mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-12 13:55:32 +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>
356 lines
8.3 KiB
C
356 lines
8.3 KiB
C
/*
|
|
* SPARC64 Huge TLB page support.
|
|
*
|
|
* Copyright (C) 2002, 2003, 2006 David S. Miller (davem@davemloft.net)
|
|
*/
|
|
|
|
#include <linux/init.h>
|
|
#include <linux/module.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/hugetlb.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/sysctl.h>
|
|
|
|
#include <asm/mman.h>
|
|
#include <asm/pgalloc.h>
|
|
#include <asm/tlb.h>
|
|
#include <asm/tlbflush.h>
|
|
#include <asm/cacheflush.h>
|
|
#include <asm/mmu_context.h>
|
|
|
|
/* Slightly simplified from the non-hugepage variant because by
|
|
* definition we don't have to worry about any page coloring stuff
|
|
*/
|
|
#define VA_EXCLUDE_START (0x0000080000000000UL - (1UL << 32UL))
|
|
#define VA_EXCLUDE_END (0xfffff80000000000UL + (1UL << 32UL))
|
|
|
|
static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *filp,
|
|
unsigned long addr,
|
|
unsigned long len,
|
|
unsigned long pgoff,
|
|
unsigned long flags)
|
|
{
|
|
struct mm_struct *mm = current->mm;
|
|
struct vm_area_struct * vma;
|
|
unsigned long task_size = TASK_SIZE;
|
|
unsigned long start_addr;
|
|
|
|
if (test_thread_flag(TIF_32BIT))
|
|
task_size = STACK_TOP32;
|
|
if (unlikely(len >= VA_EXCLUDE_START))
|
|
return -ENOMEM;
|
|
|
|
if (len > mm->cached_hole_size) {
|
|
start_addr = addr = mm->free_area_cache;
|
|
} else {
|
|
start_addr = addr = TASK_UNMAPPED_BASE;
|
|
mm->cached_hole_size = 0;
|
|
}
|
|
|
|
task_size -= len;
|
|
|
|
full_search:
|
|
addr = ALIGN(addr, HPAGE_SIZE);
|
|
|
|
for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
|
|
/* At this point: (!vma || addr < vma->vm_end). */
|
|
if (addr < VA_EXCLUDE_START &&
|
|
(addr + len) >= VA_EXCLUDE_START) {
|
|
addr = VA_EXCLUDE_END;
|
|
vma = find_vma(mm, VA_EXCLUDE_END);
|
|
}
|
|
if (unlikely(task_size < addr)) {
|
|
if (start_addr != TASK_UNMAPPED_BASE) {
|
|
start_addr = addr = TASK_UNMAPPED_BASE;
|
|
mm->cached_hole_size = 0;
|
|
goto full_search;
|
|
}
|
|
return -ENOMEM;
|
|
}
|
|
if (likely(!vma || addr + len <= vma->vm_start)) {
|
|
/*
|
|
* Remember the place where we stopped the search:
|
|
*/
|
|
mm->free_area_cache = addr + len;
|
|
return addr;
|
|
}
|
|
if (addr + mm->cached_hole_size < vma->vm_start)
|
|
mm->cached_hole_size = vma->vm_start - addr;
|
|
|
|
addr = ALIGN(vma->vm_end, HPAGE_SIZE);
|
|
}
|
|
}
|
|
|
|
static unsigned long
|
|
hugetlb_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
|
|
const unsigned long len,
|
|
const unsigned long pgoff,
|
|
const unsigned long flags)
|
|
{
|
|
struct vm_area_struct *vma;
|
|
struct mm_struct *mm = current->mm;
|
|
unsigned long addr = addr0;
|
|
|
|
/* This should only ever run for 32-bit processes. */
|
|
BUG_ON(!test_thread_flag(TIF_32BIT));
|
|
|
|
/* check if free_area_cache is useful for us */
|
|
if (len <= mm->cached_hole_size) {
|
|
mm->cached_hole_size = 0;
|
|
mm->free_area_cache = mm->mmap_base;
|
|
}
|
|
|
|
