From 848ef58695d8c013f24633352586279cfb40e9d9 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Tue, 1 Apr 2014 17:02:53 +0300 Subject: net: rfkill: gpio: remove unused and obsolete platform parameters After upgrading to descriptor based gpios, the gpio numbers are not used anymore. The power_clk_name and the platform specific setup and close hooks are not used by anybody, and we should not encourage use of such things, so removing them. Acked-by: Alexandre Courbot Reviewed-by: Linus Walleij Signed-off-by: Heikki Krogerus Signed-off-by: Johannes Berg --- include/linux/rfkill-gpio.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rfkill-gpio.h b/include/linux/rfkill-gpio.h index 4d09f6eab359..20bcb55498cd 100644 --- a/include/linux/rfkill-gpio.h +++ b/include/linux/rfkill-gpio.h @@ -27,21 +27,11 @@ * struct rfkill_gpio_platform_data - platform data for rfkill gpio device. * for unused gpio's, the expected value is -1. * @name: name for the gpio rf kill instance - * @reset_gpio: GPIO which is used for reseting rfkill switch - * @shutdown_gpio: GPIO which is used for shutdown of rfkill switch - * @power_clk_name: [optional] name of clk to turn off while blocked - * @gpio_runtime_close: clean up platform specific gpio configuration - * @gpio_runtime_setup: set up platform specific gpio configuration */ struct rfkill_gpio_platform_data { char *name; - int reset_gpio; - int shutdown_gpio; - const char *power_clk_name; enum rfkill_type type; - void (*gpio_runtime_close)(struct platform_device *); - int (*gpio_runtime_setup)(struct platform_device *); }; #endif /* __RFKILL_GPIO_H */ -- cgit v1.2.3 From af6b6967d6e17fe070c0fd1be364c34cbd31a523 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Wed, 16 Apr 2014 17:19:12 +0200 Subject: net: phy: export genphy_config_init() This enables other drivers to call this generic implementation, and then only do specific details on top of it. Signed-off-by: Daniel Mack Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 4d0221fd0688..51d15f684e7e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -666,6 +666,7 @@ static inline int phy_read_status(struct phy_device *phydev) return phydev->drv->read_status(phydev); } +int genphy_config_init(struct phy_device *phydev); int genphy_setup_forced(struct phy_device *phydev); int genphy_restart_aneg(struct phy_device *phydev); int genphy_config_aneg(struct phy_device *phydev); -- cgit v1.2.3 From a0265d28b3a5877b5b8edd14eb12a2ccb60ab1f3 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 17 Apr 2014 13:45:03 +0800 Subject: net: Add __dev_forward_skb This patch adds the helper __dev_forward_skb which is identical to dev_forward_skb except that it doesn't actually inject the skb into the stack. This is useful where we wish to have finer control over how the packet is injected, e.g., via netif_rx_ni or netif_receive_skb. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7ed3a3aa6604..a803d792df1e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2633,6 +2633,7 @@ int dev_get_phys_port_id(struct net_device *dev, struct netdev_phys_port_id *ppid); int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq); +int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); bool is_skb_forwardable(struct net_device *dev, struct sk_buff *skb); -- cgit v1.2.3 From 68957303f44a501af5cf37913208a2acaa6bcdf1 Mon Sep 17 00:00:00 2001 From: Christophe Ricard Date: Tue, 25 Mar 2014 06:51:47 +0100 Subject: NFC: ST21NFCA: Add driver for STMicroelectronics ST21NFCA NFC Chip Add driver for STMicroelectronics ST21NFCA NFC controller. ST21NFCA is using HCI protocol, shdlc as LLC layer & I2C as communication protocol. Adding support for Reader/Writer mode with Tag type 1/2/3/4 A & B. It is using proprietary gate 15 for ISO14443-3 such as type 1 & type 2 tags. It is using proprietary gate 14 for type F tags. ST21NFCA_DEVICE_MGNT_GATE gives access to proprietary CLF configuration. Standard gate for ISO14443-4 A (13) & B (11) are also used. ST21NFCA specific mecanism: One particular point to notice for the data handling is that frame does not contain any length value. Therefore the i2c part of this driver is managing the reception with a read length sequence until the end of frame (0x7e) is reached. In order to avoid conflict between sof & eof a mecanism called byte stuffing concist of an escape byte (0x7d) insertion before special byte (0x7e, 0x7d). The special byte is then xored with 0x20. In this driver, When data are available in the CLF, the interrupt gpio is driven to active state and triggered an interrupt. Once the i2c_master_recv start, the interrupt gpio is driven to idle state until its complete. If the frame is incomplete or data are still available, interrupts will be triggered again. Signed-off-by: Christophe Ricard Signed-off-by: Samuel Ortiz --- include/linux/platform_data/st21nfca.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) create mode 100644 include/linux/platform_data/st21nfca.h (limited to 'include/linux') diff --git a/include/linux/platform_data/st21nfca.h b/include/linux/platform_data/st21nfca.h new file mode 100644 index 000000000000..1730312398ff --- /dev/null +++ b/include/linux/platform_data/st21nfca.h @@ -0,0 +1,32 @@ +/* + * Driver include for the ST21NFCA NFC chip. + * + * Copyright (C) 2014 STMicroelectronics SAS. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see . + */ + +#ifndef _ST21NFCA_HCI_H_ +#define _ST21NFCA_HCI_H_ + +#include + +#define ST21NFCA_HCI_DRIVER_NAME "st21nfca_hci" + +struct st21nfca_nfc_platform_data { + unsigned int gpio_irq; + unsigned int gpio_ena; + unsigned int irq_polarity; +}; + +#endif /* _ST21NFCA_HCI_H_ */ -- cgit v1.2.3 From 3de0b592394d17b2c41a261a6a493a521213f299 Mon Sep 17 00:00:00 2001 From: Venkata Duvvuru Date: Mon, 21 Apr 2014 15:37:59 +0530 Subject: ethtool: Support for configurable RSS hash key This ethtool patch primarily copies the ioctl command data structures from/to the User space and invokes the driver hook. Signed-off-by: Venkat Duvvuru Signed-off-by: David S. Miller --- include/linux/ethtool.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 0a114d05f68d..212f537fc686 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -154,13 +154,23 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings) * @reset: Reset (part of) the device, as specified by a bitmask of * flags from &enum ethtool_reset_flags. Returns a negative * error code or zero. + * @get_rxfh_key_size: Get the size of the RX flow hash key. + * Returns zero if not supported for this specific device. * @get_rxfh_indir_size: Get the size of the RX flow hash indirection table. * Returns zero if not supported for this specific device. * @get_rxfh_indir: Get the contents of the RX flow hash indirection table. * Will not be called if @get_rxfh_indir_size returns zero. + * @get_rxfh: Get the contents of the RX flow hash indirection table and hash + * key. + * Will not be called if @get_rxfh_indir_size and @get_rxfh_key_size + * returns zero. * Returns a negative error code or zero. * @set_rxfh_indir: Set the contents of the RX flow hash indirection table. * Will not be called if @get_rxfh_indir_size returns zero. + * @set_rxfh: Set the contents of the RX flow hash indirection table and + * hash key. + * Will not be called if @get_rxfh_indir_size and @get_rxfh_key_size + * returns zero. * Returns a negative error code or zero. * @get_channels: Get number of channels. * @set_channels: Set number of channels. Returns a negative error code or @@ -232,7 +242,10 @@ struct ethtool_ops { int (*set_rxnfc)(struct net_device *, struct ethtool_rxnfc *); int (*flash_device)(struct net_device *, struct ethtool_flash *); int (*reset)(struct net_device *, u32 *); + u32 (*get_rxfh_key_size)(struct net_device *); u32 (*get_rxfh_indir_size)(struct net_device *); + int (*get_rxfh)(struct net_device *, u32 *, u8 *); + int (*set_rxfh)(struct net_device *, u32 *, u8 *); int (*get_rxfh_indir)(struct net_device *, u32 *); int (*set_rxfh_indir)(struct net_device *, const u32 *); void (*get_channels)(struct net_device *, struct ethtool_channels *); -- cgit v1.2.3 From 4cd3675ebf74d7f559038ded6aa8088e4099a83d Mon Sep 17 00:00:00 2001 From: Chema Gonzalez Date: Mon, 21 Apr 2014 09:21:24 -0700 Subject: filter: added BPF random opcode Added a new ancillary load (bpf call in eBPF parlance) that produces a 32-bit random number. We are implementing it as an ancillary load (instead of an ISA opcode) because (a) it is simpler, (b) allows easy JITing, and (c) seems more in line with generic ISAs that do not have "get a random number" as a instruction, but as an OS call. The main use for this ancillary load is to perform random packet sampling. Signed-off-by: Chema Gonzalez Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/filter.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 024fd03e5d18..759abf78dd61 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -223,6 +223,7 @@ enum { BPF_S_ANC_VLAN_TAG, BPF_S_ANC_VLAN_TAG_PRESENT, BPF_S_ANC_PAY_OFFSET, + BPF_S_ANC_RANDOM, }; #endif /* __LINUX_FILTER_H__ */ -- cgit v1.2.3 From 4f520900522fd596e336c07e9aafd5b7a9564235 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Tue, 22 Apr 2014 21:31:54 -0400 Subject: netlink: have netlink per-protocol bind function return an error code. Have the netlink per-protocol optional bind function return an int error code rather than void to signal a failure. This will enable netlink protocols to perform extra checks including capabilities and permissions verifications when updating memberships in multicast groups. In netlink_bind() and netlink_setsockopt() the call to the per-protocol bind function was moved above the multicast group update to prevent any access to the multicast socket groups before checking with the per-protocol bind function. This will enable the per-protocol bind function to be used to check permissions which could be denied before making them available, and to avoid the messy job of undoing the addition should the per-protocol bind function fail. The netfilter subsystem seems to be the only one currently using the per-protocol bind function. Signed-off-by: Richard Guy Briggs Signed-off-by: David S. Miller --- include/linux/netlink.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index aad8eeaf416d..5146ce066498 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -45,7 +45,8 @@ 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); }; -- cgit v1.2.3 From 4af619ae2ccf47a2b3a108e1926736484721370f Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Thu, 24 Apr 2014 19:09:05 +0200 Subject: at86rf230: use irq_get_trigger_type This patch removes the platform data for the irq_type. We use instead the irq_get_trigger_type function to get these flags which should already configured by the interrupt controller. Signed-off-by: Alexander Aring Signed-off-by: David S. Miller --- include/linux/spi/at86rf230.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/at86rf230.h b/include/linux/spi/at86rf230.h index aa327a8105ad..b2b1afbb3202 100644 --- a/include/linux/spi/at86rf230.h +++ b/include/linux/spi/at86rf230.h @@ -26,20 +26,6 @@ struct at86rf230_platform_data { int rstn; int slp_tr; int dig2; - - /* Setting the irq_type will configure the driver to request - * the platform irq trigger type according to the given value - * and configure the interrupt polarity of the device to the - * corresponding polarity. - * - * Allowed values are: IRQF_TRIGGER_RISING, IRQF_TRIGGER_FALLING, - * IRQF_TRIGGER_HIGH and IRQF_TRIGGER_LOW - * - * Setting it to 0, the driver does not touch the trigger type - * configuration of the interrupt and sets the interrupt polarity - * of the device to high active (the default value). - */ - int irq_type; }; #endif -- cgit v1.2.3 From 683399eddb9fff742b1a14c5a5d03e12bfc0afff Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Sun, 20 Apr 2014 18:57:36 -0600 Subject: netfilter: nfnetlink_acct: Adding quota support to accounting framework nfacct objects already support accounting at the byte and packet level. As such it is a natural extension to add the possiblity to define a ceiling limit for both metrics. All the support for quotas itself is added to nfnetlink acctounting framework to stay coherent with current accounting object management. Quota limit checks are implemented in xt_nfacct filter where statistic collection is already done. Pablo Neira Ayuso has also contributed to this feature. Signed-off-by: Mathieu Poirier Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink_acct.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_acct.h b/include/linux/netfilter/nfnetlink_acct.h index b2e85e59f760..6ec975748742 100644 --- a/include/linux/netfilter/nfnetlink_acct.h +++ b/include/linux/netfilter/nfnetlink_acct.h @@ -3,11 +3,17 @@ #include +enum { + NFACCT_NO_QUOTA = -1, + NFACCT_UNDERQUOTA, + NFACCT_OVERQUOTA, +}; struct nf_acct; struct nf_acct *nfnl_acct_find_get(const char *filter_name); void nfnl_acct_put(struct nf_acct *acct); void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct); - +extern int nfnl_acct_overquota(const struct sk_buff *skb, + struct nf_acct *nfacct); #endif /* _NFNL_ACCT_H */ -- cgit v1.2.3 From 6d48f44b7b2af67b33c1ae5994b8f642685c8bc8 Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Wed, 30 Apr 2014 15:23:33 +0300 Subject: mdio_bus: implement devm_mdiobus_alloc/devm_mdiobus_free Add a resource managed devm_mdiobus_alloc[_size]()/devm_mdiobus_free() to automatically clean up MDIO bus alocations made by MDIO drivers, thus leading to simplified MDIO drivers code. Cc: Florian Fainelli Cc: Sergei Shtylyov Acked-and-tested-by: Lad, Prabhakar Signed-off-by: Grygorii Strashko Signed-off-by: David S. Miller --- include/linux/phy.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 51d15f684e7e..864ddafad8cc 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -198,6 +198,13 @@ static inline struct mii_bus *mdiobus_alloc(void) int mdiobus_register(struct mii_bus *bus); void mdiobus_unregister(struct mii_bus *bus); void mdiobus_free(struct mii_bus *bus); +struct mii_bus *devm_mdiobus_alloc_size(struct device *dev, int sizeof_priv); +static inline struct mii_bus *devm_mdiobus_alloc(struct device *dev) +{ + return devm_mdiobus_alloc_size(dev, 0); +} + +void devm_mdiobus_free(struct device *dev, struct mii_bus *bus); struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); int mdiobus_read(struct mii_bus *bus, int addr, u32 regnum); int mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val); -- cgit v1.2.3 From e114a710aa5058c0ba4aa1dfb105132aefeb5e04 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 30 Apr 2014 11:58:13 -0700 Subject: tcp: fix cwnd limited checking to improve congestion control Yuchung discovered tcp_is_cwnd_limited() was returning false in slow start phase even if the application filled the socket write queue. All congestion modules take into account tcp_is_cwnd_limited() before increasing cwnd, so this behavior limits slow start from probing the bandwidth at full speed. The problem is that even if write queue is full (aka we are _not_ application limited), cwnd can be under utilized if TSO should auto defer or TCP Small queues decided to hold packets. So the in_flight can be kept to smaller value, and we can get to the point tcp_is_cwnd_limited() returns false. With TCP Small Queues and FQ/pacing, this issue is more visible. We fix this by having tcp_cwnd_validate(), which is supposed to track such things, take into account unsent_segs, the number of segs that we are not sending at the moment due to TSO or TSQ, but intend to send real soon. Then when we are cwnd-limited, remember this fact while we are processing the window of ACKs that comes back. For example, suppose we have a brand new connection with cwnd=10; we are in slow start, and we send a flight of 9 packets. By the time we have received ACKs for all 9 packets we want our cwnd to be 18. We implement this by setting tp->lsnd_pending to 9, and considering ourselves to be cwnd-limited while cwnd is less than twice tp->lsnd_pending (2*9 -> 18). This makes tcp_is_cwnd_limited() more understandable, by removing the GSO/TSO kludge, that tried to work around the issue. Note the in_flight parameter can be removed in a followup cleanup patch. Signed-off-by: Eric Dumazet Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 239946868142..4e37c71ecd74 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -230,6 +230,7 @@ struct tcp_sock { u32 snd_cwnd_clamp; /* Do not allow snd_cwnd to grow above this */ u32 snd_cwnd_used; u32 snd_cwnd_stamp; + u32 lsnd_pending; /* packets inflight or unsent since last xmit */ u32 prior_cwnd; /* Congestion window at start of Recovery. */ u32 prr_delivered; /* Number of newly delivered packets to * receiver in Recovery. */ -- cgit v1.2.3 From 5bcfedf06f7fdf9efcf65dc11198e9012f7530f4 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 1 May 2014 18:34:18 +0200 Subject: net: filter: simplify label names from jump-table This patch simplifies label naming for the BPF jump-table. When we define labels via DL(), we just concatenate/textify the combination of instruction opcode which consists of the class, subclass, word size, target register and so on. Each time we leave BPF_ prefix intact, so that e.g. the preprocessor generates a label BPF_ALU_BPF_ADD_BPF_X for DL(BPF_ALU, BPF_ADD, BPF_X) whereas a label name of ALU_ADD_X is much more easy to grasp. Pure cleanup only. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/filter.