Re: [Qemu-devel] [PATCH qemu v6 08/15] spapr_iommu: Introduce "enabled" state for TCE table

[David Gibson]

On Sat, Apr 11, 2015 at 01:24:37AM +1000, Alexey Kardashevskiy wrote:
> Currently TCE tables are created once at start and their size never
> changes. We are going to change that by introducing a Dynamic DMA windows
> support where DMA configuration may change during the guest execution.
> 
> This changes spapr_tce_new_table() to create an empty stub object. Only
> LIOBN is assigned by the time of creation. It still will be called once
> at the owner object (VIO or PHB) creation.
> 
> This introduces an "enabled" state for TCE table objects with two
> helper functions - spapr_tce_table_enable()/spapr_tce_table_disable().
> spapr_tce_table_enable() receives TCE table parameters and allocates
> a guest view of the TCE table (in the user space or KVM).
> spapr_tce_table_disable() disposes the table.
> 
> Follow up patches will disable+enable tables on reset (system reset
> or DDW reset).
> 
> No visible change in behaviour is expected except the actual table
> will be reallocated every reset. We might optimize this later.
> 
> The other way to implement this would be dynamically create/remove
> the TCE table QOM objects but this would make migration impossible
> as migration expects all QOM objects to exist at the receiver
> so we have to have TCE table objects created when migration begins.
> 
> Signed-off-by: Alexey Kardashevskiy <address@hidden>
> ---
> Changes:
> v6:
> * got rid of set_props()
> ---
>  hw/ppc/spapr_iommu.c    | 104 
> +++++++++++++++++++++++++++++++-----------------
>  hw/ppc/spapr_pci.c      |  16 +++++---
>  hw/ppc/spapr_pci_vfio.c |  10 ++---
>  hw/ppc/spapr_vio.c      |   9 ++---
>  include/hw/ppc/spapr.h  |  11 ++---
>  5 files changed, 93 insertions(+), 57 deletions(-)
> 
> diff --git a/hw/ppc/spapr_iommu.c b/hw/ppc/spapr_iommu.c
> index a14cdc4..64f20f2 100644
> --- a/hw/ppc/spapr_iommu.c
> +++ b/hw/ppc/spapr_iommu.c
> @@ -126,8 +126,47 @@ static MemoryRegionIOMMUOps spapr_iommu_ops = {
>  static int spapr_tce_table_realize(DeviceState *dev)
>  {
>      sPAPRTCETable *tcet = SPAPR_TCE_TABLE(dev);
> +
> +    QLIST_INSERT_HEAD(&spapr_tce_tables, tcet, list);
> +
> +    vmstate_register(DEVICE(tcet), tcet->liobn, &vmstate_spapr_tce_table,
> +                     tcet);
> +
> +    return 0;
> +}
> +
> +sPAPRTCETable *spapr_tce_new_table(DeviceState *owner, uint32_t liobn)
> +{
> +    sPAPRTCETable *tcet;
> +    char tmp[64];
> +
> +    if (spapr_tce_find_by_liobn(liobn)) {
> +        fprintf(stderr, "Attempted to create TCE table with duplicate"
> +                " LIOBN 0x%x\n", liobn);
> +        return NULL;
> +    }
> +
> +    tcet = SPAPR_TCE_TABLE(object_new(TYPE_SPAPR_TCE_TABLE));
> +    tcet->liobn = liobn;
> +
> +    snprintf(tmp, sizeof(tmp), "tce-table-%x", liobn);
> +    object_property_add_child(OBJECT(owner), tmp, OBJECT(tcet), NULL);
> +
> +    object_property_set_bool(OBJECT(tcet), true, "realized", NULL);
> +
> +    trace_spapr_iommu_new_table(tcet->liobn, tcet, tcet->table, tcet->fd);
> +
> +    return tcet;
> +}
> +
> +static void spapr_tce_table_do_enable(sPAPRTCETable *tcet)

AFAICT there's only one caller of this, so it's not clear why this
isn't just open-coded in spapr_tce_table_enable().

