| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1422523325-1389-24-git-send-email-aik@ozlabs.ru>
Date: Thu, 29 Jan 2015 20:22:04 +1100
From: Alexey Kardashevskiy <aik@...abs.ru>
To: linuxppc-dev@...ts.ozlabs.org
Cc: Alexey Kardashevskiy <aik@...abs.ru>,
Benjamin Herrenschmidt <benh@...nel.crashing.org>,
Paul Mackerras <paulus@...ba.org>,
Michael Ellerman <mpe@...erman.id.au>,
Gavin Shan <gwshan@...ux.vnet.ibm.com>,
Alex Williamson <alex.williamson@...hat.com>,
Alexander Graf <agraf@...e.de>,
Alexander Gordeev <agordeev@...hat.com>,
linux-kernel@...r.kernel.org
Subject: [PATCH v3 23/24] vfio/spapr: Enable multiple groups in a container
Signed-off-by: Alexey Kardashevskiy <aik@...abs.ru>
---
drivers/vfio/vfio_iommu_spapr_tce.c | 243 +++++++++++++++++++++++-------------
1 file changed, 155 insertions(+), 88 deletions(-)
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index d0987ae..8bcafb7 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -84,9 +84,15 @@ static void decrement_locked_vm(long npages)
*/
struct tce_container {
struct mutex lock;
- struct iommu_group *grp;
bool enabled;
struct list_head mem_list;
+ struct iommu_table tables[POWERPC_IOMMU_MAX_TABLES];
+ struct list_head group_list;
+};
+
+struct tce_iommu_group {
+ struct list_head next;
+ struct iommu_group *grp;
};
struct tce_memory {
@@ -265,17 +271,21 @@ static bool tce_check_page_size(struct page *page, unsigned page_shift)
return false;
}
+static inline bool tce_groups_attached(struct tce_container *container)
+{
+ return !list_empty(&container->group_list);
+}
+
static struct iommu_table *spapr_tce_find_table(
struct tce_container *container,
phys_addr_t ioba)
{
long i;
struct iommu_table *ret = NULL;
- struct powerpc_iommu *iommu = iommu_group_get_iommudata(container->grp);
mutex_lock(&container->lock);
for (i = 0; i < POWERPC_IOMMU_MAX_TABLES; ++i) {
- struct iommu_table *tbl = &iommu->tables[i];
+ struct iommu_table *tbl = &container->tables[i];
unsigned long entry = ioba >> tbl->it_page_shift;
unsigned long start = tbl->it_offset;
unsigned long end = start + tbl->it_size;
@@ -290,13 +300,31 @@ static struct iommu_table *spapr_tce_find_table(
return ret;
}
+static unsigned long tce_default_winsize(struct tce_container *container)
+{
+ struct tce_iommu_group *tcegrp;
+ struct powerpc_iommu *iommu;
+
+ if (!tce_groups_attached(container))
+ return 0;
+
+ tcegrp = list_first_entry(&container->group_list,
+ struct tce_iommu_group, next);
+ if (!tcegrp)
+ return 0;
+
+ iommu = iommu_group_get_iommudata(tcegrp->grp);
+ if (!iommu)
+ return 0;
+
+ return iommu->tce32_size;
+}
+
static int tce_iommu_enable(struct tce_container *container)
{
int ret = 0;
- struct powerpc_iommu *iommu;
- struct iommu_table *tbl;
- if (!container->grp)
+ if (!tce_groups_attached(container))
return -ENXIO;
if (container->enabled)
@@ -328,12 +356,8 @@ static int tce_iommu_enable(struct tce_container *container)
* KVM agnostic.
