It seem that addition of cache support for M-class CPUs uncovered
latent bug in DMA usage. NOMMU memory model has been treated as being
always consistent; however, for R/M CPU classes memory can be covered
by MPU which in turn might configure RAM as Normal i.e. bufferable and
cacheable. It breaks dma_alloc_coherent() and friends, since data can
stuck in caches now or be buffered.
This patch set is trying to address the issue by providing region of
memory suitable for consistent DMA operations. It is supposed that
such region is marked by MPU as non-cacheable. Robin suggested to
advertise such memory as reserved shared-dma-pool, rather then using
homebrew command line option, and extend dma-coherent to provide
default DMA area in the similar way as it is done for CMA (PATCH
4/7). It allows us to offload all bookkeeping on generic coherent DMA
framework, and it seems that it might be reused by other architectures
like c6x and blackfin.
While reviewing/testing previous vesrions of the patch set it turned
out that dma-coherent does not take into account "dma-ranges" device
tree property, so it is addressed in PATCH 3/7.
For ARM, dedicated DMA region is required for cases other than:
- MMU/MPU is off
- cpu is v7m w/o cache support
- device is coherent
In case one of the above conditions is true dma operations are forced
to be coherent and wired with dma_noop_ops.
To make life easier NOMMU dma operations are kept in separate
compilation unit.
Since the issue was reported in the same time as Benjamin sent his
patch [1] to allow mmap for NOMMU, his case is also addressed in this
series (PATCH 1/7 and PATCH 2/7).
Thanks!
[1] http://www.armlinux.org.uk/developer/patches/viewpatch.php?id=8633/1
Cc: Joerg Roedel <[email protected]>
Cc: Christian Borntraeger <[email protected]>
Cc: Michal Nazarewicz <[email protected]>
Cc: Marek Szyprowski <[email protected]>
Cc: Alan Stern <[email protected]>
Cc: Yoshinori Sato <[email protected]>
Cc: Rich Felker <[email protected]>
Cc: Roger Quadros <[email protected]>
Cc: Greg Kroah-Hartman <[email protected]>
Cc: Rob Herring <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Doug Ledford <[email protected]>
Changelog:
v3 -> v4
- rebased on v4.11-rc7
- made CONFIG_ARM_DMA_MEM_BUFFERABLE optional for CPU_V7M
- added Arnd's Acked-by
v2 -> v3
- fixed warnings reported by Alexandre and kbuild robot
v1 -> v2
- rebased on v4.11-rc1
- added Robin's Reviewed-by
- dedicated flag is introduced to use dev->dma_pfn_offset
rather than mem->device_base in case memory region is
configured via device tree (so Tested-by discarded there)
RFC v6 -> v1
- dropped RFC tag
- added Alexandre's Tested-by
Vladimir Murzin (7):
dma: Take into account dma_pfn_offset
dma: Add simple dma_noop_mmap
drivers: dma-coherent: Account dma_pfn_offset when used with device
tree
drivers: dma-coherent: Introduce default DMA pool
ARM: NOMMU: Introduce dma operations for noMMU
ARM: NOMMU: Set ARM_DMA_MEM_BUFFERABLE for M-class cpus
ARM: dma-mapping: Remove traces of NOMMU code
.../bindings/reserved-memory/reserved-memory.txt | 3 +
arch/arm/Kconfig | 1 +
arch/arm/include/asm/dma-mapping.h | 2 +-
arch/arm/mm/Kconfig | 4 +-
arch/arm/mm/Makefile | 5 +-
arch/arm/mm/dma-mapping-nommu.c | 253 +++++++++++++++++++++
arch/arm/mm/dma-mapping.c | 29 +--
drivers/base/dma-coherent.c | 74 +++++-
lib/dma-noop.c | 29 ++-
9 files changed, 355 insertions(+), 45 deletions(-)
create mode 100644 arch/arm/mm/dma-mapping-nommu.c
--
2.0.0
This patch adds a simple implementation of mmap to dma_noop_ops.
