[linux-next] LinuxNextTracking branch, master, updated. next-20140605

The following commit has been merged in the master branch: commit c99f7abf0e69987e4add567e155e042cb1f2a20b Merge: 92ff71b8fe9cd9c673615fc6f3870af7376d7c84 d8b0426af5b67973585712c9af36b86f6ea97815 Author: David S. Miller davem@davemloft.net Date: Tue Jun 3 23:32:12 2014 -0700

Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Conflicts: include/net/inetpeer.h net/ipv6/output_core.c

Changes in net were fixing bugs in code removed in net-next.

Signed-off-by: David S. Miller davem@davemloft.net

diff --combined MAINTAINERS index dd33abf,6c484ac..a328709 --- a/MAINTAINERS +++ b/MAINTAINERS @@@ -1888,7 -1888,7 +1888,7 @@@ F: drivers/net/ethernet/broadcom/bnx2. F: drivers/net/ethernet/broadcom/bnx2_*

BROADCOM BNX2X 10 GIGABIT ETHERNET DRIVER -M: Ariel Elior ariele@broadcom.com +M: Ariel Elior ariel.elior@qlogic.com L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/broadcom/bnx2x/ @@@ -1968,12 -1968,6 +1968,12 @@@ S: Maintaine F: drivers/bcma/ F: include/linux/bcma/

+BROADCOM SYSTEMPORT ETHERNET DRIVER +M: Florian Fainelli f.fainelli@gmail.com +L: netdev@vger.kernel.org +S: Supported +F: drivers/net/ethernet/broadcom/bcmsysport.* + BROCADE BFA FC SCSI DRIVER M: Anil Gurumurthy anil.gurumurthy@qlogic.com M: Sudarsana Kalluru sudarsana.kalluru@qlogic.com @@@ -2229,8 -2223,9 +2229,8 @@@ F: drivers/platform/chrome CISCO VIC ETHERNET NIC DRIVER M: Christian Benvenuti benve@cisco.com M: Sujith Sankar ssujith@cisco.com -M: Govindarajulu Varadarajan govindarajulu90@gmail.com +M: Govindarajulu Varadarajan _govind@gmx.com M: Neel Patel neepatel@cisco.com -M: Nishank Trivedi nistrive@cisco.com S: Supported F: drivers/net/ethernet/cisco/enic/

@@@ -3158,10 -3153,9 +3158,9 @@@ S: Maintaine F: drivers/scsi/eata_pio.*

EBTABLES - M: Bart De Schuymer bart.de.schuymer@pandora.be L: netfilter-devel@vger.kernel.org W: http://ebtables.sourceforge.net/ - S: Maintained + S: Orphan F: include/linux/netfilter_bridge/ebt_*.h F: include/uapi/linux/netfilter_bridge/ebt_*.h F: net/bridge/netfilter/ebt*.c @@@ -7410,6 -7404,14 +7409,14 @@@ F: drivers/rpmsg F: Documentation/rpmsg.txt F: include/linux/rpmsg.h

+ RESET CONTROLLER FRAMEWORK + M: Philipp Zabel p.zabel@pengutronix.de + S: Maintained + F: drivers/reset/ + F: Documentation/devicetree/bindings/reset/ + F: include/linux/reset.h + F: include/linux/reset-controller.h + RFKILL M: Johannes Berg johannes@sipsolutions.net L: linux-wireless@vger.kernel.org diff --combined drivers/net/ethernet/Kconfig index f0e2a4d,0513494..edb7186 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@@ -39,6 -39,7 +39,7 @@@ source "drivers/net/ethernet/cisco/Kcon config CX_ECAT tristate "Beckhoff CX5020 EtherCAT master support" depends on PCI + depends on X86 || COMPILE_TEST ---help--- Driver for EtherCAT master module located on CCAT FPGA that can be found on Beckhoff CX5020, and possibly other of CX @@@ -67,7 -68,6 +68,7 @@@ source "drivers/net/ethernet/neterion/K source "drivers/net/ethernet/faraday/Kconfig" source "drivers/net/ethernet/freescale/Kconfig" source "drivers/net/ethernet/fujitsu/Kconfig" +source "drivers/net/ethernet/hisilicon/Kconfig" source "drivers/net/ethernet/hp/Kconfig" source "drivers/net/ethernet/ibm/Kconfig" source "drivers/net/ethernet/intel/Kconfig" diff --combined drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index d18441e,72197d0..23da479 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@@ -6,7 -6,7 +6,7 @@@ * it under the terms of the GNU General Public License as published by * the Free Software Foundation. * - * Maintained by: Eilon Greenstein eilong@broadcom.com + * Maintained by: Ariel Elior ariel.elior@qlogic.com * Written by: Eliezer Tamir * Based on code from Michael Chan's bnx2 driver * UDP CSUM errata workaround by Arik Gendelman @@@ -906,6 -906,18 +906,18 @@@ static int bnx2x_rx_int(struct bnx2x_fa bd_prod = RX_BD(bd_prod); bd_cons = RX_BD(bd_cons);

+ /* A rmb() is required to ensure that the CQE is not read + * before it is written by the adapter DMA. PCI ordering + * rules will make sure the other fields are written before + * the marker at the end of struct eth_fast_path_rx_cqe + * but without rmb() a weakly ordered processor can process + * stale data. Without the barrier TPA state-machine might + * enter inconsistent state and kernel stack might be + * provided with incorrect packet description - these lead + * to various kernel crashed. + */ + rmb(); + cqe_fp_flags = cqe_fp->type_error_flags; cqe_fp_type = cqe_fp_flags & ETH_FAST_PATH_RX_CQE_TYPE;

diff --combined drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index ff2bdd8,6fa9cd4..cf14218 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@@ -6,7 -6,7 +6,7 @@@ * it under the terms of the GNU General Public License as published by * the Free Software Foundation. * - * Maintained by: Eilon Greenstein eilong@broadcom.com + * Maintained by: Ariel Elior ariel.elior@qlogic.com * Written by: Eliezer Tamir * Based on code from Michael Chan's bnx2 driver * UDP CSUM errata workaround by Arik Gendelman @@@ -13283,8 -13283,8 +13283,8 @@@ static int bnx2x_eeh_nic_unload(struct netdev_reset_tc(bp->dev);

del_timer_sync(&bp->timer); - cancel_delayed_work(&bp->sp_task); - cancel_delayed_work(&bp->period_task); + cancel_delayed_work_sync(&bp->sp_task); + cancel_delayed_work_sync(&bp->period_task);

spin_lock_bh(&bp->stats_lock); bp->stats_state = STATS_STATE_DISABLED; diff --combined drivers/net/ethernet/mellanox/mlx4/main.c index 38e9a4c,c187d74..19606a4 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@@ -104,6 -104,8 +104,6 @@@ module_param(enable_64b_cqe_eqe, bool, MODULE_PARM_DESC(enable_64b_cqe_eqe, "Enable 64 byte CQEs/EQEs when the FW supports this (default: True)");

-#define HCA_GLOBAL_CAP_MASK 0 - #define PF_CONTEXT_BEHAVIOUR_MASK MLX4_FUNC_CAP_64B_EQE_CQE

static char mlx4_version[] = @@@ -132,7 -134,8 +132,7 @@@ MODULE_PARM_DESC(log_num_vlan, "Log2 ma

static bool use_prio; module_param_named(use_prio, use_prio, bool, 0444); -MODULE_PARM_DESC(use_prio, "Enable steering by VLAN priority on ETH ports " - "(0/1, default 0)"); +MODULE_PARM_DESC(use_prio, "Enable steering by VLAN priority on ETH ports (deprecated)");

int log_mtts_per_seg = ilog2(MLX4_MTT_ENTRY_PER_SEG); module_param_named(log_mtts_per_seg, log_mtts_per_seg, int, 0444); @@@ -160,7 -163,8 +160,7 @@@ int mlx4_check_port_params(struct mlx4_ for (i = 0; i < dev->caps.num_ports - 1; i++) { if (port_type[i] != port_type[i + 1]) { if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_DPDP)) { - mlx4_err(dev, "Only same port types supported " - "on this HCA, aborting.\n"); + mlx4_err(dev, "Only same port types supported on this HCA, aborting\n"); return -EINVAL; } } @@@ -168,8 -172,8 +168,8 @@@

for (i = 0; i < dev->caps.num_ports; i++) { if (!(port_type[i] & dev->caps.supported_type[i+1])) { - mlx4_err(dev, "Requested port type for port %d is not " - "supported on this HCA\n", i + 1); + mlx4_err(dev, "Requested port type for port %d is not supported on this HCA\n", + i + 1); return -EINVAL; } } @@@ -191,23 -195,26 +191,23 @@@ static int mlx4_dev_cap(struct mlx4_de

err = mlx4_QUERY_DEV_CAP(dev, dev_cap); if (err) { - mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting.\n"); + mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting\n"); return err; }

if (dev_cap->min_page_sz > PAGE_SIZE) { - mlx4_err(dev, "HCA minimum page size of %d bigger than " - "kernel PAGE_SIZE of %ld, aborting.\n", + mlx4_err(dev, "HCA minimum page size of %d bigger than kernel PAGE_SIZE of %ld, aborting\n", dev_cap->min_page_sz, PAGE_SIZE); return -ENODEV; } if (dev_cap->num_ports > MLX4_MAX_PORTS) { - mlx4_err(dev, "HCA has %d ports, but we only support %d, " - "aborting.\n", + mlx4_err(dev, "HCA has %d ports, but we only support %d, aborting\n", dev_cap->num_ports, MLX4_MAX_PORTS); return -ENODEV; }

if (dev_cap->uar_size > pci_resource_len(dev->pdev, 2)) { - mlx4_err(dev, "HCA reported UAR size of 0x%x bigger than " - "PCI resource 2 size of 0x%llx, aborting.\n", + mlx4_err(dev, "HCA reported UAR size of 0x%x bigger than PCI resource 2 size of 0x%llx, aborting\n", dev_cap->uar_size, (unsigned long long) pci_resource_len(dev->pdev, 2)); return -ENODEV; @@@ -289,6 -296,7 +289,6 @@@

dev->caps.log_num_macs = log_num_mac; dev->caps.log_num_vlans = MLX4_LOG_NUM_VLANS; - dev->caps.log_num_prios = use_prio ? 3 : 0;

for (i = 1; i <= dev->caps.num_ports; ++i) { dev->caps.port_type[i] = MLX4_PORT_TYPE_NONE; @@@ -339,12 -347,14 +339,12 @@@

if (dev->caps.log_num_macs > dev_cap->log_max_macs[i]) { dev->caps.log_num_macs = dev_cap->log_max_macs[i]; - mlx4_warn(dev, "Requested number of MACs is too much " - "for port %d, reducing to %d.\n", + mlx4_warn(dev, "Requested number of MACs is too much for port %d, reducing to %d\n", i, 1 << dev->caps.log_num_macs); } if (dev->caps.log_num_vlans > dev_cap->log_max_vlans[i]) { dev->caps.log_num_vlans = dev_cap->log_max_vlans[i]; - mlx4_warn(dev, "Requested number of VLANs is too much " - "for port %d, reducing to %d.\n", + mlx4_warn(dev, "Requested number of VLANs is too much for port %d, reducing to %d\n", i, 1 << dev->caps.log_num_vlans); } } @@@ -356,6 -366,7 +356,6 @@@ dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_ADDR] = (1 << dev->caps.log_num_macs) * (1 << dev->caps.log_num_vlans) * - (1 << dev->caps.log_num_prios) * dev->caps.num_ports; dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_EXCH] = MLX4_NUM_FEXCH;

@@@ -573,14 -584,13 +573,14 @@@ static int mlx4_slave_cap(struct mlx4_d memset(&hca_param, 0, sizeof(hca_param)); err = mlx4_QUERY_HCA(dev, &hca_param); if (err) { - mlx4_err(dev, "QUERY_HCA command failed, aborting.\n"); + mlx4_err(dev, "QUERY_HCA command failed, aborting\n"); return err; }

- /*fail if the hca has an unknown capability */ - if ((hca_param.global_caps | HCA_GLOBAL_CAP_MASK) != - HCA_GLOBAL_CAP_MASK) { + /* fail if the hca has an unknown global capability + * at this time global_caps should be always zeroed + */ + if (hca_param.global_caps) { mlx4_err(dev, "Unknown hca global capabilities\n"); return -ENOSYS; } @@@ -593,18 -603,19 +593,18 @@@ dev->caps.max_qp_dest_rdma = 1 << hca_param.log_rd_per_qp; err = mlx4_dev_cap(dev, &dev_cap); if (err) { - mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting.\n"); + mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting\n"); return err; }

err = mlx4_QUERY_FW(dev); if (err) - mlx4_err(dev, "QUERY_FW command failed: could not get FW version.\n"); + mlx4_err(dev, "QUERY_FW command failed: could not get FW version\n");

page_size = ~dev->caps.page_size_cap + 1; mlx4_warn(dev, "HCA minimum page size:%d\n", page_size); if (page_size > PAGE_SIZE) { - mlx4_err(dev, "HCA minimum page size of %d bigger than " - "kernel PAGE_SIZE of %ld, aborting.\n", + mlx4_err(dev, "HCA minimum page size of %d bigger than kernel PAGE_SIZE of %ld, aborting\n", page_size, PAGE_SIZE); return -ENODEV; } @@@ -622,8 -633,8 +622,8 @@@ memset(&func_cap, 0, sizeof(func_cap)); err = mlx4_QUERY_FUNC_CAP(dev, 0, &func_cap); if (err) { - mlx4_err(dev, "QUERY_FUNC_CAP general command failed, aborting (%d).\n", - err); + mlx4_err(dev, "QUERY_FUNC_CAP general command failed, aborting (%d)\n", + err); return err; }

@@@ -650,8 -661,8 +650,8 @@@ dev->caps.num_amgms = 0;

if (dev->caps.num_ports > MLX4_MAX_PORTS) { - mlx4_err(dev, "HCA has %d ports, but we only support %d, " - "aborting.\n", dev->caps.num_ports, MLX4_MAX_PORTS); + mlx4_err(dev, "HCA has %d ports, but we only support %d, aborting\n", + dev->caps.num_ports, MLX4_MAX_PORTS); return -ENODEV; }

@@@ -669,8 -680,8 +669,8 @@@ for (i = 1; i <= dev->caps.num_ports; ++i) { err = mlx4_QUERY_FUNC_CAP(dev, (u32) i, &func_cap); if (err) { - mlx4_err(dev, "QUERY_FUNC_CAP port command failed for" - " port %d, aborting (%d).\n", i, err); + mlx4_err(dev, "QUERY_FUNC_CAP port command failed for port %d, aborting (%d)\n", + i, err); goto err_mem; } dev->caps.qp0_tunnel[i - 1] = func_cap.qp0_tunnel_qpn; @@@ -688,7 -699,8 +688,7 @@@ if (dev->caps.uar_page_size * (dev->caps.num_uars - dev->caps.reserved_uars) > pci_resource_len(dev->pdev, 2)) { - mlx4_err(dev, "HCA reported UAR region size of 0x%x bigger than " - "PCI resource 2 size of 0x%llx, aborting.\n", + mlx4_err(dev, "HCA reported UAR region size of 0x%x bigger than PCI resource 2 size of 0x%llx, aborting\n", dev->caps.uar_page_size * dev->caps.num_uars, (unsigned long long) pci_resource_len(dev->pdev, 2)); goto err_mem; @@@ -710,7 -722,7 +710,7 @@@ }

dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_TS; - mlx4_warn(dev, "Timestamping is not supported in slave mode.\n"); + mlx4_warn(dev, "Timestamping is not supported in slave mode\n");

slave_adjust_steering_mode(dev, &dev_cap, &hca_param);

@@@ -772,8 -784,8 +772,8 @@@ int mlx4_change_port_types(struct mlx4_ dev->caps.port_type[port] = port_types[port - 1]; err = mlx4_SET_PORT(dev, port, -1); if (err) { - mlx4_err(dev, "Failed to set port %d, " - "aborting\n", port); + mlx4_err(dev, "Failed to set port %d, aborting\n", + port); goto out; } } @@@ -856,7 -868,9 +856,7 @@@ static ssize_t set_port_type(struct dev } } if (err) { - mlx4_err(mdev, "Auto sensing is not supported on this HCA. " - "Set only 'eth' or 'ib' for both ports " - "(should be the same)\n"); + mlx4_err(mdev, "Auto sensing is not supported on this HCA. Set only 'eth' or 'ib' for both ports (should be the same)\n"); goto out; }

@@@ -961,8 -975,8 +961,8 @@@ static ssize_t set_port_ib_mtu(struct d mlx4_CLOSE_PORT(mdev, port); err = mlx4_SET_PORT(mdev, port, -1); if (err) { - mlx4_err(mdev, "Failed to set port %d, " - "aborting\n", port); + mlx4_err(mdev, "Failed to set port %d, aborting\n", + port); goto err_set_port; } } @@@ -981,19 -995,19 +981,19 @@@ static int mlx4_load_fw(struct mlx4_de priv->fw.fw_icm = mlx4_alloc_icm(dev, priv->fw.fw_pages, GFP_HIGHUSER | __GFP_NOWARN, 0); if (!priv->fw.fw_icm) { - mlx4_err(dev, "Couldn't allocate FW area, aborting.\n"); + mlx4_err(dev, "Couldn't allocate FW area, aborting\n"); return -ENOMEM; }

err = mlx4_MAP_FA(dev, priv->fw.fw_icm); if (err) { - mlx4_err(dev, "MAP_FA command failed, aborting.\n"); + mlx4_err(dev, "MAP_FA command failed, aborting\n"); goto err_free; }

err = mlx4_RUN_FW(dev); if (err) { - mlx4_err(dev, "RUN_FW command failed, aborting.\n"); + mlx4_err(dev, "RUN_FW command failed, aborting\n"); goto err_unmap_fa; }

@@@ -1077,30 -1091,30 +1077,30 @@@ static int mlx4_init_icm(struct mlx4_de

err = mlx4_SET_ICM_SIZE(dev, icm_size, &aux_pages); if (err) { - mlx4_err(dev, "SET_ICM_SIZE command failed, aborting.\n"); + mlx4_err(dev, "SET_ICM_SIZE command failed, aborting\n"); return err; }

- mlx4_dbg(dev, "%lld KB of HCA context requires %lld KB aux memory.\n", + mlx4_dbg(dev, "%lld KB of HCA context requires %lld KB aux memory\n", (unsigned long long) icm_size >> 10, (unsigned long long) aux_pages << 2);

priv->fw.aux_icm = mlx4_alloc_icm(dev, aux_pages, GFP_HIGHUSER | __GFP_NOWARN, 0); if (!priv->fw.aux_icm) { - mlx4_err(dev, "Couldn't allocate aux memory, aborting.\n"); + mlx4_err(dev, "Couldn't allocate aux memory, aborting\n"); return -ENOMEM; }

err = mlx4_MAP_ICM_AUX(dev, priv->fw.aux_icm); if (err) { - mlx4_err(dev, "MAP_ICM_AUX command failed, aborting.\n"); + mlx4_err(dev, "MAP_ICM_AUX command failed, aborting\n"); goto err_free_aux; }

err = mlx4_init_cmpt_table(dev, init_hca->cmpt_base, dev_cap->cmpt_entry_sz); if (err) { - mlx4_err(dev, "Failed to map cMPT context memory, aborting.\n"); + mlx4_err(dev, "Failed to map cMPT context memory, aborting\n"); goto err_unmap_aux; }

@@@ -1111,7 -1125,7 +1111,7 @@@ init_hca->eqc_base, dev_cap->eqc_entry_sz, num_eqs, num_eqs, 0, 0); if (err) { - mlx4_err(dev, "Failed to map EQ context memory, aborting.\n"); + mlx4_err(dev, "Failed to map EQ context memory, aborting\n"); goto err_unmap_cmpt; }

@@@ -1132,7 -1146,7 +1132,7 @@@ dev->caps.num_mtts, dev->caps.reserved_mtts, 1, 0); if (err) { - mlx4_err(dev, "Failed to map MTT context memory, aborting.\n"); + mlx4_err(dev, "Failed to map MTT context memory, aborting\n"); goto err_unmap_eq; }

@@@ -1142,7 -1156,7 +1142,7 @@@ dev->caps.num_mpts, dev->caps.reserved_mrws, 1, 1); if (err) { - mlx4_err(dev, "Failed to map dMPT context memory, aborting.\n"); + mlx4_err(dev, "Failed to map dMPT context memory, aborting\n"); goto err_unmap_mtt; }

@@@ -1153,7 -1167,7 +1153,7 @@@ dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW], 0, 0); if (err) { - mlx4_err(dev, "Failed to map QP context memory, aborting.\n"); + mlx4_err(dev, "Failed to map QP context memory, aborting\n"); goto err_unmap_dmpt; }

@@@ -1164,7 -1178,7 +1164,7 @@@ dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW], 0, 0); if (err) { - mlx4_err(dev, "Failed to map AUXC context memory, aborting.\n"); + mlx4_err(dev, "Failed to map AUXC context memory, aborting\n"); goto err_unmap_qp; }

@@@ -1175,7 -1189,7 +1175,7 @@@ dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW], 0, 0); if (err) { - mlx4_err(dev, "Failed to map ALTC context memory, aborting.\n"); + mlx4_err(dev, "Failed to map ALTC context memory, aborting\n"); goto err_unmap_auxc; }

@@@ -1196,7 -1210,7 +1196,7 @@@ dev->caps.num_cqs, dev->caps.reserved_cqs, 0, 0); if (err) { - mlx4_err(dev, "Failed to map CQ context memory, aborting.\n"); + mlx4_err(dev, "Failed to map CQ context memory, aborting\n"); goto err_unmap_rdmarc; }

@@@ -1206,7 -1220,7 +1206,7 @@@ dev->caps.num_srqs, dev->caps.reserved_srqs, 0, 0); if (err) { - mlx4_err(dev, "Failed to map SRQ context memory, aborting.\n"); + mlx4_err(dev, "Failed to map SRQ context memory, aborting\n"); goto err_unmap_cq; }

@@@ -1224,7 -1238,7 +1224,7 @@@ dev->caps.num_mgms + dev->caps.num_amgms, 0, 0); if (err) { - mlx4_err(dev, "Failed to map MCG context memory, aborting.\n"); + mlx4_err(dev, "Failed to map MCG context memory, aborting\n"); goto err_unmap_srq; }

@@@ -1301,7 -1315,7 +1301,7 @@@ static void mlx4_slave_exit(struct mlx4

mutex_lock(&priv->cmd.slave_cmd_mutex); if (mlx4_comm_cmd(dev, MLX4_COMM_CMD_RESET, 0, MLX4_COMM_TIME)) - mlx4_warn(dev, "Failed to close slave function.\n"); + mlx4_warn(dev, "Failed to close slave function\n"); mutex_unlock(&priv->cmd.slave_cmd_mutex); }

@@@ -1399,7 -1413,7 +1399,7 @@@ static int mlx4_init_slave(struct mlx4_ u32 cmd_channel_ver;

if (atomic_read(&pf_loading)) { - mlx4_warn(dev, "PF is not ready. Deferring probe\n"); + mlx4_warn(dev, "PF is not ready - Deferring probe\n"); return -EPROBE_DEFER; }

@@@ -1412,7 -1426,8 +1412,7 @@@ * NUM_OF_RESET_RETRIES times before leaving.*/ if (ret_from_reset) { if (MLX4_DELAY_RESET_SLAVE == ret_from_reset) { - mlx4_warn(dev, "slave is currently in the " - "middle of FLR. Deferring probe.\n"); + mlx4_warn(dev, "slave is currently in the middle of FLR - Deferring probe\n"); mutex_unlock(&priv->cmd.slave_cmd_mutex); return -EPROBE_DEFER; } else @@@ -1426,7 -1441,8 +1426,7 @@@

if (MLX4_COMM_GET_IF_REV(cmd_channel_ver) != MLX4_COMM_GET_IF_REV(slave_read)) { - mlx4_err(dev, "slave driver version is not supported" - " by the master\n"); + mlx4_err(dev, "slave driver version is not supported by the master\n"); goto err; }

