#include <linux/err.h>
#include <linux/idr.h>
#include <linux/sysfs.h>
+#include <linux/debugfs.h>
#include <linux/cpuhotplug.h>
#include "zram_drv.h"
/* Module params (documentation at end) */
static unsigned int num_devices = 1;
+/*
+ * Pages that compress to sizes equals or greater than this are stored
+ * uncompressed in memory.
+ */
+static size_t huge_class_size;
static void zram_free_page(struct zram *zram, size_t index);
+static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
+ u32 index, int offset, struct bio *bio);
+
+
+static int zram_slot_trylock(struct zram *zram, u32 index)
+{
+ return bit_spin_trylock(ZRAM_LOCK, &zram->table[index].flags);
+}
+
+static void zram_slot_lock(struct zram *zram, u32 index)
+{
+ bit_spin_lock(ZRAM_LOCK, &zram->table[index].flags);
+}
+
+static void zram_slot_unlock(struct zram *zram, u32 index)
+{
+ bit_spin_unlock(ZRAM_LOCK, &zram->table[index].flags);
+}
static inline bool init_done(struct zram *zram)
{
}
/* 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);
+ return zram->table[index].flags & BIT(flag);
}
static void zram_set_flag(struct zram *zram, u32 index,
enum zram_pageflags flag)
{
- zram->table[index].value |= BIT(flag);
+ zram->table[index].flags |= BIT(flag);
}
static void zram_clear_flag(struct zram *zram, u32 index,
enum zram_pageflags flag)
{
- zram->table[index].value &= ~BIT(flag);
+ zram->table[index].flags &= ~BIT(flag);
}
static inline void zram_set_element(struct zram *zram, u32 index,
static size_t zram_get_obj_size(struct zram *zram, u32 index)
{
- return zram->table[index].value & (BIT(ZRAM_FLAG_SHIFT) - 1);
+ return zram->table[index].flags & (BIT(ZRAM_FLAG_SHIFT) - 1);
}
static void zram_set_obj_size(struct zram *zram,
u32 index, size_t size)
{
- unsigned long flags = zram->table[index].value >> ZRAM_FLAG_SHIFT;
+ unsigned long flags = zram->table[index].flags >> ZRAM_FLAG_SHIFT;
+
+ zram->table[index].flags = (flags << ZRAM_FLAG_SHIFT) | size;
+}
- zram->table[index].value = (flags << ZRAM_FLAG_SHIFT) | size;
+static inline bool zram_allocated(struct zram *zram, u32 index)
+{
+ return zram_get_obj_size(zram, index) ||
+ zram_test_flag(zram, index, ZRAM_SAME) ||
+ zram_test_flag(zram, index, ZRAM_WB);
}
#if PAGE_SIZE != 4096
}
#endif
-static void zram_revalidate_disk(struct zram *zram)
-{
- revalidate_disk(zram->disk);
- /* revalidate_disk reset the BDI_CAP_STABLE_WRITES so set again */
- zram->disk->queue->backing_dev_info->capabilities |=
- BDI_CAP_STABLE_WRITES;
-}
-
/*
* Check if request is within bounds and aligned on zram logical blocks.
*/
return len;
}
+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);
+ unsigned long nr_pages = zram->disksize >> PAGE_SHIFT;
+ int index;
+ char mode_buf[8];
+ ssize_t sz;
+
+ sz = strscpy(mode_buf, buf, sizeof(mode_buf));
+ if (sz <= 0)
+ return -EINVAL;
+
+ /* ignore trailing new line */
+ if (mode_buf[sz - 1] == '\n')
+ mode_buf[sz - 1] = 0x00;
+
+ if (strcmp(mode_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.
+ * See the comment in writeback_store.
