From 8bf62ecee58360749c5f0e68bc97d5e02a6816b1 Mon Sep 17 00:00:00 2001 From: Albert Lee Date: Thu, 12 May 2005 15:29:42 -0400 Subject: [libata] C/H/S support, for older devices --- include/linux/ata.h | 14 ++++++++++++++ include/linux/libata.h | 6 ++++++ 2 files changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index f178894edd04..d8981402cd5b 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -125,6 +125,7 @@ enum { ATA_CMD_PACKET = 0xA0, ATA_CMD_VERIFY = 0x40, ATA_CMD_VERIFY_EXT = 0x42, + ATA_CMD_INIT_DEV_PARAMS = 0x91, /* SETFEATURES stuff */ SETFEATURES_XFER = 0x03, @@ -174,6 +175,7 @@ enum { ATA_TFLAG_ISADDR = (1 << 1), /* enable r/w to nsect/lba regs */ ATA_TFLAG_DEVICE = (1 << 2), /* enable r/w to device reg */ ATA_TFLAG_WRITE = (1 << 3), /* data dir: host->dev==1 (write) */ + ATA_TFLAG_LBA = (1 << 4), /* enable LBA */ }; enum ata_tf_protocols { @@ -242,6 +244,18 @@ struct ata_taskfile { ((u64) (id)[(n) + 1] << 16) | \ ((u64) (id)[(n) + 0]) ) +static inline int ata_id_current_chs_valid(u16 *id) +{ + /* For ATA-1 devices, if the INITIALIZE DEVICE PARAMETERS command + has not been issued to the device then the values of + id[54] to id[56] are vendor specific. */ + return (id[53] & 0x01) && /* Current translation valid */ + id[54] && /* cylinders in current translation */ + id[55] && /* heads in current translation */ + id[55] <= 16 && + id[56]; /* sectors in current translation */ +} + static inline int atapi_cdb_len(u16 *dev_id) { u16 tmp = dev_id[0] & 0x3; diff --git a/include/linux/libata.h b/include/linux/libata.h index 505160ab472b..bd0df84cfd87 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -95,6 +95,7 @@ enum { ATA_DFLAG_LBA48 = (1 << 0), /* device supports LBA48 */ ATA_DFLAG_PIO = (1 << 1), /* device currently in PIO mode */ ATA_DFLAG_LOCK_SECTORS = (1 << 2), /* don't adjust max_sectors */ + ATA_DFLAG_LBA = (1 << 3), /* device supports LBA */ ATA_DEV_UNKNOWN = 0, /* unknown device */ ATA_DEV_ATA = 1, /* ATA device */ @@ -278,6 +279,11 @@ struct ata_device { u8 xfer_protocol; /* taskfile xfer protocol */ u8 read_cmd; /* opcode to use on read */ u8 write_cmd; /* opcode to use on write */ + + /* for CHS addressing */ + u16 cylinders; /* Number of cylinders */ + u16 heads; /* Number of heads */ + u16 sectors; /* Number of sectors per track */ }; struct ata_port { -- cgit v1.2.3 From 3173c8907ffb2c64456142da3df2bd0500bd59e0 Mon Sep 17 00:00:00 2001 From: Nishanth Aravamudan Date: Sun, 11 Sep 2005 02:09:55 -0700 Subject: [PATCH] drivers/net: fix-up schedule_timeout() usage Use schedule_timeout_interruptible() instead of set_current_state()/schedule_timeout() to reduce kernel size. Signed-off-by: Nishanth Aravamudan Cc: Jeff Garzik Cc: "David S. Miller" Signed-off-by: Andrew Morton Signed-off-by: Jeff Garzik --- include/linux/ibmtr.h | 4 ++-- include/linux/netdevice.h | 6 ++---- 2 files changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ibmtr.h b/include/linux/ibmtr.h index 2ef0b21517fb..1c7a0dd5536a 100644 --- a/include/linux/ibmtr.h +++ b/include/linux/ibmtr.h @@ -7,8 +7,8 @@ /* ported to the Alpha architecture 02/20/96 (just used the HZ macro) */ #define TR_RETRY_INTERVAL (30*HZ) /* 500 on PC = 5 s */ -#define TR_RST_TIME (HZ/20) /* 5 on PC = 50 ms */ -#define TR_BUSY_INTERVAL (HZ/5) /* 5 on PC = 200 ms */ +#define TR_RST_TIME (msecs_to_jiffies(50)) /* 5 on PC = 50 ms */ +#define TR_BUSY_INTERVAL (msecs_to_jiffies(200)) /* 5 on PC = 200 ms */ #define TR_SPIN_INTERVAL (3*HZ) /* 3 seconds before init timeout */ #define TR_ISA 1 diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7c717907896d..98c98e6cd4f3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -852,11 +852,9 @@ static inline void netif_rx_complete(struct net_device *dev) static inline void netif_poll_disable(struct net_device *dev) { - while (test_and_set_bit(__LINK_STATE_RX_SCHED, &dev->state)) { + while (test_and_set_bit(__LINK_STATE_RX_SCHED, &dev->state)) /* No hurry. */ - current->state = TASK_INTERRUPTIBLE; - schedule_timeout(1); - } + schedule_timeout_interruptible(1); } static inline void netif_poll_enable(struct net_device *dev) -- cgit v1.2.3 From 8e18d1f9c9dcbf2de5b79cad771ed639983ab6cd Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Sat, 10 Sep 2005 14:45:00 -0700 Subject: [PATCH] Replace drivers/net/wan custom ctype macros with standard ones Replace the custom is_digit()/is_hex_digit() macros with isdigit()/isxdigit() from Additionaly remove unused macro is_alpha() from Signed-off-by: Tobias Klauser Cc: Jeff Garzik Signed-off-by: Andrew Morton Signed-off-by: Jeff Garzik --- include/linux/cyclomx.h | 2 -- include/linux/wanpipe.h | 9 --------- 2 files changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cyclomx.h b/include/linux/cyclomx.h index 04fa7dff079c..300d704bdb9a 100644 --- a/include/linux/cyclomx.h +++ b/include/linux/cyclomx.h @@ -37,8 +37,6 @@ #include #endif -#define is_digit(ch) (((ch)>=(unsigned)'0'&&(ch)<=(unsigned)'9')?1:0) - /* Adapter Data Space. * This structure is needed because we handle multiple cards, otherwise * static data would do it. diff --git a/include/linux/wanpipe.h b/include/linux/wanpipe.h index 167d956c492b..dae9860091dd 100644 --- a/include/linux/wanpipe.h +++ b/include/linux/wanpipe.h @@ -265,15 +265,6 @@ typedef struct { #include #include - -#define is_digit(ch) (((ch)>=(unsigned)'0'&&(ch)<=(unsigned)'9')?1:0) -#define is_alpha(ch) ((((ch)>=(unsigned)'a'&&(ch)<=(unsigned)'z')||\ - ((ch)>=(unsigned)'A'&&(ch)<=(unsigned)'Z'))?1:0) -#define is_hex_digit(ch) ((((ch)>=(unsigned)'0'&&(ch)<=(unsigned)'9')||\ - ((ch)>=(unsigned)'a'&&(ch)<=(unsigned)'f')||\ - ((ch)>=(unsigned)'A'&&(ch)<=(unsigned)'F'))?1:0) - - /****** Data Structures *****************************************************/ /* Adapter Data Space. -- cgit v1.2.3 From 7665a08928f241247afe8c76865cdbe4ef5489bf Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Fri, 9 Sep 2005 23:17:28 -0700 Subject: [PATCH] drivers/net/wan/: possible cleanups This patch contains possible cleanups including the following: - make needlessly global code static - #if 0 the following unused global function: - sdladrv.c: sdla_intde - remove the following unused global variable: - lmc_media.c: lmc_t1_cables - remove the following unneeded EXPORT_SYMBOL's: - cycx_drv.c: cycx_inten - sdladrv.c: sdla_inten - sdladrv.c: sdla_intde - sdladrv.c: sdla_intack - sdladrv.c: sdla_intr - syncppp.c: sppp_input - syncppp.c: sppp_change_mtu Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Jeff Garzik --- include/linux/cycx_drv.h | 1 - include/linux/sdladrv.h | 4 ---- 2 files changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cycx_drv.h b/include/linux/cycx_drv.h index 6621df86a748..12fe6b0bfcff 100644 --- a/include/linux/cycx_drv.h +++ b/include/linux/cycx_drv.h @@ -60,6 +60,5 @@ extern int cycx_peek(struct cycx_hw *hw, u32 addr, void *buf, u32 len); extern int cycx_poke(struct cycx_hw *hw, u32 addr, void *buf, u32 len); extern int cycx_exec(void __iomem *addr); -extern void cycx_inten(struct cycx_hw *hw); extern void cycx_intr(struct cycx_hw *hw); #endif /* _CYCX_DRV_H */ diff --git a/include/linux/sdladrv.h b/include/linux/sdladrv.h index 78f634007fc6..c85e103d5e7b 100644 --- a/include/linux/sdladrv.h +++ b/include/linux/sdladrv.h @@ -52,12 +52,8 @@ typedef struct sdlahw extern int sdla_setup (sdlahw_t* hw, void* sfm, unsigned len); extern int sdla_down (sdlahw_t* hw); -extern int sdla_inten (sdlahw_t* hw); -extern int sdla_intde (sdlahw_t* hw); -extern int sdla_intack (sdlahw_t* hw); extern void S514_intack (sdlahw_t* hw, u32 int_status); extern void read_S514_int_stat (sdlahw_t* hw, u32* int_status); -extern int sdla_intr (sdlahw_t* hw); extern int sdla_mapmem (sdlahw_t* hw, unsigned long addr); extern int sdla_peek (sdlahw_t* hw, unsigned long addr, void* buf, unsigned len); -- cgit v1.2.3 From 43ec6e95e4d8a73afc2405a44b955c380aeeb65a Mon Sep 17 00:00:00 2001 From: Dale Farnsworth Date: Tue, 23 Aug 2005 10:30:29 -0700 Subject: [PATCH] mii: Add test for GigE support Signed-off-by: Dale Farnsworth Signed-off-by: Jeff Garzik --- include/linux/mii.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mii.h b/include/linux/mii.h index 9b8d0476988a..68f5a0f392dd 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -158,6 +158,7 @@ extern int mii_link_ok (struct mii_if_info *mii); extern int mii_nway_restart (struct mii_if_info *mii); extern int mii_ethtool_gset(struct mii_if_info *mii, struct ethtool_cmd *ecmd); extern int mii_ethtool_sset(struct mii_if_info *mii, struct ethtool_cmd *ecmd); +extern int mii_check_gmii_support(struct mii_if_info *mii); extern void mii_check_link (struct mii_if_info *mii); extern unsigned int mii_check_media (struct mii_if_info *mii, unsigned int ok_to_print, -- cgit v1.2.3 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 v1.2.3 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 v1.2.3 From 3905ec4561b7b049e9c2e27311d072c356dbdee2 Mon Sep 17 00:00:00 2001 From: James Ketrenos Date: Wed, 21 Sep 2005 11:56:42 -0500 Subject: [PATCH] ieee80211: Added ieee80211_radiotap.h tree 383c59b2516a61f2683f02dfebbed0caf6ee5dc3 parent a04948f63fd96c4b875a43f78afad1a0874cc441 author Mike Kershaw 1124447833 -0500 committer James Ketrenos 1127313883 -0500 Added ieee80211_radiotap.h to enhance statistic reporting to user space from wireless drivers. Signed-off-by: Mike Kershaw Signed-off-by: James Ketrenos Signed-off-by: Jeff Garzik --- include/linux/if_arp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h index 0856548a2a08..a8b1a2071838 100644 --- a/include/linux/if_arp.h +++ b/include/linux/if_arp.h @@ -84,6 +84,7 @@ #define ARPHRD_IEEE802_TR 800 /* Magic type ident for TR */ #define ARPHRD_IEEE80211 801 /* IEEE 802.11 */ #define ARPHRD_IEEE80211_PRISM 802 /* IEEE 802.11 + Prism2 header */ +#define ARPHRD_IEEE80211_RADIOTAP 803 /* IEEE 802.11 + radiotap header */ #define ARPHRD_VOID 0xFFFF /* Void type, nothing is known */ #define ARPHRD_NONE 0xFFFE /* zero header length */ -- cgit v1.2.3 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 v1.2.3 From d305ef5d2a4e77bfa66160513f4a7494126a506b Mon Sep 17 00:00:00 2001 From: Daniel Ritz Date: Thu, 22 Sep 2005 00:47:24 -0700 Subject: [PATCH] driver core: add helper device_is_registered() add the helper and use it instead of open coding the klist_node_attached() check (which is a layering violation IMHO) idea by Alan Stern. Signed-off-by: Daniel Ritz Cc: Alan Stern Signed-off-by: Greg Kroah-Hartman Signed-off-by: Linus Torvalds --- include/linux/device.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 06e5d42f2c7b..95d607a48f06 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -317,6 +317,11 @@ dev_set_drvdata (struct device *dev, void *data) dev->driver_data = data; } +static inline int device_is_registered(struct device *dev) +{ + return klist_node_attached(&dev->knode_bus); +} + /* * High level routines for use by the bus drivers */ -- cgit v1.2.3 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 v1.2.3 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 v1.2.3 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 v1.2.3 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 v1.2.3 From 094bb20b9fcab3a1652a77741caba6b78097d622 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 11 Aug 2005 16:25:20 -0400 Subject: [PATCH] RPC: extract socket logic common to both client and server Clean-up: Move some code that is common to both RPC client- and server-side socket transports into its own source file, net/sunrpc/socklib.c. Test-plan: Compile kernel with CONFIG_NFS enabled. Millions of fsx operations over UDP, client and server. Connectathon over UDP. Version: Thu, 11 Aug 2005 16:03:09 -0400 Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 23448d0fb5bc..d8b7656bca41 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -161,6 +161,7 @@ typedef struct { typedef size_t (*skb_read_actor_t)(skb_reader_t *desc, void *to, size_t len); +extern int csum_partial_copy_to_xdr(struct xdr_buf *, struct sk_buff *); extern ssize_t xdr_partial_copy_from_skb(struct xdr_buf *, unsigned int, skb_reader_t *, skb_read_actor_t); -- cgit v1.2.3 From a246b0105bbd9a70a698f69baae2042996f2a0e9 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 11 Aug 2005 16:25:23 -0400 Subject: [PATCH] RPC: introduce client-side transport switch Move the bulk of client-side socket-specific code into a separate source file, net/sunrpc/xprtsock.c. Test-plan: Millions of fsx operations. Performance characterization such as "sio" or "iozone". Destructive testing (unplugging the network temporarily, server reboots). Connectathon with v2, v3, and v4. Version: Thu, 11 Aug 2005 16:03:38 -0400 Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 5 ----- include/linux/sunrpc/xprt.h | 38 +++++++++++++++++++++++++++++++------- 2 files changed, 31 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index d8b7656bca41..5da968729cf8 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -165,11 +165,6 @@ extern int csum_partial_copy_to_xdr(struct xdr_buf *, struct sk_buff *); extern ssize_t xdr_partial_copy_from_skb(struct xdr_buf *, unsigned int, skb_reader_t *, skb_read_actor_t); -struct socket; -struct sockaddr; -extern int xdr_sendpages(struct socket *, struct sockaddr *, int, - struct xdr_buf *, unsigned int, int); - extern int xdr_encode_word(struct xdr_buf *, int, u32); extern int xdr_decode_word(struct xdr_buf *, int, u32 *); diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index e618c1649814..d82b47ab73cb 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -59,7 +59,13 @@ extern unsigned int xprt_tcp_slot_table_entries; */ #define RPC_REESTABLISH_TIMEOUT (15*HZ) -/* RPC call and reply header size as number of 32bit words (verifier +/* + * RPC transport idle timeout. + */ +#define RPC_IDLE_DISCONNECT_TIMEOUT (5*60*HZ) + +/* + * RPC call and reply header size as number of 32bit words (verifier * size computed separately) */ #define RPC_CALLHDRSIZE 6 @@ -121,12 +127,19 @@ struct rpc_rqst { #define rq_svec rq_snd_buf.head #define rq_slen rq_snd_buf.len -#define XPRT_LAST_FRAG (1 << 0) -#define XPRT_COPY_RECM (1 << 1) -#define XPRT_COPY_XID (1 << 2) -#define XPRT_COPY_DATA (1 << 3) +struct rpc_task; +struct rpc_xprt; + +struct rpc_xprt_ops { + void (*set_buffer_size)(struct rpc_xprt *xprt); + void (*connect)(struct rpc_task *task); + int (*send_request)(struct rpc_task *task); + void (*close)(struct rpc_xprt *xprt); + void (*destroy)(struct rpc_xprt *xprt); +}; struct rpc_xprt { + struct rpc_xprt_ops * ops; /* transport methods */ struct socket * sock; /* BSD socket layer */ struct sock * inet; /* INET layer */ @@ -199,14 +212,22 @@ struct rpc_xprt { wait_queue_head_t cong_wait; }; +#define XPRT_LAST_FRAG (1 << 0) +#define XPRT_COPY_RECM (1 << 1) +#define XPRT_COPY_XID (1 << 2) +#define XPRT_COPY_DATA (1 << 3) + #ifdef __KERNEL__ struct rpc_xprt * xprt_create_proto(int proto, struct sockaddr_in *addr, struct rpc_timeout *toparms); +void xprt_disconnect(struct rpc_xprt *); int xprt_destroy(struct rpc_xprt *); void xprt_set_timeout(struct rpc_timeout *, unsigned int, unsigned long); - +struct rpc_rqst * xprt_lookup_rqst(struct rpc_xprt *, u32); +void xprt_complete_rqst(struct rpc_xprt *, + struct rpc_rqst *, int); void xprt_reserve(struct rpc_task *); int xprt_prepare_transmit(struct rpc_task *); void xprt_transmit(struct rpc_task *); @@ -214,7 +235,10 @@ void xprt_receive(struct rpc_task *); int xprt_adjust_timeout(struct rpc_rqst *req); void xprt_release(struct rpc_task *); void xprt_connect(struct rpc_task *); -void xprt_sock_setbufsize(struct rpc_xprt *); +int xs_setup_udp(struct rpc_xprt *, + struct rpc_timeout *); +int xs_setup_tcp(struct rpc_xprt *, + struct rpc_timeout *); #define XPRT_LOCKED 0 #define XPRT_CONNECT 1 -- cgit v1.2.3 From 9903cd1c27a1f30e8efea75e125be3b2002f7cb9 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 11 Aug 2005 16:25:26 -0400 Subject: [PATCH] RPC: transport switch function naming Introduce block header comments and a function naming convention to the socket transport implementation. Provide a debug setting for transports that is separate from RPCDBG_XPRT. Eliminate xprt_default_timeout(). Provide block comments for exposed interfaces in xprt.c, and eliminate the useless obvious comments. Convert printk's to dprintk's. Test-plan: Compile kernel with CONFIG_NFS enabled. Version: Thu, 11 Aug 2005 16:04:04 -0400 Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/debug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/debug.h b/include/linux/sunrpc/debug.h index eadb31e3c198..42d299747956 100644 --- a/include/linux/sunrpc/debug.h +++ b/include/linux/sunrpc/debug.h @@ -32,6 +32,7 @@ #define RPCDBG_AUTH 0x0010 #define RPCDBG_PMAP 0x0020 #define RPCDBG_SCHED 0x0040 +#define RPCDBG_TRANS 0x0080 #define RPCDBG_SVCSOCK 0x0100 #define RPCDBG_SVCDSP 0x0200 #define RPCDBG_MISC 0x0400 -- cgit v1.2.3 From 4a0f8c04f2ece949d54a0c4fd7490259cf23a58a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 11 Aug 2005 16:25:32 -0400 Subject: [PATCH] RPC: Rename sock_lock Clean-up: replace a name reference to sockets in the generic parts of the RPC client by renaming sock_lock in the rpc_xprt structure. Test-plan: Compile kernel with CONFIG_NFS enabled. Version: Thu, 11 Aug 2005 16:05:00 -0400 Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index d82b47ab73cb..c4f903f0e17c 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -198,7 +198,7 @@ struct rpc_xprt { /* * Send stuff */ - spinlock_t sock_lock; /* lock socket info */ + spinlock_t transport_lock; /* lock transport info */ spinlock_t xprt_lock; /* lock xprt info */ struct rpc_task * snd_task; /* Task blocked in send */ -- cgit v1.2.3 From 5dc07727f86b25851e95193a0c484ea21b531c47 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 11 Aug 2005 16:25:35 -0400 Subject: [PATCH] RPC: Rename xprt_lock Clean-up: Replace the xprt_lock with something more aptly named. This lock single-threads the XID and request slot reservation process. Test-plan: Compile kernel with CONFIG_NFS enabled. Version: Thu, 11 Aug 2005 16:05:26 -0400 Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index c4f903f0e17c..41ce296dded1 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -199,7 +199,7 @@ struct rpc_xprt { * Send stuff */ spinlock_t transport_lock; /* lock transport info */ - spinlock_t xprt_lock; /* lock xprt info */ + spinlock_t reserve_lock; /* lock slot table */ struct rpc_task * snd_task; /* Task blocked in send */ struct list_head recv; -- cgit v1.2.3 From 2226feb6bcd0e5e117a9be3ea3dd3ffc14f3e41e Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 11 Aug 2005 16:25:38 -0400 Subject: [PATCH] RPC: rename the sockstate field Clean-up: get rid of a name reference to sockets in the generic parts of the RPC client by renaming the sockstate field in the rpc_xprt structure. Test-plan: Compile kernel with CONFIG_NFS enabled. Version: Thu, 11 Aug 2005 16:05:53 -0400 Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 60 ++++++++++++++++++++++++++++++++++++--------- 1 file changed, 49 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 41ce296dded1..009a3bb4f997 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -163,7 +163,7 @@ struct rpc_xprt { struct list_head free; /* free slots */ struct rpc_rqst * slot; /* slot table storage */ unsigned int max_reqs; /* total slots */ - unsigned long sockstate; /* Socket state */ + unsigned long state; /* transport state */ unsigned char shutdown : 1, /* being shut down */ nocong : 1, /* no congestion control */ resvport : 1, /* use a reserved port */ @@ -240,16 +240,54 @@ int xs_setup_udp(struct rpc_xprt *, int xs_setup_tcp(struct rpc_xprt *, struct rpc_timeout *); -#define XPRT_LOCKED 0 -#define XPRT_CONNECT 1 -#define XPRT_CONNECTING 2 - -#define xprt_connected(xp) (test_bit(XPRT_CONNECT, &(xp)->sockstate)) -#define xprt_set_connected(xp) (set_bit(XPRT_CONNECT, &(xp)->sockstate)) -#define xprt_test_and_set_connected(xp) (test_and_set_bit(XPRT_CONNECT, &(xp)->sockstate)) -#define xprt_test_and_clear_connected(xp) \ - (test_and_clear_bit(XPRT_CONNECT, &(xp)->sockstate)) -#define xprt_clear_connected(xp) (clear_bit(XPRT_CONNECT, &(xp)->sockstate)) +/* + * Reserved bit positions in xprt->state + */ +#define XPRT_LOCKED (0) +#define XPRT_CONNECTED (1) +#define XPRT_CONNECTING (2) + +static inline void xprt_set_connected(struct rpc_xprt *xprt) +{ + set_bit(XPRT_CONNECTED, &xprt->state); +} + +static inline void xprt_clear_connected(struct rpc_xprt *xprt) +{ + clear_bit(XPRT_CONNECTED, &xprt->state); +} + +static inline int xprt_connected(struct rpc_xprt *xprt) +{ + return test_bit(XPRT_CONNECTED, &xprt->state); +} + +static inline int xprt_test_and_set_connected(struct rpc_xprt *xprt) +{ + return test_and_set_bit(XPRT_CONNECTED, &xprt->state); +} + +static inline int xprt_test_and_clear_connected(struct rpc_xprt *xprt) +{ + return test_and_clear_bit(XPRT_CONNECTED, &xprt->state); +} + +static inline void xprt_clear_connecting(struct rpc_xprt *xprt) +{ + smp_mb__before_clear_bit(); + clear_bit(XPRT_CONNECTING, &xprt->state); + smp_mb__after_clear_bit(); +} + +static inline int xprt_connecting(struct rpc_xprt *xprt) +{ + return test_bit(XPRT_CONNECTING, &xprt->state); +} + +static inline int xprt_test_and_set_connecting(struct rpc_xprt *xprt) +{ + return test_and_set_bit(XPRT_CONNECTING, &xprt->state); +} #endif /* __KERNEL__*/ -- cgit v1.2.3 From 44fbac2288dfed6f1963ac00bf922c3bcd779cd1 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 11 Aug 2005 16:25:44 -0400 Subject: [PATCH] RPC: Add helper for waking tasks pending on a transport Clean-up: remove only reference to xprt->pending from the socket transport implementation. This makes a cleaner interface for other transport implementations as well. Test-plan: Compile kernel with CONFIG_NFS enabled. Version: Thu, 11 Aug 2005 16:06:52 -0400 Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 009a3bb4f997..d5223993fca9 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -232,6 +232,7 @@ void xprt_reserve(struct rpc_task *); int xprt_prepare_transmit(struct rpc_task *); void xprt_transmit(struct rpc_task *); void xprt_receive(struct rpc_task *); +void xprt_wake_pending_tasks(struct rpc_xprt *, int); int xprt_adjust_timeout(struct rpc_rqst *req); void xprt_release(struct rpc_task *); void xprt_connect(struct rpc_task *); -- cgit v1.2.3 From 55aa4f58aa43dc9a51fb80010630d94b96053a2e Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 11 Aug 2005 16:25:47 -0400 Subject: [PATCH] RPC: client-side transport switch cleanup Clean-up: change some comments to reflect the realities of the new RPC transport switch mechanism. Get rid of unused xprt_receive() prototype. Also, organize function prototypes in xprt.h by usage and scope. Test-plan: Compile kernel with CONFIG_NFS enabled. Version: Thu, 11 Aug 2005 16:07:21 -0400 Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 61 ++++++++++++++++++++++++++------------------- 1 file changed, 35 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index d5223993fca9..bfbc492ae36d 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -1,5 +1,5 @@ /* - * linux/include/linux/sunrpc/clnt_xprt.h + * linux/include/linux/sunrpc/xprt.h * * Declarations for the RPC transport interface. * @@ -150,8 +150,8 @@ struct rpc_xprt { unsigned long cong; /* current congestion */ unsigned long cwnd; /* congestion window */ - unsigned int rcvsize, /* socket receive buffer size */ - sndsize; /* socket send buffer size */ + unsigned int rcvsize, /* transport rcv buffer size */ + sndsize; /* transport send buffer size */ size_t max_payload; /* largest RPC payload size, in bytes */ @@ -184,12 +184,12 @@ struct rpc_xprt { unsigned long tcp_copied, /* copied to request */ tcp_flags; /* - * Connection of sockets + * Connection of transports */ - struct work_struct sock_connect; + struct work_struct connect_worker; unsigned short port; /* - * Disconnection of idle sockets + * Disconnection of idle transports */ struct work_struct task_cleanup; struct timer_list timer; @@ -219,27 +219,36 @@ struct rpc_xprt { #ifdef __KERNEL__ -struct rpc_xprt * xprt_create_proto(int proto, struct sockaddr_in *addr, - struct rpc_timeout *toparms); -void xprt_disconnect(struct rpc_xprt *); -int xprt_destroy(struct rpc_xprt *); -void xprt_set_timeout(struct rpc_timeout *, unsigned int, - unsigned long); -struct rpc_rqst * xprt_lookup_rqst(struct rpc_xprt *, u32); -void xprt_complete_rqst(struct rpc_xprt *, - struct rpc_rqst *, int); -void xprt_reserve(struct rpc_task *); -int xprt_prepare_transmit(struct rpc_task *); -void xprt_transmit(struct rpc_task *); -void xprt_receive(struct rpc_task *); -void xprt_wake_pending_tasks(struct rpc_xprt *, int); +/* + * Transport operations used by ULPs + */ +struct rpc_xprt * xprt_create_proto(int proto, struct sockaddr_in *addr, struct rpc_timeout *to); +void xprt_set_timeout(struct rpc_timeout *to, unsigned int retr, unsigned long incr); + +/* + * Generic internal transport functions + */ +void xprt_connect(struct rpc_task *task); +void xprt_reserve(struct rpc_task *task); +int xprt_prepare_transmit(struct rpc_task *task); +void xprt_transmit(struct rpc_task *task); int xprt_adjust_timeout(struct rpc_rqst *req); -void xprt_release(struct rpc_task *); -void xprt_connect(struct rpc_task *); -int xs_setup_udp(struct rpc_xprt *, - struct rpc_timeout *); -int xs_setup_tcp(struct rpc_xprt *, - struct rpc_timeout *); +void xprt_release(struct rpc_task *task); +int xprt_destroy(struct rpc_xprt *xprt); + +/* + * Transport switch helper functions + */ +void xprt_wake_pending_tasks(struct rpc_xprt *xprt, int status); +struct rpc_rqst * xprt_lookup_rqst(struct rpc_xprt *xprt, u32 xid); +void xprt_complete_rqst(struct rpc_xprt *xprt, struct rpc_rqst *req, int copied); +void xprt_disconnect(struct rpc_xprt *xprt); + +/* + * Socket transport setup operations + */ +int xs_setup_udp(struct rpc_xprt *xprt, struct rpc_timeout *to); +int xs_setup_tcp(struct rpc_xprt *xprt, struct rpc_timeout *to); /* * Reserved bit positions in xprt->state -- cgit v1.2.3 From c7b2cae8a634015b72941ba2fc6c4bc9b8d3a129 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 11 Aug 2005 16:25:50 -0400 Subject: [PATCH] RPC: separate TCP and UDP write space callbacks Split the socket write space callback function into a TCP version and UDP version, eliminating one dependence on the "xprt->stream" variable. Keep the common pieces of this path in xprt.c so other transports can use it too. Test-plan: Write-intensive workload on a single mount point. Version: Thu, 11 Aug 2005 16:07:51 -0400 Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index bfbc492ae36d..e73174c7e450 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -240,6 +240,8 @@ int xprt_destroy(struct rpc_xprt *xprt); * Transport switch helper functions */ void xprt_wake_pending_tasks(struct rpc_xprt *xprt, int status); +void xprt_wait_for_buffer_space(struct rpc_task *task); +void xprt_write_space(struct rpc_xprt *xprt); struct rpc_rqst * xprt_lookup_rqst(struct rpc_xprt *xprt, u32 xid); void xprt_complete_rqst(struct rpc_xprt *xprt, struct rpc_rqst *req, int copied); void xprt_disconnect(struct rpc_xprt *xprt); -- cgit v1.2.3 From 808012fbb23a52ec59352445d2076d175ad4ab26 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 25 Aug 2005 16:25:49 -0700 Subject: [PATCH] RPC: skip over transport-specific heads automatically Add a generic mechanism for skipping over transport-specific headers when constructing an RPC request. This removes another "xprt->stream" dependency. Test-plan: Write-intensive workload on a single mount point (try both UDP and TCP). Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/msg_prot.h | 25 +++++++++++++++++++++++++ include/linux/sunrpc/xprt.h | 7 +++++++ 2 files changed, 32 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h index 15f115332389..f43f237360ae 100644 --- a/include/linux/sunrpc/msg_prot.h +++ b/include/linux/sunrpc/msg_prot.h @@ -76,5 +76,30 @@ enum rpc_auth_stat { #define RPC_MAXNETNAMELEN 256 +/* + * From RFC 1831: + * + * "A record is composed of one or more record fragments. A record + * fragment is a four-byte header followed by 0 to (2**31) - 1 bytes of + * fragment data. The bytes encode an unsigned binary number; as with + * XDR integers, the byte order is from highest to lowest. The number + * encodes two values -- a boolean which indicates whether the fragment + * is the last fragment of the record (bit value 1 implies the fragment + * is the last fragment) and a 31-bit unsigned binary value which is the + * length in bytes of the fragment's data. The boolean value is the + * highest-order bit of the header; the length is the 31 low-order bits. + * (Note that this record specification is NOT in XDR standard form!)" + * + * The Linux RPC client always sends its requests in a single record + * fragment, limiting the maximum payload size for stream transports to + * 2GB. + */ + +typedef u32 rpc_fraghdr; + +#define RPC_LAST_STREAM_FRAGMENT (1U << 31) +#define RPC_FRAGMENT_SIZE_MASK (~RPC_LAST_STREAM_FRAGMENT) +#define RPC_MAX_FRAGMENT_SIZE ((1U << 31) - 1) + #endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_MSGPROT_H_ */ diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index e73174c7e450..966c456a0f6d 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -155,6 +155,8 @@ struct rpc_xprt { size_t max_payload; /* largest RPC payload size, in bytes */ + unsigned int tsh_size; /* size of transport specific + header */ struct rpc_wait_queue sending; /* requests waiting to send */ struct rpc_wait_queue resend; /* requests waiting to resend */ @@ -236,6 +238,11 @@ int xprt_adjust_timeout(struct rpc_rqst *req); void xprt_release(struct rpc_task *task); int xprt_destroy(struct rpc_xprt *xprt); +static inline u32 *xprt_skip_transport_header(struct rpc_xprt *xprt, u32 *p) +{ + return p + xprt->tsh_size; +} + /* * Transport switch helper functions */ -- cgit v1.2.3 From 43118c29dea2b23798bd42a147015cceee7fa885 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 25 Aug 2005 16:25:49 -0700 Subject: [PATCH] RPC: get rid of xprt->stream Now we can fix up the last few places that use the "xprt->stream" variable, and get rid of it from the rpc_xprt structure. Test-plan: Destructive testing (unplugging the network temporarily). Connectathon with UDP and TCP. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 966c456a0f6d..c9477f022efb 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -168,8 +168,7 @@ struct rpc_xprt { unsigned long state; /* transport state */ unsigned char shutdown : 1, /* being shut down */ nocong : 1, /* no congestion control */ - resvport : 1, /* use a reserved port */ - stream : 1; /* TCP */ + resvport : 1; /* use a reserved port */ /* * XID -- cgit v1.2.3 From fe3aca290f17ae4978bd73d02aa4029f1c9c024c Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 25 Aug 2005 16:25:50 -0700 Subject: [PATCH] RPC: add API to set transport-specific timeouts Prepare the way to remove the "xprt->nocong" variable by adding a callout to the RPC client transport switch API to handle setting RPC retransmit timeouts. Add a pair of generic helper functions that provide the ability to set a simple fixed timeout, or to set a timeout based on the state of a round- trip estimator. Test-plan: Use WAN simulation to cause sporadic bursty packet loss. Look for significant regression in performance or client stability. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index c9477f022efb..ac08e99a81cb 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -134,6 +134,7 @@ struct rpc_xprt_ops { void (*set_buffer_size)(struct rpc_xprt *xprt); void (*connect)(struct rpc_task *task); int (*send_request)(struct rpc_task *task); + void (*set_retrans_timeout)(struct rpc_task *task); void (*close)(struct rpc_xprt *xprt); void (*destroy)(struct rpc_xprt *xprt); }; @@ -245,6 +246,8 @@ static inline u32 *xprt_skip_transport_header(struct rpc_xprt *xprt, u32 *p) /* * Transport switch helper functions */ +void xprt_set_retrans_timeout_def(struct rpc_task *task); +void xprt_set_retrans_timeout_rtt(struct rpc_task *task); void xprt_wake_pending_tasks(struct rpc_xprt *xprt, int status); void xprt_wait_for_buffer_space(struct rpc_task *task); void xprt_write_space(struct rpc_xprt *xprt); -- cgit v1.2.3 From 12a804698b29d040b7cdd92e8a44b0e75164dae9 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 25 Aug 2005 16:25:51 -0700 Subject: [PATCH] RPC: expose API for serializing access to RPC transports The next several patches introduce an API that allows transports to choose whether the RPC client provides congestion control or whether the transport itself provides it. The first method we abstract is the one that serializes access to the RPC transport to prevent the bytes from different requests from mingling together. This method provides proper request serialization and the opportunity to prevent new requests from being started because the transport is congested. The normal situation is for the transport to handle congestion control itself. Although NFS over UDP was first, it has been recognized after years of experience that having the transport provide congestion control is much better than doing it in the RPC client. Thus TCP, and probably every future transport implementation, will use the default method, xprt_lock_write, provided in xprt.c, which does not provide any kind of congestion control. UDP can continue using the xprt.c-provided Van Jacobson congestion avoidance implementation. Test-plan: Use WAN simulation to cause sporadic bursty packet loss. Look for significant regression in performance or client stability. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index ac08e99a81cb..eee1c6877851 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -132,6 +132,7 @@ struct rpc_xprt; struct rpc_xprt_ops { void (*set_buffer_size)(struct rpc_xprt *xprt); + int (*reserve_xprt)(struct rpc_task *task); void (*connect)(struct rpc_task *task); int (*send_request)(struct rpc_task *task); void (*set_retrans_timeout)(struct rpc_task *task); @@ -232,6 +233,8 @@ void xprt_set_timeout(struct rpc_timeout *to, unsigned int retr, unsigned long */ void xprt_connect(struct rpc_task *task); void xprt_reserve(struct rpc_task *task); +int xprt_reserve_xprt(struct rpc_task *task); +int xprt_reserve_xprt_cong(struct rpc_task *task); int xprt_prepare_transmit(struct rpc_task *task); void xprt_transmit(struct rpc_task *task); int xprt_adjust_timeout(struct rpc_rqst *req); -- cgit v1.2.3 From 49e9a89086b3cae784a4868ca852863e4f4ea3fe Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 25 Aug 2005 16:25:51 -0700 Subject: [PATCH] RPC: expose API for serializing access to RPC transports The next method we abstract is the one that releases a transport, allowing another task to have access to the transport. Again, one generic version of this is provided for transports that don't need the RPC client to perform congestion control, and one version is for transports that can use the original Van Jacobson implementation in xprt.c. Test-plan: Use WAN simulation to cause sporadic bursty packet loss. Look for significant regression in performance or client stability. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index eee1c6877851..86833b725bb5 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -133,6 +133,7 @@ struct rpc_xprt; struct rpc_xprt_ops { void (*set_buffer_size)(struct rpc_xprt *xprt); int (*reserve_xprt)(struct rpc_task *task); + void (*release_xprt)(struct rpc_xprt *xprt, struct rpc_task *task); void (*connect)(struct rpc_task *task); int (*send_request)(struct rpc_task *task); void (*set_retrans_timeout)(struct rpc_task *task); @@ -238,6 +239,8 @@ int xprt_reserve_xprt_cong(struct rpc_task *task); int xprt_prepare_transmit(struct rpc_task *task); void xprt_transmit(struct rpc_task *task); int xprt_adjust_timeout(struct rpc_rqst *req); +void xprt_release_xprt(struct rpc_xprt *xprt, struct rpc_task *task); +void xprt_release_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_release(struct rpc_task *task); int xprt_destroy(struct rpc_xprt *xprt); -- cgit v1.2.3 From 46c0ee8bc4ad3743de05e8b8b20201df44dcb6d3 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 25 Aug 2005 16:25:52 -0700 Subject: [PATCH] RPC: separate xprt_timer implementations Allow transports to hook the retransmit timer interrupt. Some transports calculate their congestion window here so that a retransmit timeout has immediate effect on the congestion window. Test-plan: Use WAN simulation to cause sporadic bursty packet loss. Look for significant regression in performance or client stability. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 86833b725bb5..443c3f984cf9 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -137,6 +137,7 @@ struct rpc_xprt_ops { void (*connect)(struct rpc_task *task); int (*send_request)(struct rpc_task *task); void (*set_retrans_timeout)(struct rpc_task *task); + void (*timer)(struct rpc_task *task); void (*close)(struct rpc_xprt *xprt); void (*destroy)(struct rpc_xprt *xprt); }; @@ -257,6 +258,7 @@ void xprt_set_retrans_timeout_rtt(struct rpc_task *task); void xprt_wake_pending_tasks(struct rpc_xprt *xprt, int status); void xprt_wait_for_buffer_space(struct rpc_task *task); void xprt_write_space(struct rpc_xprt *xprt); +void xprt_adjust_cwnd(struct rpc_task *task, int result); struct rpc_rqst * xprt_lookup_rqst(struct rpc_xprt *xprt, u32 xid); void xprt_complete_rqst(struct rpc_xprt *xprt, struct rpc_rqst *req, int copied); void xprt_disconnect(struct rpc_xprt *xprt); -- cgit v1.2.3 From 1570c1e41eabf6b7031f3e4322a2cf1cbe319fee Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 25 Aug 2005 16:25:52 -0700 Subject: [PATCH] RPC: add generic interface for adjusting the congestion window A new interface that allows transports to adjust their congestion window using the Van Jacobson implementation in xprt.c is provided. Test-plan: Use WAN simulation to cause sporadic bursty packet loss. Look for significant regression in performance or client stability. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 443c3f984cf9..2e48752d55d9 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -258,9 +258,10 @@ void xprt_set_retrans_timeout_rtt(struct rpc_task *task); void xprt_wake_pending_tasks(struct rpc_xprt *xprt, int status); void xprt_wait_for_buffer_space(struct rpc_task *task); void xprt_write_space(struct rpc_xprt *xprt); +void xprt_update_rtt(struct rpc_task *task); void xprt_adjust_cwnd(struct rpc_task *task, int result); struct rpc_rqst * xprt_lookup_rqst(struct rpc_xprt *xprt, u32 xid); -void xprt_complete_rqst(struct rpc_xprt *xprt, struct rpc_rqst *req, int copied); +void xprt_complete_rqst(struct rpc_task *task, int copied); void xprt_disconnect(struct rpc_xprt *xprt); /* -- cgit v1.2.3 From a58dd398f5db4f73d5c581069fd70a4304cc4f0a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 25 Aug 2005 16:25:53 -0700 Subject: [PATCH] RPC: add a release_rqst callout to the RPC transport switch The final place where congestion control state is adjusted is in xprt_release, where each request is finally released. Add a callout there to allow transports to perform additional processing when a request is about to be released. Test-plan: Use WAN simulation to cause sporadic bursty packet loss. Look for significant regression in performance or client stability. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 2e48752d55d9..64e77658fa30 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -138,6 +138,7 @@ struct rpc_xprt_ops { int (*send_request)(struct rpc_task *task); void (*set_retrans_timeout)(struct rpc_task *task); void (*timer)(struct rpc_task *task); + void (*release_request)(struct rpc_task *task); void (*close)(struct rpc_xprt *xprt); void (*destroy)(struct rpc_xprt *xprt); }; @@ -262,6 +263,7 @@ void xprt_update_rtt(struct rpc_task *task); void xprt_adjust_cwnd(struct rpc_task *task, int result); struct rpc_rqst * xprt_lookup_rqst(struct rpc_xprt *xprt, u32 xid); void xprt_complete_rqst(struct rpc_task *task, int copied); +void xprt_release_rqst_cong(struct rpc_task *task); void xprt_disconnect(struct rpc_xprt *xprt); /* -- cgit v1.2.3 From ed63c003701a314c4893c11eceb9d68f8f46c662 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 25 Aug 2005 16:25:53 -0700 Subject: [PATCH] RPC: remove xprt->nocong Get rid of the "xprt->nocong" variable. Test-plan: Use WAN simulation to cause sporadic bursty packet loss with UDP mounts. Look for significant regression in performance or client stability. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 64e77658fa30..559fb471f6f2 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -172,7 +172,6 @@ struct rpc_xprt { unsigned int max_reqs; /* total slots */ unsigned long state; /* transport state */ unsigned char shutdown : 1, /* being shut down */ - nocong : 1, /* no congestion control */ resvport : 1; /* use a reserved port */ /* -- cgit v1.2.3 From 555ee3af161b037865793bd4bebc06b58daafde6 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 25 Aug 2005 16:25:54 -0700 Subject: [PATCH] RPC: clean up after nocong was removed Clean-up: Move some macros that are specific to the Van Jacobson implementation into xprt.c. Get rid of the cong_wait field in rpc_xprt, which is no longer used. Get rid of xprt_clear_backlog. Test-plan: Compile with CONFIG_NFS enabled. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 559fb471f6f2..dcf0326bda01 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -15,20 +15,6 @@ #include #include -/* - * The transport code maintains an estimate on the maximum number of out- - * standing RPC requests, using a smoothed version of the congestion - * avoidance implemented in 44BSD. This is basically the Van Jacobson - * congestion algorithm: If a retransmit occurs, the congestion window is - * halved; otherwise, it is incremented by 1/cwnd when - * - * - a reply is received and - * - a full number of requests are outstanding and - * - the congestion window hasn't been updated recently. - * - * Upper procedures may check whether a request would block waiting for - * a free RPC slot by using the RPC_CONGESTED() macro. - */ extern unsigned int xprt_udp_slot_table_entries; extern unsigned int xprt_tcp_slot_table_entries; @@ -36,12 +22,6 @@ extern unsigned int xprt_tcp_slot_table_entries; #define RPC_DEF_SLOT_TABLE (16U) #define RPC_MAX_SLOT_TABLE (128U) -#define RPC_CWNDSHIFT (8U) -#define RPC_CWNDSCALE (1U << RPC_CWNDSHIFT) -#define RPC_INITCWND RPC_CWNDSCALE -#define RPC_MAXCWND(xprt) ((xprt)->max_reqs << RPC_CWNDSHIFT) -#define RPCXPRT_CONGESTED(xprt) ((xprt)->cong >= (xprt)->cwnd) - /* Default timeout values */ #define RPC_MAX_UDP_TIMEOUT (60*HZ) #define RPC_MAX_TCP_TIMEOUT (600*HZ) @@ -213,8 +193,6 @@ struct rpc_xprt { void (*old_data_ready)(struct sock *, int); void (*old_state_change)(struct sock *); void (*old_write_space)(struct sock *); - - wait_queue_head_t cong_wait; }; #define XPRT_LAST_FRAG (1 << 0) -- cgit v1.2.3 From 529b33c6db0120126b1381faa51406dc463acdc9 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 25 Aug 2005 16:25:54 -0700 Subject: [PATCH] RPC: allow RPC client's port range to be adjustable Select an RPC client source port between 650 and 1023 instead of between 1 and 800. The old range conflicts with a number of network services. Provide sysctls to allow admins to select a different port range. Note that this doesn't affect user-level RPC library behavior, which still uses 1 to 800. Based on a suggestion by Olaf Kirch . Test-plan: Repeated mount and unmount. Destructive testing. Idle timeouts. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/debug.h | 2 ++ include/linux/sunrpc/xprt.h | 17 ++++++++++++++--- 2 files changed, 16 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/debug.h b/include/linux/sunrpc/debug.h index 42d299747956..1a42d902bc11 100644 --- a/include/linux/sunrpc/debug.h +++ b/include/linux/sunrpc/debug.h @@ -95,6 +95,8 @@ enum { CTL_NLMDEBUG, CTL_SLOTTABLE_UDP, CTL_SLOTTABLE_TCP, + CTL_MIN_RESVPORT, + CTL_MAX_RESVPORT, }; #endif /* _LINUX_SUNRPC_DEBUG_H_ */ diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index dcf0326bda01..9d9266cf8a36 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -51,6 +51,17 @@ extern unsigned int xprt_tcp_slot_table_entries; #define RPC_CALLHDRSIZE 6 #define RPC_REPHDRSIZE 4 +/* + * Parameters for choosing a free port + */ +extern unsigned int xprt_min_resvport; +extern unsigned int xprt_max_resvport; + +#define RPC_MIN_RESVPORT (1U) +#define RPC_MAX_RESVPORT (65535U) +#define RPC_DEF_MIN_RESVPORT (650U) +#define RPC_DEF_MAX_RESVPORT (1023U) + /* * This describes a timeout strategy */ @@ -62,6 +73,9 @@ struct rpc_timeout { unsigned char to_exponential; }; +struct rpc_task; +struct rpc_xprt; + /* * This describes a complete RPC request */ @@ -107,9 +121,6 @@ struct rpc_rqst { #define rq_svec rq_snd_buf.head #define rq_slen rq_snd_buf.len -struct rpc_task; -struct rpc_xprt; - struct rpc_xprt_ops { void (*set_buffer_size)(struct rpc_xprt *xprt); int (*reserve_xprt)(struct rpc_task *task); -- cgit v1.2.3 From 03bf4b707eee06706c9db343dd5c905b7ee47ed2 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 25 Aug 2005 16:25:55 -0700 Subject: [PATCH] RPC: parametrize various transport connect timeouts Each transport implementation can now set unique bind, connect, reestablishment, and idle timeout values. These are variables, allowing the values to be modified dynamically. This permits exponential backoff of any of these values, for instance. As an example, we implement exponential backoff for the connection reestablishment timeout. Test-plan: Destructive testing (unplugging the network temporarily). Connectathon with UDP and TCP. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 4 ++++ include/linux/sunrpc/xprt.h | 29 ++++++----------------------- 2 files changed, 10 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 9a6047ff1b25..7bac2785c6e4 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -41,6 +41,10 @@ #define NFS_MAX_FILE_IO_BUFFER_SIZE 32768 #define NFS_DEF_FILE_IO_BUFFER_SIZE 4096 +/* Default timeout values */ +#define NFS_MAX_UDP_TIMEOUT (60*HZ) +#define NFS_MAX_TCP_TIMEOUT (600*HZ) + /* * superblock magic number for NFS */ diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 9d9266cf8a36..2543adf18551 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -22,28 +22,6 @@ extern unsigned int xprt_tcp_slot_table_entries; #define RPC_DEF_SLOT_TABLE (16U) #define RPC_MAX_SLOT_TABLE (128U) -/* Default timeout values */ -#define RPC_MAX_UDP_TIMEOUT (60*HZ) -#define RPC_MAX_TCP_TIMEOUT (600*HZ) - -/* - * Wait duration for an RPC TCP connection to be established. Solaris - * NFS over TCP uses 60 seconds, for example, which is in line with how - * long a server takes to reboot. - */ -#define RPC_CONNECT_TIMEOUT (60*HZ) - -/* - * Delay an arbitrary number of seconds before attempting to reconnect - * after an error. - */ -#define RPC_REESTABLISH_TIMEOUT (15*HZ) - -/* - * RPC transport idle timeout. - */ -#define RPC_IDLE_DISCONNECT_TIMEOUT (5*60*HZ) - /* * RPC call and reply header size as number of 32bit words (verifier * size computed separately) @@ -182,14 +160,19 @@ struct rpc_xprt { /* * Connection of transports */ + unsigned long connect_timeout, + bind_timeout, + reestablish_timeout; struct work_struct connect_worker; unsigned short port; + /* * Disconnection of idle transports */ struct work_struct task_cleanup; struct timer_list timer; - unsigned long last_used; + unsigned long last_used, + idle_timeout; /* * Send stuff -- cgit v1.2.3 From 470056c288334eb0b37be26c9ff8aee37ed1cc7a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 25 Aug 2005 16:25:56 -0700 Subject: [PATCH] RPC: rationalize set_buffer_size In fact, ->set_buffer_size should be completely functionless for non-UDP. Test-plan: Check socket buffer size on UDP sockets over time. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 2543adf18551..99cad3ead81d 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -100,7 +100,7 @@ struct rpc_rqst { #define rq_slen rq_snd_buf.len struct rpc_xprt_ops { - void (*set_buffer_size)(struct rpc_xprt *xprt); + void (*set_buffer_size)(struct rpc_xprt *xprt, size_t sndsize, size_t rcvsize); int (*reserve_xprt)(struct rpc_task *task); void (*release_xprt)(struct rpc_xprt *xprt, struct rpc_task *task); void (*connect)(struct rpc_task *task); @@ -124,7 +124,7 @@ struct rpc_xprt { unsigned long cong; /* current congestion */ unsigned long cwnd; /* congestion window */ - unsigned int rcvsize, /* transport rcv buffer size */ + size_t rcvsize, /* transport rcv buffer size */ sndsize; /* transport send buffer size */ size_t max_payload; /* largest RPC payload size, -- cgit v1.2.3 From 278c995c8a153bb2a9bc427e931cfb9c8034c9d7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 24 Jul 2005 23:53:01 +0100 Subject: [PATCH] RPC,NFS: new rpc_pipefs patch Currently rpc_mkdir/rpc_rmdir and rpc_mkpipe/mk_unlink have an API that's a little unfortunate. They take a path relative to the rpc_pipefs root and thus need to perform a full lookup. If you look at debugfs or usbfs they always store the dentry for directories they created and thus can pass in a dentry + single pathname component pair into their equivalents of the above functions. And in fact rpc_pipefs actually stores a dentry for all but one component so this change not only simplifies the core rpc_pipe code but also the callers. Unfortuntately this code path is only used by the NFS4 idmapper and AUTH_GSSAPI for which I don't have a test enviroment. Could someone give it a spin? It's the last bit needed before we can rework the lookup_hash API Signed-off-by: Christoph Hellwig Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 2 +- include/linux/sunrpc/rpc_pipe_fs.h | 9 +++++---- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index ab151bbb66df..b5b51c196690 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -59,7 +59,7 @@ struct rpc_clnt { int cl_nodelen; /* nodename length */ char cl_nodename[UNX_MAXNODENAME]; - char cl_pathname[30];/* Path in rpc_pipe_fs */ + struct dentry * __cl_parent_dentry; struct dentry * cl_dentry; /* inode */ struct rpc_clnt * cl_parent; /* Points to parent of clones */ struct rpc_rtt cl_rtt_default; diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h index 63929349571f..63878d05c9a9 100644 --- a/include/linux/sunrpc/rpc_pipe_fs.h +++ b/include/linux/sunrpc/rpc_pipe_fs.h @@ -41,10 +41,11 @@ RPC_I(struct inode *inode) extern int rpc_queue_upcall(struct inode *, struct rpc_pipe_msg *); -extern struct dentry *rpc_mkdir(char *, struct rpc_clnt *); -extern int rpc_rmdir(char *); -extern struct dentry *rpc_mkpipe(char *, void *, struct rpc_pipe_ops *, int flags); -extern int rpc_unlink(char *); +extern struct dentry *rpc_mkdir(struct dentry *, char *, struct rpc_clnt *); +extern void rpc_rmdir(struct dentry *); +extern struct dentry *rpc_mkpipe(struct dentry *, char *, void *, + struct rpc_pipe_ops *, int flags); +extern void rpc_unlink(struct dentry *); #endif #endif -- cgit v1.2.3 From f134585a7343d71f9be7f0cf97e2145f21dd10c6 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 23 Sep 2005 11:08:25 -0400 Subject: Revert "[PATCH] RPC,NFS: new rpc_pipefs patch" This reverts 17f4e6febca160a9f9dd4bdece9784577a2f4524 commit. --- include/linux/sunrpc/clnt.h | 2 +- include/linux/sunrpc/rpc_pipe_fs.h | 9 ++++----- 2 files changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index b5b51c196690..ab151bbb66df 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -59,7 +59,7 @@ struct rpc_clnt { int cl_nodelen; /* nodename length */ char cl_nodename[UNX_MAXNODENAME]; - struct dentry * __cl_parent_dentry; + char cl_pathname[30];/* Path in rpc_pipe_fs */ struct dentry * cl_dentry; /* inode */ struct rpc_clnt * cl_parent; /* Points to parent of clones */ struct rpc_rtt cl_rtt_default; diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h index 63878d05c9a9..63929349571f 100644 --- a/include/linux/sunrpc/rpc_pipe_fs.h +++ b/include/linux/sunrpc/rpc_pipe_fs.h @@ -41,11 +41,10 @@ RPC_I(struct inode *inode) extern int rpc_queue_upcall(struct inode *, struct rpc_pipe_msg *); -extern struct dentry *rpc_mkdir(struct dentry *, char *, struct rpc_clnt *); -extern void rpc_rmdir(struct dentry *); -extern struct dentry *rpc_mkpipe(struct dentry *, char *, void *, - struct rpc_pipe_ops *, int flags); -extern void rpc_unlink(struct dentry *); +extern struct dentry *rpc_mkdir(char *, struct rpc_clnt *); +extern int rpc_rmdir(char *); +extern struct dentry *rpc_mkpipe(char *, void *, struct rpc_pipe_ops *, int flags); +extern int rpc_unlink(char *); #endif #endif -- cgit v1.2.3 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 v1.2.3 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 v1.2.3 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 v1.2.3 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 v1.2.3 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 v1.2.3 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 v1.2.3 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 v1.2.3 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 v1.2.3 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 v1.2.3 From 14be71f4c5c5ad1e222c5202ee6d234e9c8828b7 Mon Sep 17 00:00:00 2001 From: Albert Lee Date: Tue, 27 Sep 2005 17:36:35 +0800 Subject: [PATCH] libata: rename host states Changes: s/PIO_ST_/HSM_ST_/ and s/pio_task_state/hsm_task_state/. Signed-off-by: Albert Lee Signed-off-by: Jeff Garzik --- include/linux/libata.