---
Changes since v1:
- Use dom0-iommu instead of the iommu option.
- Only enable by default on Intel hardware.
---
Cc: Andrew Cooper <andrew.coop...@citrix.com>
Cc: George Dunlap <george.dun...@eu.citrix.com>
Cc: Ian Jackson <ian.jack...@eu.citrix.com>
Cc: Jan Beulich <jbeul...@suse.com>
Cc: Julien Grall <julien.gr...@arm.com>
Cc: Konrad Rzeszutek Wilk <konrad.w...@oracle.com>
Cc: Stefano Stabellini <sstabell...@kernel.org>
Cc: Tim Deegan <t...@xen.org>
Cc: Wei Liu <wei.l...@citrix.com>
Cc: Kevin Tian <kevin.t...@intel.com>
---
docs/misc/xen-command-line.markdown | 14 +++++++
xen/drivers/passthrough/arm/iommu.c | 4 ++
xen/drivers/passthrough/iommu.c | 5 +++
xen/drivers/passthrough/vtd/extern.h | 2 -
xen/drivers/passthrough/vtd/iommu.c | 6 ---
xen/drivers/passthrough/vtd/x86/vtd.c | 58 +-------------------------
xen/drivers/passthrough/x86/iommu.c | 60 +++++++++++++++++++++++++++
xen/include/xen/iommu.h | 2 +
8 files changed, 86 insertions(+), 65 deletions(-)
diff --git a/docs/misc/xen-command-line.markdown
b/docs/misc/xen-command-line.markdown
index a2a07cc6c8..30d970bc2e 100644
--- a/docs/misc/xen-command-line.markdown
+++ b/docs/misc/xen-command-line.markdown
@@ -1230,6 +1230,17 @@ detection of systems known to misbehave upon accesses to
that port.
>> Controls whether to setup DMA remappings for all the host RAM except
regions
>> in use by Xen.
+> `inclusive`
+
+> Default: `true` on Intel hardware, `false` otherwise
+
+>> Use this to work around firmware issues providing incorrect RMRR or IVMD
+>> entries. Rather than only mapping RAM pages for IOMMU accesses for Dom0,
+>> with this option all pages up to 4GB, not marked as unusable in the E820
+>> table, will get a mapping established. Note that this option is only
+>> applicable to a PV dom0. Also note that if `strict` mode is enabled
+>> then conventional RAM pages not assigned to dom0 will not be mapped.
+
### iommu\_dev\_iotlb\_timeout
> `= <integer>`
@@ -1242,6 +1253,9 @@ wait descriptor timed out', try increasing this value.
### iommu\_inclusive\_mapping (VT-d)
> `= <boolean>`
+**WARNING: This command line option is deprecated, and superseded by
+_dom0-iommu=inclusive_ - using both options in combination is undefined.**
+
> Default: `true`
Use this to work around firmware issues providing incorrect RMRR entries.
diff --git a/xen/drivers/passthrough/arm/iommu.c
b/xen/drivers/passthrough/arm/iommu.c
index 95b1abb972..325997b19f 100644
--- a/xen/drivers/passthrough/arm/iommu.c
+++ b/xen/drivers/passthrough/arm/iommu.c
@@ -73,3 +73,7 @@ int arch_iommu_populate_page_table(struct domain *d)
/* The IOMMU shares the p2m with the CPU */
return -ENOSYS;
}
+
+void __hwdom_init arch_iommu_hwdom_init(struct domain *d)
+{
+}
diff --git a/xen/drivers/passthrough/iommu.c b/xen/drivers/passthrough/iommu.c
index 88e23bbd04..6611e13cc2 100644
--- a/xen/drivers/passthrough/iommu.c
+++ b/xen/drivers/passthrough/iommu.c
@@ -74,6 +74,7 @@ bool_t __read_mostly amd_iommu_perdev_intremap = 1;
custom_param("dom0-iommu", parse_dom0_iommu_param);
bool __hwdom_initdata iommu_dom0_strict;
bool __read_mostly iommu_dom0_passthrough;
+int8_t __hwdom_initdata iommu_dom0_inclusive = -1;
DEFINE_PER_CPU(bool_t, iommu_dont_flush_iotlb);
@@ -158,6 +159,8 @@ static int __init parse_dom0_iommu_param(const char *s)
