Linux-ACPI Archive on lore.kernel.org
 help / color / Atom feed
* support range based offsets in dma-direct v3
@ 2020-09-16  6:14 Christoph Hellwig
  2020-09-16  6:14 ` [PATCH 1/6] ARM/dma-mapping: remove a __arch_page_to_dma #error Christoph Hellwig
                   ` (6 more replies)
  0 siblings, 7 replies; 15+ messages in thread
From: Christoph Hellwig @ 2020-09-16  6:14 UTC (permalink / raw)
  To: iommu, Russell King, Santosh Shilimkar, Greg Kroah-Hartman
  Cc: Jim Quinlan, Nathan Chancellor, Florian Fainelli, Robin Murphy,
	Rob Herring, Frank Rowand, Ohad Ben-Cohen, Bjorn Andersson,
	linux-remoteproc, linux-usb, linux-arm-kernel, linux-kernel,
	linux-sh, linux-pci, linux-acpi, devicetree

Hi all,

this series adds range-based offsets to the dma-direct implementation.  The
guts of the change are a patch from Jim with some modifications from me,
but to do it nicely we need to ARM patches to prepare for it as well.

Changes since v2:
 - fix a mismerge
 - return (phys_addr_t)-1 from translate_dma_to_phys when there is no
   matching range to fix dma_capable checks

Changes since v1:
 - rebased on top of the latests dma-mapping for-next tree
 - add two more trivial ARM cleanups
 - remove the DMA property inheritance hack in usb
 - move the remaining copy of the ranges into the remoteproc driver
   as it should not be seen as a general API, but as a quirk for
   remoteproc that we need to fix ASAP

Diffstat:

^ permalink raw reply	[flat|nested] 15+ messages in thread

* [PATCH 1/6] ARM/dma-mapping: remove a __arch_page_to_dma #error
  2020-09-16  6:14 support range based offsets in dma-direct v3 Christoph Hellwig
@ 2020-09-16  6:14 ` Christoph Hellwig
  2020-09-16  6:14 ` [PATCH 2/6] ARM/dma-mapping: remove dma_to_virt Christoph Hellwig
                   ` (5 subsequent siblings)
  6 siblings, 0 replies; 15+ messages in thread
From: Christoph Hellwig @ 2020-09-16  6:14 UTC (permalink / raw)
  To: iommu, Russell King, Santosh Shilimkar, Greg Kroah-Hartman
  Cc: Jim Quinlan, Nathan Chancellor, Florian Fainelli, Robin Murphy,
	Rob Herring, Frank Rowand, Ohad Ben-Cohen, Bjorn Andersson,
	linux-remoteproc, linux-usb, linux-arm-kernel, linux-kernel,
	linux-sh, linux-pci, linux-acpi, devicetree

The __arch_page_to_dma hook is long gone.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/arm/include/asm/dma-mapping.h | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index bdd80ddbca3451..70d95677656044 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -23,10 +23,6 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 	return NULL;
 }
 
-#ifdef __arch_page_to_dma
-#error Please update to __arch_pfn_to_dma
-#endif
-
 /*
  * dma_to_pfn/pfn_to_dma/dma_to_virt/virt_to_dma are architecture private
  * functions used internally by the DMA-mapping API to provide DMA
-- 
2.28.0


^ permalink raw reply	[flat|nested] 15+ messages in thread

* [PATCH 2/6] ARM/dma-mapping: remove dma_to_virt
  2020-09-16  6:14 support range based offsets in dma-direct v3 Christoph Hellwig
  2020-09-16  6:14 ` [PATCH 1/6] ARM/dma-mapping: remove a __arch_page_to_dma #error Christoph Hellwig
@ 2020-09-16  6:14 ` Christoph Hellwig
  2020-09-16  6:14 ` [PATCH 3/6] ARM/dma-mapping: move various helpers from dma-mapping.h to dma-direct.h Christoph Hellwig
                   ` (4 subsequent siblings)
  6 siblings, 0 replies; 15+ messages in thread
From: Christoph Hellwig @ 2020-09-16  6:14 UTC (permalink / raw)
  To: iommu, Russell King, Santosh Shilimkar, Greg Kroah-Hartman
  Cc: Jim Quinlan, Nathan Chancellor, Florian Fainelli, Robin Murphy,
	Rob Herring, Frank Rowand, Ohad Ben-Cohen, Bjorn Andersson,
	linux-remoteproc, linux-usb, linux-arm-kernel, linux-kernel,
	linux-sh, linux-pci, linux-acpi, devicetree

dma_to_virt is entirely unused, remove it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/arm/include/asm/dma-mapping.h        | 18 +-----------------
 arch/arm/mach-omap1/include/mach/memory.h |  4 ----
 2 files changed, 1 insertion(+), 21 deletions(-)

diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index 70d95677656044..cf2535fb8891f5 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -24,7 +24,7 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 }
 
 /*
- * dma_to_pfn/pfn_to_dma/dma_to_virt/virt_to_dma are architecture private
+ * dma_to_pfn/pfn_to_dma/virt_to_dma are architecture private
  * functions used internally by the DMA-mapping API to provide DMA
  * addresses. They must not be used by drivers.
  */
@@ -46,17 +46,6 @@ static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
 	return pfn;
 }
 
-static inline void *dma_to_virt(struct device *dev, dma_addr_t addr)
-{
-	if (dev) {
-		unsigned long pfn = dma_to_pfn(dev, addr);
-
-		return phys_to_virt(__pfn_to_phys(pfn));
-	}
-
-	return (void *)__bus_to_virt((unsigned long)addr);
-}
-
 static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
 {
 	if (dev)
@@ -76,11 +65,6 @@ static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
 	return __arch_dma_to_pfn(dev, addr);
 }
 
-static inline void *dma_to_virt(struct device *dev, dma_addr_t addr)
-{
-	return __arch_dma_to_virt(dev, addr);
-}
-
 static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
 {
 	return __arch_virt_to_dma(dev, addr);
diff --git a/arch/arm/mach-omap1/include/mach/memory.h b/arch/arm/mach-omap1/include/mach/memory.h
index 1142560e0078f5..e43697c3297bf2 100644
--- a/arch/arm/mach-omap1/include/mach/memory.h
+++ b/arch/arm/mach-omap1/include/mach/memory.h
@@ -41,10 +41,6 @@
 	   __phys_to_pfn(__dma);				\
 	})
 
-#define __arch_dma_to_virt(dev, addr)	({ (void *) (is_lbus_device(dev) ? \
-						lbus_to_virt(addr) : \
-						__phys_to_virt(addr)); })
-
 #define __arch_virt_to_dma(dev, addr)	({ unsigned long __addr = (unsigned long)(addr); \
 					   (dma_addr_t) (is_lbus_device(dev) ? \
 						virt_to_lbus(__addr) : \
-- 
2.28.0


^ permalink raw reply	[flat|nested] 15+ messages in thread

* [PATCH 3/6] ARM/dma-mapping: move various helpers from dma-mapping.h to dma-direct.h
  2020-09-16  6:14 support range based offsets in dma-direct v3 Christoph Hellwig
  2020-09-16  6:14 ` [PATCH 1/6] ARM/dma-mapping: remove a __arch_page_to_dma #error Christoph Hellwig
  2020-09-16  6:14 ` [PATCH 2/6] ARM/dma-mapping: remove dma_to_virt Christoph Hellwig
@ 2020-09-16  6:14 ` Christoph Hellwig
  2020-09-16  6:14 ` [PATCH 4/6] ARM/keystone: move the DMA offset handling under ifdef CONFIG_ARM_LPAE Christoph Hellwig
                   ` (3 subsequent siblings)
  6 siblings, 0 replies; 15+ messages in thread
From: Christoph Hellwig @ 2020-09-16  6:14 UTC (permalink / raw)
  To: iommu, Russell King, Santosh Shilimkar, Greg Kroah-Hartman
  Cc: Jim Quinlan, Nathan Chancellor, Florian Fainelli, Robin Murphy,
	Rob Herring, Frank Rowand, Ohad Ben-Cohen, Bjorn Andersson,
	linux-remoteproc, linux-usb, linux-arm-kernel, linux-kernel,
	linux-sh, linux-pci, linux-acpi, devicetree

Move the helpers to translate to and from direct mapping DMA addresses
to dma-direct.h.  This not only is the most logical place, but the new
placement also avoids dependency loops with pending commits.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
---
 arch/arm/common/dmabounce.c        |  2 +-
 arch/arm/include/asm/dma-direct.h  | 50 ++++++++++++++++++++++++++++++
 arch/arm/include/asm/dma-mapping.h | 50 ------------------------------
 3 files changed, 51 insertions(+), 51 deletions(-)

diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c
index f4b719bde76367..d3e00ea9208834 100644
--- a/arch/arm/common/dmabounce.c
+++ b/arch/arm/common/dmabounce.c
@@ -24,7 +24,7 @@
 #include <linux/slab.h>
 #include <linux/page-flags.h>
 #include <linux/device.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-direct.h>
 #include <linux/dmapool.h>
 #include <linux/list.h>
 #include <linux/scatterlist.h>
diff --git a/arch/arm/include/asm/dma-direct.h b/arch/arm/include/asm/dma-direct.h
index bca0de56753439..fbcf4367b5cb1a 100644
--- a/arch/arm/include/asm/dma-direct.h
+++ b/arch/arm/include/asm/dma-direct.h
@@ -2,6 +2,56 @@
 #ifndef ASM_ARM_DMA_DIRECT_H
 #define ASM_ARM_DMA_DIRECT_H 1
 
+#include <asm/memory.h>
+
+/*
+ * dma_to_pfn/pfn_to_dma/virt_to_dma are architecture private
+ * functions used internally by the DMA-mapping API to provide DMA
+ * addresses. They must not be used by drivers.
+ */
+#ifndef __arch_pfn_to_dma
+static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
+{
+	if (dev)
+		pfn -= dev->dma_pfn_offset;
+	return (dma_addr_t)__pfn_to_bus(pfn);
+}
+
+static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
+{
+	unsigned long pfn = __bus_to_pfn(addr);
+
+	if (dev)
+		pfn += dev->dma_pfn_offset;
+
+	return pfn;
+}
+
+static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
+{
+	if (dev)
+		return pfn_to_dma(dev, virt_to_pfn(addr));
+
+	return (dma_addr_t)__virt_to_bus((unsigned long)(addr));
+}
+
+#else
+static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
+{
+	return __arch_pfn_to_dma(dev, pfn);
+}
+
+static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
+{
+	return __arch_dma_to_pfn(dev, addr);
+}
+
+static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
+{
+	return __arch_virt_to_dma(dev, addr);
+}
+#endif
+
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	unsigned int offset = paddr & ~PAGE_MASK;
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index cf2535fb8891f5..0a1a536368c3a4 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -8,8 +8,6 @@
 #include <linux/scatterlist.h>
 #include <linux/dma-debug.h>
 
-#include <asm/memory.h>
-
 #include <xen/xen.h>
 #include <asm/xen/hypervisor.h>
 
@@ -23,54 +21,6 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 	return NULL;
 }
 
-/*
- * dma_to_pfn/pfn_to_dma/virt_to_dma are architecture private
- * functions used internally by the DMA-mapping API to provide DMA
- * addresses. They must not be used by drivers.
- */
-#ifndef __arch_pfn_to_dma
-static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
-{
-	if (dev)
-		pfn -= dev->dma_pfn_offset;
-	return (dma_addr_t)__pfn_to_bus(pfn);
-}
-
-static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
-{
-	unsigned long pfn = __bus_to_pfn(addr);
-
-	if (dev)
-		pfn += dev->dma_pfn_offset;
-
-	return pfn;
-}
-
-static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
-{
-	if (dev)
-		return pfn_to_dma(dev, virt_to_pfn(addr));
-
-	return (dma_addr_t)__virt_to_bus((unsigned long)(addr));
-}
-
-#else
-static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
-{
-	return __arch_pfn_to_dma(dev, pfn);
-}
-
-static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
-{
-	return __arch_dma_to_pfn(dev, addr);
-}
-
-static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
-{
-	return __arch_virt_to_dma(dev, addr);
-}
-#endif
-
 /**
  * arm_dma_alloc - allocate consistent memory for DMA
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
-- 
2.28.0


^ permalink raw reply	[flat|nested] 15+ messages in thread

* [PATCH 4/6] ARM/keystone: move the DMA offset handling under ifdef CONFIG_ARM_LPAE
  2020-09-16  6:14 support range based offsets in dma-direct v3 Christoph Hellwig
                   ` (2 preceding siblings ...)
  2020-09-16  6:14 ` [PATCH 3/6] ARM/dma-mapping: move various helpers from dma-mapping.h to dma-direct.h Christoph Hellwig
@ 2020-09-16  6:14 ` Christoph Hellwig
  2020-09-16  6:14 ` [PATCH 5/6] usb: don't inherity DMA properties for USB devices Christoph Hellwig
                   ` (2 subsequent siblings)
  6 siblings, 0 replies; 15+ messages in thread
From: Christoph Hellwig @ 2020-09-16  6:14 UTC (permalink / raw)
  To: iommu, Russell King, Santosh Shilimkar, Greg Kroah-Hartman
  Cc: Jim Quinlan, Nathan Chancellor, Florian Fainelli, Robin Murphy,
	Rob Herring, Frank Rowand, Ohad Ben-Cohen, Bjorn Andersson,
	linux-remoteproc, linux-usb, linux-arm-kernel, linux-kernel,
	linux-sh, linux-pci, linux-acpi, devicetree

The DMA offset notifier can only be used if PHYS_OFFSET is at least
KEYSTONE_HIGH_PHYS_START, which can't be represented by a 32-bit
phys_addr_t.  Currently the code compiles fine despite that, a pending
change to the DMA offset handling would create a compiler warning for
this case.  Add an ifdef to not compile the code except for LPAE
configs.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
---
 arch/arm/mach-keystone/keystone.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/arm/mach-keystone/keystone.c b/arch/arm/mach-keystone/keystone.c
index 638808c4e12247..dcd031ba84c2e0 100644
--- a/arch/arm/mach-keystone/keystone.c
+++ b/arch/arm/mach-keystone/keystone.c
@@ -24,6 +24,7 @@
 
 #include "keystone.h"
 
+#ifdef CONFIG_ARM_LPAE
 static unsigned long keystone_dma_pfn_offset __read_mostly;
 
 static int keystone_platform_notifier(struct notifier_block *nb,
@@ -48,14 +49,17 @@ static int keystone_platform_notifier(struct notifier_block *nb,
 static struct notifier_block platform_nb = {
 	.notifier_call = keystone_platform_notifier,
 };
+#endif /* CONFIG_ARM_LPAE */
 
 static void __init keystone_init(void)
 {
+#ifdef CONFIG_ARM_LPAE
 	if (PHYS_OFFSET >= KEYSTONE_HIGH_PHYS_START) {
 		keystone_dma_pfn_offset = PFN_DOWN(KEYSTONE_HIGH_PHYS_START -
 						   KEYSTONE_LOW_PHYS_START);
 		bus_register_notifier(&platform_bus_type, &platform_nb);
 	}
+#endif
 	keystone_pm_runtime_init();
 }
 
-- 
2.28.0


^ permalink raw reply	[flat|nested] 15+ messages in thread

* [PATCH 5/6] usb: don't inherity DMA properties for USB devices
  2020-09-16  6:14 support range based offsets in dma-direct v3 Christoph Hellwig
                   ` (3 preceding siblings ...)
  2020-09-16  6:14 ` [PATCH 4/6] ARM/keystone: move the DMA offset handling under ifdef CONFIG_ARM_LPAE Christoph Hellwig
@ 2020-09-16  6:14 ` Christoph Hellwig
  2020-09-16  6:14 ` [PATCH 6/6] dma-mapping: introduce DMA range map, supplanting dma_pfn_offset Christoph Hellwig
  2020-09-17 16:45 ` support range based offsets in dma-direct v3 Christoph Hellwig
  6 siblings, 0 replies; 15+ messages in thread
From: Christoph Hellwig @ 2020-09-16  6:14 UTC (permalink / raw)
  To: iommu, Russell King, Santosh Shilimkar, Greg Kroah-Hartman
  Cc: Jim Quinlan, Nathan Chancellor, Florian Fainelli, Robin Murphy,
	Rob Herring, Frank Rowand, Ohad Ben-Cohen, Bjorn Andersson,
	linux-remoteproc, linux-usb, linux-arm-kernel, linux-kernel,
	linux-sh, linux-pci, linux-acpi, devicetree

As the comment in usb_alloc_dev correctly states, drivers can't use
the DMA API on usb device, and at least calling dma_set_mask on them
is highly dangerous.  Unlike what the comment states upper level drivers
also can't really use the presence of a dma mask to check for DMA
support, as the dma_mask is set by default for most busses.

Setting the dma_mask comes from "[PATCH] usbcore dma updates (and doc)"
in BitKeeper times, as it seems like it was primarily for setting the
NETIF_F_HIGHDMA flag in USB drivers, something that has long been
fixed up since.

Setting the dma_pfn_offset comes from commit b44bbc46a8bb
("usb: core: setup dma_pfn_offset for USB devices and, interfaces"),
which worked around the fact that the scsi_calculate_bounce_limits
functions wasn't going through the proper driver interface to query
DMA information, but that function was removed in commit 21e07dba9fb1
("scsi: reduce use of block bounce buffers") years ago.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/message.c |  6 ------
 drivers/usb/core/usb.c     | 12 ------------
 2 files changed, 18 deletions(-)

diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index 6197938dcc2d8f..9e45732dc1d1d1 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -1954,12 +1954,6 @@ int usb_set_configuration(struct usb_device *dev, int configuration)
 		intf->dev.bus = &usb_bus_type;
 		intf->dev.type = &usb_if_device_type;
 		intf->dev.groups = usb_interface_groups;
-		/*
-		 * Please refer to usb_alloc_dev() to see why we set
-		 * dma_mask and dma_pfn_offset.
-		 */
-		intf->dev.dma_mask = dev->dev.dma_mask;
-		intf->dev.dma_pfn_offset = dev->dev.dma_pfn_offset;
 		INIT_WORK(&intf->reset_ws, __usb_queue_reset_device);
 		intf->minor = -1;
 		device_initialize(&intf->dev);
diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c
index bafc113f2b3ef3..9b4ac4415f1a47 100644
--- a/drivers/usb/core/usb.c
+++ b/drivers/usb/core/usb.c
@@ -599,18 +599,6 @@ struct usb_device *usb_alloc_dev(struct usb_device *parent,
 	dev->dev.bus = &usb_bus_type;
 	dev->dev.type = &usb_device_type;
 	dev->dev.groups = usb_device_groups;
-	/*
-	 * Fake a dma_mask/offset for the USB device:
-	 * We cannot really use the dma-mapping API (dma_alloc_* and
-	 * dma_map_*) for USB devices but instead need to use
-	 * usb_alloc_coherent and pass data in 'urb's, but some subsystems
-	 * manually look into the mask/offset pair to determine whether
-	 * they need bounce buffers.
-	 * Note: calling dma_set_mask() on a USB device would set the
-	 * mask for the entire HCD, so don't do that.
-	 */
-	dev->dev.dma_mask = bus->sysdev->dma_mask;
-	dev->dev.dma_pfn_offset = bus->sysdev->dma_pfn_offset;
 	set_dev_node(&dev->dev, dev_to_node(bus->sysdev));
 	dev->state = USB_STATE_ATTACHED;
 	dev->lpm_disable_count = 1;
-- 
2.28.0


^ permalink raw reply	[flat|nested] 15+ messages in thread

* [PATCH 6/6] dma-mapping: introduce DMA range map, supplanting dma_pfn_offset
  2020-09-16  6:14 support range based offsets in dma-direct v3 Christoph Hellwig
                   ` (4 preceding siblings ...)
  2020-09-16  6:14 ` [PATCH 5/6] usb: don't inherity DMA properties for USB devices Christoph Hellwig
@ 2020-09-16  6:14 ` Christoph Hellwig
  2020-09-16 17:36   ` Mathieu Poirier
  2020-10-26 15:33   ` Geert Uytterhoeven
  2020-09-17 16:45 ` support range based offsets in dma-direct v3 Christoph Hellwig
  6 siblings, 2 replies; 15+ messages in thread
From: Christoph Hellwig @ 2020-09-16  6:14 UTC (permalink / raw)
  To: iommu, Russell King, Santosh Shilimkar, Greg Kroah-Hartman
  Cc: Jim Quinlan, Nathan Chancellor, Florian Fainelli, Robin Murphy,
	Rob Herring, Frank Rowand, Ohad Ben-Cohen, Bjorn Andersson,
	linux-remoteproc, linux-usb, linux-arm-kernel, linux-kernel,
	linux-sh, linux-pci, linux-acpi, devicetree

From: Jim Quinlan <james.quinlan@broadcom.com>

The new field 'dma_range_map' in struct device is used to facilitate the
use of single or multiple offsets between mapping regions of cpu addrs and
dma addrs.  It subsumes the role of "dev->dma_pfn_offset" which was only
capable of holding a single uniform offset and had no region bounds
checking.

The function of_dma_get_range() has been modified so that it takes a single
argument -- the device node -- and returns a map, NULL, or an error code.
The map is an array that holds the information regarding the DMA regions.
Each range entry contains the address offset, the cpu_start address, the
dma_start address, and the size of the region.

of_dma_configure() is the typical manner to set range offsets but there are
a number of ad hoc assignments to "dev->dma_pfn_offset" in the kernel
driver code.  These cases now invoke the function
dma_direct_set_offset(dev, cpu_addr, dma_addr, size).