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index ceee1fc42c60..bb2d916bce44 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -156,15 +156,15 @@ enum { ATA_SHIFT_PIO = 11, }; -enum pio_task_states { - PIO_ST_UNKNOWN, - PIO_ST_IDLE, - PIO_ST_POLL, - PIO_ST_TMOUT, - PIO_ST, - PIO_ST_LAST, - PIO_ST_LAST_POLL, - PIO_ST_ERR, +enum hsm_task_states { + HSM_ST_UNKNOWN, + HSM_ST_IDLE, + HSM_ST_POLL, + HSM_ST_TMOUT, + HSM_ST, + HSM_ST_LAST, + HSM_ST_LAST_POLL, + HSM_ST_ERR, }; /* forward declarations */ @@ -319,7 +319,7 @@ struct ata_port { struct work_struct packet_task; struct work_struct pio_task; - unsigned int pio_task_state; + unsigned int hsm_task_state; unsigned long pio_task_timeout; void *private_data; -- cgit v1.2.3 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 v1.2.3 From b4b52db71529bbe46da914eda772fb574914c94d Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Mon, 26 Sep 2005 12:48:41 +0100 Subject: [PATCH] ata: re-order speeds sensibly. Signed-off-by: Jeff Garzik --- include/linux/ata.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index 85169ea9eb01..ecb7346d0c16 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -147,14 +147,14 @@ enum { XFER_MW_DMA_2 = 0x22, XFER_MW_DMA_1 = 0x21, XFER_MW_DMA_0 = 0x20, + XFER_SW_DMA_2 = 0x12, + XFER_SW_DMA_1 = 0x11, + XFER_SW_DMA_0 = 0x10, XFER_PIO_4 = 0x0C, XFER_PIO_3 = 0x0B, XFER_PIO_2 = 0x0A, XFER_PIO_1 = 0x09, XFER_PIO_0 = 0x08, - XFER_SW_DMA_2 = 0x12, - XFER_SW_DMA_1 = 0x11, - XFER_SW_DMA_0 = 0x10, XFER_PIO_SLOW = 0x00, /* ATAPI stuff */ -- cgit v1.2.3 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 v1.2.3 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 v1.2.3 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 v1.2.3 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 v1.2.3 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 v1.2.3 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 v1.2.3 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 v1.2.3 From 47a8659380d40d5c0786ddb62a89b3f7f1392430 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Tue, 4 Oct 2005 08:09:19 -0400 Subject: libata: bitmask based pci init functions for one or two ports This redoes the n_ports logic I proposed before as a bitmask. ata_pci_init_native_mode is now used with a mask allowing for mixed mode stuff later on. ata_pci_init_legacy_port is called with port number and does one port now not two. Instead it is called twice by the ata init logic which cleans both of them up. There are stil limits in the original code left over - IRQ/port mapping for legacy mode should be arch specific values - You can have one legacy mode IDE adapter per PCI root bridge on some systems - Doesn't handle mixed mode devices yet (but is now a lot closer to it) --- include/linux/libata.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 4739a75b983d..4d45179872cc 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -155,6 +155,10 @@ enum { ATA_SHIFT_UDMA = 0, ATA_SHIFT_MWDMA = 8, ATA_SHIFT_PIO = 11, + + /* Masks for port functions */ + ATA_PORT_PRIMARY = (1 << 0), + ATA_PORT_SECONDARY = (1 << 1), }; enum hsm_task_states { @@ -458,7 +462,7 @@ struct pci_bits { extern void ata_pci_host_stop (struct ata_host_set *host_set); extern struct ata_probe_ent * -ata_pci_init_native_mode(struct pci_dev *pdev, struct ata_port_info **port); +ata_pci_init_native_mode(struct pci_dev *pdev, struct ata_port_info **port, int portmask); extern int pci_test_config_bits(struct pci_dev *pdev, struct pci_bits *bits); #endif /* CONFIG_PCI */ -- cgit v1.2.3 From ce0fe7e70a0ad11097a3773e9f3f0de3d859edf0 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 4 Oct 2005 17:43:06 +0100 Subject: [PATCH] bfs endianness annotations Signed-off-by: Alexey Dobriyan Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/bfs_fs.h | 42 +++++++++++++++++++++--------------------- 1 file changed, 21 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bfs_fs.h b/include/linux/bfs_fs.h index c1237aa92e38..8ed6dfdcd783 100644 --- a/include/linux/bfs_fs.h +++ b/include/linux/bfs_fs.h @@ -20,19 +20,19 @@ /* BFS inode layout on disk */ struct bfs_inode { - __u16 i_ino; + __le16 i_ino; __u16 i_unused; - __u32 i_sblock; - __u32 i_eblock; - __u32 i_eoffset; - __u32 i_vtype; - __u32 i_mode; - __s32 i_uid; - __s32 i_gid; - __u32 i_nlink; - __u32 i_atime; - __u32 i_mtime; - __u32 i_ctime; + __le32 i_sblock; + __le32 i_eblock; + __le32 i_eoffset; + __le32 i_vtype; + __le32 i_mode; + __le32 i_uid; + __le32 i_gid; + __le32 i_nlink; + __le32 i_atime; + __le32 i_mtime; + __le32 i_ctime; __u32 i_padding[4]; }; @@ -41,17 +41,17 @@ struct bfs_inode { #define BFS_DIRS_PER_BLOCK 32 struct bfs_dirent { - __u16 ino; + __le16 ino; char name[BFS_NAMELEN]; }; /* BFS superblock layout on disk */ struct bfs_super_block { - __u32 s_magic; - __u32 s_start; - __u32 s_end; - __s32 s_from; - __s32 s_to; + __le32 s_magic; + __le32 s_start; + __le32 s_end; + __le32 s_from; + __le32 s_to; __s32 s_bfrom; __s32 s_bto; char s_fsname[6]; @@ -66,15 +66,15 @@ struct bfs_super_block { #define BFS_INO2OFF(ino) \ ((__u32)(((ino) - BFS_ROOT_INO) * sizeof(struct bfs_inode)) + BFS_BSIZE) #define BFS_NZFILESIZE(ip) \ - ((cpu_to_le32((ip)->i_eoffset) + 1) - cpu_to_le32((ip)->i_sblock) * BFS_BSIZE) + ((le32_to_cpu((ip)->i_eoffset) + 1) - le32_to_cpu((ip)->i_sblock) * BFS_BSIZE) #define BFS_FILESIZE(ip) \ ((ip)->i_sblock == 0 ? 0 : BFS_NZFILESIZE(ip)) #define BFS_FILEBLOCKS(ip) \ - ((ip)->i_sblock == 0 ? 0 : (cpu_to_le32((ip)->i_eblock) + 1) - cpu_to_le32((ip)->i_sblock)) + ((ip)->i_sblock == 0 ? 0 : (le32_to_cpu((ip)->i_eblock) + 1) - le32_to_cpu((ip)->i_sblock)) #define BFS_UNCLEAN(bfs_sb, sb) \ - ((cpu_to_le32(bfs_sb->s_from) != -1) && (cpu_to_le32(bfs_sb->s_to) != -1) && !(sb->s_flags & MS_RDONLY)) + ((le32_to_cpu(bfs_sb->s_from) != -1) && (le32_to_cpu(bfs_sb->s_to) != -1) && !(sb->s_flags & MS_RDONLY)) #endif /* _LINUX_BFS_FS_H */ -- cgit v1.2.3 From 7b5b3f3d826ea87c224c66de9c95c09e7f110ecd Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 4 Oct 2005 22:38:44 -0700 Subject: [ATM]: fix sparse gfp nocast warnings Fix implicit nocast warnings in atm code: net/atm/atm_misc.c:35:44: warning: implicit cast to nocast type drivers/atm/fore200e.c:183:33: warning: implicit cast to nocast type Also use kzalloc() instead of kmalloc(). Signed-off-by: Randy Dunlap Signed-off-by: David S. Miller --- include/linux/atmdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h index 9f374cfa1b05..f1fd849e5535 100644 --- a/include/linux/atmdev.h +++ b/include/linux/atmdev.h @@ -457,7 +457,7 @@ static inline void atm_dev_put(struct atm_dev *dev) int atm_charge(struct atm_vcc *vcc,int truesize); struct sk_buff *atm_alloc_charge(struct atm_vcc *vcc,int pdu_size, - int gfp_flags); + unsigned int __nocast gfp_flags); int atm_pcr_goal(struct atm_trafprm *tp); void vcc_release_async(struct atm_vcc *vcc, int reply); -- cgit v1.2.3 From 17b698856328a42d5874ac87640e2cd84a824eef Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 4 Oct 2005 22:41:16 -0700 Subject: [CONNECTOR]: fix sparse gfp nocast warnings Fix implicit nocast warnings in connector code: drivers/connector/connector.c:102:24: warning: implicit cast to nocast type drivers/connector/connector.c:114:45: warning: implicit cast to nocast type Signed-off-by: Randy Dunlap Signed-off-by: David S. Miller --- include/linux/connector.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/connector.h b/include/linux/connector.h index 86d4b0a81713..96582c9911ac 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -149,7 +149,7 @@ struct cn_dev { 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_netlink_send(struct cn_msg *, u32, unsigned int __nocast); 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); -- cgit v1.2.3 From 3d2aef668920e8d93b77f145f8f647f62abe75db Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 4 Oct 2005 22:45:14 -0700 Subject: [TEXTSEARCH]: fix sparse gfp nocast warnings Fix nocast sparse warnings: include/linux/textsearch.h:165:57: warning: implicit cast to nocast type Signed-off-by: Randy Dunlap Signed-off-by: David S. Miller --- include/linux/textsearch.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/textsearch.h b/include/linux/textsearch.h index 941f45ac117a..1a4990e448e9 100644 --- a/include/linux/textsearch.h +++ b/include/linux/textsearch.h @@ -158,7 +158,8 @@ extern unsigned int textsearch_find_continuous(struct ts_config *, #define TS_PRIV_ALIGNTO 8 #define TS_PRIV_ALIGN(len) (((len) + TS_PRIV_ALIGNTO-1) & ~(TS_PRIV_ALIGNTO-1)) -static inline struct ts_config *alloc_ts_config(size_t payload, int gfp_mask) +static inline struct ts_config *alloc_ts_config(size_t payload, + unsigned int __nocast gfp_mask) { struct ts_config *conf; -- cgit v1.2.3 From 67846b30171cc4d706125f630193a76a26bb334a Mon Sep 17 00:00:00 2001 From: Jeff Garzik Date: Wed, 5 Oct 2005 02:58:32 -0400 Subject: libata: add ata_ratelimit(), use it in AHCI driver irq handler --- include/linux/libata.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 4d45179872cc..7929cfc9318d 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -410,6 +410,8 @@ extern int ata_scsi_queuecmd(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmn extern int ata_scsi_error(struct Scsi_Host *host); extern int ata_scsi_release(struct Scsi_Host *host); extern unsigned int ata_host_intr(struct ata_port *ap, struct ata_queued_cmd *qc); +extern int ata_ratelimit(void); + /* * Default driver ops implementations */ -- cgit v1.2.3 From 0f21ba7cc3320d33459ecb3f538f1a42040c29cd Mon Sep 17 00:00:00 2001 From: Eric Kinzie Date: Thu, 6 Oct 2005 22:19:28 -0700 Subject: [ATM]: add support for LECS addresses learned from network From: Eric Kinzie Signed-off-by: Chas Williams Signed-off-by: David S. Miller --- include/linux/atmdev.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h index f1fd849e5535..aca9b344bd35 100644 --- a/include/linux/atmdev.h +++ b/include/linux/atmdev.h @@ -76,6 +76,13 @@ struct atm_dev_stats { /* set interface ESI */ #define ATM_SETESIF _IOW('a',ATMIOC_ITF+13,struct atmif_sioc) /* force interface ESI */ +#define ATM_ADDLECSADDR _IOW('a', ATMIOC_ITF+14, struct atmif_sioc) + /* register a LECS address */ +#define ATM_DELLECSADDR _IOW('a', ATMIOC_ITF+15, struct atmif_sioc) + /* unregister a LECS address */ +#define ATM_GETLECSADDR _IOW('a', ATMIOC_ITF+16, struct atmif_sioc) + /* retrieve LECS address(es) */ + #define ATM_GETSTAT _IOW('a',ATMIOC_SARCOM+0,struct atmif_sioc) /* get AAL layer statistics */ #define ATM_GETSTATZ _IOW('a',ATMIOC_SARCOM+1,struct atmif_sioc) @@ -328,6 +335,8 @@ struct atm_dev_addr { struct list_head entry; /* next address */ }; +enum atm_addr_type_t { ATM_ADDR_LOCAL, ATM_ADDR_LECS }; + struct atm_dev { const struct atmdev_ops *ops; /* device operations; NULL if unused */ const struct atmphy_ops *phy; /* PHY operations, may be undefined */ @@ -338,6 +347,7 @@ struct atm_dev { void *phy_data; /* private PHY date */ unsigned long flags; /* device flags (ATM_DF_*) */ struct list_head local; /* local ATM addresses */ + struct list_head lecs; /* LECS ATM addresses learned via ILMI */ unsigned char esi[ESI_LEN]; /* ESI ("MAC" addr) */ struct atm_cirange ci_range; /* VPI/VCI range */ struct k_atm_dev_stats stats; /* statistics */ -- cgit v1.2.3 From 468ed2b0c85ec4310b429e60358213b6d077289e Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 7 Oct 2005 15:07:38 +0100 Subject: [PATCH] Keys: Split key permissions checking into a .c file The attached patch splits key permissions checking out of key-ui.h and moves it into a .c file. It's quite large and called quite a lot, and it's about to get bigger with the addition of LSM support for keys... key_any_permission() is also discarded as it's no longer used. Signed-Off-By: David Howells Signed-off-by: Linus Torvalds --- include/linux/key-ui.h | 91 +++----------------------------------------------- 1 file changed, 5 insertions(+), 86 deletions(-) (limited to 'include/linux') diff --git a/include/linux/key-ui.h b/include/linux/key-ui.h index 918c34a8347e..7a2e332067c3 100644 --- a/include/linux/key-ui.h +++ b/include/linux/key-ui.h @@ -38,97 +38,16 @@ struct keyring_list { struct key *keys[0]; }; - /* * check to see whether permission is granted to use a key in the desired way */ -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 (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 && - in_group_p(key->gid) - ) - kperm = key->perm >> 8; - else - kperm = key->perm; - - kperm = kperm & perm & KEY_ALL; - - return kperm == 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 key_ref_t key_ref, key_perm_t perm) -{ - struct key *key = key_ref_to_ptr(key_ref); - key_perm_t kperm; - - 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 && - in_group_p(key->gid) - ) - kperm = key->perm >> 8; - else - kperm = key->perm; +extern int key_task_permission(const key_ref_t key_ref, + struct task_struct *context, + key_perm_t perm); - kperm = kperm & perm & KEY_ALL; - - return kperm != 0; -} - -static inline int key_task_groups_search(struct task_struct *tsk, gid_t gid) -{ - int ret; - - task_lock(tsk); - ret = groups_search(tsk->group_info, gid); - task_unlock(tsk); - return ret; -} - -static inline int key_task_permission(const key_ref_t key_ref, - struct task_struct *context, - 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 (is_key_possessed(key_ref)) { - kperm = key->perm >> 24; - } - else if (key->uid == context->fsuid) { - kperm = key->perm >> 16; - } - else if (key->gid != -1 && - key->perm & KEY_GRP_ALL && ( - key->gid == context->fsgid || - key_task_groups_search(context, key->gid) - ) - ) { - kperm = key->perm >> 8; - } - else { - kperm = key->perm; - } - - kperm = kperm & perm & KEY_ALL; - - return kperm == perm; - + return key_task_permission(key_ref, current, perm); } extern key_ref_t lookup_user_key(struct task_struct *context, -- cgit v1.2.3 From dd0fc66fb33cd610bc1a5db8a5e232d34879b4d7 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 7 Oct 2005 07:46:04 +0100 Subject: [PATCH] gfp flags annotations - part 1 - added typedef unsigned int __nocast gfp_t; - replaced __nocast uses for gfp flags with gfp_t - it gives exactly the same warnings as far as sparse is concerned, doesn't change generated code (from gcc point of view we replaced unsigned int with typedef) and documents what's going on far better. Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/atmdev.h | 2 +- include/linux/bio.h | 6 +++--- include/linux/buffer_head.h | 2 +- include/linux/connector.h | 2 +- include/linux/cpuset.h | 5 ++--- include/linux/dmapool.h | 2 +- include/linux/gfp.h | 14 +++++++------- include/linux/jbd.h | 2 +- include/linux/kfifo.h | 4 ++-- include/linux/mempool.h | 9 ++++----- include/linux/netlink.h | 2 +- include/linux/pagemap.h | 2 +- include/linux/posix_acl.h | 6 +++--- include/linux/radix-tree.h | 2 +- include/linux/security.h | 6 ++---- include/linux/skbuff.h | 28 ++++++++++++++-------------- include/linux/slab.h | 19 +++++++++---------- include/linux/string.h | 2 +- include/linux/swap.h | 2 +- include/linux/textsearch.h | 2 +- include/linux/types.h | 4 ++++ include/linux/vmalloc.h | 4 ++-- 22 files changed, 63 insertions(+), 64 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h index aca9b344bd35..e7d0593bb576 100644 --- a/include/linux/atmdev.h +++ b/include/linux/atmdev.h @@ -467,7 +467,7 @@ static inline void atm_dev_put(struct atm_dev *dev) int atm_charge(struct atm_vcc *vcc,int truesize); struct sk_buff *atm_alloc_charge(struct atm_vcc *vcc,int pdu_size, - unsigned int __nocast gfp_flags); + gfp_t gfp_flags); int atm_pcr_goal(struct atm_trafprm *tp); void vcc_release_async(struct atm_vcc *vcc, int reply); diff --git a/include/linux/bio.h b/include/linux/bio.h index 6e1c79c8b6bf..3344b4e8e43a 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -276,8 +276,8 @@ extern void bio_pair_release(struct bio_pair *dbio); extern struct bio_set *bioset_create(int, int, int); extern void bioset_free(struct bio_set *); -extern struct bio *bio_alloc(unsigned int __nocast, int); -extern struct bio *bio_alloc_bioset(unsigned int __nocast, int, struct bio_set *); +extern struct bio *bio_alloc(gfp_t, int); +extern struct bio *bio_alloc_bioset(gfp_t, int, struct bio_set *); extern void bio_put(struct bio *); extern void bio_free(struct bio *, struct bio_set *); @@ -287,7 +287,7 @@ extern int bio_phys_segments(struct request_queue *, struct bio *); extern int bio_hw_segments(struct request_queue *, struct bio *); extern void __bio_clone(struct bio *, struct bio *); -extern struct bio *bio_clone(struct bio *, unsigned int __nocast); +extern struct bio *bio_clone(struct bio *, gfp_t); extern void bio_init(struct bio *); diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 90828493791f..6a1d154c0825 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -172,7 +172,7 @@ void __brelse(struct buffer_head *); void __bforget(struct buffer_head *); void __breadahead(struct block_device *, sector_t block, int size); struct buffer_head *__bread(struct block_device *, sector_t block, int size); -struct buffer_head *alloc_buffer_head(unsigned int __nocast gfp_flags); +struct buffer_head *alloc_buffer_head(gfp_t gfp_flags); void free_buffer_head(struct buffer_head * bh); void FASTCALL(unlock_buffer(struct buffer_head *bh)); void FASTCALL(__lock_buffer(struct buffer_head *bh)); diff --git a/include/linux/connector.h b/include/linux/connector.h index 96582c9911ac..95952cc1f525 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -149,7 +149,7 @@ struct cn_dev { 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, unsigned int __nocast); +int cn_netlink_send(struct cn_msg *, u32, gfp_t); 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); diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 24062a1dbf61..6e2deef96b34 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -23,7 +23,7 @@ void cpuset_init_current_mems_allowed(void); void cpuset_update_current_mems_allowed(void); void cpuset_restrict_to_mems_allowed(unsigned long *nodes); int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl); -extern int cpuset_zone_allowed(struct zone *z, unsigned int __nocast gfp_mask); +extern int cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask); extern int cpuset_excl_nodes_overlap(const struct task_struct *p); extern struct file_operations proc_cpuset_operations; extern char *cpuset_task_status_allowed(struct task_struct *task, char *buffer); @@ -49,8 +49,7 @@ static inline int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl) return 1; } -static inline int cpuset_zone_allowed(struct zone *z, - unsigned int __nocast gfp_mask) +static inline int cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return 1; } diff --git a/include/linux/dmapool.h b/include/linux/dmapool.h index 4932ee5c77f0..76f12f46db7f 100644 --- a/include/linux/dmapool.h +++ b/include/linux/dmapool.h @@ -19,7 +19,7 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev, void dma_pool_destroy(struct dma_pool *pool); -void *dma_pool_alloc(struct dma_pool *pool, unsigned int __nocast mem_flags, +void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags, dma_addr_t *handle); void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t addr); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 4dc990f3b5cc..3010e172394d 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -85,9 +85,9 @@ static inline void arch_free_page(struct page *page, int order) { } #endif extern struct page * -FASTCALL(__alloc_pages(unsigned int, unsigned int, struct zonelist *)); +FASTCALL(__alloc_pages(gfp_t, unsigned int, struct zonelist *)); -static inline struct page *alloc_pages_node(int nid, unsigned int __nocast gfp_mask, +static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) { if (unlikely(order >= MAX_ORDER)) @@ -98,17 +98,17 @@ static inline struct page *alloc_pages_node(int nid, unsigned int __nocast gfp_m } #ifdef CONFIG_NUMA -extern struct page *alloc_pages_current(unsigned int __nocast gfp_mask, unsigned order); +extern struct page *alloc_pages_current(gfp_t gfp_mask, unsigned order); static inline struct page * -alloc_pages(unsigned int __nocast gfp_mask, unsigned int order) +alloc_pages(gfp_t gfp_mask, unsigned int order) { if (unlikely(order >= MAX_ORDER)) return NULL; return alloc_pages_current(gfp_mask, order); } -extern struct page *alloc_page_vma(unsigned __nocast gfp_mask, +extern struct page *alloc_page_vma(gfp_t gfp_mask, struct vm_area_struct *vma, unsigned long addr); #else #define alloc_pages(gfp_mask, order) \ @@ -117,8 +117,8 @@ extern struct page *alloc_page_vma(unsigned __nocast gfp_mask, #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) -extern unsigned long FASTCALL(__get_free_pages(unsigned int __nocast gfp_mask, unsigned int order)); -extern unsigned long FASTCALL(get_zeroed_page(unsigned int __nocast gfp_mask)); +extern unsigned long FASTCALL(__get_free_pages(gfp_t gfp_mask, unsigned int order)); +extern unsigned long FASTCALL(get_zeroed_page(gfp_t gfp_mask)); #define __get_free_page(gfp_mask) \ __get_free_pages((gfp_mask),0) diff --git a/include/linux/jbd.h b/include/linux/jbd.h index de097269bd7f..ff853b3173c6 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -935,7 +935,7 @@ void journal_put_journal_head(struct journal_head *jh); */ extern kmem_cache_t *jbd_handle_cache; -static inline handle_t *jbd_alloc_handle(unsigned int __nocast gfp_flags) +static inline handle_t *jbd_alloc_handle(gfp_t gfp_flags) { return kmem_cache_alloc(jbd_handle_cache, gfp_flags); } diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h index c27cd428d269..48eccd865bd8 100644 --- a/include/linux/kfifo.h +++ b/include/linux/kfifo.h @@ -35,8 +35,8 @@ struct kfifo { }; extern struct kfifo *kfifo_init(unsigned char *buffer, unsigned int size, - unsigned int __nocast gfp_mask, spinlock_t *lock); -extern struct kfifo *kfifo_alloc(unsigned int size, unsigned int __nocast gfp_mask, + gfp_t gfp_mask, spinlock_t *lock); +extern struct kfifo *kfifo_alloc(unsigned int size, gfp_t gfp_mask, spinlock_t *lock); extern void kfifo_free(struct kfifo *fifo); extern unsigned int __kfifo_put(struct kfifo *fifo, diff --git a/include/linux/mempool.h b/include/linux/mempool.h index 796220ce47cc..f2427d7394b0 100644 --- a/include/linux/mempool.h +++ b/include/linux/mempool.h @@ -6,7 +6,7 @@ #include -typedef void * (mempool_alloc_t)(unsigned int __nocast gfp_mask, void *pool_data); +typedef void * (mempool_alloc_t)(gfp_t gfp_mask, void *pool_data); typedef void (mempool_free_t)(void *element, void *pool_data); typedef struct mempool_s { @@ -26,17 +26,16 @@ extern mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn, extern mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data, int nid); -extern int mempool_resize(mempool_t *pool, int new_min_nr, - unsigned int __nocast gfp_mask); +extern int mempool_resize(mempool_t *pool, int new_min_nr, gfp_t gfp_mask); extern void mempool_destroy(mempool_t *pool); -extern void * mempool_alloc(mempool_t *pool, unsigned int __nocast gfp_mask); +extern void * mempool_alloc(mempool_t *pool, gfp_t gfp_mask); extern void mempool_free(void *element, mempool_t *pool); /* * A mempool_alloc_t and mempool_free_t that get the memory from * a slab that is passed in through pool_data. */ -void *mempool_alloc_slab(unsigned int __nocast gfp_mask, void *pool_data); +void *mempool_alloc_slab(gfp_t gfp_mask, void *pool_data); void mempool_free_slab(void *element, void *pool_data); #endif /* _LINUX_MEMPOOL_H */ diff --git a/include/linux/netlink.h b/include/linux/netlink.h index bdebdc564506..ba25ca874c20 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -131,7 +131,7 @@ extern struct sock *netlink_kernel_create(int unit, unsigned int groups, void (* extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err); 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, - __u32 group, unsigned int __nocast allocation); + __u32 group, gfp_t allocation); extern void netlink_set_err(struct sock *ssk, __u32 pid, __u32 group, int code); extern int netlink_register_notifier(struct notifier_block *nb); extern int netlink_unregister_notifier(struct notifier_block *nb); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index d9a25647a295..acbf31c154f8 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -19,7 +19,7 @@ #define AS_EIO (__GFP_BITS_SHIFT + 0) /* IO error on async write */ #define AS_ENOSPC (__GFP_BITS_SHIFT + 1) /* ENOSPC on async write */ -static inline unsigned int __nocast mapping_gfp_mask(struct address_space * mapping) +static inline gfp_t mapping_gfp_mask(struct address_space * mapping) { return mapping->flags & __GFP_BITS_MASK; } diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 4caedddaa033..4bc241290c24 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -71,11 +71,11 @@ posix_acl_release(struct posix_acl *acl) /* posix_acl.c */ -extern struct posix_acl *posix_acl_alloc(int, unsigned int __nocast); -extern struct posix_acl *posix_acl_clone(const struct posix_acl *, unsigned int __nocast); +extern struct posix_acl *posix_acl_alloc(int, gfp_t); +extern struct posix_acl *posix_acl_clone(const struct posix_acl *, gfp_t); extern int posix_acl_valid(const struct posix_acl *); extern int posix_acl_permission(struct inode *, const struct posix_acl *, int); -extern struct posix_acl *posix_acl_from_mode(mode_t, unsigned int __nocast); +extern struct posix_acl *posix_acl_from_mode(mode_t, gfp_t); extern int posix_acl_equiv_mode(const struct posix_acl *, mode_t *); extern int posix_acl_create_masq(struct posix_acl *, mode_t *); extern int posix_acl_chmod_masq(struct posix_acl *, mode_t); diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 9c51917b1cce..045d4761febc 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -50,7 +50,7 @@ void *radix_tree_delete(struct radix_tree_root *, unsigned long); unsigned int radix_tree_gang_lookup(struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items); -int radix_tree_preload(unsigned int __nocast gfp_mask); +int radix_tree_preload(gfp_t gfp_mask); void radix_tree_init(void); void *radix_tree_tag_set(struct radix_tree_root *root, unsigned long index, int tag); diff --git a/include/linux/security.h b/include/linux/security.h index 0e43460d374e..627382e74057 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -2634,8 +2634,7 @@ static inline int security_socket_getpeersec(struct socket *sock, char __user *o return security_ops->socket_getpeersec(sock, optval, optlen, len); } -static inline int security_sk_alloc(struct sock *sk, int family, - unsigned int __nocast priority) +static inline int security_sk_alloc(struct sock *sk, int family, gfp_t priority) { return security_ops->sk_alloc_security(sk, family, priority); } @@ -2752,8 +2751,7 @@ static inline int security_socket_getpeersec(struct socket *sock, char __user *o return -ENOPROTOOPT; } -static inline int security_sk_alloc(struct sock *sk, int family, - unsigned int __nocast priority) +static inline int security_sk_alloc(struct sock *sk, int family, gfp_t priority) { return 0; } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 466c879f82b8..8f5d9e7f8734 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -302,37 +302,37 @@ struct sk_buff { extern void __kfree_skb(struct sk_buff *skb); extern struct sk_buff *__alloc_skb(unsigned int size, - unsigned int __nocast priority, int fclone); + gfp_t priority, int fclone); static inline struct sk_buff *alloc_skb(unsigned int size, - unsigned int __nocast priority) + gfp_t priority) { return __alloc_skb(size, priority, 0); } static inline struct sk_buff *alloc_skb_fclone(unsigned int size, - unsigned int __nocast priority) + gfp_t priority) { return __alloc_skb(size, priority, 1); } extern struct sk_buff *alloc_skb_from_cache(kmem_cache_t *cp, unsigned int size, - unsigned int __nocast priority); + gfp_t priority); extern void kfree_skbmem(struct sk_buff *skb); extern struct sk_buff *skb_clone(struct sk_buff *skb, - unsigned int __nocast priority); + gfp_t priority); extern struct sk_buff *skb_copy(const struct sk_buff *skb, - unsigned int __nocast priority); + gfp_t priority); extern struct sk_buff *pskb_copy(struct sk_buff *skb, - unsigned int __nocast gfp_mask); + gfp_t gfp_mask); extern int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, - unsigned int __nocast gfp_mask); + gfp_t gfp_mask); extern struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom); extern struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, - unsigned int __nocast priority); + gfp_t priority); extern struct sk_buff * skb_pad(struct sk_buff *skb, int pad); #define dev_kfree_skb(a) kfree_skb(a) extern void skb_over_panic(struct sk_buff *skb, int len, @@ -484,7 +484,7 @@ 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, - unsigned int __nocast pri) + gfp_t pri) { might_sleep_if(pri & __GFP_WAIT); if (skb_shared(skb)) { @@ -516,7 +516,7 @@ static inline struct sk_buff *skb_share_check(struct sk_buff *skb, * %NULL is returned on a memory allocation failure. */ static inline struct sk_buff *skb_unshare(struct sk_buff *skb, - unsigned int __nocast pri) + gfp_t pri) { might_sleep_if(pri & __GFP_WAIT); if (skb_cloned(skb)) { @@ -1017,7 +1017,7 @@ static inline void __skb_queue_purge(struct sk_buff_head *list) * %NULL is returned in there is no free memory. */ static inline struct sk_buff *__dev_alloc_skb(unsigned int length, - unsigned int __nocast gfp_mask) + gfp_t gfp_mask) { struct sk_buff *skb = alloc_skb(length + 16, gfp_mask); if (likely(skb)) @@ -1130,8 +1130,8 @@ static inline int skb_can_coalesce(struct sk_buff *skb, int i, * If there is no free memory -ENOMEM is returned, otherwise zero * is returned and the old skb data released. */ -extern int __skb_linearize(struct sk_buff *skb, unsigned int __nocast gfp); -static inline int skb_linearize(struct sk_buff *skb, unsigned int __nocast gfp) +extern int __skb_linearize(struct sk_buff *skb, gfp_t gfp); +static inline int skb_linearize(struct sk_buff *skb, gfp_t gfp) { return __skb_linearize(skb, gfp); } diff --git a/include/linux/slab.h b/include/linux/slab.h index 1f356f3bbc64..5fc04a16ecb0 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -61,11 +61,11 @@ extern kmem_cache_t *kmem_cache_create(const char *, size_t, size_t, unsigned lo void (*)(void *, kmem_cache_t *, unsigned long)); extern int kmem_cache_destroy(kmem_cache_t *); extern int kmem_cache_shrink(kmem_cache_t *); -extern void *kmem_cache_alloc(kmem_cache_t *, unsigned int __nocast); +extern void *kmem_cache_alloc(kmem_cache_t *, gfp_t); extern void kmem_cache_free(kmem_cache_t *, void *); extern unsigned int kmem_cache_size(kmem_cache_t *); extern const char *kmem_cache_name(kmem_cache_t *); -extern kmem_cache_t *kmem_find_general_cachep(size_t size, unsigned int __nocast gfpflags); +extern kmem_cache_t *kmem_find_general_cachep(size_t size, gfp_t gfpflags); /* Size description struct for general caches. */ struct cache_sizes { @@ -74,9 +74,9 @@ struct cache_sizes { kmem_cache_t *cs_dmacachep; }; extern struct cache_sizes malloc_sizes[]; -extern void *__kmalloc(size_t, unsigned int __nocast); +extern void *__kmalloc(size_t, gfp_t); -static inline void *kmalloc(size_t size, unsigned int __nocast flags) +static inline void *kmalloc(size_t size, gfp_t flags) { if (__builtin_constant_p(size)) { int i = 0; @@ -99,7 +99,7 @@ found: return __kmalloc(size, flags); } -extern void *kzalloc(size_t, unsigned int __nocast); +extern void *kzalloc(size_t, gfp_t); /** * kcalloc - allocate memory for an array. The memory is set to zero. @@ -107,7 +107,7 @@ extern void *kzalloc(size_t, unsigned int __nocast); * @size: element size. * @flags: the type of memory to allocate. */ -static inline void *kcalloc(size_t n, size_t size, unsigned int __nocast flags) +static inline void *kcalloc(size_t n, size_t size, gfp_t flags) { if (n != 0 && size > INT_MAX / n) return NULL; @@ -118,15 +118,14 @@ extern void kfree(const void *); extern unsigned int ksize(const void *); #ifdef CONFIG_NUMA -extern void *kmem_cache_alloc_node(kmem_cache_t *, - unsigned int __nocast flags, int node); -extern void *kmalloc_node(size_t size, unsigned int __nocast flags, int node); +extern void *kmem_cache_alloc_node(kmem_cache_t *, gfp_t flags, int node); +extern void *kmalloc_node(size_t size, gfp_t flags, int node); #else static inline void *kmem_cache_alloc_node(kmem_cache_t *cachep, int flags, int node) { return kmem_cache_alloc(cachep, flags); } -static inline void *kmalloc_node(size_t size, unsigned int __nocast flags, int node) +static inline void *kmalloc_node(size_t size, gfp_t flags, int node) { return kmalloc(size, flags); } diff --git a/include/linux/string.h b/include/linux/string.h index dab2652acbd8..369be3264a55 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -88,7 +88,7 @@ extern int memcmp(const void *,const void *,__kernel_size_t); extern void * memchr(const void *,int,__kernel_size_t); #endif -extern char *kstrdup(const char *s, unsigned int __nocast gfp); +extern char *kstrdup(const char *s, gfp_t gfp); #ifdef __cplusplus } diff --git a/include/linux/swap.h b/include/linux/swap.h index 3c9ff0048153..a7bf1a3b1496 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -147,7 +147,7 @@ struct swap_list_t { #define vm_swap_full() (nr_swap_pages*2 < total_swap_pages) /* linux/mm/oom_kill.c */ -extern void out_of_memory(unsigned int __nocast gfp_mask, int order); +extern void out_of_memory(gfp_t gfp_mask, int order); /* linux/mm/memory.c */ extern void swapin_readahead(swp_entry_t, unsigned long, struct vm_area_struct *); diff --git a/include/linux/textsearch.h b/include/linux/textsearch.h index 1a4990e448e9..515046d1b2f4 100644 --- a/include/linux/textsearch.h +++ b/include/linux/textsearch.h @@ -159,7 +159,7 @@ extern unsigned int textsearch_find_continuous(struct ts_config *, #define TS_PRIV_ALIGN(len) (((len) + TS_PRIV_ALIGNTO-1) & ~(TS_PRIV_ALIGNTO-1)) static inline struct ts_config *alloc_ts_config(size_t payload, - unsigned int __nocast gfp_mask) + gfp_t gfp_mask) { struct ts_config *conf; diff --git a/include/linux/types.h b/include/linux/types.h index 2b678c22ca4a..0aee34f9da9f 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -165,6 +165,10 @@ typedef __u64 __bitwise __le64; typedef __u64 __bitwise __be64; #endif +#ifdef __KERNEL__ +typedef unsigned __nocast gfp_t; +#endif + struct ustat { __kernel_daddr_t f_tfree; __kernel_ino_t f_tinode; diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index b244f69ef682..3701a0673d2c 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -34,8 +34,8 @@ struct vm_struct { extern void *vmalloc(unsigned long size); extern void *vmalloc_exec(unsigned long size); extern void *vmalloc_32(unsigned long size); -extern void *__vmalloc(unsigned long size, unsigned int __nocast gfp_mask, pgprot_t prot); -extern void *__vmalloc_area(struct vm_struct *area, unsigned int __nocast gfp_mask, pgprot_t prot); +extern void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot); +extern void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot); extern void vfree(void *addr); extern void *vmap(struct page **pages, unsigned int count, -- cgit v1.2.3 From 3dd083255ddcfa87751fa8e32f61a9547a15a541 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 9 Oct 2005 21:19:40 +0200 Subject: [PATCH] x86_64: Set up safe page tables during resume The following patch makes swsusp avoid the possible temporary corruption of page translation tables during resume on x86-64. This is achieved by creating a copy of the relevant page tables that will not be modified by swsusp and can be safely used by it on resume. The problem is that during resume on x86-64 swsusp may temporarily corrupt the page tables used for the direct mapping of RAM. If that happens, a page fault occurs and cannot be handled properly, which leads to the solid hang of the affected system. This leads to the loss of the system's state from before suspend and may result in the loss of data or the corruption of filesystems, so it is a serious issue. Also, it appears to happen quite often (for me, as often as 50% of the time). The problem is related to the fact that (at least) one of the PMD entries used in the direct memory mapping (starting at PAGE_OFFSET) points to a page table the physical address of which is much greater than the physical address of the PMD entry itself. Moreover, unfortunately, the physical address of the page table before suspend (i.e. the one stored in the suspend image) happens to be different to the physical address of the corresponding page table used during resume (i.e. the one that is valid right before swsusp_arch_resume() in arch/x86_64/kernel/suspend_asm.S is executed). Thus while the image is restored, the "offending" PMD entry gets overwritten, so it does not point to the right physical address any more (i.e. there's no page table at the address pointed to by it, because it points to the address the page table has been at during suspend). Consequently, if the PMD entry is used later on, and it _is_ used in the process of copying the image pages, a page fault occurs, but it cannot be handled in the normal way and the system hangs. In principle we can call create_resume_mapping() from swsusp_arch_resume() (ie. from suspend_asm.S), but then the memory allocations in create_resume_mapping(), resume_pud_mapping(), and resume_pmd_mapping() must be made carefully so that we use _only_ NosaveFree pages in them (the other pages are overwritten by the loop in swsusp_arch_resume()). Additionally, we are in atomic context at that time, so we cannot use GFP_KERNEL. Moreover, if one of the allocations fails, we should free all of the allocated pages, so we need to trace them somehow. All of this is done in the appended patch, except that the functions populating the page tables are located in arch/x86_64/kernel/suspend.c rather than in init.c. It may be done in a more elegan way in the future, with the help of some swsusp patches that are in the works now. [AK: move some externs into headers, renamed a function] Signed-off-by: Rafael J. Wysocki Signed-off-by: Andi Kleen Signed-off-by: Linus Torvalds --- include/linux/suspend.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index f2e96fdfaae0..ad15a54806d8 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -71,5 +71,7 @@ void restore_processor_state(void); struct saved_context; void __save_processor_state(struct saved_context *ctxt); void __restore_processor_state(struct saved_context *ctxt); +extern unsigned long get_usable_page(unsigned gfp_mask); +extern void free_eaten_memory(void); #endif /* _LINUX_SWSUSP_H */ -- cgit v1.2.3 From 46113830a18847cff8da73005e57bc49c2f95a56 Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Mon, 10 Oct 2005 19:44:29 +0200 Subject: [PATCH] Fix signal sending in usbdevio on async URB completion If a process issues an URB from userspace and (starts to) terminate before the URB comes back, we run into the issue described above. This is because the urb saves a pointer to "current" when it is posted to the device, but there's no guarantee that this pointer is still valid afterwards. In fact, there are three separate issues: 1) the pointer to "current" can become invalid, since the task could be completely gone when the URB completion comes back from the device. 2) Even if the saved task pointer is still pointing to a valid task_struct, task_struct->sighand could have gone meanwhile. 3) Even if the process is perfectly fine, permissions may have changed, and we can no longer send it a signal. So what we do instead, is to save the PID and uid's of the process, and introduce a new kill_proc_info_as_uid() function. Signed-off-by: Harald Welte [ Fixed up types and added symbol exports ] Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index c3ba31f210a9..27519df0f987 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1018,6 +1018,7 @@ extern int force_sig_info(int, struct siginfo *, struct task_struct *); extern int __kill_pg_info(int sig, struct siginfo *info, pid_t pgrp); extern int kill_pg_info(int, struct siginfo *, pid_t); extern int kill_proc_info(int, struct siginfo *, pid_t); +extern int kill_proc_info_as_uid(int, struct siginfo *, pid_t, uid_t, uid_t); extern void do_notify_parent(struct task_struct *, int); extern void force_sig(int, struct task_struct *); extern void force_sig_specific(int, struct task_struct *); -- cgit v1.2.3 From ebe0bbf06c9e03613bdcb6b5a704595a9344b7ff Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Mon, 10 Oct 2005 20:52:19 -0700 Subject: [NETFILTER] nfnetlink: use highest bit of nfa_type to indicate nested TLV As Henrik Nordstrom pointed out, all our efforts with "split endian" (i.e. host byte order tags, net byte order values) are useless, unless a parser can determine whether an attribute is nested or not. This patch steals the highest bit of nfattr.nfa_type to indicate whether the data payload contains a nested nfattr (1) or not (0). This will break userspace compatibility, but luckily no kernel with nfnetlink was released so far. Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 1d5b10ae2399..f08e870100f4 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -41,11 +41,15 @@ enum nfnetlink_groups { struct nfattr { u_int16_t nfa_len; - u_int16_t nfa_type; + u_int16_t nfa_type; /* we use 15 bits for the type, and the highest + * bit to indicate whether the payload is nested */ } __attribute__ ((packed)); -/* FIXME: Shamelessly copy and pasted from rtnetlink.h, it's time - * to put this in a generic file */ +/* FIXME: Apart from NFNL_NFA_NESTED shamelessly copy and pasted from + * rtnetlink.h, it's time to put this in a generic file */ + +#define NFNL_NFA_NEST 0x8000 +#define NFA_TYPE(attr) ((attr)->nfa_type & 0x7fff) #define NFA_ALIGNTO 4 #define NFA_ALIGN(len) (((len) + NFA_ALIGNTO - 1) & ~(NFA_ALIGNTO - 1)) @@ -59,7 +63,7 @@ struct nfattr #define NFA_PAYLOAD(nfa) ((int)((nfa)->nfa_len) - NFA_LENGTH(0)) #define NFA_NEST(skb, type) \ ({ struct nfattr *__start = (struct nfattr *) (skb)->tail; \ - NFA_PUT(skb, type, 0, NULL); \ + NFA_PUT(skb, (NFNL_NFA_NEST | type), 0, NULL); \ __start; }) #define NFA_NEST_END(skb, start) \ ({ (start)->nfa_len = ((skb)->tail - (unsigned char *) (start)); \ -- cgit v1.2.3 From b3a91d037a2575040f9b6a483f60c407a3d80368 Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Mon, 10 Oct 2005 20:52:36 -0700 Subject: [NETFILTER] nat: remove bogus structure member When 'rustynat' was merged in 2.6.12, the use of the "helper" pointer of struct ipt_nat_info was obsoleted, but the pointer not removed from the struct. This patch removes the pointer, thereby yet again shrinking struct ip_conntrack. Discovered-by: Rusty Russell Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ip_nat.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_nat.h b/include/linux/netfilter_ipv4/ip_nat.h index e201ec6e9905..41a107de17cf 100644 --- a/include/linux/netfilter_ipv4/ip_nat.h +++ b/include/linux/netfilter_ipv4/ip_nat.h @@ -58,10 +58,6 @@ extern rwlock_t ip_nat_lock; struct ip_nat_info { struct list_head bysource; - - /* Helper (NULL if none). */ - struct ip_nat_helper *helper; - struct ip_nat_seq seq[IP_CT_DIR_MAX]; }; -- cgit v1.2.3 From 5bbc243aafff9ad653dc7a9fa7bcaf0b4631355a Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Mon, 10 Oct 2005 20:54:01 -0700 Subject: [NETFILTER]: Add missing include to ip_conntrack_tuple.h Without this #include, __be16 is not defined and userspace programs will break. Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ip_conntrack_tuple.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_conntrack_tuple.h b/include/linux/netfilter_ipv4/ip_conntrack_tuple.h index 20e43f018b7c..3232db11a4e5 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack_tuple.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_tuple.h @@ -1,6 +1,8 @@ #ifndef _IP_CONNTRACK_TUPLE_H #define _IP_CONNTRACK_TUPLE_H +#include + /* A `tuple' is a structure containing the information to uniquely identify a connection. ie. if two packets have the same tuple, they are in the same connection; if not, they are not. -- cgit v1.2.3 From e1c73b78e3706bd3c336d4730a01dd4081dfb7ee Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 10 Oct 2005 20:55:49 -0700 Subject: [NETFILTER] ctnetlink: add one nesting level for TCP state To keep consistency, the TCP private protocol information is nested attributes under CTA_PROTOINFO_TCP. This way the sequence of attributes to access the TCP state information looks like here below: CTA_PROTOINFO CTA_PROTOINFO_TCP CTA_PROTOINFO_TCP_STATE instead of: CTA_PROTOINFO CTA_PROTOINFO_TCP_STATE Signed-off-by: Pablo Neira Ayuso Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink_conntrack.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h index 5c55751c78e4..fb5511030185 100644 --- a/include/linux/netfilter/nfnetlink_conntrack.h +++ b/include/linux/netfilter/nfnetlink_conntrack.h @@ -70,11 +70,18 @@ enum ctattr_l4proto { enum ctattr_protoinfo { CTA_PROTOINFO_UNSPEC, - CTA_PROTOINFO_TCP_STATE, + CTA_PROTOINFO_TCP, __CTA_PROTOINFO_MAX }; #define CTA_PROTOINFO_MAX (__CTA_PROTOINFO_MAX - 1) +enum ctattr_protoinfo_tcp { + CTA_PROTOINFO_TCP_UNSPEC, + CTA_PROTOINFO_TCP_STATE, + __CTA_PROTOINFO_TCP_MAX +}; +#define CTA_PROTOINFO_TCP_MAX (__CTA_PROTOINFO_TCP_MAX - 1) + enum ctattr_counters { CTA_COUNTERS_UNSPEC, CTA_COUNTERS_PACKETS, -- cgit v1.2.3 From a051a8f7306476af0a74370ad56e793cb6c43bf7 Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Mon, 10 Oct 2005 21:21:10 -0700 Subject: [NETFILTER]: Use only 32bit counters for CONNTRACK_ACCT Initially we used 64bit counters for conntrack-based accounting, since we had no event mechanism to tell userspace that our counters are about to overflow. With nfnetlink_conntrack, we now have such a event mechanism and thus can save 16bytes per connection. Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink_conntrack.h | 6 ++++-- include/linux/netfilter_ipv4/ip_conntrack.h | 8 ++++++-- 2 files changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h index fb5511030185..116fcaced909 100644 --- a/include/linux/netfilter/nfnetlink_conntrack.h +++ b/include/linux/netfilter/nfnetlink_conntrack.h @@ -84,8 +84,10 @@ enum ctattr_protoinfo_tcp { enum ctattr_counters { CTA_COUNTERS_UNSPEC, - CTA_COUNTERS_PACKETS, - CTA_COUNTERS_BYTES, + CTA_COUNTERS_PACKETS, /* old 64bit counters */ + CTA_COUNTERS_BYTES, /* old 64bit counters */ + CTA_COUNTERS32_PACKETS, + CTA_COUNTERS32_BYTES, __CTA_COUNTERS_MAX }; #define CTA_COUNTERS_MAX (__CTA_COUNTERS_MAX - 1) diff --git a/include/linux/netfilter_ipv4/ip_conntrack.h b/include/linux/netfilter_ipv4/ip_conntrack.h index 4ced38736813..d078bb91d9e5 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack.h +++ b/include/linux/netfilter_ipv4/ip_conntrack.h @@ -117,6 +117,10 @@ enum ip_conntrack_events /* NAT info */ IPCT_NATINFO_BIT = 10, IPCT_NATINFO = (1 << IPCT_NATINFO_BIT), + + /* Counter highest bit has been set */ + IPCT_COUNTER_FILLING_BIT = 11, + IPCT_COUNTER_FILLING = (1 << IPCT_COUNTER_FILLING_BIT), }; enum ip_conntrack_expect_events { @@ -192,8 +196,8 @@ do { \ struct ip_conntrack_counter { - u_int64_t packets; - u_int64_t bytes; + u_int32_t packets; + u_int32_t bytes; }; struct ip_conntrack_helper; -- cgit v1.2.3 From 339231537506846cb232a2f0cc4a2c662b2d5b07 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 10 Oct 2005 21:23:28 -0700 Subject: [NETFILTER] ctnetlink: allow userspace to change TCP state This patch adds the ability of changing the state a TCP connection. I know that this must be used with care but it's required to provide a complete conntrack creation via conntrack_netlink. So I'll document this aspect on the upcoming docs. Signed-off-by: Pablo Neira Ayuso Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ip_conntrack_protocol.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_conntrack_protocol.h b/include/linux/netfilter_ipv4/ip_conntrack_protocol.h index b6b99be8632a..2c76b879e3dc 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack_protocol.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_protocol.h @@ -52,6 +52,9 @@ struct ip_conntrack_protocol int (*to_nfattr)(struct sk_buff *skb, struct nfattr *nfa, const struct ip_conntrack *ct); + /* convert nfnetlink attributes to protoinfo */ + int (*from_nfattr)(struct nfattr *tb[], struct ip_conntrack *ct); + int (*tuple_to_nfattr)(struct sk_buff *skb, const struct ip_conntrack_tuple *t); int (*nfattr_to_tuple)(struct nfattr *tb[], -- cgit v1.2.3 From afb997c6163b33292d31a09d6aa5cbb03ffa5bf1 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Wed, 12 Oct 2005 15:12:21 -0700 Subject: [NETPOLL]: wrong return for null netpoll_poll_lock() When netpoll is not being used, the macro that defines the removed routing netpoll_poll_lock defines the return as zero, but the real routine returns a `void *` Signed-off-by: Ben Dooks Signed-off-by: David S. Miller --- include/linux/netpoll.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 5ade54a78dbb..ca5a8733000f 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -86,7 +86,7 @@ static inline void netpoll_poll_unlock(void *have) #else #define netpoll_rx(a) 0 -#define netpoll_poll_lock(a) 0 +#define netpoll_poll_lock(a) NULL #define netpoll_poll_unlock(a) #endif -- cgit v1.2.3 From c8923c6b852d3a97c1faad0566e38fca330375a7 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 13 Oct 2005 14:41:23 -0700 Subject: [NETFILTER]: Fix OOPSes on machines with discontiguous cpu numbering. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Original patch by Harald Welte, with feedback from Herbert Xu and testing by Sébastien Bernard. EBTABLES, ARP tables, and IP/IP6 tables all assume that cpus are numbered linearly. That is not necessarily true. This patch fixes that up by calculating the largest possible cpu number, and allocating enough per-cpu structure space given that. Signed-off-by: David S. Miller --- include/linux/cpumask.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index b15826f6e3a2..fe9778301d07 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -392,4 +392,16 @@ extern cpumask_t cpu_present_map; #define for_each_online_cpu(cpu) for_each_cpu_mask((cpu), cpu_online_map) #define for_each_present_cpu(cpu) for_each_cpu_mask((cpu), cpu_present_map) +/* Find the highest possible smp_processor_id() */ +static inline unsigned int highest_possible_processor_id(void) +{ + unsigned int cpu, highest = 0; + + for_each_cpu_mask(cpu, cpu_possible_map) + highest = cpu; + + return highest; +} + + #endif /* __LINUX_CPUMASK_H */ -- cgit v1.2.3 From e26148d934762b61133a64b6862f870624ff617d Mon Sep 17 00:00:00 2001 From: Tim Schmielau Date: Fri, 14 Oct 2005 15:59:05 -0700 Subject: [PATCH] Fix copy-and-paste error in BSD accounting Fix copy and paste error in jiffies_to_AHZ conversion which leads to wrong BSD accounting information on alpha and ia64 when CONFIG_BSD_PROCESS_ACCT_V3 is turned on. Also update comment to match reorganised header files. Signed-off-by: Tim Schmielau Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/acct.