mptcp/openmptcprouter
1
0
Fork 0
mirror of https://github.com/Ysurac/openmptcprouter.git synced 2025-03-09 15:40:20 +00:00
Code Issues Releases Wiki Activity

Update Linux 5.4 kernel and clean some files

Browse source
This commit is contained in:
Ycarus (Yannick Chabanois) 2022-03-16 20:53:52 +01:00
parent 272324aa1a
commit 0a55523ea5
26 changed files with 870 additions and 4059 deletions
Download patch file Download diff file Expand all files Collapse all files

1650
root/target/linux/generic/backport-5.4/070-v5.5-MIPS-BPF-Restore-MIPS32-cBPF-JIT.patch
View file

File diff suppressed because it is too large Load diff

53
root/target/linux/generic/backport-5.4/097-bpf-fix-integer-overflow-in-arg-calculation.patch
View file

@ -1,53 +0,0 @@
From: Bui Quang Minh @ 2021-01-26 8:26 UTC (permalink / raw)
To: ast, daniel, davem, kuba, hawk, john.fastabend, andrii, kafai,
songliubraving, yhs, kpsingh, jakub, lmb
Cc: netdev, bpf, linux-kernel, minhquangbui99
In 32-bit architecture, the result of sizeof() is a 32-bit integer so
the expression becomes the multiplication between 2 32-bit integer which
can potentially leads to integer overflow. As a result,
bpf_map_area_alloc() allocates less memory than needed.
Fix this by casting 1 operand to u64.
Signed-off-by: Bui Quang Minh <minhquangbui99@gmail.com>
---
kernel/bpf/devmap.c | 4 ++--
net/core/sock_map.c | 2 +-
2 files changed, 3 insertions(+), 3 deletions(-)
Index: linux-5.4.147/kernel/bpf/devmap.c
===================================================================
--- linux-5.4.147.orig/kernel/bpf/devmap.c
+++ linux-5.4.147/kernel/bpf/devmap.c
@@ -94,7 +94,7 @@ static struct hlist_head *dev_map_create
int i;
struct hlist_head *hash;
- hash = bpf_map_area_alloc(entries * sizeof(*hash), numa_node);
+ hash = bpf_map_area_alloc((u64) entries * sizeof(*hash), numa_node);
if (hash != NULL)
for (i = 0; i < entries; i++)
INIT_HLIST_HEAD(&hash[i]);
@@ -159,7 +159,7 @@ static int dev_map_init_map(struct bpf_d
spin_lock_init(&dtab->index_lock);
} else {
- dtab->netdev_map = bpf_map_area_alloc(dtab->map.max_entries *
+ dtab->netdev_map = bpf_map_area_alloc((u64) dtab->map.max_entries *
sizeof(struct bpf_dtab_netdev *),
dtab->map.numa_node);
if (!dtab->netdev_map)
Index: linux-5.4.147/net/core/sock_map.c
===================================================================
--- linux-5.4.147.orig/net/core/sock_map.c
+++ linux-5.4.147/net/core/sock_map.c
@@ -48,7 +48,7 @@ static struct bpf_map *sock_map_alloc(un
if (err)
goto free_stab;
- stab->sks = bpf_map_area_alloc(stab->map.max_entries *
+ stab->sks = bpf_map_area_alloc((u64) stab->map.max_entries *
sizeof(struct sock *),
stab->map.numa_node);
if (stab->sks)

115
root/target/linux/generic/backport-5.4/370-netfilter-nf_flow_table-fix-offloaded-connection-tim.patch
View file