Signed-off-by: Jim Quinlan <james.quinlan@broadcom.com>
[hch: various interface cleanups]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Nathan Chancellor <natechancellor@gmail.com>
---
 arch/arm/include/asm/dma-direct.h             |  9 +--
 arch/arm/mach-keystone/keystone.c             | 17 ++---
 arch/arm/mach-omap1/include/mach/memory.h     |  4 +
 arch/sh/drivers/pci/pcie-sh7786.c             |  9 ++-
 arch/x86/pci/sta2x11-fixup.c                  |  6 +-
 drivers/acpi/arm64/iort.c                     |  6 +-
 drivers/base/core.c                           |  2 +
 drivers/gpu/drm/sun4i/sun4i_backend.c         |  8 +-
 drivers/iommu/io-pgtable-arm.c                |  2 +-
 .../platform/sunxi/sun4i-csi/sun4i_csi.c      |  9 ++-
 .../platform/sunxi/sun6i-csi/sun6i_csi.c      | 11 ++-
 drivers/of/address.c                          | 73 ++++++++-----------
 drivers/of/device.c                           | 44 ++++++-----
 drivers/of/of_private.h                       | 11 +--
 drivers/of/unittest.c                         | 34 ++++++---
 drivers/remoteproc/remoteproc_core.c          | 24 +++++-
 .../staging/media/sunxi/cedrus/cedrus_hw.c    | 10 ++-
 include/linux/device.h                        |  4 +-
 include/linux/dma-direct.h                    | 54 ++++++++++++--
 include/linux/dma-mapping.h                   |  9 ++-
 kernel/dma/coherent.c                         |  7 +-
 kernel/dma/direct.c                           | 51 ++++++++++++-
 22 files changed, 285 insertions(+), 119 deletions(-)

diff --git a/arch/arm/include/asm/dma-direct.h b/arch/arm/include/asm/dma-direct.h
index fbcf4367b5cb1a..436544aeb83405 100644
--- a/arch/arm/include/asm/dma-direct.h
+++ b/arch/arm/include/asm/dma-direct.h
@@ -12,8 +12,8 @@
 #ifndef __arch_pfn_to_dma
 static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
 {
-	if (dev)
-		pfn -= dev->dma_pfn_offset;
+	if (dev && dev->dma_range_map)
+		pfn = PFN_DOWN(translate_phys_to_dma(dev, PFN_PHYS(pfn)));
 	return (dma_addr_t)__pfn_to_bus(pfn);
 }
 
@@ -21,9 +21,8 @@ static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
 {
 	unsigned long pfn = __bus_to_pfn(addr);
 
-	if (dev)
-		pfn += dev->dma_pfn_offset;
-
+	if (dev && dev->dma_range_map)
+		pfn = PFN_DOWN(translate_dma_to_phys(dev, PFN_PHYS(pfn)));
 	return pfn;
 }
 
diff --git a/arch/arm/mach-keystone/keystone.c b/arch/arm/mach-keystone/keystone.c
index dcd031ba84c2e0..09a65c2dfd7327 100644
--- a/arch/arm/mach-keystone/keystone.c
+++ b/arch/arm/mach-keystone/keystone.c
@@ -8,6 +8,7 @@
  */
 #include <linux/io.h>
 #include <linux/of.h>
+#include <linux/dma-mapping.h>
 #include <linux/init.h>
 #include <linux/of_platform.h>
 #include <linux/of_address.h>
@@ -25,8 +26,6 @@
 #include "keystone.h"
 
 #ifdef CONFIG_ARM_LPAE
-static unsigned long keystone_dma_pfn_offset __read_mostly;
-
 static int keystone_platform_notifier(struct notifier_block *nb,
 				      unsigned long event, void *data)
 {
@@ -39,9 +38,12 @@ static int keystone_platform_notifier(struct notifier_block *nb,
 		return NOTIFY_BAD;
 
 	if (!dev->of_node) {
-		dev->dma_pfn_offset = keystone_dma_pfn_offset;
-		dev_err(dev, "set dma_pfn_offset%08lx\n",
-			dev->dma_pfn_offset);
+		int ret = dma_direct_set_offset(dev, KEYSTONE_HIGH_PHYS_START,
+						KEYSTONE_LOW_PHYS_START,
+						KEYSTONE_HIGH_PHYS_SIZE);
+		dev_err(dev, "set dma_offset%08llx%s\n",
+			KEYSTONE_HIGH_PHYS_START - KEYSTONE_LOW_PHYS_START,
+			ret ? " failed" : "");
 	}
 	return NOTIFY_OK;
 }
@@ -54,11 +56,8 @@ static struct notifier_block platform_nb = {
 static void __init keystone_init(void)
 {
 #ifdef CONFIG_ARM_LPAE
-	if (PHYS_OFFSET >= KEYSTONE_HIGH_PHYS_START) {
-		keystone_dma_pfn_offset = PFN_DOWN(KEYSTONE_HIGH_PHYS_START -
-						   KEYSTONE_LOW_PHYS_START);
+	if (PHYS_OFFSET >= KEYSTONE_HIGH_PHYS_START)
 		bus_register_notifier(&platform_bus_type, &platform_nb);
-	}
 #endif
 	keystone_pm_runtime_init();
 }
diff --git a/arch/arm/mach-omap1/include/mach/memory.h b/arch/arm/mach-omap1/include/mach/memory.h
index e43697c3297bf2..1142560e0078f5 100644
--- a/arch/arm/mach-omap1/include/mach/memory.h
+++ b/arch/arm/mach-omap1/include/mach/memory.h
@@ -41,6 +41,10 @@
 	   __phys_to_pfn(__dma);				\
 	})
 
+#define __arch_dma_to_virt(dev, addr)	({ (void *) (is_lbus_device(dev) ? \
+						lbus_to_virt(addr) : \
+						__phys_to_virt(addr)); })
+
 #define __arch_virt_to_dma(dev, addr)	({ unsigned long __addr = (unsigned long)(addr); \
 					   (dma_addr_t) (is_lbus_device(dev) ? \
 						virt_to_lbus(__addr) : \
diff --git a/arch/sh/drivers/pci/pcie-sh7786.c b/arch/sh/drivers/pci/pcie-sh7786.c
index e0b568aaa7014c..4468289ab2cac7 100644
--- a/arch/sh/drivers/pci/pcie-sh7786.c
+++ b/arch/sh/drivers/pci/pcie-sh7786.c
@@ -12,6 +12,7 @@
 #include <linux/io.h>
 #include <linux/async.h>
 #include <linux/delay.h>
+#include <linux/dma-mapping.h>
 #include <linux/slab.h>
 #include <linux/clk.h>
 #include <linux/sh_clk.h>
@@ -31,6 +32,8 @@ struct sh7786_pcie_port {
 static struct sh7786_pcie_port *sh7786_pcie_ports;
 static unsigned int nr_ports;
 static unsigned long dma_pfn_offset;
+size_t memsize;
+u64 memstart;
 
 static struct sh7786_pcie_hwops {
 	int (*core_init)(void);
@@ -301,7 +304,6 @@ static int __init pcie_init(struct sh7786_pcie_port *port)
 	struct pci_channel *chan = port->hose;
 	unsigned int data;
 	phys_addr_t memstart, memend;
-	size_t memsize;
 	int ret, i, win;
 
 	/* Begin initialization */
@@ -368,8 +370,6 @@ static int __init pcie_init(struct sh7786_pcie_port *port)
 	memstart = ALIGN_DOWN(memstart, memsize);
 	memsize = roundup_pow_of_two(memend - memstart);
 
-	dma_pfn_offset = memstart >> PAGE_SHIFT;
-
 	/*
 	 * If there's more than 512MB of memory, we need to roll over to
 	 * LAR1/LAMR1.
@@ -487,7 +487,8 @@ int pcibios_map_platform_irq(const struct pci_dev *pdev, u8 slot, u8 pin)
 
 void pcibios_bus_add_device(struct pci_dev *pdev)
 {
-	pdev->dev.dma_pfn_offset = dma_pfn_offset;
+	dma_direct_set_offset(&pdev->dev, __pa(memory_start),
+			      __pa(memory_start) - memstart, memsize);
 }
 
 static int __init sh7786_pcie_core_init(void)
diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
index c313d784efabb9..324a207f99956b 100644
--- a/arch/x86/pci/sta2x11-fixup.c
+++ b/arch/x86/pci/sta2x11-fixup.c
@@ -133,7 +133,7 @@ static void sta2x11_map_ep(struct pci_dev *pdev)
 	struct sta2x11_instance *instance = sta2x11_pdev_to_instance(pdev);
 	struct device *dev = &pdev->dev;
 	u32 amba_base, max_amba_addr;
-	int i;
+	int i, ret;
 
 	if (!instance)
 		return;
@@ -141,7 +141,9 @@ static void sta2x11_map_ep(struct pci_dev *pdev)
 	pci_read_config_dword(pdev, AHB_BASE(0), &amba_base);
 	max_amba_addr = amba_base + STA2X11_AMBA_SIZE - 1;
 
-	dev->dma_pfn_offset = PFN_DOWN(-amba_base);
+	ret = dma_direct_set_offset(dev, 0, amba_base, STA2X11_AMBA_SIZE);
+	if (ret)
+		dev_err(dev, "sta2x11: could not set DMA offset\n");
 
 	dev->bus_dma_limit = max_amba_addr;
 	pci_set_consistent_dma_mask(pdev, max_amba_addr);
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index ec782e4a0fe419..de18c07ca02cc4 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -18,6 +18,7 @@
 #include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
+#include <linux/dma-mapping.h>
 
 #define IORT_TYPE_MASK(type)	(1 << (type))
 #define IORT_MSI_TYPE		(1 << ACPI_IORT_NODE_ITS_GROUP)
@@ -1184,8 +1185,9 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size)
 	*dma_addr = dmaaddr;
 	*dma_size = size;
 
-	dev->dma_pfn_offset = PFN_DOWN(offset);
-	dev_dbg(dev, "dma_pfn_offset(%#08llx)\n", offset);
+	ret = dma_direct_set_offset(dev, dmaaddr + offset, dmaaddr, size);
+
+	dev_dbg(dev, "dma_offset(%#08llx)%s\n", offset, ret ? " failed!" : "");
 }
 
 static void __init acpi_iort_register_irq(int hwirq, const char *name,
diff --git a/drivers/base/core.c b/drivers/base/core.c
index f6f620aa94086d..b893056e39459c 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -1792,6 +1792,8 @@ static void device_release(struct kobject *kobj)
 	 */
 	devres_release_all(dev);
 
+	kfree(dev->dma_range_map);
+
 	if (dev->release)
 		dev->release(dev);
 	else if (dev->type && dev->type->release)
diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c
index 072ea113e6be55..05e9f0d28196d9 100644
--- a/drivers/gpu/drm/sun4i/sun4i_backend.c
+++ b/drivers/gpu/drm/sun4i/sun4i_backend.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/of_device.h>
 #include <linux/of_graph.h>
+#include <linux/dma-mapping.h>
 #include <linux/platform_device.h>
 #include <linux/reset.h>
 
@@ -811,8 +812,13 @@ static int sun4i_backend_bind(struct device *dev, struct device *master,
 		 * because of an old DT, we need to set the DMA offset by hand
 		 * on our device since the RAM mapping is at 0 for the DMA bus,
 		 * unlike the CPU.
+		 *
+		 * XXX(hch): this has no business in a driver and needs to move
+		 * to the device tree.
 		 */
-		drm->dev->dma_pfn_offset = PHYS_PFN_OFFSET;
+		ret = dma_direct_set_offset(drm->dev, PHYS_OFFSET, 0, SZ_4G);
+		if (ret)
+			return ret;
 	}
 
 	backend->engine.node = dev->of_node;
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index dc7bcf858b6d2d..d77e881516a4ab 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -751,7 +751,7 @@ arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg)
 	if (cfg->oas > ARM_LPAE_MAX_ADDR_BITS)
 		return NULL;
 
-	if (!selftest_running && cfg->iommu_dev->dma_pfn_offset) {
+	if (!selftest_running && cfg->iommu_dev->dma_range_map) {
 		dev_err(cfg->iommu_dev, "Cannot accommodate DMA offset for IOMMU page tables\n");
 		return NULL;
 	}
diff --git a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
index 5319eb1ab30927..307997ee7f96a2 100644
--- a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
+++ b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/clk.h>
+#include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
@@ -182,8 +183,14 @@ static int sun4i_csi_probe(struct platform_device *pdev)
 		if (ret)
 			return ret;
 	} else {
+		/*
+		 * XXX(hch): this has no business in a driver and needs to move
+		 * to the device tree.
+		 */
 #ifdef PHYS_PFN_OFFSET
-		csi->dev->dma_pfn_offset = PHYS_PFN_OFFSET;
+		ret = dma_direct_set_offset(csi->dev, PHYS_OFFSET, 0, SZ_4G);
+		if (ret)
+			return ret;
 #endif
 	}
 
diff --git a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c
index 28e89340fed981..e69e14379fc6e4 100644
--- a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c
+++ b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c
@@ -899,8 +899,15 @@ static int sun6i_csi_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	sdev->dev = &pdev->dev;
-	/* The DMA bus has the memory mapped at 0 */
-	sdev->dev->dma_pfn_offset = PHYS_OFFSET >> PAGE_SHIFT;
+	/*
+	 * The DMA bus has the memory mapped at 0.
+	 *
+	 * XXX(hch): this has no business in a driver and needs to move
+	 * to the device tree.
+	 */
+	ret = dma_direct_set_offset(sdev->dev, PHYS_OFFSET, 0, SZ_4G);
+	if (ret)
+		return ret;
 
 	ret = sun6i_csi_resource_request(sdev, pdev);
 	if (ret)
diff --git a/drivers/of/address.c b/drivers/of/address.c
index da4f7341323f22..a49ef87aaaf21c 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -13,6 +13,7 @@
 #include <linux/sizes.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/dma-direct.h> /* for bus_dma_region */
 
 #include "of_private.h"
 
@@ -937,33 +938,33 @@ void __iomem *of_io_request_and_map(struct device_node *np, int index,
 }
 EXPORT_SYMBOL(of_io_request_and_map);
 
+#ifdef CONFIG_HAS_DMA
 /**
- * of_dma_get_range - Get DMA range info
+ * of_dma_get_range - Get DMA range info and put it into a map array
  * @np:		device node to get DMA range info
- * @dma_addr:	pointer to store initial DMA address of DMA range
- * @paddr:	pointer to store initial CPU address of DMA range
- * @size:	pointer to store size of DMA range
+ * @map:	dma range structure to return
  *
  * Look in bottom up direction for the first "dma-ranges" property
- * and parse it.
- *  dma-ranges format:
+ * and parse it.  Put the information into a DMA offset map array.
+ *
+ * dma-ranges format:
  *	DMA addr (dma_addr)	: naddr cells
  *	CPU addr (phys_addr_t)	: pna cells
  *	size			: nsize cells
  *
- * It returns -ENODEV if "dma-ranges" property was not found
- * for this device in DT.
+ * It returns -ENODEV if "dma-ranges" property was not found for this
+ * device in the DT.
  */
-int of_dma_get_range(struct device_node *np, u64 *dma_addr, u64 *paddr, u64 *size)
+int of_dma_get_range(struct device_node *np, const struct bus_dma_region **map)
 {
 	struct device_node *node = of_node_get(np);
 	const __be32 *ranges = NULL;
-	int len;
-	int ret = 0;
 	bool found_dma_ranges = false;
 	struct of_range_parser parser;
 	struct of_range range;
-	u64 dma_start = U64_MAX, dma_end = 0, dma_offset = 0;
+	struct bus_dma_region *r;
+	int len, num_ranges = 0;
+	int ret = 0;
 
 	while (node) {
 		ranges = of_get_property(node, "dma-ranges", &len);
@@ -989,49 +990,39 @@ int of_dma_get_range(struct device_node *np, u64 *dma_addr, u64 *paddr, u64 *siz
 	}
 
 	of_dma_range_parser_init(&parser, node);
+	for_each_of_range(&parser, &range)
+		num_ranges++;
+
+	r = kcalloc(num_ranges + 1, sizeof(*r), GFP_KERNEL);
+	if (!r) {
+		ret = -ENOMEM;
+ 		goto out;
+	}
 
+	/*
+	 * Record all info in the generic DMA ranges array for struct device.
+	 */
+	*map = r;
+ 	of_dma_range_parser_init(&parser, node);
 	for_each_of_range(&parser, &range) {
 		pr_debug("dma_addr(%llx) cpu_addr(%llx) size(%llx)\n",
 			 range.bus_addr, range.cpu_addr, range.size);
-
-		if (dma_offset && range.cpu_addr - range.bus_addr != dma_offset) {
-			pr_warn("Can't handle multiple dma-ranges with different offsets on node(%pOF)\n", node);
-			/* Don't error out as we'd break some existing DTs */
-			continue;
-		}
 		if (range.cpu_addr == OF_BAD_ADDR) {
 			pr_err("translation of DMA address(%llx) to CPU address failed node(%pOF)\n",
 			       range.bus_addr, node);
 			continue;
 		}
-		dma_offset = range.cpu_addr - range.bus_addr;
-
-		/* Take lower and upper limits */
-		if (range.bus_addr < dma_start)
-			dma_start = range.bus_addr;
-		if (range.bus_addr + range.size > dma_end)
-			dma_end = range.bus_addr + range.size;
-	}
-
-	if (dma_start >= dma_end) {
-		ret = -EINVAL;
-		pr_debug("Invalid DMA ranges configuration on node(%pOF)\n",
-			 node);
-		goto out;
+		r->cpu_start = range.cpu_addr;
+		r->dma_start = range.bus_addr;
+		r->size = range.size;
+		r->offset = range.cpu_addr - range.bus_addr;
+		r++;
 	}
-
-	*dma_addr = dma_start;
-	*size = dma_end - dma_start;
-	*paddr = dma_start + dma_offset;
-
-	pr_debug("final: dma_addr(%llx) cpu_addr(%llx) size(%llx)\n",
-		 *dma_addr, *paddr, *size);
-
 out:
 	of_node_put(node);
-
 	return ret;
 }
+#endif /* CONFIG_HAS_DMA */
 
 /**
  * of_dma_is_coherent - Check if device is coherent
diff --git a/drivers/of/device.c b/drivers/of/device.c
index b439c1e054349b..6e3ae7ebc33eeb 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -5,7 +5,7 @@
 #include <linux/of_device.h>
 #include <linux/of_address.h>
 #include <linux/of_iommu.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-direct.h> /* for bus_dma_region */
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mod_devicetable.h>
@@ -90,14 +90,14 @@ int of_device_add(struct platform_device *ofdev)
 int of_dma_configure_id(struct device *dev, struct device_node *np,
 			bool force_dma, const u32 *id)
 {
-	u64 dma_addr, paddr, size = 0;
-	int ret;
-	bool coherent;
-	unsigned long offset;
 	const struct iommu_ops *iommu;
-	u64 mask, end;
+	const struct bus_dma_region *map = NULL;
+	dma_addr_t dma_start = 0;
+	u64 mask, end, size = 0;
+	bool coherent;
+	int ret;
 
-	ret = of_dma_get_range(np, &dma_addr, &paddr, &size);
+	ret = of_dma_get_range(np, &map);
 	if (ret < 0) {
 		/*
 		 * For legacy reasons, we have to assume some devices need
@@ -106,26 +106,35 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
 		 */
 		if (!force_dma)
 			return ret == -ENODEV ? 0 : ret;
-
-		dma_addr = offset = 0;
 	} else {
-		offset = PFN_DOWN(paddr - dma_addr);
+		const struct bus_dma_region *r = map;
+		dma_addr_t dma_end = 0;
+
+		/* Determine the overall bounds of all DMA regions */
+		for (dma_start = ~(dma_addr_t)0; r->size; r++) {
+			/* Take lower and upper limits */
+			if (r->dma_start < dma_start)
+				dma_start = r->dma_start;
+			if (r->dma_start + r->size > dma_end)
+				dma_end = r->dma_start + r->size;
+		}
+		size = dma_end - dma_start;
 
 		/*
 		 * Add a work around to treat the size as mask + 1 in case
 		 * it is defined in DT as a mask.
 		 */
 		if (size & 1) {
-			dev_warn(dev, "Invalid size 0x%llx for dma-range\n",
+			dev_warn(dev, "Invalid size 0x%llx for dma-range(s)\n",
 				 size);
 			size = size + 1;
 		}
 
 		if (!size) {
 			dev_err(dev, "Adjusted size 0x%llx invalid\n", size);
+			kfree(map);
 			return -EINVAL;
 		}
-		dev_dbg(dev, "dma_pfn_offset(%#08lx)\n", offset);
 	}
 
 	/*
@@ -144,13 +153,11 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
 	else if (!size)
 		size = 1ULL << 32;
 
-	dev->dma_pfn_offset = offset;
-
 	/*
 	 * Limit coherent and dma mask based on size and default mask
 	 * set by the driver.
 	 */
-	end = dma_addr + size - 1;
+	end = dma_start + size - 1;
 	mask = DMA_BIT_MASK(ilog2(end) + 1);
 	dev->coherent_dma_mask &= mask;
 	*dev->dma_mask &= mask;
@@ -163,14 +170,17 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
 		coherent ? " " : " not ");
 
 	iommu = of_iommu_configure(dev, np, id);
-	if (PTR_ERR(iommu) == -EPROBE_DEFER)
+	if (PTR_ERR(iommu) == -EPROBE_DEFER) {
+		kfree(map);
 		return -EPROBE_DEFER;
+	}
 
 	dev_dbg(dev, "device is%sbehind an iommu\n",
 		iommu ? " " : " not ");
 
-	arch_setup_dma_ops(dev, dma_addr, size, iommu, coherent);
+	arch_setup_dma_ops(dev, dma_start, size, iommu, coherent);
 
+	dev->dma_range_map = map;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(of_dma_configure_id);
diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h
index edc682249c0015..d9e6a324de0a77 100644
--- a/drivers/of/of_private.h
+++ b/drivers/of/of_private.h
@@ -157,12 +157,13 @@ extern void __of_sysfs_remove_bin_file(struct device_node *np,
 extern int of_bus_n_addr_cells(struct device_node *np);
 extern int of_bus_n_size_cells(struct device_node *np);
 
-#ifdef CONFIG_OF_ADDRESS
-extern int of_dma_get_range(struct device_node *np, u64 *dma_addr,
-			    u64 *paddr, u64 *size);
+struct bus_dma_region;
+#if defined(CONFIG_OF_ADDRESS) && defined(CONFIG_HAS_DMA)
+int of_dma_get_range(struct device_node *np,
+		const struct bus_dma_region **map);
 #else
-static inline int of_dma_get_range(struct device_node *np, u64 *dma_addr,
-				   u64 *paddr, u64 *size)
+static inline int of_dma_get_range(struct device_node *np,
+		const struct bus_dma_region **map)
 {
 	return -ENODEV;
 }
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index 9b7e84bdc7d446..06cc988faf78b3 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -7,6 +7,7 @@
 
 #include <linux/memblock.h>
 #include <linux/clk.h>
+#include <linux/dma-direct.h> /* to test phys_to_dma/dma_to_phys */
 #include <linux/err.h>
 #include <linux/errno.h>
 #include <linux/hashtable.h>
@@ -869,10 +870,11 @@ static void __init of_unittest_changeset(void)
 }
 
 static void __init of_unittest_dma_ranges_one(const char *path,
-		u64 expect_dma_addr, u64 expect_paddr, u64 expect_size)
+		u64 expect_dma_addr, u64 expect_paddr)
 {
+#ifdef CONFIG_HAS_DMA
 	struct device_node *np;
-	u64 dma_addr, paddr, size;
+	const struct bus_dma_region *map = NULL;
 	int rc;
 
 	np = of_find_node_by_path(path);
@@ -881,28 +883,40 @@ static void __init of_unittest_dma_ranges_one(const char *path,
 		return;
 	}
 
-	rc = of_dma_get_range(np, &dma_addr, &paddr, &size);
+	rc = of_dma_get_range(np, &map);
 
 	unittest(!rc, "of_dma_get_range failed on node %pOF rc=%i\n", np, rc);
+
 	if (!rc) {
-		unittest(size == expect_size,
-			 "of_dma_get_range wrong size on node %pOF size=%llx\n", np, size);
+		phys_addr_t	paddr;
+		dma_addr_t	dma_addr;
+		struct device	dev_bogus;
+
+		dev_bogus.dma_range_map = map;
+		paddr = dma_to_phys(&dev_bogus, expect_dma_addr);
+		dma_addr = phys_to_dma(&dev_bogus, expect_paddr);
+
 		unittest(paddr == expect_paddr,
-			 "of_dma_get_range wrong phys addr (%llx) on node %pOF", paddr, np);
+			 "of_dma_get_range: wrong phys addr %pap (expecting %llx) on node %pOF\n",
+			 &paddr, expect_paddr, np);
 		unittest(dma_addr == expect_dma_addr,
-			 "of_dma_get_range wrong DMA addr (%llx) on node %pOF", dma_addr, np);
+			 "of_dma_get_range: wrong DMA addr %pad (expecting %llx) on node %pOF\n",
+			 &dma_addr, expect_dma_addr, np);
+
+		kfree(map);
 	}
 	of_node_put(np);
+#endif
 }
 
 static void __init of_unittest_parse_dma_ranges(void)
 {
 	of_unittest_dma_ranges_one("/testcase-data/address-tests/device@70000000",
-		0x0, 0x20000000, 0x40000000);
+		0x0, 0x20000000);
 	of_unittest_dma_ranges_one("/testcase-data/address-tests/bus@80000000/device@1000",
-		0x100000000, 0x20000000, 0x2000000000);
+		0x100000000, 0x20000000);
 	of_unittest_dma_ranges_one("/testcase-data/address-tests/pci@90000000",
-		0x80000000, 0x20000000, 0x10000000);
+		0x80000000, 0x20000000);
 }
 
 static void __init of_unittest_pci_dma_ranges(void)
diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index 7f90eeea67e279..8157dd491d2819 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -23,6 +23,7 @@
 #include <linux/slab.h>
 #include <linux/mutex.h>
 #include <linux/dma-mapping.h>
+#include <linux/dma-direct.h> /* XXX: pokes into bus_dma_range */
 #include <linux/firmware.h>
 #include <linux/string.h>
 #include <linux/debugfs.h>
@@ -458,6 +459,25 @@ static void rproc_rvdev_release(struct device *dev)
 	kfree(rvdev);
 }
 
+static int copy_dma_range_map(struct device *to, struct device *from)
+{
+	const struct bus_dma_region *map = from->dma_range_map, *new_map, *r;
+	int num_ranges = 0;
+
+	if (!map)
+		return 0;
+
+	for (r = map; r->size; r++)
+		num_ranges++;
+
+	new_map = kmemdup(map, array_size(num_ranges + 1, sizeof(*map)),
+			  GFP_KERNEL);
+	if (!new_map)
+		return -ENOMEM;
+	to->dma_range_map = new_map;
+	return 0;
+}
+
 /**
  * rproc_handle_vdev() - handle a vdev fw resource
  * @rproc: the remote processor
@@ -529,7 +549,9 @@ static int rproc_handle_vdev(struct rproc *rproc, struct fw_rsc_vdev *rsc,
 	/* Initialise vdev subdevice */
 	snprintf(name, sizeof(name), "vdev%dbuffer", rvdev->index);
 	rvdev->dev.parent = &rproc->dev;
-	rvdev->dev.dma_pfn_offset = rproc->dev.parent->dma_pfn_offset;
+	ret = copy_dma_range_map(&rvdev->dev, rproc->dev.parent);
+	if (ret)
+		return ret;
 	rvdev->dev.release = rproc_rvdev_release;
 	dev_set_name(&rvdev->dev, "%s#%s", dev_name(rvdev->dev.parent), name);
 	dev_set_drvdata(&rvdev->dev, rvdev);
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_hw.c b/drivers/staging/media/sunxi/cedrus/cedrus_hw.c
index 1744e6fcc99980..bcf050a04ffc45 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_hw.c
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_hw.c
@@ -227,11 +227,17 @@ int cedrus_hw_probe(struct cedrus_dev *dev)
 	 * the RAM offset to the physcal addresses.
 	 *
 	 * This information will eventually be obtained from device-tree.
+	 *
+	 * XXX(hch): this has no business in a driver and needs to move
+	 * to the device tree.
 	 */
 
