linux/arch/microblaze/mm/consistent.c

252 lines
6.3 KiB
C
Raw Normal View History

/*
* Microblaze support for cache consistent memory.
* Copyright (C) 2010 Michal Simek <monstr@monstr.eu>
* Copyright (C) 2010 PetaLogix
* Copyright (C) 2005 John Williams <jwilliams@itee.uq.edu.au>
*
* Based on PowerPC version derived from arch/arm/mm/consistent.c
* Copyright (C) 2001 Dan Malek (dmalek@jlc.net)
* Copyright (C) 2000 Russell King
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/export.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/stddef.h>
#include <linux/vmalloc.h>
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/bootmem.h>
#include <linux/highmem.h>
#include <linux/pci.h>
#include <linux/interrupt.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 16:04:11 +08:00
#include <linux/gfp.h>
#include <asm/pgalloc.h>
#include <linux/io.h>
#include <linux/hardirq.h>
#include <linux/mmu_context.h>
#include <asm/mmu.h>
#include <linux/uaccess.h>
#include <asm/pgtable.h>
#include <asm/cpuinfo.h>
#include <asm/tlbflush.h>
#ifndef CONFIG_MMU
/* I have to use dcache values because I can't relate on ram size */
# define UNCACHED_SHADOW_MASK (cpuinfo.dcache_high - cpuinfo.dcache_base + 1)
#endif
/*
* Consistent memory allocators. Used for DMA devices that want to
* share uncached memory with the processor core.
* My crufty no-MMU approach is simple. In the HW platform we can optionally
* mirror the DDR up above the processor cacheable region. So, memory accessed
* in this mirror region will not be cached. It's alloced from the same
* pool as normal memory, but the handle we return is shifted up into the
* uncached region. This will no doubt cause big problems if memory allocated
* here is not also freed properly. -- JW
*/
void *consistent_alloc(gfp_t gfp, size_t size, dma_addr_t *dma_handle)
{
unsigned long order, vaddr;
void *ret;
unsigned int i, err = 0;
struct page *page, *end;
#ifdef CONFIG_MMU
phys_addr_t pa;
struct vm_struct *area;
unsigned long va;
#endif
if (in_interrupt())
BUG();
/* Only allocate page size areas. */
size = PAGE_ALIGN(size);
order = get_order(size);
vaddr = __get_free_pages(gfp, order);
if (!vaddr)
return NULL;
/*
* we need to ensure that there are no cachelines in use,
* or worse dirty in this area.
*/
flush_dcache_range(virt_to_phys((void *)vaddr),
virt_to_phys((void *)vaddr) + size);
#ifndef CONFIG_MMU
ret = (void *)vaddr;
/*
* Here's the magic! Note if the uncached shadow is not implemented,
* it's up to the calling code to also test that condition and make
* other arranegments, such as manually flushing the cache and so on.
*/
# ifdef CONFIG_XILINX_UNCACHED_SHADOW
ret = (void *)((unsigned) ret | UNCACHED_SHADOW_MASK);
# endif
if ((unsigned int)ret > cpuinfo.dcache_base &&
(unsigned int)ret < cpuinfo.dcache_high)
pr_warn("ERROR: Your cache coherent area is CACHED!!!\n");
/* dma_handle is same as physical (shadowed) address */
*dma_handle = (dma_addr_t)ret;
#else
/* Allocate some common virtual space to map the new pages. */
area = get_vm_area(size, VM_ALLOC);
if (!area) {
free_pages(vaddr, order);
return NULL;
}
va = (unsigned long) area->addr;
ret = (void *)va;
/* This gives us the real physical address of the first page. */
*dma_handle = pa = virt_to_bus((void *)vaddr);
#endif
/*
* free wasted pages. We skip the first page since we know
* that it will have count = 1 and won't require freeing.
* We also mark the pages in use as reserved so that
* remap_page_range works.
*/
page = virt_to_page(vaddr);
end = page + (1 << order);
split_page(page, order);
for (i = 0; i < size && err == 0; i += PAGE_SIZE) {
#ifdef CONFIG_MMU
/* MS: This is the whole magic - use cache inhibit pages */
err = map_page(va + i, pa + i, _PAGE_KERNEL | _PAGE_NO_CACHE);
#endif
SetPageReserved(page);
page++;
}
/* Free the otherwise unused pages. */
while (page < end) {
__free_page(page);
page++;
}
if (err) {
free_pages(vaddr, order);
return NULL;
}
return ret;
}
EXPORT_SYMBOL(consistent_alloc);
/*
* free page(s) as defined by the above mapping.
*/
void consistent_free(size_t size, void *vaddr)
{
struct page *page;
if (in_interrupt())
BUG();
size = PAGE_ALIGN(size);
#ifndef CONFIG_MMU
/* Clear SHADOW_MASK bit in address, and free as per usual */
# ifdef CONFIG_XILINX_UNCACHED_SHADOW
vaddr = (void *)((unsigned)vaddr & ~UNCACHED_SHADOW_MASK);
# endif
page = virt_to_page(vaddr);
do {
__free_reserved_page(page);
page++;
} while (size -= PAGE_SIZE);
#else
do {
pte_t *ptep;
unsigned long pfn;
ptep = pte_offset_kernel(pmd_offset(pgd_offset_k(
(unsigned int)vaddr),
(unsigned int)vaddr),
(unsigned int)vaddr);
if (!pte_none(*ptep) && pte_present(*ptep)) {
pfn = pte_pfn(*ptep);
pte_clear(&init_mm, (unsigned int)vaddr, ptep);
if (pfn_valid(pfn)) {
page = pfn_to_page(pfn);
__free_reserved_page(page);
}
}
vaddr += PAGE_SIZE;
} while (size -= PAGE_SIZE);
/* flush tlb */
flush_tlb_all();
#endif
}
EXPORT_SYMBOL(consistent_free);
/*
* make an area consistent.
*/
void consistent_sync(void *vaddr, size_t size, int direction)
{
unsigned long start;
unsigned long end;
start = (unsigned long)vaddr;
/* Convert start address back down to unshadowed memory region */
#ifdef CONFIG_XILINX_UNCACHED_SHADOW
start &= ~UNCACHED_SHADOW_MASK;
#endif
end = start + size;
switch (direction) {
case PCI_DMA_NONE:
BUG();
case PCI_DMA_FROMDEVICE: /* invalidate only */
invalidate_dcache_range(start, end);
break;
case PCI_DMA_TODEVICE: /* writeback only */
flush_dcache_range(start, end);
break;
case PCI_DMA_BIDIRECTIONAL: /* writeback and invalidate */
flush_dcache_range(start, end);
break;
}
}
EXPORT_SYMBOL(consistent_sync);
/*
* consistent_sync_page makes memory consistent. identical
* to consistent_sync, but takes a struct page instead of a
* virtual address
*/
void consistent_sync_page(struct page *page, unsigned long offset,
size_t size, int direction)
{
unsigned long start = (unsigned long)page_address(page) + offset;
consistent_sync((void *)start, size, direction);
}
EXPORT_SYMBOL(consistent_sync_page);