Every IOMMU has some granularity which MemoryRegionIOMMUOps::translate uses when translating, however this information is not available outside the translate context for various checks.
This adds a get_page_sizes callback to MemoryRegionIOMMUOps and a wrapper for it so IOMMU users (such as VFIO) can know the actual page size(s) used by an IOMMU. The qemu_real_host_page_mask is used as fallback. This removes vfio_container_granularity() and uses new callback in memory_region_iommu_replay() when replaying IOMMU mappings on added IOMMU memory region. Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru> --- Changes: v14: * removed vfio_container_granularity(), changed memory_region_iommu_replay() v4: * s/1<<TARGET_PAGE_BITS/qemu_real_host_page_size/ --- hw/ppc/spapr_iommu.c | 8 ++++++++ hw/vfio/common.c | 6 ------ include/exec/memory.h | 18 ++++++++++++++---- memory.c | 17 ++++++++++++++--- 4 files changed, 36 insertions(+), 13 deletions(-) diff --git a/hw/ppc/spapr_iommu.c b/hw/ppc/spapr_iommu.c index dd662da..6dc3c45 100644 --- a/hw/ppc/spapr_iommu.c +++ b/hw/ppc/spapr_iommu.c @@ -144,6 +144,13 @@ static void spapr_tce_table_pre_save(void *opaque) tcet->mig_table = tcet->table; } +static uint64_t spapr_tce_get_page_sizes(MemoryRegion *iommu) +{ + sPAPRTCETable *tcet = container_of(iommu, sPAPRTCETable, iommu); + + return 1ULL << tcet->page_shift; +} + static void spapr_tce_table_do_enable(sPAPRTCETable *tcet); static void spapr_tce_table_do_disable(sPAPRTCETable *tcet); @@ -203,6 +210,7 @@ static const VMStateDescription vmstate_spapr_tce_table = { static MemoryRegionIOMMUOps spapr_iommu_ops = { .translate = spapr_tce_translate_iommu, + .get_page_sizes = spapr_tce_get_page_sizes, }; static int spapr_tce_table_realize(DeviceState *dev) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index d45e2db..55723c9 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -313,11 +313,6 @@ out: rcu_read_unlock(); } -static hwaddr vfio_container_granularity(VFIOContainer *container) -{ - return (hwaddr)1 << ctz64(container->iova_pgsizes); -} - static void vfio_listener_region_add(MemoryListener *listener, MemoryRegionSection *section) { @@ -385,7 +380,6 @@ static void vfio_listener_region_add(MemoryListener *listener, memory_region_register_iommu_notifier(giommu->iommu, &giommu->n); memory_region_iommu_replay(giommu->iommu, &giommu->n, - vfio_container_granularity(container), false); return; diff --git a/include/exec/memory.h b/include/exec/memory.h index 2de7898..eb5ce67 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -150,6 +150,8 @@ typedef struct MemoryRegionIOMMUOps MemoryRegionIOMMUOps; struct MemoryRegionIOMMUOps { /* Return a TLB entry that contains a given address. */ IOMMUTLBEntry (*translate)(MemoryRegion *iommu, hwaddr addr, bool is_write); + /* Returns supported page sizes */ + uint64_t (*get_page_sizes)(MemoryRegion *iommu); }; typedef struct CoalescedMemoryRange CoalescedMemoryRange; @@ -573,6 +575,15 @@ static inline bool memory_region_is_iommu(MemoryRegion *mr) /** + * memory_region_iommu_get_page_sizes: get supported page sizes in an iommu + * + * Returns %bitmap of supported page sizes for an iommu. + * + * @mr: the memory region being queried + */ +uint64_t memory_region_iommu_get_page_sizes(MemoryRegion *mr); + +/** * memory_region_notify_iommu: notify a change in an IOMMU translation entry. * * @mr: the memory region that was changed @@ -596,16 +607,15 @@ void memory_region_register_iommu_notifier(MemoryRegion *mr, Notifier *n); /** * memory_region_iommu_replay: replay existing IOMMU translations to - * a notifier + * a notifier with the minimum page granularity returned by + * mr->iommu_ops->get_page_sizes(). * * @mr: the memory region to observe * @n: the notifier to which to replay iommu mappings - * @granularity: Minimum page granularity to replay notifications for * @is_write: Whether to treat the replay as a translate "write" * through the iommu */ -void memory_region_iommu_replay(MemoryRegion *mr, Notifier *n, - hwaddr granularity, bool is_write); +void memory_region_iommu_replay(MemoryRegion *mr, Notifier *n, bool is_write); /** * memory_region_unregister_iommu_notifier: unregister a notifier for diff --git a/memory.c b/memory.c index 95f7209..64a84d3 100644 --- a/memory.c +++ b/memory.c @@ -1512,12 +1512,14 @@ void memory_region_register_iommu_notifier(MemoryRegion *mr, Notifier *n) notifier_list_add(&mr->iommu_notify, n); } -void memory_region_iommu_replay(MemoryRegion *mr, Notifier *n, - hwaddr granularity, bool is_write) +void memory_region_iommu_replay(MemoryRegion *mr, Notifier *n, bool is_write) { - hwaddr addr; + hwaddr addr, granularity; IOMMUTLBEntry iotlb; + g_assert(mr->iommu_ops && mr->iommu_ops->get_page_sizes); + granularity = (hwaddr)1 << ctz64(mr->iommu_ops->get_page_sizes(mr)); + for (addr = 0; addr < memory_region_size(mr); addr += granularity) { iotlb = mr->iommu_ops->translate(mr, addr, is_write); if (iotlb.perm != IOMMU_NONE) { @@ -1544,6 +1546,15 @@ void memory_region_notify_iommu(MemoryRegion *mr, notifier_list_notify(&mr->iommu_notify, &entry); } +uint64_t memory_region_iommu_get_page_sizes(MemoryRegion *mr) +{ + assert(memory_region_is_iommu(mr)); + if (mr->iommu_ops && mr->iommu_ops->get_page_sizes) { + return mr->iommu_ops->get_page_sizes(mr); + } + return qemu_real_host_page_size; +} + void memory_region_set_log(MemoryRegion *mr, bool log, unsigned client) { uint8_t mask = 1 << client; -- 2.5.0.rc3