Home Home > GIT Browse > openSUSE-15.0
summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJiri Kosina <jkosina@suse.cz>2018-10-01 15:13:39 +0200
committerJiri Kosina <jkosina@suse.cz>2018-10-01 15:13:39 +0200
commit4733e02b73f5d857e0c60914ec7d642d1a3c1063 (patch)
tree9845af282a215a5d0acb0fbad520c56f50b3ac01
parent1f1a4711e6b141c79112b7a5b720fd6c9ee27cf3 (diff)
parent736bcf93f8ac26f2646938a92f95f69807f5a70d (diff)
Merge remote-tracking branch 'origin/users/mhocko/SLE11-SP4/for-next' into SLE11-SP4rpm-3.0.101-108.77
-rw-r--r--patches.suse/mm-vmacache-optimize-overflow-system-wide-flushing.patch42
-rw-r--r--series.conf1
2 files changed, 0 insertions, 43 deletions
diff --git a/patches.suse/mm-vmacache-optimize-overflow-system-wide-flushing.patch b/patches.suse/mm-vmacache-optimize-overflow-system-wide-flushing.patch
deleted file mode 100644
index 59339b3ba1..0000000000
--- a/patches.suse/mm-vmacache-optimize-overflow-system-wide-flushing.patch
+++ /dev/null
@@ -1,42 +0,0 @@
-From 6b4ebc3a9078c5b7b8c4cf495a0b1d2d0e0bfe7a Mon Sep 17 00:00:00 2001
-From: Davidlohr Bueso <davidlohr@hp.com>
-Date: Wed, 4 Jun 2014 16:06:47 -0700
-Subject: [PATCH] mm,vmacache: optimize overflow system-wide flushing
-Git-commit: 6b4ebc3a9078c5b7b8c4cf495a0b1d2d0e0bfe7a
-Patch-mainline: 3.16
-References: VM Performance
-
-For single threaded workloads, we can avoid flushing and iterating through
-the entire list of tasks, making the whole function a lot faster,
-requiring only a single atomic read for the mm_users.
-
-Signed-off-by: Davidlohr Bueso <davidlohr@hp.com>
-Suggested-by: Oleg Nesterov <oleg@redhat.com>
-Cc: Aswin Chandramouleeswaran <aswin@hp.com>
-Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
-Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
-
----
- mm/vmacache.c | 10 ++++++++++
- 1 file changed, 10 insertions(+)
-
---- a/mm/vmacache.c
-+++ b/mm/vmacache.c
-@@ -17,6 +17,16 @@ void vmacache_flush_all(struct mm_struct
- {
- struct task_struct *g, *p;
-
-+ /*
-+ * Single threaded tasks need not iterate the entire
-+ * list of process. We can avoid the flushing as well
-+ * since the mm's seqnum was increased and don't have
-+ * to worry about other threads' seqnum. Current's
-+ * flush will occur upon the next lookup.
-+ */
-+ if (atomic_read(&mm->mm_users) == 1)
-+ return;
-+
- read_lock(&tasklist_lock);
-
- do_each_thread(g, p) {
diff --git a/series.conf b/series.conf
index f3aae987ef..a74953f9d0 100644
--- a/series.conf
+++ b/series.conf
@@ -2352,7 +2352,6 @@
patches.suse/0001-mm-per-thread-vma-caching.patch
patches.suse/enable-mm-per-thread-vma-caching.patch
- patches.suse/mm-vmacache-optimize-overflow-system-wide-flushing.patch
patches.fixes/autofs-fix-lockref-lookup.patch