/* either no address requested or can't fit in requested address hole */
|
|
addr = mm->free_area_cache & HPAGE_MASK;
|
|
|
|
/* make sure it can fit in the remaining address space */
|
|
if (likely(addr > len)) {
|
|
vma = find_vma(mm, addr-len);
|
|
if (!vma || addr <= vma->vm_start) {
|
|
/* remember the address as a hint for next time */
|
|
return (mm->free_area_cache = addr-len);
|
|
}
|
|
}
|
|
|
|
if (unlikely(mm->mmap_base < len))
|
|
goto bottomup;
|
|
|
|
addr = (mm->mmap_base-len) & HPAGE_MASK;
|
|
|
|
do {
|
|
/*
|
|
* Lookup failure means no vma is above this address,
|
|
* else if new region fits below vma->vm_start,
|
|
* return with success:
|
|
*/
|
|
vma = find_vma(mm, addr);
|
|
if (likely(!vma || addr+len <= vma->vm_start)) {
|
|
/* remember the address as a hint for next time */
|
|
return (mm->free_area_cache = addr);
|
|
}
|
|
|
|
/* remember the largest hole we saw so far */
|
|
if (addr + mm->cached_hole_size < vma->vm_start)
|
|
mm->cached_hole_size = vma->vm_start - addr;
|
|
|
|
/* try just below the current vma->vm_start */
|
|
addr = (vma->vm_start-len) & HPAGE_MASK;
|
|
} while (likely(len < vma->vm_start));
|
|
|
|
bottomup:
|
|
/*
|
|
* A failed mmap() very likely causes application failure,
|
|
* so fall back to the bottom-up function here. This scenario
|
|
* can happen with large stack limits and large mmap()
|
|
* allocations.
|
|
*/
|
|
mm->cached_hole_size = ~0UL;
|
|
mm->free_area_cache = TASK_UNMAPPED_BASE;
|
|
addr = arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
|
|
/*
|
|
* Restore the topdown base:
|
|
*/
|
|
mm->free_area_cache = mm->mmap_base;
|
|
mm->cached_hole_size = ~0UL;
|
|
|
|
return addr;
|
|
}
|
|
|
|
unsigned long
|
|
hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
|
|
unsigned long len, unsigned long pgoff, unsigned long flags)
|
|
{
|
|
struct mm_struct *mm = current->mm;
|
|
struct vm_area_struct *vma;
|
|
unsigned long task_size = TASK_SIZE;
|
|
|
|
if (test_thread_flag(TIF_32BIT))
|
|
task_size = STACK_TOP32;
|
|
|
|
if (len & ~HPAGE_MASK)
|
|
return -EINVAL;
|
|
if (len > task_size)
|
|
return -ENOMEM;
|
|
|
|
if (flags & MAP_FIXED) {
|
|
if (prepare_hugepage_range(file, addr, len))
|
|
return -EINVAL;
|
|
return addr;
|
|
}
|
|
|
|
if (addr) {
|
|
addr = ALIGN(addr, HPAGE_SIZE);
|
|
vma = find_vma(mm, addr);
|
|
if (task_size - len >= addr &&
|
|
(!vma || addr + len <= vma->vm_start))
|
|
return addr;
|
|
}
|
|
if (mm->get_unmapped_area == arch_get_unmapped_area)
|
|
return hugetlb_get_unmapped_area_bottomup(file, addr, len,
|
|
pgoff, flags);
|
|
else
|
|
return hugetlb_get_unmapped_area_topdown(file, addr, len,
|
|
pgoff, flags);
|
|
}
|
|
|
|
pte_t *huge_pte_alloc(struct mm_struct *mm,
|
|
unsigned long addr, unsigned long sz)
|
|
{
|
|
pgd_t *pgd;
|
|
pud_t *pud;
|
|
pmd_t *pmd;
|
|
pte_t *pte = NULL;
|
|
|
|
/* We must align the address, because our caller will run
|
|
* set_huge_pte_at() on whatever we return, which writes out
|
|
* all of the sub-ptes for the hugepage range. So we have
|
|
* to give it the first such sub-pte.
