diff --git a/Documentation/virtual/kvm/devices/vfio.txt b/Documentation/virtual/kvm/devices/vfio.txt
index ef51740c67ca..ddb5a6512ab3 100644
--- a/Documentation/virtual/kvm/devices/vfio.txt
+++ b/Documentation/virtual/kvm/devices/vfio.txt
@@ -16,7 +16,24 @@ Groups:
KVM_DEV_VFIO_GROUP attributes:
KVM_DEV_VFIO_GROUP_ADD: Add a VFIO group to VFIO-KVM device tracking
+ kvm_device_attr.addr points to an int32_t file descriptor
+ for the VFIO group.
KVM_DEV_VFIO_GROUP_DEL: Remove a VFIO group from VFIO-KVM device tracking
+ kvm_device_attr.addr points to an int32_t file descriptor
+ for the VFIO group.
+ KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: attaches a guest visible TCE table
+ allocated by sPAPR KVM.
+ kvm_device_attr.addr points to a struct:
-For each, kvm_device_attr.addr points to an int32_t file descriptor
-for the VFIO group.
+ struct kvm_vfio_spapr_tce {
+ __u32 argsz;
+ __s32 groupfd;
+ __s32 tablefd;
+ __u8 pad[4];
+ };
+
+ where
+ @argsz is the size of kvm_vfio_spapr_tce_liobn;
+ @groupfd is a file descriptor for a VFIO group;
+ @tablefd is a file descriptor for a TCE table allocated via
+ KVM_CREATE_SPAPR_TCE.diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 28350a294b1e..94774503c70d 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -191,6 +191,13 @@ struct kvmppc_pginfo {
atomic_t refcnt;
};
+struct kvmppc_spapr_tce_iommu_table {
+ struct rcu_head rcu;
+ struct list_head next;
+ struct iommu_table *tbl;
+ atomic_t refs;
+};
+
struct kvmppc_spapr_tce_table {
struct list_head list;
struct kvm *kvm;@@ -199,6 +206,7 @@ struct kvmppc_spapr_tce_table {
u32 page_shift;
u64 offset; /* in pages */
u64 size; /* window size in pages */
+ struct list_head iommu_tables;
struct page *pages[0];
};
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 0a21c8503974..17b947a0060d 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -163,6 +163,11 @@ extern long kvmppc_prepare_vrma(struct kvm *kvm,
extern void kvmppc_map_vrma(struct kvm_vcpu *vcpu,
struct kvm_memory_slot *memslot, unsigned long porder);
extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu);
+extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm,
+ int tablefd,
+ struct iommu_group *grp);
+extern void kvm_spapr_tce_detach_iommu_group(struct kvm *kvm,
+ struct iommu_group *grp);
extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
struct kvm_create_spapr_tce_64 *args);
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 810f74317987..9e4025724e28 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1068,6 +1068,7 @@ struct kvm_device_attr {
#define KVM_DEV_VFIO_GROUP 1
#define KVM_DEV_VFIO_GROUP_ADD 1
#define KVM_DEV_VFIO_GROUP_DEL 2
+#define KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE 3
enum kvm_device_type {
KVM_DEV_TYPE_FSL_MPIC_20 = 1,@@ -1089,6 +1090,13 @@ enum kvm_device_type {
KVM_DEV_TYPE_MAX,
};
+struct kvm_vfio_spapr_tce {
+ __u32 argsz;
+ __s32 groupfd;
+ __s32 tablefd;
+ __u8 pad[4];
+};
+
/*
* ioctls for VM fds
*/diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index 15df8ae627d9..f86d07781ee9 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -27,6 +27,8 @@
#include <linux/hugetlb.h>
#include <linux/list.h>
#include <linux/anon_inodes.h>
+#include <linux/iommu.h>
+#include <linux/file.h>
#include <asm/tlbflush.h>