*/
if (!tce_preregistered(container)) {
- iommu = iommu_group_get_iommudata(container->grp);
- if (!iommu)
- return -EFAULT;
-
- tbl = &iommu->tables[0];
- ret = try_increment_locked_vm(IOMMU_TABLE_PAGES(tbl));
+ ret = try_increment_locked_vm(
+ tce_default_winsize(container) >> PAGE_SHIFT);
if (ret)
return ret;
}
@@ -343,27 +367,23 @@ static int tce_iommu_enable(struct tce_container *container)
return ret;
}
+static int tce_iommu_clear(struct tce_container *container,
+ struct iommu_table *tbl,
+ unsigned long entry, unsigned long pages);
+
static void tce_iommu_disable(struct tce_container *container)
{
- struct powerpc_iommu *iommu;
- struct iommu_table *tbl;
-
if (!container->enabled)
return;
container->enabled = false;
- if (!container->grp || !current->mm)
+ if (!current->mm)
return;
- if (!tce_preregistered(container)) {
- iommu = iommu_group_get_iommudata(container->grp);
- if (!iommu)
- return;
-
- tbl = &iommu->tables[0];
- decrement_locked_vm(IOMMU_TABLE_PAGES(tbl));
- }
+ if (!tce_preregistered(container))
+ decrement_locked_vm(
+ tce_default_winsize(container) >> PAGE_SHIFT);
}
static void *tce_iommu_open(unsigned long arg)
@@ -381,20 +401,44 @@ static void *tce_iommu_open(unsigned long arg)
mutex_init(&container->lock);
INIT_LIST_HEAD_RCU(&container->mem_list);
+ INIT_LIST_HEAD_RCU(&container->group_list);
return container;
}
static void tce_iommu_release(void *iommu_data)
{
+ int i;
+ struct powerpc_iommu *iommu;
+ struct tce_iommu_group *tcegrp;
struct tce_container *container = iommu_data;
struct tce_memory *mem, *memtmp;
+ struct powerpc_iommu_ops *iommuops = NULL;
- WARN_ON(container->grp);
tce_iommu_disable(container);
- if (container->grp)
- tce_iommu_detach_group(iommu_data, container->grp);
+ while (tce_groups_attached(container)) {
+ tcegrp = list_first_entry(&container->group_list,
+ struct tce_iommu_group, next);
+ iommu = iommu_group_get_iommudata(tcegrp->grp);
+ iommuops = iommu->ops;
+ tce_iommu_detach_group(iommu_data, tcegrp->grp);
+ }
+
+ /* Free tables */
+ if (iommuops) {
+ for (i = 0; i < POWERPC_IOMMU_MAX_TABLES; ++i) {
+ struct iommu_table *tbl = &container->tables[i];
+
+ tce_iommu_clear(container, tbl,
+ tbl->it_offset, tbl->it_size);
+
+ if (!tce_preregistered(container))
+ decrement_locked_vm(IOMMU_TABLE_PAGES(tbl));
+
+ iommuops->free_table(tbl);
+ }
+ }
list_for_each_entry_safe(mem, memtmp, &container->mem_list, next)
tce_do_unregister_pages(container, mem);
@@ -568,16 +612,17 @@ static long tce_iommu_ioctl(void *iommu_data,
case VFIO_IOMMU_SPAPR_TCE_GET_INFO: {
struct vfio_iommu_spapr_tce_info info;
- struct iommu_table *tbl;
+ struct tce_iommu_group *tcegrp;
struct powerpc_iommu *iommu;
- if (WARN_ON(!container->grp))
+ if (!tce_groups_attached(container))
return -ENXIO;
- iommu = iommu_group_get_iommudata(container->grp);
+ tcegrp = list_first_entry(&container->group_list,
+ struct tce_iommu_group, next);
+ iommu = iommu_group_get_iommudata(tcegrp->grp);
- tbl = &iommu->tables[0];
- if (WARN_ON_ONCE(!tbl))
+ if (!iommu)
return -ENXIO;
minsz = offsetofend(struct vfio_iommu_spapr_tce_info,
@@ -589,9 +634,8 @@ static long tce_iommu_ioctl(void *iommu_data,
if (info.argsz < minsz)
return -EINVAL;
- info.dma32_window_start = tbl->it_offset << tbl->it_page_shift;
- info.dma32_window_size = tbl->it_size << tbl->it_page_shift;
- info.flags = 0;
+ info.dma32_window_start = iommu->tce32_start;
+ info.dma32_window_size = iommu->tce32_size;
if (copy_to_user((void __user *)arg, &info, minsz))
return -EFAULT;
@@ -603,9 +647,8 @@ static long tce_iommu_ioctl(void *iommu_data,
struct iommu_table *tbl;
unsigned long tce;
- if (WARN_ON(!container->grp ||
- !iommu_group_get_iommudata(container->grp)))
- return -ENXIO;
+ if (!container->enabled)
+ return -EPERM;
minsz = offsetofend(struct vfio_iommu_type1_dma_map, size);
@@ -655,10 +698,6 @@ static long tce_iommu_ioctl(void *iommu_data,
struct vfio_iommu_type1_dma_unmap param;
struct iommu_table *tbl;
- if (WARN_ON(!container->grp ||
- !iommu_group_get_iommudata(container->grp)))
- return -ENXIO;
-
minsz = offsetofend(struct vfio_iommu_type1_dma_unmap,
size);
@@ -747,12 +786,20 @@ static long tce_iommu_ioctl(void *iommu_data,
tce_iommu_disable(container);
mutex_unlock(&container->lock);
return 0;
- case VFIO_EEH_PE_OP:
- if (!container->grp)
- return -ENODEV;
- return vfio_spapr_iommu_eeh_ioctl(container->grp,
