linux/arch/powerpc/mm/dma-noncoherent.c
Tejun Heo 5a0e3ad6af 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>
2010-03-30 22:02:32 +09:00

402 lines
9.9 KiB
C

/*
* PowerPC version derived from arch/arm/mm/consistent.c
* Copyright (C) 2001 Dan Malek (dmalek@jlc.net)
*
* Copyright (C) 2000 Russell King
*
* Consistent memory allocators. Used for DMA devices that want to
* share uncached memory with the processor core. The function return
* is the virtual address and 'dma_handle' is the physical address.
* Mostly stolen from the ARM port, with some changes for PowerPC.
* -- Dan
*
* Reorganized to get rid of the arch-specific consistent_* functions
* and provide non-coherent implementations for the DMA API. -Matt
*
* Added in_interrupt() safe dma_alloc_coherent()/dma_free_coherent()
* implementation. This is pulled straight from ARM and barely
* modified. -Matt
*
* 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/sched.h>
#include <linux/slab.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/highmem.h>
#include <linux/dma-mapping.h>
#include <asm/tlbflush.h>
#include "mmu_decl.h"
/*
* This address range defaults to a value that is safe for all
* platforms which currently set CONFIG_NOT_COHERENT_CACHE. It
* can be further configured for specific applications under
* the "Advanced Setup" menu. -Matt
*/
#define CONSISTENT_BASE (IOREMAP_TOP)
#define CONSISTENT_END (CONSISTENT_BASE + CONFIG_CONSISTENT_SIZE)
#define CONSISTENT_OFFSET(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PAGE_SHIFT)
/*
* This is the page table (2MB) covering uncached, DMA consistent allocations
*/
static DEFINE_SPINLOCK(consistent_lock);
/*
* VM region handling support.
*
* This should become something generic, handling VM region allocations for
* vmalloc and similar (ioremap, module space, etc).
*
* I envisage vmalloc()'s supporting vm_struct becoming:
*
* struct vm_struct {
* struct vm_region region;
* unsigned long flags;
* struct page **pages;
* unsigned int nr_pages;
* unsigned long phys_addr;
* };
*
* get_vm_area() would then call vm_region_alloc with an appropriate
* struct vm_region head (eg):
*
* struct vm_region vmalloc_head = {
* .vm_list = LIST_HEAD_INIT(vmalloc_head.vm_list),
* .vm_start = VMALLOC_START,
* .vm_end = VMALLOC_END,
* };
*
* However, vmalloc_head.vm_start is variable (typically, it is dependent on
* the amount of RAM found at boot time.) I would imagine that get_vm_area()
* would have to initialise this each time prior to calling vm_region_alloc().
*/
struct ppc_vm_region {
struct list_head vm_list;
unsigned long vm_start;
unsigned long vm_end;
};
static struct ppc_vm_region consistent_head = {
.vm_list = LIST_HEAD_INIT(consistent_head.vm_list),
.vm_start = CONSISTENT_BASE,
.vm_end = CONSISTENT_END,
};
static struct ppc_vm_region *
ppc_vm_region_alloc(struct ppc_vm_region *head, size_t size, gfp_t gfp)
{
unsigned long addr = head->vm_start, end = head->vm_end - size;
unsigned long flags;
struct ppc_vm_region *c, *new;
new = kmalloc(sizeof(struct ppc_vm_region), gfp);
if (!new)
goto out;
spin_lock_irqsave(&consistent_lock, flags);
list_for_each_entry(c, &head->vm_list, vm_list) {
if ((addr + size) < addr)
goto nospc;
if ((addr + size) <= c->vm_start)
goto found;
addr = c->vm_end;
if (addr > end)
goto nospc;
}
found:
/*
* Insert this entry _before_ the one we found.
*/
list_add_tail(&new->vm_list, &c->vm_list);
new->vm_start = addr;
new->vm_end = addr + size;
spin_unlock_irqrestore(&consistent_lock, flags);
return new;
nospc:
spin_unlock_irqrestore(&consistent_lock, flags);
kfree(new);
out:
return NULL;
}
static struct ppc_vm_region *ppc_vm_region_find(struct ppc_vm_region *head, unsigned long addr)
{
struct ppc_vm_region *c;
list_for_each_entry(c, &head->vm_list, vm_list) {
if (c->vm_start == addr)
goto out;
}
c = NULL;
out:
return c;
}
/*
* Allocate DMA-coherent memory space and return both the kernel remapped
* virtual and bus address for that space.
*/
void *
__dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp)
{
struct page *page;
struct ppc_vm_region *c;
unsigned long order;
u64 mask = ISA_DMA_THRESHOLD, limit;
if (dev) {
mask = dev->coherent_dma_mask;
/*
* Sanity check the DMA mask - it must be non-zero, and
* must be able to be satisfied by a DMA allocation.
*/
if (mask == 0) {
dev_warn(dev, "coherent DMA mask is unset\n");
goto no_page;
}
if ((~mask) & ISA_DMA_THRESHOLD) {
dev_warn(dev, "coherent DMA mask %#llx is smaller "
"than system GFP_DMA mask %#llx\n",
mask, (unsigned long long)ISA_DMA_THRESHOLD);
goto no_page;
}
}
size = PAGE_ALIGN(size);
limit = (mask + 1) & ~mask;
if ((limit && size >= limit) ||
size >= (CONSISTENT_END - CONSISTENT_BASE)) {
printk(KERN_WARNING "coherent allocation too big (requested %#x mask %#Lx)\n",
size, mask);
return NULL;
}
order = get_order(size);
/* Might be useful if we ever have a real legacy DMA zone... */
if (mask != 0xffffffff)
gfp |= GFP_DMA;
page = alloc_pages(gfp, order);
if (!page)
goto no_page;
/*
* Invalidate any data that might be lurking in the
* kernel direct-mapped region for device DMA.