+ */
+ 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_slot_unlock(zram, index);
+ }
+
+ up_read(&zram->init_lock);
+
+ return len;
+}
+
#ifdef CONFIG_ZRAM_WRITEBACK
-static bool zram_wb_enabled(struct zram *zram)
+static ssize_t writeback_limit_enable_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ struct zram *zram = dev_to_zram(dev);
+ u64 val;
+ ssize_t ret = -EINVAL;
+
+ if (kstrtoull(buf, 10, &val))
+ return ret;
+
+ down_read(&zram->init_lock);
+ spin_lock(&zram->wb_limit_lock);
+ zram->wb_limit_enable = val;
+ spin_unlock(&zram->wb_limit_lock);
+ up_read(&zram->init_lock);
+ ret = len;
+
+ return ret;
+}
+
+static ssize_t writeback_limit_enable_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ bool val;
+ struct zram *zram = dev_to_zram(dev);
+
+ down_read(&zram->init_lock);
+ spin_lock(&zram->wb_limit_lock);
+ val = zram->wb_limit_enable;
+ spin_unlock(&zram->wb_limit_lock);
+ up_read(&zram->init_lock);
+
+ return scnprintf(buf, PAGE_SIZE, "%d\n", val);
+}
+
+static ssize_t writeback_limit_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
{
- return zram->backing_dev;
+ struct zram *zram = dev_to_zram(dev);
+ u64 val;
+ ssize_t ret = -EINVAL;
+
+ if (kstrtoull(buf, 10, &val))
+ return ret;
+
+ down_read(&zram->init_lock);
+ spin_lock(&zram->wb_limit_lock);
+ zram->bd_wb_limit = val;
+ spin_unlock(&zram->wb_limit_lock);
+ up_read(&zram->init_lock);
+ ret = len;
+
+ return ret;
+}
+
+static ssize_t writeback_limit_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ u64 val;
+ struct zram *zram = dev_to_zram(dev);
+
+ down_read(&zram->init_lock);
+ spin_lock(&zram->wb_limit_lock);
+ val = zram->bd_wb_limit;
+ spin_unlock(&zram->wb_limit_lock);
+ up_read(&zram->init_lock);
+
+ return scnprintf(buf, PAGE_SIZE, "%llu\n", val);
}
static void reset_bdev(struct zram *zram)
{
struct block_device *bdev;
- if (!zram_wb_enabled(zram))
+ if (!zram->backing_dev)
return;
bdev = zram->bdev;
ssize_t ret;
down_read(&zram->init_lock);
- if (!zram_wb_enabled(zram)) {
+ if (!zram->backing_dev) {
memcpy(buf, "none\n", 5);
up_read(&zram->init_lock);
return 5;
goto out;
reset_bdev(zram);
- spin_lock_init(&zram->bitmap_lock);
zram->old_block_size = old_block_size;
zram->bdev = bdev;
return err;
}
-static unsigned long get_entry_bdev(struct zram *zram)
+static unsigned long alloc_block_bdev(struct zram *zram)
{
- unsigned long entry;
-
- spin_lock(&zram->bitmap_lock);
+ unsigned long blk_idx = 1;
+retry:
/* skip 0 bit to confuse zram.handle = 0 */
- entry = find_next_zero_bit(zram->bitmap, zram->nr_pages, 1);
- if (entry == zram->nr_pages) {
- spin_unlock(&zram->bitmap_lock);
+ blk_idx = find_next_zero_bit(zram->bitmap, zram->nr_pages, blk_idx);
+ if (blk_idx == zram->nr_pages)
return 0;
- }
- set_bit(entry, zram->bitmap);
- spin_unlock(&zram->bitmap_lock);
+ if (test_and_set_bit(blk_idx, zram->bitmap))
+ goto retry;
- return entry;
+ atomic64_inc(&zram->stats.bd_count);
+ return blk_idx;
}
-static void put_entry_bdev(struct zram *zram, unsigned long entry)
+static void free_block_bdev(struct zram *zram, unsigned long blk_idx)
{
int was_set;
- spin_lock(&zram->bitmap_lock);
- was_set = test_and_clear_bit(entry, zram->bitmap);
- spin_unlock(&zram->bitmap_lock);
+ was_set = test_and_clear_bit(blk_idx, zram->bitmap);
WARN_ON_ONCE(!was_set);
+ atomic64_dec(&zram->stats.bd_count);
}
-void zram_page_end_io(struct bio *bio)
