linux_dsm_epyc7002/arch/mips/mm/dma-default.c

383 lines
8.8 KiB
C
Raw Normal View History

/*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*
* Copyright (C) 2000 Ani Joshi <ajoshi@unixbox.com>
* Copyright (C) 2000, 2001, 06 Ralf Baechle <ralf@linux-mips.org>
* swiped from i386, and cloned for MIPS by Geert, polished by Ralf.
*/
#include <linux/types.h>
#include <linux/dma-mapping.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/scatterlist.h>
#include <linux/string.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 <asm/cache.h>
#include <asm/io.h>
#include <dma-coherence.h>
static inline unsigned long dma_addr_to_virt(struct device *dev,
dma_addr_t dma_addr)
{
unsigned long addr = plat_dma_addr_to_phys(dev, dma_addr);
return (unsigned long)phys_to_virt(addr);
}
/*
* Warning on the terminology - Linux calls an uncached area coherent;
* MIPS terminology calls memory areas with hardware maintained coherency
* coherent.
*/
static inline int cpu_is_noncoherent_r10000(struct device *dev)
{
return !plat_device_is_coherent(dev) &&
(current_cpu_type() == CPU_R10000 ||
current_cpu_type() == CPU_R12000);
}
static gfp_t massage_gfp_flags(const struct device *dev, gfp_t gfp)
{
gfp_t dma_flag;
/* ignore region specifiers */
gfp &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM);
#ifdef CONFIG_ISA
if (dev == NULL)
dma_flag = __GFP_DMA;
else
#endif
#if defined(CONFIG_ZONE_DMA32) && defined(CONFIG_ZONE_DMA)
if (dev->coherent_dma_mask < DMA_BIT_MASK(32))
dma_flag = __GFP_DMA;
else if (dev->coherent_dma_mask < DMA_BIT_MASK(64))
dma_flag = __GFP_DMA32;
else
#endif
#if defined(CONFIG_ZONE_DMA32) && !defined(CONFIG_ZONE_DMA)
if (dev->coherent_dma_mask < DMA_BIT_MASK(64))
dma_flag = __GFP_DMA32;
else
#endif
#if defined(CONFIG_ZONE_DMA) && !defined(CONFIG_ZONE_DMA32)
if (dev->coherent_dma_mask < DMA_BIT_MASK(64))
dma_flag = __GFP_DMA;
else
#endif
dma_flag = 0;
/* Don't invoke OOM killer */
gfp |= __GFP_NORETRY;
return gfp | dma_flag;
}
void *dma_alloc_noncoherent(struct device *dev, size_t size,
dma_addr_t * dma_handle, gfp_t gfp)
{
void *ret;
gfp = massage_gfp_flags(dev, gfp);
ret = (void *) __get_free_pages(gfp, get_order(size));
if (ret != NULL) {
memset(ret, 0, size);
*dma_handle = plat_map_dma_mem(dev, ret, size);
}
return ret;
}
EXPORT_SYMBOL(dma_alloc_noncoherent);
void *dma_alloc_coherent(struct device *dev, size_t size,
dma_addr_t * dma_handle, gfp_t gfp)
{
void *ret;
if (dma_alloc_from_coherent(dev, size, dma_handle, &ret))
return ret;
gfp = massage_gfp_flags(dev, gfp);
ret = (void *) __get_free_pages(gfp, get_order(size));
if (ret) {
memset(ret, 0, size);
*dma_handle = plat_map_dma_mem(dev, ret, size);
if (!plat_device_is_coherent(dev)) {
dma_cache_wback_inv((unsigned long) ret, size);
ret = UNCAC_ADDR(ret);
}
}
return ret;
}
EXPORT_SYMBOL(dma_alloc_coherent);
void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr,
dma_addr_t dma_handle)
{
plat_unmap_dma_mem(dev, dma_handle, size, DMA_BIDIRECTIONAL);
free_pages((unsigned long) vaddr, get_order(size));
}
EXPORT_SYMBOL(dma_free_noncoherent);
void dma_free_coherent(struct device *dev, size_t size, void *vaddr,
dma_addr_t dma_handle)
{
unsigned long addr = (unsigned long) vaddr;
int order = get_order(size);
if (dma_release_from_coherent(dev, order, vaddr))
return;
plat_unmap_dma_mem(dev, dma_handle, size, DMA_BIDIRECTIONAL);
if (!plat_device_is_coherent(dev))
addr = CAC_ADDR(addr);
free_pages(addr, get_order(size));
}
EXPORT_SYMBOL(dma_free_coherent);
static inline void __dma_sync(unsigned long addr, size_t size,
enum dma_data_direction direction)
{
