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>
208 lines
4.8 KiB
C
208 lines
4.8 KiB
C
/*
|
|
* IA-64 Huge TLB Page Support for Kernel.
|
|
*
|
|
* Copyright (C) 2002-2004 Rohit Seth <rohit.seth@intel.com>
|
|
* Copyright (C) 2003-2004 Ken Chen <kenneth.w.chen@intel.com>
|
|
*
|
|
* Sep, 2003: add numa support
|
|
* Feb, 2004: dynamic hugetlb page size via boot parameter
|
|
*/
|
|
|
|
#include <linux/init.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/hugetlb.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/module.h>
|
|
#include <linux/sysctl.h>
|
|
#include <linux/log2.h>
|
|
#include <asm/mman.h>
|
|
#include <asm/pgalloc.h>
|
|
#include <asm/tlb.h>
|
|
#include <asm/tlbflush.h>
|
|
|
|
unsigned int hpage_shift = HPAGE_SHIFT_DEFAULT;
|
|
EXPORT_SYMBOL(hpage_shift);
|
|
|
|
pte_t *
|
|
huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz)
|
|
{
|
|
unsigned long taddr = htlbpage_to_page(addr);
|
|
pgd_t *pgd;
|
|
pud_t *pud;
|
|
pmd_t *pmd;
|
|
pte_t *pte = NULL;
|
|
|
|
pgd = pgd_offset(mm, taddr);
|
|
pud = pud_alloc(mm, pgd, taddr);
|
|
if (pud) {
|
|
pmd = pmd_alloc(mm, pud, taddr);
|
|
if (pmd)
|
|
pte = pte_alloc_map(mm, pmd, taddr);
|
|
}
|
|
return pte;
|
|
}
|
|
|
|
pte_t *
|
|
huge_pte_offset (struct mm_struct *mm, unsigned long addr)
|
|
{
|
|
unsigned long taddr = htlbpage_to_page(addr);
|
|
pgd_t *pgd;
|
|
pud_t *pud;
|
|
pmd_t *pmd;
|
|
pte_t *pte = NULL;
|
|
|
|
pgd = pgd_offset(mm, taddr);
|
|
if (pgd_present(*pgd)) {
|
|
pud = pud_offset(pgd, taddr);
|
|
if (pud_present(*pud)) {
|
|
pmd = pmd_offset(pud, taddr);
|
|
if (pmd_present(*pmd))
|
|
pte = pte_offset_map(pmd, taddr);
|
|
}
|
|
}
|
|
|
|
return pte;
|
|
}
|
|
|
|
int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
#define mk_pte_huge(entry) { pte_val(entry) |= _PAGE_P; }
|
|
|
|
/*
|
|
* Don't actually need to do any preparation, but need to make sure
|
|
* the address is in the right region.
|
|
*/
|
|
int prepare_hugepage_range(struct file *file,
|
|
unsigned long addr, unsigned long len)
|
|
{
|
|
if (len & ~HPAGE_MASK)
|
|
return -EINVAL;
|
|
if (addr & ~HPAGE_MASK)
|
|
return -EINVAL;
|
|
if (REGION_NUMBER(addr) != RGN_HPAGE)
|
|
return -EINVAL;
|
|
|
|
return 0;
|
|
}
|
|
|
|
struct page *follow_huge_addr(struct mm_struct *mm, unsigned long addr, int write)
|
|
{
|
|
struct page *page;
|
|
pte_t *ptep;
|
|
|
|
if (REGION_NUMBER(addr) != RGN_HPAGE)
|
|
return ERR_PTR(-EINVAL);
|
|
|
|
ptep = huge_pte_offset(mm, addr);
|
|
if (!ptep || pte_none(*ptep))
|
|
return NULL;
|
|
page = pte_page(*ptep);
|
|
page += ((addr & ~HPAGE_MASK) >> PAGE_SHIFT);
|
|
return page;
|
|
}
|
|
int pmd_huge(pmd_t pmd)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
int pud_huge(pud_t pud)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
struct page *
|
|
follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
void hugetlb_free_pgd_range(struct mmu_gather *tlb,
|
|
unsigned long addr, unsigned long end,
|
|
unsigned long floor, unsigned long ceiling)
|
|
{
|
|
/*
|
|
* This is called to free hugetlb page tables.
