diff --git a/Documentation/blockdev/zram.txt b/Documentation/blockdev/zram.txt
index 78db38d02bc9a27a7ffd936ef857455960fe7459..875b2b56b87fc88131324bb10bbecc8594e02109 100644
--- a/Documentation/blockdev/zram.txt
+++ b/Documentation/blockdev/zram.txt
@@ -243,5 +243,29 @@ to backing storage rather than keeping it in memory.
User should set up backing device via /sys/block/zramX/backing_dev
before disksize setting.
+= memory tracking
+
+With CONFIG_ZRAM_MEMORY_TRACKING, user can know information of the
+zram block. It could be useful to catch cold or incompressible
+pages of the process with*pagemap.
+If you enable the feature, you could see block state via
+/sys/kernel/debug/zram/zram0/block_state". The output is as follows,
+
+ 300 75.033841 .wh
+ 301 63.806904 s..
+ 302 63.806919 ..h
+
+First column is zram's block index.
+Second column is access time since the system was booted
+Third column is state of the block.
+(s: same page
+w: written page to backing store
+h: huge page)
+
+First line of above example says 300th block is accessed at 75.033841sec
+and the block's state is huge so it is written back to the backing
+storage. It's a debugging feature so anyone shouldn't rely on it to work
+properly.
+
Nitin Gupta
ngupta@vflare.org
diff --git a/drivers/block/zram/Kconfig b/drivers/block/zram/Kconfig
index 7cd4a8ec3c8fa24b827a19004179f1231b8c2999..cb53957d58f9e40e64908cf7df39ed62caeee33c 100644
--- a/drivers/block/zram/Kconfig
+++ b/drivers/block/zram/Kconfig
@@ -12,7 +12,7 @@ config ZRAM
It has several use cases, for example: /tmp storage, use as swap
disks and maybe many more.
- See zram.txt for more information.
+ See Documentation/blockdev/zram.txt for more information.
config ZRAM_WRITEBACK
bool "Write back incompressible page to backing device"
@@ -24,4 +24,14 @@ config ZRAM_WRITEBACK
For this feature, admin should set up backing device via
/sys/block/zramX/backing_dev.
- See zram.txt for more infomration.
+ See Documentation/blockdev/zram.txt for more information.
+
+config ZRAM_MEMORY_TRACKING
+ bool "Track zRam block status"
+ depends on ZRAM && DEBUG_FS
+ help
+ With this feature, admin can track the state of allocated blocks
+ of zRAM. Admin could see the information via
+ /sys/kernel/debug/zram/zramX/block_state.
+
+ See Documentation/blockdev/zram.txt for more information.
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index de4fdb599a585e510d30d23693d4c0312517c973..5d8abb87eed24b6ed6395a2e63def0660199e7e3 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -31,6 +31,7 @@
#include <linux/err.h>
#include <linux/idr.h>
#include <linux/sysfs.h>
+#include <linux/debugfs.h>
#include "zram_drv.h"
@@ -61,6 +62,13 @@ static inline bool init_done(struct zram *zram)
return zram->disksize;
}
+static inline bool zram_allocated(struct zram *zram, u32 index)
+{
+
+ return (zram->table[index].value >> (ZRAM_FLAG_SHIFT + 1)) ||
+ zram->table[index].handle;
+}
+
static inline struct zram *dev_to_zram(struct device *dev)
{
return (struct zram *)dev_to_disk(dev)->private_data;
@@ -77,7 +85,7 @@ static void zram_set_handle(struct zram *zram, u32 index, unsigned long handle)
}
/* flag operations require table entry bit_spin_lock() being held */
-static int zram_test_flag(struct zram *zram, u32 index,
+static bool zram_test_flag(struct zram *zram, u32 index,
enum zram_pageflags flag)
{
return zram->table[index].value & BIT(flag);
@@ -101,16 +109,6 @@ static inline void zram_set_element(struct zram *zram, u32 index,
zram->table[index].element = element;
}
-static void zram_accessed(struct zram *zram, u32 index)
-{
- zram->table[index].ac_time = sched_clock();
-}
-
-static void zram_reset_access(struct zram *zram, u32 index)
-{
- zram->table[index].ac_time = 0;
-}
-
static unsigned long zram_get_element(struct zram *zram, u32 index)
{
return zram->table[index].element;
@@ -630,6 +628,122 @@ static int read_from_bdev(struct zram *zram, struct bio_vec *bvec,
static void zram_wb_clear(struct zram *zram, u32 index) {}
#endif
+#ifdef CONFIG_ZRAM_MEMORY_TRACKING
+
+static struct dentry *zram_debugfs_root;
+
+static void zram_debugfs_create(void)
+{
+ zram_debugfs_root = debugfs_create_dir("zram", NULL);
+}
+
+static void zram_debugfs_destroy(void)
