[PATCH] mm: flush_tlb_range outside ptlock

There was one small but very significant change in the previous patch:
mprotect's flush_tlb_range fell outside the page_table_lock: as it is in 2.4,
but that doesn't prove it safe in 2.6.

On some architectures flush_tlb_range comes to the same as flush_tlb_mm, which
has always been called from outside page_table_lock in dup_mmap, and is so
proved safe.  Others required a deeper audit: I could find no reliance on
page_table_lock in any; but in ia64 and parisc found some code which looks a
bit as if it might want preemption disabled.  That won't do any actual harm,
so pending a decision from the maintainers, disable preemption there.

Remove comments on page_table_lock from flush_tlb_mm, flush_tlb_range and
flush_tlb_page entries in cachetlb.txt: they were rather misleading (what
generic code does is different from what usually happens), the rules are now
changing, and it's not yet clear where we'll end up (will the generic
tlb_flush_mmu happen always under lock?  never under lock?  or sometimes under
and sometimes not?).

Signed-off-by: Hugh Dickins <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

Documentation/cachetlb.txt

@@ -49,9 +49,6 @@ changes occur:
 	page table operations such as what happens during
 	fork, and exec.
 
-	Platform developers note that generic code will always
-	invoke this interface without mm->page_table_lock held.
-
 3) void flush_tlb_range(struct vm_area_struct *vma,
 			unsigned long start, unsigned long end)
 
@@ -72,9 +69,6 @@ changes occur:
 	call flush_tlb_page (see below) for each entry which may be
 	modified.
 
-	Platform developers note that generic code will always
-	invoke this interface with mm->page_table_lock held.
-
 4) void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
 
 	This time we need to remove the PAGE_SIZE sized translation
@@ -93,9 +87,6 @@ changes occur:
 
 	This is used primarily during fault processing.
 
-	Platform developers note that generic code will always
-	invoke this interface with mm->page_table_lock held.
-
 5) void flush_tlb_pgtables(struct mm_struct *mm,
 			   unsigned long start, unsigned long end)
 

arch/ia64/mm/tlb.c

@@ -158,10 +158,12 @@ flush_tlb_range (struct vm_area_struct *vma, unsigned long start, unsigned long
 # ifdef CONFIG_SMP
 	platform_global_tlb_purge(mm, start, end, nbits);
 # else
+	preempt_disable();
 	do {
 		ia64_ptcl(start, (nbits<<2));
 		start += (1UL << nbits);
 	} while (start < end);
+	preempt_enable();
 # endif
 
 	ia64_srlz_i();			/* srlz.i implies srlz.d */

include/asm-parisc/tlbflush.h

@@ -88,7 +88,7 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
 	if (npages >= 512)  /* 2MB of space: arbitrary, should be tuned */
 		flush_tlb_all();
 	else {
-
+		preempt_disable();
 		mtsp(vma->vm_mm->context,1);
 		purge_tlb_start();
 		if (split_tlb) {
@@ -102,6 +102,7 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
 				pdtlb(start);
 				start += PAGE_SIZE;
 			}
+		preempt_enable();
 		}
 		purge_tlb_end();
 	}