ -2957,6 +2957,37 @@ static void vfio_unregister_req_notifier(VFIOPCIDevice *vdev)
> vdev->req_enabled = false;
> }
>
> +static bool vfio_interrupt_setup(VFIOPCIDevice *vdev, Error **errp)
> +{
> + PCIDevice *pdev = &vdev->pdev;
> +
> + /* QEMU emulates all of MSI & MSIX */
> + if (pdev->cap_present & QEMU_PCI_CAP_MSIX) {
> + memset(vdev->emulated_config_bits + pdev->msix_cap, 0xff,
> + MSIX_CAP_LENGTH);
> + }
> +
> + if (pdev->cap_present & QEMU_PCI_CAP_MSI) {
> + memset(vdev->emulated_config_bits + pdev->msi_cap, 0xff,
> + vdev->msi_cap_size);
> + }
> +
> + if (vfio_pci_read_config(&vdev->pdev, PCI_INTERRUPT_PIN, 1)) {
> + vdev->intx.mmap_timer = timer_new_ms(QEMU_CLOCK_VIRTUAL,
> + vfio_intx_mmap_enable, vdev);
> + pci_device_set_intx_routing_notifier(&vdev->pdev,
> + vfio_intx_routing_notifier);
> + vdev->irqchip_change_notifier.notify = vfio_irqchip_change;
> + kvm_irqchip_add_change_notifier(&vdev->irqchip_change_notifier);
> + if (!vfio_intx_enable(vdev, errp)) {
> + pci_device_set_intx_routing_notifier(&vdev->pdev, NULL);
> + kvm_irqchip_remove_change_notifier(&vdev->irqchip_change_notifier);
> + return false;
> + }
> + }
> + return true;
> +}
> +
> static void vfio_realize(PCIDevice *pdev, Error **errp)
> {
> ERRP_GUARD();
> @@ -3157,27 +3188,8 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
> }
> }
>
> - /* QEMU emulates all of MSI & MSIX */
> - if (pdev->cap_present & QEMU_PCI_CAP_MSIX) {
> - memset(vdev->emulated_config_bits + pdev->msix_cap, 0xff,
> - MSIX_CAP_LENGTH);
> - }
> -
> - if (pdev->cap_present & QEMU_PCI_CAP_MSI) {
> - memset(vdev->emulated_config_bits + pdev->msi_cap, 0xff,
> - vdev->msi_cap_size);
> - }
> -
> - if (vfio_pci_read_config(&vdev->pdev, PCI_INTERRUPT_PIN, 1)) {
> - vdev->intx.mmap_timer = timer_new_ms(QEMU_CLOCK_VIRTUAL,
> - vfio_intx_mmap_enable, vdev);
> - pci_device_set_intx_routing_notifier(&vdev->pdev,
> - vfio_intx_routing_notifier);
> - vdev->irqchip_change_notifier.notify = vfio_irqchip_change;
> - kvm_irqchip_add_change_notifier(&vdev->irqchip_change_notifier);
> - if (!vfio_intx_enable(vdev, errp)) {
> - goto out_deregister;
> - }
> + if (!vfio_interrupt_setup(vdev, errp)) {
> + goto out_teardown;
is that the correct exit label ?
Thanks,
C.
> }
>
> if (vdev->display != ON_OFF_AUTO_OFF) {
^ permalink raw reply [flat|nested] 64+ messages in thread* Re: [PATCH v8 06/28] vfio: refactor out vfio_interrupt_setup()
2025-04-03 9:23 ` Cédric Le Goater
@ 2025-04-03 9:38 ` John Levon
0 siblings, 0 replies; 64+ messages in thread
From: John Levon @ 2025-04-03 9:38 UTC (permalink / raw)
To: Cédric Le Goater
Cc: qemu-devel, Jason Herne, Thanos Makatos, Halil Pasic,
Daniel P. Berrangé, Eric Farman, Tony Krowiak, Thomas Huth,
qemu-s390x, Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin
On Thu, Apr 03, 2025 at 11:23:09AM +0200, Cédric Le Goater wrote:
> On 2/19/25 15:48, John Levon wrote:
> > Refactor the interrupt setup code out of vfio_realize(), as we will
> > later need this for vfio-user too.
> >
> > Signed-off-by: John Levon <john.levon@nutanix.com>
> > static void vfio_realize(PCIDevice *pdev, Error **errp)
> > {
> > ERRP_GUARD();
> > @@ -3157,27 +3188,8 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
> > }
> > }
> > - /* QEMU emulates all of MSI & MSIX */
> > - if (pdev->cap_present & QEMU_PCI_CAP_MSIX) {
> > - memset(vdev->emulated_config_bits + pdev->msix_cap, 0xff,
> > - MSIX_CAP_LENGTH);
> > - }
> > -
> > - if (pdev->cap_present & QEMU_PCI_CAP_MSI) {
> > - memset(vdev->emulated_config_bits + pdev->msi_cap, 0xff,
> > - vdev->msi_cap_size);
> > - }
> > -
> > - if (vfio_pci_read_config(&vdev->pdev, PCI_INTERRUPT_PIN, 1)) {
> > - vdev->intx.mmap_timer = timer_new_ms(QEMU_CLOCK_VIRTUAL,
> > - vfio_intx_mmap_enable, vdev);
> > - pci_device_set_intx_routing_notifier(&vdev->pdev,
> > - vfio_intx_routing_notifier);
> > - vdev->irqchip_change_notifier.notify = vfio_irqchip_change;
> > - kvm_irqchip_add_change_notifier(&vdev->irqchip_change_notifier);
> > - if (!vfio_intx_enable(vdev, errp)) {
> > - goto out_deregister;
> > - }
> > + if (!vfio_interrupt_setup(vdev, errp)) {
> > + goto out_teardown;
>
> is that the correct exit label ?
Thanks, missed during rebase, it should be out_unset_idev
There is also a bug in the self-cleanup of vfio_interrupt_setup(): it's not
doing timer_free(vdev->intx.mmap_timer);
regards
john
^ permalink raw reply [flat|nested] 64+ messages in thread
* [PATCH v8 07/28] vfio: refactor out vfio_pci_config_setup()
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (5 preceding siblings ...)
2025-02-19 14:48 ` [PATCH v8 06/28] vfio: refactor out vfio_interrupt_setup() John Levon
@ 2025-02-19 14:48 ` John Levon
2025-04-03 9:30 ` Cédric Le Goater
2025-02-19 14:48 ` [PATCH v8 08/28] vfio: add region cache John Levon
` (23 subsequent siblings)
30 siblings, 1 reply; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin
Refactor the PCI config setup code out of vfio_realize(), as we will
later need this for vfio-user too.
Signed-off-by: John Levon <john.levon@nutanix.com>
---
hw/vfio/pci.c | 176 +++++++++++++++++++++++++++-----------------------
1 file changed, 94 insertions(+), 82 deletions(-)
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 5fb6c4c4c6..83fe329474 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -2957,6 +2957,99 @@ static void vfio_unregister_req_notifier(VFIOPCIDevice *vdev)
vdev->req_enabled = false;
}
+static bool vfio_pci_config_setup(VFIOPCIDevice *vdev, Error **errp)
+{
+ PCIDevice *pdev = &vdev->pdev;
+ VFIODevice *vbasedev = &vdev->vbasedev;
+
+ /* vfio emulates a lot for us, but some bits need extra love */
+ vdev->emulated_config_bits = g_malloc0(vdev->config_size);
+
+ /* QEMU can choose to expose the ROM or not */
+ memset(vdev->emulated_config_bits + PCI_ROM_ADDRESS, 0xff, 4);
+ /* QEMU can also add or extend BARs */
+ memset(vdev->emulated_config_bits + PCI_BASE_ADDRESS_0, 0xff, 6 * 4);
+
+ /*
+ * The PCI spec reserves vendor ID 0xffff as an invalid value. The
+ * device ID is managed by the vendor and need only be a 16-bit value.
+ * Allow any 16-bit value for subsystem so they can be hidden or changed.
+ */
+ if (vdev->vendor_id != PCI_ANY_ID) {
+ if (vdev->vendor_id >= 0xffff) {
+ error_setg(errp, "invalid PCI vendor ID provided");
+ return false;
+ }
+ vfio_add_emulated_word(vdev, PCI_VENDOR_ID, vdev->vendor_id, ~0);
+ trace_vfio_pci_emulated_vendor_id(vbasedev->name, vdev->vendor_id);
+ } else {
+ vdev->vendor_id = pci_get_word(pdev->config + PCI_VENDOR_ID);
+ }
+
+ if (vdev->device_id != PCI_ANY_ID) {
+ if (vdev->device_id > 0xffff) {
+ error_setg(errp, "invalid PCI device ID provided");
+ return false;
+ }
+ vfio_add_emulated_word(vdev, PCI_DEVICE_ID, vdev->device_id, ~0);
+ trace_vfio_pci_emulated_device_id(vbasedev->name, vdev->device_id);
+ } else {
+ vdev->device_id = pci_get_word(pdev->config + PCI_DEVICE_ID);
+ }
+
+ if (vdev->sub_vendor_id != PCI_ANY_ID) {
+ if (vdev->sub_vendor_id > 0xffff) {
+ error_setg(errp, "invalid PCI subsystem vendor ID provided");
+ return false;
+ }
+ vfio_add_emulated_word(vdev, PCI_SUBSYSTEM_VENDOR_ID,
+ vdev->sub_vendor_id, ~0);
+ trace_vfio_pci_emulated_sub_vendor_id(vbasedev->name,
+ vdev->sub_vendor_id);
+ }
+
+ if (vdev->sub_device_id != PCI_ANY_ID) {
+ if (vdev->sub_device_id > 0xffff) {
+ error_setg(errp, "invalid PCI subsystem device ID provided");
+ return false;
+ }
+ vfio_add_emulated_word(vdev, PCI_SUBSYSTEM_ID, vdev->sub_device_id, ~0);
+ trace_vfio_pci_emulated_sub_device_id(vbasedev->name,
+ vdev->sub_device_id);
+ }
+
+ /* QEMU can change multi-function devices to single function, or reverse */
+ vdev->emulated_config_bits[PCI_HEADER_TYPE] =
+ PCI_HEADER_TYPE_MULTI_FUNCTION;
+
+ /* Restore or clear multifunction, this is always controlled by QEMU */
+ if (vdev->pdev.cap_present & QEMU_PCI_CAP_MULTIFUNCTION) {
+ vdev->pdev.config[PCI_HEADER_TYPE] |= PCI_HEADER_TYPE_MULTI_FUNCTION;
+ } else {
+ vdev->pdev.config[PCI_HEADER_TYPE] &= ~PCI_HEADER_TYPE_MULTI_FUNCTION;
+ }
+
+ /*
+ * Clear host resource mapping info. If we choose not to register a
+ * BAR, such as might be the case with the option ROM, we can get
+ * confusing, unwritable, residual addresses from the host here.
+ */
+ memset(&vdev->pdev.config[PCI_BASE_ADDRESS_0], 0, 24);
+ memset(&vdev->pdev.config[PCI_ROM_ADDRESS], 0, 4);
+
+ vfio_pci_size_rom(vdev);
+
+ vfio_bars_prepare(vdev);
+
+ if (!vfio_msix_early_setup(vdev, errp)) {
+ return false;
+ }
+
+ vfio_bars_register(vdev);
+
+ return true;
+}
+
static bool vfio_interrupt_setup(VFIOPCIDevice *vdev, Error **errp)
{
PCIDevice *pdev = &vdev->pdev;
@@ -3060,91 +3153,10 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
goto error;
}
- /* vfio emulates a lot for us, but some bits need extra love */
- vdev->emulated_config_bits = g_malloc0(vdev->config_size);
-
- /* QEMU can choose to expose the ROM or not */
- memset(vdev->emulated_config_bits + PCI_ROM_ADDRESS, 0xff, 4);
- /* QEMU can also add or extend BARs */
- memset(vdev->emulated_config_bits + PCI_BASE_ADDRESS_0, 0xff, 6 * 4);
-
- /*
- * The PCI spec reserves vendor ID 0xffff as an invalid value. The
- * device ID is managed by the vendor and need only be a 16-bit value.
- * Allow any 16-bit value for subsystem so they can be hidden or changed.
- */
- if (vdev->vendor_id != PCI_ANY_ID) {
- if (vdev->vendor_id >= 0xffff) {
- error_setg(errp, "invalid PCI vendor ID provided");
- goto error;
- }
- vfio_add_emulated_word(vdev, PCI_VENDOR_ID, vdev->vendor_id, ~0);
- trace_vfio_pci_emulated_vendor_id(vbasedev->name, vdev->vendor_id);
- } else {
- vdev->vendor_id = pci_get_word(pdev->config + PCI_VENDOR_ID);
- }
-
- if (vdev->device_id != PCI_ANY_ID) {
- if (vdev->device_id > 0xffff) {
- error_setg(errp, "invalid PCI device ID provided");
- goto error;
- }
- vfio_add_emulated_word(vdev, PCI_DEVICE_ID, vdev->device_id, ~0);
- trace_vfio_pci_emulated_device_id(vbasedev->name, vdev->device_id);
- } else {
- vdev->device_id = pci_get_word(pdev->config + PCI_DEVICE_ID);
- }
-
- if (vdev->sub_vendor_id != PCI_ANY_ID) {
- if (vdev->sub_vendor_id > 0xffff) {
- error_setg(errp, "invalid PCI subsystem vendor ID provided");
- goto error;
- }
- vfio_add_emulated_word(vdev, PCI_SUBSYSTEM_VENDOR_ID,
- vdev->sub_vendor_id, ~0);
- trace_vfio_pci_emulated_sub_vendor_id(vbasedev->name,
- vdev->sub_vendor_id);
- }
-
- if (vdev->sub_device_id != PCI_ANY_ID) {
- if (vdev->sub_device_id > 0xffff) {
- error_setg(errp, "invalid PCI subsystem device ID provided");
- goto error;
- }
- vfio_add_emulated_word(vdev, PCI_SUBSYSTEM_ID, vdev->sub_device_id, ~0);
- trace_vfio_pci_emulated_sub_device_id(vbasedev->name,
- vdev->sub_device_id);
- }
-
- /* QEMU can change multi-function devices to single function, or reverse */
- vdev->emulated_config_bits[PCI_HEADER_TYPE] =
- PCI_HEADER_TYPE_MULTI_FUNCTION;
-
- /* Restore or clear multifunction, this is always controlled by QEMU */
- if (vdev->pdev.cap_present & QEMU_PCI_CAP_MULTIFUNCTION) {
- vdev->pdev.config[PCI_HEADER_TYPE] |= PCI_HEADER_TYPE_MULTI_FUNCTION;
- } else {
- vdev->pdev.config[PCI_HEADER_TYPE] &= ~PCI_HEADER_TYPE_MULTI_FUNCTION;
- }
-
- /*
- * Clear host resource mapping info. If we choose not to register a
- * BAR, such as might be the case with the option ROM, we can get
- * confusing, unwritable, residual addresses from the host here.
- */
- memset(&vdev->pdev.config[PCI_BASE_ADDRESS_0], 0, 24);
- memset(&vdev->pdev.config[PCI_ROM_ADDRESS], 0, 4);
-
- vfio_pci_size_rom(vdev);
-
- vfio_bars_prepare(vdev);
-
- if (!vfio_msix_early_setup(vdev, errp)) {
+ if (!vfio_pci_config_setup(vdev, errp)) {
goto error;
}
- vfio_bars_register(vdev);
-
if (!vbasedev->mdev &&
!pci_device_set_iommu_device(pdev, vbasedev->hiod, errp)) {
error_prepend(errp, "Failed to set vIOMMU: ");
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* Re: [PATCH v8 07/28] vfio: refactor out vfio_pci_config_setup()
2025-02-19 14:48 ` [PATCH v8 07/28] vfio: refactor out vfio_pci_config_setup() John Levon
@ 2025-04-03 9:30 ` Cédric Le Goater
0 siblings, 0 replies; 64+ messages in thread
From: Cédric Le Goater @ 2025-04-03 9:30 UTC (permalink / raw)
To: John Levon, qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin
On 2/19/25 15:48, John Levon wrote:
> Refactor the PCI config setup code out of vfio_realize(), as we will
> later need this for vfio-user too.
>
> Signed-off-by: John Levon <john.levon@nutanix.com>
We should have more of these routines to reduce vfio_realize(). It's
way too big.
This can be merged now.
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Thanks,
C.
> ---
> hw/vfio/pci.c | 176 +++++++++++++++++++++++++++-----------------------
> 1 file changed, 94 insertions(+), 82 deletions(-)
>
> diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
> index 5fb6c4c4c6..83fe329474 100644
> --- a/hw/vfio/pci.c
> +++ b/hw/vfio/pci.c
> @@ -2957,6 +2957,99 @@ static void vfio_unregister_req_notifier(VFIOPCIDevice *vdev)
> vdev->req_enabled = false;
> }
>
> +static bool vfio_pci_config_setup(VFIOPCIDevice *vdev, Error **errp)
> +{
> + PCIDevice *pdev = &vdev->pdev;
> + VFIODevice *vbasedev = &vdev->vbasedev;
> +
> + /* vfio emulates a lot for us, but some bits need extra love */
> + vdev->emulated_config_bits = g_malloc0(vdev->config_size);
> +
> + /* QEMU can choose to expose the ROM or not */
> + memset(vdev->emulated_config_bits + PCI_ROM_ADDRESS, 0xff, 4);
> + /* QEMU can also add or extend BARs */
> + memset(vdev->emulated_config_bits + PCI_BASE_ADDRESS_0, 0xff, 6 * 4);
> +
> + /*
> + * The PCI spec reserves vendor ID 0xffff as an invalid value. The
> + * device ID is managed by the vendor and need only be a 16-bit value.
> + * Allow any 16-bit value for subsystem so they can be hidden or changed.
> + */
> + if (vdev->vendor_id != PCI_ANY_ID) {
> + if (vdev->vendor_id >= 0xffff) {
> + error_setg(errp, "invalid PCI vendor ID provided");
> + return false;
> + }
> + vfio_add_emulated_word(vdev, PCI_VENDOR_ID, vdev->vendor_id, ~0);
> + trace_vfio_pci_emulated_vendor_id(vbasedev->name, vdev->vendor_id);
> + } else {
> + vdev->vendor_id = pci_get_word(pdev->config + PCI_VENDOR_ID);
> + }
> +
> + if (vdev->device_id != PCI_ANY_ID) {
> + if (vdev->device_id > 0xffff) {
> + error_setg(errp, "invalid PCI device ID provided");
> + return false;
> + }
> + vfio_add_emulated_word(vdev, PCI_DEVICE_ID, vdev->device_id, ~0);
> + trace_vfio_pci_emulated_device_id(vbasedev->name, vdev->device_id);
> + } else {
> + vdev->device_id = pci_get_word(pdev->config + PCI_DEVICE_ID);
> + }
> +
> + if (vdev->sub_vendor_id != PCI_ANY_ID) {
> + if (vdev->sub_vendor_id > 0xffff) {
> + error_setg(errp, "invalid PCI subsystem vendor ID provided");
> + return false;
> + }
> + vfio_add_emulated_word(vdev, PCI_SUBSYSTEM_VENDOR_ID,
> + vdev->sub_vendor_id, ~0);
> + trace_vfio_pci_emulated_sub_vendor_id(vbasedev->name,
> + vdev->sub_vendor_id);
> + }
> +
> + if (vdev->sub_device_id != PCI_ANY_ID) {
> + if (vdev->sub_device_id > 0xffff) {
> + error_setg(errp, "invalid PCI subsystem device ID provided");
> + return false;
> + }
> + vfio_add_emulated_word(vdev, PCI_SUBSYSTEM_ID, vdev->sub_device_id, ~0);
> + trace_vfio_pci_emulated_sub_device_id(vbasedev->name,
> + vdev->sub_device_id);
> + }
> +
> + /* QEMU can change multi-function devices to single function, or reverse */
> + vdev->emulated_config_bits[PCI_HEADER_TYPE] =
> + PCI_HEADER_TYPE_MULTI_FUNCTION;
> +
> + /* Restore or clear multifunction, this is always controlled by QEMU */
> + if (vdev->pdev.cap_present & QEMU_PCI_CAP_MULTIFUNCTION) {
> + vdev->pdev.config[PCI_HEADER_TYPE] |= PCI_HEADER_TYPE_MULTI_FUNCTION;
> + } else {
> + vdev->pdev.config[PCI_HEADER_TYPE] &= ~PCI_HEADER_TYPE_MULTI_FUNCTION;
> + }
> +
> + /*
> + * Clear host resource mapping info. If we choose not to register a
> + * BAR, such as might be the case with the option ROM, we can get
> + * confusing, unwritable, residual addresses from the host here.
> + */
> + memset(&vdev->pdev.config[PCI_BASE_ADDRESS_0], 0, 24);
> + memset(&vdev->pdev.config[PCI_ROM_ADDRESS], 0, 4);
> +
> + vfio_pci_size_rom(vdev);
> +
> + vfio_bars_prepare(vdev);
> +
> + if (!vfio_msix_early_setup(vdev, errp)) {
> + return false;
> + }
> +
> + vfio_bars_register(vdev);
> +
> + return true;
> +}
> +
> static bool vfio_interrupt_setup(VFIOPCIDevice *vdev, Error **errp)
> {
> PCIDevice *pdev = &vdev->pdev;
> @@ -3060,91 +3153,10 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
> goto error;
> }
>
> - /* vfio emulates a lot for us, but some bits need extra love */
> - vdev->emulated_config_bits = g_malloc0(vdev->config_size);
> -
> - /* QEMU can choose to expose the ROM or not */
> - memset(vdev->emulated_config_bits + PCI_ROM_ADDRESS, 0xff, 4);
> - /* QEMU can also add or extend BARs */
> - memset(vdev->emulated_config_bits + PCI_BASE_ADDRESS_0, 0xff, 6 * 4);
> -
> - /*
> - * The PCI spec reserves vendor ID 0xffff as an invalid value. The
> - * device ID is managed by the vendor and need only be a 16-bit value.
> - * Allow any 16-bit value for subsystem so they can be hidden or changed.
> - */
> - if (vdev->vendor_id != PCI_ANY_ID) {
> - if (vdev->vendor_id >= 0xffff) {
> - error_setg(errp, "invalid PCI vendor ID provided");
> - goto error;
> - }
> - vfio_add_emulated_word(vdev, PCI_VENDOR_ID, vdev->vendor_id, ~0);
> - trace_vfio_pci_emulated_vendor_id(vbasedev->name, vdev->vendor_id);
> - } else {
> - vdev->vendor_id = pci_get_word(pdev->config + PCI_VENDOR_ID);
> - }
> -
> - if (vdev->device_id != PCI_ANY_ID) {
> - if (vdev->device_id > 0xffff) {
> - error_setg(errp, "invalid PCI device ID provided");
> - goto error;
> - }
> - vfio_add_emulated_word(vdev, PCI_DEVICE_ID, vdev->device_id, ~0);
> - trace_vfio_pci_emulated_device_id(vbasedev->name, vdev->device_id);
> - } else {
> - vdev->device_id = pci_get_word(pdev->config + PCI_DEVICE_ID);
> - }
> -
> - if (vdev->sub_vendor_id != PCI_ANY_ID) {
> - if (vdev->sub_vendor_id > 0xffff) {
> - error_setg(errp, "invalid PCI subsystem vendor ID provided");
> - goto error;
> - }
> - vfio_add_emulated_word(vdev, PCI_SUBSYSTEM_VENDOR_ID,
> - vdev->sub_vendor_id, ~0);
> - trace_vfio_pci_emulated_sub_vendor_id(vbasedev->name,
> - vdev->sub_vendor_id);
> - }
> -
> - if (vdev->sub_device_id != PCI_ANY_ID) {
> - if (vdev->sub_device_id > 0xffff) {
> - error_setg(errp, "invalid PCI subsystem device ID provided");
> - goto error;
> - }
> - vfio_add_emulated_word(vdev, PCI_SUBSYSTEM_ID, vdev->sub_device_id, ~0);
> - trace_vfio_pci_emulated_sub_device_id(vbasedev->name,
> - vdev->sub_device_id);
> - }
> -
> - /* QEMU can change multi-function devices to single function, or reverse */
> - vdev->emulated_config_bits[PCI_HEADER_TYPE] =
> - PCI_HEADER_TYPE_MULTI_FUNCTION;
> -
> - /* Restore or clear multifunction, this is always controlled by QEMU */
> - if (vdev->pdev.cap_present & QEMU_PCI_CAP_MULTIFUNCTION) {
> - vdev->pdev.config[PCI_HEADER_TYPE] |= PCI_HEADER_TYPE_MULTI_FUNCTION;
> - } else {
> - vdev->pdev.config[PCI_HEADER_TYPE] &= ~PCI_HEADER_TYPE_MULTI_FUNCTION;
> - }
> -
> - /*
> - * Clear host resource mapping info. If we choose not to register a
> - * BAR, such as might be the case with the option ROM, we can get
> - * confusing, unwritable, residual addresses from the host here.
> - */
> - memset(&vdev->pdev.config[PCI_BASE_ADDRESS_0], 0, 24);
> - memset(&vdev->pdev.config[PCI_ROM_ADDRESS], 0, 4);
> -
> - vfio_pci_size_rom(vdev);
> -
> - vfio_bars_prepare(vdev);
> -
> - if (!vfio_msix_early_setup(vdev, errp)) {
> + if (!vfio_pci_config_setup(vdev, errp)) {
> goto error;
> }
>
> - vfio_bars_register(vdev);
> -
> if (!vbasedev->mdev &&
> !pci_device_set_iommu_device(pdev, vbasedev->hiod, errp)) {
> error_prepend(errp, "Failed to set vIOMMU: ");
^ permalink raw reply [flat|nested] 64+ messages in thread
* [PATCH v8 08/28] vfio: add region cache
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (6 preceding siblings ...)
2025-02-19 14:48 ` [PATCH v8 07/28] vfio: refactor out vfio_pci_config_setup() John Levon
@ 2025-02-19 14:48 ` John Levon
2025-04-03 15:46 ` Cédric Le Goater
2025-02-19 14:48 ` [PATCH v8 09/28] vfio: split out VFIOKernelPCIDevice John Levon
` (22 subsequent siblings)
30 siblings, 1 reply; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin, Jagannathan Raman, John Johnson,
Elena Ufimtseva
From: Jagannathan Raman <jag.raman@oracle.com>
Instead of requesting region information on demand with
VFIO_DEVICE_GET_REGION_INFO, maintain a cache: this will become
necessary for performance for vfio-user, where this call becomes a
message over the control socket, so is of higher overhead than the
traditional path.
Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
---
hw/vfio/ccw.c | 5 -----
hw/vfio/common.c | 12 ++++++++++++
hw/vfio/container.c | 10 ++++++++++
hw/vfio/helpers.c | 21 ++++++++++++++++-----
hw/vfio/igd.c | 8 ++++----
hw/vfio/pci.c | 8 ++++----
include/hw/vfio/vfio-common.h | 1 +
7 files changed, 47 insertions(+), 18 deletions(-)
diff --git a/hw/vfio/ccw.c b/hw/vfio/ccw.c
index 67bc137f9b..22378d50bc 100644
--- a/hw/vfio/ccw.c
+++ b/hw/vfio/ccw.c
@@ -510,7 +510,6 @@ static bool vfio_ccw_get_region(VFIOCCWDevice *vcdev, Error **errp)
vcdev->io_region_offset = info->offset;
vcdev->io_region = g_malloc0(info->size);
- g_free(info);
/* check for the optional async command region */
ret = vfio_get_dev_region_info(vdev, VFIO_REGION_TYPE_CCW,
@@ -523,7 +522,6 @@ static bool vfio_ccw_get_region(VFIOCCWDevice *vcdev, Error **errp)
}
vcdev->async_cmd_region_offset = info->offset;
vcdev->async_cmd_region = g_malloc0(info->size);
- g_free(info);
}
ret = vfio_get_dev_region_info(vdev, VFIO_REGION_TYPE_CCW,
@@ -536,7 +534,6 @@ static bool vfio_ccw_get_region(VFIOCCWDevice *vcdev, Error **errp)
}
vcdev->schib_region_offset = info->offset;
vcdev->schib_region = g_malloc(info->size);
- g_free(info);
}
ret = vfio_get_dev_region_info(vdev, VFIO_REGION_TYPE_CCW,
@@ -550,7 +547,6 @@ static bool vfio_ccw_get_region(VFIOCCWDevice *vcdev, Error **errp)
}
vcdev->crw_region_offset = info->offset;
vcdev->crw_region = g_malloc(info->size);
- g_free(info);
}
return true;
@@ -560,7 +556,6 @@ out_err:
g_free(vcdev->schib_region);
g_free(vcdev->async_cmd_region);
g_free(vcdev->io_region);
- g_free(info);
return false;
}
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 4434e0a0a2..1866b3d3c5 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -1569,6 +1569,16 @@ retry:
return info;
}
+static void vfio_get_all_regions(VFIODevice *vbasedev)
+{
+ struct vfio_region_info *info;
+ int i;
+
+ for (i = 0; i < vbasedev->num_regions; i++) {
+ vfio_get_region_info(vbasedev, i, &info);
+ }
+}
+
void vfio_prepare_device(VFIODevice *vbasedev, VFIOContainerBase *bcontainer,
VFIOGroup *group, struct vfio_device_info *info)
{
@@ -1586,6 +1596,8 @@ void vfio_prepare_device(VFIODevice *vbasedev, VFIOContainerBase *bcontainer,
}
QLIST_INSERT_HEAD(&vfio_device_list, vbasedev, global_next);
+
+ vfio_get_all_regions(vbasedev);
}
bool vfio_attach_device_by_iommu_type(const char *iommu_type, char *name,
diff --git a/hw/vfio/container.c b/hw/vfio/container.c
index 37a3befbc5..36cd245c92 100644
--- a/hw/vfio/container.c
+++ b/hw/vfio/container.c
@@ -886,6 +886,16 @@ static bool vfio_get_device(VFIOGroup *group, const char *name,
static void vfio_put_base_device(VFIODevice *vbasedev)
{
+ if (vbasedev->regions != NULL) {
+ int i;
+
+ for (i = 0; i < vbasedev->num_regions; i++) {
+ g_free(vbasedev->regions[i]);
+ }
+ g_free(vbasedev->regions);
+ vbasedev->regions = NULL;
+ }
+
if (!vbasedev->group) {
return;
}
diff --git a/hw/vfio/helpers.c b/hw/vfio/helpers.c
index 4b255d4f3a..3c923d23b9 100644
--- a/hw/vfio/helpers.c
+++ b/hw/vfio/helpers.c
@@ -345,7 +345,7 @@ static int vfio_setup_region_sparse_mmaps(VFIORegion *region,
int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region,
int index, const char *name)
{
- g_autofree struct vfio_region_info *info = NULL;
+ struct vfio_region_info *info = NULL;
int ret;
ret = vfio_get_region_info(vbasedev, index, &info);
@@ -562,6 +562,17 @@ int vfio_get_region_info(VFIODevice *vbasedev, int index,
{
size_t argsz = sizeof(struct vfio_region_info);
+ /* create region cache */
+ if (vbasedev->regions == NULL) {
+ vbasedev->regions = g_new0(struct vfio_region_info *,
+ vbasedev->num_regions);
+ }
+ /* check cache */
+ if (vbasedev->regions[index] != NULL) {
+ *info = vbasedev->regions[index];
+ return 0;
+ }
+
*info = g_malloc0(argsz);
(*info)->index = index;
@@ -581,6 +592,9 @@ retry:
goto retry;
}
+ /* fill cache */
+ vbasedev->regions[index] = *info;
+
return 0;
}
@@ -599,7 +613,6 @@ int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type,
hdr = vfio_get_region_info_cap(*info, VFIO_REGION_INFO_CAP_TYPE);
if (!hdr) {
- g_free(*info);
continue;
}
@@ -611,8 +624,6 @@ int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type,
if (cap_type->type == type && cap_type->subtype == subtype) {
return 0;
}
-
- g_free(*info);
}
*info = NULL;
@@ -621,7 +632,7 @@ int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type,
bool vfio_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_type)
{
- g_autofree struct vfio_region_info *info = NULL;
+ struct vfio_region_info *info = NULL;
bool ret = false;
if (!vfio_get_region_info(vbasedev, region, &info)) {
diff --git a/hw/vfio/igd.c b/hw/vfio/igd.c
index b1a237edd6..b5425ba9c0 100644
--- a/hw/vfio/igd.c
+++ b/hw/vfio/igd.c
@@ -490,10 +490,10 @@ void vfio_probe_igd_bar0_quirk(VFIOPCIDevice *vdev, int nr)
void vfio_probe_igd_bar4_quirk(VFIOPCIDevice *vdev, int nr)
{
- g_autofree struct vfio_region_info *rom = NULL;
- g_autofree struct vfio_region_info *opregion = NULL;
- g_autofree struct vfio_region_info *host = NULL;
- g_autofree struct vfio_region_info *lpc = NULL;
+ struct vfio_region_info *rom = NULL;
+ struct vfio_region_info *opregion = NULL;
+ struct vfio_region_info *host = NULL;
+ struct vfio_region_info *lpc = NULL;
VFIOQuirk *quirk;
VFIOIGDQuirk *igd;
PCIDevice *lpc_bridge;
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 83fe329474..a4f99fc5e0 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -879,7 +879,7 @@ static void vfio_update_msi(VFIOPCIDevice *vdev)
static void vfio_pci_load_rom(VFIOPCIDevice *vdev)
{
- g_autofree struct vfio_region_info *reg_info = NULL;
+ struct vfio_region_info *reg_info = NULL;
uint64_t size;
off_t off = 0;
ssize_t bytes;
@@ -2665,7 +2665,7 @@ static VFIODeviceOps vfio_pci_ops = {
bool vfio_populate_vga(VFIOPCIDevice *vdev, Error **errp)
{
VFIODevice *vbasedev = &vdev->vbasedev;
- g_autofree struct vfio_region_info *reg_info = NULL;
+ struct vfio_region_info *reg_info = NULL;
int ret;
ret = vfio_get_region_info(vbasedev, VFIO_PCI_VGA_REGION_INDEX, ®_info);
@@ -2730,7 +2730,7 @@ bool vfio_populate_vga(VFIOPCIDevice *vdev, Error **errp)
static bool vfio_populate_device(VFIOPCIDevice *vdev, Error **errp)
{
VFIODevice *vbasedev = &vdev->vbasedev;
- g_autofree struct vfio_region_info *reg_info = NULL;
+ struct vfio_region_info *reg_info = NULL;
struct vfio_irq_info irq_info = { .argsz = sizeof(irq_info) };
int i, ret = -1;
@@ -3177,7 +3177,7 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
if (!vdev->igd_opregion &&
vdev->features & VFIO_FEATURE_ENABLE_IGD_OPREGION) {
- g_autofree struct vfio_region_info *opregion = NULL;
+ struct vfio_region_info *opregion = NULL;
if (vdev->pdev.qdev.hotplugged) {
error_setg(errp,
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index ae3ecbd9f6..304030e71d 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -151,6 +151,7 @@ typedef struct VFIODevice {
IOMMUFDBackend *iommufd;
VFIOIOASHwpt *hwpt;
QLIST_ENTRY(VFIODevice) hwpt_next;
+ struct vfio_region_info **regions;
} VFIODevice;
struct VFIODeviceOps {
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* Re: [PATCH v8 08/28] vfio: add region cache
2025-02-19 14:48 ` [PATCH v8 08/28] vfio: add region cache John Levon
@ 2025-04-03 15:46 ` Cédric Le Goater
2025-04-03 16:00 ` John Levon
0 siblings, 1 reply; 64+ messages in thread
From: Cédric Le Goater @ 2025-04-03 15:46 UTC (permalink / raw)
To: John Levon, qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin,
Jagannathan Raman, John Johnson, Elena Ufimtseva
On 2/19/25 15:48, John Levon wrote:
> From: Jagannathan Raman <jag.raman@oracle.com>
>
> Instead of requesting region information on demand with
> VFIO_DEVICE_GET_REGION_INFO, maintain a cache: this will become
> necessary for performance for vfio-user, where this call becomes a
> message over the control socket, so is of higher overhead than the
> traditional path.
>
> Originally-by: John Johnson <john.g.johnson@oracle.com>
> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
> Signed-off-by: John Levon <john.levon@nutanix.com>
> ---
> hw/vfio/ccw.c | 5 -----
> hw/vfio/common.c | 12 ++++++++++++
> hw/vfio/container.c | 10 ++++++++++
> hw/vfio/helpers.c | 21 ++++++++++++++++-----
> hw/vfio/igd.c | 8 ++++----
> hw/vfio/pci.c | 8 ++++----
> include/hw/vfio/vfio-common.h | 1 +
> 7 files changed, 47 insertions(+), 18 deletions(-)
>
> diff --git a/hw/vfio/ccw.c b/hw/vfio/ccw.c
> index 67bc137f9b..22378d50bc 100644
> --- a/hw/vfio/ccw.c
> +++ b/hw/vfio/ccw.c
> @@ -510,7 +510,6 @@ static bool vfio_ccw_get_region(VFIOCCWDevice *vcdev, Error **errp)
>
> vcdev->io_region_offset = info->offset;
> vcdev->io_region = g_malloc0(info->size);
> - g_free(info);
>
> /* check for the optional async command region */
> ret = vfio_get_dev_region_info(vdev, VFIO_REGION_TYPE_CCW,
> @@ -523,7 +522,6 @@ static bool vfio_ccw_get_region(VFIOCCWDevice *vcdev, Error **errp)
> }
> vcdev->async_cmd_region_offset = info->offset;
> vcdev->async_cmd_region = g_malloc0(info->size);
> - g_free(info);
> }
>
> ret = vfio_get_dev_region_info(vdev, VFIO_REGION_TYPE_CCW,
> @@ -536,7 +534,6 @@ static bool vfio_ccw_get_region(VFIOCCWDevice *vcdev, Error **errp)
> }
> vcdev->schib_region_offset = info->offset;
> vcdev->schib_region = g_malloc(info->size);
> - g_free(info);
> }
>
> ret = vfio_get_dev_region_info(vdev, VFIO_REGION_TYPE_CCW,
> @@ -550,7 +547,6 @@ static bool vfio_ccw_get_region(VFIOCCWDevice *vcdev, Error **errp)
> }
> vcdev->crw_region_offset = info->offset;
> vcdev->crw_region = g_malloc(info->size);
> - g_free(info);
> }
>
> return true;
> @@ -560,7 +556,6 @@ out_err:
> g_free(vcdev->schib_region);
> g_free(vcdev->async_cmd_region);
> g_free(vcdev->io_region);
> - g_free(info);
> return false;
> }
>
> diff --git a/hw/vfio/common.c b/hw/vfio/common.c
> index 4434e0a0a2..1866b3d3c5 100644
> --- a/hw/vfio/common.c
> +++ b/hw/vfio/common.c
> @@ -1569,6 +1569,16 @@ retry:
> return info;
> }
>
> +static void vfio_get_all_regions(VFIODevice *vbasedev)
> +{
> + struct vfio_region_info *info;
> + int i;
> +
> + for (i = 0; i < vbasedev->num_regions; i++) {
> + vfio_get_region_info(vbasedev, i, &info);
> + }
> +}
> +
> void vfio_prepare_device(VFIODevice *vbasedev, VFIOContainerBase *bcontainer,
> VFIOGroup *group, struct vfio_device_info *info)
> {
> @@ -1586,6 +1596,8 @@ void vfio_prepare_device(VFIODevice *vbasedev, VFIOContainerBase *bcontainer,
> }
>
> QLIST_INSERT_HEAD(&vfio_device_list, vbasedev, global_next);
> +
> + vfio_get_all_regions(vbasedev);
> }
>
> bool vfio_attach_device_by_iommu_type(const char *iommu_type, char *name,
> diff --git a/hw/vfio/container.c b/hw/vfio/container.c
> index 37a3befbc5..36cd245c92 100644
> --- a/hw/vfio/container.c
> +++ b/hw/vfio/container.c
> @@ -886,6 +886,16 @@ static bool vfio_get_device(VFIOGroup *group, const char *name,
>
> static void vfio_put_base_device(VFIODevice *vbasedev)
> {
> + if (vbasedev->regions != NULL) {
> + int i;
> +
> + for (i = 0; i < vbasedev->num_regions; i++) {
> + g_free(vbasedev->regions[i]);
> + }
> + g_free(vbasedev->regions);
> + vbasedev->regions = NULL;
> + }
> +
> if (!vbasedev->group) {
> return;
> }
> diff --git a/hw/vfio/helpers.c b/hw/vfio/helpers.c
> index 4b255d4f3a..3c923d23b9 100644
> --- a/hw/vfio/helpers.c
> +++ b/hw/vfio/helpers.c
> @@ -345,7 +345,7 @@ static int vfio_setup_region_sparse_mmaps(VFIORegion *region,
> int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region,
> int index, const char *name)
> {
> - g_autofree struct vfio_region_info *info = NULL;
> + struct vfio_region_info *info = NULL;
> int ret;
>
> ret = vfio_get_region_info(vbasedev, index, &info);
> @@ -562,6 +562,17 @@ int vfio_get_region_info(VFIODevice *vbasedev, int index,
> {
> size_t argsz = sizeof(struct vfio_region_info);
>
> + /* create region cache */
> + if (vbasedev->regions == NULL) {
> + vbasedev->regions = g_new0(struct vfio_region_info *,
> + vbasedev->num_regions);
> + }
> + /* check cache */
> + if (vbasedev->regions[index] != NULL) {
> + *info = vbasedev->regions[index];
> + return 0;
> + }
> +
why not populate vbasedev->regions[index] in vfio_get_all_regions() ?
Thanks,
C.
> *info = g_malloc0(argsz);
>
> (*info)->index = index;
> @@ -581,6 +592,9 @@ retry:
> goto retry;
> }
>
> + /* fill cache */
> + vbasedev->regions[index] = *info;
> +
> return 0;
> }
>
> @@ -599,7 +613,6 @@ int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type,
>
> hdr = vfio_get_region_info_cap(*info, VFIO_REGION_INFO_CAP_TYPE);
> if (!hdr) {
> - g_free(*info);
> continue;
> }
>
> @@ -611,8 +624,6 @@ int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type,
> if (cap_type->type == type && cap_type->subtype == subtype) {
> return 0;
> }
> -
> - g_free(*info);
> }
>
> *info = NULL;
> @@ -621,7 +632,7 @@ int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type,
>
> bool vfio_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_type)
> {
> - g_autofree struct vfio_region_info *info = NULL;
> + struct vfio_region_info *info = NULL;
> bool ret = false;
>
> if (!vfio_get_region_info(vbasedev, region, &info)) {
> diff --git a/hw/vfio/igd.c b/hw/vfio/igd.c
> index b1a237edd6..b5425ba9c0 100644
> --- a/hw/vfio/igd.c
> +++ b/hw/vfio/igd.c
> @@ -490,10 +490,10 @@ void vfio_probe_igd_bar0_quirk(VFIOPCIDevice *vdev, int nr)
>
> void vfio_probe_igd_bar4_quirk(VFIOPCIDevice *vdev, int nr)
> {
> - g_autofree struct vfio_region_info *rom = NULL;
> - g_autofree struct vfio_region_info *opregion = NULL;
> - g_autofree struct vfio_region_info *host = NULL;
> - g_autofree struct vfio_region_info *lpc = NULL;
> + struct vfio_region_info *rom = NULL;
> + struct vfio_region_info *opregion = NULL;
> + struct vfio_region_info *host = NULL;
> + struct vfio_region_info *lpc = NULL;
> VFIOQuirk *quirk;
> VFIOIGDQuirk *igd;
> PCIDevice *lpc_bridge;
> diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
> index 83fe329474..a4f99fc5e0 100644
> --- a/hw/vfio/pci.c
> +++ b/hw/vfio/pci.c
> @@ -879,7 +879,7 @@ static void vfio_update_msi(VFIOPCIDevice *vdev)
>
> static void vfio_pci_load_rom(VFIOPCIDevice *vdev)
> {
> - g_autofree struct vfio_region_info *reg_info = NULL;
> + struct vfio_region_info *reg_info = NULL;
> uint64_t size;
> off_t off = 0;
> ssize_t bytes;
> @@ -2665,7 +2665,7 @@ static VFIODeviceOps vfio_pci_ops = {
> bool vfio_populate_vga(VFIOPCIDevice *vdev, Error **errp)
> {
> VFIODevice *vbasedev = &vdev->vbasedev;
> - g_autofree struct vfio_region_info *reg_info = NULL;
> + struct vfio_region_info *reg_info = NULL;
> int ret;
>
> ret = vfio_get_region_info(vbasedev, VFIO_PCI_VGA_REGION_INDEX, ®_info);
> @@ -2730,7 +2730,7 @@ bool vfio_populate_vga(VFIOPCIDevice *vdev, Error **errp)
> static bool vfio_populate_device(VFIOPCIDevice *vdev, Error **errp)
> {
> VFIODevice *vbasedev = &vdev->vbasedev;
> - g_autofree struct vfio_region_info *reg_info = NULL;
> + struct vfio_region_info *reg_info = NULL;
> struct vfio_irq_info irq_info = { .argsz = sizeof(irq_info) };
> int i, ret = -1;
>
> @@ -3177,7 +3177,7 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
>
> if (!vdev->igd_opregion &&
> vdev->features & VFIO_FEATURE_ENABLE_IGD_OPREGION) {
> - g_autofree struct vfio_region_info *opregion = NULL;
> + struct vfio_region_info *opregion = NULL;
>
> if (vdev->pdev.qdev.hotplugged) {
> error_setg(errp,
> diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
> index ae3ecbd9f6..304030e71d 100644
> --- a/include/hw/vfio/vfio-common.h
> +++ b/include/hw/vfio/vfio-common.h
> @@ -151,6 +151,7 @@ typedef struct VFIODevice {
> IOMMUFDBackend *iommufd;
> VFIOIOASHwpt *hwpt;
> QLIST_ENTRY(VFIODevice) hwpt_next;
> + struct vfio_region_info **regions;
> } VFIODevice;
>
> struct VFIODeviceOps {
^ permalink raw reply [flat|nested] 64+ messages in thread* Re: [PATCH v8 08/28] vfio: add region cache
2025-04-03 15:46 ` Cédric Le Goater
@ 2025-04-03 16:00 ` John Levon
2025-04-04 16:57 ` Cédric Le Goater
0 siblings, 1 reply; 64+ messages in thread
From: John Levon @ 2025-04-03 16:00 UTC (permalink / raw)
To: Cédric Le Goater
Cc: qemu-devel, Jason Herne, Thanos Makatos, Halil Pasic,
Daniel P. Berrangé, Eric Farman, Tony Krowiak, Thomas Huth,
qemu-s390x, Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin,
Jagannathan Raman, John Johnson, Elena Ufimtseva
On Thu, Apr 03, 2025 at 05:46:03PM +0200, Cédric Le Goater wrote:
> > +static void vfio_get_all_regions(VFIODevice *vbasedev)
> > +{
> > + struct vfio_region_info *info;
> > + int i;
> > +
> > + for (i = 0; i < vbasedev->num_regions; i++) {
> > + vfio_get_region_info(vbasedev, i, &info);
> > + }
> > +}
> > +
> > void vfio_prepare_device(VFIODevice *vbasedev, VFIOContainerBase *bcontainer,
> > VFIOGroup *group, struct vfio_device_info *info)
> > {
> > @@ -1586,6 +1596,8 @@ void vfio_prepare_device(VFIODevice *vbasedev, VFIOContainerBase *bcontainer,
> > }
> > QLIST_INSERT_HEAD(&vfio_device_list, vbasedev, global_next);
> > +
> > + vfio_get_all_regions(vbasedev);
> > }
> > + /* check cache */
> > + if (vbasedev->regions[index] != NULL) {
> > + *info = vbasedev->regions[index];
> > + return 0;
> > + }
> > +
>
> why not populate vbasedev->regions[index] in vfio_get_all_regions() ?
Good question. I presume it's not possible for us to ever look up a region
that has somehow appeared *after* vfio_prepare_device() ?
We'd end up off the end of the array in that case anyway.
regards
john
^ permalink raw reply [flat|nested] 64+ messages in thread* Re: [PATCH v8 08/28] vfio: add region cache
2025-04-03 16:00 ` John Levon
@ 2025-04-04 16:57 ` Cédric Le Goater
2025-04-04 17:18 ` John Levon
0 siblings, 1 reply; 64+ messages in thread
From: Cédric Le Goater @ 2025-04-04 16:57 UTC (permalink / raw)
To: John Levon
Cc: qemu-devel, Jason Herne, Thanos Makatos, Halil Pasic,
Daniel P. Berrangé, Eric Farman, Tony Krowiak, Thomas Huth,
qemu-s390x, Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin,
Jagannathan Raman, John Johnson, Elena Ufimtseva
On 4/3/25 18:00, John Levon wrote:
> On Thu, Apr 03, 2025 at 05:46:03PM +0200, Cédric Le Goater wrote:
>
>>> +static void vfio_get_all_regions(VFIODevice *vbasedev)
>>> +{
>>> + struct vfio_region_info *info;
>>> + int i;
>>> +
>>> + for (i = 0; i < vbasedev->num_regions; i++) {
>>> + vfio_get_region_info(vbasedev, i, &info);
>>> + }
>>> +}
>>> +
>>> void vfio_prepare_device(VFIODevice *vbasedev, VFIOContainerBase *bcontainer,
>>> VFIOGroup *group, struct vfio_device_info *info)
>>> {
>>> @@ -1586,6 +1596,8 @@ void vfio_prepare_device(VFIODevice *vbasedev, VFIOContainerBase *bcontainer,
>>> }
>>> QLIST_INSERT_HEAD(&vfio_device_list, vbasedev, global_next);
>>> +
>>> + vfio_get_all_regions(vbasedev);
>>> }
>
>>> + /* check cache */
>>> + if (vbasedev->regions[index] != NULL) {
>>> + *info = vbasedev->regions[index];
>>> + return 0;
>>> + }
>>> +
>>
>> why not populate vbasedev->regions[index] in vfio_get_all_regions() ?
>
> Good question. I presume it's not possible for us to ever look up a region
> that has somehow appeared *after* vfio_prepare_device() ?
>
> We'd end up off the end of the array in that case anyway.
I was confused. I thought we were caching VFIORegions ...
Anyway, this is an optimisation and I fail to understand where
the VFIO_DEVICE_GET_REGION_INFO ioctl is called on a hot path.
Is it for interrupts ? Please explain.
Do you have figures ?
Thanks,
C.
^ permalink raw reply [flat|nested] 64+ messages in thread* Re: [PATCH v8 08/28] vfio: add region cache
2025-04-04 16:57 ` Cédric Le Goater
@ 2025-04-04 17:18 ` John Levon
2025-04-08 13:48 ` John Levon
0 siblings, 1 reply; 64+ messages in thread
From: John Levon @ 2025-04-04 17:18 UTC (permalink / raw)
To: Cédric Le Goater
Cc: qemu-devel, Jason Herne, Thanos Makatos, Halil Pasic,
Daniel P. Berrangé, Eric Farman, Tony Krowiak, Thomas Huth,
qemu-s390x, Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin,
Jagannathan Raman, John Johnson, Elena Ufimtseva
On Fri, Apr 04, 2025 at 06:57:46PM +0200, Cédric Le Goater wrote:
> > > why not populate vbasedev->regions[index] in vfio_get_all_regions() ?
> >
> > Good question. I presume it's not possible for us to ever look up a region
> > that has somehow appeared *after* vfio_prepare_device() ?
> >
> > We'd end up off the end of the array in that case anyway.
>
> I was confused. I thought we were caching VFIORegions ...
>
> Anyway, this is an optimisation and I fail to understand where
> the VFIO_DEVICE_GET_REGION_INFO ioctl is called on a hot path.
>
> Is it for interrupts ? Please explain.
>
> Do you have figures ?
That's a great question that I don't know the answer to (like much of this code
I just inherited it). Let me try to investigate.
regards
john
^ permalink raw reply [flat|nested] 64+ messages in thread
* Re: [PATCH v8 08/28] vfio: add region cache
2025-04-04 17:18 ` John Levon
@ 2025-04-08 13:48 ` John Levon
0 siblings, 0 replies; 64+ messages in thread
From: John Levon @ 2025-04-08 13:48 UTC (permalink / raw)
To: Cédric Le Goater
Cc: qemu-devel, Jason Herne, Thanos Makatos, Halil Pasic,
Daniel P. Berrangé, Eric Farman, Tony Krowiak, Thomas Huth,
qemu-s390x, Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin,
Jagannathan Raman, John Johnson, Elena Ufimtseva
On Fri, Apr 04, 2025 at 06:18:20PM +0100, John Levon wrote:
> On Fri, Apr 04, 2025 at 06:57:46PM +0200, Cédric Le Goater wrote:
>
> > > > why not populate vbasedev->regions[index] in vfio_get_all_regions() ?
> > >
> > > Good question. I presume it's not possible for us to ever look up a region
> > > that has somehow appeared *after* vfio_prepare_device() ?
> > >
> > > We'd end up off the end of the array in that case anyway.
> >
> > I was confused. I thought we were caching VFIORegions ...
> >
> > Anyway, this is an optimisation and I fail to understand where
> > the VFIO_DEVICE_GET_REGION_INFO ioctl is called on a hot path.
> >
> > Is it for interrupts ? Please explain.
> >
> > Do you have figures ?
>
> That's a great question that I don't know the answer to (like much of this code
> I just inherited it). Let me try to investigate.
I found one reason. hw/vfio/pci.c stores VFIOPCIDevice::config_offset so it
doesn't need to do a get region info on every config space access.
But after the refactoring, vfio_io_region_read() gets passed a region index (the
idea of a "region offset" isn't meaningful to vfio-user).
Without the cache, the kernel vfio implementation:
```
867 static int vfio_io_region_write(VFIODevice *vbasedev, uint8_t index, off_t off,
868 uint32_t size, void *data, bool post)
869 {
870 struct vfio_region_info *info = vbasedev->regions[index];
871 int ret;
872
873 ret = pwrite(vbasedev->fd, data, size, info->offset + off);
```
would have to look up the region offset every time.
regards
john
^ permalink raw reply [flat|nested] 64+ messages in thread
* [PATCH v8 09/28] vfio: split out VFIOKernelPCIDevice
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (7 preceding siblings ...)
2025-02-19 14:48 ` [PATCH v8 08/28] vfio: add region cache John Levon
@ 2025-02-19 14:48 ` John Levon
2025-04-03 17:13 ` Cédric Le Goater
2025-02-19 14:48 ` [PATCH v8 10/28] vfio: add device IO ops vector John Levon
` (21 subsequent siblings)
30 siblings, 1 reply; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin, Jagannathan Raman, John Johnson,
Elena Ufimtseva
From: Jagannathan Raman <jag.raman@oracle.com>
Split out code specific to the kernel-side vfio implementation from the
VFIOPCIDevice class into a VFIOKernelPCIDevice. The forthcoming
VFIOUserPCIDevice will share the base VFIOPCIDevice class.
Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
---
hw/vfio/helpers.c | 2 +-
hw/vfio/pci.c | 107 ++++++++++++++++++++++++++++------------------
hw/vfio/pci.h | 16 ++++++-
3 files changed, 80 insertions(+), 45 deletions(-)
diff --git a/hw/vfio/helpers.c b/hw/vfio/helpers.c
index 3c923d23b9..94bbc5747c 100644
--- a/hw/vfio/helpers.c
+++ b/hw/vfio/helpers.c
@@ -744,7 +744,7 @@ bool vfio_device_hiod_realize(VFIODevice *vbasedev, Error **errp)
VFIODevice *vfio_get_vfio_device(Object *obj)
{
if (object_dynamic_cast(obj, TYPE_VFIO_PCI)) {
- return &VFIO_PCI(obj)->vbasedev;
+ return &VFIO_PCI(obj)->device.vbasedev;
} else {
return NULL;
}
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index a4f99fc5e0..812743e9dd 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -239,7 +239,7 @@ static void vfio_intx_update(VFIOPCIDevice *vdev, PCIINTxRoute *route)
static void vfio_intx_routing_notifier(PCIDevice *pdev)
{
- VFIOPCIDevice *vdev = VFIO_PCI(pdev);
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
PCIINTxRoute route;
if (vdev->interrupt != VFIO_INT_INTx) {
@@ -514,7 +514,7 @@ static void vfio_update_kvm_msi_virq(VFIOMSIVector *vector, MSIMessage msg,
static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr,
MSIMessage *msg, IOHandler *handler)
{
- VFIOPCIDevice *vdev = VFIO_PCI(pdev);
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
VFIOMSIVector *vector;
int ret;
bool resizing = !!(vdev->nr_vectors < nr + 1);
@@ -619,7 +619,7 @@ static int vfio_msix_vector_use(PCIDevice *pdev,
static void vfio_msix_vector_release(PCIDevice *pdev, unsigned int nr)
{
- VFIOPCIDevice *vdev = VFIO_PCI(pdev);
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
VFIOMSIVector *vector = &vdev->msi_vectors[nr];
trace_vfio_msix_vector_release(vdev->vbasedev.name, nr);
@@ -1167,7 +1167,7 @@ static const MemoryRegionOps vfio_vga_ops = {
*/
static void vfio_sub_page_bar_update_mapping(PCIDevice *pdev, int bar)
{
- VFIOPCIDevice *vdev = VFIO_PCI(pdev);
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
VFIORegion *region = &vdev->bars[bar].region;
MemoryRegion *mmap_mr, *region_mr, *base_mr;
PCIIORegion *r;
@@ -1213,7 +1213,7 @@ static void vfio_sub_page_bar_update_mapping(PCIDevice *pdev, int bar)
*/
uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len)
{
- VFIOPCIDevice *vdev = VFIO_PCI(pdev);
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
uint32_t emu_bits = 0, emu_val = 0, phys_val = 0, val;
memcpy(&emu_bits, vdev->emulated_config_bits + addr, len);
@@ -1246,7 +1246,7 @@ uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len)
void vfio_pci_write_config(PCIDevice *pdev,
uint32_t addr, uint32_t val, int len)
{
- VFIOPCIDevice *vdev = VFIO_PCI(pdev);
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
uint32_t val_le = cpu_to_le32(val);
trace_vfio_pci_write_config(vdev->vbasedev.name, addr, val, len);
@@ -3084,7 +3084,7 @@ static bool vfio_interrupt_setup(VFIOPCIDevice *vdev, Error **errp)
static void vfio_realize(PCIDevice *pdev, Error **errp)
{
ERRP_GUARD();
- VFIOPCIDevice *vdev = VFIO_PCI(pdev);
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
VFIODevice *vbasedev = &vdev->vbasedev;
int i, ret;
char uuid[UUID_STR_LEN];
@@ -3274,7 +3274,7 @@ error:
static void vfio_instance_finalize(Object *obj)
{
- VFIOPCIDevice *vdev = VFIO_PCI(obj);
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(obj);
vfio_display_finalize(vdev);
vfio_bars_finalize(vdev);
@@ -3292,7 +3292,7 @@ static void vfio_instance_finalize(Object *obj)
static void vfio_exitfn(PCIDevice *pdev)
{
- VFIOPCIDevice *vdev = VFIO_PCI(pdev);
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
VFIODevice *vbasedev = &vdev->vbasedev;
vfio_unregister_req_notifier(vdev);
@@ -3316,7 +3316,7 @@ static void vfio_exitfn(PCIDevice *pdev)
static void vfio_pci_reset(DeviceState *dev)
{
- VFIOPCIDevice *vdev = VFIO_PCI(dev);
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(dev);
trace_vfio_pci_reset(vdev->vbasedev.name);
@@ -3356,7 +3356,7 @@ post_reset:
static void vfio_instance_init(Object *obj)
{
PCIDevice *pci_dev = PCI_DEVICE(obj);
- VFIOPCIDevice *vdev = VFIO_PCI(obj);
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(obj);
VFIODevice *vbasedev = &vdev->vbasedev;
device_add_bootindex_property(obj, &vdev->bootindex,
@@ -3377,28 +3377,15 @@ static void vfio_instance_init(Object *obj)
pci_dev->cap_present |= QEMU_PCI_CAP_EXPRESS;
}
-static const Property vfio_pci_dev_properties[] = {
- DEFINE_PROP_PCI_HOST_DEVADDR("host", VFIOPCIDevice, host),
- DEFINE_PROP_UUID_NODEFAULT("vf-token", VFIOPCIDevice, vf_token),
- DEFINE_PROP_STRING("sysfsdev", VFIOPCIDevice, vbasedev.sysfsdev),
+static const Property vfio_pci_base_dev_properties[] = {
DEFINE_PROP_ON_OFF_AUTO("x-pre-copy-dirty-page-tracking", VFIOPCIDevice,
vbasedev.pre_copy_dirty_page_tracking,
ON_OFF_AUTO_ON),
DEFINE_PROP_ON_OFF_AUTO("x-device-dirty-page-tracking", VFIOPCIDevice,
vbasedev.device_dirty_page_tracking,
ON_OFF_AUTO_ON),
- DEFINE_PROP_ON_OFF_AUTO("display", VFIOPCIDevice,
- display, ON_OFF_AUTO_OFF),
- DEFINE_PROP_UINT32("xres", VFIOPCIDevice, display_xres, 0),
- DEFINE_PROP_UINT32("yres", VFIOPCIDevice, display_yres, 0),
DEFINE_PROP_UINT32("x-intx-mmap-timeout-ms", VFIOPCIDevice,
intx.mmap_timeout, 1100),
- DEFINE_PROP_BIT("x-vga", VFIOPCIDevice, features,
- VFIO_FEATURE_ENABLE_VGA_BIT, false),
- DEFINE_PROP_BIT("x-req", VFIOPCIDevice, features,
- VFIO_FEATURE_ENABLE_REQ_BIT, true),
- DEFINE_PROP_BIT("x-igd-opregion", VFIOPCIDevice, features,
- VFIO_FEATURE_ENABLE_IGD_OPREGION_BIT, false),
DEFINE_PROP_ON_OFF_AUTO("enable-migration", VFIOPCIDevice,
vbasedev.enable_migration, ON_OFF_AUTO_AUTO),
DEFINE_PROP_BOOL("migration-events", VFIOPCIDevice,
@@ -3409,8 +3396,6 @@ static const Property vfio_pci_dev_properties[] = {
DEFINE_PROP_BOOL("x-no-kvm-intx", VFIOPCIDevice, no_kvm_intx, false),
DEFINE_PROP_BOOL("x-no-kvm-msi", VFIOPCIDevice, no_kvm_msi, false),
DEFINE_PROP_BOOL("x-no-kvm-msix", VFIOPCIDevice, no_kvm_msix, false),
- DEFINE_PROP_BOOL("x-no-geforce-quirks", VFIOPCIDevice,
- no_geforce_quirks, false),
DEFINE_PROP_BOOL("x-no-kvm-ioeventfd", VFIOPCIDevice, no_kvm_ioeventfd,
false),
DEFINE_PROP_BOOL("x-no-vfio-ioeventfd", VFIOPCIDevice, no_vfio_ioeventfd,
@@ -3421,12 +3406,57 @@ static const Property vfio_pci_dev_properties[] = {
sub_vendor_id, PCI_ANY_ID),
DEFINE_PROP_UINT32("x-pci-sub-device-id", VFIOPCIDevice,
sub_device_id, PCI_ANY_ID),
+ DEFINE_PROP_OFF_AUTO_PCIBAR("x-msix-relocation", VFIOPCIDevice, msix_relo,
+ OFF_AUTO_PCIBAR_OFF),
+};
+
+
+static void vfio_pci_base_dev_class_init(ObjectClass *klass, void *data)
+{
+ DeviceClass *dc = DEVICE_CLASS(klass);
+ PCIDeviceClass *pdc = PCI_DEVICE_CLASS(klass);
+
+ device_class_set_props(dc, vfio_pci_base_dev_properties);
+ dc->desc = "VFIO PCI base device";
+ set_bit(DEVICE_CATEGORY_MISC, dc->categories);
+ pdc->exit = vfio_exitfn;
+ pdc->config_read = vfio_pci_read_config;
+ pdc->config_write = vfio_pci_write_config;
+}
+
+static const TypeInfo vfio_pci_base_dev_info = {
+ .name = TYPE_VFIO_PCI_BASE,
+ .parent = TYPE_PCI_DEVICE,
+ .instance_size = 0,
+ .abstract = true,
+ .class_init = vfio_pci_base_dev_class_init,
+ .interfaces = (InterfaceInfo[]) {
+ { INTERFACE_PCIE_DEVICE },
+ { INTERFACE_CONVENTIONAL_PCI_DEVICE },
+ { }
+ },
+};
+
+static const Property vfio_pci_dev_properties[] = {
+ DEFINE_PROP_PCI_HOST_DEVADDR("host", VFIOPCIDevice, host),
+ DEFINE_PROP_UUID_NODEFAULT("vf-token", VFIOPCIDevice, vf_token),
+ DEFINE_PROP_STRING("sysfsdev", VFIOPCIDevice, vbasedev.sysfsdev),
+ DEFINE_PROP_ON_OFF_AUTO("display", VFIOPCIDevice,
+ display, ON_OFF_AUTO_OFF),
+ DEFINE_PROP_UINT32("xres", VFIOPCIDevice, display_xres, 0),
+ DEFINE_PROP_UINT32("yres", VFIOPCIDevice, display_yres, 0),
+ DEFINE_PROP_BIT("x-vga", VFIOPCIDevice, features,
+ VFIO_FEATURE_ENABLE_VGA_BIT, false),
+ DEFINE_PROP_BIT("x-req", VFIOPCIDevice, features,
+ VFIO_FEATURE_ENABLE_REQ_BIT, true),
+ DEFINE_PROP_BIT("x-igd-opregion", VFIOPCIDevice, features,
+ VFIO_FEATURE_ENABLE_IGD_OPREGION_BIT, false),
+ DEFINE_PROP_BOOL("x-no-geforce-quirks", VFIOPCIDevice,
+ no_geforce_quirks, false),
DEFINE_PROP_UINT32("x-igd-gms", VFIOPCIDevice, igd_gms, 0),
DEFINE_PROP_UNSIGNED_NODEFAULT("x-nv-gpudirect-clique", VFIOPCIDevice,
nv_gpudirect_clique,
qdev_prop_nv_gpudirect_clique, uint8_t),
- DEFINE_PROP_OFF_AUTO_PCIBAR("x-msix-relocation", VFIOPCIDevice, msix_relo,
- OFF_AUTO_PCIBAR_OFF),
#ifdef CONFIG_IOMMUFD
DEFINE_PROP_LINK("iommufd", VFIOPCIDevice, vbasedev.iommufd,
TYPE_IOMMUFD_BACKEND, IOMMUFDBackend *),
@@ -3437,7 +3467,8 @@ static const Property vfio_pci_dev_properties[] = {
#ifdef CONFIG_IOMMUFD
static void vfio_pci_set_fd(Object *obj, const char *str, Error **errp)
{
- vfio_device_set_fd(&VFIO_PCI(obj)->vbasedev, str, errp);
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(obj);
+ vfio_device_set_fd(&vdev->vbasedev, str, errp);
}
#endif
@@ -3452,25 +3483,16 @@ static void vfio_pci_dev_class_init(ObjectClass *klass, void *data)
object_class_property_add_str(klass, "fd", NULL, vfio_pci_set_fd);
#endif
dc->desc = "VFIO-based PCI device assignment";
- set_bit(DEVICE_CATEGORY_MISC, dc->categories);
pdc->realize = vfio_realize;
- pdc->exit = vfio_exitfn;
- pdc->config_read = vfio_pci_read_config;
- pdc->config_write = vfio_pci_write_config;
}
static const TypeInfo vfio_pci_dev_info = {
.name = TYPE_VFIO_PCI,
- .parent = TYPE_PCI_DEVICE,
- .instance_size = sizeof(VFIOPCIDevice),
+ .parent = TYPE_VFIO_PCI_BASE,
+ .instance_size = sizeof(VFIOKernelPCIDevice),
.class_init = vfio_pci_dev_class_init,
.instance_init = vfio_instance_init,
.instance_finalize = vfio_instance_finalize,
- .interfaces = (InterfaceInfo[]) {
- { INTERFACE_PCIE_DEVICE },
- { INTERFACE_CONVENTIONAL_PCI_DEVICE },
- { }
- },
};
static const Property vfio_pci_dev_nohotplug_properties[] = {
@@ -3490,12 +3512,13 @@ static void vfio_pci_nohotplug_dev_class_init(ObjectClass *klass, void *data)
static const TypeInfo vfio_pci_nohotplug_dev_info = {
.name = TYPE_VFIO_PCI_NOHOTPLUG,
.parent = TYPE_VFIO_PCI,
- .instance_size = sizeof(VFIOPCIDevice),
+ .instance_size = sizeof(VFIOKernelPCIDevice),
.class_init = vfio_pci_nohotplug_dev_class_init,
};
static void register_vfio_pci_dev_type(void)
{
+ type_register_static(&vfio_pci_base_dev_info);
type_register_static(&vfio_pci_dev_info);
type_register_static(&vfio_pci_nohotplug_dev_info);
}
diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h
index 43c166680a..8e79740ddb 100644
--- a/hw/vfio/pci.h
+++ b/hw/vfio/pci.h
@@ -116,8 +116,13 @@ typedef struct VFIOMSIXInfo {
bool noresize;
} VFIOMSIXInfo;
-#define TYPE_VFIO_PCI "vfio-pci"
-OBJECT_DECLARE_SIMPLE_TYPE(VFIOPCIDevice, VFIO_PCI)
+/*
+ * TYPE_VFIO_PCI_BASE is an abstract type used to share code
+ * between VFIO implementations that use a kernel driver
+ * with those that use user sockets.
+ */
+#define TYPE_VFIO_PCI_BASE "vfio-pci-base"
+OBJECT_DECLARE_SIMPLE_TYPE(VFIOPCIDevice, VFIO_PCI_BASE)
struct VFIOPCIDevice {
PCIDevice pdev;
@@ -182,6 +187,13 @@ struct VFIOPCIDevice {
Notifier irqchip_change_notifier;
};
+#define TYPE_VFIO_PCI "vfio-pci"
+OBJECT_DECLARE_SIMPLE_TYPE(VFIOKernelPCIDevice, VFIO_PCI)
+
+struct VFIOKernelPCIDevice {
+ VFIOPCIDevice device;
+};
+
/* Use uin32_t for vendor & device so PCI_ANY_ID expands and cannot match hw */
static inline bool vfio_pci_is(VFIOPCIDevice *vdev, uint32_t vendor, uint32_t device)
{
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* Re: [PATCH v8 09/28] vfio: split out VFIOKernelPCIDevice
2025-02-19 14:48 ` [PATCH v8 09/28] vfio: split out VFIOKernelPCIDevice John Levon
@ 2025-04-03 17:13 ` Cédric Le Goater
2025-04-03 18:08 ` John Levon
0 siblings, 1 reply; 64+ messages in thread
From: Cédric Le Goater @ 2025-04-03 17:13 UTC (permalink / raw)
To: John Levon, qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin,
Jagannathan Raman, John Johnson, Elena Ufimtseva
On 2/19/25 15:48, John Levon wrote:
> From: Jagannathan Raman <jag.raman@oracle.com>
>
> Split out code specific to the kernel-side vfio implementation from the
> VFIOPCIDevice class into a VFIOKernelPCIDevice. The forthcoming
> VFIOUserPCIDevice will share the base VFIOPCIDevice class.
The new VFIOKernelPCIDevice struct is not needed. Please drop it.
I am not sure the new TYPE_VFIO_PCI_BASE class is needed too.
Are the properties the only difference ?
Thanks,
C.
> Originally-by: John Johnson <john.g.johnson@oracle.com>
> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
> Signed-off-by: John Levon <john.levon@nutanix.com>
> ---
> hw/vfio/helpers.c | 2 +-
> hw/vfio/pci.c | 107 ++++++++++++++++++++++++++++------------------
> hw/vfio/pci.h | 16 ++++++-
> 3 files changed, 80 insertions(+), 45 deletions(-)
>
> diff --git a/hw/vfio/helpers.c b/hw/vfio/helpers.c
> index 3c923d23b9..94bbc5747c 100644
> --- a/hw/vfio/helpers.c
> +++ b/hw/vfio/helpers.c
> @@ -744,7 +744,7 @@ bool vfio_device_hiod_realize(VFIODevice *vbasedev, Error **errp)
> VFIODevice *vfio_get_vfio_device(Object *obj)
> {
> if (object_dynamic_cast(obj, TYPE_VFIO_PCI)) {
> - return &VFIO_PCI(obj)->vbasedev;
> + return &VFIO_PCI(obj)->device.vbasedev;
> } else {
> return NULL;
> }
> diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
> index a4f99fc5e0..812743e9dd 100644
> --- a/hw/vfio/pci.c
> +++ b/hw/vfio/pci.c
> @@ -239,7 +239,7 @@ static void vfio_intx_update(VFIOPCIDevice *vdev, PCIINTxRoute *route)
>
> static void vfio_intx_routing_notifier(PCIDevice *pdev)
> {
> - VFIOPCIDevice *vdev = VFIO_PCI(pdev);
> + VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
> PCIINTxRoute route;
>
> if (vdev->interrupt != VFIO_INT_INTx) {
> @@ -514,7 +514,7 @@ static void vfio_update_kvm_msi_virq(VFIOMSIVector *vector, MSIMessage msg,
> static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr,
> MSIMessage *msg, IOHandler *handler)
> {
> - VFIOPCIDevice *vdev = VFIO_PCI(pdev);
> + VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
> VFIOMSIVector *vector;
> int ret;
> bool resizing = !!(vdev->nr_vectors < nr + 1);
> @@ -619,7 +619,7 @@ static int vfio_msix_vector_use(PCIDevice *pdev,
>
> static void vfio_msix_vector_release(PCIDevice *pdev, unsigned int nr)
> {
> - VFIOPCIDevice *vdev = VFIO_PCI(pdev);
> + VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
> VFIOMSIVector *vector = &vdev->msi_vectors[nr];
>
> trace_vfio_msix_vector_release(vdev->vbasedev.name, nr);
> @@ -1167,7 +1167,7 @@ static const MemoryRegionOps vfio_vga_ops = {
> */
> static void vfio_sub_page_bar_update_mapping(PCIDevice *pdev, int bar)
> {
> - VFIOPCIDevice *vdev = VFIO_PCI(pdev);
> + VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
> VFIORegion *region = &vdev->bars[bar].region;
> MemoryRegion *mmap_mr, *region_mr, *base_mr;
> PCIIORegion *r;
> @@ -1213,7 +1213,7 @@ static void vfio_sub_page_bar_update_mapping(PCIDevice *pdev, int bar)
> */
> uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len)
> {
> - VFIOPCIDevice *vdev = VFIO_PCI(pdev);
> + VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
> uint32_t emu_bits = 0, emu_val = 0, phys_val = 0, val;
>
> memcpy(&emu_bits, vdev->emulated_config_bits + addr, len);
> @@ -1246,7 +1246,7 @@ uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len)
> void vfio_pci_write_config(PCIDevice *pdev,
> uint32_t addr, uint32_t val, int len)
> {
> - VFIOPCIDevice *vdev = VFIO_PCI(pdev);
> + VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
> uint32_t val_le = cpu_to_le32(val);
>
> trace_vfio_pci_write_config(vdev->vbasedev.name, addr, val, len);
> @@ -3084,7 +3084,7 @@ static bool vfio_interrupt_setup(VFIOPCIDevice *vdev, Error **errp)
> static void vfio_realize(PCIDevice *pdev, Error **errp)
> {
> ERRP_GUARD();
> - VFIOPCIDevice *vdev = VFIO_PCI(pdev);
> + VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
> VFIODevice *vbasedev = &vdev->vbasedev;
> int i, ret;
> char uuid[UUID_STR_LEN];
> @@ -3274,7 +3274,7 @@ error:
>
> static void vfio_instance_finalize(Object *obj)
> {
> - VFIOPCIDevice *vdev = VFIO_PCI(obj);
> + VFIOPCIDevice *vdev = VFIO_PCI_BASE(obj);
>
> vfio_display_finalize(vdev);
> vfio_bars_finalize(vdev);
> @@ -3292,7 +3292,7 @@ static void vfio_instance_finalize(Object *obj)
>
> static void vfio_exitfn(PCIDevice *pdev)
> {
> - VFIOPCIDevice *vdev = VFIO_PCI(pdev);
> + VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
> VFIODevice *vbasedev = &vdev->vbasedev;
>
> vfio_unregister_req_notifier(vdev);
> @@ -3316,7 +3316,7 @@ static void vfio_exitfn(PCIDevice *pdev)
>
> static void vfio_pci_reset(DeviceState *dev)
> {
> - VFIOPCIDevice *vdev = VFIO_PCI(dev);
> + VFIOPCIDevice *vdev = VFIO_PCI_BASE(dev);
>
> trace_vfio_pci_reset(vdev->vbasedev.name);
>
> @@ -3356,7 +3356,7 @@ post_reset:
> static void vfio_instance_init(Object *obj)
> {
> PCIDevice *pci_dev = PCI_DEVICE(obj);
> - VFIOPCIDevice *vdev = VFIO_PCI(obj);
> + VFIOPCIDevice *vdev = VFIO_PCI_BASE(obj);
> VFIODevice *vbasedev = &vdev->vbasedev;
>
> device_add_bootindex_property(obj, &vdev->bootindex,
> @@ -3377,28 +3377,15 @@ static void vfio_instance_init(Object *obj)
> pci_dev->cap_present |= QEMU_PCI_CAP_EXPRESS;
> }
>
> -static const Property vfio_pci_dev_properties[] = {
> - DEFINE_PROP_PCI_HOST_DEVADDR("host", VFIOPCIDevice, host),
> - DEFINE_PROP_UUID_NODEFAULT("vf-token", VFIOPCIDevice, vf_token),
> - DEFINE_PROP_STRING("sysfsdev", VFIOPCIDevice, vbasedev.sysfsdev),
> +static const Property vfio_pci_base_dev_properties[] = {
> DEFINE_PROP_ON_OFF_AUTO("x-pre-copy-dirty-page-tracking", VFIOPCIDevice,
> vbasedev.pre_copy_dirty_page_tracking,
> ON_OFF_AUTO_ON),
> DEFINE_PROP_ON_OFF_AUTO("x-device-dirty-page-tracking", VFIOPCIDevice,
> vbasedev.device_dirty_page_tracking,
> ON_OFF_AUTO_ON),
> - DEFINE_PROP_ON_OFF_AUTO("display", VFIOPCIDevice,
> - display, ON_OFF_AUTO_OFF),
> - DEFINE_PROP_UINT32("xres", VFIOPCIDevice, display_xres, 0),
> - DEFINE_PROP_UINT32("yres", VFIOPCIDevice, display_yres, 0),
> DEFINE_PROP_UINT32("x-intx-mmap-timeout-ms", VFIOPCIDevice,
> intx.mmap_timeout, 1100),
> - DEFINE_PROP_BIT("x-vga", VFIOPCIDevice, features,
> - VFIO_FEATURE_ENABLE_VGA_BIT, false),
> - DEFINE_PROP_BIT("x-req", VFIOPCIDevice, features,
> - VFIO_FEATURE_ENABLE_REQ_BIT, true),
> - DEFINE_PROP_BIT("x-igd-opregion", VFIOPCIDevice, features,
> - VFIO_FEATURE_ENABLE_IGD_OPREGION_BIT, false),
> DEFINE_PROP_ON_OFF_AUTO("enable-migration", VFIOPCIDevice,
> vbasedev.enable_migration, ON_OFF_AUTO_AUTO),
> DEFINE_PROP_BOOL("migration-events", VFIOPCIDevice,
> @@ -3409,8 +3396,6 @@ static const Property vfio_pci_dev_properties[] = {
> DEFINE_PROP_BOOL("x-no-kvm-intx", VFIOPCIDevice, no_kvm_intx, false),
> DEFINE_PROP_BOOL("x-no-kvm-msi", VFIOPCIDevice, no_kvm_msi, false),
> DEFINE_PROP_BOOL("x-no-kvm-msix", VFIOPCIDevice, no_kvm_msix, false),
> - DEFINE_PROP_BOOL("x-no-geforce-quirks", VFIOPCIDevice,
> - no_geforce_quirks, false),
> DEFINE_PROP_BOOL("x-no-kvm-ioeventfd", VFIOPCIDevice, no_kvm_ioeventfd,
> false),
> DEFINE_PROP_BOOL("x-no-vfio-ioeventfd", VFIOPCIDevice, no_vfio_ioeventfd,
> @@ -3421,12 +3406,57 @@ static const Property vfio_pci_dev_properties[] = {
> sub_vendor_id, PCI_ANY_ID),
> DEFINE_PROP_UINT32("x-pci-sub-device-id", VFIOPCIDevice,
> sub_device_id, PCI_ANY_ID),
> + DEFINE_PROP_OFF_AUTO_PCIBAR("x-msix-relocation", VFIOPCIDevice, msix_relo,
> + OFF_AUTO_PCIBAR_OFF),
> +};
> +
> +
> +static void vfio_pci_base_dev_class_init(ObjectClass *klass, void *data)
> +{
> + DeviceClass *dc = DEVICE_CLASS(klass);
> + PCIDeviceClass *pdc = PCI_DEVICE_CLASS(klass);
> +
> + device_class_set_props(dc, vfio_pci_base_dev_properties);
> + dc->desc = "VFIO PCI base device";
> + set_bit(DEVICE_CATEGORY_MISC, dc->categories);
> + pdc->exit = vfio_exitfn;
> + pdc->config_read = vfio_pci_read_config;
> + pdc->config_write = vfio_pci_write_config;
> +}
> +
> +static const TypeInfo vfio_pci_base_dev_info = {
> + .name = TYPE_VFIO_PCI_BASE,
> + .parent = TYPE_PCI_DEVICE,
> + .instance_size = 0,
> + .abstract = true,
> + .class_init = vfio_pci_base_dev_class_init,
> + .interfaces = (InterfaceInfo[]) {
> + { INTERFACE_PCIE_DEVICE },
> + { INTERFACE_CONVENTIONAL_PCI_DEVICE },
> + { }
> + },
> +};
> +
> +static const Property vfio_pci_dev_properties[] = {
> + DEFINE_PROP_PCI_HOST_DEVADDR("host", VFIOPCIDevice, host),
> + DEFINE_PROP_UUID_NODEFAULT("vf-token", VFIOPCIDevice, vf_token),
> + DEFINE_PROP_STRING("sysfsdev", VFIOPCIDevice, vbasedev.sysfsdev),
> + DEFINE_PROP_ON_OFF_AUTO("display", VFIOPCIDevice,
> + display, ON_OFF_AUTO_OFF),
> + DEFINE_PROP_UINT32("xres", VFIOPCIDevice, display_xres, 0),
> + DEFINE_PROP_UINT32("yres", VFIOPCIDevice, display_yres, 0),
> + DEFINE_PROP_BIT("x-vga", VFIOPCIDevice, features,
> + VFIO_FEATURE_ENABLE_VGA_BIT, false),
> + DEFINE_PROP_BIT("x-req", VFIOPCIDevice, features,
> + VFIO_FEATURE_ENABLE_REQ_BIT, true),
> + DEFINE_PROP_BIT("x-igd-opregion", VFIOPCIDevice, features,
> + VFIO_FEATURE_ENABLE_IGD_OPREGION_BIT, false),
> + DEFINE_PROP_BOOL("x-no-geforce-quirks", VFIOPCIDevice,
> + no_geforce_quirks, false),
> DEFINE_PROP_UINT32("x-igd-gms", VFIOPCIDevice, igd_gms, 0),
> DEFINE_PROP_UNSIGNED_NODEFAULT("x-nv-gpudirect-clique", VFIOPCIDevice,
> nv_gpudirect_clique,
> qdev_prop_nv_gpudirect_clique, uint8_t),
> - DEFINE_PROP_OFF_AUTO_PCIBAR("x-msix-relocation", VFIOPCIDevice, msix_relo,
> - OFF_AUTO_PCIBAR_OFF),
> #ifdef CONFIG_IOMMUFD
> DEFINE_PROP_LINK("iommufd", VFIOPCIDevice, vbasedev.iommufd,
> TYPE_IOMMUFD_BACKEND, IOMMUFDBackend *),
> @@ -3437,7 +3467,8 @@ static const Property vfio_pci_dev_properties[] = {
> #ifdef CONFIG_IOMMUFD
> static void vfio_pci_set_fd(Object *obj, const char *str, Error **errp)
> {
> - vfio_device_set_fd(&VFIO_PCI(obj)->vbasedev, str, errp);
> + VFIOPCIDevice *vdev = VFIO_PCI_BASE(obj);
> + vfio_device_set_fd(&vdev->vbasedev, str, errp);
> }
> #endif
>
> @@ -3452,25 +3483,16 @@ static void vfio_pci_dev_class_init(ObjectClass *klass, void *data)
> object_class_property_add_str(klass, "fd", NULL, vfio_pci_set_fd);
> #endif
> dc->desc = "VFIO-based PCI device assignment";
> - set_bit(DEVICE_CATEGORY_MISC, dc->categories);
> pdc->realize = vfio_realize;
> - pdc->exit = vfio_exitfn;
> - pdc->config_read = vfio_pci_read_config;
> - pdc->config_write = vfio_pci_write_config;
> }
>
> static const TypeInfo vfio_pci_dev_info = {
> .name = TYPE_VFIO_PCI,
> - .parent = TYPE_PCI_DEVICE,
> - .instance_size = sizeof(VFIOPCIDevice),
> + .parent = TYPE_VFIO_PCI_BASE,
> + .instance_size = sizeof(VFIOKernelPCIDevice),
> .class_init = vfio_pci_dev_class_init,
> .instance_init = vfio_instance_init,
> .instance_finalize = vfio_instance_finalize,
> - .interfaces = (InterfaceInfo[]) {
> - { INTERFACE_PCIE_DEVICE },
> - { INTERFACE_CONVENTIONAL_PCI_DEVICE },
> - { }
> - },
> };
>
> static const Property vfio_pci_dev_nohotplug_properties[] = {
> @@ -3490,12 +3512,13 @@ static void vfio_pci_nohotplug_dev_class_init(ObjectClass *klass, void *data)
> static const TypeInfo vfio_pci_nohotplug_dev_info = {
> .name = TYPE_VFIO_PCI_NOHOTPLUG,
> .parent = TYPE_VFIO_PCI,
> - .instance_size = sizeof(VFIOPCIDevice),
> + .instance_size = sizeof(VFIOKernelPCIDevice),
> .class_init = vfio_pci_nohotplug_dev_class_init,
> };
>
> static void register_vfio_pci_dev_type(void)
> {
> + type_register_static(&vfio_pci_base_dev_info);
> type_register_static(&vfio_pci_dev_info);
> type_register_static(&vfio_pci_nohotplug_dev_info);
> }
> diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h
> index 43c166680a..8e79740ddb 100644
> --- a/hw/vfio/pci.h
> +++ b/hw/vfio/pci.h
> @@ -116,8 +116,13 @@ typedef struct VFIOMSIXInfo {
> bool noresize;
> } VFIOMSIXInfo;
>
> -#define TYPE_VFIO_PCI "vfio-pci"
> -OBJECT_DECLARE_SIMPLE_TYPE(VFIOPCIDevice, VFIO_PCI)
> +/*
> + * TYPE_VFIO_PCI_BASE is an abstract type used to share code
> + * between VFIO implementations that use a kernel driver
> + * with those that use user sockets.
> + */
> +#define TYPE_VFIO_PCI_BASE "vfio-pci-base"
> +OBJECT_DECLARE_SIMPLE_TYPE(VFIOPCIDevice, VFIO_PCI_BASE)
>
> struct VFIOPCIDevice {
> PCIDevice pdev;
> @@ -182,6 +187,13 @@ struct VFIOPCIDevice {
> Notifier irqchip_change_notifier;
> };
>
> +#define TYPE_VFIO_PCI "vfio-pci"
> +OBJECT_DECLARE_SIMPLE_TYPE(VFIOKernelPCIDevice, VFIO_PCI)
> +
> +struct VFIOKernelPCIDevice {
> + VFIOPCIDevice device;
> +};
> +
> /* Use uin32_t for vendor & device so PCI_ANY_ID expands and cannot match hw */
> static inline bool vfio_pci_is(VFIOPCIDevice *vdev, uint32_t vendor, uint32_t device)
> {
^ permalink raw reply [flat|nested] 64+ messages in thread* Re: [PATCH v8 09/28] vfio: split out VFIOKernelPCIDevice
2025-04-03 17:13 ` Cédric Le Goater
@ 2025-04-03 18:08 ` John Levon
2025-04-04 12:49 ` Cédric Le Goater
0 siblings, 1 reply; 64+ messages in thread
From: John Levon @ 2025-04-03 18:08 UTC (permalink / raw)
To: Cédric Le Goater
Cc: qemu-devel, Jason Herne, Thanos Makatos, Halil Pasic,
Daniel P. Berrangé, Eric Farman, Tony Krowiak, Thomas Huth,
qemu-s390x, Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin,
Jagannathan Raman, John Johnson, Elena Ufimtseva
On Thu, Apr 03, 2025 at 07:13:30PM +0200, Cédric Le Goater wrote:
> On 2/19/25 15:48, John Levon wrote:
> > From: Jagannathan Raman <jag.raman@oracle.com>
> >
> > Split out code specific to the kernel-side vfio implementation from the
> > VFIOPCIDevice class into a VFIOKernelPCIDevice. The forthcoming
> > VFIOUserPCIDevice will share the base VFIOPCIDevice class.
>
> The new VFIOKernelPCIDevice struct is not needed. Please drop it.
I presume the idea was if something was ever needed in the struct that was
kernel vfio specific, it could go there. But sure.
> I am not sure the new TYPE_VFIO_PCI_BASE class is needed too.
> Are the properties the only difference ?
I'm not sure if you're talking about the type specifically (a bit sketchy on how
qemu's klass/type system works) or the existence of the base/kernel/user
separation at all.
If it's possible to set up vfio_user_pci_dev_info and its callbacks without
needing a sub-type then maybe not? Honestly I'm not really sure why we have
sub-classes and inheritance like this.
regards
john
^ permalink raw reply [flat|nested] 64+ messages in thread
* Re: [PATCH v8 09/28] vfio: split out VFIOKernelPCIDevice
2025-04-03 18:08 ` John Levon
@ 2025-04-04 12:49 ` Cédric Le Goater
2025-04-04 14:21 ` John Levon
0 siblings, 1 reply; 64+ messages in thread
From: Cédric Le Goater @ 2025-04-04 12:49 UTC (permalink / raw)
To: John Levon
Cc: qemu-devel, Jason Herne, Thanos Makatos, Halil Pasic,
Daniel P. Berrangé, Eric Farman, Tony Krowiak, Thomas Huth,
qemu-s390x, Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin,
Jagannathan Raman, John Johnson, Elena Ufimtseva
On 4/3/25 20:08, John Levon wrote:
> On Thu, Apr 03, 2025 at 07:13:30PM +0200, Cédric Le Goater wrote:
>
>> On 2/19/25 15:48, John Levon wrote:
>>> From: Jagannathan Raman <jag.raman@oracle.com>
>>>
>>> Split out code specific to the kernel-side vfio implementation from the
>>> VFIOPCIDevice class into a VFIOKernelPCIDevice. The forthcoming
>>> VFIOUserPCIDevice will share the base VFIOPCIDevice class.
>>
>> The new VFIOKernelPCIDevice struct is not needed. Please drop it.
>
> I presume the idea was if something was ever needed in the struct that was
> kernel vfio specific, it could go there. But sure.
> >> I am not sure the new TYPE_VFIO_PCI_BASE class is needed too.
>> Are the properties the only difference ?
>
> I'm not sure if you're talking about the type specifically (a bit sketchy on how
> qemu's klass/type system works) or the existence of the base/kernel/user
> separation at all.
I am talking about the base/kernel/user separation.
> If it's possible to set up vfio_user_pci_dev_info and its callbacks without
> needing a sub-type then maybe not?
I think the vfio-user-device could inherit directly from vfio-pci
and override the io ops callbacks. It would minimize the changes.
> Honestly I'm not really sure why we have sub-classes and inheritance like this.
The VFIO Devices have a double nature : VFIO and a bus device
nature (PCI, AP, etc) and multi-inheritance is not (well)
supported by QOM. We have interfaces but they are stateless.
Thanks,
C.
^ permalink raw reply [flat|nested] 64+ messages in thread
* Re: [PATCH v8 09/28] vfio: split out VFIOKernelPCIDevice
2025-04-04 12:49 ` Cédric Le Goater
@ 2025-04-04 14:21 ` John Levon
2025-04-04 14:48 ` Cédric Le Goater
0 siblings, 1 reply; 64+ messages in thread
From: John Levon @ 2025-04-04 14:21 UTC (permalink / raw)
To: Cédric Le Goater
Cc: qemu-devel, Jason Herne, Thanos Makatos, Halil Pasic,
Daniel P. Berrangé, Eric Farman, Tony Krowiak, Thomas Huth,
qemu-s390x, Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin,
Jagannathan Raman, John Johnson, Elena Ufimtseva
On Fri, Apr 04, 2025 at 02:49:40PM +0200, Cédric Le Goater wrote:
> > If it's possible to set up vfio_user_pci_dev_info and its callbacks without
> > needing a sub-type then maybe not?
>
> I think the vfio-user-device could inherit directly from vfio-pci
> and override the io ops callbacks. It would minimize the changes.
We'd get all the kernel-vfio specific properties then though?
regards
john
^ permalink raw reply [flat|nested] 64+ messages in thread
* Re: [PATCH v8 09/28] vfio: split out VFIOKernelPCIDevice
2025-04-04 14:21 ` John Levon
@ 2025-04-04 14:48 ` Cédric Le Goater
2025-04-04 15:44 ` John Levon
0 siblings, 1 reply; 64+ messages in thread
From: Cédric Le Goater @ 2025-04-04 14:48 UTC (permalink / raw)
To: John Levon
Cc: qemu-devel, Jason Herne, Thanos Makatos, Halil Pasic,
Daniel P. Berrangé, Eric Farman, Tony Krowiak, Thomas Huth,
qemu-s390x, Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin,
Jagannathan Raman, John Johnson, Elena Ufimtseva
On 4/4/25 16:21, John Levon wrote:
> On Fri, Apr 04, 2025 at 02:49:40PM +0200, Cédric Le Goater wrote:
>
>>> If it's possible to set up vfio_user_pci_dev_info and its callbacks without
>>> needing a sub-type then maybe not?
>>
>> I think the vfio-user-device could inherit directly from vfio-pci
>> and override the io ops callbacks. It would minimize the changes.
>
> We'd get all the kernel-vfio specific properties then though?
OK. That's what I thought. It was not clear in the diff.
Let's give it a try in the next spin but please remove the
VFIOKernelPCIDevice type. it is not needed.
Thanks,
C.
^ permalink raw reply [flat|nested] 64+ messages in thread
* Re: [PATCH v8 09/28] vfio: split out VFIOKernelPCIDevice
2025-04-04 14:48 ` Cédric Le Goater
@ 2025-04-04 15:44 ` John Levon
0 siblings, 0 replies; 64+ messages in thread
From: John Levon @ 2025-04-04 15:44 UTC (permalink / raw)
To: Cédric Le Goater
Cc: qemu-devel, Jason Herne, Thanos Makatos, Halil Pasic,
Daniel P. Berrangé, Eric Farman, Tony Krowiak, Thomas Huth,
qemu-s390x, Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin,
Jagannathan Raman, John Johnson, Elena Ufimtseva
On Fri, Apr 04, 2025 at 04:48:10PM +0200, Cédric Le Goater wrote:
> On 4/4/25 16:21, John Levon wrote:
> > On Fri, Apr 04, 2025 at 02:49:40PM +0200, Cédric Le Goater wrote:
> >
> > > > If it's possible to set up vfio_user_pci_dev_info and its callbacks without
> > > > needing a sub-type then maybe not?
> > >
> > > I think the vfio-user-device could inherit directly from vfio-pci
> > > and override the io ops callbacks. It would minimize the changes.
> >
> > We'd get all the kernel-vfio specific properties then though?
>
> OK. That's what I thought. It was not clear in the diff.
>
> Let's give it a try in the next spin but please remove the
> VFIOKernelPCIDevice type. it is not needed.
Sure
thanks
john
^ permalink raw reply [flat|nested] 64+ messages in thread
* [PATCH v8 10/28] vfio: add device IO ops vector
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (8 preceding siblings ...)
2025-02-19 14:48 ` [PATCH v8 09/28] vfio: split out VFIOKernelPCIDevice John Levon
@ 2025-02-19 14:48 ` John Levon
2025-04-04 14:36 ` Cédric Le Goater
2025-02-19 14:48 ` [PATCH v8 11/28] vfio-user: introduce vfio-user protocol specification John Levon
` (20 subsequent siblings)
30 siblings, 1 reply; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin, Jagannathan Raman, John Johnson,
Elena Ufimtseva
From: Jagannathan Raman <jag.raman@oracle.com>
For vfio-user, device operations such as IRQ handling and region
read/writes are implemented in userspace over the control socket, not
ioctl() or read()/write() to the vfio kernel driver; add an ops vector
to generalize this, and implement vfio_dev_io_ioctl for interacting
with the kernel vfio driver.
The ops consistently use the "-errno" return style, as the vfio-user
implementations get their errors from response messages not from the
kernel; adjust the callers to handle this as necessary.
Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
---
hw/vfio/ap.c | 2 +-
hw/vfio/ccw.c | 2 +-
hw/vfio/common.c | 13 +--
hw/vfio/helpers.c | 110 ++++++++++++++++++++++---
hw/vfio/pci.c | 147 ++++++++++++++++++++++------------
hw/vfio/platform.c | 2 +-
include/hw/vfio/vfio-common.h | 27 ++++++-
7 files changed, 227 insertions(+), 76 deletions(-)
diff --git a/hw/vfio/ap.c b/hw/vfio/ap.c
index 30b08ad375..1adce1ab40 100644
--- a/hw/vfio/ap.c
+++ b/hw/vfio/ap.c
@@ -228,7 +228,7 @@ static void vfio_ap_instance_init(Object *obj)
* handle ram_block_discard_disable().
*/
vfio_device_init(vbasedev, VFIO_DEVICE_TYPE_AP, &vfio_ap_ops,
- DEVICE(vapdev), true);
+ &vfio_dev_io_ioctl, DEVICE(vapdev), true);
/* AP device is mdev type device */
vbasedev->mdev = true;
diff --git a/hw/vfio/ccw.c b/hw/vfio/ccw.c
index 22378d50bc..8c16648819 100644
--- a/hw/vfio/ccw.c
+++ b/hw/vfio/ccw.c
@@ -682,7 +682,7 @@ static void vfio_ccw_instance_init(Object *obj)
* ram_block_discard_disable().
*/
vfio_device_init(vbasedev, VFIO_DEVICE_TYPE_CCW, &vfio_ccw_ops,
- DEVICE(vcdev), true);
+ &vfio_dev_io_ioctl, DEVICE(vcdev), true);
}
#ifdef CONFIG_IOMMUFD
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 1866b3d3c5..cc0c0f7fc7 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -971,7 +971,7 @@ static void vfio_devices_dma_logging_stop(VFIOContainerBase *bcontainer)
continue;
}
- if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) {
+ if (vbasedev->io->device_feature(vbasedev, feature)) {
warn_report("%s: Failed to stop DMA logging, err %d (%s)",
vbasedev->name, -errno, strerror(errno));
}
@@ -1074,10 +1074,9 @@ static bool vfio_devices_dma_logging_start(VFIOContainerBase *bcontainer,
continue;
}
- ret = ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature);
+ ret = vbasedev->io->device_feature(vbasedev, feature);
if (ret) {
- ret = -errno;
- error_setg_errno(errp, errno, "%s: Failed to start DMA logging",
+ error_setg_errno(errp, -ret, "%s: Failed to start DMA logging",
vbasedev->name);
goto out;
}
@@ -1145,6 +1144,7 @@ static int vfio_device_dma_logging_report(VFIODevice *vbasedev, hwaddr iova,
struct vfio_device_feature *feature = (struct vfio_device_feature *)buf;
struct vfio_device_feature_dma_logging_report *report =
(struct vfio_device_feature_dma_logging_report *)feature->data;
+ int ret;
report->iova = iova;
report->length = size;
@@ -1155,8 +1155,9 @@ static int vfio_device_dma_logging_report(VFIODevice *vbasedev, hwaddr iova,
feature->flags = VFIO_DEVICE_FEATURE_GET |
VFIO_DEVICE_FEATURE_DMA_LOGGING_REPORT;
- if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) {
- return -errno;
+ ret = vbasedev->io->device_feature(vbasedev, feature);
+ if (ret) {
+ return -ret;
}
return 0;
diff --git a/hw/vfio/helpers.c b/hw/vfio/helpers.c
index 94bbc5747c..bef1540295 100644
--- a/hw/vfio/helpers.c
+++ b/hw/vfio/helpers.c
@@ -44,7 +44,7 @@ void vfio_disable_irqindex(VFIODevice *vbasedev, int index)
.count = 0,
};
- ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
+ vbasedev->io->set_irqs(vbasedev, &irq_set);
}
void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index)
@@ -57,7 +57,7 @@ void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index)
.count = 1,
};
- ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
+ vbasedev->io->set_irqs(vbasedev, &irq_set);
}
void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index)
@@ -70,7 +70,7 @@ void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index)
.count = 1,
};
- ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
+ vbasedev->io->set_irqs(vbasedev, &irq_set);
}
static inline const char *action_to_str(int action)
@@ -117,6 +117,7 @@ bool vfio_set_irq_signaling(VFIODevice *vbasedev, int index, int subindex,
int argsz;
const char *name;
int32_t *pfd;
+ int ret;
argsz = sizeof(*irq_set) + sizeof(*pfd);
@@ -129,7 +130,9 @@ bool vfio_set_irq_signaling(VFIODevice *vbasedev, int index, int subindex,
pfd = (int32_t *)&irq_set->data;
*pfd = fd;
- if (!ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, irq_set)) {
+ ret = vbasedev->io->set_irqs(vbasedev, irq_set);
+
+ if (!ret) {
return true;
}
@@ -161,6 +164,7 @@ void vfio_region_write(void *opaque, hwaddr addr,
uint32_t dword;
uint64_t qword;
} buf;
+ int ret;
switch (size) {
case 1:
@@ -180,11 +184,12 @@ void vfio_region_write(void *opaque, hwaddr addr,
break;
}
- if (pwrite(vbasedev->fd, &buf, size, region->fd_offset + addr) != size) {
+ ret = vbasedev->io->region_write(vbasedev, region->nr, addr, size, &buf);
+ if (ret != size) {
error_report("%s(%s:region%d+0x%"HWADDR_PRIx", 0x%"PRIx64
- ",%d) failed: %m",
+ ",%d) failed: %s",
__func__, vbasedev->name, region->nr,
- addr, data, size);
+ addr, data, size, ret < 0 ? strerror(ret) : "short write");
}
trace_vfio_region_write(vbasedev->name, region->nr, addr, data, size);
@@ -212,11 +217,13 @@ uint64_t vfio_region_read(void *opaque,
uint64_t qword;
} buf;
uint64_t data = 0;
+ int ret;
- if (pread(vbasedev->fd, &buf, size, region->fd_offset + addr) != size) {
- error_report("%s(%s:region%d+0x%"HWADDR_PRIx", %d) failed: %m",
+ ret = vbasedev->io->region_read(vbasedev, region->nr, addr, size, &buf);
+ if (ret != size) {
+ error_report("%s(%s:region%d+0x%"HWADDR_PRIx", %d) failed: %s",
__func__, vbasedev->name, region->nr,
- addr, size);
+ addr, size, ret < 0 ? strerror(ret) : "short read");
return (uint64_t)-1;
}
switch (size) {
@@ -561,6 +568,7 @@ int vfio_get_region_info(VFIODevice *vbasedev, int index,
struct vfio_region_info **info)
{
size_t argsz = sizeof(struct vfio_region_info);
+ int ret;
/* create region cache */
if (vbasedev->regions == NULL) {
@@ -579,10 +587,11 @@ int vfio_get_region_info(VFIODevice *vbasedev, int index,
retry:
(*info)->argsz = argsz;
- if (ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, *info)) {
+ ret = vbasedev->io->get_region_info(vbasedev, *info);
+ if (ret != 0) {
g_free(*info);
*info = NULL;
- return -errno;
+ return ret;
}
if ((*info)->argsz > argsz) {
@@ -689,11 +698,12 @@ void vfio_device_set_fd(VFIODevice *vbasedev, const char *str, Error **errp)
}
void vfio_device_init(VFIODevice *vbasedev, int type, VFIODeviceOps *ops,
- DeviceState *dev, bool ram_discard)
+ VFIODeviceIO *io, DeviceState *dev, bool ram_discard)
{
vbasedev->type = type;
vbasedev->ops = ops;
vbasedev->dev = dev;
+ vbasedev->io = io;
vbasedev->fd = -1;
vbasedev->ram_block_discard_allowed = ram_discard;
@@ -749,3 +759,77 @@ VFIODevice *vfio_get_vfio_device(Object *obj)
return NULL;
}
}
+
+/*
+ * Traditional ioctl() based io
+ */
+
+static int vfio_io_device_feature(VFIODevice *vbasedev,
+ struct vfio_device_feature *feature)
+{
+ int ret;
+
+ ret = ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature);
+
+ return ret < 0 ? -errno : ret;
+}
+
+static int vfio_io_get_region_info(VFIODevice *vbasedev,
+ struct vfio_region_info *info)
+{
+ int ret;
+
+ ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, info);
+
+ return ret < 0 ? -errno : ret;
+}
+
+static int vfio_io_get_irq_info(VFIODevice *vbasedev,
+ struct vfio_irq_info *info)
+{
+ int ret;
+
+ ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_IRQ_INFO, info);
+
+ return ret < 0 ? -errno : ret;
+}
+
+static int vfio_io_set_irqs(VFIODevice *vbasedev, struct vfio_irq_set *irqs)
+{
+ int ret;
+
+ ret = ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, irqs);
+
+ return ret < 0 ? -errno : ret;
+}
+
+static int vfio_io_region_read(VFIODevice *vbasedev, uint8_t index, off_t off,
+ uint32_t size, void *data)
+{
+ struct vfio_region_info *info = vbasedev->regions[index];
+ int ret;
+
+ ret = pread(vbasedev->fd, data, size, info->offset + off);
+
+ return ret < 0 ? -errno : ret;
+}
+
+static int vfio_io_region_write(VFIODevice *vbasedev, uint8_t index, off_t off,
+ uint32_t size, void *data)
+{
+ struct vfio_region_info *info = vbasedev->regions[index];
+ int ret;
+
+ ret = pwrite(vbasedev->fd, data, size, info->offset + off);
+
+ return ret < 0 ? -errno : ret;
+}
+
+VFIODeviceIO vfio_dev_io_ioctl = {
+ .device_feature = vfio_io_device_feature,
+ .get_region_info = vfio_io_get_region_info,
+ .get_irq_info = vfio_io_get_irq_info,
+ .set_irqs = vfio_io_set_irqs,
+ .region_read = vfio_io_region_read,
+ .region_write = vfio_io_region_write,
+};
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 812743e9dd..a9cc9366fb 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -45,6 +45,14 @@
#include "migration/qemu-file.h"
#include "system/iommufd.h"
+/* convenience macros for PCI config space */
+#define VDEV_CONFIG_READ(vbasedev, off, size, data) \
+ ((vbasedev)->io->region_read((vbasedev), VFIO_PCI_CONFIG_REGION_INDEX, \
+ (off), (size), (data)))
+#define VDEV_CONFIG_WRITE(vbasedev, off, size, data) \
+ ((vbasedev)->io->region_write((vbasedev), VFIO_PCI_CONFIG_REGION_INDEX, \
+ (off), (size), (data)))
+
#define TYPE_VFIO_PCI_NOHOTPLUG "vfio-pci-nohotplug"
/* Protected by BQL */
@@ -379,6 +387,7 @@ static void vfio_msi_interrupt(void *opaque)
static int vfio_enable_msix_no_vec(VFIOPCIDevice *vdev)
{
g_autofree struct vfio_irq_set *irq_set = NULL;
+ VFIODevice *vbasedev = &vdev->vbasedev;
int ret = 0, argsz;
int32_t *fd;
@@ -394,7 +403,7 @@ static int vfio_enable_msix_no_vec(VFIOPCIDevice *vdev)
fd = (int32_t *)&irq_set->data;
*fd = -1;
- ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set);
+ ret = vbasedev->io->set_irqs(vbasedev, irq_set);
return ret;
}
@@ -453,7 +462,7 @@ static int vfio_enable_vectors(VFIOPCIDevice *vdev, bool msix)
fds[i] = fd;
}
- ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set);
+ ret = vdev->vbasedev.io->set_irqs(&vdev->vbasedev, irq_set);
g_free(irq_set);
@@ -763,7 +772,8 @@ retry:
ret = vfio_enable_vectors(vdev, false);
if (ret) {
if (ret < 0) {
- error_report("vfio: Error: Failed to setup MSI fds: %m");
+ error_report("vfio: Error: Failed to setup MSI fds: %s",
+ strerror(-ret));
} else {
error_report("vfio: Error: Failed to enable %d "
"MSI vectors, retry with %d", vdev->nr_vectors, ret);
@@ -879,14 +889,17 @@ static void vfio_update_msi(VFIOPCIDevice *vdev)
static void vfio_pci_load_rom(VFIOPCIDevice *vdev)
{
+ VFIODevice *vbasedev = &vdev->vbasedev;
struct vfio_region_info *reg_info = NULL;
uint64_t size;
off_t off = 0;
ssize_t bytes;
+ int ret;
- if (vfio_get_region_info(&vdev->vbasedev,
- VFIO_PCI_ROM_REGION_INDEX, ®_info)) {
- error_report("vfio: Error getting ROM info: %m");
+ ret = vfio_get_region_info(vbasedev, VFIO_PCI_ROM_REGION_INDEX, ®_info);
+
+ if (ret != 0) {
+ error_report("vfio: Error getting ROM info: %s", strerror(-ret));
return;
}
@@ -911,18 +924,19 @@ static void vfio_pci_load_rom(VFIOPCIDevice *vdev)
memset(vdev->rom, 0xff, size);
while (size) {
- bytes = pread(vdev->vbasedev.fd, vdev->rom + off,
- size, vdev->rom_offset + off);
+ bytes = vbasedev->io->region_read(vbasedev, VFIO_PCI_ROM_REGION_INDEX,
+ off, size, vdev->rom + off);
if (bytes == 0) {
break;
} else if (bytes > 0) {
off += bytes;
size -= bytes;
} else {
- if (errno == EINTR || errno == EAGAIN) {
+ if (bytes == -EINTR || bytes == -EAGAIN) {
continue;
}
- error_report("vfio: Error reading device ROM: %m");
+ error_report("vfio: Error reading device ROM: %s",
+ strerror(-bytes));
break;
}
}
@@ -1010,10 +1024,9 @@ static const MemoryRegionOps vfio_rom_ops = {
static void vfio_pci_size_rom(VFIOPCIDevice *vdev)
{
+ VFIODevice *vbasedev = &vdev->vbasedev;
uint32_t orig, size = cpu_to_le32((uint32_t)PCI_ROM_ADDRESS_MASK);
- off_t offset = vdev->config_offset + PCI_ROM_ADDRESS;
char *name;
- int fd = vdev->vbasedev.fd;
if (vdev->pdev.romfile || !vdev->pdev.rom_bar) {
/* Since pci handles romfile, just print a message and return */
@@ -1030,11 +1043,12 @@ static void vfio_pci_size_rom(VFIOPCIDevice *vdev)
* Use the same size ROM BAR as the physical device. The contents
* will get filled in later when the guest tries to read it.