 #ifdef PHYS_PFN_OFFSET
-	if (!(variant->quirks & CEDRUS_QUIRK_NO_DMA_OFFSET))
-		dev->dev->dma_pfn_offset = PHYS_PFN_OFFSET;
+	if (!(variant->quirks & CEDRUS_QUIRK_NO_DMA_OFFSET)) {
+		ret = dma_direct_set_offset(dev->dev, PHYS_OFFSET, 0, SZ_4G);
+		if (ret)
+			return ret;
+	}
 #endif
 
 	ret = of_reserved_mem_device_init(dev->dev);
diff --git a/include/linux/device.h b/include/linux/device.h
index ca18da4768e3e8..1c78621fc3c01f 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -466,7 +466,7 @@ struct dev_links_info {
  * 		such descriptors.
  * @bus_dma_limit: Limit of an upstream bridge or bus which imposes a smaller
  *		DMA limit than the device itself supports.
- * @dma_pfn_offset: offset of DMA memory range relatively of RAM
+ * @dma_range_map: map for DMA memory ranges relative to that of RAM
  * @dma_parms:	A low level driver may set these to teach IOMMU code about
  * 		segment limitations.
  * @dma_pools:	Dma pools (if dma'ble device).
@@ -561,7 +561,7 @@ struct device {
 					     64 bit addresses for consistent
 					     allocations such descriptors. */
 	u64		bus_dma_limit;	/* upstream dma constraint */
-	unsigned long	dma_pfn_offset;
+	const struct bus_dma_region *dma_range_map;
 
 	struct device_dma_parameters *dma_parms;
 
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 805010ea5346f9..c6b21acba7a459 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -14,6 +14,41 @@
 
 extern unsigned int zone_dma_bits;
 
+/*
+ * Record the mapping of CPU physical to DMA addresses for a given region.
+ */
+struct bus_dma_region {
+	phys_addr_t	cpu_start;
+	dma_addr_t	dma_start;
+	u64		size;
+	u64		offset;
+};
+
+static inline dma_addr_t translate_phys_to_dma(struct device *dev,
+		phys_addr_t paddr)
+{
+	const struct bus_dma_region *m;
+
+	for (m = dev->dma_range_map; m->size; m++)
+		if (paddr >= m->cpu_start && paddr - m->cpu_start < m->size)
+			return (dma_addr_t)paddr - m->offset;
+
+	/* make sure dma_capable fails when no translation is available */
+	return DMA_MAPPING_ERROR; 
+}
+
+static inline phys_addr_t translate_dma_to_phys(struct device *dev,
+		dma_addr_t dma_addr)
+{
+	const struct bus_dma_region *m;
+
+	for (m = dev->dma_range_map; m->size; m++)
+		if (dma_addr >= m->dma_start && dma_addr - m->dma_start < m->size)
+			return (phys_addr_t)dma_addr + m->offset;
+
+	return (phys_addr_t)-1;
+}
+
 #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA
 #include <asm/dma-direct.h>
 #ifndef phys_to_dma_unencrypted
@@ -23,9 +58,9 @@ extern unsigned int zone_dma_bits;
 static inline dma_addr_t phys_to_dma_unencrypted(struct device *dev,
 		phys_addr_t paddr)
 {
-	dma_addr_t dev_addr = (dma_addr_t)paddr;
-
-	return dev_addr - ((dma_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
+	if (dev->dma_range_map)
+		return translate_phys_to_dma(dev, paddr);
+	return paddr;
 }
 
 /*
@@ -39,10 +74,14 @@ static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return __sme_set(phys_to_dma_unencrypted(dev, paddr));
 }
 
-static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
-	phys_addr_t paddr = (phys_addr_t)dev_addr +
-		((phys_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
+	phys_addr_t paddr;
+
+	if (dev->dma_range_map)
+		paddr = translate_dma_to_phys(dev, dma_addr);
+	else
+		paddr = dma_addr;
 
 	return __sme_clr(paddr);
 }
@@ -64,7 +103,8 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size,
 
 	if (!dev->dma_mask)
 		return false;
-
+	if (addr == DMA_MAPPING_ERROR)
+		return false;
 	if (is_ram && !IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) &&
 	    min(addr, end) < phys_to_dma(dev, PFN_PHYS(min_low_pfn)))
 		return false;
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index df0bff2ea750e0..bb138ac6f5e63e 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -730,4 +730,11 @@ static inline int dma_mmap_wc(struct device *dev,
 #define dma_unmap_len_set(PTR, LEN_NAME, VAL)    do { } while (0)
 #endif
 
-#endif
+/*
+ * Legacy interface to set up the dma offset map.  Drivers really should not
+ * actually use it, but we have a few legacy cases left.
+ */
+int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
+		dma_addr_t dma_start, u64 size);
+
+#endif /* _LINUX_DMA_MAPPING_H */
diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c
index f85d14bbfcbe03..c0685196fb6d42 100644
--- a/kernel/dma/coherent.c
+++ b/kernel/dma/coherent.c
@@ -7,7 +7,7 @@
 #include <linux/slab.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-direct.h>
 
 struct dma_coherent_mem {
 	void		*virt_base;
@@ -32,9 +32,8 @@ static inline dma_addr_t dma_get_device_base(struct device *dev,
 					     struct dma_coherent_mem * mem)
 {
 	if (mem->use_dev_dma_pfn_offset)
-		return (mem->pfn_base - dev->dma_pfn_offset) << PAGE_SHIFT;
-	else
-		return mem->device_base;
+		return phys_to_dma(dev, PFN_PHYS(mem->pfn_base));
+	return mem->device_base;
 }
 
 static int dma_init_coherent_memory(phys_addr_t phys_addr,
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 54db9cfdaecc6d..750659f7447c4b 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -13,6 +13,7 @@
 #include <linux/pfn.h>
 #include <linux/vmalloc.h>
 #include <linux/set_memory.h>
+#include <linux/slab.h>
 
 /*
  * Most architectures use ZONE_DMA for the first 16 Megabytes, but some use it
@@ -66,8 +67,12 @@ static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 
 static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
 {
-	return phys_to_dma_direct(dev, phys) + size - 1 <=
-			min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
+	dma_addr_t dma_addr = phys_to_dma_direct(dev, phys);
+
+	if (dma_addr == DMA_MAPPING_ERROR)
+		return false;
+	return dma_addr + size - 1 <=
+		min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
 }
 
 /*
@@ -461,3 +466,45 @@ bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr)
 	return !dev_is_dma_coherent(dev) ||
 		is_swiotlb_buffer(dma_to_phys(dev, dma_addr));
 }
+
+/**
+ * dma_direct_set_offset - Assign scalar offset for a single DMA range.
+ * @dev:	device pointer; needed to "own" the alloced memory.
+ * @cpu_start:  beginning of memory region covered by this offset.
+ * @dma_start:  beginning of DMA/PCI region covered by this offset.
+ * @size:	size of the region.
+ *
+ * This is for the simple case of a uniform offset which cannot
+ * be discovered by "dma-ranges".
+ *
+ * It returns -ENOMEM if out of memory, -EINVAL if a map
+ * already exists, 0 otherwise.
+ *
+ * Note: any call to this from a driver is a bug.  The mapping needs
+ * to be described by the device tree or other firmware interfaces.
+ */
+int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
+			 dma_addr_t dma_start, u64 size)
+{
+	struct bus_dma_region *map;
+	u64 offset = (u64)cpu_start - (u64)dma_start;
+
+	if (dev->dma_range_map) {
+		dev_err(dev, "attempt to add DMA range to existing map\n");
+		return -EINVAL;
+	}
+
+	if (!offset)
+		return 0;
+
+	map = kcalloc(2, sizeof(*map), GFP_KERNEL);
+	if (!map)
+		return -ENOMEM;
+	map[0].cpu_start = cpu_start;
+	map[0].dma_start = dma_start;
+	map[0].offset = offset;
+	map[0].size = size;
+	dev->dma_range_map = map;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dma_direct_set_offset);
-- 
2.28.0


^ permalink raw reply	[flat|nested] 15+ messages in thread

* Re: [PATCH 6/6] dma-mapping: introduce DMA range map, supplanting dma_pfn_offset
  2020-09-16  6:14 ` [PATCH 6/6] dma-mapping: introduce DMA range map, supplanting dma_pfn_offset Christoph Hellwig
@ 2020-09-16 17:36   ` Mathieu Poirier
  2020-10-26 15:33   ` Geert Uytterhoeven
  1 sibling, 0 replies; 15+ messages in thread
From: Mathieu Poirier @ 2020-09-16 17:36 UTC (permalink / raw)
  To: Christoph Hellwig
  Cc: iommu, Russell King, Santosh Shilimkar, Greg Kroah-Hartman,
	Jim Quinlan, Nathan Chancellor, Florian Fainelli, Robin Murphy,
	Rob Herring, Frank Rowand, Ohad Ben-Cohen, Bjorn Andersson,
	linux-remoteproc, linux-usb, linux-arm-kernel, linux-kernel,
	linux-sh, linux-pci, linux-acpi, devicetree

On Wed, Sep 16, 2020 at 08:14:59AM +0200, Christoph Hellwig wrote:
> From: Jim Quinlan <james.quinlan@broadcom.com>
> 
> The new field 'dma_range_map' in struct device is used to facilitate the
> use of single or multiple offsets between mapping regions of cpu addrs and
> dma addrs.  It subsumes the role of "dev->dma_pfn_offset" which was only
> capable of holding a single uniform offset and had no region bounds
> checking.
> 
> The function of_dma_get_range() has been modified so that it takes a single
> argument -- the device node -- and returns a map, NULL, or an error code.
> The map is an array that holds the information regarding the DMA regions.
> Each range entry contains the address offset, the cpu_start address, the
> dma_start address, and the size of the region.
> 
> of_dma_configure() is the typical manner to set range offsets but there are
> a number of ad hoc assignments to "dev->dma_pfn_offset" in the kernel
> driver code.  These cases now invoke the function
> dma_direct_set_offset(dev, cpu_addr, dma_addr, size).
> 
> Signed-off-by: Jim Quinlan <james.quinlan@broadcom.com>
> [hch: various interface cleanups]
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> Tested-by: Nathan Chancellor <natechancellor@gmail.com>
> ---
>  arch/arm/include/asm/dma-direct.h             |  9 +--
>  arch/arm/mach-keystone/keystone.c             | 17 ++---
>  arch/arm/mach-omap1/include/mach/memory.h     |  4 +
>  arch/sh/drivers/pci/pcie-sh7786.c             |  9 ++-
>  arch/x86/pci/sta2x11-fixup.c                  |  6 +-
>  drivers/acpi/arm64/iort.c                     |  6 +-
>  drivers/base/core.c                           |  2 +
>  drivers/gpu/drm/sun4i/sun4i_backend.c         |  8 +-
>  drivers/iommu/io-pgtable-arm.c                |  2 +-
>  .../platform/sunxi/sun4i-csi/sun4i_csi.c      |  9 ++-
>  .../platform/sunxi/sun6i-csi/sun6i_csi.c      | 11 ++-
>  drivers/of/address.c                          | 73 ++++++++-----------
>  drivers/of/device.c                           | 44 ++++++-----
>  drivers/of/of_private.h                       | 11 +--
>  drivers/of/unittest.c                         | 34 ++++++---
>  drivers/remoteproc/remoteproc_core.c          | 24 +++++-
>  .../staging/media/sunxi/cedrus/cedrus_hw.c    | 10 ++-
>  include/linux/device.h                        |  4 +-
>  include/linux/dma-direct.h                    | 54 ++++++++++++--
>  include/linux/dma-mapping.h                   |  9 ++-
>  kernel/dma/coherent.c                         |  7 +-
>  kernel/dma/direct.c                           | 51 ++++++++++++-
>  22 files changed, 285 insertions(+), 119 deletions(-)
> 
> diff --git a/arch/arm/include/asm/dma-direct.h b/arch/arm/include/asm/dma-direct.h
> index fbcf4367b5cb1a..436544aeb83405 100644
> --- a/arch/arm/include/asm/dma-direct.h
> +++ b/arch/arm/include/asm/dma-direct.h
> @@ -12,8 +12,8 @@
>  #ifndef __arch_pfn_to_dma
>  static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
>  {
> -	if (dev)
> -		pfn -= dev->dma_pfn_offset;
> +	if (dev && dev->dma_range_map)
> +		pfn = PFN_DOWN(translate_phys_to_dma(dev, PFN_PHYS(pfn)));
>  	return (dma_addr_t)__pfn_to_bus(pfn);
>  }
>  
> @@ -21,9 +21,8 @@ static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
>  {
>  	unsigned long pfn = __bus_to_pfn(addr);
>  
> -	if (dev)
> -		pfn += dev->dma_pfn_offset;
> -
> +	if (dev && dev->dma_range_map)
> +		pfn = PFN_DOWN(translate_dma_to_phys(dev, PFN_PHYS(pfn)));
>  	return pfn;
>  }
>  
> diff --git a/arch/arm/mach-keystone/keystone.c b/arch/arm/mach-keystone/keystone.c
> index dcd031ba84c2e0..09a65c2dfd7327 100644
> --- a/arch/arm/mach-keystone/keystone.c
> +++ b/arch/arm/mach-keystone/keystone.c
> @@ -8,6 +8,7 @@
>   */
>  #include <linux/io.h>
>  #include <linux/of.h>
> +#include <linux/dma-mapping.h>
>  #include <linux/init.h>
>  #include <linux/of_platform.h>
>  #include <linux/of_address.h>
> @@ -25,8 +26,6 @@
>  #include "keystone.h"
>  
>  #ifdef CONFIG_ARM_LPAE
> -static unsigned long keystone_dma_pfn_offset __read_mostly;
> -
>  static int keystone_platform_notifier(struct notifier_block *nb,
>  				      unsigned long event, void *data)
>  {
> @@ -39,9 +38,12 @@ static int keystone_platform_notifier(struct notifier_block *nb,
>  		return NOTIFY_BAD;
>  
>  	if (!dev->of_node) {
> -		dev->dma_pfn_offset = keystone_dma_pfn_offset;
> -		dev_err(dev, "set dma_pfn_offset%08lx\n",
> -			dev->dma_pfn_offset);
> +		int ret = dma_direct_set_offset(dev, KEYSTONE_HIGH_PHYS_START,
> +						KEYSTONE_LOW_PHYS_START,
> +						KEYSTONE_HIGH_PHYS_SIZE);
> +		dev_err(dev, "set dma_offset%08llx%s\n",
> +			KEYSTONE_HIGH_PHYS_START - KEYSTONE_LOW_PHYS_START,
> +			ret ? " failed" : "");
>  	}
>  	return NOTIFY_OK;
>  }
> @@ -54,11 +56,8 @@ static struct notifier_block platform_nb = {
>  static void __init keystone_init(void)
>  {
>  #ifdef CONFIG_ARM_LPAE
> -	if (PHYS_OFFSET >= KEYSTONE_HIGH_PHYS_START) {
> -		keystone_dma_pfn_offset = PFN_DOWN(KEYSTONE_HIGH_PHYS_START -
> -						   KEYSTONE_LOW_PHYS_START);
> +	if (PHYS_OFFSET >= KEYSTONE_HIGH_PHYS_START)
>  		bus_register_notifier(&platform_bus_type, &platform_nb);
> -	}
>  #endif
>  	keystone_pm_runtime_init();
>  }
> diff --git a/arch/arm/mach-omap1/include/mach/memory.h b/arch/arm/mach-omap1/include/mach/memory.h
> index e43697c3297bf2..1142560e0078f5 100644
> --- a/arch/arm/mach-omap1/include/mach/memory.h
> +++ b/arch/arm/mach-omap1/include/mach/memory.h
> @@ -41,6 +41,10 @@
>  	   __phys_to_pfn(__dma);				\
>  	})
>  
> +#define __arch_dma_to_virt(dev, addr)	({ (void *) (is_lbus_device(dev) ? \
> +						lbus_to_virt(addr) : \
> +						__phys_to_virt(addr)); })
> +
>  #define __arch_virt_to_dma(dev, addr)	({ unsigned long __addr = (unsigned long)(addr); \
>  					   (dma_addr_t) (is_lbus_device(dev) ? \
>  						virt_to_lbus(__addr) : \
> diff --git a/arch/sh/drivers/pci/pcie-sh7786.c b/arch/sh/drivers/pci/pcie-sh7786.c
> index e0b568aaa7014c..4468289ab2cac7 100644
> --- a/arch/sh/drivers/pci/pcie-sh7786.c
> +++ b/arch/sh/drivers/pci/pcie-sh7786.c
> @@ -12,6 +12,7 @@
>  #include <linux/io.h>
>  #include <linux/async.h>
>  #include <linux/delay.h>
> +#include <linux/dma-mapping.h>
>  #include <linux/slab.h>
>  #include <linux/clk.h>
>  #include <linux/sh_clk.h>
> @@ -31,6 +32,8 @@ struct sh7786_pcie_port {
>  static struct sh7786_pcie_port *sh7786_pcie_ports;
>  static unsigned int nr_ports;
>  static unsigned long dma_pfn_offset;
> +size_t memsize;
> +u64 memstart;
>  
>  static struct sh7786_pcie_hwops {
>  	int (*core_init)(void);
> @@ -301,7 +304,6 @@ static int __init pcie_init(struct sh7786_pcie_port *port)
>  	struct pci_channel *chan = port->hose;
>  	unsigned int data;
>  	phys_addr_t memstart, memend;
> -	size_t memsize;
>  	int ret, i, win;
>  
>  	/* Begin initialization */
> @@ -368,8 +370,6 @@ static int __init pcie_init(struct sh7786_pcie_port *port)
>  	memstart = ALIGN_DOWN(memstart, memsize);
>  	memsize = roundup_pow_of_two(memend - memstart);
>  
> -	dma_pfn_offset = memstart >> PAGE_SHIFT;
> -
>  	/*
>  	 * If there's more than 512MB of memory, we need to roll over to
>  	 * LAR1/LAMR1.
> @@ -487,7 +487,8 @@ int pcibios_map_platform_irq(const struct pci_dev *pdev, u8 slot, u8 pin)
>  
>  void pcibios_bus_add_device(struct pci_dev *pdev)
>  {
> -	pdev->dev.dma_pfn_offset = dma_pfn_offset;
> +	dma_direct_set_offset(&pdev->dev, __pa(memory_start),
> +			      __pa(memory_start) - memstart, memsize);
>  }
>  
>  static int __init sh7786_pcie_core_init(void)
> diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
> index c313d784efabb9..324a207f99956b 100644
> --- a/arch/x86/pci/sta2x11-fixup.c
> +++ b/arch/x86/pci/sta2x11-fixup.c
> @@ -133,7 +133,7 @@ static void sta2x11_map_ep(struct pci_dev *pdev)
>  	struct sta2x11_instance *instance = sta2x11_pdev_to_instance(pdev);
>  	struct device *dev = &pdev->dev;
>  	u32 amba_base, max_amba_addr;
> -	int i;
> +	int i, ret;
>  
>  	if (!instance)
>  		return;
> @@ -141,7 +141,9 @@ static void sta2x11_map_ep(struct pci_dev *pdev)
>  	pci_read_config_dword(pdev, AHB_BASE(0), &amba_base);
>  	max_amba_addr = amba_base + STA2X11_AMBA_SIZE - 1;
>  
> -	dev->dma_pfn_offset = PFN_DOWN(-amba_base);
> +	ret = dma_direct_set_offset(dev, 0, amba_base, STA2X11_AMBA_SIZE);
> +	if (ret)
> +		dev_err(dev, "sta2x11: could not set DMA offset\n");
>  
>  	dev->bus_dma_limit = max_amba_addr;
>  	pci_set_consistent_dma_mask(pdev, max_amba_addr);
> diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
> index ec782e4a0fe419..de18c07ca02cc4 100644
> --- a/drivers/acpi/arm64/iort.c
> +++ b/drivers/acpi/arm64/iort.c
> @@ -18,6 +18,7 @@
>  #include <linux/pci.h>
>  #include <linux/platform_device.h>
>  #include <linux/slab.h>
> +#include <linux/dma-mapping.h>
>  
>  #define IORT_TYPE_MASK(type)	(1 << (type))
>  #define IORT_MSI_TYPE		(1 << ACPI_IORT_NODE_ITS_GROUP)
> @@ -1184,8 +1185,9 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size)
>  	*dma_addr = dmaaddr;
>  	*dma_size = size;
>  
> -	dev->dma_pfn_offset = PFN_DOWN(offset);
> -	dev_dbg(dev, "dma_pfn_offset(%#08llx)\n", offset);
> +	ret = dma_direct_set_offset(dev, dmaaddr + offset, dmaaddr, size);
> +
> +	dev_dbg(dev, "dma_offset(%#08llx)%s\n", offset, ret ? " failed!" : "");
>  }
>  
>  static void __init acpi_iort_register_irq(int hwirq, const char *name,
> diff --git a/drivers/base/core.c b/drivers/base/core.c
> index f6f620aa94086d..b893056e39459c 100644
> --- a/drivers/base/core.c
> +++ b/drivers/base/core.c
> @@ -1792,6 +1792,8 @@ static void device_release(struct kobject *kobj)
>  	 */
>  	devres_release_all(dev);
>  
> +	kfree(dev->dma_range_map);
> +
>  	if (dev->release)
>  		dev->release(dev);
>  	else if (dev->type && dev->type->release)
> diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c
> index 072ea113e6be55..05e9f0d28196d9 100644
> --- a/drivers/gpu/drm/sun4i/sun4i_backend.c
> +++ b/drivers/gpu/drm/sun4i/sun4i_backend.c
> @@ -11,6 +11,7 @@
>  #include <linux/module.h>
>  #include <linux/of_device.h>
>  #include <linux/of_graph.h>
> +#include <linux/dma-mapping.h>
>  #include <linux/platform_device.h>
>  #include <linux/reset.h>
>  
> @@ -811,8 +812,13 @@ static int sun4i_backend_bind(struct device *dev, struct device *master,
>  		 * because of an old DT, we need to set the DMA offset by hand
>  		 * on our device since the RAM mapping is at 0 for the DMA bus,
>  		 * unlike the CPU.
> +		 *
> +		 * XXX(hch): this has no business in a driver and needs to move
> +		 * to the device tree.
>  		 */
> -		drm->dev->dma_pfn_offset = PHYS_PFN_OFFSET;
> +		ret = dma_direct_set_offset(drm->dev, PHYS_OFFSET, 0, SZ_4G);
> +		if (ret)
> +			return ret;
>  	}
>  
>  	backend->engine.node = dev->of_node;
> diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
> index dc7bcf858b6d2d..d77e881516a4ab 100644
> --- a/drivers/iommu/io-pgtable-arm.c
> +++ b/drivers/iommu/io-pgtable-arm.c
> @@ -751,7 +751,7 @@ arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg)
>  	if (cfg->oas > ARM_LPAE_MAX_ADDR_BITS)
>  		return NULL;
>  
> -	if (!selftest_running && cfg->iommu_dev->dma_pfn_offset) {
> +	if (!selftest_running && cfg->iommu_dev->dma_range_map) {
>  		dev_err(cfg->iommu_dev, "Cannot accommodate DMA offset for IOMMU page tables\n");
>  		return NULL;
>  	}
> diff --git a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
> index 5319eb1ab30927..307997ee7f96a2 100644
> --- a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
> +++ b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
> @@ -7,6 +7,7 @@
>   */
>  
>  #include <linux/clk.h>
> +#include <linux/dma-mapping.h>
>  #include <linux/interrupt.h>
>  #include <linux/module.h>
>  #include <linux/mutex.h>
> @@ -182,8 +183,14 @@ static int sun4i_csi_probe(struct platform_device *pdev)
>  		if (ret)
>  			return ret;
>  	} else {
> +		/*
> +		 * XXX(hch): this has no business in a driver and needs to move
> +		 * to the device tree.
> +		 */
>  #ifdef PHYS_PFN_OFFSET
> -		csi->dev->dma_pfn_offset = PHYS_PFN_OFFSET;
> +		ret = dma_direct_set_offset(csi->dev, PHYS_OFFSET, 0, SZ_4G);
> +		if (ret)
> +			return ret;
>  #endif
>  	}
>  
> diff --git a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c
> index 28e89340fed981..e69e14379fc6e4 100644
> --- a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c
> +++ b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c
> @@ -899,8 +899,15 @@ static int sun6i_csi_probe(struct platform_device *pdev)
>  		return -ENOMEM;
>  
>  	sdev->dev = &pdev->dev;
> -	/* The DMA bus has the memory mapped at 0 */
> -	sdev->dev->dma_pfn_offset = PHYS_OFFSET >> PAGE_SHIFT;
> +	/*
> +	 * The DMA bus has the memory mapped at 0.
> +	 *
> +	 * XXX(hch): this has no business in a driver and needs to move
> +	 * to the device tree.
> +	 */
> +	ret = dma_direct_set_offset(sdev->dev, PHYS_OFFSET, 0, SZ_4G);
> +	if (ret)
> +		return ret;
>  
>  	ret = sun6i_csi_resource_request(sdev, pdev);
>  	if (ret)
> diff --git a/drivers/of/address.c b/drivers/of/address.c
> index da4f7341323f22..a49ef87aaaf21c 100644
> --- a/drivers/of/address.c
> +++ b/drivers/of/address.c
> @@ -13,6 +13,7 @@
>  #include <linux/sizes.h>
>  #include <linux/slab.h>
>  #include <linux/string.h>
> +#include <linux/dma-direct.h> /* for bus_dma_region */
>  
>  #include "of_private.h"
>  
> @@ -937,33 +938,33 @@ void __iomem *of_io_request_and_map(struct device_node *np, int index,
>  }
>  EXPORT_SYMBOL(of_io_request_and_map);
>  
> +#ifdef CONFIG_HAS_DMA
>  /**
> - * of_dma_get_range - Get DMA range info
> + * of_dma_get_range - Get DMA range info and put it into a map array
>   * @np:		device node to get DMA range info
> - * @dma_addr:	pointer to store initial DMA address of DMA range
> - * @paddr:	pointer to store initial CPU address of DMA range
> - * @size:	pointer to store size of DMA range
> + * @map:	dma range structure to return
>   *
>   * Look in bottom up direction for the first "dma-ranges" property
> - * and parse it.
> - *  dma-ranges format:
> + * and parse it.  Put the information into a DMA offset map array.
> + *
> + * dma-ranges format:
>   *	DMA addr (dma_addr)	: naddr cells
>   *	CPU addr (phys_addr_t)	: pna cells
>   *	size			: nsize cells
>   *
> - * It returns -ENODEV if "dma-ranges" property was not found
> - * for this device in DT.
> + * It returns -ENODEV if "dma-ranges" property was not found for this
> + * device in the DT.
>   */
> -int of_dma_get_range(struct device_node *np, u64 *dma_addr, u64 *paddr, u64 *size)
> +int of_dma_get_range(struct device_node *np, const struct bus_dma_region **map)
>  {
>  	struct device_node *node = of_node_get(np);
>  	const __be32 *ranges = NULL;
> -	int len;
> -	int ret = 0;
>  	bool found_dma_ranges = false;
>  	struct of_range_parser parser;
>  	struct of_range range;
> -	u64 dma_start = U64_MAX, dma_end = 0, dma_offset = 0;
> +	struct bus_dma_region *r;
> +	int len, num_ranges = 0;
> +	int ret = 0;
>  
>  	while (node) {
>  		ranges = of_get_property(node, "dma-ranges", &len);
> @@ -989,49 +990,39 @@ int of_dma_get_range(struct device_node *np, u64 *dma_addr, u64 *paddr, u64 *siz
>  	}
>  
>  	of_dma_range_parser_init(&parser, node);
> +	for_each_of_range(&parser, &range)
> +		num_ranges++;
> +
> +	r = kcalloc(num_ranges + 1, sizeof(*r), GFP_KERNEL);
> +	if (!r) {
> +		ret = -ENOMEM;
> + 		goto out;
> +	}
>  
> +	/*
> +	 * Record all info in the generic DMA ranges array for struct device.
> +	 */
> +	*map = r;
> + 	of_dma_range_parser_init(&parser, node);
>  	for_each_of_range(&parser, &range) {
>  		pr_debug("dma_addr(%llx) cpu_addr(%llx) size(%llx)\n",
>  			 range.bus_addr, range.cpu_addr, range.size);
> -
> -		if (dma_offset && range.cpu_addr - range.bus_addr != dma_offset) {
> -			pr_warn("Can't handle multiple dma-ranges with different offsets on node(%pOF)\n", node);
> -			/* Don't error out as we'd break some existing DTs */
> -			continue;
> -		}
>  		if (range.cpu_addr == OF_BAD_ADDR) {
>  			pr_err("translation of DMA address(%llx) to CPU address failed node(%pOF)\n",
>  			       range.bus_addr, node);
>  			continue;
>  		}
> -		dma_offset = range.cpu_addr - range.bus_addr;
> -
> -		/* Take lower and upper limits */
> -		if (range.bus_addr < dma_start)
> -			dma_start = range.bus_addr;
> -		if (range.bus_addr + range.size > dma_end)
> -			dma_end = range.bus_addr + range.size;
> -	}
> -
> -	if (dma_start >= dma_end) {
> -		ret = -EINVAL;
> -		pr_debug("Invalid DMA ranges configuration on node(%pOF)\n",
> -			 node);
> -		goto out;
> +		r->cpu_start = range.cpu_addr;
> +		r->dma_start = range.bus_addr;
> +		r->size = range.size;
> +		r->offset = range.cpu_addr - range.bus_addr;
> +		r++;
>  	}
> -
> -	*dma_addr = dma_start;
> -	*size = dma_end - dma_start;
> -	*paddr = dma_start + dma_offset;
> -
> -	pr_debug("final: dma_addr(%llx) cpu_addr(%llx) size(%llx)\n",
> -		 *dma_addr, *paddr, *size);
> -
>  out:
>  	of_node_put(node);
> -
>  	return ret;
>  }
> +#endif /* CONFIG_HAS_DMA */
>  
>  /**
>   * of_dma_is_coherent - Check if device is coherent
> diff --git a/drivers/of/device.c b/drivers/of/device.c
> index b439c1e054349b..6e3ae7ebc33eeb 100644
> --- a/drivers/of/device.c
> +++ b/drivers/of/device.c
> @@ -5,7 +5,7 @@
>  #include <linux/of_device.h>
>  #include <linux/of_address.h>
>  #include <linux/of_iommu.h>
> -#include <linux/dma-mapping.h>
> +#include <linux/dma-direct.h> /* for bus_dma_region */
>  #include <linux/init.h>
>  #include <linux/module.h>
>  #include <linux/mod_devicetable.h>
> @@ -90,14 +90,14 @@ int of_device_add(struct platform_device *ofdev)
>  int of_dma_configure_id(struct device *dev, struct device_node *np,
>  			bool force_dma, const u32 *id)
>  {
> -	u64 dma_addr, paddr, size = 0;
> -	int ret;
> -	bool coherent;
> -	unsigned long offset;
>  	const struct iommu_ops *iommu;
> -	u64 mask, end;
> +	const struct bus_dma_region *map = NULL;
> +	dma_addr_t dma_start = 0;
> +	u64 mask, end, size = 0;
> +	bool coherent;
> +	int ret;
>  
> -	ret = of_dma_get_range(np, &dma_addr, &paddr, &size);
> +	ret = of_dma_get_range(np, &map);
>  	if (ret < 0) {
>  		/*
>  		 * For legacy reasons, we have to assume some devices need
> @@ -106,26 +106,35 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
>  		 */
>  		if (!force_dma)
>  			return ret == -ENODEV ? 0 : ret;
> -
> -		dma_addr = offset = 0;
>  	} else {
> -		offset = PFN_DOWN(paddr - dma_addr);
> +		const struct bus_dma_region *r = map;
> +		dma_addr_t dma_end = 0;
> +
> +		/* Determine the overall bounds of all DMA regions */
> +		for (dma_start = ~(dma_addr_t)0; r->size; r++) {
> +			/* Take lower and upper limits */
> +			if (r->dma_start < dma_start)
> +				dma_start = r->dma_start;
> +			if (r->dma_start + r->size > dma_end)
> +				dma_end = r->dma_start + r->size;
> +		}
> +		size = dma_end - dma_start;
>  
>  		/*
>  		 * Add a work around to treat the size as mask + 1 in case
>  		 * it is defined in DT as a mask.
>  		 */
>  		if (size & 1) {
> -			dev_warn(dev, "Invalid size 0x%llx for dma-range\n",
> +			dev_warn(dev, "Invalid size 0x%llx for dma-range(s)\n",
>  				 size);
>  			size = size + 1;
>  		}
>  
>  		if (!size) {
>  			dev_err(dev, "Adjusted size 0x%llx invalid\n", size);
> +			kfree(map);
>  			return -EINVAL;
>  		}
> -		dev_dbg(dev, "dma_pfn_offset(%#08lx)\n", offset);
>  	}
>  
>  	/*
> @@ -144,13 +153,11 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
>  	else if (!size)
>  		size = 1ULL << 32;
>  
> -	dev->dma_pfn_offset = offset;
> -
>  	/*
>  	 * Limit coherent and dma mask based on size and default mask
>  	 * set by the driver.
>  	 */
> -	end = dma_addr + size - 1;
> +	end = dma_start + size - 1;
>  	mask = DMA_BIT_MASK(ilog2(end) + 1);
>  	dev->coherent_dma_mask &= mask;
>  	*dev->dma_mask &= mask;
> @@ -163,14 +170,17 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
>  		coherent ? " " : " not ");
>  
>  	iommu = of_iommu_configure(dev, np, id);
> -	if (PTR_ERR(iommu) == -EPROBE_DEFER)
> +	if (PTR_ERR(iommu) == -EPROBE_DEFER) {
> +		kfree(map);
>  		return -EPROBE_DEFER;
> +	}
>  
>  	dev_dbg(dev, "device is%sbehind an iommu\n",
>  		iommu ? " " : " not ");
>  
> -	arch_setup_dma_ops(dev, dma_addr, size, iommu, coherent);
> +	arch_setup_dma_ops(dev, dma_start, size, iommu, coherent);
>  
> +	dev->dma_range_map = map;
>  	return 0;
>  }
>  EXPORT_SYMBOL_GPL(of_dma_configure_id);
> diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h
> index edc682249c0015..d9e6a324de0a77 100644
> --- a/drivers/of/of_private.h
> +++ b/drivers/of/of_private.h
> @@ -157,12 +157,13 @@ extern void __of_sysfs_remove_bin_file(struct device_node *np,
>  extern int of_bus_n_addr_cells(struct device_node *np);
>  extern int of_bus_n_size_cells(struct device_node *np);
>  
> -#ifdef CONFIG_OF_ADDRESS
> -extern int of_dma_get_range(struct device_node *np, u64 *dma_addr,
> -			    u64 *paddr, u64 *size);
> +struct bus_dma_region;
> +#if defined(CONFIG_OF_ADDRESS) && defined(CONFIG_HAS_DMA)
> +int of_dma_get_range(struct device_node *np,
> +		const struct bus_dma_region **map);
>  #else
> -static inline int of_dma_get_range(struct device_node *np, u64 *dma_addr,
> -				   u64 *paddr, u64 *size)
> +static inline int of_dma_get_range(struct device_node *np,
> +		const struct bus_dma_region **map)
>  {
>  	return -ENODEV;
>  }
> diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
> index 9b7e84bdc7d446..06cc988faf78b3 100644
> --- a/drivers/of/unittest.c
> +++ b/drivers/of/unittest.c
> @@ -7,6 +7,7 @@
>  
>  #include <linux/memblock.h>
>  #include <linux/clk.h>
> +#include <linux/dma-direct.h> /* to test phys_to_dma/dma_to_phys */
>  #include <linux/err.h>
>  #include <linux/errno.h>
>  #include <linux/hashtable.h>
> @@ -869,10 +870,11 @@ static void __init of_unittest_changeset(void)
>  }
>  
>  static void __init of_unittest_dma_ranges_one(const char *path,
> -		u64 expect_dma_addr, u64 expect_paddr, u64 expect_size)
> +		u64 expect_dma_addr, u64 expect_paddr)
>  {
> +#ifdef CONFIG_HAS_DMA
>  	struct device_node *np;
> -	u64 dma_addr, paddr, size;
> +	const struct bus_dma_region *map = NULL;
>  	int rc;
>  
>  	np = of_find_node_by_path(path);
> @@ -881,28 +883,40 @@ static void __init of_unittest_dma_ranges_one(const char *path,
>  		return;
>  	}
>  
> -	rc = of_dma_get_range(np, &dma_addr, &paddr, &size);
> +	rc = of_dma_get_range(np, &map);
>  
>  	unittest(!rc, "of_dma_get_range failed on node %pOF rc=%i\n", np, rc);
> +
>  	if (!rc) {
> -		unittest(size == expect_size,
> -			 "of_dma_get_range wrong size on node %pOF size=%llx\n", np, size);
> +		phys_addr_t	paddr;
> +		dma_addr_t	dma_addr;
> +		struct device	dev_bogus;
> +
> +		dev_bogus.dma_range_map = map;
> +		paddr = dma_to_phys(&dev_bogus, expect_dma_addr);
> +		dma_addr = phys_to_dma(&dev_bogus, expect_paddr);
> +
>  		unittest(paddr == expect_paddr,
> -			 "of_dma_get_range wrong phys addr (%llx) on node %pOF", paddr, np);
> +			 "of_dma_get_range: wrong phys addr %pap (expecting %llx) on node %pOF\n",
> +			 &paddr, expect_paddr, np);
>  		unittest(dma_addr == expect_dma_addr,
> -			 "of_dma_get_range wrong DMA addr (%llx) on node %pOF", dma_addr, np);
> +			 "of_dma_get_range: wrong DMA addr %pad (expecting %llx) on node %pOF\n",
> +			 &dma_addr, expect_dma_addr, np);
> +
> +		kfree(map);
>  	}
>  	of_node_put(np);
> +#endif
>  }
>  
>  static void __init of_unittest_parse_dma_ranges(void)
>  {
>  	of_unittest_dma_ranges_one("/testcase-data/address-tests/device@70000000",
> -		0x0, 0x20000000, 0x40000000);
> +		0x0, 0x20000000);
>  	of_unittest_dma_ranges_one("/testcase-data/address-tests/bus@80000000/device@1000",
> -		0x100000000, 0x20000000, 0x2000000000);
> +		0x100000000, 0x20000000);
>  	of_unittest_dma_ranges_one("/testcase-data/address-tests/pci@90000000",
> -		0x80000000, 0x20000000, 0x10000000);
> +		0x80000000, 0x20000000);
>  }
>  
>  static void __init of_unittest_pci_dma_ranges(void)
> diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
> index 7f90eeea67e279..8157dd491d2819 100644
> --- a/drivers/remoteproc/remoteproc_core.c
> +++ b/drivers/remoteproc/remoteproc_core.c
> @@ -23,6 +23,7 @@
>  #include <linux/slab.h>
>  #include <linux/mutex.h>
>  #include <linux/dma-mapping.h>
> +#include <linux/dma-direct.h> /* XXX: pokes into bus_dma_range */
>  #include <linux/firmware.h>
>  #include <linux/string.h>
>  #include <linux/debugfs.h>
> @@ -458,6 +459,25 @@ static void rproc_rvdev_release(struct device *dev)
>  	kfree(rvdev);
>  }
>  
> +static int copy_dma_range_map(struct device *to, struct device *from)
> +{
> +	const struct bus_dma_region *map = from->dma_range_map, *new_map, *r;
> +	int num_ranges = 0;
> +
> +	if (!map)
> +		return 0;
> +
> +	for (r = map; r->size; r++)
> +		num_ranges++;
> +
> +	new_map = kmemdup(map, array_size(num_ranges + 1, sizeof(*map)),
> +			  GFP_KERNEL);
> +	if (!new_map)
> +		return -ENOMEM;
> +	to->dma_range_map = new_map;
> +	return 0;
> +}
> +
>  /**
>   * rproc_handle_vdev() - handle a vdev fw resource
>   * @rproc: the remote processor
> @@ -529,7 +549,9 @@ static int rproc_handle_vdev(struct rproc *rproc, struct fw_rsc_vdev *rsc,
>  	/* Initialise vdev subdevice */
>  	snprintf(name, sizeof(name), "vdev%dbuffer", rvdev->index);
>  	rvdev->dev.parent = &rproc->dev;
> -	rvdev->dev.dma_pfn_offset = rproc->dev.parent->dma_pfn_offset;
> +	ret = copy_dma_range_map(&rvdev->dev, rproc->dev.parent);
> +	if (ret)
> +		return ret;

