summaryrefslogtreecommitdiffstats
path: root/Documentation/vm
diff options
context:
space:
mode:
authorWu Fengguang <fengguang.wu@intel.com>2009-12-16 12:19:59 +0100
committerAndi Kleen <ak@linux.intel.com>2009-12-16 12:19:59 +0100
commit31d3d3484f9bd263925ecaa341500ac2df3a5d9b (patch)
tree38f331f27f3b4bc537303fc90490b88d53e43710 /Documentation/vm
parent7c116f2b0dbac4a1dd051c7a5e8cef37701cafd4 (diff)
downloadop-kernel-dev-31d3d3484f9bd263925ecaa341500ac2df3a5d9b.zip
op-kernel-dev-31d3d3484f9bd263925ecaa341500ac2df3a5d9b.tar.gz
HWPOISON: limit hwpoison injector to known page types
__memory_failure()'s workflow is set PG_hwpoison //... unset PG_hwpoison if didn't pass hwpoison filter That could kill unrelated process if it happens to page fault on the page with the (temporary) PG_hwpoison. The race should be big enough to appear in stress tests. Fix it by grabbing the page and checking filter at inject time. This also avoids the very noisy "Injecting memory failure..." messages. - we don't touch madvise() based injection, because the filters are generally not necessary for it. - if we want to apply the filters to h/w aided injection, we'd better to rearrange the logic in __memory_failure() instead of this patch. AK: fix documentation, use drain all, cleanups CC: Haicheng Li <haicheng.li@intel.com> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andi Kleen <ak@linux.intel.com>
Diffstat (limited to 'Documentation/vm')
-rw-r--r--Documentation/vm/hwpoison.txt3
1 files changed, 2 insertions, 1 deletions
diff --git a/Documentation/vm/hwpoison.txt b/Documentation/vm/hwpoison.txt
index fdf5804..4ef7bb3 100644
--- a/Documentation/vm/hwpoison.txt
+++ b/Documentation/vm/hwpoison.txt
@@ -103,7 +103,8 @@ hwpoison-inject module through debugfs
corrupt-pfn
-Inject hwpoison fault at PFN echoed into this file.
+Inject hwpoison fault at PFN echoed into this file. This does
+some early filtering to avoid corrupted unintended pages in test suites.
unpoison-pfn
OpenPOWER on IntegriCloud