@@@ -1504,7 -1520,8 +1504,7 @@@ static void choose_steering_mode(struc

if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER || dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER) - mlx4_warn(dev, "Must have both UC_STEER and MC_STEER flags " - "set to use B0 steering. Falling back to A0 steering mode.\n"); + mlx4_warn(dev, "Must have both UC_STEER and MC_STEER flags set to use B0 steering - falling back to A0 steering mode\n"); } dev->oper_log_mgm_entry_size = mlx4_log_num_mgm_entry_size > 0 ? @@@ -1512,7 -1529,8 +1512,7 @@@ MLX4_DEFAULT_MGM_LOG_ENTRY_SIZE; dev->caps.num_qp_per_mgm = mlx4_get_qp_per_mgm(dev); } - mlx4_dbg(dev, "Steering mode is: %s, oper_log_mgm_entry_size = %d, " - "modparam log_num_mgm_entry_size = %d\n", + mlx4_dbg(dev, "Steering mode is: %s, oper_log_mgm_entry_size = %d, modparam log_num_mgm_entry_size = %d\n", mlx4_steering_mode_str(dev->caps.steering_mode), dev->oper_log_mgm_entry_size, mlx4_log_num_mgm_entry_size); @@@ -1546,15 -1564,15 +1546,15 @@@ static int mlx4_init_hca(struct mlx4_de err = mlx4_QUERY_FW(dev); if (err) { if (err == -EACCES) - mlx4_info(dev, "non-primary physical function, skipping.\n"); + mlx4_info(dev, "non-primary physical function, skipping\n"); else - mlx4_err(dev, "QUERY_FW command failed, aborting.\n"); + mlx4_err(dev, "QUERY_FW command failed, aborting\n"); return err; }

err = mlx4_load_fw(dev); if (err) { - mlx4_err(dev, "Failed to start FW, aborting.\n"); + mlx4_err(dev, "Failed to start FW, aborting\n"); return err; }

@@@ -1566,7 -1584,7 +1566,7 @@@

err = mlx4_dev_cap(dev, &dev_cap); if (err) { - mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting.\n"); + mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting\n"); goto err_stop_fw; }

@@@ -1607,7 -1625,7 +1607,7 @@@

err = mlx4_INIT_HCA(dev, &init_hca); if (err) { - mlx4_err(dev, "INIT_HCA command failed, aborting.\n"); + mlx4_err(dev, "INIT_HCA command failed, aborting\n"); goto err_free_icm; } /* @@@ -1618,7 -1636,7 +1618,7 @@@ memset(&init_hca, 0, sizeof(init_hca)); err = mlx4_QUERY_HCA(dev, &init_hca); if (err) { - mlx4_err(dev, "QUERY_HCA command failed, disable timestamp.\n"); + mlx4_err(dev, "QUERY_HCA command failed, disable timestamp\n"); dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_TS; } else { dev->caps.hca_core_clock = @@@ -1631,14 -1649,14 +1631,14 @@@ if (!dev->caps.hca_core_clock) { dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_TS; mlx4_err(dev, - "HCA frequency is 0. Timestamping is not supported."); + "HCA frequency is 0 - timestamping is not supported\n"); } else if (map_internal_clock(dev)) { /* * Map internal clock, * in case of failure disable timestamping */ dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_TS; - mlx4_err(dev, "Failed to map internal clock. Timestamping is not supported.\n"); + mlx4_err(dev, "Failed to map internal clock. Timestamping is not supported\n"); } } } else { @@@ -1665,7 -1683,7 +1665,7 @@@

err = mlx4_QUERY_ADAPTER(dev, &adapter); if (err) { - mlx4_err(dev, "QUERY_ADAPTER command failed, aborting.\n"); + mlx4_err(dev, "QUERY_ADAPTER command failed, aborting\n"); goto unmap_bf; }

@@@ -1775,69 -1793,79 +1775,69 @@@ static int mlx4_setup_hca(struct mlx4_d

err = mlx4_init_uar_table(dev); if (err) { - mlx4_err(dev, "Failed to initialize " - "user access region table, aborting.\n"); - return err; + mlx4_err(dev, "Failed to initialize user access region table, aborting\n"); + return err; }

err = mlx4_uar_alloc(dev, &priv->driver_uar); if (err) { - mlx4_err(dev, "Failed to allocate driver access region, " - "aborting.\n"); + mlx4_err(dev, "Failed to allocate driver access region, aborting\n"); goto err_uar_table_free; }

priv->kar = ioremap((phys_addr_t) priv->driver_uar.pfn << PAGE_SHIFT, PAGE_SIZE); if (!priv->kar) { - mlx4_err(dev, "Couldn't map kernel access region, " - "aborting.\n"); + mlx4_err(dev, "Couldn't map kernel access region, aborting\n"); err = -ENOMEM; goto err_uar_free; }

err = mlx4_init_pd_table(dev); if (err) { - mlx4_err(dev, "Failed to initialize " - "protection domain table, aborting.\n"); + mlx4_err(dev, "Failed to initialize protection domain table, aborting\n"); goto err_kar_unmap; }

err = mlx4_init_xrcd_table(dev); if (err) { - mlx4_err(dev, "Failed to initialize " - "reliable connection domain table, aborting.\n"); + mlx4_err(dev, "Failed to initialize reliable connection domain table, aborting\n"); goto err_pd_table_free; }

err = mlx4_init_mr_table(dev); if (err) { - mlx4_err(dev, "Failed to initialize " - "memory region table, aborting.\n"); + mlx4_err(dev, "Failed to initialize memory region table, aborting\n"); goto err_xrcd_table_free; }

if (!mlx4_is_slave(dev)) { err = mlx4_init_mcg_table(dev); if (err) { - mlx4_err(dev, "Failed to initialize multicast group table, aborting.\n"); + mlx4_err(dev, "Failed to initialize multicast group table, aborting\n"); goto err_mr_table_free; } }

err = mlx4_init_eq_table(dev); if (err) { - mlx4_err(dev, "Failed to initialize " - "event queue table, aborting.\n"); + mlx4_err(dev, "Failed to initialize event queue table, aborting\n"); goto err_mcg_table_free; }

err = mlx4_cmd_use_events(dev); if (err) { - mlx4_err(dev, "Failed to switch to event-driven " - "firmware commands, aborting.\n"); + mlx4_err(dev, "Failed to switch to event-driven firmware commands, aborting\n"); goto err_eq_table_free; }

err = mlx4_NOP(dev); if (err) { if (dev->flags & MLX4_FLAG_MSI_X) { - mlx4_warn(dev, "NOP command failed to generate MSI-X " - "interrupt IRQ %d).\n", + mlx4_warn(dev, "NOP command failed to generate MSI-X interrupt IRQ %d)\n", priv->eq_table.eq[dev->caps.num_comp_vectors].irq); - mlx4_warn(dev, "Trying again without MSI-X.\n"); + mlx4_warn(dev, "Trying again without MSI-X\n"); } else { - mlx4_err(dev, "NOP command failed to generate interrupt " - "(IRQ %d), aborting.\n", + mlx4_err(dev, "NOP command failed to generate interrupt (IRQ %d), aborting\n", priv->eq_table.eq[dev->caps.num_comp_vectors].irq); mlx4_err(dev, "BIOS or ACPI interrupt routing problem?\n"); } @@@ -1849,25 -1877,28 +1849,25 @@@

err = mlx4_init_cq_table(dev); if (err) { - mlx4_err(dev, "Failed to initialize " - "completion queue table, aborting.\n"); + mlx4_err(dev, "Failed to initialize completion queue table, aborting\n"); goto err_cmd_poll; }

err = mlx4_init_srq_table(dev); if (err) { - mlx4_err(dev, "Failed to initialize " - "shared receive queue table, aborting.\n"); + mlx4_err(dev, "Failed to initialize shared receive queue table, aborting\n"); goto err_cq_table_free; }

err = mlx4_init_qp_table(dev); if (err) { - mlx4_err(dev, "Failed to initialize " - "queue pair table, aborting.\n"); + mlx4_err(dev, "Failed to initialize queue pair table, aborting\n"); goto err_srq_table_free; }

err = mlx4_init_counters_table(dev); if (err && err != -ENOENT) { - mlx4_err(dev, "Failed to initialize counters table, aborting.\n"); + mlx4_err(dev, "Failed to initialize counters table, aborting\n"); goto err_qp_table_free; }

@@@ -1877,8 -1908,9 +1877,8 @@@ err = mlx4_get_port_ib_caps(dev, port, &ib_port_default_caps); if (err) - mlx4_warn(dev, "failed to get port %d default " - "ib capabilities (%d). Continuing " - "with caps = 0\n", port, err); + mlx4_warn(dev, "failed to get port %d default ib capabilities (%d). Continuing with caps = 0\n", + port, err); dev->caps.ib_port_def_cap[port] = ib_port_default_caps;

/* initialize per-slave default ib port capabilities */ @@@ -1888,7 -1920,7 +1888,7 @@@ if (i == mlx4_master_func_num(dev)) continue; priv->mfunc.master.slave_state[i].ib_cap_mask[port] = - ib_port_default_caps; + ib_port_default_caps; } }

@@@ -1901,7 -1933,7 +1901,7 @@@ dev->caps.pkey_table_len[port] : -1); if (err) { mlx4_err(dev, "Failed to set port %d, aborting\n", - port); + port); goto err_counters_table_free; } } @@@ -1977,7 -2009,7 +1977,7 @@@ static void mlx4_enable_msi_x(struct ml kfree(entries); goto no_msi; } else if (nreq < MSIX_LEGACY_SZ + - dev->caps.num_ports * MIN_MSIX_P_PORT) { + dev->caps.num_ports * MIN_MSIX_P_PORT) { /*Working in legacy mode , all EQ's shared*/ dev->caps.comp_pool = 0; dev->caps.num_comp_vectors = nreq - 1; @@@ -2012,6 -2044,7 +2012,7 @@@ static int mlx4_init_port_info(struct m if (!mlx4_is_slave(dev)) { mlx4_init_mac_table(dev, &info->mac_table); mlx4_init_vlan_table(dev, &info->vlan_table); + mlx4_init_roce_gid_table(dev, &info->gid_table); info->base_qpn = mlx4_get_base_qpn(dev, port); }

@@@ -2177,7 -2210,8 +2178,7 @@@ static int __mlx4_init_one(struct pci_d

err = pci_enable_device(pdev); if (err) { - dev_err(&pdev->dev, "Cannot enable PCI device, " - "aborting.\n"); + dev_err(&pdev->dev, "Cannot enable PCI device, aborting\n"); return err; }

@@@ -2224,13 -2258,14 +2225,13 @@@ */ if (!(pci_dev_data & MLX4_PCI_DEV_IS_VF) && !(pci_resource_flags(pdev, 0) & IORESOURCE_MEM)) { - dev_err(&pdev->dev, "Missing DCS, aborting." - "(driver_data: 0x%x, pci_resource_flags(pdev, 0):0x%lx)\n", + dev_err(&pdev->dev, "Missing DCS, aborting (driver_data: 0x%x, pci_resource_flags(pdev, 0):0x%lx)\n", pci_dev_data, pci_resource_flags(pdev, 0)); err = -ENODEV; goto err_disable_pdev; } if (!(pci_resource_flags(pdev, 2) & IORESOURCE_MEM)) { - dev_err(&pdev->dev, "Missing UAR, aborting.\n"); + dev_err(&pdev->dev, "Missing UAR, aborting\n"); err = -ENODEV; goto err_disable_pdev; } @@@ -2245,19 -2280,21 +2246,19 @@@

err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64)); if (err) { - dev_warn(&pdev->dev, "Warning: couldn't set 64-bit PCI DMA mask.\n"); + dev_warn(&pdev->dev, "Warning: couldn't set 64-bit PCI DMA mask\n"); err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); if (err) { - dev_err(&pdev->dev, "Can't set PCI DMA mask, aborting.\n"); + dev_err(&pdev->dev, "Can't set PCI DMA mask, aborting\n"); goto err_release_regions; } } err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); if (err) { - dev_warn(&pdev->dev, "Warning: couldn't set 64-bit " - "consistent PCI DMA mask.\n"); + dev_warn(&pdev->dev, "Warning: couldn't set 64-bit consistent PCI DMA mask\n"); err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); if (err) { - dev_err(&pdev->dev, "Can't set consistent PCI DMA mask, " - "aborting.\n"); + dev_err(&pdev->dev, "Can't set consistent PCI DMA mask, aborting\n"); goto err_release_regions; } } @@@ -2288,7 -2325,7 +2289,7 @@@ if (total_vfs) { unsigned vfs_offset = 0; for (i = 0; i < sizeof(nvfs)/sizeof(nvfs[0]) && - vfs_offset + nvfs[i] < extended_func_num(pdev); + vfs_offset + nvfs[i] < extended_func_num(pdev); vfs_offset += nvfs[i], i++) ; if (i == sizeof(nvfs)/sizeof(nvfs[0])) { @@@ -2314,7 -2351,8 +2315,7 @@@ if (err < 0) goto err_free_dev; else { - mlx4_warn(dev, "Multiple PFs not yet supported." - " Skipping PF.\n"); + mlx4_warn(dev, "Multiple PFs not yet supported - Skipping PF\n"); err = -EINVAL; goto err_free_dev; } @@@ -2324,8 -2362,8 +2325,8 @@@ mlx4_warn(dev, "Enabling SR-IOV with %d VFs\n", total_vfs); dev->dev_vfs = kzalloc( - total_vfs * sizeof(*dev->dev_vfs), - GFP_KERNEL); + total_vfs * sizeof(*dev->dev_vfs), + GFP_KERNEL); if (NULL == dev->dev_vfs) { mlx4_err(dev, "Failed to allocate memory for VFs\n"); err = 0; @@@ -2333,14 -2371,14 +2334,14 @@@ atomic_inc(&pf_loading); err = pci_enable_sriov(pdev, total_vfs); if (err) { - mlx4_err(dev, "Failed to enable SR-IOV, continuing without SR-IOV (err = %d).\n", + mlx4_err(dev, "Failed to enable SR-IOV, continuing without SR-IOV (err = %d)\n", err); atomic_dec(&pf_loading); err = 0; } else { mlx4_warn(dev, "Running in master mode\n"); dev->flags |= MLX4_FLAG_SRIOV | - MLX4_FLAG_MASTER; + MLX4_FLAG_MASTER; dev->num_vfs = total_vfs; sriov_initialized = 1; } @@@ -2357,7 -2395,7 +2358,7 @@@ */ err = mlx4_reset(dev); if (err) { - mlx4_err(dev, "Failed to reset HCA, aborting.\n"); + mlx4_err(dev, "Failed to reset HCA, aborting\n"); goto err_rel_own; } } @@@ -2365,7 -2403,7 +2366,7 @@@ slave_start: err = mlx4_cmd_init(dev); if (err) { - mlx4_err(dev, "Failed to init command interface, aborting.\n"); + mlx4_err(dev, "Failed to init command interface, aborting\n"); goto err_sriov; }

@@@ -2379,7 -2417,8 +2380,7 @@@ dev->num_slaves = 0; err = mlx4_multi_func_init(dev); if (err) { - mlx4_err(dev, "Failed to init slave mfunc" - " interface, aborting.\n"); + mlx4_err(dev, "Failed to init slave mfunc interface, aborting\n"); goto err_cmd; } } @@@ -2411,7 -2450,8 +2412,7 @@@ unsigned sum = 0; err = mlx4_multi_func_init(dev); if (err) { - mlx4_err(dev, "Failed to init master mfunc" - "interface, aborting.\n"); + mlx4_err(dev, "Failed to init master mfunc interface, aborting\n"); goto err_close; } if (sriov_initialized) { @@@ -2422,7 -2462,10 +2423,7 @@@ if (ib_ports && (num_vfs_argc > 1 || probe_vfs_argc > 1)) { mlx4_err(dev, - "Invalid syntax of num_vfs/probe_vfs " - "with IB port. Single port VFs syntax" - " is only supported when all ports " - "are configured as ethernet\n"); + "Invalid syntax of num_vfs/probe_vfs with IB port - single port VFs syntax is only supported when all ports are configured as ethernet\n"); goto err_close; } for (i = 0; i < sizeof(nvfs)/sizeof(nvfs[0]); i++) { @@@ -2448,7 -2491,8 +2449,7 @@@ if ((mlx4_is_mfunc(dev)) && !(dev->flags & MLX4_FLAG_MSI_X)) { err = -ENOSYS; - mlx4_err(dev, "INTx is not supported in multi-function mode." - " aborting.\n"); + mlx4_err(dev, "INTx is not supported in multi-function mode, aborting\n"); goto err_free_eq; }

@@@ -2593,7 -2637,7 +2594,7 @@@ static void __mlx4_remove_one(struct pc /* in SRIOV it is not allowed to unload the pf's * driver while there are alive vf's */ if (mlx4_is_master(dev) && mlx4_how_many_lives_vf(dev)) - printk(KERN_ERR "Removing PF when there are assigned VF's !!!\n"); + pr_warn("Removing PF when there are assigned VF's !!!\n"); mlx4_stop_sense(dev); mlx4_unregister_device(dev);

@@@ -2764,36 -2808,33 +2765,36 @@@ static struct pci_driver mlx4_driver = static int __init mlx4_verify_params(void) { if ((log_num_mac < 0) || (log_num_mac > 7)) { - pr_warning("mlx4_core: bad num_mac: %d\n", log_num_mac); + pr_warn("mlx4_core: bad num_mac: %d\n", log_num_mac); return -1; }

if (log_num_vlan != 0) - pr_warning("mlx4_core: log_num_vlan - obsolete module param, using %d\n", - MLX4_LOG_NUM_VLANS); + pr_warn("mlx4_core: log_num_vlan - obsolete module param, using %d\n", + MLX4_LOG_NUM_VLANS); + + if (use_prio != 0) + pr_warn("mlx4_core: use_prio - obsolete module param, ignored\n");

if ((log_mtts_per_seg < 1) || (log_mtts_per_seg > 7)) { - pr_warning("mlx4_core: bad log_mtts_per_seg: %d\n", log_mtts_per_seg); + pr_warn("mlx4_core: bad log_mtts_per_seg: %d\n", + log_mtts_per_seg); return -1; }

/* Check if module param for ports type has legal combination */ if (port_type_array[0] == false && port_type_array[1] == true) { - printk(KERN_WARNING "Module parameter configuration ETH/IB is not supported. Switching to default configuration IB/IB\n"); + pr_warn("Module parameter configuration ETH/IB is not supported. Switching to default configuration IB/IB\n"); port_type_array[0] = true; }

if (mlx4_log_num_mgm_entry_size != -1 && (mlx4_log_num_mgm_entry_size < MLX4_MIN_MGM_LOG_ENTRY_SIZE || mlx4_log_num_mgm_entry_size > MLX4_MAX_MGM_LOG_ENTRY_SIZE)) { - pr_warning("mlx4_core: mlx4_log_num_mgm_entry_size (%d) not " - "in legal range (-1 or %d..%d)\n", - mlx4_log_num_mgm_entry_size, - MLX4_MIN_MGM_LOG_ENTRY_SIZE, - MLX4_MAX_MGM_LOG_ENTRY_SIZE); + pr_warn("mlx4_core: mlx4_log_num_mgm_entry_size (%d) not in legal range (-1 or %d..%d)\n", + mlx4_log_num_mgm_entry_size, + MLX4_MIN_MGM_LOG_ENTRY_SIZE, + MLX4_MAX_MGM_LOG_ENTRY_SIZE); return -1; }

diff --combined drivers/net/ethernet/mellanox/mlx4/mlx4.h index 9dd1b30,8e9eb02..4b416ed --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@@ -216,19 -216,18 +216,19 @@@ extern int mlx4_debug_level #define mlx4_debug_level (0) #endif /* CONFIG_MLX4_DEBUG */

-#define mlx4_dbg(mdev, format, arg...) \ +#define mlx4_dbg(mdev, format, ...) \ do { \ if (mlx4_debug_level) \ - dev_printk(KERN_DEBUG, &mdev->pdev->dev, format, ##arg); \ + dev_printk(KERN_DEBUG, &(mdev)->pdev->dev, format, \ + ##__VA_ARGS__); \ } while (0)

-#define mlx4_err(mdev, format, arg...) \ - dev_err(&mdev->pdev->dev, format, ##arg) -#define mlx4_info(mdev, format, arg...) \ - dev_info(&mdev->pdev->dev, format, ##arg) -#define mlx4_warn(mdev, format, arg...) \ - dev_warn(&mdev->pdev->dev, format, ##arg) +#define mlx4_err(mdev, format, ...) \ + dev_err(&(mdev)->pdev->dev, format, ##__VA_ARGS__) +#define mlx4_info(mdev, format, ...) \ + dev_info(&(mdev)->pdev->dev, format, ##__VA_ARGS__) +#define mlx4_warn(mdev, format, ...) \ + dev_warn(&(mdev)->pdev->dev, format, ##__VA_ARGS__)

extern int mlx4_log_num_mgm_entry_size; extern int log_mtts_per_seg; @@@ -696,6 -695,17 +696,17 @@@ struct mlx4_mac_table int max; };

+ #define MLX4_ROCE_GID_ENTRY_SIZE 16 + + struct mlx4_roce_gid_entry { + u8 raw[MLX4_ROCE_GID_ENTRY_SIZE]; + }; + + struct mlx4_roce_gid_table { + struct mlx4_roce_gid_entry roce_gids[MLX4_ROCE_MAX_GIDS]; + struct mutex mutex; + }; + #define MLX4_MAX_VLAN_NUM 128 #define MLX4_VLAN_TABLE_SIZE (MLX4_MAX_VLAN_NUM << 2)

@@@ -759,6 -769,7 +770,7 @@@ struct mlx4_port_info struct device_attribute port_mtu_attr; struct mlx4_mac_table mac_table; struct mlx4_vlan_table vlan_table; + struct mlx4_roce_gid_table gid_table; int base_qpn; };

@@@ -789,10 -800,6 +801,6 @@@ enum MLX4_USE_RR = 1, };

- struct mlx4_roce_gid_entry { - u8 raw[16]; - }; - struct mlx4_priv { struct mlx4_dev dev;

@@@ -840,7 -847,6 +848,6 @@@ int fs_hash_mode; u8 virt2phys_pkey[MLX4_MFUNC_MAX][MLX4_MAX_PORTS][MLX4_MAX_PORT_PKEYS]; __be64 slave_node_guids[MLX4_MFUNC_MAX]; - struct mlx4_roce_gid_entry roce_gids[MLX4_MAX_PORTS][MLX4_ROCE_MAX_GIDS];

atomic_t opreq_count; struct work_struct opreq_task; @@@ -1141,6 -1147,8 +1148,8 @@@ int mlx4_change_port_types(struct mlx4_

void mlx4_init_mac_table(struct mlx4_dev *dev, struct mlx4_mac_table *table); void mlx4_init_vlan_table(struct mlx4_dev *dev, struct mlx4_vlan_table *table); + void mlx4_init_roce_gid_table(struct mlx4_dev *dev, + struct mlx4_roce_gid_table *table); void __mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan); int __mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index);

@@@ -1150,6 -1158,7 +1159,7 @@@ int mlx4_get_slave_from_resource_id(str enum mlx4_resource resource_type, u64 resource_id, int *slave); void mlx4_delete_all_resources_for_slave(struct mlx4_dev *dev, int slave_id); + void mlx4_reset_roce_gids(struct mlx4_dev *dev, int slave); int mlx4_init_resource_tracker(struct mlx4_dev *dev);

void mlx4_free_resource_tracker(struct mlx4_dev *dev, diff --combined drivers/net/ethernet/mellanox/mlx4/port.c index 376f2f1,5ec6f20..7ab9717 --- a/drivers/net/ethernet/mellanox/mlx4/port.c +++ b/drivers/net/ethernet/mellanox/mlx4/port.c @@@ -75,6 -75,16 +75,16 @@@ void mlx4_init_vlan_table(struct mlx4_d table->total = 0; }

+ void mlx4_init_roce_gid_table(struct mlx4_dev *dev, + struct mlx4_roce_gid_table *table) + { + int i; + + mutex_init(&table->mutex); + for (i = 0; i < MLX4_ROCE_MAX_GIDS; i++) + memset(table->roce_gids[i].raw, 0, MLX4_ROCE_GID_ENTRY_SIZE); + } + static int validate_index(struct mlx4_dev *dev, struct mlx4_mac_table *table, int index) { @@@ -244,8 -254,8 +254,8 @@@ void __mlx4_unregister_mac(struct mlx4_ if (validate_index(dev, table, index)) goto out; if (--table->refs[index]) { - mlx4_dbg(dev, "Have more references for index %d," - "no need to modify mac table\n", index); + mlx4_dbg(dev, "Have more references for index %d, no need to modify mac table\n", + index); goto out; }

