* [PATCH v4 1/2] ARM: dma-mapping: Don't use outer_flush_range when the L2C is coherent
2015-09-29 16:50 [PATCH v4 0/2] Fix dma mapping when the cache is coherent Gregory CLEMENT
@ 2015-09-29 16:50 ` Gregory CLEMENT
2015-09-29 17:10 ` Russell King - ARM Linux
2015-09-29 16:50 ` [PATCH v4 2/2] ARM: dma-mapping: Fix the coherent case when iommu is used Gregory CLEMENT
1 sibling, 1 reply; 8+ messages in thread
From: Gregory CLEMENT @ 2015-09-29 16:50 UTC (permalink / raw)
To: linux-arm-kernel
When a L2 cache controller is used in a system that provides hardware
coherency, the entire outer cache operations are useless, and can be
skipped. Moreover, on some systems, it is harmful as it causes
deadlocks between the Marvell coherency mechanism, the Marvell PCIe
controller and the Cortex-A9.
In the current kernel implementation, the outer cache flush range
operation is triggered by the dma_alloc function.
This operation can be take place during runtime and in some
circumstances may lead to the PCIe/PL310 deadlock on Armada 375/38x
SoCs.
This patch extends the __dma_clear_buffer() function to receive a
boolean argument related to the coherency of the system. The same
things is done for the calling functions.
Reported-by: Nadav Haklai <nadavh@marvell•com>
Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons•com>
Cc: <stable@vger•kernel.org> # v3.16+
Reviewed-by: Catalin Marinas <catalin.marinas@arm•com>
---
arch/arm/mm/dma-mapping.c | 56 +++++++++++++++++++++++++++++++----------------
1 file changed, 37 insertions(+), 19 deletions(-)
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index e62604384945..c8ed0c16c5a8 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -225,7 +225,7 @@ static u64 get_coherent_dma_mask(struct device *dev)
return mask;
}
-static void __dma_clear_buffer(struct page *page, size_t size)
+static void __dma_clear_buffer(struct page *page, size_t size, bool is_coherent)
{
/*
* Ensure that the allocated pages are zeroed, and that any data
@@ -237,17 +237,21 @@ static void __dma_clear_buffer(struct page *page, size_t size)
while (size > 0) {
void *ptr = kmap_atomic(page);
memset(ptr, 0, PAGE_SIZE);
- dmac_flush_range(ptr, ptr + PAGE_SIZE);
+ if (!is_coherent)
+ dmac_flush_range(ptr, ptr + PAGE_SIZE);
kunmap_atomic(ptr);
page++;
size -= PAGE_SIZE;
}
- outer_flush_range(base, end);
+ if (!is_coherent)
+ outer_flush_range(base, end);
} else {
void *ptr = page_address(page);
memset(ptr, 0, size);
- dmac_flush_range(ptr, ptr + size);
- outer_flush_range(__pa(ptr), __pa(ptr) + size);
+ if (!is_coherent) {
+ dmac_flush_range(ptr, ptr + size);
+ outer_flush_range(__pa(ptr), __pa(ptr) + size);
+ }
}
}
@@ -255,7 +259,8 @@ static void __dma_clear_buffer(struct page *page, size_t size)
* Allocate a DMA buffer for 'dev' of size 'size' using the
* specified gfp mask. Note that 'size' must be page aligned.
*/
-static struct page *__dma_alloc_buffer(struct device *dev, size_t size, gfp_t gfp)
+static struct page *__dma_alloc_buffer(struct device *dev, size_t size,
+ gfp_t gfp, bool is_coherent)
{
unsigned long order = get_order(size);
struct page *page, *p, *e;
@@ -271,7 +276,7 @@ static struct page *__dma_alloc_buffer(struct device *dev, size_t size, gfp_t gf
for (p = page + (size >> PAGE_SHIFT), e = page + (1 << order); p < e; p++)
__free_page(p);
- __dma_clear_buffer(page, size);
+ __dma_clear_buffer(page, size, is_coherent);
return page;
}
@@ -293,7 +298,8 @@ static void __dma_free_buffer(struct page *page, size_t size)
static void *__alloc_from_contiguous(struct device *dev, size_t size,
pgprot_t prot, struct page **ret_page,
- const void *caller, bool want_vaddr);
+ const void *caller, bool want_vaddr,
+ bool is_coherent);
static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
pgprot_t prot, struct page **ret_page,
@@ -359,9 +365,13 @@ static int __init atomic_pool_init(void)
if (!atomic_pool)
goto out;
+ /*
+ * The atomic pool is only used for non-coherent allocations
+ * so we must pass false for is_coherent.
