summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2012-05-25 09:18:59 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2012-05-25 09:18:59 -0700
commitd484864dd96e1830e7689510597707c1df8cd681 (patch)
tree51551708ba3f26d05575fa91daaf0c0d970a77c3 /arch/x86
parentbe87cfb47c5c740f7b17929bcd7c480b228513e0 (diff)
parent0f51596bd39a5c928307ffcffc9ba07f90f42a8b (diff)
downloadop-kernel-dev-d484864dd96e1830e7689510597707c1df8cd681.zip
op-kernel-dev-d484864dd96e1830e7689510597707c1df8cd681.tar.gz
Merge branch 'for-linus' of git://git.linaro.org/people/mszyprowski/linux-dma-mapping
Pull CMA and ARM DMA-mapping updates from Marek Szyprowski: "These patches contain two major updates for DMA mapping subsystem (mainly for ARM architecture). First one is Contiguous Memory Allocator (CMA) which makes it possible for device drivers to allocate big contiguous chunks of memory after the system has booted. The main difference from the similar frameworks is the fact that CMA allows to transparently reuse the memory region reserved for the big chunk allocation as a system memory, so no memory is wasted when no big chunk is allocated. Once the alloc request is issued, the framework migrates system pages to create space for the required big chunk of physically contiguous memory. For more information one can refer to nice LWN articles: - 'A reworked contiguous memory allocator': http://lwn.net/Articles/447405/ - 'CMA and ARM': http://lwn.net/Articles/450286/ - 'A deep dive into CMA': http://lwn.net/Articles/486301/ - and the following thread with the patches and links to all previous versions: https://lkml.org/lkml/2012/4/3/204 The main client for this new framework is ARM DMA-mapping subsystem. The second part provides a complete redesign in ARM DMA-mapping subsystem. The core implementation has been changed to use common struct dma_map_ops based infrastructure with the recent updates for new dma attributes merged in v3.4-rc2. This allows to use more than one implementation of dma-mapping calls and change/select them on the struct device basis. The first client of this new infractructure is dmabounce implementation which has been completely cut out of the core, common code. The last patch of this redesign update introduces a new, experimental implementation of dma-mapping calls on top of generic IOMMU framework. This lets ARM sub-platform to transparently use IOMMU for DMA-mapping calls if one provides required IOMMU hardware. For more information please refer to the following thread: http://www.spinics.net/lists/arm-kernel/msg175729.html The last patch merges changes from both updates and provides a resolution for the conflicts which cannot be avoided when patches have been applied on the same files (mainly arch/arm/mm/dma-mapping.c)." Acked by Andrew Morton <akpm@linux-foundation.org>: "Yup, this one please. It's had much work, plenty of review and I think even Russell is happy with it." * 'for-linus' of git://git.linaro.org/people/mszyprowski/linux-dma-mapping: (28 commits) ARM: dma-mapping: use PMD size for section unmap cma: fix migration mode ARM: integrate CMA with DMA-mapping subsystem X86: integrate CMA with DMA-mapping subsystem drivers: add Contiguous Memory Allocator mm: trigger page reclaim in alloc_contig_range() to stabilise watermarks mm: extract reclaim code from __alloc_pages_direct_reclaim() mm: Serialize access to min_free_kbytes mm: page_isolation: MIGRATE_CMA isolation functions added mm: mmzone: MIGRATE_CMA migration type added mm: page_alloc: change fallbacks array handling mm: page_alloc: introduce alloc_contig_range() mm: compaction: export some of the functions mm: compaction: introduce isolate_freepages_range() mm: compaction: introduce map_pages() mm: compaction: introduce isolate_migratepages_range() mm: page_alloc: remove trailing whitespace ARM: dma-mapping: add support for IOMMU mapper ARM: dma-mapping: use alloc, mmap, free from dma_ops ARM: dma-mapping: remove redundant code and do the cleanup ... Conflicts: arch/x86/include/asm/dma-mapping.h
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig1
-rw-r--r--arch/x86/include/asm/dma-contiguous.h13
-rw-r--r--arch/x86/include/asm/dma-mapping.h5
-rw-r--r--arch/x86/kernel/pci-dma.c18
-rw-r--r--arch/x86/kernel/pci-nommu.c8
-rw-r--r--arch/x86/kernel/setup.c2
