From 17b14451fd2b187ddd6303726755a3af0a926b6c Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Thu, 15 Sep 2005 15:44:00 +0100 Subject: [PATCH] PATCH: remove function for non-PCI as requested Signed-off-by: Alan Cox Signed-off-by: Jeff Garzik --- include/linux/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 022105c745fc..ceee1fc42c60 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -393,6 +393,7 @@ extern int ata_pci_init_one (struct pci_dev *pdev, struct ata_port_info **port_i extern void ata_pci_remove_one (struct pci_dev *pdev); #endif /* CONFIG_PCI */ extern int ata_device_add(struct ata_probe_ent *ent); +extern void ata_host_set_remove(struct ata_host_set *host_set); extern int ata_scsi_detect(Scsi_Host_Template *sht); extern int ata_scsi_ioctl(struct scsi_device *dev, int cmd, void __user *arg); extern int ata_scsi_queuecmd(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *)); -- cgit v1.2.2 From e86ee6682b649183c11013a98be02f25e9ae399d Mon Sep 17 00:00:00 2001 From: Andy Currid Date: Mon, 19 Sep 2005 06:17:52 -0700 Subject: [PATCH] Add NVIDIA device ID in sata_nv Signed-off-by: Andy Currid Signed-off-by: Jeff Garzik --- include/linux/pci_ids.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index f6c1a142286a..cb414ea42f02 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1267,7 +1267,8 @@ #define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP51_SATA 0x0266 #define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP51_SATA2 0x0267 #define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP55_IDE 0x036E -#define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP55_SATA 0x036F +#define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP55_SATA 0x037E +#define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP55_SATA2 0x037F #define PCI_DEVICE_ID_NVIDIA_NVENET_12 0x0268 #define PCI_DEVICE_ID_NVIDIA_NVENET_13 0x0269 #define PCI_DEVICE_ID_NVIDIA_MCP51_AUDIO 0x026B -- cgit v1.2.2 From 590232a7150674b2036291eaefce085f3f9659c8 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 22 Sep 2005 04:30:44 -0300 Subject: [LLC]: Add sysctl support for the LLC timeouts Signed-off-by: Jochen Friedrich Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/sysctl.h | 26 +++++++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 3a29a9f9b451..fc8e367f671e 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -202,7 +202,8 @@ enum NET_TR=14, NET_DECNET=15, NET_ECONET=16, - NET_SCTP=17, + NET_SCTP=17, + NET_LLC=18, }; /* /proc/sys/kernel/random */ @@ -522,6 +523,29 @@ enum { NET_IPX_FORWARDING=2 }; +/* /proc/sys/net/llc */ +enum { + NET_LLC2=1, + NET_LLC_STATION=2, +}; + +/* /proc/sys/net/llc/llc2 */ +enum { + NET_LLC2_TIMEOUT=1, +}; + +/* /proc/sys/net/llc/station */ +enum { + NET_LLC_STATION_ACK_TIMEOUT=1, +}; + +/* /proc/sys/net/llc/llc2/timeout */ +enum { + NET_LLC2_ACK_TIMEOUT=1, + NET_LLC2_P_TIMEOUT=2, + NET_LLC2_REJ_TIMEOUT=3, + NET_LLC2_BUSY_TIMEOUT=4, +}; /* /proc/sys/net/appletalk */ enum { -- cgit v1.2.2 From e4c94330e3395ae87451bded2840a25d04f27902 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 22 Sep 2005 21:43:45 -0700 Subject: [PATCH] reboot: comment and factor the main reboot functions In the lead up to 2.6.13 I fixed a large number of reboot problems by making the calling conventions consistent. Despite checking and double checking my work it appears I missed an obvious one. This first patch simply refactors the reboot routines so all of the preparation for various kinds of reboots are in their own functions. Making it very hard to get the various kinds of reboot out of sync. Signed-off-by: Eric W. Biederman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/reboot.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/reboot.h b/include/linux/reboot.h index 3b3266ff1a95..7ab2cdb83ef0 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -59,6 +59,10 @@ extern void machine_crash_shutdown(struct pt_regs *); * Architecture independent implemenations of sys_reboot commands. */ +extern void kernel_restart_prepare(char *cmd); +extern void kernel_halt_prepare(void); +extern void kernel_power_off_prepare(void); + extern void kernel_restart(char *cmd); extern void kernel_halt(void); extern void kernel_power_off(void); -- cgit v1.2.2 From 67497205b12e3cb408259cc09b50c3a9d12cd935 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 22 Sep 2005 23:45:24 -0700 Subject: [NETFILTER] Fix sparse endian warnings in pptp helper Signed-off-by: Alexey Dobriyan Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ip_conntrack_pptp.h | 118 +++++++++++----------- include/linux/netfilter_ipv4/ip_conntrack_tuple.h | 6 +- 2 files changed, 62 insertions(+), 62 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_conntrack_pptp.h b/include/linux/netfilter_ipv4/ip_conntrack_pptp.h index 389e3851d52f..50a761db5a04 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack_pptp.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_pptp.h @@ -60,8 +60,8 @@ struct ip_ct_pptp_expect { struct pptp_pkt_hdr { __u16 packetLength; - __u16 packetType; - __u32 magicCookie; + __be16 packetType; + __be32 magicCookie; }; /* PptpControlMessageType values */ @@ -93,7 +93,7 @@ struct pptp_pkt_hdr { #define PPTP_REMOVE_DEVICE_ERROR 6 struct PptpControlHeader { - __u16 messageType; + __be16 messageType; __u16 reserved; }; @@ -106,13 +106,13 @@ struct PptpControlHeader { #define PPTP_BEARER_CAP_DIGITAL 0x2 struct PptpStartSessionRequest { - __u16 protocolVersion; + __be16 protocolVersion; __u8 reserved1; __u8 reserved2; - __u32 framingCapability; - __u32 bearerCapability; - __u16 maxChannels; - __u16 firmwareRevision; + __be32 framingCapability; + __be32 bearerCapability; + __be16 maxChannels; + __be16 firmwareRevision; __u8 hostName[64]; __u8 vendorString[64]; }; @@ -125,13 +125,13 @@ struct PptpStartSessionRequest { #define PPTP_START_UNKNOWN_PROTOCOL 5 struct PptpStartSessionReply { - __u16 protocolVersion; + __be16 protocolVersion; __u8 resultCode; __u8 generalErrorCode; - __u32 framingCapability; - __u32 bearerCapability; - __u16 maxChannels; - __u16 firmwareRevision; + __be32 framingCapability; + __be32 bearerCapability; + __be16 maxChannels; + __be16 firmwareRevision; __u8 hostName[64]; __u8 vendorString[64]; }; @@ -155,7 +155,7 @@ struct PptpStopSessionReply { }; struct PptpEchoRequest { - __u32 identNumber; + __be32 identNumber; }; /* PptpEchoReplyResultCode */ @@ -163,7 +163,7 @@ struct PptpEchoRequest { #define PPTP_ECHO_GENERAL_ERROR 2 struct PptpEchoReply { - __u32 identNumber; + __be32 identNumber; __u8 resultCode; __u8 generalErrorCode; __u16 reserved; @@ -180,16 +180,16 @@ struct PptpEchoReply { #define PPTP_DONT_CARE_BEARER_TYPE 3 struct PptpOutCallRequest { - __u16 callID; - __u16 callSerialNumber; - __u32 minBPS; - __u32 maxBPS; - __u32 bearerType; - __u32 framingType; - __u16 packetWindow; - __u16 packetProcDelay; + __be16 callID; + __be16 callSerialNumber; + __be32 minBPS; + __be32 maxBPS; + __be32 