summaryrefslogtreecommitdiffstats
path: root/include
diff options
context:
space:
mode:
authorBenjamin Herrenschmidt <benh@kernel.crashing.org>2007-05-27 15:18:22 +1000
committerPaul Mackerras <paulus@samba.org>2007-06-02 21:01:55 +1000
commit6ad8d010b2f364b739020e514e61b6a73444464b (patch)
treebb6b10d3c1b2db68a8bca66a587fa2db0a8f2fd9 /include
parent988519acb3dbe7168276a36cbb8fd91fddbffaee (diff)
[POWERPC] Fix possible access to free pages
I think we have a subtle race on ppc64 with the tlb batching. The common code expects tlb_flush() to actually flush any pending TLB batch. It does that because it delays all page freeing until after tlb_flush() is called, in order to ensure no stale reference to those pages exist in any TLB, thus causing potential access to the freed pages. However, our tlb_flush only triggers the RCU for freeing page table pages, it does not currently trigger a flush of a pending TLB/hash batch, which is, I think, an error. This fixes it. Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
Diffstat (limited to 'include')
-rw-r--r--include/asm-powerpc/tlb.h9
1 files changed, 9 insertions, 0 deletions
diff --git a/include/asm-powerpc/tlb.h b/include/asm-powerpc/tlb.h
index 0a17682663d..66714042e43 100644
--- a/include/asm-powerpc/tlb.h
+++ b/include/asm-powerpc/tlb.h
@@ -38,6 +38,15 @@ extern void pte_free_finish(void);
static inline void tlb_flush(struct mmu_gather *tlb)
{
+ struct ppc64_tlb_batch *tlbbatch = &__get_cpu_var(ppc64_tlb_batch);
+
+ /* If there's a TLB batch pending, then we must flush it because the
+ * pages are going to be freed and we really don't want to have a CPU
+ * access a freed page because it has a stale TLB
+ */
+ if (tlbbatch->index)
+ __flush_tlb_pending(tlbbatch);
+
pte_free_finish();
}