From c6a33e2464edd87f8c12cc2d11369a5b44c65b77 Mon Sep 17 00:00:00 2001 From: Albert Lee Date: Wed, 12 Oct 2005 15:12:26 +0800 Subject: [PATCH] libata CHS: LBA28/LBA48 optimization (revise #6) - add lba_28_ok() and lba_48_ok() to ata.h. - check ending block number instead of staring block number. - use lba_28_ok() for CHS range check - LBA28/LBA48 optimization Suggested by Mark Lord and Alan Cox. Signed-off-by: Albert Lee ===== Signed-off-by: Jeff Garzik --- include/linux/ata.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index 630908c9378b..b7e7e1cb2633 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -291,4 +291,16 @@ static inline int ata_ok(u8 status) == ATA_DRDY); } +static inline int lba_28_ok(u64 block, u32 n_block) +{ + /* check the ending block number */ + return ((block + n_block - 1) < ((u64)1 << 28)) && (n_block <= 256); +} + +static inline int lba_48_ok(u64 block, u32 n_block) +{ + /* check the ending block number */ + return ((block + n_block - 1) < ((u64)1 << 48)) && (n_block <= 65536); +} + #endif /* __LINUX_ATA_H__ */ -- cgit v1.2.3 From f03aa2d89ad600a1ed21a223f196776f217cfe00 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Sat, 14 Jan 2006 03:10:22 +0100 Subject: [PATCH] drivers/net/arcnet/: possible cleanups This patch contains the following possible cleanups: - make needlessly global code static - arcnet.c: remove the unneeded EXPORT_SYMBOL(arc_proto_null) - arcnet.c: remove the unneeded EXPORT_SYMBOL(arcnet_dump_packet) To make Jeff happy, arcnet.c still prints arcnet: v3.93 BETA 2000/04/29 - by Avery Pennarun et al. Signed-off-by: Adrian Bunk Signed-off-by: Jeff Garzik --- include/linux/arcdevice.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/arcdevice.h b/include/linux/arcdevice.h index 7198f129e135..231ba090ae34 100644 --- a/include/linux/arcdevice.h +++ b/include/linux/arcdevice.h @@ -206,7 +206,6 @@ struct ArcProto { extern struct ArcProto *arc_proto_map[256], *arc_proto_default, *arc_bcast_proto, *arc_raw_proto; -extern struct ArcProto arc_proto_null; /* @@ -334,17 +333,9 @@ void arcnet_dump_skb(struct net_device *dev, struct sk_buff *skb, char *desc); #define arcnet_dump_skb(dev,skb,desc) ; #endif -#if (ARCNET_DEBUG_MAX & D_RX) || (ARCNET_DEBUG_MAX & D_TX) -void arcnet_dump_packet(struct net_device *dev, int bufnum, char *desc, - int take_arcnet_lock); -#else -#define arcnet_dump_packet(dev, bufnum, desc,take_arcnet_lock) ; -#endif - void arcnet_unregister_proto(struct ArcProto *proto); irqreturn_t arcnet_interrupt(int irq, void *dev_id, struct pt_regs *regs); struct net_device *alloc_arcdev(char *name); -void arcnet_rx(struct net_device *dev, int bufnum); #endif /* __KERNEL__ */ #endif /* _LINUX_ARCDEVICE_H */ -- cgit v1.2.3 From bfd6057959ecd3ff779a373a4d07cda2c2d0eec1 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 17 Jan 2006 19:34:42 -0500 Subject: From: Borislav Petkov libata new debugging macro definitions Signed-off-by: Borislav Petkov Signed-off-by: Randy Dunlap --- include/linux/libata.h | 52 +++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 45 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index a43c95f8f968..339f7e75cb60 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -35,7 +35,8 @@ #include /* - * compile-time options + * compile-time options: to be removed as soon as all the drivers are + * converted to the new debugging mechanism */ #undef ATA_DEBUG /* debugging output */ #undef ATA_VERBOSE_DEBUG /* yet more debugging output */ @@ -71,6 +72,38 @@ } #endif +/* NEW: debug levels */ +#define HAVE_LIBATA_MSG 1 + +enum { + ATA_MSG_DRV = 0x0001, + ATA_MSG_INFO = 0x0002, + ATA_MSG_PROBE = 0x0004, + ATA_MSG_WARN = 0x0008, + ATA_MSG_MALLOC = 0x0010, + ATA_MSG_CTL = 0x0020, + ATA_MSG_INTR = 0x0040, + ATA_MSG_ERR = 0x0080, +}; + +#define ata_msg_drv(p) ((p)->msg_enable & ATA_MSG_DRV) +#define ata_msg_info(p) ((p)->msg_enable & ATA_MSG_INFO) +#define ata_msg_probe(p) ((p)->msg_enable & ATA_MSG_PROBE) +#define ata_msg_warn(p) ((p)->msg_enable & ATA_MSG_WARN) +#define ata_msg_malloc(p) ((p)->msg_enable & ATA_MSG_MALLOC) +#define ata_msg_ctl(p) ((p)->msg_enable & ATA_MSG_CTL) +#define ata_msg_intr(p) ((p)->msg_enable & ATA_MSG_INTR) +#define ata_msg_err(p) ((p)->msg_enable & ATA_MSG_ERR) + +static inline u32 ata_msg_init(int dval, int default_msg_enable_bits) +{ + if (dval < 0 || dval >= (sizeof(u32) * 8)) + return default_msg_enable_bits; /* should be 0x1 - only driver info msgs */ + if (!dval) + return 0; + return (1 << dval) - 1; +} + /* defines only for the constants which don't work well as enums */ #define ATA_TAG_POISON 0xfafbfcfdU @@ -356,6 +389,8 @@ struct ata_port { unsigned int hsm_task_state; unsigned long pio_task_timeout; + u32 msg_enable; + void *private_data; }; @@ -640,9 +675,9 @@ static inline u8 ata_wait_idle(struct ata_port *ap) if (status & (ATA_BUSY | ATA_DRQ)) { unsigned long l = ap->ioaddr.status_addr; - printk(KERN_WARNING - "ATA: abnormal status 0x%X on port 0x%lX\n", - status, l); + if (ata_msg_warn(ap)) + printk(KERN_WARNING "ATA: abnormal status 0x%X on port 0x%lX\n", + status, l); } return status; @@ -734,7 +769,8 @@ static inline u8 ata_irq_ack(struct ata_port *ap, unsigned int chk_drq) status = ata_busy_wait(ap, bits, 1000); if (status & bits) - DPRINTK("abnormal status 0x%X\n", status); + if (ata_msg_err(ap)) + printk(KERN_ERR "abnormal status 0x%X\n", status); /* get controller status; clear intr, err bits */ if (ap->flags & ATA_FLAG_MMIO) { @@ -752,8 +788,10 @@ static inline u8 ata_irq_ack(struct ata_port *ap, unsigned int chk_drq) post_stat = inb(ap->ioaddr.bmdma_addr + ATA_DMA_STATUS); } - VPRINTK("irq ack: host_stat 0x%X, new host_stat 0x%X, drv_stat 0x%X\n", - host_stat, post_stat, status); + if (ata_msg_intr(ap)) + printk(KERN_INFO "%s: irq ack: host_stat 0x%X, new host_stat 0x%X, drv_stat 0x%X\n", + __FUNCTION__, + host_stat, post_stat, status); return status; } -- cgit v1.2.3 From 6ac48b458769059ee6147dd8bf2767e820407292 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 23 Jan 2006 17:11:05 -0200 Subject: V4L/DVB (3408): Included new sliced VBI types to videodev2.h and tvp5150 - Added other sliced VBI types to videodev2.h - tvp5150 now uses standard V4L2 API codes from videodev2.h - Implemented VIDIOC_G_SLICED_VBI_CAP for tvp5150. This is dynamically filled based on defined VDP C-RAM values filled by the driver. Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 51 ++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 44 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index ce40675324bd..27ae3d679cbe 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -949,13 +949,50 @@ struct v4l2_sliced_vbi_format __u32 reserved[2]; /* must be zero */ }; -#define V4L2_SLICED_TELETEXT_B (0x0001) -#define V4L2_SLICED_VPS (0x0400) -#define V4L2_SLICED_CAPTION_525 (0x1000) -#define V4L2_SLICED_WSS_625 (0x4000) - -#define V4L2_SLICED_VBI_525 (V4L2_SLICED_CAPTION_525) -#define V4L2_SLICED_VBI_625 (V4L2_SLICED_TELETEXT_B | V4L2_SLICED_VPS | V4L2_SLICED_WSS_625) +/* Teletext WST, defined on ITU-R BT.653-2 */ +#define V4L2_SLICED_TELETEXT_PAL_B (0x000001) +#define V4L2_SLICED_TELETEXT_PAL_C (0x000002) +#define V4L2_SLICED_TELETEXT_NTSC_B (0x000010) +#define V4L2_SLICED_TELETEXT_SECAM (0x000020) + +/* Teletext NABTS, defined on ITU-R BT.653-2 */ +#define V4L2_SLICED_TELETEXT_NTSC_C (0x000040) +#define V4L2_SLICED_TELETEXT_NTSC_D (0x000080) + +/* Video Program System, defined on ETS 300 231*/ +#define V4L2_SLICED_VPS (0x000400) + +/* Closed Caption, defined on EIA-608 */ +#define V4L2_SLICED_CAPTION_525 (0x001000) +#define V4L2_SLICED_CAPTION_625 (0x002000) + +/* Wide Screen System, defined on ITU-R BT1119.1 */ +#define V4L2_SLICED_WSS_625 (0x004000) + +/* Wide Screen System, defined on IEC 61880 */ +#define V4L2_SLICED_WSS_525 (0x008000) + +/* Vertical Interval Timecode (VITC), defined on SMPTE 12M */ +#define V4l2_SLICED_VITC_625 (0x010000) +#define V4l2_SLICED_VITC_525 (0x020000) + +/* Compat macro - Should be removed for 2.6.18 */ +#define V4L2_SLICED_TELETEXT_B V4L2_SLICED_TELETEXT_PAL_B + +#define V4L2_SLICED_VBI_525 (V4L2_SLICED_TELETEXT_NTSC_B |\ + V4L2_SLICED_TELETEXT_NTSC_C |\ + V4L2_SLICED_TELETEXT_NTSC_D |\ + V4L2_SLICED_CAPTION_525 |\ + V4L2_SLICED_WSS_525 |\ + V4l2_SLICED_VITC_525) + +#define V4L2_SLICED_VBI_625 (V4L2_SLICED_TELETEXT_PAL_B |\ + V4L2_SLICED_TELETEXT_PAL_C |\ + V4L2_SLICED_TELETEXT_SECAM |\ + V4L2_SLICED_VPS |\ + V4L2_SLICED_CAPTION_625 |\ + V4L2_SLICED_WSS_625 |\ + V4l2_SLICED_VITC_625) struct v4l2_sliced_vbi_cap { -- cgit v1.2.3 From 4d0dddb10723cee2b3048bd2389673703bc228e4 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 23 Jan 2006 17:11:07 -0200 Subject: V4L/DVB (3419): added some VBI macros and moved minor definitions to header file - Moved some hardcoded minor numbers to videodev2.h - Included more comments for sliced VBI standards - Included some VBI macros to group similar standards Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 38 +++++++++++++++++++++++++++++++++----- 1 file changed, 33 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 27ae3d679cbe..6e33ce96cab0 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -21,7 +21,7 @@ #include /* need __user */ -#define OBSOLETE_OWNER 1 /* It will be removed for 2.6.15 */ +#define OBSOLETE_OWNER 1 /* It will be removed for 2.6.17 */ #define HAVE_V4L2 1 /* @@ -48,6 +48,16 @@ #ifdef __KERNEL__ +/* Minor device allocation */ +#define MINOR_VFL_TYPE_GRABBER_MIN 0 +#define MINOR_VFL_TYPE_GRABBER_MAX 63 +#define MINOR_VFL_TYPE_RADIO_MIN 64 +#define MINOR_VFL_TYPE_RADIO_MAX 127 +#define MINOR_VFL_TYPE_VTX_MIN 192 +#define MINOR_VFL_TYPE_VTX_MAX 223 +#define MINOR_VFL_TYPE_VBI_MIN 224 +#define MINOR_VFL_TYPE_VBI_MAX 255 + #define VFL_TYPE_GRABBER 0 #define VFL_TYPE_VBI 1 #define VFL_TYPE_RADIO 2 @@ -949,13 +959,15 @@ struct v4l2_sliced_vbi_format __u32 reserved[2]; /* must be zero */ }; -/* Teletext WST, defined on ITU-R BT.653-2 */ +/* Teletext World System Teletext + (WST), defined on ITU-R BT.653-2 */ #define V4L2_SLICED_TELETEXT_PAL_B (0x000001) #define V4L2_SLICED_TELETEXT_PAL_C (0x000002) #define V4L2_SLICED_TELETEXT_NTSC_B (0x000010) #define V4L2_SLICED_TELETEXT_SECAM (0x000020) -/* Teletext NABTS, defined on ITU-R BT.653-2 */ +/* Teletext North American Broadcast Teletext Specification + (NABTS), defined on ITU-R BT.653-2 */ #define V4L2_SLICED_TELETEXT_NTSC_C (0x000040) #define V4L2_SLICED_TELETEXT_NTSC_D (0x000080) @@ -976,8 +988,24 @@ struct v4l2_sliced_vbi_format #define V4l2_SLICED_VITC_625 (0x010000) #define V4l2_SLICED_VITC_525 (0x020000) -/* Compat macro - Should be removed for 2.6.18 */ -#define V4L2_SLICED_TELETEXT_B V4L2_SLICED_TELETEXT_PAL_B +#define V4L2_SLICED_TELETEXT_B (V4L2_SLICED_TELETEXT_PAL_B |\ + V4L2_SLICED_TELETEXT_NTSC_B) + +#define V4L2_SLICED_TELETEXT (V4L2_SLICED_TELETEXT_PAL_B |\ + V4L2_SLICED_TELETEXT_PAL_C |\ + V4L2_SLICED_TELETEXT_SECAM |\ + V4L2_SLICED_TELETEXT_NTSC_B |\ + V4L2_SLICED_TELETEXT_NTSC_C |\ + V4L2_SLICED_TELETEXT_NTSC_D) + +#define V4L2_SLICED_CAPTION (V4L2_SLICED_CAPTION_525 |\ + V4L2_SLICED_CAPTION_625) + +#define V4L2_SLICED_WSS (V4L2_SLICED_WSS_525 |\ + V4L2_SLICED_WSS_625) + +#define V4L2_SLICED_VITC (V4L2_SLICED_VITC_525 |\ + V4L2_SLICED_VITC_625) #define V4L2_SLICED_VBI_525 (V4L2_SLICED_TELETEXT_NTSC_B |\ V4L2_SLICED_TELETEXT_NTSC_C |\ -- cgit v1.2.3 From 77853bf2b48e34449e826a9ef4df5ea0dbe947f4 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 23 Jan 2006 13:09:36 +0900 Subject: [PATCH] libata: make the owner of a qc responsible for freeing it qc used to be freed automatically on command completion. However, as a qc can carry information about its completion status, it can be useful to its owner/issuer after command completion. This patch makes freeing qc responsibility of its owner. This simplifies ata_exec_internal() and makes command turn-around for atapi request sensing less hackish. This change was originally suggested by Jeff Garzik. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- 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 46ccea215892..d58b659cf3f5 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -235,7 +235,7 @@ struct ata_port; struct ata_queued_cmd; /* typedefs */ -typedef int (*ata_qc_cb_t) (struct ata_queued_cmd *qc); +typedef void (*ata_qc_cb_t) (struct ata_queued_cmd *qc); struct ata_ioports { unsigned long cmd_addr; -- cgit v1.2.3 From 11a56d2439259892319df81cf1582687d7e7fde5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 23 Jan 2006 13:09:36 +0900 Subject: [PATCH] libata: add detailed AC_ERR_* flags Add detailed AC_ERR_* flags and use them. Long-term goal is to describe all errors with err_mask and tf combination (tf for failed sector information, etc...). After proper error diagnosis is implemented, sense data should also be generated from err_mask instead of directly from hardware tf registers as it is currently. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index d58b659cf3f5..8ff3a7f6f63c 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -222,10 +222,15 @@ enum hsm_task_states { }; enum ata_completion_errors { - AC_ERR_OTHER = (1 << 0), - AC_ERR_DEV = (1 << 1), - AC_ERR_ATA_BUS = (1 << 2), - AC_ERR_HOST_BUS = (1 << 3), + AC_ERR_DEV = (1 << 0), /* device reported error */ + AC_ERR_HSM = (1 << 1), /* host state machine violation */ + AC_ERR_TIMEOUT = (1 << 2), /* timeout */ + AC_ERR_MEDIA = (1 << 3), /* media error */ + AC_ERR_ATA_BUS = (1 << 4), /* ATA bus error */ + AC_ERR_HOST_BUS = (1 << 5), /* host bus error */ + AC_ERR_SYSTEM = (1 << 6), /* system error */ + AC_ERR_INVALID = (1 << 7), /* invalid argument */ + AC_ERR_OTHER = (1 << 8), /* unknown */ }; /* forward declarations */ @@ -833,7 +838,7 @@ static inline int ata_try_flush_cache(const struct ata_device *dev) static inline unsigned int ac_err_mask(u8 status) { if (status & ATA_BUSY) - return AC_ERR_ATA_BUS; + return AC_ERR_HSM; if (status & (ATA_ERR | ATA_DF)) return AC_ERR_DEV; return 0; -- cgit v1.2.3 From 9a3d9eb0177eb10500d49cd283b35576082a522d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 23 Jan 2006 13:09:36 +0900 Subject: [PATCH] libata: return AC_ERR_* from issue functions Return AC_ERR_* mask from issue fuctions instead of 0/-1. This enables things like failing a qc with AC_ERR_HSM when the device doesn't set DRDY when the qc is about to be issued. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 8ff3a7f6f63c..b1ea2f98bfbb 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -427,7 +427,7 @@ struct ata_port_operations { void (*bmdma_start) (struct ata_queued_cmd *qc); void (*qc_prep) (struct ata_queued_cmd *qc); - int (*qc_issue) (struct ata_queued_cmd *qc); + unsigned int (*qc_issue) (struct ata_queued_cmd *qc); void (*eng_timeout) (struct ata_port *ap); @@ -515,7 +515,7 @@ extern void ata_port_stop (struct ata_port *ap); extern void ata_host_stop (struct ata_host_set *host_set); extern irqreturn_t ata_interrupt (int irq, void *dev_instance, struct pt_regs *regs); extern void ata_qc_prep(struct ata_queued_cmd *qc); -extern int ata_qc_issue_prot(struct ata_queued_cmd *qc); +extern unsigned int ata_qc_issue_prot(struct ata_queued_cmd *qc); 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, -- cgit v1.2.3 From a72ec4ce6d3ae92e76baf5b2c65cc26e5e775e83 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 23 Jan 2006 13:09:37 +0900 Subject: [PATCH] libata: implement and apply ata_eh_qc_complete/retry() Implement ata_eh_qc_complete/retry() using scsi_eh_finish_cmd() and scsi_eh_flush_done_q(). This removes all eh scsicmd finish hacks from low level drivers. This change was first suggested by Jeff Garzik. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index b1ea2f98bfbb..576788de962a 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -398,6 +398,7 @@ struct ata_port { unsigned long pio_task_timeout; u32 msg_enable; + struct list_head eh_done_q; void *private_data; }; @@ -490,6 +491,8 @@ extern int ata_scsi_detect(struct 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 *)); extern int ata_scsi_error(struct Scsi_Host *host); +extern void ata_eh_qc_complete(struct ata_queued_cmd *qc); +extern void ata_eh_qc_retry(struct ata_queued_cmd *qc); 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_scsi_device_resume(struct scsi_device *); -- cgit v1.2.3 From 6f8b99589524f3e759e44721376abcdf88ed8915 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 24 Jan 2006 17:05:21 +0900 Subject: [PATCH] libata: export ata_busy_sleep Export ata_busy_sleep(), to be used by low level driver reset functions. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 576788de962a..45646f6ebbf5 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -500,6 +500,9 @@ extern int ata_scsi_device_suspend(struct scsi_device *); extern int ata_device_resume(struct ata_port *, struct ata_device *); extern int ata_device_suspend(struct ata_port *, struct ata_device *); extern int ata_ratelimit(void); +extern unsigned int ata_busy_sleep(struct ata_port *ap, + unsigned long timeout_pat, + unsigned long timeout); /* * Default driver ops implementations -- cgit v1.2.3 From c19ba8af4f104cca28d548cac55c128b28dd31fb Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 24 Jan 2006 17:05:22 +0900 Subject: [PATCH] libata: new ->probe_reset operation Add new ->probe_reset operation to ata_port_operations obsoleting ->phy_reset. The main difference from ->phy_reset is that the new operation is not allowed to manipulate libata internals directly. It's not allowed to configure or disable the port or devices. It can only succeed or fail and classify attached devices into passed @classes. This change gives more control to higher level and eases sharing reset methods with EH. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 45646f6ebbf5..a84d1c3a5429 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -148,9 +148,9 @@ enum { ATA_FLAG_PORT_DISABLED = (1 << 2), /* port is disabled, ignore it */ ATA_FLAG_SATA = (1 << 3), ATA_FLAG_NO_LEGACY = (1 << 4), /* no legacy mode check */ - ATA_FLAG_SRST = (1 << 5), /* use ATA SRST, not E.D.D. */ + ATA_FLAG_SRST = (1 << 5), /* (obsolete) use ATA SRST, not E.D.D. */ ATA_FLAG_MMIO = (1 << 6), /* use MMIO, not PIO */ - ATA_FLAG_SATA_RESET = (1 << 7), /* use COMRESET */ + ATA_FLAG_SATA_RESET = (1 << 7), /* (obsolete) use COMRESET */ ATA_FLAG_PIO_DMA = (1 << 8), /* PIO cmds via DMA */ ATA_FLAG_NOINTR = (1 << 9), /* FIXME: Remove this once * proper HSM is in place. */ @@ -419,7 +419,9 @@ struct ata_port_operations { u8 (*check_altstatus)(struct ata_port *ap); void (*dev_select)(struct ata_port *ap, unsigned int device); - void (*phy_reset) (struct ata_port *ap); + void (*phy_reset) (struct ata_port *ap); /* obsolete */ + int (*probe_reset) (struct ata_port *ap, unsigned int *classes); + void (*post_set_mode) (struct ata_port *ap); int (*check_atapi_dma) (struct ata_queued_cmd *qc); -- cgit v1.2.3 From d0412d967032b9e147bcbacc9ff0c0342636cf2d Mon Sep 17 00:00:00 2001 From: James Chapman Date: Fri, 27 Jan 2006 01:15:30 -0700 Subject: [PATCH] mv643xx_eth: use MII library for ethtool functions Use the common ethtool support functions of the MII library. Add generic MII ioctl handler. Add PHY parameter speed/duplex/negotiation initialization and modification. Signed-off-by: James Chapman Signed-off-by: Dale Farnsworth Signed-off-by: Jeff Garzik --- include/linux/mv643xx.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mv643xx.h b/include/linux/mv643xx.h index 0b08cd692201..7ffbeac7d2bb 100644 --- a/include/linux/mv643xx.h +++ b/include/linux/mv643xx.h @@ -1214,6 +1214,7 @@ struct mv64xxx_i2c_pdata { #define MV643XX_ETH_FORCE_BP_MODE_NO_JAM 0 #define MV643XX_ETH_FORCE_BP_MODE_JAM_TX (1<<7) #define MV643XX_ETH_FORCE_BP_MODE_JAM_TX_ON_RX_ERR (1<<8) +#define MV643XX_ETH_SERIAL_PORT_CONTROL_RESERVED (1<<9) #define MV643XX_ETH_FORCE_LINK_FAIL 0 #define MV643XX_ETH_DO_NOT_FORCE_LINK_FAIL (1<<10) #define MV643XX_ETH_RETRANSMIT_16_ATTEMPTS 0 @@ -1243,6 +1244,8 @@ struct mv64xxx_i2c_pdata { #define MV643XX_ETH_SET_MII_SPEED_TO_10 0 #define MV643XX_ETH_SET_MII_SPEED_TO_100 (1<<24) +#define MV643XX_ETH_MAX_RX_PACKET_MASK (0x7<<17) + #define MV643XX_ETH_PORT_SERIAL_CONTROL_DEFAULT_VALUE \ MV643XX_ETH_DO_NOT_FORCE_LINK_PASS | \ MV643XX_ETH_ENABLE_AUTO_NEG_FOR_DUPLX | \ -- cgit v1.2.3 From 01999873a455fe9104e91820c72849e608239928 Mon Sep 17 00:00:00 2001 From: Dale Farnsworth Date: Fri, 27 Jan 2006 01:18:01 -0700 Subject: [PATCH] mv643xx_eth: Clean up platform_data configuration We shouldn't expose the hardware register contents in platform_data. The only things we allow the user to configure are autoneg, speed, and duplex. Add specific platform_data fields for these values and remove the registers configs. Signed-off-by: Dale Farnsworth Signed-off-by: Jeff Garzik --- include/linux/mv643xx.h | 24 ++++++++---------------- 1 file changed, 8 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mv643xx.h b/include/linux/mv643xx.h index 7ffbeac7d2bb..955d3069d727 100644 --- a/include/linux/mv643xx.h +++ b/include/linux/mv643xx.h @@ -1288,23 +1288,15 @@ struct mv64xxx_i2c_pdata { #define MV643XX_ETH_NAME "mv643xx_eth" struct mv643xx_eth_platform_data { - /* - * Non-values for mac_addr, phy_addr, port_config, etc. - * override the default value. Setting the corresponding - * force_* field, causes the default value to be overridden - * even when zero. - */ - unsigned int force_phy_addr:1; - unsigned int force_port_config:1; - unsigned int force_port_config_extend:1; - unsigned int force_port_sdma_config:1; - unsigned int force_port_serial_control:1; - int phy_addr; char *mac_addr; /* pointer to mac address */ - u32 port_config; - u32 port_config_extend; - u32 port_sdma_config; - u32 port_serial_control; + u16 force_phy_addr; /* force override if phy_addr == 0 */ + u16 phy_addr; + + /* If speed is 0, then speed and duplex are autonegotiated. */ + int speed; /* 0, SPEED_10, SPEED_100, SPEED_1000 */ + int duplex; /* DUPLEX_HALF or DUPLEX_FULL */ + + /* non-zero values of the following fields override defaults */ u32 tx_queue_size; u32 rx_queue_size; u32 tx_sram_addr; -- cgit v1.2.3 From a62c0fc526c344d8163f7a9e45e68cc63826ffd3 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 24 Jan 2006 17:05:22 +0900 Subject: [PATCH] libata: implement ata_drive_probe_reset() Most low level drivers share supported reset/classify actions and sequence. This patch implements ata_drive_probe_reset() which helps constructing ->probe_reset from three component operations - softreset, hardreset and postreset. This minimizes duplicate code and yet allows flexibility if needed. The three component operations can also be shared by EH later. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index a84d1c3a5429..38e08ce2d1af 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -241,6 +241,8 @@ struct ata_queued_cmd; /* typedefs */ typedef void (*ata_qc_cb_t) (struct ata_queued_cmd *qc); +typedef int (*ata_reset_fn_t)(struct ata_port *, int, unsigned int *); +typedef void (*ata_postreset_fn_t)(struct ata_port *ap, unsigned int *); struct ata_ioports { unsigned long cmd_addr; @@ -478,6 +480,9 @@ extern void ata_port_probe(struct ata_port *); extern void __sata_phy_reset(struct ata_port *ap); extern void sata_phy_reset(struct ata_port *ap); extern void ata_bus_reset(struct ata_port *ap); +extern int ata_drive_probe_reset(struct ata_port *ap, + ata_reset_fn_t softreset, ata_reset_fn_t hardreset, + ata_postreset_fn_t postreset, unsigned int *classes); extern void ata_port_disable(struct ata_port *); extern void ata_std_ports(struct ata_ioports *ioaddr); #ifdef CONFIG_PCI -- cgit v1.2.3 From c2bd58047b9b5c91a3b0a851de66a877f2eb7ae3 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 24 Jan 2006 17:05:22 +0900 Subject: [PATCH] libata: implement standard reset component operations and ->probe_reset Implement SRST, COMRESET and standard postreset component operations for ata_drive_probe_reset(), and use these three functions to implement ata_std_probe_reset. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 38e08ce2d1af..474cdfa35d1e 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -483,6 +483,11 @@ extern void ata_bus_reset(struct ata_port *ap); extern int ata_drive_probe_reset(struct ata_port *ap, ata_reset_fn_t softreset, ata_reset_fn_t hardreset, ata_postreset_fn_t postreset, unsigned int *classes); +extern int ata_std_softreset(struct ata_port *ap, int verbose, + unsigned int *classes); +extern int sata_std_hardreset(struct ata_port *ap, int verbose, + unsigned int *class); +extern void ata_std_postreset(struct ata_port *ap, unsigned int *classes); extern void ata_port_disable(struct ata_port *); extern void ata_std_ports(struct ata_ioports *ioaddr); #ifdef CONFIG_PCI @@ -523,6 +528,7 @@ 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 void ata_exec_command(struct ata_port *ap, const struct ata_taskfile *tf); +extern int ata_std_probe_reset(struct ata_port *ap, unsigned int *classes); 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); -- cgit v1.2.3 From d97a11e091a0bf40f1cfb0bbf443ddd7b455b133 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 7 Feb 2006 06:48:40 -0200 Subject: V4L/DVB (3300): Add standard for South Korean NTSC-M using A2 audio. South Korea uses NTSC-M but with A2 audio instead of BTSC. Several audio chips need this information in order to set the correct audio processing registers. Acked-by: Mauro Carvalho Chehab Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 6e33ce96cab0..965c8902fe60 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -638,6 +638,7 @@ typedef __u64 v4l2_std_id; #define V4L2_STD_NTSC_M ((v4l2_std_id)0x00001000) #define V4L2_STD_NTSC_M_JP ((v4l2_std_id)0x00002000) #define V4L2_STD_NTSC_443 ((v4l2_std_id)0x00004000) +#define V4L2_STD_NTSC_M_KR ((v4l2_std_id)0x00008000) #define V4L2_STD_SECAM_B ((v4l2_std_id)0x00010000) #define V4L2_STD_SECAM_D ((v4l2_std_id)0x00020000) @@ -670,7 +671,8 @@ typedef __u64 v4l2_std_id; V4L2_STD_PAL_H |\ V4L2_STD_PAL_I) #define V4L2_STD_NTSC (V4L2_STD_NTSC_M |\ - V4L2_STD_NTSC_M_JP) + V4L2_STD_NTSC_M_JP |\ + V4L2_STD_NTSC_M_KR) #define V4L2_STD_SECAM_DK (V4L2_STD_SECAM_D |\ V4L2_STD_SECAM_K |\ V4L2_STD_SECAM_K1) -- cgit v1.2.3 From 3593cab5d62c4c7abced1076710f9bc2d8847433 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 7 Feb 2006 06:49:14 -0200 Subject: V4L/DVB (3318b): sem2mutex: drivers/media/, #2 Semaphore to mutex conversion. The conversion was generated via scripts, and the result was validated automatically via a script as well. Signed-off-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 965c8902fe60..1dd8efeff35a 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -17,6 +17,7 @@ #include /* need struct timeval */ #include #include +#include #endif #include /* need __user */ @@ -90,7 +91,7 @@ struct video_device /* for videodev.c intenal usage -- please don't touch */ int users; /* video_exclusive_{open|close} ... */ - struct semaphore lock; /* ... helper function uses these */ + struct mutex lock; /* ... helper function uses these */ char devfs_name[64]; /* devfs */ struct class_device class_dev; /* sysfs */ }; -- cgit v1.2.3 From dde44589bf9fac0168c6ce6d097c99c33b18074f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 2 Feb 2006 00:56:10 +0900 Subject: [PATCH] libata: implement ATA_FLAG_IN_EH port flag ATA_FLAG_IN_EH flag is set on entry to EH and cleared on completion. This patch just sets and clears the flag. Following patches will build normal qc execution / EH synchronization aroung this flag. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- 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 474cdfa35d1e..55176df403a5 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -162,6 +162,8 @@ enum { ATA_FLAG_PIO_LBA48 = (1 << 13), /* Host DMA engine is LBA28 only */ ATA_FLAG_IRQ_MASK = (1 << 14), /* Mask IRQ in PIO xfers */ + ATA_FLAG_IN_EH = (1 << 15), /* EH in progress */ + ATA_QCFLAG_ACTIVE = (1 << 1), /* cmd not yet ack'd to scsi lyer */ ATA_QCFLAG_SG = (1 << 3), /* have s/g table? */ ATA_QCFLAG_SINGLE = (1 << 4), /* no s/g, just a single buffer */ -- cgit v1.2.3 From c18d06f89fd09ee0059c4899e615c471d59af66a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 2 Feb 2006 00:56:10 +0900 Subject: [PATCH] libata: EH / pio tasks synchronization This patch makes sure that pio tasks are flushed before proceeding with EH. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 55176df403a5..f4cd1eb734a0 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -162,7 +162,8 @@ enum { ATA_FLAG_PIO_LBA48 = (1 << 13), /* Host DMA engine is LBA28 only */ ATA_FLAG_IRQ_MASK = (1 << 14), /* Mask IRQ in PIO xfers */ - ATA_FLAG_IN_EH = (1 << 15), /* EH in progress */ + ATA_FLAG_FLUSH_PIO_TASK = (1 << 15), /* Flush PIO task */ + ATA_FLAG_IN_EH = (1 << 16), /* EH in progress */ ATA_QCFLAG_ACTIVE = (1 << 1), /* cmd not yet ack'd to scsi lyer */ ATA_QCFLAG_SG = (1 << 3), /* have s/g table? */ -- cgit v1.2.3 From 7944ea9522ce0ea32d57894b3dc2540b0bdca66e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 2 Feb 2006 18:20:00 +0900 Subject: [PATCH] libata: add probeinit component operation to ata_drive_probe_reset() This patch adds probeinit component operation to ata_drive_probe_reset(). If present, this new operation is called before performing any reset. The operations's roll is to prepare @ap for following probe-reset operations. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- 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 f4cd1eb734a0..e8f29cefc351 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -244,6 +244,7 @@ struct ata_queued_cmd; /* typedefs */ typedef void (*ata_qc_cb_t) (struct ata_queued_cmd *qc); +typedef void (*ata_probeinit_fn_t)(struct ata_port *); typedef int (*ata_reset_fn_t)(struct ata_port *, int, unsigned int *); typedef void (*ata_postreset_fn_t)(struct ata_port *ap, unsigned int *); @@ -484,6 +485,7 @@ extern void __sata_phy_reset(struct ata_port *ap); extern void sata_phy_reset(struct ata_port *ap); extern void ata_bus_reset(struct ata_port *ap); extern int ata_drive_probe_reset(struct ata_port *ap, + ata_probeinit_fn_t probeinit, ata_reset_fn_t softreset, ata_reset_fn_t hardreset, ata_postreset_fn_t postreset, unsigned int *classes); extern int ata_std_softreset(struct ata_port *ap, int verbose, -- cgit v1.2.3 From 8a19ac89edbe9b702c10fd2039b8cb2db4644a5f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 2 Feb 2006 18:20:00 +0900 Subject: [PATCH] libata: implement ata_std_probeinit() This patch implements the off-the-shelf probeinit component operation. Currently, all it does is waking up the PHY if it's a SATA port. Signed-off-by: Tejun Heo 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 e8f29cefc351..68b3fe6f9a4d 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -488,6 +488,7 @@ extern int ata_drive_probe_reset(struct ata_port *ap, ata_probeinit_fn_t probeinit, ata_reset_fn_t softreset, ata_reset_fn_t hardreset, ata_postreset_fn_t postreset, unsigned int *classes); +extern void ata_std_probeinit(struct ata_port *ap); extern int ata_std_softreset(struct ata_port *ap, int verbose, unsigned int *classes); extern int sata_std_hardreset(struct ata_port *ap, int verbose, -- cgit v1.2.3 From 341963b909a01d2f38d86f5db8dd1f8c80bd6dbf Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 10 Feb 2006 15:10:48 +0900 Subject: [PATCH] libata: add ATA_QCFLAG_EH_SCHEDULED Add ATA_QCFLAG_EH_SCHEDULED. If this flag is set, the qc is owned by EH and normal completion path is not allowed to finish it. This patch doesn't actually use this flag. Signed-off-by: Tejun Heo 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 68b3fe6f9a4d..5c70a57f93ee 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -169,6 +169,7 @@ enum { ATA_QCFLAG_SG = (1 << 3), /* have s/g table? */ ATA_QCFLAG_SINGLE = (1 << 4), /* no s/g, just a single buffer */ ATA_QCFLAG_DMAMAP = ATA_QCFLAG_SG | ATA_QCFLAG_SINGLE, + ATA_QCFLAG_EH_SCHEDULED = (1 << 5), /* EH scheduled */ /* various lengths of time */ ATA_TMOUT_EDD = 5 * HZ, /* heuristic */ -- cgit v1.2.3 From f29841e08fa20a7f2c8bc1b70306975299c66ee7 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 10 Feb 2006 15:10:48 +0900 Subject: [PATCH] libata: implement ata_scsi_timed_out() Implement ata_scsi_timed_out(), to be used as scsi_host_template->eh_timed_out callback for all libata drivers. Without this function, the following race exists. If a qc completes after SCSI timer expires but before libata EH kicks in, the qc gets completed but the scsicmd still gets passed to libata EH resulting in ->eng_timeout invocation with NULL qc, which none is handling properly. This patch makes sure that scmd and qc share the same lifetime. Original idea from Jeff Garzik . Signed-off-by: Tejun Heo 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 5c70a57f93ee..c1e198655bb1 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -509,6 +509,7 @@ extern void ata_host_set_remove(struct ata_host_set *host_set); extern int ata_scsi_detect(struct 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 *)); +extern enum scsi_eh_timer_return ata_scsi_timed_out(struct scsi_cmnd *cmd); extern int ata_scsi_error(struct Scsi_Host *host); extern void ata_eh_qc_complete(struct ata_queued_cmd *qc); extern void ata_eh_qc_retry(struct ata_queued_cmd *qc); -- cgit v1.2.3 From 76014427e60f7ecfdc689dfbcb48e9760e1da4fb Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sat, 11 Feb 2006 15:13:49 +0900 Subject: [PATCH] libata: inline ata_qc_complete() This patch inlines ata_qc_complete() and uninlines __ata_qc_complete() as suggested by Jeff Garzik. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index c1e198655bb1..695d9ae6ec03 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -556,7 +556,7 @@ extern void ata_bmdma_start (struct ata_queued_cmd *qc); extern void ata_bmdma_stop(struct ata_queued_cmd *qc); extern u8 ata_bmdma_status(struct ata_port *ap); extern void ata_bmdma_irq_clear(struct ata_port *ap); -extern void ata_qc_complete(struct ata_queued_cmd *qc); +extern void __ata_qc_complete(struct ata_queued_cmd *qc); extern void ata_eng_timeout(struct ata_port *ap); extern void ata_scsi_simulate(struct ata_port *ap, struct ata_device *dev, struct scsi_cmnd *cmd, @@ -756,6 +756,24 @@ static inline void ata_qc_reinit(struct ata_queued_cmd *qc) ata_tf_init(qc->ap, &qc->tf, qc->dev->devno); } +/** + * ata_qc_complete - Complete an active ATA command + * @qc: Command to complete + * @err_mask: ATA Status register contents + * + * Indicate to the mid and upper layers that an ATA + * command has completed, with either an ok or not-ok status. + * + * LOCKING: + * spin_lock_irqsave(host_set lock) + */ +static inline void ata_qc_complete(struct ata_queued_cmd *qc) +{ + if (unlikely(qc->flags & ATA_QCFLAG_EH_SCHEDULED)) + return; + + __ata_qc_complete(qc); +} /** * ata_irq_on - Enable interrupts on a port. -- cgit v1.2.3 From bef4a456b8dc8b3638f4d49a25a89e1467da9483 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sat, 11 Feb 2006 19:11:13 +0900 Subject: [PATCH] libata: kill assert() macro libata assert() now has no user left. Kill it. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 695d9ae6ec03..83a1f2ead861 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -62,16 +62,6 @@ #define BPRINTK(fmt, args...) if (ap->flags & ATA_FLAG_DEBUGMSG) printk(KERN_ERR "%s: " fmt, __FUNCTION__, ## args) -#ifdef ATA_NDEBUG -#define assert(expr) -#else -#define assert(expr) \ - if(unlikely(!(expr))) { \ - printk(KERN_ERR "Assertion failed! %s,%s,%s,line=%d\n", \ - #expr,__FILE__,__FUNCTION__,__LINE__); \ - } -#endif - /* NEW: debug levels */ #define HAVE_LIBATA_MSG 1 -- cgit v1.2.3 From 0e949ff304a7ca07db38c17fbbf3ead1085d7bbf Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 12 Feb 2006 22:47:04 +0900 Subject: [PATCH] libata: implement ata_dev_id_c_string() ata_dev_id_c_string() reads ATA string from the specified offset of the given IDENTIFY PAGE and puts it in the specified buffer in trimmed and NULL-terminated form. The caller must supply a buffer which is one byte larger than the maximum size of the target ID string. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- 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 83a1f2ead861..0853032673b7 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -540,6 +540,8 @@ extern void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg, 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_id_c_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); extern void ata_bmdma_start (struct ata_queued_cmd *qc); -- cgit v1.2.3 From 3d2ca91095f8ab6dc0cb925374eec62fa5336764 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 12 Feb 2006 22:47:04 +0900 Subject: [PATCH] libata: separate out ata_id_major_version() Separate out ATA major version calculation from ata_dev_identify() into ata_id_major_version(). It's preparation for splitting ata_dev_identify(). Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/ata.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index a8155ca4947f..b02a16c435e7 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -267,6 +267,16 @@ struct ata_taskfile { ((u64) (id)[(n) + 1] << 16) | \ ((u64) (id)[(n) + 0]) ) +static inline unsigned int ata_id_major_version(const u16 *id) +{ + unsigned int mver; + + for (mver = 14; mver >= 1; mver--) + if (id[ATA_ID_MAJOR_VER] & (1 << mver)) + break; + return mver; +} + static inline int ata_id_current_chs_valid(const u16 *id) { /* For ATA-1 devices, if the INITIALIZE DEVICE PARAMETERS command -- cgit v1.2.3 From 6e7846e9c548443c86cfbad9e4defb4bdcfc538b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 12 Feb 2006 23:32:58 +0900 Subject: [PATCH] libata: move cdb_len for host to device cdb_len is per-device property. Sharing cdb_len on ap results in inaccurate configuration on revalidation and hotplugging. This patch makes cdb_len per-device. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- 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 0853032673b7..853c98859a9f 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -348,6 +348,7 @@ struct ata_device { unsigned int multi_count; /* sectors count for READ/WRITE MULTIPLE */ + unsigned int cdb_len; /* for CHS addressing */ u16 cylinders; /* Number of cylinders */ @@ -377,7 +378,6 @@ struct ata_port { unsigned int mwdma_mask; unsigned int udma_mask; unsigned int cbl; /* cable type; ATA_CBL_xxx */ - unsigned int cdb_len; struct ata_device device[ATA_MAX_DEVICES]; -- cgit v1.2.3 From b00eec1d58ee71131375bfeb86e64bceec3f5618 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 12 Feb 2006 23:32:59 +0900 Subject: [PATCH] libata: add per-device max_sectors If a low level driver wants to control max_sectors, it had to adjust ap->host->max_sectors and set ATA_DFLAG_LOCK_SECTORS to tell ata_scsi_slave_config not to override the limit. This is not only cumbersome but also incorrect for hosts which support more than one devices per port. This patch adds per-device ->max_sectors. If the field is unset (zero), libata core layer will adjust ->max_sectors according to default rules. If the field is set, libata honors the setting. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 853c98859a9f..afe46457124e 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -122,8 +122,7 @@ enum { /* struct ata_device stuff */ 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_DFLAG_LBA = (1 << 2), /* device supports LBA */ ATA_DEV_UNKNOWN = 0, /* unknown device */ ATA_DEV_ATA = 1, /* ATA device */ @@ -348,6 +347,7 @@ struct ata_device { unsigned int multi_count; /* sectors count for READ/WRITE MULTIPLE */ + unsigned int max_sectors; /* per-device max sectors */ unsigned int cdb_len; /* for CHS addressing */ -- cgit v1.2.3 From 6a62a04d4705df4f9f9bee39e889b9e920eeca47 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 13 Feb 2006 10:02:46 +0900 Subject: [PATCH] libata: rename ata_dev_id_[c_]string() This patch renames ata_dev_id_[c_]string() to ata_id_[c_]string(). All other functions which read data from ATA ID data start with ata_id and those two function names were getting too long. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index afe46457124e..0d6bf50ad029 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -538,10 +538,10 @@ extern void ata_sg_init_one(struct ata_queued_cmd *qc, void *buf, extern void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg, unsigned int n_elem); 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_id_c_string(const u16 *id, unsigned char *s, - unsigned int ofs, unsigned int len); +extern void ata_id_string(const u16 *id, unsigned char *s, + unsigned int ofs, unsigned int len); +extern void ata_id_c_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); extern void ata_bmdma_start (struct ata_queued_cmd *qc); -- cgit v1.2.3 From 85edae14e4ee5e68cf037e9e4bca7498ea16874d Mon Sep 17 00:00:00 2001 From: Michal Janusz Miroslaw Date: Thu, 23 Feb 2006 09:49:35 +0000 Subject: [SERIAL] Trivial comment fix: include/linux/serial_reg.h Trivial comment fix for include/linux/serial_reg.h Signed-off-by: Russell King --- include/linux/serial_reg.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_reg.h b/include/linux/serial_reg.h index 6a2bb955844b..3c8a6aa77415 100644 --- a/include/linux/serial_reg.h +++ b/include/linux/serial_reg.h @@ -247,10 +247,10 @@ #define UART_CTR 0xFF /* - * The 16C950 Additional Control Reigster + * The 16C950 Additional Control Register */ #define UART_ACR_RXDIS 0x01 /* Receiver disable */ -#define UART_ACR_TXDIS 0x02 /* Receiver disable */ +#define UART_ACR_TXDIS 0x02 /* Transmitter disable */ #define UART_ACR_DSRFC 0x04 /* DSR Flow Control */ #define UART_ACR_TLENB 0x20 /* 950 trigger levels enable */ #define UART_ACR_ICRRD 0x40 /* ICR Read enable */ -- cgit v1.2.3 From c04030e16dbea2f7581f82cc6688695927f6ac5b Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Fri, 24 Feb 2006 13:04:21 -0800 Subject: [PATCH] flags parameter for linkat I'm currently at the POSIX meeting and one thing covered was the incompatibility of Linux's link() with the POSIX definition. The name. Linux does not follow symlinks, POSIX requires it does. Even if somebody thinks this is a good default behavior we cannot change this because it would break the ABI. But the fact remains that some application might want this behavior. We have one chance to help implementing this without breaking the behavior. For this we could use the new linkat interface which would need a new flags parameter. If the new parameter is AT_SYMLINK_FOLLOW the new behavior could be invoked. I do not want to introduce such a patch now. But we could add the parameter now, just don't use it. The patch below would do this. Can we get this late patch applied before the release more or less fixes the syscall API? Signed-off-by: Ulrich Drepper Signed-off-by: Ralf Baechle Cc: Heiko Carstens Cc: Martin Schwidefsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/syscalls.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index d73501ba7e44..b9ea44ac0ddb 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -543,7 +543,7 @@ asmlinkage long sys_unlinkat(int dfd, const char __user * pathname, int flag); asmlinkage long sys_symlinkat(const char __user * oldname, int newdfd, const char __user * newname); asmlinkage long sys_linkat(int olddfd, const char __user *oldname, - int newdfd, const char __user *newname); + int newdfd, const char __user *newname, int flags); asmlinkage long sys_renameat(int olddfd, const char __user * oldname, int newdfd, const char __user * newname); asmlinkage long sys_futimesat(int dfd, char __user *filename, -- cgit v1.2.3 From 749eef857948a3de789b7d0e3b96d92199d723cf Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 27 Feb 2006 00:07:40 -0300 Subject: V4L/DVB (3334): Added ET61X251 fourcc type Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 1dd8efeff35a..3f1504353472 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -326,6 +326,7 @@ struct v4l2_pix_format #define V4L2_PIX_FMT_SN9C10X v4l2_fourcc('S','9','1','0') /* SN9C10x compression */ #define V4L2_PIX_FMT_PWC1 v4l2_fourcc('P','W','C','1') /* pwc older webcam */ #define V4L2_PIX_FMT_PWC2 v4l2_fourcc('P','W','C','2') /* pwc newer webcam */ +#define V4L2_PIX_FMT_ET61X251 v4l2_fourcc('E','6','2','5') /* ET61X251 compression */ /* * F O R M A T E N U M E R A T I O N -- cgit v1.2.3 From f05cce863fa399dd79c5aa3896d608b8b86d8030 Mon Sep 17 00:00:00 2001 From: Andreas Oberritter Date: Mon, 27 Feb 2006 00:09:00 -0300 Subject: V4L/DVB (3375): Add AUDIO_GET_PTS and VIDEO_GET_PTS ioctls Add two new ioctls to read the 33 bit presentation time stamp from audio and video devices as defined in ITU T-REC-H.222.0 and ISO/IEC 13818-1. Acked-by: Johannes Stezenbach Signed-off-by: Andreas Oberritter Signed-off-by: Mauro Carvalho Chehab --- include/linux/dvb/audio.h | 13 +++++++++++++ include/linux/dvb/video.h | 13 +++++++++++++ 2 files changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dvb/audio.h b/include/linux/dvb/audio.h index 2b8797084685..0874a67c6b92 100644 --- a/include/linux/dvb/audio.h +++ b/include/linux/dvb/audio.h @@ -121,4 +121,17 @@ typedef uint16_t audio_attributes_t; #define AUDIO_SET_ATTRIBUTES _IOW('o', 17, audio_attributes_t) #define AUDIO_SET_KARAOKE _IOW('o', 18, audio_karaoke_t) +/** + * AUDIO_GET_PTS + * + * Read the 33 bit presentation time stamp as defined + * in ITU T-REC-H.222.0 / ISO/IEC 13818-1. + * + * The PTS should belong to the currently played + * frame if possible, but may also be a value close to it + * like the PTS of the last decoded frame or the last PTS + * extracted by the PES parser. + */ +#define AUDIO_GET_PTS _IOR('o', 19, __u64) + #endif /* _DVBAUDIO_H_ */ diff --git a/include/linux/dvb/video.h b/include/linux/dvb/video.h index b1999bfeaa56..1f7fa0351daf 100644 --- a/include/linux/dvb/video.h +++ b/include/linux/dvb/video.h @@ -200,4 +200,17 @@ typedef uint16_t video_attributes_t; #define VIDEO_GET_SIZE _IOR('o', 55, video_size_t) #define VIDEO_GET_FRAME_RATE _IOR('o', 56, unsigned int) +/** + * VIDEO_GET_PTS + * + * Read the 33 bit presentation time stamp as defined + * in ITU T-REC-H.222.0 / ISO/IEC 13818-1. + * + * The PTS should belong to the currently played + * frame if possible, but may also be a value close to it + * like the PTS of the last decoded frame or the last PTS + * extracted by the PES parser. + */ +#define VIDEO_GET_PTS _IOR('o', 57, __u64) + #endif /*_DVBVIDEO_H_*/ -- cgit v1.2.3 From bafac2a512bf4fd2ce7520f3976ce8aab4435f74 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 27 Feb 2006 13:04:17 -0800 Subject: [NETFILTER]: Restore {ipt,ip6t,ebt}_LOG compatibility The nfnetlink_log infrastructure changes broke compatiblity of the LOG targets. They currently use whatever log backend was registered first, which means that if ipt_ULOG was loaded first, no messages will be printed to the ring buffer anymore. Restore compatiblity by using the old log functions by default and only use the nf_log backend if the user explicitly said so. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter_bridge/ebt_log.h | 1 + include/linux/netfilter_ipv4/ipt_LOG.h | 3 ++- include/linux/netfilter_ipv6/ip6t_LOG.h | 3 ++- 3 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_bridge/ebt_log.h b/include/linux/netfilter_bridge/ebt_log.h index 358fbc84fb59..96e231ae7554 100644 --- a/include/linux/netfilter_bridge/ebt_log.h +++ b/include/linux/netfilter_bridge/ebt_log.h @@ -3,6 +3,7 @@ #define EBT_LOG_IP 0x01 /* if the frame is made by ip, log the ip information */ #define EBT_LOG_ARP 0x02 +#define EBT_LOG_NFLOG 0x04 #define EBT_LOG_MASK (EBT_LOG_IP | EBT_LOG_ARP) #define EBT_LOG_PREFIX_SIZE 30 #define EBT_LOG_WATCHER "log" diff --git a/include/linux/netfilter_ipv4/ipt_LOG.h b/include/linux/netfilter_ipv4/ipt_LOG.h index 22d16177319b..892f9a33fea8 100644 --- a/include/linux/netfilter_ipv4/ipt_LOG.h +++ b/include/linux/netfilter_ipv4/ipt_LOG.h @@ -6,7 +6,8 @@ #define IPT_LOG_TCPOPT 0x02 /* Log TCP options */ #define IPT_LOG_IPOPT 0x04 /* Log IP options */ #define IPT_LOG_UID 0x08 /* Log UID owning local socket */ -#define IPT_LOG_MASK 0x0f +#define IPT_LOG_NFLOG 0x10 /* Log using nf_log backend */ +#define IPT_LOG_MASK 0x1f struct ipt_log_info { unsigned char level; diff --git a/include/linux/netfilter_ipv6/ip6t_LOG.h b/include/linux/netfilter_ipv6/ip6t_LOG.h index 9008ff5c40ae..060c1a1c6c60 100644 --- a/include/linux/netfilter_ipv6/ip6t_LOG.h +++ b/include/linux/netfilter_ipv6/ip6t_LOG.h @@ -6,7 +6,8 @@ #define IP6T_LOG_TCPOPT 0x02 /* Log TCP options */ #define IP6T_LOG_IPOPT 0x04 /* Log IP options */ #define IP6T_LOG_UID 0x08 /* Log UID owning local socket */ -#define IP6T_LOG_MASK 0x0f +#define IP6T_LOG_NFLOG 0x10 /* Log using nf_log backend */ +#define IP6T_LOG_MASK 0x1f struct ip6t_log_info { unsigned char level; -- cgit v1.2.3 From 1fa44ecad2b86475e038aed81b0bf333fa484f8b Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Thu, 23 Feb 2006 12:43:43 -0600 Subject: [SCSI] add execute_in_process_context() API We have several points in the SCSI stack (primarily for our device functions) where we need to guarantee process context, but (given the place where the last reference was released) we cannot guarantee this. This API gets around the issue by executing the function directly if the caller has process context, but scheduling a workqueue to execute in process context if the caller doesn't have it. Signed-off-by: James Bottomley --- include/linux/workqueue.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 86b111300231..957c21c16d62 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -20,6 +20,10 @@ struct work_struct { struct timer_list timer; }; +struct execute_work { + struct work_struct work; +}; + #define __WORK_INITIALIZER(n, f, d) { \ .entry = { &(n).entry, &(n).entry }, \ .func = (f), \ @@ -74,6 +78,8 @@ extern void init_workqueues(void); void cancel_rearming_delayed_work(struct work_struct *work); void cancel_rearming_delayed_workqueue(struct workqueue_struct *, struct work_struct *); +int execute_in_process_context(void (*fn)(void *), void *, + struct execute_work *); /* * Kill off a pending schedule_delayed_work(). Note that the work callback -- cgit v1.2.3 From d2b176ed878d4d5fcc0bd35656dfd373f3702af9 Mon Sep 17 00:00:00 2001 From: Jes Sorensen Date: Tue, 28 Feb 2006 09:42:23 -0800 Subject: [IA64] sysctl option to silence unaligned trap warnings Allow sysadmin to disable all warnings about userland apps making unaligned accesses by using: # echo 1 > /proc/sys/kernel/ignore-unaligned-usertrap Rather than having to use prctl on a process by process basis. Default behaivour leaves the warnings enabled. Signed-off-by: Jes Sorensen Signed-off-by: Tony Luck --- include/linux/sysctl.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 0e92bf7ec28e..bac61db26456 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -147,6 +147,7 @@ enum KERN_SETUID_DUMPABLE=69, /* int: behaviour of dumps for setuid core */ KERN_SPIN_RETRY=70, /* int: number of spinlock retries */ KERN_ACPI_VIDEO_FLAGS=71, /* int: flags for setting up video after ACPI sleep */ + KERN_IA64_UNALIGNED=72, /* int: ia64 unaligned userland trap enable */ }; -- cgit v1.2.3 From 0551fbd29e16fccd46e41b7d01bf0f8f39b14212 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Tue, 28 Feb 2006 16:59:19 -0800 Subject: [PATCH] Add mm->task_size and fix powerpc vdso This patch adds mm->task_size to keep track of the task size of a given mm and uses that to fix the powerpc vdso so that it uses the mm task size to decide what pages to fault in instead of the current thread flags (which broke when ptracing). (akpm: I expect that mm_struct.task_size will become the way in which we finally sort out the confusion between 32-bit processes and 32-bit mm's. It may need tweaks, but at this stage this patch is powerpc-only.) Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index b6f51e3a38ec..ff2e09c953b9 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -298,8 +298,9 @@ struct mm_struct { unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); void (*unmap_area) (struct mm_struct *mm, unsigned long addr); - unsigned long mmap_base; /* base of mmap area */ - unsigned long cached_hole_size; /* if non-zero, the largest hole below free_area_cache */ + unsigned long mmap_base; /* base of mmap area */ + unsigned long task_size; /* size of task vm space */ + unsigned long cached_hole_size; /* if non-zero, the largest hole below free_area_cache */ unsigned long free_area_cache; /* first hole of size cached_hole_size or larger */ pgd_t * pgd; atomic_t mm_users; /* How many users with user space? */ -- cgit v1.2.3 From 3af1efe8a301f5b1c813f5f761cb1e10d6175605 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Thu, 2 Mar 2006 13:25:26 -0500 Subject: [PATCH] reiserfs: fix unaligned bitmap usage The bitmaps associated with generation numbers for directory entries are declared as an array of ints. On some platforms, this causes alignment exceptions. The following patch uses the standard bitmap declaration macros to declare the bitmaps, fixing the problem. Originally from Takashi Iwai. Signed-off-by: Takashi Iwai Acked-by: Jeff Mahoney Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 7d51149bd793..dad78cecfd20 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -1052,7 +1052,7 @@ struct reiserfs_dir_entry { int de_entrylen; int de_namelen; char *de_name; - char *de_gen_number_bit_string; + unsigned long *de_gen_number_bit_string; __u32 de_dir_id; __u32 de_objectid; -- cgit v1.2.3 From 597afd21401c85bdf9441830abf431c2be6fd45f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 1 Mar 2006 01:25:38 +0900 Subject: [PATCH] libata: seperate out ata_class_present() Seperate out ata_class_present() from ata_dev_present(). This is useful because new reset mechanism deals with classes[] directly. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 66b6847225df..22e86cb2d166 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -645,10 +645,14 @@ static inline unsigned int ata_tag_valid(unsigned int tag) return (tag < ATA_MAX_QUEUE) ? 1 : 0; } +static inline unsigned int ata_class_present(unsigned int class) +{ + return class == ATA_DEV_ATA || class == ATA_DEV_ATAPI; +} + static inline unsigned int ata_dev_present(const struct ata_device *dev) { - return ((dev->class == ATA_DEV_ATA) || - (dev->class == ATA_DEV_ATAPI)); + return ata_class_present(dev->class); } static inline u8 ata_chk_status(struct ata_port *ap) -- cgit v1.2.3 From d9572b1d5e60b63e27e17f1f7771c5a26dd5d81e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 1 Mar 2006 16:09:35 +0900 Subject: [PATCH] libata: convert dev->id to pointer Convert dev->id from array to pointer. This is to accomodate revalidation. During revalidation, both old and new IDENTIFY pages should be accessible and single ->id array doesn't cut it. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- 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 22e86cb2d166..9f273dd1958c 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -339,7 +339,7 @@ struct ata_device { unsigned long flags; /* ATA_DFLAG_xxx */ unsigned int class; /* ATA_DEV_xxx */ unsigned int devno; /* 0 or 1 */ - u16 id[ATA_ID_WORDS]; /* IDENTIFY xxx DEVICE data */ + u16 *id; /* IDENTIFY xxx DEVICE data */ u8 pio_mode; u8 dma_mode; u8 xfer_mode; -- cgit v1.2.3 From 4b2f3ededc035525038a7a9247074243dac6b351 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 1 Mar 2006 16:09:36 +0900 Subject: [PATCH] libata: fold ata_dev_config() into ata_dev_configure() ata_dev_config() needs to be done everytime a device is configured. Fold it into ata_dev_configure(). Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 9f273dd1958c..86a504f0ef06 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -542,7 +542,6 @@ extern void ata_id_string(const u16 *id, unsigned char *s, unsigned int ofs, unsigned int len); extern void ata_id_c_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); extern void ata_bmdma_start (struct ata_queued_cmd *qc); extern void ata_bmdma_stop(struct ata_queued_cmd *qc); -- cgit v1.2.3 From 8f903c708fcc2b579ebf16542bf6109bad593a1d Mon Sep 17 00:00:00 2001 From: Jay Vosburgh Date: Tue, 21 Feb 2006 16:36:44 -0800 Subject: [PATCH] bonding: suppress duplicate packets Originally submitted by Kenzo Iwami; his original description is: The current bonding driver receives duplicate packets when broadcast/ multicast packets are sent by other devices or packets are flooded by the switch. In this patch, new flags are added in priv_flags of net_device structure to let the bonding driver discard duplicate packets in dev.c:skb_bond(). Modified by Jay Vosburgh to change a define name, update some comments, rearrange the new skb_bond() for clarity, clear all bonding priv_flags on slave release, and update the driver version. Signed-off-by: Kenzo Iwami Signed-off-by: Jay Vosburgh Signed-off-by: Jeff Garzik --- include/linux/if.h | 3 +++ include/linux/if_ether.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if.h b/include/linux/if.h index ce627d9092ef..12c6f6d157c3 100644 --- a/include/linux/if.h +++ b/include/linux/if.h @@ -52,6 +52,9 @@ /* Private (from user) interface flags (netdevice->priv_flags). */ #define IFF_802_1Q_VLAN 0x1 /* 802.1Q VLAN device. */ #define IFF_EBRIDGE 0x2 /* Ethernet bridging device. */ +#define IFF_SLAVE_INACTIVE 0x4 /* bonding slave not the curr. active */ +#define IFF_MASTER_8023AD 0x8 /* bonding master, 802.3ad. */ +#define IFF_MASTER_ALB 0x10 /* bonding master, balance-alb. */ #define IF_GET_IFACE 0x0001 /* for querying only */ #define IF_GET_PROTO 0x0002 diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h index 7a92c1ce1457..ab08f35cbc35 100644 --- a/include/linux/if_ether.h +++ b/include/linux/if_ether.h @@ -61,6 +61,7 @@ #define ETH_P_8021Q 0x8100 /* 802.1Q VLAN Extended Header */ #define ETH_P_IPX 0x8137 /* IPX over DIX */ #define ETH_P_IPV6 0x86DD /* IPv6 over bluebook */ +#define ETH_P_SLOW 0x8809 /* Slow Protocol. See 802.3ad 43B */ #define ETH_P_WCCP 0x883E /* Web-cache coordination protocol * defined in draft-wilson-wrec-wccp-v2-00.txt */ #define ETH_P_PPP_DISC 0x8863 /* PPPoE discovery messages */ -- cgit v1.2.3 From 623a3128aa2b86caa8e06e762e9e444177e4fa47 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 5 Mar 2006 17:55:58 +0900 Subject: [PATCH] libata: implement ata_dev_revalidate() ata_dev_revalidate() re-reads IDENTIFY PAGE of the given device and makes sure it's the same device as the configured one. Once it's verified that it's the same device, @dev is configured according to newly read IDENTIFY PAGE. Note that revalidation currently doesn't invoke transfer mode reconfiguration. Criteria for 'same device' * same class (of course) * same model string * same serial string * if ATA, same n_sectors (to catch geometry parameter changes) Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- 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 86a504f0ef06..66dce58f1941 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -485,6 +485,8 @@ extern int ata_std_softreset(struct ata_port *ap, int verbose, extern int sata_std_hardreset(struct ata_port *ap, int verbose, unsigned int *class); extern void ata_std_postreset(struct ata_port *ap, unsigned int *classes); +extern int ata_dev_revalidate(struct ata_port *ap, struct ata_device *dev, + int post_reset); extern void ata_port_disable(struct ata_port *); extern void ata_std_ports(struct ata_ioports *ioaddr); #ifdef CONFIG_PCI -- cgit v1.2.3 From 1e4b27df55166ce3b276f55bab223fa4ae8c5525 Mon Sep 17 00:00:00 2001 From: Karsten Keil Date: Mon, 6 Mar 2006 15:42:37 -0800 Subject: [PATCH] i4l: add new PCI IDs for HFC-S PCI Add new PCI IDs for HFC-S PCI based ISDN TA 'Primux II S0' and 'Primux II S0' from Gerdes AG Signed-off-by: Martin Bachem Signed-off-by: Karsten Keil Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 82b83da25d77..1709b5009d2e 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1752,6 +1752,8 @@ #define PCI_DEVICE_ID_CCD_B00B 0xb00b #define PCI_DEVICE_ID_CCD_B00C 0xb00c #define PCI_DEVICE_ID_CCD_B100 0xb100 +#define PCI_DEVICE_ID_CCD_B700 0xb700 +#define PCI_DEVICE_ID_CCD_B701 0xb701 #define PCI_VENDOR_ID_EXAR 0x13a8 #define PCI_DEVICE_ID_EXAR_XR17C152 0x0152 -- cgit v1.2.3 From 69239749e1ac4f3496906aa4267cb9f61ce52c9c Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 6 Mar 2006 15:42:45 -0800 Subject: [PATCH] fix next_timer_interrupt() for hrtimer Also from Thomas Gleixner Function next_timer_interrupt() got broken with a recent patch 6ba1b91213e81aa92b5cf7539f7d2a94ff54947c as sys_nanosleep() was moved to hrtimer. This broke things as next_timer_interrupt() did not check hrtimer tree for next event. Function next_timer_interrupt() is needed with dyntick (CONFIG_NO_IDLE_HZ, VST) implementations, as the system can be in idle when next hrtimer event was supposed to happen. At least ARM and S390 currently use next_timer_interrupt(). Signed-off-by: Thomas Gleixner Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Russell King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hrtimer.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 6361544bb6ae..6401c31d6add 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -116,6 +116,10 @@ extern int hrtimer_try_to_cancel(struct hrtimer *timer); extern ktime_t hrtimer_get_remaining(const struct hrtimer *timer); extern int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp); +#ifdef CONFIG_NO_IDLE_HZ +extern ktime_t hrtimer_get_next_event(void); +#endif + static inline int hrtimer_active(const struct hrtimer *timer) { return timer->state == HRTIMER_PENDING; -- cgit v1.2.3 From 78679302fe428f4f3dc853a51ee24f306010d874 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Mon, 6 Mar 2006 15:42:49 -0800 Subject: [PATCH] memory-hotplug compile fix include/linux/memory_hotplug.h:53: warning: 'struct page' declared inside parameter list (akpm: I tossed in a couple more possibly-needed-sometime struct decls too) Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 01f03bc06eff..968b1aa3732c 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -6,6 +6,10 @@ #include #include +struct page; +struct zone; +struct pglist_data; + #ifdef CONFIG_MEMORY_HOTPLUG /* * pgdat resizing functions -- cgit v1.2.3 From a615fa83959896f8eac76c235953fb164cd1a9b9 Mon Sep 17 00:00:00 2001 From: Jack Steiner Date: Mon, 6 Mar 2006 15:42:50 -0800 Subject: [PATCH] Increase max kmalloc size for very large systems Systems with extemely large numbers of nodes or cpus need to kmalloc structures larger than is currently supported. This patch increases the maximum supported size for very large systems. This patch should have no effect on current systems. (akpm: why not just use alloc_pages() for sysfs_cpus?) Signed-off-by: Jack Steiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kmalloc_sizes.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kmalloc_sizes.h b/include/linux/kmalloc_sizes.h index d82d4c05c12d..bda23e00ed71 100644 --- a/include/linux/kmalloc_sizes.h +++ b/include/linux/kmalloc_sizes.h @@ -19,8 +19,10 @@ CACHE(32768) CACHE(65536) CACHE(131072) -#ifndef CONFIG_MMU +#if (NR_CPUS > 512) || (MAX_NUMNODES > 256) || !defined(CONFIG_MMU) CACHE(262144) +#endif +#ifndef CONFIG_MMU CACHE(524288) CACHE(1048576) #ifdef CONFIG_LARGE_ALLOCS -- cgit v1.2.3 From a19cbd4bf258840ade3b6ee9e9256006d0644e09 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 8 Mar 2006 14:03:09 -0800 Subject: Mark the pipe file operations static They aren't used (nor even really usable) outside of pipe.c anyway Signed-off-by: Linus Torvalds --- include/linux/fs.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index e059da947007..0cc34b1c42c9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1418,9 +1418,6 @@ extern int is_bad_inode(struct inode *); extern struct file_operations read_fifo_fops; extern struct file_operations write_fifo_fops; extern struct file_operations rdwr_fifo_fops; -extern struct file_operations read_pipe_fops; -extern struct file_operations write_pipe_fops; -extern struct file_operations rdwr_pipe_fops; extern int fs_may_remount_ro(struct super_block *); -- cgit v1.2.3 From e2bab3d92486fb781f4d06f56339264ed1492392 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 7 Mar 2006 21:55:31 -0800 Subject: [PATCH] percpu_counter_sum() Implement percpu_counter_sum(). This is a more accurate but slower version of percpu_counter_read_positive(). We need this for Alex's speedup-ext3_statfs patch and for the nr_file accounting fix. Otherwise these things would be too inaccurate on large CPU counts. Cc: Ravikiran G Thirumalai Cc: Alex Tomas Cc: "David S. Miller" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/percpu_counter.