net: bridge: add flush filtering support
Subsystems (3)
Nikolay Aleksandrov
maintainerv4 cover net: bridge: add flush filtering support
Hi,
This patch-set adds support to specify filtering conditions for a bulk delete (flush) operation. This version uses a new nlmsghdr delete flag called NLM_F_BULK in combination with a new ndo_fdb_del_bulk op which is used to signal that the driver supports bulk deletes (that avoids pushing common mac address checks to ndo_fdb_del implementations and also has a different prototype and parsed attribute expectations, more info in patch 03). The new delete flag can be used for any RTM_DEL* type, implementations just need to be careful with older kernels which are doing non-strict attribute parses. A new rtnl flag (RTNL_FLAG_BULK_DEL_SUPPORTED) is used to show that the delete supports NLM_F_BULK. A proper error is returned if bulk delete is not supported. For old kernels I use the fact that mac address attribute (lladdr) is mandatory in the classic fdb del case, but it's not allowed if bulk deleting so older kernels will error out.
Patch 01 and 02 are minor rtnetlink cleanups to make the code easier to read. They remove hardcoded values and use names instead. Patch 03 uses BIT() for rtnl flags.
Patch 04 adds the new NLM_F_BULK delete request modifier, patch 05 adds the new bulk delete flag and checks for it if the delete requests have NLM_F_BULK set, it also warns if rtnl register is called with a non-delete kind and the bulk delete flag is set.
Patch 06 adds the new ndo_fdb_del_bulk call. Patch 07 adds NLM_F_BULK support to rtnl_fdb_del, on such request strict parsing is used only for the supported attributes, and if the ndo is implemented it's called, the NTF_SELF/MASTER rules are the same as for the standard rtnl_fdb_del. Patch 08 implements bridge-specific minimal ndo_fdb_del_bulk call which uses the current br_fdb_flush to delete all entries. Patch 09 adds filtering support to the new bridge flush op which supports target ifindex (port or bridge), vlan id and flags/state mask. Patch 10 adds ndm state and flags mask attributes which will be used for filtering. Patch 11 converts ndm state/flags and their masks to bridge-private flags and fills them in the filter descriptor for matching. Finally patch 12 fills in the target ifindex (after validating it) and vlan id (already validated by rtnl_fdb_flush) for matching. Flush filtering is needed because user-space applications need a quick way to delete only a specific set of entries, e.g. mlag implementations need a way to flush only dynamic entries excluding externally learned ones or only externally learned ones without static entries etc. Also apps usually want to target only a specific vlan or port/vlan combination. The current 2 flush operations (per port and bridge-wide) are not extensible and cannot provide such filtering.
I decided against embedding new attrs into the old flush attributes for multiple reasons - proper error handling on unsupported attributes, older kernels silently flushing all, need for a second mechanism to signal that the attribute should be parsed (e.g. using boolopts), special treatment for permanent entries.
Examples:
$ bridge fdb flush dev bridge vlan 100 static < flush all static entries on vlan 100 > $ bridge fdb flush dev bridge vlan 1 dynamic < flush all dynamic entries on vlan 1 > $ bridge fdb flush dev bridge port ens16 vlan 1 dynamic < flush all dynamic entries on port ens16 and vlan 1 > $ bridge fdb flush dev ens16 vlan 1 dynamic master < as above: flush all dynamic entries on port ens16 and vlan 1 > $ bridge fdb flush dev bridge nooffloaded nopermanent self < flush all non-offloaded and non-permanent entries > $ bridge fdb flush dev bridge static noextern_learn < flush all static entries which are not externally learned > $ bridge fdb flush dev bridge permanent < flush all permanent entries > $ bridge fdb flush dev bridge port bridge permanent < flush all permanent entries pointing to the bridge itself >
Example of a flush call with unsupported netlink attribute (NDA_DST):
$ bridge fdb flush dev bridge vlan 100 dynamic dst Error: Unsupported attribute.
Example of a flush call on an older kernel:
$ bridge fdb flush dev bridge dynamic Error: invalid address.
Example of calling PF_UNSPEC RTM_DELNEIGH which doesn't support bulk delete with NLM_F_BULK set (ip neigh is changed to add the flag):
$ ip n del 192.168.122.5 lladdr 00:11:22:33:44:55 dev ens3 Error: Bulk delete is not supported.
Note that all flags have their negated version (static vs nostatic etc) and there are some tricky cases to handle like "static" which in flag terms means fdbs that have NUD_NOARP but *not* NUD_PERMANENT, so the mask matches on both but we need only NUD_NOARP to be set. That's because permanent entries have both set so we can't just match on NUD_NOARP. Also note that this flush operation doesn't treat permanent entries in a special way (fdb_delete vs fdb_delete_local), it will delete them regardless if any port is using them. We can extend the api with a flag to do that if needed in the future.
Patch-sets (in order):
- Initial bulk del infra and fdb flush filtering (this set)
- iproute2 support
- selftests
v4: Add and check for rtnl del bulk supported flag when using
NLM_F_BULK (new patch 05), patches 01 - 03 are also new minor cleanups to remove use of raw values and make code easier to read, don't rename br_fdb_flush in patch 08, set port ifindex as flush target if NDA_IFINDEX is missing and flush was called with port netdev and NTF_MASTER (patch 12).
v3: Add NLM_F_BULK delete modifier and ndo_fdb_del_bulk callback,
patches 01 - 03 and 06 are new. Patch 04 is changed to implement bulk_del instead of flush, patches 05, 07 and 08 are adjusted to use NDA_ attributes
Thanks,
Nik
Nikolay Aleksandrov (12):
net: rtnetlink: add msg kind names
net: rtnetlink: add helper to extract msg type's kind
net: rtnetlink: use BIT for flag values
net: netlink: add NLM_F_BULK delete request modifier
net: rtnetlink: add bulk delete support flag
net: add ndo_fdb_del_bulk
net: rtnetlink: add NLM_F_BULK support to rtnl_fdb_del
net: bridge: fdb: add ndo_fdb_del_bulk
net: bridge: fdb: add support for fine-grained flushing
net: rtnetlink: add ndm flags and state mask attributes
net: bridge: fdb: add support for flush filtering based on ndm flags
and state
net: bridge: fdb: add support for flush filtering based on ifindex and
vlan
include/linux/netdevice.h | 9 ++ include/net/rtnetlink.h | 16 +++- include/uapi/linux/neighbour.h | 2 + include/uapi/linux/netlink.h | 1 + net/bridge/br_device.c | 1 + net/bridge/br_fdb.c | 157 +++++++++++++++++++++++++++++++-- net/bridge/br_netlink.c | 9 +- net/bridge/br_private.h | 18 +++- net/bridge/br_sysfs_br.c | 6 +- net/core/rtnetlink.c | 85 +++++++++++++----- 10 files changed, 269 insertions(+), 35 deletions(-)
Signature · 1 line
2.35.1
Nikolay Aleksandrov
maintainerPATCH v4 1/12 net: rtnetlink: add msg kind names
Add rtnl kind names instead of using raw values. We'll need to check for DEL kind later to validate bulk flag support.
---
v4: new patch
include/net/rtnetlink.h | 7 +++++++ net/core/rtnetlink.c | 6 +++--- 2 files changed, 10 insertions(+), 3 deletions(-)
include/net/rtnetlink.h +7 -0
@@ -13,6 +13,13 @@ enum rtnl_link_flags { RTNL_FLAG_DOIT_UNLOCKED = 1, }; +enum rtnl_kinds { +RTNL_KIND_NEW , +RTNL_KIND_DEL , +RTNL_KIND_GET , +RTNL_KIND_SET +}; +void rtnl_register (int protocol,int msgtype,rtnl_doit_func ,rtnl_dumpit_func ,unsigned int flags); int rtnl_register_module(struct module *owner, int protocol, int msgtype,
net/core/rtnetlink.c +3 -3
@@ -5928,11 +5928,11 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, {struct net *net =sock_net (skb->sk);struct rtnl_link *link; +enum rtnl_kinds kind;struct module *owner;int err = -EOPNOTSUPP ;rtnl_doit_func doit;unsigned int flags; -int kind;int family;int type;
@@ -5949,11 +5949,11 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, family = ((struct rtgenmsg *)nlmsg_data (nlh))->rtgen_family; kind = type&3 ; -if (kind !=2 && !netlink_net_capable (skb,CAP_NET_ADMIN )) +if (kind !=RTNL_KIND_GET && !netlink_net_capable (skb,CAP_NET_ADMIN ))return -EPERM ;rcu_read_lock (); -if (kind ==2 && nlh->nlmsg_flags&NLM_F_DUMP ) { +if (kind ==RTNL_KIND_GET && (nlh->nlmsg_flags &NLM_F_DUMP )) {struct sock *rtnl;rtnl_dumpit_func dumpit;u32 min_dump_alloc =0 ;
Signature · 1 line
2.35.1
Nikolay Aleksandrov
maintainerPATCH v4 2/12 net: rtnetlink: add helper to extract msg type's kind
In reply to Nikolay AleksandrovAdd a helper which extracts the msg type's kind using the kind mask (0x3).
