mm: memcontrol: change val type to long in __mod_memcg_{lruvec_}state()

The __mod_memcg_state() and __mod_memcg_lruvec_state() functions are also
used to reparent non-hierarchical stats.  In this scenario, the values
passed to them are accumulated statistics that might be extremely large
and exceed the upper limit of a 32-bit integer.

Change the val parameter type from int to long in these functions and
their corresponding tracepoints (memcg_rstat_stats) to prevent potential
overflow issues.

After that, in memcg_state_val_in_pages(), if the passed val is negative,
the expression val * unit / PAGE_SIZE could be implicitly converted to a
massive positive number when compared with 1UL in the max() macro.  This
leads to returning an incorrect massive positive value.

Fix this by using abs(val) to calculate the magnitude first, and then
restoring the sign of the value before returning the result.
Additionally, use mult_frac() to prevent potential overflow during the
multiplication of val and unit.

Link: https://lore.kernel.org/70a9440e49c464b4dca88bcabc6b491bd335c9f0.1774604356.git.zhengqi.arch@bytedance.com
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Reported-by: Harry Yoo (Oracle) <harry@kernel.org>
Reviewed-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Reviewed-by: Harry Yoo (Oracle) <harry@kernel.org>
Cc: Allen Pais <apais@linux.microsoft.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: David Hildenbrand <david@kernel.org>
Cc: Hamza Mahfooz <hamzamahfooz@linux.microsoft.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Imran Khan <imran.f.khan@oracle.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kamalesh Babulal <kamalesh.babulal@oracle.com>
Cc: Lance Yang <lance.yang@linux.dev>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Michal Koutný <mkoutny@suse.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Usama Arif <usamaarif642@gmail.com>
Cc: Wei Xu <weixugc@google.com>
Cc: Yuanchu Xie <yuanchu@google.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/trace/events/memcg.h b/include/trace/events/memcg.h
index dfe2f51019b4c126064759d68c23108644b52ba8..51b62c5931fc24282ce131d3b4a7d59f78f4715a 100644 (file)
--- a/include/trace/events/memcg.h
+++ b/include/trace/events/memcg.h
@@ -11,14 +11,14 @@
 
 DECLARE_EVENT_CLASS(memcg_rstat_stats,
 
-       TP_PROTO(struct mem_cgroup *memcg, int item, int val),
+       TP_PROTO(struct mem_cgroup *memcg, int item, long val),
 
        TP_ARGS(memcg, item, val),
 
        TP_STRUCT__entry(
                __field(u64, id)
                __field(int, item)
-               __field(int, val)
+               __field(long, val)
        ),
 
        TP_fast_assign(
@@ -27,20 +27,20 @@ DECLARE_EVENT_CLASS(memcg_rstat_stats,
                __entry->val = val;
        ),
 
-       TP_printk("memcg_id=%llu item=%d val=%d",
+       TP_printk("memcg_id=%llu item=%d val=%ld",
                  __entry->id, __entry->item, __entry->val)
 );
 
 DEFINE_EVENT(memcg_rstat_stats, mod_memcg_state,
 
-       TP_PROTO(struct mem_cgroup *memcg, int item, int val),
+       TP_PROTO(struct mem_cgroup *memcg, int item, long val),
 
        TP_ARGS(memcg, item, val)
 );
 
 DEFINE_EVENT(memcg_rstat_stats, mod_memcg_lruvec_state,
 
-       TP_PROTO(struct mem_cgroup *memcg, int item, int val),
+       TP_PROTO(struct mem_cgroup *memcg, int item, long val),
 
        TP_ARGS(memcg, item, val)
 );

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 4ee668c20fa68a6787c31895a2e853fb4e667bc9..685e6dd48ce575132f55a1214ad89de6c69ffcd3 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -527,7 +527,7 @@ unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 
 #ifdef CONFIG_MEMCG_V1
 static void __mod_memcg_lruvec_state(struct mem_cgroup_per_node *pn,
-                                    enum node_stat_item idx, int val);
+                                    enum node_stat_item idx, long val);
 
 void reparent_memcg_lruvec_state_local(struct mem_cgroup *memcg,
                                       struct mem_cgroup *parent, int idx)
@@ -784,14 +784,20 @@ static int memcg_page_state_unit(int item);
  * Normalize the value passed into memcg_rstat_updated() to be in pages. Round
  * up non-zero sub-page updates to 1 page as zero page updates are ignored.
  */
-static int memcg_state_val_in_pages(int idx, int val)
+static long memcg_state_val_in_pages(int idx, long val)
 {
        int unit = memcg_page_state_unit(idx);
+       long res;
 
        if (!val || unit == PAGE_SIZE)
                return val;
-       else
-               return max(val * unit / PAGE_SIZE, 1UL);
+
+       /* Get the absolute value of (val * unit / PAGE_SIZE). */
+       res = mult_frac(abs(val), unit, PAGE_SIZE);
+       /* Round up zero values. */
+       res = res ? : 1;
+
+       return val < 0 ? -res : res;
 }
 
 #ifdef CONFIG_MEMCG_V1
@@ -831,7 +837,7 @@ static inline void get_non_dying_memcg_end(void)
 #endif
 
 static void __mod_memcg_state(struct mem_cgroup *memcg,
-                             enum memcg_stat_item idx, int val)
+                             enum memcg_stat_item idx, long val)
 {
        int i = memcg_stats_index(idx);
        int cpu;
@@ -896,7 +902,7 @@ void reparent_memcg_state_local(struct mem_cgroup *memcg,
 #endif
 
 static void __mod_memcg_lruvec_state(struct mem_cgroup_per_node *pn,
-                                    enum node_stat_item idx, int val)
+                                    enum node_stat_item idx, long val)
 {
        struct mem_cgroup *memcg = pn->memcg;
        int i = memcg_stats_index(idx);