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acct.h b/include/linux/acct.h index 1993a3691768..19f70462b3be 100644 --- a/include/linux/acct.h +++ b/include/linux/acct.h @@ -162,13 +162,13 @@ typedef struct acct acct_t; #ifdef __KERNEL__ /* * Yet another set of HZ to *HZ helper functions. - * See for the original. + * See for the original. */ static inline u32 jiffies_to_AHZ(unsigned long x) { #if (TICK_NSEC % (NSEC_PER_SEC / AHZ)) == 0 - return x / (HZ / USER_HZ); + return x / (HZ / AHZ); #else u64 tmp = (u64)x * TICK_NSEC; do_div(tmp, (NSEC_PER_SEC / AHZ)); -- cgit v1.2.3 From 688ce17b8599abc548b406c00e4d18ae0dec954f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 16 Oct 2005 00:17:33 -0700 Subject: [PATCH]: highest_possible_processor_id() has to be a macro ... otherwise, things like alpha and sparc64 break and break badly. They define cpu_possible_map to something else in smp.h *AFTER* having included cpumask.h. If that puppy is a macro, expansion will happen at the actual caller, when we'd already seen #define cpu_possible_map ... and we will get the right thing used. As an inline helper it will be tokenized before we get to that define and that's it; no matter what we define later, it won't affect anything. We get modules with dependency on cpu_possible_map instead of the right symbol (phys_cpu_present_map in case of sparc64), or outright link errors if they are built-in. Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/cpumask.h | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index fe9778301d07..9bdba8169b41 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -393,15 +393,13 @@ extern cpumask_t cpu_present_map; #define for_each_present_cpu(cpu) for_each_cpu_mask((cpu), cpu_present_map) /* Find the highest possible smp_processor_id() */ -static inline unsigned int highest_possible_processor_id(void) -{ - unsigned int cpu, highest = 0; - - for_each_cpu_mask(cpu, cpu_possible_map) - highest = cpu; - - return highest; -} +#define highest_possible_processor_id() \ +({ \ + unsigned int cpu, highest = 0; \ + for_each_cpu_mask(cpu, cpu_possible_map) \ + highest = cpu; \ + highest; \ +}) #endif /* __LINUX_CPUMASK_H */ -- cgit v1.2.3 From b24d18aa743dad0c42918157c5d717686269d3a8 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Sun, 16 Oct 2005 20:29:20 -0700 Subject: [PATCH] list: add missing rcu_dereference on first element It seems that all the list_*_rcu primitives are missing a memory barrier on the very first dereference. For example, #define list_for_each_rcu(pos, head) \ for (pos = (head)->next; prefetch(pos->next), pos != (head); \ pos = rcu_dereference(pos->next)) It will go something like: pos = (head)->next prefetch(pos->next) pos != (head) do stuff We're missing a barrier here. pos = rcu_dereference(pos->next) fetch pos->next barrier given by rcu_dereference(pos->next) store pos Without the missing barrier, the pos->next value may turn out to be stale. In fact, if "do stuff" were also dereferencing pos and relying on list_for_each_rcu to provide the barrier then it may also break. So here is a patch to make sure that we have a barrier for the first element in the list. Signed-off-by: Herbert Xu Acked-by: "Paul E. McKenney" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list.h | 39 ++++++++++++++++++++++----------------- 1 file changed, 22 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index e6ec59682274..084971f333fe 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -442,12 +442,14 @@ static inline void list_splice_init(struct list_head *list, * as long as the traversal is guarded by rcu_read_lock(). */ #define list_for_each_rcu(pos, head) \ - for (pos = (head)->next; prefetch(pos->next), pos != (head); \ - pos = rcu_dereference(pos->next)) + for (pos = (head)->next; \ + prefetch(rcu_dereference(pos)->next), pos != (head); \ + pos = pos->next) #define __list_for_each_rcu(pos, head) \ - for (pos = (head)->next; pos != (head); \ - pos = rcu_dereference(pos->next)) + for (pos = (head)->next; \ + rcu_dereference(pos) != (head); \ + pos = pos->next) /** * list_for_each_safe_rcu - iterate over an rcu-protected list safe @@ -461,8 +463,9 @@ static inline void list_splice_init(struct list_head *list, * as long as the traversal is guarded by rcu_read_lock(). */ #define list_for_each_safe_rcu(pos, n, head) \ - for (pos = (head)->next, n = pos->next; pos != (head); \ - pos = rcu_dereference(n), n = pos->next) + for (pos = (head)->next; \ + n = rcu_dereference(pos)->next, pos != (head); \ + pos = n) /** * list_for_each_entry_rcu - iterate over rcu list of given type @@ -474,11 +477,11 @@ static inline void list_splice_init(struct list_head *list, * the _rcu list-mutation primitives such as list_add_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ -#define list_for_each_entry_rcu(pos, head, member) \ - for (pos = list_entry((head)->next, typeof(*pos), member); \ - prefetch(pos->member.next), &pos->member != (head); \ - pos = rcu_dereference(list_entry(pos->member.next, \ - typeof(*pos), member))) +#define list_for_each_entry_rcu(pos, head, member) \ + for (pos = list_entry((head)->next, typeof(*pos), member); \ + prefetch(rcu_dereference(pos)->member.next), \ + &pos->member != (head); \ + pos = list_entry(pos->member.next, typeof(*pos), member)) /** @@ -492,8 +495,9 @@ static inline void list_splice_init(struct list_head *list, * as long as the traversal is guarded by rcu_read_lock(). */ #define list_for_each_continue_rcu(pos, head) \ - for ((pos) = (pos)->next; prefetch((pos)->next), (pos) != (head); \ - (pos) = rcu_dereference((pos)->next)) + for ((pos) = (pos)->next; \ + prefetch(rcu_dereference((pos))->next), (pos) != (head); \ + (pos) = (pos)->next) /* * Double linked lists with a single pointer list head. @@ -696,8 +700,9 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev, pos = n) #define hlist_for_each_rcu(pos, head) \ - for ((pos) = (head)->first; pos && ({ prefetch((pos)->next); 1; }); \ - (pos) = rcu_dereference((pos)->next)) + for ((pos) = (head)->first; \ + rcu_dereference((pos)) && ({ prefetch((pos)->next); 1; }); \ + (pos) = (pos)->next) /** * hlist_for_each_entry - iterate over list of given type @@ -762,9 +767,9 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev, */ #define hlist_for_each_entry_rcu(tpos, pos, head, member) \ for (pos = (head)->first; \ - pos && ({ prefetch(pos->next); 1;}) && \ + rcu_dereference(pos) && ({ prefetch(pos->next); 1;}) && \ ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ - pos = rcu_dereference(pos->next)) + pos = pos->next) #else #warning "don't include kernel headers in userspace" -- cgit v1.2.3 From 5ee832dbc6770135ec8d63296af0a4374557bb79 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 17 Oct 2005 20:01:21 +0200 Subject: [PATCH] rcu: keep rcu callback event counter This makes call_rcu() keep track of how many events there are on the RCU list, and cause a reschedule event when the list gets too long. This helps keep RCU event lists down. Signed-off-by: Linus Torvalds --- include/linux/rcupdate.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 4e65eb44adfd..70191a5a148f 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -94,6 +94,7 @@ struct rcu_data { long batch; /* Batch # for current RCU batch */ struct rcu_head *nxtlist; struct rcu_head **nxttail; + long count; /* # of queued items */ struct rcu_head *curlist; struct rcu_head **curtail; struct rcu_head *donelist; -- cgit v1.2.3 From 4faa5285283fad081443e3612ca426a311bb6c7e Mon Sep 17 00:00:00 2001 From: Zach Brown Date: Mon, 17 Oct 2005 16:43:33 -0700 Subject: [PATCH] aio: revert lock_kiocb() lock_kiocb() was introduced to serialize retrying and cancellation. In the process of doing so it tried to sleep waiting for KIF_LOCKED while holding the ctx_lock spinlock. Recent fixes have ensured that multiple concurrent retries won't be attempted for a given iocb. Cancel has other problems and has no significant in-tree users that have been complaining about it. So for the immediate future we'll revert sleeping with the lock held and will address proper cancellation and retry serialization in the future. Signed-off-by: Zach Brown Acked-by: Benjamin LaHaise Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index 60def658b246..0decf66117c1 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -24,7 +24,12 @@ struct kioctx; #define KIOCB_SYNC_KEY (~0U) /* ki_flags bits */ -#define KIF_LOCKED 0 +/* + * This may be used for cancel/retry serialization in the future, but + * for now it's unused and we probably don't want modules to even + * think they can use it. + */ +/* #define KIF_LOCKED 0 */ #define KIF_KICKED 1 #define KIF_CANCELLED 2 -- cgit v1.2.3 From 8cbd6df1f0ce977ab7b61feffa59879bb5e0ed8f Mon Sep 17 00:00:00 2001 From: Albert Lee Date: Wed, 12 Oct 2005 15:06:27 +0800 Subject: [PATCH] libata CHS: calculate read/write commands and protocol on the fly (revise #6) - merge ata_prot_to_cmd() and ata_dev_set_protocol() as ata_rwcmd_protocol() - pave road for read/write multiple support - remove usage of pre-cached command and protocol values and call ata_rwcmd_protocol() instead Signed-off-by: Albert Lee ============== Signed-off-by: Jeff Garzik --- include/linux/ata.h | 4 ++++ include/linux/libata.h | 6 ++---- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index ecb7346d0c16..630908c9378b 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -128,6 +128,10 @@ enum { ATA_CMD_PIO_READ_EXT = 0x24, ATA_CMD_PIO_WRITE = 0x30, ATA_CMD_PIO_WRITE_EXT = 0x34, + ATA_CMD_READ_MULTI = 0xC4, + ATA_CMD_READ_MULTI_EXT = 0x29, + ATA_CMD_WRITE_MULTI = 0xC5, + ATA_CMD_WRITE_MULTI_EXT = 0x39, ATA_CMD_SET_FEATURES = 0xEF, ATA_CMD_PACKET = 0xA0, ATA_CMD_VERIFY = 0x40, diff --git a/include/linux/libata.h b/include/linux/libata.h index 7929cfc9318d..0261c55f3483 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -283,10 +283,8 @@ struct ata_device { u8 xfer_mode; unsigned int xfer_shift; /* ATA_SHIFT_xxx */ - /* cache info about current transfer mode */ - u8 xfer_protocol; /* taskfile xfer protocol */ - u8 read_cmd; /* opcode to use on read */ - u8 write_cmd; /* opcode to use on write */ + unsigned int multi_count; /* sectors count for + READ/WRITE MULTIPLE */ /* for CHS addressing */ u16 cylinders; /* Number of cylinders */ -- cgit v1.2.3 From 5e5ce5be6f0161d2a069a4f8a1154fe639c5c02f Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 18 Oct 2005 14:20:11 -0700 Subject: RPC: allow call_encode() to delay transmission of an RPC call. Currently, call_encode will cause the entire RPC call to abort if it returns an error. This is unnecessarily rigid, and gets in the way of attempts to allow the NFSv4 layer to order RPC calls that carry sequence ids. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 99cad3ead81d..068e1fb0868b 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -211,6 +211,7 @@ int xprt_reserve_xprt(struct rpc_task *task); int xprt_reserve_xprt_cong(struct rpc_task *task); int xprt_prepare_transmit(struct rpc_task *task); void xprt_transmit(struct rpc_task *task); +void xprt_abort_transmit(struct rpc_task *task); int xprt_adjust_timeout(struct rpc_rqst *req); void xprt_release_xprt(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_release_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); -- cgit v1.2.3 From cee54fc944422c44e476736c045a9e8053cb0644 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 18 Oct 2005 14:20:12 -0700 Subject: NFSv4: Add functions to order RPC calls NFSv4 file state-changing functions such as OPEN, CLOSE, LOCK,... are all labelled with "sequence identifiers" in order to prevent the server from reordering RPC requests, as this could cause its file state to become out of sync with the client. Currently the NFS client code enforces this ordering locally using semaphores to restrict access to structures until the RPC call is done. This, of course, only works with synchronous RPC calls, since the user process must first grab the semaphore. By dropping semaphores, and instead teaching the RPC engine to hold the RPC calls until they are ready to be sent, we can extend this process to work nicely with asynchronous RPC calls too. This patch adds a new list called "rpc_sequence" that defines the order of the RPC calls to be sent. We add one such list for each state_owner. When an RPC call is ready to be sent, it checks if it is top of the rpc_sequence list. If so, it proceeds. If not, it goes back to sleep, and loops until it hits top of the list. Once the RPC call has completed, it can then bump the sequence id counter, and remove itself from the rpc_sequence list, and then wake up the next sleeper. Note that the state_owner sequence ids and lock_owner sequence ids are all indexed to the same rpc_sequence list, so OPEN, LOCK,... requests are all ordered w.r.t. each other. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index a2bf6914ff1b..d578912bf9a9 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -96,12 +96,13 @@ struct nfs4_change_info { u64 after; }; +struct nfs_seqid; /* * Arguments to the open call. */ struct nfs_openargs { const struct nfs_fh * fh; - __u32 seqid; + struct nfs_seqid * seqid; int open_flags; __u64 clientid; __u32 id; @@ -136,7 +137,7 @@ struct nfs_openres { struct nfs_open_confirmargs { const struct nfs_fh * fh; nfs4_stateid stateid; - __u32 seqid; + struct nfs_seqid * seqid; }; struct nfs_open_confirmres { @@ -149,7 +150,7 @@ struct nfs_open_confirmres { struct nfs_closeargs { struct nfs_fh * fh; nfs4_stateid stateid; - __u32 seqid; + struct nfs_seqid * seqid; int open_flags; }; @@ -165,15 +166,15 @@ struct nfs_lowner { }; struct nfs_open_to_lock { - __u32 open_seqid; + struct nfs_seqid * open_seqid; nfs4_stateid open_stateid; - __u32 lock_seqid; + struct nfs_seqid * lock_seqid; struct nfs_lowner lock_owner; }; struct nfs_exist_lock { nfs4_stateid stateid; - __u32 seqid; + struct nfs_seqid * seqid; }; struct nfs_lock_opargs { @@ -186,7 +187,7 @@ struct nfs_lock_opargs { }; struct nfs_locku_opargs { - __u32 seqid; + struct nfs_seqid * seqid; nfs4_stateid stateid; }; -- cgit v1.2.3 From 9512135df14f8293b9bc5e8fb22d4279dee5ff66 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 18 Oct 2005 14:20:12 -0700 Subject: NFSv4: Fix a potential CLOSE race Once the state_owner and lock_owner semaphores get removed, it will be possible for other OPEN requests to reopen the same file if they have lower sequence ids than our CLOSE call. This patch ensures that we recheck the file state once nfs_wait_on_sequence() has completed waiting. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index d578912bf9a9..cac0df950c66 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -149,7 +149,7 @@ struct nfs_open_confirmres { */ struct nfs_closeargs { struct nfs_fh * fh; - nfs4_stateid stateid; + nfs4_stateid * stateid; struct nfs_seqid * seqid; int open_flags; }; -- cgit v1.2.3 From faf5f49c2d9c0af2847837c232a432cc146e203b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 18 Oct 2005 14:20:15 -0700 Subject: NFSv4: Make NFS clean up byte range locks asynchronously Currently we fail to do so if the process was signalled. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index cac0df950c66..849f95c5fae4 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -188,7 +188,7 @@ struct nfs_lock_opargs { struct nfs_locku_opargs { struct nfs_seqid * seqid; - nfs4_stateid stateid; + nfs4_stateid * stateid; }; struct nfs_lockargs { -- cgit v1.2.3 From 06735b3454824bd561decbde46111f144e905923 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 18 Oct 2005 14:20:15 -0700 Subject: NFSv4: Fix up handling of open_to_lock sequence ids Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 19 ++++--------------- 1 file changed, 4 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 849f95c5fae4..57efcc27f20b 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -165,25 +165,14 @@ struct nfs_lowner { u32 id; }; -struct nfs_open_to_lock { - struct nfs_seqid * open_seqid; - nfs4_stateid open_stateid; +struct nfs_lock_opargs { struct nfs_seqid * lock_seqid; + nfs4_stateid * lock_stateid; + struct nfs_seqid * open_seqid; + nfs4_stateid * open_stateid; struct nfs_lowner lock_owner; -}; - -struct nfs_exist_lock { - nfs4_stateid stateid; - struct nfs_seqid * seqid; -}; - -struct nfs_lock_opargs { __u32 reclaim; __u32 new_lock_owner; - union { - struct nfs_open_to_lock *open_lock; - struct nfs_exist_lock *exist_lock; - } u; }; struct nfs_locku_opargs { -- cgit v1.2.3 From 834f2a4a1554dc5b2598038b3fe8703defcbe467 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 18 Oct 2005 14:20:16 -0700 Subject: VFS: Allow the filesystem to return a full file pointer on open intent This is needed by NFSv4 for atomicity reasons: our open command is in fact a lookup+open, so we need to be able to propagate open context information from lookup() into the resulting struct file's private_data field. Signed-off-by: Trond Myklebust --- include/linux/namei.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index 7db67b008cac..1c975d0d9e94 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -8,6 +8,7 @@ struct vfsmount; struct open_intent { int flags; int create_mode; + struct file *file; }; enum { MAX_NESTED_LINKS = 5 }; @@ -65,6 +66,13 @@ extern int FASTCALL(link_path_walk(const char *, struct nameidata *)); extern void path_release(struct nameidata *); extern void path_release_on_umount(struct nameidata *); +extern int __user_path_lookup_open(const char __user *, unsigned lookup_flags, struct nameidata *nd, int open_flags); +extern int path_lookup_open(const char *, unsigned lookup_flags, struct nameidata *, int open_flags); +extern struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry, + int (*open)(struct inode *, struct file *)); +extern struct file *nameidata_to_filp(struct nameidata *nd, int flags); +extern void release_open_intent(struct nameidata *); + extern struct dentry * lookup_one_len(const char *, struct dentry *, int); extern struct dentry * lookup_hash(struct qstr *, struct dentry *); -- cgit v1.2.3 From 02a913a73b52071e93f4b76db3e86138d19efffd Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 18 Oct 2005 14:20:17 -0700 Subject: NFSv4: Eliminate nfsv4 open race... Make NFSv4 return the fully initialized file pointer with the stateid that it created in the lookup w/intent. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 57efcc27f20b..60086dac11d5 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -712,7 +712,7 @@ struct nfs_rpc_ops { int (*write) (struct nfs_write_data *); int (*commit) (struct nfs_write_data *); int (*create) (struct inode *, struct dentry *, - struct iattr *, int); + struct iattr *, int, struct nameidata *); int (*remove) (struct inode *, struct qstr *); int (*unlink_setup) (struct rpc_message *, struct dentry *, struct qstr *); -- cgit v1.2.3 From 293f1eb551a77fe5c8956a559a3c0baea95cd9bc Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Thu, 13 Oct 2005 16:54:37 -0400 Subject: SUNRPC: Add support for privacy to generic gss-api code. Add support for privacy to generic gss-api code. This is dead code until we have both a mechanism that supports privacy and code in the client or server that uses it. Signed-off-by: J. Bruce Fields Signed-off-by: Trond Myklebust --- include/linux/sunrpc/gss_api.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h index 689262f63059..e896752ffbf9 100644 --- a/include/linux/sunrpc/gss_api.h +++ b/include/linux/sunrpc/gss_api.h @@ -48,6 +48,17 @@ u32 gss_verify_mic( struct xdr_buf *message, struct xdr_netobj *mic_token, u32 *qstate); +u32 gss_wrap( + struct gss_ctx *ctx_id, + u32 qop, + int offset, + struct xdr_buf *outbuf, + struct page **inpages); +u32 gss_unwrap( + struct gss_ctx *ctx_id, + u32 *qop, + int offset, + struct xdr_buf *inbuf); u32 gss_delete_sec_context( struct gss_ctx **ctx_id); @@ -93,6 +104,17 @@ struct gss_api_ops { struct xdr_buf *message, struct xdr_netobj *mic_token, u32 *qstate); + u32 (*gss_wrap)( + struct gss_ctx *ctx_id, + u32 qop, + int offset, + struct xdr_buf *outbuf, + struct page **inpages); + u32 (*gss_unwrap)( + struct gss_ctx *ctx_id, + u32 *qop, + int offset, + struct xdr_buf *buf); void (*gss_delete_sec_context)( void *internal_ctx_id); }; -- cgit v1.2.3 From ead5e1c26fdcd969cf40c49cb0589d56879d240d Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Thu, 13 Oct 2005 16:54:43 -0400 Subject: SUNRPC: Provide a callback to allow free pages allocated during xdr encoding For privacy, we need to allocate pages to store the encrypted data (passed in pages can't be used without the risk of corrupting data in the page cache). So we need a way to free that memory after the request has been transmitted. Signed-off-by: J. Bruce Fields Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 068e1fb0868b..3b8b6e823c70 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -73,7 +73,10 @@ struct rpc_rqst { int rq_cong; /* has incremented xprt->cong */ int rq_received; /* receive completed */ u32 rq_seqno; /* gss seq no. used on req. */ - + int rq_enc_pages_num; + struct page **rq_enc_pages; /* scratch pages for use by + gss privacy code */ + void (*rq_release_snd_buf)(struct rpc_rqst *); /* release rq_enc_pages */ struct list_head rq_list; struct xdr_buf rq_private_buf; /* The receive buffer -- cgit v1.2.3 From 24b2605becc10ca63c4c30808fa59a8abbf68727 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Thu, 13 Oct 2005 16:54:53 -0400 Subject: RPCSEC_GSS: cleanup au_rslack calculation Various xdr encode routines use au_rslack to guess where the reply argument will end up, so we can set up the xdr_buf to recieve data into the right place for zero copy. Currently we calculate the au_rslack estimate when we check the verifier. Normally this only depends on the verifier size. In the integrity case we add a few bytes to allow for a length and sequence number. It's a bit simpler to calculate only the verifier size when we check the verifier, and delay the full calculation till we unwrap. Signed-off-by: J. Bruce Fields Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 04ebc24db348..b68c11a2d6dd 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -66,7 +66,12 @@ struct rpc_cred_cache { struct rpc_auth { unsigned int au_cslack; /* call cred size estimate */ - unsigned int au_rslack; /* reply verf size guess */ + /* guess at number of u32's auth adds before + * reply data; normally the verifier size: */ + unsigned int au_rslack; + /* for gss, used to calculate au_rslack: */ + unsigned int au_verfsize; + unsigned int au_flags; /* various flags */ struct rpc_authops * au_ops; /* operations */ rpc_authflavor_t au_flavor; /* pseudoflavor (note may -- cgit v1.2.3 From bfa91516b57483fc9c81d8d90325fd2c3c16ac48 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Thu, 13 Oct 2005 16:55:08 -0400 Subject: RPCSEC_GSS: krb5 pre-privacy cleanup The code this was originally derived from processed wrap and mic tokens using the same functions. This required some contortions, and more would be required with the addition of xdr_buf's, so it's better to separate out the two code paths. In preparation for adding privacy support, remove the last vestiges of the old wrap token code. Signed-off-by: J. Bruce Fields Signed-off-by: Trond Myklebust --- include/linux/sunrpc/gss_krb5.