@@@ -443,8 -453,9 +453,8 @@@ void __mlx4_unregister_vlan(struct mlx4 }

if (--table->refs[index]) { - mlx4_dbg(dev, "Have %d more references for index %d," - "no need to modify vlan table\n", table->refs[index], - index); + mlx4_dbg(dev, "Have %d more references for index %d, no need to modify vlan table\n", + table->refs[index], index); goto out; } table->entries[index] = 0; @@@ -583,6 -594,84 +593,84 @@@ int mlx4_get_base_gid_ix(struct mlx4_de } EXPORT_SYMBOL_GPL(mlx4_get_base_gid_ix);

+ static int mlx4_reset_roce_port_gids(struct mlx4_dev *dev, int slave, + int port, struct mlx4_cmd_mailbox *mailbox) + { + struct mlx4_roce_gid_entry *gid_entry_mbox; + struct mlx4_priv *priv = mlx4_priv(dev); + int num_gids, base, offset; + int i, err; + + num_gids = mlx4_get_slave_num_gids(dev, slave, port); + base = mlx4_get_base_gid_ix(dev, slave, port); + + memset(mailbox->buf, 0, MLX4_MAILBOX_SIZE); + + mutex_lock(&(priv->port[port].gid_table.mutex)); + /* Zero-out gids belonging to that slave in the port GID table */ + for (i = 0, offset = base; i < num_gids; offset++, i++) + memcpy(priv->port[port].gid_table.roce_gids[offset].raw, + zgid_entry.raw, MLX4_ROCE_GID_ENTRY_SIZE); + + /* Now, copy roce port gids table to mailbox for passing to FW */ + gid_entry_mbox = (struct mlx4_roce_gid_entry *)mailbox->buf; + for (i = 0; i < MLX4_ROCE_MAX_GIDS; gid_entry_mbox++, i++) + memcpy(gid_entry_mbox->raw, + priv->port[port].gid_table.roce_gids[i].raw, + MLX4_ROCE_GID_ENTRY_SIZE); + + err = mlx4_cmd(dev, mailbox->dma, + ((u32)port) | (MLX4_SET_PORT_GID_TABLE << 8), 1, + MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B, + MLX4_CMD_NATIVE); + mutex_unlock(&(priv->port[port].gid_table.mutex)); + return err; + } + + + void mlx4_reset_roce_gids(struct mlx4_dev *dev, int slave) + { + struct mlx4_active_ports actv_ports; + struct mlx4_cmd_mailbox *mailbox; + int num_eth_ports, err; + int i; + + if (slave < 0 || slave > dev->num_vfs) + return; + + actv_ports = mlx4_get_active_ports(dev, slave); + + for (i = 0, num_eth_ports = 0; i < dev->caps.num_ports; i++) { + if (test_bit(i, actv_ports.ports)) { + if (dev->caps.port_type[i + 1] != MLX4_PORT_TYPE_ETH) + continue; + num_eth_ports++; + } + } + + if (!num_eth_ports) + return; + + /* have ETH ports. Alloc mailbox for SET_PORT command */ + mailbox = mlx4_alloc_cmd_mailbox(dev); + if (IS_ERR(mailbox)) + return; + + for (i = 0; i < dev->caps.num_ports; i++) { + if (test_bit(i, actv_ports.ports)) { + if (dev->caps.port_type[i + 1] != MLX4_PORT_TYPE_ETH) + continue; + err = mlx4_reset_roce_port_gids(dev, slave, i + 1, mailbox); + if (err) + mlx4_warn(dev, "Could not reset ETH port GID table for slave %d, port %d (%d)\n", + slave, i + 1, err); + } + } + + mlx4_free_cmd_mailbox(dev, mailbox); + return; + } + static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod, u8 op_mod, struct mlx4_cmd_mailbox *inbox) { @@@ -691,10 -780,12 +779,12 @@@ /* 2. Check that do not have duplicates in OTHER * entries in the port GID table */ + + mutex_lock(&(priv->port[port].gid_table.mutex)); for (i = 0; i < MLX4_ROCE_MAX_GIDS; i++) { if (i >= base && i < base + num_gids) continue; /* don't compare to slave's current gids */ - gid_entry_tbl = &priv->roce_gids[port - 1][i]; + gid_entry_tbl = &priv->port[port].gid_table.roce_gids[i]; if (!memcmp(gid_entry_tbl->raw, zgid_entry.raw, sizeof(zgid_entry))) continue; gid_entry_mbox = (struct mlx4_roce_gid_entry *)(inbox->buf); @@@ -705,8 -796,10 +795,9 @@@ if (!memcmp(gid_entry_mbox->raw, gid_entry_tbl->raw, sizeof(gid_entry_tbl->raw))) { /* found duplicate */ - mlx4_warn(dev, "requested gid entry for slave:%d " - "is a duplicate of gid at index %d\n", + mlx4_warn(dev, "requested gid entry for slave:%d is a duplicate of gid at index %d\n", slave, i); + mutex_unlock(&(priv->port[port].gid_table.mutex)); return -EINVAL; } } @@@ -715,16 -808,24 +806,24 @@@ /* insert slave GIDs with memcpy, starting at slave's base index */ gid_entry_mbox = (struct mlx4_roce_gid_entry *)(inbox->buf); for (i = 0, offset = base; i < num_gids; gid_entry_mbox++, offset++, i++) - memcpy(priv->roce_gids[port - 1][offset].raw, gid_entry_mbox->raw, 16); + memcpy(priv->port[port].gid_table.roce_gids[offset].raw, + gid_entry_mbox->raw, MLX4_ROCE_GID_ENTRY_SIZE);

/* Now, copy roce port gids table to current mailbox for passing to FW */ gid_entry_mbox = (struct mlx4_roce_gid_entry *)(inbox->buf); for (i = 0; i < MLX4_ROCE_MAX_GIDS; gid_entry_mbox++, i++) - memcpy(gid_entry_mbox->raw, priv->roce_gids[port - 1][i].raw, 16); - - break; + memcpy(gid_entry_mbox->raw, + priv->port[port].gid_table.roce_gids[i].raw, + MLX4_ROCE_GID_ENTRY_SIZE); + + err = mlx4_cmd(dev, inbox->dma, in_mod & 0xffff, op_mod, + MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B, + MLX4_CMD_NATIVE); + mutex_unlock(&(priv->port[port].gid_table.mutex)); + return err; } - return mlx4_cmd(dev, inbox->dma, in_mod, op_mod, + + return mlx4_cmd(dev, inbox->dma, in_mod & 0xffff, op_mod, MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE); } @@@ -1097,7 -1198,8 +1196,8 @@@ int mlx4_get_slave_from_roce_gid(struc num_vfs = bitmap_weight(slaves_pport.slaves, dev->num_vfs + 1) - 1;

for (i = 0; i < MLX4_ROCE_MAX_GIDS; i++) { - if (!memcmp(priv->roce_gids[port - 1][i].raw, gid, 16)) { + if (!memcmp(priv->port[port].gid_table.roce_gids[i].raw, gid, + MLX4_ROCE_GID_ENTRY_SIZE)) { found_ix = i; break; } @@@ -1185,7 -1287,8 +1285,8 @@@ int mlx4_get_roce_gid_from_slave(struc if (!mlx4_is_master(dev)) return -EINVAL;

- memcpy(gid, priv->roce_gids[port - 1][slave_id].raw, 16); + memcpy(gid, priv->port[port].gid_table.roce_gids[slave_id].raw, + MLX4_ROCE_GID_ENTRY_SIZE); return 0; } EXPORT_SYMBOL(mlx4_get_roce_gid_from_slave); diff --combined drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index dd821b3,f16e539..b6cddef --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@@ -586,6 -586,7 +586,7 @@@ void mlx4_free_resource_tracker(struct } /* free master's vlans */ i = dev->caps.function; + mlx4_reset_roce_gids(dev, i); mutex_lock(&priv->mfunc.master.res_tracker.slave_list[i].mutex); rem_slave_vlans(dev, i); mutex_unlock(&priv->mfunc.master.res_tracker.slave_list[i].mutex); @@@ -962,7 -963,7 +963,7 @@@ static struct res_common *alloc_tr(u64 ret = alloc_srq_tr(id); break; case RES_MAC: - printk(KERN_ERR "implementation missing\n"); + pr_err("implementation missing\n"); return NULL; case RES_COUNTER: ret = alloc_counter_tr(id); @@@ -1056,10 -1057,10 +1057,10 @@@ static int remove_mtt_ok(struct res_mt { if (res->com.state == RES_MTT_BUSY || atomic_read(&res->ref_count)) { - printk(KERN_DEBUG "%s-%d: state %s, ref_count %d\n", - __func__, __LINE__, - mtt_states_str(res->com.state), - atomic_read(&res->ref_count)); + pr_devel("%s-%d: state %s, ref_count %d\n", + __func__, __LINE__, + mtt_states_str(res->com.state), + atomic_read(&res->ref_count)); return -EBUSY; } else if (res->com.state != RES_MTT_ALLOCATED) return -EPERM; @@@ -3880,7 -3881,7 +3881,7 @@@ static int add_eth_header(struct mlx4_d } } if (!be_mac) { - pr_err("Failed adding eth header to FS rule, Can't find matching MAC for port %d .\n", + pr_err("Failed adding eth header to FS rule, Can't find matching MAC for port %d\n", port); return -EINVAL; } @@@ -3977,7 -3978,7 +3978,7 @@@ int mlx4_QP_FLOW_STEERING_ATTACH_wrappe qpn = be32_to_cpu(ctrl->qpn) & 0xffffff; err = get_res(dev, slave, qpn, RES_QP, &rqp); if (err) { - pr_err("Steering rule with qpn 0x%x rejected.\n", qpn); + pr_err("Steering rule with qpn 0x%x rejected\n", qpn); return err; } rule_header = (struct _rule_hw *)(ctrl + 1); @@@ -3995,7 -3996,7 +3996,7 @@@ case MLX4_NET_TRANS_RULE_ID_IPV4: case MLX4_NET_TRANS_RULE_ID_TCP: case MLX4_NET_TRANS_RULE_ID_UDP: - pr_warn("Can't attach FS rule without L2 headers, adding L2 header.\n"); + pr_warn("Can't attach FS rule without L2 headers, adding L2 header\n"); if (add_eth_header(dev, slave, inbox, rlist, header_id)) { err = -EINVAL; goto err_put; @@@ -4004,7 -4005,7 +4005,7 @@@ sizeof(struct mlx4_net_trans_rule_hw_eth) >> 2; break; default: - pr_err("Corrupted mailbox.\n"); + pr_err("Corrupted mailbox\n"); err = -EINVAL; goto err_put; } @@@ -4018,7 -4019,7 +4019,7 @@@

err = add_res_range(dev, slave, vhcr->out_param, 1, RES_FS_RULE, qpn); if (err) { - mlx4_err(dev, "Fail to add flow steering resources.\n "); + mlx4_err(dev, "Fail to add flow steering resources\n"); /* detach rule*/ mlx4_cmd(dev, vhcr->out_param, 0, 0, MLX4_QP_FLOW_STEERING_DETACH, MLX4_CMD_TIME_CLASS_A, @@@ -4056,7 -4057,7 +4057,7 @@@ int mlx4_QP_FLOW_STEERING_DETACH_wrappe

err = rem_res_range(dev, slave, vhcr->in_param, 1, RES_FS_RULE, 0); if (err) { - mlx4_err(dev, "Fail to remove flow steering resources.\n "); + mlx4_err(dev, "Fail to remove flow steering resources\n"); goto out; }

@@@ -4185,8 -4186,8 +4186,8 @@@ static void rem_slave_qps(struct mlx4_d

err = move_all_busy(dev, slave, RES_QP); if (err) - mlx4_warn(dev, "rem_slave_qps: Could not move all qps to busy" - "for slave %d\n", slave); + mlx4_warn(dev, "rem_slave_qps: Could not move all qps to busy for slave %d\n", + slave);

spin_lock_irq(mlx4_tlock(dev)); list_for_each_entry_safe(qp, tmp, qp_list, com.list) { @@@ -4224,8 -4225,10 +4225,8 @@@ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE); if (err) - mlx4_dbg(dev, "rem_slave_qps: failed" - " to move slave %d qpn %d to" - " reset\n", slave, - qp->local_qpn); + mlx4_dbg(dev, "rem_slave_qps: failed to move slave %d qpn %d to reset\n", + slave, qp->local_qpn); atomic_dec(&qp->rcq->ref_count); atomic_dec(&qp->scq->ref_count); atomic_dec(&qp->mtt->ref_count); @@@ -4259,8 -4262,8 +4260,8 @@@ static void rem_slave_srqs(struct mlx4_

err = move_all_busy(dev, slave, RES_SRQ); if (err) - mlx4_warn(dev, "rem_slave_srqs: Could not move all srqs to " - "busy for slave %d\n", slave); + mlx4_warn(dev, "rem_slave_srqs: Could not move all srqs - too busy for slave %d\n", + slave);

spin_lock_irq(mlx4_tlock(dev)); list_for_each_entry_safe(srq, tmp, srq_list, com.list) { @@@ -4290,7 -4293,9 +4291,7 @@@ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE); if (err) - mlx4_dbg(dev, "rem_slave_srqs: failed" - " to move slave %d srq %d to" - " SW ownership\n", + mlx4_dbg(dev, "rem_slave_srqs: failed to move slave %d srq %d to SW ownership\n", slave, srqn);

atomic_dec(&srq->mtt->ref_count); @@@ -4325,8 -4330,8 +4326,8 @@@ static void rem_slave_cqs(struct mlx4_d

err = move_all_busy(dev, slave, RES_CQ); if (err) - mlx4_warn(dev, "rem_slave_cqs: Could not move all cqs to " - "busy for slave %d\n", slave); + mlx4_warn(dev, "rem_slave_cqs: Could not move all cqs - too busy for slave %d\n", + slave);

spin_lock_irq(mlx4_tlock(dev)); list_for_each_entry_safe(cq, tmp, cq_list, com.list) { @@@ -4356,7 -4361,9 +4357,7 @@@ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE); if (err) - mlx4_dbg(dev, "rem_slave_cqs: failed" - " to move slave %d cq %d to" - " SW ownership\n", + mlx4_dbg(dev, "rem_slave_cqs: failed to move slave %d cq %d to SW ownership\n", slave, cqn); atomic_dec(&cq->mtt->ref_count); state = RES_CQ_ALLOCATED; @@@ -4388,8 -4395,8 +4389,8 @@@ static void rem_slave_mrs(struct mlx4_d

err = move_all_busy(dev, slave, RES_MPT); if (err) - mlx4_warn(dev, "rem_slave_mrs: Could not move all mpts to " - "busy for slave %d\n", slave); + mlx4_warn(dev, "rem_slave_mrs: Could not move all mpts - too busy for slave %d\n", + slave);

spin_lock_irq(mlx4_tlock(dev)); list_for_each_entry_safe(mpt, tmp, mpt_list, com.list) { @@@ -4424,7 -4431,9 +4425,7 @@@ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE); if (err) - mlx4_dbg(dev, "rem_slave_mrs: failed" - " to move slave %d mpt %d to" - " SW ownership\n", + mlx4_dbg(dev, "rem_slave_mrs: failed to move slave %d mpt %d to SW ownership\n", slave, mptn); if (mpt->mtt) atomic_dec(&mpt->mtt->ref_count); @@@ -4456,8 -4465,8 +4457,8 @@@ static void rem_slave_mtts(struct mlx4_

err = move_all_busy(dev, slave, RES_MTT); if (err) - mlx4_warn(dev, "rem_slave_mtts: Could not move all mtts to " - "busy for slave %d\n", slave); + mlx4_warn(dev, "rem_slave_mtts: Could not move all mtts - too busy for slave %d\n", + slave);

spin_lock_irq(mlx4_tlock(dev)); list_for_each_entry_safe(mtt, tmp, mtt_list, com.list) { @@@ -4559,8 -4568,8 +4560,8 @@@ static void rem_slave_eqs(struct mlx4_d

err = move_all_busy(dev, slave, RES_EQ); if (err) - mlx4_warn(dev, "rem_slave_eqs: Could not move all eqs to " - "busy for slave %d\n", slave); + mlx4_warn(dev, "rem_slave_eqs: Could not move all eqs - too busy for slave %d\n", + slave);

spin_lock_irq(mlx4_tlock(dev)); list_for_each_entry_safe(eq, tmp, eq_list, com.list) { @@@ -4592,8 -4601,9 +4593,8 @@@ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE); if (err) - mlx4_dbg(dev, "rem_slave_eqs: failed" - " to move slave %d eqs %d to" - " SW ownership\n", slave, eqn); + mlx4_dbg(dev, "rem_slave_eqs: failed to move slave %d eqs %d to SW ownership\n", + slave, eqn); mlx4_free_cmd_mailbox(dev, mailbox); atomic_dec(&eq->mtt->ref_count); state = RES_EQ_RESERVED; @@@ -4622,8 -4632,8 +4623,8 @@@ static void rem_slave_counters(struct m

err = move_all_busy(dev, slave, RES_COUNTER); if (err) - mlx4_warn(dev, "rem_slave_counters: Could not move all counters to " - "busy for slave %d\n", slave); + mlx4_warn(dev, "rem_slave_counters: Could not move all counters - too busy for slave %d\n", + slave);

spin_lock_irq(mlx4_tlock(dev)); list_for_each_entry_safe(counter, tmp, counter_list, com.list) { @@@ -4653,8 -4663,8 +4654,8 @@@ static void rem_slave_xrcdns(struct mlx

err = move_all_busy(dev, slave, RES_XRCD); if (err) - mlx4_warn(dev, "rem_slave_xrcdns: Could not move all xrcdns to " - "busy for slave %d\n", slave); + mlx4_warn(dev, "rem_slave_xrcdns: Could not move all xrcdns - too busy for slave %d\n", + slave);

spin_lock_irq(mlx4_tlock(dev)); list_for_each_entry_safe(xrcd, tmp, xrcdn_list, com.list) { @@@ -4672,7 -4682,7 +4673,7 @@@ void mlx4_delete_all_resources_for_slave(struct mlx4_dev *dev, int slave) { struct mlx4_priv *priv = mlx4_priv(dev); - + mlx4_reset_roce_gids(dev, slave); mutex_lock(&priv->mfunc.master.res_tracker.slave_list[slave].mutex); rem_slave_vlans(dev, slave); rem_slave_macs(dev, slave); @@@ -4799,8 -4809,10 +4800,8 @@@ void mlx4_vf_immed_vlan_work_handler(st 0, MLX4_CMD_UPDATE_QP, MLX4_CMD_TIME_CLASS_C, MLX4_CMD_NATIVE); if (err) { - mlx4_info(dev, "UPDATE_QP failed for slave %d, " - "port %d, qpn %d (%d)\n", - work->slave, port, qp->local_qpn, - err); + mlx4_info(dev, "UPDATE_QP failed for slave %d, port %d, qpn %d (%d)\n", + work->slave, port, qp->local_qpn, err); errors++; } } diff --combined drivers/net/ethernet/renesas/sh_eth.c index 6a94ede,08ed9a3..b19a323c --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@@ -307,6 -307,27 +307,27 @@@ static const u16 sh_eth_offset_fast_sh4 };

static const u16 sh_eth_offset_fast_sh3_sh2[SH_ETH_MAX_REGISTER_OFFSET] = { + [EDMR] = 0x0000, + [EDTRR] = 0x0004, + [EDRRR] = 0x0008, + [TDLAR] = 0x000c, + [RDLAR] = 0x0010, + [EESR] = 0x0014, + [EESIPR] = 0x0018, + [TRSCER] = 0x001c, + [RMFCR] = 0x0020, + [TFTR] = 0x0024, + [FDR] = 0x0028, + [RMCR] = 0x002c, + [EDOCR] = 0x0030, + [FCFTR] = 0x0034, + [RPADIR] = 0x0038, + [TRIMD] = 0x003c, + [RBWAR] = 0x0040, + [RDFAR] = 0x0044, + [TBRAR] = 0x004c, + [TDFAR] = 0x0050, + [ECMR] = 0x0160, [ECSR] = 0x0164, [ECSIPR] = 0x0168, @@@ -546,7 -567,6 +567,6 @@@ static struct sh_eth_cpu_data sh7757_da .register_type = SH_ETH_REG_FAST_SH4,

.eesipr_value = DMAC_M_RFRMER | DMAC_M_ECI | 0x003fffff, - .rmcr_value = RMCR_RNC,

.tx_check = EESR_FTC | EESR_CND | EESR_DLC | EESR_CD | EESR_RTO, .eesr_err_check = EESR_TWB | EESR_TABT | EESR_RABT | EESR_RFE | @@@ -624,7 -644,6 +644,6 @@@ static struct sh_eth_cpu_data sh7757_da EESR_RFE | EESR_RDE | EESR_RFRMER | EESR_TFE | EESR_TDE | EESR_ECI, .fdr_value = 0x0000072f, - .rmcr_value = RMCR_RNC,

.irq_flags = IRQF_SHARED, .apr = 1, @@@ -752,7 -771,6 +771,6 @@@ static struct sh_eth_cpu_data r8a7740_d EESR_RFE | EESR_RDE | EESR_RFRMER | EESR_TFE | EESR_TDE | EESR_ECI, .fdr_value = 0x0000070f, - .rmcr_value = RMCR_RNC,

.apr = 1, .mpr = 1, @@@ -784,7 -802,6 +802,6 @@@ static struct sh_eth_cpu_data r7s72100_ EESR_RFE | EESR_RDE | EESR_RFRMER | EESR_TFE | EESR_TDE | EESR_ECI, .fdr_value = 0x0000070f, - .rmcr_value = RMCR_RNC,

.no_psr = 1, .apr = 1, @@@ -833,9 -850,6 +850,6 @@@ static void sh_eth_set_default_cpu_data if (!cd->fdr_value) cd->fdr_value = DEFAULT_FDR_INIT;

- if (!cd->rmcr_value) - cd->rmcr_value = DEFAULT_RMCR_VALUE; - if (!cd->tx_check) cd->tx_check = DEFAULT_TX_CHECK;

@@@ -1287,8 -1301,8 +1301,8 @@@ static int sh_eth_dev_init(struct net_d sh_eth_write(ndev, mdp->cd->fdr_value, FDR); sh_eth_write(ndev, 0, TFTR);

- /* Frame recv control */ - sh_eth_write(ndev, mdp->cd->rmcr_value, RMCR); + /* Frame recv control (enable multiple-packets per rx irq) */ + sh_eth_write(ndev, RMCR_RNC, RMCR);

sh_eth_write(ndev, DESC_I_RINT8 | DESC_I_RINT5 | DESC_I_TINT2, TRSCER);

@@@ -2627,8 -2641,8 +2641,8 @@@ static int sh_mdio_init(struct sh_eth_p pdev->name, pdev->id);

/* PHY IRQ */ - mdp->mii_bus->irq = devm_kzalloc(dev, sizeof(int) * PHY_MAX_ADDR, - GFP_KERNEL); + mdp->mii_bus->irq = devm_kmalloc_array(dev, PHY_MAX_ADDR, sizeof(int), + GFP_KERNEL); if (!mdp->mii_bus->irq) { ret = -ENOMEM; goto out_free_bus; @@@ -2843,7 -2857,7 +2857,7 @@@ static int sh_eth_drv_probe(struct plat ndev->netdev_ops = &sh_eth_netdev_ops_tsu; else ndev->netdev_ops = &sh_eth_netdev_ops; - SET_ETHTOOL_OPS(ndev, &sh_eth_ethtool_ops); + ndev->ethtool_ops = &sh_eth_ethtool_ops; ndev->watchdog_timeo = TX_TIMEOUT;

