[PATCH 02/10] iommu/vt-d: Add __iommu_flush_iotlb_psi()

From: Lu Baolu
Date: Mon Feb 19 2024 - 06:22:19 EST


From: Yi Liu <yi.l.liu@xxxxxxxxx>

Add __iommu_flush_iotlb_psi() to do the psi iotlb flush with a DID input
rather than calculating it within the helper.

This is useful when flushing cache for parent domain which reuses DIDs of
its nested domains.

Signed-off-by: Yi Liu <yi.l.liu@xxxxxxxxx>
Reviewed-by: Kevin Tian <kevin.tian@xxxxxxxxx>
Link: https://lore.kernel.org/r/20240208082307.15759-3-yi.l.liu@xxxxxxxxx
Signed-off-by: Lu Baolu <baolu.lu@xxxxxxxxxxxxxxx>
---
drivers/iommu/intel/iommu.c | 78 ++++++++++++++++++++-----------------
1 file changed, 43 insertions(+), 35 deletions(-)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index e393c62776f3..dbdb8366c42a 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -1368,6 +1368,46 @@ static void domain_flush_pasid_iotlb(struct intel_iommu *iommu,
spin_unlock_irqrestore(&domain->lock, flags);
}

+static void __iommu_flush_iotlb_psi(struct intel_iommu *iommu, u16 did,
+ unsigned long pfn, unsigned int pages,
+ int ih)
+{
+ unsigned int aligned_pages = __roundup_pow_of_two(pages);
+ unsigned long bitmask = aligned_pages - 1;
+ unsigned int mask = ilog2(aligned_pages);
+ u64 addr = (u64)pfn << VTD_PAGE_SHIFT;
+
+ /*
+ * PSI masks the low order bits of the base address. If the
+ * address isn't aligned to the mask, then compute a mask value
+ * needed to ensure the target range is flushed.
+ */
+ if (unlikely(bitmask & pfn)) {
+ unsigned long end_pfn = pfn + pages - 1, shared_bits;
+
+ /*
+ * Since end_pfn <= pfn + bitmask, the only way bits
+ * higher than bitmask can differ in pfn and end_pfn is
+ * by carrying. This means after masking out bitmask,
+ * high bits starting with the first set bit in
+ * shared_bits are all equal in both pfn and end_pfn.
+ */
+ shared_bits = ~(pfn ^ end_pfn) & ~bitmask;
+ mask = shared_bits ? __ffs(shared_bits) : BITS_PER_LONG;
+ }
+
+ /*
+ * Fallback to domain selective flush if no PSI support or
+ * the size is too big.
+ */
+ if (!cap_pgsel_inv(iommu->cap) || mask > cap_max_amask_val(iommu->cap))
+ iommu->flush.flush_iotlb(iommu, did, 0, 0,
+ DMA_TLB_DSI_FLUSH);
+ else
+ iommu->flush.flush_iotlb(iommu, did, addr | ih, mask,
+ DMA_TLB_PSI_FLUSH);
+}
+
static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
struct dmar_domain *domain,
unsigned long pfn, unsigned int pages,
@@ -1384,42 +1424,10 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
if (ih)
ih = 1 << 6;

- if (domain->use_first_level) {
+ if (domain->use_first_level)
domain_flush_pasid_iotlb(iommu, domain, addr, pages, ih);
- } else {
- unsigned long bitmask = aligned_pages - 1;
-
- /*
- * PSI masks the low order bits of the base address. If the
- * address isn't aligned to the mask, then compute a mask value
- * needed to ensure the target range is flushed.
- */
- if (unlikely(bitmask & pfn)) {
- unsigned long end_pfn = pfn + pages - 1, shared_bits;
-
- /*
- * Since end_pfn <= pfn + bitmask, the only way bits
- * higher than bitmask can differ in pfn and end_pfn is
- * by carrying. This means after masking out bitmask,
- * high bits starting with the first set bit in
- * shared_bits are all equal in both pfn and end_pfn.
- */
- shared_bits = ~(pfn ^ end_pfn) & ~bitmask;
- mask = shared_bits ? __ffs(shared_bits) : BITS_PER_LONG;
- }
-
- /*
- * Fallback to domain selective flush if no PSI support or
- * the size is too big.
- */
- if (!cap_pgsel_inv(iommu->cap) ||
- mask > cap_max_amask_val(iommu->cap))
- iommu->flush.flush_iotlb(iommu, did, 0, 0,
- DMA_TLB_DSI_FLUSH);
- else
- iommu->flush.flush_iotlb(iommu, did, addr | ih, mask,
- DMA_TLB_PSI_FLUSH);
- }
+ else
+ __iommu_flush_iotlb_psi(iommu, did, pfn, pages, ih);

/*
* In caching mode, changes of pages from non-present to present require
--
2.34.1