zram: introduce an aged idle interface

This change introduces an aged idle interface to the existing idle sysfs
file for zram.

When CONFIG_ZRAM_MEMORY_TRACKING is enabled the idle file now also
accepts an integer argument.  This integer is the age (in seconds) of
pages to mark as idle.  The idle file still supports 'all' as it always
has.  This new approach allows for much more control over which pages
get marked as idle.

[bgeffon@google.com: use IS_ENABLED and cleanup comment]
Link: https://lkml.kernel.org/r/20210924161128.1508015-1-bgeffon@google.com
[bgeffon@google.com: Sergey's cleanup suggestions]
Link: https://lkml.kernel.org/r/20210929143056.13067-1-bgeffon@google.com
Link: https://lkml.kernel.org/r/20210923130115.1344361-1-bgeffon@google.com
Signed-off-by: Brian Geffon <bgeffon@google.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: Jesse Barnes <jsbarnes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/Documentation/admin-guide/blockdev/zram.rst b/Documentation/admin-guide/blockdev/zram.rst
index 700329d25f5799dbd69c7724bac55b0f290804d8..3e11926a4df95dc08eeb319329d7db8568743da5 100644 (file)
--- a/Documentation/admin-guide/blockdev/zram.rst
+++ b/Documentation/admin-guide/blockdev/zram.rst
@@ -328,6 +328,14 @@ as idle::
 From now on, any pages on zram are idle pages. The idle mark
 will be removed until someone requests access of the block.
 IOW, unless there is access request, those pages are still idle pages.
+Additionally, when CONFIG_ZRAM_MEMORY_TRACKING is enabled pages can be
+marked as idle based on how long (in seconds) it's been since they were
+last accessed::
+
+        echo 86400 > /sys/block/zramX/idle
+
+In this example all pages which haven't been accessed in more than 86400
+seconds (one day) will be marked idle.
 
 Admin can request writeback of those idle pages at right timing via::
 

diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index f61910c65f0f574a37c1c0d04c9afcb88cddcb00..0a9309a2ef54702896bb6d88c456e8af3d57ecd9 100644 (file)
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -291,22 +291,16 @@ static ssize_t mem_used_max_store(struct device *dev,
        return len;
 }
 
-static ssize_t idle_store(struct device *dev,
-               struct device_attribute *attr, const char *buf, size_t len)
+/*
+ * Mark all pages which are older than or equal to cutoff as IDLE.
+ * Callers should hold the zram init lock in read mode
+ */
+static void mark_idle(struct zram *zram, ktime_t cutoff)
 {
-       struct zram *zram = dev_to_zram(dev);
+       int is_idle = 1;
        unsigned long nr_pages = zram->disksize >> PAGE_SHIFT;
        int index;
 
-       if (!sysfs_streq(buf, "all"))
-               return -EINVAL;
-
-       down_read(&zram->init_lock);
-       if (!init_done(zram)) {
-               up_read(&zram->init_lock);
-               return -EINVAL;
-       }
-
        for (index = 0; index < nr_pages; index++) {
                /*
                 * Do not mark ZRAM_UNDER_WB slot as ZRAM_IDLE to close race.
@@ -314,14 +308,50 @@ static ssize_t idle_store(struct device *dev,
                 */
                zram_slot_lock(zram, index);
                if (zram_allocated(zram, index) &&
-                               !zram_test_flag(zram, index, ZRAM_UNDER_WB))
-                       zram_set_flag(zram, index, ZRAM_IDLE);
+                               !zram_test_flag(zram, index, ZRAM_UNDER_WB)) {
+#ifdef CONFIG_ZRAM_MEMORY_TRACKING
+                       is_idle = !cutoff || ktime_after(cutoff, zram->table[index].ac_time);
+#endif
+                       if (is_idle)
+                               zram_set_flag(zram, index, ZRAM_IDLE);
+               }
                zram_slot_unlock(zram, index);
        }
+}
 
-       up_read(&zram->init_lock);
+static ssize_t idle_store(struct device *dev,
+               struct device_attribute *attr, const char *buf, size_t len)
+{
+       struct zram *zram = dev_to_zram(dev);
+       ktime_t cutoff_time = 0;
+       ssize_t rv = -EINVAL;
 
-       return len;
+       if (!sysfs_streq(buf, "all")) {
+               /*
+                * If it did not parse as 'all' try to treat it as an integer when
+                * we have memory tracking enabled.
+                */
+               u64 age_sec;
+
+               if (IS_ENABLED(CONFIG_ZRAM_MEMORY_TRACKING) && !kstrtoull(buf, 0, &age_sec))
+                       cutoff_time = ktime_sub(ktime_get_boottime(),
+                                       ns_to_ktime(age_sec * NSEC_PER_SEC));
+               else
+                       goto out;
+       }
+
+       down_read(&zram->init_lock);
+       if (!init_done(zram))
+               goto out_unlock;
+
+       /* A cutoff_time of 0 marks everything as idle, this is the "all" behavior */
+       mark_idle(zram, cutoff_time);
+       rv = len;
+
+out_unlock:
+       up_read(&zram->init_lock);
+out:
+       return rv;
 }
 
 #ifdef CONFIG_ZRAM_WRITEBACK