+{
+ debugfs_remove_recursive(zram_debugfs_root);
+}
+
+static void zram_accessed(struct zram *zram, u32 index)
+{
+ zram->table[index].ac_time = ktime_get_boottime();
+}
+
+static void zram_reset_access(struct zram *zram, u32 index)
+{
+ zram->table[index].ac_time.tv64 = 0;
+}
+
+static ssize_t read_block_state(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ char *kbuf;
+ ssize_t index, written = 0;
+ struct zram *zram = file->private_data;
+ unsigned long nr_pages = zram->disksize >> PAGE_SHIFT;
+ struct timespec64 ts;
+ gfp_t kmalloc_flags;
+
+ kmalloc_flags = GFP_KERNEL;
+ if (count > PAGE_SIZE)
+ kmalloc_flags |= __GFP_NOWARN | __GFP_NORETRY;
+
+ kbuf = kmalloc_node(count, kmalloc_flags, NUMA_NO_NODE);
+ if (!kbuf && count > PAGE_SIZE)
+ kbuf = vmalloc(count);
+
+ if (!kbuf)
+ return -ENOMEM;
+
+ down_read(&zram->init_lock);
+ if (!init_done(zram)) {
+ up_read(&zram->init_lock);
+ kvfree(kbuf);
+ return -EINVAL;
+ }
+
+ for (index = *ppos; index < nr_pages; index++) {
+ int copied;
+
+ zram_slot_lock(zram, index);
+ if (!zram_allocated(zram, index))
+ goto next;
+
+ ts = ktime_to_timespec64(zram->table[index].ac_time);
+ copied = snprintf(kbuf + written, count,
+ "%12zd %12lld.%06lu %c%c%c\n",
+ index, (s64)ts.tv_sec,
+ ts.tv_nsec / NSEC_PER_USEC,
+ zram_test_flag(zram, index, ZRAM_SAME) ? 's' : '.',
+ zram_test_flag(zram, index, ZRAM_WB) ? 'w' : '.',
+ zram_test_flag(zram, index, ZRAM_HUGE) ? 'h' : '.');
+
+ if (count < copied) {
+ zram_slot_unlock(zram, index);
+ break;
+ }
+ written += copied;
+ count -= copied;
+next:
+ zram_slot_unlock(zram, index);
+ *ppos += 1;
+ }
+
+ up_read(&zram->init_lock);
+ if (copy_to_user(buf, kbuf, written))
+ written = -EFAULT;
+ kvfree(kbuf);
+
+ return written;
+}
+
+static const struct file_operations proc_zram_block_state_op = {
+ .open = simple_open,
+ .read = read_block_state,
+ .llseek = default_llseek,
+};
+
+static void zram_debugfs_register(struct zram *zram)
+{
+ if (!zram_debugfs_root)
+ return;
+
+ zram->debugfs_dir = debugfs_create_dir(zram->disk->disk_name,
+ zram_debugfs_root);
+ debugfs_create_file("block_state", 0400, zram->debugfs_dir,
+ zram, &proc_zram_block_state_op);
+}
+
+static void zram_debugfs_unregister(struct zram *zram)
+{
+ debugfs_remove_recursive(zram->debugfs_dir);
+}
+#else
+static void zram_debugfs_create(void) {};
+static void zram_debugfs_destroy(void) {};
+static void zram_accessed(struct zram *zram, u32 index) {};
+static void zram_reset_access(struct zram *zram, u32 index) {};
+static void zram_debugfs_register(struct zram *zram) {};
+static void zram_debugfs_unregister(struct zram *zram) {};
+#endif
/*
* We switched to per-cpu streams and this attr is not needed anymore.
@@ -1605,6 +1719,7 @@ static int zram_add(void)
}
strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor));
+ zram_debugfs_register(zram);
pr_info("Added device: %s\n", zram->disk->disk_name);
return device_id;
@@ -1638,6 +1753,7 @@ static int zram_remove(struct zram *zram)
zram->claim = true;
mutex_unlock(&bdev->bd_mutex);
+ zram_debugfs_unregister(zram);
/*
* Remove sysfs first, so no one will perform a disksize
* store while we destroy the devices. This also helps during
@@ -1736,6 +1852,7 @@ static void destroy_devices(void)
{
class_unregister(&zram_control_class);
idr_for_each(&zram_index_idr, &zram_remove_cb, NULL);
+ zram_debugfs_destroy();
idr_destroy(&zram_index_idr);
unregister_blkdev(zram_major, "zram");
}
@@ -1750,6 +1867,7 @@ static int __init zram_init(void)
return ret;
}
+ zram_debugfs_create();
zram_major = register_blkdev(0, "zram");
if (zram_major <= 0) {
pr_err("Unable to get major number\n");
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index 79c73f50a2a222b2cd49b0c160906d3b4ae564d1..bbda650f0dc1f63a28a2496e119b8fda634e5c09 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -78,7 +78,9 @@ struct zram_table_entry {
unsigned long element;
};
unsigned long value;
- u64 ac_time;
+#ifdef CONFIG_ZRAM_MEMORY_TRACKING
+ ktime_t ac_time;
+#endif
};
struct zram_stats {
@@ -127,5 +129,8 @@ struct zram {
unsigned long nr_pages;
spinlock_t bitmap_lock;
#endif
+#ifdef CONFIG_ZRAM_MEMORY_TRACKING
+ struct dentry *debugfs_dir;
+#endif
};
#endif