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 759abf78dd61..b042d1db127f 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -37,6 +37,9 @@ #define BPF_CALL 0x80 /* function call */ #define BPF_EXIT 0x90 /* function return */ +/* Placeholder/dummy for 0 */ +#define BPF_0 0 + /* BPF has 10 general purpose 64-bit registers and stack frame. */ #define MAX_BPF_REG 11 -- cgit v1.2.3 From 30743837dd204d2b04fd4e9d3db78cc7b118c81a Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 1 May 2014 18:34:19 +0200 Subject: net: filter: make register naming more comprehensible The current code is a bit hard to parse on which registers can be used, how they are mapped and all play together. It makes much more sense to define this a bit more clearly so that the code is a bit more intuitive. This patch cleans this up, and makes naming a bit more consistent among the code. This also allows for moving some of the defines into the header file. Clearing of A and X registers in __sk_run_filter() do not get a particular register name assigned as they have not an 'official' function, but rather just result from the concrete initial mapping of old BPF programs. Since for BPF helper functions for BPF_CALL we already use small letters, so be consistent here as well. No functional changes. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/filter.h | 44 ++++++++++++++++++++++++++++++++++++-------- 1 file changed, 36 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index b042d1db127f..ed1efab10b8f 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -40,16 +40,47 @@ /* Placeholder/dummy for 0 */ #define BPF_0 0 +/* Register numbers */ +enum { + BPF_REG_0 = 0, + BPF_REG_1, + BPF_REG_2, + BPF_REG_3, + BPF_REG_4, + BPF_REG_5, + BPF_REG_6, + BPF_REG_7, + BPF_REG_8, + BPF_REG_9, + BPF_REG_10, + __MAX_BPF_REG, +}; + /* BPF has 10 general purpose 64-bit registers and stack frame. */ -#define MAX_BPF_REG 11 +#define MAX_BPF_REG __MAX_BPF_REG + +/* ArgX, context and stack frame pointer register positions. Note, + * Arg1, Arg2, Arg3, etc are used as argument mappings of function + * calls in BPF_CALL instruction. + */ +#define BPF_REG_ARG1 BPF_REG_1 +#define BPF_REG_ARG2 BPF_REG_2 +#define BPF_REG_ARG3 BPF_REG_3 +#define BPF_REG_ARG4 BPF_REG_4 +#define BPF_REG_ARG5 BPF_REG_5 +#define BPF_REG_CTX BPF_REG_6 +#define BPF_REG_FP BPF_REG_10 + +/* Additional register mappings for converted user programs. */ +#define BPF_REG_A BPF_REG_0 +#define BPF_REG_X BPF_REG_7 +#define BPF_REG_TMP BPF_REG_8 /* BPF program can access up to 512 bytes of stack space. */ #define MAX_BPF_STACK 512 -/* Arg1, context and stack frame pointer register positions. */ -#define ARG1_REG 1 -#define CTX_REG 6 -#define FP_REG 10 +/* Macro to invoke filter function. */ +#define SK_RUN_FILTER(filter, ctx) (*filter->bpf_func)(ctx, filter->insnsi) struct sock_filter_int { __u8 code; /* opcode */ @@ -100,9 +131,6 @@ static inline unsigned int sk_filter_size(unsigned int proglen) #define sk_filter_proglen(fprog) \ (fprog->len * sizeof(fprog->filter[0])) -#define SK_RUN_FILTER(filter, ctx) \ - (*filter->bpf_func)(ctx, filter->insnsi) - int sk_filter(struct sock *sk, struct sk_buff *skb); u32 sk_run_filter_int_seccomp(const struct seccomp_data *ctx, -- cgit v1.2.3 From 76ba0aae673075c77a8b775e9133c8e8b1a44563 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Fri, 2 May 2014 16:29:18 -0700 Subject: net: Generalize checksum_init functions Create a general __skb_checksum_validate function (actually a macro) to subsume the various checksum_init functions. This function can either init the checksum, or do the full validation (logically checksum_init+skb_check_complete)-- a flag specifies if full vaidation is performed. Also, there is a flag to the function to indicate that zero checksums are allowed (to support optional UDP checksums). Added several stub functions for calling __skb_checksum_validate. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/skbuff.h | 93 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 93 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 08074a810164..3ca0dda5a42e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2741,6 +2741,99 @@ static inline __sum16 skb_checksum_complete(struct sk_buff *skb) 0 : __skb_checksum_complete(skb); } +/* Check if we need to perform checksum complete validation. + * + * Returns true if checksum complete is needed, false otherwise + * (either checksum is unnecessary or zero checksum is allowed). + */ +static inline bool __skb_checksum_validate_needed(struct sk_buff *skb, + bool zero_okay, + __sum16 check) +{ + if (skb_csum_unnecessary(skb)) { + return false; + } else if (zero_okay && !check) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + return false; + } + + return true; +} + +/* For small packets <= CHECKSUM_BREAK peform checksum complete directly + * in checksum_init. + */ +#define CHECKSUM_BREAK 76 + +/* Validate (init) checksum based on checksum complete. + * + * Return values: + * 0: checksum is validated or try to in skb_checksum_complete. In the latter + * case the ip_summed will not be CHECKSUM_UNNECESSARY and the pseudo + * checksum is stored in skb->csum for use in __skb_checksum_complete + * non-zero: value of invalid checksum + * + */ +static inline __sum16 __skb_checksum_validate_complete(struct sk_buff *skb, + bool complete, + __wsum psum) +{ + if (skb->ip_summed == CHECKSUM_COMPLETE) { + if (!csum_fold(csum_add(psum, skb->csum))) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + return 0; + } + } + + skb->csum = psum; + + if (complete || skb->len <= CHECKSUM_BREAK) + return __skb_checksum_complete(skb); + + return 0; +} + +static inline __wsum null_compute_pseudo(struct sk_buff *skb, int proto) +{ + return 0; +} + +/* Perform checksum validate (init). Note that this is a macro since we only + * want to calculate the pseudo header which is an input function if necessary. + * First we try to validate without any computation (checksum unnecessary) and + * then calculate based on checksum complete calling the function to compute + * pseudo header. + * + * Return values: + * 0: checksum is validated or try to in skb_checksum_complete + * non-zero: value of invalid checksum + */ +#define __skb_checksum_validate(skb, proto, complete, \ + zero_okay, check, compute_pseudo) \ +({ \ + __sum16 __ret = 0; \ + if (__skb_checksum_validate_needed(skb, zero_okay, check)) \ + __ret = __skb_checksum_validate_complete(skb, \ + complete, compute_pseudo(skb, proto)); \ + __ret; \ +}) + +#define skb_checksum_init(skb, proto, compute_pseudo) \ + __skb_checksum_validate(skb, proto, false, false, 0, compute_pseudo) + +#define skb_checksum_init_zero_check(skb, proto, check, compute_pseudo) \ + __skb_checksum_validate(skb, proto, false, true, check, compute_pseudo) + +#define skb_checksum_validate(skb, proto, compute_pseudo) \ + __skb_checksum_validate(skb, proto, true, false, 0, compute_pseudo) + +#define skb_checksum_validate_zero_check(skb, proto, check, \ + compute_pseudo) \ + __skb_checksum_validate_(skb, proto, true, true, check, compute_pseudo) + +#define skb_checksum_simple_validate(skb) \ + __skb_checksum_validate(skb, 0, true, false, 0, null_compute_pseudo) + #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) void nf_conntrack_destroy(struct nf_conntrack *nfct); static inline void nf_conntrack_put(struct nf_conntrack *nfct) -- cgit v1.2.3 From 552a515707a5caf9fa9f3620d68fc28146c6b1b9 Mon Sep 17 00:00:00 2001 From: Helmut Schaa Date: Wed, 7 May 2014 09:28:31 +0200 Subject: ath9k: Allow platform override without EEPROM override Add a new platform data flag "use_eeprom" that indicates that the eeprom found on the card itself should be used instead of the one present in the platform data. This allows to override the MAC address of a PCI card while preserving the eeprom data from the card itself. The default behavior is preserved. Signed-off-by: Helmut Schaa Signed-off-by: John W. Linville --- include/linux/ath9k_platform.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ath9k_platform.h b/include/linux/ath9k_platform.h index 8598f8eacb20..a495a959e8a7 100644 --- a/include/linux/ath9k_platform.h +++ b/include/linux/ath9k_platform.h @@ -36,6 +36,8 @@ struct ath9k_platform_data { int (*get_mac_revision)(void); int (*external_reset)(void); + + bool use_eeprom; }; #endif /* _LINUX_ATH9K_PLATFORM_H */ -- cgit v1.2.3 From 9739eef13c926645fbf88bcb77e66442fa75d688 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 8 May 2014 14:10:51 -0700 Subject: net: filter: make BPF conversion more readable Introduce BPF helper macros to define instructions (similar to old BPF_STMT/BPF_JUMP macros) Use them while converting classic BPF to internal and in BPF testsuite later. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/filter.h | 51 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index ed1efab10b8f..4457b383961c 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -79,6 +79,57 @@ enum { /* BPF program can access up to 512 bytes of stack space. */ #define MAX_BPF_STACK 512 +/* bpf_add|sub|...: a += x, bpf_mov: a = x */ +#define BPF_ALU64_REG(op, a, x) \ + ((struct sock_filter_int) {BPF_ALU64|BPF_OP(op)|BPF_X, a, x, 0, 0}) +#define BPF_ALU32_REG(op, a, x) \ + ((struct sock_filter_int) {BPF_ALU|BPF_OP(op)|BPF_X, a, x, 0, 0}) + +/* bpf_add|sub|...: a += imm, bpf_mov: a = imm */ +#define BPF_ALU64_IMM(op, a, imm) \ + ((struct sock_filter_int) {BPF_ALU64|BPF_OP(op)|BPF_K, a, 0, 0, imm}) +#define BPF_ALU32_IMM(op, a, imm) \ + ((struct sock_filter_int) {BPF_ALU|BPF_OP(op)|BPF_K, a, 0, 0, imm}) + +/* R0 = *(uint *) (skb->data + off) */ +#define BPF_LD_ABS(size, off) \ + ((struct sock_filter_int) {BPF_LD|BPF_SIZE(size)|BPF_ABS, 0, 0, 0, off}) + +/* R0 = *(uint *) (skb->data + x + off) */ +#define BPF_LD_IND(size, x, off) \ + ((struct sock_filter_int) {BPF_LD|BPF_SIZE(size)|BPF_IND, 0, x, 0, off}) + +/* a = *(uint *) (x + off) */ +#define BPF_LDX_MEM(sz, a, x, off) \ + ((struct sock_filter_int) {BPF_LDX|BPF_SIZE(sz)|BPF_MEM, a, x, off, 0}) + +/* if (a 'op' x) goto pc+off */ +#define BPF_JMP_REG(op, a, x, off) \ + ((struct sock_filter_int) {BPF_JMP|BPF_OP(op)|BPF_X, a, x, off, 0}) + +/* if (a 'op' imm) goto pc+off */ +#define BPF_JMP_IMM(op, a, imm, off) \ + ((struct sock_filter_int) {BPF_JMP|BPF_OP(op)|BPF_K, a, 0, off, imm}) + +#define BPF_EXIT_INSN() \ + ((struct sock_filter_int) {BPF_JMP|BPF_EXIT, 0, 0, 0, 0}) + +static inline int size_to_bpf(int size) +{ + switch (size) { + case 1: + return BPF_B; + case 2: + return BPF_H; + case 4: + return BPF_W; + case 8: + return BPF_DW; + default: + return -EINVAL; + } +} + /* Macro to invoke filter function. */ #define SK_RUN_FILTER(filter, ctx) (*filter->bpf_func)(ctx, filter->insnsi) -- cgit v1.2.3 From 60ff746739bf805a912484643c720b6124826140 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Sun, 4 May 2014 16:39:18 -0700 Subject: net: rename local_df to ignore_df MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As suggested by several people, rename local_df to ignore_df, since it means "ignore df bit if it is set". Cc: Maciej Żenczykowski Cc: Florian Westphal Cc: David S. Miller Cc: Eric Dumazet Signed-off-by: Cong Wang Acked-by: Maciej Żenczykowski Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3ca0dda5a42e..7a9beeb1c458 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -426,7 +426,7 @@ static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1, * @csum_start: Offset from skb->head where checksumming should start * @csum_offset: Offset from csum_start where checksum should be stored * @priority: Packet queueing priority - * @local_df: allow local fragmentation + * @ignore_df: allow local fragmentation * @cloned: Head may be cloned (check refcnt to be sure) * @ip_summed: Driver fed us an IP checksum * @nohdr: Payload reference only, must not modify header @@ -514,7 +514,7 @@ struct sk_buff { }; __u32 priority; kmemcheck_bitfield_begin(flags1); - __u8 local_df:1, + __u8 ignore_df:1, cloned:1, ip_summed:2, nohdr:1, -- cgit v1.2.3 From f06c7f9f92295faf701a9628b383156c4efb6119 Mon Sep 17 00:00:00 2001 From: dingtianhong Date: Fri, 9 May 2014 14:58:05 +0800 Subject: vlan: rename __vlan_find_dev_deep() to __vlan_find_dev_deep_rcu() The __vlan_find_dev_deep should always called in RCU, according David's suggestion, rename to __vlan_find_dev_deep_rcu looks more reasonable. Signed-off-by: Ding Tianhong Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 13bbbde00e68..8c0fb7f3a9a5 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -106,7 +106,7 @@ struct vlan_pcpu_stats { #if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) -extern struct net_device *__vlan_find_dev_deep(struct net_device *real_dev, +extern struct net_device *__vlan_find_dev_deep_rcu(struct net_device *real_dev, __be16 vlan_proto, u16 vlan_id); extern struct net_device *vlan_dev_real_dev(const struct net_device *dev); extern u16 vlan_dev_vlan_id(const struct net_device *dev); @@ -199,7 +199,7 @@ extern void vlan_vids_del_by_dev(struct net_device *dev, extern bool vlan_uses_dev(const struct net_device *dev); #else static inline struct net_device * -__vlan_find_dev_deep(struct net_device *real_dev, +__vlan_find_dev_deep_rcu(struct net_device *real_dev, __be16 vlan_proto, u16 vlan_id) { return NULL; -- cgit v1.2.3 From 7ad24ea4bf620a32631d7b3069c3e30c078b0c3e Mon Sep 17 00:00:00 2001 From: Wilfried Klaebe Date: Sun, 11 May 2014 00:12:32 +0000 Subject: net: get rid of SET_ETHTOOL_OPS net: get rid of SET_ETHTOOL_OPS Dave Miller mentioned he'd like to see SET_ETHTOOL_OPS gone. This does that. Mostly done via coccinelle script: @@ struct ethtool_ops *ops; struct net_device *dev; @@ - SET_ETHTOOL_OPS(dev, ops); + dev->ethtool_ops = ops; Compile tested only, but I'd seriously wonder if this broke anything. Suggested-by: Dave Miller Signed-off-by: Wilfried Klaebe Acked-by: Felipe Balbi Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index adc4658e9873..2dea98cbbdba 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -56,9 +56,6 @@ struct device; struct phy_device; /* 802.11 specific */ struct wireless_dev; - /* source back-compat hooks */ -#define SET_ETHTOOL_OPS(netdev,ops) \ - ( (netdev)->ethtool_ops = (ops) ) void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops); -- cgit v1.2.3 From 50a0ffaf75e9d2d97200b523f2c600f40e9756b1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Sun, 11 May 2014 10:47:15 +0200 Subject: net: cdc_ncm/cdc_mbim: rework probing of NCM/MBIM functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The NCM class match in the cdc_mbim driver is confusing and cause unexpected behaviour. The USB core guarantees that a USB interface is in altsetting 0 when probing starts. This means that devices implementing a NCM 1.0 backwards compatible MBIM function (a "NCM/MBIM function") always hit the NCM entry in the cdc_mbim driver match table. Such functions will never match any of the MBIM entries. This causes unexpeced behaviour for cases where the NCM and MBIM entries are differet, which is currently the case for all except Ericsson devices. Improve the probing of NCM/MBIM functions by looking up the device again in the cdc_mbim match table after switching to the MBIM identity. The shared altsetting selection is updated to better accommodate the new probing logic, returning the preferred altsetting for the control interface instead of the data interface. The control interface altsetting update is moved to the cdc_mbim driver. It is never necessary to change the control interface altsetting for NCM. Cc: Greg Suarez Reported by: Yu-an Shih Signed-off-by: Bjørn Mork Signed-off-by: David S. Miller --- include/linux/usb/cdc_ncm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index 44b38b92236a..55b6feead93b 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -121,7 +121,7 @@ struct cdc_ncm_ctx { u16 connected; }; -u8 cdc_ncm_select_altsetting(struct usbnet *dev, struct usb_interface *intf); +u8 cdc_ncm_select_altsetting(struct usb_interface *intf); int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting); void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf); struct sk_buff *cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign); -- cgit v1.2.3 From 89278c9dc922272df921042aafa18311f3398c6c Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Sun, 11 May 2014 20:22:10 -0700 Subject: tcp: simplify fast open cookie processing Consolidate various cookie checking and generation code to simplify the fast open processing. The main goal is to reduce code duplication in tcp_v4_conn_request() for IPv6 support. Removes two experimental sysctl flags TFO_SERVER_ALWAYS and TFO_SERVER_COOKIE_NOT_CHKD used primarily for developmental debugging purposes. Signed-off-by: Yuchung Cheng Signed-off-by: Daniel Lee Signed-off-by: Jerry Chu Signed-off-by: Eric Dumazet Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- include/linux/tcp.