#include <asm/kvm_ppc.h>
@@ -39,6 +41,7 @@
#include <asm/udbg.h>
#include <asm/iommu.h>
#include <asm/tce.h>
+#include <asm/mmu_context.h>
static unsigned long kvmppc_tce_pages(unsigned long iommu_pages)
{@@ -90,6 +93,25 @@ static long kvmppc_account_memlimit(unsigned long stt_pages, bool inc)
return ret;
}
+static void kvm_spapr_tce_iommu_table_free(struct rcu_head *head)
+{
+ struct kvmppc_spapr_tce_iommu_table *stit = container_of(head,
+ struct kvmppc_spapr_tce_iommu_table, rcu);
+
+ kfree(stit);
+}
+
+static void kvm_spapr_tce_iommu_table_put(
+ struct kvmppc_spapr_tce_iommu_table *stit)
+{
+ iommu_table_put(stit->tbl);
+ if (atomic_dec_return(&stit->refs))
+ return;
+
+ list_del_rcu(&stit->next);
+ call_rcu(&stit->rcu, kvm_spapr_tce_iommu_table_free);
+}
+
static void release_spapr_tce_table(struct rcu_head *head)
{
struct kvmppc_spapr_tce_table *stt = container_of(head,@@ -130,8 +152,23 @@ static int kvm_spapr_tce_release(struct inode *inode, struct file *filp)
{
struct kvmppc_spapr_tce_table *stt = filp->private_data;
+ kick_all_cpus_sync();
list_del_rcu(&stt->list);
+ mutex_lock(&stt->kvm->lock);
+
+ while (!list_empty(&stt->iommu_tables)) {
+ struct kvmppc_spapr_tce_iommu_table *stit;
+
+ stit = list_first_entry(&stt->iommu_tables,
+ struct kvmppc_spapr_tce_iommu_table, next);
+
+ while (atomic_read(&stit->refs))
+ kvm_spapr_tce_iommu_table_put(stit);
+ }
+
+ mutex_unlock(&stt->kvm->lock);
+
kvm_put_kvm(stt->kvm);
kvmppc_account_memlimit(@@ -146,6 +183,98 @@ static const struct file_operations kvm_spapr_tce_fops = {
.release = kvm_spapr_tce_release,
};
+extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
+ struct iommu_group *grp)
+{
+ struct kvmppc_spapr_tce_table *stt = NULL;
+ bool found = false;
+ struct iommu_table *tbl = NULL;
+ struct iommu_table_group *table_group;
+ long i;
+ struct kvmppc_spapr_tce_iommu_table *stit;
+ struct fd f;
+
+ f = fdget(tablefd);
+ if (!f.file)
+ return -EBADF;
+
+ list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) {
+ if (stt == f.file->private_data) {
+ found = true;
+ break;
+ }
+ }
+
+ fdput(f);
+
+ if (!found)
+ return -ENODEV;
+
+ table_group = iommu_group_get_iommudata(grp);
+ if (!table_group)
+ return -EFAULT;
+
+ for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+ struct iommu_table *tbltmp = table_group->tables[i];
+
+ if (!tbltmp)
+ continue;
+
+ if ((tbltmp->it_page_shift == stt->page_shift) &&
+ (tbltmp->it_offset == stt->offset)) {
+ tbl = tbltmp;
+ break;
+ }
+ }
+ if (!tbl)
+ return -ENODEV;
+
+ iommu_table_get(tbl);
+
+ list_for_each_entry_rcu(stit, &stt->iommu_tables, next) {
+ if (stit->tbl == tbl) {
+ atomic_inc(&stit->refs);
+ return 0;
+ }
+ }
+
+ stit = kzalloc(sizeof(*stit), GFP_KERNEL);
+ stit->tbl = tbl;
+ atomic_set(&stit->refs, 1);
+ list_add_rcu(&stit->next, &stt->iommu_tables);
+
+ return 0;
+}
+
+extern void kvm_spapr_tce_detach_iommu_group(struct kvm *kvm,
+ struct iommu_group *grp)
+{
+ struct kvmppc_spapr_tce_table *stt;
+ struct iommu_table_group *table_group;
+ struct kvmppc_spapr_tce_iommu_table *stit;
+
+ table_group = iommu_group_get_iommudata(grp);
+ if (!table_group)
+ return;
+
+ mutex_lock(&kvm->lock);
+
+ list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) {
+ list_for_each_entry_rcu(stit, &stt->iommu_tables, next) {
+ long i;
+