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index bd6708e2c027..682525511c9e 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -39,6 +39,7 @@ static inline void percpu_counter_destroy(struct percpu_counter *fbc) } void percpu_counter_mod(struct percpu_counter *fbc, long amount); +long percpu_counter_sum(struct percpu_counter *fbc); static inline long percpu_counter_read(struct percpu_counter *fbc) { @@ -92,6 +93,11 @@ static inline long percpu_counter_read_positive(struct percpu_counter *fbc) return fbc->count; } +static inline long percpu_counter_sum(struct percpu_counter *fbc) +{ + return percpu_counter_read_positive(fbc); +} + #endif /* CONFIG_SMP */ static inline void percpu_counter_inc(struct percpu_counter *fbc) -- cgit v1.2.3 From 21a1ea9eb40411d4ee29448c53b9e4c0654d6ceb Mon Sep 17 00:00:00 2001 From: Dipankar Sarma Date: Tue, 7 Mar 2006 21:55:33 -0800 Subject: [PATCH] rcu batch tuning This patch adds new tunables for RCU queue and finished batches. There are two types of controls - number of completed RCU updates invoked in a batch (blimit) and monitoring for high rate of incoming RCUs on a cpu (qhimark, qlowmark). By default, the per-cpu batch limit is set to a small value. If the input RCU rate exceeds the high watermark, we do two things - force quiescent state on all cpus and set the batch limit of the CPU to INTMAX. Setting batch limit to INTMAX forces all finished RCUs to be processed in one shot. If we have more than INTMAX RCUs queued up, then we have bigger problems anyway. Once the incoming queued RCUs fall below the low watermark, the batch limit is set to the default. Signed-off-by: Dipankar Sarma Cc: "Paul E. McKenney" Cc: "David S. Miller" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rcupdate.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index b87aefa082e2..c2ec6c77874e 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -98,13 +98,17 @@ struct rcu_data { long batch; /* Batch # for current RCU batch */ struct rcu_head *nxtlist; struct rcu_head **nxttail; - long count; /* # of queued items */ + long qlen; /* # of queued callbacks */ struct rcu_head *curlist; struct rcu_head **curtail; struct rcu_head *donelist; struct rcu_head **donetail; + long blimit; /* Upper limit on a processed batch */ int cpu; struct rcu_head barrier; +#ifdef CONFIG_SMP + long last_rs_qlen; /* qlen during the last resched */ +#endif }; DECLARE_PER_CPU(struct rcu_data, rcu_data); -- cgit v1.2.3 From 529bf6be5c04f2e869d07bfdb122e9fd98ade714 Mon Sep 17 00:00:00 2001 From: Dipankar Sarma Date: Tue, 7 Mar 2006 21:55:35 -0800 Subject: [PATCH] fix file counting I have benchmarked this on an x86_64 NUMA system and see no significant performance difference on kernbench. Tested on both x86_64 and powerpc. The way we do file struct accounting is not very suitable for batched freeing. For scalability reasons, file accounting was constructor/destructor based. This meant that nr_files was decremented only when the object was removed from the slab cache. This is susceptible to slab fragmentation. With RCU based file structure, consequent batched freeing and a test program like Serge's, we just speed this up and end up with a very fragmented slab - llm22:~ # cat /proc/sys/fs/file-nr 587730 0 758844 At the same time, I see only a 2000+ objects in filp cache. The following patch I fixes this problem. This patch changes the file counting by removing the filp_count_lock. Instead we use a separate percpu counter, nr_files, for now and all accesses to it are through get_nr_files() api. In the sysctl handler for nr_files, we populate files_stat.nr_files before returning to user. Counting files as an when they are created and destroyed (as opposed to inside slab) allows us to correctly count open files with RCU. Signed-off-by: Dipankar Sarma Cc: "Paul E. McKenney" Cc: "David S. Miller" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/file.h | 2 -- include/linux/fs.h | 1 + 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index 418b6101b59a..9901b850f2e4 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -60,8 +60,6 @@ extern void put_filp(struct file *); extern int get_unused_fd(void); extern void FASTCALL(put_unused_fd(unsigned int fd)); struct kmem_cache; -extern void filp_ctor(void * objp, struct kmem_cache *cachep, unsigned long cflags); -extern void filp_dtor(void * objp, struct kmem_cache *cachep, unsigned long dflags); extern struct file ** alloc_fd_array(int); extern void free_fd_array(struct file **, int); diff --git a/include/linux/fs.h b/include/linux/fs.h index 0cc34b1c42c9..51c0c93bdf93 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -35,6 +35,7 @@ struct files_stat_struct { int max_files; /* tunable */ }; extern struct files_stat_struct files_stat; +extern int get_max_files(void); struct inodes_stat_t { int nr_inodes; -- cgit v1.2.3 From 0ef675d491bd65028fa838015ebc6ce8abefab6f Mon Sep 17 00:00:00 2001 From: Atsushi Nemoto Date: Thu, 9 Mar 2006 17:33:38 -0800 Subject: [PATCH] mtd: 64 bit fixes Fix some bugs in mtd/jffs2 on 64bit platform. The MEMGETBADBLOCK/MEMSETBADBLOCK ioctl are not listed in compat_ioctl.h. And some variables in jffs2 are declared as uint32_t but used to hold size_t values. Signed-off-by: Atsushi Nemoto Cc: Thomas Gleixner Acked-by: David Woodhouse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat_ioctl.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat_ioctl.h b/include/linux/compat_ioctl.h index 8fad50f8e389..ae7dfb790df3 100644 --- a/include/linux/compat_ioctl.h +++ b/include/linux/compat_ioctl.h @@ -696,6 +696,8 @@ COMPATIBLE_IOCTL(MEMLOCK) COMPATIBLE_IOCTL(MEMUNLOCK) COMPATIBLE_IOCTL(MEMGETREGIONCOUNT) COMPATIBLE_IOCTL(MEMGETREGIONINFO) +COMPATIBLE_IOCTL(MEMGETBADBLOCK) +COMPATIBLE_IOCTL(MEMSETBADBLOCK) /* NBD */ ULONG_IOCTL(NBD_SET_SOCK) ULONG_IOCTL(NBD_SET_BLKSIZE) -- cgit v1.2.3 From 8fce4d8e3b9e3cf47cc8afeb6077e22ab795d989 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 9 Mar 2006 17:33:54 -0800 Subject: [PATCH] slab: Node rotor for freeing alien caches and remote per cpu pages. The cache reaper currently tries to free all alien caches and all remote per cpu pages in each pass of cache_reap. For a machines with large number of nodes (such as Altix) this may lead to sporadic delays of around ~10ms. Interrupts are disabled while reclaiming creating unacceptable delays. This patch changes that behavior by adding a per cpu reap_node variable. Instead of attempting to free all caches, we free only one alien cache and the per cpu pages from one remote node. That reduces the time spend in cache_reap. However, doing so will lengthen the time it takes to completely drain all remote per cpu pagesets and all alien caches. The time needed will grow with the number of nodes in the system. All caches are drained when they overflow their respective capacity. So the drawback here is only that a bit of memory may be wasted for awhile longer. Details: 1. Rename drain_remote_pages to drain_node_pages to allow the specification of the node to drain of pcp pages. 2. Add additional functions init_reap_node, next_reap_node for NUMA that manage a per cpu reap_node counter. 3. Add a reap_alien function that reaps only from the current reap_node. For us this seems to be a critical issue. Holdoffs of an average of ~7ms cause some HPC benchmarks to slow down significantly. F.e. NAS parallel slows down dramatically. NAS parallel has a 12-16 seconds runtime w/o rotor compared to 5.8 secs with the rotor patches. It gets down to 5.05 secs with the additional interrupt holdoff reductions. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 20f9148e38d9..7851e6b520cf 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -157,9 +157,9 @@ extern void FASTCALL(free_cold_page(struct page *page)); void page_alloc_init(void); #ifdef CONFIG_NUMA -void drain_remote_pages(void); +void drain_node_pages(int node); #else -static inline void drain_remote_pages(void) { }; +static inline void drain_node_pages(int node) { }; #endif #endif /* __LINUX_GFP_H */ -- cgit v1.2.3 From 0adb25d2e71ab047423d6fc63d5d184590d0a66f Mon Sep 17 00:00:00 2001 From: Kirill Korotaev Date: Sat, 11 Mar 2006 03:27:13 -0800 Subject: [PATCH] ext3: ext3_symlink should use GFP_NOFS allocations inside This patch fixes illegal __GFP_FS allocation inside ext3 transaction in ext3_symlink(). Such allocation may re-enter ext3 code from try_to_free_pages. But JBD/ext3 code keeps a pointer to current journal handle in task_struct and, hence, is not reentrable. This bug led to "Assertion failure in journal_dirty_metadata()" messages. http://bugzilla.openvz.org/show_bug.cgi?id=115 Signed-off-by: Andrey Savochkin Signed-off-by: Kirill Korotaev Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 51c0c93bdf93..128d0082522c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1664,6 +1664,8 @@ extern int vfs_follow_link(struct nameidata *, const char *); extern int page_readlink(struct dentry *, char __user *, int); extern void *page_follow_link_light(struct dentry *, struct nameidata *); extern void page_put_link(struct dentry *, struct nameidata *, void *); +extern int __page_symlink(struct inode *inode, const char *symname, int len, + gfp_t gfp_mask); extern int page_symlink(struct inode *inode, const char *symname, int len); extern struct inode_operations page_symlink_inode_operations; extern int generic_readlink(struct dentry *, char __user *, int); -- cgit v1.2.3 From 7cd9013be6c22f3ff6f777354f766c8c0b955e17 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 11 Mar 2006 03:27:18 -0800 Subject: [PATCH] remove __put_task_struct_cb export again The patch '[PATCH] RCU signal handling' [1] added an export for __put_task_struct_cb, a put_task_struct helper newly introduced in that patch. But the put_task_struct couldn't be used modular previously as __put_task_struct wasn't exported. There are not callers of it in modular code, and it shouldn't be exported because we don't want drivers to hold references to task_structs. This patch removes the export and folds __put_task_struct into __put_task_struct_cb as there's no other caller. [1] http://www2.kernel.org/git/gitweb.cgi?p=linux/kernel/git/torvalds/linux-2.6.git;a=commit;h=e56d090310d7625ecb43a1eeebd479f04affb48b Signed-off-by: Christoph Hellwig Acked-by: Paul E. McKenney Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index ff2e09c953b9..62e6314382f0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -892,7 +892,6 @@ static inline int pid_alive(struct task_struct *p) } extern void free_task(struct task_struct *tsk); -extern void __put_task_struct(struct task_struct *tsk); #define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0) extern void __put_task_struct_cb(struct rcu_head *rhp); -- cgit v1.2.3 From 86e45b6bd6900c4a0b3666fb18b46e215f775c4f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 5 Mar 2006 15:29:09 +0900 Subject: [PATCH] libata: implement port_task Implement port_task. LLDD's can schedule a function to be executed with context after specified delay. libata core takes care of synchronization against EH. This is generalized form of pio_task and packet_task which are tied to PIO hsm implementation. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 66dce58f1941..3ad2570f663b 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -388,6 +388,8 @@ struct ata_port { struct ata_host_stats stats; struct ata_host_set *host_set; + struct work_struct port_task; + struct work_struct packet_task; struct work_struct pio_task; @@ -515,6 +517,8 @@ extern int ata_ratelimit(void); extern unsigned int ata_busy_sleep(struct ata_port *ap, unsigned long timeout_pat, unsigned long timeout); +extern void ata_port_queue_task(struct ata_port *ap, void (*fn)(void *), + void *data, unsigned long delay); /* * Default driver ops implementations -- cgit v1.2.3 From 507ceda00302c071029277652d9faa5a0a55419a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 5 Mar 2006 15:29:09 +0900 Subject: [PATCH] libata: kill unused pio_task and packet_task Kill unused pio_task and packet_task. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 3ad2570f663b..9ad020ac8591 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -390,9 +390,6 @@ struct ata_port { struct work_struct port_task; - struct work_struct packet_task; - - struct work_struct pio_task; unsigned int hsm_task_state; unsigned long pio_task_timeout; -- cgit v1.2.3 From 2e755f68ee23b03484fde18d978f910cc5479cb8 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 5 Mar 2006 15:29:09 +0900 Subject: [PATCH] libata: rename ATA_FLAG_FLUSH_PIO_TASK to ATA_FLAG_FLUSH_PORT_TASK Rename ATA_FLAG_FLUSH_PIO_TASK to ATA_FLAG_FLUSH_PORT_TASK. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- 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 9ad020ac8591..15674923cc84 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -151,7 +151,7 @@ enum { ATA_FLAG_PIO_LBA48 = (1 << 13), /* Host DMA engine is LBA28 only */ ATA_FLAG_IRQ_MASK = (1 << 14), /* Mask IRQ in PIO xfers */ - ATA_FLAG_FLUSH_PIO_TASK = (1 << 15), /* Flush PIO task */ + ATA_FLAG_FLUSH_PORT_TASK = (1 << 15), /* Flush port task */ ATA_FLAG_IN_EH = (1 << 16), /* EH in progress */ ATA_QCFLAG_ACTIVE = (1 << 1), /* cmd not yet ack'd to scsi lyer */ -- cgit v1.2.3 From 1da7b0d01b20bf21f3263d8d2f17fa49a214d773 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 6 Mar 2006 04:31:56 +0900 Subject: [PATCH] libata: improve xfer mask constants and update ata_mode_string() Add ATA_BITS_*, ATA_MASK_* macros and reorder xfer_mask fields such that higher transfer mode is placed at higher order bit. As thie reordering breaks ata_mode_string(), this patch also rewrites ata_mode_string(). Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 15674923cc84..239408ecfddf 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -188,11 +188,19 @@ enum { PORT_DISABLED = 2, /* encoding various smaller bitmaps into a single - * unsigned long bitmap + * unsigned int bitmap */ - ATA_SHIFT_UDMA = 0, - ATA_SHIFT_MWDMA = 8, - ATA_SHIFT_PIO = 11, + ATA_BITS_PIO = 5, + ATA_BITS_MWDMA = 3, + ATA_BITS_UDMA = 8, + + ATA_SHIFT_PIO = 0, + ATA_SHIFT_MWDMA = ATA_SHIFT_PIO + ATA_BITS_PIO, + ATA_SHIFT_UDMA = ATA_SHIFT_MWDMA + ATA_BITS_MWDMA, + + ATA_MASK_PIO = ((1 << ATA_BITS_PIO) - 1) << ATA_SHIFT_PIO, + ATA_MASK_MWDMA = ((1 << ATA_BITS_MWDMA) - 1) << ATA_SHIFT_MWDMA, + ATA_MASK_UDMA = ((1 << ATA_BITS_UDMA) - 1) << ATA_SHIFT_UDMA, /* size of buffer to pad xfers ending on unaligned boundaries */ ATA_DMA_PAD_SZ = 4, -- cgit v1.2.3 From 044cc6c8ec311c4ddeebfcc31c53dea282de70b7 Mon Sep 17 00:00:00 2001 From: "andrew.vasquez@qlogic.com" Date: Thu, 9 Mar 2006 14:27:13 -0800 Subject: [SCSI] qla2xxx: Add ISP54xx support. Chip is similar in form to our ISP24xx offering. Signed-off-by: Andrew Vasquez 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 82b83da25d77..1afac931351e 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -852,6 +852,8 @@ #define PCI_DEVICE_ID_QLOGIC_ISP2432 0x2432 #define PCI_DEVICE_ID_QLOGIC_ISP2512 0x2512 #define PCI_DEVICE_ID_QLOGIC_ISP2522 0x2522 +#define PCI_DEVICE_ID_QLOGIC_ISP5422 0x5422 +#define PCI_DEVICE_ID_QLOGIC_ISP5432 0x5432 #define PCI_VENDOR_ID_CYRIX 0x1078 #define PCI_DEVICE_ID_CYRIX_5510 0x0000 -- cgit v1.2.3 From e935d5da8e5d12fabe5b632736c50eae0427e8c8 Mon Sep 17 00:00:00 2001 From: "Moore, Eric" Date: Tue, 14 Mar 2006 09:18:18 -0700 Subject: [SCSI] drivers/base/bus.c - export reprobe Adding support for exposing hidden raid components for sg interface. The sdev->no_uld_attach flag will set set accordingly. The sas module supports adding/removing raid volumes using online storage management application interface. This patch was provided to me by Christoph Hellwig. Signed-off-by: Eric Moore Signed-off-by: Greg Kroah-Hartman Signed-off-by: James Bottomley --- include/linux/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 58df18d9cd3e..e8ac5bcfbec7 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -378,6 +378,7 @@ extern void device_bind_driver(struct device * dev); extern void device_release_driver(struct device * dev); extern int device_attach(struct device * dev); extern void driver_attach(struct device_driver * drv); +extern void device_reprobe(struct device *dev); /* -- cgit v1.2.3 From 243f196d572822214bb86522f28b30e096d67414 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Thu, 16 Mar 2006 14:10:19 +0000 Subject: [ARM] 3366/1: Allow the 16bpp mode configuration in the CLCD control register Patch from Catalin Marinas Starting with PL111, the 5551 or 565 modes can be configured in the primecell's control register directly. This patch detects the required mode and sets the correct value. Signed-off-by: Catalin Marinas Signed-off-by: Russell King --- include/linux/amba/clcd.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/amba/clcd.h b/include/linux/amba/clcd.h index 6b8d73dc1ab0..9cf64b1b688b 100644 --- a/include/linux/amba/clcd.h +++ b/include/linux/amba/clcd.h @@ -54,6 +54,7 @@ #define CNTL_LCDBPP4 (2 << 1) #define CNTL_LCDBPP8 (3 << 1) #define CNTL_LCDBPP16 (4 << 1) +#define CNTL_LCDBPP16_565 (6 << 1) #define CNTL_LCDBPP24 (5 << 1) #define CNTL_LCDBW (1 << 4) #define CNTL_LCDTFT (1 << 5) @@ -209,7 +210,16 @@ static inline void clcdfb_decode(struct clcd_fb *fb, struct clcd_regs *regs) val |= CNTL_LCDBPP8; break; case 16: - val |= CNTL_LCDBPP16; + /* + * PL110 cannot choose between 5551 and 565 modes in + * its control register + */ + if ((fb->dev->periphid & 0x000fffff) == 0x00041110) + val |= CNTL_LCDBPP16; + else if (fb->fb.var.green.length == 5) + val |= CNTL_LCDBPP16; + else + val |= CNTL_LCDBPP16_565; break; case 32: val |= CNTL_LCDBPP24; -- cgit v1.2.3 From 12a057321529df2fb650ac5f34dfd7abcca667df Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 18 Mar 2006 13:38:01 -0500 Subject: [PATCH] keep sync and async cfq_queue separate Signed-off-by: Al Viro --- 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 860e7a485a5f..e19cb631084e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -58,7 +58,7 @@ struct cfq_io_context { * circular list of cfq_io_contexts belonging to a process io context */ struct list_head list; - struct cfq_queue *cfqq; + struct cfq_queue *cfqq[2]; void *key; struct io_context *ioc; -- cgit v1.2.3 From d9ff41879364cfca7c15abc20ae398e35de3f883 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 18 Mar 2006 13:51:22 -0500 Subject: [PATCH] make cfq_exit_queue() prune the cfq_io_context for that queue Signed-off-by: Al Viro --- include/linux/blkdev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e19cb631084e..80518f703538 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -69,6 +69,8 @@ struct cfq_io_context { unsigned long ttime_samples; unsigned long ttime_mean; + struct list_head queue_list; + void (*dtor)(struct cfq_io_context *); void (*exit)(struct cfq_io_context *); }; -- cgit v1.2.3 From e17a9489b4a686bb5e9615e1d375c67619cb99c5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 18 Mar 2006 13:21:20 -0500 Subject: [PATCH] stop elv_unregister() from rogering other iosched's data, fix locking Signed-off-by: Al Viro --- include/linux/elevator.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 18cf1f3e1184..f65766ef0532 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -48,6 +48,7 @@ struct elevator_ops elevator_init_fn *elevator_init_fn; elevator_exit_fn *elevator_exit_fn; + void (*trim)(struct io_context *); }; #define ELV_NAME_MAX (16) -- cgit v1.2.3 From 483f4afc421435b7cfe5e88f74eea0b73a476d75 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 18 Mar 2006 18:34:37 -0500 Subject: [PATCH] fix sysfs interaction and lifetime rules handling for queues --- include/linux/blkdev.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 80518f703538..56bb6a4e15f3 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -406,8 +406,6 @@ struct request_queue struct blk_queue_tag *queue_tags; - atomic_t refcnt; - unsigned int nr_sorted; unsigned int in_flight; @@ -426,6 +424,8 @@ struct request_queue struct request pre_flush_rq, bar_rq, post_flush_rq; struct request *orig_bar_rq; unsigned int bi_size; + + struct mutex sysfs_lock; }; #define RQ_INACTIVE (-1) @@ -727,7 +727,7 @@ extern long nr_blockdev_pages(void); int blk_get_queue(request_queue_t *); 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)) +extern void blk_put_queue(request_queue_t *); /* * tag stuff -- cgit v1.2.3 From 3d1ab40f4c20767afbd361b258a531d73e3e6fc2 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 18 Mar 2006 18:35:43 -0500 Subject: [PATCH] elevator_t lifetime rules and sysfs fixes --- include/linux/elevator.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index f65766ef0532..4d0a80f13ee0 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -61,7 +61,7 @@ struct elevator_type struct list_head list; struct elevator_ops ops; struct elevator_type *elevator_type; - struct kobj_type *elevator_ktype; + struct attribute **elevator_attrs; char elevator_name[ELV_NAME_MAX]; struct module *elevator_owner; }; @@ -75,6 +75,7 @@ struct elevator_queue void *elevator_data; struct kobject kobj; struct elevator_type *elevator_type; + struct mutex sysfs_lock; }; /* @@ -141,6 +142,12 @@ enum { ELV_MQUEUE_MUST, }; +struct elv_fs_entry { + struct attribute attr; + ssize_t (*show)(elevator_t *, char *); + ssize_t (*store)(elevator_t *, const char *, size_t); +}; + #define rq_end_sector(rq) ((rq)->sector + (rq)->nr_sectors) #endif -- cgit v1.2.3 From e572ec7e4e432de7ecf7bd2e62117646fa64e518 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 18 Mar 2006 22:27:18 -0500 Subject: [PATCH] fix rmmod problems with elevator attributes, clean them up --- include/linux/elevator.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 4d0a80f13ee0..ad133fcfb239 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -53,6 +53,12 @@ struct elevator_ops #define ELV_NAME_MAX (16) +struct elv_fs_entry { + struct attribute attr; + ssize_t (*show)(elevator_t *, char *); + ssize_t (*store)(elevator_t *, const char *, size_t); +}; + /* * identifies an elevator type, such as AS or deadline */ @@ -61,7 +67,7 @@ struct elevator_type struct list_head list; struct elevator_ops ops; struct elevator_type *elevator_type; - struct attribute **elevator_attrs; + struct elv_fs_entry *elevator_attrs; char elevator_name[ELV_NAME_MAX]; struct module *elevator_owner; }; @@ -142,12 +148,6 @@ enum { ELV_MQUEUE_MUST, }; -struct elv_fs_entry { - struct attribute attr; - ssize_t (*show)(elevator_t *, char *); - ssize_t (*store)(elevator_t *, const char *, size_t); -}; - #define rq_end_sector(rq) ((rq)->sector + (rq)->nr_sectors) #endif -- cgit v1.2.3 From 4a29cc2e503b33a1e96db4c3f9a94165f153f259 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Sun, 19 Mar 2006 13:21:12 -0800 Subject: [TG3]: 40-bit DMA workaround part 2 The 40-bit DMA workaround recently implemented for 5714, 5715, and 5780 needs to be expanded because there may be other tg3 devices behind the EPB Express to PCIX bridge in the 5780 class device. For example, some 4-port card or mother board designs have 5704 behind the 5714. All devices behind the EPB require the 40-bit DMA workaround. Thanks to Chris Elmquist again for reporting the problem and testing the patch. Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- 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 1709b5009d2e..751eea58bde8 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1365,6 +1365,7 @@ #define PCI_DEVICE_ID_SERVERWORKS_HE 0x0008 #define PCI_DEVICE_ID_SERVERWORKS_LE 0x0009 #define PCI_DEVICE_ID_SERVERWORKS_GCNB_LE 0x0017 +#define PCI_DEVICE_ID_SERVERWORKS_EPB 0x0103 #define PCI_DEVICE_ID_SERVERWORKS_OSB4 0x0200 #define PCI_DEVICE_ID_SERVERWORKS_CSB5 0x0201 #define PCI_DEVICE_ID_SERVERWORKS_CSB6 0x0203 -- cgit v1.2.3 From 02fd473bd4844befc74f7ca67cd60891e0a2d890 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sat, 11 Feb 2006 02:25:21 -0800 Subject: [SPARC64]: Add SUN4V Hypervisor Console driver. Since it can do things like BREAK and HUP, we implement this as a serial uart driver. This still needs interrupt probing code, as I haven't figured out how interrupts will work or be probed for on SUN4V yet. Signed-off-by: David S. Miller --- include/linux/serial_core.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 4041122dabfc..57abcea1cb5d 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -127,6 +127,9 @@ /* Hilscher netx */ #define PORT_NETX 71 +/* SUN4V Hypervisor Console */ +#define PORT_SUNHV 72 + #ifdef __KERNEL__ #include -- cgit v1.2.3 From d358788f3f30113e49882187d794832905e42592 Mon Sep 17 00:00:00 2001 From: Russell King Date: Mon, 20 Mar 2006 20:00:09 +0000 Subject: [SERIAL] kernel console should send CRLF not LFCR Glen Turner reported that writing LFCR rather than the more traditional CRLF causes issues with some terminals. Since this aflicts many serial drivers, extract the common code to a library function (uart_console_write) and arrange for each driver to supply a "putchar" function. Signed-off-by: Russell King --- include/linux/serial_core.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 4041122dabfc..f7434e5086f5 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -366,6 +366,9 @@ void uart_parse_options(char *options, int *baud, int *parity, int *bits, int uart_set_options(struct uart_port *port, struct console *co, int baud, int parity, int bits, int flow); struct tty_driver *uart_console_device(struct console *co, int *index); +void uart_console_write(struct uart_port *port, const char *s, + unsigned int count, + void (*putchar)(struct uart_port *, int)); /* * Port/driver registration/removal -- cgit v1.2.3 From 58383af629efb07e5a0694e445eda0c65b16e1de Mon Sep 17 00:00:00 2001 From: Jes Sorensen Date: Mon, 6 Feb 2006 14:12:43 -0800 Subject: [PATCH] kobj_map semaphore to mutex conversion Convert the kobj_map code to use a mutex instead of a semaphore. It converts the single two users as well, genhd.c and char_dev.c. Signed-off-by: Jes Sorensen Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- include/linux/kobj_map.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kobj_map.h b/include/linux/kobj_map.h index cbe7d8008042..bafe178a381f 100644 --- a/include/linux/kobj_map.h +++ b/include/linux/kobj_map.h @@ -1,6 +1,6 @@ #ifdef __KERNEL__ -#include +#include typedef struct kobject *kobj_probe_t(dev_t, int *, void *); struct kobj_map; @@ -9,6 +9,6 @@ int kobj_map(struct kobj_map *, dev_t, unsigned long, struct module *, kobj_probe_t *, int (*)(dev_t, void *), void *); void kobj_unmap(struct kobj_map *, dev_t, unsigned long); struct kobject *kobj_lookup(struct kobj_map *, dev_t, int *); -struct kobj_map *kobj_map_init(kobj_probe_t *, struct semaphore *); +struct kobj_map *kobj_map_init(kobj_probe_t *, struct mutex *); #endif -- cgit v1.2.3 From 9f28bb7e1d0188a993403ab39b774785892805e1 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 20 Mar 2006 13:17:13 -0800 Subject: [PATCH] add EXPORT_SYMBOL_GPL_FUTURE() This patch adds the ability to mark symbols that will be changed in the future, so that kernel modules that don't include MODULE_LICENSE("GPL") and use the symbols, will be flagged and printed out to the system log. Signed-off-by: Greg Kroah-Hartman --- include/linux/module.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 84d75f3a8aca..a25d5f61548c 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -198,6 +198,9 @@ void *__symbol_get_gpl(const char *symbol); #define EXPORT_SYMBOL_GPL(sym) \ __EXPORT_SYMBOL(sym, "_gpl") +#define EXPORT_SYMBOL_GPL_FUTURE(sym) \ + __EXPORT_SYMBOL(sym, "_gpl_future") + #endif struct module_ref @@ -255,6 +258,11 @@ struct module unsigned int num_gpl_syms; const unsigned long *gpl_crcs; + /* symbols that will be GPL-only in the near future. */ + const struct kernel_symbol *gpl_future_syms; + unsigned int num_gpl_future_syms; + const unsigned long *gpl_future_crcs; + /* Exception table */ unsigned int num_exentries; const struct exception_table_entry *extable; @@ -441,6 +449,7 @@ void module_remove_driver(struct device_driver *); #else /* !CONFIG_MODULES... */ #define EXPORT_SYMBOL(sym) #define EXPORT_SYMBOL_GPL(sym) +#define EXPORT_SYMBOL_GPL_FUTURE(sym) /* Given an address, look for it in the exception tables. */ static inline const struct exception_table_entry * -- cgit v1.2.3 From 03e88ae1b13dfdc8bbaa59b8198e1ca53aad12ac Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 16 Feb 2006 13:50:23 -0800 Subject: [PATCH] fix module sysfs files reference counting The module files, refcnt, version, and srcversion did not properly increment the owner's module reference count, allowing the modules to be removed while the files were open, causing oopses. This patch fixes this, and also fixes the problem that the version and srcversion files were not showing up, unless CONFIG_MODULE_UNLOAD was enabled, which is not correct. Cc: Nathan Lynch Signed-off-by: Greg Kroah-Hartman --- include/linux/module.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index a25d5f61548c..70bd843c71cb 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -245,6 +245,7 @@ struct module /* Sysfs stuff. */ struct module_kobject mkobj; struct module_param_attrs *param_attrs; + struct module_attribute *modinfo_attrs; const char *version; const char *srcversion; -- cgit v1.2.3 From 4f2928d0a439553f0288d9483faf417430629635 Mon Sep 17 00:00:00 2001 From: Tilman Schmidt Date: Fri, 24 Feb 2006 11:05:45 +0100 Subject: [PATCH] Driver core: add macros notice(), dev_notice() Both usb.h and device.h have collections of convenience macros for printk() with the KERN_ERR, KERN_WARNING, and KERN_NOTICE severity levels. This patch adds macros for the KERN_NOTICE level which was so far uncatered for. These macros already exist privately in drivers/isdn/gigaset/gigaset.h (currently in the process of being submitted for the kernel tree) but they really belong with their brothers and sisters in include/linux/{device,usb}.h. Signed-off-by: Tilman Schmidt Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 58df18d9cd3e..5b595fdfb672 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -424,6 +424,8 @@ extern void firmware_unregister(struct subsystem *); dev_printk(KERN_INFO , dev , format , ## arg) #define dev_warn(dev, format, arg...) \ dev_printk(KERN_WARNING , dev , format , ## arg) +#define dev_notice(dev, format, arg...) \ + dev_printk(KERN_NOTICE , dev , format , ## arg) /* Create alias, so I can be autoloaded. */ #define MODULE_ALIAS_CHARDEV(major,minor) \ -- cgit v1.2.3 From 22f98c0cd7e003b896ee52ded945081307118745 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Sat, 4 Mar 2006 13:15:31 +0100 Subject: [PATCH] Kobject: kobject.h: fix a typo It shouldn't cause real harm, but it hurts my eyes. Signed-off-by: Adrian Bunk Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index c374b5fa8d3b..7ece63f8abbd 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -255,7 +255,7 @@ struct subsys_attribute { extern int subsys_create_file(struct subsystem * , struct subsys_attribute *); extern void subsys_remove_file(struct subsystem * , struct subsys_attribute *); -#if defined(CONFIG_HOTPLUG) & defined(CONFIG_NET) +#if defined(CONFIG_HOTPLUG) && defined(CONFIG_NET) void kobject_uevent(struct kobject *kobj, enum kobject_action action); int add_uevent_var(char **envp, int num_envp, int *cur_index, -- cgit v1.2.3 From dd308bc355a1aa4f202fe9a3133b6c676cb9606c Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Tue, 7 Mar 2006 21:41:59 +1100 Subject: [PATCH] debugfs: Add debugfs_create_blob() helper for exporting binary data I wanted to export a binary blob via debugfs, and although it was pretty easy it seems like it'd be easier if there was a helper for it. It's a pity we need the wrapper struct but I can't see a cleaner way to do it. Signed-off-by: Michael Ellerman Signed-off-by: Greg Kroah-Hartman --- include/linux/debugfs.