From 69821638b27407d8648cb04de01b06b30a291bde Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 27 Jul 2012 06:28:53 +0000 Subject: team: add signed 32-bit team option type Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_team.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 6960fc1841a7..e5571c420800 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -130,6 +130,7 @@ enum team_option_type { TEAM_OPTION_TYPE_STRING, TEAM_OPTION_TYPE_BINARY, TEAM_OPTION_TYPE_BOOL, + TEAM_OPTION_TYPE_S32, }; struct team_option_inst_info { @@ -146,6 +147,7 @@ struct team_gsetter_ctx { u32 len; } bin_val; bool bool_val; + s32 s32_val; } data; struct team_option_inst_info *info; }; -- cgit v1.2.3 From a86fc6b7d603992070c04bd7a8c217d55688b077 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 27 Jul 2012 06:28:54 +0000 Subject: team: add per port priority option Allow userspace to set port priority. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_team.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/if_team.h b/include/linux/if_team.h index e5571c420800..06495b3e7a99 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -67,6 +67,7 @@ struct team_port { struct netpoll *np; #endif + s32 priority; /* lower number ~ higher priority */ long mode_priv[0]; }; -- cgit v1.2.3 From 8ff5105a2b9dd0ba596719b165c1827d101e5f1a Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 27 Jul 2012 06:28:55 +0000 Subject: team: add support for queue override by setting queue_id for port Similar to what bonding has. This allows to set queue_id for port so this port will be used when skb with matching skb->queue_mapping is going to be transmitted. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_team.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 06495b3e7a99..33fcc20b5881 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -68,6 +68,8 @@ struct team_port { #endif s32 priority; /* lower number ~ higher priority */ + u16 queue_id; + struct list_head qom_list; /* node in queue override mapping list */ long mode_priv[0]; }; @@ -200,6 +202,8 @@ struct team { const struct team_mode *mode; struct team_mode_ops ops; + bool queue_override_enabled; + struct list_head *qom_lists; /* array of queue override mapping lists */ long mode_priv[TEAM_MODE_PRIV_LONGS]; }; -- cgit v1.2.3 From 47061bc440b90a16d856fb0dba1cffc36427efa4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 3 Aug 2012 20:54:15 +0000 Subject: net: skb_share_check() should use consume_skb() In order to avoid false drop_monitor indications, we should call consume_skb() if skb_clone() was successful. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7632c87da2c9..b33a3a1f205e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -846,13 +846,16 @@ static inline int skb_shared(const struct sk_buff *skb) * * NULL is returned on a memory allocation failure. */ -static inline struct sk_buff *skb_share_check(struct sk_buff *skb, - gfp_t pri) +static inline struct sk_buff *skb_share_check(struct sk_buff *skb, gfp_t pri) { might_sleep_if(pri & __GFP_WAIT); if (skb_shared(skb)) { struct sk_buff *nskb = skb_clone(skb, pri); - kfree_skb(skb); + + if (likely(nskb)) + consume_skb(skb); + else + kfree_skb(skb); skb = nskb; } return skb; -- cgit v1.2.3 From 9eb43e765368f835d92c93844ebce30da7efeb84 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 3 Aug 2012 21:27:25 +0000 Subject: ipv4: Introduce IN_DEV_NET_ROUTE_LOCALNET performance profiles show a high cost in the IN_DEV_ROUTE_LOCALNET() call done in ip_route_input_slow(), because of multiple dereferences, even if cache lines are clean and available in cpu caches. Since we already have the 'net' pointer, introduce IN_DEV_NET_ROUTE_LOCALNET() macro avoiding two dereferences (dev_net(in_dev->dev)) Also change the tests to use IN_DEV_NET_ROUTE_LOCALNET() only if saddr or/and daddr are loopback addresse. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 67f9ddacb70c..d032780d0ce5 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -104,9 +104,14 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) #define IN_DEV_ANDCONF(in_dev, attr) \ (IPV4_DEVCONF_ALL(dev_net(in_dev->dev), attr) && \ IN_DEV_CONF_GET((in_dev), attr)) -#define IN_DEV_ORCONF(in_dev, attr) \ - (IPV4_DEVCONF_ALL(dev_net(in_dev->dev), attr) || \ + +#define IN_DEV_NET_ORCONF(in_dev, net, attr) \ + (IPV4_DEVCONF_ALL(net, attr) || \ IN_DEV_CONF_GET((in_dev), attr)) + +#define IN_DEV_ORCONF(in_dev, attr) \ + IN_DEV_NET_ORCONF(in_dev, dev_net(in_dev->dev), attr) + #define IN_DEV_MAXCONF(in_dev, attr) \ (max(IPV4_DEVCONF_ALL(dev_net(in_dev->dev), attr), \ IN_DEV_CONF_GET((in_dev), attr))) @@ -133,6 +138,8 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) IN_DEV_ORCONF((in_dev), \ PROMOTE_SECONDARIES) #define IN_DEV_ROUTE_LOCALNET(in_dev) IN_DEV_ORCONF(in_dev, ROUTE_LOCALNET) +#define IN_DEV_NET_ROUTE_LOCALNET(in_dev, net) \ + IN_DEV_NET_ORCONF(in_dev, net, ROUTE_LOCALNET) #define IN_DEV_RX_REDIRECTS(in_dev) \ ((IN_DEV_FORWARD(in_dev) && \ -- cgit v1.2.3 From 14a196807482e6fc74f15fc03176d5c08880588f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 4 Aug 2012 20:33:59 +0000 Subject: net: reorganize IP MIB values Reduce IP latencies by placing hot MIB IP fields in a single cache line. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/snmp.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/snmp.h b/include/linux/snmp.h index 00bc189cb395..ad6e3a6bf9fb 100644 --- a/include/linux/snmp.h +++ b/include/linux/snmp.h @@ -18,7 +18,14 @@ enum { IPSTATS_MIB_NUM = 0, +/* frequently written fields in fast path, kept in same cache line */ IPSTATS_MIB_INPKTS, /* InReceives */ + IPSTATS_MIB_INOCTETS, /* InOctets */ + IPSTATS_MIB_INDELIVERS, /* InDelivers */ + IPSTATS_MIB_OUTFORWDATAGRAMS, /* OutForwDatagrams */ + IPSTATS_MIB_OUTPKTS, /* OutRequests */ + IPSTATS_MIB_OUTOCTETS, /* OutOctets */ +/* other fields */ IPSTATS_MIB_INHDRERRORS, /* InHdrErrors */ IPSTATS_MIB_INTOOBIGERRORS, /* InTooBigErrors */ IPSTATS_MIB_INNOROUTES, /* InNoRoutes */ @@ -26,9 +33,6 @@ enum IPSTATS_MIB_INUNKNOWNPROTOS, /* InUnknownProtos */ IPSTATS_MIB_INTRUNCATEDPKTS, /* InTruncatedPkts */ IPSTATS_MIB_INDISCARDS, /* InDiscards */ - IPSTATS_MIB_INDELIVERS, /* InDelivers */ - IPSTATS_MIB_OUTFORWDATAGRAMS, /* OutForwDatagrams */ - IPSTATS_MIB_OUTPKTS, /* OutRequests */ IPSTATS_MIB_OUTDISCARDS, /* OutDiscards */ IPSTATS_MIB_OUTNOROUTES, /* OutNoRoutes */ IPSTATS_MIB_REASMTIMEOUT, /* ReasmTimeout */ @@ -42,8 +46,6 @@ enum IPSTATS_MIB_OUTMCASTPKTS, /* OutMcastPkts */ IPSTATS_MIB_INBCASTPKTS, /* InBcastPkts */ IPSTATS_MIB_OUTBCASTPKTS, /* OutBcastPkts */ - IPSTATS_MIB_INOCTETS, /* InOctets */ - IPSTATS_MIB_OUTOCTETS, /* OutOctets */ IPSTATS_MIB_INMCASTOCTETS, /* InMcastOctets */ IPSTATS_MIB_OUTMCASTOCTETS, /* OutMcastOctets */ IPSTATS_MIB_INBCASTOCTETS, /* InBcastOctets */ -- cgit v1.2.3 From a399a8053164ec8bcb06fed52be9941a26ecde11 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 8 Aug 2012 21:13:53 +0000 Subject: time: jiffies_delta_to_clock_t() helper to the rescue MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Various /proc/net files sometimes report crazy timer values, expressed in clock_t units. This happens when an expired timer delta (expires - jiffies) is passed to jiffies_to_clock_t(). This function has an overflow in : return div_u64((u64)x * TICK_NSEC, NSEC_PER_SEC / USER_HZ); commit cbbc719fccdb8cb (time: Change jiffies_to_clock_t() argument type to unsigned long) only got around the problem. As we cant output negative values in /proc/net/tcp without breaking various tools, I suggest adding a jiffies_delta_to_clock_t() wrapper that caps the negative delta to a 0 value. Signed-off-by: Eric Dumazet Reported-by: Maciej Żenczykowski Cc: Thomas Gleixner Cc: Paul Gortmaker Cc: Andrew Morton Cc: hank Signed-off-by: David S. Miller --- include/linux/jiffies.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 265e2c3cbd1c..aded9b1ac5ca 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -303,7 +303,13 @@ extern void jiffies_to_timespec(const unsigned long jiffies, extern unsigned long timeval_to_jiffies(const struct timeval *value); extern void jiffies_to_timeval(const unsigned long jiffies, struct timeval *value); + extern clock_t jiffies_to_clock_t(unsigned long x); +static inline clock_t jiffies_delta_to_clock_t(long delta) +{ + return jiffies_to_clock_t(max(0L, delta)); +} + extern unsigned long clock_t_to_jiffies(unsigned long x); extern u64 jiffies_64_to_clock_t(u64 x); extern u64 nsec_to_clock_t(u64 x); -- cgit v1.2.3 From b14f243a42c7aa43de71f878641acd003f223022 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Wed, 8 Aug 2012 21:52:28 +0000 Subject: net: Dont use ifindices in hash fns Eric noticed, that when there will be devices with equal indices, some hash functions that use them will become less effective as they could. Fix this in advance by mixing the net_device address into the hash value instead of the device index. This is true for arp and ndisc hash fns. The netlabel, can and llc ones are also ifindex-based, but that three are init_net-only, thus will not be affected. Many thanks to David and Eric for the hash32_ptr implementation! Signed-off-by: Pavel Emelyanov Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/hash.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hash.h b/include/linux/hash.h index b80506bdd733..24df9e70406f 100644 --- a/include/linux/hash.h +++ b/include/linux/hash.h @@ -67,4 +67,14 @@ static inline unsigned long hash_ptr(const void *ptr, unsigned int bits) { return hash_long((unsigned long)ptr, bits); } + +static inline u32 hash32_ptr(const void *ptr) +{ + unsigned long val = (unsigned long)ptr; + +#if BITS_PER_LONG == 64 + val ^= (val >> 32); +#endif + return (u32)val; +} #endif /* _LINUX_HASH_H */ -- cgit v1.2.3 From 3213e1a570783ca3a41d025cede4a27b18bc24c9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Wed, 8 Aug 2012 19:10:14 +0200 Subject: bcma: add (mostly) NAND defines MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Rafał Miłecki Signed-off-by: John W. Linville --- include/linux/bcma/bcma_driver_chipcommon.h | 85 +++++++++++++++++++++++++++++ include/linux/bcma/bcma_regs.h | 2 + 2 files changed, 87 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index 3c80885fa829..fcb06fb284eb 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -94,6 +94,7 @@ #define BCMA_CC_CHIPST_4706_SFLASH_TYPE BIT(2) /* 0: 8b-p/ST-s flash, 1: 16b-p/Atmal-s flash */ #define BCMA_CC_CHIPST_4706_MIPS_BENDIAN BIT(3) /* 0: little, 1: big endian */ #define BCMA_CC_CHIPST_4706_PCIE1_DISABLE BIT(5) /* PCIE1 enable strap pin */ +#define BCMA_CC_CHIPST_5357_NAND_BOOT BIT(4) /* NAND boot, valid for CC rev 38 and/or BCM5357 */ #define BCMA_CC_JCMD 0x0030 /* Rev >= 10 only */ #define BCMA_CC_JCMD_START 0x80000000 #define BCMA_CC_JCMD_BUSY 0x80000000 @@ -260,6 +261,29 @@ #define BCMA_CC_SROM_CONTROL_SIZE_16K 0x00000004 #define BCMA_CC_SROM_CONTROL_SIZE_SHIFT 1 #define BCMA_CC_SROM_CONTROL_PRESENT 0x00000001 +/* Block 0x140 - 0x190 registers are chipset specific */ +#define BCMA_CC_4706_FLASHSCFG 0x18C /* Flash struct configuration */ +#define BCMA_CC_4706_FLASHSCFG_MASK 0x000000ff +#define BCMA_CC_4706_FLASHSCFG_SF1 0x00000001 /* 2nd serial flash present */ +#define BCMA_CC_4706_FLASHSCFG_PF1 0x00000002 /* 2nd parallel flash present */ +#define BCMA_CC_4706_FLASHSCFG_SF1_TYPE 0x00000004 /* 2nd serial flash type : 0 : ST, 1 : Atmel */ +#define BCMA_CC_4706_FLASHSCFG_NF1 0x00000008 /* 2nd NAND flash present */ +#define BCMA_CC_4706_FLASHSCFG_1ST_MADDR_SEG_MASK 0x000000f0 +#define BCMA_CC_4706_FLASHSCFG_1ST_MADDR_SEG_4MB 0x00000010 /* 4MB */ +#define BCMA_CC_4706_FLASHSCFG_1ST_MADDR_SEG_8MB 0x00000020 /* 8MB */ +#define BCMA_CC_4706_FLASHSCFG_1ST_MADDR_SEG_16MB 0x00000030 /* 16MB */ +#define BCMA_CC_4706_FLASHSCFG_1ST_MADDR_SEG_32MB 0x00000040 /* 32MB */ +#define BCMA_CC_4706_FLASHSCFG_1ST_MADDR_SEG_64MB 0x00000050 /* 64MB */ +#define BCMA_CC_4706_FLASHSCFG_1ST_MADDR_SEG_128MB 0x00000060 /* 128MB */ +#define BCMA_CC_4706_FLASHSCFG_1ST_MADDR_SEG_256MB 0x00000070 /* 256MB */ +/* NAND flash registers for BCM4706 (corerev = 31) */ +#define BCMA_CC_NFLASH_CTL 0x01A0 +#define BCMA_CC_NFLASH_CTL_ERR 0x08000000 +#define BCMA_CC_NFLASH_CONF 0x01A4 +#define BCMA_CC_NFLASH_COL_ADDR 0x01A8 +#define BCMA_CC_NFLASH_ROW_ADDR 0x01AC +#define BCMA_CC_NFLASH_DATA 0x01B0 +#define BCMA_CC_NFLASH_WAITCNT0 0x01B4 /* 0x1E0 is defined as shared BCMA_CLKCTLST */ #define BCMA_CC_HW_WORKAROUND 0x01E4 /* Hardware workaround (rev >= 20) */ #define BCMA_CC_UART0_DATA 0x0300 @@ -319,6 +343,60 @@ #define BCMA_CC_PLLCTL_ADDR 0x0660 #define BCMA_CC_PLLCTL_DATA 0x0664 #define BCMA_CC_SPROM 0x0800 /* SPROM beginning */ +/* NAND flash MLC controller registers (corerev >= 38) */ +#define BCMA_CC_NAND_REVISION 0x0C00 +#define BCMA_CC_NAND_CMD_START 0x0C04 +#define BCMA_CC_NAND_CMD_ADDR_X 0x0C08 +#define BCMA_CC_NAND_CMD_ADDR 0x0C0C +#define BCMA_CC_NAND_CMD_END_ADDR 0x0C10 +#define BCMA_CC_NAND_CS_NAND_SELECT 0x0C14 +#define BCMA_CC_NAND_CS_NAND_XOR 0x0C18 +#define BCMA_CC_NAND_SPARE_RD0 0x0C20 +#define BCMA_CC_NAND_SPARE_RD4 0x0C24 +#define BCMA_CC_NAND_SPARE_RD8 0x0C28 +#define BCMA_CC_NAND_SPARE_RD12 0x0C2C +#define BCMA_CC_NAND_SPARE_WR0 0x0C30 +#define BCMA_CC_NAND_SPARE_WR4 0x0C34 +#define BCMA_CC_NAND_SPARE_WR8 0x0C38 +#define BCMA_CC_NAND_SPARE_WR12 0x0C3C +#define BCMA_CC_NAND_ACC_CONTROL 0x0C40 +#define BCMA_CC_NAND_CONFIG 0x0C48 +#define BCMA_CC_NAND_TIMING_1 0x0C50 +#define BCMA_CC_NAND_TIMING_2 0x0C54 +#define BCMA_CC_NAND_SEMAPHORE 0x0C58 +#define BCMA_CC_NAND_DEVID 0x0C60 +#define BCMA_CC_NAND_DEVID_X 0x0C64 +#define BCMA_CC_NAND_BLOCK_LOCK_STATUS 0x0C68 +#define BCMA_CC_NAND_INTFC_STATUS 0x0C6C +#define BCMA_CC_NAND_ECC_CORR_ADDR_X 0x0C70 +#define BCMA_CC_NAND_ECC_CORR_ADDR 0x0C74 +#define BCMA_CC_NAND_ECC_UNC_ADDR_X 0x0C78 +#define BCMA_CC_NAND_ECC_UNC_ADDR 0x0C7C +#define BCMA_CC_NAND_READ_ERROR_COUNT 0x0C80 +#define BCMA_CC_NAND_CORR_STAT_THRESHOLD 0x0C84 +#define BCMA_CC_NAND_READ_ADDR_X 0x0C90 +#define BCMA_CC_NAND_READ_ADDR 0x0C94 +#define BCMA_CC_NAND_PAGE_PROGRAM_ADDR_X 0x0C98 +#define BCMA_CC_NAND_PAGE_PROGRAM_ADDR 0x0C9C +#define BCMA_CC_NAND_COPY_BACK_ADDR_X 0x0CA0 +#define BCMA_CC_NAND_COPY_BACK_ADDR 0x0CA4 +#define BCMA_CC_NAND_BLOCK_ERASE_ADDR_X 0x0CA8 +#define BCMA_CC_NAND_BLOCK_ERASE_ADDR 0x0CAC +#define BCMA_CC_NAND_INV_READ_ADDR_X 0x0CB0 +#define BCMA_CC_NAND_INV_READ_ADDR 0x0CB4 +#define BCMA_CC_NAND_BLK_WR_PROTECT 0x0CC0 +#define BCMA_CC_NAND_ACC_CONTROL_CS1 0x0CD0 +#define BCMA_CC_NAND_CONFIG_CS1 0x0CD4 +#define BCMA_CC_NAND_TIMING_1_CS1 0x0CD8 +#define BCMA_CC_NAND_TIMING_2_CS1 0x0CDC +#define BCMA_CC_NAND_SPARE_RD16 0x0D30 +#define BCMA_CC_NAND_SPARE_RD20 0x0D34 +#define BCMA_CC_NAND_SPARE_RD24 0x0D38 +#define BCMA_CC_NAND_SPARE_RD28 0x0D3C +#define BCMA_CC_NAND_CACHE_ADDR 0x0D40 +#define BCMA_CC_NAND_CACHE_DATA 0x0D44 +#define BCMA_CC_NAND_CTRL_CONFIG 0x0D48 +#define BCMA_CC_NAND_CTRL_STATUS 0x0D4C /* Divider allocation in 4716/47162/5356 */ #define BCMA_CC_PMU5_MAINPLL_CPU 1 @@ -409,6 +487,13 @@ /* 4313 Chip specific ChipControl register bits */ #define BCMA_CCTRL_4313_12MA_LED_DRIVE 0x00000007 /* 12 mA drive strengh for later 4313 */ +/* BCM5357 ChipControl register bits */ +#define BCMA_CHIPCTL_5357_EXTPA BIT(14) +#define BCMA_CHIPCTL_5357_ANT_MUX_2O3 BIT(15) +#define BCMA_CHIPCTL_5357_NFLASH BIT(16) +#define BCMA_CHIPCTL_5357_I2S_PINS_ENABLE BIT(18) +#define BCMA_CHIPCTL_5357_I2CSPI_PINS_ENABLE BIT(19) + /* Data for the PMU, if available. * Check availability with ((struct bcma_chipcommon)->capabilities & BCMA_CC_CAP_PMU) */ diff --git a/include/linux/bcma/bcma_regs.h b/include/linux/bcma/bcma_regs.h index 5a71d5719640..a393e82bf7bf 100644 --- a/include/linux/bcma/bcma_regs.h +++ b/include/linux/bcma/bcma_regs.h @@ -11,11 +11,13 @@ #define BCMA_CLKCTLST_HAVEHTREQ 0x00000010 /* HT available request */ #define BCMA_CLKCTLST_HWCROFF 0x00000020 /* Force HW clock request off */ #define BCMA_CLKCTLST_EXTRESREQ 0x00000700 /* Mask of external resource requests */ +#define BCMA_CLKCTLST_EXTRESREQ_SHIFT 8 #define BCMA_CLKCTLST_HAVEALP 0x00010000 /* ALP available */ #define BCMA_CLKCTLST_HAVEHT 0x00020000 /* HT available */ #define BCMA_CLKCTLST_BP_ON_ALP 0x00040000 /* RO: running on ALP clock */ #define BCMA_CLKCTLST_BP_ON_HT 0x00080000 /* RO: running on HT clock */ #define BCMA_CLKCTLST_EXTRESST 0x07000000 /* Mask of external resource status */ +#define BCMA_CLKCTLST_EXTRESST_SHIFT 24 /* Is there any BCM4328 on BCMA bus? */ #define BCMA_CLKCTLST_4328A0_HAVEHT 0x00010000 /* 4328a0 has reversed bits */ #define BCMA_CLKCTLST_4328A0_HAVEALP 0x00020000 /* 4328a0 has reversed bits */ -- cgit v1.2.3 From 902d9e0f48ddc18fb37c1b1edf5e3b27aaba1505 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Wed, 8 Aug 2012 19:37:04 +0200 Subject: ssb: check for flash presentence MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We can not assume parallel flash is always present, there are boards with *serial* flash and probably some without flash at all. Define some bits by the way. Signed-off-by: Rafał Miłecki Reviewed-by: Hauke Mehrtens Signed-off-by: John W. Linville --- include/linux/ssb/ssb_driver_chipcommon.