+static void zram_page_end_io(struct bio *bio)
{
struct page *page = bio->bi_io_vec[0].bv_page;
return 1;
}
+#define HUGE_WRITEBACK 1
+#define IDLE_WRITEBACK 2
+
+static ssize_t writeback_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ struct zram *zram = dev_to_zram(dev);
+ unsigned long nr_pages = zram->disksize >> PAGE_SHIFT;
+ unsigned long index;
+ struct bio bio;
+ struct bio_vec bio_vec;
+ struct page *page;
+ ssize_t ret, sz;
+ char mode_buf[8];
+ int mode = -1;
+ unsigned long blk_idx = 0;
+
+ sz = strscpy(mode_buf, buf, sizeof(mode_buf));
+ if (sz <= 0)
+ return -EINVAL;
+
+ /* ignore trailing newline */
+ if (mode_buf[sz - 1] == '\n')
+ mode_buf[sz - 1] = 0x00;
+
+ if (!strcmp(mode_buf, "idle"))
+ mode = IDLE_WRITEBACK;
+ else if (!strcmp(mode_buf, "huge"))
+ mode = HUGE_WRITEBACK;
+
+ if (mode == -1)
+ return -EINVAL;
+
+ down_read(&zram->init_lock);
+ if (!init_done(zram)) {
+ ret = -EINVAL;
+ goto release_init_lock;
+ }
+
+ if (!zram->backing_dev) {
+ ret = -ENODEV;
+ goto release_init_lock;
+ }
+
+ page = alloc_page(GFP_KERNEL);
+ if (!page) {
+ ret = -ENOMEM;
+ goto release_init_lock;
+ }
+
+ for (index = 0; index < nr_pages; index++) {
+ struct bio_vec bvec;
+
+ bvec.bv_page = page;
+ bvec.bv_len = PAGE_SIZE;
+ bvec.bv_offset = 0;
+
+ spin_lock(&zram->wb_limit_lock);
+ if (zram->wb_limit_enable && !zram->bd_wb_limit) {
+ spin_unlock(&zram->wb_limit_lock);
+ ret = -EIO;
+ break;
+ }
+ spin_unlock(&zram->wb_limit_lock);
+
+ if (!blk_idx) {
+ blk_idx = alloc_block_bdev(zram);
+ if (!blk_idx) {
+ ret = -ENOSPC;
+ break;
+ }
+ }
+
+ zram_slot_lock(zram, index);
+ if (!zram_allocated(zram, index))
+ goto next;
+
+ if (zram_test_flag(zram, index, ZRAM_WB) ||
+ zram_test_flag(zram, index, ZRAM_SAME) ||
+ zram_test_flag(zram, index, ZRAM_UNDER_WB))
+ goto next;
+
+ if (mode == IDLE_WRITEBACK &&
+ !zram_test_flag(zram, index, ZRAM_IDLE))
+ goto next;
+ if (mode == HUGE_WRITEBACK &&
+ !zram_test_flag(zram, index, ZRAM_HUGE))
+ goto next;
+ /*
+ * Clearing ZRAM_UNDER_WB is duty of caller.
+ * IOW, zram_free_page never clear it.
+ */
+ zram_set_flag(zram, index, ZRAM_UNDER_WB);
+ /* Need for hugepage writeback racing */
+ zram_set_flag(zram, index, ZRAM_IDLE);
+ zram_slot_unlock(zram, index);
+ if (zram_bvec_read(zram, &bvec, index, 0, NULL)) {
+ zram_slot_lock(zram, index);
+ zram_clear_flag(zram, index, ZRAM_UNDER_WB);
+ zram_clear_flag(zram, index, ZRAM_IDLE);
+ zram_slot_unlock(zram, index);
+ continue;
+ }
+
+ bio_init(&bio, &bio_vec, 1);
+ bio_set_dev(&bio, zram->bdev);
+ bio.bi_iter.bi_sector = blk_idx * (PAGE_SIZE >> 9);
+ bio.bi_opf = REQ_OP_WRITE | REQ_SYNC;
+
+ bio_add_page(&bio, bvec.bv_page, bvec.bv_len,
+ bvec.bv_offset);
+ /*
+ * XXX: A single page IO would be inefficient for write
+ * but it would be not bad as starter.
+ */
+ ret = submit_bio_wait(&bio);
+ if (ret) {
+ zram_slot_lock(zram, index);
+ zram_clear_flag(zram, index, ZRAM_UNDER_WB);
+ zram_clear_flag(zram, index, ZRAM_IDLE);
+ zram_slot_unlock(zram, index);
+ continue;
+ }
+
+ atomic64_inc(&zram->stats.bd_writes);
+ /*
+ * We released zram_slot_lock so need to check if the slot was
+ * changed. If there is freeing for the slot, we can catch it
+ * easily by zram_allocated.
+ * A subtle case is the slot is freed/reallocated/marked as
+ * ZRAM_IDLE again. To close the race, idle_store doesn't
+ * mark ZRAM_IDLE once it found the slot was ZRAM_UNDER_WB.
