diff --git a/Documentation/virtual/kvm/devices/vfio.txt b/Documentation/virtual/kvm/devices/vfio.txt
index ef51740c67ca..f95d867168ea 100644
--- a/Documentation/virtual/kvm/devices/vfio.txt
+++ b/Documentation/virtual/kvm/devices/vfio.txt
@@ -16,7 +16,25 @@ 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;
+ __u32 flags;
+ __s32 groupfd;
+ __s32 tablefd;
+ };
+
+ where
+ @argsz is the size of kvm_vfio_spapr_tce_liobn;
+ @flags are not supported now, must be zero;
+ @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 7bba8f415627..857ae2c6aa39 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 vfio_group *group;
+ struct iommu_table *tbl;
+};
+
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 72c2a155641f..66de7e73b3d3 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -164,6 +164,10 @@ 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 vfio_group *group);
+extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm,
+ struct vfio_group *group);
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 f5a52ffb6b58..e743cb0d176e 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1088,6 +1088,7 @@ 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,@@ -1109,6 +1110,13 @@ enum kvm_device_type {
KVM_DEV_TYPE_MAX,
};
+struct kvm_vfio_spapr_tce {
+ __u32 argsz;
+ __u32 flags;
+ __s32 groupfd;
+ __s32 tablefd;
+};
+
/*
* ioctls for VM fds
*/diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index e96a4590464c..be18cda01e1b 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -28,6 +28,10 @@
#include <linux/hugetlb.h>
#include <linux/list.h>
#include <linux/anon_inodes.h>
+#include <linux/iommu.h>
+#include <linux/file.h>
+#include <linux/vfio.h>
+#include <linux/module.h>
#include <asm/tlbflush.h>
#include <asm/kvm_ppc.h>
@@ -40,6 +44,36 @@
#include <asm/udbg.h>
#include <asm/iommu.h>
#include <asm/tce.h>
+#include <asm/mmu_context.h>
+
+static void kvm_vfio_group_put_external_user(struct vfio_group *vfio_group)
+{
+ void (*fn)(struct vfio_group *);
+
+ fn = symbol_get(vfio_group_put_external_user);
+ if (WARN_ON(!fn))
+ return;
+
+ fn(vfio_group);
+
+ symbol_put(vfio_group_put_external_user);
+}
+
+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;
+}
static unsigned long kvmppc_tce_pages(unsigned long iommu_pages)
{@@ -91,6 +125,130 @@ 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);
+
+ iommu_table_put(stit->tbl);
+ kvm_vfio_group_put_external_user(stit->group);
+
+ kfree(stit);
+}
+
+static void kvm_spapr_tce_liobn_release_iommu_group(
+ struct kvmppc_spapr_tce_table *stt,
+ struct vfio_group *group)
+{
+ struct kvmppc_spapr_tce_iommu_table *stit, *tmp;
+
+ list_for_each_entry_safe(stit, tmp, &stt->iommu_tables, next) {
+ if (group && (stit->group != group))
+ continue;
+
+ list_del_rcu(&stit->next);
+
+ call_rcu(&stit->rcu, kvm_spapr_tce_iommu_table_free);
+ }
+}
+
+extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm,
+ struct vfio_group *group)
+{
+ struct kvmppc_spapr_tce_table *stt;
+
+ list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list)
+ kvm_spapr_tce_liobn_release_iommu_group(stt, group);
+}
+
+extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
+ struct vfio_group *group)
+{
+ struct kvmppc_spapr_tce_table *stt = NULL;
+ bool found = false;
+ struct iommu_table *tbl = NULL;
+ struct iommu_table_group *table_group;
+ long i, ret = 0;
+ struct kvmppc_spapr_tce_iommu_table *stit;
+ struct fd f;
+ int group_id;
+ struct iommu_group *grp;
+
+ group_id = kvm_vfio_external_user_iommu_id(group);
+ grp = iommu_group_get_by_id(group_id);
+ if (WARN_ON(!grp))
+ return -EIO;
+
+ f = fdget(tablefd);
+ if (!f.file) {
+ ret = -EBADF;
+ goto put_exit;
+ }
+
+ 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) {
+ ret = -EINVAL;
+ goto put_exit;
+ }
+
+ table_group = iommu_group_get_iommudata(grp);
+ if (WARN_ON(!table_group)) {
+ ret = -EFAULT;
+ goto put_exit;
+ }
+
+ for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+ struct iommu_table *tbltmp = table_group->tables[i];
+
+ if (!tbltmp)
+ continue;
+
+ /*
+ * Make sure hardware table parameters are exactly the same;
+ * this is used in the TCE handlers where boundary checks
+ * use only the first attached table.
