The existing KVM_CREATE_SPAPR_TCE only supports 32bit windows which is not
enough for directly mapped windows as the guest can get more than 4GB.
This adds KVM_CREATE_SPAPR_TCE_64 ioctl and advertises it
via KVM_CAP_SPAPR_TCE_64 capability.
Since 64bit windows are to support Dynamic DMA windows (DDW), let's add
@bus_offset and @page_shift which are also required by DDW.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
Documentation/virtual/kvm/api.txt | 51 +++++++++++++++++++++++++++++++++++++
arch/powerpc/include/asm/kvm_ppc.h | 2 +-
arch/powerpc/include/uapi/asm/kvm.h | 9 +++++++
arch/powerpc/kvm/book3s_64_vio.c | 10 +++++---
arch/powerpc/kvm/powerpc.c | 25 +++++++++++++++++-
include/uapi/linux/kvm.h | 2 ++
6 files changed, 94 insertions(+), 5 deletions(-)
diff --git a/Documentation/virtual/kvm/api.txt
b/Documentation/virtual/kvm/api.txt
index e1c72bf..b4695ea 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -2520,6 +2520,57 @@ an implementation for these despite the in kernel
acceleration.
This capability is always enabled.
+4.88 KVM_CREATE_SPAPR_TCE_64
+
+Capability: KVM_CAP_SPAPR_TCE_64
+Architectures: powerpc
+Type: vm ioctl
+Parameters: struct kvm_create_spapr_tce_64 (in)
+Returns: file descriptor for manipulating the created TCE table
+
+This is an extension for KVM_CAP_SPAPR_TCE which only supports 32bit
+windows.
+
+This creates a virtual TCE (translation control entry) table, which
+is an IOMMU for PAPR-style virtual I/O. It is used to translate
+logical addresses used in virtual I/O into guest physical addresses,
+and provides a scatter/gather capability for PAPR virtual I/O.
+
+/* for KVM_CAP_SPAPR_TCE_64 */
+struct kvm_create_spapr_tce_64 {
+ __u64 liobn;
+ __u32 page_shift;
+ __u64 offset; /* in pages */
+ __u64 size; /* in pages */
+ __u32 flags;
+};
+
+
+!!! FIXME !!!
+
+
+The liobn field gives the logical IO bus number for which to create a
+TCE table. The window_size field specifies the size of the DMA window
+which this TCE table will translate - the table will contain one 64
+bit TCE entry for every IOMMU page. The bus_offset field tells where
+this window is mapped on the IO bus. The page_shift field tells the size
+of the pages in this window (for example, 10, 16, 24 for 4K, 64K, 16MB
+page sizes respectively). The flags field is not used at the moment
+but provides the room for extensions.
+
+When the guest issues an H_PUT_TCE/H_PUT_TCE_INDIRECT/H_STUFF_TCE hcall
+on a liobn for which a TCE table has been created using this ioctl(),
+the kernel will handle it in real or virtual mode, updating the TCE table.
+If liobn has not been registered with this ioctl, H_PUT_TCE/etc calls
+will cause a vm exit and must be handled by userspace.
+
+The return value is a file descriptor which can be passed to mmap(2)
+to map the created TCE table into userspace. This lets userspace read
+the entries written by kernel-handled H_PUT_TCE calls, and also lets
+userspace update the TCE table directly which is useful in some
+circumstances.
