At the moment presence of vfio-pci devices on a bus affect the way
the guest view table is allocated. If there is no vfio-pci on a PHB
and the host kernel supports KVM acceleration of H_PUT_TCE, a table
is allocated in KVM. However, if there is vfio-pci and we do yet not
KVM acceleration for these, the table has to be allocated by
the userspace. At the moment the table is allocated once at boot time
but next patches will reallocate it.
This moves kvmppc_create_spapr_tce/g_malloc0 and their counterparts
to helpers.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
Reviewed-by: David Gibson <da...@gibson.dropbear.id.au>
---
hw/ppc/spapr_iommu.c | 58 +++++++++++++++++++++++++++++++++++-----------------
trace-events | 2 +-
2 files changed, 40 insertions(+), 20 deletions(-)
diff --git a/hw/ppc/spapr_iommu.c b/hw/ppc/spapr_iommu.c
index 277f289..8132f64 100644
--- a/hw/ppc/spapr_iommu.c
+++ b/hw/ppc/spapr_iommu.c
@@ -75,6 +75,37 @@ static IOMMUAccessFlags
spapr_tce_iommu_access_flags(uint64_t tce)
}
}
+static uint64_t *spapr_tce_alloc_table(uint32_t liobn,
+ uint32_t page_shift,
+ uint32_t nb_table,
+ int *fd,
+ bool need_vfio)
+{
+ uint64_t *table = NULL;
+ uint64_t window_size = (uint64_t)nb_table << page_shift;
+
+ if (kvm_enabled() && !(window_size >> 32)) {
+ table = kvmppc_create_spapr_tce(liobn, window_size, fd, need_vfio);
+ }
+
+ if (!table) {
+ *fd = -1;
+ table = g_malloc0(nb_table * sizeof(uint64_t));
+ }
+
+ trace_spapr_iommu_new_table(liobn, table, *fd);
+
+ return table;
+}
+
+static void spapr_tce_free_table(uint64_t *table, int fd, uint32_t nb_table)
+{
+ if (!kvm_enabled() ||
+ (kvmppc_remove_spapr_tce(table, fd, nb_table) != 0)) {
+ g_free(table);
+ }
+}
+
/* Called from RCU critical section */
static IOMMUTLBEntry spapr_tce_translate_iommu(MemoryRegion *iommu, hwaddr
addr,
bool is_write)
@@ -141,21 +172,13 @@ static MemoryRegionIOMMUOps spapr_iommu_ops = {
static int spapr_tce_table_realize(DeviceState *dev)
{
sPAPRTCETable *tcet = SPAPR_TCE_TABLE(dev);
- uint64_t window_size = (uint64_t)tcet->nb_table << tcet->page_shift;
- if (kvm_enabled() && !(window_size >> 32)) {
- tcet->table = kvmppc_create_spapr_tce(tcet->liobn,
- window_size,
- &tcet->fd,
- tcet->need_vfio);
- }
-
- if (!tcet->table) {
- size_t table_size = tcet->nb_table * sizeof(uint64_t);
- tcet->table = g_malloc0(table_size);
- }
-
- trace_spapr_iommu_new_table(tcet->liobn, tcet, tcet->table, tcet->fd);
+ tcet->fd = -1;
+ tcet->table = spapr_tce_alloc_table(tcet->liobn,
+ tcet->page_shift,
+ tcet->nb_table,
+ &tcet->fd,
+ tcet->need_vfio);
memory_region_init_iommu(&tcet->iommu, OBJECT(dev), &spapr_iommu_ops,
"iommu-spapr",
@@ -241,11 +264,8 @@ static void spapr_tce_table_unrealize(DeviceState *dev,
Error **errp)
QLIST_REMOVE(tcet, list);
- if (!kvm_enabled() ||
- (kvmppc_remove_spapr_tce(tcet->table, tcet->fd,
- tcet->nb_table) != 0)) {
- g_free(tcet->table);
- }
+ spapr_tce_free_table(tcet->table, tcet->fd, tcet->nb_table);
+ tcet->fd = -1;
}
MemoryRegion *spapr_tce_get_iommu(sPAPRTCETable *tcet)
diff --git a/trace-events b/trace-events
index d494de1..6a94736 100644
--- a/trace-events
+++ b/trace-events
@@ -1430,7 +1430,7 @@ spapr_iommu_pci_get(uint64_t liobn, uint64_t ioba,
uint64_t ret, uint64_t tce) "
spapr_iommu_pci_indirect(uint64_t liobn, uint64_t ioba, uint64_t tce, uint64_t
iobaN, uint64_t tceN, uint64_t ret) "liobn=%"PRIx64" ioba=0x%"PRIx64"
tcelist=0x%"PRIx64" iobaN=0x%"PRIx64" tceN=0x%"PRIx64" ret=%"PRId64
spapr_iommu_pci_stuff(uint64_t liobn, uint64_t ioba, uint64_t tce_value,
uint64_t npages, uint64_t ret) "liobn=%"PRIx64" ioba=0x%"PRIx64"
tcevalue=0x%"PRIx64" npages=%"PRId64" ret=%"PRId64
spapr_iommu_xlate(uint64_t liobn, uint64_t ioba, uint64_t tce, unsigned perm,
unsigned pgsize) "liobn=%"PRIx64" 0x%"PRIx64" -> 0x%"PRIx64" perm=%u mask=%x"
-spapr_iommu_new_table(uint64_t liobn, void *tcet, void *table, int fd)
"liobn=%"PRIx64" tcet=%p table=%p fd=%d"
+spapr_iommu_new_table(uint64_t liobn, void *table, int fd) "liobn=%"PRIx64"
table=%p fd=%d"
# hw/ppc/ppc.c
ppc_tb_adjust(uint64_t offs1, uint64_t offs2, int64_t diff, int64_t seconds)
"adjusted from 0x%"PRIx64" to 0x%"PRIx64", diff %"PRId64" (%"PRId64"s)"
--
2.5.0.rc3