---
v4: new patch
include/net/rtnetlink.h | 6 ++++++ net/core/rtnetlink.c | 2 +- 2 files changed, 7 insertions(+), 1 deletion(-)
include/net/rtnetlink.h +6 -0
@@ -19,6 +19,12 @@ enum rtnl_kinds {RTNL_KIND_GET , RTNL_KIND_SET }; +#define RTNL_KIND_MASK 0x3 + +static inline enum rtnl_kinds rtnl_msgtype_kind (int msgtype) +{ +return msgtype &RTNL_KIND_MASK ; +}void rtnl_register (int protocol,int msgtype,rtnl_doit_func ,rtnl_dumpit_func ,unsigned int flags);
net/core/rtnetlink.c +1 -1
@@ -5947,7 +5947,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,return 0 ; family = ((struct rtgenmsg *)nlmsg_data (nlh))->rtgen_family; - kind = type&3 ; + kind =rtnl_msgtype_kind (type);if (kind !=RTNL_KIND_GET && !netlink_net_capable (skb,CAP_NET_ADMIN ))return -EPERM ;
Signature · 1 line
2.35.1
Nikolay Aleksandrov
maintainerPATCH v4 3/12 net: rtnetlink: use BIT for flag values
In reply to Nikolay AleksandrovUse BIT to define flag values.
---
v4: new patch
include/net/rtnetlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
include/net/rtnetlink.h +1 -1
@@ -10,7 +10,7 @@ typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *,typedef int (*rtnl_dumpit_func )(struct sk_buff *,struct netlink_callback *);enum rtnl_link_flags { -RTNL_FLAG_DOIT_UNLOCKED =1 , +RTNL_FLAG_DOIT_UNLOCKED =BIT (0 ), };enum rtnl_kinds {
Signature · 1 line
2.35.1
Nikolay Aleksandrov
maintainerPATCH v4 4/12 net: netlink: add NLM_F_BULK delete request modifier
In reply to Nikolay AleksandrovAdd a new delete request modifier called NLM_F_BULK which, when supported, would cause the request to delete multiple objects. The flag is a convenient way to signal that a multiple delete operation is requested which can be gradually added to different delete requests. In order to make sure older kernels will error out if the operation is not supported instead of doing something unintended we have to break a required condition when implementing support for this flag, f.e. for neighbors we will omit the mandatory mac address attribute. Initially it will be used to add flush with filtering support for bridge fdbs, but it also opens the door to add similar support to others.
--- include/uapi/linux/netlink.h | 1 + 1 file changed, 1 insertion(+)
include/uapi/linux/netlink.h +1 -0
@@ -72,6 +72,7 @@ struct nlmsghdr {/* Modifiers to DELETE request */ #define NLM_F_NONREC 0x100/* Do not delete recursively */ +#define NLM_F_BULK 0x200/* Delete multiple objects */ /* Flags for ACK message */ #define NLM_F_CAPPED 0x100/* request was capped */
Signature · 1 line
2.35.1
Re: [PATCH net-next v4 04/12] net: netlink: add NLM_F_BULK delete request modifier
Le 13/04/2022 à 12:51, Nikolay Aleksandrov a écrit :
Quoted 21 lines
Add a new delete request modifier called
NLM_F_BULKwhich, when supported, would cause the request to delete multiple objects. The flag is a convenient way to signal that a multiple delete operation is requested which can be gradually added to different delete requests. In order to make sure older kernels will error out if the operation is not supported instead of doing something unintended we have to break a required condition when implementing support for this flag, f.e. for neighbors we will omit the mandatory mac address attribute. Initially it will be used to add flush with filtering support for bridge fdbs, but it also opens the door to add similar support to others.Signed-off-by Nikolay Aleksandrov <[email protected]>--- include/uapi/linux/netlink.h | 1 + 1 file changed, 1 insertion(+)include/uapi/linux/netlink.h +0
-0
include/uapi/linux/netlink.h struct nlmsghdr { · line 75
Quoted 4 lines
include/uapi/linux/netlink.h +1
-0@@ -72,6 +72,7 @@ struct nlmsghdr {/* Modifiers to DELETE request */ #define NLM_F_NONREC 0x100/* Do not delete recursively */ +#define NLM_F_BULK 0x200/* Delete multiple objects */
Sorry to reply to an old patch, but FWIW, this patch broke the uAPI. One of our applications was using NLM_F_EXCL with RTM_DELTFILTER. This is conceptually wrong but it was working. After this patch, the kernel returns an error (EOPNOTSUPP).
Here is the patch series:
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/log/?h=92716869375b
We probably can't do anything now, but to avoid this in the future, I see only two options:
- enforce flags validation depending on the operation (but this may break some existing apps)
- stop adding new flags that overlap between NEW and DEL operations (by adding a comment or defining dummy flags).
Any thoughts?
Regards,
Nicolas
Nikolay Aleksandrov
maintainerRe: [PATCH net-next v4 04/12] net: netlink: add NLM_F_BULK delete request modifier
Quoted 35 lines · Nicolas Dichtel
Le 13/04/2022 à 12:51, Nikolay Aleksandrov a écrit :
Quoted 21 lines
Add a new delete request modifier called
NLM_F_BULKwhich, when supported, would cause the request to delete multiple objects. The flag is a convenient way to signal that a multiple delete operation is requested which can be gradually added to different delete requests. In order to make sure older kernels will error out if the operation is not supported instead of doing something unintended we have to break a required condition when implementing support for this flag, f.e. for neighbors we will omit the mandatory mac address attribute. Initially it will be used to add flush with filtering support for bridge fdbs, but it also opens the door to add similar support to others.Signed-off-by Nikolay Aleksandrov <[email protected]>--- include/uapi/linux/netlink.h | 1 + 1 file changed, 1 insertion(+)include/uapi/linux/netlink.h +0
-0include/uapi/linux/netlink.h struct nlmsghdr { · line 75
Quoted 4 lines
include/uapi/linux/netlink.h +1
-0@@ -72,6 +72,7 @@ struct nlmsghdr {/* Modifiers to DELETE request */ #define NLM_F_NONREC 0x100/* Do not delete recursively */ +#define NLM_F_BULK 0x200/* Delete multiple objects */ Sorry to reply to an old patch, but FWIW, this patch broke the uAPI. One of our applications was using
NLM_F_EXCLwithRTM_DELTFILTER. This is conceptually wrong but it was working. After this patch, the kernel returns an error (EOPNOTSUPP).Here is the patch series:
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/log/?h=92716869375b
Quoted 9 lines
We probably can't do anything now, but to avoid this in the future, I see only two options:
- enforce flags validation depending on the operation (but this may break some existing apps)
- stop adding new flags that overlap between NEW and DEL operations (by adding a comment or defining dummy flags).Any thoughts?
Personally I'd prefer to enforce validation so we don't lose the flags because of buggy user-space applications, but we can break someone (who arguably should fix their app though). We already had that discussion while the set was under review[1] and just to be a bit more confident I also tried searching for open-source buggy users, but didn't find any.
Quoted 2 lines
Regards,
Nicolas
[1] https://lore.kernel.org/netdev/[email protected]/t/#m23018ce831dae16d42cb9c393c7c6bad1bc621c3
Re: [PATCH net-next v4 04/12] net: netlink: add NLM_F_BULK delete request modifier
Le 20/09/2022 à 11:05, Nikolay Aleksandrov a écrit :
Quoted 43 lines · Nicolas Dichtel
Quoted 42 lines
Le 13/04/2022 à 12:51, Nikolay Aleksandrov a écrit :
Quoted 21 lines
Add a new delete request modifier called
NLM_F_BULKwhich, when supported, would cause the request to delete multiple objects. The flag is a convenient way to signal that a multiple delete operation is requested which can be gradually added to different delete requests. In order to make sure older kernels will error out if the operation is not supported instead of doing something unintended we have to break a required condition when implementing support for this flag, f.e. for neighbors we will omit the mandatory mac address attribute. Initially it will be used to add flush with filtering support for bridge fdbs, but it also opens the door to add similar support to others.Signed-off-by Nikolay Aleksandrov <[email protected]>--- include/uapi/linux/netlink.h | 1 + 1 file changed, 1 insertion(+)include/uapi/linux/netlink.h +0
-0include/uapi/linux/netlink.h struct nlmsghdr { · line 75
Quoted 4 lines
include/uapi/linux/netlink.h +1
-0@@ -72,6 +72,7 @@ struct nlmsghdr {/* Modifiers to DELETE request */ #define NLM_F_NONREC 0x100/* Do not delete recursively */ +#define NLM_F_BULK 0x200/* Delete multiple objects */ Sorry to reply to an old patch, but FWIW, this patch broke the uAPI. One of our applications was using
NLM_F_EXCLwithRTM_DELTFILTER. This is conceptually wrong but it was working. After this patch, the kernel returns an error (EOPNOTSUPP).Here is the patch series:
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/log/?h=92716869375bWe probably can't do anything now, but to avoid this in the future, I see only two options:
- enforce flags validation depending on the operation (but this may break some existing apps)
- stop adding new flags that overlap between NEW and DEL operations (by adding a comment or defining dummy flags).