|
|
*
|
|
* The offset of these addresses from the base of the hugetlb
|
|
* region must be scaled down by HPAGE_SIZE/PAGE_SIZE so that
|
|
* the standard free_pgd_range will free the right page tables.
|
|
*
|
|
* If floor and ceiling are also in the hugetlb region, they
|
|
* must likewise be scaled down; but if outside, left unchanged.
|
|
*/
|
|
|
|
addr = htlbpage_to_page(addr);
|
|
end = htlbpage_to_page(end);
|
|
if (REGION_NUMBER(floor) == RGN_HPAGE)
|
|
floor = htlbpage_to_page(floor);
|
|
if (REGION_NUMBER(ceiling) == RGN_HPAGE)
|
|
ceiling = htlbpage_to_page(ceiling);
|
|
|
|
free_pgd_range(tlb, addr, end, floor, ceiling);
|
|
}
|
|
|
|
unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
|
|
unsigned long pgoff, unsigned long flags)
|
|
{
|
|
struct vm_area_struct *vmm;
|
|
|
|
if (len > RGN_MAP_LIMIT)
|
|
return -ENOMEM;
|
|
if (len & ~HPAGE_MASK)
|
|
return -EINVAL;
|
|
|
|
/* Handle MAP_FIXED */
|
|
if (flags & MAP_FIXED) {
|
|
if (prepare_hugepage_range(file, addr, len))
|
|
return -EINVAL;
|
|
return addr;
|
|
}
|
|
|
|
/* This code assumes that RGN_HPAGE != 0. */
|
|
if ((REGION_NUMBER(addr) != RGN_HPAGE) || (addr & (HPAGE_SIZE - 1)))
|
|
addr = HPAGE_REGION_BASE;
|
|
else
|
|
addr = ALIGN(addr, HPAGE_SIZE);
|
|
for (vmm = find_vma(current->mm, addr); ; vmm = vmm->vm_next) {
|
|
/* At this point: (!vmm || addr < vmm->vm_end). */
|
|
if (REGION_OFFSET(addr) + len > RGN_MAP_LIMIT)
|
|
return -ENOMEM;
|
|
if (!vmm || (addr + len) <= vmm->vm_start)
|
|
return addr;
|
|
addr = ALIGN(vmm->vm_end, HPAGE_SIZE);
|
|
}
|
|
}
|
|
|
|
static int __init hugetlb_setup_sz(char *str)
|
|
{
|
|
u64 tr_pages;
|
|
unsigned long long size;
|
|
|
|
if (ia64_pal_vm_page_size(&tr_pages, NULL) != 0)
|
|
/*
|
|
* shouldn't happen, but just in case.
|
|
*/
|
|
tr_pages = 0x15557000UL;
|
|
|
|
size = memparse(str, &str);
|
|
if (*str || !is_power_of_2(size) || !(tr_pages & size) ||
|
|
size <= PAGE_SIZE ||
|
|
size >= (1UL << PAGE_SHIFT << MAX_ORDER)) {
|
|
printk(KERN_WARNING "Invalid huge page size specified\n");
|
|
return 1;
|
|
}
|
|
|
|
hpage_shift = __ffs(size);
|
|
/*
|
|
* boot cpu already executed ia64_mmu_init, and has HPAGE_SHIFT_DEFAULT
|
|
* override here with new page shift.
|
|
*/
|
|
ia64_set_rr(HPAGE_REGION_BASE, hpage_shift << 2);
|
|
return 0;
|
|
}
|
|
early_param("hugepagesz", hugetlb_setup_sz);
|