+ */
if (dev_get_cma_area(NULL))
ptr = __alloc_from_contiguous(NULL, atomic_pool_size, prot,
- &page, atomic_pool_init, true);
+ &page, atomic_pool_init, true, false);
else
ptr = __alloc_remap_buffer(NULL, atomic_pool_size, gfp, prot,
&page, atomic_pool_init, true);
@@ -475,7 +485,11 @@ static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
{
struct page *page;
void *ptr = NULL;
- page = __dma_alloc_buffer(dev, size, gfp);
+ /*
+ * __alloc_remap_buffer is only called when the device is
+ * non-coherent
+ */
+ page = __dma_alloc_buffer(dev, size, gfp, false);
if (!page)
return NULL;
if (!want_vaddr)
@@ -530,7 +544,8 @@ static int __free_from_pool(void *start, size_t size)
static void *__alloc_from_contiguous(struct device *dev, size_t size,
pgprot_t prot, struct page **ret_page,
- const void *caller, bool want_vaddr)
+ const void *caller, bool want_vaddr,
+ bool is_coherent)
{
unsigned long order = get_order(size);
size_t count = size >> PAGE_SHIFT;
@@ -541,7 +556,7 @@ static void *__alloc_from_contiguous(struct device *dev, size_t size,
if (!page)
return NULL;
- __dma_clear_buffer(page, size);
+ __dma_clear_buffer(page, size, is_coherent);
if (!want_vaddr)
goto out;
@@ -591,7 +606,7 @@ static inline pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot)
#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) NULL
+#define __alloc_from_contiguous(dev, size, prot, ret, c, wv, is_coherent) NULL
#define __free_from_pool(cpu_addr, size) 0
#define __free_from_contiguous(dev, page, cpu_addr, size, wv) do { } while (0)
#define __dma_free_remap(cpu_addr, size) do { } while (0)
@@ -602,7 +617,8 @@ static void *__alloc_simple_buffer(struct device *dev, size_t size, gfp_t gfp,
struct page **ret_page)
{
struct page *page;
- page = __dma_alloc_buffer(dev, size, gfp);
+ /* __alloc_simple_buffer is only called when the device is coherent */
+ page = __dma_alloc_buffer(dev, size, gfp, true);
if (!page)
return NULL;
@@ -653,7 +669,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
addr = __alloc_simple_buffer(dev, size, gfp, &page);
else if (dev_get_cma_area(dev) && (gfp & __GFP_WAIT))
addr = __alloc_from_contiguous(dev, size, prot, &page,
- caller, want_vaddr);
+ caller, want_vaddr, is_coherent);
else if (is_coherent)
addr = __alloc_simple_buffer(dev, size, gfp, &page);
else if (!(gfp & __GFP_WAIT))
@@ -1123,7 +1139,8 @@ static inline void __free_iova(struct dma_iommu_mapping *mapping,
}
static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
- gfp_t gfp, struct dma_attrs *attrs)
+ gfp_t gfp, struct dma_attrs *attrs,
+ bool is_coherent)
{
struct page **pages;
int count = size >> PAGE_SHIFT;
@@ -1146,7 +1163,7 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
if (!page)
goto error;
- __dma_clear_buffer(page, size);
+ __dma_clear_buffer(page, size, is_coherent);
for (i = 0; i < count; i++)
pages[i] = page + i;
@@ -1190,7 +1207,7 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
pages[i + j] = pages[i] + j;
}
- __dma_clear_buffer(pages[i], PAGE_SIZE << order);
+ __dma_clear_buffer(pages[i], PAGE_SIZE << order, is_coherent);
i += 1 << order;
count -= 1 << order;
}
@@ -1373,7 +1390,8 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
*/
gfp &= ~(__GFP_COMP);
- pages = __iommu_alloc_buffer(dev, size, gfp, attrs);
+ /* For now always consider we are in a non-coherent case */
+ pages = __iommu_alloc_buffer(dev, size, gfp, attrs, false);
if (!pages)
return NULL;
--
2.1.0