*/
- if (pread(fd, &orig, 4, offset) != 4 ||
- pwrite(fd, &size, 4, offset) != 4 ||
- pread(fd, &size, 4, offset) != 4 ||
- pwrite(fd, &orig, 4, offset) != 4) {
- error_report("%s(%s) failed: %m", __func__, vdev->vbasedev.name);
+ if (VDEV_CONFIG_READ(vbasedev, PCI_ROM_ADDRESS, 4, &orig) != 4 ||
+ VDEV_CONFIG_WRITE(vbasedev, PCI_ROM_ADDRESS, 4, &size) != 4 ||
+ VDEV_CONFIG_READ(vbasedev, PCI_ROM_ADDRESS, 4, &size) != 4 ||
+ VDEV_CONFIG_WRITE(vbasedev, PCI_ROM_ADDRESS, 4, &orig) != 4) {
+
+ error_report("%s(%s) ROM access failed", __func__, vbasedev->name);
return;
}
@@ -1214,6 +1228,7 @@ static void vfio_sub_page_bar_update_mapping(PCIDevice *pdev, int bar)
uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len)
{
VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
+ VFIODevice *vbasedev = &vdev->vbasedev;
uint32_t emu_bits = 0, emu_val = 0, phys_val = 0, val;
memcpy(&emu_bits, vdev->emulated_config_bits + addr, len);
@@ -1226,12 +1241,13 @@ uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len)
if (~emu_bits & (0xffffffffU >> (32 - len * 8))) {
ssize_t ret;
- ret = pread(vdev->vbasedev.fd, &phys_val, len,
- vdev->config_offset + addr);
+ ret = VDEV_CONFIG_READ(vbasedev, addr, len, &phys_val);
if (ret != len) {
- error_report("%s(%s, 0x%x, 0x%x) failed: %m",
- __func__, vdev->vbasedev.name, addr, len);
- return -errno;
+ const char *err = ret < 0 ? strerror(-ret) : "short read";
+
+ error_report("%s(%s, 0x%x, 0x%x) failed: %s",
+ __func__, vbasedev->name, addr, len, err);
+ return -1;
}
phys_val = le32_to_cpu(phys_val);
}
@@ -1247,15 +1263,19 @@ void vfio_pci_write_config(PCIDevice *pdev,
uint32_t addr, uint32_t val, int len)
{
VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
+ VFIODevice *vbasedev = &vdev->vbasedev;
uint32_t val_le = cpu_to_le32(val);
+ int ret;
trace_vfio_pci_write_config(vdev->vbasedev.name, addr, val, len);
/* Write everything to VFIO, let it filter out what we can't write */
- if (pwrite(vdev->vbasedev.fd, &val_le, len, vdev->config_offset + addr)
- != len) {
- error_report("%s(%s, 0x%x, 0x%x, 0x%x) failed: %m",
- __func__, vdev->vbasedev.name, addr, val, len);
+ ret = VDEV_CONFIG_WRITE(vbasedev, addr, len, &val_le);
+ if (ret != len) {
+ const char *err = ret < 0 ? strerror(-ret) : "short write";
+
+ error_report("%s(%s, 0x%x, 0x%x, 0x%x) failed: %s",
+ __func__, vbasedev->name, addr, val, len, err);
}
/* MSI/MSI-X Enabling/Disabling */
@@ -1343,9 +1363,12 @@ static bool vfio_msi_setup(VFIOPCIDevice *vdev, int pos, Error **errp)
int ret, entries;
Error *err = NULL;
- if (pread(vdev->vbasedev.fd, &ctrl, sizeof(ctrl),
- vdev->config_offset + pos + PCI_CAP_FLAGS) != sizeof(ctrl)) {
- error_setg_errno(errp, errno, "failed reading MSI PCI_CAP_FLAGS");
+ ret = VDEV_CONFIG_READ(&vdev->vbasedev, pos + PCI_CAP_FLAGS,
+ sizeof(ctrl), &ctrl);
+ if (ret != sizeof(ctrl)) {
+ const char *errmsg = ret < 0 ? strerror(-ret) : "short read";
+
+ error_setg(errp, "failed reading MSI PCI_CAP_FLAGS %s", errmsg);
return false;
}
ctrl = le16_to_cpu(ctrl);
@@ -1549,34 +1572,43 @@ static bool vfio_pci_relocate_msix(VFIOPCIDevice *vdev, Error **errp)
*/
static bool vfio_msix_early_setup(VFIOPCIDevice *vdev, Error **errp)
{
+ VFIODevice *vbasedev = &vdev->vbasedev;
uint8_t pos;
uint16_t ctrl;
uint32_t table, pba;
- int ret, fd = vdev->vbasedev.fd;
struct vfio_irq_info irq_info = { .argsz = sizeof(irq_info),
.index = VFIO_PCI_MSIX_IRQ_INDEX };
VFIOMSIXInfo *msix;
+ int ret;
pos = pci_find_capability(&vdev->pdev, PCI_CAP_ID_MSIX);
if (!pos) {
return true;
}
- if (pread(fd, &ctrl, sizeof(ctrl),
- vdev->config_offset + pos + PCI_MSIX_FLAGS) != sizeof(ctrl)) {
- error_setg_errno(errp, errno, "failed to read PCI MSIX FLAGS");
+ ret = VDEV_CONFIG_READ(vbasedev, pos + PCI_MSIX_FLAGS,
+ sizeof(ctrl), &ctrl);
+ if (ret != sizeof(ctrl)) {
+ const char *err = ret < 0 ? strerror(-ret) : "short read";
+
+ error_setg(errp, "failed to read PCI MSIX FLAGS: %s", err);
return false;
}
- if (pread(fd, &table, sizeof(table),
- vdev->config_offset + pos + PCI_MSIX_TABLE) != sizeof(table)) {
- error_setg_errno(errp, errno, "failed to read PCI MSIX TABLE");
+ ret = VDEV_CONFIG_READ(vbasedev, pos + PCI_MSIX_TABLE,
+ sizeof(table), &table);
+ if (ret != sizeof(table)) {
+ const char *err = ret < 0 ? strerror(-ret) : "short read";
+
+ error_setg(errp, "failed to read PCI MSIX TABLE: %s", err);
return false;
}
- if (pread(fd, &pba, sizeof(pba),
- vdev->config_offset + pos + PCI_MSIX_PBA) != sizeof(pba)) {
- error_setg_errno(errp, errno, "failed to read PCI MSIX PBA");
+ ret = VDEV_CONFIG_READ(vbasedev, pos + PCI_MSIX_PBA, sizeof(pba), &pba);
+ if (ret != sizeof(pba)) {
+ const char *err = ret < 0 ? strerror(-ret) : "short read";
+
+ error_setg(errp, "failed to read PCI MSIX PBA: %s", err);
return false;
}
@@ -1591,7 +1623,7 @@ static bool vfio_msix_early_setup(VFIOPCIDevice *vdev, Error **errp)
msix->pba_offset = pba & ~PCI_MSIX_FLAGS_BIRMASK;
msix->entries = (ctrl & PCI_MSIX_FLAGS_QSIZE) + 1;
- ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_IRQ_INFO, &irq_info);
+ ret = vdev->vbasedev.io->get_irq_info(&vdev->vbasedev, &irq_info);
if (ret < 0) {
error_setg_errno(errp, -ret, "failed to get MSI-X irq info");
g_free(msix);
@@ -1735,10 +1767,12 @@ static void vfio_bar_prepare(VFIOPCIDevice *vdev, int nr)
}
/* Determine what type of BAR this is for registration */
- ret = pread(vdev->vbasedev.fd, &pci_bar, sizeof(pci_bar),
- vdev->config_offset + PCI_BASE_ADDRESS_0 + (4 * nr));
+ ret = VDEV_CONFIG_READ(&vdev->vbasedev, PCI_BASE_ADDRESS_0 + (4 * nr),
+ sizeof(pci_bar), &pci_bar);
if (ret != sizeof(pci_bar)) {
- error_report("vfio: Failed to read BAR %d (%m)", nr);
+ const char *err = ret < 0 ? strerror(-ret) : "short read";
+
+ error_report("vfio: Failed to read BAR %d: %s", nr, err);
return;
}
@@ -2438,21 +2472,25 @@ void vfio_pci_pre_reset(VFIOPCIDevice *vdev)
void vfio_pci_post_reset(VFIOPCIDevice *vdev)
{
+ VFIODevice *vbasedev = &vdev->vbasedev;
Error *err = NULL;
- int nr;
+ int ret, nr;
if (!vfio_intx_enable(vdev, &err)) {
error_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name);
}
for (nr = 0; nr < PCI_NUM_REGIONS - 1; ++nr) {
- off_t addr = vdev->config_offset + PCI_BASE_ADDRESS_0 + (4 * nr);
+ off_t addr = PCI_BASE_ADDRESS_0 + (4 * nr);
uint32_t val = 0;
uint32_t len = sizeof(val);
- if (pwrite(vdev->vbasedev.fd, &val, len, addr) != len) {
- error_report("%s(%s) reset bar %d failed: %m", __func__,
- vdev->vbasedev.name, nr);
+ ret = VDEV_CONFIG_WRITE(vbasedev, addr, len, &val);
+ if (ret != len) {
+ const char *errmsg = ret < 0 ? strerror(-ret) : "short write";
+
+ error_report("%s(%s) reset bar %d failed: %s", __func__,
+ vbasedev->name, nr, errmsg);
}
}
@@ -2794,10 +2832,10 @@ static bool vfio_populate_device(VFIOPCIDevice *vdev, Error **errp)
irq_info.index = VFIO_PCI_ERR_IRQ_INDEX;
- ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_IRQ_INFO, &irq_info);
+ ret = vbasedev->io->get_irq_info(vbasedev, &irq_info);
if (ret) {
/* This can fail for an old kernel or legacy PCI dev */
- trace_vfio_populate_device_get_irq_info_failure(strerror(errno));
+ trace_vfio_populate_device_get_irq_info_failure(strerror(-ret));
} else if (irq_info.count == 1) {
vdev->pci_aer = true;
} else {
@@ -2915,8 +2953,11 @@ static void vfio_register_req_notifier(VFIOPCIDevice *vdev)
return;
}
- if (ioctl(vdev->vbasedev.fd,
- VFIO_DEVICE_GET_IRQ_INFO, &irq_info) < 0 || irq_info.count < 1) {
+ if (vdev->vbasedev.io->get_irq_info(&vdev->vbasedev, &irq_info) < 0) {
+ return;
+ }
+
+ if (irq_info.count < 1) {
return;
}
@@ -3368,7 +3409,7 @@ static void vfio_instance_init(Object *obj)
vdev->host.function = ~0U;
vfio_device_init(vbasedev, VFIO_DEVICE_TYPE_PCI, &vfio_pci_ops,
- DEVICE(vdev), false);
+ &vfio_dev_io_ioctl, DEVICE(vdev), false);
vdev->nv_gpudirect_clique = 0xFF;
diff --git a/hw/vfio/platform.c b/hw/vfio/platform.c
index f491f4dc95..51534fd941 100644
--- a/hw/vfio/platform.c
+++ b/hw/vfio/platform.c
@@ -648,7 +648,7 @@ static void vfio_platform_instance_init(Object *obj)
VFIODevice *vbasedev = &vdev->vbasedev;
vfio_device_init(vbasedev, VFIO_DEVICE_TYPE_PLATFORM, &vfio_platform_ops,
- DEVICE(vdev), false);
+ &vfio_dev_io_ioctl, DEVICE(vdev), false);
}
#ifdef CONFIG_IOMMUFD
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index 304030e71d..3512556590 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -116,6 +116,7 @@ typedef struct VFIOIOMMUFDContainer {
OBJECT_DECLARE_SIMPLE_TYPE(VFIOIOMMUFDContainer, VFIO_IOMMU_IOMMUFD);
typedef struct VFIODeviceOps VFIODeviceOps;
+typedef struct VFIODeviceIO VFIODeviceIO;
typedef struct VFIODevice {
QLIST_ENTRY(VFIODevice) next;
@@ -136,6 +137,7 @@ typedef struct VFIODevice {
OnOffAuto enable_migration;
bool migration_events;
VFIODeviceOps *ops;
+ VFIODeviceIO *io;
unsigned int num_irqs;
unsigned int num_regions;
unsigned int flags;
@@ -186,6 +188,29 @@ struct VFIODeviceOps {
int (*vfio_load_config)(VFIODevice *vdev, QEMUFile *f);
};
+#ifdef CONFIG_LINUX
+
+/*
+ * How devices communicate with the server. The default option is through
+ * ioctl() to the kernel VFIO driver, but vfio-user can use a socket to a remote
+ * process.
+ */
+struct VFIODeviceIO {
+ int (*device_feature)(VFIODevice *vdev, struct vfio_device_feature *);
+ int (*get_region_info)(VFIODevice *vdev,
+ struct vfio_region_info *info);
+ int (*get_irq_info)(VFIODevice *vdev, struct vfio_irq_info *irq);
+ int (*set_irqs)(VFIODevice *vdev, struct vfio_irq_set *irqs);
+ int (*region_read)(VFIODevice *vdev, uint8_t nr, off_t off, uint32_t size,
+ void *data);
+ int (*region_write)(VFIODevice *vdev, uint8_t nr, off_t off, uint32_t size,
+ void *data);
+};
+
+extern VFIODeviceIO vfio_dev_io_ioctl;
+
+#endif /* CONFIG_LINUX */
+
typedef struct VFIOGroup {
int fd;
int groupid;
@@ -317,6 +342,6 @@ int vfio_get_dirty_bitmap(const VFIOContainerBase *bcontainer, uint64_t iova,
bool vfio_device_get_name(VFIODevice *vbasedev, Error **errp);
void vfio_device_set_fd(VFIODevice *vbasedev, const char *str, Error **errp);
void vfio_device_init(VFIODevice *vbasedev, int type, VFIODeviceOps *ops,
- DeviceState *dev, bool ram_discard);
+ VFIODeviceIO *io, DeviceState *dev, bool ram_discard);
int vfio_device_get_aw_bits(VFIODevice *vdev);
#endif /* HW_VFIO_VFIO_COMMON_H */
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* Re: [PATCH v8 10/28] vfio: add device IO ops vector
2025-02-19 14:48 ` [PATCH v8 10/28] vfio: add device IO ops vector John Levon
@ 2025-04-04 14:36 ` Cédric Le Goater
2025-04-04 15:53 ` John Levon
0 siblings, 1 reply; 64+ messages in thread
From: Cédric Le Goater @ 2025-04-04 14:36 UTC (permalink / raw)
To: John Levon, qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin,
Jagannathan Raman, John Johnson, Elena Ufimtseva
On 2/19/25 15:48, John Levon wrote:
> From: Jagannathan Raman <jag.raman@oracle.com>
>
> For vfio-user, device operations such as IRQ handling and region
> read/writes are implemented in userspace over the control socket, not
> ioctl() or read()/write() to the vfio kernel driver; add an ops vector
> to generalize this, and implement vfio_dev_io_ioctl for interacting
> with the kernel vfio driver.
>
> The ops consistently use the "-errno" return style, as the vfio-user
> implementations get their errors from response messages not from the
> kernel; adjust the callers to handle this as necessary.
Please adjust the callers before introducing the new ops.
> Originally-by: John Johnson <john.g.johnson@oracle.com>
> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
> Signed-off-by: John Levon <john.levon@nutanix.com>
> ---
> hw/vfio/ap.c | 2 +-
> hw/vfio/ccw.c | 2 +-
> hw/vfio/common.c | 13 +--
> hw/vfio/helpers.c | 110 ++++++++++++++++++++++---
> hw/vfio/pci.c | 147 ++++++++++++++++++++++------------
> hw/vfio/platform.c | 2 +-
> include/hw/vfio/vfio-common.h | 27 ++++++-
> 7 files changed, 227 insertions(+), 76 deletions(-)
>
> diff --git a/hw/vfio/ap.c b/hw/vfio/ap.c
> index 30b08ad375..1adce1ab40 100644
> --- a/hw/vfio/ap.c
> +++ b/hw/vfio/ap.c
> @@ -228,7 +228,7 @@ static void vfio_ap_instance_init(Object *obj)
> * handle ram_block_discard_disable().
> */
> vfio_device_init(vbasedev, VFIO_DEVICE_TYPE_AP, &vfio_ap_ops,
> - DEVICE(vapdev), true);
> + &vfio_dev_io_ioctl, DEVICE(vapdev), true);
Hmm, most of these parameters should be VFIODeviceClass attributes but
it doesn't exist. I don't see any nice improvements. Let's keep it.
>
> /* AP device is mdev type device */
> vbasedev->mdev = true;
> diff --git a/hw/vfio/ccw.c b/hw/vfio/ccw.c
> index 22378d50bc..8c16648819 100644
> --- a/hw/vfio/ccw.c
> +++ b/hw/vfio/ccw.c
> @@ -682,7 +682,7 @@ static void vfio_ccw_instance_init(Object *obj)
> * ram_block_discard_disable().
> */
> vfio_device_init(vbasedev, VFIO_DEVICE_TYPE_CCW, &vfio_ccw_ops,
> - DEVICE(vcdev), true);
> + &vfio_dev_io_ioctl, DEVICE(vcdev), true);
> }
>
> #ifdef CONFIG_IOMMUFD
> diff --git a/hw/vfio/common.c b/hw/vfio/common.c
> index 1866b3d3c5..cc0c0f7fc7 100644
> --- a/hw/vfio/common.c
> +++ b/hw/vfio/common.c
> @@ -971,7 +971,7 @@ static void vfio_devices_dma_logging_stop(VFIOContainerBase *bcontainer)
> continue;
> }
>
> - if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) {
> + if (vbasedev->io->device_feature(vbasedev, feature)) {
> warn_report("%s: Failed to stop DMA logging, err %d (%s)",
> vbasedev->name, -errno, strerror(errno));
> }
> @@ -1074,10 +1074,9 @@ static bool vfio_devices_dma_logging_start(VFIOContainerBase *bcontainer,
> continue;
> }
>
> - ret = ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature);
> + ret = vbasedev->io->device_feature(vbasedev, feature);
> if (ret) {
> - ret = -errno;
> - error_setg_errno(errp, errno, "%s: Failed to start DMA logging",
> + error_setg_errno(errp, -ret, "%s: Failed to start DMA logging",
> vbasedev->name);
> goto out;
> }
> @@ -1145,6 +1144,7 @@ static int vfio_device_dma_logging_report(VFIODevice *vbasedev, hwaddr iova,
> struct vfio_device_feature *feature = (struct vfio_device_feature *)buf;
> struct vfio_device_feature_dma_logging_report *report =
> (struct vfio_device_feature_dma_logging_report *)feature->data;
> + int ret;
>
> report->iova = iova;
> report->length = size;
> @@ -1155,8 +1155,9 @@ static int vfio_device_dma_logging_report(VFIODevice *vbasedev, hwaddr iova,
> feature->flags = VFIO_DEVICE_FEATURE_GET |
> VFIO_DEVICE_FEATURE_DMA_LOGGING_REPORT;
>
> - if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) {
> - return -errno;
> + ret = vbasedev->io->device_feature(vbasedev, feature);
> + if (ret) {
> + return -ret;
> }
>
> return 0;
> diff --git a/hw/vfio/helpers.c b/hw/vfio/helpers.c
> index 94bbc5747c..bef1540295 100644
> --- a/hw/vfio/helpers.c
> +++ b/hw/vfio/helpers.c
> @@ -44,7 +44,7 @@ void vfio_disable_irqindex(VFIODevice *vbasedev, int index)
> .count = 0,
> };
>
> - ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
> + vbasedev->io->set_irqs(vbasedev, &irq_set);
> }
>
> void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index)
> @@ -57,7 +57,7 @@ void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index)
> .count = 1,
> };
>
> - ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
> + vbasedev->io->set_irqs(vbasedev, &irq_set);
> }
>
> void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index)
> @@ -70,7 +70,7 @@ void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index)
> .count = 1,
> };
>
> - ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
> + vbasedev->io->set_irqs(vbasedev, &irq_set);
> }
>
> static inline const char *action_to_str(int action)
> @@ -117,6 +117,7 @@ bool vfio_set_irq_signaling(VFIODevice *vbasedev, int index, int subindex,
> int argsz;
> const char *name;
> int32_t *pfd;
> + int ret;
>
> argsz = sizeof(*irq_set) + sizeof(*pfd);
>
> @@ -129,7 +130,9 @@ bool vfio_set_irq_signaling(VFIODevice *vbasedev, int index, int subindex,
> pfd = (int32_t *)&irq_set->data;
> *pfd = fd;
>
> - if (!ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, irq_set)) {
> + ret = vbasedev->io->set_irqs(vbasedev, irq_set);
> +
> + if (!ret) {
> return true;
> }
>
> @@ -161,6 +164,7 @@ void vfio_region_write(void *opaque, hwaddr addr,
> uint32_t dword;
> uint64_t qword;
> } buf;
> + int ret;
>
> switch (size) {
> case 1:
> @@ -180,11 +184,12 @@ void vfio_region_write(void *opaque, hwaddr addr,
> break;
> }
>
> - if (pwrite(vbasedev->fd, &buf, size, region->fd_offset + addr) != size) {
> + ret = vbasedev->io->region_write(vbasedev, region->nr, addr, size, &buf);
> + if (ret != size) {
> error_report("%s(%s:region%d+0x%"HWADDR_PRIx", 0x%"PRIx64
> - ",%d) failed: %m",
> + ",%d) failed: %s",
> __func__, vbasedev->name, region->nr,
> - addr, data, size);
> + addr, data, size, ret < 0 ? strerror(ret) : "short write");
> }
>
> trace_vfio_region_write(vbasedev->name, region->nr, addr, data, size);
> @@ -212,11 +217,13 @@ uint64_t vfio_region_read(void *opaque,
> uint64_t qword;
> } buf;
> uint64_t data = 0;
> + int ret;
>
> - if (pread(vbasedev->fd, &buf, size, region->fd_offset + addr) != size) {
> - error_report("%s(%s:region%d+0x%"HWADDR_PRIx", %d) failed: %m",
> + ret = vbasedev->io->region_read(vbasedev, region->nr, addr, size, &buf);
> + if (ret != size) {
> + error_report("%s(%s:region%d+0x%"HWADDR_PRIx", %d) failed: %s",
> __func__, vbasedev->name, region->nr,
> - addr, size);
> + addr, size, ret < 0 ? strerror(ret) : "short read");
> return (uint64_t)-1;
> }
> switch (size) {
> @@ -561,6 +568,7 @@ int vfio_get_region_info(VFIODevice *vbasedev, int index,
> struct vfio_region_info **info)
> {
> size_t argsz = sizeof(struct vfio_region_info);
> + int ret;
>
> /* create region cache */
> if (vbasedev->regions == NULL) {
> @@ -579,10 +587,11 @@ int vfio_get_region_info(VFIODevice *vbasedev, int index,
> retry:
> (*info)->argsz = argsz;
>
> - if (ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, *info)) {
> + ret = vbasedev->io->get_region_info(vbasedev, *info);
> + if (ret != 0) {
> g_free(*info);
> *info = NULL;
> - return -errno;
> + return ret;
> }
>
> if ((*info)->argsz > argsz) {
> @@ -689,11 +698,12 @@ void vfio_device_set_fd(VFIODevice *vbasedev, const char *str, Error **errp)
> }
>
> void vfio_device_init(VFIODevice *vbasedev, int type, VFIODeviceOps *ops,
> - DeviceState *dev, bool ram_discard)
> + VFIODeviceIO *io, DeviceState *dev, bool ram_discard)
> {
> vbasedev->type = type;
> vbasedev->ops = ops;
> vbasedev->dev = dev;
> + vbasedev->io = io;
> vbasedev->fd = -1;
>
> vbasedev->ram_block_discard_allowed = ram_discard;
> @@ -749,3 +759,77 @@ VFIODevice *vfio_get_vfio_device(Object *obj)
> return NULL;
> }
> }
> +
> +/*
> + * Traditional ioctl() based io
> + */
> +
> +static int vfio_io_device_feature(VFIODevice *vbasedev,
> + struct vfio_device_feature *feature)
'vfio_device' prefix ? vfio_device_io_device_feature. Minor since it's
local to the file.
> +{
> + int ret;
> +
> + ret = ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature);
> +
> + return ret < 0 ? -errno : ret;
> +}
> +
> +static int vfio_io_get_region_info(VFIODevice *vbasedev,
> + struct vfio_region_info *info)
> +{
> + int ret;
> +
> + ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, info);
> +
> + return ret < 0 ? -errno : ret;
> +}
> +
> +static int vfio_io_get_irq_info(VFIODevice *vbasedev,
> + struct vfio_irq_info *info)
> +{
> + int ret;
> +
> + ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_IRQ_INFO, info);
> +
> + return ret < 0 ? -errno : ret;
> +}
> +
> +static int vfio_io_set_irqs(VFIODevice *vbasedev, struct vfio_irq_set *irqs)
> +{
> + int ret;
> +
> + ret = ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, irqs);
> +
> + return ret < 0 ? -errno : ret;
> +}
> +
> +static int vfio_io_region_read(VFIODevice *vbasedev, uint8_t index, off_t off,
> + uint32_t size, void *data)
> +{
> + struct vfio_region_info *info = vbasedev->regions[index];
> + int ret;
> +
> + ret = pread(vbasedev->fd, data, size, info->offset + off);
> +
> + return ret < 0 ? -errno : ret;
> +}
> +
> +static int vfio_io_region_write(VFIODevice *vbasedev, uint8_t index, off_t off,
> + uint32_t size, void *data)
> +{
> + struct vfio_region_info *info = vbasedev->regions[index];
> + int ret;
> +
> + ret = pwrite(vbasedev->fd, data, size, info->offset + off);
> +
> + return ret < 0 ? -errno : ret;
> +}
> +
> +VFIODeviceIO vfio_dev_io_ioctl = {
vfio_device_io_ops_ioctl
> + .device_feature = vfio_io_device_feature,
> + .get_region_info = vfio_io_get_region_info,
> + .get_irq_info = vfio_io_get_irq_info,
> + .set_irqs = vfio_io_set_irqs,
> + .region_read = vfio_io_region_read,
> + .region_write = vfio_io_region_write,
> +};
> diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
> index 812743e9dd..a9cc9366fb 100644
> --- a/hw/vfio/pci.c
> +++ b/hw/vfio/pci.c
> @@ -45,6 +45,14 @@
> #include "migration/qemu-file.h"
> #include "system/iommufd.h"
>
> +/* convenience macros for PCI config space */
> +#define VDEV_CONFIG_READ(vbasedev, off, size, data) \
> + ((vbasedev)->io->region_read((vbasedev), VFIO_PCI_CONFIG_REGION_INDEX, \
> + (off), (size), (data)))
> +#define VDEV_CONFIG_WRITE(vbasedev, off, size, data) \
> + ((vbasedev)->io->region_write((vbasedev), VFIO_PCI_CONFIG_REGION_INDEX, \
> + (off), (size), (data)))
> +
Pease introduce these helpers in a separate patch.
> #define TYPE_VFIO_PCI_NOHOTPLUG "vfio-pci-nohotplug"
>
> /* Protected by BQL */
> @@ -379,6 +387,7 @@ static void vfio_msi_interrupt(void *opaque)
> static int vfio_enable_msix_no_vec(VFIOPCIDevice *vdev)
> {
> g_autofree struct vfio_irq_set *irq_set = NULL;
> + VFIODevice *vbasedev = &vdev->vbasedev;
> int ret = 0, argsz;
> int32_t *fd;
>
> @@ -394,7 +403,7 @@ static int vfio_enable_msix_no_vec(VFIOPCIDevice *vdev)
> fd = (int32_t *)&irq_set->data;
> *fd = -1;
>
> - ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set);
> + ret = vbasedev->io->set_irqs(vbasedev, irq_set);
>
> return ret;
> }
> @@ -453,7 +462,7 @@ static int vfio_enable_vectors(VFIOPCIDevice *vdev, bool msix)
> fds[i] = fd;
> }
>
> - ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set);
> + ret = vdev->vbasedev.io->set_irqs(&vdev->vbasedev, irq_set);
>
> g_free(irq_set);
>
> @@ -763,7 +772,8 @@ retry:
> ret = vfio_enable_vectors(vdev, false);
> if (ret) {
> if (ret < 0) {
> - error_report("vfio: Error: Failed to setup MSI fds: %m");
> + error_report("vfio: Error: Failed to setup MSI fds: %s",
> + strerror(-ret));
> } else {
> error_report("vfio: Error: Failed to enable %d "
> "MSI vectors, retry with %d", vdev->nr_vectors, ret);
> @@ -879,14 +889,17 @@ static void vfio_update_msi(VFIOPCIDevice *vdev)
>
> static void vfio_pci_load_rom(VFIOPCIDevice *vdev)
> {
> + VFIODevice *vbasedev = &vdev->vbasedev;
> struct vfio_region_info *reg_info = NULL;
> uint64_t size;
> off_t off = 0;
> ssize_t bytes;
> + int ret;
>
> - if (vfio_get_region_info(&vdev->vbasedev,
> - VFIO_PCI_ROM_REGION_INDEX, ®_info)) {
> - error_report("vfio: Error getting ROM info: %m");
> + ret = vfio_get_region_info(vbasedev, VFIO_PCI_ROM_REGION_INDEX, ®_info);
> +
> + if (ret != 0) {
> + error_report("vfio: Error getting ROM info: %s", strerror(-ret));
> return;
> }
>
> @@ -911,18 +924,19 @@ static void vfio_pci_load_rom(VFIOPCIDevice *vdev)
> memset(vdev->rom, 0xff, size);
>
> while (size) {
> - bytes = pread(vdev->vbasedev.fd, vdev->rom + off,
> - size, vdev->rom_offset + off);
> + bytes = vbasedev->io->region_read(vbasedev, VFIO_PCI_ROM_REGION_INDEX,
> + off, size, vdev->rom + off);
> if (bytes == 0) {
> break;
> } else if (bytes > 0) {
> off += bytes;
> size -= bytes;
> } else {
> - if (errno == EINTR || errno == EAGAIN) {
> + if (bytes == -EINTR || bytes == -EAGAIN) {
> continue;
> }
> - error_report("vfio: Error reading device ROM: %m");
> + error_report("vfio: Error reading device ROM: %s",
> + strerror(-bytes));
> break;
> }
> }
> @@ -1010,10 +1024,9 @@ static const MemoryRegionOps vfio_rom_ops = {
>
> static void vfio_pci_size_rom(VFIOPCIDevice *vdev)
> {
> + VFIODevice *vbasedev = &vdev->vbasedev;
> uint32_t orig, size = cpu_to_le32((uint32_t)PCI_ROM_ADDRESS_MASK);
> - off_t offset = vdev->config_offset + PCI_ROM_ADDRESS;
> char *name;
> - int fd = vdev->vbasedev.fd;
>
> if (vdev->pdev.romfile || !vdev->pdev.rom_bar) {
> /* Since pci handles romfile, just print a message and return */
> @@ -1030,11 +1043,12 @@ static void vfio_pci_size_rom(VFIOPCIDevice *vdev)
> * Use the same size ROM BAR as the physical device. The contents
> * will get filled in later when the guest tries to read it.
> */
> - if (pread(fd, &orig, 4, offset) != 4 ||
> - pwrite(fd, &size, 4, offset) != 4 ||
> - pread(fd, &size, 4, offset) != 4 ||
> - pwrite(fd, &orig, 4, offset) != 4) {
> - error_report("%s(%s) failed: %m", __func__, vdev->vbasedev.name);
> + if (VDEV_CONFIG_READ(vbasedev, PCI_ROM_ADDRESS, 4, &orig) != 4 ||
> + VDEV_CONFIG_WRITE(vbasedev, PCI_ROM_ADDRESS, 4, &size) != 4 ||
> + VDEV_CONFIG_READ(vbasedev, PCI_ROM_ADDRESS, 4, &size) != 4 ||
> + VDEV_CONFIG_WRITE(vbasedev, PCI_ROM_ADDRESS, 4, &orig) != 4) {
> +
> + error_report("%s(%s) ROM access failed", __func__, vbasedev->name);
> return;
> }
>
> @@ -1214,6 +1228,7 @@ static void vfio_sub_page_bar_update_mapping(PCIDevice *pdev, int bar)
> uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len)
> {
> VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
> + VFIODevice *vbasedev = &vdev->vbasedev;
> uint32_t emu_bits = 0, emu_val = 0, phys_val = 0, val;
>
> memcpy(&emu_bits, vdev->emulated_config_bits + addr, len);
> @@ -1226,12 +1241,13 @@ uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len)
> if (~emu_bits & (0xffffffffU >> (32 - len * 8))) {
> ssize_t ret;
>
> - ret = pread(vdev->vbasedev.fd, &phys_val, len,
> - vdev->config_offset + addr);
> + ret = VDEV_CONFIG_READ(vbasedev, addr, len, &phys_val);
> if (ret != len) {
> - error_report("%s(%s, 0x%x, 0x%x) failed: %m",
> - __func__, vdev->vbasedev.name, addr, len);
> - return -errno;
> + const char *err = ret < 0 ? strerror(-ret) : "short read";
> +
> + error_report("%s(%s, 0x%x, 0x%x) failed: %s",
> + __func__, vbasedev->name, addr, len, err);
> + return -1;
> }
> phys_val = le32_to_cpu(phys_val);
> }
> @@ -1247,15 +1263,19 @@ void vfio_pci_write_config(PCIDevice *pdev,
> uint32_t addr, uint32_t val, int len)
> {
> VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
> + VFIODevice *vbasedev = &vdev->vbasedev;
> uint32_t val_le = cpu_to_le32(val);
> + int ret;
>
> trace_vfio_pci_write_config(vdev->vbasedev.name, addr, val, len);
>
> /* Write everything to VFIO, let it filter out what we can't write */
> - if (pwrite(vdev->vbasedev.fd, &val_le, len, vdev->config_offset + addr)
> - != len) {
> - error_report("%s(%s, 0x%x, 0x%x, 0x%x) failed: %m",
> - __func__, vdev->vbasedev.name, addr, val, len);
> + ret = VDEV_CONFIG_WRITE(vbasedev, addr, len, &val_le);
> + if (ret != len) {
> + const char *err = ret < 0 ? strerror(-ret) : "short write";
> +
> + error_report("%s(%s, 0x%x, 0x%x, 0x%x) failed: %s",
> + __func__, vbasedev->name, addr, val, len, err);
> }
>
> /* MSI/MSI-X Enabling/Disabling */
> @@ -1343,9 +1363,12 @@ static bool vfio_msi_setup(VFIOPCIDevice *vdev, int pos, Error **errp)
> int ret, entries;
> Error *err = NULL;
>
> - if (pread(vdev->vbasedev.fd, &ctrl, sizeof(ctrl),
> - vdev->config_offset + pos + PCI_CAP_FLAGS) != sizeof(ctrl)) {
> - error_setg_errno(errp, errno, "failed reading MSI PCI_CAP_FLAGS");
> + ret = VDEV_CONFIG_READ(&vdev->vbasedev, pos + PCI_CAP_FLAGS,
> + sizeof(ctrl), &ctrl);
> + if (ret != sizeof(ctrl)) {
> + const char *errmsg = ret < 0 ? strerror(-ret) : "short read";
> +
> + error_setg(errp, "failed reading MSI PCI_CAP_FLAGS %s", errmsg);
> return false;
> }
> ctrl = le16_to_cpu(ctrl);
> @@ -1549,34 +1572,43 @@ static bool vfio_pci_relocate_msix(VFIOPCIDevice *vdev, Error **errp)
> */
> static bool vfio_msix_early_setup(VFIOPCIDevice *vdev, Error **errp)
> {
> + VFIODevice *vbasedev = &vdev->vbasedev;
> uint8_t pos;
> uint16_t ctrl;
> uint32_t table, pba;
> - int ret, fd = vdev->vbasedev.fd;
> struct vfio_irq_info irq_info = { .argsz = sizeof(irq_info),
> .index = VFIO_PCI_MSIX_IRQ_INDEX };
> VFIOMSIXInfo *msix;
> + int ret;
>
> pos = pci_find_capability(&vdev->pdev, PCI_CAP_ID_MSIX);
> if (!pos) {
> return true;
> }
>
> - if (pread(fd, &ctrl, sizeof(ctrl),
> - vdev->config_offset + pos + PCI_MSIX_FLAGS) != sizeof(ctrl)) {
> - error_setg_errno(errp, errno, "failed to read PCI MSIX FLAGS");
> + ret = VDEV_CONFIG_READ(vbasedev, pos + PCI_MSIX_FLAGS,
> + sizeof(ctrl), &ctrl);
> + if (ret != sizeof(ctrl)) {
> + const char *err = ret < 0 ? strerror(-ret) : "short read";
> +
> + error_setg(errp, "failed to read PCI MSIX FLAGS: %s", err);
> return false;
> }
>
> - if (pread(fd, &table, sizeof(table),
> - vdev->config_offset + pos + PCI_MSIX_TABLE) != sizeof(table)) {
> - error_setg_errno(errp, errno, "failed to read PCI MSIX TABLE");
> + ret = VDEV_CONFIG_READ(vbasedev, pos + PCI_MSIX_TABLE,
> + sizeof(table), &table);
> + if (ret != sizeof(table)) {
> + const char *err = ret < 0 ? strerror(-ret) : "short read";
> +
> + error_setg(errp, "failed to read PCI MSIX TABLE: %s", err);
> return false;
> }
>
> - if (pread(fd, &pba, sizeof(pba),
> - vdev->config_offset + pos + PCI_MSIX_PBA) != sizeof(pba)) {
> - error_setg_errno(errp, errno, "failed to read PCI MSIX PBA");
> + ret = VDEV_CONFIG_READ(vbasedev, pos + PCI_MSIX_PBA, sizeof(pba), &pba);
> + if (ret != sizeof(pba)) {
> + const char *err = ret < 0 ? strerror(-ret) : "short read";
> +
> + error_setg(errp, "failed to read PCI MSIX PBA: %s", err);
> return false;
> }
>
> @@ -1591,7 +1623,7 @@ static bool vfio_msix_early_setup(VFIOPCIDevice *vdev, Error **errp)
> msix->pba_offset = pba & ~PCI_MSIX_FLAGS_BIRMASK;
> msix->entries = (ctrl & PCI_MSIX_FLAGS_QSIZE) + 1;
>
> - ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_IRQ_INFO, &irq_info);
> + ret = vdev->vbasedev.io->get_irq_info(&vdev->vbasedev, &irq_info);
> if (ret < 0) {
> error_setg_errno(errp, -ret, "failed to get MSI-X irq info");
> g_free(msix);
> @@ -1735,10 +1767,12 @@ static void vfio_bar_prepare(VFIOPCIDevice *vdev, int nr)
> }
>
> /* Determine what type of BAR this is for registration */
> - ret = pread(vdev->vbasedev.fd, &pci_bar, sizeof(pci_bar),
> - vdev->config_offset + PCI_BASE_ADDRESS_0 + (4 * nr));
> + ret = VDEV_CONFIG_READ(&vdev->vbasedev, PCI_BASE_ADDRESS_0 + (4 * nr),
> + sizeof(pci_bar), &pci_bar);
> if (ret != sizeof(pci_bar)) {
> - error_report("vfio: Failed to read BAR %d (%m)", nr);
> + const char *err = ret < 0 ? strerror(-ret) : "short read";
> +
> + error_report("vfio: Failed to read BAR %d: %s", nr, err);
> return;
> }
>
> @@ -2438,21 +2472,25 @@ void vfio_pci_pre_reset(VFIOPCIDevice *vdev)
>
> void vfio_pci_post_reset(VFIOPCIDevice *vdev)
> {
> + VFIODevice *vbasedev = &vdev->vbasedev;
> Error *err = NULL;
> - int nr;
> + int ret, nr;
>
> if (!vfio_intx_enable(vdev, &err)) {
> error_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name);
> }
>
> for (nr = 0; nr < PCI_NUM_REGIONS - 1; ++nr) {
> - off_t addr = vdev->config_offset + PCI_BASE_ADDRESS_0 + (4 * nr);
> + off_t addr = PCI_BASE_ADDRESS_0 + (4 * nr);
> uint32_t val = 0;
> uint32_t len = sizeof(val);
>
> - if (pwrite(vdev->vbasedev.fd, &val, len, addr) != len) {
> - error_report("%s(%s) reset bar %d failed: %m", __func__,
> - vdev->vbasedev.name, nr);
> + ret = VDEV_CONFIG_WRITE(vbasedev, addr, len, &val);
> + if (ret != len) {
> + const char *errmsg = ret < 0 ? strerror(-ret) : "short write";
> +
> + error_report("%s(%s) reset bar %d failed: %s", __func__,
> + vbasedev->name, nr, errmsg);
> }
> }
>
> @@ -2794,10 +2832,10 @@ static bool vfio_populate_device(VFIOPCIDevice *vdev, Error **errp)
>
> irq_info.index = VFIO_PCI_ERR_IRQ_INDEX;
>
> - ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_IRQ_INFO, &irq_info);
> + ret = vbasedev->io->get_irq_info(vbasedev, &irq_info);
> if (ret) {
> /* This can fail for an old kernel or legacy PCI dev */
> - trace_vfio_populate_device_get_irq_info_failure(strerror(errno));
> + trace_vfio_populate_device_get_irq_info_failure(strerror(-ret));
> } else if (irq_info.count == 1) {
> vdev->pci_aer = true;
> } else {
> @@ -2915,8 +2953,11 @@ static void vfio_register_req_notifier(VFIOPCIDevice *vdev)
> return;
> }
>
> - if (ioctl(vdev->vbasedev.fd,
> - VFIO_DEVICE_GET_IRQ_INFO, &irq_info) < 0 || irq_info.count < 1) {
> + if (vdev->vbasedev.io->get_irq_info(&vdev->vbasedev, &irq_info) < 0) {
> + return;
> + }
> +
> + if (irq_info.count < 1) {
> return;
> }
>
> @@ -3368,7 +3409,7 @@ static void vfio_instance_init(Object *obj)
> vdev->host.function = ~0U;
>
> vfio_device_init(vbasedev, VFIO_DEVICE_TYPE_PCI, &vfio_pci_ops,
> - DEVICE(vdev), false);
> + &vfio_dev_io_ioctl, DEVICE(vdev), false);
>
> vdev->nv_gpudirect_clique = 0xFF;
>
> diff --git a/hw/vfio/platform.c b/hw/vfio/platform.c
> index f491f4dc95..51534fd941 100644
> --- a/hw/vfio/platform.c
> +++ b/hw/vfio/platform.c
> @@ -648,7 +648,7 @@ static void vfio_platform_instance_init(Object *obj)
> VFIODevice *vbasedev = &vdev->vbasedev;
>
> vfio_device_init(vbasedev, VFIO_DEVICE_TYPE_PLATFORM, &vfio_platform_ops,
> - DEVICE(vdev), false);
> + &vfio_dev_io_ioctl, DEVICE(vdev), false);
> }
>
> #ifdef CONFIG_IOMMUFD
> diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
> index 304030e71d..3512556590 100644
> --- a/include/hw/vfio/vfio-common.h
> +++ b/include/hw/vfio/vfio-common.h
> @@ -116,6 +116,7 @@ typedef struct VFIOIOMMUFDContainer {
> OBJECT_DECLARE_SIMPLE_TYPE(VFIOIOMMUFDContainer, VFIO_IOMMU_IOMMUFD);
>
> typedef struct VFIODeviceOps VFIODeviceOps;
> +typedef struct VFIODeviceIO VFIODeviceIO;
I suggest VFIODeviceIOOps
> typedef struct VFIODevice {
> QLIST_ENTRY(VFIODevice) next;
> @@ -136,6 +137,7 @@ typedef struct VFIODevice {
> OnOffAuto enable_migration;
> bool migration_events;
> VFIODeviceOps *ops;
> + VFIODeviceIO *io;
io_ops
> unsigned int num_irqs;
> unsigned int num_regions;
> unsigned int flags;
> @@ -186,6 +188,29 @@ struct VFIODeviceOps {
> int (*vfio_load_config)(VFIODevice *vdev, QEMUFile *f);
> };
>
> +#ifdef CONFIG_LINUX
> +
> +/*
> + * How devices communicate with the server. The default option is through
> + * ioctl() to the kernel VFIO driver, but vfio-user can use a socket to a remote
> + * process.
> + */
> +struct VFIODeviceIO {
> + int (*device_feature)(VFIODevice *vdev, struct vfio_device_feature *);
> + int (*get_region_info)(VFIODevice *vdev,
> + struct vfio_region_info *info);
> + int (*get_irq_info)(VFIODevice *vdev, struct vfio_irq_info *irq);
> + int (*set_irqs)(VFIODevice *vdev, struct vfio_irq_set *irqs);
> + int (*region_read)(VFIODevice *vdev, uint8_t nr, off_t off, uint32_t size,
> + void *data);
> + int (*region_write)(VFIODevice *vdev, uint8_t nr, off_t off, uint32_t size,
> + void *data);
> +};
> +
> +extern VFIODeviceIO vfio_dev_io_ioctl;
vfio_dev_io_ops_ioctl
> +> +#endif /* CONFIG_LINUX */
> +
> typedef struct VFIOGroup {
> int fd;
> int groupid;
> @@ -317,6 +342,6 @@ int vfio_get_dirty_bitmap(const VFIOContainerBase *bcontainer, uint64_t iova,
> bool vfio_device_get_name(VFIODevice *vbasedev, Error **errp);
> void vfio_device_set_fd(VFIODevice *vbasedev, const char *str, Error **errp);
> void vfio_device_init(VFIODevice *vbasedev, int type, VFIODeviceOps *ops,
> - DeviceState *dev, bool ram_discard);
> + VFIODeviceIO *io, DeviceState *dev, bool ram_discard);
VFIODeviceIOOps *io_ops
> int vfio_device_get_aw_bits(VFIODevice *vdev);
> #endif /* HW_VFIO_VFIO_COMMON_H */
Just minor changes. Looks good.
Thanks,
C.
^ permalink raw reply [flat|nested] 64+ messages in thread* Re: [PATCH v8 10/28] vfio: add device IO ops vector
2025-04-04 14:36 ` Cédric Le Goater
@ 2025-04-04 15:53 ` John Levon
0 siblings, 0 replies; 64+ messages in thread
From: John Levon @ 2025-04-04 15:53 UTC (permalink / raw)
To: Cédric Le Goater
Cc: qemu-devel, Jason Herne, Thanos Makatos, Halil Pasic,
Daniel P. Berrangé, Eric Farman, Tony Krowiak, Thomas Huth,
qemu-s390x, Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin,
Jagannathan Raman, John Johnson, Elena Ufimtseva
On Fri, Apr 04, 2025 at 04:36:47PM +0200, Cédric Le Goater wrote:
> On 2/19/25 15:48, John Levon wrote:
> > From: Jagannathan Raman <jag.raman@oracle.com>
> >
> > For vfio-user, device operations such as IRQ handling and region
> > read/writes are implemented in userspace over the control socket, not
> > ioctl() or read()/write() to the vfio kernel driver; add an ops vector
> > to generalize this, and implement vfio_dev_io_ioctl for interacting
> > with the kernel vfio driver.
> >
> > The ops consistently use the "-errno" return style, as the vfio-user
> > implementations get their errors from response messages not from the
> > kernel; adjust the callers to handle this as necessary.
>
> Please adjust the callers before introducing the new ops.
As in change things like vfio_enable_vectors() to be "return -errno" style as a
preparatory change ? I can do that
> > +/*
> > + * Traditional ioctl() based io
> > + */
> > +
> > +static int vfio_io_device_feature(VFIODevice *vbasedev,
> > + struct vfio_device_feature *feature)
>
> 'vfio_device' prefix ? vfio_device_io_device_feature. Minor since it's
> local to the file.
Sure. Actually I don't really like "io" here either, but not sure of a better
prefix. "vfio_device_kern" ?? Getting a bit long winded.
> Just minor changes. Looks good.
I'll pick up all your other naming suggestions too
regards
john
^ permalink raw reply [flat|nested] 64+ messages in thread
* [PATCH v8 11/28] vfio-user: introduce vfio-user protocol specification
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (9 preceding siblings ...)
2025-02-19 14:48 ` [PATCH v8 10/28] vfio: add device IO ops vector John Levon
@ 2025-02-19 14:48 ` John Levon
2025-02-19 14:48 ` [PATCH v8 12/28] vfio-user: add vfio-user class and container John Levon
` (19 subsequent siblings)
30 siblings, 0 replies; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin
From: Thanos Makatos <thanos.makatos@nutanix.com>
This patch introduces the vfio-user protocol specification (formerly
known as VFIO-over-socket), which is designed to allow devices to be
emulated outside QEMU, in a separate process. vfio-user reuses the
existing VFIO defines, structs and concepts.
It has been earlier discussed as an RFC in:
"RFC: use VFIO over a UNIX domain socket to implement device offloading"
Signed-off-by: Thanos Makatos <thanos.makatos@nutanix.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
---
MAINTAINERS | 8 +-
docs/devel/index-internals.rst | 1 +
docs/devel/vfio-user.rst | 1522 ++++++++++++++++++++++++++++++++
3 files changed, 1530 insertions(+), 1 deletion(-)
create mode 100644 docs/devel/vfio-user.rst
diff --git a/MAINTAINERS b/MAINTAINERS
index 3848d37a38..3e7e6743cc 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4148,12 +4148,18 @@ F: hw/remote/proxy-memory-listener.c
F: include/hw/remote/proxy-memory-listener.h
F: hw/remote/iohub.c
F: include/hw/remote/iohub.h
-F: subprojects/libvfio-user
F: hw/remote/vfio-user-obj.c
F: include/hw/remote/vfio-user-obj.h
F: hw/remote/iommu.c
F: include/hw/remote/iommu.h
+VFIO-USER:
+M: John Levon <john.levon@nutanix.com>
+M: Thanos Makatos <thanos.makatos@nutanix.com>
+S: Supported
+F: docs/devel/vfio-user.rst
+F: subprojects/libvfio-user
+
EBPF:
M: Jason Wang <jasowang@redhat.com>
R: Andrew Melnychenko <andrew@daynix.com>
diff --git a/docs/devel/index-internals.rst b/docs/devel/index-internals.rst
index bca597c658..0bc24f0e51 100644
--- a/docs/devel/index-internals.rst
+++ b/docs/devel/index-internals.rst
@@ -21,6 +21,7 @@ Details about QEMU's various subsystems including how to add features to them.
s390-dasd-ipl
tracing
vfio-iommufd
+ vfio-user
writing-monitor-commands
virtio-backends
crypto
diff --git a/docs/devel/vfio-user.rst b/docs/devel/vfio-user.rst
new file mode 100644
index 0000000000..0d96477a68
--- /dev/null
+++ b/docs/devel/vfio-user.rst
@@ -0,0 +1,1522 @@
+.. include:: <isonum.txt>
+********************************
+vfio-user Protocol Specification
+********************************
+
+--------------
+Version_ 0.9.1
+--------------
+
+.. contents:: Table of Contents
+
+Introduction
+============
+vfio-user is a protocol that allows a device to be emulated in a separate
+process outside of a Virtual Machine Monitor (VMM). vfio-user devices consist
+of a generic VFIO device type, living inside the VMM, which we call the client,
+and the core device implementation, living outside the VMM, which we call the
+server.
+
+The vfio-user specification is partly based on the
+`Linux VFIO ioctl interface <https://www.kernel.org/doc/html/latest/driver-api/vfio.html>`_.
+
+VFIO is a mature and stable API, backed by an extensively used framework. The
+existing VFIO client implementation in QEMU (``qemu/hw/vfio/``) can be largely
+re-used, though there is nothing in this specification that requires that
+particular implementation. None of the VFIO kernel modules are required for
+supporting the protocol, on either the client or server side. Some source
+definitions in VFIO are re-used for vfio-user.
+
+The main idea is to allow a virtual device to function in a separate process in
+the same host over a UNIX domain socket. A UNIX domain socket (``AF_UNIX``) is
+chosen because file descriptors can be trivially sent over it, which in turn
+allows:
+
+* Sharing of client memory for DMA with the server.
+* Sharing of server memory with the client for fast MMIO.
+* Efficient sharing of eventfd's for triggering interrupts.
+
+Other socket types could be used which allow the server to run in a separate
+guest in the same host (``AF_VSOCK``) or remotely (``AF_INET``). Theoretically
+the underlying transport does not necessarily have to be a socket, however we do
+not examine such alternatives. In this protocol version we focus on using a UNIX
+domain socket and introduce basic support for the other two types of sockets
+without considering performance implications.
+
+While passing of file descriptors is desirable for performance reasons, support
+is not necessary for either the client or the server in order to implement the
+protocol. There is always an in-band, message-passing fall back mechanism.
+
+Overview
+========
+
+VFIO is a framework that allows a physical device to be securely passed through
+to a user space process; the device-specific kernel driver does not drive the
+device at all. Typically, the user space process is a VMM and the device is
+passed through to it in order to achieve high performance. VFIO provides an API
+and the required functionality in the kernel. QEMU has adopted VFIO to allow a
+guest to directly access physical devices, instead of emulating them in
+software.
+
+vfio-user reuses the core VFIO concepts defined in its API, but implements them
+as messages to be sent over a socket. It does not change the kernel-based VFIO
+in any way, in fact none of the VFIO kernel modules need to be loaded to use
+vfio-user. It is also possible for the client to concurrently use the current
+kernel-based VFIO for one device, and vfio-user for another device.
+
+VFIO Device Model
+-----------------
+
+A device under VFIO presents a standard interface to the user process. Many of
+the VFIO operations in the existing interface use the ``ioctl()`` system call, and
+references to the existing interface are called the ``ioctl()`` implementation in
+this document.
+
+The following sections describe the set of messages that implement the vfio-user
+interface over a socket. In many cases, the messages are analogous to data
+structures used in the ``ioctl()`` implementation. Messages derived from the
+``ioctl()`` will have a name derived from the ``ioctl()`` command name. E.g., the
+``VFIO_DEVICE_GET_INFO`` ``ioctl()`` command becomes a
+``VFIO_USER_DEVICE_GET_INFO`` message. The purpose of this reuse is to share as
+much code as feasible with the ``ioctl()`` implementation``.
+
+Connection Initiation
+^^^^^^^^^^^^^^^^^^^^^
+
+After the client connects to the server, the initial client message is
+``VFIO_USER_VERSION`` to propose a protocol version and set of capabilities to
+apply to the session. The server replies with a compatible version and set of
+capabilities it supports, or closes the connection if it cannot support the
+advertised version.
+
+Device Information
+^^^^^^^^^^^^^^^^^^
+
+The client uses a ``VFIO_USER_DEVICE_GET_INFO`` message to query the server for
+information about the device. This information includes:
+
+* The device type and whether it supports reset (``VFIO_DEVICE_FLAGS_``),
+* the number of device regions, and
+* the device presents to the client the number of interrupt types the device
+ supports.
+
+Region Information
+^^^^^^^^^^^^^^^^^^
+
+The client uses ``VFIO_USER_DEVICE_GET_REGION_INFO`` messages to query the
+server for information about the device's regions. This information describes:
+
+* Read and write permissions, whether it can be memory mapped, and whether it
+ supports additional capabilities (``VFIO_REGION_INFO_CAP_``).
+* Region index, size, and offset.
+
+When a device region can be mapped by the client, the server provides a file
+descriptor which the client can ``mmap()``. The server is responsible for
+polling for client updates to memory mapped regions.
+
+Region Capabilities
+"""""""""""""""""""
+
+Some regions have additional capabilities that cannot be described adequately
+by the region info data structure. These capabilities are returned in the
+region info reply in a list similar to PCI capabilities in a PCI device's
+configuration space.
+
+Sparse Regions
+""""""""""""""
+A region can be memory-mappable in whole or in part. When only a subset of a
+region can be mapped by the client, a ``VFIO_REGION_INFO_CAP_SPARSE_MMAP``
+capability is included in the region info reply. This capability describes
+which portions can be mapped by the client.
+
+.. Note::
+ For example, in a virtual NVMe controller, sparse regions can be used so
+ that accesses to the NVMe registers (found in the beginning of BAR0) are
+ trapped (an infrequent event), while allowing direct access to the doorbells
+ (an extremely frequent event as every I/O submission requires a write to
+ BAR0), found in the next page after the NVMe registers in BAR0.
+
+Device-Specific Regions
+"""""""""""""""""""""""
+
+A device can define regions additional to the standard ones (e.g. PCI indexes
+0-8). This is achieved by including a ``VFIO_REGION_INFO_CAP_TYPE`` capability
+in the region info reply of a device-specific region. Such regions are reflected
+in ``struct vfio_user_device_info.num_regions``. Thus, for PCI devices this
+value can be equal to, or higher than, ``VFIO_PCI_NUM_REGIONS``.
+
+Region I/O via file descriptors
+-------------------------------
+
+For unmapped regions, region I/O from the client is done via
+``VFIO_USER_REGION_READ/WRITE``. As an optimization, ioeventfds or ioregionfds
+may be configured for sub-regions of some regions. A client may request
+information on these sub-regions via ``VFIO_USER_DEVICE_GET_REGION_IO_FDS``; by
+configuring the returned file descriptors as ioeventfds or ioregionfds, the
+server can be directly notified of I/O (for example, by KVM) without taking a
+trip through the client.
+
+Interrupts
+^^^^^^^^^^
+
+The client uses ``VFIO_USER_DEVICE_GET_IRQ_INFO`` messages to query the server
+for the device's interrupt types. The interrupt types are specific to the bus
+the device is attached to, and the client is expected to know the capabilities
+of each interrupt type. The server can signal an interrupt by directly injecting
+interrupts into the guest via an event file descriptor. The client configures
+how the server signals an interrupt with ``VFIO_USER_SET_IRQS`` messages.
+
+Device Read and Write
+^^^^^^^^^^^^^^^^^^^^^
+
+When the guest executes load or store operations to an unmapped device region,
+the client forwards these operations to the server with
+``VFIO_USER_REGION_READ`` or ``VFIO_USER_REGION_WRITE`` messages. The server
+will reply with data from the device on read operations or an acknowledgement on
+write operations. See `Read and Write Operations`_.
+
+Client memory access
+--------------------
+
+The client uses ``VFIO_USER_DMA_MAP`` and ``VFIO_USER_DMA_UNMAP`` messages to
+inform the server of the valid DMA ranges that the server can access on behalf
+of a device (typically, VM guest memory). DMA memory may be accessed by the
+server via ``VFIO_USER_DMA_READ`` and ``VFIO_USER_DMA_WRITE`` messages over the
+socket. In this case, the "DMA" part of the naming is a misnomer.
+
+Actual direct memory access of client memory from the server is possible if the
+client provides file descriptors the server can ``mmap()``. Note that ``mmap()``
+privileges cannot be revoked by the client, therefore file descriptors should
+only be exported in environments where the client trusts the server not to
+corrupt guest memory.
+
+See `Read and Write Operations`_.
+
+Client/server interactions
+==========================
+
+Socket
+------
+
+A server can serve:
+
+1) one or more clients, and/or
+2) one or more virtual devices, belonging to one or more clients.
+
+The current protocol specification requires a dedicated socket per
+client/server connection. It is a server-side implementation detail whether a
+single server handles multiple virtual devices from the same or multiple
+clients. The location of the socket is implementation-specific. Multiplexing
+clients, devices, and servers over the same socket is not supported in this
+version of the protocol.
+
+Authentication
+--------------
+
+For ``AF_UNIX``, we rely on OS mandatory access controls on the socket files,
+therefore it is up to the management layer to set up the socket as required.