Quoted 6 lines
Quoted 2 lines
Any thoughts?
Personally I'd prefer to enforce validation so we don't lose the flags because of buggy user-space applications, but we can break someone (who arguably should fix their app though). We already had that discussion while the set was under review[1] and just to be a bit more confident I also
Thanks for the link. Finally, someone has (almost) complained :D
Quoted 1 line
tried searching for open-source buggy users, but didn't find any.
The trend seems to let someone else add another specific flag if needed. Thus, it seems that checking flags is the way to go.
The pro is that if someone complains, the patch could be reverted, which is not the case for a new feature like this bulk for example.
Regards,
Nicolas
Nikolay Aleksandrov
maintainerPATCH v4 5/12 net: rtnetlink: add bulk delete support flag
In reply to Nikolay AleksandrovAdd a new rtnl flag (RTNL_FLAG_BULK_DEL_SUPPORTED) which is used to verify that the delete operation allows bulk object deletion. Also emit a warning if anyone tries to set it for non-delete kind.
---
v4: new patch
include/net/rtnetlink.h | 3 ++- net/core/rtnetlink.c | 8 ++++++++ 2 files changed, 10 insertions(+), 1 deletion(-)
include/net/rtnetlink.h +2 -1
@@ -10,7 +10,8 @@ typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *,typedef int (*rtnl_dumpit_func )(struct sk_buff *,struct netlink_callback *);enum rtnl_link_flags { -RTNL_FLAG_DOIT_UNLOCKED =BIT (0 ), +RTNL_FLAG_DOIT_UNLOCKED =BIT (0 ), +RTNL_FLAG_BULK_DEL_SUPPORTED =BIT (1 ), };enum rtnl_kinds {
net/core/rtnetlink.c +8 -0
@@ -249,6 +249,8 @@ static int rtnl_register_internal(struct module *owner,if (dumpit) link->dumpit = dumpit; +WARN_ON (rtnl_msgtype_kind (msgtype) !=RTNL_KIND_DEL && + (flags &RTNL_FLAG_BULK_DEL_SUPPORTED )); link->flags |= flags;/* publish protocol:msgtype */
@@ -6009,6 +6011,12 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, } flags = link->flags; +if (kind ==RTNL_KIND_DEL && (nlh->nlmsg_flags &NLM_F_BULK ) && + !(flags &RTNL_FLAG_BULK_DEL_SUPPORTED )) { +NL_SET_ERR_MSG (extack,"Bulk delete is not supported" ); + goto err_unlock; + } +if (flags &RTNL_FLAG_DOIT_UNLOCKED ) { doit = link->doit;rcu_read_unlock ();
Signature · 1 line
2.35.1
Re: [PATCH net-next v4 05/12] net: rtnetlink: add bulk delete support flag
Quoted 41 lines · Nikolay Aleksandrov
Add a new rtnl flag (
RTNL_FLAG_BULK_DEL_SUPPORTED) which is used to verify that the delete operation allows bulk object deletion. Also emit a warning if anyone tries to set it for non-delete kind.Suggested-by David Ahern <[email protected]>Signed-off-by Nikolay Aleksandrov <[email protected]>---
v4: new patchinclude/net/rtnetlink.h | 3 ++- net/core/rtnetlink.c | 8 ++++++++ 2 files changed, 10 insertions(+), 1 deletion(-)include/net/rtnetlink.h +2
-1@@ -10,7 +10,8 @@ typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *,typedef int (*rtnl_dumpit_func )(struct sk_buff *,struct netlink_callback *);enum rtnl_link_flags { -RTNL_FLAG_DOIT_UNLOCKED =BIT (0 ), +RTNL_FLAG_DOIT_UNLOCKED =BIT (0 ), +RTNL_FLAG_BULK_DEL_SUPPORTED =BIT (1 ), };enum rtnl_kinds {net/core/rtnetlink.c +2
-0@@ -249,6 +249,8 @@ static int rtnl_register_internal(struct module *owner,if (dumpit) link->dumpit = dumpit; +WARN_ON (rtnl_msgtype_kind (msgtype) !=RTNL_KIND_DEL && + (flags &RTNL_FLAG_BULK_DEL_SUPPORTED )); link->flags |= flags;/* publish protocol:msgtype */
net/core/rtnetlink.c static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, · line 6017
Quoted 7 lines
net/core/rtnetlink.c +4
-0@@ -6009,6 +6011,12 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, } flags = link->flags; +if (kind ==RTNL_KIND_DEL && (nlh->nlmsg_flags &NLM_F_BULK ) && + !(flags &RTNL_FLAG_BULK_DEL_SUPPORTED )) { +NL_SET_ERR_MSG (extack,"Bulk delete is not supported" ); + goto err_unlock;
If a buggy user space application is sending messages with NLM_F_BULK set (unintentionally), will it break on newer kernel? I couldn't find where the kernel was validating that reserved flags are not used (I suspect it doesn't).
Assuming the above is correct and of interest, maybe just emit a warning via extack and drop the goto? Alternatively, we can see if anyone complains which might never happen
Quoted 8 lines
net/core/rtnetlink.c +2
-0+ } +if (flags &RTNL_FLAG_DOIT_UNLOCKED ) { doit = link->doit;rcu_read_unlock ();Signature · 1 line
2.35.1
Nikolay Aleksandrov
maintainerRe: [PATCH net-next v4 05/12] net: rtnetlink: add bulk delete support flag
Quoted 44 lines · Ido Schimmel
Quoted 43 lines · Nikolay Aleksandrov
Add a new rtnl flag (
RTNL_FLAG_BULK_DEL_SUPPORTED) which is used to verify that the delete operation allows bulk object deletion. Also emit a warning if anyone tries to set it for non-delete kind.Suggested-by David Ahern <[email protected]>Signed-off-by Nikolay Aleksandrov <[email protected]>---
v4: new patchinclude/net/rtnetlink.h | 3 ++- net/core/rtnetlink.c | 8 ++++++++ 2 files changed, 10 insertions(+), 1 deletion(-)include/net/rtnetlink.h +2
-1@@ -10,7 +10,8 @@ typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *,typedef int (*rtnl_dumpit_func )(struct sk_buff *,struct netlink_callback *);enum rtnl_link_flags { -RTNL_FLAG_DOIT_UNLOCKED =BIT (0 ), +RTNL_FLAG_DOIT_UNLOCKED =BIT (0 ), +RTNL_FLAG_BULK_DEL_SUPPORTED =BIT (1 ), };enum rtnl_kinds {net/core/rtnetlink.c +2
-0@@ -249,6 +249,8 @@ static int rtnl_register_internal(struct module *owner,if (dumpit) link->dumpit = dumpit; +WARN_ON (rtnl_msgtype_kind (msgtype) !=RTNL_KIND_DEL && + (flags &RTNL_FLAG_BULK_DEL_SUPPORTED )); link->flags |= flags;/* publish protocol:msgtype */ @@ -6009,6 +6011,12 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, }
Quoted 10 lines
net/core/rtnetlink.c static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, · line 6017
Quoted 5 lines
net/core/rtnetlink.c +4
-0flags = link->flags; +if (kind ==RTNL_KIND_DEL && (nlh->nlmsg_flags &NLM_F_BULK ) && + !(flags &RTNL_FLAG_BULK_DEL_SUPPORTED )) { +NL_SET_ERR_MSG (extack,"Bulk delete is not supported" ); + goto err_unlock;If a buggy user space application is sending messages with
NLM_F_BULKset (unintentionally), will it break on newer kernel? I couldn't find where the kernel was validating that reserved flags are not used (I suspect it doesn't).
Correct, it doesn't.
Quoted 5 lines
Assuming the above is correct and of interest, maybe just emit a warning via extack and drop the goto? Alternatively, we can see if anyone complains which might never happen
TBH I prefer to error out on an unsupported flag, but I get the problem. These weren't validated before and we start checking now. The problem is that we'll return an extack without an error, but the delete might also remove something. Hrm.. perhaps we can rephrase the error in that case (since it becomes a warning in iproute2 terms):
"NLM_F_BULK flag is set but bulk delete operation is not supported"
So it will warn the user it has an unsupported flag.
WDYT ?
IMO we should bite the bullet and keep the error though. :)
Quoted 8 lines
Quoted 8 lines
net/core/rtnetlink.c +2
-0+ } +if (flags &RTNL_FLAG_DOIT_UNLOCKED ) { doit = link->doit;rcu_read_unlock ();Signature · 1 line
2.35.1
Re: [PATCH net-next v4 05/12] net: rtnetlink: add bulk delete support flag
Quoted 21 lines · Nikolay Aleksandrov
Quoted 4 lines
If a buggy user space application is sending messages with
NLM_F_BULKset (unintentionally), will it break on newer kernel? I couldn't find where the kernel was validating that reserved flags are not used (I suspect it doesn't).Correct, it doesn't.