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index ffe31d2eb9ec..cb35833e2ae3 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -121,13 +121,12 @@ make_checksum(s32 cksumtype, char *header, int hdrlen, struct xdr_buf *body, u32 krb5_make_token(struct krb5_ctx *context_handle, int qop_req, struct xdr_buf *input_message_buffer, - struct xdr_netobj *output_message_buffer, int toktype); + struct xdr_netobj *output_message_buffer); u32 krb5_read_token(struct krb5_ctx *context_handle, struct xdr_netobj *input_token_buffer, - struct xdr_buf *message_buffer, - int *qop_state, int toktype); + struct xdr_buf *message_buffer, int *qop_state); u32 krb5_encrypt(struct crypto_tfm * key, -- cgit v1.2.3 From 14ae162c24d985593d5b19437d7f3d8fd0062b59 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Thu, 13 Oct 2005 16:55:13 -0400 Subject: RPCSEC_GSS: Add support for privacy to krb5 rpcsec_gss mechanism. Add support for privacy to the krb5 rpcsec_gss mechanism. Signed-off-by: J. Bruce Fields Signed-off-by: Trond Myklebust --- include/linux/sunrpc/gss_krb5.h | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index cb35833e2ae3..7f93c2d5ebdb 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -116,7 +116,7 @@ enum seal_alg { s32 make_checksum(s32 cksumtype, char *header, int hdrlen, struct xdr_buf *body, - struct xdr_netobj *cksum); + int body_offset, struct xdr_netobj *cksum); u32 krb5_make_token(struct krb5_ctx *context_handle, int qop_req, @@ -128,6 +128,15 @@ krb5_read_token(struct krb5_ctx *context_handle, struct xdr_netobj *input_token_buffer, struct xdr_buf *message_buffer, int *qop_state); +u32 +gss_wrap_kerberos(struct gss_ctx *ctx_id, u32 qop, int offset, + struct xdr_buf *outbuf, struct page **pages); + +u32 +gss_unwrap_kerberos(struct gss_ctx *ctx_id, u32 *qop, int offset, + struct xdr_buf *buf); + + u32 krb5_encrypt(struct crypto_tfm * key, void *iv, void *in, void *out, int length); @@ -136,6 +145,13 @@ u32 krb5_decrypt(struct crypto_tfm * key, void *iv, void *in, void *out, int length); +int +gss_encrypt_xdr_buf(struct crypto_tfm *tfm, struct xdr_buf *outbuf, int offset, + struct page **pages); + +int +gss_decrypt_xdr_buf(struct crypto_tfm *tfm, struct xdr_buf *inbuf, int offset); + s32 krb5_make_seq_num(struct crypto_tfm * key, int direction, -- cgit v1.2.3 From 00fd6e14255fe7a249315746386d640bc4e9e758 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Thu, 13 Oct 2005 16:55:18 -0400 Subject: RPCSEC_GSS remove all qop parameters Not only are the qop parameters that are passed around throughout the gssapi unused by any currently implemented mechanism, but there appears to be some doubt as to whether they will ever be used. Let's just kill them off for now. Signed-off-by: J. Bruce Fields Signed-off-by: Trond Myklebust --- include/linux/sunrpc/gss_api.h | 13 ++----------- include/linux/sunrpc/gss_err.h | 10 ---------- include/linux/sunrpc/gss_krb5.h | 8 ++++---- include/linux/sunrpc/gss_spkm3.h | 4 ++-- 4 files changed, 8 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h index e896752ffbf9..9b8bcf125c18 100644 --- a/include/linux/sunrpc/gss_api.h +++ b/include/linux/sunrpc/gss_api.h @@ -40,23 +40,19 @@ int gss_import_sec_context( struct gss_ctx **ctx_id); u32 gss_get_mic( struct gss_ctx *ctx_id, - u32 qop, struct xdr_buf *message, struct xdr_netobj *mic_token); u32 gss_verify_mic( struct gss_ctx *ctx_id, struct xdr_buf *message, - struct xdr_netobj *mic_token, - u32 *qstate); + struct xdr_netobj *mic_token); u32 gss_wrap( struct gss_ctx *ctx_id, - u32 qop, int offset, struct xdr_buf *outbuf, struct page **inpages); u32 gss_unwrap( struct gss_ctx *ctx_id, - u32 *qop, int offset, struct xdr_buf *inbuf); u32 gss_delete_sec_context( @@ -67,7 +63,6 @@ char *gss_service_to_auth_domain_name(struct gss_api_mech *, u32 service); struct pf_desc { u32 pseudoflavor; - u32 qop; u32 service; char *name; char *auth_domain_name; @@ -96,23 +91,19 @@ struct gss_api_ops { struct gss_ctx *ctx_id); u32 (*gss_get_mic)( struct gss_ctx *ctx_id, - u32 qop, struct xdr_buf *message, struct xdr_netobj *mic_token); u32 (*gss_verify_mic)( struct gss_ctx *ctx_id, struct xdr_buf *message, - struct xdr_netobj *mic_token, - u32 *qstate); + struct xdr_netobj *mic_token); u32 (*gss_wrap)( struct gss_ctx *ctx_id, - u32 qop, int offset, struct xdr_buf *outbuf, struct page **inpages); u32 (*gss_unwrap)( struct gss_ctx *ctx_id, - u32 *qop, int offset, struct xdr_buf *buf); void (*gss_delete_sec_context)( diff --git a/include/linux/sunrpc/gss_err.h b/include/linux/sunrpc/gss_err.h index 92608a2e574c..a6807867bd21 100644 --- a/include/linux/sunrpc/gss_err.h +++ b/include/linux/sunrpc/gss_err.h @@ -65,16 +65,6 @@ typedef unsigned int OM_uint32; #define GSS_C_MECH_CODE 2 -/* - * Define the default Quality of Protection for per-message services. Note - * that an implementation that offers multiple levels of QOP may either reserve - * a value (for example zero, as assumed here) to mean "default protection", or - * alternatively may simply equate GSS_C_QOP_DEFAULT to a specific explicit - * QOP value. However a value of 0 should always be interpreted by a GSSAPI - * implementation as a request for the default protection level. - */ -#define GSS_C_QOP_DEFAULT 0 - /* * Expiration time of 2^32-1 seconds means infinite lifetime for a * credential or security context diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 7f93c2d5ebdb..a7bda4edb853 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -119,21 +119,21 @@ make_checksum(s32 cksumtype, char *header, int hdrlen, struct xdr_buf *body, int body_offset, struct xdr_netobj *cksum); u32 -krb5_make_token(struct krb5_ctx *context_handle, int qop_req, +krb5_make_token(struct krb5_ctx *context_handle, struct xdr_buf *input_message_buffer, struct xdr_netobj *output_message_buffer); u32 krb5_read_token(struct krb5_ctx *context_handle, struct xdr_netobj *input_token_buffer, - struct xdr_buf *message_buffer, int *qop_state); + struct xdr_buf *message_buffer); u32 -gss_wrap_kerberos(struct gss_ctx *ctx_id, u32 qop, int offset, +gss_wrap_kerberos(struct gss_ctx *ctx_id, int offset, struct xdr_buf *outbuf, struct page **pages); u32 -gss_unwrap_kerberos(struct gss_ctx *ctx_id, u32 *qop, int offset, +gss_unwrap_kerberos(struct gss_ctx *ctx_id, int offset, struct xdr_buf *buf); diff --git a/include/linux/sunrpc/gss_spkm3.h b/include/linux/sunrpc/gss_spkm3.h index b5c9968c3c17..0beb2cf00a84 100644 --- a/include/linux/sunrpc/gss_spkm3.h +++ b/include/linux/sunrpc/gss_spkm3.h @@ -41,9 +41,9 @@ struct spkm3_ctx { #define SPKM_WRAP_TOK 5 #define SPKM_DEL_TOK 6 -u32 spkm3_make_token(struct spkm3_ctx *ctx, int qop_req, struct xdr_buf * text, struct xdr_netobj * token, int toktype); +u32 spkm3_make_token(struct spkm3_ctx *ctx, struct xdr_buf * text, struct xdr_netobj * token, int toktype); -u32 spkm3_read_token(struct spkm3_ctx *ctx, struct xdr_netobj *read_token, struct xdr_buf *message_buffer, int *qop_state, int toktype); +u32 spkm3_read_token(struct spkm3_ctx *ctx, struct xdr_netobj *read_token, struct xdr_buf *message_buffer, int toktype); #define CKSUMTYPE_RSA_MD5 0x0007 -- cgit v1.2.3 From a0857d03b21fa54653c9d2fe7a315381176015b4 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Thu, 13 Oct 2005 16:55:23 -0400 Subject: RPCSEC_GSS: krb5 cleanup Remove some senseless wrappers. Signed-off-by: J. Bruce Fields Signed-off-by: Trond Myklebust --- include/linux/sunrpc/gss_krb5.h | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index a7bda4edb853..2c3601d31045 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -118,15 +118,11 @@ s32 make_checksum(s32 cksumtype, char *header, int hdrlen, struct xdr_buf *body, int body_offset, struct xdr_netobj *cksum); -u32 -krb5_make_token(struct krb5_ctx *context_handle, - struct xdr_buf *input_message_buffer, - struct xdr_netobj *output_message_buffer); +u32 gss_get_mic_kerberos(struct gss_ctx *, struct xdr_buf *, + struct xdr_netobj *); -u32 -krb5_read_token(struct krb5_ctx *context_handle, - struct xdr_netobj *input_token_buffer, - struct xdr_buf *message_buffer); +u32 gss_verify_mic_kerberos(struct gss_ctx *, struct xdr_buf *, + struct xdr_netobj *); u32 gss_wrap_kerberos(struct gss_ctx *ctx_id, int offset, -- cgit v1.2.3 From 3359b54c8c07338f3a863d1109b42eebccdcf379 Mon Sep 17 00:00:00 2001 From: "Seth, Rohit" Date: Tue, 18 Oct 2005 14:15:12 -0700 Subject: [PATCH] Handle spurious page fault for hugetlb region The hugetlb pages are currently pre-faulted. At the time of mmap of hugepages, we populate the new PTEs. It is possible that HW has already cached some of the unused PTEs internally. These stale entries never get a chance to be purged in existing control flow. This patch extends the check in page fault code for hugepages. Check if a faulted address falls with in size for the hugetlb file backing it. We return VM_FAULT_MINOR for these cases (assuming that the arch specific page-faulting code purges the stale entry for the archs that need it). Signed-off-by: Rohit Seth [ This is apparently arguably an ia64 port bug. But the code won't hurt, and for now it fixes a real problem on some ia64 machines ] Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index e670b0d13fe0..42cb7d70f9ac 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -155,11 +155,24 @@ static inline void set_file_hugepages(struct file *file) { file->f_op = &hugetlbfs_file_operations; } + +static inline int valid_hugetlb_file_off(struct vm_area_struct *vma, + unsigned long address) +{ + struct inode *inode = vma->vm_file->f_dentry->d_inode; + loff_t file_off = address - vma->vm_start; + + file_off += (vma->vm_pgoff << PAGE_SHIFT); + + return (file_off < inode->i_size); +} + #else /* !CONFIG_HUGETLBFS */ #define is_file_hugepages(file) 0 #define set_file_hugepages(file) BUG() #define hugetlb_zero_setup(size) ERR_PTR(-ENOSYS) +#define valid_hugetlb_file_off(vma, address) 0 #endif /* !CONFIG_HUGETLBFS */ -- cgit v1.2.3 From 281dd25cdc0d6903929b79183816d151ea626341 Mon Sep 17 00:00:00 2001 From: Yasunori Goto Date: Wed, 19 Oct 2005 15:52:18 -0700 Subject: [PATCH] swiotlb: make sure initial DMA allocations really are in DMA memory This introduces a limit parameter to the core bootmem allocator; The new parameter indicates that physical memory allocated by the bootmem allocator should be within the requested limit. We also introduce alloc_bootmem_low_pages_limit, alloc_bootmem_node_limit, alloc_bootmem_low_pages_node_limit apis, but alloc_bootmem_low_pages_limit is the only api used for swiotlb. The existing alloc_bootmem_low_pages() api could instead have been changed and made to pass right limit to the core allocator. But that would make the patch more intrusive for 2.6.14, as other arches use alloc_bootmem_low_pages(). We may be done that post 2.6.14 as a cleanup. With this, swiotlb gets memory within 4G for both x86_64 and ia64 arches. Signed-off-by: Yasunori Goto Cc: Ravikiran G Thirumalai Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 32 ++++++++++++++++++++++++++++++-- 1 file changed, 30 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 82bd8842d11c..3b03b0b868dd 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -43,7 +43,7 @@ typedef struct bootmem_data { extern unsigned long __init bootmem_bootmap_pages (unsigned long); extern unsigned long __init init_bootmem (unsigned long addr, unsigned long memend); extern void __init free_bootmem (unsigned long addr, unsigned long size); -extern void * __init __alloc_bootmem (unsigned long size, unsigned long align, unsigned long goal); +extern void * __init __alloc_bootmem_limit (unsigned long size, unsigned long align, unsigned long goal, unsigned long limit); #ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE extern void __init reserve_bootmem (unsigned long addr, unsigned long size); #define alloc_bootmem(x) \ @@ -54,6 +54,16 @@ extern void __init reserve_bootmem (unsigned long addr, unsigned long size); __alloc_bootmem((x), PAGE_SIZE, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_low_pages(x) \ __alloc_bootmem((x), PAGE_SIZE, 0) + +#define alloc_bootmem_limit(x, limit) \ + __alloc_bootmem_limit((x), SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS), (limit)) +#define alloc_bootmem_low_limit(x, limit) \ + __alloc_bootmem_limit((x), SMP_CACHE_BYTES, 0, (limit)) +#define alloc_bootmem_pages_limit(x, limit) \ + __alloc_bootmem_limit((x), PAGE_SIZE, __pa(MAX_DMA_ADDRESS), (limit)) +#define alloc_bootmem_low_pages_limit(x, limit) \ + __alloc_bootmem_limit((x), PAGE_SIZE, 0, (limit)) + #endif /* !CONFIG_HAVE_ARCH_BOOTMEM_NODE */ extern unsigned long __init free_all_bootmem (void); @@ -61,7 +71,7 @@ extern unsigned long __init init_bootmem_node (pg_data_t *pgdat, unsigned long f extern void __init reserve_bootmem_node (pg_data_t *pgdat, unsigned long physaddr, unsigned long size); extern void __init free_bootmem_node (pg_data_t *pgdat, unsigned long addr, unsigned long size); extern unsigned long __init free_all_bootmem_node (pg_data_t *pgdat); -extern void * __init __alloc_bootmem_node (pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal); +extern void * __init __alloc_bootmem_node_limit (pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal, unsigned long limit); #ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE #define alloc_bootmem_node(pgdat, x) \ __alloc_bootmem_node((pgdat), (x), SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) @@ -69,6 +79,14 @@ extern void * __init __alloc_bootmem_node (pg_data_t *pgdat, unsigned long size, __alloc_bootmem_node((pgdat), (x), PAGE_SIZE, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_low_pages_node(pgdat, x) \ __alloc_bootmem_node((pgdat), (x), PAGE_SIZE, 0) + +#define alloc_bootmem_node_limit(pgdat, x, limit) \ + __alloc_bootmem_node_limit((pgdat), (x), SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS), (limit)) +#define alloc_bootmem_pages_node_limit(pgdat, x, limit) \ + __alloc_bootmem_node_limit((pgdat), (x), PAGE_SIZE, __pa(MAX_DMA_ADDRESS), (limit)) +#define alloc_bootmem_low_pages_node_limit(pgdat, x, limit) \ + __alloc_bootmem_node_limit((pgdat), (x), PAGE_SIZE, 0, (limit)) + #endif /* !CONFIG_HAVE_ARCH_BOOTMEM_NODE */ #ifdef CONFIG_HAVE_ARCH_ALLOC_REMAP @@ -105,5 +123,15 @@ extern void *__init alloc_large_system_hash(const char *tablename, #endif extern int __initdata hashdist; /* Distribute hashes across NUMA nodes? */ +static inline void *__alloc_bootmem (unsigned long size, unsigned long align, unsigned long goal) +{ + return __alloc_bootmem_limit(size, align, goal, 0); +} + +static inline void *__alloc_bootmem_node (pg_data_t *pgdat, unsigned long size, unsigned long align, + unsigned long goal) +{ + return __alloc_bootmem_node_limit(pgdat, size, align, goal, 0); +} #endif /* _LINUX_BOOTMEM_H */ -- cgit v1.2.3 From ac9b9c667c2e1194e22ebe0a441ae1c37aaa9b90 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 20 Oct 2005 16:24:28 +0100 Subject: [PATCH] Fix handling spurious page fault for hugetlb region This reverts commit 3359b54c8c07338f3a863d1109b42eebccdcf379 and replaces it with a cleaner version that is purely based on page table operations, so that the synchronization between inode size and hugetlb mappings becomes moot. Signed-off-by: Hugh Dickins Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 42cb7d70f9ac..d664330d900e 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -25,6 +25,8 @@ int is_hugepage_mem_enough(size_t); unsigned long hugetlb_total_pages(void); struct page *alloc_huge_page(void); void free_huge_page(struct page *); +int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, int write_access); extern unsigned long max_huge_pages; extern const unsigned long hugetlb_zero, hugetlb_infinity; @@ -99,6 +101,7 @@ static inline unsigned long hugetlb_total_pages(void) do { } while (0) #define alloc_huge_page() ({ NULL; }) #define free_huge_page(p) ({ (void)(p); BUG(); }) +#define hugetlb_fault(mm, vma, addr, write) ({ BUG(); 0; }) #ifndef HPAGE_MASK #define HPAGE_MASK 0 /* Keep the compiler happy */ @@ -155,24 +158,11 @@ static inline void set_file_hugepages(struct file *file) { file->f_op = &hugetlbfs_file_operations; } - -static inline int valid_hugetlb_file_off(struct vm_area_struct *vma, - unsigned long address) -{ - struct inode *inode = vma->vm_file->f_dentry->d_inode; - loff_t file_off = address - vma->vm_start; - - file_off += (vma->vm_pgoff << PAGE_SHIFT); - - return (file_off < inode->i_size); -} - #else /* !CONFIG_HUGETLBFS */ #define is_file_hugepages(file) 0 #define set_file_hugepages(file) BUG() #define hugetlb_zero_setup(size) ERR_PTR(-ENOSYS) -#define valid_hugetlb_file_off(vma, address) 0 #endif /* !CONFIG_HUGETLBFS */ -- cgit v1.2.3 From 11e29e21514517f3022a1f30998ac4c7b1197658 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Fri, 21 Oct 2005 18:46:32 -0400 Subject: libata: handle early device PIO modes correctly --- include/linux/ata.h | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index 630908c9378b..33276d1d05d2 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -42,13 +42,18 @@ enum { ATA_SECT_SIZE = 512, ATA_ID_WORDS = 256, - ATA_ID_PROD_OFS = 27, - ATA_ID_FW_REV_OFS = 23, ATA_ID_SERNO_OFS = 10, - ATA_ID_MAJOR_VER = 80, - ATA_ID_PIO_MODES = 64, + ATA_ID_FW_REV_OFS = 23, + ATA_ID_PROD_OFS = 27, + ATA_ID_OLD_PIO_MODES = 51, + ATA_ID_FIELD_VALID = 53, ATA_ID_MWDMA_MODES = 63, + ATA_ID_PIO_MODES = 64, + ATA_ID_EIDE_DMA_MIN = 65, + ATA_ID_EIDE_PIO = 67, + ATA_ID_EIDE_PIO_IORDY = 68, ATA_ID_UDMA_MODES = 88, + ATA_ID_MAJOR_VER = 80, ATA_ID_PIO4 = (1 << 1), ATA_PCI_CTL_OFS = 2, -- cgit v1.2.3 From 452503f993feffe96e8cc9fbff4888b96e2c5e40 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Fri, 21 Oct 2005 19:01:32 -0400 Subject: Add ide-timing functionality to libata. This is needed for full AMD and VIA drivers and possibly more. Functions to turn actual clocking and cycle timings into register values. Also to merge shared timings to compute an optimal timing set. Built from the drivers/ide version by Vojtech Pavlik Signed-off-by: Alan Cox Signed-off-by: Jeff Garzik --- include/linux/libata.h | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 0261c55f3483..0e214f8c8f9f 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -388,6 +388,19 @@ struct ata_port_info { struct ata_port_operations *port_ops; }; +struct ata_timing { + unsigned short mode; /* ATA mode */ + unsigned short setup; /* t1 */ + unsigned short act8b; /* t2 for 8-bit I/O */ + unsigned short rec8b; /* t2i for 8-bit I/O */ + unsigned short cyc8b; /* t0 for 8-bit I/O */ + unsigned short active; /* t2 or tD */ + unsigned short recover; /* t2i or tK */ + unsigned short cycle; /* t0 */ + unsigned short udma; /* t2CYCTYP/2 */ +}; + +#define FIT(v,vmin,vmax) max_t(short,min_t(short,v,vmax),vmin) extern void ata_port_probe(struct ata_port *); extern void __sata_phy_reset(struct ata_port *ap); @@ -451,6 +464,32 @@ extern int ata_std_bios_param(struct scsi_device *sdev, sector_t capacity, int geom[]); extern int ata_scsi_slave_config(struct scsi_device *sdev); +/* + * Timing helpers + */ +extern int ata_timing_compute(struct ata_device *, unsigned short, + struct ata_timing *, int, int); +extern void ata_timing_merge(const struct ata_timing *, + const struct ata_timing *, struct ata_timing *, + unsigned int); + +enum { + ATA_TIMING_SETUP = (1 << 0), + ATA_TIMING_ACT8B = (1 << 1), + ATA_TIMING_REC8B = (1 << 2), + ATA_TIMING_CYC8B = (1 << 3), + ATA_TIMING_8BIT = ATA_TIMING_ACT8B | ATA_TIMING_REC8B | + ATA_TIMING_CYC8B, + ATA_TIMING_ACTIVE = (1 << 4), + ATA_TIMING_RECOVER = (1 << 5), + ATA_TIMING_CYCLE = (1 << 6), + ATA_TIMING_UDMA = (1 << 7), + ATA_TIMING_ALL = ATA_TIMING_SETUP | ATA_TIMING_ACT8B | + ATA_TIMING_REC8B | ATA_TIMING_CYC8B | + ATA_TIMING_ACTIVE | ATA_TIMING_RECOVER | + ATA_TIMING_CYCLE | ATA_TIMING_UDMA, +}; + #ifdef CONFIG_PCI struct pci_bits { -- cgit v1.2.3 From cf482935c6abe5245e481213c6e6df808c976f56 Mon Sep 17 00:00:00 2001 From: Jeff Garzik Date: Sat, 22 Oct 2005 00:19:33 -0400 Subject: libata: turn on block layer clustering --- include/linux/libata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 0e214f8c8f9f..634b5aa0a615 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -91,7 +91,7 @@ enum { ATA_SHT_EMULATED = 1, ATA_SHT_CMD_PER_LUN = 1, ATA_SHT_THIS_ID = -1, - ATA_SHT_USE_CLUSTERING = 0, + ATA_SHT_USE_CLUSTERING = 1, /* struct ata_device stuff */ ATA_DFLAG_LBA48 = (1 << 0), /* device supports LBA48 */ -- cgit v1.2.3 From 057ace5e79da9ebf2aa82833cfea825533ac06fb Mon Sep 17 00:00:00 2001 From: Jeff Garzik Date: Sat, 22 Oct 2005 14:27:05 -0400 Subject: libata: const-ification bombing run Enforce access rules where appropriate. If the compiler is smart enough, this may buy us an optimization or two as a side effect. --- include/linux/ata.h | 6 +++--- include/linux/libata.h | 32 ++++++++++++++++---------------- 2 files changed, 19 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index 33276d1d05d2..d2873b732bb1 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -261,7 +261,7 @@ struct ata_taskfile { ((u64) (id)[(n) + 1] << 16) | \ ((u64) (id)[(n) + 0]) ) -static inline int ata_id_current_chs_valid(u16 *id) +static inline int ata_id_current_chs_valid(const u16 *id) { /* For ATA-1 devices, if the INITIALIZE DEVICE PARAMETERS command has not been issued to the device then the values of @@ -273,7 +273,7 @@ static inline int ata_id_current_chs_valid(u16 *id) id[56]; /* sectors in current translation */ } -static inline int atapi_cdb_len(u16 *dev_id) +static inline int atapi_cdb_len(const u16 *dev_id) { u16 tmp = dev_id[0] & 0x3; switch (tmp) { @@ -283,7 +283,7 @@ static inline int atapi_cdb_len(u16 *dev_id) } } -static inline int is_atapi_taskfile(struct ata_taskfile *tf) +static inline int is_atapi_taskfile(const struct ata_taskfile *tf) { return (tf->protocol == ATA_PROT_ATAPI) || (tf->protocol == ATA_PROT_ATAPI_NODATA) || diff --git a/include/linux/libata.h b/include/linux/libata.h index 634b5aa0a615..00a8a5738858 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -202,7 +202,7 @@ struct ata_ioports { struct ata_probe_ent { struct list_head node; struct device *dev; - struct ata_port_operations *port_ops; + const struct ata_port_operations *port_ops; Scsi_Host_Template *sht; struct ata_ioports port[ATA_MAX_PORTS]; unsigned int n_ports; @@ -225,7 +225,7 @@ struct ata_host_set { void __iomem *mmio_base; unsigned int n_ports; void *private_data; - struct ata_port_operations *ops; + const struct ata_port_operations *ops; struct ata_port * ports[0]; }; @@ -294,7 +294,7 @@ struct ata_device { struct ata_port { struct Scsi_Host *host; /* our co-allocated scsi host */ - struct ata_port_operations *ops; + const struct ata_port_operations *ops; unsigned long flags; /* ATA_FLAG_xxx */ unsigned int id; /* unique id req'd by scsi midlyr */ unsigned int port_no; /* unique port #; from zero */ @@ -341,10 +341,10 @@ struct ata_port_operations { void (*set_piomode) (struct ata_port *, struct ata_device *); void (*set_dmamode) (struct ata_port *, struct ata_device *); - void (*tf_load) (struct ata_port *ap, struct ata_taskfile *tf); + void (*tf_load) (struct ata_port *ap, const struct ata_taskfile *tf); void (*tf_read) (struct ata_port *ap, struct ata_taskfile *tf); - void (*exec_command)(struct ata_port *ap, struct ata_taskfile *tf); + void (*exec_command)(struct ata_port *ap, const struct ata_taskfile *tf); u8 (*check_status)(struct ata_port *ap); u8 (*check_altstatus)(struct ata_port *ap); u8 (*check_err)(struct ata_port *ap); @@ -385,7 +385,7 @@ struct ata_port_info { unsigned long pio_mask; unsigned long mwdma_mask; unsigned long udma_mask; - struct ata_port_operations *port_ops; + const struct ata_port_operations *port_ops; }; struct ata_timing { @@ -413,7 +413,7 @@ extern int ata_pci_init_one (struct pci_dev *pdev, struct ata_port_info **port_i unsigned int n_ports); extern void ata_pci_remove_one (struct pci_dev *pdev); #endif /* CONFIG_PCI */ -extern int ata_device_add(struct ata_probe_ent *ent); +extern int ata_device_add(const 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); @@ -426,16 +426,16 @@ extern int ata_ratelimit(void); /* * Default driver ops implementations */ -extern void ata_tf_load(struct ata_port *ap, struct ata_taskfile *tf); +extern void ata_tf_load(struct ata_port *ap, const struct ata_taskfile *tf); extern void ata_tf_read(struct ata_port *ap, struct ata_taskfile *tf); -extern void ata_tf_to_fis(struct ata_taskfile *tf, u8 *fis, u8 pmp); -extern void ata_tf_from_fis(u8 *fis, struct ata_taskfile *tf); +extern void ata_tf_to_fis(const struct ata_taskfile *tf, u8 *fis, u8 pmp); +extern void ata_tf_from_fis(const u8 *fis, struct ata_taskfile *tf); extern void ata_noop_dev_select (struct ata_port *ap, unsigned int device); extern void ata_std_dev_select (struct ata_port *ap, unsigned int device); extern u8 ata_check_status(struct ata_port *ap); extern u8 ata_altstatus(struct ata_port *ap); extern u8 ata_chk_err(struct ata_port *ap); -extern void ata_exec_command(struct ata_port *ap, struct ata_taskfile *tf); +extern void ata_exec_command(struct ata_port *ap, const struct ata_taskfile *tf); extern int ata_port_start (struct ata_port *ap); extern void ata_port_stop (struct ata_port *ap); extern void ata_host_stop (struct ata_host_set *host_set); @@ -446,8 +446,8 @@ extern void ata_sg_init_one(struct ata_queued_cmd *qc, void *buf, unsigned int buflen); extern void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg, unsigned int n_elem); -extern unsigned int ata_dev_classify(struct ata_taskfile *tf); -extern void ata_dev_id_string(u16 *id, unsigned char *s, +extern unsigned int ata_dev_classify(const struct ata_taskfile *tf); +extern void ata_dev_id_string(const u16 *id, unsigned char *s, unsigned int ofs, unsigned int len); extern void ata_dev_config(struct ata_port *ap, unsigned int i); extern void ata_bmdma_setup (struct ata_queued_cmd *qc); @@ -502,7 +502,7 @@ struct pci_bits { extern void ata_pci_host_stop (struct ata_host_set *host_set); extern struct ata_probe_ent * ata_pci_init_native_mode(struct pci_dev *pdev, struct ata_port_info **port, int portmask); -extern int pci_test_config_bits(struct pci_dev *pdev, struct pci_bits *bits); +extern int pci_test_config_bits(struct pci_dev *pdev, const struct pci_bits *bits); #endif /* CONFIG_PCI */ @@ -512,7 +512,7 @@ static inline unsigned int ata_tag_valid(unsigned int tag) return (tag < ATA_MAX_QUEUE) ? 1 : 0; } -static inline unsigned int ata_dev_present(struct ata_device *dev) +static inline unsigned int ata_dev_present(const struct ata_device *dev) { return ((dev->class == ATA_DEV_ATA) || (dev->class == ATA_DEV_ATAPI)); @@ -711,7 +711,7 @@ static inline unsigned int sata_dev_present(struct ata_port *ap) return ((scr_read(ap, SCR_STATUS) & 0xf) == 0x3) ? 1 : 0; } -static inline int ata_try_flush_cache(struct ata_device *dev) +static inline int ata_try_flush_cache(const struct ata_device *dev) { return ata_id_wcache_enabled(dev->id) || ata_id_has_flush(dev->id) || -- cgit v1.2.3 From 8d3b35914aa54232b27e6a2b57d84092aadc5e86 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Sun, 23 Oct 2005 12:57:18 -0700 Subject: [PATCH] inotify/idr leak fix Fix a bug which was reported and diagnosed by Stefan Jones IDR trees include a cache of idr_layer objects. There's no way to destroy this cache, so when we discard an overall idr tree we end up leaking some memory. Add and use idr_destroy() for this. v9fs and infiniband also need to use idr_destroy() to avoid leaks. Or, we make the cache global, like radix_tree_preload(). Which is probably better. Later. Cc: Eric Van Hensbergen Cc: Roland Dreier Cc: Robert Love Cc: John McCutchan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/idr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index ca3b7e462576..3d5de45f961b 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -75,4 +75,5 @@ int idr_pre_get(struct idr *idp, unsigned gfp_mask); int idr_get_new(struct idr *idp, void *ptr, int *id); int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id); void idr_remove(struct idr *idp, int id); +void idr_destroy(struct idr *idp); void idr_init(struct idr *idp); -- cgit v1.2.3 From add7b58e7558dd2894f3c17ca8574099fcba5c15 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Mon, 24 Oct 2005 22:11:57 +0100 Subject: [SERIAL] support the Exsys EX-4055 4S four-port card Tested by Wolfgang Denk with this device: 00:0f.0 Network controller: PLX Technology, Inc. PCI <-> IOBus Bridge (rev 01) Subsystem: Exsys EX-4055 4S(16C550) RS-232 Control: I/O+ Mem+ BusMaster- SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B- Status: Cap- 66Mhz- UDF- FastB2B+ ParErr- DEVSEL=medium >TAbort- SERR- Signed-off-by: Russell King --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index f74ed9462475..ca0691c319ab 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2696,6 +2696,7 @@ #define PCI_SUBVENDOR_ID_EXSYS 0xd84d #define PCI_SUBDEVICE_ID_EXSYS_4014 0x4014 +#define PCI_SUBDEVICE_ID_EXSYS_4055 0x4055 #define PCI_VENDOR_ID_TIGERJET 0xe159 #define PCI_DEVICE_ID_TIGERJET_300 0x0001 -- cgit v1.2.3 From 551f8f0e87becb415c522adccab524a7a05ca83a Mon Sep 17 00:00:00 2001 From: Justin Chen Date: Mon, 24 Oct 2005 22:16:38 +0100 Subject: [SERIAL] new hp diva console port Add the new ID 0x132a and configure the new PCI Diva console port. This device supports only 1 single console UART. Signed-off-by: Andrew Morton Signed-off-by: Russell King --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index ca0691c319ab..71834f05504f 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -723,6 +723,7 @@ #define PCI_DEVICE_ID_HP_DIVA_EVEREST 0x1282 #define PCI_DEVICE_ID_HP_DIVA_AUX 0x1290 #define PCI_DEVICE_ID_HP_DIVA_RMP3 0x1301 +#define PCI_DEVICE_ID_HP_DIVA_HURRICANE 0x132a #define PCI_DEVICE_ID_HP_CISS 0x3210 #define PCI_DEVICE_ID_HP_CISSA 0x3220 #define PCI_DEVICE_ID_HP_CISSB 0x3222 -- cgit v1.2.3 From c83c24861882758b9731e8550225cd1e52a4cd1c Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 18 Oct 2005 22:07:41 -0700 Subject: [SK_BUFF] kernel-doc: fix skbuff warnings Add kernel-doc to skbuff.h, skbuff.c to eliminate kernel-doc warnings. Signed-off-by: Randy Dunlap Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/skbuff.