Currently, each unmapped page is handled as an individual iommu
region notification. Attempt to group contiguous unmap operations
into fewer notifications to reduce overhead.
Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com>
---
hw/s390x/s390-pci-inst.c | 51 ++++++++++++++++++++++++++++++++++++++++
1 file changed, 51 insertions(+)
diff --git a/hw/s390x/s390-pci-inst.c b/hw/s390x/s390-pci-inst.c
index 7cc4bcf850..66e764f901 100644
--- a/hw/s390x/s390-pci-inst.c
+++ b/hw/s390x/s390-pci-inst.c
@@ -640,6 +640,8 @@ static uint32_t s390_pci_update_iotlb(S390PCIIOMMU *iommu,
}
g_hash_table_remove(iommu->iotlb, &entry->iova);
inc_dma_avail(iommu);
+ /* Don't notify the iommu yet, maybe we can bundle contiguous unmaps */
+ goto out;
} else {
if (cache) {
if (cache->perm == entry->perm &&
@@ -663,15 +665,44 @@ static uint32_t s390_pci_update_iotlb(S390PCIIOMMU *iommu,
dec_dma_avail(iommu);
}
+ /*
+ * All associated iotlb entries have already been cleared, trigger the
+ * unmaps.
+ */
memory_region_notify_iommu(&iommu->iommu_mr, 0, event);
out:
return iommu->dma_limit ? iommu->dma_limit->avail : 1;
}
+static void s390_pci_batch_unmap(S390PCIIOMMU *iommu, uint64_t iova,
+ uint64_t len)
+{
+ uint64_t remain = len, start = iova, end = start + len - 1, mask, size;
+ IOMMUTLBEvent event = {
+ .type = IOMMU_NOTIFIER_UNMAP,
+ .entry = {
+ .target_as = &address_space_memory,
+ .translated_addr = 0,
+ .perm = IOMMU_NONE,
+ },
+ };
+
+ while (remain >= TARGET_PAGE_SIZE) {
+ mask = dma_aligned_pow2_mask(start, end, 64);
+ size = mask + 1;
+ event.entry.iova = start;
+ event.entry.addr_mask = mask;
+ memory_region_notify_iommu(&iommu->iommu_mr, 0, event);
+ start += size;
+ remain -= size;
+ }
+}
+
int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra)
{
CPUS390XState *env = &cpu->env;
+ uint64_t iova, coalesce = 0;
uint32_t fh;
uint16_t error = 0;
S390PCIBusDevice *pbdev;
@@ -742,6 +773,21 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra)
break;
}
+ /*
+ * If this is an unmap of a PTE, let's try to coalesce multiple unmaps
+ * into as few notifier events as possible.
+ */
+ if (entry.perm == IOMMU_NONE && entry.len == TARGET_PAGE_SIZE) {
+ if (coalesce == 0) {
+ iova = entry.iova;
+ }
+ coalesce += entry.len;
+ } else if (coalesce > 0) {
+ /* Unleash the coalesced unmap before processing a new map */
+ s390_pci_batch_unmap(iommu, iova, coalesce);
+ coalesce = 0;
+ }
+
start += entry.len;
while (entry.iova < start && entry.iova < end) {
if (dma_avail > 0 || entry.perm == IOMMU_NONE) {
@@ -759,6 +805,11 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra)
}
}
}
+ if (coalesce) {
+ /* Unleash the coalesced unmap before finishing rpcit */
+ s390_pci_batch_unmap(iommu, iova, coalesce);
+ coalesce = 0;
+ }
if (again && dma_avail > 0)
goto retry;
err:
--
2.37.3On Fri, 2022-10-28 at 15:47 -0400, Matthew Rosato wrote:
> Currently, each unmapped page is handled as an individual iommu
> region notification. Attempt to group contiguous unmap operations
> into fewer notifications to reduce overhead.
>
> Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com>
> ---
> hw/s390x/s390-pci-inst.c | 51
> ++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 51 insertions(+)
>
> diff --git a/hw/s390x/s390-pci-inst.c b/hw/s390x/s390-pci-inst.c
> index 7cc4bcf850..66e764f901 100644
> --- a/hw/s390x/s390-pci-inst.c
> +++ b/hw/s390x/s390-pci-inst.c
> @@ -640,6 +640,8 @@ static uint32_t
> s390_pci_update_iotlb(S390PCIIOMMU *iommu,
> }
> g_hash_table_remove(iommu->iotlb, &entry->iova);
> inc_dma_avail(iommu);
> + /* Don't notify the iommu yet, maybe we can bundle
> contiguous unmaps */
> + goto out;
> } else {
> if (cache) {
> if (cache->perm == entry->perm &&
> @@ -663,15 +665,44 @@ static uint32_t
> s390_pci_update_iotlb(S390PCIIOMMU *iommu,
> dec_dma_avail(iommu);
> }
>
> + /*
> + * All associated iotlb entries have already been cleared,
> trigger the
> + * unmaps.
> + */
> memory_region_notify_iommu(&iommu->iommu_mr, 0, event);
>
> out:
> return iommu->dma_limit ? iommu->dma_limit->avail : 1;
> }
>
> +static void s390_pci_batch_unmap(S390PCIIOMMU *iommu, uint64_t iova,
> + uint64_t len)
> +{
> + uint64_t remain = len, start = iova, end = start + len - 1,
> mask, size;
> + IOMMUTLBEvent event = {
> + .type = IOMMU_NOTIFIER_UNMAP,
> + .entry = {
> + .target_as = &address_space_memory,
> + .translated_addr = 0,
> + .perm = IOMMU_NONE,
> + },
> + };
> +
> + while (remain >= TARGET_PAGE_SIZE) {
> + mask = dma_aligned_pow2_mask(start, end, 64);
> + size = mask + 1;
> + event.entry.iova = start;
> + event.entry.addr_mask = mask;
> + memory_region_notify_iommu(&iommu->iommu_mr, 0, event);
> + start += size;
> + remain -= size;
> + }
> +}
> +
> int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2,
> uintptr_t ra)
> {
> CPUS390XState *env = &cpu->env;
> + uint64_t iova, coalesce = 0;
> uint32_t fh;
> uint16_t error = 0;
> S390PCIBusDevice *pbdev;
> @@ -742,6 +773,21 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1,
> uint8_t r2, uintptr_t ra)
> break;
> }
>
> + /*
> + * If this is an unmap of a PTE, let's try to coalesce
> multiple unmaps
> + * into as few notifier events as possible.
> + */
> + if (entry.perm == IOMMU_NONE && entry.len ==
> TARGET_PAGE_SIZE) {
> + if (coalesce == 0) {
> + iova = entry.iova;
> + }
> + coalesce += entry.len;
> + } else if (coalesce > 0) {
> + /* Unleash the coalesced unmap before processing a new
> map */
> + s390_pci_batch_unmap(iommu, iova, coalesce);
> + coalesce = 0;
> + }
> +
> start += entry.len;
> while (entry.iova < start && entry.iova < end) {
> if (dma_avail > 0 || entry.perm == IOMMU_NONE) {
> @@ -759,6 +805,11 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1,
> uint8_t r2, uintptr_t ra)
> }
> }
> }
> + if (coalesce) {
I'd guess this should be "coalesce > 0" as above. Regardless,
Reviewed-by: Eric Farman <farman@linux.ibm.com>
> + /* Unleash the coalesced unmap before finishing rpcit */
> + s390_pci_batch_unmap(iommu, iova, coalesce);
> + coalesce = 0;
> + }
> if (again && dma_avail > 0)
> goto retry;
> err:
© 2016 - 2026 Red Hat, Inc.