bearerType; + __be32 framingType; + __be16 packetWindow; + __be16 packetProcDelay; __u16 reserved1; - __u16 phoneNumberLength; + __be16 phoneNumberLength; __u16 reserved2; __u8 phoneNumber[64]; __u8 subAddress[64]; @@ -205,24 +205,24 @@ struct PptpOutCallRequest { #define PPTP_OUTCALL_DONT_ACCEPT 7 struct PptpOutCallReply { - __u16 callID; - __u16 peersCallID; + __be16 callID; + __be16 peersCallID; __u8 resultCode; __u8 generalErrorCode; - __u16 causeCode; - __u32 connectSpeed; - __u16 packetWindow; - __u16 packetProcDelay; - __u32 physChannelID; + __be16 causeCode; + __be32 connectSpeed; + __be16 packetWindow; + __be16 packetProcDelay; + __be32 physChannelID; }; struct PptpInCallRequest { - __u16 callID; - __u16 callSerialNumber; - __u32 callBearerType; - __u32 physChannelID; - __u16 dialedNumberLength; - __u16 dialingNumberLength; + __be16 callID; + __be16 callSerialNumber; + __be32 callBearerType; + __be32 physChannelID; + __be16 dialedNumberLength; + __be16 dialingNumberLength; __u8 dialedNumber[64]; __u8 dialingNumber[64]; __u8 subAddress[64]; @@ -234,54 +234,54 @@ struct PptpInCallRequest { #define PPTP_INCALL_DONT_ACCEPT 3 struct PptpInCallReply { - __u16 callID; - __u16 peersCallID; + __be16 callID; + __be16 peersCallID; __u8 resultCode; __u8 generalErrorCode; - __u16 packetWindow; - __u16 packetProcDelay; + __be16 packetWindow; + __be16 packetProcDelay; __u16 reserved; }; struct PptpInCallConnected { - __u16 peersCallID; + __be16 peersCallID; __u16 reserved; - __u32 connectSpeed; - __u16 packetWindow; - __u16 packetProcDelay; - __u32 callFramingType; + __be32 connectSpeed; + __be16 packetWindow; + __be16 packetProcDelay; + __be32 callFramingType; }; struct PptpClearCallRequest { - __u16 callID; + __be16 callID; __u16 reserved; }; struct PptpCallDisconnectNotify { - __u16 callID; + __be16 callID; __u8 resultCode; __u8 generalErrorCode; - __u16 causeCode; + __be16 causeCode; __u16 reserved; __u8 callStatistics[128]; }; struct PptpWanErrorNotify { - __u16 peersCallID; + __be16 peersCallID; __u16 reserved; - __u32 crcErrors; - __u32 framingErrors; - __u32 hardwareOverRuns; - __u32 bufferOverRuns; - __u32 timeoutErrors; - __u32 alignmentErrors; + __be32 crcErrors; + __be32 framingErrors; + __be32 hardwareOverRuns; + __be32 bufferOverRuns; + __be32 timeoutErrors; + __be32 alignmentErrors; }; struct PptpSetLinkInfo { - __u16 peersCallID; + __be16 peersCallID; __u16 reserved; - __u32 sendAccm; - __u32 recvAccm; + __be32 sendAccm; + __be32 recvAccm; }; diff --git a/include/linux/netfilter_ipv4/ip_conntrack_tuple.h b/include/linux/netfilter_ipv4/ip_conntrack_tuple.h index 14dc0f7b6556..20e43f018b7c 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack_tuple.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_tuple.h @@ -17,7 +17,7 @@ union ip_conntrack_manip_proto u_int16_t all; struct { - u_int16_t port; + __be16 port; } tcp; struct { u_int16_t port; @@ -29,7 +29,7 @@ union ip_conntrack_manip_proto u_int16_t port; } sctp; struct { - u_int16_t key; /* key is 32bit, pptp only uses 16 */ + __be16 key; /* key is 32bit, pptp only uses 16 */ } gre; }; @@ -65,7 +65,7 @@ struct ip_conntrack_tuple u_int16_t port; } sctp; struct { - u_int16_t key; /* key is 32bit, + __be16 key; /* key is 32bit, * pptp only uses 16 */ } gre; } u; -- cgit v1.2.2 From a82b748930fce0dab22c64075c38c830ae116904 Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Thu, 22 Sep 2005 23:45:44 -0700 Subject: [NETFILTER] remove unneeded structure definition from conntrack helper Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ip_conntrack_pptp.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_conntrack_pptp.h b/include/linux/netfilter_ipv4/ip_conntrack_pptp.h index 50a761db5a04..816144c75de0 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack_pptp.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_pptp.h @@ -284,13 +284,6 @@ struct PptpSetLinkInfo { __be32 recvAccm; }; - -struct pptp_priv_data { - __u16 call_id; - __u16 mcall_id; - __u16 pcall_id; -}; - union pptp_ctrl_union { struct PptpStartSessionRequest sreq; struct PptpStartSessionReply srep; -- cgit v1.2.2 From 1dfbab59498d6f227c91988bab6c71af049a5333 Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Thu, 22 Sep 2005 23:46:57 -0700 Subject: [NETFILTER] Fix conntrack event cache deadlock/oops This patch fixes a number of bugs. It cannot be reasonably split up in multiple fixes, since all bugs interact with each other and affect the same function: Bug #1: The event cache code cannot be called while a lock is held. Therefore, the call to ip_conntrack_event_cache() within ip_ct_refresh_acct() needs to be moved outside of the locked section. This fixes a number of 2.6.14-rcX oops and deadlock reports. Bug #2: We used to call ct_add_counters() for unconfirmed connections without holding a lock. Since the add operations are not atomic, we could race with another CPU. Bug #3: ip_ct_refresh_acct() lost REFRESH events in some cases where refresh (and the corresponding event) are desired, but no accounting shall be performed. Both, evenst and accounting implicitly depended on the skb parameter bein non-null. We now re-introduce a non-accounting "ip_ct_refresh()" variant to explicitly state the desired behaviour. Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ip_conntrack.h | 25 +++++++++++++++++++++---- 1 file changed, 21 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_conntrack.h b/include/linux/netfilter_ipv4/ip_conntrack.h index bace72a76cc4..4ced38736813 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack.h +++ b/include/linux/netfilter_ipv4/ip_conntrack.h @@ -332,11 +332,28 @@ extern void need_ip_conntrack(void); extern int invert_tuplepr(struct ip_conntrack_tuple *inverse, const struct ip_conntrack_tuple *orig); +extern void __ip_ct_refresh_acct(struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + const struct sk_buff *skb, + unsigned long extra_jiffies, + int do_acct); + +/* Refresh conntrack for this many jiffies and do accounting */ +static inline void ip_ct_refresh_acct(struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + const struct sk_buff *skb, + unsigned long extra_jiffies) +{ + __ip_ct_refresh_acct(ct, ctinfo, skb, extra_jiffies, 1); +} + /* Refresh conntrack for this many jiffies */ -extern void ip_ct_refresh_acct(struct ip_conntrack *ct, - enum ip_conntrack_info ctinfo, - const struct sk_buff *skb, - unsigned long extra_jiffies); +static inline void ip_ct_refresh(struct ip_conntrack *ct, + const struct sk_buff *skb, + unsigned long extra_jiffies) +{ + __ip_ct_refresh_acct(ct, 0, skb, extra_jiffies, 0); +} /* These are for NAT. Icky. */ /* Update TCP window tracking data when NAT mangles the packet */ -- cgit v1.2.2 From 8c3520d4eb3b1bbf2e45fbae8dcfb8db06d5e775 Mon Sep 17 00:00:00 2001 From: Daniel Ritz Date: Sun, 21 Aug 2005 22:29:26 -0700 Subject: [PATCH] yenta: auto-tune EnE bridges for CardBus cards Echo Audio cardbus products are known to be incompatible with EnE bridges. in order to maybe solve the problem a EnE specific test bit has to be set, another cleared...but other setups have a good chance to break when just forcing the bits. so do the whole thingy automatically. The patch adds a hook in cb_alloc() that allows special tuning for the different chipsets. for ene just match the Echo products and set/clear the test bits, defaults to do the same thing as w/o the patch to not break working setups. Signed-off-by: Daniel Ritz Cc: Linus Torvalds Signed-off-by: Andrew Morton Signed-off-by: Dominik Brodowski --- include/linux/pci_ids.