iommu_dom0_strict = val;
else if ( !strncmp(s, "relaxed", ss - s) )
iommu_dom0_strict = !val;
+ else if ( !strncmp(s, "inclusive", ss - s) )
+ iommu_dom0_inclusive = val;
else
rc = -EINVAL;
@@ -240,6 +243,8 @@ void __hwdom_init iommu_hwdom_init(struct domain *d)
}
hd->platform_ops->hwdom_init(d);
+
+ arch_iommu_hwdom_init(d);
}
void iommu_teardown(struct domain *d)
diff --git a/xen/drivers/passthrough/vtd/extern.h
b/xen/drivers/passthrough/vtd/extern.h
index fb7edfaef9..91cadc602e 100644
--- a/xen/drivers/passthrough/vtd/extern.h
+++ b/xen/drivers/passthrough/vtd/extern.h
@@ -99,6 +99,4 @@ void pci_vtd_quirk(const struct pci_dev *);
bool_t platform_supports_intremap(void);
bool_t platform_supports_x2apic(void);
-void vtd_set_hwdom_mapping(struct domain *d);
-
#endif // _VTD_EXTERN_H_
diff --git a/xen/drivers/passthrough/vtd/iommu.c
b/xen/drivers/passthrough/vtd/iommu.c
index 8ac774215b..c880b0ce21 100644
--- a/xen/drivers/passthrough/vtd/iommu.c
+++ b/xen/drivers/passthrough/vtd/iommu.c
@@ -1304,12 +1304,6 @@ static void __hwdom_init intel_iommu_hwdom_init(struct
domain *d)
{
struct acpi_drhd_unit *drhd;
- if ( !iommu_dom0_passthrough && is_pv_domain(d) )
- {
- /* Set up 1:1 page table for hardware domain. */
- vtd_set_hwdom_mapping(d);
- }
-
setup_hwdom_pci_devices(d, setup_hwdom_device);
setup_hwdom_rmrr(d);
diff --git a/xen/drivers/passthrough/vtd/x86/vtd.c b/xen/drivers/passthrough/vtd/x86/vtd.c
index 00a9891005..20323051d0 100644
--- a/xen/drivers/passthrough/vtd/x86/vtd.c
+++ b/xen/drivers/passthrough/vtd/x86/vtd.c
@@ -25,7 +25,6 @@
#include <xen/irq.h>
#include <xen/numa.h>
#include <asm/fixmap.h>
-#include <asm/setup.h>
#include "../iommu.h"
#include "../dmar.h"
#include "../vtd.h"
@@ -35,8 +34,7 @@
* iommu_inclusive_mapping: when set, all memory below 4GB is included in dom0
* 1:1 iommu mappings except xen and unusable regions.
*/
-static bool_t __hwdom_initdata iommu_inclusive_mapping = 1;
-boolean_param("iommu_inclusive_mapping", iommu_inclusive_mapping);
+boolean_param("iommu_inclusive_mapping", iommu_dom0_inclusive);
void *map_vtd_domain_page(u64 maddr)
{
@@ -108,57 +106,3 @@ void hvm_dpci_isairq_eoi(struct domain *d, unsigned int
isairq)
spin_unlock(&d->event_lock);
}
-void __hwdom_init vtd_set_hwdom_mapping(struct domain *d)
-{
- unsigned long i, top, max_pfn;
-
- BUG_ON(!is_hardware_domain(d));
-
- max_pfn = (GB(4) >> PAGE_SHIFT) - 1;
- top = max(max_pdx, pfn_to_pdx(max_pfn) + 1);
-
- for ( i = 0; i < top; i++ )
- {
- unsigned long pfn = pdx_to_pfn(i);
- bool map;
- int rc;
-
- /*
- * Set up 1:1 mapping for dom0. Default to include only
- * conventional RAM areas and let RMRRs include needed reserved
- * regions. When set, the inclusive mapping additionally maps in
- * every pfn up to 4GB except those that fall in unusable ranges.
- */
- if ( pfn > max_pfn && !mfn_valid(_mfn(pfn)) )
- continue;
-
- if ( iommu_inclusive_mapping && pfn <= max_pfn )
- map = !page_is_ram_type(pfn, RAM_TYPE_UNUSABLE);
- else
- map = page_is_ram_type(pfn, RAM_TYPE_CONVENTIONAL);
-
- if ( !map )
- continue;
-
- /* Exclude Xen bits */
- if ( xen_in_range(pfn) )
- continue;
-
- /*
- * If dom0-strict mode is enabled then exclude conventional RAM
- * and let the common code map dom0's pages.