switch (direction) {
case DMA_TO_DEVICE:
dma_cache_wback(addr, size);
break;
case DMA_FROM_DEVICE:
dma_cache_inv(addr, size);
break;
case DMA_BIDIRECTIONAL:
dma_cache_wback_inv(addr, size);
break;
default:
BUG();
}
}
dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size,
enum dma_data_direction direction)
{
unsigned long addr = (unsigned long) ptr;
if (!plat_device_is_coherent(dev))
__dma_sync(addr, size, direction);
return plat_map_dma_mem(dev, ptr, size);
}
EXPORT_SYMBOL(dma_map_single);
void dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
enum dma_data_direction direction)
{
if (cpu_is_noncoherent_r10000(dev))
__dma_sync(dma_addr_to_virt(dev, dma_addr), size,
direction);
plat_unmap_dma_mem(dev, dma_addr, size, direction);
}
EXPORT_SYMBOL(dma_unmap_single);
int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
enum dma_data_direction direction)
{
int i;
BUG_ON(direction == DMA_NONE);
for (i = 0; i < nents; i++, sg++) {
unsigned long addr;
addr = (unsigned long) sg_virt(sg);
if (!plat_device_is_coherent(dev) && addr)
__dma_sync(addr, sg->length, direction);
sg->dma_address = plat_map_dma_mem(dev,
(void *)addr, sg->length);
}
return nents;
}
EXPORT_SYMBOL(dma_map_sg);
dma_addr_t dma_map_page(struct device *dev, struct page *page,
unsigned long offset, size_t size, enum dma_data_direction direction)
{
BUG_ON(direction == DMA_NONE);
if (!plat_device_is_coherent(dev)) {
unsigned long addr;
addr = (unsigned long) page_address(page) + offset;
__dma_sync(addr, size, direction);
}
return plat_map_dma_mem_page(dev, page) + offset;
}
EXPORT_SYMBOL(dma_map_page);
void dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
enum dma_data_direction direction)
{
unsigned long addr;
int i;
BUG_ON(direction == DMA_NONE);
for (i = 0; i < nhwentries; i++, sg++) {
if (!plat_device_is_coherent(dev) &&
direction != DMA_TO_DEVICE) {
addr = (unsigned long) sg_virt(sg);
if (addr)
__dma_sync(addr, sg->length, direction);
}
plat_unmap_dma_mem(dev, sg->dma_address, sg->length, direction);
}
}
EXPORT_SYMBOL(dma_unmap_sg);
void dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
size_t size, enum dma_data_direction direction)
{
BUG_ON(direction == DMA_NONE);
if (cpu_is_noncoherent_r10000(dev)) {
unsigned long addr;
addr = dma_addr_to_virt(dev, dma_handle);
__dma_sync(addr, size, direction);
}
}
EXPORT_SYMBOL(dma_sync_single_for_cpu);
void dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle,
size_t size, enum dma_data_direction direction)
{
BUG_ON(direction == DMA_NONE);
plat_extra_sync_for_device(dev);
if (!plat_device_is_coherent(dev)) {
unsigned long addr;
addr = dma_addr_to_virt(dev, dma_handle);
__dma_sync(addr, size, direction);
}
}
EXPORT_SYMBOL(dma_sync_single_for_device);
void dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t dma_handle,
unsigned long offset, size_t size, enum dma_data_direction direction)
{
BUG_ON(direction == DMA_NONE);
if (cpu_is_noncoherent_r10000(dev)) {
unsigned long addr;
addr = dma_addr_to_virt(dev, dma_handle);
__dma_sync(addr + offset, size, direction);
}
}
EXPORT_SYMBOL(dma_sync_single_range_for_cpu);
void dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle,
unsigned long offset, size_t size, enum dma_data_direction direction)
{
BUG_ON(direction == DMA_NONE);
plat_extra_sync_for_device(dev);
if (!plat_device_is_coherent(dev)) {
unsigned long addr;
addr = dma_addr_to_virt(dev, dma_handle);
__dma_sync(addr + offset, size, direction);
}
}
EXPORT_SYMBOL(dma_sync_single_range_for_device);
void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems,
enum dma_data_direction direction)