+ for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+ if (stit->tbl != table_group->tables[i])
+ continue;
+
+ kvm_spapr_tce_iommu_table_put(stit);
+ }
+ }
+ }
+
+ mutex_unlock(&kvm->lock);
+}
+
long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
struct kvm_create_spapr_tce_64 *args)
{@@ -181,6 +310,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
stt->offset = args->offset;
stt->size = size;
stt->kvm = kvm;
+ INIT_LIST_HEAD_RCU(&stt->iommu_tables);
for (i = 0; i < npages; i++) {
stt->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO);@@ -209,11 +339,161 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
return ret;
}
+static long kvmppc_tce_iommu_mapped_dec(struct kvm *kvm,
+ struct iommu_table *tbl, unsigned long entry)
+{
+ struct mm_iommu_table_group_mem_t *mem = NULL;
+ const unsigned long pgsize = 1ULL << tbl->it_page_shift;
+ unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+
+ if (!pua)
+ return H_HARDWARE;
+
+ mem = mm_iommu_lookup(kvm->mm, *pua, pgsize);
+ if (!mem)
+ return H_HARDWARE;
+
+ mm_iommu_mapped_dec(mem);
+
+ *pua = 0;
+
+ return H_SUCCESS;
+}
+
+static long kvmppc_tce_iommu_unmap(struct kvm *kvm,
+ struct iommu_table *tbl, unsigned long entry)
+{
+ enum dma_data_direction dir = DMA_NONE;
+ unsigned long hpa = 0;
+
+ if (iommu_tce_xchg(tbl, entry, &hpa, &dir))
+ return H_HARDWARE;
+
+ if (dir == DMA_NONE)
+ return H_SUCCESS;
+
+ return kvmppc_tce_iommu_mapped_dec(kvm, tbl, entry);
+}
+
+long kvmppc_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl,
+ unsigned long entry, unsigned long gpa,
+ enum dma_data_direction dir)
+{
+ long ret;
+ unsigned long hpa, ua, *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+ struct mm_iommu_table_group_mem_t *mem;
+
+ if (!pua)
+ /* it_userspace allocation might be delayed */
+ return H_TOO_HARD;
+
+ if (kvmppc_gpa_to_ua(kvm, gpa, &ua, NULL))
+ return H_HARDWARE;
+
+ mem = mm_iommu_lookup(kvm->mm, ua, 1ULL << tbl->it_page_shift);
+ if (!mem)
+ return H_HARDWARE;
+
+ if (mm_iommu_ua_to_hpa(mem, ua, &hpa))
+ return H_HARDWARE;
+
+ if (mm_iommu_mapped_inc(mem))
+ return H_HARDWARE;
+
+ ret = iommu_tce_xchg(tbl, entry, &hpa, &dir);
+ if (ret) {
+ mm_iommu_mapped_dec(mem);
+ return H_TOO_HARD;
+ }
+
+ if (dir != DMA_NONE)
+ kvmppc_tce_iommu_mapped_dec(kvm, tbl, entry);
+
+ *pua = ua;
+
+ return 0;
+}
+
+long kvmppc_h_put_tce_iommu(struct kvm_vcpu *vcpu,
+ struct iommu_table *tbl,
+ unsigned long liobn, unsigned long ioba,
+ unsigned long tce)
+{
+ long idx, ret = H_HARDWARE;
+ const unsigned long entry = ioba >> tbl->it_page_shift;
+ const unsigned long gpa = tce & ~(TCE_PCI_READ | TCE_PCI_WRITE);
+ const enum dma_data_direction dir = iommu_tce_direction(tce);
+
+ /* Clear TCE */
+ if (dir == DMA_NONE) {
+ if (iommu_tce_clear_param_check(tbl, ioba, 0, 1))
+ return H_PARAMETER;
+
+ return kvmppc_tce_iommu_unmap(vcpu->kvm, tbl, entry);
+ }
+
+ /* Put TCE */
+ if (iommu_tce_put_param_check(tbl, ioba, gpa))
+ return H_PARAMETER;
+
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
+ ret = kvmppc_tce_iommu_map(vcpu->kvm, tbl, entry, gpa, dir);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
+
+ return ret;
+}
+
+static long kvmppc_h_put_tce_indirect_iommu(struct kvm_vcpu *vcpu,
+ struct iommu_table *tbl, unsigned long ioba,
+ u64 __user *tces, unsigned long npages)
