linux_dsm_epyc7002/arch/xtensa/kernel/pci-dma.c

213 lines
5.0 KiB
C
Raw Normal View History

/*
* DMA coherent memory allocation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the
* Free Software Foundation; either version 2 of the License, or (at your
* option) any later version.
*
* Copyright (C) 2002 - 2005 Tensilica Inc.
* Copyright (C) 2015 Cadence Design Systems Inc.
*
* Based on version for i386.
*
* Chris Zankel <chris@zankel.net>
* Joe Taylor <joe@tensilica.com, joetylr@yahoo.com>
*/
#include <linux/dma-contiguous.h>
#include <linux/dma-noncoherent.h>
#include <linux/dma-direct.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/highmem.h>
#include <linux/mm.h>
#include <linux/types.h>
#include <asm/cacheflush.h>
#include <asm/io.h>
#include <asm/platform.h>
static void do_cache_op(phys_addr_t paddr, size_t size,
void (*fn)(unsigned long, unsigned long))
{
unsigned long off = paddr & (PAGE_SIZE - 1);
unsigned long pfn = PFN_DOWN(paddr);
struct page *page = pfn_to_page(pfn);
if (!PageHighMem(page))
fn((unsigned long)phys_to_virt(paddr), size);
else
while (size > 0) {
size_t sz = min_t(size_t, size, PAGE_SIZE - off);
void *vaddr = kmap_atomic(page);
fn((unsigned long)vaddr + off, sz);
kunmap_atomic(vaddr);
off = 0;
++page;
size -= sz;
}
}
void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
size_t size, enum dma_data_direction dir)
{
switch (dir) {
case DMA_BIDIRECTIONAL:
case DMA_FROM_DEVICE:
do_cache_op(paddr, size, __invalidate_dcache_range);
break;
case DMA_NONE:
BUG();
break;
default:
break;
}
}
void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
size_t size, enum dma_data_direction dir)
{
switch (dir) {
case DMA_BIDIRECTIONAL:
case DMA_TO_DEVICE:
if (XCHAL_DCACHE_IS_WRITEBACK)
do_cache_op(paddr, size, __flush_dcache_range);
break;
case DMA_NONE:
BUG();
break;
default:
break;
}
}
#ifdef CONFIG_MMU
bool platform_vaddr_cached(const void *p)
{
unsigned long addr = (unsigned long)p;
return addr >= XCHAL_KSEG_CACHED_VADDR &&
addr - XCHAL_KSEG_CACHED_VADDR < XCHAL_KSEG_SIZE;
}
bool platform_vaddr_uncached(const void *p)
{
unsigned long addr = (unsigned long)p;
return addr >= XCHAL_KSEG_BYPASS_VADDR &&
addr - XCHAL_KSEG_BYPASS_VADDR < XCHAL_KSEG_SIZE;
}
void *platform_vaddr_to_uncached(void *p)
{
return p + XCHAL_KSEG_BYPASS_VADDR - XCHAL_KSEG_CACHED_VADDR;
}
void *platform_vaddr_to_cached(void *p)
{
return p + XCHAL_KSEG_CACHED_VADDR - XCHAL_KSEG_BYPASS_VADDR;
}
#else
bool __attribute__((weak)) platform_vaddr_cached(const void *p)
{
WARN_ONCE(1, "Default %s implementation is used\n", __func__);
return true;
}
bool __attribute__((weak)) platform_vaddr_uncached(const void *p)
{
WARN_ONCE(1, "Default %s implementation is used\n", __func__);
return false;
}
void __attribute__((weak)) *platform_vaddr_to_uncached(void *p)
{
WARN_ONCE(1, "Default %s implementation is used\n", __func__);
return p;
}
void __attribute__((weak)) *platform_vaddr_to_cached(void *p)
{
WARN_ONCE(1, "Default %s implementation is used\n", __func__);
return p;
}
#endif
/*
* Note: We assume that the full memory space is always mapped to 'kseg'
* Otherwise we have to use page attributes (not implemented).
*/
void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
gfp_t flag, unsigned long attrs)
{
unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
struct page *page = NULL;
/* ignore region speicifiers */
flag &= ~(__GFP_DMA | __GFP_HIGHMEM);
if (dev == NULL || (dev->coherent_dma_mask < 0xffffffff))
flag |= GFP_DMA;
if (gfpflags_allow_blocking(flag))
page = dma_alloc_from_contiguous(dev, count, get_order(size),
flag & __GFP_NOWARN);
if (!page)
page = alloc_pages(flag | __GFP_ZERO, get_order(size));
if (!page)
return NULL;
*handle = phys_to_dma(dev, page_to_phys(page));
if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) {
return page;
}
#ifdef CONFIG_MMU
if (PageHighMem(page)) {
void *p;
p = dma_common_contiguous_remap(page, size, VM_MAP,
pgprot_noncached(PAGE_KERNEL),
__builtin_return_address(0));
if (!p) {
if (!dma_release_from_contiguous(dev, page, count))
__free_pages(page, get_order(size));
}
return p;
}
#endif
BUG_ON(!platform_vaddr_cached(page_address(page)));
__invalidate_dcache_range((unsigned long)page_address(page), size);
return platform_vaddr_to_uncached(page_address(page));
}
void arch_dma_free(struct device *dev, size_t size, void *vaddr,
dma_addr_t dma_handle, unsigned long attrs)
{
unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
struct page *page;
if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) {
page = vaddr;
} else if (platform_vaddr_uncached(vaddr)) {
page = virt_to_page(platform_vaddr_to_cached(vaddr));
} else {
#ifdef CONFIG_MMU
dma_common_free_remap(vaddr, size, VM_MAP);
#endif
page = pfn_to_page(PHYS_PFN(dma_to_phys(dev, dma_handle)));
}
if (!dma_release_from_contiguous(dev, page, count))
__free_pages(page, get_order(size));
}