BPF Archive on lore.kernel.org
 help / color / Atom feed
From: Sasha Levin <sashal@kernel.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: "Toke Høiland-Jørgensen" <toke@redhat.com>,
	"Tetsuo Handa" <penguin-kernel@I-love.SAKURA.ne.jp>,
	"Alexei Starovoitov" <ast@kernel.org>,
	"John Fastabend" <john.fastabend@gmail.com>,
	"Sasha Levin" <sashal@kernel.org>,
	netdev@vger.kernel.org, bpf@vger.kernel.org
Subject: [PATCH AUTOSEL 5.4 172/205] xdp: Fix cleanup on map free for devmap_hash map type
Date: Thu, 16 Jan 2020 11:42:27 -0500
Message-ID: <20200116164300.6705-172-sashal@kernel.org> (raw)
In-Reply-To: <20200116164300.6705-1-sashal@kernel.org>

From: Toke Høiland-Jørgensen <toke@redhat.com>

[ Upstream commit 071cdecec57fb5d5df78e6a12114ad7bccea5b0e ]

Tetsuo pointed out that it was not only the device unregister hook that was
broken for devmap_hash types, it was also cleanup on map free. So better
fix this as well.

While we're at it, there's no reason to allocate the netdev_map array for
DEVMAP_HASH, so skip that and adjust the cost accordingly.

Fixes: 6f9d451ab1a3 ("xdp: Add devmap_hash map type for looking up devices by hashed index")
Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20191121133612.430414-1-toke@redhat.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/bpf/devmap.c | 74 ++++++++++++++++++++++++++++-----------------
 1 file changed, 46 insertions(+), 28 deletions(-)

diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 3867864cdc2f..3d3d61b5985b 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -74,7 +74,7 @@ struct bpf_dtab_netdev {
 
 struct bpf_dtab {
 	struct bpf_map map;
-	struct bpf_dtab_netdev **netdev_map;
+	struct bpf_dtab_netdev **netdev_map; /* DEVMAP type only */
 	struct list_head __percpu *flush_list;
 	struct list_head list;
 
@@ -101,6 +101,12 @@ static struct hlist_head *dev_map_create_hash(unsigned int entries)
 	return hash;
 }
 
+static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab,
+						    int idx)
+{
+	return &dtab->dev_index_head[idx & (dtab->n_buckets - 1)];
+}
+
 static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr)
 {
 	int err, cpu;
@@ -120,8 +126,7 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr)
 	bpf_map_init_from_attr(&dtab->map, attr);
 
 	/* make sure page count doesn't overflow */
-	cost = (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *);
-	cost += sizeof(struct list_head) * num_possible_cpus();
+	cost = (u64) sizeof(struct list_head) * num_possible_cpus();
 
 	if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
 		dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries);
@@ -129,6 +134,8 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr)
 		if (!dtab->n_buckets) /* Overflow check */
 			return -EINVAL;
 		cost += (u64) sizeof(struct hlist_head) * dtab->n_buckets;
+	} else {
+		cost += (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *);
 	}
 
 	/* if map size is larger than memlock limit, reject it */
@@ -143,24 +150,22 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr)
 	for_each_possible_cpu(cpu)
 		INIT_LIST_HEAD(per_cpu_ptr(dtab->flush_list, cpu));
 
-	dtab->netdev_map = bpf_map_area_alloc(dtab->map.max_entries *
-					      sizeof(struct bpf_dtab_netdev *),
-					      dtab->map.numa_node);
-	if (!dtab->netdev_map)
-		goto free_percpu;
-
 	if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
 		dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets);
 		if (!dtab->dev_index_head)
-			goto free_map_area;
+			goto free_percpu;
 
 		spin_lock_init(&dtab->index_lock);
+	} else {
+		dtab->netdev_map = bpf_map_area_alloc(dtab->map.max_entries *
+						      sizeof(struct bpf_dtab_netdev *),
+						      dtab->map.numa_node);
+		if (!dtab->netdev_map)
+			goto free_percpu;
 	}
 
 	return 0;
 
-free_map_area:
-	bpf_map_area_free(dtab->netdev_map);
 free_percpu:
 	free_percpu(dtab->flush_list);
 free_charge:
@@ -228,21 +233,40 @@ static void dev_map_free(struct bpf_map *map)
 			cond_resched();
 	}
 
-	for (i = 0; i < dtab->map.max_entries; i++) {
-		struct bpf_dtab_netdev *dev;
+	if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
+		for (i = 0; i < dtab->n_buckets; i++) {
+			struct bpf_dtab_netdev *dev;
+			struct hlist_head *head;
+			struct hlist_node *next;
 
-		dev = dtab->netdev_map[i];
-		if (!dev)
-			continue;
+			head = dev_map_index_hash(dtab, i);
 
-		free_percpu(dev->bulkq);
-		dev_put(dev->dev);
-		kfree(dev);
+			hlist_for_each_entry_safe(dev, next, head, index_hlist) {
+				hlist_del_rcu(&dev->index_hlist);
+				free_percpu(dev->bulkq);
+				dev_put(dev->dev);
+				kfree(dev);
+			}
+		}
+
+		kfree(dtab->dev_index_head);
+	} else {
+		for (i = 0; i < dtab->map.max_entries; i++) {
+			struct bpf_dtab_netdev *dev;
+
+			dev = dtab->netdev_map[i];
+			if (!dev)
+				continue;
+
+			free_percpu(dev->bulkq);
+			dev_put(dev->dev);
+			kfree(dev);
+		}
+
+		bpf_map_area_free(dtab->netdev_map);
 	}
 
 	free_percpu(dtab->flush_list);
-	bpf_map_area_free(dtab->netdev_map);
-	kfree(dtab->dev_index_head);
 	kfree(dtab);
 }
 
@@ -263,12 +287,6 @@ static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 	return 0;
 }
 
-static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab,
-						    int idx)
-{
-	return &dtab->dev_index_head[idx & (dtab->n_buckets - 1)];
-}
-
 struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key)
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
-- 
2.20.1


  parent reply index

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20200116164300.6705-1-sashal@kernel.org>
2020-01-16 16:40 ` [PATCH AUTOSEL 5.4 049/205] net: netsec: Correct dma sync for XDP_TX frames Sasha Levin
2020-01-16 16:40 ` [PATCH AUTOSEL 5.4 077/205] libbpf: Fix compatibility for kernels without need_wakeup Sasha Levin
2020-01-16 16:40 ` [PATCH AUTOSEL 5.4 080/205] libbpf: Don't use kernel-side u32 type in xsk.c Sasha Levin
2020-01-16 16:41 ` [PATCH AUTOSEL 5.4 111/205] libbpf: Fix memory leak/double free issue Sasha Levin
2020-01-16 16:41 ` [PATCH AUTOSEL 5.4 112/205] libbpf: Fix potential overflow issue Sasha Levin
2020-01-16 16:41 ` [PATCH AUTOSEL 5.4 113/205] libbpf: Fix another potential overflow issue in bpf_prog_linfo Sasha Levin
2020-01-16 16:41 ` [PATCH AUTOSEL 5.4 114/205] libbpf: Make btf__resolve_size logic always check size error condition Sasha Levin
2020-01-16 16:42 ` [PATCH AUTOSEL 5.4 155/205] libbpf: Fix call relocation offset calculation bug Sasha Levin
2020-01-16 16:42 ` [PATCH AUTOSEL 5.4 164/205] bpf: skmsg, fix potential psock NULL pointer dereference Sasha Levin
2020-01-16 16:42 ` Sasha Levin [this message]
2020-01-16 16:42 ` [PATCH AUTOSEL 5.4 179/205] bpf: Support pre-2.25-binutils objcopy for vmlinux BTF Sasha Levin
2020-01-16 16:42 ` [PATCH AUTOSEL 5.4 180/205] libbpf: Fix Makefile' libbpf symbol mismatch diagnostic Sasha Levin
2020-01-16 16:42 ` [PATCH AUTOSEL 5.4 186/205] bpf: Force .BTF section start to zero when dumping from vmlinux Sasha Levin
2020-01-16 16:42 ` [PATCH AUTOSEL 5.4 191/205] samples/bpf: Fix broken xdp_rxq_info due to map order assumptions 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=20200116164300.6705-172-sashal@kernel.org \
    --to=sashal@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=john.fastabend@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=penguin-kernel@I-love.SAKURA.ne.jp \
    --cc=stable@vger.kernel.org \
    --cc=toke@redhat.com \
    /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

BPF Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/bpf/0 bpf/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 bpf bpf/ https://lore.kernel.org/bpf \
		bpf@vger.kernel.org
	public-inbox-index bpf

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.bpf


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git