mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-21 08:19:28 +00:00
![Tejun Heo](/assets/img/avatar_default.png)
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>
289 lines
6.2 KiB
C
289 lines
6.2 KiB
C
/*
|
|
* DMA region bookkeeping routines
|
|
*
|
|
* Copyright (C) 2002 Maas Digital LLC
|
|
*
|
|
* This code is licensed under the GPL. See the file COPYING in the root
|
|
* directory of the kernel sources for details.
|
|
*/
|
|
|
|
#include <linux/mm.h>
|
|
#include <linux/module.h>
|
|
#include <linux/pci.h>
|
|
#include <linux/vmalloc.h>
|
|
#include <linux/scatterlist.h>
|
|
|
|
#include "dma.h"
|
|
|
|
/* dma_prog_region */
|
|
|
|
void dma_prog_region_init(struct dma_prog_region *prog)
|
|
{
|
|
prog->kvirt = NULL;
|
|
prog->dev = NULL;
|
|
prog->n_pages = 0;
|
|
prog->bus_addr = 0;
|
|
}
|
|
|
|
int dma_prog_region_alloc(struct dma_prog_region *prog, unsigned long n_bytes,
|
|
struct pci_dev *dev)
|
|
{
|
|
/* round up to page size */
|
|
n_bytes = PAGE_ALIGN(n_bytes);
|
|
|
|
prog->n_pages = n_bytes >> PAGE_SHIFT;
|
|
|
|
prog->kvirt = pci_alloc_consistent(dev, n_bytes, &prog->bus_addr);
|
|
if (!prog->kvirt) {
|
|
printk(KERN_ERR
|
|
"dma_prog_region_alloc: pci_alloc_consistent() failed\n");
|
|
dma_prog_region_free(prog);
|
|
return -ENOMEM;
|
|
}
|
|
|
|
prog->dev = dev;
|
|
|
|
return 0;
|
|
}
|
|
|
|
void dma_prog_region_free(struct dma_prog_region *prog)
|
|
{
|
|
if (prog->kvirt) {
|
|
pci_free_consistent(prog->dev, prog->n_pages << PAGE_SHIFT,
|
|
prog->kvirt, prog->bus_addr);
|
|
}
|
|
|
|
prog->kvirt = NULL;
|
|
prog->dev = NULL;
|
|
prog->n_pages = 0;
|
|
prog->bus_addr = 0;
|
|
}
|
|
|
|
/* dma_region */
|
|
|
|
/**
|
|
* dma_region_init - clear out all fields but do not allocate anything
|
|
*/
|
|
void dma_region_init(struct dma_region *dma)
|
|
{
|
|
dma->kvirt = NULL;
|
|
dma->dev = NULL;
|
|
dma->n_pages = 0;
|
|
dma->n_dma_pages = 0;
|
|
dma->sglist = NULL;
|
|
}
|
|
|
|
/**
|
|
* dma_region_alloc - allocate the buffer and map it to the IOMMU
|
|
*/
|
|
int dma_region_alloc(struct dma_region *dma, unsigned long n_bytes,
|
|
struct pci_dev *dev, int direction)
|
|
{
|
|
unsigned int i;
|
|
|
|
/* round up to page size */
|
|
n_bytes = PAGE_ALIGN(n_bytes);
|
|
|
|
dma->n_pages = n_bytes >> PAGE_SHIFT;
|
|
|
|
dma->kvirt = vmalloc_32(n_bytes);
|
|
if (!dma->kvirt) {
|
|
printk(KERN_ERR "dma_region_alloc: vmalloc_32() failed\n");
|
|
goto err;
|
|
}
|
|
|
|
/* Clear the ram out, no junk to the user */
|
|
memset(dma->kvirt, 0, n_bytes);
|
|
|
|
/* allocate scatter/gather list */
|
|
dma->sglist = vmalloc(dma->n_pages * sizeof(*dma->sglist));
|
|
if (!dma->sglist) {
|
|
printk(KERN_ERR "dma_region_alloc: vmalloc(sglist) failed\n");
|
|
goto err;
|
|
}
|
|
|
|
sg_init_table(dma->sglist, dma->n_pages);
|
|
|
|
/* fill scatter/gather list with pages */
|
|
for (i = 0; i < dma->n_pages; i++) {
|
|
unsigned long va =
|
|
(unsigned long)dma->kvirt + (i << PAGE_SHIFT);
|
|
|
|
sg_set_page(&dma->sglist[i], vmalloc_to_page((void *)va),
|
|
PAGE_SIZE, 0);
|
|
}
|
|
|
|
/* map sglist to the IOMMU */
|
|
dma->n_dma_pages =
|
|
pci_map_sg(dev, dma->sglist, dma->n_pages, direction);
|
|
|
|
if (dma->n_dma_pages == 0) {
|
|
printk(KERN_ERR "dma_region_alloc: pci_map_sg() failed\n");
|
|
goto err;
|
|
}
|
|
|
|
dma->dev = dev;
|
|
dma->direction = direction;
|
|
|
|
return 0;
|
|
|
|
err:
|
|
dma_region_free(dma);
|
|
return -ENOMEM;
|
|
}
|
|
|
|
/**
|
|
* dma_region_free - unmap and free the buffer
|
|
*/
|
|
void dma_region_free(struct dma_region *dma)
|
|
{
|
|
if (dma->n_dma_pages) {
|
|
pci_unmap_sg(dma->dev, dma->sglist, dma->n_pages,
|
|
dma->direction);
|
|
dma->n_dma_pages = 0;
|
|
dma->dev = NULL;
|
|
}
|
|
|
|
vfree(dma->sglist);
|
|
dma->sglist = NULL;
|
|
|
|
vfree(dma->kvirt);
|
|
dma->kvirt = NULL;
|
|
dma->n_pages = 0;
|
|
}
|
|
|
|
/* find the scatterlist index and remaining offset corresponding to a
|
|
given offset from the beginning of the buffer */
|
|
static inline int dma_region_find(struct dma_region *dma, unsigned long offset,
|
|
unsigned int start, unsigned long *rem)
|
|
{
|
|
int i;
|
|
unsigned long off = offset;
|
|
|
|
for (i = start; i < dma->n_dma_pages; i++) {
|
|
if (off < sg_dma_len(&dma->sglist[i])) {
|
|
*rem = off;
|
|
break;
|
|
}
|
|
|
|
off -= sg_dma_len(&dma->sglist[i]);
|
|
}
|
|
|
|
BUG_ON(i >= dma->n_dma_pages);
|
|
|
|
return i;
|
|
}
|
|
|
|
/**
|
|
* dma_region_offset_to_bus - get bus address of an offset within a DMA region
|
|
*
|
|
* Returns the DMA bus address of the byte with the given @offset relative to
|
|
* the beginning of the @dma.
|
|
*/
|
|
dma_addr_t dma_region_offset_to_bus(struct dma_region * dma,
|
|
unsigned long offset)
|
|
{
|
|
unsigned long rem = 0;
|
|
|
|
struct scatterlist *sg =
|
|
&dma->sglist[dma_region_find(dma, offset, 0, &rem)];
|
|
return sg_dma_address(sg) + rem;
|
|
}
|
|
|
|
/**
|
|
* dma_region_sync_for_cpu - sync the CPU's view of the buffer
|
|
*/
|
|
void dma_region_sync_for_cpu(struct dma_region *dma, unsigned long offset,
|
|
unsigned long len)
|
|
{
|
|
int first, last;
|
|
unsigned long rem = 0;
|
|
|
|
if (!len)
|
|
len = 1;
|
|
|
|
first = dma_region_find(dma, offset, 0, &rem);
|
|
last = dma_region_find(dma, rem + len - 1, first, &rem);
|
|
|
|
pci_dma_sync_sg_for_cpu(dma->dev, &dma->sglist[first], last - first + 1,
|
|
dma->direction);
|
|
}
|
|
|
|
/**
|
|
* dma_region_sync_for_device - sync the IO bus' view of the buffer
|
|
*/
|
|
void dma_region_sync_for_device(struct dma_region *dma, unsigned long offset,
|
|
unsigned long len)
|
|
{
|
|
int first, last;
|
|
unsigned long rem = 0;
|
|
|
|
if (!len)
|
|
len = 1;
|
|
|
|
first = dma_region_find(dma, offset, 0, &rem);
|
|
last = dma_region_find(dma, rem + len - 1, first, &rem);
|
|
|
|
pci_dma_sync_sg_for_device(dma->dev, &dma->sglist[first],
|
|
last - first + 1, dma->direction);
|
|
}
|
|
|
|
#ifdef CONFIG_MMU
|
|
|
|
static int dma_region_pagefault(struct vm_area_struct *vma,
|
|
struct vm_fault *vmf)
|
|
{
|
|
struct dma_region *dma = (struct dma_region *)vma->vm_private_data;
|
|
|
|
if (!dma->kvirt)
|
|
return VM_FAULT_SIGBUS;
|
|
|
|
if (vmf->pgoff >= dma->n_pages)
|
|
return VM_FAULT_SIGBUS;
|
|
|
|
vmf->page = vmalloc_to_page(dma->kvirt + (vmf->pgoff << PAGE_SHIFT));
|
|
get_page(vmf->page);
|
|
return 0;
|
|
}
|
|
|
|
static const struct vm_operations_struct dma_region_vm_ops = {
|
|
.fault = dma_region_pagefault,
|
|
};
|
|
|
|
/**
|
|
* dma_region_mmap - map the buffer into a user space process
|
|
*/
|
|
int dma_region_mmap(struct dma_region *dma, struct file *file,
|
|
struct vm_area_struct *vma)
|
|
{
|
|
unsigned long size;
|
|
|
|
if (!dma->kvirt)
|
|
return -EINVAL;
|
|
|
|
/* must be page-aligned (XXX: comment is wrong, we could allow pgoff) */
|
|
if (vma->vm_pgoff != 0)
|
|
return -EINVAL;
|
|
|
|
/* check the length */
|
|
size = vma->vm_end - vma->vm_start;
|
|
if (size > (dma->n_pages << PAGE_SHIFT))
|
|
return -EINVAL;
|
|
|
|
vma->vm_ops = &dma_region_vm_ops;
|
|
vma->vm_private_data = dma;
|
|
vma->vm_file = file;
|
|
vma->vm_flags |= VM_RESERVED | VM_ALWAYSDUMP;
|
|
|
|
return 0;
|
|
}
|
|
|
|
#else /* CONFIG_MMU */
|
|
|
|
int dma_region_mmap(struct dma_region *dma, struct file *file,
|
|
struct vm_area_struct *vma)
|
|
{
|
|
return -EINVAL;
|
|
}
|
|
|
|
#endif /* CONFIG_MMU */
|