net: sched: conditionally obtain rtnl lock in cls hw offloads API

In order to remove dependency on rtnl lock from offloads code of
classifiers, take rtnl lock conditionally before executing driver
callbacks. Only obtain rtnl lock if block is bound to devices that require
it.

Block bind/unbind code is rtnl-locked and obtains block->cb_lock while
holding rtnl lock. Obtain locks in same order in tc_setup_cb_*() functions
to prevent deadlock.

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 1a39779..3c103cf 100644 (file)
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -3076,11 +3076,28 @@ __tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type,
 int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type,
                     void *type_data, bool err_stop, bool rtnl_held)
 {
+       bool take_rtnl = READ_ONCE(block->lockeddevcnt) && !rtnl_held;
        int ok_count;
 
+retry:
+       if (take_rtnl)
+               rtnl_lock();
        down_read(&block->cb_lock);
+       /* Need to obtain rtnl lock if block is bound to devs that require it.
+        * In block bind code cb_lock is obtained while holding rtnl, so we must
+        * obtain the locks in same order here.
+        */
+       if (!rtnl_held && !take_rtnl && block->lockeddevcnt) {
+               up_read(&block->cb_lock);
+               take_rtnl = true;
+               goto retry;
+       }
+
        ok_count = __tc_setup_cb_call(block, type, type_data, err_stop);
+
        up_read(&block->cb_lock);
+       if (take_rtnl)
+               rtnl_unlock();
        return ok_count;
 }
 EXPORT_SYMBOL(tc_setup_cb_call);
@@ -3095,9 +3112,23 @@ int tc_setup_cb_add(struct tcf_block *block, struct tcf_proto *tp,
                    enum tc_setup_type type, void *type_data, bool err_stop,
                    u32 *flags, unsigned int *in_hw_count, bool rtnl_held)
 {
+       bool take_rtnl = READ_ONCE(block->lockeddevcnt) && !rtnl_held;
        int ok_count;
 
+retry:
+       if (take_rtnl)
+               rtnl_lock();
        down_read(&block->cb_lock);
+       /* Need to obtain rtnl lock if block is bound to devs that require it.
+        * In block bind code cb_lock is obtained while holding rtnl, so we must
+        * obtain the locks in same order here.
+        */
+       if (!rtnl_held && !take_rtnl && block->lockeddevcnt) {
+               up_read(&block->cb_lock);
+               take_rtnl = true;
+               goto retry;
+       }
+
        /* Make sure all netdevs sharing this block are offload-capable. */
        if (block->nooffloaddevcnt && err_stop) {
                ok_count = -EOPNOTSUPP;
@@ -3115,6 +3146,8 @@ int tc_setup_cb_add(struct tcf_block *block, struct tcf_proto *tp,
                                          ok_count, true);
 err_unlock:
        up_read(&block->cb_lock);
+       if (take_rtnl)
+               rtnl_unlock();
        return ok_count < 0 ? ok_count : 0;
 }
 EXPORT_SYMBOL(tc_setup_cb_add);
@@ -3131,9 +3164,23 @@ int tc_setup_cb_replace(struct tcf_block *block, struct tcf_proto *tp,
                        u32 *new_flags, unsigned int *new_in_hw_count,
                        bool rtnl_held)
 {
+       bool take_rtnl = READ_ONCE(block->lockeddevcnt) && !rtnl_held;
        int ok_count;
 
+retry:
+       if (take_rtnl)
+               rtnl_lock();
        down_read(&block->cb_lock);
+       /* Need to obtain rtnl lock if block is bound to devs that require it.
+        * In block bind code cb_lock is obtained while holding rtnl, so we must
+        * obtain the locks in same order here.
+        */
+       if (!rtnl_held && !take_rtnl && block->lockeddevcnt) {
+               up_read(&block->cb_lock);
+               take_rtnl = true;
+               goto retry;
+       }
+
        /* Make sure all netdevs sharing this block are offload-capable. */
        if (block->nooffloaddevcnt && err_stop) {
                ok_count = -EOPNOTSUPP;
@@ -3155,6 +3202,8 @@ int tc_setup_cb_replace(struct tcf_block *block, struct tcf_proto *tp,
                                          new_flags, ok_count, true);
 err_unlock:
        up_read(&block->cb_lock);
+       if (take_rtnl)
+               rtnl_unlock();
        return ok_count < 0 ? ok_count : 0;
 }
 EXPORT_SYMBOL(tc_setup_cb_replace);
@@ -3167,9 +3216,23 @@ int tc_setup_cb_destroy(struct tcf_block *block, struct tcf_proto *tp,
                        enum tc_setup_type type, void *type_data, bool err_stop,
                        u32 *flags, unsigned int *in_hw_count, bool rtnl_held)
 {
+       bool take_rtnl = READ_ONCE(block->lockeddevcnt) && !rtnl_held;
        int ok_count;
 
+retry:
+       if (take_rtnl)
+               rtnl_lock();
        down_read(&block->cb_lock);
+       /* Need to obtain rtnl lock if block is bound to devs that require it.
+        * In block bind code cb_lock is obtained while holding rtnl, so we must
+        * obtain the locks in same order here.
+        */
+       if (!rtnl_held && !take_rtnl && block->lockeddevcnt) {
+               up_read(&block->cb_lock);
+               take_rtnl = true;
+               goto retry;
+       }
+
        ok_count = __tc_setup_cb_call(block, type, type_data, err_stop);
 
        tc_cls_offload_cnt_reset(block, tp, in_hw_count, flags);
@@ -3177,6 +3240,8 @@ int tc_setup_cb_destroy(struct tcf_block *block, struct tcf_proto *tp,
                tp->ops->hw_del(tp, type_data);
 
        up_read(&block->cb_lock);
+       if (take_rtnl)
+               rtnl_unlock();
        return ok_count < 0 ? ok_count : 0;
 }
 EXPORT_SYMBOL(tc_setup_cb_destroy);