6 files changed, 38 insertions, 9 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 66cc380..81c3e8b 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -32,6 +32,7 @@ config X86
select ARCH_WANT_OPTIONAL_GPIOLIB
select ARCH_WANT_FRAME_POINTERS
select HAVE_DMA_ATTRS
+ select HAVE_DMA_CONTIGUOUS if !SWIOTLB
select HAVE_KRETPROBES
select HAVE_OPTPROBES
select HAVE_FTRACE_MCOUNT_RECORD
diff --git a/arch/x86/include/asm/dma-contiguous.h b/arch/x86/include/asm/dma-contiguous.h
new file mode 100644
index 0000000..c092416
--- /dev/null
+++ b/arch/x86/include/asm/dma-contiguous.h
@@ -0,0 +1,13 @@
+#ifndef ASMX86_DMA_CONTIGUOUS_H
+#define ASMX86_DMA_CONTIGUOUS_H
+
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+#include <asm-generic/dma-contiguous.h>
+
+static inline void
+dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
+
+#endif
+#endif
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 61c0bd2..f7b4c79 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -13,6 +13,7 @@
#include <asm/io.h>
#include <asm/swiotlb.h>
#include <asm-generic/dma-coherent.h>
+#include <linux/dma-contiguous.h>
#ifdef CONFIG_ISA
# define ISA_DMA_BIT_MASK DMA_BIT_MASK(24)
@@ -62,6 +63,10 @@ extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
dma_addr_t *dma_addr, gfp_t flag,
struct dma_attrs *attrs);
+extern void dma_generic_free_coherent(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t dma_addr,
+ struct dma_attrs *attrs);
+
#ifdef CONFIG_X86_DMA_REMAP /* Platform code defines bridge-specific code */
extern bool dma_capable(struct device *dev, dma_addr_t addr, size_t size);
extern dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr);
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 3003250..62c9457 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -100,14 +100,18 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size,
struct dma_attrs *attrs)
{
unsigned long dma_mask;
- struct page *page;
+ struct page *page = NULL;
+ unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
dma_addr_t addr;
dma_mask = dma_alloc_coherent_mask(dev, flag);
flag |= __GFP_ZERO;
again:
- page = alloc_pages_node(dev_to_node(dev), flag, get_order(size));
+ if (!(flag & GFP_ATOMIC))
+ page = dma_alloc_from_contiguous(dev, count, get_order(size));
+ if (!page)
+ page = alloc_pages_node(dev_to_node(dev), flag, get_order(size));
if (!page)
return NULL;
@@ -127,6 +131,16 @@ again:
return page_address(page);
}
+void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr,
+ dma_addr_t dma_addr, struct dma_attrs *attrs)
+{
+ unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+ struct page *page = virt_to_page(vaddr);
+
+ if (!dma_release_from_contiguous(dev, page, count))
+ free_pages((unsigned long)vaddr, get_order(size));
+}
+
/*
* See <Documentation/x86/x86_64/boot-options.txt> for the iommu kernel
* parameter documentation.
diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
index f960506..871be4a 100644
--- a/arch/x86/kernel/pci-nommu.c
+++ b/arch/x86/kernel/pci-nommu.c
@@ -74,12 +74,6 @@ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg,
return nents;
}
-static void nommu_free_coherent(struct device *dev, size_t size, void *vaddr,
- dma_addr_t dma_addr, struct dma_attrs *attrs)
-{
- free_pages((unsigned long)vaddr, get_order(size));
-}
-
static void nommu_sync_single_for_device(struct device *dev,
dma_addr_t addr, size_t size,
enum dma_data_direction dir)
@@ -97,7 +91,7 @@ static void nommu_sync_sg_for_device(struct device *dev,
struct dma_map_ops nommu_dma_ops = {
.alloc = dma_generic_alloc_coherent,
- .free = nommu_free_coherent,
+ .free = dma_generic_free_coherent,
.map_sg = nommu_map_sg,
.map_page = nommu_map_page,
.sync_single_for_device = nommu_sync_single_for_device,
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 366c688..f2afee6 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -49,6 +49,7 @@
#include <asm/pci-direct.h>
#include <linux/init_ohci1394_dma.h>
#include <linux/kvm_para.h>
+#include <linux/dma-contiguous.h>
#include <linux/errno.h>
#include <linux/kernel.h>
@@ -925,6 +926,7 @@ void __init setup_arch(char **cmdline_p)
}
#endif
memblock.current_limit = get_max_mapped();
+ dma_contiguous_reserve(0);
/*
* NOTE: On x86-32, only from this point on, fixmaps are ready for use.
OpenPOWER on IntegriCloud