linux_dsm_epyc7002/arch/powerpc/kernel/dma.c

244 lines
6.0 KiB
C
Raw Normal View History

/*
* Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corporation
*
* Provide default implementations of the DMA mapping callbacks for
* directly mapped busses.
*/
#include <linux/device.h>
#include <linux/dma-mapping.h>
#include <linux/dma-debug.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 15:04:11 +07:00
#include <linux/gfp.h>
#include <linux/memblock.h>
#include <linux/export.h>
#include <linux/pci.h>
#include <asm/vio.h>
#include <asm/bug.h>
#include <asm/machdep.h>
/*
* Generic direct DMA implementation
*
* This implementation supports a per-device offset that can be applied if
* the address at which memory is visible to devices is not 0. Platform code
* can set archdata.dma_data to an unsigned long holding the offset. By
* default the offset is PCI_DRAM_OFFSET.
*/
void *dma_direct_alloc_coherent(struct device *dev, size_t size,
dma_addr_t *dma_handle, gfp_t flag,
struct dma_attrs *attrs)
{
void *ret;
#ifdef CONFIG_NOT_COHERENT_CACHE
ret = __dma_alloc_coherent(dev, size, dma_handle, flag);
if (ret == NULL)
return NULL;
*dma_handle += get_dma_offset(dev);
return ret;
#else
struct page *page;
int node = dev_to_node(dev);
/* ignore region specifiers */
flag &= ~(__GFP_HIGHMEM);
page = alloc_pages_node(node, flag, get_order(size));
if (page == NULL)
return NULL;
ret = page_address(page);
memset(ret, 0, size);
*dma_handle = __pa(ret) + get_dma_offset(dev);
return ret;
#endif
}
void dma_direct_free_coherent(struct device *dev, size_t size,
void *vaddr, dma_addr_t dma_handle,
struct dma_attrs *attrs)
{
#ifdef CONFIG_NOT_COHERENT_CACHE
__dma_free_coherent(size, vaddr);
#else
free_pages((unsigned long)vaddr, get_order(size));
#endif
}
int dma_direct_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
void *cpu_addr, dma_addr_t handle, size_t size,
struct dma_attrs *attrs)
{
unsigned long pfn;
#ifdef CONFIG_NOT_COHERENT_CACHE
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
pfn = __dma_get_coherent_pfn((unsigned long)cpu_addr);
#else
pfn = page_to_pfn(virt_to_page(cpu_addr));
#endif
return remap_pfn_range(vma, vma->vm_start,
pfn + vma->vm_pgoff,
vma->vm_end - vma->vm_start,
vma->vm_page_prot);
}
static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
int nents, enum dma_data_direction direction,
struct dma_attrs *attrs)
{
struct scatterlist *sg;
int i;
for_each_sg(sgl, sg, nents, i) {
sg->dma_address = sg_phys(sg) + get_dma_offset(dev);
sg->dma_length = sg->length;
__dma_sync_page(sg_page(sg), sg->offset, sg->length, direction);
}
return nents;
}
static void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sg,
int nents, enum dma_data_direction direction,
struct dma_attrs *attrs)
{
}
static int dma_direct_dma_supported(struct device *dev, u64 mask)
{
#ifdef CONFIG_PPC64
/* Could be improved so platforms can set the limit in case
* they have limited DMA windows
*/
return mask >= get_dma_offset(dev) + (memblock_end_of_DRAM() - 1);
#else
return 1;
#endif
}
static u64 dma_direct_get_required_mask(struct device *dev)
{
u64 end, mask;
end = memblock_end_of_DRAM() + get_dma_offset(dev);
mask = 1ULL << (fls64(end) - 1);
mask += mask - 1;
return mask;
}
static inline dma_addr_t dma_direct_map_page(struct device *dev,
struct page *page,
unsigned long offset,
size_t size,
enum dma_data_direction dir,
struct dma_attrs *attrs)
{
BUG_ON(dir == DMA_NONE);
__dma_sync_page(page, offset, size, dir);
return page_to_phys(page) + offset + get_dma_offset(dev);
}
static inline void dma_direct_unmap_page(struct device *dev,
dma_addr_t dma_address,
size_t size,
enum dma_data_direction direction,
struct dma_attrs *attrs)
{
}
#ifdef CONFIG_NOT_COHERENT_CACHE
static inline void dma_direct_sync_sg(struct device *dev,
struct scatterlist *sgl, int nents,
enum dma_data_direction direction)
{
struct scatterlist *sg;
int i;
for_each_sg(sgl, sg, nents, i)
__dma_sync_page(sg_page(sg), sg->offset, sg->length, direction);
}
static inline void dma_direct_sync_single(struct device *dev,
dma_addr_t dma_handle, size_t size,
enum dma_data_direction direction)
{
__dma_sync(bus_to_virt(dma_handle), size, direction);
}
#endif
struct dma_map_ops dma_direct_ops = {
.alloc = dma_direct_alloc_coherent,
.free = dma_direct_free_coherent,
.mmap = dma_direct_mmap_coherent,
.map_sg = dma_direct_map_sg,
.unmap_sg = dma_direct_unmap_sg,
.dma_supported = dma_direct_dma_supported,
.map_page = dma_direct_map_page,
.unmap_page = dma_direct_unmap_page,
.get_required_mask = dma_direct_get_required_mask,
#ifdef CONFIG_NOT_COHERENT_CACHE
.sync_single_for_cpu = dma_direct_sync_single,
.sync_single_for_device = dma_direct_sync_single,
.sync_sg_for_cpu = dma_direct_sync_sg,
.sync_sg_for_device = dma_direct_sync_sg,
#endif
};
EXPORT_SYMBOL(dma_direct_ops);
#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
int __dma_set_mask(struct device *dev, u64 dma_mask)
{
struct dma_map_ops *dma_ops = get_dma_ops(dev);
if ((dma_ops != NULL) && (dma_ops->set_dma_mask != NULL))
return dma_ops->set_dma_mask(dev, dma_mask);
if (!dev->dma_mask || !dma_supported(dev, dma_mask))
return -EIO;
*dev->dma_mask = dma_mask;
return 0;
}
int dma_set_mask(struct device *dev, u64 dma_mask)
{
if (ppc_md.dma_set_mask)
return ppc_md.dma_set_mask(dev, dma_mask);
return __dma_set_mask(dev, dma_mask);
}
EXPORT_SYMBOL(dma_set_mask);
u64 dma_get_required_mask(struct device *dev)
{
struct dma_map_ops *dma_ops = get_dma_ops(dev);
if (ppc_md.dma_get_required_mask)
return ppc_md.dma_get_required_mask(dev);
if (unlikely(dma_ops == NULL))
return 0;
if (dma_ops->get_required_mask)
return dma_ops->get_required_mask(dev);
return DMA_BIT_MASK(8 * sizeof(dma_addr_t));
}
EXPORT_SYMBOL_GPL(dma_get_required_mask);
static int __init dma_init(void)
{
dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
#ifdef CONFIG_PCI
dma_debug_add_bus(&pci_bus_type);
#endif
#ifdef CONFIG_IBMVIO
dma_debug_add_bus(&vio_bus_type);
#endif
return 0;
}
fs_initcall(dma_init);