+Socket types that span guests or hosts will require a proper authentication
+mechanism. Defining that mechanism is deferred to a future version of the
+protocol.
+
+Command Concurrency
+-------------------
+
+A client may pipeline multiple commands without waiting for previous command
+replies. The server will process commands in the order they are received. A
+consequence of this is if a client issues a command with the *No_reply* bit,
+then subsequently issues a command without *No_reply*, the older command will
+have been processed before the reply to the younger command is sent by the
+server. The client must be aware of the device's capability to process
+concurrent commands if pipelining is used. For example, pipelining allows
+multiple client threads to concurrently access device regions; the client must
+ensure these accesses obey device semantics.
+
+An example is a frame buffer device, where the device may allow concurrent
+access to different areas of video memory, but may have indeterminate behavior
+if concurrent accesses are performed to command or status registers.
+
+Note that unrelated messages sent from the server to the client can appear in
+between a client to server request/reply and vice versa.
+
+Implementers should be prepared for certain commands to exhibit potentially
+unbounded latencies. For example, ``VFIO_USER_DEVICE_RESET`` may take an
+arbitrarily long time to complete; clients should take care not to block
+unnecessarily.
+
+Socket Disconnection Behavior
+-----------------------------
+The server and the client can disconnect from each other, either intentionally
+or unexpectedly. Both the client and the server need to know how to handle such
+events.
+
+Server Disconnection
+^^^^^^^^^^^^^^^^^^^^
+A server disconnecting from the client may indicate that:
+
+1) A virtual device has been restarted, either intentionally (e.g. because of a
+ device update) or unintentionally (e.g. because of a crash).
+2) A virtual device has been shut down with no intention to be restarted.
+
+It is impossible for the client to know whether or not a failure is
+intermittent or innocuous and should be retried, therefore the client should
+reset the VFIO device when it detects the socket has been disconnected.
+Error recovery will be driven by the guest's device error handling
+behavior.
+
+Client Disconnection
+^^^^^^^^^^^^^^^^^^^^
+The client disconnecting from the server primarily means that the client
+has exited. Currently, this means that the guest is shut down so the device is
+no longer needed therefore the server can automatically exit. However, there
+can be cases where a client disconnection should not result in a server exit:
+
+1) A single server serving multiple clients.
+2) A multi-process QEMU upgrading itself step by step, which is not yet
+ implemented.
+
+Therefore in order for the protocol to be forward compatible, the server should
+respond to a client disconnection as follows:
+
+ - all client memory regions are unmapped and cleaned up (including closing any
+ passed file descriptors)
+ - all IRQ file descriptors passed from the old client are closed
+ - the device state should otherwise be retained
+
+The expectation is that when a client reconnects, it will re-establish IRQ and
+client memory mappings.
+
+If anything happens to the client (such as qemu really did exit), the control
+stack will know about it and can clean up resources accordingly.
+
+Security Considerations
+-----------------------
+
+Speaking generally, vfio-user clients should not trust servers, and vice versa.
+Standard tools and mechanisms should be used on both sides to validate input and
+prevent against denial of service scenarios, buffer overflow, etc.
+
+Request Retry and Response Timeout
+----------------------------------
+A failed command is a command that has been successfully sent and has been
+responded to with an error code. Failure to send the command in the first place
+(e.g. because the socket is disconnected) is a different type of error examined
+earlier in the disconnect section.
+
+.. Note::
+ QEMU's VFIO retries certain operations if they fail. While this makes sense
+ for real HW, we don't know for sure whether it makes sense for virtual
+ devices.
+
+Defining a retry and timeout scheme is deferred to a future version of the
+protocol.
+
+Message sizes
+-------------
+
+Some requests have an ``argsz`` field. In a request, it defines the maximum
+expected reply payload size, which should be at least the size of the fixed
+reply payload headers defined here. The *request* payload size is defined by the
+usual ``msg_size`` field in the header, not the ``argsz`` field.
+
+In a reply, the server sets ``argsz`` field to the size needed for a full
+payload size. This may be less than the requested maximum size. This may be
+larger than the requested maximum size: in that case, the full payload is not
+included in the reply, but the ``argsz`` field in the reply indicates the needed
+size, allowing a client to allocate a larger buffer for holding the reply before
+trying again.
+
+In addition, during negotiation (see `Version`_), the client and server may
+each specify a ``max_data_xfer_size`` value; this defines the maximum data that
+may be read or written via one of the ``VFIO_USER_DMA/REGION_READ/WRITE``
+messages; see `Read and Write Operations`_.
+
+Protocol Specification
+======================
+
+To distinguish from the base VFIO symbols, all vfio-user symbols are prefixed
+with ``vfio_user`` or ``VFIO_USER``. In this revision, all data is in the
+endianness of the host system, although this may be relaxed in future
+revisions in cases where the client and server run on different hosts
+with different endianness.
+
+Unless otherwise specified, all sizes should be presumed to be in bytes.
+
+.. _Commands:
+
+Commands
+--------
+The following table lists the VFIO message command IDs, and whether the
+message command is sent from the client or the server.
+
+====================================== ========= =================
+Name Command Request Direction
+====================================== ========= =================
+``VFIO_USER_VERSION`` 1 client -> server
+``VFIO_USER_DMA_MAP`` 2 client -> server
+``VFIO_USER_DMA_UNMAP`` 3 client -> server
+``VFIO_USER_DEVICE_GET_INFO`` 4 client -> server
+``VFIO_USER_DEVICE_GET_REGION_INFO`` 5 client -> server
+``VFIO_USER_DEVICE_GET_REGION_IO_FDS`` 6 client -> server
+``VFIO_USER_DEVICE_GET_IRQ_INFO`` 7 client -> server
+``VFIO_USER_DEVICE_SET_IRQS`` 8 client -> server
+``VFIO_USER_REGION_READ`` 9 client -> server
+``VFIO_USER_REGION_WRITE`` 10 client -> server
+``VFIO_USER_DMA_READ`` 11 server -> client
+``VFIO_USER_DMA_WRITE`` 12 server -> client
+``VFIO_USER_DEVICE_RESET`` 13 client -> server
+``VFIO_USER_REGION_WRITE_MULTI`` 15 client -> server
+====================================== ========= =================
+
+Header
+------
+
+All messages, both command messages and reply messages, are preceded by a
+16-byte header that contains basic information about the message. The header is
+followed by message-specific data described in the sections below.
+
++----------------+--------+-------------+
+| Name | Offset | Size |
++================+========+=============+
+| Message ID | 0 | 2 |
++----------------+--------+-------------+
+| Command | 2 | 2 |
++----------------+--------+-------------+
+| Message size | 4 | 4 |
++----------------+--------+-------------+
+| Flags | 8 | 4 |
++----------------+--------+-------------+
+| | +-----+------------+ |
+| | | Bit | Definition | |
+| | +=====+============+ |
+| | | 0-3 | Type | |
+| | +-----+------------+ |
+| | | 4 | No_reply | |
+| | +-----+------------+ |
+| | | 5 | Error | |
+| | +-----+------------+ |
++----------------+--------+-------------+
+| Error | 12 | 4 |
++----------------+--------+-------------+
+| <message data> | 16 | variable |
++----------------+--------+-------------+
+
+* *Message ID* identifies the message, and is echoed in the command's reply
+ message. Message IDs belong entirely to the sender, can be re-used (even
+ concurrently) and the receiver must not make any assumptions about their
+ uniqueness.
+* *Command* specifies the command to be executed, listed in Commands_. It is
+ also set in the reply header.
+* *Message size* contains the size of the entire message, including the header.
+* *Flags* contains attributes of the message:
+
+ * The *Type* bits indicate the message type.
+
+ * *Command* (value 0x0) indicates a command message.
+ * *Reply* (value 0x1) indicates a reply message acknowledging a previous
+ command with the same message ID.
+ * *No_reply* in a command message indicates that no reply is needed for this
+ command. This is commonly used when multiple commands are sent, and only
+ the last needs acknowledgement.
+ * *Error* in a reply message indicates the command being acknowledged had
+ an error. In this case, the *Error* field will be valid.
+
+* *Error* in a reply message is an optional UNIX errno value. It may be zero
+ even if the Error bit is set in Flags. It is reserved in a command message.
+
+Each command message in Commands_ must be replied to with a reply message,
+unless the message sets the *No_Reply* bit. The reply consists of the header
+with the *Reply* bit set, plus any additional data.
+
+If an error occurs, the reply message must only include the reply header.
+
+As the header is standard in both requests and replies, it is not included in
+the command-specific specifications below; each message definition should be
+appended to the standard header, and the offsets are given from the end of the
+standard header.
+
+``VFIO_USER_VERSION``
+---------------------
+
+.. _Version:
+
+This is the initial message sent by the client after the socket connection is
+established; the same format is used for the server's reply.
+
+Upon establishing a connection, the client must send a ``VFIO_USER_VERSION``
+message proposing a protocol version and a set of capabilities. The server
+compares these with the versions and capabilities it supports and sends a
+``VFIO_USER_VERSION`` reply according to the following rules.
+
+* The major version in the reply must be the same as proposed. If the client
+ does not support the proposed major, it closes the connection.
+* The minor version in the reply must be equal to or less than the minor
+ version proposed.
+* The capability list must be a subset of those proposed. If the server
+ requires a capability the client did not include, it closes the connection.
+
+The protocol major version will only change when incompatible protocol changes
+are made, such as changing the message format. The minor version may change
+when compatible changes are made, such as adding new messages or capabilities,
+Both the client and server must support all minor versions less than the
+maximum minor version it supports. E.g., an implementation that supports
+version 1.3 must also support 1.0 through 1.2.
+
+When making a change to this specification, the protocol version number must
+be included in the form "added in version X.Y"
+
+Request
+^^^^^^^
+
+============== ====== ====
+Name Offset Size
+============== ====== ====
+version major 0 2
+version minor 2 2
+version data 4 variable (including terminating NUL). Optional.
+============== ====== ====
+
+The version data is an optional UTF-8 encoded JSON byte array with the following
+format:
+
++--------------+--------+-----------------------------------+
+| Name | Type | Description |
++==============+========+===================================+
+| capabilities | object | Contains common capabilities that |
+| | | the sender supports. Optional. |
++--------------+--------+-----------------------------------+
+
+Capabilities:
+
++--------------------+---------+------------------------------------------------+
+| Name | Type | Description |
++====================+=========+================================================+
+| max_msg_fds | number | Maximum number of file descriptors that can be |
+| | | received by the sender in one message. |
+| | | Optional. If not specified then the receiver |
+| | | must assume a value of ``1``. |
++--------------------+---------+------------------------------------------------+
+| max_data_xfer_size | number | Maximum ``count`` for data transfer messages; |
+| | | see `Read and Write Operations`_. Optional, |
+| | | with a default value of 1048576 bytes. |
++--------------------+---------+------------------------------------------------+
+| pgsizes | number | Page sizes supported in DMA map operations |
+| | | or'ed together. Optional, with a default value |
+| | | of supporting only 4k pages. |
++--------------------+---------+------------------------------------------------+
+| max_dma_maps | number | Maximum number DMA map windows that can be |
+| | | valid simultaneously. Optional, with a |
+| | | value of 65535 (64k-1). |
++--------------------+---------+------------------------------------------------+
+| migration | object | Migration capability parameters. If missing |
+| | | then migration is not supported by the sender. |
++--------------------+---------+------------------------------------------------+
+| write_multiple | boolean | ``VFIO_USER_REGION_WRITE_MULTI`` messages |
+| | | are supported if the value is ``true``. |
++--------------------+---------+------------------------------------------------+
+
+The migration capability contains the following name/value pairs:
+
++-----------------+--------+--------------------------------------------------+
+| Name | Type | Description |
++=================+========+==================================================+
+| pgsize | number | Page size of dirty pages bitmap. The smallest |
+| | | between the client and the server is used. |
++-----------------+--------+--------------------------------------------------+
+| max_bitmap_size | number | Maximum bitmap size in ``VFIO_USER_DIRTY_PAGES`` |
+| | | and ``VFIO_DMA_UNMAP`` messages. Optional, |
+| | | with a default value of 256MB. |
++-----------------+--------+--------------------------------------------------+
+
+Reply
+^^^^^
+
+The same message format is used in the server's reply with the semantics
+described above.
+
+``VFIO_USER_DMA_MAP``
+---------------------
+
+This command message is sent by the client to the server to inform it of the
+memory regions the server can access. It must be sent before the server can
+perform any DMA to the client. It is normally sent directly after the version
+handshake is completed, but may also occur when memory is added to the client,
+or if the client uses a vIOMMU.
+
+Request
+^^^^^^^
+
+The request payload for this message is a structure of the following format:
+
++-------------+--------+-------------+
+| Name | Offset | Size |
++=============+========+=============+
+| argsz | 0 | 4 |
++-------------+--------+-------------+
+| flags | 4 | 4 |
++-------------+--------+-------------+
+| | +-----+------------+ |
+| | | Bit | Definition | |
+| | +=====+============+ |
+| | | 0 | readable | |
+| | +-----+------------+ |
+| | | 1 | writeable | |
+| | +-----+------------+ |
++-------------+--------+-------------+
+| offset | 8 | 8 |
++-------------+--------+-------------+
+| address | 16 | 8 |
++-------------+--------+-------------+
+| size | 24 | 8 |
++-------------+--------+-------------+
+
+* *argsz* is the size of the above structure. Note there is no reply payload,
+ so this field differs from other message types.
+* *flags* contains the following region attributes:
+
+ * *readable* indicates that the region can be read from.
+
+ * *writeable* indicates that the region can be written to.
+
+* *offset* is the file offset of the region with respect to the associated file
+ descriptor, or zero if the region is not mappable
+* *address* is the base DMA address of the region.
+* *size* is the size of the region.
+
+This structure is 32 bytes in size, so the message size is 16 + 32 bytes.
+
+If the DMA region being added can be directly mapped by the server, a file
+descriptor must be sent as part of the message meta-data. The region can be
+mapped via the mmap() system call. On ``AF_UNIX`` sockets, the file descriptor
+must be passed as ``SCM_RIGHTS`` type ancillary data. Otherwise, if the DMA
+region cannot be directly mapped by the server, no file descriptor must be sent
+as part of the message meta-data and the DMA region can be accessed by the
+server using ``VFIO_USER_DMA_READ`` and ``VFIO_USER_DMA_WRITE`` messages,
+explained in `Read and Write Operations`_. A command to map over an existing
+region must be failed by the server with ``EEXIST`` set in error field in the
+reply.
+
+Reply
+^^^^^
+
+There is no payload in the reply message.
+
+``VFIO_USER_DMA_UNMAP``
+-----------------------
+
+This command message is sent by the client to the server to inform it that a
+DMA region, previously made available via a ``VFIO_USER_DMA_MAP`` command
+message, is no longer available for DMA. It typically occurs when memory is
+subtracted from the client or if the client uses a vIOMMU. The DMA region is
+described by the following structure:
+
+Request
+^^^^^^^
+
+The request payload for this message is a structure of the following format:
+
++--------------+--------+------------------------+
+| Name | Offset | Size |
++==============+========+========================+
+| argsz | 0 | 4 |
++--------------+--------+------------------------+
+| flags | 4 | 4 |
++--------------+--------+------------------------+
+| address | 8 | 8 |
++--------------+--------+------------------------+
+| size | 16 | 8 |
++--------------+--------+------------------------+
+
+* *argsz* is the maximum size of the reply payload.
+* *flags* is unused in this version.
+* *address* is the base DMA address of the DMA region.
+* *size* is the size of the DMA region.
+
+The address and size of the DMA region being unmapped must match exactly a
+previous mapping.
+
+Reply
+^^^^^
+
+Upon receiving a ``VFIO_USER_DMA_UNMAP`` command, if the file descriptor is
+mapped then the server must release all references to that DMA region before
+replying, which potentially includes in-flight DMA transactions.
+
+The server responds with the original DMA entry in the request.
+
+
+``VFIO_USER_DEVICE_GET_INFO``
+-----------------------------
+
+This command message is sent by the client to the server to query for basic
+information about the device.
+
+Request
+^^^^^^^
+
++-------------+--------+--------------------------+
+| Name | Offset | Size |
++=============+========+==========================+
+| argsz | 0 | 4 |
++-------------+--------+--------------------------+
+| flags | 4 | 4 |
++-------------+--------+--------------------------+
+| | +-----+-------------------------+ |
+| | | Bit | Definition | |
+| | +=====+=========================+ |
+| | | 0 | VFIO_DEVICE_FLAGS_RESET | |
+| | +-----+-------------------------+ |
+| | | 1 | VFIO_DEVICE_FLAGS_PCI | |
+| | +-----+-------------------------+ |
++-------------+--------+--------------------------+
+| num_regions | 8 | 4 |
++-------------+--------+--------------------------+
+| num_irqs | 12 | 4 |
++-------------+--------+--------------------------+
+
+* *argsz* is the maximum size of the reply payload
+* all other fields must be zero.
+
+Reply
+^^^^^
+
++-------------+--------+--------------------------+
+| Name | Offset | Size |
++=============+========+==========================+
+| argsz | 0 | 4 |
++-------------+--------+--------------------------+
+| flags | 4 | 4 |
++-------------+--------+--------------------------+
+| | +-----+-------------------------+ |
+| | | Bit | Definition | |
+| | +=====+=========================+ |
+| | | 0 | VFIO_DEVICE_FLAGS_RESET | |
+| | +-----+-------------------------+ |
+| | | 1 | VFIO_DEVICE_FLAGS_PCI | |
+| | +-----+-------------------------+ |
++-------------+--------+--------------------------+
+| num_regions | 8 | 4 |
++-------------+--------+--------------------------+
+| num_irqs | 12 | 4 |
++-------------+--------+--------------------------+
+
+* *argsz* is the size required for the full reply payload (16 bytes today)
+* *flags* contains the following device attributes.
+
+ * ``VFIO_DEVICE_FLAGS_RESET`` indicates that the device supports the
+ ``VFIO_USER_DEVICE_RESET`` message.
+ * ``VFIO_DEVICE_FLAGS_PCI`` indicates that the device is a PCI device.
+
+* *num_regions* is the number of memory regions that the device exposes.
+* *num_irqs* is the number of distinct interrupt types that the device supports.
+
+This version of the protocol only supports PCI devices. Additional devices may
+be supported in future versions.
+
+``VFIO_USER_DEVICE_GET_REGION_INFO``
+------------------------------------
+
+This command message is sent by the client to the server to query for
+information about device regions. The VFIO region info structure is defined in
+``<linux/vfio.h>`` (``struct vfio_region_info``).
+
+Request
+^^^^^^^
+
++------------+--------+------------------------------+
+| Name | Offset | Size |
++============+========+==============================+
+| argsz | 0 | 4 |
++------------+--------+------------------------------+
+| flags | 4 | 4 |
++------------+--------+------------------------------+
+| index | 8 | 4 |
++------------+--------+------------------------------+
+| cap_offset | 12 | 4 |
++------------+--------+------------------------------+
+| size | 16 | 8 |
++------------+--------+------------------------------+
+| offset | 24 | 8 |
++------------+--------+------------------------------+
+
+* *argsz* the maximum size of the reply payload
+* *index* is the index of memory region being queried, it is the only field
+ that is required to be set in the command message.
+* all other fields must be zero.
+
+Reply
+^^^^^
+
++------------+--------+------------------------------+
+| Name | Offset | Size |
++============+========+==============================+
+| argsz | 0 | 4 |
++------------+--------+------------------------------+
+| flags | 4 | 4 |
++------------+--------+------------------------------+
+| | +-----+-----------------------------+ |
+| | | Bit | Definition | |
+| | +=====+=============================+ |
+| | | 0 | VFIO_REGION_INFO_FLAG_READ | |
+| | +-----+-----------------------------+ |
+| | | 1 | VFIO_REGION_INFO_FLAG_WRITE | |
+| | +-----+-----------------------------+ |
+| | | 2 | VFIO_REGION_INFO_FLAG_MMAP | |
+| | +-----+-----------------------------+ |
+| | | 3 | VFIO_REGION_INFO_FLAG_CAPS | |
+| | +-----+-----------------------------+ |
++------------+--------+------------------------------+
++------------+--------+------------------------------+
+| index | 8 | 4 |
++------------+--------+------------------------------+
+| cap_offset | 12 | 4 |
++------------+--------+------------------------------+
+| size | 16 | 8 |
++------------+--------+------------------------------+
+| offset | 24 | 8 |
++------------+--------+------------------------------+
+
+* *argsz* is the size required for the full reply payload (region info structure
+ plus the size of any region capabilities)
+* *flags* are attributes of the region:
+
+ * ``VFIO_REGION_INFO_FLAG_READ`` allows client read access to the region.
+ * ``VFIO_REGION_INFO_FLAG_WRITE`` allows client write access to the region.
+ * ``VFIO_REGION_INFO_FLAG_MMAP`` specifies the client can mmap() the region.
+ When this flag is set, the reply will include a file descriptor in its
+ meta-data. On ``AF_UNIX`` sockets, the file descriptors will be passed as
+ ``SCM_RIGHTS`` type ancillary data.
+ * ``VFIO_REGION_INFO_FLAG_CAPS`` indicates additional capabilities found in the
+ reply.
+
+* *index* is the index of memory region being queried, it is the only field
+ that is required to be set in the command message.
+* *cap_offset* describes where additional region capabilities can be found.
+ cap_offset is relative to the beginning of the VFIO region info structure.
+ The data structure it points is a VFIO cap header defined in
+ ``<linux/vfio.h>``.
+* *size* is the size of the region.
+* *offset* is the offset that should be given to the mmap() system call for
+ regions with the MMAP attribute. It is also used as the base offset when
+ mapping a VFIO sparse mmap area, described below.
+
+VFIO region capabilities
+""""""""""""""""""""""""
+
+The VFIO region information can also include a capabilities list. This list is
+similar to a PCI capability list - each entry has a common header that
+identifies a capability and where the next capability in the list can be found.
+The VFIO capability header format is defined in ``<linux/vfio.h>`` (``struct
+vfio_info_cap_header``).
+
+VFIO cap header format
+""""""""""""""""""""""
+
++---------+--------+------+
+| Name | Offset | Size |
++=========+========+======+
+| id | 0 | 2 |
++---------+--------+------+
+| version | 2 | 2 |
++---------+--------+------+
+| next | 4 | 4 |
++---------+--------+------+
+
+* *id* is the capability identity.
+* *version* is a capability-specific version number.
+* *next* specifies the offset of the next capability in the capability list. It
+ is relative to the beginning of the VFIO region info structure.
+
+VFIO sparse mmap cap header
+"""""""""""""""""""""""""""
+
++------------------+----------------------------------+
+| Name | Value |
++==================+==================================+
+| id | VFIO_REGION_INFO_CAP_SPARSE_MMAP |
++------------------+----------------------------------+
+| version | 0x1 |
++------------------+----------------------------------+
+| next | <next> |
++------------------+----------------------------------+
+| sparse mmap info | VFIO region info sparse mmap |
++------------------+----------------------------------+
+
+This capability is defined when only a subrange of the region supports
+direct access by the client via mmap(). The VFIO sparse mmap area is defined in
+``<linux/vfio.h>`` (``struct vfio_region_sparse_mmap_area`` and ``struct
+vfio_region_info_cap_sparse_mmap``).
+
+VFIO region info cap sparse mmap
+""""""""""""""""""""""""""""""""
+
++----------+--------+------+
+| Name | Offset | Size |
++==========+========+======+
+| nr_areas | 0 | 4 |
++----------+--------+------+
+| reserved | 4 | 4 |
++----------+--------+------+
+| offset | 8 | 8 |
++----------+--------+------+
+| size | 16 | 8 |
++----------+--------+------+
+| ... | | |
++----------+--------+------+
+
+* *nr_areas* is the number of sparse mmap areas in the region.
+* *offset* and size describe a single area that can be mapped by the client.
+ There will be *nr_areas* pairs of offset and size. The offset will be added to
+ the base offset given in the ``VFIO_USER_DEVICE_GET_REGION_INFO`` to form the
+ offset argument of the subsequent mmap() call.
+
+The VFIO sparse mmap area is defined in ``<linux/vfio.h>`` (``struct
+vfio_region_info_cap_sparse_mmap``).
+
+
+``VFIO_USER_DEVICE_GET_REGION_IO_FDS``
+--------------------------------------
+
+Clients can access regions via ``VFIO_USER_REGION_READ/WRITE`` or, if provided, by
+``mmap()`` of a file descriptor provided by the server.
+
+``VFIO_USER_DEVICE_GET_REGION_IO_FDS`` provides an alternative access mechanism via
+file descriptors. This is an optional feature intended for performance
+improvements where an underlying sub-system (such as KVM) supports communication
+across such file descriptors to the vfio-user server, without needing to
+round-trip through the client.
+
+The server returns an array of sub-regions for the requested region. Each
+sub-region describes a span (offset and size) of a region, along with the
+requested file descriptor notification mechanism to use. Each sub-region in the
+response message may choose to use a different method, as defined below. The
+two mechanisms supported in this specification are ioeventfds and ioregionfds.
+
+The server in addition returns a file descriptor in the ancillary data; clients
+are expected to configure each sub-region's file descriptor with the requested
+notification method. For example, a client could configure KVM with the
+requested ioeventfd via a ``KVM_IOEVENTFD`` ``ioctl()``.
+
+Request
+^^^^^^^
+
++-------------+--------+------+
+| Name | Offset | Size |
++=============+========+======+
+| argsz | 0 | 4 |
++-------------+--------+------+
+| flags | 4 | 4 |
++-------------+--------+------+
+| index | 8 | 4 |
++-------------+--------+------+
+| count | 12 | 4 |
++-------------+--------+------+
+
+* *argsz* the maximum size of the reply payload
+* *index* is the index of memory region being queried
+* all other fields must be zero
+
+The client must set ``flags`` to zero and specify the region being queried in
+the ``index``.
+
+Reply
+^^^^^
+
++-------------+--------+------+
+| Name | Offset | Size |
++=============+========+======+
+| argsz | 0 | 4 |
++-------------+--------+------+
+| flags | 4 | 4 |
++-------------+--------+------+
+| index | 8 | 4 |
++-------------+--------+------+
+| count | 12 | 4 |
++-------------+--------+------+
+| sub-regions | 16 | ... |
++-------------+--------+------+
+
+* *argsz* is the size of the region IO FD info structure plus the
+ total size of the sub-region array. Thus, each array entry "i" is at offset
+ i * ((argsz - 32) / count). Note that currently this is 40 bytes for both IO
+ FD types, but this is not to be relied on. As elsewhere, this indicates the
+ full reply payload size needed.
+* *flags* must be zero
+* *index* is the index of memory region being queried
+* *count* is the number of sub-regions in the array
+* *sub-regions* is the array of Sub-Region IO FD info structures
+
+The reply message will additionally include at least one file descriptor in the
+ancillary data. Note that more than one sub-region may share the same file
+descriptor.
+
+Note that it is the client's responsibility to verify the requested values (for
+example, that the requested offset does not exceed the region's bounds).
+
+Each sub-region given in the response has one of two possible structures,
+depending whether *type* is ``VFIO_USER_IO_FD_TYPE_IOEVENTFD`` or
+``VFIO_USER_IO_FD_TYPE_IOREGIONFD``:
+
+Sub-Region IO FD info format (ioeventfd)
+""""""""""""""""""""""""""""""""""""""""
+
++-----------+--------+------+
+| Name | Offset | Size |
++===========+========+======+
+| offset | 0 | 8 |
++-----------+--------+------+
+| size | 8 | 8 |
++-----------+--------+------+
+| fd_index | 16 | 4 |
++-----------+--------+------+
+| type | 20 | 4 |
++-----------+--------+------+
+| flags | 24 | 4 |
++-----------+--------+------+
+| padding | 28 | 4 |
++-----------+--------+------+
+| datamatch | 32 | 8 |
++-----------+--------+------+
+
+* *offset* is the offset of the start of the sub-region within the region
+ requested ("physical address offset" for the region)
+* *size* is the length of the sub-region. This may be zero if the access size is
+ not relevant, which may allow for optimizations
+* *fd_index* is the index in the ancillary data of the FD to use for ioeventfd
+ notification; it may be shared.
+* *type* is ``VFIO_USER_IO_FD_TYPE_IOEVENTFD``
+* *flags* is any of:
+
+ * ``KVM_IOEVENTFD_FLAG_DATAMATCH``
+ * ``KVM_IOEVENTFD_FLAG_PIO``
+ * ``KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY`` (FIXME: makes sense?)
+
+* *datamatch* is the datamatch value if needed
+
+See https://www.kernel.org/doc/Documentation/virtual/kvm/api.txt, *4.59
+KVM_IOEVENTFD* for further context on the ioeventfd-specific fields.
+
+Sub-Region IO FD info format (ioregionfd)
+"""""""""""""""""""""""""""""""""""""""""
+
++-----------+--------+------+
+| Name | Offset | Size |
++===========+========+======+
+| offset | 0 | 8 |
++-----------+--------+------+
+| size | 8 | 8 |
++-----------+--------+------+
+| fd_index | 16 | 4 |
++-----------+--------+------+
+| type | 20 | 4 |
++-----------+--------+------+
+| flags | 24 | 4 |
++-----------+--------+------+
+| padding | 28 | 4 |
++-----------+--------+------+
+| user_data | 32 | 8 |
++-----------+--------+------+
+
+* *offset* is the offset of the start of the sub-region within the region
+ requested ("physical address offset" for the region)
+* *size* is the length of the sub-region. This may be zero if the access size is
+ not relevant, which may allow for optimizations; ``KVM_IOREGION_POSTED_WRITES``
+ must be set in *flags* in this case
+* *fd_index* is the index in the ancillary data of the FD to use for ioregionfd
+ messages; it may be shared
+* *type* is ``VFIO_USER_IO_FD_TYPE_IOREGIONFD``
+* *flags* is any of:
+
+ * ``KVM_IOREGION_PIO``
+ * ``KVM_IOREGION_POSTED_WRITES``
+
+* *user_data* is an opaque value passed back to the server via a message on the
+ file descriptor
+
+For further information on the ioregionfd-specific fields, see:
+https://lore.kernel.org/kvm/cover.1613828726.git.eafanasova@gmail.com/
+
+(FIXME: update with final API docs.)
+
+``VFIO_USER_DEVICE_GET_IRQ_INFO``
+---------------------------------
+
+This command message is sent by the client to the server to query for
+information about device interrupt types. The VFIO IRQ info structure is
+defined in ``<linux/vfio.h>`` (``struct vfio_irq_info``).
+
+Request
+^^^^^^^
+
++-------+--------+---------------------------+
+| Name | Offset | Size |
++=======+========+===========================+
+| argsz | 0 | 4 |
++-------+--------+---------------------------+
+| flags | 4 | 4 |
++-------+--------+---------------------------+
+| | +-----+--------------------------+ |
+| | | Bit | Definition | |
+| | +=====+==========================+ |
+| | | 0 | VFIO_IRQ_INFO_EVENTFD | |
+| | +-----+--------------------------+ |
+| | | 1 | VFIO_IRQ_INFO_MASKABLE | |
+| | +-----+--------------------------+ |
+| | | 2 | VFIO_IRQ_INFO_AUTOMASKED | |
+| | +-----+--------------------------+ |
+| | | 3 | VFIO_IRQ_INFO_NORESIZE | |
+| | +-----+--------------------------+ |
++-------+--------+---------------------------+
+| index | 8 | 4 |
++-------+--------+---------------------------+
+| count | 12 | 4 |
++-------+--------+---------------------------+
+
+* *argsz* is the maximum size of the reply payload (16 bytes today)
+* index is the index of IRQ type being queried (e.g. ``VFIO_PCI_MSIX_IRQ_INDEX``)
+* all other fields must be zero
+
+Reply
+^^^^^
+
++-------+--------+---------------------------+
+| Name | Offset | Size |
++=======+========+===========================+
+| argsz | 0 | 4 |
++-------+--------+---------------------------+
+| flags | 4 | 4 |
++-------+--------+---------------------------+
+| | +-----+--------------------------+ |
+| | | Bit | Definition | |
+| | +=====+==========================+ |
+| | | 0 | VFIO_IRQ_INFO_EVENTFD | |
+| | +-----+--------------------------+ |
+| | | 1 | VFIO_IRQ_INFO_MASKABLE | |
+| | +-----+--------------------------+ |
+| | | 2 | VFIO_IRQ_INFO_AUTOMASKED | |
+| | +-----+--------------------------+ |
+| | | 3 | VFIO_IRQ_INFO_NORESIZE | |
+| | +-----+--------------------------+ |
++-------+--------+---------------------------+
+| index | 8 | 4 |
++-------+--------+---------------------------+
+| count | 12 | 4 |
++-------+--------+---------------------------+
+
+* *argsz* is the size required for the full reply payload (16 bytes today)
+* *flags* defines IRQ attributes:
+
+ * ``VFIO_IRQ_INFO_EVENTFD`` indicates the IRQ type can support server eventfd
+ signalling.
+ * ``VFIO_IRQ_INFO_MASKABLE`` indicates that the IRQ type supports the ``MASK``
+ and ``UNMASK`` actions in a ``VFIO_USER_DEVICE_SET_IRQS`` message.
+ * ``VFIO_IRQ_INFO_AUTOMASKED`` indicates the IRQ type masks itself after being
+ triggered, and the client must send an ``UNMASK`` action to receive new
+ interrupts.
+ * ``VFIO_IRQ_INFO_NORESIZE`` indicates ``VFIO_USER_SET_IRQS`` operations setup
+ interrupts as a set, and new sub-indexes cannot be enabled without disabling
+ the entire type.
+* index is the index of IRQ type being queried
+* count describes the number of interrupts of the queried type.
+
+``VFIO_USER_DEVICE_SET_IRQS``
+-----------------------------
+
+This command message is sent by the client to the server to set actions for
+device interrupt types. The VFIO IRQ set structure is defined in
+``<linux/vfio.h>`` (``struct vfio_irq_set``).
+
+Request
+^^^^^^^
+
++-------+--------+------------------------------+
+| Name | Offset | Size |
++=======+========+==============================+
+| argsz | 0 | 4 |
++-------+--------+------------------------------+
+| flags | 4 | 4 |
++-------+--------+------------------------------+
+| | +-----+-----------------------------+ |
+| | | Bit | Definition | |
+| | +=====+=============================+ |
+| | | 0 | VFIO_IRQ_SET_DATA_NONE | |
+| | +-----+-----------------------------+ |
+| | | 1 | VFIO_IRQ_SET_DATA_BOOL | |
+| | +-----+-----------------------------+ |
+| | | 2 | VFIO_IRQ_SET_DATA_EVENTFD | |
+| | +-----+-----------------------------+ |
+| | | 3 | VFIO_IRQ_SET_ACTION_MASK | |
+| | +-----+-----------------------------+ |
+| | | 4 | VFIO_IRQ_SET_ACTION_UNMASK | |
+| | +-----+-----------------------------+ |
+| | | 5 | VFIO_IRQ_SET_ACTION_TRIGGER | |
+| | +-----+-----------------------------+ |
++-------+--------+------------------------------+
+| index | 8 | 4 |
++-------+--------+------------------------------+
+| start | 12 | 4 |
++-------+--------+------------------------------+
+| count | 16 | 4 |
++-------+--------+------------------------------+
+| data | 20 | variable |
++-------+--------+------------------------------+
+
+* *argsz* is the size of the VFIO IRQ set request payload, including any *data*
+ field. Note there is no reply payload, so this field differs from other
+ message types.
+* *flags* defines the action performed on the interrupt range. The ``DATA``
+ flags describe the data field sent in the message; the ``ACTION`` flags
+ describe the action to be performed. The flags are mutually exclusive for
+ both sets.
+
+ * ``VFIO_IRQ_SET_DATA_NONE`` indicates there is no data field in the command.
+ The action is performed unconditionally.
+ * ``VFIO_IRQ_SET_DATA_BOOL`` indicates the data field is an array of boolean
+ bytes. The action is performed if the corresponding boolean is true.
+ * ``VFIO_IRQ_SET_DATA_EVENTFD`` indicates an array of event file descriptors
+ was sent in the message meta-data. These descriptors will be signalled when
+ the action defined by the action flags occurs. In ``AF_UNIX`` sockets, the
+ descriptors are sent as ``SCM_RIGHTS`` type ancillary data.
+ If no file descriptors are provided, this de-assigns the specified
+ previously configured interrupts.
+ * ``VFIO_IRQ_SET_ACTION_MASK`` indicates a masking event. It can be used with
+ ``VFIO_IRQ_SET_DATA_BOOL`` or ``VFIO_IRQ_SET_DATA_NONE`` to mask an interrupt,
+ or with ``VFIO_IRQ_SET_DATA_EVENTFD`` to generate an event when the guest masks
+ the interrupt.
+ * ``VFIO_IRQ_SET_ACTION_UNMASK`` indicates an unmasking event. It can be used
+ with ``VFIO_IRQ_SET_DATA_BOOL`` or ``VFIO_IRQ_SET_DATA_NONE`` to unmask an
+ interrupt, or with ``VFIO_IRQ_SET_DATA_EVENTFD`` to generate an event when the
+ guest unmasks the interrupt.
+ * ``VFIO_IRQ_SET_ACTION_TRIGGER`` indicates a triggering event. It can be used
+ with ``VFIO_IRQ_SET_DATA_BOOL`` or ``VFIO_IRQ_SET_DATA_NONE`` to trigger an
+ interrupt, or with ``VFIO_IRQ_SET_DATA_EVENTFD`` to generate an event when the
+ server triggers the interrupt.
+
+* *index* is the index of IRQ type being setup.
+* *start* is the start of the sub-index being set.
+* *count* describes the number of sub-indexes being set. As a special case, a
+ count (and start) of 0, with data flags of ``VFIO_IRQ_SET_DATA_NONE`` disables
+ all interrupts of the index.
+* *data* is an optional field included when the
+ ``VFIO_IRQ_SET_DATA_BOOL`` flag is present. It contains an array of booleans
+ that specify whether the action is to be performed on the corresponding
+ index. It's used when the action is only performed on a subset of the range
+ specified.
+
+Not all interrupt types support every combination of data and action flags.
+The client must know the capabilities of the device and IRQ index before it
+sends a ``VFIO_USER_DEVICE_SET_IRQ`` message.
+
+In typical operation, a specific IRQ may operate as follows:
+
+1. The client sends a ``VFIO_USER_DEVICE_SET_IRQ`` message with
+ ``flags=(VFIO_IRQ_SET_DATA_EVENTFD|VFIO_IRQ_SET_ACTION_TRIGGER)`` along
+ with an eventfd. This associates the IRQ with a particular eventfd on the
+ server side.
+
+#. The client may send a ``VFIO_USER_DEVICE_SET_IRQ`` message with
+ ``flags=(VFIO_IRQ_SET_DATA_EVENTFD|VFIO_IRQ_SET_ACTION_MASK/UNMASK)`` along
+ with another eventfd. This associates the given eventfd with the
+ mask/unmask state on the server side.
+
+#. The server may trigger the IRQ by writing 1 to the eventfd.
+
+#. The server may mask/unmask an IRQ which will write 1 to the corresponding
+ mask/unmask eventfd, if there is one.
+
+5. A client may trigger a device IRQ itself, by sending a
+ ``VFIO_USER_DEVICE_SET_IRQ`` message with
+ ``flags=(VFIO_IRQ_SET_DATA_NONE/BOOL|VFIO_IRQ_SET_ACTION_TRIGGER)``.
+
+6. A client may mask or unmask the IRQ, by sending a
+ ``VFIO_USER_DEVICE_SET_IRQ`` message with
+ ``flags=(VFIO_IRQ_SET_DATA_NONE/BOOL|VFIO_IRQ_SET_ACTION_MASK/UNMASK)``.
+
+Reply
+^^^^^
+
+There is no payload in the reply.
+
+.. _Read and Write Operations:
+
+Note that all of these operations must be supported by the client and/or server,
+even if the corresponding memory or device region has been shared as mappable.
+
+The ``count`` field must not exceed the value of ``max_data_xfer_size`` of the
+peer, for both reads and writes.
+
+``VFIO_USER_REGION_READ``
+-------------------------
+
+If a device region is not mappable, it's not directly accessible by the client
+via ``mmap()`` of the underlying file descriptor. In this case, a client can
+read from a device region with this message.
+
+Request
+^^^^^^^
+
++--------+--------+----------+
+| Name | Offset | Size |
++========+========+==========+
+| offset | 0 | 8 |
++--------+--------+----------+
+| region | 8 | 4 |
++--------+--------+----------+
+| count | 12 | 4 |
++--------+--------+----------+
+
+* *offset* into the region being accessed.
+* *region* is the index of the region being accessed.
+* *count* is the size of the data to be transferred.
+
+Reply
+^^^^^
+
++--------+--------+----------+
+| Name | Offset | Size |
++========+========+==========+
+| offset | 0 | 8 |
++--------+--------+----------+
+| region | 8 | 4 |
++--------+--------+----------+
+| count | 12 | 4 |
++--------+--------+----------+
+| data | 16 | variable |
++--------+--------+----------+
+
+* *offset* into the region accessed.
+* *region* is the index of the region accessed.
+* *count* is the size of the data transferred.
+* *data* is the data that was read from the device region.
+
+``VFIO_USER_REGION_WRITE``
+--------------------------
+
+If a device region is not mappable, it's not directly accessible by the client
+via mmap() of the underlying fd. In this case, a client can write to a device
+region with this message.
+
+Request
+^^^^^^^
+
++--------+--------+----------+
+| Name | Offset | Size |
++========+========+==========+
+| offset | 0 | 8 |
++--------+--------+----------+
+| region | 8 | 4 |
++--------+--------+----------+
+| count | 12 | 4 |
++--------+--------+----------+
+| data | 16 | variable |
++--------+--------+----------+
+
+* *offset* into the region being accessed.
+* *region* is the index of the region being accessed.
+* *count* is the size of the data to be transferred.
+* *data* is the data to write
+
+Reply
+^^^^^
+
++--------+--------+----------+
+| Name | Offset | Size |
++========+========+==========+
+| offset | 0 | 8 |
++--------+--------+----------+
+| region | 8 | 4 |
++--------+--------+----------+
+| count | 12 | 4 |
++--------+--------+----------+
+
+* *offset* into the region accessed.
+* *region* is the index of the region accessed.
+* *count* is the size of the data transferred.
+
+``VFIO_USER_DMA_READ``
+-----------------------
+
+If the client has not shared mappable memory, the server can use this message to
+read from guest memory.
+
+Request
+^^^^^^^
+
++---------+--------+----------+
+| Name | Offset | Size |
++=========+========+==========+
+| address | 0 | 8 |
++---------+--------+----------+
+| count | 8 | 8 |
++---------+--------+----------+
+
+* *address* is the client DMA memory address being accessed. This address must have
+ been previously exported to the server with a ``VFIO_USER_DMA_MAP`` message.
+* *count* is the size of the data to be transferred.
+
+Reply
+^^^^^
+
++---------+--------+----------+
+| Name | Offset | Size |
++=========+========+==========+
+| address | 0 | 8 |
++---------+--------+----------+
+| count | 8 | 8 |
++---------+--------+----------+
+| data | 16 | variable |
++---------+--------+----------+
+
+* *address* is the client DMA memory address being accessed.
+* *count* is the size of the data transferred.
+* *data* is the data read.
+
+``VFIO_USER_DMA_WRITE``
+-----------------------
+
+If the client has not shared mappable memory, the server can use this message to
+write to guest memory.
+
+Request
+^^^^^^^
+
++---------+--------+----------+
+| Name | Offset | Size |
++=========+========+==========+
+| address | 0 | 8 |
++---------+--------+----------+
+| count | 8 | 8 |
++---------+--------+----------+
+| data | 16 | variable |
++---------+--------+----------+
+
+* *address* is the client DMA memory address being accessed. This address must have
+ been previously exported to the server with a ``VFIO_USER_DMA_MAP`` message.
+* *count* is the size of the data to be transferred.
+* *data* is the data to write
+
+Reply
+^^^^^
+
++---------+--------+----------+
+| Name | Offset | Size |
++=========+========+==========+
+| address | 0 | 8 |
++---------+--------+----------+
+| count | 8 | 4 |
++---------+--------+----------+
+
+* *address* is the client DMA memory address being accessed.
+* *count* is the size of the data transferred.
+
+``VFIO_USER_DEVICE_RESET``
+--------------------------
+
+This command message is sent from the client to the server to reset the device.
+Neither the request or reply have a payload.
+
+``VFIO_USER_REGION_WRITE_MULTI``
+--------------------------------
+
+This message can be used to coalesce multiple device write operations
+into a single messgage. It is only used as an optimization when the
+outgoing message queue is relatively full.
+
+Request
+^^^^^^^
+
++---------+--------+----------+
+| Name | Offset | Size |
++=========+========+==========+
+| wr_cnt | 0 | 8 |
++---------+--------+----------+
+| wrs | 8 | variable |
++---------+--------+----------+
+
+* *wr_cnt* is the number of device writes coalesced in the message
+* *wrs* is an array of device writes defined below
+
+Single Device Write Format
+""""""""""""""""""""""""""
+
++--------+--------+----------+
+| Name | Offset | Size |
++========+========+==========+
+| offset | 0 | 8 |
++--------+--------+----------+
+| region | 8 | 4 |
++--------+--------+----------+
+| count | 12 | 4 |
++--------+--------+----------+
+| data | 16 | 8 |
++--------+--------+----------+
+
+* *offset* into the region being accessed.
+* *region* is the index of the region being accessed.
+* *count* is the size of the data to be transferred. This format can
+ only describe writes of 8 bytes or less.
+* *data* is the data to write.
+
+Reply
+^^^^^
+
++---------+--------+----------+
+| Name | Offset | Size |
++=========+========+==========+
+| wr_cnt | 0 | 8 |
++---------+--------+----------+
+
+* *wr_cnt* is the number of device writes completed.
+
+
+Appendices
+==========
+
+Unused VFIO ``ioctl()`` commands
+--------------------------------
+
+The following VFIO commands do not have an equivalent vfio-user command:
+
+* ``VFIO_GET_API_VERSION``
+* ``VFIO_CHECK_EXTENSION``
+* ``VFIO_SET_IOMMU``
+* ``VFIO_GROUP_GET_STATUS``
+* ``VFIO_GROUP_SET_CONTAINER``
+* ``VFIO_GROUP_UNSET_CONTAINER``
+* ``VFIO_GROUP_GET_DEVICE_FD``
+* ``VFIO_IOMMU_GET_INFO``
+
+However, once support for live migration for VFIO devices is finalized some
+of the above commands may have to be handled by the client in their
+corresponding vfio-user form. This will be addressed in a future protocol
+version.
+
+VFIO groups and containers
+^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+The current VFIO implementation includes group and container idioms that
+describe how a device relates to the host IOMMU. In the vfio-user
+implementation, the IOMMU is implemented in SW by the client, and is not
+visible to the server. The simplest idea would be that the client put each
+device into its own group and container.
+
+Backend Program Conventions
+---------------------------
+
+vfio-user backend program conventions are based on the vhost-user ones.
+
+* The backend program must not daemonize itself.
+* No assumptions must be made as to what access the backend program has on the
+ system.
+* File descriptors 0, 1 and 2 must exist, must have regular
+ stdin/stdout/stderr semantics, and can be redirected.
+* The backend program must honor the SIGTERM signal.
+* The backend program must accept the following commands line options:
+
+ * ``--socket-path=PATH``: path to UNIX domain socket,
+ * ``--fd=FDNUM``: file descriptor for UNIX domain socket, incompatible with
+ ``--socket-path``
+* The backend program must be accompanied with a JSON file stored under
+ ``/usr/share/vfio-user``.
+
+TODO add schema similar to docs/interop/vhost-user.json.
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* [PATCH v8 12/28] vfio-user: add vfio-user class and container
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (10 preceding siblings ...)
2025-02-19 14:48 ` [PATCH v8 11/28] vfio-user: introduce vfio-user protocol specification John Levon
@ 2025-02-19 14:48 ` John Levon
2025-02-19 14:48 ` [PATCH v8 13/28] vfio-user: connect vfio proxy to remote server John Levon
` (18 subsequent siblings)
30 siblings, 0 replies; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin, Jagannathan Raman, John Johnson,
Elena Ufimtseva
From: Jagannathan Raman <jag.raman@oracle.com>
Introduce basic plumbing for vfio-user behind a new
--enable-vfio-user-client option.
We introduce VFIOUserContainer in hw/vfio-user/container.c, which is a
container type for the "IOMMU" type "vfio-iommu-user", and share some
common container code from hw/vfio/container.c.
Add hw/vfio-user/pci.c for instantiating VFIOUserPCIDevice objects,
sharing some common code from hw/vfio/pci.c.
Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
---
MAINTAINERS | 2 +
hw/meson.build | 1 +
hw/vfio-user/container.c | 222 ++++++++++++++++++++++++++
hw/vfio-user/container.h | 23 +++
hw/vfio-user/meson.build | 9 ++
hw/vfio-user/pci.c | 154 ++++++++++++++++++
hw/vfio/container.c | 2 +-
hw/vfio/pci.c | 12 +-
hw/vfio/pci.h | 7 +
include/hw/vfio/vfio-common.h | 3 +
include/hw/vfio/vfio-container-base.h | 1 +
meson_options.txt | 2 +
scripts/meson-buildoptions.sh | 4 +
13 files changed, 435 insertions(+), 7 deletions(-)
create mode 100644 hw/vfio-user/container.c
create mode 100644 hw/vfio-user/container.h
create mode 100644 hw/vfio-user/meson.build
create mode 100644 hw/vfio-user/pci.c
diff --git a/MAINTAINERS b/MAINTAINERS
index 3e7e6743cc..c403742c27 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4158,6 +4158,8 @@ M: John Levon <john.levon@nutanix.com>
M: Thanos Makatos <thanos.makatos@nutanix.com>
S: Supported
F: docs/devel/vfio-user.rst
+F: hw/vfio-user/*
+F: include/hw/vfio-user/*
F: subprojects/libvfio-user
EBPF:
diff --git a/hw/meson.build b/hw/meson.build
index b827c82c5d..91e8d2bdc0 100644
--- a/hw/meson.build
+++ b/hw/meson.build
@@ -38,6 +38,7 @@ subdir('tpm')
subdir('ufs')
subdir('usb')
subdir('vfio')
+subdir('vfio-user')
subdir('virtio')
subdir('watchdog')
subdir('xen')
diff --git a/hw/vfio-user/container.c b/hw/vfio-user/container.c
new file mode 100644
index 0000000000..7b1c202517
--- /dev/null
+++ b/hw/vfio-user/container.c
@@ -0,0 +1,222 @@
+/*
+ * Container for vfio-user IOMMU type: rather than communicating with the kernel
+ * vfio driver, we communicate over a socket to a server using the vfio-user
+ * protocol.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ */
+
+#include <sys/ioctl.h>
+#include <linux/vfio.h>
+#include "qemu/osdep.h"
+
+#include "exec/address-spaces.h"
+#include "exec/memory.h"
+#include "exec/ram_addr.h"
+#include "hw/hw.h"
+#include "hw/vfio/pci.h"
+#include "hw/vfio-user/container.h"
+#include "qemu/error-report.h"
+#include "qemu/range.h"
+#include "qapi/error.h"
+#include "trace.h"
+
+static int vfio_user_dma_unmap(const VFIOContainerBase *bcontainer,
+ hwaddr iova, ram_addr_t size,
+ IOMMUTLBEntry *iotlb, int flags)
+{
+ return -ENOTSUP;
+}
+
+static int vfio_user_dma_map(const VFIOContainerBase *bcontainer, hwaddr iova,
+ ram_addr_t size, void *vaddr, bool readonly,
+ MemoryRegion *mrp)
+{
+ return -ENOTSUP;
+}
+
+static int
+vfio_user_set_dirty_page_tracking(const VFIOContainerBase *bcontainer,
+ bool start, Error **errp)
+{
+ error_setg_errno(errp, ENOTSUP, "Not supported");
+ return -ENOTSUP;
+}
+
+static int vfio_user_query_dirty_bitmap(const VFIOContainerBase *bcontainer,
+ VFIOBitmap *vbmap, hwaddr iova,
+ hwaddr size, Error **errp)
+{
+ error_setg_errno(errp, ENOTSUP, "Not supported");
+ return -ENOTSUP;
+}
+
+static bool vfio_user_setup(VFIOContainerBase *bcontainer, Error **errp)
+{
+ error_setg_errno(errp, ENOTSUP, "Not supported");
+ return -ENOTSUP;
+}
+
+static VFIOUserContainer *vfio_create_user_container(Error **errp)
+{
+ VFIOUserContainer *container;
+
+ container = VFIO_IOMMU_USER(object_new(TYPE_VFIO_IOMMU_USER));
+ return container;
+}
+
+/*
+ * Try to mirror vfio_connect_container() as much as possible.
+ */
+static VFIOUserContainer *
+vfio_connect_user_container(AddressSpace *as, Error **errp)
+{
+ VFIOContainerBase *bcontainer;
+ VFIOUserContainer *container;
+ VFIOAddressSpace *space;
+ VFIOIOMMUClass *vioc;
+
+ space = vfio_get_address_space(as);
+
+ container = vfio_create_user_container(errp);
+ if (!container) {
+ goto put_space_exit;
+ }
+
+ bcontainer = &container->bcontainer;
+
+ if (!vfio_cpr_register_container(bcontainer, errp)) {
+ goto free_container_exit;
+ }
+
+ vioc = VFIO_IOMMU_GET_CLASS(bcontainer);
+ assert(vioc->setup);
+
+ if (!vioc->setup(bcontainer, errp)) {
+ goto unregister_container_exit;
+ }
+
+ vfio_address_space_insert(space, bcontainer);
+
+ bcontainer->listener = vfio_memory_listener;
+ memory_listener_register(&bcontainer->listener, bcontainer->space->as);
+
+ if (bcontainer->error) {
+ errno = EINVAL;
+ error_propagate_prepend(errp, bcontainer->error,
+ "memory listener initialization failed: ");
+ goto listener_release_exit;
+ }
+
+ bcontainer->initialized = true;
+
+ return container;
+
+listener_release_exit:
+ memory_listener_unregister(&bcontainer->listener);
+ if (vioc->release) {
+ vioc->release(bcontainer);
+ }
+
+unregister_container_exit:
+ vfio_cpr_unregister_container(bcontainer);
+
+free_container_exit:
+ object_unref(container);
+
+put_space_exit:
+ vfio_put_address_space(space);
+
+ return NULL;
+}
+
+static void vfio_disconnect_user_container(VFIOUserContainer *container)
+{
+ VFIOContainerBase *bcontainer = &container->bcontainer;
+ VFIOIOMMUClass *vioc = VFIO_IOMMU_GET_CLASS(bcontainer);
+
+ memory_listener_unregister(&bcontainer->listener);
+ if (vioc->release) {
+ vioc->release(bcontainer);
+ }
+
+ VFIOAddressSpace *space = bcontainer->space;
+
+ vfio_cpr_unregister_container(bcontainer);
+ object_unref(container);
+
+ vfio_put_address_space(space);
+}
+
+static bool vfio_user_get_device(VFIOUserContainer *container,
+ VFIODevice *vbasedev, Error **errp)
+{
+ struct vfio_device_info info = { 0 };
+
+ vbasedev->fd = -1;
+
+ vfio_prepare_device(vbasedev, &container->bcontainer, NULL, &info);
+
+ return true;
+}
+
+/*
+ * vfio_user_attach_device: attach a device to a new container.
