diff --git a/Documentation/core-api/dma-api.rst b/Documentation/core-api/dma-api.rst
index ba23a472f794..69d4ebe4f96d 100644
--- a/Documentation/core-api/dma-api.rst
+++ b/Documentation/core-api/dma-api.rst
@@ -154,7 +154,7 @@ others should not be larger than the returned value.
 ::
 
 	size_t
-	dma_opt_mapping_size(struct device *dev);
+	dma_max_opt_mapping_size(struct device *dev);
 
 Returns the maximum optimal size of a mapping for the device.
 
diff --git a/MAINTAINERS b/MAINTAINERS
index cdd7434fdb6f..c06f28684c4c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7772,6 +7772,7 @@ F:	include/linux/dma-direct.h
 F:	include/linux/dma-map-ops.h
 F:	include/linux/dma-mapping.h
 F:	include/linux/swiotlb.h
+F:	include/trace/events/dma.h
 F:	kernel/dma/
 
 DMA MAPPING & SCATTERLIST API [RUST]
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index 882cd70c7a2f..a6cf55c6fd55 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -125,7 +125,7 @@ static int __init xen_mm_init(void)
 		return 0;
 
 	/* we can work with the default swiotlb */
-	rc = swiotlb_init_late(swiotlb_size_or_default(),
+	rc = swiotlb_init_late(swiotlb_default_pool_size(),
 			       xen_swiotlb_gfp(), NULL);
 	if (rc < 0)
 		return rc;
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 2a8de20d2b44..4e7682dfe366 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -349,7 +349,7 @@ void __init arch_mm_preinit(void)
 		unsigned long size =
 			DIV_ROUND_UP(memblock_phys_mem_size(), 1024);
 
-		swiotlb_adjust_size(min(swiotlb_size_or_default(), size));
+		swiotlb_adjust_size(min(swiotlb_default_pool_size(), size));
 	}
 
 	swiotlb_init(true, flags);
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 857f9a55039c..b50de11605c6 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -186,7 +186,7 @@ void __init arch_mm_preinit(void)
 		 */
 		unsigned long size =
 			DIV_ROUND_UP(memblock_phys_mem_size(), 1024);
-		swiotlb_adjust_size(min(swiotlb_size_or_default(), size));
+		swiotlb_adjust_size(min(swiotlb_default_pool_size(), size));
 		swiotlb = true;
 		swiotlb_flags |= SWIOTLB_ANY;
 	}
diff --git a/arch/x86/include/asm/crash_reserve.h b/arch/x86/include/asm/crash_reserve.h
index 7835b2cdff04..047f638a766d 100644
--- a/arch/x86/include/asm/crash_reserve.h
+++ b/arch/x86/include/asm/crash_reserve.h
@@ -18,7 +18,7 @@
  * no good way to detect the paging mode of the target kernel which will be
  * loaded for dumping.
  */
-extern unsigned long swiotlb_size_or_default(void);
+extern unsigned long swiotlb_default_pool_size(void);
 
 #ifdef CONFIG_X86_32
 # define CRASH_ADDR_LOW_MAX     SZ_512M
@@ -33,7 +33,7 @@ extern unsigned long swiotlb_size_or_default(void);
 static inline unsigned long crash_low_size_default(void)
 {
 #ifdef CONFIG_X86_64
-	return max(swiotlb_size_or_default() + (8UL << 20), 256UL << 20);
+	return max(swiotlb_default_pool_size() + (8UL << 20), 256UL << 20);
 #else
 	return 0;
 #endif
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 68ee57800fef..26b9c2d71cd3 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1628,10 +1628,12 @@ static void *iommu_dma_alloc_pages(struct device *dev, size_t size,
 	void *cpu_addr;
 
 	page = dma_alloc_contiguous(dev, alloc_size, gfp);
-	if (!page)
-		page = alloc_pages_node(node, gfp, get_order(alloc_size));
-	if (!page)
-		return NULL;
+	if (!page) {
+		cpu_addr = alloc_pages_exact_nid(node, alloc_size, gfp);
+		if (!cpu_addr)
+			return NULL;
+		page = virt_to_page(cpu_addr);
+	}
 
 	if (!coherent || PageHighMem(page)) {
 		pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs);
@@ -1762,7 +1764,7 @@ unsigned long iommu_dma_get_merge_boundary(struct device *dev)
 	return (1UL << __ffs(domain->pgsize_bitmap)) - 1;
 }
 
-size_t iommu_dma_opt_mapping_size(void)
+size_t iommu_dma_max_opt_mapping_size(void)
 {
 	return iova_rcache_range();
 }
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 77317e5d00f9..dbcfc7ddb78a 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -3747,7 +3747,7 @@ static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev,
 	 */
 	dev->ctrl.max_hw_sectors = min_t(u32,
 			NVME_MAX_BYTES >> SECTOR_SHIFT,
-			dma_opt_mapping_size(&pdev->dev) >> 9);
+			dma_max_opt_mapping_size(&pdev->dev) >> SECTOR_SHIFT);
 	dev->ctrl.max_segments = NVME_MAX_SEGS;
 	dev->ctrl.max_integrity_segments = 1;
 	return dev;
diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c
index a825966f60e5..50ecce7ef9cd 100644
--- a/drivers/scsi/scsi_transport_sas.c
+++ b/drivers/scsi/scsi_transport_sas.c
@@ -225,8 +225,8 @@ static int sas_bsg_initialize(struct Scsi_Host *shost, struct sas_rphy *rphy)
 
 /*
  * Set shost->opt_sectors from the DMA optimal mapping size, but only
- * when dma_opt_mapping_size() is strictly less than dma_max_mapping_size(),
- * indicating a genuine optimization hint from an IOMMU or DMA backend.
+ * when dma_max_opt_mapping_size() is strictly less than
+ * dma_max_mapping_size(), indicating a genuine optimization hint.
  * When the two are equal (e.g. IOMMU disabled / passthrough), no real
  * hint exists, so leave opt_sectors at 0 to avoid bogus optimal_io_size
  * values that break filesystem geometry (e.g. mkfs.xfs stripe alignment).
@@ -234,16 +234,16 @@ static int sas_bsg_initialize(struct Scsi_Host *shost, struct sas_rphy *rphy)
 static void sas_dma_setup_opt_sectors(struct Scsi_Host *shost)
 {
 	struct device *dma_dev = shost->dma_dev;
-	size_t opt = dma_opt_mapping_size(dma_dev);
+	size_t max_opt = dma_max_opt_mapping_size(dma_dev);
 	size_t max = dma_max_mapping_size(dma_dev);
 	unsigned int opt_sectors;
 
-	/* opt >= max means no real hint was provided by the DMA layer */
-	if (opt >= max)
+	/* max_opt >= max means no real hint was provided by the DMA layer */
+	if (max_opt >= max)
 		return;
 
 	/* Clamp to max_sectors to avoid overflow in sector arithmetic */
-	opt_sectors = min_t(unsigned int, opt >> SECTOR_SHIFT,
+	opt_sectors = min_t(unsigned int, max_opt >> SECTOR_SHIFT,
 			    shost->max_sectors);
 
 	/* Guard against zero before rounddown_pow_of_two() */
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 8fae2b7deb20..afaf2c12189b 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -60,7 +60,7 @@ struct dma_map_ops {
 	int (*dma_supported)(struct device *dev, u64 mask);
 	u64 (*get_required_mask)(struct device *dev);
 	size_t (*max_mapping_size)(struct device *dev);
-	size_t (*opt_mapping_size)(void);
+	size_t (*max_opt_mapping_size)(void);
 	unsigned long (*get_merge_boundary)(struct device *dev);
 };
 
@@ -143,7 +143,7 @@ static inline struct page *dma_alloc_contiguous(struct device *dev, size_t size,
 static inline void dma_free_contiguous(struct device *dev, struct page *page,
 		size_t size)
 {
-	__free_pages(page, get_order(size));
+	free_pages_exact(page_address(page), size);
 }
 #endif /* CONFIG_DMA_CMA*/
 
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index a3e880649fa4..efde0e5a58dc 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -207,7 +207,7 @@ int dma_set_coherent_mask(struct device *dev, u64 mask);
 u64 dma_get_required_mask(struct device *dev);
 bool dma_addressing_limited(struct device *dev);
 size_t dma_max_mapping_size(struct device *dev);
-size_t dma_opt_mapping_size(struct device *dev);
+size_t dma_max_opt_mapping_size(struct device *dev);
 unsigned long dma_get_merge_boundary(struct device *dev);
 struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size,
 		enum dma_data_direction dir, gfp_t gfp, unsigned long attrs);
@@ -326,7 +326,7 @@ static inline size_t dma_max_mapping_size(struct device *dev)
 {
 	return 0;
 }
-static inline size_t dma_opt_mapping_size(struct device *dev)
+static inline size_t dma_max_opt_mapping_size(struct device *dev)
 {
 	return 0;
 }
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index b62e2fd53cb4..63a7654c725f 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -325,7 +325,7 @@ void *alloc_pages_exact_noprof(size_t size, gfp_t gfp_mask) __alloc_size(1);
 
 void free_pages_exact(void *virt, size_t size);
 
-__meminit void *alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mask) __alloc_size(2);
+void *alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mask) __alloc_size(2);
 #define alloc_pages_exact_nid(...)					\
 	alloc_hooks(alloc_pages_exact_nid_noprof(__VA_ARGS__))
 
diff --git a/include/linux/iommu-dma.h b/include/linux/iommu-dma.h
index 060f6e23ab3c..fae5d50e4f27 100644
--- a/include/linux/iommu-dma.h
+++ b/include/linux/iommu-dma.h
@@ -39,7 +39,7 @@ int iommu_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs);
 unsigned long iommu_dma_get_merge_boundary(struct device *dev);
-size_t iommu_dma_opt_mapping_size(void);
+size_t iommu_dma_max_opt_mapping_size(void);
 size_t iommu_dma_max_mapping_size(struct device *dev);
 void iommu_dma_free(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t handle, unsigned long attrs);
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 2a421241b980..5f24edf47b68 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -38,7 +38,7 @@ struct scatterlist;
 #define IO_TLB_DEFAULT_SIZE (64UL << 20)
 #endif
 
-unsigned long swiotlb_size_or_default(void);
+unsigned long swiotlb_default_pool_size(void);
 void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
 	int (*remap)(void *tlb, unsigned long nslabs));
 int swiotlb_init_late(size_t size, gfp_t gfp_mask,
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 66093460584e..90937dc7c627 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -451,8 +451,8 @@ struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp)
  *
  * This function releases memory allocated by dma_alloc_contiguous(). As the
  * cma_release returns false when provided pages do not belong to contiguous
- * area and true otherwise, this function then does a fallback __free_pages()
- * upon a false-return.
+ * area and true otherwise, this function then does a fallback
+ * free_pages_exact() upon a false-return.
  */
 void dma_free_contiguous(struct device *dev, struct page *page, size_t size)
 {
@@ -476,7 +476,7 @@ void dma_free_contiguous(struct device *dev, struct page *page, size_t size)
 	}
 
 	/* not in any cma, free from buddy */
-	__free_pages(page, get_order(size));
+	free_pages_exact(page_address(page), size);
 }
 
 /*
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 026d50de340e..36c1f7cbb2ae 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -489,8 +489,10 @@ static int active_cacheline_insert(struct dma_debug_entry *entry,
 	/* If the device is not writing memory then we don't have any
 	 * concerns about the cpu consuming stale data.  This mitigates
 	 * legitimate usages of overlapping mappings.
+	 * MMIO mappings are never CPU-cacheable and do not need tracking either.
 	 */
-	if (entry->direction == DMA_TO_DEVICE)
+	if (entry->direction == DMA_TO_DEVICE ||
+	    entry->attrs & DMA_ATTR_MMIO)
 		return 0;
 
 	spin_lock_irqsave(&radix_lock, flags);
@@ -519,7 +521,8 @@ static void active_cacheline_remove(struct dma_debug_entry *entry)
 	unsigned long flags;
 
 	/* ...mirror the insert case */
-	if (entry->direction == DMA_TO_DEVICE)
+	if (entry->direction == DMA_TO_DEVICE ||
+	    entry->attrs & DMA_ATTR_MMIO)
 		return;
 
 	spin_lock_irqsave(&radix_lock, flags);
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index da665ca22d5c..25e9a86835fd 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -120,6 +120,7 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 	int node = dev_to_node(dev);
 	struct page *page;
 	u64 phys_limit;
+	void *va;
 
 	WARN_ON_ONCE(!PAGE_ALIGNED(size));
 
@@ -133,9 +134,9 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 		dma_free_contiguous(dev, page, size);
 	}
 
-	while ((page = alloc_pages_node(node, gfp, get_order(size)))
-	       && !dma_coherent_ok(dev, page_to_phys(page), size)) {
-		__free_pages(page, get_order(size));
+	while ((va = alloc_pages_exact_nid(node, size, gfp)) &&
+	       !dma_coherent_ok(dev, virt_to_phys(va), size)) {
+		free_pages_exact(va, size);
 
 		if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
 		    phys_limit < DMA_BIT_MASK(64) &&
@@ -146,6 +147,7 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 		else
 			return NULL;
 	}
+	page = va ? virt_to_page(va) : NULL;
 
 	return page;
 }
@@ -179,6 +181,22 @@ static struct page *dma_direct_alloc_from_pool(struct device *dev, size_t size,
 	return page;
 }
 
+/*
+ * Check if the allocation can skip the kernel mapping and return the page
+ * pointer as the cookie.
+ */
+static bool dma_direct_use_no_mapping(struct device *dev, unsigned long attrs)
+{
+	if ((attrs & (DMA_ATTR_NO_KERNEL_MAPPING | __DMA_ATTR_ALLOC_CC_SHARED)) !=
+	    DMA_ATTR_NO_KERNEL_MAPPING)
+		return false;
+	if (is_swiotlb_for_alloc(dev))
+		return false;
+	if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_ALLOC) && !dev_is_dma_coherent(dev))
+		return false;
+	return true;
+}
+
 static void *dma_direct_alloc_no_mapping(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp)
 {
@@ -226,8 +244,7 @@ void *dma_direct_alloc(struct device *dev, size_t size,
 	if (attrs & DMA_ATTR_NO_WARN)
 		gfp |= __GFP_NOWARN;
 
-	if (((attrs & (DMA_ATTR_NO_KERNEL_MAPPING | __DMA_ATTR_ALLOC_CC_SHARED)) ==
-	     DMA_ATTR_NO_KERNEL_MAPPING) && !is_swiotlb_for_alloc(dev))
+	if (dma_direct_use_no_mapping(dev, attrs))
 		return dma_direct_alloc_no_mapping(dev, size, dma_handle, gfp);
 
 	if (!dev_is_dma_coherent(dev)) {
@@ -374,8 +391,7 @@ void dma_direct_free(struct device *dev, size_t size,
 	if (attrs & __DMA_ATTR_ALLOC_CC_SHARED)
 		mark_mem_encrypted = true;
 
-	if (((attrs & (DMA_ATTR_NO_KERNEL_MAPPING | __DMA_ATTR_ALLOC_CC_SHARED)) ==
-	     DMA_ATTR_NO_KERNEL_MAPPING) && !is_swiotlb_for_alloc(dev)) {
+	if (dma_direct_use_no_mapping(dev, attrs)) {
 		/* cpu_addr is a struct page cookie, not a kernel address */
 		dma_free_contiguous(dev, cpu_addr, size);
 		return;
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index bf2651a70b7c..82e701648d60 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -1012,19 +1012,19 @@ size_t dma_max_mapping_size(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(dma_max_mapping_size);
 
-size_t dma_opt_mapping_size(struct device *dev)
+size_t dma_max_opt_mapping_size(struct device *dev)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 	size_t size = SIZE_MAX;
 
 	if (use_dma_iommu(dev))
-		size = iommu_dma_opt_mapping_size();
-	else if (ops && ops->opt_mapping_size)
-		size = ops->opt_mapping_size();
+		size = iommu_dma_max_opt_mapping_size();
+	else if (ops && ops->max_opt_mapping_size)
+		size = ops->max_opt_mapping_size();
 
 	return min(dma_max_mapping_size(dev), size);
 }
-EXPORT_SYMBOL_GPL(dma_opt_mapping_size);
+EXPORT_SYMBOL_GPL(dma_max_opt_mapping_size);
 
 unsigned long dma_get_merge_boundary(struct device *dev)
 {
diff --git a/kernel/dma/ops_helpers.c b/kernel/dma/ops_helpers.c
index 6b5f9208d31c..5cdf3f60cf47 100644
--- a/kernel/dma/ops_helpers.c
+++ b/kernel/dma/ops_helpers.c
@@ -67,10 +67,13 @@ struct page *dma_common_alloc_pages(struct device *dev, size_t size,
 	phys_addr_t phys;
 
 	page = dma_alloc_contiguous(dev, size, gfp);
-	if (!page)
-		page = alloc_pages_node(dev_to_node(dev), gfp, get_order(size));
-	if (!page)
-		return NULL;
+	if (!page) {
+		void *va = alloc_pages_exact_nid(dev_to_node(dev), size, gfp);
+
+		if (!va)
+			return NULL;
+		page = virt_to_page(va);
+	}
 
 	phys = page_to_phys(page);
 	if (use_dma_iommu(dev))
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 5edea93ec635..2c57b49ac7c0 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -100,6 +100,7 @@ static struct io_tlb_mem io_tlb_default_mem;
 
 static unsigned long default_nslabs = IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT;
 static unsigned long default_nareas;
+static bool swiotlb_cmdline_size_set __initdata;
 
 /**
  * struct io_tlb_area - IO TLB memory area descriptor
@@ -117,27 +118,20 @@ struct io_tlb_area {
 	spinlock_t lock;
 };
 
-/*
- * Round up number of slabs to the next power of 2. The last area is going
- * be smaller than the rest if default_nslabs is not power of two.
- * The number of slot in an area should be a multiple of IO_TLB_SEGSIZE,
- * otherwise a segment may span two or more areas. It conflicts with free
- * contiguous slots tracking: free slots are treated contiguous no matter
- * whether they cross an area boundary.
- *
- * Return true if default_nslabs is rounded up.
- */
-static bool round_up_default_nslabs(void)
+/* Return a power-of-two number of slabs that can be split between areas. */
+static unsigned long swiotlb_calc_nslabs(unsigned long size,
+		unsigned long nareas)
 {
-	if (!default_nareas)
-		return false;
+	unsigned long nslabs;
 
-	if (default_nslabs < IO_TLB_SEGSIZE * default_nareas)
-		default_nslabs = IO_TLB_SEGSIZE * default_nareas;
-	else if (is_power_of_2(default_nslabs))
-		return false;
-	default_nslabs = roundup_pow_of_two(default_nslabs);
-	return true;
+	nslabs = ALIGN(DIV_ROUND_UP(size, IO_TLB_SIZE), IO_TLB_SEGSIZE);
+	if (nareas && nslabs < IO_TLB_SEGSIZE * nareas)
+		nslabs = IO_TLB_SEGSIZE * nareas;
+
+	if (!is_power_of_2(nslabs))
+		nslabs = roundup_pow_of_two(nslabs);
+
+	return nslabs;
 }
 
 /**
@@ -150,6 +144,8 @@ static bool round_up_default_nslabs(void)
  */
 static void swiotlb_adjust_nareas(unsigned int nareas)
 {
+	unsigned long nslabs;
+
 	if (!nareas)
 		nareas = 1;
 	else if (!is_power_of_2(nareas))
@@ -158,9 +154,12 @@ static void swiotlb_adjust_nareas(unsigned int nareas)
 	default_nareas = nareas;
 
 	pr_info("area num %d.\n", nareas);
-	if (round_up_default_nslabs())
+	nslabs = swiotlb_calc_nslabs(default_nslabs << IO_TLB_SHIFT, nareas);
+	if (nslabs != default_nslabs) {
+		default_nslabs = nslabs;
 		pr_info("SWIOTLB bounce buffer size roundup to %luMB",
 			(default_nslabs << IO_TLB_SHIFT) >> 20);
+	}
 }
 