{
int i;
BUG_ON(direction == DMA_NONE);
/* Make sure that gcc doesn't leave the empty loop body. */
for (i = 0; i < nelems; i++, sg++) {
if (cpu_is_noncoherent_r10000(dev))
__dma_sync((unsigned long)page_address(sg_page(sg)),
sg->length, direction);
}
}
EXPORT_SYMBOL(dma_sync_sg_for_cpu);
void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems,
enum dma_data_direction direction)
{
int i;
BUG_ON(direction == DMA_NONE);
/* Make sure that gcc doesn't leave the empty loop body. */
for (i = 0; i < nelems; i++, sg++) {
if (!plat_device_is_coherent(dev))
__dma_sync((unsigned long)page_address(sg_page(sg)),
sg->length, direction);
}
}
EXPORT_SYMBOL(dma_sync_sg_for_device);
dma-mapping: add the device argument to dma_mapping_error() Add per-device dma_mapping_ops support for CONFIG_X86_64 as POWER architecture does: This enables us to cleanly fix the Calgary IOMMU issue that some devices are not behind the IOMMU (http://lkml.org/lkml/2008/5/8/423). I think that per-device dma_mapping_ops support would be also helpful for KVM people to support PCI passthrough but Andi thinks that this makes it difficult to support the PCI passthrough (see the above thread). So I CC'ed this to KVM camp. Comments are appreciated. A pointer to dma_mapping_ops to struct dev_archdata is added. If the pointer is non NULL, DMA operations in asm/dma-mapping.h use it. If it's NULL, the system-wide dma_ops pointer is used as before. If it's useful for KVM people, I plan to implement a mechanism to register a hook called when a new pci (or dma capable) device is created (it works with hot plugging). It enables IOMMUs to set up an appropriate dma_mapping_ops per device. The major obstacle is that dma_mapping_error doesn't take a pointer to the device unlike other DMA operations. So x86 can't have dma_mapping_ops per device. Note all the POWER IOMMUs use the same dma_mapping_error function so this is not a problem for POWER but x86 IOMMUs use different dma_mapping_error functions. The first patch adds the device argument to dma_mapping_error. The patch is trivial but large since it touches lots of drivers and dma-mapping.h in all the architecture. This patch: dma_mapping_error() doesn't take a pointer to the device unlike other DMA operations. So we can't have dma_mapping_ops per device. Note that POWER already has dma_mapping_ops per device but all the POWER IOMMUs use the same dma_mapping_error function. x86 IOMMUs use device argument. [akpm@linux-foundation.org: fix sge] [akpm@linux-foundation.org: fix svc_rdma] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix bnx2x] [akpm@linux-foundation.org: fix s2io] [akpm@linux-foundation.org: fix pasemi_mac] [akpm@linux-foundation.org: fix sdhci] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix sparc] [akpm@linux-foundation.org: fix ibmvscsi] Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Muli Ben-Yehuda <muli@il.ibm.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Avi Kivity <avi@qumranet.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 09:44:49 +07:00
int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
{
return plat_dma_mapping_error(dev, dma_addr);
}
EXPORT_SYMBOL(dma_mapping_error);
int dma_supported(struct device *dev, u64 mask)
{
return plat_dma_supported(dev, mask);
}
EXPORT_SYMBOL(dma_supported);
void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
enum dma_data_direction direction)
{
BUG_ON(direction == DMA_NONE);
plat_extra_sync_for_device(dev);
if (!plat_device_is_coherent(dev))
__dma_sync((unsigned long)vaddr, size, direction);
}
EXPORT_SYMBOL(dma_cache_sync);