+ * Thus, we could close the race by checking ZRAM_IDLE bit.
+ */
+ zram_slot_lock(zram, index);
+ if (!zram_allocated(zram, index) ||
+ !zram_test_flag(zram, index, ZRAM_IDLE)) {
+ zram_clear_flag(zram, index, ZRAM_UNDER_WB);
+ zram_clear_flag(zram, index, ZRAM_IDLE);
+ goto next;
+ }
+
+ zram_free_page(zram, index);
+ zram_clear_flag(zram, index, ZRAM_UNDER_WB);
+ zram_set_flag(zram, index, ZRAM_WB);
+ zram_set_element(zram, index, blk_idx);
+ blk_idx = 0;
+ atomic64_inc(&zram->stats.pages_stored);
+ spin_lock(&zram->wb_limit_lock);
+ if (zram->wb_limit_enable && zram->bd_wb_limit > 0)
+ zram->bd_wb_limit -= 1UL << (PAGE_SHIFT - 12);
+ spin_unlock(&zram->wb_limit_lock);
+next:
+ zram_slot_unlock(zram, index);
+ }
+
+ if (blk_idx)
+ free_block_bdev(zram, blk_idx);
+ ret = len;
+ __free_page(page);
+release_init_lock:
+ up_read(&zram->init_lock);
+
+ return ret;
+}
+
struct zram_work {
struct work_struct work;
struct zram *zram;
static int read_from_bdev(struct zram *zram, struct bio_vec *bvec,
unsigned long entry, struct bio *parent, bool sync)
{
+ atomic64_inc(&zram->stats.bd_reads);
if (sync)
return read_from_bdev_sync(zram, bvec, entry, parent);
else
return read_from_bdev_async(zram, bvec, entry, parent);
}
+#else
+static inline void reset_bdev(struct zram *zram) {};
+static int read_from_bdev(struct zram *zram, struct bio_vec *bvec,
+ unsigned long entry, struct bio *parent, bool sync)
+{
+ return -EIO;
+}
+
+static void free_block_bdev(struct zram *zram, unsigned long blk_idx) {};
+#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 int write_to_bdev(struct zram *zram, struct bio_vec *bvec,
- u32 index, struct bio *parent,
- unsigned long *pentry)
+static void zram_debugfs_destroy(void)
{
- struct bio *bio;
- unsigned long entry;
+ debugfs_remove_recursive(zram_debugfs_root);
+}
- bio = bio_alloc(GFP_ATOMIC, 1);
- if (!bio)
+static void zram_accessed(struct zram *zram, u32 index)
+{
+ zram_clear_flag(zram, index, ZRAM_IDLE);
+ zram->table[index].ac_time = ktime_get_boottime();
+}
+
+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;
+
+ kbuf = kvmalloc(count, GFP_KERNEL);
+ if (!kbuf)
return -ENOMEM;
- entry = get_entry_bdev(zram);
- if (!entry) {
- bio_put(bio);
- return -ENOSPC;
+ down_read(&zram->init_lock);
+ if (!init_done(zram)) {
+ up_read(&zram->init_lock);
+ kvfree(kbuf);
+ return -EINVAL;
}
- bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9);
- bio_set_dev(bio, zram->bdev);
- if (!bio_add_page(bio, bvec->bv_page, bvec->bv_len,
- bvec->bv_offset)) {
- bio_put(bio);
- put_entry_bdev(zram, entry);
- return -EIO;
- }
+ for (index = *ppos; index < nr_pages; index++) {
+ int copied;
- if (!parent) {
- bio->bi_opf = REQ_OP_WRITE | REQ_SYNC;
- bio->bi_end_io = zram_page_end_io;
- } else {
- bio->bi_opf = parent->bi_opf;
- bio_chain(bio, parent);
+ 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%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' : '.',
+ zram_test_flag(zram, index, ZRAM_IDLE) ? 'i' : '.');
+
+ if (count < copied) {
+ zram_slot_unlock(zram, index);
+ break;
+ }
+ written += copied;
+ count -= copied;
+next:
+ zram_slot_unlock(zram, index);
+ *ppos += 1;
}
- submit_bio(bio);
- *pentry = entry;
+ up_read(&zram->init_lock);
+ if (copy_to_user(buf, kbuf, written))
+ written = -EFAULT;
+ kvfree(kbuf);