+ */
+ if ((tbltmp->it_page_shift == stt->page_shift) &&
+ (tbltmp->it_offset == stt->offset) &&
+ (tbltmp->it_size == stt->size)) {
+ tbl = tbltmp;
+ break;
+ }
+ }
+ if (!tbl) {
+ ret = -EINVAL;
+ goto put_exit;
+ }
+
+ list_for_each_entry_rcu(stit, &stt->iommu_tables, next) {
+ if ((stit->tbl == tbl) && (stit->group == group)) {
+ ret = -EBUSY;
+ goto put_exit;
+ }
+ }
+
+ iommu_table_get(tbl);
+
+ stit = kzalloc(sizeof(*stit), GFP_KERNEL);
+ stit->tbl = tbl;
+ stit->group = group;
+
+ list_add_rcu(&stit->next, &stt->iommu_tables);
+
+put_exit:
+ iommu_group_put(grp);
+
+ return ret;
+}
+
static void release_spapr_tce_table(struct rcu_head *head)
{
struct kvmppc_spapr_tce_table *stt = container_of(head,@@ -133,6 +291,8 @@ static int kvm_spapr_tce_release(struct inode *inode, struct file *filp)
list_del_rcu(&stt->list);
+ kvm_spapr_tce_liobn_release_iommu_group(stt, NULL /* release all */);
+
kvm_put_kvm(stt->kvm);
kvmppc_account_memlimit(
@@ -183,6 +343,7 @@ 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);@@ -211,11 +372,101 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
return ret;
}
+static void kvmppc_clear_tce(struct iommu_table *tbl, unsigned long entry)
+{
+ unsigned long hpa = 0;
+ enum dma_data_direction dir = DMA_NONE;
+
+ iommu_tce_xchg(tbl, entry, &hpa, &dir);
+}
+
+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)
+ /* it_userspace allocation might be delayed */
+ return H_TOO_HARD;
+
+ mem = mm_iommu_lookup(kvm->mm, *pua, pgsize);
+ if (!mem)
+ return H_TOO_HARD;
+
+ 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;
+ long ret;
+
+ if (WARN_ON_ONCE(iommu_tce_xchg(tbl, entry, &hpa, &dir)))
+ return H_HARDWARE;
+
+ if (dir == DMA_NONE)
+ return H_SUCCESS;
+
+ ret = kvmppc_tce_iommu_mapped_dec(kvm, tbl, entry);
+ if (ret != H_SUCCESS)
+ iommu_tce_xchg(tbl, entry, &hpa, &dir);
+
+ return ret;
+}
+
+long kvmppc_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl,
+ unsigned long entry, unsigned long ua,
+ enum dma_data_direction dir)
+{
+ long ret;
+ unsigned long hpa, *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;
+
+ mem = mm_iommu_lookup(kvm->mm, ua, 1ULL << tbl->it_page_shift);
+ if (!mem)
+ /* This only handles v2 IOMMU type, v1 is handled via ioctl() */
+ return H_TOO_HARD;
+
+ if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, &hpa)))
+ return H_HARDWARE;
+
+ if (mm_iommu_mapped_inc(mem))
+ return H_CLOSED;
+
+ ret = iommu_tce_xchg(tbl, entry, &hpa, &dir);
+ if (WARN_ON_ONCE(ret)) {
+ mm_iommu_mapped_dec(mem);
+ return H_HARDWARE;
+ }
+
+ if (dir != DMA_NONE)
+ kvmppc_tce_iommu_mapped_dec(kvm, tbl, entry);
+
+ *pua = ua;
+
+ return 0;
+}
+
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;
+ long ret, idx;
+ struct kvmppc_spapr_tce_iommu_table *stit;
+ unsigned long entry, ua = 0;
+ enum dma_data_direction dir;
/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
/* liobn, ioba, tce); */@@ -232,7 +483,35 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
if (ret != H_SUCCESS)
return ret;