@ -1,115 +0,0 @@
From: Felix Fietkau <nbd@nbd.name>
Date: Wed, 13 Jun 2018 12:33:39 +0200
Subject: [PATCH] netfilter: nf_flow_table: fix offloaded connection timeout
corner case
The full teardown of offloaded flows is deferred to a gc work item,
however processing of packets by netfilter needs to happen immediately
after a teardown is requested, because the conntrack state needs to be
fixed up.
Since the IPS_OFFLOAD_BIT is still kept until the teardown is complete,
the netfilter conntrack gc can accidentally bump the timeout of a
connection where offload was just stopped, causing a conntrack entry
leak.
Fix this by moving the conntrack timeout bumping from conntrack core to
the nf_flow_offload and add a check to prevent bogus timeout bumps.
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1207,18 +1207,6 @@ static bool gc_worker_can_early_drop(con
return false;
}
-#define DAY (86400 * HZ)
-
-/* Set an arbitrary timeout large enough not to ever expire, this save
- * us a check for the IPS_OFFLOAD_BIT from the packet path via
- * nf_ct_is_expired().
- */
-static void nf_ct_offload_timeout(struct nf_conn *ct)
-{
- if (nf_ct_expires(ct) < DAY / 2)
- ct->timeout = nfct_time_stamp + DAY;
-}
-
static void gc_worker(struct work_struct *work)
{
unsigned long end_time = jiffies + GC_SCAN_MAX_DURATION;
@@ -1250,11 +1238,9 @@ static void gc_worker(struct work_struct
tmp = nf_ct_tuplehash_to_ctrack(h);
scanned++;
- if (test_bit(IPS_OFFLOAD_BIT, &tmp->status)) {
- nf_ct_offload_timeout(tmp);
+ if (test_bit(IPS_OFFLOAD_BIT, &tmp->status))
continue;
- }
if (nf_ct_is_expired(tmp)) {
nf_ct_gc_expired(tmp);
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -198,10 +198,29 @@ static const struct rhashtable_params nf
.automatic_shrinking = true,
};
+#define DAY (86400 * HZ)
+
+/* Set an arbitrary timeout large enough not to ever expire, this save
+ * us a check for the IPS_OFFLOAD_BIT from the packet path via
+ * nf_ct_is_expired().
+ */
+static void nf_ct_offload_timeout(struct flow_offload *flow)
+{
+ struct flow_offload_entry *entry;
+ struct nf_conn *ct;
+
+ entry = container_of(flow, struct flow_offload_entry, flow);
+ ct = entry->ct;
+
+ if (nf_ct_expires(ct) < DAY / 2)
+ ct->timeout = nfct_time_stamp + DAY;
+}
+
int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow)
{
int err;
+ nf_ct_offload_timeout(flow);
flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
err = rhashtable_insert_fast(&flow_table->rhashtable,
@@ -304,6 +323,7 @@ nf_flow_table_iterate(struct nf_flowtabl
rhashtable_walk_start(&hti);
while ((tuplehash = rhashtable_walk_next(&hti))) {
+
if (IS_ERR(tuplehash)) {
if (PTR_ERR(tuplehash) != -EAGAIN) {
err = PTR_ERR(tuplehash);
@@ -328,10 +348,17 @@ static void nf_flow_offload_gc_step(stru
{
struct nf_flowtable *flow_table = data;
struct flow_offload_entry *e;
+ bool teardown;
e = container_of(flow, struct flow_offload_entry, flow);
- if (nf_flow_has_expired(flow) || nf_ct_is_dying(e->ct) ||
- (flow->flags & (FLOW_OFFLOAD_DYING | FLOW_OFFLOAD_TEARDOWN)))
+
+ teardown = flow->flags & (FLOW_OFFLOAD_DYING |
+ FLOW_OFFLOAD_TEARDOWN);
+
+ if (!teardown)
+ nf_ct_offload_timeout(flow);
+
+ if (nf_flow_has_expired(flow) || teardown)
flow_offload_del(flow_table, flow);
}

486
root/target/linux/generic/hack-5.4/690-mptcp_v0.96.patch
View file

File diff suppressed because it is too large Load diff

554
root/target/linux/generic/pending-5.4/640-netfilter-nf_flow_table-add-hardware-offload-support.patch Normal file
View file

@ -0,0 +1,554 @@
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 11 Jan 2018 16:32:00 +0100
Subject: [PATCH] netfilter: nf_flow_table: add hardware offload support
This patch adds the infrastructure to offload flows to hardware, in case
the nic/switch comes with built-in flow tables capabilities.
If the hardware comes with no hardware flow tables or they have
limitations in terms of features, the existing infrastructure falls back
to the software flow table implementation.
The software flow table garbage collector skips entries that resides in
the hardware, so the hardware will be responsible for releasing this
flow table entry too via flow_offload_dead().
Hardware configuration, either to add or to delete entries, is done from
the hardware offload workqueue, to ensure this is done from user context
given that we may sleep when grabbing the mdio mutex.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
create mode 100644 net/netfilter/nf_flow_table_hw.c
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -922,6 +922,13 @@ struct devlink;
struct tlsdev_ops;
+struct flow_offload;
+
+enum flow_offload_type {
+ FLOW_OFFLOAD_ADD = 0,
+ FLOW_OFFLOAD_DEL,
+};
+
/*
* This structure defines the management hooks for network devices.
* The following hooks can be defined; unless noted otherwise, they are
@@ -1154,6 +1161,10 @@ struct tlsdev_ops;
* int (*ndo_bridge_dellink)(struct net_device *dev, struct nlmsghdr *nlh,
* u16 flags);
*
+ * int (*ndo_flow_offload)(enum flow_offload_type type,
+ * struct flow_offload *flow);
+ * Adds/deletes flow entry to/from net device flowtable.
+ *
* int (*ndo_change_carrier)(struct net_device *dev, bool new_carrier);
* Called to change device carrier. Soft-devices (like dummy, team, etc)
* which do not represent real hardware may define this to allow their
@@ -1401,6 +1412,8 @@ struct net_device_ops {
int (*ndo_bridge_dellink)(struct net_device *dev,
struct nlmsghdr *nlh,
u16 flags);
+ int (*ndo_flow_offload)(enum flow_offload_type type,
+ struct flow_offload *flow);
int (*ndo_change_carrier)(struct net_device *dev,
bool new_carrier);
int (*ndo_get_phys_port_id)(struct net_device *dev,
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -21,11 +21,17 @@ struct nf_flowtable_type {
struct module *owner;
};
+enum nf_flowtable_flags {
+ NF_FLOWTABLE_F_HW = 0x1,
+};
+
struct nf_flowtable {
struct list_head list;
struct rhashtable rhashtable;
const struct nf_flowtable_type *type;
+ u32 flags;
struct delayed_work gc_work;
+ possible_net_t ft_net;
};
enum flow_offload_tuple_dir {
@@ -68,6 +74,7 @@ struct flow_offload_tuple_rhash {
#define FLOW_OFFLOAD_DNAT 0x2
#define FLOW_OFFLOAD_DYING 0x4
#define FLOW_OFFLOAD_TEARDOWN 0x8
+#define FLOW_OFFLOAD_HW 0x10
struct flow_offload {
struct flow_offload_tuple_rhash tuplehash[FLOW_OFFLOAD_DIR_MAX];
@@ -120,6 +127,22 @@ unsigned int nf_flow_offload_ip_hook(voi
unsigned int nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state);
+void nf_flow_offload_hw_add(struct net *net, struct flow_offload *flow,
+ struct nf_conn *ct);
+void nf_flow_offload_hw_del(struct net *net, struct flow_offload *flow);
+
+struct nf_flow_table_hw {
+ struct module *owner;
+ void (*add)(struct net *net, struct flow_offload *flow,
+ struct nf_conn *ct);
+ void (*del)(struct net *net, struct flow_offload *flow);
+};
+
+int nf_flow_table_hw_register(const struct nf_flow_table_hw *offload);
+void nf_flow_table_hw_unregister(const struct nf_flow_table_hw *offload);
+
+extern struct work_struct nf_flow_offload_hw_work;
+
#define MODULE_ALIAS_NF_FLOWTABLE(family) \
MODULE_ALIAS("nf-flowtable-" __stringify(family))
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -1516,6 +1516,7 @@ enum nft_object_attributes {
* @NFTA_FLOWTABLE_HOOK: netfilter hook configuration(NLA_U32)
* @NFTA_FLOWTABLE_USE: number of references to this flow table (NLA_U32)
* @NFTA_FLOWTABLE_HANDLE: object handle (NLA_U64)
+ * @NFTA_FLOWTABLE_FLAGS: flags (NLA_U32)
*/
enum nft_flowtable_attributes {
NFTA_FLOWTABLE_UNSPEC,
@@ -1525,6 +1526,7 @@ enum nft_flowtable_attributes {
NFTA_FLOWTABLE_USE,
NFTA_FLOWTABLE_HANDLE,
NFTA_FLOWTABLE_PAD,
+ NFTA_FLOWTABLE_FLAGS,
__NFTA_FLOWTABLE_MAX
};
#define NFTA_FLOWTABLE_MAX (__NFTA_FLOWTABLE_MAX - 1)
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -711,6 +711,15 @@ config NF_FLOW_TABLE
To compile it as a module, choose M here.
+config NF_FLOW_TABLE_HW
+ tristate "Netfilter flow table hardware offload module"
+ depends on NF_FLOW_TABLE
+ help
+ This option adds hardware offload support for the flow table core
+ infrastructure.
+
+ To compile it as a module, choose M here.
+
config NETFILTER_XTABLES
tristate "Netfilter Xtables support (required for ip_tables)"
default m if NETFILTER_ADVANCED=n
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -123,6 +123,7 @@ obj-$(CONFIG_NF_FLOW_TABLE) += nf_flow_t
nf_flow_table-objs := nf_flow_table_core.o nf_flow_table_ip.o
obj-$(CONFIG_NF_FLOW_TABLE_INET) += nf_flow_table_inet.o
+obj-$(CONFIG_NF_FLOW_TABLE_HW) += nf_flow_table_hw.o
# generic X tables
obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -248,10 +248,16 @@ static inline bool nf_flow_has_expired(c
return nf_flow_timeout_delta(flow->timeout) <= 0;
}
+static inline bool nf_flow_in_hw(const struct flow_offload *flow)
+{
+ return flow->flags & FLOW_OFFLOAD_HW;
+}
+
static void flow_offload_del(struct nf_flowtable *flow_table,
struct flow_offload *flow)
{
struct flow_offload_entry *e;
+ struct net *net = read_pnet(&flow_table->ft_net);
rhashtable_remove_fast(&flow_table->rhashtable,
&flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].node,
@@ -271,6 +277,9 @@ static void flow_offload_del(struct nf_f
if (!(flow->flags & FLOW_OFFLOAD_TEARDOWN))
flow_offload_fixup_ct_state(e->ct);
+ if (nf_flow_in_hw(flow))
+ nf_flow_offload_hw_del(net, flow);
+
flow_offload_free(flow);
}
@@ -490,10 +502,43 @@ int nf_flow_dnat_port(const struct flow_
}
EXPORT_SYMBOL_GPL(nf_flow_dnat_port);
+static const struct nf_flow_table_hw __rcu *nf_flow_table_hw_hook __read_mostly;
+
+static int nf_flow_offload_hw_init(struct nf_flowtable *flow_table)
+{
+ const struct nf_flow_table_hw *offload;
+
+ if (!rcu_access_pointer(nf_flow_table_hw_hook))
+ request_module("nf-flow-table-hw");
+
+ rcu_read_lock();
+ offload = rcu_dereference(nf_flow_table_hw_hook);
+ if (!offload)
+ goto err_no_hw_offload;
+
+ if (!try_module_get(offload->owner))
+ goto err_no_hw_offload;
+
+ rcu_read_unlock();
+
+ return 0;
+
+err_no_hw_offload:
+ rcu_read_unlock();
+
+ return -EOPNOTSUPP;
+}
+
int nf_flow_table_init(struct nf_flowtable *flowtable)
{
int err;
+ if (flowtable->flags & NF_FLOWTABLE_F_HW) {
+ err = nf_flow_offload_hw_init(flowtable);
+ if (err)
+ return err;
+ }
+
INIT_DEFERRABLE_WORK(&flowtable->gc_work, nf_flow_offload_work_gc);
err = rhashtable_init(&flowtable->rhashtable,
@@ -534,6 +579,8 @@ static void nf_flow_table_iterate_cleanu
{
nf_flow_table_iterate(flowtable, nf_flow_table_do_cleanup, dev);
flush_delayed_work(&flowtable->gc_work);
+ if (flowtable->flags & NF_FLOWTABLE_F_HW)
+ flush_work(&nf_flow_offload_hw_work);
}
void nf_flow_table_cleanup(struct net_device *dev)
@@ -547,6 +594,26 @@ void nf_flow_table_cleanup(struct net_de
}
EXPORT_SYMBOL_GPL(nf_flow_table_cleanup);
+struct work_struct nf_flow_offload_hw_work;
+EXPORT_SYMBOL_GPL(nf_flow_offload_hw_work);
+
+/* Give the hardware workqueue the chance to remove entries from hardware.*/
+static void nf_flow_offload_hw_free(struct nf_flowtable *flowtable)
+{
+ const struct nf_flow_table_hw *offload;
+
+ flush_work(&nf_flow_offload_hw_work);
+
+ rcu_read_lock();
+ offload = rcu_dereference(nf_flow_table_hw_hook);
+ if (!offload) {
+ rcu_read_unlock();
+ return;
+ }
+ module_put(offload->owner);
+ rcu_read_unlock();
+}
+
void nf_flow_table_free(struct nf_flowtable *flow_table)
{
mutex_lock(&flowtable_lock);
@@ -556,9 +623,58 @@ void nf_flow_table_free(struct nf_flowta
nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL);
nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, flow_table);
rhashtable_destroy(&flow_table->rhashtable);
+ if (flow_table->flags & NF_FLOWTABLE_F_HW)
+ nf_flow_offload_hw_free(flow_table);
}
EXPORT_SYMBOL_GPL(nf_flow_table_free);
+/* Must be called from user context. */
+void nf_flow_offload_hw_add(struct net *net, struct flow_offload *flow,
+ struct nf_conn *ct)
+{
+ const struct nf_flow_table_hw *offload;
+
+ rcu_read_lock();
+ offload = rcu_dereference(nf_flow_table_hw_hook);
+ if (offload)
+ offload->add(net, flow, ct);
+ rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(nf_flow_offload_hw_add);
+
+/* Must be called from user context. */
+void nf_flow_offload_hw_del(struct net *net, struct flow_offload *flow)
+{
+ const struct nf_flow_table_hw *offload;
+
+ rcu_read_lock();
+ offload = rcu_dereference(nf_flow_table_hw_hook);
+ if (offload)
+ offload->del(net, flow);
+ rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(nf_flow_offload_hw_del);
+
+int nf_flow_table_hw_register(const struct nf_flow_table_hw *offload)
+{
+ if (rcu_access_pointer(nf_flow_table_hw_hook))
+ return -EBUSY;
+
+ rcu_assign_pointer(nf_flow_table_hw_hook, offload);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(nf_flow_table_hw_register);
+
+void nf_flow_table_hw_unregister(const struct nf_flow_table_hw *offload)
+{
+ WARN_ON(rcu_access_pointer(nf_flow_table_hw_hook) != offload);
+ rcu_assign_pointer(nf_flow_table_hw_hook, NULL);
+
+ synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(nf_flow_table_hw_unregister);
+
static int nf_flow_table_netdev_event(struct notifier_block *this,
unsigned long event, void *ptr)
{
--- /dev/null
+++ b/net/netfilter/nf_flow_table_hw.c
@@ -0,0 +1,169 @@
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netfilter.h>
+#include <linux/rhashtable.h>
+#include <linux/netdevice.h>
+#include <net/netfilter/nf_flow_table.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_tuple.h>
+
+static DEFINE_SPINLOCK(flow_offload_hw_pending_list_lock);
+static LIST_HEAD(flow_offload_hw_pending_list);
+
+static DEFINE_MUTEX(nf_flow_offload_hw_mutex);
+
+struct flow_offload_hw {
+ struct list_head list;
+ enum flow_offload_type type;
+ struct flow_offload *flow;
+ struct nf_conn *ct;
+ possible_net_t flow_hw_net;
+};
+
+static int do_flow_offload_hw(struct net *net, struct flow_offload *flow,
+ int type)
+{
+ struct net_device *indev;
+ int ret, ifindex;
+
+ ifindex = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.iifidx;
+ indev = dev_get_by_index(net, ifindex);
+ if (WARN_ON(!indev))
+ return 0;
+
+ mutex_lock(&nf_flow_offload_hw_mutex);
+ ret = indev->netdev_ops->ndo_flow_offload(type, flow);
+ mutex_unlock(&nf_flow_offload_hw_mutex);
+
+ dev_put(indev);
+
+ return ret;
+}
+
+static void flow_offload_hw_work_add(struct flow_offload_hw *offload)
+{
+ struct net *net;
+ int ret;
+
+ if (nf_ct_is_dying(offload->ct))
+ return;
+
+ net = read_pnet(&offload->flow_hw_net);
+ ret = do_flow_offload_hw(net, offload->flow, FLOW_OFFLOAD_ADD);
+ if (ret >= 0)
+ offload->flow->flags |= FLOW_OFFLOAD_HW;
+}
+
+static void flow_offload_hw_work_del(struct flow_offload_hw *offload)
+{
+ struct net *net = read_pnet(&offload->flow_hw_net);
+
+ do_flow_offload_hw(net, offload->flow, FLOW_OFFLOAD_DEL);
+}
+
+static void flow_offload_hw_work(struct work_struct *work)
+{
+ struct flow_offload_hw *offload, *next;
+ LIST_HEAD(hw_offload_pending);
+
+ spin_lock_bh(&flow_offload_hw_pending_list_lock);
+ list_replace_init(&flow_offload_hw_pending_list, &hw_offload_pending);
+ spin_unlock_bh(&flow_offload_hw_pending_list_lock);
+
+ list_for_each_entry_safe(offload, next, &hw_offload_pending, list) {
+ switch (offload->type) {
+ case FLOW_OFFLOAD_ADD:
+ flow_offload_hw_work_add(offload);
+ break;
+ case FLOW_OFFLOAD_DEL:
+ flow_offload_hw_work_del(offload);
+ break;
+ }
+ if (offload->ct)
+ nf_conntrack_put(&offload->ct->ct_general);
+ list_del(&offload->list);
+ kfree(offload);
+ }
+}
+
+static void flow_offload_queue_work(struct flow_offload_hw *offload)
+{
+ spin_lock_bh(&flow_offload_hw_pending_list_lock);
+ list_add_tail(&offload->list, &flow_offload_hw_pending_list);
+ spin_unlock_bh(&flow_offload_hw_pending_list_lock);
+
+ schedule_work(&nf_flow_offload_hw_work);
+}
+
+static void flow_offload_hw_add(struct net *net, struct flow_offload *flow,
+ struct nf_conn *ct)
+{
+ struct flow_offload_hw *offload;
+
+ offload = kmalloc(sizeof(struct flow_offload_hw), GFP_ATOMIC);
+ if (!offload)
+ return;
+
+ nf_conntrack_get(&ct->ct_general);
+ offload->type = FLOW_OFFLOAD_ADD;
+ offload->ct = ct;
+ offload->flow = flow;
+ write_pnet(&offload->flow_hw_net, net);
+
+ flow_offload_queue_work(offload);
+}
+
+static void flow_offload_hw_del(struct net *net, struct flow_offload *flow)
+{
+ struct flow_offload_hw *offload;
+
+ offload = kmalloc(sizeof(struct flow_offload_hw), GFP_ATOMIC);
+ if (!offload)
+ return;
+
+ offload->type = FLOW_OFFLOAD_DEL;
+ offload->ct = NULL;
+ offload->flow = flow;
+ write_pnet(&offload->flow_hw_net, net);
+
+ flow_offload_queue_work(offload);
+}
+
+static const struct nf_flow_table_hw flow_offload_hw = {
+ .add = flow_offload_hw_add,
+ .del = flow_offload_hw_del,
+ .owner = THIS_MODULE,
+};
+
+static int __init nf_flow_table_hw_module_init(void)
+{
+ INIT_WORK(&nf_flow_offload_hw_work, flow_offload_hw_work);
+ nf_flow_table_hw_register(&flow_offload_hw);
+
+ return 0;
+}
+
+static void __exit nf_flow_table_hw_module_exit(void)
+{
+ struct flow_offload_hw *offload, *next;
+ LIST_HEAD(hw_offload_pending);
+
+ nf_flow_table_hw_unregister(&flow_offload_hw);
+ cancel_work_sync(&nf_flow_offload_hw_work);
+
+ list_for_each_entry_safe(offload, next, &hw_offload_pending, list) {
+ if (offload->ct)
+ nf_conntrack_put(&offload->ct->ct_general);
+ list_del(&offload->list);
+ kfree(offload);
+ }
+}
+
+module_init(nf_flow_table_hw_module_init);
+module_exit(nf_flow_table_hw_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
+MODULE_ALIAS("nf-flow-table-hw");
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -5743,6 +5743,13 @@ static int nf_tables_flowtable_parse_hoo
if (err < 0)
return err;
+ for (i = 0; i < n; i++) {
+ if (flowtable->data.flags & NF_FLOWTABLE_F_HW &&
+ !dev_array[i]->netdev_ops->ndo_flow_offload) {
+ return -EOPNOTSUPP;
+ }
+ }
+
ops = kcalloc(n, sizeof(struct nf_hook_ops), GFP_KERNEL);
if (!ops)
return -ENOMEM;
@@ -5873,10 +5880,19 @@ static int nf_tables_newflowtable(struct
}
flowtable->data.type = type;
+ write_pnet(&flowtable->data.ft_net, net);
+
err = type->init(&flowtable->data);
if (err < 0)
goto err3;
+ if (nla[NFTA_FLOWTABLE_FLAGS]) {
+ flowtable->data.flags =
+ ntohl(nla_get_be32(nla[NFTA_FLOWTABLE_FLAGS]));
+ if (flowtable->data.flags & ~NF_FLOWTABLE_F_HW)
+ goto err4;
+ }
+
err = nf_tables_flowtable_parse_hook(&ctx, nla[NFTA_FLOWTABLE_HOOK],
flowtable);
if (err < 0)
@@ -6002,7 +6018,8 @@ static int nf_tables_fill_flowtable_info
nla_put_string(skb, NFTA_FLOWTABLE_NAME, flowtable->name) ||
nla_put_be32(skb, NFTA_FLOWTABLE_USE, htonl(flowtable->use)) ||
nla_put_be64(skb, NFTA_FLOWTABLE_HANDLE, cpu_to_be64(flowtable->handle),
- NFTA_FLOWTABLE_PAD))
+ NFTA_FLOWTABLE_PAD) ||
+ nla_put_be32(skb, NFTA_FLOWTABLE_FLAGS, htonl(flowtable->data.flags)))
goto nla_put_failure;
nest = nla_nest_start_noflag(skb, NFTA_FLOWTABLE_HOOK);
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -128,6 +128,9 @@ static void nft_flow_offload_eval(const
if (ret < 0)
goto err_flow_add;
+ if (flowtable->flags & NF_FLOWTABLE_F_HW)
+ nf_flow_offload_hw_add(nft_net(pkt), flow, ct);
+
dst_release(route.tuple[!dir].dst);
return;

344
root/target/linux/generic/pending-5.4/690-net-add-support-for-threaded-NAPI-polling.patch
View file

@ -1,344 +0,0 @@
From: Felix Fietkau <nbd@nbd.name>
Date: Sun, 26 Jul 2020 14:03:21 +0200
Subject: [PATCH] net: add support for threaded NAPI polling
For some drivers (especially 802.11 drivers), doing a lot of work in the NAPI
poll function does not perform well. Since NAPI poll is bound to the CPU it
was scheduled from, we can easily end up with a few very busy CPUs spending
most of their time in softirq/ksoftirqd and some idle ones.
Introduce threaded NAPI for such drivers based on a workqueue. The API is the
same except for using netif_threaded_napi_add instead of netif_napi_add.
In my tests with mt76 on MT7621 using threaded NAPI + a thread for tx scheduling
improves LAN->WLAN bridging throughput by 10-50%. Throughput without threaded
NAPI is wildly inconsistent, depending on the CPU that runs the tx scheduling
thread.
With threaded NAPI it seems stable and consistent (and higher than the best
results I got without it).
Based on a patch by Hillf Danton
Cc: Hillf Danton <hdanton@sina.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -340,6 +340,7 @@ struct napi_struct {
struct list_head dev_list;
struct hlist_node napi_hash_node;
unsigned int napi_id;
+ struct work_struct work;
};
enum {
@@ -350,6 +351,7 @@ enum {
NAPI_STATE_HASHED, /* In NAPI hash (busy polling possible) */
NAPI_STATE_NO_BUSY_POLL,/* Do not add in napi_hash, no busy polling */
NAPI_STATE_IN_BUSY_POLL,/* sk_busy_loop() owns this NAPI */
+ NAPI_STATE_THREADED, /* Use threaded NAPI */
};
enum {
@@ -360,6 +362,7 @@ enum {
NAPIF_STATE_HASHED = BIT(NAPI_STATE_HASHED),
NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL),
NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL),
+ NAPIF_STATE_THREADED = BIT(NAPI_STATE_THREADED),
};
enum gro_result {
@@ -2101,6 +2104,7 @@ struct net_device {
struct lock_class_key addr_list_lock_key;
bool proto_down;
unsigned wol_enabled:1;
+ unsigned threaded:1;
};
#define to_net_dev(d) container_of(d, struct net_device, dev)
@@ -2281,6 +2285,26 @@ void netif_napi_add(struct net_device *d
int (*poll)(struct napi_struct *, int), int weight);
/**
+ * netif_threaded_napi_add - initialize a NAPI context
+ * @dev: network device
+ * @napi: NAPI context
+ * @poll: polling function
+ * @weight: default weight
+ *
+ * This variant of netif_napi_add() should be used from drivers using NAPI
+ * with CPU intensive poll functions.
+ * This will schedule polling from a high priority workqueue
+ */
+static inline void netif_threaded_napi_add(struct net_device *dev,
+ struct napi_struct *napi,
+ int (*poll)(struct napi_struct *, int),
+ int weight)
+{
+ set_bit(NAPI_STATE_THREADED, &napi->state);
+ netif_napi_add(dev, napi, poll, weight);
+}
+
+/**
* netif_tx_napi_add - initialize a NAPI context
* @dev: network device
* @napi: NAPI context
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -156,6 +156,7 @@ static DEFINE_SPINLOCK(offload_lock);
struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
struct list_head ptype_all __read_mostly; /* Taps */
static struct list_head offload_base __read_mostly;
+static struct workqueue_struct *napi_workq __read_mostly;
static int netif_rx_internal(struct sk_buff *skb);
static int call_netdevice_notifiers_info(unsigned long val,
@@ -5931,6 +5932,11 @@ void __napi_schedule(struct napi_struct
{
unsigned long flags;
+ if (test_bit(NAPI_STATE_THREADED, &n->state)) {
+ queue_work(napi_workq, &n->work);
+ return;
+ }
+
local_irq_save(flags);
____napi_schedule(this_cpu_ptr(&softnet_data), n);
local_irq_restore(flags);
@@ -6246,9 +6256,89 @@ static void init_gro_hash(struct napi_st
napi->gro_bitmask = 0;
}
+static int __napi_poll(struct napi_struct *n, bool *repoll)
+{
+ int work, weight;
+
+ weight = n->weight;
+
+ /* This NAPI_STATE_SCHED test is for avoiding a race
+ * with netpoll's poll_napi(). Only the entity which
+ * obtains the lock and sees NAPI_STATE_SCHED set will
+ * actually make the ->poll() call. Therefore we avoid
+ * accidentally calling ->poll() when NAPI is not scheduled.
+ */
+ work = 0;
+ if (test_bit(NAPI_STATE_SCHED, &n->state)) {
+ work = n->poll(n, weight);
+ trace_napi_poll(n, work, weight);
+ }
+
+ WARN_ON_ONCE(work > weight);
+
+ if (likely(work < weight))
+ return work;
+
+ /* Drivers must not modify the NAPI state if they
+ * consume the entire weight. In such cases this code
+ * still "owns" the NAPI instance and therefore can
+ * move the instance around on the list at-will.
+ */
+ if (unlikely(napi_disable_pending(n))) {
+ napi_complete(n);
+ return work;
+ }
+
+ if (n->gro_bitmask) {
+ /* flush too old packets
