From: Alexey Kardashevskiy <aik@ozlabs.ru>
To: linuxppc-dev@lists.ozlabs.org
Cc: kvm@vger.kernel.org, Alexey Kardashevskiy <aik@ozlabs.ru>,
linux-kernel@vger.kernel.org,
Alex Williamson <alex.williamson@redhat.com>,
Paul Mackerras <paulus@samba.org>
Subject: [PATCH v5 15/29] vfio: powerpc/spapr: powerpc/powernv/ioda2: Rework IOMMU ownership control
Date: Tue, 10 Mar 2015 01:07:11 +1100 [thread overview]
Message-ID: <1425910045-26167-16-git-send-email-aik@ozlabs.ru> (raw)
In-Reply-To: <1425910045-26167-1-git-send-email-aik@ozlabs.ru>
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@ozlabs.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
next prev parent reply other threads:[~2015-03-09 14:08 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-03-09 14:06 [PATCH v5 00/29] powerpc/iommu/vfio: Enable Dynamic DMA windows Alexey Kardashevskiy
2015-03-09 14:06 ` [PATCH v5 01/29] vfio: powerpc/spapr: Move page pinning from arch code to VFIO IOMMU driver Alexey Kardashevskiy
2015-03-09 14:06 ` [PATCH v5 02/29] vfio: powerpc/spapr: Do cleanup when releasing the group Alexey Kardashevskiy
2015-03-09 14:06 ` [PATCH v5 03/29] vfio: powerpc/spapr: Check that TCE page size is equal to it_page_size Alexey Kardashevskiy
2015-03-10 19:56 ` Alex Williamson
2015-03-10 22:57 ` Alexey Kardashevskiy
2015-03-10 23:03 ` Alex Williamson
2015-03-10 23:14 ` Benjamin Herrenschmidt
2015-03-10 23:34 ` Alex Williamson
2015-03-10 23:45 ` Alexey Kardashevskiy
2015-03-09 14:07 ` [PATCH v5 04/29] vfio: powerpc/spapr: Use it_page_size Alexey Kardashevskiy
2015-03-09 14:07 ` [PATCH v5 05/29] vfio: powerpc/spapr: Move locked_vm accounting to helpers Alexey Kardashevskiy
2015-03-09 14:07 ` [PATCH v5 06/29] vfio: powerpc/spapr: Disable DMA mappings on disabled container Alexey Kardashevskiy
2015-03-09 14:07 ` [PATCH v5 07/29] vfio: powerpc/spapr: Moving pinning/unpinning to helpers Alexey Kardashevskiy
2015-03-10 23:36 ` Alex Williamson
2015-03-09 14:07 ` [PATCH v5 08/29] vfio: powerpc/spapr: Register memory Alexey Kardashevskiy
2015-03-09 14:07 ` [PATCH v5 09/29] vfio: powerpc/spapr: Rework attach/detach Alexey Kardashevskiy
2015-03-09 14:07 ` [PATCH v5 10/29] powerpc/powernv: Do not set "read" flag if direction==DMA_NONE Alexey Kardashevskiy
2015-03-09 14:07 ` [PATCH v5 11/29] powerpc/iommu: Move tce_xxx callbacks from ppc_md to iommu_table Alexey Kardashevskiy
2015-03-09 14:07 ` [PATCH v5 12/29] powerpc/iommu: Introduce iommu_table_alloc() helper Alexey Kardashevskiy
2015-03-09 14:07 ` [PATCH v5 13/29] powerpc/spapr: vfio: Switch from iommu_table to new iommu_table_group Alexey Kardashevskiy
2015-03-09 14:07 ` [PATCH v5 14/29] vfio: powerpc/spapr: powerpc/iommu: Rework IOMMU ownership control Alexey Kardashevskiy
2015-03-09 14:07 ` Alexey Kardashevskiy [this message]
2015-03-09 14:07 ` [PATCH v5 16/29] powerpc/iommu: Fix IOMMU ownership control functions Alexey Kardashevskiy
2015-03-09 14:07 ` [PATCH v5 17/29] powerpc/powernv/ioda/ioda2: Rework tce_build()/tce_free() Alexey Kardashevskiy
2015-03-09 14:07 ` [PATCH v5 18/29] powerpc/iommu/powernv: Release replaced TCE Alexey Kardashevskiy
2015-03-09 14:07 ` [PATCH v5 19/29] poweppc/powernv/ioda2: Rework iommu_table creation Alexey Kardashevskiy
2015-03-09 14:07 ` [PATCH v5 20/29] powerpc/powernv/ioda2: Introduce pnv_pci_ioda2_create_table/pnc_pci_free_table Alexey Kardashevskiy
2015-03-09 14:07 ` [PATCH v5 21/29] powerpc/powernv/ioda2: Introduce pnv_pci_ioda2_set_window Alexey Kardashevskiy
2015-03-09 14:07 ` [PATCH v5 22/29] powerpc/iommu: Split iommu_free_table into 2 helpers Alexey Kardashevskiy
2015-03-09 14:07 ` [PATCH v5 23/29] powerpc/powernv: Implement multilevel TCE tables Alexey Kardashevskiy
2015-03-09 14:07 ` [PATCH v5 24/29] powerpc/powernv: Change prototypes to receive iommu Alexey Kardashevskiy
2015-03-09 14:07 ` [PATCH v5 25/29] powerpc/powernv/ioda: Define and implement DMA table/window management callbacks Alexey Kardashevskiy
2015-03-11 8:54 ` Alexey Kardashevskiy
2015-03-11 9:31 ` Benjamin Herrenschmidt
2015-03-09 14:07 ` [PATCH v5 26/29] vfio: powerpc/spapr: Define v2 IOMMU Alexey Kardashevskiy
2015-03-11 0:00 ` Alex Williamson
2015-03-09 14:07 ` [PATCH v5 27/29] vfio: powerpc/spapr: powerpc/powernv/ioda2: Rework ownership Alexey Kardashevskiy
2015-03-11 0:09 ` Alex Williamson
2015-03-11 0:29 ` Alexey Kardashevskiy
2015-03-09 14:07 ` [PATCH v5 28/29] vfio: powerpc/spapr: Support multiple groups in one container if possible Alexey Kardashevskiy
2015-03-09 14:07 ` [PATCH v5 29/29] vfio: powerpc/spapr: Support Dynamic DMA windows Alexey Kardashevskiy
2015-03-11 1:10 ` Alex Williamson
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1425910045-26167-16-git-send-email-aik@ozlabs.ru \
--to=aik@ozlabs.ru \
--cc=alex.williamson@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=paulus@samba.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).