summaryrefslogtreecommitdiffstats
path: root/drivers/vfio
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/vfio')
-rw-r--r--drivers/vfio/vfio_iommu_spapr_tce.c328
1 files changed, 217 insertions, 111 deletions
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 80378ddadc5c..c8823578a1b2 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -31,49 +31,49 @@
static void tce_iommu_detach_group(void *iommu_data,
struct iommu_group *iommu_group);
-static long try_increment_locked_vm(long npages)
+static long try_increment_locked_vm(struct mm_struct *mm, long npages)
{
long ret = 0, locked, lock_limit;
- if (!current || !current->mm)
- return -ESRCH; /* process exited */
+ if (WARN_ON_ONCE(!mm))
+ return -EPERM;
if (!npages)
return 0;
- down_write(&current->mm->mmap_sem);
- locked = current->mm->locked_vm + npages;
+ down_write(&mm->mmap_sem);
+ locked = mm->locked_vm + npages;
lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
if (locked > lock_limit && !capable(CAP_IPC_LOCK))
ret = -ENOMEM;
else
- current->mm->locked_vm += npages;
+ mm->locked_vm += npages;
pr_debug("[%d] RLIMIT_MEMLOCK +%ld %ld/%ld%s\n", current->pid,
npages << PAGE_SHIFT,
- current->mm->locked_vm << PAGE_SHIFT,
+ mm->locked_vm << PAGE_SHIFT,
rlimit(RLIMIT_MEMLOCK),
ret ? " - exceeded" : "");
- up_write(&current->mm->mmap_sem);
+ up_write(&mm->mmap_sem);
return ret;
}
-static void decrement_locked_vm(long npages)
+static void decrement_locked_vm(struct mm_struct *mm, long npages)
{
- if (!current || !current->mm || !npages)
- return; /* process exited */
+ if (!mm || !npages)
+ return;
- down_write(&current->mm->mmap_sem);
- if (WARN_ON_ONCE(npages > current->mm->locked_vm))
- npages = current->mm->locked_vm;
- current->mm->locked_vm -= npages;
+ down_write(&mm->mmap_sem);
+ if (WARN_ON_ONCE(npages > mm->locked_vm))
+ npages = mm->locked_vm;
+ mm->locked_vm -= npages;
pr_debug("[%d] RLIMIT_MEMLOCK -%ld %ld/%ld\n", current->pid,
npages << PAGE_SHIFT,
- current->mm->locked_vm << PAGE_SHIFT,
+ mm->locked_vm << PAGE_SHIFT,
rlimit(RLIMIT_MEMLOCK));
- up_write(&current->mm->mmap_sem);
+ up_write(&mm->mmap_sem);
}
/*
@@ -89,6 +89,15 @@ struct tce_iommu_group {
};
/*
+ * A container needs to remember which preregistered region it has
+ * referenced to do proper cleanup at the userspace process exit.
+ */
+struct tce_iommu_prereg {
+ struct list_head next;
+ struct mm_iommu_table_group_mem_t *mem;
+};
+
+/*
* The container descriptor supports only a single group per container.
* Required by the API as the container is not supplied with the IOMMU group
* at the moment of initialization.