- return 0;
+ return written;
}
-static void zram_wb_clear(struct zram *zram, u32 index)
+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)
{
- unsigned long entry;
+ if (!zram_debugfs_root)
+ return;
- zram_clear_flag(zram, index, ZRAM_WB);
- entry = zram_get_element(zram, index);
- zram_set_element(zram, index, 0);
- put_entry_bdev(zram, entry);
+ 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);
}
-#else
-static bool zram_wb_enabled(struct zram *zram) { return false; }
-static inline void reset_bdev(struct zram *zram) {};
-static int write_to_bdev(struct zram *zram, struct bio_vec *bvec,
- u32 index, struct bio *parent,
- unsigned long *pentry)
-
+static void zram_debugfs_unregister(struct zram *zram)
{
- return -EIO;
+ debugfs_remove_recursive(zram->debugfs_dir);
}
-
-static int read_from_bdev(struct zram *zram, struct bio_vec *bvec,
- unsigned long entry, struct bio *parent, bool sync)
+#else
+static void zram_debugfs_create(void) {};
+static void zram_debugfs_destroy(void) {};
+static void zram_accessed(struct zram *zram, u32 index)
{
- return -EIO;
-}
-static void zram_wb_clear(struct zram *zram, u32 index) {}
+ zram_clear_flag(zram, index, ZRAM_IDLE);
+};
+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.
* However, we will keep it around for some time, because:
max_used = atomic_long_read(&zram->stats.max_used_pages);
ret = scnprintf(buf, PAGE_SIZE,
- "%8llu %8llu %8llu %8lu %8ld %8llu %8lu\n",
+ "%8llu %8llu %8llu %8lu %8ld %8llu %8lu %8llu\n",
orig_size << PAGE_SHIFT,
(u64)atomic64_read(&zram->stats.compr_data_size),
mem_used << PAGE_SHIFT,
zram->limit_pages << PAGE_SHIFT,
max_used << PAGE_SHIFT,
(u64)atomic64_read(&zram->stats.same_pages),
- pool_stats.pages_compacted);
+ pool_stats.pages_compacted,
+ (u64)atomic64_read(&zram->stats.huge_pages));
up_read(&zram->init_lock);
return ret;
}
+#ifdef CONFIG_ZRAM_WRITEBACK
+#define FOUR_K(x) ((x) * (1 << (PAGE_SHIFT - 12)))
+static ssize_t bd_stat_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct zram *zram = dev_to_zram(dev);
+ ssize_t ret;
+
+ down_read(&zram->init_lock);
+ ret = scnprintf(buf, PAGE_SIZE,
+ "%8llu %8llu %8llu\n",
+ FOUR_K((u64)atomic64_read(&zram->stats.bd_count)),
+ FOUR_K((u64)atomic64_read(&zram->stats.bd_reads)),
+ FOUR_K((u64)atomic64_read(&zram->stats.bd_writes)));
+ up_read(&zram->init_lock);
+
+ return ret;
+}
+#endif
+
static ssize_t debug_stat_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
down_read(&zram->init_lock);
ret = scnprintf(buf, PAGE_SIZE,
- "version: %d\n%8llu\n",
+ "version: %d\n%8llu %8llu\n",
version,
- (u64)atomic64_read(&zram->stats.writestall));
+ (u64)atomic64_read(&zram->stats.writestall),
+ (u64)atomic64_read(&zram->stats.miss_free));
up_read(&zram->init_lock);
return ret;
static DEVICE_ATTR_RO(io_stat);
static DEVICE_ATTR_RO(mm_stat);
+#ifdef CONFIG_ZRAM_WRITEBACK
+static DEVICE_ATTR_RO(bd_stat);
+#endif
static DEVICE_ATTR_RO(debug_stat);
-static void zram_slot_lock(struct zram *zram, u32 index)
-{
- bit_spin_lock(ZRAM_ACCESS, &zram->table[index].value);
-}
-
-static void zram_slot_unlock(struct zram *zram, u32 index)
-{
- bit_spin_unlock(ZRAM_ACCESS, &zram->table[index].value);
-}
-
static void zram_meta_free(struct zram *zram, u64 disksize)
{
size_t num_pages = disksize >> PAGE_SHIFT;
return false;