- cmd, arg);
+ case VFIO_EEH_PE_OP: {
+ struct tce_iommu_group *tcegrp;
+
+ ret = 0;
+ list_for_each_entry(tcegrp, &container->group_list, next) {
+ ret = vfio_spapr_iommu_eeh_ioctl(tcegrp->grp,
+ cmd, arg);
+ if (ret)
+ return ret;
+ }
+ return ret;
+ }
+
}
return -ENOTTY;
@@ -761,40 +808,63 @@ static long tce_iommu_ioctl(void *iommu_data,
static int tce_iommu_attach_group(void *iommu_data,
struct iommu_group *iommu_group)
{
- int ret = 0;
+ int ret = 0, i;
struct tce_container *container = iommu_data;
- struct powerpc_iommu *iommu;
+ struct powerpc_iommu *iommu = iommu_group_get_iommudata(iommu_group);
+ struct tce_iommu_group *tcegrp;
mutex_lock(&container->lock);
/* pr_debug("tce_vfio: Attaching group #%u to iommu %p\n",
iommu_group_id(iommu_group), iommu_group); */
- if (container->grp) {
- pr_warn("tce_vfio: Only one group per IOMMU container is allowed, existing id=%d, attaching id=%d\n",
- iommu_group_id(container->grp),
- iommu_group_id(iommu_group));
- ret = -EBUSY;
- } else if (container->enabled) {
- pr_err("tce_vfio: attaching group #%u to enabled container\n",
- iommu_group_id(iommu_group));
- ret = -EBUSY;
+
+ list_for_each_entry(tcegrp, &container->group_list, next) {
+ struct powerpc_iommu *iommutmp;
+
+ if (tcegrp->grp == iommu_group) {
+ pr_warn("tce_vfio: Group %d is already attached\n",
+ iommu_group_id(iommu_group));
+ ret = -EBUSY;
+ goto unlock_exit;
+ }
+ iommutmp = iommu_group_get_iommudata(tcegrp->grp);
+ if (iommutmp->ops != iommu->ops) {
+ pr_warn("tce_vfio: Group %d is incompatible with group %d\n",
+ iommu_group_id(iommu_group),
+ iommu_group_id(tcegrp->grp));
+ ret = -EBUSY;
+ goto unlock_exit;
+ }
+ }
+
+ /*
+ * Disable iommu bypass, otherwise the user can DMA to all of
+ * our physical memory via the bypass window instead of just
+ * the pages that has been explicitly mapped into the iommu
+ */
+ if (iommu->ops && iommu->ops->set_ownership) {
+ iommu->ops->set_ownership(iommu, true);
} else {
- iommu = iommu_group_get_iommudata(iommu_group);
- if (WARN_ON_ONCE(!iommu))
- return -ENXIO;
- /*
- * Disable iommu bypass, otherwise the user can DMA to all of
- * our physical memory via the bypass window instead of just
- * the pages that has been explicitly mapped into the iommu
- */
- if (iommu->ops && iommu->ops->set_ownership) {
- iommu->ops->set_ownership(iommu, true);
- container->grp = iommu_group;
- } else {
- return -ENODEV;
- }
+ ret = -ENODEV;
+ goto unlock_exit;
}
+ tcegrp = kzalloc(sizeof(*tcegrp), GFP_KERNEL);
+ tcegrp->grp = iommu_group;
+ list_add(&tcegrp->next, &container->group_list);
+ for (i = 0; i < POWERPC_IOMMU_MAX_TABLES; ++i) {
+ struct iommu_table *tbl = &container->tables[i];
+
+ if (!tbl->it_size)
+ continue;
+
+ /* Set the default window to a new group */
+ ret = iommu->ops->set_window(iommu, i, tbl);
+ if (ret)
+ goto unlock_exit;
+ }
+
+unlock_exit:
mutex_unlock(&container->lock);
return ret;
@@ -805,33 +875,30 @@ static void tce_iommu_detach_group(void *iommu_data,
{
struct tce_container *container = iommu_data;
struct powerpc_iommu *iommu;
+ struct tce_iommu_group *tcegrp, *tcegrptmp;
+ long i;
mutex_lock(&container->lock);
- if (iommu_group != container->grp) {
- pr_warn("tce_vfio: detaching group #%u, expected group is #%u\n",
- iommu_group_id(iommu_group),
- iommu_group_id(container->grp));
- } else {
- if (container->enabled) {
- pr_warn("tce_vfio: detaching group #%u from enabled container, forcing disable\n",
- iommu_group_id(container->grp));
- tce_iommu_disable(container);
- }
- /* pr_debug("tce_vfio: detaching group #%u from iommu %p\n",
- iommu_group_id(iommu_group), iommu_group); */
- container->grp = NULL;
+ /* Detach windows from IOMMUs */
+ list_for_each_entry_safe(tcegrp, tcegrptmp, &container->group_list,
+ next) {
+ if (tcegrp->grp != iommu_group)
+ continue;
+ list_del(&tcegrp->next);
iommu = iommu_group_get_iommudata(iommu_group);
BUG_ON(!iommu);
- tce_iommu_clear(container, &iommu->tables[0],
- iommu->tables[0].it_offset,
- iommu->tables[0].it_size);
+ for (i = 0; i < POWERPC_IOMMU_MAX_TABLES; ++i)
+ iommu->ops->unset_window(iommu, i);
/* Kernel owns the device now, we can restore bypass */
if (iommu->ops && iommu->ops->set_ownership)
iommu->ops->set_ownership(iommu, false);
+
+ kfree(tcegrp);
+ break;
}
mutex_unlock(&container->lock);
}
--
2.0.0
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists