From 9f683dfe8099639f9ac859287744a9ed1c3698a0 Mon Sep 17 00:00:00 2001
From: Petr Tesarik <ptesarik@suse.com>
Date: Thu, 10 Jul 2025 10:38:29 +0200
Subject: dma-direct: clean up the logic in __dma_direct_alloc_pages()

Convert a goto-based loop to a while() loop. To allow the simplification,
return early when allocation from CMA is successful. As a bonus, this early
return avoids a repeated dma_coherent_ok() check.

No functional change.

Signed-off-by: Petr Tesarik <ptesarik@suse.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20250710083829.1853466-1-ptesarik@suse.com
---
 kernel/dma/direct.c | 31 +++++++++++++------------------
 1 file changed, 13 insertions(+), 18 deletions(-)

(limited to 'kernel/dma')

diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 24c359d9c879..302e89580972 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -120,7 +120,7 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 		gfp_t gfp, bool allow_highmem)
 {
 	int node = dev_to_node(dev);
-	struct page *page = NULL;
+	struct page *page;
 	u64 phys_limit;
 
 	WARN_ON_ONCE(!PAGE_ALIGNED(size));
@@ -131,30 +131,25 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 	gfp |= dma_direct_optimal_gfp_mask(dev, &phys_limit);
 	page = dma_alloc_contiguous(dev, size, gfp);
 	if (page) {
-		if (!dma_coherent_ok(dev, page_to_phys(page), size) ||
-		    (!allow_highmem && PageHighMem(page))) {
-			dma_free_contiguous(dev, page, size);
-			page = NULL;
-		}
+		if (dma_coherent_ok(dev, page_to_phys(page), size) &&
+		    (allow_highmem || !PageHighMem(page)))
+			return page;
+
+		dma_free_contiguous(dev, page, size);
 	}
-again:
-	if (!page)
-		page = alloc_pages_node(node, gfp, get_order(size));
-	if (page && !dma_coherent_ok(dev, page_to_phys(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));
-		page = NULL;
 
 		if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
 		    phys_limit < DMA_BIT_MASK(64) &&
-		    !(gfp & (GFP_DMA32 | GFP_DMA))) {
+		    !(gfp & (GFP_DMA32 | GFP_DMA)))
 			gfp |= GFP_DMA32;
-			goto again;
-		}
-
-		if (IS_ENABLED(CONFIG_ZONE_DMA) && !(gfp & GFP_DMA)) {
+		else if (IS_ENABLED(CONFIG_ZONE_DMA) && !(gfp & GFP_DMA))
 			gfp = (gfp & ~GFP_DMA32) | GFP_DMA;
-			goto again;
-		}
+		else
+			return NULL;
 	}
 
 	return page;
-- 
cgit v1.2.3


From 110aa2c74dbd9de862afc8546d1b9be4c86f9eb0 Mon Sep 17 00:00:00 2001
From: Qianfeng Rong <rongqianfeng@vivo.com>
Date: Tue, 5 Aug 2025 10:32:22 +0800
Subject: swiotlb: Remove redundant __GFP_NOWARN

Commit 16f5dfbc851b ("gfp: include __GFP_NOWARN in GFP_NOWAIT")
made GFP_NOWAIT implicitly include __GFP_NOWARN.

Therefore, explicit __GFP_NOWARN combined with GFP_NOWAIT
(e.g., `GFP_NOWAIT | __GFP_NOWARN`) is now redundant. Let's clean
up these redundant flags across subsystems.

No functional changes.

Signed-off-by: Qianfeng Rong <rongqianfeng@vivo.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20250805023222.332920-1-rongqianfeng@vivo.com
---
 kernel/dma/swiotlb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel/dma')

diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index abcf3fa63a56..0d37da3d95b6 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -1209,7 +1209,7 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
 	nslabs = nr_slots(alloc_size);
 	phys_limit = min_not_zero(*dev->dma_mask, dev->bus_dma_limit);
 	pool = swiotlb_alloc_pool(dev, nslabs, nslabs, 1, phys_limit,
-				  GFP_NOWAIT | __GFP_NOWARN);
+				  GFP_NOWAIT);
 	if (!pool)
 		return -1;
 
-- 
cgit v1.2.3


From 2c223f7239f376a90d71903ec474ba887cf21d94 Mon Sep 17 00:00:00 2001
From: Oreoluwa Babatunde <oreoluwa.babatunde@oss.qualcomm.com>
Date: Wed, 6 Aug 2025 10:24:21 -0700
Subject: of: reserved_mem: Restructure call site for
 dma_contiguous_early_fixup()

Restructure the call site for dma_contiguous_early_fixup() to
where the reserved_mem nodes are being parsed from the DT so that
dma_mmu_remap[] is populated before dma_contiguous_remap() is called.

Fixes: 8a6e02d0c00e ("of: reserved_mem: Restructure how the reserved memory regions are processed")
Signed-off-by: Oreoluwa Babatunde <oreoluwa.babatunde@oss.qualcomm.com>
Tested-by: William Zhang <william.zhang@broadcom.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20250806172421.2748302-1-oreoluwa.babatunde@oss.qualcomm.com
---
 drivers/of/of_reserved_mem.c | 16 ++++++++++++----
 include/linux/dma-map-ops.h  |  3 +++
 kernel/dma/contiguous.c      |  2 --
 3 files changed, 15 insertions(+), 6 deletions(-)

(limited to 'kernel/dma')

diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index 77016c0cc296..7350b23cb734 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -25,6 +25,7 @@
 #include <linux/memblock.h>
 #include <linux/kmemleak.h>
 #include <linux/cma.h>
+#include <linux/dma-map-ops.h>
 
 #include "of_private.h"
 
@@ -175,13 +176,17 @@ static int __init __reserved_mem_reserve_reg(unsigned long node,
 		base = dt_mem_next_cell(dt_root_addr_cells, &prop);
 		size = dt_mem_next_cell(dt_root_size_cells, &prop);
 
-		if (size &&
-		    early_init_dt_reserve_memory(base, size, nomap) == 0)
+		if (size && early_init_dt_reserve_memory(base, size, nomap) == 0) {
+			/* Architecture specific contiguous memory fixup. */
+			if (of_flat_dt_is_compatible(node, "shared-dma-pool") &&
+			    of_get_flat_dt_prop(node, "reusable", NULL))
+				dma_contiguous_early_fixup(base, size);
 			pr_debug("Reserved memory: reserved region for node '%s': base %pa, size %lu MiB\n",
 				uname, &base, (unsigned long)(size / SZ_1M));
-		else
+		} else {
 			pr_err("Reserved memory: failed to reserve memory for node '%s': base %pa, size %lu MiB\n",
 			       uname, &base, (unsigned long)(size / SZ_1M));
+		}
 
 		len -= t_len;
 	}
@@ -472,7 +477,10 @@ static int __init __reserved_mem_alloc_size(unsigned long node, const char *unam
 		       uname, (unsigned long)(size / SZ_1M));
 		return -ENOMEM;
 	}
-
+	/* Architecture specific contiguous memory fixup. */
+	if (of_flat_dt_is_compatible(node, "shared-dma-pool") &&
+	    of_get_flat_dt_prop(node, "reusable", NULL))
+		dma_contiguous_early_fixup(base, size);
 	/* Save region in the reserved_mem array */
 	fdt_reserved_mem_save_node(node, uname, base, size);
 	return 0;
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index f48e5fb88bd5..332b80c42b6f 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -153,6 +153,9 @@ static inline void dma_free_contiguous(struct device *dev, struct page *page,
 {
 	__free_pages(page, get_order(size));
 }
+static inline void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size)
+{
+}
 #endif /* CONFIG_DMA_CMA*/
 
 #ifdef CONFIG_DMA_DECLARE_COHERENT
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 67af8a55185d..d9b9dcba6ff7 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -483,8 +483,6 @@ static int __init rmem_cma_setup(struct reserved_mem *rmem)
 		pr_err("Reserved memory: unable to setup CMA region\n");
 		return err;
 	}
-	/* Architecture specific contiguous memory fixup. */
-	dma_contiguous_early_fixup(rmem->base, rmem->size);
 
 	if (default_cma)
 		dma_contiguous_default_area = cma;
-- 
cgit v1.2.3


From 89a2d212bdb4bc29bed8e7077abe054b801137ea Mon Sep 17 00:00:00 2001
From: Shanker Donthineni <sdonthineni@nvidia.com>
Date: Mon, 11 Aug 2025 13:17:59 -0500
Subject: dma/pool: Ensure DMA_DIRECT_REMAP allocations are decrypted

When CONFIG_DMA_DIRECT_REMAP is enabled, atomic pool pages are
remapped via dma_common_contiguous_remap() using the supplied
pgprot. Currently, the mapping uses
pgprot_dmacoherent(PAGE_KERNEL), which leaves the memory encrypted
on systems with memory encryption enabled (e.g., ARM CCA Realms).

This can cause the DMA layer to fail or crash when accessing the
memory, as the underlying physical pages are not configured as
expected.

Fix this by requesting a decrypted mapping in the vmap() call:
pgprot_decrypted(pgprot_dmacoherent(PAGE_KERNEL))

This ensures that atomic pool memory is consistently mapped
unencrypted.

Cc: stable@vger.kernel.org
Signed-off-by: Shanker Donthineni <sdonthineni@nvidia.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20250811181759.998805-1-sdonthineni@nvidia.com
---
 kernel/dma/pool.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'kernel/dma')

diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index 7b04f7575796..ee45dee33d49 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -102,8 +102,8 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
 
 #ifdef CONFIG_DMA_DIRECT_REMAP
 	addr = dma_common_contiguous_remap(page, pool_size,
-					   pgprot_dmacoherent(PAGE_KERNEL),
-					   __builtin_return_address(0));
+			pgprot_decrypted(pgprot_dmacoherent(PAGE_KERNEL)),
+			__builtin_return_address(0));
 	if (!addr)
 		goto free_page;
 #else
-- 
cgit v1.2.3


From 7e2368a21741e2db542330b32aa6fdd8908e7cff Mon Sep 17 00:00:00 2001
From: Baochen Qiang <baochen.qiang@oss.qualcomm.com>
Date: Thu, 28 Aug 2025 16:17:33 +0800
Subject: dma-debug: don't enforce dma mapping check on noncoherent allocations

As discussed in [1], there is no need to enforce dma mapping check on
noncoherent allocations, a simple test on the returned CPU address is
good enough.

Add a new pair of debug helpers and use them for noncoherent alloc/free
to fix this issue.

Fixes: efa70f2fdc84 ("dma-mapping: add a new dma_alloc_pages API")
Link: https://lore.kernel.org/all/ff6c1fe6-820f-4e58-8395-df06aa91706c@oss.qualcomm.com # 1
Signed-off-by: Baochen Qiang <baochen.qiang@oss.qualcomm.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20250828-dma-debug-fix-noncoherent-dma-check-v1-1-76e9be0dd7fc@oss.qualcomm.com
---
 kernel/dma/debug.c   | 48 +++++++++++++++++++++++++++++++++++++++++++++++-
 kernel/dma/debug.h   | 20 ++++++++++++++++++++
 kernel/dma/mapping.c |  4 ++--
 3 files changed, 69 insertions(+), 3 deletions(-)

(limited to 'kernel/dma')

diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index e43c6de2bce4..b82399437db0 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -39,6 +39,7 @@ enum {
 	dma_debug_sg,
 	dma_debug_coherent,
 	dma_debug_resource,
+	dma_debug_noncoherent,
 };
 
 enum map_err_types {
@@ -141,6 +142,7 @@ static const char *type2name[] = {
 	[dma_debug_sg] = "scatter-gather",
 	[dma_debug_coherent] = "coherent",
 	[dma_debug_resource] = "resource",
+	[dma_debug_noncoherent] = "noncoherent",
 };
 
 static const char *dir2name[] = {
@@ -993,7 +995,8 @@ static void check_unmap(struct dma_debug_entry *ref)
 			   "[mapped as %s] [unmapped as %s]\n",
 			   ref->dev_addr, ref->size,
 			   type2name[entry->type], type2name[ref->type]);
-	} else if (entry->type == dma_debug_coherent &&
+	} else if ((entry->type == dma_debug_coherent ||
+		    entry->type == dma_debug_noncoherent) &&
 		   ref->paddr != entry->paddr) {
 		err_printk(ref->dev, entry, "device driver frees "
 			   "DMA memory with different CPU address "
@@ -1581,6 +1584,49 @@ void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 	}
 }
 
+void debug_dma_alloc_pages(struct device *dev, struct page *page,
+			   size_t size, int direction,
+			   dma_addr_t dma_addr,
+			   unsigned long attrs)
+{
+	struct dma_debug_entry *entry;
+
+	if (unlikely(dma_debug_disabled()))
+		return;
+
+	entry = dma_entry_alloc();
+	if (!entry)
+		return;
+
+	entry->type      = dma_debug_noncoherent;
+	entry->dev       = dev;
+	entry->paddr	 = page_to_phys(page);
+	entry->size      = size;
+	entry->dev_addr  = dma_addr;
+	entry->direction = direction;
+
+	add_dma_entry(entry, attrs);
+}
+
+void debug_dma_free_pages(struct device *dev, struct page *page,
+			  size_t size, int direction,
+			  dma_addr_t dma_addr)
+{
+	struct dma_debug_entry ref = {
+		.type           = dma_debug_noncoherent,
+		.dev            = dev,
+		.paddr		= page_to_phys(page),
+		.dev_addr       = dma_addr,
+		.size           = size,
+		.direction      = direction,
+	};
+
+	if (unlikely(dma_debug_disabled()))
+		return;
+
+	check_unmap(&ref);
+}
+
 static int __init dma_debug_driver_setup(char *str)
 {
 	int i;
diff --git a/kernel/dma/debug.h b/kernel/dma/debug.h
index f525197d3cae..48757ca13f31 100644
--- a/kernel/dma/debug.h
+++ b/kernel/dma/debug.h
@@ -54,6 +54,13 @@ extern void debug_dma_sync_sg_for_cpu(struct device *dev,
 extern void debug_dma_sync_sg_for_device(struct device *dev,
 					 struct scatterlist *sg,
 					 int nelems, int direction);
+extern void debug_dma_alloc_pages(struct device *dev, struct page *page,
+				  size_t size, int direction,
+				  dma_addr_t dma_addr,
+				  unsigned long attrs);
+extern void debug_dma_free_pages(struct device *dev, struct page *page,
+				 size_t size, int direction,
+				 dma_addr_t dma_addr);
 #else /* CONFIG_DMA_API_DEBUG */
 static inline void debug_dma_map_page(struct device *dev, struct page *page,
 				      size_t offset, size_t size,
@@ -126,5 +133,18 @@ static inline void debug_dma_sync_sg_for_device(struct device *dev,
 						int nelems, int direction)
 {
 }
+
+static inline void debug_dma_alloc_pages(struct device *dev, struct page *page,
+					 size_t size, int direction,
+					 dma_addr_t dma_addr,
+					 unsigned long attrs)
+{
+}
+
+static inline void debug_dma_free_pages(struct device *dev, struct page *page,
+					size_t size, int direction,
+					dma_addr_t dma_addr)
+{
+}
 #endif /* CONFIG_DMA_API_DEBUG */
 #endif /* _KERNEL_DMA_DEBUG_H */
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 107e4a4d251d..56de28a3b179 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -712,7 +712,7 @@ struct page *dma_alloc_pages(struct device *dev, size_t size,
 	if (page) {
 		trace_dma_alloc_pages(dev, page_to_virt(page), *dma_handle,
 				      size, dir, gfp, 0);
-		debug_dma_map_page(dev, page, 0, size, dir, *dma_handle, 0);
+		debug_dma_alloc_pages(dev, page, size, dir, *dma_handle, 0);
 	} else {
 		trace_dma_alloc_pages(dev, NULL, 0, size, dir, gfp, 0);
 	}
@@ -738,7 +738,7 @@ void dma_free_pages(struct device *dev, size_t size, struct page *page,
 		dma_addr_t dma_handle, enum dma_data_direction dir)
 {
 	trace_dma_free_pages(dev, page_to_virt(page), dma_handle, size, dir, 0);
-	debug_dma_unmap_page(dev, dma_handle, size, dir);
+	debug_dma_free_pages(dev, page, size, dir, dma_handle);
 	__dma_free_pages(dev, size, page, dma_handle, dir);
 }
 EXPORT_SYMBOL_GPL(dma_free_pages);
-- 
cgit v1.2.3


From e9e81d86fee63c6d5757841ab557019ddf73786f Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Tue, 9 Sep 2025 16:27:31 +0300
Subject: dma-debug: refactor to use physical addresses for page mapping

Convert the DMA debug infrastructure from page-based to physical address-based
mapping as a preparation to rely on physical address for DMA mapping routines.

The refactoring renames debug_dma_map_page() to debug_dma_map_phys() and
changes its signature to accept a phys_addr_t parameter instead of struct page
and offset. Similarly, debug_dma_unmap_page() becomes debug_dma_unmap_phys().
A new dma_debug_phy type is introduced to distinguish physical address mappings
from other debug entry types. All callers throughout the codebase are updated
to pass physical addresses directly, eliminating the need for page-to-physical
conversion in the debug layer.

This refactoring eliminates the need to convert between page pointers and
physical addresses in the debug layer, making the code more efficient and
consistent with the DMA mapping API's physical address focus.

Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
[mszyprow: added a fixup]
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/56d1a6769b68dfcbf8b26a75a7329aeb8e3c3b6a.1757423202.git.leonro@nvidia.com
Link: https://lore.kernel.org/all/20250910052618.GH341237@unreal/
---
 Documentation/core-api/dma-api.rst |  4 ++--
 include/linux/page-flags.h         |  1 +
 kernel/dma/debug.c                 | 39 +++++++++++++++++++-------------------
 kernel/dma/debug.h                 | 16 +++++++---------
 kernel/dma/mapping.c               | 10 +++++-----
 5 files changed, 35 insertions(+), 35 deletions(-)

(limited to 'kernel/dma')

diff --git a/Documentation/core-api/dma-api.rst b/Documentation/core-api/dma-api.rst
index 3087bea715ed..ca75b3541679 100644
--- a/Documentation/core-api/dma-api.rst
+++ b/Documentation/core-api/dma-api.rst
@@ -761,7 +761,7 @@ example warning message may look like this::
 	[<ffffffff80235177>] find_busiest_group+0x207/0x8a0
 	[<ffffffff8064784f>] _spin_lock_irqsave+0x1f/0x50
 	[<ffffffff803c7ea3>] check_unmap+0x203/0x490
-	[<ffffffff803c8259>] debug_dma_unmap_page+0x49/0x50
+	[<ffffffff803c8259>] debug_dma_unmap_phys+0x49/0x50
 	[<ffffffff80485f26>] nv_tx_done_optimized+0xc6/0x2c0
 	[<ffffffff80486c13>] nv_nic_irq_optimized+0x73/0x2b0
 	[<ffffffff8026df84>] handle_IRQ_event+0x34/0x70
@@ -855,7 +855,7 @@ that a driver may be leaking mappings.
 dma-debug interface debug_dma_mapping_error() to debug drivers that fail
 to check DMA mapping errors on addresses returned by dma_map_single() and
 dma_map_page() interfaces. This interface clears a flag set by
-debug_dma_map_page() to indicate that dma_mapping_error() has been called by
+debug_dma_map_phys() to indicate that dma_mapping_error() has been called by
 the driver. When driver does unmap, debug_dma_unmap() checks the flag and if
 this flag is still set, prints warning message that includes call trace that
 leads up to the unmap. This interface can be called from dma_mapping_error()
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 8d3fa3a91ce4..2a1f34617802 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -618,6 +618,7 @@ FOLIO_FLAG(dropbehind, FOLIO_HEAD_PAGE)
 #else
 PAGEFLAG_FALSE(HighMem, highmem)
 #endif
+#define PhysHighMem(__p) (PageHighMem(phys_to_page(__p)))
 
 /* Does kmap_local_folio() only allow access to one page of the folio? */
 #ifdef CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index b82399437db0..b275db9ca6a0 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -40,6 +40,7 @@ enum {
 	dma_debug_coherent,
 	dma_debug_resource,
 	dma_debug_noncoherent,
+	dma_debug_phy,
 };
 
 enum map_err_types {
@@ -143,6 +144,7 @@ static const char *type2name[] = {
 	[dma_debug_coherent] = "coherent",
 	[dma_debug_resource] = "resource",
 	[dma_debug_noncoherent] = "noncoherent",
+	[dma_debug_phy] = "phy",
 };
 
 static const char *dir2name[] = {
@@ -1054,17 +1056,16 @@ static void check_unmap(struct dma_debug_entry *ref)
 	dma_entry_free(entry);
 }
 
-static void check_for_stack(struct device *dev,
-			    struct page *page, size_t offset)
+static void check_for_stack(struct device *dev, phys_addr_t phys)
 {
 	void *addr;
 	struct vm_struct *stack_vm_area = task_stack_vm_area(current);
 
 	if (!stack_vm_area) {
 		/* Stack is direct-mapped. */
-		if (PageHighMem(page))
+		if (PhysHighMem(phys))
 			return;
-		addr = page_address(page) + offset;
+		addr = phys_to_virt(phys);
 		if (object_is_on_stack(addr))
 			err_printk(dev, NULL, "device driver maps memory from stack [addr=%p]\n", addr);
 	} else {
@@ -1072,10 +1073,12 @@ static void check_for_stack(struct device *dev,
 		int i;
 
 		for (i = 0; i < stack_vm_area->nr_pages; i++) {
-			if (page != stack_vm_area->pages[i])
+			if (__phys_to_pfn(phys) !=
+			    page_to_pfn(stack_vm_area->pages[i]))
 				continue;
 
-			addr = (u8 *)current->stack + i * PAGE_SIZE + offset;
+			addr = (u8 *)current->stack + i * PAGE_SIZE +
+			       (phys % PAGE_SIZE);
 			err_printk(dev, NULL, "device driver maps memory from stack [probable addr=%p]\n", addr);
 			break;
 		}
@@ -1204,9 +1207,8 @@ void debug_dma_map_single(struct device *dev, const void *addr,
 }
 EXPORT_SYMBOL(debug_dma_map_single);
 
-void debug_dma_map_page(struct device *dev, struct page *page, size_t offset,
-			size_t size, int direction, dma_addr_t dma_addr,
-			unsigned long attrs)
+void debug_dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
+		int direction, dma_addr_t dma_addr, unsigned long attrs)
 {
 	struct dma_debug_entry *entry;
 
@@ -1221,19 +1223,18 @@ void debug_dma_map_page(struct device *dev, struct page *page, size_t offset,
 		return;
 
 	entry->dev       = dev;
-	entry->type      = dma_debug_single;
-	entry->paddr	 = page_to_phys(page) + offset;
+	entry->type      = dma_debug_phy;
+	entry->paddr	 = phys;
 	entry->dev_addr  = dma_addr;
 	entry->size      = size;
 	entry->direction = direction;
 	entry->map_err_type = MAP_ERR_NOT_CHECKED;
 
-	check_for_stack(dev, page, offset);
+	if (!(attrs & DMA_ATTR_MMIO)) {
+		check_for_stack(dev, phys);
 
-	if (!PageHighMem(page)) {
-		void *addr = page_address(page) + offset;
-
-		check_for_illegal_area(dev, addr, size);
+		if (!PhysHighMem(phys))
+			check_for_illegal_area(dev, phys_to_virt(phys), size);
 	}
 
 	add_dma_entry(entry, attrs);
@@ -1277,11 +1278,11 @@ void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 }
 EXPORT_SYMBOL(debug_dma_mapping_error);
 
-void debug_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
+void debug_dma_unmap_phys(struct device *dev, dma_addr_t dma_addr,
 			  size_t size, int direction)
 {
 	struct dma_debug_entry ref = {
-		.type           = dma_debug_single,
+		.type           = dma_debug_phy,
 		.dev            = dev,
 		.dev_addr       = dma_addr,
 		.size           = size,
@@ -1305,7 +1306,7 @@ void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
 		return;
 
 	for_each_sg(sg, s, nents, i) {
-		check_for_stack(dev, sg_page(s), s->offset);
+		check_for_stack(dev, sg_phys(s));
 		if (!PageHighMem(sg_page(s)))
 			check_for_illegal_area(dev, sg_virt(s), s->length);
 	}
diff --git a/kernel/dma/debug.h b/kernel/dma/debug.h
index 48757ca13f31..bedae973e725 100644
--- a/kernel/dma/debug.h
+++ b/kernel/dma/debug.h
@@ -9,12 +9,11 @@
 #define _KERNEL_DMA_DEBUG_H
 
 #ifdef CONFIG_DMA_API_DEBUG
-extern void debug_dma_map_page(struct device *dev, struct page *page,
-			       size_t offset, size_t size,
-			       int direction, dma_addr_t dma_addr,
+extern void debug_dma_map_phys(struct device *dev, phys_addr_t phys,
+			       size_t size, int direction, dma_addr_t dma_addr,
 			       unsigned long attrs);
 
-extern void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
+extern void debug_dma_unmap_phys(struct device *dev, dma_addr_t addr,
 				 size_t size, int direction);
 
 extern void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
@@ -62,14 +61,13 @@ extern void debug_dma_free_pages(struct device *dev, struct page *page,
 				 size_t size, int direction,
 				 dma_addr_t dma_addr);
 #else /* CONFIG_DMA_API_DEBUG */
-static inline void debug_dma_map_page(struct device *dev, struct page *page,
-				      size_t offset, size_t size,
-				      int direction, dma_addr_t dma_addr,
-				      unsigned long attrs)
+static inline void debug_dma_map_phys(struct device *dev, phys_addr_t phys,
+				      size_t size, int direction,
+				      dma_addr_t dma_addr, unsigned long attrs)
 {
 }
 
-static inline void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
+static inline void debug_dma_unmap_phys(struct device *dev, dma_addr_t addr,
 					size_t size, int direction)
 {
 }
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 56de28a3b179..0b7e16c69bf1 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -157,6 +157,7 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
 		unsigned long attrs)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
+	phys_addr_t phys = page_to_phys(page) + offset;
 	dma_addr_t addr;
 
 	BUG_ON(!valid_dma_direction(dir));
@@ -165,16 +166,15 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
 		return DMA_MAPPING_ERROR;
 
 	if (dma_map_direct(dev, ops) ||
-	    arch_dma_map_page_direct(dev, page_to_phys(page) + offset + size))
+	    arch_dma_map_page_direct(dev, phys + size))
 		addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
 	else if (use_dma_iommu(dev))
 		addr = iommu_dma_map_page(dev, page, offset, size, dir, attrs);
 	else
 		addr = ops->map_page(dev, page, offset, size, dir, attrs);
 	kmsan_handle_dma(page, offset, size, dir);
-	trace_dma_map_page(dev, page_to_phys(page) + offset, addr, size, dir,
-			   attrs);
-	debug_dma_map_page(dev, page, offset, size, dir, addr, attrs);
+	trace_dma_map_page(dev, phys, addr, size, dir, attrs);
+	debug_dma_map_phys(dev, phys, size, dir, addr, attrs);
 
 	return addr;
 }
@@ -194,7 +194,7 @@ void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size,
 	else
 		ops->unmap_page(dev, addr, size, dir, attrs);
 	trace_dma_unmap_page(dev, addr, size, dir, attrs);
-	debug_dma_unmap_page(dev, addr, size, dir);
+	debug_dma_unmap_phys(dev, addr, size, dir);
 }
 EXPORT_SYMBOL(dma_unmap_page_attrs);
 
-- 
cgit v1.2.3


From 76bb7c49f50ce7687f98eb35e78798584652dd0e Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Tue, 9 Sep 2025 16:27:32 +0300
Subject: dma-mapping: rename trace_dma_*map_page to trace_dma_*map_phys

As a preparation for following map_page -> map_phys API conversion,
let's rename trace_dma_*map_page() to be trace_dma_*map_phys().

Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/c0c02d7d8bd4a148072d283353ba227516a76682.1757423202.git.leonro@nvidia.com
---
 include/trace/events/dma.h | 4 ++--
 kernel/dma/mapping.c       | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'kernel/dma')

diff --git a/include/trace/events/dma.h b/include/trace/events/dma.h
index ee90d6f1dcf3..84416c7d6bfa 100644
--- a/include/trace/events/dma.h
+++ b/include/trace/events/dma.h
@@ -72,7 +72,7 @@ DEFINE_EVENT(dma_map, name, \
 		 size_t size, enum dma_data_direction dir, unsigned long attrs), \
 	TP_ARGS(dev, phys_addr, dma_addr, size, dir, attrs))
 
-DEFINE_MAP_EVENT(dma_map_page);
+DEFINE_MAP_EVENT(dma_map_phys);
 DEFINE_MAP_EVENT(dma_map_resource);
 
 DECLARE_EVENT_CLASS(dma_unmap,
@@ -110,7 +110,7 @@ DEFINE_EVENT(dma_unmap, name, \
 		 enum dma_data_direction dir, unsigned long attrs), \
 	TP_ARGS(dev, addr, size, dir, attrs))
 
-DEFINE_UNMAP_EVENT(dma_unmap_page);
+DEFINE_UNMAP_EVENT(dma_unmap_phys);
 DEFINE_UNMAP_EVENT(dma_unmap_resource);
 
 DECLARE_EVENT_CLASS(dma_alloc_class,
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 0b7e16c69bf1..bd3bb6d59d72 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -173,7 +173,7 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
 	else
 		addr = ops->map_page(dev, page, offset, size, dir, attrs);
 	kmsan_handle_dma(page, offset, size, dir);
-	trace_dma_map_page(dev, phys, addr, size, dir, attrs);
+	trace_dma_map_phys(dev, phys, addr, size, dir, attrs);
 	debug_dma_map_phys(dev, phys, size, dir, addr, attrs);
 
 	return addr;
@@ -193,7 +193,7 @@ void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size,
 		iommu_dma_unmap_page(dev, addr, size, dir, attrs);
 	else
 		ops->unmap_page(dev, addr, size, dir, attrs);
-	trace_dma_unmap_page(dev, addr, size, dir, attrs);
+	trace_dma_unmap_phys(dev, addr, size, dir, attrs);
 	debug_dma_unmap_phys(dev, addr, size, dir);
 }
 EXPORT_SYMBOL(dma_unmap_page_attrs);
-- 
cgit v1.2.3


From 513559f73700966ded094b090c3ecc6dff877ef9 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Tue, 9 Sep 2025 16:27:33 +0300
Subject: iommu/dma: rename iommu_dma_*map_page to iommu_dma_*map_phys

Rename the IOMMU DMA mapping functions to better reflect their actual
calling convention. The functions iommu_dma_map_page() and
iommu_dma_unmap_page() are renamed to iommu_dma_map_phys() and
iommu_dma_unmap_phys() respectively, as they already operate on physical
addresses rather than page structures.

The calling convention changes from accepting (struct page *page,
unsigned long offset) to (phys_addr_t phys), which eliminates the need
for page-to-physical address conversion within the functions. This
renaming prepares for the broader DMA API conversion from page-based
to physical address-based mapping throughout the kernel.

All callers are updated to pass physical addresses directly, including
dma_map_page_attrs(), scatterlist mapping functions, and DMA page
allocation helpers. The change simplifies the code by removing the
page_to_phys() + offset calculation that was previously done inside
the IOMMU functions.

Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/ed172f95f8f57782beae04f782813366894e98df.1757423202.git.leonro@nvidia.com
---
 drivers/iommu/dma-iommu.c | 14 ++++++--------
 include/linux/iommu-dma.h |  7 +++----
 kernel/dma/mapping.c      |  4 ++--
 kernel/dma/ops_helpers.c  |  6 +++---
 4 files changed, 14 insertions(+), 17 deletions(-)

(limited to 'kernel/dma')

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index e1185ba73e23..aea119f32f96 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1195,11 +1195,9 @@ static inline size_t iova_unaligned(struct iova_domain *iovad, phys_addr_t phys,
 	return iova_offset(iovad, phys | size);
 }
 
-dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
-	      unsigned long offset, size_t size, enum dma_data_direction dir,
-	      unsigned long attrs)
+dma_addr_t iommu_dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
 {
-	phys_addr_t phys = page_to_phys(page) + offset;
 	bool coherent = dev_is_dma_coherent(dev);
 	int prot = dma_info_to_prot(dir, coherent, attrs);
 	struct iommu_domain *domain = iommu_get_dma_domain(dev);
@@ -1227,7 +1225,7 @@ dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
 	return iova;
 }
 
-void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
+void iommu_dma_unmap_phys(struct device *dev, dma_addr_t dma_handle,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 	struct iommu_domain *domain = iommu_get_dma_domain(dev);
@@ -1346,7 +1344,7 @@ static void iommu_dma_unmap_sg_swiotlb(struct device *dev, struct scatterlist *s
 	int i;
 
 	for_each_sg(sg, s, nents, i)
-		iommu_dma_unmap_page(dev, sg_dma_address(s),
+		iommu_dma_unmap_phys(dev, sg_dma_address(s),
 				sg_dma_len(s), dir, attrs);
 }
 
@@ -1359,8 +1357,8 @@ static int iommu_dma_map_sg_swiotlb(struct device *dev, struct scatterlist *sg,
 	sg_dma_mark_swiotlb(sg);
 
 	for_each_sg(sg, s, nents, i) {
-		sg_dma_address(s) = iommu_dma_map_page(dev, sg_page(s),
-				s->offset, s->length, dir, attrs);
+		sg_dma_address(s) = iommu_dma_map_phys(dev, sg_phys(s),
+				s->length, dir, attrs);
 		if (sg_dma_address(s) == DMA_MAPPING_ERROR)
 			goto out_unmap;
 		sg_dma_len(s) = s->length;
diff --git a/include/linux/iommu-dma.h b/include/linux/iommu-dma.h
index 508beaa44c39..485bdffed988 100644
--- a/include/linux/iommu-dma.h
+++ b/include/linux/iommu-dma.h
@@ -21,10 +21,9 @@ static inline bool use_dma_iommu(struct device *dev)
 }
 #endif /* CONFIG_IOMMU_DMA */
 
-dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size, enum dma_data_direction dir,
-		unsigned long attrs);
-void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
+dma_addr_t iommu_dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
+		enum dma_data_direction dir, unsigned long attrs);
+void iommu_dma_unmap_phys(struct device *dev, dma_addr_t dma_handle,
 		size_t size, enum dma_data_direction dir, unsigned long attrs);
 int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 		enum dma_data_direction dir, unsigned long attrs);
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index bd3bb6d59d72..90ad728205b9 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -169,7 +169,7 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
 	    arch_dma_map_page_direct(dev, phys + size))
 		addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
 	else if (use_dma_iommu(dev))
-		addr = iommu_dma_map_page(dev, page, offset, size, dir, attrs);
+		addr = iommu_dma_map_phys(dev, phys, size, dir, attrs);
 	else
 		addr = ops->map_page(dev, page, offset, size, dir, attrs);
 	kmsan_handle_dma(page, offset, size, dir);
@@ -190,7 +190,7 @@ void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size,
 	    arch_dma_unmap_page_direct(dev, addr + size))
 		dma_direct_unmap_page(dev, addr, size, dir, attrs);
 	else if (use_dma_iommu(dev))
-		iommu_dma_unmap_page(dev, addr, size, dir, attrs);
+		iommu_dma_unmap_phys(dev, addr, size, dir, attrs);
 	else
 		ops->unmap_page(dev, addr, size, dir, attrs);
 	trace_dma_unmap_phys(dev, addr, size, dir, attrs);
diff --git a/kernel/dma/ops_helpers.c b/kernel/dma/ops_helpers.c
index 9afd569eadb9..6f9d604d9d40 100644
--- a/kernel/dma/ops_helpers.c
+++ b/kernel/dma/ops_helpers.c
@@ -72,8 +72,8 @@ struct page *dma_common_alloc_pages(struct device *dev, size_t size,
 		return NULL;
 
 	if (use_dma_iommu(dev))
-		*dma_handle = iommu_dma_map_page(dev, page, 0, size, dir,
-						 DMA_ATTR_SKIP_CPU_SYNC);
+		*dma_handle = iommu_dma_map_phys(dev, page_to_phys(page), size,
+						 dir, DMA_ATTR_SKIP_CPU_SYNC);
 	else
 		*dma_handle = ops->map_page(dev, page, 0, size, dir,
 					    DMA_ATTR_SKIP_CPU_SYNC);
@@ -92,7 +92,7 @@ void dma_common_free_pages(struct device *dev, size_t size, struct page *page,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	if (use_dma_iommu(dev))
-		iommu_dma_unmap_page(dev, dma_handle, size, dir,
+		iommu_dma_unmap_phys(dev, dma_handle, size, dir,
 				     DMA_ATTR_SKIP_CPU_SYNC);
 	else if (ops->unmap_page)
 		ops->unmap_page(dev, dma_handle, size, dir,
-- 
cgit v1.2.3


From e53d29f957b36ba1666331956c6ccb047bb157d2 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Tue, 9 Sep 2025 16:27:35 +0300
Subject: dma-mapping: convert dma_direct_*map_page to be phys_addr_t based

Convert the DMA direct mapping functions to accept physical addresses
directly instead of page+offset parameters. The functions were already
operating on physical addresses internally, so this change eliminates
the redundant page-to-physical conversion at the API boundary.

The functions dma_direct_map_page() and dma_direct_unmap_page() are
renamed to dma_direct_map_phys() and dma_direct_unmap_phys() respectively,
with their calling convention changed from (struct page *page,
unsigned long offset) to (phys_addr_t phys).

Architecture-specific functions arch_dma_map_page_direct() and
arch_dma_unmap_page_direct() are similarly renamed to
arch_dma_map_phys_direct() and arch_dma_unmap_phys_direct().

The is_pci_p2pdma_page() checks are replaced with DMA_ATTR_MMIO checks
to allow integration with dma_direct_map_resource and dma_direct_map_phys()
is extended to support MMIO path either.

Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/bb15a22f76dc2e26683333ff54e789606cfbfcf0.1757423202.git.leonro@nvidia.com
---
 arch/powerpc/kernel/dma-iommu.c |  4 +--
 include/linux/dma-map-ops.h     |  8 +++---
 kernel/dma/direct.c             |  6 ++---
 kernel/dma/direct.h             | 57 ++++++++++++++++++++++++++---------------
 kernel/dma/mapping.c            |  8 +++---
 5 files changed, 49 insertions(+), 34 deletions(-)

(limited to 'kernel/dma')

diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 4d64a5db50f3..0359ab72cd3b 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -14,7 +14,7 @@
 #define can_map_direct(dev, addr) \
 	((dev)->bus_dma_limit >= phys_to_dma((dev), (addr)))
 
-bool arch_dma_map_page_direct(struct device *dev, phys_addr_t addr)
+bool arch_dma_map_phys_direct(struct device *dev, phys_addr_t addr)
 {
 	if (likely(!dev->bus_dma_limit))
 		return false;
@@ -24,7 +24,7 @@ bool arch_dma_map_page_direct(struct device *dev, phys_addr_t addr)
 
 #define is_direct_handle(dev, h) ((h) >= (dev)->archdata.dma_offset)
 
-bool arch_dma_unmap_page_direct(struct device *dev, dma_addr_t dma_handle)
+bool arch_dma_unmap_phys_direct(struct device *dev, dma_addr_t dma_handle)
 {
 	if (likely(!dev->bus_dma_limit))
 		return false;
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 332b80c42b6f..10882d00cb17 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -395,15 +395,15 @@ void *arch_dma_set_uncached(void *addr, size_t size);
 void arch_dma_clear_uncached(void *addr, size_t size);
 
 #ifdef CONFIG_ARCH_HAS_DMA_MAP_DIRECT
-bool arch_dma_map_page_direct(struct device *dev, phys_addr_t addr);
-bool arch_dma_unmap_page_direct(struct device *dev, dma_addr_t dma_handle);
+bool arch_dma_map_phys_direct(struct device *dev, phys_addr_t addr);
+bool arch_dma_unmap_phys_direct(struct device *dev, dma_addr_t dma_handle);
 bool arch_dma_map_sg_direct(struct device *dev, struct scatterlist *sg,
 		int nents);
 bool arch_dma_unmap_sg_direct(struct device *dev, struct scatterlist *sg,
 		int nents);
 #else
-#define arch_dma_map_page_direct(d, a)		(false)
-#define arch_dma_unmap_page_direct(d, a)	(false)
+#define arch_dma_map_phys_direct(d, a)		(false)
+#define arch_dma_unmap_phys_direct(d, a)	(false)
 #define arch_dma_map_sg_direct(d, s, n)		(false)
 #define arch_dma_unmap_sg_direct(d, s, n)	(false)
 #endif
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 302e89580972..ba7524f169bc 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -448,7 +448,7 @@ void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
 		if (sg_dma_is_bus_address(sg))
 			sg_dma_unmark_bus_address(sg);
 		else
-			dma_direct_unmap_page(dev, sg->dma_address,
+			dma_direct_unmap_phys(dev, sg->dma_address,
 					      sg_dma_len(sg), dir, attrs);
 	}
 }
@@ -471,8 +471,8 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 			 */
 			break;
 		case PCI_P2PDMA_MAP_NONE:
-			sg->dma_address = dma_direct_map_page(dev, sg_page(sg),
-					sg->offset, sg->length, dir, attrs);
+			sg->dma_address = dma_direct_map_phys(dev, sg_phys(sg),
+					sg->length, dir, attrs);
 			if (sg->dma_address == DMA_MAPPING_ERROR) {
 				ret = -EIO;
 				goto out_unmap;
diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
index d2c0b7e632fc..da2fadf45bcd 100644
--- a/kernel/dma/direct.h
+++ b/kernel/dma/direct.h
@@ -80,42 +80,57 @@ static inline void dma_direct_sync_single_for_cpu(struct device *dev,
 		arch_dma_mark_clean(paddr, size);
 }
 
-static inline dma_addr_t dma_direct_map_page(struct device *dev,
-		struct page *page, unsigned long offset, size_t size,
-		enum dma_data_direction dir, unsigned long attrs)
+static inline dma_addr_t dma_direct_map_phys(struct device *dev,
+		phys_addr_t phys, size_t size, enum dma_data_direction dir,
+		unsigned long attrs)
 {
-	phys_addr_t phys = page_to_phys(page) + offset;
-	dma_addr_t dma_addr = phys_to_dma(dev, phys);
+	dma_addr_t dma_addr;
 
 	if (is_swiotlb_force_bounce(dev)) {
-		if (is_pci_p2pdma_page(page))
-			return DMA_MAPPING_ERROR;
+		if (attrs & DMA_ATTR_MMIO)
+			goto err_overflow;
+
 		return swiotlb_map(dev, phys, size, dir, attrs);
 	}
 
-	if (unlikely(!dma_capable(dev, dma_addr, size, true)) ||
-	    dma_kmalloc_needs_bounce(dev, size, dir)) {
-		if (is_pci_p2pdma_page(page))
-			return DMA_MAPPING_ERROR;
-		if (is_swiotlb_active(dev))
-			return swiotlb_map(dev, phys, size, dir, attrs);
-
-		dev_WARN_ONCE(dev, 1,
-			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
-			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
-		return DMA_MAPPING_ERROR;
+	if (attrs & DMA_ATTR_MMIO) {
+		dma_addr = phys;
+		if (unlikely(!dma_capable(dev, dma_addr, size, false)))
+			goto err_overflow;
+	} else {
+		dma_addr = phys_to_dma(dev, phys);
+		if (unlikely(!dma_capable(dev, dma_addr, size, true)) ||
+		    dma_kmalloc_needs_bounce(dev, size, dir)) {
+			if (is_swiotlb_active(dev))
+				return swiotlb_map(dev, phys, size, dir, attrs);
+
+			goto err_overflow;
+		}
 	}
 
-	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+	if (!dev_is_dma_coherent(dev) &&
+	    !(attrs & (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_MMIO)))
 		arch_sync_dma_for_device(phys, size, dir);
 	return dma_addr;
+
+err_overflow:
+	dev_WARN_ONCE(
+		dev, 1,
+		"DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
+		&dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
+	return DMA_MAPPING_ERROR;
 }
 
-static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
+static inline void dma_direct_unmap_phys(struct device *dev, dma_addr_t addr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
-	phys_addr_t phys = dma_to_phys(dev, addr);
+	phys_addr_t phys;
+
+	if (attrs & DMA_ATTR_MMIO)
+		/* nothing to do: uncached and no swiotlb */
+		return;
 
+	phys = dma_to_phys(dev, addr);
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
 
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 90ad728205b9..3ac7d15e095f 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -166,8 +166,8 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
 		return DMA_MAPPING_ERROR;
 
 	if (dma_map_direct(dev, ops) ||
-	    arch_dma_map_page_direct(dev, phys + size))
-		addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
+	    arch_dma_map_phys_direct(dev, phys + size))
+		addr = dma_direct_map_phys(dev, phys, size, dir, attrs);
 	else if (use_dma_iommu(dev))
 		addr = iommu_dma_map_phys(dev, phys, size, dir, attrs);
 	else
@@ -187,8 +187,8 @@ void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size,
 
 	BUG_ON(!valid_dma_direction(dir));
 	if (dma_map_direct(dev, ops) ||
-	    arch_dma_unmap_page_direct(dev, addr + size))
-		dma_direct_unmap_page(dev, addr, size, dir, attrs);
+	    arch_dma_unmap_phys_direct(dev, addr + size))
+		dma_direct_unmap_phys(dev, addr, size, dir, attrs);
 	else if (use_dma_iommu(dev))
 		iommu_dma_unmap_phys(dev, addr, size, dir, attrs);
 	else
-- 
cgit v1.2.3


From 6eb1e769b2c13a33cb2ca694454a7561d3d72c0a Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Tue, 9 Sep 2025 16:27:36 +0300
Subject: kmsan: convert kmsan_handle_dma to use physical addresses

Convert the KMSAN DMA handling function from page-based to physical
address-based interface.

The refactoring renames kmsan_handle_dma() parameters from accepting
(struct page *page, size_t offset, size_t size) to (phys_addr_t phys,
size_t size). The existing semantics where callers are expected to
provide only kmap memory is continued here.

Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/3557cbaf66e935bc794f37d2b891ef75cbf2c80c.1757423202.git.leonro@nvidia.com
---
 drivers/virtio/virtio_ring.c |  4 ++--
 include/linux/kmsan.h        |  9 ++++-----
 kernel/dma/mapping.c         |  3 ++-
 mm/kmsan/hooks.c             | 10 ++++++----
 tools/virtio/linux/kmsan.h   |  2 +-
 5 files changed, 15 insertions(+), 13 deletions(-)

(limited to 'kernel/dma')

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index f5062061c408..c147145a6593 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -378,7 +378,7 @@ static int vring_map_one_sg(const struct vring_virtqueue *vq, struct scatterlist
 		 * is initialized by the hardware. Explicitly check/unpoison it
 		 * depending on the direction.
 		 */
-		kmsan_handle_dma(sg_page(sg), sg->offset, sg->length, direction);
+		kmsan_handle_dma(sg_phys(sg), sg->length, direction);
 		*addr = (dma_addr_t)sg_phys(sg);
 		return 0;
 	}
@@ -3157,7 +3157,7 @@ dma_addr_t virtqueue_dma_map_single_attrs(struct virtqueue *_vq, void *ptr,
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
 	if (!vq->use_dma_api) {
-		kmsan_handle_dma(virt_to_page(ptr), offset_in_page(ptr), size, dir);
+		kmsan_handle_dma(virt_to_phys(ptr), size, dir);
 		return (dma_addr_t)virt_to_phys(ptr);
 	}
 
diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h
index 2b1432cc16d5..f2fd221107bb 100644
--- a/include/linux/kmsan.h
+++ b/include/linux/kmsan.h
@@ -182,8 +182,7 @@ void kmsan_iounmap_page_range(unsigned long start, unsigned long end);
 
 /**
  * kmsan_handle_dma() - Handle a DMA data transfer.
- * @page:   first page of the buffer.
- * @offset: offset of the buffer within the first page.
+ * @phys:   physical address of the buffer.
  * @size:   buffer size.
  * @dir:    one of possible dma_data_direction values.
  *
@@ -192,7 +191,7 @@ void kmsan_iounmap_page_range(unsigned long start, unsigned long end);
  * * initializes the buffer, if it is copied from device;
  * * does both, if this is a DMA_BIDIRECTIONAL transfer.
  */
-void kmsan_handle_dma(struct page *page, size_t offset, size_t size,
+void kmsan_handle_dma(phys_addr_t phys, size_t size,
 		      enum dma_data_direction dir);
 
 /**
@@ -372,8 +371,8 @@ static inline void kmsan_iounmap_page_range(unsigned long start,
 {
 }
 
-static inline void kmsan_handle_dma(struct page *page, size_t offset,
-				    size_t size, enum dma_data_direction dir)
+static inline void kmsan_handle_dma(phys_addr_t phys, size_t size,
+				    enum dma_data_direction dir)
 {
 }
 
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 3ac7d15e095f..e47bcf7cc43d 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -172,7 +172,8 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
 		addr = iommu_dma_map_phys(dev, phys, size, dir, attrs);
 	else
 		addr = ops->map_page(dev, page, offset, size, dir, attrs);
-	kmsan_handle_dma(page, offset, size, dir);
+
+	kmsan_handle_dma(phys, size, dir);
 	trace_dma_map_phys(dev, phys, addr, size, dir, attrs);
 	debug_dma_map_phys(dev, phys, size, dir, addr, attrs);
 
diff --git a/mm/kmsan/hooks.c b/mm/kmsan/hooks.c
index 97de3d6194f0..fa9475e5ec4e 100644
--- a/mm/kmsan/hooks.c
+++ b/mm/kmsan/hooks.c
@@ -336,14 +336,16 @@ static void kmsan_handle_dma_page(const void *addr, size_t size,
 }
 
 /* Helper function to handle DMA data transfers. */
-void kmsan_handle_dma(struct page *page, size_t offset, size_t size,
+void kmsan_handle_dma(phys_addr_t phys, size_t size,
 		      enum dma_data_direction dir)
 {
-	u64 page_offset, to_go, addr;
+	struct page *page = phys_to_page(phys);
+	u64 page_offset, to_go;
+	void *addr;
 
-	if (PageHighMem(page))
+	if (PhysHighMem(phys))
 		return;
-	addr = (u64)page_address(page) + offset;
+	addr = page_to_virt(page);
 	/*
 	 * The kernel may occasionally give us adjacent DMA pages not belonging
 	 * to the same allocation. Process them separately to avoid triggering
diff --git a/tools/virtio/linux/kmsan.h b/tools/virtio/linux/kmsan.h
index 272b5aa285d5..6cd2e3efd03d 100644
--- a/tools/virtio/linux/kmsan.h
+++ b/tools/virtio/linux/kmsan.h
@@ -4,7 +4,7 @@
 
 #include <linux/gfp.h>
 
-inline void kmsan_handle_dma(struct page *page, size_t offset, size_t size,
+inline void kmsan_handle_dma(phys_addr_t phys, size_t size,
 			     enum dma_data_direction dir)
 {
 }
-- 
cgit v1.2.3


From 18c9cbb042c930eb37f68df216319a371f4fcb22 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Tue, 9 Sep 2025 16:27:37 +0300
Subject: dma-mapping: implement DMA_ATTR_MMIO for dma_(un)map_page_attrs()

Make dma_map_page_attrs() and dma_map_page_attrs() respect
DMA_ATTR_MMIO.

DMA_ATR_MMIO makes the functions behave the same as
dma_(un)map_resource():
 - No swiotlb is possible
 - Legacy dma_ops arches use ops->map_resource()
 - No kmsan
 - No arch_dma_map_phys_direct()

The prior patches have made the internal functions called here
support DMA_ATTR_MMIO.

This is also preparation for turning dma_map_resource() into an inline
calling dma_map_phys(DMA_ATTR_MMIO) to consolidate the flows.

Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/3660e2c78ea409d6c483a215858fb3af52cd0ed3.1757423202.git.leonro@nvidia.com
---
 kernel/dma/mapping.c | 26 +++++++++++++++++++++-----
 1 file changed, 21 insertions(+), 5 deletions(-)

(limited to 'kernel/dma')

diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index e47bcf7cc43d..95eab531e227 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -158,6 +158,7 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 	phys_addr_t phys = page_to_phys(page) + offset;
+	bool is_mmio = attrs & DMA_ATTR_MMIO;
 	dma_addr_t addr;
 
 	BUG_ON(!valid_dma_direction(dir));
@@ -166,14 +167,25 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
 		return DMA_MAPPING_ERROR;
 
 	if (dma_map_direct(dev, ops) ||
-	    arch_dma_map_phys_direct(dev, phys + size))
+	    (!is_mmio && arch_dma_map_phys_direct(dev, phys + size)))
 		addr = dma_direct_map_phys(dev, phys, size, dir, attrs);
 	else if (use_dma_iommu(dev))
 		addr = iommu_dma_map_phys(dev, phys, size, dir, attrs);
-	else
+	else if (is_mmio) {
+		if (!ops->map_resource)
+			return DMA_MAPPING_ERROR;
+
+		addr = ops->map_resource(dev, phys, size, dir, attrs);
+	} else {
+		/*
+		 * The dma_ops API contract for ops->map_page() requires
+		 * kmappable memory, while ops->map_resource() does not.
+		 */
 		addr = ops->map_page(dev, page, offset, size, dir, attrs);
+	}
 
-	kmsan_handle_dma(phys, size, dir);
+	if (!is_mmio)
+		kmsan_handle_dma(phys, size, dir);
 	trace_dma_map_phys(dev, phys, addr, size, dir, attrs);
 	debug_dma_map_phys(dev, phys, size, dir, addr, attrs);
 
@@ -185,14 +197,18 @@ void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size,
 		enum dma_data_direction dir, unsigned long attrs)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
+	bool is_mmio = attrs & DMA_ATTR_MMIO;
 
 	BUG_ON(!valid_dma_direction(dir));
 	if (dma_map_direct(dev, ops) ||
-	    arch_dma_unmap_phys_direct(dev, addr + size))
+	    (!is_mmio && arch_dma_unmap_phys_direct(dev, addr + size)))
 		dma_direct_unmap_phys(dev, addr, size, dir, attrs);
 	else if (use_dma_iommu(dev))
 		iommu_dma_unmap_phys(dev, addr, size, dir, attrs);
-	else
+	else if (is_mmio) {
+		if (ops->unmap_resource)
+			ops->unmap_resource(dev, addr, size, dir, attrs);
+	} else
 		ops->unmap_page(dev, addr, size, dir, attrs);
 	trace_dma_unmap_phys(dev, addr, size, dir, attrs);
 	debug_dma_unmap_phys(dev, addr, size, dir);
-- 
cgit v1.2.3


From f7326196a781622b33bfbdabb00f5e72b5fb5679 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Tue, 9 Sep 2025 16:27:39 +0300
Subject: dma-mapping: export new dma_*map_phys() interface

Introduce new DMA mapping functions dma_map_phys() and dma_unmap_phys()
that operate directly on physical addresses instead of page+offset
parameters. This provides a more efficient interface for drivers that
already have physical addresses available.

The new functions are implemented as the primary mapping layer, with
the existing dma_map_page_attrs()/dma_map_resource() and
dma_unmap_page_attrs()/dma_unmap_resource() functions converted to simple
wrappers around the phys-based implementations.

In case dma_map_page_attrs(), the struct page is converted to physical
address with help of page_to_phys() function and dma_map_resource()
provides physical address as is together with addition of DMA_ATTR_MMIO
attribute.

The old page-based API is preserved in mapping.c to ensure that existing
code won't be affected by changing EXPORT_SYMBOL to EXPORT_SYMBOL_GPL
variant for dma_*map_phys().

Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/54cc52af91777906bbe4a386113437ba0bcfba9c.1757423202.git.leonro@nvidia.com
---
 drivers/iommu/dma-iommu.c   | 14 ---------
 include/linux/dma-direct.h  |  2 --
 include/linux/dma-mapping.h | 13 +++++++++
 include/linux/iommu-dma.h   |  4 ---
 include/trace/events/dma.h  |  2 --
 kernel/dma/debug.c          | 43 ----------------------------
 kernel/dma/debug.h          | 21 --------------
 kernel/dma/direct.c         | 16 -----------
 kernel/dma/mapping.c        | 69 ++++++++++++++++++++++++---------------------
 9 files changed, 50 insertions(+), 134 deletions(-)

(limited to 'kernel/dma')

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 6804aaf034a1..7944a3af4545 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1556,20 +1556,6 @@ void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
 		__iommu_dma_unmap(dev, start, end - start);
 }
 
-dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-	return __iommu_dma_map(dev, phys, size,
-			dma_info_to_prot(dir, false, attrs) | IOMMU_MMIO,
-			dma_get_mask(dev));
-}
-
-void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-	__iommu_dma_unmap(dev, handle, size);
-}
-
 static void __iommu_dma_free(struct device *dev, size_t size, void *cpu_addr)
 {
 	size_t alloc_size = PAGE_ALIGN(size);
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index f3bc0bcd7098..c249912456f9 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -149,7 +149,5 @@ void dma_direct_free_pages(struct device *dev, size_t size,
 		struct page *page, dma_addr_t dma_addr,
 		enum dma_data_direction dir);
 int dma_direct_supported(struct device *dev, u64 mask);
-dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs);
 
 #endif /* _LINUX_DMA_DIRECT_H */
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 4254fd9bdf5d..8248ff9363ee 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -138,6 +138,10 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
 		unsigned long attrs);
 void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size,
 		enum dma_data_direction dir, unsigned long attrs);
+dma_addr_t dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
+		enum dma_data_direction dir, unsigned long attrs);
+void dma_unmap_phys(struct device *dev, dma_addr_t addr, size_t size,
+		enum dma_data_direction dir, unsigned long attrs);
 unsigned int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
 		int nents, enum dma_data_direction dir, unsigned long attrs);
 void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg,
@@ -192,6 +196,15 @@ static inline void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 }
+static inline dma_addr_t dma_map_phys(struct device *dev, phys_addr_t phys,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	return DMA_MAPPING_ERROR;
+}
+static inline void dma_unmap_phys(struct device *dev, dma_addr_t addr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+}
 static inline unsigned int dma_map_sg_attrs(struct device *dev,
 		struct scatterlist *sg, int nents, enum dma_data_direction dir,
 		unsigned long attrs)
diff --git a/include/linux/iommu-dma.h b/include/linux/iommu-dma.h
index 485bdffed988..a92b3ff9b934 100644
--- a/include/linux/iommu-dma.h
+++ b/include/linux/iommu-dma.h
@@ -42,10 +42,6 @@ size_t iommu_dma_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);
-dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
-		size_t size, enum dma_data_direction dir, unsigned long attrs);
-void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir, unsigned long attrs);
 struct sg_table *iommu_dma_alloc_noncontiguous(struct device *dev, size_t size,
 		enum dma_data_direction dir, gfp_t gfp, unsigned long attrs);
 void iommu_dma_free_noncontiguous(struct device *dev, size_t size,
diff --git a/include/trace/events/dma.h b/include/trace/events/dma.h
index 84416c7d6bfa..5da59fd8121d 100644
--- a/include/trace/events/dma.h
+++ b/include/trace/events/dma.h
@@ -73,7 +73,6 @@ DEFINE_EVENT(dma_map, name, \
 	TP_ARGS(dev, phys_addr, dma_addr, size, dir, attrs))
 
 DEFINE_MAP_EVENT(dma_map_phys);
-DEFINE_MAP_EVENT(dma_map_resource);
 
 DECLARE_EVENT_CLASS(dma_unmap,
 	TP_PROTO(struct device *dev, dma_addr_t addr, size_t size,
@@ -111,7 +110,6 @@ DEFINE_EVENT(dma_unmap, name, \
 	TP_ARGS(dev, addr, size, dir, attrs))
 
 DEFINE_UNMAP_EVENT(dma_unmap_phys);
-DEFINE_UNMAP_EVENT(dma_unmap_resource);
 
 DECLARE_EVENT_CLASS(dma_alloc_class,
 	TP_PROTO(struct device *dev, void *virt_addr, dma_addr_t dma_addr,
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index b275db9ca6a0..1e5c64cb6a42 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -38,7 +38,6 @@ enum {
 	dma_debug_single,
 	dma_debug_sg,
 	dma_debug_coherent,
-	dma_debug_resource,
 	dma_debug_noncoherent,
 	dma_debug_phy,
 };
@@ -142,7 +141,6 @@ static const char *type2name[] = {
 	[dma_debug_single] = "single",
 	[dma_debug_sg] = "scatter-gather",
 	[dma_debug_coherent] = "coherent",
-	[dma_debug_resource] = "resource",
 	[dma_debug_noncoherent] = "noncoherent",
 	[dma_debug_phy] = "phy",
 };
@@ -1446,47 +1444,6 @@ void debug_dma_free_coherent(struct device *dev, size_t size,
 	check_unmap(&ref);
 }
 
-void debug_dma_map_resource(struct device *dev, phys_addr_t addr, size_t size,
-			    int direction, dma_addr_t dma_addr,
-			    unsigned long attrs)
-{
-	struct dma_debug_entry *entry;
-
-	if (unlikely(dma_debug_disabled()))
-		return;
-
-	entry = dma_entry_alloc();
-	if (!entry)
-		return;
-
-	entry->type		= dma_debug_resource;
-	entry->dev		= dev;
-	entry->paddr		= addr;
-	entry->size		= size;
-	entry->dev_addr		= dma_addr;
-	entry->direction	= direction;
-	entry->map_err_type	= MAP_ERR_NOT_CHECKED;
-
-	add_dma_entry(entry, attrs);
-}
-
-void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr,
-			      size_t size, int direction)
-{
-	struct dma_debug_entry ref = {
-		.type           = dma_debug_resource,
-		.dev            = dev,
-		.dev_addr       = dma_addr,
-		.size           = size,
-		.direction      = direction,
-	};
-
-	if (unlikely(dma_debug_disabled()))
-		return;
-
-	check_unmap(&ref);
-}
-
 void debug_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
 				   size_t size, int direction)
 {
diff --git a/kernel/dma/debug.h b/kernel/dma/debug.h
index bedae973e725..da7be0bddcf6 100644
--- a/kernel/dma/debug.h
+++ b/kernel/dma/debug.h
@@ -30,14 +30,6 @@ extern void debug_dma_alloc_coherent(struct device *dev, size_t size,
 extern void debug_dma_free_coherent(struct device *dev, size_t size,
 				    void *virt, dma_addr_t addr);
 
-extern void debug_dma_map_resource(struct device *dev, phys_addr_t addr,
-				   size_t size, int direction,
-				   dma_addr_t dma_addr,
-				   unsigned long attrs);
-
-extern void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr,
-				     size_t size, int direction);
-
 extern void debug_dma_sync_single_for_cpu(struct device *dev,
 					  dma_addr_t dma_handle, size_t size,
 					  int direction);
@@ -95,19 +87,6 @@ static inline void debug_dma_free_coherent(struct device *dev, size_t size,
 {
 }
 
-static inline void debug_dma_map_resource(struct device *dev, phys_addr_t addr,
-					  size_t size, int direction,
-					  dma_addr_t dma_addr,
-					  unsigned long attrs)
-{
-}
-
-static inline void debug_dma_unmap_resource(struct device *dev,
-					    dma_addr_t dma_addr, size_t size,
-					    int direction)
-{
-}
-
 static inline void debug_dma_sync_single_for_cpu(struct device *dev,
 						 dma_addr_t dma_handle,
 						 size_t size, int direction)
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index ba7524f169bc..1f9ee9759426 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -497,22 +497,6 @@ out_unmap:
 	return ret;
 }
 
-dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-	dma_addr_t dma_addr = paddr;
-
-	if (unlikely(!dma_capable(dev, dma_addr, size, false))) {
-		dev_err_once(dev,
-			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
-			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
-		WARN_ON_ONCE(1);
-		return DMA_MAPPING_ERROR;
-	}
-
-	return dma_addr;
-}
-
 int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs)
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 95eab531e227..fe7472f13b10 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -152,12 +152,10 @@ static inline bool dma_map_direct(struct device *dev,
 	return dma_go_direct(dev, *dev->dma_mask, ops);
 }
 
-dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
-		size_t offset, size_t size, enum dma_data_direction dir,
-		unsigned long attrs)
+dma_addr_t dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
-	phys_addr_t phys = page_to_phys(page) + offset;
 	bool is_mmio = attrs & DMA_ATTR_MMIO;
 	dma_addr_t addr;
 
@@ -177,6 +175,9 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
 
 		addr = ops->map_resource(dev, phys, size, dir, attrs);
 	} else {
+		struct page *page = phys_to_page(phys);
+		size_t offset = offset_in_page(phys);
+
 		/*
 		 * The dma_ops API contract for ops->map_page() requires
 		 * kmappable memory, while ops->map_resource() does not.
@@ -191,9 +192,26 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
 
 	return addr;
 }
+EXPORT_SYMBOL_GPL(dma_map_phys);
+
+dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
+		size_t offset, size_t size, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+	phys_addr_t phys = page_to_phys(page) + offset;
+
+	if (unlikely(attrs & DMA_ATTR_MMIO))
+		return DMA_MAPPING_ERROR;
+
+	if (IS_ENABLED(CONFIG_DMA_API_DEBUG) &&
+	    WARN_ON_ONCE(is_zone_device_page(page)))
+		return DMA_MAPPING_ERROR;
+
+	return dma_map_phys(dev, phys, size, dir, attrs);
+}
 EXPORT_SYMBOL(dma_map_page_attrs);
 
