[RFC PATCH v1 1/8] iommu/dma: Prepare MSI physical address lists
From: Andrew Jones
Date: Wed Aug 26 2026 - 10:54:46 EST
Software MSI mappings may cover an ordered list of physical addresses
which must be mapped into one contiguous IOVA range. Extend the internal
DMA-IOMMU mapping helpers to accept an address array, address count, and
required mapping granule.
Teach iommu_dma_get_msi_page() to map the list into one contiguous IOVA
allocation. Keep the existing per-page cache entries and mark the first
entry with the size of the allocation so an identical list can reuse the
mapping without changing the existing cache representation.
This prepares for the forthcoming iommu_dma_prepare_msi_list() API.
Signed-off-by: Andrew Jones <andrew.jones@xxxxxxxxxxxxxxxx>
---
drivers/iommu/dma-iommu.c | 115 ++++++++++++++++++++++++++++----------
1 file changed, 87 insertions(+), 28 deletions(-)
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 9a07eb39336e..c256531ff19f 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -42,6 +42,7 @@ struct iommu_dma_msi_page {
struct list_head list;
dma_addr_t iova;
phys_addr_t phys;
+ size_t range_size; /* IOVA range size, or 0 if not the first map */
};
enum iommu_dma_queue_type {
@@ -481,7 +482,7 @@ static int cookie_init_hw_msi_region(struct iommu_dma_cookie *cookie,
num_pages = iova_align(iovad, end - start) >> iova_shift(iovad);
for (i = 0; i < num_pages; i++) {
- msi_page = kmalloc_obj(*msi_page);
+ msi_page = kzalloc_obj(*msi_page);
if (!msi_page)
return -ENOMEM;
@@ -2196,15 +2197,41 @@ static struct list_head *cookie_msi_pages(const struct iommu_domain *domain)
}
}
+static bool iommu_dma_msi_range_matches(struct list_head *msi_page_list,
+ const struct iommu_dma_msi_page *base_page,
+ const phys_addr_t *phys_addrs,
+ unsigned int nr_addrs, size_t granule)
+{
+ const struct iommu_dma_msi_page *msi_page;
+ unsigned int nr_found = 0;
+ dma_addr_t offset;
+
+ list_for_each_entry(msi_page, msi_page_list, list) {
+ if (msi_page->iova < base_page->iova)
+ continue;
+ offset = msi_page->iova - base_page->iova;
+ if (offset >= base_page->range_size)
+ continue;
+ if (!IS_ALIGNED(offset, granule) || msi_page->phys != phys_addrs[offset / granule])
+ return false;
+ nr_found++;
+ }
+
+ return nr_found == nr_addrs;
+}
+
static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
- phys_addr_t msi_addr, struct iommu_domain *domain)
+ const phys_addr_t *phys_addrs, unsigned int nr_addrs, size_t granule,
+ struct iommu_domain *domain)
{
struct list_head *msi_page_list = cookie_msi_pages(domain);
- struct iommu_dma_msi_page *msi_page;
- dma_addr_t iova;
+ struct iommu_dma_msi_page *msi_page, *first_page = NULL;
int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
- size_t size = cookie_msi_granule(domain);
static DEFINE_MUTEX(msi_prepare_lock);
+ LIST_HEAD(new_msi_pages);
+ dma_addr_t base_iova;
+ unsigned int i;
+ size_t size;
/*
* Normally a device's default domain is only ever attached to that
@@ -2218,32 +2245,60 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
*/
guard(mutex)(&msi_prepare_lock);
- msi_addr &= ~(phys_addr_t)(size - 1);
- list_for_each_entry(msi_page, msi_page_list, list)
- if (msi_page->phys == msi_addr)
+ if (!nr_addrs || nr_addrs > SIZE_MAX / granule)
+ return NULL;
+ size = nr_addrs * granule;
+
+ list_for_each_entry(msi_page, msi_page_list, list) {
+ if (msi_page->phys != phys_addrs[0])
+ continue;
+ if (nr_addrs == 1)
+ return msi_page;
+ if (msi_page->range_size == size &&
+ iommu_dma_msi_range_matches(msi_page_list, msi_page, phys_addrs,
+ nr_addrs, granule))
return msi_page;
+ }
- msi_page = kzalloc_obj(*msi_page);
- if (!msi_page)
- return NULL;
+ for (i = 0; i < nr_addrs; i++) {
+ msi_page = kzalloc_obj(*msi_page);
+ if (!msi_page)
+ goto out_free_pages;
+ list_add_tail(&msi_page->list, &new_msi_pages);
+ }
- iova = iommu_dma_alloc_iova(domain, size, dma_get_mask(dev), dev);
- if (!iova)
- goto out_free_page;
+ base_iova = iommu_dma_alloc_iova(domain, size, dma_get_mask(dev), dev);
+ if (!base_iova)
+ goto out_free_pages;
- if (iommu_map(domain, iova, msi_addr, size, prot, GFP_KERNEL))
- goto out_free_iova;
+ i = 0;
+ list_for_each_entry(msi_page, &new_msi_pages, list) {
+ msi_page->phys = phys_addrs[i];
+ msi_page->iova = base_iova + i * granule;
+ if (!i)
+ first_page = msi_page;
+ if (iommu_map(domain, msi_page->iova, msi_page->phys, granule, prot, GFP_KERNEL))
+ goto out_unmap;
+ i++;
+ }
- INIT_LIST_HEAD(&msi_page->list);
- msi_page->phys = msi_addr;
- msi_page->iova = iova;
- list_add(&msi_page->list, msi_page_list);
- return msi_page;
+ first_page->range_size = size;
+ list_splice(&new_msi_pages, msi_page_list);
+ return first_page;
-out_free_iova:
- iommu_dma_free_iova(domain, iova, size, NULL);
-out_free_page:
- kfree(msi_page);
+out_unmap:
+ if (i) {
+ size_t unmap = iommu_unmap(domain, base_iova, i * granule);
+
+ WARN_ON_ONCE(unmap != i * granule);
+ }
+ iommu_dma_free_iova(domain, base_iova, size, NULL);
+out_free_pages:
+ while (!list_empty(&new_msi_pages)) {
+ msi_page = list_first_entry(&new_msi_pages, typeof(*msi_page), list);
+ list_del(&msi_page->list);
+ kfree(msi_page);
+ }
return NULL;
}
@@ -2252,19 +2307,23 @@ int iommu_dma_sw_msi(struct iommu_domain *domain, struct msi_desc *desc,
{
struct device *dev = msi_desc_to_dev(desc);
const struct iommu_dma_msi_page *msi_page;
+ phys_addr_t phys_addr;
+ size_t granule;
if (!has_msi_cookie(domain)) {
msi_desc_set_iommu_msi_iova(desc, 0, 0);
return 0;
}
+ granule = cookie_msi_granule(domain);
+ phys_addr = ALIGN_DOWN(msi_addr, granule);
+
iommu_group_mutex_assert(dev);
- msi_page = iommu_dma_get_msi_page(dev, msi_addr, domain);
+ msi_page = iommu_dma_get_msi_page(dev, &phys_addr, 1, granule, domain);
if (!msi_page)
return -ENOMEM;
- msi_desc_set_iommu_msi_iova(desc, msi_page->iova,
- ilog2(cookie_msi_granule(domain)));
+ msi_desc_set_iommu_msi_iova(desc, msi_page->iova, ilog2(granule));
return 0;
}
--
2.43.0