From fbdd90ea830162960fb8fbe377dfef9a54d74d2f Mon Sep 17 00:00:00 2001 From: Eyal Shapira Date: Mon, 11 Nov 2013 20:14:00 +0200 Subject: mac80211: enable easier manipulation of VHT beamforming caps Introduce shift and mask defines for beamformee STS cap and number of sounding dimensions cap as these can take any 3 bit value. While at it also cleanup an unrequired parenthesis. Signed-off-by: Eyal Shapira Reviewed-by: Johannes Berg Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 8c3b26a21574..776cbb80d098 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1411,8 +1411,12 @@ struct ieee80211_vht_operation { #define IEEE80211_VHT_CAP_RXSTBC_MASK 0x00000700 #define IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE 0x00000800 #define IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE 0x00001000 -#define IEEE80211_VHT_CAP_BEAMFORMEE_STS_MAX 0x0000e000 -#define IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_MAX 0x00070000 +#define IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT 13 +#define IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK \ + (7 << IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT) +#define IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_SHIFT 16 +#define IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_MASK \ + (7 << IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_SHIFT) #define IEEE80211_VHT_CAP_MU_BEAMFORMER_CAPABLE 0x00080000 #define IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE 0x00100000 #define IEEE80211_VHT_CAP_VHT_TXOP_PS 0x00200000 -- cgit v1.3-14-g43fede From 4b2f13a25133b115eb56771bd4a8e71a82aea968 Mon Sep 17 00:00:00 2001 From: Jeff Kirsher Date: Fri, 6 Dec 2013 06:28:48 -0800 Subject: sctp: Fix FSF address in file headers Several files refer to an old address for the Free Software Foundation in the file header comment. Resolve by replacing the address with the URL so that we do not have to keep updating the header comments anytime the address changes. CC: Vlad Yasevich CC: Neil Horman Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- include/linux/sctp.h | 5 ++--- include/net/sctp/sctp.h | 5 ++--- include/net/sctp/sm.h | 5 ++--- include/net/sctp/structs.h | 5 ++--- include/net/sctp/tsnmap.h | 5 ++--- include/net/sctp/ulpevent.h | 5 ++--- include/net/sctp/ulpqueue.h | 5 ++--- include/uapi/linux/sctp.h | 5 ++--- net/sctp/associola.c | 5 ++--- net/sctp/auth.c | 5 ++--- net/sctp/bind_addr.c | 5 ++--- net/sctp/chunk.c | 5 ++--- net/sctp/command.c | 5 ++--- net/sctp/debug.c | 5 ++--- net/sctp/endpointola.c | 5 ++--- net/sctp/input.c | 5 ++--- net/sctp/inqueue.c | 5 ++--- net/sctp/ipv6.c | 5 ++--- net/sctp/objcnt.c | 5 ++--- net/sctp/output.c | 5 ++--- net/sctp/outqueue.c | 5 ++--- net/sctp/primitive.c | 5 ++--- net/sctp/proc.c | 5 ++--- net/sctp/protocol.c | 5 ++--- net/sctp/sm_make_chunk.c | 5 ++--- net/sctp/sm_sideeffect.c | 5 ++--- net/sctp/sm_statefuns.c | 5 ++--- net/sctp/sm_statetable.c | 5 ++--- net/sctp/socket.c | 5 ++--- net/sctp/ssnmap.c | 5 ++--- net/sctp/sysctl.c | 5 ++--- net/sctp/transport.c | 5 ++--- net/sctp/tsnmap.c | 5 ++--- net/sctp/ulpevent.c | 5 ++--- net/sctp/ulpqueue.c | 5 ++--- 35 files changed, 70 insertions(+), 105 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 3bfe8d6ee248..c4c5eba26d9f 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -23,9 +23,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index c5fe80697f8d..610a8c8738fa 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -21,9 +21,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index 4ef75af340b6..7f4eeb340a54 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -21,9 +21,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email addresses: diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index ea0ca5f6e629..e416d6ac9c70 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -19,9 +19,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email addresses: diff --git a/include/net/sctp/tsnmap.h b/include/net/sctp/tsnmap.h index 54bbbe547303..31b8dbaad45a 100644 --- a/include/net/sctp/tsnmap.h +++ b/include/net/sctp/tsnmap.h @@ -22,9 +22,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/include/net/sctp/ulpevent.h b/include/net/sctp/ulpevent.h index 27b9f5c90153..daacb32b55b5 100644 --- a/include/net/sctp/ulpevent.h +++ b/include/net/sctp/ulpevent.h @@ -25,9 +25,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/include/net/sctp/ulpqueue.h b/include/net/sctp/ulpqueue.h index b0cf5d54d717..e0dce07b8794 100644 --- a/include/net/sctp/ulpqueue.h +++ b/include/net/sctp/ulpqueue.h @@ -24,9 +24,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email addresses: diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index ca451e99b28b..266022a2be4a 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -22,9 +22,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 68a27f9796d2..66882a26713b 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -22,9 +22,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 46b5977978a1..5c9f64c1c906 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -16,9 +16,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index 077bb070052b..871cdf9567e6 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -21,9 +21,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index f2044fcb9dd1..5573e425b0c0 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -18,9 +18,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/command.c b/net/sctp/command.c index 3d9a9ff69c03..dd7375851618 100644 --- a/net/sctp/command.c +++ b/net/sctp/command.c @@ -19,9 +19,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/debug.c b/net/sctp/debug.c index e89015d8935a..95d7b15dad21 100644 --- a/net/sctp/debug.c +++ b/net/sctp/debug.c @@ -22,9 +22,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 09b8daac87c8..6ffb6c1b13b7 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -23,9 +23,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/input.c b/net/sctp/input.c index 98b69bbecdd9..66038533ca5c 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -23,9 +23,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 5856932fdc38..4de12afa13d4 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -24,9 +24,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 7567e6f1a920..32db816ffbaa 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -21,9 +21,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/objcnt.c b/net/sctp/objcnt.c index 647396baa56f..0c28e8a55324 100644 --- a/net/sctp/objcnt.c +++ b/net/sctp/objcnt.c @@ -20,9 +20,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/output.c b/net/sctp/output.c index 0e2644d0a773..6371337e1fe7 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -20,9 +20,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index f51ba985a36e..b6b09f3f1a81 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -22,9 +22,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/primitive.c b/net/sctp/primitive.c index ce1ffd811775..ab8d9f96a177 100644 --- a/net/sctp/primitive.c +++ b/net/sctp/primitive.c @@ -23,9 +23,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 0c0642156842..de32e14f7398 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -16,9 +16,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 5e17092f4ada..19bd4c5bdae9 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -23,9 +23,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index fe690320b1e4..d9aaf9641aaa 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -23,9 +23,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 1a6eef39ab2f..02b7ad1ff467 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -22,9 +22,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index dfe3f36ff2aa..dd0eba919a8b 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -22,9 +22,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/sm_statetable.c b/net/sctp/sm_statetable.c index c5999b2dde7d..a4f17437fb22 100644 --- a/net/sctp/sm_statetable.c +++ b/net/sctp/sm_statetable.c @@ -22,9 +22,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 72046b9729a8..191cd9257806 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -28,9 +28,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/ssnmap.c b/net/sctp/ssnmap.c index 6007124aefa0..b9c8521c1a98 100644 --- a/net/sctp/ssnmap.c +++ b/net/sctp/ssnmap.c @@ -18,9 +18,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 6b36561a1b3b..80b17b5df6bb 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -19,9 +19,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/transport.c b/net/sctp/transport.c index e332efb124cc..1d4f3ac29baf 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -24,9 +24,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/tsnmap.c b/net/sctp/tsnmap.c index fbda20028285..7635f9f2311d 100644 --- a/net/sctp/tsnmap.c +++ b/net/sctp/tsnmap.c @@ -21,9 +21,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 81089ed65456..85c64658bd0b 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -22,9 +22,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index 1c1484ed605d..a67470083be8 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -21,9 +21,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): -- cgit v1.3-14-g43fede From e9fbdf176d2a7993b9d4c487b50c68d1c6019b2c Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 5 Dec 2013 14:52:13 -0800 Subject: net: phy: breakdown PHY_*_FEATURES defines Breakdown the PHY_*_FEATURES into per speed defines such that we can easily re-use them individually. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 48a4dc3cb8cf..7ff751ae6f0a 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -27,18 +27,27 @@ #include -#define PHY_BASIC_FEATURES (SUPPORTED_10baseT_Half | \ - SUPPORTED_10baseT_Full | \ - SUPPORTED_100baseT_Half | \ - SUPPORTED_100baseT_Full | \ - SUPPORTED_Autoneg | \ +#define PHY_DEFAULT_FEATURES (SUPPORTED_Autoneg | \ SUPPORTED_TP | \ SUPPORTED_MII) -#define PHY_GBIT_FEATURES (PHY_BASIC_FEATURES | \ - SUPPORTED_1000baseT_Half | \ +#define PHY_10BT_FEATURES (SUPPORTED_10baseT_Half | \ + SUPPORTED_10baseT_Full) + +#define PHY_100BT_FEATURES (SUPPORTED_100baseT_Half | \ + SUPPORTED_100baseT_Full) + +#define PHY_1000BT_FEATURES (SUPPORTED_1000baseT_Half | \ SUPPORTED_1000baseT_Full) +#define PHY_BASIC_FEATURES (PHY_10BT_FEATURES | \ + PHY_100BT_FEATURES | \ + PHY_DEFAULT_FEATURES) + +#define PHY_GBIT_FEATURES (PHY_BASIC_FEATURES | \ + PHY_1000BT_FEATURES) + + /* * Set phydev->irq to PHY_POLL if interrupts are not supported, * or not desired for this PHY. Set to PHY_IGNORE_INTERRUPT if -- cgit v1.3-14-g43fede From e6247027e5173c00efb2084d688d06ff835bc3b0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 5 Dec 2013 04:45:08 -0800 Subject: net: introduce dev_consume_skb_any() Some network drivers use dev_kfree_skb_any() and dev_kfree_skb_irq() helpers to free skbs, both for dropped packets and TX completed ones. We need to separate the two causes to get better diagnostics given by dropwatch or "perf record -e skb:kfree_skb" This patch provides two new helpers, dev_consume_skb_any() and dev_consume_skb_irq() to be used for consumed skbs. __dev_kfree_skb_irq() is slightly optimized to remove one atomic_dec_and_test() in fast path, and use this_cpu_{r|w} accessors. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 53 +++++++++++++++++++++++++++++++++++++++-------- net/core/dev.c | 45 ++++++++++++++++++++++++++-------------- 2 files changed, 74 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7f0ed423a360..9d55e5188b96 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2368,17 +2368,52 @@ static inline int netif_copy_real_num_queues(struct net_device *to_dev, #define DEFAULT_MAX_NUM_RSS_QUEUES (8) int netif_get_num_default_rss_queues(void); -/* Use this variant when it is known for sure that it - * is executing from hardware interrupt context or with hardware interrupts - * disabled. - */ -void dev_kfree_skb_irq(struct sk_buff *skb); +enum skb_free_reason { + SKB_REASON_CONSUMED, + SKB_REASON_DROPPED, +}; + +void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason); +void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason); -/* Use this variant in places where it could be invoked - * from either hardware interrupt or other context, with hardware interrupts - * either disabled or enabled. +/* + * It is not allowed to call kfree_skb() or consume_skb() from hardware + * interrupt context or with hardware interrupts being disabled. + * (in_irq() || irqs_disabled()) + * + * We provide four helpers that can be used in following contexts : + * + * dev_kfree_skb_irq(skb) when caller drops a packet from irq context, + * replacing kfree_skb(skb) + * + * dev_consume_skb_irq(skb) when caller consumes a packet from irq context. + * Typically used in place of consume_skb(skb) in TX completion path + * + * dev_kfree_skb_any(skb) when caller doesn't know its current irq context, + * replacing kfree_skb(skb) + * + * dev_consume_skb_any(skb) when caller doesn't know its current irq context, + * and consumed a packet. Used in place of consume_skb(skb) */ -void dev_kfree_skb_any(struct sk_buff *skb); +static inline void dev_kfree_skb_irq(struct sk_buff *skb) +{ + __dev_kfree_skb_irq(skb, SKB_REASON_DROPPED); +} + +static inline void dev_consume_skb_irq(struct sk_buff *skb) +{ + __dev_kfree_skb_irq(skb, SKB_REASON_CONSUMED); +} + +static inline void dev_kfree_skb_any(struct sk_buff *skb) +{ + __dev_kfree_skb_any(skb, SKB_REASON_DROPPED); +} + +static inline void dev_consume_skb_any(struct sk_buff *skb) +{ + __dev_kfree_skb_any(skb, SKB_REASON_CONSUMED); +} int netif_rx(struct sk_buff *skb); int netif_rx_ni(struct sk_buff *skb); diff --git a/net/core/dev.c b/net/core/dev.c index c98052487e98..6cc98dd49c7a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2145,30 +2145,42 @@ void __netif_schedule(struct Qdisc *q) } EXPORT_SYMBOL(__netif_schedule); -void dev_kfree_skb_irq(struct sk_buff *skb) +struct dev_kfree_skb_cb { + enum skb_free_reason reason; +}; + +static struct dev_kfree_skb_cb *get_kfree_skb_cb(const struct sk_buff *skb) +{ + return (struct dev_kfree_skb_cb *)skb->cb; +} + +void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason) { - if (atomic_dec_and_test(&skb->users)) { - struct softnet_data *sd; - unsigned long flags; + unsigned long flags; - local_irq_save(flags); - sd = &__get_cpu_var(softnet_data); - skb->next = sd->completion_queue; - sd->completion_queue = skb; - raise_softirq_irqoff(NET_TX_SOFTIRQ); - local_irq_restore(flags); + if (likely(atomic_read(&skb->users) == 1)) { + smp_rmb(); + atomic_set(&skb->users, 0); + } else if (likely(!atomic_dec_and_test(&skb->users))) { + return; } + get_kfree_skb_cb(skb)->reason = reason; + local_irq_save(flags); + skb->next = __this_cpu_read(softnet_data.completion_queue); + __this_cpu_write(softnet_data.completion_queue, skb); + raise_softirq_irqoff(NET_TX_SOFTIRQ); + local_irq_restore(flags); } -EXPORT_SYMBOL(dev_kfree_skb_irq); +EXPORT_SYMBOL(__dev_kfree_skb_irq); -void dev_kfree_skb_any(struct sk_buff *skb) +void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason) { if (in_irq() || irqs_disabled()) - dev_kfree_skb_irq(skb); + __dev_kfree_skb_irq(skb, reason); else dev_kfree_skb(skb); } -EXPORT_SYMBOL(dev_kfree_skb_any); +EXPORT_SYMBOL(__dev_kfree_skb_any); /** @@ -3306,7 +3318,10 @@ static void net_tx_action(struct softirq_action *h) clist = clist->next; WARN_ON(atomic_read(&skb->users)); - trace_kfree_skb(skb, net_tx_action); + if (likely(get_kfree_skb_cb(skb)->reason == SKB_REASON_CONSUMED)) + trace_consume_skb(skb); + else + trace_kfree_skb(skb, net_tx_action); __kfree_skb(skb); } } -- cgit v1.3-14-g43fede From 0d74c42f788caf3cad727c61c490d9459bc8918b Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 5 Dec 2013 14:54:38 -0800 Subject: ether_addr_equal: Optimize implementation, remove unused compare_ether_addr Add a new check for CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS to reduce the number of or's used in the ether_addr_equal comparison to very slightly improve function performance. Simplify the ether_addr_equal_64bits implementation. Integrate and remove the zap_last_2bytes helper as it's now used only once. Remove the now unused compare_ether_addr function. Update the unaligned-memory-access documentation to remove the compare_ether_addr description and show how unaligned accesses could occur with ether_addr_equal. Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- Documentation/unaligned-memory-access.txt | 28 +++++++++++------ include/linux/etherdevice.h | 51 +++++++++++-------------------- 2 files changed, 37 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/Documentation/unaligned-memory-access.txt b/Documentation/unaligned-memory-access.txt index f866c72291bf..a445da098bc6 100644 --- a/Documentation/unaligned-memory-access.txt +++ b/Documentation/unaligned-memory-access.txt @@ -137,24 +137,34 @@ Code that causes unaligned access ================================= With the above in mind, let's move onto a real life example of a function -that can cause an unaligned memory access. The following function adapted +that can cause an unaligned memory access. The following function taken from include/linux/etherdevice.h is an optimized routine to compare two ethernet MAC addresses for equality. -unsigned int compare_ether_addr(const u8 *addr1, const u8 *addr2) +bool ether_addr_equal(const u8 *addr1, const u8 *addr2) { - const u16 *a = (const u16 *) addr1; - const u16 *b = (const u16 *) addr2; +#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + u32 fold = ((*(const u32 *)addr1) ^ (*(const u32 *)addr2)) | + ((*(const u16 *)(addr1 + 4)) ^ (*(const u16 *)(addr2 + 4))); + + return fold == 0; +#else + const u16 *a = (const u16 *)addr1; + const u16 *b = (const u16 *)addr2; return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | (a[2] ^ b[2])) != 0; +#endif } -In the above function, the reference to a[0] causes 2 bytes (16 bits) to -be read from memory starting at address addr1. Think about what would happen -if addr1 was an odd address such as 0x10003. (Hint: it'd be an unaligned -access.) +In the above function, when the hardware has efficient unaligned access +capability, there is no issue with this code. But when the hardware isn't +able to access memory on arbitrary boundaries, the reference to a[0] causes +2 bytes (16 bits) to be read from memory starting at address addr1. + +Think about what would happen if addr1 was an odd address such as 0x10003. +(Hint: it'd be an unaligned access.) Despite the potential unaligned access problems with the above function, it -is included in the kernel anyway but is understood to only work on +is included in the kernel anyway but is understood to only work normally on 16-bit-aligned addresses. It is up to the caller to ensure this alignment or not use this function at all. This alignment-unsafe function is still useful as it is a decent optimization for the cases when you can ensure alignment, diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index fc4a9aa7dd82..3526e819d7ae 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -26,6 +26,7 @@ #include #include #include +#include #ifdef __KERNEL__ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); @@ -210,41 +211,27 @@ static inline void eth_hw_addr_inherit(struct net_device *dst, memcpy(dst->dev_addr, src->dev_addr, ETH_ALEN); } -/** - * compare_ether_addr - Compare two Ethernet addresses - * @addr1: Pointer to a six-byte array containing the Ethernet address - * @addr2: Pointer other six-byte array containing the Ethernet address - * - * Compare two Ethernet addresses, returns 0 if equal, non-zero otherwise. - * Unlike memcmp(), it doesn't return a value suitable for sorting. - */ -static inline unsigned compare_ether_addr(const u8 *addr1, const u8 *addr2) -{ - const u16 *a = (const u16 *) addr1; - const u16 *b = (const u16 *) addr2; - - BUILD_BUG_ON(ETH_ALEN != 6); - return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | (a[2] ^ b[2])) != 0; -} - /** * ether_addr_equal - Compare two Ethernet addresses * @addr1: Pointer to a six-byte array containing the Ethernet address * @addr2: Pointer other six-byte array containing the Ethernet address * * Compare two Ethernet addresses, returns true if equal + * + * Please note: addr1 & addr2 must both be aligned to u16. */ static inline bool ether_addr_equal(const u8 *addr1, const u8 *addr2) { - return !compare_ether_addr(addr1, addr2); -} +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) + u32 fold = ((*(const u32 *)addr1) ^ (*(const u32 *)addr2)) | + ((*(const u16 *)(addr1 + 4)) ^ (*(const u16 *)(addr2 + 4))); -static inline unsigned long zap_last_2bytes(unsigned long value) -{ -#ifdef __BIG_ENDIAN - return value >> 16; + return fold == 0; #else - return value << 16; + const u16 *a = (const u16 *)addr1; + const u16 *b = (const u16 *)addr2; + + return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | (a[2] ^ b[2])) == 0; #endif } @@ -265,16 +252,14 @@ static inline unsigned long zap_last_2bytes(unsigned long value) static inline bool ether_addr_equal_64bits(const u8 addr1[6+2], const u8 addr2[6+2]) { -#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS - unsigned long fold = ((*(unsigned long *)addr1) ^ - (*(unsigned long *)addr2)); - - if (sizeof(fold) == 8) - return zap_last_2bytes(fold) == 0; +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 + u64 fold = (*(const u64 *)addr1) ^ (*(const u64 *)addr2); - fold |= zap_last_2bytes((*(unsigned long *)(addr1 + 4)) ^ - (*(unsigned long *)(addr2 + 4))); - return fold == 0; +#ifdef __BIG_ENDIAN + return (fold >> 16) == 0; +#else + return (fold << 16) == 0; +#endif #else return ether_addr_equal(addr1, addr2); #endif -- cgit v1.3-14-g43fede From 0f978bfaf2600040f9826f394eb12e023bef3068 Mon Sep 17 00:00:00 2001 From: Sujith Manoharan Date: Fri, 6 Dec 2013 16:28:45 +0530 Subject: ath9k: Use a separate TX gain table for WZR-HP-G450H The Buffalo device WZR-HP-G450H uses the index 3 for TX gain, which is set to the high_power table currently. Later variants of the router use the same index, but instead refer to the low_ob_db gain table. This is not handled in the driver since there is no way to distinguish board revisions and the high_power table is used (incorrectly) for the newer variants. By default, devices based on AR9300 using the TX gain index 3 have to use the high_power table. To make sure that WZR-HP-G450H is not broken when the high_power table is updated, use a separate array based on information obtained from the platform data. The current situation where only the original variant of WZR-HP-G450H works properly stays unchanged. Signed-off-by: Sujith Manoharan Signed-off-by: John W. Linville --- .../wireless/ath/ath9k/ar9003_buffalo_initvals.h | 126 +++++++++++++++++++++ drivers/net/wireless/ath/ath9k/ar9003_hw.c | 12 +- drivers/net/wireless/ath/ath9k/hw.h | 1 + drivers/net/wireless/ath/ath9k/init.c | 36 ++++-- include/linux/ath9k_platform.h | 2 + 5 files changed, 165 insertions(+), 12 deletions(-) create mode 100644 drivers/net/wireless/ath/ath9k/ar9003_buffalo_initvals.h (limited to 'include/linux') diff --git a/drivers/net/wireless/ath/ath9k/ar9003_buffalo_initvals.h b/drivers/net/wireless/ath/ath9k/ar9003_buffalo_initvals.h new file mode 100644 index 000000000000..59cf738f70df --- /dev/null +++ b/drivers/net/wireless/ath/ath9k/ar9003_buffalo_initvals.h @@ -0,0 +1,126 @@ +/* + * Copyright (c) 2013 Qualcomm Atheros Inc. + * + * Permission to use, copy, modify, and/or distribute this software for any + * purpose with or without fee is hereby granted, provided that the above + * copyright notice and this permission notice appear in all copies. + * + * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES + * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR + * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES + * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN + * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF + * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + */ + +#ifndef INITVALS_9003_BUFFALO_H +#define INITVALS_9003_BUFFALO_H + +static const u32 ar9300Modes_high_power_tx_gain_table_buffalo[][5] = { + /* Addr 5G_HT20 5G_HT40 2G_HT40 2G_HT20 */ + {0x0000a2dc, 0x0380c7fc, 0x0380c7fc, 0x03aaa352, 0x03aaa352}, + {0x0000a2e0, 0x0000f800, 0x0000f800, 0x03ccc584, 0x03ccc584}, + {0x0000a2e4, 0x03ff0000, 0x03ff0000, 0x03f0f800, 0x03f0f800}, + {0x0000a2e8, 0x00000000, 0x00000000, 0x03ff0000, 0x03ff0000}, + {0x0000a410, 0x000050d8, 0x000050d8, 0x000050d9, 0x000050d9}, + {0x0000a500, 0x00002220, 0x00002220, 0x00000000, 0x00000000}, + {0x0000a504, 0x04002222, 0x04002222, 0x04000002, 0x04000002}, + {0x0000a508, 0x09002421, 0x09002421, 0x08000004, 0x08000004}, + {0x0000a50c, 0x0d002621, 0x0d002621, 0x0b000200, 0x0b000200}, + {0x0000a510, 0x13004620, 0x13004620, 0x0f000202, 0x0f000202}, + {0x0000a514, 0x19004a20, 0x19004a20, 0x11000400, 0x11000400}, + {0x0000a518, 0x1d004e20, 0x1d004e20, 0x15000402, 0x15000402}, + {0x0000a51c, 0x21005420, 0x21005420, 0x19000404, 0x19000404}, + {0x0000a520, 0x26005e20, 0x26005e20, 0x1b000603, 0x1b000603}, + {0x0000a524, 0x2b005e40, 0x2b005e40, 0x1f000a02, 0x1f000a02}, + {0x0000a528, 0x2f005e42, 0x2f005e42, 0x23000a04, 0x23000a04}, + {0x0000a52c, 0x33005e44, 0x33005e44, 0x26000a20, 0x26000a20}, + {0x0000a530, 0x38005e65, 0x38005e65, 0x2a000e20, 0x2a000e20}, + {0x0000a534, 0x3c005e69, 0x3c005e69, 0x2e000e22, 0x2e000e22}, + {0x0000a538, 0x40005e6b, 0x40005e6b, 0x31000e24, 0x31000e24}, + {0x0000a53c, 0x44005e6d, 0x44005e6d, 0x34001640, 0x34001640}, + {0x0000a540, 0x49005e72, 0x49005e72, 0x38001660, 0x38001660}, + {0x0000a544, 0x4e005eb2, 0x4e005eb2, 0x3b001861, 0x3b001861}, + {0x0000a548, 0x53005f12, 0x53005f12, 0x3e001a81, 0x3e001a81}, + {0x0000a54c, 0x59025eb2, 0x59025eb2, 0x42001a83, 0x42001a83}, + {0x0000a550, 0x5e025f12, 0x5e025f12, 0x44001c84, 0x44001c84}, + {0x0000a554, 0x61027f12, 0x61027f12, 0x48001ce3, 0x48001ce3}, + {0x0000a558, 0x6702bf12, 0x6702bf12, 0x4c001ce5, 0x4c001ce5}, + {0x0000a55c, 0x6b02bf14, 0x6b02bf14, 0x50001ce9, 0x50001ce9}, + {0x0000a560, 0x6f02bf16, 0x6f02bf16, 0x54001ceb, 0x54001ceb}, + {0x0000a564, 0x6f02bf16, 0x6f02bf16, 0x56001eec, 0x56001eec}, + {0x0000a568, 0x6f02bf16, 0x6f02bf16, 0x56001eec, 0x56001eec}, + {0x0000a56c, 0x6f02bf16, 0x6f02bf16, 0x56001eec, 0x56001eec}, + {0x0000a570, 0x6f02bf16, 0x6f02bf16, 0x56001eec, 0x56001eec}, + {0x0000a574, 0x6f02bf16, 0x6f02bf16, 0x56001eec, 0x56001eec}, + {0x0000a578, 0x6f02bf16, 0x6f02bf16, 0x56001eec, 0x56001eec}, + {0x0000a57c, 0x6f02bf16, 0x6f02bf16, 0x56001eec, 0x56001eec}, + {0x0000a580, 0x00802220, 0x00802220, 0x00800000, 0x00800000}, + {0x0000a584, 0x04802222, 0x04802222, 0x04800002, 0x04800002}, + {0x0000a588, 0x09802421, 0x09802421, 0x08800004, 0x08800004}, + {0x0000a58c, 0x0d802621, 0x0d802621, 0x0b800200, 0x0b800200}, + {0x0000a590, 0x13804620, 0x13804620, 0x0f800202, 0x0f800202}, + {0x0000a594, 0x19804a20, 0x19804a20, 0x11800400, 0x11800400}, + {0x0000a598, 0x1d804e20, 0x1d804e20, 0x15800402, 0x15800402}, + {0x0000a59c, 0x21805420, 0x21805420, 0x19800404, 0x19800404}, + {0x0000a5a0, 0x26805e20, 0x26805e20, 0x1b800603, 0x1b800603}, + {0x0000a5a4, 0x2b805e40, 0x2b805e40, 0x1f800a02, 0x1f800a02}, + {0x0000a5a8, 0x2f805e42, 0x2f805e42, 0x23800a04, 0x23800a04}, + {0x0000a5ac, 0x33805e44, 0x33805e44, 0x26800a20, 0x26800a20}, + {0x0000a5b0, 0x38805e65, 0x38805e65, 0x2a800e20, 0x2a800e20}, + {0x0000a5b4, 0x3c805e69, 0x3c805e69, 0x2e800e22, 0x2e800e22}, + {0x0000a5b8, 0x40805e6b, 0x40805e6b, 0x31800e24, 0x31800e24}, + {0x0000a5bc, 0x44805e6d, 0x44805e6d, 0x34801640, 0x34801640}, + {0x0000a5c0, 0x49805e72, 0x49805e72, 0x38801660, 0x38801660}, + {0x0000a5c4, 0x4e805eb2, 0x4e805eb2, 0x3b801861, 0x3b801861}, + {0x0000a5c8, 0x53805f12, 0x53805f12, 0x3e801a81, 0x3e801a81}, + {0x0000a5cc, 0x59825eb2, 0x59825eb2, 0x42801a83, 0x42801a83}, + {0x0000a5d0, 0x5e825f12, 0x5e825f12, 0x44801c84, 0x44801c84}, + {0x0000a5d4, 0x61827f12, 0x61827f12, 0x48801ce3, 0x48801ce3}, + {0x0000a5d8, 0x6782bf12, 0x6782bf12, 0x4c801ce5, 0x4c801ce5}, + {0x0000a5dc, 0x6b82bf14, 0x6b82bf14, 0x50801ce9, 0x50801ce9}, + {0x0000a5e0, 0x6f82bf16, 0x6f82bf16, 0x54801ceb, 0x54801ceb}, + {0x0000a5e4, 0x6f82bf16, 0x6f82bf16, 0x56801eec, 0x56801eec}, + {0x0000a5e8, 0x6f82bf16, 0x6f82bf16, 0x56801eec, 0x56801eec}, + {0x0000a5ec, 0x6f82bf16, 0x6f82bf16, 0x56801eec, 0x56801eec}, + {0x0000a5f0, 0x6f82bf16, 0x6f82bf16, 0x56801eec, 0x56801eec}, + {0x0000a5f4, 0x6f82bf16, 0x6f82bf16, 0x56801eec, 0x56801eec}, + {0x0000a5f8, 0x6f82bf16, 0x6f82bf16, 0x56801eec, 0x56801eec}, + {0x0000a5fc, 0x6f82bf16, 0x6f82bf16, 0x56801eec, 0x56801eec}, + {0x0000a600, 0x00000000, 0x00000000, 0x00000000, 0x00000000}, + {0x0000a604, 0x00000000, 0x00000000, 0x00000000, 0x00000000}, + {0x0000a608, 0x00000000, 0x00000000, 0x00000000, 0x00000000}, + {0x0000a60c, 0x00000000, 0x00000000, 0x00000000, 0x00000000}, + {0x0000a610, 0x00804000, 0x00804000, 0x00000000, 0x00000000}, + {0x0000a614, 0x00804201, 0x00804201, 0x01404000, 0x01404000}, + {0x0000a618, 0x0280c802, 0x0280c802, 0x01404501, 0x01404501}, + {0x0000a61c, 0x0280ca03, 0x0280ca03, 0x02008501, 0x02008501}, + {0x0000a620, 0x04c15104, 0x04c15104, 0x0280ca03, 0x0280ca03}, + {0x0000a624, 0x04c15305, 0x04c15305, 0x03010c04, 0x03010c04}, + {0x0000a628, 0x04c15305, 0x04c15305, 0x04014c04, 0x04014c04}, + {0x0000a62c, 0x04c15305, 0x04c15305, 0x04015005, 0x04015005}, + {0x0000a630, 0x04c15305, 0x04c15305, 0x04015005, 0x04015005}, + {0x0000a634, 0x04c15305, 0x04c15305, 0x04015005, 0x04015005}, + {0x0000a638, 0x04c15305, 0x04c15305, 0x04015005, 0x04015005}, + {0x0000a63c, 0x04c15305, 0x04c15305, 0x04015005, 0x04015005}, + {0x0000b2dc, 0x0380c7fc, 0x0380c7fc, 0x03aaa352, 0x03aaa352}, + {0x0000b2e0, 0x0000f800, 0x0000f800, 0x03ccc584, 0x03ccc584}, + {0x0000b2e4, 0x03ff0000, 0x03ff0000, 0x03f0f800, 0x03f0f800}, + {0x0000b2e8, 0x00000000, 0x00000000, 0x03ff0000, 0x03ff0000}, + {0x0000c2dc, 0x0380c7fc, 0x0380c7fc, 0x03aaa352, 0x03aaa352}, + {0x0000c2e0, 0x0000f800, 0x0000f800, 0x03ccc584, 0x03ccc584}, + {0x0000c2e4, 0x03ff0000, 0x03ff0000, 0x03f0f800, 0x03f0f800}, + {0x0000c2e8, 0x00000000, 0x00000000, 0x03ff0000, 0x03ff0000}, + {0x00016044, 0x012492d4, 0x012492d4, 0x012492d4, 0x012492d4}, + {0x00016048, 0x66480001, 0x66480001, 0x66480001, 0x66480001}, + {0x00016068, 0x6db6db6c, 0x6db6db6c, 0x6db6db6c, 0x6db6db6c}, + {0x00016444, 0x012492d4, 0x012492d4, 0x012492d4, 0x012492d4}, + {0x00016448, 0x66480001, 0x66480001, 0x66480001, 0x66480001}, + {0x00016468, 0x6db6db6c, 0x6db6db6c, 0x6db6db6c, 0x6db6db6c}, + {0x00016844, 0x012492d4, 0x012492d4, 0x012492d4, 0x012492d4}, + {0x00016848, 0x66480001, 0x66480001, 0x66480001, 0x66480001}, + {0x00016868, 0x6db6db6c, 0x6db6db6c, 0x6db6db6c, 0x6db6db6c}, +}; + +#endif /* INITVALS_9003_BUFFALO_H */ diff --git a/drivers/net/wireless/ath/ath9k/ar9003_hw.c b/drivers/net/wireless/ath/ath9k/ar9003_hw.c index 4e8ae4a79dc0..29613ebbc5d7 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_hw.c +++ b/drivers/net/wireless/ath/ath9k/ar9003_hw.c @@ -17,6 +17,7 @@ #include "hw.h" #include "ar9003_mac.h" #include "ar9003_2p2_initvals.h" +#include "ar9003_buffalo_initvals.h" #include "ar9485_initvals.h" #include "ar9340_initvals.h" #include "ar9330_1p1_initvals.h" @@ -592,9 +593,14 @@ static void ar9003_tx_gain_table_mode3(struct ath_hw *ah) else if (AR_SREV_9565(ah)) INIT_INI_ARRAY(&ah->iniModesTxGain, ar9565_1p0_modes_high_power_tx_gain_table); - else - INIT_INI_ARRAY(&ah->iniModesTxGain, - ar9300Modes_high_power_tx_gain_table_2p2); + else { + if (ah->config.tx_gain_buffalo) + INIT_INI_ARRAY(&ah->iniModesTxGain, + ar9300Modes_high_power_tx_gain_table_buffalo); + else + INIT_INI_ARRAY(&ah->iniModesTxGain, + ar9300Modes_high_power_tx_gain_table_2p2); + } } static void ar9003_tx_gain_table_mode4(struct ath_hw *ah) diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h index 7490047acd11..b1ff54631dca 100644 --- a/drivers/net/wireless/ath/ath9k/hw.h +++ b/drivers/net/wireless/ath/ath9k/hw.h @@ -316,6 +316,7 @@ struct ath9k_ops_config { bool xatten_margin_cfg; bool alt_mingainidx; bool no_pll_pwrsave; + bool tx_gain_buffalo; }; enum ath9k_int { diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c index 5a0b7e82c85f..609b7e13f3f0 100644 --- a/drivers/net/wireless/ath/ath9k/init.c +++ b/drivers/net/wireless/ath/ath9k/init.c @@ -554,7 +554,7 @@ static void ath9k_init_misc(struct ath_softc *sc) sc->spec_config.fft_period = 0xF; } -static void ath9k_init_platform(struct ath_softc *sc) +static void ath9k_init_pcoem_platform(struct ath_softc *sc) { struct ath_hw *ah = sc->sc_ah; struct ath9k_hw_capabilities *pCap = &ah->caps; @@ -664,6 +664,27 @@ static void ath9k_eeprom_release(struct ath_softc *sc) release_firmware(sc->sc_ah->eeprom_blob); } +static int ath9k_init_soc_platform(struct ath_softc *sc) +{ + struct ath9k_platform_data *pdata = sc->dev->platform_data; + struct ath_hw *ah = sc->sc_ah; + int ret = 0; + + if (!pdata) + return 0; + + if (pdata->eeprom_name) { + ret = ath9k_eeprom_request(sc, pdata->eeprom_name); + if (ret) + return ret; + } + + if (pdata->tx_gain_buffalo) + ah->config.tx_gain_buffalo = true; + + return ret; +} + static int ath9k_init_softc(u16 devid, struct ath_softc *sc, const struct ath_bus_ops *bus_ops) { @@ -717,7 +738,11 @@ static int ath9k_init_softc(u16 devid, struct ath_softc *sc, /* * Platform quirks. */ - ath9k_init_platform(sc); + ath9k_init_pcoem_platform(sc); + + ret = ath9k_init_soc_platform(sc); + if (ret) + return ret; /* * Enable WLAN/BT RX Antenna diversity only when: @@ -731,7 +756,6 @@ static int ath9k_init_softc(u16 devid, struct ath_softc *sc, common->bt_ant_diversity = 1; spin_lock_init(&common->cc_lock); - spin_lock_init(&sc->sc_serial_rw); spin_lock_init(&sc->sc_pm_lock); mutex_init(&sc->mutex); @@ -753,12 +777,6 @@ static int ath9k_init_softc(u16 devid, struct ath_softc *sc, ath_read_cachesize(common, &csz); common->cachelsz = csz << 2; /* convert to bytes */ - if (pdata && pdata->eeprom_name) { - ret = ath9k_eeprom_request(sc, pdata->eeprom_name); - if (ret) - return ret; - } - /* Initializes the hardware for all supported chipsets */ ret = ath9k_hw_init(ah); if (ret) diff --git a/include/linux/ath9k_platform.h b/include/linux/ath9k_platform.h index fcdd81bd5314..8598f8eacb20 100644 --- a/include/linux/ath9k_platform.h +++ b/include/linux/ath9k_platform.h @@ -32,6 +32,8 @@ struct ath9k_platform_data { u32 gpio_val; bool is_clk_25mhz; + bool tx_gain_buffalo; + int (*get_mac_revision)(void); int (*external_reset)(void); }; -- cgit v1.3-14-g43fede From 4262e5ccbbb5171abd2921eed16ed339633d6478 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 6 Dec 2013 11:36:16 +0100 Subject: net: dev: move inline skb_needs_linearize helper to header As we need it elsewhere, move the inline helper function of skb_needs_linearize() over to skbuff.h include file. While at it, also convert the return to 'bool' instead of 'int' and add a proper kernel doc. Signed-off-by: Daniel Borkmann Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/linux/skbuff.h | 18 ++++++++++++++++++ net/core/dev.c | 15 --------------- 2 files changed, 18 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 215b5ea1cb30..77c7aae1c6b2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2392,6 +2392,24 @@ static inline void *skb_header_pointer(const struct sk_buff *skb, int offset, return buffer; } +/** + * skb_needs_linearize - check if we need to linearize a given skb + * depending on the given device features. + * @skb: socket buffer to check + * @features: net device features + * + * Returns true if either: + * 1. skb has frag_list and the device doesn't support FRAGLIST, or + * 2. skb is fragmented and the device does not support SG. + */ +static inline bool skb_needs_linearize(struct sk_buff *skb, + netdev_features_t features) +{ + return skb_is_nonlinear(skb) && + ((skb_has_frag_list(skb) && !(features & NETIF_F_FRAGLIST)) || + (skb_shinfo(skb)->nr_frags && !(features & NETIF_F_SG))); +} + static inline void skb_copy_from_linear_data(const struct sk_buff *skb, void *to, const unsigned int len) diff --git a/net/core/dev.c b/net/core/dev.c index 6cc98dd49c7a..355df36360b4 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2535,21 +2535,6 @@ netdev_features_t netif_skb_features(struct sk_buff *skb) } EXPORT_SYMBOL(netif_skb_features); -/* - * Returns true if either: - * 1. skb has frag_list and the device doesn't support FRAGLIST, or - * 2. skb is fragmented and the device does not support SG. - */ -static inline int skb_needs_linearize(struct sk_buff *skb, - netdev_features_t features) -{ - return skb_is_nonlinear(skb) && - ((skb_has_frag_list(skb) && - !(features & NETIF_F_FRAGLIST)) || - (skb_shinfo(skb)->nr_frags && - !(features & NETIF_F_SG))); -} - int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, void *accel_priv) { -- cgit v1.3-14-g43fede From 114002bc1af6c63de4c003f8c5d3ca0bb430d987 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 6 Dec 2013 13:01:30 -0800 Subject: net: phy: report link partner features through ethtool The PHY library already reads the MII_STAT1000 and MII_LPA registers in genphy_read_status(), so extend it to also populate the PHY device link partner advertised features such that we can feed this back into ethtool when asked for it in phy_ethtool_gset(). Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/phy.c | 1 + drivers/net/phy/phy_device.c | 6 ++++++ include/linux/phy.h | 5 +++-- 3 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 36c6994436b7..05cb8fe742f9 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -289,6 +289,7 @@ int phy_ethtool_gset(struct phy_device *phydev, struct ethtool_cmd *cmd) cmd->supported = phydev->supported; cmd->advertising = phydev->advertising; + cmd->lp_advertising = phydev->lp_advertising; ethtool_cmd_speed_set(cmd, phydev->speed); cmd->duplex = phydev->duplex; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index d6447b3f7409..6db36595eac9 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -839,6 +839,8 @@ int genphy_read_status(struct phy_device *phydev) if (err) return err; + phydev->lp_advertising = 0; + if (AUTONEG_ENABLE == phydev->autoneg) { if (phydev->supported & (SUPPORTED_1000baseT_Half | SUPPORTED_1000baseT_Full)) { @@ -852,6 +854,8 @@ int genphy_read_status(struct phy_device *phydev) if (adv < 0) return adv; + phydev->lp_advertising = + mii_stat1000_to_ethtool_lpa_t(lpagb); lpagb &= adv << 2; } @@ -860,6 +864,8 @@ int genphy_read_status(struct phy_device *phydev) if (lpa < 0) return lpa; + phydev->lp_advertising |= mii_lpa_to_ethtool_lpa_t(lpa); + adv = phy_read(phydev, MII_ADVERTISE); if (adv < 0) diff --git a/include/linux/phy.h b/include/linux/phy.h index 7ff751ae6f0a..90a666e0884b 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -287,8 +287,8 @@ struct phy_c45_device_ids { * adjust_state: Callback for the enet driver to respond to * changes in the state machine. * - * speed, duplex, pause, supported, advertising, and - * autoneg are used like in mii_if_info + * speed, duplex, pause, supported, advertising, lp_advertising, + * and autoneg are used like in mii_if_info * * interrupts currently only supports enabled or disabled, * but could be changed in the future to support enabling @@ -340,6 +340,7 @@ struct phy_device { /* See mii.h for more info */ u32 supported; u32 advertising; + u32 lp_advertising; int autoneg; -- cgit v1.3-14-g43fede From 1d4c8c29841b9991cdf3c7cc4ba7f96a94f104ca Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Sat, 7 Dec 2013 19:26:56 +0100 Subject: neigh: restore old behaviour of default parms values Previously inet devices were only constructed when addresses are added. Therefore the default neigh parms values they get are the ones at the time of these operations. Now that we're creating inet devices earlier, this changes the behaviour of default neigh parms values in an incompatible way (see bug #8519). This patch creates a compromise by setting the default values at the same point as before but only for those that have not been explicitly set by the user since the inet device's creation. Introduced by: commit 8030f54499925d073a88c09f30d5d844fb1b3190 Author: Herbert Xu Date: Thu Feb 22 01:53:47 2007 +0900 [IPV4] devinet: Register inetdev earlier. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 7 +++++ include/net/neighbour.h | 13 ++++++++ net/core/neighbour.c | 74 ++++++++++++++++++++++++++++++++++++++++++---- net/ipv4/devinet.c | 2 ++ net/ipv4/ipmr.c | 2 ++ 5 files changed, 92 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 0d678aefe69d..ae174ca565c9 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -220,6 +220,13 @@ static inline struct in_device *__in_dev_get_rtnl(const struct net_device *dev) return rtnl_dereference(dev->ip_ptr); } +static inline struct neigh_parms *__in_dev_arp_parms_get_rcu(const struct net_device *dev) +{ + struct in_device *in_dev = __in_dev_get_rcu(dev); + + return in_dev ? in_dev->arp_parms : NULL; +} + void in_dev_finish_destroy(struct in_device *idev); static inline void in_dev_put(struct in_device *idev) diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 95615c9ad13a..41b1ce6c96a8 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -21,6 +21,7 @@ #include #include #include +#include #include #include @@ -81,16 +82,28 @@ struct neigh_parms { int reachable_time; int data[NEIGH_VAR_DATA_MAX]; + DECLARE_BITMAP(data_state, NEIGH_VAR_DATA_MAX); }; static inline void neigh_var_set(struct neigh_parms *p, int index, int val) { + set_bit(index, p->data_state); p->data[index] = val; } #define NEIGH_VAR(p, attr) ((p)->data[NEIGH_VAR_ ## attr]) #define NEIGH_VAR_SET(p, attr, val) neigh_var_set(p, NEIGH_VAR_ ## attr, val) +static inline void neigh_parms_data_state_setall(struct neigh_parms *p) +{ + bitmap_fill(p->data_state, NEIGH_VAR_DATA_MAX); +} + +static inline void neigh_parms_data_state_cleanall(struct neigh_parms *p) +{ + bitmap_zero(p->data_state, NEIGH_VAR_DATA_MAX); +} + struct neigh_statistics { unsigned long allocs; /* number of allocated neighs */ unsigned long destroys; /* number of destroyed neighs */ diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 65ead080167b..c4a7879bfb15 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -38,6 +38,7 @@ #include #include #include +#include #define DEBUG #define NEIGH_DEBUG 1 @@ -1464,6 +1465,8 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, p->next = tbl->parms.next; tbl->parms.next = p; write_unlock_bh(&tbl->lock); + + neigh_parms_data_state_cleanall(p); } return p; } @@ -2813,22 +2816,68 @@ static int proc_unres_qlen(struct ctl_table *ctl, int write, return ret; } +static struct neigh_parms *neigh_get_dev_parms_rcu(struct net_device *dev, + int family) +{ + if (family == AF_INET) + return __in_dev_arp_parms_get_rcu(dev); + return NULL; +} + +static void neigh_copy_dflt_parms(struct net *net, struct neigh_parms *p, + int index) +{ + struct net_device *dev; + int family = neigh_parms_family(p); + + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { + struct neigh_parms *dst_p = + neigh_get_dev_parms_rcu(dev, family); + + if (dst_p && !test_bit(index, dst_p->data_state)) + dst_p->data[index] = p->data[index]; + } + rcu_read_unlock(); +} + +static void neigh_proc_update(struct ctl_table *ctl, int write) +{ + struct net_device *dev = ctl->extra1; + struct neigh_parms *p = ctl->extra2; + struct net *net = p->net; + int index = (int *) ctl->data - p->data; + + if (!write) + return; + + set_bit(index, p->data_state); + if (!dev) /* NULL dev means this is default value */ + neigh_copy_dflt_parms(net, p, index); +} + static int neigh_proc_dointvec_zero_intmax(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table tmp = *ctl; + int ret; tmp.extra1 = &zero; tmp.extra2 = &int_max; - return proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + neigh_proc_update(ctl, write); + return ret; } int neigh_proc_dointvec(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - return proc_dointvec(ctl, write, buffer, lenp, ppos); + int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; } EXPORT_SYMBOL(neigh_proc_dointvec); @@ -2836,7 +2885,10 @@ int neigh_proc_dointvec_jiffies(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - return proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos); + int ret = proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; } EXPORT_SYMBOL(neigh_proc_dointvec_jiffies); @@ -2844,14 +2896,20 @@ static int neigh_proc_dointvec_userhz_jiffies(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - return proc_dointvec_userhz_jiffies(ctl, write, buffer, lenp, ppos); + int ret = proc_dointvec_userhz_jiffies(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; } int neigh_proc_dointvec_ms_jiffies(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - return proc_dointvec_ms_jiffies(ctl, write, buffer, lenp, ppos); + int ret = proc_dointvec_ms_jiffies(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; } EXPORT_SYMBOL(neigh_proc_dointvec_ms_jiffies); @@ -2859,7 +2917,10 @@ static int neigh_proc_dointvec_unres_qlen(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - return proc_unres_qlen(ctl, write, buffer, lenp, ppos); + int ret = proc_unres_qlen(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; } #define NEIGH_PARMS_DATA_OFFSET(index) \ @@ -2962,6 +3023,7 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, for (i = 0; i < ARRAY_SIZE(t->neigh_vars); i++) { t->neigh_vars[i].data += (long) p; t->neigh_vars[i].extra1 = dev; + t->neigh_vars[i].extra2 = p; } if (dev) { diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index e1c19535fe38..43065be36301 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -500,6 +500,7 @@ static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa) return -ENOBUFS; } ipv4_devconf_setall(in_dev); + neigh_parms_data_state_setall(in_dev->arp_parms); if (ifa->ifa_dev != in_dev) { WARN_ON(ifa->ifa_dev); in_dev_hold(in_dev); @@ -747,6 +748,7 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, goto errout; ipv4_devconf_setall(in_dev); + neigh_parms_data_state_setall(in_dev->arp_parms); in_dev_hold(in_dev); if (tb[IFA_ADDRESS] == NULL) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 62212c772a4b..421a24934ffd 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -425,6 +425,7 @@ struct net_device *ipmr_new_tunnel(struct net *net, struct vifctl *v) goto failure; ipv4_devconf_setall(in_dev); + neigh_parms_data_state_setall(in_dev->arp_parms); IPV4_DEVCONF(in_dev->cnf, RP_FILTER) = 0; if (dev_open(dev)) @@ -517,6 +518,7 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) } ipv4_devconf_setall(in_dev); + neigh_parms_data_state_setall(in_dev->arp_parms); IPV4_DEVCONF(in_dev->cnf, RP_FILTER) = 0; rcu_read_unlock(); -- cgit v1.3-14-g43fede From 73eaef87e98a96fe8b8a586f916b2721bf512efa Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Fri, 6 Dec 2013 14:21:01 -0800 Subject: etherdevice: Add ether_addr_equal_unaligned Add a generic routine to test if possibly unaligned to u16 Ethernet addresses are equal. If CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS is set, this uses the slightly faster generic routine ether_addr_equal, otherwise this uses memcmp. Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 3526e819d7ae..2f0e3d0818bc 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -265,6 +265,24 @@ static inline bool ether_addr_equal_64bits(const u8 addr1[6+2], #endif } +/** + * ether_addr_equal_unaligned - Compare two not u16 aligned Ethernet addresses + * @addr1: Pointer to a six-byte array containing the Ethernet address + * @addr2: Pointer other six-byte array containing the Ethernet address + * + * Compare two Ethernet addresses, returns true if equal + * + * Please note: Use only when any Ethernet address may not be u16 aligned. + */ +static inline bool ether_addr_equal_unaligned(const u8 *addr1, const u8 *addr2) +{ +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) + return ether_addr_equal(addr1, addr2); +#else + return memcmp(addr1, addr2, ETH_ALEN) == 0; +#endif +} + /** * is_etherdev_addr - Tell if given Ethernet address belongs to the device. * @dev: Pointer to a device structure -- cgit v1.3-14-g43fede From 2c722fe1c821a100ca87fcc36e90a9bceb497c7c Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Fri, 6 Dec 2013 15:44:21 -0800 Subject: etherdevice: Optimize a few is__ether_addr functions If CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS is set, several is__ether_addr functions can be slightly improved by using u32 dereferences. I believe all current uses of is_zero_ether_addr and is_broadcast_ether_addr are u16 aligned, so always use u16 references to improve those functions performance. Document the u16 alignment requirements. Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 2f0e3d0818bc..f344ac04f858 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -61,6 +61,8 @@ static const u8 eth_reserved_addr_base[ETH_ALEN] __aligned(2) = * * Return true if address is link local reserved addr (01:80:c2:00:00:0X) per * IEEE 802.1Q 8.6.3 Frame filtering. + * + * Please note: addr must be aligned to u16. */ static inline bool is_link_local_ether_addr(const u8 *addr) { @@ -68,7 +70,12 @@ static inline bool is_link_local_ether_addr(const u8 *addr) static const __be16 *b = (const __be16 *)eth_reserved_addr_base; static const __be16 m = cpu_to_be16(0xfff0); +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) + return (((*(const u32 *)addr) ^ (*(const u32 *)b)) | + ((a[2] ^ b[2]) & m)) == 0; +#else return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | ((a[2] ^ b[2]) & m)) == 0; +#endif } /** @@ -76,10 +83,18 @@ static inline bool is_link_local_ether_addr(const u8 *addr) * @addr: Pointer to a six-byte array containing the Ethernet address * * Return true if the address is all zeroes. + * + * Please note: addr must be aligned to u16. */ static inline bool is_zero_ether_addr(const u8 *addr) { - return !