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index a5fa6a6eede8..4b0428e335be 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -21,6 +21,11 @@ struct file_operations; +struct debugfs_blob_wrapper { + void *data; + unsigned long size; +}; + #if defined(CONFIG_DEBUG_FS) struct dentry *debugfs_create_file(const char *name, mode_t mode, struct dentry *parent, void *data, @@ -39,6 +44,9 @@ struct dentry *debugfs_create_u32(const char *name, mode_t mode, struct dentry *debugfs_create_bool(const char *name, mode_t mode, struct dentry *parent, u32 *value); +struct dentry *debugfs_create_blob(const char *name, mode_t mode, + struct dentry *parent, + struct debugfs_blob_wrapper *blob); #else #include @@ -94,6 +102,13 @@ static inline struct dentry *debugfs_create_bool(const char *name, mode_t mode, return ERR_PTR(-ENODEV); } +static inline struct dentry *debugfs_create_blob(const char *name, mode_t mode, + struct dentry *parent, + struct debugfs_blob_wrapper *blob) +{ + return ERR_PTR(-ENODEV); +} + #endif #endif -- cgit v1.2.3 From 7423172a50968de1905a61413c52bb070a62f5ce Mon Sep 17 00:00:00 2001 From: Jun'ichi Nomura Date: Mon, 13 Mar 2006 17:14:25 -0500 Subject: [PATCH] kobject_add_dir Adding kobject_add_dir() function which creates a subdirectory for a given kobject. Signed-off-by: Jun'ichi Nomura Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 7ece63f8abbd..4cb1214ec290 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -80,6 +80,8 @@ extern void kobject_unregister(struct kobject *); extern struct kobject * kobject_get(struct kobject *); extern void kobject_put(struct kobject *); +extern struct kobject *kobject_add_dir(struct kobject *, const char *); + extern char * kobject_get_path(struct kobject *, gfp_t); struct kobj_type { -- cgit v1.2.3 From a29d642a4aa99c5234314ab2523281139226c231 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 7 Mar 2006 23:53:25 -0800 Subject: [PATCH] get_cpu_sysdev() signedness fix Doing (int < NR_CPUS) doesn't dtrt if it's negative.. Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- include/linux/cpu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 0ed1d4853c69..d612b89dce33 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -32,7 +32,7 @@ struct cpu { }; extern int register_cpu(struct cpu *, int, struct node *); -extern struct sys_device *get_cpu_sysdev(int cpu); +extern struct sys_device *get_cpu_sysdev(unsigned cpu); #ifdef CONFIG_HOTPLUG_CPU extern void unregister_cpu(struct cpu *, struct node *); #endif -- cgit v1.2.3 From e266a12492f7ca9142882710bff92e902b7c95c8 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Tue, 8 Nov 2005 21:05:43 +0100 Subject: [PATCH] USB: drivers/usb/core/message.c: make usb_get_string() static After the removal of usb-midi.c, there's no longer any external user of usb_get_string(). Signed-off-by: Adrian Bunk Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 827cc6de5f5c..130d125fda12 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1018,8 +1018,6 @@ extern int usb_get_descriptor(struct usb_device *dev, unsigned char desctype, unsigned char descindex, void *buf, int size); extern int usb_get_status(struct usb_device *dev, int type, int target, void *data); -extern int usb_get_string(struct usb_device *dev, - unsigned short langid, unsigned char index, void *buf, int size); extern int usb_string(struct usb_device *dev, int index, char *buf, size_t size); -- cgit v1.2.3 From 80cb9aee01245b38325dd84f1359b14a3f01f10d Mon Sep 17 00:00:00 2001 From: Randy Vinson Date: Fri, 20 Jan 2006 13:53:38 -0800 Subject: [PATCH] USB: EHCI for Freescale 83xx Adding a Host Mode USB driver for the Freescale 83xx. This driver supports both the Dual-Role (DR) controller and the Multi-Port-Host (MPH) controller present in the Freescale MPC8349. It has been tested with the MPC8349CDS reference system. This driver depends on platform support code for setting up the pins on the device package in a manner appropriate for the board in use. Note that this patch requires selecting the EHCI controller option under the USB Host menu. Signed-off-by: Randy Vinson Signed-off-by: Greg Kroah-Hartman --- include/linux/fsl_devices.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsl_devices.h b/include/linux/fsl_devices.h index a9f1cfd096ff..a3a0e078f79d 100644 --- a/include/linux/fsl_devices.h +++ b/include/linux/fsl_devices.h @@ -83,5 +83,32 @@ struct fsl_i2c_platform_data { #define FSL_I2C_DEV_SEPARATE_DFSRR 0x00000001 #define FSL_I2C_DEV_CLOCK_5200 0x00000002 + +enum fsl_usb2_operating_modes { + FSL_USB2_MPH_HOST, + FSL_USB2_DR_HOST, + FSL_USB2_DR_DEVICE, + FSL_USB2_DR_OTG, +}; + +enum fsl_usb2_phy_modes { + FSL_USB2_PHY_NONE, + FSL_USB2_PHY_ULPI, + FSL_USB2_PHY_UTMI, + FSL_USB2_PHY_UTMI_WIDE, + FSL_USB2_PHY_SERIAL, +}; + +struct fsl_usb2_platform_data { + /* board specific information */ + enum fsl_usb2_operating_modes operating_mode; + enum fsl_usb2_phy_modes phy_mode; + unsigned int port_enables; +}; + +/* Flags in fsl_usb2_mph_platform_data */ +#define FSL_USB2_PORT0_ENABLED 0x00000001 +#define FSL_USB2_PORT1_ENABLED 0x00000002 + #endif /* _FSL_DEVICE_H_ */ #endif /* __KERNEL__ */ -- cgit v1.2.3 From 329af28b141ab4ae847aff1362864c4cc332641f Mon Sep 17 00:00:00 2001 From: David Brownell Date: Sat, 18 Feb 2006 12:31:05 -0800 Subject: [PATCH] USB: gadget driver section fixups This adds __init section annotations to gadget driver bind() routines to remove calls from .text into .init sections (for endpoint autoconfig). Likewise it adds __exit section annotations to their unbind() routines. The specification of the gadget driver register/unregister functions is updated to explicitly allow use of those sections. Signed-off-by: David Brownell Signed-off-by: Greg Kroah-Hartman --- include/linux/usb_gadget.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb_gadget.h b/include/linux/usb_gadget.h index ff81117eb733..1d78870ed8af 100644 --- a/include/linux/usb_gadget.h +++ b/include/linux/usb_gadget.h @@ -801,7 +801,9 @@ struct usb_gadget_driver { * Call this in your gadget driver's module initialization function, * to tell the underlying usb controller driver about your driver. * The driver's bind() function will be called to bind it to a - * gadget. This function must be called in a context that can sleep. + * gadget before this registration call returns. It's expected that + * the bind() functions will be in init sections. + * This function must be called in a context that can sleep. */ int usb_gadget_register_driver (struct usb_gadget_driver *driver); @@ -814,7 +816,8 @@ int usb_gadget_register_driver (struct usb_gadget_driver *driver); * going away. If the controller is connected to a USB host, * it will first disconnect(). The driver is also requested * to unbind() and clean up any device state, before this procedure - * finally returns. + * finally returns. It's expected that the unbind() functions + * will in in exit sections, so may not be linked in some kernels. * This function must be called in a context that can sleep. */ int usb_gadget_unregister_driver (struct usb_gadget_driver *driver); -- cgit v1.2.3 From 65f5c7c1143fb8eed5bc7e7d8c926346e00fe3c0 Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Mon, 20 Mar 2006 16:55:08 -0800 Subject: [IPV6]: ROUTE: Add accept_ra_defrtr sysctl. This controls whether we accept default router information in RAs. Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/linux/ipv6.h | 2 ++ include/linux/sysctl.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 9c8f4c9ed429..c5131a02869a 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -145,6 +145,7 @@ struct ipv6_devconf { __s32 max_desync_factor; #endif __s32 max_addresses; + __s32 accept_ra_defrtr; void *sysctl; }; @@ -167,6 +168,7 @@ enum { DEVCONF_MAX_DESYNC_FACTOR, DEVCONF_MAX_ADDRESSES, DEVCONF_FORCE_MLD_VERSION, + DEVCONF_ACCEPT_RA_DEFRTR, DEVCONF_MAX }; diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index bac61db26456..0f494137d037 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -531,6 +531,7 @@ enum { NET_IPV6_MAX_DESYNC_FACTOR=15, NET_IPV6_MAX_ADDRESSES=16, NET_IPV6_FORCE_MLD_VERSION=17, + NET_IPV6_ACCEPT_RA_DEFRTR=18, __NET_IPV6_MAX }; -- cgit v1.2.3 From c4fd30eb18666972230689eb30e8f90844bce635 Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Mon, 20 Mar 2006 16:55:26 -0800 Subject: [IPV6]: ADDRCONF: Add accept_ra_pinfo sysctl. This controls whether we accept Prefix Information in RAs. Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/linux/ipv6.h | 2 ++ include/linux/sysctl.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index c5131a02869a..2c3b799480c5 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -146,6 +146,7 @@ struct ipv6_devconf { #endif __s32 max_addresses; __s32 accept_ra_defrtr; + __s32 accept_ra_pinfo; void *sysctl; }; @@ -169,6 +170,7 @@ enum { DEVCONF_MAX_ADDRESSES, DEVCONF_FORCE_MLD_VERSION, DEVCONF_ACCEPT_RA_DEFRTR, + DEVCONF_ACCEPT_RA_PINFO, DEVCONF_MAX }; diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 0f494137d037..09378ea505bd 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -532,6 +532,7 @@ enum { NET_IPV6_MAX_ADDRESSES=16, NET_IPV6_FORCE_MLD_VERSION=17, NET_IPV6_ACCEPT_RA_DEFRTR=18, + NET_IPV6_ACCEPT_RA_PINFO=19, __NET_IPV6_MAX }; -- cgit v1.2.3 From ebacaaa0fdf4402cdf4c8e569f54af36b6f0aa2d Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Mon, 20 Mar 2006 17:04:53 -0800 Subject: [IPV6]: ROUTE: Add support for Router Preference (RFC4191). Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/linux/icmpv6.h | 11 +++++++++-- include/linux/ipv6_route.h | 8 ++++++++ 2 files changed, 17 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index 0cf6c8b12caf..c771a7db9871 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -40,14 +40,16 @@ struct icmp6hdr { struct icmpv6_nd_ra { __u8 hop_limit; #if defined(__LITTLE_ENDIAN_BITFIELD) - __u8 reserved:6, + __u8 reserved:4, + router_pref:2, other:1, managed:1; #elif defined(__BIG_ENDIAN_BITFIELD) __u8 managed:1, other:1, - reserved:6; + router_pref:2, + reserved:4; #else #error "Please fix " #endif @@ -70,8 +72,13 @@ struct icmp6hdr { #define icmp6_addrconf_managed icmp6_dataun.u_nd_ra.managed #define icmp6_addrconf_other icmp6_dataun.u_nd_ra.other #define icmp6_rt_lifetime icmp6_dataun.u_nd_ra.rt_lifetime +#define icmp6_router_pref icmp6_dataun.u_nd_ra.router_pref }; +#define ICMPV6_ROUTER_PREF_LOW 0x3 +#define ICMPV6_ROUTER_PREF_MEDIUM 0x0 +#define ICMPV6_ROUTER_PREF_HIGH 0x1 +#define ICMPV6_ROUTER_PREF_INVALID 0x2 #define ICMPV6_DEST_UNREACH 1 #define ICMPV6_PKT_TOOBIG 2 diff --git a/include/linux/ipv6_route.h b/include/linux/ipv6_route.h index d7c41d1d706a..f4b085c91608 100644 --- a/include/linux/ipv6_route.h +++ b/include/linux/ipv6_route.h @@ -27,8 +27,16 @@ #define RTF_FLOW 0x02000000 /* flow significant route */ #define RTF_POLICY 0x04000000 /* policy route */ +#define RTF_PREF(pref) ((pref) << 27) +#define RTF_PREF_MASK 0x18000000 + #define RTF_LOCAL 0x80000000 +#ifdef __KERNEL__ +#define IPV6_EXTRACT_PREF(flag) (((flag) & RTF_PREF_MASK) >> 27) +#define IPV6_DECODE_PREF(pref) ((pref) ^ 2) /* 1:low,2:med,3:high */ +#endif + struct in6_rtmsg { struct in6_addr rtmsg_dst; struct in6_addr rtmsg_src; -- cgit v1.2.3 From 930d6ff2e2a5f1538448d3b0b2652a8f0c0f6cba Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Mon, 20 Mar 2006 17:05:30 -0800 Subject: [IPV6]: ROUTE: Add accept_ra_rtr_pref sysctl. Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/linux/ipv6.h | 4 ++++ include/linux/sysctl.h | 1 + 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 2c3b799480c5..108b75dccd9f 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -147,6 +147,9 @@ struct ipv6_devconf { __s32 max_addresses; __s32 accept_ra_defrtr; __s32 accept_ra_pinfo; +#ifdef CONFIG_IPV6_ROUTER_PREF + __s32 accept_ra_rtr_pref; +#endif void *sysctl; }; @@ -171,6 +174,7 @@ enum { DEVCONF_FORCE_MLD_VERSION, DEVCONF_ACCEPT_RA_DEFRTR, DEVCONF_ACCEPT_RA_PINFO, + DEVCONF_ACCEPT_RA_RTR_PREF, DEVCONF_MAX }; diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 09378ea505bd..236f537b38d2 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -533,6 +533,7 @@ enum { NET_IPV6_FORCE_MLD_VERSION=17, NET_IPV6_ACCEPT_RA_DEFRTR=18, NET_IPV6_ACCEPT_RA_PINFO=19, + NET_IPV6_ACCEPT_RA_RTR_PREF=20, __NET_IPV6_MAX }; -- cgit v1.2.3 From 52e1635631b342803aecaf81a362c1464e3da2e5 Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Mon, 20 Mar 2006 17:05:47 -0800 Subject: [IPV6]: ROUTE: Add router_probe_interval sysctl. Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/linux/ipv6.h | 2 ++ include/linux/sysctl.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 108b75dccd9f..c609cc702375 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -149,6 +149,7 @@ struct ipv6_devconf { __s32 accept_ra_pinfo; #ifdef CONFIG_IPV6_ROUTER_PREF __s32 accept_ra_rtr_pref; + __s32 rtr_probe_interval; #endif void *sysctl; }; @@ -175,6 +176,7 @@ enum { DEVCONF_ACCEPT_RA_DEFRTR, DEVCONF_ACCEPT_RA_PINFO, DEVCONF_ACCEPT_RA_RTR_PREF, + DEVCONF_RTR_PROBE_INTERVAL, DEVCONF_MAX }; diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 236f537b38d2..f49488ffefef 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -534,6 +534,7 @@ enum { NET_IPV6_ACCEPT_RA_DEFRTR=18, NET_IPV6_ACCEPT_RA_PINFO=19, NET_IPV6_ACCEPT_RA_RTR_PREF=20, + NET_IPV6_RTR_PROBE_INTERVAL=21, __NET_IPV6_MAX }; -- cgit v1.2.3 From 70ceb4f53929f73746be72f73707cd9f8753e2fc Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Mon, 20 Mar 2006 17:06:24 -0800 Subject: [IPV6]: ROUTE: Add experimental support for Route Information Option in RA (RFC4191). Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/linux/ipv6_route.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ipv6_route.h b/include/linux/ipv6_route.h index f4b085c91608..b323ff577967 100644 --- a/include/linux/ipv6_route.h +++ b/include/linux/ipv6_route.h @@ -23,6 +23,8 @@ #define RTF_NONEXTHOP 0x00200000 /* route with no nexthop */ #define RTF_EXPIRES 0x00400000 +#define RTF_ROUTEINFO 0x00800000 /* route information - RA */ + #define RTF_CACHE 0x01000000 /* cache entry */ #define RTF_FLOW 0x02000000 /* flow significant route */ #define RTF_POLICY 0x04000000 /* policy route */ -- cgit v1.2.3 From 09c884d4c3b45cda904c2291d4723074ff523611 Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Mon, 20 Mar 2006 17:07:03 -0800 Subject: [IPV6]: ROUTE: Add accept_ra_rt_info_max_plen sysctl. Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/linux/ipv6.h | 4 ++++ include/linux/sysctl.h | 1 + 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index c609cc702375..1263d8cb3c18 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -150,6 +150,9 @@ struct ipv6_devconf { #ifdef CONFIG_IPV6_ROUTER_PREF __s32 accept_ra_rtr_pref; __s32 rtr_probe_interval; +#ifdef CONFIG_IPV6_ROUTE_INFO + __s32 accept_ra_rt_info_max_plen; +#endif #endif void *sysctl; }; @@ -177,6 +180,7 @@ enum { DEVCONF_ACCEPT_RA_PINFO, DEVCONF_ACCEPT_RA_RTR_PREF, DEVCONF_RTR_PROBE_INTERVAL, + DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN, DEVCONF_MAX }; diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index f49488ffefef..8ad4beab2888 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -535,6 +535,7 @@ enum { NET_IPV6_ACCEPT_RA_PINFO=19, NET_IPV6_ACCEPT_RA_RTR_PREF=20, NET_IPV6_RTR_PROBE_INTERVAL=21, + NET_IPV6_ACCEPT_RA_RT_INFO_MAX_PLEN=22, __NET_IPV6_MAX }; -- cgit v1.2.3 From b00055aacdb172c05067612278ba27265fcd05ce Mon Sep 17 00:00:00 2001 From: Stefan Rompf Date: Mon, 20 Mar 2006 17:09:11 -0800 Subject: [NET] core: add RFC2863 operstate this patch adds a dormant flag to network devices, RFC2863 operstate derived from these flags and possibility for userspace interaction. It allows drivers to signal that a device is unusable for user traffic without disabling queueing (and therefore the possibility for protocol establishment traffic to flow) and a userspace supplicant (WPA, 802.1X) to mark a device unusable without changes to the driver. It is the result of our long discussion. However I must admit that it represents what Jamal and I agreed on with compromises towards Krzysztof, but Thomas and Krzysztof still disagree with some parts. Anyway I think it should be applied. Signed-off-by: Stefan Rompf Signed-off-by: David S. Miller --- include/linux/if.h | 26 +++++++++++++++++++++++--- include/linux/netdevice.h | 35 +++++++++++++++++++++++++++++++++-- include/linux/rtnetlink.h | 2 ++ 3 files changed, 58 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if.h b/include/linux/if.h index 12c6f6d157c3..374e20ad8b0d 100644 --- a/include/linux/if.h +++ b/include/linux/if.h @@ -33,7 +33,7 @@ #define IFF_LOOPBACK 0x8 /* is a loopback net */ #define IFF_POINTOPOINT 0x10 /* interface is has p-p link */ #define IFF_NOTRAILERS 0x20 /* avoid use of trailers */ -#define IFF_RUNNING 0x40 /* interface running and carrier ok */ +#define IFF_RUNNING 0x40 /* interface RFC2863 OPER_UP */ #define IFF_NOARP 0x80 /* no ARP protocol */ #define IFF_PROMISC 0x100 /* receive all packets */ #define IFF_ALLMULTI 0x200 /* receive all multicast packets*/ @@ -43,12 +43,16 @@ #define IFF_MULTICAST 0x1000 /* Supports multicast */ -#define IFF_VOLATILE (IFF_LOOPBACK|IFF_POINTOPOINT|IFF_BROADCAST|IFF_MASTER|IFF_SLAVE|IFF_RUNNING) - #define IFF_PORTSEL 0x2000 /* can set media type */ #define IFF_AUTOMEDIA 0x4000 /* auto media select active */ #define IFF_DYNAMIC 0x8000 /* dialup device with changing addresses*/ +#define IFF_LOWER_UP 0x10000 /* driver signals L1 up */ +#define IFF_DORMANT 0x20000 /* driver signals dormant */ + +#define IFF_VOLATILE (IFF_LOOPBACK|IFF_POINTOPOINT|IFF_BROADCAST|\ + IFF_MASTER|IFF_SLAVE|IFF_RUNNING|IFF_LOWER_UP|IFF_DORMANT) + /* Private (from user) interface flags (netdevice->priv_flags). */ #define IFF_802_1Q_VLAN 0x1 /* 802.1Q VLAN device. */ #define IFF_EBRIDGE 0x2 /* Ethernet bridging device. */ @@ -83,6 +87,22 @@ #define IF_PROTO_FR_ETH_PVC 0x200B #define IF_PROTO_RAW 0x200C /* RAW Socket */ +/* RFC 2863 operational status */ +enum { + IF_OPER_UNKNOWN, + IF_OPER_NOTPRESENT, + IF_OPER_DOWN, + IF_OPER_LOWERLAYERDOWN, + IF_OPER_TESTING, + IF_OPER_DORMANT, + IF_OPER_UP, +}; + +/* link modes */ +enum { + IF_LINK_MODE_DEFAULT, + IF_LINK_MODE_DORMANT, /* limit upward transition to dormant */ +}; /* * Device mapping structure. I'd just gone off and designed a diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7fda03d338d1..b825be201bce 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -230,7 +230,8 @@ enum netdev_state_t __LINK_STATE_SCHED, __LINK_STATE_NOCARRIER, __LINK_STATE_RX_SCHED, - __LINK_STATE_LINKWATCH_PENDING + __LINK_STATE_LINKWATCH_PENDING, + __LINK_STATE_DORMANT, }; @@ -335,11 +336,14 @@ struct net_device */ - unsigned short flags; /* interface flags (a la BSD) */ + unsigned int flags; /* interface flags (a la BSD) */ unsigned short gflags; unsigned short priv_flags; /* Like 'flags' but invisible to userspace. */ unsigned short padded; /* How much padding added by alloc_netdev() */ + unsigned char operstate; /* RFC2863 operstate */ + unsigned char link_mode; /* mapping policy to operstate */ + unsigned mtu; /* interface MTU value */ unsigned short type; /* interface hardware type */ unsigned short hard_header_len; /* hardware hdr length */ @@ -714,6 +718,10 @@ static inline void dev_put(struct net_device *dev) /* Carrier loss detection, dial on demand. The functions netif_carrier_on * and _off may be called from IRQ context, but it is caller * who is responsible for serialization of these calls. + * + * The name carrier is inappropriate, these functions should really be + * called netif_lowerlayer_*() because they represent the state of any + * kind of lower layer not just hardware media. */ extern void linkwatch_fire_event(struct net_device *dev); @@ -729,6 +737,29 @@ extern void netif_carrier_on(struct net_device *dev); extern void netif_carrier_off(struct net_device *dev); +static inline void netif_dormant_on(struct net_device *dev) +{ + if (!test_and_set_bit(__LINK_STATE_DORMANT, &dev->state)) + linkwatch_fire_event(dev); +} + +static inline void netif_dormant_off(struct net_device *dev) +{ + if (test_and_clear_bit(__LINK_STATE_DORMANT, &dev->state)) + linkwatch_fire_event(dev); +} + +static inline int netif_dormant(const struct net_device *dev) +{ + return test_bit(__LINK_STATE_DORMANT, &dev->state); +} + + +static inline int netif_oper_up(const struct net_device *dev) { + return (dev->operstate == IF_OPER_UP || + dev->operstate == IF_OPER_UNKNOWN /* backward compat */); +} + /* Hot-plugging. */ static inline int netif_device_present(struct net_device *dev) { diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index d50482ba27fe..edccefb45188 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -733,6 +733,8 @@ enum #define IFLA_MAP IFLA_MAP IFLA_WEIGHT, #define IFLA_WEIGHT IFLA_WEIGHT + IFLA_OPERSTATE, + IFLA_LINKMODE, __IFLA_MAX }; -- cgit v1.2.3 From 77d2ca350018c507815f5d38a40ffb597eb9ae25 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 20 Mar 2006 17:12:12 -0800 Subject: [NET]: Reduce size of struct sk_buff on 64 bit architectures Move skb->nf_mark next to skb->tc_index to remove a 4 byte hole between skb->nfmark and skb->nfct and another one between skb->users and skb->head when CONFIG_NETFILTER, CONFIG_NET_SCHED and CONFIG_NET_CLS_ACT are enabled. For all other combinations the size stays the same. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ad7cc22bd424..838ce0fdcef7 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -270,7 +270,6 @@ struct sk_buff { void (*destructor)(struct sk_buff *skb); #ifdef CONFIG_NETFILTER - __u32 nfmark; struct nf_conntrack *nfct; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) struct sk_buff *nfct_reasm; @@ -278,6 +277,7 @@ struct sk_buff { #ifdef CONFIG_BRIDGE_NETFILTER struct nf_bridge_info *nf_bridge; #endif + __u32 nfmark; #endif /* CONFIG_NETFILTER */ #ifdef CONFIG_NET_SCHED __u16 tc_index; /* traffic control index */ -- cgit v1.2.3 From 5ee956125a780baf15f2c1d09f2cbf8adcf598fe Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Mon, 20 Mar 2006 17:14:12 -0800 Subject: [NETFILTER] NAT sequence adjustment: Save eight bytes per conntrack This patch reduces the size of 'struct ip_conntrack' on systems with NAT by eight bytes. The sequence number delta values can be int16_t, since we only support one sequence number modification per window anyway, and one such modification is not going to exceed 32kB ;) Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ip_nat.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_nat.h b/include/linux/netfilter_ipv4/ip_nat.h index 41a107de17cf..e9f5ed1d9f68 100644 --- a/include/linux/netfilter_ipv4/ip_nat.h +++ b/include/linux/netfilter_ipv4/ip_nat.h @@ -23,7 +23,7 @@ struct ip_nat_seq { * modification (if any) */ u_int32_t correction_pos; /* sequence number offset before and after last modification */ - int32_t offset_before, offset_after; + int16_t offset_before, offset_after; }; /* Single range specification. */ -- cgit v1.2.3 From 0af5f6c1eba4a18e6b2ed518b589927d778c6c16 Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Mon, 20 Mar 2006 17:15:11 -0800 Subject: [NETFILTER] nfnetlink_log: add sequence numbers for log events By using a sequence number for every logged netfilter event, we can determine from userspace whether logging information was lots somewhere downstream. The user has a choice of either having per-instance local sequence counters, or using a global sequence counter, or both. Signed-off-by: Harald Welte Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink_log.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_log.h b/include/linux/netfilter/nfnetlink_log.h index b04b03880595..a7497c7436df 100644 --- a/include/linux/netfilter/nfnetlink_log.h +++ b/include/linux/netfilter/nfnetlink_log.h @@ -47,6 +47,8 @@ enum nfulnl_attr_type { NFULA_PAYLOAD, /* opaque data payload */ NFULA_PREFIX, /* string prefix */ NFULA_UID, /* user id of socket */ + NFULA_SEQ, /* instance-local sequence number */ + NFULA_SEQ_GLOBAL, /* global sequence number */ __NFULA_MAX }; @@ -77,6 +79,7 @@ enum nfulnl_attr_config { NFULA_CFG_NLBUFSIZ, /* u_int32_t buffer size */ NFULA_CFG_TIMEOUT, /* u_int32_t in 1/100 s */ NFULA_CFG_QTHRESH, /* u_int32_t */ + NFULA_CFG_FLAGS, /* u_int16_t */ __NFULA_CFG_MAX }; #define NFULA_CFG_MAX (__NFULA_CFG_MAX -1) @@ -85,4 +88,7 @@ enum nfulnl_attr_config { #define NFULNL_COPY_META 0x01 #define NFULNL_COPY_PACKET 0x02 +#define NFULNL_CFG_F_SEQ 0x0001 +#define NFULNL_CFG_F_SEQ_GLOBAL 0x0002 + #endif /* _NFNETLINK_LOG_H */ -- cgit v1.2.3 From d8dcffee860d6b63996923b10f07c91d3d6c2fab Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 20 Mar 2006 17:18:05 -0800 Subject: [LIST]: Introduce list_for_each_entry_safe_from For iterate over list of given type from existing point safe against removal of list entry. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/list.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index 47208bd99f9e..beb6e48e116f 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -437,6 +437,19 @@ static inline void list_splice_init(struct list_head *list, &pos->member != (head); \ pos = n, n = list_entry(n->member.next, typeof(*n), member)) +/** + * list_for_each_entry_safe_from - iterate over list of given type + * from existing point safe against removal of list entry + * @pos: the type * to use as a loop counter. + * @n: another type * to use as temporary storage + * @head: the head for your list. + * @member: the name of the list_struct within the struct. + */ +#define list_for_each_entry_safe_from(pos, n, head, member) \ + for (n = list_entry(pos->member.next, typeof(*pos), member); \ + &pos->member != (head); \ + pos = n, n = list_entry(n->member.next, typeof(*n), member)) + /** * list_for_each_entry_safe_reverse - iterate backwards over list of given type safe against * removal of list entry -- cgit v1.2.3 From e229c2fb3370a0c4ebac06cad67ce1cb35abcfe6 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 20 Mar 2006 17:19:17 -0800 Subject: [LIST]: Introduce list_for_each_entry_from For iterating over list of given type continuing from existing point. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/list.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index beb6e48e116f..67258b47e9ca 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -410,6 +410,17 @@ static inline void list_splice_init(struct list_head *list, prefetch(pos->member.next), &pos->member != (head); \ pos = list_entry(pos->member.next, typeof(*pos), member)) +/** + * list_for_each_entry_from - iterate over list of given type + * continuing from existing point + * @pos: the type * to use as a loop counter. + * @head: the head for your list. + * @member: the name of the list_struct within the struct. + */ +#define list_for_each_entry_from(pos, head, member) \ + for (; prefetch(pos->member.next), &pos->member != (head); \ + pos = list_entry(pos->member.next, typeof(*pos), member)) + /** * list_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @pos: the type * to use as a loop counter. -- cgit v1.2.3 From 2a91aa3967398fb94eccc8da67c82bce9f67afdf Mon Sep 17 00:00:00 2001 From: Andrea Bittau Date: Mon, 20 Mar 2006 17:41:47 -0800 Subject: [DCCP] CCID2: Initial CCID2 (TCP-Like) implementation Original work by Andrea Bittau, Arnaldo Melo cleaned up and fixed several issues on the merge process. For now CCID2 was turned the default for all SOCK_DCCP connections, but this will be remedied soon with the merge of the feature negotiation code. Signed-off-by: Andrea Bittau Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/dccp.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 088529f54965..268b4579d7e5 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -314,9 +314,9 @@ static inline unsigned int dccp_hdr_len(const struct sk_buff *skb) /* initial values for each feature */ #define DCCPF_INITIAL_SEQUENCE_WINDOW 100 -/* FIXME: for now we're using CCID 3 (TFRC) */ -#define DCCPF_INITIAL_CCID 3 -#define DCCPF_INITIAL_SEND_ACK_VECTOR 0 +/* FIXME: for now we're using CCID 2 (TCP-Like) */ +#define DCCPF_INITIAL_CCID 2 +#define DCCPF_INITIAL_SEND_ACK_VECTOR 1 /* FIXME: for now we're default to 1 but it should really be 0 */ #define DCCPF_INITIAL_SEND_NDP_COUNT 1 @@ -430,6 +430,8 @@ struct dccp_sock { struct timeval dccps_timestamp_time; __u32 dccps_timestamp_echo; __u32 dccps_packet_size; + __u16 dccps_l_ack_ratio; + __u16 dccps_r_ack_ratio; unsigned long dccps_ndp_count; __u32 dccps_mss_cache; struct dccp_options dccps_options; -- cgit v1.2.3 From afe00251dd9b53d51de91ff0099961f42bbf3754 Mon Sep 17 00:00:00 2001 From: Andrea Bittau Date: Mon, 20 Mar 2006 17:43:56 -0800 Subject: [DCCP]: Initial feature negotiation implementation Still needs more work, but boots and doesn't crashes, even does some negotiation! 18:38:52.174934 127.0.0.1.43458 > 127.0.0.1.5001: request 18:38:52.218526 127.0.0.1.5001 > 127.0.0.1.43458: response 18:38:52.185398 127.0.0.1.43458 > 127.0.0.1.5001: :-) Signed-off-by: Andrea Bittau Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/dccp.h | 35 ++++++++++++++++++++++++++++++++++- 1 file changed, 34 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 268b4579d7e5..f91c8a62406d 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -154,6 +154,10 @@ enum { DCCPO_MANDATORY = 1, DCCPO_MIN_RESERVED = 3, DCCPO_MAX_RESERVED = 31, + DCCPO_CHANGE_L = 32, + DCCPO_CONFIRM_L = 33, + DCCPO_CHANGE_R = 34, + DCCPO_CONFIRM_R = 35, DCCPO_NDP_COUNT = 37, DCCPO_ACK_VECTOR_0 = 38, DCCPO_ACK_VECTOR_1 = 39, @@ -168,7 +172,9 @@ enum { /* DCCP features */ enum { DCCPF_RESERVED = 0, + DCCPF_CCID = 1, DCCPF_SEQUENCE_WINDOW = 3, + DCCPF_ACK_RATIO = 5, DCCPF_SEND_ACK_VECTOR = 6, DCCPF_SEND_NDP_COUNT = 7, /* 10-127 reserved */ @@ -176,9 +182,18 @@ enum { DCCPF_MAX_CCID_SPECIFIC = 255, }; +/* this structure is argument to DCCP_SOCKOPT_CHANGE_X */ +struct dccp_so_feat { + __u8 dccpsf_feat; + __u8 *dccpsf_val; + __u8 dccpsf_len; +}; + /* DCCP socket options */ #define DCCP_SOCKOPT_PACKET_SIZE 1 #define DCCP_SOCKOPT_SERVICE 2 +#define DCCP_SOCKOPT_CHANGE_L 3 +#define DCCP_SOCKOPT_CHANGE_R 4 #define DCCP_SOCKOPT_CCID_RX_INFO 128 #define DCCP_SOCKOPT_CCID_TX_INFO 192 @@ -314,8 +329,8 @@ static inline unsigned int dccp_hdr_len(const struct sk_buff *skb) /* initial values for each feature */ #define DCCPF_INITIAL_SEQUENCE_WINDOW 100 -/* FIXME: for now we're using CCID 2 (TCP-Like) */ #define DCCPF_INITIAL_CCID 2 +#define DCCPF_INITIAL_ACK_RATIO 2 #define DCCPF_INITIAL_SEND_ACK_VECTOR 1 /* FIXME: for now we're default to 1 but it should really be 0 */ #define DCCPF_INITIAL_SEND_NDP_COUNT 1 @@ -335,6 +350,24 @@ struct dccp_options { __u8 dccpo_tx_ccid; __u8 dccpo_send_ack_vector; __u8 dccpo_send_ndp_count; + __u8 dccpo_ack_ratio; + struct list_head dccpo_pending; + struct list_head dccpo_conf; +}; + +struct dccp_opt_conf { + __u8 *dccpoc_val; + __u8 dccpoc_len; +}; + +struct dccp_opt_pend { + struct list_head dccpop_node; + __u8 dccpop_type; + __u8 dccpop_feat; + __u8 *dccpop_val; + __u8 dccpop_len; + int dccpop_conf; + struct dccp_opt_conf *dccpop_sc; }; extern void __dccp_options_init(struct dccp_options *dccpo); -- cgit v1.2.3 From d4d2c558fd3e1f5e386b153f194aa8f0be496c77 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Mon, 20 Mar 2006 17:47:20 -0800 Subject: [TG3]: Add support for 5714S and 5715S Add support for 5714S and 5715S. Signed-off-by: Michael Chan 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 751eea58bde8..a3a09cceb026 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1857,12 +1857,14 @@ #define PCI_DEVICE_ID_TIGON3_5705M 0x165d #define PCI_DEVICE_ID_TIGON3_5705M_2 0x165e #define PCI_DEVICE_ID_TIGON3_5714 0x1668 +#define PCI_DEVICE_ID_TIGON3_5714S 0x1669 #define PCI_DEVICE_ID_TIGON3_5780 0x166a #define PCI_DEVICE_ID_TIGON3_5780S 0x166b #define PCI_DEVICE_ID_TIGON3_5705F 0x166e #define PCI_DEVICE_ID_TIGON3_5750 0x1676 #define PCI_DEVICE_ID_TIGON3_5751 0x1677 #define PCI_DEVICE_ID_TIGON3_5715 0x1678 +#define PCI_DEVICE_ID_TIGON3_5715S 0x1679 #define PCI_DEVICE_ID_TIGON3_5750M 0x167c #define PCI_DEVICE_ID_TIGON3_5751M 0x167d #define PCI_DEVICE_ID_TIGON3_5751F 0x167e -- cgit v1.2.3 From 5d424d5a674f782d0659a3b66d951f412901faee Mon Sep 17 00:00:00 2001 From: John Heffner Date: Mon, 20 Mar 2006 17:53:41 -0800 Subject: [TCP]: MTU probing Implementation of packetization layer path mtu discovery for TCP, based on the internet-draft currently found at . Signed-off-by: John Heffner Signed-off-by: David S. Miller --- include/linux/sysctl.