+ */
+static bool vfio_user_attach_device(const char *name, VFIODevice *vbasedev,
+ AddressSpace *as, Error **errp)
+{
+ VFIOUserContainer *container;
+
+ container = vfio_connect_user_container(as, errp);
+ if (container == NULL) {
+ error_prepend(errp, "failed to connect proxy");
+ return false;
+ }
+
+ return vfio_user_get_device(container, vbasedev, errp);
+}
+
+static void vfio_user_detach_device(VFIODevice *vbasedev)
+{
+ VFIOUserContainer *container = container_of(vbasedev->bcontainer,
+ VFIOUserContainer, bcontainer);
+
+ QLIST_REMOVE(vbasedev, global_next);
+ QLIST_REMOVE(vbasedev, container_next);
+ vbasedev->bcontainer = NULL;
+ vfio_put_base_device(vbasedev);
+ vfio_disconnect_user_container(container);
+}
+
+static int vfio_user_pci_hot_reset(VFIODevice *vbasedev, bool single)
+{
+ /* ->needs_reset is always false for vfio-user. */
+ return 0;
+}
+
+static void vfio_iommu_user_class_init(ObjectClass *klass, void *data)
+{
+ VFIOIOMMUClass *vioc = VFIO_IOMMU_CLASS(klass);
+
+ vioc->setup = vfio_user_setup;
+ vioc->dma_map = vfio_user_dma_map;
+ vioc->dma_unmap = vfio_user_dma_unmap;
+ vioc->attach_device = vfio_user_attach_device;
+ vioc->detach_device = vfio_user_detach_device;
+ vioc->set_dirty_page_tracking = vfio_user_set_dirty_page_tracking;
+ vioc->query_dirty_bitmap = vfio_user_query_dirty_bitmap;
+ vioc->pci_hot_reset = vfio_user_pci_hot_reset;
+};
+
+static const TypeInfo types[] = {
+ {
+ .name = TYPE_VFIO_IOMMU_USER,
+ .parent = TYPE_VFIO_IOMMU,
+ .instance_size = sizeof(VFIOUserContainer),
+ .class_init = vfio_iommu_user_class_init,
+ },
+};
+
+DEFINE_TYPES(types)
diff --git a/hw/vfio-user/container.h b/hw/vfio-user/container.h
new file mode 100644
index 0000000000..24ce13bc2d
--- /dev/null
+++ b/hw/vfio-user/container.h
@@ -0,0 +1,23 @@
+/*
+ * vfio-user specific definitions.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ */
+
+#ifndef HW_VFIO_USER_CONTAINER_H
+#define HW_VFIO_USER_CONTAINER_H
+
+#include <inttypes.h>
+#include <stdbool.h>
+
+#include "hw/vfio/vfio-common.h"
+
+/* MMU container sub-class for vfio-user. */
+typedef struct VFIOUserContainer {
+ VFIOContainerBase bcontainer;
+} VFIOUserContainer;
+
+OBJECT_DECLARE_SIMPLE_TYPE(VFIOUserContainer, VFIO_IOMMU_USER);
+
+#endif /* HW_VFIO_USER_CONTAINER_H */
diff --git a/hw/vfio-user/meson.build b/hw/vfio-user/meson.build
new file mode 100644
index 0000000000..f1fee70c85
--- /dev/null
+++ b/hw/vfio-user/meson.build
@@ -0,0 +1,9 @@
+vfio_user_ss = ss.source_set()
+vfio_user_ss.add(files(
+ 'container.c',
+ 'pci.c',
+))
+
+if get_option('vfio_user_client').enabled()
+ specific_ss.add_all(vfio_user_ss)
+endif
diff --git a/hw/vfio-user/pci.c b/hw/vfio-user/pci.c
new file mode 100644
index 0000000000..6c85c60179
--- /dev/null
+++ b/hw/vfio-user/pci.c
@@ -0,0 +1,154 @@
+/*
+ * vfio PCI device over a UNIX socket.
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include <linux/vfio.h>
+#include <sys/ioctl.h>
+#include "qemu/osdep.h"
+
+#include "hw/hw.h"
+#include "hw/pci/msi.h"
+#include "hw/pci/msix.h"
+#include "hw/pci/pci_bridge.h"
+#include "hw/qdev-properties.h"
+#include "hw/qdev-properties-system.h"
+#include "hw/vfio/pci.h"
+#include "qapi/error.h"
+#include "qobject/qdict.h"
+#include "qemu/error-report.h"
+#include "qemu/module.h"
+#include "qemu/range.h"
+#include "qemu/units.h"
+#include "system/kvm.h"
+#include "trace.h"
+
+#define TYPE_VFIO_USER_PCI "vfio-user-pci"
+OBJECT_DECLARE_SIMPLE_TYPE(VFIOUserPCIDevice, VFIO_USER_PCI)
+
+struct VFIOUserPCIDevice {
+ VFIOPCIDevice device;
+ char *sock_name;
+};
+
+/*
+ * Emulated devices don't use host hot reset
+ */
+static void vfio_user_compute_needs_reset(VFIODevice *vbasedev)
+{
+ vbasedev->needs_reset = false;
+}
+
+static VFIODeviceOps vfio_user_pci_ops = {
+ .vfio_compute_needs_reset = vfio_user_compute_needs_reset,
+ .vfio_eoi = vfio_intx_eoi,
+ .vfio_get_object = vfio_pci_get_object,
+ .vfio_save_config = vfio_pci_save_config,
+ .vfio_load_config = vfio_pci_load_config,
+};
+
+static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
+{
+ ERRP_GUARD();
+ VFIOUserPCIDevice *udev = VFIO_USER_PCI(pdev);
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
+ VFIODevice *vbasedev = &vdev->vbasedev;
+ AddressSpace *as;
+
+ /*
+ * TODO: make option parser understand SocketAddress
+ * and use that instead of having scalar options
+ * for each socket type.
+ */
+ if (!udev->sock_name) {
+ error_setg(errp, "No socket specified");
+ error_append_hint(errp, "Use -device vfio-user-pci,socket=<name>\n");
+ return;
+ }
+
+ vbasedev->name = g_strdup_printf("VFIO user <%s>", udev->sock_name);
+ vbasedev->ops = &vfio_user_pci_ops;
+ vbasedev->type = VFIO_DEVICE_TYPE_PCI;
+ vbasedev->dev = DEVICE(vdev);
+
+ /*
+ * vfio-user devices are effectively mdevs (don't use a host iommu).
+ */
+ vbasedev->mdev = true;
+
+ as = pci_device_iommu_address_space(pdev);
+ if (!vfio_attach_device_by_iommu_type(TYPE_VFIO_IOMMU_USER,
+ vbasedev->name, vbasedev,
+ as, errp)) {
+ error_prepend(errp, VFIO_MSG_PREFIX, vbasedev->name);
+ return;
+ }
+}
+
+static void vfio_user_instance_init(Object *obj)
+{
+ PCIDevice *pci_dev = PCI_DEVICE(obj);
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(obj);
+ VFIODevice *vbasedev = &vdev->vbasedev;
+
+ device_add_bootindex_property(obj, &vdev->bootindex,
+ "bootindex", NULL,
+ &pci_dev->qdev);
+ vdev->host.domain = ~0U;
+ vdev->host.bus = ~0U;
+ vdev->host.slot = ~0U;
+ vdev->host.function = ~0U;
+
+ vfio_device_init(vbasedev, VFIO_DEVICE_TYPE_PCI, &vfio_user_pci_ops,
+ &vfio_dev_io_ioctl, DEVICE(vdev), false);
+
+ vdev->nv_gpudirect_clique = 0xFF;
+
+ /*
+ * QEMU_PCI_CAP_EXPRESS initialization does not depend on QEMU command
+ * line, therefore, no need to wait to realize like other devices.
+ */
+ pci_dev->cap_present |= QEMU_PCI_CAP_EXPRESS;
+}
+
+static void vfio_user_instance_finalize(Object *obj)
+{
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(obj);
+
+ vfio_pci_put_device(vdev);
+}
+
+static const Property vfio_user_pci_dev_properties[] = {
+ DEFINE_PROP_STRING("socket", VFIOUserPCIDevice, sock_name),
+};
+
+static void vfio_user_pci_dev_class_init(ObjectClass *klass, void *data)
+{
+ DeviceClass *dc = DEVICE_CLASS(klass);
+ PCIDeviceClass *pdc = PCI_DEVICE_CLASS(klass);
+
+ device_class_set_props(dc, vfio_user_pci_dev_properties);
+ dc->desc = "VFIO over socket PCI device assignment";
+ pdc->realize = vfio_user_pci_realize;
+}
+
+static const TypeInfo vfio_user_pci_dev_info = {
+ .name = TYPE_VFIO_USER_PCI,
+ .parent = TYPE_VFIO_PCI_BASE,
+ .instance_size = sizeof(VFIOUserPCIDevice),
+ .class_init = vfio_user_pci_dev_class_init,
+ .instance_init = vfio_user_instance_init,
+ .instance_finalize = vfio_user_instance_finalize,
+};
+
+static void register_vfio_user_dev_type(void)
+{
+ type_register_static(&vfio_user_pci_dev_info);
+}
+
+ type_init(register_vfio_user_dev_type)
diff --git a/hw/vfio/container.c b/hw/vfio/container.c
index 36cd245c92..0e1af34ce4 100644
--- a/hw/vfio/container.c
+++ b/hw/vfio/container.c
@@ -884,7 +884,7 @@ static bool vfio_get_device(VFIOGroup *group, const char *name,
return true;
}
-static void vfio_put_base_device(VFIODevice *vbasedev)
+void vfio_put_base_device(VFIODevice *vbasedev)
{
if (vbasedev->regions != NULL) {
int i;
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index a9cc9366fb..a7084a7690 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -109,7 +109,7 @@ static void vfio_intx_interrupt(void *opaque)
}
}
-static void vfio_intx_eoi(VFIODevice *vbasedev)
+void vfio_intx_eoi(VFIODevice *vbasedev)
{
VFIOPCIDevice *vdev = container_of(vbasedev, VFIOPCIDevice, vbasedev);
@@ -2587,7 +2587,7 @@ static void vfio_pci_compute_needs_reset(VFIODevice *vbasedev)
}
}
-static Object *vfio_pci_get_object(VFIODevice *vbasedev)
+Object *vfio_pci_get_object(VFIODevice *vbasedev)
{
VFIOPCIDevice *vdev = container_of(vbasedev, VFIOPCIDevice, vbasedev);
@@ -2643,7 +2643,7 @@ static const VMStateDescription vmstate_vfio_pci_config = {
}
};
-static int vfio_pci_save_config(VFIODevice *vbasedev, QEMUFile *f, Error **errp)
+int vfio_pci_save_config(VFIODevice *vbasedev, QEMUFile *f, Error **errp)
{
VFIOPCIDevice *vdev = container_of(vbasedev, VFIOPCIDevice, vbasedev);
@@ -2651,7 +2651,7 @@ static int vfio_pci_save_config(VFIODevice *vbasedev, QEMUFile *f, Error **errp)
errp);
}
-static int vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f)
+int vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f)
{
VFIOPCIDevice *vdev = container_of(vbasedev, VFIOPCIDevice, vbasedev);
PCIDevice *pdev = &vdev->pdev;
@@ -2847,7 +2847,7 @@ static bool vfio_populate_device(VFIOPCIDevice *vdev, Error **errp)
return true;
}
-static void vfio_pci_put_device(VFIOPCIDevice *vdev)
+void vfio_pci_put_device(VFIOPCIDevice *vdev)
{
vfio_detach_device(&vdev->vbasedev);
@@ -3394,7 +3394,7 @@ post_reset:
vfio_pci_post_reset(vdev);
}
-static void vfio_instance_init(Object *obj)
+void vfio_instance_init(Object *obj)
{
PCIDevice *pci_dev = PCI_DEVICE(obj);
VFIOPCIDevice *vdev = VFIO_PCI_BASE(obj);
diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h
index 8e79740ddb..c0f030f4db 100644
--- a/hw/vfio/pci.h
+++ b/hw/vfio/pci.h
@@ -213,6 +213,13 @@ uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len);
void vfio_pci_write_config(PCIDevice *pdev,
uint32_t addr, uint32_t val, int len);
+void vfio_intx_eoi(VFIODevice *vbasedev);
+Object *vfio_pci_get_object(VFIODevice *vbasedev);
+int vfio_pci_save_config(VFIODevice *vbasedev, QEMUFile *f, Error **errp);
+int vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f);
+void vfio_pci_put_device(VFIOPCIDevice *vdev);
+void vfio_instance_init(Object *obj);
+
uint64_t vfio_vga_read(void *opaque, hwaddr addr, unsigned size);
void vfio_vga_write(void *opaque, hwaddr addr, uint64_t data, unsigned size);
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index 3512556590..ee8e7f7c0d 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -80,6 +80,7 @@ typedef struct VFIOMigration {
struct VFIOGroup;
+/* MMU container sub-class for legacy vfio implementation. */
typedef struct VFIOContainer {
VFIOContainerBase bcontainer;
int fd; /* /dev/vfio/vfio, empowered by the attached groups */
@@ -106,6 +107,7 @@ typedef struct VFIOIOASHwpt {
QLIST_ENTRY(VFIOIOASHwpt) next;
} VFIOIOASHwpt;
+/* MMU container sub-class for vfio iommufd implementation. */
typedef struct VFIOIOMMUFDContainer {
VFIOContainerBase bcontainer;
IOMMUFDBackend *be;
@@ -285,6 +287,7 @@ bool vfio_attach_device_by_iommu_type(const char *iommu_type, char *name,
Error **errp);
void vfio_detach_device(VFIODevice *vbasedev);
VFIODevice *vfio_get_vfio_device(Object *obj);
+void vfio_put_base_device(VFIODevice *vbasedev);
int vfio_kvm_device_add_fd(int fd, Error **errp);
int vfio_kvm_device_del_fd(int fd, Error **errp);
diff --git a/include/hw/vfio/vfio-container-base.h b/include/hw/vfio/vfio-container-base.h
index 24e48e3a07..1ce93c5b9b 100644
--- a/include/hw/vfio/vfio-container-base.h
+++ b/include/hw/vfio/vfio-container-base.h
@@ -100,6 +100,7 @@ vfio_container_get_page_size_mask(const VFIOContainerBase *bcontainer)
#define TYPE_VFIO_IOMMU_LEGACY TYPE_VFIO_IOMMU "-legacy"
#define TYPE_VFIO_IOMMU_SPAPR TYPE_VFIO_IOMMU "-spapr"
#define TYPE_VFIO_IOMMU_IOMMUFD TYPE_VFIO_IOMMU "-iommufd"
+#define TYPE_VFIO_IOMMU_USER TYPE_VFIO_IOMMU "-user"
OBJECT_DECLARE_TYPE(VFIOContainerBase, VFIOIOMMUClass, VFIO_IOMMU)
diff --git a/meson_options.txt b/meson_options.txt
index 5eeaf3eee5..ba9bc07fcf 100644
--- a/meson_options.txt
+++ b/meson_options.txt
@@ -109,6 +109,8 @@ option('multiprocess', type: 'feature', value: 'auto',
description: 'Out of process device emulation support')
option('relocatable', type : 'boolean', value : true,
description: 'toggle relocatable install')
+option('vfio_user_client', type: 'feature', value: 'disabled',
+ description: 'vfio-user client support')
option('vfio_user_server', type: 'feature', value: 'disabled',
description: 'vfio-user server support')
option('dbus_display', type: 'feature', value: 'auto',
diff --git a/scripts/meson-buildoptions.sh b/scripts/meson-buildoptions.sh
index a8066aab03..6ee381df8c 100644
--- a/scripts/meson-buildoptions.sh
+++ b/scripts/meson-buildoptions.sh
@@ -201,6 +201,8 @@ meson_options_help() {
printf "%s\n" ' vdi vdi image format support'
printf "%s\n" ' vduse-blk-export'
printf "%s\n" ' VDUSE block export support'
+ printf "%s\n" ' vfio-user-client'
+ printf "%s\n" ' vfio-user client support'
printf "%s\n" ' vfio-user-server'
printf "%s\n" ' vfio-user server support'
printf "%s\n" ' vhdx vhdx image format support'
@@ -529,6 +531,8 @@ _meson_option_parse() {
--disable-vdi) printf "%s" -Dvdi=disabled ;;
--enable-vduse-blk-export) printf "%s" -Dvduse_blk_export=enabled ;;
--disable-vduse-blk-export) printf "%s" -Dvduse_blk_export=disabled ;;
+ --enable-vfio-user-client) printf "%s" -Dvfio_user_client=enabled ;;
+ --disable-vfio-user-client) printf "%s" -Dvfio_user_client=disabled ;;
--enable-vfio-user-server) printf "%s" -Dvfio_user_server=enabled ;;
--disable-vfio-user-server) printf "%s" -Dvfio_user_server=disabled ;;
--enable-vhdx) printf "%s" -Dvhdx=enabled ;;
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* [PATCH v8 13/28] vfio-user: connect vfio proxy to remote server
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (11 preceding siblings ...)
2025-02-19 14:48 ` [PATCH v8 12/28] vfio-user: add vfio-user class and container John Levon
@ 2025-02-19 14:48 ` John Levon
2025-02-19 14:48 ` [PATCH v8 14/28] vfio-user: implement message receive infrastructure John Levon
` (17 subsequent siblings)
30 siblings, 0 replies; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin, Jagannathan Raman, John Johnson,
Elena Ufimtseva
From: Jagannathan Raman <jag.raman@oracle.com>
Introduce the vfio-user "proxy": this is the client code responsible for
sending and receiving vfio-user messages across the control socket.
The new files hw/vfio-user/common.[ch] contain some basic plumbing for
managing the proxy; initialize the proxy during realization of the
VFIOUserPCIDevice instance.
Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
---
hw/vfio-user/common.c | 171 ++++++++++++++++++++++++++++++++++
hw/vfio-user/common.h | 78 ++++++++++++++++
hw/vfio-user/meson.build | 1 +
hw/vfio-user/pci.c | 18 ++++
include/hw/vfio/vfio-common.h | 2 +
5 files changed, 270 insertions(+)
create mode 100644 hw/vfio-user/common.c
create mode 100644 hw/vfio-user/common.h
diff --git a/hw/vfio-user/common.c b/hw/vfio-user/common.c
new file mode 100644
index 0000000000..e829abccec
--- /dev/null
+++ b/hw/vfio-user/common.c
@@ -0,0 +1,171 @@
+/*
+ * vfio protocol over a UNIX socket.
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include <linux/vfio.h>
+#include <sys/ioctl.h>
+
+#include "hw/hw.h"
+#include "hw/vfio/vfio-common.h"
+#include "io/channel.h"
+#include "io/channel-socket.h"
+#include "io/channel-util.h"
+#include "qapi/error.h"
+#include "qemu/error-report.h"
+#include "qemu/lockable.h"
+#include "qemu/sockets.h"
+#include "system/iothread.h"
+
+#include "common.h"
+
+static IOThread *vfio_user_iothread;
+
+static void vfio_user_shutdown(VFIOUserProxy *proxy);
+
+
+/*
+ * Functions called by main, CPU, or iothread threads
+ */
+
+static void vfio_user_shutdown(VFIOUserProxy *proxy)
+{
+ qio_channel_shutdown(proxy->ioc, QIO_CHANNEL_SHUTDOWN_READ, NULL);
+ qio_channel_set_aio_fd_handler(proxy->ioc, proxy->ctx, NULL,
+ proxy->ctx, NULL, NULL);
+}
+
+/*
+ * Functions only called by iothread
+ */
+
+static void vfio_user_cb(void *opaque)
+{
+ VFIOUserProxy *proxy = opaque;
+
+ QEMU_LOCK_GUARD(&proxy->lock);
+
+ proxy->state = VFIO_PROXY_CLOSED;
+ qemu_cond_signal(&proxy->close_cv);
+}
+
+
+/*
+ * Functions called by main or CPU threads
+ */
+
+static QLIST_HEAD(, VFIOUserProxy) vfio_user_sockets =
+ QLIST_HEAD_INITIALIZER(vfio_user_sockets);
+
+VFIOUserProxy *vfio_user_connect_dev(SocketAddress *addr, Error **errp)
+{
+ VFIOUserProxy *proxy;
+ QIOChannelSocket *sioc;
+ QIOChannel *ioc;
+ char *sockname;
+
+ if (addr->type != SOCKET_ADDRESS_TYPE_UNIX) {
+ error_setg(errp, "vfio_user_connect - bad address family");
+ return NULL;
+ }
+ sockname = addr->u.q_unix.path;
+
+ sioc = qio_channel_socket_new();
+ ioc = QIO_CHANNEL(sioc);
+ if (qio_channel_socket_connect_sync(sioc, addr, errp)) {
+ object_unref(OBJECT(ioc));
+ return NULL;
+ }
+ qio_channel_set_blocking(ioc, false, NULL);
+
+ proxy = g_malloc0(sizeof(VFIOUserProxy));
+ proxy->sockname = g_strdup_printf("unix:%s", sockname);
+ proxy->ioc = ioc;
+ proxy->flags = VFIO_PROXY_CLIENT;
+ proxy->state = VFIO_PROXY_CONNECTED;
+
+ qemu_mutex_init(&proxy->lock);
+ qemu_cond_init(&proxy->close_cv);
+
+ if (vfio_user_iothread == NULL) {
+ vfio_user_iothread = iothread_create("VFIO user", errp);
+ }
+
+ proxy->ctx = iothread_get_aio_context(vfio_user_iothread);
+
+ QTAILQ_INIT(&proxy->outgoing);
+ QTAILQ_INIT(&proxy->incoming);
+ QTAILQ_INIT(&proxy->free);
+ QTAILQ_INIT(&proxy->pending);
+ QLIST_INSERT_HEAD(&vfio_user_sockets, proxy, next);
+
+ return proxy;
+}
+
+void vfio_user_disconnect(VFIOUserProxy *proxy)
+{
+ VFIOUserMsg *r1, *r2;
+
+ qemu_mutex_lock(&proxy->lock);
+
+ /* our side is quitting */
+ if (proxy->state == VFIO_PROXY_CONNECTED) {
+ vfio_user_shutdown(proxy);
+ if (!QTAILQ_EMPTY(&proxy->pending)) {
+ error_printf("vfio_user_disconnect: outstanding requests\n");
+ }
+ }
+ object_unref(OBJECT(proxy->ioc));
+ proxy->ioc = NULL;
+
+ proxy->state = VFIO_PROXY_CLOSING;
+ QTAILQ_FOREACH_SAFE(r1, &proxy->outgoing, next, r2) {
+ qemu_cond_destroy(&r1->cv);
+ QTAILQ_REMOVE(&proxy->outgoing, r1, next);
+ g_free(r1);
+ }
+ QTAILQ_FOREACH_SAFE(r1, &proxy->incoming, next, r2) {
+ qemu_cond_destroy(&r1->cv);
+ QTAILQ_REMOVE(&proxy->incoming, r1, next);
+ g_free(r1);
+ }
+ QTAILQ_FOREACH_SAFE(r1, &proxy->pending, next, r2) {
+ qemu_cond_destroy(&r1->cv);
+ QTAILQ_REMOVE(&proxy->pending, r1, next);
+ g_free(r1);
+ }
+ QTAILQ_FOREACH_SAFE(r1, &proxy->free, next, r2) {
+ qemu_cond_destroy(&r1->cv);
+ QTAILQ_REMOVE(&proxy->free, r1, next);
+ g_free(r1);
+ }
+
+ /*
+ * Make sure the iothread isn't blocking anywhere
+ * with a ref to this proxy by waiting for a BH
+ * handler to run after the proxy fd handlers were
+ * deleted above.
+ */
+ aio_bh_schedule_oneshot(proxy->ctx, vfio_user_cb, proxy);
+ qemu_cond_wait(&proxy->close_cv, &proxy->lock);
+
+ /* we now hold the only ref to proxy */
+ qemu_mutex_unlock(&proxy->lock);
+ qemu_cond_destroy(&proxy->close_cv);
+ qemu_mutex_destroy(&proxy->lock);
+
+ QLIST_REMOVE(proxy, next);
+ if (QLIST_EMPTY(&vfio_user_sockets)) {
+ iothread_destroy(vfio_user_iothread);
+ vfio_user_iothread = NULL;
+ }
+
+ g_free(proxy->sockname);
+ g_free(proxy);
+}
diff --git a/hw/vfio-user/common.h b/hw/vfio-user/common.h
new file mode 100644
index 0000000000..3529f03df9
--- /dev/null
+++ b/hw/vfio-user/common.h
@@ -0,0 +1,78 @@
+#ifndef VFIO_USER_COMMON_H
+#define VFIO_USER_COMMON_H
+
+/*
+ * vfio protocol over a UNIX socket.
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+typedef struct {
+ int send_fds;
+ int recv_fds;
+ int *fds;
+} VFIOUserFDs;
+
+enum msg_type {
+ VFIO_MSG_NONE,
+ VFIO_MSG_ASYNC,
+ VFIO_MSG_WAIT,
+ VFIO_MSG_NOWAIT,
+ VFIO_MSG_REQ,
+};
+
+typedef struct VFIOUserMsg {
+ QTAILQ_ENTRY(VFIOUserMsg) next;
+ VFIOUserFDs *fds;
+ uint32_t rsize;
+ uint32_t id;
+ QemuCond cv;
+ bool complete;
+ enum msg_type type;
+} VFIOUserMsg;
+
+
+enum proxy_state {
+ VFIO_PROXY_CONNECTED = 1,
+ VFIO_PROXY_ERROR = 2,
+ VFIO_PROXY_CLOSING = 3,
+ VFIO_PROXY_CLOSED = 4,
+};
+
+typedef QTAILQ_HEAD(VFIOUserMsgQ, VFIOUserMsg) VFIOUserMsgQ;
+
+typedef struct VFIOUserProxy {
+ QLIST_ENTRY(VFIOUserProxy) next;
+ char *sockname;
+ struct QIOChannel *ioc;
+ void (*request)(void *opaque, VFIOUserMsg *msg);
+ void *req_arg;
+ int flags;
+ QemuCond close_cv;
+ AioContext *ctx;
+ QEMUBH *req_bh;
+
+ /*
+ * above only changed when BQL is held
+ * below are protected by per-proxy lock
+ */
+ QemuMutex lock;
+ VFIOUserMsgQ free;
+ VFIOUserMsgQ pending;
+ VFIOUserMsgQ incoming;
+ VFIOUserMsgQ outgoing;
+ VFIOUserMsg *last_nowait;
+ enum proxy_state state;
+} VFIOUserProxy;
+
+/* VFIOProxy flags */
+#define VFIO_PROXY_CLIENT 0x1
+
+VFIOUserProxy *vfio_user_connect_dev(SocketAddress *addr, Error **errp);
+void vfio_user_disconnect(VFIOUserProxy *proxy);
+
+#endif /* VFIO_USER_COMMON_H */
diff --git a/hw/vfio-user/meson.build b/hw/vfio-user/meson.build
index f1fee70c85..b89985c641 100644
--- a/hw/vfio-user/meson.build
+++ b/hw/vfio-user/meson.build
@@ -1,5 +1,6 @@
vfio_user_ss = ss.source_set()
vfio_user_ss.add(files(
+ 'common.c',
'container.c',
'pci.c',
))
diff --git a/hw/vfio-user/pci.c b/hw/vfio-user/pci.c
index 6c85c60179..bfd9051524 100644
--- a/hw/vfio-user/pci.c
+++ b/hw/vfio-user/pci.c
@@ -19,6 +19,8 @@
#include "hw/qdev-properties.h"
#include "hw/qdev-properties-system.h"
#include "hw/vfio/pci.h"
+#include "hw/vfio-user/common.h"
+#include "hw/vfio-user/container.h"
#include "qapi/error.h"
#include "qobject/qdict.h"
#include "qemu/error-report.h"
@@ -59,6 +61,8 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
VFIODevice *vbasedev = &vdev->vbasedev;
AddressSpace *as;
+ SocketAddress addr;
+ VFIOUserProxy *proxy;
/*
* TODO: make option parser understand SocketAddress
@@ -71,6 +75,15 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
return;
}
+ memset(&addr, 0, sizeof(addr));
+ addr.type = SOCKET_ADDRESS_TYPE_UNIX;
+ addr.u.q_unix.path = udev->sock_name;
+ proxy = vfio_user_connect_dev(&addr, errp);
+ if (!proxy) {
+ return;
+ }
+ vbasedev->proxy = proxy;
+
vbasedev->name = g_strdup_printf("VFIO user <%s>", udev->sock_name);
vbasedev->ops = &vfio_user_pci_ops;
vbasedev->type = VFIO_DEVICE_TYPE_PCI;
@@ -119,8 +132,13 @@ static void vfio_user_instance_init(Object *obj)
static void vfio_user_instance_finalize(Object *obj)
{
VFIOPCIDevice *vdev = VFIO_PCI_BASE(obj);
+ VFIODevice *vbasedev = &vdev->vbasedev;
vfio_pci_put_device(vdev);
+
+ if (vbasedev->proxy != NULL) {
+ vfio_user_disconnect(vbasedev->proxy);
+ }
}
static const Property vfio_user_pci_dev_properties[] = {
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index ee8e7f7c0d..699e8a9376 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -79,6 +79,7 @@ typedef struct VFIOMigration {
} VFIOMigration;
struct VFIOGroup;
+typedef struct VFIOUserProxy VFIOUserProxy;
/* MMU container sub-class for legacy vfio implementation. */
typedef struct VFIOContainer {
@@ -155,6 +156,7 @@ typedef struct VFIODevice {
IOMMUFDBackend *iommufd;
VFIOIOASHwpt *hwpt;
QLIST_ENTRY(VFIODevice) hwpt_next;
+ VFIOUserProxy *proxy;
struct vfio_region_info **regions;
} VFIODevice;
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* [PATCH v8 14/28] vfio-user: implement message receive infrastructure
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (12 preceding siblings ...)
2025-02-19 14:48 ` [PATCH v8 13/28] vfio-user: connect vfio proxy to remote server John Levon
@ 2025-02-19 14:48 ` John Levon
2025-02-19 14:48 ` [PATCH v8 15/28] vfio-user: implement message send infrastructure John Levon
` (16 subsequent siblings)
30 siblings, 0 replies; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin, Jagannathan Raman, John Johnson,
Elena Ufimtseva
From: Jagannathan Raman <jag.raman@oracle.com>
Add the basic implementation for receiving vfio-user messages from the
control socket.
Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
---
hw/vfio-user/common.c | 412 +++++++++++++++++++++++++++++++++++++-
hw/vfio-user/common.h | 10 +
hw/vfio-user/pci.c | 11 +
hw/vfio-user/protocol.h | 54 +++++
hw/vfio-user/trace-events | 6 +
hw/vfio-user/trace.h | 1 +
meson.build | 1 +
7 files changed, 493 insertions(+), 2 deletions(-)
create mode 100644 hw/vfio-user/protocol.h
create mode 100644 hw/vfio-user/trace-events
create mode 100644 hw/vfio-user/trace.h
diff --git a/hw/vfio-user/common.c b/hw/vfio-user/common.c
index e829abccec..2c4ee14ede 100644
--- a/hw/vfio-user/common.c
+++ b/hw/vfio-user/common.c
@@ -14,21 +14,37 @@
#include "hw/hw.h"
#include "hw/vfio/vfio-common.h"
+#include "hw/vfio-user/common.h"
+#include "hw/vfio-user/trace.h"
#include "io/channel.h"
#include "io/channel-socket.h"
#include "io/channel-util.h"
#include "qapi/error.h"
#include "qemu/error-report.h"
#include "qemu/lockable.h"
+#include "qemu/main-loop.h"
#include "qemu/sockets.h"
#include "system/iothread.h"
-#include "common.h"
-
static IOThread *vfio_user_iothread;
static void vfio_user_shutdown(VFIOUserProxy *proxy);
+static VFIOUserMsg *vfio_user_getmsg(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
+ VFIOUserFDs *fds);
+static VFIOUserFDs *vfio_user_getfds(int numfds);
+static void vfio_user_recycle(VFIOUserProxy *proxy, VFIOUserMsg *msg);
+
+static void vfio_user_recv(void *opaque);
+static int vfio_user_recv_one(VFIOUserProxy *proxy);
+static void vfio_user_cb(void *opaque);
+
+static void vfio_user_request(void *opaque);
+static inline void vfio_user_set_error(VFIOUserHdr *hdr, uint32_t err)
+{
+ hdr->flags |= VFIO_USER_ERROR;
+ hdr->error_reply = err;
+}
/*
* Functions called by main, CPU, or iothread threads
@@ -41,10 +57,340 @@ static void vfio_user_shutdown(VFIOUserProxy *proxy)
proxy->ctx, NULL, NULL);
}
+static VFIOUserMsg *vfio_user_getmsg(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
+ VFIOUserFDs *fds)
+{
+ VFIOUserMsg *msg;
+
+ msg = QTAILQ_FIRST(&proxy->free);
+ if (msg != NULL) {
+ QTAILQ_REMOVE(&proxy->free, msg, next);
+ } else {
+ msg = g_malloc0(sizeof(*msg));
+ qemu_cond_init(&msg->cv);
+ }
+
+ msg->hdr = hdr;
+ msg->fds = fds;
+ return msg;
+}
+
+/*
+ * Recycle a message list entry to the free list.
+ */
+static void vfio_user_recycle(VFIOUserProxy *proxy, VFIOUserMsg *msg)
+{
+ if (msg->type == VFIO_MSG_NONE) {
+ error_printf("vfio_user_recycle - freeing free msg\n");
+ return;
+ }
+
+ /* free msg buffer if no one is waiting to consume the reply */
+ if (msg->type == VFIO_MSG_NOWAIT || msg->type == VFIO_MSG_ASYNC) {
+ g_free(msg->hdr);
+ if (msg->fds != NULL) {
+ g_free(msg->fds);
+ }
+ }
+
+ msg->type = VFIO_MSG_NONE;
+ msg->hdr = NULL;
+ msg->fds = NULL;
+ msg->complete = false;
+ QTAILQ_INSERT_HEAD(&proxy->free, msg, next);
+}
+
+static VFIOUserFDs *vfio_user_getfds(int numfds)
+{
+ VFIOUserFDs *fds = g_malloc0(sizeof(*fds) + (numfds * sizeof(int)));
+
+ fds->fds = (int *)((char *)fds + sizeof(*fds));
+
+ return fds;
+}
+
/*
* Functions only called by iothread
*/
+/*
+ * Process a received message.
+ */
+static void vfio_user_process(VFIOUserProxy *proxy, VFIOUserMsg *msg,
+ bool isreply)
+{
+
+ /*
+ * Replies signal a waiter, if none just check for errors
+ * and free the message buffer.
+ *
+ * Requests get queued for the BH.
+ */
+ if (isreply) {
+ msg->complete = true;
+ if (msg->type == VFIO_MSG_WAIT) {
+ qemu_cond_signal(&msg->cv);
+ } else {
+ if (msg->hdr->flags & VFIO_USER_ERROR) {
+ error_printf("vfio_user_process: error reply on async ");
+ error_printf("request command %x error %s\n",
+ msg->hdr->command,
+ strerror(msg->hdr->error_reply));
+ }
+ /* youngest nowait msg has been ack'd */
+ if (proxy->last_nowait == msg) {
+ proxy->last_nowait = NULL;
+ }
+ vfio_user_recycle(proxy, msg);
+ }
+ } else {
+ QTAILQ_INSERT_TAIL(&proxy->incoming, msg, next);
+ qemu_bh_schedule(proxy->req_bh);
+ }
+}
+
+/*
+ * Complete a partial message read
+ */
+static int vfio_user_complete(VFIOUserProxy *proxy, Error **errp)
+{
+ VFIOUserMsg *msg = proxy->part_recv;
+ size_t msgleft = proxy->recv_left;
+ bool isreply;
+ char *data;
+ int ret;
+
+ data = (char *)msg->hdr + (msg->hdr->size - msgleft);
+ while (msgleft > 0) {
+ ret = qio_channel_read(proxy->ioc, data, msgleft, errp);
+
+ /* error or would block */
+ if (ret <= 0) {
+ /* try for rest on next iternation */
+ if (ret == QIO_CHANNEL_ERR_BLOCK) {
+ proxy->recv_left = msgleft;
+ }
+ return ret;
+ }
+ trace_vfio_user_recv_read(msg->hdr->id, ret);
+
+ msgleft -= ret;
+ data += ret;
+ }
+
+ /*
+ * Read complete message, process it.
+ */
+ proxy->part_recv = NULL;
+ proxy->recv_left = 0;
+ isreply = (msg->hdr->flags & VFIO_USER_TYPE) == VFIO_USER_REPLY;
+ vfio_user_process(proxy, msg, isreply);
+
+ /* return positive value */
+ return 1;
+}
+
+static void vfio_user_recv(void *opaque)
+{
+ VFIOUserProxy *proxy = opaque;
+
+ QEMU_LOCK_GUARD(&proxy->lock);
+
+ if (proxy->state == VFIO_PROXY_CONNECTED) {
+ while (vfio_user_recv_one(proxy) == 0) {
+ ;
+ }
+ }
+}
+
+/*
+ * Receive and process one incoming message.
+ *
+ * For replies, find matching outgoing request and wake any waiters.
+ * For requests, queue in incoming list and run request BH.
+ */
+static int vfio_user_recv_one(VFIOUserProxy *proxy)
+{
+ VFIOUserMsg *msg = NULL;
+ g_autofree int *fdp = NULL;
+ VFIOUserFDs *reqfds;
+ VFIOUserHdr hdr;
+ struct iovec iov = {
+ .iov_base = &hdr,
+ .iov_len = sizeof(hdr),
+ };
+ bool isreply = false;
+ int i, ret;
+ size_t msgleft, numfds = 0;
+ char *data = NULL;
+ char *buf = NULL;
+ Error *local_err = NULL;
+
+ /*
+ * Complete any partial reads
+ */
+ if (proxy->part_recv != NULL) {
+ ret = vfio_user_complete(proxy, &local_err);
+
+ /* still not complete, try later */
+ if (ret == QIO_CHANNEL_ERR_BLOCK) {
+ return ret;
+ }
+
+ if (ret <= 0) {
+ goto fatal;
+ }
+ /* else fall into reading another msg */
+ }
+
+ /*
+ * Read header
+ */
+ ret = qio_channel_readv_full(proxy->ioc, &iov, 1, &fdp, &numfds, 0,
+ &local_err);
+ if (ret == QIO_CHANNEL_ERR_BLOCK) {
+ return ret;
+ }
+
+ /* read error or other side closed connection */
+ if (ret <= 0) {
+ goto fatal;
+ }
+
+ if (ret < sizeof(hdr)) {
+ error_setg(&local_err, "short read of header");
+ goto fatal;
+ }
+
+ /*
+ * Validate header
+ */
+ if (hdr.size < sizeof(VFIOUserHdr)) {
+ error_setg(&local_err, "bad header size");
+ goto fatal;
+ }
+ switch (hdr.flags & VFIO_USER_TYPE) {
+ case VFIO_USER_REQUEST:
+ isreply = false;
+ break;
+ case VFIO_USER_REPLY:
+ isreply = true;
+ break;
+ default:
+ error_setg(&local_err, "unknown message type");
+ goto fatal;
+ }
+ trace_vfio_user_recv_hdr(proxy->sockname, hdr.id, hdr.command, hdr.size,
+ hdr.flags);
+
+ /*
+ * For replies, find the matching pending request.
+ * For requests, reap incoming FDs.
+ */
+ if (isreply) {
+ QTAILQ_FOREACH(msg, &proxy->pending, next) {
+ if (hdr.id == msg->id) {
+ break;
+ }
+ }
+ if (msg == NULL) {
+ error_setg(&local_err, "unexpected reply");
+ goto err;
+ }
+ QTAILQ_REMOVE(&proxy->pending, msg, next);
+
+ /*
+ * Process any received FDs
+ */
+ if (numfds != 0) {
+ if (msg->fds == NULL || msg->fds->recv_fds < numfds) {
+ error_setg(&local_err, "unexpected FDs");
+ goto err;
+ }
+ msg->fds->recv_fds = numfds;
+ memcpy(msg->fds->fds, fdp, numfds * sizeof(int));
+ }
+ } else {
+ if (numfds != 0) {
+ reqfds = vfio_user_getfds(numfds);
+ memcpy(reqfds->fds, fdp, numfds * sizeof(int));
+ } else {
+ reqfds = NULL;
+ }
+ }
+
+ /*
+ * Put the whole message into a single buffer.
+ */
+ if (isreply) {
+ if (hdr.size > msg->rsize) {
+ error_setg(&local_err, "reply larger than recv buffer");
+ goto err;
+ }
+ *msg->hdr = hdr;
+ data = (char *)msg->hdr + sizeof(hdr);
+ } else {
+ buf = g_malloc0(hdr.size);
+ memcpy(buf, &hdr, sizeof(hdr));
+ data = buf + sizeof(hdr);
+ msg = vfio_user_getmsg(proxy, (VFIOUserHdr *)buf, reqfds);
+ msg->type = VFIO_MSG_REQ;
+ }
+
+ /*
+ * Read rest of message.
+ */
+ msgleft = hdr.size - sizeof(hdr);
+ while (msgleft > 0) {
+ ret = qio_channel_read(proxy->ioc, data, msgleft, &local_err);
+
+ /* prepare to complete read on next iternation */
+ if (ret == QIO_CHANNEL_ERR_BLOCK) {
+ proxy->part_recv = msg;
+ proxy->recv_left = msgleft;
+ return ret;
+ }
+
+ if (ret <= 0) {
+ goto fatal;
+ }
+ trace_vfio_user_recv_read(hdr.id, ret);
+
+ msgleft -= ret;
+ data += ret;
+ }
+
+ vfio_user_process(proxy, msg, isreply);
+ return 0;
+
+ /*
+ * fatal means the other side closed or we don't trust the stream
+ * err means this message is corrupt
+ */
+fatal:
+ vfio_user_shutdown(proxy);
+ proxy->state = VFIO_PROXY_ERROR;
+
+ /* set error if server side closed */
+ if (ret == 0) {
+ error_setg(&local_err, "server closed socket");
+ }
+
+err:
+ for (i = 0; i < numfds; i++) {
+ close(fdp[i]);
+ }
+ if (isreply && msg != NULL) {
+ /* force an error to keep sending thread from hanging */
+ vfio_user_set_error(msg->hdr, EINVAL);
+ msg->complete = true;
+ qemu_cond_signal(&msg->cv);
+ }
+ error_prepend(&local_err, "vfio_user_recv_one: ");
+ error_report_err(local_err);
+ return -1;
+}
+
static void vfio_user_cb(void *opaque)
{
VFIOUserProxy *proxy = opaque;
@@ -60,6 +406,53 @@ static void vfio_user_cb(void *opaque)
* Functions called by main or CPU threads
*/
+/*
+ * Process incoming requests.
+ *
+ * The bus-specific callback has the form:
+ * request(opaque, msg)
+ * where 'opaque' was specified in vfio_user_set_handler
+ * and 'msg' is the inbound message.
+ *
+ * The callback is responsible for disposing of the message buffer,
+ * usually by re-using it when calling vfio_send_reply or vfio_send_error,
+ * both of which free their message buffer when the reply is sent.
+ *
+ * If the callback uses a new buffer, it needs to free the old one.
+ */
+static void vfio_user_request(void *opaque)
+{
+ VFIOUserProxy *proxy = opaque;
+ VFIOUserMsgQ new, free;
+ VFIOUserMsg *msg, *m1;
+
+ /* reap all incoming */
+ QTAILQ_INIT(&new);
+ WITH_QEMU_LOCK_GUARD(&proxy->lock) {
+ QTAILQ_FOREACH_SAFE(msg, &proxy->incoming, next, m1) {
+ QTAILQ_REMOVE(&proxy->incoming, msg, next);
+ QTAILQ_INSERT_TAIL(&new, msg, next);
+ }
+ }
+
+ /* process list */
+ QTAILQ_INIT(&free);
+ QTAILQ_FOREACH_SAFE(msg, &new, next, m1) {
+ QTAILQ_REMOVE(&new, msg, next);
+ trace_vfio_user_recv_request(msg->hdr->command);
+ proxy->request(proxy->req_arg, msg);
+ QTAILQ_INSERT_HEAD(&free, msg, next);
+ }
+
+ /* free list */
+ WITH_QEMU_LOCK_GUARD(&proxy->lock) {
+ QTAILQ_FOREACH_SAFE(msg, &free, next, m1) {
+ vfio_user_recycle(proxy, msg);
+ }
+ }
+}
+
+
static QLIST_HEAD(, VFIOUserProxy) vfio_user_sockets =
QLIST_HEAD_INITIALIZER(vfio_user_sockets);
@@ -98,6 +491,7 @@ VFIOUserProxy *vfio_user_connect_dev(SocketAddress *addr, Error **errp)
}
proxy->ctx = iothread_get_aio_context(vfio_user_iothread);
+ proxy->req_bh = qemu_bh_new(vfio_user_request, proxy);
QTAILQ_INIT(&proxy->outgoing);
QTAILQ_INIT(&proxy->incoming);
@@ -108,6 +502,18 @@ VFIOUserProxy *vfio_user_connect_dev(SocketAddress *addr, Error **errp)
return proxy;
}
+void vfio_user_set_handler(VFIODevice *vbasedev,
+ void (*handler)(void *opaque, VFIOUserMsg *msg),
+ void *req_arg)
+{
+ VFIOUserProxy *proxy = vbasedev->proxy;
+
+ proxy->request = handler;
+ proxy->req_arg = req_arg;
+ qio_channel_set_aio_fd_handler(proxy->ioc, proxy->ctx,
+ vfio_user_recv, NULL, NULL, proxy);
+}
+
void vfio_user_disconnect(VFIOUserProxy *proxy)
{
VFIOUserMsg *r1, *r2;
@@ -123,6 +529,8 @@ void vfio_user_disconnect(VFIOUserProxy *proxy)
}
object_unref(OBJECT(proxy->ioc));
proxy->ioc = NULL;
+ qemu_bh_delete(proxy->req_bh);
+ proxy->req_bh = NULL;
proxy->state = VFIO_PROXY_CLOSING;
QTAILQ_FOREACH_SAFE(r1, &proxy->outgoing, next, r2) {
diff --git a/hw/vfio-user/common.h b/hw/vfio-user/common.h
index 3529f03df9..71c0dea82d 100644
--- a/hw/vfio-user/common.h
+++ b/hw/vfio-user/common.h
@@ -11,6 +11,8 @@
*
*/
+#include "hw/vfio-user/protocol.h"
+
typedef struct {
int send_fds;
int recv_fds;
@@ -27,6 +29,7 @@ enum msg_type {
typedef struct VFIOUserMsg {
QTAILQ_ENTRY(VFIOUserMsg) next;
+ VFIOUserHdr *hdr;
VFIOUserFDs *fds;
uint32_t rsize;
uint32_t id;
@@ -66,13 +69,20 @@ typedef struct VFIOUserProxy {
VFIOUserMsgQ incoming;
VFIOUserMsgQ outgoing;
VFIOUserMsg *last_nowait;
+ VFIOUserMsg *part_recv;
+ size_t recv_left;
enum proxy_state state;
} VFIOUserProxy;
/* VFIOProxy flags */
#define VFIO_PROXY_CLIENT 0x1
+typedef struct VFIODevice VFIODevice;
+
VFIOUserProxy *vfio_user_connect_dev(SocketAddress *addr, Error **errp);
void vfio_user_disconnect(VFIOUserProxy *proxy);
+void vfio_user_set_handler(VFIODevice *vbasedev,
+ void (*handler)(void *opaque, VFIOUserMsg *msg),
+ void *reqarg);
#endif /* VFIO_USER_COMMON_H */
diff --git a/hw/vfio-user/pci.c b/hw/vfio-user/pci.c
index bfd9051524..fb6c872768 100644
--- a/hw/vfio-user/pci.c
+++ b/hw/vfio-user/pci.c
@@ -38,6 +38,16 @@ struct VFIOUserPCIDevice {
char *sock_name;
};
+/*
+ * Incoming request message callback.
+ *
+ * Runs off main loop, so BQL held.
+ */
+static void vfio_user_pci_process_req(void *opaque, VFIOUserMsg *msg)
+{
+
+}
+
/*
* Emulated devices don't use host hot reset
*/
@@ -83,6 +93,7 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
return;
}
vbasedev->proxy = proxy;
+ vfio_user_set_handler(vbasedev, vfio_user_pci_process_req, vdev);
vbasedev->name = g_strdup_printf("VFIO user <%s>", udev->sock_name);
vbasedev->ops = &vfio_user_pci_ops;
diff --git a/hw/vfio-user/protocol.h b/hw/vfio-user/protocol.h
new file mode 100644
index 0000000000..d23877c958
--- /dev/null
+++ b/hw/vfio-user/protocol.h
@@ -0,0 +1,54 @@
+#ifndef VFIO_USER_PROTOCOL_H
+#define VFIO_USER_PROTOCOL_H
+
+/*
+ * vfio protocol over a UNIX socket.
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ *
+ * Each message has a standard header that describes the command
+ * being sent, which is almost always a VFIO ioctl().
+ *
+ * The header may be followed by command-specific data, such as the
+ * region and offset info for read and write commands.
+ */
+
+typedef struct {
+ uint16_t id;
+ uint16_t command;
+ uint32_t size;
+ uint32_t flags;
+ uint32_t error_reply;
+} VFIOUserHdr;
+
+/* VFIOUserHdr commands */
+enum vfio_user_command {
+ VFIO_USER_VERSION = 1,
+ VFIO_USER_DMA_MAP = 2,
+ VFIO_USER_DMA_UNMAP = 3,
+ VFIO_USER_DEVICE_GET_INFO = 4,
+ VFIO_USER_DEVICE_GET_REGION_INFO = 5,
+ VFIO_USER_DEVICE_GET_REGION_IO_FDS = 6,
+ VFIO_USER_DEVICE_GET_IRQ_INFO = 7,
+ VFIO_USER_DEVICE_SET_IRQS = 8,
+ VFIO_USER_REGION_READ = 9,
+ VFIO_USER_REGION_WRITE = 10,
+ VFIO_USER_DMA_READ = 11,
+ VFIO_USER_DMA_WRITE = 12,
+ VFIO_USER_DEVICE_RESET = 13,
+ VFIO_USER_DIRTY_PAGES = 14,
+ VFIO_USER_MAX,
+};
+
+/* VFIOUserHdr flags */
+#define VFIO_USER_REQUEST 0x0
+#define VFIO_USER_REPLY 0x1
+#define VFIO_USER_TYPE 0xF
+
+#define VFIO_USER_NO_REPLY 0x10
+#define VFIO_USER_ERROR 0x20
+
+#endif /* VFIO_USER_PROTOCOL_H */
diff --git a/hw/vfio-user/trace-events b/hw/vfio-user/trace-events
new file mode 100644
index 0000000000..89d6c11c4c
--- /dev/null
+++ b/hw/vfio-user/trace-events
@@ -0,0 +1,6 @@
+# See docs/devel/tracing.rst for syntax documentation.
+
+# common.c
+vfio_user_recv_hdr(const char *name, uint16_t id, uint16_t cmd, uint32_t size, uint32_t flags) " (%s) id 0x%x cmd 0x%x size 0x%x flags 0x%x"
+vfio_user_recv_read(uint16_t id, int read) " id 0x%x read 0x%x"
+vfio_user_recv_request(uint16_t cmd) " command 0x%x"
diff --git a/hw/vfio-user/trace.h b/hw/vfio-user/trace.h
new file mode 100644
index 0000000000..574b59aa89
--- /dev/null
+++ b/hw/vfio-user/trace.h
@@ -0,0 +1 @@
+#include "trace/trace-hw_vfio_user.h"
diff --git a/meson.build b/meson.build
index 8ed10b6624..0651d0710b 100644
--- a/meson.build
+++ b/meson.build
@@ -3593,6 +3593,7 @@ if have_system
'hw/ufs',
'hw/usb',
'hw/vfio',
+ 'hw/vfio-user',
'hw/virtio',
'hw/watchdog',
'hw/xen',
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* [PATCH v8 15/28] vfio-user: implement message send infrastructure
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (13 preceding siblings ...)
2025-02-19 14:48 ` [PATCH v8 14/28] vfio-user: implement message receive infrastructure John Levon
@ 2025-02-19 14:48 ` John Levon
2025-02-19 14:48 ` [PATCH v8 16/28] vfio-user: implement VFIO_USER_DEVICE_GET_INFO John Levon
` (15 subsequent siblings)
30 siblings, 0 replies; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin, Jagannathan Raman, John Johnson,
Elena Ufimtseva
From: Jagannathan Raman <jag.raman@oracle.com>
Add plumbing for sending vfio-user messages on the control socket.
Add initial version negotation on connection.
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>
---
hw/vfio-user/common.c | 495 ++++++++++++++++++++++++++++++++++++++
hw/vfio-user/common.h | 9 +
hw/vfio-user/pci.c | 18 +-
hw/vfio-user/protocol.h | 62 +++++
hw/vfio-user/trace-events | 2 +
5 files changed, 584 insertions(+), 2 deletions(-)
diff --git a/hw/vfio-user/common.c b/hw/vfio-user/common.c
index 2c4ee14ede..634f95f2e3 100644
--- a/hw/vfio-user/common.c
+++ b/hw/vfio-user/common.c
@@ -20,15 +20,21 @@
#include "io/channel-socket.h"
#include "io/channel-util.h"
#include "qapi/error.h"
+#include "qobject/qdict.h"
+#include "qobject/qjson.h"
+#include "qobject/qstring.h"
+#include "qobject/qnum.h"
#include "qemu/error-report.h"
#include "qemu/lockable.h"
#include "qemu/main-loop.h"
#include "qemu/sockets.h"
#include "system/iothread.h"
+static int wait_time = 5000; /* wait up to 5 sec for busy servers */
static IOThread *vfio_user_iothread;
static void vfio_user_shutdown(VFIOUserProxy *proxy);
+static int vfio_user_send_qio(VFIOUserProxy *proxy, VFIOUserMsg *msg);
static VFIOUserMsg *vfio_user_getmsg(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
VFIOUserFDs *fds);
static VFIOUserFDs *vfio_user_getfds(int numfds);
@@ -36,9 +42,16 @@ static void vfio_user_recycle(VFIOUserProxy *proxy, VFIOUserMsg *msg);
static void vfio_user_recv(void *opaque);
static int vfio_user_recv_one(VFIOUserProxy *proxy);
+static void vfio_user_send(void *opaque);
+static int vfio_user_send_one(VFIOUserProxy *proxy);
static void vfio_user_cb(void *opaque);
static void vfio_user_request(void *opaque);
+static int vfio_user_send_queued(VFIOUserProxy *proxy, VFIOUserMsg *msg);
+static void vfio_user_send_wait(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
+ VFIOUserFDs *fds, int rsize);
+static void vfio_user_request_msg(VFIOUserHdr *hdr, uint16_t cmd,
+ uint32_t size, uint32_t flags);
static inline void vfio_user_set_error(VFIOUserHdr *hdr, uint32_t err)
{
@@ -57,6 +70,35 @@ static void vfio_user_shutdown(VFIOUserProxy *proxy)
proxy->ctx, NULL, NULL);
}
+static int vfio_user_send_qio(VFIOUserProxy *proxy, VFIOUserMsg *msg)
+{
+ VFIOUserFDs *fds = msg->fds;
+ struct iovec iov = {
+ .iov_base = msg->hdr,
+ .iov_len = msg->hdr->size,
+ };
+ size_t numfds = 0;
+ int ret, *fdp = NULL;
+ Error *local_err = NULL;
+
+ if (fds != NULL && fds->send_fds != 0) {
+ numfds = fds->send_fds;
+ fdp = fds->fds;
+ }
+
+ ret = qio_channel_writev_full(proxy->ioc, &iov, 1, fdp, numfds, 0,
+ &local_err);
+
+ if (ret == -1) {
+ vfio_user_set_error(msg->hdr, EIO);
+ vfio_user_shutdown(proxy);
+ error_report_err(local_err);
+ }
+ trace_vfio_user_send_write(msg->hdr->id, ret);
+
+ return ret;
+}
+
static VFIOUserMsg *vfio_user_getmsg(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
VFIOUserFDs *fds)
{
@@ -97,6 +139,7 @@ static void vfio_user_recycle(VFIOUserProxy *proxy, VFIOUserMsg *msg)
msg->hdr = NULL;
msg->fds = NULL;
msg->complete = false;
+ msg->pending = false;
QTAILQ_INSERT_HEAD(&proxy->free, msg, next);
}
@@ -391,6 +434,54 @@ err:
return -1;
}
+/*
+ * Send messages from outgoing queue when the socket buffer has space.
+ * If we deplete 'outgoing', remove ourselves from the poll list.
+ */
+static void vfio_user_send(void *opaque)
+{
+ VFIOUserProxy *proxy = opaque;
+
+ QEMU_LOCK_GUARD(&proxy->lock);
+
+ if (proxy->state == VFIO_PROXY_CONNECTED) {
+ while (!QTAILQ_EMPTY(&proxy->outgoing)) {
+ if (vfio_user_send_one(proxy) < 0) {
+ return;
+ }
+ }
+ qio_channel_set_aio_fd_handler(proxy->ioc, proxy->ctx,
+ vfio_user_recv, NULL, NULL, proxy);
+ }
+}
+
+/*
+ * Send a single message.
+ *
+ * Sent async messages are freed, others are moved to pending queue.
+ */
+static int vfio_user_send_one(VFIOUserProxy *proxy)
+{
+ VFIOUserMsg *msg;
+ int ret;
+
+ msg = QTAILQ_FIRST(&proxy->outgoing);
+ ret = vfio_user_send_qio(proxy, msg);
+ if (ret < 0) {
+ return ret;
+ }
+
+ QTAILQ_REMOVE(&proxy->outgoing, msg, next);
+ if (msg->type == VFIO_MSG_ASYNC) {
+ vfio_user_recycle(proxy, msg);
+ } else {
+ QTAILQ_INSERT_TAIL(&proxy->pending, msg, next);
+ msg->pending = true;
+ }
+
+ return 0;
+}
+
static void vfio_user_cb(void *opaque)
{
VFIOUserProxy *proxy = opaque;
@@ -452,6 +543,119 @@ static void vfio_user_request(void *opaque)
}
}
+/*
+ * Messages are queued onto the proxy's outgoing list.
+ *
+ * It handles 3 types of messages:
+ *
+ * async messages - replies and posted writes
+ *
+ * There will be no reply from the server, so message
+ * buffers are freed after they're sent.
+ *
+ * nowait messages - map/unmap during address space transactions
+ *
+ * These are also sent async, but a reply is expected so that
+ * vfio_wait_reqs() can wait for the youngest nowait request.
+ * They transition from the outgoing list to the pending list
+ * when sent, and are freed when the reply is received.
+ *
+ * wait messages - all other requests
+ *
+ * The reply to these messages is waited for by their caller.