Cc: Joerg Roedel <[email protected]>
Cc: Christian Borntraeger <[email protected]>
Reported-by: Benjamin Gaignard <[email protected]>
Tested-by: Benjamin Gaignard <[email protected]>
Tested-by: Andras Szemzo <[email protected]>
Tested-by: Alexandre TORGUE <[email protected]>
Signed-off-by: Vladimir Murzin <[email protected]>
---
lib/dma-noop.c | 21 +++++++++++++++++++++
1 file changed, 21 insertions(+)
diff --git a/lib/dma-noop.c b/lib/dma-noop.c
index ff4ef5e..0acc3f6 100644
--- a/lib/dma-noop.c
+++ b/lib/dma-noop.c
@@ -66,6 +66,26 @@ static int dma_noop_supported(struct device *dev, u64 mask)
return 1;
}
+static int dma_noop_mmap(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ unsigned long attrs)
+{
+ unsigned long user_count = vma_pages(vma);
+ unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+ unsigned long pfn = page_to_pfn(virt_to_page(cpu_addr));
+ unsigned long off = vma->vm_pgoff;
+ int ret = -ENXIO;
+
+ if (off < count && user_count <= (count - off)) {
+ ret = remap_pfn_range(vma, vma->vm_start,
+ pfn + off,
+ user_count << PAGE_SHIFT,
+ vma->vm_page_prot);
+ }
+
+ return ret;
+}
+
const struct dma_map_ops dma_noop_ops = {
.alloc = dma_noop_alloc,
.free = dma_noop_free,
@@ -73,6 +93,7 @@ const struct dma_map_ops dma_noop_ops = {
.map_sg = dma_noop_map_sg,
.mapping_error = dma_noop_mapping_error,
.dma_supported = dma_noop_supported,
+ .mmap = dma_noop_mmap,
};
EXPORT_SYMBOL(dma_noop_ops);
--
2.0.0
DMA operations for NOMMU case have been just factored out into
separate compilation unit, so don't keep dead code.
Tested-by: Benjamin Gaignard <[email protected]>
Tested-by: Andras Szemzo <[email protected]>
Tested-by: Alexandre TORGUE <[email protected]>
Signed-off-by: Vladimir Murzin <[email protected]>
Acked-by: Arnd Bergmann <[email protected]>
---
arch/arm/mm/dma-mapping.c | 29 ++---------------------------
1 file changed, 2 insertions(+), 27 deletions(-)
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 475811f..cd90338 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -344,8 +344,6 @@ static void __dma_free_buffer(struct page *page, size_t size)
}
}
-#ifdef CONFIG_MMU
-
static void *__alloc_from_contiguous(struct device *dev, size_t size,
pgprot_t prot, struct page **ret_page,
const void *caller, bool want_vaddr,
@@ -647,22 +645,6 @@ static inline pgprot_t __get_dma_pgprot(unsigned long attrs, pgprot_t prot)
return prot;
}
-#define nommu() 0
-
-#else /* !CONFIG_MMU */
-
-#define nommu() 1
-
-#define __get_dma_pgprot(attrs, prot) __pgprot(0)
-#define __alloc_remap_buffer(dev, size, gfp, prot, ret, c, wv) NULL
-#define __alloc_from_pool(size, ret_page) NULL
-#define __alloc_from_contiguous(dev, size, prot, ret, c, wv, coherent_flag, gfp) NULL
-#define __free_from_pool(cpu_addr, size) do { } while (0)
-#define __free_from_contiguous(dev, page, cpu_addr, size, wv) do { } while (0)
-#define __dma_free_remap(cpu_addr, size) do { } while (0)
-
-#endif /* CONFIG_MMU */
-
static void *__alloc_simple_buffer(struct device *dev, size_t size, gfp_t gfp,
struct page **ret_page)
{
@@ -805,7 +787,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
if (cma)
buf->allocator = &cma_allocator;
- else if (nommu() || is_coherent)
+ else if (is_coherent)
buf->allocator = &simple_allocator;
else if (allowblock)
buf->allocator = &remap_allocator;
@@ -854,8 +836,7 @@ static int __arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
void *cpu_addr, dma_addr_t dma_addr, size_t size,
unsigned long attrs)
{
- int ret = -ENXIO;
-#ifdef CONFIG_MMU
+ int ret;
unsigned long nr_vma_pages = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
unsigned long pfn = dma_to_pfn(dev, dma_addr);
@@ -870,10 +851,6 @@ static int __arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
vma->vm_end - vma->vm_start,
vma->vm_page_prot);
}
-#else
- ret = vm_iomap_memory(vma, vma->vm_start,
- (vma->vm_end - vma->vm_start));
-#endif /* CONFIG_MMU */
return ret;
}
@@ -892,9 +869,7 @@ int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
void *cpu_addr, dma_addr_t dma_addr, size_t size,
unsigned long attrs)
{
-#ifdef CONFIG_MMU
vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
-#endif /* CONFIG_MMU */
return __arm_dma_mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
}
--
2.0.0
Now, we have dedicated non-cacheable region for consistent DMA
operations. However, that region can still be marked as bufferable by
MPU, so it'd be safer to have barriers by default.