- kvmppc_tce_put(stt, ioba >> stt->page_shift, tce);
+ dir = iommu_tce_direction(tce);
+ if ((dir != DMA_NONE) && kvmppc_gpa_to_ua(vcpu->kvm,
+ tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL))
+ return H_PARAMETER;
+
+ entry = ioba >> stt->page_shift;
+
+ list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+ if (dir == DMA_NONE) {
+ ret = kvmppc_tce_iommu_unmap(vcpu->kvm,
+ stit->tbl, entry);
+ } else {
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
+ ret = kvmppc_tce_iommu_map(vcpu->kvm, stit->tbl,
+ entry, ua, dir);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
+ }
+
+ if (ret == H_SUCCESS)
+ continue;
+
+ if (ret == H_TOO_HARD)
+ return ret;
+
+ WARN_ON_ONCE(1);
+ kvmppc_clear_tce(stit->tbl, entry);
+ }
+
+ kvmppc_tce_put(stt, entry, tce);
return H_SUCCESS;
}@@ -247,6 +526,7 @@ 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)
@@ -285,6 +565,26 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
if (ret != H_SUCCESS)
goto unlock_exit;
+ if (kvmppc_gpa_to_ua(vcpu->kvm,
+ tce & ~(TCE_PCI_READ | TCE_PCI_WRITE),
+ &ua, NULL))
+ return H_PARAMETER;
+
+ list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+ ret = kvmppc_tce_iommu_map(vcpu->kvm,
+ stit->tbl, entry + i, ua,
+ iommu_tce_direction(tce));
+
+ if (ret == H_SUCCESS)
+ continue;
+
+ if (ret == H_TOO_HARD)
+ goto unlock_exit;
+
+ WARN_ON_ONCE(1);
+ kvmppc_clear_tce(stit->tbl, entry);
+ }
+
kvmppc_tce_put(stt, entry + i, tce);
}
@@ -301,6 +601,7 @@ 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)@@ -314,6 +615,24 @@ 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) {
+ unsigned long entry = ioba >> stit->tbl->it_page_shift;
+
+ for (i = 0; i < npages; ++i) {
+ ret = kvmppc_tce_iommu_unmap(vcpu->kvm,
+ stit->tbl, entry + i);
+
+ if (ret == H_SUCCESS)
+ continue;
+
+ if (ret == H_TOO_HARD)
+ return ret;
+
+ WARN_ON_ONCE(1);
+ kvmppc_clear_tce(stit->tbl, entry);
+ }
+ }
+
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 440d3ab5dc32..eda0a8f6fae8 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -40,6 +40,31 @@
#include <asm/iommu.h>
#include <asm/tce.h>
+#ifdef CONFIG_BUG
+
+#define WARN_ON_ONCE_RM(condition) ({ \
+ static bool __section(.data.unlikely) __warned; \
+ int __ret_warn_once = !!(condition); \
+ \
+ if (unlikely(__ret_warn_once && !__warned)) { \
+ __warned = true; \
+ pr_err("WARN_ON_ONCE_RM: (%s) at %s:%u\n", \
+ __stringify(condition), \
+ __func__, __LINE__); \
+ dump_stack(); \
+ } \
+ unlikely(__ret_warn_once); \
+})
+
+#else
+
+#define WARN_ON_ONCE_RM(condition) ({ \
+ int __ret_warn_on = !!(condition); \
+ unlikely(__ret_warn_on); \
+})
+
+#endif
+
#define TCES_PER_PAGE (PAGE_SIZE / sizeof(u64))
/*@@ -161,11 +186,117 @@ long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa,
EXPORT_SYMBOL_GPL(kvmppc_gpa_to_ua);
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+static void kvmppc_rm_clear_tce(struct iommu_table *tbl, unsigned long entry)
+{
+ unsigned long hpa = 0;
+ enum dma_data_direction dir = DMA_NONE;
+
+ iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