- */
- if ( iommu_dom0_strict &&
- page_is_ram_type(pfn, RAM_TYPE_CONVENTIONAL) )
- continue;
-
- rc = iommu_map_page(d, pfn, pfn, IOMMUF_readable|IOMMUF_writable);
- if ( rc )
- printk(XENLOG_WARNING VTDPREFIX " d%d: IOMMU mapping failed: %d\n",
- d->domain_id, rc);
-
- if (!(i & 0xfffff))
- process_pending_softirqs();
- }
-}
-
diff --git a/xen/drivers/passthrough/x86/iommu.c
b/xen/drivers/passthrough/x86/iommu.c
index 68182afd91..bf6edf4c04 100644
--- a/xen/drivers/passthrough/x86/iommu.c
+++ b/xen/drivers/passthrough/x86/iommu.c
@@ -20,6 +20,8 @@
#include <xen/softirq.h>
#include <xsm/xsm.h>
+#include <asm/setup.h>
+
void iommu_update_ire_from_apic(
unsigned int apic, unsigned int reg, unsigned int value)
{
@@ -132,6 +134,64 @@ void arch_iommu_domain_destroy(struct domain *d)
{
}
+void __hwdom_init arch_iommu_hwdom_init(struct domain *d)
+{
+ unsigned long i, top, max_pfn;
+
+ BUG_ON(!is_hardware_domain(d));
+
+ /* Set the default value of inclusive depending on the hardware. */
+ if ( iommu_dom0_inclusive == -1 )
+ iommu_dom0_inclusive = boot_cpu_data.x86_vendor == X86_VENDOR_INTEL;
+
+ max_pfn = (GB(4) >> PAGE_SHIFT) - 1;
+ top = max(max_pdx, pfn_to_pdx(max_pfn) + 1);
+
+ for ( i = 0; i < top; i++ )
+ {
+ unsigned long pfn = pdx_to_pfn(i);
+ bool map;
+ int rc;
+
+ /*
+ * Set up 1:1 mapping for dom0. Default to include only
+ * conventional RAM areas and let RMRRs include needed reserved
+ * regions. When set, the inclusive mapping additionally maps in
+ * every pfn up to 4GB except those that fall in unusable ranges.
+ */
+ if ( pfn > max_pfn && !mfn_valid(_mfn(pfn)) )
+ continue;
+
+ if ( iommu_dom0_inclusive && pfn <= max_pfn )
+ map = !page_is_ram_type(pfn, RAM_TYPE_UNUSABLE);
+ else
+ map = page_is_ram_type(pfn, RAM_TYPE_CONVENTIONAL);
+
+ if ( !map )
+ continue;
+
+ /* Exclude Xen bits */
+ if ( xen_in_range(pfn) )
+ continue;
+
+ /*
+ * If dom0-strict mode is enabled then exclude conventional RAM
+ * and let the common code map dom0's pages.
+ */
+ if ( iommu_dom0_strict &&
+ page_is_ram_type(pfn, RAM_TYPE_CONVENTIONAL) )
+ continue;
+
+ rc = iommu_map_page(d, pfn, pfn, IOMMUF_readable|IOMMUF_writable);
+ if ( rc )
+ printk(XENLOG_WARNING " d%d: IOMMU mapping failed: %d\n",
+ d->domain_id, rc);
+
+ if (!(i & 0xfffff))
+ process_pending_softirqs();
+ }
+}
+
/*
* Local variables:
* mode: C
diff --git a/xen/include/xen/iommu.h b/xen/include/xen/iommu.h
index c0c6975ac4..99e5b89c0f 100644
--- a/xen/include/xen/iommu.h
+++ b/xen/include/xen/iommu.h
@@ -37,6 +37,7 @@ extern bool_t iommu_debug;
extern bool_t amd_iommu_perdev_intremap;
extern bool iommu_dom0_strict, iommu_dom0_passthrough;
+extern int8_t iommu_dom0_inclusive;
extern unsigned int iommu_dev_iotlb_timeout;
@@ -51,6 +52,7 @@ void arch_iommu_domain_destroy(struct domain *d);
int arch_iommu_domain_init(struct domain *d);
int arch_iommu_populate_page_table(struct domain *d);
void arch_iommu_check_autotranslated_hwdom(struct domain *d);
+void arch_iommu_hwdom_init(struct domain *d);
int iommu_construct(struct domain *d);