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 4e37c71ecd74..bc35e4709e8e 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -366,11 +366,6 @@ static inline bool tcp_passive_fastopen(const struct sock *sk) tcp_sk(sk)->fastopen_rsk != NULL); } -static inline bool fastopen_cookie_present(struct tcp_fastopen_cookie *foc) -{ - return foc->len != -1; -} - extern void tcp_sock_destruct(struct sock *sk); static inline int fastopen_init_queue(struct sock *sk, int backlog) -- cgit v1.2.3 From 2eacc23c422b4553030168f315cb49522fa1b1f6 Mon Sep 17 00:00:00 2001 From: Yuval Atias Date: Wed, 14 May 2014 12:15:10 +0300 Subject: net/mlx4_core: Enforce irq affinity changes immediatly During heavy traffic, napi is constatntly polling the complition queue and no interrupt is fired. Because of that, changes to irq affinity are ignored until traffic is stopped and resumed. By registering to the irq notifier mechanism, and forcing interrupt when affinity is changed, irq affinity changes will be immediatly enforced. Signed-off-by: Yuval Atias Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index ba87bd21295a..c0468e6f0442 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -577,6 +577,9 @@ struct mlx4_cq { u32 cons_index; + u16 irq; + bool irq_affinity_change; + __be32 *set_ci_db; __be32 *arm_db; int arm_sn; -- cgit v1.2.3 From 622582786c9e041d0bd52bde201787adeab249f8 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 13 May 2014 19:50:46 -0700 Subject: net: filter: x86: internal BPF JIT Maps all internal BPF instructions into x86_64 instructions. This patch replaces original BPF x64 JIT with internal BPF x64 JIT. sysctl net.core.bpf_jit_enable is reused as on/off switch. Performance: 1. old BPF JIT and internal BPF JIT generate equivalent x86_64 code. No performance difference is observed for filters that were JIT-able before Example assembler code for BPF filter "tcpdump port 22" original BPF -> old JIT: original BPF -> internal BPF -> new JIT: 0: push %rbp 0: push %rbp 1: mov %rsp,%rbp 1: mov %rsp,%rbp 4: sub $0x60,%rsp 4: sub $0x228,%rsp 8: mov %rbx,-0x8(%rbp) b: mov %rbx,-0x228(%rbp) // prologue 12: mov %r13,-0x220(%rbp) 19: mov %r14,-0x218(%rbp) 20: mov %r15,-0x210(%rbp) 27: xor %eax,%eax // clear A c: xor %ebx,%ebx 29: xor %r13,%r13 // clear X e: mov 0x68(%rdi),%r9d 2c: mov 0x68(%rdi),%r9d 12: sub 0x6c(%rdi),%r9d 30: sub 0x6c(%rdi),%r9d 16: mov 0xd8(%rdi),%r8 34: mov 0xd8(%rdi),%r10 3b: mov %rdi,%rbx 1d: mov $0xc,%esi 3e: mov $0xc,%esi 22: callq 0xffffffffe1021e15 43: callq 0xffffffffe102bd75 27: cmp $0x86dd,%eax 48: cmp $0x86dd,%rax 2c: jne 0x0000000000000069 4f: jne 0x000000000000009a 2e: mov $0x14,%esi 51: mov $0x14,%esi 33: callq 0xffffffffe1021e31 56: callq 0xffffffffe102bd91 38: cmp $0x84,%eax 5b: cmp $0x84,%rax 3d: je 0x0000000000000049 62: je 0x0000000000000074 3f: cmp $0x6,%eax 64: cmp $0x6,%rax 42: je 0x0000000000000049 68: je 0x0000000000000074 44: cmp $0x11,%eax 6a: cmp $0x11,%rax 47: jne 0x00000000000000c6 6e: jne 0x0000000000000117 49: mov $0x36,%esi 74: mov $0x36,%esi 4e: callq 0xffffffffe1021e15 79: callq 0xffffffffe102bd75 53: cmp $0x16,%eax 7e: cmp $0x16,%rax 56: je 0x00000000000000bf 82: je 0x0000000000000110 58: mov $0x38,%esi 88: mov $0x38,%esi 5d: callq 0xffffffffe1021e15 8d: callq 0xffffffffe102bd75 62: cmp $0x16,%eax 92: cmp $0x16,%rax 65: je 0x00000000000000bf 96: je 0x0000000000000110 67: jmp 0x00000000000000c6 98: jmp 0x0000000000000117 69: cmp $0x800,%eax 9a: cmp $0x800,%rax 6e: jne 0x00000000000000c6 a1: jne 0x0000000000000117 70: mov $0x17,%esi a3: mov $0x17,%esi 75: callq 0xffffffffe1021e31 a8: callq 0xffffffffe102bd91 7a: cmp $0x84,%eax ad: cmp $0x84,%rax 7f: je 0x000000000000008b b4: je 0x00000000000000c2 81: cmp $0x6,%eax b6: cmp $0x6,%rax 84: je 0x000000000000008b ba: je 0x00000000000000c2 86: cmp $0x11,%eax bc: cmp $0x11,%rax 89: jne 0x00000000000000c6 c0: jne 0x0000000000000117 8b: mov $0x14,%esi c2: mov $0x14,%esi 90: callq 0xffffffffe1021e15 c7: callq 0xffffffffe102bd75 95: test $0x1fff,%ax cc: test $0x1fff,%rax 99: jne 0x00000000000000c6 d3: jne 0x0000000000000117 d5: mov %rax,%r14 9b: mov $0xe,%esi d8: mov $0xe,%esi a0: callq 0xffffffffe1021e44 dd: callq 0xffffffffe102bd91 // MSH e2: and $0xf,%eax e5: shl $0x2,%eax e8: mov %rax,%r13 eb: mov %r14,%rax ee: mov %r13,%rsi a5: lea 0xe(%rbx),%esi f1: add $0xe,%esi a8: callq 0xffffffffe1021e0d f4: callq 0xffffffffe102bd6d ad: cmp $0x16,%eax f9: cmp $0x16,%rax b0: je 0x00000000000000bf fd: je 0x0000000000000110 ff: mov %r13,%rsi b2: lea 0x10(%rbx),%esi 102: add $0x10,%esi b5: callq 0xffffffffe1021e0d 105: callq 0xffffffffe102bd6d ba: cmp $0x16,%eax 10a: cmp $0x16,%rax bd: jne 0x00000000000000c6 10e: jne 0x0000000000000117 bf: mov $0xffff,%eax 110: mov $0xffff,%eax c4: jmp 0x00000000000000c8 115: jmp 0x000000000000011c c6: xor %eax,%eax 117: mov $0x0,%eax c8: mov -0x8(%rbp),%rbx 11c: mov -0x228(%rbp),%rbx // epilogue cc: leaveq 123: mov -0x220(%rbp),%r13 cd: retq 12a: mov -0x218(%rbp),%r14 131: mov -0x210(%rbp),%r15 138: leaveq 139: retq On fully cached SKBs both JITed functions take 12 nsec to execute. BPF interpreter executes the program in 30 nsec. The difference in generated assembler is due to the following: Old BPF imlements LDX_MSH instruction via sk_load_byte_msh() helper function inside bpf_jit.S. New JIT removes the helper and does it explicitly, so ldx_msh cost is the same for both JITs, but generated code looks longer. New JIT has 4 registers to save, so prologue/epilogue are larger, but the cost is within noise on x64. Old JIT checks whether first insn clears A and if not emits 'xor %eax,%eax'. New JIT clears %rax unconditionally. 2. old BPF JIT doesn't support ANC_NLATTR, ANC_PAY_OFFSET, ANC_RANDOM extensions. New JIT supports all BPF extensions. Performance of such filters improves 2-4 times depending on a filter. The longer the filter the higher performance gain. Synthetic benchmarks with many ancillary loads see 20x speedup which seems to be the maximum gain from JIT Notes: . net.core.bpf_jit_enable=2 + tools/net/bpf_jit_disasm is still functional and can be used to see generated assembler . there are two jit_compile() functions and code flow for classic filters is: sk_attach_filter() - load classic BPF bpf_jit_compile() - try to JIT from classic BPF sk_convert_filter() - convert classic to internal bpf_int_jit_compile() - JIT from internal BPF seccomp and tracing filters will just call bpf_int_jit_compile() Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/filter.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 4457b383961c..9d5ae0a2c954 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -207,6 +207,9 @@ void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to); void sk_filter_charge(struct sock *sk, struct sk_filter *fp); void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp); +u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); +void bpf_int_jit_compile(struct sk_filter *fp); + #ifdef CONFIG_BPF_JIT #include #include -- cgit v1.2.3 From 1836eea209546b870dd83f3f4ef234d6598a560d Mon Sep 17 00:00:00 2001 From: George Spelvin Date: Sat, 10 May 2014 10:32:57 -0400 Subject: lib/crc7: Shift crc7() output left 1 bit This eliminates a 1-bit left shift in every single caller, and makes the inner loop of the CRC computation more efficient. Renamed crc7 to crc7_be (big-endian) since the interface changed. Also purged #include from files that don't use it at all. Signed-off-by: George Spelvin Reviewed-by: Pavel Machek Acked-by: Ulf Hansson Signed-off-by: John W. Linville --- include/linux/crc7.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crc7.h b/include/linux/crc7.h index 1786e772d5c6..d590765106f3 100644 --- a/include/linux/crc7.h +++ b/include/linux/crc7.h @@ -2,13 +2,13 @@ #define _LINUX_CRC7_H #include -extern const u8 crc7_syndrome_table[256]; +extern const u8 crc7_be_syndrome_table[256]; -static inline u8 crc7_byte(u8 crc, u8 data) +static inline u8 crc7_be_byte(u8 crc, u8 data) { - return crc7_syndrome_table[(crc << 1) ^ data]; + return crc7_be_syndrome_table[crc ^ data]; } -extern u8 crc7(u8 crc, const u8 *buffer, size_t len); +extern u8 crc7_be(u8 crc, const u8 *buffer, size_t len); #endif -- cgit v1.2.3 From a75951217472c522c324adb0a4de3ba69d656ef5 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Fri, 16 May 2014 16:14:04 +0200 Subject: net: phy: extend fixed driver with fixed_phy_register() The existing fixed_phy_add() function has several drawbacks that prevents it from being used as is for OF-based declaration of fixed PHYs: * The address of the PHY on the fake bus needs to be passed, while a dynamic allocation is desired. * Since the phy_device instantiation is post-poned until the next mdiobus scan, there is no way to associate the fixed PHY with its OF node, which later prevents of_phy_connect() from finding this fixed PHY from a given OF node. To solve this, this commit introduces fixed_phy_register(), which will allocate an available PHY address, add the PHY using fixed_phy_add() and instantiate the phy_device structure associated with the provided OF node. Signed-off-by: Thomas Petazzoni Acked-by: Florian Fainelli Acked-by: Grant Likely Tested-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy_fixed.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy_fixed.h b/include/linux/phy_fixed.h index 509d8f5f984e..4f2478b47136 100644 --- a/include/linux/phy_fixed.h +++ b/include/linux/phy_fixed.h @@ -9,15 +9,26 @@ struct fixed_phy_status { int asym_pause; }; +struct device_node; + #ifdef CONFIG_FIXED_PHY extern int fixed_phy_add(unsigned int irq, int phy_id, struct fixed_phy_status *status); +extern int fixed_phy_register(unsigned int irq, + struct fixed_phy_status *status, + struct device_node *np); #else static inline int fixed_phy_add(unsigned int irq, int phy_id, struct fixed_phy_status *status) { return -ENODEV; } +static inline int fixed_phy_register(unsigned int irq, + struct fixed_phy_status *status, + struct device_node *np) +{ + return -ENODEV; +} #endif /* CONFIG_FIXED_PHY */ /* -- cgit v1.2.3 From 3be2a49e5c08d268f8af0dd4fe89a24ea8cdc339 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Fri, 16 May 2014 16:14:05 +0200 Subject: of: provide a binding for fixed link PHYs Some Ethernet MACs have a "fixed link", and are not connected to a normal MDIO-managed PHY device. For those situations, a Device Tree binding allows to describe a "fixed link" using a special PHY node. This patch adds: * A documentation for the fixed PHY Device Tree binding. * An of_phy_is_fixed_link() function that an Ethernet driver can call on its PHY phandle to find out whether it's a fixed link PHY or not. It should typically be used to know if of_phy_register_fixed_link() should be called. * An of_phy_register_fixed_link() function that instantiates the fixed PHY into the PHY subsystem, so that when the driver calls of_phy_connect(), the PHY device associated to the OF node will be found. These two additional functions also support the old fixed-link Device Tree binding used on PowerPC platforms, so that ultimately, the network device drivers for those platforms could be converted to use of_phy_is_fixed_link() and of_phy_register_fixed_link() instead of of_phy_connect_fixed_link(), while keeping compatibility with their respective Device Tree bindings. Signed-off-by: Thomas Petazzoni Reviewed-by: Florian Fainelli Tested-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/of_mdio.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 881a7c3571f4..0aa367e316cb 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -72,4 +72,19 @@ static inline struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np) } #endif /* CONFIG_OF */ +#if defined(CONFIG_OF) && defined(CONFIG_FIXED_PHY) +extern int of_phy_register_fixed_link(struct device_node *np); +extern bool of_phy_is_fixed_link(struct device_node *np); +#else +static inline int of_phy_register_fixed_link(struct device_node *np) +{ + return -ENOSYS; +} +static inline bool of_phy_is_fixed_link(struct device_node *np) +{ + return false; +} +#endif + + #endif /* __LINUX_OF_MDIO_H */ -- cgit v1.2.3 From 3e9c156e2c210ab67b12b1b692983a6b97c19d3f Mon Sep 17 00:00:00 2001 From: Phoebe Buckheister Date: Fri, 16 May 2014 17:46:44 +0200 Subject: ieee802154: add netlink interfaces for llsec This patch adds user-visible interfaces for the llsec infrastructure. For the added methods, the only major difference between all add/remove implementation lies in how the specific object is parsed, and for dump requests, how objects are written into netlink messages. To save on boilerplate code, table dumps are routed through a helper function that handles netlink dump state, leaving the actual dumping code to care only about iterating over the table to be dumped and filling netlink messages. For add/remove methods, the boilerplate required to work is not quite as large, but still enough to also move into a local helper. Signed-off-by: Phoebe Buckheister Signed-off-by: David S. Miller --- include/linux/nl802154.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl802154.h b/include/linux/nl802154.h index c8d7f3965fff..20163b9a0eae 100644 --- a/include/linux/nl802154.h +++ b/include/linux/nl802154.h @@ -80,6 +80,22 @@ enum { IEEE802154_ATTR_FRAME_RETRIES, + IEEE802154_ATTR_LLSEC_ENABLED, + IEEE802154_ATTR_LLSEC_SECLEVEL, + IEEE802154_ATTR_LLSEC_KEY_MODE, + IEEE802154_ATTR_LLSEC_KEY_SOURCE_SHORT, + IEEE802154_ATTR_LLSEC_KEY_SOURCE_EXTENDED, + IEEE802154_ATTR_LLSEC_KEY_ID, + IEEE802154_ATTR_LLSEC_FRAME_COUNTER, + IEEE802154_ATTR_LLSEC_KEY_BYTES, + IEEE802154_ATTR_LLSEC_KEY_USAGE_FRAME_TYPES, + IEEE802154_ATTR_LLSEC_KEY_USAGE_COMMANDS, + IEEE802154_ATTR_LLSEC_FRAME_TYPE, + IEEE802154_ATTR_LLSEC_CMD_FRAME_ID, + IEEE802154_ATTR_LLSEC_SECLEVELS, + IEEE802154_ATTR_LLSEC_DEV_OVERRIDE, + IEEE802154_ATTR_LLSEC_DEV_KEY_MODE, + __IEEE802154_ATTR_MAX, }; @@ -134,6 +150,21 @@ enum { IEEE802154_SET_MACPARAMS, + IEEE802154_LLSEC_GETPARAMS, + IEEE802154_LLSEC_SETPARAMS, + IEEE802154_LLSEC_LIST_KEY, + IEEE802154_LLSEC_ADD_KEY, + IEEE802154_LLSEC_DEL_KEY, + IEEE802154_LLSEC_LIST_DEV, + IEEE802154_LLSEC_ADD_DEV, + IEEE802154_LLSEC_DEL_DEV, + IEEE802154_LLSEC_LIST_DEVKEY, + IEEE802154_LLSEC_ADD_DEVKEY, + IEEE802154_LLSEC_DEL_DEVKEY, + IEEE802154_LLSEC_LIST_SECLEVEL, + IEEE802154_LLSEC_ADD_SECLEVEL, + IEEE802154_LLSEC_DEL_SECLEVEL, + __IEEE802154_CMD_MAX, }; -- cgit v1.2.3 From 6c4e548ff36672eeb78f8288a2920d66fa4a6a66 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Fri, 16 May 2014 21:48:22 +0200 Subject: net: cdc_ncm: use ethtool to tune coalescing settings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Datagram coalescing is an integral part of the NCM and MBIM protocols, intended to reduce the interrupt load primarily on the device end of the USB link. As with all coalescing solutions, there is a trade-off between buffering and interrupts. The current defaults are based on the assumption that device side buffers should be the limiting factor. However, many modern high speed LTE modems suffers from buffer-bloat, making this assumption fail. This results in sub-optimal performance due to excessive coalescing. And in cases where such modems are connected to cheap embedded hosts there is often severe buffer allocation issues, giving very noticeable performance degradation . A start on improving this is going from build time hard coded limits to per device user configurable limits. The ethtool coalescing API was selected as user interface because, although the tuned values are buffer sizes, these settings directly control datagram coalescing. Signed-off-by: Bjørn Mork Signed-off-by: David S. Miller --- include/linux/usb/cdc_ncm.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index 55b6feead93b..5c1066b4dc41 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -72,7 +72,9 @@ /* Restart the timer, if amount of datagrams is less than given value */ #define CDC_NCM_RESTART_TIMER_DATAGRAM_CNT 3 #define CDC_NCM_TIMER_PENDING_CNT 2 -#define CDC_NCM_TIMER_INTERVAL (400UL * NSEC_PER_USEC) +#define CDC_NCM_TIMER_INTERVAL_USEC 400UL +#define CDC_NCM_TIMER_INTERVAL_MIN 5UL +#define CDC_NCM_TIMER_INTERVAL_MAX (15UL * USEC_PER_SEC) /* The following macro defines the minimum header space */ #define CDC_NCM_MIN_HDR_SIZE \ @@ -107,6 +109,8 @@ struct cdc_ncm_ctx { spinlock_t mtx; atomic_t stop; + u64 timer_interval; + u32 tx_timer_pending; u32 tx_curr_frame_num; u32 rx_max; -- cgit v1.2.3 From 70559b8970e52aa9962dc823fd4498af06809544 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Fri, 16 May 2014 21:48:23 +0200 Subject: net: cdc_ncm: use true max dgram count for header estimates MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Many newer NCM and MBIM devices will request a maximum tx datagram count which is much smaller than our hard-coded absolute max. We can reduce the overhead without sacrificing any of the simplicity for these devices, by simply using the true negotiated count in when calculated the maximum NTH and NDP header sizes. Signed-off-by: Bjørn Mork Signed-off-by: David S. Miller --- include/linux/usb/cdc_ncm.h | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index 5c1066b4dc41..60a44b8a464e 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -76,15 +76,6 @@ #define CDC_NCM_TIMER_INTERVAL_MIN 5UL #define CDC_NCM_TIMER_INTERVAL_MAX (15UL * USEC_PER_SEC) -/* The following macro defines the minimum header space */ -#define CDC_NCM_MIN_HDR_SIZE \ - (sizeof(struct usb_cdc_ncm_nth16) + sizeof(struct usb_cdc_ncm_ndp16) + \ - (CDC_NCM_DPT_DATAGRAMS_MAX + 1) * sizeof(struct usb_cdc_ncm_dpe16)) - -#define CDC_NCM_NDP_SIZE \ - (sizeof(struct usb_cdc_ncm_ndp16) + \ - (CDC_NCM_DPT_DATAGRAMS_MAX + 1) * sizeof(struct usb_cdc_ncm_dpe16)) - #define cdc_ncm_comm_intf_is_mbim(x) ((x)->desc.bInterfaceSubClass == USB_CDC_SUBCLASS_MBIM && \ (x)->desc.bInterfaceProtocol == USB_CDC_PROTO_NONE) #define cdc_ncm_data_intf_is_mbim(x) ((x)->desc.bInterfaceProtocol == USB_CDC_MBIM_PROTO_NTB) @@ -110,6 +101,7 @@ struct cdc_ncm_ctx { atomic_t stop; u64 timer_interval; + u32 max_ndp_size; u32 tx_timer_pending; u32 tx_curr_frame_num; -- cgit v1.2.3 From 43e4c6dfc0fd781e68f20caf563a06f5c6ece995 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Fri, 16 May 2014 21:48:24 +0200 Subject: net: cdc_ncm: set reasonable padding limits MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We pad frames larger than X to maximum size for devices which don't need a ZLP after maximum sized frames. This allows the device to optimize its transfers for one fixed buffer size. X was arbitrarily set at 512 bytes regardless of real buffer maximum, causing extreme overheads due to excessive padding of larger tx buffers. Limit the padding to at most 3 full USB packets, still allowing the overhead to payload ratio of 3/1. Signed-off-by: Bjørn Mork Signed-off-by: David S. Miller --- include/linux/usb/cdc_ncm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index 60a44b8a464e..79de6724d398 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -115,6 +115,7 @@ struct cdc_ncm_ctx { u16 tx_seq; u16 rx_seq; u16 connected; + u16 min_tx_pkt; }; u8 cdc_ncm_select_altsetting(struct usb_interface *intf); -- cgit v1.2.3 From beeecd42c3b41d17d0bf1d839db99274c287f514 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Fri, 16 May 2014 21:48:25 +0200 Subject: net: cdc_ncm/cdc_mbim: adding NCM protocol statistics MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To have an idea of the effects of the protocol coalescing it's useful to have some counters showing the different aspects. Due to the asymmetrical usbnet interface the netdev rx_bytes counter has been counting real received payload, while the tx_bytes counter has included the NCM/MBIM framing overhead. This overhead can be many times the payload because of the aggressive padding strategy of this driver, and will vary a lot depending on device and traffic. With very few exceptions, users are only interested in the payload size. Having an somewhat accurate payload byte counter is particularly important for mobile broadband devices, which many NCM devices and of course all MBIM devices are. Users and userspace applications will use this counter to monitor account quotas. Having protocol specific counters for the overhead, we are now able to correct the tx_bytes netdev counter so that it shows the real payload Signed-off-by: Bjørn Mork Signed-off-by: David S. Miller --- include/linux/usb/cdc_ncm.