+ * They also transition from outgoing to pending when sent, but
+ * the message buffer is returned to the caller with the reply
+ * contents. The caller is responsible for freeing these messages.
+ *
+ * As an optimization, if the outgoing list and the socket send
+ * buffer are empty, the message is sent inline instead of being
+ * added to the outgoing list. The rest of the transitions are
+ * unchanged.
+ *
+ * returns 0 if the message was sent or queued
+ * returns -1 on send error
+ */
+static int vfio_user_send_queued(VFIOUserProxy *proxy, VFIOUserMsg *msg)
+{
+ int ret;
+
+ /*
+ * Unsent outgoing msgs - add to tail
+ */
+ if (!QTAILQ_EMPTY(&proxy->outgoing)) {
+ QTAILQ_INSERT_TAIL(&proxy->outgoing, msg, next);
+ return 0;
+ }
+
+ /*
+ * Try inline - if blocked, queue it and kick send poller
+ */
+ if (proxy->flags & VFIO_PROXY_FORCE_QUEUED) {
+ ret = QIO_CHANNEL_ERR_BLOCK;
+ } else {
+ ret = vfio_user_send_qio(proxy, msg);
+ }
+ if (ret == QIO_CHANNEL_ERR_BLOCK) {
+ QTAILQ_INSERT_HEAD(&proxy->outgoing, msg, next);
+ qio_channel_set_aio_fd_handler(proxy->ioc, proxy->ctx,
+ vfio_user_recv, proxy->ctx,
+ vfio_user_send, proxy);
+ return 0;
+ }
+ if (ret == -1) {
+ return ret;
+ }
+
+ /*
+ * Sent - free async, add others to pending
+ */
+ if (msg->type == VFIO_MSG_ASYNC) {
+ vfio_user_recycle(proxy, msg);
+ } else {
+ QTAILQ_INSERT_TAIL(&proxy->pending, msg, next);
+ msg->pending = true;
+ }
+
+ return 0;
+}
+
+static void vfio_user_send_wait(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
+ VFIOUserFDs *fds, int rsize)
+{
+ VFIOUserMsg *msg;
+ int ret;
+
+ if (hdr->flags & VFIO_USER_NO_REPLY) {
+ error_printf("vfio_user_send_wait on async message\n");
+ vfio_user_set_error(hdr, EINVAL);
+ return;
+ }
+
+ qemu_mutex_lock(&proxy->lock);
+
+ msg = vfio_user_getmsg(proxy, hdr, fds);
+ msg->id = hdr->id;
+ msg->rsize = rsize ? rsize : hdr->size;
+ msg->type = VFIO_MSG_WAIT;
+
+ ret = vfio_user_send_queued(proxy, msg);
+
+ if (ret == 0) {
+ while (!msg->complete) {
+ if (!qemu_cond_timedwait(&msg->cv, &proxy->lock, wait_time)) {
+ VFIOUserMsgQ *list;
+
+ list = msg->pending ? &proxy->pending : &proxy->outgoing;
+ QTAILQ_REMOVE(list, msg, next);
+ vfio_user_set_error(hdr, ETIMEDOUT);
+ break;
+ }
+ }
+ }
+ vfio_user_recycle(proxy, msg);
+
+ qemu_mutex_unlock(&proxy->lock);
+}
static QLIST_HEAD(, VFIOUserProxy) vfio_user_sockets =
QLIST_HEAD_INITIALIZER(vfio_user_sockets);
@@ -480,6 +684,15 @@ VFIOUserProxy *vfio_user_connect_dev(SocketAddress *addr, Error **errp)
proxy = g_malloc0(sizeof(VFIOUserProxy));
proxy->sockname = g_strdup_printf("unix:%s", sockname);
proxy->ioc = ioc;
+
+ /* init defaults */
+ proxy->max_xfer_size = VFIO_USER_DEF_MAX_XFER;
+ proxy->max_send_fds = VFIO_USER_DEF_MAX_FDS;
+ proxy->max_dma = VFIO_USER_DEF_MAP_MAX;
+ proxy->dma_pgsizes = VFIO_USER_DEF_PGSIZE;
+ proxy->max_bitmap = VFIO_USER_DEF_MAX_BITMAP;
+ proxy->migr_pgsize = VFIO_USER_DEF_PGSIZE;
+
proxy->flags = VFIO_PROXY_CLIENT;
proxy->state = VFIO_PROXY_CONNECTED;
@@ -577,3 +790,285 @@ void vfio_user_disconnect(VFIOUserProxy *proxy)
g_free(proxy->sockname);
g_free(proxy);
}
+
+static void vfio_user_request_msg(VFIOUserHdr *hdr, uint16_t cmd,
+ uint32_t size, uint32_t flags)
+{
+ static uint16_t next_id;
+
+ hdr->id = qatomic_fetch_inc(&next_id);
+ hdr->command = cmd;
+ hdr->size = size;
+ hdr->flags = (flags & ~VFIO_USER_TYPE) | VFIO_USER_REQUEST;
+ hdr->error_reply = 0;
+}
+
+struct cap_entry {
+ const char *name;
+ bool (*check)(VFIOUserProxy *proxy, QObject *qobj, Error **errp);
+};
+
+static bool caps_parse(VFIOUserProxy *proxy, QDict *qdict,
+ struct cap_entry caps[], Error **errp)
+{
+ QObject *qobj;
+ struct cap_entry *p;
+
+ for (p = caps; p->name != NULL; p++) {
+ qobj = qdict_get(qdict, p->name);
+ if (qobj != NULL) {
+ if (!p->check(proxy, qobj, errp)) {
+ return false;
+ }
+ qdict_del(qdict, p->name);
+ }
+ }
+
+ /* warning, for now */
+ if (qdict_size(qdict) != 0) {
+ warn_report("spurious capabilities");
+ }
+ return true;
+}
+
+static bool check_migr_pgsize(VFIOUserProxy *proxy, QObject *qobj, Error **errp)
+{
+ QNum *qn = qobject_to(QNum, qobj);
+ uint64_t pgsize;
+
+ if (qn == NULL || !qnum_get_try_uint(qn, &pgsize)) {
+ error_setg(errp, "malformed %s", VFIO_USER_CAP_PGSIZE);
+ return false;
+ }
+
+ /* must be larger than default */
+ if (pgsize & (VFIO_USER_DEF_PGSIZE - 1)) {
+ error_setg(errp, "pgsize 0x%"PRIx64" too small", pgsize);
+ return false;
+ }
+
+ proxy->migr_pgsize = pgsize;
+ return true;
+}
+
+static bool check_bitmap(VFIOUserProxy *proxy, QObject *qobj, Error **errp)
+{
+ QNum *qn = qobject_to(QNum, qobj);
+ uint64_t bitmap_size;
+
+ if (qn == NULL || !qnum_get_try_uint(qn, &bitmap_size)) {
+ error_setg(errp, "malformed %s", VFIO_USER_CAP_MAX_BITMAP);
+ return false;
+ }
+
+ /* can only lower it */
+ if (bitmap_size > VFIO_USER_DEF_MAX_BITMAP) {
+ error_setg(errp, "%s too large", VFIO_USER_CAP_MAX_BITMAP);
+ return false;
+ }
+
+ proxy->max_bitmap = bitmap_size;
+ return true;
+}
+
+static struct cap_entry caps_migr[] = {
+ { VFIO_USER_CAP_PGSIZE, check_migr_pgsize },
+ { VFIO_USER_CAP_MAX_BITMAP, check_bitmap },
+ { NULL }
+};
+
+static bool check_max_fds(VFIOUserProxy *proxy, QObject *qobj, Error **errp)
+{
+ QNum *qn = qobject_to(QNum, qobj);
+ uint64_t max_send_fds;
+
+ if (qn == NULL || !qnum_get_try_uint(qn, &max_send_fds) ||
+ max_send_fds > VFIO_USER_MAX_MAX_FDS) {
+ error_setg(errp, "malformed %s", VFIO_USER_CAP_MAX_FDS);
+ return false;
+ }
+ proxy->max_send_fds = max_send_fds;
+ return true;
+}
+
+static bool check_max_xfer(VFIOUserProxy *proxy, QObject *qobj, Error **errp)
+{
+ QNum *qn = qobject_to(QNum, qobj);
+ uint64_t max_xfer_size;
+
+ if (qn == NULL || !qnum_get_try_uint(qn, &max_xfer_size) ||
+ max_xfer_size > VFIO_USER_MAX_MAX_XFER) {
+ error_setg(errp, "malformed %s", VFIO_USER_CAP_MAX_XFER);
+ return false;
+ }
+ proxy->max_xfer_size = max_xfer_size;
+ return true;
+}
+
+static bool check_pgsizes(VFIOUserProxy *proxy, QObject *qobj, Error **errp)
+{
+ QNum *qn = qobject_to(QNum, qobj);
+ uint64_t pgsizes;
+
+ if (qn == NULL || !qnum_get_try_uint(qn, &pgsizes)) {
+ error_setg(errp, "malformed %s", VFIO_USER_CAP_PGSIZES);
+ return false;
+ }
+
+ /* must be larger than default */
+ if (pgsizes & (VFIO_USER_DEF_PGSIZE - 1)) {
+ error_setg(errp, "pgsize 0x%"PRIx64" too small", pgsizes);
+ return false;
+ }
+
+ proxy->dma_pgsizes = pgsizes;
+ return true;
+}
+
+static bool check_max_dma(VFIOUserProxy *proxy, QObject *qobj, Error **errp)
+{
+ QNum *qn = qobject_to(QNum, qobj);
+ uint64_t max_dma;
+
+ if (qn == NULL || !qnum_get_try_uint(qn, &max_dma)) {
+ error_setg(errp, "malformed %s", VFIO_USER_CAP_MAP_MAX);
+ return false;
+ }
+
+ /* can only lower it */
+ if (max_dma > VFIO_USER_DEF_MAP_MAX) {
+ error_setg(errp, "%s too large", VFIO_USER_CAP_MAP_MAX);
+ return false;
+ }
+
+ proxy->max_dma = max_dma;
+ return true;
+}
+
+static bool check_migr(VFIOUserProxy *proxy, QObject *qobj, Error **errp)
+{
+ QDict *qdict = qobject_to(QDict, qobj);
+
+ if (qdict == NULL) {
+ error_setg(errp, "malformed %s", VFIO_USER_CAP_MAX_FDS);
+ return true;
+ }
+ return caps_parse(proxy, qdict, caps_migr, errp);
+}
+
+static struct cap_entry caps_cap[] = {
+ { VFIO_USER_CAP_MAX_FDS, check_max_fds },
+ { VFIO_USER_CAP_MAX_XFER, check_max_xfer },
+ { VFIO_USER_CAP_PGSIZES, check_pgsizes },
+ { VFIO_USER_CAP_MAP_MAX, check_max_dma },
+ { VFIO_USER_CAP_MIGR, check_migr },
+ { NULL }
+};
+
+static bool check_cap(VFIOUserProxy *proxy, QObject *qobj, Error **errp)
+{
+ QDict *qdict = qobject_to(QDict, qobj);
+
+ if (qdict == NULL) {
+ error_setg(errp, "malformed %s", VFIO_USER_CAP);
+ return false;
+ }
+ return caps_parse(proxy, qdict, caps_cap, errp);
+}
+
+static struct cap_entry ver_0_0[] = {
+ { VFIO_USER_CAP, check_cap },
+ { NULL }
+};
+
+static bool caps_check(VFIOUserProxy *proxy, int minor, const char *caps,
+ Error **errp)
+{
+ QObject *qobj;
+ QDict *qdict;
+ bool ret;
+
+ qobj = qobject_from_json(caps, NULL);
+ if (qobj == NULL) {
+ error_setg(errp, "malformed capabilities %s", caps);
+ return false;
+ }
+ qdict = qobject_to(QDict, qobj);
+ if (qdict == NULL) {
+ error_setg(errp, "capabilities %s not an object", caps);
+ qobject_unref(qobj);
+ return false;
+ }
+ ret = caps_parse(proxy, qdict, ver_0_0, errp);
+
+ qobject_unref(qobj);
+ return ret;
+}
+
+static GString *caps_json(void)
+{
+ QDict *dict = qdict_new();
+ QDict *capdict = qdict_new();
+ QDict *migdict = qdict_new();
+ GString *str;
+
+ qdict_put_int(migdict, VFIO_USER_CAP_PGSIZE, VFIO_USER_DEF_PGSIZE);
+ qdict_put_int(migdict, VFIO_USER_CAP_MAX_BITMAP, VFIO_USER_DEF_MAX_BITMAP);
+ qdict_put_obj(capdict, VFIO_USER_CAP_MIGR, QOBJECT(migdict));
+
+ qdict_put_int(capdict, VFIO_USER_CAP_MAX_FDS, VFIO_USER_MAX_MAX_FDS);
+ qdict_put_int(capdict, VFIO_USER_CAP_MAX_XFER, VFIO_USER_DEF_MAX_XFER);
+ qdict_put_int(capdict, VFIO_USER_CAP_PGSIZES, VFIO_USER_DEF_PGSIZE);
+ qdict_put_int(capdict, VFIO_USER_CAP_MAP_MAX, VFIO_USER_DEF_MAP_MAX);
+
+ qdict_put_obj(dict, VFIO_USER_CAP, QOBJECT(capdict));
+
+ str = qobject_to_json(QOBJECT(dict));
+ qobject_unref(dict);
+ return str;
+}
+
+bool vfio_user_validate_version(VFIOUserProxy *proxy, Error **errp)
+{
+ g_autofree VFIOUserVersion *msgp = NULL;
+ GString *caps;
+ char *reply;
+ int size, caplen;
+
+ caps = caps_json();
+ caplen = caps->len + 1;
+ size = sizeof(*msgp) + caplen;
+ msgp = g_malloc0(size);
+
+ vfio_user_request_msg(&msgp->hdr, VFIO_USER_VERSION, size, 0);
+ msgp->major = VFIO_USER_MAJOR_VER;
+ msgp->minor = VFIO_USER_MINOR_VER;
+ memcpy(&msgp->capabilities, caps->str, caplen);
+ g_string_free(caps, true);
+ trace_vfio_user_version(msgp->major, msgp->minor, msgp->capabilities);
+
+ vfio_user_send_wait(proxy, &msgp->hdr, NULL, 0);
+ if (msgp->hdr.flags & VFIO_USER_ERROR) {
+ error_setg_errno(errp, msgp->hdr.error_reply, "version reply");
+ return false;
+ }
+
+ if (msgp->major != VFIO_USER_MAJOR_VER ||
+ msgp->minor > VFIO_USER_MINOR_VER) {
+ error_setg(errp, "incompatible server version");
+ return false;
+ }
+
+ reply = msgp->capabilities;
+ if (reply[msgp->hdr.size - sizeof(*msgp) - 1] != '\0') {
+ error_setg(errp, "corrupt version reply");
+ return false;
+ }
+
+ if (!caps_check(proxy, msgp->minor, reply, errp)) {
+ return false;
+ }
+
+ trace_vfio_user_version(msgp->major, msgp->minor, msgp->capabilities);
+ return true;
+}
diff --git a/hw/vfio-user/common.h b/hw/vfio-user/common.h
index 71c0dea82d..9f4243a67d 100644
--- a/hw/vfio-user/common.h
+++ b/hw/vfio-user/common.h
@@ -35,6 +35,7 @@ typedef struct VFIOUserMsg {
uint32_t id;
QemuCond cv;
bool complete;
+ bool pending;
enum msg_type type;
} VFIOUserMsg;
@@ -54,6 +55,12 @@ typedef struct VFIOUserProxy {
struct QIOChannel *ioc;
void (*request)(void *opaque, VFIOUserMsg *msg);
void *req_arg;
+ uint64_t max_xfer_size;
+ uint64_t max_send_fds;
+ uint64_t max_dma;
+ uint64_t dma_pgsizes;
+ uint64_t max_bitmap;
+ uint64_t migr_pgsize;
int flags;
QemuCond close_cv;
AioContext *ctx;
@@ -76,6 +83,7 @@ typedef struct VFIOUserProxy {
/* VFIOProxy flags */
#define VFIO_PROXY_CLIENT 0x1
+#define VFIO_PROXY_FORCE_QUEUED 0x4
typedef struct VFIODevice VFIODevice;
@@ -84,5 +92,6 @@ void vfio_user_disconnect(VFIOUserProxy *proxy);
void vfio_user_set_handler(VFIODevice *vbasedev,
void (*handler)(void *opaque, VFIOUserMsg *msg),
void *reqarg);
+bool vfio_user_validate_version(VFIOUserProxy *proxy, Error **errp);
#endif /* VFIO_USER_COMMON_H */
diff --git a/hw/vfio-user/pci.c b/hw/vfio-user/pci.c
index fb6c872768..69806eb863 100644
--- a/hw/vfio-user/pci.c
+++ b/hw/vfio-user/pci.c
@@ -36,6 +36,7 @@ OBJECT_DECLARE_SIMPLE_TYPE(VFIOUserPCIDevice, VFIO_USER_PCI)
struct VFIOUserPCIDevice {
VFIOPCIDevice device;
char *sock_name;
+ bool send_queued; /* all sends are queued */
};
/*
@@ -95,6 +96,14 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
vbasedev->proxy = proxy;
vfio_user_set_handler(vbasedev, vfio_user_pci_process_req, vdev);
+ if (udev->send_queued) {
+ proxy->flags |= VFIO_PROXY_FORCE_QUEUED;
+ }
+
+ if (!vfio_user_validate_version(proxy, errp)) {
+ goto error;
+ }
+
vbasedev->name = g_strdup_printf("VFIO user <%s>", udev->sock_name);
vbasedev->ops = &vfio_user_pci_ops;
vbasedev->type = VFIO_DEVICE_TYPE_PCI;
@@ -109,9 +118,13 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
if (!vfio_attach_device_by_iommu_type(TYPE_VFIO_IOMMU_USER,
vbasedev->name, vbasedev,
as, errp)) {
- error_prepend(errp, VFIO_MSG_PREFIX, vbasedev->name);
- return;
+ goto error;
}
+
+ return;
+
+error:
+ error_prepend(errp, VFIO_MSG_PREFIX, vdev->vbasedev.name);
}
static void vfio_user_instance_init(Object *obj)
@@ -154,6 +167,7 @@ static void vfio_user_instance_finalize(Object *obj)
static const Property vfio_user_pci_dev_properties[] = {
DEFINE_PROP_STRING("socket", VFIOUserPCIDevice, sock_name),
+ DEFINE_PROP_BOOL("x-send-queued", VFIOUserPCIDevice, send_queued, false),
};
static void vfio_user_pci_dev_class_init(ObjectClass *klass, void *data)
diff --git a/hw/vfio-user/protocol.h b/hw/vfio-user/protocol.h
index d23877c958..5de5b2030c 100644
--- a/hw/vfio-user/protocol.h
+++ b/hw/vfio-user/protocol.h
@@ -51,4 +51,66 @@ enum vfio_user_command {
#define VFIO_USER_NO_REPLY 0x10
#define VFIO_USER_ERROR 0x20
+
+/*
+ * VFIO_USER_VERSION
+ */
+typedef struct {
+ VFIOUserHdr hdr;
+ uint16_t major;
+ uint16_t minor;
+ char capabilities[];
+} VFIOUserVersion;
+
+#define VFIO_USER_MAJOR_VER 0
+#define VFIO_USER_MINOR_VER 0
+
+#define VFIO_USER_CAP "capabilities"
+
+/* "capabilities" members */
+#define VFIO_USER_CAP_MAX_FDS "max_msg_fds"
+#define VFIO_USER_CAP_MAX_XFER "max_data_xfer_size"
+#define VFIO_USER_CAP_PGSIZES "pgsizes"
+#define VFIO_USER_CAP_MAP_MAX "max_dma_maps"
+#define VFIO_USER_CAP_MIGR "migration"
+
+/* "migration" members */
+#define VFIO_USER_CAP_PGSIZE "pgsize"
+#define VFIO_USER_CAP_MAX_BITMAP "max_bitmap_size"
+
+/*
+ * Max FDs mainly comes into play when a device supports multiple interrupts
+ * where each ones uses an eventfd to inject it into the guest.
+ * It is clamped by the the number of FDs the qio channel supports in a
+ * single message.
+ */
+#define VFIO_USER_DEF_MAX_FDS 8
+#define VFIO_USER_MAX_MAX_FDS 16
+
+/*
+ * Max transfer limits the amount of data in region and DMA messages.
+ * Region R/W will be very small (limited by how much a single instruction
+ * can process) so just use a reasonable limit here.
+ */
+#define VFIO_USER_DEF_MAX_XFER (1024 * 1024)
+#define VFIO_USER_MAX_MAX_XFER (64 * 1024 * 1024)
+
+/*
+ * Default pagesizes supported is 4k.
+ */
+#define VFIO_USER_DEF_PGSIZE 4096
+
+/*
+ * Default max number of DMA mappings is stolen from the
+ * linux kernel "dma_entry_limit"
+ */
+#define VFIO_USER_DEF_MAP_MAX 65535
+
+/*
+ * Default max bitmap size is also take from the linux kernel,
+ * where usage of signed ints limits the VA range to 2^31 bytes.
+ * Dividing that by the number of bits per byte yields 256MB
+ */
+#define VFIO_USER_DEF_MAX_BITMAP (256 * 1024 * 1024)
+
#endif /* VFIO_USER_PROTOCOL_H */
diff --git a/hw/vfio-user/trace-events b/hw/vfio-user/trace-events
index 89d6c11c4c..7a3645024f 100644
--- a/hw/vfio-user/trace-events
+++ b/hw/vfio-user/trace-events
@@ -4,3 +4,5 @@
vfio_user_recv_hdr(const char *name, uint16_t id, uint16_t cmd, uint32_t size, uint32_t flags) " (%s) id 0x%x cmd 0x%x size 0x%x flags 0x%x"
vfio_user_recv_read(uint16_t id, int read) " id 0x%x read 0x%x"
vfio_user_recv_request(uint16_t cmd) " command 0x%x"
+vfio_user_send_write(uint16_t id, int wrote) " id 0x%x wrote 0x%x"
+vfio_user_version(uint16_t major, uint16_t minor, const char *caps) " major %d minor %d caps: %s"
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* [PATCH v8 16/28] vfio-user: implement VFIO_USER_DEVICE_GET_INFO
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (14 preceding siblings ...)
2025-02-19 14:48 ` [PATCH v8 15/28] vfio-user: implement message send infrastructure John Levon
@ 2025-02-19 14:48 ` John Levon
2025-02-19 14:48 ` [PATCH v8 17/28] vfio-user: implement VFIO_USER_DEVICE_GET_REGION_INFO John Levon
` (14 subsequent siblings)
30 siblings, 0 replies; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin, Jagannathan Raman, John Johnson,
Elena Ufimtseva
From: Jagannathan Raman <jag.raman@oracle.com>
Add support for getting basic device information.
Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
---
hw/vfio-user/common.c | 34 ++++++++++++++++++++++++++++++++++
hw/vfio-user/common.h | 1 +
hw/vfio-user/container.c | 10 +++++++++-
hw/vfio-user/protocol.h | 12 ++++++++++++
hw/vfio-user/trace-events | 1 +
5 files changed, 57 insertions(+), 1 deletion(-)
diff --git a/hw/vfio-user/common.c b/hw/vfio-user/common.c
index 634f95f2e3..55d1da4e51 100644
--- a/hw/vfio-user/common.c
+++ b/hw/vfio-user/common.c
@@ -30,6 +30,13 @@
#include "qemu/sockets.h"
#include "system/iothread.h"
+/*
+ * These are to defend against a malign server trying
+ * to force us to run out of memory.
+ */
+#define VFIO_USER_MAX_REGIONS 100
+#define VFIO_USER_MAX_IRQS 50
+
static int wait_time = 5000; /* wait up to 5 sec for busy servers */
static IOThread *vfio_user_iothread;
@@ -1072,3 +1079,30 @@ bool vfio_user_validate_version(VFIOUserProxy *proxy, Error **errp)
trace_vfio_user_version(msgp->major, msgp->minor, msgp->capabilities);
return true;
}
+
+int vfio_user_get_info(VFIOUserProxy *proxy, struct vfio_device_info *info)
+{
+ VFIOUserDeviceInfo msg;
+ uint32_t argsz = sizeof(msg) - sizeof(msg.hdr);
+
+ memset(&msg, 0, sizeof(msg));
+ vfio_user_request_msg(&msg.hdr, VFIO_USER_DEVICE_GET_INFO, sizeof(msg), 0);
+ msg.argsz = argsz;
+
+ vfio_user_send_wait(proxy, &msg.hdr, NULL, 0);
+ if (msg.hdr.flags & VFIO_USER_ERROR) {
+ return -msg.hdr.error_reply;
+ }
+ trace_vfio_user_get_info(msg.num_regions, msg.num_irqs);
+
+ memcpy(info, &msg.argsz, argsz);
+
+ /* defend against a malicious server */
+ if (info->num_regions > VFIO_USER_MAX_REGIONS ||
+ info->num_irqs > VFIO_USER_MAX_IRQS) {
+ error_printf("%s: invalid reply\n", __func__);
+ return -EINVAL;
+ }
+
+ return 0;
+}
diff --git a/hw/vfio-user/common.h b/hw/vfio-user/common.h
index 9f4243a67d..11a80d4e7c 100644
--- a/hw/vfio-user/common.h
+++ b/hw/vfio-user/common.h
@@ -93,5 +93,6 @@ void vfio_user_set_handler(VFIODevice *vbasedev,
void (*handler)(void *opaque, VFIOUserMsg *msg),
void *reqarg);
bool vfio_user_validate_version(VFIOUserProxy *proxy, Error **errp);
+int vfio_user_get_info(VFIOUserProxy *proxy, struct vfio_device_info *info);
#endif /* VFIO_USER_COMMON_H */
diff --git a/hw/vfio-user/container.c b/hw/vfio-user/container.c
index 7b1c202517..c079d6f89b 100644
--- a/hw/vfio-user/container.c
+++ b/hw/vfio-user/container.c
@@ -16,6 +16,7 @@
#include "exec/ram_addr.h"
#include "hw/hw.h"
#include "hw/vfio/pci.h"
+#include "hw/vfio-user/common.h"
#include "hw/vfio-user/container.h"
#include "qemu/error-report.h"
#include "qemu/range.h"
@@ -152,7 +153,14 @@ static void vfio_disconnect_user_container(VFIOUserContainer *container)
static bool vfio_user_get_device(VFIOUserContainer *container,
VFIODevice *vbasedev, Error **errp)
{
- struct vfio_device_info info = { 0 };
+ struct vfio_device_info info = { .argsz = sizeof(info) };
+ int ret;
+
+ ret = vfio_user_get_info(vbasedev->proxy, &info);
+ if (ret) {
+ error_setg_errno(errp, -ret, "get info failure");
+ return ret;
+ }
vbasedev->fd = -1;
diff --git a/hw/vfio-user/protocol.h b/hw/vfio-user/protocol.h
index 5de5b2030c..5f9ef1768f 100644
--- a/hw/vfio-user/protocol.h
+++ b/hw/vfio-user/protocol.h
@@ -113,4 +113,16 @@ typedef struct {
*/
#define VFIO_USER_DEF_MAX_BITMAP (256 * 1024 * 1024)
+/*
+ * VFIO_USER_DEVICE_GET_INFO
+ * imported from struct vfio_device_info
+ */
+typedef struct {
+ VFIOUserHdr hdr;
+ uint32_t argsz;
+ uint32_t flags;
+ uint32_t num_regions;
+ uint32_t num_irqs;
+} VFIOUserDeviceInfo;
+
#endif /* VFIO_USER_PROTOCOL_H */
diff --git a/hw/vfio-user/trace-events b/hw/vfio-user/trace-events
index 7a3645024f..6b06a3ed82 100644
--- a/hw/vfio-user/trace-events
+++ b/hw/vfio-user/trace-events
@@ -6,3 +6,4 @@ vfio_user_recv_read(uint16_t id, int read) " id 0x%x read 0x%x"
vfio_user_recv_request(uint16_t cmd) " command 0x%x"
vfio_user_send_write(uint16_t id, int wrote) " id 0x%x wrote 0x%x"
vfio_user_version(uint16_t major, uint16_t minor, const char *caps) " major %d minor %d caps: %s"
+vfio_user_get_info(uint32_t nregions, uint32_t nirqs) " #regions %d #irqs %d"
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* [PATCH v8 17/28] vfio-user: implement VFIO_USER_DEVICE_GET_REGION_INFO
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (15 preceding siblings ...)
2025-02-19 14:48 ` [PATCH v8 16/28] vfio-user: implement VFIO_USER_DEVICE_GET_INFO John Levon
@ 2025-02-19 14:48 ` John Levon
2025-02-19 14:48 ` [PATCH v8 18/28] vfio-user: implement VFIO_USER_REGION_READ/WRITE John Levon
` (13 subsequent siblings)
30 siblings, 0 replies; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin, Jagannathan Raman, John Johnson,
Elena Ufimtseva
From: Jagannathan Raman <jag.raman@oracle.com>
Add support for per-region info fds. Unlike kernel vfio, vfio-user can
have a separate fd to support mmap() of individual regions; add
->use_regfds as needed to support this difference.
Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
---
hw/vfio-user/common.c | 68 +++++++++++++++++++++++++++++++++++
hw/vfio-user/common.h | 2 ++
hw/vfio-user/pci.c | 2 ++
hw/vfio-user/protocol.h | 14 ++++++++
hw/vfio-user/trace-events | 1 +
hw/vfio/ap.c | 2 ++
hw/vfio/ccw.c | 2 ++
hw/vfio/container.c | 7 ++++
hw/vfio/helpers.c | 28 +++++++++++++--
hw/vfio/pci.c | 2 ++
hw/vfio/platform.c | 2 ++
include/hw/vfio/vfio-common.h | 5 ++-
12 files changed, 131 insertions(+), 4 deletions(-)
diff --git a/hw/vfio-user/common.c b/hw/vfio-user/common.c
index 55d1da4e51..7b96d715cb 100644
--- a/hw/vfio-user/common.c
+++ b/hw/vfio-user/common.c
@@ -1106,3 +1106,71 @@ int vfio_user_get_info(VFIOUserProxy *proxy, struct vfio_device_info *info)
return 0;
}
+
+static int vfio_user_get_region_info(VFIOUserProxy *proxy,
+ struct vfio_region_info *info,
+ VFIOUserFDs *fds)
+{
+ g_autofree VFIOUserRegionInfo *msgp = NULL;
+ uint32_t size;
+
+ /* data returned can be larger than vfio_region_info */
+ if (info->argsz < sizeof(*info)) {
+ error_printf("vfio_user_get_region_info argsz too small\n");
+ return -E2BIG;
+ }
+ if (fds != NULL && fds->send_fds != 0) {
+ error_printf("vfio_user_get_region_info can't send FDs\n");
+ return -EINVAL;
+ }
+
+ size = info->argsz + sizeof(VFIOUserHdr);
+ msgp = g_malloc0(size);
+
+ vfio_user_request_msg(&msgp->hdr, VFIO_USER_DEVICE_GET_REGION_INFO,
+ sizeof(*msgp), 0);
+ msgp->argsz = info->argsz;
+ msgp->index = info->index;
+
+ vfio_user_send_wait(proxy, &msgp->hdr, fds, size);
+ if (msgp->hdr.flags & VFIO_USER_ERROR) {
+ return -msgp->hdr.error_reply;
+ }
+ trace_vfio_user_get_region_info(msgp->index, msgp->flags, msgp->size);
+
+ memcpy(info, &msgp->argsz, info->argsz);
+ return 0;
+}
+
+
+/*
+ * Socket-based io_ops
+ */
+
+static int vfio_user_io_get_region_info(VFIODevice *vbasedev,
+ struct vfio_region_info *info,
+ int *fd)
+{
+ int ret;
+ VFIOUserFDs fds = { 0, 1, fd};
+
+ ret = vfio_user_get_region_info(vbasedev->proxy, info, &fds);
+ if (ret) {
+ return ret;
+ }
+
+ if (info->index > vbasedev->num_regions) {
+ return -EINVAL;
+ }
+ /* cap_offset in valid area */
+ if ((info->flags & VFIO_REGION_INFO_FLAG_CAPS) &&
+ (info->cap_offset < sizeof(*info) || info->cap_offset > info->argsz)) {
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+VFIODeviceIO vfio_dev_io_sock = {
+ .get_region_info = vfio_user_io_get_region_info,
+};
diff --git a/hw/vfio-user/common.h b/hw/vfio-user/common.h
index 11a80d4e7c..30a3125ea3 100644
--- a/hw/vfio-user/common.h
+++ b/hw/vfio-user/common.h
@@ -95,4 +95,6 @@ void vfio_user_set_handler(VFIODevice *vbasedev,
bool vfio_user_validate_version(VFIOUserProxy *proxy, Error **errp);
int vfio_user_get_info(VFIOUserProxy *proxy, struct vfio_device_info *info);
+extern VFIODeviceIO vfio_dev_io_sock;
+
#endif /* VFIO_USER_COMMON_H */
diff --git a/hw/vfio-user/pci.c b/hw/vfio-user/pci.c
index 69806eb863..fdff6c99e6 100644
--- a/hw/vfio-user/pci.c
+++ b/hw/vfio-user/pci.c
@@ -108,6 +108,8 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
vbasedev->ops = &vfio_user_pci_ops;
vbasedev->type = VFIO_DEVICE_TYPE_PCI;
vbasedev->dev = DEVICE(vdev);
+ vbasedev->io = &vfio_dev_io_sock;
+ vbasedev->use_regfds = true;
/*
* vfio-user devices are effectively mdevs (don't use a host iommu).
diff --git a/hw/vfio-user/protocol.h b/hw/vfio-user/protocol.h
index 5f9ef1768f..6f70a48905 100644
--- a/hw/vfio-user/protocol.h
+++ b/hw/vfio-user/protocol.h
@@ -125,4 +125,18 @@ typedef struct {
uint32_t num_irqs;
} VFIOUserDeviceInfo;
+/*
+ * VFIO_USER_DEVICE_GET_REGION_INFO
+ * imported from struct vfio_region_info
+ */
+typedef struct {
+ VFIOUserHdr hdr;
+ uint32_t argsz;
+ uint32_t flags;
+ uint32_t index;
+ uint32_t cap_offset;
+ uint64_t size;
+ uint64_t offset;
+} VFIOUserRegionInfo;
+
#endif /* VFIO_USER_PROTOCOL_H */
diff --git a/hw/vfio-user/trace-events b/hw/vfio-user/trace-events
index 6b06a3ed82..1860430301 100644
--- a/hw/vfio-user/trace-events
+++ b/hw/vfio-user/trace-events
@@ -7,3 +7,4 @@ vfio_user_recv_request(uint16_t cmd) " command 0x%x"
vfio_user_send_write(uint16_t id, int wrote) " id 0x%x wrote 0x%x"
vfio_user_version(uint16_t major, uint16_t minor, const char *caps) " major %d minor %d caps: %s"
vfio_user_get_info(uint32_t nregions, uint32_t nirqs) " #regions %d #irqs %d"
+vfio_user_get_region_info(uint32_t index, uint32_t flags, uint64_t size) " index %d flags 0x%x size 0x%"PRIx64
diff --git a/hw/vfio/ap.c b/hw/vfio/ap.c
index 1adce1ab40..54b1815f1d 100644
--- a/hw/vfio/ap.c
+++ b/hw/vfio/ap.c
@@ -162,6 +162,8 @@ static void vfio_ap_realize(DeviceState *dev, Error **errp)
return;
}
+ vbasedev->use_regfds = false;
+
if (!vfio_attach_device(vbasedev->name, vbasedev,
&address_space_memory, errp)) {
goto error;
diff --git a/hw/vfio/ccw.c b/hw/vfio/ccw.c
index 8c16648819..085a3fc6e6 100644
--- a/hw/vfio/ccw.c
+++ b/hw/vfio/ccw.c
@@ -586,6 +586,8 @@ static void vfio_ccw_realize(DeviceState *dev, Error **errp)
goto out_unrealize;
}
+ vbasedev->use_regfds = false;
+
if (!vfio_attach_device(cdev->mdevid, vbasedev,
&address_space_memory, errp)) {
goto out_attach_dev_err;
diff --git a/hw/vfio/container.c b/hw/vfio/container.c
index 0e1af34ce4..ddb86edb65 100644
--- a/hw/vfio/container.c
+++ b/hw/vfio/container.c
@@ -890,10 +890,17 @@ void vfio_put_base_device(VFIODevice *vbasedev)
int i;
for (i = 0; i < vbasedev->num_regions; i++) {
+ if (vbasedev->regfds != NULL && vbasedev->regfds[i] != -1) {
+ close(vbasedev->regfds[i]);
+ }
g_free(vbasedev->regions[i]);
}
g_free(vbasedev->regions);
vbasedev->regions = NULL;
+ if (vbasedev->regfds != NULL) {
+ g_free(vbasedev->regfds);
+ vbasedev->regfds = NULL;
+ }
}
if (!vbasedev->group) {
diff --git a/hw/vfio/helpers.c b/hw/vfio/helpers.c
index bef1540295..4ed393420e 100644
--- a/hw/vfio/helpers.c
+++ b/hw/vfio/helpers.c
@@ -365,6 +365,12 @@ int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region,
region->size = info->size;
region->fd_offset = info->offset;
region->nr = index;
+ if (vbasedev->regfds != NULL) {
+ region->fd = vbasedev->regfds[index];
+ } else {
+ region->fd = vbasedev->fd;
+ }
+
if (region->size) {
region->mem = g_new0(MemoryRegion, 1);
@@ -443,7 +449,7 @@ int vfio_region_mmap(VFIORegion *region)
region->mmaps[i].mmap = mmap(map_align, region->mmaps[i].size, prot,
MAP_SHARED | MAP_FIXED,
- region->vbasedev->fd,
+ region->fd,
region->fd_offset +
region->mmaps[i].offset);
if (region->mmaps[i].mmap == MAP_FAILED) {
@@ -568,12 +574,16 @@ int vfio_get_region_info(VFIODevice *vbasedev, int index,
struct vfio_region_info **info)
{
size_t argsz = sizeof(struct vfio_region_info);
+ int fd = -1;
int ret;
/* create region cache */
if (vbasedev->regions == NULL) {
vbasedev->regions = g_new0(struct vfio_region_info *,
vbasedev->num_regions);
+ if (vbasedev->use_regfds) {
+ vbasedev->regfds = g_new0(int, vbasedev->num_regions);
+ }
}
/* check cache */
if (vbasedev->regions[index] != NULL) {
@@ -587,22 +597,33 @@ int vfio_get_region_info(VFIODevice *vbasedev, int index,
retry:
(*info)->argsz = argsz;
- ret = vbasedev->io->get_region_info(vbasedev, *info);
+ ret = vbasedev->io->get_region_info(vbasedev, *info, &fd);
if (ret != 0) {
g_free(*info);
*info = NULL;
+ if (vbasedev->regfds != NULL) {
+ vbasedev->regfds[index] = -1;
+ }
+
return ret;
}
if ((*info)->argsz > argsz) {
argsz = (*info)->argsz;
*info = g_realloc(*info, argsz);
+ if (fd != -1) {
+ close(fd);
+ fd = -1;
+ }
goto retry;
}
/* fill cache */
vbasedev->regions[index] = *info;
+ if (vbasedev->regfds != NULL) {
+ vbasedev->regfds[index] = fd;
+ }
return 0;
}
@@ -775,10 +796,11 @@ static int vfio_io_device_feature(VFIODevice *vbasedev,
}
static int vfio_io_get_region_info(VFIODevice *vbasedev,
- struct vfio_region_info *info)
+ struct vfio_region_info *info, int *fd)
{
int ret;
+ *fd = -1;
ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, info);
return ret < 0 ? -errno : ret;
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index a7084a7690..4ab3bfa2fa 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -3175,6 +3175,8 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
name = g_strdup(vbasedev->name);
}
+ vbasedev->use_regfds = false;
+
if (!vfio_attach_device(name, vbasedev,
pci_device_iommu_address_space(pdev), errp)) {
goto error;
diff --git a/hw/vfio/platform.c b/hw/vfio/platform.c
index 51534fd941..a76cc6a194 100644
--- a/hw/vfio/platform.c
+++ b/hw/vfio/platform.c
@@ -575,6 +575,8 @@ static void vfio_platform_realize(DeviceState *dev, Error **errp)
VFIODevice *vbasedev = &vdev->vbasedev;
int i;
+ vbasedev->use_regfds = false;
+
qemu_mutex_init(&vdev->intp_mutex);
trace_vfio_platform_realize(vbasedev->sysfsdev ?
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index 699e8a9376..ab7fa7135a 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -59,6 +59,7 @@ typedef struct VFIORegion {
uint32_t nr_mmaps;
VFIOMmap *mmaps;
uint8_t nr; /* cache the region number for debug */
+ int fd; /* fd to mmap() region */
} VFIORegion;
typedef struct VFIOMigration {
@@ -139,6 +140,7 @@ typedef struct VFIODevice {
bool ram_block_discard_allowed;
OnOffAuto enable_migration;
bool migration_events;
+ bool use_regfds;
VFIODeviceOps *ops;
VFIODeviceIO *io;
unsigned int num_irqs;
@@ -158,6 +160,7 @@ typedef struct VFIODevice {
QLIST_ENTRY(VFIODevice) hwpt_next;
VFIOUserProxy *proxy;
struct vfio_region_info **regions;
+ int *regfds;
} VFIODevice;
struct VFIODeviceOps {
@@ -202,7 +205,7 @@ struct VFIODeviceOps {
struct VFIODeviceIO {
int (*device_feature)(VFIODevice *vdev, struct vfio_device_feature *);
int (*get_region_info)(VFIODevice *vdev,
- struct vfio_region_info *info);
+ struct vfio_region_info *info, int *fd);
int (*get_irq_info)(VFIODevice *vdev, struct vfio_irq_info *irq);
int (*set_irqs)(VFIODevice *vdev, struct vfio_irq_set *irqs);
int (*region_read)(VFIODevice *vdev, uint8_t nr, off_t off, uint32_t size,
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* [PATCH v8 18/28] vfio-user: implement VFIO_USER_REGION_READ/WRITE
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (16 preceding siblings ...)
2025-02-19 14:48 ` [PATCH v8 17/28] vfio-user: implement VFIO_USER_DEVICE_GET_REGION_INFO John Levon
@ 2025-02-19 14:48 ` John Levon
2025-02-19 14:48 ` [PATCH v8 19/28] vfio-user: set up PCI in vfio_user_pci_realize() John Levon
` (12 subsequent siblings)
30 siblings, 0 replies; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin, Jagannathan Raman, John Johnson,
Elena Ufimtseva
From: Jagannathan Raman <jag.raman@oracle.com>
Also add support for posted writes on remote devices.
Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
---
hw/vfio-user/common.c | 120 ++++++++++++++++++++++++++++++++++
hw/vfio-user/common.h | 1 +
hw/vfio-user/pci.c | 5 ++
hw/vfio-user/protocol.h | 12 ++++
hw/vfio-user/trace-events | 1 +
hw/vfio/helpers.c | 8 ++-
hw/vfio/pci.c | 5 +-
include/hw/vfio/vfio-common.h | 3 +-
8 files changed, 150 insertions(+), 5 deletions(-)
diff --git a/hw/vfio-user/common.c b/hw/vfio-user/common.c
index 7b96d715cb..1a9033af5c 100644
--- a/hw/vfio-user/common.c
+++ b/hw/vfio-user/common.c
@@ -55,6 +55,8 @@ static void vfio_user_cb(void *opaque);
static void vfio_user_request(void *opaque);
static int vfio_user_send_queued(VFIOUserProxy *proxy, VFIOUserMsg *msg);
+static void vfio_user_send_async(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
+ VFIOUserFDs *fds);
static void vfio_user_send_wait(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
VFIOUserFDs *fds, int rsize);
static void vfio_user_request_msg(VFIOUserHdr *hdr, uint16_t cmd,
@@ -626,6 +628,33 @@ static int vfio_user_send_queued(VFIOUserProxy *proxy, VFIOUserMsg *msg)
return 0;
}
+/*
+ * async send - msg can be queued, but will be freed when sent
+ */
+static void vfio_user_send_async(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
+ VFIOUserFDs *fds)
+{
+ VFIOUserMsg *msg;
+ int ret;
+
+ if (!(hdr->flags & (VFIO_USER_NO_REPLY | VFIO_USER_REPLY))) {
+ error_printf("vfio_user_send_async on sync message\n");
+ return;
+ }
+
+ QEMU_LOCK_GUARD(&proxy->lock);
+
+ msg = vfio_user_getmsg(proxy, hdr, fds);
+ msg->id = hdr->id;
+ msg->rsize = 0;
+ msg->type = VFIO_MSG_ASYNC;
+
+ ret = vfio_user_send_queued(proxy, msg);
+ if (ret < 0) {
+ vfio_user_recycle(proxy, msg);
+ }
+}
+
static void vfio_user_send_wait(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
VFIOUserFDs *fds, int rsize)
{
@@ -1139,9 +1168,84 @@ static int vfio_user_get_region_info(VFIOUserProxy *proxy,
trace_vfio_user_get_region_info(msgp->index, msgp->flags, msgp->size);
memcpy(info, &msgp->argsz, info->argsz);
+
+ /* read-after-write hazard if guest can directly access region */
+ if (info->flags & VFIO_REGION_INFO_FLAG_MMAP) {
+ WITH_QEMU_LOCK_GUARD(&proxy->lock) {
+ proxy->flags |= VFIO_PROXY_NO_POST;
+ }
+ }
+
return 0;
}
+static int vfio_user_region_read(VFIOUserProxy *proxy, uint8_t index,
+ off_t offset, uint32_t count, void *data)
+{
+ g_autofree VFIOUserRegionRW *msgp = NULL;
+ int size = sizeof(*msgp) + count;
+
+ if (count > proxy->max_xfer_size) {
+ return -EINVAL;
+ }
+
+ msgp = g_malloc0(size);
+ vfio_user_request_msg(&msgp->hdr, VFIO_USER_REGION_READ, sizeof(*msgp), 0);
+ msgp->offset = offset;
+ msgp->region = index;
+ msgp->count = count;
+ trace_vfio_user_region_rw(msgp->region, msgp->offset, msgp->count);
+
+ vfio_user_send_wait(proxy, &msgp->hdr, NULL, size);
+ if (msgp->hdr.flags & VFIO_USER_ERROR) {
+ return -msgp->hdr.error_reply;
+ } else if (msgp->count > count) {
+ return -E2BIG;
+ } else {
+ memcpy(data, &msgp->data, msgp->count);
+ }
+
+ return msgp->count;
+}
+
+static int vfio_user_region_write(VFIOUserProxy *proxy, uint8_t index,
+ off_t offset, uint32_t count, void *data,
+ bool post)
+{
+ VFIOUserRegionRW *msgp = NULL;
+ int flags = post ? VFIO_USER_NO_REPLY : 0;
+ int size = sizeof(*msgp) + count;
+ int ret;
+
+ if (count > proxy->max_xfer_size) {
+ return -EINVAL;
+ }
+
+ msgp = g_malloc0(size);
+ vfio_user_request_msg(&msgp->hdr, VFIO_USER_REGION_WRITE, size, flags);
+ msgp->offset = offset;
+ msgp->region = index;
+ msgp->count = count;
+ memcpy(&msgp->data, data, count);
+ trace_vfio_user_region_rw(msgp->region, msgp->offset, msgp->count);
+
+ /* async send will free msg after it's sent */
+ if (post && !(proxy->flags & VFIO_PROXY_NO_POST)) {
+ vfio_user_send_async(proxy, &msgp->hdr, NULL);
+ return count;
+ }
+
+ vfio_user_send_wait(proxy, &msgp->hdr, NULL, 0);
+ if (msgp->hdr.flags & VFIO_USER_ERROR) {
+ ret = -msgp->hdr.error_reply;
+ } else {
+ ret = count;
+ }
+
+ g_free(msgp);
+ return ret;
+}
+
/*
* Socket-based io_ops
@@ -1171,6 +1275,22 @@ static int vfio_user_io_get_region_info(VFIODevice *vbasedev,
return 0;
}
+static int vfio_user_io_region_read(VFIODevice *vbasedev, uint8_t index,
+ off_t off, uint32_t size, void *data)
+{
+ return vfio_user_region_read(vbasedev->proxy, index, off, size, data);
+}
+
+static int vfio_user_io_region_write(VFIODevice *vbasedev, uint8_t index,
+ off_t off, unsigned size, void *data,
+ bool post)
+{
+ return vfio_user_region_write(vbasedev->proxy, index, off, size, data,
+ post);
+}
+
VFIODeviceIO vfio_dev_io_sock = {
.get_region_info = vfio_user_io_get_region_info,
+ .region_read = vfio_user_io_region_read,
+ .region_write = vfio_user_io_region_write,
};
diff --git a/hw/vfio-user/common.h b/hw/vfio-user/common.h
index 30a3125ea3..31b11ed614 100644
--- a/hw/vfio-user/common.h
+++ b/hw/vfio-user/common.h
@@ -84,6 +84,7 @@ typedef struct VFIOUserProxy {
/* VFIOProxy flags */
#define VFIO_PROXY_CLIENT 0x1
#define VFIO_PROXY_FORCE_QUEUED 0x4
+#define VFIO_PROXY_NO_POST 0x8
typedef struct VFIODevice VFIODevice;
diff --git a/hw/vfio-user/pci.c b/hw/vfio-user/pci.c
index fdff6c99e6..26d2960985 100644
--- a/hw/vfio-user/pci.c
+++ b/hw/vfio-user/pci.c
@@ -37,6 +37,7 @@ struct VFIOUserPCIDevice {
VFIOPCIDevice device;
char *sock_name;
bool send_queued; /* all sends are queued */
+ bool no_post; /* all regions write are sync */
};
/*
@@ -99,6 +100,9 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
if (udev->send_queued) {
proxy->flags |= VFIO_PROXY_FORCE_QUEUED;
}
+ if (udev->no_post) {
+ proxy->flags |= VFIO_PROXY_NO_POST;
+ }
if (!vfio_user_validate_version(proxy, errp)) {
goto error;
@@ -170,6 +174,7 @@ static void vfio_user_instance_finalize(Object *obj)
static const Property vfio_user_pci_dev_properties[] = {
DEFINE_PROP_STRING("socket", VFIOUserPCIDevice, sock_name),
DEFINE_PROP_BOOL("x-send-queued", VFIOUserPCIDevice, send_queued, false),
+ DEFINE_PROP_BOOL("x-no-posted-writes", VFIOUserPCIDevice, no_post, false),
};
static void vfio_user_pci_dev_class_init(ObjectClass *klass, void *data)
diff --git a/hw/vfio-user/protocol.h b/hw/vfio-user/protocol.h
index 6f70a48905..6987435e96 100644
--- a/hw/vfio-user/protocol.h
+++ b/hw/vfio-user/protocol.h
@@ -139,4 +139,16 @@ typedef struct {
uint64_t offset;
} VFIOUserRegionInfo;
+/*
+ * VFIO_USER_REGION_READ
+ * VFIO_USER_REGION_WRITE
+ */
+typedef struct {
+ VFIOUserHdr hdr;
+ uint64_t offset;
+ uint32_t region;
+ uint32_t count;
+ char data[];
+} VFIOUserRegionRW;
+
#endif /* VFIO_USER_PROTOCOL_H */
diff --git a/hw/vfio-user/trace-events b/hw/vfio-user/trace-events
index 1860430301..3f5aebe7ac 100644
--- a/hw/vfio-user/trace-events
+++ b/hw/vfio-user/trace-events
@@ -8,3 +8,4 @@ vfio_user_send_write(uint16_t id, int wrote) " id 0x%x wrote 0x%x"
vfio_user_version(uint16_t major, uint16_t minor, const char *caps) " major %d minor %d caps: %s"
vfio_user_get_info(uint32_t nregions, uint32_t nirqs) " #regions %d #irqs %d"
vfio_user_get_region_info(uint32_t index, uint32_t flags, uint64_t size) " index %d flags 0x%x size 0x%"PRIx64
+vfio_user_region_rw(uint32_t region, uint64_t off, uint32_t count) " region %d offset 0x%"PRIx64" count %d"
diff --git a/hw/vfio/helpers.c b/hw/vfio/helpers.c
index 4ed393420e..6bc7600ab1 100644
--- a/hw/vfio/helpers.c
+++ b/hw/vfio/helpers.c
@@ -184,7 +184,8 @@ void vfio_region_write(void *opaque, hwaddr addr,
break;
}
- ret = vbasedev->io->region_write(vbasedev, region->nr, addr, size, &buf);
+ ret = vbasedev->io->region_write(vbasedev, region->nr, addr, size, &buf,
+ region->post_wr);
if (ret != size) {
error_report("%s(%s:region%d+0x%"HWADDR_PRIx", 0x%"PRIx64
",%d) failed: %s",
@@ -365,13 +366,14 @@ int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region,
region->size = info->size;
region->fd_offset = info->offset;
region->nr = index;
+ region->post_wr = false;
+
if (vbasedev->regfds != NULL) {
region->fd = vbasedev->regfds[index];
} else {
region->fd = vbasedev->fd;
}
-
if (region->size) {
region->mem = g_new0(MemoryRegion, 1);
memory_region_init_io(region->mem, obj, &vfio_region_ops,
@@ -837,7 +839,7 @@ static int vfio_io_region_read(VFIODevice *vbasedev, uint8_t index, off_t off,
}
static int vfio_io_region_write(VFIODevice *vbasedev, uint8_t index, off_t off,
- uint32_t size, void *data)
+ uint32_t size, void *data, bool post)
{
struct vfio_region_info *info = vbasedev->regions[index];
int ret;
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 4ab3bfa2fa..168e331607 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -51,7 +51,7 @@
(off), (size), (data)))
#define VDEV_CONFIG_WRITE(vbasedev, off, size, data) \
((vbasedev)->io->region_write((vbasedev), VFIO_PCI_CONFIG_REGION_INDEX, \
- (off), (size), (data)))
+ (off), (size), (data), false))
#define TYPE_VFIO_PCI_NOHOTPLUG "vfio-pci-nohotplug"
@@ -1782,6 +1782,9 @@ static void vfio_bar_prepare(VFIOPCIDevice *vdev, int nr)
bar->type = pci_bar & (bar->ioport ? ~PCI_BASE_ADDRESS_IO_MASK :
~PCI_BASE_ADDRESS_MEM_MASK);
bar->size = bar->region.size;
+
+ /* IO regions are sync, memory can be async */
+ bar->region.post_wr = (bar->ioport == 0);
}
static void vfio_bars_prepare(VFIOPCIDevice *vdev)
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index ab7fa7135a..5adbff4fa7 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -60,6 +60,7 @@ typedef struct VFIORegion {
VFIOMmap *mmaps;
uint8_t nr; /* cache the region number for debug */
int fd; /* fd to mmap() region */
+ bool post_wr; /* writes can be posted */
} VFIORegion;
typedef struct VFIOMigration {
@@ -211,7 +212,7 @@ struct VFIODeviceIO {
int (*region_read)(VFIODevice *vdev, uint8_t nr, off_t off, uint32_t size,
void *data);
int (*region_write)(VFIODevice *vdev, uint8_t nr, off_t off, uint32_t size,
- void *data);
+ void *data, bool post);
};
extern VFIODeviceIO vfio_dev_io_ioctl;
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* [PATCH v8 19/28] vfio-user: set up PCI in vfio_user_pci_realize()
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (17 preceding siblings ...)
2025-02-19 14:48 ` [PATCH v8 18/28] vfio-user: implement VFIO_USER_REGION_READ/WRITE John Levon
@ 2025-02-19 14:48 ` John Levon
2025-02-19 14:48 ` [PATCH v8 20/28] vfio-user: implement VFIO_USER_DEVICE_GET/SET_IRQ* John Levon
` (11 subsequent siblings)
30 siblings, 0 replies; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin, Jagannathan Raman, John Johnson,
Elena Ufimtseva
From: Jagannathan Raman <jag.raman@oracle.com>
Re-use PCI setup functions from hw/vfio/pci.c to realize the vfio-user
PCI device.
Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
---
hw/vfio-user/pci.c | 42 ++++++++++++++++++++++++++++++++++++++++++
hw/vfio/pci.c | 18 +++++++++---------
hw/vfio/pci.h | 9 +++++++++
3 files changed, 60 insertions(+), 9 deletions(-)
diff --git a/hw/vfio-user/pci.c b/hw/vfio-user/pci.c
index 26d2960985..b8c1cc34c2 100644
--- a/hw/vfio-user/pci.c
+++ b/hw/vfio-user/pci.c
@@ -75,6 +75,7 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
AddressSpace *as;
SocketAddress addr;
VFIOUserProxy *proxy;
+ int ret;
/*
* TODO: make option parser understand SocketAddress
@@ -127,8 +128,45 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
goto error;
}
+ if (!vfio_populate_device(vdev, errp)) {
+ goto error;
+ }
+
+ /* Get a copy of config space */
+ ret = vbasedev->io->region_read(vbasedev, VFIO_PCI_CONFIG_REGION_INDEX, 0,
+ MIN(pci_config_size(pdev), vdev->config_size),
+ pdev->config);
+ if (ret < (int)MIN(pci_config_size(&vdev->pdev), vdev->config_size)) {
+ error_setg_errno(errp, -ret, "failed to read device config space");
+ goto error;
+ }
+
+ if (!vfio_pci_config_setup(vdev, errp)) {
+ goto error;
+ }
+
+ /*
+ * vfio_pci_config_setup will have registered the device's BARs
+ * and setup any MSIX BARs, so errors after it succeeds must
+ * use out_teardown
+ */
+
+ if (!vfio_add_capabilities(vdev, errp)) {
+ goto out_teardown;
+ }
+
+ if (!vfio_interrupt_setup(vdev, errp)) {
+ goto out_teardown;
+ }
+
+ vfio_register_err_notifier(vdev);
+ vfio_register_req_notifier(vdev);
+
return;
+out_teardown:
+ vfio_teardown_msi(vdev);
+ vfio_bars_exit(vdev);
error:
error_prepend(errp, VFIO_MSG_PREFIX, vdev->vbasedev.name);
}
@@ -164,6 +202,10 @@ static void vfio_user_instance_finalize(Object *obj)
VFIOPCIDevice *vdev = VFIO_PCI_BASE(obj);
VFIODevice *vbasedev = &vdev->vbasedev;
+ vfio_bars_finalize(vdev);
+ g_free(vdev->emulated_config_bits);
+ g_free(vdev->rom);
+
vfio_pci_put_device(vdev);
if (vbasedev->proxy != NULL) {
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 168e331607..f85215417d 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -1730,7 +1730,7 @@ static bool vfio_msix_setup(VFIOPCIDevice *vdev, int pos, Error **errp)
return true;
}
-static void vfio_teardown_msi(VFIOPCIDevice *vdev)
+void vfio_teardown_msi(VFIOPCIDevice *vdev)
{
msi_uninit(&vdev->pdev);
@@ -1831,7 +1831,7 @@ static void vfio_bars_register(VFIOPCIDevice *vdev)
}
}
-static void vfio_bars_exit(VFIOPCIDevice *vdev)
+void vfio_bars_exit(VFIOPCIDevice *vdev)
{
int i;
@@ -1851,7 +1851,7 @@ static void vfio_bars_exit(VFIOPCIDevice *vdev)
}
}
-static void vfio_bars_finalize(VFIOPCIDevice *vdev)
+void vfio_bars_finalize(VFIOPCIDevice *vdev)
{
int i;
@@ -2419,7 +2419,7 @@ static void vfio_add_ext_cap(VFIOPCIDevice *vdev)
return;
}
-static bool vfio_add_capabilities(VFIOPCIDevice *vdev, Error **errp)
+bool vfio_add_capabilities(VFIOPCIDevice *vdev, Error **errp)
{
PCIDevice *pdev = &vdev->pdev;
@@ -2768,7 +2768,7 @@ bool vfio_populate_vga(VFIOPCIDevice *vdev, Error **errp)
return true;
}
-static bool vfio_populate_device(VFIOPCIDevice *vdev, Error **errp)
+bool vfio_populate_device(VFIOPCIDevice *vdev, Error **errp)
{
VFIODevice *vbasedev = &vdev->vbasedev;
struct vfio_region_info *reg_info = NULL;
@@ -2886,7 +2886,7 @@ static void vfio_err_notifier_handler(void *opaque)
* and continue after disabling error recovery support for the
* device.
*/
-static void vfio_register_err_notifier(VFIOPCIDevice *vdev)
+void vfio_register_err_notifier(VFIOPCIDevice *vdev)
{
Error *err = NULL;
int32_t fd;
@@ -2945,7 +2945,7 @@ static void vfio_req_notifier_handler(void *opaque)
}
}
-static void vfio_register_req_notifier(VFIOPCIDevice *vdev)
+void vfio_register_req_notifier(VFIOPCIDevice *vdev)
{
struct vfio_irq_info irq_info = { .argsz = sizeof(irq_info),
.index = VFIO_PCI_REQ_IRQ_INDEX };
@@ -3001,7 +3001,7 @@ static void vfio_unregister_req_notifier(VFIOPCIDevice *vdev)
vdev->req_enabled = false;
}
-static bool vfio_pci_config_setup(VFIOPCIDevice *vdev, Error **errp)
+bool vfio_pci_config_setup(VFIOPCIDevice *vdev, Error **errp)
{
PCIDevice *pdev = &vdev->pdev;
VFIODevice *vbasedev = &vdev->vbasedev;
@@ -3094,7 +3094,7 @@ static bool vfio_pci_config_setup(VFIOPCIDevice *vdev, Error **errp)
return true;
}
-static bool vfio_interrupt_setup(VFIOPCIDevice *vdev, Error **errp)
+bool vfio_interrupt_setup(VFIOPCIDevice *vdev, Error **errp)
{
PCIDevice *pdev = &vdev->pdev;
diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h
index c0f030f4db..7e126822f9 100644
--- a/hw/vfio/pci.h
+++ b/hw/vfio/pci.h
@@ -218,6 +218,15 @@ Object *vfio_pci_get_object(VFIODevice *vbasedev);
int vfio_pci_save_config(VFIODevice *vbasedev, QEMUFile *f, Error **errp);
int vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f);
void vfio_pci_put_device(VFIOPCIDevice *vdev);
+bool vfio_populate_device(VFIOPCIDevice *vdev, Error **errp);
+void vfio_teardown_msi(VFIOPCIDevice *vdev);
+void vfio_bars_exit(VFIOPCIDevice *vdev);
+void vfio_bars_finalize(VFIOPCIDevice *vdev);
+bool vfio_add_capabilities(VFIOPCIDevice *vdev, Error **errp);
+void vfio_register_err_notifier(VFIOPCIDevice *vdev);
+void vfio_register_req_notifier(VFIOPCIDevice *vdev);
+bool vfio_pci_config_setup(VFIOPCIDevice *vdev, Error **errp);
+bool vfio_interrupt_setup(VFIOPCIDevice *vdev, Error **errp);
void vfio_instance_init(Object *obj);
uint64_t vfio_vga_read(void *opaque, hwaddr addr, unsigned size);
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* [PATCH v8 20/28] vfio-user: implement VFIO_USER_DEVICE_GET/SET_IRQ*
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (18 preceding siblings ...)
2025-02-19 14:48 ` [PATCH v8 19/28] vfio-user: set up PCI in vfio_user_pci_realize() John Levon
@ 2025-02-19 14:48 ` John Levon
2025-02-19 14:48 ` [PATCH v8 21/28] vfio-user: forward MSI-X PBA BAR accesses to server John Levon
` (10 subsequent siblings)
30 siblings, 0 replies; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin, Jagannathan Raman, John Johnson,
Elena Ufimtseva
From: Jagannathan Raman <jag.raman@oracle.com>
IRQ setup uses the same semantics as the traditional vfio path, but we
need to share the corresponding file descriptors with the server as
necessary.
Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
---
hw/vfio-user/common.c | 140 ++++++++++++++++++++++++++++++++++++++
hw/vfio-user/protocol.h | 25 +++++++
hw/vfio-user/trace-events | 2 +
3 files changed, 167 insertions(+)
diff --git a/hw/vfio-user/common.c b/hw/vfio-user/common.c
index 1a9033af5c..182ef5ab8f 100644
--- a/hw/vfio-user/common.c
+++ b/hw/vfio-user/common.c
@@ -1179,6 +1179,122 @@ static int vfio_user_get_region_info(VFIOUserProxy *proxy,
return 0;
}
+static int vfio_user_get_irq_info(VFIOUserProxy *proxy,
+ struct vfio_irq_info *info)
+{
+ VFIOUserIRQInfo msg;
+
+ memset(&msg, 0, sizeof(msg));
+ vfio_user_request_msg(&msg.hdr, VFIO_USER_DEVICE_GET_IRQ_INFO,
+ sizeof(msg), 0);
+ msg.argsz = info->argsz;
+ msg.index = info->index;
+
+ vfio_user_send_wait(proxy, &msg.hdr, NULL, 0);
+ if (msg.hdr.flags & VFIO_USER_ERROR) {
+ return -msg.hdr.error_reply;
+ }
+ trace_vfio_user_get_irq_info(msg.index, msg.flags, msg.count);
+
+ memcpy(info, &msg.argsz, sizeof(*info));
+ return 0;
+}
+
+static int irq_howmany(int *fdp, uint32_t cur, uint32_t max)
+{
+ int n = 0;
+
+ if (fdp[cur] != -1) {
+ do {
+ n++;
+ } while (n < max && fdp[cur + n] != -1);
+ } else {
+ do {
+ n++;
+ } while (n < max && fdp[cur + n] == -1);
+ }
+
+ return n;
+}
+
+static int vfio_user_set_irqs(VFIOUserProxy *proxy, struct vfio_irq_set *irq)
+{
+ g_autofree VFIOUserIRQSet *msgp = NULL;
+ uint32_t size, nfds, send_fds, sent_fds, max;
+
+ if (irq->argsz < sizeof(*irq)) {
+ error_printf("vfio_user_set_irqs argsz too small\n");
+ return -EINVAL;
+ }
+
+ /*
+ * Handle simple case
+ */
+ if ((irq->flags & VFIO_IRQ_SET_DATA_EVENTFD) == 0) {
+ size = sizeof(VFIOUserHdr) + irq->argsz;
+ msgp = g_malloc0(size);
+
+ vfio_user_request_msg(&msgp->hdr, VFIO_USER_DEVICE_SET_IRQS, size, 0);
+ msgp->argsz = irq->argsz;
+ msgp->flags = irq->flags;
+ msgp->index = irq->index;
+ msgp->start = irq->start;
+ msgp->count = irq->count;
+ trace_vfio_user_set_irqs(msgp->index, msgp->start, msgp->count,
+ msgp->flags);
+
+ vfio_user_send_wait(proxy, &msgp->hdr, NULL, 0);
+ if (msgp->hdr.flags & VFIO_USER_ERROR) {
+ return -msgp->hdr.error_reply;
+ }
+
+ return 0;
+ }
+
+ /*
+ * Calculate the number of FDs to send
+ * and adjust argsz
+ */
+ nfds = (irq->argsz - sizeof(*irq)) / sizeof(int);
+ irq->argsz = sizeof(*irq);
+ msgp = g_malloc0(sizeof(*msgp));
+ /*
+ * Send in chunks if over max_send_fds
+ */
+ for (sent_fds = 0; nfds > sent_fds; sent_fds += send_fds) {
+ VFIOUserFDs *arg_fds, loop_fds;
+
+ /* must send all valid FDs or all invalid FDs in single msg */
+ max = nfds - sent_fds;
+ if (max > proxy->max_send_fds) {
+ max = proxy->max_send_fds;
+ }
+ send_fds = irq_howmany((int *)irq->data, sent_fds, max);
+
+ vfio_user_request_msg(&msgp->hdr, VFIO_USER_DEVICE_SET_IRQS,
+ sizeof(*msgp), 0);
+ msgp->argsz = irq->argsz;
+ msgp->flags = irq->flags;
+ msgp->index = irq->index;
+ msgp->start = irq->start + sent_fds;
+ msgp->count = send_fds;
+ trace_vfio_user_set_irqs(msgp->index, msgp->start, msgp->count,
+ msgp->flags);
+
+ loop_fds.send_fds = send_fds;
+ loop_fds.recv_fds = 0;
+ loop_fds.fds = (int *)irq->data + sent_fds;
+ arg_fds = loop_fds.fds[0] != -1 ? &loop_fds : NULL;
+
+ vfio_user_send_wait(proxy, &msgp->hdr, arg_fds, 0);
+ if (msgp->hdr.flags & VFIO_USER_ERROR) {
+ return -msgp->hdr.error_reply;
+ }
+ }
+
+ return 0;
+}
+
static int vfio_user_region_read(VFIOUserProxy *proxy, uint8_t index,
off_t offset, uint32_t count, void *data)
{
@@ -1275,6 +1391,28 @@ static int vfio_user_io_get_region_info(VFIODevice *vbasedev,
return 0;
}
+static int vfio_user_io_get_irq_info(VFIODevice *vbasedev,
+ struct vfio_irq_info *irq)
+{
+ int ret;
+
+ ret = vfio_user_get_irq_info(vbasedev->proxy, irq);
+ if (ret) {
+ return ret;
+ }
+
+ if (irq->index > vbasedev->num_irqs) {
+ return -EINVAL;
+ }
+ return 0;
+}
+
+static int vfio_user_io_set_irqs(VFIODevice *vbasedev,
+ struct vfio_irq_set *irqs)
+{
+ return vfio_user_set_irqs(vbasedev->proxy, irqs);
+}
+
static int vfio_user_io_region_read(VFIODevice *vbasedev, uint8_t index,
off_t off, uint32_t size, void *data)
{
@@ -1291,6 +1429,8 @@ static int vfio_user_io_region_write(VFIODevice *vbasedev, uint8_t index,
VFIODeviceIO vfio_dev_io_sock = {
.get_region_info = vfio_user_io_get_region_info,
+ .get_irq_info = vfio_user_io_get_irq_info,
+ .set_irqs = vfio_user_io_set_irqs,
.region_read = vfio_user_io_region_read,
.region_write = vfio_user_io_region_write,
};
diff --git a/hw/vfio-user/protocol.h b/hw/vfio-user/protocol.h
index 6987435e96..48dd475ab3 100644
--- a/hw/vfio-user/protocol.h
+++ b/hw/vfio-user/protocol.h
@@ -139,6 +139,31 @@ typedef struct {
uint64_t offset;
} VFIOUserRegionInfo;
+/*
+ * VFIO_USER_DEVICE_GET_IRQ_INFO
+ * imported from struct vfio_irq_info
+ */
+typedef struct {
+ VFIOUserHdr hdr;
+ uint32_t argsz;
+ uint32_t flags;
+ uint32_t index;
+ uint32_t count;
+} VFIOUserIRQInfo;
+
+/*
+ * VFIO_USER_DEVICE_SET_IRQS
+ * imported from struct vfio_irq_set
+ */
+typedef struct {
+ VFIOUserHdr hdr;
+ uint32_t argsz;
+ uint32_t flags;
+ uint32_t index;
+ uint32_t start;
+ uint32_t count;
+} VFIOUserIRQSet;
+
/*
* VFIO_USER_REGION_READ
* VFIO_USER_REGION_WRITE
diff --git a/hw/vfio-user/trace-events b/hw/vfio-user/trace-events
index 3f5aebe7ac..053f5932eb 100644
--- a/hw/vfio-user/trace-events
+++ b/hw/vfio-user/trace-events
@@ -9,3 +9,5 @@ vfio_user_version(uint16_t major, uint16_t minor, const char *caps) " major %d m
vfio_user_get_info(uint32_t nregions, uint32_t nirqs) " #regions %d #irqs %d"
vfio_user_get_region_info(uint32_t index, uint32_t flags, uint64_t size) " index %d flags 0x%x size 0x%"PRIx64
vfio_user_region_rw(uint32_t region, uint64_t off, uint32_t count) " region %d offset 0x%"PRIx64" count %d"
+vfio_user_get_irq_info(uint32_t index, uint32_t flags, uint32_t count) " index %d flags 0x%x count %d"
+vfio_user_set_irqs(uint32_t index, uint32_t start, uint32_t count, uint32_t flags) " index %d start %d count %d flags 0x%x"
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* [PATCH v8 21/28] vfio-user: forward MSI-X PBA BAR accesses to server
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (19 preceding siblings ...)
2025-02-19 14:48 ` [PATCH v8 20/28] vfio-user: implement VFIO_USER_DEVICE_GET/SET_IRQ* John Levon
@ 2025-02-19 14:48 ` John Levon
2025-02-19 14:48 ` [PATCH v8 22/28] vfio-user: set up container access to the proxy John Levon
` (9 subsequent siblings)
30 siblings, 0 replies; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin, Jagannathan Raman, John Johnson,
Elena Ufimtseva
From: Jagannathan Raman <jag.raman@oracle.com>
For vfio-user, the server holds the pending IRQ state; set up an I/O
region for the MSI-X PBA so we can ask the server for this state on a
PBA read.
If VFIO_IRQ_INFO_MASKABLE is set for VFIO_PCI_MSIX_IRQ_INDEX, record
this in ->can_mask_msix, and use it to individually mask MSI-X
interrupts as needed.
Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
---
hw/vfio-user/pci.c | 63 +++++++++++++++++++++++++
hw/vfio/helpers.c | 26 +++++++++++
hw/vfio/pci.c | 86 +++++++++++++++++++++++++----------
hw/vfio/pci.h | 2 +
include/hw/vfio/vfio-common.h | 2 +
5 files changed, 156 insertions(+), 23 deletions(-)
diff --git a/hw/vfio-user/pci.c b/hw/vfio-user/pci.c
index b8c1cc34c2..cf1e642399 100644
--- a/hw/vfio-user/pci.c
+++ b/hw/vfio-user/pci.c
@@ -40,6 +40,62 @@ struct VFIOUserPCIDevice {
bool no_post; /* all regions write are sync */
};
+/*
+ * The server maintains the device's pending interrupts,
+ * via its MSIX table and PBA, so we treat these accesses
+ * like PCI config space and forward them.
+ */
+static uint64_t vfio_user_pba_read(void *opaque, hwaddr addr,
+ unsigned size)
+{
+ VFIOPCIDevice *vdev = opaque;
+ VFIORegion *region = &vdev->bars[vdev->msix->pba_bar].region;
+ uint64_t data;
+
+ /* server copy is what matters */
+ data = vfio_region_read(region, addr + vdev->msix->pba_offset, size);
+ return data;
+}
+
+static void vfio_user_pba_write(void *opaque, hwaddr addr,
+ uint64_t data, unsigned size)
+{
+ /* dropped */
+}
+
+static const MemoryRegionOps vfio_user_pba_ops = {
+ .read = vfio_user_pba_read,
+ .write = vfio_user_pba_write,
+ .endianness = DEVICE_LITTLE_ENDIAN,
+};
+
+static void vfio_user_msix_setup(VFIOPCIDevice *vdev)
+{
+ MemoryRegion *vfio_reg, *msix_reg, *pba_reg;
+
+ pba_reg = g_new0(MemoryRegion, 1);
+ vdev->msix->pba_region = pba_reg;
+
+ vfio_reg = vdev->bars[vdev->msix->pba_bar].mr;
+ msix_reg = &vdev->pdev.msix_pba_mmio;
+ memory_region_init_io(pba_reg, OBJECT(vdev), &vfio_user_pba_ops, vdev,
+ "VFIO MSIX PBA", int128_get64(msix_reg->size));
+ memory_region_add_subregion_overlap(vfio_reg, vdev->msix->pba_offset,
+ pba_reg, 1);
+}
+
+static void vfio_user_msix_teardown(VFIOPCIDevice *vdev)
+{
+ MemoryRegion *mr, *sub;
+
+ mr = vdev->bars[vdev->msix->pba_bar].mr;
+ sub = vdev->msix->pba_region;
+ memory_region_del_subregion(mr, sub);
+
+ g_free(vdev->msix->pba_region);
+ vdev->msix->pba_region = NULL;
+}
+
/*
* Incoming request message callback.
*
@@ -154,6 +210,9 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
if (!vfio_add_capabilities(vdev, errp)) {
goto out_teardown;
}
+ if (vdev->msix != NULL) {
+ vfio_user_msix_setup(vdev);
+ }
if (!vfio_interrupt_setup(vdev, errp)) {
goto out_teardown;
@@ -206,6 +265,10 @@ static void vfio_user_instance_finalize(Object *obj)
g_free(vdev->emulated_config_bits);
g_free(vdev->rom);
+ if (vdev->msix != NULL) {
+ vfio_user_msix_teardown(vdev);
+ }
+
vfio_pci_put_device(vdev);
if (vbasedev->proxy != NULL) {
diff --git a/hw/vfio/helpers.c b/hw/vfio/helpers.c
index 6bc7600ab1..2ab30fa91b 100644
--- a/hw/vfio/helpers.c
+++ b/hw/vfio/helpers.c
@@ -73,6 +73,32 @@ void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index)
vbasedev->io->set_irqs(vbasedev, &irq_set);
}
+void vfio_mask_single_irq(VFIODevice *vbasedev, int index, int irq)
+{
+ struct vfio_irq_set irq_set = {
+ .argsz = sizeof(irq_set),
+ .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_MASK,
+ .index = index,
+ .start = irq,
+ .count = 1,
+ };
+
+ vbasedev->io->set_irqs(vbasedev, &irq_set);
+}
+
+void vfio_unmask_single_irq(VFIODevice *vbasedev, int index, int irq)
+{
+ struct vfio_irq_set irq_set = {
+ .argsz = sizeof(irq_set),
+ .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_UNMASK,
+ .index = index,
+ .start = irq,
+ .count = 1,
+ };
+
+ vbasedev->io->set_irqs(vbasedev, &irq_set);
+}
+
static inline const char *action_to_str(int action)
{
switch (action) {
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index f85215417d..b9c7e13053 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -520,11 +520,30 @@ static void vfio_update_kvm_msi_virq(VFIOMSIVector *vector, MSIMessage msg,
kvm_irqchip_commit_routes(kvm_state);
}
+static void set_irq_signalling(VFIODevice *vbasedev, VFIOMSIVector *vector,
+ unsigned int nr)
+{
+ Error *err = NULL;
+ int32_t fd;
+
+ if (vector->virq >= 0) {
+ fd = event_notifier_get_fd(&vector->kvm_interrupt);
+ } else {
+ fd = event_notifier_get_fd(&vector->interrupt);
+ }
+
+ if (!vfio_set_irq_signaling(vbasedev, VFIO_PCI_MSIX_IRQ_INDEX, nr,
+ VFIO_IRQ_SET_ACTION_TRIGGER, fd, &err)) {
+ error_reportf_err(err, VFIO_MSG_PREFIX, vbasedev->name);
+ }
+}
+
static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr,
MSIMessage *msg, IOHandler *handler)
{
VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
VFIOMSIVector *vector;
+ bool new_vec = false;
int ret;
bool resizing = !!(vdev->nr_vectors < nr + 1);
@@ -539,6 +558,7 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr,
error_report("vfio: Error: event_notifier_init failed");
}
vector->use = true;
+ new_vec = true;
msix_vector_use(pdev, nr);
}
@@ -565,6 +585,7 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr,
kvm_irqchip_commit_route_changes(&vfio_route_change);
vfio_connect_kvm_msi_virq(vector);
}
+ new_vec = true;
}
}
@@ -574,38 +595,35 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr,
* in use, so we shutdown and incrementally increase them as needed.
* nr_vectors represents the total number of vectors allocated.
*
+ * Otherwise, unmask the vector if the vector is already setup (and we can
+ * do so) or send the fd if not.
+ *
* When dynamic allocation is supported, let the host only allocate
* and enable a vector when it is in use in guest. nr_vectors represents
* the upper bound of vectors being enabled (but not all of the ranges
* is allocated or enabled).
*/
+
if (resizing) {
vdev->nr_vectors = nr + 1;
}
if (!vdev->defer_kvm_irq_routing) {
- if (vdev->msix->noresize && resizing) {
- 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);
- }
- } else {
- Error *err = NULL;
- int32_t fd;
-
- if (vector->virq >= 0) {
- fd = event_notifier_get_fd(&vector->kvm_interrupt);
+ if (resizing) {
+ if (vdev->msix->noresize) {
+ 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);
+ }
} else {
- fd = event_notifier_get_fd(&vector->interrupt);
- }
-
- if (!vfio_set_irq_signaling(&vdev->vbasedev,
- VFIO_PCI_MSIX_IRQ_INDEX, nr,
- VFIO_IRQ_SET_ACTION_TRIGGER, fd,
- &err)) {
- error_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name);
+ set_irq_signalling(&vdev->vbasedev, vector, nr);
}
+ } else if (vdev->can_mask_msix && !new_vec) {
+ vfio_unmask_single_irq(&vdev->vbasedev, VFIO_PCI_MSIX_IRQ_INDEX,
+ nr);
+ } else {
+ set_irq_signalling(&vdev->vbasedev, vector, nr);
}
}
@@ -633,6 +651,12 @@ static void vfio_msix_vector_release(PCIDevice *pdev, unsigned int nr)
trace_vfio_msix_vector_release(vdev->vbasedev.name, nr);
+ /* just mask vector if peer supports it */
+ if (vdev->can_mask_msix) {
+ vfio_mask_single_irq(&vdev->vbasedev, VFIO_PCI_MSIX_IRQ_INDEX, nr);
+ return;
+ }
+
/*
* There are still old guests that mask and unmask vectors on every
* interrupt. If we're using QEMU bypass with a KVM irqfd, leave all of
@@ -704,7 +728,7 @@ static void vfio_msix_enable(VFIOPCIDevice *vdev)
if (ret) {
error_report("vfio: failed to enable vectors, %d", ret);
}
- } else {
+ } else if (!vdev->can_mask_msix) {
/*
* Some communication channels between VF & PF or PF & fw rely on the
* physical state of the device and expect that enabling MSI-X from the
@@ -721,6 +745,13 @@ static void vfio_msix_enable(VFIOPCIDevice *vdev)
if (ret) {
error_report("vfio: failed to enable MSI-X, %d", ret);
}
+ } else {
+ /*
+ * If we can use irq masking, send an invalid fd on vector 0
+ * to enable MSI-X without any vectors enabled.
+ */
+ vfio_set_irq_signaling(&vdev->vbasedev, VFIO_PCI_MSIX_IRQ_INDEX, 0,
+ VFIO_IRQ_SET_ACTION_TRIGGER, -1, NULL);
}
trace_vfio_msix_enable(vdev->vbasedev.name);
@@ -2772,7 +2803,7 @@ bool vfio_populate_device(VFIOPCIDevice *vdev, Error **errp)
{
VFIODevice *vbasedev = &vdev->vbasedev;
struct vfio_region_info *reg_info = NULL;
- struct vfio_irq_info irq_info = { .argsz = sizeof(irq_info) };
+ struct vfio_irq_info irq_info;
int i, ret = -1;
/* Sanity check device */
@@ -2833,8 +2864,17 @@ bool vfio_populate_device(VFIOPCIDevice *vdev, Error **errp)
}
}
- irq_info.index = VFIO_PCI_ERR_IRQ_INDEX;
+ irq_info.index = VFIO_PCI_MSIX_IRQ_INDEX;
+ irq_info.argsz = sizeof(irq_info);
+ ret = vbasedev->io->get_irq_info(vbasedev, &irq_info);
+ if (ret == 0 && (irq_info.flags & VFIO_IRQ_INFO_MASKABLE)) {
+ vdev->can_mask_msix = true;
+ } else {
+ vdev->can_mask_msix = false;
+ }
+ irq_info.index = VFIO_PCI_ERR_IRQ_INDEX;
+ irq_info.argsz = sizeof(irq_info);
ret = vbasedev->io->get_irq_info(vbasedev, &irq_info);
if (ret) {
/* This can fail for an old kernel or legacy PCI dev */
diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h
index 7e126822f9..db1b2010fe 100644
--- a/hw/vfio/pci.h
+++ b/hw/vfio/pci.h
@@ -114,6 +114,7 @@ typedef struct VFIOMSIXInfo {
uint32_t pba_offset;
unsigned long *pending;
bool noresize;
+ MemoryRegion *pba_region;
} VFIOMSIXInfo;
/*
@@ -183,6 +184,7 @@ struct VFIOPCIDevice {
bool defer_kvm_irq_routing;
bool clear_parent_atomics_on_exit;
bool skip_vsc_check;
+ bool can_mask_msix;
VFIODisplay *dpy;
Notifier irqchip_change_notifier;
};
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index 5adbff4fa7..cf2033d6c0 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -267,6 +267,8 @@ void vfio_address_space_insert(VFIOAddressSpace *space,
void vfio_disable_irqindex(VFIODevice *vbasedev, int index);
void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index);
void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index);
+void vfio_unmask_single_irq(VFIODevice *vbasedev, int index, int irq);
+void vfio_mask_single_irq(VFIODevice *vbasedev, int index, int irq);
bool vfio_set_irq_signaling(VFIODevice *vbasedev, int index, int subindex,
int action, int fd, Error **errp);
void vfio_region_write(void *opaque, hwaddr addr,
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* [PATCH v8 22/28] vfio-user: set up container access to the proxy
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (20 preceding siblings ...)
2025-02-19 14:48 ` [PATCH v8 21/28] vfio-user: forward MSI-X PBA BAR accesses to server John Levon
@ 2025-02-19 14:48 ` John Levon
2025-02-19 14:48 ` [PATCH v8 23/28] vfio-user: implement VFIO_USER_DEVICE_RESET John Levon
` (8 subsequent siblings)
30 siblings, 0 replies; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin, Jagannathan Raman, John Johnson,
Elena Ufimtseva
From: Jagannathan Raman <jag.raman@oracle.com>
The user container will shortly need access to the underlying vfio-user
proxy; set this up.
Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
---
hw/vfio-user/container.c | 43 +++++++++++++++++++++++++++++++---------
hw/vfio-user/container.h | 1 +
hw/vfio/container.c | 4 +++-
3 files changed, 38 insertions(+), 10 deletions(-)
diff --git a/hw/vfio-user/container.c b/hw/vfio-user/container.c
index c079d6f89b..0c487dbb92 100644
--- a/hw/vfio-user/container.c
+++ b/hw/vfio-user/container.c
@@ -55,15 +55,28 @@ static int vfio_user_query_dirty_bitmap(const VFIOContainerBase *bcontainer,
static bool vfio_user_setup(VFIOContainerBase *bcontainer, Error **errp)
{
- error_setg_errno(errp, ENOTSUP, "Not supported");
- return -ENOTSUP;
+ VFIOUserContainer *container = container_of(bcontainer, VFIOUserContainer,
+ bcontainer);
+
+ assert(container->proxy->dma_pgsizes != 0);
+ bcontainer->pgsizes = container->proxy->dma_pgsizes;
+ bcontainer->dma_max_mappings = container->proxy->max_dma;
+
+ /* No live migration support yet. */
+ bcontainer->dirty_pages_supported = false;
+ bcontainer->max_dirty_bitmap_size = container->proxy->max_bitmap;
+ bcontainer->dirty_pgsizes = container->proxy->migr_pgsize;
+
+ return true;
}
-static VFIOUserContainer *vfio_create_user_container(Error **errp)
+static VFIOUserContainer *vfio_create_user_container(VFIODevice *vbasedev,
+ Error **errp)
{
VFIOUserContainer *container;
container = VFIO_IOMMU_USER(object_new(TYPE_VFIO_IOMMU_USER));
+ container->proxy = vbasedev->proxy;
return container;
}
@@ -71,16 +84,18 @@ static VFIOUserContainer *vfio_create_user_container(Error **errp)
* Try to mirror vfio_connect_container() as much as possible.
*/
static VFIOUserContainer *
-vfio_connect_user_container(AddressSpace *as, Error **errp)
+vfio_connect_user_container(AddressSpace *as, VFIODevice *vbasedev,
+ Error **errp)
{
VFIOContainerBase *bcontainer;
VFIOUserContainer *container;
VFIOAddressSpace *space;
VFIOIOMMUClass *vioc;
+ int ret;
space = vfio_get_address_space(as);
- container = vfio_create_user_container(errp);
+ container = vfio_create_user_container(vbasedev, errp);
if (!container) {
goto put_space_exit;
}
@@ -91,11 +106,17 @@ vfio_connect_user_container(AddressSpace *as, Error **errp)
goto free_container_exit;
}
+ ret = ram_block_uncoordinated_discard_disable(true);
+ if (ret) {
+ error_setg_errno(errp, -ret, "Cannot set discarding of RAM broken");
+ goto unregister_container_exit;
+ }
+
vioc = VFIO_IOMMU_GET_CLASS(bcontainer);
assert(vioc->setup);
if (!vioc->setup(bcontainer, errp)) {
- goto unregister_container_exit;
+ goto enable_discards_exit;
}
vfio_address_space_insert(space, bcontainer);
@@ -120,6 +141,9 @@ listener_release_exit:
vioc->release(bcontainer);
}
+enable_discards_exit:
+ ram_block_uncoordinated_discard_disable(false);
+
unregister_container_exit:
vfio_cpr_unregister_container(bcontainer);
@@ -136,14 +160,15 @@ static void vfio_disconnect_user_container(VFIOUserContainer *container)
{
VFIOContainerBase *bcontainer = &container->bcontainer;
VFIOIOMMUClass *vioc = VFIO_IOMMU_GET_CLASS(bcontainer);
+ VFIOAddressSpace *space = bcontainer->space;
+
+ ram_block_uncoordinated_discard_disable(false);
memory_listener_unregister(&bcontainer->listener);
if (vioc->release) {
vioc->release(bcontainer);
}
- VFIOAddressSpace *space = bcontainer->space;
-
vfio_cpr_unregister_container(bcontainer);
object_unref(container);
@@ -177,7 +202,7 @@ static bool vfio_user_attach_device(const char *name, VFIODevice *vbasedev,
{
VFIOUserContainer *container;
- container = vfio_connect_user_container(as, errp);
+ container = vfio_connect_user_container(as, vbasedev, errp);
if (container == NULL) {
error_prepend(errp, "failed to connect proxy");
return false;
diff --git a/hw/vfio-user/container.h b/hw/vfio-user/container.h
index 24ce13bc2d..8a033d5598 100644
--- a/hw/vfio-user/container.h
+++ b/hw/vfio-user/container.h
@@ -16,6 +16,7 @@
/* MMU container sub-class for vfio-user. */
typedef struct VFIOUserContainer {
VFIOContainerBase bcontainer;
+ VFIOUserProxy *proxy;
} VFIOUserContainer;
OBJECT_DECLARE_SIMPLE_TYPE(VFIOUserContainer, VFIO_IOMMU_USER);
diff --git a/hw/vfio/container.c b/hw/vfio/container.c
index ddb86edb65..797707d0fd 100644
--- a/hw/vfio/container.c
+++ b/hw/vfio/container.c
@@ -909,7 +909,9 @@ void vfio_put_base_device(VFIODevice *vbasedev)
QLIST_REMOVE(vbasedev, next);
vbasedev->group = NULL;
trace_vfio_put_base_device(vbasedev->fd);
- close(vbasedev->fd);
+ if (vbasedev->fd != -1) {
+ close(vbasedev->fd);
+ }
}
static int vfio_device_groupid(VFIODevice *vbasedev, Error **errp)
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* [PATCH v8 23/28] vfio-user: implement VFIO_USER_DEVICE_RESET
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (21 preceding siblings ...)
2025-02-19 14:48 ` [PATCH v8 22/28] vfio-user: set up container access to the proxy John Levon
@ 2025-02-19 14:48 ` John Levon
2025-02-19 14:48 ` [PATCH v8 24/28] vfio-user: implement VFIO_USER_DMA_MAP/UNMAP John Levon
` (7 subsequent siblings)
30 siblings, 0 replies; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin, Jagannathan Raman, John Johnson,
Elena Ufimtseva
From: Jagannathan Raman <jag.raman@oracle.com>
Hook this call up to the legacy reset handler for vfio-user-pci.
Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
---
hw/vfio-user/common.c | 12 ++++++++++++
hw/vfio-user/common.h | 1 +
hw/vfio-user/pci.c | 15 +++++++++++++++
3 files changed, 28 insertions(+)
diff --git a/hw/vfio-user/common.c b/hw/vfio-user/common.c
index 182ef5ab8f..160a1f0536 100644
--- a/hw/vfio-user/common.c
+++ b/hw/vfio-user/common.c
@@ -1362,6 +1362,18 @@ static int vfio_user_region_write(VFIOUserProxy *proxy, uint8_t index,
return ret;
}
+void vfio_user_reset(VFIOUserProxy *proxy)
+{
+ VFIOUserHdr msg;
+
+ vfio_user_request_msg(&msg, VFIO_USER_DEVICE_RESET, sizeof(msg), 0);
+
+ vfio_user_send_wait(proxy, &msg, NULL, 0);
+ if (msg.flags & VFIO_USER_ERROR) {
+ error_printf("reset reply error %d\n", msg.error_reply);
+ }
+}
+
/*
* Socket-based io_ops
diff --git a/hw/vfio-user/common.h b/hw/vfio-user/common.h
index 31b11ed614..c09637dd48 100644
--- a/hw/vfio-user/common.h
+++ b/hw/vfio-user/common.h
@@ -95,6 +95,7 @@ void vfio_user_set_handler(VFIODevice *vbasedev,
void *reqarg);
bool vfio_user_validate_version(VFIOUserProxy *proxy, Error **errp);
int vfio_user_get_info(VFIOUserProxy *proxy, struct vfio_device_info *info);
+void vfio_user_reset(VFIOUserProxy *proxy);
extern VFIODeviceIO vfio_dev_io_sock;
diff --git a/hw/vfio-user/pci.c b/hw/vfio-user/pci.c
index cf1e642399..d520b7592b 100644
--- a/hw/vfio-user/pci.c
+++ b/hw/vfio-user/pci.c
@@ -276,6 +276,20 @@ static void vfio_user_instance_finalize(Object *obj)
}
}
+static void vfio_user_pci_reset(DeviceState *dev)
+{
+ VFIOPCIDevice *vdev = VFIO_PCI_BASE(dev);
+ VFIODevice *vbasedev = &vdev->vbasedev;
+
+ vfio_pci_pre_reset(vdev);
+
+ if (vbasedev->reset_works) {
+ vfio_user_reset(vbasedev->proxy);
+ }
+
+ vfio_pci_post_reset(vdev);
+}
+
static const Property vfio_user_pci_dev_properties[] = {
DEFINE_PROP_STRING("socket", VFIOUserPCIDevice, sock_name),
DEFINE_PROP_BOOL("x-send-queued", VFIOUserPCIDevice, send_queued, false),
@@ -287,6 +301,7 @@ static void vfio_user_pci_dev_class_init(ObjectClass *klass, void *data)
DeviceClass *dc = DEVICE_CLASS(klass);
PCIDeviceClass *pdc = PCI_DEVICE_CLASS(klass);
+ device_class_set_legacy_reset(dc, vfio_user_pci_reset);
device_class_set_props(dc, vfio_user_pci_dev_properties);
dc->desc = "VFIO over socket PCI device assignment";
pdc->realize = vfio_user_pci_realize;
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* [PATCH v8 24/28] vfio-user: implement VFIO_USER_DMA_MAP/UNMAP
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (22 preceding siblings ...)
2025-02-19 14:48 ` [PATCH v8 23/28] vfio-user: implement VFIO_USER_DEVICE_RESET John Levon
@ 2025-02-19 14:48 ` John Levon
2025-02-19 14:48 ` [PATCH v8 25/28] vfio-user: implement VFIO_USER_DMA_READ/WRITE John Levon
` (6 subsequent siblings)
30 siblings, 0 replies; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin, John Levon, John Johnson, Jagannathan Raman,
Elena Ufimtseva
From: John Levon <levon@movementarian.org>
When the vfio-user container gets mapping updates, share them with the
vfio-user by sending a message; this can include the region fd, allowing
the server to directly mmap() the region as needed.
For performance, we only wait for the message responses when we're doing
with a series of updates via the listener_commit() callback.
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>
---
hw/vfio-user/common.c | 89 +++++++++++++++++++++++++++----
hw/vfio-user/common.h | 9 ++++
hw/vfio-user/container.c | 107 +++++++++++++++++++++++++++++++++++++-
hw/vfio-user/protocol.h | 32 ++++++++++++
hw/vfio-user/trace-events | 4 ++
5 files changed, 229 insertions(+), 12 deletions(-)
diff --git a/hw/vfio-user/common.c b/hw/vfio-user/common.c
index 160a1f0536..b78b9e57e8 100644
--- a/hw/vfio-user/common.c
+++ b/hw/vfio-user/common.c
@@ -44,7 +44,6 @@ static void vfio_user_shutdown(VFIOUserProxy *proxy);
static int vfio_user_send_qio(VFIOUserProxy *proxy, VFIOUserMsg *msg);
static VFIOUserMsg *vfio_user_getmsg(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
VFIOUserFDs *fds);
-static VFIOUserFDs *vfio_user_getfds(int numfds);
static void vfio_user_recycle(VFIOUserProxy *proxy, VFIOUserMsg *msg);
static void vfio_user_recv(void *opaque);
@@ -57,10 +56,6 @@ static void vfio_user_request(void *opaque);
static int vfio_user_send_queued(VFIOUserProxy *proxy, VFIOUserMsg *msg);
static void vfio_user_send_async(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
VFIOUserFDs *fds);
-static void vfio_user_send_wait(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
- VFIOUserFDs *fds, int rsize);
-static void vfio_user_request_msg(VFIOUserHdr *hdr, uint16_t cmd,
- uint32_t size, uint32_t flags);
static inline void vfio_user_set_error(VFIOUserHdr *hdr, uint32_t err)
{
@@ -152,7 +147,7 @@ static void vfio_user_recycle(VFIOUserProxy *proxy, VFIOUserMsg *msg)
QTAILQ_INSERT_HEAD(&proxy->free, msg, next);
}
-static VFIOUserFDs *vfio_user_getfds(int numfds)
+VFIOUserFDs *vfio_user_getfds(int numfds)
{
VFIOUserFDs *fds = g_malloc0(sizeof(*fds) + (numfds * sizeof(int)));
@@ -655,8 +650,38 @@ static void vfio_user_send_async(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
}
}
-static void vfio_user_send_wait(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
- VFIOUserFDs *fds, int rsize)
+/*
+ * nowait send - vfio_wait_reqs() can wait for it later
+ */
+void vfio_user_send_nowait(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
+ VFIOUserFDs *fds, int rsize)
+{
+ VFIOUserMsg *msg;
+ int ret;
+
+ if (hdr->flags & VFIO_USER_NO_REPLY) {
+ error_printf("vfio_user_send_nowait on async message\n");
+ return;
+ }
+
+ QEMU_LOCK_GUARD(&proxy->lock);
+
+ msg = vfio_user_getmsg(proxy, hdr, fds);
+ msg->id = hdr->id;
+ msg->rsize = rsize ? rsize : hdr->size;
+ msg->type = VFIO_MSG_NOWAIT;
+
+ ret = vfio_user_send_queued(proxy, msg);
+ if (ret < 0) {
+ vfio_user_recycle(proxy, msg);
+ return;
+ }
+
+ proxy->last_nowait = msg;
+}
+
+void vfio_user_send_wait(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
+ VFIOUserFDs *fds, int rsize)
{
VFIOUserMsg *msg;
int ret;
@@ -693,6 +718,50 @@ static void vfio_user_send_wait(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
qemu_mutex_unlock(&proxy->lock);
}
+void vfio_user_wait_reqs(VFIOUserProxy *proxy)
+{
+ VFIOUserMsg *msg;
+
+ /*
+ * Any DMA map/unmap requests sent in the middle
+ * of a memory region transaction were sent nowait.
+ * Wait for them here.
+ */
+ qemu_mutex_lock(&proxy->lock);
+ if (proxy->last_nowait != NULL) {
+ /*
+ * Change type to WAIT to wait for reply
+ */
+ msg = proxy->last_nowait;
+ msg->type = VFIO_MSG_WAIT;
+ proxy->last_nowait = NULL;
+ while (!msg->complete) {
+ if (!qemu_cond_timedwait(&msg->cv, &proxy->lock, wait_time)) {
+ VFIOUserMsgQ *list;
+
+ list = msg->pending ? &proxy->pending : &proxy->outgoing;
+ QTAILQ_REMOVE(list, msg, next);
+ error_printf("vfio_wait_reqs - timed out\n");
+ break;
+ }
+ }
+
+ if (msg->hdr->flags & VFIO_USER_ERROR) {
+ error_printf("vfio_user_wait_reqs - error reply on async ");
+ error_printf("request: command %x error %s\n", msg->hdr->command,
+ strerror(msg->hdr->error_reply));
+ }
+
+ /*
+ * Change type back to NOWAIT to free
+ */
+ msg->type = VFIO_MSG_NOWAIT;
+ vfio_user_recycle(proxy, msg);
+ }
+
+ qemu_mutex_unlock(&proxy->lock);
+}
+
static QLIST_HEAD(, VFIOUserProxy) vfio_user_sockets =
QLIST_HEAD_INITIALIZER(vfio_user_sockets);
@@ -827,8 +896,8 @@ void vfio_user_disconnect(VFIOUserProxy *proxy)
g_free(proxy);
}
-static void vfio_user_request_msg(VFIOUserHdr *hdr, uint16_t cmd,
- uint32_t size, uint32_t flags)
+void vfio_user_request_msg(VFIOUserHdr *hdr, uint16_t cmd,
+ uint32_t size, uint32_t flags)
{
static uint16_t next_id;
diff --git a/hw/vfio-user/common.h b/hw/vfio-user/common.h
index c09637dd48..f7cc02d2e7 100644
--- a/hw/vfio-user/common.h
+++ b/hw/vfio-user/common.h
@@ -65,6 +65,7 @@ typedef struct VFIOUserProxy {
QemuCond close_cv;
AioContext *ctx;
QEMUBH *req_bh;
+ bool async_ops;
/*
* above only changed when BQL is held
@@ -96,6 +97,14 @@ void vfio_user_set_handler(VFIODevice *vbasedev,
bool vfio_user_validate_version(VFIOUserProxy *proxy, Error **errp);
int vfio_user_get_info(VFIOUserProxy *proxy, struct vfio_device_info *info);
void vfio_user_reset(VFIOUserProxy *proxy);
+VFIOUserFDs *vfio_user_getfds(int numfds);
+void vfio_user_request_msg(VFIOUserHdr *hdr, uint16_t cmd,
+ uint32_t size, uint32_t flags);
+void vfio_user_wait_reqs(VFIOUserProxy *proxy);
+void vfio_user_send_nowait(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
+ VFIOUserFDs *fds, int rsize);
+void vfio_user_send_wait(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
+ VFIOUserFDs *fds, int rsize);
extern VFIODeviceIO vfio_dev_io_sock;
diff --git a/hw/vfio-user/container.c b/hw/vfio-user/container.c
index 0c487dbb92..3974bc8a8c 100644
--- a/hw/vfio-user/container.c
+++ b/hw/vfio-user/container.c
@@ -23,18 +23,119 @@
#include "qapi/error.h"
#include "trace.h"
+/*
+ * When DMA space is the physical address space, the region add/del listeners
+ * will fire during memory update transactions. These depend on BQL being held,
+ * so do any resulting map/demap ops async while keeping BQL.
+ */
+static void vfio_user_listener_begin(VFIOContainerBase *bcontainer)
+{
+ VFIOUserContainer *container = container_of(bcontainer, VFIOUserContainer,
+ bcontainer);
+
+ container->proxy->async_ops = true;
+}
+
+static void vfio_user_listener_commit(VFIOContainerBase *bcontainer)
+{
+ VFIOUserContainer *container = container_of(bcontainer, VFIOUserContainer,
+ bcontainer);
+
+ /* wait here for any async requests sent during the transaction */
+ container->proxy->async_ops = false;
+ vfio_user_wait_reqs(container->proxy);
+}
+
static int vfio_user_dma_unmap(const VFIOContainerBase *bcontainer,
hwaddr iova, ram_addr_t size,
IOMMUTLBEntry *iotlb, int flags)
{
- return -ENOTSUP;
+ VFIOUserContainer *container = container_of(bcontainer, VFIOUserContainer,
+ bcontainer);
+
+ VFIOUserDMAUnmap *msgp = g_malloc(sizeof(*msgp));
+
+ vfio_user_request_msg(&msgp->hdr, VFIO_USER_DMA_UNMAP, sizeof(*msgp), 0);
+ msgp->argsz = sizeof(struct vfio_iommu_type1_dma_unmap);
+ msgp->flags = flags;
+ msgp->iova = iova;
+ msgp->size = size;
+ trace_vfio_user_dma_unmap(msgp->iova, msgp->size, msgp->flags,
+ container->proxy->async_ops);
+
+ if (container->proxy->async_ops) {
+ vfio_user_send_nowait(container->proxy, &msgp->hdr, NULL, 0);
+ return 0;
+ }
+
+ vfio_user_send_wait(container->proxy, &msgp->hdr, NULL, 0);
+ if (msgp->hdr.flags & VFIO_USER_ERROR) {
+ return -msgp->hdr.error_reply;
+ }
+
+ g_free(msgp);
+ return 0;
}
static int vfio_user_dma_map(const VFIOContainerBase *bcontainer, hwaddr iova,
ram_addr_t size, void *vaddr, bool readonly,
MemoryRegion *mrp)
{
- return -ENOTSUP;
+ VFIOUserContainer *container = container_of(bcontainer, VFIOUserContainer,
+ bcontainer);
+
+ VFIOUserProxy *proxy = container->proxy;
+ int fd = memory_region_get_fd(mrp);
+ int ret;
+
+ VFIOUserFDs *fds = NULL;
+ VFIOUserDMAMap *msgp = g_malloc0(sizeof(*msgp));
+
+ vfio_user_request_msg(&msgp->hdr, VFIO_USER_DMA_MAP, sizeof(*msgp), 0);
+ msgp->argsz = sizeof(struct vfio_iommu_type1_dma_map);
+ msgp->flags = VFIO_DMA_MAP_FLAG_READ;
+ msgp->offset = 0;
+ msgp->iova = iova;
+ msgp->size = size;
+
+ /*
+ * vaddr enters as a QEMU process address; make it either a file offset
+ * for mapped areas or leave as 0.
+ */
+ if (fd != -1) {
+ msgp->offset = qemu_ram_block_host_offset(mrp->ram_block, vaddr);
+ }
+
+ if (!readonly) {
+ msgp->flags |= VFIO_DMA_MAP_FLAG_WRITE;
+ }
+
+ trace_vfio_user_dma_map(msgp->iova, msgp->size, msgp->offset, msgp->flags,
+ container->proxy->async_ops);
+
+ /*
+ * The async_ops case sends without blocking or dropping BQL.
+ * They're later waited for in vfio_send_wait_reqs.
+ */
+ if (container->proxy->async_ops) {
+ /* can't use auto variable since we don't block */
+ if (fd != -1) {
+ fds = vfio_user_getfds(1);
+ fds->send_fds = 1;
+ fds->fds[0] = fd;
+ }
+ vfio_user_send_nowait(proxy, &msgp->hdr, fds, 0);
+ ret = 0;
+ } else {
+ VFIOUserFDs local_fds = { 1, 0, &fd };
+
+ fds = fd != -1 ? &local_fds : NULL;
+ vfio_user_send_wait(proxy, &msgp->hdr, fds, 0);
+ ret = (msgp->hdr.flags & VFIO_USER_ERROR) ? -msgp->hdr.error_reply : 0;
+ g_free(msgp);
+ }
+
+ return ret;
}
static int
@@ -234,6 +335,8 @@ static void vfio_iommu_user_class_init(ObjectClass *klass, void *data)
VFIOIOMMUClass *vioc = VFIO_IOMMU_CLASS(klass);
vioc->setup = vfio_user_setup;
+ vioc->listener_begin = vfio_user_listener_begin,
+ vioc->listener_commit = vfio_user_listener_commit,
vioc->dma_map = vfio_user_dma_map;
vioc->dma_unmap = vfio_user_dma_unmap;
vioc->attach_device = vfio_user_attach_device;
diff --git a/hw/vfio-user/protocol.h b/hw/vfio-user/protocol.h
index 48dd475ab3..109076d820 100644
--- a/hw/vfio-user/protocol.h
+++ b/hw/vfio-user/protocol.h
@@ -113,6 +113,31 @@ typedef struct {
*/
#define VFIO_USER_DEF_MAX_BITMAP (256 * 1024 * 1024)
+/*
+ * VFIO_USER_DMA_MAP
+ * imported from struct vfio_iommu_type1_dma_map
+ */
+typedef struct {
+ VFIOUserHdr hdr;
+ uint32_t argsz;
+ uint32_t flags;
+ uint64_t offset; /* FD offset */
+ uint64_t iova;
+ uint64_t size;
+} VFIOUserDMAMap;
+
+/*
+ * VFIO_USER_DMA_UNMAP
+ * imported from struct vfio_iommu_type1_dma_unmap
+ */
+typedef struct {
+ VFIOUserHdr hdr;
+ uint32_t argsz;
+ uint32_t flags;
+ uint64_t iova;
+ uint64_t size;
+} VFIOUserDMAUnmap;
+
/*
* VFIO_USER_DEVICE_GET_INFO
* imported from struct vfio_device_info
@@ -176,4 +201,11 @@ typedef struct {
char data[];
} VFIOUserRegionRW;
+/*imported from struct vfio_bitmap */
+typedef struct {
+ uint64_t pgsize;
+ uint64_t size;
+ char data[];
+} VFIOUserBitmap;
+
#endif /* VFIO_USER_PROTOCOL_H */
diff --git a/hw/vfio-user/trace-events b/hw/vfio-user/trace-events
index 053f5932eb..7ef98813b3 100644
--- a/hw/vfio-user/trace-events
+++ b/hw/vfio-user/trace-events
@@ -11,3 +11,7 @@ vfio_user_get_region_info(uint32_t index, uint32_t flags, uint64_t size) " index
vfio_user_region_rw(uint32_t region, uint64_t off, uint32_t count) " region %d offset 0x%"PRIx64" count %d"
vfio_user_get_irq_info(uint32_t index, uint32_t flags, uint32_t count) " index %d flags 0x%x count %d"
vfio_user_set_irqs(uint32_t index, uint32_t start, uint32_t count, uint32_t flags) " index %d start %d count %d flags 0x%x"
+
+# container.c
+vfio_user_dma_map(uint64_t iova, uint64_t size, uint64_t off, uint32_t flags, bool async_ops) " iova 0x%"PRIx64" size 0x%"PRIx64" off 0x%"PRIx64" flags 0x%x async_ops %d"
+vfio_user_dma_unmap(uint64_t iova, uint64_t size, uint32_t flags, bool async_ops) " iova 0x%"PRIx64" size 0x%"PRIx64" flags 0x%x async_ops %d"
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* [PATCH v8 25/28] vfio-user: implement VFIO_USER_DMA_READ/WRITE
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (23 preceding siblings ...)
2025-02-19 14:48 ` [PATCH v8 24/28] vfio-user: implement VFIO_USER_DMA_MAP/UNMAP John Levon
@ 2025-02-19 14:48 ` John Levon
2025-02-19 14:48 ` [PATCH v8 26/28] vfio-user: add 'no-direct-dma' option John Levon
` (5 subsequent siblings)
30 siblings, 0 replies; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin, Jagannathan Raman, John Johnson,
Elena Ufimtseva
From: Jagannathan Raman <jag.raman@oracle.com>
Unlike most other messages, this is a server->client message, for when a
server wants to do "DMA"; this is slow, so normally the server has
memory directly mapped instead.
Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
---
hw/vfio-user/common.c | 57 +++++++++++++++++++++
hw/vfio-user/common.h | 3 ++
hw/vfio-user/pci.c | 110 ++++++++++++++++++++++++++++++++++++++++
hw/vfio-user/protocol.h | 13 ++++-
4 files changed, 182 insertions(+), 1 deletion(-)
diff --git a/hw/vfio-user/common.c b/hw/vfio-user/common.c
index b78b9e57e8..38f8eef317 100644
--- a/hw/vfio-user/common.c
+++ b/hw/vfio-user/common.c
@@ -377,6 +377,10 @@ static int vfio_user_recv_one(VFIOUserProxy *proxy)
*msg->hdr = hdr;
data = (char *)msg->hdr + sizeof(hdr);
} else {
+ if (hdr.size > proxy->max_xfer_size + sizeof(VFIOUserDMARW)) {
+ error_setg(&local_err, "vfio_user_recv request larger than max");
+ goto err;
+ }
buf = g_malloc0(hdr.size);
memcpy(buf, &hdr, sizeof(hdr));
data = buf + sizeof(hdr);
@@ -762,6 +766,59 @@ void vfio_user_wait_reqs(VFIOUserProxy *proxy)
qemu_mutex_unlock(&proxy->lock);
}
+/*
+ * Reply to an incoming request.
+ */
+void vfio_user_send_reply(VFIOUserProxy *proxy, VFIOUserHdr *hdr, int size)
+{
+
+ if (size < sizeof(VFIOUserHdr)) {
+ error_printf("vfio_user_send_reply - size too small\n");
+ g_free(hdr);
+ return;
+ }
+
+ /*
+ * convert header to associated reply
+ */
+ hdr->flags = VFIO_USER_REPLY;
+ hdr->size = size;
+
+ vfio_user_send_async(proxy, hdr, NULL);
+}
+
+/*
+ * Send an error reply to an incoming request.
+ */
+void vfio_user_send_error(VFIOUserProxy *proxy, VFIOUserHdr *hdr, int error)
+{
+
+ /*
+ * convert header to associated reply
+ */
+ hdr->flags = VFIO_USER_REPLY;
+ hdr->flags |= VFIO_USER_ERROR;
+ hdr->error_reply = error;
+ hdr->size = sizeof(*hdr);
+
+ vfio_user_send_async(proxy, hdr, NULL);
+}
+
+/*
+ * Close FDs erroneously received in an incoming request.