 /**
@@ -255,6 +254,7 @@ setup_io_tlb_npages(char *str)
 		/* avoid tail segment of size < IO_TLB_SEGSIZE */
 		default_nslabs =
 			ALIGN(simple_strtoul(str, &str, 0), IO_TLB_SEGSIZE);
+		swiotlb_cmdline_size_set = true;
 	}
 	if (*str == ',')
 		++str;
@@ -285,7 +285,7 @@ setup_io_tlb_npages(char *str)
 }
 early_param("swiotlb", setup_io_tlb_npages);
 
-unsigned long swiotlb_size_or_default(void)
+unsigned long swiotlb_default_pool_size(void)
 {
 	return default_nslabs << IO_TLB_SHIFT;
 }
@@ -297,13 +297,11 @@ void __init swiotlb_adjust_size(unsigned long size)
 	 * architectures such as those supporting memory encryption to
 	 * adjust/expand SWIOTLB size for their use.
 	 */
-	if (default_nslabs != IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT)
+	if (swiotlb_cmdline_size_set)
 		return;
 
-	size = ALIGN(size, IO_TLB_SIZE);
-	default_nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
-	if (round_up_default_nslabs())
-		size = default_nslabs << IO_TLB_SHIFT;
+	default_nslabs = swiotlb_calc_nslabs(size, default_nareas);
+	size = default_nslabs << IO_TLB_SHIFT;
 	pr_info("SWIOTLB bounce buffer size adjusted to %luMB", size >> 20);
 }
 
@@ -2083,8 +2081,8 @@ static int __init rmem_swiotlb_setup(unsigned long node,
 	    of_get_flat_dt_prop(node, "no-map", NULL))
 		return -EINVAL;
 
-	pr_info("Reserved memory: created restricted DMA pool at %pa, size %ld MiB\n",
-		&rmem->base, (unsigned long)rmem->size / SZ_1M);
+	pr_info("Reserved memory: created restricted DMA pool at %pa, size %llu KiB\n",
+		&rmem->base, (unsigned long long)(rmem->size / SZ_1K));
 	return 0;
 }
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ff7b9acf0144..3322f9e75616 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5648,7 +5648,7 @@ EXPORT_SYMBOL(alloc_pages_exact_noprof);
  *
  * Return: pointer to the allocated area or %NULL in case of error.
  */
-void * __meminit alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mask)
+void *alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mask)
 {
 	unsigned int order = get_order(size);
 	struct page *p;
diff --git a/tools/dma/Makefile b/tools/dma/Makefile
index e4abf37bf020..20ae7f09cd20 100644
--- a/tools/dma/Makefile
+++ b/tools/dma/Makefile
@@ -7,7 +7,13 @@ bindir ?= /usr/bin
 # isn't set and when invoked from selftests build, where srctree
 # is set to ".". building_out_of_srctree is undefined for in srctree
 # builds
+ifeq ($(srctree),)
+update_srctree := 1
+endif
 ifndef building_out_of_srctree
+update_srctree := 1
+endif
+ifeq ($(update_srctree),1)
 srctree := $(patsubst %/,%,$(dir $(CURDIR)))
 srctree := $(patsubst %/,%,$(dir $(srctree)))
 endif
@@ -38,8 +44,8 @@ prepare: $(OUTPUT)include/linux/map_benchmark.h
 FORCE:
 
 DMA_MAP_BENCHMARK = dma_map_benchmark
-$(DMA_MAP_BENCHMARK): prepare FORCE
-	$(CC) $(CFLAGS) $(DMA_MAP_BENCHMARK).c -o $(DMA_MAP_BENCHMARK)
+$(OUTPUT)$(DMA_MAP_BENCHMARK): prepare FORCE
+	$(CC) $(CFLAGS) $(DMA_MAP_BENCHMARK).c -o $@
 
 clean:
 	rm -f $(ALL_PROGRAMS)