Quoted 5 lines
Assuming the above is correct and of interest, maybe just emit a warning via extack and drop the goto? Alternatively, we can see if anyone complains which might never happen
TBH I prefer to error out on an unsupported flag, but I get the problem. These weren't validated before and we start checking now. The problem is that we'll return an extack without an error, but the delete might also remove something. Hrm.. perhaps we can rephrase the error in that case (since it becomes a warning in iproute2 terms):
"NLM_F_BULKflag is set but bulk delete operation is not supported"
So it will warn the user it has an unsupported flag.
Quoted 4 lines
WDYT ?
IMO we should bite the bullet and keep the error though. :)
I agree. The check across the board for BULK flag on any DELETE requests should tell us pretty quick if someone is setting that flag when it should not be.
Nikolay Aleksandrov
maintainerPATCH v4 6/12 net: add ndo_fdb_del_bulk
In reply to Nikolay AleksandrovAdd a new netdev op called ndo_fdb_del_bulk, it will be later used for driver-specific bulk delete implementation dispatched from rtnetlink. The first user will be the bridge, we need it to signal to rtnetlink from the driver that we support bulk delete operation (NLM_F_BULK).
--- include/linux/netdevice.h | 9 +++++++++ 1 file changed, 9 insertions(+)
include/linux/netdevice.h +9 -0
@@ -1260,6 +1260,10 @@ struct netdev_net_notifier {* struct net_device *dev, * const unsigned char *addr, u16 vid) * Deletes the FDB entry from dev coresponding to addr. +* int (*ndo_fdb_del_bulk)(struct ndmsg *ndm, struct nlattr *tb[], +* struct net_device *dev, +* u16 vid, +* struct netlink_ext_ack *extack); * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, * struct net_device *dev, struct net_device *filter_dev, * int *idx)
@@ -1510,6 +1514,11 @@ struct net_device_ops {struct net_device *dev, const unsigned char *addr, u16 vid); +int (*ndo_fdb_del_bulk)(struct ndmsg *ndm, +struct nlattr *tb[], +struct net_device *dev, +u16 vid, +struct netlink_ext_ack *extack); int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev,
Signature · 1 line
2.35.1
Nikolay Aleksandrov
maintainerPATCH v4 7/12 net: rtnetlink: add NLM_F_BULK support to rtnl_fdb_del
In reply to Nikolay AleksandrovWhen NLM_F_BULK is specified in a fdb del message we need to handle it differently. First since this is a new call we can strictly validate the passed attributes, at first only ifindex and vlan are allowed as these will be the initially supported filter attributes, any other attribute is rejected. The mac address is no longer mandatory, but we use it to error out in older kernels because it cannot be specified with bulk request (the attribute is not allowed) and then we have to dispatch the call to ndo_fdb_del_bulk if the device supports it. The del bulk callback can do further validation of the attributes if necessary.
---
v4: mark PF_BRIDGE/RTM_DELNEIGH with RTNL_FLAG_BULK_DEL_SUPPORTED
net/core/rtnetlink.c | 67 +++++++++++++++++++++++++++++++------------- 1 file changed, 48 insertions(+), 19 deletions(-)
net/core/rtnetlink.c +48 -19
@@ -4169,22 +4169,34 @@ int ndo_dflt_fdb_del(struct ndmsg *ndm, }EXPORT_SYMBOL (ndo_dflt_fdb_del); +static const struct nla_policy fdb_del_bulk_policy[NDA_MAX +1 ] = { + [NDA_VLAN ] = { .type =NLA_U16 }, + [NDA_IFINDEX ] =NLA_POLICY_MIN (NLA_S32 ,1 ), +}; +static int rtnl_fdb_del (struct sk_buff *skb,struct nlmsghdr *nlh,struct netlink_ext_ack *extack) { +bool del_bulk = !!(nlh->nlmsg_flags &NLM_F_BULK );struct net *net =sock_net (skb->sk); +const struct net_device_ops *ops;struct ndmsg *ndm;struct nlattr *tb[NDA_MAX +1 ];struct net_device *dev; -__u8 *addr; +__u8 *addr =NULL ;int err;u16 vid;if (!netlink_capable (skb,CAP_NET_ADMIN ))return -EPERM ; - err =nlmsg_parse_deprecated (nlh,sizeof (*ndm), tb,NDA_MAX ,NULL , - extack); +if (!del_bulk) { + err =nlmsg_parse_deprecated (nlh,sizeof (*ndm), tb,NDA_MAX , +NULL , extack); + }else { + err =nlmsg_parse (nlh,sizeof (*ndm), tb,NDA_MAX , + fdb_del_bulk_policy, extack); + }if (err <0 )return err;
@@ -4200,9 +4212,12 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,return -ENODEV ; } -if (!tb[NDA_LLADDR ] ||nla_len (tb[NDA_LLADDR ]) !=ETH_ALEN ) { -NL_SET_ERR_MSG (extack,"invalid address" ); -return -EINVAL ; +if (!del_bulk) { +if (!tb[NDA_LLADDR ] ||nla_len (tb[NDA_LLADDR ]) !=ETH_ALEN ) { +NL_SET_ERR_MSG (extack,"invalid address" ); +return -EINVAL ; + } + addr =nla_data (tb[NDA_LLADDR ]); }if (dev->type !=ARPHRD_ETHER ) {
@@ -4210,8 +4225,6 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,return -EINVAL ; } - addr =nla_data (tb[NDA_LLADDR ]); - err =fdb_vid_parse (tb[NDA_VLAN ], &vid, extack);if (err)return err;
@@ -4222,10 +4235,16 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,if ((!ndm->ndm_flags || ndm->ndm_flags &NTF_MASTER ) &&netif_is_bridge_port (dev)) {struct net_device *br_dev =netdev_master_upper_dev_get (dev); -const struct net_device_ops *ops = br_dev->netdev_ops; -if (ops->ndo_fdb_del) - err = ops->ndo_fdb_del (ndm, tb, dev, addr, vid); + ops = br_dev->netdev_ops; +if (!del_bulk) { +if (ops->ndo_fdb_del) + err = ops->ndo_fdb_del (ndm, tb, dev, addr, vid); + }else { +if (ops->ndo_fdb_del_bulk) + err = ops->ndo_fdb_del_bulk (ndm, tb, dev, vid, + extack); + }if (err) goto out;
@@ -4235,15 +4254,24 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,/* Embedded bridge, macvlan, and any other device support */ if (ndm->ndm_flags &NTF_SELF ) { -if (dev->netdev_ops->ndo_fdb_del) - err = dev->netdev_ops->ndo_fdb_del (ndm, tb, dev, addr, - vid); -else - err =ndo_dflt_fdb_del (ndm, tb, dev, addr, vid); + ops = dev->netdev_ops; +if (!del_bulk) { +if (ops->ndo_fdb_del) + err = ops->ndo_fdb_del (ndm, tb, dev, addr, vid); +else + err =ndo_dflt_fdb_del (ndm, tb, dev, addr, vid); + }else { +/* in case err was cleared by NTF_MASTER call */ + err = -EOPNOTSUPP ; +if (ops->ndo_fdb_del_bulk) + err = ops->ndo_fdb_del_bulk (ndm, tb, dev, vid, + extack); + }if (!err) { -rtnl_fdb_notify (dev, addr, vid,RTM_DELNEIGH , - ndm->ndm_state); +if (!del_bulk) +rtnl_fdb_notify (dev, addr, vid,RTM_DELNEIGH , + ndm->ndm_state); ndm->ndm_flags &= ~NTF_SELF ; } }
@@ -6145,7 +6173,8 @@ void __init rtnetlink_init(void)rtnl_register (PF_UNSPEC ,RTM_DELLINKPROP , rtnl_dellinkprop,NULL ,0 );rtnl_register (PF_BRIDGE ,RTM_NEWNEIGH , rtnl_fdb_add,NULL ,0 ); -rtnl_register (PF_BRIDGE ,RTM_DELNEIGH , rtnl_fdb_del,NULL ,0 ); +rtnl_register (PF_BRIDGE ,RTM_DELNEIGH , rtnl_fdb_del,NULL , +RTNL_FLAG_BULK_DEL_SUPPORTED );rtnl_register (PF_BRIDGE ,RTM_GETNEIGH , rtnl_fdb_get, rtnl_fdb_dump,0 );rtnl_register (PF_BRIDGE ,RTM_GETLINK ,NULL , rtnl_bridge_getlink,0 );
Signature · 1 line
2.35.1
Re: [PATCH net-next v4 07/12] net: rtnetlink: add NLM_F_BULK support to rtnl_fdb_del
Quoted 22 lines · Nikolay Aleksandrov
When
NLM_F_BULKis specified in a fdb del message we need to handle it differently. First since this is a new call we can strictly validate the passed attributes, at first only ifindex and vlan are allowed as these will be the initially supported filter attributes, any other attribute is rejected. The mac address is no longer mandatory, but we use it to error out in older kernels because it cannot be specified with bulk request (the attribute is not allowed) and then we have to dispatch the call tondo_fdb_del_bulkif the device supports it. The del bulk callback can do further validation of the attributes if necessary.Signed-off-by Nikolay Aleksandrov <[email protected]>---
v4: mark PF_BRIDGE/RTM_DELNEIGH withRTNL_FLAG_BULK_DEL_SUPPORTEDnet/core/rtnetlink.c | 67 +++++++++++++++++++++++++++++++------------- 1 file changed, 48 insertions(+), 19 deletions(-)net/core/rtnetlink.c +0
-0
net/core/rtnetlink.c int ndo_dflt_fdb_del(struct ndmsg *ndm, · line 4173
Quoted 5 lines
net/core/rtnetlink.c +2
-0@@ -4169,22 +4169,34 @@ int ndo_dflt_fdb_del(struct ndmsg *ndm, }EXPORT_SYMBOL (ndo_dflt_fdb_del); +static const struct nla_policy fdb_del_bulk_policy[NDA_MAX +1 ] = { + [NDA_VLAN ] = { .type =NLA_U16 },
In earlier versions br_vlan_valid_id() was used to validate the VLAN, but I don't see it anymore. Maybe use
NLA_POLICY_RANGE(1, VLAN_N_VID - 2)
?