Tested-by: Benjamin Gaignard <[email protected]>
Tested-by: Andras Szemzo <[email protected]>
Tested-by: Alexandre TORGUE <[email protected]>
Reviewed-by: Robin Murphy <[email protected]>
Signed-off-by: Vladimir Murzin <[email protected]>
---
arch/arm/mm/Kconfig | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index d731f28..7e357c6 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -1049,8 +1049,8 @@ config ARM_L1_CACHE_SHIFT
default 5
config ARM_DMA_MEM_BUFFERABLE
- bool "Use non-cacheable memory for DMA" if (CPU_V6 || CPU_V6K) && !CPU_V7
- default y if CPU_V6 || CPU_V6K || CPU_V7
+ bool "Use non-cacheable memory for DMA" if (CPU_V6 || CPU_V6K || CPU_V7M) && !CPU_V7
+ default y if CPU_V6 || CPU_V6K || CPU_V7 || CPU_V7M
help
Historically, the kernel has used strongly ordered mappings to
provide DMA coherent memory. With the advent of ARMv7, mapping
--
2.0.0
R/M classes of cpus can have memory covered by MPU which in turn might
configure RAM as Normal i.e. bufferable and cacheable. It breaks
dma_alloc_coherent() and friends, since data can stuck in caches now
or be buffered.
This patch factors out DMA support for NOMMU configuration into
separate entity which provides dedicated dma_ops. We have to handle
there several cases:
- configurations with MMU/MPU setup
- configurations without MMU/MPU setup
- special case for M-class, since caches and MPU there are optional
In general we rely on default DMA area for coherent allocations or/and
per-device memory reserves suitable for coherent DMA, so if such
regions are set coherent allocations go from there.
In case MMU/MPU was not setup we fallback to normal page allocator for
DMA memory allocation.
In case we run M-class cpus, for configuration without cache support
(like Cortex-M3/M4) dma operations are forced to be coherent and wired
with dma-noop (such decision is made based on cacheid global
variable); however, if caches are detected there and no DMA coherent
region is given (either default or per-device), dma is disallowed even
MPU is not set - it is because M-class implement system memory map
which defines part of address space as Normal memory.
Reported-by: Alexandre Torgue <[email protected]>
Reported-by: Andras Szemzo <[email protected]>
Tested-by: Benjamin Gaignard <[email protected]>
Tested-by: Andras Szemzo <[email protected]>
Tested-by: Alexandre TORGUE <[email protected]>
Reviewed-by: Robin Murphy <[email protected]>
Signed-off-by: Vladimir Murzin <[email protected]>
Acked-by: Arnd Bergmann <[email protected]>
---
arch/arm/Kconfig | 1 +
arch/arm/include/asm/dma-mapping.h | 2 +-
arch/arm/mm/Makefile | 5 +-
arch/arm/mm/dma-mapping-nommu.c | 253 +++++++++++++++++++++++++++++++++++++
4 files changed, 257 insertions(+), 4 deletions(-)
create mode 100644 arch/arm/mm/dma-mapping-nommu.c
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 6ab63fa..8f0b6ca 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -22,6 +22,7 @@ config ARM
select CLONE_BACKWARDS
select CPU_PM if (SUSPEND || CPU_IDLE)
select DCACHE_WORD_ACCESS if HAVE_EFFICIENT_UNALIGNED_ACCESS
+ select DMA_NOOP_OPS if !MMU
select EDAC_SUPPORT
select EDAC_ATOMIC_SCRUB
select GENERIC_ALLOCATOR
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index 7166569..63270de 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -20,7 +20,7 @@ static inline const struct dma_map_ops *__generic_dma_ops(struct device *dev)
{
if (dev && dev->dma_ops)
return dev->dma_ops;
- return &arm_dma_ops;
+ return IS_ENABLED(CONFIG_MMU) ? &arm_dma_ops : &dma_noop_ops;
}
static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index 54857bc..ea80df7 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -2,9 +2,8 @@