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index b86a4b77007e..92efb2c767f9 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2187,7 +2187,12 @@ #define PCI_DEVICE_ID_ENE_1211 0x1211 #define PCI_DEVICE_ID_ENE_1225 0x1225 #define PCI_DEVICE_ID_ENE_1410 0x1410 +#define PCI_DEVICE_ID_ENE_710 0x1411 +#define PCI_DEVICE_ID_ENE_712 0x1412 #define PCI_DEVICE_ID_ENE_1420 0x1420 +#define PCI_DEVICE_ID_ENE_720 0x1421 +#define PCI_DEVICE_ID_ENE_722 0x1422 + #define PCI_VENDOR_ID_CHELSIO 0x1425 #define PCI_VENDOR_ID_MIPS 0x153f -- cgit v1.2.2 From 6c1a10dba92cbacb58563f5eacf93807125b488a Mon Sep 17 00:00:00 2001 From: Daniel Ritz Date: Tue, 20 Sep 2005 14:12:17 -0700 Subject: [PATCH] yenta: add support for more TI bridges Support some more TI cardbus bridges. most of them are multifunction devices which adds 1394 controllers, smartcard readers etc. this could also help with the various problems with the XX21 controllers seen on the linux-pcmcia list. Signed-off-by: Daniel Ritz Signed-off-by: Dominik Brodowski --- include/linux/pci_ids.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 92efb2c767f9..68f11ac1a314 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -769,6 +769,8 @@ #define PCI_DEVICE_ID_TI_TVP4010 0x3d04 #define PCI_DEVICE_ID_TI_TVP4020 0x3d07 #define PCI_DEVICE_ID_TI_4450 0x8011 +#define PCI_DEVICE_ID_TI_XX21_XX11 0x8031 +#define PCI_DEVICE_ID_TI_X515 0x8036 #define PCI_DEVICE_ID_TI_1130 0xac12 #define PCI_DEVICE_ID_TI_1031 0xac13 #define PCI_DEVICE_ID_TI_1131 0xac15 @@ -785,12 +787,17 @@ #define PCI_DEVICE_ID_TI_4451 0xac42 #define PCI_DEVICE_ID_TI_4510 0xac44 #define PCI_DEVICE_ID_TI_4520 0xac46 +#define PCI_DEVICE_ID_TI_7510 0xac47 +#define PCI_DEVICE_ID_TI_7610 0xac48 +#define PCI_DEVICE_ID_TI_7410 0xac49 #define PCI_DEVICE_ID_TI_1410 0xac50 #define PCI_DEVICE_ID_TI_1420 0xac51 #define PCI_DEVICE_ID_TI_1451A 0xac52 #define PCI_DEVICE_ID_TI_1620 0xac54 #define PCI_DEVICE_ID_TI_1520 0xac55 #define PCI_DEVICE_ID_TI_1510 0xac56 +#define PCI_DEVICE_ID_TI_X620 0xac8d +#define PCI_DEVICE_ID_TI_X420 0xac8e #define PCI_VENDOR_ID_SONY 0x104d #define PCI_DEVICE_ID_SONY_CXD3222 0x8039 -- cgit v1.2.2 From 4fb7edce52e5b6cf41e3375822d74a27f0b6f2dd Mon Sep 17 00:00:00 2001 From: Kars de Jong Date: Sun, 25 Sep 2005 14:39:46 +0200 Subject: [PATCH] pcmcia: fix cross-platform issues with pcmcia module aliases - Added a missing TO_NATIVE call to scripts/mod/file2alias.c:do_pcmcia_entry() - Add an alignment attribute to struct pcmcia_device_no to solve an alignment issue seen when cross-compiling on x86 for m68k. Signed-off-by: Kars de Jong Signed-off-by: Dominik Brodowski --- include/linux/mod_devicetable.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 47da39ba3f03..4ed2107bc020 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -209,10 +209,11 @@ struct pcmcia_device_id { /* for real multi-function devices */ __u8 function; - /* for pseude multi-function devices */ + /* for pseudo multi-function devices */ __u8 device_no; - __u32 prod_id_hash[4]; + __u32 prod_id_hash[4] + __attribute__((aligned(sizeof(__u32)))); /* not matched against in kernelspace*/ #ifdef __KERNEL__ -- cgit v1.2.2 From acd042bb2de50d4e6fb969281a00cc8b8b71e46d Mon Sep 17 00:00:00 2001 From: Evgeniy Polyakov Date: Mon, 26 Sep 2005 15:06:50 -0700 Subject: [CONNECTOR]: async connector mode. If input message rate from userspace is too high, do not drop them, but try to deliver using work queue allocation. Failing there is some kind of congestion control. It also removes warn_on on this condition, which scares people. Signed-off-by: Evgeniy Polyakov Signed-off-by: David S. Miller --- include/linux/connector.h | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/connector.h b/include/linux/connector.h index 96de26301f84..86d4b0a81713 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -104,12 +104,19 @@ struct cn_queue_dev { struct sock *nls; }; -struct cn_callback { +struct cn_callback_id { unsigned char name[CN_CBQ_NAMELEN]; - struct cb_id id; +}; + +struct cn_callback_data { + void (*destruct_data) (void *); + void *ddata; + + void *callback_priv; void (*callback) (void *); - void *priv; + + void *free; }; struct cn_callback_entry { @@ -118,8 +125,8 @@ struct cn_callback_entry { struct work_struct work; struct cn_queue_dev *pdev; - void (*destruct_data) (void *); - void *ddata; + struct cn_callback_id id; + struct cn_callback_data data; int seq, group; struct sock *nls; @@ -144,7 +151,7 @@ int cn_add_callback(struct cb_id *, char *, void (*callback) (void *)); void cn_del_callback(struct cb_id *); int cn_netlink_send(struct cn_msg *, u32, int); -int cn_queue_add_callback(struct cn_queue_dev *dev, struct cn_callback *cb); +int cn_queue_add_callback(struct cn_queue_dev *dev, char *name, struct cb_id *id, void (*callback)(void *)); void cn_queue_del_callback(struct cn_queue_dev *dev, struct cb_id *id); struct cn_queue_dev *cn_queue_alloc_dev(char *name, struct sock *); @@ -152,6 +159,8 @@ void cn_queue_free_dev(struct cn_queue_dev *dev); int cn_cb_equal(struct cb_id *, struct cb_id *); +void cn_queue_wrapper(void *data); + extern int cn_already_initialized; #endif /* __KERNEL__ */ -- cgit v1.2.2 From 188bab3ae0ed164bc18f98be932512d777dd038b Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Mon, 26 Sep 2005 15:25:11 -0700 Subject: [NETFILTER]: Fix invalid module autoloading by splitting iptable_nat When you've enabled conntrack and NAT as a module (standard case in all distributions), and you've also enabled the new conntrack netlink interface, loading ip_conntrack_netlink.ko will auto-load iptable_nat.ko. This causes a huge performance penalty, since for every packet you iterate the nat code, even if you don't want it. This patch splits iptable_nat.ko into the NAT core (ip_nat.ko) and the iptables frontend (iptable_nat.ko). Threfore, ip_conntrack_netlink.ko will only pull ip_nat.ko, but not the frontend. ip_nat.ko will "only" allocate some resources, but not affect runtime performance. This separation is also a nice step in anticipation of new packet filters (nf-hipac, ipset, pkttables) being able to use the NAT core. Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ip_nat_core.h | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_nat_core.h b/include/linux/netfilter_ipv4/ip_nat_core.h index 3b50eb91f007..30db23f06b03 100644 --- a/include/linux/netfilter_ipv4/ip_nat_core.h +++ b/include/linux/netfilter_ipv4/ip_nat_core.h @@ -5,16 +5,14 @@ /* This header used to share core functionality between the standalone NAT module, and the compatibility layer's use of NAT for masquerading. */ -extern int ip_nat_init(void); -extern void ip_nat_cleanup(void); -extern unsigned int nat_packet(struct ip_conntrack *ct, +extern unsigned int ip_nat_packet(struct ip_conntrack *ct, enum ip_conntrack_info conntrackinfo, unsigned int hooknum, struct sk_buff **pskb); -extern int icmp_reply_translation(struct sk_buff **pskb, - struct ip_conntrack *ct, - enum ip_nat_manip_type manip, - enum ip_conntrack_dir dir); +extern int ip_nat_icmp_reply_translation(struct sk_buff **pskb, + struct ip_conntrack *ct, + enum ip_nat_manip_type manip, + enum ip_conntrack_dir dir); #endif /* _IP_NAT_CORE_H */ -- cgit v1.2.2 From c4a3e0a529ab3e65223e81681c7c6b1bc188fa58 Mon Sep 17 00:00:00 2001 From: "Bagalkote, Sreenivas" Date: Tue, 20 Sep 2005 17:46:58 -0400 Subject: [SCSI] MegaRAID SAS RAID: new driver Signed-off-by: Sreenivas Bagalkote Signed-off-by: James Bottomley --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index c49d28eca561..20fb79810c3c 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -185,6 +185,7 @@ #define PCI_DEVICE_ID_LSI_61C102 0x0901 #define PCI_DEVICE_ID_LSI_63C815 0x1000 #define PCI_DEVICE_ID_LSI_SAS1064 0x0050 +#define PCI_DEVICE_ID_LSI_SAS1064R 0x0411 #define PCI_DEVICE_ID_LSI_SAS1066 0x005E #define PCI_DEVICE_ID_LSI_SAS1068 0x0054 #define PCI_DEVICE_ID_LSI_SAS1064A 0x005C @@ -559,6 +560,7 @@ #define PCI_VENDOR_ID_DELL 0x1028 #define PCI_DEVICE_ID_DELL_RACIII 0x0008 #define PCI_DEVICE_ID_DELL_RAC4 0x0012 +#define PCI_DEVICE_ID_DELL_PERC5 0x0015 #define PCI_VENDOR_ID_MATROX 0x102B #define PCI_DEVICE_ID_MATROX_MGA_2 0x0518 -- cgit v1.2.2 From 9356b8fc07dc126cd91d2b12f314d760ab48996e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 27 Sep 2005 15:23:16 -0700 Subject: [NET]: Reorder some hot fields of struct net_device Place them on separate cache lines in SMP to lower memory bouncing between multiple CPU accessing the device. - One part is mostly used on receive path (including eth_type_trans()) (poll_list, poll, quota, weight, last_rx, dev_addr, broadcast) - One part is mostly used on queue transmit path (qdisc) (queue_lock, qdisc, qdisc_sleeping, qdisc_list, tx_queue_len) - One part is mostly used on xmit path (device) (xmit_lock, xmit_lock_owner, priv, hard_start_xmit, trans_start) 'features' is placed outside of these hot points, in a location that may be shared by all cpus (because mostly read) name_hlist is moved close to name[IFNAMSIZ] to speedup __dev_get_by_name() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 89 +++++++++++++++++++++++++++++------------------ 1 file changed, 55 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7c717907896d..368e4c825ff1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -265,6 +265,8 @@ struct net_device * the interface. */ char name[IFNAMSIZ]; + /* device name hash chain */ + struct hlist_node name_hlist; /* * I/O specific fields @@ -292,6 +294,21 @@ struct net_device /* ------- Fields preinitialized in Space.c finish here ------- */ + /* Net device features */ + unsigned long features; +#define NETIF_F_SG 1 /* Scatter/gather IO. */ +#define NETIF_F_IP_CSUM 2 /* Can checksum only TCP/UDP over IPv4. */ +#define NETIF_F_NO_CSUM 4 /* Does not require checksum. F.e. loopack. */ +#define NETIF_F_HW_CSUM 8 /* Can checksum all the packets. */ +#define NETIF_F_HIGHDMA 32 /* Can DMA to high memory. */ +#define NETIF_F_FRAGLIST 64 /* Scatter/gather IO. */ +#define NETIF_F_HW_VLAN_TX 128 /* Transmit VLAN hw acceleration */ +#define NETIF_F_HW_VLAN_RX 256 /* Receive VLAN hw acceleration */ +#define NETIF_F_HW_VLAN_FILTER 512 /* Receive filtering on VLAN */ +#define NETIF_F_VLAN_CHALLENGED 1024 /* Device cannot handle VLAN packets */ +#define NETIF_F_TSO 2048 /* Can offload TCP/IP segmentation */ +#define NETIF_F_LLTX 4096 /* LockLess TX */ + struct net_device *next_sched; /* Interface index. Unique device identifier */ @@ -316,9 +333,6 @@ struct net_device * will (read: may be cleaned up at will). */ - /* These may be needed for future network-power-down code. */ - unsigned long trans_start; /* Time (in jiffies) of last Tx */ - unsigned long last_rx; /* Time of last Rx */ unsigned short flags; /* interface flags (a la BSD) */ unsigned short gflags; @@ -328,15 +342,12 @@ struct net_device unsigned mtu; /* interface MTU value */ unsigned short type; /* interface hardware type */ unsigned short hard_header_len; /* hardware hdr length */ - void *priv; /* pointer to private data */ struct net_device *master; /* Pointer to master device of a group, * which this device is member of. */ /* Interface address info. */ - unsigned char broadcast[MAX_ADDR_LEN]; /* hw bcast add */ - unsigned char dev_addr[MAX_ADDR_LEN]; /* hw address */ unsigned char perm_addr[MAX_ADDR_LEN]; /* permanent hw address */ unsigned char addr_len; /* hardware address length */ unsigned short dev_id; /* for shared network cards */ @@ -346,8 +357,6 @@ struct net_device int promiscuity; int allmulti; - int watchdog_timeo; - struct timer_list watchdog_timer; /* Protocol specific pointers */ @@ -358,32 +367,62 @@ struct net_device void *ec_ptr; /* Econet specific data */ void *ax25_ptr; /* AX.25 specific data */ - struct list_head poll_list; /* Link to poll list */ +/* + * Cache line mostly used on receive path (including eth_type_trans()) + */ + struct list_head poll_list ____cacheline_aligned_in_smp; + /* Link to poll list */ + + int (*poll) (struct net_device *dev, int *quota); int quota; int weight; + unsigned long last_rx; /* Time of last Rx */ + /* Interface address info used in eth_type_trans() */ + unsigned char dev_addr[MAX_ADDR_LEN]; /* hw address, (before bcast + because most packets are unicast) */ + + unsigned char broadcast[MAX_ADDR_LEN]; /* hw bcast add */ +/* + * Cache line mostly used on queue transmit path (qdisc) + */ + /* device queue lock */ + spinlock_t queue_lock ____cacheline_aligned_in_smp; struct Qdisc *qdisc; struct Qdisc *qdisc_sleeping; - struct Qdisc *qdisc_ingress; struct list_head qdisc_list; unsigned long tx_queue_len; /* Max frames per queue allowed */ /* ingress path synchronizer */ spinlock_t ingress_lock; + struct Qdisc *qdisc_ingress; + +/* + * One part is mostly used on xmit path (device) + */ /* hard_start_xmit synchronizer */ - spinlock_t xmit_lock; + spinlock_t xmit_lock ____cacheline_aligned_in_smp; /* cpu id of processor entered to hard_start_xmit or -1, if nobody entered there. */ int xmit_lock_owner; - /* device queue lock */ - spinlock_t queue_lock; + void *priv; /* pointer to private data */ + int (*hard_start_xmit) (struct sk_buff *skb, + struct net_device *dev); + /* These may be needed for future network-power-down code. */ + unsigned long trans_start; /* Time (in jiffies) of last Tx */ + + int watchdog_timeo; /* used by dev_watchdog() */ + struct timer_list watchdog_timer; + +/* + * refcnt is a very hot point, so align it on SMP + */ /* Number of references to this device */ - atomic_t refcnt; + atomic_t refcnt ____cacheline_aligned_in_smp; + /* delayed register/unregister */ struct list_head todo_list; - /* device name hash chain */ - struct hlist_node name_hlist; /* device index hash chain */ struct hlist_node index_hlist; @@ -396,21 +435,6 @@ struct net_device NETREG_RELEASED, /* called free_netdev */ } reg_state; - /* Net device features */ - unsigned long features; -#define NETIF_F_SG 1 /* Scatter/gather IO. */ -#define NETIF_F_IP_CSUM 2 /* Can checksum only TCP/UDP over IPv4. */ -#define NETIF_F_NO_CSUM 4 /* Does not require checksum. F.e. loopack. */ -#define NETIF_F_HW_CSUM 8 /* Can checksum all the packets. */ -#define NETIF_F_HIGHDMA 32 /* Can DMA to high memory. */ -#define NETIF_F_FRAGLIST 64 /* Scatter/gather IO. */ -#define NETIF_F_HW_VLAN_TX 128 /* Transmit VLAN hw acceleration */ -#define NETIF_F_HW_VLAN_RX 256 /* Receive VLAN hw acceleration */ -#define NETIF_F_HW_VLAN_FILTER 512 /* Receive filtering on VLAN */ -#define NETIF_F_VLAN_CHALLENGED 1024 /* Device cannot handle VLAN packets */ -#define NETIF_F_TSO 2048 /* Can offload TCP/IP segmentation */ -#define NETIF_F_LLTX 4096 /* LockLess TX */ - /* Called after device is detached from network. */ void (*uninit)(struct net_device *dev); /* Called after last user reference disappears. */ @@ -419,10 +443,7 @@ struct net_device /* Pointers to interface service routines. */ int (*open)(struct net_device *dev); int (*stop)(struct net_device *dev); - int (*hard_start_xmit) (struct sk_buff *skb, - struct net_device *dev); #define HAVE_NETDEV_POLL - int (*poll) (struct net_device *dev, int *quota); int (*hard_header) (struct sk_buff *skb, struct net_device *dev, unsigned short type, -- cgit v1.2.2 From 1f26dac32057baaf67d10b45c6b5277db862911d Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 27 Sep 2005 15:24:13 -0700 Subject: [NET]: Add Sun Cassini driver. Written by Adrian Sun (asun@darksunrising.com). Ported to 2.6.x by Tom 'spot' Callaway . Further cleaned up and integrated by David S. Miller Signed-off-by: David S. Miller --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 68f11ac1a314..eb36fd293b41 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -392,6 +392,7 @@ #define PCI_DEVICE_ID_NS_87560_USB 0x0012 #define PCI_DEVICE_ID_NS_83815 0x0020 #define PCI_DEVICE_ID_NS_83820 0x0022 +#define PCI_DEVICE_ID_NS_SATURN 0x0035 #define PCI_DEVICE_ID_NS_SCx200_BRIDGE 0x0500 #define PCI_DEVICE_ID_NS_SCx200_SMI 0x0501 #define PCI_DEVICE_ID_NS_SCx200_IDE 0x0502 @@ -983,6 +984,7 @@ #define PCI_DEVICE_ID_SUN_SABRE 0xa000 #define PCI_DEVICE_ID_SUN_HUMMINGBIRD 0xa001 #define PCI_DEVICE_ID_SUN_TOMATILLO 0xa801 +#define PCI_DEVICE_ID_SUN_CASSINI 0xabba #define PCI_VENDOR_ID_CMD 0x1095 #define PCI_DEVICE_ID_CMD_640 0x0640 -- cgit v1.2.2 From 2fab35d78f32fc107e1af4b1ec23f557fa20d911 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Tue, 27 Sep 2005 15:59:43 -0700 Subject: [NET]: Fix GCC4 compile error: sysctl in linux/if_ether.h The following is generated when compiling a recent (2.6.14-rc2-git5) kernel configured for ARM, with GCC4. CC init/main.o In file included from include/linux/netdevice.h:29, from include/net/sock.h:48, from init/main.c:50: include/linux/if_ether.h:114: error: array type has incomplete element type It seems that if CONFIG_SYSCTL is not set, then the compiler will throw an error due to the definition of the ether_table[] array Attached is a solution to the problem Signed-off-by: Ben Dooks Signed-off-by: David S. Miller --- include/linux/if_ether.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h index fc2d4c8225aa..d21c305c6c64 100644 --- a/include/linux/if_ether.h +++ b/include/linux/if_ether.h @@ -111,7 +111,9 @@ static inline struct ethhdr *eth_hdr(const struct sk_buff *skb) return (struct ethhdr *)skb->mac.raw; } +#ifdef CONFIG_SYSCTL extern struct ctl_table ether_table[]; #endif +#endif #endif /* _LINUX_IF_ETHER_H */ -- cgit v1.2.2 From 664cceb0093b755739e56572b836a99104ee8a75 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 28 Sep 2005 17:03:15 +0100 Subject: [PATCH] Keys: Add possessor permissions to keys [try #3] The attached patch adds extra permission grants to keys for the possessor of a key in addition to the owner, group and other permissions bits. This makes SUID binaries easier to support without going as far as labelling keys and key targets using the LSM facilities. This patch adds a second "pointer type" to key structures (struct key_ref *) that can have the bottom bit of the address set to indicate the possession of a key. This is propagated through searches from the keyring to the discovered key. It has been made a separate type so that the compiler can spot attempts to dereference a potentially incorrect pointer. The "possession" attribute can't be attached to a key structure directly as it's not an intrinsic property of a key. Pointers to keys have been replaced with struct key_ref *'s wherever possession information needs to be passed through. This does assume that the bottom bit of the pointer will always be zero on return from kmem_cache_alloc(). The key reference type has been made into a typedef so that at least it can be located in the sources, even though it's basically a pointer to an undefined type. I've also renamed the accessor functions to be more useful, and all reference variables should now end in "_ref". Signed-Off-By: David Howells Signed-off-by: Linus Torvalds --- include/linux/key-ui.h | 28 ++++++++++++------ include/linux/key.h | 78 ++++++++++++++++++++++++++++++++++++++++---------- 2 files changed, 82 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/key-ui.h b/include/linux/key-ui.h index cc326174a808..918c34a8347e 100644 --- a/include/linux/key-ui.h +++ b/include/linux/key-ui.h @@ -42,11 +42,14 @@ struct keyring_list { /* * check to see whether permission is granted to use a key in the desired way */ -static inline int key_permission(const struct key *key, key_perm_t perm) +static inline int key_permission(const key_ref_t key_ref, key_perm_t perm) { + struct key *key = key_ref_to_ptr(key_ref); key_perm_t kperm; - if (key->uid == current->fsuid) + if (is_key_possessed(key_ref)) + kperm = key->perm >> 24; + else if (key->uid == current->fsuid) kperm = key->perm >> 16; else if (key->gid != -1 && key->perm & KEY_GRP_ALL && @@ -65,11 +68,14 @@ static inline int key_permission(const struct key *key, key_perm_t perm) * check to see whether permission is granted to use a key in at least one of * the desired ways */ -static inline int key_any_permission(const struct key *key, key_perm_t perm) +static inline int key_any_permission(const key_ref_t key_ref, key_perm_t perm) { + struct key *key = key_ref_to_ptr(key_ref); key_perm_t kperm; - if (key->uid == current->fsuid) + if (is_key_possessed(key_ref)) + kperm = key->perm >> 24; + else if (key->uid == current->fsuid) kperm = key->perm >> 16; else if (key->gid != -1 && key->perm & KEY_GRP_ALL && @@ -94,13 +100,17 @@ static inline int key_task_groups_search(struct task_struct *tsk, gid_t gid) return ret; } -static inline int key_task_permission(const struct key *key, +static inline int key_task_permission(const key_ref_t key_ref, struct task_struct *context, key_perm_t perm) { + struct key *key = key_ref_to_ptr(key_ref); key_perm_t kperm; - if (key->uid == context->fsuid) { + if (is_key_possessed(key_ref)) { + kperm = key->perm >> 24; + } + else if (key->uid == context->fsuid) { kperm = key->perm >> 16; } else if (key->gid != -1 && @@ -121,9 +131,9 @@ static inline int key_task_permission(const struct key *key, } -extern struct key *lookup_user_key(struct task_struct *context, - key_serial_t id, int create, int partial, - key_perm_t perm); +extern key_ref_t lookup_user_key(struct task_struct *context, + key_serial_t id, int create, int partial, + key_perm_t perm); extern long join_session_keyring(const char *name); diff --git a/include/linux/key.h b/include/linux/key.h index 970bbd916cf4..f1efa016dbf3 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -35,11 +35,18 @@ struct key; #undef KEY_DEBUGGING -#define KEY_USR_VIEW 0x00010000 /* user can view a key's attributes */ -#define KEY_USR_READ 0x00020000 /* user can read key payload / view keyring */ -#define KEY_USR_WRITE 0x00040000 /* user can update key payload / add link to keyring */ -#define KEY_USR_SEARCH 0x00080000 /* user can find a key in search / search a keyring */ -#define KEY_USR_LINK 0x00100000 /* user can create a link to a key/keyring */ +#define KEY_POS_VIEW 0x01000000 /* possessor can view a key's attributes */ +#define KEY_POS_READ 0x02000000 /* possessor can read key payload / view keyring */ +#define KEY_POS_WRITE 0x04000000 /* possessor can update key payload / add link to keyring */ +#define KEY_POS_SEARCH 0x08000000 /* possessor can find a key in search / search a keyring */ +#define KEY_POS_LINK 0x10000000 /* possessor can create a link to a key/keyring */ +#define KEY_POS_ALL 0x1f000000 + +#define KEY_USR_VIEW 0x00010000 /* user permissions... */ +#define KEY_USR_READ 0x00020000 +#define KEY_USR_WRITE 0x00040000 +#define KEY_USR_SEARCH 0x00080000 +#define KEY_USR_LINK 0x00100000 #define KEY_USR_ALL 0x001f0000 #define KEY_GRP_VIEW 0x00000100 /* group permissions... */ @@ -65,6 +72,38 @@ struct key_owner; struct keyring_list; struct keyring_name; +/*****************************************************************************/ +/* + * key reference with possession attribute handling + * + * NOTE! key_ref_t is a typedef'd pointer to a type that is not actually + * defined. This is because we abuse the bottom bit of the reference to carry a + * flag to indicate whether the calling process possesses that key in one of + * its keyrings. + * + * the key_ref_t has been made a separate type so that the compiler can reject + * attempts to dereference it without proper conversion. + * + * the three functions are used to assemble and disassemble references + */ +typedef struct __key_reference_with_attributes *key_ref_t; + +static inline key_ref_t make_key_ref(const struct key *key, + unsigned long possession) +{ + return (key_ref_t) ((unsigned long) key | possession); +} + +static inline struct key *key_ref_to_ptr(const key_ref_t key_ref) +{ + return (struct key *) ((unsigned long) key_ref & ~1UL); +} + +static inline unsigned long is_key_possessed(const key_ref_t key_ref) +{ + return (unsigned long) key_ref & 1UL; +} + /*****************************************************************************/ /* * authentication token / access credential / keyring @@ -215,20 +254,25 @@ static inline struct key *key_get(struct key *key) return key; } +static inline void key_ref_put(key_ref_t key_ref) +{ + key_put(key_ref_to_ptr(key_ref)); +} + extern struct key *request_key(struct key_type *type, const char *description, const char *callout_info); extern int key_validate(struct key *key); -extern struct key *key_create_or_update(struct key *keyring, - const char *type, - const char *description, - const void *payload, - size_t plen, - int not_in_quota); +extern key_ref_t key_create_or_update(key_ref_t keyring, + const char *type, + const char *description, + const void *payload, + size_t plen, + int not_in_quota); -extern int key_update(struct key *key, +extern int key_update(key_ref_t key, const void *payload, size_t plen); @@ -243,9 +287,9 @@ extern struct key *keyring_alloc(const char *description, uid_t uid, gid_t gid, extern int keyring_clear(struct key *keyring); -extern struct key *keyring_search(struct key *keyring, - struct key_type *type, - const char *description); +extern key_ref_t keyring_search(key_ref_t keyring, + struct key_type *type, + const char *description); extern int keyring_add_key(struct key *keyring, struct key *key); @@ -285,6 +329,10 @@ extern void key_init(void); #define key_serial(k) 0 #define key_get(k) ({ NULL; }) #define key_put(k) do { } while(0) +#define key_ref_put(k) do { } while(0) +#define make_key_ref(k) ({ NULL; }) +#define key_ref_to_ptr(k) ({ NULL; }) +#define is_key_possessed(k) 0 #define alloc_uid_keyring(u) 0 #define switch_uid_keyring(u) do { } while(0) #define __install_session_keyring(t, k) ({ NULL; }) -- cgit v1.2.2 From aa55a08687059aa169d10a313c41f238c2070488 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 29 Sep 2005 19:58:53 +0400 Subject: [PATCH] fix TASK_STOPPED vs TASK_NONINTERACTIVE interaction do_signal_stop: for_each_thread(t) { if (t->state < TASK_STOPPED) ++sig->group_stop_count; } However, TASK_NONINTERACTIVE > TASK_STOPPED, so this loop will not count TASK_INTERRUPTIBLE | TASK_NONINTERACTIVE threads. See also wait_task_stopped(), which checks ->state > TASK_STOPPED. Signed-off-by: Oleg Nesterov [ We really probably should always use the appropriate bitmasks to test task states, not do it like this. Using something like #define TASK_RUNNABLE (TASK_RUNNING | TASK_INTERRUPTIBLE | \ TASK_UNINTERRUPTIBLE | TASK_NONINTERACTIVE) and then doing "if (task->state & TASK_RUNNABLE)" or similar. But the ordering of the task states is historical, and keeping the ordering does make sense regardless. ] Signed-off-by: Linus Torvalds --- include/linux/sched.