I realize that invalid values won't do anything, but I think it's better to only allow valid ranges.
Quoted 122 lines
net/core/rtnetlink.c +46
-19+ [NDA_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 1), +}; +static int rtnl_fdb_del (struct sk_buff *skb,struct nlmsghdr *nlh,struct netlink_ext_ack *extack) { +bool del_bulk = !!(nlh->nlmsg_flags &NLM_F_BULK );struct net *net =sock_net (skb->sk); +const struct net_device_ops *ops;struct ndmsg *ndm;struct nlattr *tb[NDA_MAX +1 ];struct net_device *dev; -__u8 *addr; +__u8 *addr =NULL ;int err;u16 vid;if (!netlink_capable (skb,CAP_NET_ADMIN ))return -EPERM ; - err =nlmsg_parse_deprecated (nlh,sizeof (*ndm), tb,NDA_MAX ,NULL , - extack); +if (!del_bulk) { + err =nlmsg_parse_deprecated (nlh,sizeof (*ndm), tb,NDA_MAX , +NULL , extack); + }else { + err =nlmsg_parse (nlh,sizeof (*ndm), tb,NDA_MAX , + fdb_del_bulk_policy, extack); + }if (err <0 )return err;@@ -4200,9 +4212,12 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,return -ENODEV ; } -if (!tb[NDA_LLADDR ] ||nla_len (tb[NDA_LLADDR ]) !=ETH_ALEN ) { -NL_SET_ERR_MSG (extack,"invalid address" ); -return -EINVAL ; +if (!del_bulk) { +if (!tb[NDA_LLADDR ] ||nla_len (tb[NDA_LLADDR ]) !=ETH_ALEN ) { +NL_SET_ERR_MSG (extack,"invalid address" ); +return -EINVAL ; + } + addr =nla_data (tb[NDA_LLADDR ]); }if (dev->type !=ARPHRD_ETHER ) {@@ -4210,8 +4225,6 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,return -EINVAL ; } - addr =nla_data (tb[NDA_LLADDR ]); - err =fdb_vid_parse (tb[NDA_VLAN ], &vid, extack);if (err)return err;@@ -4222,10 +4235,16 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,if ((!ndm->ndm_flags || ndm->ndm_flags &NTF_MASTER ) &&netif_is_bridge_port (dev)) {struct net_device *br_dev =netdev_master_upper_dev_get (dev); -const struct net_device_ops *ops = br_dev->netdev_ops; -if (ops->ndo_fdb_del) - err = ops->ndo_fdb_del (ndm, tb, dev, addr, vid); + ops = br_dev->netdev_ops; +if (!del_bulk) { +if (ops->ndo_fdb_del) + err = ops->ndo_fdb_del (ndm, tb, dev, addr, vid); + }else { +if (ops->ndo_fdb_del_bulk) + err = ops->ndo_fdb_del_bulk (ndm, tb, dev, vid, + extack); + }if (err) goto out;@@ -4235,15 +4254,24 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,/* Embedded bridge, macvlan, and any other device support */ if (ndm->ndm_flags &NTF_SELF ) { -if (dev->netdev_ops->ndo_fdb_del) - err = dev->netdev_ops->ndo_fdb_del (ndm, tb, dev, addr, - vid); -else - err =ndo_dflt_fdb_del (ndm, tb, dev, addr, vid); + ops = dev->netdev_ops; +if (!del_bulk) { +if (ops->ndo_fdb_del) + err = ops->ndo_fdb_del (ndm, tb, dev, addr, vid); +else + err =ndo_dflt_fdb_del (ndm, tb, dev, addr, vid); + }else { +/* in case err was cleared by NTF_MASTER call */ + err = -EOPNOTSUPP ; +if (ops->ndo_fdb_del_bulk) + err = ops->ndo_fdb_del_bulk (ndm, tb, dev, vid, + extack); + }if (!err) { -rtnl_fdb_notify (dev, addr, vid,RTM_DELNEIGH , - ndm->ndm_state); +if (!del_bulk) +rtnl_fdb_notify (dev, addr, vid,RTM_DELNEIGH , + ndm->ndm_state); ndm->ndm_flags &= ~NTF_SELF ; } }@@ -6145,7 +6173,8 @@ void __init rtnetlink_init(void)rtnl_register (PF_UNSPEC ,RTM_DELLINKPROP , rtnl_dellinkprop,NULL ,0 );rtnl_register (PF_BRIDGE ,RTM_NEWNEIGH , rtnl_fdb_add,NULL ,0 ); -rtnl_register (PF_BRIDGE ,RTM_DELNEIGH , rtnl_fdb_del,NULL ,0 ); +rtnl_register (PF_BRIDGE ,RTM_DELNEIGH , rtnl_fdb_del,NULL , +RTNL_FLAG_BULK_DEL_SUPPORTED );rtnl_register (PF_BRIDGE ,RTM_GETNEIGH , rtnl_fdb_get, rtnl_fdb_dump,0 );rtnl_register (PF_BRIDGE ,RTM_GETLINK ,NULL , rtnl_bridge_getlink,0 );Signature · 1 line
2.35.1
Nikolay Aleksandrov
maintainerRe: [PATCH net-next v4 07/12] net: rtnetlink: add NLM_F_BULK support to rtnl_fdb_del
Quoted 32 lines · Ido Schimmel
Quoted 22 lines · Nikolay Aleksandrov
When
NLM_F_BULKis specified in a fdb del message we need to handle it differently. First since this is a new call we can strictly validate the passed attributes, at first only ifindex and vlan are allowed as these will be the initially supported filter attributes, any other attribute is rejected. The mac address is no longer mandatory, but we use it to error out in older kernels because it cannot be specified with bulk request (the attribute is not allowed) and then we have to dispatch the call tondo_fdb_del_bulkif the device supports it. The del bulk callback can do further validation of the attributes if necessary.Signed-off-by Nikolay Aleksandrov <[email protected]>---
v4: mark PF_BRIDGE/RTM_DELNEIGH withRTNL_FLAG_BULK_DEL_SUPPORTEDnet/core/rtnetlink.c | 67 +++++++++++++++++++++++++++++++------------- 1 file changed, 48 insertions(+), 19 deletions(-)net/core/rtnetlink.c +0
-0net/core/rtnetlink.c int ndo_dflt_fdb_del(struct ndmsg *ndm, · line 4173
Quoted 5 lines
net/core/rtnetlink.c +2
-0@@ -4169,22 +4169,34 @@ int ndo_dflt_fdb_del(struct ndmsg *ndm, }EXPORT_SYMBOL (ndo_dflt_fdb_del); +static const struct nla_policy fdb_del_bulk_policy[NDA_MAX +1 ] = { + [NDA_VLAN ] = { .type =NLA_U16 },In earlier versions
br_vlan_valid_id()was used to validate the VLAN, but I don't see it anymore. Maybe use
Quoted 7 lines
NLA_POLICY_RANGE(1, VLAN_N_VID - 2)?
I realize that invalid values won't do anything, but I think it's better to only allow valid ranges.
It's already validated below, see fdb_vid_parse().
Quoted 122 lines
Quoted 122 lines
net/core/rtnetlink.c +46
-19+ [NDA_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 1), +}; +static int rtnl_fdb_del (struct sk_buff *skb,struct nlmsghdr *nlh,struct netlink_ext_ack *extack) { +bool del_bulk = !!(nlh->nlmsg_flags &NLM_F_BULK );struct net *net =sock_net (skb->sk); +const struct net_device_ops *ops;struct ndmsg *ndm;struct nlattr *tb[NDA_MAX +1 ];struct net_device *dev; -__u8 *addr; +__u8 *addr =NULL ;int err;u16 vid;if (!netlink_capable (skb,CAP_NET_ADMIN ))return -EPERM ; - err =nlmsg_parse_deprecated (nlh,sizeof (*ndm), tb,NDA_MAX ,NULL , - extack); +if (!del_bulk) { + err =nlmsg_parse_deprecated (nlh,sizeof (*ndm), tb,NDA_MAX , +NULL , extack); + }else { + err =nlmsg_parse (nlh,sizeof (*ndm), tb,NDA_MAX , + fdb_del_bulk_policy, extack); + }if (err <0 )return err;@@ -4200,9 +4212,12 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,return -ENODEV ; } -if (!tb[NDA_LLADDR ] ||nla_len (tb[NDA_LLADDR ]) !=ETH_ALEN ) { -NL_SET_ERR_MSG (extack,"invalid address" ); -return -EINVAL ; +if (!del_bulk) { +if (!tb[NDA_LLADDR ] ||nla_len (tb[NDA_LLADDR ]) !=ETH_ALEN ) { +NL_SET_ERR_MSG (extack,"invalid address" ); +return -EINVAL ; + } + addr =nla_data (tb[NDA_LLADDR ]); }if (dev->type !=ARPHRD_ETHER ) {@@ -4210,8 +4225,6 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,return -EINVAL ; } - addr =nla_data (tb[NDA_LLADDR ]); - err =fdb_vid_parse (tb[NDA_VLAN ], &vid, extack);if (err)return err;@@ -4222,10 +4235,16 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,if ((!ndm->ndm_flags || ndm->ndm_flags &NTF_MASTER ) &&netif_is_bridge_port (dev)) {struct net_device *br_dev =netdev_master_upper_dev_get (dev); -const struct net_device_ops *ops = br_dev->netdev_ops; -if (ops->ndo_fdb_del) - err = ops->ndo_fdb_del (ndm, tb, dev, addr, vid); + ops = br_dev->netdev_ops; +if (!del_bulk) { +if (ops->ndo_fdb_del) + err = ops->ndo_fdb_del (ndm, tb, dev, addr, vid); + }else { +if (ops->ndo_fdb_del_bulk) + err = ops->ndo_fdb_del_bulk (ndm, tb, dev, vid, + extack); + }if (err) goto out;@@ -4235,15 +4254,24 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,/* Embedded bridge, macvlan, and any other device support */ if (ndm->ndm_flags &NTF_SELF ) { -if (dev->netdev_ops->ndo_fdb_del) - err = dev->netdev_ops->ndo_fdb_del (ndm, tb, dev, addr, - vid); -else - err =ndo_dflt_fdb_del (ndm, tb, dev, addr, vid); + ops = dev->netdev_ops; +if (!del_bulk) { +if (ops->ndo_fdb_del) + err = ops->ndo_fdb_del (ndm, tb, dev, addr, vid); +else + err =ndo_dflt_fdb_del (ndm, tb, dev, addr, vid); + }else { +/* in case err was cleared by NTF_MASTER call */ + err = -EOPNOTSUPP ; +if (ops->ndo_fdb_del_bulk) + err = ops->ndo_fdb_del_bulk (ndm, tb, dev, vid, + extack); + }if (!err) { -rtnl_fdb_notify (dev, addr, vid,RTM_DELNEIGH , - ndm->ndm_state); +if (!del_bulk) +rtnl_fdb_notify (dev, addr, vid,RTM_DELNEIGH , + ndm->ndm_state); ndm->ndm_flags &= ~NTF_SELF ; } }@@ -6145,7 +6173,8 @@ void __init rtnetlink_init(void)rtnl_register (PF_UNSPEC ,RTM_DELLINKPROP , rtnl_dellinkprop,NULL ,0 );rtnl_register (PF_BRIDGE ,RTM_NEWNEIGH , rtnl_fdb_add,NULL ,0 ); -rtnl_register (PF_BRIDGE ,RTM_DELNEIGH , rtnl_fdb_del,NULL ,0 ); +rtnl_register (PF_BRIDGE ,RTM_DELNEIGH , rtnl_fdb_del,NULL , +RTNL_FLAG_BULK_DEL_SUPPORTED );rtnl_register (PF_BRIDGE ,RTM_GETNEIGH , rtnl_fdb_get, rtnl_fdb_dump,0 );rtnl_register (PF_BRIDGE ,RTM_GETLINK ,NULL , rtnl_bridge_getlink,0 );Signature · 1 line
2.35.1
Re: [PATCH net-next v4 07/12] net: rtnetlink: add NLM_F_BULK support to rtnl_fdb_del
Quoted 35 lines · Nikolay Aleksandrov
Quoted 34 lines · Ido Schimmel
Quoted 22 lines · Nikolay Aleksandrov
When
NLM_F_BULKis specified in a fdb del message we need to handle it differently. First since this is a new call we can strictly validate the passed attributes, at first only ifindex and vlan are allowed as these will be the initially supported filter attributes, any other attribute is rejected. The mac address is no longer mandatory, but we use it to error out in older kernels because it cannot be specified with bulk request (the attribute is not allowed) and then we have to dispatch the call tondo_fdb_del_bulkif the device supports it. The del bulk callback can do further validation of the attributes if necessary.Signed-off-by Nikolay Aleksandrov <[email protected]>---
v4: mark PF_BRIDGE/RTM_DELNEIGH withRTNL_FLAG_BULK_DEL_SUPPORTEDnet/core/rtnetlink.c | 67 +++++++++++++++++++++++++++++++------------- 1 file changed, 48 insertions(+), 19 deletions(-)net/core/rtnetlink.c +0
-0net/core/rtnetlink.c int ndo_dflt_fdb_del(struct ndmsg *ndm, · line 4173
Quoted 5 lines
net/core/rtnetlink.c +2
-0@@ -4169,22 +4169,34 @@ int ndo_dflt_fdb_del(struct ndmsg *ndm, }EXPORT_SYMBOL (ndo_dflt_fdb_del); +static const struct nla_policy fdb_del_bulk_policy[NDA_MAX +1 ] = { + [NDA_VLAN ] = { .type =NLA_U16 },In earlier versions
br_vlan_valid_id()was used to validate the VLAN, but I don't see it anymore. Maybe use
NLA_POLICY_RANGE(1, VLAN_N_VID - 2)
Quoted 7 lines
Quoted 5 lines
?
I realize that invalid values won't do anything, but I think it's better to only allow valid ranges.
It's already validated below, see
fdb_vid_parse().
Sorry, missed it :)
Nikolay Aleksandrov
maintainerPATCH v4 8/12 net: bridge: fdb: add ndo_fdb_del_bulk
In reply to Nikolay AleksandrovAdd a minimal ndo_fdb_del_bulk implementation which flushes all entries. Support for more fine-grained filtering will be added in the following patches.
---
v4: don't rename br_fdb_flush
net/bridge/br_device.c | 1 + net/bridge/br_fdb.c | 23 +++++++++++++++++++++++ net/bridge/br_private.h | 3 +++ 3 files changed, 27 insertions(+)
net/bridge/br_device.c +1 -0
@@ -465,6 +465,7 @@ static const struct net_device_ops br_netdev_ops = { .ndo_fix_features = br_fix_features, .ndo_fdb_add = br_fdb_add, .ndo_fdb_del = br_fdb_delete, + .ndo_fdb_del_bulk = br_fdb_delete_bulk, .ndo_fdb_dump = br_fdb_dump, .ndo_fdb_get = br_fdb_get, .ndo_bridge_getlink = br_getlink,
net/bridge/br_fdb.c +23 -0
@@ -572,6 +572,29 @@ void br_fdb_flush(struct net_bridge *br)spin_unlock_bh (&br->hash_lock); } +int br_fdb_delete_bulk (struct ndmsg *ndm,struct nlattr *tb[], +struct net_device *dev,u16 vid, +struct netlink_ext_ack *extack) +{ +struct net_bridge_port *p =NULL ; +struct net_bridge *br; + +if (netif_is_bridge_master (dev)) { + br =netdev_priv (dev); + }else { + p =br_port_get_rtnl (dev); +if (!p) { +NL_SET_ERR_MSG_MOD (extack,"Device is not a bridge port" ); +return -EINVAL ; + } + br = p->br; + } + +br_fdb_flush (br); + +return 0 ; +} +/* Flush all entries referring to a specific port. * if do_all is set also flush static entries * if vid is set delete all entries that match the vlan_id
net/bridge/br_private.h +3 -0
@@ -781,6 +781,9 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,int br_fdb_delete (struct ndmsg *ndm,struct nlattr *tb[],struct net_device *dev,const unsigned char *addr,u16 vid); +int br_fdb_delete_bulk (struct ndmsg *ndm,struct nlattr *tb[], +struct net_device *dev,u16 vid, +struct netlink_ext_ack *extack);int br_fdb_add (struct ndmsg *nlh,struct nlattr *tb[],struct net_device *dev,const unsigned char *addr,u16 vid,u16 nlh_flags,struct netlink_ext_ack *extack);
Signature · 1 line
2.35.1
Nikolay Aleksandrov
maintainerPATCH v4 9/12 net: bridge: fdb: add support for fine-grained flushing
In reply to Nikolay AleksandrovAdd the ability to specify exactly which fdbs to be flushed. They are described by a new structure - net_bridge_fdb_flush_desc. Currently it can match on port/bridge ifindex, vlan id and fdb flags. It is used to describe the existing dynamic fdb flush operation. Note that this flush operation doesn't treat permanent entries in a special way (fdb_delete vs fdb_delete_local), it will delete them regardless if any port is using them, so currently it can't directly replace deletes which need to handle that case, although we can extend it later for that too.