+}
+
+static long kvmppc_rm_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)
+ /* it_userspace allocation might be delayed */
+ return H_TOO_HARD;
+
+ pua = (void *) vmalloc_to_phys(pua);
+ if (WARN_ON_ONCE_RM(!pua))
+ return H_HARDWARE;
+
+ mem = mm_iommu_lookup_rm(kvm->mm, *pua, pgsize);
+ if (!mem)
+ return H_TOO_HARD;
+
+ mm_iommu_mapped_dec(mem);
+
+ *pua = 0;
+
+ return H_SUCCESS;
+}
+
+static long kvmppc_rm_tce_iommu_unmap(struct kvm *kvm,
+ struct iommu_table *tbl, unsigned long entry)
+{
+ enum dma_data_direction dir = DMA_NONE;
+ unsigned long hpa = 0;
+ long ret;
+
+ if (iommu_tce_xchg_rm(tbl, entry, &hpa, &dir))
+ /*
+ * real mode xchg can fail if struct page crosses
+ * a page boundary
+ */
+ return H_TOO_HARD;
+
+ if (dir == DMA_NONE)
+ return H_SUCCESS;
+
+ ret = kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry);
+ if (ret)
+ iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
+
+ return ret;
+}
+
+static long kvmppc_rm_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl,
+ unsigned long entry, unsigned long ua,
+ enum dma_data_direction dir)
+{
+ long ret;
+ unsigned long hpa = 0;
+ 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;
+
+ mem = mm_iommu_lookup_rm(kvm->mm, ua, 1ULL << tbl->it_page_shift);
+ if (!mem)
+ return H_TOO_HARD;
+
+ if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, &hpa)))
+ return H_HARDWARE;
+
+ pua = (void *) vmalloc_to_phys(pua);
+ if (WARN_ON_ONCE_RM(!pua))
+ return H_HARDWARE;
+
+ if (WARN_ON_ONCE_RM(mm_iommu_mapped_inc(mem)))
+ return H_CLOSED;
+
+ ret = iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
+ if (ret) {
+ mm_iommu_mapped_dec(mem);
+ /*
+ * real mode xchg can fail if struct page crosses
+ * a page boundary
+ */
+ return H_TOO_HARD;
+ }
+
+ if (dir != DMA_NONE)
+ kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry);
+
+ *pua = ua;
+
+ return 0;
+}
+
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;
+ unsigned long entry, ua = 0;
+ enum dma_data_direction dir;
/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
/* liobn, ioba, tce); */@@ -182,7 +313,32 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
if (ret != H_SUCCESS)
return ret;
- kvmppc_tce_put(stt, ioba >> stt->page_shift, tce);
+ dir = iommu_tce_direction(tce);
+ if ((dir != DMA_NONE) && kvmppc_gpa_to_ua(vcpu->kvm,
+ tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL))
+ return H_PARAMETER;
+
+ entry = ioba >> stt->page_shift;
+
+ list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+ if (dir == DMA_NONE)
+ ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm,
+ stit->tbl, entry);
+ else
+ ret = kvmppc_rm_tce_iommu_map(vcpu->kvm,
+ stit->tbl, entry, ua, dir);
+
+ if (ret == H_SUCCESS)
+ continue;
+
+ if (ret == H_TOO_HARD)
+ return ret;
+
+ WARN_ON_ONCE_RM(1);
+ kvmppc_rm_clear_tce(stit->tbl, entry);
+ }
+
+ kvmppc_tce_put(stt, entry, tce);
return H_SUCCESS;
}@@ -223,6 +379,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
unsigned long tces, entry, ua = 0;