+ */
+void vfio_user_putfds(VFIOUserMsg *msg)
+{
+ VFIOUserFDs *fds = msg->fds;
+ int i;
+
+ for (i = 0; i < fds->recv_fds; i++) {
+ close(fds->fds[i]);
+ }
+ g_free(fds);
+ msg->fds = NULL;
+}
+
static QLIST_HEAD(, VFIOUserProxy) vfio_user_sockets =
QLIST_HEAD_INITIALIZER(vfio_user_sockets);
diff --git a/hw/vfio-user/common.h b/hw/vfio-user/common.h
index f7cc02d2e7..f8c61f2128 100644
--- a/hw/vfio-user/common.h
+++ b/hw/vfio-user/common.h
@@ -105,6 +105,9 @@ void vfio_user_send_nowait(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
VFIOUserFDs *fds, int rsize);
void vfio_user_send_wait(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
VFIOUserFDs *fds, int rsize);
+void vfio_user_send_reply(VFIOUserProxy *proxy, VFIOUserHdr *hdr, int size);
+void vfio_user_send_error(VFIOUserProxy *proxy, VFIOUserHdr *hdr, int error);
+void vfio_user_putfds(VFIOUserMsg *msg);
extern VFIODeviceIO vfio_dev_io_sock;
diff --git a/hw/vfio-user/pci.c b/hw/vfio-user/pci.c
index d520b7592b..e65c7eaf02 100644
--- a/hw/vfio-user/pci.c
+++ b/hw/vfio-user/pci.c
@@ -96,6 +96,95 @@ static void vfio_user_msix_teardown(VFIOPCIDevice *vdev)
vdev->msix->pba_region = NULL;
}
+static void vfio_user_dma_read(VFIOPCIDevice *vdev, VFIOUserDMARW *msg)
+{
+ PCIDevice *pdev = &vdev->pdev;
+ VFIOUserProxy *proxy = vdev->vbasedev.proxy;
+ VFIOUserDMARW *res;
+ MemTxResult r;
+ size_t size;
+
+ if (msg->hdr.size < sizeof(*msg)) {
+ vfio_user_send_error(proxy, &msg->hdr, EINVAL);
+ return;
+ }
+ if (msg->count > proxy->max_xfer_size) {
+ vfio_user_send_error(proxy, &msg->hdr, E2BIG);
+ return;
+ }
+
+ /* switch to our own message buffer */
+ size = msg->count + sizeof(VFIOUserDMARW);
+ res = g_malloc0(size);
+ memcpy(res, msg, sizeof(*res));
+ g_free(msg);
+
+ r = pci_dma_read(pdev, res->offset, &res->data, res->count);
+
+ switch (r) {
+ case MEMTX_OK:
+ if (res->hdr.flags & VFIO_USER_NO_REPLY) {
+ g_free(res);
+ return;
+ }
+ vfio_user_send_reply(proxy, &res->hdr, size);
+ break;
+ case MEMTX_ERROR:
+ vfio_user_send_error(proxy, &res->hdr, EFAULT);
+ break;
+ case MEMTX_DECODE_ERROR:
+ vfio_user_send_error(proxy, &res->hdr, ENODEV);
+ break;
+ case MEMTX_ACCESS_ERROR:
+ vfio_user_send_error(proxy, &res->hdr, EPERM);
+ break;
+ default:
+ error_printf("vfio_user_dma_read unknown error %d\n", r);
+ vfio_user_send_error(vdev->vbasedev.proxy, &res->hdr, EINVAL);
+ }
+}
+
+static void vfio_user_dma_write(VFIOPCIDevice *vdev, VFIOUserDMARW *msg)
+{
+ PCIDevice *pdev = &vdev->pdev;
+ VFIOUserProxy *proxy = vdev->vbasedev.proxy;
+ MemTxResult r;
+
+ if (msg->hdr.size < sizeof(*msg)) {
+ vfio_user_send_error(proxy, &msg->hdr, EINVAL);
+ return;
+ }
+ /* make sure transfer count isn't larger than the message data */
+ if (msg->count > msg->hdr.size - sizeof(*msg)) {
+ vfio_user_send_error(proxy, &msg->hdr, E2BIG);
+ return;
+ }
+
+ r = pci_dma_write(pdev, msg->offset, &msg->data, msg->count);
+
+ switch (r) {
+ case MEMTX_OK:
+ if ((msg->hdr.flags & VFIO_USER_NO_REPLY) == 0) {
+ vfio_user_send_reply(proxy, &msg->hdr, sizeof(msg->hdr));
+ } else {
+ g_free(msg);
+ }
+ break;
+ case MEMTX_ERROR:
+ vfio_user_send_error(proxy, &msg->hdr, EFAULT);
+ break;
+ case MEMTX_DECODE_ERROR:
+ vfio_user_send_error(proxy, &msg->hdr, ENODEV);
+ break;
+ case MEMTX_ACCESS_ERROR:
+ vfio_user_send_error(proxy, &msg->hdr, EPERM);
+ break;
+ default:
+ error_printf("vfio_user_dma_write unknown error %d\n", r);
+ vfio_user_send_error(vdev->vbasedev.proxy, &msg->hdr, EINVAL);
+ }
+}
+
/*
* Incoming request message callback.
*
@@ -103,7 +192,28 @@ static void vfio_user_msix_teardown(VFIOPCIDevice *vdev)
*/
static void vfio_user_pci_process_req(void *opaque, VFIOUserMsg *msg)
{
+ VFIOPCIDevice *vdev = opaque;
+ VFIOUserHdr *hdr = msg->hdr;
+
+ /* no incoming PCI requests pass FDs */
+ if (msg->fds != NULL) {
+ vfio_user_send_error(vdev->vbasedev.proxy, hdr, EINVAL);
+ vfio_user_putfds(msg);
+ return;
+ }
+ switch (hdr->command) {
+ case VFIO_USER_DMA_READ:
+ vfio_user_dma_read(vdev, (VFIOUserDMARW *)hdr);
+ break;
+ case VFIO_USER_DMA_WRITE:
+ vfio_user_dma_write(vdev, (VFIOUserDMARW *)hdr);
+ break;
+ default:
+ error_printf("vfio_user_pci_process_req unknown cmd %d\n",
+ hdr->command);
+ vfio_user_send_error(vdev->vbasedev.proxy, hdr, ENOSYS);
+ }
}
/*
diff --git a/hw/vfio-user/protocol.h b/hw/vfio-user/protocol.h
index 109076d820..6bc5809cce 100644
--- a/hw/vfio-user/protocol.h
+++ b/hw/vfio-user/protocol.h
@@ -201,7 +201,18 @@ typedef struct {
char data[];
} VFIOUserRegionRW;
-/*imported from struct vfio_bitmap */
+/*
+ * VFIO_USER_DMA_READ
+ * VFIO_USER_DMA_WRITE
+ */
+typedef struct {
+ VFIOUserHdr hdr;
+ uint64_t offset;
+ uint32_t count;
+ char data[];
+} VFIOUserDMARW;
+
+/* imported from struct vfio_bitmap */
typedef struct {
uint64_t pgsize;
uint64_t size;
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* [PATCH v8 26/28] vfio-user: add 'no-direct-dma' option
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (24 preceding siblings ...)
2025-02-19 14:48 ` [PATCH v8 25/28] vfio-user: implement VFIO_USER_DMA_READ/WRITE John Levon
@ 2025-02-19 14:48 ` John Levon
2025-02-19 14:48 ` [PATCH v8 27/28] vfio-user: add 'x-msg-timeout' option John Levon
` (4 subsequent siblings)
30 siblings, 0 replies; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin, Jagannathan Raman, John Johnson,
Elena Ufimtseva
From: Jagannathan Raman <jag.raman@oracle.com>
Normally, the vfio-user client will share a region's file descriptor
with the server to allow it directly mmap() the region memory. Add an
option to disable this, so the server must use
VFIO_USER_REGION_READ/WRITE instead.
FIXME: doesn't actually stop sending the fd??
Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
---
hw/vfio-user/common.h | 1 +
hw/vfio-user/container.c | 2 +-
hw/vfio-user/pci.c | 5 +++++
3 files changed, 7 insertions(+), 1 deletion(-)
diff --git a/hw/vfio-user/common.h b/hw/vfio-user/common.h
index f8c61f2128..72138220ba 100644
--- a/hw/vfio-user/common.h
+++ b/hw/vfio-user/common.h
@@ -84,6 +84,7 @@ typedef struct VFIOUserProxy {
/* VFIOProxy flags */
#define VFIO_PROXY_CLIENT 0x1
+#define VFIO_PROXY_NO_MMAP 0x2
#define VFIO_PROXY_FORCE_QUEUED 0x4
#define VFIO_PROXY_NO_POST 0x8
diff --git a/hw/vfio-user/container.c b/hw/vfio-user/container.c
index 3974bc8a8c..3880316238 100644
--- a/hw/vfio-user/container.c
+++ b/hw/vfio-user/container.c
@@ -102,7 +102,7 @@ static int vfio_user_dma_map(const VFIOContainerBase *bcontainer, hwaddr iova,
* vaddr enters as a QEMU process address; make it either a file offset
* for mapped areas or leave as 0.
*/
- if (fd != -1) {
+ if (fd != -1 && !(container->proxy->flags & VFIO_PROXY_NO_MMAP)) {
msgp->offset = qemu_ram_block_host_offset(mrp->ram_block, vaddr);
}
diff --git a/hw/vfio-user/pci.c b/hw/vfio-user/pci.c
index e65c7eaf02..8a05e69a46 100644
--- a/hw/vfio-user/pci.c
+++ b/hw/vfio-user/pci.c
@@ -36,6 +36,7 @@ OBJECT_DECLARE_SIMPLE_TYPE(VFIOUserPCIDevice, VFIO_USER_PCI)
struct VFIOUserPCIDevice {
VFIOPCIDevice device;
char *sock_name;
+ bool no_direct_dma; /* disable shared mem for DMA */
bool send_queued; /* all sends are queued */
bool no_post; /* all regions write are sync */
};
@@ -264,6 +265,9 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
vbasedev->proxy = proxy;
vfio_user_set_handler(vbasedev, vfio_user_pci_process_req, vdev);
+ if (udev->no_direct_dma) {
+ proxy->flags |= VFIO_PROXY_NO_MMAP;
+ }
if (udev->send_queued) {
proxy->flags |= VFIO_PROXY_FORCE_QUEUED;
}
@@ -402,6 +406,7 @@ static void vfio_user_pci_reset(DeviceState *dev)
static const Property vfio_user_pci_dev_properties[] = {
DEFINE_PROP_STRING("socket", VFIOUserPCIDevice, sock_name),
+ DEFINE_PROP_BOOL("no-direct-dma", VFIOUserPCIDevice, no_direct_dma, false),
DEFINE_PROP_BOOL("x-send-queued", VFIOUserPCIDevice, send_queued, false),
DEFINE_PROP_BOOL("x-no-posted-writes", VFIOUserPCIDevice, no_post, false),
};
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* [PATCH v8 27/28] vfio-user: add 'x-msg-timeout' option
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (25 preceding siblings ...)
2025-02-19 14:48 ` [PATCH v8 26/28] vfio-user: add 'no-direct-dma' option John Levon
@ 2025-02-19 14:48 ` John Levon
2025-02-19 14:48 ` [PATCH v8 28/28] vfio-user: add coalesced posted writes John Levon
` (3 subsequent siblings)
30 siblings, 0 replies; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin, Jagannathan Raman, John Johnson,
Elena Ufimtseva
From: Jagannathan Raman <jag.raman@oracle.com>
By default, the vfio-user subsystem will wait 5 seconds for a message
reply from the server. Add an option to allow this to be configurable.
Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
---
hw/vfio-user/common.c | 7 ++++---
hw/vfio-user/common.h | 1 +
hw/vfio-user/pci.c | 4 ++++
3 files changed, 9 insertions(+), 3 deletions(-)
diff --git a/hw/vfio-user/common.c b/hw/vfio-user/common.c
index 38f8eef317..e44c8a2568 100644
--- a/hw/vfio-user/common.c
+++ b/hw/vfio-user/common.c
@@ -37,7 +37,6 @@
#define VFIO_USER_MAX_REGIONS 100
#define VFIO_USER_MAX_IRQS 50
-static int wait_time = 5000; /* wait up to 5 sec for busy servers */
static IOThread *vfio_user_iothread;
static void vfio_user_shutdown(VFIOUserProxy *proxy);
@@ -707,7 +706,8 @@ void vfio_user_send_wait(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
if (ret == 0) {
while (!msg->complete) {
- if (!qemu_cond_timedwait(&msg->cv, &proxy->lock, wait_time)) {
+ if (!qemu_cond_timedwait(&msg->cv, &proxy->lock,
+ proxy->wait_time)) {
VFIOUserMsgQ *list;
list = msg->pending ? &proxy->pending : &proxy->outgoing;
@@ -740,7 +740,8 @@ void vfio_user_wait_reqs(VFIOUserProxy *proxy)
msg->type = VFIO_MSG_WAIT;
proxy->last_nowait = NULL;
while (!msg->complete) {
- if (!qemu_cond_timedwait(&msg->cv, &proxy->lock, wait_time)) {
+ if (!qemu_cond_timedwait(&msg->cv, &proxy->lock,
+ proxy->wait_time)) {
VFIOUserMsgQ *list;
list = msg->pending ? &proxy->pending : &proxy->outgoing;
diff --git a/hw/vfio-user/common.h b/hw/vfio-user/common.h
index 72138220ba..9acf634ca7 100644
--- a/hw/vfio-user/common.h
+++ b/hw/vfio-user/common.h
@@ -62,6 +62,7 @@ typedef struct VFIOUserProxy {
uint64_t max_bitmap;
uint64_t migr_pgsize;
int flags;
+ uint32_t wait_time;
QemuCond close_cv;
AioContext *ctx;
QEMUBH *req_bh;
diff --git a/hw/vfio-user/pci.c b/hw/vfio-user/pci.c
index 8a05e69a46..fe096cc7a2 100644
--- a/hw/vfio-user/pci.c
+++ b/hw/vfio-user/pci.c
@@ -39,6 +39,7 @@ struct VFIOUserPCIDevice {
bool no_direct_dma; /* disable shared mem for DMA */
bool send_queued; /* all sends are queued */
bool no_post; /* all regions write are sync */
+ uint32_t wait_time; /* timeout for message replies */
};
/*
@@ -274,6 +275,8 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
if (udev->no_post) {
proxy->flags |= VFIO_PROXY_NO_POST;
}
+ /* user specified or 5 sec default */
+ proxy->wait_time = udev->wait_time;
if (!vfio_user_validate_version(proxy, errp)) {
goto error;
@@ -409,6 +412,7 @@ static const Property vfio_user_pci_dev_properties[] = {
DEFINE_PROP_BOOL("no-direct-dma", VFIOUserPCIDevice, no_direct_dma, false),
DEFINE_PROP_BOOL("x-send-queued", VFIOUserPCIDevice, send_queued, false),
DEFINE_PROP_BOOL("x-no-posted-writes", VFIOUserPCIDevice, no_post, false),
+ DEFINE_PROP_UINT32("x-msg-timeout", VFIOUserPCIDevice, wait_time, 5000),
};
static void vfio_user_pci_dev_class_init(ObjectClass *klass, void *data)
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* [PATCH v8 28/28] vfio-user: add coalesced posted writes
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (26 preceding siblings ...)
2025-02-19 14:48 ` [PATCH v8 27/28] vfio-user: add 'x-msg-timeout' option John Levon
@ 2025-02-19 14:48 ` John Levon
2025-02-28 17:09 ` [PATCH v8 00/28] vfio-user client Jag Raman
` (2 subsequent siblings)
30 siblings, 0 replies; 64+ messages in thread
From: John Levon @ 2025-02-19 14:48 UTC (permalink / raw)
To: qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, John Levon, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand,
Cédric Le Goater, Peter Xu, Philippe Mathieu-Daudé,
Michael S. Tsirkin, Jagannathan Raman, John Johnson,
Elena Ufimtseva
From: Jagannathan Raman <jag.raman@oracle.com>
Add new message to send multiple writes to server in a single message.
Prevents the outgoing queue from overflowing when a long latency
operation is followed by a series of posted writes.
Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
---
hw/vfio-user/common.c | 131 +++++++++++++++++++++++++++++++++++++-
hw/vfio-user/common.h | 7 ++
hw/vfio-user/protocol.h | 21 ++++++
hw/vfio-user/trace-events | 1 +
4 files changed, 158 insertions(+), 2 deletions(-)
diff --git a/hw/vfio-user/common.c b/hw/vfio-user/common.c
index e44c8a2568..809c8e6614 100644
--- a/hw/vfio-user/common.c
+++ b/hw/vfio-user/common.c
@@ -20,6 +20,7 @@
#include "io/channel-socket.h"
#include "io/channel-util.h"
#include "qapi/error.h"
+#include "qobject/qbool.h"
#include "qobject/qdict.h"
#include "qobject/qjson.h"
#include "qobject/qstring.h"
@@ -55,6 +56,7 @@ static void vfio_user_request(void *opaque);
static int vfio_user_send_queued(VFIOUserProxy *proxy, VFIOUserMsg *msg);
static void vfio_user_send_async(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
VFIOUserFDs *fds);
+static void vfio_user_flush_multi(VFIOUserProxy *proxy);
static inline void vfio_user_set_error(VFIOUserHdr *hdr, uint32_t err)
{
@@ -459,6 +461,11 @@ static void vfio_user_send(void *opaque)
}
qio_channel_set_aio_fd_handler(proxy->ioc, proxy->ctx,
vfio_user_recv, NULL, NULL, proxy);
+
+ /* queue empty - send any pending multi write msgs */
+ if (proxy->wr_multi != NULL) {
+ vfio_user_flush_multi(proxy);
+ }
}
}
@@ -479,6 +486,7 @@ static int vfio_user_send_one(VFIOUserProxy *proxy)
}
QTAILQ_REMOVE(&proxy->outgoing, msg, next);
+ proxy->num_outgoing--;
if (msg->type == VFIO_MSG_ASYNC) {
vfio_user_recycle(proxy, msg);
} else {
@@ -586,11 +594,18 @@ static int vfio_user_send_queued(VFIOUserProxy *proxy, VFIOUserMsg *msg)
{
int ret;
+ /* older coalesced writes go first */
+ if (proxy->wr_multi != NULL &&
+ ((msg->hdr->flags & VFIO_USER_TYPE) == VFIO_USER_REQUEST)) {
+ vfio_user_flush_multi(proxy);
+ }
+
/*
* Unsent outgoing msgs - add to tail
*/
if (!QTAILQ_EMPTY(&proxy->outgoing)) {
QTAILQ_INSERT_TAIL(&proxy->outgoing, msg, next);
+ proxy->num_outgoing++;
return 0;
}
@@ -604,6 +619,7 @@ static int vfio_user_send_queued(VFIOUserProxy *proxy, VFIOUserMsg *msg)
}
if (ret == QIO_CHANNEL_ERR_BLOCK) {
QTAILQ_INSERT_HEAD(&proxy->outgoing, msg, next);
+ proxy->num_outgoing = 1;
qio_channel_set_aio_fd_handler(proxy->ioc, proxy->ctx,
vfio_user_recv, proxy->ctx,
vfio_user_send, proxy);
@@ -1119,12 +1135,27 @@ static bool check_migr(VFIOUserProxy *proxy, QObject *qobj, Error **errp)
return caps_parse(proxy, qdict, caps_migr, errp);
}
+static bool check_multi(VFIOUserProxy *proxy, QObject *qobj, Error **errp)
+{
+ QBool *qb = qobject_to(QBool, qobj);
+
+ if (qb == NULL) {
+ error_setg(errp, "malformed %s", VFIO_USER_CAP_MULTI);
+ return false;
+ }
+ if (qbool_get_bool(qb)) {
+ proxy->flags |= VFIO_PROXY_USE_MULTI;
+ }
+ return true;
+}
+
static struct cap_entry caps_cap[] = {
{ VFIO_USER_CAP_MAX_FDS, check_max_fds },
{ VFIO_USER_CAP_MAX_XFER, check_max_xfer },
{ VFIO_USER_CAP_PGSIZES, check_pgsizes },
{ VFIO_USER_CAP_MAP_MAX, check_max_dma },
{ VFIO_USER_CAP_MIGR, check_migr },
+ { VFIO_USER_CAP_MULTI, check_multi },
{ NULL }
};
@@ -1183,6 +1214,7 @@ static GString *caps_json(void)
qdict_put_int(capdict, VFIO_USER_CAP_MAX_XFER, VFIO_USER_DEF_MAX_XFER);
qdict_put_int(capdict, VFIO_USER_CAP_PGSIZES, VFIO_USER_DEF_PGSIZE);
qdict_put_int(capdict, VFIO_USER_CAP_MAP_MAX, VFIO_USER_DEF_MAP_MAX);
+ qdict_put_bool(capdict, VFIO_USER_CAP_MULTI, true);
qdict_put_obj(dict, VFIO_USER_CAP, QOBJECT(capdict));
@@ -1451,19 +1483,114 @@ static int vfio_user_region_read(VFIOUserProxy *proxy, uint8_t index,
return msgp->count;
}
+static void vfio_user_flush_multi(VFIOUserProxy *proxy)
+{
+ VFIOUserMsg *msg;
+ VFIOUserWRMulti *wm = proxy->wr_multi;
+ int ret;
+
+ proxy->wr_multi = NULL;
+
+ /* adjust size for actual # of writes */
+ wm->hdr.size -= (VFIO_USER_MULTI_MAX - wm->wr_cnt) * sizeof(VFIOUserWROne);
+
+ msg = vfio_user_getmsg(proxy, &wm->hdr, NULL);
+ msg->id = wm->hdr.id;
+ msg->rsize = 0;
+ msg->type = VFIO_MSG_ASYNC;
+ trace_vfio_user_wrmulti("flush", wm->wr_cnt);
+
+ ret = vfio_user_send_queued(proxy, msg);
+ if (ret < 0) {
+ vfio_user_recycle(proxy, msg);
+ }
+}
+
+static void vfio_user_create_multi(VFIOUserProxy *proxy)
+{
+ VFIOUserWRMulti *wm;
+
+ wm = g_malloc0(sizeof(*wm));
+ vfio_user_request_msg(&wm->hdr, VFIO_USER_REGION_WRITE_MULTI,
+ sizeof(*wm), VFIO_USER_NO_REPLY);
+ proxy->wr_multi = wm;
+}
+
+static void vfio_user_add_multi(VFIOUserProxy *proxy, uint8_t index,
+ off_t offset, uint32_t count, void *data)
+{
+ VFIOUserWRMulti *wm = proxy->wr_multi;
+ VFIOUserWROne *w1 = &wm->wrs[wm->wr_cnt];
+
+ w1->offset = offset;
+ w1->region = index;
+ w1->count = count;
+ memcpy(&w1->data, data, count);
+
+ wm->wr_cnt++;
+ trace_vfio_user_wrmulti("add", wm->wr_cnt);
+ if (wm->wr_cnt == VFIO_USER_MULTI_MAX ||
+ proxy->num_outgoing < VFIO_USER_OUT_LOW) {
+ vfio_user_flush_multi(proxy);
+ }
+}
+
static int vfio_user_region_write(VFIOUserProxy *proxy, uint8_t index,
off_t offset, uint32_t count, void *data,
bool post)
{
VFIOUserRegionRW *msgp = NULL;
- int flags = post ? VFIO_USER_NO_REPLY : 0;
+ int flags;
int size = sizeof(*msgp) + count;
+ bool can_multi;
int ret;
if (count > proxy->max_xfer_size) {
return -EINVAL;
}
+ if (proxy->flags & VFIO_PROXY_NO_POST) {
+ post = false;
+ }
+
+ /* write eligible to be in a WRITE_MULTI msg ? */
+ can_multi = (proxy->flags & VFIO_PROXY_USE_MULTI) && post &&
+ count <= VFIO_USER_MULTI_DATA;
+
+ /*
+ * This should be a rare case, so first check without the lock,
+ * if we're wrong, vfio_send_queued() will flush any posted writes
+ * we missed here
+ */
+ if (proxy->wr_multi != NULL ||
+ (proxy->num_outgoing > VFIO_USER_OUT_HIGH && can_multi)) {
+
+ /*
+ * re-check with lock
+ *
+ * if already building a WRITE_MULTI msg,
+ * add this one if possible else flush pending before
+ * sending the current one
+ *
+ * else if outgoing queue is over the highwater,
+ * start a new WRITE_MULTI message
+ */
+ WITH_QEMU_LOCK_GUARD(&proxy->lock) {
+ if (proxy->wr_multi != NULL) {
+ if (can_multi) {
+ vfio_user_add_multi(proxy, index, offset, count, data);
+ return count;
+ }
+ vfio_user_flush_multi(proxy);
+ } else if (proxy->num_outgoing > VFIO_USER_OUT_HIGH && can_multi) {
+ vfio_user_create_multi(proxy);
+ vfio_user_add_multi(proxy, index, offset, count, data);
+ return count;
+ }
+ }
+ }
+
+ flags = post ? VFIO_USER_NO_REPLY : 0;
msgp = g_malloc0(size);
vfio_user_request_msg(&msgp->hdr, VFIO_USER_REGION_WRITE, size, flags);
msgp->offset = offset;
@@ -1473,7 +1600,7 @@ static int vfio_user_region_write(VFIOUserProxy *proxy, uint8_t index,
trace_vfio_user_region_rw(msgp->region, msgp->offset, msgp->count);
/* async send will free msg after it's sent */
- if (post && !(proxy->flags & VFIO_PROXY_NO_POST)) {
+ if (post) {
vfio_user_send_async(proxy, &msgp->hdr, NULL);
return count;
}
diff --git a/hw/vfio-user/common.h b/hw/vfio-user/common.h
index 9acf634ca7..96efc32bd7 100644
--- a/hw/vfio-user/common.h
+++ b/hw/vfio-user/common.h
@@ -80,6 +80,8 @@ typedef struct VFIOUserProxy {
VFIOUserMsg *last_nowait;
VFIOUserMsg *part_recv;
size_t recv_left;
+ VFIOUserWRMulti *wr_multi;
+ int num_outgoing;
enum proxy_state state;
} VFIOUserProxy;
@@ -88,6 +90,11 @@ typedef struct VFIOUserProxy {
#define VFIO_PROXY_NO_MMAP 0x2
#define VFIO_PROXY_FORCE_QUEUED 0x4
#define VFIO_PROXY_NO_POST 0x8
+#define VFIO_PROXY_USE_MULTI 0x10
+
+/* coalescing high and low water marks for VFIOProxy num_outgoing */
+#define VFIO_USER_OUT_HIGH 1024
+#define VFIO_USER_OUT_LOW 128
typedef struct VFIODevice VFIODevice;
diff --git a/hw/vfio-user/protocol.h b/hw/vfio-user/protocol.h
index 6bc5809cce..98cd0e1920 100644
--- a/hw/vfio-user/protocol.h
+++ b/hw/vfio-user/protocol.h
@@ -40,6 +40,7 @@ enum vfio_user_command {
VFIO_USER_DMA_WRITE = 12,
VFIO_USER_DEVICE_RESET = 13,
VFIO_USER_DIRTY_PAGES = 14,
+ VFIO_USER_REGION_WRITE_MULTI = 15,
VFIO_USER_MAX,
};
@@ -73,6 +74,7 @@ typedef struct {
#define VFIO_USER_CAP_PGSIZES "pgsizes"
#define VFIO_USER_CAP_MAP_MAX "max_dma_maps"
#define VFIO_USER_CAP_MIGR "migration"
+#define VFIO_USER_CAP_MULTI "write_multiple"
/* "migration" members */
#define VFIO_USER_CAP_PGSIZE "pgsize"
@@ -219,4 +221,23 @@ typedef struct {
char data[];
} VFIOUserBitmap;
+/*
+ * VFIO_USER_REGION_WRITE_MULTI
+ */
+#define VFIO_USER_MULTI_DATA 8
+#define VFIO_USER_MULTI_MAX 200
+
+typedef struct {
+ uint64_t offset;
+ uint32_t region;
+ uint32_t count;
+ char data[VFIO_USER_MULTI_DATA];
+} VFIOUserWROne;
+
+typedef struct {
+ VFIOUserHdr hdr;
+ uint64_t wr_cnt;
+ VFIOUserWROne wrs[VFIO_USER_MULTI_MAX];
+} VFIOUserWRMulti;
+
#endif /* VFIO_USER_PROTOCOL_H */
diff --git a/hw/vfio-user/trace-events b/hw/vfio-user/trace-events
index 7ef98813b3..64fac9137f 100644
--- a/hw/vfio-user/trace-events
+++ b/hw/vfio-user/trace-events
@@ -11,6 +11,7 @@ vfio_user_get_region_info(uint32_t index, uint32_t flags, uint64_t size) " index
vfio_user_region_rw(uint32_t region, uint64_t off, uint32_t count) " region %d offset 0x%"PRIx64" count %d"
vfio_user_get_irq_info(uint32_t index, uint32_t flags, uint32_t count) " index %d flags 0x%x count %d"
vfio_user_set_irqs(uint32_t index, uint32_t start, uint32_t count, uint32_t flags) " index %d start %d count %d flags 0x%x"
+vfio_user_wrmulti(const char *s, uint64_t wr_cnt) " %s count 0x%"PRIx64
# container.c
vfio_user_dma_map(uint64_t iova, uint64_t size, uint64_t off, uint32_t flags, bool async_ops) " iova 0x%"PRIx64" size 0x%"PRIx64" off 0x%"PRIx64" flags 0x%x async_ops %d"
--
2.34.1
^ permalink raw reply related [flat|nested] 64+ messages in thread* Re: [PATCH v8 00/28] vfio-user client
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (27 preceding siblings ...)
2025-02-19 14:48 ` [PATCH v8 28/28] vfio-user: add coalesced posted writes John Levon
@ 2025-02-28 17:09 ` Jag Raman
2025-03-03 11:19 ` John Levon
2025-03-14 14:25 ` Cédric Le Goater
2025-04-04 17:21 ` Cédric Le Goater
30 siblings, 1 reply; 64+ messages in thread
From: Jag Raman @ 2025-02-28 17:09 UTC (permalink / raw)
To: John Levon
Cc: qemu-devel@nongnu.org, Jason Herne, Thanos Makatos, Halil Pasic,
Daniel P. Berrangé, Eric Farman, Tony Krowiak, Thomas Huth,
qemu-s390x@nongnu.org, Matthew Rosato, Paolo Bonzini,
Marc-André Lureau, Stefano Garzarella, Alex Williamson,
David Hildenbrand, Cédric Le Goater, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin
I appreciate you posting the patches. I didn't author the patches, actually; John Johnson did it.
You could use your name as the author since you should be familiar with it now, and I can review the patches.
Please add the following to each patch so it recognizes Oracle's contribution:
Co-authored-by: John Johnson <john.g.johnson@oracle.com>
Thank you so much!
> On Feb 19, 2025, at 9:48 AM, John Levon <john.levon@nutanix.com> wrote:
>
> This is the 8th revision of the vfio-user client implementation. The vfio-user
> protocol allows for implementing (PCI) devices in another userspace process;
> SPDK is one example, which includes a virtual NVMe implementation.
>
> The vfio-user framework consists of 3 parts:
> 1) The VFIO user protocol specification.
> 2) A client - the VFIO device in QEMU that encapsulates VFIO messages
> and sends them to the server.
> 3) A server - a remote process that emulates a device.
>
> This patchset implements parts 1 and 2.
>
> It has been tested against libvfio-user test servers as well as SPDK.
>
> Thanks for previous reviews & comments.
>
> Changes since v7:
>
> - split up pci patches for easier reviewing
> - fixed lots of device ops error handling
> - vfio-user code now in hw/vfio-user
> - improved commit messages
> - various other small cleanups
>
> Jagannathan Raman (20):
> vfio/container: pass MemoryRegion to DMA operations
> vfio: add region cache
> vfio: split out VFIOKernelPCIDevice
> vfio: add device IO ops vector
> vfio-user: add vfio-user class and container
> vfio-user: connect vfio proxy to remote server
> vfio-user: implement message receive infrastructure
> vfio-user: implement message send infrastructure
> vfio-user: implement VFIO_USER_DEVICE_GET_INFO
> vfio-user: implement VFIO_USER_DEVICE_GET_REGION_INFO
> vfio-user: implement VFIO_USER_REGION_READ/WRITE
> vfio-user: set up PCI in vfio_user_pci_realize()
> vfio-user: implement VFIO_USER_DEVICE_GET/SET_IRQ*
> vfio-user: forward MSI-X PBA BAR accesses to server
> vfio-user: set up container access to the proxy
> vfio-user: implement VFIO_USER_DEVICE_RESET
> vfio-user: implement VFIO_USER_DMA_READ/WRITE
> vfio-user: add 'no-direct-dma' option
> vfio-user: add 'x-msg-timeout' option
> vfio-user: add coalesced posted writes
>
> John Levon (7):
> vfio/container: pass listener_begin/commit callbacks
> vfio/container: support VFIO_DMA_UNMAP_FLAG_ALL
> vfio: add vfio_attach_device_by_iommu_type()
> vfio: add vfio_prepare_device()
> vfio: refactor out vfio_interrupt_setup()
> vfio: refactor out vfio_pci_config_setup()
> vfio-user: implement VFIO_USER_DMA_MAP/UNMAP
>
> Thanos Makatos (1):
> vfio-user: introduce vfio-user protocol specification
>
> MAINTAINERS | 10 +-
> docs/devel/index-internals.rst | 1 +
> docs/devel/vfio-user.rst | 1522 ++++++++++++++++++++++
> hw/meson.build | 1 +
> hw/vfio-user/common.c | 1702 +++++++++++++++++++++++++
> hw/vfio-user/common.h | 123 ++
> hw/vfio-user/container.c | 358 ++++++
> hw/vfio-user/container.h | 24 +
> hw/vfio-user/meson.build | 10 +
> hw/vfio-user/pci.c | 443 +++++++
> hw/vfio-user/protocol.h | 243 ++++
> hw/vfio-user/trace-events | 18 +
> hw/vfio-user/trace.h | 1 +
> hw/vfio/ap.c | 4 +-
> hw/vfio/ccw.c | 9 +-
> hw/vfio/common.c | 137 +-
> hw/vfio/container-base.c | 8 +-
> hw/vfio/container.c | 78 +-
> hw/vfio/helpers.c | 185 ++-
> hw/vfio/igd.c | 8 +-
> hw/vfio/iommufd.c | 31 +-
> hw/vfio/pci.c | 591 +++++----
> hw/vfio/pci.h | 34 +-
> hw/vfio/platform.c | 4 +-
> hw/virtio/vhost-vdpa.c | 2 +-
> include/exec/memory.h | 4 +-
> include/hw/vfio/vfio-common.h | 45 +-
> include/hw/vfio/vfio-container-base.h | 11 +-
> meson.build | 1 +
> meson_options.txt | 2 +
> scripts/meson-buildoptions.sh | 4 +
> system/memory.c | 7 +-
> 32 files changed, 5281 insertions(+), 340 deletions(-)
> create mode 100644 docs/devel/vfio-user.rst
> create mode 100644 hw/vfio-user/common.c
> create mode 100644 hw/vfio-user/common.h
> create mode 100644 hw/vfio-user/container.c
> create mode 100644 hw/vfio-user/container.h
> create mode 100644 hw/vfio-user/meson.build
> create mode 100644 hw/vfio-user/pci.c
> create mode 100644 hw/vfio-user/protocol.h
> create mode 100644 hw/vfio-user/trace-events
> create mode 100644 hw/vfio-user/trace.h
>
> --
> 2.34.1
>
>
^ permalink raw reply [flat|nested] 64+ messages in thread* Re: [PATCH v8 00/28] vfio-user client
2025-02-28 17:09 ` [PATCH v8 00/28] vfio-user client Jag Raman
@ 2025-03-03 11:19 ` John Levon
2025-03-03 15:39 ` Jag Raman
0 siblings, 1 reply; 64+ messages in thread
From: John Levon @ 2025-03-03 11:19 UTC (permalink / raw)
To: Jag Raman
Cc: qemu-devel@nongnu.org, Jason Herne, Thanos Makatos, Halil Pasic,
Daniel P. Berrangé, Eric Farman, Tony Krowiak, Thomas Huth,
qemu-s390x@nongnu.org, Matthew Rosato, Paolo Bonzini,
Marc-André Lureau, Stefano Garzarella, Alex Williamson,
David Hildenbrand, Cédric Le Goater, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin
On Fri, Feb 28, 2025 at 05:09:00PM +0000, Jag Raman wrote:
> I appreciate you posting the patches. I didn't author the patches, actually;
> John Johnson did it.
I'll adjust the Author field and fix up the "Originally-by" tags for the next
round, thanks.
> You could use your name as the author since you should be familiar with it
> now, and I can review the patches.
This doesn't sound like the right thing to do: for most of these patches, I've
at best made small changes and JJ should remain the primary author, I think?
> Please add the following to each patch so it recognizes Oracle's contribution:
> Co-authored-by: John Johnson <john.g.johnson@oracle.com>
I can add these as well as having JJ as author if you'd prefer.
regards
john
^ permalink raw reply [flat|nested] 64+ messages in thread
* Re: [PATCH v8 00/28] vfio-user client
2025-03-03 11:19 ` John Levon
@ 2025-03-03 15:39 ` Jag Raman
0 siblings, 0 replies; 64+ messages in thread
From: Jag Raman @ 2025-03-03 15:39 UTC (permalink / raw)
To: John Levon
Cc: qemu-devel@nongnu.org, Jason Herne, Thanos Makatos, Halil Pasic,
Daniel P. Berrangé, Eric Farman, Tony Krowiak, Thomas Huth,
qemu-s390x@nongnu.org, Matthew Rosato, Paolo Bonzini,
Marc-André Lureau, Stefano Garzarella, Alex Williamson,
David Hildenbrand, Cédric Le Goater, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin
> On Mar 3, 2025, at 6:19 AM, John Levon <john.levon@nutanix.com> wrote:
>
> On Fri, Feb 28, 2025 at 05:09:00PM +0000, Jag Raman wrote:
>
>> I appreciate you posting the patches. I didn't author the patches, actually;
>> John Johnson did it.
>
> I'll adjust the Author field and fix up the "Originally-by" tags for the next
> round, thanks.
>
>> You could use your name as the author since you should be familiar with it
>> now, and I can review the patches.
>
> This doesn't sound like the right thing to do: for most of these patches, I've
> at best made small changes and JJ should remain the primary author, I think?
>
>> Please add the following to each patch so it recognizes Oracle's contribution:
>> Co-authored-by: John Johnson <john.g.johnson@oracle.com>
>
> I can add these as well as having JJ as author if you'd prefer.
That sounds good to me.
Thanks,
Jag
>
> regards
> john
^ permalink raw reply [flat|nested] 64+ messages in thread
* Re: [PATCH v8 00/28] vfio-user client
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (28 preceding siblings ...)
2025-02-28 17:09 ` [PATCH v8 00/28] vfio-user client Jag Raman
@ 2025-03-14 14:25 ` Cédric Le Goater
2025-03-14 14:48 ` Steven Sistare
2025-03-14 15:13 ` John Levon
2025-04-04 17:21 ` Cédric Le Goater
30 siblings, 2 replies; 64+ messages in thread
From: Cédric Le Goater @ 2025-03-14 14:25 UTC (permalink / raw)
To: John Levon, qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin, Steven Sistare
John,
+Steven, for the Live upsate series.
On 2/19/25 15:48, John Levon wrote:
> This is the 8th revision of the vfio-user client implementation. The vfio-user
> protocol allows for implementing (PCI) devices in another userspace process;
> SPDK is one example, which includes a virtual NVMe implementation.
>
> The vfio-user framework consists of 3 parts:
> 1) The VFIO user protocol specification.
> 2) A client - the VFIO device in QEMU that encapsulates VFIO messages
> and sends them to the server.
> 3) A server - a remote process that emulates a device.
>
> This patchset implements parts 1 and 2.
>
> It has been tested against libvfio-user test servers as well as SPDK.
>
> Thanks for previous reviews & comments.
This series is going in the right direction. Thanks for all the
changes. However, I will postpone my review for the reasons below.
VFIO initial commit in 2012 was a single file adding support for a
"vfio-pci" device. Since, the subsystem has changed a lot and it grew
to +16K line of code. Over the years, we've had numerous additions,
VFIO platform devices, s390x VFIO AP and CCW devices, migration
support with dirty tracking, support for different host IOMMU backend
devices, multifd, etc. All these additions never took the opportunity
to introduce a VFIO interface for external usage and PPC, s390x,
migration, backends subsystems happily and randomly peek and poke into
it. The subsystem is now a happy jumble of disparate functions, with
weak organization and names. The vfio-common.h header file is
good example of the result.
It's time for a global code reshuffling. I'll take care of it (and
I've already started) and this means nothing new (fixes are OK) will
be merged before this is done. I hope I have made enough progress
before the start of the QEMU 10.1 cycle. There won't be any functional
changes, but there will be new files and new function names, so it's
probably a real earthquake for your series.
Thanks,
C.
>
> Changes since v7:
>
> - split up pci patches for easier reviewing
> - fixed lots of device ops error handling
> - vfio-user code now in hw/vfio-user
> - improved commit messages
> - various other small cleanups
>
> Jagannathan Raman (20):
> vfio/container: pass MemoryRegion to DMA operations
> vfio: add region cache
> vfio: split out VFIOKernelPCIDevice
> vfio: add device IO ops vector
> vfio-user: add vfio-user class and container
> vfio-user: connect vfio proxy to remote server
> vfio-user: implement message receive infrastructure
> vfio-user: implement message send infrastructure
> vfio-user: implement VFIO_USER_DEVICE_GET_INFO
> vfio-user: implement VFIO_USER_DEVICE_GET_REGION_INFO
> vfio-user: implement VFIO_USER_REGION_READ/WRITE
> vfio-user: set up PCI in vfio_user_pci_realize()
> vfio-user: implement VFIO_USER_DEVICE_GET/SET_IRQ*
> vfio-user: forward MSI-X PBA BAR accesses to server
> vfio-user: set up container access to the proxy
> vfio-user: implement VFIO_USER_DEVICE_RESET
> vfio-user: implement VFIO_USER_DMA_READ/WRITE
> vfio-user: add 'no-direct-dma' option
> vfio-user: add 'x-msg-timeout' option
> vfio-user: add coalesced posted writes
>
> John Levon (7):
> vfio/container: pass listener_begin/commit callbacks
> vfio/container: support VFIO_DMA_UNMAP_FLAG_ALL
> vfio: add vfio_attach_device_by_iommu_type()
> vfio: add vfio_prepare_device()
> vfio: refactor out vfio_interrupt_setup()
> vfio: refactor out vfio_pci_config_setup()
> vfio-user: implement VFIO_USER_DMA_MAP/UNMAP
>
> Thanos Makatos (1):
> vfio-user: introduce vfio-user protocol specification
>
> MAINTAINERS | 10 +-
> docs/devel/index-internals.rst | 1 +
> docs/devel/vfio-user.rst | 1522 ++++++++++++++++++++++
> hw/meson.build | 1 +
> hw/vfio-user/common.c | 1702 +++++++++++++++++++++++++
> hw/vfio-user/common.h | 123 ++
> hw/vfio-user/container.c | 358 ++++++
> hw/vfio-user/container.h | 24 +
> hw/vfio-user/meson.build | 10 +
> hw/vfio-user/pci.c | 443 +++++++
> hw/vfio-user/protocol.h | 243 ++++
> hw/vfio-user/trace-events | 18 +
> hw/vfio-user/trace.h | 1 +
> hw/vfio/ap.c | 4 +-
> hw/vfio/ccw.c | 9 +-
> hw/vfio/common.c | 137 +-
> hw/vfio/container-base.c | 8 +-
> hw/vfio/container.c | 78 +-
> hw/vfio/helpers.c | 185 ++-
> hw/vfio/igd.c | 8 +-
> hw/vfio/iommufd.c | 31 +-
> hw/vfio/pci.c | 591 +++++----
> hw/vfio/pci.h | 34 +-
> hw/vfio/platform.c | 4 +-
> hw/virtio/vhost-vdpa.c | 2 +-
> include/exec/memory.h | 4 +-
> include/hw/vfio/vfio-common.h | 45 +-
> include/hw/vfio/vfio-container-base.h | 11 +-
> meson.build | 1 +
> meson_options.txt | 2 +
> scripts/meson-buildoptions.sh | 4 +
> system/memory.c | 7 +-
> 32 files changed, 5281 insertions(+), 340 deletions(-)
> create mode 100644 docs/devel/vfio-user.rst
> create mode 100644 hw/vfio-user/common.c
> create mode 100644 hw/vfio-user/common.h
> create mode 100644 hw/vfio-user/container.c
> create mode 100644 hw/vfio-user/container.h
> create mode 100644 hw/vfio-user/meson.build
> create mode 100644 hw/vfio-user/pci.c
> create mode 100644 hw/vfio-user/protocol.h
> create mode 100644 hw/vfio-user/trace-events
> create mode 100644 hw/vfio-user/trace.h
>
^ permalink raw reply [flat|nested] 64+ messages in thread* Re: [PATCH v8 00/28] vfio-user client
2025-03-14 14:25 ` Cédric Le Goater
@ 2025-03-14 14:48 ` Steven Sistare
2025-03-18 10:00 ` Cédric Le Goater
2025-03-14 15:13 ` John Levon
1 sibling, 1 reply; 64+ messages in thread
From: Steven Sistare @ 2025-03-14 14:48 UTC (permalink / raw)
To: Cédric Le Goater, John Levon, qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin
On 3/14/2025 10:25 AM, Cédric Le Goater wrote:
> John,
>
> +Steven, for the Live upsate series.
>
> On 2/19/25 15:48, John Levon wrote:
>> This is the 8th revision of the vfio-user client implementation. The vfio-user
>> protocol allows for implementing (PCI) devices in another userspace process;
>> SPDK is one example, which includes a virtual NVMe implementation.
>>
>> The vfio-user framework consists of 3 parts:
>> 1) The VFIO user protocol specification.
>> 2) A client - the VFIO device in QEMU that encapsulates VFIO messages
>> and sends them to the server.
>> 3) A server - a remote process that emulates a device.
>>
>> This patchset implements parts 1 and 2.
>>
>> It has been tested against libvfio-user test servers as well as SPDK.
>>
>> Thanks for previous reviews & comments.
>
> This series is going in the right direction. Thanks for all the
> changes. However, I will postpone my review for the reasons below.
>
> VFIO initial commit in 2012 was a single file adding support for a
> "vfio-pci" device. Since, the subsystem has changed a lot and it grew
> to +16K line of code. Over the years, we've had numerous additions,
> VFIO platform devices, s390x VFIO AP and CCW devices, migration
> support with dirty tracking, support for different host IOMMU backend
> devices, multifd, etc. All these additions never took the opportunity
> to introduce a VFIO interface for external usage and PPC, s390x,
> migration, backends subsystems happily and randomly peek and poke into
> it. The subsystem is now a happy jumble of disparate functions, with
> weak organization and names. The vfio-common.h header file is
> good example of the result.
>
> It's time for a global code reshuffling. I'll take care of it (and
> I've already started) and this means nothing new (fixes are OK) will
> be merged before this is done. I hope I have made enough progress
> before the start of the QEMU 10.1 cycle. There won't be any functional
> changes, but there will be new files and new function names, so it's
> probably a real earthquake for your series.
Hi Cedric, as part of your reshuffling, can you incorporate the code cleanup
patches that I submitted in the live update series?
- Steve
^ permalink raw reply [flat|nested] 64+ messages in thread
* Re: [PATCH v8 00/28] vfio-user client
2025-03-14 14:48 ` Steven Sistare
@ 2025-03-18 10:00 ` Cédric Le Goater
0 siblings, 0 replies; 64+ messages in thread
From: Cédric Le Goater @ 2025-03-18 10:00 UTC (permalink / raw)
To: Steven Sistare, John Levon, qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin
On 3/14/25 15:48, Steven Sistare wrote:
>
>
> On 3/14/2025 10:25 AM, Cédric Le Goater wrote:
>> John,
>>
>> +Steven, for the Live upsate series.
>>
>> On 2/19/25 15:48, John Levon wrote:
>>> This is the 8th revision of the vfio-user client implementation. The vfio-user
>>> protocol allows for implementing (PCI) devices in another userspace process;
>>> SPDK is one example, which includes a virtual NVMe implementation.
>>>
>>> The vfio-user framework consists of 3 parts:
>>> 1) The VFIO user protocol specification.
>>> 2) A client - the VFIO device in QEMU that encapsulates VFIO messages
>>> and sends them to the server.
>>> 3) A server - a remote process that emulates a device.
>>>
>>> This patchset implements parts 1 and 2.
>>>
>>> It has been tested against libvfio-user test servers as well as SPDK.
>>>
>>> Thanks for previous reviews & comments.
>>
>> This series is going in the right direction. Thanks for all the
>> changes. However, I will postpone my review for the reasons below.
>>
>> VFIO initial commit in 2012 was a single file adding support for a
>> "vfio-pci" device. Since, the subsystem has changed a lot and it grew
>> to +16K line of code. Over the years, we've had numerous additions,
>> VFIO platform devices, s390x VFIO AP and CCW devices, migration
>> support with dirty tracking, support for different host IOMMU backend
>> devices, multifd, etc. All these additions never took the opportunity
>> to introduce a VFIO interface for external usage and PPC, s390x,
>> migration, backends subsystems happily and randomly peek and poke into
>> it. The subsystem is now a happy jumble of disparate functions, with
>> weak organization and names. The vfio-common.h header file is
>> good example of the result.
>>
>> It's time for a global code reshuffling. I'll take care of it (and
>> I've already started) and this means nothing new (fixes are OK) will
>> be merged before this is done. I hope I have made enough progress
>> before the start of the QEMU 10.1 cycle. There won't be any functional
>> changes, but there will be new files and new function names, so it's
>> probably a real earthquake for your series.
>
> Hi Cedric, as part of your reshuffling, can you incorporate the code cleanup
> patches that I submitted in the live update series?
I will try when this series has had some reviews :
https://lore.kernel.org/qemu-devel/20250318095415.670319-1-clg@redhat.com/
Thanks,
C.
^ permalink raw reply [flat|nested] 64+ messages in thread
* Re: [PATCH v8 00/28] vfio-user client
2025-03-14 14:25 ` Cédric Le Goater
2025-03-14 14:48 ` Steven Sistare
@ 2025-03-14 15:13 ` John Levon
2025-03-18 10:02 ` Cédric Le Goater
1 sibling, 1 reply; 64+ messages in thread
From: John Levon @ 2025-03-14 15:13 UTC (permalink / raw)
To: Cédric Le Goater
Cc: qemu-devel, Jason Herne, Thanos Makatos, Halil Pasic,
Daniel P. Berrangé, Eric Farman, Tony Krowiak, Thomas Huth,
qemu-s390x, Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin, Steven Sistare
On Fri, Mar 14, 2025 at 03:25:53PM +0100, Cédric Le Goater wrote:
> > This is the 8th revision of the vfio-user client implementation. The vfio-user
> > protocol allows for implementing (PCI) devices in another userspace process;
> > SPDK is one example, which includes a virtual NVMe implementation.
>
> This series is going in the right direction. Thanks for all the
> changes. However, I will postpone my review for the reasons below.
>
> VFIO initial commit in 2012 was a single file adding support for a
> "vfio-pci" device. Since, the subsystem has changed a lot and it grew
> to +16K line of code. Over the years, we've had numerous additions,
> VFIO platform devices, s390x VFIO AP and CCW devices, migration
> support with dirty tracking, support for different host IOMMU backend
> devices, multifd, etc. All these additions never took the opportunity
> to introduce a VFIO interface for external usage and PPC, s390x,
> migration, backends subsystems happily and randomly peek and poke into
> it. The subsystem is now a happy jumble of disparate functions, with
> weak organization and names. The vfio-common.h header file is
> good example of the result.
Right, I certainly agree!
> It's time for a global code reshuffling. I'll take care of it (and
> I've already started) and this means nothing new (fixes are OK) will
> be merged before this is done. I hope I have made enough progress
> before the start of the QEMU 10.1 cycle. There won't be any functional
> changes, but there will be new files and new function names, so it's
> probably a real earthquake for your series.
It's had a couple of earthquakes already, very happy to bear the pain for a
better end result! I will try to look out for your series and review where I can
as well.
thanks
john
^ permalink raw reply [flat|nested] 64+ messages in thread
* Re: [PATCH v8 00/28] vfio-user client
2025-03-14 15:13 ` John Levon
@ 2025-03-18 10:02 ` Cédric Le Goater
0 siblings, 0 replies; 64+ messages in thread
From: Cédric Le Goater @ 2025-03-18 10:02 UTC (permalink / raw)
To: John Levon
Cc: qemu-devel, Jason Herne, Thanos Makatos, Halil Pasic,
Daniel P. Berrangé, Eric Farman, Tony Krowiak, Thomas Huth,
qemu-s390x, Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin, Steven Sistare
On 3/14/25 16:13, John Levon wrote:
> On Fri, Mar 14, 2025 at 03:25:53PM +0100, Cédric Le Goater wrote:
>
>>> This is the 8th revision of the vfio-user client implementation. The vfio-user
>>> protocol allows for implementing (PCI) devices in another userspace process;
>>> SPDK is one example, which includes a virtual NVMe implementation.
>>
>> This series is going in the right direction. Thanks for all the
>> changes. However, I will postpone my review for the reasons below.
>>
>> VFIO initial commit in 2012 was a single file adding support for a
>> "vfio-pci" device. Since, the subsystem has changed a lot and it grew
>> to +16K line of code. Over the years, we've had numerous additions,
>> VFIO platform devices, s390x VFIO AP and CCW devices, migration
>> support with dirty tracking, support for different host IOMMU backend
>> devices, multifd, etc. All these additions never took the opportunity
>> to introduce a VFIO interface for external usage and PPC, s390x,
>> migration, backends subsystems happily and randomly peek and poke into
>> it. The subsystem is now a happy jumble of disparate functions, with
>> weak organization and names. The vfio-common.h header file is
>> good example of the result.
>
> Right, I certainly agree!
>
>> It's time for a global code reshuffling. I'll take care of it (and
>> I've already started) and this means nothing new (fixes are OK) will
>> be merged before this is done. I hope I have made enough progress
>> before the start of the QEMU 10.1 cycle. There won't be any functional
>> changes, but there will be new files and new function names, so it's
>> probably a real earthquake for your series.
>
> It's had a couple of earthquakes already, very happy to bear the pain for a
> better end result! I will try to look out for your series and review where I can
> as well.
Here it is :
https://lore.kernel.org/qemu-devel/20250318095415.670319-1-clg@redhat.com/
Now is the time to prepare ground for your needs.
Thanks,
C.
> thanks
> john
>
^ permalink raw reply [flat|nested] 64+ messages in thread
* Re: [PATCH v8 00/28] vfio-user client
2025-02-19 14:48 [PATCH v8 00/28] vfio-user client John Levon
` (29 preceding siblings ...)
2025-03-14 14:25 ` Cédric Le Goater
@ 2025-04-04 17:21 ` Cédric Le Goater
30 siblings, 0 replies; 64+ messages in thread
From: Cédric Le Goater @ 2025-04-04 17:21 UTC (permalink / raw)
To: John Levon, qemu-devel
Cc: Jason Herne, Thanos Makatos, Halil Pasic, Daniel P. Berrangé,
Eric Farman, Tony Krowiak, Thomas Huth, qemu-s390x,
Matthew Rosato, Paolo Bonzini, Marc-André Lureau,
Stefano Garzarella, Alex Williamson, David Hildenbrand, Peter Xu,
Philippe Mathieu-Daudé, Michael S. Tsirkin
John,
On 2/19/25 15:48, John Levon wrote:
> This is the 8th revision of the vfio-user client implementation. The vfio-user
> protocol allows for implementing (PCI) devices in another userspace process;
> SPDK is one example, which includes a virtual NVMe implementation.
>
> The vfio-user framework consists of 3 parts:
> 1) The VFIO user protocol specification.
> 2) A client - the VFIO device in QEMU that encapsulates VFIO messages
> and sends them to the server.
> 3) A server - a remote process that emulates a device.
>
> This patchset implements parts 1 and 2.
>
> It has been tested against libvfio-user test servers as well as SPDK.
>
> Thanks for previous reviews & comments.
>
> Changes since v7:
>
> - split up pci patches for easier reviewing
> - fixed lots of device ops error handling
> - vfio-user code now in hw/vfio-user
> - improved commit messages
> - various other small cleanups
Could please resend next version on top
https://github.com/legoater/qemu/commits/vfio-10.1
This is the branch in which I put the experimental stuff for the
current cycle. It contains today the "spring cleanup" v2 series
I plan to send when QEMU 10.1 opens. Well, not exactly it because
I am waiting for some emails from Avihai to reach the list before
doing an update. It should be very close.
Also, could you please resend the vfio prerequisites only ? The
first 10 patches or so. It seems these could be merged soon. At
least checked for functional and performance regressions.
There are still relatively big changes in VFIO to discuss in these
patches:
vfio-user: implement VFIO_USER_DEVICE_GET_REGION_INFO
vfio-user: implement VFIO_USER_REGION_READ/WRITE
vfio-user: set up PCI in vfio_user_pci_realize()
vfio-user: forward MSI-X PBA BAR accesses to server
Something for later.
Thanks,
C.
^ permalink raw reply [flat|nested] 64+ messages in thread