For the remoteproc part and with the checkpatch errors on this patch addressed:

Tested-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Reviewed-by: Mathieu Poirier <mathieu.poirier@linaro.org>

>  	rvdev->dev.release = rproc_rvdev_release;
>  	dev_set_name(&rvdev->dev, "%s#%s", dev_name(rvdev->dev.parent), name);
>  	dev_set_drvdata(&rvdev->dev, rvdev);
> diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_hw.c b/drivers/staging/media/sunxi/cedrus/cedrus_hw.c
> index 1744e6fcc99980..bcf050a04ffc45 100644
> --- a/drivers/staging/media/sunxi/cedrus/cedrus_hw.c
> +++ b/drivers/staging/media/sunxi/cedrus/cedrus_hw.c
> @@ -227,11 +227,17 @@ int cedrus_hw_probe(struct cedrus_dev *dev)
>  	 * the RAM offset to the physcal addresses.
>  	 *
>  	 * This information will eventually be obtained from device-tree.
> +	 *
> +	 * XXX(hch): this has no business in a driver and needs to move
> +	 * to the device tree.
>  	 */
>  
>  #ifdef PHYS_PFN_OFFSET
> -	if (!(variant->quirks & CEDRUS_QUIRK_NO_DMA_OFFSET))
> -		dev->dev->dma_pfn_offset = PHYS_PFN_OFFSET;
> +	if (!(variant->quirks & CEDRUS_QUIRK_NO_DMA_OFFSET)) {
> +		ret = dma_direct_set_offset(dev->dev, PHYS_OFFSET, 0, SZ_4G);
> +		if (ret)
> +			return ret;
> +	}
>  #endif
>  
>  	ret = of_reserved_mem_device_init(dev->dev);
> diff --git a/include/linux/device.h b/include/linux/device.h
> index ca18da4768e3e8..1c78621fc3c01f 100644
> --- a/include/linux/device.h
> +++ b/include/linux/device.h
> @@ -466,7 +466,7 @@ struct dev_links_info {
>   * 		such descriptors.
>   * @bus_dma_limit: Limit of an upstream bridge or bus which imposes a smaller
>   *		DMA limit than the device itself supports.
> - * @dma_pfn_offset: offset of DMA memory range relatively of RAM
> + * @dma_range_map: map for DMA memory ranges relative to that of RAM
>   * @dma_parms:	A low level driver may set these to teach IOMMU code about
>   * 		segment limitations.
>   * @dma_pools:	Dma pools (if dma'ble device).
> @@ -561,7 +561,7 @@ struct device {
>  					     64 bit addresses for consistent
>  					     allocations such descriptors. */
>  	u64		bus_dma_limit;	/* upstream dma constraint */
> -	unsigned long	dma_pfn_offset;
> +	const struct bus_dma_region *dma_range_map;
>  
>  	struct device_dma_parameters *dma_parms;
>  
> diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
> index 805010ea5346f9..c6b21acba7a459 100644
> --- a/include/linux/dma-direct.h
> +++ b/include/linux/dma-direct.h
> @@ -14,6 +14,41 @@
>  
>  extern unsigned int zone_dma_bits;
>  
> +/*
> + * Record the mapping of CPU physical to DMA addresses for a given region.
> + */
> +struct bus_dma_region {
> +	phys_addr_t	cpu_start;
> +	dma_addr_t	dma_start;
> +	u64		size;
> +	u64		offset;
> +};
> +
> +static inline dma_addr_t translate_phys_to_dma(struct device *dev,
> +		phys_addr_t paddr)
> +{
> +	const struct bus_dma_region *m;
> +
> +	for (m = dev->dma_range_map; m->size; m++)
> +		if (paddr >= m->cpu_start && paddr - m->cpu_start < m->size)
> +			return (dma_addr_t)paddr - m->offset;
> +
> +	/* make sure dma_capable fails when no translation is available */
> +	return DMA_MAPPING_ERROR; 
> +}
> +
> +static inline phys_addr_t translate_dma_to_phys(struct device *dev,
> +		dma_addr_t dma_addr)
> +{
> +	const struct bus_dma_region *m;
> +
> +	for (m = dev->dma_range_map; m->size; m++)
> +		if (dma_addr >= m->dma_start && dma_addr - m->dma_start < m->size)
> +			return (phys_addr_t)dma_addr + m->offset;
> +
> +	return (phys_addr_t)-1;
> +}
> +
>  #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA
>  #include <asm/dma-direct.h>
>  #ifndef phys_to_dma_unencrypted
> @@ -23,9 +58,9 @@ extern unsigned int zone_dma_bits;
>  static inline dma_addr_t phys_to_dma_unencrypted(struct device *dev,
>  		phys_addr_t paddr)
>  {
> -	dma_addr_t dev_addr = (dma_addr_t)paddr;
> -
> -	return dev_addr - ((dma_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
> +	if (dev->dma_range_map)
> +		return translate_phys_to_dma(dev, paddr);
> +	return paddr;
>  }
>  
>  /*
> @@ -39,10 +74,14 @@ static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
>  	return __sme_set(phys_to_dma_unencrypted(dev, paddr));
>  }
>  
> -static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
> +static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
>  {
> -	phys_addr_t paddr = (phys_addr_t)dev_addr +
> -		((phys_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
> +	phys_addr_t paddr;
> +
> +	if (dev->dma_range_map)
> +		paddr = translate_dma_to_phys(dev, dma_addr);
> +	else
> +		paddr = dma_addr;
>  
>  	return __sme_clr(paddr);
>  }
> @@ -64,7 +103,8 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size,
>  
>  	if (!dev->dma_mask)
>  		return false;
> -
> +	if (addr == DMA_MAPPING_ERROR)
> +		return false;
>  	if (is_ram && !IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) &&
>  	    min(addr, end) < phys_to_dma(dev, PFN_PHYS(min_low_pfn)))
>  		return false;
> diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
> index df0bff2ea750e0..bb138ac6f5e63e 100644
> --- a/include/linux/dma-mapping.h
> +++ b/include/linux/dma-mapping.h
> @@ -730,4 +730,11 @@ static inline int dma_mmap_wc(struct device *dev,
>  #define dma_unmap_len_set(PTR, LEN_NAME, VAL)    do { } while (0)
>  #endif
>  
> -#endif
> +/*
> + * Legacy interface to set up the dma offset map.  Drivers really should not
> + * actually use it, but we have a few legacy cases left.
> + */
> +int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
> +		dma_addr_t dma_start, u64 size);
> +
> +#endif /* _LINUX_DMA_MAPPING_H */
> diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c
> index f85d14bbfcbe03..c0685196fb6d42 100644
> --- a/kernel/dma/coherent.c
> +++ b/kernel/dma/coherent.c
> @@ -7,7 +7,7 @@
>  #include <linux/slab.h>
>  #include <linux/kernel.h>
>  #include <linux/module.h>
> -#include <linux/dma-mapping.h>
> +#include <linux/dma-direct.h>
>  
>  struct dma_coherent_mem {
>  	void		*virt_base;
> @@ -32,9 +32,8 @@ static inline dma_addr_t dma_get_device_base(struct device *dev,
>  					     struct dma_coherent_mem * mem)
>  {
>  	if (mem->use_dev_dma_pfn_offset)
> -		return (mem->pfn_base - dev->dma_pfn_offset) << PAGE_SHIFT;
> -	else
> -		return mem->device_base;
> +		return phys_to_dma(dev, PFN_PHYS(mem->pfn_base));
> +	return mem->device_base;
>  }
>  
>  static int dma_init_coherent_memory(phys_addr_t phys_addr,
> diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
> index 54db9cfdaecc6d..750659f7447c4b 100644
> --- a/kernel/dma/direct.c
> +++ b/kernel/dma/direct.c
> @@ -13,6 +13,7 @@
>  #include <linux/pfn.h>
>  #include <linux/vmalloc.h>
>  #include <linux/set_memory.h>
> +#include <linux/slab.h>
>  
>  /*
>   * Most architectures use ZONE_DMA for the first 16 Megabytes, but some use it
> @@ -66,8 +67,12 @@ static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
>  
>  static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
>  {
> -	return phys_to_dma_direct(dev, phys) + size - 1 <=
> -			min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
> +	dma_addr_t dma_addr = phys_to_dma_direct(dev, phys);
> +
> +	if (dma_addr == DMA_MAPPING_ERROR)
> +		return false;
> +	return dma_addr + size - 1 <=
> +		min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
>  }
>  
>  /*
> @@ -461,3 +466,45 @@ bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr)
>  	return !dev_is_dma_coherent(dev) ||
>  		is_swiotlb_buffer(dma_to_phys(dev, dma_addr));
>  }
> +
> +/**
> + * dma_direct_set_offset - Assign scalar offset for a single DMA range.
> + * @dev:	device pointer; needed to "own" the alloced memory.
> + * @cpu_start:  beginning of memory region covered by this offset.
> + * @dma_start:  beginning of DMA/PCI region covered by this offset.
> + * @size:	size of the region.
> + *
> + * This is for the simple case of a uniform offset which cannot
> + * be discovered by "dma-ranges".
> + *
> + * It returns -ENOMEM if out of memory, -EINVAL if a map
> + * already exists, 0 otherwise.
> + *
> + * Note: any call to this from a driver is a bug.  The mapping needs
> + * to be described by the device tree or other firmware interfaces.
> + */
> +int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
> +			 dma_addr_t dma_start, u64 size)
> +{
> +	struct bus_dma_region *map;
> +	u64 offset = (u64)cpu_start - (u64)dma_start;
> +
> +	if (dev->dma_range_map) {
> +		dev_err(dev, "attempt to add DMA range to existing map\n");
> +		return -EINVAL;
> +	}
> +
> +	if (!offset)
> +		return 0;
> +
> +	map = kcalloc(2, sizeof(*map), GFP_KERNEL);
> +	if (!map)
> +		return -ENOMEM;
> +	map[0].cpu_start = cpu_start;
> +	map[0].dma_start = dma_start;
> +	map[0].offset = offset;
> +	map[0].size = size;
> +	dev->dma_range_map = map;
> +	return 0;
> +}
> +EXPORT_SYMBOL_GPL(dma_direct_set_offset);
> -- 
> 2.28.0
> 

^ permalink raw reply	[flat|nested] 15+ messages in thread

* Re: support range based offsets in dma-direct v3
  2020-09-16  6:14 support range based offsets in dma-direct v3 Christoph Hellwig
                   ` (5 preceding siblings ...)
  2020-09-16  6:14 ` [PATCH 6/6] dma-mapping: introduce DMA range map, supplanting dma_pfn_offset Christoph Hellwig
@ 2020-09-17 16:45 ` Christoph Hellwig
  6 siblings, 0 replies; 15+ messages in thread
From: Christoph Hellwig @ 2020-09-17 16:45 UTC (permalink / raw)
  To: iommu, Russell King, Santosh Shilimkar, Greg Kroah-Hartman
  Cc: Ohad Ben-Cohen, devicetree, Florian Fainelli, linux-sh,
	Frank Rowand, linux-usb, linux-remoteproc, linux-kernel,
	linux-acpi, Rob Herring, Jim Quinlan, linux-pci,
	Nathan Chancellor, Robin Murphy, linux-arm-kernel

I've pulled this into the dma-mapping for-next tree.  Thanks Jim and
everyone helping out!