|
|
*/
|
|
addr &= HPAGE_MASK;
|
|
|
|
pgd = pgd_offset(mm, addr);
|
|
pud = pud_alloc(mm, pgd, addr);
|
|
if (pud) {
|
|
pmd = pmd_alloc(mm, pud, addr);
|
|
if (pmd)
|
|
pte = pte_alloc_map(mm, pmd, addr);
|
|
}
|
|
return pte;
|
|
}
|
|
|
|
pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
|
|
{
|
|
pgd_t *pgd;
|
|
pud_t *pud;
|
|
pmd_t *pmd;
|
|
pte_t *pte = NULL;
|
|
|
|
addr &= HPAGE_MASK;
|
|
|
|
pgd = pgd_offset(mm, addr);
|
|
if (!pgd_none(*pgd)) {
|
|
pud = pud_offset(pgd, addr);
|
|
if (!pud_none(*pud)) {
|
|
pmd = pmd_offset(pud, addr);
|
|
if (!pmd_none(*pmd))
|
|
pte = pte_offset_map(pmd, addr);
|
|
}
|
|
}
|
|
return pte;
|
|
}
|
|
|
|
int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
|
|
pte_t *ptep, pte_t entry)
|
|
{
|
|
int i;
|
|
|
|
if (!pte_present(*ptep) && pte_present(entry))
|
|
mm->context.huge_pte_count++;
|
|
|
|
addr &= HPAGE_MASK;
|
|
for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
|
|
set_pte_at(mm, addr, ptep, entry);
|
|
ptep++;
|
|
addr += PAGE_SIZE;
|
|
pte_val(entry) += PAGE_SIZE;
|
|
}
|
|
}
|
|
|
|
pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
|
|
pte_t *ptep)
|
|
{
|
|
pte_t entry;
|
|
int i;
|
|
|
|
entry = *ptep;
|
|
if (pte_present(entry))
|
|
mm->context.huge_pte_count--;
|
|
|
|
addr &= HPAGE_MASK;
|
|
|
|
for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
|
|
pte_clear(mm, addr, ptep);
|
|
addr += PAGE_SIZE;
|
|
ptep++;
|
|
}
|
|
|
|
return entry;
|
|
}
|
|
|
|
struct page *follow_huge_addr(struct mm_struct *mm,
|
|
unsigned long address, int write)
|
|
{
|
|
return ERR_PTR(-EINVAL);
|
|
}
|
|
|
|
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;
|
|
}
|
|
|
|
static void context_reload(void *__data)
|
|
{
|
|
struct mm_struct *mm = __data;
|
|
|
|
if (mm == current->mm)
|
|
load_secondary_context(mm);
|
|
}
|
|
|
|
void hugetlb_prefault_arch_hook(struct mm_struct *mm)
|
|
{
|
|
struct tsb_config *tp = &mm->context.tsb_block[MM_TSB_HUGE];
|
|
|
|
if (likely(tp->tsb != NULL))
|
|
return;
|
|
|
|
tsb_grow(mm, MM_TSB_HUGE, 0);
|
|
tsb_context_switch(mm);
|
|
smp_tsb_sync(mm);
|
|
|
|
/* On UltraSPARC-III+ and later, configure the second half of
|
|
* the Data-TLB for huge pages.
|
|
*/
|
|
if (tlb_type == cheetah_plus) {
|
|
unsigned long ctx;
|
|
|
|
spin_lock(&ctx_alloc_lock);
|
|
ctx = mm->context.sparc64_ctx_val;
|
|
ctx &= ~CTX_PGSZ_MASK;
|
|
ctx |= CTX_PGSZ_BASE << CTX_PGSZ0_SHIFT;
|
|
ctx |= CTX_PGSZ_HUGE << CTX_PGSZ1_SHIFT;
|
|
|
|
if (ctx != mm->context.sparc64_ctx_val) {
|
|
/* When changing the page size fields, we
|
|
* must perform a context flush so that no
|
|
* stale entries match. This flush must
|
|
* occur with the original context register
|
|
* settings.
|
|
*/
|
|
do_flush_tlb_mm(mm);
|
|
|
|
/* Reload the context register of all processors
|
|
* also executing in this address space.
|
|
*/
|
|
mm->context.sparc64_ctx_val = ctx;
|
|
on_each_cpu(context_reload, mm, 0);
|
|
}
|
|
spin_unlock(&ctx_alloc_lock);
|
|
}
|
|
}
|