# Makefile for the linux arm-specific parts of the memory manager.
#
-obj-y := dma-mapping.o extable.o fault.o init.o \
- iomap.o
-
+obj-y := extable.o fault.o init.o iomap.o
+obj-y += dma-mapping$(MMUEXT).o
obj-$(CONFIG_MMU) += fault-armv.o flush.o idmap.o ioremap.o \
mmap.o pgd.o mmu.o pageattr.o
diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c
new file mode 100644
index 0000000..3ba3003
--- /dev/null
+++ b/arch/arm/mm/dma-mapping-nommu.c
@@ -0,0 +1,253 @@
+/*
+ * Based on linux/arch/arm/mm/dma-mapping.c
+ *
+ * Copyright (C) 2000-2004 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/dma-mapping.h>
+#include <linux/scatterlist.h>
+
+#include <asm/cachetype.h>
+#include <asm/cacheflush.h>
+#include <asm/outercache.h>
+#include <asm/cp15.h>
+
+#include "dma.h"
+
+/*
+ * dma_noop_ops is used if
+ * - MMU/MPU is off
+ * - cpu is v7m w/o cache support
+ * - device is coherent
+ * otherwise arm_nommu_dma_ops is used.
+ *
+ * arm_nommu_dma_ops rely on consistent DMA memory (please, refer to
+ * [1] on how to declare such memory).
+ *
+ * [1] Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt
+ */
+
+static void *arm_nommu_dma_alloc(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t gfp,
+ unsigned long attrs)
+
+{
+ const struct dma_map_ops *ops = &dma_noop_ops;
+
+ /*
+ * We are here because:
+ * - no consistent DMA region has been defined, so we can't
+ * continue.
+ * - there is no space left in consistent DMA region, so we
+ * only can fallback to generic allocator if we are
+ * advertised that consistency is not required.
+ */
+
+ if (attrs & DMA_ATTR_NON_CONSISTENT)
+ return ops->alloc(dev, size, dma_handle, gfp, attrs);
+
+ WARN_ON_ONCE(1);
+ return NULL;
+}
+
+static void arm_nommu_dma_free(struct device *dev, size_t size,
+ void *cpu_addr, dma_addr_t dma_addr,
+ unsigned long attrs)
+{
+ const struct dma_map_ops *ops = &dma_noop_ops;
+
+ if (attrs & DMA_ATTR_NON_CONSISTENT)
+ ops->free(dev, size, cpu_addr, dma_addr, attrs);
+ else
+ WARN_ON_ONCE(1);
+
+ return;
+}
+
+static int arm_nommu_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ unsigned long attrs)
+{
+ const struct dma_map_ops *ops = &dma_noop_ops;
+ int ret;
+
+ if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
+ return ret;
+
+ if (attrs & DMA_ATTR_NON_CONSISTENT)
+ return ops->mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
+
+ WARN_ON_ONCE(1);
+ return -ENXIO;
+}
+
+static void __dma_page_cpu_to_dev(phys_addr_t paddr, size_t size,
+ enum dma_data_direction dir)
+{
+ dmac_map_area(__va(paddr), size, dir);
+
+ if (dir == DMA_FROM_DEVICE)
+ outer_inv_range(paddr, paddr + size);
+ else
+ outer_clean_range(paddr, paddr + size);
+}
+
+static void __dma_page_dev_to_cpu(phys_addr_t paddr, size_t size,
+ enum dma_data_direction dir)
+{
+ if (dir != DMA_TO_DEVICE) {
+ outer_inv_range(paddr, paddr + size);
+ dmac_unmap_area(__va(paddr), size, dir);
+ }
+}
+
+static dma_addr_t arm_nommu_dma_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ dma_addr_t handle = page_to_phys(page) + offset;
+