@@ -97,24 +106,68 @@ struct tce_container {
struct mutex lock;
bool enabled;
bool v2;
+ bool def_window_pending;
unsigned long locked_pages;
+ struct mm_struct *mm;
struct iommu_table *tables[IOMMU_TABLE_GROUP_MAX_TABLES];
struct list_head group_list;
+ struct list_head prereg_list;
};
+static long tce_iommu_mm_set(struct tce_container *container)
+{
+ if (container->mm) {
+ if (container->mm == current->mm)
+ return 0;
+ return -EPERM;
+ }
+ BUG_ON(!current->mm);
+ container->mm = current->mm;
+ atomic_inc(&container->mm->mm_count);
+
+ return 0;
+}
+
+static long tce_iommu_prereg_free(struct tce_container *container,
+ struct tce_iommu_prereg *tcemem)
+{
+ long ret;
+
+ ret = mm_iommu_put(container->mm, tcemem->mem);
+ if (ret)
+ return ret;
+
+ list_del(&tcemem->next);
+ kfree(tcemem);
+
+ return 0;
+}
+
static long tce_iommu_unregister_pages(struct tce_container *container,
__u64 vaddr, __u64 size)
{
struct mm_iommu_table_group_mem_t *mem;
+ struct tce_iommu_prereg *tcemem;
+ bool found = false;
if ((vaddr & ~PAGE_MASK) || (size & ~PAGE_MASK))
return -EINVAL;
- mem = mm_iommu_find(vaddr, size >> PAGE_SHIFT);
+ mem = mm_iommu_find(container->mm, vaddr, size >> PAGE_SHIFT);
if (!mem)
return -ENOENT;
- return mm_iommu_put(mem);
+ list_for_each_entry(tcemem, &container->prereg_list, next) {
+ if (tcemem->mem == mem) {
+ found = true;
+ break;
+ }
+ }
+
+ if (!found)
+ return -ENOENT;
+
+ return tce_iommu_prereg_free(container, tcemem);
}
static long tce_iommu_register_pages(struct tce_container *container,
@@ -122,22 +175,36 @@ static long tce_iommu_register_pages(struct tce_container *container,
{
long ret = 0;
struct mm_iommu_table_group_mem_t *mem = NULL;
+ struct tce_iommu_prereg *tcemem;
unsigned long entries = size >> PAGE_SHIFT;
if ((vaddr & ~PAGE_MASK) || (size & ~PAGE_MASK) ||
((vaddr + size) < vaddr))
return -EINVAL;
- ret = mm_iommu_get(vaddr, entries, &mem);
+ mem = mm_iommu_find(container->mm, vaddr, entries);
+ if (mem) {
+ list_for_each_entry(tcemem, &container->prereg_list, next) {
+ if (tcemem->mem == mem)
+ return -EBUSY;
+ }
+ }
+
+ ret = mm_iommu_get(container->mm, vaddr, entries, &mem);
if (ret)
return ret;
+ tcemem = kzalloc(sizeof(*tcemem), GFP_KERNEL);
+ tcemem->mem = mem;
+ list_add(&tcemem->next, &container->prereg_list);
+
container->enabled = true;
return 0;
}
-static long tce_iommu_userspace_view_alloc(struct iommu_table *tbl)
+static long tce_iommu_userspace_view_alloc(struct iommu_table *tbl,
+ struct mm_struct *mm)
{
unsigned long cb = _ALIGN_UP(sizeof(tbl->it_userspace[0]) *
tbl->it_size, PAGE_SIZE);
@@ -146,13 +213,13 @@ static long tce_iommu_userspace_view_alloc(struct iommu_table *tbl)
BUG_ON(tbl->it_userspace);
- ret = try_increment_locked_vm(cb >> PAGE_SHIFT);
+ ret = try_increment_locked_vm(mm, cb >> PAGE_SHIFT);
if (ret)
return ret;
uas = vzalloc(cb);
if (!uas) {
- decrement_locked_vm(cb >> PAGE_SHIFT);
+ decrement_locked_vm(mm, cb >> PAGE_SHIFT);
return -ENOMEM;
}
tbl->it_userspace = uas;
@@ -160,7 +227,8 @@ static long tce_iommu_userspace_view_alloc(struct iommu_table *tbl)
return 0;
}
-static void tce_iommu_userspace_view_free(struct iommu_table *tbl)
+static void tce_iommu_userspace_view_free(struct iommu_table *tbl,
