mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-30 07:36:44 +07:00
5a0e3ad6af
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>
184 lines
4.5 KiB
C
184 lines
4.5 KiB
C
/* dma-alloc.c: consistent DMA memory allocation
|
|
*
|
|
* Derived from arch/ppc/mm/cachemap.c
|
|
*
|
|
* PowerPC version derived from arch/arm/mm/consistent.c
|
|
* Copyright (C) 2001 Dan Malek (dmalek@jlc.net)
|
|
*
|
|
* linux/arch/arm/mm/consistent.c
|
|
*
|
|
* 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
|
|
* Modified for 36-bit support. -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/module.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/pci.h>
|
|
#include <linux/hardirq.h>
|
|
#include <linux/gfp.h>
|
|
|
|
#include <asm/pgalloc.h>
|
|
#include <asm/io.h>
|
|
#include <asm/mmu_context.h>
|
|
#include <asm/pgtable.h>
|
|
#include <asm/mmu.h>
|
|
#include <asm/uaccess.h>
|
|
#include <asm/smp.h>
|
|
|
|
static int map_page(unsigned long va, unsigned long pa, pgprot_t prot)
|
|
{
|
|
pgd_t *pge;
|
|
pud_t *pue;
|
|
pmd_t *pme;
|
|
pte_t *pte;
|
|
int err = -ENOMEM;
|
|
|
|
/* Use upper 10 bits of VA to index the first level map */
|
|
pge = pgd_offset_k(va);
|
|
pue = pud_offset(pge, va);
|
|
pme = pmd_offset(pue, va);
|
|
|
|
/* Use middle 10 bits of VA to index the second-level map */
|
|
pte = pte_alloc_kernel(pme, va);
|
|
if (pte != 0) {
|
|
err = 0;
|
|
set_pte(pte, mk_pte_phys(pa & PAGE_MASK, prot));
|
|
}
|
|
|
|
return err;
|
|
}
|
|
|
|
/*
|
|
* This function will allocate the requested contiguous pages and
|
|
* map them into the kernel's vmalloc() space. This is done so we
|
|
* get unique mapping for these pages, outside of the kernel's 1:1
|
|
* virtual:physical mapping. This is necessary so we can cover large
|
|
* portions of the kernel with single large page TLB entries, and
|
|
* still get unique uncached pages for consistent DMA.
|
|
*/
|
|
void *consistent_alloc(gfp_t gfp, size_t size, dma_addr_t *dma_handle)
|
|
{
|
|
struct vm_struct *area;
|
|
unsigned long page, va, pa;
|
|
void *ret;
|
|
int order, err, i;
|
|
|
|
if (in_interrupt())
|
|
BUG();
|
|
|
|
/* only allocate page size areas */
|
|
size = PAGE_ALIGN(size);
|
|
order = get_order(size);
|
|
|
|
page = __get_free_pages(gfp, order);
|
|
if (!page) {
|
|
BUG();
|
|
return NULL;
|
|
}
|
|
|
|
/* allocate some common virtual space to map the new pages */
|
|
area = get_vm_area(size, VM_ALLOC);
|
|
if (area == 0) {
|
|
free_pages(page, order);
|
|
return NULL;
|
|
}
|
|
va = VMALLOC_VMADDR(area->addr);
|
|
ret = (void *) va;
|
|
|
|
/* this gives us the real physical address of the first page */
|
|
*dma_handle = pa = virt_to_bus((void *) page);
|
|
|
|
/* set refcount=1 on all pages in an order>0 allocation so that vfree() will actually free
|
|
* all pages that were allocated.
|
|
*/
|
|
if (order > 0) {
|
|
struct page *rpage = virt_to_page(page);
|
|
split_page(rpage, order);
|
|
}
|
|
|
|
err = 0;
|
|
for (i = 0; i < size && err == 0; i += PAGE_SIZE)
|
|
err = map_page(va + i, pa + i, PAGE_KERNEL_NOCACHE);
|
|
|
|
if (err) {
|
|
vfree((void *) va);
|
|
return NULL;
|
|
}
|
|
|
|
/* we need to ensure that there are no cachelines in use, or worse dirty in this area
|
|
* - can't do until after virtual address mappings are created
|
|
*/
|
|
frv_cache_invalidate(va, va + size);
|
|
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* free page(s) as defined by the above mapping.
|
|
*/
|
|
void consistent_free(void *vaddr)
|
|
{
|
|
if (in_interrupt())
|
|
BUG();
|
|
vfree(vaddr);
|
|
}
|
|
|
|
/*
|
|
* make an area consistent.
|
|
*/
|
|
void consistent_sync(void *vaddr, size_t size, int direction)
|
|
{
|
|
unsigned long start = (unsigned long) vaddr;
|
|
unsigned long end = start + size;
|
|
|
|
switch (direction) {
|
|
case PCI_DMA_NONE:
|
|
BUG();
|
|
case PCI_DMA_FROMDEVICE: /* invalidate only */
|
|
frv_cache_invalidate(start, end);
|
|
break;
|
|
case PCI_DMA_TODEVICE: /* writeback only */
|
|
frv_dcache_writeback(start, end);
|
|
break;
|
|
case PCI_DMA_BIDIRECTIONAL: /* writeback and invalidate */
|
|
frv_dcache_writeback(start, end);
|
|
break;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* consistent_sync_page make a page are 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)
|
|
{
|
|
void *start;
|
|
|
|
start = page_address(page) + offset;
|
|
consistent_sync(start, size, direction);
|
|
}
|