+ __dma_page_cpu_to_dev(handle, size, dir);
+
+ return handle;
+}
+
+static void arm_nommu_dma_unmap_page(struct device *dev, dma_addr_t handle,
+ size_t size, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ __dma_page_dev_to_cpu(handle, size, dir);
+}
+
+
+static int arm_nommu_dma_map_sg(struct device *dev, struct scatterlist *sgl,
+ int nents, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ int i;
+ struct scatterlist *sg;
+
+ for_each_sg(sgl, sg, nents, i) {
+ sg_dma_address(sg) = sg_phys(sg);
+ sg_dma_len(sg) = sg->length;
+ __dma_page_cpu_to_dev(sg_dma_address(sg), sg_dma_len(sg), dir);
+ }
+
+ return nents;
+}
+
+static void arm_nommu_dma_unmap_sg(struct device *dev, struct scatterlist *sgl,
+ int nents, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ struct scatterlist *sg;
+ int i;
+
+ for_each_sg(sgl, sg, nents, i)
+ __dma_page_dev_to_cpu(sg_dma_address(sg), sg_dma_len(sg), dir);
+}
+
+static void arm_nommu_dma_sync_single_for_device(struct device *dev,
+ dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+ __dma_page_cpu_to_dev(handle, size, dir);
+}
+
+static void arm_nommu_dma_sync_single_for_cpu(struct device *dev,
+ dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+ __dma_page_cpu_to_dev(handle, size, dir);
+}
+
+static void arm_nommu_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
+ int nents, enum dma_data_direction dir)
+{
+ struct scatterlist *sg;
+ int i;
+
+ for_each_sg(sgl, sg, nents, i)
+ __dma_page_cpu_to_dev(sg_dma_address(sg), sg_dma_len(sg), dir);
+}
+
+static void arm_nommu_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl,
+ int nents, enum dma_data_direction dir)
+{
+ struct scatterlist *sg;
+ int i;
+
+ for_each_sg(sgl, sg, nents, i)
+ __dma_page_dev_to_cpu(sg_dma_address(sg), sg_dma_len(sg), dir);
+}
+
+const struct dma_map_ops arm_nommu_dma_ops = {
+ .alloc = arm_nommu_dma_alloc,
+ .free = arm_nommu_dma_free,
+ .mmap = arm_nommu_dma_mmap,
+ .map_page = arm_nommu_dma_map_page,
+ .unmap_page = arm_nommu_dma_unmap_page,
+ .map_sg = arm_nommu_dma_map_sg,
+ .unmap_sg = arm_nommu_dma_unmap_sg,
+ .sync_single_for_device = arm_nommu_dma_sync_single_for_device,
+ .sync_single_for_cpu = arm_nommu_dma_sync_single_for_cpu,
+ .sync_sg_for_device = arm_nommu_dma_sync_sg_for_device,
+ .sync_sg_for_cpu = arm_nommu_dma_sync_sg_for_cpu,
+};
+EXPORT_SYMBOL(arm_nommu_dma_ops);
+
+static const struct dma_map_ops *arm_nommu_get_dma_map_ops(bool coherent)
+{
+ return coherent ? &dma_noop_ops : &arm_nommu_dma_ops;
+}
+
+void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
+ const struct iommu_ops *iommu, bool coherent)
+{
+ const struct dma_map_ops *dma_ops;
+
+ if (IS_ENABLED(CONFIG_CPU_V7M)) {
+ /*
+ * Cache support for v7m is optional, so can be treated as
+ * coherent if no cache has been detected. Note that it is not
+ * enough to check if MPU is in use or not since in absense of
+ * MPU system memory map is used.
+ */
+ dev->archdata.dma_coherent = (cacheid) ? coherent : true;
+ } else {
+ /*
+ * Assume coherent DMA in case MMU/MPU has not been set up.
