linux_dsm_epyc7002/drivers/base/dma-coherent.c

178 lines
4.4 KiB
C
Raw Normal View History

/*
* Coherent per-device memory handling.
* Borrowed from i386
*/
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/slab.h>
#include <linux/kernel.h>
#include <linux/dma-mapping.h>
struct dma_coherent_mem {
void *virt_base;
dma_addr_t device_base;
int size;
int flags;
unsigned long *bitmap;
};
int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
dma_addr_t device_addr, size_t size, int flags)
{
void __iomem *mem_base = NULL;
int pages = size >> PAGE_SHIFT;
int bitmap_size = BITS_TO_LONGS(pages) * sizeof(long);
if ((flags & (DMA_MEMORY_MAP | DMA_MEMORY_IO)) == 0)
goto out;
if (!size)
goto out;
if (dev->dma_mem)
goto out;
/* FIXME: this routine just ignores DMA_MEMORY_INCLUDES_CHILDREN */
mem_base = ioremap(bus_addr, size);
if (!mem_base)
goto out;
dev->dma_mem = kzalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL);
if (!dev->dma_mem)
goto out;
dev->dma_mem->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
if (!dev->dma_mem->bitmap)
goto free1_out;
dev->dma_mem->virt_base = mem_base;
dev->dma_mem->device_base = device_addr;
dev->dma_mem->size = pages;
dev->dma_mem->flags = flags;
if (flags & DMA_MEMORY_MAP)
return DMA_MEMORY_MAP;
return DMA_MEMORY_IO;
free1_out:
kfree(dev->dma_mem);
out:
if (mem_base)
iounmap(mem_base);
return 0;
}
EXPORT_SYMBOL(dma_declare_coherent_memory);
void dma_release_declared_memory(struct device *dev)
{
struct dma_coherent_mem *mem = dev->dma_mem;
if (!mem)
return;
dev->dma_mem = NULL;
iounmap(mem->virt_base);
kfree(mem->bitmap);
kfree(mem);
}
EXPORT_SYMBOL(dma_release_declared_memory);
void *dma_mark_declared_memory_occupied(struct device *dev,
dma_addr_t device_addr, size_t size)
{
struct dma_coherent_mem *mem = dev->dma_mem;
int pos, err;
size += device_addr & ~PAGE_MASK;
if (!mem)
return ERR_PTR(-EINVAL);
pos = (device_addr - mem->device_base) >> PAGE_SHIFT;
err = bitmap_allocate_region(mem->bitmap, pos, get_order(size));
if (err != 0)
return ERR_PTR(err);
return mem->virt_base + (pos << PAGE_SHIFT);
}
EXPORT_SYMBOL(dma_mark_declared_memory_occupied);
/**
* dma_alloc_from_coherent() - try to allocate memory from the per-device coherent area
*
* @dev: device from which we allocate memory
* @size: size of requested memory area
* @dma_handle: This will be filled with the correct dma handle
* @ret: This pointer will be filled with the virtual address
* to allocated area.
*
* This function should be only called from per-arch dma_alloc_coherent()
* to support allocation from per-device coherent memory pools.
*
* Returns 0 if dma_alloc_coherent should continue with allocating from
* generic memory areas, or !0 if dma_alloc_coherent should return @ret.
*/
int dma_alloc_from_coherent(struct device *dev, ssize_t size,
dma_addr_t *dma_handle, void **ret)
{
struct dma_coherent_mem *mem;
int order = get_order(size);
int pageno;
if (!dev)
return 0;
mem = dev->dma_mem;
if (!mem)
return 0;
*ret = NULL;
if (unlikely(size > (mem->size << PAGE_SHIFT)))
goto err;
pageno = bitmap_find_free_region(mem->bitmap, mem->size, order);
if (unlikely(pageno < 0))
goto err;
/*
* Memory was found in the per-device area.
*/
*dma_handle = mem->device_base + (pageno << PAGE_SHIFT);
*ret = mem->virt_base + (pageno << PAGE_SHIFT);
memset(*ret, 0, size);
return 1;
err:
/*
* In the case where the allocation can not be satisfied from the
* per-device area, try to fall back to generic memory if the
* constraints allow it.
*/
return mem->flags & DMA_MEMORY_EXCLUSIVE;
}
EXPORT_SYMBOL(dma_alloc_from_coherent);
/**
* dma_release_from_coherent() - try to free the memory allocated from per-device coherent memory pool
* @dev: device from which the memory was allocated
* @order: the order of pages allocated
* @vaddr: virtual address of allocated pages
*
* This checks whether the memory was allocated from the per-device
* coherent memory pool and if so, releases that memory.
*
* Returns 1 if we correctly released the memory, or 0 if
* dma_release_coherent() should proceed with releasing memory from
* generic pools.
*/
int dma_release_from_coherent(struct device *dev, int order, void *vaddr)
{
struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
if (mem && vaddr >= mem->virt_base && vaddr <
(mem->virt_base + (mem->size << PAGE_SHIFT))) {
int page = (vaddr - mem->virt_base) >> PAGE_SHIFT;
bitmap_release_region(mem->bitmap, page, order);
return 1;
}
return 0;
}
EXPORT_SYMBOL(dma_release_from_coherent);