---
v2: changed the flush matches func for better readability (Ido)
net/bridge/br_fdb.c | 41 ++++++++++++++++++++++++++++++++-------- net/bridge/br_netlink.c | 9 +++++++-- net/bridge/br_private.h | 10 +++++++++- net/bridge/br_sysfs_br.c | 6 +++++- 4 files changed, 54 insertions(+), 12 deletions(-)
net/bridge/br_fdb.c +33 -8
@@ -558,24 +558,49 @@ void br_fdb_cleanup(struct work_struct *work)mod_delayed_work (system_long_wq, &br->gc_work, work_delay); } -/* Completely flush all dynamic entries in forwarding database.*/ -void br_fdb_flush (struct net_bridge *br) +static bool __fdb_flush_matches (const struct net_bridge *br, +const struct net_bridge_fdb_entry *f, +const struct net_bridge_fdb_flush_desc *desc) +{ +const struct net_bridge_port *dst =READ_ONCE (f->dst); +int port_ifidx = dst ? dst->dev->ifindex : br->dev->ifindex; + +if (desc->vlan_id && desc->vlan_id != f->key.vlan_id) +return false; +if (desc->port_ifindex && desc->port_ifindex != port_ifidx) +return false; +if (desc->flags_mask && (f->flags & desc->flags_mask) != desc->flags) +return false; + +return true; +} + +/* Flush forwarding database entries matching the description */ +void br_fdb_flush (struct net_bridge *br, +const struct net_bridge_fdb_flush_desc *desc) {struct net_bridge_fdb_entry *f; -struct hlist_node *tmp; -spin_lock_bh (&br->hash_lock); -hlist_for_each_entry_safe (f, tmp, &br->fdb_list, fdb_node) { -if (!test_bit (BR_FDB_STATIC , &f->flags)) +rcu_read_lock (); +hlist_for_each_entry_rcu (f, &br->fdb_list, fdb_node) { +if (!__fdb_flush_matches (br, f, desc)) +continue ; + +spin_lock_bh (&br->hash_lock); +if (!hlist_unhashed (&f->fdb_node))fdb_delete (br, f, true); +spin_unlock_bh (&br->hash_lock); } -spin_unlock_bh (&br->hash_lock); +rcu_read_unlock (); }int br_fdb_delete_bulk (struct ndmsg *ndm,struct nlattr *tb[],struct net_device *dev,u16 vid,struct netlink_ext_ack *extack) { +struct net_bridge_fdb_flush_desc desc = { + .flags_mask =BR_FDB_STATIC + };struct net_bridge_port *p =NULL ;struct net_bridge *br;
@@ -590,7 +615,7 @@ int br_fdb_delete_bulk(struct ndmsg *ndm, struct nlattr *tb[], br = p->br; } -br_fdb_flush (br); +br_fdb_flush (br, &desc);return 0 ; }
net/bridge/br_netlink.c +7 -2
@@ -1326,8 +1326,13 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[],br_recalculate_fwd_mask (br); } -if (data[IFLA_BR_FDB_FLUSH ]) -br_fdb_flush (br); +if (data[IFLA_BR_FDB_FLUSH ]) { +struct net_bridge_fdb_flush_desc desc = { + .flags_mask =BR_FDB_STATIC + }; + +br_fdb_flush (br, &desc); + }#ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (data[IFLA_BR_MCAST_ROUTER ]) {
net/bridge/br_private.h +9 -1
@@ -274,6 +274,13 @@ struct net_bridge_fdb_entry {struct rcu_head rcu; }; +struct net_bridge_fdb_flush_desc { +unsigned long flags; +unsigned long flags_mask; +int port_ifindex; +u16 vlan_id; +}; +#define MDB_PG_FLAGS_PERMANENT BIT(0)#define MDB_PG_FLAGS_OFFLOAD BIT(1)#define MDB_PG_FLAGS_FAST_LEAVE BIT(2)
@@ -759,7 +766,8 @@ int br_fdb_init(void);void br_fdb_fini (void );int br_fdb_hash_init (struct net_bridge *br);void br_fdb_hash_fini (struct net_bridge *br); -void br_fdb_flush (struct net_bridge *br); +void br_fdb_flush (struct net_bridge *br, +const struct net_bridge_fdb_flush_desc *desc);void br_fdb_find_delete_local (struct net_bridge *br,const struct net_bridge_port *p,const unsigned char *addr,u16 vid);
net/bridge/br_sysfs_br.c +5 -1
@@ -344,7 +344,11 @@ static DEVICE_ATTR_RW(group_addr);static int set_flush (struct net_bridge *br,unsigned long val,struct netlink_ext_ack *extack) { -br_fdb_flush (br); +struct net_bridge_fdb_flush_desc desc = { + .flags_mask =BR_FDB_STATIC + }; + +br_fdb_flush (br, &desc);return 0 ; }
Signature · 1 line
2.35.1
Nikolay Aleksandrov
maintainerPATCH v4 10/12 net: rtnetlink: add ndm flags and state mask attributes
In reply to Nikolay AleksandrovAdd ndm flags/state masks which will be used for bulk delete filtering. All of these are used by the bridge and vxlan drivers. Also minimal attr policy validation is added, it is up to ndo_fdb_del_bulk implementers to further validate them.
--- include/uapi/linux/neighbour.h | 2 ++ net/core/rtnetlink.c | 2 ++ 2 files changed, 4 insertions(+)
include/uapi/linux/neighbour.h +2 -0
@@ -32,6 +32,8 @@ enum {NDA_NH_ID ,NDA_FDB_EXT_ATTRS ,NDA_FLAGS_EXT , +NDA_NDM_STATE_MASK , +NDA_NDM_FLAGS_MASK , __NDA_MAX };
net/core/rtnetlink.c +2 -0
@@ -4172,6 +4172,8 @@ EXPORT_SYMBOL(ndo_dflt_fdb_del);static const struct nla_policy fdb_del_bulk_policy[NDA_MAX +1 ] = { [NDA_VLAN ] = { .type =NLA_U16 }, [NDA_IFINDEX ] =NLA_POLICY_MIN (NLA_S32 ,1 ), + [NDA_NDM_STATE_MASK ] = { .type =NLA_U16 }, + [NDA_NDM_FLAGS_MASK ] = { .type =NLA_U8 }, }; static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
Signature · 1 line
2.35.1
Nikolay Aleksandrov
maintainerPATCH v4 11/12 net: bridge: fdb: add support for flush filtering based on ndm flags and state
In reply to Nikolay AleksandrovAdd support for fdb flush filtering based on ndm flags and state. NDM state and flags are mapped to bridge-specific flags and matched according to the specified masks. NTF_USE is used to represent added_by_user flag since it sets it on fdb add and we don't have a 1:1 mapping for it. Only allowed bits can be set, NTF_SELF and NTF_MASTER are ignored.