unsigned long *rmap = NULL;
bool prereg = false;
+ struct kvmppc_spapr_tce_iommu_table *stit;
stt = kvmppc_find_table(vcpu->kvm, liobn);
if (!stt)
@@ -270,6 +427,8 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
return H_TOO_HARD;
rmap = (void *) vmalloc_to_phys(rmap);
+ if (WARN_ON_ONCE_RM(!rmap))
+ return H_HARDWARE;
/*
* Synchronize with the MMU notifier callbacks in
@@ -293,6 +452,27 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
if (ret != H_SUCCESS)
goto unlock_exit;
+ ua = 0;
+ if (kvmppc_gpa_to_ua(vcpu->kvm,
+ tce & ~(TCE_PCI_READ | TCE_PCI_WRITE),
+ &ua, NULL))
+ return H_PARAMETER;
+
+ list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+ ret = kvmppc_rm_tce_iommu_map(vcpu->kvm,
+ stit->tbl, entry + i, ua,
+ iommu_tce_direction(tce));
+
+ if (ret == H_SUCCESS)
+ continue;
+
+ if (ret == H_TOO_HARD)
+ goto unlock_exit;
+
+ WARN_ON_ONCE_RM(1);
+ kvmppc_rm_clear_tce(stit->tbl, entry);
+ }
+
kvmppc_tce_put(stt, entry + i, tce);
}
@@ -309,6 +489,7 @@ 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)@@ -322,6 +503,24 @@ 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) {
+ unsigned long entry = ioba >> stit->tbl->it_page_shift;
+
+ for (i = 0; i < npages; ++i) {
+ ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm,
+ stit->tbl, entry + i);
+
+ if (ret == H_SUCCESS)
+ continue;
+
+ if (ret == H_TOO_HARD)
+ return ret;
+
+ WARN_ON_ONCE_RM(1);
+ kvmppc_rm_clear_tce(stit->tbl, entry);
+ }
+ }
+
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 95c91a9de351..62bdd6c48107 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -538,6 +538,8 @@ 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_RTAS:
case KVM_CAP_PPC_FIXUP_HCALL:
case KVM_CAP_PPC_ENABLE_HCALL:
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
index d32f239eb471..2b7dc22265fe 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;@@ -211,6 +215,9 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
mutex_unlock(&kv->lock);
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+ kvm_spapr_tce_release_iommu_group(dev->kvm, vfio_group);
+#endif
kvm_vfio_group_set_kvm(vfio_group, NULL);
kvm_vfio_group_put_external_user(vfio_group);
@@ -218,6 +225,53 @@ 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, tablefd);
+
+ if (copy_from_user(¶m, (void __user *)arg, minsz))
+ return -EFAULT;
+
+ if (param.argsz < minsz || param.flags)
+ 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) {
+ if (kvg->vfio_group != vfio_group)
+ continue;
+
+ ret = kvm_spapr_tce_attach_iommu_group(dev->kvm,
+ param.tablefd, vfio_group);
+
+ break;
+ }
+
+ mutex_unlock(&kv->lock);
+
+ return ret;
+ }
+#endif /* CONFIG_SPAPR_TCE_IOMMU */
}
return -ENXIO;@@ -242,6 +296,9 @@ 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;
}
@@ -257,6 +314,9 @@ 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_spapr_tce_release_iommu_group(dev->kvm, kvg->vfio_group);
+#endif
kvm_vfio_group_set_kvm(kvg->vfio_group, NULL);
kvm_vfio_group_put_external_user(kvg->vfio_group);
list_del(&kvg->node);--
2.11.0