+
+
5. The kvm_run structure
------------------------
diff --git a/arch/powerpc/include/asm/kvm_ppc.h
b/arch/powerpc/include/asm/kvm_ppc.h
index b84ed80..e0a68ef 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -128,7 +128,7 @@ extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu);
extern int kvmppc_spapr_tce_init(struct kvm_vcpu *vcpu);
extern void kvmppc_spapr_tce_free(struct kvm_vcpu *vcpu);
extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
- struct kvm_create_spapr_tce *args);
+ struct kvm_create_spapr_tce_64 *args);
extern struct kvmppc_spapr_tce_table *kvmppc_find_tce_table(
struct kvm *kvm, unsigned long liobn);
extern long kvmppc_ioba_validate(struct kvmppc_spapr_tce_table *stt,
diff --git a/arch/powerpc/include/uapi/asm/kvm.h
b/arch/powerpc/include/uapi/asm/kvm.h
index 2bc4a94..4452f6e 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -333,6 +333,15 @@ struct kvm_create_spapr_tce {
__u32 window_size;
};
+/* for KVM_CAP_SPAPR_TCE_64 */
+struct kvm_create_spapr_tce_64 {
+ __u64 liobn;
+ __u32 page_shift;
+ __u64 offset; /* in pages */
+ __u64 size; /* in pages */
+ __u32 flags;
+};
+
/* for KVM_ALLOCATE_RMA */
struct kvm_allocate_rma {
__u64 rma_size;
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index f2c8e4d..2c6ab20 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -155,20 +155,23 @@ static const struct file_operations kvm_spapr_tce_fops = {
};
long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
- struct kvm_create_spapr_tce *args)
+ struct kvm_create_spapr_tce_64 *args)
{
struct kvmppc_spapr_tce_table *stt = NULL;
long npages, size;
int ret = -ENOMEM;
int i;
+ if (!args->size)
+ return -EINVAL;
+
/* Check this LIOBN hasn't been previously allocated */
list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
if (stt->liobn == args->liobn)
return -EBUSY;
}
- size = args->window_size >> IOMMU_PAGE_SHIFT_4K;
+ size = args->size;
npages = kvmppc_stt_npages(size);
ret = kvmppc_account_memlimit(npages + 1);
if (ret)
@@ -180,7 +183,8 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
goto fail;
stt->liobn = args->liobn;
- stt->page_shift = IOMMU_PAGE_SHIFT_4K;
+ stt->page_shift = args->page_shift;
+ stt->offset = args->offset;
stt->size = size;
stt->kvm = kvm;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index e66793b..4d674ed 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -33,6 +33,7 @@
#include <asm/tlbflush.h>
#include <asm/cputhreads.h>
#include <asm/irqflags.h>
+#include <asm/iommu.h>
#include "timing.h"
#include "irq.h"
#include "../mm/mmu_decl.h"
@@ -414,6 +415,7 @@ int kvm_dev_ioctl_check_extension(long ext)
#ifdef CONFIG_PPC_BOOK3S_64
case KVM_CAP_SPAPR_TCE:
+ case KVM_CAP_SPAPR_TCE_64:
case KVM_CAP_PPC_ALLOC_HTAB:
case KVM_CAP_PPC_RTAS:
case KVM_CAP_PPC_FIXUP_HCALL:
@@ -1122,13 +1124,34 @@ long kvm_arch_vm_ioctl(struct file *filp,
break;
}
#ifdef CONFIG_PPC_BOOK3S_64
+ case KVM_CREATE_SPAPR_TCE_64: {
+ struct kvm_create_spapr_tce_64 create_tce_64;
+
+ r = -EFAULT;
+ if (copy_from_user(&create_tce_64, argp, sizeof(create_tce_64)))
+ goto out;
+ if (create_tce_64.flags) {
+ r = -EINVAL;
+ goto out;
+ }
+ r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce_64);
+ goto out;
+ }
case KVM_CREATE_SPAPR_TCE: {
struct kvm_create_spapr_tce create_tce;
+ struct kvm_create_spapr_tce_64 create_tce_64;
r = -EFAULT;
if (copy_from_user(&create_tce, argp, sizeof(create_tce)))
goto out;
- r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce);
+
+ create_tce_64.liobn = create_tce.liobn;
+ create_tce_64.page_shift = IOMMU_PAGE_SHIFT_4K;
+ create_tce_64.offset = 0;
+ create_tce_64.size = create_tce.window_size >>
+ IOMMU_PAGE_SHIFT_4K;
+ create_tce_64.flags = 0;
+ r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce_64);
goto out;
}
case KVM_PPC_GET_SMMU_INFO: {
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 65c2689..3beb542 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1033,6 +1033,8 @@ struct kvm_s390_ucas_mapping {
/* Available with KVM_CAP_PPC_ALLOC_HTAB */
#define KVM_PPC_ALLOCATE_HTAB _IOWR(KVMIO, 0xa7, __u32)
#define KVM_CREATE_SPAPR_TCE _IOW(KVMIO, 0xa8, struct
kvm_create_spapr_tce)
+#define KVM_CREATE_SPAPR_TCE_64 _IOW(KVMIO, 0xa8, \
+ struct kvm_create_spapr_tce_64)
/* Available with KVM_CAP_RMA */
#define KVM_ALLOCATE_RMA _IOR(KVMIO, 0xa9, struct kvm_allocate_rma)
/* Available with KVM_CAP_PPC_HTAB_FD */
--
2.0.0
_______________________________________________
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev
