[RFC PATCH 1/1] zram: Allow rw_page when page isn't written back.

From: Brian Geffon
Date: Mon Aug 08 2022 - 12:50:32 EST


Today when a zram device has a backing device we change the ops to
a new set which does not expose a rw_page method. This prevents the
upper layers from trying to issue a synchronous rw. This has the
downside that we penalize every rw even when it could possibly
still be performed as a synchronous rw.

This change will always expose a rw_page function and if the page
has been written back it will return -EOPNOTSUPP which will force the
upper layers to try again with bio.

To safely allow a synchronous read to proceed for pages which have not
yet written back we introduce a new flag ZRAM_NO_WB. On the first
synchronous read if the page is not written back we will set the
ZRAM_NO_WB flag. This flag, which is never cleared, prevents writeback
from ever happening to that page.

This approach works because in the case of zram as a swap backing device
the page is going to be removed from zram shortly thereafter so
preventing writeback is fine. However, if zram is being used as a
generic block device then this might prevent writeback of the page.

Signed-off-by: Brian Geffon <bgeffon@xxxxxxxxxx>
---
drivers/block/zram/zram_drv.c | 65 +++++++++++++++++++++--------------
drivers/block/zram/zram_drv.h | 1 +
2 files changed, 41 insertions(+), 25 deletions(-)

diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 92cb929a45b7..196392353bd3 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -52,9 +52,6 @@ static unsigned int num_devices = 1;
static size_t huge_class_size;

static const struct block_device_operations zram_devops;
-#ifdef CONFIG_ZRAM_WRITEBACK
-static const struct block_device_operations zram_wb_devops;
-#endif

static void zram_free_page(struct zram *zram, size_t index);
static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
@@ -439,7 +436,6 @@ static void reset_bdev(struct zram *zram)
filp_close(zram->backing_dev, NULL);
zram->backing_dev = NULL;
zram->bdev = NULL;
- zram->disk->fops = &zram_devops;
kvfree(zram->bitmap);
zram->bitmap = NULL;
}
@@ -543,17 +539,6 @@ static ssize_t backing_dev_store(struct device *dev,
zram->backing_dev = backing_dev;
zram->bitmap = bitmap;
zram->nr_pages = nr_pages;
- /*
- * With writeback feature, zram does asynchronous IO so it's no longer
- * synchronous device so let's remove synchronous io flag. Othewise,
- * upper layer(e.g., swap) could wait IO completion rather than
- * (submit and return), which will cause system sluggish.
- * Furthermore, when the IO function returns(e.g., swap_readpage),
- * upper layer expects IO was done so it could deallocate the page
- * freely but in fact, IO is going on so finally could cause
- * use-after-free when the IO is really done.
- */
- zram->disk->fops = &zram_wb_devops;
up_write(&zram->init_lock);

pr_info("setup backing device %s\n", file_name);
@@ -722,7 +707,8 @@ static ssize_t writeback_store(struct device *dev,

if (zram_test_flag(zram, index, ZRAM_WB) ||
zram_test_flag(zram, index, ZRAM_SAME) ||
- zram_test_flag(zram, index, ZRAM_UNDER_WB))
+ zram_test_flag(zram, index, ZRAM_UNDER_WB) ||
+ zram_test_flag(zram, index, ZRAM_NO_WB))
goto next;

if (mode & IDLE_WRITEBACK &&
@@ -1226,6 +1212,10 @@ static void zram_free_page(struct zram *zram, size_t index)
goto out;
}

+ if (zram_test_flag(zram, index, ZRAM_NO_WB)) {
+ zram_clear_flag(zram, index, ZRAM_NO_WB);
+ }
+
/*
* No memory is allocated for same element filled pages.
* Simply clear same page flag.
@@ -1654,6 +1644,40 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector,
index = sector >> SECTORS_PER_PAGE_SHIFT;
offset = (sector & (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT;

+#ifdef CONFIG_ZRAM_WRITEBACK
+ /*
+ * With writeback feature, zram does asynchronous IO so it's no longer
+ * synchronous device so let's remove synchronous io flag. Othewise,
+ * upper layer(e.g., swap) could wait IO completion rather than
+ * (submit and return), which will cause system sluggish.
+ * Furthermore, when the IO function returns(e.g., swap_readpage),
+ * upper layer expects IO was done so it could deallocate the page
+ * freely but in fact, IO is going on so finally could cause
+ * use-after-free when the IO is really done.
+ *
+ * If the page is not currently written back then we may proceed to
+ * read the page synchronously, otherwise, we must fail with
+ * -EOPNOTSUPP to force the upper layers to use a normal bio.
+ */
+ zram_slot_lock(zram, index);
+ if (zram_test_flag(zram, index, ZRAM_WB) ||
+ zram_test_flag(zram, index, ZRAM_UNDER_WB)) {
+ zram_slot_unlock(zram, index);
+ /* We cannot proceed with synchronous read */
+ return -EOPNOTSUPP;
+ }
+
+ /*
+ * Don't allow the page to be written back while we read it,
+ * this flag is never cleared. It shouldn't be a problem that
+ * we don't clear this flag because in the case of swap this
+ * page will be removed shortly after this read anyway.
+ */
+ if (op == REQ_OP_READ)
+ zram_set_flag(zram, index, ZRAM_NO_WB);
+ zram_slot_unlock(zram, index);
+#endif
+
bv.bv_page = page;
bv.bv_len = PAGE_SIZE;
bv.bv_offset = 0;
@@ -1827,15 +1851,6 @@ static const struct block_device_operations zram_devops = {
.owner = THIS_MODULE
};

-#ifdef CONFIG_ZRAM_WRITEBACK
-static const struct block_device_operations zram_wb_devops = {
- .open = zram_open,
- .submit_bio = zram_submit_bio,
- .swap_slot_free_notify = zram_slot_free_notify,
- .owner = THIS_MODULE
-};
-#endif
-
static DEVICE_ATTR_WO(compact);
static DEVICE_ATTR_RW(disksize);
static DEVICE_ATTR_RO(initstate);
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index 158c91e54850..20e4c6a579e0 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -50,6 +50,7 @@ enum zram_pageflags {
ZRAM_UNDER_WB, /* page is under writeback */
ZRAM_HUGE, /* Incompressible page */
ZRAM_IDLE, /* not accessed page since last idle marking */
+ ZRAM_NO_WB, /* Do not allow page to be written back */

__NR_ZRAM_PAGEFLAGS,
};
--
2.37.1.559.g78731f0fdb-goog