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 8f5d9e7f8734..b756935da9c8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -171,7 +171,6 @@ enum { * struct sk_buff - socket buffer * @next: Next buffer in list * @prev: Previous buffer in list - * @list: List we are on * @sk: Socket we are owned by * @tstamp: Time we arrived * @dev: Device we arrived on/are leaving by @@ -190,6 +189,7 @@ enum { * @cloned: Head may be cloned (check refcnt to be sure) * @nohdr: Payload reference only, must not modify header * @pkt_type: Packet class + * @fclone: skbuff clone status * @ip_summed: Driver fed us an IP checksum * @priority: Packet queueing priority * @users: User count - see {datagram,tcp}.c @@ -202,6 +202,7 @@ enum { * @destructor: Destruct function * @nfmark: Can be used for communication between hooks * @nfct: Associated connection, if any + * @ipvs_property: skbuff is owned by ipvs * @nfctinfo: Relationship of this skb to the connection * @nf_bridge: Saved data about a bridged frame - see br_netfilter.c * @tc_index: Traffic control index -- cgit v1.2.3 From 0e574af1be5f569a5d7f2800333b0bfb358a5e34 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 27 Oct 2005 22:12:38 -0400 Subject: NFS: Cleanup initialisation of struct nfs_fattr Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 7bac2785c6e4..8120fd68dee5 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -316,6 +316,11 @@ extern void nfs_file_clear_open_context(struct file *filp); /* linux/net/ipv4/ipconfig.c: trims ip addr off front of name, too. */ extern u32 root_nfs_parse_addr(char *name); /*__init*/ +static inline void nfs_fattr_init(struct nfs_fattr *fattr) +{ + fattr->valid = 0; +} + /* * linux/fs/nfs/file.c */ -- cgit v1.2.3 From 913a70fc170530f7e1ff0693595155457cc6d0ca Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 27 Oct 2005 22:12:38 -0400 Subject: NFS: Convert cache_change_attribute into a jiffy-based value Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 8120fd68dee5..abf890f5fbfb 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -280,7 +280,7 @@ static inline long nfs_save_change_attribute(struct inode *inode) static inline int nfs_verify_change_attribute(struct inode *inode, unsigned long chattr) { return !nfs_caches_unstable(inode) - && chattr == NFS_I(inode)->cache_change_attribute; + && time_after_eq(chattr, NFS_I(inode)->cache_change_attribute); } /* -- cgit v1.2.3 From 33801147a8fda6b04d7e9afe1d42f1c01d3d6837 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 27 Oct 2005 22:12:39 -0400 Subject: NFS: Optimise inode attribute cache updates Allow nfs_refresh_inode() also to update attributes on the inode if the RPC call was sent after the last call to nfs_update_inode(). Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 2 ++ include/linux/nfs_xdr.h | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index abf890f5fbfb..faeaad666ca8 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -141,6 +141,7 @@ struct nfs_inode { unsigned long attrtimeo_timestamp; __u64 change_attr; /* v4 only */ + unsigned long last_updated; /* "Generation counter" for the attribute cache. This is * bumped whenever we update the metadata on the * server. @@ -319,6 +320,7 @@ extern u32 root_nfs_parse_addr(char *name); /*__init*/ static inline void nfs_fattr_init(struct nfs_fattr *fattr) { fattr->valid = 0; + fattr->time_start = jiffies; } /* diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 60086dac11d5..aeaee7e7c51d 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -41,7 +41,7 @@ struct nfs_fattr { __u32 bitmap[2]; /* NFSv4 returned attribute bitmap */ __u64 change_attr; /* NFSv4 change attribute */ __u64 pre_change_attr;/* pre-op NFSv4 change attribute */ - unsigned long timestamp; + unsigned long time_start; }; #define NFS_ATTR_WCC 0x0001 /* pre-op WCC data */ -- cgit v1.2.3 From decf491f3076190262d4c649bed877650623903a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 27 Oct 2005 22:12:39 -0400 Subject: NFS: Don't let nfs_end_data_update() clobber attribute update information Since we almost always call nfs_end_data_update() after we called nfs_refresh_inode(), we now end up marking the inode metadata as needing revalidation immediately after having updated it. This patch rearranges things so that we mark the inode as needing revalidation _before_ we call nfs_refresh_inode() on those operations that need it. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index faeaad666ca8..325fe7ae49bb 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -241,13 +241,17 @@ static inline int nfs_caches_unstable(struct inode *inode) return atomic_read(&NFS_I(inode)->data_updates) != 0; } +static inline void nfs_mark_for_revalidate(struct inode *inode) +{ + spin_lock(&inode->i_lock); + NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS; + spin_unlock(&inode->i_lock); +} + static inline void NFS_CACHEINV(struct inode *inode) { - if (!nfs_caches_unstable(inode)) { - spin_lock(&inode->i_lock); - NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS; - spin_unlock(&inode->i_lock); - } + if (!nfs_caches_unstable(inode)) + nfs_mark_for_revalidate(inode); } static inline int nfs_server_capable(struct inode *inode, int cap) @@ -291,6 +295,7 @@ extern void nfs_zap_caches(struct inode *); extern struct inode *nfs_fhget(struct super_block *, struct nfs_fh *, struct nfs_fattr *); extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *); +extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_getattr(struct vfsmount *, struct dentry *, struct kstat *); extern int nfs_permission(struct inode *, int, struct nameidata *); extern int nfs_access_get_cached(struct inode *, struct rpc_cred *, struct nfs_access_entry *); -- cgit v1.2.3 From 56ae19f38f10aad4f27f7e12138a29b295dff07a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 27 Oct 2005 22:12:40 -0400 Subject: NFSv4: Add directory post-op attributes to the CREATE operations. Since the directory attributes change every time we CREATE a file, we might as well pick up the new directory attributes in the same compound. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index aeaee7e7c51d..6485b8b41b83 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -124,6 +124,7 @@ struct nfs_openres { struct nfs4_change_info cinfo; __u32 rflags; struct nfs_fattr * f_attr; + struct nfs_fattr * dir_attr; const struct nfs_server *server; int delegation_type; nfs4_stateid delegation; @@ -540,6 +541,7 @@ struct nfs4_create_res { struct nfs_fh * fh; struct nfs_fattr * fattr; struct nfs4_change_info dir_cinfo; + struct nfs_fattr * dir_fattr; }; struct nfs4_fsinfo_arg { -- cgit v1.2.3 From 516a6af641bb50c608329a5bd751acd0d65cc4ab Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 27 Oct 2005 22:12:41 -0400 Subject: NFS: Add optional post-op getattr instruction to the NFSv4 file close. "Optional" means that the close call will not fail if the getattr at the end of the compound fails. If it does succeed, try to refresh inode attributes. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 6485b8b41b83..4f03dc21cf4a 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -153,10 +153,13 @@ struct nfs_closeargs { nfs4_stateid * stateid; struct nfs_seqid * seqid; int open_flags; + const u32 * bitmask; }; struct nfs_closeres { nfs4_stateid stateid; + struct nfs_fattr * fattr; + const struct nfs_server *server; }; /* * * Arguments to the lock,lockt, and locku call. -- cgit v1.2.3 From 91ba2eeec5e8e86e054937eb3bf5aec5b22b1830 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 27 Oct 2005 22:12:42 -0400 Subject: NFSv4: Add post-op attributes to nfs4_proc_link() Optimise attribute revalidation when hardlinking. Add post-op attributes for the directory and the original inode. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 4f03dc21cf4a..89238b799cfd 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -566,8 +566,17 @@ struct nfs4_link_arg { const struct nfs_fh * fh; const struct nfs_fh * dir_fh; const struct qstr * name; + const u32 * bitmask; +}; + +struct nfs4_link_res { + const struct nfs_server * server; + struct nfs_fattr * fattr; + struct nfs4_change_info cinfo; + struct nfs_fattr * dir_attr; }; + struct nfs4_lookup_arg { const struct nfs_fh * dir_fh; const struct qstr * name; -- cgit v1.2.3 From 6caf2c8276d371679a798058e8fdf49f5ff831a3 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 27 Oct 2005 22:12:43 -0400 Subject: NFSv4: Add post-op attributes to nfs4_proc_rename() Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 89238b799cfd..6f0804280824 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -630,11 +630,15 @@ struct nfs4_rename_arg { const struct nfs_fh * new_dir; const struct qstr * old_name; const struct qstr * new_name; + const u32 * bitmask; }; struct nfs4_rename_res { + const struct nfs_server * server; struct nfs4_change_info old_cinfo; + struct nfs_fattr * old_fattr; struct nfs4_change_info new_cinfo; + struct nfs_fattr * new_fattr; }; struct nfs4_setclientid { -- cgit v1.2.3 From 16e429596dec4d28e16812b3a9be27f18412c567 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 27 Oct 2005 22:12:44 -0400 Subject: NFSv4: Add post-op attributes to nfs4_proc_remove() Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 6f0804280824..deeba7e2c518 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -623,6 +623,13 @@ struct nfs4_readlink { struct nfs4_remove_arg { const struct nfs_fh * fh; const struct qstr * name; + const u32 * bitmask; +}; + +struct nfs4_remove_res { + const struct nfs_server * server; + struct nfs4_change_info cinfo; + struct nfs_fattr * dir_attr; }; struct nfs4_rename_arg { -- cgit v1.2.3 From 4f9838c7ecd14f31f701f64fa65ded132fc0db8a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 27 Oct 2005 22:12:44 -0400 Subject: NFSv4: Add post-op attributes to NFSv4 write and commit callbacks. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index deeba7e2c518..40718669b9c8 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -256,6 +256,7 @@ struct nfs_writeargs { enum nfs3_stable_how stable; unsigned int pgbase; struct page ** pages; + const u32 * bitmask; }; struct nfs_writeverf { @@ -267,6 +268,7 @@ struct nfs_writeres { struct nfs_fattr * fattr; struct nfs_writeverf * verf; __u32 count; + const struct nfs_server *server; }; /* -- cgit v1.2.3 From 20e5c81fcff89535dced2ed71cf24c6c648ff40e Mon Sep 17 00:00:00 2001 From: "Chen, Kenneth W" Date: Thu, 13 Oct 2005 21:48:42 +0200 Subject: [patch] remove gendisk->stamp_idle field struct gendisk has these two fields: stamp, stamp_idle. Update to stamp_idle is always in sync with stamp and they are always the same. Therefore, it does not add any value in having two fields tracking same timestamp. Suggest to remove it. Also, we should only update gendisk stats with non-zero value. Advantage is that we don't have to needlessly calculate memory address, and then add zero to the content. Signed-off-by: Ken Chen Signed-off-by: Jens Axboe --- include/linux/genhd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 01796c41c951..142e1c1e0689 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -119,7 +119,7 @@ struct gendisk { int policy; atomic_t sync_io; /* RAID */ - unsigned long stamp, stamp_idle; + unsigned long stamp; int in_flight; #ifdef CONFIG_SMP struct disk_stats *dkstats; -- cgit v1.2.3 From 8922e16cf6269e668123acb1ae1fdc62b7a3a4fc Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 20 Oct 2005 16:23:44 +0200 Subject: [PATCH] 01/05 Implement generic dispatch queue Implements generic dispatch queue which can replace all dispatch queues implemented by each iosched. This reduces code duplication, eases enforcing semantics over dispatch queue, and simplifies specific ioscheds. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 17 +++++++++++------ include/linux/elevator.h | 16 +++++++--------- 2 files changed, 18 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index efdc9b5bc05c..2c7b9154927a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -203,6 +203,7 @@ struct request { enum rq_flag_bits { __REQ_RW, /* not set, read. set, write */ __REQ_FAILFAST, /* no low level driver retries */ + __REQ_SORTED, /* elevator knows about this request */ __REQ_SOFTBARRIER, /* may not be passed by ioscheduler */ __REQ_HARDBARRIER, /* may not be passed by drive either */ __REQ_CMD, /* is a regular fs rw request */ @@ -235,6 +236,7 @@ enum rq_flag_bits { #define REQ_RW (1 << __REQ_RW) #define REQ_FAILFAST (1 << __REQ_FAILFAST) +#define REQ_SORTED (1 << __REQ_SORTED) #define REQ_SOFTBARRIER (1 << __REQ_SOFTBARRIER) #define REQ_HARDBARRIER (1 << __REQ_HARDBARRIER) #define REQ_CMD (1 << __REQ_CMD) @@ -332,6 +334,13 @@ struct request_queue prepare_flush_fn *prepare_flush_fn; end_flush_fn *end_flush_fn; + /* + * Dispatch queue sorting + */ + sector_t last_sector; + struct request *boundary_rq; + unsigned int max_back_kb; + /* * Auto-unplugging state */ @@ -454,6 +463,7 @@ enum { #define blk_pm_request(rq) \ ((rq)->flags & (REQ_PM_SUSPEND | REQ_PM_RESUME)) +#define blk_sorted_rq(rq) ((rq)->flags & REQ_SORTED) #define blk_barrier_rq(rq) ((rq)->flags & REQ_HARDBARRIER) #define blk_barrier_preflush(rq) ((rq)->flags & REQ_BAR_PREFLUSH) #define blk_barrier_postflush(rq) ((rq)->flags & REQ_BAR_POSTFLUSH) @@ -611,12 +621,7 @@ extern void end_request(struct request *req, int uptodate); static inline void blkdev_dequeue_request(struct request *req) { - BUG_ON(list_empty(&req->queuelist)); - - list_del_init(&req->queuelist); - - if (req->rl) - elv_remove_request(req->q, req); + elv_dequeue_request(req->q, req); } /* diff --git a/include/linux/elevator.h b/include/linux/elevator.h index ea6bbc2d7407..76f4f6920744 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -8,18 +8,17 @@ typedef void (elevator_merge_req_fn) (request_queue_t *, struct request *, struc typedef void (elevator_merged_fn) (request_queue_t *, struct request *); -typedef struct request *(elevator_next_req_fn) (request_queue_t *); +typedef int (elevator_dispatch_fn) (request_queue_t *, int); -typedef void (elevator_add_req_fn) (request_queue_t *, struct request *, int); +typedef void (elevator_add_req_fn) (request_queue_t *, struct request *); typedef int (elevator_queue_empty_fn) (request_queue_t *); -typedef void (elevator_remove_req_fn) (request_queue_t *, struct request *); -typedef void (elevator_requeue_req_fn) (request_queue_t *, struct request *); typedef struct request *(elevator_request_list_fn) (request_queue_t *, struct request *); typedef void (elevator_completed_req_fn) (request_queue_t *, struct request *); typedef int (elevator_may_queue_fn) (request_queue_t *, int, struct bio *); typedef int (elevator_set_req_fn) (request_queue_t *, struct request *, struct bio *, int); typedef void (elevator_put_req_fn) (request_queue_t *, struct request *); +typedef void (elevator_activate_req_fn) (request_queue_t *, struct request *); typedef void (elevator_deactivate_req_fn) (request_queue_t *, struct request *); typedef int (elevator_init_fn) (request_queue_t *, elevator_t *); @@ -31,10 +30,9 @@ struct elevator_ops elevator_merged_fn *elevator_merged_fn; elevator_merge_req_fn *elevator_merge_req_fn; - elevator_next_req_fn *elevator_next_req_fn; + elevator_dispatch_fn *elevator_dispatch_fn; elevator_add_req_fn *elevator_add_req_fn; - elevator_remove_req_fn *elevator_remove_req_fn; - elevator_requeue_req_fn *elevator_requeue_req_fn; + elevator_activate_req_fn *elevator_activate_req_fn; elevator_deactivate_req_fn *elevator_deactivate_req_fn; elevator_queue_empty_fn *elevator_queue_empty_fn; @@ -81,15 +79,15 @@ struct elevator_queue /* * block elevator interface */ +extern void elv_dispatch_insert(request_queue_t *, struct request *, int); extern void elv_add_request(request_queue_t *, struct request *, int, int); extern void __elv_add_request(request_queue_t *, struct request *, int, int); extern int elv_merge(request_queue_t *, struct request **, struct bio *); extern void elv_merge_requests(request_queue_t *, struct request *, struct request *); extern void elv_merged_request(request_queue_t *, struct request *); -extern void elv_remove_request(request_queue_t *, struct request *); +extern void elv_dequeue_request(request_queue_t *, struct request *); extern void elv_requeue_request(request_queue_t *, struct request *); -extern void elv_deactivate_request(request_queue_t *, struct request *); extern int elv_queue_empty(request_queue_t *); extern struct request *elv_next_request(struct request_queue *q); extern struct request *elv_former_request(request_queue_t *, struct request *); -- cgit v1.2.3 From 1b47f531e244e339b648dfff071c086f936e49e1 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 20 Oct 2005 16:37:00 +0200 Subject: [PATCH] generic dispatch fixes - Split elv_dispatch_insert() into two functions - Rename rq_last_sector() to rq_end_sector() Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 13 ++++++++++++- include/linux/elevator.h | 4 +++- 2 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2c7b9154927a..a2e496f285a4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -337,7 +337,7 @@ struct request_queue /* * Dispatch queue sorting */ - sector_t last_sector; + sector_t end_sector; struct request *boundary_rq; unsigned int max_back_kb; @@ -624,6 +624,17 @@ static inline void blkdev_dequeue_request(struct request *req) elv_dequeue_request(req->q, req); } +/* + * This should be in elevator.h, but that requires pulling in rq and q + */ +static inline void elv_dispatch_add_tail(struct request_queue *q, + struct request *rq) +{ + q->end_sector = rq_end_sector(rq); + q->boundary_rq = rq; + list_add_tail(&rq->queuelist, &q->queue_head); +} + /* * Access functions for manipulating queue properties */ diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 76f4f6920744..f9b5ec38121a 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -79,7 +79,7 @@ struct elevator_queue /* * block elevator interface */ -extern void elv_dispatch_insert(request_queue_t *, struct request *, int); +extern void elv_dispatch_sort(request_queue_t *, struct request *); extern void elv_add_request(request_queue_t *, struct request *, int, int); extern void __elv_add_request(request_queue_t *, struct request *, int, int); extern int elv_merge(request_queue_t *, struct request **, struct bio *); @@ -140,4 +140,6 @@ enum { ELV_MQUEUE_MUST, }; +#define rq_end_sector(rq) ((rq)->sector + (rq)->nr_sectors) + #endif -- cgit v1.2.3 From 06b86245c052963029bfd9020ca1f08ceb66f85a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 20 Oct 2005 16:46:23 +0200 Subject: [PATCH] 03/05 move last_merge handlin into generic elevator code Currently, both generic elevator code and specific ioscheds participate in the management and usage of last_merge. This and the following patches move last_merge handling into generic elevator code. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a2e496f285a4..bd55b1df8997 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -630,6 +630,9 @@ static inline void blkdev_dequeue_request(struct request *req) static inline void elv_dispatch_add_tail(struct request_queue *q, struct request *rq) { + if (q->last_merge == rq) + q->last_merge = NULL; + q->end_sector = rq_end_sector(rq); q->boundary_rq = rq; list_add_tail(&rq->queuelist, &q->queue_head); -- cgit v1.2.3 From cb19833dccb32f97cacbfff834b53523915f13f6 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 24 Oct 2005 08:35:58 +0200 Subject: [BLOCK] kill generic max_back_kb handling This patch kills max_back_kb handling from elv_dispatch_sort() and kills max_back_kb field from struct request_queue. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bd55b1df8997..159dbcd2eb59 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -339,7 +339,6 @@ struct request_queue */ sector_t end_sector; struct request *boundary_rq; - unsigned int max_back_kb; /* * Auto-unplugging state -- cgit v1.2.3 From cb98fc8bb9c141009e2bda99c0db39d387e142cf Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 28 Oct 2005 08:29:39 +0200 Subject: [BLOCK] Reimplement elevator switch This patch reimplements elevator switch. This patch assumes generic dispatch queue patchset is applied. * Each request is tagged with REQ_ELVPRIV flag if it has its elevator private data set. * Requests which doesn't have REQ_ELVPRIV flag set never enter iosched. They are always directly back inserted to dispatch queue. Of course, elevator_put_req_fn is called only for requests which have its REQ_ELVPRIV set. * Request queue maintains the current number of requests which have its elevator data set (elevator_set_req_fn called) in q->rq->elvpriv. * If a request queue has QUEUE_FLAG_BYPASS set, elevator private data is not allocated for new requests. To switch to another iosched, we set QUEUE_FLAG_BYPASS and wait until elvpriv goes to zero; then, we attach the new iosched and clears QUEUE_FLAG_BYPASS. New implementation is much simpler and main code paths are less cluttered, IMHO. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 159dbcd2eb59..6186d5e2110f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -107,9 +107,9 @@ typedef void (rq_end_io_fn)(struct request *); struct request_list { int count[2]; int starved[2]; + int elvpriv; mempool_t *rq_pool; wait_queue_head_t wait[2]; - wait_queue_head_t drain; }; #define BLK_MAX_CDB 16 @@ -211,6 +211,7 @@ enum rq_flag_bits { __REQ_STARTED, /* drive already may have started this one */ __REQ_DONTPREP, /* don't call prep for this one */ __REQ_QUEUED, /* uses queueing */ + __REQ_ELVPRIV, /* elevator private data attached */ /* * for ATA/ATAPI devices */ @@ -244,6 +245,7 @@ enum rq_flag_bits { #define REQ_STARTED (1 << __REQ_STARTED) #define REQ_DONTPREP (1 << __REQ_DONTPREP) #define REQ_QUEUED (1 << __REQ_QUEUED) +#define REQ_ELVPRIV (1 << __REQ_ELVPRIV) #define REQ_PC (1 << __REQ_PC) #define REQ_BLOCK_PC (1 << __REQ_BLOCK_PC) #define REQ_SENSE (1 << __REQ_SENSE) @@ -413,8 +415,6 @@ struct request_queue unsigned int sg_reserved_size; int node; - struct list_head drain_list; - /* * reserved for flush operations */ @@ -442,7 +442,7 @@ enum { #define QUEUE_FLAG_DEAD 5 /* queue being torn down */ #define QUEUE_FLAG_REENTER 6 /* Re-entrancy avoidance */ #define QUEUE_FLAG_PLUGGED 7 /* queue is plugged */ -#define QUEUE_FLAG_DRAIN 8 /* draining queue for sched switch */ +#define QUEUE_FLAG_BYPASS 8 /* don't use elevator, just do FIFO */ #define QUEUE_FLAG_FLUSH 9 /* doing barrier flush sequence */ #define blk_queue_plugged(q) test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags) @@ -668,8 +668,6 @@ extern void blk_dump_rq_flags(struct request *, char *); extern void generic_unplug_device(request_queue_t *); extern void __generic_unplug_device(request_queue_t *); extern long nr_blockdev_pages(void); -extern void blk_wait_queue_drained(request_queue_t *, int); -extern void blk_finish_queue_drain(request_queue_t *); int blk_get_queue(request_queue_t *); request_queue_t *blk_alloc_queue(int gfp_mask); -- cgit v1.2.3 From 64521d1a3ba7cc7fe4ab5640da83d88144f05340 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 28 Oct 2005 08:30:39 +0200 Subject: [BLOCK] elevator switch fixes/cleanup - 100msec sleep is a little excessive, lots of requests can complete in that timeframe. Use 10msec instead. - Rename QUEUE_FLAG_BYPASS to QUEUE_FLAG_ELVSWITCH to indicate what is going on. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6186d5e2110f..7d9d14d6d8f9 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -442,7 +442,7 @@ enum { #define QUEUE_FLAG_DEAD 5 /* queue being torn down */ #define QUEUE_FLAG_REENTER 6 /* Re-entrancy avoidance */ #define QUEUE_FLAG_PLUGGED 7 /* queue is plugged */ -#define QUEUE_FLAG_BYPASS 8 /* don't use elevator, just do FIFO */ +#define QUEUE_FLAG_ELVSWITCH 8 /* don't use elevator, just do FIFO */ #define QUEUE_FLAG_FLUSH 9 /* doing barrier flush sequence */ #define blk_queue_plugged(q) test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags) -- cgit v1.2.3 From af4ca457eaf2d6682059c18463eb106e2ce58198 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 21 Oct 2005 02:55:38 -0400 Subject: [PATCH] gfp_t: infrastructure Beginning of gfp_t annotations: - -Wbitwise added to CHECKFLAGS - old __bitwise renamed to __bitwise__ - __bitwise defined to either __bitwise__ or nothing, depending on __CHECK_ENDIAN__ being defined - gfp_t switched from __nocast to __bitwise__ - force cast to gfp_t added to __GFP_... constants - new helper - gfp_zone(); extracts zone bits out of gfp_t value and casts the result to int Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 39 ++++++++++++++++++++------------------- include/linux/types.h | 9 +++++++-- 2 files changed, 27 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 3010e172394d..c3779432a723 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -12,8 +12,8 @@ struct vm_area_struct; * GFP bitmasks.. */ /* Zone modifiers in GFP_ZONEMASK (see linux/mmzone.h - low two bits) */ -#define __GFP_DMA 0x01u -#define __GFP_HIGHMEM 0x02u +#define __GFP_DMA ((__force gfp_t)0x01u) +#define __GFP_HIGHMEM ((__force gfp_t)0x02u) /* * Action modifiers - doesn't change the zoning @@ -26,24 +26,24 @@ struct vm_area_struct; * * __GFP_NORETRY: The VM implementation must not retry indefinitely. */ -#define __GFP_WAIT 0x10u /* Can wait and reschedule? */ -#define __GFP_HIGH 0x20u /* Should access emergency pools? */ -#define __GFP_IO 0x40u /* Can start physical IO? */ -#define __GFP_FS 0x80u /* Can call down to low-level FS? */ -#define __GFP_COLD 0x100u /* Cache-cold page required */ -#define __GFP_NOWARN 0x200u /* Suppress page allocation failure warning */ -#define __GFP_REPEAT 0x400u /* Retry the allocation. Might fail */ -#define __GFP_NOFAIL 0x800u /* Retry for ever. Cannot fail */ -#define __GFP_NORETRY 0x1000u /* Do not retry. Might fail */ -#define __GFP_NO_GROW 0x2000u /* Slab internal usage */ -#define __GFP_COMP 0x4000u /* Add compound page metadata */ -#define __GFP_ZERO 0x8000u /* Return zeroed page on success */ -#define __GFP_NOMEMALLOC 0x10000u /* Don't use emergency reserves */ -#define __GFP_NORECLAIM 0x20000u /* No realy zone reclaim during allocation */ -#define __GFP_HARDWALL 0x40000u /* Enforce hardwall cpuset memory allocs */ +#define __GFP_WAIT ((__force gfp_t)0x10u) /* Can wait and reschedule? */ +#define __GFP_HIGH ((__force gfp_t)0x20u) /* Should access emergency pools? */ +#define __GFP_IO ((__force gfp_t)0x40u) /* Can start physical IO? */ +#define __GFP_FS ((__force gfp_t)0x80u) /* Can call down to low-level FS? */ +#define __GFP_COLD ((__force gfp_t)0x100u) /* Cache-cold page required */ +#define __GFP_NOWARN ((__force gfp_t)0x200u) /* Suppress page allocation failure warning */ +#define __GFP_REPEAT ((__force gfp_t)0x400u) /* Retry the allocation. Might fail */ +#define __GFP_NOFAIL ((__force gfp_t)0x800u) /* Retry for ever. Cannot fail */ +#define __GFP_NORETRY ((__force gfp_t)0x1000u)/* Do not retry. Might fail */ +#define __GFP_NO_GROW ((__force gfp_t)0x2000u)/* Slab internal usage */ +#define __GFP_COMP ((__force gfp_t)0x4000u)/* Add compound page metadata */ +#define __GFP_ZERO ((__force gfp_t)0x8000u)/* Return zeroed page on success */ +#define __GFP_NOMEMALLOC ((__force gfp_t)0x10000u) /* Don't use emergency reserves */ +#define __GFP_NORECLAIM ((__force gfp_t)0x20000u) /* No realy zone reclaim during allocation */ +#define __GFP_HARDWALL ((__force gfp_t)0x40000u) /* Enforce hardwall cpuset memory allocs */ #define __GFP_BITS_SHIFT 20 /* Room for 20 __GFP_FOO bits */ -#define __GFP_BITS_MASK ((1 << __GFP_BITS_SHIFT) - 1) +#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /* if you forget to add the bitmask here kernel will crash, period */ #define GFP_LEVEL_MASK (__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS| \ @@ -64,6 +64,7 @@ struct vm_area_struct; #define GFP_DMA __GFP_DMA +#define gfp_zone(mask) ((__force int)((mask) & (__force gfp_t)GFP_ZONEMASK)) /* * There is only one page-allocator function, and two main namespaces to @@ -94,7 +95,7 @@ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, return NULL; return __alloc_pages(gfp_mask, order, - NODE_DATA(nid)->node_zonelists + (gfp_mask & GFP_ZONEMASK)); + NODE_DATA(nid)->node_zonelists + gfp_zone(gfp_mask)); } #ifdef CONFIG_NUMA diff --git a/include/linux/types.h b/include/linux/types.h index 0aee34f9da9f..21b9ce803644 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -151,7 +151,12 @@ typedef unsigned long sector_t; */ #ifdef __CHECKER__ -#define __bitwise __attribute__((bitwise)) +#define __bitwise__ __attribute__((bitwise)) +#else +#define __bitwise__ +#endif +#ifdef __CHECK_ENDIAN__ +#define __bitwise __bitwise__ #else #define __bitwise #endif @@ -166,7 +171,7 @@ typedef __u64 __bitwise __be64; #endif #ifdef __KERNEL__ -typedef unsigned __nocast gfp_t; +typedef unsigned __bitwise__ gfp_t; #endif struct ustat { -- cgit v1.2.3 From 6daa0e28627abf362138244a620a821a9027d816 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 21 Oct 2005 03:18:50 -0400 Subject: [PATCH] gfp_t: mm/* (easy parts) Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- include/linux/pagemap.h | 6 +++--- include/linux/slab.h | 2 +- include/linux/swap.h | 4 ++-- 4 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 097b3a3c693d..e1649578fb0c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -747,7 +747,7 @@ extern unsigned long do_mremap(unsigned long addr, * The callback will be passed nr_to_scan == 0 when the VM is querying the * cache size, so a fastpath for that case is appropriate. */ -typedef int (*shrinker_t)(int nr_to_scan, unsigned int gfp_mask); +typedef int (*shrinker_t)(int nr_to_scan, gfp_t gfp_mask); /* * Add an aging callback. The int is the number of 'seeks' it takes diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index acbf31c154f8..efbae53fb078 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -69,7 +69,7 @@ extern struct page * find_lock_page(struct address_space *mapping, extern struct page * find_trylock_page(struct address_space *mapping, unsigned long index); extern struct page * find_or_create_page(struct address_space *mapping, - unsigned long index, unsigned int gfp_mask); + unsigned long index, gfp_t gfp_mask); unsigned find_get_pages(struct address_space *mapping, pgoff_t start, unsigned int nr_pages, struct page **pages); unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index, @@ -92,9 +92,9 @@ extern int read_cache_pages(struct address_space *mapping, struct list_head *pages, filler_t *filler, void *data); int add_to_page_cache(struct page *page, struct address_space *mapping, - unsigned long index, int gfp_mask); + unsigned long index, gfp_t gfp_mask); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, - unsigned long index, int gfp_mask); + unsigned long index, gfp_t gfp_mask); extern void remove_from_page_cache(struct page *page); extern void __remove_from_page_cache(struct page *page); diff --git a/include/linux/slab.h b/include/linux/slab.h index 5fc04a16ecb0..09b9aa60063d 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -121,7 +121,7 @@ extern unsigned int ksize(const void *); extern void *kmem_cache_alloc_node(kmem_cache_t *, gfp_t flags, int node); extern void *kmalloc_node(size_t size, gfp_t flags, int node); #else -static inline void *kmem_cache_alloc_node(kmem_cache_t *cachep, int flags, int node) +static inline void *kmem_cache_alloc_node(kmem_cache_t *cachep, gfp_t flags, int node) { return kmem_cache_alloc(cachep, flags); } diff --git a/include/linux/swap.h b/include/linux/swap.h index a7bf1a3b1496..20c975642cab 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -171,8 +171,8 @@ extern int rotate_reclaimable_page(struct page *page); extern void swap_setup(void); /* linux/mm/vmscan.c */ -extern int try_to_free_pages(struct zone **, unsigned int); -extern int zone_reclaim(struct zone *, unsigned int, unsigned int); +extern int try_to_free_pages(struct zone **, gfp_t); +extern int zone_reclaim(struct zone *, gfp_t, unsigned int); extern int shrink_all_memory(int); extern int vm_swappiness; -- cgit v1.2.3 From fd4f2df24bc23e6b8fc069765b425c7dacf52347 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 21 Oct 2005 03:18:50 -0400 Subject: [PATCH] gfp_t: lib/* Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/idr.h | 2 +- include/linux/kobject.h | 2 +- include/linux/radix-tree.h | 2 +- include/linux/textsearch.h | 4 ++-- 4 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index 3d5de45f961b..7fb3ff9c7b0e 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -71,7 +71,7 @@ struct idr { */ void *idr_find(struct idr *idp, int id); -int idr_pre_get(struct idr *idp, unsigned gfp_mask); +int idr_pre_get(struct idr *idp, gfp_t gfp_mask); int idr_get_new(struct idr *idp, void *ptr, int *id); int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id); void idr_remove(struct idr *idp, int id); diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 3b22304f12fd..7f7403aa4a41 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -65,7 +65,7 @@ extern void kobject_unregister(struct kobject *); extern struct kobject * kobject_get(struct kobject *); extern void kobject_put(struct kobject *); -extern char * kobject_get_path(struct kobject *, int); +extern char * kobject_get_path(struct kobject *, gfp_t); struct kobj_type { void (*release)(struct kobject *); diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 045d4761febc..9f0f9281f42a 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -24,7 +24,7 @@ struct radix_tree_root { unsigned int height; - unsigned int gfp_mask; + gfp_t gfp_mask; struct radix_tree_node *rnode; }; diff --git a/include/linux/textsearch.h b/include/linux/textsearch.h index 515046d1b2f4..fc5bb4e91a58 100644 --- a/include/linux/textsearch.h +++ b/include/linux/textsearch.h @@ -40,7 +40,7 @@ struct ts_state struct ts_ops { const char *name; - struct ts_config * (*init)(const void *, unsigned int, int); + struct ts_config * (*init)(const void *, unsigned int, gfp_t); unsigned int (*find)(struct ts_config *, struct ts_state *); void (*destroy)(struct ts_config *); @@ -148,7 +148,7 @@ static inline unsigned int textsearch_get_pattern_len(struct ts_config *conf) extern int textsearch_register(struct ts_ops *); extern int textsearch_unregister(struct ts_ops *); extern struct ts_config *textsearch_prepare(const char *, const void *, - unsigned int, int, int); + unsigned int, gfp_t, int); extern void textsearch_destroy(struct ts_config *conf); extern unsigned int textsearch_find_continuous(struct ts_config *, struct ts_state *, -- cgit v1.2.3 From 7d877f3bda870ab5f001bd92528654471d5966b3 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 21 Oct 2005 03:20:43 -0400 Subject: [PATCH] gfp_t: net/* Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/security.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 627382e74057..dac956ed98f0 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1210,7 +1210,7 @@ struct security_operations { int (*socket_shutdown) (struct socket * sock, int how); int (*socket_sock_rcv_skb) (struct sock * sk, struct sk_buff * skb); int (*socket_getpeersec) (struct socket *sock, char __user *optval, int __user *optlen, unsigned len); - int (*sk_alloc_security) (struct sock *sk, int family, int priority); + int (*sk_alloc_security) (struct sock *sk, int family, gfp_t priority); void (*sk_free_security) (struct sock *sk); #endif /* CONFIG_SECURITY_NETWORK */ }; -- cgit v1.2.3 From 27496a8c67bef4d789d8e3c8317ca35813a507ae Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 21 Oct 2005 03:20:48 -0400 Subject: [PATCH] gfp_t: fs/* - ->releasepage() annotated (s/int/gfp_t), instances updated - missing gfp_t in fs/* added - fixed misannotation from the original sweep caught by bitwise checks: XFS used __nocast both for gfp_t and for flags used by XFS allocator. The latter left with unsigned int __nocast; we might want to add a different type for those but for now let's leave them alone. That, BTW, is a case when __nocast use had been actively confusing - it had been used in the same code for two different and similar types, with no way to catch misuses. Switch of gfp_t to bitwise had caught that immediately... One tricky bit is left alone to be dealt with later - mapping->flags is a mix of gfp_t and error indications. Left alone for now. Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/bio.h | 2 +- include/linux/buffer_head.h | 2 +- include/linux/fs.h | 2 +- include/linux/jbd.h | 4 ++-- include/linux/mbcache.h | 2 +- include/linux/reiserfs_fs.h | 2 +- 6 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 3344b4e8e43a..685fd3720df5 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -301,7 +301,7 @@ extern struct bio *bio_map_user_iov(struct request_queue *, struct sg_iovec *, int, int); extern void bio_unmap_user(struct bio *); extern struct bio *bio_map_kern(struct request_queue *, void *, unsigned int, - unsigned int); + gfp_t); extern void bio_set_pages_dirty(struct bio *bio); extern void bio_check_pages_dirty(struct bio *bio); extern struct bio *bio_copy_user(struct request_queue *, unsigned long, unsigned int, int); diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 6a1d154c0825..88af42f5e04a 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -188,7 +188,7 @@ extern int buffer_heads_over_limit; * Generic address_space_operations implementations for buffer_head-backed * address_spaces. */ -int try_to_release_page(struct page * page, int gfp_mask); +int try_to_release_page(struct page * page, gfp_t gfp_mask); int block_invalidatepage(struct page *page, unsigned long offset); int block_write_full_page(struct page *page, get_block_t *get_block, struct writeback_control *wbc); diff --git a/include/linux/fs.h b/include/linux/fs.h index e0b77c5af9a0..f83d997c5582 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -320,7 +320,7 @@ struct address_space_operations { /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); int (*invalidatepage) (struct page *, unsigned long); - int (*releasepage) (struct page *, int); + int (*releasepage) (struct page *, gfp_t); ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov, loff_t offset, unsigned long nr_segs); struct page* (*get_xip_page)(struct address_space *, sector_t, diff --git a/include/linux/jbd.h b/include/linux/jbd.h index ff853b3173c6..be197eb90077 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -69,7 +69,7 @@ extern int journal_enable_debug; #define jbd_debug(f, a...) /**/ #endif -extern void * __jbd_kmalloc (const char *where, size_t size, int flags, int retry); +extern void * __jbd_kmalloc (const char *where, size_t size, gfp_t flags, int retry); #define jbd_kmalloc(size, flags) \ __jbd_kmalloc(__FUNCTION__, (size), (flags), journal_oom_retry) #define jbd_rep_kmalloc(size, flags) \ @@ -890,7 +890,7 @@ extern int journal_forget (handle_t *, struct buffer_head *); extern void journal_sync_buffer (struct buffer_head *); extern int journal_invalidatepage(journal_t *, struct page *, unsigned long); -extern int journal_try_to_free_buffers(journal_t *, struct page *, int); +extern int journal_try_to_free_buffers(journal_t *, struct page *, gfp_t); extern int journal_stop(handle_t *); extern int journal_flush (journal_t *); extern void journal_lock_updates (journal_t *); diff --git a/include/linux/mbcache.h b/include/linux/mbcache.h index 9263d2db2d67..99e044b4efc6 100644 --- a/include/linux/mbcache.h +++ b/include/linux/mbcache.h @@ -22,7 +22,7 @@ struct mb_cache_entry { }; struct mb_cache_op { - int (*free)(struct mb_cache_entry *, int); + int (*free)(struct mb_cache_entry *, gfp_t); }; /* Functions on caches */ diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index af00b10294cd..001ab82df051 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -1972,7 +1972,7 @@ extern struct address_space_operations reiserfs_address_space_operations; /* fix_nodes.c */ #ifdef CONFIG_REISERFS_CHECK -void *reiserfs_kmalloc(size_t size, int flags, struct super_block *s); +void *reiserfs_kmalloc(size_t size, gfp_t flags, struct super_block *s); void reiserfs_kfree(const void *vp, size_t size, struct super_block *s); #else static inline void *reiserfs_kmalloc(size_t size, int flags, -- cgit v1.2.3 From 8267e268e0914ac9371d07f711fcf20cc572993c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 21 Oct 2005 03:20:53 -0400 Subject: [PATCH] gfp_t: block layer core Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/blkdev.h | 14 +++++++------- include/linux/elevator.h | 4 ++-- 2 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index efdc9b5bc05c..1afbdb2d752c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -96,8 +96,8 @@ struct io_context { void put_io_context(struct io_context *ioc); void exit_io_context(void); -struct io_context *current_io_context(int gfp_flags); -struct io_context *get_io_context(int gfp_flags); +struct io_context *current_io_context(gfp_t gfp_flags); +struct io_context *get_io_context(gfp_t gfp_flags); void copy_io_context(struct io_context **pdst, struct io_context **psrc); void swap_io_context(struct io_context **ioc1, struct io_context **ioc2); @@ -354,7 +354,7 @@ struct request_queue * queue needs bounce pages for pages above this limit */ unsigned long bounce_pfn; - unsigned int bounce_gfp; + gfp_t bounce_gfp; /* * various queue flags, see QUEUE_* below @@ -550,7 +550,7 @@ extern void generic_make_request(struct bio *bio); extern void blk_put_request(struct request *); extern void blk_end_sync_rq(struct request *rq); extern void blk_attempt_remerge(request_queue_t *, struct request *); -extern struct request *blk_get_request(request_queue_t *, int, int); +extern struct request *blk_get_request(request_queue_t *, int, gfp_t); extern void blk_insert_request(request_queue_t *, struct request *, int, void *); extern void blk_requeue_request(request_queue_t *, struct request *); extern void blk_plug_device(request_queue_t *); @@ -565,7 +565,7 @@ extern void blk_run_queue(request_queue_t *); extern void blk_queue_activity_fn(request_queue_t *, activity_fn *, void *); extern int blk_rq_map_user(request_queue_t *, struct request *, void __user *, unsigned int); extern int blk_rq_unmap_user(struct bio *, unsigned int); -extern int blk_rq_map_kern(request_queue_t *, struct request *, void *, unsigned int, unsigned int); +extern int blk_rq_map_kern(request_queue_t *, struct request *, void *, unsigned int, gfp_t); extern int blk_rq_map_user_iov(request_queue_t *, struct request *, struct sg_iovec *, int); extern int blk_execute_rq(request_queue_t *, struct gendisk *, struct request *, int); @@ -654,8 +654,8 @@ extern void blk_wait_queue_drained(request_queue_t *, int); extern void blk_finish_queue_drain(request_queue_t *); int blk_get_queue(request_queue_t *); -request_queue_t *blk_alloc_queue(int gfp_mask); -request_queue_t *blk_alloc_queue_node(int,int); +request_queue_t *blk_alloc_queue(gfp_t); +request_queue_t *blk_alloc_queue_node(gfp_t, int); #define blk_put_queue(q) blk_cleanup_queue((q)) /* diff --git a/include/linux/elevator.h b/include/linux/elevator.h index ea6bbc2d7407..ed93125c1db5 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -18,7 +18,7 @@ typedef struct request *(elevator_request_list_fn) (request_queue_t *, struct re typedef void (elevator_completed_req_fn) (request_queue_t *, struct request *); typedef int (elevator_may_queue_fn) (request_queue_t *, int, struct bio *); -typedef int (elevator_set_req_fn) (request_queue_t *, struct request *, struct bio *, int); +typedef int (elevator_set_req_fn) (request_queue_t *, struct request *, struct bio *, gfp_t); typedef void (elevator_put_req_fn) (request_queue_t *, struct request *); typedef void (elevator_deactivate_req_fn) (request_queue_t *, struct request *); @@ -98,7 +98,7 @@ extern int elv_register_queue(request_queue_t *q); extern void elv_unregister_queue(request_queue_t *q); extern int elv_may_queue(request_queue_t *, int, struct bio *); extern void elv_completed_request(request_queue_t *, struct request *); -extern int elv_set_request(request_queue_t *, struct request *, struct bio *, int); +extern int elv_set_request(request_queue_t *, struct request *, struct bio *, gfp_t); extern void elv_put_request(request_queue_t *, struct request *); /* -- cgit v1.2.3 From 55016f10e31bb15b85d8c500f979dfdceb37d548 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 21 Oct 2005 03:21:58 -0400 Subject: [PATCH] gfp_t: drivers/usb Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/usb.h | 8 ++++---- include/linux/usb_gadget.h | 12 ++++++------ 2 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 4dbe580f9335..8f731e8f2821 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -933,17 +933,17 @@ static inline void usb_fill_int_urb (struct urb *urb, } extern void usb_init_urb(struct urb *urb); -extern struct urb *usb_alloc_urb(int iso_packets, unsigned mem_flags); +extern struct urb *usb_alloc_urb(int iso_packets, gfp_t mem_flags); extern void usb_free_urb(struct urb *urb); #define usb_put_urb usb_free_urb extern struct urb *usb_get_urb(struct urb *urb); -extern int usb_submit_urb(struct urb *urb, unsigned mem_flags); +extern int usb_submit_urb(struct urb *urb, gfp_t mem_flags); extern int usb_unlink_urb(struct urb *urb); extern void usb_kill_urb(struct urb *urb); #define HAVE_USB_BUFFERS void *usb_buffer_alloc (struct usb_device *dev, size_t size, - unsigned mem_flags, dma_addr_t *dma); + gfp_t mem_flags, dma_addr_t *dma); void usb_buffer_free (struct usb_device *dev, size_t size, void *addr, dma_addr_t dma); @@ -1050,7 +1050,7 @@ int usb_sg_init ( struct scatterlist *sg, int nents, size_t length, - unsigned mem_flags + gfp_t mem_flags ); void usb_sg_cancel (struct usb_sg_request *io); void usb_sg_wait (struct usb_sg_request *io); diff --git a/include/linux/usb_gadget.h b/include/linux/usb_gadget.h index 71e608607324..ff81117eb733 100644 --- a/include/linux/usb_gadget.h +++ b/include/linux/usb_gadget.h @@ -107,18 +107,18 @@ struct usb_ep_ops { int (*disable) (struct usb_ep *ep); struct usb_request *(*alloc_request) (struct usb_ep *ep, - unsigned gfp_flags); + gfp_t gfp_flags); void (*free_request) (struct usb_ep *ep, struct usb_request *req); void *(*alloc_buffer) (struct usb_ep *ep, unsigned bytes, - dma_addr_t *dma, unsigned gfp_flags); + dma_addr_t *dma, gfp_t gfp_flags); void (*free_buffer) (struct usb_ep *ep, void *buf, dma_addr_t dma, unsigned bytes); // NOTE: on 2.6, drivers may also use dma_map() and // dma_sync_single_*() to directly manage dma overhead. int (*queue) (struct usb_ep *ep, struct usb_request *req, - unsigned gfp_flags); + gfp_t gfp_flags); int (*dequeue) (struct usb_ep *ep, struct usb_request *req); int (*set_halt) (struct usb_ep *ep, int value); @@ -214,7 +214,7 @@ usb_ep_disable (struct usb_ep *ep) * Returns the request, or null if one could not be allocated. */ static inline struct usb_request * -usb_ep_alloc_request (struct usb_ep *ep, unsigned gfp_flags) +usb_ep_alloc_request (struct usb_ep *ep, gfp_t gfp_flags) { return ep->ops->alloc_request (ep, gfp_flags); } @@ -254,7 +254,7 @@ usb_ep_free_request (struct usb_ep *ep, struct usb_request *req) */ static inline void * usb_ep_alloc_buffer (struct usb_ep *ep, unsigned len, dma_addr_t *dma, - unsigned gfp_flags) + gfp_t gfp_flags) { return ep->ops->alloc_buffer (ep, len, dma, gfp_flags); } @@ -330,7 +330,7 @@ usb_ep_free_buffer (struct usb_ep *ep, void *buf, dma_addr_t dma, unsigned len) * reported when the usb peripheral is disconnected. */ static inline int -usb_ep_queue (struct usb_ep *ep, struct usb_request *req, unsigned gfp_flags) +usb_ep_queue (struct usb_ep *ep, struct usb_request *req, gfp_t gfp_flags) { return ep->ops->queue (ep, req, gfp_flags); } -- cgit v1.2.3 From 9796fdd829da626374458e8706daedcc0e432ddd Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 21 Oct 2005 03:22:03 -0400 Subject: [PATCH] gfp_t: kernel/* Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/audit.h | 4 ++-- include/linux/suspend.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index b2a2509bd7ea..da3c01955f3d 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -260,11 +260,11 @@ extern int audit_filter_user(struct netlink_skb_parms *cb, int type); #ifdef CONFIG_AUDIT /* These are defined in audit.c */ /* Public API */ -extern void audit_log(struct audit_context *ctx, int gfp_mask, +extern void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, const char *fmt, ...) __attribute__((format(printf,4,5))); -extern struct audit_buffer *audit_log_start(struct audit_context *ctx, int gfp_mask, int type); +extern struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type); extern void audit_log_format(struct audit_buffer *ab, const char *fmt, ...) __attribute__((format(printf,2,3))); diff --git a/include/linux/suspend.h b/include/linux/suspend.h index ad15a54806d8..ba448c760168 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -71,7 +71,7 @@ void restore_processor_state(void); struct saved_context; void __save_processor_state(struct saved_context *ctxt); void __restore_processor_state(struct saved_context *ctxt); -extern unsigned long get_usable_page(unsigned gfp_mask); +extern unsigned long get_usable_page(gfp_t gfp_mask); extern void free_eaten_memory(void); #endif /* _LINUX_SWSUSP_H */ -- cgit v1.2.3 From b4e3ca1ab1ae9ae86134126dcdc88da1caaa32ca Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 21 Oct 2005 03:22:34 -0400 Subject: [PATCH] gfp_t: remaining bits of drivers/* Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/i2o.h | 4 ++-- include/linux/loop.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2o.h b/include/linux/i2o.h index bdc286ec947c..b4af45aad25d 100644 --- a/include/linux/i2o.h +++ b/include/linux/i2o.h @@ -492,7 +492,7 @@ static inline int i2o_dma_map_sg(struct i2o_controller *c, * Returns 0 on success or -ENOMEM on failure. */ static inline int i2o_dma_alloc(struct device *dev, struct i2o_dma *addr, - size_t len, unsigned int gfp_mask) + size_t len, gfp_t gfp_mask) { struct pci_dev *pdev = to_pci_dev(dev); int dma_64 = 0; @@ -551,7 +551,7 @@ static inline void i2o_dma_free(struct device *dev, struct i2o_dma *addr) * Returns the 0 on success or negative error code on failure. */ static inline int i2o_dma_realloc(struct device *dev, struct i2o_dma *addr, - size_t len, unsigned int gfp_mask) + size_t len, gfp_t gfp_mask) { i2o_dma_free(dev, addr); diff --git a/include/linux/loop.h b/include/linux/loop.h index 53fa51595443..40f63c9879d2 100644 --- a/include/linux/loop.h +++ b/include/linux/loop.h @@ -52,7 +52,7 @@ struct loop_device { unsigned lo_blocksize; void *key_data; - int old_gfp_mask; + gfp_t old_gfp_mask; spinlock_t lo_lock; struct bio *lo_bio; -- cgit v1.2.3 From 260b23674fdb570f3235ce55892246bef1c24c2a Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 21 Oct 2005 03:22:44 -0400 Subject: [PATCH] gfp_t: the rest zone handling, mapping->flags handling Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- include/linux/pagemap.h | 7 ++++--- 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 5ed471b58f4f..7519eb4191e7 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -302,7 +302,7 @@ void get_zone_counts(unsigned long *active, unsigned long *inactive, void build_all_zonelists(void); void wakeup_kswapd(struct zone *zone, int order); int zone_watermark_ok(struct zone *z, int order, unsigned long mark, - int alloc_type, int can_try_harder, int gfp_high); + int alloc_type, int can_try_harder, gfp_t gfp_high); #ifdef CONFIG_HAVE_MEMORY_PRESENT void memory_present(int nid, unsigned long start, unsigned long end); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index efbae53fb078..ba6c310a055f 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -21,16 +21,17 @@ static inline gfp_t mapping_gfp_mask(struct address_space * mapping) { - return mapping->flags & __GFP_BITS_MASK; + return (__force gfp_t)mapping->flags & __GFP_BITS_MASK; } /* * This is non-atomic. Only to be used before the mapping is activated. * Probably needs a barrier... */ -static inline void mapping_set_gfp_mask(struct address_space *m, int mask) +static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) { - m->flags = (m->flags & ~__GFP_BITS_MASK) | mask; + m->flags = (m->flags & ~(__force unsigned long)__GFP_BITS_MASK) | + (__force unsigned long)mask; } /* -- cgit v1.2.3