/* debug message level */ diff --combined drivers/net/ethernet/ti/davinci_emac.c index f32d730,abc286d..35a139e --- a/drivers/net/ethernet/ti/davinci_emac.c +++ b/drivers/net/ethernet/ti/davinci_emac.c @@@ -1567,7 -1567,6 +1567,6 @@@ static int emac_dev_open(struct net_dev while ((res = platform_get_resource(priv->pdev, IORESOURCE_IRQ, res_num))) { for (irq_num = res->start; irq_num <= res->end; irq_num++) { - dev_err(emac_dev, "Request IRQ %d\n", irq_num); if (request_irq(irq_num, emac_irq, 0, ndev->name, ndev)) { dev_err(emac_dev, @@@ -1865,6 -1864,7 +1864,6 @@@ static int davinci_emac_probe(struct pl struct emac_priv *priv; unsigned long hw_ram_addr; struct emac_platform_data *pdata; - struct device *emac_dev; struct cpdma_params dma_params; struct clk *emac_clk; unsigned long emac_bus_frequency; @@@ -1910,6 -1910,7 +1909,6 @@@ priv->coal_intvl = 0; priv->bus_freq_mhz = (u32)(emac_bus_frequency / 1000000);

- emac_dev = &ndev->dev; /* Get EMAC platform data */ res = platform_get_resource(pdev, IORESOURCE_MEM, 0); priv->emac_base_phys = res->start + pdata->ctrl_reg_offset; @@@ -1928,7 -1929,7 +1927,7 @@@ hw_ram_addr = (u32 __force)res->start + pdata->ctrl_ram_offset;

memset(&dma_params, 0, sizeof(dma_params)); - dma_params.dev = emac_dev; + dma_params.dev = &pdev->dev; dma_params.dmaregs = priv->emac_base; dma_params.rxthresh = priv->emac_base + 0x120; dma_params.rxfree = priv->emac_base + 0x140; @@@ -1978,7 -1979,7 +1977,7 @@@ }

ndev->netdev_ops = &emac_netdev_ops; - SET_ETHTOOL_OPS(ndev, &ethtool_ops); + ndev->ethtool_ops = &ethtool_ops; netif_napi_add(ndev, &priv->napi, emac_poll, EMAC_POLL_WEIGHT);

/* register the network device */ @@@ -1992,7 -1993,7 +1991,7 @@@

if (netif_msg_probe(priv)) { - dev_notice(emac_dev, "DaVinci EMAC Probe found device "\ + dev_notice(&pdev->dev, "DaVinci EMAC Probe found device " "(regs: %p, irq: %d)\n", (void *)priv->emac_base_phys, ndev->irq); } diff --combined drivers/net/team/team.c index 9a9ce8d,ce4989b..b4958c7 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@@ -968,7 -968,7 +968,7 @@@ static void team_port_disable(struct te static void __team_compute_features(struct team *team) { struct team_port *port; - u32 vlan_features = TEAM_VLAN_FEATURES; + u32 vlan_features = TEAM_VLAN_FEATURES & NETIF_F_ALL_FOR_ALL; unsigned short max_hard_header_len = ETH_HLEN; unsigned int flags, dst_release_flag = IFF_XMIT_DST_RELEASE;

@@@ -1724,6 -1724,7 +1724,7 @@@ static int team_change_mtu(struct net_d * to traverse list in reverse under rcu_read_lock */ mutex_lock(&team->lock); + team->port_mtu_change_allowed = true; list_for_each_entry(port, &team->port_list, list) { err = dev_set_mtu(port->dev, new_mtu); if (err) { @@@ -1732,6 -1733,7 +1733,7 @@@ goto unwind; } } + team->port_mtu_change_allowed = false; mutex_unlock(&team->lock);

dev->mtu = new_mtu; @@@ -1741,6 -1743,7 +1743,7 @@@ unwind: list_for_each_entry_continue_reverse(port, &team->port_list, list) dev_set_mtu(port->dev, dev->mtu); + team->port_mtu_change_allowed = false; mutex_unlock(&team->lock);

return err; @@@ -2851,7 -2854,9 +2854,9 @@@ static int team_device_event(struct not break; case NETDEV_PRECHANGEMTU: /* Forbid to change mtu of underlaying device */ - return NOTIFY_BAD; + if (!port->team->port_mtu_change_allowed) + return NOTIFY_BAD; + break; case NETDEV_PRE_TYPE_CHANGE: /* Forbid to change type of underlaying device */ return NOTIFY_BAD; diff --combined drivers/net/usb/ipheth.c index f725707,973275f..76465b1 --- a/drivers/net/usb/ipheth.c +++ b/drivers/net/usb/ipheth.c @@@ -59,6 -59,8 +59,8 @@@ #define USB_PRODUCT_IPHONE_3GS 0x1294 #define USB_PRODUCT_IPHONE_4 0x1297 #define USB_PRODUCT_IPAD 0x129a + #define USB_PRODUCT_IPAD_2 0x12a2 + #define USB_PRODUCT_IPAD_3 0x12a6 #define USB_PRODUCT_IPAD_MINI 0x12ab #define USB_PRODUCT_IPHONE_4_VZW 0x129c #define USB_PRODUCT_IPHONE_4S 0x12a0 @@@ -105,6 -107,14 +107,14 @@@ static struct usb_device_id ipheth_tabl { USB_DEVICE_AND_INTERFACE_INFO( USB_VENDOR_APPLE, USB_PRODUCT_IPAD, IPHETH_USBINTF_CLASS, IPHETH_USBINTF_SUBCLASS, + IPHETH_USBINTF_PROTO) }, + { USB_DEVICE_AND_INTERFACE_INFO( + USB_VENDOR_APPLE, USB_PRODUCT_IPAD_2, + IPHETH_USBINTF_CLASS, IPHETH_USBINTF_SUBCLASS, + IPHETH_USBINTF_PROTO) }, + { USB_DEVICE_AND_INTERFACE_INFO( + USB_VENDOR_APPLE, USB_PRODUCT_IPAD_3, + IPHETH_USBINTF_CLASS, IPHETH_USBINTF_SUBCLASS, IPHETH_USBINTF_PROTO) }, { USB_DEVICE_AND_INTERFACE_INFO( USB_VENDOR_APPLE, USB_PRODUCT_IPAD_MINI, @@@ -524,7 -534,7 +534,7 @@@ static int ipheth_probe(struct usb_inte usb_set_intfdata(intf, dev);

SET_NETDEV_DEV(netdev, &intf->dev); - SET_ETHTOOL_OPS(netdev, &ops); + netdev->ethtool_ops = &ops;

retval = register_netdev(netdev); if (retval) { diff --combined include/linux/netlink.h index 7a28115,034cda7..9e572da --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@@ -16,9 -16,10 +16,10 @@@ static inline struct nlmsghdr *nlmsg_hd }

enum netlink_skb_flags { - NETLINK_SKB_MMAPED = 0x1, /* Packet data is mmaped */ - NETLINK_SKB_TX = 0x2, /* Packet was sent by userspace */ - NETLINK_SKB_DELIVERED = 0x4, /* Packet was delivered */ + NETLINK_SKB_MMAPED = 0x1, /* Packet data is mmaped */ + NETLINK_SKB_TX = 0x2, /* Packet was sent by userspace */ + NETLINK_SKB_DELIVERED = 0x4, /* Packet was delivered */ + NETLINK_SKB_DST = 0x8, /* Dst set in sendto or sendmsg */ };

struct netlink_skb_parms { @@@ -45,8 -46,7 +46,8 @@@ struct netlink_kernel_cfg unsigned int flags; void (*input)(struct sk_buff *skb); struct mutex *cb_mutex; - void (*bind)(int group); + int (*bind)(int group); + void (*unbind)(int group); bool (*compare)(struct net *net, struct sock *sk); };

diff --combined include/net/inetpeer.h index 823ec7b,058271b..01d590e --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@@ -41,13 -41,14 +41,13 @@@ struct inet_peer struct rcu_head gc_rcu; }; /* - * Once inet_peer is queued for deletion (refcnt == -1), following fields - * are not available: rid, ip_id_count + * Once inet_peer is queued for deletion (refcnt == -1), following field + * is not available: rid * We can share memory with rcu_head to help keep inet_peer small. */ union { struct { atomic_t rid; /* Frag reception counter */ - atomic_t ip_id_count; /* IP ID for the next packet */ }; struct rcu_head rcu; struct inet_peer *gc_next; @@@ -164,12 -165,21 +164,11 @@@ bool inet_peer_xrlim_allow(struct inet_ void inetpeer_invalidate_tree(struct inet_peer_base *);

/* - * temporary check to make sure we dont access rid, ip_id_count, tcp_ts, + * temporary check to make sure we dont access rid, tcp_ts, * tcp_ts_stamp if no refcount is taken on inet_peer */ static inline void inet_peer_refcheck(const struct inet_peer *p) { WARN_ON_ONCE(atomic_read(&p->refcnt) <= 0); } -- - -/* can be called with or without local BH being disabled */ -static inline int inet_getid(struct inet_peer *p, int more) -{ - more++; - inet_peer_refcheck(p); - return atomic_add_return(more, &p->ip_id_count) - more; -} - #endif /* _NET_INETPEER_H */ diff --combined include/uapi/linux/audit.h index b21ea45,4c31a36..cf67147 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@@ -357,7 -357,7 +357,7 @@@ enum #define AUDIT_ARCH_MIPS64N32 (EM_MIPS|__AUDIT_ARCH_64BIT|\ __AUDIT_ARCH_CONVENTION_MIPS64_N32) #define AUDIT_ARCH_MIPSEL64 (EM_MIPS|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE) - #define AUDIT_ARCH_MIPSEL64N32 (EM_MIPS|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE\ + #define AUDIT_ARCH_MIPSEL64N32 (EM_MIPS|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE|\ __AUDIT_ARCH_CONVENTION_MIPS64_N32) #define AUDIT_ARCH_OPENRISC (EM_OPENRISC) #define AUDIT_ARCH_PARISC (EM_PARISC) @@@ -385,14 -385,6 +385,14 @@@ */ #define AUDIT_MESSAGE_TEXT_MAX 8560

+/* Multicast Netlink socket groups (default up to 32) */ +enum audit_nlgrps { + AUDIT_NLGRP_NONE, /* Group 0 not used */ + AUDIT_NLGRP_READLOG, /* "best effort" read only socket */ + __AUDIT_NLGRP_MAX +}; +#define AUDIT_NLGRP_MAX (__AUDIT_NLGRP_MAX - 1) + struct audit_status { __u32 mask; /* Bit mask for valid entries */ __u32 enabled; /* 1 = enabled, 0 = disabled */ diff --combined net/bridge/br_fdb.c index 2c45c06,474d36f..b524c36 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@@ -85,58 -85,8 +85,58 @@@ static void fdb_rcu_free(struct rcu_hea kmem_cache_free(br_fdb_cache, ent); }

+/* When a static FDB entry is added, the mac address from the entry is + * added to the bridge private HW address list and all required ports + * are then updated with the new information. + * Called under RTNL. + */ +static void fdb_add_hw(struct net_bridge *br, const unsigned char *addr) +{ + int err; + struct net_bridge_port *p, *tmp; + + ASSERT_RTNL(); + + list_for_each_entry(p, &br->port_list, list) { + if (!br_promisc_port(p)) { + err = dev_uc_add(p->dev, addr); + if (err) + goto undo; + } + } + + return; +undo: + list_for_each_entry(tmp, &br->port_list, list) { + if (tmp == p) + break; + if (!br_promisc_port(tmp)) + dev_uc_del(tmp->dev, addr); + } +} + +/* When a static FDB entry is deleted, the HW address from that entry is + * also removed from the bridge private HW address list and updates all + * the ports with needed information. + * Called under RTNL. + */ +static void fdb_del_hw(struct net_bridge *br, const unsigned char *addr) +{ + struct net_bridge_port *p; + + ASSERT_RTNL(); + + list_for_each_entry(p, &br->port_list, list) { + if (!br_promisc_port(p)) + dev_uc_del(p->dev, addr); + } +} + static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f) { + if (f->is_static) + fdb_del_hw(br, f->addr.addr); + hlist_del_rcu(&f->hlist); fdb_notify(br, f, RTM_DELNEIGH); call_rcu(&f->rcu, fdb_rcu_free); @@@ -516,7 -466,6 +516,7 @@@ static int fdb_insert(struct net_bridg return -ENOMEM;

fdb->is_local = fdb->is_static = 1; + fdb_add_hw(br, addr); fdb_notify(br, fdb, RTM_NEWNEIGH); return 0; } @@@ -538,6 -487,7 +538,7 @@@ void br_fdb_update(struct net_bridge *b { struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)]; struct net_bridge_fdb_entry *fdb; + bool fdb_modified = false;

/* some users want to always flood. */ if (hold_time(br) == 0) @@@ -558,10 -508,15 +559,15 @@@ source->dev->name); } else { /* fastpath: update of existing entry */ - fdb->dst = source; + if (unlikely(source != fdb->dst)) { + fdb->dst = source; + fdb_modified = true; + } fdb->updated = jiffies; if (unlikely(added_by_user)) fdb->added_by_user = 1; + if (unlikely(fdb_modified)) + fdb_notify(br, fdb, RTM_NEWNEIGH); } } else { spin_lock(&br->hash_lock); @@@ -616,8 -571,6 +622,8 @@@ static int fdb_fill_info(struct sk_buf

if (nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->addr)) goto nla_put_failure; + if (nla_put_u32(skb, NDA_MASTER, br->dev->ifindex)) + goto nla_put_failure; ci.ndm_used = jiffies_to_clock_t(now - fdb->used); ci.ndm_confirmed = 0; ci.ndm_updated = jiffies_to_clock_t(now - fdb->updated); @@@ -639,7 -592,6 +645,7 @@@ static inline size_t fdb_nlmsg_size(voi { return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN) /* NDA_LLADDR */ + + nla_total_size(sizeof(u32)) /* NDA_MASTER */ + nla_total_size(sizeof(u16)) /* NDA_VLAN */ + nla_total_size(sizeof(struct nda_cacheinfo)); } @@@ -732,25 -684,13 +738,25 @@@ static int fdb_add_entry(struct net_bri }

if (fdb_to_nud(fdb) != state) { - if (state & NUD_PERMANENT) - fdb->is_local = fdb->is_static = 1; - else if (state & NUD_NOARP) { + if (state & NUD_PERMANENT) { + fdb->is_local = 1; + if (!fdb->is_static) { + fdb->is_static = 1; + fdb_add_hw(br, addr); + } + } else if (state & NUD_NOARP) { fdb->is_local = 0; - fdb->is_static = 1; - } else - fdb->is_local = fdb->is_static = 0; + if (!fdb->is_static) { + fdb->is_static = 1; + fdb_add_hw(br, addr); + } + } else { + fdb->is_local = 0; + if (fdb->is_static) { + fdb->is_static = 0; + fdb_del_hw(br, addr); + } + }

modified = true; } @@@ -940,59 -880,3 +946,59 @@@ int br_fdb_delete(struct ndmsg *ndm, st out: return err; } + +int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p) +{ + struct net_bridge_fdb_entry *fdb, *tmp; + int i; + int err; + + ASSERT_RTNL(); + + for (i = 0; i < BR_HASH_SIZE; i++) { + hlist_for_each_entry(fdb, &br->hash[i], hlist) { + /* We only care for static entries */ + if (!fdb->is_static) + continue; + + err = dev_uc_add(p->dev, fdb->addr.addr); + if (err) + goto rollback; + } + } + return 0; + +rollback: + for (i = 0; i < BR_HASH_SIZE; i++) { + hlist_for_each_entry(tmp, &br->hash[i], hlist) { + /* If we reached the fdb that failed, we can stop */ + if (tmp == fdb) + break; + + /* We only care for static entries */ + if (!tmp->is_static) + continue; + + dev_uc_del(p->dev, tmp->addr.addr); + } + } + return err; +} + +void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p) +{ + struct net_bridge_fdb_entry *fdb; + int i; + + ASSERT_RTNL(); + + for (i = 0; i < BR_HASH_SIZE; i++) { + hlist_for_each_entry_rcu(fdb, &br->hash[i], hlist) { + /* We only care for static entries */ + if (!fdb->is_static) + continue; + + dev_uc_del(p->dev, fdb->addr.addr); + } + } +} diff --combined net/bridge/br_private.h index 53d6e32,59d3a85..bc17210 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@@ -174,8 -174,6 +174,8 @@@ struct net_bridge_por #define BR_ADMIN_COST 0x00000010 #define BR_LEARNING 0x00000020 #define BR_FLOOD 0x00000040 +#define BR_AUTO_MASK (BR_FLOOD | BR_LEARNING) +#define BR_PROMISC 0x00000080

#ifdef CONFIG_BRIDGE_IGMP_SNOOPING struct bridge_mcast_query ip4_query; @@@ -200,9 -198,6 +200,9 @@@ #endif };

+#define br_auto_port(p) ((p)->flags & BR_AUTO_MASK) +#define br_promisc_port(p) ((p)->flags & BR_PROMISC) + #define br_port_exists(dev) (dev->priv_flags & IFF_BRIDGE_PORT)

static inline struct net_bridge_port *br_port_get_rcu(const struct net_device *dev) @@@ -295,7 -290,6 +295,7 @@@ struct net_bridg struct timer_list topology_change_timer; struct timer_list gc_timer; struct kobject *ifobj; + u32 auto_cnt; #ifdef CONFIG_BRIDGE_VLAN_FILTERING u8 vlan_enabled; struct net_port_vlans __rcu *vlan_info; @@@ -333,6 -327,8 +333,6 @@@ struct br_input_skb_cb #define br_debug(br, format, args...) \ pr_debug("%s: " format, (br)->dev->name, ##args)

-extern struct notifier_block br_device_notifier; - /* called under bridge lock */ static inline int br_is_root_bridge(const struct net_bridge *br) { @@@ -399,8 -395,6 +399,8 @@@ int br_fdb_add(struct ndmsg *nlh, struc const unsigned char *addr, u16 nlh_flags); int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, int idx); +int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p); +void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p);

/* br_forward.c */ void br_deliver(const struct net_bridge_port *to, struct sk_buff *skb); @@@ -421,8 -415,6 +421,8 @@@ int br_del_if(struct net_bridge *br, st int br_min_mtu(const struct net_bridge *br); netdev_features_t br_features_recompute(struct net_bridge *br, netdev_features_t features); +void br_port_flags_change(struct net_bridge_port *port, unsigned long mask); +void br_manage_promisc(struct net_bridge *br);

/* br_input.c */ int br_handle_frame_finish(struct sk_buff *skb); @@@ -589,6 -581,7 +589,7 @@@ bool br_allowed_ingress(struct net_brid struct sk_buff *skb, u16 *vid); bool br_allowed_egress(struct net_bridge *br, const struct net_port_vlans *v, const struct sk_buff *skb); + bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid); struct sk_buff *br_handle_vlan(struct net_bridge *br, const struct net_port_vlans *v, struct sk_buff *skb); @@@ -640,10 -633,6 +641,10 @@@ static inline u16 br_get_pvid(const str return v->pvid ?: VLAN_N_VID; }

+static inline int br_vlan_enabled(struct net_bridge *br) +{ + return br->vlan_enabled; +} #else static inline bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, @@@ -660,6 -649,12 +661,12 @@@ static inline bool br_allowed_egress(st return true; }

+ static inline bool br_should_learn(struct net_bridge_port *p, + struct sk_buff *skb, u16 *vid) + { + return true; + } + static inline struct sk_buff *br_handle_vlan(struct net_bridge *br, const struct net_port_vlans *v, struct sk_buff *skb) @@@ -724,11 -719,6 +731,11 @@@ static inline u16 br_get_pvid(const str { return VLAN_N_VID; /* Returns invalid vid */ } + +static inline int br_vlan_enabled(struct net_bridge *br) +{ + return 0; +} #endif

/* br_netfilter.c */ diff --combined net/bridge/br_vlan.c index 24c5cc5,5fee2fe..fcc9539 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@@ -241,6 -241,34 +241,34 @@@ bool br_allowed_egress(struct net_bridg return false; }

+ /* Called under RCU */ + bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid) + { + struct net_bridge *br = p->br; + struct net_port_vlans *v; + + if (!br->vlan_enabled) + return true; + + v = rcu_dereference(p->vlan_info); + if (!v) + return false; + + br_vlan_get_tag(skb, vid); + if (!*vid) { + *vid = br_get_pvid(v); + if (*vid == VLAN_N_VID) + return false; + + return true; + } + + if (test_bit(*vid, v->vlan_bitmap)) + return true; + + return false; + } + /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. */ @@@ -332,7 -360,6 +360,7 @@@ int br_vlan_filter_toggle(struct net_br goto unlock;

br->vlan_enabled = val; + br_manage_promisc(br);

unlock: rtnl_unlock(); diff --combined net/core/dev.c index 1ba2cfe,fb8b054..5367bfb --- a/net/core/dev.c +++ b/net/core/dev.c @@@ -1661,29 -1661,6 +1661,29 @@@ bool is_skb_forwardable(struct net_devi } EXPORT_SYMBOL_GPL(is_skb_forwardable);

+int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb) +{ + if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { + if (skb_copy_ubufs(skb, GFP_ATOMIC)) { + atomic_long_inc(&dev->rx_dropped); + kfree_skb(skb); + return NET_RX_DROP; + } + } + + if (unlikely(!is_skb_forwardable(dev, skb))) { + atomic_long_inc(&dev->rx_dropped); + kfree_skb(skb); + return NET_RX_DROP; + } + + skb_scrub_packet(skb, true); + skb->protocol = eth_type_trans(skb, dev); + + return 0; +} +EXPORT_SYMBOL_GPL(__dev_forward_skb); + /** * dev_forward_skb - loopback an skb to another netif * @@@ -1704,7 -1681,24 +1704,7 @@@ */ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) { - if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { - if (skb_copy_ubufs(skb, GFP_ATOMIC)) { - atomic_long_inc(&dev->rx_dropped); - kfree_skb(skb); - return NET_RX_DROP; - } - } - - if (unlikely(!is_skb_forwardable(dev, skb))) { - atomic_long_inc(&dev->rx_dropped); - kfree_skb(skb); - return NET_RX_DROP; - } - - skb_scrub_packet(skb, true); - skb->protocol = eth_type_trans(skb, dev); - - return netif_rx_internal(skb); + return __dev_forward_skb(dev, skb) ?: netif_rx_internal(skb); } EXPORT_SYMBOL_GPL(dev_forward_skb);

@@@ -2289,8 -2283,8 +2289,8 @@@ EXPORT_SYMBOL(skb_checksum_help)

__be16 skb_network_protocol(struct sk_buff *skb, int *depth) { + unsigned int vlan_depth = skb->mac_len; __be16 type = skb->protocol; - int vlan_depth = skb->mac_len;

/* Tunnel gso handlers can set protocol to ethernet. */ if (type == htons(ETH_P_TEB)) { @@@ -2303,15 -2297,30 +2303,30 @@@ type = eth->h_proto; }

- while (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) { - struct vlan_hdr *vh; - - if (unlikely(!pskb_may_pull(skb, vlan_depth + VLAN_HLEN))) - return 0; - - vh = (struct vlan_hdr *)(skb->data + vlan_depth); - type = vh->h_vlan_encapsulated_proto; - vlan_depth += VLAN_HLEN; + /* if skb->protocol is 802.1Q/AD then the header should already be + * present at mac_len - VLAN_HLEN (if mac_len > 0), or at + * ETH_HLEN otherwise + */ + if (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) { + if (vlan_depth) { + if (unlikely(WARN_ON(vlan_depth < VLAN_HLEN))) + return 0; + vlan_depth -= VLAN_HLEN; + } else { + vlan_depth = ETH_HLEN; + } + do { + struct vlan_hdr *vh; + + if (unlikely(!pskb_may_pull(skb, + vlan_depth + VLAN_HLEN))) + return 0; + + vh = (struct vlan_hdr *)(skb->data + vlan_depth); + type = vh->h_vlan_encapsulated_proto; + vlan_depth += VLAN_HLEN; + } while (type == htons(ETH_P_8021Q) || + type == htons(ETH_P_8021AD)); }

*depth = vlan_depth; @@@ -5680,6 -5689,10 +5695,6 @@@ static void rollback_registered_many(st */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev);

- if (!dev->rtnl_link_ops || - dev->rtnl_link_state == RTNL_LINK_INITIALIZED) - rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL); - /* * Flush the unicast and multicast chains */ @@@ -5689,10 -5702,6 +5704,10 @@@ if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev);

+ if (!dev->rtnl_link_ops || + dev->rtnl_link_state == RTNL_LINK_INITIALIZED) + rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL); + /* Notifier chain MUST detach us all upper devices. */ WARN_ON(netdev_has_any_upper_dev(dev));

