This adds a way for the IOMMU user to know how much a new table will
use so it can be accounted in the locked_vm limit before allocation
happens.
This stores the allocated table size in pnv_pci_ioda2_get_table_size()
so the locked_vm counter can be updated correctly when a table is
being disposed.
This defines an iommu_table_group_ops callback to let VFIO know
how much memory will be locked if a table is created.
Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
---
Changes:
v10:
* s/ROUND_UP/_ALIGN_UP/
* fixed rounding up for @entries_shift (used to use ROUND_UP)
v9:
* reimplemented the whole patch
---
arch/powerpc/include/asm/iommu.h | 5 +++++
arch/powerpc/platforms/powernv/pci-ioda.c | 35 +++++++++++++++++++++++++++++++
2 files changed, 40 insertions(+)
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index e554175..9d37492 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -99,6 +99,7 @@ struct iommu_table {
unsigned long it_size; /* Size of iommu table in entries */
unsigned long it_indirect_levels;
unsigned long it_level_size;
+ unsigned long it_allocated_size;
unsigned long it_offset; /* Offset into global table */
unsigned long it_base; /* mapped address of tce table */
unsigned long it_index; /* which iommu table this is */
@@ -147,6 +148,10 @@ extern struct iommu_table *iommu_init_table(struct
iommu_table * tbl,
struct iommu_table_group;
struct iommu_table_group_ops {
+ unsigned long (*get_table_size)(
+ __u32 page_shift,
+ __u64 window_size,
+ __u32 levels);
long (*create_table)(struct iommu_table_group *table_group,
int num,
__u32 page_shift,
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c
b/arch/powerpc/platforms/powernv/pci-ioda.c
index 00739883..c77c85e 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -41,6 +41,7 @@
#include <asm/debug.h>
#include <asm/firmware.h>
#include <asm/pnv-pci.h>
+#include <asm/mmzone.h>
#include <misc/cxl.h>
@@ -2072,6 +2073,38 @@ static long pnv_pci_ioda2_create_table(struct
iommu_table_group *table_group,
}
#ifdef CONFIG_IOMMU_API
+static unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift,
+ __u64 window_size, __u32 levels)
+{
+ unsigned long bytes = 0;
+ const unsigned window_shift = ilog2(window_size);
+ unsigned entries_shift = window_shift - page_shift;
+ unsigned table_shift = entries_shift + 3;
+ unsigned long tce_table_size = max(0x1000UL, 1UL << table_shift);
+ unsigned long direct_table_size;
+
+ if (!levels || (levels > POWERNV_IOMMU_MAX_LEVELS) ||
+ (window_size > memory_hotplug_max()) ||
+ !is_power_of_2(window_size))
+ return 0;
+
+ /* Calculate a direct table size from window_size and levels */
+ entries_shift = (entries_shift + levels - 1) / levels;
+ table_shift = entries_shift + 3;
+ table_shift = max_t(unsigned, table_shift, PAGE_SHIFT);
+ direct_table_size = 1UL << table_shift;
+
+ for ( ; levels; --levels) {
+ bytes += _ALIGN_UP(tce_table_size, direct_table_size);
+
+ tce_table_size /= direct_table_size;
+ tce_table_size <<= 3;
+ tce_table_size = _ALIGN_UP(tce_table_size, direct_table_size);
+ }
+
+ return bytes;
+}
+
static long pnv_pci_ioda2_unset_window(struct iommu_table_group *table_group,
int num)
{
@@ -2115,6 +2148,7 @@ static void pnv_ioda2_release_ownership(struct
iommu_table_group *table_group)
}
static struct iommu_table_group_ops pnv_pci_ioda2_ops = {
+ .get_table_size = pnv_pci_ioda2_get_table_size,
.create_table = pnv_pci_ioda2_create_table,
.set_window = pnv_pci_ioda2_set_window,
.unset_window = pnv_pci_ioda2_unset_window,
@@ -2219,6 +2253,7 @@ static long pnv_pci_ioda2_table_alloc_pages(int nid,
__u64 bus_offset,
page_shift);
tbl->it_level_size = 1ULL << (level_shift - 3);
tbl->it_indirect_levels = levels - 1;
+ tbl->it_allocated_size = tce_table_allocated;
pr_devel("Created TCE table: ws=%08llx ts=%lx @%08llx\n",
window_size, tce_table_size, bus_offset);
--
2.4.0.rc3.8.gfb3e7d5
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