-void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size,
+void dma_unmap_phys(struct device *dev, dma_addr_t addr, size_t size,
 		enum dma_data_direction dir, unsigned long attrs)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
@@ -213,6 +231,16 @@ void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size,
 	trace_dma_unmap_phys(dev, addr, size, dir, attrs);
 	debug_dma_unmap_phys(dev, addr, size, dir);
 }
+EXPORT_SYMBOL_GPL(dma_unmap_phys);
+
+void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size,
+		 enum dma_data_direction dir, unsigned long attrs)
+{
+	if (unlikely(attrs & DMA_ATTR_MMIO))
+		return;
+
+	dma_unmap_phys(dev, addr, size, dir, attrs);
+}
 EXPORT_SYMBOL(dma_unmap_page_attrs);
 
 static int __dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
@@ -338,41 +366,18 @@ EXPORT_SYMBOL(dma_unmap_sg_attrs);
 dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-	dma_addr_t addr = DMA_MAPPING_ERROR;
-
-	BUG_ON(!valid_dma_direction(dir));
-
-	if (WARN_ON_ONCE(!dev->dma_mask))
+	if (IS_ENABLED(CONFIG_DMA_API_DEBUG) &&
+	    WARN_ON_ONCE(pfn_valid(PHYS_PFN(phys_addr))))
 		return DMA_MAPPING_ERROR;
 
-	if (dma_map_direct(dev, ops))
-		addr = dma_direct_map_resource(dev, phys_addr, size, dir, attrs);
-	else if (use_dma_iommu(dev))
-		addr = iommu_dma_map_resource(dev, phys_addr, size, dir, attrs);
-	else if (ops->map_resource)
-		addr = ops->map_resource(dev, phys_addr, size, dir, attrs);
-
-	trace_dma_map_resource(dev, phys_addr, addr, size, dir, attrs);
-	debug_dma_map_resource(dev, phys_addr, size, dir, addr, attrs);
-	return addr;
+	return dma_map_phys(dev, phys_addr, size, dir, attrs | DMA_ATTR_MMIO);
 }
 EXPORT_SYMBOL(dma_map_resource);
 
 void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size,
 		enum dma_data_direction dir, unsigned long attrs)
 {
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (dma_map_direct(dev, ops))
-		; /* nothing to do: uncached and no swiotlb */
-	else if (use_dma_iommu(dev))
-		iommu_dma_unmap_resource(dev, addr, size, dir, attrs);
-	else if (ops->unmap_resource)
-		ops->unmap_resource(dev, addr, size, dir, attrs);
-	trace_dma_unmap_resource(dev, addr, size, dir, attrs);
-	debug_dma_unmap_resource(dev, addr, size, dir);
+	dma_unmap_phys(dev, addr, size, dir, attrs | DMA_ATTR_MMIO);
 }
 EXPORT_SYMBOL(dma_unmap_resource);
 
-- 
cgit v1.2.3


From a16c46c2402026162111ed9fd1fc28d25223443e Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Mon, 1 Sep 2025 17:03:44 +0200
Subject: dma-remap: drop nth_page() in dma_common_contiguous_remap()

dma_common_contiguous_remap() is used to remap an "allocated contiguous
region".  Within a single allocation, there is no need to use nth_page()
anymore.

Neither the buddy, nor hugetlb, nor CMA will hand out problematic page
ranges.

Link: https://lkml.kernel.org/r/20250901150359.867252-24-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/dma/remap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel/dma')

diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c
index 9e2afad1c615..b7c1c0c92d0c 100644
--- a/kernel/dma/remap.c
+++ b/kernel/dma/remap.c
@@ -49,7 +49,7 @@ void *dma_common_contiguous_remap(struct page *page, size_t size,
 	if (!pages)
 		return NULL;
 	for (i = 0; i < count; i++)
-		pages[i] = nth_page(page, i);
+		pages[i] = page++;
 	vaddr = vmap(pages, count, VM_DMA_COHERENT, prot);
 	kvfree(pages);
 
-- 
cgit v1.2.3


From 03521c892bb8d0712c23e158ae9bdf8705897df8 Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Thu, 9 Oct 2025 16:15:08 +0200
Subject: dma-debug: don't report false positives with
 DMA_BOUNCE_UNALIGNED_KMALLOC

Commit 370645f41e6e ("dma-mapping: force bouncing if the kmalloc() size is
not cache-line-aligned") introduced DMA_BOUNCE_UNALIGNED_KMALLOC feature
and permitted architecture specific code configure kmalloc slabs with
sizes smaller than the value of dma_get_cache_alignment().

When that feature is enabled, the physical address of some small
kmalloc()-ed buffers might be not aligned to the CPU cachelines, thus not
really suitable for typical DMA.  To properly handle that case a SWIOTLB
buffer bouncing is used, so no CPU cache corruption occurs.  When that
happens, there is no point reporting a false-positive DMA-API warning that
the buffer is not properly aligned, as this is not a client driver fault.

[m.szyprowski@samsung.com: replace is_swiotlb_allocated() with is_swiotlb_active(), per Catalin]
  Link: https://lkml.kernel.org/r/20251010173009.3916215-1-m.szyprowski@samsung.com
Link: https://lkml.kernel.org/r/20251009141508.2342138-1-m.szyprowski@samsung.com
Fixes: 370645f41e6e ("dma-mapping: force bouncing if the kmalloc() size is not cache-line-aligned")
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Inki Dae <m.szyprowski@samsung.com>
Cc: Robin Murohy <robin.murphy@arm.com>
Cc: "Isaac J. Manjarres" <isaacmanjarres@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/dma/debug.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'kernel/dma')

diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 1e5c64cb6a42..138ede653de4 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -23,6 +23,7 @@
 #include <linux/ctype.h>
 #include <linux/list.h>
 #include <linux/slab.h>
+#include <linux/swiotlb.h>
 #include <asm/sections.h>
 #include "debug.h"
 
@@ -594,7 +595,9 @@ static void add_dma_entry(struct dma_debug_entry *entry, unsigned long attrs)
 	if (rc == -ENOMEM) {
 		pr_err_once("cacheline tracking ENOMEM, dma-debug disabled\n");
 		global_disable = true;
-	} else if (rc == -EEXIST && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
+	} else if (rc == -EEXIST && !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
+		   !(IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) &&
+		     is_swiotlb_active(entry->dev))) {
 		err_printk(entry->dev, entry,
 			"cacheline tracking EEXIST, overlapping mappings aren't supported\n");
 	}
-- 
cgit v1.2.3


From d0d08f4bd7f667dc7a65cd7133c0a94a6f02aca3 Mon Sep 17 00:00:00 2001
From: Pranjal Shrivastava <praan@google.com>
Date: Wed, 26 Nov 2025 11:41:12 +0000
Subject: dma-direct: Fix missing sg_dma_len assignment in P2PDMA bus mappings

Prior to commit a25e7962db0d7 ("PCI/P2PDMA: Refactor the p2pdma mapping
helpers"), P2P segments were mapped using the pci_p2pdma_map_segment()
helper. This helper was responsible for populating sg->dma_address,
marking the bus address, and also setting sg_dma_len(sg).

The refactor[1] removed this helper and moved the mapping logic directly
into the callers. While iommu_dma_map_sg() was correctly updated to set
the length in the new flow, it was missed in dma_direct_map_sg().

Thus, in dma_direct_map_sg(), the PCI_P2PDMA_MAP_BUS_ADDR case sets the
dma_address and marks the segment, but immediately executes 'continue',
which causes the loop to skip the standard assignment logic at the end:

    sg_dma_len(sg) = sg->length;

As a result, when CONFIG_NEED_SG_DMA_LENGTH is enabled, the dma_length
field remains uninitialized (zero) for P2P bus address mappings. This
breaks upper-layer drivers (for e.g. RDMA/IB) that rely on sg_dma_len()
to determine the transfer size.

Fix this by explicitly setting the DMA length in the
PCI_P2PDMA_MAP_BUS_ADDR case before continuing to the next scatterlist
entry.

Fixes: a25e7962db0d7 ("PCI/P2PDMA: Refactor the p2pdma mapping helpers")
Reported-by: Jacob Moroni <jmoroni@google.com>
Signed-off-by: Pranjal Shrivastava <praan@google.com>

[1]
https://lore.kernel.org/all/ac14a0e94355bf898de65d023ccf8a2ad22a3ece.1746424934.git.leon@kernel.org/

Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Shivaji Kant <shivajikant@google.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20251126114112.3694469-1-praan@google.com
---
 kernel/dma/direct.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'kernel/dma')

diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 1f9ee9759426..f973e7e73c90 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -481,6 +481,7 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 		case PCI_P2PDMA_MAP_BUS_ADDR:
 			sg->dma_address = pci_p2pdma_bus_addr_map(&p2pdma_state,
 					sg_phys(sg));
+			sg_dma_len(sg) = sg->length;
 			sg_dma_mark_bus_address(sg);
 			continue;
 		default:
-- 
cgit v1.2.3