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb_driver_chipcommon.h b/include/linux/ssb/ssb_driver_chipcommon.h index 1a6b0045b06b..c2b02a5c86ae 100644 --- a/include/linux/ssb/ssb_driver_chipcommon.h +++ b/include/linux/ssb/ssb_driver_chipcommon.h @@ -504,7 +504,9 @@ #define SSB_CHIPCO_FLASHCTL_ST_SE 0x02D8 /* Sector Erase */ #define SSB_CHIPCO_FLASHCTL_ST_BE 0x00C7 /* Bulk Erase */ #define SSB_CHIPCO_FLASHCTL_ST_DP 0x00B9 /* Deep Power-down */ -#define SSB_CHIPCO_FLASHCTL_ST_RSIG 0x03AB /* Read Electronic Signature */ +#define SSB_CHIPCO_FLASHCTL_ST_RES 0x03AB /* Read Electronic Signature */ +#define SSB_CHIPCO_FLASHCTL_ST_CSA 0x1000 /* Keep chip select asserted */ +#define SSB_CHIPCO_FLASHCTL_ST_SSE 0x0220 /* Sub-sector Erase */ /* Status register bits for ST flashes */ #define SSB_CHIPCO_FLASHSTA_ST_WIP 0x01 /* Write In Progress */ -- cgit v1.2.3 From ee89bab14e857678f83a71ee99e575b0fdbb58d4 Mon Sep 17 00:00:00 2001 From: Amerigo Wang Date: Thu, 9 Aug 2012 22:14:56 +0000 Subject: net: move and rename netif_notify_peers() I believe net/core/dev.c is a better place for netif_notify_peers(), because other net event notify functions also stay in this file. And rename it to netdev_notify_peers(). Cc: David S. Miller Cc: Ian Campbell Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a9db4f33407f..8d4b7316c734 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2246,8 +2246,6 @@ extern void netif_carrier_on(struct net_device *dev); extern void netif_carrier_off(struct net_device *dev); -extern void netif_notify_peers(struct net_device *dev); - /** * netif_dormant_on - mark device as dormant. * @dev: network device @@ -2596,6 +2594,7 @@ extern void __dev_set_rx_mode(struct net_device *dev); extern int dev_set_promiscuity(struct net_device *dev, int inc); extern int dev_set_allmulti(struct net_device *dev, int inc); extern void netdev_state_change(struct net_device *dev); +extern void netdev_notify_peers(struct net_device *dev); extern int netdev_bonding_change(struct net_device *dev, unsigned long event); extern void netdev_features_change(struct net_device *dev); -- cgit v1.2.3 From b7bc2a5b5bd99b216c3e5fe68c7f45c684ab5745 Mon Sep 17 00:00:00 2001 From: Amerigo Wang Date: Thu, 9 Aug 2012 22:14:57 +0000 Subject: net: remove netdev_bonding_change() I don't see any benifits to use netdev_bonding_change() than using call_netdevice_notifiers() directly. Cc: David S. Miller Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 8d4b7316c734..1d6ab69c1f3f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2595,8 +2595,6 @@ extern int dev_set_promiscuity(struct net_device *dev, int inc); extern int dev_set_allmulti(struct net_device *dev, int inc); extern void netdev_state_change(struct net_device *dev); extern void netdev_notify_peers(struct net_device *dev); -extern int netdev_bonding_change(struct net_device *dev, - unsigned long event); extern void netdev_features_change(struct net_device *dev); /* Load a device via the kmod */ extern void dev_load(struct net *net, const char *name); -- cgit v1.2.3 From c12b395a46646bab69089ce7016ac78177f6001f Mon Sep 17 00:00:00 2001 From: "xeb@mail.ru" Date: Fri, 10 Aug 2012 00:51:50 +0000 Subject: gre: Support GRE over IPv6 GRE over IPv6 implementation. Signed-off-by: Dmitry Kozlov Signed-off-by: David S. Miller --- include/linux/if_arp.h | 1 + include/linux/if_tunnel.h | 3 +++ include/linux/ip6_tunnel.h | 17 +++++++++++++++++ 3 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h index f0e69c6e8208..9adcc29f084a 100644 --- a/include/linux/if_arp.h +++ b/include/linux/if_arp.h @@ -92,6 +92,7 @@ #define ARPHRD_PHONET 820 /* PhoNet media type */ #define ARPHRD_PHONET_PIPE 821 /* PhoNet pipe header */ #define ARPHRD_CAIF 822 /* CAIF media type */ +#define ARPHRD_IP6GRE 823 /* GRE over IPv6 */ #define ARPHRD_VOID 0xFFFF /* Void type, nothing is known */ #define ARPHRD_NONE 0xFFFE /* zero header length */ diff --git a/include/linux/if_tunnel.h b/include/linux/if_tunnel.h index 5efff60b6f56..8c5035ac3142 100644 --- a/include/linux/if_tunnel.h +++ b/include/linux/if_tunnel.h @@ -75,6 +75,9 @@ enum { IFLA_GRE_TTL, IFLA_GRE_TOS, IFLA_GRE_PMTUDISC, + IFLA_GRE_ENCAP_LIMIT, + IFLA_GRE_FLOWINFO, + IFLA_GRE_FLAGS, __IFLA_GRE_MAX, }; diff --git a/include/linux/ip6_tunnel.h b/include/linux/ip6_tunnel.h index bf22b0317902..48af63c9a48d 100644 --- a/include/linux/ip6_tunnel.h +++ b/include/linux/ip6_tunnel.h @@ -31,4 +31,21 @@ struct ip6_tnl_parm { struct in6_addr raddr; /* remote tunnel end-point address */ }; +struct ip6_tnl_parm2 { + char name[IFNAMSIZ]; /* name of tunnel device */ + int link; /* ifindex of underlying L2 interface */ + __u8 proto; /* tunnel protocol */ + __u8 encap_limit; /* encapsulation limit for tunnel */ + __u8 hop_limit; /* hop limit for tunnel */ + __be32 flowinfo; /* traffic class and flowlabel for tunnel */ + __u32 flags; /* tunnel flags */ + struct in6_addr laddr; /* local tunnel end-point address */ + struct in6_addr raddr; /* remote tunnel end-point address */ + + __be16 i_flags; + __be16 o_flags; + __be32 i_key; + __be32 o_key; +}; + #endif -- cgit v1.2.3 From 96ec6327144e1ac9e6676e34fae8b49c2102fa5a Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Mon, 13 Aug 2012 05:53:28 +0000 Subject: packet: Diag core and basic socket info dumping The diag module can be built independently from the af_packet.ko one, just like it's done in unix sockets. The core dumping message carries the info available at socket creation time, i.e. family, type and protocol (in the same byte order as shown in the proc file). The socket inode number and cookie is reserved for future per-socket info retrieving. The per-protocol filtering is also reserved for future by requiring the sdiag_protocol to be zero. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- include/linux/Kbuild | 1 + include/linux/packet_diag.h | 24 ++++++++++++++++++++++++ 2 files changed, 25 insertions(+) create mode 100644 include/linux/packet_diag.h (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index d9a754474878..d823d603dadd 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -195,6 +195,7 @@ header-y += in_route.h header-y += sock_diag.h header-y += inet_diag.h header-y += unix_diag.h +header-y += packet_diag.h header-y += inotify.h header-y += input.h header-y += ioctl.h diff --git a/include/linux/packet_diag.h b/include/linux/packet_diag.h new file mode 100644 index 000000000000..fa19300ca334 --- /dev/null +++ b/include/linux/packet_diag.h @@ -0,0 +1,24 @@ +#ifndef __PACKET_DIAG_H__ +#define __PACKET_DIAG_H__ + +#include + +struct packet_diag_req { + __u8 sdiag_family; + __u8 sdiag_protocol; + __u16 pad; + __u32 pdiag_ino; + __u32 pdiag_show; + __u32 pdiag_cookie[2]; +}; + +struct packet_diag_msg { + __u8 pdiag_family; + __u8 pdiag_type; + __u16 pdiag_num; + + __u32 pdiag_ino; + __u32 pdiag_cookie[2]; +}; + +#endif -- cgit v1.2.3 From 8a360be0c5f8fe2c46f0a524886fa56596534193 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Mon, 13 Aug 2012 05:55:46 +0000 Subject: packet: Report more packet sk info via diag module This reports in one rtattr message all the other scalar values, that can be set on a packet socket with setsockopt. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- include/linux/packet_diag.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/packet_diag.h b/include/linux/packet_diag.h index fa19300ca334..3781ea4bc829 100644 --- a/include/linux/packet_diag.h +++ b/include/linux/packet_diag.h @@ -12,6 +12,8 @@ struct packet_diag_req { __u32 pdiag_cookie[2]; }; +#define PACKET_SHOW_INFO 0x00000001 /* Basic packet_sk information */ + struct packet_diag_msg { __u8 pdiag_family; __u8 pdiag_type; @@ -21,4 +23,25 @@ struct packet_diag_msg { __u32 pdiag_cookie[2]; }; +enum { + PACKET_DIAG_INFO, + + PACKET_DIAG_MAX, +}; + +struct packet_diag_info { + __u32 pdi_index; + __u32 pdi_version; + __u32 pdi_reserve; + __u32 pdi_copy_thresh; + __u32 pdi_tstamp; + __u32 pdi_flags; + +#define PDI_RUNNING 0x1 +#define PDI_AUXDATA 0x2 +#define PDI_ORIGDEV 0x4 +#define PDI_VNETHDR 0x8 +#define PDI_LOSS 0x10 +}; + #endif -- cgit v1.2.3 From eea68e2f1a0061e09265992b91fdc0014930ae92 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Mon, 13 Aug 2012 05:57:44 +0000 Subject: packet: Report socket mclist info via diag module The info is reported as an array of packet_diag_mclist structures. Each includes not only the directly configured values (index, type, etc), but also the "count". Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- include/linux/packet_diag.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/packet_diag.h b/include/linux/packet_diag.h index 3781ea4bc829..ea2e8923bd7e 100644 --- a/include/linux/packet_diag.h +++ b/include/linux/packet_diag.h @@ -13,6 +13,7 @@ struct packet_diag_req { }; #define PACKET_SHOW_INFO 0x00000001 /* Basic packet_sk information */ +#define PACKET_SHOW_MCLIST 0x00000002 /* A set of packet_diag_mclist-s */ struct packet_diag_msg { __u8 pdiag_family; @@ -25,6 +26,7 @@ struct packet_diag_msg { enum { PACKET_DIAG_INFO, + PACKET_DIAG_MCLIST, PACKET_DIAG_MAX, }; @@ -44,4 +46,12 @@ struct packet_diag_info { #define PDI_LOSS 0x10 }; +struct packet_diag_mclist { + __u32 pdmc_index; + __u32 pdmc_count; + __u16 pdmc_type; + __u16 pdmc_alen; + __u8 pdmc_addr[MAX_ADDR_LEN]; +}; + #endif -- cgit v1.2.3 From 16f01365fa01150bf3606fe702a80a03ec87953a Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Thu, 16 Aug 2012 05:34:22 +0000 Subject: packet: Report rings cfg via diag engine One extension bit may result in two nlattrs -- one per ring type. If some ring type is not configured, then the respective nlatts will be empty. The structure reported contains the data, that is given to the corresponding ring setup socket option. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- include/linux/packet_diag.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/packet_diag.h b/include/linux/packet_diag.h index ea2e8923bd7e..34ade828979b 100644 --- a/include/linux/packet_diag.h +++ b/include/linux/packet_diag.h @@ -14,6 +14,7 @@ struct packet_diag_req { #define PACKET_SHOW_INFO 0x00000001 /* Basic packet_sk information */ #define PACKET_SHOW_MCLIST 0x00000002 /* A set of packet_diag_mclist-s */ +#define PACKET_SHOW_RING_CFG 0x00000004 /* Rings configuration parameters */ struct packet_diag_msg { __u8 pdiag_family; @@ -27,6 +28,8 @@ struct packet_diag_msg { enum { PACKET_DIAG_INFO, PACKET_DIAG_MCLIST, + PACKET_DIAG_RX_RING, + PACKET_DIAG_TX_RING, PACKET_DIAG_MAX, }; @@ -54,4 +57,14 @@ struct packet_diag_mclist { __u8 pdmc_addr[MAX_ADDR_LEN]; }; +struct packet_diag_ring { + __u32 pdr_block_size; + __u32 pdr_block_nr; + __u32 pdr_frame_size; + __u32 pdr_frame_nr; + __u32 pdr_retire_tmo; + __u32 pdr_sizeof_priv; + __u32 pdr_features; +}; + #endif -- cgit v1.2.3 From fff3321d75b1a18231876a1aceb36eacbbf6221e Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Thu, 16 Aug 2012 05:36:48 +0000 Subject: packet: Report fanout status via diag engine Reported value is the same reported by the FANOUT getsockoption, but unlike it, the absent fanout setup results in absent nlattr, rather than in nlattr with zero value. This is done so, since zero fanout report may mean both -- no fanout, and fanout with both id and type zero. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- include/linux/packet_diag.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/packet_diag.h b/include/linux/packet_diag.h index 34ade828979b..93f5fa94a431 100644 --- a/include/linux/packet_diag.h +++ b/include/linux/packet_diag.h @@ -15,6 +15,7 @@ struct packet_diag_req { #define PACKET_SHOW_INFO 0x00000001 /* Basic packet_sk information */ #define PACKET_SHOW_MCLIST 0x00000002 /* A set of packet_diag_mclist-s */ #define PACKET_SHOW_RING_CFG 0x00000004 /* Rings configuration parameters */ +#define PACKET_SHOW_FANOUT 0x00000008 struct packet_diag_msg { __u8 pdiag_family; @@ -30,6 +31,7 @@ enum { PACKET_DIAG_MCLIST, PACKET_DIAG_RX_RING, PACKET_DIAG_TX_RING, + PACKET_DIAG_FANOUT, PACKET_DIAG_MAX, }; -- cgit v1.2.3 From 34f256cc7962a44537a0d33877cd93c89873098e Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Thu, 16 Aug 2012 12:09:13 +0000 Subject: tipc: eliminate configuration for maximum number of name subscriptions Gets rid of the need for users to specify the maximum number of name subscriptions supported by TIPC. TIPC now automatically provides support for the maximum number of name subscriptions to 65535. Signed-off-by: Ying Xue Signed-off-by: Jon Maloy Signed-off-by: Paul Gortmaker Signed-off-by: David S. Miller --- include/linux/tipc_config.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tipc_config.h b/include/linux/tipc_config.h index c98928420100..8dd8305c26c5 100644 --- a/include/linux/tipc_config.h +++ b/include/linux/tipc_config.h @@ -90,7 +90,7 @@ #define TIPC_CMD_GET_REMOTE_MNG 0x4003 /* tx none, rx unsigned */ #define TIPC_CMD_GET_MAX_PORTS 0x4004 /* tx none, rx unsigned */ #define TIPC_CMD_GET_MAX_PUBL 0x4005 /* tx none, rx unsigned */ -#define TIPC_CMD_GET_MAX_SUBSCR 0x4006 /* tx none, rx unsigned */ +#define TIPC_CMD_GET_MAX_SUBSCR 0x4006 /* obsoleted */ #define TIPC_CMD_GET_MAX_ZONES 0x4007 /* obsoleted */ #define TIPC_CMD_GET_MAX_CLUSTERS 0x4008 /* obsoleted */ #define TIPC_CMD_GET_MAX_NODES 0x4009 /* obsoleted */ @@ -116,7 +116,7 @@ #define TIPC_CMD_SET_REMOTE_MNG 0x8003 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_PORTS 0x8004 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_PUBL 0x8005 /* tx unsigned, rx none */ -#define TIPC_CMD_SET_MAX_SUBSCR 0x8006 /* tx unsigned, rx none */ +#define TIPC_CMD_SET_MAX_SUBSCR 0x8006 /* obsoleted */ #define TIPC_CMD_SET_MAX_ZONES 0x8007 /* obsoleted */ #define TIPC_CMD_SET_MAX_CLUSTERS 0x8008 /* obsoleted */ #define TIPC_CMD_SET_MAX_NODES 0x8009 /* obsoleted */ -- cgit v1.2.3 From e6a04b1d3ff9d5af219b2fcaebe0ef04733d597c Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Thu, 16 Aug 2012 12:09:14 +0000 Subject: tipc: eliminate configuration for maximum number of name publications Gets rid of the need for users to specify the maximum number of name publications supported by TIPC. TIPC now automatically provides support for the maximum number of name publications to 65535. Signed-off-by: Ying Xue Signed-off-by: Jon Maloy Signed-off-by: Paul Gortmaker Signed-off-by: David S. Miller --- include/linux/tipc_config.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tipc_config.h b/include/linux/tipc_config.h index 8dd8305c26c5..0b1e3f218a36 100644 --- a/include/linux/tipc_config.h +++ b/include/linux/tipc_config.h @@ -89,7 +89,7 @@ #define TIPC_CMD_GET_REMOTE_MNG 0x4003 /* tx none, rx unsigned */ #define TIPC_CMD_GET_MAX_PORTS 0x4004 /* tx none, rx unsigned */ -#define TIPC_CMD_GET_MAX_PUBL 0x4005 /* tx none, rx unsigned */ +#define TIPC_CMD_GET_MAX_PUBL 0x4005 /* obsoleted */ #define TIPC_CMD_GET_MAX_SUBSCR 0x4006 /* obsoleted */ #define TIPC_CMD_GET_MAX_ZONES 0x4007 /* obsoleted */ #define TIPC_CMD_GET_MAX_CLUSTERS 0x4008 /* obsoleted */ @@ -115,7 +115,7 @@ #define TIPC_CMD_SET_NODE_ADDR 0x8001 /* tx net_addr, rx none */ #define TIPC_CMD_SET_REMOTE_MNG 0x8003 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_PORTS 0x8004 /* tx unsigned, rx none */ -#define TIPC_CMD_SET_MAX_PUBL 0x8005 /* tx unsigned, rx none */ +#define TIPC_CMD_SET_MAX_PUBL 0x8005 /* obsoleted */ #define TIPC_CMD_SET_MAX_SUBSCR 0x8006 /* obsoleted */ #define TIPC_CMD_SET_MAX_ZONES 0x8007 /* obsoleted */ #define TIPC_CMD_SET_MAX_CLUSTERS 0x8008 /* obsoleted */ -- cgit v1.2.3 From 1d76efe1577b4323609b1bcbfafa8b731eda071a Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 17 Aug 2012 04:00:48 +0000 Subject: team: add support for non-ethernet devices This is resolved by two things: 1) allow dev_addr of different length than ETH_ALEN 2) during port add, check for dev->type and change it if necessary Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_team.