+ */
+ dev->archdata.dma_coherent = (get_cr() & CR_M) ? coherent : true;
+ }
+
+ dma_ops = arm_nommu_get_dma_map_ops(dev->archdata.dma_coherent);
+
+ set_dma_ops(dev, dma_ops);
+}
+
+void arch_teardown_dma_ops(struct device *dev)
+{
+}
+
+int dma_supported(struct device *dev, u64 mask)
+{
+ return 1;
+}
+
+EXPORT_SYMBOL(dma_supported);
+
+#define PREALLOC_DMA_DEBUG_ENTRIES 4096
+
+static int __init dma_debug_do_init(void)
+{
+ dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
+ return 0;
+}
+core_initcall(dma_debug_do_init);
--
2.0.0
Even though dma-noop-ops assumes 1:1 memory mapping DMA memory range
can be different to RAM. For example, ARM STM32F4 MCU offers the
possibility to remap SDRAM from 0xc000_0000 to 0x0 to get CPU
performance boost, but DMA continue to see SDRAM at 0xc000_0000. This
difference in mapping is handled via device-tree "dma-range" property
which leads to dev->dma_pfn_offset is set nonzero. To handle such
cases take dma_pfn_offset into account.
Cc: Joerg Roedel <[email protected]>
Cc: Christian Borntraeger <[email protected]>
Reported-by: Benjamin Gaignard <[email protected]>
Tested-by: Benjamin Gaignard <[email protected]>
Tested-by: Andras Szemzo <[email protected]>
Tested-by: Alexandre TORGUE <[email protected]>
Reviewed-by: Robin Murphy <[email protected]>
Signed-off-by: Vladimir Murzin <[email protected]>
---
lib/dma-noop.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/lib/dma-noop.c b/lib/dma-noop.c
index de26c8b..ff4ef5e 100644
--- a/lib/dma-noop.c
+++ b/lib/dma-noop.c
@@ -7,6 +7,7 @@
#include <linux/mm.h>
#include <linux/dma-mapping.h>
#include <linux/scatterlist.h>
+#include <linux/pfn.h>
static void *dma_noop_alloc(struct device *dev, size_t size,
dma_addr_t *dma_handle, gfp_t gfp,
@@ -16,7 +17,8 @@ static void *dma_noop_alloc(struct device *dev, size_t size,
ret = (void *)__get_free_pages(gfp, get_order(size));
if (ret)
- *dma_handle = virt_to_phys(ret);
+ *dma_handle = virt_to_phys(ret) - PFN_PHYS(dev->dma_pfn_offset);
+
return ret;
}
@@ -32,7 +34,7 @@ static dma_addr_t dma_noop_map_page(struct device *dev, struct page *page,
enum dma_data_direction dir,
unsigned long attrs)
{
- return page_to_phys(page) + offset;
+ return page_to_phys(page) + offset - PFN_PHYS(dev->dma_pfn_offset);
}
static int dma_noop_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
@@ -47,7 +49,7 @@ static int dma_noop_map_sg(struct device *dev, struct scatterlist *sgl, int nent
BUG_ON(!sg_page(sg));
va = sg_virt(sg);
- sg_dma_address(sg) = (dma_addr_t)virt_to_phys(va);
+ sg_dma_address(sg) = (dma_addr_t)(virt_to_phys(va) - PFN_PHYS(dev->dma_pfn_offset));
sg_dma_len(sg) = sg->length;
}
--
2.0.0
dma_declare_coherent_memory() and friends are designed to account
difference in CPU and device addresses. However, when it is used with
reserved memory regions there is assumption that CPU and device have
the same view on address space. This assumption gets invalid when
reserved memory for coherent DMA allocations is referenced by device
with non-empty "dma-range" property.
Simply feeding device address as rmem->base + dev->dma_pfn_offset
would not work due to reserved memory region can be shared, so this
patch turns device address to be expressed with help of CPU address
and device's dma_pfn_offset in case memory reservation has been done
via device tree; non device tree users continue to use the old scheme.