+ struct mm_struct *mm)
{
unsigned long cb = _ALIGN_UP(sizeof(tbl->it_userspace[0]) *
tbl->it_size, PAGE_SIZE);
@@ -170,7 +238,7 @@ static void tce_iommu_userspace_view_free(struct iommu_table *tbl)
vfree(tbl->it_userspace);
tbl->it_userspace = NULL;
- decrement_locked_vm(cb >> PAGE_SHIFT);
+ decrement_locked_vm(mm, cb >> PAGE_SHIFT);
}
static bool tce_page_is_contained(struct page *page, unsigned page_shift)
@@ -230,9 +298,6 @@ static int tce_iommu_enable(struct tce_container *container)
struct iommu_table_group *table_group;
struct tce_iommu_group *tcegrp;
- if (!current->mm)
- return -ESRCH; /* process exited */
-
if (container->enabled)
return -EBUSY;
@@ -277,8 +342,12 @@ static int tce_iommu_enable(struct tce_container *container)
if (!table_group->tce32_size)
return -EPERM;
+ ret = tce_iommu_mm_set(container);
+ if (ret)
+ return ret;
+
locked = table_group->tce32_size >> PAGE_SHIFT;
- ret = try_increment_locked_vm(locked);
+ ret = try_increment_locked_vm(container->mm, locked);
if (ret)
return ret;
@@ -296,10 +365,8 @@ static void tce_iommu_disable(struct tce_container *container)
container->enabled = false;
- if (!current->mm)
- return;
-
- decrement_locked_vm(container->locked_pages);
+ BUG_ON(!container->mm);
+ decrement_locked_vm(container->mm, container->locked_pages);
}
static void *tce_iommu_open(unsigned long arg)
@@ -317,6 +384,7 @@ static void *tce_iommu_open(unsigned long arg)
mutex_init(&container->lock);
INIT_LIST_HEAD_RCU(&container->group_list);
+ INIT_LIST_HEAD_RCU(&container->prereg_list);
container->v2 = arg == VFIO_SPAPR_TCE_v2_IOMMU;
@@ -326,7 +394,8 @@ static void *tce_iommu_open(unsigned long arg)
static int tce_iommu_clear(struct tce_container *container,
struct iommu_table *tbl,
unsigned long entry, unsigned long pages);
-static void tce_iommu_free_table(struct iommu_table *tbl);
+static void tce_iommu_free_table(struct tce_container *container,
+ struct iommu_table *tbl);
static void tce_iommu_release(void *iommu_data)
{
@@ -351,10 +420,20 @@ static void tce_iommu_release(void *iommu_data)
continue;
tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
- tce_iommu_free_table(tbl);
+ tce_iommu_free_table(container, tbl);
+ }
+
+ while (!list_empty(&container->prereg_list)) {
+ struct tce_iommu_prereg *tcemem;
+
+ tcemem = list_first_entry(&container->prereg_list,
+ struct tce_iommu_prereg, next);
+ WARN_ON_ONCE(tce_iommu_prereg_free(container, tcemem));
}
tce_iommu_disable(container);
+ if (container->mm)
+ mmdrop(container->mm);
mutex_destroy(&container->lock);
kfree(container);
@@ -369,13 +448,14 @@ static void tce_iommu_unuse_page(struct tce_container *container,
put_page(page);
}
-static int tce_iommu_prereg_ua_to_hpa(unsigned long tce, unsigned long size,
+static int tce_iommu_prereg_ua_to_hpa(struct tce_container *container,
+ unsigned long tce, unsigned long size,
unsigned long *phpa, struct mm_iommu_table_group_mem_t **pmem)
{
long ret = 0;
struct mm_iommu_table_group_mem_t *mem;
- mem = mm_iommu_lookup(tce, size);
+ mem = mm_iommu_lookup(container->mm, tce, size);
if (!mem)
return -EINVAL;
@@ -388,18 +468,18 @@ static int tce_iommu_prereg_ua_to_hpa(unsigned long tce, unsigned long size,