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index 79de6724d398..88d2d7f1820f 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -116,6 +116,17 @@ struct cdc_ncm_ctx { u16 rx_seq; u16 connected; u16 min_tx_pkt; + + /* statistics */ + u32 tx_curr_frame_payload; + u32 tx_reason_ntb_full; + u32 tx_reason_ndp_full; + u32 tx_reason_timeout; + u32 tx_reason_max_datagram; + u64 tx_overhead; + u64 tx_ntbs; + u64 rx_overhead; + u64 rx_ntbs; }; u8 cdc_ncm_select_altsetting(struct usb_interface *intf); -- cgit v1.2.3 From 50f1cb1cc8f50fa88dbeaf990ae2bae91b9ff306 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Fri, 16 May 2014 21:48:26 +0200 Subject: net: cdc_ncm: use sane defaults for rx/tx buffers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Lots of devices request much larger buffers than reasonable. This cause real problems for users of hosts with limited resources. Reducing the default buffer size to 16kB for such devices is a reasonable trade-off between allowing them to aggregate traffic and avoiding memory exhaustion on resource restrained hosts. Signed-off-by: Bjørn Mork Signed-off-by: David S. Miller --- include/linux/usb/cdc_ncm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index 88d2d7f1820f..cde506731c48 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -52,6 +52,10 @@ #define CDC_NCM_NTB_MAX_SIZE_TX 32768 /* bytes */ #define CDC_NCM_NTB_MAX_SIZE_RX 32768 /* bytes */ +/* Initial NTB length */ +#define CDC_NCM_NTB_DEF_SIZE_TX 16384 /* bytes */ +#define CDC_NCM_NTB_DEF_SIZE_RX 16384 /* bytes */ + /* Minimum value for MaxDatagramSize, ch. 6.2.9 */ #define CDC_NCM_MIN_DATAGRAM_SIZE 1514 /* bytes */ -- cgit v1.2.3 From fa83dbeee55865678025b6c1637ca08860209f87 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Fri, 16 May 2014 21:48:28 +0200 Subject: net: cdc_ncm: remove redundant "disconnected" flag MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Calling netif_carrier_{on,off} is sufficient. There is no need to duplicate the carrier state in a driver specific flag. Acked-by: Enrico Mioso Signed-off-by: Bjørn Mork Signed-off-by: David S. Miller --- include/linux/usb/cdc_ncm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index cde506731c48..8c5e38819828 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -118,7 +118,6 @@ struct cdc_ncm_ctx { u16 tx_ndp_modulus; u16 tx_seq; u16 rx_seq; - u16 connected; u16 min_tx_pkt; /* statistics */ -- cgit v1.2.3 From 678e30df2e5664619e06fcfea5490a476826d8fe Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Mon, 19 May 2014 01:25:59 +0100 Subject: ethtool: Expand documentation of ethtool_ops::{get,set}_rxfh() Some corner-cases are not explained properly. Signed-off-by: Ben Hutchings --- include/linux/ethtool.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 212f537fc686..886e127d51a6 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -162,15 +162,16 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings) * Will not be called if @get_rxfh_indir_size returns zero. * @get_rxfh: Get the contents of the RX flow hash indirection table and hash * key. - * Will not be called if @get_rxfh_indir_size and @get_rxfh_key_size - * returns zero. + * Will only be called if one or both of @get_rxfh_indir_size and + * @get_rxfh_key_size are implemented and return non-zero. * Returns a negative error code or zero. * @set_rxfh_indir: Set the contents of the RX flow hash indirection table. * Will not be called if @get_rxfh_indir_size returns zero. - * @set_rxfh: Set the contents of the RX flow hash indirection table and - * hash key. - * Will not be called if @get_rxfh_indir_size and @get_rxfh_key_size - * returns zero. + * @set_rxfh: Set the contents of the RX flow hash indirection table and/or + * hash key. Either or both arguments may be %NULL if that attribute + * is not to be changed. + * Will only be called if one or both of @get_rxfh_indir_size and + * @get_rxfh_key_size are implemented and return non-zero. * Returns a negative error code or zero. * @get_channels: Get number of channels. * @set_channels: Set number of channels. Returns a negative error code or @@ -244,8 +245,8 @@ struct ethtool_ops { int (*reset)(struct net_device *, u32 *); u32 (*get_rxfh_key_size)(struct net_device *); u32 (*get_rxfh_indir_size)(struct net_device *); - int (*get_rxfh)(struct net_device *, u32 *, u8 *); - int (*set_rxfh)(struct net_device *, u32 *, u8 *); + int (*get_rxfh)(struct net_device *, u32 *indir, u8 *key); + int (*set_rxfh)(struct net_device *, u32 *indir, u8 *key); int (*get_rxfh_indir)(struct net_device *, u32 *); int (*set_rxfh_indir)(struct net_device *, const u32 *); void (*get_channels)(struct net_device *, struct ethtool_channels *); -- cgit v1.2.3 From 61d88c6811f216de4ec26aafe24e650dc1aeb00e Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Mon, 19 May 2014 01:29:42 +0100 Subject: ethtool: Disallow ETHTOOL_SRSSH with both indir table and hash key unchanged This would be a no-op, so there is no reason to request it. This also allows conversion of the current implementations of ethtool_ops::{get,set}_rxfh_indir to ethtool_ops::{get,set}_rxfh with no change other than their parameters. Signed-off-by: Ben Hutchings --- include/linux/ethtool.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 886e127d51a6..de687a97c6e7 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -168,8 +168,8 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings) * @set_rxfh_indir: Set the contents of the RX flow hash indirection table. * Will not be called if @get_rxfh_indir_size returns zero. * @set_rxfh: Set the contents of the RX flow hash indirection table and/or - * hash key. Either or both arguments may be %NULL if that attribute - * is not to be changed. + * hash key. In case only the indirection table or hash key is to be + * changed, the other argument will be %NULL. * Will only be called if one or both of @get_rxfh_indir_size and * @get_rxfh_key_size are implemented and return non-zero. * Returns a negative error code or zero. -- cgit v1.2.3 From 33cb0fa7888510b5bd2096352b200cfe29db10fe Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Thu, 15 May 2014 02:01:23 +0100 Subject: ethtool, be2net: constify array pointer parameters to ethtool_ops::set_rxfh Signed-off-by: Ben Hutchings --- include/linux/ethtool.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index de687a97c6e7..874fde01d398 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -246,7 +246,8 @@ struct ethtool_ops { u32 (*get_rxfh_key_size)(struct net_device *); u32 (*get_rxfh_indir_size)(struct net_device *); int (*get_rxfh)(struct net_device *, u32 *indir, u8 *key); - int (*set_rxfh)(struct net_device *, u32 *indir, u8 *key); + int (*set_rxfh)(struct net_device *, const u32 *indir, + const u8 *key); int (*get_rxfh_indir)(struct net_device *, u32 *); int (*set_rxfh_indir)(struct net_device *, const u32 *); void (*get_channels)(struct net_device *, struct ethtool_channels *); -- cgit v1.2.3 From fd1159318e55e901cf269de90163b19fd62938cb Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Sat, 17 May 2014 00:03:54 +0400 Subject: can: add Renesas R-Car CAN driver Add support for the CAN controller found in Renesas R-Car SoCs. Signed-off-by: Sergei Shtylyov Signed-off-by: Marc Kleine-Budde --- include/linux/can/platform/rcar_can.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 include/linux/can/platform/rcar_can.h (limited to 'include/linux') diff --git a/include/linux/can/platform/rcar_can.h b/include/linux/can/platform/rcar_can.h new file mode 100644 index 000000000000..0f4a2f3df504 --- /dev/null +++ b/include/linux/can/platform/rcar_can.h @@ -0,0 +1,17 @@ +#ifndef _CAN_PLATFORM_RCAR_CAN_H_ +#define _CAN_PLATFORM_RCAR_CAN_H_ + +#include + +/* Clock Select Register settings */ +enum CLKR { + CLKR_CLKP1 = 0, /* Peripheral clock (clkp1) */ + CLKR_CLKP2 = 1, /* Peripheral clock (clkp2) */ + CLKR_CLKEXT = 3 /* Externally input clock */ +}; + +struct rcar_can_platform_data { + enum CLKR clock_select; /* Clock source select */ +}; + +#endif /* !_CAN_PLATFORM_RCAR_CAN_H_ */ -- cgit v1.2.3 From 42193e3efb632c84d686acacd7b2327f2b1f8c63 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Thu, 15 May 2014 20:31:56 +0200 Subject: can: unify identifiers to ensure unique include processing Armin pointed me to the fact that the identifier which is used to ensure the unique include processing in lunux/include/uapi/linux/can.h is CAN_H. This clashed with his own source as includes from libraries and APIs should use an underscore '_' at the identifier start. This patch fixes the protection identifiers in all CAN relavant includes. Reported-by: Armin Burchardt Signed-off-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- include/linux/can/core.h | 6 +++--- include/linux/can/dev.h | 6 +++--- include/linux/can/led.h | 6 +++--- include/linux/can/platform/cc770.h | 6 +++--- include/linux/can/platform/mcp251x.h | 6 +++--- include/linux/can/platform/sja1000.h | 6 +++--- include/linux/can/platform/ti_hecc.h | 6 +++--- include/linux/can/skb.h | 6 +++--- 8 files changed, 24 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/can/core.h b/include/linux/can/core.h index 78c6c52073ad..a0875001b13c 100644 --- a/include/linux/can/core.h +++ b/include/linux/can/core.h @@ -10,8 +10,8 @@ * */ -#ifndef CAN_CORE_H -#define CAN_CORE_H +#ifndef _CAN_CORE_H +#define _CAN_CORE_H #include #include @@ -58,4 +58,4 @@ extern void can_rx_unregister(struct net_device *dev, canid_t can_id, extern int can_send(struct sk_buff *skb, int loop); extern int can_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); -#endif /* CAN_CORE_H */ +#endif /* !_CAN_CORE_H */ diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 3ce5e526525f..6992afc6ba7f 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -10,8 +10,8 @@ * */ -#ifndef CAN_DEV_H -#define CAN_DEV_H +#ifndef _CAN_DEV_H +#define _CAN_DEV_H #include #include @@ -132,4 +132,4 @@ struct sk_buff *alloc_canfd_skb(struct net_device *dev, struct sk_buff *alloc_can_err_skb(struct net_device *dev, struct can_frame **cf); -#endif /* CAN_DEV_H */ +#endif /* !_CAN_DEV_H */ diff --git a/include/linux/can/led.h b/include/linux/can/led.h index 9c1167baf273..e0475c5cbb92 100644 --- a/include/linux/can/led.h +++ b/include/linux/can/led.h @@ -6,8 +6,8 @@ * published by the Free Software Foundation. */ -#ifndef CAN_LED_H -#define CAN_LED_H +#ifndef _CAN_LED_H +#define _CAN_LED_H #include #include @@ -48,4 +48,4 @@ static inline void can_led_notifier_exit(void) #endif -#endif +#endif /* !_CAN_LED_H */ diff --git a/include/linux/can/platform/cc770.h b/include/linux/can/platform/cc770.h index 7702641f87ee..78b2d44f04cf 100644 --- a/include/linux/can/platform/cc770.h +++ b/include/linux/can/platform/cc770.h @@ -1,5 +1,5 @@ -#ifndef _CAN_PLATFORM_CC770_H_ -#define _CAN_PLATFORM_CC770_H_ +#ifndef _CAN_PLATFORM_CC770_H +#define _CAN_PLATFORM_CC770_H /* CPU Interface Register (0x02) */ #define CPUIF_CEN 0x01 /* Clock Out Enable */ @@ -30,4 +30,4 @@ struct cc770_platform_data { u8 bcr; /* Bus Configuration Register */ }; -#endif /* !_CAN_PLATFORM_CC770_H_ */ +#endif /* !_CAN_PLATFORM_CC770_H */ diff --git a/include/linux/can/platform/mcp251x.h b/include/linux/can/platform/mcp251x.h index dc029dba7a03..d44fcae274ff 100644 --- a/include/linux/can/platform/mcp251x.h +++ b/include/linux/can/platform/mcp251x.h @@ -1,5 +1,5 @@ -#ifndef __CAN_PLATFORM_MCP251X_H__ -#define __CAN_PLATFORM_MCP251X_H__ +#ifndef _CAN_PLATFORM_MCP251X_H +#define _CAN_PLATFORM_MCP251X_H /* * @@ -18,4 +18,4 @@ struct mcp251x_platform_data { unsigned long oscillator_frequency; }; -#endif /* __CAN_PLATFORM_MCP251X_H__ */ +#endif /* !_CAN_PLATFORM_MCP251X_H */ diff --git a/include/linux/can/platform/sja1000.h b/include/linux/can/platform/sja1000.h index 96f8fcc78d78..93570b61ec6c 100644 --- a/include/linux/can/platform/sja1000.h +++ b/include/linux/can/platform/sja1000.h @@ -1,5 +1,5 @@ -#ifndef _CAN_PLATFORM_SJA1000_H_ -#define _CAN_PLATFORM_SJA1000_H_ +#ifndef _CAN_PLATFORM_SJA1000_H +#define _CAN_PLATFORM_SJA1000_H /* clock divider register */ #define CDR_CLKOUT_MASK 0x07 @@ -32,4 +32,4 @@ struct sja1000_platform_data { u8 cdr; /* clock divider register */ }; -#endif /* !_CAN_PLATFORM_SJA1000_H_ */ +#endif /* !_CAN_PLATFORM_SJA1000_H */ diff --git a/include/linux/can/platform/ti_hecc.h b/include/linux/can/platform/ti_hecc.h index af17cb3f7a84..a52f47ca6c8a 100644 --- a/include/linux/can/platform/ti_hecc.h +++ b/include/linux/can/platform/ti_hecc.h @@ -1,5 +1,5 @@ -#ifndef __CAN_PLATFORM_TI_HECC_H__ -#define __CAN_PLATFORM_TI_HECC_H__ +#ifndef _CAN_PLATFORM_TI_HECC_H +#define _CAN_PLATFORM_TI_HECC_H /* * TI HECC (High End CAN Controller) driver platform header @@ -41,4 +41,4 @@ struct ti_hecc_platform_data { u32 version; void (*transceiver_switch) (int); }; -#endif +#endif /* !_CAN_PLATFORM_TI_HECC_H */ diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index f9bbbb472663..cc00d15c6107 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -7,8 +7,8 @@ * */ -#ifndef CAN_SKB_H -#define CAN_SKB_H +#ifndef _CAN_SKB_H +#define _CAN_SKB_H #include #include @@ -80,4 +80,4 @@ static inline struct sk_buff *can_create_echo_skb(struct sk_buff *skb) return skb; } -#endif /* CAN_SKB_H */ +#endif /* !_CAN_SKB_H */ -- cgit v1.2.3 From 4f4aa2ec24dc45881849833a439558d3a378028c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Sun, 18 May 2014 00:22:38 +0200 Subject: ssb: sprom: add dev_id field for value overriding standard ID MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some devices may have different features despite sharing the same ID (e.g. PCI ID). For example 14e4:4331 is usually a dual band, but this can be "limited". Device with "pci/x/y/devid=0x4332" supports 2.4 GHz only. Similarly 0x4333 will mean support for 5 GHz only. Add entry in SPROM so info described above can be extracted and stored. Signed-off-by: Rafał Miłecki Acked-by: Hauke Mehrtens Signed-off-by: John W. Linville --- include/linux/ssb/ssb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 07ef9b82b66d..4568a5cc9ab8 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -33,6 +33,7 @@ struct ssb_sprom { u8 et1phyaddr; /* MII address for enet1 */ u8 et0mdcport; /* MDIO for enet0 */ u8 et1mdcport; /* MDIO for enet1 */ + u16 dev_id; /* Device ID overriding e.g. PCI ID */ u16 board_rev; /* Board revision number from SPROM. */ u16 board_num; /* Board number from SPROM. */ u16 board_type; /* Board type from SPROM. */ -- cgit v1.2.3 From 7d10d2610cc02d432168ca0c5d964cd9e85c1b06 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Mon, 19 May 2014 09:21:09 +0200 Subject: net: cdc_ncm: fix 64bit division build error MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The upper timer_interval limit is arbitrary and much higher than anything usable in the real world. Reducing it from 15s to ~4s to make the timer_interval fit in an u32 does not make much difference. The limit is still outside the practical bounds. This eliminates the need for a 64bit timer_interval, fixing a build error related to 64bit division: drivers/built-in.o: In function `cdc_ncm_get_coalesce': ak8975.c:(.text+0x1ac994): undefined reference to `__aeabi_uldivmod' Reported-by: Stephen Rothwell Signed-off-by: Bjørn Mork Signed-off-by: David S. Miller --- include/linux/usb/cdc_ncm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index 8c5e38819828..7c9b484735c5 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -78,7 +78,7 @@ #define CDC_NCM_TIMER_PENDING_CNT 2 #define CDC_NCM_TIMER_INTERVAL_USEC 400UL #define CDC_NCM_TIMER_INTERVAL_MIN 5UL -#define CDC_NCM_TIMER_INTERVAL_MAX (15UL * USEC_PER_SEC) +#define CDC_NCM_TIMER_INTERVAL_MAX (U32_MAX / NSEC_PER_USEC) #define cdc_ncm_comm_intf_is_mbim(x) ((x)->desc.bInterfaceSubClass == USB_CDC_SUBCLASS_MBIM && \ (x)->desc.bInterfaceProtocol == USB_CDC_PROTO_NONE) @@ -104,7 +104,7 @@ struct cdc_ncm_ctx { spinlock_t mtx; atomic_t stop; - u64 timer_interval; + u32 timer_interval; u32 max_ndp_size; u32 tx_timer_pending; -- cgit v1.2.3 From 5fe821a9dee241fa450703ab7015d970ee0cfb8d Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 19 May 2014 14:56:14 -0700 Subject: net: filter: cleanup invocation of internal BPF Kernel API for classic BPF socket filters is: sk_unattached_filter_create() - validate classic BPF, convert, JIT SK_RUN_FILTER() - run it sk_unattached_filter_destroy() - destroy socket filter Cleanup internal BPF kernel API as following: sk_filter_select_runtime() - final step of internal BPF creation. Try to JIT internal BPF program, if JIT is not available select interpreter SK_RUN_FILTER() - run it sk_filter_free() - free internal BPF program Disallow direct calls to BPF interpreter. Execution of the BPF program should be done with SK_RUN_FILTER() macro. Example of internal BPF create, run, destroy: struct sk_filter *fp; fp = kzalloc(sk_filter_size(prog_len), GFP_KERNEL); memcpy(fp->insni, prog, prog_len * sizeof(fp->insni[0])); fp->len = prog_len; sk_filter_select_runtime(fp); SK_RUN_FILTER(fp, ctx); sk_filter_free(fp); Sockets, seccomp, testsuite, tracing are using different ways to populate sk_filter, so first steps of program creation are not common. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/filter.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 9d5ae0a2c954..7977b3958e25 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -184,10 +184,8 @@ static inline unsigned int sk_filter_size(unsigned int proglen) int sk_filter(struct sock *sk, struct sk_buff *skb); -u32 sk_run_filter_int_seccomp(const struct seccomp_data *ctx, - const struct sock_filter_int *insni); -u32 sk_run_filter_int_skb(const struct sk_buff *ctx, - const struct sock_filter_int *insni); +void sk_filter_select_runtime(struct sk_filter *fp); +void sk_filter_free(struct sk_filter *fp); int sk_convert_filter(struct sock_filter *prog, int len, struct sock_filter_int *new_prog, int *new_len); -- cgit v1.2.3 From ca8a22634381537c92b5a10308652e1c38fd9edf Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Thu, 22 May 2014 10:41:08 -0400 Subject: tcp: make cwnd-limited checks measurement-based, and gentler Experience with the recent e114a710aa50 ("tcp: fix cwnd limited checking to improve congestion control") has shown that there are common cases where that commit can cause cwnd to be much larger than necessary. This leads to TSO autosizing cooking skbs that are too large, among other things. The main problems seemed to be: (1) That commit attempted to predict the future behavior of the connection by looking at the write queue (if TSO or TSQ limit sending). That prediction sometimes overestimated future outstanding packets. (2) That commit always allowed cwnd to grow to twice the number of outstanding packets (even in congestion avoidance, where this is not needed). This commit improves both of these, by: (1) Switching to a measurement-based approach where we explicitly track the largest number of packets in flight during the past window ("max_packets_out"), and remember whether we were cwnd-limited at the moment we finished sending that flight. (2) Only allowing cwnd to grow to twice the number of outstanding packets ("max_packets_out") in slow start. In congestion avoidance mode we now only allow cwnd to grow if it was fully utilized. Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index bc35e4709e8e..a0513210798f 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -197,7 +197,8 @@ struct tcp_sock { u8 do_early_retrans:1,/* Enable RFC5827 early-retransmit */ syn_data:1, /* SYN includes data */ syn_fastopen:1, /* SYN includes Fast Open option */ - syn_data_acked:1;/* data in SYN is acked by SYN-ACK */ + syn_data_acked:1,/* data in SYN is acked by SYN-ACK */ + is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */ u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */ /* RTT measurement */ @@ -209,6 +210,8 @@ struct tcp_sock { u32 packets_out; /* Packets which are "in flight" */ u32 retrans_out; /* Retransmitted packets out */ + u32 max_packets_out; /* max packets_out in last window */ + u32 max_packets_seq; /* right edge of max_packets_out flight */ u16 urg_data; /* Saved octet of OOB data and control flags */ u8 ecn_flags; /* ECN status bits. */ @@ -230,7 +233,6 @@ struct tcp_sock { u32 snd_cwnd_clamp; /* Do not allow snd_cwnd to grow above this */ u32 snd_cwnd_used; u32 snd_cwnd_stamp; - u32 lsnd_pending; /* packets inflight or unsent since last xmit */ u32 prior_cwnd; /* Congestion window at start of Recovery. */ u32 prr_delivered; /* Number of newly delivered packets to * receiver in Recovery. */ -- cgit v1.2.3 From da08143b85203b581f4a6461b149186b0e9592df Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michal=20Kube=C4=8Dek?= Date: Tue, 20 May 2014 08:29:25 +0200 Subject: vlan: more careful checksum features handling When combining real_dev's features and vlan_features, simple bitwise AND is used. This doesn't work well for checksum offloading features as if one set has NETIF_F_HW_CSUM and the other NETIF_F_IP_CSUM and/or NETIF_F_IPV6_CSUM, we end up with no checksum offloading. However, from the logical point of view (how can_checksum_protocol() works), NETIF_F_HW_CSUM contains the functionality of NETIF_F_IP_CSUM and NETIF_F_IPV6_CSUM so that the result should be IP/IPV6. Add helper function netdev_intersect_features() implementing this logic and use it in vlan_dev_fix_features(). Signed-off-by: Michal Kubecek Signed-off-by: David S. Miller --- include/linux/netdevice.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2dea98cbbdba..f4ad247fd324 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3153,6 +3153,20 @@ const char *netdev_drivername(const struct net_device *dev); void linkwatch_run_queue(void); +static inline netdev_features_t netdev_intersect_features(netdev_features_t f1, + netdev_features_t f2) +{ + if (f1 & NETIF_F_GEN_CSUM) + f1 |= (NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); + if (f2 & NETIF_F_GEN_CSUM) + f2 |= (NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); + f1 &= f2; + if (f1 & NETIF_F_GEN_CSUM) + f1 &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); + + return f1; +} + static inline netdev_features_t netdev_get_wanted_features( struct net_device *dev) { -- cgit v1.2.3 From ea3429c77d4e34cb2983b90e49a5506fedf70b98 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 22 May 2014 09:47:50 -0700 Subject: of: mdio: remove of_phy_connect_fixed_link All in-tree drivers have been converted to use the new pair of functions: of_is_fixed_phy_link() plus of_phy_register_fixed_link(), we can now safely remove of_phy_connect_fixed_link. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/of_mdio.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 0aa367e316cb..d449018d0726 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -22,9 +22,6 @@ extern struct phy_device *of_phy_connect(struct net_device *dev, struct phy_device *of_phy_attach(struct net_device *dev, struct device_node *phy_np, u32 flags, phy_interface_t iface); -extern struct phy_device *of_phy_connect_fixed_link(struct net_device *dev, - void (*hndlr)(struct net_device *), - phy_interface_t iface); extern struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np); @@ -59,13 +56,6 @@ static inline struct phy_device *of_phy_attach(struct net_device *dev, return NULL; } -static inline struct phy_device *of_phy_connect_fixed_link(struct net_device *dev, - void (*hndlr)(struct net_device *), - phy_interface_t iface) -{ - return NULL; -} - static inline struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np) { return NULL; -- cgit v1.2.3 From ecc8fb11cdb37d108d4597ba0f6bdff77c6019af Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Thu, 22 May 2014 15:55:39 +0300 Subject: net/mlx4_core: Deprecate use_prio module parameter use_prio was added as part of an infrastructure for running FCoE in A0 mode. FCoE didn't get into Mellanox Upstream driver, and when it will, it won't be using A0 steering mode. Therefore we can safely deprecate this module parameter without hurting any existing user. CC: Carol Soto Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index c0468e6f0442..ca38871a585c 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -449,7 +449,6 @@ struct mlx4_caps { int reserved_qps_base[MLX4_NUM_QP_REGION]; int log_num_macs; int log_num_vlans; - int log_num_prios; enum mlx4_port_type port_type[MLX4_MAX_PORTS + 1]; u8 supported_type[MLX4_MAX_PORTS + 1]; u8 suggested_type[MLX4_MAX_PORTS + 1]; -- cgit v1.2.3 From ed616689a3d95eb6c9bdbb1ef74b0f50cbdf276a Mon Sep 17 00:00:00 2001 From: Sucheta Chakraborty Date: Thu, 22 May 2014 09:59:05 -0400 Subject: net-next:v4: Add support to configure SR-IOV VF minimum and maximum Tx rate through ip tool. o min_tx_rate puts lower limit on the VF bandwidth. VF is guaranteed to have a bandwidth of at least this value. max_tx_rate puts cap on the VF bandwidth. VF can have a bandwidth of up to this value. o A new handler set_vf_rate for attr IFLA_VF_RATE has been introduced which takes 4 arguments: netdev, VF number, min_tx_rate, max_tx_rate o ndo_set_vf_rate replaces ndo_set_vf_tx_rate handler. o Drivers that currently implement ndo_set_vf_tx_rate should now call ndo_set_vf_rate instead and reject attempt to set a minimum bandwidth greater than 0 for IFLA_VF_TX_RATE when IFLA_VF_RATE is not yet implemented by driver. o If user enters only one of either min_tx_rate or max_tx_rate, then, userland should read back the other value from driver and set both for IFLA_VF_RATE. Drivers that have not yet implemented IFLA_VF_RATE should always return min_tx_rate as 0 when read from ip tool. o If both IFLA_VF_TX_RATE and IFLA_VF_RATE options are specified, then IFLA_VF_RATE should override. o Idea is to have consistent display of rate values to user. o Usage example: - ./ip link set p4p1 vf 0 rate 900 ./ip link show p4p1 32: p4p1: mtu 1500 qdisc noop state DOWN mode DEFAULT qlen 1000 link/ether 00:0e:1e:08:b0:f0 brd ff:ff:ff:ff:ff:ff vf 0 MAC 3e:a0:ca:bd:ae:5a, tx rate 900 (Mbps), max_tx_rate 900Mbps vf 1 MAC f6:c6:7c:3f:3d:6c vf 2 MAC 56:32:43:98:d7:71 vf 3 MAC d6:be:c3:b5:85:ff vf 4 MAC ee:a9:9a:1e:19:14 vf 5 MAC 4a:d0:4c:07:52:18 vf 6 MAC 3a:76:44:93:62:f9 vf 7 MAC 82:e9:e7:e3:15:1a ./ip link set p4p1 vf 0 max_tx_rate 300 min_tx_rate 200 ./ip link show p4p1 32: p4p1: mtu 1500 qdisc noop state DOWN mode DEFAULT qlen 1000 link/ether 00:0e:1e:08:b0:f0 brd ff:ff:ff:ff:ff:ff vf 0 MAC 3e:a0:ca:bd:ae:5a, tx rate 300 (Mbps), max_tx_rate 300Mbps, min_tx_rate 200Mbps vf 1 MAC f6:c6:7c:3f:3d:6c vf 2 MAC 56:32:43:98:d7:71 vf 3 MAC d6:be:c3:b5:85:ff vf 4 MAC ee:a9:9a:1e:19:14 vf 5 MAC 4a:d0:4c:07:52:18 vf 6 MAC 3a:76:44:93:62:f9 vf 7 MAC 82:e9:e7:e3:15:1a ./ip link set p4p1 vf 0 max_tx_rate 600 rate 300 ./ip link show p4p1 32: p4p1: mtu 1500 qdisc noop state DOWN mode DEFAULT qlen 1000 link/ether 00:0e:1e:08:b0:f brd ff:ff:ff:ff:ff:ff vf 0 MAC 3e:a0:ca:bd:ae:5, tx rate 600 (Mbps), max_tx_rate 600Mbps, min_tx_rate 200Mbps vf 1 MAC f6:c6:7c:3f:3d:6c vf 2 MAC 56:32:43:98:d7:71 vf 3 MAC d6:be:c3:b5:85:ff vf 4 MAC ee:a9:9a:1e:19:14 vf 5 MAC 4a:d0:4c:07:52:18 vf 6 MAC 3a:76:44:93:62:f9 vf 7 MAC 82:e9:e7:e3:15:1a Signed-off-by: Sucheta Chakraborty Signed-off-by: David S. Miller --- include/linux/if_link.h | 3 ++- include/linux/netdevice.h | 8 +++++--- 2 files changed, 7 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_link.h b/include/linux/if_link.h index a86784dec3d3..119130e9298b 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -10,8 +10,9 @@ struct ifla_vf_info { __u8 mac[32]; __u32 vlan; __u32 qos; - __u32 tx_rate; __u32 spoofchk; __u32 linkstate; + __u32 min_tx_rate; + __u32 max_tx_rate; }; #endif /* _LINUX_IF_LINK_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f4ad247fd324..9ec3a945caf2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -850,7 +850,8 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * SR-IOV management functions. * int (*ndo_set_vf_mac)(struct net_device *dev, int vf, u8* mac); * int (*ndo_set_vf_vlan)(struct net_device *dev, int vf, u16 vlan, u8 qos); - * int (*ndo_set_vf_tx_rate)(struct net_device *dev, int vf, int rate); + * int (*ndo_set_vf_rate)(struct net_device *dev, int vf, int min_tx_rate, + * int max_tx_rate); * int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting); * int (*ndo_get_vf_config)(struct net_device *dev, * int vf, struct ifla_vf_info *ivf); @@ -1044,8 +1045,9 @@ struct net_device_ops { int queue, u8 *mac); int (*ndo_set_vf_vlan)(struct net_device *dev, int queue, u16 vlan, u8 qos); - int (*ndo_set_vf_tx_rate)(struct net_device *dev, - int vf, int rate); + int (*ndo_set_vf_rate)(struct net_device *dev, + int vf, int min_tx_rate, + int max_tx_rate); int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting); int (*ndo_get_vf_config)(struct net_device *dev, -- cgit v1.2.3 From 1c19448c9ba6545b80ded18488a64a7f3d8e6998 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Fri, 23 May 2014 08:47:32 -0700 Subject: net: Make enabling of zero UDP6 csums more restrictive RFC 6935 permits zero checksums to be used in IPv6 however this is recommended only for certain tunnel protocols, it does not make checksums completely optional like they are in IPv4. This patch restricts the use of IPv6 zero checksums that was previously intoduced. no_check6_tx and no_check6_rx have been added to control the use of checksums in UDP6 RX and TX path. The normal sk_no_check_{rx,tx} settings are not used (this avoids ambiguity when dealing with a dual stack socket). A helper function has been added (udp_set_no_check6) which can be called by tunnel impelmentations to all zero checksums (send on the socket, and accept them as valid). Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/udp.h | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/udp.h b/include/linux/udp.h index 42278bbf7a88..247cfdcc4b08 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -47,7 +47,9 @@ struct udp_sock { #define udp_portaddr_node inet.sk.__sk_common.skc_portaddr_node int pending; /* Any pending frames ? */ unsigned int corkflag; /* Cork is required */ - __u16 encap_type; /* Is this an Encapsulation socket? */ + __u8 encap_type; /* Is this an Encapsulation socket? */ + unsigned char no_check6_tx:1,/* Send zero UDP6 checksums on TX? */ + no_check6_rx:1;/* Allow zero UDP6 checksums on RX? */ /* * Following member retains the information to create a UDP header * when the socket is uncorked. @@ -76,6 +78,26 @@ static inline struct udp_sock *udp_sk(const struct sock *sk) return (struct udp_sock *)sk; } +static inline void udp_set_no_check6_tx(struct sock *sk, bool val) +{ + udp_sk(sk)->no_check6_tx = val; +} + +static inline void udp_set_no_check6_rx(struct sock *sk, bool val) +{ + udp_sk(sk)->no_check6_rx = val; +} + +static inline bool udp_get_no_check6_tx(struct sock *sk) +{ + return udp_sk(sk)->no_check6_tx; +} + +static inline bool udp_get_no_check6_rx(struct sock *sk) +{ + return udp_sk(sk)->no_check6_rx; +} + #define udp_portaddr_for_each_entry(__sk, node, list) \ hlist_nulls_for_each_entry(__sk, node, list, __sk_common.skc_portaddr_node) -- cgit v1.2.3 From 8556ce79d5986a87fee4c29300b4efee07c0f15e Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 23 May 2014 18:43:57 +0200 Subject: net: filter: remove DL macro Lets get rid of this macro. After commit 5bcfedf06f7f ("net: filter: simplify label names from jump-table"), labels have become more readable due to omission of BPF_ prefix but at the same time more generic, so that things like `git grep -n` would not find them. As a middle path, lets get rid of the DL macro as it's not strictly needed and would otherwise just hide the full name. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/filter.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 7977b3958e25..2b0056afd1f7 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -37,9 +37,6 @@ #define BPF_CALL 0x80 /* function call */ #define BPF_EXIT 0x90 /* function return */ -/* Placeholder/dummy for 0 */ -#define BPF_0 0 - /* Register numbers */ enum { BPF_REG_0 = 0, -- cgit v1.2.3 From b1fcd35cf53553a0a3ef949b05106d921446abc3 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 23 May 2014 18:43:58 +0200 Subject: net: filter: let unattached filters use sock_fprog_kern The sk_unattached_filter_create() API is used by BPF filters that are not directly attached or related to sockets, and are used in team, ptp, xt_bpf, cls_bpf, etc. As such all users do their own internal managment of obtaining filter blocks and thus already have them in kernel memory and set up before calling into sk_unattached_filter_create(). As a result, due to __user annotation in sock_fprog, sparse triggers false positives (incorrect type in assignment [different address space]) when filters are set up before passing them to sk_unattached_filter_create(). Therefore, let sk_unattached_filter_create() API use sock_fprog_kern to overcome this issue. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/filter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 2b0056afd1f7..625f4de9bdf2 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -188,7 +188,7 @@ int sk_convert_filter(struct sock_filter *prog, int len, struct sock_filter_int *new_prog, int *new_len); int sk_unattached_filter_create(struct sk_filter **pfp, - struct sock_fprog *fprog); + struct sock_fprog_kern *fprog); void sk_unattached_filter_destroy(struct sk_filter *fp); int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); -- cgit v1.2.3 From 494b6590043b4cd73ceb3f58e1c012a2c6c98d85 Mon Sep 17 00:00:00 2001 From: Jes Sorensen Date: Mon, 26 May 2014 18:06:34 +0200 Subject: wireless: add missing WLAN_EID_BSS_INTOLERANT_CHL_REPORT Signed-off-by: Jes Sorensen Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index f194ccb8539c..6bff13f74050 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1711,6 +1711,7 @@ enum ieee80211_eid { WLAN_EID_RRM_ENABLED_CAPABILITIES = 70, WLAN_EID_MULTIPLE_BSSID = 71, WLAN_EID_BSS_COEX_2040 = 72, + WLAN_EID_BSS_INTOLERANT_CHL_REPORT = 73, WLAN_EID_OVERLAP_BSS_SCAN_PARAM = 74, WLAN_EID_RIC_DESCRIPTOR = 75, WLAN_EID_MMIE = 76, -- cgit v1.2.3 From 86f6cf41272de9d6ffa05ab46028b15d160a6f3e Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Sat, 24 May 2014 09:34:26 +0200 Subject: net: of_mdio: add of_mdiobus_link_phydev() Add a function to walk the list of subnodes of a mdio bus and look for a node that matches the phy's address with its 'reg' property. If found, set the of_node pointer for the phy. This allows auto-probed pyh devices to be augmented by information passed in via DT. Signed-off-by: Daniel Mack Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/of_mdio.