+{
+ unsigned long i, ret, tce, gpa;
+ const unsigned long entry = ioba >> tbl->it_page_shift;
+
+ for (i = 0; i < npages; ++i) {
+ gpa = be64_to_cpu(tces[i]) & ~(TCE_PCI_READ | TCE_PCI_WRITE);
+
+ if (iommu_tce_put_param_check(tbl, ioba +
+ (i << tbl->it_page_shift), gpa))
+ return H_PARAMETER;
+ }
+
+ for (i = 0; i < npages; ++i) {
+ tce = be64_to_cpu(tces[i]);
+ gpa = tce & ~(TCE_PCI_READ | TCE_PCI_WRITE);
+
+ ret = kvmppc_tce_iommu_map(vcpu->kvm, tbl, entry + i, gpa,
+ iommu_tce_direction(tce));
+ if (ret != H_SUCCESS)
+ return ret;
+ }
+
+ return H_SUCCESS;
+}
+
+long kvmppc_h_stuff_tce_iommu(struct kvm_vcpu *vcpu,
+ struct iommu_table *tbl,
+ unsigned long liobn, unsigned long ioba,
+ unsigned long tce_value, unsigned long npages)
+{
+ unsigned long i;
+ const unsigned long entry = ioba >> tbl->it_page_shift;
+
+ if (iommu_tce_clear_param_check(tbl, ioba, tce_value, npages))
+ return H_PARAMETER;
+
+ for (i = 0; i < npages; ++i)
+ kvmppc_tce_iommu_unmap(vcpu->kvm, tbl, entry + i);
+
+ return H_SUCCESS;
+}
+
long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
unsigned long ioba, unsigned long tce)
{
struct kvmppc_spapr_tce_table *stt;
long ret;
+ struct kvmppc_spapr_tce_iommu_table *stit;
/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
/* liobn, ioba, tce); */@@ -230,6 +510,12 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
if (ret != H_SUCCESS)
return ret;
+ list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+ ret = kvmppc_h_put_tce_iommu(vcpu, stit->tbl, liobn, ioba, tce);
+ if (ret != H_SUCCESS)
+ return ret;
+ }
+
kvmppc_tce_put(stt, ioba >> stt->page_shift, tce);
return H_SUCCESS;@@ -245,6 +531,7 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
unsigned long entry, ua = 0;
u64 __user *tces;
u64 tce;
+ struct kvmppc_spapr_tce_iommu_table *stit;
stt = kvmppc_find_table(vcpu->kvm, liobn);
if (!stt)
@@ -272,6 +559,13 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
}
tces = (u64 __user *) ua;
+ list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+ ret = kvmppc_h_put_tce_indirect_iommu(vcpu,
+ stit->tbl, ioba, tces, npages);
+ if (ret != H_SUCCESS)
+ goto unlock_exit;
+ }
+
for (i = 0; i < npages; ++i) {
if (get_user(tce, tces + i)) {
ret = H_TOO_HARD;@@ -299,6 +593,7 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
{
struct kvmppc_spapr_tce_table *stt;
long i, ret;
+ struct kvmppc_spapr_tce_iommu_table *stit;
stt = kvmppc_find_table(vcpu->kvm, liobn);
if (!stt)@@ -312,6 +607,13 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
if (tce_value & (TCE_PCI_WRITE | TCE_PCI_READ))
return H_PARAMETER;
+ list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+ ret = kvmppc_h_stuff_tce_iommu(vcpu, stit->tbl, liobn, ioba,
+ tce_value, npages);
+ if (ret != H_SUCCESS)
+ return ret;
+ }
+
for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value);
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 8a6834e6e1c8..4d6f01712a6d 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -190,11 +190,165 @@ static struct mm_iommu_table_group_mem_t *kvmppc_rm_iommu_lookup(
return mm_iommu_lookup_rm(vcpu->kvm->mm, ua, size);
}
+static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm_vcpu *vcpu,
+ struct iommu_table *tbl, unsigned long entry)
+{
+ struct mm_iommu_table_group_mem_t *mem = NULL;