return 0;
}
-static void tce_iommu_unuse_page_v2(struct iommu_table *tbl,
- unsigned long entry)
+static void tce_iommu_unuse_page_v2(struct tce_container *container,
+ struct iommu_table *tbl, unsigned long entry)
{
struct mm_iommu_table_group_mem_t *mem = NULL;
int ret;
unsigned long hpa = 0;
unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
- if (!pua || !current || !current->mm)
+ if (!pua)
return;
- ret = tce_iommu_prereg_ua_to_hpa(*pua, IOMMU_PAGE_SIZE(tbl),
+ ret = tce_iommu_prereg_ua_to_hpa(container, *pua, IOMMU_PAGE_SIZE(tbl),
&hpa, &mem);
if (ret)
pr_debug("%s: tce %lx at #%lx was not cached, ret=%d\n",
@@ -429,7 +509,7 @@ static int tce_iommu_clear(struct tce_container *container,
continue;
if (container->v2) {
- tce_iommu_unuse_page_v2(tbl, entry);
+ tce_iommu_unuse_page_v2(container, tbl, entry);
continue;
}
@@ -509,13 +589,19 @@ static long tce_iommu_build_v2(struct tce_container *container,
unsigned long hpa;
enum dma_data_direction dirtmp;
+ if (!tbl->it_userspace) {
+ ret = tce_iommu_userspace_view_alloc(tbl, container->mm);
+ if (ret)
+ return ret;
+ }
+
for (i = 0; i < pages; ++i) {
struct mm_iommu_table_group_mem_t *mem = NULL;
unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl,
entry + i);
- ret = tce_iommu_prereg_ua_to_hpa(tce, IOMMU_PAGE_SIZE(tbl),
- &hpa, &mem);
+ ret = tce_iommu_prereg_ua_to_hpa(container,
+ tce, IOMMU_PAGE_SIZE(tbl), &hpa, &mem);
if (ret)
break;
@@ -536,7 +622,7 @@ static long tce_iommu_build_v2(struct tce_container *container,
ret = iommu_tce_xchg(tbl, entry + i, &hpa, &dirtmp);
if (ret) {
/* dirtmp cannot be DMA_NONE here */
- tce_iommu_unuse_page_v2(tbl, entry + i);
+ tce_iommu_unuse_page_v2(container, tbl, entry + i);
pr_err("iommu_tce: %s failed ioba=%lx, tce=%lx, ret=%ld\n",
__func__, entry << tbl->it_page_shift,
tce, ret);
@@ -544,7 +630,7 @@ static long tce_iommu_build_v2(struct tce_container *container,
}
if (dirtmp != DMA_NONE)
- tce_iommu_unuse_page_v2(tbl, entry + i);
+ tce_iommu_unuse_page_v2(container, tbl, entry + i);
*pua = tce;
@@ -572,7 +658,7 @@ static long tce_iommu_create_table(struct tce_container *container,
if (!table_size)
return -EINVAL;
- ret = try_increment_locked_vm(table_size >> PAGE_SHIFT);
+ ret = try_increment_locked_vm(container->mm, table_size >> PAGE_SHIFT);
if (ret)
return ret;
@@ -582,25 +668,17 @@ static long tce_iommu_create_table(struct tce_container *container,
WARN_ON(!ret && !(*ptbl)->it_ops->free);
WARN_ON(!ret && ((*ptbl)->it_allocated_size != table_size));
- if (!ret && container->v2) {
- ret = tce_iommu_userspace_view_alloc(*ptbl);
- if (ret)
- (*ptbl)->it_ops->free(*ptbl);
- }
-
- if (ret)
- decrement_locked_vm(table_size >> PAGE_SHIFT);
-
return ret;
}
-static void tce_iommu_free_table(struct iommu_table *tbl)
+static void tce_iommu_free_table(struct tce_container *container,
+ struct iommu_table *tbl)
{
unsigned long pages = tbl->it_allocated_size >> PAGE_SHIFT;
- tce_iommu_userspace_view_free(tbl);
+ tce_iommu_userspace_view_free(tbl, container->mm);
tbl->it_ops->free(tbl);
- decrement_locked_vm(pages);
+ decrement_locked_vm(container->mm, pages);
}
static long tce_iommu_create_window(struct tce_container *container,
@@ -663,7 +741,7 @@ unset_exit:
