From: Gregory Price gourry.memverge@gmail.com
mainline inclusion from mainline-v6.9-rc1 commit 274519ed414bd2b9a77c5db78ee51778d37ceacf category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9OHHN CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
--------------------------------
In the event of rebind, pol->nodemask can change at the same time as an allocation occurs. We can detect this with tsk->mems_allowed_seq and prevent a miscount or an allocation failure from occurring.
The same thing happens in the allocators to detect failure, but this can prevent spurious failures in a much smaller critical section.
[gourry.memverge@gmail.com: weighted interleave checks wrong parameter] Link: https://lkml.kernel.org/r/20240206192853.3589-1-gregory.price@memverge.com Link: https://lkml.kernel.org/r/20240202170238.90004-5-gregory.price@memverge.com Signed-off-by: Gregory Price gregory.price@memverge.com Suggested-by: "Huang, Ying" ying.huang@intel.com Cc: Dan Williams dan.j.williams@intel.com Cc: Hasan Al Maruf Hasan.Maruf@amd.com Cc: Honggyu Kim honggyu.kim@sk.com Cc: Hyeongtak Ji hyeongtak.ji@sk.com Cc: Johannes Weiner hannes@cmpxchg.org Cc: Jonathan Corbet corbet@lwn.net Cc: Michal Hocko mhocko@kernel.org Cc: Rakie Kim rakie.kim@sk.com Cc: Ravi Jonnalagadda ravis.opensrc@micron.com Cc: Srinivasulu Thanneeru sthanneeru.opensrc@micron.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Ze Zuo zuoze1@huawei.com --- mm/mempolicy.c | 27 +++++++++++++++++++++++---- 1 file changed, 23 insertions(+), 4 deletions(-)
diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 2f41cf1856a3..64ef9b7a06e7 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1904,11 +1904,17 @@ bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone)
static unsigned int weighted_interleave_nodes(struct mempolicy *policy) { - unsigned int node = current->il_prev; + unsigned int node; + unsigned int cpuset_mems_cookie;
+retry: + /* to prevent miscount use tsk->mems_allowed_seq to detect rebind */ + cpuset_mems_cookie = read_mems_allowed_begin(); + node = current->il_prev; if (!current->il_weight || !node_isset(node, policy->nodes)) { node = next_node_in(node, policy->nodes); - /* can only happen if nodemask is being rebound */ + if (read_mems_allowed_retry(cpuset_mems_cookie)) + goto retry; if (node == MAX_NUMNODES) return node; current->il_prev = node; @@ -1922,8 +1928,14 @@ static unsigned int weighted_interleave_nodes(struct mempolicy *policy) static unsigned int interleave_nodes(struct mempolicy *policy) { unsigned int nid; + unsigned int cpuset_mems_cookie; + + /* to prevent miscount, use tsk->mems_allowed_seq to detect rebind */ + do { + cpuset_mems_cookie = read_mems_allowed_begin(); + nid = next_node_in(current->il_prev, policy->nodes); + } while (read_mems_allowed_retry(cpuset_mems_cookie));
- nid = next_node_in(current->il_prev, policy->nodes); if (nid < MAX_NUMNODES) current->il_prev = nid; return nid; @@ -2406,6 +2418,7 @@ static unsigned long alloc_pages_bulk_array_weighted_interleave(gfp_t gfp, struct page **page_array) { struct task_struct *me = current; + unsigned int cpuset_mems_cookie; unsigned long total_allocated = 0; unsigned long nr_allocated = 0; unsigned long rounds; @@ -2423,7 +2436,13 @@ static unsigned long alloc_pages_bulk_array_weighted_interleave(gfp_t gfp, if (!nr_pages) return 0;
- nnodes = read_once_policy_nodemask(pol, &nodes); + /* read the nodes onto the stack, retry if done during rebind */ + do { + cpuset_mems_cookie = read_mems_allowed_begin(); + nnodes = read_once_policy_nodemask(pol, &nodes); + } while (read_mems_allowed_retry(cpuset_mems_cookie)); + + /* if the nodemask has become invalid, we cannot do anything */ if (!nnodes) return 0;