^ permalink raw reply	[flat|nested] 15+ messages in thread

* Re: [PATCH 6/6] dma-mapping: introduce DMA range map, supplanting dma_pfn_offset
  2020-09-16  6:14 ` [PATCH 6/6] dma-mapping: introduce DMA range map, supplanting dma_pfn_offset Christoph Hellwig
  2020-09-16 17:36   ` Mathieu Poirier
@ 2020-10-26 15:33   ` Geert Uytterhoeven
  1 sibling, 0 replies; 15+ messages in thread
From: Geert Uytterhoeven @ 2020-10-26 15:33 UTC (permalink / raw)
  To: Christoph Hellwig, Jim Quinlan
  Cc: Linux IOMMU, Russell King, Santosh Shilimkar, Greg Kroah-Hartman,
	Nathan Chancellor, Florian Fainelli, Robin Murphy, Rob Herring,
	Frank Rowand, Ohad Ben-Cohen, Bjorn Andersson,
	open list:REMOTE PROCESSOR (REMOTEPROC) SUBSYSTEM, USB list,
	Linux ARM, Linux Kernel Mailing List, Linux-sh list, linux-pci,
	ACPI Devel Maling List,
	open list:OPEN FIRMWARE AND FLATTENED DEVICE TREE BINDINGS,
	Yoshihiro Shimoda, Marek Vasut, Linux-Renesas

Hi Christoph, Jim,

On Wed, Sep 16, 2020 at 8:30 AM Christoph Hellwig <hch@lst.de> wrote:
> From: Jim Quinlan <james.quinlan@broadcom.com>
>
> The new field 'dma_range_map' in struct device is used to facilitate the
> use of single or multiple offsets between mapping regions of cpu addrs and
> dma addrs.  It subsumes the role of "dev->dma_pfn_offset" which was only
> capable of holding a single uniform offset and had no region bounds
> checking.
>
> The function of_dma_get_range() has been modified so that it takes a single
> argument -- the device node -- and returns a map, NULL, or an error code.
> The map is an array that holds the information regarding the DMA regions.
> Each range entry contains the address offset, the cpu_start address, the
> dma_start address, and the size of the region.
>
> of_dma_configure() is the typical manner to set range offsets but there are
> a number of ad hoc assignments to "dev->dma_pfn_offset" in the kernel
> driver code.  These cases now invoke the function
> dma_direct_set_offset(dev, cpu_addr, dma_addr, size).
>
> Signed-off-by: Jim Quinlan <james.quinlan@broadcom.com>
> [hch: various interface cleanups]
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> Tested-by: Nathan Chancellor <natechancellor@gmail.com>

Thanks for your patch, which is now commit e0d072782c734d27
("dma-mapping: introduce DMA range map, supplanting dma_pfn_offset") in
v5.10-rc1, and to which I have bisected a PCIe failure on R-Car M2-W
(r8a7791/koelsch).

The first PCI host bridge, containing USB, probes fine:

 pci-rcar-gen2 ee090000.pci: host bridge /soc/pci@ee090000 ranges:
 pci-rcar-gen2 ee090000.pci:      MEM 0x00ee080000..0x00ee08ffff -> 0x00ee080000
 pci-rcar-gen2 ee090000.pci: PCI: revision 11
 pci-rcar-gen2 ee090000.pci: PCI host bridge to bus 0000:00
 pci_bus 0000:00: root bus resource [bus 00]
 pci_bus 0000:00: root bus resource [mem 0xee080000-0xee08ffff]
 pci 0000:00:00.0: [1033:0000] type 00 class 0x060000
 pci 0000:00:00.0: reg 0x10: [mem 0xee090800-0xee090bff]
 pci 0000:00:00.0: reg 0x14: [mem 0x40000000-0x7fffffff pref]
 pci 0000:00:01.0: [1033:0035] type 00 class 0x0c0310
 pci 0000:00:01.0: reg 0x10: [mem 0x00000000-0x00000fff]
 pci 0000:00:01.0: supports D1 D2
 pci 0000:00:01.0: PME# supported from D0 D1 D2 D3hot
 pci 0000:00:02.0: [1033:00e0] type 00 class 0x0c0320
 pci 0000:00:02.0: reg 0x10: [mem 0x00000000-0x000000ff]
 pci 0000:00:02.0: supports D1 D2
 pci 0000:00:02.0: PME# supported from D0 D1 D2 D3hot
 PCI: bus0: Fast back to back transfers disabled
 pci 0000:00:01.0: BAR 0: assigned [mem 0xee080000-0xee080fff]
 pci 0000:00:02.0: BAR 0: assigned [mem 0xee081000-0xee0810ff]
 pci 0000:00:01.0: enabling device (0140 -> 0142)
 pci 0000:00:02.0: enabling device (0140 -> 0142)

The second PCI host bridge, connected to an (empty) PCIe slot, fails:

 pci-rcar-gen2 ee0d0000.pci: host bridge /soc/pci@ee0d0000 ranges:
 pci-rcar-gen2 ee0d0000.pci:      MEM 0x00ee0c0000..0x00ee0cffff -> 0x00ee0c0000
 pci-rcar-gen2 ee0d0000.pci: PCI: revision 11
 pci-rcar-gen2 ee0d0000.pci: PCI host bridge to bus 0001:01
 pci_bus 0001:01: root bus resource [bus 01]
 pci_bus 0001:01: root bus resource [mem 0xee0c0000-0xee0cffff]
 pci 0001:01:00.0: [1033:0000] type 00 class 0x060000
 pci 0001:01:00.0: reg 0x10: [mem 0xee0d0800-0xee0d0bff]
 pci 0001:01:00.0: reg 0x14: [mem 0x40000000-0x7fffffff pref]
 pci 0001:01:01.0: [1033:0035] type 00 class 0x0c0310
 pci 0001:01:01.0: reg 0x10: [mem 0x00000000-0x00000fff]
 pci 0001:01:01.0: supports D1 D2
 pci 0001:01:01.0: PME# supported from D0 D1 D2 D3hot
 pci 0001:01:02.0: [1033:00e0] type 00 class 0x0c0320
 pci 0001:01:02.0: reg 0x10: [mem 0x00000000-0x000000ff]
 pci 0001:01:02.0: supports D1 D2
 pci 0001:01:02.0: PME# supported from D0 D1 D2 D3hot
 PCI: bus1: Fast back to back transfers disabled
 pci 0001:01:01.0: BAR 0: assigned [mem 0xee0c0000-0xee0c0fff]
 pci 0001:01:02.0: BAR 0: assigned [mem 0xee0c1000-0xee0c10ff]
 pci 0001:01:01.0: enabling device (0140 -> 0142)
 pci 0001:01:02.0: enabling device (0140 -> 0142)
-rcar-pcie fe000000.pcie: host bridge /soc/pcie@fe000000 ranges:
-rcar-pcie fe000000.pcie:       IO 0x00fe100000..0x00fe1fffff -> 0x0000000000
-rcar-pcie fe000000.pcie:      MEM 0x00fe200000..0x00fe3fffff -> 0x00fe200000
-rcar-pcie fe000000.pcie:      MEM 0x0030000000..0x0037ffffff -> 0x0030000000
-rcar-pcie fe000000.pcie:      MEM 0x0038000000..0x003fffffff -> 0x0038000000
-rcar-pcie fe000000.pcie:   IB MEM 0x0040000000..0x00bfffffff -> 0x0040000000
-rcar-pcie fe000000.pcie:   IB MEM 0x0200000000..0x02ffffffff -> 0x0200000000
-rcar-pcie fe000000.pcie: PCIe link down
+rcar-pcie fe000000.pcie: Adjusted size 0x0 invalid
+rcar-pcie: probe of fe000000.pcie failed with error -22

I've posted a patch "[PATCH] dma-mapping: Fix 32-bit overflow with
CONFIG_ARM_LPAE=n"
(https://lore.kernel.org/linux-arm-kernel/20201026152755.3738293-1-geert+renesas@glider.be/).

Gr{oetje,eeting}s,

                        Geert


--
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert@linux-m68k.org

In personal conversations with technical people, I call myself a hacker. But
when I'm talking to journalists I just say "programmer" or something like that.
                                -- Linus Torvalds

^ permalink raw reply	[flat|nested] 15+ messages in thread

* Re: [PATCH 6/6] dma-mapping: introduce DMA range map, supplanting dma_pfn_offset
  2020-09-15 19:55       ` Mathieu Poirier
@ 2020-09-16  6:13         ` Christoph Hellwig
  0 siblings, 0 replies; 15+ messages in thread
From: Christoph Hellwig @ 2020-09-16  6:13 UTC (permalink / raw)
  To: Mathieu Poirier
  Cc: Christoph Hellwig, iommu, Russell King, Santosh Shilimkar,
	Greg Kroah-Hartman, Jim Quinlan, Nathan Chancellor,
	Florian Fainelli, Robin Murphy, Rob Herring, Frank Rowand,
	Ohad Ben-Cohen, Bjorn Andersson, linux-remoteproc, linux-usb,
	linux-arm-kernel, linux-kernel, linux-sh, linux-pci, linux-acpi,
	devicetree, arnaud.pouliquen, loic.pallardy.st.com

On Tue, Sep 15, 2020 at 01:55:01PM -0600, Mathieu Poirier wrote:
> That did the trick - the stm32 platform driver's probe() function completes and
> the remote processor is operatinal. 
> 
> That being said the value returned by function dma_to_pfn()
> is 0x137fff in the original code and 0xfffff with your patches applied.

Yes, that is intentional.  The old code just applied the range and got
an out of range offset, the new one reports the max offset.

^ permalink raw reply	[flat|nested] 15+ messages in thread

* Re: [PATCH 6/6] dma-mapping: introduce DMA range map, supplanting dma_pfn_offset
  2020-09-15  5:41     ` Christoph Hellwig
@ 2020-09-15 19:55       ` Mathieu Poirier
  2020-09-16  6:13         ` Christoph Hellwig
  0 siblings, 1 reply; 15+ messages in thread
From: Mathieu Poirier @ 2020-09-15 19:55 UTC (permalink / raw)
  To: Christoph Hellwig
  Cc: iommu, Russell King, Santosh Shilimkar, Greg Kroah-Hartman,
	Jim Quinlan, Nathan Chancellor, Florian Fainelli, Robin Murphy,
	Rob Herring, Frank Rowand, Ohad Ben-Cohen, Bjorn Andersson,
	linux-remoteproc, linux-usb, linux-arm-kernel, linux-kernel,
	linux-sh, linux-pci, linux-acpi, devicetree, arnaud.pouliquen,
	loic.pallardy.st.com

On Tue, Sep 15, 2020 at 07:41:22AM +0200, Christoph Hellwig wrote:
> On Mon, Sep 14, 2020 at 05:01:47PM -0600, Mathieu Poirier wrote:
> 
> [700 lines of the fullquote deleted..]
> 
> > > +	for (r = map; r->size; r++)
> > > +		num_ranges++;
> > > +
> > > +	new_map = kmemdup(map, array_size(num_ranges + 1, sizeof(*map)),
> > > +			  GFP_KERNEL);
> > > +	if (!new_map)
> > > +		return -ENOMEM;
> > > +	to->dma_range_map = new_map;
> > > +	return 0;
> > > +}
> > > +
> > 
> > This patch seemed Ok to me but it broke the stm32 remoteproc implementation.  When
> > I tested things out function dma_coerce_mask_and_cohenrent() returns -5 and the
> > rest of the initialisation fails.  I isolated things to function dma_to_pfn()
> > [2].  In the original implementation __bus_to_pfn() returns 0xfffff and
> > dev->dma_pfn_offset is equal to 0x38000.  As such the function returns 0x137fff
> > and dma_supported() a non-zero value[3].
> > 
> > With this set function dma_to_pfn() received a face lift.  Function
> > __bus_to_pfn() still returns 0xfffff but translate_dma_to_phys() returns 0,
> > which forces dma_supported() to also return 0 and that is where the -5 (-EIO)
> > comes from.
> > 
> > Taking a futher look at translate_dma_to_phy(), @dma_addr never falls within the
> > bus_dma_region ranges and returns 0.
> > 
> > I'm suspecting an initialisation problem and if it occurred here, it will
> > likely show up elsewhere.
> 
> Can you try this incremental patch?
> 
> diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
> index 088c97181ab146..c6b21acba7a459 100644
> --- a/include/linux/dma-direct.h
> +++ b/include/linux/dma-direct.h
> @@ -46,7 +46,7 @@ static inline phys_addr_t translate_dma_to_phys(struct device *dev,
>  		if (dma_addr >= m->dma_start && dma_addr - m->dma_start < m->size)
>  			return (phys_addr_t)dma_addr + m->offset;
>  
> -	return 0;
> +	return (phys_addr_t)-1;

That did the trick - the stm32 platform driver's probe() function completes and
the remote processor is operatinal. 

That being said the value returned by function dma_to_pfn()
is 0x137fff in the original code and 0xfffff with your patches applied.

Thanks,
Mathieu

>  }
>  
>  #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA

^ permalink raw reply	[flat|nested] 15+ messages in thread

* Re: [PATCH 6/6] dma-mapping: introduce DMA range map, supplanting dma_pfn_offset
  2020-09-14 23:01   ` Mathieu Poirier
@ 2020-09-15  5:41     ` Christoph Hellwig
  2020-09-15 19:55       ` Mathieu Poirier
  0 siblings, 1 reply; 15+ messages in thread
From: Christoph Hellwig @ 2020-09-15  5:41 UTC (permalink / raw)
  To: Mathieu Poirier
  Cc: Christoph Hellwig, iommu, Russell King, Santosh Shilimkar,
	Greg Kroah-Hartman, Jim Quinlan, Nathan Chancellor,
	Florian Fainelli, Robin Murphy, Rob Herring, Frank Rowand,
	Ohad Ben-Cohen, Bjorn Andersson, linux-remoteproc, linux-usb,
	linux-arm-kernel, linux-kernel, linux-sh, linux-pci, linux-acpi,
	devicetree, arnaud.pouliquen, loic.pallardy.st.com

On Mon, Sep 14, 2020 at 05:01:47PM -0600, Mathieu Poirier wrote:

[700 lines of the fullquote deleted..]

> > +	for (r = map; r->size; r++)
> > +		num_ranges++;
> > +
> > +	new_map = kmemdup(map, array_size(num_ranges + 1, sizeof(*map)),
> > +			  GFP_KERNEL);
> > +	if (!new_map)
> > +		return -ENOMEM;
> > +	to->dma_range_map = new_map;
> > +	return 0;
> > +}
> > +
> 
> This patch seemed Ok to me but it broke the stm32 remoteproc implementation.  When
> I tested things out function dma_coerce_mask_and_cohenrent() returns -5 and the
> rest of the initialisation fails.  I isolated things to function dma_to_pfn()
> [2].  In the original implementation __bus_to_pfn() returns 0xfffff and
> dev->dma_pfn_offset is equal to 0x38000.  As such the function returns 0x137fff
> and dma_supported() a non-zero value[3].
> 
> With this set function dma_to_pfn() received a face lift.  Function
> __bus_to_pfn() still returns 0xfffff but translate_dma_to_phys() returns 0,
> which forces dma_supported() to also return 0 and that is where the -5 (-EIO)
> comes from.
> 
> Taking a futher look at translate_dma_to_phy(), @dma_addr never falls within the
> bus_dma_region ranges and returns 0.
> 
> I'm suspecting an initialisation problem and if it occurred here, it will
> likely show up elsewhere.

Can you try this incremental patch?

diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 088c97181ab146..c6b21acba7a459 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -46,7 +46,7 @@ static inline phys_addr_t translate_dma_to_phys(struct device *dev,
 		if (dma_addr >= m->dma_start && dma_addr - m->dma_start < m->size)
 			return (phys_addr_t)dma_addr + m->offset;
 
-	return 0;
+	return (phys_addr_t)-1;
 }
 
 #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA

^ permalink raw reply	[flat|nested] 15+ messages in thread

* Re: [PATCH 6/6] dma-mapping: introduce DMA range map, supplanting dma_pfn_offset
  2020-09-14  7:33 ` [PATCH 6/6] dma-mapping: introduce DMA range map, supplanting dma_pfn_offset Christoph Hellwig
@ 2020-09-14 23:01   ` Mathieu Poirier
  2020-09-15  5:41     ` Christoph Hellwig
  0 siblings, 1 reply; 15+ messages in thread
From: Mathieu Poirier @ 2020-09-14 23:01 UTC (permalink / raw)
  To: Christoph Hellwig
  Cc: iommu, Russell King, Santosh Shilimkar, Greg Kroah-Hartman,
	Jim Quinlan, Nathan Chancellor, Florian Fainelli, Robin Murphy,
	Rob Herring, Frank Rowand, Ohad Ben-Cohen, Bjorn Andersson,
	linux-remoteproc, linux-usb, linux-arm-kernel, linux-kernel,
	linux-sh, linux-pci, linux-acpi, devicetree, arnaud.pouliquen,
	loic.pallardy.st.com

