All of lore.kernel.org
 help / color / mirror / Atom feed
From: Sasha Levin <sashal@kernel.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: Damien Le Moal <dlemoal@kernel.org>,
	Christoph Hellwig <hch@lst.de>,
	Johannes Thumshirn <johannes.thumshirn@wdc.com>,
	Jens Axboe <axboe@kernel.dk>, Sasha Levin <sashal@kernel.org>,
	linux-block@vger.kernel.org
Subject: [PATCH AUTOSEL 6.12 07/19] block: RCU protect disk->conv_zones_bitmap
Date: Sun, 24 Nov 2024 07:38:42 -0500	[thread overview]
Message-ID: <20241124123912.3335344-7-sashal@kernel.org> (raw)
In-Reply-To: <20241124123912.3335344-1-sashal@kernel.org>

From: Damien Le Moal <dlemoal@kernel.org>

[ Upstream commit d7cb6d7414ea1b33536fa6d11805cb8dceec1f97 ]

Ensure that a disk revalidation changing the conventional zones bitmap
of a disk does not cause invalid memory references when using the
disk_zone_is_conv() helper by RCU protecting the disk->conv_zones_bitmap
pointer.

disk_zone_is_conv() is modified to operate under the RCU read lock and
the function disk_set_conv_zones_bitmap() is added to update a disk
conv_zones_bitmap pointer using rcu_replace_pointer() with the disk
zone_wplugs_lock spinlock held.

disk_free_zone_resources() is modified to call
disk_update_zone_resources() with a NULL bitmap pointer to free the disk
conv_zones_bitmap. disk_set_conv_zones_bitmap() is also used in
disk_update_zone_resources() to set the new (revalidated) bitmap and
free the old one.

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Link: https://lore.kernel.org/r/20241107064300.227731-2-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 block/blk-zoned.c      | 43 ++++++++++++++++++++++++++++++------------
 include/linux/blkdev.h |  2 +-
 2 files changed, 32 insertions(+), 13 deletions(-)

diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index af19296fa50df..74e39545562d5 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -350,9 +350,15 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
 
 static inline bool disk_zone_is_conv(struct gendisk *disk, sector_t sector)
 {
-	if (!disk->conv_zones_bitmap)
-		return false;
-	return test_bit(disk_zone_no(disk, sector), disk->conv_zones_bitmap);
+	unsigned long *bitmap;
+	bool is_conv;
+
+	rcu_read_lock();
+	bitmap = rcu_dereference(disk->conv_zones_bitmap);
+	is_conv = bitmap && test_bit(disk_zone_no(disk, sector), bitmap);
+	rcu_read_unlock();
+
+	return is_conv;
 }
 
 static bool disk_zone_is_last(struct gendisk *disk, struct blk_zone *zone)
@@ -1455,6 +1461,24 @@ static void disk_destroy_zone_wplugs_hash_table(struct gendisk *disk)
 	disk->zone_wplugs_hash_bits = 0;
 }
 
+static unsigned int disk_set_conv_zones_bitmap(struct gendisk *disk,
+					       unsigned long *bitmap)
+{
+	unsigned int nr_conv_zones = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&disk->zone_wplugs_lock, flags);
+	if (bitmap)
+		nr_conv_zones = bitmap_weight(bitmap, disk->nr_zones);
+	bitmap = rcu_replace_pointer(disk->conv_zones_bitmap, bitmap,
+				     lockdep_is_held(&disk->zone_wplugs_lock));
+	spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags);
+
+	kfree_rcu_mightsleep(bitmap);
+
+	return nr_conv_zones;
+}
+
 void disk_free_zone_resources(struct gendisk *disk)
 {
 	if (!disk->zone_wplugs_pool)
@@ -1478,8 +1502,7 @@ void disk_free_zone_resources(struct gendisk *disk)
 	mempool_destroy(disk->zone_wplugs_pool);
 	disk->zone_wplugs_pool = NULL;
 
-	bitmap_free(disk->conv_zones_bitmap);
-	disk->conv_zones_bitmap = NULL;
+	disk_set_conv_zones_bitmap(disk, NULL);
 	disk->zone_capacity = 0;
 	disk->last_zone_capacity = 0;
 	disk->nr_zones = 0;
@@ -1538,17 +1561,15 @@ static int disk_update_zone_resources(struct gendisk *disk,
 				      struct blk_revalidate_zone_args *args)
 {
 	struct request_queue *q = disk->queue;
-	unsigned int nr_seq_zones, nr_conv_zones = 0;
+	unsigned int nr_seq_zones, nr_conv_zones;
 	unsigned int pool_size;
 	struct queue_limits lim;
 
 	disk->nr_zones = args->nr_zones;
 	disk->zone_capacity = args->zone_capacity;
 	disk->last_zone_capacity = args->last_zone_capacity;
-	swap(disk->conv_zones_bitmap, args->conv_zones_bitmap);
-	if (disk->conv_zones_bitmap)
-		nr_conv_zones = bitmap_weight(disk->conv_zones_bitmap,
-					      disk->nr_zones);
+	nr_conv_zones =
+		disk_set_conv_zones_bitmap(disk, args->conv_zones_bitmap);
 	if (nr_conv_zones >= disk->nr_zones) {
 		pr_warn("%s: Invalid number of conventional zones %u / %u\n",
 			disk->disk_name, nr_conv_zones, disk->nr_zones);
@@ -1823,8 +1844,6 @@ int blk_revalidate_disk_zones(struct gendisk *disk)
 		disk_free_zone_resources(disk);
 	blk_mq_unfreeze_queue(q);
 