(addr[0] | addr[1] | addr[2] | addr[3] | addr[4] | addr[5]); +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) + return ((*(const u32 *)addr) | (*(const u16 *)(addr + 4))) == 0; +#else + return (*(const u16 *)(addr + 0) | + *(const u16 *)(addr + 2) | + *(const u16 *)(addr + 4)) == 0; +#endif } /** @@ -110,10 +125,14 @@ static inline bool is_local_ether_addr(const u8 *addr) * @addr: Pointer to a six-byte array containing the Ethernet address * * Return true if the address is the broadcast address. + * + * Please note: addr must be aligned to u16. */ static inline bool is_broadcast_ether_addr(const u8 *addr) { - return (addr[0] & addr[1] & addr[2] & addr[3] & addr[4] & addr[5]) == 0xff; + return (*(const u16 *)(addr + 0) & + *(const u16 *)(addr + 2) & + *(const u16 *)(addr + 4)) == 0xffff; } /** @@ -135,6 +154,8 @@ static inline bool is_unicast_ether_addr(const u8 *addr) * a multicast address, and is not FF:FF:FF:FF:FF:FF. * * Return true if the address is valid. + * + * Please note: addr must be aligned to u16. */ static inline bool is_valid_ether_addr(const u8 *addr) { -- cgit v1.3-14-g43fede From 1397ed35f22d7c30d0b89ba74b6b7829220dfcfd Mon Sep 17 00:00:00 2001 From: Florent Fourcot Date: Sun, 8 Dec 2013 15:46:57 +0100 Subject: ipv6: add flowinfo for tcp6 pkt_options for all cases The current implementation of IPV6_FLOWINFO only gives a result if pktoptions is available (thanks to the ip6_datagram_recv_ctl function). It gives inconsistent results to user space, sometimes there is a result for getsockopt(IPV6_FLOWINFO), sometimes not. This patch add rcv_flowinfo to store it, and return it to the userspace in the same way than other pkt_options. Signed-off-by: Florent Fourcot Reviewed-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + net/ipv6/ipv6_sockglue.c | 4 ++++ net/ipv6/tcp_ipv6.c | 4 ++++ 3 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index c56c350324e4..0b2ebfbbe0f4 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -201,6 +201,7 @@ struct ipv6_pinfo { __u8 min_hopcount; __u8 tclass; __u8 rcv_tclass; + __be32 rcv_flowinfo; __u32 dst_cookie; __u32 rx_dst_cookie; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 1c6ce3119ff8..c2db1df46385 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -1034,6 +1034,10 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, int hlim = np->mcast_hops; put_cmsg(&msg, SOL_IPV6, IPV6_2292HOPLIMIT, sizeof(hlim), &hlim); } + if (np->rxopt.bits.rxflow) { + int flowinfo = np->rcv_flowinfo; + put_cmsg(&msg, SOL_IPV6, IPV6_FLOWINFO, sizeof(flowinfo), &flowinfo); + } } len -= msg.msg_controllen; return put_user(len, optlen); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 0740f93a114a..79a196369558 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1136,6 +1136,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newnp->mcast_oif = inet6_iif(skb); newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; newnp->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(skb)); + newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb)); /* * No need to charge this sock to the relevant IPv6 refcnt debug socks count @@ -1216,6 +1217,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newnp->mcast_oif = inet6_iif(skb); newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; newnp->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(skb)); + newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb)); /* Clone native IPv6 options from listening socket (if any) @@ -1427,6 +1429,8 @@ ipv6_pktoptions: np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit; if (np->rxopt.bits.rxtclass) np->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(opt_skb)); + if (np->rxopt.bits.rxflow) + np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb)); if (ipv6_opt_accepted(sk, opt_skb)) { skb_set_owner_r(opt_skb, sk); opt_skb = xchg(&np->pktoptions, opt_skb); -- cgit v1.3-14-g43fede From 82e9f105a28006e7ff864220a28cf62ea6d1e280 Mon Sep 17 00:00:00 2001 From: Florent Fourcot Date: Sun, 8 Dec 2013 15:46:59 +0100 Subject: ipv6: remove rcv_tclass of ipv6_pinfo tclass information in now already stored in rcv_flowinfo We do not need to store the same information twice. Signed-off-by: Florent Fourcot Reviewed-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 - net/ipv6/ipv6_sockglue.c | 2 +- net/ipv6/tcp_ipv6.c | 6 +----- 3 files changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 0b2ebfbbe0f4..3fde06645553 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -200,7 +200,6 @@ struct ipv6_pinfo { dontfrag:1; __u8 min_hopcount; __u8 tclass; - __u8 rcv_tclass; __be32 rcv_flowinfo; __u32 dst_cookie; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index c2db1df46385..7d9391506856 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -1019,7 +1019,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, put_cmsg(&msg, SOL_IPV6, IPV6_HOPLIMIT, sizeof(hlim), &hlim); } if (np->rxopt.bits.rxtclass) { - int tclass = np->rcv_tclass; + int tclass = ntohl(np->rcv_flowinfo & IPV6_TCLASS_MASK) >> 20; put_cmsg(&msg, SOL_IPV6, IPV6_TCLASS, sizeof(tclass), &tclass); } if (np->rxopt.bits.rxoinfo) { diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 79a196369558..bd91e7ff482b 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1135,7 +1135,6 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newnp->opt = NULL; newnp->mcast_oif = inet6_iif(skb); newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; - newnp->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(skb)); newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb)); /* @@ -1216,7 +1215,6 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newnp->opt = NULL; newnp->mcast_oif = inet6_iif(skb); newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; - newnp->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(skb)); newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb)); /* Clone native IPv6 options from listening socket (if any) @@ -1427,9 +1425,7 @@ ipv6_pktoptions: np->mcast_oif = inet6_iif(opt_skb); if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit; - if (np->rxopt.bits.rxtclass) - np->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(opt_skb)); - if (np->rxopt.bits.rxflow) + if (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass) np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb)); if (ipv6_opt_accepted(sk, opt_skb)) { skb_set_owner_r(opt_skb, sk); -- cgit v1.3-14-g43fede From ad6c81359fc3e6086d1d6f91acda9d5d0e64b2c3 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Sun, 8 Dec 2013 12:16:10 +0100 Subject: ipv4: add support for IFA_FLAGS nl attribute Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 2 +- net/ipv4/devinet.c | 8 ++++++-- 2 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index ae174ca565c9..562e5c7c5d35 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -136,8 +136,8 @@ struct in_ifaddr { __be32 ifa_mask; __be32 ifa_broadcast; unsigned char ifa_scope; - unsigned char ifa_flags; unsigned char ifa_prefixlen; + __u32 ifa_flags; char ifa_label[IFNAMSIZ]; /* In seconds, relative to tstamp. Expiry is at tstamp + HZ * lft. */ diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 43065be36301..6f49efc9d4b7 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -99,6 +99,7 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { [IFA_BROADCAST] = { .type = NLA_U32 }, [IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) }, + [IFA_FLAGS] = { .type = NLA_U32 }, }; #define IN4_ADDR_HSIZE_SHIFT 8 @@ -757,7 +758,8 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, INIT_HLIST_NODE(&ifa->hash); ifa->ifa_prefixlen = ifm->ifa_prefixlen; ifa->ifa_mask = inet_make_mask(ifm->ifa_prefixlen); - ifa->ifa_flags = ifm->ifa_flags; + ifa->ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : + ifm->ifa_flags; ifa->ifa_scope = ifm->ifa_scope; ifa->ifa_dev = in_dev; @@ -1437,7 +1439,8 @@ static size_t inet_nlmsg_size(void) + nla_total_size(4) /* IFA_ADDRESS */ + nla_total_size(4) /* IFA_LOCAL */ + nla_total_size(4) /* IFA_BROADCAST */ - + nla_total_size(IFNAMSIZ); /* IFA_LABEL */ + + nla_total_size(IFNAMSIZ) /* IFA_LABEL */ + + nla_total_size(4); /* IFA_FLAGS */ } static inline u32 cstamp_delta(unsigned long cstamp) @@ -1505,6 +1508,7 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, nla_put_be32(skb, IFA_BROADCAST, ifa->ifa_broadcast)) || (ifa->ifa_label[0] && nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) || + nla_put_u32(skb, IFA_FLAGS, ifa->ifa_flags) || put_cacheinfo(skb, ifa->ifa_cstamp, ifa->ifa_tstamp, preferred, valid)) goto nla_put_failure; -- cgit v1.3-14-g43fede From 37cb0620073cb64101d9307931c135c70b2e3f04 Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Tue, 10 Dec 2013 20:45:41 -0800 Subject: tipc: remove TIPC usage of field af_packet_priv in struct net_device TIPC is currently using the field 'af_packet_priv' in struct net_device as a handle to find the bearer instance associated to the given network device. But, by doing so it is blocking other networking cleanups, such as the one discussed here: http://patchwork.ozlabs.org/patch/178044/ This commit removes this usage from TIPC. Instead, we introduce a new field, 'tipc_ptr', to the net_device structure, to serve this purpose. When TIPC bearer is enabled, the bearer object is associated to 'tipc_ptr'. When a TIPC packet arrives in the recv_msg() upcall from a networking device, the bearer object can now be obtained from 'tipc_ptr'. When a bearer is disabled, the bearer object is detached from its underlying network device by setting 'tipc_ptr' to NULL. Additionally, an RCU lock is used to protect the new pointer. Henceforth, the existing tipc_net_lock is used in write mode to serialize write accesses to this pointer, while the new RCU lock is applied on the read side to ensure that the pointer is 100% valid within its wrapped area for all readers. Signed-off-by: Ying Xue Cc: Patrick McHardy Reviewed-by: Paul Gortmaker Signed-off-by: Jon Maloy Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ net/tipc/bearer.h | 2 ++ net/tipc/eth_media.c | 55 +++++++++++++++++++++++++++-------------------- net/tipc/ib_media.c | 54 ++++++++++++++++++++++++++-------------------- 4 files changed, 68 insertions(+), 46 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9d55e5188b96..0ca8100f9fbc 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1282,6 +1282,9 @@ struct net_device { #endif #if IS_ENABLED(CONFIG_NET_DSA) struct dsa_switch_tree *dsa_ptr; /* dsa specific data */ +#endif +#if IS_ENABLED(CONFIG_TIPC) + struct tipc_bearer __rcu *tipc_ptr; /* TIPC specific data */ #endif void *atalk_ptr; /* AppleTalk link */ struct in_device __rcu *ip_ptr; /* IPv4 specific data */ diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index e50266aa4d10..91b8d8b92373 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -105,6 +105,7 @@ struct tipc_media { /** * struct tipc_bearer - Generic TIPC bearer structure + * @dev: ptr to associated network device * @usr_handle: pointer to additional media-specific information about bearer * @mtu: max packet size bearer can support * @lock: spinlock for controlling access to bearer @@ -127,6 +128,7 @@ struct tipc_media { * care of initializing all other fields. */ struct tipc_bearer { + struct net_device *dev; void *usr_handle; /* initalized by media */ u32 mtu; /* initalized by media */ struct tipc_media_addr addr; /* initalized by media */ diff --git a/net/tipc/eth_media.c b/net/tipc/eth_media.c index 37fb145476ec..c5f685dee15b 100644 --- a/net/tipc/eth_media.c +++ b/net/tipc/eth_media.c @@ -63,6 +63,9 @@ static int eth_started; static int recv_notification(struct notifier_block *nb, unsigned long evt, void *dv); +static int recv_msg(struct sk_buff *buf, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev); + /* * Network device notifier info */ @@ -71,6 +74,11 @@ static struct notifier_block notifier = { .priority = 0 }; +static struct packet_type tipc_packet_type __read_mostly = { + .type = __constant_htons(ETH_P_TIPC), + .func = recv_msg, +}; + /** * eth_media_addr_set - initialize Ethernet media address structure * @@ -128,20 +136,25 @@ static int send_msg(struct sk_buff *buf, struct tipc_bearer *tb_ptr, static int recv_msg(struct sk_buff *buf, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { - struct eth_media *eb_ptr = (struct eth_media *)pt->af_packet_priv; + struct tipc_bearer *b_ptr; if (!net_eq(dev_net(dev), &init_net)) { kfree_skb(buf); return NET_RX_DROP; } - if (likely(eb_ptr->bearer)) { + rcu_read_lock(); + b_ptr = rcu_dereference(dev->tipc_ptr); + if (likely(b_ptr)) { if (likely(buf->pkt_type <= PACKET_BROADCAST)) { buf->next = NULL; - tipc_recv_msg(buf, eb_ptr->bearer); + tipc_recv_msg(buf, b_ptr); + rcu_read_unlock(); return NET_RX_SUCCESS; } } + rcu_read_unlock(); + kfree_skb(buf); return NET_RX_DROP; } @@ -151,10 +164,7 @@ static int recv_msg(struct sk_buff *buf, struct net_device *dev, */ static void setup_media(struct work_struct *work) { - struct eth_media *eb_ptr = - container_of(work, struct eth_media, setup); - - dev_add_pack(&eb_ptr->tipc_packet_type); + dev_add_pack(&tipc_packet_type); } /** @@ -183,15 +193,11 @@ static int enable_media(struct tipc_bearer *tb_ptr) /* Create Ethernet bearer for device */ eb_ptr->dev = dev; - eb_ptr->tipc_packet_type.type = htons(ETH_P_TIPC); - eb_ptr->tipc_packet_type.dev = dev; - eb_ptr->tipc_packet_type.func = recv_msg; - eb_ptr->tipc_packet_type.af_packet_priv = eb_ptr; - INIT_LIST_HEAD(&(eb_ptr->tipc_packet_type.list)); INIT_WORK(&eb_ptr->setup, setup_media); schedule_work(&eb_ptr->setup); /* Associate TIPC bearer with Ethernet bearer */ + tb_ptr->dev = dev; eb_ptr->bearer = tb_ptr; tb_ptr->usr_handle = (void *)eb_ptr; memset(tb_ptr->bcast_addr.value, 0, sizeof(tb_ptr->bcast_addr.value)); @@ -200,6 +206,7 @@ static int enable_media(struct tipc_bearer *tb_ptr) tb_ptr->bcast_addr.broadcast = 1; tb_ptr->mtu = dev->mtu; eth_media_addr_set(tb_ptr, &tb_ptr->addr, (char *)dev->dev_addr); + rcu_assign_pointer(dev->tipc_ptr, tb_ptr); return 0; } @@ -213,7 +220,7 @@ static void cleanup_media(struct work_struct *work) struct eth_media *eb_ptr = container_of(work, struct eth_media, cleanup); - dev_remove_pack(&eb_ptr->tipc_packet_type); + dev_remove_pack(&tipc_packet_type); dev_put(eb_ptr->dev); eb_ptr->dev = NULL; } @@ -232,6 +239,7 @@ static void disable_media(struct tipc_bearer *tb_ptr) eb_ptr->bearer = NULL; INIT_WORK(&eb_ptr->cleanup, cleanup_media); schedule_work(&eb_ptr->cleanup); + RCU_INIT_POINTER(tb_ptr->dev->tipc_ptr, NULL); } /** @@ -243,21 +251,20 @@ static void disable_media(struct tipc_bearer *tb_ptr) static int recv_notification(struct notifier_block *nb, unsigned long evt, void *ptr) { + struct tipc_bearer *b_ptr; struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct eth_media *eb_ptr = ð_media_array[0]; - struct eth_media *stop = ð_media_array[MAX_ETH_MEDIA]; if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; - while ((eb_ptr->dev != dev)) { - if (++eb_ptr == stop) - return NOTIFY_DONE; /* couldn't find device */ - } - if (!eb_ptr->bearer) + rcu_read_lock(); + b_ptr = rcu_dereference(dev->tipc_ptr); + if (!b_ptr) { + rcu_read_unlock(); return NOTIFY_DONE; /* bearer had been disabled */ + } - eb_ptr->bearer->mtu = dev->mtu; + b_ptr->mtu = dev->mtu; switch (evt) { case NETDEV_CHANGE: @@ -266,13 +273,15 @@ static int recv_notification(struct notifier_block *nb, unsigned long evt, case NETDEV_DOWN: case NETDEV_CHANGEMTU: case NETDEV_CHANGEADDR: - tipc_reset_bearer(eb_ptr->bearer); + tipc_reset_bearer(b_ptr); break; case NETDEV_UNREGISTER: case NETDEV_CHANGENAME: - tipc_disable_bearer(eb_ptr->bearer->name); + tipc_disable_bearer(b_ptr->name); break; } + rcu_read_unlock(); + return NOTIFY_OK; } diff --git a/net/tipc/ib_media.c b/net/tipc/ib_media.c index 48e1c07842e6..9fdf03cd672b 100644 --- a/net/tipc/ib_media.c +++ b/net/tipc/ib_media.c @@ -62,6 +62,13 @@ struct ib_media { static struct ib_media ib_media_array[MAX_IB_MEDIA]; static int ib_started; +static int recv_msg(struct sk_buff *buf, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev); + +static struct packet_type tipc_packet_type __read_mostly = { + .type = __constant_htons(ETH_P_TIPC), + .func = recv_msg, +}; /** * ib_media_addr_set - initialize Infiniband media address structure @@ -120,20 +127,25 @@ static int send_msg(struct sk_buff *buf, struct tipc_bearer *tb_ptr, static int recv_msg(struct sk_buff *buf, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { - struct ib_media *ib_ptr = (struct ib_media *)pt->af_packet_priv; + struct tipc_bearer *b_ptr; if (!net_eq(dev_net(dev), &init_net)) { kfree_skb(buf); return NET_RX_DROP; } - if (likely(ib_ptr->bearer)) { + rcu_read_lock(); + b_ptr = rcu_dereference(dev->tipc_ptr); + if (likely(b_ptr)) { if (likely(buf->pkt_type <= PACKET_BROADCAST)) { buf->next = NULL; - tipc_recv_msg(buf, ib_ptr->bearer); + tipc_recv_msg(buf, b_ptr); + rcu_read_unlock(); return NET_RX_SUCCESS; } } + rcu_read_unlock(); + kfree_skb(buf); return NET_RX_DROP; } @@ -143,10 +155,7 @@ static int recv_msg(struct sk_buff *buf, struct net_device *dev, */ static void setup_media(struct work_struct *work) { - struct ib_media *ib_ptr = - container_of(work, struct ib_media, setup); - - dev_add_pack(&ib_ptr->tipc_packet_type); + dev_add_pack(&tipc_packet_type); } /** @@ -175,15 +184,11 @@ static int enable_media(struct tipc_bearer *tb_ptr) /* Create InfiniBand bearer for device */ ib_ptr->dev = dev; - ib_ptr->tipc_packet_type.type = htons(ETH_P_TIPC); - ib_ptr->tipc_packet_type.dev = dev; - ib_ptr->tipc_packet_type.func = recv_msg; - ib_ptr->tipc_packet_type.af_packet_priv = ib_ptr; - INIT_LIST_HEAD(&(ib_ptr->tipc_packet_type.list)); INIT_WORK(&ib_ptr->setup, setup_media); schedule_work(&ib_ptr->setup); /* Associate TIPC bearer with InfiniBand bearer */ + tb_ptr->dev = dev; ib_ptr->bearer = tb_ptr; tb_ptr->usr_handle = (void *)ib_ptr; memset(tb_ptr->bcast_addr.value, 0, sizeof(tb_ptr->bcast_addr.value)); @@ -192,6 +197,7 @@ static int enable_media(struct tipc_bearer *tb_ptr) tb_ptr->bcast_addr.broadcast = 1; tb_ptr->mtu = dev->mtu; ib_media_addr_set(tb_ptr, &tb_ptr->addr, (char *)dev->dev_addr); + rcu_assign_pointer(dev->tipc_ptr, tb_ptr); return 0; } @@ -205,7 +211,7 @@ static void cleanup_bearer(struct work_struct *work) struct ib_media *ib_ptr = container_of(work, struct ib_media, cleanup); - dev_remove_pack(&ib_ptr->tipc_packet_type); + dev_remove_pack(&tipc_packet_type); dev_put(ib_ptr->dev); ib_ptr->dev = NULL; } @@ -224,6 +230,7 @@ static void disable_media(struct tipc_bearer *tb_ptr) ib_ptr->bearer = NULL; INIT_WORK(&ib_ptr->cleanup, cleanup_bearer); schedule_work(&ib_ptr->cleanup); + RCU_INIT_POINTER(tb_ptr->dev->tipc_ptr, NULL); } /** @@ -235,21 +242,20 @@ static void disable_media(struct tipc_bearer *tb_ptr) static int recv_notification(struct notifier_block *nb, unsigned long evt, void *ptr) { + struct tipc_bearer *b_ptr; struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct ib_media *ib_ptr = &ib_media_array[0]; - struct ib_media *stop = &ib_media_array[MAX_IB_MEDIA]; if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; - while ((ib_ptr->dev != dev)) { - if (++ib_ptr == stop) - return NOTIFY_DONE; /* couldn't find device */ - } - if (!ib_ptr->bearer) + rcu_read_lock(); + b_ptr = rcu_dereference(dev->tipc_ptr); + if (!b_ptr) { + rcu_read_unlock(); return NOTIFY_DONE; /* bearer had been disabled */ + } - ib_ptr->bearer->mtu = dev->mtu; + b_ptr->mtu = dev->mtu; switch (evt) { case NETDEV_CHANGE: @@ -258,13 +264,15 @@ static int recv_notification(struct notifier_block *nb, unsigned long evt, case NETDEV_DOWN: case NETDEV_CHANGEMTU: case NETDEV_CHANGEADDR: - tipc_reset_bearer(ib_ptr->bearer); + tipc_reset_bearer(b_ptr); break; case NETDEV_UNREGISTER: case NETDEV_CHANGENAME: - tipc_disable_bearer(ib_ptr->bearer->name); + tipc_disable_bearer(b_ptr->name); break; } + rcu_read_unlock(); + return NOTIFY_OK; } -- cgit v1.3-14-g43fede From 98b32decc83ed3137e3ddbc918b102f8fc406b6d Mon Sep 17 00:00:00 2001 From: Jeff Kirsher Date: Fri, 6 Dec 2013 08:56:16 -0800 Subject: nfc: Fix FSF address in file headers Several files refer to an old address for the Free Software Foundation in the file header comment. Resolve by replacing the address with the URL so that we do not have to keep updating the header comments anytime the address changes. CC: linux-wireless@vger.kernel.org CC: Lauro Ramos Venancio CC: Aloisio Almeida Jr CC: Samuel Ortiz Signed-off-by: Jeff Kirsher Signed-off-by: John W. Linville --- drivers/nfc/mei_phy.c | 4 +--- drivers/nfc/microread/i2c.c | 4 +--- drivers/nfc/microread/mei.c | 4 +--- drivers/nfc/microread/microread.c | 4 +--- drivers/nfc/microread/microread.h | 4 +--- drivers/nfc/nfcwilink.c | 3 +-- drivers/nfc/pn533.c | 4 +--- drivers/nfc/pn544/i2c.c | 4 +--- drivers/nfc/pn544/mei.c | 4 +--- drivers/nfc/pn544/pn544.c | 4 +--- drivers/nfc/pn544/pn544.h | 4 +--- include/linux/platform_data/pn544.h | 3 +-- net/nfc/af_nfc.c | 4 +--- net/nfc/core.c | 4 +--- net/nfc/hci/command.c | 4 +--- net/nfc/hci/core.c | 4 +--- net/nfc/hci/hci.h | 4 +--- net/nfc/hci/hcp.c | 4 +--- net/nfc/hci/llc.c | 4 +--- net/nfc/hci/llc.h | 4 +--- net/nfc/hci/llc_nop.c | 4 +--- net/nfc/hci/llc_shdlc.c | 4 +--- net/nfc/llcp.h | 4 +--- net/nfc/llcp_commands.c | 4 +--- net/nfc/llcp_core.c | 4 +--- net/nfc/llcp_sock.c | 4 +--- net/nfc/nci/core.c | 3 +-- net/nfc/nci/data.c | 3 +-- net/nfc/nci/lib.c | 3 +-- net/nfc/nci/ntf.c | 3 +-- net/nfc/nci/rsp.c | 3 +-- net/nfc/netlink.c | 4 +--- net/nfc/nfc.h | 4 +--- net/nfc/rawsock.c | 4 +--- 34 files changed, 34 insertions(+), 95 deletions(-) (limited to 'include/linux') diff --git a/drivers/nfc/mei_phy.c b/drivers/nfc/mei_phy.c index 85f90090cc1d..1d7860551985 100644 --- a/drivers/nfc/mei_phy.c +++ b/drivers/nfc/mei_phy.c @@ -13,9 +13,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/drivers/nfc/microread/i2c.c b/drivers/nfc/microread/i2c.c index 696e3467eccc..df85cd3d9db0 100644 --- a/drivers/nfc/microread/i2c.c +++ b/drivers/nfc/microread/i2c.c @@ -13,9 +13,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/drivers/nfc/microread/mei.c b/drivers/nfc/microread/mei.c index 72fafec3d460..2d1395be64ae 100644 --- a/drivers/nfc/microread/mei.c +++ b/drivers/nfc/microread/mei.c @@ -13,9 +13,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/drivers/nfc/microread/microread.c b/drivers/nfc/microread/microread.c index 970ded6bfcf5..f868333271aa 100644 --- a/drivers/nfc/microread/microread.c +++ b/drivers/nfc/microread/microread.c @@ -13,9 +13,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/drivers/nfc/microread/microread.h b/drivers/nfc/microread/microread.h index 64b447a1c5bf..f538641431a2 100644 --- a/drivers/nfc/microread/microread.h +++ b/drivers/nfc/microread/microread.h @@ -12,9 +12,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ #ifndef __LOCAL_MICROREAD_H_ diff --git a/drivers/nfc/nfcwilink.c b/drivers/nfc/nfcwilink.c index 71308645593f..683671a71c7e 100644 --- a/drivers/nfc/nfcwilink.c +++ b/drivers/nfc/nfcwilink.c @@ -22,8 +22,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see . * */ #include diff --git a/drivers/nfc/pn533.c b/drivers/nfc/pn533.c index 2daf04c07338..3df19e657bc1 100644 --- a/drivers/nfc/pn533.c +++ b/drivers/nfc/pn533.c @@ -13,9 +13,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ #include diff --git a/drivers/nfc/pn544/i2c.c b/drivers/nfc/pn544/i2c.c index b158ee1c2ac6..d6185ff2f87b 100644 --- a/drivers/nfc/pn544/i2c.c +++ b/drivers/nfc/pn544/i2c.c @@ -13,9 +13,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/drivers/nfc/pn544/mei.c b/drivers/nfc/pn544/mei.c index ee67de50c36f..330cd4031009 100644 --- a/drivers/nfc/pn544/mei.c +++ b/drivers/nfc/pn544/mei.c @@ -13,9 +13,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ #include diff --git a/drivers/nfc/pn544/pn544.c b/drivers/nfc/pn544/pn544.c index 74cfa0a88b9e..51e21a87cd84 100644 --- a/drivers/nfc/pn544/pn544.c +++ b/drivers/nfc/pn544/pn544.c @@ -13,9 +13,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/drivers/nfc/pn544/pn544.h b/drivers/nfc/pn544/pn544.h index 01020e585443..491bf45da358 100644 --- a/drivers/nfc/pn544/pn544.h +++ b/drivers/nfc/pn544/pn544.h @@ -12,9 +12,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ #ifndef __LOCAL_PN544_H_ diff --git a/include/linux/platform_data/pn544.h b/include/linux/platform_data/pn544.h index 713bfd703342..5ce1ab983f44 100644 --- a/include/linux/platform_data/pn544.h +++ b/include/linux/platform_data/pn544.h @@ -16,8 +16,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see . */ #ifndef _PN544_H_ diff --git a/net/nfc/af_nfc.c b/net/nfc/af_nfc.c index 9d68441e2a5a..2277276f52bc 100644 --- a/net/nfc/af_nfc.c +++ b/net/nfc/af_nfc.c @@ -16,9 +16,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ #include diff --git a/net/nfc/core.c b/net/nfc/core.c index 872529105abc..02ab34132157 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -16,9 +16,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ #define pr_fmt(fmt) KBUILD_MODNAME ": %s: " fmt, __func__ diff --git a/net/nfc/hci/command.c b/net/nfc/hci/command.c index 64f922be9281..a9f4d2e62d8d 100644 --- a/net/nfc/hci/command.c +++ b/net/nfc/hci/command.c @@ -12,9 +12,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ #define pr_fmt(fmt) "hci: %s: " fmt, __func__ diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c index d07ca4c5cf8c..3b9610031baa 100644 --- a/net/nfc/hci/core.c +++ b/net/nfc/hci/core.c @@ -12,9 +12,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ #define pr_fmt(fmt) "hci: %s: " fmt, __func__ diff --git a/net/nfc/hci/hci.h b/net/nfc/hci/hci.h index b274d12c18ac..c3d2e2c1394c 100644 --- a/net/nfc/hci/hci.h +++ b/net/nfc/hci/hci.h @@ -12,9 +12,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ #ifndef __LOCAL_HCI_H diff --git a/net/nfc/hci/hcp.c b/net/nfc/hci/hcp.c index b6b4109f2343..e9de1514656e 100644 --- a/net/nfc/hci/hcp.c +++ b/net/nfc/hci/hcp.c @@ -12,9 +12,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ #define pr_fmt(fmt) "hci: %s: " fmt, __func__ diff --git a/net/nfc/hci/llc.c b/net/nfc/hci/llc.c index fe5e966e5b88..a07d2b818487 100644 --- a/net/nfc/hci/llc.c +++ b/net/nfc/hci/llc.c @@ -13,9 +13,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ #include diff --git a/net/nfc/hci/llc.h b/net/nfc/hci/llc.h index 7be0b7f3ceb6..5dad4c57ffb3 100644 --- a/net/nfc/hci/llc.h +++ b/net/nfc/hci/llc.h @@ -13,9 +13,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ #ifndef __LOCAL_LLC_H_ diff --git a/net/nfc/hci/llc_nop.c b/net/nfc/hci/llc_nop.c index 87b10291b40f..d0435d5a197b 100644 --- a/net/nfc/hci/llc_nop.c +++ b/net/nfc/hci/llc_nop.c @@ -13,9 +13,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ #include diff --git a/net/nfc/hci/llc_shdlc.c b/net/nfc/hci/llc_shdlc.c index 27b313befc35..719ad0ac40de 100644 --- a/net/nfc/hci/llc_shdlc.c +++ b/net/nfc/hci/llc_shdlc.c @@ -13,9 +13,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ #define pr_fmt(fmt) "shdlc: %s: " fmt, __func__ diff --git a/net/nfc/llcp.h b/net/nfc/llcp.h index f4d48b57ea11..de1789e3cc82 100644 --- a/net/nfc/llcp.h +++ b/net/nfc/llcp.h @@ -12,9 +12,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ enum llcp_state { diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index 1017894807c0..693cd1aad582 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -12,9 +12,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ #define pr_fmt(fmt) "llcp: %s: " fmt, __func__ diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index 81cd3416c7d4..1349074e1ffc 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -12,9 +12,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ #define pr_fmt(fmt) "llcp: %s: " fmt, __func__ diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index 824c6056bf82..69fbc8dadba7 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -12,9 +12,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ #define pr_fmt(fmt) "llcp: %s: " fmt, __func__ diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index b943d46a1644..f0e955e3a385 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -20,8 +20,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see . * */ diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c index 2a9399dd6c68..6c3aef852876 100644 --- a/net/nfc/nci/data.c +++ b/net/nfc/nci/data.c @@ -16,8 +16,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see . * */ diff --git a/net/nfc/nci/lib.c b/net/nfc/nci/lib.c index 6b7fd26c68d9..ed774a2e989a 100644 --- a/net/nfc/nci/lib.c +++ b/net/nfc/nci/lib.c @@ -20,8 +20,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see . * */ diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c index b2aa98ef0927..1e905097456b 100644 --- a/net/nfc/nci/ntf.c +++ b/net/nfc/nci/ntf.c @@ -20,8 +20,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see . * */ diff --git a/net/nfc/nci/rsp.c b/net/nfc/nci/rsp.c index dd072f38ad00..041de51ccdbe 100644 --- a/net/nfc/nci/rsp.c +++ b/net/nfc/nci/rsp.c @@ -20,8 +20,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see . * */ diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index a9b2342d5253..ebbf6fb88b35 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -16,9 +16,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ #define pr_fmt(fmt) KBUILD_MODNAME ": %s: " fmt, __func__ diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h index aaf606fc1faa..9d6e74f7e6b3 100644 --- a/net/nfc/nfc.h +++ b/net/nfc/nfc.h @@ -16,9 +16,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ #ifndef __LOCAL_NFC_H diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index 66bcd2eb5773..c27a6e86cae4 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -16,9 +16,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see . */ #define pr_fmt(fmt) KBUILD_MODNAME ": %s: " fmt, __func__ -- cgit v1.3-14-g43fede From b601fa197fff265bf60eaf6950d4c194da080f4a Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Tue, 10 Dec 2013 15:02:40 +0100 Subject: ipv4: fix wildcard search with inet_confirm_addr() Help of this function says: "in_dev: only on this interface, 0=any interface", but since commit 39a6d0630012 ("[NETNS]: Process inet_confirm_addr in the correct namespace."), the code supposes that it will never be NULL. This function is never called with in_dev == NULL, but it's exported and may be used by an external module. Because this patch restore the ability to call inet_confirm_addr() with in_dev == NULL, I partially revert the above commit, as suggested by Julian. CC: Julian Anastasov Signed-off-by: Nicolas Dichtel Reviewed-by: Julian Anastasov Signed-off-by: David S. Miller --- drivers/net/bonding/bonding.h | 4 ++-- include/linux/inetdevice.h | 5 ++--- net/ipv4/arp.c | 4 +++- net/ipv4/devinet.c | 9 ++++----- 4 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h index a9f4f9f4d8ce..a74c92c83ead 100644 --- a/drivers/net/bonding/bonding.h +++ b/drivers/net/bonding/bonding.h @@ -394,8 +394,8 @@ static inline __be32 bond_confirm_addr(struct net_device *dev, __be32 dst, __be3 in_dev = __in_dev_get_rcu(dev); if (in_dev) - addr = inet_confirm_addr(in_dev, dst, local, RT_SCOPE_HOST); - + addr = inet_confirm_addr(dev_net(dev), in_dev, dst, local, + RT_SCOPE_HOST); rcu_read_unlock(); return addr; } diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 562e5c7c5d35..0068708161ff 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -164,11 +164,10 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *); void devinet_init(void); struct in_device *inetdev_by_index(struct net *, int); __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope); -__be32 inet_confirm_addr(struct in_device *in_dev, __be32 dst, __be32 local, - int scope); +__be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst, + __be32 local, int scope); struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask); - static __inline__ int inet_ifa_match(__be32 addr, struct in_ifaddr *ifa) { return !((addr^ifa->ifa_address)&ifa->ifa_mask); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index f04185863940..b67cf805910e 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -381,6 +381,7 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip) { + struct net *net = dev_net(in_dev->dev); int scope; switch (IN_DEV_ARP_IGNORE(in_dev)) { @@ -399,6 +400,7 @@ static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip) case 3: /* Do not reply for scope host addresses */ sip = 0; scope = RT_SCOPE_LINK; + in_dev = NULL; break; case 4: /* Reserved */ case 5: @@ -410,7 +412,7 @@ static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip) default: return 0; } - return !inet_confirm_addr(in_dev, sip, tip, scope); + return !inet_confirm_addr(net, in_dev, sip, tip, scope); } static int arp_filter(__be32 sip, __be32 tip, struct net_device *dev) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 6f49efc9d4b7..84956f5f0135 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1240,22 +1240,21 @@ static __be32 confirm_addr_indev(struct in_device *in_dev, __be32 dst, /* * Confirm that local IP address exists using wildcards: - * - in_dev: only on this interface, 0=any interface + * - net: netns to check, cannot be NULL + * - in_dev: only on this interface, NULL=any interface * - dst: only in the same subnet as dst, 0=any dst * - local: address, 0=autoselect the local address * - scope: maximum allowed scope value for the local address */ -__be32 inet_confirm_addr(struct in_device *in_dev, +__be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst, __be32 local, int scope) { __be32 addr = 0; struct net_device *dev; - struct net *net; - if (scope != RT_SCOPE_LINK) + if (in_dev != NULL) return confirm_addr_indev(in_dev, dst, local, scope); - net = dev_net(in_dev->dev); rcu_read_lock(); for_each_netdev_rcu(net, dev) { in_dev = __in_dev_get_rcu(dev); -- cgit v1.3-14-g43fede From 2f6a1b6607fd6b0eb9501843a40e0c7555f37b4a Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Wed, 11 Dec 2013 13:27:11 -0500 Subject: macvlan: Remove custom recieve and forward handlers Since now macvlan and macvtap use the same receive and forward handlers, we can remove them completely and use netif_rx and dev_forward_skb() directly. Signed-off-by: Vlad Yasevich Signed-off-by: David S. Miller --- drivers/net/macvlan.c | 17 +++++------------ drivers/net/macvtap.c | 3 +-- include/linux/if_macvlan.h | 7 +------ 3 files changed, 7 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index cfb91570cddd..24ea994b6274 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -120,7 +120,7 @@ static int macvlan_broadcast_one(struct sk_buff *skb, struct net_device *dev = vlan->dev; if (local) - return vlan->forward(dev, skb); + return dev_forward_skb(dev, skb); skb->dev = dev; if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) @@ -128,7 +128,7 @@ static int macvlan_broadcast_one(struct sk_buff *skb, else skb->pkt_type = PACKET_MULTICAST; - return vlan->receive(skb); + return netif_rx(skb); } static u32 macvlan_hash_mix(const struct macvlan_dev *vlan) @@ -251,7 +251,7 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb) skb->dev = dev; skb->pkt_type = PACKET_HOST; - ret = vlan->receive(skb); + ret = netif_rx(skb); out: macvlan_count_rx(vlan, len, ret == NET_RX_SUCCESS, 0); @@ -803,10 +803,7 @@ static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[]) } int macvlan_common_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], - int (*receive)(struct sk_buff *skb), - int (*forward)(struct net_device *dev, - struct sk_buff *skb)) + struct nlattr *tb[], struct nlattr *data[]) { struct macvlan_dev *vlan = netdev_priv(dev); struct macvlan_port *port; @@ -848,8 +845,6 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, vlan->lowerdev = lowerdev; vlan->dev = dev; vlan->port = port; - vlan->receive = receive; - vlan->forward = forward; vlan->set_features = MACVLAN_FEATURES; vlan->mode = MACVLAN_MODE_VEPA; @@ -894,9 +889,7 @@ EXPORT_SYMBOL_GPL(macvlan_common_newlink); static int macvlan_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { - return macvlan_common_newlink(src_net, dev, tb, data, - netif_rx, - dev_forward_skb); + return macvlan_common_newlink(src_net, dev, tb, data); } void macvlan_dellink(struct net_device *dev, struct list_head *head) diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 85ecfccf9c60..64409af0da31 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -400,8 +400,7 @@ static int macvtap_newlink(struct net *src_net, /* Don't put anything that may fail after macvlan_common_newlink * because we can't undo what it does. */ - return macvlan_common_newlink(src_net, dev, tb, data, - netif_rx, dev_forward_skb); + return macvlan_common_newlink(src_net, dev, tb, data); } static void macvtap_dellink(struct net_device *dev, diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 84ba5ac39e03..ea22721ba269 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -69,8 +69,6 @@ struct macvlan_dev { netdev_features_t set_features; enum macvlan_mode mode; u16 flags; - int (*receive)(struct sk_buff *skb); - int (*forward)(struct net_device *dev, struct sk_buff *skb); /* This array tracks active taps. */ struct macvtap_queue __rcu *taps[MAX_MACVTAP_QUEUES]; /* This list tracks all taps (both enabled and disabled) */ @@ -103,10 +101,7 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan, extern void macvlan_common_setup(struct net_device *dev); extern int macvlan_common_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], - int (*receive)(struct sk_buff *skb), - int (*forward)(struct net_device *dev, - struct sk_buff *skb)); + struct nlattr *tb[], struct nlattr *data[]); extern void macvlan_count_rx(const struct macvlan_dev *vlan, unsigned int len, bool success, -- cgit v1.3-14-g43fede From 299603e8370a93dd5d8e8d800f0dff1ce2c53d36 Mon Sep 17 00:00:00 2001 From: Jerry Chu Date: Wed, 11 Dec 2013 20:53:45 -0800 Subject: net-gro: Prepare GRO stack for the upcoming tunneling support This patch modifies the GRO stack to avoid the use of "network_header" and associated macros like ip_hdr() and ipv6_hdr() in order to allow an arbitary number of IP hdrs (v4 or v6) to be used in the encapsulation chain. This lays the foundation for various IP tunneling support (IP-in-IP, GRE, VXLAN, SIT,...) to be added later. With this patch, the GRO stack traversing now is mostly based on skb_gro_offset rather than special hdr offsets saved in skb (e.g., skb->network_header). As a result all but the top layer (i.e., the the transport layer) must have hdrs of the same length in order for a pkt to be considered for aggregation. Therefore when adding a new encap layer (e.g., for tunneling), one must check and skip flows (e.g., by setting NAPI_GRO_CB(p)->same_flow to 0) that have a different hdr length. Note that unlike the network header, the transport header can and will continue to be set by the GRO code since there will be at most one "transport layer" in the encap chain. Signed-off-by: H.K. Jerry Chu Suggested-by: Eric Dumazet Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- net/core/dev.c | 76 ++++++++++++++++------------------------------- net/ipv4/af_inet.c | 25 ++++++++++++---- net/ipv4/tcp_offload.c | 9 +++--- net/ipv6/ip6_offload.c | 54 ++++++++++++++++++++++++++------- net/ipv6/tcpv6_offload.c | 6 ++-- 6 files changed, 97 insertions(+), 75 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0ca8100f9fbc..5260d2eae2e6 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1676,7 +1676,7 @@ struct offload_callbacks { int (*gso_send_check)(struct sk_buff *skb); struct sk_buff **(*gro_receive)(struct sk_buff **head, struct sk_buff *skb); - int (*gro_complete)(struct sk_buff *skb); + int (*gro_complete)(struct sk_buff *skb, int nhoff); }; struct packet_offload { diff --git a/net/core/dev.c b/net/core/dev.c index 355df36360b4..c95d664b2b42 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3752,7 +3752,7 @@ static int napi_gro_complete(struct sk_buff *skb) if (ptype->type != type || !ptype->callbacks.gro_complete) continue; - err = ptype->callbacks.gro_complete(skb); + err = ptype->callbacks.gro_complete(skb, 0); break; } rcu_read_unlock(); @@ -3818,6 +3818,23 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) } } +static void skb_gro_reset_offset(struct sk_buff *skb) +{ + const struct skb_shared_info *pinfo = skb_shinfo(skb); + const skb_frag_t *frag0 = &pinfo->frags[0]; + + NAPI_GRO_CB(skb)->data_offset = 0; + NAPI_GRO_CB(skb)->frag0 = NULL; + NAPI_GRO_CB(skb)->frag0_len = 0; + + if (skb_mac_header(skb) == skb_tail_pointer(skb) && + pinfo->nr_frags && + !PageHighMem(skb_frag_page(frag0))) { + NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); + NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0); + } +} + static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { struct sk_buff **pp = NULL; @@ -3833,6 +3850,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff if (skb_is_gso(skb) || skb_has_frag_list(skb)) goto normal; + skb_gro_reset_offset(skb); gro_list_prepare(napi, skb); rcu_read_lock(); @@ -3938,27 +3956,8 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) return ret; } -static void skb_gro_reset_offset(struct sk_buff *skb) -{ - const struct skb_shared_info *pinfo = skb_shinfo(skb); - const skb_frag_t *frag0 = &pinfo->frags[0]; - - NAPI_GRO_CB(skb)->data_offset = 0; - NAPI_GRO_CB(skb)->frag0 = NULL; - NAPI_GRO_CB(skb)->frag0_len = 0; - - if (skb_mac_header(skb) == skb_tail_pointer(skb) && - pinfo->nr_frags && - !PageHighMem(skb_frag_page(frag0))) { - NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); - NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0); - } -} - gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { - skb_gro_reset_offset(skb); - return napi_skb_finish(dev_gro_receive(napi, skb), skb); } EXPORT_SYMBOL(napi_gro_receive); @@ -3992,12 +3991,7 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff * { switch (ret) { case GRO_NORMAL: - case GRO_HELD: - skb->protocol = eth_type_trans(skb, skb->dev); - - if (ret == GRO_HELD) - skb_gro_pull(skb, -ETH_HLEN); - else if (netif_receive_skb(skb)) + if (netif_receive_skb(skb)) ret = GRO_DROP; break; @@ -4006,6 +4000,7 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff * napi_reuse_skb(napi, skb); break; + case GRO_HELD: case GRO_MERGED: break; } @@ -4016,36 +4011,15 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff * static struct sk_buff *napi_frags_skb(struct napi_struct *napi) { struct sk_buff *skb = napi->skb; - struct ethhdr *eth; - unsigned int hlen; - unsigned int off; napi->skb = NULL; - skb_reset_mac_header(skb); - skb_gro_reset_offset(skb); - - off = skb_gro_offset(skb); - hlen = off + sizeof(*eth); - eth = skb_gro_header_fast(skb, off); - if (skb_gro_header_hard(skb, hlen)) { - eth = skb_gro_header_slow(skb, hlen, off); - if (unlikely(!eth)) { - napi_reuse_skb(napi, skb); - skb = NULL; - goto out; - } + if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr)))) { + napi_reuse_skb(napi, skb); + return NULL; } + skb->protocol = eth_type_trans(skb, skb->dev); - skb_gro_pull(skb, sizeof(*eth)); - - /* - * This works because the only protocols we care about don't require - * special handling. We'll fix it up properly at the end. - */ - skb->protocol = eth->h_proto; - -out: return skb; } diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 70011e029ac1..ef4f9df6d698 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1377,8 +1377,12 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, if (!NAPI_GRO_CB(p)->same_flow) continue; - iph2 = ip_hdr(p); - + iph2 = (struct iphdr *)(p->data + off); + /* The above works because, with the exception of the top + * (inner most) layer, we only aggregate pkts with the same + * hdr length so all the hdrs we'll need to verify will start + * at the same offset. + */ if ((iph->protocol ^ iph2->protocol) | ((__force u32)iph->saddr ^ (__force u32)iph2->saddr) | ((__force u32)iph->daddr ^ (__force u32)iph2->daddr)) { @@ -1397,6 +1401,11 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, } NAPI_GRO_CB(skb)->flush |= flush; + skb_set_network_header(skb, off); + /* The above will be needed by the transport layer if there is one + * immediately following this IP hdr. + */ + skb_gro_pull(skb, sizeof(*iph)); skb_set_transport_header(skb, skb_gro_offset(skb)); @@ -1411,10 +1420,10 @@ out: return pp; } -static int inet_gro_complete(struct sk_buff *skb) +static int inet_gro_complete(struct sk_buff *skb, int nhoff) { - __be16 newlen = htons(skb->len - skb_network_offset(skb)); - struct iphdr *iph = ip_hdr(skb); + __be16 newlen = htons(skb->len - nhoff); + struct iphdr *iph = (struct iphdr *)(skb->data + nhoff); const struct net_offload *ops; int proto = iph->protocol; int err = -ENOSYS; @@ -1427,7 +1436,11 @@ static int inet_gro_complete(struct sk_buff *skb) if (WARN_ON(!ops || !ops->callbacks.gro_complete)) goto out_unlock; - err = ops->callbacks.gro_complete(skb); + /* Only need to add sizeof(*iph) to get to the next hdr below + * because any hdr with option will have been flushed in + * inet_gro_receive(). + */ + err = ops->callbacks.gro_complete(skb, nhoff + sizeof(*iph)); out_unlock: rcu_read_unlock(); diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 05606353c7e7..2658a27f540d 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -240,7 +240,7 @@ int tcp_gro_complete(struct sk_buff *skb) { struct tcphdr *th = tcp_hdr(skb); - skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_start = (unsigned char *)th - skb->head; skb->csum_offset = offsetof(struct tcphdr, check); skb->ip_summed = CHECKSUM_PARTIAL; @@ -272,6 +272,7 @@ static int tcp_v4_gso_send_check(struct sk_buff *skb) static struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb) { + /* Use the IP hdr immediately proceeding for this transport */ const struct iphdr *iph = skb_gro_network_header(skb); __wsum wsum; @@ -303,13 +304,13 @@ skip_csum: return tcp_gro_receive(head, skb); } -static int tcp4_gro_complete(struct sk_buff *skb) +static int tcp4_gro_complete(struct sk_buff *skb, int thoff) { const struct iphdr *iph = ip_hdr(skb); struct tcphdr *th = tcp_hdr(skb); - th->check = ~tcp_v4_check(skb->len - skb_transport_offset(skb), - iph->saddr, iph->daddr, 0); + th->check = ~tcp_v4_check(skb->len - thoff, iph->saddr, + iph->daddr, 0); skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; return tcp_gro_complete(skb); diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 4b851692b1f6..7540a0ed75ae 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -154,6 +154,35 @@ out: return segs; } +/* Return the total length of all the extension hdrs, following the same + * logic in ipv6_gso_pull_exthdrs() when parsing ext-hdrs. + */ +static int ipv6_exthdrs_len(struct ipv6hdr *iph, + const struct net_offload **opps) +{ + struct ipv6_opt_hdr *opth = NULL; + int len = 0, proto, optlen; + + proto = iph->nexthdr; + for (;;) { + if (proto != NEXTHDR_HOP) { + *opps = rcu_dereference(inet6_offloads[proto]); + if (unlikely(!(*opps))) + break; + if (!