Hi Christoph,

On Mon, Sep 14, 2020 at 09:33:43AM +0200, Christoph Hellwig wrote:
> From: Jim Quinlan <james.quinlan@broadcom.com>
> 
> The new field 'dma_range_map' in struct device is used to facilitate the
> use of single or multiple offsets between mapping regions of cpu addrs and
> dma addrs.  It subsumes the role of "dev->dma_pfn_offset" which was only
> capable of holding a single uniform offset and had no region bounds
> checking.
> 
> The function of_dma_get_range() has been modified so that it takes a single
> argument -- the device node -- and returns a map, NULL, or an error code.
> The map is an array that holds the information regarding the DMA regions.
> Each range entry contains the address offset, the cpu_start address, the
> dma_start address, and the size of the region.
> 
> of_dma_configure() is the typical manner to set range offsets but there are
> a number of ad hoc assignments to "dev->dma_pfn_offset" in the kernel
> driver code.  These cases now invoke the function
> dma_direct_set_offset(dev, cpu_addr, dma_addr, size).
> 
> Signed-off-by: Jim Quinlan <james.quinlan@broadcom.com>
> [hch: various interface cleanups]
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> Tested-by: Nathan Chancellor <natechancellor@gmail.com>
> ---
>  arch/arm/include/asm/dma-direct.h             |  9 +--
>  arch/arm/mach-keystone/keystone.c             | 17 ++---
>  arch/arm/mach-omap1/include/mach/memory.h     |  4 +
>  arch/sh/drivers/pci/pcie-sh7786.c             |  9 ++-
>  arch/x86/pci/sta2x11-fixup.c                  |  6 +-
>  drivers/acpi/arm64/iort.c                     |  6 +-
>  drivers/base/core.c                           |  2 +
>  drivers/gpu/drm/sun4i/sun4i_backend.c         |  8 +-
>  drivers/iommu/io-pgtable-arm.c                |  2 +-
>  .../platform/sunxi/sun4i-csi/sun4i_csi.c      |  9 ++-
>  .../platform/sunxi/sun6i-csi/sun6i_csi.c      | 11 ++-
>  drivers/of/address.c                          | 73 ++++++++-----------
>  drivers/of/device.c                           | 44 ++++++-----
>  drivers/of/of_private.h                       | 11 +--
>  drivers/of/unittest.c                         | 34 ++++++---
>  drivers/remoteproc/remoteproc_core.c          | 24 +++++-
>  .../staging/media/sunxi/cedrus/cedrus_hw.c    | 10 ++-
>  include/linux/device.h                        |  4 +-
>  include/linux/dma-direct.h                    | 52 +++++++++++--
>  include/linux/dma-mapping.h                   |  9 ++-
>  kernel/dma/coherent.c                         |  7 +-
>  kernel/dma/direct.c                           | 51 ++++++++++++-
>  22 files changed, 284 insertions(+), 118 deletions(-)
> 
> diff --git a/arch/arm/include/asm/dma-direct.h b/arch/arm/include/asm/dma-direct.h
> index fbcf4367b5cb1a..436544aeb83405 100644
> --- a/arch/arm/include/asm/dma-direct.h
> +++ b/arch/arm/include/asm/dma-direct.h
> @@ -12,8 +12,8 @@
>  #ifndef __arch_pfn_to_dma
>  static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
>  {
> -	if (dev)
> -		pfn -= dev->dma_pfn_offset;
> +	if (dev && dev->dma_range_map)
> +		pfn = PFN_DOWN(translate_phys_to_dma(dev, PFN_PHYS(pfn)));
>  	return (dma_addr_t)__pfn_to_bus(pfn);
>  }
>  
> @@ -21,9 +21,8 @@ static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
>  {
>  	unsigned long pfn = __bus_to_pfn(addr);
>  
> -	if (dev)
> -		pfn += dev->dma_pfn_offset;
> -
> +	if (dev && dev->dma_range_map)
> +		pfn = PFN_DOWN(translate_dma_to_phys(dev, PFN_PHYS(pfn)));
>  	return pfn;
>  }
>  
> diff --git a/arch/arm/mach-keystone/keystone.c b/arch/arm/mach-keystone/keystone.c
> index dcd031ba84c2e0..09a65c2dfd7327 100644
> --- a/arch/arm/mach-keystone/keystone.c
> +++ b/arch/arm/mach-keystone/keystone.c
> @@ -8,6 +8,7 @@
>   */
>  #include <linux/io.h>
>  #include <linux/of.h>
> +#include <linux/dma-mapping.h>
>  #include <linux/init.h>
>  #include <linux/of_platform.h>
>  #include <linux/of_address.h>
> @@ -25,8 +26,6 @@
>  #include "keystone.h"
>  
>  #ifdef CONFIG_ARM_LPAE
> -static unsigned long keystone_dma_pfn_offset __read_mostly;
> -
>  static int keystone_platform_notifier(struct notifier_block *nb,
>  				      unsigned long event, void *data)
>  {
> @@ -39,9 +38,12 @@ static int keystone_platform_notifier(struct notifier_block *nb,
>  		return NOTIFY_BAD;
>  
>  	if (!dev->of_node) {
> -		dev->dma_pfn_offset = keystone_dma_pfn_offset;
> -		dev_err(dev, "set dma_pfn_offset%08lx\n",
> -			dev->dma_pfn_offset);
> +		int ret = dma_direct_set_offset(dev, KEYSTONE_HIGH_PHYS_START,
> +						KEYSTONE_LOW_PHYS_START,
> +						KEYSTONE_HIGH_PHYS_SIZE);
> +		dev_err(dev, "set dma_offset%08llx%s\n",
> +			KEYSTONE_HIGH_PHYS_START - KEYSTONE_LOW_PHYS_START,
> +			ret ? " failed" : "");
>  	}
>  	return NOTIFY_OK;
>  }
> @@ -54,11 +56,8 @@ static struct notifier_block platform_nb = {
>  static void __init keystone_init(void)
>  {
>  #ifdef CONFIG_ARM_LPAE
> -	if (PHYS_OFFSET >= KEYSTONE_HIGH_PHYS_START) {
> -		keystone_dma_pfn_offset = PFN_DOWN(KEYSTONE_HIGH_PHYS_START -
> -						   KEYSTONE_LOW_PHYS_START);
> +	if (PHYS_OFFSET >= KEYSTONE_HIGH_PHYS_START)
>  		bus_register_notifier(&platform_bus_type, &platform_nb);
> -	}
>  #endif
>  	keystone_pm_runtime_init();
>  }
> diff --git a/arch/arm/mach-omap1/include/mach/memory.h b/arch/arm/mach-omap1/include/mach/memory.h
> index e43697c3297bf2..1142560e0078f5 100644
> --- a/arch/arm/mach-omap1/include/mach/memory.h
> +++ b/arch/arm/mach-omap1/include/mach/memory.h
> @@ -41,6 +41,10 @@
>  	   __phys_to_pfn(__dma);				\
>  	})
>  
> +#define __arch_dma_to_virt(dev, addr)	({ (void *) (is_lbus_device(dev) ? \
> +						lbus_to_virt(addr) : \
> +						__phys_to_virt(addr)); })
> +
>  #define __arch_virt_to_dma(dev, addr)	({ unsigned long __addr = (unsigned long)(addr); \
>  					   (dma_addr_t) (is_lbus_device(dev) ? \
>  						virt_to_lbus(__addr) : \
> diff --git a/arch/sh/drivers/pci/pcie-sh7786.c b/arch/sh/drivers/pci/pcie-sh7786.c
> index e0b568aaa7014c..4468289ab2cac7 100644
> --- a/arch/sh/drivers/pci/pcie-sh7786.c
> +++ b/arch/sh/drivers/pci/pcie-sh7786.c
> @@ -12,6 +12,7 @@
>  #include <linux/io.h>
>  #include <linux/async.h>
>  #include <linux/delay.h>
> +#include <linux/dma-mapping.h>
>  #include <linux/slab.h>
>  #include <linux/clk.h>
>  #include <linux/sh_clk.h>
> @@ -31,6 +32,8 @@ struct sh7786_pcie_port {
>  static struct sh7786_pcie_port *sh7786_pcie_ports;
>  static unsigned int nr_ports;
>  static unsigned long dma_pfn_offset;
> +size_t memsize;
> +u64 memstart;
>  
>  static struct sh7786_pcie_hwops {
>  	int (*core_init)(void);
> @@ -301,7 +304,6 @@ static int __init pcie_init(struct sh7786_pcie_port *port)
>  	struct pci_channel *chan = port->hose;
>  	unsigned int data;
>  	phys_addr_t memstart, memend;
> -	size_t memsize;
>  	int ret, i, win;
>  
>  	/* Begin initialization */
> @@ -368,8 +370,6 @@ static int __init pcie_init(struct sh7786_pcie_port *port)
>  	memstart = ALIGN_DOWN(memstart, memsize);
>  	memsize = roundup_pow_of_two(memend - memstart);
>  
> -	dma_pfn_offset = memstart >> PAGE_SHIFT;
> -
>  	/*
>  	 * If there's more than 512MB of memory, we need to roll over to
>  	 * LAR1/LAMR1.
> @@ -487,7 +487,8 @@ int pcibios_map_platform_irq(const struct pci_dev *pdev, u8 slot, u8 pin)
>  
>  void pcibios_bus_add_device(struct pci_dev *pdev)
>  {
> -	pdev->dev.dma_pfn_offset = dma_pfn_offset;
> +	dma_direct_set_offset(&pdev->dev, __pa(memory_start),
> +			      __pa(memory_start) - memstart, memsize);
>  }
>  
>  static int __init sh7786_pcie_core_init(void)
> diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
> index c313d784efabb9..324a207f99956b 100644
> --- a/arch/x86/pci/sta2x11-fixup.c
> +++ b/arch/x86/pci/sta2x11-fixup.c
> @@ -133,7 +133,7 @@ static void sta2x11_map_ep(struct pci_dev *pdev)
>  	struct sta2x11_instance *instance = sta2x11_pdev_to_instance(pdev);
>  	struct device *dev = &pdev->dev;
>  	u32 amba_base, max_amba_addr;
> -	int i;
> +	int i, ret;
>  
>  	if (!instance)
>  		return;
> @@ -141,7 +141,9 @@ static void sta2x11_map_ep(struct pci_dev *pdev)
>  	pci_read_config_dword(pdev, AHB_BASE(0), &amba_base);
>  	max_amba_addr = amba_base + STA2X11_AMBA_SIZE - 1;
>  
> -	dev->dma_pfn_offset = PFN_DOWN(-amba_base);
> +	ret = dma_direct_set_offset(dev, 0, amba_base, STA2X11_AMBA_SIZE);
> +	if (ret)
> +		dev_err(dev, "sta2x11: could not set DMA offset\n");
>  
>  	dev->bus_dma_limit = max_amba_addr;
>  	pci_set_consistent_dma_mask(pdev, max_amba_addr);
> diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
> index ec782e4a0fe419..de18c07ca02cc4 100644
> --- a/drivers/acpi/arm64/iort.c
> +++ b/drivers/acpi/arm64/iort.c
> @@ -18,6 +18,7 @@
>  #include <linux/pci.h>
>  #include <linux/platform_device.h>
>  #include <linux/slab.h>
> +#include <linux/dma-mapping.h>
>  
>  #define IORT_TYPE_MASK(type)	(1 << (type))
>  #define IORT_MSI_TYPE		(1 << ACPI_IORT_NODE_ITS_GROUP)
> @@ -1184,8 +1185,9 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size)
>  	*dma_addr = dmaaddr;
>  	*dma_size = size;
>  
> -	dev->dma_pfn_offset = PFN_DOWN(offset);
> -	dev_dbg(dev, "dma_pfn_offset(%#08llx)\n", offset);
> +	ret = dma_direct_set_offset(dev, dmaaddr + offset, dmaaddr, size);
> +
> +	dev_dbg(dev, "dma_offset(%#08llx)%s\n", offset, ret ? " failed!" : "");
>  }
>  
>  static void __init acpi_iort_register_irq(int hwirq, const char *name,
> diff --git a/drivers/base/core.c b/drivers/base/core.c
> index f6f620aa94086d..b893056e39459c 100644
> --- a/drivers/base/core.c
> +++ b/drivers/base/core.c
> @@ -1792,6 +1792,8 @@ static void device_release(struct kobject *kobj)
>  	 */
>  	devres_release_all(dev);
>  
> +	kfree(dev->dma_range_map);
> +
>  	if (dev->release)
>  		dev->release(dev);
>  	else if (dev->type && dev->type->release)
> diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c
> index 072ea113e6be55..05e9f0d28196d9 100644
> --- a/drivers/gpu/drm/sun4i/sun4i_backend.c
> +++ b/drivers/gpu/drm/sun4i/sun4i_backend.c
> @@ -11,6 +11,7 @@
>  #include <linux/module.h>
>  #include <linux/of_device.h>
>  #include <linux/of_graph.h>
> +#include <linux/dma-mapping.h>
>  #include <linux/platform_device.h>
>  #include <linux/reset.h>
>  
> @@ -811,8 +812,13 @@ static int sun4i_backend_bind(struct device *dev, struct device *master,
>  		 * because of an old DT, we need to set the DMA offset by hand
>  		 * on our device since the RAM mapping is at 0 for the DMA bus,
>  		 * unlike the CPU.
> +		 *
> +		 * XXX(hch): this has no business in a driver and needs to move
> +		 * to the device tree.
>  		 */
> -		drm->dev->dma_pfn_offset = PHYS_PFN_OFFSET;
> +		ret = dma_direct_set_offset(drm->dev, PHYS_OFFSET, 0, SZ_4G);
> +		if (ret)
> +			return ret;
>  	}
>  
>  	backend->engine.node = dev->of_node;
> diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
> index dc7bcf858b6d2d..d77e881516a4ab 100644
> --- a/drivers/iommu/io-pgtable-arm.c
> +++ b/drivers/iommu/io-pgtable-arm.c
> @@ -751,7 +751,7 @@ arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg)
>  	if (cfg->oas > ARM_LPAE_MAX_ADDR_BITS)
>  		return NULL;
>  
> -	if (!selftest_running && cfg->iommu_dev->dma_pfn_offset) {
> +	if (!selftest_running && cfg->iommu_dev->dma_range_map) {
>  		dev_err(cfg->iommu_dev, "Cannot accommodate DMA offset for IOMMU page tables\n");
>  		return NULL;
>  	}
> diff --git a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
> index 5319eb1ab30927..307997ee7f96a2 100644
> --- a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
> +++ b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
> @@ -7,6 +7,7 @@
>   */
>  
>  #include <linux/clk.h>
> +#include <linux/dma-mapping.h>
>  #include <linux/interrupt.h>
>  #include <linux/module.h>
>  #include <linux/mutex.h>
> @@ -182,8 +183,14 @@ static int sun4i_csi_probe(struct platform_device *pdev)
>  		if (ret)
>  			return ret;
>  	} else {
> +		/*
> +		 * XXX(hch): this has no business in a driver and needs to move
> +		 * to the device tree.
> +		 */
>  #ifdef PHYS_PFN_OFFSET
> -		csi->dev->dma_pfn_offset = PHYS_PFN_OFFSET;
> +		ret = dma_direct_set_offset(csi->dev, PHYS_OFFSET, 0, SZ_4G);
> +		if (ret)
> +			return ret;
>  #endif
>  	}
>  
> diff --git a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c
> index 28e89340fed981..e69e14379fc6e4 100644
> --- a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c
> +++ b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c
> @@ -899,8 +899,15 @@ static int sun6i_csi_probe(struct platform_device *pdev)
>  		return -ENOMEM;
>  
>  	sdev->dev = &pdev->dev;
> -	/* The DMA bus has the memory mapped at 0 */
> -	sdev->dev->dma_pfn_offset = PHYS_OFFSET >> PAGE_SHIFT;
> +	/*
> +	 * The DMA bus has the memory mapped at 0.
> +	 *
> +	 * XXX(hch): this has no business in a driver and needs to move
> +	 * to the device tree.
> +	 */
> +	ret = dma_direct_set_offset(sdev->dev, PHYS_OFFSET, 0, SZ_4G);
> +	if (ret)
> +		return ret;
>  
>  	ret = sun6i_csi_resource_request(sdev, pdev);
>  	if (ret)
> diff --git a/drivers/of/address.c b/drivers/of/address.c
> index da4f7341323f22..a49ef87aaaf21c 100644
> --- a/drivers/of/address.c
> +++ b/drivers/of/address.c
> @@ -13,6 +13,7 @@
>  #include <linux/sizes.h>
>  #include <linux/slab.h>
>  #include <linux/string.h>
> +#include <linux/dma-direct.h> /* for bus_dma_region */
>  
>  #include "of_private.h"
>  
> @@ -937,33 +938,33 @@ void __iomem *of_io_request_and_map(struct device_node *np, int index,
>  }
>  EXPORT_SYMBOL(of_io_request_and_map);
>  
> +#ifdef CONFIG_HAS_DMA
>  /**
> - * of_dma_get_range - Get DMA range info
> + * of_dma_get_range - Get DMA range info and put it into a map array
>   * @np:		device node to get DMA range info
> - * @dma_addr:	pointer to store initial DMA address of DMA range
> - * @paddr:	pointer to store initial CPU address of DMA range
> - * @size:	pointer to store size of DMA range
> + * @map:	dma range structure to return
>   *
>   * Look in bottom up direction for the first "dma-ranges" property
> - * and parse it.
> - *  dma-ranges format:
> + * and parse it.  Put the information into a DMA offset map array.
> + *
> + * dma-ranges format:
>   *	DMA addr (dma_addr)	: naddr cells
>   *	CPU addr (phys_addr_t)	: pna cells
>   *	size			: nsize cells
>   *
> - * It returns -ENODEV if "dma-ranges" property was not found
> - * for this device in DT.
> + * It returns -ENODEV if "dma-ranges" property was not found for this
> + * device in the DT.
>   */
> -int of_dma_get_range(struct device_node *np, u64 *dma_addr, u64 *paddr, u64 *size)
> +int of_dma_get_range(struct device_node *np, const struct bus_dma_region **map)
>  {
>  	struct device_node *node = of_node_get(np);
>  	const __be32 *ranges = NULL;
> -	int len;
> -	int ret = 0;
>  	bool found_dma_ranges = false;
>  	struct of_range_parser parser;
>  	struct of_range range;
> -	u64 dma_start = U64_MAX, dma_end = 0, dma_offset = 0;
> +	struct bus_dma_region *r;
> +	int len, num_ranges = 0;
> +	int ret = 0;
>  
>  	while (node) {
>  		ranges = of_get_property(node, "dma-ranges", &len);
> @@ -989,49 +990,39 @@ int of_dma_get_range(struct device_node *np, u64 *dma_addr, u64 *paddr, u64 *siz
>  	}
>  
>  	of_dma_range_parser_init(&parser, node);
> +	for_each_of_range(&parser, &range)
> +		num_ranges++;
> +
> +	r = kcalloc(num_ranges + 1, sizeof(*r), GFP_KERNEL);
> +	if (!r) {
> +		ret = -ENOMEM;
> + 		goto out;
> +	}
>  
> +	/*
> +	 * Record all info in the generic DMA ranges array for struct device.
> +	 */
> +	*map = r;
> + 	of_dma_range_parser_init(&parser, node);
>  	for_each_of_range(&parser, &range) {
>  		pr_debug("dma_addr(%llx) cpu_addr(%llx) size(%llx)\n",
>  			 range.bus_addr, range.cpu_addr, range.size);
> -
> -		if (dma_offset && range.cpu_addr - range.bus_addr != dma_offset) {
> -			pr_warn("Can't handle multiple dma-ranges with different offsets on node(%pOF)\n", node);
> -			/* Don't error out as we'd break some existing DTs */
> -			continue;
> -		}
>  		if (range.cpu_addr == OF_BAD_ADDR) {
>  			pr_err("translation of DMA address(%llx) to CPU address failed node(%pOF)\n",
>  			       range.bus_addr, node);
>  			continue;
>  		}
> -		dma_offset = range.cpu_addr - range.bus_addr;
> -
> -		/* Take lower and upper limits */
> -		if (range.bus_addr < dma_start)
> -			dma_start = range.bus_addr;
> -		if (range.bus_addr + range.size > dma_end)
> -			dma_end = range.bus_addr + range.size;
> -	}
> -
> -	if (dma_start >= dma_end) {
> -		ret = -EINVAL;
> -		pr_debug("Invalid DMA ranges configuration on node(%pOF)\n",
> -			 node);
> -		goto out;
> +		r->cpu_start = range.cpu_addr;
> +		r->dma_start = range.bus_addr;
> +		r->size = range.size;
> +		r->offset = range.cpu_addr - range.bus_addr;
> +		r++;
>  	}
> -
> -	*dma_addr = dma_start;
> -	*size = dma_end - dma_start;
> -	*paddr = dma_start + dma_offset;
> -
> -	pr_debug("final: dma_addr(%llx) cpu_addr(%llx) size(%llx)\n",
> -		 *dma_addr, *paddr, *size);
> -
>  out:
>  	of_node_put(node);
> -
>  	return ret;
>  }
> +#endif /* CONFIG_HAS_DMA */
>  
>  /**
>   * of_dma_is_coherent - Check if device is coherent
> diff --git a/drivers/of/device.c b/drivers/of/device.c
> index b439c1e054349b..6e3ae7ebc33eeb 100644
> --- a/drivers/of/device.c
> +++ b/drivers/of/device.c
> @@ -5,7 +5,7 @@
>  #include <linux/of_device.h>
>  #include <linux/of_address.h>
>  #include <linux/of_iommu.h>
> -#include <linux/dma-mapping.h>
> +#include <linux/dma-direct.h> /* for bus_dma_region */
>  #include <linux/init.h>
>  #include <linux/module.h>
>  #include <linux/mod_devicetable.h>
> @@ -90,14 +90,14 @@ int of_device_add(struct platform_device *ofdev)
>  int of_dma_configure_id(struct device *dev, struct device_node *np,
>  			bool force_dma, const u32 *id)
>  {
> -	u64 dma_addr, paddr, size = 0;
> -	int ret;
> -	bool coherent;
> -	unsigned long offset;
>  	const struct iommu_ops *iommu;
> -	u64 mask, end;
> +	const struct bus_dma_region *map = NULL;
> +	dma_addr_t dma_start = 0;
> +	u64 mask, end, size = 0;
> +	bool coherent;
> +	int ret;
>  
> -	ret = of_dma_get_range(np, &dma_addr, &paddr, &size);
> +	ret = of_dma_get_range(np, &map);
>  	if (ret < 0) {
>  		/*
>  		 * For legacy reasons, we have to assume some devices need
> @@ -106,26 +106,35 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
>  		 */
>  		if (!force_dma)
>  			return ret == -ENODEV ? 0 : ret;
> -
> -		dma_addr = offset = 0;
>  	} else {
> -		offset = PFN_DOWN(paddr - dma_addr);
> +		const struct bus_dma_region *r = map;
> +		dma_addr_t dma_end = 0;
> +
> +		/* Determine the overall bounds of all DMA regions */
> +		for (dma_start = ~(dma_addr_t)0; r->size; r++) {
> +			/* Take lower and upper limits */
> +			if (r->dma_start < dma_start)
> +				dma_start = r->dma_start;
> +			if (r->dma_start + r->size > dma_end)
> +				dma_end = r->dma_start + r->size;
> +		}
> +		size = dma_end - dma_start;
>  
>  		/*
>  		 * Add a work around to treat the size as mask + 1 in case
>  		 * it is defined in DT as a mask.
>  		 */
>  		if (size & 1) {
> -			dev_warn(dev, "Invalid size 0x%llx for dma-range\n",
> +			dev_warn(dev, "Invalid size 0x%llx for dma-range(s)\n",
>  				 size);
>  			size = size + 1;
>  		}
>  
>  		if (!size) {
>  			dev_err(dev, "Adjusted size 0x%llx invalid\n", size);
> +			kfree(map);
>  			return -EINVAL;
>  		}
> -		dev_dbg(dev, "dma_pfn_offset(%#08lx)\n", offset);
>  	}
>  
>  	/*
> @@ -144,13 +153,11 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
>  	else if (!size)
>  		size = 1ULL << 32;
>  
> -	dev->dma_pfn_offset = offset;
> -
>  	/*
>  	 * Limit coherent and dma mask based on size and default mask
>  	 * set by the driver.
>  	 */
> -	end = dma_addr + size - 1;
> +	end = dma_start + size - 1;
>  	mask = DMA_BIT_MASK(ilog2(end) + 1);
>  	dev->coherent_dma_mask &= mask;
>  	*dev->dma_mask &= mask;
> @@ -163,14 +170,17 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
>  		coherent ? " " : " not ");
>  
>  	iommu = of_iommu_configure(dev, np, id);
> -	if (PTR_ERR(iommu) == -EPROBE_DEFER)
> +	if (PTR_ERR(iommu) == -EPROBE_DEFER) {
> +		kfree(map);
>  		return -EPROBE_DEFER;
> +	}
>  
>  	dev_dbg(dev, "device is%sbehind an iommu\n",
>  		iommu ? " " : " not ");
>  
> -	arch_setup_dma_ops(dev, dma_addr, size, iommu, coherent);
> +	arch_setup_dma_ops(dev, dma_start, size, iommu, coherent);
>  
> +	dev->dma_range_map = map;
>  	return 0;
>  }
>  EXPORT_SYMBOL_GPL(of_dma_configure_id);
> diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h
> index edc682249c0015..d9e6a324de0a77 100644
> --- a/drivers/of/of_private.h
> +++ b/drivers/of/of_private.h
> @@ -157,12 +157,13 @@ extern void __of_sysfs_remove_bin_file(struct device_node *np,
>  extern int of_bus_n_addr_cells(struct device_node *np);
>  extern int of_bus_n_size_cells(struct device_node *np);
>  
> -#ifdef CONFIG_OF_ADDRESS
> -extern int of_dma_get_range(struct device_node *np, u64 *dma_addr,
> -			    u64 *paddr, u64 *size);
> +struct bus_dma_region;
> +#if defined(CONFIG_OF_ADDRESS) && defined(CONFIG_HAS_DMA)
> +int of_dma_get_range(struct device_node *np,
> +		const struct bus_dma_region **map);
>  #else
> -static inline int of_dma_get_range(struct device_node *np, u64 *dma_addr,
> -				   u64 *paddr, u64 *size)
> +static inline int of_dma_get_range(struct device_node *np,
> +		const struct bus_dma_region **map)
>  {
>  	return -ENODEV;
>  }
> diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
> index 9b7e84bdc7d446..06cc988faf78b3 100644
> --- a/drivers/of/unittest.c
> +++ b/drivers/of/unittest.c
> @@ -7,6 +7,7 @@
>  
>  #include <linux/memblock.h>
>  #include <linux/clk.h>
> +#include <linux/dma-direct.h> /* to test phys_to_dma/dma_to_phys */
>  #include <linux/err.h>
>  #include <linux/errno.h>
>  #include <linux/hashtable.h>
> @@ -869,10 +870,11 @@ static void __init of_unittest_changeset(void)
>  }
>  
>  static void __init of_unittest_dma_ranges_one(const char *path,
> -		u64 expect_dma_addr, u64 expect_paddr, u64 expect_size)
> +		u64 expect_dma_addr, u64 expect_paddr)
>  {
> +#ifdef CONFIG_HAS_DMA
>  	struct device_node *np;
> -	u64 dma_addr, paddr, size;
> +	const struct bus_dma_region *map = NULL;
>  	int rc;
>  
>  	np = of_find_node_by_path(path);
> @@ -881,28 +883,40 @@ static void __init of_unittest_dma_ranges_one(const char *path,
>  		return;
>  	}
>  
> -	rc = of_dma_get_range(np, &dma_addr, &paddr, &size);
> +	rc = of_dma_get_range(np, &map);
>  
>  	unittest(!rc, "of_dma_get_range failed on node %pOF rc=%i\n", np, rc);
> +
>  	if (!rc) {
> -		unittest(size == expect_size,
> -			 "of_dma_get_range wrong size on node %pOF size=%llx\n", np, size);
> +		phys_addr_t	paddr;
> +		dma_addr_t	dma_addr;
> +		struct device	dev_bogus;
> +
> +		dev_bogus.dma_range_map = map;
> +		paddr = dma_to_phys(&dev_bogus, expect_dma_addr);
> +		dma_addr = phys_to_dma(&dev_bogus, expect_paddr);
> +
>  		unittest(paddr == expect_paddr,
> -			 "of_dma_get_range wrong phys addr (%llx) on node %pOF", paddr, np);
> +			 "of_dma_get_range: wrong phys addr %pap (expecting %llx) on node %pOF\n",
> +			 &paddr, expect_paddr, np);
>  		unittest(dma_addr == expect_dma_addr,
> -			 "of_dma_get_range wrong DMA addr (%llx) on node %pOF", dma_addr, np);
> +			 "of_dma_get_range: wrong DMA addr %pad (expecting %llx) on node %pOF\n",
> +			 &dma_addr, expect_dma_addr, np);
> +
> +		kfree(map);
>  	}
>  	of_node_put(np);
> +#endif
>  }
>  
>  static void __init of_unittest_parse_dma_ranges(void)
>  {
>  	of_unittest_dma_ranges_one("/testcase-data/address-tests/device@70000000",
> -		0x0, 0x20000000, 0x40000000);
> +		0x0, 0x20000000);
>  	of_unittest_dma_ranges_one("/testcase-data/address-tests/bus@80000000/device@1000",
> -		0x100000000, 0x20000000, 0x2000000000);
> +		0x100000000, 0x20000000);
>  	of_unittest_dma_ranges_one("/testcase-data/address-tests/pci@90000000",
> -		0x80000000, 0x20000000, 0x10000000);
> +		0x80000000, 0x20000000);
>  }
>  
>  static void __init of_unittest_pci_dma_ranges(void)
> diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
> index 7f90eeea67e279..8157dd491d2819 100644
> --- a/drivers/remoteproc/remoteproc_core.c
> +++ b/drivers/remoteproc/remoteproc_core.c
> @@ -23,6 +23,7 @@
>  #include <linux/slab.h>
>  #include <linux/mutex.h>
>  #include <linux/dma-mapping.h>
> +#include <linux/dma-direct.h> /* XXX: pokes into bus_dma_range */
>  #include <linux/firmware.h>
>  #include <linux/string.h>
>  #include <linux/debugfs.h>
> @@ -458,6 +459,25 @@ static void rproc_rvdev_release(struct device *dev)
>  	kfree(rvdev);
>  }
>  
> +static int copy_dma_range_map(struct device *to, struct device *from)
> +{
> +	const struct bus_dma_region *map = from->dma_range_map, *new_map, *r;
> +	int num_ranges = 0;
> +
> +	if (!map)
> +		return 0;
> +
> +	for (r = map; r->size; r++)
> +		num_ranges++;
> +
> +	new_map = kmemdup(map, array_size(num_ranges + 1, sizeof(*map)),
> +			  GFP_KERNEL);
> +	if (!new_map)
> +		return -ENOMEM;
> +	to->dma_range_map = new_map;
> +	return 0;
> +}
> +

This patch seemed Ok to me but it broke the stm32 remoteproc implementation.  When
I tested things out function dma_coerce_mask_and_cohenrent() returns -5 and the
rest of the initialisation fails.  I isolated things to function dma_to_pfn()
[2].  In the original implementation __bus_to_pfn() returns 0xfffff and
dev->dma_pfn_offset is equal to 0x38000.  As such the function returns 0x137fff
and dma_supported() a non-zero value[3].

With this set function dma_to_pfn() received a face lift.  Function
__bus_to_pfn() still returns 0xfffff but translate_dma_to_phys() returns 0,
which forces dma_supported() to also return 0 and that is where the -5 (-EIO)
comes from.

Taking a futher look at translate_dma_to_phy(), @dma_addr never falls within the
bus_dma_region ranges and returns 0.

I'm suspecting an initialisation problem and if it occurred here, it will
likely show up elsewhere.