*/
{
unsigned long kaddr = (unsigned long)page_address(page);
memset(page_address(page), 0, size);
flush_dcache_range(kaddr, kaddr + size);
}
/*
* Allocate a virtual address in the consistent mapping region.
*/
c = ppc_vm_region_alloc(&consistent_head, size,
gfp & ~(__GFP_DMA | __GFP_HIGHMEM));
if (c) {
unsigned long vaddr = c->vm_start;
struct page *end = page + (1 << order);
split_page(page, order);
/*
* Set the "dma handle"
*/
*handle = page_to_phys(page);
do {
SetPageReserved(page);
map_page(vaddr, page_to_phys(page),
pgprot_noncached(PAGE_KERNEL));
page++;
vaddr += PAGE_SIZE;
} while (size -= PAGE_SIZE);
/*
* Free the otherwise unused pages.
*/
while (page < end) {
__free_page(page);
page++;
}
return (void *)c->vm_start;
}
if (page)
__free_pages(page, order);
no_page:
return NULL;
}
EXPORT_SYMBOL(__dma_alloc_coherent);
/*
* free a page as defined by the above mapping.
*/
void __dma_free_coherent(size_t size, void *vaddr)
{
struct ppc_vm_region *c;
unsigned long flags, addr;
size = PAGE_ALIGN(size);
spin_lock_irqsave(&consistent_lock, flags);
c = ppc_vm_region_find(&consistent_head, (unsigned long)vaddr);
if (!c)
goto no_area;
if ((c->vm_end - c->vm_start) != size) {
printk(KERN_ERR "%s: freeing wrong coherent size (%ld != %d)\n",
__func__, c->vm_end - c->vm_start, size);
dump_stack();
size = c->vm_end - c->vm_start;
}
addr = c->vm_start;
do {
pte_t *ptep;
unsigned long pfn;
ptep = pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(addr),
addr),
addr),
addr);
if (!pte_none(*ptep) && pte_present(*ptep)) {
pfn = pte_pfn(*ptep);
pte_clear(&init_mm, addr, ptep);
if (pfn_valid(pfn)) {
struct page *page = pfn_to_page(pfn);
ClearPageReserved(page);
__free_page(page);
}
}
addr += PAGE_SIZE;
} while (size -= PAGE_SIZE);
flush_tlb_kernel_range(c->vm_start, c->vm_end);
list_del(&c->vm_list);
spin_unlock_irqrestore(&consistent_lock, flags);
kfree(c);
return;
no_area:
spin_unlock_irqrestore(&consistent_lock, flags);
printk(KERN_ERR "%s: trying to free invalid coherent area: %p\n",
__func__, vaddr);
dump_stack();
}
EXPORT_SYMBOL(__dma_free_coherent);
/*
* make an area consistent.
*/
void __dma_sync(void *vaddr, size_t size, int direction)
{
unsigned long start = (unsigned long)vaddr;
unsigned long end = start + size;
switch (direction) {
case DMA_NONE:
BUG();
case DMA_FROM_DEVICE:
/*
* invalidate only when cache-line aligned otherwise there is
* the potential for discarding uncommitted data from the cache
*/
if ((start & (L1_CACHE_BYTES - 1)) || (size & (L1_CACHE_BYTES - 1)))
flush_dcache_range(start, end);
else
invalidate_dcache_range(start, end);
break;
case DMA_TO_DEVICE: /* writeback only */
clean_dcache_range(start, end);
break;
case DMA_BIDIRECTIONAL: /* writeback and invalidate */
flush_dcache_range(start, end);
break;
}
}
EXPORT_SYMBOL(__dma_sync);
#ifdef CONFIG_HIGHMEM
/*
* __dma_sync_page() implementation for systems using highmem.
* In this case, each page of a buffer must be kmapped/kunmapped
* in order to have a virtual address for __dma_sync(). This must
* not sleep so kmap_atomic()/kunmap_atomic() are used.
*
* Note: yes, it is possible and correct to have a buffer extend
* beyond the first page.
*/
static inline void __dma_sync_page_highmem(struct page *page,
unsigned long offset, size_t size, int direction)
{
size_t seg_size = min((size_t)(PAGE_SIZE - offset), size);
size_t cur_size = seg_size;
unsigned long flags, start, seg_offset = offset;
int nr_segs = 1 + ((size - seg_size) + PAGE_SIZE - 1)/PAGE_SIZE;
int seg_nr = 0;
local_irq_save(flags);
do {
start = (unsigned long)kmap_atomic(page + seg_nr,
KM_PPC_SYNC_PAGE) + seg_offset;
/* Sync this buffer segment */
__dma_sync((void *)start, seg_size, direction);
kunmap_atomic((void *)start, KM_PPC_SYNC_PAGE);
seg_nr++;
/* Calculate next buffer segment size */
seg_size = min((size_t)PAGE_SIZE, size - cur_size);
/* Add the segment size to our running total */
cur_size += seg_size;
seg_offset = 0;
} while (seg_nr < nr_segs);
local_irq_restore(flags);
}
#endif /* CONFIG_HIGHMEM */
/*
* __dma_sync_page makes memory consistent. identical to __dma_sync, but
* takes a struct page instead of a virtual address
*/
void __dma_sync_page(struct page *page, unsigned long offset,
size_t size, int direction)
{
#ifdef CONFIG_HIGHMEM
__dma_sync_page_highmem(page, offset, size, direction);
#else
unsigned long start = (unsigned long)page_address(page) + offset;
__dma_sync((void *)start, size, direction);
#endif
}
EXPORT_SYMBOL(__dma_sync_page);