+ const unsigned long pgsize = 1ULL << tbl->it_page_shift;
+ unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+
+ if (!pua)
+ return H_SUCCESS;
+
+ pua = (void *) vmalloc_to_phys(pua);
+ if (!pua)
+ return H_SUCCESS;
+
+ mem = kvmppc_rm_iommu_lookup(vcpu, *pua, pgsize);
+ if (!mem)
+ return H_HARDWARE;
+
+ mm_iommu_mapped_dec(mem);
+
+ *pua = 0;
+
+ return H_SUCCESS;
+}
+
+static long kvmppc_rm_tce_iommu_unmap(struct kvm_vcpu *vcpu,
+ struct iommu_table *tbl, unsigned long entry)
+{
+ enum dma_data_direction dir = DMA_NONE;
+ unsigned long hpa = 0;
+
+ if (iommu_tce_xchg_rm(tbl, entry, &hpa, &dir))
+ return H_HARDWARE;
+
+ if (dir == DMA_NONE)
+ return H_SUCCESS;
+
+ return kvmppc_rm_tce_iommu_mapped_dec(vcpu, tbl, entry);
+}
+
+long kvmppc_rm_tce_iommu_map(struct kvm_vcpu *vcpu, struct iommu_table *tbl,
+ unsigned long entry, unsigned long gpa,
+ enum dma_data_direction dir)
+{
+ long ret;
+ unsigned long hpa = 0, ua;
+ unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+ struct mm_iommu_table_group_mem_t *mem;
+
+ if (!pua)
+ /* it_userspace allocation might be delayed */
+ return H_TOO_HARD;
+
+ if (kvmppc_gpa_to_ua(vcpu->kvm, gpa, &ua, NULL))
+ return H_HARDWARE;
+
+ mem = kvmppc_rm_iommu_lookup(vcpu, ua, 1ULL << tbl->it_page_shift);
+ if (!mem)
+ return H_HARDWARE;
+
+ if (mm_iommu_ua_to_hpa_rm(mem, ua, &hpa))
+ return H_HARDWARE;
+
+ pua = (void *) vmalloc_to_phys(pua);
+ if (!pua)
+ return H_HARDWARE;
+
+ if (mm_iommu_mapped_inc(mem))
+ return H_HARDWARE;
+
+ ret = iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
+ if (ret) {
+ mm_iommu_mapped_dec(mem);
+ return H_TOO_HARD;
+ }
+
+ if (dir != DMA_NONE)
+ kvmppc_rm_tce_iommu_mapped_dec(vcpu, tbl, entry);
+
+ *pua = ua;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvmppc_rm_tce_iommu_map);
+
+static long kvmppc_rm_h_put_tce_iommu(struct kvm_vcpu *vcpu,
+ struct iommu_table *tbl, unsigned long liobn,
+ unsigned long ioba, unsigned long tce)
+{
+ const unsigned long entry = ioba >> tbl->it_page_shift;
+ const unsigned long gpa = tce & ~(TCE_PCI_READ | TCE_PCI_WRITE);
+ const enum dma_data_direction dir = iommu_tce_direction(tce);
+
+ /* Clear TCE */
+ if (dir == DMA_NONE) {
+ if (iommu_tce_clear_param_check(tbl, ioba, 0, 1))
+ return H_PARAMETER;
+
+ return kvmppc_rm_tce_iommu_unmap(vcpu, tbl, entry);
+ }
+
+ /* Put TCE */
+ if (iommu_tce_put_param_check(tbl, ioba, gpa))
+ return H_PARAMETER;
+
+ return kvmppc_rm_tce_iommu_map(vcpu, tbl, entry, gpa, dir);
+}
+
+static long kvmppc_rm_h_put_tce_indirect_iommu(struct kvm_vcpu *vcpu,
+ struct iommu_table *tbl, unsigned long ioba,
+ u64 *tces, unsigned long npages)
+{
+ unsigned long i, ret, tce, gpa;
+ const unsigned long entry = ioba >> tbl->it_page_shift;
+
+ for (i = 0; i < npages; ++i) {
+ gpa = be64_to_cpu(tces[i]) & ~(TCE_PCI_READ | TCE_PCI_WRITE);
+
+ if (iommu_tce_put_param_check(tbl, ioba +
+ (i << tbl->it_page_shift), gpa))
+ return H_PARAMETER;
+ }
+
+ for (i = 0; i < npages; ++i) {
+ tce = be64_to_cpu(tces[i]);
+ gpa = tce & ~(TCE_PCI_READ | TCE_PCI_WRITE);
+
+ ret = kvmppc_rm_tce_iommu_map(vcpu, tbl, entry + i, gpa,
+ iommu_tce_direction(tce));
+ if (ret != H_SUCCESS)
+ return ret;
+ }
+
+ return H_SUCCESS;
+}
+
+static long kvmppc_rm_h_stuff_tce_iommu(struct kvm_vcpu *vcpu,
+ struct iommu_table *tbl,
