lk/linux-kernel-test
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[PATCH] mm: arches skip ptlock

Browse Source 
Convert those few architectures which are calling pud_alloc, pmd_alloc,
pte_alloc_map on a user mm, not to take the page_table_lock first, nor drop it
after.  Each of these can continue to use pte_alloc_map, no need to change
over to pte_alloc_map_lock, they're neither racy nor swappable.

In the sparc64 io_remap_pfn_range, flush_tlb_range then falls outside of the
page_table_lock: that's okay, on sparc64 it's like flush_tlb_mm, and that has
always been called from outside of page_table_lock in dup_mmap.

Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This commit is contained in:
Hugh Dickins
2005-10-29 18:16:24 -07:00
committed by Linus Torvalds
parent c74df32c72
commit b462705ac6
5 changed files with 3 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
arch/sparc64/mm/generic.c
View File

@ -135,9 +135,8 @@ int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
dir = pgd_offset(mm, from);
flush_cache_range(vma, beg, end);
spin_lock(&mm->page_table_lock);
while (from < end) {
pud_t *pud = pud_alloc(current->mm, dir, from);
pud_t *pud = pud_alloc(mm, dir, from);
error = -ENOMEM;
if (!pud)
break;
@ -147,8 +146,7 @@ int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
from = (from + PGDIR_SIZE) & PGDIR_MASK;
dir++;
}
flush_tlb_range(vma, beg, end);
spin_unlock(&mm->page_table_lock);
flush_tlb_range(vma, beg, end);
return error;
}