+ * If HZ < 1000, flush all packets.
+ */
+ napi_gro_flush(n, HZ >= 1000);
+ }
+
+ gro_normal_list(n);
+
+ *repoll = true;
+
+ return work;
+}
+
+static void napi_workfn(struct work_struct *work)
+{
+ struct napi_struct *n = container_of(work, struct napi_struct, work);
+ void *have;
+
+ for (;;) {
+ bool repoll = false;
+
+ local_bh_disable();
+
+ have = netpoll_poll_lock(n);
+ __napi_poll(n, &repoll);
+ netpoll_poll_unlock(have);
+
+ local_bh_enable();
+
+ if (!repoll)
+ return;
+
+ if (!need_resched())
+ continue;
+
+ /*
+ * have to pay for the latency of task switch even if
+ * napi is scheduled
+ */
+ queue_work(napi_workq, work);
+ return;
+ }
+}
+
void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
int (*poll)(struct napi_struct *, int), int weight)
{
+ if (dev->threaded)
+ set_bit(NAPI_STATE_THREADED, &napi->state);
INIT_LIST_HEAD(&napi->poll_list);
hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
napi->timer.function = napi_watchdog;
@@ -6265,6 +6355,7 @@ void netif_napi_add(struct net_device *d
#ifdef CONFIG_NETPOLL
napi->poll_owner = -1;
#endif
+ INIT_WORK(&napi->work, napi_workfn);
set_bit(NAPI_STATE_SCHED, &napi->state);
set_bit(NAPI_STATE_NPSVC, &napi->state);
list_add_rcu(&napi->dev_list, &dev->napi_list);
@@ -6305,6 +6396,7 @@ static void flush_gro_hash(struct napi_s
void netif_napi_del(struct napi_struct *napi)
{
might_sleep();
+ cancel_work_sync(&napi->work);
if (napi_hash_del(napi))
synchronize_net();
list_del_init(&napi->dev_list);
@@ -6317,50 +6409,18 @@ EXPORT_SYMBOL(netif_napi_del);
static int napi_poll(struct napi_struct *n, struct list_head *repoll)
{
+ bool do_repoll = false;
void *have;
- int work, weight;
+ int work;
list_del_init(&n->poll_list);
have = netpoll_poll_lock(n);
- weight = n->weight;
-
- /* This NAPI_STATE_SCHED test is for avoiding a race
- * with netpoll's poll_napi(). Only the entity which
- * obtains the lock and sees NAPI_STATE_SCHED set will
- * actually make the ->poll() call. Therefore we avoid
- * accidentally calling ->poll() when NAPI is not scheduled.
- */
- work = 0;
- if (test_bit(NAPI_STATE_SCHED, &n->state)) {
- work = n->poll(n, weight);
- trace_napi_poll(n, work, weight);
- }
-
- WARN_ON_ONCE(work > weight);
+ work = __napi_poll(n, &do_repoll);
- if (likely(work < weight))
- goto out_unlock;
-
- /* Drivers must not modify the NAPI state if they
- * consume the entire weight. In such cases this code
- * still "owns" the NAPI instance and therefore can
- * move the instance around on the list at-will.
- */
- if (unlikely(napi_disable_pending(n))) {
- napi_complete(n);
+ if (!do_repoll)
goto out_unlock;
- }
-
- if (n->gro_bitmask) {
- /* flush too old packets
- * If HZ < 1000, flush all packets.
- */
- napi_gro_flush(n, HZ >= 1000);
- }
-
- gro_normal_list(n);
/* Some drivers may have called napi_schedule
* prior to exhausting their budget.
@@ -10340,6 +10400,10 @@ static int __init net_dev_init(void)
sd->backlog.weight = weight_p;
}
+ napi_workq = alloc_workqueue("napi_workq", WQ_UNBOUND | WQ_HIGHPRI,
+ WQ_UNBOUND_MAX_ACTIVE | WQ_SYSFS);
+ BUG_ON(!napi_workq);
+
dev_boot_phase = 0;
/* The loopback device is special if any other network devices
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -442,6 +442,52 @@ static ssize_t proto_down_store(struct d
}
NETDEVICE_SHOW_RW(proto_down, fmt_dec);
+static int change_napi_threaded(struct net_device *dev, unsigned long val)
+{
+ struct napi_struct *napi;
+
+ if (list_empty(&dev->napi_list))
+ return -EOPNOTSUPP;
+
+ list_for_each_entry(napi, &dev->napi_list, dev_list) {
+ if (val)
+ set_bit(NAPI_STATE_THREADED, &napi->state);
+ else
+ clear_bit(NAPI_STATE_THREADED, &napi->state);
+ }
+
+ return 0;
+}
+
+static ssize_t napi_threaded_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t len)
+{
+ return netdev_store(dev, attr, buf, len, change_napi_threaded);
+}
+
+static ssize_t napi_threaded_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct net_device *netdev = to_net_dev(dev);
+ struct napi_struct *napi;
+ bool enabled = false;
+
+ if (!rtnl_trylock())
+ return restart_syscall();
+
+ list_for_each_entry(napi, &netdev->napi_list, dev_list) {
+ if (test_bit(NAPI_STATE_THREADED, &napi->state))
+ enabled = true;
+ }
+
+ rtnl_unlock();
+
+ return sprintf(buf, fmt_dec, enabled);
+}
+static DEVICE_ATTR_RW(napi_threaded);
+
static ssize_t phys_port_id_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
@@ -532,6 +578,7 @@ static struct attribute *net_class_attrs
&dev_attr_flags.attr,
&dev_attr_tx_queue_len.attr,
&dev_attr_gro_flush_timeout.attr,
+ &dev_attr_napi_threaded.attr,
&dev_attr_phys_port_id.attr,
&dev_attr_phys_port_name.attr,
&dev_attr_phys_switch_id.attr,