+ unsigned long liobn, unsigned long ioba,
+ unsigned long tce_value, unsigned long npages)
+{
+ unsigned long i;
+ const unsigned long entry = ioba >> tbl->it_page_shift;
+
+ if (iommu_tce_clear_param_check(tbl, ioba, tce_value, npages))
+ return H_PARAMETER;
+
+ for (i = 0; i < npages; ++i)
+ kvmppc_rm_tce_iommu_unmap(vcpu, tbl, entry + i);
+
+ return H_SUCCESS;
+}
+
long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
unsigned long ioba, unsigned long tce)
{
struct kvmppc_spapr_tce_table *stt;
long ret;
+ struct kvmppc_spapr_tce_iommu_table *stit;
/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
/* liobn, ioba, tce); */@@ -211,6 +365,13 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
if (ret != H_SUCCESS)
return ret;
+ list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+ ret = kvmppc_rm_h_put_tce_iommu(vcpu, stit->tbl,
+ liobn, ioba, tce);
+ if (ret != H_SUCCESS)
+ return ret;
+ }
+
kvmppc_tce_put(stt, ioba >> stt->page_shift, tce);
return H_SUCCESS;@@ -278,6 +439,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
* depend on hpt.
*/
struct mm_iommu_table_group_mem_t *mem;
+ struct kvmppc_spapr_tce_iommu_table *stit;
if (kvmppc_gpa_to_ua(vcpu->kvm, tce_list, &ua, NULL))
return H_TOO_HARD;
@@ -285,6 +447,13 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
mem = kvmppc_rm_iommu_lookup(vcpu, ua, IOMMU_PAGE_SIZE_4K);
if (!mem || mm_iommu_ua_to_hpa_rm(mem, ua, &tces))
return H_TOO_HARD;
+
+ list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+ ret = kvmppc_rm_h_put_tce_indirect_iommu(vcpu,
+ stit->tbl, ioba, (u64 *)tces, npages);
+ if (ret != H_SUCCESS)
+ return ret;
+ }
} else {
/*
* This is emulated devices case.@@ -334,6 +503,8 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
{
struct kvmppc_spapr_tce_table *stt;
long i, ret;
+ struct kvmppc_spapr_tce_iommu_table *stit;
+
stt = kvmppc_find_table(vcpu->kvm, liobn);
if (!stt)@@ -347,6 +518,13 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
if (tce_value & (TCE_PCI_WRITE | TCE_PCI_READ))
return H_PARAMETER;
+ list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+ ret = kvmppc_rm_h_stuff_tce_iommu(vcpu, stit->tbl,
+ liobn, ioba, tce_value, npages);
+ if (ret != H_SUCCESS)
+ return ret;
+ }
+
for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value);
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 70963c845e96..0e555ba998c0 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -536,6 +536,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
#ifdef CONFIG_PPC_BOOK3S_64
case KVM_CAP_SPAPR_TCE:
case KVM_CAP_SPAPR_TCE_64:
+ /* fallthrough */
+ case KVM_CAP_SPAPR_TCE_VFIO:
case KVM_CAP_PPC_ALLOC_HTAB:
case KVM_CAP_PPC_RTAS:
case KVM_CAP_PPC_FIXUP_HCALL:
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
index 1dd087da6f31..e82182f9dea9 100644
--- a/virt/kvm/vfio.c
+++ b/virt/kvm/vfio.c
@@ -20,6 +20,10 @@
#include <linux/vfio.h>
#include "vfio.h"
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+#include <asm/kvm_ppc.h>
+#endif
+
struct kvm_vfio_group {
struct list_head node;
struct vfio_group *vfio_group;@@ -76,6 +80,22 @@ static bool kvm_vfio_group_is_coherent(struct vfio_group *vfio_group)
return ret > 0;
}
+static int kvm_vfio_external_user_iommu_id(struct vfio_group *vfio_group)
+{
+ int (*fn)(struct vfio_group *);
+ int ret = -1;
+