^ permalink raw reply related [flat|nested] 8+ messages in thread* [PATCH v4 2/2] ARM: dma-mapping: Fix the coherent case when iommu is used
2015-09-29 16:50 [PATCH v4 0/2] Fix dma mapping when the cache is coherent Gregory CLEMENT
2015-09-29 16:50 ` [PATCH v4 1/2] ARM: dma-mapping: Don't use outer_flush_range when the L2C " Gregory CLEMENT
@ 2015-09-29 16:50 ` Gregory CLEMENT
1 sibling, 0 replies; 8+ messages in thread
From: Gregory CLEMENT @ 2015-09-29 16:50 UTC (permalink / raw)
To: linux-arm-kernel
When doing dma allocation with IOMMU the __iommu_alloc_atomic() was
used even when the system was coherent. However, this function
allocates from a non-cacheable pool, which is fine when the device is
not cache coherent but won't work as expected in the device is cache
coherent. Indeed, the CPU and device must access the memory using the
same cacheability attributes.
Moreover when the devices are coherent, the mmap call must not change
the pg_prot flags in the vma struct. The arm_coherent_iommu_mmap_attrs
has been updated in the same way that it was done for the arm_dma_mmap
in commit 55af8a91640d ("ARM: 8387/1: arm/mm/dma-mapping.c: Add
arm_coherent_dma_mmap").
Suggested-by: Catalin Marinas <catalin.marinas@arm•com>
Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons•com>
---
arch/arm/mm/dma-mapping.c | 88 +++++++++++++++++++++++++++++++++++------------
1 file changed, 66 insertions(+), 22 deletions(-)
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index c8ed0c16c5a8..de1b0f070353 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -1340,13 +1340,16 @@ static struct page **__iommu_get_pages(void *cpu_addr, struct dma_attrs *attrs)
return NULL;
}
-static void *__iommu_alloc_atomic(struct device *dev, size_t size,
- dma_addr_t *handle)
+static void *__iommu_alloc_simple(struct device *dev, size_t size, gfp_t gfp,
+ dma_addr_t *handle, bool is_coherent)
{
struct page *page;
void *addr;
- addr = __alloc_from_pool(size, &page);
+ if (is_coherent)
+ addr = __alloc_simple_buffer(dev, size, gfp, &page);
+ else
+ addr = __alloc_from_pool(size, &page);
if (!addr)
return NULL;
@@ -1361,15 +1364,19 @@ err_mapping:
return NULL;
}
-static void __iommu_free_atomic(struct device *dev, void *cpu_addr,
- dma_addr_t handle, size_t size)
+static void __iommu_free_simple(struct device *dev, void *cpu_addr,
+ dma_addr_t handle, size_t size, bool is_coherent)
{
__iommu_remove_mapping(dev, handle, size);
- __free_from_pool(cpu_addr, size);
+ if (is_coherent)
+ __dma_free_buffer(virt_to_page(cpu_addr), size);
+ else
+ __free_from_pool(cpu_addr, size);
}
-static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
- dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
+static void *__arm_iommu_alloc_attrs(struct device *dev, size_t size,
+ dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs,
+ bool is_coherent)
{
pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL);
struct page **pages;
@@ -1378,8 +1385,8 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
*handle = DMA_ERROR_CODE;
size = PAGE_ALIGN(size);
- if (!(gfp & __GFP_WAIT))
- return __iommu_alloc_atomic(dev, size, handle);
+ if (is_coherent || !(gfp & __GFP_WAIT))
+ return __iommu_alloc_simple(dev, size, gfp, handle, is_coherent);
/*
* Following is a work-around (a.k.a. hack) to prevent pages
@@ -1390,8 +1397,7 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
*/
gfp &= ~(__GFP_COMP);
- /* For now always consider we are in a non-coherent case */
- pages = __iommu_alloc_buffer(dev, size, gfp, attrs, false);