@@@ -6503,6 -6512,11 +6518,6 @@@ free_all

free_pcpu: free_percpu(dev->pcpu_refcnt); - netif_free_tx_queues(dev); -#ifdef CONFIG_SYSFS - kfree(dev->_rx); -#endif - free_dev: netdev_freemem(dev); return NULL; diff --combined net/core/filter.c index 842f839,4aec7b9..9de0c25 --- a/net/core/filter.c +++ b/net/core/filter.c @@@ -45,27 -45,6 +45,27 @@@ #include <linux/seccomp.h> #include <linux/if_vlan.h>

+/* Registers */ +#define BPF_R0 regs[BPF_REG_0] +#define BPF_R1 regs[BPF_REG_1] +#define BPF_R2 regs[BPF_REG_2] +#define BPF_R3 regs[BPF_REG_3] +#define BPF_R4 regs[BPF_REG_4] +#define BPF_R5 regs[BPF_REG_5] +#define BPF_R6 regs[BPF_REG_6] +#define BPF_R7 regs[BPF_REG_7] +#define BPF_R8 regs[BPF_REG_8] +#define BPF_R9 regs[BPF_REG_9] +#define BPF_R10 regs[BPF_REG_10] + +/* Named registers */ +#define A regs[insn->a_reg] +#define X regs[insn->x_reg] +#define FP regs[BPF_REG_FP] +#define ARG1 regs[BPF_REG_ARG1] +#define CTX regs[BPF_REG_CTX] +#define K insn->imm + /* No hurry in this branch * * Exported for the bpf jit load helper. @@@ -78,9 -57,9 +78,9 @@@ void *bpf_internal_load_pointer_neg_hel ptr = skb_network_header(skb) + k - SKF_NET_OFF; else if (k >= SKF_LL_OFF) ptr = skb_mac_header(skb) + k - SKF_LL_OFF; - if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb)) return ptr; + return NULL; }

@@@ -89,7 -68,6 +89,7 @@@ static inline void *load_pointer(const { if (k >= 0) return skb_header_pointer(skb, k, size, buffer); + return bpf_internal_load_pointer_neg_helper(skb, k, size); }

@@@ -144,6 -122,13 +144,6 @@@ noinline u64 __bpf_call_base(u64 r1, u6 return 0; }

-/* Register mappings for user programs. */ -#define A_REG 0 -#define X_REG 7 -#define TMP_REG 8 -#define ARG2_REG 2 -#define ARG3_REG 3 - /** * __sk_run_filter - run a filter on a given context * @ctx: buffer to run the filter on @@@ -153,213 -138,212 +153,213 @@@ * keep, 0 for none. @ctx is the data we are operating on, @insn is the * array of filter instructions. */ -unsigned int __sk_run_filter(void *ctx, const struct sock_filter_int *insn) +static unsigned int __sk_run_filter(void *ctx, const struct sock_filter_int *insn) { u64 stack[MAX_BPF_STACK / sizeof(u64)]; u64 regs[MAX_BPF_REG], tmp; static const void *jumptable[256] = { [0 ... 255] = &&default_label, /* Now overwrite non-defaults ... */ -#define DL(A, B, C) [A|B|C] = &&A##_##B##_##C - DL(BPF_ALU, BPF_ADD, BPF_X), - DL(BPF_ALU, BPF_ADD, BPF_K), - DL(BPF_ALU, BPF_SUB, BPF_X), - DL(BPF_ALU, BPF_SUB, BPF_K), - DL(BPF_ALU, BPF_AND, BPF_X), - DL(BPF_ALU, BPF_AND, BPF_K), - DL(BPF_ALU, BPF_OR, BPF_X), - DL(BPF_ALU, BPF_OR, BPF_K), - DL(BPF_ALU, BPF_LSH, BPF_X), - DL(BPF_ALU, BPF_LSH, BPF_K), - DL(BPF_ALU, BPF_RSH, BPF_X), - DL(BPF_ALU, BPF_RSH, BPF_K), - DL(BPF_ALU, BPF_XOR, BPF_X), - DL(BPF_ALU, BPF_XOR, BPF_K), - DL(BPF_ALU, BPF_MUL, BPF_X), - DL(BPF_ALU, BPF_MUL, BPF_K), - DL(BPF_ALU, BPF_MOV, BPF_X), - DL(BPF_ALU, BPF_MOV, BPF_K), - DL(BPF_ALU, BPF_DIV, BPF_X), - DL(BPF_ALU, BPF_DIV, BPF_K), - DL(BPF_ALU, BPF_MOD, BPF_X), - DL(BPF_ALU, BPF_MOD, BPF_K), - DL(BPF_ALU, BPF_NEG, 0), - DL(BPF_ALU, BPF_END, BPF_TO_BE), - DL(BPF_ALU, BPF_END, BPF_TO_LE), - DL(BPF_ALU64, BPF_ADD, BPF_X), - DL(BPF_ALU64, BPF_ADD, BPF_K), - DL(BPF_ALU64, BPF_SUB, BPF_X), - DL(BPF_ALU64, BPF_SUB, BPF_K), - DL(BPF_ALU64, BPF_AND, BPF_X), - DL(BPF_ALU64, BPF_AND, BPF_K), - DL(BPF_ALU64, BPF_OR, BPF_X), - DL(BPF_ALU64, BPF_OR, BPF_K), - DL(BPF_ALU64, BPF_LSH, BPF_X), - DL(BPF_ALU64, BPF_LSH, BPF_K), - DL(BPF_ALU64, BPF_RSH, BPF_X), - DL(BPF_ALU64, BPF_RSH, BPF_K), - DL(BPF_ALU64, BPF_XOR, BPF_X), - DL(BPF_ALU64, BPF_XOR, BPF_K), - DL(BPF_ALU64, BPF_MUL, BPF_X), - DL(BPF_ALU64, BPF_MUL, BPF_K), - DL(BPF_ALU64, BPF_MOV, BPF_X), - DL(BPF_ALU64, BPF_MOV, BPF_K), - DL(BPF_ALU64, BPF_ARSH, BPF_X), - DL(BPF_ALU64, BPF_ARSH, BPF_K), - DL(BPF_ALU64, BPF_DIV, BPF_X), - DL(BPF_ALU64, BPF_DIV, BPF_K), - DL(BPF_ALU64, BPF_MOD, BPF_X), - DL(BPF_ALU64, BPF_MOD, BPF_K), - DL(BPF_ALU64, BPF_NEG, 0), - DL(BPF_JMP, BPF_CALL, 0), - DL(BPF_JMP, BPF_JA, 0), - DL(BPF_JMP, BPF_JEQ, BPF_X), - DL(BPF_JMP, BPF_JEQ, BPF_K), - DL(BPF_JMP, BPF_JNE, BPF_X), - DL(BPF_JMP, BPF_JNE, BPF_K), - DL(BPF_JMP, BPF_JGT, BPF_X), - DL(BPF_JMP, BPF_JGT, BPF_K), - DL(BPF_JMP, BPF_JGE, BPF_X), - DL(BPF_JMP, BPF_JGE, BPF_K), - DL(BPF_JMP, BPF_JSGT, BPF_X), - DL(BPF_JMP, BPF_JSGT, BPF_K), - DL(BPF_JMP, BPF_JSGE, BPF_X), - DL(BPF_JMP, BPF_JSGE, BPF_K), - DL(BPF_JMP, BPF_JSET, BPF_X), - DL(BPF_JMP, BPF_JSET, BPF_K), - DL(BPF_JMP, BPF_EXIT, 0), - DL(BPF_STX, BPF_MEM, BPF_B), - DL(BPF_STX, BPF_MEM, BPF_H), - DL(BPF_STX, BPF_MEM, BPF_W), - DL(BPF_STX, BPF_MEM, BPF_DW), - DL(BPF_STX, BPF_XADD, BPF_W), - DL(BPF_STX, BPF_XADD, BPF_DW), - DL(BPF_ST, BPF_MEM, BPF_B), - DL(BPF_ST, BPF_MEM, BPF_H), - DL(BPF_ST, BPF_MEM, BPF_W), - DL(BPF_ST, BPF_MEM, BPF_DW), - DL(BPF_LDX, BPF_MEM, BPF_B), - DL(BPF_LDX, BPF_MEM, BPF_H), - DL(BPF_LDX, BPF_MEM, BPF_W), - DL(BPF_LDX, BPF_MEM, BPF_DW), - DL(BPF_LD, BPF_ABS, BPF_W), - DL(BPF_LD, BPF_ABS, BPF_H), - DL(BPF_LD, BPF_ABS, BPF_B), - DL(BPF_LD, BPF_IND, BPF_W), - DL(BPF_LD, BPF_IND, BPF_H), - DL(BPF_LD, BPF_IND, BPF_B), -#undef DL + /* 32 bit ALU operations */ + [BPF_ALU | BPF_ADD | BPF_X] = &&ALU_ADD_X, + [BPF_ALU | BPF_ADD | BPF_K] = &&ALU_ADD_K, + [BPF_ALU | BPF_SUB | BPF_X] = &&ALU_SUB_X, + [BPF_ALU | BPF_SUB | BPF_K] = &&ALU_SUB_K, + [BPF_ALU | BPF_AND | BPF_X] = &&ALU_AND_X, + [BPF_ALU | BPF_AND | BPF_K] = &&ALU_AND_K, + [BPF_ALU | BPF_OR | BPF_X] = &&ALU_OR_X, + [BPF_ALU | BPF_OR | BPF_K] = &&ALU_OR_K, + [BPF_ALU | BPF_LSH | BPF_X] = &&ALU_LSH_X, + [BPF_ALU | BPF_LSH | BPF_K] = &&ALU_LSH_K, + [BPF_ALU | BPF_RSH | BPF_X] = &&ALU_RSH_X, + [BPF_ALU | BPF_RSH | BPF_K] = &&ALU_RSH_K, + [BPF_ALU | BPF_XOR | BPF_X] = &&ALU_XOR_X, + [BPF_ALU | BPF_XOR | BPF_K] = &&ALU_XOR_K, + [BPF_ALU | BPF_MUL | BPF_X] = &&ALU_MUL_X, + [BPF_ALU | BPF_MUL | BPF_K] = &&ALU_MUL_K, + [BPF_ALU | BPF_MOV | BPF_X] = &&ALU_MOV_X, + [BPF_ALU | BPF_MOV | BPF_K] = &&ALU_MOV_K, + [BPF_ALU | BPF_DIV | BPF_X] = &&ALU_DIV_X, + [BPF_ALU | BPF_DIV | BPF_K] = &&ALU_DIV_K, + [BPF_ALU | BPF_MOD | BPF_X] = &&ALU_MOD_X, + [BPF_ALU | BPF_MOD | BPF_K] = &&ALU_MOD_K, + [BPF_ALU | BPF_NEG] = &&ALU_NEG, + [BPF_ALU | BPF_END | BPF_TO_BE] = &&ALU_END_TO_BE, + [BPF_ALU | BPF_END | BPF_TO_LE] = &&ALU_END_TO_LE, + /* 64 bit ALU operations */ + [BPF_ALU64 | BPF_ADD | BPF_X] = &&ALU64_ADD_X, + [BPF_ALU64 | BPF_ADD | BPF_K] = &&ALU64_ADD_K, + [BPF_ALU64 | BPF_SUB | BPF_X] = &&ALU64_SUB_X, + [BPF_ALU64 | BPF_SUB | BPF_K] = &&ALU64_SUB_K, + [BPF_ALU64 | BPF_AND | BPF_X] = &&ALU64_AND_X, + [BPF_ALU64 | BPF_AND | BPF_K] = &&ALU64_AND_K, + [BPF_ALU64 | BPF_OR | BPF_X] = &&ALU64_OR_X, + [BPF_ALU64 | BPF_OR | BPF_K] = &&ALU64_OR_K, + [BPF_ALU64 | BPF_LSH | BPF_X] = &&ALU64_LSH_X, + [BPF_ALU64 | BPF_LSH | BPF_K] = &&ALU64_LSH_K, + [BPF_ALU64 | BPF_RSH | BPF_X] = &&ALU64_RSH_X, + [BPF_ALU64 | BPF_RSH | BPF_K] = &&ALU64_RSH_K, + [BPF_ALU64 | BPF_XOR | BPF_X] = &&ALU64_XOR_X, + [BPF_ALU64 | BPF_XOR | BPF_K] = &&ALU64_XOR_K, + [BPF_ALU64 | BPF_MUL | BPF_X] = &&ALU64_MUL_X, + [BPF_ALU64 | BPF_MUL | BPF_K] = &&ALU64_MUL_K, + [BPF_ALU64 | BPF_MOV | BPF_X] = &&ALU64_MOV_X, + [BPF_ALU64 | BPF_MOV | BPF_K] = &&ALU64_MOV_K, + [BPF_ALU64 | BPF_ARSH | BPF_X] = &&ALU64_ARSH_X, + [BPF_ALU64 | BPF_ARSH | BPF_K] = &&ALU64_ARSH_K, + [BPF_ALU64 | BPF_DIV | BPF_X] = &&ALU64_DIV_X, + [BPF_ALU64 | BPF_DIV | BPF_K] = &&ALU64_DIV_K, + [BPF_ALU64 | BPF_MOD | BPF_X] = &&ALU64_MOD_X, + [BPF_ALU64 | BPF_MOD | BPF_K] = &&ALU64_MOD_K, + [BPF_ALU64 | BPF_NEG] = &&ALU64_NEG, + /* Call instruction */ + [BPF_JMP | BPF_CALL] = &&JMP_CALL, + /* Jumps */ + [BPF_JMP | BPF_JA] = &&JMP_JA, + [BPF_JMP | BPF_JEQ | BPF_X] = &&JMP_JEQ_X, + [BPF_JMP | BPF_JEQ | BPF_K] = &&JMP_JEQ_K, + [BPF_JMP | BPF_JNE | BPF_X] = &&JMP_JNE_X, + [BPF_JMP | BPF_JNE | BPF_K] = &&JMP_JNE_K, + [BPF_JMP | BPF_JGT | BPF_X] = &&JMP_JGT_X, + [BPF_JMP | BPF_JGT | BPF_K] = &&JMP_JGT_K, + [BPF_JMP | BPF_JGE | BPF_X] = &&JMP_JGE_X, + [BPF_JMP | BPF_JGE | BPF_K] = &&JMP_JGE_K, + [BPF_JMP | BPF_JSGT | BPF_X] = &&JMP_JSGT_X, + [BPF_JMP | BPF_JSGT | BPF_K] = &&JMP_JSGT_K, + [BPF_JMP | BPF_JSGE | BPF_X] = &&JMP_JSGE_X, + [BPF_JMP | BPF_JSGE | BPF_K] = &&JMP_JSGE_K, + [BPF_JMP | BPF_JSET | BPF_X] = &&JMP_JSET_X, + [BPF_JMP | BPF_JSET | BPF_K] = &&JMP_JSET_K, + /* Program return */ + [BPF_JMP | BPF_EXIT] = &&JMP_EXIT, + /* Store instructions */ + [BPF_STX | BPF_MEM | BPF_B] = &&STX_MEM_B, + [BPF_STX | BPF_MEM | BPF_H] = &&STX_MEM_H, + [BPF_STX | BPF_MEM | BPF_W] = &&STX_MEM_W, + [BPF_STX | BPF_MEM | BPF_DW] = &&STX_MEM_DW, + [BPF_STX | BPF_XADD | BPF_W] = &&STX_XADD_W, + [BPF_STX | BPF_XADD | BPF_DW] = &&STX_XADD_DW, + [BPF_ST | BPF_MEM | BPF_B] = &&ST_MEM_B, + [BPF_ST | BPF_MEM | BPF_H] = &&ST_MEM_H, + [BPF_ST | BPF_MEM | BPF_W] = &&ST_MEM_W, + [BPF_ST | BPF_MEM | BPF_DW] = &&ST_MEM_DW, + /* Load instructions */ + [BPF_LDX | BPF_MEM | BPF_B] = &&LDX_MEM_B, + [BPF_LDX | BPF_MEM | BPF_H] = &&LDX_MEM_H, + [BPF_LDX | BPF_MEM | BPF_W] = &&LDX_MEM_W, + [BPF_LDX | BPF_MEM | BPF_DW] = &&LDX_MEM_DW, + [BPF_LD | BPF_ABS | BPF_W] = &&LD_ABS_W, + [BPF_LD | BPF_ABS | BPF_H] = &&LD_ABS_H, + [BPF_LD | BPF_ABS | BPF_B] = &&LD_ABS_B, + [BPF_LD | BPF_IND | BPF_W] = &&LD_IND_W, + [BPF_LD | BPF_IND | BPF_H] = &&LD_IND_H, + [BPF_LD | BPF_IND | BPF_B] = &&LD_IND_B, }; + void *ptr; + int off; + +#define CONT ({ insn++; goto select_insn; }) +#define CONT_JMP ({ insn++; goto select_insn; })

- regs[FP_REG] = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; - regs[ARG1_REG] = (u64) (unsigned long) ctx; - regs[A_REG] = 0; - regs[X_REG] = 0; + FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; + ARG1 = (u64) (unsigned long) ctx; + + /* Register for user BPF programs need to be reset first. */ + regs[BPF_REG_A] = 0; + regs[BPF_REG_X] = 0;

select_insn: goto *jumptable[insn->code];

/* ALU */ #define ALU(OPCODE, OP) \ - BPF_ALU64_##OPCODE##_BPF_X: \ + ALU64_##OPCODE##_X: \ A = A OP X; \ CONT; \ - BPF_ALU_##OPCODE##_BPF_X: \ + ALU_##OPCODE##_X: \ A = (u32) A OP (u32) X; \ CONT; \ - BPF_ALU64_##OPCODE##_BPF_K: \ + ALU64_##OPCODE##_K: \ A = A OP K; \ CONT; \ - BPF_ALU_##OPCODE##_BPF_K: \ + ALU_##OPCODE##_K: \ A = (u32) A OP (u32) K; \ CONT;

- ALU(BPF_ADD, +) - ALU(BPF_SUB, -) - ALU(BPF_AND, &) - ALU(BPF_OR, |) - ALU(BPF_LSH, <<) - ALU(BPF_RSH, >>) - ALU(BPF_XOR, ^) - ALU(BPF_MUL, *) + ALU(ADD, +) + ALU(SUB, -) + ALU(AND, &) + ALU(OR, |) + ALU(LSH, <<) + ALU(RSH, >>) + ALU(XOR, ^) + ALU(MUL, *) #undef ALU - BPF_ALU_BPF_NEG_0: + ALU_NEG: A = (u32) -A; CONT; - BPF_ALU64_BPF_NEG_0: + ALU64_NEG: A = -A; CONT; - BPF_ALU_BPF_MOV_BPF_X: + ALU_MOV_X: A = (u32) X; CONT; - BPF_ALU_BPF_MOV_BPF_K: + ALU_MOV_K: A = (u32) K; CONT; - BPF_ALU64_BPF_MOV_BPF_X: + ALU64_MOV_X: A = X; CONT; - BPF_ALU64_BPF_MOV_BPF_K: + ALU64_MOV_K: A = K; CONT; - BPF_ALU64_BPF_ARSH_BPF_X: + ALU64_ARSH_X: (*(s64 *) &A) >>= X; CONT; - BPF_ALU64_BPF_ARSH_BPF_K: + ALU64_ARSH_K: (*(s64 *) &A) >>= K; CONT; - BPF_ALU64_BPF_MOD_BPF_X: + ALU64_MOD_X: if (unlikely(X == 0)) return 0; tmp = A; A = do_div(tmp, X); CONT; - BPF_ALU_BPF_MOD_BPF_X: + ALU_MOD_X: if (unlikely(X == 0)) return 0; tmp = (u32) A; A = do_div(tmp, (u32) X); CONT; - BPF_ALU64_BPF_MOD_BPF_K: + ALU64_MOD_K: tmp = A; A = do_div(tmp, K); CONT; - BPF_ALU_BPF_MOD_BPF_K: + ALU_MOD_K: tmp = (u32) A; A = do_div(tmp, (u32) K); CONT; - BPF_ALU64_BPF_DIV_BPF_X: + ALU64_DIV_X: if (unlikely(X == 0)) return 0; do_div(A, X); CONT; - BPF_ALU_BPF_DIV_BPF_X: + ALU_DIV_X: if (unlikely(X == 0)) return 0; tmp = (u32) A; do_div(tmp, (u32) X); A = (u32) tmp; CONT; - BPF_ALU64_BPF_DIV_BPF_K: + ALU64_DIV_K: do_div(A, K); CONT; - BPF_ALU_BPF_DIV_BPF_K: + ALU_DIV_K: tmp = (u32) A; do_div(tmp, (u32) K); A = (u32) tmp; CONT; - BPF_ALU_BPF_END_BPF_TO_BE: + ALU_END_TO_BE: switch (K) { case 16: A = (__force u16) cpu_to_be16(A); @@@ -372,7 -356,7 +372,7 @@@ break; } CONT; - BPF_ALU_BPF_END_BPF_TO_LE: + ALU_END_TO_LE: switch (K) { case 16: A = (__force u16) cpu_to_le16(A); @@@ -387,144 -371,142 +387,144 @@@ CONT;

/* CALL */ - BPF_JMP_BPF_CALL_0: - /* Function call scratches R1-R5 registers, preserves R6-R9, - * and stores return value into R0. + JMP_CALL: + /* Function call scratches BPF_R1-BPF_R5 registers, + * preserves BPF_R6-BPF_R9, and stores return value + * into BPF_R0. */ - R0 = (__bpf_call_base + insn->imm)(regs[1], regs[2], regs[3], - regs[4], regs[5]); + BPF_R0 = (__bpf_call_base + insn->imm)(BPF_R1, BPF_R2, BPF_R3, + BPF_R4, BPF_R5); CONT;

/* JMP */ - BPF_JMP_BPF_JA_0: + JMP_JA: insn += insn->off; CONT; - BPF_JMP_BPF_JEQ_BPF_X: + JMP_JEQ_X: if (A == X) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_JEQ_BPF_K: + JMP_JEQ_K: if (A == K) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_JNE_BPF_X: + JMP_JNE_X: if (A != X) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_JNE_BPF_K: + JMP_JNE_K: if (A != K) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_JGT_BPF_X: + JMP_JGT_X: if (A > X) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_JGT_BPF_K: + JMP_JGT_K: if (A > K) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_JGE_BPF_X: + JMP_JGE_X: if (A >= X) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_JGE_BPF_K: + JMP_JGE_K: if (A >= K) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_JSGT_BPF_X: - if (((s64)A) > ((s64)X)) { + JMP_JSGT_X: + if (((s64) A) > ((s64) X)) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_JSGT_BPF_K: - if (((s64)A) > ((s64)K)) { + JMP_JSGT_K: + if (((s64) A) > ((s64) K)) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_JSGE_BPF_X: - if (((s64)A) >= ((s64)X)) { + JMP_JSGE_X: + if (((s64) A) >= ((s64) X)) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_JSGE_BPF_K: - if (((s64)A) >= ((s64)K)) { + JMP_JSGE_K: + if (((s64) A) >= ((s64) K)) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_JSET_BPF_X: + JMP_JSET_X: if (A & X) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_JSET_BPF_K: + JMP_JSET_K: if (A & K) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_EXIT_0: - return R0; + JMP_EXIT: + return BPF_R0;

/* STX and ST and LDX*/ #define LDST(SIZEOP, SIZE) \ - BPF_STX_BPF_MEM_##SIZEOP: \ + STX_MEM_##SIZEOP: \ *(SIZE *)(unsigned long) (A + insn->off) = X; \ CONT; \ - BPF_ST_BPF_MEM_##SIZEOP: \ + ST_MEM_##SIZEOP: \ *(SIZE *)(unsigned long) (A + insn->off) = K; \ CONT; \ - BPF_LDX_BPF_MEM_##SIZEOP: \ + LDX_MEM_##SIZEOP: \ A = *(SIZE *)(unsigned long) (X + insn->off); \ CONT;

- LDST(BPF_B, u8) - LDST(BPF_H, u16) - LDST(BPF_W, u32) - LDST(BPF_DW, u64) + LDST(B, u8) + LDST(H, u16) + LDST(W, u32) + LDST(DW, u64) #undef LDST - BPF_STX_BPF_XADD_BPF_W: /* lock xadd *(u32 *)(A + insn->off) += X */ + STX_XADD_W: /* lock xadd *(u32 *)(A + insn->off) += X */ atomic_add((u32) X, (atomic_t *)(unsigned long) (A + insn->off)); CONT; - BPF_STX_BPF_XADD_BPF_DW: /* lock xadd *(u64 *)(A + insn->off) += X */ + STX_XADD_DW: /* lock xadd *(u64 *)(A + insn->off) += X */ atomic64_add((u64) X, (atomic64_t *)(unsigned long) (A + insn->off)); CONT; - BPF_LD_BPF_ABS_BPF_W: /* R0 = ntohl(*(u32 *) (skb->data + K)) */ + LD_ABS_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + K)) */ off = K; load_word: - /* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are only - * appearing in the programs where ctx == skb. All programs - * keep 'ctx' in regs[CTX_REG] == R6, sk_convert_filter() - * saves it in R6, internal BPF verifier will check that - * R6 == ctx. + /* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are + * only appearing in the programs where ctx == + * skb. All programs keep 'ctx' in regs[BPF_REG_CTX] + * == BPF_R6, sk_convert_filter() saves it in BPF_R6, + * internal BPF verifier will check that BPF_R6 == + * ctx. * - * BPF_ABS and BPF_IND are wrappers of function calls, so - * they scratch R1-R5 registers, preserve R6-R9, and store - * return value into R0. + * BPF_ABS and BPF_IND are wrappers of function calls, + * so they scratch BPF_R1-BPF_R5 registers, preserve + * BPF_R6-BPF_R9, and store return value into BPF_R0. * * Implicit input: * ctx @@@ -534,43 -516,39 +534,43 @@@ * K == 32-bit immediate * * Output: - * R0 - 8/16/32-bit skb data converted to cpu endianness + * BPF_R0 - 8/16/32-bit skb data converted to cpu endianness */ + ptr = load_pointer((struct sk_buff *) ctx, off, 4, &tmp); if (likely(ptr != NULL)) { - R0 = get_unaligned_be32(ptr); + BPF_R0 = get_unaligned_be32(ptr); CONT; } + return 0; - BPF_LD_BPF_ABS_BPF_H: /* R0 = ntohs(*(u16 *) (skb->data + K)) */ + LD_ABS_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + K)) */ off = K; load_half: ptr = load_pointer((struct sk_buff *) ctx, off, 2, &tmp); if (likely(ptr != NULL)) { - R0 = get_unaligned_be16(ptr); + BPF_R0 = get_unaligned_be16(ptr); CONT; } + return 0; - BPF_LD_BPF_ABS_BPF_B: /* R0 = *(u8 *) (ctx + K) */ + LD_ABS_B: /* BPF_R0 = *(u8 *) (ctx + K) */ off = K; load_byte: ptr = load_pointer((struct sk_buff *) ctx, off, 1, &tmp); if (likely(ptr != NULL)) { - R0 = *(u8 *)ptr; + BPF_R0 = *(u8 *)ptr; CONT; } + return 0; - BPF_LD_BPF_IND_BPF_W: /* R0 = ntohl(*(u32 *) (skb->data + X + K)) */ + LD_IND_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + X + K)) */ off = K + X; goto load_word; - BPF_LD_BPF_IND_BPF_H: /* R0 = ntohs(*(u16 *) (skb->data + X + K)) */ + LD_IND_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + X + K)) */ off = K + X; goto load_half; - BPF_LD_BPF_IND_BPF_B: /* R0 = *(u8 *) (skb->data + X + K) */ + LD_IND_B: /* BPF_R0 = *(u8 *) (skb->data + X + K) */ off = K + X; goto load_byte;

@@@ -578,8 -556,24 +578,8 @@@ /* If we ever reach this, we have a bug somewhere. */ WARN_RATELIMIT(1, "unknown opcode %02x\n", insn->code); return 0; -#undef CONT_JMP -#undef CONT - -#undef R0 -#undef X -#undef A -#undef K }

-u32 sk_run_filter_int_seccomp(const struct seccomp_data *ctx, - const struct sock_filter_int *insni) - __attribute__ ((alias ("__sk_run_filter"))); - -u32 sk_run_filter_int_skb(const struct sk_buff *ctx, - const struct sock_filter_int *insni) - __attribute__ ((alias ("__sk_run_filter"))); -EXPORT_SYMBOL_GPL(sk_run_filter_int_skb); - /* Helper to find the offset of pkt_type in sk_buff structure. We want * to make sure its still a 3bit field starting at a byte boundary; * taken from arch/x86/net/bpf_jit_comp.c. @@@ -600,14 -594,16 +600,14 @@@ static unsigned int pkt_type_offset(voi return -1; }

-static u64 __skb_get_pay_offset(u64 ctx, u64 A, u64 X, u64 r4, u64 r5) +static u64 __skb_get_pay_offset(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) { - struct sk_buff *skb = (struct sk_buff *)(long) ctx; - - return __skb_get_poff(skb); + return __skb_get_poff((struct sk_buff *)(unsigned long) ctx); }

-static u64 __skb_get_nlattr(u64 ctx, u64 A, u64 X, u64 r4, u64 r5) +static u64 __skb_get_nlattr(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) { - struct sk_buff *skb = (struct sk_buff *)(long) ctx; + struct sk_buff *skb = (struct sk_buff *)(unsigned long) ctx; struct nlattr *nla;

if (skb_is_nonlinear(skb)) @@@ -616,19 -612,19 +616,19 @@@ if (skb->len < sizeof(struct nlattr)) return 0;

- if (A > skb->len - sizeof(struct nlattr)) + if (a > skb->len - sizeof(struct nlattr)) return 0;

- nla = nla_find((struct nlattr *) &skb->data[A], skb->len - A, X); + nla = nla_find((struct nlattr *) &skb->data[a], skb->len - a, x); if (nla) return (void *) nla - (void *) skb->data;

return 0; }

-static u64 __skb_get_nlattr_nest(u64 ctx, u64 A, u64 X, u64 r4, u64 r5) +static u64 __skb_get_nlattr_nest(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) { - struct sk_buff *skb = (struct sk_buff *)(long) ctx; + struct sk_buff *skb = (struct sk_buff *)(unsigned long) ctx; struct nlattr *nla;

if (skb_is_nonlinear(skb)) @@@ -637,31 -633,25 +637,31 @@@ if (skb->len < sizeof(struct nlattr)) return 0;

- if (A > skb->len - sizeof(struct nlattr)) + if (a > skb->len - sizeof(struct nlattr)) return 0;

- nla = (struct nlattr *) &skb->data[A]; - if (nla->nla_len > skb->len - A) + nla = (struct nlattr *) &skb->data[a]; + if (nla->nla_len > skb->len - a) return 0;

- nla = nla_find_nested(nla, X); + nla = nla_find_nested(nla, x); if (nla) return (void *) nla - (void *) skb->data;

return 0; }

-static u64 __get_raw_cpu_id(u64 ctx, u64 A, u64 X, u64 r4, u64 r5) +static u64 __get_raw_cpu_id(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) { return raw_smp_processor_id(); }

+/* note that this only generates 32-bit random numbers */ +static u64 __get_random_u32(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) +{ + return prandom_u32(); +} + static bool convert_bpf_extensions(struct sock_filter *fp, struct sock_filter_int **insnp) { @@@ -671,79 -661,119 +671,79 @@@ case SKF_AD_OFF + SKF_AD_PROTOCOL: BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2);

- insn->code = BPF_LDX | BPF_MEM | BPF_H; - insn->a_reg = A_REG; - insn->x_reg = CTX_REG; - insn->off = offsetof(struct sk_buff, protocol); - insn++; - + /* A = *(u16 *) (ctx + offsetof(protocol)) */ + *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, + offsetof(struct sk_buff, protocol)); /* A = ntohs(A) [emitting a nop or swap16] */ - insn->code = BPF_ALU | BPF_END | BPF_FROM_BE; - insn->a_reg = A_REG; - insn->imm = 16; + *insn = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, 16); break;

case SKF_AD_OFF + SKF_AD_PKTTYPE: - insn->code = BPF_LDX | BPF_MEM | BPF_B; - insn->a_reg = A_REG; - insn->x_reg = CTX_REG; - insn->off = pkt_type_offset(); + *insn = BPF_LDX_MEM(BPF_B, BPF_REG_A, BPF_REG_CTX, + pkt_type_offset()); if (insn->off < 0) return false; insn++; - - insn->code = BPF_ALU | BPF_AND | BPF_K; - insn->a_reg = A_REG; - insn->imm = PKT_TYPE_MAX; + *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, PKT_TYPE_MAX); break;

case SKF_AD_OFF + SKF_AD_IFINDEX: case SKF_AD_OFF + SKF_AD_HATYPE: - if (FIELD_SIZEOF(struct sk_buff, dev) == 8) - insn->code = BPF_LDX | BPF_MEM | BPF_DW; - else - insn->code = BPF_LDX | BPF_MEM | BPF_W; - insn->a_reg = TMP_REG; - insn->x_reg = CTX_REG; - insn->off = offsetof(struct sk_buff, dev); - insn++; - - insn->code = BPF_JMP | BPF_JNE | BPF_K; - insn->a_reg = TMP_REG; - insn->imm = 0; - insn->off = 1; - insn++; - - insn->code = BPF_JMP | BPF_EXIT; - insn++; - BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2); - - insn->a_reg = A_REG; - insn->x_reg = TMP_REG; - - if (fp->k == SKF_AD_OFF + SKF_AD_IFINDEX) { - insn->code = BPF_LDX | BPF_MEM | BPF_W; - insn->off = offsetof(struct net_device, ifindex); - } else { - insn->code = BPF_LDX | BPF_MEM | BPF_H; - insn->off = offsetof(struct net_device, type); - } + BUILD_BUG_ON(bytes_to_bpf_size(FIELD_SIZEOF(struct sk_buff, dev)) < 0); + + *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct sk_buff, dev)), + BPF_REG_TMP, BPF_REG_CTX, + offsetof(struct sk_buff, dev)); + /* if (tmp != 0) goto pc + 1 */ + *insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_TMP, 0, 1); + *insn++ = BPF_EXIT_INSN(); + if (fp->k == SKF_AD_OFF + SKF_AD_IFINDEX) + *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_TMP, + offsetof(struct net_device, ifindex)); + else + *insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_TMP, + offsetof(struct net_device, type)); break;

case SKF_AD_OFF + SKF_AD_MARK: BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);

- insn->code = BPF_LDX | BPF_MEM | BPF_W; - insn->a_reg = A_REG; - insn->x_reg = CTX_REG; - insn->off = offsetof(struct sk_buff, mark); + *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, + offsetof(struct sk_buff, mark)); break;

case SKF_AD_OFF + SKF_AD_RXHASH: BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);

- insn->code = BPF_LDX | BPF_MEM | BPF_W; - insn->a_reg = A_REG; - insn->x_reg = CTX_REG; - insn->off = offsetof(struct sk_buff, hash); + *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, + offsetof(struct sk_buff, hash)); break;

case SKF_AD_OFF + SKF_AD_QUEUE: BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2);

- insn->code = BPF_LDX | BPF_MEM | BPF_H; - insn->a_reg = A_REG; - insn->x_reg = CTX_REG; - insn->off = offsetof(struct sk_buff, queue_mapping); + *insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, + offsetof(struct sk_buff, queue_mapping)); break;

case SKF_AD_OFF + SKF_AD_VLAN_TAG: case SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT: BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2); - - insn->code = BPF_LDX | BPF_MEM | BPF_H; - insn->a_reg = A_REG; - insn->x_reg = CTX_REG; - insn->off = offsetof(struct sk_buff, vlan_tci); - insn++; - BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);

+ /* A = *(u16 *) (ctx + offsetof(vlan_tci)) */ + *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, + offsetof(struct sk_buff, vlan_tci)); if (fp->k == SKF_AD_OFF + SKF_AD_VLAN_TAG) { - insn->code = BPF_ALU | BPF_AND | BPF_K; - insn->a_reg = A_REG; - insn->imm = ~VLAN_TAG_PRESENT; + *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, + ~VLAN_TAG_PRESENT); } else { - insn->code = BPF_ALU | BPF_RSH | BPF_K; - insn->a_reg = A_REG; - insn->imm = 12; - insn++; - - insn->code = BPF_ALU | BPF_AND | BPF_K; - insn->a_reg = A_REG; - insn->imm = 1; + /* A >>= 12 */ + *insn++ = BPF_ALU32_IMM(BPF_RSH, BPF_REG_A, 12); + /* A &= 1 */ + *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 1); } break;

@@@ -751,36 -781,46 +751,36 @@@ case SKF_AD_OFF + SKF_AD_NLATTR: case SKF_AD_OFF + SKF_AD_NLATTR_NEST: case SKF_AD_OFF + SKF_AD_CPU: + case SKF_AD_OFF + SKF_AD_RANDOM: /* arg1 = ctx */ - insn->code = BPF_ALU64 | BPF_MOV | BPF_X; - insn->a_reg = ARG1_REG; - insn->x_reg = CTX_REG; - insn++; - + *insn++ = BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX); /* arg2 = A */ - insn->code = BPF_ALU64 | BPF_MOV | BPF_X; - insn->a_reg = ARG2_REG; - insn->x_reg = A_REG; - insn++; - + *insn++ = BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_A); /* arg3 = X */ - insn->code = BPF_ALU64 | BPF_MOV | BPF_X; - insn->a_reg = ARG3_REG; - insn->x_reg = X_REG; - insn++; - + *insn++ = BPF_MOV64_REG(BPF_REG_ARG3, BPF_REG_X); /* Emit call(ctx, arg2=A, arg3=X) */ - insn->code = BPF_JMP | BPF_CALL; switch (fp->k) { case SKF_AD_OFF + SKF_AD_PAY_OFFSET: - insn->imm = __skb_get_pay_offset - __bpf_call_base; + *insn = BPF_EMIT_CALL(__skb_get_pay_offset); break; case SKF_AD_OFF + SKF_AD_NLATTR: - insn->imm = __skb_get_nlattr - __bpf_call_base; + *insn = BPF_EMIT_CALL(__skb_get_nlattr); break; case SKF_AD_OFF + SKF_AD_NLATTR_NEST: - insn->imm = __skb_get_nlattr_nest - __bpf_call_base; + *insn = BPF_EMIT_CALL(__skb_get_nlattr_nest); break; case SKF_AD_OFF + SKF_AD_CPU: - insn->imm = __get_raw_cpu_id - __bpf_call_base; + *insn = BPF_EMIT_CALL(__get_raw_cpu_id); + break; + case SKF_AD_OFF + SKF_AD_RANDOM: + *insn = BPF_EMIT_CALL(__get_random_u32); break; } break;

case SKF_AD_OFF + SKF_AD_ALU_XOR_X: - insn->code = BPF_ALU | BPF_XOR | BPF_X; - insn->a_reg = A_REG; - insn->x_reg = X_REG; + /* A ^= X */ + *insn = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_X); break;

default: @@@ -830,7 -870,7 +830,7 @@@ int sk_convert_filter(struct sock_filte u8 bpf_src;

BUILD_BUG_ON(BPF_MEMWORDS * sizeof(u32) > MAX_BPF_STACK); - BUILD_BUG_ON(FP_REG + 1 != MAX_BPF_REG); + BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG);

if (len <= 0 || len >= BPF_MAXINSNS) return -EINVAL; @@@ -845,8 -885,11 +845,8 @@@ do_pass new_insn = new_prog; fp = prog;

- if (new_insn) { - new_insn->code = BPF_ALU64 | BPF_MOV | BPF_X; - new_insn->a_reg = CTX_REG; - new_insn->x_reg = ARG1_REG; - } + if (new_insn) + *new_insn = BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1); new_insn++;

for (i = 0; i < len; fp++, i++) { @@@ -894,16 -937,17 +894,16 @@@ convert_bpf_extensions(fp, &insn)) break;

- insn->code = fp->code; - insn->a_reg = A_REG; - insn->x_reg = X_REG; - insn->imm = fp->k; + *insn = BPF_RAW_INSN(fp->code, BPF_REG_A, BPF_REG_X, 0, fp->k); break;

- /* Jump opcodes map as-is, but offsets need adjustment. */ - case BPF_JMP | BPF_JA: - target = i + fp->k + 1; - insn->code = fp->code; -#define EMIT_JMP \ + /* Jump transformation cannot use BPF block macros + * everywhere as offset calculation and target updates + * require a bit more work than the rest, i.e. jump + * opcodes map as-is, but offsets need adjustment. + */ + +#define BPF_EMIT_JMP \ do { \ if (target >= len || target < 0) \ goto err; \ @@@ -912,10 -956,7 +912,10 @@@ insn->off -= insn - tmp_insns; \ } while (0)

- EMIT_JMP; + case BPF_JMP | BPF_JA: + target = i + fp->k + 1; + insn->code = fp->code; + BPF_EMIT_JMP; break;

case BPF_JMP | BPF_JEQ | BPF_K: @@@ -931,14 -972,17 +931,14 @@@ * immediate into tmp register and use it * in compare insn. */ - insn->code = BPF_ALU | BPF_MOV | BPF_K; - insn->a_reg = TMP_REG; - insn->imm = fp->k; - insn++; + *insn++ = BPF_MOV32_IMM(BPF_REG_TMP, fp->k);

- insn->a_reg = A_REG; - insn->x_reg = TMP_REG; + insn->a_reg = BPF_REG_A; + insn->x_reg = BPF_REG_TMP; bpf_src = BPF_X; } else { - insn->a_reg = A_REG; - insn->x_reg = X_REG; + insn->a_reg = BPF_REG_A; + insn->x_reg = BPF_REG_X; insn->imm = fp->k; bpf_src = BPF_SRC(fp->code); } @@@ -947,7 -991,7 +947,7 @@@ if (fp->jf == 0) { insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src; target = i + fp->jt + 1; - EMIT_JMP; + BPF_EMIT_JMP; break; }

@@@ -955,94 -999,127 +955,94 @@@ if (fp->jt == 0 && BPF_OP(fp->code) == BPF_JEQ) { insn->code = BPF_JMP | BPF_JNE | bpf_src; target = i + fp->jf + 1; - EMIT_JMP; + BPF_EMIT_JMP; break; }

/* Other jumps are mapped into two insns: Jxx and JA. */ target = i + fp->jt + 1; insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src; - EMIT_JMP; + BPF_EMIT_JMP; insn++;

insn->code = BPF_JMP | BPF_JA; target = i + fp->jf + 1; - EMIT_JMP; + BPF_EMIT_JMP; break;

/* ldxb 4 * ([14] & 0xf) is remaped into 6 insns. */ case BPF_LDX | BPF_MSH | BPF_B: - insn->code = BPF_ALU64 | BPF_MOV | BPF_X; - insn->a_reg = TMP_REG; - insn->x_reg = A_REG; - insn++; - - insn->code = BPF_LD | BPF_ABS | BPF_B; - insn->a_reg = A_REG; - insn->imm = fp->k; - insn++; - - insn->code = BPF_ALU | BPF_AND | BPF_K; - insn->a_reg = A_REG; - insn->imm = 0xf; - insn++; - - insn->code = BPF_ALU | BPF_LSH | BPF_K; - insn->a_reg = A_REG; - insn->imm = 2; - insn++; - - insn->code = BPF_ALU64 | BPF_MOV | BPF_X; - insn->a_reg = X_REG; - insn->x_reg = A_REG; - insn++; - - insn->code = BPF_ALU64 | BPF_MOV | BPF_X; - insn->a_reg = A_REG; - insn->x_reg = TMP_REG; + /* tmp = A */ + *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_A); + /* A = BPF_R0 = *(u8 *) (skb->data + K) */ + *insn++ = BPF_LD_ABS(BPF_B, fp->k); + /* A &= 0xf */ + *insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 0xf); + /* A <<= 2 */ + *insn++ = BPF_ALU32_IMM(BPF_LSH, BPF_REG_A, 2); + /* X = A */ + *insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); + /* A = tmp */ + *insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_TMP); break;

/* RET_K, RET_A are remaped into 2 insns. */ case BPF_RET | BPF_A: case BPF_RET | BPF_K: - insn->code = BPF_ALU | BPF_MOV | - (BPF_RVAL(fp->code) == BPF_K ? - BPF_K : BPF_X); - insn->a_reg = 0; - insn->x_reg = A_REG; - insn->imm = fp->k; - insn++; - - insn->code = BPF_JMP | BPF_EXIT; + *insn++ = BPF_MOV32_RAW(BPF_RVAL(fp->code) == BPF_K ? + BPF_K : BPF_X, BPF_REG_0, + BPF_REG_A, fp->k); + *insn = BPF_EXIT_INSN(); break;

/* Store to stack. */ case BPF_ST: case BPF_STX: - insn->code = BPF_STX | BPF_MEM | BPF_W; - insn->a_reg = FP_REG; - insn->x_reg = fp->code == BPF_ST ? A_REG : X_REG; - insn->off = -(BPF_MEMWORDS - fp->k) * 4; + *insn = BPF_STX_MEM(BPF_W, BPF_REG_FP, BPF_CLASS(fp->code) == + BPF_ST ? BPF_REG_A : BPF_REG_X, + -(BPF_MEMWORDS - fp->k) * 4); break;

/* Load from stack. */ case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: - insn->code = BPF_LDX | BPF_MEM | BPF_W; - insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ? - A_REG : X_REG; - insn->x_reg = FP_REG; - insn->off = -(BPF_MEMWORDS - fp->k) * 4; + *insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ? + BPF_REG_A : BPF_REG_X, BPF_REG_FP, + -(BPF_MEMWORDS - fp->k) * 4); break;

/* A = K or X = K */ case BPF_LD | BPF_IMM: case BPF_LDX | BPF_IMM: - insn->code = BPF_ALU | BPF_MOV | BPF_K; - insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ? - A_REG : X_REG; - insn->imm = fp->k; + *insn = BPF_MOV32_IMM(BPF_CLASS(fp->code) == BPF_LD ? + BPF_REG_A : BPF_REG_X, fp->k); break;

/* X = A */ case BPF_MISC | BPF_TAX: - insn->code = BPF_ALU64 | BPF_MOV | BPF_X; - insn->a_reg = X_REG; - insn->x_reg = A_REG; + *insn = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); break;

/* A = X */ case BPF_MISC | BPF_TXA: - insn->code = BPF_ALU64 | BPF_MOV | BPF_X; - insn->a_reg = A_REG; - insn->x_reg = X_REG; + *insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_X); break;

/* A = skb->len or X = skb->len */ case BPF_LD | BPF_W | BPF_LEN: case BPF_LDX | BPF_W | BPF_LEN: - insn->code = BPF_LDX | BPF_MEM | BPF_W; - insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ? - A_REG : X_REG; - insn->x_reg = CTX_REG; - insn->off = offsetof(struct sk_buff, len); + *insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ? + BPF_REG_A : BPF_REG_X, BPF_REG_CTX, + offsetof(struct sk_buff, len)); break;

- /* access seccomp_data fields */ + /* Access seccomp_data fields. */ case BPF_LDX | BPF_ABS | BPF_W: - insn->code = BPF_LDX | BPF_MEM | BPF_W; - insn->a_reg = A_REG; - insn->x_reg = CTX_REG; - insn->off = fp->k; + /* A = *(u32 *) (ctx + K) */ + *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, fp->k); break;

+ /* Unkown instruction. */ default: goto err; } @@@ -1051,6 -1128,7 +1051,6 @@@ if (new_prog) memcpy(new_insn, tmp_insns, sizeof(*insn) * (insn - tmp_insns)); - new_insn += insn - tmp_insns; }

@@@ -1065,6 -1143,7 +1065,6 @@@ new_flen = new_insn - new_prog; if (pass > 2) goto err; - goto do_pass; }

@@@ -1088,46 -1167,44 +1088,46 @@@ err */ static int check_load_and_stores(struct sock_filter *filter, int flen) { - u16 *masks, memvalid = 0; /* one bit per cell, 16 cells */ + u16 *masks, memvalid = 0; /* One bit per cell, 16 cells */ int pc, ret = 0;