> +{
>      uint64_t window_size = (uint64_t)tcet->nb_table << tcet->page_shift;
>  
> +    if (!tcet->nb_table) {
> +        return;
> +    }
> +
>      if (kvm_enabled() && !(window_size >> 32)) {
>          tcet->table = kvmppc_create_spapr_tce(tcet->liobn,
>                                                window_size,
> @@ -140,65 +179,56 @@ static int spapr_tce_table_realize(DeviceState *dev)
>          tcet->table = g_malloc0(table_size);
>      }
>  
> -    trace_spapr_iommu_new_table(tcet->liobn, tcet, tcet->table, tcet->fd);
> -
> -    memory_region_init_iommu(&tcet->iommu, OBJECT(dev), &spapr_iommu_ops,
> +    memory_region_init_iommu(&tcet->iommu, OBJECT(tcet), &spapr_iommu_ops,
>                               "iommu-spapr",
>                               (uint64_t)tcet->nb_table << tcet->page_shift);
>  
> -    QLIST_INSERT_HEAD(&spapr_tce_tables, tcet, list);
> -
> -    vmstate_register(DEVICE(tcet), tcet->liobn, &vmstate_spapr_tce_table,
> -                     tcet);
> -
> -    return 0;
> +    tcet->enabled = true;
>  }
>  
> -sPAPRTCETable *spapr_tce_new_table(DeviceState *owner, uint32_t liobn,
> -                                   uint64_t bus_offset,
> -                                   uint32_t page_shift,
> -                                   uint32_t nb_table,
> -                                   bool vfio_accel)
> +void spapr_tce_table_enable(sPAPRTCETable *tcet,
> +                            uint64_t bus_offset, uint32_t page_shift,
> +                            uint32_t nb_table, bool vfio_accel)
>  {
> -    sPAPRTCETable *tcet;
> -    char tmp[64];
> -
> -    if (spapr_tce_find_by_liobn(liobn)) {
> -        fprintf(stderr, "Attempted to create TCE table with duplicate"
> -                " LIOBN 0x%x\n", liobn);
> -        return NULL;
> -    }
> -
> -    if (!nb_table) {
> -        return NULL;
> +    if (tcet->enabled) {
> +        return;
>      }
>  
> -    tcet = SPAPR_TCE_TABLE(object_new(TYPE_SPAPR_TCE_TABLE));
> -    tcet->liobn = liobn;
>      tcet->bus_offset = bus_offset;
>      tcet->page_shift = page_shift;
>      tcet->nb_table = nb_table;
>      tcet->vfio_accel = vfio_accel;
>  
> -    snprintf(tmp, sizeof(tmp), "tce-table-%x", liobn);
> -    object_property_add_child(OBJECT(owner), tmp, OBJECT(tcet), NULL);
> -
> -    object_property_set_bool(OBJECT(tcet), true, "realized", NULL);
> -
> -    return tcet;
> +    spapr_tce_table_do_enable(tcet);
>  }
>  
> -static void spapr_tce_table_unrealize(DeviceState *dev, Error **errp)
> +void spapr_tce_table_disable(sPAPRTCETable *tcet)
>  {
> -    sPAPRTCETable *tcet = SPAPR_TCE_TABLE(dev);
> -
> -    QLIST_REMOVE(tcet, list);
> +    if (!tcet->enabled) {
> +        return;
> +    }
>  
>      if (!kvm_enabled() ||
>          (kvmppc_remove_spapr_tce(tcet->table, tcet->fd,
>                                   tcet->nb_table) != 0)) {
> +        tcet->fd = -1;
>          g_free(tcet->table);
>      }
> +    tcet->table = NULL;
> +    tcet->enabled = false;
> +    tcet->bus_offset = 0;
> +    tcet->page_shift = 0;
> +    tcet->nb_table = 0;
> +    tcet->vfio_accel = false;
> +}
> +
> +static void spapr_tce_table_unrealize(DeviceState *dev, Error **errp)
> +{
> +    sPAPRTCETable *tcet = SPAPR_TCE_TABLE(dev);
> +
> +    QLIST_REMOVE(tcet, list);
> +
> +    spapr_tce_table_disable(tcet);
>  }
>  
>  MemoryRegion *spapr_tce_get_iommu(sPAPRTCETable *tcet)
> diff --git a/hw/ppc/spapr_pci.c b/hw/ppc/spapr_pci.c
> index 8c0d2eb..c3410b8 100644
> --- a/hw/ppc/spapr_pci.c
> +++ b/hw/ppc/spapr_pci.c
> @@ -881,6 +881,12 @@ static void spapr_phb_realize(DeviceState *dev, Error 
> **errp)
>          sphb->lsi_table[i].irq = irq;
>      }
>  
> +    tcet = spapr_tce_new_table(DEVICE(sphb), sphb->dma_liobn);
> +    if (!tcet) {
> +            error_setg(errp, "failed to create TCE table");
> +            return;
> +    }
> +
>      info->dma_capabilities_update(sphb);
>      info->dma_init_window(sphb, sphb->dma_liobn, SPAPR_TCE_PAGE_SHIFT,
>                            sphb->dma32_window_size);
> @@ -908,13 +914,13 @@ static int spapr_phb_dma_init_window(sPAPRPHBState 
> *sphb,
>                                       uint64_t window_size)
>  {
>      uint64_t bus_offset = sphb->dma32_window_start;
> -    sPAPRTCETable *tcet;