((*opps)->flags & INET6_PROTO_GSO_EXTHDR)) + break; + } + if (opth == NULL) + opth = (void *)(iph+1); + else + opth = (void *)opth + optlen; + optlen = ipv6_optlen(opth); + len += optlen; + proto = opth->nexthdr; + } + return len; +} + static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, struct sk_buff *skb) { @@ -177,6 +206,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, goto out; } + skb_set_network_header(skb, off); skb_gro_pull(skb, sizeof(*iph)); skb_set_transport_header(skb, skb_gro_offset(skb)); @@ -211,12 +241,16 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, if (!NAPI_GRO_CB(p)->same_flow) continue; - iph2 = ipv6_hdr(p); + iph2 = (struct ipv6hdr *)(p->data + off); first_word = *(__be32 *)iph ^ *(__be32 *)iph2 ; - /* All fields must match except length and Traffic Class. */ - if (nlen != skb_network_header_len(p) || - (first_word & htonl(0xF00FFFFF)) || + /* All fields must match except length and Traffic Class. + * XXX skbs on the gro_list have all been parsed and pulled + * already so we don't need to compare nlen + * (nlen != (sizeof(*iph2) + ipv6_exthdrs_len(iph2, &ops))) + * memcmp() alone below is suffcient, right? + */ + if ((first_word & htonl(0xF00FFFFF)) || memcmp(&iph->nexthdr, &iph2->nexthdr, nlen - offsetof(struct ipv6hdr, nexthdr))) { NAPI_GRO_CB(p)->same_flow = 0; @@ -245,21 +279,21 @@ out: return pp; } -static int ipv6_gro_complete(struct sk_buff *skb) +static int ipv6_gro_complete(struct sk_buff *skb, int nhoff) { const struct net_offload *ops; - struct ipv6hdr *iph = ipv6_hdr(skb); + struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + nhoff); int err = -ENOSYS; - iph->payload_len = htons(skb->len - skb_network_offset(skb) - - sizeof(*iph)); + iph->payload_len = htons(skb->len - nhoff - sizeof(*iph)); rcu_read_lock(); - ops = rcu_dereference(inet6_offloads[NAPI_GRO_CB(skb)->proto]); + + nhoff += sizeof(*iph) + ipv6_exthdrs_len(iph, &ops); if (WARN_ON(!ops || !ops->callbacks.gro_complete)) goto out_unlock; - err = ops->callbacks.gro_complete(skb); + err = ops->callbacks.gro_complete(skb, nhoff); out_unlock: rcu_read_unlock(); diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index 6d18157dc32c..0d78132ff18a 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -66,13 +66,13 @@ skip_csum: return tcp_gro_receive(head, skb); } -static int tcp6_gro_complete(struct sk_buff *skb) +static int tcp6_gro_complete(struct sk_buff *skb, int thoff) { const struct ipv6hdr *iph = ipv6_hdr(skb); struct tcphdr *th = tcp_hdr(skb); - th->check = ~tcp_v6_check(skb->len - skb_transport_offset(skb), - &iph->saddr, &iph->daddr, 0); + th->check = ~tcp_v6_check(skb->len - thoff, &iph->saddr, + &iph->daddr, 0); skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; return tcp_gro_complete(skb); -- cgit v1.3-14-g43fede From e001bfad913bf119fb67c1e8dd2d4ec1f5d392fa Mon Sep 17 00:00:00 2001 From: dingtianhong Date: Fri, 13 Dec 2013 10:19:55 +0800 Subject: bonding: create bond_first_slave_rcu() The bond_first_slave_rcu() will be used to instead of bond_first_slave() in rcu_read_lock(). According to the Jay Vosburgh's suggestion, the struct netdev_adjacent should hide from users who wanted to use it directly. so I package a new function to get the first slave of the bond. Suggested-by: Nikolay Aleksandrov Suggested-by: Jay Vosburgh Suggested-by: Veaceslav Falico Signed-off-by: Ding Tianhong Signed-off-by: David S. Miller --- drivers/net/bonding/bonding.h | 4 ++++ include/linux/netdevice.h | 1 + net/core/dev.c | 21 +++++++++++++++++++++ 3 files changed, 26 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h index 8283cbdec50a..8f0d6d0c383b 100644 --- a/drivers/net/bonding/bonding.h +++ b/drivers/net/bonding/bonding.h @@ -101,6 +101,10 @@ netdev_adjacent_get_private(bond_slave_list(bond)->prev) : \ NULL) +/* Caller must have rcu_read_lock */ +#define bond_first_slave_rcu(bond) \ + netdev_lower_get_first_private_rcu(bond->dev) + #define bond_is_first_slave(bond, pos) (pos == bond_first_slave(bond)) #define bond_is_last_slave(bond, pos) (pos == bond_last_slave(bond)) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5260d2eae2e6..2c74d20dad34 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2907,6 +2907,7 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev, priv = netdev_lower_get_next_private_rcu(dev, &(iter))) void *netdev_adjacent_get_private(struct list_head *adj_list); +void *netdev_lower_get_first_private_rcu(struct net_device *dev); struct net_device *netdev_master_upper_dev_get(struct net_device *dev); struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev); int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev); diff --git a/net/core/dev.c b/net/core/dev.c index c95d664b2b42..9d4369ece679 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4543,6 +4543,27 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev, } EXPORT_SYMBOL(netdev_lower_get_next_private_rcu); +/** + * netdev_lower_get_first_private_rcu - Get the first ->private from the + * lower neighbour list, RCU + * variant + * @dev: device + * + * Gets the first netdev_adjacent->private from the dev's lower neighbour + * list. The caller must hold RCU read lock. + */ +void *netdev_lower_get_first_private_rcu(struct net_device *dev) +{ + struct netdev_adjacent *lower; + + lower = list_first_or_null_rcu(&dev->adj_list.lower, + struct netdev_adjacent, list); + if (lower) + return lower->private; + return NULL; +} +EXPORT_SYMBOL(netdev_lower_get_first_private_rcu); + /** * netdev_master_upper_dev_get_rcu - Get master upper device * @dev: device -- cgit v1.3-14-g43fede From 71ae8aac3e198c6f3577cb7ad3a17f6128e97bfa Mon Sep 17 00:00:00 2001 From: Francesco Fusco Date: Thu, 12 Dec 2013 16:09:05 +0100 Subject: lib: introduce arch optimized hash library We introduce a new hashing library that is meant to be used in the contexts where speed is more important than uniformity of the hashed values. The hash library leverages architecture specific implementation to achieve high performance and fall backs to jhash() for the generic case. On Intel-based x86 architectures, the library can exploit the crc32l instruction, part of the Intel SSE4.2 instruction set, if the instruction is supported by the processor. This implementation is twice as fast as the jhash() implementation on an i7 processor. Additional architectures, such as Arm64 provide instructions for accelerating the computation of CRC, so they could be added as well in follow-up work. Signed-off-by: Francesco Fusco Signed-off-by: Daniel Borkmann Signed-off-by: Thomas Graf Cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller --- arch/x86/include/asm/hash.h | 7 ++++ arch/x86/lib/Makefile | 2 +- arch/x86/lib/hash.c | 88 +++++++++++++++++++++++++++++++++++++++++++++ include/asm-generic/hash.h | 9 +++++ include/linux/hash.h | 36 +++++++++++++++++++ lib/Makefile | 2 +- lib/hash.c | 38 ++++++++++++++++++++ 7 files changed, 180 insertions(+), 2 deletions(-) create mode 100644 arch/x86/include/asm/hash.h create mode 100644 arch/x86/lib/hash.c create mode 100644 include/asm-generic/hash.h create mode 100644 lib/hash.c (limited to 'include/linux') diff --git a/arch/x86/include/asm/hash.h b/arch/x86/include/asm/hash.h new file mode 100644 index 000000000000..e8c58f88b1d4 --- /dev/null +++ b/arch/x86/include/asm/hash.h @@ -0,0 +1,7 @@ +#ifndef _ASM_X86_HASH_H +#define _ASM_X86_HASH_H + +struct fast_hash_ops; +extern void setup_arch_fast_hash(struct fast_hash_ops *ops); + +#endif /* _ASM_X86_HASH_H */ diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 992d63bb154f..eabcb6e6a900 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -24,7 +24,7 @@ lib-$(CONFIG_SMP) += rwlock.o lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o -obj-y += msr.o msr-reg.o msr-reg-export.o +obj-y += msr.o msr-reg.o msr-reg-export.o hash.o ifeq ($(CONFIG_X86_32),y) obj-y += atomic64_32.o diff --git a/arch/x86/lib/hash.c b/arch/x86/lib/hash.c new file mode 100644 index 000000000000..3056702e81fb --- /dev/null +++ b/arch/x86/lib/hash.c @@ -0,0 +1,88 @@ +/* + * Some portions derived from code covered by the following notice: + * + * Copyright (c) 2010-2013 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#include + +#include +#include +#include + +static inline u32 crc32_u32(u32 crc, u32 val) +{ + asm ("crc32l %1,%0\n" : "+r" (crc) : "rm" (val)); + return crc; +} + +static u32 intel_crc4_2_hash(const void *data, u32 len, u32 seed) +{ + const u32 *p32 = (const u32 *) data; + u32 i, tmp = 0; + + for (i = 0; i < len / 4; i++) + seed = crc32_u32(*p32++, seed); + + switch (3 - (len & 0x03)) { + case 0: + tmp |= *((const u8 *) p32 + 2) << 16; + /* fallthrough */ + case 1: + tmp |= *((const u8 *) p32 + 1) << 8; + /* fallthrough */ + case 2: + tmp |= *((const u8 *) p32); + seed = crc32_u32(tmp, seed); + default: + break; + } + + return seed; +} + +static u32 intel_crc4_2_hash2(const u32 *data, u32 len, u32 seed) +{ + const u32 *p32 = (const u32 *) data; + u32 i; + + for (i = 0; i < len; i++) + seed = crc32_u32(*p32++, seed); + + return seed; +} + +void setup_arch_fast_hash(struct fast_hash_ops *ops) +{ + if (cpu_has_xmm4_2) { + ops->hash = intel_crc4_2_hash; + ops->hash2 = intel_crc4_2_hash2; + } +} diff --git a/include/asm-generic/hash.h b/include/asm-generic/hash.h new file mode 100644 index 000000000000..05cb3421ee7e --- /dev/null +++ b/include/asm-generic/hash.h @@ -0,0 +1,9 @@ +#ifndef __ASM_GENERIC_HASH_H +#define __ASM_GENERIC_HASH_H + +struct arch_hash_ops; +static inline void setup_arch_fast_hash(struct arch_hash_ops *ops) +{ +} + +#endif /* __ASM_GENERIC_HASH_H */ diff --git a/include/linux/hash.h b/include/linux/hash.h index f09a0ae4d858..bd1754c7ecef 100644 --- a/include/linux/hash.h +++ b/include/linux/hash.h @@ -15,6 +15,7 @@ */ #include +#include #include /* 2^31 + 2^29 - 2^25 + 2^22 - 2^19 - 2^16 + 1 */ @@ -78,4 +79,39 @@ static inline u32 hash32_ptr(const void *ptr) #endif return (u32)val; } + +struct fast_hash_ops { + u32 (*hash)(const void *data, u32 len, u32 seed); + u32 (*hash2)(const u32 *data, u32 len, u32 seed); +}; + +/** + * arch_fast_hash - Caclulates a hash over a given buffer that can have + * arbitrary size. This function will eventually use an + * architecture-optimized hashing implementation if + * available, and trades off distribution for speed. + * + * @data: buffer to hash + * @len: length of buffer in bytes + * @seed: start seed + * + * Returns 32bit hash. + */ +extern u32 arch_fast_hash(const void *data, u32 len, u32 seed); + +/** + * arch_fast_hash2 - Caclulates a hash over a given buffer that has a + * size that is of a multiple of 32bit words. This + * function will eventually use an architecture- + * optimized hashing implementation if available, + * and trades off distribution for speed. + * + * @data: buffer to hash (must be 32bit padded) + * @len: number of 32bit words + * @seed: start seed + * + * Returns 32bit hash. + */ +extern u32 arch_fast_hash2(const u32 *data, u32 len, u32 seed); + #endif /* _LINUX_HASH_H */ diff --git a/lib/Makefile b/lib/Makefile index a459c31e8c6b..d0f79c547d97 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -26,7 +26,7 @@ obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \ bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \ gcd.o lcm.o list_sort.o uuid.o flex_array.o iovec.o clz_ctz.o \ bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o \ - percpu-refcount.o percpu_ida.o + percpu-refcount.o percpu_ida.o hash.o obj-y += string_helpers.o obj-$(CONFIG_TEST_STRING_HELPERS) += test-string_helpers.o obj-y += kstrtox.o diff --git a/lib/hash.c b/lib/hash.c new file mode 100644 index 000000000000..b89f06a2d606 --- /dev/null +++ b/lib/hash.c @@ -0,0 +1,38 @@ +/* General purpose hashing library + * + * That's a start of a kernel hashing library, which can be extended + * with further algorithms in future. arch_fast_hash{2,}() will + * eventually resolve to an architecture optimized implementation. + * + * Copyright 2013 Francesco Fusco + * Copyright 2013 Daniel Borkmann + * Copyright 2013 Thomas Graf + * Licensed under the GNU General Public License, version 2.0 (GPLv2) + */ + +#include +#include + +static struct fast_hash_ops arch_hash_ops __read_mostly = { + .hash = jhash, + .hash2 = jhash2, +}; + +u32 arch_fast_hash(const void *data, u32 len, u32 seed) +{ + return arch_hash_ops.hash(data, len, seed); +} +EXPORT_SYMBOL_GPL(arch_fast_hash); + +u32 arch_fast_hash2(const u32 *data, u32 len, u32 seed) +{ + return arch_hash_ops.hash2(data, len, seed); +} +EXPORT_SYMBOL_GPL(arch_fast_hash2); + +static int __init hashlib_init(void) +{ + setup_arch_fast_hash(&arch_hash_ops); + return 0; +} +early_initcall(hashlib_init); -- cgit v1.3-14-g43fede From 481b5d938b4a60f052d7e15965a8417125e0d39f Mon Sep 17 00:00:00 2001 From: Sebastian Hesselbarth Date: Fri, 13 Dec 2013 10:20:27 +0100 Subject: net: phy: provide phy_resume/phy_suspend helpers This adds helper functions to resume and suspend a given phy_device by calling the corresponding driver callbacks if available. Signed-off-by: Sebastian Hesselbarth Acked-by: Mugunthan V N Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 24 ++++++++++++++++++++++++ include/linux/phy.h | 2 ++ 2 files changed, 26 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 5a619f0dcf73..91f17178f1b3 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -679,6 +679,30 @@ void phy_detach(struct phy_device *phydev) } EXPORT_SYMBOL(phy_detach); +int phy_suspend(struct phy_device *phydev) +{ + struct phy_driver *phydrv = to_phy_driver(phydev->dev.driver); + struct ethtool_wolinfo wol; + + /* If the device has WOL enabled, we cannot suspend the PHY */ + wol.cmd = ETHTOOL_GWOL; + phy_ethtool_get_wol(phydev, &wol); + if (wol.wolopts) + return -EBUSY; + + if (phydrv->suspend) + return phydrv->suspend(phydev); + return 0; +} + +int phy_resume(struct phy_device *phydev) +{ + struct phy_driver *phydrv = to_phy_driver(phydev->dev.driver); + + if (phydrv->resume) + return phydrv->resume(phydev); + return 0; +} /* Generic PHY support and helper functions */ diff --git a/include/linux/phy.h b/include/linux/phy.h index 90a666e0884b..73384ff3b5e5 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -548,6 +548,8 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id, struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); int phy_init_hw(struct phy_device *phydev); +int phy_suspend(struct phy_device *phydev); +int phy_resume(struct phy_device *phydev); struct phy_device * phy_attach(struct net_device *dev, const char *bus_id, phy_interface_t interface); struct phy_device *phy_find_first(struct mii_bus *bus); -- cgit v1.3-14-g43fede From 477bb93320cec7ae74d5ccfad4f2bfa0b28fbe90 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Fri, 13 Dec 2013 12:35:56 -0800 Subject: net: remove dead code for add/del multiple These function to manipulate multiple addresses are not used anywhere in current net-next tree. Some out of tree code maybe using these but too bad; they should submit their code upstream.. Also, make __hw_addr_flush local since only used by dev_addr_lists.c Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/netdevice.h | 11 ------ net/core/dev_addr_lists.c | 97 +---------------------------------------------- 2 files changed, 1 insertion(+), 107 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2c74d20dad34..a0dfcc8c002b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2810,17 +2810,10 @@ int register_netdev(struct net_device *dev); void unregister_netdev(struct net_device *dev); /* General hardware address lists handling functions */ -int __hw_addr_add_multiple(struct netdev_hw_addr_list *to_list, - struct netdev_hw_addr_list *from_list, - int addr_len, unsigned char addr_type); -void __hw_addr_del_multiple(struct netdev_hw_addr_list *to_list, - struct netdev_hw_addr_list *from_list, - int addr_len, unsigned char addr_type); int __hw_addr_sync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len); void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len); -void __hw_addr_flush(struct netdev_hw_addr_list *list); void __hw_addr_init(struct netdev_hw_addr_list *list); /* Functions used for device addresses handling */ @@ -2828,10 +2821,6 @@ int dev_addr_add(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); int dev_addr_del(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); -int dev_addr_add_multiple(struct net_device *to_dev, - struct net_device *from_dev, unsigned char addr_type); -int dev_addr_del_multiple(struct net_device *to_dev, - struct net_device *from_dev, unsigned char addr_type); void dev_addr_flush(struct net_device *dev); int dev_addr_init(struct net_device *dev); diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index ec40a849fc42..bb504a919e33 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -186,47 +186,6 @@ static int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list, return err; } -int __hw_addr_add_multiple(struct netdev_hw_addr_list *to_list, - struct netdev_hw_addr_list *from_list, - int addr_len, unsigned char addr_type) -{ - int err; - struct netdev_hw_addr *ha, *ha2; - unsigned char type; - - list_for_each_entry(ha, &from_list->list, list) { - type = addr_type ? addr_type : ha->type; - err = __hw_addr_add(to_list, ha->addr, addr_len, type); - if (err) - goto unroll; - } - return 0; - -unroll: - list_for_each_entry(ha2, &from_list->list, list) { - if (ha2 == ha) - break; - type = addr_type ? addr_type : ha2->type; - __hw_addr_del(to_list, ha2->addr, addr_len, type); - } - return err; -} -EXPORT_SYMBOL(__hw_addr_add_multiple); - -void __hw_addr_del_multiple(struct netdev_hw_addr_list *to_list, - struct netdev_hw_addr_list *from_list, - int addr_len, unsigned char addr_type) -{ - struct netdev_hw_addr *ha; - unsigned char type; - - list_for_each_entry(ha, &from_list->list, list) { - type = addr_type ? addr_type : ha->type; - __hw_addr_del(to_list, ha->addr, addr_len, type); - } -} -EXPORT_SYMBOL(__hw_addr_del_multiple); - /* This function only works where there is a strict 1-1 relationship * between source and destionation of they synch. If you ever need to * sync addresses to more then 1 destination, you need to use @@ -264,7 +223,7 @@ void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, } EXPORT_SYMBOL(__hw_addr_unsync); -void __hw_addr_flush(struct netdev_hw_addr_list *list) +static void __hw_addr_flush(struct netdev_hw_addr_list *list) { struct netdev_hw_addr *ha, *tmp; @@ -274,7 +233,6 @@ void __hw_addr_flush(struct netdev_hw_addr_list *list) } list->count = 0; } -EXPORT_SYMBOL(__hw_addr_flush); void __hw_addr_init(struct netdev_hw_addr_list *list) { @@ -400,59 +358,6 @@ int dev_addr_del(struct net_device *dev, const unsigned char *addr, } EXPORT_SYMBOL(dev_addr_del); -/** - * dev_addr_add_multiple - Add device addresses from another device - * @to_dev: device to which addresses will be added - * @from_dev: device from which addresses will be added - * @addr_type: address type - 0 means type will be used from from_dev - * - * Add device addresses of the one device to another. - ** - * The caller must hold the rtnl_mutex. - */ -int dev_addr_add_multiple(struct net_device *to_dev, - struct net_device *from_dev, - unsigned char addr_type) -{ - int err; - - ASSERT_RTNL(); - - if (from_dev->addr_len != to_dev->addr_len) - return -EINVAL; - err = __hw_addr_add_multiple(&to_dev->dev_addrs, &from_dev->dev_addrs, - to_dev->addr_len, addr_type); - if (!err) - call_netdevice_notifiers(NETDEV_CHANGEADDR, to_dev); - return err; -} -EXPORT_SYMBOL(dev_addr_add_multiple); - -/** - * dev_addr_del_multiple - Delete device addresses by another device - * @to_dev: device where the addresses will be deleted - * @from_dev: device supplying the addresses to be deleted - * @addr_type: address type - 0 means type will be used from from_dev - * - * Deletes addresses in to device by the list of addresses in from device. - * - * The caller must hold the rtnl_mutex. - */ -int dev_addr_del_multiple(struct net_device *to_dev, - struct net_device *from_dev, - unsigned char addr_type) -{ - ASSERT_RTNL(); - - if (from_dev->addr_len != to_dev->addr_len) - return -EINVAL; - __hw_addr_del_multiple(&to_dev->dev_addrs, &from_dev->dev_addrs, - to_dev->addr_len, addr_type); - call_netdevice_notifiers(NETDEV_CHANGEADDR, to_dev); - return 0; -} -EXPORT_SYMBOL(dev_addr_del_multiple); - /* * Unicast list handling functions */ -- cgit v1.3-14-g43fede From 3958afa1b272eb07109fd31549e69193b4d7c364 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Sun, 15 Dec 2013 22:12:06 -0800 Subject: net: Change skb_get_rxhash to skb_get_hash Changing name of function as part of making the hash in skbuff to be generic property, not just for receive path. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- drivers/net/macvtap.c | 2 +- drivers/net/tun.c | 4 ++-- drivers/net/vxlan.c | 2 +- include/linux/skbuff.h | 6 +++--- net/core/dev.c | 4 ++-- net/core/flow_dissector.c | 6 +++--- net/packet/af_packet.c | 4 ++-- net/sched/cls_flow.c | 2 +- net/sched/em_meta.c | 2 +- net/sched/sch_fq.c | 2 +- 10 files changed, 17 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 64409af0da31..431f58cb2ceb 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -224,7 +224,7 @@ static struct macvtap_queue *macvtap_get_queue(struct net_device *dev, goto out; /* Check if we can use flow to select a queue */ - rxq = skb_get_rxhash(skb); + rxq = skb_get_hash(skb); if (rxq) { tap = rcu_dereference(vlan->taps[rxq % numvtaps]); goto out; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 3c5a8d8cde50..8569da248336 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -358,7 +358,7 @@ static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb) rcu_read_lock(); numqueues = ACCESS_ONCE(tun->numqueues); - txq = skb_get_rxhash(skb); + txq = skb_get_hash(skb); if (txq) { e = tun_flow_find(&tun->flows[tun_hashfn(txq)], txq); if (e) @@ -1146,7 +1146,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, skb_reset_network_header(skb); skb_probe_transport_header(skb, 0); - rxhash = skb_get_rxhash(skb); + rxhash = skb_get_hash(skb); netif_rx_ni(skb); tun->dev->stats.rx_packets++; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 58f6a0c02b17..b247a7a29366 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1405,7 +1405,7 @@ __be16 vxlan_src_port(__u16 port_min, __u16 port_max, struct sk_buff *skb) unsigned int range = (port_max - port_min) + 1; u32 hash; - hash = skb_get_rxhash(skb); + hash = skb_get_hash(skb); if (!hash) hash = jhash(skb->data, 2 * ETH_ALEN, (__force u32) skb->protocol); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 77c7aae1c6b2..4725b953e00d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -703,11 +703,11 @@ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, unsigned int to, struct ts_config *config, struct ts_state *state); -void __skb_get_rxhash(struct sk_buff *skb); -static inline __u32 skb_get_rxhash(struct sk_buff *skb) +void __skb_get_hash(struct sk_buff *skb); +static inline __u32 skb_get_hash(struct sk_buff *skb) { if (!skb->l4_rxhash) - __skb_get_rxhash(skb); + __skb_get_hash(skb); return skb->rxhash; } diff --git a/net/core/dev.c b/net/core/dev.c index 9d4369ece679..c482fe8abf87 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3006,7 +3006,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, } skb_reset_network_header(skb); - if (!skb_get_rxhash(skb)) + if (!skb_get_hash(skb)) goto done; flow_table = rcu_dereference(rxqueue->rps_flow_table); @@ -3151,7 +3151,7 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen) rcu_read_lock(); fl = rcu_dereference(sd->flow_limit); if (fl) { - new_flow = skb_get_rxhash(skb) & (fl->num_buckets - 1); + new_flow = skb_get_hash(skb) & (fl->num_buckets - 1); old_flow = fl->history[fl->history_head]; fl->history[fl->history_head] = new_flow; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index d6ef17322500..b324bfa3485c 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -202,12 +202,12 @@ static __always_inline u32 __flow_hash_1word(u32 a) } /* - * __skb_get_rxhash: calculate a flow hash based on src/dst addresses + * __skb_get_hash: calculate a flow hash based on src/dst addresses * and src/dst port numbers. Sets rxhash in skb to non-zero hash value * on success, zero indicates no valid hash. Also, sets l4_rxhash in skb * if hash is a canonical 4-tuple hash over transport ports. */ -void __skb_get_rxhash(struct sk_buff *skb) +void __skb_get_hash(struct sk_buff *skb) { struct flow_keys keys; u32 hash; @@ -234,7 +234,7 @@ void __skb_get_rxhash(struct sk_buff *skb) skb->rxhash = hash; } -EXPORT_SYMBOL(__skb_get_rxhash); +EXPORT_SYMBOL(__skb_get_hash); /* * Returns a Tx hash based on the given packet descriptor a Tx queues' number diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index cc803c63059a..24675f06f4fd 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -963,7 +963,7 @@ static void prb_clear_blk_fill_status(struct packet_ring_buffer *rb) static void prb_fill_rxhash(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { - ppd->hv1.tp_rxhash = skb_get_rxhash(pkc->skb); + ppd->hv1.tp_rxhash = skb_get_hash(pkc->skb); } static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc, @@ -1295,7 +1295,7 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev, if (!skb) return 0; } - skb_get_rxhash(skb); + skb_get_hash(skb); idx = fanout_demux_hash(f, skb, num); break; case PACKET_FANOUT_LB: diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 7881e2fccbc2..83a6322b7751 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -220,7 +220,7 @@ static u32 flow_get_vlan_tag(const struct sk_buff *skb) static u32 flow_get_rxhash(struct sk_buff *skb) { - return skb_get_rxhash(skb); + return skb_get_hash(skb); } static u32 flow_key_get(struct sk_buff *skb, int key, struct flow_keys *flow) diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index 382519a5d7f9..9b8c0b0e60d7 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -222,7 +222,7 @@ META_COLLECTOR(int_maclen) META_COLLECTOR(int_rxhash) { - dst->value = skb_get_rxhash(skb); + dst->value = skb_get_hash(skb); } /************************************************************************** diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index f2fb92dd970d..08ef7a42c0e4 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -226,7 +226,7 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) /* By forcing low order bit to 1, we make sure to not * collide with a local flow (socket pointers are word aligned) */ - sk = (struct sock *)(skb_get_rxhash(skb) | 1L); + sk = (struct sock *)(skb_get_hash(skb) | 1L); } root = &q->fq_root[hash_32((u32)(long)sk, q->fq_trees_log)]; -- cgit v1.3-14-g43fede From 7539fadcb8146a5f0db51e80d99c9e724efec7b0 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Sun, 15 Dec 2013 22:12:18 -0800 Subject: net: Add utility functions to clear rxhash In several places 'skb->rxhash = 0' is being done to clear the rxhash value in an skb. This does not clear l4_rxhash which could still be set so that the rxhash wouldn't be recalculated on subsequent call to skb_get_rxhash. This patch adds an explict function to clear all the rxhash related information in the skb properly. skb_clear_hash_if_not_l4 clears the rxhash only if it is not marked as l4_rxhash. Fixed up places where 'skb->rxhash = 0' was being called. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/skbuff.h | 12 ++++++++++++ include/net/dst.h | 5 ++--- net/ipv4/ip_fragment.c | 2 +- net/ipv4/ip_tunnel_core.c | 5 ++--- net/openvswitch/actions.c | 10 +++++----- 5 files changed, 22 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4725b953e00d..7deb7ad65914 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -712,6 +712,18 @@ static inline __u32 skb_get_hash(struct sk_buff *skb) return skb->rxhash; } +static inline void skb_clear_hash(struct sk_buff *skb) +{ + skb->rxhash = 0; + skb->l4_rxhash = 0; +} + +static inline void skb_clear_hash_if_not_l4(struct sk_buff *skb) +{ + if (!skb->l4_rxhash) + skb_clear_hash(skb); +} + #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { diff --git a/include/net/dst.h b/include/net/dst.h index 44995c13e941..77eb53fabfb0 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -322,12 +322,11 @@ static inline void __skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, skb->dev = dev; /* - * Clear rxhash so that we can recalulate the hash for the + * Clear hash so that we can recalulate the hash for the * encapsulated packet, unless we have already determine the hash * over the L4 4-tuple. */ - if (!skb->l4_rxhash) - skb->rxhash = 0; + skb_clear_hash_if_not_l4(skb); skb_set_queue_mapping(skb, 0); skb_scrub_packet(skb, !net_eq(net, dev_net(dev))); } diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 2481993a4970..c10a3ce5cbff 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -704,7 +704,7 @@ struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user) memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); if (ip_defrag(skb, user)) return NULL; - skb->rxhash = 0; + skb_clear_hash(skb); } } return skb; diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 42ffbc8d65c6..6156f4ef5e91 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -56,7 +56,7 @@ int iptunnel_xmit(struct rtable *rt, struct sk_buff *skb, skb_scrub_packet(skb, xnet); - skb->rxhash = 0; + skb_clear_hash(skb); skb_dst_set(skb, &rt->dst); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); @@ -107,8 +107,7 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto) nf_reset(skb); secpath_reset(skb); - if (!skb->l4_rxhash) - skb->rxhash = 0; + skb_clear_hash_if_not_l4(skb); skb_dst_drop(skb); skb->vlan_tci = 0; skb_set_queue_mapping(skb, 0); diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 65cfaa816075..716b7eebfe70 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -165,7 +165,7 @@ static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh, } csum_replace4(&nh->check, *addr, new_addr); - skb->rxhash = 0; + skb_clear_hash(skb); *addr = new_addr; } @@ -199,7 +199,7 @@ static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto, if (recalculate_csum) update_ipv6_checksum(skb, l4_proto, addr, new_addr); - skb->rxhash = 0; + skb_clear_hash(skb); memcpy(addr, new_addr, sizeof(__be32[4])); } @@ -296,7 +296,7 @@ static void set_tp_port(struct sk_buff *skb, __be16 *port, { inet_proto_csum_replace2(check, skb, *port, new_port, 0); *port = new_port; - skb->rxhash = 0; + skb_clear_hash(skb); } static void set_udp_port(struct sk_buff *skb, __be16 *port, __be16 new_port) @@ -310,7 +310,7 @@ static void set_udp_port(struct sk_buff *skb, __be16 *port, __be16 new_port) uh->check = CSUM_MANGLED_0; } else { *port = new_port; - skb->rxhash = 0; + skb_clear_hash(skb); } } @@ -381,7 +381,7 @@ static int set_sctp(struct sk_buff *skb, /* Carry any checksum errors through. */ sh->checksum = old_csum ^ old_correct_csum ^ new_csum; - skb->rxhash = 0; + skb_clear_hash(skb); } return 0; -- cgit v1.3-14-g43fede From 09323cc479316e046931a2c679932204b36fea6c Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Sun, 15 Dec 2013 22:16:19 -0800 Subject: net: Add function to set the rxhash The function skb_set_rxash was added for drivers to call to set the rxhash in an skb. The type of hash is also specified as a parameter (L2, L3, L4, or unknown type). Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/skbuff.h | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7deb7ad65914..99846956dff9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -703,6 +703,46 @@ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, unsigned int to, struct ts_config *config, struct ts_state *state); +/* + * Packet hash types specify the type of hash in skb_set_hash. + * + * Hash types refer to the protocol layer addresses which are used to + * construct a packet's hash. The hashes are used to differentiate or identify + * flows of the protocol layer for the hash type. Hash types are either + * layer-2 (L2), layer-3 (L3), or layer-4 (L4). + * + * Properties of hashes: + * + * 1) Two packets in different flows have different hash values + * 2) Two packets in the same flow should have the same hash value + * + * A hash at a higher layer is considered to be more specific. A driver should + * set the most specific hash possible. + * + * A driver cannot indicate a more specific hash than the layer at which a hash + * was computed. For instance an L3 hash cannot be set as an L4 hash. + * + * A driver may indicate a hash level which is less specific than the + * actual layer the hash was computed on. For instance, a hash computed + * at L4 may be considered an L3 hash. This should only be done if the + * driver can't unambiguously determine that the HW computed the hash at + * the higher layer. Note that the "should" in the second property above + * permits this. + */ +enum pkt_hash_types { + PKT_HASH_TYPE_NONE, /* Undefined type */ + PKT_HASH_TYPE_L2, /* Input: src_MAC, dest_MAC */ + PKT_HASH_TYPE_L3, /* Input: src_IP, dst_IP */ + PKT_HASH_TYPE_L4, /* Input: src_IP, dst_IP, src_port, dst_port */ +}; + +static inline void +skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type) +{ + skb->l4_rxhash = (type == PKT_HASH_TYPE_L4); + skb->rxhash = hash; +} + void __skb_get_hash(struct sk_buff *skb); static inline __u32 skb_get_hash(struct sk_buff *skb) { -- cgit v1.3-14-g43fede From 3df7a74e797aa2d8be9b7c649cfd56a8517dcf6e Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Sun, 15 Dec 2013 22:16:29 -0800 Subject: net: Add utility function to copy skb hash Adds skb_copy_hash to copy rxhash and l4_rxhash from one skb to another. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 ++++++ net/core/skbuff.c | 3 +-- 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 99846956dff9..06bedeb0d49e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -764,6 +764,12 @@ static inline void skb_clear_hash_if_not_l4(struct sk_buff *skb) skb_clear_hash(skb); } +static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) +{ + to->rxhash = from->rxhash; + to->l4_rxhash = from->l4_rxhash; +}; + #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 06e72d3cdf60..2b6b863f51f2 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -712,9 +712,8 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->inner_network_header = old->inner_network_header; new->inner_mac_header = old->inner_mac_header; skb_dst_copy(new, old); - new->rxhash = old->rxhash; + skb_copy_hash(new, old); new->ooo_okay = old->ooo_okay; - new->l4_rxhash = old->l4_rxhash; new->no_fcs = old->no_fcs; new->encapsulation = old->encapsulation; #ifdef CONFIG_XFRM -- cgit v1.3-14-g43fede From 93b36cf3425b9bd9c56df7680fb237686b9c82ae Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Sun, 15 Dec 2013 03:41:14 +0100 Subject: ipv6: support IPV6_PMTU_INTERFACE on sockets IPV6_PMTU_INTERFACE is the same as IPV6_PMTU_PROBE for ipv6. Add it nontheless for symmetry with IPv4 sockets. Also drop incoming MTU information if this mode is enabled. The additional bit in ipv6_pinfo just eats in the padding behind the bitfield. There are no changes to the layout of the struct at all. Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/linux/ipv6.h | 2 +- include/net/ip6_route.h | 7 ++++++- include/uapi/linux/in6.h | 4 ++++ net/dccp/ipv6.c | 3 +++ net/ipv6/ip6_output.c | 6 +++--- net/ipv6/ipv6_sockglue.c | 2 +- net/ipv6/tcp_ipv6.c | 3 +++ net/ipv6/udp.c | 5 ++++- net/sctp/input.c | 3 +++ 9 files changed, 28 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 3fde06645553..7e1ded0d8e45 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -191,7 +191,7 @@ struct ipv6_pinfo { /* sockopt flags */ __u16 recverr:1, sndflow:1, - pmtudisc:2, + pmtudisc:3, ipv6only:1, srcprefs:3, /* 001: prefer temporary address * 010: prefer public address diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 733747ce163c..c2626ce1f2ad 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -178,10 +178,15 @@ static inline int ip6_skb_dst_mtu(struct sk_buff *skb) { struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL; - return (np && np->pmtudisc == IPV6_PMTUDISC_PROBE) ? + return (np && np->pmtudisc >= IPV6_PMTUDISC_PROBE) ? skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb)); } +static inline bool ip6_sk_accept_pmtu(const struct sock *sk) +{ + return inet6_sk(sk)->pmtudisc != IPV6_PMTUDISC_INTERFACE; +} + static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt) { return &rt->rt6i_gateway; diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h index 440d5c479145..f94f1d013bf2 100644 --- a/include/uapi/linux/in6.h +++ b/include/uapi/linux/in6.h @@ -188,6 +188,10 @@ enum { #define IPV6_PMTUDISC_WANT 1 #define IPV6_PMTUDISC_DO 2 #define IPV6_PMTUDISC_PROBE 3 +/* same as IPV6_PMTUDISC_PROBE, provided for symetry with IPv4 + * also see comments on IP_PMTUDISC_INTERFACE + */ +#define IPV6_PMTUDISC_INTERFACE 4 /* Flowlabel */ #define IPV6_FLOWLABEL_MGR 32 diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 2b90a786e475..629019e6f8e9 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -141,6 +141,9 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (type == ICMPV6_PKT_TOOBIG) { struct dst_entry *dst = NULL; + if (!ip6_sk_accept_pmtu(sk)) + goto out; + if (sock_owned_by_user(sk)) goto out; if ((1 << sk->sk_state) & (DCCPF_LISTEN | DCCPF_CLOSED)) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 9a311cc79672..bc4e1bcdf4c0 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1165,10 +1165,10 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, np->cork.hop_limit = hlimit; np->cork.tclass = tclass; if (rt->dst.flags & DST_XFRM_TUNNEL) - mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ? + mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ? rt->dst.dev->mtu : dst_mtu(&rt->dst); else - mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ? + mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ? rt->dst.dev->mtu : dst_mtu(rt->dst.path); if (np->frag_size < mtu) { if (np->frag_size) @@ -1270,7 +1270,7 @@ alloc_new_skb: if (skb == NULL || skb_prev == NULL) ip6_append_data_mtu(&mtu, &maxfraglen, fragheaderlen, skb, rt, - np->pmtudisc == + np->pmtudisc >= IPV6_PMTUDISC_PROBE); skb_prev = skb; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 759fbf96515b..af0ecb94b3b4 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -722,7 +722,7 @@ done: case IPV6_MTU_DISCOVER: if (optlen < sizeof(int)) goto e_inval; - if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_PROBE) + if (val < IPV6_PMTUDISC_DONT || val > IPV6_PMTUDISC_INTERFACE) goto e_inval; np->pmtudisc = val; retv = 0; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index da046a5d7ffb..d955487f2c54 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -397,6 +397,9 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (sk->sk_state == TCP_LISTEN) goto out; + if (!ip6_sk_accept_pmtu(sk)) + goto out; + tp->mtu_info = ntohl(info); if (!sock_owned_by_user(sk)) tcp_v6_mtu_reduced(sk); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 089c741a3992..65ed5cd79264 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -538,8 +538,11 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (sk == NULL) return; - if (type == ICMPV6_PKT_TOOBIG) + if (type == ICMPV6_PKT_TOOBIG) { + if (!ip6_sk_accept_pmtu(sk)) + goto out; ip6_sk_update_pmtu(skb, sk, info); + } if (type == NDISC_REDIRECT) { ip6_sk_redirect(skb, sk); goto out; diff --git a/net/sctp/input.c b/net/sctp/input.c index 2a192a7c5d81..042ec6c9ae24 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -389,6 +389,9 @@ void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc, if (!t || (t->pathmtu <= pmtu)) return; + if (!ip6_sk_accept_pmtu(sk)) + return; + if (sock_owned_by_user(sk)) { asoc->pmtu_pending = 1; t->pmtu_pending = 1; -- cgit v1.3-14-g43fede From 78ea85f17b15390e30d8b47488ec7b6cf0790663 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 16 Dec 2013 23:27:09 +0100 Subject: net: skbuff: improve comment on checksumming It can be a bit confusing when looking for checksumming flags that the actual comment for this resides elsewhere further below in the header file. Thus, bring the documentation where we define these flags, and slightly improve the doc text to make it a bit more clear/readable. Also, whitespace-align values of the define while at it. Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/skbuff.h | 131 ++++++++++++++++++++++++++++--------------------- 1 file changed, 75 insertions(+), 56 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 06bedeb0d49e..c5cd016f5120 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -34,11 +34,82 @@ #include #include +/* A. Checksumming of received packets by device. + * + * CHECKSUM_NONE: + * + * Device failed to checksum this packet e.g. due to lack of capabilities. + * The packet contains full (though not verified) checksum in packet but + * not in skb->csum. Thus, skb->csum is undefined in this case. + * + * CHECKSUM_UNNECESSARY: + * + * The hardware you're dealing with doesn't calculate the full checksum + * (as in CHECKSUM_COMPLETE), but it does parse headers and verify checksums + * for specific protocols e.g. TCP/UDP/SCTP, then, for such packets it will + * set CHECKSUM_UNNECESSARY if their checksums are okay. skb->csum is still + * undefined in this case though. It is a bad option, but, unfortunately, + * nowadays most vendors do this. Apparently with the secret goal to sell + * you new devices, when you will add new protocol to your host, f.e. IPv6 8) + * + * CHECKSUM_COMPLETE: + * + * This is the most generic way. The device supplied checksum of the _whole_ + * packet as seen by netif_rx() and fills out in skb->csum. Meaning, the + * hardware doesn't need to parse L3/L4 headers to implement this. + * + * Note: Even if device supports only some protocols, but is able to produce + * skb->csum, it MUST use CHECKSUM_COMPLETE, not CHECKSUM_UNNECESSARY. + * + * CHECKSUM_PARTIAL: + * + * This is identical to the case for output below. This may occur on a packet + * received directly from another Linux OS, e.g., a virtualized Linux kernel + * on the same host. The packet can be treated in the same way as + * CHECKSUM_UNNECESSARY, except that on output (i.e., forwarding) the + * checksum must be filled in by the OS or the hardware. + * + * B. Checksumming on output. + * + * CHECKSUM_NONE: + * + * The skb was already checksummed by the protocol, or a checksum is not + * required. + * + * CHECKSUM_PARTIAL: + * + * The device is required to checksum the packet as seen by hard_start_xmit() + * from skb->csum_start up to the end, and to record/write the checksum at + * offset skb->csum_start + skb->csum_offset. + * + * The device must show its capabilities in dev->features, set up at device + * setup time, e.g. netdev_features.h: + * + * NETIF_F_HW_CSUM - It's a clever device, it's able to checksum everything. + * NETIF_F_IP_CSUM - Device is dumb, it's able to checksum only TCP/UDP over + * IPv4. Sigh. Vendors like this way for an unknown reason. + * Though, see comment above about CHECKSUM_UNNECESSARY. 8) + * NETIF_F_IPV6_CSUM - About as dumb as the last one but does IPv6 instead. + * NETIF_F_... - Well, you get the picture. + * + * CHECKSUM_UNNECESSARY: + * + * Normally, the device will do per protocol specific checksumming. Protocol + * implementations that do not want the NIC to perform the checksum + * calculation should use this flag in their outgoing skbs. + * + * NETIF_F_FCOE_CRC - This indicates that the device can do FCoE FC CRC + * offload. Correspondingly, the FCoE protocol driver + * stack should use CHECKSUM_UNNECESSARY. + * + * Any questions? No questions, good. --ANK + */ + /* Don't change this without changing skb_csum_unnecessary! */ -#define CHECKSUM_NONE 0 -#define CHECKSUM_UNNECESSARY 1 -#define CHECKSUM_COMPLETE 2 -#define CHECKSUM_PARTIAL 3 +#define CHECKSUM_NONE 0 +#define CHECKSUM_UNNECESSARY 1 +#define CHECKSUM_COMPLETE 2 +#define CHECKSUM_PARTIAL 3 #define SKB_DATA_ALIGN(X) (((X) + (SMP_CACHE_BYTES - 1)) & \ ~(SMP_CACHE_BYTES - 1)) @@ -54,58 +125,6 @@ SKB_DATA_ALIGN(sizeof(struct sk_buff)) + \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) -/* A. Checksumming of received packets by device. - * - * NONE: device failed to checksum this packet. - * skb->csum is undefined. - * - * UNNECESSARY: device parsed packet and wouldbe verified checksum. - * skb->csum is undefined. - * It is bad option, but, unfortunately, many of vendors do this. - * Apparently with secret goal to sell you new device, when you - * will add new protocol to your host. F.e. IPv6. 8) - * - * COMPLETE: the most generic way. Device supplied checksum of _all_ - * the packet as seen by netif_rx in skb->csum. - * NOTE: Even if device supports only some protocols, but - * is able to produce some skb->csum, it MUST use COMPLETE, - * not UNNECESSARY. - * - * PARTIAL: identical to the case for output below. This may occur - * on a packet received directly from another Linux OS, e.g., - * a virtualised Linux kernel on the same host. The packet can - * be treated in the same way as UNNECESSARY except that on - * output (i.e., forwarding) the checksum must be filled in - * by the OS or the hardware. - * - * B. Checksumming on output. - * - * NONE: skb is checksummed by protocol or csum is not required. - * - * PARTIAL: device is required to csum packet as seen by hard_start_xmit - * from skb->csum_start to the end and to record the checksum - * at skb->csum_start + skb->csum_offset. - * - * Device must show its capabilities in dev->features, set - * at device setup time. - * NETIF_F_HW_CSUM - it is clever device, it is able to checksum - * everything. - * NETIF_F_IP_CSUM - device is dumb. It is able to csum only - * TCP/UDP over IPv4. Sigh. Vendors like this - * way by an unknown reason. Though, see comment above - * about CHECKSUM_UNNECESSARY. 8) - * NETIF_F_IPV6_CSUM about as dumb as the last one but does IPv6 instead. - * - * UNNECESSARY: device will do per protocol specific csum. Protocol drivers - * that do not want net to perform the checksum calculation should use - * this flag in their outgoing skbs. - * NETIF_F_FCOE_CRC this indicates the device can do FCoE FC CRC - * offload. Correspondingly, the FCoE protocol driver - * stack should use CHECKSUM_UNNECESSARY. - * - * Any questions? No questions, good. --ANK - */ - struct net_device; struct scatterlist; struct pipe_inode_info; -- cgit v1.3-14-g43fede From 8e1a28e8e6797449dfdfa4739002d1e5939355a8 Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Thu, 19 Dec 2013 21:20:12 +0200 Subject: net/mlx4_core: Expose physical port id as PF/VF capability Add the infrastructure needed to support ndo_get_phys_port_id which allows users to identify to which physical port a net-device is connected to by reading a unique port id. This will work for VFs and PFs. The driver uses a new device capability - phys_port_id, The PF driver reads the port phys_port_id from Firmware and stores it. The VF driver reads the port phys_port_id from the PF using QUERY_FUNC_CAP command. Signed-off-by: Hadar Hen Zion Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/fw.c | 45 +++++++++++++++++++++++++++++++ drivers/net/ethernet/mellanox/mlx4/fw.h | 1 + drivers/net/ethernet/mellanox/mlx4/main.c | 5 ++++ include/linux/mlx4/device.h | 2 ++ 4 files changed, 53 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index bfe91aebea8e..27a84342525f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -214,6 +214,7 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave, #define QUERY_FUNC_CAP_QP0_PROXY 0x14 #define QUERY_FUNC_CAP_QP1_TUNNEL 0x18 #define QUERY_FUNC_CAP_QP1_PROXY 0x1c +#define QUERY_FUNC_CAP_PHYS_PORT_ID 0x28 #define QUERY_FUNC_CAP_FLAGS1_FORCE_MAC 0x40 #define QUERY_FUNC_CAP_FLAGS1_FORCE_VLAN 0x80 @@ -242,6 +243,9 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave, size += 2; MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_QP1_PROXY); + MLX4_PUT(outbox->buf, dev->caps.phys_port_id[vhcr->in_modifier], + QUERY_FUNC_CAP_PHYS_PORT_ID); + } else if (vhcr->op_modifier == 0) { /* enable rdma and ethernet interfaces, and new quota locations */ field = (QUERY_FUNC_CAP_FLAG_ETH | QUERY_FUNC_CAP_FLAG_RDMA | @@ -432,6 +436,10 @@ int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, u32 gen_or_port, MLX4_GET(size, outbox, QUERY_FUNC_CAP_QP1_PROXY); func_cap->qp1_proxy_qpn = size & 0xFFFFFF; + if (func_cap->flags1 & QUERY_FUNC_CAP_FLAGS1_NIC_INFO) + MLX4_GET(func_cap->phys_port_id, outbox, + QUERY_FUNC_CAP_PHYS_PORT_ID); + /* All other resources are allocated by the master, but we still report * 'num' and 'reserved' capabilities as follows: * - num remains the maximum resource index @@ -1712,6 +1720,43 @@ int mlx4_NOP(struct mlx4_dev *dev) return mlx4_cmd(dev, 0, 0x1f, 0, MLX4_CMD_NOP, 100, MLX4_CMD_NATIVE); } +int mlx4_get_phys_port_id(struct mlx4_dev *dev) +{ + u8 port; + u32 *outbox; + struct mlx4_cmd_mailbox *mailbox; + u32 in_mod; + u32 guid_hi, guid_lo; + int err, ret = 0; +#define MOD_STAT_CFG_PORT_OFFSET 8 +#define MOD_STAT_CFG_GUID_H 0X14 +#define MOD_STAT_CFG_GUID_L 0X1c + + mailbox = mlx4_alloc_cmd_mailbox(dev); + if (IS_ERR(mailbox)) + return PTR_ERR(mailbox); + outbox = mailbox->buf; + + for (port = 1; port <= dev->caps.num_ports; port++) { + in_mod = port << MOD_STAT_CFG_PORT_OFFSET; + err = mlx4_cmd_box(dev, 0, mailbox->dma, in_mod, 0x2, + MLX4_CMD_MOD_STAT_CFG, MLX4_CMD_TIME_CLASS_A, + MLX4_CMD_NATIVE); + if (err) { + mlx4_err(dev, "Fail to get port %d uplink guid\n", + port); + ret = err; + } else { + MLX4_GET(guid_hi, outbox, MOD_STAT_CFG_GUID_H); + MLX4_GET(guid_lo, outbox, MOD_STAT_CFG_GUID_L); + dev->caps.phys_port_id[port] = (u64)guid_lo | + (u64)guid_hi << 32; + } + } + mlx4_free_cmd_mailbox(dev, mailbox); + return ret; +} + #define MLX4_WOL_SETUP_MODE (5 << 28) int mlx4_wol_read(struct mlx4_dev *dev, u64 *config, int port) { diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h index 9d952983b076..6811ee00ba7c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.h +++ b/drivers/net/ethernet/mellanox/mlx4/fw.h @@ -141,6 +141,7 @@ struct mlx4_func_cap { u8 physical_port; u8 port_flags; u8 flags1; + u64 phys_port_id; }; struct mlx4_adapter { diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index b37478db9851..6b13a15b3306 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -606,6 +606,7 @@ static int mlx4_slave_cap(struct mlx4_dev *dev) dev->caps.qp1_tunnel[i - 1] = func_cap.qp1_tunnel_qpn; dev->caps.qp1_proxy[i - 1] = func_cap.qp1_proxy_qpn; dev->caps.port_mask[i] = dev->caps.port_type[i]; + dev->caps.phys_port_id[i] = func_cap.phys_port_id; if (mlx4_get_slave_pkey_gid_tbl_len(dev, i, &dev->caps.gid_table_len[i], &dev->caps.pkey_table_len[i])) @@ -1484,6 +1485,10 @@ static int mlx4_init_hca(struct mlx4_dev *dev) choose_steering_mode(dev, &dev_cap); + err = mlx4_get_phys_port_id(dev); + if (err) + mlx4_err(dev, "Fail to get physical port id\n"); + if (mlx4_is_master(dev)) mlx4_parav_master_pf_caps(dev); diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 7d3a523160ba..294b7c58fe95 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -454,6 +454,7 @@ struct mlx4_caps { u32 userspace_caps; /* userspace must be aware of these */ u32 function_caps; /* VFs must be aware of these */ u16 hca_core_clock; + u64 phys_port_id[MLX4_MAX_PORTS + 1]; }; struct mlx4_buf_list { @@ -1113,6 +1114,7 @@ int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap, int *vector); void mlx4_release_eq(struct mlx4_dev *dev, int vec); +int mlx4_get_phys_port_id(struct mlx4_dev *dev); int mlx4_wol_read(struct mlx4_dev *dev, u64 *config, int port); int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port); -- cgit v1.3-14-g43fede From 18be099badcfc4a12f058addc55c4270d5a8bec8 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Fri, 20 Dec 2013 01:39:52 +0300 Subject: sh_eth: add PHY IRQ to platform data Allow the platform code to pass PHY's IRQ to the driver. Print this IRQ along with the other PHY datails in sh_eth_phy_init(). Signed-off-by: Sergei Shtylyov Signed-off-by: David S. Miller --- drivers/net/ethernet/renesas/sh_eth.c | 6 ++++-- include/linux/sh_eth.h | 1 + 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 8601d0c638cc..9d8013f82019 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -1685,8 +1685,8 @@ static int sh_eth_phy_init(struct net_device *ndev) return PTR_ERR(phydev); } - dev_info(&ndev->dev, "attached phy %i to driver %s\n", - phydev->addr, phydev->drv->name); + dev_info(&ndev->dev, "attached PHY %d (IRQ %d) to driver %s\n", + phydev->addr, phydev->irq, phydev->drv->name); mdp->phydev = phydev; @@ -2544,6 +2544,8 @@ static int sh_mdio_init(struct net_device *ndev, int id, for (i = 0; i < PHY_MAX_ADDR; i++) mdp->mii_bus->irq[i] = PHY_POLL; + if (pd->phy_irq > 0) + mdp->mii_bus->irq[pd->phy] = pd->phy_irq; /* register mdio bus */ ret = mdiobus_register(mdp->mii_bus); diff --git a/include/linux/sh_eth.h b/include/linux/sh_eth.h index 90b5e30c2f22..8c9131db2b25 100644 --- a/include/linux/sh_eth.h +++ b/include/linux/sh_eth.h @@ -8,6 +8,7 @@ enum {EDMAC_LITTLE_ENDIAN, EDMAC_BIG_ENDIAN}; struct sh_eth_plat_data { int phy; + int phy_irq; int edmac_endian; phy_interface_t phy_interface; void (*set_mdio_gate)(void *addr); -- cgit v1.3-14-g43fede From 652a4a53fce4b50e4cfa92055deefadc3a3627fa Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Thu, 26 Dec 2013 10:12:41 -0800 Subject: mdio: unused ethtool functions Use it or lose it. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- drivers/net/mdio.c | 28 ---------------------------- include/linux/mdio.h | 3 --- 2 files changed, 31 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/mdio.c b/drivers/net/mdio.c index 8403316eb02b..3e027ed0b3bb 100644 --- a/drivers/net/mdio.c +++ b/drivers/net/mdio.c @@ -341,34 +341,6 @@ void mdio45_ethtool_gset_npage(const struct mdio_if_info *mdio, } EXPORT_SYMBOL(mdio45_ethtool_gset_npage); -/** - * mdio45_ethtool_spauseparam_an - set auto-negotiated pause parameters - * @mdio: MDIO interface - * @ecmd: Ethtool request structure - * - * This function assumes that the PHY has an auto-negotiation MMD. It - * will enable and disable advertising of flow control as appropriate. - */ -void mdio45_ethtool_spauseparam_an(const struct mdio_if_info *mdio, - const struct ethtool_pauseparam *ecmd) -{ - int adv, old_adv; - - WARN_ON(!