[PATCH v4 01/21] iommufd: Convert struct iommufd_sw_msi_maps to a growable bitmap
From: Andrew Jones
Date: Thu Aug 20 2026 - 17:45:11 EST
struct iommufd_sw_msi_maps uses a fixed 64-bit bitmap, limiting each
group and hardware page table to 64 software MSI mappings. RISC-V
interrupt remapping needs a mapping for every possible CPU, so this
limit is insufficient.
Make the bitmap grow on demand and treat IDs beyond its current size
as absent. Cap it at 16K entries to bound allocation size while leaving
ample room for expected software MSI users.
Signed-off-by: Andrew Jones <andrew.jones@xxxxxxxxxxxxxxxx>
---
drivers/iommu/iommufd/device.c | 3 +-
drivers/iommu/iommufd/driver.c | 38 +++++++++++++++--------
drivers/iommu/iommufd/hw_pagetable.c | 1 +
drivers/iommu/iommufd/iommufd_private.h | 41 +++++++++++++++++++++++--
4 files changed, 67 insertions(+), 16 deletions(-)
diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c
index d488c23fd353..868f1e591208 100644
--- a/drivers/iommu/iommufd/device.c
+++ b/drivers/iommu/iommufd/device.c
@@ -34,6 +34,7 @@ static void iommufd_group_release(struct kref *kref)
NULL, GFP_KERNEL);
iommu_group_put(igroup->group);
mutex_destroy(&igroup->lock);
+ kfree(igroup->required_sw_msi.bitmap);
kfree(igroup);
}
@@ -384,7 +385,7 @@ static int iommufd_group_setup_msi(struct iommufd_group *igroup,
int rc;
if (cur->sw_msi_start != igroup->sw_msi_start ||
- !test_bit(cur->id, igroup->required_sw_msi.bitmap))
+ !iommufd_sw_msi_maps_test_bit(&igroup->required_sw_msi, cur->id))
continue;
rc = iommufd_sw_msi_install(ictx, hwpt_paging, cur);
diff --git a/drivers/iommu/iommufd/driver.c b/drivers/iommu/iommufd/driver.c
index 3b8067976eac..9b9316ae4266 100644
--- a/drivers/iommu/iommufd/driver.c
+++ b/drivers/iommu/iommufd/driver.c
@@ -196,13 +196,15 @@ iommufd_sw_msi_get_map(struct iommufd_ctx *ictx, phys_addr_t msi_addr,
list_for_each_entry(cur, &ictx->sw_msi_list, sw_msi_item) {
if (cur->sw_msi_start != sw_msi_start)
continue;
+ if (cur->pgoff == UINT_MAX)
+ return ERR_PTR(-EOVERFLOW);
max_pgoff = max(max_pgoff, cur->pgoff + 1);
if (cur->msi_addr == msi_addr)
return cur;
}
- if (ictx->sw_msi_id >=
- BITS_PER_BYTE * sizeof_field(struct iommufd_sw_msi_maps, bitmap))
+ if (ictx->sw_msi_id > IOMMUFD_SW_MSI_MAX_ID ||
+ max_pgoff > (ULONG_MAX - sw_msi_start) / PAGE_SIZE)
return ERR_PTR(-EOVERFLOW);
cur = kzalloc_obj(*cur);
@@ -222,21 +224,26 @@ int iommufd_sw_msi_install(struct iommufd_ctx *ictx,
struct iommufd_sw_msi_map *msi_map)
{
unsigned long iova;
+ int rc;
lockdep_assert_held(&ictx->sw_msi_lock);
+ if (iommufd_sw_msi_maps_test_bit(&hwpt_paging->present_sw_msi,
+ msi_map->id))
+ return 0;
+
iova = msi_map->sw_msi_start + msi_map->pgoff * PAGE_SIZE;
- if (!test_bit(msi_map->id, hwpt_paging->present_sw_msi.bitmap)) {
- int rc;
-
- rc = iommu_map(hwpt_paging->common.domain, iova,
- msi_map->msi_addr, PAGE_SIZE,
- IOMMU_WRITE | IOMMU_READ | IOMMU_MMIO,
- GFP_KERNEL_ACCOUNT);
- if (rc)
- return rc;