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 33fcc20b5881..8b000b295730 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -123,7 +123,7 @@ struct team_mode_ops { bool (*transmit)(struct team *team, struct sk_buff *skb); int (*port_enter)(struct team *team, struct team_port *port); void (*port_leave)(struct team *team, struct team_port *port); - void (*port_change_mac)(struct team *team, struct team_port *port); + void (*port_change_dev_addr)(struct team *team, struct team_port *port); void (*port_enabled)(struct team *team, struct team_port *port); void (*port_disabled)(struct team *team, struct team_port *port); }; @@ -238,7 +238,7 @@ static inline struct team_port *team_get_port_by_index_rcu(struct team *team, return NULL; } -extern int team_port_set_team_mac(struct team_port *port); +extern int team_port_set_team_dev_addr(struct team_port *port); extern int team_options_register(struct team *team, const struct team_option *option, size_t option_count); -- cgit v1.2.3 From 98104fdeda63d57631c9f89e90a7b83b58fcee40 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sat, 16 Jun 2012 00:19:54 +0200 Subject: cfg80211: add P2P Device abstraction In order to support using a different MAC address for the P2P Device address we must first have a P2P Device abstraction that can be assigned a MAC address. This abstraction will also be useful to support offloading P2P operations to the device, e.g. periodic listen for discoverability. Currently, the driver is responsible for assigning a MAC address to the P2P Device, but this could be changed by allowing a MAC address to be given to the NEW_INTERFACE command. As it has no associated netdev, a P2P Device can only be identified by its wdev identifier but the previous patches allowed using the wdev identifier in various APIs, e.g. remain-on-channel. Signed-off-by: Johannes Berg --- include/linux/nl80211.h | 30 ++++++++++++++++++++++++++---- 1 file changed, 26 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 2f3878806403..458416279347 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -565,6 +565,14 @@ * %NL80211_ATTR_IFINDEX is now on %NL80211_ATTR_WIPHY_FREQ with * %NL80211_ATTR_WIPHY_CHANNEL_TYPE. * + * @NL80211_CMD_START_P2P_DEVICE: Start the given P2P Device, identified by + * its %NL80211_ATTR_WDEV identifier. It must have been created with + * %NL80211_CMD_NEW_INTERFACE previously. After it has been started, the + * P2P Device can be used for P2P operations, e.g. remain-on-channel and + * public action frame TX. + * @NL80211_CMD_STOP_P2P_DEVICE: Stop the given P2P Device, identified by + * its %NL80211_ATTR_WDEV identifier. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -708,6 +716,9 @@ enum nl80211_commands { NL80211_CMD_CH_SWITCH_NOTIFY, + NL80211_CMD_START_P2P_DEVICE, + NL80211_CMD_STOP_P2P_DEVICE, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -1575,6 +1586,10 @@ enum nl80211_attrs { * @NL80211_IFTYPE_MESH_POINT: mesh point * @NL80211_IFTYPE_P2P_CLIENT: P2P client * @NL80211_IFTYPE_P2P_GO: P2P group owner + * @NL80211_IFTYPE_P2P_DEVICE: P2P device interface type, this is not a netdev + * and therefore can't be created in the normal ways, use the + * %NL80211_CMD_START_P2P_DEVICE and %NL80211_CMD_STOP_P2P_DEVICE + * commands to create and destroy one * @NL80211_IFTYPE_MAX: highest interface type number currently defined * @NUM_NL80211_IFTYPES: number of defined interface types * @@ -1593,6 +1608,7 @@ enum nl80211_iftype { NL80211_IFTYPE_MESH_POINT, NL80211_IFTYPE_P2P_CLIENT, NL80211_IFTYPE_P2P_GO, + NL80211_IFTYPE_P2P_DEVICE, /* keep last */ NUM_NL80211_IFTYPES, @@ -2994,12 +3010,18 @@ enum nl80211_ap_sme_features { * @NL80211_FEATURE_CELL_BASE_REG_HINTS: This driver has been tested * to work properly to suppport receiving regulatory hints from * cellular base stations. + * @NL80211_FEATURE_P2P_DEVICE_NEEDS_CHANNEL: If this is set, an active + * P2P Device (%NL80211_IFTYPE_P2P_DEVICE) requires its own channel + * in the interface combinations, even when it's only used for scan + * and remain-on-channel. This could be due to, for example, the + * remain-on-channel implementation requiring a channel context. */ enum nl80211_feature_flags { - NL80211_FEATURE_SK_TX_STATUS = 1 << 0, - NL80211_FEATURE_HT_IBSS = 1 << 1, - NL80211_FEATURE_INACTIVITY_TIMER = 1 << 2, - NL80211_FEATURE_CELL_BASE_REG_HINTS = 1 << 3, + NL80211_FEATURE_SK_TX_STATUS = 1 << 0, + NL80211_FEATURE_HT_IBSS = 1 << 1, + NL80211_FEATURE_INACTIVITY_TIMER = 1 << 2, + NL80211_FEATURE_CELL_BASE_REG_HINTS = 1 << 3, + NL80211_FEATURE_P2P_DEVICE_NEEDS_CHANNEL = 1 << 4, }; /** -- cgit v1.2.3 From 6f6bbc186dc8e4e0c628db7decbd1a5e02cb5fd8 Mon Sep 17 00:00:00 2001 From: Jesse Brandeburg Date: Thu, 26 Jul 2012 02:30:53 +0000 Subject: ethtool.h: MDI setting support This change modifies the core ethtool struct to allow a driver to support setting of MDI/MDI-X state for twisted pair wiring. This change uses a previously reserved u8 and should not change any binary compatibility of ethtool. Also as per Ben Hutchings' suggestion, the capabilities are stored in a separate byte so the driver can report if it supports changing settings. see thread: http://kerneltrap.org/mailarchive/linux-netdev/2010/11/17/6289820/thread see ethtool patches titled: ethtool: allow setting MDI-X state Signed-off-by: Jesse Brandeburg CC: Ben Hutchings Tested-by: Aaron Brown aaron.f.brown@intel.com Signed-off-by: Jeff Kirsher --- include/linux/ethtool.h | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 21eff418091b..fcb4f8e60c1c 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -45,8 +45,10 @@ struct ethtool_cmd { * bits) in Mbps. Please use * ethtool_cmd_speed()/_set() to * access it */ - __u8 eth_tp_mdix; - __u8 reserved2; + __u8 eth_tp_mdix; /* twisted pair MDI-X status */ + __u8 eth_tp_mdix_ctrl; /* twisted pair MDI-X control, when set, + * link should be renegotiated if necessary + */ __u32 lp_advertising; /* Features the link partner advertises */ __u32 reserved[2]; }; @@ -1229,10 +1231,13 @@ struct ethtool_ops { #define AUTONEG_DISABLE 0x00 #define AUTONEG_ENABLE 0x01 -/* Mode MDI or MDI-X */ -#define ETH_TP_MDI_INVALID 0x00 -#define ETH_TP_MDI 0x01 -#define ETH_TP_MDI_X 0x02 +/* MDI or MDI-X status/control - if MDI/MDI_X/AUTO is set then + * the driver is required to renegotiate link + */ +#define ETH_TP_MDI_INVALID 0x00 /* status: unknown; control: unsupported */ +#define ETH_TP_MDI 0x01 /* status: MDI; control: force MDI */ +#define ETH_TP_MDI_X 0x02 /* status: MDI-X; control: force MDI-X */ +#define ETH_TP_MDI_AUTO 0x03 /* control: auto-select */ /* Wake-On-Lan options. */ #define WAKE_PHY (1 << 0) -- cgit v1.2.3 From 06d7de831dab8b93adb86e039a2f3d36604a9197 Mon Sep 17 00:00:00 2001 From: AceLan Kao Date: Thu, 26 Jul 2012 09:51:08 +0800 Subject: Revert "rfkill: remove dead code" This reverts commit 2e48928d8a0f38c1b5c81eb3f1294de8a6382c68. Those functions are needed and should not be removed, or there is no way to set the rfkill led trigger name. Signed-off-by: AceLan Kao Signed-off-by: Johannes Berg --- include/linux/rfkill.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h index 6fdf02737e9d..0ec590bb3611 100644 --- a/include/linux/rfkill.h +++ b/include/linux/rfkill.h @@ -354,6 +354,37 @@ static inline bool rfkill_blocked(struct rfkill *rfkill) } #endif /* RFKILL || RFKILL_MODULE */ + +#ifdef CONFIG_RFKILL_LEDS +/** + * rfkill_get_led_trigger_name - Get the LED trigger name for the button's LED. + * This function might return a NULL pointer if registering of the + * LED trigger failed. Use this as "default_trigger" for the LED. + */ +const char *rfkill_get_led_trigger_name(struct rfkill *rfkill); + +/** + * rfkill_set_led_trigger_name -- set the LED trigger name + * @rfkill: rfkill struct + * @name: LED trigger name + * + * This function sets the LED trigger name of the radio LED + * trigger that rfkill creates. It is optional, but if called + * must be called before rfkill_register() to be effective. + */ +void rfkill_set_led_trigger_name(struct rfkill *rfkill, const char *name); +#else +static inline const char *rfkill_get_led_trigger_name(struct rfkill *rfkill) +{ + return NULL; +} + +static inline void +rfkill_set_led_trigger_name(struct rfkill *rfkill, const char *name) +{ +} +#endif + #endif /* __KERNEL__ */ #endif /* RFKILL_H */ -- cgit v1.2.3 From d57ef3a6a2eeb88df47e892c66692e3f59722ffe Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Fri, 10 Aug 2012 21:23:53 +0200 Subject: bcma: detect and register serial flash device MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Rafał Miłecki Signed-off-by: John W. Linville --- include/linux/bcma/bcma_driver_chipcommon.h | 13 +++++++++++++ include/linux/bcma/bcma_regs.h | 2 ++ 2 files changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index fcb06fb284eb..bed89694c5f9 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -509,6 +509,16 @@ struct bcma_pflash { u32 window_size; }; +#ifdef CONFIG_BCMA_SFLASH +struct bcma_sflash { + bool present; + u32 window; + u32 blocksize; + u16 numblocks; + u32 size; +}; +#endif + struct bcma_serial_port { void *regs; unsigned long clockspeed; @@ -529,6 +539,9 @@ struct bcma_drv_cc { struct bcma_chipcommon_pmu pmu; #ifdef CONFIG_BCMA_DRIVER_MIPS struct bcma_pflash pflash; +#ifdef CONFIG_BCMA_SFLASH + struct bcma_sflash sflash; +#endif int nr_serial_ports; struct bcma_serial_port serial_ports[4]; diff --git a/include/linux/bcma/bcma_regs.h b/include/linux/bcma/bcma_regs.h index a393e82bf7bf..6c9cb93ae3de 100644 --- a/include/linux/bcma/bcma_regs.h +++ b/include/linux/bcma/bcma_regs.h @@ -85,4 +85,6 @@ * (2 ZettaBytes), high 32 bits */ +#define BCMA_SFLASH 0x1c000000 + #endif /* LINUX_BCMA_REGS_H_ */ -- cgit v1.2.3 From 371a00448f95adaa612cf1a0b31a11e7093bc706 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Sun, 12 Aug 2012 13:08:05 +0200 Subject: bcma: detect and register NAND flash device MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Rafał Miłecki Signed-off-by: John W. Linville --- include/linux/bcma/bcma_driver_chipcommon.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index bed89694c5f9..9810d4b29abf 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -519,6 +519,16 @@ struct bcma_sflash { }; #endif +#ifdef CONFIG_BCMA_NFLASH +struct mtd_info; + +struct bcma_nflash { + bool present; + + struct mtd_info *mtd; +}; +#endif + struct bcma_serial_port { void *regs; unsigned long clockspeed; @@ -542,6 +552,9 @@ struct bcma_drv_cc { #ifdef CONFIG_BCMA_SFLASH struct bcma_sflash sflash; #endif +#ifdef CONFIG_BCMA_NFLASH + struct bcma_nflash nflash; +#endif int nr_serial_ports; struct bcma_serial_port serial_ports[4]; -- cgit v1.2.3 From 0115e8e30d6fcdd4b8faa30d3ffd90859a591f51 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 22 Aug 2012 17:19:46 +0000 Subject: net: remove delay at device dismantle I noticed extra one second delay in device dismantle, tracked down to a call to dst_dev_event() while some call_rcu() are still in RCU queues. These call_rcu() were posted by rt_free(struct rtable *rt) calls. We then wait a little (but one second) in netdev_wait_allrefs() before kicking again NETDEV_UNREGISTER. As the call_rcu() are now completed, dst_dev_event() can do the needed device swap on busy dst. To solve this problem, add a new NETDEV_UNREGISTER_FINAL, called after a rcu_barrier(), but outside of RTNL lock. Use NETDEV_UNREGISTER_FINAL with care ! Change dst_dev_event() handler to react to NETDEV_UNREGISTER_FINAL Also remove NETDEV_UNREGISTER_BATCH, as its not used anymore after IP cache removal. With help from Gao feng Signed-off-by: Eric Dumazet Cc: Tom Herbert Cc: Mahesh Bandewar Cc: "Eric W. Biederman" Cc: Gao feng Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4936f09a9333..9ad7fa8c10e0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1553,7 +1553,7 @@ struct packet_type { #define NETDEV_PRE_TYPE_CHANGE 0x000E #define NETDEV_POST_TYPE_CHANGE 0x000F #define NETDEV_POST_INIT 0x0010 -#define NETDEV_UNREGISTER_BATCH 0x0011 +#define NETDEV_UNREGISTER_FINAL 0x0011 #define NETDEV_RELEASE 0x0012 #define NETDEV_NOTIFY_PEERS 0x0013 #define NETDEV_JOIN 0x0014 -- cgit v1.2.3 From b32607dd47d456b99f0a16f1c37bc8a0975ffb19 Mon Sep 17 00:00:00 2001 From: "Allan, Bruce W" Date: Mon, 20 Aug 2012 04:55:29 +0000 Subject: mdio: translation of MMD EEE registers to/from ethtool settings The helper functions which translate IEEE MDIO Manageable Device (MMD) Energy-Efficient Ethernet (EEE) registers 3.20, 7.60 and 7.61 to and from the comparable ethtool supported/advertised settings will be needed by drivers other than those in PHYLIB (e.g. e1000e in a follow-on patch). In the same fashion as similar translation functions in linux/mii.h, move these functions from the PHYLIB core to the linux/mdio.h header file so the code will not have to be duplicated in each driver needing MMD-to-ethtool (and vice-versa) translations. The function and some variable names have been renamed to be more descriptive. Not tested on the only hardware that currently calls the related functions, stmmac, because I don't have access to any. Has been compile tested and the translations have been tested on a locally modified version of e1000e. Signed-off-by: Bruce Allan Cc: Giuseppe Cavallaro Signed-off-by: David S. Miller --- include/linux/mdio.h | 83 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 83 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 7cccafe50e7b..6c406845f7e2 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -377,5 +377,88 @@ static inline void mdio45_ethtool_gset(const struct mdio_if_info *mdio, extern int mdio_mii_ioctl(const struct mdio_if_info *mdio, struct mii_ioctl_data *mii_data, int cmd); +/** + * mmd_eee_cap_to_ethtool_sup_t + * @eee_cap: value of the MMD EEE Capability register + * + * A small helper function that translates MMD EEE Capability (3.20) bits + * to ethtool supported settings. + */ +static inline u32 mmd_eee_cap_to_ethtool_sup_t(u16 eee_cap) +{ + u32 supported = 0; + + if (eee_cap & MDIO_EEE_100TX) + supported |= SUPPORTED_100baseT_Full; + if (eee_cap & MDIO_EEE_1000T) + supported |= SUPPORTED_1000baseT_Full; + if (eee_cap & MDIO_EEE_10GT) + supported |= SUPPORTED_10000baseT_Full; + if (eee_cap & MDIO_EEE_1000KX) + supported |= SUPPORTED_1000baseKX_Full; + if (eee_cap & MDIO_EEE_10GKX4) + supported |= SUPPORTED_10000baseKX4_Full; + if (eee_cap & MDIO_EEE_10GKR) + supported |= SUPPORTED_10000baseKR_Full; + + return supported; +} + +/** + * mmd_eee_adv_to_ethtool_adv_t + * @eee_adv: value of the MMD EEE Advertisement/Link Partner Ability registers + * + * A small helper function that translates the MMD EEE Advertisment (7.60) + * and MMD EEE Link Partner Ability (7.61) bits to ethtool advertisement + * settings. + */ +static inline u32 mmd_eee_adv_to_ethtool_adv_t(u16 eee_adv) +{ + u32 adv = 0; + + if (eee_adv & MDIO_EEE_100TX) + adv |= ADVERTISED_100baseT_Full; + if (eee_adv & MDIO_EEE_1000T) + adv |= ADVERTISED_1000baseT_Full; + if (eee_adv & MDIO_EEE_10GT) + adv |= ADVERTISED_10000baseT_Full; + if (eee_adv & MDIO_EEE_1000KX) + adv |= ADVERTISED_1000baseKX_Full; + if (eee_adv & MDIO_EEE_10GKX4) + adv |= ADVERTISED_10000baseKX4_Full; + if (eee_adv & MDIO_EEE_10GKR) + adv |= ADVERTISED_10000baseKR_Full; + + return adv; +} + +/** + * ethtool_adv_to_mmd_eee_adv_t + * @adv: the ethtool advertisement settings + * + * A small helper function that translates ethtool advertisement settings + * to EEE advertisements for the MMD EEE Advertisement (7.60) and + * MMD EEE Link Partner Ability (7.61) registers. + */ +static inline u16 ethtool_adv_to_mmd_eee_adv_t(u32 adv) +{ + u16 reg = 0; + + if (adv & ADVERTISED_100baseT_Full) + reg |= MDIO_EEE_100TX; + if (adv & ADVERTISED_1000baseT_Full) + reg |= MDIO_EEE_1000T; + if (adv & ADVERTISED_10000baseT_Full) + reg |= MDIO_EEE_10GT; + if (adv & ADVERTISED_1000baseKX_Full) + reg |= MDIO_EEE_1000KX; + if (adv & ADVERTISED_10000baseKX4_Full) + reg |= MDIO_EEE_10GKX4; + if (adv & ADVERTISED_10000baseKR_Full) + reg |= MDIO_EEE_10GKR; + + return reg; +} + #endif /* __KERNEL__ */ #endif /* __LINUX_MDIO_H__ */ -- cgit v1.2.3 From 8f4cccbbd92f2ad0ddbbc498ef7cee2a1c3defe9 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Mon, 20 Aug 2012 22:16:51 +0100 Subject: net: Set device operstate at registration time The operstate of a device is initially IF_OPER_UNKNOWN and is updated asynchronously by linkwatch after each change of carrier state reported by the driver. The default carrier state of a net device is on, and this will never be changed on drivers that do not support carrier detection, thus the operstate remains IF_OPER_UNKNOWN. For devices that do support carrier detection, the driver must set the carrier state to off initially, then poll the hardware state when the device is opened. However, we must not activate linkwatch for a unregistered device, and commit b473001 ('net: Do not fire linkwatch events until the device is registered.') ensured that we don't. But this means that the operstate for many devices that support carrier detection remains IF_OPER_UNKNOWN when it should be IF_OPER_DOWN. The same issue exists with the dormant state. The proper initialisation sequence, avoiding a race with opening of the device, is: rtnl_lock(); rc = register_netdevice(dev); if (rc) goto out_unlock; netif_carrier_off(dev); /* or netif_dormant_on(dev) */ rtnl_unlock(); but it seems silly that this should have to be repeated in so many drivers. Further, the operstate seen immediately after opening the device may still be IF_OPER_UNKNOWN due to the asynchronous nature of linkwatch. Commit 22604c8 ('net: Fix for initial link state in 2.6.28') attempted to fix this by setting the operstate synchronously, but it was reverted as it could lead to deadlock. This initialises the operstate synchronously at registration time only. Signed-off-by: Ben Hutchings 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 9ad7fa8c10e0..ccac82e61604 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2227,6 +2227,7 @@ static inline