| 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: <1425910045-26167-16-git-send-email-aik@ozlabs.ru>
Date: Tue, 10 Mar 2015 01:07:11 +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>,
Alex Williamson <alex.williamson@...hat.com>,
kvm@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: [PATCH v5 15/29] vfio: powerpc/spapr: powerpc/powernv/ioda2: Rework IOMMU ownership control
At the moment the iommu_table struct has a set_bypass() which enables/
disables DMA bypass on IODA2 PHB. This is exposed to POWERPC IOMMU code
which calls this callback when external IOMMU users such as VFIO are
about to get over a PHB.
The set_bypass() callback is not really an iommu_table function but
IOMMU/PE function. This introduces a iommu_table_group_ops struct and
adds a set_ownership() callback to it which is called when an external
user takes control over the IOMMU.
This renames set_bypass() to set_ownership() as it is not necessarily
just enabling bypassing, it can be something else/more so let's give it
more generic name. The bool parameter is inverted.
The callback is implemented for IODA2 only. Other platforms (P5IOC2,
IODA1) will use the old iommu_take_ownership/iommu_release_ownership API.
Signed-off-by: Alexey Kardashevskiy <aik@...abs.ru>
---
arch/powerpc/include/asm/iommu.h | 14 +++++++++++++-
arch/powerpc/platforms/powernv/pci-ioda.c | 30 ++++++++++++++++++++++--------
drivers/vfio/vfio_iommu_spapr_tce.c | 26 ++++++++++++++++++++++----
3 files changed, 57 insertions(+), 13 deletions(-)
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index b9e50d3..d1f8c6c 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -92,7 +92,6 @@ struct iommu_table {
unsigned long it_page_shift;/* table iommu page size */
struct iommu_table_group *it_group;
struct iommu_table_ops *it_ops;
- void (*set_bypass)(struct iommu_table *tbl, bool enable);
};
/* Pure 2^n version of get_order */
@@ -127,11 +126,24 @@ extern struct iommu_table *iommu_init_table(struct iommu_table * tbl,
#define IOMMU_TABLE_GROUP_MAX_TABLES 1
+struct iommu_table_group;
+
+struct iommu_table_group_ops {
+ /*
+ * Switches ownership from the kernel itself to an external
+ * user. While onwership is enabled, the kernel cannot use IOMMU
+ * for itself.
+ */
+ void (*set_ownership)(struct iommu_table_group *table_group,
+ bool enable);
+};
+
struct iommu_table_group {
#ifdef CONFIG_IOMMU_API
struct iommu_group *group;
#endif
struct iommu_table tables[IOMMU_TABLE_GROUP_MAX_TABLES];
+ struct iommu_table_group_ops *ops;
};
#ifdef CONFIG_IOMMU_API
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 61956e2..67a3fe4 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1257,10 +1257,8 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
__free_pages(tce_mem, get_order(TCE32_TABLE_SIZE * segs));
}
-static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable)
+static void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable)
{
- struct pnv_ioda_pe *pe = container_of(tbl->it_group, struct pnv_ioda_pe,
- table_group);
uint16_t window_id = (pe->pe_number << 1 ) + 1;
int64_t rc;
@@ -1288,7 +1286,8 @@ static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable)
* host side.
*/
if (pe->pdev)
- set_iommu_table_base(&pe->pdev->dev, tbl);
+ set_iommu_table_base(&pe->pdev->dev,
+ &pe->table_group.tables[0]);
else
pnv_ioda_setup_bus_dma(pe, pe->pbus, false);
}
@@ -1304,13 +1303,27 @@ static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb,
/* TVE #1 is selected by PCI address bit 59 */
pe->tce_bypass_base = 1ull << 59;
- /* Install set_bypass callback for VFIO */
- pe->table_group.tables[0].set_bypass = pnv_pci_ioda2_set_bypass;
-
/* Enable bypass by default */
- pnv_pci_ioda2_set_bypass(&pe->table_group.tables[0], true);
+ pnv_pci_ioda2_set_bypass(pe, true);
}
+static void pnv_ioda2_set_ownership(struct iommu_table_group *table_group,
+ bool enable)
+{
+ struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
+ table_group);
+ if (enable)
+ iommu_take_ownership(table_group);
+ else
+ iommu_release_ownership(table_group);
+
+ pnv_pci_ioda2_set_bypass(pe, !enable);
+}
+
+static struct iommu_table_group_ops pnv_pci_ioda2_ops = {
+ .set_ownership = pnv_ioda2_set_ownership,
+};
+
static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
struct pnv_ioda_pe *pe)
{
@@ -1378,6 +1391,7 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
}
tbl->it_ops = &pnv_iommu_ops;
iommu_init_table(tbl, phb->hose->node);
+ pe->table_group.ops = &pnv_pci_ioda2_ops;
iommu_register_group(&pe->table_group, phb->hose->global_number,
pe->pe_number);
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 6372b3b..10e9e76 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -809,9 +809,22 @@ static int tce_iommu_attach_group(void *iommu_data,
goto unlock_exit;
}
- ret = iommu_take_ownership(table_group);
- if (!ret)
- container->grp = iommu_group;
+ if (!table_group->ops || !table_group->ops->set_ownership) {
+ ret = iommu_take_ownership(table_group);
+ } else {
+ /*
+ * 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
+ */
+ table_group->ops->set_ownership(table_group, true);
+ ret = 0;
+ }
+
+ if (ret)
+ goto unlock_exit;
+
+ container->grp = iommu_group;
unlock_exit:
mutex_unlock(&container->lock);
@@ -846,9 +859,14 @@ static void tce_iommu_detach_group(void *iommu_data,
table_group = iommu_group_get_iommudata(iommu_group);
BUG_ON(!table_group);
- iommu_release_ownership(table_group);
+ /* Kernel owns the device now, we can restore bypass */
+ if (!table_group->ops || !table_group->ops->set_ownership)
+ iommu_release_ownership(table_group);
+ else
+ table_group->ops->set_ownership(table_group, false);
unlock_exit:
+
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