-	kfree(args.conv_zones_bitmap);
-
 	return ret;
 }
 EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 50c3b959da281..3027ce2de7319 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -194,7 +194,7 @@ struct gendisk {
 	unsigned int		nr_zones;
 	unsigned int		zone_capacity;
 	unsigned int		last_zone_capacity;
-	unsigned long		*conv_zones_bitmap;
+	unsigned long __rcu	*conv_zones_bitmap;
 	unsigned int            zone_wplugs_hash_bits;
 	spinlock_t              zone_wplugs_lock;
 	struct mempool_s	*zone_wplugs_pool;
-- 
2.43.0


  parent reply	other threads:[~2024-11-24 12:39 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-11-24 12:38 [PATCH AUTOSEL 6.12 01/19] s390/pci: Sort PCI functions prior to creating virtual busses Sasha Levin
2024-11-24 12:38 ` [PATCH AUTOSEL 6.12 02/19] s390/pci: Use topology ID for multi-function devices Sasha Levin
2024-11-24 12:38 ` [PATCH AUTOSEL 6.12 03/19] s390/pci: Ignore RID for isolated VFs Sasha Levin
2024-11-24 12:38 ` [PATCH AUTOSEL 6.12 04/19] epoll: annotate racy check Sasha Levin
2024-11-24 12:38 ` [PATCH AUTOSEL 6.12 05/19] kselftest/arm64: Log fp-stress child startup errors to stdout Sasha Levin
2024-11-24 12:38 ` [PATCH AUTOSEL 6.12 06/19] s390/cpum_sf: Handle CPU hotplug remove during sampling Sasha Levin
2024-11-24 12:38 ` Sasha Levin [this message]
2024-11-24 12:38 ` [PATCH AUTOSEL 6.12 08/19] btrfs: don't take dev_replace rwsem on task already holding it Sasha Levin
2024-11-24 12:38 ` [PATCH AUTOSEL 6.12 09/19] btrfs: zlib: make the compression path to handle sector size < page size Sasha Levin
2024-11-25 15:20   ` David Sterba
2024-12-10 16:20     ` Sasha Levin
2024-11-24 12:38 ` [PATCH AUTOSEL 6.12 10/19] btrfs: make extent_range_clear_dirty_for_io() to handle sector size < page size cases Sasha Levin
2024-11-25 15:21   ` David Sterba
2024-11-24 12:38 ` [PATCH AUTOSEL 6.12 11/19] btrfs: avoid unnecessary device path update for the same device Sasha Levin
2024-11-24 12:38 ` [PATCH AUTOSEL 6.12 12/19] btrfs: canonicalize the device path before adding it Sasha Levin
2024-11-24 12:38 ` [PATCH AUTOSEL 6.12 13/19] btrfs: reduce lock contention when eb cache miss for btree search Sasha Levin
2024-11-25 11:23   ` Filipe Manana
2024-11-24 12:38 ` [PATCH AUTOSEL 6.12 14/19] btrfs: do not clear read-only when adding sprout device Sasha Levin
2024-11-24 12:38 ` [PATCH AUTOSEL 6.12 15/19] btrfs: fix warning on PTR_ERR() against NULL device at btrfs_control_ioctl() Sasha Levin
2024-11-24 12:38 ` [PATCH AUTOSEL 6.12 16/19] md/raid1: Handle bio_split() errors Sasha Levin
2024-11-25  8:55   ` John Garry
2024-12-10 16:21     ` Sasha Levin
2024-11-24 12:38 ` [PATCH AUTOSEL 6.12 17/19] kselftest/arm64: Corrupt P0 in the irritator when testing SSVE Sasha Levin
2024-11-24 12:38 ` [PATCH AUTOSEL 6.12 18/19] kselftest/arm64: Don't leak pipe fds in pac.exec_sign_all() Sasha Levin
2024-11-24 12:38 ` [PATCH AUTOSEL 6.12 19/19] ext4: partial zero eof block on unaligned inode size extension Sasha Levin

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20241124123912.3335344-7-sashal@kernel.org \
    --to=sashal@kernel.org \
    --cc=axboe@kernel.dk \
    --cc=dlemoal@kernel.org \
    --cc=hch@lst.de \
    --cc=johannes.thumshirn@wdc.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=stable@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.