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 | 46 +++++++++++++++++++++++++++++++++++++
arch/powerpc/include/asm/kvm_host.h | 4 +++-
arch/powerpc/include/asm/kvm_ppc.h | 2 +-
arch/powerpc/include/uapi/asm/kvm.h | 9 ++++++++
arch/powerpc/kvm/book3s_64_vio.c | 4 +++-
arch/powerpc/kvm/powerpc.c | 24 ++++++++++++++++++-
include/uapi/linux/kvm.h | 2 ++
7 files changed, 87 insertions(+), 4 deletions(-)
diff --git a/Documentation/virtual/kvm/api.txt
b/Documentation/virtual/kvm/api.txt
index b4f5365..8a2a2da 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -2484,6 +2484,52 @@ calls by the guest for that service will be passed to
userspace to be
handled.
+4.87 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;
+ __u64 window_size;
+ __u64 bus_offset;
+ __u32 page_shift;
+ __u32 flags;
+};
+
+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_size field tells a size
+of the pages in this window, can be 4K, 64K, 16MB, etc. 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_host.h
b/arch/powerpc/include/asm/kvm_host.h
index 1eaea2d..260a810 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -179,7 +179,9 @@ struct kvmppc_spapr_tce_table {
struct list_head list;
struct kvm *kvm;
u64 liobn;
- u32 window_size;
+ u64 window_size;
+ u64 bus_offset;
+ u32 page_shift;
struct page *pages[0];
};
diff --git a/arch/powerpc/include/asm/kvm_ppc.h
b/arch/powerpc/include/asm/kvm_ppc.h
index 4096f16..b472fd3 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -126,7 +126,7 @@ extern void kvmppc_map_vrma(struct kvm_vcpu *vcpu,
extern int kvmppc_pseries_do_hcall(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 long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
unsigned long ioba, unsigned long tce);
extern long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
diff --git a/arch/powerpc/include/uapi/asm/kvm.h
b/arch/powerpc/include/uapi/asm/kvm.h
index a6665be..0ada7b4 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;
+ __u64 window_size;
+ __u64 bus_offset;
+ __u32 page_shift;
+ __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 54cf9bc..230fa5f 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -98,7 +98,7 @@ 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;
@@ -120,6 +120,8 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
stt->liobn = args->liobn;
stt->window_size = args->window_size;
+ stt->bus_offset = args->bus_offset;
+ stt->page_shift = args->page_shift;
stt->kvm = kvm;
for (i = 0; i < npages; i++) {
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 3cf541a..3b78b8d 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"
@@ -373,6 +374,7 @@ 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:
#ifdef CONFIG_KVM_XICS
@@ -1077,13 +1079,33 @@ 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.window_size = create_tce.window_size;
+ create_tce_64.bus_offset = 0;
+ create_tce_64.page_shift = 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 e6972bf..c435cbb 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1018,6 +1018,8 @@ 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
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