(mdio->mmds & MDIO_DEVS_AN)); - - old_adv = mdio->mdio_read(mdio->dev, mdio->prtad, MDIO_MMD_AN, - MDIO_AN_ADVERTISE); - adv = ((old_adv & ~(ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM)) | - mii_advertise_flowctrl((ecmd->rx_pause ? FLOW_CTRL_RX : 0) | - (ecmd->tx_pause ? FLOW_CTRL_TX : 0))); - if (adv != old_adv) { - mdio->mdio_write(mdio->dev, mdio->prtad, MDIO_MMD_AN, - MDIO_AN_ADVERTISE, adv); - mdio45_nway_restart(mdio); - } -} -EXPORT_SYMBOL(mdio45_ethtool_spauseparam_an); - /** * mdio_mii_ioctl - MII ioctl interface for MDIO (clause 22 or 45) PHYs * @mdio: MDIO interface diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 3d15c838116c..b42963bc81dd 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -70,9 +70,6 @@ extern int mdio45_nway_restart(const struct mdio_if_info *mdio); extern void mdio45_ethtool_gset_npage(const struct mdio_if_info *mdio, struct ethtool_cmd *ecmd, u32 npage_adv, u32 npage_lpa); -extern void -mdio45_ethtool_spauseparam_an(const struct mdio_if_info *mdio, - const struct ethtool_pauseparam *ecmd); /** * mdio45_ethtool_gset - get settings for ETHTOOL_GSET -- cgit v1.3-14-g43fede From 0db901bd33f09b0dbf39d12261f689812e343c26 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Fri, 27 Dec 2013 12:06:46 -0800 Subject: macvlan: make start_xmit local Only used in one file, no need to expose Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- drivers/net/macvlan.c | 5 ++--- include/linux/if_macvlan.h | 3 --- 2 files changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 24ea994b6274..10406dbc35b3 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -290,8 +290,8 @@ xmit_world: return dev_queue_xmit(skb); } -netdev_tx_t macvlan_start_xmit(struct sk_buff *skb, - struct net_device *dev) +static netdev_tx_t macvlan_start_xmit(struct sk_buff *skb, + struct net_device *dev) { unsigned int len = skb->len; int ret; @@ -317,7 +317,6 @@ netdev_tx_t macvlan_start_xmit(struct sk_buff *skb, } return ret; } -EXPORT_SYMBOL_GPL(macvlan_start_xmit); static int macvlan_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index ea22721ba269..551bdd3722a2 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -111,9 +111,6 @@ extern void macvlan_dellink(struct net_device *dev, struct list_head *head); extern int macvlan_link_register(struct rtnl_link_ops *ops); -extern netdev_tx_t macvlan_start_xmit(struct sk_buff *skb, - struct net_device *dev); - #if IS_ENABLED(CONFIG_MACVLAN) static inline struct net_device * macvlan_dev_real_dev(const struct net_device *dev) -- cgit v1.3-14-g43fede From 24245a1b055df246dc94517c1a8b1fdfe7668da0 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Sun, 29 Dec 2013 11:43:35 -0800 Subject: lro: remove dead code Remove leftover code that is not used anywhere in current tree. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/inet_lro.h | 23 ------- net/ipv4/inet_lro.c | 173 ----------------------------------------------- 2 files changed, 196 deletions(-) (limited to 'include/linux') diff --git a/include/linux/inet_lro.h b/include/linux/inet_lro.h index 2cf55afbcd4e..9a715cfa1fe3 100644 --- a/include/linux/inet_lro.h +++ b/include/linux/inet_lro.h @@ -133,33 +133,10 @@ struct net_lro_mgr { void lro_receive_skb(struct net_lro_mgr *lro_mgr, struct sk_buff *skb, void *priv); - -/* - * Processes a fragment list - * - * This functions aggregate fragments and generate SKBs do pass - * the packets to the stack. - * - * @lro_mgr: LRO manager to use - * @frags: Fragment to be processed. Must contain entire header in first - * element. - * @len: Length of received data - * @true_size: Actual size of memory the fragment is consuming - * @priv: Private data that may be used by driver functions - * (for example get_tcp_ip_hdr) - */ - -void lro_receive_frags(struct net_lro_mgr *lro_mgr, - struct skb_frag_struct *frags, - int len, int true_size, void *priv, __wsum sum); - /* * Forward all aggregated SKBs held by lro_mgr to network stack */ void lro_flush_all(struct net_lro_mgr *lro_mgr); -void lro_flush_pkt(struct net_lro_mgr *lro_mgr, - struct iphdr *iph, struct tcphdr *tcph); - #endif diff --git a/net/ipv4/inet_lro.c b/net/ipv4/inet_lro.c index 1975f52933c5..f17ea49b28fb 100644 --- a/net/ipv4/inet_lro.c +++ b/net/ipv4/inet_lro.c @@ -230,29 +230,6 @@ static void lro_add_packet(struct net_lro_desc *lro_desc, struct sk_buff *skb, lro_desc->last_skb = skb; } -static void lro_add_frags(struct net_lro_desc *lro_desc, - int len, int hlen, int truesize, - struct skb_frag_struct *skb_frags, - struct iphdr *iph, struct tcphdr *tcph) -{ - struct sk_buff *skb = lro_desc->parent; - int tcp_data_len = TCP_PAYLOAD_LENGTH(iph, tcph); - - lro_add_common(lro_desc, iph, tcph, tcp_data_len); - - skb->truesize += truesize; - - skb_frags[0].page_offset += hlen; - skb_frag_size_sub(&skb_frags[0], hlen); - - while (tcp_data_len > 0) { - *(lro_desc->next_frag) = *skb_frags; - tcp_data_len -= skb_frag_size(skb_frags); - lro_desc->next_frag++; - skb_frags++; - skb_shinfo(skb)->nr_frags++; - } -} static int lro_check_tcp_conn(struct net_lro_desc *lro_desc, struct iphdr *iph, @@ -371,128 +348,6 @@ out: return 1; } - -static struct sk_buff *lro_gen_skb(struct net_lro_mgr *lro_mgr, - struct skb_frag_struct *frags, - int len, int true_size, - void *mac_hdr, - int hlen, __wsum sum, - u32 ip_summed) -{ - struct sk_buff *skb; - struct skb_frag_struct *skb_frags; - int data_len = len; - int hdr_len = min(len, hlen); - - skb = netdev_alloc_skb(lro_mgr->dev, hlen + lro_mgr->frag_align_pad); - if (!skb) - return NULL; - - skb_reserve(skb, lro_mgr->frag_align_pad); - skb->len = len; - skb->data_len = len - hdr_len; - skb->truesize += true_size; - skb->tail += hdr_len; - - memcpy(skb->data, mac_hdr, hdr_len); - - skb_frags = skb_shinfo(skb)->frags; - while (data_len > 0) { - *skb_frags = *frags; - data_len -= skb_frag_size(frags); - skb_frags++; - frags++; - skb_shinfo(skb)->nr_frags++; - } - - skb_shinfo(skb)->frags[0].page_offset += hdr_len; - skb_frag_size_sub(&skb_shinfo(skb)->frags[0], hdr_len); - - skb->ip_summed = ip_summed; - skb->csum = sum; - skb->protocol = eth_type_trans(skb, lro_mgr->dev); - return skb; -} - -static struct sk_buff *__lro_proc_segment(struct net_lro_mgr *lro_mgr, - struct skb_frag_struct *frags, - int len, int true_size, - void *priv, __wsum sum) -{ - struct net_lro_desc *lro_desc; - struct iphdr *iph; - struct tcphdr *tcph; - struct sk_buff *skb; - u64 flags; - void *mac_hdr; - int mac_hdr_len; - int hdr_len = LRO_MAX_PG_HLEN; - int vlan_hdr_len = 0; - - if (!lro_mgr->get_frag_header || - lro_mgr->get_frag_header(frags, (void *)&mac_hdr, (void *)&iph, - (void *)&tcph, &flags, priv)) { - mac_hdr = skb_frag_address(frags); - goto out1; - } - - if (!(flags & LRO_IPV4) || !(flags & LRO_TCP)) - goto out1; - - hdr_len = (int)((void *)(tcph) + TCP_HDR_LEN(tcph) - mac_hdr); - mac_hdr_len = (int)((void *)(iph) - mac_hdr); - - lro_desc = lro_get_desc(lro_mgr, lro_mgr->lro_arr, iph, tcph); - if (!lro_desc) - goto out1; - - if (!lro_desc->active) { /* start new lro session */ - if (lro_tcp_ip_check(iph, tcph, len - mac_hdr_len, NULL)) - goto out1; - - skb = lro_gen_skb(lro_mgr, frags, len, true_size, mac_hdr, - hdr_len, 0, lro_mgr->ip_summed_aggr); - if (!skb) - goto out; - - if ((skb->protocol == htons(ETH_P_8021Q)) && - !(lro_mgr->features & LRO_F_EXTRACT_VLAN_ID)) - vlan_hdr_len = VLAN_HLEN; - - iph = (void *)(skb->data + vlan_hdr_len); - tcph = (void *)((u8 *)skb->data + vlan_hdr_len - + IP_HDR_LEN(iph)); - - lro_init_desc(lro_desc, skb, iph, tcph); - LRO_INC_STATS(lro_mgr, aggregated); - return NULL; - } - - if (lro_desc->tcp_next_seq != ntohl(tcph->seq)) - goto out2; - - if (lro_tcp_ip_check(iph, tcph, len - mac_hdr_len, lro_desc)) - goto out2; - - lro_add_frags(lro_desc, len, hdr_len, true_size, frags, iph, tcph); - LRO_INC_STATS(lro_mgr, aggregated); - - if ((skb_shinfo(lro_desc->parent)->nr_frags >= lro_mgr->max_aggr) || - lro_desc->parent->len > (0xFFFF - lro_mgr->dev->mtu)) - lro_flush(lro_mgr, lro_desc); - - return NULL; - -out2: /* send aggregated packets to the stack */ - lro_flush(lro_mgr, lro_desc); - -out1: /* Original packet has to be posted to the stack */ - skb = lro_gen_skb(lro_mgr, frags, len, true_size, mac_hdr, - hdr_len, sum, lro_mgr->ip_summed); -out: - return skb; -} - void lro_receive_skb(struct net_lro_mgr *lro_mgr, struct sk_buff *skb, void *priv) @@ -506,23 +361,6 @@ void lro_receive_skb(struct net_lro_mgr *lro_mgr, } EXPORT_SYMBOL(lro_receive_skb); -void lro_receive_frags(struct net_lro_mgr *lro_mgr, - struct skb_frag_struct *frags, - int len, int true_size, void *priv, __wsum sum) -{ - struct sk_buff *skb; - - skb = __lro_proc_segment(lro_mgr, frags, len, true_size, priv, sum); - if (!skb) - return; - - if (lro_mgr->features & LRO_F_NAPI) - netif_receive_skb(skb); - else - netif_rx(skb); -} -EXPORT_SYMBOL(lro_receive_frags); - void lro_flush_all(struct net_lro_mgr *lro_mgr) { int i; @@ -534,14 +372,3 @@ void lro_flush_all(struct net_lro_mgr *lro_mgr) } } EXPORT_SYMBOL(lro_flush_all); - -void lro_flush_pkt(struct net_lro_mgr *lro_mgr, - struct iphdr *iph, struct tcphdr *tcph) -{ - struct net_lro_desc *lro_desc; - - lro_desc = lro_get_desc(lro_mgr, lro_mgr->lro_arr, iph, tcph); - if (lro_desc->active) - lro_flush(lro_mgr, lro_desc); -} -EXPORT_SYMBOL(lro_flush_pkt); -- cgit v1.3-14-g43fede From 0a9a8bfd29aa5ba2298dc80852cdbb63a42f6576 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Mon, 23 Dec 2013 08:29:42 -0500 Subject: printk: Add a DEPRECATED macro sctp has several points in its setsockopt path in which it issues deprecation warnings. It seems like it might be handy to macrotize such a warning so other subsystems can use it easily Signed-off-by: Neil Horman CC: Greg Kroah-Hartman CC: "David S. Miller" CC: linux-kernel@vger.kernel.org CC: netdev@vger.kernel.org Signed-off-by: David S. Miller --- include/linux/printk.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index 694925837a16..26fb95ce5080 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -87,6 +87,13 @@ struct va_format { */ #define HW_ERR "[Hardware Error]: " +/* + * DEPRECATED + * Add this to a message whenever you want to warn user space about the use + * of a deprecated aspect of an API so they can stop using it + */ +#define DEPRECATED "[Deprecated]: " + /* * Dummy printk for disabled debugging statements to use whilst maintaining * gcc's format and side-effect checking. -- cgit v1.3-14-g43fede From 7ffdf726cfe0d188907bdbb0e7729fb35a69c219 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Mon, 23 Dec 2013 16:09:43 +0200 Subject: net/mlx4_core: Add basic support for TCP/IP offloads under tunneling Add the low-level device commands and definitions used for TCP/IP HW offloads of tunneled/vxlan traffic which are supported by the ConnectX3-pro NIC. This is done through the following elements: - read tunneling device caps in QUERY_DEV_CAP - add helper function to do SET_PORT for tunneling - add DMFS VXLAN steering rule definitions - add CQE and WQE checksum offload field definitions Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/fw.c | 19 +++++++++++++- drivers/net/ethernet/mellanox/mlx4/main.c | 14 +++++++++++ drivers/net/ethernet/mellanox/mlx4/mcg.c | 14 +++++++++-- drivers/net/ethernet/mellanox/mlx4/port.c | 41 +++++++++++++++++++++++++++++++ include/linux/mlx4/cmd.h | 1 + include/linux/mlx4/cq.h | 5 ++++ include/linux/mlx4/device.h | 37 +++++++++++++++++++++++++++- include/linux/mlx4/qp.h | 6 +++++ 8 files changed, 133 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index 27a84342525f..55c4ea740258 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -134,7 +134,8 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags) [5] = "Time stamping support", [6] = "VST (control vlan insertion/stripping) support", [7] = "FSM (MAC anti-spoofing) support", - [8] = "Dynamic QP updates support" + [8] = "Dynamic QP updates support", + [9] = "TCP/IP offloads/flow-steering for VXLAN support" }; int i; @@ -536,6 +537,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) #define QUERY_DEV_CAP_RSVD_LKEY_OFFSET 0x98 #define QUERY_DEV_CAP_MAX_ICM_SZ_OFFSET 0xa0 #define QUERY_DEV_CAP_FW_REASSIGN_MAC 0x9d +#define QUERY_DEV_CAP_VXLAN 0x9e dev_cap->flags2 = 0; mailbox = mlx4_alloc_cmd_mailbox(dev); @@ -701,6 +703,9 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) MLX4_GET(field, outbox, QUERY_DEV_CAP_FW_REASSIGN_MAC); if (field & 1<<6) dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_REASSIGN_MAC_EN; + MLX4_GET(field, outbox, QUERY_DEV_CAP_VXLAN); + if (field & 1<<3) + dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS; MLX4_GET(dev_cap->max_icm_sz, outbox, QUERY_DEV_CAP_MAX_ICM_SZ_OFFSET); if (dev_cap->flags & MLX4_DEV_CAP_FLAG_COUNTERS) @@ -849,6 +854,11 @@ int mlx4_QUERY_DEV_CAP_wrapper(struct mlx4_dev *dev, int slave, field &= 0x7f; MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_CQ_TS_SUPPORT_OFFSET); + /* For guests, disable vxlan tunneling */ + MLX4_GET(field, outbox, QUERY_DEV_CAP_VXLAN); + field &= 0xf7; + MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_VXLAN); + /* For guests, report Blueflame disabled */ MLX4_GET(field, outbox->buf, QUERY_DEV_CAP_BF_OFFSET); field &= 0x7f; @@ -1274,6 +1284,7 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param) #define INIT_HCA_IN_SIZE 0x200 #define INIT_HCA_VERSION_OFFSET 0x000 #define INIT_HCA_VERSION 2 +#define INIT_HCA_VXLAN_OFFSET 0x0c #define INIT_HCA_CACHELINE_SZ_OFFSET 0x0e #define INIT_HCA_FLAGS_OFFSET 0x014 #define INIT_HCA_QPC_OFFSET 0x020 @@ -1432,6 +1443,12 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param) MLX4_PUT(inbox, param->uar_page_sz, INIT_HCA_UAR_PAGE_SZ_OFFSET); MLX4_PUT(inbox, param->log_uar_sz, INIT_HCA_LOG_UAR_SZ_OFFSET); + /* set parser VXLAN attributes */ + if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS) { + u8 parser_params = 0; + MLX4_PUT(inbox, parser_params, INIT_HCA_VXLAN_OFFSET); + } + err = mlx4_cmd(dev, mailbox->dma, 0, 0, MLX4_CMD_INIT_HCA, 10000, MLX4_CMD_NATIVE); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index fbebfb0a6436..d2b8b3918b45 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -1444,6 +1444,19 @@ static void choose_steering_mode(struct mlx4_dev *dev, mlx4_log_num_mgm_entry_size); } +static void choose_tunnel_offload_mode(struct mlx4_dev *dev, + struct mlx4_dev_cap *dev_cap) +{ + if (dev->caps.steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED && + dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS) + dev->caps.tunnel_offload_mode = MLX4_TUNNEL_OFFLOAD_MODE_VXLAN; + else + dev->caps.tunnel_offload_mode = MLX4_TUNNEL_OFFLOAD_MODE_NONE; + + mlx4_dbg(dev, "Tunneling offload mode is: %s\n", (dev->caps.tunnel_offload_mode + == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) ? "vxlan" : "none"); +} + static int mlx4_init_hca(struct mlx4_dev *dev) { struct mlx4_priv *priv = mlx4_priv(dev); @@ -1484,6 +1497,7 @@ static int mlx4_init_hca(struct mlx4_dev *dev) } choose_steering_mode(dev, &dev_cap); + choose_tunnel_offload_mode(dev, &dev_cap); err = mlx4_get_phys_port_id(dev); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c index 7c83e6ccc9da..bfe65f7be91c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mcg.c +++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c @@ -697,7 +697,8 @@ const u16 __sw_id_hw[] = { [MLX4_NET_TRANS_RULE_ID_IPV6] = 0xE003, [MLX4_NET_TRANS_RULE_ID_IPV4] = 0xE002, [MLX4_NET_TRANS_RULE_ID_TCP] = 0xE004, - [MLX4_NET_TRANS_RULE_ID_UDP] = 0xE006 + [MLX4_NET_TRANS_RULE_ID_UDP] = 0xE006, + [MLX4_NET_TRANS_RULE_ID_VXLAN] = 0xE008 }; int mlx4_map_sw_to_hw_steering_id(struct mlx4_dev *dev, @@ -722,7 +723,9 @@ static const int __rule_hw_sz[] = { [MLX4_NET_TRANS_RULE_ID_TCP] = sizeof(struct mlx4_net_trans_rule_hw_tcp_udp), [MLX4_NET_TRANS_RULE_ID_UDP] = - sizeof(struct mlx4_net_trans_rule_hw_tcp_udp) + sizeof(struct mlx4_net_trans_rule_hw_tcp_udp), + [MLX4_NET_TRANS_RULE_ID_VXLAN] = + sizeof(struct mlx4_net_trans_rule_hw_vxlan) }; int mlx4_hw_rule_sz(struct mlx4_dev *dev, @@ -787,6 +790,13 @@ static int parse_trans_rule(struct mlx4_dev *dev, struct mlx4_spec_list *spec, rule_hw->tcp_udp.src_port_msk = spec->tcp_udp.src_port_msk; break; + case MLX4_NET_TRANS_RULE_ID_VXLAN: + rule_hw->vxlan.vni = + cpu_to_be32(be32_to_cpu(spec->vxlan.vni) << 8); + rule_hw->vxlan.vni_mask = + cpu_to_be32(be32_to_cpu(spec->vxlan.vni_mask) << 8); + break; + default: return -EINVAL; } diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c index 97d342fa5032..93f75ec78c82 100644 --- a/drivers/net/ethernet/mellanox/mlx4/port.c +++ b/drivers/net/ethernet/mellanox/mlx4/port.c @@ -800,6 +800,47 @@ int mlx4_SET_PORT_SCHEDULER(struct mlx4_dev *dev, u8 port, u8 *tc_tx_bw, } EXPORT_SYMBOL(mlx4_SET_PORT_SCHEDULER); +enum { + VXLAN_ENABLE_MODIFY = 1 << 7, + VXLAN_STEERING_MODIFY = 1 << 6, + + VXLAN_ENABLE = 1 << 7, +}; + +struct mlx4_set_port_vxlan_context { + u32 reserved1; + u8 modify_flags; + u8 reserved2; + u8 enable_flags; + u8 steering; +}; + +int mlx4_SET_PORT_VXLAN(struct mlx4_dev *dev, u8 port, u8 steering) +{ + int err; + u32 in_mod; + struct mlx4_cmd_mailbox *mailbox; + struct mlx4_set_port_vxlan_context *context; + + mailbox = mlx4_alloc_cmd_mailbox(dev); + if (IS_ERR(mailbox)) + return PTR_ERR(mailbox); + context = mailbox->buf; + memset(context, 0, sizeof(*context)); + + context->modify_flags = VXLAN_ENABLE_MODIFY | VXLAN_STEERING_MODIFY; + context->enable_flags = VXLAN_ENABLE; + context->steering = steering; + + in_mod = MLX4_SET_PORT_VXLAN << 8 | port; + err = mlx4_cmd(dev, mailbox->dma, in_mod, 1, MLX4_CMD_SET_PORT, + MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE); + + mlx4_free_cmd_mailbox(dev, mailbox); + return err; +} +EXPORT_SYMBOL(mlx4_SET_PORT_VXLAN); + int mlx4_SET_MCAST_FLTR_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_vhcr *vhcr, struct mlx4_cmd_mailbox *inbox, diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index 8df61bc5da00..b0ec0fe035c0 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -180,6 +180,7 @@ enum { MLX4_SET_PORT_GID_TABLE = 0x5, MLX4_SET_PORT_PRIO2TC = 0x8, MLX4_SET_PORT_SCHEDULER = 0x9, + MLX4_SET_PORT_VXLAN = 0xB }; enum { diff --git a/include/linux/mlx4/cq.h b/include/linux/mlx4/cq.h index 98fa492cf406..5dd0d70a0689 100644 --- a/include/linux/mlx4/cq.h +++ b/include/linux/mlx4/cq.h @@ -81,7 +81,12 @@ struct mlx4_ts_cqe { } __packed; enum { + MLX4_CQE_L2_TUNNEL_IPOK = 1 << 31, MLX4_CQE_VLAN_PRESENT_MASK = 1 << 29, + MLX4_CQE_L2_TUNNEL = 1 << 27, + MLX4_CQE_L2_TUNNEL_CSUM = 1 << 26, + MLX4_CQE_L2_TUNNEL_IPV4 = 1 << 25, + MLX4_CQE_QPN_MASK = 0xffffff, }; diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 294b7c58fe95..c99ecf6d2c67 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -118,6 +118,11 @@ static inline const char *mlx4_steering_mode_str(int steering_mode) } } +enum { + MLX4_TUNNEL_OFFLOAD_MODE_NONE, + MLX4_TUNNEL_OFFLOAD_MODE_VXLAN +}; + enum { MLX4_DEV_CAP_FLAG_RC = 1LL << 0, MLX4_DEV_CAP_FLAG_UC = 1LL << 1, @@ -160,7 +165,8 @@ enum { MLX4_DEV_CAP_FLAG2_TS = 1LL << 5, MLX4_DEV_CAP_FLAG2_VLAN_CONTROL = 1LL << 6, MLX4_DEV_CAP_FLAG2_FSM = 1LL << 7, - MLX4_DEV_CAP_FLAG2_UPDATE_QP = 1LL << 8 + MLX4_DEV_CAP_FLAG2_UPDATE_QP = 1LL << 8, + MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS = 1LL << 9 }; enum { @@ -455,6 +461,7 @@ struct mlx4_caps { u32 function_caps; /* VFs must be aware of these */ u16 hca_core_clock; u64 phys_port_id[MLX4_MAX_PORTS + 1]; + int tunnel_offload_mode; }; struct mlx4_buf_list { @@ -909,6 +916,7 @@ enum mlx4_net_trans_rule_id { MLX4_NET_TRANS_RULE_ID_IPV4, MLX4_NET_TRANS_RULE_ID_TCP, MLX4_NET_TRANS_RULE_ID_UDP, + MLX4_NET_TRANS_RULE_ID_VXLAN, MLX4_NET_TRANS_RULE_NUM, /* should be last */ }; @@ -966,6 +974,12 @@ struct mlx4_spec_ib { u8 dst_gid_msk[16]; }; +struct mlx4_spec_vxlan { + __be32 vni; + __be32 vni_mask; + +}; + struct mlx4_spec_list { struct list_head list; enum mlx4_net_trans_rule_id id; @@ -974,6 +988,7 @@ struct mlx4_spec_list { struct mlx4_spec_ib ib; struct mlx4_spec_ipv4 ipv4; struct mlx4_spec_tcp_udp tcp_udp; + struct mlx4_spec_vxlan vxlan; }; }; @@ -1060,6 +1075,15 @@ struct mlx4_net_trans_rule_hw_ipv4 { __be32 src_ip_msk; } __packed; +struct mlx4_net_trans_rule_hw_vxlan { + u8 size; + u8 rsvd; + __be16 id; + __be32 rsvd1; + __be32 vni; + __be32 vni_mask; +} __packed; + struct _rule_hw { union { struct { @@ -1071,9 +1095,19 @@ struct _rule_hw { struct mlx4_net_trans_rule_hw_ib ib; struct mlx4_net_trans_rule_hw_ipv4 ipv4; struct mlx4_net_trans_rule_hw_tcp_udp tcp_udp; + struct mlx4_net_trans_rule_hw_vxlan vxlan; }; }; +enum { + VXLAN_STEER_BY_OUTER_MAC = 1 << 0, + VXLAN_STEER_BY_OUTER_VLAN = 1 << 1, + VXLAN_STEER_BY_VSID_VNI = 1 << 2, + VXLAN_STEER_BY_INNER_MAC = 1 << 3, + VXLAN_STEER_BY_INNER_VLAN = 1 << 4, +}; + + int mlx4_flow_steer_promisc_add(struct mlx4_dev *dev, u8 port, u32 qpn, enum mlx4_net_trans_promisc_mode mode); int mlx4_flow_steer_promisc_remove(struct mlx4_dev *dev, u8 port, @@ -1096,6 +1130,7 @@ int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn, int mlx4_SET_PORT_PRIO2TC(struct mlx4_dev *dev, u8 port, u8 *prio2tc); int mlx4_SET_PORT_SCHEDULER(struct mlx4_dev *dev, u8 port, u8 *tc_tx_bw, u8 *pg, u16 *ratelimit); +int mlx4_SET_PORT_VXLAN(struct mlx4_dev *dev, u8 port, u8 steering); int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx); int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index); void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan); diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 6d351473c292..59f8ba84568b 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -109,6 +109,10 @@ enum { MLX4_RSS_TCP_IPV4 = 1 << 4, MLX4_RSS_IPV4 = 1 << 5, + MLX4_RSS_BY_OUTER_HEADERS = 0 << 6, + MLX4_RSS_BY_INNER_HEADERS = 2 << 6, + MLX4_RSS_BY_INNER_HEADERS_IPONLY = 3 << 6, + /* offset of mlx4_rss_context within mlx4_qp_context.pri_path */ MLX4_RSS_OFFSET_IN_QPC_PRI_PATH = 0x24, /* offset of being RSS indirection QP within mlx4_qp_context.flags */ @@ -252,6 +256,8 @@ enum { /* param3 */ enum { MLX4_WQE_CTRL_NEC = 1 << 29, + MLX4_WQE_CTRL_IIP = 1 << 28, + MLX4_WQE_CTRL_ILP = 1 << 27, MLX4_WQE_CTRL_FENCE = 1 << 6, MLX4_WQE_CTRL_CQ_UPDATE = 3 << 2, MLX4_WQE_CTRL_SOLICITED = 1 << 1, -- cgit v1.3-14-g43fede From 2173f8d953e76026bf6ede8ec81ad35ec158dae9 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 30 Dec 2013 10:49:22 -0800 Subject: netlink: cleanup tap related functions Cleanups in netlink_tap code * remove unused function netlink_clear_multicast_users * make local function static Signed-off-by: Stephen Hemminger Reviewed-by: Johannes Berg Signed-off-by: David S. Miller --- include/linux/netlink.h | 2 -- net/netlink/af_netlink.c | 18 +----------------- 2 files changed, 1 insertion(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 7a6c396a263b..aad8eeaf416d 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -62,7 +62,6 @@ extern void netlink_kernel_release(struct sock *sk); extern int __netlink_change_ngroups(struct sock *sk, unsigned int groups); extern int netlink_change_ngroups(struct sock *sk, unsigned int groups); extern void __netlink_clear_multicast_users(struct sock *sk, unsigned int group); -extern void netlink_clear_multicast_users(struct sock *sk, unsigned int group); extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err); extern int netlink_has_listeners(struct sock *sk, unsigned int group); extern struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size, @@ -168,7 +167,6 @@ struct netlink_tap { }; extern int netlink_add_tap(struct netlink_tap *nt); -extern int __netlink_remove_tap(struct netlink_tap *nt); extern int netlink_remove_tap(struct netlink_tap *nt); #endif /* __LINUX_NETLINK_H */ diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 3f75f1cd9eb3..b077b90c1254 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -131,7 +131,7 @@ int netlink_add_tap(struct netlink_tap *nt) } EXPORT_SYMBOL_GPL(netlink_add_tap); -int __netlink_remove_tap(struct netlink_tap *nt) +static int __netlink_remove_tap(struct netlink_tap *nt) { bool found = false; struct netlink_tap *tmp; @@ -155,7 +155,6 @@ out: return found ? 0 : -ENODEV; } -EXPORT_SYMBOL_GPL(__netlink_remove_tap); int netlink_remove_tap(struct netlink_tap *nt) { @@ -2540,21 +2539,6 @@ void __netlink_clear_multicast_users(struct sock *ksk, unsigned int group) netlink_update_socket_mc(nlk_sk(sk), group, 0); } -/** - * netlink_clear_multicast_users - kick off multicast listeners - * - * This function removes all listeners from the given group. - * @ksk: The kernel netlink socket, as returned by - * netlink_kernel_create(). - * @group: The multicast group to clear. - */ -void netlink_clear_multicast_users(struct sock *ksk, unsigned int group) -{ - netlink_table_grab(); - __netlink_clear_multicast_users(ksk, group); - netlink_table_ungrab(); -} - struct nlmsghdr * __nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int flags) { -- cgit v1.3-14-g43fede From 1d143d9f0c833fcf38cc737eb0a8698fa2dd144c Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Sun, 29 Dec 2013 14:01:29 -0800 Subject: net: core functions cleanup The following functions are not used outside of net/core/dev.c and should be declared static. call_netdevice_notifiers_info __dev_remove_offload netdev_has_any_upper_dev __netdev_adjacent_dev_remove __netdev_adjacent_dev_link_lists __netdev_adjacent_dev_unlink_lists __netdev_adjacent_dev_unlink __netdev_adjacent_dev_link_neighbour __netdev_adjacent_dev_unlink_neighbour And the following are never used and should be deleted netdev_lower_dev_get_private_rcu __netdev_find_adj_rcu Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 ---- net/core/dev.c | 82 +++++++++++++++-------------------------------- 2 files changed, 26 insertions(+), 62 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 88afa8048a7c..bec60c481966 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1741,8 +1741,6 @@ netdev_notifier_info_to_dev(const struct netdev_notifier_info *info) return info->dev; } -int call_netdevice_notifiers_info(unsigned long val, struct net_device *dev, - struct netdev_notifier_info *info); int call_netdevice_notifiers(unsigned long val, struct net_device *dev); @@ -1809,7 +1807,6 @@ void dev_remove_pack(struct packet_type *pt); void __dev_remove_pack(struct packet_type *pt); void dev_add_offload(struct packet_offload *po); void dev_remove_offload(struct packet_offload *po); -void __dev_remove_offload(struct packet_offload *po); struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short flags, unsigned short mask); @@ -2867,7 +2864,6 @@ extern int weight_p; extern int bpf_jit_enable; bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev); -bool netdev_has_any_upper_dev(struct net_device *dev); struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, struct list_head **iter); @@ -2907,8 +2903,6 @@ int netdev_master_upper_dev_link_private(struct net_device *dev, void *private); void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev); -void *netdev_lower_dev_get_private_rcu(struct net_device *dev, - struct net_device *lower_dev); void *netdev_lower_dev_get_private(struct net_device *dev, struct net_device *lower_dev); int skb_checksum_help(struct sk_buff *skb); diff --git a/net/core/dev.c b/net/core/dev.c index cc9ab80581d7..77f43aa373fe 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -480,7 +480,7 @@ EXPORT_SYMBOL(dev_add_offload); * and must not be freed until after all the CPU's have gone * through a quiescent state. */ -void __dev_remove_offload(struct packet_offload *po) +static void __dev_remove_offload(struct packet_offload *po) { struct list_head *head = &offload_base; struct packet_offload *po1; @@ -498,7 +498,6 @@ void __dev_remove_offload(struct packet_offload *po) out: spin_unlock(&offload_lock); } -EXPORT_SYMBOL(__dev_remove_offload); /** * dev_remove_offload - remove packet offload handler @@ -1566,14 +1565,14 @@ EXPORT_SYMBOL(unregister_netdevice_notifier); * are as for raw_notifier_call_chain(). */ -int call_netdevice_notifiers_info(unsigned long val, struct net_device *dev, - struct netdev_notifier_info *info) +static int call_netdevice_notifiers_info(unsigned long val, + struct net_device *dev, + struct netdev_notifier_info *info) { ASSERT_RTNL(); netdev_notifier_info_init(info, dev); return raw_notifier_call_chain(&netdev_chain, val, info); } -EXPORT_SYMBOL(call_netdevice_notifiers_info); /** * call_netdevice_notifiers - call all network notifier blocks @@ -4355,19 +4354,6 @@ struct netdev_adjacent { struct rcu_head rcu; }; -static struct netdev_adjacent *__netdev_find_adj_rcu(struct net_device *dev, - struct net_device *adj_dev, - struct list_head *adj_list) -{ - struct netdev_adjacent *adj; - - list_for_each_entry_rcu(adj, adj_list, list) { - if (adj->dev == adj_dev) - return adj; - } - return NULL; -} - static struct netdev_adjacent *__netdev_find_adj(struct net_device *dev, struct net_device *adj_dev, struct list_head *adj_list) @@ -4406,13 +4392,12 @@ EXPORT_SYMBOL(netdev_has_upper_dev); * Find out if a device is linked to an upper device and return true in case * it is. The caller must hold the RTNL lock. */ -bool netdev_has_any_upper_dev(struct net_device *dev) +static bool netdev_has_any_upper_dev(struct net_device *dev) { ASSERT_RTNL(); return !list_empty(&dev->all_adj_list.upper); } -EXPORT_SYMBOL(netdev_has_any_upper_dev); /** * netdev_master_upper_dev_get - Get master upper device @@ -4644,9 +4629,9 @@ free_adj: return ret; } -void __netdev_adjacent_dev_remove(struct net_device *dev, - struct net_device *adj_dev, - struct list_head *dev_list) +static void __netdev_adjacent_dev_remove(struct net_device *dev, + struct net_device *adj_dev, + struct list_head *dev_list) { struct netdev_adjacent *adj; char linkname[IFNAMSIZ+7]; @@ -4684,11 +4669,11 @@ void __netdev_adjacent_dev_remove(struct net_device *dev, kfree_rcu(adj, rcu); } -int __netdev_adjacent_dev_link_lists(struct net_device *dev, - struct net_device *upper_dev, - struct list_head *up_list, - struct list_head *down_list, - void *private, bool master) +static int __netdev_adjacent_dev_link_lists(struct net_device *dev, + struct net_device *upper_dev, + struct list_head *up_list, + struct list_head *down_list, + void *private, bool master) { int ret; @@ -4707,8 +4692,8 @@ int __netdev_adjacent_dev_link_lists(struct net_device *dev, return 0; } -int __netdev_adjacent_dev_link(struct net_device *dev, - struct net_device *upper_dev) +static int __netdev_adjacent_dev_link(struct net_device *dev, + struct net_device *upper_dev) { return __netdev_adjacent_dev_link_lists(dev, upper_dev, &dev->all_adj_list.upper, @@ -4716,26 +4701,26 @@ int __netdev_adjacent_dev_link(struct net_device *dev, NULL, false); } -void __netdev_adjacent_dev_unlink_lists(struct net_device *dev, - struct net_device *upper_dev, - struct list_head *up_list, - struct list_head *down_list) +static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev, + struct net_device *upper_dev, + struct list_head *up_list, + struct list_head *down_list) { __netdev_adjacent_dev_remove(dev, upper_dev, up_list); __netdev_adjacent_dev_remove(upper_dev, dev, down_list); } -void __netdev_adjacent_dev_unlink(struct net_device *dev, - struct net_device *upper_dev) +static void __netdev_adjacent_dev_unlink(struct net_device *dev, + struct net_device *upper_dev) { __netdev_adjacent_dev_unlink_lists(dev, upper_dev, &dev->all_adj_list.upper, &upper_dev->all_adj_list.lower); } -int __netdev_adjacent_dev_link_neighbour(struct net_device *dev, - struct net_device *upper_dev, - void *private, bool master) +static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev, + struct net_device *upper_dev, + void *private, bool master) { int ret = __netdev_adjacent_dev_link(dev, upper_dev); @@ -4754,8 +4739,8 @@ int __netdev_adjacent_dev_link_neighbour(struct net_device *dev, return 0; } -void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev, - struct net_device *upper_dev) +static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev, + struct net_device *upper_dev) { __netdev_adjacent_dev_unlink(dev, upper_dev); __netdev_adjacent_dev_unlink_lists(dev, upper_dev, @@ -4944,21 +4929,6 @@ void netdev_upper_dev_unlink(struct net_device *dev, } EXPORT_SYMBOL(netdev_upper_dev_unlink); -void *netdev_lower_dev_get_private_rcu(struct net_device *dev, - struct net_device *lower_dev) -{ - struct netdev_adjacent *lower; - - if (!lower_dev) - return NULL; - lower = __netdev_find_adj_rcu(dev, lower_dev, &dev->adj_list.lower); - if (!lower) - return NULL; - - return lower->private; -} -EXPORT_SYMBOL(netdev_lower_dev_get_private_rcu); - void *netdev_lower_dev_get_private(struct net_device *dev, struct net_device *lower_dev) { -- cgit v1.3-14-g43fede From 96bfc80d83d4b109bd5c5af6bc323424e920c84d Mon Sep 17 00:00:00 2001 From: Sachin Kamat Date: Mon, 30 Dec 2013 10:41:56 +0530 Subject: net: Cleanup in eth-netx.h Commit 2960ed346877 ("ARM: netx: move platform_data definitions") moved the file to the current location but forgot to remove the pointer to its previous location. Clean it up. While at it also change the header file protection macros appropriately. Signed-off-by: Sachin Kamat Cc: Sascha Hauer Signed-off-by: David S. Miller --- include/linux/platform_data/eth-netx.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/eth-netx.h b/include/linux/platform_data/eth-netx.h index 88af1ac28ead..a395159725d5 100644 --- a/include/linux/platform_data/eth-netx.h +++ b/include/linux/platform_data/eth-netx.h @@ -1,6 +1,4 @@ /* - * arch/arm/mach-netx/include/mach/eth.h - * * Copyright (c) 2005 Sascha Hauer , Pengutronix * * This program is free software; you can redistribute it and/or modify @@ -17,8 +15,8 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ -#ifndef ASMARM_ARCH_ETH_H -#define ASMARM_ARCH_ETH_H +#ifndef __ETH_NETX_H +#define __ETH_NETX_H struct netxeth_platform_data { unsigned int xcno; /* number of xmac/xpec engine this eth uses */ -- cgit v1.3-14-g43fede From 02eca9d2cc541806e8f03b4131c7ee9120246df7 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 30 Dec 2013 17:13:10 -0800 Subject: netfilter: ipset: remove unused code Function never used in current upstream code. Signed-off-by: Stephen Hemminger Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 1 - net/netfilter/ipset/ip_set_core.c | 28 ---------------------------- 2 files changed, 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index c7174b816674..0c7d01eae56c 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -331,7 +331,6 @@ extern ip_set_id_t ip_set_get_byname(struct net *net, const char *name, struct ip_set **set); extern void ip_set_put_byindex(struct net *net, ip_set_id_t index); extern const char *ip_set_name_byindex(struct net *net, ip_set_id_t index); -extern ip_set_id_t ip_set_nfnl_get(struct net *net, const char *name); extern ip_set_id_t ip_set_nfnl_get_byindex(struct net *net, ip_set_id_t index); extern void ip_set_nfnl_put(struct net *net, ip_set_id_t index); diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index bac7e01df67f..de770ec39e51 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -624,34 +624,6 @@ EXPORT_SYMBOL_GPL(ip_set_name_byindex); * call nfnl_lock for us. */ -/* - * Find set by name, reference it once. The reference makes sure the - * thing pointed to, does not go away under our feet. - * - * The nfnl mutex is used in the function. - */ -ip_set_id_t -ip_set_nfnl_get(struct net *net, const char *name) -{ - ip_set_id_t i, index = IPSET_INVALID_ID; - struct ip_set *s; - struct ip_set_net *inst = ip_set_pernet(net); - - nfnl_lock(NFNL_SUBSYS_IPSET); - for (i = 0; i < inst->ip_set_max; i++) { - s = nfnl_set(inst, i); - if (s != NULL && STREQ(s->name, name)) { - __ip_set_get(s); - index = i; - break; - } - } - nfnl_unlock(NFNL_SUBSYS_IPSET); - - return index; -} -EXPORT_SYMBOL_GPL(ip_set_nfnl_get); - /* * Find set by index, reference it once. The reference makes sure the * thing pointed to, does not go away under our feet. -- cgit v1.3-14-g43fede From fe1217c4f3f7d7cbf8efdd8dd5fdc7204a1d65a8 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 29 Dec 2013 18:27:10 +0100 Subject: net: net_cls: move cgroupfs classid handling into core Zefan Li requested [1] to perform the following cleanup/refactoring: - Split cgroupfs classid handling into net core to better express a possible more generic use. - Disable module support for cgroupfs bits as the majority of other cgroupfs subsystems do not have that, and seems to be not wished from cgroup side. Zefan probably might want to follow-up for netprio later on. - By this, code can be further reduced which previously took care of functionality built when compiled as module. cgroupfs bits are being placed under net/core/netclassid_cgroup.c, so that we are consistent with {netclassid,netprio}_cgroup naming that is under net/core/ as suggested by Zefan. No change in functionality, but only code refactoring that is being done here. [1] http://patchwork.ozlabs.org/patch/304825/ Suggested-by: Li Zefan Signed-off-by: Daniel Borkmann Cc: Zefan Li Cc: Thomas Graf Cc: cgroups@vger.kernel.org Acked-by: Li Zefan Signed-off-by: Pablo Neira Ayuso --- include/linux/cgroup_subsys.h | 2 +- include/net/cls_cgroup.h | 40 +++++--------- net/Kconfig | 7 +++ net/core/Makefile | 1 + net/core/netclassid_cgroup.c | 120 ++++++++++++++++++++++++++++++++++++++++++ net/core/sock.c | 12 ----- net/sched/Kconfig | 1 + net/sched/cls_cgroup.c | 111 +------------------------------------- 8 files changed, 143 insertions(+), 151 deletions(-) create mode 100644 net/core/netclassid_cgroup.c (limited to 'include/linux') diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h index b613ffd402d1..58bf94de4b8e 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -31,7 +31,7 @@ SUBSYS(devices) SUBSYS(freezer) #endif -#if IS_SUBSYS_ENABLED(CONFIG_NET_CLS_CGROUP) +#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_NET_CLASSID) SUBSYS(net_cls) #endif diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h index 33d03b648646..9cf2d5ef38d9 100644 --- a/include/net/cls_cgroup.h +++ b/include/net/cls_cgroup.h @@ -16,17 +16,16 @@ #include #include #include +#include -#if IS_ENABLED(CONFIG_NET_CLS_CGROUP) -struct cgroup_cls_state -{ +#ifdef CONFIG_CGROUP_NET_CLASSID +struct cgroup_cls_state { struct cgroup_subsys_state css; u32 classid; }; -void sock_update_classid(struct sock *sk); +struct cgroup_cls_state *task_cls_state(struct task_struct *p); -#if IS_BUILTIN(CONFIG_NET_CLS_CGROUP) static inline u32 task_cls_classid(struct task_struct *p) { u32 classid; @@ -41,33 +40,18 @@ static inline u32 task_cls_classid(struct task_struct *p) return classid; } -#elif IS_MODULE(CONFIG_NET_CLS_CGROUP) -static inline u32 task_cls_classid(struct task_struct *p) -{ - struct cgroup_subsys_state *css; - u32 classid = 0; - - if (in_interrupt()) - return 0; - - rcu_read_lock(); - css = task_css(p, net_cls_subsys_id); - if (css) - classid = container_of(css, - struct cgroup_cls_state, css)->classid; - rcu_read_unlock(); - return classid; -} -#endif -#else /* !CGROUP_NET_CLS_CGROUP */ static inline void sock_update_classid(struct sock *sk) { -} + u32 classid; -static inline u32 task_cls_classid(struct task_struct *p) + classid = task_cls_classid(current); + if (classid != sk->sk_classid) + sk->sk_classid = classid; +} +#else /* !CONFIG_CGROUP_NET_CLASSID */ +static inline void sock_update_classid(struct sock *sk) { - return 0; } -#endif /* CGROUP_NET_CLS_CGROUP */ +#endif /* CONFIG_CGROUP_NET_CLASSID */ #endif /* _NET_CLS_CGROUP_H */ diff --git a/net/Kconfig b/net/Kconfig index d334678c0bd8..7da10b830d70 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -245,6 +245,13 @@ config NETPRIO_CGROUP Cgroup subsystem for use in assigning processes to network priorities on a per-interface basis +config CGROUP_NET_CLASSID + boolean "Network classid cgroup" + depends on CGROUPS + ---help--- + Cgroup subsystem for use as general purpose socket classid marker that is + being used in cls_cgroup and for netfilter matching. + config NET_RX_BUSY_POLL boolean default y diff --git a/net/core/Makefile b/net/core/Makefile index b33b996f5dd6..4839a2796964 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -22,3 +22,4 @@ obj-$(CONFIG_TRACEPOINTS) += net-traces.o obj-$(CONFIG_NET_DROP_MONITOR) += drop_monitor.o obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o obj-$(CONFIG_NETPRIO_CGROUP) += netprio_cgroup.o +obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c new file mode 100644 index 000000000000..719efd541668 --- /dev/null +++ b/net/core/netclassid_cgroup.c @@ -0,0 +1,120 @@ +/* + * net/core/netclassid_cgroup.c Classid Cgroupfs Handling + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Authors: Thomas Graf + */ + +#include +#include +#include +#include +#include +#include + +static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state *css) +{ + return css ? container_of(css, struct cgroup_cls_state, css) : NULL; +} + +struct cgroup_cls_state *task_cls_state(struct task_struct *p) +{ + return css_cls_state(task_css(p, net_cls_subsys_id)); +} +EXPORT_SYMBOL_GPL(task_cls_state); + +static struct cgroup_subsys_state * +cgrp_css_alloc(struct cgroup_subsys_state *parent_css) +{ + struct cgroup_cls_state *cs; + + cs = kzalloc(sizeof(*cs), GFP_KERNEL); + if (!cs) + return ERR_PTR(-ENOMEM); + + return &cs->css; +} + +static int cgrp_css_online(struct cgroup_subsys_state *css) +{ + struct cgroup_cls_state *cs = css_cls_state(css); + struct cgroup_cls_state *parent = css_cls_state(css_parent(css)); + + if (parent) + cs->classid = parent->classid; + + return 0; +} + +static void cgrp_css_free(struct cgroup_subsys_state *css) +{ + kfree(css_cls_state(css)); +} + +static int update_classid(const void *v, struct file *file, unsigned n) +{ + int err; + struct socket *sock = sock_from_file(file, &err); + + if (sock) + sock->sk->sk_classid = (u32)(unsigned long)v; + + return 0; +} + +static void cgrp_attach(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset) +{ + struct cgroup_cls_state *cs = css_cls_state(css); + void *v = (void *)(unsigned long)cs->classid; + struct task_struct *p; + + cgroup_taskset_for_each(p, css, tset) { + task_lock(p); + iterate_fd(p->files, 0, update_classid, v); + task_unlock(p); + } +} + +static u64 read_classid(struct cgroup_subsys_state *css, struct cftype *cft) +{ + return css_cls_state(css)->classid; +} + +static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft, + u64 value) +{ + css_cls_state(css)->classid = (u32) value; + + return 0; +} + +static struct cftype ss_files[] = { + { + .name = "classid", + .read_u64 = read_classid, + .write_u64 = write_classid, + }, + { } /* terminate */ +}; + +struct cgroup_subsys net_cls_subsys = { + .name = "net_cls", + .css_alloc = cgrp_css_alloc, + .css_online = cgrp_css_online, + .css_free = cgrp_css_free, + .attach = cgrp_attach, + .subsys_id = net_cls_subsys_id, + .base_cftypes = ss_files, + .module = THIS_MODULE, +}; + +static int __init init_netclassid_cgroup(void) +{ + return cgroup_load_subsys(&net_cls_subsys); +} +__initcall(init_netclassid_cgroup); diff --git a/net/core/sock.c b/net/core/sock.c index ab20ed9b0f31..3f150729fb15 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1308,18 +1308,6 @@ static void sk_prot_free(struct proto *prot, struct sock *sk) module_put(owner); } -#if IS_ENABLED(CONFIG_NET_CLS_CGROUP) -void sock_update_classid(struct sock *sk) -{ - u32 classid; - - classid = task_cls_classid(current); - if (classid != sk->sk_classid) - sk->sk_classid = classid; -} -EXPORT_SYMBOL(sock_update_classid); -#endif - #if IS_ENABLED(CONFIG_NETPRIO_CGROUP) void sock_update_netprioidx(struct sock *sk) { diff --git a/net/sched/Kconfig b/net/sched/Kconfig index ad1f1d819203..f711a471d0b7 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -435,6 +435,7 @@ config NET_CLS_FLOW config NET_CLS_CGROUP tristate "Control Group Classifier" select NET_CLS + select CGROUP_NET_CLASSID depends on CGROUPS ---help--- Say Y here if you want to classify packets based on the control diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 16006c92c3fd..838fa40abad1 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -11,109 +11,13 @@ #include #include -#include -#include -#include #include -#include #include -#include #include #include #include #include -static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state *css) -{ - return css ? container_of(css, struct cgroup_cls_state, css) : NULL; -} - -static inline struct cgroup_cls_state *task_cls_state(struct task_struct *p) -{ - return css_cls_state(task_css(p, net_cls_subsys_id)); -} - -static struct cgroup_subsys_state * -cgrp_css_alloc(struct cgroup_subsys_state *parent_css) -{ - struct cgroup_cls_state *cs; - - cs = kzalloc(sizeof(*cs), GFP_KERNEL); - if (!cs) - return ERR_PTR(-ENOMEM); - return &cs->css; -} - -static int cgrp_css_online(struct cgroup_subsys_state *css) -{ - struct cgroup_cls_state *cs = css_cls_state(css); - struct cgroup_cls_state *parent = css_cls_state(css_parent(css)); - - if (parent) - cs->classid = parent->classid; - return 0; -} - -static void cgrp_css_free(struct cgroup_subsys_state *css) -{ - kfree(css_cls_state(css)); -} - -static int update_classid(const void *v, struct file *file, unsigned n) -{ - int err; - struct socket *sock = sock_from_file(file, &err); - if (sock) - sock->sk->sk_classid = (u32)(unsigned long)v; - return 0; -} - -static void cgrp_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) -{ - struct task_struct *p; - struct cgroup_cls_state *cs = css_cls_state(css); - void *v = (void *)(unsigned long)cs->classid; - - cgroup_taskset_for_each(p, css, tset) { - task_lock(p); - iterate_fd(p->files, 0, update_classid, v); - task_unlock(p); - } -} - -static u64 read_classid(struct cgroup_subsys_state *css, struct cftype *cft) -{ - return css_cls_state(css)->classid; -} - -static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft, - u64 value) -{ - css_cls_state(css)->classid = (u32) value; - return 0; -} - -static struct cftype ss_files[] = { - { - .name = "classid", - .read_u64 = read_classid, - .write_u64 = write_classid, - }, - { } /* terminate */ -}; - -struct cgroup_subsys net_cls_subsys = { - .name = "net_cls", - .css_alloc = cgrp_css_alloc, - .css_online = cgrp_css_online, - .css_free = cgrp_css_free, - .attach = cgrp_attach, - .subsys_id = net_cls_subsys_id, - .base_cftypes = ss_files, - .module = THIS_MODULE, -}; - struct cls_cgroup_head { u32 handle; struct tcf_exts exts; @@ -309,25 +213,12 @@ static struct tcf_proto_ops cls_cgroup_ops __read_mostly = { static int __init init_cgroup_cls(void) { - int ret; - - ret = cgroup_load_subsys(&net_cls_subsys); - if (ret) - goto out; - - ret = register_tcf_proto_ops(&cls_cgroup_ops); - if (ret) - cgroup_unload_subsys(&net_cls_subsys); - -out: - return ret; + return register_tcf_proto_ops(&cls_cgroup_ops); } static void __exit exit_cgroup_cls(void) { unregister_tcf_proto_ops(&cls_cgroup_ops); - - cgroup_unload_subsys(&net_cls_subsys); } module_init(init_cgroup_cls); -- cgit v1.3-14-g43fede From 86f8515f9721fa171483f0fe0391968fbb949cc9 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 29 Dec 2013 17:27:11 +0100 Subject: net: netprio: rename config to be more consistent with cgroup configs While we're at it and introduced CGROUP_NET_CLASSID, lets also make NETPRIO_CGROUP more consistent with the rest of cgroups and rename it into CONFIG_CGROUP_NET_PRIO so that for networking, we now have CONFIG_CGROUP_NET_{PRIO,CLASSID}. This not only makes the CONFIG option consistent among networking cgroups, but also among cgroups CONFIG conventions in general as the vast majority has a prefix of CONFIG_CGROUP_. Signed-off-by: Daniel Borkmann Cc: Zefan Li Cc: cgroups@vger.kernel.org Acked-by: Li Zefan Signed-off-by: Pablo Neira Ayuso --- include/linux/cgroup_subsys.h | 2 +- include/linux/netdevice.h | 2 +- include/net/netprio_cgroup.h | 18 ++++++------------ include/net/sock.h | 2 +- net/Kconfig | 4 ++-- net/core/Makefile | 2 +- net/core/dev.c | 2 +- net/core/sock.c | 2 +- 8 files changed, 14 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h index 58bf94de4b8e..7b99d717411d 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -43,7 +43,7 @@ SUBSYS(blkio) SUBSYS(perf) #endif -#if IS_SUBSYS_ENABLED(CONFIG_NETPRIO_CGROUP) +#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_NET_PRIO) SUBSYS(net_prio) #endif diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5260d2eae2e6..45cf68194aa8 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1444,7 +1444,7 @@ struct net_device { /* max exchange id for FCoE LRO by ddp */ unsigned int fcoe_ddp_xid; #endif -#if IS_ENABLED(CONFIG_NETPRIO_CGROUP) +#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) struct netprio_map __rcu *priomap; #endif /* phy device may attach itself for hardware timestamping */ diff --git a/include/net/netprio_cgroup.h b/include/net/netprio_cgroup.h index 099d02782e22..dafc09f0fdbc 100644 --- a/include/net/netprio_cgroup.h +++ b/include/net/netprio_cgroup.h @@ -13,12 +13,12 @@ #ifndef _NETPRIO_CGROUP_H #define _NETPRIO_CGROUP_H + #include #include #include - -#if IS_ENABLED(CONFIG_NETPRIO_CGROUP) +#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) struct netprio_map { struct rcu_head rcu; u32 priomap_len; @@ -27,8 +27,7 @@ struct netprio_map { void sock_update_netprioidx(struct sock *sk); -#if IS_BUILTIN(CONFIG_NETPRIO_CGROUP) - +#if IS_BUILTIN(CONFIG_CGROUP_NET_PRIO) static inline u32 task_netprioidx(struct task_struct *p) { struct cgroup_subsys_state *css; @@ -40,9 +39,7 @@ static inline u32 task_netprioidx(struct task_struct *p) rcu_read_unlock(); return idx; } - -#elif IS_MODULE(CONFIG_NETPRIO_CGROUP) - +#elif IS_MODULE(CONFIG_CGROUP_NET_PRIO) static inline u32 task_netprioidx(struct task_struct *p) { struct cgroup_subsys_state *css; @@ -56,9 +53,7 @@ static inline u32 task_netprioidx(struct task_struct *p) return idx; } #endif - -#else /* !CONFIG_NETPRIO_CGROUP */ - +#else /* !CONFIG_CGROUP_NET_PRIO */ static inline u32 task_netprioidx(struct task_struct *p) { return 0; @@ -66,6 +61,5 @@ static inline u32 task_netprioidx(struct task_struct *p) #define sock_update_netprioidx(sk) -#endif /* CONFIG_NETPRIO_CGROUP */ - +#endif /* CONFIG_CGROUP_NET_PRIO */ #endif /* _NET_CLS_CGROUP_H */ diff --git a/include/net/sock.h b/include/net/sock.h index 2ef3c3eca47a..ef5e2be6eaf3 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -395,7 +395,7 @@ struct sock { unsigned short sk_ack_backlog; unsigned short sk_max_ack_backlog; __u32 sk_priority; -#if IS_ENABLED(CONFIG_NETPRIO_CGROUP) +#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) __u32 sk_cgrp_prioidx; #endif struct pid *sk_peer_pid; diff --git a/net/Kconfig b/net/Kconfig index 7da10b830d70..e411046a62e3 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -238,12 +238,12 @@ config XPS depends on SMP default y -config NETPRIO_CGROUP +config CGROUP_NET_PRIO tristate "Network priority cgroup" depends on CGROUPS ---help--- Cgroup subsystem for use in assigning processes to network priorities on - a per-interface basis + a per-interface basis. config CGROUP_NET_CLASSID boolean "Network classid cgroup" diff --git a/net/core/Makefile b/net/core/Makefile index 4839a2796964..9628c20acff6 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -21,5 +21,5 @@ obj-$(CONFIG_FIB_RULES) += fib_rules.o obj-$(CONFIG_TRACEPOINTS) += net-traces.o obj-$(CONFIG_NET_DROP_MONITOR) += drop_monitor.o obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o -obj-$(CONFIG_NETPRIO_CGROUP) += netprio_cgroup.o +obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o diff --git a/net/core/dev.c b/net/core/dev.c index c95d664b2b42..888a79b2b8b9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2747,7 +2747,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, return rc; } -#if IS_ENABLED(CONFIG_NETPRIO_CGROUP) +#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) static void skb_update_prio(struct sk_buff *skb) { struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap); diff --git a/net/core/sock.c b/net/core/sock.c index 3f150729fb15..a29735c9a05d 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1308,7 +1308,7 @@ static void sk_prot_free(struct proto *prot, struct sock *sk) module_put(owner); } -#if IS_ENABLED(CONFIG_NETPRIO_CGROUP) +#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) void sock_update_netprioidx(struct sock *sk) { if (in_interrupt()) -- cgit v1.3-14-g43fede From 8f09898bf02fc24b7a525e9cfc78f38dcdf3a4eb Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Fri, 3 Jan 2014 09:17:14 -0800 Subject: socket: cleanups Namespace related cleaning * make cred_to_ucred static * remove unused sock_rmalloc function Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/socket.h | 2 -- include/net/sock.h | 2 -- net/core/sock.c | 21 ++------------------- 3 files changed, 2 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 445ef7519dc2..5d488a65ad20 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -305,8 +305,6 @@ struct ucred { /* IPX options */ #define IPX_TYPE 1 -extern void cred_to_ucred(struct pid *pid, const struct cred *cred, struct ucred *ucred); - extern int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov, int offset, int len); extern int csum_partial_copy_fromiovecend(unsigned char *kdata, diff --git a/include/net/sock.h b/include/net/sock.h index bd716b6996ff..8d9af66ccf2c 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1549,8 +1549,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority); struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority); -struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force, - gfp_t priority); void sock_wfree(struct sk_buff *skb); void skb_orphan_partial(struct sk_buff *skb); void sock_rfree(struct sk_buff *skb); diff --git a/net/core/sock.c b/net/core/sock.c index 5393b4b719d7..0358855576a8 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -925,8 +925,8 @@ set_rcvbuf: EXPORT_SYMBOL(sock_setsockopt); -void cred_to_ucred(struct pid *pid, const struct cred *cred, - struct ucred *ucred) +static void cred_to_ucred(struct pid *pid, const struct cred *cred, + struct ucred *ucred) { ucred->pid = pid_vnr(pid); ucred->uid = ucred->gid = -1; @@ -937,7 +937,6 @@ void cred_to_ucred(struct pid *pid, const struct cred *cred, ucred->gid = from_kgid_munged(current_ns, cred->egid); } } -EXPORT_SYMBOL_GPL(cred_to_ucred); int sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) @@ -1665,22 +1664,6 @@ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, } EXPORT_SYMBOL(sock_wmalloc); -/* - * Allocate a skb from the socket's receive buffer. - */ -struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force, - gfp_t priority) -{ - if (force || atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) { - struct sk_buff *skb = alloc_skb(size, priority); - if (skb) { - skb_set_owner_r(skb, sk); - return skb; - } - } - return NULL; -} - /* * Allocate a memory block from the socket's option memory buffer. */ -- cgit v1.3-14-g43fede From 4017b4d3212b7b9d979d7174cbe340c9acbb4666 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Sun, 5 Jan 2014 03:20:17 +0300 Subject: : coding style fixes Running 'checkpatch.pl' gives some errors and warnings: - no spaces around =; - * separated by space from the function name; - { in function definition not on a separate line; - line over 80 characters. While fixing these, also fix the following style issues: - file name in the heading comment; - alignment not matching open paren. Signed-off-by: Sergei Shtylyov Signed-off-by: David S. Miller --- include/linux/phy.h | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 73384ff3b5e5..d4cb756a41c5 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1,6 +1,4 @@ /* - * include/linux/phy.h - * * Framework and drivers for configuring and reading different PHYs * Based on code in sungem_phy.c and gianfar_phy.c * @@ -240,7 +238,7 @@ int mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val); * - phy_stop moves to HALTED */ enum phy_state { - PHY_DOWN=0, + PHY_DOWN = 0, PHY_STARTING, PHY_READY, PHY_PENDING, @@ -544,21 +542,22 @@ static inline bool phy_is_internal(struct phy_device *phydev) } struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id, - bool is_c45, struct phy_c45_device_ids *c45_ids); + bool is_c45, + struct phy_c45_device_ids *c45_ids); struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); int phy_init_hw(struct phy_device *phydev); int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); -struct phy_device * phy_attach(struct net_device *dev, - const char *bus_id, phy_interface_t interface); +struct phy_device *phy_attach(struct net_device *dev, const char *bus_id, + phy_interface_t interface); struct phy_device *phy_find_first(struct mii_bus *bus); int phy_connect_direct(struct net_device *dev, struct phy_device *phydev, - void (*handler)(struct net_device *), - phy_interface_t interface); -struct phy_device * phy_connect(struct net_device *dev, const char *bus_id, - void (*handler)(struct net_device *), - phy_interface_t interface); + void (*handler)(struct net_device *), + phy_interface_t interface); +struct phy_device *phy_connect(struct net_device *dev, const char *bus_id, + void (*handler)(struct net_device *), + phy_interface_t interface); void phy_disconnect(struct phy_device *phydev); void phy_detach(struct phy_device *phydev); void phy_start(struct phy_device *phydev); @@ -567,7 +566,8 @@ int phy_start_aneg(struct phy_device *phydev); int phy_stop_interrupts(struct phy_device *phydev); -static inline int phy_read_status(struct phy_device *phydev) { +static inline int phy_read_status(struct phy_device *phydev) +{ return phydev->drv->read_status(phydev); } @@ -586,22 +586,21 @@ void phy_state_machine(struct work_struct *work); void phy_change(struct work_struct *work); void phy_mac_interrupt(struct phy_device *phydev, int new_link); void phy_start_machine(struct phy_device *phydev, - void (*handler)(struct net_device *)); + void (*handler)(struct net_device *)); void phy_stop_machine(struct phy_device *phydev); int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd); int phy_ethtool_gset(struct phy_device *phydev, struct ethtool_cmd *cmd); -int phy_mii_ioctl(struct phy_device *phydev, - struct ifreq *ifr, int cmd); +int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd); int phy_start_interrupts(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); void phy_device_free(struct phy_device *phydev); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, - int (*run)(struct phy_device *)); + int (*run)(struct phy_device *)); int phy_register_fixup_for_id(const char *bus_id, - int (*run)(struct phy_device *)); + int (*run)(struct phy_device *)); int phy_register_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask, - int (*run)(struct phy_device *)); + int (*run)(struct phy_device *)); int phy_scan_fixups(struct phy_device *phydev); int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable); @@ -609,7 +608,8 @@ int phy_get_eee_err(struct phy_device *phydev); int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data); int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_eee *data); int phy_ethtool_set_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol); -void phy_ethtool_get_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol); +void phy_ethtool_get_wol(struct phy_device *phydev, + struct ethtool_wolinfo *wol); int __init mdio_bus_init(void); void mdio_bus_exit(void); -- cgit v1.3-14-g43fede From 29935aebc7a8f2d3f9cc1743f24f0db8b4610ece Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Sun, 5 Jan 2014 03:27:17 +0300 Subject: phylib: remove unused adjust_state() callback Remove adjust_state() callback from 'struct phy_device' since it seems to have never been really used from the inception: phy_start_machine() has been always called with 2nd argument equal to NULL. Signed-off-by: Sergei Shtylyov Signed-off-by: David S. Miller --- drivers/net/phy/mdio_bus.c | 4 ++-- drivers/net/phy/phy.c | 17 +++-------------- drivers/net/phy/phy_device.c | 2 +- include/linux/phy.h | 7 +------ 4 files changed, 7 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 0ca0dfecd153..930694d3a13f 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -379,7 +379,7 @@ static int mdio_bus_resume(struct device *dev) no_resume: if (phydev->attached_dev && phydev->adjust_link) - phy_start_machine(phydev, NULL); + phy_start_machine(phydev); return 0; } @@ -401,7 +401,7 @@ static int mdio_bus_restore(struct device *dev) phydev->link = 0; phydev->state = PHY_UP; - phy_start_machine(phydev, NULL); + phy_start_machine(phydev); return 0; } diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 4e6dcc1cc237..19da5ab615bd 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -406,21 +406,15 @@ EXPORT_SYMBOL(phy_start_aneg); /** * phy_start_machine - start PHY state machine tracking * @phydev: the phy_device struct - * @handler: callback function for state change notifications * * Description: The PHY infrastructure can run a state machine * which tracks whether the PHY is starting up, negotiating, * etc. This function starts the timer which tracks the state - * of the PHY. If you want to be notified when the state changes, - * pass in the callback @handler, otherwise, pass NULL. If you - * want to maintain your own state machine, do not call this - * function. + * of the PHY. If you want to maintain your own state machine, + * do not call this function. */ -void phy_start_machine(struct phy_device *phydev, - void (*handler)(struct net_device *)) +void phy_start_machine(struct phy_device *phydev) { - phydev->adjust_state = handler; - queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, HZ); } @@ -440,8 +434,6 @@ void phy_stop_machine(struct phy_device *phydev) if (phydev->state > PHY_UP) phydev->state = PHY_UP; mutex_unlock(&phydev->lock); - - phydev->adjust_state = NULL; } /** @@ -706,9 +698,6 @@ void phy_state_machine(struct work_struct *work) mutex_lock(&phydev->lock); - if (phydev->adjust_state) - phydev->adjust_state(phydev->attached_dev); - switch (phydev->state) { case PHY_DOWN: case PHY_STARTING: diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 1f1f8d77aa6a..09aa9e564296 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -422,7 +422,7 @@ int phy_connect_direct(struct net_device *dev, struct phy_device *phydev, return rc; phy_prepare_link(phydev, handler); - phy_start_machine(phydev, NULL); + phy_start_machine(phydev); if (phydev->irq > 0) phy_start_interrupts(phydev); diff --git a/include/linux/phy.h b/include/linux/phy.h index d4cb756a41c5..cf1bb480cfb1 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -282,8 +282,6 @@ struct phy_c45_device_ids { * attached_dev: The attached enet driver's device instance ptr * adjust_link: Callback for the enet controller to respond to * changes in the link state. - * adjust_state: Callback for the enet driver to respond to - * changes in the state machine. * * speed, duplex, pause, supported, advertising, lp_advertising, * and autoneg are used like in mii_if_info @@ -364,8 +362,6 @@ struct phy_device { struct net_device *attached_dev; void (*adjust_link)(struct net_device *dev); - - void (*adjust_state)(struct net_device *dev); }; #define to_phy_device(d) container_of(d, struct phy_device, dev) @@ -585,8 +581,7 @@ int phy_drivers_register(struct phy_driver *new_driver, int n); void phy_state_machine(struct work_struct *work); void phy_change(struct work_struct *work); void phy_mac_interrupt(struct phy_device *phydev, int new_link); -void phy_start_machine(struct phy_device *phydev, - void (*handler)(struct net_device *)); +void phy_start_machine(struct phy_device *phydev); void phy_stop_machine(struct phy_device *phydev); int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd); int phy_ethtool_gset(struct phy_device *phydev, struct ethtool_cmd *cmd); -- cgit v1.3-14-g43fede From fbfcec635dba38345a446f44b22352cd96ad9463 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Sun, 5 Jan 2014 03:28:27 +0300 Subject: phylib: make phy_scan_fixups() static phy_scan_fixups() isn't and shouldn't be called by the drivers directly, so unexport it. And since Florian Fainelli's recent patches, the function is only called locally, so we can make it static as well. Signed-off-by: Sergei Shtylyov Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 3 +-- include/linux/phy.h | 1 - 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 09aa9e564296..5d81c89ee52b 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -122,7 +122,7 @@ static int phy_needs_fixup(struct phy_device *phydev, struct phy_fixup *fixup) } /* Runs any matching fixups for this phydev */ -int phy_scan_fixups(struct phy_device *phydev) +static int phy_scan_fixups(struct phy_device *phydev) { struct phy_fixup *fixup; @@ -141,7 +141,6 @@ int phy_scan_fixups(struct phy_device *phydev) return 0; } -EXPORT_SYMBOL(phy_scan_fixups); struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id, bool is_c45, diff --git a/include/linux/phy.h b/include/linux/phy.h index cf1bb480cfb1..7c81dd8870d4 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -596,7 +596,6 @@ int phy_register_fixup_for_id(const char *bus_id, int (*run)(struct phy_device *)); int phy_register_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); -int phy_scan_fixups(struct phy_device *phydev); int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable); int phy_get_eee_err(struct phy_device *phydev); -- cgit v1.3-14-g43fede From 8f84985fec10de64a6b4cdfea45f2b0ab8f07c78 Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Sat, 4 Jan 2014 13:57:59 +0800 Subject: net: unify the pcpu_tstats and br_cpu_netstats as one They are same, so unify them as one, pcpu_sw_netstats. Define pcpu_sw_netstat in netdevice.h, remove pcpu_tstats from if_tunnel and remove br_cpu_netstats from br_private.h Cc: Cong Wang Cc: Stephen Hemminger Signed-off-by: Li RongQing Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 11 ++++++----- include/linux/if_tunnel.h | 9 --------- include/linux/netdevice.h | 11 ++++++++++- include/net/ip6_tunnel.h | 2 +- include/net/ip_tunnels.h | 4 ++-- net/bridge/br_device.c | 10 +++++----- net/bridge/br_input.c | 2 +- net/bridge/br_private.h | 10 +--------- net/ipv4/ip_tunnel.c | 9 +++++---- net/ipv4/ip_vti.c | 2 +- net/ipv6/ip6_gre.c | 10 +++++----- net/ipv6/ip6_tunnel.c | 12 ++++++------ net/ipv6/ip6_vti.c | 10 +++++----- net/ipv6/sit.c | 10 +++++----- net/openvswitch/vport.c | 12 ++++++------ net/openvswitch/vport.h | 2 +- 16 files changed, 60 insertions(+), 66 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index aef44aa44fe3..474a99ed0222 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1081,7 +1081,7 @@ static void vxlan_rcv(struct vxlan_sock *vs, struct iphdr *oip = NULL; struct ipv6hdr *oip6 = NULL; struct vxlan_dev *vxlan; - struct pcpu_tstats *stats; + struct pcpu_sw_netstats *stats; union vxlan_addr saddr; __u32 vni; int err = 0; @@ -1587,11 +1587,12 @@ EXPORT_SYMBOL_GPL(vxlan_xmit_skb); static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, struct vxlan_dev *dst_vxlan) { - struct pcpu_tstats *tx_stats = this_cpu_ptr(src_vxlan->dev->tstats); - struct pcpu_tstats *rx_stats = this_cpu_ptr(dst_vxlan->dev->tstats); + struct pcpu_sw_netstats *tx_stats, *rx_stats; union vxlan_addr loopback; union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip; + tx_stats = this_cpu_ptr(src_vxlan->dev->tstats); + rx_stats = this_cpu_ptr(dst_vxlan->dev->tstats); skb->pkt_type = PACKET_HOST; skb->encapsulation = 0; skb->dev = dst_vxlan->dev; @@ -1897,12 +1898,12 @@ static int vxlan_init(struct net_device *dev) struct vxlan_sock *vs; int i; - dev->tstats = alloc_percpu(struct pcpu_tstats); + dev->tstats = alloc_percpu(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; for_each_possible_cpu(i) { - struct pcpu_tstats *vxlan_stats; + struct pcpu_sw_netstats *vxlan_stats; vxlan_stats = per_cpu_ptr(dev->tstats, i); u64_stats_init(&vxlan_stats->syncp); } diff --git a/include/linux/if_tunnel.h b/include/linux/if_tunnel.h index f4e56ecd0b1a..712710bc0580 100644 --- a/include/linux/if_tunnel.h +++ b/include/linux/if_tunnel.h @@ -13,13 +13,4 @@ #define for_each_ip_tunnel_rcu(pos, start) \ for (pos = rcu_dereference(start); pos; pos = rcu_dereference(pos->next)) -/* often modified stats are per cpu, other are shared (netdev->stats) */ -struct pcpu_tstats { - u64 rx_packets; - u64 rx_bytes; - u64 tx_packets; - u64 tx_bytes; - struct u64_stats_sync syncp; -}; - #endif /* _IF_TUNNEL_H_ */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index bec60c481966..51c0fe258163 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1409,7 +1409,7 @@ struct net_device { union { void *ml_priv; struct pcpu_lstats __percpu *lstats; /* loopback stats */ - struct pcpu_tstats __percpu *tstats; /* tunnel stats */ + struct pcpu_sw_netstats __percpu *tstats; struct pcpu_dstats __percpu *dstats; /* dummy stats */ struct pcpu_vstats __percpu *vstats; /* veth stats */ }; @@ -1685,6 +1685,15 @@ struct packet_offload { struct list_head list; }; +/* often modified stats are per cpu, other are shared (netdev->stats) */ +struct pcpu_sw_netstats { + u64 rx_packets; + u64 rx_bytes; + u64 tx_packets; + u64 tx_bytes; + struct u64_stats_sync syncp; +}; + #include /* netdevice notifier chain. Please remember to update the rtnetlink diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 6d1549c4893c..a5593dab6af7 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -79,7 +79,7 @@ static inline void ip6tunnel_xmit(struct sk_buff *skb, struct net_device *dev) err = ip6_local_out(skb); if (net_xmit_eval(err) == 0) { - struct pcpu_tstats *tstats = this_cpu_ptr(dev->tstats); + struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); tstats->tx_bytes += pkt_len; tstats->tx_packets++; diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 9e25b1bc31da..cd729becbb07 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -162,10 +162,10 @@ struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, bool gre_csum, static inline void iptunnel_xmit_stats(int err, struct net_device_stats *err_stats, - struct pcpu_tstats __percpu *stats) + struct pcpu_sw_netstats __percpu *stats) { if (err > 0) { - struct pcpu_tstats *tstats = this_cpu_ptr(stats); + struct pcpu_sw_netstats *tstats = this_cpu_ptr(stats); u64_stats_update_begin(&tstats->syncp); tstats->tx_bytes += err; diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index f00cfd2a0143..e4401a531afb 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -32,7 +32,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) const unsigned char *dest = skb->data; struct net_bridge_fdb_entry *dst; struct net_bridge_mdb_entry *mdst; - struct br_cpu_netstats *brstats = this_cpu_ptr(br->stats); + struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats); u16 vid = 0; rcu_read_lock(); @@ -90,12 +90,12 @@ static int br_dev_init(struct net_device *dev) struct net_bridge *br = netdev_priv(dev); int i; - br->stats = alloc_percpu(struct br_cpu_netstats); + br->stats = alloc_percpu(struct pcpu_sw_netstats); if (!br->stats) return -ENOMEM; for_each_possible_cpu(i) { - struct br_cpu_netstats *br_dev_stats; + struct pcpu_sw_netstats *br_dev_stats; br_dev_stats = per_cpu_ptr(br->stats, i); u64_stats_init(&br_dev_stats->syncp); } @@ -135,12 +135,12 @@ static struct rtnl_link_stats64 *br_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct net_bridge *br = netdev_priv(dev); - struct br_cpu_netstats tmp, sum = { 0 }; + struct pcpu_sw_netstats tmp, sum = { 0 }; unsigned int cpu; for_each_possible_cpu(cpu) { unsigned int start; - const struct br_cpu_netstats *bstats + const struct pcpu_sw_netstats *bstats = per_cpu_ptr(br->stats, cpu); do { start = u64_stats_fetch_begin_bh(&bstats->syncp); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 7e73c32e205d..bf8dc7d308d6 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -28,7 +28,7 @@ static int br_pass_frame_up(struct sk_buff *skb) { struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev; struct net_bridge *br = netdev_priv(brdev); - struct br_cpu_netstats *brstats = this_cpu_ptr(br->stats); + struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats); u64_stats_update_begin(&brstats->syncp); brstats->rx_packets++; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 2e77d923c8ee..3733f152351c 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -210,21 +210,13 @@ static inline struct net_bridge_port *br_port_get_rtnl(const struct net_device * rtnl_dereference(dev->rx_handler_data) : NULL; } -struct br_cpu_netstats { - u64 rx_packets; - u64 rx_bytes; - u64 tx_packets; - u64 tx_bytes; - struct u64_stats_sync syncp; -}; - struct net_bridge { spinlock_t lock; struct list_head port_list; struct net_device *dev; - struct br_cpu_netstats __percpu *stats; + struct pcpu_sw_netstats __percpu *stats; spinlock_t hash_lock; struct hlist_head hash[BR_HASH_SIZE]; #ifdef CONFIG_BRIDGE_NETFILTER diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index e2c9cff26eb5..07a5ed374262 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -132,7 +132,8 @@ struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev, int i; for_each_possible_cpu(i) { - const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i); + const struct pcpu_sw_netstats *tstats = + per_cpu_ptr(dev->tstats, i); u64 rx_packets, rx_bytes, tx_packets, tx_bytes; unsigned int start; @@ -460,7 +461,7 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net, int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, const struct tnl_ptk_info *tpi, bool log_ecn_error) { - struct pcpu_tstats *tstats; + struct pcpu_sw_netstats *tstats; const struct iphdr *iph = ip_hdr(skb); int err; @@ -1049,12 +1050,12 @@ int ip_tunnel_init(struct net_device *dev) int i, err; dev->destructor = ip_tunnel_dev_free; - dev->tstats = alloc_percpu(struct pcpu_tstats); + dev->tstats = alloc_percpu(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; for_each_possible_cpu(i) { - struct pcpu_tstats *ipt_stats; + struct pcpu_sw_netstats *ipt_stats; ipt_stats = per_cpu_ptr(dev->tstats, i); u64_stats_init(&ipt_stats->syncp); } diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 52b802a0cd8c..0783200ad8d2 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -60,7 +60,7 @@ static int vti_rcv(struct sk_buff *skb) tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, iph->saddr, iph->daddr, 0); if (tunnel != NULL) { - struct pcpu_tstats *tstats; + struct pcpu_sw_netstats *tstats; u32 oldmark = skb->mark; int ret; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index e27fb78c61f2..e7a440dd5c0d 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -498,7 +498,7 @@ static int ip6gre_rcv(struct sk_buff *skb) &ipv6h->saddr, &ipv6h->daddr, key, gre_proto); if (tunnel) { - struct pcpu_tstats *tstats; + struct pcpu_sw_netstats *tstats; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; @@ -1265,12 +1265,12 @@ static int ip6gre_tunnel_init(struct net_device *dev) if (ipv6_addr_any(&tunnel->parms.raddr)) dev->header_ops = &ip6gre_header_ops; - dev->tstats = alloc_percpu(struct pcpu_tstats); + dev->tstats = alloc_percpu(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; for_each_possible_cpu(i) { - struct pcpu_tstats *ip6gre_tunnel_stats; + struct pcpu_sw_netstats *ip6gre_tunnel_stats; ip6gre_tunnel_stats = per_cpu_ptr(dev->tstats, i); u64_stats_init(&ip6gre_tunnel_stats->syncp); } @@ -1466,12 +1466,12 @@ static int ip6gre_tap_init(struct net_device *dev) ip6gre_tnl_link_config(tunnel, 1); - dev->tstats = alloc_percpu(struct pcpu_tstats); + dev->tstats = alloc_percpu(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; for_each_possible_cpu(i) { - struct pcpu_tstats *ip6gre_tap_stats; + struct pcpu_sw_netstats *ip6gre_tap_stats; ip6gre_tap_stats = per_cpu_ptr(dev->tstats, i); u64_stats_init(&ip6gre_tap_stats->syncp); } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 8d7c9867a445..02894216a46d 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -29,7 +29,6 @@ #include #include #include -#include #include #include #include @@ -102,11 +101,12 @@ struct ip6_tnl_net { static struct net_device_stats *ip6_get_stats(struct net_device *dev) { - struct pcpu_tstats sum = { 0 }; + struct pcpu_sw_netstats sum = { 0 }; int i; for_each_possible_cpu(i) { - const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i); + const struct pcpu_sw_netstats *tstats = + per_cpu_ptr(dev->tstats, i); sum.rx_packets += tstats->rx_packets; sum.rx_bytes += tstats->rx_bytes; @@ -784,7 +784,7 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, if ((t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr)) != NULL) { - struct pcpu_tstats *tstats; + struct pcpu_sw_netstats *tstats; if (t->parms.proto != ipproto && t->parms.proto != 0) { rcu_read_unlock(); @@ -1497,12 +1497,12 @@ ip6_tnl_dev_init_gen(struct net_device *dev) t->dev = dev; t->net = dev_net(dev); - dev->tstats = alloc_percpu(struct pcpu_tstats); + dev->tstats = alloc_percpu(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; for_each_possible_cpu(i) { - struct pcpu_tstats *ip6_tnl_stats; + struct pcpu_sw_netstats *ip6_tnl_stats; ip6_tnl_stats = per_cpu_ptr(dev->tstats, i); u64_stats_init(&ip6_tnl_stats->syncp); } diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index ed94ba61dda0..da1d9e4d62ca 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -24,7 +24,6 @@ #include #include #include -#include #include #include #include @@ -77,11 +76,12 @@ struct vti6_net { static struct net_device_stats *vti6_get_stats(struct net_device *dev) { - struct pcpu_tstats sum = { 0 }; + struct pcpu_sw_netstats sum = { 0 }; int i; for_each_possible_cpu(i) { - const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i); + const struct pcpu_sw_netstats *tstats = + per_cpu_ptr(dev->tstats, i); sum.rx_packets += tstats->rx_packets; sum.rx_bytes += tstats->rx_bytes; @@ -312,7 +312,7 @@ static int vti6_rcv(struct sk_buff *skb) if ((t = vti6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr)) != NULL) { - struct pcpu_tstats *tstats; + struct pcpu_sw_netstats *tstats; if (t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) { rcu_read_unlock(); @@ -753,7 +753,7 @@ static inline int vti6_dev_init_gen(struct net_device *dev) t->dev = dev; t->net = dev_net(dev); - dev->tstats = alloc_percpu(struct pcpu_tstats); + dev->tstats = alloc_percpu(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; return 0; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 366fbba3359a..9937b2616713 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -671,7 +671,7 @@ static int ipip6_rcv(struct sk_buff *skb) tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->saddr, iph->daddr); if (tunnel != NULL) { - struct pcpu_tstats *tstats; + struct pcpu_sw_netstats *tstats; if (tunnel->parms.iph.protocol != IPPROTO_IPV6 && tunnel->parms.iph.protocol != 0) @@ -1361,12 +1361,12 @@ static int ipip6_tunnel_init(struct net_device *dev) memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); ipip6_tunnel_bind_dev(dev); - dev->tstats = alloc_percpu(struct pcpu_tstats); + dev->tstats = alloc_percpu(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; for_each_possible_cpu(i) { - struct pcpu_tstats *ipip6_tunnel_stats; + struct pcpu_sw_netstats *ipip6_tunnel_stats; ipip6_tunnel_stats = per_cpu_ptr(dev->tstats, i); u64_stats_init(&ipip6_tunnel_stats->syncp); } @@ -1391,12 +1391,12 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) iph->ihl = 5; iph->ttl = 64; - dev->tstats = alloc_percpu(struct pcpu_tstats); + dev->tstats = alloc_percpu(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; for_each_possible_cpu(i) { - struct pcpu_tstats *ipip6_fb_stats; + struct pcpu_sw_netstats *ipip6_fb_stats; ipip6_fb_stats = per_cpu_ptr(dev->tstats, i); u64_stats_init(&ipip6_fb_stats->syncp); } diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index d830a95f03a4..f5275dd29cd9 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -136,14 +136,14 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops, vport->ops = ops; INIT_HLIST_NODE(&vport->dp_hash_node); - vport->percpu_stats = alloc_percpu(struct pcpu_tstats); + vport->percpu_stats = alloc_percpu(struct pcpu_sw_netstats); if (!vport->percpu_stats) { kfree(vport); return ERR_PTR(-ENOMEM); } for_each_possible_cpu(i) { - struct pcpu_tstats *vport_stats; + struct pcpu_sw_netstats *vport_stats; vport_stats = per_cpu_ptr(vport->percpu_stats, i); u64_stats_init(&vport_stats->syncp); } @@ -275,8 +275,8 @@ void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats) spin_unlock_bh(&vport->stats_lock); for_each_possible_cpu(i) { - const struct pcpu_tstats *percpu_stats; - struct pcpu_tstats local_stats; + const struct pcpu_sw_netstats *percpu_stats; + struct pcpu_sw_netstats local_stats; unsigned int start; percpu_stats = per_cpu_ptr(vport->percpu_stats, i); @@ -344,7 +344,7 @@ int ovs_vport_get_options(const struct vport *vport, struct sk_buff *skb) void ovs_vport_receive(struct vport *vport, struct sk_buff *skb, struct ovs_key_ipv4_tunnel *tun_key) { - struct pcpu_tstats *stats; + struct pcpu_sw_netstats *stats; stats = this_cpu_ptr(vport->percpu_stats); u64_stats_update_begin(&stats->syncp); @@ -370,7 +370,7 @@ int ovs_vport_send(struct vport *vport, struct sk_buff *skb) int sent = vport->ops->send(vport, skb); if (likely(sent > 0)) { - struct pcpu_tstats *stats; + struct pcpu_sw_netstats *stats; stats = this_cpu_ptr(vport->percpu_stats); diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h index 1a9fbcec6e1b..bc97ef7fa2af 100644 --- a/net/openvswitch/vport.h +++ b/net/openvswitch/vport.h @@ -87,7 +87,7 @@ struct vport { struct hlist_node dp_hash_node; const struct vport_ops *ops; - struct pcpu_tstats __percpu *percpu_stats; + struct pcpu_sw_netstats __percpu *percpu_stats; spinlock_t stats_lock; struct vport_err_stats err_stats; -- cgit v1.3-14-g43fede From cdf3e274cf1b36e9a2fef2d175cabc566af841b2 Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Sat, 4 Jan 2014 14:22:34 +0800 Subject: macvlan: unify macvlan_pcpu_stats and vlan_pcpu_stats They are same, so unify them as one; since macvlan is a kind of vlan, vlan_pcpu_stats should be a proper name for vlan and macvlan. Signed-off-by: Li RongQing Signed-off-by: David S. Miller --- drivers/net/macvlan.c | 8 ++++---- include/linux/if_macvlan.h | 27 +++------------------------ 2 files changed, 7 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 10406dbc35b3..94198366de7f 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -305,7 +305,7 @@ static netdev_tx_t macvlan_start_xmit(struct sk_buff *skb, } if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { - struct macvlan_pcpu_stats *pcpu_stats; + struct vlan_pcpu_stats *pcpu_stats; pcpu_stats = this_cpu_ptr(vlan->pcpu_stats); u64_stats_update_begin(&pcpu_stats->syncp); @@ -545,12 +545,12 @@ static int macvlan_init(struct net_device *dev) macvlan_set_lockdep_class(dev); - vlan->pcpu_stats = alloc_percpu(struct macvlan_pcpu_stats); + vlan->pcpu_stats = alloc_percpu(struct vlan_pcpu_stats); if (!vlan->pcpu_stats) return -ENOMEM; for_each_possible_cpu(i) { - struct macvlan_pcpu_stats *mvlstats; + struct vlan_pcpu_stats *mvlstats; mvlstats = per_cpu_ptr(vlan->pcpu_stats, i); u64_stats_init(&mvlstats->syncp); } @@ -576,7 +576,7 @@ static struct rtnl_link_stats64 *macvlan_dev_get_stats64(struct net_device *dev, struct macvlan_dev *vlan = netdev_priv(dev); if (vlan->pcpu_stats) { - struct macvlan_pcpu_stats *p; + struct vlan_pcpu_stats *p; u64 rx_packets, rx_bytes, rx_multicast, tx_packets, tx_bytes; u32 rx_errors = 0, tx_dropped = 0; unsigned int start; diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 551bdd3722a2..7c8b20b120ea 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -2,6 +2,7 @@ #define _LINUX_IF_MACVLAN_H #include +#include #include #include #include @@ -24,28 +25,6 @@ static inline struct socket *macvtap_get_socket(struct file *f) struct macvlan_port; struct macvtap_queue; -/** - * struct macvlan_pcpu_stats - MACVLAN percpu stats - * @rx_packets: number of received packets - * @rx_bytes: number of received bytes - * @rx_multicast: number of received multicast packets - * @tx_packets: number of transmitted packets - * @tx_bytes: number of transmitted bytes - * @syncp: synchronization point for 64bit counters - * @rx_errors: number of rx errors - * @tx_dropped: number of tx dropped packets - */ -struct macvlan_pcpu_stats { - u64 rx_packets; - u64 rx_bytes; - u64 rx_multicast; - u64 tx_packets; - u64 tx_bytes; - struct u64_stats_sync syncp; - u32 rx_errors; - u32 tx_dropped; -}; - /* * Maximum times a macvtap device can be opened. This can be used to * configure the number of receive queue, e.g. for multiqueue virtio. @@ -62,7 +41,7 @@ struct macvlan_dev { struct macvlan_port *port; struct net_device *lowerdev; void *fwd_priv; - struct macvlan_pcpu_stats __percpu *pcpu_stats; + struct vlan_pcpu_stats __percpu *pcpu_stats; DECLARE_BITMAP(mc_filter, MACVLAN_MC_FILTER_SZ); @@ -84,7 +63,7 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan, bool multicast) { if (likely(success)) { - struct macvlan_pcpu_stats *pcpu_stats; + struct vlan_pcpu_stats *pcpu_stats; pcpu_stats = this_cpu_ptr(vlan->pcpu_stats); u64_stats_update_begin(&pcpu_stats->syncp); -- cgit v1.3-14-g43fede From b2395b8aeaa2f181ee87f5840c6268992b30ed95 Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Sun, 5 Jan 2014 01:10:43 +0100 Subject: bcma: export bcma_find_core_unit() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This function is used to get a specific core when there is more than one core of that specific type. This is used in bgmac to reset all GMAC cores. Signed-off-by: Hauke Mehrtens Acked-by: Rafał Miłecki Signed-off-by: David S. Miller --- drivers/bcma/bcma_private.h | 2 -- drivers/bcma/main.c | 13 +------------ include/linux/bcma/bcma.h | 9 ++++++++- 3 files changed, 9 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/bcma/bcma_private.h b/drivers/bcma/bcma_private.h index 0215f9ad755c..09b632ad0fe2 100644 --- a/drivers/bcma/bcma_private.h +++ b/drivers/bcma/bcma_private.h @@ -33,8 +33,6 @@ int __init bcma_bus_early_register(struct bcma_bus *bus, int bcma_bus_suspend(struct bcma_bus *bus); int bcma_bus_resume(struct bcma_bus *bus); #endif -struct bcma_device *bcma_find_core_unit(struct bcma_bus *bus, u16 coreid, - u8 unit); /* scan.c */ int bcma_bus_scan(struct bcma_bus *bus); diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c index 5a9f6bdc88f1..34ea4c588d36 100644 --- a/drivers/bcma/main.c +++ b/drivers/bcma/main.c @@ -78,18 +78,6 @@ static u16 bcma_cc_core_id(struct bcma_bus *bus) return BCMA_CORE_CHIPCOMMON; } -struct bcma_device *bcma_find_core(struct bcma_bus *bus, u16 coreid) -{ - struct bcma_device *core; - - list_for_each_entry(core, &bus->cores, list) { - if (core->id.id == coreid) - return core; - } - return NULL; -} -EXPORT_SYMBOL_GPL(bcma_find_core); - struct bcma_device *bcma_find_core_unit(struct bcma_bus *bus, u16 coreid, u8 unit) { @@ -101,6 +89,7 @@ struct bcma_device *bcma_find_core_unit(struct bcma_bus *bus, u16 coreid, } return NULL; } +EXPORT_SYMBOL_GPL(bcma_find_core_unit); bool bcma_wait_value(struct bcma_device *core, u16 reg, u32 mask, u32 value, int timeout) diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 4d043c30216f..0b3bb16c705a 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -418,7 +418,14 @@ static inline void bcma_maskset16(struct bcma_device *cc, bcma_write16(cc, offset, (bcma_read16(cc, offset) & mask) | set); } -extern struct bcma_device *bcma_find_core(struct bcma_bus *bus, u16 coreid); +extern struct bcma_device *bcma_find_core_unit(struct bcma_bus *bus, u16 coreid, + u8 unit); +static inline struct bcma_device *bcma_find_core(struct bcma_bus *bus, + u16 coreid) +{ + return bcma_find_core_unit(bus, coreid, 0); +} + extern bool bcma_core_is_enabled(struct bcma_device *core); extern void bcma_core_disable(struct bcma_device *core, u32 flags); extern int bcma_core_enable(struct bcma_device *core, u32 flags); -- cgit v1.3-14-g43fede From 1e85c9b66d86a776e78c332d5d32ae370ab84d3f Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Mon, 6 Jan 2014 01:41:20 +0100 Subject: 8021q: make vlan_pcpu_stats visible without CONFIG_VLAN_8021Q macvlan needs vlan_pcpu_stats so make it visible even if compiling without VLAN_8021Q support. Otherwise a very long compiler error happens. Fixes: cdf3e274cf1b36 ("macvlan: unify macvlan_pcpu_stats and vlan_pcpu_stats") Cc: Li RongQing Signed-off-by: Hannes Frederic Sowa Acked-By: Li RongQing Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index f252deb99454..bbedfb56bd66 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -82,25 +82,6 @@ static inline int is_vlan_dev(struct net_device *dev) #define vlan_tx_tag_get(__skb) ((__skb)->vlan_tci & ~VLAN_TAG_PRESENT) #define vlan_tx_tag_get_id(__skb) ((__skb)->vlan_tci & VLAN_VID_MASK) -#if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) - -extern struct net_device *__vlan_find_dev_deep(struct net_device *real_dev, - __be16 vlan_proto, u16 vlan_id); -extern struct net_device *vlan_dev_real_dev(const struct net_device *dev); -extern u16 vlan_dev_vlan_id(const struct net_device *dev); - -/** - * struct vlan_priority_tci_mapping - vlan egress priority mappings - * @priority: skb priority - * @vlan_qos: vlan priority: (skb->priority << 13) & 0xE000 - * @next: pointer to next struct - */ -struct vlan_priority_tci_mapping { - u32 priority; - u16 vlan_qos; - struct vlan_priority_tci_mapping *next; -}; - /** * struct vlan_pcpu_stats - VLAN percpu rx/tx stats * @rx_packets: number of received packets @@ -123,6 +104,25 @@ struct vlan_pcpu_stats { u32 tx_dropped; }; +#if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) + +extern struct net_device *__vlan_find_dev_deep(struct net_device *real_dev, + __be16 vlan_proto, u16 vlan_id); +extern struct net_device *vlan_dev_real_dev(const struct net_device *dev); +extern u16 vlan_dev_vlan_id(const struct net_device *dev); + +/** + * struct vlan_priority_tci_mapping - vlan egress priority mappings + * @priority: skb priority + * @vlan_qos: vlan priority: (skb->priority << 13) & 0xE000 + * @next: pointer to next struct + */ +struct vlan_priority_tci_mapping { + u32 priority; + u16 vlan_qos; + struct vlan_priority_tci_mapping *next; +}; + struct proc_dir_entry; struct netpoll; -- cgit v1.3-14-g43fede From 6e08d757b72f280c45cfec61e63216adb419e2dd Mon Sep 17 00:00:00 2001 From: Arend van Spriel Date: Mon, 6 Jan 2014 12:40:50 +0100 Subject: mmc: add SDIO identifiers for Broadcom WLAN devices The SDIO identifier for Broadcom WLAN devices were defined in the brcmfmac SDIO driver. Moving the definitions in MMC header file seems common sense. Reviewed-by: Hante Meuleman Reviewed-by: Pieter-Paul Giesberts Signed-off-by: Arend van Spriel Signed-off-by: John W. Linville --- drivers/net/wireless/brcm80211/brcmfmac/bcmsdh.c | 2 -- drivers/net/wireless/brcm80211/brcmfmac/sdio_chip.c | 1 + drivers/net/wireless/brcm80211/brcmfmac/sdio_chip.h | 8 -------- include/linux/mmc/sdio_ids.h | 9 +++++++++ 4 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh.c index 07015e198b3c..68dd999df98e 100644 --- a/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh.c +++ b/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh.c @@ -47,8 +47,6 @@ #define SDIOH_API_ACCESS_RETRY_LIMIT 2 -#define SDIO_VENDOR_ID_BROADCOM 0x02d0 - #define DMA_ALIGN_MASK 0x03 #define SDIO_FUNC1_BLOCKSIZE 64 diff --git a/drivers/net/wireless/brcm80211/brcmfmac/sdio_chip.c b/drivers/net/wireless/brcm80211/brcmfmac/sdio_chip.c index 6aa6ba02b036..a0b8409063f1 100644 --- a/drivers/net/wireless/brcm80211/brcmfmac/sdio_chip.c +++ b/drivers/net/wireless/brcm80211/brcmfmac/sdio_chip.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include diff --git a/drivers/net/wireless/brcm80211/brcmfmac/sdio_chip.h b/drivers/net/wireless/brcm80211/brcmfmac/sdio_chip.h index d0f4b45b24c7..7ea424e20773 100644 --- a/drivers/net/wireless/brcm80211/brcmfmac/sdio_chip.h +++ b/drivers/net/wireless/brcm80211/brcmfmac/sdio_chip.h @@ -54,14 +54,6 @@ #define BRCMF_MAX_CORENUM 6 -/* SDIO device ID */ -#define SDIO_DEVICE_ID_BROADCOM_43143 43143 -#define SDIO_DEVICE_ID_BROADCOM_43241 0x4324 -#define SDIO_DEVICE_ID_BROADCOM_4329 0x4329 -#define SDIO_DEVICE_ID_BROADCOM_4330 0x4330 -#define SDIO_DEVICE_ID_BROADCOM_4334 0x4334 -#define SDIO_DEVICE_ID_BROADCOM_4335_4339 0x4335 - struct chip_core_info { u16 id; u16 rev; diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 9f03feedc8e7..d8836623f36a 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -23,6 +23,15 @@ /* * Vendors and devices. Sort key: vendor first, device next. */ +#define SDIO_VENDOR_ID_BROADCOM 0x02d0 +#define SDIO_DEVICE_ID_BROADCOM_43143 43143 +#define SDIO_DEVICE_ID_BROADCOM_43241 0x4324 +#define SDIO_DEVICE_ID_BROADCOM_4329 0x4329 +#define SDIO_DEVICE_ID_BROADCOM_4330 0x4330 +#define SDIO_DEVICE_ID_BROADCOM_4334 0x4334 +#define SDIO_DEVICE_ID_BROADCOM_4335_4339 0x4335 +#define SDIO_DEVICE_ID_BROADCOM_43362 43362 + #define SDIO_VENDOR_ID_INTEL 0x0089 #define SDIO_DEVICE_ID_INTEL_IWMC3200WIMAX 0x1402 #define SDIO_DEVICE_ID_INTEL_IWMC3200WIFI 0x1403 -- cgit v1.3-14-g43fede From 996b175e39ed42ec2aa0c63b4a03cc500aa6269f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 6 Jan 2014 09:36:12 -0800 Subject: tcp: out_of_order_queue do not use its lock TCP out_of_order_queue lock is not used, as queue manipulation happens with socket lock held and we therefore use the lockless skb queue routines (as __skb_queue_head()) We can use __skb_queue_head_init() instead of skb_queue_head_init() to make this more consistent. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 5 ++++- net/ipv4/tcp.c | 2 +- net/ipv4/tcp_minisocks.c | 2 +- 3 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index d68633452d9b..4ad0706d40eb 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -248,7 +248,10 @@ struct tcp_sock { struct sk_buff* lost_skb_hint; struct sk_buff *retransmit_skb_hint; - struct sk_buff_head out_of_order_queue; /* Out of order segments go here */ + /* OOO segments go in this list. Note that socket lock must be held, + * as we do not use sk_buff_head lock. + */ + struct sk_buff_head out_of_order_queue; /* SACKs data, these 2 need to be together (see tcp_options_write) */ struct tcp_sack_block duplicate_sack[1]; /* D-SACK block */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index d099f9a055c6..e2a40515e665 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -381,7 +381,7 @@ void tcp_init_sock(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - skb_queue_head_init(&tp->out_of_order_queue); + __skb_queue_head_init(&tp->out_of_order_queue); tcp_init_xmit_timers(sk); tcp_prequeue_init(tp); INIT_LIST_HEAD(&tp->tsq_node); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 97b684159861..3aa9e3247991 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -425,7 +425,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, tcp_set_ca_state(newsk, TCP_CA_Open); tcp_init_xmit_timers(newsk); - skb_queue_head_init(&newtp->out_of_order_queue); + __skb_queue_head_init(&newtp->out_of_order_queue); newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1; newtp->rx_opt.saw_tstamp = 0; -- cgit v1.3-14-g43fede From af2806f8f90a150160be898cd85332459c83c5cb Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Fri, 13 Dec 2013 15:22:17 +0100 Subject: net: Export skb_zerocopy() to zerocopy from one skb to another Make the skb zerocopy logic written for nfnetlink queue available for use by other modules. Signed-off-by: Thomas Graf Reviewed-by: Daniel Borkmann Acked-by: David S. Miller Signed-off-by: Jesse Gross --- include/linux/skbuff.h | 3 ++ net/core/skbuff.c | 85 ++++++++++++++++++++++++++++++++++++ net/netfilter/nfnetlink_queue_core.c | 59 ++----------------------- 3 files changed, 92 insertions(+), 55 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index bec1cc7d5e3c..7c48e2d4c72b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2345,6 +2345,9 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, struct pipe_inode_info *pipe, unsigned int len, unsigned int flags); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); +unsigned int skb_zerocopy_headlen(const struct sk_buff *from); +void skb_zerocopy(struct sk_buff *to, const struct sk_buff *from, + int len, int hlen); void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len); int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen); void skb_scrub_packet(struct sk_buff *skb, bool xnet); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 2718fed53d8c..55859cb8b83d 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2122,6 +2122,91 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, } EXPORT_SYMBOL(skb_copy_and_csum_bits); + /** + * skb_zerocopy_headlen - Calculate headroom needed for skb_zerocopy() + * @from: source buffer + * + * Calculates the amount of linear headroom needed in the 'to' skb passed + * into skb_zerocopy(). + */ +unsigned int +skb_zerocopy_headlen(const struct sk_buff *from) +{ + unsigned int hlen = 0; + + if (!from->head_frag || + skb_headlen(from) < L1_CACHE_BYTES || + skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) + hlen = skb_headlen(from); + + if (skb_has_frag_list(from)) + hlen = from->len; + + return hlen; +} +EXPORT_SYMBOL_GPL(skb_zerocopy_headlen); + +/** + * skb_zerocopy - Zero copy skb to skb + * @to: destination buffer + * @source: source buffer + * @len: number of bytes to copy from source buffer + * @hlen: size of linear headroom in destination buffer + * + * Copies up to `len` bytes from `from` to `to` by creating references + * to the frags in the source buffer. + * + * The `hlen` as calculated by skb_zerocopy_headlen() specifies the + * headroom in the `to` buffer. + */ +void +skb_zerocopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen) +{ + int i, j = 0; + int plen = 0; /* length of skb->head fragment */ + struct page *page; + unsigned int offset; + + BUG_ON(!from->head_frag && !hlen); + + /* dont bother with small payloads */ + if (len <= skb_tailroom(to)) { + skb_copy_bits(from, 0, skb_put(to, len), len); + return; + } + + if (hlen) { + skb_copy_bits(from, 0, skb_put(to, hlen), hlen); + len -= hlen; + } else { + plen = min_t(int, skb_headlen(from), len); + if (plen) { + page = virt_to_head_page(from->head); + offset = from->data - (unsigned char *)page_address(page); + __skb_fill_page_desc(to, 0, page, offset, plen); + get_page(page); + j = 1; + len -= plen; + } + } + + to->truesize += len + plen; + to->len += len + plen; + to->data_len += len + plen; + + for (i = 0; i < skb_shinfo(from)->nr_frags; i++) { + if (!len) + break; + skb_shinfo(to)->frags[j] = skb_shinfo(from)->frags[i]; + skb_shinfo(to)->frags[j].size = min_t(int, skb_shinfo(to)->frags[j].size, len); + len -= skb_shinfo(to)->frags[j].size; + skb_frag_ref(to, j); + j++; + } + skb_shinfo(to)->nr_frags = j; +} +EXPORT_SYMBOL_GPL(skb_zerocopy); + void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to) { __wsum csum; diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 21258cf70091..615ee12647ae 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -235,51 +235,6 @@ nfqnl_flush(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn, unsigned long data) spin_unlock_bh(&queue->lock); } -static void -nfqnl_zcopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen) -{ - int i, j = 0; - int plen = 0; /* length of skb->head fragment */ - struct page *page; - unsigned int offset; - - /* dont bother with small payloads */ - if (len <= skb_tailroom(to)) { - skb_copy_bits(from, 0, skb_put(to, len), len); - return; - } - - if (hlen) { - skb_copy_bits(from, 0, skb_put(to, hlen), hlen); - len -= hlen; - } else { - plen = min_t(int, skb_headlen(from), len); - if (plen) { - page = virt_to_head_page(from->head); - offset = from->data - (unsigned char *)page_address(page); - __skb_fill_page_desc(to, 0, page, offset, plen); - get_page(page); - j = 1; - len -= plen; - } - } - - to->truesize += len + plen; - to->len += len + plen; - to->data_len += len + plen; - - for (i = 0; i < skb_shinfo(from)->nr_frags; i++) { - if (!len) - break; - skb_shinfo(to)->frags[j] = skb_shinfo(from)->frags[i]; - skb_shinfo(to)->frags[j].size = min_t(int, skb_shinfo(to)->frags[j].size, len); - len -= skb_shinfo(to)->frags[j].size; - skb_frag_ref(to, j); - j++; - } - skb_shinfo(to)->nr_frags = j; -} - static int nfqnl_put_packet_info(struct sk_buff *nlskb, struct sk_buff *packet, bool csum_verify) @@ -304,7 +259,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, { size_t size; size_t data_len = 0, cap_len = 0; - int hlen = 0; + unsigned int hlen = 0; struct sk_buff *skb; struct nlattr *nla; struct nfqnl_msg_packet_hdr *pmsg; @@ -356,14 +311,8 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, if (data_len > entskb->len) data_len = entskb->len; - if (!entskb->head_frag || - skb_headlen(entskb) < L1_CACHE_BYTES || - skb_shinfo(entskb)->nr_frags >= MAX_SKB_FRAGS) - hlen = skb_headlen(entskb); - - if (skb_has_frag_list(entskb)) - hlen = entskb->len; - hlen = min_t(int, data_len, hlen); + hlen = skb_zerocopy_headlen(entskb); + hlen = min_t(unsigned int, hlen, data_len); size += sizeof(struct nlattr) + hlen; cap_len = entskb->len; break; @@ -504,7 +453,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, nla->nla_type = NFQA_PAYLOAD; nla->nla_len = nla_attr_size(data_len); - nfqnl_zcopy(skb, entskb, data_len, hlen); + skb_zerocopy(skb, entskb, data_len, hlen); } nlh->nlmsg_len = skb->len; -- cgit v1.3-14-g43fede From bf5a755f5e9186406bbf50f4087100af5bd68e40 Mon Sep 17 00:00:00 2001 From: Jerry Chu Date: Tue, 7 Jan 2014 10:23:19 -0800 Subject: net-gre-gro: Add GRE support to the GRO stack This patch built on top of Commit 299603e8370a93dd5d8e8d800f0dff1ce2c53d36 ("net-gro: Prepare GRO stack for the upcoming tunneling support") to add the support of the standard GRE (RFC1701/RFC2784/RFC2890) to the GRO stack. It also serves as an example for supporting other encapsulation protocols in the GRO stack in the future. The patch supports version 0 and all the flags (key, csum, seq#) but will flush any pkt with the S (seq#) flag. This is because the S flag is not support by GSO, and a GRO pkt may end up in the forwarding path, thus requiring GSO support to break it up correctly. Currently the "packet_offload" structure only contains L3 (ETH_P_IP/ ETH_P_IPV6) GRO offload support so the encapped pkts are limited to IP pkts (i.e., w/o L2 hdr). But support for other protocol type can be easily added, so is the support for GRE variations like NVGRE. The patch also support csum offload. Specifically if the csum flag is on and the h/w is capable of checksumming the payload (CHECKSUM_COMPLETE), the code will take advantage of the csum computed by the h/w when validating the GRE csum. Note that commit 60769a5dcd8755715c7143b4571d5c44f01796f1 "ipv4: gre: add GRO capability" already introduces GRO capability to IPv4 GRE tunnels, using the gro_cells infrastructure. But GRO is done after GRE hdr has been removed (i.e., decapped). The following patch applies GRO when pkts first come in (before hitting the GRE tunnel code). There is some performance advantage for applying GRO as early as possible. Also this approach is transparent to other subsystem like Open vSwitch where GRE decap is handled outside of the IP stack hence making it harder for the gro_cells stuff to apply. On the other hand, some NICs are still not capable of hashing on the inner hdr of a GRE pkt (RSS). In that case the GRO processing of pkts from the same remote host will all happen on the same CPU and the performance may be suboptimal. I'm including some rough preliminary performance numbers below. Note that the performance will be highly dependent on traffic load, mix as usual. Moreover it also depends on NIC offload features hence the following is by no means a comprehesive study. Local testing and tuning will be needed to decide the best setting. All tests spawned 50 copies of netperf TCP_STREAM and ran for 30 secs. (super_netperf 50 -H 192.168.1.18 -l 30) An IP GRE tunnel with only the key flag on (e.g., ip tunnel add gre1 mode gre local 10.246.17.18 remote 10.246.17.17 ttl 255 key 123) is configured. The GRO support for pkts AFTER decap are controlled through the device feature of the GRE device (e.g., ethtool -K gre1 gro on/off). 