BUILD_BUG_ON(BPF_MEMWORDS > 16); + masks = kmalloc(flen * sizeof(*masks), GFP_KERNEL); if (!masks) return -ENOMEM; + memset(masks, 0xff, flen * sizeof(*masks));

for (pc = 0; pc < flen; pc++) { memvalid &= masks[pc];

switch (filter[pc].code) { - case BPF_S_ST: - case BPF_S_STX: + case BPF_ST: + case BPF_STX: memvalid |= (1 << filter[pc].k); break; - case BPF_S_LD_MEM: - case BPF_S_LDX_MEM: + case BPF_LD | BPF_MEM: + case BPF_LDX | BPF_MEM: if (!(memvalid & (1 << filter[pc].k))) { ret = -EINVAL; goto error; } break; - case BPF_S_JMP_JA: - /* a jump must set masks on target */ + case BPF_JMP | BPF_JA: + /* A jump must set masks on target */ masks[pc + 1 + filter[pc].k] &= memvalid; memvalid = ~0; break; - case BPF_S_JMP_JEQ_K: - case BPF_S_JMP_JEQ_X: - case BPF_S_JMP_JGE_K: - case BPF_S_JMP_JGE_X: - case BPF_S_JMP_JGT_K: - case BPF_S_JMP_JGT_X: - case BPF_S_JMP_JSET_X: - case BPF_S_JMP_JSET_K: - /* a jump must set masks on targets */ + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP | BPF_JEQ | BPF_X: + case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JSET | BPF_K: + case BPF_JMP | BPF_JSET | BPF_X: + /* A jump must set masks on targets */ masks[pc + 1 + filter[pc].jt] &= memvalid; masks[pc + 1 + filter[pc].jf] &= memvalid; memvalid = ~0; @@@ -1139,72 -1216,6 +1139,72 @@@ error return ret; }

+static bool chk_code_allowed(u16 code_to_probe) +{ + static const bool codes[] = { + /* 32 bit ALU operations */ + [BPF_ALU | BPF_ADD | BPF_K] = true, + [BPF_ALU | BPF_ADD | BPF_X] = true, + [BPF_ALU | BPF_SUB | BPF_K] = true, + [BPF_ALU | BPF_SUB | BPF_X] = true, + [BPF_ALU | BPF_MUL | BPF_K] = true, + [BPF_ALU | BPF_MUL | BPF_X] = true, + [BPF_ALU | BPF_DIV | BPF_K] = true, + [BPF_ALU | BPF_DIV | BPF_X] = true, + [BPF_ALU | BPF_MOD | BPF_K] = true, + [BPF_ALU | BPF_MOD | BPF_X] = true, + [BPF_ALU | BPF_AND | BPF_K] = true, + [BPF_ALU | BPF_AND | BPF_X] = true, + [BPF_ALU | BPF_OR | BPF_K] = true, + [BPF_ALU | BPF_OR | BPF_X] = true, + [BPF_ALU | BPF_XOR | BPF_K] = true, + [BPF_ALU | BPF_XOR | BPF_X] = true, + [BPF_ALU | BPF_LSH | BPF_K] = true, + [BPF_ALU | BPF_LSH | BPF_X] = true, + [BPF_ALU | BPF_RSH | BPF_K] = true, + [BPF_ALU | BPF_RSH | BPF_X] = true, + [BPF_ALU | BPF_NEG] = true, + /* Load instructions */ + [BPF_LD | BPF_W | BPF_ABS] = true, + [BPF_LD | BPF_H | BPF_ABS] = true, + [BPF_LD | BPF_B | BPF_ABS] = true, + [BPF_LD | BPF_W | BPF_LEN] = true, + [BPF_LD | BPF_W | BPF_IND] = true, + [BPF_LD | BPF_H | BPF_IND] = true, + [BPF_LD | BPF_B | BPF_IND] = true, + [BPF_LD | BPF_IMM] = true, + [BPF_LD | BPF_MEM] = true, + [BPF_LDX | BPF_W | BPF_LEN] = true, + [BPF_LDX | BPF_B | BPF_MSH] = true, + [BPF_LDX | BPF_IMM] = true, + [BPF_LDX | BPF_MEM] = true, + /* Store instructions */ + [BPF_ST] = true, + [BPF_STX] = true, + /* Misc instructions */ + [BPF_MISC | BPF_TAX] = true, + [BPF_MISC | BPF_TXA] = true, + /* Return instructions */ + [BPF_RET | BPF_K] = true, + [BPF_RET | BPF_A] = true, + /* Jump instructions */ + [BPF_JMP | BPF_JA] = true, + [BPF_JMP | BPF_JEQ | BPF_K] = true, + [BPF_JMP | BPF_JEQ | BPF_X] = true, + [BPF_JMP | BPF_JGE | BPF_K] = true, + [BPF_JMP | BPF_JGE | BPF_X] = true, + [BPF_JMP | BPF_JGT | BPF_K] = true, + [BPF_JMP | BPF_JGT | BPF_X] = true, + [BPF_JMP | BPF_JSET | BPF_K] = true, + [BPF_JMP | BPF_JSET | BPF_X] = true, + }; + + if (code_to_probe >= ARRAY_SIZE(codes)) + return false; + + return codes[code_to_probe]; +} + /** * sk_chk_filter - verify socket filter code * @filter: filter to verify @@@ -1221,76 -1232,153 +1221,76 @@@ */ int sk_chk_filter(struct sock_filter *filter, unsigned int flen) { - /* - * Valid instructions are initialized to non-0. - * Invalid instructions are initialized to 0. - */ - static const u8 codes[] = { - [BPF_ALU|BPF_ADD|BPF_K] = BPF_S_ALU_ADD_K, - [BPF_ALU|BPF_ADD|BPF_X] = BPF_S_ALU_ADD_X, - [BPF_ALU|BPF_SUB|BPF_K] = BPF_S_ALU_SUB_K, - [BPF_ALU|BPF_SUB|BPF_X] = BPF_S_ALU_SUB_X, - [BPF_ALU|BPF_MUL|BPF_K] = BPF_S_ALU_MUL_K, - [BPF_ALU|BPF_MUL|BPF_X] = BPF_S_ALU_MUL_X, - [BPF_ALU|BPF_DIV|BPF_X] = BPF_S_ALU_DIV_X, - [BPF_ALU|BPF_MOD|BPF_K] = BPF_S_ALU_MOD_K, - [BPF_ALU|BPF_MOD|BPF_X] = BPF_S_ALU_MOD_X, - [BPF_ALU|BPF_AND|BPF_K] = BPF_S_ALU_AND_K, - [BPF_ALU|BPF_AND|BPF_X] = BPF_S_ALU_AND_X, - [BPF_ALU|BPF_OR|BPF_K] = BPF_S_ALU_OR_K, - [BPF_ALU|BPF_OR|BPF_X] = BPF_S_ALU_OR_X, - [BPF_ALU|BPF_XOR|BPF_K] = BPF_S_ALU_XOR_K, - [BPF_ALU|BPF_XOR|BPF_X] = BPF_S_ALU_XOR_X, - [BPF_ALU|BPF_LSH|BPF_K] = BPF_S_ALU_LSH_K, - [BPF_ALU|BPF_LSH|BPF_X] = BPF_S_ALU_LSH_X, - [BPF_ALU|BPF_RSH|BPF_K] = BPF_S_ALU_RSH_K, - [BPF_ALU|BPF_RSH|BPF_X] = BPF_S_ALU_RSH_X, - [BPF_ALU|BPF_NEG] = BPF_S_ALU_NEG, - [BPF_LD|BPF_W|BPF_ABS] = BPF_S_LD_W_ABS, - [BPF_LD|BPF_H|BPF_ABS] = BPF_S_LD_H_ABS, - [BPF_LD|BPF_B|BPF_ABS] = BPF_S_LD_B_ABS, - [BPF_LD|BPF_W|BPF_LEN] = BPF_S_LD_W_LEN, - [BPF_LD|BPF_W|BPF_IND] = BPF_S_LD_W_IND, - [BPF_LD|BPF_H|BPF_IND] = BPF_S_LD_H_IND, - [BPF_LD|BPF_B|BPF_IND] = BPF_S_LD_B_IND, - [BPF_LD|BPF_IMM] = BPF_S_LD_IMM, - [BPF_LDX|BPF_W|BPF_LEN] = BPF_S_LDX_W_LEN, - [BPF_LDX|BPF_B|BPF_MSH] = BPF_S_LDX_B_MSH, - [BPF_LDX|BPF_IMM] = BPF_S_LDX_IMM, - [BPF_MISC|BPF_TAX] = BPF_S_MISC_TAX, - [BPF_MISC|BPF_TXA] = BPF_S_MISC_TXA, - [BPF_RET|BPF_K] = BPF_S_RET_K, - [BPF_RET|BPF_A] = BPF_S_RET_A, - [BPF_ALU|BPF_DIV|BPF_K] = BPF_S_ALU_DIV_K, - [BPF_LD|BPF_MEM] = BPF_S_LD_MEM, - [BPF_LDX|BPF_MEM] = BPF_S_LDX_MEM, - [BPF_ST] = BPF_S_ST, - [BPF_STX] = BPF_S_STX, - [BPF_JMP|BPF_JA] = BPF_S_JMP_JA, - [BPF_JMP|BPF_JEQ|BPF_K] = BPF_S_JMP_JEQ_K, - [BPF_JMP|BPF_JEQ|BPF_X] = BPF_S_JMP_JEQ_X, - [BPF_JMP|BPF_JGE|BPF_K] = BPF_S_JMP_JGE_K, - [BPF_JMP|BPF_JGE|BPF_X] = BPF_S_JMP_JGE_X, - [BPF_JMP|BPF_JGT|BPF_K] = BPF_S_JMP_JGT_K, - [BPF_JMP|BPF_JGT|BPF_X] = BPF_S_JMP_JGT_X, - [BPF_JMP|BPF_JSET|BPF_K] = BPF_S_JMP_JSET_K, - [BPF_JMP|BPF_JSET|BPF_X] = BPF_S_JMP_JSET_X, - }; - int pc; bool anc_found; + int pc;

if (flen == 0 || flen > BPF_MAXINSNS) return -EINVAL;

- /* check the filter code now */ + /* Check the filter code now */ for (pc = 0; pc < flen; pc++) { struct sock_filter *ftest = &filter[pc]; - u16 code = ftest->code;

- if (code >= ARRAY_SIZE(codes)) - return -EINVAL; - code = codes[code]; - if (!code) + /* May we actually operate on this code? */ + if (!chk_code_allowed(ftest->code)) return -EINVAL; + /* Some instructions need special checks */ - switch (code) { - case BPF_S_ALU_DIV_K: - case BPF_S_ALU_MOD_K: - /* check for division by zero */ + switch (ftest->code) { + case BPF_ALU | BPF_DIV | BPF_K: + case BPF_ALU | BPF_MOD | BPF_K: + /* Check for division by zero */ if (ftest->k == 0) return -EINVAL; break; - case BPF_S_LD_MEM: - case BPF_S_LDX_MEM: - case BPF_S_ST: - case BPF_S_STX: - /* check for invalid memory addresses */ + case BPF_LD | BPF_MEM: + case BPF_LDX | BPF_MEM: + case BPF_ST: + case BPF_STX: + /* Check for invalid memory addresses */ if (ftest->k >= BPF_MEMWORDS) return -EINVAL; break; - case BPF_S_JMP_JA: - /* - * Note, the large ftest->k might cause loops. + case BPF_JMP | BPF_JA: + /* Note, the large ftest->k might cause loops. * Compare this with conditional jumps below, * where offsets are limited. --ANK (981016) */ - if (ftest->k >= (unsigned int)(flen-pc-1)) + if (ftest->k >= (unsigned int)(flen - pc - 1)) return -EINVAL; break; - case BPF_S_JMP_JEQ_K: - case BPF_S_JMP_JEQ_X: - case BPF_S_JMP_JGE_K: - case BPF_S_JMP_JGE_X: - case BPF_S_JMP_JGT_K: - case BPF_S_JMP_JGT_X: - case BPF_S_JMP_JSET_X: - case BPF_S_JMP_JSET_K: - /* for conditionals both must be safe */ + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP | BPF_JEQ | BPF_X: + case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JSET | BPF_K: + case BPF_JMP | BPF_JSET | BPF_X: + /* Both conditionals must be safe */ if (pc + ftest->jt + 1 >= flen || pc + ftest->jf + 1 >= flen) return -EINVAL; break; - case BPF_S_LD_W_ABS: - case BPF_S_LD_H_ABS: - case BPF_S_LD_B_ABS: + case BPF_LD | BPF_W | BPF_ABS: + case BPF_LD | BPF_H | BPF_ABS: + case BPF_LD | BPF_B | BPF_ABS: anc_found = false; -#define ANCILLARY(CODE) case SKF_AD_OFF + SKF_AD_##CODE: \ - code = BPF_S_ANC_##CODE; \ - anc_found = true; \ - break - switch (ftest->k) { - ANCILLARY(PROTOCOL); - ANCILLARY(PKTTYPE); - ANCILLARY(IFINDEX); - ANCILLARY(NLATTR); - ANCILLARY(NLATTR_NEST); - ANCILLARY(MARK); - ANCILLARY(QUEUE); - ANCILLARY(HATYPE); - ANCILLARY(RXHASH); - ANCILLARY(CPU); - ANCILLARY(ALU_XOR_X); - ANCILLARY(VLAN_TAG); - ANCILLARY(VLAN_TAG_PRESENT); - ANCILLARY(PAY_OFFSET); - } - - /* ancillary operation unknown or unsupported */ + if (bpf_anc_helper(ftest) & BPF_ANC) + anc_found = true; + /* Ancillary operation unknown or unsupported */ if (anc_found == false && ftest->k >= SKF_AD_OFF) return -EINVAL; } - ftest->code = code; }

- /* last instruction must be a RET code */ + /* Last instruction must be a RET code */ switch (filter[flen - 1].code) { - case BPF_S_RET_K: - case BPF_S_RET_A: + case BPF_RET | BPF_K: + case BPF_RET | BPF_A: return check_load_and_stores(filter, flen); } + return -EINVAL; } EXPORT_SYMBOL(sk_chk_filter); @@@ -1335,7 -1423,7 +1335,7 @@@ static void sk_filter_release_rcu(struc struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu);

sk_release_orig_filter(fp); - bpf_jit_free(fp); + sk_filter_free(fp); }

/** @@@ -1373,7 -1461,7 +1373,7 @@@ static struct sk_filter *__sk_migrate_r

fp_new = sock_kmalloc(sk, len, GFP_KERNEL); if (fp_new) { - memcpy(fp_new, fp, sizeof(struct sk_filter)); + *fp_new = *fp; /* As we're kepping orig_prog in fp_new along, * we need to make sure we're not evicting it * from the old fp. @@@ -1390,7 -1478,7 +1390,7 @@@ static struct sk_filter *__sk_migrate_f { struct sock_filter *old_prog; struct sk_filter *old_fp; - int i, err, new_len, old_len = fp->len; + int err, new_len, old_len = fp->len;

/* We are free to overwrite insns et al right here as it * won't be used at this point in time anymore internally @@@ -1400,6 -1488,13 +1400,6 @@@ BUILD_BUG_ON(sizeof(struct sock_filter) != sizeof(struct sock_filter_int));

- /* For now, we need to unfiddle BPF_S_* identifiers in place. - * This can sooner or later on be subject to removal, e.g. when - * JITs have been converted. - */ - for (i = 0; i < fp->len; i++) - sk_decode_filter(&fp->insns[i], &fp->insns[i]); - /* Conversion cannot happen on overlapping memory areas, * so we need to keep the user BPF around until the 2nd * pass. At this time, the user BPF is stored in fp->insns. @@@ -1428,6 -1523,7 +1428,6 @@@ goto out_err_free; }

- fp->bpf_func = sk_run_filter_int_skb; fp->len = new_len;

/* 2nd pass: remap sock_filter insns into sock_filter_int insns. */ @@@ -1440,8 -1536,6 +1440,8 @@@ */ goto out_err_free;

+ sk_filter_select_runtime(fp); + kfree(old_prog); return fp;

@@@ -1456,33 -1550,6 +1456,33 @@@ out_err return ERR_PTR(err); }

+void __weak bpf_int_jit_compile(struct sk_filter *prog) +{ +} + +/** + * sk_filter_select_runtime - select execution runtime for BPF program + * @fp: sk_filter populated with internal BPF program + * + * try to JIT internal BPF program, if JIT is not available select interpreter + * BPF program will be executed via SK_RUN_FILTER() macro + */ +void sk_filter_select_runtime(struct sk_filter *fp) +{ + fp->bpf_func = (void *) __sk_run_filter; + + /* Probe if internal BPF can be JITed */ + bpf_int_jit_compile(fp); +} +EXPORT_SYMBOL_GPL(sk_filter_select_runtime); + +/* free internal BPF program */ +void sk_filter_free(struct sk_filter *fp) +{ + bpf_jit_free(fp); +} +EXPORT_SYMBOL_GPL(sk_filter_free); + static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp, struct sock *sk) { @@@ -1492,8 -1559,13 +1492,13 @@@ fp->jited = 0;

err = sk_chk_filter(fp->insns, fp->len); - if (err) + if (err) { + if (sk != NULL) + sk_filter_uncharge(sk, fp); + else + kfree(fp); return ERR_PTR(err); + }

/* Probe if we can JIT compile the filter and if so, do * the compilation of the filter. @@@ -1520,7 -1592,7 +1525,7 @@@ * a negative errno code is returned. On success the return is zero. */ int sk_unattached_filter_create(struct sk_filter **pfp, - struct sock_fprog *fprog) + struct sock_fprog_kern *fprog) { unsigned int fsize = sk_filter_proglen(fprog); struct sk_filter *fp; @@@ -1641,6 -1713,83 +1646,6 @@@ int sk_detach_filter(struct sock *sk } EXPORT_SYMBOL_GPL(sk_detach_filter);

-void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to) -{ - static const u16 decodes[] = { - [BPF_S_ALU_ADD_K] = BPF_ALU|BPF_ADD|BPF_K, - [BPF_S_ALU_ADD_X] = BPF_ALU|BPF_ADD|BPF_X, - [BPF_S_ALU_SUB_K] = BPF_ALU|BPF_SUB|BPF_K, - [BPF_S_ALU_SUB_X] = BPF_ALU|BPF_SUB|BPF_X, - [BPF_S_ALU_MUL_K] = BPF_ALU|BPF_MUL|BPF_K, - [BPF_S_ALU_MUL_X] = BPF_ALU|BPF_MUL|BPF_X, - [BPF_S_ALU_DIV_X] = BPF_ALU|BPF_DIV|BPF_X, - [BPF_S_ALU_MOD_K] = BPF_ALU|BPF_MOD|BPF_K, - [BPF_S_ALU_MOD_X] = BPF_ALU|BPF_MOD|BPF_X, - [BPF_S_ALU_AND_K] = BPF_ALU|BPF_AND|BPF_K, - [BPF_S_ALU_AND_X] = BPF_ALU|BPF_AND|BPF_X, - [BPF_S_ALU_OR_K] = BPF_ALU|BPF_OR|BPF_K, - [BPF_S_ALU_OR_X] = BPF_ALU|BPF_OR|BPF_X, - [BPF_S_ALU_XOR_K] = BPF_ALU|BPF_XOR|BPF_K, - [BPF_S_ALU_XOR_X] = BPF_ALU|BPF_XOR|BPF_X, - [BPF_S_ALU_LSH_K] = BPF_ALU|BPF_LSH|BPF_K, - [BPF_S_ALU_LSH_X] = BPF_ALU|BPF_LSH|BPF_X, - [BPF_S_ALU_RSH_K] = BPF_ALU|BPF_RSH|BPF_K, - [BPF_S_ALU_RSH_X] = BPF_ALU|BPF_RSH|BPF_X, - [BPF_S_ALU_NEG] = BPF_ALU|BPF_NEG, - [BPF_S_LD_W_ABS] = BPF_LD|BPF_W|BPF_ABS, - [BPF_S_LD_H_ABS] = BPF_LD|BPF_H|BPF_ABS, - [BPF_S_LD_B_ABS] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_PROTOCOL] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_PKTTYPE] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_IFINDEX] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_NLATTR] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_NLATTR_NEST] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_MARK] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_QUEUE] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_HATYPE] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_RXHASH] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_CPU] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_ALU_XOR_X] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_VLAN_TAG] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_VLAN_TAG_PRESENT] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_PAY_OFFSET] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_LD_W_LEN] = BPF_LD|BPF_W|BPF_LEN, - [BPF_S_LD_W_IND] = BPF_LD|BPF_W|BPF_IND, - [BPF_S_LD_H_IND] = BPF_LD|BPF_H|BPF_IND, - [BPF_S_LD_B_IND] = BPF_LD|BPF_B|BPF_IND, - [BPF_S_LD_IMM] = BPF_LD|BPF_IMM, - [BPF_S_LDX_W_LEN] = BPF_LDX|BPF_W|BPF_LEN, - [BPF_S_LDX_B_MSH] = BPF_LDX|BPF_B|BPF_MSH, - [BPF_S_LDX_IMM] = BPF_LDX|BPF_IMM, - [BPF_S_MISC_TAX] = BPF_MISC|BPF_TAX, - [BPF_S_MISC_TXA] = BPF_MISC|BPF_TXA, - [BPF_S_RET_K] = BPF_RET|BPF_K, - [BPF_S_RET_A] = BPF_RET|BPF_A, - [BPF_S_ALU_DIV_K] = BPF_ALU|BPF_DIV|BPF_K, - [BPF_S_LD_MEM] = BPF_LD|BPF_MEM, - [BPF_S_LDX_MEM] = BPF_LDX|BPF_MEM, - [BPF_S_ST] = BPF_ST, - [BPF_S_STX] = BPF_STX, - [BPF_S_JMP_JA] = BPF_JMP|BPF_JA, - [BPF_S_JMP_JEQ_K] = BPF_JMP|BPF_JEQ|BPF_K, - [BPF_S_JMP_JEQ_X] = BPF_JMP|BPF_JEQ|BPF_X, - [BPF_S_JMP_JGE_K] = BPF_JMP|BPF_JGE|BPF_K, - [BPF_S_JMP_JGE_X] = BPF_JMP|BPF_JGE|BPF_X, - [BPF_S_JMP_JGT_K] = BPF_JMP|BPF_JGT|BPF_K, - [BPF_S_JMP_JGT_X] = BPF_JMP|BPF_JGT|BPF_X, - [BPF_S_JMP_JSET_K] = BPF_JMP|BPF_JSET|BPF_K, - [BPF_S_JMP_JSET_X] = BPF_JMP|BPF_JSET|BPF_X, - }; - u16 code; - - code = filt->code; - - to->code = decodes[code]; - to->jt = filt->jt; - to->jf = filt->jf; - to->k = filt->k; -} - int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, unsigned int len) { diff --combined net/core/rtnetlink.c index f31268d,f4e9037..741b22c --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@@ -798,8 -798,8 +798,8 @@@ static inline int rtnl_vfinfo_size(cons size += num_vfs * (nla_total_size(sizeof(struct ifla_vf_mac)) + nla_total_size(sizeof(struct ifla_vf_vlan)) + - nla_total_size(sizeof(struct ifla_vf_tx_rate)) + - nla_total_size(sizeof(struct ifla_vf_spoofchk))); + nla_total_size(sizeof(struct ifla_vf_spoofchk)) + + nla_total_size(sizeof(struct ifla_vf_rate))); return size; } else return 0; @@@ -1065,7 -1065,6 +1065,7 @@@ static int rtnl_fill_ifinfo(struct sk_b struct ifla_vf_info ivi; struct ifla_vf_mac vf_mac; struct ifla_vf_vlan vf_vlan; + struct ifla_vf_rate vf_rate; struct ifla_vf_tx_rate vf_tx_rate; struct ifla_vf_spoofchk vf_spoofchk; struct ifla_vf_link_state vf_linkstate; @@@ -1086,7 -1085,6 +1086,7 @@@ break; vf_mac.vf = vf_vlan.vf = + vf_rate.vf = vf_tx_rate.vf = vf_spoofchk.vf = vf_linkstate.vf = ivi.vf; @@@ -1094,9 -1092,7 +1094,9 @@@ memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac)); vf_vlan.vlan = ivi.vlan; vf_vlan.qos = ivi.qos; - vf_tx_rate.rate = ivi.tx_rate; + vf_tx_rate.rate = ivi.max_tx_rate; + vf_rate.min_tx_rate = ivi.min_tx_rate; + vf_rate.max_tx_rate = ivi.max_tx_rate; vf_spoofchk.setting = ivi.spoofchk; vf_linkstate.link_state = ivi.linkstate; vf = nla_nest_start(skb, IFLA_VF_INFO); @@@ -1106,8 -1102,6 +1106,8 @@@ } if (nla_put(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac) || nla_put(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan) || + nla_put(skb, IFLA_VF_RATE, sizeof(vf_rate), + &vf_rate) || nla_put(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate), &vf_tx_rate) || nla_put(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk), @@@ -1214,8 -1208,6 +1214,8 @@@ static const struct nla_policy ifla_vf_ .len = sizeof(struct ifla_vf_tx_rate) }, [IFLA_VF_SPOOFCHK] = { .type = NLA_BINARY, .len = sizeof(struct ifla_vf_spoofchk) }, + [IFLA_VF_RATE] = { .type = NLA_BINARY, + .len = sizeof(struct ifla_vf_rate) }, };

static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = { @@@ -1375,29 -1367,11 +1375,29 @@@ static int do_setvfinfo(struct net_devi } case IFLA_VF_TX_RATE: { struct ifla_vf_tx_rate *ivt; + struct ifla_vf_info ivf; ivt = nla_data(vf); err = -EOPNOTSUPP; - if (ops->ndo_set_vf_tx_rate) - err = ops->ndo_set_vf_tx_rate(dev, ivt->vf, - ivt->rate); + if (ops->ndo_get_vf_config) + err = ops->ndo_get_vf_config(dev, ivt->vf, + &ivf); + if (err) + break; + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_rate) + err = ops->ndo_set_vf_rate(dev, ivt->vf, + ivf.min_tx_rate, + ivt->rate); + break; + } + case IFLA_VF_RATE: { + struct ifla_vf_rate *ivt; + ivt = nla_data(vf); + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_rate) + err = ops->ndo_set_vf_rate(dev, ivt->vf, + ivt->min_tx_rate, + ivt->max_tx_rate); break; } case IFLA_VF_SPOOFCHK: { @@@ -2045,11 -2019,15 +2045,15 @@@ replay if (ops->newlink) { err = ops->newlink(net, dev, tb, data); /* Drivers should call free_netdev() in ->destructor - * and unregister it on failure so that device could be - * finally freed in rtnl_unlock. + * and unregister it on failure after registration + * so that device could be finally freed in rtnl_unlock. */ - if (err < 0) + if (err < 0) { + /* If device is not registered at all, free it now */ + if (dev->reg_state == NETREG_UNINITIALIZED) + free_netdev(dev); goto out; + } } else { err = register_netdevice(dev); if (err < 0) { diff --combined net/ipv4/tcp_input.c index 350b207,3a26b3b..931529d --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@@ -2684,13 -2684,12 +2684,12 @@@ static void tcp_process_loss(struct soc bool recovered = !before(tp->snd_una, tp->high_seq);

if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */ - if (flag & FLAG_ORIG_SACK_ACKED) { - /* Step 3.b. A timeout is spurious if not all data are - * lost, i.e., never-retransmitted data are (s)acked. - */ - tcp_try_undo_loss(sk, true); + /* Step 3.b. A timeout is spurious if not all data are + * lost, i.e., never-retransmitted data are (s)acked. + */ + if (tcp_try_undo_loss(sk, flag & FLAG_ORIG_SACK_ACKED)) return; - } + if (after(tp->snd_nxt, tp->high_seq) && (flag & FLAG_DATA_SACKED || is_dupack)) { tp->frto = 0; /* Loss was real: 2nd part of step 3.a */ @@@ -2938,11 -2937,10 +2937,11 @@@ static void tcp_synack_rtt_meas(struct tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt_us, -1L); }

