swap: add a limit for readahead page-cluster value

Currenty there is no upper limit for /proc/sys/vm/page-cluster, and it's a
bit shift value, so it could result in overflow of the 32-bit integer.
Add a reasonable upper limit for it, read-in at most 2**31 pages, which is
a large enough value for readahead.

Link: https://lkml.kernel.org/r/20221023162533.81561-1-ryncsn@gmail.com
Signed-off-by: Kairui Song <kasong@tencent.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 429ff89bfe06e06a175abcf33826646f0ad43eb1..255931ebf2dc468fa11d5171248a87d80239469a 100644 (file)
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -74,6 +74,7 @@ static inline void totalram_pages_add(long count)
 
 extern void * high_memory;
 extern int page_cluster;
+extern const int page_cluster_max;
 
 #ifdef CONFIG_SYSCTL
 extern int sysctl_legacy_va_layout;

diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 188c305aeb8b7fd8984721122dcfe11bd658aeaa..71a4350ac601b31a838a686c4f15346f4ffd77a3 100644 (file)
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2125,6 +2125,7 @@ static struct ctl_table vm_table[] = {
                .mode           = 0644,
                .proc_handler   = proc_dointvec_minmax,
                .extra1         = SYSCTL_ZERO,
+               .extra2         = (void *)&page_cluster_max,
        },
        {
                .procname       = "dirtytime_expire_seconds",

diff --git a/mm/swap.c b/mm/swap.c
index 2f12a2ee1d3af1f4735a2a658efca841c7031a0e..b9a6817e07ffeff9d54f4902ceccc0dd2d7657d2 100644 (file)
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -43,8 +43,9 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/pagemap.h>
 
-/* How many pages do we try to swap or page in/out together? */
+/* How many pages do we try to swap or page in/out together? As a power of 2 */
 int page_cluster;
+const int page_cluster_max = 31;
 
 /* Protecting only lru_rotate.fbatch which requires disabling interrupts */
 struct lru_rotate {