Cc: Michal Nazarewicz <[email protected]>
Cc: Marek Szyprowski <[email protected]>
Cc: Roger Quadros <[email protected]>
Cc: Greg Kroah-Hartman <[email protected]>
Tested-by: Benjamin Gaignard <[email protected]>
Tested-by: Andras Szemzo <[email protected]>
Tested-by: Alexandre TORGUE <[email protected]>
Signed-off-by: Vladimir Murzin <[email protected]>
---
drivers/base/dma-coherent.c | 15 +++++++++++++--
1 file changed, 13 insertions(+), 2 deletions(-)
diff --git a/drivers/base/dma-coherent.c b/drivers/base/dma-coherent.c
index 640a7e6..99c9695 100644
--- a/drivers/base/dma-coherent.c
+++ b/drivers/base/dma-coherent.c
@@ -16,8 +16,18 @@ struct dma_coherent_mem {
int flags;
unsigned long *bitmap;
spinlock_t spinlock;
+ bool use_dev_dma_pfn_offset;
};
+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;
+}
+
static bool dma_init_coherent_memory(
phys_addr_t phys_addr, dma_addr_t device_addr, size_t size, int flags,
struct dma_coherent_mem **mem)
@@ -133,7 +143,7 @@ void *dma_mark_declared_memory_occupied(struct device *dev,
return ERR_PTR(-EINVAL);
spin_lock_irqsave(&mem->spinlock, flags);
- pos = (device_addr - mem->device_base) >> PAGE_SHIFT;
+ pos = PFN_DOWN(device_addr - dma_get_device_base(dev, mem));
err = bitmap_allocate_region(mem->bitmap, pos, get_order(size));
spin_unlock_irqrestore(&mem->spinlock, flags);
@@ -186,7 +196,7 @@ int dma_alloc_from_coherent(struct device *dev, ssize_t size,
/*
* Memory was found in the per-device area.
*/
- *dma_handle = mem->device_base + (pageno << PAGE_SHIFT);
+ *dma_handle = dma_get_device_base(dev, mem) + (pageno << PAGE_SHIFT);
*ret = mem->virt_base + (pageno << PAGE_SHIFT);
dma_memory_map = (mem->flags & DMA_MEMORY_MAP);
spin_unlock_irqrestore(&mem->spinlock, flags);
@@ -299,6 +309,7 @@ static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev)
&rmem->base, (unsigned long)rmem->size / SZ_1M);
return -ENODEV;
}
+ mem->use_dev_dma_pfn_offset = true;
rmem->priv = mem;
dma_assign_coherent_memory(dev, mem);
return 0;
--
2.0.0
This patch introduces default coherent DMA pool similar to default CMA
area concept. To keep other users safe code kept under CONFIG_ARM.
Cc: Michal Nazarewicz <[email protected]>
Cc: Marek Szyprowski <[email protected]>
Cc: Rob Herring <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Greg Kroah-Hartman <[email protected]>
Suggested-by: Robin Murphy <[email protected]>
Tested-by: Benjamin Gaignard <[email protected]>
Tested-by: Andras Szemzo <[email protected]>
Tested-by: Alexandre TORGUE <[email protected]>
Signed-off-by: Vladimir Murzin <[email protected]>
---
.../bindings/reserved-memory/reserved-memory.txt | 3 ++
drivers/base/dma-coherent.c | 59 +++++++++++++++++++---
2 files changed, 55 insertions(+), 7 deletions(-)
diff --git a/Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt b/Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt
index 3da0ebd..16291f2 100644
--- a/Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt
+++ b/Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt
@@ -68,6 +68,9 @@ Linux implementation note:
- If a "linux,cma-default" property is present, then Linux will use the
region for the default pool of the contiguous memory allocator.
+- If a "linux,dma-default" property is present, then Linux will use the
+ region for the default pool of the consistent DMA allocator.