-static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight) +static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) { const struct inet_connection_sock *icsk = inet_csk(sk); - icsk->icsk_ca_ops->cong_avoid(sk, ack, acked, in_flight); + + icsk->icsk_ca_ops->cong_avoid(sk, ack, acked); tcp_sk(sk)->snd_cwnd_stamp = tcp_time_stamp; }

@@@ -3365,6 -3363,7 +3364,6 @@@ static int tcp_ack(struct sock *sk, con u32 ack_seq = TCP_SKB_CB(skb)->seq; u32 ack = TCP_SKB_CB(skb)->ack_seq; bool is_dupack = false; - u32 prior_in_flight; u32 prior_fackets; int prior_packets = tp->packets_out; const int prior_unsacked = tp->packets_out - tp->sacked_out; @@@ -3397,6 -3396,7 +3396,6 @@@ flag |= FLAG_SND_UNA_ADVANCED;

prior_fackets = tp->fackets_out; - prior_in_flight = tcp_packets_in_flight(tp);

/* ts_recent update must be made after we are sure that the packet * is in window. @@@ -3451,7 -3451,7 +3450,7 @@@

/* Advance cwnd if state allows */ if (tcp_may_raise_cwnd(sk, flag)) - tcp_cong_avoid(sk, ack, acked, prior_in_flight); + tcp_cong_avoid(sk, ack, acked);

if (tcp_ack_is_dubious(sk, flag)) { is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); @@@ -4702,6 -4702,28 +4701,6 @@@ static int tcp_prune_queue(struct sock return -1; }

-/* RFC2861, slow part. Adjust cwnd, after it was not full during one rto. - * As additional protections, we do not touch cwnd in retransmission phases, - * and if application hit its sndbuf limit recently. - */ -void tcp_cwnd_application_limited(struct sock *sk) -{ - struct tcp_sock *tp = tcp_sk(sk); - - if (inet_csk(sk)->icsk_ca_state == TCP_CA_Open && - sk->sk_socket && !test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { - /* Limited by application or receiver window. */ - u32 init_win = tcp_init_cwnd(tp, __sk_dst_get(sk)); - u32 win_used = max(tp->snd_cwnd_used, init_win); - if (win_used < tp->snd_cwnd) { - tp->snd_ssthresh = tcp_current_ssthresh(sk); - tp->snd_cwnd = (tp->snd_cwnd + win_used) >> 1; - } - tp->snd_cwnd_used = 0; - } - tp->snd_cwnd_stamp = tcp_time_stamp; -} - static bool tcp_should_expand_sndbuf(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); diff --combined net/ipv6/output_core.c index 6179ac1,56596ce..ffa0293 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@@ -8,7 -8,32 +8,6 @@@ #include <net/addrconf.h> #include <net/secure_seq.h>

- -void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) -{ - static atomic_t ipv6_fragmentation_id; - struct in6_addr addr; - int ident; - -#if IS_ENABLED(CONFIG_IPV6) - struct inet_peer *peer; - struct net *net; - - net = dev_net(rt->dst.dev); - peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); - if (peer) { - fhdr->identification = htonl(inet_getid(peer, 0)); - inet_putpeer(peer); - return; - } -#endif - ident = atomic_inc_return(&ipv6_fragmentation_id); - - addr = rt->rt6i_dst.addr; - addr.s6_addr32[0] ^= (__force __be32)ident; - fhdr->identification = htonl(secure_ipv6_id(addr.s6_addr32)); -} -EXPORT_SYMBOL(ipv6_select_ident); - int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) { u16 offset = sizeof(struct ipv6hdr); diff --combined net/netfilter/ipvs/ip_vs_core.c index d9da8c4,3d2d2c8..e683675 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@@ -97,7 -97,7 +97,7 @@@ const char *ip_vs_proto_name(unsigned i return "ICMPv6"; #endif default: - sprintf(buf, "IP_%d", proto); + sprintf(buf, "IP_%u", proto); return buf; } } @@@ -1392,15 -1392,19 +1392,19 @@@ ip_vs_in_icmp(struct sk_buff *skb, int

if (ipip) { __be32 info = ic->un.gateway; + __u8 type = ic->type; + __u8 code = ic->code;

/* Update the MTU */ if (ic->type == ICMP_DEST_UNREACH && ic->code == ICMP_FRAG_NEEDED) { struct ip_vs_dest *dest = cp->dest; u32 mtu = ntohs(ic->un.frag.mtu); + __be16 frag_off = cih->frag_off;

/* Strip outer IP and ICMP, go to IPIP header */ - __skb_pull(skb, ihl + sizeof(_icmph)); + if (pskb_pull(skb, ihl + sizeof(_icmph)) == NULL) + goto ignore_ipip; offset2 -= ihl + sizeof(_icmph); skb_reset_network_header(skb); IP_VS_DBG(12, "ICMP for IPIP %pI4->%pI4: mtu=%u\n", @@@ -1408,7 -1412,7 +1412,7 @@@ ipv4_update_pmtu(skb, dev_net(skb->dev), mtu, 0, 0, 0, 0); /* Client uses PMTUD? */ - if (!(cih->frag_off & htons(IP_DF))) + if (!(frag_off & htons(IP_DF))) goto ignore_ipip; /* Prefer the resulting PMTU */ if (dest) { @@@ -1427,12 -1431,13 +1431,13 @@@ /* Strip outer IP, ICMP and IPIP, go to IP header of * original request. */ - __skb_pull(skb, offset2); + if (pskb_pull(skb, offset2) == NULL) + goto ignore_ipip; skb_reset_network_header(skb); IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n", &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, - ic->type, ic->code, ntohl(info)); - icmp_send(skb, ic->type, ic->code, info); + type, code, ntohl(info)); + icmp_send(skb, type, code, info); /* ICMP can be shorter but anyways, account it */ ip_vs_out_stats(cp, skb);

diff --combined net/netlink/af_netlink.c index e0ccd84,f22757a..15c731f --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@@ -1206,8 -1206,7 +1206,8 @@@ static int netlink_create(struct net *n struct module *module = NULL; struct mutex *cb_mutex; struct netlink_sock *nlk; - void (*bind)(int group); + int (*bind)(int group); + void (*unbind)(int group); int err = 0;

sock->state = SS_UNCONNECTED; @@@ -1233,7 -1232,6 +1233,7 @@@ err = -EPROTONOSUPPORT; cb_mutex = nl_table[protocol].cb_mutex; bind = nl_table[protocol].bind; + unbind = nl_table[protocol].unbind; netlink_unlock_table();

if (err < 0) @@@ -1250,7 -1248,6 +1250,7 @@@ nlk = nlk_sk(sock->sk); nlk->module = module; nlk->netlink_bind = bind; + nlk->netlink_unbind = unbind; out: return err;

@@@ -1304,7 -1301,6 +1304,7 @@@ static int netlink_release(struct socke kfree_rcu(old, rcu); nl_table[sk->sk_protocol].module = NULL; nl_table[sk->sk_protocol].bind = NULL; + nl_table[sk->sk_protocol].unbind = NULL; nl_table[sk->sk_protocol].flags = 0; nl_table[sk->sk_protocol].registered = 0; } @@@ -1377,7 -1373,9 +1377,9 @@@ retry bool __netlink_ns_capable(const struct netlink_skb_parms *nsp, struct user_namespace *user_ns, int cap) { - return sk_ns_capable(nsp->sk, user_ns, cap); + return ((nsp->flags & NETLINK_SKB_DST) || + file_ns_capable(nsp->sk->sk_socket->file, user_ns, cap)) && + ns_capable(user_ns, cap); } EXPORT_SYMBOL(__netlink_ns_capable);

@@@ -1480,19 -1478,6 +1482,19 @@@ static int netlink_realloc_groups(struc return err; }

+static void netlink_unbind(int group, long unsigned int groups, + struct netlink_sock *nlk) +{ + int undo; + + if (!nlk->netlink_unbind) + return; + + for (undo = 0; undo < group; undo++) + if (test_bit(group, &groups)) + nlk->netlink_unbind(undo); +} + static int netlink_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { @@@ -1501,7 -1486,6 +1503,7 @@@ struct netlink_sock *nlk = nlk_sk(sk); struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr; int err; + long unsigned int groups = nladdr->nl_groups;

if (addr_len < sizeof(struct sockaddr_nl)) return -EINVAL; @@@ -1510,7 -1494,7 +1512,7 @@@ return -EINVAL;

/* Only superuser is allowed to listen multicasts */ - if (nladdr->nl_groups) { + if (groups) { if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV)) return -EPERM; err = netlink_realloc_groups(sk); @@@ -1518,45 -1502,37 +1520,45 @@@ return err; }

- if (nlk->portid) { + if (nlk->portid) if (nladdr->nl_pid != nlk->portid) return -EINVAL; - } else { + + if (nlk->netlink_bind && groups) { + int group; + + for (group = 0; group < nlk->ngroups; group++) { + if (!test_bit(group, &groups)) + continue; + err = nlk->netlink_bind(group); + if (!err) + continue; + netlink_unbind(group, groups, nlk); + return err; + } + } + + if (!nlk->portid) { err = nladdr->nl_pid ? netlink_insert(sk, net, nladdr->nl_pid) : netlink_autobind(sock); - if (err) + if (err) { + netlink_unbind(nlk->ngroups - 1, groups, nlk); return err; + } }

- if (!nladdr->nl_groups && (nlk->groups == NULL || !(u32)nlk->groups[0])) + if (!groups && (nlk->groups == NULL || !(u32)nlk->groups[0])) return 0;

netlink_table_grab(); netlink_update_subscriptions(sk, nlk->subscriptions + - hweight32(nladdr->nl_groups) - + hweight32(groups) - hweight32(nlk->groups[0])); - nlk->groups[0] = (nlk->groups[0] & ~0xffffffffUL) | nladdr->nl_groups; + nlk->groups[0] = (nlk->groups[0] & ~0xffffffffUL) | groups; netlink_update_listeners(sk); netlink_table_ungrab();

- if (nlk->netlink_bind && nlk->groups[0]) { - int i; - - for (i = 0; i < nlk->ngroups; i++) { - if (test_bit(i, nlk->groups)) - nlk->netlink_bind(i); - } - } - return 0; }

@@@ -2194,17 -2170,13 +2196,17 @@@ static int netlink_setsockopt(struct so return err; if (!val || val - 1 >= nlk->ngroups) return -EINVAL; + if (optname == NETLINK_ADD_MEMBERSHIP && nlk->netlink_bind) { + err = nlk->netlink_bind(val); + if (err) + return err; + } netlink_table_grab(); netlink_update_socket_mc(nlk, val, optname == NETLINK_ADD_MEMBERSHIP); netlink_table_ungrab(); - - if (nlk->netlink_bind) - nlk->netlink_bind(val); + if (optname == NETLINK_DROP_MEMBERSHIP && nlk->netlink_unbind) + nlk->netlink_unbind(val);

err = 0; break; @@@ -2323,6 -2295,7 +2325,7 @@@ static int netlink_sendmsg(struct kioc struct sk_buff *skb; int err; struct scm_cookie scm; + u32 netlink_skb_flags = 0;

if (msg->msg_flags&MSG_OOB) return -EOPNOTSUPP; @@@ -2344,6 -2317,7 +2347,7 @@@ if ((dst_group || dst_portid) && !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) goto out; + netlink_skb_flags |= NETLINK_SKB_DST; } else { dst_portid = nlk->dst_portid; dst_group = nlk->dst_group; @@@ -2373,6 -2347,7 +2377,7 @@@ NETLINK_CB(skb).portid = nlk->portid; NETLINK_CB(skb).dst_group = dst_group; NETLINK_CB(skb).creds = siocb->scm->creds; + NETLINK_CB(skb).flags = netlink_skb_flags;

err = -EFAULT; if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) { diff --combined net/xfrm/xfrm_user.c index fd9a16a,09336b2..412d9dc --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@@ -597,6 -597,9 +597,6 @@@ static int xfrm_add_sa(struct sk_buff * struct xfrm_state *x; int err; struct km_event c; - kuid_t loginuid = audit_get_loginuid(current); - unsigned int sessionid = audit_get_sessionid(current); - u32 sid;

err = verify_newsa_info(p, attrs); if (err) @@@ -612,7 -615,8 +612,7 @@@ else err = xfrm_state_update(x);

- security_task_getsecid(current, &sid); - xfrm_audit_state_add(x, err ? 0 : 1, loginuid, sessionid, sid); + xfrm_audit_state_add(x, err ? 0 : 1, true);

if (err < 0) { x->km.state = XFRM_STATE_DEAD; @@@ -672,6 -676,9 +672,6 @@@ static int xfrm_del_sa(struct sk_buff * int err = -ESRCH; struct km_event c; struct xfrm_usersa_id *p = nlmsg_data(nlh); - kuid_t loginuid = audit_get_loginuid(current); - unsigned int sessionid = audit_get_sessionid(current); - u32 sid;

x = xfrm_user_state_lookup(net, p, attrs, &err); if (x == NULL) @@@ -696,7 -703,8 +696,7 @@@ km_state_notify(x, &c);

out: - security_task_getsecid(current, &sid); - xfrm_audit_state_delete(x, err ? 0 : 1, loginuid, sessionid, sid); + xfrm_audit_state_delete(x, err ? 0 : 1, true); xfrm_state_put(x); return err; } @@@ -947,6 -955,20 +947,20 @@@ static struct sk_buff *xfrm_state_netli return skb; }

+ /* A wrapper for nlmsg_multicast() checking that nlsk is still available. + * Must be called with RCU read lock. + */ + static inline int xfrm_nlmsg_multicast(struct net *net, struct sk_buff *skb, + u32 pid, unsigned int group) + { + struct sock *nlsk = rcu_dereference(net->xfrm.nlsk); + + if (nlsk) + return nlmsg_multicast(nlsk, skb, pid, group, GFP_ATOMIC); + else + return -1; + } + static inline size_t xfrm_spdinfo_msgsize(void) { return NLMSG_ALIGN(4) @@@ -1406,6 -1428,9 +1420,6 @@@ static int xfrm_add_policy(struct sk_bu struct km_event c; int err; int excl; - kuid_t loginuid = audit_get_loginuid(current); - unsigned int sessionid = audit_get_sessionid(current); - u32 sid;

err = verify_newpolicy_info(p); if (err) @@@ -1424,7 -1449,8 +1438,7 @@@ * a type XFRM_MSG_UPDPOLICY - JHS */ excl = nlh->nlmsg_type == XFRM_MSG_NEWPOLICY; err = xfrm_policy_insert(p->dir, xp, excl); - security_task_getsecid(current, &sid); - xfrm_audit_policy_add(xp, err ? 0 : 1, loginuid, sessionid, sid); + xfrm_audit_policy_add(xp, err ? 0 : 1, true);

if (err) { security_xfrm_policy_free(xp->security); @@@ -1661,7 -1687,13 +1675,7 @@@ static int xfrm_get_policy(struct sk_bu NETLINK_CB(skb).portid); } } else { - kuid_t loginuid = audit_get_loginuid(current); - unsigned int sessionid = audit_get_sessionid(current); - u32 sid; - - security_task_getsecid(current, &sid); - xfrm_audit_policy_delete(xp, err ? 0 : 1, loginuid, sessionid, - sid); + xfrm_audit_policy_delete(xp, err ? 0 : 1, true);

if (err != 0) goto out; @@@ -1686,9 -1718,13 +1700,9 @@@ static int xfrm_flush_sa(struct sk_buf struct net *net = sock_net(skb->sk); struct km_event c; struct xfrm_usersa_flush *p = nlmsg_data(nlh); - struct xfrm_audit audit_info; int err;

- audit_info.loginuid = audit_get_loginuid(current); - audit_info.sessionid = audit_get_sessionid(current); - security_task_getsecid(current, &audit_info.secid); - err = xfrm_state_flush(net, p->proto, &audit_info); + err = xfrm_state_flush(net, p->proto, true); if (err) { if (err == -ESRCH) /* empty table */ return 0; @@@ -1872,12 -1908,16 +1886,12 @@@ static int xfrm_flush_policy(struct sk_ struct km_event c; u8 type = XFRM_POLICY_TYPE_MAIN; int err; - struct xfrm_audit audit_info;

err = copy_from_user_policy_type(&type, attrs); if (err) return err;

- audit_info.loginuid = audit_get_loginuid(current); - audit_info.sessionid = audit_get_sessionid(current); - security_task_getsecid(current, &audit_info.secid); - err = xfrm_policy_flush(net, type, &audit_info); + err = xfrm_policy_flush(net, type, true); if (err) { if (err == -ESRCH) /* empty table */ return 0; @@@ -1943,8 -1983,14 +1957,8 @@@ static int xfrm_add_pol_expire(struct s

err = 0; if (up->hard) { - kuid_t loginuid = audit_get_loginuid(current); - unsigned int sessionid = audit_get_sessionid(current); - u32 sid; - - security_task_getsecid(current, &sid); xfrm_policy_delete(xp, p->dir); - xfrm_audit_policy_delete(xp, 1, loginuid, sessionid, sid); - + xfrm_audit_policy_delete(xp, 1, true); } else { // reset the timers here? WARN(1, "Dont know what to do with soft policy expire\n"); @@@ -1980,8 -2026,13 +1994,8 @@@ static int xfrm_add_sa_expire(struct sk km_state_expired(x, ue->hard, nlh->nlmsg_pid);

if (ue->hard) { - kuid_t loginuid = audit_get_loginuid(current); - unsigned int sessionid = audit_get_sessionid(current); - u32 sid; - - security_task_getsecid(current, &sid); __xfrm_state_delete(x); - xfrm_audit_state_delete(x, 1, loginuid, sessionid, sid); + xfrm_audit_state_delete(x, 1, true); } err = 0; out: @@@ -2228,7 -2279,7 +2242,7 @@@ static int xfrm_send_migrate(const stru if (build_migrate(skb, m, num_migrate, k, sel, dir, type) < 0) BUG();

- return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_MIGRATE, GFP_ATOMIC); + return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_MIGRATE); } #else static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, @@@ -2419,7 -2470,7 +2433,7 @@@ static int xfrm_exp_state_notify(struc return -EMSGSIZE; }

- return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_EXPIRE, GFP_ATOMIC); + return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_EXPIRE); }

static int xfrm_aevent_state_notify(struct xfrm_state *x, const struct km_event *c) @@@ -2434,7 -2485,7 +2448,7 @@@ if (build_aevent(skb, x, c) < 0) BUG();

- return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_AEVENTS, GFP_ATOMIC); + return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_AEVENTS); }

static int xfrm_notify_sa_flush(const struct km_event *c) @@@ -2460,7 -2511,7 +2474,7 @@@

nlmsg_end(skb, nlh);

- return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_SA, GFP_ATOMIC); + return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_SA); }

static inline size_t xfrm_sa_len(struct xfrm_state *x) @@@ -2547,7 -2598,7 +2561,7 @@@ static int xfrm_notify_sa(struct xfrm_s

nlmsg_end(skb, nlh);

- return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_SA, GFP_ATOMIC); + return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_SA);

out_free_skb: kfree_skb(skb); @@@ -2638,7 -2689,7 +2652,7 @@@ static int xfrm_send_acquire(struct xfr if (build_acquire(skb, x, xt, xp) < 0) BUG();

- return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_ACQUIRE, GFP_ATOMIC); + return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_ACQUIRE); }

/* User gives us xfrm_user_policy_info followed by an array of 0 @@@ -2752,7 -2803,7 +2766,7 @@@ static int xfrm_exp_policy_notify(struc if (build_polexpire(skb, xp, dir, c) < 0) BUG();

- return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_EXPIRE, GFP_ATOMIC); + return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_EXPIRE); }

static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_event *c) @@@ -2814,7 -2865,7 +2828,7 @@@

nlmsg_end(skb, nlh);

- return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_POLICY, GFP_ATOMIC); + return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_POLICY);

out_free_skb: kfree_skb(skb); @@@ -2842,7 -2893,7 +2856,7 @@@ static int xfrm_notify_policy_flush(con

nlmsg_end(skb, nlh);

- return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_POLICY, GFP_ATOMIC); + return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_POLICY);

out_free_skb: kfree_skb(skb); @@@ -2911,7 -2962,7 +2925,7 @@@ static int xfrm_send_report(struct net if (build_report(skb, proto, sel, addr) < 0) BUG();

- return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_REPORT, GFP_ATOMIC); + return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_REPORT); }

static inline size_t xfrm_mapping_msgsize(void) @@@ -2963,7 -3014,7 +2977,7 @@@ static int xfrm_send_mapping(struct xfr if (build_mapping(skb, x, ipaddr, sport) < 0) BUG();

- return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_MAPPING, GFP_ATOMIC); + return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_MAPPING); }

static bool xfrm_is_alive(const struct km_event *c)