table_group = iommu_group_get_iommudata(tcegrp->grp);
table_group->ops->unset_window(table_group, num);
}
- tce_iommu_free_table(tbl);
+ tce_iommu_free_table(container, tbl);
return ret;
}
@@ -701,12 +779,41 @@ static long tce_iommu_remove_window(struct tce_container *container,
/* Free table */
tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
- tce_iommu_free_table(tbl);
+ tce_iommu_free_table(container, tbl);
container->tables[num] = NULL;
return 0;
}
+static long tce_iommu_create_default_window(struct tce_container *container)
+{
+ long ret;
+ __u64 start_addr = 0;
+ struct tce_iommu_group *tcegrp;
+ struct iommu_table_group *table_group;
+
+ if (!container->def_window_pending)
+ return 0;
+
+ if (!tce_groups_attached(container))
+ return -ENODEV;
+
+ tcegrp = list_first_entry(&container->group_list,
+ struct tce_iommu_group, next);
+ table_group = iommu_group_get_iommudata(tcegrp->grp);
+ if (!table_group)
+ return -ENODEV;
+
+ ret = tce_iommu_create_window(container, IOMMU_PAGE_SHIFT_4K,
+ table_group->tce32_size, 1, &start_addr);
+ WARN_ON_ONCE(!ret && start_addr);
+
+ if (!ret)
+ container->def_window_pending = false;
+
+ return ret;
+}
+
static long tce_iommu_ioctl(void *iommu_data,
unsigned int cmd, unsigned long arg)
{
@@ -727,7 +834,17 @@ static long tce_iommu_ioctl(void *iommu_data,
}
return (ret < 0) ? 0 : ret;
+ }
+
+ /*
+ * Sanity check to prevent one userspace from manipulating
+ * another userspace mm.
+ */
+ BUG_ON(!container);
+ if (container->mm && container->mm != current->mm)
+ return -EPERM;
+ switch (cmd) {
case VFIO_IOMMU_SPAPR_TCE_GET_INFO: {
struct vfio_iommu_spapr_tce_info info;
struct tce_iommu_group *tcegrp;
@@ -797,6 +914,10 @@ static long tce_iommu_ioctl(void *iommu_data,
VFIO_DMA_MAP_FLAG_WRITE))
return -EINVAL;
+ ret = tce_iommu_create_default_window(container);
+ if (ret)
+ return ret;
+
num = tce_iommu_find_table(container, param.iova, &tbl);
if (num < 0)
return -ENXIO;
@@ -860,6 +981,10 @@ static long tce_iommu_ioctl(void *iommu_data,
if (param.flags)
return -EINVAL;
+ ret = tce_iommu_create_default_window(container);
+ if (ret)
+ return ret;
+
num = tce_iommu_find_table(container, param.iova, &tbl);
if (num < 0)
return -ENXIO;
@@ -888,6 +1013,10 @@ static long tce_iommu_ioctl(void *iommu_data,
minsz = offsetofend(struct vfio_iommu_spapr_register_memory,
size);
+ ret = tce_iommu_mm_set(container);
+ if (ret)
+ return ret;
+
if (copy_from_user(&param, (void __user *)arg, minsz))
return -EFAULT;
@@ -911,6 +1040,9 @@ static long tce_iommu_ioctl(void *iommu_data,
if (!container->v2)
break;
+ if (!container->mm)
+ return -EPERM;
+
minsz = offsetofend(struct vfio_iommu_spapr_register_memory,
size);
@@ -969,6 +1101,10 @@ static long tce_iommu_ioctl(void *iommu_data,
if (!container->v2)
break;
+ ret = tce_iommu_mm_set(container);
+ if (ret)
+ return ret;
+
if (!tce_groups_attached(container))
return -ENXIO;
@@ -986,6 +1122,10 @@ static long tce_iommu_ioctl(void *iommu_data,
mutex_lock(&container->lock);
+ ret = tce_iommu_create_default_window(container);
+ if (ret)
+ return ret;
+
ret = tce_iommu_create_window(container, create.page_shift,
create.window_size, create.levels,
&create.start_addr);