Thanks,
Mathieu

[1]. https://elixir.bootlin.com/linux/v5.9-rc4/source/drivers/remoteproc/stm32_rproc.c#L773
[2]. https://elixir.bootlin.com/linux/v5.9-rc4/source/arch/arm/include/asm/dma-mapping.h#L43
[3]. https://elixir.bootlin.com/linux/v5.9-rc4/source/kernel/dma/mapping.c#L539 

>  /**
>   * rproc_handle_vdev() - handle a vdev fw resource
>   * @rproc: the remote processor
> @@ -529,7 +549,9 @@ static int rproc_handle_vdev(struct rproc *rproc, struct fw_rsc_vdev *rsc,
>  	/* Initialise vdev subdevice */
>  	snprintf(name, sizeof(name), "vdev%dbuffer", rvdev->index);
>  	rvdev->dev.parent = &rproc->dev;
> -	rvdev->dev.dma_pfn_offset = rproc->dev.parent->dma_pfn_offset;
> +	ret = copy_dma_range_map(&rvdev->dev, rproc->dev.parent);
> +	if (ret)
> +		return ret;
>  	rvdev->dev.release = rproc_rvdev_release;
>  	dev_set_name(&rvdev->dev, "%s#%s", dev_name(rvdev->dev.parent), name);
>  	dev_set_drvdata(&rvdev->dev, rvdev);
> diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_hw.c b/drivers/staging/media/sunxi/cedrus/cedrus_hw.c
> index 1744e6fcc99980..bcf050a04ffc45 100644
> --- a/drivers/staging/media/sunxi/cedrus/cedrus_hw.c
> +++ b/drivers/staging/media/sunxi/cedrus/cedrus_hw.c
> @@ -227,11 +227,17 @@ int cedrus_hw_probe(struct cedrus_dev *dev)
>  	 * the RAM offset to the physcal addresses.
>  	 *
>  	 * This information will eventually be obtained from device-tree.
> +	 *
> +	 * XXX(hch): this has no business in a driver and needs to move
> +	 * to the device tree.
>  	 */
>  
>  #ifdef PHYS_PFN_OFFSET
> -	if (!(variant->quirks & CEDRUS_QUIRK_NO_DMA_OFFSET))
> -		dev->dev->dma_pfn_offset = PHYS_PFN_OFFSET;
> +	if (!(variant->quirks & CEDRUS_QUIRK_NO_DMA_OFFSET)) {
> +		ret = dma_direct_set_offset(dev->dev, PHYS_OFFSET, 0, SZ_4G);
> +		if (ret)
> +			return ret;
> +	}
>  #endif
>  
>  	ret = of_reserved_mem_device_init(dev->dev);
> diff --git a/include/linux/device.h b/include/linux/device.h
> index ca18da4768e3e8..1c78621fc3c01f 100644
> --- a/include/linux/device.h
> +++ b/include/linux/device.h
> @@ -466,7 +466,7 @@ struct dev_links_info {
>   * 		such descriptors.
>   * @bus_dma_limit: Limit of an upstream bridge or bus which imposes a smaller
>   *		DMA limit than the device itself supports.
> - * @dma_pfn_offset: offset of DMA memory range relatively of RAM
> + * @dma_range_map: map for DMA memory ranges relative to that of RAM
>   * @dma_parms:	A low level driver may set these to teach IOMMU code about
>   * 		segment limitations.
>   * @dma_pools:	Dma pools (if dma'ble device).
> @@ -561,7 +561,7 @@ struct device {
>  					     64 bit addresses for consistent
>  					     allocations such descriptors. */
>  	u64		bus_dma_limit;	/* upstream dma constraint */
> -	unsigned long	dma_pfn_offset;
> +	const struct bus_dma_region *dma_range_map;
>  
>  	struct device_dma_parameters *dma_parms;
>  
> diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
> index 805010ea5346f9..bd619579505687 100644
> --- a/include/linux/dma-direct.h
> +++ b/include/linux/dma-direct.h
> @@ -14,6 +14,41 @@
>  
>  extern unsigned int zone_dma_bits;
>  
> +/*
> + * Record the mapping of CPU physical to DMA addresses for a given region.
> + */
> +struct bus_dma_region {
> +	phys_addr_t	cpu_start;
> +	dma_addr_t	dma_start;
> +	u64		size;
> +	u64		offset;
> +};
> +
> +static inline dma_addr_t translate_phys_to_dma(struct device *dev,
> +		phys_addr_t paddr)
> +{
> +	const struct bus_dma_region *m;
> +
> +	for (m = dev->dma_range_map; m->size; m++)
> +		if (paddr >= m->cpu_start && paddr - m->cpu_start < m->size)
> +			return (dma_addr_t)paddr - m->offset;
> +
> +	/* make sure dma_capable fails when no translation is available */
> +	return DMA_MAPPING_ERROR; 
> +}
> +
> +static inline phys_addr_t translate_dma_to_phys(struct device *dev,
> +		dma_addr_t dma_addr)
> +{
> +	const struct bus_dma_region *m;
> +
> +	for (m = dev->dma_range_map; m->size; m++)
> +		if (dma_addr >= m->dma_start && dma_addr - m->dma_start < m->size)
> +			return (phys_addr_t)dma_addr + m->offset;
> +
> +	return 0;
> +}
> +
>  #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA
>  #include <asm/dma-direct.h>
>  #ifndef phys_to_dma_unencrypted
> @@ -23,9 +58,9 @@ extern unsigned int zone_dma_bits;
>  static inline dma_addr_t phys_to_dma_unencrypted(struct device *dev,
>  		phys_addr_t paddr)
>  {
> -	dma_addr_t dev_addr = (dma_addr_t)paddr;
> -
> -	return dev_addr - ((dma_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
> +	if (dev->dma_range_map)
> +		return translate_phys_to_dma(dev, paddr);
> +	return paddr;
>  }
>  
>  /*
> @@ -41,8 +76,12 @@ static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
>  
>  static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
>  {
> -	phys_addr_t paddr = (phys_addr_t)dev_addr +
> -		((phys_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
> +	phys_addr_t paddr;
> +
> +	if (dev->dma_range_map)
> +		paddr = translate_dma_to_phys(dev, dma_addr);
> +	else
> +		paddr = dma_addr;
>  
>  	return __sme_clr(paddr);
>  }
> @@ -64,7 +103,8 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size,
>  
>  	if (!dev->dma_mask)
>  		return false;
> -
> +	if (addr == DMA_MAPPING_ERROR)
> +		return false;
>  	if (is_ram && !IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) &&
>  	    min(addr, end) < phys_to_dma(dev, PFN_PHYS(min_low_pfn)))
>  		return false;
> diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
> index df0bff2ea750e0..bb138ac6f5e63e 100644
> --- a/include/linux/dma-mapping.h
> +++ b/include/linux/dma-mapping.h
> @@ -730,4 +730,11 @@ static inline int dma_mmap_wc(struct device *dev,
>  #define dma_unmap_len_set(PTR, LEN_NAME, VAL)    do { } while (0)
>  #endif
>  
> -#endif
> +/*
> + * Legacy interface to set up the dma offset map.  Drivers really should not
> + * actually use it, but we have a few legacy cases left.
> + */
> +int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
> +		dma_addr_t dma_start, u64 size);
> +
> +#endif /* _LINUX_DMA_MAPPING_H */
> diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c
> index f85d14bbfcbe03..c0685196fb6d42 100644
> --- a/kernel/dma/coherent.c
> +++ b/kernel/dma/coherent.c
> @@ -7,7 +7,7 @@
>  #include <linux/slab.h>
>  #include <linux/kernel.h>
>  #include <linux/module.h>
> -#include <linux/dma-mapping.h>
> +#include <linux/dma-direct.h>
>  
>  struct dma_coherent_mem {
>  	void		*virt_base;
> @@ -32,9 +32,8 @@ static inline dma_addr_t dma_get_device_base(struct device *dev,
>  					     struct dma_coherent_mem * mem)
>  {
>  	if (mem->use_dev_dma_pfn_offset)
> -		return (mem->pfn_base - dev->dma_pfn_offset) << PAGE_SHIFT;
> -	else
> -		return mem->device_base;
> +		return phys_to_dma(dev, PFN_PHYS(mem->pfn_base));
> +	return mem->device_base;
>  }
>  
>  static int dma_init_coherent_memory(phys_addr_t phys_addr,
> diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
> index 54db9cfdaecc6d..750659f7447c4b 100644
> --- a/kernel/dma/direct.c
> +++ b/kernel/dma/direct.c
> @@ -13,6 +13,7 @@
>  #include <linux/pfn.h>
>  #include <linux/vmalloc.h>
>  #include <linux/set_memory.h>
> +#include <linux/slab.h>
>  
>  /*
>   * Most architectures use ZONE_DMA for the first 16 Megabytes, but some use it
> @@ -66,8 +67,12 @@ static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
>  
>  static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
>  {
> -	return phys_to_dma_direct(dev, phys) + size - 1 <=
> -			min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
> +	dma_addr_t dma_addr = phys_to_dma_direct(dev, phys);
> +
> +	if (dma_addr == DMA_MAPPING_ERROR)
> +		return false;
> +	return dma_addr + size - 1 <=
> +		min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
>  }
>  
>  /*
> @@ -461,3 +466,45 @@ bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr)
>  	return !dev_is_dma_coherent(dev) ||
>  		is_swiotlb_buffer(dma_to_phys(dev, dma_addr));
>  }
> +
> +/**
> + * dma_direct_set_offset - Assign scalar offset for a single DMA range.
> + * @dev:	device pointer; needed to "own" the alloced memory.
> + * @cpu_start:  beginning of memory region covered by this offset.
> + * @dma_start:  beginning of DMA/PCI region covered by this offset.
> + * @size:	size of the region.
> + *
> + * This is for the simple case of a uniform offset which cannot
> + * be discovered by "dma-ranges".
> + *
> + * It returns -ENOMEM if out of memory, -EINVAL if a map
> + * already exists, 0 otherwise.
> + *
> + * Note: any call to this from a driver is a bug.  The mapping needs
> + * to be described by the device tree or other firmware interfaces.
> + */
> +int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
> +			 dma_addr_t dma_start, u64 size)
> +{
> +	struct bus_dma_region *map;
> +	u64 offset = (u64)cpu_start - (u64)dma_start;
> +
> +	if (dev->dma_range_map) {
> +		dev_err(dev, "attempt to add DMA range to existing map\n");
> +		return -EINVAL;
> +	}
> +
> +	if (!offset)
> +		return 0;
> +
> +	map = kcalloc(2, sizeof(*map), GFP_KERNEL);
> +	if (!map)
> +		return -ENOMEM;
> +	map[0].cpu_start = cpu_start;
> +	map[0].dma_start = dma_start;
> +	map[0].offset = offset;
> +	map[0].size = size;
> +	dev->dma_range_map = map;
> +	return 0;
> +}
> +EXPORT_SYMBOL_GPL(dma_direct_set_offset);
> -- 
> 2.28.0
> 

^ permalink raw reply	[flat|nested] 15+ messages in thread

* [PATCH 6/6] dma-mapping: introduce DMA range map, supplanting dma_pfn_offset
  2020-09-14  7:33 support range based offsets in dma-direct v2 Christoph Hellwig
@ 2020-09-14  7:33 ` Christoph Hellwig
  2020-09-14 23:01   ` Mathieu Poirier
  0 siblings, 1 reply; 15+ messages in thread
From: Christoph Hellwig @ 2020-09-14  7:33 UTC (permalink / raw)
  To: iommu, Russell King, Santosh Shilimkar, Greg Kroah-Hartman
  Cc: Jim Quinlan, Nathan Chancellor, Florian Fainelli, Robin Murphy,
	Rob Herring, Frank Rowand, Ohad Ben-Cohen, Bjorn Andersson,
	linux-remoteproc, linux-usb, linux-arm-kernel, linux-kernel,
	linux-sh, linux-pci, linux-acpi, devicetree

From: Jim Quinlan <james.quinlan@broadcom.com>

The new field 'dma_range_map' in struct device is used to facilitate the
use of single or multiple offsets between mapping regions of cpu addrs and
dma addrs.  It subsumes the role of "dev->dma_pfn_offset" which was only
capable of holding a single uniform offset and had no region bounds
checking.

The function of_dma_get_range() has been modified so that it takes a single
argument -- the device node -- and returns a map, NULL, or an error code.
The map is an array that holds the information regarding the DMA regions.
Each range entry contains the address offset, the cpu_start address, the
dma_start address, and the size of the region.

of_dma_configure() is the typical manner to set range offsets but there are
a number of ad hoc assignments to "dev->dma_pfn_offset" in the kernel
driver code.  These cases now invoke the function
dma_direct_set_offset(dev, cpu_addr, dma_addr, size).

Signed-off-by: Jim Quinlan <james.quinlan@broadcom.com>
[hch: various interface cleanups]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Nathan Chancellor <natechancellor@gmail.com>
---
 arch/arm/include/asm/dma-direct.h             |  9 +--
 arch/arm/mach-keystone/keystone.c             | 17 ++---
 arch/arm/mach-omap1/include/mach/memory.h     |  4 +
 arch/sh/drivers/pci/pcie-sh7786.c             |  9 ++-
 arch/x86/pci/sta2x11-fixup.c                  |  6 +-
 drivers/acpi/arm64/iort.c                     |  6 +-
 drivers/base/core.c                           |  2 +
 drivers/gpu/drm/sun4i/sun4i_backend.c         |  8 +-
 drivers/iommu/io-pgtable-arm.c                |  2 +-
 .../platform/sunxi/sun4i-csi/sun4i_csi.c      |  9 ++-
 .../platform/sunxi/sun6i-csi/sun6i_csi.c      | 11 ++-
 drivers/of/address.c                          | 73 ++++++++-----------
 drivers/of/device.c                           | 44 ++++++-----
 drivers/of/of_private.h                       | 11 +--
 drivers/of/unittest.c                         | 34 ++++++---
 drivers/remoteproc/remoteproc_core.c          | 24 +++++-
 .../staging/media/sunxi/cedrus/cedrus_hw.c    | 10 ++-
 include/linux/device.h                        |  4 +-
 include/linux/dma-direct.h                    | 52 +++++++++++--
 include/linux/dma-mapping.h                   |  9 ++-
 kernel/dma/coherent.c                         |  7 +-
 kernel/dma/direct.c                           | 51 ++++++++++++-
 22 files changed, 284 insertions(+), 118 deletions(-)

diff --git a/arch/arm/include/asm/dma-direct.h b/arch/arm/include/asm/dma-direct.h
index fbcf4367b5cb1a..436544aeb83405 100644
--- a/arch/arm/include/asm/dma-direct.h
+++ b/arch/arm/include/asm/dma-direct.h
@@ -12,8 +12,8 @@
 #ifndef __arch_pfn_to_dma
 static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
 {
-	if (dev)
-		pfn -= dev->dma_pfn_offset;
+	if (dev && dev->dma_range_map)
+		pfn = PFN_DOWN(translate_phys_to_dma(dev, PFN_PHYS(pfn)));
 	return (dma_addr_t)__pfn_to_bus(pfn);
 }
 
@@ -21,9 +21,8 @@ static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
 {
 	unsigned long pfn = __bus_to_pfn(addr);
 
-	if (dev)
-		pfn += dev->dma_pfn_offset;
-
+	if (dev && dev->dma_range_map)
+		pfn = PFN_DOWN(translate_dma_to_phys(dev, PFN_PHYS(pfn)));
 	return pfn;
 }
 
diff --git a/arch/arm/mach-keystone/keystone.c b/arch/arm/mach-keystone/keystone.c
index dcd031ba84c2e0..09a65c2dfd7327 100644
--- a/arch/arm/mach-keystone/keystone.c
+++ b/arch/arm/mach-keystone/keystone.c
@@ -8,6 +8,7 @@
  */
 #include <linux/io.h>
 #include <linux/of.h>
+#include <linux/dma-mapping.h>
 #include <linux/init.h>
 #include <linux/of_platform.h>
 #include <linux/of_address.h>
@@ -25,8 +26,6 @@
 #include "keystone.h"
 
 #ifdef CONFIG_ARM_LPAE
-static unsigned long keystone_dma_pfn_offset __read_mostly;
-
 static int keystone_platform_notifier(struct notifier_block *nb,
 				      unsigned long event, void *data)
 {
@@ -39,9 +38,12 @@ static int keystone_platform_notifier(struct notifier_block *nb,
 		return NOTIFY_BAD;
 
 	if (!dev->of_node) {
-		dev->dma_pfn_offset = keystone_dma_pfn_offset;
-		dev_err(dev, "set dma_pfn_offset%08lx\n",
-			dev->dma_pfn_offset);
+		int ret = dma_direct_set_offset(dev, KEYSTONE_HIGH_PHYS_START,
+						KEYSTONE_LOW_PHYS_START,
+						KEYSTONE_HIGH_PHYS_SIZE);
+		dev_err(dev, "set dma_offset%08llx%s\n",
+			KEYSTONE_HIGH_PHYS_START - KEYSTONE_LOW_PHYS_START,
+			ret ? " failed" : "");
 	}
 	return NOTIFY_OK;
 }
@@ -54,11 +56,8 @@ static struct notifier_block platform_nb = {
 static void __init keystone_init(void)
 {
 #ifdef CONFIG_ARM_LPAE
-	if (PHYS_OFFSET >= KEYSTONE_HIGH_PHYS_START) {
-		keystone_dma_pfn_offset = PFN_DOWN(KEYSTONE_HIGH_PHYS_START -
-						   KEYSTONE_LOW_PHYS_START);
+	if (PHYS_OFFSET >= KEYSTONE_HIGH_PHYS_START)
 		bus_register_notifier(&platform_bus_type, &platform_nb);
-	}
 #endif
 	keystone_pm_runtime_init();
 }
diff --git a/arch/arm/mach-omap1/include/mach/memory.h b/arch/arm/mach-omap1/include/mach/memory.h
index e43697c3297bf2..1142560e0078f5 100644
--- a/arch/arm/mach-omap1/include/mach/memory.h
+++ b/arch/arm/mach-omap1/include/mach/memory.h
@@ -41,6 +41,10 @@
 	   __phys_to_pfn(__dma);				\
 	})
 
+#define __arch_dma_to_virt(dev, addr)	({ (void *) (is_lbus_device(dev) ? \
+						lbus_to_virt(addr) : \
+						__phys_to_virt(addr)); })
+
 #define __arch_virt_to_dma(dev, addr)	({ unsigned long __addr = (unsigned long)(addr); \
 					   (dma_addr_t) (is_lbus_device(dev) ? \
 						virt_to_lbus(__addr) : \
diff --git a/arch/sh/drivers/pci/pcie-sh7786.c b/arch/sh/drivers/pci/pcie-sh7786.c
index e0b568aaa7014c..4468289ab2cac7 100644
--- a/arch/sh/drivers/pci/pcie-sh7786.c
+++ b/arch/sh/drivers/pci/pcie-sh7786.c
@@ -12,6 +12,7 @@
 #include <linux/io.h>
 #include <linux/async.h>
 #include <linux/delay.h>
+#include <linux/dma-mapping.h>
 #include <linux/slab.h>
 #include <linux/clk.h>
 #include <linux/sh_clk.h>
@@ -31,6 +32,8 @@ struct sh7786_pcie_port {
 static struct sh7786_pcie_port *sh7786_pcie_ports;
 static unsigned int nr_ports;
 static unsigned long dma_pfn_offset;
+size_t memsize;
+u64 memstart;
 
 static struct sh7786_pcie_hwops {
 	int (*core_init)(void);
@@ -301,7 +304,6 @@ static int __init pcie_init(struct sh7786_pcie_port *port)
 	struct pci_channel *chan = port->hose;
 	unsigned int data;
 	phys_addr_t memstart, memend;
-	size_t memsize;
 	int ret, i, win;
 
 	/* Begin initialization */
@@ -368,8 +370,6 @@ static int __init pcie_init(struct sh7786_pcie_port *port)
 	memstart = ALIGN_DOWN(memstart, memsize);
 	memsize = roundup_pow_of_two(memend - memstart);
 
-	dma_pfn_offset = memstart >> PAGE_SHIFT;
-
 	/*
 	 * If there's more than 512MB of memory, we need to roll over to
 	 * LAR1/LAMR1.
@@ -487,7 +487,8 @@ int pcibios_map_platform_irq(const struct pci_dev *pdev, u8 slot, u8 pin)
 
 void pcibios_bus_add_device(struct pci_dev *pdev)
 {
-	pdev->dev.dma_pfn_offset = dma_pfn_offset;
+	dma_direct_set_offset(&pdev->dev, __pa(memory_start),
+			      __pa(memory_start) - memstart, memsize);
 }
 
 static int __init sh7786_pcie_core_init(void)
diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
index c313d784efabb9..324a207f99956b 100644
--- a/arch/x86/pci/sta2x11-fixup.c
+++ b/arch/x86/pci/sta2x11-fixup.c
@@ -133,7 +133,7 @@ static void sta2x11_map_ep(struct pci_dev *pdev)
 	struct sta2x11_instance *instance = sta2x11_pdev_to_instance(pdev);
 	struct device *dev = &pdev->dev;
 	u32 amba_base, max_amba_addr;
-	int i;
+	int i, ret;
 
 	if (!instance)
 		return;
@@ -141,7 +141,9 @@ static void sta2x11_map_ep(struct pci_dev *pdev)
 	pci_read_config_dword(pdev, AHB_BASE(0), &amba_base);
 	max_amba_addr = amba_base + STA2X11_AMBA_SIZE - 1;
 
-	dev->dma_pfn_offset = PFN_DOWN(-amba_base);
+	ret = dma_direct_set_offset(dev, 0, amba_base, STA2X11_AMBA_SIZE);
+	if (ret)
+		dev_err(dev, "sta2x11: could not set DMA offset\n");
 
 	dev->bus_dma_limit = max_amba_addr;
 	pci_set_consistent_dma_mask(pdev, max_amba_addr);
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index ec782e4a0fe419..de18c07ca02cc4 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -18,6 +18,7 @@
 #include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
+#include <linux/dma-mapping.h>
 
 #define IORT_TYPE_MASK(type)	(1 << (type))
 #define IORT_MSI_TYPE		(1 << ACPI_IORT_NODE_ITS_GROUP)
@@ -1184,8 +1185,9 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size)
 	*dma_addr = dmaaddr;
 	*dma_size = size;
 
-	dev->dma_pfn_offset = PFN_DOWN(offset);
-	dev_dbg(dev, "dma_pfn_offset(%#08llx)\n", offset);
+	ret = dma_direct_set_offset(dev, dmaaddr + offset, dmaaddr, size);
+
+	dev_dbg(dev, "dma_offset(%#08llx)%s\n", offset, ret ? " failed!" : "");
 }
 
 static void __init acpi_iort_register_irq(int hwirq, const char *name,
diff --git a/drivers/base/core.c b/drivers/base/core.c
index f6f620aa94086d..b893056e39459c 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -1792,6 +1792,8 @@ static void device_release(struct kobject *kobj)
 	 */
 	devres_release_all(dev);
 
+	kfree(dev->dma_range_map);
+
 	if (dev->release)
 		dev->release(dev);
 	else if (dev->type && dev->type->release)
diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c
index 072ea113e6be55..05e9f0d28196d9 100644
--- a/drivers/gpu/drm/sun4i/sun4i_backend.c
+++ b/drivers/gpu/drm/sun4i/sun4i_backend.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/of_device.h>
 #include <linux/of_graph.h>
+#include <linux/dma-mapping.h>
 #include <linux/platform_device.h>
 #include <linux/reset.h>
 
@@ -811,8 +812,13 @@ static int sun4i_backend_bind(struct device *dev, struct device *master,
 		 * because of an old DT, we need to set the DMA offset by hand
 		 * on our device since the RAM mapping is at 0 for the DMA bus,
 		 * unlike the CPU.
+		 *
+		 * XXX(hch): this has no business in a driver and needs to move
+		 * to the device tree.
 		 */
-		drm->dev->dma_pfn_offset = PHYS_PFN_OFFSET;
+		ret = dma_direct_set_offset(drm->dev, PHYS_OFFSET, 0, SZ_4G);
+		if (ret)
+			return ret;
 	}
 
 	backend->engine.node = dev->of_node;
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index dc7bcf858b6d2d..d77e881516a4ab 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -751,7 +751,7 @@ arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg)
 	if (cfg->oas > ARM_LPAE_MAX_ADDR_BITS)
 		return NULL;
 
-	if (!selftest_running && cfg->iommu_dev->dma_pfn_offset) {
+	if (!selftest_running && cfg->iommu_dev->dma_range_map) {
 		dev_err(cfg->iommu_dev, "Cannot accommodate DMA offset for IOMMU page tables\n");
 		return NULL;
 	}
diff --git a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
index 5319eb1ab30927..307997ee7f96a2 100644
--- a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
+++ b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/clk.h>
+#include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
@@ -182,8 +183,14 @@ static int sun4i_csi_probe(struct platform_device *pdev)
 		if (ret)
 			return ret;
 	} else {
+		/*
+		 * XXX(hch): this has no business in a driver and needs to move
+		 * to the device tree.
+		 */
 #ifdef PHYS_PFN_OFFSET
-		csi->dev->dma_pfn_offset = PHYS_PFN_OFFSET;
+		ret = dma_direct_set_offset(csi->dev, PHYS_OFFSET, 0, SZ_4G);
+		if (ret)
+			return ret;
 #endif
 	}
 
diff --git a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c
index 28e89340fed981..e69e14379fc6e4 100644
--- a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c
+++ b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c
@@ -899,8 +899,15 @@ static int sun6i_csi_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	sdev->dev = &pdev->dev;
-	/* The DMA bus has the memory mapped at 0 */
-	sdev->dev->dma_pfn_offset = PHYS_OFFSET >> PAGE_SHIFT;
+	/*
+	 * The DMA bus has the memory mapped at 0.
+	 *
+	 * XXX(hch): this has no business in a driver and needs to move
+	 * to the device tree.
+	 */
+	ret = dma_direct_set_offset(sdev->dev, PHYS_OFFSET, 0, SZ_4G);
+	if (ret)
+		return ret;
 
 	ret = sun6i_csi_resource_request(sdev, pdev);
 	if (ret)
diff --git a/drivers/of/address.c b/drivers/of/address.c
index da4f7341323f22..a49ef87aaaf21c 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -13,6 +13,7 @@
 #include <linux/sizes.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/dma-direct.h> /* for bus_dma_region */
 