void dev_hold(struct net_device *dev) * kind of lower layer not just hardware media. */ +extern void linkwatch_init_dev(struct net_device *dev); extern void linkwatch_fire_event(struct net_device *dev); extern void linkwatch_forget_dev(struct net_device *dev); -- cgit v1.2.3 From 9b361c13ceeae872161175d39f4798ee345ed10c Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 23 Aug 2012 03:26:52 +0000 Subject: vlan: add helper which can be called to see if device is used by vlan also, remove unused vlan_info definition from header CC: Patrick McHardy Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index a810987cb80e..e6ff12dd717b 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -74,8 +74,6 @@ static inline struct vlan_ethhdr *vlan_eth_hdr(const struct sk_buff *skb) /* found in socket.c */ extern void vlan_ioctl_set(int (*hook)(struct net *, void __user *)); -struct vlan_info; - static inline int is_vlan_dev(struct net_device *dev) { return dev->priv_flags & IFF_802_1Q_VLAN; @@ -101,6 +99,8 @@ extern int vlan_vids_add_by_dev(struct net_device *dev, const struct net_device *by_dev); extern void vlan_vids_del_by_dev(struct net_device *dev, const struct net_device *by_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, u16 vlan_id) @@ -151,6 +151,11 @@ static inline void vlan_vids_del_by_dev(struct net_device *dev, const struct net_device *by_dev) { } + +static inline bool vlan_uses_dev(const struct net_device *dev) +{ + return false; +} #endif /** -- cgit v1.2.3 From 4cdd34084d539c758d00c5dc7bf95db2e4f2bc70 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sun, 26 Aug 2012 19:13:58 +0200 Subject: netfilter: nf_conntrack_ipv6: improve fragmentation handling The IPv6 conntrack fragmentation currently has a couple of shortcomings. Fragmentes are collected in PREROUTING/OUTPUT, are defragmented, the defragmented packet is then passed to conntrack, the resulting conntrack information is attached to each original fragment and the fragments then continue their way through the stack. Helper invocation occurs in the POSTROUTING hook, at which point only the original fragments are available. The result of this is that fragmented packets are never passed to helpers. This patch improves the situation in the following way: - If a reassembled packet belongs to a connection that has a helper assigned, the reassembled packet is passed through the stack instead of the original fragments. - During defragmentation, the largest received fragment size is stored. On output, the packet is refragmented if required. If the largest received fragment size exceeds the outgoing MTU, a "packet too big" message is generated, thus behaving as if the original fragments were passed through the stack from an outside point of view. - The ipv6_helper() hook function can't receive fragments anymore for connections using a helper, so it is switched to use ipv6_skip_exthdr() instead of the netfilter specific nf_ct_ipv6_skip_exthdr() and the reassembled packets are passed to connection tracking helpers. The result of this is that we can properly track fragmented packets, but still generate ICMPv6 Packet too big messages if we would have before. This patch is also required as a precondition for IPv6 NAT, where NAT helpers might enlarge packets up to a point that they require fragmentation. In that case we can't generate Packet too big messages since the proper MTU can't be calculated in all cases (f.i. when changing textual representation of a variable amount of addresses), so the packet is transparently fragmented iff the original packet or fragments would have fit the outgoing MTU. IPVS parts by Jesper Dangaard Brouer . Signed-off-by: Patrick McHardy --- include/linux/ipv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 879db26ec401..0b94e91ed685 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -256,6 +256,7 @@ struct inet6_skb_parm { #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) __u16 dsthao; #endif + __u16 frag_max_size; #define IP6SKB_XFRM_TRANSFORMED 1 #define IP6SKB_FORWARDED 2 -- cgit v1.2.3 From 051966c0c644a1c96092d4206e00704ade813c9a Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sun, 26 Aug 2012 19:14:04 +0200 Subject: netfilter: nf_nat: add protoff argument to packet mangling functions For mangling IPv6 packets the protocol header offset needs to be known by the NAT packet mangling functions. Add a so far unused protoff argument and convert the conntrack and NAT helpers to use it in preparation of IPv6 NAT. Signed-off-by: Patrick McHardy --- include/linux/netfilter/nf_conntrack_amanda.h | 1 + include/linux/netfilter/nf_conntrack_ftp.h | 1 + include/linux/netfilter/nf_conntrack_h323.h | 15 ++++++++++----- include/linux/netfilter/nf_conntrack_irc.h | 1 + include/linux/netfilter/nf_conntrack_pptp.h | 2 ++ include/linux/netfilter/nf_conntrack_sip.h | 12 ++++++++++-- 6 files changed, 25 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_amanda.h b/include/linux/netfilter/nf_conntrack_amanda.h index 0bb5a6976bf3..4b59a1584959 100644 --- a/include/linux/netfilter/nf_conntrack_amanda.h +++ b/include/linux/netfilter/nf_conntrack_amanda.h @@ -4,6 +4,7 @@ extern unsigned int (*nf_nat_amanda_hook)(struct sk_buff *skb, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned int matchoff, unsigned int matchlen, struct nf_conntrack_expect *exp); diff --git a/include/linux/netfilter/nf_conntrack_ftp.h b/include/linux/netfilter/nf_conntrack_ftp.h index 3e3aa08980c3..28f18df36525 100644 --- a/include/linux/netfilter/nf_conntrack_ftp.h +++ b/include/linux/netfilter/nf_conntrack_ftp.h @@ -34,6 +34,7 @@ struct nf_conntrack_expect; extern unsigned int (*nf_nat_ftp_hook)(struct sk_buff *skb, enum ip_conntrack_info ctinfo, enum nf_ct_ftp_type type, + unsigned int protoff, unsigned int matchoff, unsigned int matchlen, struct nf_conntrack_expect *exp); diff --git a/include/linux/netfilter/nf_conntrack_h323.h b/include/linux/netfilter/nf_conntrack_h323.h index 26f9226ea72b..f381020eee92 100644 --- a/include/linux/netfilter/nf_conntrack_h323.h +++ b/include/linux/netfilter/nf_conntrack_h323.h @@ -36,12 +36,12 @@ extern void nf_conntrack_h245_expect(struct nf_conn *new, struct nf_conntrack_expect *this); extern void nf_conntrack_q931_expect(struct nf_conn *new, struct nf_conntrack_expect *this); -extern int (*set_h245_addr_hook) (struct sk_buff *skb, +extern int (*set_h245_addr_hook) (struct sk_buff *skb, unsigned int protoff, unsigned char **data, int dataoff, H245_TransportAddress *taddr, union nf_inet_addr *addr, __be16 port); -extern int (*set_h225_addr_hook) (struct sk_buff *skb, +extern int (*set_h225_addr_hook) (struct sk_buff *skb, unsigned int protoff, unsigned char **data, int dataoff, TransportAddress *taddr, union nf_inet_addr *addr, @@ -49,40 +49,45 @@ extern int (*set_h225_addr_hook) (struct sk_buff *skb, extern int (*set_sig_addr_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned char **data, + unsigned int protoff, unsigned char **data, TransportAddress *taddr, int count); extern int (*set_ras_addr_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned char **data, + unsigned int protoff, unsigned char **data, TransportAddress *taddr, int count); extern int (*nat_rtp_rtcp_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned char **data, int dataoff, + unsigned int protoff, unsigned char **data, + int dataoff, H245_TransportAddress *taddr, __be16 port, __be16 rtp_port, struct nf_conntrack_expect *rtp_exp, struct nf_conntrack_expect *rtcp_exp); extern int (*nat_t120_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, H245_TransportAddress *taddr, __be16 port, struct nf_conntrack_expect *exp); extern int (*nat_h245_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, TransportAddress *taddr, __be16 port, struct nf_conntrack_expect *exp); extern int (*nat_callforwarding_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, TransportAddress *taddr, __be16 port, struct nf_conntrack_expect *exp); extern int (*nat_q931_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, TransportAddress *taddr, int idx, __be16 port, struct nf_conntrack_expect *exp); diff --git a/include/linux/netfilter/nf_conntrack_irc.h b/include/linux/netfilter/nf_conntrack_irc.h index 36282bf71b63..4bb9bae67176 100644 --- a/include/linux/netfilter/nf_conntrack_irc.h +++ b/include/linux/netfilter/nf_conntrack_irc.h @@ -7,6 +7,7 @@ extern unsigned int (*nf_nat_irc_hook)(struct sk_buff *skb, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned int matchoff, unsigned int matchlen, struct nf_conntrack_expect *exp); diff --git a/include/linux/netfilter/nf_conntrack_pptp.h b/include/linux/netfilter/nf_conntrack_pptp.h index 3bbde0c3a8a6..2ab2830316b7 100644 --- a/include/linux/netfilter/nf_conntrack_pptp.h +++ b/include/linux/netfilter/nf_conntrack_pptp.h @@ -303,12 +303,14 @@ struct nf_conntrack_expect; extern int (*nf_nat_pptp_hook_outbound)(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, struct PptpControlHeader *ctlh, union pptp_ctrl_union *pptpReq); extern int (*nf_nat_pptp_hook_inbound)(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, struct PptpControlHeader *ctlh, union pptp_ctrl_union *pptpReq); diff --git a/include/linux/netfilter/nf_conntrack_sip.h b/include/linux/netfilter/nf_conntrack_sip.h index 89f2a627f3f0..1afc669a393e 100644 --- a/include/linux/netfilter/nf_conntrack_sip.h +++ b/include/linux/netfilter/nf_conntrack_sip.h @@ -37,10 +37,12 @@ struct sdp_media_type { struct sip_handler { const char *method; unsigned int len; - int (*request)(struct sk_buff *skb, unsigned int dataoff, + int (*request)(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq); - int (*response)(struct sk_buff *skb, unsigned int dataoff, + int (*response)(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq, unsigned int code); }; @@ -105,11 +107,13 @@ enum sdp_header_types { }; extern unsigned int (*nf_nat_sip_hook)(struct sk_buff *skb, + unsigned int protoff, unsigned int dataoff, const char **dptr, unsigned int *datalen); extern void (*nf_nat_sip_seq_adjust_hook)(struct sk_buff *skb, s16 off); extern unsigned int (*nf_nat_sip_expect_hook)(struct sk_buff *skb, + unsigned int protoff, unsigned int dataoff, const char **dptr, unsigned int *datalen, @@ -117,6 +121,7 @@ extern unsigned int (*nf_nat_sip_expect_hook)(struct sk_buff *skb, unsigned int matchoff, unsigned int matchlen); extern unsigned int (*nf_nat_sdp_addr_hook)(struct sk_buff *skb, + unsigned int protoff, unsigned int dataoff, const char **dptr, unsigned int *datalen, @@ -125,6 +130,7 @@ extern unsigned int (*nf_nat_sdp_addr_hook)(struct sk_buff *skb, enum sdp_header_types term, const union nf_inet_addr *addr); extern unsigned int (*nf_nat_sdp_port_hook)(struct sk_buff *skb, + unsigned int protoff, unsigned int dataoff, const char **dptr, unsigned int *datalen, @@ -132,12 +138,14 @@ extern unsigned int (*nf_nat_sdp_port_hook)(struct sk_buff *skb, unsigned int matchlen, u_int16_t port); extern unsigned int (*nf_nat_sdp_session_hook)(struct sk_buff *skb, + unsigned int protoff, unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int sdpoff, const union nf_inet_addr *addr); extern unsigned int (*nf_nat_sdp_media_hook)(struct sk_buff *skb, + unsigned int protoff, unsigned int dataoff, const char **dptr, unsigned int *datalen, -- cgit v1.2.3 From c7232c9979cba684c50b64c513c4a83c9aa70563 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sun, 26 Aug 2012 19:14:06 +0200 Subject: netfilter: add protocol independent NAT core Convert the IPv4 NAT implementation to a protocol independent core and address family specific modules. Signed-off-by: Patrick McHardy --- include/linux/netfilter.h | 14 ++++++-------- include/linux/netfilter/nf_nat.h | 8 ++++++++ include/linux/netfilter/nfnetlink_conntrack.h | 6 ++++-- include/linux/netfilter_ipv4.h | 1 - 4 files changed, 18 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index c613cf0d7884..1dcf2a38e51f 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -342,7 +342,7 @@ extern int nf_register_afinfo(const struct nf_afinfo *afinfo); extern void nf_unregister_afinfo(const struct nf_afinfo *afinfo); #include -extern void (*ip_nat_decode_session)(struct sk_buff *, struct flowi *); +extern void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *); static inline void nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) @@ -350,13 +350,11 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) #ifdef CONFIG_NF_NAT_NEEDED void (*decodefn)(struct sk_buff *, struct flowi *); - if (family == AF_INET) { - rcu_read_lock(); - decodefn = rcu_dereference(ip_nat_decode_session); - if (decodefn) - decodefn(skb, fl); - rcu_read_unlock(); - } + rcu_read_lock(); + decodefn = rcu_dereference(nf_nat_decode_session_hook); + if (decodefn) + decodefn(skb, fl); + rcu_read_unlock(); #endif } diff --git a/include/linux/netfilter/nf_nat.h b/include/linux/netfilter/nf_nat.h index 8df2d13730b2..bf0cc373ffb6 100644 --- a/include/linux/netfilter/nf_nat.h +++ b/include/linux/netfilter/nf_nat.h @@ -22,4 +22,12 @@ struct nf_nat_ipv4_multi_range_compat { struct nf_nat_ipv4_range range[1]; }; +struct nf_nat_range { + unsigned int flags; + union nf_inet_addr min_addr; + union nf_inet_addr max_addr; + union nf_conntrack_man_proto min_proto; + union nf_conntrack_man_proto max_proto; +}; + #endif /* _NETFILTER_NF_NAT_H */ diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h index f649f7423ca2..68920eab287c 100644 --- a/include/linux/netfilter/nfnetlink_conntrack.h +++ b/include/linux/netfilter/nfnetlink_conntrack.h @@ -142,8 +142,10 @@ enum ctattr_tstamp { enum ctattr_nat { CTA_NAT_UNSPEC, - CTA_NAT_MINIP, - CTA_NAT_MAXIP, + CTA_NAT_V4_MINIP, +#define CTA_NAT_MINIP CTA_NAT_V4_MINIP + CTA_NAT_V4_MAXIP, +#define CTA_NAT_MAXIP CTA_NAT_V4_MAXIP CTA_NAT_PROTO, __CTA_NAT_MAX }; diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h index e2b12801378d..b962dfc695ae 100644 --- a/include/linux/netfilter_ipv4.h +++ b/include/linux/netfilter_ipv4.h @@ -79,7 +79,6 @@ enum nf_ip_hook_priorities { #ifdef __KERNEL__ extern int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type); -extern int ip_xfrm_me_harder(struct sk_buff *skb); extern __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol); #endif /*__KERNEL__*/ -- cgit v1.2.3 From 58a317f1061c894d2344c0b6a18ab4a64b69b815 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sun, 26 Aug 2012 19:14:12 +0200 Subject: netfilter: ipv6: add IPv6 NAT support Signed-off-by: Patrick McHardy --- include/linux/netfilter/nfnetlink_conntrack.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h index 68920eab287c..43bfe3e1685b 100644 --- a/include/linux/netfilter/nfnetlink_conntrack.h +++ b/include/linux/netfilter/nfnetlink_conntrack.h @@ -147,6 +147,8 @@ enum ctattr_nat { CTA_NAT_V4_MAXIP, #define CTA_NAT_MAXIP CTA_NAT_V4_MAXIP CTA_NAT_PROTO, + CTA_NAT_V6_MINIP, + CTA_NAT_V6_MAXIP, __CTA_NAT_MAX }; #define CTA_NAT_MAX (__CTA_NAT_MAX - 1) -- cgit v1.2.3 From 9a664821068739dbc8eac13770e28167b46a0c0f Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sun, 26 Aug 2012 19:14:25 +0200 Subject: netfilter: nf_nat: support IPv6 in SIP NAT helper Add IPv6 support to the SIP NAT helper. There are no functional differences to IPv4 NAT, just different formats for addresses. Signed-off-by: Patrick McHardy --- include/linux/netfilter/nf_conntrack_sip.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_sip.h b/include/linux/netfilter/nf_conntrack_sip.h index 1afc669a393e..387bdd02945d 100644 --- a/include/linux/netfilter/nf_conntrack_sip.h +++ b/include/linux/netfilter/nf_conntrack_sip.h @@ -99,10 +99,8 @@ enum sip_header_types { enum sdp_header_types { SDP_HDR_UNSPEC, SDP_HDR_VERSION, - SDP_HDR_OWNER_IP4, - SDP_HDR_CONNECTION_IP4, - SDP_HDR_OWNER_IP6, - SDP_HDR_CONNECTION_IP6, + SDP_HDR_OWNER, + SDP_HDR_CONNECTION, SDP_HDR_MEDIA, }; @@ -111,7 +109,8 @@ extern unsigned int (*nf_nat_sip_hook)(struct sk_buff *skb, unsigned int dataoff, const char **dptr, unsigned int *datalen); -extern void (*nf_nat_sip_seq_adjust_hook)(struct sk_buff *skb, s16 off); +extern void (*nf_nat_sip_seq_adjust_hook)(struct sk_buff *skb, + unsigned int protoff, s16 off); extern unsigned int (*nf_nat_sip_expect_hook)(struct sk_buff *skb, unsigned int protoff, unsigned int dataoff, -- cgit v1.2.3 From 8a91bb0c304b0853f8c59b1b48c7822c52362cba Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sun, 26 Aug 2012 19:14:31 +0200 Subject: netfilter: ip6tables: add stateless IPv6-to-IPv6 Network Prefix Translation target Signed-off-by: Patrick McHardy --- include/linux/netfilter_ipv6/Kbuild | 1 + include/linux/netfilter_ipv6/ip6t_NPT.h | 16 ++++++++++++++++ 2 files changed, 17 insertions(+) create mode 100644 include/linux/netfilter_ipv6/ip6t_NPT.h (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv6/Kbuild b/include/linux/netfilter_ipv6/Kbuild index bd095bc075e9..b88c0058bf73 100644 --- a/include/linux/netfilter_ipv6/Kbuild +++ b/include/linux/netfilter_ipv6/Kbuild @@ -1,6 +1,7 @@ header-y += ip6_tables.h header-y += ip6t_HL.h header-y += ip6t_LOG.h +header-y += ip6t_NPT.h header-y += ip6t_REJECT.h header-y += ip6t_ah.h header-y += ip6t_frag.h diff --git a/include/linux/netfilter_ipv6/ip6t_NPT.h b/include/linux/netfilter_ipv6/ip6t_NPT.h new file mode 100644 index 000000000000..f763355481b5 --- /dev/null +++ b/include/linux/netfilter_ipv6/ip6t_NPT.h @@ -0,0 +1,16 @@ +#ifndef __NETFILTER_IP6T_NPT +#define __NETFILTER_IP6T_NPT + +#include +#include + +struct ip6t_npt_tginfo { + union nf_inet_addr src_pfx; + union nf_inet_addr dst_pfx; + __u8 src_pfx_len; + __u8 dst_pfx_len; + /* Used internally by the kernel */ + __sum16 adjustment; +}; + +#endif /* __NETFILTER_IP6T_NPT */ -- cgit v1.2.3 From f9dc9ac51610a35629c8211b6b8c9b0c65cf0e1d Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Fri, 24 Aug 2012 01:58:59 +0000 Subject: of/mdio: Add dummy functions in of_mdio.h. This patch adds dummy functions in of_mdio.h, so that driver need not ifdef there code with CONFIG_OF. Signed-off-by: Srinivas Kandagatla Signed-off-by: David S. Miller --- include/linux/of_mdio.