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 8ad4beab2888..6e8880ea49e7 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -397,6 +397,8 @@ enum NET_TCP_CONG_CONTROL=110, NET_TCP_ABC=111, NET_IPV4_IPFRAG_MAX_DIST=112, + NET_TCP_MTU_PROBING=113, + NET_TCP_BASE_MSS=114, }; enum { -- cgit v1.2.3 From ba66c6e8b292997467128506f39fa6607e959050 Mon Sep 17 00:00:00 2001 From: Ian McDonald Date: Mon, 20 Mar 2006 17:56:56 -0800 Subject: [DCCP]: Set the default CCID according to kernel config selection Now CCID2 is the default, as stated in the RFC drafts, but we allow a config where just CCID3 is built, where CCID3 becomes the default. Signed-off-by: Ian McDonald Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/dccp.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index f91c8a62406d..a70d1a27e7fc 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -329,9 +329,18 @@ static inline unsigned int dccp_hdr_len(const struct sk_buff *skb) /* initial values for each feature */ #define DCCPF_INITIAL_SEQUENCE_WINDOW 100 -#define DCCPF_INITIAL_CCID 2 #define DCCPF_INITIAL_ACK_RATIO 2 + +#if defined(CONFIG_IP_DCCP_CCID2) || defined(CONFIG_IP_DCCP_CCID2_MODULE) +#define DCCPF_INITIAL_CCID 2 #define DCCPF_INITIAL_SEND_ACK_VECTOR 1 +#elif defined(CONFIG_IP_DCCP_CCID3) || defined(CONFIG_IP_DCCP_CCID3_MODULE) +#define DCCPF_INITIAL_CCID 3 +#define DCCPF_INITIAL_SEND_ACK_VECTOR 0 +#else +#error "At least one CCID must be built as the default" +#endif + /* FIXME: for now we're default to 1 but it should really be 0 */ #define DCCPF_INITIAL_SEND_NDP_COUNT 1 -- cgit v1.2.3 From 37f9f7334b86ffc3b8a1921842ae33cb9aa22ee3 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 20 Mar 2006 17:59:06 -0800 Subject: [NETFILTER]: xt_tables: add centralized error checking Introduce new functions for common match/target checks (private data size, valid hooks, valid tables and valid protocols) to get more consistent error reporting and to avoid each module duplicating them. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/x_tables.h | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 6500d4e59d46..b9c37e1e6730 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -92,8 +92,6 @@ struct xt_match const char name[XT_FUNCTION_MAXNAMELEN-1]; - u_int8_t revision; - /* Return true or false: return FALSE and set *hotdrop = 1 to force immediate packet drop. */ /* Arguments changed since 2.6.9, as this must now handle @@ -120,6 +118,12 @@ struct xt_match /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; + + char *table; + unsigned int matchsize; + unsigned int hooks; + unsigned short proto; + u_int8_t revision; }; /* Registration hooks for targets. */ @@ -129,8 +133,6 @@ struct xt_target const char name[XT_FUNCTION_MAXNAMELEN-1]; - u_int8_t revision; - /* Returns verdict. Argument order changed since 2.6.9, as this must now handle non-linear skbs, using skb_copy_bits and skb_ip_make_writable. */ @@ -156,6 +158,12 @@ struct xt_target /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; + + char *table; + unsigned int targetsize; + unsigned int hooks; + unsigned short proto; + u_int8_t revision; }; /* Furniture shopping... */ @@ -207,6 +215,13 @@ extern void xt_unregister_target(int af, struct xt_target *target); extern int xt_register_match(int af, struct xt_match *target); extern void xt_unregister_match(int af, struct xt_match *target); +extern int xt_check_match(const struct xt_match *match, unsigned short family, + unsigned int size, const char *table, unsigned int hook, + unsigned short proto, int inv_proto); +extern int xt_check_target(const struct xt_target *target, unsigned short family, + unsigned int size, const char *table, unsigned int hook, + unsigned short proto, int inv_proto); + extern int xt_register_table(struct xt_table *table, struct xt_table_info *bootstrap, struct xt_table_info *newinfo); -- cgit v1.2.3 From 1c524830d0b39472f0278989bf1119750a5e234d Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 20 Mar 2006 18:02:15 -0800 Subject: [NETFILTER]: x_tables: pass registered match/target data to match/target functions This allows to make decisions based on the revision (and address family with a follow-up patch) at runtime. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/x_tables.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index b9c37e1e6730..2fdbc4a446bf 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -100,6 +100,7 @@ struct xt_match int (*match)(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -109,12 +110,14 @@ struct xt_match /* Should return true or false. */ int (*checkentry)(const char *tablename, const void *ip, + const struct xt_match *match, void *matchinfo, unsigned int matchinfosize, unsigned int hook_mask); /* Called when entry of this type deleted. */ - void (*destroy)(void *matchinfo, unsigned int matchinfosize); + void (*destroy)(const struct xt_match *match, void *matchinfo, + unsigned int matchinfosize); /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; @@ -140,6 +143,7 @@ struct xt_target const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct xt_target *target, const void *targinfo, void *userdata); @@ -149,12 +153,14 @@ struct xt_target /* Should return true or false. */ int (*checkentry)(const char *tablename, const void *entry, + const struct xt_target *target, void *targinfo, unsigned int targinfosize, unsigned int hook_mask); /* Called when entry of this type deleted. */ - void (*destroy)(void *targinfo, unsigned int targinfosize); + void (*destroy)(const struct xt_target *target, void *targinfo, + unsigned int targinfosize); /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; -- cgit v1.2.3 From c4b885139203d37f76662c37ae645fe8e0f4e4e5 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 20 Mar 2006 18:03:40 -0800 Subject: [NETFILTER]: x_tables: replace IPv4/IPv6 policy match by address family independant version Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/x_tables.h | 4 ++ include/linux/netfilter/xt_policy.h | 58 +++++++++++++++++++++++++ include/linux/netfilter_ipv4/ipt_policy.h | 69 +++++++----------------------- include/linux/netfilter_ipv6/ip6t_policy.h | 69 +++++++----------------------- 4 files changed, 94 insertions(+), 106 deletions(-) create mode 100644 include/linux/netfilter/xt_policy.h (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 2fdbc4a446bf..46a0f974f87c 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -126,6 +126,8 @@ struct xt_match unsigned int matchsize; unsigned int hooks; unsigned short proto; + + unsigned short family; u_int8_t revision; }; @@ -169,6 +171,8 @@ struct xt_target unsigned int targetsize; unsigned int hooks; unsigned short proto; + + unsigned short family; u_int8_t revision; }; diff --git a/include/linux/netfilter/xt_policy.h b/include/linux/netfilter/xt_policy.h new file mode 100644 index 000000000000..a8132ec076fb --- /dev/null +++ b/include/linux/netfilter/xt_policy.h @@ -0,0 +1,58 @@ +#ifndef _XT_POLICY_H +#define _XT_POLICY_H + +#define XT_POLICY_MAX_ELEM 4 + +enum xt_policy_flags +{ + XT_POLICY_MATCH_IN = 0x1, + XT_POLICY_MATCH_OUT = 0x2, + XT_POLICY_MATCH_NONE = 0x4, + XT_POLICY_MATCH_STRICT = 0x8, +}; + +enum xt_policy_modes +{ + XT_POLICY_MODE_TRANSPORT, + XT_POLICY_MODE_TUNNEL +}; + +struct xt_policy_spec +{ + u_int8_t saddr:1, + daddr:1, + proto:1, + mode:1, + spi:1, + reqid:1; +}; + +union xt_policy_addr +{ + struct in_addr a4; + struct in6_addr a6; +}; + +struct xt_policy_elem +{ + union xt_policy_addr saddr; + union xt_policy_addr smask; + union xt_policy_addr daddr; + union xt_policy_addr dmask; + u_int32_t spi; + u_int32_t reqid; + u_int8_t proto; + u_int8_t mode; + + struct xt_policy_spec match; + struct xt_policy_spec invert; +}; + +struct xt_policy_info +{ + struct xt_policy_elem pol[XT_POLICY_MAX_ELEM]; + u_int16_t flags; + u_int16_t len; +}; + +#endif /* _XT_POLICY_H */ diff --git a/include/linux/netfilter_ipv4/ipt_policy.h b/include/linux/netfilter_ipv4/ipt_policy.h index a3f6eff39d33..b9478a255301 100644 --- a/include/linux/netfilter_ipv4/ipt_policy.h +++ b/include/linux/netfilter_ipv4/ipt_policy.h @@ -1,58 +1,21 @@ #ifndef _IPT_POLICY_H #define _IPT_POLICY_H -#define IPT_POLICY_MAX_ELEM 4 - -enum ipt_policy_flags -{ - IPT_POLICY_MATCH_IN = 0x1, - IPT_POLICY_MATCH_OUT = 0x2, - IPT_POLICY_MATCH_NONE = 0x4, - IPT_POLICY_MATCH_STRICT = 0x8, -}; - -enum ipt_policy_modes -{ - IPT_POLICY_MODE_TRANSPORT, - IPT_POLICY_MODE_TUNNEL -}; - -struct ipt_policy_spec -{ - u_int8_t saddr:1, - daddr:1, - proto:1, - mode:1, - spi:1, - reqid:1; -}; - -union ipt_policy_addr -{ - struct in_addr a4; - struct in6_addr a6; -}; - -struct ipt_policy_elem -{ - union ipt_policy_addr saddr; - union ipt_policy_addr smask; - union ipt_policy_addr daddr; - union ipt_policy_addr dmask; - u_int32_t spi; - u_int32_t reqid; - u_int8_t proto; - u_int8_t mode; - - struct ipt_policy_spec match; - struct ipt_policy_spec invert; -}; - -struct ipt_policy_info -{ - struct ipt_policy_elem pol[IPT_POLICY_MAX_ELEM]; - u_int16_t flags; - u_int16_t len; -}; +#define IPT_POLICY_MAX_ELEM XT_POLICY_MAX_ELEM + +/* ipt_policy_flags */ +#define IPT_POLICY_MATCH_IN XT_POLICY_MATCH_IN +#define IPT_POLICY_MATCH_OUT XT_POLICY_MATCH_OUT +#define IPT_POLICY_MATCH_NONE XT_POLICY_MATCH_NONE +#define IPT_POLICY_MATCH_STRICT XT_POLICY_MATCH_STRICT + +/* ipt_policy_modes */ +#define IPT_POLICY_MODE_TRANSPORT XT_POLICY_MODE_TRANSPORT +#define IPT_POLICY_MODE_TUNNEL XT_POLICY_MODE_TUNNEL + +#define ipt_policy_spec xt_policy_spec +#define ipt_policy_addr xt_policy_addr +#define ipt_policy_elem xt_policy_elem +#define ipt_policy_info xt_policy_info #endif /* _IPT_POLICY_H */ diff --git a/include/linux/netfilter_ipv6/ip6t_policy.h b/include/linux/netfilter_ipv6/ip6t_policy.h index 671bd818300f..6bab3163d2fb 100644 --- a/include/linux/netfilter_ipv6/ip6t_policy.h +++ b/include/linux/netfilter_ipv6/ip6t_policy.h @@ -1,58 +1,21 @@ #ifndef _IP6T_POLICY_H #define _IP6T_POLICY_H -#define IP6T_POLICY_MAX_ELEM 4 - -enum ip6t_policy_flags -{ - IP6T_POLICY_MATCH_IN = 0x1, - IP6T_POLICY_MATCH_OUT = 0x2, - IP6T_POLICY_MATCH_NONE = 0x4, - IP6T_POLICY_MATCH_STRICT = 0x8, -}; - -enum ip6t_policy_modes -{ - IP6T_POLICY_MODE_TRANSPORT, - IP6T_POLICY_MODE_TUNNEL -}; - -struct ip6t_policy_spec -{ - u_int8_t saddr:1, - daddr:1, - proto:1, - mode:1, - spi:1, - reqid:1; -}; - -union ip6t_policy_addr -{ - struct in_addr a4; - struct in6_addr a6; -}; - -struct ip6t_policy_elem -{ - union ip6t_policy_addr saddr; - union ip6t_policy_addr smask; - union ip6t_policy_addr daddr; - union ip6t_policy_addr dmask; - u_int32_t spi; - u_int32_t reqid; - u_int8_t proto; - u_int8_t mode; - - struct ip6t_policy_spec match; - struct ip6t_policy_spec invert; -}; - -struct ip6t_policy_info -{ - struct ip6t_policy_elem pol[IP6T_POLICY_MAX_ELEM]; - u_int16_t flags; - u_int16_t len; -}; +#define IP6T_POLICY_MAX_ELEM XT_POLICY_MAX_ELEM + +/* ip6t_policy_flags */ +#define IP6T_POLICY_MATCH_IN XT_POLICY_MATCH_IN +#define IP6T_POLICY_MATCH_OUT XT_POLICY_MATCH_OUT +#define IP6T_POLICY_MATCH_NONE XT_POLICY_MATCH_NONE +#define IP6T_POLICY_MATCH_STRICT XT_POLICY_MATCH_STRICT + +/* ip6t_policy_modes */ +#define IP6T_POLICY_MODE_TRANSPORT XT_POLICY_MODE_TRANSPORT +#define IP6T_POLICY_MODE_TUNNEL XT_POLICY_MODE_TUNNEL + +#define ip6t_policy_spec xt_policy_spec +#define ip6t_policy_addr xt_policy_addr +#define ip6t_policy_elem xt_policy_elem +#define ip6t_policy_info xt_policy_info #endif /* _IP6T_POLICY_H */ -- cgit v1.2.3 From a24276924875802853b5bdc12c56d29f1c1bbc79 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 20 Mar 2006 18:03:59 -0800 Subject: [NETFILTER]: ctnetlink: avoid unneccessary event message generation Avoid unneccessary event message generation by checking for netlink listeners before building a message. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 934a2479f160..9f5b12cf489b 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -164,6 +164,7 @@ extern void nfattr_parse(struct nfattr *tb[], int maxattr, __res; \ }) +extern int nfnetlink_has_listeners(unsigned int group); extern int nfnetlink_send(struct sk_buff *skb, u32 pid, unsigned group, int echo); extern int nfnetlink_unicast(struct sk_buff *skb, u_int32_t pid, int flags); -- cgit v1.2.3 From 4277a083ecd2c8771058641132bcecea04ca6608 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 20 Mar 2006 18:52:01 -0800 Subject: [NETLINK]: Add netlink_has_listeners for avoiding unneccessary event message generation Keep a bitmask of multicast groups with subscribed listeners to let netlink users check for listeners before generating multicast messages. Queries don't perform any locking, which may result in false positives, it is guaranteed however that any new subscriptions are visible before bind() or setsockopt() return. Signed-off-by: Patrick McHardy ACKed-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/linux/netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index c256ebe2a7b4..f8f3d1c927f8 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -151,6 +151,7 @@ struct netlink_skb_parms extern struct sock *netlink_kernel_create(int unit, unsigned int groups, void (*input)(struct sock *sk, int len), struct module *module); extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err); +extern int netlink_has_listeners(struct sock *sk, unsigned int group); extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 pid, int nonblock); extern int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 pid, __u32 group, gfp_t allocation); -- cgit v1.2.3 From f8cd54884e675dfaf0c86cc7c088adb6ca9d7638 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Mon, 20 Mar 2006 19:15:11 -0800 Subject: [IPSEC]: Sync series - core changes This patch provides the core functionality needed for sync events for ipsec. Derived work of Krisztian KOVACS Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/linux/sysctl.h | 2 ++ include/linux/xfrm.h | 30 ++++++++++++++++++++++++++++++ 2 files changed, 32 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 6e8880ea49e7..b686548f32e0 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -261,6 +261,8 @@ enum NET_CORE_DEV_WEIGHT=17, NET_CORE_SOMAXCONN=18, NET_CORE_BUDGET=19, + NET_CORE_AEVENT_ETIME=20, + NET_CORE_AEVENT_RSEQTH=21, }; /* /proc/sys/net/ethernet */ diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index 82fbb758e28f..b54a12940ef6 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -156,6 +156,10 @@ enum { XFRM_MSG_FLUSHPOLICY, #define XFRM_MSG_FLUSHPOLICY XFRM_MSG_FLUSHPOLICY + XFRM_MSG_NEWAE, +#define XFRM_MSG_NEWAE XFRM_MSG_NEWAE + XFRM_MSG_GETAE, +#define XFRM_MSG_GETAE XFRM_MSG_GETAE __XFRM_MSG_MAX }; #define XFRM_MSG_MAX (__XFRM_MSG_MAX - 1) @@ -194,6 +198,21 @@ struct xfrm_encap_tmpl { xfrm_address_t encap_oa; }; +/* AEVENT flags */ +enum xfrm_ae_ftype_t { + XFRM_AE_UNSPEC, + XFRM_AE_RTHR=1, /* replay threshold*/ + XFRM_AE_RVAL=2, /* replay value */ + XFRM_AE_LVAL=4, /* lifetime value */ + XFRM_AE_ETHR=8, /* expiry timer threshold */ + XFRM_AE_CR=16, /* Event cause is replay update */ + XFRM_AE_CE=32, /* Event cause is timer expiry */ + XFRM_AE_CU=64, /* Event cause is policy update */ + __XFRM_AE_MAX + +#define XFRM_AE_MAX (__XFRM_AE_MAX - 1) +}; + /* Netlink message attributes. */ enum xfrm_attr_type_t { XFRMA_UNSPEC, @@ -205,6 +224,10 @@ enum xfrm_attr_type_t { XFRMA_SA, XFRMA_POLICY, XFRMA_SEC_CTX, /* struct xfrm_sec_ctx */ + XFRMA_LTIME_VAL, + XFRMA_REPLAY_VAL, + XFRMA_REPLAY_THRESH, + XFRMA_ETIMER_THRESH, __XFRMA_MAX #define XFRMA_MAX (__XFRMA_MAX - 1) @@ -235,6 +258,11 @@ struct xfrm_usersa_id { __u8 proto; }; +struct xfrm_aevent_id { + __u32 flags; + struct xfrm_usersa_id sa_id; +}; + struct xfrm_userspi_info { struct xfrm_usersa_info info; __u32 min; @@ -306,6 +334,8 @@ enum xfrm_nlgroups { #define XFRMNLGRP_SA XFRMNLGRP_SA XFRMNLGRP_POLICY, #define XFRMNLGRP_POLICY XFRMNLGRP_POLICY + XFRMNLGRP_AEVENTS, +#define XFRMNLGRP_AEVENTS XFRMNLGRP_AEVENTS __XFRMNLGRP_MAX }; #define XFRMNLGRP_MAX (__XFRMNLGRP_MAX - 1) -- cgit v1.2.3 From 91f0ebf7b6d5cb2b6e818d48587566144821babe Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 20 Mar 2006 19:21:44 -0800 Subject: [DCCP] CCID: Improve CCID infrastructure 1. No need for ->ccid_init nor ->ccid_exit, this is what module_{init,exit} does and anynways neither ccid2 nor ccid3 were using it. 2. Rename struct ccid to struct ccid_operations and introduce struct ccid with a pointer to ccid_operations and rigth after it the rx or tx private state. 3. Remove the pointer to the state of the half connections from struct dccp_sock, now its derived thru ccid_priv() from the ccid pointer. Now we also can implement the setsockopt for changing the CCID easily as no ccid init routines can affect struct dccp_sock in any way that prevents other CCIDs from working if a CCID switch operation is asked by apps. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/dccp.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index a70d1a27e7fc..bdd756cc60b1 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -478,8 +478,6 @@ struct dccp_sock { __u32 dccps_mss_cache; struct dccp_options dccps_options; struct dccp_ackvec *dccps_hc_rx_ackvec; - void *dccps_hc_rx_ccid_private; - void *dccps_hc_tx_ccid_private; struct ccid *dccps_hc_rx_ccid; struct ccid *dccps_hc_tx_ccid; struct dccp_options_received dccps_options_received; -- cgit v1.2.3 From a193a4abdd1f742a57f3f70b6a83c3e536876e97 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 20 Mar 2006 19:23:05 -0800 Subject: [NETFILTER]: Fix skb->nf_bridge lifetime issues The bridge netfilter code simulates the NF_IP_PRE_ROUTING hook and skips the real hook by registering with high priority and returning NF_STOP if skb->nf_bridge is present and the BRNF_NF_BRIDGE_PREROUTING flag is not set. The flag is only set during the simulated hook. Because skb->nf_bridge is only freed when the packet is destroyed, the packet will not only skip the first invocation of NF_IP_PRE_ROUTING, but in the case of tunnel devices on top of the bridge also all further ones. Forwarded packets from a bridge encapsulated by a tunnel device and sent as locally outgoing packet will also still have the incorrect bridge information from the input path attached. We already have nf_reset calls on all RX/TX paths of tunnel devices, so simply reset the nf_bridge field there too. As an added bonus, the bridge information for locally delivered packets is now also freed when the packet is queued to a socket. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/skbuff.h | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 838ce0fdcef7..1a2611030d36 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1351,16 +1351,6 @@ static inline void nf_conntrack_put_reasm(struct sk_buff *skb) kfree_skb(skb); } #endif -static inline void nf_reset(struct sk_buff *skb) -{ - nf_conntrack_put(skb->nfct); - skb->nfct = NULL; -#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) - nf_conntrack_put_reasm(skb->nfct_reasm); - skb->nfct_reasm = NULL; -#endif -} - #ifdef CONFIG_BRIDGE_NETFILTER static inline void nf_bridge_put(struct nf_bridge_info *nf_bridge) { @@ -1373,6 +1363,20 @@ static inline void nf_bridge_get(struct nf_bridge_info *nf_bridge) atomic_inc(&nf_bridge->use); } #endif /* CONFIG_BRIDGE_NETFILTER */ +static inline void nf_reset(struct sk_buff *skb) +{ + nf_conntrack_put(skb->nfct); + skb->nfct = NULL; +#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) + nf_conntrack_put_reasm(skb->nfct_reasm); + skb->nfct_reasm = NULL; +#endif +#ifdef CONFIG_BRIDGE_NETFILTER + nf_bridge_put(skb->nf_bridge); + skb->nf_bridge = NULL; +#endif +} + #else /* CONFIG_NETFILTER */ static inline void nf_reset(struct sk_buff *skb) {} #endif /* CONFIG_NETFILTER */ -- cgit v1.2.3 From 60fe62e789076ae7c13f7ffb35fec4b24802530d Mon Sep 17 00:00:00 2001 From: Andrea Bittau Date: Mon, 20 Mar 2006 19:23:32 -0800 Subject: [DCCP]: sparse endianness annotations This also fixes the layout of dccp_hdr short sequence numbers, problem was not fatal now as we only support long (48 bits) sequence numbers. Signed-off-by: Andrea Bittau Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/dccp.h | 52 +++++++++++++++++++++------------------------------- 1 file changed, 21 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index bdd756cc60b1..496dbad8e896 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -18,7 +18,7 @@ * @dccph_seq - sequence number high or low order 24 bits, depends on dccph_x */ struct dccp_hdr { - __u16 dccph_sport, + __be16 dccph_sport, dccph_dport; __u8 dccph_doff; #if defined(__LITTLE_ENDIAN_BITFIELD) @@ -32,18 +32,18 @@ struct dccp_hdr { #endif __u16 dccph_checksum; #if defined(__LITTLE_ENDIAN_BITFIELD) - __u32 dccph_x:1, + __u8 dccph_x:1, dccph_type:4, - dccph_reserved:3, - dccph_seq:24; + dccph_reserved:3; #elif defined(__BIG_ENDIAN_BITFIELD) - __u32 dccph_reserved:3, + __u8 dccph_reserved:3, dccph_type:4, - dccph_x:1, - dccph_seq:24; + dccph_x:1; #else #error "Adjust your defines" #endif + __u8 dccph_seq2; + __be16 dccph_seq; }; /** @@ -52,7 +52,7 @@ struct dccp_hdr { * @dccph_seq_low - low 24 bits of a 48 bit seq packet */ struct dccp_hdr_ext { - __u32 dccph_seq_low; + __be32 dccph_seq_low; }; /** @@ -62,7 +62,7 @@ struct dccp_hdr_ext { * @dccph_req_options - list of options (must be a multiple of 32 bits */ struct dccp_hdr_request { - __u32 dccph_req_service; + __be32 dccph_req_service; }; /** * struct dccp_hdr_ack_bits - acknowledgment bits common to most packets @@ -71,9 +71,9 @@ struct dccp_hdr_request { * @dccph_resp_ack_nr_low - 48 bit ack number low order bits, contains GSR */ struct dccp_hdr_ack_bits { - __u32 dccph_reserved1:8, - dccph_ack_nr_high:24; - __u32 dccph_ack_nr_low; + __be16 dccph_reserved1; + __be16 dccph_ack_nr_high; + __be32 dccph_ack_nr_low; }; /** * struct dccp_hdr_response - Conection initiation response header @@ -85,7 +85,7 @@ struct dccp_hdr_ack_bits { */ struct dccp_hdr_response { struct dccp_hdr_ack_bits dccph_resp_ack; - __u32 dccph_resp_service; + __be32 dccph_resp_service; }; /** @@ -269,16 +269,12 @@ static inline unsigned int dccp_basic_hdr_len(const struct sk_buff *skb) static inline __u64 dccp_hdr_seq(const struct sk_buff *skb) { const struct dccp_hdr *dh = dccp_hdr(skb); -#if defined(__LITTLE_ENDIAN_BITFIELD) - __u64 seq_nr = ntohl(dh->dccph_seq << 8); -#elif defined(__BIG_ENDIAN_BITFIELD) - __u64 seq_nr = ntohl(dh->dccph_seq); -#else -#error "Adjust your defines" -#endif + __u64 seq_nr = ntohs(dh->dccph_seq); if (dh->dccph_x != 0) seq_nr = (seq_nr << 32) + ntohl(dccp_hdrx(skb)->dccph_seq_low); + else + seq_nr += (u32)dh->dccph_seq2 << 16; return seq_nr; } @@ -296,13 +292,7 @@ static inline struct dccp_hdr_ack_bits *dccp_hdr_ack_bits(const struct sk_buff * static inline u64 dccp_hdr_ack_seq(const struct sk_buff *skb) { const struct dccp_hdr_ack_bits *dhack = dccp_hdr_ack_bits(skb); -#if defined(__LITTLE_ENDIAN_BITFIELD) - return (((u64)ntohl(dhack->dccph_ack_nr_high << 8)) << 32) + ntohl(dhack->dccph_ack_nr_low); -#elif defined(__BIG_ENDIAN_BITFIELD) - return (((u64)ntohl(dhack->dccph_ack_nr_high)) << 32) + ntohl(dhack->dccph_ack_nr_low); -#else -#error "Adjust your defines" -#endif + return ((u64)ntohs(dhack->dccph_ack_nr_high) << 32) + ntohl(dhack->dccph_ack_nr_low); } static inline struct dccp_hdr_response *dccp_hdr_response(struct sk_buff *skb) @@ -387,7 +377,7 @@ struct dccp_request_sock { struct inet_request_sock dreq_inet_rsk; __u64 dreq_iss; __u64 dreq_isr; - __u32 dreq_service; + __be32 dreq_service; }; static inline struct dccp_request_sock *dccp_rsk(const struct request_sock *req) @@ -415,13 +405,13 @@ enum dccp_role { struct dccp_service_list { __u32 dccpsl_nr; - __u32 dccpsl_list[0]; + __be32 dccpsl_list[0]; }; #define DCCP_SERVICE_INVALID_VALUE htonl((__u32)-1) static inline int dccp_list_has_service(const struct dccp_service_list *sl, - const u32 service) + const __be32 service) { if (likely(sl != NULL)) { u32 i = sl->dccpsl_nr; @@ -467,7 +457,7 @@ struct dccp_sock { __u64 dccps_gss; __u64 dccps_gsr; __u64 dccps_gar; - __u32 dccps_service; + __be32 dccps_service; struct dccp_service_list *dccps_service_list; struct timeval dccps_timestamp_time; __u32 dccps_timestamp_echo; -- cgit v1.2.3 From 93ce20928f6e197707add8f670ae0cd029107e8f Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 20 Mar 2006 19:23:58 -0800 Subject: [DCCP]: Make CCID2 be the default As per the draft. This fixes the build when netfilter dccp components are built and dccp isn't. Thanks to Reuben Farrelly for reporting this. The following changesets will introduce /proc/sys/net/dccp/defaults/ to give more flexibility to DCCP developers and testers while apps doesn't use setsockopt to specify the desired CCID, etc. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/dccp.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 496dbad8e896..e35f680f909b 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -320,17 +320,8 @@ static inline unsigned int dccp_hdr_len(const struct sk_buff *skb) /* initial values for each feature */ #define DCCPF_INITIAL_SEQUENCE_WINDOW 100 #define DCCPF_INITIAL_ACK_RATIO 2 - -#if defined(CONFIG_IP_DCCP_CCID2) || defined(CONFIG_IP_DCCP_CCID2_MODULE) #define DCCPF_INITIAL_CCID 2 #define DCCPF_INITIAL_SEND_ACK_VECTOR 1 -#elif defined(CONFIG_IP_DCCP_CCID3) || defined(CONFIG_IP_DCCP_CCID3_MODULE) -#define DCCPF_INITIAL_CCID 3 -#define DCCPF_INITIAL_SEND_ACK_VECTOR 0 -#else -#error "At least one CCID must be built as the default" -#endif - /* FIXME: for now we're default to 1 but it should really be 0 */ #define DCCPF_INITIAL_SEND_NDP_COUNT 1 -- cgit v1.2.3 From e55d912f5b75723159348a7fc7692f869a86636a Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 20 Mar 2006 19:25:02 -0800 Subject: [DCCP] feat: Introduce sysctls for the default features [root@qemu ~]# for a in /proc/sys/net/dccp/default/* ; do echo $a ; cat $a ; done /proc/sys/net/dccp/default/ack_ratio 2 /proc/sys/net/dccp/default/rx_ccid 3 /proc/sys/net/dccp/default/send_ackvec 1 /proc/sys/net/dccp/default/send_ndp 1 /proc/sys/net/dccp/default/seq_window 100 /proc/sys/net/dccp/default/tx_ccid 3 [root@qemu ~]# So if wanting to test ccid3 as the tx CCID one can just do: [root@qemu ~]# echo 3 > /proc/sys/net/dccp/default/tx_ccid [root@qemu ~]# echo 2 > /proc/sys/net/dccp/default/rx_ccid [root@qemu ~]# cat /proc/sys/net/dccp/default/[tr]x_ccid 2 3 [root@qemu ~]# Of course we also need the setsockopt for each app to tell its preferences, but for testing or defining something other than CCID2 as the default for apps that don't explicitely set their preference the sysctl interface is handy. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/sysctl.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index b686548f32e0..dfcf449afc7c 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -211,6 +211,7 @@ enum NET_SCTP=17, NET_LLC=18, NET_NETFILTER=19, + NET_DCCP=20, }; /* /proc/sys/kernel/random */ @@ -571,6 +572,21 @@ enum { __NET_NEIGH_MAX }; +/* /proc/sys/net/dccp */ +enum { + NET_DCCP_DEFAULT=1, +}; + +/* /proc/sys/net/dccp/default */ +enum { + NET_DCCP_DEFAULT_SEQ_WINDOW = 1, + NET_DCCP_DEFAULT_RX_CCID = 2, + NET_DCCP_DEFAULT_TX_CCID = 3, + NET_DCCP_DEFAULT_ACK_RATIO = 4, + NET_DCCP_DEFAULT_SEND_ACKVEC = 5, + NET_DCCP_DEFAULT_SEND_NDP = 6, +}; + /* /proc/sys/net/ipx */ enum { NET_IPX_PPROP_BROADCASTING=1, -- cgit v1.2.3 From 4bf07ef3fd5db2df7d1899fcf9c67d2263ead2e2 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Mon, 20 Mar 2006 21:25:50 -0800 Subject: [XFRM]: Rearrange struct xfrm_aevent_id for better compatibility. struct xfrm_aevent_id needs to be 32-bit + 64-bit align friendly. Based upon suggestions from Yoshifuji. Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/linux/xfrm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index b54a12940ef6..6b42cc474c01 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -259,8 +259,8 @@ struct xfrm_usersa_id { }; struct xfrm_aevent_id { - __u32 flags; struct xfrm_usersa_id sa_id; + __u32 flags; }; struct xfrm_userspi_info { -- cgit v1.2.3 From 231d06ae826664b83369166449144304859a62fa Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=F6rn=20Engel?= Date: Mon, 20 Mar 2006 21:28:35 -0800 Subject: [NET]: Uninline kfree_skb and allow NULL argument MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit o Uninline kfree_skb, which saves some 15k of object code on my notebook. o Allow kfree_skb to be called with a NULL argument. Subsequent patches can remove conditional from drivers and further reduce source and object size. Signed-off-by: Jörn Engel Signed-off-by: David S. Miller --- include/linux/skbuff.h | 17 +---------------- 1 file changed, 1 insertion(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 1a2611030d36..75c963103b9f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -304,6 +304,7 @@ struct sk_buff { #include +extern void kfree_skb(struct sk_buff *skb); extern void __kfree_skb(struct sk_buff *skb); extern struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int fclone); @@ -403,22 +404,6 @@ static inline struct sk_buff *skb_get(struct sk_buff *skb) * atomic change. */ -/** - * kfree_skb - free an sk_buff - * @skb: buffer to free - * - * Drop a reference to the buffer and free it if the usage count has - * hit zero. - */ -static inline void kfree_skb(struct sk_buff *skb) -{ - if (likely(atomic_read(&skb->users) == 1)) - smp_rmb(); - else if (likely(!atomic_dec_and_test(&skb->users))) - return; - __kfree_skb(skb); -} - /** * skb_cloned - is the buffer a clone * @skb: buffer to check -- cgit v1.2.3 From 0e7b13685f9a06949ea3070c97c0f0085a08cd37 Mon Sep 17 00:00:00 2001 From: John Heffner Date: Mon, 20 Mar 2006 21:32:58 -0800 Subject: [TCP] mtu probing: move tcp-specific data out of inet_connection_sock This moves some TCP-specific MTU probing state out of inet_connection_sock back to tcp_sock. Signed-off-by: John Heffner Signed-off-by: David S. Miller --- include/linux/tcp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index f2bb2396853f..542d39596bd8 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -343,6 +343,12 @@ struct tcp_sock { __u32 seq; __u32 time; } rcvq_space; + +/* TCP-specific MTU probe information. */ + struct { + __u32 probe_seq_start; + __u32 probe_seq_end; + } mtu_probe; }; static inline struct tcp_sock *tcp_sk(const struct sock *sk) -- cgit v1.2.3 From 0ac81ae34ec8898e7eb1388fe21e3cee7b626a88 Mon Sep 17 00:00:00 2001 From: David Basden Date: Mon, 20 Mar 2006 22:21:10 -0800 Subject: [IRDA]: TOIM3232 dongle support Here goes a patch for supporting TOIM3232 based serial IrDA dongles. The code is based on the tekram dongle code. It's been tested with a TOIM3232 based IRWave 320S dongle. It may work for TOIM4232 dongles, although it's not been tested. Signed-off-by: David Basden Signed-off-by: Samuel Ortiz Signed-off-by: David S. Miller --- include/linux/irda.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/irda.h b/include/linux/irda.h index 95dee174cdc5..09d8f105a5a8 100644 --- a/include/linux/irda.h +++ b/include/linux/irda.h @@ -76,6 +76,7 @@ typedef enum { IRDA_MCP2120_DONGLE = 9, IRDA_ACT200L_DONGLE = 10, IRDA_MA600_DONGLE = 11, + IRDA_TOIM3232_DONGLE = 12, } IRDA_DONGLE; /* Protocol types to be used for SOCK_DGRAM */ -- cgit v1.2.3 From 6756ae4b4e97aba48c042b4aa6b77a18f507d2cb Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Mon, 20 Mar 2006 22:23:58 -0800 Subject: [NET]: Convert RTNL to mutex. This patch turns the RTNL from a semaphore to a new 2.6.16 mutex and gets rid of some of the leftover legacy. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 20 +++++++------------- 1 file changed, 7 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index edccefb45188..d263853a8f1c 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -907,6 +907,7 @@ struct tcamsg #ifdef __KERNEL__ #include +#include extern size_t rtattr_strlcpy(char *dest, const struct rtattr *rta, size_t size); static __inline__ int rtattr_strcmp(const struct rtattr *rta, const char *str) @@ -1038,24 +1039,17 @@ __rta_reserve(struct sk_buff *skb, int attrtype, int attrlen) extern void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change); -extern struct semaphore rtnl_sem; - -#define rtnl_shlock() down(&rtnl_sem) -#define rtnl_shlock_nowait() down_trylock(&rtnl_sem) - -#define rtnl_shunlock() do { up(&rtnl_sem); \ - if (rtnl && rtnl->sk_receive_queue.qlen) \ - rtnl->sk_data_ready(rtnl, 0); \ - } while(0) - +/* RTNL is used as a global lock for all changes to network configuration */ extern void rtnl_lock(void); -extern int rtnl_lock_interruptible(void); extern void rtnl_unlock(void); +extern int rtnl_trylock(void); + extern void rtnetlink_init(void); +extern void __rtnl_unlock(void); #define ASSERT_RTNL() do { \ - if (unlikely(down_trylock(&rtnl_sem) == 0)) { \ - up(&rtnl_sem); \ + if (unlikely(rtnl_trylock())) { \ + rtnl_unlock(); \ printk(KERN_ERR "RTNL: assertion failed at %s (%d)\n", \ __FILE__, __LINE__); \ dump_stack(); \ -- cgit v1.2.3 From 99cae7fca1311573f2777b8ceaa8a5abd6e9b04e Mon Sep 17 00:00:00 2001 From: Alpt Date: Mon, 20 Mar 2006 22:26:17 -0800 Subject: [NET] rtnetlink: Add RTPROT entry for Netsukuku. The Netsukuku daemon is using the same number to mark its routes, you can see it here: http://hinezumilabs.org/cgi-bin/viewcvs.cgi/netsukuku/src/krnl_route.h?rev=HEAD&content-type=text/vnd.viewcvs-markup Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index d263853a8f1c..d572d5376319 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -199,6 +199,7 @@ enum #define RTPROT_BIRD 12 /* BIRD */ #define RTPROT_DNROUTED 13 /* DECnet routing daemon */ #define RTPROT_XORP 14 /* XORP */ +#define RTPROT_NTK 15 /* Netsukuku */ /* rtm_scope -- cgit v1.2.3 From d9ab5ad12b0d865bdb1b750d81192d34465541e9 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Mon, 20 Mar 2006 22:27:35 -0800 Subject: [TG3]: Add 5787 and 5754 basic support Add basic support for 2 new chips 5787 and 5754. Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- include/linux/pci_ids.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index a3a09cceb026..b9810ddf435a 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1861,14 +1861,18 @@ #define PCI_DEVICE_ID_TIGON3_5780 0x166a #define PCI_DEVICE_ID_TIGON3_5780S 0x166b #define PCI_DEVICE_ID_TIGON3_5705F 0x166e +#define PCI_DEVICE_ID_TIGON3_5754M 0x1672 #define PCI_DEVICE_ID_TIGON3_5750 0x1676 #define PCI_DEVICE_ID_TIGON3_5751 0x1677 #define PCI_DEVICE_ID_TIGON3_5715 0x1678 #define PCI_DEVICE_ID_TIGON3_5715S 0x1679 +#define PCI_DEVICE_ID_TIGON3_5754 0x167a #define PCI_DEVICE_ID_TIGON3_5750M 0x167c #define PCI_DEVICE_ID_TIGON3_5751M 0x167d #define PCI_DEVICE_ID_TIGON3_5751F 0x167e +#define PCI_DEVICE_ID_TIGON3_5787M 0x1693 #define PCI_DEVICE_ID_TIGON3_5782 0x1696 +#define PCI_DEVICE_ID_TIGON3_5787 0x169b #define PCI_DEVICE_ID_TIGON3_5788 0x169c #define PCI_DEVICE_ID_TIGON3_5789 0x169d #define PCI_DEVICE_ID_TIGON3_5702X 0x16a6 -- cgit v1.2.3 From 153330618691694af64f39fb56c9de051862380e Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Mon, 20 Mar 2006 22:32:28 -0800 Subject: [NET]: dev_put/dev_hold cleanup Get rid of the old __dev_put macro that is just a hold over from pre 2.6 kernel. And turn dev_hold into an inline instead of a macro. Signed-off-by: Stephen Hemminger Signed-off-by: Andrew Morton Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b825be201bce..950dc55e5192 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -712,8 +712,10 @@ static inline void dev_put(struct net_device *dev) atomic_dec(&dev->refcnt); } -#define __dev_put(dev) atomic_dec(&(dev)->refcnt) -#define dev_hold(dev) atomic_inc(&(dev)->refcnt) +static inline void dev_hold(struct net_device *dev) +{ + atomic_inc(&dev->refcnt); +} /* Carrier loss detection, dial on demand. The functions netif_carrier_on * and _off may be called from IRQ context, but it is caller -- cgit v1.2.3 From 57b47a53ec4a67691ba32cff5768e8d78fa6c67f Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 20 Mar 2006 22:35:41 -0800 Subject: [NET]: sem2mutex part 2 Semaphore to mutex conversion. The conversion was generated via scripts, and the result was validated automatically via a script as well. Signed-off-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: David S. Miller --- include/linux/sunrpc/svcsock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index d33c6face032..b4acb3d37c3f 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -36,7 +36,7 @@ struct svc_sock { struct list_head sk_deferred; /* deferred requests that need to * be revisted */ - struct semaphore sk_sem; /* to serialize sending data */ + struct mutex sk_mutex; /* to serialize sending data */ int (*sk_recvfrom)(struct svc_rqst *rqstp); int (*sk_sendto)(struct svc_rqst *rqstp); -- cgit v1.2.3 From abd596a4b68b6526c2676233e10602dd9660e9d7 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Mon, 20 Mar 2006 22:39:47 -0800 Subject: [IPV4] ARP: Alloc acceptance of unsolicited ARP via netdevice sysctl. Signed-off-by: Neil Horman Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 1 + include/linux/sysctl.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index fd7af86151b1..92297ff24e85 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -25,6 +25,7 @@ struct ipv4_devconf int arp_filter; int arp_announce; int arp_ignore; + int arp_accept; int medium_id; int no_xfrm; int no_policy; diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index dfcf449afc7c..8754568a75d7 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -456,6 +456,7 @@ enum NET_IPV4_CONF_ARP_ANNOUNCE=18, NET_IPV4_CONF_ARP_IGNORE=19, NET_IPV4_CONF_PROMOTE_SECONDARIES=20, + NET_IPV4_CONF_ARP_ACCEPT=21, __NET_IPV4_CONF_MAX }; -- cgit v1.2.3 From 15d99e02babae8bc20b836917ace07d93e318149 Mon Sep 17 00:00:00 2001 From: Rick Jones Date: Mon, 20 Mar 2006 22:40:29 -0800 Subject: [TCP]: sysctl to allow TCP window > 32767 sans wscale Back in the dark ages, we had to be conservative and only allow 15-bit window fields if the window scale option was not negotiated. Some ancient stacks used a signed 16-bit quantity for the window field of the TCP header and would get confused. Those days are long gone, so we can use the full 16-bits by default now. There is a sysctl added so that we can still interact with such old stacks Signed-off-by: Rick Jones Signed-off-by: David S. Miller --- include/linux/sysctl.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 8754568a75d7..76eaeff76f82 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -402,6 +402,7 @@ enum NET_IPV4_IPFRAG_MAX_DIST=112, NET_TCP_MTU_PROBING=113, NET_TCP_BASE_MSS=114, + NET_IPV4_TCP_WORKAROUND_SIGNED_WINDOWS=115, }; enum { -- cgit v1.2.3 From 2c7946a7bf45ae86736ab3b43d0085e43947945c Mon Sep 17 00:00:00 2001 From: Catherine Zhang Date: Mon, 20 Mar 2006 22:41:23 -0800 Subject: [SECURITY]: TCP/UDP getpeersec This patch implements an application of the LSM-IPSec networking controls whereby an application can determine the label of the security association its TCP or UDP sockets are currently connected to via getsockopt and the auxiliary data mechanism of recvmsg. Patch purpose: This patch enables a security-aware application to retrieve the security context of an IPSec security association a particular TCP or UDP socket is using. The application can then use this security context to determine the security context for processing on behalf of the peer at the other end of this connection. In the case of UDP, the security context is for each individual packet. An example application is the inetd daemon, which could be modified to start daemons running at security contexts dependent on the remote client. Patch design approach: - Design for TCP The patch enables the SELinux LSM to set the peer security context for a socket based on the security context of the IPSec security association. The application may retrieve this context using getsockopt. When called, the kernel determines if the socket is a connected (TCP_ESTABLISHED) TCP socket and, if so, uses the dst_entry cache on the socket to retrieve the security associations. If a security association has a security context, the context string is returned, as for UNIX domain sockets. - Design for UDP Unlike TCP, UDP is connectionless. This requires a somewhat different API to retrieve the peer security context. With TCP, the peer security context stays the same throughout the connection, thus it can be retrieved at any time between when the connection is established and when it is torn down. With UDP, each read/write can have different peer and thus the security context might change every time. As a result the security context retrieval must be done TOGETHER with the packet retrieval. The solution is to build upon the existing Unix domain socket API for retrieving user credentials. Linux offers the API for obtaining user credentials via ancillary messages (i.e., out of band/control messages that are bundled together with a normal message). Patch implementation details: - Implementation for TCP The security context can be retrieved by applications using getsockopt with the existing SO_PEERSEC flag. As an example (ignoring error checking): getsockopt(sockfd, SOL_SOCKET, SO_PEERSEC, optbuf, &optlen); printf("Socket peer context is: %s\n", optbuf); The SELinux function, selinux_socket_getpeersec, is extended to check for labeled security associations for connected (TCP_ESTABLISHED == sk->sk_state) TCP sockets only. If so, the socket has a dst_cache of struct dst_entry values that may refer to security associations. If these have security associations with security contexts, the security context is returned. getsockopt returns a buffer that contains a security context string or the buffer is unmodified. - Implementation for UDP To retrieve the security context, the application first indicates to the kernel such desire by setting the IP_PASSSEC option via getsockopt. Then the application retrieves the security context using the auxiliary data mechanism. An example server application for UDP should look like this: toggle = 1; toggle_len = sizeof(toggle); setsockopt(sockfd, SOL_IP, IP_PASSSEC, &toggle, &toggle_len); recvmsg(sockfd, &msg_hdr, 0); if (msg_hdr.msg_controllen > sizeof(struct cmsghdr)) { cmsg_hdr = CMSG_FIRSTHDR(&msg_hdr); if (cmsg_hdr->cmsg_len <= CMSG_LEN(sizeof(scontext)) && cmsg_hdr->cmsg_level == SOL_IP && cmsg_hdr->cmsg_type == SCM_SECURITY) { memcpy(&scontext, CMSG_DATA(cmsg_hdr), sizeof(scontext)); } } ip_setsockopt is enhanced with a new socket option IP_PASSSEC to allow a server socket to receive security context of the peer. A new ancillary message type SCM_SECURITY. When the packet is received we get the security context from the sec_path pointer which is contained in the sk_buff, and copy it to the ancillary message space. An additional LSM hook, selinux_socket_getpeersec_udp, is defined to retrieve the security context from the SELinux space. The existing function, selinux_socket_getpeersec does not suit our purpose, because the security context is copied directly to user space, rather than to kernel space. Testing: We have tested the patch by setting up TCP and UDP connections between applications on two machines using the IPSec policies that result in labeled security associations being built. For TCP, we can then extract the peer security context using getsockopt on either end. For UDP, the receiving end can retrieve the security context using the auxiliary data mechanism of recvmsg. Signed-off-by: Catherine Zhang Acked-by: James Morris Acked-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/in.h | 1 + include/linux/security.h | 25 +++++++++++++++++++------ include/linux/socket.h | 1 + 3 files changed, 21 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/in.h b/include/linux/in.h index ba355384016a..94f557fa4636 100644 --- a/include/linux/in.h +++ b/include/linux/in.h @@ -72,6 +72,7 @@ struct in_addr { #define IP_FREEBIND 15 #define IP_IPSEC_POLICY 16 #define IP_XFRM_POLICY 17 +#define IP_PASSSEC 18 /* BSD compatibility */ #define IP_RECVRETOPTS IP_RETOPTS diff --git a/include/linux/security.h b/include/linux/security.h index 7cbef482e13a..b18eb8cfa639 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1286,7 +1286,8 @@ struct security_operations { int (*socket_setsockopt) (struct socket * sock, int level, int optname); 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 (*socket_getpeersec_stream) (struct socket *sock, char __user *optval, int __user *optlen, unsigned len); + int (*socket_getpeersec_dgram) (struct sk_buff *skb, char **secdata, u32 *seclen); int (*sk_alloc_security) (struct sock *sk, int family, gfp_t priority); void (*sk_free_security) (struct sock *sk); unsigned int (*sk_getsid) (struct sock *sk, struct flowi *fl, u8 dir); @@ -2741,10 +2742,16 @@ static inline int security_sock_rcv_skb (struct sock * sk, return security_ops->socket_sock_rcv_skb (sk, skb); } -static inline int security_socket_getpeersec(struct socket *sock, char __user *optval, - int __user *optlen, unsigned len) +static inline int security_socket_getpeersec_stream(struct socket *sock, char __user *optval, + int __user *optlen, unsigned len) { - return security_ops->socket_getpeersec(sock, optval, optlen, len); + return security_ops->socket_getpeersec_stream(sock, optval, optlen, len); +} + +static inline int security_socket_getpeersec_dgram(struct sk_buff *skb, char **secdata, + u32 *seclen) +{ + return security_ops->socket_getpeersec_dgram(skb, secdata, seclen); } static inline int security_sk_alloc(struct sock *sk, int family, gfp_t priority) @@ -2863,8 +2870,14 @@ static inline int security_sock_rcv_skb (struct sock * sk, return 0; } -static inline int security_socket_getpeersec(struct socket *sock, char __user *optval, - int __user *optlen, unsigned len) +static inline int security_socket_getpeersec_stream(struct socket *sock, char __user *optval, + int __user *optlen, unsigned len) +{ + return -ENOPROTOOPT; +} + +static inline int security_socket_getpeersec_dgram(struct sk_buff *skb, char **secdata, + u32 *seclen) { return -ENOPROTOOPT; } diff --git a/include/linux/socket.h b/include/linux/socket.h index b02dda4ee83d..9ab2ddd80221 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -150,6 +150,7 @@ __KINLINE struct cmsghdr * cmsg_nxthdr (struct msghdr *__msg, struct cmsghdr *__ #define SCM_RIGHTS 0x01 /* rw: access rights (array of int) */ #define SCM_CREDENTIALS 0x02 /* rw: struct ucred */ +#define SCM_SECURITY 0x03 /* rw: security label */ struct ucred { __u32 pid; -- cgit v1.2.3 From c4ea94ab3710eb2434abe2eab1a479c2dc01f8ac Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Mon, 20 Mar 2006 22:42:39 -0800 Subject: [DECnet]: Endian annotation and fixes for DECnet. The typedef for dn_address has been removed in favour of using __le16 or __u16 directly as appropriate. All the DECnet header files are updated accordingly. The byte ordering of dn_eth2dn() and dn_dn2eth() are both changed since just about all their callers wanted network order rather than host order, so the conversion is now done in the functions themselves. Several missed endianess conversions have been picked up during the conversion process. The nh_gw field in struct dn_fib_info has been changed from a 32 bit field to 16 bits as it ought to be. One or two cases of using htons rather than dn_htons in the routing code have been found and fixed. There are still a few warnings to fix, but this patch deals with the important cases. Signed-off-by: Steven Whitehouse Signed-off-by: Patrick Caulfield Signed-off-by: David S. Miller --- include/linux/dn.h | 44 ++++++++++++++++++++++---------------------- 1 file changed, 22 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dn.h b/include/linux/dn.h index 782cae49e64c..10b6a6fd5837 100644 --- a/include/linux/dn.h +++ b/include/linux/dn.h @@ -71,17 +71,17 @@ struct dn_naddr { - unsigned short a_len; - unsigned char a_addr[DN_MAXADDL]; + __le16 a_len; + __u8 a_addr[DN_MAXADDL]; /* Two bytes little endian */ }; struct sockaddr_dn { - unsigned short sdn_family; - unsigned char sdn_flags; - unsigned char sdn_objnum; - unsigned short sdn_objnamel; - unsigned char sdn_objname[DN_MAXOBJL]; + __u16 sdn_family; + __u8 sdn_flags; + __u8 sdn_objnum; + __le16 sdn_objnamel; + __u8 sdn_objname[DN_MAXOBJL]; struct dn_naddr sdn_add; }; #define sdn_nodeaddrl sdn_add.a_len /* Node address length */ @@ -93,38 +93,38 @@ struct sockaddr_dn * DECnet set/get DSO_CONDATA, DSO_DISDATA (optional data) structure */ struct optdata_dn { - unsigned short opt_status; /* Extended status return */ + __le16 opt_status; /* Extended status return */ #define opt_sts opt_status - unsigned short opt_optl; /* Length of user data */ - unsigned char opt_data[16]; /* User data */ + __le16 opt_optl; /* Length of user data */ + __u8 opt_data[16]; /* User data */ }; struct accessdata_dn { - unsigned char acc_accl; - unsigned char acc_acc[DN_MAXACCL]; - unsigned char acc_passl; - unsigned char acc_pass[DN_MAXACCL]; - unsigned char acc_userl; - unsigned char acc_user[DN_MAXACCL]; + __u8 acc_accl; + __u8 acc_acc[DN_MAXACCL]; + __u8 acc_passl; + __u8 acc_pass[DN_MAXACCL]; + __u8 acc_userl; + __u8 acc_user[DN_MAXACCL]; }; /* * DECnet logical link information structure */ struct linkinfo_dn { - unsigned short idn_segsize; /* Segment size for link */ - unsigned char idn_linkstate; /* Logical link state */ + __le16 idn_segsize; /* Segment size for link */ + __u8 idn_linkstate; /* Logical link state */ }; /* * Ethernet address format (for DECnet) */ union etheraddress { - unsigned char dne_addr[6]; /* Full ethernet address */ + __u8 dne_addr[6]; /* Full ethernet address */ struct { - unsigned char dne_hiord[4]; /* DECnet HIORD prefix */ - unsigned char dne_nodeaddr[2]; /* DECnet node address */ + __u8 dne_hiord[4]; /* DECnet HIORD prefix */ + __u8 dne_nodeaddr[2]; /* DECnet node address */ } dne_remote; }; @@ -133,7 +133,7 @@ union etheraddress { * DECnet physical socket address format */ struct dn_addr { - unsigned short dna_family; /* AF_DECnet */ + __le16 dna_family; /* AF_DECnet */ union etheraddress dna_netaddr; /* DECnet ethernet address */ }; -- cgit v1.2.3 From cbb042f9e1292434e3cacb90e67d8d381aeac5a9 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 20 Mar 2006 22:43:56 -0800 Subject: [NET]: Replace skb_pull/skb_postpull_rcsum with skb_pull_rcsum We're now starting to have quite a number of places that do skb_pull followed immediately by an skb_postpull_rcsum. We can merge these two operations into one function with skb_pull_rcsum. This makes sense since most pull operations on receive skb's need to update the checksum. I've decided to make this out-of-line since it is fairly big and the fast path where hardware checksums are enabled need to call csum_partial anyway. Since this is a brand new function we get to add an extra check on the len argument. As it is most callers of skb_pull ignore its return value which essentially means that there is no check on the len argument. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 75c963103b9f..613b9513f8b9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1159,12 +1159,14 @@ static inline int skb_linearize(struct sk_buff *skb, gfp_t gfp) */ static inline void skb_postpull_rcsum(struct sk_buff *skb, - const void *start, int len) + const void *start, unsigned int len) { if (skb->ip_summed == CHECKSUM_HW) skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0)); } +unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); + /** * pskb_trim_rcsum - trim received skb and update checksum * @skb: buffer to trim -- cgit v1.2.3 From 3fdadf7d27e3fbcf72930941884387d1f4936f04 Mon Sep 17 00:00:00 2001 From: Dmitry Mishin Date: Mon, 20 Mar 2006 22:45:21 -0800 Subject: [NET]: {get|set}sockopt compatibility layer This patch extends {get|set}sockopt compatibility layer in order to move protocol specific parts to their place and avoid huge universal net/compat.c file in the future. Signed-off-by: Dmitry Mishin Signed-off-by: David S. Miller --- include/linux/net.h | 4 ++++ include/linux/netfilter.h | 9 +++++++++ 2 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 28195a2d8ff0..152fa6551fd8 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -149,6 +149,10 @@ struct proto_ops { int optname, char __user *optval, int optlen); int (*getsockopt)(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); + int (*compat_setsockopt)(struct socket *sock, int level, + int optname, char __user *optval, int optlen); + int (*compat_getsockopt)(struct socket *sock, int level, + int optname, char __user *optval, int __user *optlen); int (*sendmsg) (struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t total_len); int (*recvmsg) (struct kiocb *iocb, struct socket *sock, diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 468896939843..412e52ca9720 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -80,10 +80,14 @@ struct nf_sockopt_ops int set_optmin; int set_optmax; int (*set)(struct sock *sk, int optval, void __user *user, unsigned int len); + int (*compat_set)(struct sock *sk, int optval, + void __user *user, unsigned int len); int get_optmin; int get_optmax; int (*get)(struct sock *sk, int optval, void __user *user, int *len); + int (*compat_get)(struct sock *sk, int optval, + void __user *user, int *len); /* Number of users inside set() or get(). */ unsigned int use; @@ -246,6 +250,11 @@ int nf_setsockopt(struct sock *sk, int pf, int optval, char __user *opt, int nf_getsockopt(struct sock *sk, int pf, int optval, char __user *opt, int *len); +int compat_nf_setsockopt(struct sock *sk, int pf, int optval, + char __user *opt, int len); +int compat_nf_getsockopt(struct sock *sk, int pf, int optval, + char __user *opt, int *len); + /* Packet queuing */ struct nf_queue_handler { int (*outfn)(struct sk_buff *skb, struct nf_info *info, -- cgit v1.2.3 From a4bf3902427a128455b8de299ff0918072b2e974 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 20 Mar 2006 22:50:58 -0800 Subject: [DCCP] minisock: Rename struct dccp_options to struct dccp_minisock This will later be included in struct dccp_request_sock so that we can have per connection feature negotiation state while in the 3way handshake, when we clone the DCCP_ROLE_LISTEN socket (in dccp_create_openreq_child) we'll just copy this state from dreq_minisock to dccps_minisock. Also the feature negotiation and option parsing code will mostly touch dccps_minisock, which will simplify some stuff. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/dccp.h | 43 ++++++++++++++++++++++++++----------------- 1 file changed, 26 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index e35f680f909b..676333b9fad0 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -328,21 +328,24 @@ static inline unsigned int dccp_hdr_len(const struct sk_buff *skb) #define DCCP_NDP_LIMIT 0xFFFFFF /** - * struct dccp_options - option values for a DCCP connection - * @dccpo_sequence_window - Sequence Window Feature (section 7.5.2) - * @dccpo_ccid - Congestion Control Id (CCID) (section 10) - * @dccpo_send_ack_vector - Send Ack Vector Feature (section 11.5) - * @dccpo_send_ndp_count - Send NDP Count Feature (7.7.2) + * struct dccp_minisock - Minimal DCCP connection representation + * + * Will be used to pass the state from dccp_request_sock to dccp_sock. + * + * @dccpms_sequence_window - Sequence Window Feature (section 7.5.2) + * @dccpms_ccid - Congestion Control Id (CCID) (section 10) + * @dccpms_send_ack_vector - Send Ack Vector Feature (section 11.5) + * @dccpms_send_ndp_count - Send NDP Count Feature (7.7.2) */ -struct dccp_options { - __u64 dccpo_sequence_window; - __u8 dccpo_rx_ccid; - __u8 dccpo_tx_ccid; - __u8 dccpo_send_ack_vector; - __u8 dccpo_send_ndp_count; - __u8 dccpo_ack_ratio; - struct list_head dccpo_pending; - struct list_head dccpo_conf; +struct dccp_minisock { + __u64 dccpms_sequence_window; + __u8 dccpms_rx_ccid; + __u8 dccpms_tx_ccid; + __u8 dccpms_send_ack_vector; + __u8 dccpms_send_ndp_count; + __u8 dccpms_ack_ratio; + struct list_head dccpms_pending; + struct list_head dccpms_conf; }; struct dccp_opt_conf { @@ -360,8 +363,9 @@ struct dccp_opt_pend { struct dccp_opt_conf *dccpop_sc; }; -extern void __dccp_options_init(struct dccp_options *dccpo); -extern void dccp_options_init(struct dccp_options *dccpo); +extern void __dccp_minisock_init(struct dccp_minisock *dmsk); +extern void dccp_minisock_init(struct dccp_minisock *dmsk); + extern int dccp_parse_options(struct sock *sk, struct sk_buff *skb); struct dccp_request_sock { @@ -457,7 +461,7 @@ struct dccp_sock { __u16 dccps_r_ack_ratio; unsigned long dccps_ndp_count; __u32 dccps_mss_cache; - struct dccp_options dccps_options; + struct dccp_minisock dccps_minisock; struct dccp_ackvec *dccps_hc_rx_ackvec; struct ccid *dccps_hc_rx_ccid; struct ccid *dccps_hc_tx_ccid; @@ -473,6 +477,11 @@ static inline struct dccp_sock *dccp_sk(const struct sock *sk) return (struct dccp_sock *)sk; } +static inline struct dccp_minisock *dccp_msk(const struct sock *sk) +{ + return (struct dccp_minisock *)&dccp_sk(sk)->dccps_minisock; +} + static inline int dccp_service_not_initialized(const struct sock *sk) { return dccp_sk(sk)->dccps_service == DCCP_SERVICE_INVALID_VALUE; -- cgit v1.2.3 From fdeabdefb227be9aa932f59a23ddb47e003e643e Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Mon, 20 Mar 2006 22:58:21 -0800 Subject: [BRIDGE]: netfilter inline cleanup Move nf_bridge_alloc from header file to the one place it is used and optimize it. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/netfilter_bridge.h | 27 --------------------------- 1 file changed, 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h index de4d397865ce..a75b84bb9a88 100644 --- a/include/linux/netfilter_bridge.h +++ b/include/linux/netfilter_bridge.h @@ -47,22 +47,6 @@ enum nf_br_hook_priorities { #define BRNF_BRIDGED 0x08 #define BRNF_NF_BRIDGE_PREROUTING 0x10 -static inline -struct nf_bridge_info *nf_bridge_alloc(struct sk_buff *skb) -{ - struct nf_bridge_info **nf_bridge = &(skb->nf_bridge); - - if ((*nf_bridge = kmalloc(sizeof(**nf_bridge), GFP_ATOMIC)) != NULL) { - atomic_set(&(*nf_bridge)->use, 1); - (*nf_bridge)->mask = 0; - (*nf_bridge)->physindev = (*nf_bridge)->physoutdev = NULL; -#if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) - (*nf_bridge)->netoutdev = NULL; -#endif - } - - return *nf_bridge; -} /* Only used in br_forward.c */ static inline @@ -77,17 +61,6 @@ void nf_bridge_maybe_copy_header(struct sk_buff *skb) } } -static inline -void nf_bridge_save_header(struct sk_buff *skb) -{ - int header_size = 16; - - if (skb->protocol == __constant_htons(ETH_P_8021Q)) - header_size = 18; - - memcpy(skb->nf_bridge->data, skb->data - header_size, header_size); -} - /* This is called by the IP fragmenting code and it ensures there is * enough room for the encapsulating header (if there is one). */ static inline -- cgit v1.2.3 From 5e35941d990123f155b02d5663e51a24f816b6f3 Mon Sep 17 00:00:00 2001 From: Jing Min Zhao Date: Mon, 20 Mar 2006 23:41:17 -0800 Subject: [NETFILTER]: Add H.323 conntrack/NAT helper Signed-off-by: Jing Min Zhao Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ip_conntrack.h | 2 ++ include/linux/netfilter_ipv4/ip_conntrack_h323.h | 30 ++++++++++++++++++++++++ 2 files changed, 32 insertions(+) create mode 100644 include/linux/netfilter_ipv4/ip_conntrack_h323.h (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_conntrack.h b/include/linux/netfilter_ipv4/ip_conntrack.h index 215765f043e6..f32d75c4f4cf 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack.h +++ b/include/linux/netfilter_ipv4/ip_conntrack.h @@ -29,6 +29,7 @@ union ip_conntrack_expect_proto { }; /* Add protocol helper include file here */ +#include #include #include #include @@ -37,6 +38,7 @@ union ip_conntrack_expect_proto { /* per conntrack: application helper private data */ union ip_conntrack_help { /* insert conntrack helper private data (master) here */ + struct ip_ct_h323_master ct_h323_info; struct ip_ct_pptp_master ct_pptp_info; struct ip_ct_ftp_master ct_ftp_info; struct ip_ct_irc_master ct_irc_info; diff --git a/include/linux/netfilter_ipv4/ip_conntrack_h323.h b/include/linux/netfilter_ipv4/ip_conntrack_h323.h new file mode 100644 index 000000000000..0987cea53840 --- /dev/null +++ b/include/linux/netfilter_ipv4/ip_conntrack_h323.h @@ -0,0 +1,30 @@ +#ifndef _IP_CONNTRACK_H323_H +#define _IP_CONNTRACK_H323_H + +#ifdef __KERNEL__ + +#define RAS_PORT 1719 +#define Q931_PORT 1720 +#define H323_RTP_CHANNEL_MAX 4 /* Audio, video, FAX and other */ + +/* This structure exists only once per master */ +struct ip_ct_h323_master { + + /* Original and NATed Q.931 or H.245 signal ports */ + u_int16_t sig_port[IP_CT_DIR_MAX]; + + /* Original and NATed RTP ports */ + u_int16_t rtp_port[H323_RTP_CHANNEL_MAX][IP_CT_DIR_MAX]; + + union { + /* RAS connection timeout */ + u_int32_t timeout; + + /* Next TPKT length (for separate TPKT header and data) */ + u_int16_t tpkt_len[IP_CT_DIR_MAX]; + }; +}; + +#endif + +#endif -- cgit v1.2.3 From f10b7897ee29649fa7f0ccdc8d859ccd6ce7dbfd Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 25 Jan 2006 22:34:01 +1100 Subject: [CRYPTO] api: Align tfm context as wide as possible Since tfm contexts can contain arbitrary types we should provide at least natural alignment (__attribute__ ((__aligned__))) for them. In particular, this is needed on the Xscale which is a 32-bit architecture with a u64 type that requires 64-bit alignment. This problem was reported by Ronen Shitrit. The crypto_tfm structure's size was 44 bytes on 32-bit architectures and 80 bytes on 64-bit architectures. So adding this requirement only means that we have to add an extra 4 bytes on 32-bit architectures. On i386 the natural alignment is 16 bytes which also benefits the VIA Padlock as it no longer has to manually align its context structure to 128 bits. Signed-off-by: Herbert Xu --- include/linux/crypto.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index d88bf8aa8b47..0ab1bc1152ca 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -229,6 +229,8 @@ struct crypto_tfm { } crt_u; struct crypto_alg *__crt_alg; + + char __crt_ctx[] __attribute__ ((__aligned__)); }; /* @@ -301,7 +303,13 @@ static inline unsigned int crypto_tfm_alg_alignmask(struct crypto_tfm *tfm) static inline void *crypto_tfm_ctx(struct crypto_tfm *tfm) { - return (void *)&tfm[1]; + return tfm->__crt_ctx; +} + +static inline unsigned int crypto_tfm_ctx_alignment(void) +{ + struct crypto_tfm *tfm; + return __alignof__(tfm->__crt_ctx); } /* -- cgit v1.2.3 From 30afc84cf7325e88fb9746340eba3c161080ff49 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sat, 18 Mar 2006 18:40:14 +0900 Subject: [SCSI] libata: implement minimal transport template for ->eh_timed_out SCSI midlayer has moved hostt->eh_timed_out to transport template. As libata doesn't need full-blown transport support yet, implement minimal transport for libata. No transport class or whatsoever, just empty transport template with ->eh_timed_out hook. Signed-off-by: Tejun Heo Signed-off-by: James Bottomley --- include/linux/libata.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 239408ecfddf..204c37a55f06 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -508,7 +508,6 @@ extern void ata_host_set_remove(struct ata_host_set *host_set); extern int ata_scsi_detect(struct 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 *)); -extern enum scsi_eh_timer_return ata_scsi_timed_out(struct scsi_cmnd *cmd); extern int ata_scsi_error(struct Scsi_Host *host); extern void ata_eh_qc_complete(struct ata_queued_cmd *qc); extern void ata_eh_qc_retry(struct ata_queued_cmd *qc); -- cgit v1.2.3 From 4de151d8cd2553e7e89044ab5d72fcad4eb04afb Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 22 Mar 2006 00:13:35 +0100 Subject: It's UTF-8 Fix some comments to "UTF-8". Signed-off-by: Alexey Dobriyan Signed-off-by: Adrian Bunk --- include/linux/msdos_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/msdos_fs.h b/include/linux/msdos_fs.h index e933e2a355ad..8bcd9450d926 100644 --- a/include/linux/msdos_fs.h +++ b/include/linux/msdos_fs.h @@ -199,7 +199,7 @@ struct fat_mount_options { sys_immutable:1, /* set = system files are immutable */ dotsOK:1, /* set = hidden and system files are named '.filename' */ isvfat:1, /* 0=no vfat long filename support, 1=vfat support */ - utf8:1, /* Use of UTF8 character set (Default) */ + utf8:1, /* Use of UTF-8 character set (Default) */ unicode_xlate:1, /* create escape sequences for unhandled Unicode */ numtail:1, /* Does first alias have a numeric '~1' type tail? */ atari:1, /* Use Atari GEMDOS variation of MS-DOS fs */ -- cgit v1.2.3 From 116f232b3794a8b6ebde21aef5004b18cc1cfa86 Mon Sep 17 00:00:00 2001 From: Rytchkov Alexey Date: Wed, 22 Mar 2006 00:58:53 +0100 Subject: fixed path to moved file in include/linux/device.h Signed-off-by: Adrian Bunk --- include/linux/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 5b595fdfb672..10c1693a2529 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -399,7 +399,7 @@ extern struct device * get_device(struct device * dev); extern void put_device(struct device * dev); -/* drivers/base/power.c */ +/* drivers/base/power/shutdown.c */ extern void device_shutdown(void); -- cgit v1.2.3 From f59b0cf8a3a39b75e580066c6a9aeabd97ec2743 Mon Sep 17 00:00:00 2001 From: Albert Lee Date: Thu, 16 Mar 2006 17:59:22 +0800 Subject: [PATCH] libata-dev: Remove ATA_PROT_PIO_MULT Remove the ATA_PROT_PIO_MULT protocol. Signed-off-by: Albert Lee Signed-off-by: Jeff Garzik --- include/linux/ata.