@@ -1003,6 +1143,10 @@ static long tce_iommu_ioctl(void *iommu_data,
if (!container->v2)
break;
+ ret = tce_iommu_mm_set(container);
+ if (ret)
+ return ret;
+
if (!tce_groups_attached(container))
return -ENXIO;
@@ -1018,6 +1162,11 @@ static long tce_iommu_ioctl(void *iommu_data,
if (remove.flags)
return -EINVAL;
+ if (container->def_window_pending && !remove.start_addr) {
+ container->def_window_pending = false;
+ return 0;
+ }
+
mutex_lock(&container->lock);
ret = tce_iommu_remove_window(container, remove.start_addr);
@@ -1043,7 +1192,7 @@ static void tce_iommu_release_ownership(struct tce_container *container,
continue;
tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
- tce_iommu_userspace_view_free(tbl);
+ tce_iommu_userspace_view_free(tbl, container->mm);
if (tbl->it_map)
iommu_release_ownership(tbl);
@@ -1062,10 +1211,7 @@ static int tce_iommu_take_ownership(struct tce_container *container,
if (!tbl || !tbl->it_map)
continue;
- rc = tce_iommu_userspace_view_alloc(tbl);
- if (!rc)
- rc = iommu_take_ownership(tbl);
-
+ rc = iommu_take_ownership(tbl);
if (rc) {
for (j = 0; j < i; ++j)
iommu_release_ownership(
@@ -1100,9 +1246,6 @@ static void tce_iommu_release_ownership_ddw(struct tce_container *container,
static long tce_iommu_take_ownership_ddw(struct tce_container *container,
struct iommu_table_group *table_group)
{
- long i, ret = 0;
- struct iommu_table *tbl = NULL;
-
if (!table_group->ops->create_table || !table_group->ops->set_window ||
!table_group->ops->release_ownership) {
WARN_ON_ONCE(1);
@@ -1111,47 +1254,7 @@ static long tce_iommu_take_ownership_ddw(struct tce_container *container,
table_group->ops->take_ownership(table_group);
- /*
- * If it the first group attached, check if there is
- * a default DMA window and create one if none as
- * the userspace expects it to exist.
- */
- if (!tce_groups_attached(container) && !container->tables[0]) {
- ret = tce_iommu_create_table(container,
- table_group,
- 0, /* window number */
- IOMMU_PAGE_SHIFT_4K,
- table_group->tce32_size,
- 1, /* default levels */
- &tbl);
- if (ret)
- goto release_exit;
- else
- container->tables[0] = tbl;
- }
-
- /* Set all windows to the new group */
- for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
- tbl = container->tables[i];
-
- if (!tbl)
- continue;
-
- /* Set the default window to a new group */
- ret = table_group->ops->set_window(table_group, i, tbl);
- if (ret)
- goto release_exit;
- }
-
return 0;
-
-release_exit:
- for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i)
- table_group->ops->unset_window(table_group, i);
-
- table_group->ops->release_ownership(table_group);
-
- return ret;
}
static int tce_iommu_attach_group(void *iommu_data,
@@ -1203,10 +1306,13 @@ static int tce_iommu_attach_group(void *iommu_data,
}
if (!table_group->ops || !table_group->ops->take_ownership ||
- !table_group->ops->release_ownership)
+ !table_group->ops->release_ownership) {
ret = tce_iommu_take_ownership(container, table_group);
- else
+ } else {
ret = tce_iommu_take_ownership_ddw(container, table_group);
+ if (!tce_groups_attached(container) && !container->tables[0])
+ container->def_window_pending = true;
+ }
if (!ret) {
tcegrp->grp = iommu_group;