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 912c27a0f7ee..6ef49b803efb 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -12,6 +12,7 @@ #include #include +#ifdef CONFIG_OF extern int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np); extern struct phy_device *of_phy_find_device(struct device_node *phy_np); extern struct phy_device *of_phy_connect(struct net_device *dev, @@ -24,4 +25,36 @@ extern struct phy_device *of_phy_connect_fixed_link(struct net_device *dev, extern struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np); +#else /* CONFIG_OF */ +int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) +{ + return -ENOSYS; +} + +struct phy_device *of_phy_find_device(struct device_node *phy_np) +{ + return NULL; +} + +struct phy_device *of_phy_connect(struct net_device *dev, + struct device_node *phy_np, + void (*hndlr)(struct net_device *), + u32 flags, phy_interface_t iface) +{ + return NULL; +} + +struct phy_device *of_phy_connect_fixed_link(struct net_device *dev, + void (*hndlr)(struct net_device *), + phy_interface_t iface) +{ + return NULL; +} + +struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np) +{ + return NULL; +} +#endif /* CONFIG_OF */ + #endif /* __LINUX_OF_MDIO_H */ -- cgit v1.2.3 From d56631a66c0d0c9d662abfb38cd1f6326eeebd7c Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Thu, 30 Aug 2012 05:50:43 +0000 Subject: net:stmmac: Remove bus_id from mdio platform data. This patch removes bus_id from mdio platform data, The reason to remove bus_id is, stmmac mdio bus_id is always same as stmmac bus-id, so there is no point in passing this in different variable. Also stmmac ethernet driver connects to phy with bus_id passed its platform data. So, having single bus-id is much simpler. Signed-off-by: Srinivas Kandagatla Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index b69bdb1e08b6..a1547ea3920d 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -76,7 +76,6 @@ /* Platfrom data for platform device structure's platform_data field */ struct stmmac_mdio_bus_data { - int bus_id; int (*phy_reset)(void *priv); unsigned int phy_mask; int *irqs; -- cgit v1.2.3 From 1046716368979dee857a2b8a91c4a8833f21b9cb Mon Sep 17 00:00:00 2001 From: Jerry Chu Date: Fri, 31 Aug 2012 12:29:11 +0000 Subject: tcp: TCP Fast Open Server - header & support functions This patch adds all the necessary data structure and support functions to implement TFO server side. It also documents a number of flags for the sysctl_tcp_fastopen knob, and adds a few Linux extension MIBs. In addition, it includes the following: 1. a new TCP_FASTOPEN socket option an application must call to supply a max backlog allowed in order to enable TFO on its listener. 2. A number of key data structures: "fastopen_rsk" in tcp_sock - for a big socket to access its request_sock for retransmission and ack processing purpose. It is non-NULL iff 3WHS not completed. "fastopenq" in request_sock_queue - points to a per Fast Open listener data structure "fastopen_queue" to keep track of qlen (# of outstanding Fast Open requests) and max_qlen, among other things. "listener" in tcp_request_sock - to point to the original listener for book-keeping purpose, i.e., to maintain qlen against max_qlen as part of defense against IP spoofing attack. 3. various data structure and functions, many in tcp_fastopen.c, to support server side Fast Open cookie operations, including /proc/sys/net/ipv4/tcp_fastopen_key to allow manual rekeying. Signed-off-by: H.K. Jerry Chu Cc: Yuchung Cheng Cc: Neal Cardwell Cc: Eric Dumazet Cc: Tom Herbert Signed-off-by: David S. Miller --- include/linux/snmp.h | 4 ++++ include/linux/tcp.h | 45 ++++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 46 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/snmp.h b/include/linux/snmp.h index ad6e3a6bf9fb..fdfba235f9f1 100644 --- a/include/linux/snmp.h +++ b/include/linux/snmp.h @@ -241,6 +241,10 @@ enum LINUX_MIB_TCPCHALLENGEACK, /* TCPChallengeACK */ LINUX_MIB_TCPSYNCHALLENGE, /* TCPSYNChallenge */ LINUX_MIB_TCPFASTOPENACTIVE, /* TCPFastOpenActive */ + LINUX_MIB_TCPFASTOPENPASSIVE, /* TCPFastOpenPassive*/ + LINUX_MIB_TCPFASTOPENPASSIVEFAIL, /* TCPFastOpenPassiveFail */ + LINUX_MIB_TCPFASTOPENLISTENOVERFLOW, /* TCPFastOpenListenOverflow */ + LINUX_MIB_TCPFASTOPENCOOKIEREQD, /* TCPFastOpenCookieReqd */ __LINUX_MIB_MAX }; diff --git a/include/linux/tcp.h b/include/linux/tcp.h index eb125a4c30b3..ae46df590629 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -110,6 +110,7 @@ enum { #define TCP_REPAIR_QUEUE 20 #define TCP_QUEUE_SEQ 21 #define TCP_REPAIR_OPTIONS 22 +#define TCP_FASTOPEN 23 /* Enable FastOpen on listeners */ struct tcp_repair_opt { __u32 opt_code; @@ -246,6 +247,7 @@ static inline unsigned int tcp_optlen(const struct sk_buff *skb) /* TCP Fast Open */ #define TCP_FASTOPEN_COOKIE_MIN 4 /* Min Fast Open Cookie size in bytes */ #define TCP_FASTOPEN_COOKIE_MAX 16 /* Max Fast Open Cookie size in bytes */ +#define TCP_FASTOPEN_COOKIE_SIZE 8 /* the size employed by this impl. */ /* TCP Fast Open Cookie as stored in memory */ struct tcp_fastopen_cookie { @@ -312,9 +314,14 @@ struct tcp_request_sock { /* Only used by TCP MD5 Signature so far. */ const struct tcp_request_sock_ops *af_specific; #endif + struct sock *listener; /* needed for TFO */ u32 rcv_isn; u32 snt_isn; u32 snt_synack; /* synack sent time */ + u32 rcv_nxt; /* the ack # by SYNACK. For + * FastOpen it's the seq# + * after data-in-SYN. + */ }; static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) @@ -505,14 +512,18 @@ struct tcp_sock { struct tcp_md5sig_info __rcu *md5sig_info; #endif -/* TCP fastopen related information */ - struct tcp_fastopen_request *fastopen_req; - /* When the cookie options are generated and exchanged, then this * object holds a reference to them (cookie_values->kref). Also * contains related tcp_cookie_transactions fields. */ struct tcp_cookie_values *cookie_values; + +/* TCP fastopen related information */ + struct tcp_fastopen_request *fastopen_req; + /* fastopen_rsk points to request_sock that resulted in this big + * socket. Used to retransmit SYNACKs etc. + */ + struct request_sock *fastopen_rsk; }; enum tsq_flags { @@ -552,6 +563,34 @@ static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk) return (struct tcp_timewait_sock *)sk; } +static inline bool tcp_passive_fastopen(const struct sock *sk) +{ + return (sk->sk_state == TCP_SYN_RECV && + tcp_sk(sk)->fastopen_rsk != NULL); +} + +static inline bool fastopen_cookie_present(struct tcp_fastopen_cookie *foc) +{ + return foc->len != -1; +} + +static inline int fastopen_init_queue(struct sock *sk, int backlog) +{ + struct request_sock_queue *queue = + &inet_csk(sk)->icsk_accept_queue; + + if (queue->fastopenq == NULL) { + queue->fastopenq = kzalloc( + sizeof(struct fastopen_queue), + sk->sk_allocation); + if (queue->fastopenq == NULL) + return -ENOMEM; + spin_lock_init(&queue->fastopenq->lock); + } + queue->fastopenq->max_qlen = backlog; + return 0; +} + #endif /* __KERNEL__ */ #endif /* _LINUX_TCP_H */ -- cgit v1.2.3 From d23ff701643a4a725e2c7a8ba2d567d39daa29ea Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Tue, 4 Sep 2012 11:03:15 +0000 Subject: tcp: add generic netlink support for tcp_metrics Add support for genl "tcp_metrics". No locking is changed, only that now we can unlink and delete entries after grace period. We implement get/del for single entry and dump to support show/flush filtering in user space. Del without address attribute causes flush for all addresses, sadly under genl_mutex. v2: - remove rcu_assign_pointer as suggested by Eric Dumazet, it is not needed because there are no other writes under lock - move the flushing code in tcp_metrics_flush_all v3: - remove synchronize_rcu on flush as suggested by Eric Dumazet Signed-off-by: Julian Anastasov Signed-off-by: David S. Miller --- include/linux/Kbuild | 1 + include/linux/tcp_metrics.h | 54 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 55 insertions(+) create mode 100644 include/linux/tcp_metrics.h (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 1f2c1c787f17..90da0af28352 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -363,6 +363,7 @@ header-y += sysctl.h header-y += sysinfo.h header-y += taskstats.h header-y += tcp.h +header-y += tcp_metrics.h header-y += telephony.h header-y += termios.h header-y += time.h diff --git a/include/linux/tcp_metrics.h b/include/linux/tcp_metrics.h new file mode 100644 index 000000000000..cb5157b55f32 --- /dev/null +++ b/include/linux/tcp_metrics.h @@ -0,0 +1,54 @@ +/* tcp_metrics.h - TCP Metrics Interface */ + +#ifndef _LINUX_TCP_METRICS_H +#define _LINUX_TCP_METRICS_H + +#include + +/* NETLINK_GENERIC related info + */ +#define TCP_METRICS_GENL_NAME "tcp_metrics" +#define TCP_METRICS_GENL_VERSION 0x1 + +enum tcp_metric_index { + TCP_METRIC_RTT, + TCP_METRIC_RTTVAR, + TCP_METRIC_SSTHRESH, + TCP_METRIC_CWND, + TCP_METRIC_REORDERING, + + /* Always last. */ + __TCP_METRIC_MAX, +}; + +#define TCP_METRIC_MAX (__TCP_METRIC_MAX - 1) + +enum { + TCP_METRICS_ATTR_UNSPEC, + TCP_METRICS_ATTR_ADDR_IPV4, /* u32 */ + TCP_METRICS_ATTR_ADDR_IPV6, /* binary */ + TCP_METRICS_ATTR_AGE, /* msecs */ + TCP_METRICS_ATTR_TW_TSVAL, /* u32, raw, rcv tsval */ + TCP_METRICS_ATTR_TW_TS_STAMP, /* s32, sec age */ + TCP_METRICS_ATTR_VALS, /* nested +1, u32 */ + TCP_METRICS_ATTR_FOPEN_MSS, /* u16 */ + TCP_METRICS_ATTR_FOPEN_SYN_DROPS, /* u16, count of drops */ + TCP_METRICS_ATTR_FOPEN_SYN_DROP_TS, /* msecs age */ + TCP_METRICS_ATTR_FOPEN_COOKIE, /* binary */ + + __TCP_METRICS_ATTR_MAX, +}; + +#define TCP_METRICS_ATTR_MAX (__TCP_METRICS_ATTR_MAX - 1) + +enum { + TCP_METRICS_CMD_UNSPEC, + TCP_METRICS_CMD_GET, + TCP_METRICS_CMD_DEL, + + __TCP_METRICS_CMD_MAX, +}; + +#define TCP_METRICS_CMD_MAX (__TCP_METRICS_CMD_MAX - 1) + +#endif /* _LINUX_TCP_METRICS_H */ -- cgit v1.2.3 From 23d3b8bfb8eb20e7d96afa09991e6a5ed1c83164 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 5 Sep 2012 01:02:56 +0000 Subject: net: qdisc busylock needs lockdep annotations It seems we need to provide ability for stacked devices to use specific lock_class_key for sch->busylock We could instead default l2tpeth tx_queue_len to 0 (no qdisc), but a user might use a qdisc anyway. (So same fixes are probably needed on non LLTX stacked drivers) Noticed while stressing L2TPV3 setup : ====================================================== [ INFO: possible circular locking dependency detected ] 3.6.0-rc3+ #788 Not tainted ------------------------------------------------------- netperf/4660 is trying to acquire lock: (l2tpsock){+.-...}, at: [] l2tp_xmit_skb+0x172/0xa50 [l2tp_core] but task is already holding lock: (&(&sch->busylock)->rlock){+.-...}, at: [] dev_queue_xmit+0xd75/0xe00 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&(&sch->busylock)->rlock){+.-...}: [] lock_acquire+0x90/0x200 [] _raw_spin_lock_irqsave+0x4c/0x60 [] __wake_up+0x32/0x70 [] tty_wakeup+0x3e/0x80 [] pty_write+0x73/0x80 [] tty_put_char+0x3c/0x40 [] process_echoes+0x142/0x330 [] n_tty_receive_buf+0x8fb/0x1230 [] flush_to_ldisc+0x142/0x1c0 [] process_one_work+0x198/0x760 [] worker_thread+0x186/0x4b0 [] kthread+0x93/0xa0 [] kernel_thread_helper+0x4/0x10 -> #0 (l2tpsock){+.-...}: [] __lock_acquire+0x1628/0x1b10 [] lock_acquire+0x90/0x200 [] _raw_spin_lock+0x41/0x50 [] l2tp_xmit_skb+0x172/0xa50 [l2tp_core] [] l2tp_eth_dev_xmit+0x32/0x60 [l2tp_eth] [] dev_hard_start_xmit+0x502/0xa70 [] sch_direct_xmit+0xfe/0x290 [] dev_queue_xmit+0x1e5/0xe00 [] ip_finish_output+0x3d0/0x890 [] ip_output+0x59/0xf0 [] ip_local_out+0x2d/0xa0 [] ip_queue_xmit+0x1c3/0x680 [] tcp_transmit_skb+0x402/0xa60 [] tcp_write_xmit+0x1f4/0xa30 [] tcp_push_one+0x30/0x40 [] tcp_sendmsg+0xe82/0x1040 [] inet_sendmsg+0x125/0x230 [] sock_sendmsg+0xdc/0xf0 [] sys_sendto+0xfe/0x130 [] system_call_fastpath+0x16/0x1b Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&(&sch->busylock)->rlock); lock(l2tpsock); lock(&(&sch->busylock)->rlock); lock(l2tpsock); *** DEADLOCK *** 5 locks held by netperf/4660: #0: (sk_lock-AF_INET){+.+.+.}, at: [] tcp_sendmsg+0x2c/0x1040 #1: (rcu_read_lock){.+.+..}, at: [] ip_queue_xmit+0x0/0x680 #2: (rcu_read_lock_bh){.+....}, at: [] ip_finish_output+0x135/0x890 #3: (rcu_read_lock_bh){.+....}, at: [] dev_queue_xmit+0x0/0xe00 #4: (&(&sch->busylock)->rlock){+.-...}, at: [] dev_queue_xmit+0xd75/0xe00 stack backtrace: Pid: 4660, comm: netperf Not tainted 3.6.0-rc3+ #788 Call Trace: [] print_circular_bug+0x1fb/0x20c [] __lock_acquire+0x1628/0x1b10 [] ? check_usage+0x9b/0x4d0 [] ? __lock_acquire+0x2e4/0x1b10 [] lock_acquire+0x90/0x200 [] ? l2tp_xmit_skb+0x172/0xa50 [l2tp_core] [] _raw_spin_lock+0x41/0x50 [] ? l2tp_xmit_skb+0x172/0xa50 [l2tp_core] [] l2tp_xmit_skb+0x172/0xa50 [l2tp_core] [] l2tp_eth_dev_xmit+0x32/0x60 [l2tp_eth] [] dev_hard_start_xmit+0x502/0xa70 [] ? dev_hard_start_xmit+0x5e/0xa70 [] ? dev_queue_xmit+0x141/0xe00 [] sch_direct_xmit+0xfe/0x290 [] dev_queue_xmit+0x1e5/0xe00 [] ? dev_hard_start_xmit+0xa70/0xa70 [] ip_finish_output+0x3d0/0x890 [] ? ip_finish_output+0x135/0x890 [] ip_output+0x59/0xf0 [] ip_local_out+0x2d/0xa0 [] ip_queue_xmit+0x1c3/0x680 [] ? ip_local_out+0xa0/0xa0 [] tcp_transmit_skb+0x402/0xa60 [] ? tcp_md5_do_lookup+0x18e/0x1a0 [] tcp_write_xmit+0x1f4/0xa30 [] tcp_push_one+0x30/0x40 [] tcp_sendmsg+0xe82/0x1040 [] inet_sendmsg+0x125/0x230 [] ? inet_create+0x6b0/0x6b0 [] ? sock_update_classid+0xc2/0x3b0 [] ? sock_update_classid+0x130/0x3b0 [] sock_sendmsg+0xdc/0xf0 [] ? fget_light+0x3f9/0x4f0 [] sys_sendto+0xfe/0x130 [] ? trace_hardirqs_on+0xd/0x10 [] ? _raw_spin_unlock_irq+0x30/0x50 [] ? finish_task_switch+0x83/0xf0 [] ? finish_task_switch+0x46/0xf0 [] ? sysret_check+0x1b/0x56 [] system_call_fastpath+0x16/0x1b Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ccac82e61604..ae3153c0db0a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1322,6 +1322,8 @@ struct net_device { /* phy device may attach itself for hardware timestamping */ struct phy_device *phydev; + struct lock_class_key *qdisc_tx_busylock; + /* group the device belongs to */ int group; -- cgit v1.2.3 From ad0ed62f340a03acca5ae3e7430a08bf289aaffe Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 24 Jul 2012 17:38:43 +0200 Subject: wireless: remove obsolete chan no/center freq conversion functions There are a number of functions that shouldn't really be used when modern functions that take the band are available in cfg80211. Remove these, but for now keep * ieee80211_freq_to_dsss_chan and * ieee80211_dsss_chan_to_freq as they're used in older drivers. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 80 ----------------------------------------------- 1 file changed, 80 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index e02fc682bb68..2385119f8bb0 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1934,36 +1934,6 @@ static inline bool ieee80211_is_public_action(struct ieee80211_hdr *hdr, return mgmt->u.action.category == WLAN_CATEGORY_PUBLIC; } -/** - * ieee80211_fhss_chan_to_freq - get channel frequency - * @channel: the FHSS channel - * - * Convert IEEE802.11 FHSS channel to frequency (MHz) - * Ref IEEE 802.11-2007 section 14.6 - */ -static inline int ieee80211_fhss_chan_to_freq(int channel) -{ - if ((channel > 1) && (channel < 96)) - return channel + 2400; - else - return -1; -} - -/** - * ieee80211_freq_to_fhss_chan - get channel - * @freq: the channels frequency - * - * Convert frequency (MHz) to IEEE802.11 FHSS channel - * Ref IEEE 802.11-2007 section 14.6 - */ -static inline int ieee80211_freq_to_fhss_chan(int freq) -{ - if ((freq > 2401) && (freq < 2496)) - return freq - 2400; - else - return -1; -} - /** * ieee80211_dsss_chan_to_freq - get channel center frequency * @channel: the DSSS channel @@ -2000,56 +1970,6 @@ static inline int ieee80211_freq_to_dsss_chan(int freq) return -1; } -/* Convert IEEE802.11 HR DSSS channel to frequency (MHz) and back - * Ref IEEE 802.11-2007 section 18.4.6.2 - * - * The channels and frequencies are the same as those defined for DSSS - */ -#define ieee80211_hr_chan_to_freq(chan) ieee80211_dsss_chan_to_freq(chan) -#define ieee80211_freq_to_hr_chan(freq) ieee80211_freq_to_dsss_chan(freq) - -/* Convert IEEE802.11 ERP channel to frequency (MHz) and back - * Ref IEEE 802.11-2007 section 19.4.2 - */ -#define ieee80211_erp_chan_to_freq(chan) ieee80211_hr_chan_to_freq(chan) -#define ieee80211_freq_to_erp_chan(freq) ieee80211_freq_to_hr_chan(freq) - -/** - * ieee80211_ofdm_chan_to_freq - get channel center frequency - * @s_freq: starting frequency == (dotChannelStartingFactor/2) MHz - * @channel: the OFDM channel - * - * Convert IEEE802.11 OFDM channel to center frequency (MHz) - * Ref IEEE 802.11-2007 section 17.3.8.3.2 - */ -static inline int ieee80211_ofdm_chan_to_freq(int s_freq, int channel) -{ - if ((channel > 0) && (channel <= 200) && - (s_freq >= 4000)) - return s_freq + (channel * 5); - else - return -1; -} - -/** - * ieee80211_freq_to_ofdm_channel - get channel - * @s_freq: starting frequency == (dotChannelStartingFactor/2) MHz - * @freq: the frequency - * - * Convert frequency (MHz) to IEEE802.11 OFDM channel - * Ref IEEE 802.11-2007 section 17.3.8.3.2 - * - * This routine selects the channel with the closest center frequency. - */ -static inline int ieee80211_freq_to_ofdm_chan(int s_freq, int freq) -{ - if ((freq > (s_freq + 2)) && (freq <= (s_freq + 1202)) && - (s_freq >= 4000)) - return (freq + 2 - s_freq) / 5; - else - return -1; -} - /** * ieee80211_tu_to_usec - convert time units (TU) to microseconds * @tu: the TUs -- cgit v1.2.3 From dbe9a4173ea53b72b2c35d19f676a85b69f1c9fe Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 6 Sep 2012 18:20:01 +0000 Subject: scm: Don't use struct ucred in NETLINK_CB and struct scm_cookie. Passing uids and gids on NETLINK_CB from a process in one user namespace to a process in another user namespace can result in the wrong uid or gid being presented to userspace. Avoid that problem by passing kuids and kgids instead. - define struct scm_creds for use in scm_cookie and netlink_skb_parms that holds uid and gid information in kuid_t and kgid_t. - Modify scm_set_cred to fill out scm_creds by heand instead of using cred_to_ucred to fill out struct ucred. This conversion ensures userspace does not get incorrect uid or gid values to look at. - Modify scm_recv to convert from struct scm_creds to struct ucred before copying credential values to userspace. - Modify __scm_send to populate struct scm_creds on in the scm_cookie, instead of just copying struct ucred from userspace. - Modify netlink_sendmsg to copy scm_creds instead of struct ucred into the NETLINK_CB. Signed-off-by: "Eric W. Biederman" 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 c9fdde2bc73f..df73cf4b0290 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -153,6 +153,7 @@ struct nlattr { #include #include +#include struct net; @@ -162,7 +163,7 @@ static inline struct nlmsghdr *nlmsg_hdr(const struct sk_buff *skb) } struct netlink_skb_parms { - struct ucred creds; /* Skb credentials */ + struct scm_creds creds; /* Skb credentials */ __u32 pid; __u32 dst_group; struct sock *ssk; -- cgit v1.2.3 From 220a60a425146b0e37998cc0b3082f0541aad866 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Mon, 3 Sep 2012 11:34:58 +0100 Subject: pps/ptp: Allow PHC devices to adjust PPS events for known delay Initial version by Stuart Hodgson Some PHC device drivers may deliver PPS events with a significant and variable delay, but still be able to measure precisely what that delay is. Add a pps_sub_ts() function for subtracting a delay from the timestamp(s) in a PPS event, and a PTP event type (PTP_CLOCK_PPSUSR) for which the caller provides a complete PPS event. Signed-off-by: Ben Hutchings --- include/linux/pps_kernel.h | 9 +++++++++ include/linux/ptp_clock_kernel.h | 10 ++++++++-- 2 files changed, 17 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pps_kernel.h b/include/linux/pps_kernel.h index 94048547f29a..0cc45ae1afd5 100644 --- a/include/linux/pps_kernel.h +++ b/include/linux/pps_kernel.h @@ -116,5 +116,14 @@ static inline void pps_get_ts(struct pps_event_time *ts) #endif /* CONFIG_NTP_PPS */ +/* Subtract known time delay from PPS event time(s) */ +static inline void pps_sub_ts(struct pps_event_time *ts, struct timespec delta) +{ + ts->ts_real = timespec_sub(ts->ts_real, delta); +#ifdef CONFIG_NTP_PPS + ts->ts_raw = timespec_sub(ts->ts_raw, delta); +#endif +} + #endif /* LINUX_PPS_KERNEL_H */ diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 945704c2ed65..a644b29f1161 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -21,6 +21,7 @@ #ifndef _PTP_CLOCK_KERNEL_H_ #define _PTP_CLOCK_KERNEL_H_ +#include #include @@ -110,6 +111,7 @@ enum ptp_clock_events { PTP_CLOCK_ALARM, PTP_CLOCK_EXTTS, PTP_CLOCK_PPS, + PTP_CLOCK_PPSUSR, }; /** @@ -117,13 +119,17 @@ enum ptp_clock_events { * * @type: One of the ptp_clock_events enumeration values. * @index: Identifies the source of the event. - * @timestamp: When the event occured. + * @timestamp: When the event occurred (%PTP_CLOCK_EXTTS only). + * @pps_times: When the event occurred (%PTP_CLOCK_PPSUSR only). */ struct ptp_clock_event { int type; int index; - u64 timestamp; + union { + u64 timestamp; + struct pps_event_time pps_times; + }; }; /** -- cgit v1.2.3 From 9785e10aedfa0fad5c1aac709dce5ada1b123783 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sat, 8 Sep 2012 02:53:53 +0000 Subject: netlink: kill netlink_set_nonroot Replace netlink_set_nonroot by one new field `flags' in struct netlink_kernel_cfg that is passed to netlink_kernel_create. This patch also renames NL_NONROOT_* to NL_CFG_F_NONROOT_* since now the flags field in nl_table is generic (so we can add more flags if needed in the future). Also adjust all callers in the net-next tree to use these flags instead of netlink_set_nonroot. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/linux/netlink.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index df73cf4b0290..8719a4e235a5 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -176,12 +176,16 @@ struct netlink_skb_parms { extern void netlink_table_grab(void); extern void netlink_table_ungrab(void); +#define NL_CFG_F_NONROOT_RECV (1 << 0) +#define NL_CFG_F_NONROOT_SEND (1 << 1) + /* optional Netlink kernel configuration parameters */ struct netlink_kernel_cfg { unsigned int groups; void (*input)(struct sk_buff *skb); struct mutex *cb_mutex; void (*bind)(int group); + unsigned int flags; }; extern struct sock *netlink_kernel_create(struct net *net, int unit, @@ -260,11 +264,6 @@ extern int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, const struct nlmsghdr *nlh, struct netlink_dump_control *control); - -#define NL_NONROOT_RECV 0x1 -#define NL_NONROOT_SEND 0x2 -extern void netlink_set_nonroot(int protocol, unsigned flag); - #endif /* __KERNEL__ */ #endif /* __LINUX_NETLINK_H */ -- cgit v1.2.3 From 9f00d9776bc5beb92e8bfc884a7e96ddc5589e2e Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sat, 8 Sep 2012 02:53:54 +0000 Subject: netlink: hide struct module parameter in netlink_kernel_create This patch defines netlink_kernel_create as a wrapper function of __netlink_kernel_create to hide the struct module *me parameter (which seems to be THIS_MODULE in all existing netlink subsystems). Suggested by David S. Miller. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/linux/netlink.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 8719a4e235a5..cd17dda5a987 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -153,6 +153,7 @@ struct nlattr { #include #include +#include #include struct net; @@ -188,9 +189,15 @@ struct netlink_kernel_cfg { unsigned int flags; }; -extern struct sock *netlink_kernel_create(struct net *net, int unit, - struct module *module, - struct netlink_kernel_cfg *cfg); +extern struct sock *__netlink_kernel_create(struct net *net, int unit, + struct module *module, + struct netlink_kernel_cfg *cfg); +static inline struct sock * +netlink_kernel_create(struct net *net, int unit, struct netlink_kernel_cfg *cfg) +{ + return __netlink_kernel_create(net, unit, THIS_MODULE, cfg); +} + extern void netlink_kernel_release(struct sock *sk); extern int __netlink_change_ngroups(struct sock *sk, unsigned int groups); extern int netlink_change_ngroups(struct sock *sk, unsigned int groups); -- cgit v1.2.3 From 15e473046cb6e5d18a4d0057e61d76315230382b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 7 Sep 2012 20:12:54 +0000 Subject: netlink: Rename pid to portid to avoid confusion It is a frequent mistake to confuse the netlink port identifier with a process identifier. Try to reduce this confusion by renaming fields that hold port identifiers portid instead of pid. I have carefully avoided changing the structures exported to userspace to avoid changing the userspace API. I have successfully built an allyesconfig kernel with this change. Signed-off-by: "Eric W. Biederman" Acked-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/netlink.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index cd17dda5a987..73ade5fbc856 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -165,7 +165,7 @@ static inline struct nlmsghdr *nlmsg_hdr(const struct sk_buff *skb) struct netlink_skb_parms { struct scm_creds creds; /* Skb credentials */ - __u32 pid; + __u32 portid; __u32 dst_group; struct sock *ssk; }; @@ -205,14 +205,14 @@ extern void __netlink_clear_multicast_users(struct sock *sk, unsigned int group) extern void netlink_clear_multicast_users(struct sock *sk, unsigned int group); extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err); extern int netlink_has_listeners(struct sock *sk, unsigned int group); -extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 pid, int nonblock); -extern int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 pid, +extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock); +extern int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid, __u32 group, gfp_t allocation); extern int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, - __u32 pid, __u32 group, gfp_t allocation, + __u32 portid, __u32 group, gfp_t allocation, int (*filter)(struct sock *dsk, struct sk_buff *skb, void *data), void *filter_data); -extern int netlink_set_err(struct sock *ssk, __u32 pid, __u32 group, int code); +extern int netlink_set_err(struct sock *ssk, __u32 portid, __u32 group, int code); extern int netlink_register_notifier(struct notifier_block *nb); extern int netlink_unregister_notifier(struct notifier_block *nb); @@ -253,12 +253,12 @@ struct netlink_callback { struct netlink_notify { struct net *net; - int pid; + int portid; int protocol; }; struct nlmsghdr * -__nlmsg_put(struct sk_buff *skb, u32 pid, u32 seq, int type, int len, int flags); +__nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int flags); struct netlink_dump_control { int (*dump)(struct sk_buff *skb, struct netlink_callback *); -- cgit v1.2.3 From b6069a95706ca5738be3f5d90fd286cbd13ac695 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 7 Sep 2012 22:03:35 +0000 Subject: filter: add MOD operation Add a new ALU opcode, to compute a modulus. Commit ffe06c17afbbb used an ancillary to implement XOR_X, but here we reserve one of the available ALU opcode to implement both MOD_X and MOD_K Signed-off-by: Eric Dumazet Suggested-by: George Bakos Cc: Jay Schulist Cc: Jiri Pirko Cc: Andi Kleen Signed-off-by: David S. Miller --- include/linux/filter.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 82b01357af8b..3cf5fd561d86 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -74,6 +74,8 @@ struct sock_fprog { /* Required for SO_ATTACH_FILTER. */ #define BPF_LSH 0x60 #define BPF_RSH 0x70 #define BPF_NEG 0x80 +#define BPF_MOD 0x90 + #define BPF_JA 0x00 #define BPF_JEQ 0x10 #define BPF_JGT 0x20 @@ -196,6 +198,8 @@ enum { 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, -- cgit v1.2.3 From 6d57e9078e880a3dd232d579f42ac437a8f1ef7b Mon Sep 17 00:00:00 2001 From: Duan Jiong Date: Sat, 8 Sep 2012 16:32:28 +0000 Subject: etherdevice: introduce help function eth_zero_addr() a lot of code has either the memset or an inefficient copy from a static array that contains the all-zeros Ethernet address. Introduce help function eth_zero_addr() to fill an address with all zeros, making the code clearer and allowing us to get rid of some constant arrays. Signed-off-by: Duan Jiong Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index d426336d92d9..b006ba0a9f42 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -150,6 +150,17 @@ static inline void eth_broadcast_addr(u8 *addr) memset(addr, 0xff, ETH_ALEN); } +/** + * eth_zero_addr - Assign zero address + * @addr: Pointer to a six-byte array containing the Ethernet address + * + * Assign the zero address to the given address array. + */ +static inline void eth_zero_addr(u8 *addr) +{ + memset(addr, 0x00, ETH_ALEN); +} + /** * eth_hw_addr_random - Generate software assigned random Ethernet and * set device flag -- cgit v1.2.3 From ed44a951c72ab409f932b1c15914488308e86da2 Mon Sep 17 00:00:00 2001 From: Pandiyarajan Pitchaimuthu Date: Tue, 18 Sep 2012 16:50:49 +0530 Subject: cfg80211/nl80211: Notify connection request failure in AP mode In AP mode, when a station requests connection to an AP and if the request is failed for particular reason, userspace is notified about the failure through NL80211_CMD_CONN_FAILED command. Reason for the failure is sent through the attribute NL80211_ATTR_CONN_FAILED_REASON. Signed-off-by: Pandiyarajan Pitchaimuthu Signed-off-by: Johannes Berg --- include/linux/nl80211.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 458416279347..7df9b500c804 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -573,6 +573,11 @@ * @NL80211_CMD_STOP_P2P_DEVICE: Stop the given P2P Device, identified by * its %NL80211_ATTR_WDEV identifier. * + * @NL80211_CMD_CONN_FAILED: connection request to an AP failed; used to + * notify userspace that AP has rejected the connection request from a + * station, due to particular reason. %NL80211_ATTR_CONN_FAILED_REASON + * is used for this. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -719,6 +724,8 @@ enum nl80211_commands { NL80211_CMD_START_P2P_DEVICE, NL80211_CMD_STOP_P2P_DEVICE, + NL80211_CMD_CONN_FAILED, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -1262,6 +1269,10 @@ enum nl80211_commands { * was used to provide the hint. For the different types of * allowed user regulatory hints see nl80211_user_reg_hint_type. * + * @NL80211_ATTR_CONN_FAILED_REASON: The reason for which AP has rejected + * the connection request from a station. nl80211_connect_failed_reason + * enum has different reasons of connection failure. + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -1517,6 +1528,8 @@ enum nl80211_attrs { NL80211_ATTR_USER_REG_HINT_TYPE, + NL80211_ATTR_CONN_FAILED_REASON, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -3045,4 +3058,15 @@ enum nl80211_probe_resp_offload_support_attr { NL80211_PROBE_RESP_OFFLOAD_SUPPORT_80211U = 1<<3, }; +/** + * enum nl80211_connect_failed_reason - connection request failed reasons + * @NL80211_CONN_FAIL_MAX_CLIENTS: Maximum number of clients that can be + * handled by the AP is reached. + * @NL80211_CONN_FAIL_BLOCKED_CLIENT: Client's MAC is in the AP's blocklist. + */ +enum nl80211_connect_failed_reason { + NL80211_CONN_FAIL_MAX_CLIENTS, + NL80211_CONN_FAIL_BLOCKED_CLIENT, +}; + #endif /* __LINUX_NL80211_H */ -- cgit v1.2.3 From 6b6e27255f29a6191ef8ad96bfcc392ab2ef6c71 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 17 Sep 2012 10:03:26 +0000 Subject: netdev: make address const in device address management The internal functions for add/deleting addresses don't change their argument. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/netdevice.h | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ae3153c0db0a..82264e717e53 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -907,10 +907,10 @@ struct netdev_fcoe_hbainfo { * Must return >0 or -errno if it changed dev->features itself. * * int (*ndo_fdb_add)(struct ndmsg *ndm, struct net_device *dev, - * unsigned char *addr, u16 flags) + * const unsigned char *addr, u16 flags) * Adds an FDB entry to dev for addr. * int (*ndo_fdb_del)(struct ndmsg *ndm, struct net_device *dev, - * unsigned char *addr) + * const unsigned char *addr) * Deletes the FDB entry from dev coresponding to addr. * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, * struct net_device *dev, int idx) @@ -1017,11 +1017,11 @@ struct net_device_ops { int (*ndo_fdb_add)(struct ndmsg *ndm, struct net_device *dev, - unsigned char *addr, + const unsigned char *addr, u16 flags); int (*ndo_fdb_del)(struct ndmsg *ndm, struct net_device *dev, - unsigned char *addr); + const unsigned char *addr); int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, @@ -2561,9 +2561,9 @@ extern void __hw_addr_flush(struct netdev_hw_addr_list *list); extern void __hw_addr_init(struct netdev_hw_addr_list *list); /* Functions used for device addresses handling */ -extern int dev_addr_add(struct net_device *dev, unsigned char *addr, +extern int dev_addr_add(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); -extern int dev_addr_del(struct net_device *dev, unsigned char *addr, +extern int dev_addr_del(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); extern int dev_addr_add_multiple(struct net_device *to_dev, struct net_device *from_dev, @@ -2575,20 +2575,20 @@ extern void dev_addr_flush(struct net_device *dev); extern int dev_addr_init(struct net_device *dev); /* Functions used for unicast addresses handling */ -extern int dev_uc_add(struct net_device *dev, unsigned char *addr); -extern int dev_uc_add_excl(struct net_device *dev, unsigned char *addr); -extern int dev_uc_del(struct net_device *dev, unsigned char *addr); +extern int dev_uc_add(struct net_device *dev, const unsigned char *addr); +extern int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr); +extern int dev_uc_del(struct net_device *dev, const unsigned char *addr); extern int dev_uc_sync(struct net_device *to, struct net_device *from); extern void dev_uc_unsync(struct net_device *to, struct net_device *from); extern void dev_uc_flush(struct net_device *dev); extern void dev_uc_init(struct net_device *dev); /* Functions used for multicast addresses handling */ -extern int dev_mc_add(struct net_device *dev, unsigned char *addr); -extern int dev_mc_add_global(struct net_device *dev, unsigned char *addr); -extern int dev_mc_add_excl(struct net_device *dev, unsigned char *addr); -extern int dev_mc_del(struct net_device *dev, unsigned char *addr); -extern int dev_mc_del_global(struct net_device *dev, unsigned char *addr); +extern int dev_mc_add(struct net_device *dev, const unsigned char *addr); +extern int dev_mc_add_global(struct net_device *dev, const unsigned char *addr); +extern int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr); +extern int dev_mc_del(struct net_device *dev, const unsigned char *addr); +extern int dev_mc_del_global(struct net_device *dev, const unsigned char *addr); extern int dev_mc_sync(struct net_device *to, struct net_device *from); extern void dev_mc_unsync(struct net_device *to, struct net_device *from); extern void dev_mc_flush(struct net_device *dev); -- cgit v1.2.3 From 8c4c49df5cfeb8d56e5b85a430c8cbcb86c2ac37 Mon Sep 17 00:00:00 2001 From: Amerigo Wang Date: Mon, 17 Sep 2012 20:16:31 +0000 Subject: netpoll: call ->ndo_select_queue() in tx path In netpoll tx path, we miss the chance of calling ->ndo_select_queue(), thus could cause problems when bonding is involved. This patch makes dev_pick_tx() extern (and rename it to netdev_pick_tx()) to let netpoll call it in netpoll_send_skb_on_dev(). Reported-by: Sylvain Munaut Cc: "David S. Miller" Cc: Eric Dumazet Signed-off-by: Cong Wang Tested-by: Sylvain Munaut Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 82264e717e53..6c131f055ab0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1403,6 +1403,9 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, f(dev, &dev->_tx[i], arg); } +extern struct netdev_queue *netdev_pick_tx(struct net_device *dev, + struct sk_buff *skb); + /* * Net namespace inlines */ -- cgit v1.2.3 From 9baa0b0364103dd726384c71db30b74044754743 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Thu, 13 Sep 2012 05:56:36 +0000 Subject: IB/ipoib: Add rtnl_link_ops support Add rtnl_link_ops to IPoIB, with the first usage being child device create/delete through them. Childs devices are now either legacy ones, created/deleted through the ipoib sysfs entries, or RTNL ones. Adding support for RTNL childs involved refactoring of ipoib_vlan_add which is now used by both the sysfs and the link_ops code. Also, added ndo_uninit entry to support calling unregister_netdevice_queue from the rtnl dellink entry. This required removal of calls to ipoib_dev_cleanup from the driver in flows which use unregister_netdevice, since the networking core will invoke ipoib_uninit which does exactly that. Signed-off-by: Erez Shitrit Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/if_link.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_link.h b/include/linux/if_link.h index ac173bd2ab65..24c0dd09af54 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -398,4 +398,15 @@ struct ifla_port_vsi { __u8 pad[3]; }; + +/* IPoIB section */ + +enum { + IFLA_IPOIB_UNSPEC, + IFLA_IPOIB_PKEY, + __IFLA_IPOIB_MAX +}; + +#define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1) + #endif /* _LINUX_IF_LINK_H */ -- cgit v1.2.3 From bb68b64724a4fd6b93d83b39aeffa4aadb2562fc Mon Sep 17 00:00:00 2001 From: Christoph Paasch Date: Tue, 18 Sep 2012 14:19:23 +0000 Subject: ipv4: Don't add TCP-code in inet_sock_destruct Signed-off-by: Christoph Paasch Acked-by: H.K. Jerry Chu Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index ae46df590629..67c789ae719c 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -574,6 +574,8 @@ 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) { struct request_sock_queue *queue = @@ -585,6 +587,8 @@ static inline int fastopen_init_queue(struct sock *sk, int backlog) sk->sk_allocation); if (queue->fastopenq == NULL) return -ENOMEM; + + sk->sk_destruct = tcp_sock_destruct; spin_lock_init(&queue->fastopenq->lock); } queue->fastopenq->max_qlen = backlog; -- cgit v1.2.3 From abb17e6c0c7b27693201dc85f75dbb184279fd10 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 21 Sep 2012 09:35:38 +0000 Subject: netlink: use instead of Since (9f00d97 netlink: hide struct module parameter in netlink_kernel_create), linux/netlink.h includes linux/module.h because of the use of THIS_MODULE. Use linux/export.h instead, as suggested by Stephen Rothwell, which is significantly smaller and defines THIS_MODULES. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/linux/netlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 73ade5fbc856..b3dc992fb25b 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -153,7 +153,7 @@ struct nlattr { #include #include -#include +#include #include struct net; -- cgit v1.2.3 From 1ef761582c074448bae5be97abde5934667e7710 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Sat, 22 Sep 2012 07:02:03 +0000 Subject: ptp: link the phc device to its parent device PTP Hardware Clock devices appear as class devices in sysfs. This patch changes the registration API to use the parent device, clarifying the clock's relationship to the underlying device. Signed-off-by: Richard Cochran Acked-by: Ben Hutchings Acked-by: Jeff Kirsher Signed-off-by: David S. Miller --- include/linux/ptp_clock_kernel.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index a644b29f1161..56c71b27112e 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -21,6 +21,7 @@ #ifndef _PTP_CLOCK_KERNEL_H_ #define _PTP_CLOCK_KERNEL_H_ +#include #include #include @@ -93,10 +94,12 @@ struct ptp_clock; /** * ptp_clock_register() - register a PTP hardware clock driver * - * @info: Structure describing the new clock. + * @info: Structure describing the new clock. + * @parent: Pointer to the parent device of the new clock. */ -extern struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info); +extern struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, + struct device *parent); /** * ptp_clock_unregister() - unregister a PTP hardware clock driver -- cgit v1.2.3 From de46584675fad02b7f8255f31be0ea1be5cd185b Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Sat, 22 Sep 2012 07:02:04 +0000 Subject: ptp: clarify the clock_name sysfs attribute There has been some confusion among PHC driver authors about the intended purpose of the clock_name attribute. This patch expands the documation in order to clarify how the clock_name field should be understood. Signed-off-by: Richard Cochran Signed-off-by: David S. Miller --- include/linux/ptp_clock_kernel.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 56c71b27112e..f2dc6d8fc680 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -42,7 +42,9 @@ struct ptp_clock_request { * struct ptp_clock_info - decribes a PTP hardware clock * * @owner: The clock driver should set to THIS_MODULE. - * @name: A short name to identify the clock. + * @name: A short "friendly name" to identify the clock and to + * help distinguish PHY based devices from MAC based ones. + * The string is not meant to be a unique id. * @max_adj: The maximum possible frequency adjustment, in parts per billon. * @n_alarm: The number of programmable alarms. * @n_ext_ts: The number of external time stamp channels. -- cgit v1.2.3 From 85f8c13e4122eb04fae9d3801eabaa45e3006a88 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Sat, 22 Sep 2012 22:42:08 +0200 Subject: netfilter: ipset: Rewrite cidr book keeping to handle /0 Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set_ahash.h | 104 ++++++++++++++------------- 1 file changed, 55 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h index b114d35aea5e..495acdf7251f 100644 --- a/include/linux/netfilter/ipset/ip_set_ahash.h +++ b/include/linux/netfilter/ipset/ip_set_ahash.h @@ -137,50 +137,59 @@ htable_bits(u32 hashsize) #endif #define SET_HOST_MASK(family) (family == AF_INET ? 32 : 128) +#ifdef IP_SET_HASH_WITH_MULTI +#define NETS_LENGTH(family) (SET_HOST_MASK(family) + 1) +#else +#define NETS_LENGTH(family) SET_HOST_MASK(family) +#endif /* Network cidr size book keeping when the hash stores different * sized networks */ static void -add_cidr(struct ip_set_hash *h, u8 cidr, u8 host_mask) +add_cidr(struct ip_set_hash *h, u8 cidr, u8 nets_length) { - u8 i; - - ++h->nets[cidr-1].nets; - - pr_debug("add_cidr added %u: %u\n", cidr, h->nets[cidr-1].nets); + int i, j; - if (h->nets[cidr-1].nets > 1) - return; - - /* New cidr size */ - for (i = 0; i < host_mask && h->nets[i].cidr; i++) { - /* Add in increasing prefix order, so larger cidr first */ - if (h->nets[i].cidr < cidr) - swap(h->nets[i].cidr, cidr); + /* Add in increasing prefix order, so larger cidr first */ + for (i = 0, j = -1; i < nets_length && h->nets[i].nets; i++) { + if (j != -1) + continue; + else if (h->nets[i].cidr < cidr) + j = i; + else if (h->nets[i].cidr == cidr) { + h->nets[i].nets++; + return; + } + } + if (j != -1) { + for (; i > j; i--) { + h->nets[i].cidr = h->nets[i - 1].cidr; + h->nets[i].nets = h->nets[i - 1].nets; + } } - if (i < host_mask) - h->nets[i].cidr = cidr; + h->nets[i].cidr = cidr; + h->nets[i].nets = 1; } static void -del_cidr(struct ip_set_hash *h, u8 cidr, u8 host_mask) +del_cidr(struct ip_set_hash *h, u8 cidr, u8 nets_length) { - u8 i; - - --h->nets[cidr-1].nets; + u8 i, j; - pr_debug("del_cidr deleted %u: %u\n", cidr, h->nets[cidr-1].nets); + for (i = 0; i < nets_length - 1 && h->nets[i].cidr != cidr; i++) + ; + h->nets[i].nets--; - if (h->nets[cidr-1].nets != 0) + if (h->nets[i].nets != 0) return; - /* All entries with this cidr size deleted, so cleanup h->cidr[] */ - for (i = 0; i < host_mask - 1 && h->nets[i].cidr; i++) { - if (h->nets[i].cidr == cidr) - h->nets[i].cidr = cidr = h->nets[i+1].cidr; + for (j = i; j < nets_length - 1 && h->nets[j].nets; j++) { + h->nets[j].cidr = h->nets[j + 1].cidr; + h->nets[j].nets = h->nets[j + 1].nets; } - h->nets[i - 1].cidr = 0; } +#else +#define NETS_LENGTH(family) 0 #endif /* Destroy the hashtable part of the set */ @@ -202,14 +211,14 @@ ahash_destroy(struct htable *t) /* Calculate the actual memory size of the set data */ static size_t -ahash_memsize(const struct ip_set_hash *h, size_t dsize, u8 host_mask) +ahash_memsize(const struct ip_set_hash *h, size_t dsize, u8 nets_length) { u32 i; struct htable *t = h->table; size_t memsize = sizeof(*h) + sizeof(*t) #ifdef IP_SET_HASH_WITH_NETS - + sizeof(struct ip_set_hash_nets) * host_mask + + sizeof(struct ip_set_hash_nets) * nets_length #endif + jhash_size(t->htable_bits) * sizeof(struct hbucket); @@ -238,7 +247,7 @@ ip_set_hash_flush(struct ip_set *set) } #ifdef IP_SET_HASH_WITH_NETS memset(h->nets, 0, sizeof(struct ip_set_hash_nets) - * SET_HOST_MASK(set->family)); + * NETS_LENGTH(set->family)); #endif h->elements = 0; } @@ -271,9 +280,6 @@ ip_set_hash_destroy(struct ip_set *set) (jhash2((u32 *)(data), HKEY_DATALEN/sizeof(u32), initval) \ & jhash_mask(htable_bits)) -#define CONCAT(a, b, c) a##b##c -#define TOKEN(a, b, c) CONCAT(a, b, c) - /* Type/family dependent function prototypes */ #define type_pf_data_equal TOKEN(TYPE, PF, _data_equal) @@ -478,7 +484,7 @@ type_pf_add(struct ip_set *set, void *value, u32 timeout, u32 flags) } #ifdef IP_SET_HASH_WITH_NETS - add_cidr(h, CIDR(d->cidr), HOST_MASK); + add_cidr(h, CIDR(d->cidr), NETS_LENGTH(set->family)); #endif h->elements++; out: @@ -513,7 +519,7 @@ type_pf_del(struct ip_set *set, void *value, u32 timeout, u32 flags) n->pos--; h->elements--; #ifdef IP_SET_HASH_WITH_NETS - del_cidr(h, CIDR(d->cidr), HOST_MASK); + del_cidr(h, CIDR(d->cidr), NETS_LENGTH(set->family)); #endif if (n->pos + AHASH_INIT_SIZE < n->size) { void *tmp = kzalloc((n->size - AHASH_INIT_SIZE) @@ -546,10 +552,10 @@ type_pf_test_cidrs(struct ip_set *set, struct type_pf_elem *d, u32 timeout) const struct type_pf_elem *data; int i, j = 0; u32 key, multi = 0; - u8 host_mask = SET_HOST_MASK(set->family); + u8 nets_length = NETS_LENGTH(set->family); pr_debug("test by nets\n"); - for (; j < host_mask && h->nets[j].cidr && !multi; j++) { + for (; j < nets_length && h->nets[j].nets && !multi; j++) { type_pf_data_netmask(d, h->nets[j].cidr); key = HKEY(d, h->initval, t->htable_bits); n = hbucket(t, key); @@ -604,7 +610,7 @@ type_pf_head(struct ip_set *set, struct sk_buff *skb) memsize = ahash_memsize(h, with_timeout(h->timeout) ? sizeof(struct type_pf_telem) : sizeof(struct type_pf_elem), - set->family == AF_INET ? 32 : 128); + NETS_LENGTH(set->family)); read_unlock_bh(&set->lock); nested = ipset_nest_start(skb, IPSET_ATTR_DATA); @@ -783,7 +789,7 @@ type_pf_elem_tadd(struct hbucket *n, const struct type_pf_elem *value, /* Delete expired elements from the hashtable */ static void -type_pf_expire(struct ip_set_hash *h) +type_pf_expire(struct ip_set_hash *h, u8 nets_length) { struct htable *t = h->table; struct hbucket *n; @@ -798,7 +804,7 @@ type_pf_expire(struct ip_set_hash *h) if (type_pf_data_expired(data)) { pr_debug("expired %u/%u\n", i, j); #ifdef IP_SET_HASH_WITH_NETS - del_cidr(h, CIDR(data->cidr), HOST_MASK); + del_cidr(h, CIDR(data->cidr), nets_length); #endif if (j != n->pos - 1) /* Not last one */ @@ -839,7 +845,7 @@ type_pf_tresize(struct ip_set *set, bool retried) if (!retried) { i = h->elements; write_lock_bh(&set->lock); - type_pf_expire(set->data); + type_pf_expire(set->data, NETS_LENGTH(set->family)); write_unlock_bh(&set->lock); if (h->elements < i) return 0; @@ -904,7 +910,7 @@ type_pf_tadd(struct ip_set *set, void *value, u32 timeout, u32 flags) if (h->elements >= h->maxelem) /* FIXME: when set is full, we slow down here */ - type_pf_expire(h); + type_pf_expire(h, NETS_LENGTH(set->family)); if (h->elements >= h->maxelem) { if (net_ratelimit()) pr_warning("Set %s is full, maxelem %u reached\n", @@ -933,8 +939,8 @@ type_pf_tadd(struct ip_set *set, void *value, u32 timeout, u32 flags) if (j != AHASH_MAX(h) + 1) { data = ahash_tdata(n, j); #ifdef IP_SET_HASH_WITH_NETS - del_cidr(h, CIDR(data->cidr), HOST_MASK); - add_cidr(h, CIDR(d->cidr), HOST_MASK); + del_cidr(h, CIDR(data->cidr), NETS_LENGTH(set->family)); + add_cidr(h, CIDR(d->cidr), NETS_LENGTH(set->family)); #endif type_pf_data_copy(data, d); type_pf_data_timeout_set(data, timeout); @@ -952,7 +958,7 @@ type_pf_tadd(struct ip_set *set, void *value, u32 timeout, u32 flags) } #ifdef IP_SET_HASH_WITH_NETS - add_cidr(h, CIDR(d->cidr), HOST_MASK); + add_cidr(h, CIDR(d->cidr), NETS_LENGTH(set->family)); #endif h->elements++; out: @@ -986,7 +992,7 @@ type_pf_tdel(struct ip_set *set, void *value, u32 timeout, u32 flags) n->pos--; h->elements--; #ifdef IP_SET_HASH_WITH_NETS - del_cidr(h, CIDR(d->cidr), HOST_MASK); + del_cidr(h, CIDR(d->cidr), NETS_LENGTH(set->family)); #endif if (n->pos + AHASH_INIT_SIZE < n->size) { void *tmp = kzalloc((n->size - AHASH_INIT_SIZE) @@ -1016,9 +1022,9 @@ type_pf_ttest_cidrs(struct ip_set *set, struct type_pf_elem *d, u32 timeout) struct hbucket *n; int i, j = 0; u32 key, multi = 0; - u8 host_mask = SET_HOST_MASK(set->family); + u8 nets_length = NETS_LENGTH(set->family); - for (; j < host_mask && h->nets[j].cidr && !multi; j++) { + for (; j < nets_length && h->nets[j].nets && !multi; j++) { type_pf_data_netmask(d, h->nets[j].cidr); key = HKEY(d, h->initval, t->htable_bits); n = hbucket(t, key); @@ -1147,7 +1153,7 @@ type_pf_gc(unsigned long ul_set) pr_debug("called\n"); write_lock_bh(&set->lock); - type_pf_expire(h); + type_pf_expire(h, NETS_LENGTH(set->family)); write_unlock_bh(&set->lock); h->gc.expires = jiffies + IPSET_GC_PERIOD(h->timeout) * HZ; -- cgit v1.2.3 From 10111a6ef373c377e87730749a0f68210c3fd062 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Fri, 21 Sep 2012 21:59:32 +0200 Subject: netfilter: ipset: Include supported revisions in module description Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 2edc64cab739..1d954c6c4e08 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -206,9 +206,15 @@ enum ip_set_kopt { #include #include #include +#include #include #include +#define _IP_SET_MODULE_DESC(a, b, c) \ + MODULE_DESCRIPTION(a " type of IP sets, revisions " b "-" c) +#define IP_SET_MODULE_DESC(a, b, c) \ + _IP_SET_MODULE_DESC(a, __stringify(b), __stringify(c)) + /* Set features */ enum ip_set_feature { IPSET_TYPE_IP_FLAG = 0, -- cgit v1.2.3 From 3ace95c0ac125a042cfb682d0a9bbdbf1e5a2c65 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Fri, 21 Sep 2012 22:01:45 +0200 Subject: netfilter: ipset: Coding style fixes Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set.h | 5 +++-- include/linux/netfilter/ipset/ip_set_ahash.h | 2 +- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 1d954c6c4e08..0c1e97b3acfb 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -255,7 +255,7 @@ struct ip_set_type_variant { * returns negative error code, * zero for no match/success to add/delete * positive for matching element */ - int (*kadt)(struct ip_set *set, const struct sk_buff * skb, + int (*kadt)(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, const struct ip_set_adt_opt *opt); @@ -430,7 +430,8 @@ static inline int nla_put_ipaddr4(struct sk_buff *skb, int type, __be32 ipaddr) return ret; } -static inline int nla_put_ipaddr6(struct sk_buff *skb, int type, const struct in6_addr *ipaddrptr) +static inline int nla_put_ipaddr6(struct sk_buff *skb, int type, + const struct in6_addr *ipaddrptr) { struct nlattr *__nested = ipset_nest_start(skb, type); int ret; diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h index 495acdf7251f..ef9acd3c8450 100644 --- a/include/linux/netfilter/ipset/ip_set_ahash.h +++ b/include/linux/netfilter/ipset/ip_set_ahash.h @@ -696,7 +696,7 @@ nla_put_failure: } static int -type_pf_kadt(struct ip_set *set, const struct sk_buff * skb, +type_pf_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, const struct ip_set_adt_opt *opt); static int -- cgit v1.2.3 From 3e0304a583d72c747caa8afac76b8d514aa293f5 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Fri, 21 Sep 2012 22:02:36 +0200 Subject: netfilter: ipset: Support to match elements marked with "nomatch" Exceptions can now be matched and we can branch according to the possible cases: a. match in the set if the element is not flagged as "nomatch" b. match in the set if the element is flagged with "nomatch" c. no match i.e. iptables ... -m set --match-set ... -j ... iptables ... -m set --match-set ... --nomatch-entries -j ... ... Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 0c1e97b3acfb..528697b3c152 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -190,6 +190,7 @@ enum ip_set_dim { * If changed, new revision of iptables match/target is required. */ IPSET_DIM_MAX = 6, + IPSET_BIT_RETURN_NOMATCH = 7, }; /* Option flags for kernel operations */ @@ -198,6 +199,7 @@ enum ip_set_kopt { IPSET_DIM_ONE_SRC = (1 << IPSET_DIM_ONE), IPSET_DIM_TWO_SRC = (1 << IPSET_DIM_TWO), IPSET_DIM_THREE_SRC = (1 << IPSET_DIM_THREE), + IPSET_RETURN_NOMATCH = (1 << IPSET_BIT_RETURN_NOMATCH), }; #ifdef __KERNEL__ @@ -229,6 +231,8 @@ enum ip_set_feature { IPSET_TYPE_NAME = (1 << IPSET_TYPE_NAME_FLAG), IPSET_TYPE_IFACE_FLAG = 5, IPSET_TYPE_IFACE = (1 << IPSET_TYPE_IFACE_FLAG), + IPSET_TYPE_NOMATCH_FLAG = 6, + IPSET_TYPE_NOMATCH = (1 << IPSET_TYPE_NOMATCH_FLAG), /* Strictly speaking not a feature, but a flag for dumping: * this settype must be dumped last */ IPSET_DUMP_LAST_FLAG = 7, -- cgit v1.2.3 From c9d2ea96ca3bbc85264803ff6bd66eb3bbefdb77 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sun, 23 Sep 2012 02:09:23 -0400 Subject: netlink: Rearrange netlink_kernel_cfg to save space on 64-bit. Suggested by Jan Engelhardt. Signed-off-by: David S. Miller --- include/linux/netlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index b3dc992fb25b..f80c56ac4d82 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -183,10 +183,10 @@ extern void netlink_table_ungrab(void); /* optional Netlink kernel configuration parameters */ struct netlink_kernel_cfg { unsigned int groups; + unsigned int flags; void (*input)(struct sk_buff *skb); struct mutex *cb_mutex; void (*bind)(int group); - unsigned int flags; }; extern struct sock *__netlink_kernel_create(struct net *net, int unit, -- cgit v1.2.3 From 54eb3df3a7d01b6cd395bdc1098280f2f93fbec5 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 17 Sep 2012 00:23:09 +0000 Subject: netfilter: xt_time: add support to ignore day transition Currently, if you want to do something like: "match Monday, starting 23:00, for two hours" You need two rules, one for Mon 23:00 to 0:00 and one for Tue 0:00-1:00. The rule: --weekdays Mo --timestart 23:00 --timestop 01:00 looks correct, but it will first match on monday from midnight to 1 a.m. and then again for another hour from 23:00 onwards. This permits userspace to explicitly ignore the day transition and match for a single, continuous time period instead. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/xt_time.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/xt_time.h b/include/linux/netfilter/xt_time.h index 7c37fac576c4..095886019396 100644 --- a/include/linux/netfilter/xt_time.h +++ b/include/linux/netfilter/xt_time.h @@ -17,6 +17,9 @@ enum { /* Match against local time (instead of UTC) */ XT_TIME_LOCAL_TZ = 1 << 0, + /* treat timestart > timestop (e.g. 23:00-01:00) as single period */ + XT_TIME_CONTIGUOUS = 1 << 1, + /* Shortcuts */ XT_TIME_ALL_MONTHDAYS = 0xFFFFFFFE, XT_TIME_ALL_WEEKDAYS = 0xFE, @@ -24,4 +27,6 @@ enum { XT_TIME_MAX_DAYTIME = 24 * 60 * 60 - 1, }; +#define XT_TIME_ALL_FLAGS (XT_TIME_LOCAL_TZ|XT_TIME_CONTIGUOUS) + #endif /* _XT_TIME_H */ -- cgit v1.2.3 From 7be54ca4764bdead40bee7b645a72718c20ff2c8 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 21 Sep 2012 16:52:08 +0200 Subject: netfilter: nf_ct_ftp: add sequence tracking pickup facility for injected entries This patch allows the FTP helper to pickup the sequence tracking from the first packet seen. This is useful to fix the breakage of the first FTP command after the failover while using conntrackd to synchronize states. The seq_aft_nl_num field in struct nf_ct_ftp_info has been shrinked to 16-bits (enough for what it does), so we can use the remaining 16-bits to store the flags while using the same size for the private FTP helper data. Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_ftp.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_ftp.h b/include/linux/netfilter/nf_conntrack_ftp.h index 28f18df36525..8faf3f792d13 100644 --- a/include/linux/netfilter/nf_conntrack_ftp.h +++ b/include/linux/netfilter/nf_conntrack_ftp.h @@ -18,13 +18,17 @@ enum nf_ct_ftp_type { #define FTP_PORT 21 +#define NF_CT_FTP_SEQ_PICKUP (1 << 0) + #define NUM_SEQ_TO_REMEMBER 2 /* This structure exists only once per master */ struct nf_ct_ftp_master { /* Valid seq positions for cmd matching after newline */ u_int32_t seq_aft_nl[IP_CT_DIR_MAX][NUM_SEQ_TO_REMEMBER]; /* 0 means seq_match_aft_nl not set */ - int seq_aft_nl_num[IP_CT_DIR_MAX]; + u_int16_t seq_aft_nl_num[IP_CT_DIR_MAX]; + /* pickup sequence tracking, useful for conntrackd */ + u_int16_t flags[IP_CT_DIR_MAX]; }; struct nf_conntrack_expect; -- cgit v1.2.3 From 6ee584be3ee30f72dec8a8ca87bc10824e27a631 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 24 Sep 2012 14:52:12 +0200 Subject: netfilter: nfnetlink_queue: add NFQA_CAP_LEN attribute This patch adds the NFQA_CAP_LEN attribute that allows us to know what is the real packet size from user-space (even if we decided to retrieve just a few bytes from the packet instead of all of it). Security software that inspects packets should always check for this new attribute to make sure that it is inspecting the entire packet. This also helps to provide a workaround for the problem described in: http://marc.info/?l=netfilter-devel&m=134519473212536&w=2 Original idea from Florian Westphal. Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink_queue.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_queue.h b/include/linux/netfilter/nfnetlink_queue.h index 3b1c1360aedf..70ec8c2bc11a 100644 --- a/include/linux/netfilter/nfnetlink_queue.h +++ b/include/linux/netfilter/nfnetlink_queue.h @@ -44,6 +44,7 @@ enum nfqnl_attr_type { NFQA_PAYLOAD, /* opaque data payload */ NFQA_CT, /* nf_conntrack_netlink.h */ NFQA_CT_INFO, /* enum ip_conntrack_info */ + NFQA_CAP_LEN, /* __u32 length of captured packet */ __NFQA_MAX }; -- cgit v1.2.3 From 5640f7685831e088fe6c2e1f863a6805962f8e81 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 23 Sep 2012 23:04:42 +0000 Subject: net: use a per task frag allocator We currently use a per socket order-0 page cache for tcp_sendmsg() operations. This page is used to build fragments for skbs. Its done to increase probability of coalescing small write() into single segments in skbs still in write queue (not yet sent) But it wastes a lot of memory for applications handling many mostly idle sockets, since each socket holds one page in sk->sk_sndmsg_page Its also quite inefficient to build TSO 64KB packets, because we need about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit page allocator more than wanted. This patch adds a per task frag allocator and uses bigger pages, if available. An automatic fallback is done in case of memory pressure. (up to 32768 bytes per frag, thats order-3 pages on x86) This increases TCP stream performance by 20% on loopback device, but also benefits on other network devices, since 8x less frags are mapped on transmit and unmapped on tx completion. Alexander Duyck mentioned a probable performance win on systems with IOMMU enabled. Its possible some SG enabled hardware cant cope with bigger fragments, but their ndo_start_xmit() should already handle this, splitting a fragment in sub fragments, since some arches have PAGE_SIZE=65536 Successfully tested on various ethernet devices. (ixgbe, igb, bnx2x, tg3, mellanox mlx4) Signed-off-by: Eric Dumazet Cc: Ben Hutchings Cc: Vijay Subramanian Cc: Alexander Duyck Tested-by: Vijay Subramanian Signed-off-by: David S. Miller --- include/linux/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index b8c86648a2f9..a8e2413f6bc3 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1530,6 +1530,9 @@ struct task_struct { * cache last used pipe for splice */ struct pipe_inode_info *splice_pipe; + + struct page_frag task_frag; + #ifdef CONFIG_TASK_DELAY_ACCT struct task_delay_info *delays; #endif -- cgit v1.2.3 From 9e49e88958feb41ec701fa34b44723dabadbc28c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 24 Sep 2012 02:23:59 +0000 Subject: filter: add XOR instruction for use with X/K SKF_AD_ALU_XOR_X has been added a while ago, but as an 'ancillary' operation that is invoked through a negative offset in K within BPF load operations. Since BPF_MOD has recently been added, BPF_XOR should also be part of the common ALU operations. Removing SKF_AD_ALU_XOR_X might not be an option since this is exposed to user space. Signed-off-by: Daniel Borkmann Acked-by: Eric Dumazet 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 3cf5fd561d86..2ded090e10f4 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -75,6 +75,7 @@ struct sock_fprog { /* Required for SO_ATTACH_FILTER. */ #define BPF_RSH 0x70 #define BPF_NEG 0x80 #define BPF_MOD 0x90 +#define BPF_XOR 0xa0 #define BPF_JA 0x00 #define BPF_JEQ 0x10 @@ -204,6 +205,8 @@ enum { 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, -- cgit v1.2.3 From 4463523bef98ff827a89cf8219db7dfac4350241 Mon Sep 17 00:00:00 2001 From: Thierry Escande Date: Wed, 26 Sep 2012 18:16:44 +0200 Subject: NFC: LLCP raw socket support This adds support for socket of type SOCK_RAW to LLCP. sk_buff are copied and sent to raw sockets with a 2 bytes extra header: The first byte header contains the nfc adapter index. The second one contains flags: - 0x01 - Direction (0=RX, 1=TX) - 0x02-0x80 - Reserved A raw socket has to be explicitly bound to a nfc adapter. This is achieved by specifying the adapter index to be bound to in the dev_idx field of the sockaddr_nfc_llcp struct passed to bind(). Signed-off-by: Thierry Escande Signed-off-by: Samuel Ortiz --- include/linux/nfc.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfc.h b/include/linux/nfc.h index 6189f27e305b..d908d17da56d 100644 --- a/include/linux/nfc.h +++ b/include/linux/nfc.h @@ -183,4 +183,15 @@ struct sockaddr_nfc_llcp { #define NFC_HEADER_SIZE 1 +/** + * Pseudo-header info for raw socket packets + * First byte is the adapter index + * Second byte contains flags + * - 0x01 - Direction (0=RX, 1=TX) + * - 0x02-0x80 - Reserved + **/ +#define NFC_LLCP_RAW_HEADER_SIZE 2 +#define NFC_LLCP_DIRECTION_RX 0x00 +#define NFC_LLCP_DIRECTION_TX 0x01 + #endif /*__LINUX_NFC_H */ -- cgit v1.2.3 From 404f7c9e118e0c92902afe1853d35f5638fe4a4c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 26 Sep 2012 07:07:47 +0000 Subject: net: struct napi_struct fields reordering Remove two holes on 64bit arches, and put dev_list at the end of napi_struct since its not used in fast path. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6c131f055ab0..dd320bb22a5a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -338,18 +338,16 @@ struct napi_struct { unsigned long state; int weight; + unsigned int gro_count; int (*poll)(struct napi_struct *, int); #ifdef CONFIG_NETPOLL spinlock_t poll_lock; int poll_owner; #endif - - unsigned int gro_count; - struct net_device *dev; - struct list_head dev_list; struct sk_buff *gro_list; struct sk_buff *skb; + struct list_head dev_list; }; enum { -- cgit v1.2.3 From 862096a8bbf8f992f6d0a1a8786ffd3fc7437e48 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Thu, 27 Sep 2012 12:06:02 +0000 Subject: IB/ipoib: Add more rtnl_link_ops callbacks Add the rtnl_link_ops changelink and fill_info callbacks, through which the admin can now set/get the driver mode, etc policies. Maintain the proprietary sysfs entries only for legacy childs. For child devices, set dev->iflink to point to the parent device ifindex, such that user space tools can now correctly show the uplink relation as done for vlan, macvlan, etc devices. Pointed out by Patrick McHardy Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/if_link.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_link.h b/include/linux/if_link.h index 24c0dd09af54..4491177e984d 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -404,9 +404,16 @@ struct ifla_port_vsi { enum { IFLA_IPOIB_UNSPEC, IFLA_IPOIB_PKEY, + IFLA_IPOIB_MODE, + IFLA_IPOIB_UMCAST, __IFLA_IPOIB_MAX }; +enum { + IPOIB_MODE_DATAGRAM = 0, /* using unreliable datagram QPs */ + IPOIB_MODE_CONNECTED = 1, /* using connected QPs */ +}; + #define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1) #endif /* _LINUX_IF_LINK_H */ -- cgit v1.2.3 From edc7d57327bd08bfd04f41531d49b176369db218 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 1 Oct 2012 12:32:33 +0000 Subject: netlink: add attributes to fdb interface Later changes need to be able to refer to neighbour attributes when doing fdb_add. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index dd320bb22a5a..807a610f193c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -904,7 +904,8 @@ struct netdev_fcoe_hbainfo { * feature set might be less than what was returned by ndo_fix_features()). * Must return >0 or -errno if it changed dev->features itself. * - * int (*ndo_fdb_add)(struct ndmsg *ndm, struct net_device *dev, + * int (*ndo_fdb_add)(struct ndmsg *ndm, struct nlattr *tb[], + * struct net_device *dev, * const unsigned char *addr, u16 flags) * Adds an FDB entry to dev for addr. * int (*ndo_fdb_del)(struct ndmsg *ndm, struct net_device *dev, @@ -1014,6 +1015,7 @@ struct net_device_ops { void (*ndo_neigh_destroy)(struct neighbour *n); int (*ndo_fdb_add)(struct ndmsg *ndm, + struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 flags); -- cgit v1.2.3 From d342894c5d2f8c7df194c793ec4059656e09ca31 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 1 Oct 2012 12:32:35 +0000 Subject: vxlan: virtual extensible lan This is an implementation of Virtual eXtensible Local Area Network as described in draft RFC: http://tools.ietf.org/html/draft-mahalingam-dutt-dcops-vxlan-02 The driver integrates a Virtual Tunnel Endpoint (VTEP) functionality that learns MAC to IP address mapping. This implementation has not been tested only against the Linux userspace implementation using TAP, not against other vendor's equipment. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/if_link.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_link.h b/include/linux/if_link.h index 4491177e984d..e4dad4ddf085 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -272,6 +272,22 @@ enum macvlan_mode { #define MACVLAN_FLAG_NOPROMISC 1 +/* VXLAN section */ +enum { + IFLA_VXLAN_UNSPEC, + IFLA_VXLAN_ID, + IFLA_VXLAN_GROUP, + IFLA_VXLAN_LINK, + IFLA_VXLAN_LOCAL, + IFLA_VXLAN_TTL, + IFLA_VXLAN_TOS, + IFLA_VXLAN_LEARNING, + IFLA_VXLAN_AGEING, + IFLA_VXLAN_LIMIT, + __IFLA_VXLAN_MAX +}; +#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) + /* SR-IOV virtual function management section */ enum { -- cgit v1.2.3