+
Device node references to reserved memory
-----------------------------------------
Regions in the /reserved-memory node may be referenced by other device
diff --git a/drivers/base/dma-coherent.c b/drivers/base/dma-coherent.c
index 99c9695..2ae24c2 100644
--- a/drivers/base/dma-coherent.c
+++ b/drivers/base/dma-coherent.c
@@ -19,6 +19,15 @@ struct dma_coherent_mem {
bool use_dev_dma_pfn_offset;
};
+static struct dma_coherent_mem *dma_coherent_default_memory __ro_after_init;
+
+static inline struct dma_coherent_mem *dev_get_coherent_memory(struct device *dev)
+{
+ if (dev && dev->dma_mem)
+ return dev->dma_mem;
+ return dma_coherent_default_memory;
+}
+
static inline dma_addr_t dma_get_device_base(struct device *dev,
struct dma_coherent_mem * mem)
{
@@ -93,6 +102,9 @@ static void dma_release_coherent_memory(struct dma_coherent_mem *mem)
static int dma_assign_coherent_memory(struct device *dev,
struct dma_coherent_mem *mem)
{
+ if (!dev)
+ return -ENODEV;
+
if (dev->dma_mem)
return -EBUSY;
@@ -171,15 +183,12 @@ EXPORT_SYMBOL(dma_mark_declared_memory_occupied);
int dma_alloc_from_coherent(struct device *dev, ssize_t size,
dma_addr_t *dma_handle, void **ret)
{
- struct dma_coherent_mem *mem;
+ struct dma_coherent_mem *mem = dev_get_coherent_memory(dev);
int order = get_order(size);
unsigned long flags;
int pageno;
int dma_memory_map;
- if (!dev)
- return 0;
- mem = dev->dma_mem;
if (!mem)
return 0;
@@ -233,7 +242,7 @@ EXPORT_SYMBOL(dma_alloc_from_coherent);
*/
int dma_release_from_coherent(struct device *dev, int order, void *vaddr)
{
- struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
+ struct dma_coherent_mem *mem = dev_get_coherent_memory(dev);
if (mem && vaddr >= mem->virt_base && vaddr <
(mem->virt_base + (mem->size << PAGE_SHIFT))) {
@@ -267,7 +276,7 @@ EXPORT_SYMBOL(dma_release_from_coherent);
int dma_mmap_from_coherent(struct device *dev, struct vm_area_struct *vma,
void *vaddr, size_t size, int *ret)
{
- struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
+ struct dma_coherent_mem *mem = dev_get_coherent_memory(dev);
if (mem && vaddr >= mem->virt_base && vaddr + size <=
(mem->virt_base + (mem->size << PAGE_SHIFT))) {
@@ -297,6 +306,8 @@ EXPORT_SYMBOL(dma_mmap_from_coherent);
#include <linux/of_fdt.h>
#include <linux/of_reserved_mem.h>
+static struct reserved_mem *dma_reserved_default_memory __initdata;
+
static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev)
{
struct dma_coherent_mem *mem = rmem->priv;
@@ -318,7 +329,8 @@ static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev)
static void rmem_dma_device_release(struct reserved_mem *rmem,
struct device *dev)
{
- dev->dma_mem = NULL;
+ if (dev)
+ dev->dma_mem = NULL;
}
static const struct reserved_mem_ops rmem_dma_ops = {
@@ -338,6 +350,12 @@ static int __init rmem_dma_setup(struct reserved_mem *rmem)
pr_err("Reserved memory: regions without no-map are not yet supported\n");
return -EINVAL;
}
+
+ if (of_get_flat_dt_prop(node, "linux,dma-default", NULL)) {
+ WARN(dma_reserved_default_memory,
+ "Reserved memory: region for default DMA coherent area is redefined\n");
+ dma_reserved_default_memory = rmem;
+ }
#endif
rmem->ops = &rmem_dma_ops;
@@ -345,5 +363,32 @@ static int __init rmem_dma_setup(struct reserved_mem *rmem)
&rmem->base, (unsigned long)rmem->size / SZ_1M);
return 0;
}
+
+static int __init dma_init_reserved_memory(void)
+{
+ const struct reserved_mem_ops *ops;
+ int ret;
+
+ if (!dma_reserved_default_memory)
+ return -ENOMEM;
+
+ ops = dma_reserved_default_memory->ops;
+
+ /*
+ * We rely on rmem_dma_device_init() does not propagate error of
+ * dma_assign_coherent_memory() for "NULL" device.
+ */
+ ret = ops->device_init(dma_reserved_default_memory, NULL);
+
+ if (!ret) {
+ dma_coherent_default_memory = dma_reserved_default_memory->priv;
+ pr_info("DMA: default coherent area is set\n");
+ }
+
+ return ret;
+}
+
+core_initcall(dma_init_reserved_memory);
+
RESERVEDMEM_OF_DECLARE(dma, "shared-dma-pool", rmem_dma_setup);
#endif
--
2.0.0