mm, swap: add sysfs interface for VMA based swap readahead

The sysfs interface to control the VMA based swap readahead is added as
follow,

/sys/kernel/mm/swap/vma_ra_enabled

Enable the VMA based swap readahead algorithm, or use the original
global swap readahead algorithm.

/sys/kernel/mm/swap/vma_ra_max_order

Set the max order of the readahead window size for the VMA based swap
readahead algorithm.

The corresponding ABI documentation is added too.

Link: http://lkml.kernel.org/r/20170807054038.1843-5-ying.huang@intel.com
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Shaohua Li <shli@kernel.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Cc: Tim Chen <tim.c.chen@intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-swap b/Documentation/ABI/testing/sysfs-kernel-mm-swap
new file mode 100644 (file)
index 0000000..587db52
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-kernel-mm-swap
@@ -0,0 +1,26 @@
+What:          /sys/kernel/mm/swap/
+Date:          August 2017
+Contact:       Linux memory management mailing list <linux-mm@kvack.org>
+Description:   Interface for swapping
+
+What:          /sys/kernel/mm/swap/vma_ra_enabled
+Date:          August 2017
+Contact:       Linux memory management mailing list <linux-mm@kvack.org>
+Description:   Enable/disable VMA based swap readahead.
+
+               If set to true, the VMA based swap readahead algorithm
+               will be used for swappable anonymous pages mapped in a
+               VMA, and the global swap readahead algorithm will be
+               still used for tmpfs etc. other users.  If set to
+               false, the global swap readahead algorithm will be
+               used for all swappable pages.
+
+What:          /sys/kernel/mm/swap/vma_ra_max_order
+Date:          August 2017
+Contact:       Linux memory management mailing list <linux-mm@kvack.org>
+Description:   The max readahead size in order for VMA based swap readahead
+
+               VMA based swap readahead algorithm will readahead at
+               most 1 << max_order pages for each readahead.  The
+               real readahead size for each readahead will be scaled
+               according to the estimation algorithm.

diff --git a/mm/swap_state.c b/mm/swap_state.c
index 3885fef7bdf594453adc82f860e422e634850b6a..71ce2d1ccbf7357238306d5e900a8bee7944e1cb 100644 (file)
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -751,3 +751,83 @@ skip:
        return read_swap_cache_async(fentry, gfp_mask, vma, vmf->address,
                                     swap_ra->win == 1);
 }
+
+#ifdef CONFIG_SYSFS
+static ssize_t vma_ra_enabled_show(struct kobject *kobj,
+                                    struct kobj_attribute *attr, char *buf)
+{
+       return sprintf(buf, "%s\n", swap_vma_readahead ? "true" : "false");
+}
+static ssize_t vma_ra_enabled_store(struct kobject *kobj,
+                                     struct kobj_attribute *attr,
+                                     const char *buf, size_t count)
+{
+       if (!strncmp(buf, "true", 4) || !strncmp(buf, "1", 1))
+               swap_vma_readahead = true;
+       else if (!strncmp(buf, "false", 5) || !strncmp(buf, "0", 1))
+               swap_vma_readahead = false;
+       else
+               return -EINVAL;
+
+       return count;
+}
+static struct kobj_attribute vma_ra_enabled_attr =
+       __ATTR(vma_ra_enabled, 0644, vma_ra_enabled_show,
+              vma_ra_enabled_store);
+
+static ssize_t vma_ra_max_order_show(struct kobject *kobj,
+                                    struct kobj_attribute *attr, char *buf)
+{
+       return sprintf(buf, "%d\n", swap_ra_max_order);
+}
+static ssize_t vma_ra_max_order_store(struct kobject *kobj,
+                                     struct kobj_attribute *attr,
+                                     const char *buf, size_t count)
+{
+       int err, v;
+
+       err = kstrtoint(buf, 10, &v);
+       if (err || v > SWAP_RA_ORDER_CEILING || v <= 0)
+               return -EINVAL;
+
+       swap_ra_max_order = v;
+
+       return count;
+}
+static struct kobj_attribute vma_ra_max_order_attr =
+       __ATTR(vma_ra_max_order, 0644, vma_ra_max_order_show,
+              vma_ra_max_order_store);
+
+static struct attribute *swap_attrs[] = {
+       &vma_ra_enabled_attr.attr,
+       &vma_ra_max_order_attr.attr,
+       NULL,
+};
+
+static struct attribute_group swap_attr_group = {
+       .attrs = swap_attrs,
+};
+
+static int __init swap_init_sysfs(void)
+{
+       int err;
+       struct kobject *swap_kobj;
+
+       swap_kobj = kobject_create_and_add("swap", mm_kobj);
+       if (!swap_kobj) {
+               pr_err("failed to create swap kobject\n");
+               return -ENOMEM;
+       }
+       err = sysfs_create_group(swap_kobj, &swap_attr_group);
+       if (err) {
+               pr_err("failed to register swap group\n");
+               goto delete_obj;
+       }
+       return 0;
+
+delete_obj:
+       kobject_put(swap_kobj);
+       return err;
+}
+subsys_initcall(swap_init_sysfs);
+#endif