+ pages = __iommu_alloc_buffer(dev, size, gfp, attrs, is_coherent);
if (!pages)
return NULL;
@@ -1416,7 +1422,19 @@ err_buffer:
return NULL;
}
-static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
+static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
+ dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
+{
+ return __arm_iommu_alloc_attrs(dev, size, handle, gfp, attrs, false);
+}
+
+static void *arm_coherent_iommu_alloc_attrs(struct device *dev, size_t size,
+ dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
+{
+ return __arm_iommu_alloc_attrs(dev, size, handle, gfp, attrs, true);
+}
+
+static int __arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
void *cpu_addr, dma_addr_t dma_addr, size_t size,
struct dma_attrs *attrs)
{
@@ -1424,8 +1442,6 @@ static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
unsigned long usize = vma->vm_end - vma->vm_start;
struct page **pages = __iommu_get_pages(cpu_addr, attrs);
- vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
-
if (!pages)
return -ENXIO;
@@ -1442,18 +1458,34 @@ static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
return 0;
}
+static int arm_iommu_mmap_attrs(struct device *dev,
+ struct vm_area_struct *vma, void *cpu_addr,
+ dma_addr_t dma_addr, size_t size, struct dma_attrs *attrs)
+{
+ vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
+
+ return __arm_iommu_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, attrs);
+}
+
+static int arm_coherent_iommu_mmap_attrs(struct device *dev,
+ struct vm_area_struct *vma, void *cpu_addr,
+ dma_addr_t dma_addr, size_t size, struct dma_attrs *attrs)
+{
+ return __arm_iommu_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, attrs);
+}
+
/*
* free a page as defined by the above mapping.
* Must not be called with IRQs disabled.
*/
-void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
- dma_addr_t handle, struct dma_attrs *attrs)
+void __arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
+ dma_addr_t handle, struct dma_attrs *attrs, bool is_coherent)
{
struct page **pages;
size = PAGE_ALIGN(size);
- if (__in_atomic_pool(cpu_addr, size)) {
- __iommu_free_atomic(dev, cpu_addr, handle, size);
+ if (is_coherent || __in_atomic_pool(cpu_addr, size)) {
+ __iommu_free_simple(dev, cpu_addr, handle, size, is_coherent);
return;
}
@@ -1472,6 +1504,18 @@ void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
__iommu_free_buffer(dev, pages, size, attrs);
}
+void arm_iommu_free_attrs(struct device *dev, size_t size,
+ void *cpu_addr, dma_addr_t handle, struct dma_attrs *attrs)
+{
+ __arm_iommu_free_attrs(dev, size, cpu_addr, handle, attrs, false);
+}
+
+void arm_coherent_iommu_free_attrs(struct device *dev, size_t size,
+ void *cpu_addr, dma_addr_t handle, struct dma_attrs *attrs)
+{
+ __arm_iommu_free_attrs(dev, size, cpu_addr, handle, attrs, true);
+}
+
static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
void *cpu_addr, dma_addr_t dma_addr,
size_t size, struct dma_attrs *attrs)
@@ -1878,9 +1922,9 @@ struct dma_map_ops iommu_ops = {
};
struct dma_map_ops iommu_coherent_ops = {
- .alloc = arm_iommu_alloc_attrs,
- .free = arm_iommu_free_attrs,
- .mmap = arm_iommu_mmap_attrs,
+ .alloc = arm_coherent_iommu_alloc_attrs,
+ .free = arm_coherent_iommu_free_attrs,
+ .mmap = arm_coherent_iommu_mmap_attrs,
.get_sgtable = arm_iommu_get_sgtable,
.map_page = arm_coherent_iommu_map_page,
--
2.1.0
^ permalink raw reply related [flat|nested] 8+ messages in thread