1.1 ethtool -K gre1 gro off; ethtool -K eth0 gro off thruput: 9.16Gbps CPU utilization: 19% 1.2 ethtool -K gre1 gro on; ethtool -K eth0 gro off thruput: 5.9Gbps CPU utilization: 15% 1.3 ethtool -K gre1 gro off; ethtool -K eth0 gro on thruput: 9.26Gbps CPU utilization: 12-13% 1.4 ethtool -K gre1 gro on; ethtool -K eth0 gro on thruput: 9.26Gbps CPU utilization: 10% The following tests were performed on a different NIC that is capable of csum offload. I.e., the h/w is capable of computing IP payload csum (CHECKSUM_COMPLETE). 2.1 ethtool -K gre1 gro on (hence will use gro_cells) 2.1.1 ethtool -K eth0 gro off; csum offload disabled thruput: 8.53Gbps CPU utilization: 9% 2.1.2 ethtool -K eth0 gro off; csum offload enabled thruput: 8.97Gbps CPU utilization: 7-8% 2.1.3 ethtool -K eth0 gro on; csum offload disabled thruput: 8.83Gbps CPU utilization: 5-6% 2.1.4 ethtool -K eth0 gro on; csum offload enabled thruput: 8.98Gbps CPU utilization: 5% 2.2 ethtool -K gre1 gro off 2.2.1 ethtool -K eth0 gro off; csum offload disabled thruput: 5.93Gbps CPU utilization: 9% 2.2.2 ethtool -K eth0 gro off; csum offload enabled thruput: 5.62Gbps CPU utilization: 8% 2.2.3 ethtool -K eth0 gro on; csum offload disabled thruput: 7.69Gbps CPU utilization: 8% 2.2.4 ethtool -K eth0 gro on; csum offload enabled thruput: 8.96Gbps CPU utilization: 5-6% Signed-off-by: H.K. Jerry Chu Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 18 +++++- net/core/dev.c | 26 ++++++++ net/ipv4/af_inet.c | 10 ++- net/ipv4/gre_offload.c | 160 ++++++++++++++++++++++++++++++++++++++++++++++ net/ipv4/tcp_offload.c | 7 +- net/ipv6/ip6_offload.c | 2 +- 6 files changed, 216 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d9c961aa6a7f..a2a70cc70e7b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1632,7 +1632,10 @@ struct napi_gro_cb { int data_offset; /* This is non-zero if the packet cannot be merged with the new skb. */ - int flush; + u16 flush; + + /* Save the IP ID here and check when we get to the transport layer */ + u16 flush_id; /* Number of segments aggregated. */ u16 count; @@ -1651,6 +1654,9 @@ struct napi_gro_cb { /* Used in ipv6_gro_receive() */ int proto; + /* used to support CHECKSUM_COMPLETE for tunneling protocols */ + __wsum csum; + /* used in skb_gro_receive() slow path */ struct sk_buff *last; }; @@ -1900,6 +1906,14 @@ static inline void *skb_gro_network_header(struct sk_buff *skb) skb_network_offset(skb); } +static inline void skb_gro_postpull_rcsum(struct sk_buff *skb, + const void *start, unsigned int len) +{ + if (skb->ip_summed == CHECKSUM_COMPLETE) + NAPI_GRO_CB(skb)->csum = csum_sub(NAPI_GRO_CB(skb)->csum, + csum_partial(start, len, 0)); +} + static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, @@ -2440,6 +2454,8 @@ gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); struct sk_buff *napi_get_frags(struct napi_struct *napi); gro_result_t napi_gro_frags(struct napi_struct *napi); +struct packet_offload *gro_find_receive_by_type(__be16 type); +struct packet_offload *gro_find_complete_by_type(__be16 type); static inline void napi_free_frags(struct napi_struct *napi) { diff --git a/net/core/dev.c b/net/core/dev.c index b3c574a88026..ce01847793c0 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3846,6 +3846,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff skb_gro_reset_offset(skb); gro_list_prepare(napi, skb); + NAPI_GRO_CB(skb)->csum = skb->csum; /* Needed for CHECKSUM_COMPLETE */ rcu_read_lock(); list_for_each_entry_rcu(ptype, head, list) { @@ -3922,6 +3923,31 @@ normal: goto pull; } +struct packet_offload *gro_find_receive_by_type(__be16 type) +{ + struct list_head *offload_head = &offload_base; + struct packet_offload *ptype; + + list_for_each_entry_rcu(ptype, offload_head, list) { + if (ptype->type != type || !ptype->callbacks.gro_receive) + continue; + return ptype; + } + return NULL; +} + +struct packet_offload *gro_find_complete_by_type(__be16 type) +{ + struct list_head *offload_head = &offload_base; + struct packet_offload *ptype; + + list_for_each_entry_rcu(ptype, offload_head, list) { + if (ptype->type != type || !ptype->callbacks.gro_complete) + continue; + return ptype; + } + return NULL; +} static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) { diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index b8bc1a3d5cf1..6268a4751e64 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1391,9 +1391,15 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, NAPI_GRO_CB(p)->flush |= (iph->ttl ^ iph2->ttl) | (iph->tos ^ iph2->tos) | - (__force int)((iph->frag_off ^ iph2->frag_off) & htons(IP_DF)) | - ((u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) ^ id); + ((iph->frag_off ^ iph2->frag_off) & htons(IP_DF)); + /* Save the IP ID check to be included later when we get to + * the transport layer so only the inner most IP ID is checked. + * This is because some GSO/TSO implementations do not + * correctly increment the IP ID for the outer hdrs. + */ + NAPI_GRO_CB(p)->flush_id = + ((u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) ^ id); NAPI_GRO_CB(p)->flush |= flush; } diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 9138cfb10140..746a7b10d434 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -116,10 +116,170 @@ out: return segs; } +/* Compute the whole skb csum in s/w and store it, then verify GRO csum + * starting from gro_offset. + */ +static __sum16 gro_skb_checksum(struct sk_buff *skb) +{ + __sum16 sum; + + skb->csum = skb_checksum(skb, 0, skb->len, 0); + NAPI_GRO_CB(skb)->csum = csum_sub(skb->csum, + csum_partial(skb->data, skb_gro_offset(skb), 0)); + sum = csum_fold(NAPI_GRO_CB(skb)->csum); + if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE)) { + if (unlikely(!sum)) + netdev_rx_csum_fault(skb->dev); + } else + skb->ip_summed = CHECKSUM_COMPLETE; + + return sum; +} + +static struct sk_buff **gre_gro_receive(struct sk_buff **head, + struct sk_buff *skb) +{ + struct sk_buff **pp = NULL; + struct sk_buff *p; + const struct gre_base_hdr *greh; + unsigned int hlen, grehlen; + unsigned int off; + int flush = 1; + struct packet_offload *ptype; + __be16 type; + + off = skb_gro_offset(skb); + hlen = off + sizeof(*greh); + greh = skb_gro_header_fast(skb, off); + if (skb_gro_header_hard(skb, hlen)) { + greh = skb_gro_header_slow(skb, hlen, off); + if (unlikely(!greh)) + goto out; + } + + /* Only support version 0 and K (key), C (csum) flags. Note that + * although the support for the S (seq#) flag can be added easily + * for GRO, this is problematic for GSO hence can not be enabled + * here because a GRO pkt may end up in the forwarding path, thus + * requiring GSO support to break it up correctly. + */ + if ((greh->flags & ~(GRE_KEY|GRE_CSUM)) != 0) + goto out; + + type = greh->protocol; + + rcu_read_lock(); + ptype = gro_find_receive_by_type(type); + if (ptype == NULL) + goto out_unlock; + + grehlen = GRE_HEADER_SECTION; + + if (greh->flags & GRE_KEY) + grehlen += GRE_HEADER_SECTION; + + if (greh->flags & GRE_CSUM) + grehlen += GRE_HEADER_SECTION; + + hlen = off + grehlen; + if (skb_gro_header_hard(skb, hlen)) { + greh = skb_gro_header_slow(skb, hlen, off); + if (unlikely(!greh)) + goto out_unlock; + } + if (greh->flags & GRE_CSUM) { /* Need to verify GRE csum first */ + __sum16 csum = 0; + + if (skb->ip_summed == CHECKSUM_COMPLETE) + csum = csum_fold(NAPI_GRO_CB(skb)->csum); + /* Don't trust csum error calculated/reported by h/w */ + if (skb->ip_summed == CHECKSUM_NONE || csum != 0) + csum = gro_skb_checksum(skb); + + /* GRE CSUM is the 1's complement of the 1's complement sum + * of the GRE hdr plus payload so it should add up to 0xffff + * (and 0 after csum_fold()) just like the IPv4 hdr csum. + */ + if (csum) + goto out_unlock; + } + flush = 0; + + for (p = *head; p; p = p->next) { + const struct gre_base_hdr *greh2; + + if (!NAPI_GRO_CB(p)->same_flow) + continue; + + /* The following checks are needed to ensure only pkts + * from the same tunnel are considered for aggregation. + * The criteria for "the same tunnel" includes: + * 1) same version (we only support version 0 here) + * 2) same protocol (we only support ETH_P_IP for now) + * 3) same set of flags + * 4) same key if the key field is present. + */ + greh2 = (struct gre_base_hdr *)(p->data + off); + + if (greh2->flags != greh->flags || + greh2->protocol != greh->protocol) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + if (greh->flags & GRE_KEY) { + /* compare keys */ + if (*(__be32 *)(greh2+1) != *(__be32 *)(greh+1)) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + } + } + + skb_gro_pull(skb, grehlen); + + /* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/ + skb_gro_postpull_rcsum(skb, greh, grehlen); + + pp = ptype->callbacks.gro_receive(head, skb); + +out_unlock: + rcu_read_unlock(); +out: + NAPI_GRO_CB(skb)->flush |= flush; + + return pp; +} + +int gre_gro_complete(struct sk_buff *skb, int nhoff) +{ + struct gre_base_hdr *greh = (struct gre_base_hdr *)(skb->data + nhoff); + struct packet_offload *ptype; + unsigned int grehlen = sizeof(*greh); + int err = -ENOENT; + __be16 type; + + type = greh->protocol; + if (greh->flags & GRE_KEY) + grehlen += GRE_HEADER_SECTION; + + if (greh->flags & GRE_CSUM) + grehlen += GRE_HEADER_SECTION; + + rcu_read_lock(); + ptype = gro_find_complete_by_type(type); + if (ptype != NULL) + err = ptype->callbacks.gro_complete(skb, nhoff + grehlen); + + rcu_read_unlock(); + return err; +} + static const struct net_offload gre_offload = { .callbacks = { .gso_send_check = gre_gso_send_check, .gso_segment = gre_gso_segment, + .gro_receive = gre_gro_receive, + .gro_complete = gre_gro_complete, }, }; diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 2658a27f540d..771a3950d87a 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -197,7 +197,8 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb) goto out_check_final; found: - flush = NAPI_GRO_CB(p)->flush; + /* Include the IP ID check below from the inner most IP hdr */ + flush = NAPI_GRO_CB(p)->flush | NAPI_GRO_CB(p)->flush_id; flush |= (__force int)(flags & TCP_FLAG_CWR); flush |= (__force int)((flags ^ tcp_flag_word(th2)) & ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH)); @@ -230,7 +231,7 @@ out_check_final: pp = head; out: - NAPI_GRO_CB(skb)->flush |= flush; + NAPI_GRO_CB(skb)->flush |= (flush != 0); return pp; } @@ -280,7 +281,7 @@ static struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff * if (NAPI_GRO_CB(skb)->flush) goto skip_csum; - wsum = skb->csum; + wsum = NAPI_GRO_CB(skb)->csum; switch (skb->ip_summed) { case CHECKSUM_NONE: diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 6fb4162fa785..1e8683b135bb 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -190,7 +190,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, unsigned int nlen; unsigned int hlen; unsigned int off; - int flush = 1; + u16 flush = 1; int proto; __wsum csum; -- cgit v1.3-14-g43fede From fd44b93cb5eee218231f6ce5883df937b3b9c3eb Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 7 Jan 2014 23:23:44 +0100 Subject: net: skbuff: const-ify casts in skb_queue_* functions We should const-ify comparisons on skb_queue_* inline helper functions as their parameters are const as well, so lets not drop that. Suggested-by: Brad Spengler Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 956e11a168d8..d97f2d07d02b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -827,7 +827,7 @@ static inline struct skb_shared_hwtstamps *skb_hwtstamps(struct sk_buff *skb) */ static inline int skb_queue_empty(const struct sk_buff_head *list) { - return list->next == (struct sk_buff *)list; + return list->next == (const struct sk_buff *) list; } /** @@ -840,7 +840,7 @@ static inline int skb_queue_empty(const struct sk_buff_head *list) static inline bool skb_queue_is_last(const struct sk_buff_head *list, const struct sk_buff *skb) { - return skb->next == (struct sk_buff *)list; + return skb->next == (const struct sk_buff *) list; } /** @@ -853,7 +853,7 @@ static inline bool skb_queue_is_last(const struct sk_buff_head *list, static inline bool skb_queue_is_first(const struct sk_buff_head *list, const struct sk_buff *skb) { - return skb->prev == (struct sk_buff *)list; + return skb->prev == (const struct sk_buff *) list; } /** -- cgit v1.3-14-g43fede From 852c0153df5082311f50c062275813905f39f56e Mon Sep 17 00:00:00 2001 From: Avinash Patil Date: Thu, 9 Jan 2014 15:22:57 -0800 Subject: ieee80211: add definition for TDLS wide band extended capability Seventh bit of 8th byte of extended capabilities specifies wide bandwidth support for TDLS links. Add this definition to ieee80211. Signed-off-by: Avinash Patil Signed-off-by: Bing Zhao Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 776cbb80d098..b382c7c49d84 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1902,6 +1902,7 @@ enum ieee80211_tdls_actioncode { #define WLAN_EXT_CAPA5_TDLS_PROHIBITED BIT(6) #define WLAN_EXT_CAPA8_OPMODE_NOTIF BIT(6) +#define WLAN_EXT_CAPA8_TDLS_WIDE_BW_ENABLED BIT(7) /* TDLS specific payload type in the LLC/SNAP header */ #define WLAN_TDLS_SNAP_RFTYPE 0x2 -- cgit v1.3-14-g43fede From 28cb1749e8dcf7f2b49174ae8531e3e5be741736 Mon Sep 17 00:00:00 2001 From: Avinash Patil Date: Fri, 10 Jan 2014 11:08:55 -0800 Subject: ieee80211: add definition for SMS4 key len Add SMS4 key length definition to ieee80211_key_len enum. It's used by WAPI. Signed-off-by: Avinash Patil Signed-off-by: Bing Zhao Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index b382c7c49d84..e526a8cecb70 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1857,6 +1857,7 @@ enum ieee80211_key_len { WLAN_KEY_LEN_CCMP = 16, WLAN_KEY_LEN_TKIP = 32, WLAN_KEY_LEN_AES_CMAC = 16, + WLAN_KEY_LEN_SMS4 = 32, }; #define IEEE80211_WEP_IV_LEN 4 -- cgit v1.3-14-g43fede From efabdfb95ab698b51009e7783ddc2714cef0aecf Mon Sep 17 00:00:00 2001 From: Andy Fleming Date: Fri, 10 Jan 2014 14:25:09 +0800 Subject: phylib: Add Clause 45 read/write functions Need an extra parameter to read or write Clause 45 PHYs, so need a different API with the extra parameter. Signed-off-by: Andy Fleming Signed-off-by: Shaohui Xie Signed-off-by: David S. Miller --- include/linux/phy.h | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 7c81dd8870d4..3eda43c90875 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -487,6 +487,24 @@ struct phy_fixup { int (*run)(struct phy_device *phydev); }; +/** + * phy_read_mmd - Convenience function for reading a register + * from an MMD on a given PHY. + * @phydev: The phy_device struct + * @devad: The MMD to read from + * @regnum: The register on the MMD to read + * + * Same rules as for phy_read(); + */ +static inline int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum) +{ + if (!phydev->is_c45) + return -EOPNOTSUPP; + + return mdiobus_read(phydev->bus, phydev->addr, + MII_ADDR_C45 | (devad << 16) | (regnum & 0xffff)); +} + /** * phy_read - Convenience function for reading a given PHY register * @phydev: the phy_device struct @@ -537,6 +555,27 @@ static inline bool phy_is_internal(struct phy_device *phydev) return phydev->is_internal; } +/** + * phy_write_mmd - Convenience function for writing a register + * on an MMD on a given PHY. + * @phydev: The phy_device struct + * @devad: The MMD to read from + * @regnum: The register on the MMD to read + * @val: value to write to @regnum + * + * Same rules as for phy_write(); + */ +static inline int phy_write_mmd(struct phy_device *phydev, int devad, + u32 regnum, u16 val) +{ + if (!phydev->is_c45) + return -EOPNOTSUPP; + + regnum = MII_ADDR_C45 | ((devad & 0x1f) << 16) | (regnum & 0xffff); + + return mdiobus_write(phydev->bus, phydev->addr, regnum, val); +} + struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id, bool is_c45, struct phy_c45_device_ids *c45_ids); -- cgit v1.3-14-g43fede From 898dd0bda366edd0b077db4389a26c00509c73c9 Mon Sep 17 00:00:00 2001 From: Andy Fleming Date: Fri, 10 Jan 2014 14:26:46 +0800 Subject: phylib: introduce PHY_INTERFACE_MODE_XGMII for 10G PHY Signed-off-by: Andy Fleming Signed-off-by: Shaohui Xie Acked-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/of/of_net.c | 1 + include/linux/phy.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/drivers/of/of_net.c b/drivers/of/of_net.c index 8f9be2e09937..a208a457558c 100644 --- a/drivers/of/of_net.c +++ b/drivers/of/of_net.c @@ -30,6 +30,7 @@ static const char *phy_modes[] = { [PHY_INTERFACE_MODE_RGMII_TXID] = "rgmii-txid", [PHY_INTERFACE_MODE_RTBI] = "rtbi", [PHY_INTERFACE_MODE_SMII] = "smii", + [PHY_INTERFACE_MODE_XGMII] = "xgmii", }; /** diff --git a/include/linux/phy.h b/include/linux/phy.h index 3eda43c90875..a9685b109049 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -73,6 +73,7 @@ typedef enum { PHY_INTERFACE_MODE_RGMII_TXID, PHY_INTERFACE_MODE_RTBI, PHY_INTERFACE_MODE_SMII, + PHY_INTERFACE_MODE_XGMII, } phy_interface_t; -- cgit v1.3-14-g43fede From 257184d7cc03519e1ea37b421879767b4194ce8c Mon Sep 17 00:00:00 2001 From: Andy Fleming Date: Fri, 10 Jan 2014 14:27:54 +0800 Subject: phylib: Support attaching to generic 10g driver phy_attach_direct() may now attach to a generic 10G driver. It can also be used exactly as phy_connect_direct(), which will be useful when using of_mdio, as phy_connect (and therefore of_phy_connect) start the PHY state machine, which is currently irrelevant for 10G PHYs. Signed-off-by: Andy Fleming Signed-off-by: Shaohui Xie Acked-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 22 +++++++++------------- include/linux/phy.h | 2 ++ 2 files changed, 11 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 18714fe0f074..39794c4d7b21 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -62,9 +62,6 @@ static struct phy_driver genphy_driver[GENPHY_DRV_MAX]; static LIST_HEAD(phy_fixup_list); static DEFINE_MUTEX(phy_fixup_lock); -static int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, - u32 flags, phy_interface_t interface); - /** * phy_register_fixup - creates a new phy_fixup and adds it to the list * @bus_id: A string which matches phydev->dev.bus_id (or PHY_ANY_ID) @@ -567,13 +564,13 @@ EXPORT_SYMBOL(phy_init_hw); * * Description: Called by drivers to attach to a particular PHY * device. The phy_device is found, and properly hooked up - * to the phy_driver. If no driver is attached, then the - * genphy_driver is used. The phy_device is given a ptr to + * to the phy_driver. If no driver is attached, then a + * generic driver is used. The phy_device is given a ptr to * the attaching device, and given a callback for link status * change. The phy_device is returned to the attaching driver. */ -static int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, - u32 flags, phy_interface_t interface) +int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, + u32 flags, phy_interface_t interface) { struct device *d = &phydev->dev; int err; @@ -582,12 +579,10 @@ static int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, * exist, and we should use the genphy driver. */ if (NULL == d->driver) { - if (phydev->is_c45) { - pr_err("No driver for phy %x\n", phydev->phy_id); - return -ENODEV; - } - - d->driver = &genphy_driver[GENPHY_DRV_1G].driver; + if (phydev->is_c45) + d->driver = &genphy_driver[GENPHY_DRV_10G].driver; + else + d->driver = &genphy_driver[GENPHY_DRV_1G].driver; err = d->driver->probe(d); if (err >= 0) @@ -623,6 +618,7 @@ static int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, return err; } +EXPORT_SYMBOL(phy_attach_direct); /** * phy_attach - attach a network device to a particular PHY device diff --git a/include/linux/phy.h b/include/linux/phy.h index a9685b109049..565188ca328f 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -588,6 +588,8 @@ int phy_resume(struct phy_device *phydev); struct phy_device *phy_attach(struct net_device *dev, const char *bus_id, phy_interface_t interface); struct phy_device *phy_find_first(struct mii_bus *bus); +int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, + u32 flags, phy_interface_t interface); int phy_connect_direct(struct net_device *dev, struct phy_device *phydev, void (*handler)(struct net_device *), phy_interface_t interface); -- cgit v1.3-14-g43fede From 7614aba6a330a6c4937edc24fd4c6a935c1ae703 Mon Sep 17 00:00:00 2001 From: Andy Fleming Date: Fri, 10 Jan 2014 14:28:11 +0800 Subject: phylib: Add of_phy_attach 10G PHYs don't currently support running the state machine, which is implicitly setup via of_phy_connect(). Therefore, it is necessary to implement an OF version of phy_attach(), which does everything except start the state machine. Signed-off-by: Andy Fleming Signed-off-by: Shaohui Xie Acked-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/of/of_mdio.c | 20 ++++++++++++++++++++ include/linux/of_mdio.h | 10 ++++++++++ 2 files changed, 30 insertions(+) (limited to 'include/linux') diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index a43b8523c61e..875b7b6f0d2a 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -254,3 +254,23 @@ struct phy_device *of_phy_connect_fixed_link(struct net_device *dev, return IS_ERR(phy) ? NULL : phy; } EXPORT_SYMBOL(of_phy_connect_fixed_link); + +/** + * of_phy_attach - Attach to a PHY without starting the state machine + * @dev: pointer to net_device claiming the phy + * @phy_np: Node pointer for the PHY + * @flags: flags to pass to the PHY + * @iface: PHY data interface type + */ +struct phy_device *of_phy_attach(struct net_device *dev, + struct device_node *phy_np, u32 flags, + phy_interface_t iface) +{ + struct phy_device *phy = of_phy_find_device(phy_np); + + if (!phy) + return NULL; + + return phy_attach_direct(dev, phy, flags, iface) ? NULL : phy; +} +EXPORT_SYMBOL(of_phy_attach); diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 8163107b94b4..6fe8464ed767 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -19,6 +19,9 @@ extern struct phy_device *of_phy_connect(struct net_device *dev, struct device_node *phy_np, void (*hndlr)(struct net_device *), u32 flags, phy_interface_t iface); +struct phy_device *of_phy_attach(struct net_device *dev, + struct device_node *phy_np, u32 flags, + phy_interface_t iface); extern struct phy_device *of_phy_connect_fixed_link(struct net_device *dev, void (*hndlr)(struct net_device *), phy_interface_t iface); @@ -44,6 +47,13 @@ static inline struct phy_device *of_phy_connect(struct net_device *dev, return NULL; } +static inline struct phy_device *of_phy_attach(struct net_device *dev, + struct device_node *phy_np, + u32 flags, phy_interface_t iface) +{ + return NULL; +} + static inline struct phy_device *of_phy_connect_fixed_link(struct net_device *dev, void (*hndlr)(struct net_device *), phy_interface_t iface) -- cgit v1.3-14-g43fede From ed1f50c3a7c1ad1b1b4d584308eab77d57a330f8 Mon Sep 17 00:00:00 2001 From: Paul Durrant Date: Thu, 9 Jan 2014 10:02:46 +0000 Subject: net: add skb_checksum_setup This patch adds a function to set up the partial checksum offset for IP packets (and optionally re-calculate the pseudo-header checksum) into the core network code. The implementation was previously private and duplicated between xen-netback and xen-netfront, however it is not xen-specific and is potentially useful to any network driver. Signed-off-by: Paul Durrant Cc: David Miller Cc: Eric Dumazet Cc: Veaceslav Falico Cc: Alexander Duyck Cc: Nicolas Dichtel Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 + net/core/skbuff.c | 273 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 275 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d97f2d07d02b..48b760505cb6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2893,6 +2893,8 @@ static inline void skb_checksum_none_assert(const struct sk_buff *skb) bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off); +int skb_checksum_setup(struct sk_buff *skb, bool recalculate); + u32 __skb_get_poff(const struct sk_buff *skb); /** diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 1d641e781f85..15057d29b010 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -65,6 +65,7 @@ #include #include #include +#include #include #include @@ -3549,6 +3550,278 @@ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off) } EXPORT_SYMBOL_GPL(skb_partial_csum_set); +static int skb_maybe_pull_tail(struct sk_buff *skb, unsigned int len, + unsigned int max) +{ + if (skb_headlen(skb) >= len) + return 0; + + /* If we need to pullup then pullup to the max, so we + * won't need to do it again. + */ + if (max > skb->len) + max = skb->len; + + if (__pskb_pull_tail(skb, max - skb_headlen(skb)) == NULL) + return -ENOMEM; + + if (skb_headlen(skb) < len) + return -EPROTO; + + return 0; +} + +/* This value should be large enough to cover a tagged ethernet header plus + * maximally sized IP and TCP or UDP headers. + */ +#define MAX_IP_HDR_LEN 128 + +static int skb_checksum_setup_ip(struct sk_buff *skb, bool recalculate) +{ + unsigned int off; + bool fragment; + int err; + + fragment = false; + + err = skb_maybe_pull_tail(skb, + sizeof(struct iphdr), + MAX_IP_HDR_LEN); + if (err < 0) + goto out; + + if (ip_hdr(skb)->frag_off & htons(IP_OFFSET | IP_MF)) + fragment = true; + + off = ip_hdrlen(skb); + + err = -EPROTO; + + if (fragment) + goto out; + + switch (ip_hdr(skb)->protocol) { + case IPPROTO_TCP: + err = skb_maybe_pull_tail(skb, + off + sizeof(struct tcphdr), + MAX_IP_HDR_LEN); + if (err < 0) + goto out; + + if (!skb_partial_csum_set(skb, off, + offsetof(struct tcphdr, check))) { + err = -EPROTO; + goto out; + } + + if (recalculate) + tcp_hdr(skb)->check = + ~csum_tcpudp_magic(ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, + skb->len - off, + IPPROTO_TCP, 0); + break; + case IPPROTO_UDP: + err = skb_maybe_pull_tail(skb, + off + sizeof(struct udphdr), + MAX_IP_HDR_LEN); + if (err < 0) + goto out; + + if (!skb_partial_csum_set(skb, off, + offsetof(struct udphdr, check))) { + err = -EPROTO; + goto out; + } + + if (recalculate) + udp_hdr(skb)->check = + ~csum_tcpudp_magic(ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, + skb->len - off, + IPPROTO_UDP, 0); + break; + default: + goto out; + } + + err = 0; + +out: + return err; +} + +/* This value should be large enough to cover a tagged ethernet header plus + * an IPv6 header, all options, and a maximal TCP or UDP header. + */ +#define MAX_IPV6_HDR_LEN 256 + +#define OPT_HDR(type, skb, off) \ + (type *)(skb_network_header(skb) + (off)) + +static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate) +{ + int err; + u8 nexthdr; + unsigned int off; + unsigned int len; + bool fragment; + bool done; + + fragment = false; + done = false; + + off = sizeof(struct ipv6hdr); + + err = skb_maybe_pull_tail(skb, off, MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + nexthdr = ipv6_hdr(skb)->nexthdr; + + len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len); + while (off <= len && !done) { + switch (nexthdr) { + case IPPROTO_DSTOPTS: + case IPPROTO_HOPOPTS: + case IPPROTO_ROUTING: { + struct ipv6_opt_hdr *hp; + + err = skb_maybe_pull_tail(skb, + off + + sizeof(struct ipv6_opt_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + hp = OPT_HDR(struct ipv6_opt_hdr, skb, off); + nexthdr = hp->nexthdr; + off += ipv6_optlen(hp); + break; + } + case IPPROTO_AH: { + struct ip_auth_hdr *hp; + + err = skb_maybe_pull_tail(skb, + off + + sizeof(struct ip_auth_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + hp = OPT_HDR(struct ip_auth_hdr, skb, off); + nexthdr = hp->nexthdr; + off += ipv6_authlen(hp); + break; + } + case IPPROTO_FRAGMENT: { + struct frag_hdr *hp; + + err = skb_maybe_pull_tail(skb, + off + + sizeof(struct frag_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + hp = OPT_HDR(struct frag_hdr, skb, off); + + if (hp->frag_off & htons(IP6_OFFSET | IP6_MF)) + fragment = true; + + nexthdr = hp->nexthdr; + off += sizeof(struct frag_hdr); + break; + } + default: + done = true; + break; + } + } + + err = -EPROTO; + + if (!done || fragment) + goto out; + + switch (nexthdr) { + case IPPROTO_TCP: + err = skb_maybe_pull_tail(skb, + off + sizeof(struct tcphdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + if (!skb_partial_csum_set(skb, off, + offsetof(struct tcphdr, check))) { + err = -EPROTO; + goto out; + } + + if (recalculate) + tcp_hdr(skb)->check = + ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + skb->len - off, + IPPROTO_TCP, 0); + break; + case IPPROTO_UDP: + err = skb_maybe_pull_tail(skb, + off + sizeof(struct udphdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + if (!skb_partial_csum_set(skb, off, + offsetof(struct udphdr, check))) { + err = -EPROTO; + goto out; + } + + if (recalculate) + udp_hdr(skb)->check = + ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + skb->len - off, + IPPROTO_UDP, 0); + break; + default: + goto out; + } + + err = 0; + +out: + return err; +} + +/** + * skb_checksum_setup - set up partial checksum offset + * @skb: the skb to set up + * @recalculate: if true the pseudo-header checksum will be recalculated + */ +int skb_checksum_setup(struct sk_buff *skb, bool recalculate) +{ + int err; + + switch (skb->protocol) { + case htons(ETH_P_IP): + err = skb_checksum_setup_ip(skb, recalculate); + break; + + case htons(ETH_P_IPV6): + err = skb_checksum_setup_ipv6(skb, recalculate); + break; + + default: + err = -EPROTO; + break; + } + + return err; +} +EXPORT_SYMBOL(skb_checksum_setup); + void __skb_warn_lro_forwarding(const struct sk_buff *skb) { net_warn_ratelimited("%s: received packets cannot be forwarded while LRO is enabled\n", -- cgit v1.3-14-g43fede From 63862b5bef7349dd1137e4c70702c67d77565785 Mon Sep 17 00:00:00 2001 From: Aruna-Hewapathirane Date: Sat, 11 Jan 2014 07:15:59 -0500 Subject: net: replace macros net_random and net_srandom with direct calls to prandom This patch removes the net_random and net_srandom macros and replaces them with direct calls to the prandom ones. As new commits only seem to use prandom_u32 there is no use to keep them around. This change makes it easier to grep for users of prandom_u32. Signed-off-by: Aruna-Hewapathirane Suggested-by: Hannes Frederic Sowa Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- drivers/infiniband/core/cma.c | 2 +- include/linux/net.h | 3 --- include/net/red.h | 2 +- net/802/garp.c | 2 +- net/802/mrp.c | 2 +- net/core/neighbour.c | 5 +++-- net/core/stream.c | 2 +- net/ipv4/devinet.c | 2 +- net/ipv4/igmp.c | 6 +++--- net/ipv4/inet_connection_sock.c | 2 +- net/ipv4/udp.c | 2 +- net/ipv6/addrconf.c | 4 ++-- net/ipv6/ip6_flowlabel.c | 2 +- net/ipv6/mcast.c | 10 +++++----- net/netfilter/ipvs/ip_vs_conn.c | 2 +- net/netfilter/xt_statistic.c | 2 +- net/openvswitch/actions.c | 2 +- net/rds/bind.c | 2 +- net/sched/act_gact.c | 2 +- net/sched/sch_fq_codel.c | 2 +- net/sched/sch_hhf.c | 2 +- net/sched/sch_netem.c | 19 ++++++++++--------- net/sched/sch_pie.c | 2 +- net/sched/sch_sfb.c | 4 ++-- net/sched/sch_sfq.c | 6 +++--- net/sctp/socket.c | 2 +- net/sunrpc/cache.c | 2 +- net/sunrpc/xprt.c | 2 +- net/sunrpc/xprtsock.c | 2 +- net/xfrm/xfrm_state.c | 2 +- 30 files changed, 50 insertions(+), 51 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 8e49db690f33..6c17f2dc0f09 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -2310,7 +2310,7 @@ static int cma_alloc_any_port(struct idr *ps, struct rdma_id_private *id_priv) inet_get_local_port_range(&init_net, &low, &high); remaining = (high - low) + 1; - rover = net_random() % remaining + low; + rover = prandom_u32() % remaining + low; retry: if (last_used_port != rover && !idr_find(ps, (unsigned short) rover)) { diff --git a/include/linux/net.h b/include/linux/net.h index 69be3e6079c8..94734a6259a4 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -245,9 +245,6 @@ do { \ #define net_dbg_ratelimited(fmt, ...) \ net_ratelimited_function(pr_debug, fmt, ##__VA_ARGS__) -#define net_random() prandom_u32() -#define net_srandom(seed) prandom_seed((__force u32)(seed)) - bool __net_get_random_once(void *buf, int nbytes, bool *done, struct static_key *done_key); diff --git a/include/net/red.h b/include/net/red.h index ef46058d35bf..168bb2f495f2 100644 --- a/include/net/red.h +++ b/include/net/red.h @@ -303,7 +303,7 @@ static inline unsigned long red_calc_qavg(const struct red_parms *p, static inline u32 red_random(const struct red_parms *p) { - return reciprocal_divide(net_random(), p->max_P_reciprocal); + return reciprocal_divide(prandom_u32(), p->max_P_reciprocal); } static inline int red_mark_probability(const struct red_parms *p, diff --git a/net/802/garp.c b/net/802/garp.c index 5d9630a0eb93..b38ee6dcba45 100644 --- a/net/802/garp.c +++ b/net/802/garp.c @@ -397,7 +397,7 @@ static void garp_join_timer_arm(struct garp_applicant *app) { unsigned long delay; - delay = (u64)msecs_to_jiffies(garp_join_time) * net_random() >> 32; + delay = (u64)msecs_to_jiffies(garp_join_time) * prandom_u32() >> 32; mod_timer(&app->join_timer, jiffies + delay); } diff --git a/net/802/mrp.c b/net/802/mrp.c index 3ed616215870..72db2785ef2c 100644 --- a/net/802/mrp.c +++ b/net/802/mrp.c @@ -583,7 +583,7 @@ static void mrp_join_timer_arm(struct mrp_applicant *app) { unsigned long delay; - delay = (u64)msecs_to_jiffies(mrp_join_time) * net_random() >> 32; + delay = (u64)msecs_to_jiffies(mrp_join_time) * prandom_u32() >> 32; mod_timer(&app->join_timer, jiffies + delay); } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index ea97361f0e9b..e360d9e65c04 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -117,7 +117,7 @@ static void neigh_cleanup_and_release(struct neighbour *neigh) unsigned long neigh_rand_reach_time(unsigned long base) { - return base ? (net_random() % base) + (base >> 1) : 0; + return base ? (prandom_u32() % base) + (base >> 1) : 0; } EXPORT_SYMBOL(neigh_rand_reach_time); @@ -1415,7 +1415,8 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, struct sk_buff *skb) { unsigned long now = jiffies; - unsigned long sched_next = now + (net_random() % + + unsigned long sched_next = now + (prandom_u32() % NEIGH_VAR(p, PROXY_DELAY)); if (tbl->proxy_queue.qlen > NEIGH_VAR(p, PROXY_QLEN)) { diff --git a/net/core/stream.c b/net/core/stream.c index 512f0a24269b..301c05f26060 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -122,7 +122,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) DEFINE_WAIT(wait); if (sk_stream_memory_free(sk)) - current_timeo = vm_wait = (net_random() % (HZ / 5)) + 2; + current_timeo = vm_wait = (prandom_u32() % (HZ / 5)) + 2; while (1) { set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 9809f7b69728..646023bd5449 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -464,7 +464,7 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, } if (!(ifa->ifa_flags & IFA_F_SECONDARY)) { - net_srandom(ifa->ifa_local); + prandom_seed((__force u32) ifa->ifa_local); ifap = last_primary; } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index bcbf33e58324..97e4d1655d26 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -211,7 +211,7 @@ static void igmp_stop_timer(struct ip_mc_list *im) /* It must be called with locked im->lock */ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) { - int tv = net_random() % max_delay; + int tv = prandom_u32() % max_delay; im->tm_running = 1; if (!mod_timer(&im->timer, jiffies+tv+2)) @@ -220,7 +220,7 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) static void igmp_gq_start_timer(struct in_device *in_dev) { - int tv = net_random() % in_dev->mr_maxdelay; + int tv = prandom_u32() % in_dev->mr_maxdelay; in_dev->mr_gq_running = 1; if (!mod_timer(&in_dev->mr_gq_timer, jiffies+tv+2)) @@ -229,7 +229,7 @@ static void igmp_gq_start_timer(struct in_device *in_dev) static void igmp_ifc_start_timer(struct in_device *in_dev, int delay) { - int tv = net_random() % delay; + int tv = prandom_u32() % delay; if (!mod_timer(&in_dev->mr_ifc_timer, jiffies+tv+2)) in_dev_hold(in_dev); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index fc0e649cc002..0d1e2cb877ec 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -109,7 +109,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) again: inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; - smallest_rover = rover = net_random() % remaining + low; + smallest_rover = rover = prandom_u32() % remaining + low; smallest_size = -1; do { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 80f649fbee63..3d3141fd0580 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -223,7 +223,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; - rand = net_random(); + rand = prandom_u32(); first = (((u64)rand * remaining) >> 32) + low; /* * force rand to be an odd multiple of UDP_HTABLE_SIZE diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index b0cd122e5fb4..5329cccf55dc 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3104,7 +3104,7 @@ static void addrconf_dad_kick(struct inet6_ifaddr *ifp) if (ifp->flags & IFA_F_OPTIMISTIC) rand_num = 0; else - rand_num = net_random() % (idev->cnf.rtr_solicit_delay ? : 1); + rand_num = prandom_u32() % (idev->cnf.rtr_solicit_delay ? : 1); ifp->dad_probes = idev->cnf.dad_transmits; addrconf_mod_dad_timer(ifp, rand_num); @@ -3117,7 +3117,7 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp) addrconf_join_solict(dev, &ifp->addr); - net_srandom(ifp->addr.s6_addr32[3]); + prandom_seed((__force u32) ifp->addr.s6_addr32[3]); read_lock_bh(&idev->lock); spin_lock(&ifp->lock); diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index e7fb7106550f..cbc93517b455 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -210,7 +210,7 @@ static struct ip6_flowlabel *fl_intern(struct net *net, spin_lock_bh(&ip6_fl_lock); if (label == 0) { for (;;) { - fl->label = htonl(net_random())&IPV6_FLOWLABEL_MASK; + fl->label = htonl(prandom_u32())&IPV6_FLOWLABEL_MASK; if (fl->label) { lfl = __fl_lookup(net, fl->label); if (lfl == NULL) diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index d18f9f903db6..7ff82b3e54b6 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -999,7 +999,7 @@ bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, static void mld_gq_start_timer(struct inet6_dev *idev) { - unsigned long tv = net_random() % idev->mc_maxdelay; + unsigned long tv = prandom_u32() % idev->mc_maxdelay; idev->mc_gq_running = 1; if (!mod_timer(&idev->mc_gq_timer, jiffies+tv+2)) @@ -1015,7 +1015,7 @@ static void mld_gq_stop_timer(struct inet6_dev *idev) static void mld_ifc_start_timer(struct inet6_dev *idev, unsigned long delay) { - unsigned long tv = net_random() % delay; + unsigned long tv = prandom_u32() % delay; if (!mod_timer(&idev->mc_ifc_timer, jiffies+tv+2)) in6_dev_hold(idev); @@ -1030,7 +1030,7 @@ static void mld_ifc_stop_timer(struct inet6_dev *idev) static void mld_dad_start_timer(struct inet6_dev *idev, unsigned long delay) { - unsigned long tv = net_random() % delay; + unsigned long tv = prandom_u32() % delay; if (!mod_timer(&idev->mc_dad_timer, jiffies+tv+2)) in6_dev_hold(idev); @@ -1061,7 +1061,7 @@ static void igmp6_group_queried(struct ifmcaddr6 *ma, unsigned long resptime) } if (delay >= resptime) - delay = net_random() % resptime; + delay = prandom_u32() % resptime; ma->mca_timer.expires = jiffies + delay; if (!mod_timer(&ma->mca_timer, jiffies + delay)) @@ -2328,7 +2328,7 @@ static void igmp6_join_group(struct ifmcaddr6 *ma) igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REPORT); - delay = net_random() % unsolicited_report_interval(ma->idev); + delay = prandom_u32() % unsolicited_report_interval(ma->idev); spin_lock_bh(&ma->mca_lock); if (del_timer(&ma->mca_timer)) { diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 4c8e5c0aa1ab..59a1a85bcb3e 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1209,7 +1209,7 @@ void ip_vs_random_dropentry(struct net *net) * Randomly scan 1/32 of the whole table every second */ for (idx = 0; idx < (ip_vs_conn_tab_size>>5); idx++) { - unsigned int hash = net_random() & ip_vs_conn_tab_mask; + unsigned int hash = prandom_u32() & ip_vs_conn_tab_mask; hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) { if (cp->flags & IP_VS_CONN_F_TEMPLATE) diff --git a/net/netfilter/xt_statistic.c b/net/netfilter/xt_statistic.c index 4fe4fb4276d0..11de55e7a868 100644 --- a/net/netfilter/xt_statistic.c +++ b/net/netfilter/xt_statistic.c @@ -37,7 +37,7 @@ statistic_mt(const struct sk_buff *skb, struct xt_action_param *par) switch (info->mode) { case XT_STATISTIC_MODE_RANDOM: - if ((net_random() & 0x7FFFFFFF) < info->u.random.probability) + if ((prandom_u32() & 0x7FFFFFFF) < info->u.random.probability) ret = !ret; break; case XT_STATISTIC_MODE_NTH: diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 716b7eebfe70..2c77e7b1a913 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -445,7 +445,7 @@ static int sample(struct datapath *dp, struct sk_buff *skb, a = nla_next(a, &rem)) { switch (nla_type(a)) { case OVS_SAMPLE_ATTR_PROBABILITY: - if (net_random() >= nla_get_u32(a)) + if (prandom_u32() >= nla_get_u32(a)) return 0; break; diff --git a/net/rds/bind.c b/net/rds/bind.c index b5ad65a0067e..a2e6562da751 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -117,7 +117,7 @@ static int rds_add_bound(struct rds_sock *rs, __be32 addr, __be16 *port) rover = be16_to_cpu(*port); last = rover; } else { - rover = max_t(u16, net_random(), 2); + rover = max_t(u16, prandom_u32(), 2); last = rover - 1; } diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index f26e6b890cc7..31333073cd80 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -29,7 +29,7 @@ static struct tcf_hashinfo gact_hash_info; #ifdef CONFIG_GACT_PROB static int gact_net_rand(struct tcf_gact *gact) { - if (!gact->tcfg_pval || net_random() % gact->tcfg_pval) + if (!gact->tcfg_pval || prandom_u32() % gact->tcfg_pval) return gact->tcf_action; return gact->tcfg_paction; } diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 55786283a3df..ba5bc929eac7 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -390,7 +390,7 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt) sch->limit = 10*1024; q->flows_cnt = 1024; q->quantum = psched_mtu(qdisc_dev(sch)); - q->perturbation = net_random(); + q->perturbation = prandom_u32(); INIT_LIST_HEAD(&q->new_flows); INIT_LIST_HEAD(&q->old_flows); codel_params_init(&q->cparams); diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 1cf84a9e13aa..647680b1c625 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -607,7 +607,7 @@ static int hhf_init(struct Qdisc *sch, struct nlattr *opt) sch->limit = 1000; q->quantum = psched_mtu(qdisc_dev(sch)); - q->perturbation = net_random(); + q->perturbation = prandom_u32(); INIT_LIST_HEAD(&q->new_buckets); INIT_LIST_HEAD(&q->old_buckets); diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 090a4e3ecd0d..3019c10d6c56 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -169,7 +169,7 @@ static inline struct netem_skb_cb *netem_skb_cb(struct sk_buff *skb) static void init_crandom(struct crndstate *state, unsigned long rho) { state->rho = rho; - state->last = net_random(); + state->last = prandom_u32(); } /* get_crandom - correlated random number generator @@ -182,9 +182,9 @@ static u32 get_crandom(struct crndstate *state) unsigned long answer; if (state->rho == 0) /* no correlation */ - return net_random(); + return prandom_u32(); - value = net_random(); + value = prandom_u32(); rho = (u64)state->rho + 1; answer = (value * ((1ull<<32) - rho) + state->last * rho) >> 32; state->last = answer; @@ -198,7 +198,7 @@ static u32 get_crandom(struct crndstate *state) static bool loss_4state(struct netem_sched_data *q) { struct clgstate *clg = &q->clg; - u32 rnd = net_random(); + u32 rnd = prandom_u32(); /* * Makes a comparison between rnd and the transition @@ -264,15 +264,15 @@ static bool loss_gilb_ell(struct netem_sched_data *q) switch (clg->state) { case 1: - if (net_random() < clg->a1) + if (prandom_u32() < clg->a1) clg->state = 2; - if (net_random() < clg->a4) + if (prandom_u32() < clg->a4) return true; break; case 2: - if (net_random() < clg->a2) + if (prandom_u32() < clg->a2) clg->state = 1; - if (net_random() > clg->a3) + if (prandom_u32() > clg->a3) return true; } @@ -457,7 +457,8 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) skb_checksum_help(skb))) return qdisc_drop(skb, sch); - skb->data[net_random() % skb_headlen(skb)] ^= 1<<(net_random() % 8); + skb->data[prandom_u32() % skb_headlen(skb)] ^= + 1<<(prandom_u32() % 8); } if (unlikely(skb_queue_len(&sch->q) >= sch->limit)) diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index fe65340c8eb4..a255d0200a59 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -122,7 +122,7 @@ static bool drop_early(struct Qdisc *sch, u32 packet_size) else local_prob = q->vars.prob; - rnd = net_random(); + rnd = prandom_u32(); if (rnd < local_prob) return true; diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 30ea4674cabd..9b0f7093d970 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -220,7 +220,7 @@ static u32 sfb_compute_qlen(u32 *prob_r, u32 *avgpm_r, const struct sfb_sched_da static void sfb_init_perturbation(u32 slot, struct sfb_sched_data *q) { - q->bins[slot].perturbation = net_random(); + q->bins[slot].perturbation = prandom_u32(); } static void sfb_swap_slot(struct sfb_sched_data *q) @@ -381,7 +381,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch) goto enqueue; } - r = net_random() & SFB_MAX_PROB; + r = prandom_u32() & SFB_MAX_PROB; if (unlikely(r < p_min)) { if (unlikely(p_min > SFB_MAX_PROB / 2)) { diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 76f01e0258df..87317ff0b4ec 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -629,7 +629,7 @@ static void sfq_perturbation(unsigned long arg) spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); - q->perturbation = net_random(); + q->perturbation = prandom_u32(); if (!q->filter_list && q->tail) sfq_rehash(sch); spin_unlock(root_lock); @@ -698,7 +698,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) del_timer(&q->perturb_timer); if (q->perturb_period) { mod_timer(&q->perturb_timer, jiffies + q->perturb_period); - q->perturbation = net_random(); + q->perturbation = prandom_u32(); } sch_tree_unlock(sch); kfree(p); @@ -759,7 +759,7 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt) q->quantum = psched_mtu(qdisc_dev(sch)); q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum); q->perturb_period = 0; - q->perturbation = net_random(); + q->perturbation = prandom_u32(); if (opt) { int err = sfq_change(sch, opt); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index d32dae78a486..7cc62b922f12 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5926,7 +5926,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) inet_get_local_port_range(sock_net(sk), &low, &high); remaining = (high - low) + 1; - rover = net_random() % remaining + low; + rover = prandom_u32() % remaining + low; do { rover++; diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index a72de074172d..e521d20e1970 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -619,7 +619,7 @@ static void cache_limit_defers(void) /* Consider removing either the first or the last */ if (cache_defer_cnt > DFR_MAX) { - if (net_random() & 1) + if (prandom_u32() & 1) discard = list_entry(cache_defer_list.next, struct cache_deferred_req, recent); else diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 04199bc8416f..1750048130a7 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1188,7 +1188,7 @@ static inline __be32 xprt_alloc_xid(struct rpc_xprt *xprt) static inline void xprt_init_xid(struct rpc_xprt *xprt) { - xprt->xid = net_random(); + xprt->xid = prandom_u32(); } static void xprt_request_init(struct rpc_task *task, struct rpc_xprt *xprt) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index dd9d295813cf..75b045e1cd50 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1674,7 +1674,7 @@ static void xs_udp_timer(struct rpc_xprt *xprt, struct rpc_task *task) static unsigned short xs_get_random_port(void) { unsigned short range = xprt_max_resvport - xprt_min_resvport; - unsigned short rand = (unsigned short) net_random() % range; + unsigned short rand = (unsigned short) prandom_u32() % range; return rand + xprt_min_resvport; } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 62181486ead8..8d11d28991a4 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1565,7 +1565,7 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) } else { u32 spi = 0; for (h = 0; h < high-low+1; h++) { - spi = low + net_random()%(high-low+1); + spi = low + prandom_u32()%(high-low+1); x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family); if (x0 == NULL) { x->id.spi = htonl(spi); -- cgit v1.3-14-g43fede From 5bb025fae53889cc99a21058c5dd369bf8cce820 Mon Sep 17 00:00:00 2001 From: Veaceslav Falico Date: Tue, 14 Jan 2014 21:58:51 +0100 Subject: net: rename sysfs symlinks on device name change Currently, we don't rename the upper/lower_ifc symlinks in /sys/class/net/*/ , which might result stale/duplicate links/names. Fix this by adding netdev_adjacent_rename_links(dev, oldname) which renames all the upper/lower interface's links to dev from the upper/lower_oldname to the new name. We don't need a rollback because only we control these symlinks and if we fail to rename them - sysfs will anyway complain. Reported-by: Ding Tianhong CC: Ding Tianhong CC: "David S. Miller" CC: Eric Dumazet CC: Nicolas Dichtel CC: Cong Wang Signed-off-by: Veaceslav Falico Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + net/core/dev.c | 22 ++++++++++++++++++++++ 2 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5c88ab19b3eb..30f6513f3b4d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2941,6 +2941,7 @@ int netdev_master_upper_dev_link_private(struct net_device *dev, void *private); void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev); +void netdev_adjacent_rename_links(struct net_device *dev, char *oldname); void *netdev_lower_dev_get_private(struct net_device *dev, struct net_device *lower_dev); int skb_checksum_help(struct sk_buff *skb); diff --git a/net/core/dev.c b/net/core/dev.c index 130d3bd0ce6f..995755733997 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1119,6 +1119,8 @@ rollback: write_seqcount_end(&devnet_rename_seq); + netdev_adjacent_rename_links(dev, oldname); + write_lock_bh(&dev_base_lock); hlist_del_rcu(&dev->name_hlist); write_unlock_bh(&dev_base_lock); @@ -1138,6 +1140,7 @@ rollback: err = ret; write_seqcount_begin(&devnet_rename_seq); memcpy(dev->name, oldname, IFNAMSIZ); + memcpy(oldname, newname, IFNAMSIZ); goto rollback; } else { pr_err("%s: name change rollback failed: %d\n", @@ -4999,6 +5002,25 @@ void netdev_upper_dev_unlink(struct net_device *dev, } EXPORT_SYMBOL(netdev_upper_dev_unlink); +void netdev_adjacent_rename_links(struct net_device *dev, char *oldname) +{ + struct netdev_adjacent *iter; + + list_for_each_entry(iter, &dev->adj_list.upper, list) { + netdev_adjacent_sysfs_del(iter->dev, oldname, + &iter->dev->adj_list.lower); + netdev_adjacent_sysfs_add(iter->dev, dev, + &iter->dev->adj_list.lower); + } + + list_for_each_entry(iter, &dev->adj_list.lower, list) { + netdev_adjacent_sysfs_del(iter->dev, oldname, + &iter->dev->adj_list.upper); + netdev_adjacent_sysfs_add(iter->dev, dev, + &iter->dev->adj_list.upper); + } +} + void *netdev_lower_dev_get_private(struct net_device *dev, struct net_device *lower_dev) { -- cgit v1.3-14-g43fede From 286ab723d4b83d37deb4017008ef1444a95cfb0d Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 14 Jan 2014 15:18:47 -0800 Subject: etherdevice: Use ether_addr_copy to copy an Ethernet address Some systems can use the normally known u16 alignment of Ethernet addresses to save some code/text bytes and cycles. This does not change currently emitted code on x86 by gcc 4.8. Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index f344ac04f858..9c5529dc6d07 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -217,6 +217,28 @@ static inline void eth_hw_addr_random(struct net_device *dev) eth_random_addr(dev->dev_addr); } +/** + * ether_addr_copy - Copy an Ethernet address + * @dst: Pointer to a six-byte array Ethernet address destination + * @src: Pointer to a six-byte array Ethernet address source + * + * Please note: dst & src must both be aligned to u16. + */ +static inline void ether_addr_copy(u8 *dst, const u8 *src) +{ +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) + *(u32 *)dst = *(const u32 *)src; + *(u16 *)(dst + 4) = *(const u16 *)(src + 4); +#else + u16 *a = (u16 *)dst; + const u16 *b = (const u16 *)src; + + a[0] = b[0]; + a[1] = b[1]; + a[2] = b[2]; +#endif +} + /** * eth_hw_addr_inherit - Copy dev_addr from another net_device * @dst: pointer to net_device to copy dev_addr to @@ -229,7 +251,7 @@ static inline void eth_hw_addr_inherit(struct net_device *dst, struct net_device *src) { dst->addr_assign_type = src->addr_assign_type; - memcpy(dst->dev_addr, src->dev_addr, ETH_ALEN); + ether_addr_copy(dst->dev_addr, src->dev_addr); } /** -- cgit v1.3-14-g43fede From 9cbadf094d9d479413dc8cfa77dff9e732184337 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Thu, 16 Jan 2014 10:51:43 +0000 Subject: net: stmmac: support max-speed device tree property This patch adds support to "max-speed" property which is a standard Ethernet device tree property. max-speed specifies maximum speed (specified in megabits per second) supported the device. Depending on the clocking schemes some of the boards can only support few link speeds, so having a way to limit the link speed in the mac driver would allow such setups to work reliably. Without this patch there is no way to tell the driver to limit the link speed. Signed-off-by: Srinivas Kandagatla Acked-by: Giuseppe Cavallaro Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 +++- drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 4 ++++ include/linux/stmmac.h | 1 + 3 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index ecdc8ab50425..15192c05750f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -776,6 +776,7 @@ static int stmmac_init_phy(struct net_device *dev) char phy_id_fmt[MII_BUS_ID_SIZE + 3]; char bus_id[MII_BUS_ID_SIZE]; int interface = priv->plat->interface; + int max_speed = priv->plat->max_speed; priv->oldlink = 0; priv->speed = 0; priv->oldduplex = -1; @@ -800,7 +801,8 @@ static int stmmac_init_phy(struct net_device *dev) /* Stop Advertising 1000BASE Capability if interface is not GMII */ if ((interface == PHY_INTERFACE_MODE_MII) || - (interface == PHY_INTERFACE_MODE_RMII)) + (interface == PHY_INTERFACE_MODE_RMII) || + (max_speed < 1000 && max_speed > 0)) phydev->advertising &= ~(SUPPORTED_1000baseT_Half | SUPPORTED_1000baseT_Full); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 38bd1f4fbe33..9377ee623fa5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -42,6 +42,10 @@ static int stmmac_probe_config_dt(struct platform_device *pdev, *mac = of_get_mac_address(np); plat->interface = of_get_phy_mode(np); + /* Get max speed of operation from device tree */ + if (of_property_read_u32(np, "max-speed", &plat->max_speed)) + plat->max_speed = -1; + plat->bus_id = of_alias_get_id(np, "ethernet"); if (plat->bus_id < 0) plat->bus_id = 0; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index bb5deb0feb6b..33ace712e7e8 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -110,6 +110,7 @@ struct plat_stmmacenet_data { int force_sf_dma_mode; int force_thresh_dma_mode; int riwt_off; + int max_speed; void (*fix_mac_speed)(void *priv, unsigned int speed); void (*bus_setup)(void __iomem *ioaddr); int (*init)(struct platform_device *pdev); -- cgit v1.3-14-g43fede From 57bdf7f42be05640f8080b06844c94367ad1884b Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Wed, 15 Jan 2014 08:57:54 -0800 Subject: net: Add skb_get_hash_raw Function to just return skb->rxhash without checking to see if it needs to be recomputed. Signed-off-by: Tom Herbert Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 48b760505cb6..1f689e62e4cb 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -771,6 +771,11 @@ static inline __u32 skb_get_hash(struct sk_buff *skb) return skb->rxhash; } +static inline __u32 skb_get_hash_raw(const struct sk_buff *skb) +{ + return skb->rxhash; +} + static inline void skb_clear_hash(struct sk_buff *skb) { skb->rxhash = 0; -- cgit v1.3-14-g43fede From 1d486bfb66971ebacc2a46a23431ace9af70dc66 Mon Sep 17 00:00:00 2001 From: Veaceslav Falico Date: Thu, 16 Jan 2014 00:02:18 +0100 Subject: net: add NETDEV_PRECHANGEMTU to notify before mtu change happens Currently, if a device changes its mtu, first the change happens (invloving all the side effects), and after that the NETDEV_CHANGEMTU is sent so that other devices can catch up with the new mtu. However, if they return NOTIFY_BAD, then the change is reverted and error returned. This is a really long and costy operation (sometimes). To fix this, add NETDEV_PRECHANGEMTU notification which is called prior to any change actually happening, and if any callee returns NOTIFY_BAD - the change is aborted. This way we're skipping all the playing with apply/revert the mtu. CC: "David S. Miller" CC: Jiri Pirko CC: Eric Dumazet CC: Nicolas Dichtel CC: Cong Wang Signed-off-by: Veaceslav Falico Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 ++- net/core/dev.c | 5 +++++ 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 30f6513f3b4d..d7668b881d08 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1718,7 +1718,7 @@ struct pcpu_sw_netstats { #define NETDEV_CHANGE 0x0004 /* Notify device state change */ #define NETDEV_REGISTER 0x0005 #define NETDEV_UNREGISTER 0x0006 -#define NETDEV_CHANGEMTU 0x0007 +#define NETDEV_CHANGEMTU 0x0007 /* notify after mtu change happened */ #define NETDEV_CHANGEADDR 0x0008 #define NETDEV_GOING_DOWN 0x0009 #define NETDEV_CHANGENAME 0x000A @@ -1734,6 +1734,7 @@ struct pcpu_sw_netstats { #define NETDEV_JOIN 0x0014 #define NETDEV_CHANGEUPPER 0x0015 #define NETDEV_RESEND_IGMP 0x0016 +#define NETDEV_PRECHANGEMTU 0x0017 /* notify before mtu change happened */ int register_netdevice_notifier(struct notifier_block *nb); int unregister_netdevice_notifier(struct notifier_block *nb); diff --git a/net/core/dev.c b/net/core/dev.c index b2c1869b04e3..f87bedd51eed 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5392,6 +5392,11 @@ int dev_set_mtu(struct net_device *dev, int new_mtu) if (!netif_device_present(dev)) return -ENODEV; + err = call_netdevice_notifiers(NETDEV_PRECHANGEMTU, dev); + err = notifier_to_errno(err); + if (err) + return err; + orig_mtu = dev->mtu; err = __dev_set_mtu(dev, new_mtu); -- cgit v1.3-14-g43fede From a953be53ce40440acb4740edb48577b9468d4c3d Mon Sep 17 00:00:00 2001 From: Michael Dalton Date: Thu, 16 Jan 2014 22:23:28 -0800 Subject: net-sysfs: add support for device-specific rx queue sysfs attributes Extend existing support for netdevice receive queue sysfs attributes to permit a device-specific attribute group. Initial use case for this support will be to allow the virtio-net device to export per-receive queue mergeable receive buffer size. Signed-off-by: Michael Dalton Signed-off-by: David S. Miller --- include/linux/netdevice.h | 35 +++++++++++++++++++++++++++++---- net/core/dev.c | 12 ++++++------ net/core/net-sysfs.c | 50 +++++++++++++++++++++++++++-------------------- 3 files changed, 66 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d7668b881d08..e985231fe04b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -668,15 +668,28 @@ extern struct rps_sock_flow_table __rcu *rps_sock_flow_table; bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id, u16 filter_id); #endif +#endif /* CONFIG_RPS */ /* This structure contains an instance of an RX queue. */ struct netdev_rx_queue { +#ifdef CONFIG_RPS struct rps_map __rcu *rps_map; struct rps_dev_flow_table __rcu *rps_flow_table; +#endif struct kobject kobj; struct net_device *dev; } ____cacheline_aligned_in_smp; -#endif /* CONFIG_RPS */ + +/* + * RX queue sysfs structures and functions. + */ +struct rx_queue_attribute { + struct attribute attr; + ssize_t (*show)(struct netdev_rx_queue *queue, + struct rx_queue_attribute *attr, char *buf); + ssize_t (*store)(struct netdev_rx_queue *queue, + struct rx_queue_attribute *attr, const char *buf, size_t len); +}; #ifdef CONFIG_XPS /* @@ -1313,7 +1326,7 @@ struct net_device { unicast) */ -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS struct netdev_rx_queue *_rx; /* Number of RX queues allocated at register_netdev() time */ @@ -1424,6 +1437,8 @@ struct net_device { struct device dev; /* space for optional device, statistics, and wireless sysfs groups */ const struct attribute_group *sysfs_groups[4]; + /* space for optional per-rx queue attributes */ + const struct attribute_group *sysfs_rx_queue_group; /* rtnetlink link ops */ const struct rtnl_link_ops *rtnl_link_ops; @@ -2375,7 +2390,7 @@ static inline bool netif_is_multiqueue(const struct net_device *dev) int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq); -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq); #else static inline int netif_set_real_num_rx_queues(struct net_device *dev, @@ -2394,7 +2409,7 @@ static inline int netif_copy_real_num_queues(struct net_device *to_dev, from_dev->real_num_tx_queues); if (err) return err; -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS return netif_set_real_num_rx_queues(to_dev, from_dev->real_num_rx_queues); #else @@ -2402,6 +2417,18 @@ static inline int netif_copy_real_num_queues(struct net_device *to_dev, #endif } +#ifdef CONFIG_SYSFS +static inline unsigned int get_netdev_rx_queue_index( + struct netdev_rx_queue *queue) +{ + struct net_device *dev = queue->dev; + int index = queue - dev->_rx; + + BUG_ON(index >= dev->num_rx_queues); + return index; +} +#endif + #define DEFAULT_MAX_NUM_RSS_QUEUES (8) int netif_get_num_default_rss_queues(void); diff --git a/net/core/dev.c b/net/core/dev.c index f87bedd51eed..288df6232006 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2083,7 +2083,7 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) } EXPORT_SYMBOL(netif_set_real_num_tx_queues); -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS /** * netif_set_real_num_rx_queues - set actual number of RX queues used * @dev: Network device @@ -5764,7 +5764,7 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev, } EXPORT_SYMBOL(netif_stacked_transfer_operstate); -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS static int netif_alloc_rx_queues(struct net_device *dev) { unsigned int i, count = dev->num_rx_queues; @@ -6309,7 +6309,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, return NULL; } -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS if (rxqs < 1) { pr_err("alloc_netdev: Unable to allocate device with zero RX queues\n"); return NULL; @@ -6365,7 +6365,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, if (netif_alloc_netdev_queues(dev)) goto free_all; -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS dev->num_rx_queues = rxqs; dev->real_num_rx_queues = rxqs; if (netif_alloc_rx_queues(dev)) @@ -6385,7 +6385,7 @@ free_all: free_pcpu: free_percpu(dev->pcpu_refcnt); netif_free_tx_queues(dev); -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS kfree(dev->_rx); #endif @@ -6410,7 +6410,7 @@ void free_netdev(struct net_device *dev) release_net(dev_net(dev)); netif_free_tx_queues(dev); -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS kfree(dev->_rx); #endif diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 49843bf7e43e..7eeadeecc5a2 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -498,17 +498,7 @@ static struct attribute_group wireless_group = { #define net_class_groups NULL #endif /* CONFIG_SYSFS */ -#ifdef CONFIG_RPS -/* - * RX queue sysfs structures and functions. - */ -struct rx_queue_attribute { - struct attribute attr; - ssize_t (*show)(struct netdev_rx_queue *queue, - struct rx_queue_attribute *attr, char *buf); - ssize_t (*store)(struct netdev_rx_queue *queue, - struct rx_queue_attribute *attr, const char *buf, size_t len); -}; +#ifdef CONFIG_SYSFS #define to_rx_queue_attr(_attr) container_of(_attr, \ struct rx_queue_attribute, attr) @@ -543,6 +533,7 @@ static const struct sysfs_ops rx_queue_sysfs_ops = { .store = rx_queue_attr_store, }; +#ifdef CONFIG_RPS static ssize_t show_rps_map(struct netdev_rx_queue *queue, struct rx_queue_attribute *attribute, char *buf) { @@ -718,16 +709,20 @@ static struct rx_queue_attribute rps_cpus_attribute = static struct rx_queue_attribute rps_dev_flow_table_cnt_attribute = __ATTR(rps_flow_cnt, S_IRUGO | S_IWUSR, show_rps_dev_flow_table_cnt, store_rps_dev_flow_table_cnt); +#endif /* CONFIG_RPS */ static struct attribute *rx_queue_default_attrs[] = { +#ifdef CONFIG_RPS &rps_cpus_attribute.attr, &rps_dev_flow_table_cnt_attribute.attr, +#endif NULL }; static void rx_queue_release(struct kobject *kobj) { struct netdev_rx_queue *queue = to_rx_queue(kobj); +#ifdef CONFIG_RPS struct rps_map *map; struct rps_dev_flow_table *flow_table; @@ -743,6 +738,7 @@ static void rx_queue_release(struct kobject *kobj) RCU_INIT_POINTER(queue->rps_flow_table, NULL); call_rcu(&flow_table->rcu, rps_dev_flow_table_release); } +#endif memset(kobj, 0, sizeof(*kobj)); dev_put(queue->dev); @@ -763,25 +759,36 @@ static int rx_queue_add_kobject(struct net_device *net, int index) kobj->kset = net->queues_kset; error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL, "rx-%u", index); - if (error) { - kobject_put(kobj); - return error; + if (error) + goto exit; + + if (net->sysfs_rx_queue_group) { + error = sysfs_create_group(kobj, net->sysfs_rx_queue_group); + if (error) + goto exit; } kobject_uevent(kobj, KOBJ_ADD); dev_hold(queue->dev); + return error; +exit: + kobject_put(kobj); return error; } -#endif /* CONFIG_RPS */ +#endif /* CONFIG_SYFS */ int net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num) { -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS int i; int error = 0; +#ifndef CONFIG_RPS + if (!net->sysfs_rx_queue_group) + return 0; +#endif for (i = old_num; i < new_num; i++) { error = rx_queue_add_kobject(net, i); if (error) { @@ -790,8 +797,12 @@ net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num) } } - while (--i >= new_num) + while (--i >= new_num) { + if (net->sysfs_rx_queue_group) + sysfs_remove_group(&net->_rx[i].kobj, + net->sysfs_rx_queue_group); kobject_put(&net->_rx[i].kobj); + } return error; #else @@ -1155,9 +1166,6 @@ static int register_queue_kobjects(struct net_device *net) NULL, &net->dev.kobj); if (!net->queues_kset) return -ENOMEM; -#endif - -#ifdef CONFIG_RPS real_rx = net->real_num_rx_queues; #endif real_tx = net->real_num_tx_queues; @@ -1184,7 +1192,7 @@ static void remove_queue_kobjects(struct net_device *net) { int real_rx = 0, real_tx = 0; -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS real_rx = net->real_num_rx_queues; #endif real_tx = net->real_num_tx_queues; -- cgit v1.3-14-g43fede From 1d3ee88ae0d605629bf369ab0b868dae8ca62a48 Mon Sep 17 00:00:00 2001 From: "sfeldma@cumulusnetworks.com" Date: Thu, 16 Jan 2014 22:57:56 -0800 Subject: bonding: add netlink attributes to slave link dev If link is IFF_SLAVE, extend link dev netlink attributes to include slave attributes with new IFLA_SLAVE nest. Add netlink notification (RTM_NEWLINK) when slave status changes from backup to active, or visa-versa. Adds new ndo_get_slave op to net_device_ops to fill skb with IFLA_SLAVE attributes. Currently only used by bonding driver, but could be used by other aggregating devices with slaves. Signed-off-by: Scott Feldman Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 1 + drivers/net/bonding/bond_netlink.c | 36 +++++++++++++++++++++++++ drivers/net/bonding/bonding.h | 11 ++++++-- include/linux/netdevice.h | 5 ++++ include/uapi/linux/if_link.h | 13 +++++++++ net/core/rtnetlink.c | 54 ++++++++++++++++++++++++++++++++++++++ 6 files changed, 118 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index df85cec3e5d9..3220b488dd1e 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3883,6 +3883,7 @@ static const struct net_device_ops bond_netdev_ops = { #endif .ndo_add_slave = bond_enslave, .ndo_del_slave = bond_release, + .ndo_get_slave = bond_get_slave, .ndo_fix_features = bond_fix_features, }; diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index 555c7837d8e6..21c648854a8c 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -22,6 +22,42 @@ #include #include "bonding.h" +int bond_get_slave(struct net_device *slave_dev, struct sk_buff *skb) +{ + struct slave *slave = bond_slave_get_rtnl(slave_dev); + const struct aggregator *agg; + + if (nla_put_u8(skb, IFLA_SLAVE_STATE, bond_slave_state(slave))) + goto nla_put_failure; + + if (nla_put_u8(skb, IFLA_SLAVE_MII_STATUS, slave->link)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_SLAVE_LINK_FAILURE_COUNT, + slave->link_failure_count)) + goto nla_put_failure; + + if (nla_put(skb, IFLA_SLAVE_PERM_HWADDR, + slave_dev->addr_len, slave->perm_hwaddr)) + goto nla_put_failure; + + if (nla_put_u16(skb, IFLA_SLAVE_QUEUE_ID, slave->queue_id)) + goto nla_put_failure; + + if (slave->bond->params.mode == BOND_MODE_8023AD) { + agg = SLAVE_AD_INFO(slave).port.aggregator; + if (agg) + if (nla_put_u16(skb, IFLA_SLAVE_AD_AGGREGATOR_ID, + agg->aggregator_identifier)) + goto nla_put_failure; + } + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = { [IFLA_BOND_MODE] = { .type = NLA_U8 }, [IFLA_BOND_ACTIVE_SLAVE] = { .type = NLA_U32 }, diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h index 309757d8482b..8a935f8f2b3c 100644 --- a/drivers/net/bonding/bonding.h +++ b/drivers/net/bonding/bonding.h @@ -285,12 +285,18 @@ static inline bool bond_is_lb(const struct bonding *bond) static inline void bond_set_active_slave(struct slave *slave) { - slave->backup = 0; + if (slave->backup) { + slave->backup = 0; + rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_KERNEL); + } } static inline void bond_set_backup_slave(struct slave *slave) { - slave->backup = 1; + if (!slave->backup) { + slave->backup = 1; + rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_KERNEL); + } } static inline int bond_slave_state(struct slave *slave) @@ -426,6 +432,7 @@ int bond_sysfs_slave_add(struct slave *slave); void bond_sysfs_slave_del(struct slave *slave); int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev); int bond_release(struct net_device *bond_dev, struct net_device *slave_dev); +int bond_get_slave(struct net_device *slave_dev, struct sk_buff *skb); int bond_xmit_hash(struct bonding *bond, struct sk_buff *skb, int count); int bond_parse_parm(const char *mode_arg, const struct bond_parm_tbl *tbl); int bond_parm_tbl_lookup(int mode, const struct bond_parm_tbl *tbl); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e985231fe04b..83ce2aee65e6 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -921,6 +921,9 @@ struct netdev_phys_port_id { * int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev); * Called to release previously enslaved netdev. * + * int (*ndo_get_slave)(struct net_device *slave_dev, struct sk_buff *skb); + * Called to fill netlink skb with slave info. + * * Feature/offload setting functions. * netdev_features_t (*ndo_fix_features)(struct net_device *dev, * netdev_features_t features); @@ -1093,6 +1096,8 @@ struct net_device_ops { struct net_device *slave_dev); int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev); + int (*ndo_get_slave)(struct net_device *slave_dev, + struct sk_buff *skb); netdev_features_t (*ndo_fix_features)(struct net_device *dev, netdev_features_t features); int (*ndo_set_features)(struct net_device *dev, diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 3e6bd3c7445d..ba2f3bf5fdf5 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -144,6 +144,7 @@ enum { IFLA_NUM_RX_QUEUES, IFLA_CARRIER, IFLA_PHYS_PORT_ID, + IFLA_SLAVE, __IFLA_MAX }; @@ -368,6 +369,18 @@ enum { #define IFLA_BOND_AD_INFO_MAX (__IFLA_BOND_AD_INFO_MAX - 1) +enum { + IFLA_SLAVE_STATE, + IFLA_SLAVE_MII_STATUS, + IFLA_SLAVE_LINK_FAILURE_COUNT, + IFLA_SLAVE_PERM_HWADDR, + IFLA_SLAVE_QUEUE_ID, + IFLA_SLAVE_AD_AGGREGATOR_ID, + __IFLA_SLAVE_MAX, +}; + +#define IFLA_SLAVE_MAX (__IFLA_SLAVE_MAX - 1) + /* SR-IOV virtual function management section */ enum { diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index e6e7d582f901..4f85de7aca33 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -721,6 +721,28 @@ static size_t rtnl_port_size(const struct net_device *dev) return port_self_size; } +static size_t rtnl_bond_slave_size(const struct net_device *dev) +{ + struct net_device *bond; + size_t slave_size = + nla_total_size(sizeof(struct nlattr)) + /* IFLA_SLAVE */ + nla_total_size(1) + /* IFLA_SLAVE_STATE */ + nla_total_size(1) + /* IFLA_SLAVE_MII_STATUS */ + nla_total_size(4) + /* IFLA_SLAVE_LINK_FAILURE_COUNT */ + nla_total_size(MAX_ADDR_LEN) + /* IFLA_SLAVE_PERM_HWADDR */ + nla_total_size(2) + /* IFLA_SLAVE_QUEUE_ID */ + nla_total_size(2) + /* IFLA_SLAVE_AD_AGGREGATOR_ID */ + 0; + + if (netif_is_bond_slave((struct net_device *)dev)) { + bond = netdev_master_upper_dev_get((struct net_device *)dev); + if (bond && bond->netdev_ops->ndo_get_slave) + return slave_size; + } + + return 0; +} + static noinline size_t if_nlmsg_size(const struct net_device *dev, u32 ext_filter_mask) { @@ -750,6 +772,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ + rtnl_link_get_size(dev) /* IFLA_LINKINFO */ + rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */ + + rtnl_bond_slave_size(dev) /* IFLA_SLAVE */ + nla_total_size(MAX_PHYS_PORT_ID_LEN); /* IFLA_PHYS_PORT_ID */ } @@ -847,6 +870,34 @@ static int rtnl_phys_port_id_fill(struct sk_buff *skb, struct net_device *dev) return 0; } +static size_t rtnl_bond_slave_fill(struct sk_buff *skb, struct net_device *dev) +{ + struct net_device *bond; + struct nlattr *nest; + int err; + + if (!netif_is_bond_slave(dev)) + return 0; + + bond = netdev_master_upper_dev_get(dev); + if (!bond || !bond->netdev_ops->ndo_get_slave) + return 0; + + nest = nla_nest_start(skb, IFLA_SLAVE); + if (!nest) + return -EMSGSIZE; + + err = bond->netdev_ops->ndo_get_slave(dev, skb); + if (err) { + nla_nest_cancel(skb, nest); + return (err == -EMSGSIZE) ? err : 0; + } + + nla_nest_end(skb, nest); + + return 0; +} + static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, unsigned int flags, u32 ext_filter_mask) @@ -1001,6 +1052,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, if (rtnl_port_fill(skb, dev)) goto nla_put_failure; + if (rtnl_bond_slave_fill(skb, dev)) + goto nla_put_failure; + if (dev->rtnl_link_ops) { if (rtnl_link_fill(skb, dev) < 0) goto nla_put_failure; -- cgit v1.3-14-g43fede From ea02f9411d9faa3553ed09ce0ec9f00ceae9885e Mon Sep 17 00:00:00 2001 From: Michal Sekletar Date: Fri, 17 Jan 2014 17:09:45 +0100 Subject: net: introduce SO_BPF_EXTENSIONS For user space packet capturing libraries such as libpcap, there's currently only one way to check which BPF extensions are supported by the kernel, that is, commit aa1113d9f85d ("net: filter: return -EINVAL if BPF_S_ANC* operation is not supported"). For querying all extensions at once this might be rather inconvenient. Therefore, this patch introduces a new option which can be used as an argument for getsockopt(), and allows one to obtain information about which BPF extensions are supported by the current kernel. As David Miller suggests, we do not need to define any bits right now and status quo can just return 0 in order to state that this versions supports SKF_AD_PROTOCOL up to SKF_AD_PAY_OFFSET. Later additions to BPF extensions need to add their bits to the bpf_tell_extensions() function, as documented in the comment. Signed-off-by: Michal Sekletar Cc: David Miller Reviewed-by: Daniel Borkmann Signed-off-by: David S. Miller --- arch/alpha/include/uapi/asm/socket.h | 2 ++ arch/avr32/include/uapi/asm/socket.h | 2 ++ arch/cris/include/uapi/asm/socket.h | 2 ++ arch/frv/include/uapi/asm/socket.h | 2 ++ arch/ia64/include/uapi/asm/socket.h | 2 ++ arch/m32r/include/uapi/asm/socket.h | 2 ++ arch/mips/include/uapi/asm/socket.h | 2 ++ arch/mn10300/include/uapi/asm/socket.h | 2 ++ arch/parisc/include/uapi/asm/socket.h | 2 ++ arch/powerpc/include/uapi/asm/socket.h | 2 ++ arch/s390/include/uapi/asm/socket.h | 2 ++ arch/sparc/include/uapi/asm/socket.h | 2 ++ arch/xtensa/include/uapi/asm/socket.h | 2 ++ include/linux/filter.h | 11 +++++++++++ include/uapi/asm-generic/socket.h | 2 ++ net/core/sock.c | 4 ++++ 16 files changed, 43 insertions(+) (limited to 'include/linux') diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index e3a1491d5073..3de1394bcab8 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -85,4 +85,6 @@ #define SO_MAX_PACING_RATE 47 +#define SO_BPF_EXTENSIONS 48 + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/avr32/include/uapi/asm/socket.h b/arch/avr32/include/uapi/asm/socket.h index cbf902e4cd9e..6e6cd159924b 100644 --- a/arch/avr32/include/uapi/asm/socket.h +++ b/arch/avr32/include/uapi/asm/socket.h @@ -78,4 +78,6 @@ #define SO_MAX_PACING_RATE 47 +#define SO_BPF_EXTENSIONS 48 + #endif /* _UAPI__ASM_AVR32_SOCKET_H */ diff --git a/arch/cris/include/uapi/asm/socket.h b/arch/cris/include/uapi/asm/socket.h index 13829aaaeec5..ed94e5ed0a23 100644 --- a/arch/cris/include/uapi/asm/socket.h +++ b/arch/cris/include/uapi/asm/socket.h @@ -80,6 +80,8 @@ #define SO_MAX_PACING_RATE 47 +#define SO_BPF_EXTENSIONS 48 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h index 5d4299762426..ca2c6e6f31c6 100644 --- a/arch/frv/include/uapi/asm/socket.h +++ b/arch/frv/include/uapi/asm/socket.h @@ -78,5 +78,7 @@ #define SO_MAX_PACING_RATE 47 +#define SO_BPF_EXTENSIONS 48 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h index c25302fb48d9..a1b49bac7951 100644 --- a/arch/ia64/include/uapi/asm/socket.h +++ b/arch/ia64/include/uapi/asm/socket.h @@ -87,4 +87,6 @@ #define SO_MAX_PACING_RATE 47 +#define SO_BPF_EXTENSIONS 48 + #endif /* _ASM_IA64_SOCKET_H */ diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h index 52966650114f..6c9a24b3aefa 100644 --- a/arch/m32r/include/uapi/asm/socket.h +++ b/arch/m32r/include/uapi/asm/socket.h @@ -78,4 +78,6 @@ #define SO_MAX_PACING_RATE 47 +#define SO_BPF_EXTENSIONS 48 + #endif /* _ASM_M32R_SOCKET_H */ diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 0df9787cd84d..a14baa218c76 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -96,4 +96,6 @@ #define SO_MAX_PACING_RATE 47 +#define SO_BPF_EXTENSIONS 48 + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h index 71dedcae55a6..6aa3ce1854aa 100644 --- a/arch/mn10300/include/uapi/asm/socket.h +++ b/arch/mn10300/include/uapi/asm/socket.h @@ -78,4 +78,6 @@ #define SO_MAX_PACING_RATE 47 +#define SO_BPF_EXTENSIONS 48 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index 70b3674dac4e..fe35ceacf0e7 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -77,4 +77,6 @@ #define SO_MAX_PACING_RATE 0x4028 +#define SO_BPF_EXTENSIONS 0x4029 + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h index fa698324a1fd..a9c3e2e18c05 100644 --- a/arch/powerpc/include/uapi/asm/socket.h +++ b/arch/powerpc/include/uapi/asm/socket.h @@ -85,4 +85,6 @@ #define SO_MAX_PACING_RATE 47 +#define SO_BPF_EXTENSIONS 48 + #endif /* _ASM_POWERPC_SOCKET_H */ diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h index c286c2e868f0..e031332096d7 100644 --- a/arch/s390/include/uapi/asm/socket.h +++ b/arch/s390/include/uapi/asm/socket.h @@ -84,4 +84,6 @@ #define SO_MAX_PACING_RATE 47 +#define SO_BPF_EXTENSIONS 48 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 0f21e9a5ca18..54d9608681b6 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -74,6 +74,8 @@ #define SO_MAX_PACING_RATE 0x0031 +#define SO_BPF_EXTENSIONS 0x0032 + /* Security levels - as per NRL IPv6 - don't actually do anything */ #define SO_SECURITY_AUTHENTICATION 0x5001 #define SO_SECURITY_ENCRYPTION_TRANSPORT 0x5002 diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h index 7db5c22faa68..39acec0cf0b1 100644 --- a/arch/xtensa/include/uapi/asm/socket.h +++ b/arch/xtensa/include/uapi/asm/socket.h @@ -89,4 +89,6 @@ #define SO_MAX_PACING_RATE 47 +#define SO_BPF_EXTENSIONS 48 + #endif /* _XTENSA_SOCKET_H */ diff --git a/include/linux/filter.h b/include/linux/filter.h index ff4e40cd45b1..1a95a2dcf113 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -83,6 +83,17 @@ static inline void bpf_jit_free(struct sk_filter *fp) #define SK_RUN_FILTER(FILTER, SKB) sk_run_filter(SKB, FILTER->insns) #endif +static inline int bpf_tell_extensions(void) +{ + /* When adding new BPF extension it is necessary to enumerate + * it here, so userspace software which wants to know what is + * supported can do so by inspecting return value of this + * function + */ + + return 0; +} + enum { BPF_S_RET_K = 1, BPF_S_RET_A, diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 38f14d0264c3..ea0796bdcf88 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -80,4 +80,6 @@ #define SO_MAX_PACING_RATE 47 +#define SO_BPF_EXTENSIONS 48 + #endif /* __ASM_GENERIC_SOCKET_H */ diff --git a/net/core/sock.c b/net/core/sock.c index b3f7ee3008a0..0c127dcdf6a8 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1167,6 +1167,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sock_flag(sk, SOCK_FILTER_LOCKED); break; + case SO_BPF_EXTENSIONS: + v.val = bpf_tell_extensions(); + break; + case SO_SELECT_ERR_QUEUE: v.val = sock_flag(sk, SOCK_SELECT_ERR_QUEUE); break; -- cgit v1.3-14-g43fede From df3687ffc6653e4d32168338b4dee20c164ed7c9 Mon Sep 17 00:00:00 2001 From: Florent Fourcot Date: Fri, 17 Jan 2014 17:15:03 +0100 Subject: ipv6: add the IPV6_FL_F_REFLECT flag to IPV6_FL_A_GET With this option, the socket will reply with the flow label value read on received packets. The goal is to have a connection with the same flow label in both direction of the communication. Changelog of V4: * Do not erase the flow label on the listening socket. Use pktopts to store the received value Signed-off-by: Florent Fourcot Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + include/uapi/linux/in6.h | 1 + net/ipv6/ip6_flowlabel.c | 21 +++++++++++++++++++++ net/ipv6/tcp_ipv6.c | 12 +++++++++++- 4 files changed, 34 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 7e1ded0d8e45..1084304fd75a 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -191,6 +191,7 @@ struct ipv6_pinfo { /* sockopt flags */ __u16 recverr:1, sndflow:1, + repflow:1, pmtudisc:3, ipv6only:1, srcprefs:3, /* 001: prefer temporary address diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h index f94f1d013bf2..02c0cd685a27 100644 --- a/include/uapi/linux/in6.h +++ b/include/uapi/linux/in6.h @@ -85,6 +85,7 @@ struct in6_flowlabel_req { #define IPV6_FL_F_CREATE 1 #define IPV6_FL_F_EXCL 2 +#define IPV6_FL_F_REFLECT 4 #define IPV6_FL_S_NONE 0 #define IPV6_FL_S_EXCL 1 diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index cbc93517b455..55823f187446 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -486,6 +486,11 @@ int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq) struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_fl_socklist *sfl; + if (np->repflow) { + freq->flr_label = np->flow_label; + return 0; + } + rcu_read_lock_bh(); for_each_sk_fl_rcu(np, sfl) { @@ -527,6 +532,15 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) switch (freq.flr_action) { case IPV6_FL_A_PUT: + if (freq.flr_flags & IPV6_FL_F_REFLECT) { + if (sk->sk_protocol != IPPROTO_TCP) + return -ENOPROTOOPT; + if (!np->repflow) + return -ESRCH; + np->flow_label = 0; + np->repflow = 0; + return 0; + } spin_lock_bh(&ip6_sk_fl_lock); for (sflp = &np->ipv6_fl_list; (sfl = rcu_dereference(*sflp))!=NULL; @@ -567,6 +581,13 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) return -ESRCH; case IPV6_FL_A_GET: + if (freq.flr_flags & IPV6_FL_F_REFLECT) { + if (sk->sk_protocol != IPPROTO_TCP) + return -ENOPROTOOPT; + np->repflow = 1; + return 0; + } + if (freq.flr_label & ~IPV6_FLOWLABEL_MASK) return -EINVAL; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index b5512696e9ed..b61fa8bac3bd 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -483,6 +483,9 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst, &ireq->ir_v6_rmt_addr); fl6->daddr = ireq->ir_v6_rmt_addr; + if (np->repflow && (ireq->pktopts != NULL)) + fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts)); + skb_set_queue_mapping(skb, queue_mapping); err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass); err = net_xmit_eval(err); @@ -1018,7 +1021,8 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (!isn) { if (ipv6_opt_accepted(sk, skb) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || - np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) { + np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim || + np->repflow) { atomic_inc(&skb->users); ireq->pktopts = skb; } @@ -1143,6 +1147,8 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newnp->mcast_oif = inet6_iif(skb); newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb)); + if (np->repflow) + newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb)); /* * No need to charge this sock to the relevant IPv6 refcnt debug socks count @@ -1223,6 +1229,8 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newnp->mcast_oif = inet6_iif(skb); newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb)); + if (np->repflow) + newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb)); /* Clone native IPv6 options from listening socket (if any) @@ -1434,6 +1442,8 @@ ipv6_pktoptions: np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit; if (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass) np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb)); + if (np->repflow) + np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb)); if (ipv6_opt_accepted(sk, opt_skb)) { skb_set_owner_r(opt_skb, sk); opt_skb = xchg(&np->pktoptions, opt_skb); -- cgit v1.3-14-g43fede From 4b261c75a99f29c93a0b6babfc180cdf566bd654 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Mon, 20 Jan 2014 03:43:08 +0100 Subject: ipv6: make IPV6_RECVPKTINFO work for ipv4 datagrams We currently don't report IPV6_RECVPKTINFO in cmsg access ancillary data for IPv4 datagrams on IPv6 sockets. This patch splits the ip6_datagram_recv_ctl into two functions, one which handles both protocol families, AF_INET and AF_INET6, while the ip6_datagram_recv_specific_ctl only handles IPv6 cmsg data. ip6_datagram_recv_*_ctl never reported back any errors, so we can make them return void. Also provide a helper for protocols which don't offer dual personality to further use ip6_datagram_recv_ctl, which is exported to modules. I needed to shuffle the code for ping around a bit to make it easier to implement dual personality for ping ipv6 sockets in future. Reported-by: Gert Doering Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/linux/ipv6.h | 3 +++ include/net/ip.h | 1 + include/net/ping.h | 8 ++++++-- include/net/transp_v6.h | 9 +++++++-- net/ipv4/ip_sockglue.c | 6 +++--- net/ipv4/ping.c | 7 ++++++- net/ipv6/datagram.c | 38 ++++++++++++++++++++++++++++++-------- net/ipv6/ipv6_sockglue.c | 4 +--- net/ipv6/ping.c | 10 ++++++---- net/ipv6/udp.c | 6 +++++- 10 files changed, 68 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 1084304fd75a..2faef339d8f2 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -284,6 +284,8 @@ static inline void inet_sk_copy_descendant(struct sock *sk_to, #define __ipv6_only_sock(sk) (inet6_sk(sk)->ipv6only) #define ipv6_only_sock(sk) ((sk)->sk_family == PF_INET6 && __ipv6_only_sock(sk)) +#define ipv6_sk_rxinfo(sk) ((sk)->sk_family == PF_INET6 && \ + inet6_sk(sk)->rxopt.bits.rxinfo) static inline const struct in6_addr *inet6_rcv_saddr(const struct sock *sk) { @@ -300,6 +302,7 @@ static inline int inet_v6_ipv6only(const struct sock *sk) #else #define __ipv6_only_sock(sk) 0 #define ipv6_only_sock(sk) 0 +#define ipv6_sk_rxinfo(sk) 0 static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk) { diff --git a/include/net/ip.h b/include/net/ip.h index 7876e3b96ce3..23be0fd37937 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -63,6 +63,7 @@ struct ipcm_cookie { }; #define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb)) +#define PKTINFO_SKB_CB(skb) ((struct in_pktinfo *)((skb)->cb)) struct ip_ra_chain { struct ip_ra_chain __rcu *next; diff --git a/include/net/ping.h b/include/net/ping.h index 76013653e08c..026479b61a2d 100644 --- a/include/net/ping.h +++ b/include/net/ping.h @@ -33,8 +33,12 @@ struct pingv6_ops { int (*ipv6_recv_error)(struct sock *sk, struct msghdr *msg, int len, int *addr_len); - int (*ip6_datagram_recv_ctl)(struct sock *sk, struct msghdr *msg, - struct sk_buff *skb); + void (*ip6_datagram_recv_common_ctl)(struct sock *sk, + struct msghdr *msg, + struct sk_buff *skb); + void (*ip6_datagram_recv_specific_ctl)(struct sock *sk, + struct msghdr *msg, + struct sk_buff *skb); int (*icmpv6_err_convert)(u8 type, u8 code, int *err); void (*ipv6_icmp_error)(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload); diff --git a/include/net/transp_v6.h b/include/net/transp_v6.h index 48660e50ae90..b927413dde86 100644 --- a/include/net/transp_v6.h +++ b/include/net/transp_v6.h @@ -32,8 +32,13 @@ void tcpv6_exit(void); int udpv6_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); -int ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, - struct sk_buff *skb); +/* this does all the common and the specific ctl work */ +void ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, + struct sk_buff *skb); +void ip6_datagram_recv_common_ctl(struct sock *sk, struct msghdr *msg, + struct sk_buff *skb); +void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg, + struct sk_buff *skb); int ip6_datagram_send_ctl(struct net *net, struct sock *sk, struct msghdr *msg, struct flowi6 *fl6, struct ipv6_txoptions *opt, diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 22f15eb1c260..580dd96666e0 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -56,7 +56,6 @@ /* * SOL_IP control messages. */ -#define PKTINFO_SKB_CB(__skb) ((struct in_pktinfo *)((__skb)->cb)) static void ip_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb) { @@ -1055,9 +1054,10 @@ e_inval: void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb) { struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb); + bool prepare = (inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO) || + ipv6_sk_rxinfo(sk); - if ((inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO) && - skb_rtable(skb)) { + if (prepare && skb_rtable(skb)) { pktinfo->ipi_ifindex = inet_iif(skb); pktinfo->ipi_spec_dst.s_addr = fib_compute_spec_dst(skb); } else { diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index e09e8839d622..4a9e4266a0c3 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -906,7 +906,12 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, } if (inet6_sk(sk)->rxopt.all) - pingv6_ops.ip6_datagram_recv_ctl(sk, msg, skb); + pingv6_ops.ip6_datagram_recv_common_ctl(sk, msg, skb); + if (skb->protocol == htons(ETH_P_IPV6) && + inet6_sk(sk)->rxopt.all) + pingv6_ops.ip6_datagram_recv_specific_ctl(sk, msg, skb); + else if (skb->protocol == htons(ETH_P_IP) && isk->cmsg_flags) + ip_cmsg_recv(msg, skb); #endif } else { BUG(); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index bce73cbd203a..cd8699bd2e6b 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -377,10 +377,12 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) sin->sin6_family = AF_INET6; sin->sin6_flowinfo = 0; sin->sin6_port = 0; + if (np->rxopt.all) + ip6_datagram_recv_common_ctl(sk, msg, skb); if (skb->protocol == htons(ETH_P_IPV6)) { sin->sin6_addr = ipv6_hdr(skb)->saddr; if (np->rxopt.all) - ip6_datagram_recv_ctl(sk, msg, skb); + ip6_datagram_recv_specific_ctl(sk, msg, skb); sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr, IP6CB(skb)->iif); @@ -471,20 +473,34 @@ out: } -int ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, - struct sk_buff *skb) +void ip6_datagram_recv_common_ctl(struct sock *sk, struct msghdr *msg, + struct sk_buff *skb) { struct ipv6_pinfo *np = inet6_sk(sk); - struct inet6_skb_parm *opt = IP6CB(skb); - unsigned char *nh = skb_network_header(skb); + bool is_ipv6 = skb->protocol == htons(ETH_P_IPV6); if (np->rxopt.bits.rxinfo) { struct in6_pktinfo src_info; - src_info.ipi6_ifindex = opt->iif; - src_info.ipi6_addr = ipv6_hdr(skb)->daddr; + if (is_ipv6) { + src_info.ipi6_ifindex = IP6CB(skb)->iif; + src_info.ipi6_addr = ipv6_hdr(skb)->daddr; + } else { + src_info.ipi6_ifindex = + PKTINFO_SKB_CB(skb)->ipi_ifindex; + ipv6_addr_set_v4mapped(ip_hdr(skb)->daddr, + &src_info.ipi6_addr); + } put_cmsg(msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info); } +} + +void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg, + struct sk_buff *skb) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + struct inet6_skb_parm *opt = IP6CB(skb); + unsigned char *nh = skb_network_header(skb); if (np->rxopt.bits.rxhlim) { int hlim = ipv6_hdr(skb)->hop_limit; @@ -602,7 +618,13 @@ int ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, put_cmsg(msg, SOL_IPV6, IPV6_ORIGDSTADDR, sizeof(sin6), &sin6); } } - return 0; +} + +void ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, + struct sk_buff *skb) +{ + ip6_datagram_recv_common_ctl(sk, msg, skb); + ip6_datagram_recv_specific_ctl(sk, msg, skb); } EXPORT_SYMBOL_GPL(ip6_datagram_recv_ctl); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 7024a874e901..0a00f449de5e 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -1002,10 +1002,8 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, release_sock(sk); if (skb) { - int err = ip6_datagram_recv_ctl(sk, &msg, skb); + ip6_datagram_recv_ctl(sk, &msg, skb); kfree_skb(skb); - if (err) - return err; } else { if (np->rxopt.bits.rxinfo) { struct in6_pktinfo src_info; diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index cd71f3a540be..94a3d04c3200 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -62,10 +62,9 @@ static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, { return -EAFNOSUPPORT; } -static int dummy_ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, +static void dummy_ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) { - return -EAFNOSUPPORT; } static int dummy_icmpv6_err_convert(u8 type, u8 code, int *err) { @@ -254,7 +253,9 @@ int __init pingv6_init(void) return ret; #endif pingv6_ops.ipv6_recv_error = ipv6_recv_error; - pingv6_ops.ip6_datagram_recv_ctl = ip6_datagram_recv_ctl; + pingv6_ops.ip6_datagram_recv_common_ctl = ip6_datagram_recv_common_ctl; + pingv6_ops.ip6_datagram_recv_specific_ctl = + ip6_datagram_recv_specific_ctl; pingv6_ops.icmpv6_err_convert = icmpv6_err_convert; pingv6_ops.ipv6_icmp_error = ipv6_icmp_error; pingv6_ops.ipv6_chk_addr = ipv6_chk_addr; @@ -267,7 +268,8 @@ int __init pingv6_init(void) void pingv6_exit(void) { pingv6_ops.ipv6_recv_error = dummy_ipv6_recv_error; - pingv6_ops.ip6_datagram_recv_ctl = dummy_ip6_datagram_recv_ctl; + pingv6_ops.ip6_datagram_recv_common_ctl = dummy_ip6_datagram_recv_ctl; + pingv6_ops.ip6_datagram_recv_specific_ctl = dummy_ip6_datagram_recv_ctl; pingv6_ops.icmpv6_err_convert = dummy_icmpv6_err_convert; pingv6_ops.ipv6_icmp_error = dummy_ipv6_icmp_error; pingv6_ops.ipv6_chk_addr = dummy_ipv6_chk_addr; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 233c3ab6aee4..1e586d92260e 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -477,12 +477,16 @@ try_again: } *addr_len = sizeof(*sin6); } + + if (np->rxopt.all) + ip6_datagram_recv_common_ctl(sk, msg, skb); + if (is_udp4) { if (inet->cmsg_flags) ip_cmsg_recv(msg, skb); } else { if (np->rxopt.all) - ip6_datagram_recv_ctl(sk, msg, skb); + ip6_datagram_recv_specific_ctl(sk, msg, skb); } err = copied; -- cgit v1.3-14-g43fede From 31956660693f130ff1de1040725e0636adb9261f Mon Sep 17 00:00:00 2001 From: Jean Sacren Date: Sun, 19 Jan 2014 15:24:53 -0700 Subject: sctp: fix missing SCTP mailing list address update The commit 91705c61b5202 ("net: sctp: trivial: update mailing list address") updated almost all the SCTP mailing list address from "lksctp-developers@lists.sourceforge.net" to "linux-sctp@vger.kernel.org" except for the one in include/linux/sctp.h file. Fix this way trivial one so that all is updated. Signed-off-by: Jean Sacren Cc: Daniel Borkmann Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/sctp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index c4c5eba26d9f..a9414fd49dc6 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -28,7 +28,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers + * lksctp developers * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp -- cgit v1.3-14-g43fede From 938dfdaa3c0f92e9a490d324f3bce43bbaef7632 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Fri, 17 Jan 2014 21:24:42 +0800 Subject: net: stmmac: Allocate and pass soc/board specific data to callbacks The current .init and .exit callbacks requires access to driver private data structures. This is not a good seperation and abstraction. Instead, we add a new .setup callback for allocating private data, and pass the returned pointer to the other callbacks. Signed-off-by: Chen-Yu Tsai Signed-off-by: David S. Miller --- Documentation/networking/stmmac.txt | 12 ++++++++---- drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 18 ++++++++++++++---- include/linux/stmmac.h | 6 ++++-- 3 files changed, 26 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/Documentation/networking/stmmac.txt b/Documentation/networking/stmmac.txt index cdd916da838d..2090895b08d4 100644 --- a/Documentation/networking/stmmac.txt +++ b/Documentation/networking/stmmac.txt @@ -127,8 +127,9 @@ struct plat_stmmacenet_data { int riwt_off; void (*fix_mac_speed)(void *priv, unsigned int speed); void (*bus_setup)(void __iomem *ioaddr); - int (*init)(struct platform_device *pdev); - void (*exit)(struct platform_device *pdev); + void *(*setup)(struct platform_device *pdev); + int (*init)(struct platform_device *pdev, void *priv); + void (*exit)(struct platform_device *pdev, void *priv); void *custom_cfg; void *custom_data; void *bsp_priv; @@ -169,10 +170,13 @@ Where: o bus_setup: perform HW setup of the bus. For example, on some ST platforms this field is used to configure the AMBA bridge to generate more efficient STBus traffic. - o init/exit: callbacks used for calling a custom initialization; + o setup/init/exit: callbacks used for calling a custom initialization; this is sometime necessary on some platforms (e.g. ST boxes) where the HW needs to have set some PIO lines or system cfg - registers. + registers. setup should return a pointer to private data, + which will be stored in bsp_priv, and then passed to init and + exit callbacks. init/exit callbacks should not use or modify + platform data. o custom_cfg/custom_data: this is a custom configuration that can be passed while initializing the resources. o bsp_priv: another private pointer. diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index cc6b89a75f99..704a5e0069c0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -144,9 +144,16 @@ static int stmmac_pltfr_probe(struct platform_device *pdev) } } + /* Custom setup (if needed) */ + if (plat_dat->setup) { + plat_dat->bsp_priv = plat_dat->setup(pdev); + if (IS_ERR(plat_dat->bsp_priv)) + return PTR_ERR(plat_dat->bsp_priv); + } + /* Custom initialisation (if needed)*/ if (plat_dat->init) { - ret = plat_dat->init(pdev); + ret = plat_dat->init(pdev, plat_dat->bsp_priv); if (unlikely(ret)) return ret; } @@ -203,7 +210,10 @@ static int stmmac_pltfr_remove(struct platform_device *pdev) int ret = stmmac_dvr_remove(ndev); if (priv->plat->exit) - priv->plat->exit(pdev); + priv->plat->exit(pdev, priv->plat->bsp_priv); + + if (priv->plat->free) + priv->plat->free(pdev, priv->plat->bsp_priv); return ret; } @@ -218,7 +228,7 @@ static int stmmac_pltfr_suspend(struct device *dev) ret = stmmac_suspend(ndev); if (priv->plat->exit) - priv->plat->exit(pdev); + priv->plat->exit(pdev, priv->plat->bsp_priv); return ret; } @@ -230,7 +240,7 @@ static int stmmac_pltfr_resume(struct device *dev) struct platform_device *pdev = to_platform_device(dev); if (priv->plat->init) - priv->plat->init(pdev); + priv->plat->init(pdev, priv->plat->bsp_priv); return stmmac_resume(ndev); } diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 33ace712e7e8..0a5a7aca562e 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -113,8 +113,10 @@ struct plat_stmmacenet_data { int max_speed; void (*fix_mac_speed)(void *priv, unsigned int speed); void (*bus_setup)(void __iomem *ioaddr); - int (*init)(struct platform_device *pdev); - void (*exit)(struct platform_device *pdev); + void *(*setup)(struct platform_device *pdev); + void (*free)(struct platform_device *pdev, void *priv); + int (*init)(struct platform_device *pdev, void *priv); + void (*exit)(struct platform_device *pdev, void *priv); void *custom_cfg; void *custom_data; void *bsp_priv; -- cgit v1.3-14-g43fede From 022066f50f53000679d31eb407693085f37b3f14 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Fri, 17 Jan 2014 21:24:46 +0800 Subject: net: stmmac: Use driver data and callbacks tied with compatible strings The stmmac driver core allows passing feature flags and callbacks via platform data. Add a similar stmmac_of_data to pass flags and callbacks tied to compatible strings. This allows us to extend stmmac with glue layers for different SoCs. Signed-off-by: Chen-Yu Tsai Signed-off-by: David S. Miller --- .../net/ethernet/stmicro/stmmac/stmmac_platform.c | 44 +++++++++++++++++----- include/linux/stmmac.h | 18 +++++++++ 2 files changed, 52 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 82110f141d09..bf119db15212 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -26,8 +26,20 @@ #include #include #include +#include #include "stmmac.h" +static const struct of_device_id stmmac_dt_ids[] = { + /* SoC specific glue layers should come before generic bindings */ + { .compatible = "st,spear600-gmac"}, + { .compatible = "snps,dwmac-3.610"}, + { .compatible = "snps,dwmac-3.70a"}, + { .compatible = "snps,dwmac-3.710"}, + { .compatible = "snps,dwmac"}, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, stmmac_dt_ids); + #ifdef CONFIG_OF static int stmmac_probe_config_dt(struct platform_device *pdev, struct plat_stmmacenet_data *plat, @@ -35,10 +47,32 @@ static int stmmac_probe_config_dt(struct platform_device *pdev, { struct device_node *np = pdev->dev.of_node; struct stmmac_dma_cfg *dma_cfg; + const struct of_device_id *device; if (!np) return -ENODEV; + device = of_match_device(stmmac_dt_ids, &pdev->dev); + if (!device) + return -ENODEV; + + if (device->data) { + const struct stmmac_of_data *data = device->data; + plat->has_gmac = data->has_gmac; + plat->enh_desc = data->enh_desc; + plat->tx_coe = data->tx_coe; + plat->rx_coe = data->rx_coe; + plat->bugged_jumbo = data->bugged_jumbo; + plat->pmt = data->pmt; + plat->riwt_off = data->riwt_off; + plat->fix_mac_speed = data->fix_mac_speed; + plat->bus_setup = data->bus_setup; + plat->setup = data->setup; + plat->free = data->free; + plat->init = data->init; + plat->exit = data->exit; + } + *mac = of_get_mac_address(np); plat->interface = of_get_phy_mode(np); @@ -259,16 +293,6 @@ static int stmmac_pltfr_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(stmmac_pltfr_pm_ops, stmmac_pltfr_suspend, stmmac_pltfr_resume); -static const struct of_device_id stmmac_dt_ids[] = { - { .compatible = "st,spear600-gmac"}, - { .compatible = "snps,dwmac-3.610"}, - { .compatible = "snps,dwmac-3.70a"}, - { .compatible = "snps,dwmac-3.710"}, - { .compatible = "snps,dwmac"}, - { /* sentinel */ } -}; -MODULE_DEVICE_TABLE(of, stmmac_dt_ids); - struct platform_driver stmmac_pltfr_driver = { .probe = stmmac_pltfr_probe, .remove = stmmac_pltfr_remove, diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 0a5a7aca562e..1367974b7e84 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -121,4 +121,22 @@ struct plat_stmmacenet_data { void *custom_data; void *bsp_priv; }; + +/* of_data for SoC glue layer device tree bindings */ + +struct stmmac_of_data { + int has_gmac; + int enh_desc; + int tx_coe; + int rx_coe; + int bugged_jumbo; + int pmt; + int riwt_off; + void (*fix_mac_speed)(void *priv, unsigned int speed); + void (*bus_setup)(void __iomem *ioaddr); + void *(*setup)(struct platform_device *pdev); + void (*free)(struct platform_device *pdev, void *priv); + int (*init)(struct platform_device *pdev, void *priv); + void (*exit)(struct platform_device *pdev, void *priv); +}; #endif -- cgit v1.3-14-g43fede From 2618abb73c8953f0848511fc13f68da4d8337574 Mon Sep 17 00:00:00 2001 From: Vince Bridgers Date: Mon, 20 Jan 2014 05:39:01 -0600 Subject: stmmac: Fix kernel crashes for jumbo frames These changes correct the following issues with jumbo frames on the stmmac driver: 1) The Synopsys EMAC can be configured to support different FIFO sizes at core configuration time. There's no way to query the controller and know the FIFO size, so the driver needs to get this information from the device tree in order to know how to correctly handle MTU changes and setting up dma buffers. The default max-frame-size is as currently used, which is the size of a jumbo frame. 