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index b02a16c435e7..6b188b3b61dd 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -204,7 +204,6 @@ enum ata_tf_protocols { ATA_PROT_UNKNOWN, /* unknown/invalid */ ATA_PROT_NODATA, /* no data */ ATA_PROT_PIO, /* PIO single sector */ - ATA_PROT_PIO_MULT, /* PIO multiple sector */ ATA_PROT_DMA, /* DMA */ ATA_PROT_ATAPI, /* packet command, PIO data xfer*/ ATA_PROT_ATAPI_NODATA, /* packet command, no data */ -- cgit v1.2.3 From e46834cd2ddb1e2941806cb8fec60fb6bdd2ec29 Mon Sep 17 00:00:00 2001 From: Brian King Date: Fri, 17 Mar 2006 17:04:03 -0600 Subject: [PATCH] libata: Add some dummy noop functions Add some dummy noop functions for use by libata clients that do not need to do anything. Future SAS patches will utilize these functions. Signed-off-by: Brian King 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 239408ecfddf..17e5a719c72b 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -543,6 +543,7 @@ extern void ata_port_stop (struct ata_port *ap); extern void ata_host_stop (struct ata_host_set *host_set); extern irqreturn_t ata_interrupt (int irq, void *dev_instance, struct pt_regs *regs); extern void ata_qc_prep(struct ata_queued_cmd *qc); +extern void ata_noop_qc_prep(struct ata_queued_cmd *qc); extern unsigned int ata_qc_issue_prot(struct ata_queued_cmd *qc); extern void ata_sg_init_one(struct ata_queued_cmd *qc, void *buf, unsigned int buflen); -- cgit v1.2.3 From b6782728d703fa3f0e5478a8b89e49ea10b1fdd0 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Tue, 21 Mar 2006 15:52:49 +0000 Subject: [PATCH] libata: Add the useful macros/constants needed for merging PATA stuff HPA presence/enabled HPA commands Also add ata_id_is_cfa() as that is needed to detect and handle CF cards which currently we reject. Signed-off-by: Jeff Garzik --- include/linux/ata.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index 6b188b3b61dd..312a2c0c64e6 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -146,6 +146,8 @@ enum { ATA_CMD_STANDBYNOW1 = 0xE0, ATA_CMD_IDLEIMMEDIATE = 0xE1, ATA_CMD_INIT_DEV_PARAMS = 0x91, + ATA_CMD_READ_NATIVE_MAX = 0xF8, + ATA_CMD_READ_NATIVE_MAX_EXT = 0x27, /* SETFEATURES stuff */ SETFEATURES_XFER = 0x03, @@ -246,18 +248,22 @@ struct ata_taskfile { }; #define ata_id_is_ata(id) (((id)[0] & (1 << 15)) == 0) +#define ata_id_is_cfa(id) ((id)[0] == 0x848A) #define ata_id_is_sata(id) ((id)[93] == 0) #define ata_id_rahead_enabled(id) ((id)[85] & (1 << 6)) #define ata_id_wcache_enabled(id) ((id)[85] & (1 << 5)) +#define ata_id_hpa_enabled(id) ((id)[85] & (1 << 10)) #define ata_id_has_fua(id) ((id)[84] & (1 << 6)) #define ata_id_has_flush(id) ((id)[83] & (1 << 12)) #define ata_id_has_flush_ext(id) ((id)[83] & (1 << 13)) #define ata_id_has_lba48(id) ((id)[83] & (1 << 10)) +#define ata_id_has_hpa(id) ((id)[82] & (1 << 10)) #define ata_id_has_wcache(id) ((id)[82] & (1 << 5)) #define ata_id_has_pm(id) ((id)[82] & (1 << 3)) #define ata_id_has_lba(id) ((id)[49] & (1 << 9)) #define ata_id_has_dma(id) ((id)[49] & (1 << 8)) #define ata_id_removeable(id) ((id)[0] & (1 << 7)) +#define ata_id_has_dword_io(id) ((id)[50] & (1 << 0)) #define ata_id_u32(id,n) \ (((u32) (id)[(n) + 1] << 16) | ((u32) (id)[(n)])) #define ata_id_u64(id,n) \ -- cgit v1.2.3 From 17bb34a3c548c4fd2a7c859123a631f97c2af09f Mon Sep 17 00:00:00 2001 From: Jeff Garzik Date: Tue, 21 Mar 2006 21:29:21 -0500 Subject: [libata] add prototypes for helpers Add prototypes for stuff recently added by Alan. --- include/linux/libata.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 17e5a719c72b..d81cecdda4f3 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -502,6 +502,7 @@ 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); extern int ata_pci_device_suspend(struct pci_dev *pdev, pm_message_t state); extern int ata_pci_device_resume(struct pci_dev *pdev); +extern int ata_pci_clear_simplex(struct pci_dev *pdev); #endif /* CONFIG_PCI */ extern int ata_device_add(const struct ata_probe_ent *ent); extern void ata_host_set_remove(struct ata_host_set *host_set); @@ -610,7 +611,7 @@ 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, const struct pci_bits *bits); - +extern unsigned long ata_pci_default_filter(const struct ata_port *, struct ata_device *, unsigned long); #endif /* CONFIG_PCI */ -- cgit v1.2.3 From 89bbfc95d65839d6ae23ddab8a3cc5af4ae88383 Mon Sep 17 00:00:00 2001 From: Shaun Pereira Date: Tue, 21 Mar 2006 23:58:08 -0800 Subject: [NET]: allow 32 bit socket ioctl in 64 bit kernel Since the register_ioctl32_conversion() patch in the kernel is now obsolete, provide another method to allow 32 bit user space ioctls to reach the kernel. Signed-off-by: Shaun Pereira Acked-by: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: David S. Miller --- include/linux/net.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 152fa6551fd8..84a490e5f0a1 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -143,6 +143,8 @@ struct proto_ops { struct poll_table_struct *wait); int (*ioctl) (struct socket *sock, unsigned int cmd, unsigned long arg); + int (*compat_ioctl) (struct socket *sock, unsigned int cmd, + unsigned long arg); int (*listen) (struct socket *sock, int len); int (*shutdown) (struct socket *sock, int flags); int (*setsockopt)(struct socket *sock, int level, @@ -251,6 +253,8 @@ SOCKCALL_UWRAP(name, poll, (struct file *file, struct socket *sock, struct poll_ (file, sock, wait)) \ SOCKCALL_WRAP(name, ioctl, (struct socket *sock, unsigned int cmd, \ unsigned long arg), (sock, cmd, arg)) \ +SOCKCALL_WRAP(name, compat_ioctl, (struct socket *sock, unsigned int cmd, \ + unsigned long arg), (sock, cmd, arg)) \ SOCKCALL_WRAP(name, listen, (struct socket *sock, int len), (sock, len)) \ SOCKCALL_WRAP(name, shutdown, (struct socket *sock, int flags), (sock, flags)) \ SOCKCALL_WRAP(name, setsockopt, (struct socket *sock, int level, int optname, \ @@ -275,6 +279,7 @@ static const struct proto_ops name##_ops = { \ .getname = __lock_##name##_getname, \ .poll = __lock_##name##_poll, \ .ioctl = __lock_##name##_ioctl, \ + .compat_ioctl = __lock_##name##_compat_ioctl, \ .listen = __lock_##name##_listen, \ .shutdown = __lock_##name##_shutdown, \ .setsockopt = __lock_##name##_setsockopt, \ @@ -283,6 +288,7 @@ static const struct proto_ops name##_ops = { \ .recvmsg = __lock_##name##_recvmsg, \ .mmap = __lock_##name##_mmap, \ }; + #endif #define MODULE_ALIAS_NETPROTO(proto) \ -- cgit v1.2.3 From a64b7b936dcd926ace745c07c14f45ecfaddb034 Mon Sep 17 00:00:00 2001 From: Shaun Pereira Date: Wed, 22 Mar 2006 00:01:31 -0800 Subject: [X25]: allow ITU-T DTE facilities for x25 Allows use of the optional user facility to insert ITU-T (http://www.itu.int/ITU-T/) specified DTE facilities in call set-up x25 packets. This feature is optional; no facilities will be added if the ioctl is not used, and call setup packet remains the same as before. If the ioctls provided by the patch are used, then a facility marker will be added to the x25 packet header so that the called dte address extension facility can be differentiated from other types of facilities (as described in the ITU-T X.25 recommendation) that are also allowed in the x25 packet header. Facility markers are made up of two octets, and may be present in the x25 packet headers of call-request, incoming call, call accepted, clear request, and clear indication packets. The first of the two octets represents the facility code field and is set to zero by this patch. The second octet of the marker represents the facility parameter field and is set to 0x0F because the marker will be inserted before ITU-T type DTE facilities. Since according to ITU-T X.25 Recommendation X.25(10/96)- 7.1 "All networks will support the facility markers with a facility parameter field set to all ones or to 00001111", therefore this patch should work with all x.25 networks. While there are many ITU-T DTE facilities, this patch implements only the called and calling address extension, with placeholders in the x25_dte_facilities structure for the rest of the facilities. Testing: This patch was tested using a cisco xot router connected on its serial ports to an X.25 network, and on its lan ports to a host running an xotd daemon. It is also possible to test this patch using an xotd daemon and an x25tap patch, where the xotd daemons work back-to-back without actually using an x.25 network. See www.fyonne.net for details on how to do this. Signed-off-by: Shaun Pereira Acked-by: Andrew Hendry Signed-off-by: Andrew Morton Signed-off-by: David S. Miller --- include/linux/x25.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/x25.h b/include/linux/x25.h index 16d44931afa0..d035e4e87d07 100644 --- a/include/linux/x25.h +++ b/include/linux/x25.h @@ -11,6 +11,8 @@ #ifndef X25_KERNEL_H #define X25_KERNEL_H +#include + #define SIOCX25GSUBSCRIP (SIOCPROTOPRIVATE + 0) #define SIOCX25SSUBSCRIP (SIOCPROTOPRIVATE + 1) #define SIOCX25GFACILITIES (SIOCPROTOPRIVATE + 2) @@ -21,6 +23,8 @@ #define SIOCX25SCUDMATCHLEN (SIOCPROTOPRIVATE + 7) #define SIOCX25CALLACCPTAPPRV (SIOCPROTOPRIVATE + 8) #define SIOCX25SENDCALLACCPT (SIOCPROTOPRIVATE + 9) +#define SIOCX25GDTEFACILITIES (SIOCPROTOPRIVATE + 10) +#define SIOCX25SDTEFACILITIES (SIOCPROTOPRIVATE + 11) /* * Values for {get,set}sockopt. @@ -77,6 +81,8 @@ struct x25_subscrip_struct { #define X25_MASK_PACKET_SIZE 0x04 #define X25_MASK_WINDOW_SIZE 0x08 +#define X25_MASK_CALLING_AE 0x10 +#define X25_MASK_CALLED_AE 0x20 /* @@ -98,6 +104,26 @@ struct x25_facilities { unsigned int reverse; }; +/* +* ITU DTE facilities +* Only the called and calling address +* extension are currently implemented. +* The rest are in place to avoid the struct +* changing size if someone needs them later +*/ + +struct x25_dte_facilities { + __u16 delay_cumul; + __u16 delay_target; + __u16 delay_max; + __u8 min_throughput; + __u8 expedited; + __u8 calling_len; + __u8 called_len; + __u8 calling_ae[20]; + __u8 called_ae[20]; +}; + /* * Call User Data structure. */ -- cgit v1.2.3 From 9d2f928ddf64ca0361562e30faf584cd33055c60 Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Wed, 22 Mar 2006 10:53:19 +0100 Subject: [PATCH] Intruduce DMA_28BIT_MASK This patch introduces the DMA_28BIT_MASK constant in dma-mapping.h ALSA drivers using this mask are changed to use the new constant. Signed-off-by: Tobias Klauser Acked-by: Takashi Iwai Acked-by: Jaroslav Kysela --- include/linux/dma-mapping.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 2d80cc761a15..a8731062a74c 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -20,6 +20,7 @@ enum dma_data_direction { #define DMA_31BIT_MASK 0x000000007fffffffULL #define DMA_30BIT_MASK 0x000000003fffffffULL #define DMA_29BIT_MASK 0x000000001fffffffULL +#define DMA_28BIT_MASK 0x000000000fffffffULL #include -- cgit v1.2.3 From 4024ce5e0f396447cc1e07fd65c2a1d056b066bb Mon Sep 17 00:00:00 2001 From: Joe Korty Date: Wed, 22 Mar 2006 00:07:43 -0800 Subject: [PATCH] rtc.h broke strace(1) builds Git patch 52dfa9a64cfb3dd01fa1ee1150d589481e54e28e [PATCH] move rtc_interrupt() prototype to rtc.h broke strace(1) builds. The below moves the kernel-only additions lower, under the already provided #ifdef __KERNEL__ statement. Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rtc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 0b2ba67ff13c..b739ac1f7ca0 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -11,8 +11,6 @@ #ifndef _LINUX_RTC_H_ #define _LINUX_RTC_H_ -#include - /* * The struct used to pass data via the following ioctl. Similar to the * struct tm in , but it needs to be here so that the kernel @@ -95,6 +93,8 @@ struct rtc_pll_info { #ifdef __KERNEL__ +#include + typedef struct rtc_task { void (*func)(void *private_data); void *private_data; -- cgit v1.2.3 From 8d438f96d2b8eade6cbcd8adfc22dae6f5cbd6c0 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 22 Mar 2006 00:07:59 -0800 Subject: [PATCH] mm: PageLRU no testset PG_lru is protected by zone->lru_lock. It does not need TestSet/TestClear operations. Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index d52999c43336..58856c823f8b 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -239,10 +239,9 @@ extern void __mod_page_state_offset(unsigned long offset, unsigned long delta); #define __ClearPageDirty(page) __clear_bit(PG_dirty, &(page)->flags) #define TestClearPageDirty(page) test_and_clear_bit(PG_dirty, &(page)->flags) -#define SetPageLRU(page) set_bit(PG_lru, &(page)->flags) #define PageLRU(page) test_bit(PG_lru, &(page)->flags) -#define TestSetPageLRU(page) test_and_set_bit(PG_lru, &(page)->flags) -#define TestClearPageLRU(page) test_and_clear_bit(PG_lru, &(page)->flags) +#define SetPageLRU(page) set_bit(PG_lru, &(page)->flags) +#define ClearPageLRU(page) clear_bit(PG_lru, &(page)->flags) #define PageActive(page) test_bit(PG_active, &(page)->flags) #define SetPageActive(page) set_bit(PG_active, &(page)->flags) -- cgit v1.2.3 From 4c84cacfa424264f7ad5287298d3ea4a3e935278 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 22 Mar 2006 00:08:00 -0800 Subject: [PATCH] mm: PageActive no testset PG_active is protected by zone->lru_lock, it does not need TestSet/TestClear operations. Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 58856c823f8b..5d1e7bd85107 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -246,8 +246,6 @@ extern void __mod_page_state_offset(unsigned long offset, unsigned long delta); #define PageActive(page) test_bit(PG_active, &(page)->flags) #define SetPageActive(page) set_bit(PG_active, &(page)->flags) #define ClearPageActive(page) clear_bit(PG_active, &(page)->flags) -#define TestClearPageActive(page) test_and_clear_bit(PG_active, &(page)->flags) -#define TestSetPageActive(page) test_and_set_bit(PG_active, &(page)->flags) #define PageSlab(page) test_bit(PG_slab, &(page)->flags) #define SetPageSlab(page) set_bit(PG_slab, &(page)->flags) -- cgit v1.2.3 From 674539115cc88473f623581e1d53c0e2ecef2179 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 22 Mar 2006 00:08:00 -0800 Subject: [PATCH] mm: less atomic ops In the page release paths, we can be sure that nobody will mess with our page->flags because the refcount has dropped to 0. So no need for atomic operations here. Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_inline.h | 2 +- include/linux/page-flags.h | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 8ac854f7f190..3b6723dfaff3 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -32,7 +32,7 @@ del_page_from_lru(struct zone *zone, struct page *page) { list_del(&page->lru); if (PageActive(page)) { - ClearPageActive(page); + __ClearPageActive(page); zone->nr_active--; } else { zone->nr_inactive--; diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 5d1e7bd85107..da71d63df465 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -242,10 +242,12 @@ extern void __mod_page_state_offset(unsigned long offset, unsigned long delta); #define PageLRU(page) test_bit(PG_lru, &(page)->flags) #define SetPageLRU(page) set_bit(PG_lru, &(page)->flags) #define ClearPageLRU(page) clear_bit(PG_lru, &(page)->flags) +#define __ClearPageLRU(page) __clear_bit(PG_lru, &(page)->flags) #define PageActive(page) test_bit(PG_active, &(page)->flags) #define SetPageActive(page) set_bit(PG_active, &(page)->flags) #define ClearPageActive(page) clear_bit(PG_active, &(page)->flags) +#define __ClearPageActive(page) __clear_bit(PG_active, &(page)->flags) #define PageSlab(page) test_bit(PG_slab, &(page)->flags) #define SetPageSlab(page) set_bit(PG_slab, &(page)->flags) -- cgit v1.2.3 From 5e9dace8d386def04219134d7160e8a778824764 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 22 Mar 2006 00:08:01 -0800 Subject: [PATCH] mm: page_alloc less atomics More atomic operation removal from page allocator Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index da71d63df465..76c7ffdd0424 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -328,8 +328,8 @@ extern void __mod_page_state_offset(unsigned long offset, unsigned long delta); #define TestClearPageReclaim(page) test_and_clear_bit(PG_reclaim, &(page)->flags) #define PageCompound(page) test_bit(PG_compound, &(page)->flags) -#define SetPageCompound(page) set_bit(PG_compound, &(page)->flags) -#define ClearPageCompound(page) clear_bit(PG_compound, &(page)->flags) +#define __SetPageCompound(page) __set_bit(PG_compound, &(page)->flags) +#define __ClearPageCompound(page) __clear_bit(PG_compound, &(page)->flags) #ifdef CONFIG_SWAP #define PageSwapCache(page) test_bit(PG_swapcache, &(page)->flags) -- cgit v1.2.3 From f205b2fe62d321403525065a4cb31b6bff1bbe53 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 22 Mar 2006 00:08:02 -0800 Subject: [PATCH] mm: slab less atomics Atomic operation removal from slab Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 76c7ffdd0424..8cef69d462f2 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -250,10 +250,8 @@ extern void __mod_page_state_offset(unsigned long offset, unsigned long delta); #define __ClearPageActive(page) __clear_bit(PG_active, &(page)->flags) #define PageSlab(page) test_bit(PG_slab, &(page)->flags) -#define SetPageSlab(page) set_bit(PG_slab, &(page)->flags) -#define ClearPageSlab(page) clear_bit(PG_slab, &(page)->flags) -#define TestClearPageSlab(page) test_and_clear_bit(PG_slab, &(page)->flags) -#define TestSetPageSlab(page) test_and_set_bit(PG_slab, &(page)->flags) +#define __SetPageSlab(page) __set_bit(PG_slab, &(page)->flags) +#define __ClearPageSlab(page) __clear_bit(PG_slab, &(page)->flags) #ifdef CONFIG_HIGHMEM #define PageHighMem(page) is_highmem(page_zone(page)) -- cgit v1.2.3 From 7c8ee9a86340db686cd4314e9944dc9b6111bda9 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 22 Mar 2006 00:08:03 -0800 Subject: [PATCH] mm: simplify vmscan vs release refcounting The VM has an interesting race where a page refcount can drop to zero, but it is still on the LRU lists for a short time. This was solved by testing a 0->1 refcount transition when picking up pages from the LRU, and dropping the refcount in that case. Instead, use atomic_add_unless to ensure we never pick up a 0 refcount page from the LRU, thus a 0 refcount page will never have its refcount elevated until it is allocated again. Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 498ff8778fb6..b12d5c76420d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -301,17 +301,20 @@ struct page { * Drop a ref, return true if the logical refcount fell to zero (the page has * no users) */ -#define put_page_testzero(p) \ - ({ \ - BUG_ON(atomic_read(&(p)->_count) == -1);\ - atomic_add_negative(-1, &(p)->_count); \ - }) +static inline int put_page_testzero(struct page *page) +{ + BUG_ON(atomic_read(&page->_count) == -1); + return atomic_add_negative(-1, &page->_count); +} /* - * Grab a ref, return true if the page previously had a logical refcount of - * zero. ie: returns true if we just grabbed an already-deemed-to-be-free page + * Try to grab a ref unless the page has a refcount of zero, return false if + * that is the case. */ -#define get_page_testone(p) atomic_inc_and_test(&(p)->_count) +static inline int get_page_unless_zero(struct page *page) +{ + return atomic_add_unless(&page->_count, 1, -1); +} #define set_page_count(p,v) atomic_set(&(p)->_count, (v) - 1) #define __put_page(p) atomic_dec(&(p)->_count) -- cgit v1.2.3 From 8dc04efbfb3c08a08fb7a3b97348d5d561b26ae2 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 22 Mar 2006 00:08:03 -0800 Subject: [PATCH] mm: de-skew page refcounting atomic_add_unless (atomic_inc_not_zero) no longer requires an offset refcount to function correctly. Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 19 +++++-------------- 1 file changed, 5 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index b12d5c76420d..9bbddf228cd9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -286,15 +286,6 @@ struct page { * * Also, many kernel routines increase the page count before a critical * routine so they can be sure the page doesn't go away from under them. - * - * Since 2.6.6 (approx), a free page has ->_count = -1. This is so that we - * can use atomic_add_negative(-1, page->_count) to detect when the page - * becomes free and so that we can also use atomic_inc_and_test to atomically - * detect when we just tried to grab a ref on a page which some other CPU has - * already deemed to be freeable. - * - * NO code should make assumptions about this internal detail! Use the provided - * macros which retain the old rules: page_count(page) == 0 is a free page. */ /* @@ -303,8 +294,8 @@ struct page { */ static inline int put_page_testzero(struct page *page) { - BUG_ON(atomic_read(&page->_count) == -1); - return atomic_add_negative(-1, &page->_count); + BUG_ON(atomic_read(&page->_count) == 0); + return atomic_dec_and_test(&page->_count); } /* @@ -313,10 +304,10 @@ static inline int put_page_testzero(struct page *page) */ static inline int get_page_unless_zero(struct page *page) { - return atomic_add_unless(&page->_count, 1, -1); + return atomic_inc_not_zero(&page->_count); } -#define set_page_count(p,v) atomic_set(&(p)->_count, (v) - 1) +#define set_page_count(p,v) atomic_set(&(p)->_count, (v)) #define __put_page(p) atomic_dec(&(p)->_count) extern void FASTCALL(__page_cache_release(struct page *)); @@ -325,7 +316,7 @@ static inline int page_count(struct page *page) { if (PageCompound(page)) page = (struct page *)page_private(page); - return atomic_read(&page->_count) + 1; + return atomic_read(&page->_count); } static inline void get_page(struct page *page) -- cgit v1.2.3 From 8dfcc9ba27e2ed257e5de9539f7f03e57c2c0e33 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 22 Mar 2006 00:08:05 -0800 Subject: [PATCH] mm: split highorder pages Have an explicit mm call to split higher order pages into individual pages. Should help to avoid bugs and be more explicit about the code's intention. Signed-off-by: Nick Piggin Cc: Russell King Cc: David Howells Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: Paul Mundt Cc: "David S. Miller" Cc: Chris Zankel Signed-off-by: Yoichi Yuasa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9bbddf228cd9..e67980654c49 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -328,6 +328,12 @@ static inline void get_page(struct page *page) void put_page(struct page *page); +#ifdef CONFIG_MMU +void split_page(struct page *page, unsigned int order); +#else +static inline void split_page(struct page *page, unsigned int order) {} +#endif + /* * Multiple processes may "see" the same page. E.g. for untouched * mappings of /dev/null, all processes see the same page full of -- cgit v1.2.3 From 9d41415221214ca4820b9464dfa548e2f20e7dd5 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 22 Mar 2006 00:08:06 -0800 Subject: [PATCH] mm: page_state comment more Clarify that preemption needs to be guarded against with the __xxx_page_state functions. Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 8cef69d462f2..9ea629c02a4b 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -86,8 +86,9 @@ * - The __xxx_page_state variants can be used safely when interrupts are * disabled. * - The __xxx_page_state variants can be used if the field is only - * modified from process context, or only modified from interrupt context. - * In this case, the field should be commented here. + * modified from process context and protected from preemption, or only + * modified from interrupt context. In this case, the field should be + * commented here. */ struct page_state { unsigned long nr_dirty; /* Dirty writeable pages */ -- cgit v1.2.3 From b50ec7d8070ae7a39fe78e65a8812bbc3ca2f7ac Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Wed, 22 Mar 2006 00:08:09 -0800 Subject: [PATCH] kcalloc(): INT_MAX -> ULONG_MAX Since size_t has the same size as a long on all architectures, it's enough for overflow checks to check against ULONG_MAX. This change could allow a compiler better optimization (especially in the n=1 case). The practical effect seems to be positive, but quite small: text data bss dec hex filename 21762380 5859870 1848928 29471178 1c1b1ca vmlinux-old 21762211 5859870 1848928 29471009 1c1b121 vmlinux-patched Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 8cf52939d0ab..38bed95dda7a 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -118,7 +118,7 @@ extern void *kzalloc(size_t, gfp_t); */ static inline void *kcalloc(size_t n, size_t size, gfp_t flags) { - if (n != 0 && size > INT_MAX / n) + if (n != 0 && size > ULONG_MAX / n) return NULL; return kzalloc(n * size, flags); } -- cgit v1.2.3 From ac2b898ca6fb06196a26869c23b66afe7944e52e Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 22 Mar 2006 00:08:15 -0800 Subject: [PATCH] slab: Remove SLAB_NO_REAP option SLAB_NO_REAP is documented as an option that will cause this slab not to be reaped under memory pressure. However, that is not what happens. The only thing that SLAB_NO_REAP controls at the moment is the reclaim of the unused slab elements that were allocated in batch in cache_reap(). Cache_reap() is run every few seconds independently of memory pressure. Could we remove the whole thing? Its only used by three slabs anyways and I cannot find a reason for having this option. There is an additional problem with SLAB_NO_REAP. If set then the recovery of objects from alien caches is switched off. Objects not freed on the same node where they were initially allocated will only be reused if a certain amount of objects accumulates from one alien node (not very likely) or if the cache is explicitly shrunk. (Strangely __cache_shrink does not check for SLAB_NO_REAP) Getting rid of SLAB_NO_REAP fixes the problems with alien cache freeing. Signed-off-by: Christoph Lameter Cc: Pekka Enberg Cc: Manfred Spraul Cc: Mark Fasheh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 38bed95dda7a..2b28c849d75a 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -38,7 +38,6 @@ typedef struct kmem_cache kmem_cache_t; #define SLAB_DEBUG_INITIAL 0x00000200UL /* Call constructor (as verifier) */ #define SLAB_RED_ZONE 0x00000400UL /* Red zone objs in a cache */ #define SLAB_POISON 0x00000800UL /* Poison objects */ -#define SLAB_NO_REAP 0x00001000UL /* never reap from the cache */ #define SLAB_HWCACHE_ALIGN 0x00002000UL /* align objs on a h/w cache lines */ #define SLAB_CACHE_DMA 0x00004000UL /* use GFP_DMA memory */ #define SLAB_MUST_HWCACHE_ALIGN 0x00008000UL /* force alignment */ -- cgit v1.2.3 From 78eef01b0fae087c5fadbd85dd4fe2918c3a015f Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 22 Mar 2006 00:08:16 -0800 Subject: [PATCH] on_each_cpu(): disable local interrupts When on_each_cpu() runs the callback on other CPUs, it runs with local interrupts disabled. So we should run the function with local interrupts disabled on this CPU, too. And do the same for UP, so the callback is run in the same environment on both UP and SMP. (strictly it should do preempt_disable() too, but I think local_irq_disable is sufficiently equivalent). Also uninlines on_each_cpu(). softirq.c was the most appropriate file I could find, but it doesn't seem to justify creating a new file. Oh, and fix up that comment over (under?) x86's smp_call_function(). It drives me nuts. Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/smp.h | 23 +++++++++-------------- 1 file changed, 9 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index 44153fdf73fc..d699a16b0cb2 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -52,23 +52,12 @@ extern void smp_cpus_done(unsigned int max_cpus); /* * Call a function on all other processors */ -extern int smp_call_function (void (*func) (void *info), void *info, - int retry, int wait); +int smp_call_function(void(*func)(void *info), void *info, int retry, int wait); /* * Call a function on all processors */ -static inline int on_each_cpu(void (*func) (void *info), void *info, - int retry, int wait) -{ - int ret = 0; - - preempt_disable(); - ret = smp_call_function(func, info, retry, wait); - func(info); - preempt_enable(); - return ret; -} +int on_each_cpu(void (*func) (void *info), void *info, int retry, int wait); #define MSG_ALL_BUT_SELF 0x8000 /* Assume <32768 CPU's */ #define MSG_ALL 0x8001 @@ -94,7 +83,13 @@ void smp_prepare_boot_cpu(void); #define raw_smp_processor_id() 0 #define hard_smp_processor_id() 0 #define smp_call_function(func,info,retry,wait) ({ 0; }) -#define on_each_cpu(func,info,retry,wait) ({ func(info); 0; }) +#define on_each_cpu(func,info,retry,wait) \ + ({ \ + local_irq_disable(); \ + func(info); \ + local_irq_enable(); \ + 0; \ + }) static inline void smp_send_reschedule(int cpu) { } #define num_booting_cpus() 1 #define smp_prepare_boot_cpu() do {} while (0) -- cgit v1.2.3 From 69e05944af39fc6c97b09380c8721e38433bd828 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 22 Mar 2006 00:08:19 -0800 Subject: [PATCH] vmscan: use unsigned longs Turn basically everything in vmscan.c into `unsigned long'. This is to avoid the possibility that some piece of code in there might decide to operate upon more than 4G (or even 2G) of pages in one hit. This might be silly, but we'll need it one day. Cc: Christoph Lameter Cc: Nick Piggin Signed-off-by: Rafael J. Wysocki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- include/linux/swap.h | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index e67980654c49..1850cf8bad64 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1046,7 +1046,7 @@ int in_gate_area_no_task(unsigned long addr); int drop_caches_sysctl_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); -int shrink_slab(unsigned long scanned, gfp_t gfp_mask, +unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask, unsigned long lru_pages); void drop_pagecache(void); void drop_slab(void); diff --git a/include/linux/swap.h b/include/linux/swap.h index d572b19afb7d..3dc6c89c49b8 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -172,8 +172,8 @@ 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 **, gfp_t); -extern int shrink_all_memory(int); +extern unsigned long try_to_free_pages(struct zone **, gfp_t); +extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; #ifdef CONFIG_NUMA @@ -190,11 +190,11 @@ static inline int zone_reclaim(struct zone *z, gfp_t mask, unsigned int order) #ifdef CONFIG_MIGRATION extern int isolate_lru_page(struct page *p); -extern int putback_lru_pages(struct list_head *l); +extern unsigned long putback_lru_pages(struct list_head *l); extern int migrate_page(struct page *, struct page *); extern void migrate_page_copy(struct page *, struct page *); extern int migrate_page_remove_references(struct page *, struct page *, int); -extern int migrate_pages(struct list_head *l, struct list_head *t, +extern unsigned long migrate_pages(struct list_head *l, struct list_head *t, struct list_head *moved, struct list_head *failed); extern int fail_migrate_page(struct page *, struct page *); #else -- cgit v1.2.3 From 0f8053a509ceba4a077a50ea7b77039b5559b428 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 22 Mar 2006 00:08:33 -0800 Subject: [PATCH] mm: make __put_page internal Remove __put_page from outside the core mm/. It is dangerous because it does not handle compound pages nicely, and misses 1->0 transitions. If a user later appears that really needs the extra speed we can reevaluate. Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1850cf8bad64..9b3cdfc8046d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -308,7 +308,6 @@ static inline int get_page_unless_zero(struct page *page) } #define set_page_count(p,v) atomic_set(&(p)->_count, (v)) -#define __put_page(p) atomic_dec(&(p)->_count) extern void FASTCALL(__page_cache_release(struct page *)); -- cgit v1.2.3 From 84097518d1ecd2330f9488e4c2d09953a3340e74 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 22 Mar 2006 00:08:34 -0800 Subject: [PATCH] mm: nommu use compound pages Now that compound page handling is properly fixed in the VM, move nommu over to using compound pages rather than rolling their own refcounting. nommu vm page refcounting is broken anyway, but there is no need to have divergent code in the core VM now, nor when it gets fixed. Signed-off-by: Nick Piggin Cc: David Howells (Needs testing, please). Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9b3cdfc8046d..3d84b7a35e0d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -327,11 +327,7 @@ static inline void get_page(struct page *page) void put_page(struct page *page); -#ifdef CONFIG_MMU void split_page(struct page *page, unsigned int order); -#else -static inline void split_page(struct page *page, unsigned int order) {} -#endif /* * Multiple processes may "see" the same page. E.g. for untouched -- cgit v1.2.3 From 7835e98b2e3c66dba79cb0ff8ebb90a2fe030c29 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 22 Mar 2006 00:08:40 -0800 Subject: [PATCH] remove set_page_count() outside mm/ set_page_count usage outside mm/ is limited to setting the refcount to 1. Remove set_page_count from outside mm/, and replace those users with init_page_count() and set_page_refcounted(). This allows more debug checking, and tighter control on how code is allowed to play around with page->_count. Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3d84b7a35e0d..7d8c127daad7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -307,8 +307,6 @@ static inline int get_page_unless_zero(struct page *page) return atomic_inc_not_zero(&page->_count); } -#define set_page_count(p,v) atomic_set(&(p)->_count, (v)) - extern void FASTCALL(__page_cache_release(struct page *)); static inline int page_count(struct page *page) @@ -325,6 +323,15 @@ static inline void get_page(struct page *page) atomic_inc(&page->_count); } +/* + * Setup the page count before being freed into the page allocator for + * the first time (boot or memory hotplug) + */ +static inline void init_page_count(struct page *page) +{ + atomic_set(&page->_count, 1); +} + void put_page(struct page *page); void split_page(struct page *page, unsigned int order); -- cgit v1.2.3 From 617d2214ee06c209e5c375c280d50abace8058e1 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 22 Mar 2006 00:08:43 -0800 Subject: [PATCH] mm: optimise page_count Optimise page_count compound page test and make it consistent with similar functions. Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7d8c127daad7..6aa016f1d3ae 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -311,7 +311,7 @@ extern void FASTCALL(__page_cache_release(struct page *)); static inline int page_count(struct page *page) { - if (PageCompound(page)) + if (unlikely(PageCompound(page))) page = (struct page *)page_private(page); return atomic_read(&page->_count); } -- cgit v1.2.3 From 8f860591ffb29738cf5539b6fbf27f50dcdeb380 Mon Sep 17 00:00:00 2001 From: "Zhang, Yanmin" Date: Wed, 22 Mar 2006 00:08:50 -0800 Subject: [PATCH] Enable mprotect on huge pages 2.6.16-rc3 uses hugetlb on-demand paging, but it doesn_t support hugetlb mprotect. From: David Gibson Remove a test from the mprotect() path which checks that the mprotect()ed range on a hugepage VMA is hugepage aligned (yes, really, the sense of is_aligned_hugepage_range() is the opposite of what you'd guess :-/). In fact, we don't need this test. If the given addresses match the beginning/end of a hugepage VMA they must already be suitably aligned. If they don't, then mprotect_fixup() will attempt to split the VMA. The very first test in split_vma() will check for a badly aligned address on a hugepage VMA and return -EINVAL if necessary. From: "Chen, Kenneth W" On i386 and x86-64, pte flag _PAGE_PSE collides with _PAGE_PROTNONE. The identify of hugetlb pte is lost when changing page protection via mprotect. A page fault occurs later will trigger a bug check in huge_pte_alloc(). The fix is to always make new pte a hugetlb pte and also to clean up legacy code where _PAGE_PRESENT is forced on in the pre-faulting day. Signed-off-by: Zhang Yanmin Cc: David Gibson Cc: "David S. Miller" Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: William Lee Irwin III Signed-off-by: Ken Chen Signed-off-by: Nishanth Aravamudan Cc: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 68d82ad6b17c..fa83836b63d2 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -41,6 +41,8 @@ struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write); int is_aligned_hugepage_range(unsigned long addr, unsigned long len); int pmd_huge(pmd_t pmd); +void hugetlb_change_protection(struct vm_area_struct *vma, + unsigned long address, unsigned long end, pgprot_t newprot); #ifndef ARCH_HAS_HUGEPAGE_ONLY_RANGE #define is_hugepage_only_range(mm, addr, len) 0 @@ -101,6 +103,8 @@ static inline unsigned long hugetlb_total_pages(void) #define free_huge_page(p) ({ (void)(p); BUG(); }) #define hugetlb_fault(mm, vma, addr, write) ({ BUG(); 0; }) +#define hugetlb_change_protection(vma, address, end, newprot) + #ifndef HPAGE_MASK #define HPAGE_MASK PAGE_MASK /* Keep the compiler happy */ #define HPAGE_SIZE PAGE_SIZE -- cgit v1.2.3 From b45b5bd65f668a665db40d093e4e1fe563533608 Mon Sep 17 00:00:00 2001 From: David Gibson Date: Wed, 22 Mar 2006 00:08:55 -0800 Subject: [PATCH] hugepage: Strict page reservation for hugepage inodes These days, hugepages are demand-allocated at first fault time. There's a somewhat dubious (and racy) heuristic when making a new mmap() to check if there are enough available hugepages to fully satisfy that mapping. A particularly obvious case where the heuristic breaks down is where a process maps its hugepages not as a single chunk, but as a bunch of individually mmap()ed (or shmat()ed) blocks without touching and instantiating the pages in between allocations. In this case the size of each block is compared against the total number of available hugepages. It's thus easy for the process to become overcommitted, because each block mapping will succeed, although the total number of hugepages required by all blocks exceeds the number available. In particular, this defeats such a program which will detect a mapping failure and adjust its hugepage usage downward accordingly. The patch below addresses this problem, by strictly reserving a number of physical hugepages for hugepage inodes which have been mapped, but not instatiated. MAP_SHARED mappings are thus "safe" - they will fail on mmap(), not later with an OOM SIGKILL. MAP_PRIVATE mappings can still trigger an OOM. (Actually SHARED mappings can technically still OOM, but only if the sysadmin explicitly reduces the hugepage pool between mapping and instantiation) This patch appears to address the problem at hand - it allows DB2 to start correctly, for instance, which previously suffered the failure described above. This patch causes no regressions on the libhugetblfs testsuite, and makes a test (designed to catch this problem) pass which previously failed (ppc64, POWER5). Signed-off-by: David Gibson Cc: William Lee Irwin III Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index fa83836b63d2..cafe73eecb05 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -20,7 +20,6 @@ void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long) int hugetlb_prefault(struct address_space *, struct vm_area_struct *); int hugetlb_report_meminfo(char *); int hugetlb_report_node_meminfo(int, char *); -int is_hugepage_mem_enough(size_t); unsigned long hugetlb_total_pages(void); struct page *alloc_huge_page(struct vm_area_struct *, unsigned long); void free_huge_page(struct page *); @@ -89,7 +88,6 @@ static inline unsigned long hugetlb_total_pages(void) #define copy_hugetlb_page_range(src, dst, vma) ({ BUG(); 0; }) #define hugetlb_prefault(mapping, vma) ({ BUG(); 0; }) #define unmap_hugepage_range(vma, start, end) BUG() -#define is_hugepage_mem_enough(size) 0 #define hugetlb_report_meminfo(buf) 0 #define hugetlb_report_node_meminfo(n, buf) 0 #define follow_huge_pmd(mm, addr, pmd, write) NULL @@ -132,6 +130,8 @@ struct hugetlbfs_sb_info { struct hugetlbfs_inode_info { struct shared_policy policy; + /* Protected by the (global) hugetlb_lock */ + unsigned long prereserved_hpages; struct inode vfs_inode; }; @@ -148,6 +148,10 @@ static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb) extern struct file_operations hugetlbfs_file_operations; extern struct vm_operations_struct hugetlb_vm_ops; struct file *hugetlb_zero_setup(size_t); +int hugetlb_extend_reservation(struct hugetlbfs_inode_info *info, + unsigned long atleast_hpages); +void hugetlb_truncate_reservation(struct hugetlbfs_inode_info *info, + unsigned long atmost_hpages); int hugetlb_get_quota(struct address_space *mapping); void hugetlb_put_quota(struct address_space *mapping); -- cgit v1.2.3 From 27a85ef1b81300cfff06b4c8037e9914dfb09acc Mon Sep 17 00:00:00 2001 From: David Gibson Date: Wed, 22 Mar 2006 00:08:56 -0800 Subject: [PATCH] hugepage: Make {alloc,free}_huge_page() local Originally, mm/hugetlb.c just handled the hugepage physical allocation path and its {alloc,free}_huge_page() functions were used from the arch specific hugepage code. These days those functions are only used with mm/hugetlb.c itself. Therefore, this patch makes them static and removes their prototypes from hugetlb.h. This requires a small rearrangement of code in mm/hugetlb.c to avoid a forward declaration. This patch causes no regressions on the libhugetlbfs testsuite (ppc64, POWER5). Signed-off-by: David Gibson Cc: William Lee Irwin III Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index cafe73eecb05..5d84c368ffe4 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -21,8 +21,6 @@ int hugetlb_prefault(struct address_space *, struct vm_area_struct *); int hugetlb_report_meminfo(char *); int hugetlb_report_node_meminfo(int, char *); unsigned long hugetlb_total_pages(void); -struct page *alloc_huge_page(struct vm_area_struct *, unsigned long); -void free_huge_page(struct page *); int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, int write_access); @@ -97,8 +95,6 @@ static inline unsigned long hugetlb_total_pages(void) #define is_hugepage_only_range(mm, addr, len) 0 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) \ do { } while (0) -#define alloc_huge_page(vma, addr) ({ NULL; }) -#define free_huge_page(p) ({ (void)(p); BUG(); }) #define hugetlb_fault(mm, vma, addr, write) ({ BUG(); 0; }) #define hugetlb_change_protection(vma, address, end, newprot) -- cgit v1.2.3 From 9da61aef0fd5b17dd4bf4baf33db12c470def774 Mon Sep 17 00:00:00 2001 From: David Gibson Date: Wed, 22 Mar 2006 00:08:57 -0800 Subject: [PATCH] hugepage: Fix hugepage logic in free_pgtables() free_pgtables() has special logic to call hugetlb_free_pgd_range() instead of the normal free_pgd_range() on hugepage VMAs. However, the test it uses to do so is incorrect: it calls is_hugepage_only_range on a hugepage sized range at the start of the vma. is_hugepage_only_range() will return true if the given range has any intersection with a hugepage address region, and in this case the given region need not be hugepage aligned. So, for example, this test can return true if called on, say, a 4k VMA immediately preceding a (nicely aligned) hugepage VMA. At present we get away with this because the powerpc version of hugetlb_free_pgd_range() is just a call to free_pgd_range(). On ia64 (the only other arch with a non-trivial is_hugepage_only_range()) we get away with it for a different reason; the hugepage area is not contiguous with the rest of the user address space, and VMAs are not permitted in between, so the test can't return a false positive there. Nonetheless this should be fixed. We do that in the patch below by replacing the is_hugepage_only_range() test with an explicit test of the VMA using is_vm_hugetlb_page(). This in turn changes behaviour for platforms where is_hugepage_only_range() returns false always (everything except powerpc and ia64). We address this by ensuring that hugetlb_free_pgd_range() is defined to be identical to free_pgd_range() (instead of a no-op) on everything except ia64. Even so, it will prevent some otherwise possible coalescing of calls down to free_pgd_range(). Since this only happens for hugepage VMAs, removing this small optimization seems unlikely to cause any trouble. This patch causes no regressions on the libhugetlbfs testsuite - ppc64 POWER5 (8-way), ppc64 G5 (2-way) and i386 Pentium M (UP). Signed-off-by: David Gibson Cc: William Lee Irwin III Acked-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 5d84c368ffe4..e465fbf1ef5f 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -43,8 +43,10 @@ void hugetlb_change_protection(struct vm_area_struct *vma, #ifndef ARCH_HAS_HUGEPAGE_ONLY_RANGE #define is_hugepage_only_range(mm, addr, len) 0 -#define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) \ - do { } while (0) +#endif + +#ifndef ARCH_HAS_HUGETLB_FREE_PGD_RANGE +#define hugetlb_free_pgd_range free_pgd_range #endif #ifndef ARCH_HAS_PREPARE_HUGEPAGE_RANGE @@ -93,8 +95,7 @@ static inline unsigned long hugetlb_total_pages(void) #define prepare_hugepage_range(addr, len) (-EINVAL) #define pmd_huge(x) 0 #define is_hugepage_only_range(mm, addr, len) 0 -#define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) \ - do { } while (0) +#define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; }) #define hugetlb_fault(mm, vma, addr, write) ({ BUG(); 0; }) #define hugetlb_change_protection(vma, address, end, newprot) -- cgit v1.2.3 From 3915bcf38fe0b6d130b4bbde97804f29a0becf32 Mon Sep 17 00:00:00 2001 From: David Gibson Date: Wed, 22 Mar 2006 00:08:59 -0800 Subject: [PATCH] hugepage: Move hugetlb_free_pgd_range() prototype to hugetlb.h The optional hugepage callback, hugetlb_free_pgd_range() is presently implemented non-trivially only on ia64 (but I plan to add one for powerpc shortly). It has its own prototype for the function in asm-ia64/pgtable.h. However, since the function is called from generic code, it make sense for its prototype to be in the generic hugetlb.h header file, as the protypes other arch callbacks already are (prepare_hugepage_range(), set_huge_pte_at(), etc.). This patch makes it so. Signed-off-by: David Gibson Cc: William Lee Irwin III Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index e465fbf1ef5f..5db25ffdb3eb 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -47,6 +47,10 @@ void hugetlb_change_protection(struct vm_area_struct *vma, #ifndef ARCH_HAS_HUGETLB_FREE_PGD_RANGE #define hugetlb_free_pgd_range free_pgd_range +#else +void hugetlb_free_pgd_range(struct mmu_gather **tlb, unsigned long addr, + unsigned long end, unsigned long floor, + unsigned long ceiling); #endif #ifndef ARCH_HAS_PREPARE_HUGEPAGE_RANGE -- cgit v1.2.3 From 42b88befd6e0dae1a5fe04c03925037fa890e1f3 Mon Sep 17 00:00:00 2001 From: David Gibson Date: Wed, 22 Mar 2006 00:09:01 -0800 Subject: [PATCH] hugepage: is_aligned_hugepage_range() cleanup Quite a long time back, prepare_hugepage_range() replaced is_aligned_hugepage_range() as the callback from mm/mmap.c to arch code to verify if an address range is suitable for a hugepage mapping. is_aligned_hugepage_range() stuck around, but only to implement prepare_hugepage_range() on archs which didn't implement their own. Most archs (everything except ia64 and powerpc) used the same implementation of is_aligned_hugepage_range(). On powerpc, which implements its own prepare_hugepage_range(), the custom version was never used. In addition, "is_aligned_hugepage_range()" was a bad name, because it suggests it returns true iff the given range is a good hugepage range, whereas in fact it returns 0-or-error (so the sense is reversed). This patch cleans up by abolishing is_aligned_hugepage_range(). Instead prepare_hugepage_range() is defined directly. Most archs use the default version, which simply checks the given region is aligned to the size of a hugepage. ia64 and powerpc define custom versions. The ia64 one simply checks that the range is in the correct address space region in addition to being suitably aligned. The powerpc version (just as previously) checks for suitable addresses, and if necessary performs low-level MMU frobbing to set up new areas for use by hugepages. No libhugetlbfs testsuite regressions on ppc64 (POWER5 LPAR). Signed-off-by: David Gibson Signed-off-by: Zhang Yanmin Cc: "David S. Miller" Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: William Lee Irwin III Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 5db25ffdb3eb..d6f1019625af 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -36,7 +36,6 @@ struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, int write); struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write); -int is_aligned_hugepage_range(unsigned long addr, unsigned long len); int pmd_huge(pmd_t pmd); void hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot); @@ -54,8 +53,18 @@ void hugetlb_free_pgd_range(struct mmu_gather **tlb, unsigned long addr, #endif #ifndef ARCH_HAS_PREPARE_HUGEPAGE_RANGE -#define prepare_hugepage_range(addr, len) \ - is_aligned_hugepage_range(addr, len) +/* + * If the arch doesn't supply something else, assume that hugepage + * size aligned regions are ok without further preparation. + */ +static inline int prepare_hugepage_range(unsigned long addr, unsigned long len) +{ + if (len & ~HPAGE_MASK) + return -EINVAL; + if (addr & ~HPAGE_MASK) + return -EINVAL; + return 0; +} #else int prepare_hugepage_range(unsigned long addr, unsigned long len); #endif @@ -95,7 +104,6 @@ static inline unsigned long hugetlb_total_pages(void) #define hugetlb_report_meminfo(buf) 0 #define hugetlb_report_node_meminfo(n, buf) 0 #define follow_huge_pmd(mm, addr, pmd, write) NULL -#define is_aligned_hugepage_range(addr, len) 0 #define prepare_hugepage_range(addr, len) (-EINVAL) #define pmd_huge(x) 0 #define is_hugepage_only_range(mm, addr, len) 0 -- cgit v1.2.3 From b20a35035f983f4ac7e29c4a68f30e43510007e0 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 22 Mar 2006 00:09:12 -0800 Subject: [PATCH] page migration reorg Centralize the page migration functions in anticipation of additional tinkering. Creates a new file mm/migrate.c 1. Extract buffer_migrate_page() from fs/buffer.c 2. Extract central migration code from vmscan.c 3. Extract some components from mempolicy.c 4. Export pageout() and remove_from_swap() from vmscan.c 5. Make it possible to configure NUMA systems without page migration and non-NUMA systems with page migration. I had to so some #ifdeffing in mempolicy.c that may need a cleanup. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 36 ++++++++++++++++++++++++++++++++++++ include/linux/swap.h | 34 +++++++++++++++------------------- 2 files changed, 51 insertions(+), 19 deletions(-) create mode 100644 include/linux/migrate.h (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h new file mode 100644 index 000000000000..7d09962c3c0b --- /dev/null +++ b/include/linux/migrate.h @@ -0,0 +1,36 @@ +#ifndef _LINUX_MIGRATE_H +#define _LINUX_MIGRATE_H + +#include +#include + +#ifdef CONFIG_MIGRATION +extern int isolate_lru_page(struct page *p, struct list_head *pagelist); +extern int putback_lru_pages(struct list_head *l); +extern int migrate_page(struct page *, struct page *); +extern void migrate_page_copy(struct page *, struct page *); +extern int migrate_page_remove_references(struct page *, struct page *, int); +extern int migrate_pages(struct list_head *l, struct list_head *t, + struct list_head *moved, struct list_head *failed); +int migrate_pages_to(struct list_head *pagelist, + struct vm_area_struct *vma, int dest); +extern int fail_migrate_page(struct page *, struct page *); + +extern int migrate_prep(void); + +#else + +static inline int isolate_lru_page(struct page *p, struct list_head *list) + { return -ENOSYS; } +static inline int putback_lru_pages(struct list_head *l) { return 0; } +static inline int migrate_pages(struct list_head *l, struct list_head *t, + struct list_head *moved, struct list_head *failed) { return -ENOSYS; } + +static inline int migrate_prep(void) { return -ENOSYS; } + +/* Possible settings for the migrate_page() method in address_operations */ +#define migrate_page NULL +#define fail_migrate_page NULL + +#endif /* CONFIG_MIGRATION */ +#endif /* _LINUX_MIGRATE_H */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 3dc6c89c49b8..12415dd94451 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -175,6 +175,21 @@ extern void swap_setup(void); extern unsigned long try_to_free_pages(struct zone **, gfp_t); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; +extern int remove_mapping(struct address_space *mapping, struct page *page); + +/* possible outcome of pageout() */ +typedef enum { + /* failed to write page out, page is locked */ + PAGE_KEEP, + /* move page to the active list, page is locked */ + PAGE_ACTIVATE, + /* page has been sent to the disk successfully, page is unlocked */ + PAGE_SUCCESS, + /* page is clean and locked */ + PAGE_CLEAN, +} pageout_t; + +extern pageout_t pageout(struct page *page, struct address_space *mapping); #ifdef CONFIG_NUMA extern int zone_reclaim_mode; @@ -188,25 +203,6 @@ static inline int zone_reclaim(struct zone *z, gfp_t mask, unsigned int order) } #endif -#ifdef CONFIG_MIGRATION -extern int isolate_lru_page(struct page *p); -extern unsigned long putback_lru_pages(struct list_head *l); -extern int migrate_page(struct page *, struct page *); -extern void migrate_page_copy(struct page *, struct page *); -extern int migrate_page_remove_references(struct page *, struct page *, int); -extern unsigned long migrate_pages(struct list_head *l, struct list_head *t, - struct list_head *moved, struct list_head *failed); -extern int fail_migrate_page(struct page *, struct page *); -#else -static inline int isolate_lru_page(struct page *p) { return -ENOSYS; } -static inline int putback_lru_pages(struct list_head *l) { return 0; } -static inline int migrate_pages(struct list_head *l, struct list_head *t, - struct list_head *moved, struct list_head *failed) { return -ENOSYS; } -/* Possible settings for the migrate_page() method in address_operations */ -#define migrate_page NULL -#define fail_migrate_page NULL -#endif - #ifdef CONFIG_MMU /* linux/mm/shmem.c */ extern int shmem_unuse(swp_entry_t entry, struct page *page); -- cgit v1.2.3 From a45049c51ce6a3fecf2a909b591b28164c927112 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 22 Mar 2006 13:55:40 -0800 Subject: [NETFILTER]: x_tables: set the protocol family in x_tables targets/matches Set the family field in xt_[matches|targets] registered. Signed-off-by: Pablo Neira Ayuso Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/x_tables.h | 8 ++++---- include/linux/netfilter_arp/arp_tables.h | 6 ++++-- include/linux/netfilter_ipv4/ip_tables.h | 14 +++++++++----- include/linux/netfilter_ipv6/ip6_tables.h | 14 +++++++++----- 4 files changed, 26 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 46a0f974f87c..bf71efb63007 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -220,10 +220,10 @@ struct xt_table_info char *entries[NR_CPUS]; }; -extern int xt_register_target(int af, struct xt_target *target); -extern void xt_unregister_target(int af, struct xt_target *target); -extern int xt_register_match(int af, struct xt_match *target); -extern void xt_unregister_match(int af, struct xt_match *target); +extern int xt_register_target(struct xt_target *target); +extern void xt_unregister_target(struct xt_target *target); +extern int xt_register_match(struct xt_match *target); +extern void xt_unregister_match(struct xt_match *target); extern int xt_check_match(const struct xt_match *match, unsigned short family, unsigned int size, const char *table, unsigned int hook, diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index fd21796e5131..a27be05f67f0 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -263,8 +263,10 @@ static __inline__ struct arpt_entry_target *arpt_get_target(struct arpt_entry *e */ #ifdef __KERNEL__ -#define arpt_register_target(tgt) xt_register_target(NF_ARP, tgt) -#define arpt_unregister_target(tgt) xt_unregister_target(NF_ARP, tgt) +#define arpt_register_target(tgt) \ +({ (tgt)->family = NF_ARP; \ + xt_register_target(tgt); }) +#define arpt_unregister_target(tgt) xt_unregister_target(tgt) extern int arpt_register_table(struct arpt_table *table, const struct arpt_replace *repl); diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index 76ba24b68515..ee262b5344e1 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -321,11 +321,15 @@ ipt_get_target(struct ipt_entry *e) #include extern void ipt_init(void) __init; -#define ipt_register_target(tgt) xt_register_target(AF_INET, tgt) -#define ipt_unregister_target(tgt) xt_unregister_target(AF_INET, tgt) - -#define ipt_register_match(mtch) xt_register_match(AF_INET, mtch) -#define ipt_unregister_match(mtch) xt_unregister_match(AF_INET, mtch) +#define ipt_register_target(tgt) \ +({ (tgt)->family = AF_INET; \ + xt_register_target(tgt); }) +#define ipt_unregister_target(tgt) xt_unregister_target(tgt) + +#define ipt_register_match(mtch) \ +({ (mtch)->family = AF_INET; \ + xt_register_match(mtch); }) +#define ipt_unregister_match(mtch) xt_unregister_match(mtch) //#define ipt_register_table(tbl, repl) xt_register_table(AF_INET, tbl, repl) //#define ipt_unregister_table(tbl) xt_unregister_table(AF_INET, tbl) diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index f249b574f0fa..7107f942eb05 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -334,11 +334,15 @@ ip6t_get_target(struct ip6t_entry *e) #include extern void ip6t_init(void) __init; -#define ip6t_register_target(tgt) xt_register_target(AF_INET6, tgt) -#define ip6t_unregister_target(tgt) xt_unregister_target(AF_INET6, tgt) - -#define ip6t_register_match(match) xt_register_match(AF_INET6, match) -#define ip6t_unregister_match(match) xt_unregister_match(AF_INET6, match) +#define ip6t_register_target(tgt) \ +({ (tgt)->family = AF_INET6; \ + xt_register_target(tgt); }) +#define ip6t_unregister_target(tgt) xt_unregister_target(tgt) + +#define ip6t_register_match(match) \ +({ (match)->family = AF_INET6; \ + xt_register_match(match); }) +#define ip6t_unregister_match(match) xt_unregister_match(match) extern int ip6t_register_table(struct ip6t_table *table, const struct ip6t_replace *repl); -- cgit v1.2.3 From 1e30a014e311e627b91489ff5ec1b54496d308af Mon Sep 17 00:00:00 2001 From: Dmitry Mishin Date: Wed, 22 Mar 2006 13:56:56 -0800 Subject: [NETFILTER]: futher {ip,ip6,arp}_tables unification This patch moves {ip,ip6,arp}t_entry_{match,target} definitions to x_tables.h. This move simplifies code and future compatibility fixes. Signed-off-by: Dmitry Mishin Acked-off-by: Kirill Korotaev Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/x_tables.h | 56 +++++++++++++++++++++++++++++ include/linux/netfilter_arp/arp_tables.h | 31 ++--------------- include/linux/netfilter_ipv4/ip_tables.h | 58 ++----------------------------- include/linux/netfilter_ipv6/ip6_tables.h | 57 ++---------------------------- 4 files changed, 64 insertions(+), 138 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index bf71efb63007..1350e47b0234 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -4,6 +4,62 @@ #define XT_FUNCTION_MAXNAMELEN 30 #define XT_TABLE_MAXNAMELEN 32 +struct xt_entry_match +{ + union { + struct { + u_int16_t match_size; + + /* Used by userspace */ + char name[XT_FUNCTION_MAXNAMELEN-1]; + + u_int8_t revision; + } user; + struct { + u_int16_t match_size; + + /* Used inside the kernel */ + struct xt_match *match; + } kernel; + + /* Total length */ + u_int16_t match_size; + } u; + + unsigned char data[0]; +}; + +struct xt_entry_target +{ + union { + struct { + u_int16_t target_size; + + /* Used by userspace */ + char name[XT_FUNCTION_MAXNAMELEN-1]; + + u_int8_t revision; + } user; + struct { + u_int16_t target_size; + + /* Used inside the kernel */ + struct xt_target *target; + } kernel; + + /* Total length */ + u_int16_t target_size; + } u; + + unsigned char data[0]; +}; + +struct xt_standard_target +{ + struct xt_entry_target target; + int verdict; +}; + /* The argument to IPT_SO_GET_REVISION_*. Returns highest revision * kernel supports, if >= revision. */ struct xt_get_revision diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index a27be05f67f0..62cc27daca4e 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -65,35 +65,8 @@ struct arpt_arp { u_int16_t invflags; }; -struct arpt_entry_target -{ - union { - struct { - u_int16_t target_size; - - /* Used by userspace */ - char name[ARPT_FUNCTION_MAXNAMELEN-1]; - u_int8_t revision; - } user; - struct { - u_int16_t target_size; - - /* Used inside the kernel */ - struct arpt_target *target; - } kernel; - - /* Total length */ - u_int16_t target_size; - } u; - - unsigned char data[0]; -}; - -struct arpt_standard_target -{ - struct arpt_entry_target target; - int verdict; -}; +#define arpt_entry_target xt_entry_target +#define arpt_standard_target xt_standard_target /* Values for "flag" field in struct arpt_ip (general arp structure). * No flags defined yet. diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index ee262b5344e1..d5b8c0d6a12b 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -52,61 +52,9 @@ struct ipt_ip { u_int8_t invflags; }; -struct ipt_entry_match -{ - union { - struct { - u_int16_t match_size; - - /* Used by userspace */ - char name[IPT_FUNCTION_MAXNAMELEN-1]; - - u_int8_t revision; - } user; - struct { - u_int16_t match_size; - - /* Used inside the kernel */ - struct ipt_match *match; - } kernel; - - /* Total length */ - u_int16_t match_size; - } u; - - unsigned char data[0]; -}; - -struct ipt_entry_target -{ - union { - struct { - u_int16_t target_size; - - /* Used by userspace */ - char name[IPT_FUNCTION_MAXNAMELEN-1]; - - u_int8_t revision; - } user; - struct { - u_int16_t target_size; - - /* Used inside the kernel */ - struct ipt_target *target; - } kernel; - - /* Total length */ - u_int16_t target_size; - } u; - - unsigned char data[0]; -}; - -struct ipt_standard_target -{ - struct ipt_entry_target target; - int verdict; -}; +#define ipt_entry_match xt_entry_match +#define ipt_entry_target xt_entry_target +#define ipt_standard_target xt_standard_target #define ipt_counters xt_counters diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 7107f942eb05..d0d5d1ee4be3 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -56,60 +56,9 @@ struct ip6t_ip6 { u_int8_t invflags; }; -/* FIXME: If alignment in kernel different from userspace? --RR */ -struct ip6t_entry_match -{ - union { - struct { - u_int16_t match_size; - - /* Used by userspace */ - char name[IP6T_FUNCTION_MAXNAMELEN-1]; - u_int8_t revision; - } user; - struct { - u_int16_t match_size; - - /* Used inside the kernel */ - struct ip6t_match *match; - } kernel; - - /* Total length */ - u_int16_t match_size; - } u; - - unsigned char data[0]; -}; - -struct ip6t_entry_target -{ - union { - struct { - u_int16_t target_size; - - /* Used by userspace */ - char name[IP6T_FUNCTION_MAXNAMELEN-1]; - u_int8_t revision; - } user; - struct { - u_int16_t target_size; - - /* Used inside the kernel */ - struct ip6t_target *target; - } kernel; - - /* Total length */ - u_int16_t target_size; - } u; - - unsigned char data[0]; -}; - -struct ip6t_standard_target -{ - struct ip6t_entry_target target; - int verdict; -}; +#define ip6t_entry_match xt_entry_match +#define ip6t_entry_target xt_entry_target +#define ip6t_standard_target xt_standard_target #define ip6t_counters xt_counters -- cgit v1.2.3