 #include "of_private.h"
 
@@ -937,33 +938,33 @@ void __iomem *of_io_request_and_map(struct device_node *np, int index,
 }
 EXPORT_SYMBOL(of_io_request_and_map);
 
+#ifdef CONFIG_HAS_DMA
 /**
- * of_dma_get_range - Get DMA range info
+ * of_dma_get_range - Get DMA range info and put it into a map array
  * @np:		device node to get DMA range info
- * @dma_addr:	pointer to store initial DMA address of DMA range
- * @paddr:	pointer to store initial CPU address of DMA range
- * @size:	pointer to store size of DMA range
+ * @map:	dma range structure to return
  *
  * Look in bottom up direction for the first "dma-ranges" property
- * and parse it.
- *  dma-ranges format:
+ * and parse it.  Put the information into a DMA offset map array.
+ *
+ * dma-ranges format:
  *	DMA addr (dma_addr)	: naddr cells
  *	CPU addr (phys_addr_t)	: pna cells
  *	size			: nsize cells
  *
- * It returns -ENODEV if "dma-ranges" property was not found
- * for this device in DT.
+ * It returns -ENODEV if "dma-ranges" property was not found for this
+ * device in the DT.
  */
-int of_dma_get_range(struct device_node *np, u64 *dma_addr, u64 *paddr, u64 *size)
+int of_dma_get_range(struct device_node *np, const struct bus_dma_region **map)
 {
 	struct device_node *node = of_node_get(np);
 	const __be32 *ranges = NULL;
-	int len;
-	int ret = 0;
 	bool found_dma_ranges = false;
 	struct of_range_parser parser;
 	struct of_range range;
-	u64 dma_start = U64_MAX, dma_end = 0, dma_offset = 0;
+	struct bus_dma_region *r;
+	int len, num_ranges = 0;
+	int ret = 0;
 
 	while (node) {
 		ranges = of_get_property(node, "dma-ranges", &len);
@@ -989,49 +990,39 @@ int of_dma_get_range(struct device_node *np, u64 *dma_addr, u64 *paddr, u64 *siz
 	}
 
 	of_dma_range_parser_init(&parser, node);
+	for_each_of_range(&parser, &range)
+		num_ranges++;
+
+	r = kcalloc(num_ranges + 1, sizeof(*r), GFP_KERNEL);
+	if (!r) {
+		ret = -ENOMEM;
+ 		goto out;
+	}
 
+	/*
+	 * Record all info in the generic DMA ranges array for struct device.
+	 */
+	*map = r;
+ 	of_dma_range_parser_init(&parser, node);
 	for_each_of_range(&parser, &range) {
 		pr_debug("dma_addr(%llx) cpu_addr(%llx) size(%llx)\n",
 			 range.bus_addr, range.cpu_addr, range.size);
-
-		if (dma_offset && range.cpu_addr - range.bus_addr != dma_offset) {
-			pr_warn("Can't handle multiple dma-ranges with different offsets on node(%pOF)\n", node);
-			/* Don't error out as we'd break some existing DTs */
-			continue;
-		}
 		if (range.cpu_addr == OF_BAD_ADDR) {
 			pr_err("translation of DMA address(%llx) to CPU address failed node(%pOF)\n",
 			       range.bus_addr, node);
 			continue;
 		}
-		dma_offset = range.cpu_addr - range.bus_addr;
-
-		/* Take lower and upper limits */
-		if (range.bus_addr < dma_start)
-			dma_start = range.bus_addr;
-		if (range.bus_addr + range.size > dma_end)
-			dma_end = range.bus_addr + range.size;
-	}
-
-	if (dma_start >= dma_end) {
-		ret = -EINVAL;
-		pr_debug("Invalid DMA ranges configuration on node(%pOF)\n",
-			 node);
-		goto out;
+		r->cpu_start = range.cpu_addr;
+		r->dma_start = range.bus_addr;
+		r->size = range.size;
+		r->offset = range.cpu_addr - range.bus_addr;
+		r++;
 	}
-
-	*dma_addr = dma_start;
-	*size = dma_end - dma_start;
-	*paddr = dma_start + dma_offset;
-
-	pr_debug("final: dma_addr(%llx) cpu_addr(%llx) size(%llx)\n",
-		 *dma_addr, *paddr, *size);
-
 out:
 	of_node_put(node);
-
 	return ret;
 }
+#endif /* CONFIG_HAS_DMA */
 
 /**
  * of_dma_is_coherent - Check if device is coherent
diff --git a/drivers/of/device.c b/drivers/of/device.c
index b439c1e054349b..6e3ae7ebc33eeb 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -5,7 +5,7 @@
 #include <linux/of_device.h>
 #include <linux/of_address.h>
 #include <linux/of_iommu.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-direct.h> /* for bus_dma_region */
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mod_devicetable.h>
@@ -90,14 +90,14 @@ int of_device_add(struct platform_device *ofdev)
 int of_dma_configure_id(struct device *dev, struct device_node *np,
 			bool force_dma, const u32 *id)
 {
-	u64 dma_addr, paddr, size = 0;
-	int ret;
-	bool coherent;
-	unsigned long offset;
 	const struct iommu_ops *iommu;
-	u64 mask, end;
+	const struct bus_dma_region *map = NULL;
+	dma_addr_t dma_start = 0;
+	u64 mask, end, size = 0;
+	bool coherent;
+	int ret;
 
-	ret = of_dma_get_range(np, &dma_addr, &paddr, &size);
+	ret = of_dma_get_range(np, &map);
 	if (ret < 0) {
 		/*
 		 * For legacy reasons, we have to assume some devices need
@@ -106,26 +106,35 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
 		 */
 		if (!force_dma)
 			return ret == -ENODEV ? 0 : ret;
-
-		dma_addr = offset = 0;
 	} else {
-		offset = PFN_DOWN(paddr - dma_addr);
+		const struct bus_dma_region *r = map;
+		dma_addr_t dma_end = 0;
+
+		/* Determine the overall bounds of all DMA regions */
+		for (dma_start = ~(dma_addr_t)0; r->size; r++) {
+			/* Take lower and upper limits */
+			if (r->dma_start < dma_start)
+				dma_start = r->dma_start;
+			if (r->dma_start + r->size > dma_end)
+				dma_end = r->dma_start + r->size;
+		}
+		size = dma_end - dma_start;
 
 		/*
 		 * Add a work around to treat the size as mask + 1 in case
 		 * it is defined in DT as a mask.
 		 */
 		if (size & 1) {
-			dev_warn(dev, "Invalid size 0x%llx for dma-range\n",
+			dev_warn(dev, "Invalid size 0x%llx for dma-range(s)\n",
 				 size);
 			size = size + 1;
 		}
 
 		if (!size) {
 			dev_err(dev, "Adjusted size 0x%llx invalid\n", size);
+			kfree(map);
 			return -EINVAL;
 		}
-		dev_dbg(dev, "dma_pfn_offset(%#08lx)\n", offset);
 	}
 
 	/*
@@ -144,13 +153,11 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
 	else if (!size)
 		size = 1ULL << 32;
 
-	dev->dma_pfn_offset = offset;
-
 	/*
 	 * Limit coherent and dma mask based on size and default mask
 	 * set by the driver.
 	 */
-	end = dma_addr + size - 1;
+	end = dma_start + size - 1;
 	mask = DMA_BIT_MASK(ilog2(end) + 1);
 	dev->coherent_dma_mask &= mask;
 	*dev->dma_mask &= mask;
@@ -163,14 +170,17 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
 		coherent ? " " : " not ");
 
 	iommu = of_iommu_configure(dev, np, id);
-	if (PTR_ERR(iommu) == -EPROBE_DEFER)
+	if (PTR_ERR(iommu) == -EPROBE_DEFER) {
+		kfree(map);
 		return -EPROBE_DEFER;
+	}
 
 	dev_dbg(dev, "device is%sbehind an iommu\n",
 		iommu ? " " : " not ");
 
-	arch_setup_dma_ops(dev, dma_addr, size, iommu, coherent);
+	arch_setup_dma_ops(dev, dma_start, size, iommu, coherent);
 
+	dev->dma_range_map = map;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(of_dma_configure_id);
diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h
index edc682249c0015..d9e6a324de0a77 100644
--- a/drivers/of/of_private.h
+++ b/drivers/of/of_private.h
@@ -157,12 +157,13 @@ extern void __of_sysfs_remove_bin_file(struct device_node *np,
 extern int of_bus_n_addr_cells(struct device_node *np);
 extern int of_bus_n_size_cells(struct device_node *np);
 
-#ifdef CONFIG_OF_ADDRESS
-extern int of_dma_get_range(struct device_node *np, u64 *dma_addr,
-			    u64 *paddr, u64 *size);
+struct bus_dma_region;
+#if defined(CONFIG_OF_ADDRESS) && defined(CONFIG_HAS_DMA)
+int of_dma_get_range(struct device_node *np,
+		const struct bus_dma_region **map);
 #else
-static inline int of_dma_get_range(struct device_node *np, u64 *dma_addr,
-				   u64 *paddr, u64 *size)
+static inline int of_dma_get_range(struct device_node *np,
+		const struct bus_dma_region **map)
 {
 	return -ENODEV;
 }
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index 9b7e84bdc7d446..06cc988faf78b3 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -7,6 +7,7 @@
 
 #include <linux/memblock.h>
 #include <linux/clk.h>
+#include <linux/dma-direct.h> /* to test phys_to_dma/dma_to_phys */
 #include <linux/err.h>
 #include <linux/errno.h>
 #include <linux/hashtable.h>
@@ -869,10 +870,11 @@ static void __init of_unittest_changeset(void)
 }
 
 static void __init of_unittest_dma_ranges_one(const char *path,
-		u64 expect_dma_addr, u64 expect_paddr, u64 expect_size)
+		u64 expect_dma_addr, u64 expect_paddr)
 {
+#ifdef CONFIG_HAS_DMA
 	struct device_node *np;
-	u64 dma_addr, paddr, size;
+	const struct bus_dma_region *map = NULL;
 	int rc;
 
 	np = of_find_node_by_path(path);
@@ -881,28 +883,40 @@ static void __init of_unittest_dma_ranges_one(const char *path,
 		return;
 	}
 
-	rc = of_dma_get_range(np, &dma_addr, &paddr, &size);
+	rc = of_dma_get_range(np, &map);
 
 	unittest(!rc, "of_dma_get_range failed on node %pOF rc=%i\n", np, rc);
+
 	if (!rc) {
-		unittest(size == expect_size,
-			 "of_dma_get_range wrong size on node %pOF size=%llx\n", np, size);
+		phys_addr_t	paddr;
+		dma_addr_t	dma_addr;
+		struct device	dev_bogus;
+
+		dev_bogus.dma_range_map = map;
+		paddr = dma_to_phys(&dev_bogus, expect_dma_addr);
+		dma_addr = phys_to_dma(&dev_bogus, expect_paddr);
+
 		unittest(paddr == expect_paddr,
-			 "of_dma_get_range wrong phys addr (%llx) on node %pOF", paddr, np);
+			 "of_dma_get_range: wrong phys addr %pap (expecting %llx) on node %pOF\n",
+			 &paddr, expect_paddr, np);
 		unittest(dma_addr == expect_dma_addr,
-			 "of_dma_get_range wrong DMA addr (%llx) on node %pOF", dma_addr, np);
+			 "of_dma_get_range: wrong DMA addr %pad (expecting %llx) on node %pOF\n",
+			 &dma_addr, expect_dma_addr, np);
+
+		kfree(map);
 	}
 	of_node_put(np);
+#endif
 }
 
 static void __init of_unittest_parse_dma_ranges(void)
 {
 	of_unittest_dma_ranges_one("/testcase-data/address-tests/device@70000000",
-		0x0, 0x20000000, 0x40000000);
+		0x0, 0x20000000);
 	of_unittest_dma_ranges_one("/testcase-data/address-tests/bus@80000000/device@1000",
-		0x100000000, 0x20000000, 0x2000000000);
+		0x100000000, 0x20000000);
 	of_unittest_dma_ranges_one("/testcase-data/address-tests/pci@90000000",
-		0x80000000, 0x20000000, 0x10000000);
+		0x80000000, 0x20000000);
 }
 
 static void __init of_unittest_pci_dma_ranges(void)
diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index 7f90eeea67e279..8157dd491d2819 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -23,6 +23,7 @@
 #include <linux/slab.h>
 #include <linux/mutex.h>
 #include <linux/dma-mapping.h>
+#include <linux/dma-direct.h> /* XXX: pokes into bus_dma_range */
 #include <linux/firmware.h>
 #include <linux/string.h>
 #include <linux/debugfs.h>
@@ -458,6 +459,25 @@ static void rproc_rvdev_release(struct device *dev)
 	kfree(rvdev);
 }
 
+static int copy_dma_range_map(struct device *to, struct device *from)
+{
+	const struct bus_dma_region *map = from->dma_range_map, *new_map, *r;
+	int num_ranges = 0;
+
+	if (!map)
+		return 0;
+
+	for (r = map; r->size; r++)
+		num_ranges++;
+
+	new_map = kmemdup(map, array_size(num_ranges + 1, sizeof(*map)),
+			  GFP_KERNEL);
+	if (!new_map)
+		return -ENOMEM;
+	to->dma_range_map = new_map;
+	return 0;
+}
+
 /**
  * rproc_handle_vdev() - handle a vdev fw resource
  * @rproc: the remote processor
@@ -529,7 +549,9 @@ static int rproc_handle_vdev(struct rproc *rproc, struct fw_rsc_vdev *rsc,
 	/* Initialise vdev subdevice */
 	snprintf(name, sizeof(name), "vdev%dbuffer", rvdev->index);
 	rvdev->dev.parent = &rproc->dev;
-	rvdev->dev.dma_pfn_offset = rproc->dev.parent->dma_pfn_offset;
+	ret = copy_dma_range_map(&rvdev->dev, rproc->dev.parent);
+	if (ret)
+		return ret;
 	rvdev->dev.release = rproc_rvdev_release;
 	dev_set_name(&rvdev->dev, "%s#%s", dev_name(rvdev->dev.parent), name);
 	dev_set_drvdata(&rvdev->dev, rvdev);
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_hw.c b/drivers/staging/media/sunxi/cedrus/cedrus_hw.c
index 1744e6fcc99980..bcf050a04ffc45 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_hw.c
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_hw.c
@@ -227,11 +227,17 @@ int cedrus_hw_probe(struct cedrus_dev *dev)
 	 * the RAM offset to the physcal addresses.
 	 *
 	 * This information will eventually be obtained from device-tree.
+	 *
+	 * XXX(hch): this has no business in a driver and needs to move
+	 * to the device tree.
 	 */
 
 #ifdef PHYS_PFN_OFFSET
-	if (!(variant->quirks & CEDRUS_QUIRK_NO_DMA_OFFSET))
-		dev->dev->dma_pfn_offset = PHYS_PFN_OFFSET;
+	if (!(variant->quirks & CEDRUS_QUIRK_NO_DMA_OFFSET)) {
+		ret = dma_direct_set_offset(dev->dev, PHYS_OFFSET, 0, SZ_4G);
+		if (ret)
+			return ret;
+	}
 #endif
 
 	ret = of_reserved_mem_device_init(dev->dev);
diff --git a/include/linux/device.h b/include/linux/device.h
index ca18da4768e3e8..1c78621fc3c01f 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -466,7 +466,7 @@ struct dev_links_info {
  * 		such descriptors.
  * @bus_dma_limit: Limit of an upstream bridge or bus which imposes a smaller
  *		DMA limit than the device itself supports.
- * @dma_pfn_offset: offset of DMA memory range relatively of RAM
+ * @dma_range_map: map for DMA memory ranges relative to that of RAM
  * @dma_parms:	A low level driver may set these to teach IOMMU code about
  * 		segment limitations.
  * @dma_pools:	Dma pools (if dma'ble device).
@@ -561,7 +561,7 @@ struct device {
 					     64 bit addresses for consistent
 					     allocations such descriptors. */
 	u64		bus_dma_limit;	/* upstream dma constraint */
-	unsigned long	dma_pfn_offset;
+	const struct bus_dma_region *dma_range_map;
 
 	struct device_dma_parameters *dma_parms;
 
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 805010ea5346f9..bd619579505687 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -14,6 +14,41 @@
 
 extern unsigned int zone_dma_bits;
 
+/*
+ * Record the mapping of CPU physical to DMA addresses for a given region.
+ */
+struct bus_dma_region {
+	phys_addr_t	cpu_start;
+	dma_addr_t	dma_start;
+	u64		size;
+	u64		offset;
+};
+
+static inline dma_addr_t translate_phys_to_dma(struct device *dev,
+		phys_addr_t paddr)
+{
+	const struct bus_dma_region *m;
+
+	for (m = dev->dma_range_map; m->size; m++)
+		if (paddr >= m->cpu_start && paddr - m->cpu_start < m->size)
+			return (dma_addr_t)paddr - m->offset;
+
+	/* make sure dma_capable fails when no translation is available */
+	return DMA_MAPPING_ERROR; 
+}
+
+static inline phys_addr_t translate_dma_to_phys(struct device *dev,
+		dma_addr_t dma_addr)
+{
+	const struct bus_dma_region *m;
+
+	for (m = dev->dma_range_map; m->size; m++)
+		if (dma_addr >= m->dma_start && dma_addr - m->dma_start < m->size)
+			return (phys_addr_t)dma_addr + m->offset;
+
+	return 0;
+}
+
 #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA
 #include <asm/dma-direct.h>
 #ifndef phys_to_dma_unencrypted
@@ -23,9 +58,9 @@ extern unsigned int zone_dma_bits;
 static inline dma_addr_t phys_to_dma_unencrypted(struct device *dev,
 		phys_addr_t paddr)
 {
-	dma_addr_t dev_addr = (dma_addr_t)paddr;
-
-	return dev_addr - ((dma_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
+	if (dev->dma_range_map)
+		return translate_phys_to_dma(dev, paddr);
+	return paddr;
 }
 
 /*
@@ -41,8 +76,12 @@ static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 
 static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
 {
-	phys_addr_t paddr = (phys_addr_t)dev_addr +
-		((phys_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
+	phys_addr_t paddr;
+
+	if (dev->dma_range_map)
+		paddr = translate_dma_to_phys(dev, dma_addr);
+	else
+		paddr = dma_addr;
 
 	return __sme_clr(paddr);
 }
@@ -64,7 +103,8 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size,
 
 	if (!dev->dma_mask)
 		return false;
-
+	if (addr == DMA_MAPPING_ERROR)
+		return false;
 	if (is_ram && !IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) &&
 	    min(addr, end) < phys_to_dma(dev, PFN_PHYS(min_low_pfn)))
 		return false;
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index df0bff2ea750e0..bb138ac6f5e63e 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -730,4 +730,11 @@ static inline int dma_mmap_wc(struct device *dev,
 #define dma_unmap_len_set(PTR, LEN_NAME, VAL)    do { } while (0)
 #endif
 
-#endif
+/*
+ * Legacy interface to set up the dma offset map.  Drivers really should not
+ * actually use it, but we have a few legacy cases left.
+ */
+int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
+		dma_addr_t dma_start, u64 size);
+
+#endif /* _LINUX_DMA_MAPPING_H */
diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c
index f85d14bbfcbe03..c0685196fb6d42 100644
--- a/kernel/dma/coherent.c
+++ b/kernel/dma/coherent.c
@@ -7,7 +7,7 @@
 #include <linux/slab.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-direct.h>
 
 struct dma_coherent_mem {
 	void		*virt_base;
@@ -32,9 +32,8 @@ static inline dma_addr_t dma_get_device_base(struct device *dev,
 					     struct dma_coherent_mem * mem)
 {
 	if (mem->use_dev_dma_pfn_offset)
-		return (mem->pfn_base - dev->dma_pfn_offset) << PAGE_SHIFT;
-	else
-		return mem->device_base;
+		return phys_to_dma(dev, PFN_PHYS(mem->pfn_base));
+	return mem->device_base;
 }
 
 static int dma_init_coherent_memory(phys_addr_t phys_addr,
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 54db9cfdaecc6d..750659f7447c4b 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -13,6 +13,7 @@
 #include <linux/pfn.h>
 #include <linux/vmalloc.h>
 #include <linux/set_memory.h>
+#include <linux/slab.h>
 
 /*
  * Most architectures use ZONE_DMA for the first 16 Megabytes, but some use it
@@ -66,8 +67,12 @@ static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 
 static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
 {
-	return phys_to_dma_direct(dev, phys) + size - 1 <=
-			min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
+	dma_addr_t dma_addr = phys_to_dma_direct(dev, phys);
+
+	if (dma_addr == DMA_MAPPING_ERROR)
+		return false;
+	return dma_addr + size - 1 <=
+		min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
 }
 
 /*
@@ -461,3 +466,45 @@ bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr)
 	return !dev_is_dma_coherent(dev) ||
 		is_swiotlb_buffer(dma_to_phys(dev, dma_addr));
 }
+
+/**
+ * dma_direct_set_offset - Assign scalar offset for a single DMA range.
+ * @dev:	device pointer; needed to "own" the alloced memory.
+ * @cpu_start:  beginning of memory region covered by this offset.
+ * @dma_start:  beginning of DMA/PCI region covered by this offset.
+ * @size:	size of the region.
+ *
+ * This is for the simple case of a uniform offset which cannot
+ * be discovered by "dma-ranges".
+ *
+ * It returns -ENOMEM if out of memory, -EINVAL if a map
+ * already exists, 0 otherwise.
+ *
+ * Note: any call to this from a driver is a bug.  The mapping needs
+ * to be described by the device tree or other firmware interfaces.
+ */
+int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
+			 dma_addr_t dma_start, u64 size)
+{
+	struct bus_dma_region *map;
+	u64 offset = (u64)cpu_start - (u64)dma_start;
+
+	if (dev->dma_range_map) {
+		dev_err(dev, "attempt to add DMA range to existing map\n");
+		return -EINVAL;
+	}
+
+	if (!offset)
+		return 0;
+
+	map = kcalloc(2, sizeof(*map), GFP_KERNEL);
+	if (!map)
+		return -ENOMEM;
+	map[0].cpu_start = cpu_start;
+	map[0].dma_start = dma_start;
+	map[0].offset = offset;
+	map[0].size = size;
+	dev->dma_range_map = map;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dma_direct_set_offset);
-- 
2.28.0


^ permalink raw reply	[flat|nested] 15+ messages in thread

end of thread, back to index

Thread overview: 15+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-09-16  6:14 support range based offsets in dma-direct v3 Christoph Hellwig
2020-09-16  6:14 ` [PATCH 1/6] ARM/dma-mapping: remove a __arch_page_to_dma #error Christoph Hellwig
2020-09-16  6:14 ` [PATCH 2/6] ARM/dma-mapping: remove dma_to_virt Christoph Hellwig
2020-09-16  6:14 ` [PATCH 3/6] ARM/dma-mapping: move various helpers from dma-mapping.h to dma-direct.h Christoph Hellwig
2020-09-16  6:14 ` [PATCH 4/6] ARM/keystone: move the DMA offset handling under ifdef CONFIG_ARM_LPAE Christoph Hellwig
2020-09-16  6:14 ` [PATCH 5/6] usb: don't inherity DMA properties for USB devices Christoph Hellwig
2020-09-16  6:14 ` [PATCH 6/6] dma-mapping: introduce DMA range map, supplanting dma_pfn_offset Christoph Hellwig
2020-09-16 17:36   ` Mathieu Poirier
2020-10-26 15:33   ` Geert Uytterhoeven
2020-09-17 16:45 ` support range based offsets in dma-direct v3 Christoph Hellwig
  -- strict thread matches above, loose matches on Subject: below --
2020-09-14  7:33 support range based offsets in dma-direct v2 Christoph Hellwig
2020-09-14  7:33 ` [PATCH 6/6] dma-mapping: introduce DMA range map, supplanting dma_pfn_offset Christoph Hellwig
2020-09-14 23:01   ` Mathieu Poirier
2020-09-15  5:41     ` Christoph Hellwig
2020-09-15 19:55       ` Mathieu Poirier
2020-09-16  6:13         ` Christoph Hellwig

Linux-ACPI Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-acpi/0 linux-acpi/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-acpi linux-acpi/ https://lore.kernel.org/linux-acpi \
		linux-acpi@vger.kernel.org
	public-inbox-index linux-acpi

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-acpi


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git