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index d449018d0726..a70c9493d55a 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -25,6 +25,9 @@ struct phy_device *of_phy_attach(struct net_device *dev, extern struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np); +extern void of_mdiobus_link_phydev(struct mii_bus *mdio, + struct phy_device *phydev); + #else /* CONFIG_OF */ static inline int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) { @@ -60,6 +63,11 @@ static inline struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np) { return NULL; } + +static inline void of_mdiobus_link_phydev(struct mii_bus *mdio, + struct phy_device *phydev) +{ +} #endif /* CONFIG_OF */ #if defined(CONFIG_OF) && defined(CONFIG_FIXED_PHY) -- cgit v1.2.3 From c8865b64b05b2f4eeefd369373e9c8aeb069e7a1 Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Sun, 25 May 2014 17:47:26 +0300 Subject: cpumask: Utility function to set n'th cpu - local cpu first This function sets the n'th cpu - local cpu's first. For example: in a 16 cores server with even cpu's local, will get the following values: cpumask_set_cpu_local_first(0, numa, cpumask) => cpu 0 is set cpumask_set_cpu_local_first(1, numa, cpumask) => cpu 2 is set ... cpumask_set_cpu_local_first(7, numa, cpumask) => cpu 14 is set cpumask_set_cpu_local_first(8, numa, cpumask) => cpu 1 is set cpumask_set_cpu_local_first(9, numa, cpumask) => cpu 3 is set ... cpumask_set_cpu_local_first(15, numa, cpumask) => cpu 15 is set Curently this function will be used by multi queue networking devices to calculate the irq affinity mask, such that as many local cpu's as possible will be utilized to handle the mq device irq's. Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/cpumask.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index d08e4d2a9b92..3551d667ef9f 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -257,6 +257,8 @@ static inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } +int cpumask_set_cpu_local_first(int i, int numa_node, cpumask_t *dstp); + /** * cpumask_clear_cpu - clear a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) -- cgit v1.2.3 From 70a640d0dae3a9b1b222ce673eb5d92c263ddd61 Mon Sep 17 00:00:00 2001 From: Yuval Atias Date: Sun, 25 May 2014 17:47:27 +0300 Subject: net/mlx4_en: Use affinity hint MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The “affinity hint” mechanism is used by the user space daemon, irqbalancer, to indicate a preferred CPU mask for irqs. Irqbalancer can use this hint to balance the irqs between the cpus indicated by the mask. We wish the HCA to preferentially map the IRQs it uses to numa cores close to it. To accomplish this, we use cpumask_set_cpu_local_first(), that sets the affinity hint according the following policy: First it maps IRQs to “close” numa cores. If these are exhausted, the remaining IRQs are mapped to “far” numa cores. Signed-off-by: Yuval Atias Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index ca38871a585c..b9b70e00e3c1 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -1161,7 +1161,7 @@ int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr); int mlx4_SYNC_TPT(struct mlx4_dev *dev); int mlx4_test_interrupts(struct mlx4_dev *dev); int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap, - int *vector); + int *vector, cpumask_t *cpu_hint_mask); void mlx4_release_eq(struct mlx4_dev *dev, int vec); int mlx4_get_phys_port_id(struct mlx4_dev *dev); -- cgit v1.2.3 From ee39facbf82e73e468c504d2b40e83e2d223c28c Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sun, 1 Jun 2014 21:58:02 -0700 Subject: net: Revert mlx4 cpumask changes. This reverts commit 70a640d0dae3a9b1b222ce673eb5d92c263ddd61 ("net/mlx4_en: Use affinity hint") and commit c8865b64b05b2f4eeefd369373e9c8aeb069e7a1 ("cpumask: Utility function to set n'th cpu - local cpu first") because these changes break the build when SMP is disabled amongst other things. Reported-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/cpumask.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 3551d667ef9f..d08e4d2a9b92 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -257,8 +257,6 @@ static inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } -int cpumask_set_cpu_local_first(int i, int numa_node, cpumask_t *dstp); - /** * cpumask_clear_cpu - clear a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) -- cgit v1.2.3 From 3480593131e0b781287dae0139bf7ccee7cba7ff Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 29 May 2014 10:22:50 +0200 Subject: net: filter: get rid of BPF_S_* enum This patch finally allows us to get rid of the BPF_S_* enum. Currently, the code performs unnecessary encode and decode workarounds in seccomp and filter migration itself when a filter is being attached in order to overcome BPF_S_* encoding which is not used anymore by the new interpreter resp. JIT compilers. Keeping it around would mean that also in future we would need to extend and maintain this enum and related encoders/decoders. We can get rid of all that and save us these operations during filter attaching. Naturally, also JIT compilers need to be updated by this. Before JIT conversion is being done, each compiler checks if A is being loaded at startup to obtain information if it needs to emit instructions to clear A first. Since BPF extensions are a subset of BPF_LD | BPF_{W,H,B} | BPF_ABS variants, case statements for extensions can be removed at that point. To ease and minimalize code changes in the classic JITs, we have introduced bpf_anc_helper(). Tested with test_bpf on x86_64 (JIT, int), s390x (JIT, int), arm (JIT, int), i368 (int), ppc64 (JIT, int); for sparc we unfortunately didn't have access, but changes are analogous to the rest. Joint work with Alexei Starovoitov. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Cc: Benjamin Herrenschmidt Cc: Martin Schwidefsky Cc: Mircea Gherzan Cc: Kees Cook Acked-by: Chema Gonzalez Signed-off-by: David S. Miller --- include/linux/filter.h | 108 +++++++++++++++++-------------------------------- 1 file changed, 38 insertions(+), 70 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 625f4de9bdf2..49ef7a298c92 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -197,7 +197,6 @@ int sk_detach_filter(struct sock *sk); int sk_chk_filter(struct sock_filter *filter, unsigned int flen); int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned int len); -void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to); void sk_filter_charge(struct sock *sk, struct sk_filter *fp); void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp); @@ -205,6 +204,41 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp); u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); void bpf_int_jit_compile(struct sk_filter *fp); +#define BPF_ANC BIT(15) + +static inline u16 bpf_anc_helper(const struct sock_filter *ftest) +{ + BUG_ON(ftest->code & BPF_ANC); + + switch (ftest->code) { + case BPF_LD | BPF_W | BPF_ABS: + case BPF_LD | BPF_H | BPF_ABS: + case BPF_LD | BPF_B | BPF_ABS: +#define BPF_ANCILLARY(CODE) case SKF_AD_OFF + SKF_AD_##CODE: \ + return BPF_ANC | SKF_AD_##CODE + switch (ftest->k) { + BPF_ANCILLARY(PROTOCOL); + BPF_ANCILLARY(PKTTYPE); + BPF_ANCILLARY(IFINDEX); + BPF_ANCILLARY(NLATTR); + BPF_ANCILLARY(NLATTR_NEST); + BPF_ANCILLARY(MARK); + BPF_ANCILLARY(QUEUE); + BPF_ANCILLARY(HATYPE); + BPF_ANCILLARY(RXHASH); + BPF_ANCILLARY(CPU); + BPF_ANCILLARY(ALU_XOR_X); + BPF_ANCILLARY(VLAN_TAG); + BPF_ANCILLARY(VLAN_TAG_PRESENT); + BPF_ANCILLARY(PAY_OFFSET); + BPF_ANCILLARY(RANDOM); + } + /* Fallthrough. */ + default: + return ftest->code; + } +} + #ifdef CONFIG_BPF_JIT #include #include @@ -224,86 +258,20 @@ static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen, } #else #include + static inline void bpf_jit_compile(struct sk_filter *fp) { } + static inline void bpf_jit_free(struct sk_filter *fp) { kfree(fp); } -#endif +#endif /* CONFIG_BPF_JIT */ static inline int bpf_tell_extensions(void) { return SKF_AD_MAX; } -enum { - BPF_S_RET_K = 1, - BPF_S_RET_A, - BPF_S_ALU_ADD_K, - BPF_S_ALU_ADD_X, - BPF_S_ALU_SUB_K, - BPF_S_ALU_SUB_X, - BPF_S_ALU_MUL_K, - BPF_S_ALU_MUL_X, - BPF_S_ALU_DIV_X, - BPF_S_ALU_MOD_K, - BPF_S_ALU_MOD_X, - BPF_S_ALU_AND_K, - BPF_S_ALU_AND_X, - BPF_S_ALU_OR_K, - BPF_S_ALU_OR_X, - BPF_S_ALU_XOR_K, - BPF_S_ALU_XOR_X, - BPF_S_ALU_LSH_K, - BPF_S_ALU_LSH_X, - BPF_S_ALU_RSH_K, - BPF_S_ALU_RSH_X, - BPF_S_ALU_NEG, - BPF_S_LD_W_ABS, - BPF_S_LD_H_ABS, - BPF_S_LD_B_ABS, - BPF_S_LD_W_LEN, - BPF_S_LD_W_IND, - BPF_S_LD_H_IND, - BPF_S_LD_B_IND, - BPF_S_LD_IMM, - BPF_S_LDX_W_LEN, - BPF_S_LDX_B_MSH, - BPF_S_LDX_IMM, - BPF_S_MISC_TAX, - BPF_S_MISC_TXA, - BPF_S_ALU_DIV_K, - BPF_S_LD_MEM, - BPF_S_LDX_MEM, - BPF_S_ST, - BPF_S_STX, - BPF_S_JMP_JA, - BPF_S_JMP_JEQ_K, - BPF_S_JMP_JEQ_X, - BPF_S_JMP_JGE_K, - BPF_S_JMP_JGE_X, - BPF_S_JMP_JGT_K, - BPF_S_JMP_JGT_X, - BPF_S_JMP_JSET_K, - BPF_S_JMP_JSET_X, - /* Ancillary data */ - BPF_S_ANC_PROTOCOL, - BPF_S_ANC_PKTTYPE, - BPF_S_ANC_IFINDEX, - BPF_S_ANC_NLATTR, - BPF_S_ANC_NLATTR_NEST, - BPF_S_ANC_MARK, - BPF_S_ANC_QUEUE, - BPF_S_ANC_HATYPE, - BPF_S_ANC_RXHASH, - BPF_S_ANC_CPU, - BPF_S_ANC_ALU_XOR_X, - BPF_S_ANC_VLAN_TAG, - BPF_S_ANC_VLAN_TAG_PRESENT, - BPF_S_ANC_PAY_OFFSET, - BPF_S_ANC_RANDOM, -}; - #endif /* __LINUX_FILTER_H__ */ -- cgit v1.2.3 From f8f6d679aaa78b989d9aee8d2935066fbdca2a30 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 29 May 2014 10:22:51 +0200 Subject: net: filter: improve filter block macros Commit 9739eef13c92 ("net: filter: make BPF conversion more readable") started to introduce helper macros similar to BPF_STMT()/BPF_JUMP() macros from classic BPF. However, quite some statements in the filter conversion functions remained in the old style which gives a mixture of block macros and non block macros in the code. This patch makes the block macros itself more readable by using explicit member initialization, and converts the remaining ones where possible to remain in a more consistent state. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/filter.h | 255 +++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 205 insertions(+), 50 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 49ef7a298c92..f0c2ad43b4af 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -76,56 +76,211 @@ enum { /* BPF program can access up to 512 bytes of stack space. */ #define MAX_BPF_STACK 512 -/* bpf_add|sub|...: a += x, bpf_mov: a = x */ -#define BPF_ALU64_REG(op, a, x) \ - ((struct sock_filter_int) {BPF_ALU64|BPF_OP(op)|BPF_X, a, x, 0, 0}) -#define BPF_ALU32_REG(op, a, x) \ - ((struct sock_filter_int) {BPF_ALU|BPF_OP(op)|BPF_X, a, x, 0, 0}) - -/* bpf_add|sub|...: a += imm, bpf_mov: a = imm */ -#define BPF_ALU64_IMM(op, a, imm) \ - ((struct sock_filter_int) {BPF_ALU64|BPF_OP(op)|BPF_K, a, 0, 0, imm}) -#define BPF_ALU32_IMM(op, a, imm) \ - ((struct sock_filter_int) {BPF_ALU|BPF_OP(op)|BPF_K, a, 0, 0, imm}) - -/* R0 = *(uint *) (skb->data + off) */ -#define BPF_LD_ABS(size, off) \ - ((struct sock_filter_int) {BPF_LD|BPF_SIZE(size)|BPF_ABS, 0, 0, 0, off}) - -/* R0 = *(uint *) (skb->data + x + off) */ -#define BPF_LD_IND(size, x, off) \ - ((struct sock_filter_int) {BPF_LD|BPF_SIZE(size)|BPF_IND, 0, x, 0, off}) - -/* a = *(uint *) (x + off) */ -#define BPF_LDX_MEM(sz, a, x, off) \ - ((struct sock_filter_int) {BPF_LDX|BPF_SIZE(sz)|BPF_MEM, a, x, off, 0}) - -/* if (a 'op' x) goto pc+off */ -#define BPF_JMP_REG(op, a, x, off) \ - ((struct sock_filter_int) {BPF_JMP|BPF_OP(op)|BPF_X, a, x, off, 0}) - -/* if (a 'op' imm) goto pc+off */ -#define BPF_JMP_IMM(op, a, imm, off) \ - ((struct sock_filter_int) {BPF_JMP|BPF_OP(op)|BPF_K, a, 0, off, imm}) - -#define BPF_EXIT_INSN() \ - ((struct sock_filter_int) {BPF_JMP|BPF_EXIT, 0, 0, 0, 0}) - -static inline int size_to_bpf(int size) -{ - switch (size) { - case 1: - return BPF_B; - case 2: - return BPF_H; - case 4: - return BPF_W; - case 8: - return BPF_DW; - default: - return -EINVAL; - } -} +/* Helper macros for filter block array initializers. */ + +/* ALU ops on registers, bpf_add|sub|...: A += X */ + +#define BPF_ALU64_REG(OP, A, X) \ + ((struct sock_filter_int) { \ + .code = BPF_ALU64 | BPF_OP(OP) | BPF_X, \ + .a_reg = A, \ + .x_reg = X, \ + .off = 0, \ + .imm = 0 }) + +#define BPF_ALU32_REG(OP, A, X) \ + ((struct sock_filter_int) { \ + .code = BPF_ALU | BPF_OP(OP) | BPF_X, \ + .a_reg = A, \ + .x_reg = X, \ + .off = 0, \ + .imm = 0 }) + +/* ALU ops on immediates, bpf_add|sub|...: A += IMM */ + +#define BPF_ALU64_IMM(OP, A, IMM) \ + ((struct sock_filter_int) { \ + .code = BPF_ALU64 | BPF_OP(OP) | BPF_K, \ + .a_reg = A, \ + .x_reg = 0, \ + .off = 0, \ + .imm = IMM }) + +#define BPF_ALU32_IMM(OP, A, IMM) \ + ((struct sock_filter_int) { \ + .code = BPF_ALU | BPF_OP(OP) | BPF_K, \ + .a_reg = A, \ + .x_reg = 0, \ + .off = 0, \ + .imm = IMM }) + +/* Endianess conversion, cpu_to_{l,b}e(), {l,b}e_to_cpu() */ + +#define BPF_ENDIAN(TYPE, A, LEN) \ + ((struct sock_filter_int) { \ + .code = BPF_ALU | BPF_END | BPF_SRC(TYPE), \ + .a_reg = A, \ + .x_reg = 0, \ + .off = 0, \ + .imm = LEN }) + +/* Short form of mov, A = X */ + +#define BPF_MOV64_REG(A, X) \ + ((struct sock_filter_int) { \ + .code = BPF_ALU64 | BPF_MOV | BPF_X, \ + .a_reg = A, \ + .x_reg = X, \ + .off = 0, \ + .imm = 0 }) + +#define BPF_MOV32_REG(A, X) \ + ((struct sock_filter_int) { \ + .code = BPF_ALU | BPF_MOV | BPF_X, \ + .a_reg = A, \ + .x_reg = X, \ + .off = 0, \ + .imm = 0 }) + +/* Short form of mov, A = IMM */ + +#define BPF_MOV64_IMM(A, IMM) \ + ((struct sock_filter_int) { \ + .code = BPF_ALU64 | BPF_MOV | BPF_K, \ + .a_reg = A, \ + .x_reg = 0, \ + .off = 0, \ + .imm = IMM }) + +#define BPF_MOV32_IMM(A, IMM) \ + ((struct sock_filter_int) { \ + .code = BPF_ALU | BPF_MOV | BPF_K, \ + .a_reg = A, \ + .x_reg = 0, \ + .off = 0, \ + .imm = IMM }) + +/* Short form of mov based on type, BPF_X: A = X, BPF_K: A = IMM */ + +#define BPF_MOV64_RAW(TYPE, A, X, IMM) \ + ((struct sock_filter_int) { \ + .code = BPF_ALU64 | BPF_MOV | BPF_SRC(TYPE), \ + .a_reg = A, \ + .x_reg = X, \ + .off = 0, \ + .imm = IMM }) + +#define BPF_MOV32_RAW(TYPE, A, X, IMM) \ + ((struct sock_filter_int) { \ + .code = BPF_ALU | BPF_MOV | BPF_SRC(TYPE), \ + .a_reg = A, \ + .x_reg = X, \ + .off = 0, \ + .imm = IMM }) + +/* Direct packet access, R0 = *(uint *) (skb->data + OFF) */ + +#define BPF_LD_ABS(SIZE, OFF) \ + ((struct sock_filter_int) { \ + .code = BPF_LD | BPF_SIZE(SIZE) | BPF_ABS, \ + .a_reg = 0, \ + .x_reg = 0, \ + .off = 0, \ + .imm = OFF }) + +/* Indirect packet access, R0 = *(uint *) (skb->data + X + OFF) */ + +#define BPF_LD_IND(SIZE, X, OFF) \ + ((struct sock_filter_int) { \ + .code = BPF_LD | BPF_SIZE(SIZE) | BPF_IND, \ + .a_reg = 0, \ + .x_reg = X, \ + .off = 0, \ + .imm = OFF }) + +/* Memory store, A = *(uint *) (X + OFF), and vice versa */ + +#define BPF_LDX_MEM(SIZE, A, X, OFF) \ + ((struct sock_filter_int) { \ + .code = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEM, \ + .a_reg = A, \ + .x_reg = X, \ + .off = OFF, \ + .imm = 0 }) + +#define BPF_STX_MEM(SIZE, A, X, OFF) \ + ((struct sock_filter_int) { \ + .code = BPF_STX | BPF_SIZE(SIZE) | BPF_MEM, \ + .a_reg = A, \ + .x_reg = X, \ + .off = OFF, \ + .imm = 0 }) + +/* Conditional jumps against registers, if (A 'op' X) goto pc + OFF */ + +#define BPF_JMP_REG(OP, A, X, OFF) \ + ((struct sock_filter_int) { \ + .code = BPF_JMP | BPF_OP(OP) | BPF_X, \ + .a_reg = A, \ + .x_reg = X, \ + .off = OFF, \ + .imm = 0 }) + +/* Conditional jumps against immediates, if (A 'op' IMM) goto pc + OFF */ + +#define BPF_JMP_IMM(OP, A, IMM, OFF) \ + ((struct sock_filter_int) { \ + .code = BPF_JMP | BPF_OP(OP) | BPF_K, \ + .a_reg = A, \ + .x_reg = 0, \ + .off = OFF, \ + .imm = IMM }) + +/* Function call */ + +#define BPF_EMIT_CALL(FUNC) \ + ((struct sock_filter_int) { \ + .code = BPF_JMP | BPF_CALL, \ + .a_reg = 0, \ + .x_reg = 0, \ + .off = 0, \ + .imm = ((FUNC) - __bpf_call_base) }) + +/* Raw code statement block */ + +#define BPF_RAW_INSN(CODE, A, X, OFF, IMM) \ + ((struct sock_filter_int) { \ + .code = CODE, \ + .a_reg = A, \ + .x_reg = X, \ + .off = OFF, \ + .imm = IMM }) + +/* Program exit */ + +#define BPF_EXIT_INSN() \ + ((struct sock_filter_int) { \ + .code = BPF_JMP | BPF_EXIT, \ + .a_reg = 0, \ + .x_reg = 0, \ + .off = 0, \ + .imm = 0 }) + +#define bytes_to_bpf_size(bytes) \ +({ \ + int bpf_size = -EINVAL; \ + \ + if (bytes == sizeof(u8)) \ + bpf_size = BPF_B; \ + else if (bytes == sizeof(u16)) \ + bpf_size = BPF_H; \ + else if (bytes == sizeof(u32)) \ + bpf_size = BPF_W; \ + else if (bytes == sizeof(u64)) \ + bpf_size = BPF_DW; \ + \ + bpf_size; \ +}) /* Macro to invoke filter function. */ #define SK_RUN_FILTER(filter, ctx) (*filter->bpf_func)(ctx, filter->insnsi) -- cgit v1.2.3 From 96b2e73c5471542cb9c622c4360716684f8797ed Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 2 Jun 2014 00:18:48 -0700 Subject: Revert "net/mlx4_en: Use affinity hint" This reverts commit 70a640d0dae3a9b1b222ce673eb5d92c263ddd61. Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index b9b70e00e3c1..ca38871a585c 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -1161,7 +1161,7 @@ int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr); int mlx4_SYNC_TPT(struct mlx4_dev *dev); int mlx4_test_interrupts(struct mlx4_dev *dev); int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap, - int *vector, cpumask_t *cpu_hint_mask); + int *vector); void mlx4_release_eq(struct mlx4_dev *dev, int vec); int mlx4_get_phys_port_id(struct mlx4_dev *dev); -- cgit v1.2.3 From 670e5b8eaf85704742bc3cb1df51fdd3ce08fc15 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 28 May 2014 18:44:46 -0700 Subject: net: Add support for device specific address syncing This change provides a function to be used in order to break the ndo_set_rx_mode call into a set of address add and remove calls. The code is based on the implementation of dev_uc_sync/dev_mc_sync. Since they essentially do the same thing but with only one dev I simply named my functions __dev_uc_sync/__dev_mc_sync. I also implemented an unsync version of the functions as well to allow for cleanup on close. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/netdevice.h | 73 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 73 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2db1610bf109..774e5391eb8e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3003,6 +3003,15 @@ int __hw_addr_sync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len); void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len); +int __hw_addr_sync_dev(struct netdev_hw_addr_list *list, + struct net_device *dev, + int (*sync)(struct net_device *, const unsigned char *), + int (*unsync)(struct net_device *, + const unsigned char *)); +void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list, + struct net_device *dev, + int (*unsync)(struct net_device *, + const unsigned char *)); void __hw_addr_init(struct netdev_hw_addr_list *list); /* Functions used for device addresses handling */ @@ -3023,6 +3032,38 @@ void dev_uc_unsync(struct net_device *to, struct net_device *from); void dev_uc_flush(struct net_device *dev); void dev_uc_init(struct net_device *dev); +/** + * __dev_uc_sync - Synchonize device's unicast list + * @dev: device to sync + * @sync: function to call if address should be added + * @unsync: function to call if address should be removed + * + * Add newly added addresses to the interface, and release + * addresses that have been deleted. + **/ +static inline int __dev_uc_sync(struct net_device *dev, + int (*sync)(struct net_device *, + const unsigned char *), + int (*unsync)(struct net_device *, + const unsigned char *)) +{ + return __hw_addr_sync_dev(&dev->uc, dev, sync, unsync); +} + +/** + * __dev_uc_unsync - Remove synchonized addresses from device + * @dev: device to sync + * @unsync: function to call if address should be removed + * + * Remove all addresses that were added to the device by dev_uc_sync(). + **/ +static inline void __dev_uc_unsync(struct net_device *dev, + int (*unsync)(struct net_device *, + const unsigned char *)) +{ + __hw_addr_unsync_dev(&dev->uc, dev, unsync); +} + /* Functions used for multicast addresses handling */ int dev_mc_add(struct net_device *dev, const unsigned char *addr); int dev_mc_add_global(struct net_device *dev, const unsigned char *addr); @@ -3035,6 +3076,38 @@ void dev_mc_unsync(struct net_device *to, struct net_device *from); void dev_mc_flush(struct net_device *dev); void dev_mc_init(struct net_device *dev); +/** + * __dev_mc_sync - Synchonize device's multicast list + * @dev: device to sync + * @sync: function to call if address should be added + * @unsync: function to call if address should be removed + * + * Add newly added addresses to the interface, and release + * addresses that have been deleted. + **/ +static inline int __dev_mc_sync(struct net_device *dev, + int (*sync)(struct net_device *, + const unsigned char *), + int (*unsync)(struct net_device *, + const unsigned char *)) +{ + return __hw_addr_sync_dev(&dev->mc, dev, sync, unsync); +} + +/** + * __dev_mc_unsync - Remove synchonized addresses from device + * @dev: device to sync + * @unsync: function to call if address should be removed + * + * Remove all addresses that were added to the device by dev_mc_sync(). + **/ +static inline void __dev_mc_unsync(struct net_device *dev, + int (*unsync)(struct net_device *, + const unsigned char *)) +{ + __hw_addr_unsync_dev(&dev->mc, dev, unsync); +} + /* Functions used for secondary unicast and multicast support */ void dev_set_rx_mode(struct net_device *dev); void __dev_set_rx_mode(struct net_device *dev); -- cgit v1.2.3 From 688cea83f4396fa98b77a126ed278b89daccccdc Mon Sep 17 00:00:00 2001 From: dingtianhong Date: Fri, 30 May 2014 16:00:56 +0800 Subject: macvlan: add netpoll support Add netpoll support to macvlan devices. Based on the netpoll support in the 802.1q vlan code. Tested and macvlan could work well with netconsole. Signed-off-by: Ding Tianhong Signed-off-by: David S. Miller --- include/linux/if_macvlan.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index a9a53b12397b..6b2c7cf352a5 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -57,6 +57,9 @@ struct macvlan_dev { netdev_features_t tap_features; int minor; int nest_level; +#ifdef CONFIG_NET_POLL_CONTROLLER + struct netpoll *netpoll; +#endif }; static inline void macvlan_count_rx(const struct macvlan_dev *vlan, -- cgit v1.2.3 From fe62d001372388abb15a324148c913f9b43722a8 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Thu, 15 May 2014 01:25:27 +0100 Subject: ethtool: Replace ethtool_ops::{get,set}_rxfh_indir() with {get,set}_rxfh() ETHTOOL_{G,S}RXFHINDIR and ETHTOOL_{G,S}RSSH should work for drivers regardless of whether they expose the hash key, unless you try to set a hash key for a driver that doesn't expose it. Signed-off-by: Ben Hutchings Acked-by: Jeff Kirsher --- include/linux/ethtool.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 874fde01d398..e658229fee39 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -158,15 +158,11 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings) * Returns zero if not supported for this specific device. * @get_rxfh_indir_size: Get the size of the RX flow hash indirection table. * Returns zero if not supported for this specific device. - * @get_rxfh_indir: Get the contents of the RX flow hash indirection table. - * Will not be called if @get_rxfh_indir_size returns zero. * @get_rxfh: Get the contents of the RX flow hash indirection table and hash * key. * Will only be called if one or both of @get_rxfh_indir_size and * @get_rxfh_key_size are implemented and return non-zero. * Returns a negative error code or zero. - * @set_rxfh_indir: Set the contents of the RX flow hash indirection table. - * Will not be called if @get_rxfh_indir_size returns zero. * @set_rxfh: Set the contents of the RX flow hash indirection table and/or * hash key. In case only the indirection table or hash key is to be * changed, the other argument will be %NULL. @@ -248,8 +244,6 @@ struct ethtool_ops { int (*get_rxfh)(struct net_device *, u32 *indir, u8 *key); int (*set_rxfh)(struct net_device *, const u32 *indir, const u8 *key); - int (*get_rxfh_indir)(struct net_device *, u32 *); - int (*set_rxfh_indir)(struct net_device *, const u32 *); void (*get_channels)(struct net_device *, struct ethtool_channels *); int (*set_channels)(struct net_device *, struct ethtool_channels *); int (*get_dump_flag)(struct net_device *, struct ethtool_dump *); -- cgit v1.2.3 From 7e2b10c1e52ca37fb522be49f4be367f9311d0cd Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Wed, 4 Jun 2014 17:20:02 -0700 Subject: net: Support for multiple checksums with gso When creating a GSO packet segment we may need to set more than one checksum in the packet (for instance a TCP checksum and UDP checksum for VXLAN encapsulation). To be efficient, we want to do checksum calculation for any part of the packet at most once. This patch adds csum_start offset to skb_gso_cb. This tracks the starting offset for skb->csum which is initially set in skb_segment. When a protocol needs to compute a transport checksum it calls gso_make_checksum which computes the checksum value from the start of transport header to csum_start and then adds in skb->csum to get the full checksum. skb->csum and csum_start are then updated to reflect the checksum of the resultant packet starting from the transport header. This patch also adds a flag to skbuff, encap_hdr_csum, which is set in *gso_segment fucntions to indicate that a tunnel protocol needs checksum calculation Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/skbuff.h | 26 +++++++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7a9beeb1c458..d8d397acb52c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -567,7 +567,8 @@ struct sk_buff { * headers if needed */ __u8 encapsulation:1; - /* 6/8 bit hole (depending on ndisc_nodetype presence) */ + __u8 encap_hdr_csum:1; + /* 5/7 bit hole (depending on ndisc_nodetype presence) */ kmemcheck_bitfield_end(flags2); #if defined CONFIG_NET_DMA || defined CONFIG_NET_RX_BUSY_POLL @@ -2988,6 +2989,7 @@ static inline struct sec_path *skb_sec_path(struct sk_buff *skb) struct skb_gso_cb { int mac_offset; int encap_level; + __u16 csum_start; }; #define SKB_GSO_CB(skb) ((struct skb_gso_cb *)(skb)->cb) @@ -3012,6 +3014,28 @@ static inline int gso_pskb_expand_head(struct sk_buff *skb, int extra) return 0; } +/* Compute the checksum for a gso segment. First compute the checksum value + * from the start of transport header to SKB_GSO_CB(skb)->csum_start, and + * then add in skb->csum (checksum from csum_start to end of packet). + * skb->csum and csum_start are then updated to reflect the checksum of the + * resultant packet starting from the transport header-- the resultant checksum + * is in the res argument (i.e. normally zero or ~ of checksum of a pseudo + * header. + */ +static inline __sum16 gso_make_checksum(struct sk_buff *skb, __wsum res) +{ + int plen = SKB_GSO_CB(skb)->csum_start - skb_headroom(skb) - + skb_transport_offset(skb); + __u16 csum; + + csum = csum_fold(csum_partial(skb_transport_header(skb), + plen, skb->csum)); + skb->csum = res; + SKB_GSO_CB(skb)->csum_start -= plen; + + return csum; +} + static inline bool skb_is_gso(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_size; -- cgit v1.2.3 From 0f4f4ffa7b7c3d29d0537a126145c9f8d8ed5dbc Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Wed, 4 Jun 2014 17:20:16 -0700 Subject: net: Add GSO support for UDP tunnels with checksum Added a new netif feature for GSO_UDP_TUNNEL_CSUM. This indicates that a device is capable of computing the UDP checksum in the encapsulating header of a UDP tunnel. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 1 + include/linux/skbuff.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index c26d0ec2ef3a..f1338e0f9866 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -45,6 +45,7 @@ enum { NETIF_F_GSO_IPIP_BIT, /* ... IPIP tunnel with TSO */ NETIF_F_GSO_SIT_BIT, /* ... SIT tunnel with TSO */ NETIF_F_GSO_UDP_TUNNEL_BIT, /* ... UDP TUNNEL with TSO */ + NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT,/* ... UDP TUNNEL with TSO & CSUM */ NETIF_F_GSO_MPLS_BIT, /* ... MPLS segmentation */ /**/NETIF_F_GSO_LAST = /* last bit, see GSO_MASK */ NETIF_F_GSO_MPLS_BIT, diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d8d397acb52c..5a6d10a538f5 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -345,6 +345,8 @@ enum { SKB_GSO_UDP_TUNNEL = 1 << 9, SKB_GSO_MPLS = 1 << 10, + + SKB_GSO_UDP_TUNNEL_CSUM = 1 << 11, }; #if BITS_PER_LONG > 32 -- cgit v1.2.3 From 4749c09c37030ccdc44aecebe0f71b02a377fc14 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Wed, 4 Jun 2014 17:20:23 -0700 Subject: gre: Call gso_make_checksum Call gso_make_checksum. This should have the benefit of using a checksum that may have been previously computed for the packet. This also adds NETIF_F_GSO_GRE_CSUM to differentiate devices that offload GRE GSO with and without the GRE checksum offloaed. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 2 ++ include/linux/skbuff.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index f1338e0f9866..e5a589435e2b 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -42,6 +42,7 @@ enum { NETIF_F_TSO6_BIT, /* ... TCPv6 segmentation */ NETIF_F_FSO_BIT, /* ... FCoE segmentation */ NETIF_F_GSO_GRE_BIT, /* ... GRE with TSO */ + NETIF_F_GSO_GRE_CSUM_BIT, /* ... GRE with csum with TSO */ NETIF_F_GSO_IPIP_BIT, /* ... IPIP tunnel with TSO */ NETIF_F_GSO_SIT_BIT, /* ... SIT tunnel with TSO */ NETIF_F_GSO_UDP_TUNNEL_BIT, /* ... UDP TUNNEL with TSO */ @@ -112,6 +113,7 @@ enum { #define NETIF_F_RXFCS __NETIF_F(RXFCS) #define NETIF_F_RXALL __NETIF_F(RXALL) #define NETIF_F_GSO_GRE __NETIF_F(GSO_GRE) +#define NETIF_F_GSO_GRE_CSUM __NETIF_F(GSO_GRE_CSUM) #define NETIF_F_GSO_IPIP __NETIF_F(GSO_IPIP) #define NETIF_F_GSO_SIT __NETIF_F(GSO_SIT) #define NETIF_F_GSO_UDP_TUNNEL __NETIF_F(GSO_UDP_TUNNEL) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5a6d10a538f5..c705808bef9c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -347,6 +347,8 @@ enum { SKB_GSO_MPLS = 1 << 10, SKB_GSO_UDP_TUNNEL_CSUM = 1 << 11, + + SKB_GSO_GRE_CSUM = 1 << 12, }; #if BITS_PER_LONG > 32 -- cgit v1.2.3 From ca05e3a7551b71891d42d637d3a1e443c6bbd781 Mon Sep 17 00:00:00 2001 From: Paul Bolle Date: Sun, 1 Jun 2014 23:47:24 +0200 Subject: isdn/capi: move capi_info2str to capidrv.c capi_info2str() is apparently meant to be of general utility. It is actually only used in capidrv.c. So move it from capiutil.c to capidrv.c and (obviously) stop exporting it. And, since we're touching this, merge the two versions of this function. Signed-off-by: Paul Bolle Signed-off-by: Tilman Schmidt Signed-off-by: David S. Miller --- include/linux/isdn/capiutil.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/isdn/capiutil.h b/include/linux/isdn/capiutil.h index 5a52f2c94f3f..44bd6046e6e2 100644 --- a/include/linux/isdn/capiutil.h +++ b/include/linux/isdn/capiutil.h @@ -164,11 +164,6 @@ unsigned capi_cmsg_header(_cmsg * cmsg, __u16 _ApplId, __u8 _Command, __u8 _Subcommand, __u16 _Messagenumber, __u32 _Controller); -/* - * capi_info2str generated a readable string for Capi2.0 reasons. - */ -char *capi_info2str(__u16 reason); - /*-----------------------------------------------------------------------*/ /* -- cgit v1.2.3 From 46cfd6ea23b0a207c87269d86457727dc4485708 Mon Sep 17 00:00:00 2001 From: Konrad Zapalowicz Date: Thu, 5 Jun 2014 20:27:42 +0200 Subject: net: phy: fix sparse warning in fixed.c This commit fixes the following sparse warning: drivers/net/phy/fixed.c:207 - warning: symbol 'fixed_phy_del' was not declared. Should it be static? by adding symbol definition to the phy_fixed.h API file. It is ok to do because the function in question is an exported symbol. Signed-off-by: Konrad Zapalowicz Signed-off-by: David S. Miller --- include/linux/phy_fixed.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy_fixed.h b/include/linux/phy_fixed.h index 4f2478b47136..ae612acebb53 100644 --- a/include/linux/phy_fixed.h +++ b/include/linux/phy_fixed.h @@ -17,6 +17,7 @@ extern int fixed_phy_add(unsigned int irq, int phy_id, extern int fixed_phy_register(unsigned int irq, struct fixed_phy_status *status, struct device_node *np); +extern void fixed_phy_del(int phy_addr); #else static inline int fixed_phy_add(unsigned int irq, int phy_id, struct fixed_phy_status *status) @@ -29,6 +30,10 @@ static inline int fixed_phy_register(unsigned int irq, { return -ENODEV; } +static inline int fixed_phy_del(int phy_addr) +{ + return -ENODEV; +} #endif /* CONFIG_FIXED_PHY */ /* -- cgit v1.2.3 From 07f8ac4a1e26e8283542cdaf658a6e2a12fd6980 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Linus=20L=C3=BCssing?= Date: Sat, 7 Jun 2014 18:26:28 +0200 Subject: bridge: add export of multicast database adjacent to net_dev MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With this new, exported function br_multicast_list_adjacent(net_dev) a list of IPv4/6 addresses is returned. This list contains all multicast addresses sensed by the bridge multicast snooping feature on all bridge ports of the bridge interface of net_dev, excluding addresses from the specified net_device itself. Adding bridge support to the batman-adv multicast optimization requires batman-adv knowing about the existence of bridged-in multicast listeners to be able to reliably serve them with multicast packets. Signed-off-by: Linus Lüssing Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 1085ffeef956..44d6eb0eb852 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -16,9 +16,27 @@ #include #include +struct br_ip { + union { + __be32 ip4; +#if IS_ENABLED(CONFIG_IPV6) + struct in6_addr ip6; +#endif + } u; + __be16 proto; + __u16 vid; +}; + +struct br_ip_list { + struct list_head list; + struct br_ip addr; +}; + extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *)); typedef int br_should_route_hook_t(struct sk_buff *skb); extern br_should_route_hook_t __rcu *br_should_route_hook; +int br_multicast_list_adjacent(struct net_device *dev, + struct list_head *br_ip_list); #endif -- cgit v1.2.3 From 2cd4143192e8c60f66cb32c3a30c76d0470a372d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Linus=20L=C3=BCssing?