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 49e617fa0f66..afe6c61f13e5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -110,11 +110,11 @@ extern unsigned long nr_iowait(void); #define TASK_RUNNING 0 #define TASK_INTERRUPTIBLE 1 #define TASK_UNINTERRUPTIBLE 2 -#define TASK_STOPPED 4 -#define TASK_TRACED 8 -#define EXIT_ZOMBIE 16 -#define EXIT_DEAD 32 -#define TASK_NONINTERACTIVE 64 +#define TASK_NONINTERACTIVE 4 +#define TASK_STOPPED 8 +#define TASK_TRACED 16 +#define EXIT_ZOMBIE 32 +#define EXIT_DEAD 64 #define __set_task_state(tsk, state_value) \ do { (tsk)->state = (state_value); } while (0) -- cgit v1.2.2 From 4a8342d233a39ee582e9f7260e12d2f5fd194a05 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 29 Sep 2005 15:18:21 -0700 Subject: Revert task flag re-ordering, add comments Roland points out that the flags end up having non-obvious dependencies elsewhere, so revert aa55a08687059aa169d10a313c41f238c2070488 and add some comments about why things are as they are. We'll just have to fix up the broken comparisons. Roland has a patch. Signed-off-by: Linus Torvalds --- include/linux/sched.h | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index afe6c61f13e5..c3ba31f210a9 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -107,14 +107,26 @@ extern unsigned long nr_iowait(void); #include +/* + * Task state bitmask. NOTE! These bits are also + * encoded in fs/proc/array.c: get_task_state(). + * + * We have two separate sets of flags: task->state + * is about runnability, while task->exit_state are + * about the task exiting. Confusing, but this way + * modifying one set can't modify the other one by + * mistake. + */ #define TASK_RUNNING 0 #define TASK_INTERRUPTIBLE 1 #define TASK_UNINTERRUPTIBLE 2 -#define TASK_NONINTERACTIVE 4 -#define TASK_STOPPED 8 -#define TASK_TRACED 16 -#define EXIT_ZOMBIE 32 -#define EXIT_DEAD 64 +#define TASK_STOPPED 4 +#define TASK_TRACED 8 +/* in tsk->exit_state */ +#define EXIT_ZOMBIE 16 +#define EXIT_DEAD 32 +/* in tsk->state again */ +#define TASK_NONINTERACTIVE 64 #define __set_task_state(tsk, state_value) \ do { (tsk)->state = (state_value); } while (0) -- cgit v1.2.2 From 897f15fb587fd2772b9e7ff6ec0265057f3c3975 Mon Sep 17 00:00:00 2001 From: Zach Brown Date: Fri, 30 Sep 2005 11:58:55 -0700 Subject: [PATCH] aio: remove unlocked task_list test and resulting race Only one of the run or kick path is supposed to put an iocb on the run list. If both of them do it than one of them can end up referencing a freed iocb. The kick path could delete the task_list item from the wait queue before getting the ctx_lock and putting the iocb on the run list. The run path was testing the task_list item outside the lock so that it could catch ki_retry methods that return -EIOCBRETRY *without* putting the iocb on a wait queue and promising to call kick_iocb. This unlocked check could then race with the kick path to cause both to try and put the iocb on the run list. The patch stops the run path from testing task_list by requring that any ki_retry that returns -EIOCBRETRY *must* guarantee that kick_iocb() will be called in the future. aio_p{read,write}, the only in-tree -EIOCBRETRY users, are updated. Signed-off-by: Zach Brown Signed-off-by: Benjamin LaHaise Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index a4d5af907f90..60def658b246 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -43,6 +43,40 @@ struct kioctx; #define kiocbIsKicked(iocb) test_bit(KIF_KICKED, &(iocb)->ki_flags) #define kiocbIsCancelled(iocb) test_bit(KIF_CANCELLED, &(iocb)->ki_flags) +/* is there a better place to document function pointer methods? */ +/** + * ki_retry - iocb forward progress callback + * @kiocb: The kiocb struct to advance by performing an operation. + * + * This callback is called when the AIO core wants a given AIO operation + * to make forward progress. The kiocb argument describes the operation + * that is to be performed. As the operation proceeds, perhaps partially, + * ki_retry is expected to update the kiocb with progress made. Typically + * ki_retry is set in the AIO core and it itself calls file_operations + * helpers. + * + * ki_retry's return value determines when the AIO operation is completed + * and an event is generated in the AIO event ring. Except the special + * return values described below, the value that is returned from ki_retry + * is transferred directly into the completion ring as the operation's + * resulting status. Once this has happened ki_retry *MUST NOT* reference + * the kiocb pointer again. + * + * If ki_retry returns -EIOCBQUEUED it has made a promise that aio_complete() + * will be called on the kiocb pointer in the future. The AIO core will + * not ask the method again -- ki_retry must ensure forward progress. + * aio_complete() must be called once and only once in the future, multiple + * calls may result in undefined behaviour. + * + * If ki_retry returns -EIOCBRETRY it has made a promise that kick_iocb() + * will be called on the kiocb pointer in the future. This may happen + * through generic helpers that associate kiocb->ki_wait with a wait + * queue head that ki_retry uses via current->io_wait. It can also happen + * with custom tracking and manual calls to kick_iocb(), though that is + * discouraged. In either case, kick_iocb() must be called once and only + * once. ki_retry must ensure forward progress, the AIO core will wait + * indefinitely for kick_iocb() to be called. + */ struct kiocb { struct list_head ki_run_list; long ki_flags; -- cgit v1.2.2 From fd2e54b35bd70d11c160ded4834e2378e915356e Mon Sep 17 00:00:00 2001 From: Diego Calleja Date: Sat, 1 Oct 2005 17:00:48 +0200 Subject: [PATCH] trivial #if -> #ifdef Use '#ifdef' consistently on __KERNEL__. This was reported as bug #5340 (isn't easier to send a fix than report the bug?!) Signed-off-by: Diego Calleja Signed-off-by: Linus Torvalds --- include/linux/mod_devicetable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 4ed2107bc020..2f0299a448f6 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -183,7 +183,7 @@ struct of_device_id char name[32]; char type[32]; char compatible[128]; -#if __KERNEL__ +#ifdef __KERNEL__ void *data; #else kernel_ulong_t data; -- cgit v1.2.2 From 325ed8239309cb29f10ea58c5a668058ead11479 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 3 Oct 2005 13:57:23 -0700 Subject: [NET]: Fix packet timestamping. I've found the problem in general. It affects any 64-bit architecture. The problem occurs when you change the system time. Suppose that when you boot your system clock is forward by a day. This gets recorded down in skb_tv_base. You then wind the clock back by a day. From that point onwards the offset will be negative which essentially overflows the 32-bit variables they're stored in. In fact, why don't we just store the real time stamp in those 32-bit variables? After all, we're not going to overflow for quite a while yet. When we do overflow, we'll need a better solution of course. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/skbuff.h | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2741c0c55e83..466c879f82b8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -155,8 +155,6 @@ struct skb_shared_info { #define SKB_DATAREF_SHIFT 16 #define SKB_DATAREF_MASK ((1 << SKB_DATAREF_SHIFT) - 1) -extern struct timeval skb_tv_base; - struct skb_timeval { u32 off_sec; u32 off_usec; @@ -175,7 +173,7 @@ enum { * @prev: Previous buffer in list * @list: List we are on * @sk: Socket we are owned by - * @tstamp: Time we arrived stored as offset to skb_tv_base + * @tstamp: Time we arrived * @dev: Device we arrived on/are leaving by * @input_dev: Device we arrived on * @h: Transport layer header @@ -1255,10 +1253,6 @@ static inline void skb_get_timestamp(const struct sk_buff *skb, struct timeval * { stamp->tv_sec = skb->tstamp.off_sec; stamp->tv_usec = skb->tstamp.off_usec; - if (skb->tstamp.off_sec) { - stamp->tv_sec += skb_tv_base.tv_sec; - stamp->tv_usec += skb_tv_base.tv_usec; - } } /** @@ -1272,8 +1266,8 @@ static inline void skb_get_timestamp(const struct sk_buff *skb, struct timeval * */ static inline void skb_set_timestamp(struct sk_buff *skb, const struct timeval *stamp) { - skb->tstamp.off_sec = stamp->tv_sec - skb_tv_base.tv_sec; - skb->tstamp.off_usec = stamp->tv_usec - skb_tv_base.tv_usec; + skb->tstamp.off_sec = stamp->tv_sec; + skb->tstamp.off_usec = stamp->tv_usec; } extern void __net_timestamp(struct sk_buff *skb); -- cgit v1.2.2 From 81c3d5470ecc70564eb9209946730fe2be93ad06 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 3 Oct 2005 14:13:38 -0700 Subject: [INET]: speedup inet (tcp/dccp) lookups Arnaldo and I agreed it could be applied now, because I have other pending patches depending on this one (Thank you Arnaldo) (The other important patch moves skc_refcnt in a separate cache line, so that the SMP/NUMA performance doesnt suffer from cache line ping pongs) 1) First some performance data : -------------------------------- tcp_v4_rcv() wastes a *lot* of time in __inet_lookup_established() The most time critical code is : sk_for_each(sk, node, &head->chain) { if (INET_MATCH(sk, acookie, saddr, daddr, ports, dif)) goto hit; /* You sunk my battleship! */ } The sk_for_each() does use prefetch() hints but only the begining of "struct sock" is prefetched. As INET_MATCH first comparison uses inet_sk(__sk)->daddr, wich is far away from the begining of "struct sock", it has to bring into CPU cache cold cache line. Each iteration has to use at least 2 cache lines. This can be problematic if some chains are very long. 2) The goal ----------- The idea I had is to change things so that INET_MATCH() may return FALSE in 99% of cases only using the data already in the CPU cache, using one cache line per iteration. 3) Description of the patch --------------------------- Adds a new 'unsigned int skc_hash' field in 'struct sock_common', filling a 32 bits hole on 64 bits platform. struct sock_common { unsigned short skc_family; volatile unsigned char skc_state; unsigned char skc_reuse; int skc_bound_dev_if; struct hlist_node skc_node; struct hlist_node skc_bind_node; atomic_t skc_refcnt; + unsigned int skc_hash; struct proto *skc_prot; }; Store in this 32 bits field the full hash, not masked by (ehash_size - 1) Using this full hash as the first comparison done in INET_MATCH permits us immediatly skip the element without touching a second cache line in case of a miss. Suppress the sk_hashent/tw_hashent fields since skc_hash (aliased to sk_hash and tw_hash) already contains the slot number if we mask with (ehash_size - 1) File include/net/inet_hashtables.h 64 bits platforms : #define INET_MATCH(__sk, __hash, __cookie, __saddr, __daddr, __ports, __dif)\ (((__sk)->sk_hash == (__hash)) ((*((__u64 *)&(inet_sk(__sk)->daddr)))== (__cookie)) && \ ((*((__u32 *)&(inet_sk(__sk)->dport))) == (__ports)) && \ (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) 32bits platforms: #define TCP_IPV4_MATCH(__sk, __hash, __cookie, __saddr, __daddr, __ports, __dif)\ (((__sk)->sk_hash == (__hash)) && \ (inet_sk(__sk)->daddr == (__saddr)) && \ (inet_sk(__sk)->rcv_saddr == (__daddr)) && \ (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) - Adds a prefetch(head->chain.first) in __inet_lookup_established()/__tcp_v4_check_established() and __inet6_lookup_established()/__tcp_v6_check_established() and __dccp_v4_check_established() to bring into cache the first element of the list, before the {read|write}_lock(&head->lock); Signed-off-by: Eric Dumazet Acked-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/ipv6.h | 5 +++-- include/linux/tc_ematch/tc_em_meta.h | 2 +- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index bb6f88e14061..e0b922785d98 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -372,8 +372,9 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk) #define inet_v6_ipv6only(__sk) 0 #endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */ -#define INET6_MATCH(__sk, __saddr, __daddr, __ports, __dif) \ - (((*((__u32 *)&(inet_sk(__sk)->dport))) == (__ports)) && \ +#define INET6_MATCH(__sk, __hash, __saddr, __daddr, __ports, __dif)\ + (((__sk)->sk_hash == (__hash)) && \ + ((*((__u32 *)&(inet_sk(__sk)->dport))) == (__ports)) && \ ((__sk)->sk_family == AF_INET6) && \ ipv6_addr_equal(&inet6_sk(__sk)->daddr, (__saddr)) && \ ipv6_addr_equal(&inet6_sk(__sk)->rcv_saddr, (__daddr)) && \ diff --git a/include/linux/tc_ematch/tc_em_meta.h b/include/linux/tc_ematch/tc_em_meta.h index 081b1ee8516e..e21937cf91d0 100644 --- a/include/linux/tc_ematch/tc_em_meta.h +++ b/include/linux/tc_ematch/tc_em_meta.h @@ -71,7 +71,7 @@ enum TCF_META_ID_SK_SNDBUF, TCF_META_ID_SK_ALLOCS, TCF_META_ID_SK_ROUTE_CAPS, - TCF_META_ID_SK_HASHENT, + TCF_META_ID_SK_HASH, TCF_META_ID_SK_LINGERTIME, TCF_META_ID_SK_ACK_BACKLOG, TCF_META_ID_SK_MAX_ACK_BACKLOG, -- cgit v1.2.2 From e5ed639913eea3e4783a550291775ab78dd84966 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 3 Oct 2005 14:35:55 -0700 Subject: [IPV4]: Replace __in_dev_get with __in_dev_get_rcu/rtnl The following patch renames __in_dev_get() to __in_dev_get_rtnl() and introduces __in_dev_get_rcu() to cover the second case. 1) RCU with refcnt should use in_dev_get(). 2) RCU without refcnt should use __in_dev_get_rcu(). 3) All others must hold RTNL and use __in_dev_get_rtnl(). There is one exception in net/ipv4/route.c which is in fact a pre-existing race condition. I've marked it as such so that we remember to fix it. This patch is based on suggestions and prior work by Suzanne Wood and Paul McKenney. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 7e1e15f934f3..fd7af86151b1 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -142,13 +142,21 @@ static __inline__ int bad_mask(u32 mask, u32 addr) #define endfor_ifa(in_dev) } +static inline struct in_device *__in_dev_get_rcu(const struct net_device *dev) +{ + struct in_device *in_dev = dev->ip_ptr; + if (in_dev) + in_dev = rcu_dereference(in_dev); + return in_dev; +} + static __inline__ struct in_device * in_dev_get(const struct net_device *dev) { struct in_device *in_dev; rcu_read_lock(); - in_dev = dev->ip_ptr; + in_dev = __in_dev_get_rcu(dev); if (in_dev) atomic_inc(&in_dev->refcnt); rcu_read_unlock(); @@ -156,7 +164,7 @@ in_dev_get(const struct net_device *dev) } static __inline__ struct in_device * -__in_dev_get(const struct net_device *dev) +__in_dev_get_rtnl(const struct net_device *dev) { return (struct in_device*)dev->ip_ptr; } -- cgit v1.2.2