dma-mapping: Provide an interface to allow allocate IOVA

JIRA: https://issues.redhat.com/browse/RHEL-113839
Upstream-Status: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
Conflicts: iommu_dma_free_iova still takes cookie in RHEL9.

commit 393cf70
Author: Leon Romanovsky <leonro@nvidia.com>
Date:   Mon May 5 10:01:42 2025 +0300

    dma-mapping: Provide an interface to allow allocate IOVA

    Extend DMA-API to provide an interface to allocate IOVA space.

    Such interface is needed to give to the callers ability to allocate
    IOVA space with specific alignment. After allocation of such space,
    callers will be able to reuse that IOVA space for multiple mappings.

    Reviewed-by: Christoph Hellwig <hch@lst.de>
    Tested-by: Jens Axboe <axboe@kernel.dk>
    Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
    Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
    Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>

(cherry picked from commit 393cf70)
Co-developed-by: Claude claude-sonnet-4
Signed-off-by: Jerry Snitselaar <jsnitsel@redhat.com>

Author: snits

drivers/iommu/dma-iommu.c

@@ -1746,6 +1746,92 @@ size_t iommu_dma_max_mapping_size(struct device *dev)
 	return SIZE_MAX;
 }
 
+/**
+ * dma_iova_try_alloc - Try to allocate an IOVA space
+ * @dev: Device to allocate the IOVA space for
+ * @state: IOVA state
+ * @phys: physical address
+ * @size: IOVA size
+ *
+ * Check if @dev supports the IOVA-based DMA API, and if yes allocate IOVA space
+ * for the given base address and size.
+ *
+ * Note: @phys is only used to calculate the IOVA alignment. Callers that always
+ * do PAGE_SIZE aligned transfers can safely pass 0 here.
+ *
+ * Returns %true if the IOVA-based DMA API can be used and IOVA space has been
+ * allocated, or %false if the regular DMA API should be used.
+ */
+bool dma_iova_try_alloc(struct device *dev, struct dma_iova_state *state,
+		phys_addr_t phys, size_t size)
+{
+	struct iommu_dma_cookie *cookie;
+	struct iommu_domain *domain;
+	struct iova_domain *iovad;
+	size_t iova_off;
+	dma_addr_t addr;
+
+	memset(state, 0, sizeof(*state));
+	if (!use_dma_iommu(dev))
+		return false;
+
+	domain = iommu_get_dma_domain(dev);
+	cookie = domain->iova_cookie;
+	iovad = &cookie->iovad;
+	iova_off = iova_offset(iovad, phys);
+
+	if (static_branch_unlikely(&iommu_deferred_attach_enabled) &&
+	    iommu_deferred_attach(dev, iommu_get_domain_for_dev(dev)))
+		return false;
+
+	if (WARN_ON_ONCE(!size))
+		return false;
+
+	/*
+	 * DMA_IOVA_USE_SWIOTLB is flag which is set by dma-iommu
+	 * internals, make sure that caller didn't set it and/or
+	 * didn't use this interface to map SIZE_MAX.
+	 */
+	if (WARN_ON_ONCE((u64)size & DMA_IOVA_USE_SWIOTLB))
+		return false;
+
+	addr = iommu_dma_alloc_iova(domain,
+			iova_align(iovad, size + iova_off),
+			dma_get_mask(dev), dev);
+	if (!addr)
+		return false;
+
+	state->addr = addr + iova_off;
+	state->__size = size;
+	return true;
+}
+EXPORT_SYMBOL_GPL(dma_iova_try_alloc);
+
+/**
+ * dma_iova_free - Free an IOVA space
+ * @dev: Device to free the IOVA space for
+ * @state: IOVA state
+ *
+ * Undoes a successful dma_try_iova_alloc().
+ *
+ * Note that all dma_iova_link() calls need to be undone first.  For callers
+ * that never call dma_iova_unlink(), dma_iova_destroy() can be used instead
+ * which unlinks all ranges and frees the IOVA space in a single efficient
+ * operation.
+ */
+void dma_iova_free(struct device *dev, struct dma_iova_state *state)
+{
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
+	size_t iova_start_pad = iova_offset(iovad, state->addr);
+	size_t size = dma_iova_size(state);
+
+	iommu_dma_free_iova(cookie, state->addr - iova_start_pad,
+			iova_align(iovad, size + iova_start_pad), NULL);
+}
+EXPORT_SYMBOL_GPL(dma_iova_free);
+
 void iommu_setup_dma_ops(struct device *dev)
 {
 	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);

include/linux/dma-mapping.h

@@ -72,6 +72,22 @@
 
 #define DMA_BIT_MASK(n)	(((n) == 64) ? ~0ULL : ((1ULL<<(n))-1))
 
+struct dma_iova_state {
+	dma_addr_t addr;
+	u64 __size;
+};
+
+/*
+ * Use the high bit to mark if we used swiotlb for one or more ranges.
+ */
+#define DMA_IOVA_USE_SWIOTLB		(1ULL << 63)
+
+static inline size_t dma_iova_size(struct dma_iova_state *state)
+{
+	/* Casting is needed for 32-bits systems */
+	return (size_t)(state->__size & ~DMA_IOVA_USE_SWIOTLB);
+}
+
 #ifdef CONFIG_DMA_API_DEBUG
 void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr);
 void debug_dma_map_single(struct device *dev, const void *addr,
@@ -277,6 +293,38 @@ static inline int dma_mmap_noncontiguous(struct device *dev,
 }
 #endif /* CONFIG_HAS_DMA */
 
+#ifdef CONFIG_IOMMU_DMA
+/**
+ * dma_use_iova - check if the IOVA API is used for this state
+ * @state: IOVA state
+ *
+ * Return %true if the DMA transfers uses the dma_iova_*() calls or %false if
+ * they can't be used.
+ */
+static inline bool dma_use_iova(struct dma_iova_state *state)
+{
+	return state->__size != 0;
+}
+
+bool dma_iova_try_alloc(struct device *dev, struct dma_iova_state *state,
+		phys_addr_t phys, size_t size);
+void dma_iova_free(struct device *dev, struct dma_iova_state *state);
+#else /* CONFIG_IOMMU_DMA */
+static inline bool dma_use_iova(struct dma_iova_state *state)
+{
+	return false;
+}
+static inline bool dma_iova_try_alloc(struct device *dev,
+		struct dma_iova_state *state, phys_addr_t phys, size_t size)
+{
+	return false;
+}
+static inline void dma_iova_free(struct device *dev,
+		struct dma_iova_state *state)
+{
+}
+#endif /* CONFIG_IOMMU_DMA */
+
 #if defined(CONFIG_HAS_DMA) && defined(CONFIG_DMA_NEED_SYNC)
 void __dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size,
 		enum dma_data_direction dir);