2) The driver was enabling Jumbo frames by default, but was not allocating dma buffers of sufficient size to handle the maximum possible packet size that could be received. This led to memory corruption since DMAs were occurring beyond the extent of the allocated receive buffers for certain types of network traffic. kernel BUG at net/core/skbuff.c:126! Internal error: Oops - BUG: 0 [#1] SMP ARM Modules linked in: CPU: 0 PID: 563 Comm: sockperf Not tainted 3.13.0-rc6-01523-gf7111b9 #31 task: ef35e580 ti: ef252000 task.ti: ef252000 PC is at skb_panic+0x60/0x64 LR is at skb_panic+0x60/0x64 pc : [] lr : [] psr: 60000113 sp : ef253c18 ip : 60000113 fp : 00000000 r10: ef3a5400 r9 : 00000ebc r8 : ef3a546c r7 : ee59f000 r6 : ee59f084 r5 : ee59ff40 r4 : ee59f140 r3 : 000003e2 r2 : 00000007 r1 : c0b9c420 r0 : 0000007d Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment user Control: 10c5387d Table: 2e8ac04a DAC: 00000015 Process sockperf (pid: 563, stack limit = 0xef252248) Stack: (0xef253c18 to 0xef254000) 3c00: 00000ebc ee59f000 3c20: ee59f084 ee59ff40 ee59f140 c04a9cd8 ee8c50c0 00000ebc ee59ff40 00000000 3c40: ee59f140 c02d0ef0 00000056 ef1eda80 ee8c50c0 00000ebc 22bbef29 c0318f8c 3c60: 00000056 ef3a547c ffe2c716 c02c9c90 c0ba1298 ef3a5838 ef3a5838 ef3a5400 3c80: 000020c0 ee573840 000055cb ef3f2050 c053f0e0 c0319214 22b9b085 22d92813 3ca0: 00001c80 004b8e00 ef3a5400 ee573840 ef3f2064 22d92813 ef3f2064 000055cb 3cc0: ef3f2050 c031a19c ef252000 00000000 00000000 c0561bc0 00000000 ff00ffff 3ce0: c05621c0 ef3a5400 ef3f2064 ee573840 00000020 ef3f2064 000055cb ef3f2050 3d00: c053f0e0 c031cad0 c053e740 00000e60 00000000 00000000 ee573840 ef3a5400 3d20: ef0a6e00 00000000 ef3f2064 c032507c 00010000 00000020 c0561bc0 c0561bc0 3d40: ee599850 c032799c 00000000 ee573840 c055a380 ef3a5400 00000000 ef3f2064 3d60: ef3f2050 c032799c 0101c7c0 2b6755cb c059a280 c030e4d8 000055cb ffffffff 3d80: ee574fc0 c055a380 ee574000 ee573840 00002b67 ee573840 c03fe9c4 c053fa68 3da0: c055a380 00001f6f 00000000 ee573840 c053f0e0 c0304fdc ef0a6e01 ef3f2050 3dc0: ee573858 ef031000 ee573840 c03055d8 c0ba0c40 ef000f40 00100100 c053f0dc 3de0: c053ffdc c053f0f0 00000008 00000000 ef031000 c02da948 00001140 00000000 3e00: c0563c78 ef253e5f 00000020 ee573840 00000020 c053f0f0 ef313400 ee573840 3e20: c053f0e0 00000000 00000000 c05380c0 ef313400 00001000 00000015 c02df280 3e40: ee574000 ef001e00 00000000 00001080 00000042 005cd980 ef031500 ef031500 3e60: 00000000 c02df824 ef031500 c053e390 c0541084 f00b1e00 c05925e8 c02df864 3e80: 00001f5c ef031440 c053e390 c0278524 00000002 00000000 c0b9eb48 c02df280 3ea0: ee8c7180 00000100 c0542ca8 00000015 00000040 ef031500 ef031500 ef031500 3ec0: c027803c ef252000 00000040 000000ec c05380c0 c0b9eb40 c0b9eb48 c02df940 3ee0: ef060780 ffffa4dd c0564a9c c056343c 002e80a8 00000080 ef031500 00000001 3f00: c053808c ef252000 fffec100 00000003 00000004 002e80a8 0000000c c00258f0 3f20: 002e80a8 c005e704 00000005 00000100 c05634d0 c0538080 c05333e0 00000000 3f40: 0000000a c0565580 c05380c0 ffffa4dc c05434f4 00400100 00000004 c0534cd4 3f60: 00000098 00000000 fffec100 002e80a8 00000004 002e80a8 002a20e0 c0025da8 3f80: c0534cd4 c000f020 fffec10c c053ea60 ef253fb0 c0008530 0000ffe2 b6ef67f4 3fa0: 40000010 ffffffff 00000124 c0012f3c 0000ffe2 002e80f0 0000ffe2 00004000 3fc0: becb6338 becb6334 00000004 00000124 002e80a8 00000004 002e80a8 002a20e0 3fe0: becb6300 becb62f4 002773bb b6ef67f4 40000010 ffffffff 00000000 00000000 [] (skb_panic+0x60/0x64) from [] (skb_put+0x4c/0x50) [] (skb_put+0x4c/0x50) from [] (tcp_collapse+0x314/0x3ec) [] (tcp_collapse+0x314/0x3ec) from [] (tcp_try_rmem_schedule+0x1b0/0x3c4) [] (tcp_try_rmem_schedule+0x1b0/0x3c4) from [] (tcp_data_queue+0x480/0xe6c) [] (tcp_data_queue+0x480/0xe6c) from [] (tcp_rcv_established+0x180/0x62c) [] (tcp_rcv_established+0x180/0x62c) from [] (tcp_v4_do_rcv+0x13c/0x31c) [] (tcp_v4_do_rcv+0x13c/0x31c) from [] (tcp_v4_rcv+0x718/0x73c) [] (tcp_v4_rcv+0x718/0x73c) from [] (ip_local_deliver+0x98/0x274) [] (ip_local_deliver+0x98/0x274) from [] (ip_rcv+0x420/0x758) [] (ip_rcv+0x420/0x758) from [] (__netif_receive_skb_core+0x44c/0x5bc) [] (__netif_receive_skb_core+0x44c/0x5bc) from [] (netif_receive_skb+0x48/0xb4) [] (netif_receive_skb+0x48/0xb4) from [] (napi_gro_flush+0x70/0x94) [] (napi_gro_flush+0x70/0x94) from [] (napi_complete+0x1c/0x34) [] (napi_complete+0x1c/0x34) from [] (stmmac_poll+0x4e8/0x5c8) [] (stmmac_poll+0x4e8/0x5c8) from [] (net_rx_action+0xc4/0x1e4) [] (net_rx_action+0xc4/0x1e4) from [] (__do_softirq+0x12c/0x2e8) [] (__do_softirq+0x12c/0x2e8) from [] (irq_exit+0x78/0xac) [] (irq_exit+0x78/0xac) from [] (handle_IRQ+0x44/0x90) [] (handle_IRQ+0x44/0x90) from [] (gic_handle_irq+0x2c/0x5c) [] (gic_handle_irq+0x2c/0x5c) from [] (__irq_usr+0x3c/0x60) 3) The driver was setting the dma buffer size after allocating dma buffers, which caused a system panic when changing the MTU. BUG: Bad page state in process ifconfig pfn:2e850 page:c0b72a00 count:0 mapcount:0 mapping: (null) index:0x0 page flags: 0x200(arch_1) Modules linked in: CPU: 0 PID: 566 Comm: ifconfig Not tainted 3.13.0-rc6-01523-gf7111b9 #29 [] (unwind_backtrace+0x0/0xf8) from [] (show_stack+0x10/0x14) [] (show_stack+0x10/0x14) from [] (dump_stack+0x70/0x88) [] (dump_stack+0x70/0x88) from [] (bad_page+0xc8/0x118) [] (bad_page+0xc8/0x118) from [] (get_page_from_freelist+0x744/0x870) [] (get_page_from_freelist+0x744/0x870) from [] (__alloc_pages_nodemask+0x118/0x86c) [] (__alloc_pages_nodemask+0x118/0x86c) from [] (__get_free_pages+0x10/0x54) [] (__get_free_pages+0x10/0x54) from [] (kmalloc_order_trace+0x24/0xa0) [] (kmalloc_order_trace+0x24/0xa0) from [] (__kmalloc_reserve.isra.21+0x24/0x70) [] (__kmalloc_reserve.isra.21+0x24/0x70) from [] (__alloc_skb+0x68/0x13c) [] (__alloc_skb+0x68/0x13c) from [] (__netdev_alloc_skb+0x3c/0xe8) [] (__netdev_alloc_skb+0x3c/0xe8) from [] (stmmac_open+0x63c/0x1024) [] (stmmac_open+0x63c/0x1024) from [] (__dev_open+0xa0/0xfc) [] (__dev_open+0xa0/0xfc) from [] (__dev_change_flags+0x94/0x158) [] (__dev_change_flags+0x94/0x158) from [] (dev_change_flags+0x18/0x48) [] (dev_change_flags+0x18/0x48) from [] (devinet_ioctl+0x638/0x700) [] (devinet_ioctl+0x638/0x700) from [] (sock_ioctl+0x64/0x290) [] (sock_ioctl+0x64/0x290) from [] (do_vfs_ioctl+0x78/0x5b8) [] (do_vfs_ioctl+0x78/0x5b8) from [] (SyS_ioctl+0x3c/0x5c) [] (SyS_ioctl+0x3c/0x5c) from [] The fixes have been verified using reproducible, automated testing. Signed-off-by: Vince Bridgers Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 4 +++- drivers/net/ethernet/stmicro/stmmac/dwmac1000.h | 7 ++----- drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c | 7 ++++++- drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 11 +++++++---- drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 13 +++++++++++++ include/linux/stmmac.h | 1 + 7 files changed, 33 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 5a60b3fb00b6..7834a3993946 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -292,6 +292,8 @@ struct dma_features { #define STMMAC_CHAIN_MODE 0x1 #define STMMAC_RING_MODE 0x2 +#define JUMBO_LEN 9000 + struct stmmac_desc_ops { /* DMA RX descriptor ring initialization */ void (*init_rx_desc) (struct dma_desc *p, int disable_rx_ic, int mode, @@ -368,7 +370,7 @@ struct stmmac_dma_ops { struct stmmac_ops { /* MAC core initialization */ - void (*core_init) (void __iomem *ioaddr); + void (*core_init) (void __iomem *ioaddr, int mtu); /* Enable and verify that the IPC module is supported */ int (*rx_ipc) (void __iomem *ioaddr); /* Dump MAC registers */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h index c12aabb8cf93..f37d90f114f5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h @@ -126,11 +126,8 @@ enum power_event { #define GMAC_ANE_PSE (3 << 7) #define GMAC_ANE_PSE_SHIFT 7 - /* GMAC Configuration defines */ -#define GMAC_CONTROL_TC 0x01000000 /* Transmit Conf. in RGMII/SGMII */ -#define GMAC_CONTROL_WD 0x00800000 /* Disable Watchdog on receive */ - /* GMAC Configuration defines */ +#define GMAC_CONTROL_2K 0x08000000 /* IEEE 802.3as 2K packets */ #define GMAC_CONTROL_TC 0x01000000 /* Transmit Conf. in RGMII/SGMII */ #define GMAC_CONTROL_WD 0x00800000 /* Disable Watchdog on receive */ #define GMAC_CONTROL_JD 0x00400000 /* Jabber disable */ @@ -156,7 +153,7 @@ enum inter_frame_gap { #define GMAC_CONTROL_RE 0x00000004 /* Receiver Enable */ #define GMAC_CORE_INIT (GMAC_CONTROL_JD | GMAC_CONTROL_PS | GMAC_CONTROL_ACS | \ - GMAC_CONTROL_JE | GMAC_CONTROL_BE) + GMAC_CONTROL_BE) /* GMAC Frame Filter defines */ #define GMAC_FRAME_FILTER_PR 0x00000001 /* Promiscuous Mode */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c index cdd926832e27..b3e148ef5683 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c @@ -32,10 +32,15 @@ #include #include "dwmac1000.h" -static void dwmac1000_core_init(void __iomem *ioaddr) +static void dwmac1000_core_init(void __iomem *ioaddr, int mtu) { u32 value = readl(ioaddr + GMAC_CONTROL); value |= GMAC_CORE_INIT; + if (mtu > 1500) + value |= GMAC_CONTROL_2K; + if (mtu > 2000) + value |= GMAC_CONTROL_JE; + writel(value, ioaddr + GMAC_CONTROL); /* Mask GMAC interrupts */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c index 5857d677dac1..2ff767bcfdd0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c @@ -32,7 +32,7 @@ #include #include "dwmac100.h" -static void dwmac100_core_init(void __iomem *ioaddr) +static void dwmac100_core_init(void __iomem *ioaddr, int mtu) { u32 value = readl(ioaddr + MAC_CONTROL); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 5db91be962c2..d93aa87408c2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -54,7 +54,6 @@ #include #define STMMAC_ALIGN(x) L1_CACHE_ALIGN(x) -#define JUMBO_LEN 9000 /* Module parameters */ #define TX_TIMEO 5000 @@ -93,7 +92,7 @@ static int tc = TC_DEFAULT; module_param(tc, int, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(tc, "DMA threshold control value"); -#define DMA_BUFFER_SIZE BUF_SIZE_2KiB +#define DMA_BUFFER_SIZE BUF_SIZE_4KiB static int buf_sz = DMA_BUFFER_SIZE; module_param(buf_sz, int, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(buf_sz, "DMA buffer size"); @@ -994,6 +993,8 @@ static int init_dma_desc_rings(struct net_device *dev) if (bfsize < BUF_SIZE_16KiB) bfsize = stmmac_set_bfsize(dev->mtu, priv->dma_buf_sz); + priv->dma_buf_sz = bfsize; + if (netif_msg_probe(priv)) pr_debug("%s: txsize %d, rxsize %d, bfsize %d\n", __func__, txsize, rxsize, bfsize); @@ -1023,7 +1024,6 @@ static int init_dma_desc_rings(struct net_device *dev) } priv->cur_rx = 0; priv->dirty_rx = (unsigned int)(i - rxsize); - priv->dma_buf_sz = bfsize; buf_sz = bfsize; /* Setup the chained descriptor addresses */ @@ -1624,7 +1624,7 @@ static int stmmac_hw_setup(struct net_device *dev) priv->plat->bus_setup(priv->ioaddr); /* Initialize the MAC Core */ - priv->hw->mac->core_init(priv->ioaddr); + priv->hw->mac->core_init(priv->ioaddr, dev->mtu); /* Enable the MAC Rx/Tx */ stmmac_set_mac(priv->ioaddr, true); @@ -2274,6 +2274,9 @@ static int stmmac_change_mtu(struct net_device *dev, int new_mtu) else max_mtu = SKB_MAX_HEAD(NET_SKB_PAD + NET_IP_ALIGN); + if (priv->plat->maxmtu < max_mtu) + max_mtu = priv->plat->maxmtu; + if ((new_mtu < 46) || (new_mtu > max_mtu)) { pr_err("%s: invalid MTU, max MTU is: %d\n", dev->name, max_mtu); return -EINVAL; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 9d4baa8b94ad..5884a7d2063b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -102,6 +102,11 @@ static int stmmac_probe_config_dt(struct platform_device *pdev, plat->force_sf_dma_mode = of_property_read_bool(np, "snps,force_sf_dma_mode"); + /* Set the maxmtu to a default of JUMBO_LEN in case the + * parameter is not present in the device tree. + */ + plat->maxmtu = JUMBO_LEN; + /* * Currently only the properties needed on SPEAr600 * are provided. All other properties should be added @@ -110,6 +115,14 @@ static int stmmac_probe_config_dt(struct platform_device *pdev, if (of_device_is_compatible(np, "st,spear600-gmac") || of_device_is_compatible(np, "snps,dwmac-3.70a") || of_device_is_compatible(np, "snps,dwmac")) { + /* Note that the max-frame-size parameter as defined in the + * ePAPR v1.1 spec is defined as max-frame-size, it's + * actually used as the IEEE definition of MAC Client + * data, or MTU. The ePAPR specification is confusing as + * the definition is max-frame-size, but usage examples + * are clearly MTUs + */ + of_property_read_u32(np, "max-frame-size", &plat->maxmtu); plat->has_gmac = 1; plat->pmt = 1; } diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 1367974b7e84..6f27d4f957bd 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -111,6 +111,7 @@ struct plat_stmmacenet_data { int force_thresh_dma_mode; int riwt_off; int max_speed; + int maxmtu; void (*fix_mac_speed)(void *priv, unsigned int speed); void (*bus_setup)(void __iomem *ioaddr); void *(*setup)(struct platform_device *pdev); -- cgit v1.3-14-g43fede From b582ef0990d457f7ce8ccf827af51a575ca0b4a6 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Mon, 20 Jan 2014 13:59:19 +0200 Subject: net: Add GRO support for UDP encapsulating protocols Add GRO handlers for protocols that do UDP encapsulation, with the intent of being able to coalesce packets which encapsulate packets belonging to the same TCP session. For GRO purposes, the destination UDP port takes the role of the ether type field in the ethernet header or the next protocol in the IP header. The UDP GRO handler will only attempt to coalesce packets whose destination port is registered to have gro handler. Use a mark on the skb GRO CB data to disallow (flush) running the udp gro receive code twice on a packet. This solves the problem of udp encapsulated packets whose inner VM packet is udp and happen to carry a port which has registered offloads. Signed-off-by: Shlomo Pongratz Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/netdevice.h | 10 +++- include/net/protocol.h | 3 + net/core/dev.c | 1 + net/ipv4/udp_offload.c | 143 ++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 156 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 83ce2aee65e6..c31022980e18 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1675,7 +1675,10 @@ struct napi_gro_cb { unsigned long age; /* Used in ipv6_gro_receive() */ - int proto; + u16 proto; + + /* Used in udp_gro_receive */ + u16 udp_mark; /* used to support CHECKSUM_COMPLETE for tunneling protocols */ __wsum csum; @@ -1714,6 +1717,11 @@ struct packet_offload { struct list_head list; }; +struct udp_offload { + __be16 port; + struct offload_callbacks callbacks; +}; + /* often modified stats are per cpu, other are shared (netdev->stats) */ struct pcpu_sw_netstats { u64 rx_packets; diff --git a/include/net/protocol.h b/include/net/protocol.h index 0e5f8665d7fb..a7e986b08147 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -108,6 +108,9 @@ int inet_del_offload(const struct net_offload *prot, unsigned char num); void inet_register_protosw(struct inet_protosw *p); void inet_unregister_protosw(struct inet_protosw *p); +int udp_add_offload(struct udp_offload *prot); +void udp_del_offload(struct udp_offload *prot); + #if IS_ENABLED(CONFIG_IPV6) int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char num); int inet6_del_protocol(const struct inet6_protocol *prot, unsigned char num); diff --git a/net/core/dev.c b/net/core/dev.c index a578af589198..da92305c344f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3893,6 +3893,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff NAPI_GRO_CB(skb)->same_flow = 0; NAPI_GRO_CB(skb)->flush = 0; NAPI_GRO_CB(skb)->free = 0; + NAPI_GRO_CB(skb)->udp_mark = 0; pp = ptype->callbacks.gro_receive(&napi->gro_list, skb); break; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 79c62bdcd3c5..ee853c55deea 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -14,6 +14,15 @@ #include #include +static DEFINE_SPINLOCK(udp_offload_lock); +static struct udp_offload_priv *udp_offload_base __read_mostly; + +struct udp_offload_priv { + struct udp_offload *offload; + struct rcu_head rcu; + struct udp_offload_priv __rcu *next; +}; + static int udp4_ufo_send_check(struct sk_buff *skb) { if (!pskb_may_pull(skb, sizeof(struct udphdr))) @@ -89,10 +98,144 @@ out: return segs; } +int udp_add_offload(struct udp_offload *uo) +{ + struct udp_offload_priv **head = &udp_offload_base; + struct udp_offload_priv *new_offload = kzalloc(sizeof(*new_offload), GFP_KERNEL); + + if (!new_offload) + return -ENOMEM; + + new_offload->offload = uo; + + spin_lock(&udp_offload_lock); + rcu_assign_pointer(new_offload->next, rcu_dereference(*head)); + rcu_assign_pointer(*head, rcu_dereference(new_offload)); + spin_unlock(&udp_offload_lock); + + return 0; +} +EXPORT_SYMBOL(udp_add_offload); + +static void udp_offload_free_routine(struct rcu_head *head) +{ + struct udp_offload_priv *ou_priv = container_of(head, struct udp_offload_priv, rcu); + kfree(ou_priv); +} + +void udp_del_offload(struct udp_offload *uo) +{ + struct udp_offload_priv __rcu **head = &udp_offload_base; + struct udp_offload_priv *uo_priv; + + spin_lock(&udp_offload_lock); + + uo_priv = rcu_dereference(*head); + for (; uo_priv != NULL; + uo_priv = rcu_dereference(*head)) { + + if (uo_priv->offload == uo) { + rcu_assign_pointer(*head, rcu_dereference(uo_priv->next)); + goto unlock; + } + head = &uo_priv->next; + } + pr_warn("udp_del_offload: didn't find offload for port %d\n", htons(uo->port)); +unlock: + spin_unlock(&udp_offload_lock); + if (uo_priv != NULL) + call_rcu(&uo_priv->rcu, udp_offload_free_routine); +} +EXPORT_SYMBOL(udp_del_offload); + +static struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb) +{ + struct udp_offload_priv *uo_priv; + struct sk_buff *p, **pp = NULL; + struct udphdr *uh, *uh2; + unsigned int hlen, off; + int flush = 1; + + if (NAPI_GRO_CB(skb)->udp_mark || + (!skb->encapsulation && skb->ip_summed != CHECKSUM_COMPLETE)) + goto out; + + /* mark that this skb passed once through the udp gro layer */ + NAPI_GRO_CB(skb)->udp_mark = 1; + + off = skb_gro_offset(skb); + hlen = off + sizeof(*uh); + uh = skb_gro_header_fast(skb, off); + if (skb_gro_header_hard(skb, hlen)) { + uh = skb_gro_header_slow(skb, hlen, off); + if (unlikely(!uh)) + goto out; + } + + rcu_read_lock(); + uo_priv = rcu_dereference(udp_offload_base); + for (; uo_priv != NULL; uo_priv = rcu_dereference(uo_priv->next)) { + if (uo_priv->offload->port == uh->dest && + uo_priv->offload->callbacks.gro_receive) + goto unflush; + } + goto out_unlock; + +unflush: + flush = 0; + + for (p = *head; p; p = p->next) { + if (!NAPI_GRO_CB(p)->same_flow) + continue; + + uh2 = (struct udphdr *)(p->data + off); + if ((*(u32 *)&uh->source != *(u32 *)&uh2->source)) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + } + + skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */ + pp = uo_priv->offload->callbacks.gro_receive(head, skb); + +out_unlock: + rcu_read_unlock(); +out: + NAPI_GRO_CB(skb)->flush |= flush; + return pp; +} + +static int udp_gro_complete(struct sk_buff *skb, int nhoff) +{ + struct udp_offload_priv *uo_priv; + __be16 newlen = htons(skb->len - nhoff); + struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); + int err = -ENOSYS; + + uh->len = newlen; + + rcu_read_lock(); + + uo_priv = rcu_dereference(udp_offload_base); + for (; uo_priv != NULL; uo_priv = rcu_dereference(uo_priv->next)) { + if (uo_priv->offload->port == uh->dest && + uo_priv->offload->callbacks.gro_complete) + break; + } + + if (uo_priv != NULL) + err = uo_priv->offload->callbacks.gro_complete(skb, nhoff + sizeof(struct udphdr)); + + rcu_read_unlock(); + return err; +} + static const struct net_offload udpv4_offload = { .callbacks = { .gso_send_check = udp4_ufo_send_check, .gso_segment = udp4_ufo_fragment, + .gro_receive = udp_gro_receive, + .gro_complete = udp_gro_complete, }, }; -- cgit v1.3-14-g43fede From 37692299319db31f33f04ce418604781fa5710fb Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 21 Jan 2014 00:19:37 +0100 Subject: net: filter: let bpf_tell_extensions return SKF_AD_MAX Michal Sekletar added in commit ea02f9411d9f ("net: introduce SO_BPF_EXTENSIONS") a facility where user space can enquire the BPF ancillary instruction set, which is imho a step into the right direction for letting user space high-level to BPF optimizers make an informed decision for possibly using these extensions. The original rationale was to return through a getsockopt(2) a bitfield of which instructions are supported and which are not, as of right now, we just return 0 to indicate a base support for SKF_AD_PROTOCOL up to SKF_AD_PAY_OFFSET. Limitations of this approach are that this API which we need to maintain for a long time can only support a maximum of 32 extensions, and needs to be additionally maintained/updated when each new extension that comes in. I thought about this a bit more and what we can do here to overcome this is to just return SKF_AD_MAX. Since we never remove any extension since we cannot break user space and always linearly increase SKF_AD_MAX on each newly added extension, user space can make a decision on what extensions are supported in the whole set of extensions and which aren't, by just checking which of them from the whole set have an offset < SKF_AD_MAX of the underlying kernel. Since SKF_AD_MAX must be updated each time we add new ones, we don't need to introduce an additional enum and got maintenance for free. At some point in time when SO_BPF_EXTENSIONS becomes ubiquitous for most kernels, then an application can simply make use of this and easily be run on newer or older underlying kernels without needing to be recompiled, of course. Since that is for 3.14, it's not too late to do this change. Cc: Michal Sekletar Cc: Eric Dumazet Signed-off-by: Daniel Borkmann Acked-by: Michal Sekletar Signed-off-by: David S. Miller --- include/linux/filter.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 1a95a2dcf113..e568c8ef896b 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -85,13 +85,7 @@ static inline void bpf_jit_free(struct sk_filter *fp) static inline int bpf_tell_extensions(void) { - /* When adding new BPF extension it is necessary to enumerate - * it here, so userspace software which wants to know what is - * supported can do so by inspecting return value of this - * function - */ - - return 0; + return SKF_AD_MAX; } enum { -- cgit v1.3-14-g43fede From f337db64af059c9a94278a8b0ab97d87259ff62f Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 22 Jan 2014 02:29:39 +0100 Subject: random32: add prandom_u32_max and convert open coded users Many functions have open coded a function that returns a random number in range [0,N-1]. Under the assumption that we have a PRNG such as taus113 with being well distributed in [0, ~0U] space, we can implement such a function as uword t = (n*m')>>32, where m' is a random number obtained from PRNG, n the right open interval border and t our resulting random number, with n,m',t in u32 universe. Lets go with Joe and simply call it prandom_u32_max(), although technically we have an right open interval endpoint, but that we have documented. Other users can further be migrated to the new prandom_u32_max() function later on; for now, we need to make sure to migrate reciprocal_divide() users for the reciprocal_divide() follow-up fixup since their function signatures are going to change. Joint work with Hannes Frederic Sowa. Cc: Jakub Zawadzki Cc: Eric Dumazet Cc: linux-kernel@vger.kernel.org Signed-off-by: Hannes Frederic Sowa Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- drivers/net/team/team_mode_random.c | 8 +------- include/linux/random.h | 18 +++++++++++++++++- net/packet/af_packet.c | 2 +- net/sched/sch_choke.c | 9 +-------- 4 files changed, 20 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/team/team_mode_random.c b/drivers/net/team/team_mode_random.c index 7f032e211343..cd2f692b8074 100644 --- a/drivers/net/team/team_mode_random.c +++ b/drivers/net/team/team_mode_random.c @@ -13,20 +13,14 @@ #include #include #include -#include #include -static u32 random_N(unsigned int N) -{ - return reciprocal_divide(prandom_u32(), N); -} - static bool rnd_transmit(struct team *team, struct sk_buff *skb) { struct team_port *port; int port_index; - port_index = random_N(team->en_port_count); + port_index = prandom_u32_max(team->en_port_count); port = team_get_port_by_index_rcu(team, port_index); if (unlikely(!port)) goto drop; diff --git a/include/linux/random.h b/include/linux/random.h index 4002b3df4c85..1cfce0e24dbd 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -8,7 +8,6 @@ #include - extern void add_device_randomness(const void *, unsigned int); extern void add_input_randomness(unsigned int type, unsigned int code, unsigned int value); @@ -38,6 +37,23 @@ struct rnd_state { u32 prandom_u32_state(struct rnd_state *state); void prandom_bytes_state(struct rnd_state *state, void *buf, int nbytes); +/** + * prandom_u32_max - returns a pseudo-random number in interval [0, ep_ro) + * @ep_ro: right open interval endpoint + * + * Returns a pseudo-random number that is in interval [0, ep_ro). Note + * that the result depends on PRNG being well distributed in [0, ~0U] + * u32 space. Here we use maximally equidistributed combined Tausworthe + * generator, that is, prandom_u32(). This is useful when requesting a + * random index of an array containing ep_ro elements, for example. + * + * Returns: pseudo-random number in interval [0, ep_ro) + */ +static inline u32 prandom_u32_max(u32 ep_ro) +{ + return (u32)(((u64) prandom_u32() * ep_ro) >> 32); +} + /* * Handle minimum values for seeds */ diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 59fb3db2e713..df3cbdd585c7 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1289,7 +1289,7 @@ static unsigned int fanout_demux_rnd(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { - return reciprocal_divide(prandom_u32(), num); + return prandom_u32_max(num); } static unsigned int fanout_demux_rollover(struct packet_fanout *f, diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index ddd73cb2d7ba..2aee02802c27 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include @@ -77,12 +76,6 @@ struct choke_sched_data { struct sk_buff **tab; }; -/* deliver a random number between 0 and N - 1 */ -static u32 random_N(unsigned int N) -{ - return reciprocal_divide(prandom_u32(), N); -} - /* number of elements in queue including holes */ static unsigned int choke_len(const struct choke_sched_data *q) { @@ -233,7 +226,7 @@ static struct sk_buff *choke_peek_random(const struct choke_sched_data *q, int retrys = 3; do { - *pidx = (q->head + random_N(choke_len(q))) & q->tab_mask; + *pidx = (q->head + prandom_u32_max(choke_len(q))) & q->tab_mask; skb = q->tab[*pidx]; if (skb) return skb; -- cgit v1.3-14-g43fede From 89770b0a69ee0e0e5e99c722192d535115f73778 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 22 Jan 2014 02:29:40 +0100 Subject: net: introduce reciprocal_scale helper and convert users As David Laight suggests, we shouldn't necessarily call this reciprocal_divide() when users didn't requested a reciprocal_value(); lets keep the basic idea and call it reciprocal_scale(). More background information on this topic can be found in [1]. Joint work with Hannes Frederic Sowa. [1] http://homepage.cs.uiowa.edu/~jones/bcd/divide.html Suggested-by: David Laight Cc: Jakub Zawadzki Cc: Eric Dumazet Cc: linux-kernel@vger.kernel.org Signed-off-by: Hannes Frederic Sowa Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/kernel.h | 19 +++++++++++++++++++ include/net/codel.h | 4 +--- net/packet/af_packet.c | 3 +-- 3 files changed, 21 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index ecb87544cc5d..03d8a6b0e2e8 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -193,6 +193,25 @@ extern int _cond_resched(void); (__x < 0) ? -__x : __x; \ }) +/** + * reciprocal_scale - "scale" a value into range [0, ep_ro) + * @val: value + * @ep_ro: right open interval endpoint + * + * Perform a "reciprocal multiplication" in order to "scale" a value into + * range [0, ep_ro), where the upper interval endpoint is right-open. + * This is useful, e.g. for accessing a index of an array containing + * ep_ro elements, for example. Think of it as sort of modulus, only that + * the result isn't that of modulo. ;) Note that if initial input is a + * small value, then result will return 0. + * + * Return: a result based on val in interval [0, ep_ro). + */ +static inline u32 reciprocal_scale(u32 val, u32 ep_ro) +{ + return (u32)(((u64) val * ep_ro) >> 32); +} + #if defined(CONFIG_MMU) && \ (defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP)) void might_fault(void); diff --git a/include/net/codel.h b/include/net/codel.h index 3b04ff5f6f8d..fe0eab32ce76 100644 --- a/include/net/codel.h +++ b/include/net/codel.h @@ -46,7 +46,6 @@ #include #include #include -#include /* Controlling Queue Delay (CoDel) algorithm * ========================================= @@ -211,10 +210,9 @@ static codel_time_t codel_control_law(codel_time_t t, codel_time_t interval, u32 rec_inv_sqrt) { - return t + reciprocal_divide(interval, rec_inv_sqrt << REC_INV_SQRT_SHIFT); + return t + reciprocal_scale(interval, rec_inv_sqrt << REC_INV_SQRT_SHIFT); } - static bool codel_should_drop(const struct sk_buff *skb, struct Qdisc *sch, struct codel_vars *vars, diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index df3cbdd585c7..97346162803d 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -88,7 +88,6 @@ #include #include #include -#include #include #ifdef CONFIG_INET #include @@ -1262,7 +1261,7 @@ static unsigned int fanout_demux_hash(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { - return reciprocal_divide(skb->rxhash, num); + return reciprocal_scale(skb->rxhash, num); } static unsigned int fanout_demux_lb(struct packet_fanout *f, -- cgit v1.3-14-g43fede From 809fa972fd90ff27225294b17a027e908b2d7b7a Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Wed, 22 Jan 2014 02:29:41 +0100 Subject: reciprocal_divide: update/correction of the algorithm MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Jakub Zawadzki noticed that some divisions by reciprocal_divide() were not correct [1][2], which he could also show with BPF code after divisions are transformed into reciprocal_value() for runtime invariance which can be passed to reciprocal_divide() later on; reverse in BPF dump ended up with a different, off-by-one K in some situations. This has been fixed by Eric Dumazet in commit aee636c4809fa5 ("bpf: do not use reciprocal divide"). This follow-up patch improves reciprocal_value() and reciprocal_divide() to work in all cases by using Granlund and Montgomery method, so that also future use is safe and without any non-obvious side-effects. Known problems with the old implementation were that division by 1 always returned 0 and some off-by-ones when the dividend and divisor where very large. This seemed to not be problematic with its current users, as far as we can tell. Eric Dumazet checked for the slab usage, we cannot surely say so in the case of flex_array. Still, in order to fix that, we propose an extension from the original implementation from commit 6a2d7a955d8d resp. [3][4], by using the algorithm proposed in "Division by Invariant Integers Using Multiplication" [5], Torbjörn Granlund and Peter L. Montgomery, that is, pseudocode for q = n/d where q, n, d is in u32 universe: 1) Initialization: int l = ceil(log_2 d) uword m' = floor((1<<32)*((1<>32 q = (t+((n-t)>>sh_1))>>sh_2 The assembler implementation from Agner Fog [6] also helped a lot while implementing. We have tested the implementation on x86_64, ppc64, i686, s390x; on x86_64/haswell we're still half the latency compared to normal divide. Joint work with Daniel Borkmann. [1] http://www.wireshark.org/~darkjames/reciprocal-buggy.c [2] http://www.wireshark.org/~darkjames/set-and-dump-filter-k-bug.c [3] https://gmplib.org/~tege/division-paper.pdf [4] http://homepage.cs.uiowa.edu/~jones/bcd/divide.html [5] http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.2556 [6] http://www.agner.org/optimize/asmlib.zip Reported-by: Jakub Zawadzki Cc: Eric Dumazet Cc: Austin S Hemmelgarn Cc: linux-kernel@vger.kernel.org Cc: Jesse Gross Cc: Jamal Hadi Salim Cc: Stephen Hemminger Cc: Matt Mackall Cc: Pekka Enberg Cc: Christoph Lameter Cc: Andy Gospodarek Cc: Veaceslav Falico Cc: Jay Vosburgh Cc: Jakub Zawadzki Signed-off-by: Daniel Borkmann Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 24 ++++++++++++++++------- drivers/net/bonding/bond_netlink.c | 4 ---- drivers/net/bonding/bond_options.c | 15 ++++++++++----- drivers/net/bonding/bond_sysfs.c | 5 ----- drivers/net/bonding/bonding.h | 3 +++ include/linux/flex_array.h | 3 ++- include/linux/reciprocal_div.h | 39 ++++++++++++++++++++------------------ include/linux/slab_def.h | 4 +++- include/net/red.h | 3 ++- lib/flex_array.c | 7 ++++++- lib/reciprocal_div.c | 24 +++++++++++++++++++---- net/sched/sch_netem.c | 6 ++++-- 12 files changed, 88 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 3220b488dd1e..f100bd958b88 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -79,7 +79,6 @@ #include #include #include -#include #include "bonding.h" #include "bond_3ad.h" #include "bond_alb.h" @@ -3596,8 +3595,9 @@ static void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int sl */ static u32 bond_rr_gen_slave_id(struct bonding *bond) { - int packets_per_slave = bond->params.packets_per_slave; u32 slave_id; + struct reciprocal_value reciprocal_packets_per_slave; + int packets_per_slave = bond->params.packets_per_slave; switch (packets_per_slave) { case 0: @@ -3607,8 +3607,10 @@ static u32 bond_rr_gen_slave_id(struct bonding *bond) slave_id = bond->rr_tx_counter; break; default: + reciprocal_packets_per_slave = + bond->params.reciprocal_packets_per_slave; slave_id = reciprocal_divide(bond->rr_tx_counter, - packets_per_slave); + reciprocal_packets_per_slave); break; } bond->rr_tx_counter++; @@ -4343,10 +4345,18 @@ static int bond_check_params(struct bond_params *params) params->resend_igmp = resend_igmp; params->min_links = min_links; params->lp_interval = lp_interval; - if (packets_per_slave > 1) - params->packets_per_slave = reciprocal_value(packets_per_slave); - else - params->packets_per_slave = packets_per_slave; + params->packets_per_slave = packets_per_slave; + if (packets_per_slave > 0) { + params->reciprocal_packets_per_slave = + reciprocal_value(packets_per_slave); + } else { + /* reciprocal_packets_per_slave is unused if + * packets_per_slave is 0 or 1, just initialize it + */ + params->reciprocal_packets_per_slave = + (struct reciprocal_value) { 0 }; + } + if (primary) { strncpy(params->primary, primary, IFNAMSIZ); params->primary[IFNAMSIZ - 1] = 0; diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index 21c648854a8c..e8526552790c 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -19,7 +19,6 @@ #include #include #include -#include #include "bonding.h" int bond_get_slave(struct net_device *slave_dev, struct sk_buff *skb) @@ -452,9 +451,6 @@ static int bond_fill_info(struct sk_buff *skb, goto nla_put_failure; packets_per_slave = bond->params.packets_per_slave; - if (packets_per_slave > 1) - packets_per_slave = reciprocal_value(packets_per_slave); - if (nla_put_u32(skb, IFLA_BOND_PACKETS_PER_SLAVE, packets_per_slave)) goto nla_put_failure; diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 945a6668da83..85e434886f2e 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -16,7 +16,6 @@ #include #include #include -#include #include "bonding.h" int bond_option_mode_set(struct bonding *bond, int mode) @@ -671,11 +670,17 @@ int bond_option_packets_per_slave_set(struct bonding *bond, pr_warn("%s: Warning: packets_per_slave has effect only in balance-rr mode\n", bond->dev->name); - if (packets_per_slave > 1) - bond->params.packets_per_slave = + bond->params.packets_per_slave = packets_per_slave; + if (packets_per_slave > 0) { + bond->params.reciprocal_packets_per_slave = reciprocal_value(packets_per_slave); - else - bond->params.packets_per_slave = packets_per_slave; + } else { + /* reciprocal_packets_per_slave is unused if + * packets_per_slave is 0 or 1, just initialize it + */ + bond->params.reciprocal_packets_per_slave = + (struct reciprocal_value) { 0 }; + } return 0; } diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index 011f163c2c67..c083e9a66ece 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -39,7 +39,6 @@ #include #include #include -#include #include "bonding.h" @@ -1374,10 +1373,6 @@ static ssize_t bonding_show_packets_per_slave(struct device *d, { struct bonding *bond = to_bond(d); unsigned int packets_per_slave = bond->params.packets_per_slave; - - if (packets_per_slave > 1) - packets_per_slave = reciprocal_value(packets_per_slave); - return sprintf(buf, "%u\n", packets_per_slave); } diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h index 8a935f8f2b3c..0a616c41dc94 100644 --- a/drivers/net/bonding/bonding.h +++ b/drivers/net/bonding/bonding.h @@ -23,6 +23,8 @@ #include #include #include +#include + #include "bond_3ad.h" #include "bond_alb.h" @@ -171,6 +173,7 @@ struct bond_params { int resend_igmp; int lp_interval; int packets_per_slave; + struct reciprocal_value reciprocal_packets_per_slave; }; struct bond_parm_tbl { diff --git a/include/linux/flex_array.h b/include/linux/flex_array.h index 6843cf193a44..b6efb0c64408 100644 --- a/include/linux/flex_array.h +++ b/include/linux/flex_array.h @@ -2,6 +2,7 @@ #define _FLEX_ARRAY_H #include +#include #include #define FLEX_ARRAY_PART_SIZE PAGE_SIZE @@ -22,7 +23,7 @@ struct flex_array { int element_size; int total_nr_elements; int elems_per_part; - u32 reciprocal_elems; + struct reciprocal_value reciprocal_elems; struct flex_array_part *parts[]; }; /* diff --git a/include/linux/reciprocal_div.h b/include/linux/reciprocal_div.h index f9c90b33285b..8c5a3fb6c6c5 100644 --- a/include/linux/reciprocal_div.h +++ b/include/linux/reciprocal_div.h @@ -4,29 +4,32 @@ #include /* - * This file describes reciprocical division. + * This algorithm is based on the paper "Division by Invariant + * Integers Using Multiplication" by Torbjörn Granlund and Peter + * L. Montgomery. * - * This optimizes the (A/B) problem, when A and B are two u32 - * and B is a known value (but not known at compile time) + * The assembler implementation from Agner Fog, which this code is + * based on, can be found here: + * http://www.agner.org/optimize/asmlib.zip * - * The math principle used is : - * Let RECIPROCAL_VALUE(B) be (((1LL << 32) + (B - 1))/ B) - * Then A / B = (u32)(((u64)(A) * (R)) >> 32) - * - * This replaces a divide by a multiply (and a shift), and - * is generally less expensive in CPU cycles. + * This optimization for A/B is helpful if the divisor B is mostly + * runtime invariant. The reciprocal of B is calculated in the + * slow-path with reciprocal_value(). The fast-path can then just use + * a much faster multiplication operation with a variable dividend A + * to calculate the division A/B. */ -/* - * Computes the reciprocal value (R) for the value B of the divisor. - * Should not be called before each reciprocal_divide(), - * or else the performance is slower than a normal divide. - */ -extern u32 reciprocal_value(u32 B); +struct reciprocal_value { + u32 m; + u8 sh1, sh2; +}; +struct reciprocal_value reciprocal_value(u32 d); -static inline u32 reciprocal_divide(u32 A, u32 R) +static inline u32 reciprocal_divide(u32 a, struct reciprocal_value R) { - return (u32)(((u64)A * R) >> 32); + u32 t = (u32)(((u64)a * R.m) >> 32); + return (t + ((a - t) >> R.sh1)) >> R.sh2; } -#endif + +#endif /* _LINUX_RECIPROCAL_DIV_H */ diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 09bfffb08a56..96e8abae19a9 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -1,6 +1,8 @@ #ifndef _LINUX_SLAB_DEF_H #define _LINUX_SLAB_DEF_H +#include + /* * Definitions unique to the original Linux SLAB allocator. */ @@ -12,7 +14,7 @@ struct kmem_cache { unsigned int shared; unsigned int size; - u32 reciprocal_buffer_size; + struct reciprocal_value reciprocal_buffer_size; /* 2) touched by every alloc & free from the backend */ unsigned int flags; /* constant flags */ diff --git a/include/net/red.h b/include/net/red.h index 168bb2f495f2..76e0b5f922c6 100644 --- a/include/net/red.h +++ b/include/net/red.h @@ -130,7 +130,8 @@ struct red_parms { u32 qth_max; /* Max avg length threshold: Wlog scaled */ u32 Scell_max; u32 max_P; /* probability, [0 .. 1.0] 32 scaled */ - u32 max_P_reciprocal; /* reciprocal_value(max_P / qth_delta) */ + /* reciprocal_value(max_P / qth_delta) */ + struct reciprocal_value max_P_reciprocal; u32 qth_delta; /* max_th - min_th */ u32 target_min; /* min_th + 0.4*(max_th - min_th) */ u32 target_max; /* min_th + 0.6*(max_th - min_th) */ diff --git a/lib/flex_array.c b/lib/flex_array.c index 6948a6692fc4..2eed22fa507c 100644 --- a/lib/flex_array.c +++ b/lib/flex_array.c @@ -90,8 +90,8 @@ struct flex_array *flex_array_alloc(int element_size, unsigned int total, { struct flex_array *ret; int elems_per_part = 0; - int reciprocal_elems = 0; int max_size = 0; + struct reciprocal_value reciprocal_elems = { 0 }; if (element_size) { elems_per_part = FLEX_ARRAY_ELEMENTS_PER_PART(element_size); @@ -119,6 +119,11 @@ EXPORT_SYMBOL(flex_array_alloc); static int fa_element_to_part_nr(struct flex_array *fa, unsigned int element_nr) { + /* + * if element_size == 0 we don't get here, so we never touch + * the zeroed fa->reciprocal_elems, which would yield invalid + * results + */ return reciprocal_divide(element_nr, fa->reciprocal_elems); } diff --git a/lib/reciprocal_div.c b/lib/reciprocal_div.c index 75510e94f7d0..464152410c51 100644 --- a/lib/reciprocal_div.c +++ b/lib/reciprocal_div.c @@ -1,11 +1,27 @@ +#include #include #include #include -u32 reciprocal_value(u32 k) +/* + * For a description of the algorithm please have a look at + * include/linux/reciprocal_div.h + */ + +struct reciprocal_value reciprocal_value(u32 d) { - u64 val = (1LL << 32) + (k - 1); - do_div(val, k); - return (u32)val; + struct reciprocal_value R; + u64 m; + int l; + + l = fls(d - 1); + m = ((1ULL << 32) * ((1ULL << l) - d)); + do_div(m, d); + ++m; + R.m = (u32)m; + R.sh1 = min(l, 1); + R.sh2 = max(l - 1, 0); + + return R; } EXPORT_SYMBOL(reciprocal_value); diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index a2bfc371b44a..de1059af6da1 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -91,7 +91,7 @@ struct netem_sched_data { u64 rate; s32 packet_overhead; u32 cell_size; - u32 cell_size_reciprocal; + struct reciprocal_value cell_size_reciprocal; s32 cell_overhead; struct crndstate { @@ -725,9 +725,11 @@ static void get_rate(struct Qdisc *sch, const struct nlattr *attr) q->rate = r->rate; q->packet_overhead = r->packet_overhead; q->cell_size = r->cell_size; + q->cell_overhead = r->cell_overhead; if (q->cell_size) q->cell_size_reciprocal = reciprocal_value(q->cell_size); - q->cell_overhead = r->cell_overhead; + else + q->cell_size_reciprocal = (struct reciprocal_value) { 0 }; } static int get_loss_clg(struct Qdisc *sch, const struct nlattr *attr) -- cgit v1.3-14-g43fede From eb97768acb3f7749a3a03ee35fee9088244113ea Mon Sep 17 00:00:00 2001 From: FX Le Bail Date: Wed, 22 Jan 2014 05:39:46 +0100 Subject: net: update comments of "struct msghdr" with the more accurate RFC3542 ones Signed-off-by: Francois-Xavier Le Bail Signed-off-by: David S. Miller --- include/linux/socket.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 5d488a65ad20..8e98297f1388 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -45,13 +45,13 @@ struct linger { */ struct msghdr { - void * msg_name; /* Socket name */ - int msg_namelen; /* Length of name */ - struct iovec * msg_iov; /* Data blocks */ - __kernel_size_t msg_iovlen; /* Number of blocks */ - void * msg_control; /* Per protocol magic (eg BSD file descriptor passing) */ - __kernel_size_t msg_controllen; /* Length of cmsg list */ - unsigned int msg_flags; + void *msg_name; /* ptr to socket address structure */ + int msg_namelen; /* size of socket address structure */ + struct iovec *msg_iov; /* scatter/gather array */ + __kernel_size_t msg_iovlen; /* # elements in msg_iov */ + void *msg_control; /* ancillary data */ + __kernel_size_t msg_controllen; /* ancillary data buffer length */ + unsigned int msg_flags; /* flags on received message */ }; /* For recvmmsg/sendmmsg */ -- cgit v1.3-14-g43fede From a9517d0f43832d787a4a0348163d659641bfd83c Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 22 Jan 2014 09:05:57 +0100 Subject: rtnetlink: remove ndo_get_slave No longer used API bond-specific can be removed now. This is now handled in a generic way in rtnl_link_ops. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c31022980e18..440a02ee6f92 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -921,9 +921,6 @@ struct netdev_phys_port_id { * int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev); * Called to release previously enslaved netdev. * - * int (*ndo_get_slave)(struct net_device *slave_dev, struct sk_buff *skb); - * Called to fill netlink skb with slave info. - * * Feature/offload setting functions. * netdev_features_t (*ndo_fix_features)(struct net_device *dev, * netdev_features_t features); @@ -1096,8 +1093,6 @@ struct net_device_ops { struct net_device *slave_dev); int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev); - int (*ndo_get_slave)(struct net_device *slave_dev, - struct sk_buff *skb); netdev_features_t (*ndo_fix_features)(struct net_device *dev, netdev_features_t features); int (*ndo_set_features)(struct net_device *dev, -- cgit v1.3-14-g43fede