- __set_bit(msi_map->id, hwpt_paging->present_sw_msi.bitmap);
- }
+ rc = iommufd_sw_msi_maps_ensure(&hwpt_paging->present_sw_msi, msi_map->id);
+ if (rc)
+ return rc;
+
+ rc = iommu_map(hwpt_paging->common.domain, iova,
+ msi_map->msi_addr, PAGE_SIZE,
+ IOMMU_WRITE | IOMMU_READ | IOMMU_MMIO,
+ GFP_KERNEL_ACCOUNT);
+ if (rc)
+ return rc;
+ __set_bit(msi_map->id, hwpt_paging->present_sw_msi.bitmap);
return 0;
}
EXPORT_SYMBOL_NS_GPL(iommufd_sw_msi_install, "IOMMUFD_INTERNAL");
@@ -290,6 +297,11 @@ int iommufd_sw_msi(struct iommu_domain *domain, struct msi_desc *desc,
if (IS_ERR(msi_map))
return PTR_ERR(msi_map);
+ rc = iommufd_sw_msi_maps_ensure(&handle->idev->igroup->required_sw_msi,
+ msi_map->id);
+ if (rc)
+ return rc;
+
rc = iommufd_sw_msi_install(ictx, hwpt_paging, msi_map);
if (rc)
return rc;
diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c
index 623cc608ca0c..54873de43eb0 100644
--- a/drivers/iommu/iommufd/hw_pagetable.c
+++ b/drivers/iommu/iommufd/hw_pagetable.c
@@ -32,6 +32,7 @@ void iommufd_hwpt_paging_destroy(struct iommufd_object *obj)
}
__iommufd_hwpt_destroy(&hwpt_paging->common);
+ kfree(hwpt_paging->present_sw_msi.bitmap);
refcount_dec(&hwpt_paging->ioas->obj.users);
}
diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index 43fbc5bed8de..9ca5f9f92cdf 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -9,6 +9,7 @@
#include <linux/iova_bitmap.h>
#include <linux/maple_tree.h>
#include <linux/rwsem.h>
+#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/xarray.h>
#include <uapi/linux/iommufd.h>
@@ -29,11 +30,47 @@ struct iommufd_sw_msi_map {
unsigned int id;
};
-/* Bitmap of struct iommufd_sw_msi_map::id */
+/* Bitmap of struct iommufd_sw_msi_map::id; starts empty, grows on demand. */
struct iommufd_sw_msi_maps {
- DECLARE_BITMAP(bitmap, 64);
+ unsigned long *bitmap;
+ unsigned int nbits;
};
+/* Large enough for foreseeable SW MSI users while bounding bitmap growth. */
+#define IOMMUFD_SW_MSI_MAX_ID (16U * 1024 - 1)
+
+/* Grow bitmap to accommodate id. Must be called under ictx->sw_msi_lock. */
+static inline int iommufd_sw_msi_maps_ensure(struct iommufd_sw_msi_maps *maps,
+ unsigned int id)
+{
+ unsigned long *new_bitmap;
+ unsigned int new_nbits;
+
+ if (id < maps->nbits)
+ return 0;
+ if (id > IOMMUFD_SW_MSI_MAX_ID)
+ return -EOVERFLOW;
+
+ new_nbits = max(ALIGN(id + 1, BITS_PER_LONG), 64U);
+ new_bitmap = krealloc(maps->bitmap,
+ BITS_TO_LONGS(new_nbits) * sizeof(unsigned long),
+ GFP_KERNEL_ACCOUNT);
+ if (!new_bitmap)
+ return -ENOMEM;
+ bitmap_clear(new_bitmap, maps->nbits, new_nbits - maps->nbits);
+ maps->bitmap = new_bitmap;
+ maps->nbits = new_nbits;
+ return 0;
+}
+
+static inline bool iommufd_sw_msi_maps_test_bit(const struct iommufd_sw_msi_maps *maps,
+ unsigned int id)
+{
+ if (id >= maps->nbits)
+ return false;
+ return test_bit(id, maps->bitmap);
+}
+
#ifdef CONFIG_IRQ_MSI_IOMMU
int iommufd_sw_msi_install(struct iommufd_ctx *ictx,
struct iommufd_hwpt_paging *hwpt_paging,
--
2.43.0