+ fn = symbol_get(vfio_external_user_iommu_id);
+ if (!fn)
+ return ret;
+
+ ret = fn(vfio_group);
+
+ symbol_put(vfio_external_user_iommu_id);
+
+ return ret;
+}
+
/*
* Groups can use the same or different IOMMU domains. If the same then
* adding a new group may change the coherency of groups we've previously@@ -110,6 +130,22 @@ static void kvm_vfio_update_coherency(struct kvm_device *dev)
mutex_unlock(&kv->lock);
}
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+static void kvm_vfio_spapr_detach_iommu_group(struct kvm *kvm,
+ struct vfio_group *vfio_group)
+{
+ int group_id;
+ struct iommu_group *grp;
+
+ group_id = kvm_vfio_external_user_iommu_id(vfio_group);
+ grp = iommu_group_get_by_id(group_id);
+ if (grp) {
+ kvm_spapr_tce_detach_iommu_group(kvm, grp);
+ iommu_group_put(grp);
+ }
+}
+#endif
+
static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
{
struct kvm_vfio *kv = dev->private;@@ -185,6 +221,11 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
if (kvg->vfio_group != vfio_group)
continue;
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+ kvm_vfio_spapr_detach_iommu_group(dev->kvm,
+ kvg->vfio_group);
+#endif
+
list_del(&kvg->node);
kvm_vfio_group_put_external_user(kvg->vfio_group);
kfree(kvg);
@@ -201,6 +242,66 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
kvm_vfio_update_coherency(dev);
return ret;
+
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+ case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: {
+ struct kvm_vfio_spapr_tce param;
+ unsigned long minsz;
+ struct kvm_vfio *kv = dev->private;
+ struct vfio_group *vfio_group;
+ struct kvm_vfio_group *kvg;
+ struct fd f;
+
+ minsz = offsetofend(struct kvm_vfio_spapr_tce, pad);
+
+ if (copy_from_user(¶m, (void __user *)arg, minsz))
+ return -EFAULT;
+
+ if (param.argsz < minsz)
+ return -EINVAL;
+
+ f = fdget(param.groupfd);
+ if (!f.file)
+ return -EBADF;
+
+ vfio_group = kvm_vfio_group_get_external_user(f.file);
+ fdput(f);
+
+ if (IS_ERR(vfio_group))
+ return PTR_ERR(vfio_group);
+
+ ret = -ENOENT;
+
+ mutex_lock(&kv->lock);
+
+ list_for_each_entry(kvg, &kv->group_list, node) {
+ int group_id;
+ struct iommu_group *grp;
+
+ if (kvg->vfio_group != vfio_group)
+ continue;
+
+ group_id = kvm_vfio_external_user_iommu_id(
+ kvg->vfio_group);
+ grp = iommu_group_get_by_id(group_id);
+ if (!grp) {
+ ret = -EFAULT;
+ break;
+ }
+
+ ret = kvm_spapr_tce_attach_iommu_group(dev->kvm,
+ param.tablefd, grp);
+ iommu_group_put(grp);
+ break;
+ }
+
+ mutex_unlock(&kv->lock);
+
+ kvm_vfio_group_put_external_user(vfio_group);
+
+ return ret;
+ }
+#endif /* CONFIG_SPAPR_TCE_IOMMU */
}
return -ENXIO;@@ -225,6 +326,9 @@ static int kvm_vfio_has_attr(struct kvm_device *dev,
switch (attr->attr) {
case KVM_DEV_VFIO_GROUP_ADD:
case KVM_DEV_VFIO_GROUP_DEL:
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+ case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE:
+#endif
return 0;
}
@@ -240,6 +344,10 @@ static void kvm_vfio_destroy(struct kvm_device *dev)
struct kvm_vfio_group *kvg, *tmp;
list_for_each_entry_safe(kvg, tmp, &kv->group_list, node) {
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+ kvm_vfio_spapr_detach_iommu_group(dev->kvm,
+ kvg->vfio_group);
+#endif
kvm_vfio_group_put_external_user(kvg->vfio_group);
list_del(&kvg->node);
kfree(kvg);--
2.11.0