}
+ if (!huge_class_size)
+ huge_class_size = zs_huge_class_size(zram->mem_pool);
return true;
}
{
unsigned long handle;
- if (zram_wb_enabled(zram) && zram_test_flag(zram, index, ZRAM_WB)) {
- zram_wb_clear(zram, index);
- atomic64_dec(&zram->stats.pages_stored);
- return;
+#ifdef CONFIG_ZRAM_MEMORY_TRACKING
+ zram->table[index].ac_time = 0;
+#endif
+ if (zram_test_flag(zram, index, ZRAM_IDLE))
+ zram_clear_flag(zram, index, ZRAM_IDLE);
+
+ if (zram_test_flag(zram, index, ZRAM_HUGE)) {
+ zram_clear_flag(zram, index, ZRAM_HUGE);
+ atomic64_dec(&zram->stats.huge_pages);
+ }
+
+ if (zram_test_flag(zram, index, ZRAM_WB)) {
+ zram_clear_flag(zram, index, ZRAM_WB);
+ free_block_bdev(zram, zram_get_element(zram, index));
+ goto out;
}
/*
*/
if (zram_test_flag(zram, index, ZRAM_SAME)) {
zram_clear_flag(zram, index, ZRAM_SAME);
- zram_set_element(zram, index, 0);
atomic64_dec(&zram->stats.same_pages);
- atomic64_dec(&zram->stats.pages_stored);
- return;
+ goto out;
}
handle = zram_get_handle(zram, index);
atomic64_sub(zram_get_obj_size(zram, index),
&zram->stats.compr_data_size);
+out:
atomic64_dec(&zram->stats.pages_stored);
-
zram_set_handle(zram, index, 0);
zram_set_obj_size(zram, index, 0);
+ WARN_ON_ONCE(zram->table[index].flags &
+ ~(1UL << ZRAM_LOCK | 1UL << ZRAM_UNDER_WB));
}
static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
unsigned int size;
void *src, *dst;
- if (zram_wb_enabled(zram)) {
- zram_slot_lock(zram, index);
- if (zram_test_flag(zram, index, ZRAM_WB)) {
- struct bio_vec bvec;
-
- zram_slot_unlock(zram, index);
+ zram_slot_lock(zram, index);
+ if (zram_test_flag(zram, index, ZRAM_WB)) {
+ struct bio_vec bvec;
- bvec.bv_page = page;
- bvec.bv_len = PAGE_SIZE;
- bvec.bv_offset = 0;
- return read_from_bdev(zram, &bvec,
- zram_get_element(zram, index),
- bio, partial_io);
- }
zram_slot_unlock(zram, index);
+
+ bvec.bv_page = page;
+ bvec.bv_len = PAGE_SIZE;
+ bvec.bv_offset = 0;
+ return read_from_bdev(zram, &bvec,
+ zram_get_element(zram, index),
+ bio, partial_io);
}
- zram_slot_lock(zram, index);
handle = zram_get_handle(zram, index);
if (!handle || zram_test_flag(zram, index, ZRAM_SAME)) {
unsigned long value;
struct page *page = bvec->bv_page;
unsigned long element = 0;
enum zram_pageflags flags = 0;
- bool allow_wb = true;
mem = kmap_atomic(page);
if (page_same_filled(mem, &element)) {
return ret;
}
- if (unlikely(comp_len > max_zpage_size)) {
- if (zram_wb_enabled(zram) && allow_wb) {
- zcomp_stream_put(zram->comp);
- ret = write_to_bdev(zram, bvec, index, bio, &element);
- if (!ret) {
- flags = ZRAM_WB;
- ret = 1;
- goto out;
- }
- allow_wb = false;
- goto compress_again;
- }
+ if (comp_len >= huge_class_size)
comp_len = PAGE_SIZE;
- }
-
/*
* handle allocation has 2 paths:
* a) fast path is executed with preemption disabled (for
zram_slot_lock(zram, index);
zram_free_page(zram, index);
+ if (comp_len == PAGE_SIZE) {
+ zram_set_flag(zram, index, ZRAM_HUGE);
+ atomic64_inc(&zram->stats.huge_pages);
+ }
+
if (flags) {
zram_set_flag(zram, index, flags);
zram_set_element(zram, index, element);
generic_end_io_acct(q, rw_acct, &zram->disk->part0, start_time);
+ zram_slot_lock(zram, index);
+ zram_accessed(zram, index);
+ zram_slot_unlock(zram, index);
+
if (unlikely(ret < 0)) {
if (!is_write)
atomic64_inc(&zram->stats.failed_reads);