= Date: Sat, 7 Jun 2014 18:26:29 +0200 Subject: bridge: memorize and export selected IGMP/MLD querier port MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Adding bridge support to the batman-adv multicast optimization requires batman-adv knowing about the existence of bridged-in IGMP/MLD queriers to be able to reliably serve any multicast listener behind this same bridge. Signed-off-by: Linus Lüssing Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 44d6eb0eb852..fd22789d7b2e 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -38,5 +38,6 @@ typedef int br_should_route_hook_t(struct sk_buff *skb); extern br_should_route_hook_t __rcu *br_should_route_hook; int br_multicast_list_adjacent(struct net_device *dev, struct list_head *br_ip_list); +bool br_multicast_has_querier_adjacent(struct net_device *dev, int proto); #endif -- cgit v1.2.3 From e430f34ee5192c84bcabd3c79ab7e2388b5eec74 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Fri, 6 Jun 2014 14:46:06 -0700 Subject: net: filter: cleanup A/X name usage The macro 'A' used in internal BPF interpreter: #define A regs[insn->a_reg] was easily confused with the name of classic BPF register 'A', since 'A' would mean two different things depending on context. This patch is trying to clean up the naming and clarify its usage in the following way: - A and X are names of two classic BPF registers - BPF_REG_A denotes internal BPF register R0 used to map classic register A in internal BPF programs generated from classic - BPF_REG_X denotes internal BPF register R7 used to map classic register X in internal BPF programs generated from classic - internal BPF instruction format: struct sock_filter_int { __u8 code; /* opcode */ __u8 dst_reg:4; /* dest register */ __u8 src_reg:4; /* source register */ __s16 off; /* signed offset */ __s32 imm; /* signed immediate constant */ }; - BPF_X/BPF_K is 1 bit used to encode source operand of instruction In classic: BPF_X - means use register X as source operand BPF_K - means use 32-bit immediate as source operand In internal: BPF_X - means use 'src_reg' register as source operand BPF_K - means use 32-bit immediate as source operand Suggested-by: Chema Gonzalez Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Acked-by: Chema Gonzalez Signed-off-by: David S. Miller --- include/linux/filter.h | 156 ++++++++++++++++++++++++++----------------------- 1 file changed, 84 insertions(+), 72 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index f0c2ad43b4af..a7e3c48d73a7 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -78,161 +78,173 @@ enum { /* Helper macros for filter block array initializers. */ -/* ALU ops on registers, bpf_add|sub|...: A += X */ +/* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */ -#define BPF_ALU64_REG(OP, A, X) \ +#define BPF_ALU64_REG(OP, DST, SRC) \ ((struct sock_filter_int) { \ .code = BPF_ALU64 | BPF_OP(OP) | BPF_X, \ - .a_reg = A, \ - .x_reg = X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ .off = 0, \ .imm = 0 }) -#define BPF_ALU32_REG(OP, A, X) \ +#define BPF_ALU32_REG(OP, DST, SRC) \ ((struct sock_filter_int) { \ .code = BPF_ALU | BPF_OP(OP) | BPF_X, \ - .a_reg = A, \ - .x_reg = X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ .off = 0, \ .imm = 0 }) -/* ALU ops on immediates, bpf_add|sub|...: A += IMM */ +/* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */ -#define BPF_ALU64_IMM(OP, A, IMM) \ +#define BPF_ALU64_IMM(OP, DST, IMM) \ ((struct sock_filter_int) { \ .code = BPF_ALU64 | BPF_OP(OP) | BPF_K, \ - .a_reg = A, \ - .x_reg = 0, \ + .dst_reg = DST, \ + .src_reg = 0, \ .off = 0, \ .imm = IMM }) -#define BPF_ALU32_IMM(OP, A, IMM) \ +#define BPF_ALU32_IMM(OP, DST, IMM) \ ((struct sock_filter_int) { \ .code = BPF_ALU | BPF_OP(OP) | BPF_K, \ - .a_reg = A, \ - .x_reg = 0, \ + .dst_reg = DST, \ + .src_reg = 0, \ .off = 0, \ .imm = IMM }) /* Endianess conversion, cpu_to_{l,b}e(), {l,b}e_to_cpu() */ -#define BPF_ENDIAN(TYPE, A, LEN) \ +#define BPF_ENDIAN(TYPE, DST, LEN) \ ((struct sock_filter_int) { \ .code = BPF_ALU | BPF_END | BPF_SRC(TYPE), \ - .a_reg = A, \ - .x_reg = 0, \ + .dst_reg = DST, \ + .src_reg = 0, \ .off = 0, \ .imm = LEN }) -/* Short form of mov, A = X */ +/* Short form of mov, dst_reg = src_reg */ -#define BPF_MOV64_REG(A, X) \ +#define BPF_MOV64_REG(DST, SRC) \ ((struct sock_filter_int) { \ .code = BPF_ALU64 | BPF_MOV | BPF_X, \ - .a_reg = A, \ - .x_reg = X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ .off = 0, \ .imm = 0 }) -#define BPF_MOV32_REG(A, X) \ +#define BPF_MOV32_REG(DST, SRC) \ ((struct sock_filter_int) { \ .code = BPF_ALU | BPF_MOV | BPF_X, \ - .a_reg = A, \ - .x_reg = X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ .off = 0, \ .imm = 0 }) -/* Short form of mov, A = IMM */ +/* Short form of mov, dst_reg = imm32 */ -#define BPF_MOV64_IMM(A, IMM) \ +#define BPF_MOV64_IMM(DST, IMM) \ ((struct sock_filter_int) { \ .code = BPF_ALU64 | BPF_MOV | BPF_K, \ - .a_reg = A, \ - .x_reg = 0, \ + .dst_reg = DST, \ + .src_reg = 0, \ .off = 0, \ .imm = IMM }) -#define BPF_MOV32_IMM(A, IMM) \ +#define BPF_MOV32_IMM(DST, IMM) \ ((struct sock_filter_int) { \ .code = BPF_ALU | BPF_MOV | BPF_K, \ - .a_reg = A, \ - .x_reg = 0, \ + .dst_reg = DST, \ + .src_reg = 0, \ .off = 0, \ .imm = IMM }) -/* Short form of mov based on type, BPF_X: A = X, BPF_K: A = IMM */ +/* Short form of mov based on type, BPF_X: dst_reg = src_reg, BPF_K: dst_reg = imm32 */ -#define BPF_MOV64_RAW(TYPE, A, X, IMM) \ +#define BPF_MOV64_RAW(TYPE, DST, SRC, IMM) \ ((struct sock_filter_int) { \ .code = BPF_ALU64 | BPF_MOV | BPF_SRC(TYPE), \ - .a_reg = A, \ - .x_reg = X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ .off = 0, \ .imm = IMM }) -#define BPF_MOV32_RAW(TYPE, A, X, IMM) \ +#define BPF_MOV32_RAW(TYPE, DST, SRC, IMM) \ ((struct sock_filter_int) { \ .code = BPF_ALU | BPF_MOV | BPF_SRC(TYPE), \ - .a_reg = A, \ - .x_reg = X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ .off = 0, \ .imm = IMM }) -/* Direct packet access, R0 = *(uint *) (skb->data + OFF) */ +/* Direct packet access, R0 = *(uint *) (skb->data + imm32) */ -#define BPF_LD_ABS(SIZE, OFF) \ +#define BPF_LD_ABS(SIZE, IMM) \ ((struct sock_filter_int) { \ .code = BPF_LD | BPF_SIZE(SIZE) | BPF_ABS, \ - .a_reg = 0, \ - .x_reg = 0, \ + .dst_reg = 0, \ + .src_reg = 0, \ .off = 0, \ - .imm = OFF }) + .imm = IMM }) -/* Indirect packet access, R0 = *(uint *) (skb->data + X + OFF) */ +/* Indirect packet access, R0 = *(uint *) (skb->data + src_reg + imm32) */ -#define BPF_LD_IND(SIZE, X, OFF) \ +#define BPF_LD_IND(SIZE, SRC, IMM) \ ((struct sock_filter_int) { \ .code = BPF_LD | BPF_SIZE(SIZE) | BPF_IND, \ - .a_reg = 0, \ - .x_reg = X, \ + .dst_reg = 0, \ + .src_reg = SRC, \ .off = 0, \ - .imm = OFF }) + .imm = IMM }) -/* Memory store, A = *(uint *) (X + OFF), and vice versa */ +/* Memory load, dst_reg = *(uint *) (src_reg + off16) */ -#define BPF_LDX_MEM(SIZE, A, X, OFF) \ +#define BPF_LDX_MEM(SIZE, DST, SRC, OFF) \ ((struct sock_filter_int) { \ .code = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEM, \ - .a_reg = A, \ - .x_reg = X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) -#define BPF_STX_MEM(SIZE, A, X, OFF) \ +/* Memory store, *(uint *) (dst_reg + off16) = src_reg */ + +#define BPF_STX_MEM(SIZE, DST, SRC, OFF) \ ((struct sock_filter_int) { \ .code = BPF_STX | BPF_SIZE(SIZE) | BPF_MEM, \ - .a_reg = A, \ - .x_reg = X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) -/* Conditional jumps against registers, if (A 'op' X) goto pc + OFF */ +/* Memory store, *(uint *) (dst_reg + off16) = imm32 */ + +#define BPF_ST_MEM(SIZE, DST, OFF, IMM) \ + ((struct sock_filter_int) { \ + .code = BPF_ST | BPF_SIZE(SIZE) | BPF_MEM, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = OFF, \ + .imm = IMM }) + +/* Conditional jumps against registers, if (dst_reg 'op' src_reg) goto pc + off16 */ -#define BPF_JMP_REG(OP, A, X, OFF) \ +#define BPF_JMP_REG(OP, DST, SRC, OFF) \ ((struct sock_filter_int) { \ .code = BPF_JMP | BPF_OP(OP) | BPF_X, \ - .a_reg = A, \ - .x_reg = X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) -/* Conditional jumps against immediates, if (A 'op' IMM) goto pc + OFF */ +/* Conditional jumps against immediates, if (dst_reg 'op' imm32) goto pc + off16 */ -#define BPF_JMP_IMM(OP, A, IMM, OFF) \ +#define BPF_JMP_IMM(OP, DST, IMM, OFF) \ ((struct sock_filter_int) { \ .code = BPF_JMP | BPF_OP(OP) | BPF_K, \ - .a_reg = A, \ - .x_reg = 0, \ + .dst_reg = DST, \ + .src_reg = 0, \ .off = OFF, \ .imm = IMM }) @@ -241,18 +253,18 @@ enum { #define BPF_EMIT_CALL(FUNC) \ ((struct sock_filter_int) { \ .code = BPF_JMP | BPF_CALL, \ - .a_reg = 0, \ - .x_reg = 0, \ + .dst_reg = 0, \ + .src_reg = 0, \ .off = 0, \ .imm = ((FUNC) - __bpf_call_base) }) /* Raw code statement block */ -#define BPF_RAW_INSN(CODE, A, X, OFF, IMM) \ +#define BPF_RAW_INSN(CODE, DST, SRC, OFF, IMM) \ ((struct sock_filter_int) { \ .code = CODE, \ - .a_reg = A, \ - .x_reg = X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ .off = OFF, \ .imm = IMM }) @@ -261,8 +273,8 @@ enum { #define BPF_EXIT_INSN() \ ((struct sock_filter_int) { \ .code = BPF_JMP | BPF_EXIT, \ - .a_reg = 0, \ - .x_reg = 0, \ + .dst_reg = 0, \ + .src_reg = 0, \ .off = 0, \ .imm = 0 }) @@ -287,8 +299,8 @@ enum { struct sock_filter_int { __u8 code; /* opcode */ - __u8 a_reg:4; /* dest register */ - __u8 x_reg:4; /* source register */ + __u8 dst_reg:4; /* dest register */ + __u8 src_reg:4; /* source register */ __s16 off; /* signed offset */ __s32 imm; /* signed immediate constant */ }; -- cgit v1.2.3 From 67cb9366ff5f99868100198efba5ca88aaa6ad25 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 11 Jun 2014 18:19:28 +0200 Subject: ktime: add ktime_after and ktime_before helper Add two minimal helper functions analogous to time_before() and time_after() that will later on both be needed by SCTP code. Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/ktime.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 31c0cd1c941a..de9e46e6bcc9 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -304,6 +304,30 @@ static inline int ktime_compare(const ktime_t cmp1, const ktime_t cmp2) return 0; } +/** + * ktime_after - Compare if a ktime_t value is bigger than another one. + * @cmp1: comparable1 + * @cmp2: comparable2 + * + * Return: true if cmp1 happened after cmp2. + */ +static inline bool ktime_after(const ktime_t cmp1, const ktime_t cmp2) +{ + return ktime_compare(cmp1, cmp2) > 0; +} + +/** + * ktime_before - Compare if a ktime_t value is smaller than another one. + * @cmp1: comparable1 + * @cmp2: comparable2 + * + * Return: true if cmp1 happened before cmp2. + */ +static inline bool ktime_before(const ktime_t cmp1, const ktime_t cmp2) +{ + return ktime_compare(cmp1, cmp2) < 0; +} + static inline s64 ktime_to_us(const ktime_t kt) { struct timeval tv = ktime_to_timeval(kt); -- cgit v1.2.3 From da91309e0a7e8966d916a74cce42ed170fde06bf Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Mon, 9 Jun 2014 10:24:38 +0300 Subject: cpumask: Utility function to set n'th cpu - local cpu first This function sets the n'th cpu - local cpu's first. For example: in a 16 cores server with even cpu's local, will get the following values: cpumask_set_cpu_local_first(0, numa, cpumask) => cpu 0 is set cpumask_set_cpu_local_first(1, numa, cpumask) => cpu 2 is set ... cpumask_set_cpu_local_first(7, numa, cpumask) => cpu 14 is set cpumask_set_cpu_local_first(8, numa, cpumask) => cpu 1 is set cpumask_set_cpu_local_first(9, numa, cpumask) => cpu 3 is set ... cpumask_set_cpu_local_first(15, numa, cpumask) => cpu 15 is set Curently this function will be used by multi queue networking devices to calculate the irq affinity mask, such that as many local cpu's as possible will be utilized to handle the mq device irq's. Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/cpumask.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index d08e4d2a9b92..d5ef249735d2 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -142,6 +142,13 @@ static inline unsigned int cpumask_any_but(const struct cpumask *mask, return 1; } +static inline int cpumask_set_cpu_local_first(int i, int numa_node, cpumask_t *dstp) +{ + set_bit(0, cpumask_bits(dstp)); + + return 0; +} + #define for_each_cpu(cpu, mask) \ for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask) #define for_each_cpu_not(cpu, mask) \ @@ -192,6 +199,7 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) int cpumask_next_and(int n, const struct cpumask *, const struct cpumask *); int cpumask_any_but(const struct cpumask *mask, unsigned int cpu); +int cpumask_set_cpu_local_first(int i, int numa_node, cpumask_t *dstp); /** * for_each_cpu - iterate over every cpu in a mask -- cgit v1.2.3 From bad93e9d4eeb0d2d6b79204d6cedc7f2e7b256f1 Mon Sep 17 00:00:00 2001 From: Octavian Purdila Date: Thu, 12 Jun 2014 01:36:26 +0300 Subject: net: add __pskb_copy_fclone and pskb_copy_for_clone There are several instances where a pskb_copy or __pskb_copy is immediately followed by an skb_clone. Add a couple of new functions to allow the copy skb to be allocated from the fclone cache and thus speed up subsequent skb_clone calls. Cc: Alexander Smirnov Cc: Dmitry Eremin-Solenikov Cc: Marek Lindner Cc: Simon Wunderlich Cc: Antonio Quartulli Cc: Marcel Holtmann Cc: Gustavo Padovan Cc: Johan Hedberg Cc: Arvid Brodin Cc: Patrick McHardy Cc: Pablo Neira Ayuso Cc: Jozsef Kadlecsik Cc: Lauro Ramos Venancio Cc: Aloisio Almeida Jr Cc: Samuel Ortiz Cc: Jon Maloy Cc: Allan Stephens Cc: Andrew Hendry Cc: Eric Dumazet Reviewed-by: Christoph Paasch Signed-off-by: Octavian Purdila Signed-off-by: David S. Miller --- include/linux/skbuff.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c705808bef9c..1f50bfe2243d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -744,7 +744,13 @@ struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src); int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask); struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority); struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t priority); -struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask); +struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom, + gfp_t gfp_mask, bool fclone); +static inline struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, + gfp_t gfp_mask) +{ + return __pskb_copy_fclone(skb, headroom, gfp_mask, false); +} int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, gfp_t gfp_mask); struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, @@ -2238,6 +2244,14 @@ static inline struct sk_buff *pskb_copy(struct sk_buff *skb, return __pskb_copy(skb, skb_headroom(skb), gfp_mask); } + +static inline struct sk_buff *pskb_copy_for_clone(struct sk_buff *skb, + gfp_t gfp_mask) +{ + return __pskb_copy_fclone(skb, skb_headroom(skb), gfp_mask, true); +} + + /** * skb_clone_writable - is the header of a clone writable * @skb: buffer to check -- cgit v1.2.3 From 5d0c2b95bc57cf8fdc0e7b3e9d7e751eb65ad052 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Tue, 10 Jun 2014 18:54:13 -0700 Subject: net: Preserve CHECKSUM_COMPLETE at validation Currently when the first checksum in a packet is validated using CHECKSUM_COMPLETE, ip_summed is overwritten to be CHECKSUM_UNNECESSARY so that any subsequent checksums in the packet are not correctly validated. This patch adds csum_valid flag in sk_buff and uses that to indicate validated checksum instead of setting CHECKSUM_UNNECESSARY. The bit is set accordingly in the skb_checksum_validate_* functions. The flag is checked in skb_checksum_complete, so that validation is communicated between checksum_init and checksum_complete sequence in TCP and UDP. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/skbuff.h | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 1f50bfe2243d..72a53805858a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -572,7 +572,8 @@ struct sk_buff { */ __u8 encapsulation:1; __u8 encap_hdr_csum:1; - /* 5/7 bit hole (depending on ndisc_nodetype presence) */ + __u8 csum_valid:1; + /* 4/6 bit hole (depending on ndisc_nodetype presence) */ kmemcheck_bitfield_end(flags2); #if defined CONFIG_NET_DMA || defined CONFIG_NET_RX_BUSY_POLL @@ -2735,7 +2736,7 @@ __sum16 __skb_checksum_complete(struct sk_buff *skb); static inline int skb_csum_unnecessary(const struct sk_buff *skb) { - return skb->ip_summed & CHECKSUM_UNNECESSARY; + return ((skb->ip_summed & CHECKSUM_UNNECESSARY) || skb->csum_valid); } /** @@ -2769,10 +2770,8 @@ static inline bool __skb_checksum_validate_needed(struct sk_buff *skb, bool zero_okay, __sum16 check) { - if (skb_csum_unnecessary(skb)) { - return false; - } else if (zero_okay && !check) { - skb->ip_summed = CHECKSUM_UNNECESSARY; + if (skb_csum_unnecessary(skb) || (zero_okay && !check)) { + skb->csum_valid = 1; return false; } @@ -2799,15 +2798,20 @@ static inline __sum16 __skb_checksum_validate_complete(struct sk_buff *skb, { if (skb->ip_summed == CHECKSUM_COMPLETE) { if (!csum_fold(csum_add(psum, skb->csum))) { - skb->ip_summed = CHECKSUM_UNNECESSARY; + skb->csum_valid = 1; return 0; } } skb->csum = psum; - if (complete || skb->len <= CHECKSUM_BREAK) - return __skb_checksum_complete(skb); + if (complete || skb->len <= CHECKSUM_BREAK) { + __sum16 csum; + + csum = __skb_checksum_complete(skb); + skb->csum_valid = !csum; + return csum; + } return 0; } @@ -2831,6 +2835,7 @@ static inline __wsum null_compute_pseudo(struct sk_buff *skb, int proto) zero_okay, check, compute_pseudo) \ ({ \ __sum16 __ret = 0; \ + skb->csum_valid = 0; \ if (__skb_checksum_validate_needed(skb, zero_okay, check)) \ __ret = __skb_checksum_validate_complete(skb, \ complete, compute_pseudo(skb, proto)); \ -- cgit v1.2.3 From 7e3cead5172927732f51fde77fef6f521e22f209 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Tue, 10 Jun 2014 18:54:19 -0700 Subject: net: Save software checksum complete In skb_checksum complete, if we need to compute the checksum for the packet (via skb_checksum) save the result as CHECKSUM_COMPLETE. Subsequent checksum verification can use this. Also, added csum_complete_sw flag to distinguish between software and hardware generated checksum complete, we should always be able to trust the software computation. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 72a53805858a..5b5cd3189c98 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -573,7 +573,8 @@ struct sk_buff { __u8 encapsulation:1; __u8 encap_hdr_csum:1; __u8 csum_valid:1; - /* 4/6 bit hole (depending on ndisc_nodetype presence) */ + __u8 csum_complete_sw:1; + /* 3/5 bit hole (depending on ndisc_nodetype presence) */ kmemcheck_bitfield_end(flags2); #if defined CONFIG_NET_DMA || defined CONFIG_NET_RX_BUSY_POLL -- cgit v1.2.3