powerpc/iommu/ioda2: Add get_table_size() to calculate the size of future table

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 <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index e5541759a37d2d2ef27bf2693b5c40d2199895dd..9d37492876897bbdfac858b547cdb8fbd9606910 100644 (file)
--- 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 510bb9c8a9e16fe32a10e7391511dc58bef16184..a7e098dba23d7e573fdf3d087258bfa7e3f77abc 100644 (file)
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -2074,6 +2074,38 @@ 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)
 {
@@ -2117,6 +2149,7 @@ 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,
@@ -2228,6 +2261,7 @@ 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 = offset;
 
        pr_devel("Created TCE table: ws=%08llx ts=%lx @%08llx\n",
                        window_size, tce_table_size, bus_offset);