zram = bdev->bd_disk->private_data;
- zram_slot_lock(zram, index);
+ atomic64_inc(&zram->stats.notify_free);
+ if (!zram_slot_trylock(zram, index)) {
+ atomic64_inc(&zram->stats.miss_free);
+ return;
+ }
+
zram_free_page(zram, index);
zram_slot_unlock(zram, index);
- atomic64_inc(&zram->stats.notify_free);
}
static int zram_rw_page(struct block_device *bdev, sector_t sector,
zram->comp = comp;
zram->disksize = disksize;
set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT);
- zram_revalidate_disk(zram);
+
+ revalidate_disk(zram->disk);
up_write(&zram->init_lock);
return len;
/* Make sure all the pending I/O are finished */
fsync_bdev(bdev);
zram_reset_device(zram);
- zram_revalidate_disk(zram);
+ revalidate_disk(zram->disk);
bdput(bdev);
mutex_lock(&bdev->bd_mutex);
static DEVICE_ATTR_WO(reset);
static DEVICE_ATTR_WO(mem_limit);
static DEVICE_ATTR_WO(mem_used_max);
+static DEVICE_ATTR_WO(idle);
static DEVICE_ATTR_RW(max_comp_streams);
static DEVICE_ATTR_RW(comp_algorithm);
#ifdef CONFIG_ZRAM_WRITEBACK
static DEVICE_ATTR_RW(backing_dev);
+static DEVICE_ATTR_WO(writeback);
+static DEVICE_ATTR_RW(writeback_limit);
+static DEVICE_ATTR_RW(writeback_limit_enable);
#endif
static struct attribute *zram_disk_attrs[] = {
&dev_attr_compact.attr,
&dev_attr_mem_limit.attr,
&dev_attr_mem_used_max.attr,
+ &dev_attr_idle.attr,
&dev_attr_max_comp_streams.attr,
&dev_attr_comp_algorithm.attr,
#ifdef CONFIG_ZRAM_WRITEBACK
&dev_attr_backing_dev.attr,
+ &dev_attr_writeback.attr,
+ &dev_attr_writeback_limit.attr,
+ &dev_attr_writeback_limit_enable.attr,
#endif
&dev_attr_io_stat.attr,
&dev_attr_mm_stat.attr,
+#ifdef CONFIG_ZRAM_WRITEBACK
+ &dev_attr_bd_stat.attr,
+#endif
&dev_attr_debug_stat.attr,
NULL,
};
device_id = ret;
init_rwsem(&zram->init_lock);
-
+#ifdef CONFIG_ZRAM_WRITEBACK
+ spin_lock_init(&zram->wb_limit_lock);
+#endif
queue = blk_alloc_queue(GFP_KERNEL);
if (!queue) {
pr_err("Error allocating disk queue for device %d\n",
/* zram devices sort of resembles non-rotational disks */
queue_flag_set_unlocked(QUEUE_FLAG_NONROT, zram->disk->queue);
queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, zram->disk->queue);
+
/*
* To ensure that we always get PAGE_SIZE aligned
* and n*PAGE_SIZED sized I/O requests.
if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE)
blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX);
+ zram->disk->queue->backing_dev_info->capabilities |=
+ BDI_CAP_STABLE_WRITES;
+
disk_to_dev(zram->disk)->groups = zram_disk_attr_groups;
add_disk(zram->disk);
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;
zram->claim = true;
mutex_unlock(&bdev->bd_mutex);
+ zram_debugfs_unregister(zram);
+
/* Make sure all the pending I/O are finished */
fsync_bdev(bdev);
zram_reset_device(zram);
pr_info("Removed device: %s\n", zram->disk->disk_name);
- blk_cleanup_queue(zram->disk->queue);
del_gendisk(zram->disk);
+ blk_cleanup_queue(zram->disk->queue);
put_disk(zram->disk);
kfree(zram);
return 0;
{
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");
cpuhp_remove_multi_state(CPUHP_ZCOMP_PREPARE);
return ret;
}
+ zram_debugfs_create();
zram_major = register_blkdev(0, "zram");
if (zram_major <= 0) {
pr_err("Unable to get major number\n");
projects / GitHub / MotorolaMobilityLLC / kernel-slsi.git / commitdiff