57
root/target/linux/generic/pending-5.4/999-fix-oeoverflow-ipheth.patch
View file

@ -1,57 +0,0 @@
From 63e4b45c82ed1bde979da7052229a4229ce9cabf Mon Sep 17 00:00:00 2001
From: Georgi Valkov <gvalkov@abv.bg>
Date: Tue, 1 Feb 2022 08:16:18 +0100
Subject: ipheth: fix EOVERFLOW in ipheth_rcvbulk_callback
When rx_buf is allocated we need to account for IPHETH_IP_ALIGN,
which reduces the usable size by 2 bytes. Otherwise we have 1512
bytes usable instead of 1514, and if we receive more than 1512
bytes, ipheth_rcvbulk_callback is called with status -EOVERFLOW,
after which the driver malfunctiones and all communication stops.
Resolves ipheth 2-1:4.2: ipheth_rcvbulk_callback: urb status: -75
Fixes: f33d9e2b48a3 ("usbnet: ipheth: fix connectivity with iOS 14")
Signed-off-by: Georgi Valkov <gvalkov@abv.bg>
Tested-by: Jan Kiszka <jan.kiszka@siemens.com>
Link: https://lore.kernel.org/all/B60B8A4B-92A0-49B3-805D-809A2433B46C@abv.bg/
Link: https://lore.kernel.org/all/24851bd2769434a5fc24730dce8e8a984c5a4505.1643699778.git.jan.kiszka@siemens.com/
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/usb/ipheth.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c
index cd33955df0b65f..6a769df0b4213c 100644
--- a/drivers/net/usb/ipheth.c
+++ b/drivers/net/usb/ipheth.c
@@ -121,7 +121,7 @@ static int ipheth_alloc_urbs(struct ipheth_device *iphone)
if (tx_buf == NULL)
goto free_rx_urb;
- rx_buf = usb_alloc_coherent(iphone->udev, IPHETH_BUF_SIZE,
+ rx_buf = usb_alloc_coherent(iphone->udev, IPHETH_BUF_SIZE + IPHETH_IP_ALIGN,
GFP_KERNEL, &rx_urb->transfer_dma);
if (rx_buf == NULL)
goto free_tx_buf;
@@ -146,7 +146,7 @@ error_nomem:
static void ipheth_free_urbs(struct ipheth_device *iphone)
{
- usb_free_coherent(iphone->udev, IPHETH_BUF_SIZE, iphone->rx_buf,
+ usb_free_coherent(iphone->udev, IPHETH_BUF_SIZE + IPHETH_IP_ALIGN, iphone->rx_buf,
iphone->rx_urb->transfer_dma);
usb_free_coherent(iphone->udev, IPHETH_BUF_SIZE, iphone->tx_buf,
iphone->tx_urb->transfer_dma);
@@ -317,7 +317,7 @@ static int ipheth_rx_submit(struct ipheth_device *dev, gfp_t mem_flags)
usb_fill_bulk_urb(dev->rx_urb, udev,
usb_rcvbulkpipe(udev, dev->bulk_in),
- dev->rx_buf, IPHETH_BUF_SIZE,
+ dev->rx_buf, IPHETH_BUF_SIZE + IPHETH_IP_ALIGN,
ipheth_rcvbulk_callback,
dev);
dev->rx_urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
--
cgit