> +    sPAPRTCETable *tcet = spapr_tce_find_by_liobn(liobn);
>  
> -    tcet = spapr_tce_new_table(DEVICE(sphb), liobn, bus_offset, page_shift,
> -                               window_size >> page_shift,
> -                               false);
> +    spapr_tce_table_enable(tcet, bus_offset, page_shift,
> +                           window_size >> page_shift,
> +                           false);
>  
> -    return tcet ? 0 : -1;
> +    return 0;
>  }
>  
>  static int spapr_phb_children_reset(Object *child, void *opaque)
> diff --git a/hw/ppc/spapr_pci_vfio.c b/hw/ppc/spapr_pci_vfio.c
> index 0ce8e61..a428166 100644
> --- a/hw/ppc/spapr_pci_vfio.c
> +++ b/hw/ppc/spapr_pci_vfio.c
> @@ -49,13 +49,13 @@ static int spapr_phb_vfio_dma_init_window(sPAPRPHBState 
> *sphb,
>                                            uint64_t window_size)
>  {
>      uint64_t bus_offset = sphb->dma32_window_start;
> -    sPAPRTCETable *tcet;
> +    sPAPRTCETable *tcet = spapr_tce_find_by_liobn(liobn);
>  
> -    tcet = spapr_tce_new_table(DEVICE(sphb), liobn, bus_offset, page_shift,
> -                               window_size >> page_shift,
> -                               true);
> +    spapr_tce_table_enable(tcet, bus_offset, page_shift,
> +                           window_size >> page_shift,
> +                           true);
>  
> -    return tcet ? 0 : -1;
> +    return 0;
>  }
>  
>  static void spapr_phb_vfio_reset(DeviceState *qdev)
> diff --git a/hw/ppc/spapr_vio.c b/hw/ppc/spapr_vio.c
> index 174033d..3e28835 100644
> --- a/hw/ppc/spapr_vio.c
> +++ b/hw/ppc/spapr_vio.c
> @@ -479,11 +479,10 @@ static void spapr_vio_busdev_realize(DeviceState *qdev, 
> Error **errp)
>          memory_region_add_subregion_overlap(&dev->mrroot, 0, &dev->mrbypass, 
> 1);
>          address_space_init(&dev->as, &dev->mrroot, qdev->id);
>  
> -        dev->tcet = spapr_tce_new_table(qdev, liobn,
> -                                        0,
> -                                        SPAPR_TCE_PAGE_SHIFT,
> -                                        pc->rtce_window_size >>
> -                                        SPAPR_TCE_PAGE_SHIFT, false);
> +        dev->tcet = spapr_tce_new_table(qdev, liobn);
> +        spapr_tce_table_enable(dev->tcet, 0, SPAPR_TCE_PAGE_SHIFT,
> +                               pc->rtce_window_size >> SPAPR_TCE_PAGE_SHIFT,
> +                               false);
>          dev->tcet->vdev = dev;
>          memory_region_add_subregion_overlap(&dev->mrroot, 0,
>                                              spapr_tce_get_iommu(dev->tcet), 
> 2);
> diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
> index 7d9ab9d..074d837 100644
> --- a/include/hw/ppc/spapr.h
> +++ b/include/hw/ppc/spapr.h
> @@ -498,6 +498,7 @@ typedef struct sPAPRTCETable sPAPRTCETable;
>  
>  struct sPAPRTCETable {
>      DeviceState parent;
> +    bool enabled;
>      uint32_t liobn;
>      uint32_t nb_table;
>      uint64_t bus_offset;
> @@ -515,11 +516,11 @@ sPAPRTCETable *spapr_tce_find_by_liobn(uint32_t liobn);
>  void spapr_events_init(sPAPREnvironment *spapr);
>  void spapr_events_fdt_skel(void *fdt, uint32_t epow_irq);
>  int spapr_h_cas_compose_response(target_ulong addr, target_ulong size);
> -sPAPRTCETable *spapr_tce_new_table(DeviceState *owner, uint32_t liobn,
> -                                   uint64_t bus_offset,
> -                                   uint32_t page_shift,
> -                                   uint32_t nb_table,
> -                                   bool vfio_accel);
> +sPAPRTCETable *spapr_tce_new_table(DeviceState *owner, uint32_t liobn);
> +void spapr_tce_table_enable(sPAPRTCETable *tcet,
> +                            uint64_t bus_offset, uint32_t page_shift,
> +                            uint32_t nb_table, bool vfio_accel);
> +void spapr_tce_table_disable(sPAPRTCETable *tcet);
>  MemoryRegion *spapr_tce_get_iommu(sPAPRTCETable *tcet);
>  int spapr_dma_dt(void *fdt, int node_off, const char *propname,
>                   uint32_t liobn, uint64_t window, uint32_t size);

-- 
David Gibson                    | I'll have my music baroque, and my code
david AT gibson.dropbear.id.au  | minimalist, thank you.  NOT _the_ _other_
                                | _way_ _around_!
http://www.ozlabs.org/~dgibson

pgpYufNhl28zO.pgp
Description: PGP signature