---
v2: ignore NTF_USE/NTF_MASTER and reject unknown flags
v3: NDFA -> NDA attributes
net/bridge/br_fdb.c | 58 ++++++++++++++++++++++++++++++++++++++--- net/bridge/br_private.h | 5 ++++ 2 files changed, 60 insertions(+), 3 deletions(-)
net/bridge/br_fdb.c +55 -3
@@ -594,13 +594,40 @@ void br_fdb_flush(struct net_bridge *br,rcu_read_unlock (); } +static unsigned long __ndm_state_to_fdb_flags (u16 ndm_state) +{ +unsigned long flags =0 ; + +if (ndm_state &NUD_PERMANENT ) +__set_bit (BR_FDB_LOCAL , &flags); +if (ndm_state &NUD_NOARP ) +__set_bit (BR_FDB_STATIC , &flags); + +return flags; +} + +static unsigned long __ndm_flags_to_fdb_flags (u8 ndm_flags) +{ +unsigned long flags =0 ; + +if (ndm_flags &NTF_USE ) +__set_bit (BR_FDB_ADDED_BY_USER , &flags); +if (ndm_flags &NTF_EXT_LEARNED ) +__set_bit (BR_FDB_ADDED_BY_EXT_LEARN , &flags); +if (ndm_flags &NTF_OFFLOADED ) +__set_bit (BR_FDB_OFFLOADED , &flags); +if (ndm_flags &NTF_STICKY ) +__set_bit (BR_FDB_STICKY , &flags); + +return flags; +} +int br_fdb_delete_bulk (struct ndmsg *ndm,struct nlattr *tb[],struct net_device *dev,u16 vid,struct netlink_ext_ack *extack) { -struct net_bridge_fdb_flush_desc desc = { - .flags_mask =BR_FDB_STATIC - }; +u8 ndm_flags = ndm->ndm_flags & ~FDB_FLUSH_IGNORED_NDM_FLAGS ; +struct net_bridge_fdb_flush_desc desc = {};struct net_bridge_port *p =NULL ;struct net_bridge *br;
@@ -615,6 +642,31 @@ int br_fdb_delete_bulk(struct ndmsg *ndm, struct nlattr *tb[], br = p->br; } +if (ndm_flags & ~FDB_FLUSH_ALLOWED_NDM_FLAGS ) { +NL_SET_ERR_MSG (extack,"Unsupported fdb flush ndm flag bits set" ); +return -EINVAL ; + } +if (ndm->ndm_state & ~FDB_FLUSH_ALLOWED_NDM_STATES ) { +NL_SET_ERR_MSG (extack,"Unsupported fdb flush ndm state bits set" ); +return -EINVAL ; + } + + desc.flags |=__ndm_state_to_fdb_flags (ndm->ndm_state); + desc.flags |=__ndm_flags_to_fdb_flags (ndm_flags); +if (tb[NDA_NDM_STATE_MASK ]) { +u16 ndm_state_mask =nla_get_u16 (tb[NDA_NDM_STATE_MASK ]); + + desc.flags_mask |=__ndm_state_to_fdb_flags (ndm_state_mask); + } +if (tb[NDA_NDM_FLAGS_MASK ]) { +u8 ndm_flags_mask =nla_get_u8 (tb[NDA_NDM_FLAGS_MASK ]); + + desc.flags_mask |=__ndm_flags_to_fdb_flags (ndm_flags_mask); + } + +br_debug (br,"flushing port ifindex: %d vlan id: %u flags: 0x%lx flags mask: 0x%lx\n" , + desc.port_ifindex, desc.vlan_id, desc.flags, desc.flags_mask); +br_fdb_flush (br, &desc);return 0 ;
net/bridge/br_private.h +5 -0
@@ -762,6 +762,11 @@ static inline void br_netpoll_disable(struct net_bridge_port *p)#endif /* br_fdb.c */ +#define FDB_FLUSH_IGNORED_NDM_FLAGS (NTF_MASTER | NTF_SELF) +#define FDB_FLUSH_ALLOWED_NDM_STATES (NUD_PERMANENT | NUD_NOARP) +#define FDB_FLUSH_ALLOWED_NDM_FLAGS (NTF_USE | NTF_EXT_LEARNED | \ + NTF_STICKY | NTF_OFFLOADED) +int br_fdb_init (void );void br_fdb_fini (void );int br_fdb_hash_init (struct net_bridge *br);
Signature · 1 line
2.35.1
Nikolay Aleksandrov
maintainerPATCH v4 12/12 net: bridge: fdb: add support for flush filtering based on ifindex and vlan
In reply to Nikolay AleksandrovAdd support for fdb flush filtering based on destination ifindex and vlan id. The ifindex must either match a port's device ifindex or the bridge's. The vlan support is trivial since it's already validated by rtnl_fdb_del, we just need to fill it in.
---
v2: validate ifindex and fill in vlan id
v3: NDFA -> NDA attributes
v4: use port's ifindex if NTF_MASTER is used and NDA_IFINDEX is not
specified
net/bridge/br_fdb.c | 45 ++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 44 insertions(+), 1 deletion(-)
net/bridge/br_fdb.c +44 -1
@@ -622,12 +622,44 @@ static unsigned long __ndm_flags_to_fdb_flags(u8 ndm_flags)return flags; } +static int __fdb_flush_validate_ifindex (const struct net_bridge *br, +int ifindex, +struct netlink_ext_ack *extack) +{ +const struct net_device *dev; + + dev =__dev_get_by_index (dev_net (br->dev), ifindex); +if (!dev) { +NL_SET_ERR_MSG_MOD (extack,"Unknown flush device ifindex" ); +return -ENODEV ; + } +if (!netif_is_bridge_master (dev) && !netif_is_bridge_port (dev)) { +NL_SET_ERR_MSG_MOD (extack,"Flush device is not a bridge or bridge port" ); +return -EINVAL ; + } +if (netif_is_bridge_master (dev) && dev != br->dev) { +NL_SET_ERR_MSG_MOD (extack, +"Flush bridge device does not match target bridge device" ); +return -EINVAL ; + } +if (netif_is_bridge_port (dev)) { +struct net_bridge_port *p =br_port_get_rtnl (dev); + +if (p->br != br) { +NL_SET_ERR_MSG_MOD (extack,"Port belongs to a different bridge device" ); +return -EINVAL ; + } + } + +return 0 ; +} +int br_fdb_delete_bulk (struct ndmsg *ndm,struct nlattr *tb[],struct net_device *dev,u16 vid,struct netlink_ext_ack *extack) {u8 ndm_flags = ndm->ndm_flags & ~FDB_FLUSH_IGNORED_NDM_FLAGS ; -struct net_bridge_fdb_flush_desc desc = {}; +struct net_bridge_fdb_flush_desc desc = { .vlan_id = vid };struct net_bridge_port *p =NULL ;struct net_bridge *br;
@@ -663,6 +695,17 @@ int br_fdb_delete_bulk(struct ndmsg *ndm, struct nlattr *tb[], desc.flags_mask |=__ndm_flags_to_fdb_flags (ndm_flags_mask); } +if (tb[NDA_IFINDEX ]) { +int err, ifidx =nla_get_s32 (tb[NDA_IFINDEX ]); + + err =__fdb_flush_validate_ifindex (br, ifidx, extack); +if (err) +return err; + desc.port_ifindex = ifidx; + }else if (p) { +/* flush was invoked with port device and NTF_MASTER */ + desc.port_ifindex = p->dev->ifindex; + }br_debug (br,"flushing port ifindex: %d vlan id: %u flags: 0x%lx flags mask: 0x%lx\n" , desc.port_ifindex, desc.vlan_id, desc.flags, desc.flags_mask);
Signature · 1 line
2.35.1
This series was applied to netdev/net-next.git (master) by David S. Miller <[email protected]>:
Hello:
This series was applied to netdev/net-next.git (master) by David S. Miller <[email protected]>:
Quoted 16 lines · On Wed, 13 Apr 2022 13:51:50 +0300 you wrote:
Hi,
This patch-set adds support to specify filtering conditions for a bulk delete (flush) operation. This version uses a new nlmsghdr delete flag calledNLM_F_BULKin combination with a newndo_fdb_del_bulkop which is used to signal that the driver supports bulk deletes (that avoids pushing common mac address checks tondo_fdb_delimplementations and also has a different prototype and parsed attribute expectations, more info in patch 03). The new delete flag can be used for any RTM_DEL* type, implementations just need to be careful with older kernels which are doing non-strict attribute parses. A new rtnl flag (RTNL_FLAG_BULK_DEL_SUPPORTED) is used to show that the delete supportsNLM_F_BULK. A proper error is returned if bulk delete is not supported. For old kernels I use the fact that mac address attribute (lladdr) is mandatory in the classic fdb del case, but it's not allowed if bulk deleting so older kernels will error out.
Quoted 1 line
[...]
Here is the summary with links:
- [net-next,v4,01/12] net: rtnetlink: add msg kind names
https://git.kernel.org/netdev/net-next/c/12dc5c2cb7b2 - [net-next,v4,02/12] net: rtnetlink: add helper to extract msg type's kind https://git.kernel.org/netdev/net-next/c/2e9ea3e30f69 - [net-next,v4,03/12] net: rtnetlink: use BIT for flag values https://git.kernel.org/netdev/net-next/c/0569e31f1bc2 - [net-next,v4,04/12] net: netlink: add NLM_F_BULK delete request modifier https://git.kernel.org/netdev/net-next/c/545528d78855 - [net-next,v4,05/12] net: rtnetlink: add bulk delete support flag https://git.kernel.org/netdev/net-next/c/a6cec0bcd342 - [net-next,v4,06/12] net: add ndo_fdb_del_bulk https://git.kernel.org/netdev/net-next/c/1306d5362a59 - [net-next,v4,07/12] net: rtnetlink: add NLM_F_BULK support to rtnl_fdb_del https://git.kernel.org/netdev/net-next/c/9e83425993f3 - [net-next,v4,08/12] net: bridge: fdb: add ndo_fdb_del_bulk https://git.kernel.org/netdev/net-next/c/edaef1917224 - [net-next,v4,09/12] net: bridge: fdb: add support for fine-grained flushing https://git.kernel.org/netdev/net-next/c/1f78ee14eeac - [net-next,v4,10/12] net: rtnetlink: add ndm flags and state mask attributes https://git.kernel.org/netdev/net-next/c/ea2c0f9e3fc2 - [net-next,v4,11/12] net: bridge: fdb: add support for flush filtering based on ndm flags and state https://git.kernel.org/netdev/net-next/c/564445fb4f0f - [net-next,v4,12/12] net: bridge: fdb: add support for flush filtering based on ifindex and vlan https://git.kernel.org/netdev/net-next/c/0dbe886a4d8d
You are awesome, thank you!
Signature · 2 lines
Deet-doot-dot, I am a bot. https://korg.docs.kernel.org/patchwork/pwbot.html